diff options
Diffstat (limited to 'kernel/bpf/syscall.c')
| -rw-r--r-- | kernel/bpf/syscall.c | 1346 |
1 files changed, 1075 insertions, 271 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a91ad518c050..1bf960aa615c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -25,6 +25,10 @@ #include <linux/nospec.h> #include <linux/audit.h> #include <uapi/linux/btf.h> +#include <linux/pgtable.h> +#include <linux/bpf_lsm.h> +#include <linux/poll.h> +#include <linux/bpf-netns.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ @@ -41,6 +45,8 @@ static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); static DEFINE_IDR(map_idr); static DEFINE_SPINLOCK(map_idr_lock); +static DEFINE_IDR(link_idr); +static DEFINE_SPINLOCK(link_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly; @@ -48,9 +54,11 @@ static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) \ [_id] = &_ops, +#define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE }; /* @@ -66,32 +74,19 @@ int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size, size_t actual_size) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - int err; + unsigned char __user *addr = uaddr + expected_size; + int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; - if (unlikely(!access_ok(uaddr, actual_size))) - return -EFAULT; - if (actual_size <= expected_size) return 0; - addr = uaddr + expected_size; - end = uaddr + actual_size; - - for (; addr < end; addr++) { - err = get_user(val, addr); - if (err) - return err; - if (val) - return -E2BIG; - } - - return 0; + res = check_zeroed_user(addr, actual_size - expected_size); + if (res < 0) + return res; + return res ? 0 : -E2BIG; } const struct bpf_map_ops bpf_map_offload_ops = { @@ -171,11 +166,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, flags); } - /* must increment bpf_prog_active to avoid kprobe+bpf triggering from - * inside bpf map update or delete otherwise deadlocks are possible - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, flags); @@ -206,8 +197,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, err = map->ops->map_update_elem(map, key, value, flags); rcu_read_unlock(); } - __this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); return err; @@ -222,8 +212,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, if (bpf_map_is_dev_bound(map)) return bpf_map_offload_lookup_elem(map, key, value); - preempt_disable(); - this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); @@ -268,8 +257,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, rcu_read_unlock(); } - this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); return err; @@ -287,27 +275,29 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) * __GFP_RETRY_MAYFAIL to avoid such situations. */ - const gfp_t flags = __GFP_NOWARN | __GFP_ZERO; + const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO; + unsigned int flags = 0; + unsigned long align = 1; void *area; if (size >= SIZE_MAX) return NULL; /* kmalloc()'ed memory can't be mmap()'ed */ - if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags, + if (mmapable) { + BUG_ON(!PAGE_ALIGNED(size)); + align = SHMLBA; + flags = VM_USERMAP; + } else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { + area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY, numa_node); if (area != NULL) return area; } - if (mmapable) { - BUG_ON(!PAGE_ALIGNED(size)); - return vmalloc_user_node_flags(size, numa_node, GFP_KERNEL | - __GFP_RETRY_MAYFAIL | flags); - } - return __vmalloc_node_flags_caller(size, numa_node, - GFP_KERNEL | __GFP_RETRY_MAYFAIL | - flags, __builtin_return_address(0)); + + return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, + gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL, + flags, numa_node, __builtin_return_address(0)); } void *bpf_map_area_alloc(u64 size, int numa_node) @@ -592,9 +582,7 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - bpf_map_inc_with_uref(map); - - if (vma->vm_flags & VM_WRITE) { + if (vma->vm_flags & VM_MAYWRITE) { mutex_lock(&map->freeze_mutex); map->writecnt++; mutex_unlock(&map->freeze_mutex); @@ -606,13 +594,11 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_WRITE) { + if (vma->vm_flags & VM_MAYWRITE) { mutex_lock(&map->freeze_mutex); map->writecnt--; mutex_unlock(&map->freeze_mutex); } - - bpf_map_put_with_uref(map); } static const struct vm_operations_struct bpf_map_default_vmops = { @@ -633,28 +619,51 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) mutex_lock(&map->freeze_mutex); - if ((vma->vm_flags & VM_WRITE) && map->frozen) { - err = -EPERM; - goto out; + if (vma->vm_flags & VM_WRITE) { + if (map->frozen) { + err = -EPERM; + goto out; + } + /* map is meant to be read-only, so do not allow mapping as + * writable, because it's possible to leak a writable page + * reference and allows user-space to still modify it after + * freezing, while verifier will assume contents do not change + */ + if (map->map_flags & BPF_F_RDONLY_PROG) { + err = -EACCES; + goto out; + } } /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; + vma->vm_flags &= ~VM_MAYEXEC; + if (!(vma->vm_flags & VM_WRITE)) + /* disallow re-mapping with PROT_WRITE */ + vma->vm_flags &= ~VM_MAYWRITE; err = map->ops->map_mmap(map, vma); if (err) goto out; - bpf_map_inc_with_uref(map); - - if (vma->vm_flags & VM_WRITE) + if (vma->vm_flags & VM_MAYWRITE) map->writecnt++; out: mutex_unlock(&map->freeze_mutex); return err; } +static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts) +{ + struct bpf_map *map = filp->private_data; + + if (map->ops->map_poll) + return map->ops->map_poll(map, filp, pts); + + return EPOLLERR; +} + const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, @@ -663,6 +672,7 @@ const struct file_operations bpf_map_fops = { .read = bpf_dummy_read, .write = bpf_dummy_write, .mmap = bpf_map_mmap, + .poll = bpf_map_poll, }; int bpf_map_new_fd(struct bpf_map *map, int flags) @@ -696,14 +706,15 @@ int bpf_get_file_flag(int flags) offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL -/* dst and src must have at least BPF_OBJ_NAME_LEN number of bytes. - * Return 0 on success and < 0 on error. +/* dst and src must have at least "size" number of bytes. + * Return strlen on success and < 0 on error. */ -static int bpf_obj_name_cpy(char *dst, const char *src) +int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size) { - const char *end = src + BPF_OBJ_NAME_LEN; + const char *end = src + size; + const char *orig_src = src; - memset(dst, 0, BPF_OBJ_NAME_LEN); + memset(dst, 0, size); /* Copy all isalnum(), '_' and '.' chars. */ while (src < end && *src) { if (!isalnum(*src) && @@ -712,11 +723,11 @@ static int bpf_obj_name_cpy(char *dst, const char *src) *dst++ = *src++; } - /* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */ + /* No '\0' found in "size" number of bytes */ if (src == end) return -EINVAL; - return 0; + return src - orig_src; } int map_check_no_btf(const struct bpf_map *map, @@ -810,8 +821,9 @@ static int map_create(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - err = bpf_obj_name_cpy(map->name, attr->map_name); - if (err) + err = bpf_obj_name_cpy(map->name, attr->map_name, + sizeof(attr->map_name)); + if (err < 0) goto free_map; atomic64_set(&map->refcnt, 1); @@ -909,6 +921,21 @@ void bpf_map_inc_with_uref(struct bpf_map *map) } EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); +struct bpf_map *bpf_map_get(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_map *map; + + map = __bpf_map_get(f); + if (IS_ERR(map)) + return map; + + bpf_map_inc(map); + fdput(f); + + return map; +} + struct bpf_map *bpf_map_get_with_uref(u32 ufd) { struct fd f = fdget(ufd); @@ -1136,13 +1163,11 @@ static int map_delete_elem(union bpf_attr *attr) goto out; } - preempt_disable(); - __this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); out: kfree(key); @@ -1254,13 +1279,11 @@ int generic_map_delete_batch(struct bpf_map *map, break; } - preempt_disable(); - __this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); if (err) break; @@ -1367,7 +1390,7 @@ int generic_map_lookup_batch(struct bpf_map *map, buf = kmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); if (!buf) { - kvfree(buf_prevkey); + kfree(buf_prevkey); return -ENOMEM; } @@ -1452,7 +1475,8 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || + !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -1480,8 +1504,10 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) if (err) goto free_value; - if (copy_to_user(uvalue, value, value_size) != 0) + if (copy_to_user(uvalue, value, value_size) != 0) { + err = -EFAULT; goto free_value; + } err = 0; @@ -1510,6 +1536,11 @@ static int map_freeze(const union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + fdput(f); + return -ENOTSUPP; + } + mutex_lock(&map->freeze_mutex); if (map->writecnt) { @@ -1520,7 +1551,7 @@ static int map_freeze(const union bpf_attr *attr) err = -EBUSY; goto err_put; } - if (!capable(CAP_SYS_ADMIN)) { + if (!bpf_capable()) { err = -EPERM; goto err_put; } @@ -1536,9 +1567,11 @@ static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _prog_ops, #define BPF_MAP_TYPE(_id, _ops) +#define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE }; static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) @@ -1931,6 +1964,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, switch (prog_type) { case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: break; @@ -1947,6 +1981,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_CGROUP_SOCK: switch (expected_attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return 0; @@ -1959,6 +1994,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: @@ -1983,15 +2022,68 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, default: return -EINVAL; } + case BPF_PROG_TYPE_SK_LOOKUP: + if (expected_attach_type == BPF_SK_LOOKUP) + return 0; + return -EINVAL; case BPF_PROG_TYPE_EXT: if (expected_attach_type) return -EINVAL; - /* fallthrough */ + fallthrough; default: return 0; } } +static bool is_net_admin_prog_type(enum bpf_prog_type prog_type) +{ + switch (prog_type) { + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: + case BPF_PROG_TYPE_XDP: + case BPF_PROG_TYPE_LWT_IN: + case BPF_PROG_TYPE_LWT_OUT: + case BPF_PROG_TYPE_LWT_XMIT: + case BPF_PROG_TYPE_LWT_SEG6LOCAL: + case BPF_PROG_TYPE_SK_SKB: + case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_LIRC_MODE2: + case BPF_PROG_TYPE_FLOW_DISSECTOR: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_EXT: /* extends any prog */ + return true; + case BPF_PROG_TYPE_CGROUP_SKB: + /* always unpriv */ + case BPF_PROG_TYPE_SK_REUSEPORT: + /* equivalent to SOCKET_FILTER. need CAP_BPF only */ + default: + return false; + } +} + +static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) +{ + switch (prog_type) { + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_STRUCT_OPS: /* has access to struct sock */ + case BPF_PROG_TYPE_EXT: /* extends any prog */ + return true; + default: + return false; + } +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD attach_prog_fd @@ -2014,7 +2106,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && - !capable(CAP_SYS_ADMIN)) + !bpf_capable()) return -EPERM; /* copy eBPF program license from user space */ @@ -2027,11 +2119,16 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) is_gpl = license_is_gpl_compatible(license); if (attr->insn_cnt == 0 || - attr->insn_cnt > (capable(CAP_SYS_ADMIN) ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) + attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) return -E2BIG; if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && - !capable(CAP_SYS_ADMIN)) + !bpf_capable()) + return -EPERM; + + if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN)) + return -EPERM; + if (is_perfmon_prog_type(type) && !perfmon_capable()) return -EPERM; bpf_prog_load_fixup_attach_type(attr); @@ -2093,8 +2190,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) goto free_prog; prog->aux->load_time = ktime_get_boottime_ns(); - err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name); - if (err) + err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, + sizeof(attr->prog_name)); + if (err < 0) goto free_prog; /* run eBPF verifier */ @@ -2169,84 +2267,415 @@ static int bpf_obj_get(const union bpf_attr *attr) attr->file_flags); } -static int bpf_tracing_prog_release(struct inode *inode, struct file *filp) +void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, + const struct bpf_link_ops *ops, struct bpf_prog *prog) { - struct bpf_prog *prog = filp->private_data; + atomic64_set(&link->refcnt, 1); + link->type = type; + link->id = 0; + link->ops = ops; + link->prog = prog; +} - WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog)); - bpf_prog_put(prog); +static void bpf_link_free_id(int id) +{ + if (!id) + return; + + spin_lock_bh(&link_idr_lock); + idr_remove(&link_idr, id); + spin_unlock_bh(&link_idr_lock); +} + +/* Clean up bpf_link and corresponding anon_inode file and FD. After + * anon_inode is created, bpf_link can't be just kfree()'d due to deferred + * anon_inode's release() call. This helper marksbpf_link as + * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt + * is not decremented, it's the responsibility of a calling code that failed + * to complete bpf_link initialization. + */ +void bpf_link_cleanup(struct bpf_link_primer *primer) +{ + primer->link->prog = NULL; + bpf_link_free_id(primer->id); + fput(primer->file); + put_unused_fd(primer->fd); +} + +void bpf_link_inc(struct bpf_link *link) +{ + atomic64_inc(&link->refcnt); +} + +/* bpf_link_free is guaranteed to be called from process context */ +static void bpf_link_free(struct bpf_link *link) +{ + bpf_link_free_id(link->id); + if (link->prog) { + /* detach BPF program, clean up used resources */ + link->ops->release(link); + bpf_prog_put(link->prog); + } + /* free bpf_link and its containing memory */ + link->ops->dealloc(link); +} + +static void bpf_link_put_deferred(struct work_struct *work) +{ + struct bpf_link *link = container_of(work, struct bpf_link, work); + + bpf_link_free(link); +} + +/* bpf_link_put can be called from atomic context, but ensures that resources + * are freed from process context + */ +void bpf_link_put(struct bpf_link *link) +{ + if (!atomic64_dec_and_test(&link->refcnt)) + return; + + if (in_atomic()) { + INIT_WORK(&link->work, bpf_link_put_deferred); + schedule_work(&link->work); + } else { + bpf_link_free(link); + } +} + +static int bpf_link_release(struct inode *inode, struct file *filp) +{ + struct bpf_link *link = filp->private_data; + + bpf_link_put(link); return 0; } -static const struct file_operations bpf_tracing_prog_fops = { - .release = bpf_tracing_prog_release, +#ifdef CONFIG_PROC_FS +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) +#define BPF_MAP_TYPE(_id, _ops) +#define BPF_LINK_TYPE(_id, _name) [_id] = #_name, +static const char *bpf_link_type_strs[] = { + [BPF_LINK_TYPE_UNSPEC] = "<invalid>", +#include <linux/bpf_types.h> +}; +#undef BPF_PROG_TYPE +#undef BPF_MAP_TYPE +#undef BPF_LINK_TYPE + +static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) +{ + const struct bpf_link *link = filp->private_data; + const struct bpf_prog *prog = link->prog; + char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; + + bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); + seq_printf(m, + "link_type:\t%s\n" + "link_id:\t%u\n" + "prog_tag:\t%s\n" + "prog_id:\t%u\n", + bpf_link_type_strs[link->type], + link->id, + prog_tag, + prog->aux->id); + if (link->ops->show_fdinfo) + link->ops->show_fdinfo(link, m); +} +#endif + +static const struct file_operations bpf_link_fops = { +#ifdef CONFIG_PROC_FS + .show_fdinfo = bpf_link_show_fdinfo, +#endif + .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; +static int bpf_link_alloc_id(struct bpf_link *link) +{ + int id; + + idr_preload(GFP_KERNEL); + spin_lock_bh(&link_idr_lock); + id = idr_alloc_cyclic(&link_idr, link, 1, INT_MAX, GFP_ATOMIC); + spin_unlock_bh(&link_idr_lock); + idr_preload_end(); + + return id; +} + +/* Prepare bpf_link to be exposed to user-space by allocating anon_inode file, + * reserving unused FD and allocating ID from link_idr. This is to be paired + * with bpf_link_settle() to install FD and ID and expose bpf_link to + * user-space, if bpf_link is successfully attached. If not, bpf_link and + * pre-allocated resources are to be freed with bpf_cleanup() call. All the + * transient state is passed around in struct bpf_link_primer. + * This is preferred way to create and initialize bpf_link, especially when + * there are complicated and expensive operations inbetween creating bpf_link + * itself and attaching it to BPF hook. By using bpf_link_prime() and + * bpf_link_settle() kernel code using bpf_link doesn't have to perform + * expensive (and potentially failing) roll back operations in a rare case + * that file, FD, or ID can't be allocated. + */ +int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) +{ + struct file *file; + int fd, id; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return fd; + + + id = bpf_link_alloc_id(link); + if (id < 0) { + put_unused_fd(fd); + return id; + } + + file = anon_inode_getfile("bpf_link", &bpf_link_fops, link, O_CLOEXEC); + if (IS_ERR(file)) { + bpf_link_free_id(id); + put_unused_fd(fd); + return PTR_ERR(file); + } + + primer->link = link; + primer->file = file; + primer->fd = fd; + primer->id = id; + return 0; +} + +int bpf_link_settle(struct bpf_link_primer *primer) +{ + /* make bpf_link fetchable by ID */ + spin_lock_bh(&link_idr_lock); + primer->link->id = primer->id; + spin_unlock_bh(&link_idr_lock); + /* make bpf_link fetchable by FD */ + fd_install(primer->fd, primer->file); + /* pass through installed FD */ + return primer->fd; +} + +int bpf_link_new_fd(struct bpf_link *link) +{ + return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC); +} + +struct bpf_link *bpf_link_get_from_fd(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_link *link; + + if (!f.file) + return ERR_PTR(-EBADF); + if (f.file->f_op != &bpf_link_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + link = f.file->private_data; + bpf_link_inc(link); + fdput(f); + + return link; +} + +struct bpf_tracing_link { + struct bpf_link link; + enum bpf_attach_type attach_type; +}; + +static void bpf_tracing_link_release(struct bpf_link *link) +{ + WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog)); +} + +static void bpf_tracing_link_dealloc(struct bpf_link *link) +{ + struct bpf_tracing_link *tr_link = + container_of(link, struct bpf_tracing_link, link); + + kfree(tr_link); +} + +static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_tracing_link *tr_link = + container_of(link, struct bpf_tracing_link, link); + + seq_printf(seq, + "attach_type:\t%d\n", + tr_link->attach_type); +} + +static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_tracing_link *tr_link = + container_of(link, struct bpf_tracing_link, link); + + info->tracing.attach_type = tr_link->attach_type; + + return 0; +} + +static const struct bpf_link_ops bpf_tracing_link_lops = { + .release = bpf_tracing_link_release, + .dealloc = bpf_tracing_link_dealloc, + .show_fdinfo = bpf_tracing_link_show_fdinfo, + .fill_link_info = bpf_tracing_link_fill_link_info, +}; + static int bpf_tracing_prog_attach(struct bpf_prog *prog) { - int tr_fd, err; + struct bpf_link_primer link_primer; + struct bpf_tracing_link *link; + int err; - if (prog->expected_attach_type != BPF_TRACE_FENTRY && - prog->expected_attach_type != BPF_TRACE_FEXIT && - prog->type != BPF_PROG_TYPE_EXT) { + switch (prog->type) { + case BPF_PROG_TYPE_TRACING: + if (prog->expected_attach_type != BPF_TRACE_FENTRY && + prog->expected_attach_type != BPF_TRACE_FEXIT && + prog->expected_attach_type != BPF_MODIFY_RETURN) { + err = -EINVAL; + goto out_put_prog; + } + break; + case BPF_PROG_TYPE_EXT: + if (prog->expected_attach_type != 0) { + err = -EINVAL; + goto out_put_prog; + } + break; + case BPF_PROG_TYPE_LSM: + if (prog->expected_attach_type != BPF_LSM_MAC) { + err = -EINVAL; + goto out_put_prog; + } + break; + default: err = -EINVAL; goto out_put_prog; } - err = bpf_trampoline_link_prog(prog); - if (err) + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; goto out_put_prog; + } + bpf_link_init(&link->link, BPF_LINK_TYPE_TRACING, + &bpf_tracing_link_lops, prog); + link->attach_type = prog->expected_attach_type; - tr_fd = anon_inode_getfd("bpf-tracing-prog", &bpf_tracing_prog_fops, - prog, O_CLOEXEC); - if (tr_fd < 0) { - WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog)); - err = tr_fd; + err = bpf_link_prime(&link->link, &link_primer); + if (err) { + kfree(link); + goto out_put_prog; + } + + err = bpf_trampoline_link_prog(prog); + if (err) { + bpf_link_cleanup(&link_primer); goto out_put_prog; } - return tr_fd; + return bpf_link_settle(&link_primer); out_put_prog: bpf_prog_put(prog); return err; } -struct bpf_raw_tracepoint { +struct bpf_raw_tp_link { + struct bpf_link link; struct bpf_raw_event_map *btp; - struct bpf_prog *prog; }; -static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp) +static void bpf_raw_tp_link_release(struct bpf_link *link) { - struct bpf_raw_tracepoint *raw_tp = filp->private_data; + struct bpf_raw_tp_link *raw_tp = + container_of(link, struct bpf_raw_tp_link, link); - if (raw_tp->prog) { - bpf_probe_unregister(raw_tp->btp, raw_tp->prog); - bpf_prog_put(raw_tp->prog); - } + bpf_probe_unregister(raw_tp->btp, raw_tp->link.prog); bpf_put_raw_tracepoint(raw_tp->btp); +} + +static void bpf_raw_tp_link_dealloc(struct bpf_link *link) +{ + struct bpf_raw_tp_link *raw_tp = + container_of(link, struct bpf_raw_tp_link, link); + kfree(raw_tp); +} + +static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_raw_tp_link *raw_tp_link = + container_of(link, struct bpf_raw_tp_link, link); + + seq_printf(seq, + "tp_name:\t%s\n", + raw_tp_link->btp->tp->name); +} + +static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_raw_tp_link *raw_tp_link = + container_of(link, struct bpf_raw_tp_link, link); + char __user *ubuf = u64_to_user_ptr(info->raw_tracepoint.tp_name); + const char *tp_name = raw_tp_link->btp->tp->name; + u32 ulen = info->raw_tracepoint.tp_name_len; + size_t tp_len = strlen(tp_name); + + if (ulen && !ubuf) + return -EINVAL; + + info->raw_tracepoint.tp_name_len = tp_len + 1; + + if (!ubuf) + return 0; + + if (ulen >= tp_len + 1) { + if (copy_to_user(ubuf, tp_name, tp_len + 1)) + return -EFAULT; + } else { + char zero = '\0'; + + if (copy_to_user(ubuf, tp_name, ulen - 1)) + return -EFAULT; + if (put_user(zero, ubuf + ulen - 1)) + return -EFAULT; + return -ENOSPC; + } + return 0; } -static const struct file_operations bpf_raw_tp_fops = { - .release = bpf_raw_tracepoint_release, - .read = bpf_dummy_read, - .write = bpf_dummy_write, +static const struct bpf_link_ops bpf_raw_tp_link_lops = { + .release = bpf_raw_tp_link_release, + .dealloc = bpf_raw_tp_link_dealloc, + .show_fdinfo = bpf_raw_tp_link_show_fdinfo, + .fill_link_info = bpf_raw_tp_link_fill_link_info, }; #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { - struct bpf_raw_tracepoint *raw_tp; + struct bpf_link_primer link_primer; + struct bpf_raw_tp_link *link; struct bpf_raw_event_map *btp; struct bpf_prog *prog; const char *tp_name; char buf[128]; - int tp_fd, err; + int err; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) return -EINVAL; @@ -2255,16 +2684,10 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) if (IS_ERR(prog)) return PTR_ERR(prog); - if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT && - prog->type != BPF_PROG_TYPE_TRACING && - prog->type != BPF_PROG_TYPE_EXT && - prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) { - err = -EINVAL; - goto out_put_prog; - } - - if (prog->type == BPF_PROG_TYPE_TRACING || - prog->type == BPF_PROG_TYPE_EXT) { + switch (prog->type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_LSM: if (attr->raw_tracepoint.name) { /* The attach point for this category of programs * should be specified via btf_id during program load. @@ -2272,11 +2695,14 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) err = -EINVAL; goto out_put_prog; } - if (prog->expected_attach_type == BPF_TRACE_RAW_TP) + if (prog->type == BPF_PROG_TYPE_TRACING && + prog->expected_attach_type == BPF_TRACE_RAW_TP) { tp_name = prog->aux->attach_func_name; - else - return bpf_tracing_prog_attach(prog); - } else { + break; + } + return bpf_tracing_prog_attach(prog); + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: if (strncpy_from_user(buf, u64_to_user_ptr(attr->raw_tracepoint.name), sizeof(buf) - 1) < 0) { @@ -2285,6 +2711,10 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) } buf[sizeof(buf) - 1] = 0; tp_name = buf; + break; + default: + err = -EINVAL; + goto out_put_prog; } btp = bpf_get_raw_tracepoint(tp_name); @@ -2293,29 +2723,29 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) goto out_put_prog; } - raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER); - if (!raw_tp) { + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { err = -ENOMEM; goto out_put_btp; } - raw_tp->btp = btp; - raw_tp->prog = prog; + bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, + &bpf_raw_tp_link_lops, prog); + link->btp = btp; - err = bpf_probe_register(raw_tp->btp, prog); - if (err) - goto out_free_tp; + err = bpf_link_prime(&link->link, &link_primer); + if (err) { + kfree(link); + goto out_put_btp; + } - tp_fd = anon_inode_getfd("bpf-raw-tracepoint", &bpf_raw_tp_fops, raw_tp, - O_CLOEXEC); - if (tp_fd < 0) { - bpf_probe_unregister(raw_tp->btp, prog); - err = tp_fd; - goto out_free_tp; + err = bpf_probe_register(link->btp, prog); + if (err) { + bpf_link_cleanup(&link_primer); + goto out_put_btp; } - return tp_fd; -out_free_tp: - kfree(raw_tp); + return bpf_link_settle(&link_primer); + out_put_btp: bpf_put_raw_tracepoint(btp); out_put_prog: @@ -2330,8 +2760,14 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: + if (!capable(CAP_NET_ADMIN)) + /* cg-skb progs can be loaded by unpriv user. + * check permissions at attach time. + */ + return -EPERM; return prog->enforce_expected_attach_type && prog->expected_attach_type != attach_type ? -EINVAL : 0; @@ -2340,75 +2776,81 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, } } -#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd - -#define BPF_F_ATTACH_MASK \ - (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE) - -static int bpf_prog_attach(const union bpf_attr *attr) +static enum bpf_prog_type +attach_type_to_prog_type(enum bpf_attach_type attach_type) { - enum bpf_prog_type ptype; - struct bpf_prog *prog; - int ret; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (CHECK_ATTR(BPF_PROG_ATTACH)) - return -EINVAL; - - if (attr->attach_flags & ~BPF_F_ATTACH_MASK) - return -EINVAL; - - switch (attr->attach_type) { + switch (attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: - ptype = BPF_PROG_TYPE_CGROUP_SKB; + return BPF_PROG_TYPE_CGROUP_SKB; break; case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: - ptype = BPF_PROG_TYPE_CGROUP_SOCK; - break; + return BPF_PROG_TYPE_CGROUP_SOCK; case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: |