diff options
Diffstat (limited to 'kernel/bpf/syscall.c')
| -rw-r--r-- | kernel/bpf/syscall.c | 3091 |
1 files changed, 2470 insertions, 621 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a91ad518c050..7b373a5e861f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2,8 +2,11 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> +#include <linux/bpf-cgroup.h> #include <linux/bpf_trace.h> #include <linux/bpf_lirc.h> +#include <linux/bpf_verifier.h> +#include <linux/bsearch.h> #include <linux/btf.h> #include <linux/syscalls.h> #include <linux/slab.h> @@ -16,7 +19,6 @@ #include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> -#include <linux/version.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/cred.h> @@ -25,6 +27,14 @@ #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/sort.h> +#include <linux/bpf-netns.h> +#include <linux/rcupdate_trace.h> +#include <linux/memcontrol.h> +#include <linux/trace_events.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ @@ -41,16 +51,21 @@ 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; +int sysctl_unprivileged_bpf_disabled __read_mostly = + IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; 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 }; /* @@ -62,39 +77,31 @@ static const struct bpf_map_ops * const bpf_map_types[] = { * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ -int bpf_check_uarg_tail_zero(void __user *uaddr, +int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size) { - unsigned char __user *addr; - unsigned char __user *end; - unsigned char val; - int err; + 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; + if (uaddr.is_kernel) + res = memchr_inv(uaddr.kernel + expected_size, 0, + actual_size - expected_size) == NULL; + else + res = check_zeroed_user(uaddr.user + expected_size, + actual_size - expected_size); + if (res < 0) + return res; + return res ? 0 : -E2BIG; } const struct bpf_map_ops bpf_map_offload_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, @@ -129,7 +136,22 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } -static u32 bpf_map_value_size(struct bpf_map *map) +static void bpf_map_write_active_inc(struct bpf_map *map) +{ + atomic64_inc(&map->writecnt); +} + +static void bpf_map_write_active_dec(struct bpf_map *map) +{ + atomic64_dec(&map->writecnt); +} + +bool bpf_map_write_active(const struct bpf_map *map) +{ + return atomic64_read(&map->writecnt) != 0; +} + +static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || @@ -162,20 +184,17 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, if (bpf_map_is_dev_bound(map)) { return bpf_map_offload_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || - map->map_type == BPF_MAP_TYPE_SOCKHASH || - map->map_type == BPF_MAP_TYPE_SOCKMAP || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); + } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || + map->map_type == BPF_MAP_TYPE_SOCKMAP) { + return sock_map_update_elem_sys(map, key, value, flags); } else if (IS_FD_PROG_ARRAY(map)) { return bpf_fd_array_map_update_elem(map, f.file, key, value, 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); @@ -199,15 +218,15 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + 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(); } - __this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); return err; @@ -222,8 +241,7 @@ 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); @@ -240,7 +258,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ @@ -262,19 +281,22 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, copy_map_value_locked(map, value, ptr, true); else copy_map_value(map, value, ptr); - /* mask lock, since value wasn't zero inited */ - check_and_init_map_lock(map, value); + /* mask lock and timer, since value wasn't zero inited */ + check_and_init_map_value(map, value); } rcu_read_unlock(); } - this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); return err; } +/* Please, do not use this function outside from the map creation path + * (e.g. in map update path) without taking care of setting the active + * memory cgroup (see at bpf_map_kmalloc_node() for example). + */ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer @@ -287,27 +309,29 @@ 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 | __GFP_ACCOUNT; + 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) @@ -345,77 +369,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); -} - -static int bpf_charge_memlock(struct user_struct *user, u32 pages) -{ - unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - - if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) { - atomic_long_sub(pages, &user->locked_vm); - return -EPERM; - } - return 0; -} - -static void bpf_uncharge_memlock(struct user_struct *user, u32 pages) -{ - if (user) - atomic_long_sub(pages, &user->locked_vm); -} - -int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size) -{ - u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT; - struct user_struct *user; - int ret; - - if (size >= U32_MAX - PAGE_SIZE) - return -E2BIG; - - user = get_current_user(); - ret = bpf_charge_memlock(user, pages); - if (ret) { - free_uid(user); - return ret; - } - - mem->pages = pages; - mem->user = user; - - return 0; -} - -void bpf_map_charge_finish(struct bpf_map_memory *mem) -{ - bpf_uncharge_memlock(mem->user, mem->pages); - free_uid(mem->user); -} - -void bpf_map_charge_move(struct bpf_map_memory *dst, - struct bpf_map_memory *src) -{ - *dst = *src; - - /* Make sure src will not be used for the redundant uncharging. */ - memset(src, 0, sizeof(struct bpf_map_memory)); -} - -int bpf_map_charge_memlock(struct bpf_map *map, u32 pages) -{ - int ret; - - ret = bpf_charge_memlock(map->memory.user, pages); - if (ret) - return ret; - map->memory.pages += pages; - return ret; -} - -void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages) -{ - bpf_uncharge_memlock(map->memory.user, pages); - map->memory.pages -= pages; + map->map_extra = attr->map_extra; } static int bpf_map_alloc_id(struct bpf_map *map) @@ -462,17 +416,208 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) __release(&map_idr_lock); } +#ifdef CONFIG_MEMCG_KMEM +static void bpf_map_save_memcg(struct bpf_map *map) +{ + /* Currently if a map is created by a process belonging to the root + * memory cgroup, get_obj_cgroup_from_current() will return NULL. + * So we have to check map->objcg for being NULL each time it's + * being used. + */ + map->objcg = get_obj_cgroup_from_current(); +} + +static void bpf_map_release_memcg(struct bpf_map *map) +{ + if (map->objcg) + obj_cgroup_put(map->objcg); +} + +static struct mem_cgroup *bpf_map_get_memcg(const struct bpf_map *map) +{ + if (map->objcg) + return get_mem_cgroup_from_objcg(map->objcg); + + return root_mem_cgroup; +} + +void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, + int node) +{ + struct mem_cgroup *memcg, *old_memcg; + void *ptr; + + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); + ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); + + return ptr; +} + +void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) +{ + struct mem_cgroup *memcg, *old_memcg; + void *ptr; + + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); + ptr = kzalloc(size, flags | __GFP_ACCOUNT); + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); + + return ptr; +} + +void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, + size_t align, gfp_t flags) +{ + struct mem_cgroup *memcg, *old_memcg; + void __percpu *ptr; + + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); + ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); + + return ptr; +} + +#else +static void bpf_map_save_memcg(struct bpf_map *map) +{ +} + +static void bpf_map_release_memcg(struct bpf_map *map) +{ +} +#endif + +static int bpf_map_kptr_off_cmp(const void *a, const void *b) +{ + const struct bpf_map_value_off_desc *off_desc1 = a, *off_desc2 = b; + + if (off_desc1->offset < off_desc2->offset) + return -1; + else if (off_desc1->offset > off_desc2->offset) + return 1; + return 0; +} + +struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset) +{ + /* Since members are iterated in btf_find_field in increasing order, + * offsets appended to kptr_off_tab are in increasing order, so we can + * do bsearch to find exact match. + */ + struct bpf_map_value_off *tab; + + if (!map_value_has_kptrs(map)) + return NULL; + tab = map->kptr_off_tab; + return bsearch(&offset, tab->off, tab->nr_off, sizeof(tab->off[0]), bpf_map_kptr_off_cmp); +} + +void bpf_map_free_kptr_off_tab(struct bpf_map *map) +{ + struct bpf_map_value_off *tab = map->kptr_off_tab; + int i; + + if (!map_value_has_kptrs(map)) + return; + for (i = 0; i < tab->nr_off; i++) { + if (tab->off[i].kptr.module) + module_put(tab->off[i].kptr.module); + btf_put(tab->off[i].kptr.btf); + } + kfree(tab); + map->kptr_off_tab = NULL; +} + +struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map) +{ + struct bpf_map_value_off *tab = map->kptr_off_tab, *new_tab; + int size, i; + + if (!map_value_has_kptrs(map)) + return ERR_PTR(-ENOENT); + size = offsetof(struct bpf_map_value_off, off[tab->nr_off]); + new_tab = kmemdup(tab, size, GFP_KERNEL | __GFP_NOWARN); + if (!new_tab) + return ERR_PTR(-ENOMEM); + /* Do a deep copy of the kptr_off_tab */ + for (i = 0; i < tab->nr_off; i++) { + btf_get(tab->off[i].kptr.btf); + if (tab->off[i].kptr.module && !try_module_get(tab->off[i].kptr.module)) { + while (i--) { + if (tab->off[i].kptr.module) + module_put(tab->off[i].kptr.module); + btf_put(tab->off[i].kptr.btf); + } + kfree(new_tab); + return ERR_PTR(-ENXIO); + } + } + return new_tab; +} + +bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b) +{ + struct bpf_map_value_off *tab_a = map_a->kptr_off_tab, *tab_b = map_b->kptr_off_tab; + bool a_has_kptr = map_value_has_kptrs(map_a), b_has_kptr = map_value_has_kptrs(map_b); + int size; + + if (!a_has_kptr && !b_has_kptr) + return true; + if (a_has_kptr != b_has_kptr) + return false; + if (tab_a->nr_off != tab_b->nr_off) + return false; + size = offsetof(struct bpf_map_value_off, off[tab_a->nr_off]); + return !memcmp(tab_a, tab_b, size); +} + +/* Caller must ensure map_value_has_kptrs is true. Note that this function can + * be called on a map value while the map_value is visible to BPF programs, as + * it ensures the correct synchronization, and we already enforce the same using + * the bpf_kptr_xchg helper on the BPF program side for referenced kptrs. + */ +void bpf_map_free_kptrs(struct bpf_map *map, void *map_value) +{ + struct bpf_map_value_off *tab = map->kptr_off_tab; + unsigned long *btf_id_ptr; + int i; + + for (i = 0; i < tab->nr_off; i++) { + struct bpf_map_value_off_desc *off_desc = &tab->off[i]; + unsigned long old_ptr; + + btf_id_ptr = map_value + off_desc->offset; + if (off_desc->type == BPF_KPTR_UNREF) { + u64 *p = (u64 *)btf_id_ptr; + + WRITE_ONCE(*p, 0); + continue; + } + old_ptr = xchg(btf_id_ptr, 0); + off_desc->kptr.dtor((void *)old_ptr); + } +} + /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); - struct bpf_map_memory mem; - bpf_map_charge_move(&mem, &map->memory); security_bpf_map_free(map); - /* implementation dependent freeing */ + kfree(map->off_arr); + bpf_map_release_memcg(map); + /* implementation dependent freeing, map_free callback also does + * bpf_map_free_kptr_off_tab, if needed. + */ map->ops->map_free(map); - bpf_map_charge_finish(&mem); } static void bpf_map_put_uref(struct bpf_map *map) @@ -493,7 +638,10 @@ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) bpf_map_free_id(map, do_idr_lock); btf_put(map->btf); INIT_WORK(&map->work, bpf_map_free_deferred); - schedule_work(&map->work); + /* Avoid spawning kworkers, since they all might contend + * for the same mutex like slab_mutex. + */ + queue_work(system_unbound_wq, &map->work); } } @@ -533,16 +681,29 @@ static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) } #ifdef CONFIG_PROC_FS +/* Provides an approximation of the map's memory footprint. + * Used only to provide a backward compatibility and display + * a reasonable "memlock" info. + */ +static unsigned long bpf_map_memory_footprint(const struct bpf_map *map) +{ + unsigned long size; + + size = round_up(map->key_size + bpf_map_value_size(map), 8); + + return round_up(map->max_entries * size, PAGE_SIZE); +} + static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { - const struct bpf_map *map = filp->private_data; - const struct bpf_array *array; + struct bpf_map *map = filp->private_data; u32 type = 0, jited = 0; - if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) { - array = container_of(map, struct bpf_array, map); - type = array->aux->type; - jited = array->aux->jited; + if (map_type_contains_progs(map)) { + spin_lock(&map->owner.lock); + type = map->owner.type; + jited = map->owner.jited; + spin_unlock(&map->owner.lock); } seq_printf(m, @@ -551,7 +712,8 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" - "memlock:\t%llu\n" + "map_extra:\t%#llx\n" + "memlock:\t%lu\n" "map_id:\t%u\n" "frozen:\t%u\n", map->map_type, @@ -559,7 +721,8 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->value_size, map->max_entries, map->map_flags, - map->memory.pages * 1ULL << PAGE_SHIFT, + (unsigned long long)map->map_extra, + bpf_map_memory_footprint(map), map->id, READ_ONCE(map->frozen)); if (type) { @@ -592,13 +755,8 @@ 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) { - mutex_lock(&map->freeze_mutex); - map->writecnt++; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ @@ -606,13 +764,8 @@ 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) { - mutex_lock(&map->freeze_mutex); - map->writecnt--; - mutex_unlock(&map->freeze_mutex); - } - - bpf_map_put_with_uref(map); + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { @@ -625,7 +778,8 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) struct bpf_map *map = filp->private_data; int err; - if (!map->ops->map_mmap || map_value_has_spin_lock(map)) + if (!map->ops->map_mmap || map_value_has_spin_lock(map) || + map_value_has_timer(map) || map_value_has_kptrs(map)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) @@ -633,28 +787,51 @@ 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) - map->writecnt++; + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_inc(map); 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 +840,7 @@ 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 +874,15 @@ 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 +891,11 @@ 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, @@ -727,6 +906,84 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } +static int map_off_arr_cmp(const void *_a, const void *_b, const void *priv) +{ + const u32 a = *(const u32 *)_a; + const u32 b = *(const u32 *)_b; + + if (a < b) + return -1; + else if (a > b) + return 1; + return 0; +} + +static void map_off_arr_swap(void *_a, void *_b, int size, const void *priv) +{ + struct bpf_map *map = (struct bpf_map *)priv; + u32 *off_base = map->off_arr->field_off; + u32 *a = _a, *b = _b; + u8 *sz_a, *sz_b; + + sz_a = map->off_arr->field_sz + (a - off_base); + sz_b = map->off_arr->field_sz + (b - off_base); + + swap(*a, *b); + swap(*sz_a, *sz_b); +} + +static int bpf_map_alloc_off_arr(struct bpf_map *map) +{ + bool has_spin_lock = map_value_has_spin_lock(map); + bool has_timer = map_value_has_timer(map); + bool has_kptrs = map_value_has_kptrs(map); + struct bpf_map_off_arr *off_arr; + u32 i; + + if (!has_spin_lock && !has_timer && !has_kptrs) { + map->off_arr = NULL; + return 0; + } + + off_arr = kmalloc(sizeof(*map->off_arr), GFP_KERNEL | __GFP_NOWARN); + if (!off_arr) + return -ENOMEM; + map->off_arr = off_arr; + + off_arr->cnt = 0; + if (has_spin_lock) { + i = off_arr->cnt; + + off_arr->field_off[i] = map->spin_lock_off; + off_arr->field_sz[i] = sizeof(struct bpf_spin_lock); + off_arr->cnt++; + } + if (has_timer) { + i = off_arr->cnt; + + off_arr->field_off[i] = map->timer_off; + off_arr->field_sz[i] = sizeof(struct bpf_timer); + off_arr->cnt++; + } + if (has_kptrs) { + struct bpf_map_value_off *tab = map->kptr_off_tab; + u32 *off = &off_arr->field_off[off_arr->cnt]; + u8 *sz = &off_arr->field_sz[off_arr->cnt]; + + for (i = 0; i < tab->nr_off; i++) { + *off++ = tab->off[i].offset; + *sz++ = sizeof(u64); + } + off_arr->cnt += tab->nr_off; + } + + if (off_arr->cnt == 1) + return 0; + sort_r(off_arr->field_off, off_arr->cnt, sizeof(off_arr->field_off[0]), + map_off_arr_cmp, map_off_arr_swap, map); + return 0; +} + static int map_check_btf(struct bpf_map *map, const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { @@ -757,7 +1014,9 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && - map->map_type != BPF_MAP_TYPE_SK_STORAGE) + map->map_type != BPF_MAP_TYPE_SK_STORAGE && + map->map_type != BPF_MAP_TYPE_INODE_STORAGE && + map->map_type != BPF_MAP_TYPE_TASK_STORAGE) return -ENOTSUPP; if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > map->value_size) { @@ -768,18 +1027,52 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, } } - if (map->ops->map_check_btf) + map->timer_off = btf_find_timer(btf, value_type); + if (map_value_has_timer(map)) { + if (map->map_flags & BPF_F_RDONLY_PROG) + return -EACCES; + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY) + return -EOPNOTSUPP; + } + + map->kptr_off_tab = btf_parse_kptrs(btf, value_type); + if (map_value_has_kptrs(map)) { + if (!bpf_capable()) { + ret = -EPERM; + goto free_map_tab; + } + if (map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) { + ret = -EACCES; + goto free_map_tab; + } + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY && + map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + } + + if (map->ops->map_check_btf) { ret = map->ops->map_check_btf(map, btf, key_type, value_type); + if (ret < 0) + goto free_map_tab; + } return ret; +free_map_tab: + bpf_map_free_kptr_off_tab(map); + return ret; } -#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id +#define BPF_MAP_CREATE_LAST_FIELD map_extra /* called via syscall */ static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); - struct bpf_map_memory mem; struct bpf_map *map; int f_flags; int err; @@ -796,6 +1089,10 @@ static int map_create(union bpf_attr *attr) return -EINVAL; } + if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_extra != 0) + return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; @@ -810,15 +1107,18 @@ 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); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); + spin_lock_init(&map->owner.lock); map->spin_lock_off = -EINVAL; + map->timer_off = -EINVAL; if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, * the bpf_prog.o must have BTF to begin with @@ -834,6 +1134,11 @@ static int map_create(union bpf_attr *attr) err = PTR_ERR(btf); goto free_map; } + if (btf_is_kernel(btf)) { + btf_put(btf); + err = -EACCES; + goto free_map; + } map->btf = btf; if (attr->btf_value_type_id) { @@ -849,14 +1154,20 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = security_bpf_map_alloc(map); + err = bpf_map_alloc_off_arr(map); if (err) goto free_map; + err = security_bpf_map_alloc(map); + if (err) + goto free_map_off_arr; + err = bpf_map_alloc_id(map); if (err) goto free_map_sec; + bpf_map_save_memcg(map); + err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. @@ -873,11 +1184,11 @@ static int map_create(union bpf_attr *attr) free_map_sec: security_bpf_map_free(map); +free_map_off_arr: + kfree(map->off_arr); free_map: btf_put(map->btf); - bpf_map_charge_move(&mem, &map->memory); map->ops->map_free(map); - bpf_map_charge_finish(&mem); return err; } @@ -909,6 +1220,22 @@ 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; +} +EXPORT_SYMBOL(bpf_map_get); + struct bpf_map *bpf_map_get_with_uref(u32 ufd) { struct fd f = fdget(ufd); @@ -956,7 +1283,7 @@ int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) static void *__bpf_copy_key(void __user *ukey, u64 key_size) { if (key_size) - return memdup_user(ukey, key_size); + return vmemdup_user(ukey, key_size); if (ukey) return ERR_PTR(-EINVAL); @@ -964,6 +1291,17 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size) return NULL; } +static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size) +{ + if (key_size) + return kvmemdup_bpfptr(ukey, key_size); + + if (!bpfptr_is_null(ukey)) + return ERR_PTR(-EINVAL); + + return NULL; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags @@ -1008,10 +1346,18 @@ static int map_lookup_elem(union bpf_attr *attr) value_size = bpf_map_value_size(map); err = -ENOMEM; - value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; + if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { + if (copy_from_user(value, uvalue, value_size)) + err = -EFAULT; + else + err = bpf_map_copy_value(map, key, value, attr->flags); + goto free_value; + } + err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; @@ -1023,9 +1369,9 @@ static int map_lookup_elem(union bpf_attr *attr) err = 0; free_value: - kfree(value); + kvfree(value); free_key: - kfree(key); + kvfree(key); err_put: fdput(f); return err; @@ -1034,10 +1380,10 @@ err_put: #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags -static int map_update_elem(union bpf_attr *attr) +static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) { - void __user *ukey = u64_to_user_ptr(attr->key); - void __user *uvalue = u64_to_user_ptr(attr->value); + bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); + bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; @@ -1052,6 +1398,7 @@ static int map_update_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1063,45 +1410,35 @@ static int map_update_elem(union bpf_attr *attr) goto err_put; } - key = __bpf_copy_key(ukey, map->key_size); + key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || - map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) - value_size = round_up(map->value_size, 8) * num_possible_cpus(); - else - value_size = map->value_size; - - err = -ENOMEM; - value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); - if (!value) + value_size = bpf_map_value_size(map); + value = kvmemdup_bpfptr(uvalue, value_size); + if (IS_ERR(value)) { + err = PTR_ERR(value); goto free_key; - - err = -EFAULT; - if (copy_from_user(value, uvalue, value_size) != 0) - goto free_value; + } err = bpf_map_update_value(map, f, key, value, attr->flags); -free_value: - kfree(value); + kvfree(value); free_key: - kfree(key); + kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } #define BPF_MAP_DELETE_ELEM_LAST_FIELD key -static int map_delete_elem(union bpf_attr *attr) +static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) { - void __user *ukey = u64_to_user_ptr(attr->key); + bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); int ufd = attr->map_fd; struct bpf_map *map; struct fd f; @@ -1115,12 +1452,13 @@ static int map_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } - key = __bpf_copy_key(ukey, map->key_size); + key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -1136,17 +1474,16 @@ 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); + kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1187,7 +1524,7 @@ static int map_get_next_key(union bpf_attr *attr) } err = -ENOMEM; - next_key = kmalloc(map->key_size, GFP_USER); + next_key = kvmalloc(map->key_size, GFP_USER); if (!next_key) goto free_key; @@ -1210,9 +1547,9 @@ out: err = 0; free_next_key: - kfree(next_key); + kvfree(next_key); free_key: - kfree(key); + kvfree(key); err_put: fdput(f); return err; @@ -1239,7 +1576,7 @@ int generic_map_delete_batch(struct bpf_map *map, if (!max_count) return 0; - key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; @@ -1254,21 +1591,21 @@ 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(); - maybe_wait_bpf_programs(map); + bpf_enable_instrumentation(); if (err) break; + cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; - kfree(key); + kvfree(key); + + maybe_wait_bpf_programs(map); return err; } @@ -1279,12 +1616,11 @@ int generic_map_update_batch(struct bpf_map *map, void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 value_size, cp, max_count; - int ufd = attr->map_fd; + int ufd = attr->batch.map_fd; void *key, *value; struct fd f; int err = 0; - f = fdget(ufd); if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; @@ -1299,16 +1635,17 @@ int generic_map_update_batch(struct bpf_map *map, if (!max_count) return 0; - key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; - value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) { - kfree(key); + kvfree(key); return -ENOMEM; } + f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */ for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, @@ -1321,13 +1658,15 @@ int generic_map_update_batch(struct bpf_map *map, if (err) break; + cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; - kfree(value); - kfree(key); + kvfree(value); + kvfree(key); + fdput(f); return err; } @@ -1361,11 +1700,11 @@ int generic_map_lookup_batch(struct bpf_map *map, if (put_user(0, &uattr->batch.count)) return -EFAULT; - buf_prevkey = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + buf_prevkey = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!buf_prevkey) return -ENOMEM; - buf = kmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); + buf = kvmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); if (!buf) { kvfree(buf_prevkey); return -ENOMEM; @@ -1417,6 +1756,7 @@ int generic_map_lookup_batch(struct bpf_map *map, swap(prev_key, key); retry = MAP_LOOKUP_RETRIES; cp++; + cond_resched(); } if (err == -EFAULT) @@ -1427,12 +1767,12 @@ int generic_map_lookup_batch(struct bpf_map *map, err = -EFAULT; free_buf: - kfree(buf_prevkey); - kfree(buf); + kvfree(buf_prevkey); + kvfree(buf); return err; } -#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value +#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags static int map_lookup_and_delete_elem(union bpf_attr *attr) { @@ -1448,48 +1788,79 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) return -EINVAL; + if (attr->flags & ~BPF_F_LOCK) + return -EINVAL; + f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + bpf_map_write_active_inc(map); + if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || + !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } + if (attr->flags && + (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK)) { + err = -EINVAL; + goto err_put; + } + + if ((attr->flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + err = -EINVAL; + goto err_put; + } + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } - value_size = map->value_size; + value_size = bpf_map_value_size(map); err = -ENOMEM; - value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; + err = -ENOTSUPP; if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK) { err = map->ops->map_pop_elem(map, value); - } else { - err = -ENOTSUPP; + } else if (map->map_type == BPF_MAP_TYPE_HASH || + map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + if (!bpf_map_is_dev_bound(map)) { + bpf_disable_instrumentation(); + rcu_read_lock(); + err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); + rcu_read_unlock(); + bpf_enable_instrumentation(); + } } 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; free_value: - kfree(value); + kvfree(value); free_key: - kfree(key); + kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1510,9 +1881,14 @@ static int map_freeze(const union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - mutex_lock(&map->freeze_mutex); + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || + map_value_has_timer(map) || map_value_has_kptrs(map)) { + fdput(f); + return -ENOTSUPP; + } - if (map->writecnt) { + mutex_lock(&map->freeze_mutex); + if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } @@ -1520,7 +1896,7 @@ 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 +1912,11 @@ 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) @@ -1590,51 +1968,6 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) audit_log_end(ab); } -int __bpf_prog_charge(struct user_struct *user, u32 pages) -{ - unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - unsigned long user_bufs; - - if (user) { - user_bufs = atomic_long_add_return(pages, &user->locked_vm); - if (user_bufs > memlock_limit) { - atomic_long_sub(pages, &user->locked_vm); - return -EPERM; - } - } - - return 0; -} - -void __bpf_prog_uncharge(struct user_struct *user, u32 pages) -{ - if (user) - atomic_long_sub(pages, &user->locked_vm); -} - -static int bpf_prog_charge_memlock(struct bpf_prog *prog) -{ - struct user_struct *user = get_current_user(); - int ret; - - ret = __bpf_prog_charge(user, prog->pages); - if (ret) { - free_uid(user); - return ret; - } - - prog->aux->user = user; - return 0; -} - -static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) -{ - struct user_struct *user = prog->aux->user; - - __bpf_prog_uncharge(user, prog->pages); - free_uid(user); -} - static int bpf_prog_alloc_id(struct bpf_prog *prog) { int id; @@ -1656,6 +1989,8 @@ static int bpf_prog_alloc_id(struct bpf_prog *prog) void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) { + unsigned long flags; + /* cBPF to eBPF migrations are currently not in the idr store. * Offloaded programs are removed from the store when their device * disappears - even if someone grabs an fd to them they are unusable, @@ -1665,7 +2000,7 @@ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) return; if (do_idr_lock) - spin_lock_bh(&prog_idr_lock); + spin_lock_irqsave(&prog_idr_lock, flags); else __acquire(&prog_idr_lock); @@ -1673,7 +2008,7 @@ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) prog->aux->id = 0; if (do_idr_lock) - spin_unlock_bh(&prog_idr_lock); + spin_unlock_irqrestore(&prog_idr_lock, flags); else __release(&prog_idr_lock); } @@ -1684,7 +2019,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); - bpf_prog_uncharge_memlock(aux->prog); + free_uid(aux->user); security_bpf_prog_free(aux); bpf_prog_free(aux->prog); } @@ -1693,22 +2028,48 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) { bpf_prog_kallsyms_del_all(prog); btf_put(prog->aux->btf); - bpf_prog_free_linfo(prog); - - if (deferred) - call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); - else + kvfree(prog->aux->jited_linfo); + kvfree(prog->aux->linfo); + kfree(prog->aux->kfunc_tab); + if (prog->aux->attach_btf) + btf_put(prog->aux->attach_btf); + + if (deferred) { + if (prog->aux->sleepable) + call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); + else + call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); + } else { __bpf_prog_put_rcu(&prog->aux->rcu); + } +} + +static void bpf_prog_put_deferred(struct work_struct *work) +{ + struct bpf_prog_aux *aux; + struct bpf_prog *prog; + + aux = container_of(work, struct bpf_prog_aux, work); + prog = aux->prog; + perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); + bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); + __bpf_prog_put_noref(prog, true); } static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { - if (atomic64_dec_and_test(&prog->aux->refcnt)) { - perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); - bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); + struct bpf_prog_aux *aux = prog->aux; + + if (atomic64_dec_and_test(&aux->refcnt)) { /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); - __bpf_prog_put_noref(prog, true); + + if (in_irq() || irqs_disabled()) { + INIT_WORK(&aux->work, bpf_prog_put_deferred); + schedule_work(&aux->work); + } else { + bpf_prog_put_deferred(&aux->work); + } } } @@ -1726,28 +2087,48 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) return 0; } +struct bpf_prog_kstats { + u64 nsecs; + u64 cnt; + u64 misses; +}; + +void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog) +{ + struct bpf_prog_stats *stats; + unsigned int flags; + + stats = this_cpu_ptr(prog->stats); + flags = u64_stats_update_begin_irqsave(&stats->syncp); + u64_stats_inc(&stats->misses); + u64_stats_update_end_irqrestore(&stats->syncp, flags); +} + static void bpf_prog_get_stats(const struct bpf_prog *prog, - struct bpf_prog_stats *stats) + struct bpf_prog_kstats *stats) { - u64 nsecs = 0, cnt = 0; + u64 nsecs = 0, cnt = 0, misses = 0; int cpu; for_each_possible_cpu(cpu) { const struct bpf_prog_stats *st; unsigned int start; - u64 tnsecs, tcnt; + u64 tnsecs, tcnt, tmisses; - st = per_cpu_ptr(prog->aux->stats, cpu); + st = per_cpu_ptr(prog->stats, cpu); do { start = u64_stats_fetch_begin_irq(&st->syncp); - tnsecs = st->nsecs; - tcnt = st->cnt; + tnsecs = u64_stats_read(&st->nsecs); + tcnt = u64_stats_read(&st->cnt); + tmisses = u64_stats_read(&st->misses); } while (u64_stats_fetch_retry_irq(&st->syncp, start)); nsecs += tnsecs; cnt += tcnt; + misses += tmisses; } stats->nsecs = nsecs; stats->cnt = cnt; + stats->misses = misses; } #ifdef CONFIG_PROC_FS @@ -1755,7 +2136,7 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - struct bpf_prog_stats stats; + struct bpf_prog_kstats stats; bpf_prog_get_stats(prog, &stats); bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); @@ -1766,14 +2147,18 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) "memlock:\t%llu\n" "prog_id:\t%u\n" "run_time_ns:\t%llu\n" - "run_cnt:\t%llu\n", + "run_cnt:\t%llu\n" + "recursion_misses:\t%llu\n" + "verified_insns:\t%u\n", prog->type, prog->jited, prog_tag, prog->pages * 1ULL << PAGE_SHIFT, prog->aux->id, stats.nsecs, - stats.cnt); + stats.cnt, + stats.misses, + prog->aux->verified_insns); } #endif @@ -1917,20 +2302,30 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) attr->expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; break; + case BPF_PROG_TYPE_SK_REUSEPORT: + if (!attr->expected_attach_type) + attr->expected_attach_type = + BPF_SK_REUSEPORT_SELECT; + break; } } static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, - u32 btf_id, u32 prog_fd) + struct btf *attach_btf, u32 btf_id, + struct bpf_prog *dst_prog) { if (btf_id) { if (btf_id > BTF_MAX_TYPE) return -EINVAL; + if (!attach_btf && !dst_prog) + return -EINVAL; + 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; @@ -1939,7 +2334,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, } } - if (prog_fd && prog_type != BPF_PROG_TYPE_TRACING && + if (attach_btf && (!btf_id || dst_prog)) + return -EINVAL; + + if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING && prog_type != BPF_PROG_TYPE_EXT) return -EINVAL; @@ -1947,6 +2345,7 @@ 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 +2358,10 @@ 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: @@ -1983,22 +2386,85 @@ 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_SK_REUSEPORT: + switch (expected_attach_type) { + case BPF_SK_REUSEPORT_SELECT: + case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: + return 0; + default: + return -EINVAL; + } + case BPF_PROG_TYPE_SYSCALL: 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 +#define BPF_PROG_LOAD_LAST_FIELD core_relo_rec_size -static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) +static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) { enum bpf_prog_type type = attr->prog_type; - struct bpf_prog *prog; + struct bpf_prog *prog, *dst_prog = NULL; + struct btf *attach_btf = NULL; int err; char license[128]; bool is_gpl; @@ -2009,17 +2475,20 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT | BPF_F_TEST_STATE_FREQ | - BPF_F_TEST_RND_HI32)) + BPF_F_SLEEPABLE | + BPF_F_TEST_RND_HI32 | + BPF_F_XDP_HAS_FRAGS)) return -EINVAL; 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 */ - if (strncpy_from_user(license, u64_to_user_ptr(attr->license), - sizeof(license) - 1) < 0) + if (strncpy_from_bpfptr(license, + make_bpfptr(attr->license, uattr.is_kernel), + sizeof(license) - 1) < 0) return -EFAULT; license[sizeof(license) - 1] = 0; @@ -2027,53 +2496,87 @@ 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; + + /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog + * or btf, we need to check which one it is + */ + if (attr->attach_prog_fd) { + dst_prog = bpf_prog_get(attr->attach_prog_fd); + if (IS_ERR(dst_prog)) { + dst_prog = NULL; + attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); + if (IS_ERR(attach_btf)) + return -EINVAL; + if (!btf_is_kernel(attach_btf)) { + /* attaching through specifying bpf_prog's BTF + * objects directly might be supported eventually + */ + btf_put(attach_btf); + return -ENOTSUPP; + } + } + } else if (attr->attach_btf_id) { + /* fall back to vmlinux BTF, if BTF type ID is specified */ + attach_btf = bpf_get_btf_vmlinux(); + if (IS_ERR(attach_btf)) + return PTR_ERR(attach_btf); + if (!attach_btf) + return -EINVAL; + btf_get(attach_btf); + } + bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, - attr->attach_btf_id, - attr->attach_prog_fd)) + attach_btf, attr->attach_btf_id, + dst_prog)) { + if (dst_prog) + bpf_prog_put(dst_prog); + if (attach_btf) + btf_put(attach_btf); return -EINVAL; + } /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); - if (!prog) + if (!prog) { + if (dst_prog) + bpf_prog_put(dst_prog); + if (attach_btf) + btf_put(attach_btf); return -ENOMEM; + } prog->expected_attach_type = attr->expected_attach_type; + prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; - if (attr->attach_prog_fd) { - struct bpf_prog *tgt_prog; - - tgt_prog = bpf_prog_get(attr->attach_prog_fd); - if (IS_ERR(tgt_prog)) { - err = PTR_ERR(tgt_prog); - goto free_prog_nouncharge; - } - prog->aux->linked_prog = tgt_prog; - } - + prog->aux->dst_prog = dst_prog; prog->aux->offload_requested = !!attr->prog_ifindex; + prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; + prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; err = security_bpf_prog_alloc(prog->aux); if (err) - goto free_prog_nouncharge; - - err = bpf_prog_charge_memlock(prog); - if (err) - goto free_prog_sec; + goto free_prog; + prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; err = -EFAULT; - if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns), - bpf_prog_insn_size(prog)) != 0) - goto free_prog; + if (copy_from_bpfptr(prog->insns, + make_bpfptr(attr->insns, uattr.is_kernel), + bpf_prog_insn_size(prog)) != 0) + goto free_prog_sec; prog->orig_prog = NULL; prog->jited = 0; @@ -2084,18 +2587,19 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_offload_init(prog, attr); if (err) - goto free_prog; + goto free_prog_sec; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) - goto free_prog; + goto free_prog_sec; prog->aux->load_time = ktime_get_boottime_ns(); - err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name); - if (err) - goto free_prog; + err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, + sizeof(attr->prog_name)); + if (err < 0) + goto free_prog_sec; /* run eBPF verifier */ err = bpf_check(&prog, attr, uattr); @@ -2140,11 +2644,12 @@ free_used_maps: */ __bpf_prog_put_noref(prog, prog->aux->func_cnt); return err; -free_prog: - bpf_prog_uncharge_memlock(prog); free_prog_sec: + free_uid(prog->aux->user); security_bpf_prog_free(prog->aux); -free_prog_nouncharge: +free_prog: + if (prog->aux->attach_btf) + btf_put(prog->aux->attach_btf); bpf_prog_free(prog); return err; } @@ -2169,160 +2674,699 @@ 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); + } +} +EXPORT_SYMBOL(bpf_link_put); + +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_tracing_prog_attach(struct bpf_prog *prog) +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 in between 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; +} +EXPORT_SYMBOL(bpf_link_get_from_fd); + +static void bpf_tracing_link_release(struct bpf_link *link) +{ + struct bpf_tracing_link *tr_link = + container_of(link, struct bpf_tracing_link, link.link); + + WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link, + tr_link->trampoline)); + + bpf_trampoline_put(tr_link->trampoline); + + /* tgt_prog is NULL if target is a kernel function */ + if (tr_link->tgt_prog) + bpf_prog_put(tr_link->tgt_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.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.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.link); + + info->tracing.attach_type = tr_link->attach_type; + bpf_trampoline_unpack_key(tr_link->trampoline->key, + &info->tracing.target_obj_id, + &info->tracing.target_btf_id); + + 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 tgt_prog_fd, + u32 btf_id, + u64 bpf_cookie) { - int tr_fd, err; + struct bpf_link_primer link_primer; + struct bpf_prog *tgt_prog = NULL; + struct bpf_trampoline *tr = NULL; + struct bpf_tracing_link *link; + u64 key = 0; + 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) + if (!!tgt_prog_fd != !!btf_id) { + err = -EINVAL; goto out_put_prog; + } + + if (tgt_prog_fd) { + /* For now we only allow new targets for BPF_PROG_TYPE_EXT */ + if (prog->type != BPF_PROG_TYPE_EXT) { + err = -EINVAL; + goto out_put_prog; + } + + tgt_prog = bpf_prog_get(tgt_prog_fd); + if (IS_ERR(tgt_prog)) { + err = PTR_ERR(tgt_prog); + tgt_prog = NULL; + goto out_put_prog; + } - 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; + key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id); + } + + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; goto out_put_prog; } - return tr_fd; + bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING, + &bpf_tracing_link_lops, prog); + link->attach_type = prog->expected_attach_type; + link->link.cookie = bpf_cookie; + + mutex_lock(&prog->aux->dst_mutex); + + /* There are a few possible cases here: + * + * - if prog->aux->dst_trampoline is set, the program was just loaded + * and not yet attached to anything, so we can use the values stored + * 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) + * + * - if tgt_prog != NULL, the caller specified tgt_prog_fd + + * target_btf_id using the link_create API. + * + * - if tgt_prog == NULL when this function was called using the old + * raw_tracepoint_open API, and we need a target from prog->aux + * + * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program + * was detached and is going for re-attachment. + */ + if (!prog->aux->dst_trampoline && !tgt_prog) { + /* + * Allow re-attach for TRACING and LSM programs. If it's + * currently linked, bpf_trampoline_link_prog will fail. + * EXT programs need to specify tgt_prog_fd, so they + * re-attach in separate code path. + */ + if (prog->type != BPF_PROG_TYPE_TRACING && + prog->type != BPF_PROG_TYPE_LSM) { + err = -EINVAL; + goto out_unlock; + } + btf_id = prog->aux->attach_btf_id; + key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id); + } + + if (!prog->aux->dst_trampoline || + (key && key != prog->aux->dst_trampoline->key)) { + /* If there is no saved target, or the specified target is + * different from the destination specified at load time, we + * need a new trampoline and a check for compatibility + */ + struct bpf_attach_target_info tgt_info = {}; + + err = bpf_check_attach_target(NULL, prog, tgt_prog, btf_id, + &tgt_info); + if (err) + goto out_unlock; + + tr = bpf_trampoline_get(key, &tgt_info); + if (!tr) { + err = -ENOMEM; + goto out_unlock; + } + } else { + /* The caller didn't specify a target, or the target was the + * same as the destination supplied during program load. This + * means we can reuse the trampoline and reference from program + * load time, and there is no need to allocate a new one. This + * can only happen once for any program, as the saved values in + * prog->aux are cleared below. + */ + tr = prog->aux->dst_trampoline; + tgt_prog = prog->aux->dst_prog; + } + err = bpf_link_prime(&link->link.link, &link_primer); + if (err) + goto out_unlock; + + err = bpf_trampoline_link_prog(&link->link, tr); + if (err) { + bpf_link_cleanup(&link_primer); + link = NULL; + goto out_unlock; + } + + link->tgt_prog = tgt_prog; + link->trampoline = tr; + + /* Always clear the trampoline and target prog from prog->aux to make + * sure the original attach destination is not kept alive after a + * program is (re-)attached to another target. + */ + if (prog->aux->dst_prog && + (tgt_prog_fd || tr != prog->aux->dst_trampoline)) + /* got extra prog ref from syscall, or attaching to different prog */ + bpf_prog_put(prog->aux->dst_prog); + if (prog->aux->dst_trampoline && tr != prog->aux->dst_trampoline) + /* we allocated a new trampoline, so free the old one */ + bpf_trampoline_put(prog->aux->dst_trampoline); + + prog->aux->dst_prog = NULL; + prog->aux->dst_trampoline = NULL; + mutex_unlock(&prog->aux->dst_mutex); + + return bpf_link_settle(&link_primer); +out_unlock: + if (tr && tr != prog->aux->dst_trampoline) + bpf_trampoline_put(tr); + mutex_unlock(&prog->aux->dst_mutex); + kfree(link); out_put_prog: - bpf_prog_put(prog); + if (tgt_prog_fd && tgt_prog) + bpf_prog_put(tgt_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 +#ifdef CONFIG_PERF_EVENTS +struct bpf_perf_link { + struct bpf_link link; + struct file *perf_file; +}; -static int bpf_raw_tracepoint_open(const union bpf_attr *attr) +static void bpf_perf_link_release(struct bpf_link *link) { - struct bpf_raw_tracepoint *raw_tp; - struct bpf_raw_event_map *btp; - struct bpf_prog *prog; - const char *tp_name; - char buf[128]; - int tp_fd, err; + struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); + struct perf_event *event = perf_link->perf_file->private_data; - if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) + perf_event_free_bpf_prog(event); + fput(perf_link->perf_file); +} + +static void bpf_perf_link_dealloc(struct bpf_link *link) +{ + struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); + + kfree(perf_link); +} + +static const struct bpf_link_ops bpf_perf_link_lops = { + .release = bpf_perf_link_release, + .dealloc = bpf_perf_link_dealloc, +}; + +static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_link_primer link_primer; + struct bpf_perf_link *link; + struct perf_event *event; + struct file *perf_file; + int err; + + if (attr->link_create.flags) return -EINVAL; - prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); - if (IS_ERR(prog)) - return PTR_ERR(prog); + perf_file = perf_event_get(attr->link_create.target_fd); + if (IS_ERR(perf_file)) + return PTR_ERR(perf_file); - 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; + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; + goto out_put_file; } + bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog); + link->perf_file = perf_file; + + err = bpf_link_prime(&link->link, &link_primer); + if (err) { + kfree(link); + goto out_put_file; + } + + event = perf_file->private_data; + err = perf_event_set_bpf_prog(event, prog, attr->link_create.perf_event.bpf_cookie); + if (err) { + bpf_link_cleanup(&link_primer); + goto out_put_file; + } + /* perf_event_set_bpf_prog() doesn't take its own refcnt on prog */ + bpf_prog_inc(prog); + + return bpf_link_settle(&link_primer); + +out_put_file: + fput(perf_file); + return err; +} +#else +static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_PERF_EVENTS */ + +static int bpf_raw_tp_link_attach(struct bpf_prog *prog, + const char __user *user_tp_name) +{ + struct bpf_link_primer link_primer; + struct bpf_raw_tp_link *link; + struct bpf_raw_event_map *btp; + const char *tp_name; + char buf[128]; + int err; - if (prog->type == BPF_PROG_TYPE_TRACING || - prog->type == BPF_PROG_TYPE_EXT) { - if (attr->raw_tracepoint.name) { + switch (prog->type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_LSM: + if (user_tp_name) /* The attach point for this category of programs * should be specified via btf_id during program load. */ - err = -EINVAL; - goto out_put_prog; - } - if (prog->expected_attach_type == BPF_TRACE_RAW_TP) + return -EINVAL; + 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 { - if (strncpy_from_user(buf, - u64_to_user_ptr(attr->raw_tracepoint.name), - sizeof(buf) - 1) < 0) { - err = -EFAULT; - goto out_put_prog; + break; } + return bpf_tracing_prog_attach(prog, 0, 0, 0); + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0) + return -EFAULT; buf[sizeof(buf) - 1] = 0; tp_name = buf; + break; + default: + return -EINVAL; } btp = bpf_get_raw_tracepoint(tp_name); - if (!btp) { - err = -ENOENT; - goto out_put_prog; - } + if (!btp) + return -ENOENT; - 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: - bpf_prog_put(prog); return err; } +#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd + +static int bpf_raw_tracepoint_open(const union bpf_attr *attr) +{ + struct bpf_prog *prog; + int fd; + + if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) + return -EINVAL; + + prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + fd = bpf_raw_tp_link_attach(prog, u64_to_user_ptr(attr->raw_tracepoint.name)); + if (fd < 0) + bpf_prog_put(prog); + return fd; +} + static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, enum bpf_attach_type attach_type) { @@ -2330,8 +3374,14 @@ 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 +3390,89 @@ 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; - break; + return BPF_PROG_TYPE_CGROUP_SKB; 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: + 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: case BPF_CGROUP_UDP6_RECVMSG: - ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - break; + return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: - ptype = BPF_PROG_TYPE_SOCK_OPS; - break; + return BPF_PROG_TYPE_SOCK_OPS; case BPF_CGROUP_DEVICE: - ptype = BPF_PROG_TYPE_CGROUP_DEVICE; - break; + return BPF_PROG_TYPE_CGROUP_DEVICE; case BPF_SK_MSG_VERDICT: - ptype = BPF_PROG_TYPE_SK_MSG; - break; + return BPF_PROG_TYPE_SK_MSG; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - ptype = BPF_PROG_TYPE_SK_SKB; - break; + case BPF_SK_SKB_VERDICT: + return BPF_PROG_TYPE_SK_SKB; case BPF_LIRC_MODE2: - ptype = BPF_PROG_TYPE_LIRC_MODE2; - break; + return BPF_PROG_TYPE_LIRC_MODE2; case BPF_FLOW_DISSECTOR: - ptype = BPF_PROG_TYPE_FLOW_DISSECTOR; - break; + return BPF_PROG_TYPE_FLOW_DISSECTOR; case BPF_CGROUP_SYSCTL: - ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; - break; + return BPF_PROG_TYPE_CGROUP_SYSCTL; case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: - ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT; - break; + return BPF_PROG_TYPE_CGROUP_SOCKOPT; + case BPF_TRACE_ITER: + case BPF_TRACE_RAW_TP: + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: + return BPF_PROG_TYPE_TRACING; + case BPF_LSM_MAC: + return BPF_PROG_TYPE_LSM; + case BPF_SK_LOOKUP: + return BPF_PROG_TYPE_SK_LOOKUP; + case BPF_XDP: + return BPF_PROG_TYPE_XDP; + case BPF_LSM_CGROUP: + return BPF_PROG_TYPE_LSM; default: - return -EINVAL; + return BPF_PROG_TYPE_UNSPEC; } +} + +#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) +{ + enum bpf_prog_type ptype; + struct bpf_prog *prog; + int ret; + + if (CHECK_ATTR(BPF_PROG_ATTACH)) + return -EINVAL; + + if (attr->attach_flags & ~BPF_F_ATTACH_MASK) + return -EINVAL; + + ptype = attach_type_to_prog_type(attr->attach_type); + if (ptype == BPF_PROG_TYPE_UNSPEC) + return -EINVAL; prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) @@ -2428,10 +3492,24 @@ static int bpf_prog_attach(const union bpf_attr *attr) ret = lirc_prog_attach(attr, prog); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: - ret = skb_flow_dissector_bpf_prog_attach(attr, prog); + ret = netns_bpf_prog_attach(attr, prog); break; - default: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SKB: + 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_LSM: + if (ptype == BPF_PROG_TYPE_LSM && + prog->expected_attach_type != BPF_LSM_CGROUP) + return -EINVAL; + ret = cgroup_bpf_prog_attach(attr, ptype, prog); + break; + default: + ret = -EINVAL; } if (ret) @@ -2445,62 +3523,34 @@ static int bpf_prog_detach(const union bpf_attr *attr) { enum bpf_prog_type ptype; - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - if (CHECK_ATTR(BPF_PROG_DETACH)) return -EINVAL; - switch (attr->attach_type) { - case BPF_CGROUP_INET_INGRESS: - case BPF_CGROUP_INET_EGRESS: - ptype = BPF_PROG_TYPE_CGROUP_SKB; - break; - case BPF_CGROUP_INET_SOCK_CREATE: - case BPF_CGROUP_INET4_POST_BIND: - case BPF_CGROUP_INET6_POST_BIND: - ptype = BPF_PROG_TYPE_CGROUP_SOCK; - break; - case BPF_CGROUP_INET4_BIND: - case BPF_CGROUP_INET6_BIND: - case BPF_CGROUP_INET4_CONNECT: - case BPF_CGROUP_INET6_CONNECT: - case BPF_CGROUP_UDP4_SENDMSG: - case BPF_CGROUP_UDP6_SENDMSG: - case BPF_CGROUP_UDP4_RECVMSG: - case BPF_CGROUP_UDP6_RECVMSG: - ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - break; - case BPF_CGROUP_SOCK_OPS: - ptype = BPF_PROG_TYPE_SOCK_OPS; - break; - case BPF_CGROUP_DEVICE: - ptype = BPF_PROG_TYPE_CGROUP_DEVICE; - break; - case BPF_SK_MSG_VERDICT: - return sock_map_get_from_fd(attr, NULL); - case BPF_SK_SKB_STREAM_PARSER: - case BPF_SK_SKB_STREAM_VERDICT: - return sock_map_get_from_fd(attr, NULL); - case BPF_LIRC_MODE2: + ptype = attach_type_to_prog_type(attr->attach_type); + + switch (ptype) { + case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_SK_SKB: + return sock_map_prog_detach(attr, ptype); + case BPF_PROG_TYPE_LIRC_MODE2: return lirc_prog_detach(attr); - case BPF_FLOW_DISSECTOR: - return skb_flow_dissector_bpf_prog_detach(attr); - case BPF_CGROUP_SYSCTL: - ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; - break; - case BPF_CGROUP_GETSOCKOPT: - case BPF_CGROUP_SETSOCKOPT: - ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT; - break; + case BPF_PROG_TYPE_FLOW_DISSECTOR: + return netns_bpf_prog_detach(attr, ptype); + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SKB: + 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_LSM: + return cgroup_bpf_prog_detach(attr, ptype); default: return -EINVAL; } - - return cgroup_bpf_prog_detach(attr, ptype); } -#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt +#define BPF_PROG_QUERY_LAST_FIELD query.prog_attach_flags static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -2516,12 +3566,17 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_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: @@ -2531,19 +3586,24 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_SYSCTL: case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: - break; + case BPF_LSM_CGROUP: + return cgroup_bpf_prog_query(attr, uattr); case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); case BPF_FLOW_DISSECTOR: - return skb_flow_dissector_prog_query(attr, uattr); + case BPF_SK_LOOKUP: + return netns_bpf_prog_query(attr, uattr); + case BPF_SK_SKB_STREAM_PARSER: + case BPF_SK_SKB_STREAM_VERDICT: + case BPF_SK_MSG_VERDICT: + case BPF_SK_SKB_VERDICT: + return sock_map_bpf_prog_query(attr, uattr); default: return -EINVAL; } - - return cgroup_bpf_prog_query(attr, uattr); } -#define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out +#define BPF_PROG_TEST_RUN_LAST_FIELD test.batch_size static int bpf_prog_test_run(const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -2551,8 +3611,6 @@ static int bpf_prog_test_run(const union bpf_attr *attr, struct bpf_prog *prog; int ret = -ENOTSUPP; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; if (CHECK_ATTR(BPF_PROG_TEST_RUN)) return -EINVAL; @@ -2603,6 +3661,44 @@ static int bpf_obj_get_next_id(const union bpf_attr *attr, return err; } +struct bpf_map *bpf_map_get_curr_or_next(u32 *id) +{ + struct bpf_map *map; + + spin_lock_bh(&map_idr_lock); +again: + map = idr_get_next(&map_idr, id); + if (map) { + map = __bpf_map_inc_not_zero(map, false); + if (IS_ERR(map)) { + (*id)++; + goto again; + } + } + spin_unlock_bh(&map_idr_lock); + + return map; +} + +struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id) +{ + struct bpf_prog *prog; + + spin_lock_bh(&prog_idr_lock); +again: + prog = idr_get_next(&prog_idr, id); + if (prog) { + prog = bpf_prog_inc_not_zero(prog); + if (IS_ERR(prog)) { + (*id)++; + goto again; + } + } + spin_unlock_bh(&prog_idr_lock); + + return prog; +} + #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id struct bpf_prog *bpf_prog_by_id(u32 id) @@ -2690,29 +3786,35 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, const struct bpf_map *map; int i; + mutex_lock(&prog->aux->used_maps_mutex); for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) { map = prog->aux->used_maps[i]; if (map == (void *)addr) { *type = BPF_PSEUDO_MAP_FD; - return map; + goto out; } if (!map->ops->map_direct_value_meta) continue; if (!map->ops->map_direct_value_meta(map, addr, off)) { *type = BPF_PSEUDO_MAP_VALUE; - return map; + goto out; } } + map = NULL; - return NULL; +out: + mutex_unlock(&prog->aux->used_maps_mutex); + return map; } -static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) +static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, + const struct cred *f_cred) { const struct bpf_map *map; struct bpf_insn *insns; u32 off, type; u64 imm; + u8 code; int i; insns = kmemdup(prog->insnsi, bpf_prog_insn_size(prog), @@ -2721,21 +3823,27 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) return insns; for (i = 0; i < prog->len; i++) { - if (insns[i].code == (BPF_JMP | BPF_TAIL_CALL)) { + code = insns[i].code; + + if (code == (BPF_JMP | BPF_TAIL_CALL)) { insns[i].code = BPF_JMP | BPF_CALL; insns[i].imm = BPF_FUNC_tail_call; /* fall-through */ } - if (insns[i].code == (BPF_JMP | BPF_CALL) || - insns[i].code == (BPF_JMP | BPF_CALL_ARGS)) { - if (insns[i].code == (BPF_JMP | BPF_CALL_ARGS)) + if (code == (BPF_JMP | BPF_CALL) || + code == (BPF_JMP | BPF_CALL_ARGS)) { + if (code == (BPF_JMP | BPF_CALL_ARGS)) insns[i].code = BPF_JMP | BPF_CALL; - if (!bpf_dump_raw_ok()) + if (!bpf_dump_raw_ok(f_cred)) insns[i].imm = 0; continue; } + if (BPF_CLASS(code) == BPF_LDX && BPF_MODE(code) == BPF_PROBE_MEM) { + insns[i].code = BPF_LDX | BPF_SIZE(code) | BPF_MEM; + continue; + } - if (insns[i].code != (BPF_LD | BPF_IMM | BPF_DW)) + if (code != (BPF_LD | BPF_IMM | BPF_DW)) continue; imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm; @@ -2782,23 +3890,26 @@ static int set_info_rec_size(struct bpf_prog_info *info) return 0; } -static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, +static int bpf_prog_get_info_by_fd(struct file *file, + struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); - struct bpf_prog_info info = {}; + struct btf *attach_btf = bpf_prog_get_target_btf(prog); + struct bpf_prog_info info; u32 info_len = attr->info.info_len; - struct bpf_prog_stats stats; + struct bpf_prog_kstats stats; char __user *uinsns; u32 ulen; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); + memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; @@ -2812,6 +3923,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, memcpy(info.tag, prog->tag, sizeof(prog->tag)); memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); + mutex_lock(&prog->aux->used_maps_mutex); ulen = info.nr_map_ids; info.nr_map_ids = prog->aux->used_map_cnt; ulen = min_t(u32, info.nr_map_ids, ulen); @@ -2821,9 +3933,12 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, for (i = 0; i < ulen; i++) if (put_user(prog->aux->used_maps[i]->id, - &user_map_ids[i])) + &user_map_ids[i])) { + mutex_unlock(&prog->aux->used_maps_mutex); return -EFAULT; + } } + mutex_unlock(&prog->aux->used_maps_mutex); err = set_info_rec_size(&info); if (err) @@ -2832,8 +3947,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, bpf_prog_get_stats(prog, &stats); info.run_time_ns = stats.nsecs; info.run_cnt = stats.cnt; + info.recursion_misses = stats.misses; - if (!capable(CAP_SYS_ADMIN)) { + info.verified_insns = prog->aux->verified_insns; + + if (!bpf_capable()) { info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; @@ -2850,11 +3968,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, struct bpf_insn *insns_sanitized; bool fault; - if (prog->blinded && !bpf_dump_raw_ok()) { + if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) { info.xlated_prog_insns = 0; goto done; } - insns_sanitized = bpf_insn_prepare_dump(prog); + insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred); if (!insns_sanitized) return -ENOMEM; uinsns = u64_to_user_ptr(info.xlated_prog_insns); @@ -2888,7 +4006,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } if (info.jited_prog_len && ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { uinsns = u64_to_user_ptr(info.jited_prog_insns); ulen = min_t(u32, info.jited_prog_len, ulen); @@ -2923,7 +4041,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, ulen = info.nr_jited_ksyms; info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { unsigned long ksym_addr; u64 __user *user_ksyms; u32 i; @@ -2954,7 +4072,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, ulen = info.nr_jited_func_lens; info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { u32 __user *user_lens; u32 func_len, i; @@ -2979,7 +4097,10 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } if (prog->aux->btf) - info.btf_id = btf_id(prog->aux->btf); + info.btf_id = btf_obj_id(prog->aux->btf); + info.attach_btf_id = prog->aux->attach_btf_id; + if (attach_btf) + info.attach_btf_obj_id = btf_obj_id(attach_btf); ulen = info.nr_func_info; info.nr_func_info = prog->aux->func_info_cnt; @@ -3011,15 +4132,16 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, else info.nr_jited_line_info = 0; if (info.nr_jited_line_info && ulen) { - if (bpf_dump_raw_ok()) { + if (bpf_dump_raw_ok(file->f_cred)) { + unsigned long line_addr; __u64 __user *user_linfo; u32 i; user_linfo = u64_to_user_ptr(info.jited_line_info); ulen = min_t(u32, info.nr_jited_line_info, ulen); for (i = 0; i < ulen; i++) { - if (put_user((__u64)(long)prog->aux->jited_linfo[i], - &user_linfo[i])) + line_addr = (unsigned long)prog->aux->jited_linfo[i]; + if (put_user((__u64)line_addr, &user_linfo[i])) return -EFAULT; } } else { @@ -3057,30 +4179,33 @@ done: return 0; } -static int bpf_map_get_info_by_fd(struct bpf_map *map, +static int bpf_map_get_info_by_fd(struct file *file, + struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info); - struct bpf_map_info info = {}; + struct bpf_map_info info; u32 info_len = attr->info.info_len; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); + memset(&info, 0, sizeof(info)); info.type = map->map_type; info.id = map->id; info.key_size = map->key_size; info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { - info.btf_id = btf_id(map->btf); + info.btf_id = btf_obj_id(map->btf); info.btf_key_type_id = map->btf_key_type_id; info.btf_value_type_id = map->btf_value_type_id; } @@ -3099,7 +4224,8 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, return 0; } -static int bpf_btf_get_info_by_fd(struct btf *btf, +static int bpf_btf_get_info_by_fd(struct file *file, + struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -3107,13 +4233,50 @@ static int bpf_btf_get_info_by_fd(struct btf *btf, u32 info_len = attr->info.info_len; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); if (err) return err; return btf_get_info_by_fd(btf, attr, uattr); } +static int bpf_link_get_info_by_fd(struct file *file, + struct bpf_link *link, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct bpf_link_info __user *uinfo = u64_to_user_ptr(attr->info.info); + struct bpf_link_info info; + u32 info_len = attr->info.info_len; + int err; + + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); + if (err) + return err; + info_len = min_t(u32, sizeof(info), info_len); + + memset(&info, 0, sizeof(info)); + if (copy_from_user(&info, uinfo, info_len)) + return -EFAULT; + + info.type = link->type; + info.id = link->id; + info.prog_id = link->prog->aux->id; + + if (link->ops->fill_link_info) { + err = link->ops->fill_link_info(link, &info); + if (err) + return err; + } + + if (copy_to_user(uinfo, &info, info_len) || + put_user(info_len, &uattr->info.info_len)) + return -EFAULT; + + return 0; +} + + #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, @@ -3131,13 +4294,16 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return -EBADFD; if (f.file->f_op == &bpf_prog_fops) - err = bpf_prog_get_info_by_fd(f.file->private_data, attr, + err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else if (f.file->f_op == &bpf_map_fops) - err = bpf_map_get_info_by_fd(f.file->private_data, attr, + err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr, uattr); else if (f.file->f_op == &btf_fops) - err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr); + err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr); + else if (f.file->f_op == &bpf_link_fops) + err = bpf_link_get_info_by_fd(f.file, f.file->private_data, + attr, uattr); else err = -EINVAL; @@ -3147,15 +4313,15 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, #define BPF_BTF_LOAD_LAST_FIELD btf_log_level -static int bpf_btf_load(const union bpf_attr *attr) +static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr) { if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; - if (!capable(CAP_SYS_ADMIN)) + if (!bpf_capable()) return -EPERM; - return btf_new_fd(attr); + return btf_new_fd(attr, uattr); } #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id @@ -3226,7 +4392,6 @@ static int bpf_task_fd_query(const union bpf_attr *attr, pid_t pid = attr->task_fd_query.pid; u32 fd = attr->task_fd_query.fd; const struct perf_event *event; - struct files_struct *files; struct task_struct *task; struct file *file; int err; @@ -3240,37 +4405,33 @@ static int bpf_task_fd_query(const union bpf_attr *attr, if (attr->task_fd_query.flags != 0) return -EINVAL; + rcu_read_lock(); task = get_pid_task(find_vpid(pid), PIDTYPE_PID); + rcu_read_unlock(); if (!task) return -ENOENT; - files = get_files_struct(task); - put_task_struct(task); - if (!files) - return -ENOENT; - err = 0; - spin_lock(&files->file_lock); - file = fcheck_files(files, fd); + file = fget_task(task, fd); + put_task_struct(task); if (!file) - err = -EBADF; - else - get_file(file); - spin_unlock(&files->file_lock); - put_files_struct(files); + return -EBADF; - if (err) - goto out; + if (file->f_op == &bpf_link_fops) { + struct bpf_link *link = file->private_data; - if (file->f_op == &bpf_raw_tp_fops) { - struct bpf_raw_tracepoint *raw_tp = file->private_data; - struct bpf_raw_event_map *btp = raw_tp->btp; + if (link->ops == &bpf_raw_tp_link_lops) { + struct bpf_raw_tp_link *raw_tp = + container_of(link, struct bpf_raw_tp_link, link); + struct bpf_raw_event_map *btp = raw_tp->btp; - err = bpf_task_fd_query_copy(attr, uattr, - raw_tp->prog->aux->id, - BPF_FD_TYPE_RAW_TRACEPOINT, - btp->tp->name, 0, 0); - goto put_file; + err = bpf_task_fd_query_copy(attr, uattr, + raw_tp->link.prog->aux->id, + BPF_FD_TYPE_RAW_TRACEPOINT, + btp->tp->name, 0, 0); + goto put_file; + } + goto out_not_supp; } event = perf_get_event(file); @@ -3290,10 +4451,10 @@ static int bpf_task_fd_query(const union bpf_attr *attr, goto put_file; } +out_not_supp: err = -ENOTSUPP; put_file: fput(file); -out: return err; } @@ -3312,6 +4473,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { + bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || + cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; + bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err, ufd; struct fd f; @@ -3324,16 +4488,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr, map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if ((cmd == BPF_MAP_LOOKUP_BATCH || - cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) && - !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { + if (has_write) + bpf_map_write_active_inc(map); + if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } - - if (cmd != BPF_MAP_LOOKUP_BATCH && - !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -3346,18 +4507,425 @@ static int bpf_map_do_batch(const union bpf_attr *attr, BPF_DO_BATCH(map->ops->map_update_batch); else BPF_DO_BATCH(map->ops->map_delete_batch); - err_put: + if (has_write) + bpf_map_write_active_dec(map); fdput(f); return err; } -SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) +#define BPF_LINK_CREATE_LAST_FIELD link_create.kprobe_multi.cookies +static int link_create(union bpf_attr *attr, bpfptr_t uattr) +{ + enum bpf_prog_type ptype; + struct bpf_prog *prog; + int ret; + + if (CHECK_ATTR(BPF_LINK_CREATE)) + return -EINVAL; + + prog = bpf_prog_get(attr->link_create.prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + ret = bpf_prog_attach_check_attach_type(prog, + attr->link_create.attach_type); + if (ret) + goto out; + + switch (prog->type) { + case BPF_PROG_TYPE_EXT: + break; + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_TRACEPOINT: + if (attr->link_create.attach_type != BPF_PERF_EVENT) { + ret = -EINVAL; + goto out; + } + break; + case BPF_PROG_TYPE_KPROBE: + if (attr->link_create.attach_type != BPF_PERF_EVENT && + attr->link_create.attach_type != BPF_TRACE_KPROBE_MULTI) { + ret = -EINVAL; + goto out; + } + break; + default: + ptype = attach_type_to_prog_type(attr->link_create.attach_type); + if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) { + ret = -EINVAL; + goto out; + } + break; + } + + switch (prog->type) { + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + ret = cgroup_bpf_link_attach(attr, prog); + break; + case BPF_PROG_TYPE_EXT: + ret = bpf_tracing_prog_attach(prog, + attr->link_create.target_fd, + attr->link_create.target_btf_id, + attr->link_create.tracing.cookie); + break; + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_TRACING: + if (attr->link_create.attach_type != prog->expected_attach_type) { + ret = -EINVAL; + goto out; + } + if (prog->expected_attach_type == BPF_TRACE_RAW_TP) + ret = bpf_raw_tp_link_attach(prog, NULL); + else if (prog->expected_attach_type == BPF_TRACE_ITER) + ret = bpf_iter_link_attach(attr, uattr, prog); + else if (prog->expected_attach_type == BPF_LSM_CGROUP) + ret = cgroup_bpf_link_attach(attr, prog); + else + ret = bpf_tracing_prog_attach(prog, + attr->link_create.target_fd, + attr->link_create.target_btf_id, + attr->link_create.tracing.cookie); + break; + case BPF_PROG_TYPE_FLOW_DISSECTOR: + case BPF_PROG_TYPE_SK_LOOKUP: + ret = netns_bpf_link_create(attr, prog); + break; +#ifdef CONFIG_NET + case BPF_PROG_TYPE_XDP: + ret = bpf_xdp_link_attach(attr, prog); + break; +#endif + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_TRACEPOINT: + ret = bpf_perf_link_attach(attr, prog); + break; + case BPF_PROG_TYPE_KPROBE: + if (attr->link_create.attach_type == BPF_PERF_EVENT) + ret = bpf_perf_link_attach(attr, prog); + else + ret = bpf_kprobe_multi_link_attach(attr, prog); + break; + default: + ret = -EINVAL; + } + +out: + if (ret < 0) + bpf_prog_put(prog); + return ret; +} + +#define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd + +static int link_update(union bpf_attr *attr) +{ + struct bpf_prog *old_prog = NULL, *new_prog; + struct bpf_link *link; + u32 flags; + int ret; + + if (CHECK_ATTR(BPF_LINK_UPDATE)) + return -EINVAL; + + flags = attr->link_update.flags; + if (flags & ~BPF_F_REPLACE) + return -EINVAL; + + link = bpf_link_get_from_fd(attr->link_update.link_fd); + if (IS_ERR(link)) + return PTR_ERR(link); + + new_prog = bpf_prog_get(attr->link_update.new_prog_fd); + if (IS_ERR(new_prog)) { + ret = PTR_ERR(new_prog); + goto out_put_link; + } + + if (flags & BPF_F_REPLACE) { + old_prog = bpf_prog_get(attr->link_update.old_prog_fd); + if (IS_ERR(old_prog)) { + ret = PTR_ERR(old_prog); + old_prog = NULL; + goto out_put_progs; + } + } else if (attr->link_update.old_prog_fd) { + ret = -EINVAL; + goto out_put_progs; + } + + if (link->ops->update_prog) + ret = link->ops->update_prog(link, new_prog, old_prog); + else + ret = -EINVAL; + +out_put_progs: + if (old_prog) + bpf_prog_put(old_prog); + if (ret) + bpf_prog_put(new_prog); +out_put_link: + bpf_link_put(link); + return ret; +} + +#define BPF_LINK_DETACH_LAST_FIELD link_detach.link_fd + +static int link_detach(union bpf_attr *attr) +{ + struct bpf_link *link; + int ret; + + if (CHECK_ATTR(BPF_LINK_DETACH)) + return -EINVAL; + + link = bpf_link_get_from_fd(attr->link_detach.link_fd); + if (IS_ERR(link)) + return PTR_ERR(link); + + if (link->ops->detach) + ret = link->ops->detach(link); + else + ret = -EOPNOTSUPP; + + bpf_link_put(link); + return ret; +} + +static struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) +{ + return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? link : ERR_PTR(-ENOENT); +} + +struct bpf_link *bpf_link_by_id(u32 id) +{ + struct bpf_link *link; + + if (!id) + return ERR_PTR(-ENOENT); + + spin_lock_bh(&link_idr_lock); + /* before link is "settled", ID is 0, pretend it doesn't exist yet */ + link = idr_find(&link_idr, id); + if (link) { + if (link->id) + link = bpf_link_inc_not_zero(link); + else + link = ERR_PTR(-EAGAIN); + } else { + link = ERR_PTR(-ENOENT); + } + spin_unlock_bh(&link_idr_lock); + return link; +} + +struct bpf_link *bpf_link_get_curr_or_next(u32 *id) +{ + struct bpf_link *link; + + spin_lock_bh(&link_idr_lock); +again: + link = idr_get_next(&link_idr, id); + if (link) { + link = bpf_link_inc_not_zero(link); + if (IS_ERR(link)) { + (*id)++; + goto again; + } + } + spin_unlock_bh(&link_idr_lock); + + return link; +} + +#define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id + +static int bpf_link_get_fd_by_id(const union bpf_attr *attr) +{ + struct bpf_link *link; + u32 id = attr->link_id; + int fd; + + if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + link = bpf_link_by_id(id); + if (IS_ERR(link)) + return PTR_ERR(link); + + fd = bpf_link_new_fd(link); + if (fd < 0) + bpf_link_put(link); + + return fd; +} + +DEFINE_MUTEX(bpf_stats_enabled_mutex); + +static int bpf_stats_release(struct inode *inode, struct file *file) +{ + mutex_lock(&bpf_stats_enabled_mutex); + static_key_slow_dec(&bpf_stats_enabled_key.key); + mutex_unlock(&bpf_stats_enabled_mutex); + return 0; +} + +static const struct file_operations bpf_stats_fops = { + .release = bpf_stats_release, +}; + +static int bpf_enable_runtime_stats(void) +{ + int fd; + + mutex_lock(&bpf_stats_enabled_mutex); + + /* Set a very high limit to avoid overflow */ + if (static_key_count(&bpf_stats_enabled_key.key) > INT_MAX / 2) { + mutex_unlock(&bpf_stats_enabled_mutex); + return -EBUSY; + } + + fd = anon_inode_getfd("bpf-stats", &bpf_stats_fops, NULL, O_CLOEXEC); + if (fd >= 0) + static_key_slow_inc(&bpf_stats_enabled_key.key); + + mutex_unlock(&bpf_stats_enabled_mutex); + return fd; +} + +#define BPF_ENABLE_STATS_LAST_FIELD enable_stats.type + +static int bpf_enable_stats(union bpf_attr *attr) +{ + + if (CHECK_ATTR(BPF_ENABLE_STATS)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + switch (attr->enable_stats.type) { + case BPF_STATS_RUN_TIME: + return bpf_enable_runtime_stats(); + default: + break; + } + return -EINVAL; +} + +#define BPF_ITER_CREATE_LAST_FIELD iter_create.flags + +static int bpf_iter_create(union bpf_attr *attr) +{ + struct bpf_link *link; + int err; + + if (CHECK_ATTR(BPF_ITER_CREATE)) + return -EINVAL; + + if (attr->iter_create.flags) + return -EINVAL; + + link = bpf_link_get_from_fd(attr->iter_create.link_fd); + if (IS_ERR(link)) + return PTR_ERR(link); + + err = bpf_iter_new_fd(link); + bpf_link_put(link); + + return err; +} + +#define BPF_PROG_BIND_MAP_LAST_FIELD prog_bind_map.flags + +static int bpf_prog_bind_map(union bpf_attr *attr) +{ + struct bpf_prog *prog; + struct bpf_map *map; + struct bpf_map **used_maps_old, **used_maps_new; + int i, ret = 0; + + if (CHECK_ATTR(BPF_PROG_BIND_MAP)) + return -EINVAL; + + if (attr->prog_bind_map.flags) + return -EINVAL; + + prog = bpf_prog_get(attr->prog_bind_map.prog_fd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + map = bpf_map_get(attr->prog_bind_map.map_fd); + if (IS_ERR(map)) { + ret = PTR_ERR(map); + goto out_prog_put; + } + + mutex_lock(&prog->aux->used_maps_mutex); + + used_maps_old = prog->aux->used_maps; + + for (i = 0; i < prog->aux->used_map_cnt; i++) + if (used_maps_old[i] == map) { + bpf_map_put(map); + goto out_unlock; + } + + used_maps_new = kmalloc_array(prog->aux->used_map_cnt + 1, + sizeof(used_maps_new[0]), + GFP_KERNEL); + if (!used_maps_new) { + ret = -ENOMEM; + goto out_unlock; + } + + memcpy(used_maps_new, used_maps_old, + sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); + used_maps_new[prog->aux->used_map_cnt] = map; + + prog->aux->used_map_cnt++; + prog->aux->used_maps = used_maps_new; + + kfree(used_maps_old); + +out_unlock: + mutex_unlock(&prog->aux->used_maps_mutex); + + if (ret) + bpf_map_put(map); +out_prog_put: + bpf_prog_put(prog); + return ret; +} + +static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { - union bpf_attr attr = {}; + union bpf_attr attr; + bool capable; int err; - if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN)) + capable = bpf_capable() || !sysctl_unprivileged_bpf_disabled; + + /* Intent here is for unprivileged_bpf_disabled to block key object + * creation commands for unprivileged users; other actions depend + * of fd availability and access to bpffs, so are dependent on + * object creation success. Capabilities are later verified for + * operations such as load and map create, so even with unprivileged + * BPF disabled, capability checks are still carried out for these + * and other operations. + */ + if (!capable && + (cmd == BPF_MAP_CREATE || cmd == BPF_PROG_LOAD)) return -EPERM; err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); @@ -3366,7 +4934,8 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz size = min_t(u32, size, sizeof(attr)); /* copy attributes from user space, may be less than sizeof(bpf_attr) */ - if (copy_from_user(&attr, uattr, size) != 0) + memset(&attr, 0, sizeof(attr)); + if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; err = security_bpf(cmd, &attr, size); @@ -3381,10 +4950,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = map_lookup_elem(&attr); break; case BPF_MAP_UPDATE_ELEM: - err = map_update_elem(&attr); + err = map_update_elem(&attr, uattr); break; case BPF_MAP_DELETE_ELEM: - err = map_delete_elem(&attr); + err = map_delete_elem(&attr, uattr); break; case BPF_MAP_GET_NEXT_KEY: err = map_get_next_key(&attr); @@ -3408,21 +4977,21 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_prog_detach(&attr); break; case BPF_PROG_QUERY: - err = bpf_prog_query(&attr, uattr); + err = bpf_prog_query(&attr, uattr.user); break; case BPF_PROG_TEST_RUN: - err = bpf_prog_test_run(&attr, uattr); + err = bpf_prog_test_run(&attr, uattr.user); break; case BPF_PROG_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &prog_idr, &prog_idr_lock); break; case BPF_MAP_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &map_idr, &map_idr_lock); break; case BPF_BTF_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &btf_idr, &btf_idr_lock); break; case BPF_PROG_GET_FD_BY_ID: @@ -3432,35 +5001,60 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_map_get_fd_by_id(&attr); break; case BPF_OBJ_GET_INFO_BY_FD: - err = bpf_obj_get_info_by_fd(&attr, uattr); + err = bpf_obj_get_info_by_fd(&attr, uattr.user); break; case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; case BPF_BTF_LOAD: - err = bpf_btf_load(&attr); + err = bpf_btf_load(&attr, uattr); break; case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); break; case BPF_TASK_FD_QUERY: - err = bpf_task_fd_query(&attr, uattr); + err = bpf_task_fd_query(&attr, uattr.user); break; case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; case BPF_MAP_LOOKUP_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH); break; case BPF_MAP_LOOKUP_AND_DELETE_BATCH: - err = bpf_map_do_batch(&attr, uattr, + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_AND_DELETE_BATCH); break; case BPF_MAP_UPDATE_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH); break; case BPF_MAP_DELETE_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH); + break; + case BPF_LINK_CREATE: + err = link_create(&attr, uattr); + break; + case BPF_LINK_UPDATE: + err = link_update(&attr); + break; + case BPF_LINK_GET_FD_BY_ID: + err = bpf_link_get_fd_by_id(&attr); + break; + case BPF_LINK_GET_NEXT_ID: + err = bpf_obj_get_next_id(&attr, uattr.user, + &link_idr, &link_idr_lock); + break; + case BPF_ENABLE_STATS: + err = bpf_enable_stats(&attr); + break; + case BPF_ITER_CREATE: + err = bpf_iter_create(&attr); + break; + case BPF_LINK_DETACH: + err = link_detach(&attr); + break; + case BPF_PROG_BIND_MAP: + err = bpf_prog_bind_map(&attr); break; default: err = -EINVAL; @@ -3469,3 +5063,258 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz return err; } + +SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) +{ + return __sys_bpf(cmd, USER_BPFPTR(uattr), size); +} + +static bool syscall_prog_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= U16_MAX) + return false; + if (off % size != 0) + return false; + return true; +} + +BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size) +{ + switch (cmd) { + case BPF_MAP_CREATE: + case BPF_MAP_DELETE_ELEM: + case BPF_MAP_UPDATE_ELEM: + case BPF_MAP_FREEZE: + case BPF_MAP_GET_FD_BY_ID: + case BPF_PROG_LOAD: + case BPF_BTF_LOAD: + case BPF_LINK_CREATE: + case BPF_RAW_TRACEPOINT_OPEN: + break; + default: + return -EINVAL; + } + return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size); +} + + +/* To shut up -Wmissing-prototypes. + * This function is used by the kernel light skeleton + * to load bpf programs when modules are loaded or during kernel boot. + * See tools/lib/bpf/skel_internal.h + */ +int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size); + +int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) +{ + struct bpf_prog * __maybe_unused prog; + struct bpf_tramp_run_ctx __maybe_unused run_ctx; + + switch (cmd) { +#ifdef CONFIG_BPF_JIT /* __bpf_prog_enter_sleepable used by trampoline and JIT */ + case BPF_PROG_TEST_RUN: + if (attr->test.data_in || attr->test.data_out || + attr->test.ctx_out || attr->test.duration || + attr->test.repeat || attr->test.flags) + return -EINVAL; + + prog = bpf_prog_get_type(attr->test.prog_fd, BPF_PROG_TYPE_SYSCALL); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + if (attr->test.ctx_size_in < prog->aux->max_ctx_offset || + attr->test.ctx_size_in > U16_MAX) { + bpf_prog_put(prog); + return -EINVAL; + } + + run_ctx.bpf_cookie = 0; + run_ctx.saved_run_ctx = NULL; + if (!__bpf_prog_enter_sleepable(prog, &run_ctx)) { + /* recursion detected */ + bpf_prog_put(prog); + return -EBUSY; + } + attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in); + __bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx); + bpf_prog_put(prog); + return 0; +#endif + default: + return ____bpf_sys_bpf(cmd, attr, size); + } +} +EXPORT_SYMBOL(kern_sys_bpf); + +static const struct bpf_func_proto bpf_sys_bpf_proto = { + .func = bpf_sys_bpf, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg3_type = ARG_CONST_SIZE, +}; + +const struct bpf_func_proto * __weak +tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return bpf_base_func_proto(func_id); +} + +BPF_CALL_1(bpf_sys_close, u32, fd) +{ + /* When bpf program calls this helper there should not be + * an fdget() without matching completed fdput(). + * This helper is allowed in the following callchain only: + * sys_bpf->prog_test_run->bpf_prog->bpf_sys_close + */ + return close_fd(fd); +} + +static const struct bpf_func_proto bpf_sys_close_proto = { + .func = bpf_sys_close, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) +{ + if (flags) + return -EINVAL; + + if (name_sz <= 1 || name[name_sz - 1]) + return -EINVAL; + + if (!bpf_dump_raw_ok(current_cred())) + return -EPERM; + + *res = kallsyms_lookup_name(name); + return *res ? 0 : -ENOENT; +} + +static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { + .func = bpf_kallsyms_lookup_name, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_LONG, +}; + +static const struct bpf_func_proto * +syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_sys_bpf: + return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto; + case BPF_FUNC_btf_find_by_name_kind: + return &bpf_btf_find_by_name_kind_proto; + case BPF_FUNC_sys_close: + return &bpf_sys_close_proto; + case BPF_FUNC_kallsyms_lookup_name: + return &bpf_kallsyms_lookup_name_proto; + default: + return tracing_prog_func_proto(func_id, prog); + } +} + +const struct bpf_verifier_ops bpf_syscall_verifier_ops = { + .get_func_proto = syscall_prog_func_proto, + .is_valid_access = syscall_prog_is_valid_access, +}; + +const struct bpf_prog_ops bpf_syscall_prog_ops = { + .test_run = bpf_prog_test_run_syscall, +}; + +#ifdef CONFIG_SYSCTL +static int bpf_stats_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct static_key *key = (struct static_key *)table->data; + static int saved_val; + int val, ret; + struct ctl_table tmp = { + .data = &val, + .maxlen = sizeof(val), + .mode = table->mode, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + mutex_lock(&bpf_stats_enabled_mutex); + val = saved_val; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret && val != saved_val) { + if (val) + static_key_slow_inc(key); + else + static_key_slow_dec(key); + saved_val = val; + } + mutex_unlock(&bpf_stats_enabled_mutex); + return ret; +} + +void __weak unpriv_ebpf_notify(int new_state) +{ +} + +static int bpf_unpriv_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, unpriv_enable = *(int *)table->data; + bool locked_state = unpriv_enable == 1; + struct ctl_table tmp = *table; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + tmp.data = &unpriv_enable; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret) { + if (locked_state && unpriv_enable != 1) + return -EPERM; + *(int *)table->data = unpriv_enable; + } + + unpriv_ebpf_notify(unpriv_enable); + + return ret; +} + +static struct ctl_table bpf_syscall_table[] = { + { + .procname = "unprivileged_bpf_disabled", + .data = &sysctl_unprivileged_bpf_disabled, + .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), + .mode = 0644, + .proc_handler = bpf_unpriv_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { + .procname = "bpf_stats_enabled", + .data = &bpf_stats_enabled_key.key, + .maxlen = sizeof(bpf_stats_enabled_key), + .mode = 0644, + .proc_handler = bpf_stats_handler, + }, + { } +}; + +static int __init bpf_syscall_sysctl_init(void) +{ + register_sysctl_init("kernel", bpf_syscall_table); + return 0; +} +late_initcall(bpf_syscall_sysctl_init); +#endif /* CONFIG_SYSCTL */ |