diff options
103 files changed, 3351 insertions, 2552 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdadb0bb6cec..c3ba4d475174 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -203,6 +203,7 @@ enum btf_field_type { BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), BPF_WORKQUEUE = (1 << 10), + BPF_UPTR = (1 << 11), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -322,6 +323,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "kptr"; case BPF_KPTR_PERCPU: return "percpu_kptr"; + case BPF_UPTR: + return "uptr"; case BPF_LIST_HEAD: return "bpf_list_head"; case BPF_LIST_NODE: @@ -350,6 +353,7 @@ static inline u32 btf_field_type_size(enum btf_field_type type) case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); @@ -379,6 +383,7 @@ static inline u32 btf_field_type_align(enum btf_field_type type) case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); @@ -419,6 +424,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: break; default: WARN_ON_ONCE(1); @@ -507,6 +513,25 @@ static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src bpf_obj_memcpy(map->record, dst, src, map->value_size, true); } +static inline void bpf_obj_swap_uptrs(const struct btf_record *rec, void *dst, void *src) +{ + unsigned long *src_uptr, *dst_uptr; + const struct btf_field *field; + int i; + + if (!btf_record_has_field(rec, BPF_UPTR)) + return; + + for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) { + if (field->type != BPF_UPTR) + continue; + + src_uptr = src + field->offset; + dst_uptr = dst + field->offset; + swap(*src_uptr, *dst_uptr); + } +} + static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size) { u32 curr_off = 0; @@ -1300,8 +1325,12 @@ void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_JIT -int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); -int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); +int bpf_trampoline_link_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog); +int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); @@ -1382,12 +1411,14 @@ void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link, - struct bpf_trampoline *tr) + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { return -ENOTSUPP; } static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, - struct bpf_trampoline *tr) + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { return -ENOTSUPP; } @@ -1491,6 +1522,9 @@ struct bpf_prog_aux { bool xdp_has_frags; bool exception_cb; bool exception_boundary; + bool is_extended; /* true if extended by freplace program */ + u64 prog_array_member_cnt; /* counts how many times as member of prog_array */ + struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */ struct bpf_arena *arena; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index dcddb0aef7d8..ab7244d8108f 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -77,7 +77,13 @@ struct bpf_local_storage_elem { struct hlist_node map_node; /* Linked to bpf_local_storage_map */ struct hlist_node snode; /* Linked to bpf_local_storage */ struct bpf_local_storage __rcu *local_storage; - struct rcu_head rcu; + union { + struct rcu_head rcu; + struct hlist_node free_node; /* used to postpone + * bpf_selem_free + * after raw_spin_unlock + */ + }; /* 8 bytes hole */ /* The data is stored in another cacheline to minimize * the number of cachelines access during a cache hit. @@ -181,7 +187,7 @@ void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, - bool charge_mem, gfp_t gfp_flags); + bool charge_mem, bool swap_uptrs, gfp_t gfp_flags); void bpf_selem_free(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map *smap, @@ -195,7 +201,7 @@ bpf_local_storage_alloc(void *owner, struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags, gfp_t gfp_flags); + void *value, u64 map_flags, bool swap_uptrs, gfp_t gfp_flags); u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map); diff --git a/include/linux/btf.h b/include/linux/btf.h index b8a583194c4a..631060e3ad14 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -75,6 +75,7 @@ #define KF_ITER_NEXT (1 << 9) /* kfunc implements BPF iter next method */ #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ #define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */ +#define KF_FASTCALL (1 << 12) /* kfunc supports bpf_fastcall protocol */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index c0e3e1426a82..139bdececdcf 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -283,5 +283,6 @@ extern u32 btf_tracing_ids[]; extern u32 bpf_cgroup_btf_id[]; extern u32 bpf_local_storage_map_btf_id[]; extern u32 btf_bpf_map_id[]; +extern u32 bpf_kmem_cache_btf_id[]; #endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4a939c90dc2e..f28b6527e815 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1973,6 +1973,8 @@ union bpf_attr { * program. * Return * The SMP id of the processor running the program. + * Attributes + * __bpf_fastcall * * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) * Description @@ -3104,10 +3106,6 @@ union bpf_attr { * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration * option, and in this case it only works on functions tagged with * **ALLOW_ERROR_INJECTION** in the kernel code. - * - * Also, the helper is only available for the architectures having - * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, - * x86 architecture is the only one to support this feature. * Return * 0 * @@ -5372,7 +5370,7 @@ union bpf_attr { * Currently, the **flags** must be 0. Currently, nr_loops is * limited to 1 << 23 (~8 million) loops. * - * long (\*callback_fn)(u32 index, void \*ctx); + * long (\*callback_fn)(u64 index, void \*ctx); * * where **index** is the current index in the loop. The index * is zero-indexed. diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 9b9c151b5c82..105328f0b9c0 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -52,3 +52,4 @@ obj-$(CONFIG_BPF_PRELOAD) += preload/ obj-$(CONFIG_BPF_SYSCALL) += relo_core.o obj-$(CONFIG_BPF_SYSCALL) += btf_iter.o obj-$(CONFIG_BPF_SYSCALL) += btf_relocate.o +obj-$(CONFIG_BPF_SYSCALL) += kmem_cache_iter.o diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 79660e3fca4c..6cdbb4c33d31 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -947,22 +947,44 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map, struct file *map_file, int fd) { struct bpf_prog *prog = bpf_prog_get(fd); + bool is_extended; if (IS_ERR(prog)) return prog; - if (!bpf_prog_map_compatible(map, prog)) { + if (prog->type == BPF_PROG_TYPE_EXT || + !bpf_prog_map_compatible(map, prog)) { bpf_prog_put(prog); return ERR_PTR(-EINVAL); } + mutex_lock(&prog->aux->ext_mutex); + is_extended = prog->aux->is_extended; + if (!is_extended) + prog->aux->prog_array_member_cnt++; + mutex_unlock(&prog->aux->ext_mutex); + if (is_extended) { + /* Extended prog can not be tail callee. It's to prevent a + * potential infinite loop like: + * tail callee prog entry -> tail callee prog subprog -> + * freplace prog entry --tailcall-> tail callee prog entry. + */ + bpf_prog_put(prog); + return ERR_PTR(-EBUSY); + } + return prog; } static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { + struct bpf_prog *prog = ptr; + + mutex_lock(&prog->aux->ext_mutex); + prog->aux->prog_array_member_cnt--; + mutex_unlock(&prog->aux->ext_mutex); /* bpf_prog is freed after one RCU or tasks trace grace period */ - bpf_prog_put(ptr); + bpf_prog_put(prog); } static u32 prog_fd_array_sys_lookup_elem(void *ptr) diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c index 28efd0a3f220..20f05de92e9c 100644 --- a/kernel/bpf/bpf_cgrp_storage.c +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -107,7 +107,7 @@ static long bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key, bpf_cgrp_storage_lock(); sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, - value, map_flags, GFP_ATOMIC); + value, map_flags, false, GFP_ATOMIC); bpf_cgrp_storage_unlock(); cgroup_put(cgroup); return PTR_ERR_OR_ZERO(sdata); @@ -181,7 +181,7 @@ BPF_CALL_5(bpf_cgrp_storage_get, struct bpf_map *, map, struct cgroup *, cgroup, if (!percpu_ref_is_dying(&cgroup->self.refcnt) && (flags & BPF_LOCAL_STORAGE_GET_F_CREATE)) sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, - value, BPF_NOEXIST, gfp_flags); + value, BPF_NOEXIST, false, gfp_flags); unlock: bpf_cgrp_storage_unlock(); diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 29da6d3838f6..44ccebc745e5 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -100,7 +100,7 @@ static long bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, sdata = bpf_local_storage_update(file_inode(fd_file(f)), (struct bpf_local_storage_map *)map, - value, map_flags, GFP_ATOMIC); + value, map_flags, false, GFP_ATOMIC); return PTR_ERR_OR_ZERO(sdata); } @@ -154,7 +154,7 @@ BPF_CALL_5(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) { sdata = bpf_local_storage_update( inode, (struct bpf_local_storage_map *)map, value, - BPF_NOEXIST, gfp_flags); + BPF_NOEXIST, false, gfp_flags); return IS_ERR(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index c938dea5ddbf..7e6a0af0afc1 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -73,7 +73,7 @@ static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, - void *value, bool charge_mem, gfp_t gfp_flags) + void *value, bool charge_mem, bool swap_uptrs, gfp_t gfp_flags) { struct bpf_local_storage_elem *selem; @@ -99,9 +99,12 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, } if (selem) { - if (value) + if (value) { + /* No need to call check_and_init_map_value as memory is zero init */ copy_map_value(&smap->map, SDATA(selem)->data, value); - /* No need to call check_and_init_map_value as memory is zero init */ + if (swap_uptrs) + bpf_obj_swap_uptrs(smap->map.record, SDATA(selem)->data, value); + } return selem; } @@ -209,8 +212,12 @@ static void __bpf_selem_free(struct bpf_local_storage_elem *selem, static void bpf_selem_free_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; selem = container_of(rcu, struct bpf_local_storage_elem, rcu); + /* The bpf_local_storage_map_free will wait for rcu_barrier */ + smap = rcu_dereference_check(SDATA(selem)->smap, 1); + bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); bpf_mem_cache_raw_free(selem); } @@ -226,16 +233,25 @@ void bpf_selem_free(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map *smap, bool reuse_now) { - bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); - if (!smap->bpf_ma) { + /* Only task storage has uptrs and task storage + * has moved to bpf_mem_alloc. Meaning smap->bpf_ma == true + * for task storage, so this bpf_obj_free_fields() won't unpin + * any uptr. + */ + bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); __bpf_selem_free(selem, reuse_now); return; } - if (!reuse_now) { - call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu); - } else { + if (reuse_now) { + /* reuse_now == true only happens when the storage owner + * (e.g. task_struct) is being destructed or the map itself + * is being destructed (ie map_free). In both cases, + * no bpf prog can have a hold on the selem. It is + * safe to unpin the uptrs and free the selem now. + */ + bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); /* Instead of using the vanilla call_rcu(), * bpf_mem_cache_free will be able to reuse selem * immediately. @@ -243,6 +259,26 @@ void bpf_selem_free(struct bpf_local_storage_elem *selem, migrate_disable(); bpf_mem_cache_free(&smap->selem_ma, selem); migrate_enable(); + return; + } + + call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu); +} + +static void bpf_selem_free_list(struct hlist_head *list, bool reuse_now) +{ + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; + struct hlist_node *n; + + /* The "_safe" iteration is needed. + * The loop is not removing the selem from the list + * but bpf_selem_free will use the selem->rcu_head + * which is union-ized with the selem->free_node. + */ + hlist_for_each_entry_safe(selem, n, list, free_node) { + smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); + bpf_selem_free(selem, smap, reuse_now); } } @@ -252,7 +288,7 @@ void bpf_selem_free(struct bpf_local_storage_elem *selem, */ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, - bool uncharge_mem, bool reuse_now) + bool uncharge_mem, struct hlist_head *free_selem_list) { struct bpf_local_storage_map *smap; bool free_local_storage; @@ -296,7 +332,7 @@ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_stor SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); - bpf_selem_free(selem, smap, reuse_now); + hlist_add_head(&selem->free_node, free_selem_list); if (rcu_access_pointer(local_storage->smap) == smap) RCU_INIT_POINTER(local_storage->smap, NULL); @@ -345,6 +381,7 @@ static void bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map *storage_smap; struct bpf_local_storage *local_storage; bool bpf_ma, free_local_storage = false; + HLIST_HEAD(selem_free_list); unsigned long flags; if (unlikely(!selem_linked_to_storage_lockless(selem))) @@ -360,9 +397,11 @@ static void bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, raw_spin_lock_irqsave(&local_storage->lock, flags); if (likely(selem_linked_to_storage(selem))) free_local_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, true, reuse_now); + local_storage, selem, true, &selem_free_list); raw_spin_unlock_irqrestore(&local_storage->lock, flags); + bpf_selem_free_list(&selem_free_list, reuse_now); + if (free_local_storage) bpf_local_storage_free(local_storage, storage_smap, bpf_ma, reuse_now); } @@ -524,11 +563,12 @@ uncharge: */ struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags, gfp_t gfp_flags) + void *value, u64 map_flags, bool swap_uptrs, gfp_t gfp_flags) { struct bpf_local_storage_data *old_sdata = NULL; struct bpf_local_storage_elem *alloc_selem, *selem = NULL; struct bpf_local_storage *local_storage; + HLIST_HEAD(old_selem_free_list); unsigned long flags; int err; @@ -550,7 +590,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, if (err) return ERR_PTR(err); - selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags); + selem = bpf_selem_alloc(smap, owner, value, true, swap_uptrs, gfp_flags); if (!selem) return ERR_PTR(-ENOMEM); @@ -584,7 +624,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, /* A lookup has just been done before and concluded a new selem is * needed. The chance of an unnecessary alloc is unlikely. */ - alloc_selem = selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags); + alloc_selem = selem = bpf_selem_alloc(smap, owner, value, true, swap_uptrs, gfp_flags); if (!alloc_selem) return ERR_PTR(-ENOMEM); @@ -624,11 +664,12 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, if (old_sdata) { bpf_selem_unlink_map(SELEM(old_sdata)); bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), - true, false); + true, &old_selem_free_list); } unlock: raw_spin_unlock_irqrestore(&local_storage->lock, flags); + bpf_selem_free_list(&old_selem_free_list, false); if (alloc_selem) { mem_uncharge(smap, owner, smap->elem_size); bpf_selem_free(alloc_selem, smap, true); @@ -706,6 +747,7 @@ void bpf_local_storage_destroy(struct bpf_local_storage *local_storage) struct bpf_local_storage_map *storage_smap; struct bpf_local_storage_elem *selem; bool bpf_ma, free_storage = false; + HLIST_HEAD(free_selem_list); struct hlist_node *n; unsigned long flags; @@ -734,10 +776,12 @@ void bpf_local_storage_destroy(struct bpf_local_storage *local_storage) * of the loop will set the free_cgroup_storage to true. */ free_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, true, true); + local_storage, selem, true, &free_selem_list); } raw_spin_unlock_irqrestore(&local_storage->lock, flags); + bpf_selem_free_list(&free_selem_list, true); + if (free_storage) bpf_local_storage_free(local_storage, storage_smap, bpf_ma, true); } @@ -883,6 +927,9 @@ void bpf_local_storage_map_free(struct bpf_map *map, synchronize_rcu(); if (smap->bpf_ma) { + rcu_barrier_tasks_trace(); + if (!rcu_trace_implies_rcu_gp()) + rcu_barrier(); bpf_mem_alloc_destroy(&smap->selem_ma); bpf_mem_alloc_destroy(&smap->storage_ma); } diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index adf6dfe0ba68..09705f9988f3 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -129,6 +129,9 @@ static long bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key, struct pid *pid; int fd, err; + if ((map_flags & BPF_F_LOCK) && btf_record_has_field(map->record, BPF_UPTR)) + return -EOPNOTSUPP; + fd = *(int *)key; pid = pidfd_get_pid(fd, &f_flags); if (IS_ERR(pid)) @@ -147,7 +150,7 @@ static long bpf_pid_task_storage_update_elem(struct bpf_map *map, void *key, bpf_task_storage_lock(); sdata = bpf_local_storage_update( task, (struct bpf_local_storage_map *)map, value, map_flags, - GFP_ATOMIC); + true, GFP_ATOMIC); bpf_task_storage_unlock(); err = PTR_ERR_OR_ZERO(sdata); @@ -219,7 +222,7 @@ static void *__bpf_task_storage_get(struct bpf_map *map, (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) && nobusy) { sdata = bpf_local_storage_update( task, (struct bpf_local_storage_map *)map, value, - BPF_NOEXIST, gfp_flags); + BPF_NOEXIST, false, gfp_flags); return IS_ERR(sdata) ? NULL : sdata->data; } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 5cd1c7a23848..ed3219da7181 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -2808,7 +2808,7 @@ static void btf_ref_type_log(struct btf_verifier_env *env, btf_verifier_log(env, "type_id=%u", t->type); } -static struct btf_kind_operations modifier_ops = { +static const struct btf_kind_operations modifier_ops = { .check_meta = btf_ref_type_check_meta, .resolve = btf_modifier_resolve, .check_member = btf_modifier_check_member, @@ -2817,7 +2817,7 @@ static struct btf_kind_operations modifier_ops = { .show = btf_modifier_show, }; -static struct btf_kind_operations ptr_ops = { +static const struct btf_kind_operations ptr_ops = { .check_meta = btf_ref_type_check_meta, .resolve = btf_ptr_resolve, .check_member = btf_ptr_check_member, @@ -2858,7 +2858,7 @@ static void btf_fwd_type_log(struct btf_verifier_env *env, btf_verifier_log(env, "%s", btf_type_kflag(t) ? "union" : "struct"); } -static struct btf_kind_operations fwd_ops = { +static const struct btf_kind_operations fwd_ops = { .check_meta = btf_fwd_check_meta, .resolve = btf_df_resolve, .check_member = btf_df_check_member, @@ -3109,7 +3109,7 @@ static void btf_array_show(const struct btf *btf, const struct btf_type *t, __btf_array_show(btf, t, type_id, data, bits_offset, show); } -static struct btf_kind_operations array_ops = { +static const struct btf_kind_operations array_ops = { .check_meta = btf_array_check_meta, .resolve = btf_array_resolve, .check_member = btf_array_check_member, @@ -3334,7 +3334,7 @@ static int btf_find_struct(const struct btf *btf, const struct btf_type *t, } static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, - u32 off, int sz, struct btf_field_info *info) + u32 off, int sz, struct btf_field_info *info, u32 field_mask) { enum btf_field_type type; u32 res_id; @@ -3358,9 +3358,14 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, type = BPF_KPTR_REF; else if (!strcmp("percpu_kptr", __btf_name_by_offset(btf, t->name_off))) type = BPF_KPTR_PERCPU; + else if (!strcmp("uptr", __btf_name_by_offset(btf, t->name_off))) + type = BPF_UPTR; else return -EINVAL; + if (!(type & field_mask)) + return BTF_FIELD_IGNORE; + /* Get the base type */ t = btf_type_skip_modifiers(btf, t->type, &res_id); /* Only pointer to struct is allowed */ @@ -3502,7 +3507,7 @@ static int btf_get_field_type(const struct btf *btf, const struct btf_type *var_ field_mask_test_name(BPF_REFCOUNT, "bpf_refcount"); /* Only return BPF_KPTR when all other types with matchable names fail */ - if (field_mask & BPF_KPTR && !__btf_type_is_struct(var_type)) { + if (field_mask & (BPF_KPTR | BPF_UPTR) && !__btf_type_is_struct(var_type)) { type = BPF_KPTR_REF; goto end; } @@ -3535,6 +3540,7 @@ static int btf_repeat_fields(struct btf_field_info *info, int info_cnt, case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: case BPF_LIST_HEAD: case BPF_RB_ROOT: break; @@ -3667,8 +3673,9 @@ static int btf_find_field_one(const struct btf *btf, case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: ret = btf_find_kptr(btf, var_type, off, sz, - info_cnt ? &info[0] : &tmp); + info_cnt ? &info[0] : &tmp, field_mask); if (ret < 0) return ret; break; @@ -3991,6 +3998,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: ret = btf_parse_kptr(btf, &rec->fields[i], &info_arr[i]); if (ret < 0) goto end; @@ -4050,12 +4058,28 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) * Hence we only need to ensure that bpf_{list_head,rb_root} ownership * does not form cycles. */ - if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_GRAPH_ROOT)) + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & (BPF_GRAPH_ROOT | BPF_UPTR))) return 0; for (i = 0; i < rec->cnt; i++) { struct btf_struct_meta *meta; + const struct btf_type *t; u32 btf_id; + if (rec->fields[i].type == BPF_UPTR) { + /* The uptr only supports pinning one page and cannot + * point to a kernel struct + */ + if (btf_is_kernel(rec->fields[i].kptr.btf)) + return -EINVAL; + t = btf_type_by_id(rec->fields[i].kptr.btf, + rec->fields[i].kptr.btf_id); + if (!t->size) + return -EINVAL; + if (t->size > PAGE_SIZE) + return -E2BIG; + continue; + } + if (!(rec->fields[i].type & BPF_GRAPH_ROOT)) continue; btf_id = rec->fields[i].graph_root.value_btf_id; @@ -4191,7 +4215,7 @@ static void btf_struct_show(const struct btf *btf, const struct btf_type *t, __btf_struct_show(btf, t, type_id, data, bits_offset, show); } -static struct btf_kind_operations struct_ops = { +static const struct btf_kind_operations struct_ops = { .check_meta = btf_struct_check_meta, .resolve = btf_struct_resolve, .check_member = btf_struct_check_member, @@ -4359,7 +4383,7 @@ static void btf_enum_show(const struct btf *btf, const struct btf_type *t, btf_show_end_type(show); } -static struct btf_kind_operations enum_ops = { +static const struct btf_kind_operations enum_ops = { .check_meta = btf_enum_check_meta, .resolve = btf_df_resolve, .check_member = btf_enum_check_member, @@ -4462,7 +4486,7 @@ static void btf_enum64_show(const struct btf *btf, const struct btf_type *t, btf_show_end_type(show); } -static struct btf_kind_operations enum64_ops = { +static const struct btf_kind_operations enum64_ops = { .check_meta = btf_enum64_check_meta, .resolve = btf_df_resolve, .check_member = btf_enum_check_member, @@ -4540,7 +4564,7 @@ done: btf_verifier_log(env, ")"); } -static struct btf_kind_operations func_proto_ops = { +static const struct btf_kind_operations func_proto_ops = { .check_meta = btf_func_proto_check_meta, .resolve = btf_df_resolve, /* @@ -4598,7 +4622,7 @@ static int btf_func_resolve(struct btf_verifier_env *env, return 0; } -static struct btf_kind_operations func_ops = { +static const struct btf_kind_operations func_ops = { .check_meta = btf_func_check_meta, .resolve = btf_func_resolve, .check_member = btf_df_check_member, @@ -5566,7 +5590,7 @@ btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf) goto free_aof; } - ret = btf_find_kptr(btf, t, 0, 0, &tmp); + ret = btf_find_kptr(btf, t, 0, 0, &tmp, BPF_KPTR); if (ret != BTF_FIELD_FOUND) continue; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 5e77c58e0601..233ea78f8f1b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -131,6 +131,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag INIT_LIST_HEAD_RCU(&fp->aux->ksym_prefix.lnode); #endif mutex_init(&fp->aux->used_maps_mutex); + mutex_init(&fp->aux->ext_mutex); mutex_init(&fp->aux->dst_mutex); return fp; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index ca3f0a2e5ed5..2e82f8d3a76f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2522,6 +2522,25 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid) } /** + * bpf_task_from_vpid - Find a struct task_struct from its vpid by looking it up + * in the pid namespace of the current task. If a task is returned, it must + * either be stored in a map, or released with bpf_task_release(). + * @vpid: The vpid of the task being looked up. + */ +__bpf_kfunc struct task_struct *bpf_task_from_vpid(s32 vpid) +{ + struct task_struct *p; + + rcu_read_lock(); + p = find_task_by_vpid(vpid); + if (p) + p = bpf_task_acquire(p); + rcu_read_unlock(); + + return p; +} + +/** * bpf_dynptr_slice() - Obtain a read-only pointer to the dynptr data. * @p: The dynptr whose data slice to retrieve * @offset: Offset into the dynptr @@ -3034,7 +3053,9 @@ BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU) BTF_ID_FLAGS(func, bpf_task_get_cgroup1, KF_ACQUIRE | KF_RCU | KF_RET_NULL) #endif BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_task_from_vpid, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_throw) +BTF_ID_FLAGS(func, bpf_send_signal_task, KF_TRUSTED_ARGS) BTF_KFUNCS_END(generic_btf_ids) static const struct btf_kfunc_id_set generic_kfunc_set = { @@ -3052,8 +3073,8 @@ BTF_ID(func, bpf_cgroup_release_dtor) #endif BTF_KFUNCS_START(common_btf_ids) -BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx) -BTF_ID_FLAGS(func, bpf_rdonly_cast) +BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx, KF_FASTCALL) +BTF_ID_FLAGS(func, bpf_rdonly_cast, KF_FASTCALL) BTF_ID_FLAGS(func, bpf_rcu_read_lock) BTF_ID_FLAGS(func, bpf_rcu_read_unlock) BTF_ID_FLAGS(func, bpf_dynptr_slice, KF_RET_NULL) @@ -3090,6 +3111,7 @@ BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW) BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_copy_from_user_str, KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_get_kmem_cache) BTF_KFUNCS_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { diff --git a/kernel/bpf/kmem_cache_iter.c b/kernel/bpf/kmem_cache_iter.c new file mode 100644 index 000000000000..ebc101d7da51 --- /dev/null +++ b/kernel/bpf/kmem_cache_iter.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024 Google */ +#include <linux/bpf.h> +#include <linux/btf_ids.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/seq_file.h> + +#include "../../mm/slab.h" /* kmem_cache, slab_caches and slab_mutex */ + +struct bpf_iter__kmem_cache { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct kmem_cache *, s); +}; + +static void *kmem_cache_iter_seq_start(struct seq_file *seq, loff_t *pos) +{ + loff_t cnt = 0; + bool found = false; + struct kmem_cache *s; + + mutex_lock(&slab_mutex); + + /* Find an entry at the given position in the slab_caches list instead + * of keeping a reference (of the last visited entry, if any) out of + * slab_mutex. It might miss something if one is deleted in the middle + * while it releases the lock. But it should be rare and there's not + * much we can do about it. + */ + list_for_each_entry(s, &slab_caches, list) { + if (cnt == *pos) { + /* Make sure this entry remains in the list by getting + * a new reference count. Note that boot_cache entries + * have a negative refcount, so don't touch them. + */ + if (s->refcount > 0) + s->refcount++; + found = true; + break; + } + cnt++; + } + mutex_unlock(&slab_mutex); + + if (!found) + return NULL; + + return s; +} + +static void kmem_cache_iter_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_meta meta; + struct bpf_iter__kmem_cache ctx = { + .meta = &meta, + .s = v, + }; + struct bpf_prog *prog; + bool destroy = false; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, true); + if (prog && !ctx.s) + bpf_iter_run_prog(prog, &ctx); + + if (ctx.s == NULL) + return; + + mutex_lock(&slab_mutex); + + /* Skip kmem_cache_destroy() for active entries */ + if (ctx.s->refcount > 1) + ctx.s->refcount--; + else if (ctx.s->refcount == 1) + destroy = true; + + mutex_unlock(&slab_mutex); + + if (destroy) + kmem_cache_destroy(ctx.s); +} + +static void *kmem_cache_iter_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct kmem_cache *s = v; + struct kmem_cache *next = NULL; + bool destroy = false; + + ++*pos; + + mutex_lock(&slab_mutex); + + if (list_last_entry(&slab_caches, struct kmem_cache, list) != s) { + next = list_next_entry(s, list); + + WARN_ON_ONCE(next->refcount == 0); + + /* boot_caches have negative refcount, don't touch them */ + if (next->refcount > 0) + next->refcount++; + } + + /* Skip kmem_cache_destroy() for active entries */ + if (s->refcount > 1) + s->refcount--; + else if (s->refcount == 1) + destroy = true; + + mutex_unlock(&slab_mutex); + + if (destroy) + kmem_cache_destroy(s); + + return next; +} + +static int kmem_cache_iter_seq_show(struct seq_file *seq, void *v) +{ + struct bpf_iter_meta meta; + struct bpf_iter__kmem_cache ctx = { + .meta = &meta, + .s = v, + }; + struct bpf_prog *prog; + int ret = 0; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, false); + if (prog) + ret = bpf_iter_run_prog(prog, &ctx); + + return ret; +} + +static const struct seq_operations kmem_cache_iter_seq_ops = { + .start = kmem_cache_iter_seq_start, + .next = kmem_cache_iter_seq_next, + .stop = kmem_cache_iter_seq_stop, + .show = kmem_cache_iter_seq_show, +}; + +BTF_ID_LIST_GLOBAL_SINGLE(bpf_kmem_cache_btf_id, struct, kmem_cache) + +static const struct bpf_iter_seq_info kmem_cache_iter_seq_info = { + .seq_ops = &kmem_cache_iter_seq_ops, +}; + +static void bpf_iter_kmem_cache_show_fdinfo(const struct bpf_iter_aux_info *aux, + struct seq_file *seq) +{ + seq_puts(seq, "kmem_cache iter\n"); +} + +DEFINE_BPF_ITER_FUNC(kmem_cache, struct bpf_iter_meta *meta, + struct kmem_cache *s) + +static struct bpf_iter_reg bpf_kmem_cache_reg_info = { + .target = "kmem_cache", + .feature = BPF_ITER_RESCHED, + .show_fdinfo = bpf_iter_kmem_cache_show_fdinfo, + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__kmem_cache, s), + PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, + }, + .seq_info = &kmem_cache_iter_seq_info, +}; + +static int __init bpf_kmem_cache_iter_init(void) +{ + bpf_kmem_cache_reg_info.ctx_arg_info[0].btf_id = bpf_kmem_cache_btf_id[0]; + return bpf_iter_reg_target(&bpf_kmem_cache_reg_info); +} + +late_initcall(bpf_kmem_cache_iter_init); diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index b3858a76e0b3..1a1b4458114c 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -252,11 +252,8 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic) static void free_one(void *obj, bool percpu) { - if (percpu) { + if (percpu) free_percpu(((void __percpu **)obj)[1]); - kfree(obj); - return; - } kfree(obj); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c5aa127ed4cc..8254b2973157 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -155,6 +155,89 @@ static void maybe_wait_bpf_programs(struct bpf_map *map) synchronize_rcu(); } +static void unpin_uptr_kaddr(void *kaddr) +{ + if (kaddr) + unpin_user_page(virt_to_page(kaddr)); +} + +static void __bpf_obj_unpin_uptrs(struct btf_record *rec, u32 cnt, void *obj) +{ + const struct btf_field *field; + void **uptr_addr; + int i; + + for (i = 0, field = rec->fields; i < cnt; i++, field++) { + if (field->type != BPF_UPTR) + continue; + + uptr_addr = obj + field->offset; + unpin_uptr_kaddr(*uptr_addr); + } +} + +static void bpf_obj_unpin_uptrs(struct btf_record *rec, void *obj) +{ + if (!btf_record_has_field(rec, BPF_UPTR)) + return; + + __bpf_obj_unpin_uptrs(rec, rec->cnt, obj); +} + +static int bpf_obj_pin_uptrs(struct btf_record *rec, void *obj) +{ + const struct btf_field *field; + const struct btf_type *t; + unsigned long start, end; + struct page *page; + void **uptr_addr; + int i, err; + + if (!btf_record_has_field(rec, BPF_UPTR)) + return 0; + + for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) { + if (field->type != BPF_UPTR) + continue; + + uptr_addr = obj + field->offset; + start = *(unsigned long *)uptr_addr; + if (!start) + continue; + + t = btf_type_by_id(field->kptr.btf, field->kptr.btf_id); + /* t->size was checked for zero before */ + if (check_add_overflow(start, t->size - 1, &end)) { + err = -EFAULT; + goto unpin_all; + } + + /* The uptr's struct cannot span across two pages */ + if ((start & PAGE_MASK) != (end & PAGE_MASK)) { + err = -EOPNOTSUPP; + goto unpin_all; + } + + err = pin_user_pages_fast(start, 1, FOLL_LONGTERM | FOLL_WRITE, &page); + if (err != 1) + goto unpin_all; + + if (PageHighMem(page)) { + err = -EOPNOTSUPP; + unpin_user_page(page); + goto unpin_all; + } + + *uptr_addr = page_address(page) + offset_in_page(start); + } + + return 0; + +unpin_all: + __bpf_obj_unpin_uptrs(rec, i, obj); + return err; +} + static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, void *key, void *value, __u64 flags) { @@ -199,9 +282,14 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { - rcu_read_lock(); - err = map->ops->map_update_elem(map, key, value, flags); - rcu_read_unlock(); + err = bpf_obj_pin_uptrs(map->record, value); + if (!err) { + rcu_read_lock(); + err = map->ops->map_update_elem(map, key, value, flags); + rcu_read_unlock(); + if (err) + bpf_obj_unpin_uptrs(map->record, value); + } } bpf_enable_instrumentation(); @@ -548,6 +636,7 @@ void btf_record_free(struct btf_record *rec) case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: if (rec->fields[i].kptr.module) module_put(rec->fields[i].kptr.module); if (btf_is_kernel(rec->fields[i].kptr.btf)) @@ -597,6 +686,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: if (btf_is_kernel(fields[i].kptr.btf)) btf_get(fields[i].kptr.btf); if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) { @@ -714,6 +804,10 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) field->kptr.dtor(xchgd_field); } break; + case BPF_UPTR: + /* The caller ensured that no one is using the uptr */ + unpin_uptr_kaddr(*(void **)field_ptr); + break; case BPF_LIST_HEAD: if (WARN_ON_ONCE(rec->spin_lock_off < 0)) continue; @@ -1105,7 +1199,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token, map->record = btf_parse_fields(btf, value_type, BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD | - BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE, + BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE | BPF_UPTR, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; @@ -1161,6 +1255,12 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token, goto free_map_tab; } break; + case BPF_UPTR: + if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + break; case BPF_LIST_HEAD: case BPF_RB_ROOT: if (map->map_type != BPF_MAP_TYPE_HASH && @@ -3218,7 +3318,8 @@ static void bpf_tracing_link_release(struct bpf_link *link) container_of(link, struct bpf_tracing_link, link.link); WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link, - tr_link->trampoline)); + tr_link->trampoline, + tr_link->tgt_prog)); bpf_trampoline_put(tr_link->trampoline); @@ -3358,7 +3459,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, * in prog->aux * * - if prog->aux->dst_trampoline is NULL, the program has already been - * attached to a target and its initial target was cleared (below) + * attached to a target and its initial target was cleared (below) * * - if tgt_prog != NULL, the caller specified tgt_prog_fd + * target_btf_id using the link_create API. @@ -3433,7 +3534,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, if (err) goto out_unlock; - err = bpf_trampoline_link_prog(&link->link, tr); + err = bpf_trampoline_link_prog(&link->link, tr, tgt_prog); if (err) { bpf_link_cleanup(&link_primer); link = NULL; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index f8302a5ca400..9f36c049f4c2 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -523,7 +523,27 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog) } } -static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) +static int bpf_freplace_check_tgt_prog(struct bpf_prog *tgt_prog) +{ + struct bpf_prog_aux *aux = tgt_prog->aux; + + guard(mutex)(&aux->ext_mutex); + if (aux->prog_array_member_cnt) + /* Program extensions can not extend target prog when the target + * prog has been updated to any prog_array map as tail callee. + * It's to prevent a potential infinite loop like: + * tgt prog entry -> tgt prog subprog -> freplace prog entry + * --tailcall-> tgt prog entry. + */ + return -EBUSY; + + aux->is_extended = true; + return 0; +} + +static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { enum bpf_tramp_prog_type kind; struct bpf_tramp_link *link_exiting; @@ -544,6 +564,9 @@ static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_tr /* Cannot attach extension if fentry/fexit are in use. */ if (cnt) return -EBUSY; + err = bpf_freplace_check_tgt_prog(tgt_prog); + if (err) + return err; tr->extension_prog = link->link.prog; return bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL, link->link.prog->bpf_func); @@ -570,17 +593,21 @@ static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_tr return err; } -int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) +int bpf_trampoline_link_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { int err; mutex_lock(&tr->mutex); - err = __bpf_trampoline_link_prog(link, tr); + err = __bpf_trampoline_link_prog(link, tr, tgt_prog); mutex_unlock(&tr->mutex); return err; } -static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) +static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { enum bpf_tramp_prog_type kind; int err; @@ -591,6 +618,8 @@ static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_ err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, tr->extension_prog->bpf_func, NULL); tr->extension_prog = NULL; + guard(mutex)(&tgt_prog->aux->ext_mutex); + tgt_prog->aux->is_extended = false; return err; } hlist_del_init(&link->tramp_hlist); @@ -599,12 +628,14 @@ static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_ } /* bpf_trampoline_unlink_prog() should never fail. */ -int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) +int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, + struct bpf_trampoline *tr, + struct bpf_prog *tgt_prog) { int err; mutex_lock(&tr->mutex); - err = __bpf_trampoline_unlink_prog(link, tr); + err = __bpf_trampoline_unlink_prog(link, tr, tgt_prog); mutex_unlock(&tr->mutex); return err; } @@ -619,7 +650,7 @@ static void bpf_shim_tramp_link_release(struct bpf_link *link) if (!shim_link->trampoline) return; - WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline)); + WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline, NULL)); bpf_trampoline_put(shim_link->trampoline); } @@ -733,7 +764,7 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, goto err; } - err = __bpf_trampoline_link_prog(&shim_link->link, tr); + err = __bpf_trampoline_link_prog(&shim_link->link, tr, NULL); if (err) goto err; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 587a6c76e564..797cf3ed32e0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5491,6 +5491,22 @@ static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr return ret; } +static int mark_uptr_ld_reg(struct bpf_verifier_env *env, u32 regno, + struct btf_field *field) +{ + struct bpf_reg_state *reg; + const struct btf_type *t; + + t = btf_type_by_id(field->kptr.btf, field->kptr.btf_id); + mark_reg_known_zero(env, cur_regs(env), regno); + reg = reg_state(env, regno); + reg->type = PTR_TO_MEM | PTR_MAYBE_NULL; + reg->mem_size = t->size; + reg->id = ++env->id_gen; + + return 0; +} + static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, int value_regno, int insn_idx, struct btf_field *kptr_field) @@ -5519,9 +5535,15 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, verbose(env, "store to referenced kptr disallowed\n"); return -EACCES; } + if (class != BPF_LDX && kptr_field->type == BPF_UPTR) { + verbose(env, "store to uptr disallowed\n"); + return -EACCES; + } if (class == BPF_LDX) { - val_reg = reg_state(env, value_regno); + if (kptr_field->type == BPF_UPTR) + return mark_uptr_ld_reg(env, value_regno, kptr_field); + /* We can simply mark the value_regno receiving the pointer * value from map as PTR_TO_BTF_ID, with the correct type. */ @@ -5579,21 +5601,26 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: + case BPF_UPTR: if (src != ACCESS_DIRECT) { - verbose(env, "kptr cannot be accessed indirectly by helper\n"); + verbose(env, "%s cannot be accessed indirectly by helper\n", + btf_field_type_name(field->type)); return -EACCES; } if (!tnum_is_const(reg->var_off)) { - verbose(env, "kptr access cannot have variable offset\n"); + verbose(env, "%s access cannot have variable offset\n", + btf_field_type_name(field->type)); return -EACCES; } if (p != off + reg->var_off.value) { - verbose(env, "kptr access misaligned expected=%u off=%llu\n", + verbose(env, "%s access misaligned expected=%u off=%llu\n", + btf_field_type_name(field->type), p, off + reg->var_off.value); return -EACCES; } if (size != bpf_size_to_bytes(BPF_DW)) { - verbose(env, "kptr access size must be BPF_DW\n"); + verbose(env, "%s access size must be BPF_DW\n", + btf_field_type_name(field->type)); return -EACCES; } break; @@ -6959,7 +6986,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return err; if (tnum_is_const(reg->var_off)) kptr_field = btf_record_find(reg->map_ptr->record, - off + reg->var_off.value, BPF_KPTR); + off + reg->var_off.value, BPF_KPTR | BPF_UPTR); if (kptr_field) { err = check_map_kptr_access(env, regno, value_regno, insn_idx, kptr_field); } else if (t == BPF_READ && value_regno >= 0) { @@ -9920,7 +9947,7 @@ static int set_loop_callback_state(struct bpf_verifier_env *env, { /* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, * u64 flags); - * callback_fn(u32 index, void *callback_ctx); + * callback_fn(u64 index, void *callback_ctx); */ callee->regs[BPF_REG_1].type = SCALAR_VALUE; callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; @@ -11262,6 +11289,7 @@ enum special_kfunc_type { KF_bpf_preempt_enable, KF_bpf_iter_css_task_new, KF_bpf_session_cookie, + KF_bpf_get_kmem_cache, }; BTF_SET_START(special_kfunc_set) @@ -11327,6 +11355,7 @@ BTF_ID(func, bpf_session_cookie) #else BTF_ID_UNUSED #endif +BTF_ID(func, bpf_get_kmem_cache) static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) { @@ -12837,6 +12866,9 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; + if (meta.func_id == special_kfunc_list[KF_bpf_get_kmem_cache]) + regs[BPF_REG_0].type |= PTR_UNTRUSTED; + if (is_iter_next_kfunc(&meta)) { struct bpf_reg_state *cur_iter; @@ -16185,10 +16217,7 @@ static u32 kfunc_fastcall_clobber_mask(struct bpf_kfunc_call_arg_meta *meta) /* Same as verifier_inlines_helper_call() but for kfuncs, see comment above */ static bool is_fastcall_kfunc_call(struct bpf_kfunc_call_arg_meta *meta) { - if (meta->btf == btf_vmlinux) - return meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] || - meta->func_id == special_kfunc_list[KF_bpf_rdonly_cast]; - return false; + return meta->kfunc_flags & KF_FASTCALL; } /* LLVM define a bpf_fastcall function attribute. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 630b763e5240..d56975984ea6 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -802,6 +802,8 @@ struct send_signal_irq_work { struct task_struct *task; u32 sig; enum pid_type type; + bool has_siginfo; + struct kernel_siginfo info; }; static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work); @@ -809,27 +811,46 @@ static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work); static void do_bpf_send_signal(struct irq_work *entry) { struct send_signal_irq_work *work; + struct kernel_siginfo *siginfo; work = container_of(entry, struct send_signal_irq_work, irq_work); - group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type); + siginfo = work->has_siginfo ? &work->info : SEND_SIG_PRIV; + + group_send_sig_info(work->sig, siginfo, work->task, work->type); put_task_struct(work->task); } -static int bpf_send_signal_common(u32 sig, enum pid_type type) +static int bpf_send_signal_common(u32 sig, enum pid_type type, struct task_struct *task, u64 value) { struct send_signal_irq_work *work = NULL; + struct kernel_siginfo info; + struct kernel_siginfo *siginfo; + + if (!task) { + task = current; + siginfo = SEND_SIG_PRIV; + } else { + clear_siginfo(&info); + info.si_signo = sig; + info.si_errno = 0; + info.si_code = SI_KERNEL; + info.si_pid = 0; + info.si_uid = 0; + info.si_value.sival_ptr = (void *)(unsigned long)value; + siginfo = &info; + } /* Similar to bpf_probe_write_user, task needs to be * in a sound condition and kernel memory access be * permitted in order to send signal to the current * task. */ - if (unlikely(current->flags & (PF_KTHREAD | PF_EXITING))) + if (unlikely(task->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; /* Task should not be pid=1 to avoid kernel panic. */ - if (unlikely(is_global_init(current))) + if (unlikely(is_global_init(task))) return -EPERM; if (irqs_disabled()) { @@ -847,19 +868,22 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) * to the irq_work. The current task may change when queued * irq works get executed. */ - work->task = get_task_struct(current); + work->task = get_task_struct(task); + work->has_siginfo = siginfo == &info; + if (work->has_siginfo) + copy_siginfo(&work->info, &info); work->sig = sig; work->type = type; irq_work_queue(&work->irq_work); return 0; } - return group_send_sig_info(sig, SEND_SIG_PRIV, current, type); + return group_send_sig_info(sig, siginfo, task, type); } BPF_CALL_1(bpf_send_signal, u32, sig) { - return bpf_send_signal_common(sig, PIDTYPE_TGID); + return bpf_send_signal_common(sig, PIDTYPE_TGID, NULL, 0); } static const struct bpf_func_proto bpf_send_signal_proto = { @@ -871,7 +895,7 @@ static const struct bpf_func_proto bpf_send_signal_proto = { BPF_CALL_1(bpf_send_signal_thread, u32, sig) { - return bpf_send_signal_common(sig, PIDTYPE_PID); + return bpf_send_signal_common(sig, PIDTYPE_PID, NULL, 0); } static const struct bpf_func_proto bpf_send_signal_thread_proto = { @@ -3480,3 +3504,16 @@ static int __init bpf_kprobe_multi_kfuncs_init(void) } late_initcall(bpf_kprobe_multi_kfuncs_init); + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_send_signal_task(struct task_struct *task, int sig, enum pid_type type, + u64 value) +{ + if (type != PIDTYPE_PID && type != PIDTYPE_TGID) + return -EINVAL; + + return bpf_send_signal_common(sig, type, task, value); +} + +__bpf_kfunc_end_defs(); diff --git a/mm/slab_common.c b/mm/slab_common.c index 3d26c257ed8b..661159b6baf9 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1323,6 +1323,25 @@ size_t ksize(const void *objp) } EXPORT_SYMBOL(ksize); +#ifdef CONFIG_BPF_SYSCALL +#include <linux/btf.h> + +__bpf_kfunc_start_defs(); + +__bpf_kfunc struct kmem_cache *bpf_get_kmem_cache(u64 addr) +{ + struct slab *slab; + + if (!virt_addr_valid((void *)(long)addr)) + return NULL; + + slab = virt_to_slab((void *)(long)addr); + return slab ? slab->slab_cache : NULL; +} + +__bpf_kfunc_end_defs(); +#endif /* CONFIG_BPF_SYSCALL */ + /* Tracepoints definitions. */ EXPORT_TRACEPOINT_SYMBOL(kmalloc); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index bc01b3aa6b0f..2f4ed83a75ae 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -106,7 +106,7 @@ static long bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, if (sock) { sdata = bpf_local_storage_update( sock->sk, (struct bpf_local_storage_map *)map, value, - map_flags, GFP_ATOMIC); + map_flags, false, GFP_ATOMIC); sockfd_put(sock); return PTR_ERR_OR_ZERO(sdata); } @@ -137,7 +137,7 @@ bpf_sk_storage_clone_elem(struct sock *newsk, { struct bpf_local_storage_elem *copy_selem; - copy_selem = bpf_selem_alloc(smap, newsk, NULL, true, GFP_ATOMIC); + copy_selem = bpf_selem_alloc(smap, newsk, NULL, true, false, GFP_ATOMIC); if (!copy_selem) return NULL; @@ -243,7 +243,7 @@ BPF_CALL_5(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, refcount_inc_not_zero(&sk->sk_refcnt)) { sdata = bpf_local_storage_update( sk, (struct bpf_local_storage_map *)map, value, - BPF_NOEXIST, gfp_flags); + BPF_NOEXIST, false, gfp_flags); /* sk must be a fullsock (guaranteed by verifier), * so sock_gen_put() is unnecessary. */ diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 7afe040cf43b..bcf103a4c14f 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -17,20 +17,12 @@ tprogs-y += tracex3 tprogs-y += tracex4 tprogs-y += tracex5 tprogs-y += tracex6 -tprogs-y += tracex7 -tprogs-y += test_probe_write_user tprogs-y += trace_output tprogs-y += lathist tprogs-y += offwaketime tprogs-y += spintest tprogs-y += map_perf_test -tprogs-y += test_overhead -tprogs-y += test_cgrp2_array_pin -tprogs-y += test_cgrp2_attach -tprogs-y += test_cgrp2_sock -tprogs-y += test_cgrp2_sock2 tprogs-y += xdp_router_ipv4 -tprogs-y += test_current_task_under_cgroup tprogs-y += trace_event tprogs-y += sampleip tprogs-y += tc_l2_redirect @@ -66,20 +58,12 @@ tracex3-objs := tracex3_user.o tracex4-objs := tracex4_user.o tracex5-objs := tracex5_user.o $(TRACE_HELPERS) tracex6-objs := tracex6_user.o -tracex7-objs := tracex7_user.o -test_probe_write_user-objs := test_probe_write_user_user.o trace_output-objs := trace_output_user.o lathist-objs := lathist_user.o offwaketime-objs := offwaketime_user.o $(TRACE_HELPERS) spintest-objs := spintest_user.o $(TRACE_HELPERS) map_perf_test-objs := map_perf_test_user.o test_overhead-objs := test_overhead_user.o -test_cgrp2_array_pin-objs := test_cgrp2_array_pin.o -test_cgrp2_attach-objs := test_cgrp2_attach.o -test_cgrp2_sock-objs := test_cgrp2_sock.o -test_cgrp2_sock2-objs := test_cgrp2_sock2.o -test_current_task_under_cgroup-objs := $(CGROUP_HELPERS) \ - test_current_task_under_cgroup_user.o trace_event-objs := trace_event_user.o $(TRACE_HELPERS) sampleip-objs := sampleip_user.o $(TRACE_HELPERS) tc_l2_redirect-objs := tc_l2_redirect_user.o @@ -107,9 +91,6 @@ always-y += tracex3.bpf.o always-y += tracex4.bpf.o always-y += tracex5.bpf.o always-y += tracex6.bpf.o -always-y += tracex7.bpf.o -always-y += sock_flags.bpf.o -always-y += test_probe_write_user.bpf.o always-y += trace_output.bpf.o always-y += tcbpf1_kern.o always-y += tc_l2_redirect_kern.o @@ -117,12 +98,7 @@ always-y += lathist_kern.o always-y += offwaketime.bpf.o always-y += spintest.bpf.o always-y += map_perf_test.bpf.o -always-y += test_overhead_tp.bpf.o -always-y += test_overhead_raw_tp.bpf.o -always-y += test_overhead_kprobe.bpf.o always-y += parse_varlen.o parse_simple.o parse_ldabs.o -always-y += test_cgrp2_tc.bpf.o -always-y += test_current_task_under_cgroup.bpf.o always-y += trace_event_kern.o always-y += sampleip_kern.o always-y += lwt_len_hist.bpf.o @@ -195,7 +171,6 @@ TPROGLDLIBS_xdp_router_ipv4 += -lm -pthread TPROGLDLIBS_tracex4 += -lrt TPROGLDLIBS_trace_output += -lrt TPROGLDLIBS_map_perf_test += -lrt -TPROGLDLIBS_test_overhead += -lrt # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: # make M=samples/bpf LLC=~/git/llvm-project/llvm/build/bin/llc CLANG=~/git/llvm-project/llvm/build/bin/clang diff --git a/samples/bpf/sock_flags.bpf.c b/samples/bpf/sock_flags.bpf.c deleted file mode 100644 index 0da749f6a9e1..000000000000 --- a/samples/bpf/sock_flags.bpf.c +++ /dev/null @@ -1,47 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "vmlinux.h" -#include "net_shared.h" -#include <bpf/bpf_helpers.h> - -SEC("cgroup/sock") -int bpf_prog1(struct bpf_sock *sk) -{ - char fmt[] = "socket: family %d type %d protocol %d\n"; - char fmt2[] = "socket: uid %u gid %u\n"; - __u64 gid_uid = bpf_get_current_uid_gid(); - __u32 uid = gid_uid & 0xffffffff; - __u32 gid = gid_uid >> 32; - - bpf_trace_printk(fmt, sizeof(fmt), sk->family, sk->type, sk->protocol); - bpf_trace_printk(fmt2, sizeof(fmt2), uid, gid); - - /* block AF_INET6, SOCK_DGRAM, IPPROTO_ICMPV6 sockets - * ie., make ping6 fail - */ - if (sk->family == AF_INET6 && - sk->type == SOCK_DGRAM && - sk->protocol == IPPROTO_ICMPV6) - return 0; - - return 1; -} - -SEC("cgroup/sock") -int bpf_prog2(struct bpf_sock *sk) -{ - char fmt[] = "socket: family %d type %d protocol %d\n"; - - bpf_trace_printk(fmt, sizeof(fmt), sk->family, sk->type, sk->protocol); - - /* block AF_INET, SOCK_DGRAM, IPPROTO_ICMP sockets - * ie., make ping fail - */ - if (sk->family == AF_INET && - sk->type == SOCK_DGRAM && - sk->protocol == IPPROTO_ICMP) - return 0; - - return 1; -} - -char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/syscall_nrs.c b/samples/bpf/syscall_nrs.c index 88f940052450..a6e600f3d477 100644 --- a/samples/bpf/syscall_nrs.c +++ b/samples/bpf/syscall_nrs.c @@ -2,6 +2,9 @@ #include <uapi/linux/unistd.h> #include <linux/kbuild.h> +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wmissing-prototypes" + #define SYSNR(_NR) DEFINE(SYS ## _NR, _NR) void syscall_defines(void) @@ -17,3 +20,5 @@ void syscall_defines(void) #endif } + +#pragma GCC diagnostic pop diff --git a/samples/bpf/tc_l2_redirect_kern.c b/samples/bpf/tc_l2_redirect_kern.c index fd2fa0004330..0b48f7ddf521 100644 --- a/samples/bpf/tc_l2_redirect_kern.c +++ b/samples/bpf/tc_l2_redirect_kern.c @@ -58,7 +58,6 @@ static __always_inline bool is_vip_addr(__be16 eth_proto, __be32 daddr) SEC("l2_to_iptun_ingress_forward") int _l2_to_iptun_ingress_forward(struct __sk_buff *skb) { - struct bpf_tunnel_key tkey = {}; void *data = (void *)(long)skb->data; struct eth_hdr *eth = data; void *data_end = (void *)(long)skb->data_end; @@ -205,7 +204,6 @@ int _l2_to_ip6tun_ingress_redirect(struct __sk_buff *skb) SEC("drop_non_tun_vip") int _drop_non_tun_vip(struct __sk_buff *skb) { - struct bpf_tunnel_key tkey = {}; void *data = (void *)(long)skb->data; struct eth_hdr *eth = data; void *data_end = (void *)(long)skb->data_end; diff --git a/samples/bpf/test_cgrp2_array_pin.c b/samples/bpf/test_cgrp2_array_pin.c deleted file mode 100644 index 05e88aa63009..000000000000 --- a/samples/bpf/test_cgrp2_array_pin.c +++ /dev/null @@ -1,106 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* Copyright (c) 2016 Facebook - */ -#include <linux/unistd.h> -#include <linux/bpf.h> - -#include <stdio.h> -#include <stdint.h> -#include <unistd.h> -#include <string.h> -#include <errno.h> -#include <fcntl.h> - -#include <bpf/bpf.h> - -static void usage(void) -{ - printf("Usage: test_cgrp2_array_pin [...]\n"); - printf(" -F <file> File to pin an BPF cgroup array\n"); - printf(" -U <file> Update an already pinned BPF cgroup array\n"); - printf(" -v <value> Full path of the cgroup2\n"); - printf(" -h Display this help\n"); -} - -int main(int argc, char **argv) -{ - const char *pinned_file = NULL, *cg2 = NULL; - int create_array = 1; - int array_key = 0; - int array_fd = -1; - int cg2_fd = -1; - int ret = -1; - int opt; - - while ((opt = getopt(argc, argv, "F:U:v:")) != -1) { - switch (opt) { - /* General args */ - case 'F': - pinned_file = optarg; - break; - case 'U': - pinned_file = optarg; - create_array = 0; - break; - case 'v': - cg2 = optarg; - break; - default: - usage(); - goto out; - } - } - - if (!cg2 || !pinned_file) { - usage(); - goto out; - } - - cg2_fd = open(cg2, O_RDONLY); - if (cg2_fd < 0) { - fprintf(stderr, "open(%s,...): %s(%d)\n", - cg2, strerror(errno), errno); - goto out; - } - - if (create_array) { - array_fd = bpf_map_create(BPF_MAP_TYPE_CGROUP_ARRAY, NULL, - sizeof(uint32_t), sizeof(uint32_t), - 1, NULL); - if (array_fd < 0) { - fprintf(stderr, - "bpf_create_map(BPF_MAP_TYPE_CGROUP_ARRAY,...): %s(%d)\n", - strerror(errno), errno); - goto out; - } - } else { - array_fd = bpf_obj_get(pinned_file); - if (array_fd < 0) { - fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n", - pinned_file, strerror(errno), errno); - goto out; - } - } - - ret = bpf_map_update_elem(array_fd, &array_key, &cg2_fd, 0); - if (ret) { - perror("bpf_map_update_elem"); - goto out; - } - - if (create_array) { - ret = bpf_obj_pin(array_fd, pinned_file); - if (ret) { - fprintf(stderr, "bpf_obj_pin(..., %s): %s(%d)\n", - pinned_file, strerror(errno), errno); - goto out; - } - } - -out: - if (array_fd != -1) - close(array_fd); - if (cg2_fd != -1) - close(cg2_fd); - return ret; -} diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c deleted file mode 100644 index 68ce69457afe..000000000000 --- a/samples/bpf/test_cgrp2_attach.c +++ /dev/null @@ -1,177 +0,0 @@ -/* eBPF example program: - * - * - Creates arraymap in kernel with 4 bytes keys and 8 byte values - * - * - Loads eBPF program - * - * The eBPF program accesses the map passed in to store two pieces of - * information. The number of invocations of the program, which maps - * to the number of packets received, is stored to key 0. Key 1 is - * incremented on each iteration by the number of bytes stored in - * the skb. - * - * - Attaches the new program to a cgroup using BPF_PROG_ATTACH - * - * - Every second, reads map[0] and map[1] to see how many bytes and - * packets were seen on any socket of tasks in the given cgroup. - */ - -#define _GNU_SOURCE - -#include <stdio.h> -#include <stdlib.h> -#include <stddef.h> -#include <string.h> -#include <unistd.h> -#include <assert.h> -#include <errno.h> -#include <fcntl.h> - -#include <linux/bpf.h> -#include <bpf/bpf.h> - -#include "bpf_insn.h" -#include "bpf_util.h" - -enum { - MAP_KEY_PACKETS, - MAP_KEY_BYTES, -}; - -char bpf_log_buf[BPF_LOG_BUF_SIZE]; - -static int prog_load(int map_fd, int verdict) -{ - struct bpf_insn prog[] = { - BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), /* save r6 so it's not clobbered by BPF_CALL */ - - /* Count packets */ - BPF_MOV64_IMM(BPF_REG_0, MAP_KEY_PACKETS), /* r0 = 0 */ - BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ - BPF_LD_MAP_FD(BPF_REG_1, map_fd), /* load map fd to r1 */ - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), - BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */ - BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), - - /* Count bytes */ - BPF_MOV64_IMM(BPF_REG_0, MAP_KEY_BYTES), /* r0 = 1 */ - BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ - BPF_LD_MAP_FD(BPF_REG_1, map_fd), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), - BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6, offsetof(struct __sk_buff, len)), /* r1 = skb->len */ - - BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0), - - BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ - BPF_EXIT_INSN(), - }; - size_t insns_cnt = ARRAY_SIZE(prog); - LIBBPF_OPTS(bpf_prog_load_opts, opts, - .log_buf = bpf_log_buf, - .log_size = BPF_LOG_BUF_SIZE, - ); - - return bpf_prog_load(BPF_PROG_TYPE_CGROUP_SKB, NULL, "GPL", - prog, insns_cnt, &opts); -} - -static int usage(const char *argv0) -{ - printf("Usage: %s [-d] [-D] <cg-path> <egress|ingress>\n", argv0); - printf(" -d Drop Traffic\n"); - printf(" -D Detach filter, and exit\n"); - return EXIT_FAILURE; -} - -static int attach_filter(int cg_fd, int type, int verdict) -{ - int prog_fd, map_fd, ret, key; - long long pkt_cnt, byte_cnt; - - map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, - sizeof(key), sizeof(byte_cnt), - 256, NULL); - if (map_fd < 0) { - printf("Failed to create map: '%s'\n", strerror(errno)); - return EXIT_FAILURE; - } - - prog_fd = prog_load(map_fd, verdict); - printf("Output from kernel verifier:\n%s\n-------\n", bpf_log_buf); - - if (prog_fd < 0) { - printf("Failed to load prog: '%s'\n", strerror(errno)); - return EXIT_FAILURE; - } - - ret = bpf_prog_attach(prog_fd, cg_fd, type, 0); - if (ret < 0) { - printf("Failed to attach prog to cgroup: '%s'\n", - strerror(errno)); - return EXIT_FAILURE; - } - while (1) { - key = MAP_KEY_PACKETS; - assert(bpf_map_lookup_elem(map_fd, &key, &pkt_cnt) == 0); - - key = MAP_KEY_BYTES; - assert(bpf_map_lookup_elem(map_fd, &key, &byte_cnt) == 0); - - printf("cgroup received %lld packets, %lld bytes\n", - pkt_cnt, byte_cnt); - sleep(1); - } - - return EXIT_SUCCESS; -} - -int main(int argc, char **argv) -{ - int detach_only = 0, verdict = 1; - enum bpf_attach_type type; - int opt, cg_fd, ret; - - while ((opt = getopt(argc, argv, "Dd")) != -1) { - switch (opt) { - case 'd': - verdict = 0; - break; - case 'D': - detach_only = 1; - break; - default: - return usage(argv[0]); - } - } - - if (argc - optind < 2) - return usage(argv[0]); - - if (strcmp(argv[optind + 1], "ingress") == 0) - type = BPF_CGROUP_INET_INGRESS; - else if (strcmp(argv[optind + 1], "egress") == 0) - type = BPF_CGROUP_INET_EGRESS; - else - return usage(argv[0]); - - cg_fd = open(argv[optind], O_DIRECTORY | O_RDONLY); - if (cg_fd < 0) { - printf("Failed to open cgroup path: '%s'\n", strerror(errno)); - return EXIT_FAILURE; - } - - if (detach_only) { - ret = bpf_prog_detach(cg_fd, type); - printf("bpf_prog_detach() returned '%s' (%d)\n", - strerror(errno), errno); - } else - ret = attach_filter(cg_fd, type, verdict); - - return ret; -} diff --git a/samples/bpf/test_cgrp2_sock.c b/samples/bpf/test_cgrp2_sock.c deleted file mode 100644 index a0811df888f4..000000000000 --- a/samples/bpf/test_cgrp2_sock.c +++ /dev/null @@ -1,294 +0,0 @@ -/* eBPF example program: - * - * - Loads eBPF program - * - * The eBPF program sets the sk_bound_dev_if index in new AF_INET{6} - * sockets opened by processes in the cgroup. - * - * - Attaches the new program to a cgroup using BPF_PROG_ATTACH - */ - -#define _GNU_SOURCE - -#include <stdio.h> -#include <stdlib.h> -#include <stddef.h> -#include <string.h> -#include <unistd.h> -#include <assert.h> -#include <errno.h> -#include <fcntl.h> -#include <net/if.h> -#include <inttypes.h> -#include <linux/bpf.h> -#include <bpf/bpf.h> - -#include "bpf_insn.h" - -char bpf_log_buf[BPF_LOG_BUF_SIZE]; - -static int prog_load(__u32 idx, __u32 mark, __u32 prio) -{ - /* save pointer to context */ - struct bpf_insn prog_start[] = { - BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), - }; - struct bpf_insn prog_end[] = { - BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = verdict */ - BPF_EXIT_INSN(), - }; - - /* set sk_bound_dev_if on socket */ - struct bpf_insn prog_dev[] = { - BPF_MOV64_IMM(BPF_REG_3, idx), - BPF_MOV64_IMM(BPF_REG_2, offsetof(struct bpf_sock, bound_dev_if)), - BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, offsetof(struct bpf_sock, bound_dev_if)), - }; - - /* set mark on socket */ - struct bpf_insn prog_mark[] = { - /* get uid of process */ - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - BPF_FUNC_get_current_uid_gid), - BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffffffff), - - /* if uid is 0, use given mark, else use the uid as the mark */ - BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), - BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), - BPF_MOV64_IMM(BPF_REG_3, mark), - - /* set the mark on the new socket */ - BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), - BPF_MOV64_IMM(BPF_REG_2, offsetof(struct bpf_sock, mark)), - BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, offsetof(struct bpf_sock, mark)), - }; - - /* set priority on socket */ - struct bpf_insn prog_prio[] = { - BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), - BPF_MOV64_IMM(BPF_REG_3, prio), - BPF_MOV64_IMM(BPF_REG_2, offsetof(struct bpf_sock, priority)), - BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, offsetof(struct bpf_sock, priority)), - }; - LIBBPF_OPTS(bpf_prog_load_opts, opts, - .log_buf = bpf_log_buf, - .log_size = BPF_LOG_BUF_SIZE, - ); - - struct bpf_insn *prog; - size_t insns_cnt; - void *p; - int ret; - - insns_cnt = sizeof(prog_start) + sizeof(prog_end); - if (idx) - insns_cnt += sizeof(prog_dev); - - if (mark) - insns_cnt += sizeof(prog_mark); - - if (prio) - insns_cnt += sizeof(prog_prio); - - p = prog = malloc(insns_cnt); - if (!prog) { - fprintf(stderr, "Failed to allocate memory for instructions\n"); - return EXIT_FAILURE; - } - - memcpy(p, prog_start, sizeof(prog_start)); - p += sizeof(prog_start); - - if (idx) { - memcpy(p, prog_dev, sizeof(prog_dev)); - p += sizeof(prog_dev); - } - - if (mark) { - memcpy(p, prog_mark, sizeof(prog_mark)); - p += sizeof(prog_mark); - } - - if (prio) { - memcpy(p, prog_prio, sizeof(prog_prio)); - p += sizeof(prog_prio); - } - - memcpy(p, prog_end, sizeof(prog_end)); - p += sizeof(prog_end); - - insns_cnt /= sizeof(struct bpf_insn); - - ret = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", - prog, insns_cnt, &opts); - - free(prog); - - return ret; -} - -static int get_bind_to_device(int sd, char *name, size_t len) -{ - socklen_t optlen = len; - int rc; - - name[0] = '\0'; - rc = getsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, &optlen); - if (rc < 0) - perror("setsockopt(SO_BINDTODEVICE)"); - - return rc; -} - -static unsigned int get_somark(int sd) -{ - unsigned int mark = 0; - socklen_t optlen = sizeof(mark); - int rc; - - rc = getsockopt(sd, SOL_SOCKET, SO_MARK, &mark, &optlen); - if (rc < 0) - perror("getsockopt(SO_MARK)"); - - return mark; -} - -static unsigned int get_priority(int sd) -{ - unsigned int prio = 0; - socklen_t optlen = sizeof(prio); - int rc; - - rc = getsockopt(sd, SOL_SOCKET, SO_PRIORITY, &prio, &optlen); - if (rc < 0) - perror("getsockopt(SO_PRIORITY)"); - - return prio; -} - -static int show_sockopts(int family) -{ - unsigned int mark, prio; - char name[16]; - int sd; - - sd = socket(family, SOCK_DGRAM, 17); - if (sd < 0) { - perror("socket"); - return 1; - } - - if (get_bind_to_device(sd, name, sizeof(name)) < 0) - return 1; - - mark = get_somark(sd); - prio = get_priority(sd); - - close(sd); - - printf("sd %d: dev %s, mark %u, priority %u\n", sd, name, mark, prio); - - return 0; -} - -static int usage(const char *argv0) -{ - printf("Usage:\n"); - printf(" Attach a program\n"); - printf(" %s -b bind-to-dev -m mark -p prio cg-path\n", argv0); - printf("\n"); - printf(" Detach a program\n"); - printf(" %s -d cg-path\n", argv0); - printf("\n"); - printf(" Show inherited socket settings (mark, priority, and device)\n"); - printf(" %s [-6]\n", argv0); - return EXIT_FAILURE; -} - -int main(int argc, char **argv) -{ - __u32 idx = 0, mark = 0, prio = 0; - const char *cgrp_path = NULL; - int cg_fd, prog_fd, ret; - int family = PF_INET; - int do_attach = 1; - int rc; - - while ((rc = getopt(argc, argv, "db:m:p:6")) != -1) { - switch (rc) { - case 'd': - do_attach = 0; - break; - case 'b': - idx = if_nametoindex(optarg); - if (!idx) { - idx = strtoumax(optarg, NULL, 0); - if (!idx) { - printf("Invalid device name\n"); - return EXIT_FAILURE; - } - } - break; - case 'm': - mark = strtoumax(optarg, NULL, 0); - break; - case 'p': - prio = strtoumax(optarg, NULL, 0); - break; - case '6': - family = PF_INET6; - break; - default: - return usage(argv[0]); - } - } - - if (optind == argc) - return show_sockopts(family); - - cgrp_path = argv[optind]; - if (!cgrp_path) { - fprintf(stderr, "cgroup path not given\n"); - return EXIT_FAILURE; - } - - if (do_attach && !idx && !mark && !prio) { - fprintf(stderr, - "One of device, mark or priority must be given\n"); - return EXIT_FAILURE; - } - - cg_fd = open(cgrp_path, O_DIRECTORY | O_RDONLY); - if (cg_fd < 0) { - printf("Failed to open cgroup path: '%s'\n", strerror(errno)); - return EXIT_FAILURE; - } - - if (do_attach) { - prog_fd = prog_load(idx, mark, prio); - if (prog_fd < 0) { - printf("Failed to load prog: '%s'\n", strerror(errno)); - printf("Output from kernel verifier:\n%s\n-------\n", - bpf_log_buf); - return EXIT_FAILURE; - } - - ret = bpf_prog_attach(prog_fd, cg_fd, - BPF_CGROUP_INET_SOCK_CREATE, 0); - if (ret < 0) { - printf("Failed to attach prog to cgroup: '%s'\n", - strerror(errno)); - return EXIT_FAILURE; - } - } else { - ret = bpf_prog_detach(cg_fd, BPF_CGROUP_INET_SOCK_CREATE); - if (ret < 0) { - printf("Failed to detach prog from cgroup: '%s'\n", - strerror(errno)); - return EXIT_FAILURE; - } - } - - close(cg_fd); - return EXIT_SUCCESS; -} diff --git a/samples/bpf/test_cgrp2_sock.sh b/samples/bpf/test_cgrp2_sock.sh deleted file mode 100755 index 36bd7cb46f06..000000000000 --- a/samples/bpf/test_cgrp2_sock.sh +++ /dev/null @@ -1,137 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -# Test various socket options that can be set by attaching programs to cgroups. - -MY_DIR=$(dirname $0) -TEST=$MY_DIR/test_cgrp2_sock -CGRP_MNT="/tmp/cgroupv2-test_cgrp2_sock" - -################################################################################ -# -print_result() -{ - local rc=$1 - local status=" OK " - - [ $rc -ne 0 ] && status="FAIL" - - printf "%-50s [%4s]\n" "$2" "$status" -} - -check_sock() -{ - out=$($TEST) - echo $out | grep -q "$1" - if [ $? -ne 0 ]; then - print_result 1 "IPv4: $2" - echo " expected: $1" - echo " have: $out" - rc=1 - else - print_result 0 "IPv4: $2" - fi -} - -check_sock6() -{ - out=$($TEST -6) - echo $out | grep -q "$1" - if [ $? -ne 0 ]; then - print_result 1 "IPv6: $2" - echo " expected: $1" - echo " have: $out" - rc=1 - else - print_result 0 "IPv6: $2" - fi -} - -################################################################################ -# - -cleanup() -{ - echo $$ >> ${CGRP_MNT}/cgroup.procs - rmdir ${CGRP_MNT}/sockopts -} - -cleanup_and_exit() -{ - local rc=$1 - local msg="$2" - - [ -n "$msg" ] && echo "ERROR: $msg" - - $TEST -d ${CGRP_MNT}/sockopts - ip li del cgrp2_sock - umount ${CGRP_MNT} - - exit $rc -} - - -################################################################################ -# main - -rc=0 - -ip li add cgrp2_sock type dummy 2>/dev/null - -set -e -mkdir -p ${CGRP_MNT} -mount -t cgroup2 none ${CGRP_MNT} -set +e - - -# make sure we have a known start point -cleanup 2>/dev/null - -mkdir -p ${CGRP_MNT}/sockopts -[ $? -ne 0 ] && cleanup_and_exit 1 "Failed to create cgroup hierarchy" - - -# set pid into cgroup -echo $$ > ${CGRP_MNT}/sockopts/cgroup.procs - -# no bpf program attached, so socket should show no settings -check_sock "dev , mark 0, priority 0" "No programs attached" -check_sock6 "dev , mark 0, priority 0" "No programs attached" - -# verify device is set -# -$TEST -b cgrp2_sock ${CGRP_MNT}/sockopts -if [ $? -ne 0 ]; then - cleanup_and_exit 1 "Failed to install program to set device" -fi -check_sock "dev cgrp2_sock, mark 0, priority 0" "Device set" -check_sock6 "dev cgrp2_sock, mark 0, priority 0" "Device set" - -# verify mark is set -# -$TEST -m 666 ${CGRP_MNT}/sockopts -if [ $? -ne 0 ]; then - cleanup_and_exit 1 "Failed to install program to set mark" -fi -check_sock "dev , mark 666, priority 0" "Mark set" -check_sock6 "dev , mark 666, priority 0" "Mark set" - -# verify priority is set -# -$TEST -p 123 ${CGRP_MNT}/sockopts -if [ $? -ne 0 ]; then - cleanup_and_exit 1 "Failed to install program to set priority" -fi -check_sock "dev , mark 0, priority 123" "Priority set" -check_sock6 "dev , mark 0, priority 123" "Priority set" - -# all 3 at once -# -$TEST -b cgrp2_sock -m 666 -p 123 ${CGRP_MNT}/sockopts -if [ $? -ne 0 ]; then - cleanup_and_exit 1 "Failed to install program to set device, mark and priority" -fi -check_sock "dev cgrp2_sock, mark 666, priority 123" "Priority set" -check_sock6 "dev cgrp2_sock, mark 666, priority 123" "Priority set" - -cleanup_and_exit $rc diff --git a/samples/bpf/test_cgrp2_sock2.c b/samples/bpf/test_cgrp2_sock2.c deleted file mode 100644 index e7060aaa2f5a..000000000000 --- a/samples/bpf/test_cgrp2_sock2.c +++ /dev/null @@ -1,95 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* eBPF example program: - * - * - Loads eBPF program - * - * The eBPF program loads a filter from file and attaches the - * program to a cgroup using BPF_PROG_ATTACH - */ - -#define _GNU_SOURCE - -#include <stdio.h> -#include <stdlib.h> -#include <stddef.h> -#include <string.h> -#include <unistd.h> -#include <assert.h> -#include <errno.h> -#include <fcntl.h> -#include <net/if.h> -#include <linux/bpf.h> -#include <bpf/bpf.h> -#include <bpf/libbpf.h> - -#include "bpf_insn.h" - -static int usage(const char *argv0) -{ - printf("Usage: %s cg-path filter-path [filter-id]\n", argv0); - return EXIT_FAILURE; -} - -int main(int argc, char **argv) -{ - int cg_fd, err, ret = EXIT_FAILURE, filter_id = 0, prog_cnt = 0; - const char *link_pin_path = "/sys/fs/bpf/test_cgrp2_sock2"; - struct bpf_link *link = NULL; - struct bpf_program *progs[2]; - struct bpf_program *prog; - struct bpf_object *obj; - - if (argc < 3) - return usage(argv[0]); - - if (argc > 3) - filter_id = atoi(argv[3]); - - cg_fd = open(argv[1], O_DIRECTORY | O_RDONLY); - if (cg_fd < 0) { - printf("Failed to open cgroup path: '%s'\n", strerror(errno)); - return ret; - } - - obj = bpf_object__open_file(argv[2], NULL); - if (libbpf_get_error(obj)) { - printf("ERROR: opening BPF object file failed\n"); - return ret; - } - - bpf_object__for_each_program(prog, obj) { - progs[prog_cnt] = prog; - prog_cnt++; - } - - if (filter_id >= prog_cnt) { - printf("Invalid program id; program not found in file\n"); - goto cleanup; - } - - /* load BPF program */ - if (bpf_object__load(obj)) { - printf("ERROR: loading BPF object file failed\n"); - goto cleanup; - } - - link = bpf_program__attach_cgroup(progs[filter_id], cg_fd); - if (libbpf_get_error(link)) { - printf("ERROR: bpf_program__attach failed\n"); - link = NULL; - goto cleanup; - } - - err = bpf_link__pin(link, link_pin_path); - if (err < 0) { - printf("ERROR: bpf_link__pin failed: %d\n", err); - goto cleanup; - } - - ret = EXIT_SUCCESS; - -cleanup: - bpf_link__destroy(link); - bpf_object__close(obj); - return ret; -} diff --git a/samples/bpf/test_cgrp2_sock2.sh b/samples/bpf/test_cgrp2_sock2.sh deleted file mode 100755 index 82acff93d739..000000000000 --- a/samples/bpf/test_cgrp2_sock2.sh +++ /dev/null @@ -1,103 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -BPFFS=/sys/fs/bpf -MY_DIR=$(dirname $0) -TEST=$MY_DIR/test_cgrp2_sock2 -LINK_PIN=$BPFFS/test_cgrp2_sock2 -BPF_PROG=$MY_DIR/sock_flags.bpf.o - -function config_device { - ip netns add at_ns0 - ip link add veth0 type veth peer name veth0b - ip link set veth0 netns at_ns0 - ip netns exec at_ns0 sysctl -q net.ipv6.conf.veth0.disable_ipv6=0 - ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0 - ip netns exec at_ns0 ip addr add 2401:db00::1/64 dev veth0 nodad - ip netns exec at_ns0 ip link set dev veth0 up - sysctl -q net.ipv6.conf.veth0b.disable_ipv6=0 - ip addr add 172.16.1.101/24 dev veth0b - ip addr add 2401:db00::2/64 dev veth0b nodad - ip link set veth0b up -} - -function config_cgroup { - rm -rf /tmp/cgroupv2 - mkdir -p /tmp/cgroupv2 - mount -t cgroup2 none /tmp/cgroupv2 - mkdir -p /tmp/cgroupv2/foo - echo $$ >> /tmp/cgroupv2/foo/cgroup.procs -} - -function config_bpffs { - if mount | grep $BPFFS > /dev/null; then - echo "bpffs already mounted" - else - echo "bpffs not mounted. Mounting..." - mount -t bpf none $BPFFS - fi -} - -function attach_bpf { - $TEST /tmp/cgroupv2/foo $BPF_PROG $1 - [ $? -ne 0 ] && exit 1 -} - -function cleanup { - rm -rf $LINK_PIN - ip link del veth0b - ip netns delete at_ns0 - umount /tmp/cgroupv2 - rm -rf /tmp/cgroupv2 -} - -cleanup 2>/dev/null - -set -e -config_device -config_cgroup -config_bpffs -set +e - -# -# Test 1 - fail ping6 -# -attach_bpf 0 -ping -c1 -w1 172.16.1.100 -if [ $? -ne 0 ]; then - echo "ping failed when it should succeed" - cleanup - exit 1 -fi - -ping6 -c1 -w1 2401:db00::1 -if [ $? -eq 0 ]; then - echo "ping6 succeeded when it should not" - cleanup - exit 1 -fi - -rm -rf $LINK_PIN -sleep 1 # Wait for link detach - -# -# Test 2 - fail ping -# -attach_bpf 1 -ping6 -c1 -w1 2401:db00::1 -if [ $? -ne 0 ]; then - echo "ping6 failed when it should succeed" - cleanup - exit 1 -fi - -ping -c1 -w1 172.16.1.100 -if [ $? -eq 0 ]; then - echo "ping succeeded when it should not" - cleanup - exit 1 -fi - -cleanup -echo -echo "*** PASS ***" diff --git a/samples/bpf/test_cgrp2_tc.bpf.c b/samples/bpf/test_cgrp2_tc.bpf.c deleted file mode 100644 index c7d2291d676f..000000000000 --- a/samples/bpf/test_cgrp2_tc.bpf.c +++ /dev/null @@ -1,56 +0,0 @@ -/* Copyright (c) 2016 Facebook - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - */ -#define KBUILD_MODNAME "foo" -#include "vmlinux.h" -#include "net_shared.h" -#include <bpf/bpf_helpers.h> - -/* copy of 'struct ethhdr' without __packed */ -struct eth_hdr { - unsigned char h_dest[ETH_ALEN]; - unsigned char h_source[ETH_ALEN]; - unsigned short h_proto; -}; - -struct { - __uint(type, BPF_MAP_TYPE_CGROUP_ARRAY); - __type(key, u32); - __type(value, u32); - __uint(pinning, LIBBPF_PIN_BY_NAME); - __uint(max_entries, 1); -} test_cgrp2_array_pin SEC(".maps"); - -SEC("filter") -int handle_egress(struct __sk_buff *skb) -{ - void *data = (void *)(long)skb->data; - struct eth_hdr *eth = data; - struct ipv6hdr *ip6h = data + sizeof(*eth); - void *data_end = (void *)(long)skb->data_end; - char dont_care_msg[] = "dont care %04x %d\n"; - char pass_msg[] = "pass\n"; - char reject_msg[] = "reject\n"; - - /* single length check */ - if (data + sizeof(*eth) + sizeof(*ip6h) > data_end) - return TC_ACT_OK; - - if (eth->h_proto != bpf_htons(ETH_P_IPV6) || - ip6h->nexthdr != IPPROTO_ICMPV6) { - bpf_trace_printk(dont_care_msg, sizeof(dont_care_msg), - eth->h_proto, ip6h->nexthdr); - return TC_ACT_OK; - } else if (bpf_skb_under_cgroup(skb, &test_cgrp2_array_pin, 0) != 1) { - bpf_trace_printk(pass_msg, sizeof(pass_msg)); - return TC_ACT_OK; - } else { - bpf_trace_printk(reject_msg, sizeof(reject_msg)); - return TC_ACT_SHOT; - } -} - -char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/test_cgrp2_tc.sh b/samples/bpf/test_cgrp2_tc.sh deleted file mode 100755 index 38e8dbc9d16e..000000000000 --- a/samples/bpf/test_cgrp2_tc.sh +++ /dev/null @@ -1,187 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -MY_DIR=$(dirname $0) -# Details on the bpf prog -BPF_CGRP2_ARRAY_NAME='test_cgrp2_array_pin' -BPF_PROG="$MY_DIR/test_cgrp2_tc.bpf.o" -BPF_SECTION='filter' - -[ -z "$TC" ] && TC='tc' -[ -z "$IP" ] && IP='ip' - -# Names of the veth interface, net namespace...etc. -HOST_IFC='ve' -NS_IFC='vens' -NS='ns' - -find_mnt() { - cat /proc/mounts | \ - awk '{ if ($3 == "'$1'" && mnt == "") { mnt = $2 }} END { print mnt }' -} - -# Init cgroup2 vars -init_cgrp2_vars() { - CGRP2_ROOT=$(find_mnt cgroup2) - if [ -z "$CGRP2_ROOT" ] - then - CGRP2_ROOT='/mnt/cgroup2' - MOUNT_CGRP2="yes" - fi - CGRP2_TC="$CGRP2_ROOT/tc" - CGRP2_TC_LEAF="$CGRP2_TC/leaf" -} - -# Init bpf fs vars -init_bpf_fs_vars() { - local bpf_fs_root=$(find_mnt bpf) - [ -n "$bpf_fs_root" ] || return -1 - BPF_FS_TC_SHARE="$bpf_fs_root/tc/globals" -} - -setup_cgrp2() { - case $1 in - start) - if [ "$MOUNT_CGRP2" == 'yes' ] - then - [ -d $CGRP2_ROOT ] || mkdir -p $CGRP2_ROOT - mount -t cgroup2 none $CGRP2_ROOT || return $? - fi - mkdir -p $CGRP2_TC_LEAF - ;; - *) - rmdir $CGRP2_TC_LEAF && rmdir $CGRP2_TC - [ "$MOUNT_CGRP2" == 'yes' ] && umount $CGRP2_ROOT - ;; - esac -} - -setup_bpf_cgrp2_array() { - local bpf_cgrp2_array="$BPF_FS_TC_SHARE/$BPF_CGRP2_ARRAY_NAME" - case $1 in - start) - $MY_DIR/test_cgrp2_array_pin -U $bpf_cgrp2_array -v $CGRP2_TC - ;; - *) - [ -d "$BPF_FS_TC_SHARE" ] && rm -f $bpf_cgrp2_array - ;; - esac -} - -setup_net() { - case $1 in - start) - $IP link add $HOST_IFC type veth peer name $NS_IFC || return $? - $IP link set dev $HOST_IFC up || return $? - sysctl -q net.ipv6.conf.$HOST_IFC.disable_ipv6=0 - sysctl -q net.ipv6.conf.$HOST_IFC.accept_dad=0 - - $IP netns add $NS || return $? - $IP link set dev $NS_IFC netns $NS || return $? - $IP -n $NS link set dev $NS_IFC up || return $? - $IP netns exec $NS sysctl -q net.ipv6.conf.$NS_IFC.disable_ipv6=0 - $IP netns exec $NS sysctl -q net.ipv6.conf.$NS_IFC.accept_dad=0 - $TC qdisc add dev $HOST_IFC clsact || return $? - $TC filter add dev $HOST_IFC egress bpf da obj $BPF_PROG sec $BPF_SECTION || return $? - ;; - *) - $IP netns del $NS - $IP link del $HOST_IFC - ;; - esac -} - -run_in_cgrp() { - # Fork another bash and move it under the specified cgroup. - # It makes the cgroup cleanup easier at the end of the test. - cmd='echo $$ > ' - cmd="$cmd $1/cgroup.procs; exec $2" - bash -c "$cmd" -} - -do_test() { - run_in_cgrp $CGRP2_TC_LEAF "ping -6 -c3 ff02::1%$HOST_IFC >& /dev/null" - local dropped=$($TC -s qdisc show dev $HOST_IFC | tail -3 | \ - awk '/drop/{print substr($7, 0, index($7, ",")-1)}') - if [[ $dropped -eq 0 ]] - then - echo "FAIL" - return 1 - else - echo "Successfully filtered $dropped packets" - return 0 - fi -} - -do_exit() { - if [ "$DEBUG" == "yes" ] && [ "$MODE" != 'cleanuponly' ] - then - echo "------ DEBUG ------" - echo "mount: "; mount | grep -E '(cgroup2|bpf)'; echo - echo "$CGRP2_TC_LEAF: "; ls -l $CGRP2_TC_LEAF; echo - if [ -d "$BPF_FS_TC_SHARE" ] - then - echo "$BPF_FS_TC_SHARE: "; ls -l $BPF_FS_TC_SHARE; echo - fi - echo "Host net:" - $IP netns - $IP link show dev $HOST_IFC - $IP -6 a show dev $HOST_IFC - $TC -s qdisc show dev $HOST_IFC - echo - echo "$NS net:" - $IP -n $NS link show dev $NS_IFC - $IP -n $NS -6 link show dev $NS_IFC - echo "------ DEBUG ------" - echo - fi - - if [ "$MODE" != 'nocleanup' ] - then - setup_net stop - setup_bpf_cgrp2_array stop - setup_cgrp2 stop - fi -} - -init_cgrp2_vars -init_bpf_fs_vars - -while [[ $# -ge 1 ]] -do - a="$1" - case $a in - debug) - DEBUG='yes' - shift 1 - ;; - cleanup-only) - MODE='cleanuponly' - shift 1 - ;; - no-cleanup) - MODE='nocleanup' - shift 1 - ;; - *) - echo "test_cgrp2_tc [debug] [cleanup-only | no-cleanup]" - echo " debug: Print cgrp and network setup details at the end of the test" - echo " cleanup-only: Try to cleanup things from last test. No test will be run" - echo " no-cleanup: Run the test but don't do cleanup at the end" - echo "[Note: If no arg is given, it will run the test and do cleanup at the end]" - echo - exit -1 - ;; - esac -done - -trap do_exit 0 - -[ "$MODE" == 'cleanuponly' ] && exit - -setup_cgrp2 start || exit $? -setup_net start || exit $? -init_bpf_fs_vars || exit $? -setup_bpf_cgrp2_array start || exit $? -do_test -echo diff --git a/samples/bpf/test_current_task_under_cgroup.bpf.c b/samples/bpf/test_current_task_under_cgroup.bpf.c deleted file mode 100644 index 58b9cf7ed659..000000000000 --- a/samples/bpf/test_current_task_under_cgroup.bpf.c +++ /dev/null @@ -1,43 +0,0 @@ -/* Copyright (c) 2016 Sargun Dhillon <sargun@sargun.me> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - */ - -#include "vmlinux.h" -#include <linux/version.h> -#include <bpf/bpf_helpers.h> -#include <bpf/bpf_tracing.h> -#include <bpf/bpf_core_read.h> - -struct { - __uint(type, BPF_MAP_TYPE_CGROUP_ARRAY); - __uint(key_size, sizeof(u32)); - __uint(value_size, sizeof(u32)); - __uint(max_entries, 1); -} cgroup_map SEC(".maps"); - -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __type(key, u32); - __type(value, u64); - __uint(max_entries, 1); -} perf_map SEC(".maps"); - -/* Writes the last PID that called sync to a map at index 0 */ -SEC("ksyscall/sync") -int BPF_KSYSCALL(bpf_prog1) -{ - u64 pid = bpf_get_current_pid_tgid(); - int idx = 0; - - if (!bpf_current_task_under_cgroup(&cgroup_map, 0)) - return 0; - - bpf_map_update_elem(&perf_map, &idx, &pid, BPF_ANY); - return 0; -} - -char _license[] SEC("license") = "GPL"; -u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/test_current_task_under_cgroup_user.c b/samples/bpf/test_current_task_under_cgroup_user.c deleted file mode 100644 index 9726ed2a8a8b..000000000000 --- a/samples/bpf/test_current_task_under_cgroup_user.c +++ /dev/null @@ -1,115 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* Copyright (c) 2016 Sargun Dhillon <sargun@sargun.me> - */ - -#define _GNU_SOURCE -#include <stdio.h> -#include <unistd.h> -#include <bpf/bpf.h> -#include <bpf/libbpf.h> -#include "cgroup_helpers.h" - -#define CGROUP_PATH "/my-cgroup" - -int main(int argc, char **argv) -{ - pid_t remote_pid, local_pid = getpid(); - int cg2 = -1, idx = 0, rc = 1; - struct bpf_link *link = NULL; - struct bpf_program *prog; - struct bpf_object *obj; - char filename[256]; - int map_fd[2]; - - snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]); - obj = bpf_object__open_file(filename, NULL); - if (libbpf_get_error(obj)) { - fprintf(stderr, "ERROR: opening BPF object file failed\n"); - return 0; - } - - prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); - if (!prog) { - printf("finding a prog in obj file failed\n"); - goto cleanup; - } - - /* load BPF program */ - if (bpf_object__load(obj)) { - fprintf(stderr, "ERROR: loading BPF object file failed\n"); - goto cleanup; - } - - map_fd[0] = bpf_object__find_map_fd_by_name(obj, "cgroup_map"); - map_fd[1] = bpf_object__find_map_fd_by_name(obj, "perf_map"); - if (map_fd[0] < 0 || map_fd[1] < 0) { - fprintf(stderr, "ERROR: finding a map in obj file failed\n"); - goto cleanup; - } - - link = bpf_program__attach(prog); - if (libbpf_get_error(link)) { - fprintf(stderr, "ERROR: bpf_program__attach failed\n"); - link = NULL; - goto cleanup; - } - - if (setup_cgroup_environment()) - goto err; - - cg2 = create_and_get_cgroup(CGROUP_PATH); - - if (cg2 < 0) - goto err; - - if (bpf_map_update_elem(map_fd[0], &idx, &cg2, BPF_ANY)) { - log_err("Adding target cgroup to map"); - goto err; - } - - if (join_cgroup(CGROUP_PATH)) - goto err; - - /* - * The installed helper program catched the sync call, and should - * write it to the map. - */ - - sync(); - bpf_map_lookup_elem(map_fd[1], &idx, &remote_pid); - - if (local_pid != remote_pid) { - fprintf(stderr, - "BPF Helper didn't write correct PID to map, but: %d\n", - remote_pid); - goto err; - } - - /* Verify the negative scenario; leave the cgroup */ - if (join_cgroup("/")) - goto err; - - remote_pid = 0; - bpf_map_update_elem(map_fd[1], &idx, &remote_pid, BPF_ANY); - - sync(); - bpf_map_lookup_elem(map_fd[1], &idx, &remote_pid); - - if (local_pid == remote_pid) { - fprintf(stderr, "BPF cgroup negative test did not work\n"); - goto err; - } - - rc = 0; - -err: - if (cg2 != -1) - close(cg2); - - cleanup_cgroup_environment(); - -cleanup: - bpf_link__destroy(link); - bpf_object__close(obj); - return rc; -} diff --git a/samples/bpf/test_overhead_kprobe.bpf.c b/samples/bpf/test_overhead_kprobe.bpf.c deleted file mode 100644 index 668cf5259c60..000000000000 --- a/samples/bpf/test_overhead_kprobe.bpf.c +++ /dev/null @@ -1,41 +0,0 @@ -/* Copyright (c) 2016 Facebook - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - */ -#include "vmlinux.h" -#include <linux/version.h> -#include <bpf/bpf_helpers.h> -#include <bpf/bpf_tracing.h> -#include <bpf/bpf_core_read.h> - -SEC("kprobe/__set_task_comm") -int prog(struct pt_regs *ctx) -{ - struct signal_struct *signal; - struct task_struct *tsk; - char oldcomm[TASK_COMM_LEN] = {}; - char newcomm[TASK_COMM_LEN] = {}; - u16 oom_score_adj; - u32 pid; - - tsk = (void *)PT_REGS_PARM1_CORE(ctx); - - pid = BPF_CORE_READ(tsk, pid); - bpf_core_read_str(oldcomm, sizeof(oldcomm), &tsk->comm); - bpf_core_read_str(newcomm, sizeof(newcomm), - (void *)PT_REGS_PARM2(ctx)); - signal = BPF_CORE_READ(tsk, signal); - oom_score_adj = BPF_CORE_READ(signal, oom_score_adj); - return 0; -} - -SEC("kprobe/fib_table_lookup") -int prog2(struct pt_regs *ctx) -{ - return 0; -} - -char _license[] SEC("license") = "GPL"; -u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/test_overhead_raw_tp.bpf.c b/samples/bpf/test_overhead_raw_tp.bpf.c deleted file mode 100644 index 6af39fe3f8dd..000000000000 --- a/samples/bpf/test_overhead_raw_tp.bpf.c +++ /dev/null @@ -1,17 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2018 Facebook */ -#include "vmlinux.h" -#include <bpf/bpf_helpers.h> - -SEC("raw_tracepoint/task_rename") -int prog(struct bpf_raw_tracepoint_args *ctx) -{ - return 0; -} - -SEC("raw_tracepoint/fib_table_lookup") -int prog2(struct bpf_raw_tracepoint_args *ctx) -{ - return 0; -} -char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/test_overhead_tp.bpf.c b/samples/bpf/test_overhead_tp.bpf.c deleted file mode 100644 index 5dc08b587978..000000000000 --- a/samples/bpf/test_overhead_tp.bpf.c +++ /dev/null @@ -1,23 +0,0 @@ -/* Copyright (c) 2016 Facebook - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - */ -#include "vmlinux.h" -#include <bpf/bpf_helpers.h> - -/* from /sys/kernel/tracing/events/task/task_rename/format */ -SEC("tracepoint/task/task_rename") -int prog(struct trace_event_raw_task_rename *ctx) -{ - return 0; -} - -/* from /sys/kernel/tracing/events/fib/fib_table_lookup/format */ -SEC("tracepoint/fib/fib_table_lookup") -int prog2(struct trace_event_raw_fib_table_lookup *ctx) -{ - return 0; -} -char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c deleted file mode 100644 index dbd86f7b1473..000000000000 --- a/samples/bpf/test_overhead_user.c +++ /dev/null @@ -1,225 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* Copyright (c) 2016 Facebook - */ -#define _GNU_SOURCE -#include <sched.h> -#include <errno.h> -#include <stdio.h> -#include <sys/types.h> -#include <asm/unistd.h> -#include <fcntl.h> -#include <unistd.h> -#include <assert.h> -#include <sys/wait.h> -#include <sys/socket.h> -#include <arpa/inet.h> -#include <stdlib.h> -#include <signal.h> -#include <linux/bpf.h> -#include <string.h> -#include <time.h> -#include <bpf/bpf.h> -#include <bpf/libbpf.h> - -#define MAX_CNT 1000000 -#define DUMMY_IP "127.0.0.1" -#define DUMMY_PORT 80 - -static struct bpf_link *links[2]; -static struct bpf_object *obj; -static int cnt; - -static __u64 time_get_ns(void) -{ - struct timespec ts; - - clock_gettime(CLOCK_MONOTONIC, &ts); - return ts.tv_sec * 1000000000ull + ts.tv_nsec; -} - -static void test_task_rename(int cpu) -{ - char buf[] = "test\n"; - __u64 start_time; - int i, fd; - - fd = open("/proc/self/comm", O_WRONLY|O_TRUNC); - if (fd < 0) { - printf("couldn't open /proc\n"); - exit(1); - } - start_time = time_get_ns(); - for (i = 0; i < MAX_CNT; i++) { - if (write(fd, buf, sizeof(buf)) < 0) { - printf("task rename failed: %s\n", strerror(errno)); - close(fd); - return; - } - } - printf("task_rename:%d: %lld events per sec\n", - cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); - close(fd); -} - -static void test_fib_table_lookup(int cpu) -{ - struct sockaddr_in addr; - char buf[] = "test\n"; - __u64 start_time; - int i, fd; - - fd = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP); - if (fd < 0) { - printf("couldn't open socket\n"); - exit(1); - } - memset((char *)&addr, 0, sizeof(addr)); - addr.sin_addr.s_addr = inet_addr(DUMMY_IP); - addr.sin_port = htons(DUMMY_PORT); - addr.sin_family = AF_INET; - start_time = time_get_ns(); - for (i = 0; i < MAX_CNT; i++) { - if (sendto(fd, buf, strlen(buf), 0, - (struct sockaddr *)&addr, sizeof(addr)) < 0) { - printf("failed to start ping: %s\n", strerror(errno)); - close(fd); - return; - } - } - printf("fib_table_lookup:%d: %lld events per sec\n", - cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); - close(fd); -} - -static void loop(int cpu, int flags) -{ - cpu_set_t cpuset; - - CPU_ZERO(&cpuset); - CPU_SET(cpu, &cpuset); - sched_setaffinity(0, sizeof(cpuset), &cpuset); - - if (flags & 1) - test_task_rename(cpu); - if (flags & 2) - test_fib_table_lookup(cpu); -} - -static void run_perf_test(int tasks, int flags) -{ - pid_t pid[tasks]; - int i; - - for (i = 0; i < tasks; i++) { - pid[i] = fork(); - if (pid[i] == 0) { - loop(i, flags); - exit(0); - } else if (pid[i] == -1) { - printf("couldn't spawn #%d process\n", i); - exit(1); - } - } - for (i = 0; i < tasks; i++) { - int status; - - assert(waitpid(pid[i], &status, 0) == pid[i]); - assert(status == 0); - } -} - -static int load_progs(char *filename) -{ - struct bpf_program *prog; - int err = 0; - - obj = bpf_object__open_file(filename, NULL); - err = libbpf_get_error(obj); - if (err < 0) { - fprintf(stderr, "ERROR: opening BPF object file failed\n"); - return err; - } - - /* load BPF program */ - err = bpf_object__load(obj); - if (err < 0) { - fprintf(stderr, "ERROR: loading BPF object file failed\n"); - return err; - } - - bpf_object__for_each_program(prog, obj) { - links[cnt] = bpf_program__attach(prog); - err = libbpf_get_error(links[cnt]); - if (err < 0) { - fprintf(stderr, "ERROR: bpf_program__attach failed\n"); - links[cnt] = NULL; - return err; - } - cnt++; - } - - return err; -} - -static void unload_progs(void) -{ - while (cnt) - bpf_link__destroy(links[--cnt]); - - bpf_object__close(obj); -} - -int main(int argc, char **argv) -{ - int num_cpu = sysconf(_SC_NPROCESSORS_ONLN); - int test_flags = ~0; - char filename[256]; - int err = 0; - - - if (argc > 1) - test_flags = atoi(argv[1]) ? : test_flags; - if (argc > 2) - num_cpu = atoi(argv[2]) ? : num_cpu; - - if (test_flags & 0x3) { - printf("BASE\n"); - run_perf_test(num_cpu, test_flags); - } - - if (test_flags & 0xC) { - snprintf(filename, sizeof(filename), - "%s_kprobe.bpf.o", argv[0]); - - printf("w/KPROBE\n"); - err = load_progs(filename); - if (!err) - run_perf_test(num_cpu, test_flags >> 2); - - unload_progs(); - } - - if (test_flags & 0x30) { - snprintf(filename, sizeof(filename), - "%s_tp.bpf.o", argv[0]); - printf("w/TRACEPOINT\n"); - err = load_progs(filename); - if (!err) - run_perf_test(num_cpu, test_flags >> 4); - - unload_progs(); - } - - if (test_flags & 0xC0) { - snprintf(filename, sizeof(filename), - "%s_raw_tp.bpf.o", argv[0]); - printf("w/RAW_TRACEPOINT\n"); - err = load_progs(filename); - if (!err) - run_perf_test(num_cpu, test_flags >> 6); - - unload_progs(); - } - - return err; -} diff --git a/samples/bpf/test_override_return.sh b/samples/bpf/test_override_return.sh deleted file mode 100755 index 35db26f736b9..000000000000 --- a/samples/bpf/test_override_return.sh +++ /dev/null @@ -1,16 +0,0 @@ -#!/bin/bash - -rm -r tmpmnt -rm -f testfile.img -dd if=/dev/zero of=testfile.img bs=1M seek=1000 count=1 -DEVICE=$(losetup --show -f testfile.img) -mkfs.btrfs -f $DEVICE -mkdir tmpmnt -./tracex7 $DEVICE -if [ $? -eq 0 ] -then - echo "SUCCESS!" -else - echo "FAILED!" -fi -losetup -d $DEVICE diff --git a/samples/bpf/test_probe_write_user.bpf.c b/samples/bpf/test_probe_write_user.bpf.c deleted file mode 100644 index a4f3798b7fb0..000000000000 --- a/samples/bpf/test_probe_write_user.bpf.c +++ /dev/null @@ -1,52 +0,0 @@ -/* Copyright (c) 2016 Sargun Dhillon <sargun@sargun.me> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - */ -#include "vmlinux.h" -#include <string.h> -#include <linux/version.h> -#include <bpf/bpf_helpers.h> -#include <bpf/bpf_tracing.h> -#include <bpf/bpf_core_read.h> - -struct { - __uint(type, BPF_MAP_TYPE_HASH); - __type(key, struct sockaddr_in); - __type(value, struct sockaddr_in); - __uint(max_entries, 256); -} dnat_map SEC(".maps"); - -/* kprobe is NOT a stable ABI - * kernel functions can be removed, renamed or completely change semantics. - * Number of arguments and their positions can change, etc. - * In such case this bpf+kprobe example will no longer be meaningful - * - * This example sits on a syscall, and the syscall ABI is relatively stable - * of course, across platforms, and over time, the ABI may change. - */ -SEC("ksyscall/connect") -int BPF_KSYSCALL(bpf_prog1, int fd, struct sockaddr_in *uservaddr, - int addrlen) -{ - struct sockaddr_in new_addr, orig_addr = {}; - struct sockaddr_in *mapped_addr; - - if (addrlen > sizeof(orig_addr)) - return 0; - - if (bpf_probe_read_user(&orig_addr, sizeof(orig_addr), uservaddr) != 0) - return 0; - - mapped_addr = bpf_map_lookup_elem(&dnat_map, &orig_addr); - if (mapped_addr != NULL) { - memcpy(&new_addr, mapped_addr, sizeof(new_addr)); - bpf_probe_write_user(uservaddr, &new_addr, - sizeof(new_addr)); - } - return 0; -} - -char _license[] SEC("license") = "GPL"; -u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/test_probe_write_user_user.c b/samples/bpf/test_probe_write_user_user.c deleted file mode 100644 index 2a539aec4116..000000000000 --- a/samples/bpf/test_probe_write_user_user.c +++ /dev/null @@ -1,108 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <stdio.h> -#include <assert.h> -#include <unistd.h> -#include <bpf/bpf.h> -#include <bpf/libbpf.h> -#include <sys/socket.h> -#include <netinet/in.h> -#include <arpa/inet.h> - -int main(int ac, char **argv) -{ - struct sockaddr_in *serv_addr_in, *mapped_addr_in, *tmp_addr_in; - struct sockaddr serv_addr, mapped_addr, tmp_addr; - int serverfd, serverconnfd, clientfd, map_fd; - struct bpf_link *link = NULL; - struct bpf_program *prog; - struct bpf_object *obj; - socklen_t sockaddr_len; - char filename[256]; - char *ip; - - serv_addr_in = (struct sockaddr_in *)&serv_addr; - mapped_addr_in = (struct sockaddr_in *)&mapped_addr; - tmp_addr_in = (struct sockaddr_in *)&tmp_addr; - - snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]); - obj = bpf_object__open_file(filename, NULL); - if (libbpf_get_error(obj)) { - fprintf(stderr, "ERROR: opening BPF object file failed\n"); - return 0; - } - - prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); - if (libbpf_get_error(prog)) { - fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); - goto cleanup; - } - - /* load BPF program */ - if (bpf_object__load(obj)) { - fprintf(stderr, "ERROR: loading BPF object file failed\n"); - goto cleanup; - } - - map_fd = bpf_object__find_map_fd_by_name(obj, "dnat_map"); - if (map_fd < 0) { - fprintf(stderr, "ERROR: finding a map in obj file failed\n"); - goto cleanup; - } - - link = bpf_program__attach(prog); - if (libbpf_get_error(link)) { - fprintf(stderr, "ERROR: bpf_program__attach failed\n"); - link = NULL; - goto cleanup; - } - - assert((serverfd = socket(AF_INET, SOCK_STREAM, 0)) > 0); - assert((clientfd = socket(AF_INET, SOCK_STREAM, 0)) > 0); - - /* Bind server to ephemeral port on lo */ - memset(&serv_addr, 0, sizeof(serv_addr)); - serv_addr_in->sin_family = AF_INET; - serv_addr_in->sin_port = 0; - serv_addr_in->sin_addr.s_addr = htonl(INADDR_LOOPBACK); - - assert(bind(serverfd, &serv_addr, sizeof(serv_addr)) == 0); - - sockaddr_len = sizeof(serv_addr); - assert(getsockname(serverfd, &serv_addr, &sockaddr_len) == 0); - ip = inet_ntoa(serv_addr_in->sin_addr); - printf("Server bound to: %s:%d\n", ip, ntohs(serv_addr_in->sin_port)); - - memset(&mapped_addr, 0, sizeof(mapped_addr)); - mapped_addr_in->sin_family = AF_INET; - mapped_addr_in->sin_port = htons(5555); - mapped_addr_in->sin_addr.s_addr = inet_addr("255.255.255.255"); - - assert(!bpf_map_update_elem(map_fd, &mapped_addr, &serv_addr, BPF_ANY)); - - assert(listen(serverfd, 5) == 0); - - ip = inet_ntoa(mapped_addr_in->sin_addr); - printf("Client connecting to: %s:%d\n", - ip, ntohs(mapped_addr_in->sin_port)); - assert(connect(clientfd, &mapped_addr, sizeof(mapped_addr)) == 0); - - sockaddr_len = sizeof(tmp_addr); - ip = inet_ntoa(tmp_addr_in->sin_addr); - assert((serverconnfd = accept(serverfd, &tmp_addr, &sockaddr_len)) > 0); - printf("Server received connection from: %s:%d\n", - ip, ntohs(tmp_addr_in->sin_port)); - - sockaddr_len = sizeof(tmp_addr); - assert(getpeername(clientfd, &tmp_addr, &sockaddr_len) == 0); - ip = inet_ntoa(tmp_addr_in->sin_addr); - printf("Client's peer address: %s:%d\n", - ip, ntohs(tmp_addr_in->sin_port)); - - /* Is the server's getsockname = the socket getpeername */ - assert(memcmp(&serv_addr, &tmp_addr, sizeof(struct sockaddr_in)) == 0); - -cleanup: - bpf_link__destroy(link); - bpf_object__close(obj); - return 0; -} diff --git a/samples/bpf/tracex7.bpf.c b/samples/bpf/tracex7.bpf.c deleted file mode 100644 index ab8d6704a5a4..000000000000 --- a/samples/bpf/tracex7.bpf.c +++ /dev/null @@ -1,15 +0,0 @@ -#include "vmlinux.h" -#include <linux/version.h> -#include <bpf/bpf_helpers.h> - -SEC("kprobe/open_ctree") -int bpf_prog1(struct pt_regs *ctx) -{ - unsigned long rc = -12; - - bpf_override_return(ctx, rc); - return 0; -} - -char _license[] SEC("license") = "GPL"; -u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex7_user.c b/samples/bpf/tracex7_user.c deleted file mode 100644 index b10b5e03a226..000000000000 --- a/samples/bpf/tracex7_user.c +++ /dev/null @@ -1,56 +0,0 @@ -#define _GNU_SOURCE - -#include <stdio.h> -#include <unistd.h> -#include <bpf/libbpf.h> - -int main(int argc, char **argv) -{ - struct bpf_link *link = NULL; - struct bpf_program *prog; - struct bpf_object *obj; - char filename[256]; - char command[256]; - int ret = 0; - FILE *f; - - if (!argv[1]) { - fprintf(stderr, "ERROR: Run with the btrfs device argument!\n"); - return 0; - } - - snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]); - obj = bpf_object__open_file(filename, NULL); - if (libbpf_get_error(obj)) { - fprintf(stderr, "ERROR: opening BPF object file failed\n"); - return 0; - } - - prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); - if (!prog) { - fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); - goto cleanup; - } - - /* load BPF program */ - if (bpf_object__load(obj)) { - fprintf(stderr, "ERROR: loading BPF object file failed\n"); - goto cleanup; - } - - link = bpf_program__attach(prog); - if (libbpf_get_error(link)) { - fprintf(stderr, "ERROR: bpf_program__attach failed\n"); - link = NULL; - goto cleanup; - } - - snprintf(command, 256, "mount %s tmpmnt/", argv[1]); - f = popen(command, "r"); - ret = pclose(f); - -cleanup: - bpf_link__destroy(link); - bpf_object__close(obj); - return ret ? 0 : 1; -} diff --git a/samples/bpf/xdp_adjust_tail_kern.c b/samples/bpf/xdp_adjust_tail_kern.c index ffdd548627f0..da67bcad1c63 100644 --- a/samples/bpf/xdp_adjust_tail_kern.c +++ b/samples/bpf/xdp_adjust_tail_kern.c @@ -57,6 +57,7 @@ static __always_inline void swap_mac(void *data, struct ethhdr *orig_eth) static __always_inline __u16 csum_fold_helper(__u32 csum) { + csum = (csum & 0xffff) + (csum >> 16); return ~((csum & 0xffff) + (csum >> 16)); } diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index c55878bddfdd..e74a01a85070 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -37,10 +37,11 @@ class APIElement(object): @desc: textual description of the symbol @ret: (optional) description of any associated return value """ - def __init__(self, proto='', desc='', ret=''): + def __init__(self, proto='', desc='', ret='', attrs=[]): self.proto = proto self.desc = desc self.ret = ret + self.attrs = attrs class Helper(APIElement): @@ -81,6 +82,11 @@ class Helper(APIElement): return res +ATTRS = { + '__bpf_fastcall': 'bpf_fastcall' +} + + class HeaderParser(object): """ An object used to parse a file in order to extract the documentation of a @@ -111,7 +117,8 @@ class HeaderParser(object): proto = self.parse_proto() desc = self.parse_desc(proto) ret = self.parse_ret(proto) - return Helper(proto=proto, desc=desc, ret=ret) + attrs = self.parse_attrs(proto) + return Helper(proto=proto, desc=desc, ret=ret, attrs=attrs) def parse_symbol(self): p = re.compile(r' \* ?(BPF\w+)$') @@ -192,6 +199,28 @@ class HeaderParser(object): raise Exception("No return found for " + proto) return ret + def parse_attrs(self, proto): + p = re.compile(r' \* ?(?:\t| {5,8})Attributes$') + capture = p.match(self.line) + if not capture: + return [] + # Expect a single line with mnemonics for attributes separated by spaces + self.line = self.reader.readline() + p = re.compile(r' \* ?(?:\t| {5,8})(?:\t| {8})(.*)') + capture = p.match(self.line) + if not capture: + raise Exception("Incomplete 'Attributes' section for " + proto) + attrs = capture.group(1).split(' ') + for attr in attrs: + if attr not in ATTRS: + raise Exception("Unexpected attribute '" + attr + "' specified for " + proto) + self.line = self.reader.readline() + if self.line != ' *\n': + raise Exception("Expecting empty line after 'Attributes' section for " + proto) + # Prepare a line for next self.parse_* to consume + self.line = self.reader.readline() + return attrs + def seek_to(self, target, help_message, discard_lines = 1): self.reader.seek(0) offset = self.reader.read().find(target) @@ -789,6 +818,21 @@ class PrinterHelpers(Printer): print('%s;' % fwd) print('') + used_attrs = set() + for helper in self.elements: + for attr in helper.attrs: + used_attrs.add(attr) + for attr in sorted(used_attrs): + print('#ifndef %s' % attr) + print('#if __has_attribute(%s)' % ATTRS[attr]) + print('#define %s __attribute__((%s))' % (attr, ATTRS[attr])) + print('#else') + print('#define %s' % attr) + print('#endif') + print('#endif') + if used_attrs: + print('') + def print_footer(self): footer = '' print(footer) @@ -827,7 +871,10 @@ class PrinterHelpers(Printer): print(' *{}{}'.format(' \t' if line else '', line)) print(' */') - print('static %s %s(* const %s)(' % (self.map_type(proto['ret_type']), + print('static ', end='') + if helper.attrs: + print('%s ' % (" ".join(helper.attrs)), end='') + print('%s %s(* const %s)(' % (self.map_type(proto['ret_type']), proto['ret_star'], proto['name']), end='') comma = '' for i, a in enumerate(proto['args']): diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 7d2af1ff3c8d..547c1ccdce98 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -1,11 +1,15 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2019 Facebook */ +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif #include <errno.h> #include <fcntl.h> #include <linux/err.h> #include <stdbool.h> #include <stdio.h> +#include <stdlib.h> #include <string.h> #include <unistd.h> #include <linux/btf.h> @@ -21,6 +25,7 @@ #include "main.h" #define KFUNC_DECL_TAG "bpf_kfunc" +#define FASTCALL_DECL_TAG "bpf_fastcall" static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_UNKN] = "UNKNOWN", @@ -464,19 +469,59 @@ static int dump_btf_raw(const struct btf *btf, return 0; } +struct ptr_array { + __u32 cnt; + __u32 cap; + const void **elems; +}; + +static int ptr_array_push(const void *ptr, struct ptr_array *arr) +{ + __u32 new_cap; + void *tmp; + + if (arr->cnt == arr->cap) { + new_cap = (arr->cap ?: 16) * 2; + tmp = realloc(arr->elems, sizeof(*arr->elems) * new_cap); + if (!tmp) + return -ENOMEM; + arr->elems = tmp; + arr->cap = new_cap; + } + arr->elems[arr->cnt++] = ptr; + return 0; +} + +static void ptr_array_free(struct ptr_array *arr) +{ + free(arr->elems); +} + +static int cmp_kfuncs(const void *pa, const void *pb, void *ctx) +{ + struct btf *btf = ctx; + const struct btf_type *a = *(void **)pa; + const struct btf_type *b = *(void **)pb; + + return strcmp(btf__str_by_offset(btf, a->name_off), + btf__str_by_offset(btf, b->name_off)); +} + static int dump_btf_kfuncs(struct btf_dump *d, const struct btf *btf) { LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts); - int cnt = btf__type_cnt(btf); - int i; + __u32 cnt = btf__type_cnt(btf), i, j; + struct ptr_array fastcalls = {}; + struct ptr_array kfuncs = {}; + int err = 0; printf("\n/* BPF kfuncs */\n"); printf("#ifndef BPF_NO_KFUNC_PROTOTYPES\n"); for (i = 1; i < cnt; i++) { const struct btf_type *t = btf__type_by_id(btf, i); + const struct btf_type *ft; const char *name; - int err; if (!btf_is_decl_tag(t)) continue; @@ -484,27 +529,53 @@ static int dump_btf_kfuncs(struct btf_dump *d, const struct btf *btf) if (btf_decl_tag(t)->component_idx != -1) continue; - name = btf__name_by_offset(btf, t->name_off); - if (strncmp(name, KFUNC_DECL_TAG, sizeof(KFUNC_DECL_TAG))) + ft = btf__type_by_id(btf, t->type); + if (!btf_is_func(ft)) continue; - t = btf__type_by_id(btf, t->type); - if (!btf_is_func(t)) - continue; + name = btf__name_by_offset(btf, t->name_off); + if (strncmp(name, KFUNC_DECL_TAG, sizeof(KFUNC_DECL_TAG)) == 0) { + err = ptr_array_push(ft, &kfuncs); + if (err) + goto out; + } + + if (strncmp(name, FASTCALL_DECL_TAG, sizeof(FASTCALL_DECL_TAG)) == 0) { + err = ptr_array_push(ft, &fastcalls); + if (err) + goto out; + } + } + + /* Sort kfuncs by name for improved vmlinux.h stability */ + qsort_r(kfuncs.elems, kfuncs.cnt, sizeof(*kfuncs.elems), cmp_kfuncs, (void *)btf); + for (i = 0; i < kfuncs.cnt; i++) { + const struct btf_type *t = kfuncs.elems[i]; printf("extern "); + /* Assume small amount of fastcall kfuncs */ + for (j = 0; j < fastcalls.cnt; j++) { + if (fastcalls.elems[j] == t) { + printf("__bpf_fastcall "); + break; + } + } + opts.field_name = btf__name_by_offset(btf, t->name_off); err = btf_dump__emit_type_decl(d, t->type, &opts); if (err) - return err; + goto out; printf(" __weak __ksym;\n"); } printf("#endif\n\n"); - return 0; +out: + ptr_array_free(&fastcalls); + ptr_array_free(&kfuncs); + return err; } static void __printf(2, 0) btf_dump_printf(void *ctx, @@ -718,6 +789,13 @@ static int dump_btf_c(const struct btf *btf, printf("#ifndef __weak\n"); printf("#define __weak __attribute__((weak))\n"); printf("#endif\n\n"); + printf("#ifndef __bpf_fastcall\n"); + printf("#if __has_attribute(bpf_fastcall)\n"); + printf("#define __bpf_fastcall __attribute__((bpf_fastcall))\n"); + printf("#else\n"); + printf("#define __bpf_fastcall\n"); + printf("#endif\n"); + printf("#endif\n\n"); if (root_type_cnt) { for (i = 0; i < root_type_cnt; i++) { diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index d54aaa0619df..bd9f960bce3d 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -679,8 +679,8 @@ static int sets_patch(struct object *obj) next = rb_first(&obj->sets); while (next) { - struct btf_id_set8 *set8; - struct btf_id_set *set; + struct btf_id_set8 *set8 = NULL; + struct btf_id_set *set = NULL; unsigned long addr, off; struct btf_id *id; diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c index 9a5c1f008fe6..fced54a3adf6 100644 --- a/tools/bpf/runqslower/runqslower.bpf.c +++ b/tools/bpf/runqslower/runqslower.bpf.c @@ -70,7 +70,6 @@ int handle__sched_switch(u64 *ctx) struct task_struct *next = (struct task_struct *)ctx[2]; struct runq_event event = {}; u64 *tsp, delta_us; - long state; u32 pid; /* ivcsw: treat like an enqueue event and store timestamp */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4a939c90dc2e..f28b6527e815 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1973,6 +1973,8 @@ union bpf_attr { * program. * Return * The SMP id of the processor running the program. + * Attributes + * __bpf_fastcall * * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) * Description @@ -3104,10 +3106,6 @@ union bpf_attr { * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration * option, and in this case it only works on functions tagged with * **ALLOW_ERROR_INJECTION** in the kernel code. - * - * Also, the helper is only available for the architectures having - * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, - * x86 architecture is the only one to support this feature. * Return * 0 * @@ -5372,7 +5370,7 @@ union bpf_attr { * Currently, the **flags** must be 0. Currently, nr_loops is * limited to 1 << 23 (~8 million) loops. * - * long (\*callback_fn)(u32 index, void \*ctx); + * long (\*callback_fn)(u64 index, void \*ctx); * * where **index** is the current index in the loop. The index * is zero-indexed. diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 1b22f0f37288..857a5f7b413d 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -61,7 +61,8 @@ ifndef VERBOSE endif INCLUDES = -I$(or $(OUTPUT),.) \ - -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi + -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/arch/$(SRCARCH)/include export prefix libdir src obj diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h index fdf44403ff36..6ff963a491d9 100644 --- a/tools/lib/bpf/bpf_gen_internal.h +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -34,6 +34,7 @@ struct bpf_gen { void *data_cur; void *insn_start; void *insn_cur; + bool swapped_endian; ssize_t cleanup_label; __u32 nr_progs; __u32 nr_maps; diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 80bc0242e8dc..686824b8b413 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -185,6 +185,7 @@ enum libbpf_tristate { #define __kptr_untrusted __attribute__((btf_type_tag("kptr_untrusted"))) #define __kptr __attribute__((btf_type_tag("kptr"))) #define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr"))) +#define __uptr __attribute__((btf_type_tag("uptr"))) #if defined (__clang__) #define bpf_ksym_exists(sym) ({ \ diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 3c131039c523..e9673c0ecbe7 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -2885,7 +2885,7 @@ int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, return btf_commit_type(btf, sz); } -struct btf_ext_sec_setup_param { +struct btf_ext_sec_info_param { __u32 off; __u32 len; __u32 min_rec_size; @@ -2893,14 +2893,20 @@ struct btf_ext_sec_setup_param { const char *desc; }; -static int btf_ext_setup_info(struct btf_ext *btf_ext, - struct btf_ext_sec_setup_param *ext_sec) +/* + * Parse a single info subsection of the BTF.ext info data: + * - validate subsection structure and elements + * - save info subsection start and sizing details in struct btf_ext + * - endian-independent operation, for calling before byte-swapping + */ +static int btf_ext_parse_sec_info(struct btf_ext *btf_ext, + struct btf_ext_sec_info_param *ext_sec, + bool is_native) { const struct btf_ext_info_sec *sinfo; struct btf_ext_info *ext_info; __u32 info_left, record_size; size_t sec_cnt = 0; - /* The start of the info sec (including the __u32 record_size). */ void *info; if (ext_sec->len == 0) @@ -2912,6 +2918,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return -EINVAL; } + /* The start of the info sec (including the __u32 record_size). */ info = btf_ext->data + btf_ext->hdr->hdr_len + ext_sec->off; info_left = ext_sec->len; @@ -2927,9 +2934,13 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return -EINVAL; } - /* The record size needs to meet the minimum standard */ - record_size = *(__u32 *)info; + /* The record size needs to meet either the minimum standard or, when + * handling non-native endianness data, the exact standard so as + * to allow safe byte-swapping. + */ + record_size = is_native ? *(__u32 *)info : bswap_32(*(__u32 *)info); if (record_size < ext_sec->min_rec_size || + (!is_native && record_size != ext_sec->min_rec_size) || record_size & 0x03) { pr_debug("%s section in .BTF.ext has invalid record size %u\n", ext_sec->desc, record_size); @@ -2941,7 +2952,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, /* If no records, return failure now so .BTF.ext won't be used. */ if (!info_left) { - pr_debug("%s section in .BTF.ext has no records", ext_sec->desc); + pr_debug("%s section in .BTF.ext has no records\n", ext_sec->desc); return -EINVAL; } @@ -2956,7 +2967,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return -EINVAL; } - num_records = sinfo->num_info; + num_records = is_native ? sinfo->num_info : bswap_32(sinfo->num_info); if (num_records == 0) { pr_debug("%s section has incorrect num_records in .BTF.ext\n", ext_sec->desc); @@ -2984,64 +2995,157 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return 0; } -static int btf_ext_setup_func_info(struct btf_ext *btf_ext) +/* Parse all info secs in the BTF.ext info data */ +static int btf_ext_parse_info(struct btf_ext *btf_ext, bool is_native) { - struct btf_ext_sec_setup_param param = { + struct btf_ext_sec_info_param func_info = { .off = btf_ext->hdr->func_info_off, .len = btf_ext->hdr->func_info_len, .min_rec_size = sizeof(struct bpf_func_info_min), .ext_info = &btf_ext->func_info, .desc = "func_info" }; - - return btf_ext_setup_info(btf_ext, ¶m); -} - -static int btf_ext_setup_line_info(struct btf_ext *btf_ext) -{ - struct btf_ext_sec_setup_param param = { + struct btf_ext_sec_info_param line_info = { .off = btf_ext->hdr->line_info_off, .len = btf_ext->hdr->line_info_len, .min_rec_size = sizeof(struct bpf_line_info_min), .ext_info = &btf_ext->line_info, .desc = "line_info", }; - - return btf_ext_setup_info(btf_ext, ¶m); -} - -static int btf_ext_setup_core_relos(struct btf_ext *btf_ext) -{ - struct btf_ext_sec_setup_param param = { + struct btf_ext_sec_info_param core_relo = { .off = btf_ext->hdr->core_relo_off, .len = btf_ext->hdr->core_relo_len, .min_rec_size = sizeof(struct bpf_core_relo), .ext_info = &btf_ext->core_relo_info, .desc = "core_relo", }; + int err; + + err = btf_ext_parse_sec_info(btf_ext, &func_info, is_native); + if (err) + return err; + + err = btf_ext_parse_sec_info(btf_ext, &line_info, is_native); + if (err) + return err; + + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + return 0; /* skip core relos parsing */ + + err = btf_ext_parse_sec_info(btf_ext, &core_relo, is_native); + if (err) + return err; + + return 0; +} + +/* Swap byte-order of BTF.ext header with any endianness */ +static void btf_ext_bswap_hdr(struct btf_ext_header *h) +{ + bool is_native = h->magic == BTF_MAGIC; + __u32 hdr_len; + + hdr_len = is_native ? h->hdr_len : bswap_32(h->hdr_len); + + h->magic = bswap_16(h->magic); + h->hdr_len = bswap_32(h->hdr_len); + h->func_info_off = bswap_32(h->func_info_off); + h->func_info_len = bswap_32(h->func_info_len); + h->line_info_off = bswap_32(h->line_info_off); + h->line_info_len = bswap_32(h->line_info_len); + + if (hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + return; + + h->core_relo_off = bswap_32(h->core_relo_off); + h->core_relo_len = bswap_32(h->core_relo_len); +} + +/* Swap byte-order of generic info subsection */ +static void btf_ext_bswap_info_sec(void *info, __u32 len, bool is_native, + info_rec_bswap_fn bswap_fn) +{ + struct btf_ext_info_sec *sec; + __u32 info_left, rec_size, *rs; + + if (len == 0) + return; + + rs = info; /* info record size */ + rec_size = is_native ? *rs : bswap_32(*rs); + *rs = bswap_32(*rs); + + sec = info + sizeof(__u32); /* info sec #1 */ + info_left = len - sizeof(__u32); + while (info_left) { + unsigned int sec_hdrlen = sizeof(struct btf_ext_info_sec); + __u32 i, num_recs; + void *p; + + num_recs = is_native ? sec->num_info : bswap_32(sec->num_info); + sec->sec_name_off = bswap_32(sec->sec_name_off); + sec->num_info = bswap_32(sec->num_info); + p = sec->data; /* info rec #1 */ + for (i = 0; i < num_recs; i++, p += rec_size) + bswap_fn(p); + sec = p; + info_left -= sec_hdrlen + (__u64)rec_size * num_recs; + } +} + +/* + * Swap byte-order of all info data in a BTF.ext section + * - requires BTF.ext hdr in native endianness + */ +static void btf_ext_bswap_info(struct btf_ext *btf_ext, void *data) +{ + const bool is_native = btf_ext->swapped_endian; + const struct btf_ext_header *h = data; + void *info; + + /* Swap func_info subsection byte-order */ + info = data + h->hdr_len + h->func_info_off; + btf_ext_bswap_info_sec(info, h->func_info_len, is_native, + (info_rec_bswap_fn)bpf_func_info_bswap); + + /* Swap line_info subsection byte-order */ + info = data + h->hdr_len + h->line_info_off; + btf_ext_bswap_info_sec(info, h->line_info_len, is_native, + (info_rec_bswap_fn)bpf_line_info_bswap); + + /* Swap core_relo subsection byte-order (if present) */ + if (h->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + return; - return btf_ext_setup_info(btf_ext, ¶m); + info = data + h->hdr_len + h->core_relo_off; + btf_ext_bswap_info_sec(info, h->core_relo_len, is_native, + (info_rec_bswap_fn)bpf_core_relo_bswap); } -static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) +/* Parse hdr data and info sections: check and convert to native endianness */ +static int btf_ext_parse(struct btf_ext *btf_ext) { - const struct btf_ext_header *hdr = (struct btf_ext_header *)data; + __u32 hdr_len, data_size = btf_ext->data_size; + struct btf_ext_header *hdr = btf_ext->hdr; + bool swapped_endian = false; + int err; - if (data_size < offsetofend(struct btf_ext_header, hdr_len) || - data_size < hdr->hdr_len) { - pr_debug("BTF.ext header not found"); + if (data_size < offsetofend(struct btf_ext_header, hdr_len)) { + pr_debug("BTF.ext header too short\n"); return -EINVAL; } + hdr_len = hdr->hdr_len; if (hdr->magic == bswap_16(BTF_MAGIC)) { - pr_warn("BTF.ext in non-native endianness is not supported\n"); - return -ENOTSUP; + swapped_endian = true; + hdr_len = bswap_32(hdr_len); } else if (hdr->magic != BTF_MAGIC) { pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic); return -EINVAL; } - if (hdr->version != BTF_VERSION) { + /* Ensure known version of structs, current BTF_VERSION == 1 */ + if (hdr->version != 1) { pr_debug("Unsupported BTF.ext version:%u\n", hdr->version); return -ENOTSUP; } @@ -3051,11 +3155,39 @@ static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) return -ENOTSUP; } - if (data_size == hdr->hdr_len) { + if (data_size < hdr_len) { + pr_debug("BTF.ext header not found\n"); + return -EINVAL; + } else if (data_size == hdr_len) { pr_debug("BTF.ext has no data\n"); return -EINVAL; } + /* Verify mandatory hdr info details present */ + if (hdr_len < offsetofend(struct btf_ext_header, line_info_len)) { + pr_warn("BTF.ext header missing func_info, line_info\n"); + return -EINVAL; + } + + /* Keep hdr native byte-order in memory for introspection */ + if (swapped_endian) + btf_ext_bswap_hdr(btf_ext->hdr); + + /* Validate info subsections and cache key metadata */ + err = btf_ext_parse_info(btf_ext, !swapped_endian); + if (err) + return err; + + /* Keep infos native byte-order in memory for introspection */ + if (swapped_endian) + btf_ext_bswap_info(btf_ext, btf_ext->data); + + /* + * Set btf_ext->swapped_endian only after all header and info data has + * been swapped, helping bswap functions determine if their data are + * in native byte-order when called. + */ + btf_ext->swapped_endian = swapped_endian; return 0; } @@ -3067,6 +3199,7 @@ void btf_ext__free(struct btf_ext *btf_ext) free(btf_ext->line_info.sec_idxs); free(btf_ext->core_relo_info.sec_idxs); free(btf_ext->data); + free(btf_ext->data_swapped); free(btf_ext); } @@ -3087,29 +3220,7 @@ struct btf_ext *btf_ext__new(const __u8 *data, __u32 size) } memcpy(btf_ext->data, data, size); - err = btf_ext_parse_hdr(btf_ext->data, size); - if (err) - goto done; - - if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, line_info_len)) { - err = -EINVAL; - goto done; - } - - err = btf_ext_setup_func_info(btf_ext); - if (err) - goto done; - - err = btf_ext_setup_line_info(btf_ext); - if (err) - goto done; - - if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) - goto done; /* skip core relos parsing */ - - err = btf_ext_setup_core_relos(btf_ext); - if (err) - goto done; + err = btf_ext_parse(btf_ext); done: if (err) { @@ -3120,15 +3231,66 @@ done: return btf_ext; } +static void *btf_ext_raw_data(const struct btf_ext *btf_ext_ro, bool swap_endian) +{ + struct btf_ext *btf_ext = (struct btf_ext *)btf_ext_ro; + const __u32 data_sz = btf_ext->data_size; + void *data; + + /* Return native data (always present) or swapped data if present */ + if (!swap_endian) + return btf_ext->data; + else if (btf_ext->data_swapped) + return btf_ext->data_swapped; + + /* Recreate missing swapped data, then cache and return */ + data = calloc(1, data_sz); + if (!data) + return NULL; + memcpy(data, btf_ext->data, data_sz); + + btf_ext_bswap_info(btf_ext, data); + btf_ext_bswap_hdr(data); + btf_ext->data_swapped = data; + return data; +} + const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size) { + void *data; + + data = btf_ext_raw_data(btf_ext, btf_ext->swapped_endian); + if (!data) + return errno = ENOMEM, NULL; + *size = btf_ext->data_size; - return btf_ext->data; + return data; } __attribute__((alias("btf_ext__raw_data"))) const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size); +enum btf_endianness btf_ext__endianness(const struct btf_ext *btf_ext) +{ + if (is_host_big_endian()) + return btf_ext->swapped_endian ? BTF_LITTLE_ENDIAN : BTF_BIG_ENDIAN; + else + return btf_ext->swapped_endian ? BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN; +} + +int btf_ext__set_endianness(struct btf_ext *btf_ext, enum btf_endianness endian) +{ + if (endian != BTF_LITTLE_ENDIAN && endian != BTF_BIG_ENDIAN) + return libbpf_err(-EINVAL); + + btf_ext->swapped_endian = is_host_big_endian() != (endian == BTF_BIG_ENDIAN); + + if (!btf_ext->swapped_endian) { + free(btf_ext->data_swapped); + btf_ext->data_swapped = NULL; + } + return 0; +} struct btf_dedup; @@ -3291,7 +3453,7 @@ int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts) d = btf_dedup_new(btf, opts); if (IS_ERR(d)) { - pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d)); + pr_debug("btf_dedup_new failed: %ld\n", PTR_ERR(d)); return libbpf_err(-EINVAL); } diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 4e349ad79ee6..47ee8f6ac489 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -167,6 +167,9 @@ LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset); LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size); LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext); LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size); +LIBBPF_API enum btf_endianness btf_ext__endianness(const struct btf_ext *btf_ext); +LIBBPF_API int btf_ext__set_endianness(struct btf_ext *btf_ext, + enum btf_endianness endian); LIBBPF_API int btf__find_str(struct btf *btf, const char *s); LIBBPF_API int btf__add_str(struct btf *btf, const char *s); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 0a7327541c17..468392f9882d 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -867,8 +867,8 @@ static void btf_dump_emit_bit_padding(const struct btf_dump *d, } pads[] = { {"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8} }; - int new_off, pad_bits, bits, i; - const char *pad_type; + int new_off = 0, pad_bits = 0, bits, i; + const char *pad_type = NULL; if (cur_off >= next_off) return; /* no gap */ @@ -1304,7 +1304,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, * chain, restore stack, emit warning, and try to * proceed nevertheless */ - pr_warn("not enough memory for decl stack:%d", err); + pr_warn("not enough memory for decl stack: %d\n", err); d->decl_stack_cnt = stack_start; return; } diff --git a/tools/lib/bpf/btf_relocate.c b/tools/lib/bpf/btf_relocate.c index 4f7399d85eab..b72f83e15156 100644 --- a/tools/lib/bpf/btf_relocate.c +++ b/tools/lib/bpf/btf_relocate.c @@ -428,7 +428,7 @@ static int btf_relocate_rewrite_strs(struct btf_relocate *r, __u32 i) } else { off = r->str_map[*str_off]; if (!off) { - pr_warn("string '%s' [offset %u] is not mapped to base BTF", + pr_warn("string '%s' [offset %u] is not mapped to base BTF\n", btf__str_by_offset(r->btf, off), *str_off); return -ENOENT; } diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index cf3323fd47b8..8a2b0f62d91d 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -401,6 +401,15 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) opts->insns_sz = gen->insn_cur - gen->insn_start; opts->data = gen->data_start; opts->data_sz = gen->data_cur - gen->data_start; + + /* use target endianness for embedded loader */ + if (gen->swapped_endian) { + struct bpf_insn *insn = (struct bpf_insn *)opts->insns; + int insn_cnt = opts->insns_sz / sizeof(struct bpf_insn); + + for (i = 0; i < insn_cnt; i++) + bpf_insn_bswap(insn++); + } } return gen->error; } @@ -414,6 +423,28 @@ void bpf_gen__free(struct bpf_gen *gen) free(gen); } +/* + * Fields of bpf_attr are set to values in native byte-order before being + * written to the target-bound data blob, and may need endian conversion. + * This macro allows providing the correct value in situ more simply than + * writing a separate converter for *all fields* of *all records* included + * in union bpf_attr. Note that sizeof(rval) should match the assignment + * target to avoid runtime problems. + */ +#define tgt_endian(rval) ({ \ + typeof(rval) _val = (rval); \ + if (gen->swapped_endian) { \ + switch (sizeof(_val)) { \ + case 1: break; \ + case 2: _val = bswap_16(_val); break; \ + case 4: _val = bswap_32(_val); break; \ + case 8: _val = bswap_64(_val); break; \ + default: pr_warn("unsupported bswap size!\n"); \ + } \ + } \ + _val; \ +}) + void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, __u32 btf_raw_size) { @@ -422,11 +453,12 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: load_btf: size %d\n", btf_raw_size); btf_data = add_data(gen, btf_raw_data, btf_raw_size); - attr.btf_size = btf_raw_size; + attr.btf_size = tgt_endian(btf_raw_size); btf_load_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: load_btf: off %d size %d, attr: off %d size %d\n", + btf_data, btf_raw_size, btf_load_attr, attr_size); /* populate union bpf_attr with user provided log details */ move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_level), 4, @@ -457,28 +489,29 @@ void bpf_gen__map_create(struct bpf_gen *gen, union bpf_attr attr; memset(&attr, 0, attr_size); - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = value_size; - attr.map_flags = map_attr->map_flags; - attr.map_extra = map_attr->map_extra; + attr.map_type = tgt_endian(map_type); + attr.key_size = tgt_endian(key_size); + attr.value_size = tgt_endian(value_size); + attr.map_flags = tgt_endian(map_attr->map_flags); + attr.map_extra = tgt_endian(map_attr->map_extra); if (map_name) libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); - attr.numa_node = map_attr->numa_node; - attr.map_ifindex = map_attr->map_ifindex; - attr.max_entries = max_entries; - attr.btf_key_type_id = map_attr->btf_key_type_id; - attr.btf_value_type_id = map_attr->btf_value_type_id; - - pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n", - attr.map_name, map_idx, map_type, attr.btf_value_type_id); + attr.numa_node = tgt_endian(map_attr->numa_node); + attr.map_ifindex = tgt_endian(map_attr->map_ifindex); + attr.max_entries = tgt_endian(max_entries); + attr.btf_key_type_id = tgt_endian(map_attr->btf_key_type_id); + attr.btf_value_type_id = tgt_endian(map_attr->btf_value_type_id); map_create_attr = add_data(gen, &attr, attr_size); - if (attr.btf_value_type_id) + pr_debug("gen: map_create: %s idx %d type %d value_type_id %d, attr: off %d size %d\n", + map_name, map_idx, map_type, map_attr->btf_value_type_id, + map_create_attr, attr_size); + + if (map_attr->btf_value_type_id) /* populate union bpf_attr with btf_fd saved in the stack earlier */ move_stack2blob(gen, attr_field(map_create_attr, btf_fd), 4, stack_off(btf_fd)); - switch (attr.map_type) { + switch (map_type) { case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: move_stack2blob(gen, attr_field(map_create_attr, inner_map_fd), 4, @@ -498,8 +531,8 @@ void bpf_gen__map_create(struct bpf_gen *gen, /* emit MAP_CREATE command */ emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size); debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d", - attr.map_name, map_idx, map_type, value_size, - attr.btf_value_type_id); + map_name, map_idx, map_type, value_size, + map_attr->btf_value_type_id); emit_check_err(gen); /* remember map_fd in the stack, if successful */ if (map_idx < 0) { @@ -784,12 +817,12 @@ log: emit_ksym_relo_log(gen, relo, kdesc->ref); } -static __u32 src_reg_mask(void) +static __u32 src_reg_mask(struct bpf_gen *gen) { -#if defined(__LITTLE_ENDIAN_BITFIELD) - return 0x0f; /* src_reg,dst_reg,... */ -#elif defined(__BIG_ENDIAN_BITFIELD) - return 0xf0; /* dst_reg,src_reg,... */ +#if defined(__LITTLE_ENDIAN_BITFIELD) /* src_reg,dst_reg,... */ + return gen->swapped_endian ? 0xf0 : 0x0f; +#elif defined(__BIG_ENDIAN_BITFIELD) /* dst_reg,src_reg,... */ + return gen->swapped_endian ? 0x0f : 0xf0; #else #error "Unsupported bit endianness, cannot proceed" #endif @@ -840,7 +873,7 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 3)); clear_src_reg: /* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */ - reg_mask = src_reg_mask(); + reg_mask = src_reg_mask(gen); emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code))); emit(gen, BPF_ALU32_IMM(BPF_AND, BPF_REG_9, reg_mask)); emit(gen, BPF_STX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, offsetofend(struct bpf_insn, code))); @@ -931,48 +964,94 @@ static void cleanup_relos(struct bpf_gen *gen, int insns) cleanup_core_relo(gen); } +/* Convert func, line, and core relo info blobs to target endianness */ +static void info_blob_bswap(struct bpf_gen *gen, int func_info, int line_info, + int core_relos, struct bpf_prog_load_opts *load_attr) +{ + struct bpf_func_info *fi = gen->data_start + func_info; + struct bpf_line_info *li = gen->data_start + line_info; + struct bpf_core_relo *cr = gen->data_start + core_relos; + int i; + + for (i = 0; i < load_attr->func_info_cnt; i++) + bpf_func_info_bswap(fi++); + + for (i = 0; i < load_attr->line_info_cnt; i++) + bpf_line_info_bswap(li++); + + for (i = 0; i < gen->core_relo_cnt; i++) + bpf_core_relo_bswap(cr++); +} + void bpf_gen__prog_load(struct bpf_gen *gen, enum bpf_prog_type prog_type, const char *prog_name, const char *license, struct bpf_insn *insns, size_t insn_cnt, struct bpf_prog_load_opts *load_attr, int prog_idx) { + int func_info_tot_sz = load_attr->func_info_cnt * + load_attr->func_info_rec_size; + int line_info_tot_sz = load_attr->line_info_cnt * + load_attr->line_info_rec_size; + int core_relo_tot_sz = gen->core_relo_cnt * + sizeof(struct bpf_core_relo); int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos; int attr_size = offsetofend(union bpf_attr, core_relo_rec_size); union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: prog_load: type %d insns_cnt %zd progi_idx %d\n", - prog_type, insn_cnt, prog_idx); /* add license string to blob of bytes */ license_off = add_data(gen, license, strlen(license) + 1); /* add insns to blob of bytes */ insns_off = add_data(gen, insns, insn_cnt * sizeof(struct bpf_insn)); + pr_debug("gen: prog_load: prog_idx %d type %d insn off %d insns_cnt %zd license off %d\n", + prog_idx, prog_type, insns_off, insn_cnt, license_off); - attr.prog_type = prog_type; - attr.expected_attach_type = load_attr->expected_attach_type; - attr.attach_btf_id = load_attr->attach_btf_id; - attr.prog_ifindex = load_attr->prog_ifindex; - attr.kern_version = 0; - attr.insn_cnt = (__u32)insn_cnt; - attr.prog_flags = load_attr->prog_flags; - - attr.func_info_rec_size = load_attr->func_info_rec_size; - attr.func_info_cnt = load_attr->func_info_cnt; - func_info = add_data(gen, load_attr->func_info, - attr.func_info_cnt * attr.func_info_rec_size); + /* convert blob insns to target endianness */ + if (gen->swapped_endian) { + struct bpf_insn *insn = gen->data_start + insns_off; + int i; - attr.line_info_rec_size = load_attr->line_info_rec_size; - attr.line_info_cnt = load_attr->line_info_cnt; - line_info = add_data(gen, load_attr->line_info, - attr.line_info_cnt * attr.line_info_rec_size); + for (i = 0; i < insn_cnt; i++, insn++) + bpf_insn_bswap(insn); + } - attr.core_relo_rec_size = sizeof(struct bpf_core_relo); - attr.core_relo_cnt = gen->core_relo_cnt; - core_relos = add_data(gen, gen->core_relos, - attr.core_relo_cnt * attr.core_relo_rec_size); + attr.prog_type = tgt_endian(prog_type); + attr.expected_attach_type = tgt_endian(load_attr->expected_attach_type); + attr.attach_btf_id = tgt_endian(load_attr->attach_btf_id); + attr.prog_ifindex = tgt_endian(load_attr->prog_ifindex); + attr.kern_version = 0; + attr.insn_cnt = tgt_endian((__u32)insn_cnt); + attr.prog_flags = tgt_endian(load_attr->prog_flags); + + attr.func_info_rec_size = tgt_endian(load_attr->func_info_rec_size); + attr.func_info_cnt = tgt_endian(load_attr->func_info_cnt); + func_info = add_data(gen, load_attr->func_info, func_info_tot_sz); + pr_debug("gen: prog_load: func_info: off %d cnt %d rec size %d\n", + func_info, load_attr->func_info_cnt, + load_attr->func_info_rec_size); + + attr.line_info_rec_size = tgt_endian(load_attr->line_info_rec_size); + attr.line_info_cnt = tgt_endian(load_attr->line_info_cnt); + line_info = add_data(gen, load_attr->line_info, line_info_tot_sz); + pr_debug("gen: prog_load: line_info: off %d cnt %d rec size %d\n", + line_info, load_attr->line_info_cnt, + load_attr->line_info_rec_size); + + attr.core_relo_rec_size = tgt_endian((__u32)sizeof(struct bpf_core_relo)); + attr.core_relo_cnt = tgt_endian(gen->core_relo_cnt); + core_relos = add_data(gen, gen->core_relos, core_relo_tot_sz); + pr_debug("gen: prog_load: core_relos: off %d cnt %d rec size %zd\n", + core_relos, gen->core_relo_cnt, + sizeof(struct bpf_core_relo)); + + /* convert all info blobs to target endianness */ + if (gen->swapped_endian) + info_blob_bswap(gen, func_info, line_info, core_relos, load_attr); libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); prog_load_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: prog_load: attr: off %d size %d\n", + prog_load_attr, attr_size); /* populate union bpf_attr with a pointer to license */ emit_rel_store(gen, attr_field(prog_load_attr, license), license_off); @@ -1040,7 +1119,6 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, int zero = 0; memset(&attr, 0, attr_size); - pr_debug("gen: map_update_elem: idx %d\n", map_idx); value = add_data(gen, pvalue, value_size); key = add_data(gen, &zero, sizeof(zero)); @@ -1068,6 +1146,8 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); map_update_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: map_update_elem: idx %d, value: off %d size %d, attr: off %d size %d\n", + map_idx, value, value_size, map_update_attr, attr_size); move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, blob_fd_array_off(gen, map_idx)); emit_rel_store(gen, attr_field(map_update_attr, key), key); @@ -1084,14 +1164,16 @@ void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slo int attr_size = offsetofend(union bpf_attr, flags); int map_update_attr, key; union bpf_attr attr; + int tgt_slot; memset(&attr, 0, attr_size); - pr_debug("gen: populate_outer_map: outer %d key %d inner %d\n", - outer_map_idx, slot, inner_map_idx); - key = add_data(gen, &slot, sizeof(slot)); + tgt_slot = tgt_endian(slot); + key = add_data(gen, &tgt_slot, sizeof(tgt_slot)); map_update_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: populate_outer_map: outer %d key %d inner %d, attr: off %d size %d\n", + outer_map_idx, slot, inner_map_idx, map_update_attr, attr_size); move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, blob_fd_array_off(gen, outer_map_idx)); emit_rel_store(gen, attr_field(map_update_attr, key), key); @@ -1112,8 +1194,9 @@ void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx) union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: map_freeze: idx %d\n", map_idx); map_freeze_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: map_freeze: idx %d, attr: off %d size %d\n", + map_idx, map_freeze_attr, attr_size); move_blob2blob(gen, attr_field(map_freeze_attr, map_fd), 4, blob_fd_array_off(gen, map_idx)); /* emit MAP_FREEZE command */ diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index c12f8320e668..0c4f155e8eb7 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -166,8 +166,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value); * @bkt: integer used as a bucket loop cursor */ #define hashmap__for_each_entry(map, cur, bkt) \ - for (bkt = 0; bkt < map->cap; bkt++) \ - for (cur = map->buckets[bkt]; cur; cur = cur->next) + for (bkt = 0; bkt < (map)->cap; bkt++) \ + for (cur = (map)->buckets[bkt]; cur; cur = cur->next) /* * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe @@ -178,8 +178,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value); * @bkt: integer used as a bucket loop cursor */ #define hashmap__for_each_entry_safe(map, cur, tmp, bkt) \ - for (bkt = 0; bkt < map->cap; bkt++) \ - for (cur = map->buckets[bkt]; \ + for (bkt = 0; bkt < (map)->cap; bkt++) \ + for (cur = (map)->buckets[bkt]; \ cur && ({tmp = cur->next; true; }); \ cur = tmp) @@ -190,19 +190,19 @@ bool hashmap_find(const struct hashmap *map, long key, long *value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = map->buckets \ - ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + for (cur = (map)->buckets \ + ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \ : NULL; \ cur; \ cur = cur->next) \ - if (map->equal_fn(cur->key, (_key), map->ctx)) + if ((map)->equal_fn(cur->key, (_key), (map)->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = map->buckets \ - ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + for (cur = (map)->buckets \ + ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \ : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ - if (map->equal_fn(cur->key, (_key), map->ctx)) + if ((map)->equal_fn(cur->key, (_key), (map)->ctx)) #endif /* __LIBBPF_HASHMAP_H */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 219facd0e66e..711173acbcef 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -694,6 +694,8 @@ struct bpf_object { /* Information when doing ELF related work. Only valid if efile.elf is not NULL */ struct elf_state efile; + unsigned char byteorder; + struct btf *btf; struct btf_ext *btf_ext; @@ -940,6 +942,20 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return 0; } +static void bpf_object_bswap_progs(struct bpf_object *obj) +{ + struct bpf_program *prog = obj->programs; + struct bpf_insn *insn; + int p, i; + + for (p = 0; p < obj->nr_programs; p++, prog++) { + insn = prog->insns; + for (i = 0; i < prog->insns_cnt; i++, insn++) + bpf_insn_bswap(insn); + } + pr_debug("converted %zu BPF programs to native byte order\n", obj->nr_programs); +} + static const struct btf_member * find_member_by_offset(const struct btf_type *t, __u32 bit_offset) { @@ -1506,6 +1522,7 @@ static void bpf_object__elf_finish(struct bpf_object *obj) elf_end(obj->efile.elf); obj->efile.elf = NULL; + obj->efile.ehdr = NULL; obj->efile.symbols = NULL; obj->efile.arena_data = NULL; @@ -1571,6 +1588,16 @@ static int bpf_object__elf_init(struct bpf_object *obj) goto errout; } + /* Validate ELF object endianness... */ + if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB && + ehdr->e_ident[EI_DATA] != ELFDATA2MSB) { + err = -LIBBPF_ERRNO__ENDIAN; + pr_warn("elf: '%s' has unknown byte order\n", obj->path); + goto errout; + } + /* and save after bpf_object_open() frees ELF data */ + obj->byteorder = ehdr->e_ident[EI_DATA]; + if (elf_getshdrstrndx(elf, &obj->efile.shstrndx)) { pr_warn("elf: failed to get section names section index for %s: %s\n", obj->path, elf_errmsg(-1)); @@ -1599,19 +1626,15 @@ errout: return err; } -static int bpf_object__check_endianness(struct bpf_object *obj) +static bool is_native_endianness(struct bpf_object *obj) { #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ - if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2LSB) - return 0; + return obj->byteorder == ELFDATA2LSB; #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2MSB) - return 0; + return obj->byteorder == ELFDATA2MSB; #else # error "Unrecognized __BYTE_ORDER__" #endif - pr_warn("elf: endianness mismatch in %s.\n", obj->path); - return -LIBBPF_ERRNO__ENDIAN; } static int @@ -3581,11 +3604,12 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) report: if (err) { btf_mandatory = kernel_needs_btf(obj); - pr_warn("Error loading .BTF into kernel: %d. %s\n", err, - btf_mandatory ? "BTF is mandatory, can't proceed." - : "BTF is optional, ignoring."); - if (!btf_mandatory) + if (btf_mandatory) { + pr_warn("Error loading .BTF into kernel: %d. BTF is mandatory, can't proceed.\n", err); + } else { + pr_info("Error loading .BTF into kernel: %d. BTF is optional, ignoring.\n", err); err = 0; + } } return err; } @@ -3953,6 +3977,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj) return -LIBBPF_ERRNO__FORMAT; } + /* change BPF program insns to native endianness for introspection */ + if (!is_native_endianness(obj)) + bpf_object_bswap_progs(obj); + /* sort BPF programs by section name and in-section instruction offset * for faster search */ @@ -3985,7 +4013,7 @@ static bool sym_is_subprog(const Elf64_Sym *sym, int text_shndx) return true; /* global function */ - return bind == STB_GLOBAL && type == STT_FUNC; + return (bind == STB_GLOBAL || bind == STB_WEAK) && type == STT_FUNC; } static int find_extern_btf_id(const struct btf *btf, const char *ext_name) @@ -4389,7 +4417,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj) static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog) { - return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; + return prog->sec_idx == obj->efile.text_shndx; } struct bpf_program * @@ -5094,6 +5122,7 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) enum libbpf_map_type map_type = map->libbpf_type; char *cp, errmsg[STRERR_BUFSIZE]; int err, zero = 0; + size_t mmap_sz; if (obj->gen_loader) { bpf_gen__map_update_elem(obj->gen_loader, map - obj->maps, @@ -5107,8 +5136,8 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) if (err) { err = -errno; cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("Error setting initial map(%s) contents: %s\n", - map->name, cp); + pr_warn("map '%s': failed to set initial contents: %s\n", + bpf_map__name(map), cp); return err; } @@ -5118,11 +5147,43 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) if (err) { err = -errno; cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("Error freezing map(%s) as read-only: %s\n", - map->name, cp); + pr_warn("map '%s': failed to freeze as read-only: %s\n", + bpf_map__name(map), cp); return err; } } + + /* Remap anonymous mmap()-ed "map initialization image" as + * a BPF map-backed mmap()-ed memory, but preserving the same + * memory address. This will cause kernel to change process' + * page table to point to a different piece of kernel memory, + * but from userspace point of view memory address (and its + * contents, being identical at this point) will stay the + * same. This mapping will be released by bpf_object__close() + * as per normal clean up procedure. + */ + mmap_sz = bpf_map_mmap_sz(map); + if (map->def.map_flags & BPF_F_MMAPABLE) { + void *mmaped; + int prot; + + if (map->def.map_flags & BPF_F_RDONLY_PROG) + prot = PROT_READ; + else + prot = PROT_READ | PROT_WRITE; + mmaped = mmap(map->mmaped, mmap_sz, prot, MAP_SHARED | MAP_FIXED, map->fd, 0); + if (mmaped == MAP_FAILED) { + err = -errno; + pr_warn("map '%s': failed to re-mmap() contents: %d\n", + bpf_map__name(map), err); + return err; + } + map->mmaped = mmaped; + } else if (map->mmaped) { + munmap(map->mmaped, mmap_sz); + map->mmaped = NULL; + } + return 0; } @@ -5439,8 +5500,7 @@ retry: err = bpf_object__populate_internal_map(obj, map); if (err < 0) goto err_out; - } - if (map->def.type == BPF_MAP_TYPE_ARENA) { + } else if (map->def.type == BPF_MAP_TYPE_ARENA) { map->mmaped = mmap((void *)(long)map->map_extra, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, map->map_extra ? MAP_SHARED | MAP_FIXED : MAP_SHARED, @@ -7352,8 +7412,14 @@ static int libbpf_prepare_prog_load(struct bpf_program *prog, opts->prog_flags |= BPF_F_XDP_HAS_FRAGS; /* special check for usdt to use uprobe_multi link */ - if ((def & SEC_USDT) && kernel_supports(prog->obj, FEAT_UPROBE_MULTI_LINK)) + if ((def & SEC_USDT) && kernel_supports(prog->obj, FEAT_UPROBE_MULTI_LINK)) { + /* for BPF_TRACE_UPROBE_MULTI, user might want to query expected_attach_type + * in prog, and expected_attach_type we set in kernel is from opts, so we + * update both. + */ prog->expected_attach_type = BPF_TRACE_UPROBE_MULTI; + opts->expected_attach_type = BPF_TRACE_UPROBE_MULTI; + } if ((def & SEC_ATTACH_BTF) && !prog->attach_btf_id) { int btf_obj_fd = 0, btf_type_id = 0, err; @@ -7443,6 +7509,7 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog load_attr.attach_btf_id = prog->attach_btf_id; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; + load_attr.expected_attach_type = prog->expected_attach_type; /* specify func_info/line_info only if kernel supports them */ if (obj->btf && btf__fd(obj->btf) >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) { @@ -7474,9 +7541,6 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog insns_cnt = prog->insns_cnt; } - /* allow prog_prepare_load_fn to change expected_attach_type */ - load_attr.expected_attach_type = prog->expected_attach_type; - if (obj->gen_loader) { bpf_gen__prog_load(obj->gen_loader, prog->type, prog->name, license, insns, insns_cnt, &load_attr, @@ -7992,7 +8056,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, } err = bpf_object__elf_init(obj); - err = err ? : bpf_object__check_endianness(obj); err = err ? : bpf_object__elf_collect(obj); err = err ? : bpf_object__collect_externs(obj); err = err ? : bpf_object_fixup_btf(obj); @@ -8498,8 +8561,15 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch return libbpf_err(-EINVAL); } - if (obj->gen_loader) + /* Disallow kernel loading programs of non-native endianness but + * permit cross-endian creation of "light skeleton". + */ + if (obj->gen_loader) { bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); + } else if (!is_native_endianness(obj)) { + pr_warn("object '%s': loading non-native endianness is unsupported\n", obj->name); + return libbpf_err(-LIBBPF_ERRNO__ENDIAN); + } err = bpf_object_prepare_token(obj); err = err ? : bpf_object__probe_loading(obj); @@ -9096,6 +9166,7 @@ int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts) if (!gen) return -ENOMEM; gen->opts = opts; + gen->swapped_endian = !is_native_endianness(obj); obj->gen_loader = gen; return 0; } @@ -12760,7 +12831,7 @@ struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, } if (prog->type != BPF_PROG_TYPE_EXT) { - pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace", + pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace\n", prog->name); return libbpf_err_ptr(-EINVAL); } @@ -13834,7 +13905,7 @@ int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s) map_type = btf__type_by_id(btf, map_type_id); if (!btf_is_datasec(map_type)) { - pr_warn("type for map '%1$s' is not a datasec: %2$s", + pr_warn("type for map '%1$s' is not a datasec: %2$s\n", bpf_map__name(map), __btf_kind_str(btf_kind(map_type))); return libbpf_err(-EINVAL); @@ -13877,46 +13948,11 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) for (i = 0; i < s->map_cnt; i++) { struct bpf_map_skeleton *map_skel = (void *)s->maps + i * s->map_skel_sz; struct bpf_map *map = *map_skel->map; - size_t mmap_sz = bpf_map_mmap_sz(map); - int prot, map_fd = map->fd; - void **mmaped = map_skel->mmaped; - - if (!mmaped) - continue; - - if (!(map->def.map_flags & BPF_F_MMAPABLE)) { - *mmaped = NULL; - continue; - } - if (map->def.type == BPF_MAP_TYPE_ARENA) { - *mmaped = map->mmaped; + if (!map_skel->mmaped) continue; - } - - if (map->def.map_flags & BPF_F_RDONLY_PROG) - prot = PROT_READ; - else - prot = PROT_READ | PROT_WRITE; - /* Remap anonymous mmap()-ed "map initialization image" as - * a BPF map-backed mmap()-ed memory, but preserving the same - * memory address. This will cause kernel to change process' - * page table to point to a different piece of kernel memory, - * but from userspace point of view memory address (and its - * contents, being identical at this point) will stay the - * same. This mapping will be released by bpf_object__close() - * as per normal clean up procedure, so we don't need to worry - * about it from skeleton's clean up perspective. - */ - *mmaped = mmap(map->mmaped, mmap_sz, prot, MAP_SHARED | MAP_FIXED, map_fd, 0); - if (*mmaped == MAP_FAILED) { - err = -errno; - *mmaped = NULL; - pr_warn("failed to re-mmap() map '%s': %d\n", - bpf_map__name(map), err); - return libbpf_err(err); - } + *map_skel->mmaped = map->mmaped; } return 0; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 0096e483f7eb..f40ccc2946e7 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -421,6 +421,8 @@ LIBBPF_1.5.0 { global: btf__distill_base; btf__relocate; + btf_ext__endianness; + btf_ext__set_endianness; bpf_map__autoattach; bpf_map__set_autoattach; bpf_object__token_fd; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 408df59e0771..de498e2dd6b0 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -10,6 +10,7 @@ #define __LIBBPF_LIBBPF_INTERNAL_H #include <stdlib.h> +#include <byteswap.h> #include <limits.h> #include <errno.h> #include <linux/err.h> @@ -448,11 +449,11 @@ struct btf_ext_info { * * The func_info subsection layout: * record size for struct bpf_func_info in the func_info subsection - * struct btf_sec_func_info for section #1 + * struct btf_ext_info_sec for section #1 * a list of bpf_func_info records for section #1 * where struct bpf_func_info mimics one in include/uapi/linux/bpf.h * but may not be identical - * struct btf_sec_func_info for section #2 + * struct btf_ext_info_sec for section #2 * a list of bpf_func_info records for section #2 * ...... * @@ -484,6 +485,8 @@ struct btf_ext { struct btf_ext_header *hdr; void *data; }; + void *data_swapped; + bool swapped_endian; struct btf_ext_info func_info; struct btf_ext_info line_info; struct btf_ext_info core_relo_info; @@ -511,6 +514,32 @@ struct bpf_line_info_min { __u32 line_col; }; +/* Functions to byte-swap info records */ + +typedef void (*info_rec_bswap_fn)(void *); + +static inline void bpf_func_info_bswap(struct bpf_func_info *i) +{ + i->insn_off = bswap_32(i->insn_off); + i->type_id = bswap_32(i->type_id); +} + +static inline void bpf_line_info_bswap(struct bpf_line_info *i) +{ + i->insn_off = bswap_32(i->insn_off); + i->file_name_off = bswap_32(i->file_name_off); + i->line_off = bswap_32(i->line_off); + i->line_col = bswap_32(i->line_col); +} + +static inline void bpf_core_relo_bswap(struct bpf_core_relo *i) +{ + i->insn_off = bswap_32(i->insn_off); + i->type_id = bswap_32(i->type_id); + i->access_str_off = bswap_32(i->access_str_off); + i->kind = bswap_32(i->kind); +} + enum btf_field_iter_kind { BTF_FIELD_ITER_IDS, BTF_FIELD_ITER_STRS, @@ -588,6 +617,16 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn) return insn->code == (BPF_LD | BPF_IMM | BPF_DW); } +static inline void bpf_insn_bswap(struct bpf_insn *insn) +{ + __u8 tmp_reg = insn->dst_reg; + + insn->dst_reg = insn->src_reg; + insn->src_reg = tmp_reg; + insn->off = bswap_16(insn->off); + insn->imm = bswap_32(insn->imm); +} + /* Unconditionally dup FD, ensuring it doesn't use [0, 2] range. * Original FD is not closed or altered in any other way. * Preserves original FD value, if it's invalid (negative). diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index e0005c6ade88..f83c1c29982c 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -135,6 +135,7 @@ struct bpf_linker { int fd; Elf *elf; Elf64_Ehdr *elf_hdr; + bool swapped_endian; /* Output sections metadata */ struct dst_sec *secs; @@ -324,13 +325,8 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) linker->elf_hdr->e_machine = EM_BPF; linker->elf_hdr->e_type = ET_REL; -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ - linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2LSB; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2MSB; -#else -#error "Unknown __BYTE_ORDER__" -#endif + /* Set unknown ELF endianness, assign later from input files */ + linker->elf_hdr->e_ident[EI_DATA] = ELFDATANONE; /* STRTAB */ /* initialize strset with an empty string to conform to ELF */ @@ -396,6 +392,8 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) pr_warn_elf("failed to create SYMTAB data"); return -EINVAL; } + /* Ensure libelf translates byte-order of symbol records */ + sec->data->d_type = ELF_T_SYM; str_off = strset__add_str(linker->strtab_strs, sec->sec_name); if (str_off < 0) @@ -539,19 +537,21 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, const struct bpf_linker_file_opts *opts, struct src_obj *obj) { -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ - const int host_endianness = ELFDATA2LSB; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - const int host_endianness = ELFDATA2MSB; -#else -#error "Unknown __BYTE_ORDER__" -#endif int err = 0; Elf_Scn *scn; Elf_Data *data; Elf64_Ehdr *ehdr; Elf64_Shdr *shdr; struct src_sec *sec; + unsigned char obj_byteorder; + unsigned char link_byteorder = linker->elf_hdr->e_ident[EI_DATA]; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + const unsigned char host_byteorder = ELFDATA2LSB; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + const unsigned char host_byteorder = ELFDATA2MSB; +#else +#error "Unknown __BYTE_ORDER__" +#endif pr_debug("linker: adding object file '%s'...\n", filename); @@ -577,11 +577,25 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, pr_warn_elf("failed to get ELF header for %s", filename); return err; } - if (ehdr->e_ident[EI_DATA] != host_endianness) { + + /* Linker output endianness set by first input object */ + obj_byteorder = ehdr->e_ident[EI_DATA]; + if (obj_byteorder != ELFDATA2LSB && obj_byteorder != ELFDATA2MSB) { err = -EOPNOTSUPP; - pr_warn_elf("unsupported byte order of ELF file %s", filename); + pr_warn("unknown byte order of ELF file %s\n", filename); return err; } + if (link_byteorder == ELFDATANONE) { + linker->elf_hdr->e_ident[EI_DATA] = obj_byteorder; + linker->swapped_endian = obj_byteorder != host_byteorder; + pr_debug("linker: set %s-endian output byte order\n", + obj_byteorder == ELFDATA2MSB ? "big" : "little"); + } else if (link_byteorder != obj_byteorder) { + err = -EOPNOTSUPP; + pr_warn("byte order mismatch with ELF file %s\n", filename); + return err; + } + if (ehdr->e_type != ET_REL || ehdr->e_machine != EM_BPF || ehdr->e_ident[EI_CLASS] != ELFCLASS64) { @@ -1109,6 +1123,24 @@ static bool sec_content_is_same(struct dst_sec *dst_sec, struct src_sec *src_sec return true; } +static bool is_exec_sec(struct dst_sec *sec) +{ + if (!sec || sec->ephemeral) + return false; + return (sec->shdr->sh_type == SHT_PROGBITS) && + (sec->shdr->sh_flags & SHF_EXECINSTR); +} + +static void exec_sec_bswap(void *raw_data, int size) +{ + const int insn_cnt = size / sizeof(struct bpf_insn); + struct bpf_insn *insn = raw_data; + int i; + + for (i = 0; i < insn_cnt; i++, insn++) + bpf_insn_bswap(insn); +} + static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src_sec *src) { void *tmp; @@ -1168,6 +1200,10 @@ static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src memset(dst->raw_data + dst->sec_sz, 0, dst_align_sz - dst->sec_sz); /* now copy src data at a properly aligned offset */ memcpy(dst->raw_data + dst_align_sz, src->data->d_buf, src->shdr->sh_size); + + /* convert added bpf insns to native byte-order */ + if (linker->swapped_endian && is_exec_sec(dst)) + exec_sec_bswap(dst->raw_data + dst_align_sz, src->shdr->sh_size); } dst->sec_sz = dst_final_sz; @@ -2415,6 +2451,10 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) if (glob_sym && glob_sym->var_idx >= 0) { __s64 sz; + /* FUNCs don't have size, nothing to update */ + if (btf_is_func(t)) + continue; + dst_var = &dst_sec->sec_vars[glob_sym->var_idx]; /* Because underlying BTF type might have * changed, so might its size have changed, so @@ -2628,6 +2668,10 @@ int bpf_linker__finalize(struct bpf_linker *linker) if (!sec->scn) continue; + /* restore sections with bpf insns to target byte-order */ + if (linker->swapped_endian && is_exec_sec(sec)) + exec_sec_bswap(sec->raw_data, sec->sec_sz); + sec->data->d_buf = sec->raw_data; } @@ -2696,6 +2740,7 @@ static int emit_elf_data_sec(struct bpf_linker *linker, const char *sec_name, static int finalize_btf(struct bpf_linker *linker) { + enum btf_endianness link_endianness; LIBBPF_OPTS(btf_dedup_opts, opts); struct btf *btf = linker->btf; const void *raw_data; @@ -2740,6 +2785,13 @@ static int finalize_btf(struct bpf_linker *linker) return err; } + /* Set .BTF and .BTF.ext output byte order */ + link_endianness = linker->elf_hdr->e_ident[EI_DATA] == ELFDATA2MSB ? + BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN; + btf__set_endianness(linker->btf, link_endianness); + if (linker->btf_ext) + btf_ext__set_endianness(linker->btf_ext, link_endianness); + /* Emit .BTF section */ raw_data = btf__raw_data(linker->btf, &raw_sz); if (!raw_data) diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index 63a4d5ad12d1..7632e9d41827 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -1339,7 +1339,7 @@ int bpf_core_calc_relo_insn(const char *prog_name, cands->cands[i].id, cand_spec); if (err < 0) { bpf_core_format_spec(spec_buf, sizeof(spec_buf), cand_spec); - pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n ", + pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n", prog_name, relo_idx, i, spec_buf, err); return err; } diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index 0875452521e9..4d5fa079b5d6 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -351,10 +351,11 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) attr.test.ctx_size_in = opts->ctx->sz; err = skel_sys_bpf(BPF_PROG_RUN, &attr, test_run_attr_sz); if (err < 0 || (int)attr.test.retval < 0) { - opts->errstr = "failed to execute loader prog"; if (err < 0) { + opts->errstr = "failed to execute loader prog"; set_err; } else { + opts->errstr = "error returned by loader prog"; err = (int)attr.test.retval; #ifndef __KERNEL__ errno = -err; diff --git a/tools/lib/bpf/zip.c b/tools/lib/bpf/zip.c index 3f26d629b2b4..88c376a8348d 100644 --- a/tools/lib/bpf/zip.c +++ b/tools/lib/bpf/zip.c @@ -223,7 +223,7 @@ struct zip_archive *zip_archive_open(const char *path) if (!archive) { munmap(data, size); return ERR_PTR(-ENOMEM); - }; + } archive->data = data; archive->size = size; diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c index eb896d30545b..555d617c1f50 100644 --- a/tools/lib/subcmd/parse-options.c +++ b/tools/lib/subcmd/parse-options.c @@ -807,7 +807,7 @@ static int option__cmp(const void *va, const void *vb) static struct option *options__order(const struct option *opts) { int nr_opts = 0, nr_group = 0, nr_parent = 0, len; - const struct option *o, *p = opts; + const struct option *o = NULL, *p = opts; struct option *opt, *ordered = NULL, *group; /* flatten the options that have parents */ diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index e6533b3400de..d45c9a9b304d 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -16,7 +16,6 @@ fixdep /test_progs-cpuv4 test_verifier_log feature -test_sock urandom_read test_sockmap test_lirc_mode2_user diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 75016962f795..a226d0647c4e 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -10,6 +10,7 @@ TOOLSDIR := $(abspath ../../..) LIBDIR := $(TOOLSDIR)/lib BPFDIR := $(LIBDIR)/bpf TOOLSINCDIR := $(TOOLSDIR)/include +TOOLSARCHINCDIR := $(TOOLSDIR)/arch/$(SRCARCH)/include BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool APIDIR := $(TOOLSINCDIR)/uapi ifneq ($(O),) @@ -44,7 +45,7 @@ CFLAGS += -g $(OPT_FLAGS) -rdynamic \ -Wall -Werror -fno-omit-frame-pointer \ $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ - -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) + -I$(TOOLSINCDIR) -I$(TOOLSARCHINCDIR) -I$(APIDIR) -I$(OUTPUT) LDFLAGS += $(SAN_LDFLAGS) LDLIBS += $(LIBELF_LIBS) -lz -lrt -lpthread @@ -83,7 +84,7 @@ endif # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ - test_sock test_sockmap \ + test_sockmap \ test_tcpnotify_user test_sysctl \ test_progs-no_alu32 TEST_INST_SUBDIRS := no_alu32 @@ -132,7 +133,6 @@ TEST_PROGS := test_kmod.sh \ test_tunnel.sh \ test_lwt_seg6local.sh \ test_lirc_mode2.sh \ - test_skb_cgroup_id.sh \ test_flow_dissector.sh \ test_xdp_vlan_mode_generic.sh \ test_xdp_vlan_mode_native.sh \ @@ -349,7 +349,6 @@ JSON_WRITER := $(OUTPUT)/json_writer.o CAP_HELPERS := $(OUTPUT)/cap_helpers.o NETWORK_HELPERS := $(OUTPUT)/network_helpers.o -$(OUTPUT)/test_sock: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS) $(OUTPUT)/test_sock_fields: $(CGROUP_HELPERS) $(TESTING_HELPERS) @@ -460,6 +459,7 @@ endef IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \ grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__') MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) +BPF_TARGET_ENDIAN=$(if $(IS_LITTLE_ENDIAN),--target=bpfel,--target=bpfeb) ifneq ($(CROSS_COMPILE),) CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) @@ -487,17 +487,17 @@ $(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h # $4 - binary name define CLANG_BPF_BUILD_RULE $(call msg,CLNG-BPF,$4,$2) - $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v3 -o $2 + $(Q)$(CLANG) $3 -O2 $(BPF_TARGET_ENDIAN) -c $1 -mcpu=v3 -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32 define CLANG_NOALU32_BPF_BUILD_RULE $(call msg,CLNG-BPF,$4,$2) - $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2 + $(Q)$(CLANG) $3 -O2 $(BPF_TARGET_ENDIAN) -c $1 -mcpu=v2 -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but with cpu-v4 define CLANG_CPUV4_BPF_BUILD_RULE $(call msg,CLNG-BPF,$4,$2) - $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v4 -o $2 + $(Q)$(CLANG) $3 -O2 $(BPF_TARGET_ENDIAN) -c $1 -mcpu=v4 -o $2 endef # Build BPF object using GCC define GCC_BPF_BUILD_RULE @@ -637,10 +637,11 @@ $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_OUTPUT)/%: $$$$(%-deps) $(BPFTOOL) | $(TR # When the compiler generates a %.d file, only skel basenames (not # full paths) are specified as prerequisites for corresponding %.o -# file. This target makes %.skel.h basename dependent on full paths, -# linking generated %.d dependency with actual %.skel.h files. -$(notdir %.skel.h): $(TRUNNER_OUTPUT)/%.skel.h - @true +# file. vpath directives below instruct make to search for skel files +# in TRUNNER_OUTPUT, if they are not present in the working directory. +vpath %.skel.h $(TRUNNER_OUTPUT) +vpath %.lskel.h $(TRUNNER_OUTPUT) +vpath %.subskel.h $(TRUNNER_OUTPUT) endif diff --git a/tools/testing/selftests/bpf/config.vm b/tools/testing/selftests/bpf/config.vm index a9746ca78777..da543b24c144 100644 --- a/tools/testing/selftests/bpf/config.vm +++ b/tools/testing/selftests/bpf/config.vm @@ -1,12 +1,15 @@ -CONFIG_9P_FS=y CONFIG_9P_FS_POSIX_ACL=y CONFIG_9P_FS_SECURITY=y +CONFIG_9P_FS=y CONFIG_CRYPTO_DEV_VIRTIO=y -CONFIG_NET_9P=y +CONFIG_FUSE_FS=y +CONFIG_FUSE_PASSTHROUGH=y CONFIG_NET_9P_VIRTIO=y +CONFIG_NET_9P=y CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_BLK=y CONFIG_VIRTIO_CONSOLE=y +CONFIG_VIRTIO_FS=y CONFIG_VIRTIO_NET=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_VSOCKETS_COMMON=y diff --git a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c new file mode 100644 index 000000000000..848d8fc9171f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Google */ + +#include <test_progs.h> +#include <bpf/libbpf.h> +#include <bpf/btf.h> +#include "kmem_cache_iter.skel.h" + +#define SLAB_NAME_MAX 32 + +struct kmem_cache_result { + char name[SLAB_NAME_MAX]; + long obj_size; +}; + +static void subtest_kmem_cache_iter_check_task_struct(struct kmem_cache_iter *skel) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .flags = 0, /* Run it with the current task */ + ); + int prog_fd = bpf_program__fd(skel->progs.check_task_struct); + + /* Get task_struct and check it if's from a slab cache */ + ASSERT_OK(bpf_prog_test_run_opts(prog_fd, &opts), "prog_test_run"); + + /* The BPF program should set 'found' variable */ + ASSERT_EQ(skel->bss->task_struct_found, 1, "task_struct_found"); +} + +static void subtest_kmem_cache_iter_check_slabinfo(struct kmem_cache_iter *skel) +{ + FILE *fp; + int map_fd; + char name[SLAB_NAME_MAX]; + unsigned long objsize; + char rest_of_line[1000]; + struct kmem_cache_result r; + int seen = 0; + + fp = fopen("/proc/slabinfo", "r"); + if (fp == NULL) { + /* CONFIG_SLUB_DEBUG is not enabled */ + return; + } + + map_fd = bpf_map__fd(skel->maps.slab_result); + + /* Ignore first two lines for header */ + fscanf(fp, "slabinfo - version: %*d.%*d\n"); + fscanf(fp, "# %*s %*s %*s %*s %*s %*s : %[^\n]\n", rest_of_line); + + /* Compare name and objsize only - others can be changes frequently */ + while (fscanf(fp, "%s %*u %*u %lu %*u %*u : %[^\n]\n", + name, &objsize, rest_of_line) == 3) { + int ret = bpf_map_lookup_elem(map_fd, &seen, &r); + + if (!ASSERT_OK(ret, "kmem_cache_lookup")) + break; + + ASSERT_STREQ(r.name, name, "kmem_cache_name"); + ASSERT_EQ(r.obj_size, objsize, "kmem_cache_objsize"); + + seen++; + } + + ASSERT_EQ(skel->bss->kmem_cache_seen, seen, "kmem_cache_seen_eq"); + + fclose(fp); +} + +void test_kmem_cache_iter(void) +{ + DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); + struct kmem_cache_iter *skel = NULL; + union bpf_iter_link_info linfo = {}; + struct bpf_link *link; + char buf[256]; + int iter_fd; + + skel = kmem_cache_iter__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kmem_cache_iter__open_and_load")) + return; + + opts.link_info = &linfo; + opts.link_info_len = sizeof(linfo); + + link = bpf_program__attach_iter(skel->progs.slab_info_collector, &opts); + if (!ASSERT_OK_PTR(link, "attach_iter")) + goto destroy; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_GE(iter_fd, 0, "iter_create")) + goto free_link; + + memset(buf, 0, sizeof(buf)); + while (read(iter_fd, buf, sizeof(buf) > 0)) { + /* Read out all contents */ + printf("%s", buf); + } + + /* Next reads should return 0 */ + ASSERT_EQ(read(iter_fd, buf, sizeof(buf)), 0, "read"); + + if (test__start_subtest("check_task_struct")) + subtest_kmem_cache_iter_check_task_struct(skel); + if (test__start_subtest("check_slabinfo")) + subtest_kmem_cache_iter_check_slabinfo(skel); + + close(iter_fd); + +free_link: + bpf_link__destroy(link); +destroy: + kmem_cache_iter__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c index 27676a04d0b6..169ce689b97c 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_buf.c +++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c @@ -169,7 +169,6 @@ static void bpf_prog_load_log_buf(void) ASSERT_GE(fd, 0, "good_fd1"); if (fd >= 0) close(fd); - fd = -1; /* log_level == 2 should always fill log_buf, even for good prog */ log_buf[0] = '\0'; @@ -180,7 +179,6 @@ static void bpf_prog_load_log_buf(void) ASSERT_GE(fd, 0, "good_fd2"); if (fd >= 0) close(fd); - fd = -1; /* log_level == 0 should fill log_buf for bad prog */ log_buf[0] = '\0'; @@ -191,7 +189,6 @@ static void bpf_prog_load_log_buf(void) ASSERT_LT(fd, 0, "bad_fd"); if (fd >= 0) close(fd); - fd = -1; free(log_buf); } diff --git a/tools/testing/selftests/bpf/prog_tests/perf_link.c b/tools/testing/selftests/bpf/prog_tests/perf_link.c index 3a25f1c743a1..d940ff87fa08 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_link.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_link.c @@ -4,8 +4,12 @@ #include <pthread.h> #include <sched.h> #include <test_progs.h> +#include "testing_helpers.h" #include "test_perf_link.skel.h" +#define BURN_TIMEOUT_MS 100 +#define BURN_TIMEOUT_NS BURN_TIMEOUT_MS * 1000000 + static void burn_cpu(void) { volatile int j = 0; @@ -32,6 +36,7 @@ void serial_test_perf_link(void) int run_cnt_before, run_cnt_after; struct bpf_link_info info; __u32 info_len = sizeof(info); + __u64 timeout_time_ns; /* create perf event */ memset(&attr, 0, sizeof(attr)); @@ -63,8 +68,14 @@ void serial_test_perf_link(void) ASSERT_GT(info.prog_id, 0, "link_prog_id"); /* ensure we get at least one perf_event prog execution */ - burn_cpu(); - ASSERT_GT(skel->bss->run_cnt, 0, "run_cnt"); + timeout_time_ns = get_time_ns() + BURN_TIMEOUT_NS; + while (true) { + burn_cpu(); + if (skel->bss->run_cnt > 0) + break; + if (!ASSERT_LT(get_time_ns(), timeout_time_ns, "run_cnt_timeout")) + break; + } /* perf_event is still active, but we close link and BPF program * shouldn't be executed anymore diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 6cc69900b310..1aed94ec14ef 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -8,17 +8,25 @@ static int sigusr1_received; static void sigusr1_handler(int signum) { - sigusr1_received = 1; + sigusr1_received = 8; +} + +static void sigusr1_siginfo_handler(int s, siginfo_t *i, void *v) +{ + sigusr1_received = (int)(long long)i->si_value.sival_ptr; } static void test_send_signal_common(struct perf_event_attr *attr, - bool signal_thread) + bool signal_thread, bool remote) { struct test_send_signal_kern *skel; + struct sigaction sa; int pipe_c2p[2], pipe_p2c[2]; int err = -1, pmu_fd = -1; + volatile int j = 0; char buf[256]; pid_t pid; + int old_prio; if (!ASSERT_OK(pipe(pipe_c2p), "pipe_c2p")) return; @@ -39,11 +47,14 @@ static void test_send_signal_common(struct perf_event_attr *attr, } if (pid == 0) { - int old_prio; - volatile int j = 0; - /* install signal handler and notify parent */ - ASSERT_NEQ(signal(SIGUSR1, sigusr1_handler), SIG_ERR, "signal"); + if (remote) { + sa.sa_sigaction = sigusr1_siginfo_handler; + sa.sa_flags = SA_RESTART | SA_SIGINFO; + ASSERT_NEQ(sigaction(SIGUSR1, &sa, NULL), -1, "sigaction"); + } else { + ASSERT_NEQ(signal(SIGUSR1, sigusr1_handler), SIG_ERR, "signal"); + } close(pipe_c2p[0]); /* close read */ close(pipe_p2c[1]); /* close write */ @@ -52,10 +63,12 @@ static void test_send_signal_common(struct perf_event_attr *attr, * that if an interrupt happens, the underlying task * is this process. */ - errno = 0; - old_prio = getpriority(PRIO_PROCESS, 0); - ASSERT_OK(errno, "getpriority"); - ASSERT_OK(setpriority(PRIO_PROCESS, 0, -20), "setpriority"); + if (!remote) { + errno = 0; + old_prio = getpriority(PRIO_PROCESS, 0); + ASSERT_OK(errno, "getpriority"); + ASSERT_OK(setpriority(PRIO_PROCESS, 0, -20), "setpriority"); + } /* notify parent signal handler is installed */ ASSERT_EQ(write(pipe_c2p[1], buf, 1), 1, "pipe_write"); @@ -66,20 +79,25 @@ static void test_send_signal_common(struct perf_event_attr *attr, /* wait a little for signal handler */ for (int i = 0; i < 1000000000 && !sigusr1_received; i++) { j /= i + j + 1; - if (!attr) - /* trigger the nanosleep tracepoint program. */ - usleep(1); + if (remote) + sleep(1); + else + if (!attr) + /* trigger the nanosleep tracepoint program. */ + usleep(1); } - buf[0] = sigusr1_received ? '2' : '0'; - ASSERT_EQ(sigusr1_received, 1, "sigusr1_received"); + buf[0] = sigusr1_received; + + ASSERT_EQ(sigusr1_received, 8, "sigusr1_received"); ASSERT_EQ(write(pipe_c2p[1], buf, 1), 1, "pipe_write"); /* wait for parent notification and exit */ ASSERT_EQ(read(pipe_p2c[0], buf, 1), 1, "pipe_read"); /* restore the old priority */ - ASSERT_OK(setpriority(PRIO_PROCESS, 0, old_prio), "setpriority"); + if (!remote) + ASSERT_OK(setpriority(PRIO_PROCESS, 0, old_prio), "setpriority"); close(pipe_c2p[1]); close(pipe_p2c[0]); @@ -93,6 +111,17 @@ static void test_send_signal_common(struct perf_event_attr *attr, if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) goto skel_open_load_failure; + /* boost with a high priority so we got a higher chance + * that if an interrupt happens, the underlying task + * is this process. + */ + if (remote) { + errno = 0; + old_prio = getpriority(PRIO_PROCESS, 0); + ASSERT_OK(errno, "getpriority"); + ASSERT_OK(setpriority(PRIO_PROCESS, 0, -20), "setpriority"); + } + if (!attr) { err = test_send_signal_kern__attach(skel); if (!ASSERT_OK(err, "skel_attach")) { @@ -100,8 +129,12 @@ static void test_send_signal_common(struct perf_event_attr *attr, goto destroy_skel; } } else { - pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1 /* cpu */, - -1 /* group id */, 0 /* flags */); + if (!remote) + pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1 /* cpu */, + -1 /* group id */, 0 /* flags */); + else + pmu_fd = syscall(__NR_perf_event_open, attr, getpid(), -1 /* cpu */, + -1 /* group id */, 0 /* flags */); if (!ASSERT_GE(pmu_fd, 0, "perf_event_open")) { err = -1; goto destroy_skel; @@ -119,11 +152,30 @@ static void test_send_signal_common(struct perf_event_attr *attr, /* trigger the bpf send_signal */ skel->bss->signal_thread = signal_thread; skel->bss->sig = SIGUSR1; - skel->bss->pid = pid; + if (!remote) { + skel->bss->target_pid = 0; + skel->bss->pid = pid; + } else { + skel->bss->target_pid = pid; + skel->bss->pid = getpid(); + } /* notify child that bpf program can send_signal now */ ASSERT_EQ(write(pipe_p2c[1], buf, 1), 1, "pipe_write"); + /* For the remote test, the BPF program is triggered from this + * process but the other process/thread is signaled. + */ + if (remote) { + if (!attr) { + for (int i = 0; i < 10; i++) + usleep(1); + } else { + for (int i = 0; i < 100000000; i++) + j /= i + 1; + } + } + /* wait for result */ err = read(pipe_c2p[0], buf, 1); if (!ASSERT_GE(err, 0, "reading pipe")) @@ -133,7 +185,7 @@ static void test_send_signal_common(struct perf_event_attr *attr, goto disable_pmu; } - ASSERT_EQ(buf[0], '2', "incorrect result"); + ASSERT_EQ(buf[0], 8, "incorrect result"); /* notify child safe to exit */ ASSERT_EQ(write(pipe_p2c[1], buf, 1), 1, "pipe_write"); @@ -142,18 +194,21 @@ disable_pmu: close(pmu_fd); destroy_skel: test_send_signal_kern__destroy(skel); + /* restore the old priority */ + if (remote) + ASSERT_OK(setpriority(PRIO_PROCESS, 0, old_prio), "setpriority"); skel_open_load_failure: close(pipe_c2p[0]); close(pipe_p2c[1]); wait(NULL); } -static void test_send_signal_tracepoint(bool signal_thread) +static void test_send_signal_tracepoint(bool signal_thread, bool remote) { - test_send_signal_common(NULL, signal_thread); + test_send_signal_common(NULL, signal_thread, remote); } -static void test_send_signal_perf(bool signal_thread) +static void test_send_signal_perf(bool signal_thread, bool remote) { struct perf_event_attr attr = { .freq = 1, @@ -162,10 +217,10 @@ static void test_send_signal_perf(bool signal_thread) .config = PERF_COUNT_SW_CPU_CLOCK, }; - test_send_signal_common(&attr, signal_thread); + test_send_signal_common(&attr, signal_thread, remote); } -static void test_send_signal_nmi(bool signal_thread) +static void test_send_signal_nmi(bool signal_thread, bool remote) { struct perf_event_attr attr = { .sample_period = 1, @@ -191,21 +246,35 @@ static void test_send_signal_nmi(bool signal_thread) close(pmu_fd); } - test_send_signal_common(&attr, signal_thread); + test_send_signal_common(&attr, signal_thread, remote); } void test_send_signal(void) { if (test__start_subtest("send_signal_tracepoint")) - test_send_signal_tracepoint(false); + test_send_signal_tracepoint(false, false); if (test__start_subtest("send_signal_perf")) - test_send_signal_perf(false); + test_send_signal_perf(false, false); if (test__start_subtest("send_signal_nmi")) - test_send_signal_nmi(false); + test_send_signal_nmi(false, false); if (test__start_subtest("send_signal_tracepoint_thread")) - test_send_signal_tracepoint(true); + test_send_signal_tracepoint(true, false); if (test__start_subtest("send_signal_perf_thread")) - test_send_signal_perf(true); + test_send_signal_perf(true, false); if (test__start_subtest("send_signal_nmi_thread")) - test_send_signal_nmi(true); + test_send_signal_nmi(true, false); + + /* Signal remote thread and thread group */ + if (test__start_subtest("send_signal_tracepoint_remote")) + test_send_signal_tracepoint(false, true); + if (test__start_subtest("send_signal_perf_remote")) + test_send_signal_perf(false, true); + if (test__start_subtest("send_signal_nmi_remote")) + test_send_signal_nmi(false, true); + if (test__start_subtest("send_signal_tracepoint_thread_remote")) + test_send_signal_tracepoint(true, true); + if (test__start_subtest("send_signal_perf_thread_remote")) + test_send_signal_perf(true, true); + if (test__start_subtest("send_signal_nmi_thread_remote")) + test_send_signal_nmi(true, true); } diff --git a/tools/testing/selftests/bpf/prog_tests/sock_create.c b/tools/testing/selftests/bpf/prog_tests/sock_create.c new file mode 100644 index 000000000000..187ffc5e60c4 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sock_create.c @@ -0,0 +1,348 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <test_progs.h> +#include "cgroup_helpers.h" + +static char bpf_log_buf[4096]; +static bool verbose; + +enum sock_create_test_error { + OK = 0, + DENY_CREATE, +}; + +static struct sock_create_test { + const char *descr; + const struct bpf_insn insns[64]; + enum bpf_attach_type attach_type; + enum bpf_attach_type expected_attach_type; + + int domain; + int type; + int protocol; + + int optname; + int optval; + enum sock_create_test_error error; +} tests[] = { + { + .descr = "AF_INET set priority", + .insns = { + /* r3 = 123 (priority) */ + BPF_MOV64_IMM(BPF_REG_3, 123), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, + offsetof(struct bpf_sock, priority)), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + + .domain = AF_INET, + .type = SOCK_DGRAM, + + .optname = SO_PRIORITY, + .optval = 123, + }, + { + .descr = "AF_INET6 set priority", + .insns = { + /* r3 = 123 (priority) */ + BPF_MOV64_IMM(BPF_REG_3, 123), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, + offsetof(struct bpf_sock, priority)), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + + .domain = AF_INET6, + .type = SOCK_DGRAM, + + .optname = SO_PRIORITY, + .optval = 123, + }, + { + .descr = "AF_INET set mark", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* get uid of process */ + BPF_EMIT_CALL(BPF_FUNC_get_current_uid_gid), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffffffff), + + /* if uid is 0, use given mark(666), else use uid as the mark */ + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_3, 666), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, + offsetof(struct bpf_sock, mark)), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + + .domain = AF_INET, + .type = SOCK_DGRAM, + + .optname = SO_MARK, + .optval = 666, + }, + { + .descr = "AF_INET6 set mark", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* get uid of process */ + BPF_EMIT_CALL(BPF_FUNC_get_current_uid_gid), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffffffff), + + /* if uid is 0, use given mark(666), else use uid as the mark */ + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_3, 666), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, + offsetof(struct bpf_sock, mark)), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + + .domain = AF_INET6, + .type = SOCK_DGRAM, + + .optname = SO_MARK, + .optval = 666, + }, + { + .descr = "AF_INET bound to iface", + .insns = { + /* r3 = 1 (lo interface) */ + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, + offsetof(struct bpf_sock, bound_dev_if)), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + + .domain = AF_INET, + .type = SOCK_DGRAM, + + .optname = SO_BINDTOIFINDEX, + .optval = 1, + }, + { + .descr = "AF_INET6 bound to iface", + .insns = { + /* r3 = 1 (lo interface) */ + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, + offsetof(struct bpf_sock, bound_dev_if)), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + + .domain = AF_INET6, + .type = SOCK_DGRAM, + + .optname = SO_BINDTOIFINDEX, + .optval = 1, + }, + { + .descr = "block AF_INET, SOCK_DGRAM, IPPROTO_ICMP socket", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = verdict */ + + /* sock->family == AF_INET */ + BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, + offsetof(struct bpf_sock, family)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, AF_INET, 5), + + /* sock->type == SOCK_DGRAM */ + BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, + offsetof(struct bpf_sock, type)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, SOCK_DGRAM, 3), + + /* sock->protocol == IPPROTO_ICMP */ + BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, + offsetof(struct bpf_sock, protocol)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, IPPROTO_ICMP, 1), + + /* return 0 (block) */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + + .domain = AF_INET, + .type = SOCK_DGRAM, + .protocol = IPPROTO_ICMP, + + .error = DENY_CREATE, + }, + { + .descr = "block AF_INET6, SOCK_DGRAM, IPPROTO_ICMPV6 socket", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = verdict */ + + /* sock->family == AF_INET6 */ + BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, + offsetof(struct bpf_sock, family)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, AF_INET6, 5), + + /* sock->type == SOCK_DGRAM */ + BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, + offsetof(struct bpf_sock, type)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, SOCK_DGRAM, 3), + + /* sock->protocol == IPPROTO_ICMPV6 */ + BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, + offsetof(struct bpf_sock, protocol)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, IPPROTO_ICMPV6, 1), + + /* return 0 (block) */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + + .domain = AF_INET, + .type = SOCK_DGRAM, + .protocol = IPPROTO_ICMPV6, + + .error = DENY_CREATE, + }, + { + .descr = "load w/o expected_attach_type (compat mode)", + .insns = { + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .expected_attach_type = 0, + .attach_type = BPF_CGROUP_INET_SOCK_CREATE, + + .domain = AF_INET, + .type = SOCK_STREAM, + }, +}; + +static int load_prog(const struct bpf_insn *insns, + enum bpf_attach_type expected_attach_type) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .expected_attach_type = expected_attach_type, + .log_level = 2, + .log_buf = bpf_log_buf, + .log_size = sizeof(bpf_log_buf), + ); + int fd, insns_cnt = 0; + + for (; + insns[insns_cnt].code != (BPF_JMP | BPF_EXIT); + insns_cnt++) { + } + insns_cnt++; + + fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, + insns_cnt, &opts); + if (verbose && fd < 0) + fprintf(stderr, "%s\n", bpf_log_buf); + + return fd; +} + +static int run_test(int cgroup_fd, struct sock_create_test *test) +{ + int sock_fd, err, prog_fd, optval, ret = -1; + socklen_t optlen = sizeof(optval); + + prog_fd = load_prog(test->insns, test->expected_attach_type); + if (prog_fd < 0) { + log_err("Failed to load BPF program"); + return -1; + } + + err = bpf_prog_attach(prog_fd, cgroup_fd, test->attach_type, 0); + if (err < 0) { + log_err("Failed to attach BPF program"); + goto close_prog_fd; + } + + sock_fd = socket(test->domain, test->type, test->protocol); + if (sock_fd < 0) { + if (test->error == DENY_CREATE) + ret = 0; + else + log_err("Failed to create socket"); + + goto detach_prog; + } + + if (test->optname) { + err = getsockopt(sock_fd, SOL_SOCKET, test->optname, &optval, &optlen); + if (err) { + log_err("Failed to call getsockopt"); + goto cleanup; + } + + if (optval != test->optval) { + errno = 0; + log_err("getsockopt returned unexpected optval"); + goto cleanup; + } + } + + ret = test->error != OK; + +cleanup: + close(sock_fd); +detach_prog: + bpf_prog_detach2(prog_fd, cgroup_fd, test->attach_type); +close_prog_fd: + close(prog_fd); + return ret; +} + +void test_sock_create(void) +{ + int cgroup_fd, i; + + cgroup_fd = test__join_cgroup("/sock_create"); + if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup")) + return; + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + if (!test__start_subtest(tests[i].descr)) + continue; + + ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr); + } + + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/prog_tests/sock_post_bind.c index 810c3740b2cc..788135c9c673 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_post_bind.c @@ -1,132 +1,35 @@ // SPDX-License-Identifier: GPL-2.0 -// Copyright (c) 2018 Facebook - -#include <stdio.h> -#include <unistd.h> - -#include <arpa/inet.h> -#include <sys/types.h> -#include <sys/socket.h> - -#include <linux/filter.h> - -#include <bpf/bpf.h> - +#include <linux/bpf.h> +#include <test_progs.h> #include "cgroup_helpers.h" -#include <bpf/bpf_endian.h> -#include "bpf_util.h" -#define CG_PATH "/foo" -#define MAX_INSNS 512 +#define TEST_NS "sock_post_bind" -char bpf_log_buf[BPF_LOG_BUF_SIZE]; -static bool verbose = false; +static char bpf_log_buf[4096]; -struct sock_test { - const char *descr; +static struct sock_post_bind_test { + const char *descr; /* BPF prog properties */ - struct bpf_insn insns[MAX_INSNS]; - enum bpf_attach_type expected_attach_type; - enum bpf_attach_type attach_type; + const struct bpf_insn insns[64]; + enum bpf_attach_type attach_type; + enum bpf_attach_type expected_attach_type; /* Socket properties */ - int domain; - int type; + int domain; + int type; /* Endpoint to bind() to */ const char *ip; unsigned short port; unsigned short port_retry; + /* Expected test result */ enum { - LOAD_REJECT, ATTACH_REJECT, BIND_REJECT, SUCCESS, RETRY_SUCCESS, RETRY_REJECT } result; -}; - -static struct sock_test tests[] = { - { - .descr = "bind4 load with invalid access: src_ip6", - .insns = { - BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock, src_ip6[0])), - BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_EXIT_INSN(), - }, - .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, - .attach_type = BPF_CGROUP_INET4_POST_BIND, - .result = LOAD_REJECT, - }, - { - .descr = "bind4 load with invalid access: mark", - .insns = { - BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock, mark)), - BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_EXIT_INSN(), - }, - .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, - .attach_type = BPF_CGROUP_INET4_POST_BIND, - .result = LOAD_REJECT, - }, - { - .descr = "bind6 load with invalid access: src_ip4", - .insns = { - BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock, src_ip4)), - BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_EXIT_INSN(), - }, - .expected_attach_type = BPF_CGROUP_INET6_POST_BIND, - .attach_type = BPF_CGROUP_INET6_POST_BIND, - .result = LOAD_REJECT, - }, - { - .descr = "sock_create load with invalid access: src_port", - .insns = { - BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock, src_port)), - BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_EXIT_INSN(), - }, - .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, - .attach_type = BPF_CGROUP_INET_SOCK_CREATE, - .result = LOAD_REJECT, - }, - { - .descr = "sock_create load w/o expected_attach_type (compat mode)", - .insns = { - BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_EXIT_INSN(), - }, - .expected_attach_type = 0, - .attach_type = BPF_CGROUP_INET_SOCK_CREATE, - .domain = AF_INET, - .type = SOCK_STREAM, - .ip = "127.0.0.1", - .port = 8097, - .result = SUCCESS, - }, - { - .descr = "sock_create load w/ expected_attach_type", - .insns = { - BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_EXIT_INSN(), - }, - .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, - .attach_type = BPF_CGROUP_INET_SOCK_CREATE, - .domain = AF_INET, - .type = SOCK_STREAM, - .ip = "127.0.0.1", - .port = 8097, - .result = SUCCESS, - }, +} tests[] = { { .descr = "attach type mismatch bind4 vs bind6", .insns = { @@ -374,40 +277,29 @@ static struct sock_test tests[] = { }, }; -static size_t probe_prog_length(const struct bpf_insn *fp) -{ - size_t len; - - for (len = MAX_INSNS - 1; len > 0; --len) - if (fp[len].code != 0 || fp[len].imm != 0) - break; - return len + 1; -} - -static int load_sock_prog(const struct bpf_insn *prog, - enum bpf_attach_type attach_type) +static int load_prog(const struct bpf_insn *insns, + enum bpf_attach_type expected_attach_type) { - LIBBPF_OPTS(bpf_prog_load_opts, opts); - int ret, insn_cnt; - - insn_cnt = probe_prog_length(prog); - - opts.expected_attach_type = attach_type; - opts.log_buf = bpf_log_buf; - opts.log_size = BPF_LOG_BUF_SIZE; - opts.log_level = 2; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .expected_attach_type = expected_attach_type, + .log_level = 2, + .log_buf = bpf_log_buf, + .log_size = sizeof(bpf_log_buf), + ); + int fd, insns_cnt = 0; + + for (; + insns[insns_cnt].code != (BPF_JMP | BPF_EXIT); + insns_cnt++) { + } + insns_cnt++; - ret = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", prog, insn_cnt, &opts); - if (verbose && ret < 0) + fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, + insns_cnt, &opts); + if (fd < 0) fprintf(stderr, "%s\n", bpf_log_buf); - return ret; -} - -static int attach_sock_prog(int cgfd, int progfd, - enum bpf_attach_type attach_type) -{ - return bpf_prog_attach(progfd, cgfd, attach_type, BPF_F_ALLOW_OVERRIDE); + return fd; } static int bind_sock(int domain, int type, const char *ip, @@ -477,22 +369,16 @@ out: return res; } -static int run_test_case(int cgfd, const struct sock_test *test) +static int run_test(int cgroup_fd, struct sock_post_bind_test *test) { - int progfd = -1; - int err = 0; - int res; - - printf("Test case: %s .. ", test->descr); - progfd = load_sock_prog(test->insns, test->expected_attach_type); - if (progfd < 0) { - if (test->result == LOAD_REJECT) - goto out; - else - goto err; - } + int err, prog_fd, res, ret = 0; - if (attach_sock_prog(cgfd, progfd, test->attach_type) < 0) { + prog_fd = load_prog(test->insns, test->expected_attach_type); + if (prog_fd < 0) + goto err; + + err = bpf_prog_attach(prog_fd, cgroup_fd, test->attach_type, 0); + if (err < 0) { if (test->result == ATTACH_REJECT) goto out; else @@ -503,54 +389,38 @@ static int run_test_case(int cgfd, const struct sock_test *test) test->port_retry); if (res > 0 && test->result == res) goto out; - err: - err = -1; + ret = -1; out: /* Detaching w/o checking return code: best effort attempt. */ - if (progfd != -1) - bpf_prog_detach(cgfd, test->attach_type); - close(progfd); - printf("[%s]\n", err ? "FAIL" : "PASS"); - return err; + if (prog_fd != -1) + bpf_prog_detach(cgroup_fd, test->attach_type); + close(prog_fd); + return ret; } -static int run_tests(int cgfd) +void test_sock_post_bind(void) { - int passes = 0; - int fails = 0; + struct netns_obj *ns; + int cgroup_fd; int i; - for (i = 0; i < ARRAY_SIZE(tests); ++i) { - if (run_test_case(cgfd, &tests[i])) - ++fails; - else - ++passes; - } - printf("Summary: %d PASSED, %d FAILED\n", passes, fails); - return fails ? -1 : 0; -} - -int main(int argc, char **argv) -{ - int cgfd = -1; - int err = 0; + cgroup_fd = test__join_cgroup("/post_bind"); + if (!ASSERT_OK_FD(cgroup_fd, "join_cgroup")) + return; - cgfd = cgroup_setup_and_join(CG_PATH); - if (cgfd < 0) - goto err; + ns = netns_new(TEST_NS, true); + if (!ASSERT_OK_PTR(ns, "netns_new")) + goto cleanup; - /* Use libbpf 1.0 API mode */ - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + for (i = 0; i < ARRAY_SIZE(tests); i++) { + if (!test__start_subtest(tests[i].descr)) + continue; - if (run_tests(cgfd)) - goto err; + ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr); + } - goto out; -err: - err = -1; -out: - close(cgfd); - cleanup_cgroup_environment(); - return err; +cleanup: + netns_free(ns); + close(cgroup_fd); } diff --git a/tools/testing/selftests/bpf/prog_tests/subskeleton.c b/tools/testing/selftests/bpf/prog_tests/subskeleton.c index 9c31b7004f9c..fdf13ed0152a 100644 --- a/tools/testing/selftests/bpf/prog_tests/subskeleton.c +++ b/tools/testing/selftests/bpf/prog_tests/subskeleton.c @@ -46,7 +46,8 @@ static int subskeleton_lib_subresult(struct bpf_object *obj) return result; } -void test_subskeleton(void) +/* initialize and load through skeleton, then instantiate subskeleton out of it */ +static void subtest_skel_subskeleton(void) { int err, result; struct test_subskeleton *skel; @@ -76,3 +77,76 @@ void test_subskeleton(void) cleanup: test_subskeleton__destroy(skel); } + +/* initialize and load through generic bpf_object API, then instantiate subskeleton out of it */ +static void subtest_obj_subskeleton(void) +{ + int err, result; + const void *elf_bytes; + size_t elf_bytes_sz = 0, rodata_sz = 0, bss_sz = 0; + struct bpf_object *obj; + const struct bpf_map *map; + const struct bpf_program *prog; + struct bpf_link *link = NULL; + struct test_subskeleton__rodata *rodata; + struct test_subskeleton__bss *bss; + + elf_bytes = test_subskeleton__elf_bytes(&elf_bytes_sz); + if (!ASSERT_OK_PTR(elf_bytes, "elf_bytes")) + return; + + obj = bpf_object__open_mem(elf_bytes, elf_bytes_sz, NULL); + if (!ASSERT_OK_PTR(obj, "obj_open_mem")) + return; + + map = bpf_object__find_map_by_name(obj, ".rodata"); + if (!ASSERT_OK_PTR(map, "rodata_map_by_name")) + goto cleanup; + + rodata = bpf_map__initial_value(map, &rodata_sz); + if (!ASSERT_OK_PTR(rodata, "rodata_get")) + goto cleanup; + + rodata->rovar1 = 10; + rodata->var1 = 1; + subskeleton_lib_setup(obj); + + err = bpf_object__load(obj); + if (!ASSERT_OK(err, "obj_load")) + goto cleanup; + + prog = bpf_object__find_program_by_name(obj, "handler1"); + if (!ASSERT_OK_PTR(prog, "prog_by_name")) + goto cleanup; + + link = bpf_program__attach(prog); + if (!ASSERT_OK_PTR(link, "prog_attach")) + goto cleanup; + + /* trigger tracepoint */ + usleep(1); + + map = bpf_object__find_map_by_name(obj, ".bss"); + if (!ASSERT_OK_PTR(map, "bss_map_by_name")) + goto cleanup; + + bss = bpf_map__initial_value(map, &bss_sz); + if (!ASSERT_OK_PTR(rodata, "rodata_get")) + goto cleanup; + + result = subskeleton_lib_subresult(obj) * 10; + ASSERT_EQ(bss->out1, result, "out1"); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); +} + + +void test_subskeleton(void) +{ + if (test__start_subtest("skel_subskel")) + subtest_skel_subskeleton(); + if (test__start_subtest("obj_subskel")) + subtest_obj_subskeleton(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index 21c5a37846ad..40f22454cf05 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -1496,8 +1496,8 @@ static void test_tailcall_bpf2bpf_hierarchy_3(void) RUN_TESTS(tailcall_bpf2bpf_hierarchy3); } -/* test_tailcall_freplace checks that the attached freplace prog is OK to - * update the prog_array map. +/* test_tailcall_freplace checks that the freplace prog fails to update the + * prog_array map, no matter whether the freplace prog attaches to its target. */ static void test_tailcall_freplace(void) { @@ -1505,7 +1505,7 @@ static void test_tailcall_freplace(void) struct bpf_link *freplace_link = NULL; struct bpf_program *freplace_prog; struct tc_bpf2bpf *tc_skel = NULL; - int prog_fd, map_fd; + int prog_fd, tc_prog_fd, map_fd; char buff[128] = {}; int err, key; @@ -1523,9 +1523,10 @@ static void test_tailcall_freplace(void) if (!ASSERT_OK_PTR(tc_skel, "tc_bpf2bpf__open_and_load")) goto out; - prog_fd = bpf_program__fd(tc_skel->progs.entry_tc); + tc_prog_fd = bpf_program__fd(tc_skel->progs.entry_tc); freplace_prog = freplace_skel->progs.entry_freplace; - err = bpf_program__set_attach_target(freplace_prog, prog_fd, "subprog"); + err = bpf_program__set_attach_target(freplace_prog, tc_prog_fd, + "subprog_tc"); if (!ASSERT_OK(err, "set_attach_target")) goto out; @@ -1533,27 +1534,116 @@ static void test_tailcall_freplace(void) if (!ASSERT_OK(err, "tailcall_freplace__load")) goto out; - freplace_link = bpf_program__attach_freplace(freplace_prog, prog_fd, - "subprog"); + map_fd = bpf_map__fd(freplace_skel->maps.jmp_table); + prog_fd = bpf_program__fd(freplace_prog); + key = 0; + err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY); + ASSERT_ERR(err, "update jmp_table failure"); + + freplace_link = bpf_program__attach_freplace(freplace_prog, tc_prog_fd, + "subprog_tc"); if (!ASSERT_OK_PTR(freplace_link, "attach_freplace")) goto out; - map_fd = bpf_map__fd(freplace_skel->maps.jmp_table); - prog_fd = bpf_program__fd(freplace_prog); + err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY); + ASSERT_ERR(err, "update jmp_table failure"); + +out: + bpf_link__destroy(freplace_link); + tailcall_freplace__destroy(freplace_skel); + tc_bpf2bpf__destroy(tc_skel); +} + +/* test_tailcall_bpf2bpf_freplace checks the failure that fails to attach a tail + * callee prog with freplace prog or fails to update an extended prog to + * prog_array map. + */ +static void test_tailcall_bpf2bpf_freplace(void) +{ + struct tailcall_freplace *freplace_skel = NULL; + struct bpf_link *freplace_link = NULL; + struct tc_bpf2bpf *tc_skel = NULL; + char buff[128] = {}; + int prog_fd, map_fd; + int err, key; + + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); + + tc_skel = tc_bpf2bpf__open_and_load(); + if (!ASSERT_OK_PTR(tc_skel, "tc_bpf2bpf__open_and_load")) + goto out; + + prog_fd = bpf_program__fd(tc_skel->progs.entry_tc); + freplace_skel = tailcall_freplace__open(); + if (!ASSERT_OK_PTR(freplace_skel, "tailcall_freplace__open")) + goto out; + + err = bpf_program__set_attach_target(freplace_skel->progs.entry_freplace, + prog_fd, "subprog_tc"); + if (!ASSERT_OK(err, "set_attach_target")) + goto out; + + err = tailcall_freplace__load(freplace_skel); + if (!ASSERT_OK(err, "tailcall_freplace__load")) + goto out; + + /* OK to attach then detach freplace prog. */ + + freplace_link = bpf_program__attach_freplace(freplace_skel->progs.entry_freplace, + prog_fd, "subprog_tc"); + if (!ASSERT_OK_PTR(freplace_link, "attach_freplace")) + goto out; + + err = bpf_link__destroy(freplace_link); + if (!ASSERT_OK(err, "destroy link")) + goto out; + + /* OK to update prog_array map then delete element from the map. */ + key = 0; + map_fd = bpf_map__fd(freplace_skel->maps.jmp_table); err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY); if (!ASSERT_OK(err, "update jmp_table")) goto out; - prog_fd = bpf_program__fd(tc_skel->progs.entry_tc); - err = bpf_prog_test_run_opts(prog_fd, &topts); - ASSERT_OK(err, "test_run"); - ASSERT_EQ(topts.retval, 34, "test_run retval"); + err = bpf_map_delete_elem(map_fd, &key); + if (!ASSERT_OK(err, "delete_elem from jmp_table")) + goto out; + + /* Fail to attach a tail callee prog with freplace prog. */ + + err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY); + if (!ASSERT_OK(err, "update jmp_table")) + goto out; + + freplace_link = bpf_program__attach_freplace(freplace_skel->progs.entry_freplace, + prog_fd, "subprog_tc"); + if (!ASSERT_ERR_PTR(freplace_link, "attach_freplace failure")) + goto out; + + err = bpf_map_delete_elem(map_fd, &key); + if (!ASSERT_OK(err, "delete_elem from jmp_table")) + goto out; + + /* Fail to update an extended prog to prog_array map. */ + + freplace_link = bpf_program__attach_freplace(freplace_skel->progs.entry_freplace, + prog_fd, "subprog_tc"); + if (!ASSERT_OK_PTR(freplace_link, "attach_freplace")) + goto out; + + err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY); + if (!ASSERT_ERR(err, "update jmp_table failure")) + goto out; out: bpf_link__destroy(freplace_link); - tc_bpf2bpf__destroy(tc_skel); tailcall_freplace__destroy(freplace_skel); + tc_bpf2bpf__destroy(tc_skel); } void test_tailcalls(void) @@ -1606,4 +1696,6 @@ void test_tailcalls(void) test_tailcall_bpf2bpf_hierarchy_3(); if (test__start_subtest("tailcall_freplace")) test_tailcall_freplace(); + if (test__start_subtest("tailcall_bpf2bpf_freplace")) + test_tailcall_bpf2bpf_freplace(); } diff --git a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c index d4579f735398..83b90335967a 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c +++ b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c @@ -68,6 +68,74 @@ cleanup: task_kfunc_success__destroy(skel); } +static int run_vpid_test(void *prog_name) +{ + struct task_kfunc_success *skel; + struct bpf_program *prog; + int prog_fd, err = 0; + + if (getpid() != 1) + return 1; + + skel = open_load_task_kfunc_skel(); + if (!skel) + return 2; + + if (skel->bss->err) { + err = 3; + goto cleanup; + } + + prog = bpf_object__find_program_by_name(skel->obj, prog_name); + if (!prog) { + err = 4; + goto cleanup; + } + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + err = 5; + goto cleanup; + } + + if (bpf_prog_test_run_opts(prog_fd, NULL)) { + err = 6; + goto cleanup; + } + + if (skel->bss->err) + err = 7 + skel->bss->err; +cleanup: + task_kfunc_success__destroy(skel); + return err; +} + +static void run_vpid_success_test(const char *prog_name) +{ + const int stack_size = 1024 * 1024; + int child_pid, wstatus; + char *stack; + + stack = (char *)malloc(stack_size); + if (!ASSERT_OK_PTR(stack, "clone_stack")) + return; + + child_pid = clone(run_vpid_test, stack + stack_size, + CLONE_NEWPID | SIGCHLD, (void *)prog_name); + if (!ASSERT_GT(child_pid, -1, "child_pid")) + goto cleanup; + + if (!ASSERT_GT(waitpid(child_pid, &wstatus, 0), -1, "waitpid")) + goto cleanup; + + if (WEXITSTATUS(wstatus) > 7) + ASSERT_OK(WEXITSTATUS(wstatus) - 7, "vpid_test_failure"); + else + ASSERT_OK(WEXITSTATUS(wstatus), "run_vpid_test_err"); +cleanup: + free(stack); +} + static const char * const success_tests[] = { "test_task_acquire_release_argument", "test_task_acquire_release_current", @@ -83,6 +151,11 @@ static const char * const success_tests[] = { "test_task_kfunc_flavor_relo_not_found", }; +static const char * const vpid_success_tests[] = { + "test_task_from_vpid_current", + "test_task_from_vpid_invalid", +}; + void test_task_kfunc(void) { int i; @@ -94,5 +167,12 @@ void test_task_kfunc(void) run_success_test(success_tests[i]); } + for (i = 0; i < ARRAY_SIZE(vpid_success_tests); i++) { + if (!test__start_subtest(vpid_success_tests[i])) + continue; + + run_vpid_success_test(vpid_success_tests[i]); + } + RUN_TESTS(task_kfunc_failure); } diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c index c33c05161a9e..00cc9d0aee5d 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c @@ -7,12 +7,20 @@ #include <pthread.h> #include <sys/syscall.h> /* For SYS_xxx definitions */ #include <sys/types.h> +#include <sys/eventfd.h> +#include <sys/mman.h> #include <test_progs.h> +#include <bpf/btf.h> #include "task_local_storage_helpers.h" #include "task_local_storage.skel.h" #include "task_local_storage_exit_creds.skel.h" #include "task_ls_recursion.skel.h" #include "task_storage_nodeadlock.skel.h" +#include "uptr_test_common.h" +#include "task_ls_uptr.skel.h" +#include "uptr_update_failure.skel.h" +#include "uptr_failure.skel.h" +#include "uptr_map_failure.skel.h" static void test_sys_enter_exit(void) { @@ -227,6 +235,259 @@ done: sched_setaffinity(getpid(), sizeof(old), &old); } +static struct user_data udata __attribute__((aligned(16))) = { + .a = 1, + .b = 2, +}; + +static struct user_data udata2 __attribute__((aligned(16))) = { + .a = 3, + .b = 4, +}; + +static void check_udata2(int expected) +{ + udata2.result = udata2.nested_result = 0; + usleep(1); + ASSERT_EQ(udata2.result, expected, "udata2.result"); + ASSERT_EQ(udata2.nested_result, expected, "udata2.nested_result"); +} + +static void test_uptr_basic(void) +{ + int map_fd, parent_task_fd, ev_fd; + struct value_type value = {}; + struct task_ls_uptr *skel; + pid_t child_pid, my_tid; + __u64 ev_dummy_data = 1; + int err; + + my_tid = syscall(SYS_gettid); + parent_task_fd = sys_pidfd_open(my_tid, 0); + if (!ASSERT_OK_FD(parent_task_fd, "parent_task_fd")) + return; + + ev_fd = eventfd(0, 0); + if (!ASSERT_OK_FD(ev_fd, "ev_fd")) { + close(parent_task_fd); + return; + } + + skel = task_ls_uptr__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + goto out; + + map_fd = bpf_map__fd(skel->maps.datamap); + value.udata = &udata; + value.nested.udata = &udata; + err = bpf_map_update_elem(map_fd, &parent_task_fd, &value, BPF_NOEXIST); + if (!ASSERT_OK(err, "update_elem(udata)")) + goto out; + + err = task_ls_uptr__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto out; + + child_pid = fork(); + if (!ASSERT_NEQ(child_pid, -1, "fork")) + goto out; + + /* Call syscall in the child process, but access the map value of + * the parent process in the BPF program to check if the user kptr + * is translated/mapped correctly. + */ + if (child_pid == 0) { + /* child */ + + /* Overwrite the user_data in the child process to check if + * the BPF program accesses the user_data of the parent. + */ + udata.a = 0; + udata.b = 0; + + /* Wait for the parent to set child_pid */ + read(ev_fd, &ev_dummy_data, sizeof(ev_dummy_data)); + exit(0); + } + + skel->bss->parent_pid = my_tid; + skel->bss->target_pid = child_pid; + + write(ev_fd, &ev_dummy_data, sizeof(ev_dummy_data)); + + err = waitpid(child_pid, NULL, 0); + ASSERT_EQ(err, child_pid, "waitpid"); + ASSERT_EQ(udata.result, MAGIC_VALUE + udata.a + udata.b, "udata.result"); + ASSERT_EQ(udata.nested_result, MAGIC_VALUE + udata.a + udata.b, "udata.nested_result"); + + skel->bss->target_pid = my_tid; + + /* update_elem: uptr changes from udata1 to udata2 */ + value.udata = &udata2; + value.nested.udata = &udata2; + err = bpf_map_update_elem(map_fd, &parent_task_fd, &value, BPF_EXIST); + if (!ASSERT_OK(err, "update_elem(udata2)")) + goto out; + check_udata2(MAGIC_VALUE + udata2.a + udata2.b); + + /* update_elem: uptr changes from udata2 uptr to NULL */ + memset(&value, 0, sizeof(value)); + err = bpf_map_update_elem(map_fd, &parent_task_fd, &value, BPF_EXIST); + if (!ASSERT_OK(err, "update_elem(udata2)")) + goto out; + check_udata2(0); + + /* update_elem: uptr changes from NULL to udata2 */ + value.udata = &udata2; + value.nested.udata = &udata2; + err = bpf_map_update_elem(map_fd, &parent_task_fd, &value, BPF_EXIST); + if (!ASSERT_OK(err, "update_elem(udata2)")) + goto out; + check_udata2(MAGIC_VALUE + udata2.a + udata2.b); + + /* Check if user programs can access the value of user kptrs + * through bpf_map_lookup_elem(). Make sure the kernel value is not + * leaked. + */ + err = bpf_map_lookup_elem(map_fd, &parent_task_fd, &value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto out; + ASSERT_EQ(value.udata, NULL, "value.udata"); + ASSERT_EQ(value.nested.udata, NULL, "value.nested.udata"); + + /* delete_elem */ + err = bpf_map_delete_elem(map_fd, &parent_task_fd); + ASSERT_OK(err, "delete_elem(udata2)"); + check_udata2(0); + + /* update_elem: add uptr back to test map_free */ + value.udata = &udata2; + value.nested.udata = &udata2; + err = bpf_map_update_elem(map_fd, &parent_task_fd, &value, BPF_NOEXIST); + ASSERT_OK(err, "update_elem(udata2)"); + +out: + task_ls_uptr__destroy(skel); + close(ev_fd); + close(parent_task_fd); +} + +static void test_uptr_across_pages(void) +{ + int page_size = getpagesize(); + struct value_type value = {}; + struct task_ls_uptr *skel; + int err, task_fd, map_fd; + void *mem; + + task_fd = sys_pidfd_open(getpid(), 0); + if (!ASSERT_OK_FD(task_fd, "task_fd")) + return; + + mem = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (!ASSERT_OK_PTR(mem, "mmap(page_size * 2)")) { + close(task_fd); + return; + } + + skel = task_ls_uptr__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + goto out; + + map_fd = bpf_map__fd(skel->maps.datamap); + value.udata = mem + page_size - offsetof(struct user_data, b); + err = bpf_map_update_elem(map_fd, &task_fd, &value, 0); + if (!ASSERT_ERR(err, "update_elem(udata)")) + goto out; + ASSERT_EQ(errno, EOPNOTSUPP, "errno"); + + value.udata = mem + page_size - sizeof(struct user_data); + err = bpf_map_update_elem(map_fd, &task_fd, &value, 0); + ASSERT_OK(err, "update_elem(udata)"); + +out: + task_ls_uptr__destroy(skel); + close(task_fd); + munmap(mem, page_size * 2); +} + +static void test_uptr_update_failure(void) +{ + struct value_lock_type value = {}; + struct uptr_update_failure *skel; + int err, task_fd, map_fd; + + task_fd = sys_pidfd_open(getpid(), 0); + if (!ASSERT_OK_FD(task_fd, "task_fd")) + return; + + skel = uptr_update_failure__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + goto out; + + map_fd = bpf_map__fd(skel->maps.datamap); + + value.udata = &udata; + err = bpf_map_update_elem(map_fd, &task_fd, &value, BPF_F_LOCK); + if (!ASSERT_ERR(err, "update_elem(udata, BPF_F_LOCK)")) + goto out; + ASSERT_EQ(errno, EOPNOTSUPP, "errno"); + + err = bpf_map_update_elem(map_fd, &task_fd, &value, BPF_EXIST); + if (!ASSERT_ERR(err, "update_elem(udata, BPF_EXIST)")) + goto out; + ASSERT_EQ(errno, ENOENT, "errno"); + + err = bpf_map_update_elem(map_fd, &task_fd, &value, BPF_NOEXIST); + if (!ASSERT_OK(err, "update_elem(udata, BPF_NOEXIST)")) + goto out; + + value.udata = &udata2; + err = bpf_map_update_elem(map_fd, &task_fd, &value, BPF_NOEXIST); + if (!ASSERT_ERR(err, "update_elem(udata2, BPF_NOEXIST)")) + goto out; + ASSERT_EQ(errno, EEXIST, "errno"); + +out: + uptr_update_failure__destroy(skel); + close(task_fd); +} + +static void test_uptr_map_failure(const char *map_name, int expected_errno) +{ + LIBBPF_OPTS(bpf_map_create_opts, create_attr); + struct uptr_map_failure *skel; + struct bpf_map *map; + struct btf *btf; + int map_fd, err; + + skel = uptr_map_failure__open(); + if (!ASSERT_OK_PTR(skel, "uptr_map_failure__open")) + return; + + map = bpf_object__find_map_by_name(skel->obj, map_name); + btf = bpf_object__btf(skel->obj); + err = btf__load_into_kernel(btf); + if (!ASSERT_OK(err, "btf__load_into_kernel")) + goto done; + + create_attr.map_flags = bpf_map__map_flags(map); + create_attr.btf_fd = btf__fd(btf); + create_attr.btf_key_type_id = bpf_map__btf_key_type_id(map); + create_attr.btf_value_type_id = bpf_map__btf_value_type_id(map); + map_fd = bpf_map_create(bpf_map__type(map), map_name, + bpf_map__key_size(map), bpf_map__value_size(map), + 0, &create_attr); + if (ASSERT_ERR_FD(map_fd, "map_create")) + ASSERT_EQ(errno, expected_errno, "errno"); + else + close(map_fd); + +done: + uptr_map_failure__destroy(skel); +} + void test_task_local_storage(void) { if (test__start_subtest("sys_enter_exit")) @@ -237,4 +498,21 @@ void test_task_local_storage(void) test_recursion(); if (test__start_subtest("nodeadlock")) test_nodeadlock(); + if (test__start_subtest("uptr_basic")) + test_uptr_basic(); + if (test__start_subtest("uptr_across_pages")) + test_uptr_across_pages(); + if (test__start_subtest("uptr_update_failure")) + test_uptr_update_failure(); + if (test__start_subtest("uptr_map_failure_e2big")) { + if (getpagesize() == PAGE_SIZE) + test_uptr_map_failure("large_uptr_map", E2BIG); + else + test__skip(); + } + if (test__start_subtest("uptr_map_failure_size0")) + test_uptr_map_failure("empty_uptr_map", EINVAL); + if (test__start_subtest("uptr_map_failure_kstruct")) + test_uptr_map_failure("kstruct_uptr_map", EINVAL); + RUN_TESTS(uptr_failure); } diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c index 844f6fc8487b..2c39902b8a09 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -836,10 +836,10 @@ uprobe_consumer_test(struct uprobe_multi_consumers *skel, return 0; } -static void consumer_test(struct uprobe_multi_consumers *skel, - unsigned long before, unsigned long after) +static int consumer_test(struct uprobe_multi_consumers *skel, + unsigned long before, unsigned long after) { - int err, idx; + int err, idx, ret = -1; printf("consumer_test before %lu after %lu\n", before, after); @@ -869,32 +869,29 @@ static void consumer_test(struct uprobe_multi_consumers *skel, fmt = "prog 0/1: uprobe"; } else { /* - * uprobe return is tricky ;-) - * * to trigger uretprobe consumer, the uretprobe needs to be installed, * which means one of the 'return' uprobes was alive when probe was hit: * * idxs: 2/3 uprobe return in 'installed' mask - * - * in addition if 'after' state removes everything that was installed in - * 'before' state, then uprobe kernel object goes away and return uprobe - * is not installed and we won't hit it even if it's in 'after' state. */ unsigned long had_uretprobes = before & 0b1100; /* is uretprobe installed */ - unsigned long probe_preserved = before & after; /* did uprobe go away */ - if (had_uretprobes && probe_preserved && test_bit(idx, after)) + if (had_uretprobes && test_bit(idx, after)) val++; fmt = "idx 2/3: uretprobe"; } - ASSERT_EQ(skel->bss->uprobe_result[idx], val, fmt); + if (!ASSERT_EQ(skel->bss->uprobe_result[idx], val, fmt)) + goto cleanup; skel->bss->uprobe_result[idx] = 0; } + ret = 0; + cleanup: for (idx = 0; idx < 4; idx++) uprobe_detach(skel, idx); + return ret; } static void test_consumers(void) @@ -946,9 +943,11 @@ static void test_consumers(void) for (before = 0; before < 16; before++) { for (after = 0; after < 16; after++) - consumer_test(skel, before, after); + if (consumer_test(skel, before, after)) + goto out; } +out: uprobe_multi_consumers__destroy(skel); } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h index c41ee80533ca..3305dc3a74b3 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter.h +++ b/tools/testing/selftests/bpf/progs/bpf_iter.h @@ -24,6 +24,7 @@ #define BTF_F_PTR_RAW BTF_F_PTR_RAW___not_used #define BTF_F_ZERO BTF_F_ZERO___not_used #define bpf_iter__ksym bpf_iter__ksym___not_used +#define bpf_iter__kmem_cache bpf_iter__kmem_cache___not_used #include "vmlinux.h" #undef bpf_iter_meta #undef bpf_iter__bpf_map @@ -48,6 +49,7 @@ #undef BTF_F_PTR_RAW #undef BTF_F_ZERO #undef bpf_iter__ksym +#undef bpf_iter__kmem_cache struct bpf_iter_meta { struct seq_file *seq; @@ -165,3 +167,8 @@ struct bpf_iter__ksym { struct bpf_iter_meta *meta; struct kallsym_iter *ksym; }; + +struct bpf_iter__kmem_cache { + struct bpf_iter_meta *meta; + struct kmem_cache *s; +} __attribute__((preserve_access_index)); diff --git a/tools/testing/selftests/bpf/progs/kmem_cache_iter.c b/tools/testing/selftests/bpf/progs/kmem_cache_iter.c new file mode 100644 index 000000000000..72c9dafecd98 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kmem_cache_iter.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Google */ + +#include "bpf_iter.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +#define SLAB_NAME_MAX 32 + +struct kmem_cache_result { + char name[SLAB_NAME_MAX]; + long obj_size; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(void *)); + __uint(value_size, SLAB_NAME_MAX); + __uint(max_entries, 1); +} slab_hash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(struct kmem_cache_result)); + __uint(max_entries, 1024); +} slab_result SEC(".maps"); + +extern struct kmem_cache *bpf_get_kmem_cache(u64 addr) __ksym; + +/* Result, will be checked by userspace */ +int task_struct_found; +int kmem_cache_seen; + +SEC("iter/kmem_cache") +int slab_info_collector(struct bpf_iter__kmem_cache *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct kmem_cache *s = ctx->s; + struct kmem_cache_result *r; + int idx; + + if (s) { + /* To make sure if the slab_iter implements the seq interface + * properly and it's also useful for debugging. + */ + BPF_SEQ_PRINTF(seq, "%s: %u\n", s->name, s->size); + + idx = kmem_cache_seen; + r = bpf_map_lookup_elem(&slab_result, &idx); + if (r == NULL) + return 0; + + kmem_cache_seen++; + + /* Save name and size to match /proc/slabinfo */ + bpf_probe_read_kernel_str(r->name, sizeof(r->name), s->name); + r->obj_size = s->size; + + if (!bpf_strncmp(r->name, 11, "task_struct")) + bpf_map_update_elem(&slab_hash, &s, r->name, BPF_NOEXIST); + } + + return 0; +} + +SEC("raw_tp/bpf_test_finish") +int BPF_PROG(check_task_struct) +{ + u64 curr = bpf_get_current_task(); + struct kmem_cache *s; + char *name; + + s = bpf_get_kmem_cache(curr); + if (s == NULL) { + task_struct_found = -1; + return 0; + } + name = bpf_map_lookup_elem(&slab_hash, &s); + if (name && !bpf_strncmp(name, 11, "task_struct")) + task_struct_found = 1; + else + task_struct_found = -2; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/linked_funcs1.c b/tools/testing/selftests/bpf/progs/linked_funcs1.c index cc79dddac182..049a1f78de3f 100644 --- a/tools/testing/selftests/bpf/progs/linked_funcs1.c +++ b/tools/testing/selftests/bpf/progs/linked_funcs1.c @@ -63,6 +63,8 @@ extern int set_output_val2(int x); /* here we'll force set_output_ctx2() to be __hidden in the final obj file */ __hidden extern void set_output_ctx2(__u64 *ctx); +void *bpf_cast_to_kern_ctx(void *obj) __ksym; + SEC("?raw_tp/sys_enter") int BPF_PROG(handler1, struct pt_regs *regs, long id) { @@ -86,4 +88,10 @@ int BPF_PROG(handler1, struct pt_regs *regs, long id) return 0; } +/* Generate BTF FUNC record and test linking with duplicate extern functions */ +void kfunc_gen1(void) +{ + bpf_cast_to_kern_ctx(0); +} + char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/linked_funcs2.c b/tools/testing/selftests/bpf/progs/linked_funcs2.c index 942cc5526ddf..96850759fd8d 100644 --- a/tools/testing/selftests/bpf/progs/linked_funcs2.c +++ b/tools/testing/selftests/bpf/progs/linked_funcs2.c @@ -63,6 +63,8 @@ extern int set_output_val1(int x); /* here we'll force set_output_ctx1() to be __hidden in the final obj file */ __hidden extern void set_output_ctx1(__u64 *ctx); +void *bpf_cast_to_kern_ctx(void *obj) __ksym; + SEC("?raw_tp/sys_enter") int BPF_PROG(handler2, struct pt_regs *regs, long id) { @@ -86,4 +88,10 @@ int BPF_PROG(handler2, struct pt_regs *regs, long id) return 0; } +/* Generate BTF FUNC record and test linking with duplicate extern functions */ +void kfunc_gen2(void) +{ + bpf_cast_to_kern_ctx(0); +} + char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_detach.c b/tools/testing/selftests/bpf/progs/struct_ops_detach.c index 56b787a89876..d7fdcabe7d90 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_detach.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_detach.c @@ -6,5 +6,17 @@ char _license[] SEC("license") = "GPL"; +/* + * This subprogram validates that libbpf handles the situation in which BPF + * object has subprograms in .text section, but has no entry BPF programs. + * At some point that was causing issues due to legacy logic of treating such + * subprogram as entry program (with unknown program type, which would fail). + */ +int dangling_subprog(void) +{ + /* do nothing, just be here */ + return 0; +} + SEC(".struct_ops.link") struct bpf_testmod_ops testmod_do_detach; diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_common.h b/tools/testing/selftests/bpf/progs/task_kfunc_common.h index 6720c4b5be41..e9c4fea7a4bb 100644 --- a/tools/testing/selftests/bpf/progs/task_kfunc_common.h +++ b/tools/testing/selftests/bpf/progs/task_kfunc_common.h @@ -23,6 +23,7 @@ struct { struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; void bpf_task_release(struct task_struct *p) __ksym; struct task_struct *bpf_task_from_pid(s32 pid) __ksym; +struct task_struct *bpf_task_from_vpid(s32 vpid) __ksym; void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c index ad88a3796ddf..4c07ea193f72 100644 --- a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c +++ b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c @@ -247,6 +247,20 @@ int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 cl return 0; } +SEC("tp_btf/task_newtask") +__failure __msg("Possibly NULL pointer passed to trusted arg0") +int BPF_PROG(task_kfunc_from_vpid_no_null_check, struct task_struct *task, u64 clone_flags) +{ + struct task_struct *acquired; + + acquired = bpf_task_from_vpid(task->pid); + + /* Releasing bpf_task_from_vpid() lookup without a NULL check. */ + bpf_task_release(acquired); + + return 0; +} + SEC("lsm/task_free") __failure __msg("R1 must be a rcu pointer") int BPF_PROG(task_kfunc_from_lsm_task_free, struct task_struct *task) diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_success.c b/tools/testing/selftests/bpf/progs/task_kfunc_success.c index a55149015063..5fb4fc19d26a 100644 --- a/tools/testing/selftests/bpf/progs/task_kfunc_success.c +++ b/tools/testing/selftests/bpf/progs/task_kfunc_success.c @@ -366,3 +366,54 @@ int BPF_PROG(task_kfunc_acquire_trusted_walked, struct task_struct *task, u64 cl return 0; } + +SEC("syscall") +int test_task_from_vpid_current(const void *ctx) +{ + struct task_struct *current, *v_task; + + v_task = bpf_task_from_vpid(1); + if (!v_task) { + err = 1; + return 0; + } + + current = bpf_get_current_task_btf(); + + /* The current process should be the init process (pid 1) in the new pid namespace. */ + if (current != v_task) + err = 2; + + bpf_task_release(v_task); + return 0; +} + +SEC("syscall") +int test_task_from_vpid_invalid(const void *ctx) +{ + struct task_struct *v_task; + + v_task = bpf_task_from_vpid(-1); + if (v_task) { + err = 1; + goto err; + } + + /* There should be only one process (current process) in the new pid namespace. */ + v_task = bpf_task_from_vpid(2); + if (v_task) { + err = 2; + goto err; + } + + v_task = bpf_task_from_vpid(9999); + if (v_task) { + err = 3; + goto err; + } + + return 0; +err: + bpf_task_release(v_task); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/task_ls_uptr.c b/tools/testing/selftests/bpf/progs/task_ls_uptr.c new file mode 100644 index 000000000000..ddbe11b46eef --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_ls_uptr.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "uptr_test_common.h" + +struct task_struct *bpf_task_from_pid(s32 pid) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; +void bpf_cgroup_release(struct cgroup *cgrp) __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct value_type); +} datamap SEC(".maps"); + +pid_t target_pid = 0; +pid_t parent_pid = 0; + +SEC("tp_btf/sys_enter") +int on_enter(__u64 *ctx) +{ + struct task_struct *task, *data_task; + struct value_type *ptr; + struct user_data *udata; + struct cgroup *cgrp; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + data_task = bpf_task_from_pid(parent_pid); + if (!data_task) + return 0; + + ptr = bpf_task_storage_get(&datamap, data_task, 0, 0); + bpf_task_release(data_task); + if (!ptr) + return 0; + + cgrp = bpf_kptr_xchg(&ptr->cgrp, NULL); + if (cgrp) { + int lvl = cgrp->level; + + bpf_cgroup_release(cgrp); + return lvl; + } + + udata = ptr->udata; + if (!udata || udata->result) + return 0; + udata->result = MAGIC_VALUE + udata->a + udata->b; + + udata = ptr->nested.udata; + if (udata && !udata->nested_result) + udata->nested_result = udata->result; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c index 8a0632c37839..d1a57f7d09bd 100644 --- a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c @@ -5,10 +5,11 @@ #include "bpf_misc.h" __noinline -int subprog(struct __sk_buff *skb) +int subprog_tc(struct __sk_buff *skb) { int ret = 1; + __sink(skb); __sink(ret); return ret; } @@ -16,7 +17,7 @@ int subprog(struct __sk_buff *skb) SEC("tc") int entry_tc(struct __sk_buff *skb) { - return subprog(skb); + return subprog_tc(skb); } char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c index 92354cd72044..176a355e3062 100644 --- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c +++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c @@ -1,27 +1,50 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook -#include <linux/bpf.h> +#include <vmlinux.h> #include <linux/version.h> #include <bpf/bpf_helpers.h> -__u32 sig = 0, pid = 0, status = 0, signal_thread = 0; +struct task_struct *bpf_task_from_pid(int pid) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; +int bpf_send_signal_task(struct task_struct *task, int sig, enum pid_type type, u64 value) __ksym; + +__u32 sig = 0, pid = 0, status = 0, signal_thread = 0, target_pid = 0; static __always_inline int bpf_send_signal_test(void *ctx) { + struct task_struct *target_task = NULL; int ret; + u64 value; if (status != 0 || pid == 0) return 0; if ((bpf_get_current_pid_tgid() >> 32) == pid) { - if (signal_thread) - ret = bpf_send_signal_thread(sig); - else - ret = bpf_send_signal(sig); + if (target_pid) { + target_task = bpf_task_from_pid(target_pid); + if (!target_task) + return 0; + value = 8; + } + + if (signal_thread) { + if (target_pid) + ret = bpf_send_signal_task(target_task, sig, PIDTYPE_PID, value); + else + ret = bpf_send_signal_thread(sig); + } else { + if (target_pid) + ret = bpf_send_signal_task(target_task, sig, PIDTYPE_TGID, value); + else + ret = bpf_send_signal(sig); + } if (ret == 0) status = 1; } + if (target_task) + bpf_task_release(target_task); + return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c index 43f40c4fe241..1c8b678e2e9a 100644 --- a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c +++ b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c @@ -28,8 +28,8 @@ struct { }, }; -SEC(".data.A") struct bpf_spin_lock lockA; -SEC(".data.B") struct bpf_spin_lock lockB; +static struct bpf_spin_lock lockA SEC(".data.A"); +static struct bpf_spin_lock lockB SEC(".data.B"); SEC("?tc") int lock_id_kptr_preserve(void *ctx) diff --git a/tools/testing/selftests/bpf/progs/uptr_failure.c b/tools/testing/selftests/bpf/progs/uptr_failure.c new file mode 100644 index 000000000000..0cfa1fd61440 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/uptr_failure.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_experimental.h" +#include "bpf_misc.h" +#include "uptr_test_common.h" + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct value_type); +} datamap SEC(".maps"); + +SEC("?syscall") +__failure __msg("store to uptr disallowed") +int uptr_write(const void *ctx) +{ + struct task_struct *task; + struct value_type *v; + + task = bpf_get_current_task_btf(); + v = bpf_task_storage_get(&datamap, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!v) + return 0; + + v->udata = NULL; + return 0; +} + +SEC("?syscall") +__failure __msg("store to uptr disallowed") +int uptr_write_nested(const void *ctx) +{ + struct task_struct *task; + struct value_type *v; + + task = bpf_get_current_task_btf(); + v = bpf_task_storage_get(&datamap, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!v) + return 0; + + v->nested.udata = NULL; + return 0; +} + +SEC("?syscall") +__failure __msg("R1 invalid mem access 'mem_or_null'") +int uptr_no_null_check(const void *ctx) +{ + struct task_struct *task; + struct value_type *v; + + task = bpf_get_current_task_btf(); + v = bpf_task_storage_get(&datamap, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!v) + return 0; + + v->udata->result = 0; + + return 0; +} + +SEC("?syscall") +__failure __msg("doesn't point to kptr") +int uptr_kptr_xchg(const void *ctx) +{ + struct task_struct *task; + struct value_type *v; + + task = bpf_get_current_task_btf(); + v = bpf_task_storage_get(&datamap, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!v) + return 0; + + bpf_kptr_xchg(&v->udata, NULL); + + return 0; +} + +SEC("?syscall") +__failure __msg("invalid mem access 'scalar'") +int uptr_obj_new(const void *ctx) +{ + struct value_type *v; + + v = bpf_obj_new(typeof(*v)); + if (!v) + return 0; + + if (v->udata) + v->udata->result = 0; + + bpf_obj_drop(v); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/uptr_map_failure.c b/tools/testing/selftests/bpf/progs/uptr_map_failure.c new file mode 100644 index 000000000000..417b763d76b4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/uptr_map_failure.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "uptr_test_common.h" + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct large_uptr); +} large_uptr_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct empty_uptr); +} empty_uptr_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct kstruct_uptr); +} kstruct_uptr_map SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/uptr_update_failure.c b/tools/testing/selftests/bpf/progs/uptr_update_failure.c new file mode 100644 index 000000000000..86c3bb954abc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/uptr_update_failure.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "uptr_test_common.h" + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct value_lock_type); +} datamap SEC(".maps"); + +/* load test only. not used */ +SEC("syscall") +int not_used(void *ctx) +{ + struct value_lock_type *ptr; + struct task_struct *task; + struct user_data *udata; + + task = bpf_get_current_task_btf(); + ptr = bpf_task_storage_get(&datamap, task, 0, 0); + if (!ptr) + return 0; + + bpf_spin_lock(&ptr->lock); + + udata = ptr->udata; + if (!udata) { + bpf_spin_unlock(&ptr->lock); + return 0; + } + udata->result = MAGIC_VALUE + udata->a + udata->b; + + bpf_spin_unlock(&ptr->lock); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c index ee76b51005ab..d3e70e38e442 100644 --- a/tools/testing/selftests/bpf/progs/verifier_sock.c +++ b/tools/testing/selftests/bpf/progs/verifier_sock.c @@ -977,4 +977,64 @@ l1_%=: r0 = *(u8*)(r7 + 0); \ : __clobber_all); } +SEC("cgroup/post_bind4") +__description("sk->src_ip6[0] [load 1st byte]") +__failure __msg("invalid bpf_context access off=28 size=2") +__naked void post_bind4_read_src_ip6(void) +{ + asm volatile (" \ + r6 = r1; \ + r7 = *(u16*)(r6 + %[bpf_sock_src_ip6_0]); \ + r0 = 1; \ + exit; \ +" : + : __imm_const(bpf_sock_src_ip6_0, offsetof(struct bpf_sock, src_ip6[0])) + : __clobber_all); +} + +SEC("cgroup/post_bind4") +__description("sk->mark [load mark]") +__failure __msg("invalid bpf_context access off=16 size=2") +__naked void post_bind4_read_mark(void) +{ + asm volatile (" \ + r6 = r1; \ + r7 = *(u16*)(r6 + %[bpf_sock_mark]); \ + r0 = 1; \ + exit; \ +" : + : __imm_const(bpf_sock_mark, offsetof(struct bpf_sock, mark)) + : __clobber_all); +} + +SEC("cgroup/post_bind6") +__description("sk->src_ip4 [load src_ip4]") +__failure __msg("invalid bpf_context access off=24 size=2") +__naked void post_bind6_read_src_ip4(void) +{ + asm volatile (" \ + r6 = r1; \ + r7 = *(u16*)(r6 + %[bpf_sock_src_ip4]); \ + r0 = 1; \ + exit; \ +" : + : __imm_const(bpf_sock_src_ip4, offsetof(struct bpf_sock, src_ip4)) + : __clobber_all); +} + +SEC("cgroup/sock_create") +__description("sk->src_port [word load]") +__failure __msg("invalid bpf_context access off=44 size=2") +__naked void sock_create_read_src_port(void) +{ + asm volatile (" \ + r6 = r1; \ + r7 = *(u16*)(r6 + %[bpf_sock_src_port]); \ + r0 = 1; \ + exit; \ +" : + : __imm_const(bpf_sock_src_port, offsetof(struct bpf_sock, src_port)) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index c7a70e1a1085..7421874380c2 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -20,11 +20,13 @@ #include "network_helpers.h" +/* backtrace() and backtrace_symbols_fd() are glibc specific, + * use header file when glibc is available and provide stub + * implementations when another libc implementation is used. + */ #ifdef __GLIBC__ #include <execinfo.h> /* backtrace */ -#endif - -/* Default backtrace funcs if missing at link */ +#else __weak int backtrace(void **buffer, int size) { return 0; @@ -34,6 +36,7 @@ __weak void backtrace_symbols_fd(void *const *buffer, int size, int fd) { dprintf(fd, "<backtrace not supported>\n"); } +#endif /*__GLIBC__ */ int env_verbosity = 0; @@ -868,6 +871,7 @@ static int libbpf_print_fn(enum libbpf_print_level level, va_copy(args2, args); vfprintf(libbpf_capture_stream, format, args2); + va_end(args2); } if (env.verbosity < VERBOSE_VERY && level == LIBBPF_DEBUG) diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 7767d9a825ae..7a58895867c3 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -390,6 +390,14 @@ int test__join_cgroup(const char *path); ___ok; \ }) +#define ASSERT_ERR_FD(fd, name) ({ \ + static int duration = 0; \ + int ___fd = (fd); \ + bool ___ok = ___fd < 0; \ + CHECK(!___ok, (name), "unexpected fd: %d\n", ___fd); \ + ___ok; \ +}) + #define SYS(goto_label, fmt, ...) \ ({ \ char cmd[1024]; \ diff --git a/tools/testing/selftests/bpf/uprobe_multi.c b/tools/testing/selftests/bpf/uprobe_multi.c index c7828b13e5ff..dd38dc68f635 100644 --- a/tools/testing/selftests/bpf/uprobe_multi.c +++ b/tools/testing/selftests/bpf/uprobe_multi.c @@ -12,6 +12,10 @@ #define MADV_POPULATE_READ 22 #endif +#ifndef MADV_PAGEOUT +#define MADV_PAGEOUT 21 +#endif + int __attribute__((weak)) uprobe(void) { return 0; diff --git a/tools/testing/selftests/bpf/uptr_test_common.h b/tools/testing/selftests/bpf/uptr_test_common.h new file mode 100644 index 000000000000..f8a134ba12f9 --- /dev/null +++ b/tools/testing/selftests/bpf/uptr_test_common.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ + +#ifndef _UPTR_TEST_COMMON_H +#define _UPTR_TEST_COMMON_H + +#define MAGIC_VALUE 0xabcd1234 +#define PAGE_SIZE 4096 + +#ifdef __BPF__ +/* Avoid fwd btf type being generated for the following struct */ +struct large_data *dummy_large_data; +struct empty_data *dummy_empty_data; +struct user_data *dummy_data; +struct cgroup *dummy_cgrp; +#else +#define __uptr +#define __kptr +#endif + +struct user_data { + int a; + int b; + int result; + int nested_result; +}; + +struct nested_udata { + struct user_data __uptr *udata; +}; + +struct value_type { + struct user_data __uptr *udata; + struct cgroup __kptr *cgrp; + struct nested_udata nested; +}; + +struct value_lock_type { + struct user_data __uptr *udata; + struct bpf_spin_lock lock; +}; + +struct large_data { + __u8 one_page[PAGE_SIZE]; + int a; +}; + +struct large_uptr { + struct large_data __uptr *udata; +}; + +struct empty_data { +}; + +struct empty_uptr { + struct empty_data __uptr *udata; +}; + +struct kstruct_uptr { + struct cgroup __uptr *cgrp; +}; + +#endif diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 1ec5c4c47235..e12ef953fba8 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -16,6 +16,7 @@ #include <sys/stat.h> #include <bpf/libbpf.h> #include <bpf/btf.h> +#include <bpf/bpf.h> #include <libelf.h> #include <gelf.h> #include <float.h> @@ -179,6 +180,7 @@ static struct env { int files_skipped; int progs_processed; int progs_skipped; + int top_src_lines; } env; static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) @@ -228,6 +230,7 @@ static const struct argp_option opts[] = { "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" }, { "test-reg-invariants", 'r', NULL, 0, "Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" }, + { "top-src-lines", 'S', "N", 0, "Emit N most frequent source code lines" }, {}, }; @@ -327,6 +330,14 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) return err; } break; + case 'S': + errno = 0; + env.top_src_lines = strtol(arg, NULL, 10); + if (errno) { + fprintf(stderr, "invalid top lines N specifier: %s\n", arg); + argp_usage(state); + } + break; case ARGP_KEY_ARG: tmp = realloc(env.filenames, (env.filename_cnt + 1) * sizeof(*env.filenames)); if (!tmp) @@ -854,6 +865,118 @@ static int parse_verif_log(char * const buf, size_t buf_sz, struct verif_stats * return 0; } +struct line_cnt { + char *line; + int cnt; +}; + +static int str_cmp(const void *a, const void *b) +{ + const char **str1 = (const char **)a; + const char **str2 = (const char **)b; + + return strcmp(*str1, *str2); +} + +static int line_cnt_cmp(const void *a, const void *b) +{ + const struct line_cnt *a_cnt = (const struct line_cnt *)a; + const struct line_cnt *b_cnt = (const struct line_cnt *)b; + + if (a_cnt->cnt != b_cnt->cnt) + return a_cnt->cnt < b_cnt->cnt ? -1 : 1; + return strcmp(a_cnt->line, b_cnt->line); +} + +static int print_top_src_lines(char * const buf, size_t buf_sz, const char *prog_name) +{ + int lines_cap = 0; + int lines_size = 0; + char **lines = NULL; + char *line = NULL; + char *state; + struct line_cnt *freq = NULL; + struct line_cnt *cur; + int unique_lines; + int err = 0; + int i; + + while ((line = strtok_r(line ? NULL : buf, "\n", &state))) { + if (strncmp(line, "; ", 2) != 0) + continue; + line += 2; + + if (lines_size == lines_cap) { + char **tmp; + + lines_cap = max(16, lines_cap * 2); + tmp = realloc(lines, lines_cap * sizeof(*tmp)); + if (!tmp) { + err = -ENOMEM; + goto cleanup; + } + lines = tmp; + } + lines[lines_size] = line; + lines_size++; + } + + if (lines_size == 0) + goto cleanup; + + qsort(lines, lines_size, sizeof(*lines), str_cmp); + + freq = calloc(lines_size, sizeof(*freq)); + if (!freq) { + err = -ENOMEM; + goto cleanup; + } + + cur = freq; + cur->line = lines[0]; + cur->cnt = 1; + for (i = 1; i < lines_size; ++i) { + if (strcmp(lines[i], cur->line) != 0) { + cur++; + cur->line = lines[i]; + cur->cnt = 0; + } + cur->cnt++; + } + unique_lines = cur - freq + 1; + + qsort(freq, unique_lines, sizeof(struct line_cnt), line_cnt_cmp); + + printf("Top source lines (%s):\n", prog_name); + for (i = 0; i < min(unique_lines, env.top_src_lines); ++i) { + const char *src_code = freq[i].line; + const char *src_line = NULL; + char *split = strrchr(freq[i].line, '@'); + + if (split) { + src_line = split + 1; + + while (*src_line && isspace(*src_line)) + src_line++; + + while (split > src_code && isspace(*split)) + split--; + *split = '\0'; + } + + if (src_line) + printf("%5d: (%s)\t%s\n", freq[i].cnt, src_line, src_code); + else + printf("%5d: %s\n", freq[i].cnt, src_code); + } + printf("\n"); + +cleanup: + free(freq); + free(lines); + return err; +} + static int guess_prog_type_by_ctx_name(const char *ctx_name, enum bpf_prog_type *prog_type, enum bpf_attach_type *attach_type) @@ -987,6 +1110,35 @@ skip_freplace_fixup: return; } +static int max_verifier_log_size(void) +{ + const int SMALL_LOG_SIZE = UINT_MAX >> 8; + const int BIG_LOG_SIZE = UINT_MAX >> 2; + struct bpf_insn insns[] = { + { .code = BPF_ALU | BPF_MOV | BPF_X, .dst_reg = BPF_REG_0, }, + { .code = BPF_JMP | BPF_EXIT, }, + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_size = BIG_LOG_SIZE, + .log_buf = (void *)-1, + .log_level = 4 + ); + int ret, insn_cnt = ARRAY_SIZE(insns); + static int log_size; + + if (log_size != 0) + return log_size; + + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); + + if (ret == -EFAULT) + log_size = BIG_LOG_SIZE; + else /* ret == -EINVAL, big log size is not supported by the verifier */ + log_size = SMALL_LOG_SIZE; + + return log_size; +} + static int process_prog(const char *filename, struct bpf_object *obj, struct bpf_program *prog) { const char *base_filename = basename(strdupa(filename)); @@ -1009,13 +1161,16 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf stats = &env.prog_stats[env.prog_stat_cnt++]; memset(stats, 0, sizeof(*stats)); - if (env.verbose) { - buf_sz = env.log_size ? env.log_size : 16 * 1024 * 1024; + if (env.verbose || env.top_src_lines > 0) { + buf_sz = env.log_size ? env.log_size : max_verifier_log_size(); buf = malloc(buf_sz); if (!buf) return -ENOMEM; /* ensure we always request stats */ log_level = env.log_level | 4 | (env.log_fixed ? 8 : 0); + /* --top-src-lines needs verifier log */ + if (env.top_src_lines > 0 && env.log_level == 0) + log_level |= 2; } else { buf = verif_log_buf; buf_sz = sizeof(verif_log_buf); @@ -1048,6 +1203,8 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf filename, prog_name, stats->stats[DURATION], err ? "failure" : "success", buf); } + if (env.top_src_lines > 0) + print_top_src_lines(buf, buf_sz, stats->prog_name); if (verif_log_buf != buf) free(buf); |