cregit-Linux how code gets into the kernel

Release 4.15 kernel/bpf/syscall.c

Directory: kernel/bpf
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 */
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/sched/signal.h>
#include <linux/vmalloc.h>
#include <linux/mmzone.h>
#include <linux/anon_inodes.h>
#include <linux/file.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>
#include <linux/timekeeping.h>
#include <linux/ctype.h>


#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
                           (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
                           (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
                           (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)

#define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)

#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map))


#define BPF_OBJ_FLAG_MASK   (BPF_F_RDONLY | BPF_F_WRONLY)

DEFINE_PER_CPU(int, bpf_prog_active);
static DEFINE_IDR(prog_idr);
static DEFINE_SPINLOCK(prog_idr_lock);
static DEFINE_IDR(map_idr);
static DEFINE_SPINLOCK(map_idr_lock);


int sysctl_unprivileged_bpf_disabled __read_mostly;


static const struct bpf_map_ops * const bpf_map_types[] = {

#define BPF_PROG_TYPE(_id, _ops)

#define BPF_MAP_TYPE(_id, _ops) \
	[_id] = &_ops,
#include <linux/bpf_types.h>

#undef BPF_PROG_TYPE

#undef BPF_MAP_TYPE
};

/*
 * If we're handed a bigger struct than we know of, ensure all the unknown bits
 * are 0 - i.e. new user-space does not rely on any kernel feature extensions
 * we don't know about yet.
 *
 * There is a ToCToU between this function call and the following
 * copy_from_user() call. However, this is not a concern since this function is
 * meant to be a future-proofing of bits.
 */

static int check_uarg_tail_zero(void __user *uaddr, size_t expected_size, size_t actual_size) { unsigned char __user *addr; unsigned char __user *end; unsigned char val; int err; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; if (unlikely(!access_ok(VERIFY_READ, 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; }

Contributors

PersonTokensPropCommitsCommitProp
Mickaël Salaün129100.00%2100.00%
Total129100.00%2100.00%


static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) { struct bpf_map *map; if (attr->map_type >= ARRAY_SIZE(bpf_map_types) || !bpf_map_types[attr->map_type]) return ERR_PTR(-EINVAL); map = bpf_map_types[attr->map_type]->map_alloc(attr); if (IS_ERR(map)) return map; map->ops = bpf_map_types[attr->map_type]; map->map_type = attr->map_type; return map; }

Contributors

PersonTokensPropCommitsCommitProp
Alexei Starovoitov6167.78%150.00%
Johannes Berg2932.22%150.00%
Total90100.00%2100.00%


void *bpf_map_area_alloc(size_t size, int numa_node) { /* We definitely need __GFP_NORETRY, so OOM killer doesn't * trigger under memory pressure as we really just want to * fail instead. */ const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO; void *area; if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, GFP_USER | flags, numa_node); if (area != NULL) return area; } return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | flags, __builtin_return_address(0)); }

Contributors

PersonTokensPropCommitsCommitProp
Daniel Borkmann6583.33%150.00%
Martin KaFai Lau1316.67%150.00%
Total78100.00%2100.00%


void bpf_map_area_free(void *area) { kvfree(area); }

Contributors

PersonTokensPropCommitsCommitProp
Daniel Borkmann14100.00%1100.00%
Total14100.00%1100.00%


int bpf_map_precharge_memlock(u32 pages) { struct user_struct *user = get_current_user(); unsigned long memlock_limit, cur; memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; cur = atomic_long_read(&user->locked_vm); free_uid(user); if (cur + pages > memlock_limit) return -EPERM; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Alexei Starovoitov61100.00%1100.00%
Total61100.00%1100.00%


static int bpf_map_charge_memlock(struct bpf_map *map) { struct user_struct *user = get_current_user(); unsigned long memlock_limit; memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; atomic_long_add(map->pages, &user->locked_vm); if (atomic_long_read(&user->locked_vm) > memlock_limit) { atomic_long_sub(map->pages, &user->locked_vm); free_uid(user); return -EPERM; } map->user = user; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Alexei Starovoitov88100.00%1100.00%
Total88100.00%1100.00%


static void bpf_map_uncharge_memlock(struct bpf_map *map) { struct user_struct *user = map->user; atomic_long_sub(map->pages, &user->locked_vm); free_uid(user); }

Contributors

PersonTokensPropCommitsCommitProp
Alexei Starovoitov37100.00%1100.00%
Total37100.00%1100.00%


static int bpf_map_alloc_id(struct bpf_map *map) { int id; spin_lock_bh(&map_idr_lock); id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); if (id > 0) map->id = id; spin_unlock_bh(&map_idr_lock); if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; }

Contributors

PersonTokensPropCommitsCommitProp
Martin KaFai Lau75100.00%1100.00%
Total75100.00%1100.00%


static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) { unsigned long flags; if (do_idr_lock) spin_lock_irqsave(&map_idr_lock, flags); else __acquire(&map_idr_lock); idr_remove(&map_idr, map->id); if (do_idr_lock) spin_unlock_irqrestore(&map_idr_lock, flags); else __release(&map_idr_lock); }

Contributors

PersonTokensPropCommitsCommitProp
Martin KaFai Lau5684.85%266.67%
Eric Dumazet1015.15%133.33%
Total66100.00%3100.00%

/* called from workqueue */
static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); bpf_map_uncharge_memlock(map); security_bpf_map_free(map); /* implementation dependent freeing */ map->ops->map_free(map); }

Contributors

PersonTokensPropCommitsCommitProp
Alexei Starovoitov4189.13%266.67%
Chenbo Feng510.87%133.33%
Total46100.00%3100.00%


static void bpf_map_put_uref(struct bpf_map *map) { if (atomic_dec_and_test(&map->usercnt)) { if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) bpf_fd_array_map_clear(map); } }

Contributors

PersonTokensPropCommitsCommitProp
Daniel Borkmann36100.00%1100.00%
Total36100.00%1100.00%

/* decrement map refcnt and schedule it for freeing via workqueue * (unrelying map implementation ops->map_free() might sleep) */
static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) { if (atomic_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ bpf_map_free_id(map, do_idr_lock); INIT_WORK(&map->work, bpf_map_free_deferred); schedule_work(&map->work); } }

Contributors

PersonTokensPropCommitsCommitProp
Alexei Starovoitov3975.00%125.00%
Martin KaFai Lau1325.00%375.00%
Total52100.00%4100.00%


void bpf_map_put(struct bpf_map *map) { __bpf_map_put(map, true); }

Contributors

PersonTokensPropCommitsCommitProp
Martin KaFai Lau17100.00%1100.00%
Total17100.00%1100.00%


void bpf_map_put_with_uref(struct bpf_map *map) { bpf_map_put_uref(map); bpf_map_put(map); }

Contributors

PersonTokensPropCommitsCommitProp
Daniel Borkmann20100.00%1100.00%
Total20100.00%1100.00%


static int bpf_map_release(struct inode *inode, struct file *filp) { struct bpf_map *map = filp->private_data; if (map->ops->map_release) map->ops->map_release(map, filp); bpf_map_put_with_uref(map); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Daniel Borkmann2853.85%150.00%
Alexei Starovoitov2446.15%150.00%
Total52100.00%2100.00%

#ifdef CONFIG_PROC_FS
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; u32 owner_prog_type = 0; u32 owner_jited = 0; if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) { array = container_of(map, struct bpf_array, map); owner_prog_type = array->owner_prog_type; owner_jited = array->owner_jited; } seq_printf(m, "map_type:\t%u\n" "key_size:\t%u\n" "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" "memlock:\t%llu\n", map->map_type, map->key_size, map->value_size, map->max_entries, map->map_flags, map->pages * 1ULL << PAGE_SHIFT); if (owner_prog_type) { seq_printf(m, "owner_prog_type:\t%u\n", owner_prog_type); seq_printf(m, "owner_jited:\t%u\n", owner_jited); } }

Contributors

PersonTokensPropCommitsCommitProp
Daniel Borkmann140100.00%4100.00%
Total140100.00%4100.00%

#endif
static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_READ. */ return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Chenbo Feng28100.00%1100.00%
Total28100.00%1100.00%


static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_WRITE. */ return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
Chenbo Feng29100.00%1100.00%
Total29100.00%1100.00%

const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, .read = bpf_dummy_read, .write = bpf_dummy_write, };
int bpf_map_new_fd(struct bpf_map *map, int flags) { int ret; ret = security_bpf_map(map, OPEN_FMODE(flags)); if (ret < 0) return ret; return anon_inode_getfd("bpf-map", &bpf_map_fops, map, flags | O_CLOEXEC); }

Contributors

PersonTokensPropCommitsCommitProp
Chenbo Feng2853.85%266.67%
Daniel Borkmann2446.15%133.33%
Total52100.00%3100.00%


int bpf_get_file_flag(int flags) { if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) return -EINVAL; if (flags & BPF_F_RDONLY) return O_RDONLY; if (flags & BPF_F_WRONLY) return O_WRONLY; return O_RDWR; }

Contributors

PersonTokensPropCommitsCommitProp
Chenbo Feng47100.00%1100.00%
Total47100.00%1100.00%

/* helper macro to check that unused fields 'union bpf_attr' are zero */ #define CHECK_ATTR(CMD) \ memchr_inv((void *) &attr->CMD##_LAST_FIELD + \ sizeof(attr->CMD##_LAST_FIELD), 0, \ sizeof(*attr) - \ 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. */
static int bpf_obj_name_cpy(char *dst, const char *src) { const char *end = src + BPF_OBJ_NAME_LEN; memset(dst, 0, BPF_OBJ_NAME_LEN); /* Copy all isalnum() and '_' char */ while (src < end && *src) { if (!isalnum(*src) && *src != '_') return -EINVAL; *dst++ = *src++; } /* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */ if (src == end) return -EINVAL; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Martin KaFai Lau85100.00%2100.00%
Total85100.00%2100.00%

#define BPF_MAP_CREATE_LAST_FIELD map_name /* called via syscall */
static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct bpf_map *map; int f_flags; int err; err = CHECK_ATTR(BPF_MAP_CREATE); if (err) return -EINVAL; f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) return -EINVAL; /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ map = find_and_alloc_map(attr); if (IS_ERR(map)) return PTR_ERR(map); err = bpf_obj_name_cpy(map->name, attr->map_name); if (err) goto free_map_nouncharge; atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); err = security_bpf_map_alloc(map); if (err) goto free_map_nouncharge; err = bpf_map_charge_memlock(map); if (err) goto free_map_sec; err = bpf_map_alloc_id(map); if (err) goto free_map; err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. * bpf_map_put() is needed because the above * bpf_map_alloc_id() has published the map * to the userspace and the userspace may * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. */ bpf_map_put(map); return err; } trace_bpf_map_create(map, err); return err; free_map: bpf_map_uncharge_memlock(map); free_map_sec: security_bpf_map_free(map); free_map_nouncharge: map->ops->map_free(map); return err; }

Contributors

PersonTokensPropCommitsCommitProp
Alexei Starovoitov10641.41%215.38%
Martin KaFai Lau7830.47%430.77%
Chenbo Feng4517.58%215.38%
Daniel Borkmann238.98%430.77%
Eric Dumazet41.56%17.69%
Total256100.00%13100.00%

/* if error is returned, fd is released. * On success caller should complete fd access with matching fdput() */
struct bpf_map *__bpf_map_get(struct fd f) { if (!f.file) return ERR_PTR(-EBADF); if (f.file->f_op != &bpf_map_fops) { fdput(f); return ERR_PTR(-EINVAL); } return f.file->private_data; }

Contributors

PersonTokensPropCommitsCommitProp
Alexei Starovoitov5392.98%266.67%
Daniel Borkmann47.02%133.33%
Total57100.00%3100.00%

/* prog's and map's refcnt limit */ #define BPF_MAX_REFCNT 32768
struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref) { if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) { atomic_dec(&map->refcnt); return ERR_PTR(-EBUSY); } if (uref) atomic_inc(&map->usercnt); return map; }

Contributors

PersonTokensPropCommitsCommitProp
Daniel Borkmann3152.54%266.67%
Alexei Starovoitov2847.46%133.33%
Total59100.00%3100.00%


struct bpf_map *bpf_map_get_with_uref(u32 ufd) { struct fd f = fdget(ufd); struct bpf_map *map; map = __bpf_map_get(f); if (IS_ERR(map)) return map; map = bpf_map_inc(map, true); fdput(f); return map; }

Contributors

PersonTokensPropCommitsCommitProp
Daniel Borkmann5187.93%240.00%
Alexei Starovoitov712.07%360.00%
Total58100.00%5100.00%

/* map_idr_lock should have been held */
static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, bool uref) { int refold; refold = __atomic_add_unless(&map->refcnt, 1, 0); if (refold >= BPF_MAX_REFCNT) { __bpf_map_put(map, false); return ERR_PTR(-EBUSY); } if (!refold) return ERR_PTR(-ENOENT); if (uref) atomic_inc(&map->usercnt); return map; }

Contributors

PersonTokensPropCommitsCommitProp
Martin KaFai Lau82100.00%1100.00%
Total82100.00%1100.00%


int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { return -ENOTSUPP; }

Contributors

PersonTokensPropCommitsCommitProp
Alexei Starovoitov23100.00%1100.00%
Total23100.00%1100.00%

/* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value
static int map_lookup_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); int ufd = attr->map_fd; struct bpf_map *map; void *key, *value, *ptr; u32 value_size; struct fd f; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) return -EINVAL; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(f.file->f_mode & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } key = memdup_user(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) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else if (IS_FD_MAP(map)) value_size = sizeof(u32); else value_size = map->value_size; err = -ENOMEM; value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); } else if (IS_FD_ARRAY(map)) { err = bpf_fd_array_map_lookup_elem(map, key, value); } else if (IS_FD_HASH(map)) { err = bpf_fd_htab_map_lookup_elem(map, key, value); } else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); if (ptr) memcpy(value, ptr, value_size); rcu_read_unlock(); err = ptr ? 0 : -ENOENT; } if (err) goto free_value; err = -EFAULT; if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; trace_bpf_map_lookup_elem(map, ufd, key, value); err = 0; free_value: kfree(value); free_key: kfree(key); err_put: fdput(f); return err; }

Contributors

PersonTokensPropCommitsCommitProp
Alexei Starovoitov33472.29%637.50%
Martin KaFai Lau6914.94%425.00%
Chenbo Feng234.98%16.25%
Daniel Borkmann234.98%318.75%
Al Viro112.38%16.25%
Mickaël Salaün20.43%16.25%
Total462100.00%16100.00%

#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
static int map_update_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; u32 value_size; struct fd f; int err; if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) return -EINVAL; f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(f.file->f_mode & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } key = memdup_user(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) 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) goto free_key; err = -EFAULT; if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; /* Need to create a kthread, thus must support schedule */ if (map->map_type == BPF_MAP_TYPE_CPUMAP) { err = map->ops->map_update_elem(map, key, value, attr->flags); goto out; } /* 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); 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, attr->flags);