p71924506
/
linux_old1
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
linux_old1/kernel/bpf/syscall.c

617 lines
13 KiB
C
Raw Normal View History

bpf: introduce BPF syscall and maps BPF syscall is a multiplexor for a range of different operations on eBPF. This patch introduces syscall with single command to create a map. Next patch adds commands to access maps. 'maps' is a generic storage of different types for sharing data between kernel and userspace. Userspace example: /* this syscall wrapper creates a map with given type and attributes * and returns map_fd on success. * use close(map_fd) to delete the map */ int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries) { union bpf_attr attr = { .map_type = map_type, .key_size = key_size, .value_size = value_size, .max_entries = max_entries }; return bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } 'union bpf_attr' is backwards compatible with future extensions. More details in Documentation/networking/filter.txt and in manpage Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:57 +08:00
/* 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/syscalls.h>
#include <linux/slab.h>
#include <linux/anon_inodes.h>
bpf: add lookup/update/delete/iterate methods to BPF maps 'maps' is a generic storage of different types for sharing data between kernel and userspace. The maps are accessed from user space via BPF syscall, which has commands: - create a map with given type and attributes fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size) returns fd or negative error - lookup key in a given map referenced by fd err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero and stores found elem into value or negative error - create or update key/value pair in a given map err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero or negative error - find and delete element by key in a given map err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key - iterate map elements (based on input key return next_key) err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->next_key - close(fd) deletes the map Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:59 +08:00
#include <linux/file.h>
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
#include <linux/license.h>
#include <linux/filter.h>
bpf: introduce BPF syscall and maps BPF syscall is a multiplexor for a range of different operations on eBPF. This patch introduces syscall with single command to create a map. Next patch adds commands to access maps. 'maps' is a generic storage of different types for sharing data between kernel and userspace. Userspace example: /* this syscall wrapper creates a map with given type and attributes * and returns map_fd on success. * use close(map_fd) to delete the map */ int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries) { union bpf_attr attr = { .map_type = map_type, .key_size = key_size, .value_size = value_size, .max_entries = max_entries }; return bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } 'union bpf_attr' is backwards compatible with future extensions. More details in Documentation/networking/filter.txt and in manpage Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:57 +08:00
static LIST_HEAD(bpf_map_types);
static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
{
struct bpf_map_type_list *tl;
struct bpf_map *map;
list_for_each_entry(tl, &bpf_map_types, list_node) {
if (tl->type == attr->map_type) {
map = tl->ops->map_alloc(attr);
if (IS_ERR(map))
return map;
map->ops = tl->ops;
map->map_type = attr->map_type;
return map;
}
}
return ERR_PTR(-EINVAL);
}
/* boot time registration of different map implementations */
void bpf_register_map_type(struct bpf_map_type_list *tl)
{
list_add(&tl->list_node, &bpf_map_types);
}
/* called from workqueue */
static void bpf_map_free_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_map, work);
/* implementation dependent freeing */
map->ops->map_free(map);
}
/* decrement map refcnt and schedule it for freeing via workqueue
* (unrelying map implementation ops->map_free() might sleep)
*/
void bpf_map_put(struct bpf_map *map)
{
if (atomic_dec_and_test(&map->refcnt)) {
INIT_WORK(&map->work, bpf_map_free_deferred);
schedule_work(&map->work);
}
}
static int bpf_map_release(struct inode *inode, struct file *filp)
{
struct bpf_map *map = filp->private_data;
bpf_map_put(map);
return 0;
}
static const struct file_operations bpf_map_fops = {
.release = bpf_map_release,
};
/* 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
#define BPF_MAP_CREATE_LAST_FIELD max_entries
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
struct bpf_map *map;
int err;
err = CHECK_ATTR(BPF_MAP_CREATE);
if (err)
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);
atomic_set(&map->refcnt, 1);
err = anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC);
if (err < 0)
/* failed to allocate fd */
goto free_map;
return err;
free_map:
map->ops->map_free(map);
return err;
}
bpf: add lookup/update/delete/iterate methods to BPF maps 'maps' is a generic storage of different types for sharing data between kernel and userspace. The maps are accessed from user space via BPF syscall, which has commands: - create a map with given type and attributes fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size) returns fd or negative error - lookup key in a given map referenced by fd err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero and stores found elem into value or negative error - create or update key/value pair in a given map err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero or negative error - find and delete element by key in a given map err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key - iterate map elements (based on input key return next_key) err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->next_key - close(fd) deletes the map Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:59 +08:00
/* 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)
{
struct bpf_map *map;
if (!f.file)
return ERR_PTR(-EBADF);
if (f.file->f_op != &bpf_map_fops) {
fdput(f);
return ERR_PTR(-EINVAL);
}
map = f.file->private_data;
return map;
}
/* helper to convert user pointers passed inside __aligned_u64 fields */
static void __user *u64_to_ptr(__u64 val)
{
return (void __user *) (unsigned long) val;
}
/* 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_ptr(attr->key);
void __user *uvalue = u64_to_ptr(attr->value);
int ufd = attr->map_fd;
struct fd f = fdget(ufd);
struct bpf_map *map;
bpf: rcu lock must not be held when calling copy_to_user() BUG: sleeping function called from invalid context at mm/memory.c:3732 in_atomic(): 0, irqs_disabled(): 0, pid: 671, name: test_maps 1 lock held by test_maps/671: #0: (rcu_read_lock){......}, at: [<0000000000264190>] map_lookup_elem+0xe8/0x260 Call Trace: ([<0000000000115b7e>] show_trace+0x12e/0x150) [<0000000000115c40>] show_stack+0xa0/0x100 [<00000000009b163c>] dump_stack+0x74/0xc8 [<000000000017424a>] ___might_sleep+0x23a/0x248 [<00000000002b58e8>] might_fault+0x70/0xe8 [<0000000000264230>] map_lookup_elem+0x188/0x260 [<0000000000264716>] SyS_bpf+0x20e/0x840 Fix it by allocating temporary buffer to store map element value. Fixes: db20fd2b0108 ("bpf: add lookup/update/delete/iterate methods to BPF maps") Reported-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-23 09:11:08 +08:00
void *key, *value, *ptr;
bpf: add lookup/update/delete/iterate methods to BPF maps 'maps' is a generic storage of different types for sharing data between kernel and userspace. The maps are accessed from user space via BPF syscall, which has commands: - create a map with given type and attributes fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size) returns fd or negative error - lookup key in a given map referenced by fd err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero and stores found elem into value or negative error - create or update key/value pair in a given map err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero or negative error - find and delete element by key in a given map err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key - iterate map elements (based on input key return next_key) err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->next_key - close(fd) deletes the map Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:59 +08:00
int err;
if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
return -EINVAL;
map = bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
goto err_put;
err = -EFAULT;
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
bpf: rcu lock must not be held when calling copy_to_user() BUG: sleeping function called from invalid context at mm/memory.c:3732 in_atomic(): 0, irqs_disabled(): 0, pid: 671, name: test_maps 1 lock held by test_maps/671: #0: (rcu_read_lock){......}, at: [<0000000000264190>] map_lookup_elem+0xe8/0x260 Call Trace: ([<0000000000115b7e>] show_trace+0x12e/0x150) [<0000000000115c40>] show_stack+0xa0/0x100 [<00000000009b163c>] dump_stack+0x74/0xc8 [<000000000017424a>] ___might_sleep+0x23a/0x248 [<00000000002b58e8>] might_fault+0x70/0xe8 [<0000000000264230>] map_lookup_elem+0x188/0x260 [<0000000000264716>] SyS_bpf+0x20e/0x840 Fix it by allocating temporary buffer to store map element value. Fixes: db20fd2b0108 ("bpf: add lookup/update/delete/iterate methods to BPF maps") Reported-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-23 09:11:08 +08:00
err = -ENOMEM;
value = kmalloc(map->value_size, GFP_USER);
bpf: add lookup/update/delete/iterate methods to BPF maps 'maps' is a generic storage of different types for sharing data between kernel and userspace. The maps are accessed from user space via BPF syscall, which has commands: - create a map with given type and attributes fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size) returns fd or negative error - lookup key in a given map referenced by fd err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero and stores found elem into value or negative error - create or update key/value pair in a given map err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero or negative error - find and delete element by key in a given map err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key - iterate map elements (based on input key return next_key) err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->next_key - close(fd) deletes the map Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:59 +08:00
if (!value)
bpf: rcu lock must not be held when calling copy_to_user() BUG: sleeping function called from invalid context at mm/memory.c:3732 in_atomic(): 0, irqs_disabled(): 0, pid: 671, name: test_maps 1 lock held by test_maps/671: #0: (rcu_read_lock){......}, at: [<0000000000264190>] map_lookup_elem+0xe8/0x260 Call Trace: ([<0000000000115b7e>] show_trace+0x12e/0x150) [<0000000000115c40>] show_stack+0xa0/0x100 [<00000000009b163c>] dump_stack+0x74/0xc8 [<000000000017424a>] ___might_sleep+0x23a/0x248 [<00000000002b58e8>] might_fault+0x70/0xe8 [<0000000000264230>] map_lookup_elem+0x188/0x260 [<0000000000264716>] SyS_bpf+0x20e/0x840 Fix it by allocating temporary buffer to store map element value. Fixes: db20fd2b0108 ("bpf: add lookup/update/delete/iterate methods to BPF maps") Reported-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-23 09:11:08 +08:00
goto free_key;
rcu_read_lock();
ptr = map->ops->map_lookup_elem(map, key);
if (ptr)
memcpy(value, ptr, map->value_size);
rcu_read_unlock();
err = -ENOENT;
if (!ptr)
goto free_value;
bpf: add lookup/update/delete/iterate methods to BPF maps 'maps' is a generic storage of different types for sharing data between kernel and userspace. The maps are accessed from user space via BPF syscall, which has commands: - create a map with given type and attributes fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size) returns fd or negative error - lookup key in a given map referenced by fd err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero and stores found elem into value or negative error - create or update key/value pair in a given map err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero or negative error - find and delete element by key in a given map err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key - iterate map elements (based on input key return next_key) err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->next_key - close(fd) deletes the map Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:59 +08:00
err = -EFAULT;
if (copy_to_user(uvalue, value, map->value_size) != 0)
bpf: rcu lock must not be held when calling copy_to_user() BUG: sleeping function called from invalid context at mm/memory.c:3732 in_atomic(): 0, irqs_disabled(): 0, pid: 671, name: test_maps 1 lock held by test_maps/671: #0: (rcu_read_lock){......}, at: [<0000000000264190>] map_lookup_elem+0xe8/0x260 Call Trace: ([<0000000000115b7e>] show_trace+0x12e/0x150) [<0000000000115c40>] show_stack+0xa0/0x100 [<00000000009b163c>] dump_stack+0x74/0xc8 [<000000000017424a>] ___might_sleep+0x23a/0x248 [<00000000002b58e8>] might_fault+0x70/0xe8 [<0000000000264230>] map_lookup_elem+0x188/0x260 [<0000000000264716>] SyS_bpf+0x20e/0x840 Fix it by allocating temporary buffer to store map element value. Fixes: db20fd2b0108 ("bpf: add lookup/update/delete/iterate methods to BPF maps") Reported-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-23 09:11:08 +08:00
goto free_value;
bpf: add lookup/update/delete/iterate methods to BPF maps 'maps' is a generic storage of different types for sharing data between kernel and userspace. The maps are accessed from user space via BPF syscall, which has commands: - create a map with given type and attributes fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size) returns fd or negative error - lookup key in a given map referenced by fd err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero and stores found elem into value or negative error - create or update key/value pair in a given map err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero or negative error - find and delete element by key in a given map err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key - iterate map elements (based on input key return next_key) err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->next_key - close(fd) deletes the map Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:59 +08:00
err = 0;
bpf: rcu lock must not be held when calling copy_to_user() BUG: sleeping function called from invalid context at mm/memory.c:3732 in_atomic(): 0, irqs_disabled(): 0, pid: 671, name: test_maps 1 lock held by test_maps/671: #0: (rcu_read_lock){......}, at: [<0000000000264190>] map_lookup_elem+0xe8/0x260 Call Trace: ([<0000000000115b7e>] show_trace+0x12e/0x150) [<0000000000115c40>] show_stack+0xa0/0x100 [<00000000009b163c>] dump_stack+0x74/0xc8 [<000000000017424a>] ___might_sleep+0x23a/0x248 [<00000000002b58e8>] might_fault+0x70/0xe8 [<0000000000264230>] map_lookup_elem+0x188/0x260 [<0000000000264716>] SyS_bpf+0x20e/0x840 Fix it by allocating temporary buffer to store map element value. Fixes: db20fd2b0108 ("bpf: add lookup/update/delete/iterate methods to BPF maps") Reported-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-23 09:11:08 +08:00
free_value:
kfree(value);
bpf: add lookup/update/delete/iterate methods to BPF maps 'maps' is a generic storage of different types for sharing data between kernel and userspace. The maps are accessed from user space via BPF syscall, which has commands: - create a map with given type and attributes fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size) returns fd or negative error - lookup key in a given map referenced by fd err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero and stores found elem into value or negative error - create or update key/value pair in a given map err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero or negative error - find and delete element by key in a given map err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key - iterate map elements (based on input key return next_key) err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->next_key - close(fd) deletes the map Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:59 +08:00
free_key:
kfree(key);
err_put:
fdput(f);
return err;
}
bpf: add 'flags' attribute to BPF_MAP_UPDATE_ELEM command the current meaning of BPF_MAP_UPDATE_ELEM syscall command is: either update existing map element or create a new one. Initially the plan was to add a new command to handle the case of 'create new element if it didn't exist', but 'flags' style looks cleaner and overall diff is much smaller (more code reused), so add 'flags' attribute to BPF_MAP_UPDATE_ELEM command with the following meaning: #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ bpf_update_elem(fd, key, value, BPF_NOEXIST) call can fail with EEXIST if element already exists. bpf_update_elem(fd, key, value, BPF_EXIST) can fail with ENOENT if element doesn't exist. Userspace will call it as: int bpf_update_elem(int fd, void *key, void *value, __u64 flags) { union bpf_attr attr = { .map_fd = fd, .key = ptr_to_u64(key), .value = ptr_to_u64(value), .flags = flags; }; return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); } First two bits of 'flags' are used to encode style of bpf_update_elem() command. Bits 2-63 are reserved for future use. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-14 09:36:44 +08:00
#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
bpf: add lookup/update/delete/iterate methods to BPF maps 'maps' is a generic storage of different types for sharing data between kernel and userspace. The maps are accessed from user space via BPF syscall, which has commands: - create a map with given type and attributes fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size) returns fd or negative error - lookup key in a given map referenced by fd err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero and stores found elem into value or negative error - create or update key/value pair in a given map err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero or negative error - find and delete element by key in a given map err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key - iterate map elements (based on input key return next_key) err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->next_key - close(fd) deletes the map Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:59 +08:00
static int map_update_elem(union bpf_attr *attr)
{
void __user *ukey = u64_to_ptr(attr->key);
void __user *uvalue = u64_to_ptr(attr->value);
int ufd = attr->map_fd;
struct fd f = fdget(ufd);
struct bpf_map *map;
void *key, *value;
int err;
if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM))
return -EINVAL;
map = bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
goto err_put;
err = -EFAULT;
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
err = -ENOMEM;
value = kmalloc(map->value_size, GFP_USER);
if (!value)
goto free_key;
err = -EFAULT;
if (copy_from_user(value, uvalue, map->value_size) != 0)
goto free_value;
/* eBPF program that use maps are running under rcu_read_lock(),
* therefore all map accessors rely on this fact, so do the same here
*/
rcu_read_lock();
bpf: add 'flags' attribute to BPF_MAP_UPDATE_ELEM command the current meaning of BPF_MAP_UPDATE_ELEM syscall command is: either update existing map element or create a new one. Initially the plan was to add a new command to handle the case of 'create new element if it didn't exist', but 'flags' style looks cleaner and overall diff is much smaller (more code reused), so add 'flags' attribute to BPF_MAP_UPDATE_ELEM command with the following meaning: #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ bpf_update_elem(fd, key, value, BPF_NOEXIST) call can fail with EEXIST if element already exists. bpf_update_elem(fd, key, value, BPF_EXIST) can fail with ENOENT if element doesn't exist. Userspace will call it as: int bpf_update_elem(int fd, void *key, void *value, __u64 flags) { union bpf_attr attr = { .map_fd = fd, .key = ptr_to_u64(key), .value = ptr_to_u64(value), .flags = flags; }; return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); } First two bits of 'flags' are used to encode style of bpf_update_elem() command. Bits 2-63 are reserved for future use. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-14 09:36:44 +08:00
err = map->ops->map_update_elem(map, key, value, attr->flags);
bpf: add lookup/update/delete/iterate methods to BPF maps 'maps' is a generic storage of different types for sharing data between kernel and userspace. The maps are accessed from user space via BPF syscall, which has commands: - create a map with given type and attributes fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size) returns fd or negative error - lookup key in a given map referenced by fd err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero and stores found elem into value or negative error - create or update key/value pair in a given map err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero or negative error - find and delete element by key in a given map err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key - iterate map elements (based on input key return next_key) err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->next_key - close(fd) deletes the map Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:59 +08:00
rcu_read_unlock();
free_value:
kfree(value);
free_key:
kfree(key);
err_put:
fdput(f);
return err;
}
#define BPF_MAP_DELETE_ELEM_LAST_FIELD key
static int map_delete_elem(union bpf_attr *attr)
{
void __user *ukey = u64_to_ptr(attr->key);
int ufd = attr->map_fd;
struct fd f = fdget(ufd);
struct bpf_map *map;
void *key;
int err;
if (CHECK_ATTR(BPF_MAP_DELETE_ELEM))
return -EINVAL;
map = bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
goto err_put;
err = -EFAULT;
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
rcu_read_lock();
err = map->ops->map_delete_elem(map, key);
rcu_read_unlock();
free_key:
kfree(key);
err_put:
fdput(f);
return err;
}
/* last field in 'union bpf_attr' used by this command */
#define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key
static int map_get_next_key(union bpf_attr *attr)
{
void __user *ukey = u64_to_ptr(attr->key);
void __user *unext_key = u64_to_ptr(attr->next_key);
int ufd = attr->map_fd;
struct fd f = fdget(ufd);
struct bpf_map *map;
void *key, *next_key;
int err;
if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY))
return -EINVAL;
map = bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
err = -ENOMEM;
key = kmalloc(map->key_size, GFP_USER);
if (!key)
goto err_put;
err = -EFAULT;
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
err = -ENOMEM;
next_key = kmalloc(map->key_size, GFP_USER);
if (!next_key)
goto free_key;
rcu_read_lock();
err = map->ops->map_get_next_key(map, key, next_key);
rcu_read_unlock();
if (err)
goto free_next_key;
err = -EFAULT;
if (copy_to_user(unext_key, next_key, map->key_size) != 0)
goto free_next_key;
err = 0;
free_next_key:
kfree(next_key);
free_key:
kfree(key);
err_put:
fdput(f);
return err;
}
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
static LIST_HEAD(bpf_prog_types);
static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
{
struct bpf_prog_type_list *tl;
list_for_each_entry(tl, &bpf_prog_types, list_node) {
if (tl->type == type) {
prog->aux->ops = tl->ops;
ebpf: move read-only fields to bpf_prog and shrink bpf_prog_aux is_gpl_compatible and prog_type should be moved directly into bpf_prog as they stay immutable during bpf_prog's lifetime, are core attributes and they can be locked as read-only later on via bpf_prog_select_runtime(). With a bit of rearranging, this also allows us to shrink bpf_prog_aux to exactly 1 cacheline. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-01 19:31:47 +08:00
prog->type = type;
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
return 0;
}
}
ebpf: move read-only fields to bpf_prog and shrink bpf_prog_aux is_gpl_compatible and prog_type should be moved directly into bpf_prog as they stay immutable during bpf_prog's lifetime, are core attributes and they can be locked as read-only later on via bpf_prog_select_runtime(). With a bit of rearranging, this also allows us to shrink bpf_prog_aux to exactly 1 cacheline. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-01 19:31:47 +08:00
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
return -EINVAL;
}
void bpf_register_prog_type(struct bpf_prog_type_list *tl)
{
list_add(&tl->list_node, &bpf_prog_types);
}
bpf: handle pseudo BPF_CALL insn in native eBPF programs userspace is using pseudo BPF_CALL instructions which encode one of 'enum bpf_func_id' inside insn->imm field. Verifier checks that program using correct function arguments to given func_id. If all checks passed, kernel needs to fixup BPF_CALL->imm fields by replacing func_id with in-kernel function pointer. eBPF interpreter just calls the function. In-kernel eBPF users continue to use generic BPF_CALL. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:01 +08:00
/* fixup insn->imm field of bpf_call instructions:
* if (insn->imm == BPF_FUNC_map_lookup_elem)
* insn->imm = bpf_map_lookup_elem - __bpf_call_base;
* else if (insn->imm == BPF_FUNC_map_update_elem)
* insn->imm = bpf_map_update_elem - __bpf_call_base;
* else ...
*
* this function is called after eBPF program passed verification
*/
static void fixup_bpf_calls(struct bpf_prog *prog)
{
const struct bpf_func_proto *fn;
int i;
for (i = 0; i < prog->len; i++) {
struct bpf_insn *insn = &prog->insnsi[i];
if (insn->code == (BPF_JMP | BPF_CALL)) {
/* we reach here when program has bpf_call instructions
* and it passed bpf_check(), means that
* ops->get_func_proto must have been supplied, check it
*/
BUG_ON(!prog->aux->ops->get_func_proto);
fn = prog->aux->ops->get_func_proto(insn->imm);
/* all functions that have prototype and verifier allowed
* programs to call them, must be real in-kernel functions
*/
BUG_ON(!fn->func);
insn->imm = fn->func - __bpf_call_base;
}
}
}
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
/* drop refcnt on maps used by eBPF program and free auxilary data */
static void free_used_maps(struct bpf_prog_aux *aux)
{
int i;
for (i = 0; i < aux->used_map_cnt; i++)
bpf_map_put(aux->used_maps[i]);
kfree(aux->used_maps);
}
void bpf_prog_put(struct bpf_prog *prog)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
free_used_maps(prog->aux);
bpf_prog_free(prog);
}
}
cls_bpf: add initial eBPF support for programmable classifiers This work extends the "classic" BPF programmable tc classifier by extending its scope also to native eBPF code! This allows for user space to implement own custom, 'safe' C like classifiers (or whatever other frontend language LLVM et al may provide in future), that can then be compiled with the LLVM eBPF backend to an eBPF elf file. The result of this can be loaded into the kernel via iproute2's tc. In the kernel, they can be JITed on major archs and thus run in native performance. Simple, minimal toy example to demonstrate the workflow: #include <linux/ip.h> #include <linux/if_ether.h> #include <linux/bpf.h> #include "tc_bpf_api.h" __section("classify") int cls_main(struct sk_buff *skb) { return (0x800 << 16) | load_byte(skb, ETH_HLEN + __builtin_offsetof(struct iphdr, tos)); } char __license[] __section("license") = "GPL"; The classifier can then be compiled into eBPF opcodes and loaded via tc, for example: clang -O2 -emit-llvm -c cls.c -o - | llc -march=bpf -filetype=obj -o cls.o tc filter add dev em1 parent 1: bpf cls.o [...] As it has been demonstrated, the scope can even reach up to a fully fledged flow dissector (similarly as in samples/bpf/sockex2_kern.c). For tc, maps are allowed to be used, but from kernel context only, in other words, eBPF code can keep state across filter invocations. In future, we perhaps may reattach from a different application to those maps e.g., to read out collected statistics/state. Similarly as in socket filters, we may extend functionality for eBPF classifiers over time depending on the use cases. For that purpose, cls_bpf programs are using BPF_PROG_TYPE_SCHED_CLS program type, so we can allow additional functions/accessors (e.g. an ABI compatible offset translation to skb fields/metadata). For an initial cls_bpf support, we allow the same set of helper functions as eBPF socket filters, but we could diverge at some point in time w/o problem. I was wondering whether cls_bpf and act_bpf could share C programs, I can imagine that at some point, we introduce i) further common handlers for both (or even beyond their scope), and/or if truly needed ii) some restricted function space for each of them. Both can be abstracted easily through struct bpf_verifier_ops in future. The context of cls_bpf versus act_bpf is slightly different though: a cls_bpf program will return a specific classid whereas act_bpf a drop/non-drop return code, latter may also in future mangle skbs. That said, we can surely have a "classify" and "action" section in a single object file, or considered mentioned constraint add a possibility of a shared section. The workflow for getting native eBPF running from tc [1] is as follows: for f_bpf, I've added a slightly modified ELF parser code from Alexei's kernel sample, which reads out the LLVM compiled object, sets up maps (and dynamically fixes up map fds) if any, and loads the eBPF instructions all centrally through the bpf syscall. The resulting fd from the loaded program itself is being passed down to cls_bpf, which looks up struct bpf_prog from the fd store, and holds reference, so that it stays available also after tc program lifetime. On tc filter destruction, it will then drop its reference. Moreover, I've also added the optional possibility to annotate an eBPF filter with a name (e.g. path to object file, or something else if preferred) so that when tc dumps currently installed filters, some more context can be given to an admin for a given instance (as opposed to just the file descriptor number). Last but not least, bpf_prog_get() and bpf_prog_put() needed to be exported, so that eBPF can be used from cls_bpf built as a module. Thanks to 60a3b2253c41 ("net: bpf: make eBPF interpreter images read-only") I think this is of no concern since anything wanting to alter eBPF opcode after verification stage would crash the kernel. [1] http://git.breakpoint.cc/cgit/dborkman/iproute2.git/log/?h=ebpf Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Jiri Pirko <jiri@resnulli.us> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-01 19:31:48 +08:00
EXPORT_SYMBOL_GPL(bpf_prog_put);
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
static int bpf_prog_release(struct inode *inode, struct file *filp)
{
struct bpf_prog *prog = filp->private_data;
bpf_prog_put(prog);
return 0;
}
static const struct file_operations bpf_prog_fops = {
.release = bpf_prog_release,
};
static struct bpf_prog *get_prog(struct fd f)
{
struct bpf_prog *prog;
if (!f.file)
return ERR_PTR(-EBADF);
if (f.file->f_op != &bpf_prog_fops) {
fdput(f);
return ERR_PTR(-EINVAL);
}
prog = f.file->private_data;
return prog;
}
/* called by sockets/tracing/seccomp before attaching program to an event
* pairs with bpf_prog_put()
*/
struct bpf_prog *bpf_prog_get(u32 ufd)
{
struct fd f = fdget(ufd);
struct bpf_prog *prog;
prog = get_prog(f);
if (IS_ERR(prog))
return prog;
atomic_inc(&prog->aux->refcnt);
fdput(f);
return prog;
}
cls_bpf: add initial eBPF support for programmable classifiers This work extends the "classic" BPF programmable tc classifier by extending its scope also to native eBPF code! This allows for user space to implement own custom, 'safe' C like classifiers (or whatever other frontend language LLVM et al may provide in future), that can then be compiled with the LLVM eBPF backend to an eBPF elf file. The result of this can be loaded into the kernel via iproute2's tc. In the kernel, they can be JITed on major archs and thus run in native performance. Simple, minimal toy example to demonstrate the workflow: #include <linux/ip.h> #include <linux/if_ether.h> #include <linux/bpf.h> #include "tc_bpf_api.h" __section("classify") int cls_main(struct sk_buff *skb) { return (0x800 << 16) | load_byte(skb, ETH_HLEN + __builtin_offsetof(struct iphdr, tos)); } char __license[] __section("license") = "GPL"; The classifier can then be compiled into eBPF opcodes and loaded via tc, for example: clang -O2 -emit-llvm -c cls.c -o - | llc -march=bpf -filetype=obj -o cls.o tc filter add dev em1 parent 1: bpf cls.o [...] As it has been demonstrated, the scope can even reach up to a fully fledged flow dissector (similarly as in samples/bpf/sockex2_kern.c). For tc, maps are allowed to be used, but from kernel context only, in other words, eBPF code can keep state across filter invocations. In future, we perhaps may reattach from a different application to those maps e.g., to read out collected statistics/state. Similarly as in socket filters, we may extend functionality for eBPF classifiers over time depending on the use cases. For that purpose, cls_bpf programs are using BPF_PROG_TYPE_SCHED_CLS program type, so we can allow additional functions/accessors (e.g. an ABI compatible offset translation to skb fields/metadata). For an initial cls_bpf support, we allow the same set of helper functions as eBPF socket filters, but we could diverge at some point in time w/o problem. I was wondering whether cls_bpf and act_bpf could share C programs, I can imagine that at some point, we introduce i) further common handlers for both (or even beyond their scope), and/or if truly needed ii) some restricted function space for each of them. Both can be abstracted easily through struct bpf_verifier_ops in future. The context of cls_bpf versus act_bpf is slightly different though: a cls_bpf program will return a specific classid whereas act_bpf a drop/non-drop return code, latter may also in future mangle skbs. That said, we can surely have a "classify" and "action" section in a single object file, or considered mentioned constraint add a possibility of a shared section. The workflow for getting native eBPF running from tc [1] is as follows: for f_bpf, I've added a slightly modified ELF parser code from Alexei's kernel sample, which reads out the LLVM compiled object, sets up maps (and dynamically fixes up map fds) if any, and loads the eBPF instructions all centrally through the bpf syscall. The resulting fd from the loaded program itself is being passed down to cls_bpf, which looks up struct bpf_prog from the fd store, and holds reference, so that it stays available also after tc program lifetime. On tc filter destruction, it will then drop its reference. Moreover, I've also added the optional possibility to annotate an eBPF filter with a name (e.g. path to object file, or something else if preferred) so that when tc dumps currently installed filters, some more context can be given to an admin for a given instance (as opposed to just the file descriptor number). Last but not least, bpf_prog_get() and bpf_prog_put() needed to be exported, so that eBPF can be used from cls_bpf built as a module. Thanks to 60a3b2253c41 ("net: bpf: make eBPF interpreter images read-only") I think this is of no concern since anything wanting to alter eBPF opcode after verification stage would crash the kernel. [1] http://git.breakpoint.cc/cgit/dborkman/iproute2.git/log/?h=ebpf Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Jiri Pirko <jiri@resnulli.us> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-01 19:31:48 +08:00
EXPORT_SYMBOL_GPL(bpf_prog_get);
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
/* last field in 'union bpf_attr' used by this command */
bpf: verifier (add ability to receive verification log) add optional attributes for BPF_PROG_LOAD syscall: union bpf_attr { struct { ... __u32 log_level; /* verbosity level of eBPF verifier */ __u32 log_size; /* size of user buffer */ __aligned_u64 log_buf; /* user supplied 'char *buffer' */ }; }; when log_level > 0 the verifier will return its verification log in the user supplied buffer 'log_buf' which can be used by program author to analyze why verifier rejected given program. 'Understanding eBPF verifier messages' section of Documentation/networking/filter.txt provides several examples of these messages, like the program: BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_CALL_FUNC(BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0), BPF_EXIT_INSN(), will be rejected with the following multi-line message in log_buf: 0: (7a) *(u64 *)(r10 -8) = 0 1: (bf) r2 = r10 2: (07) r2 += -8 3: (b7) r1 = 0 4: (85) call 1 5: (15) if r0 == 0x0 goto pc+1 R0=map_ptr R10=fp 6: (7a) *(u64 *)(r0 +4) = 0 misaligned access off 4 size 8 The format of the output can change at any time as verifier evolves. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:03 +08:00
#define BPF_PROG_LOAD_LAST_FIELD log_buf
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
static int bpf_prog_load(union bpf_attr *attr)
{
enum bpf_prog_type type = attr->prog_type;
struct bpf_prog *prog;
int err;
char license[128];
bool is_gpl;
if (CHECK_ATTR(BPF_PROG_LOAD))
return -EINVAL;
/* copy eBPF program license from user space */
if (strncpy_from_user(license, u64_to_ptr(attr->license),
sizeof(license) - 1) < 0)
return -EFAULT;
license[sizeof(license) - 1] = 0;
/* eBPF programs must be GPL compatible to use GPL-ed functions */
is_gpl = license_is_gpl_compatible(license);
if (attr->insn_cnt >= BPF_MAXINSNS)
return -EINVAL;
/* plain bpf_prog allocation */
prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
if (!prog)
return -ENOMEM;
prog->len = attr->insn_cnt;
err = -EFAULT;
if (copy_from_user(prog->insns, u64_to_ptr(attr->insns),
prog->len * sizeof(struct bpf_insn)) != 0)
goto free_prog;
prog->orig_prog = NULL;
prog->jited = false;
atomic_set(&prog->aux->refcnt, 1);
ebpf: move read-only fields to bpf_prog and shrink bpf_prog_aux is_gpl_compatible and prog_type should be moved directly into bpf_prog as they stay immutable during bpf_prog's lifetime, are core attributes and they can be locked as read-only later on via bpf_prog_select_runtime(). With a bit of rearranging, this also allows us to shrink bpf_prog_aux to exactly 1 cacheline. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-01 19:31:47 +08:00
prog->gpl_compatible = is_gpl;
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
/* find program type: socket_filter vs tracing_filter */
err = find_prog_type(type, prog);
if (err < 0)
goto free_prog;
/* run eBPF verifier */
bpf: verifier (add docs) this patch adds all of eBPF verfier documentation and empty bpf_check() The end goal for the verifier is to statically check safety of the program. Verifier will catch: - loops - out of range jumps - unreachable instructions - invalid instructions - uninitialized register access - uninitialized stack access - misaligned stack access - out of range stack access - invalid calling convention More details in Documentation/networking/filter.txt Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:02 +08:00
err = bpf_check(prog, attr);
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
if (err < 0)
goto free_used_maps;
bpf: handle pseudo BPF_CALL insn in native eBPF programs userspace is using pseudo BPF_CALL instructions which encode one of 'enum bpf_func_id' inside insn->imm field. Verifier checks that program using correct function arguments to given func_id. If all checks passed, kernel needs to fixup BPF_CALL->imm fields by replacing func_id with in-kernel function pointer. eBPF interpreter just calls the function. In-kernel eBPF users continue to use generic BPF_CALL. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:01 +08:00
/* fixup BPF_CALL->imm field */
fixup_bpf_calls(prog);
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
/* eBPF program is ready to be JITed */
bpf_prog_select_runtime(prog);
err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC);
if (err < 0)
/* failed to allocate fd */
goto free_used_maps;
return err;
free_used_maps:
free_used_maps(prog->aux);
free_prog:
bpf_prog_free(prog);
return err;
}
bpf: introduce BPF syscall and maps BPF syscall is a multiplexor for a range of different operations on eBPF. This patch introduces syscall with single command to create a map. Next patch adds commands to access maps. 'maps' is a generic storage of different types for sharing data between kernel and userspace. Userspace example: /* this syscall wrapper creates a map with given type and attributes * and returns map_fd on success. * use close(map_fd) to delete the map */ int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries) { union bpf_attr attr = { .map_type = map_type, .key_size = key_size, .value_size = value_size, .max_entries = max_entries }; return bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } 'union bpf_attr' is backwards compatible with future extensions. More details in Documentation/networking/filter.txt and in manpage Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:57 +08:00
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
int err;
/* the syscall is limited to root temporarily. This restriction will be
* lifted when security audit is clean. Note that eBPF+tracing must have
* this restriction, since it may pass kernel data to user space
*/
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!access_ok(VERIFY_READ, uattr, 1))
return -EFAULT;
if (size > PAGE_SIZE) /* silly large */
return -E2BIG;
/* 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 dont know about yet.
*/
if (size > sizeof(attr)) {
unsigned char __user *addr;
unsigned char __user *end;
unsigned char val;
addr = (void __user *)uattr + sizeof(attr);
end = (void __user *)uattr + size;
for (; addr < end; addr++) {
err = get_user(val, addr);
if (err)
return err;
if (val)
return -E2BIG;
}
size = sizeof(attr);
}
/* copy attributes from user space, may be less than sizeof(bpf_attr) */
if (copy_from_user(&attr, uattr, size) != 0)
return -EFAULT;
switch (cmd) {
case BPF_MAP_CREATE:
err = map_create(&attr);
break;
bpf: add lookup/update/delete/iterate methods to BPF maps 'maps' is a generic storage of different types for sharing data between kernel and userspace. The maps are accessed from user space via BPF syscall, which has commands: - create a map with given type and attributes fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size) returns fd or negative error - lookup key in a given map referenced by fd err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero and stores found elem into value or negative error - create or update key/value pair in a given map err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero or negative error - find and delete element by key in a given map err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key - iterate map elements (based on input key return next_key) err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->next_key - close(fd) deletes the map Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:59 +08:00
case BPF_MAP_LOOKUP_ELEM:
err = map_lookup_elem(&attr);
break;
case BPF_MAP_UPDATE_ELEM:
err = map_update_elem(&attr);
break;
case BPF_MAP_DELETE_ELEM:
err = map_delete_elem(&attr);
break;
case BPF_MAP_GET_NEXT_KEY:
err = map_get_next_key(&attr);
break;
bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:00 +08:00
case BPF_PROG_LOAD:
err = bpf_prog_load(&attr);
break;
bpf: introduce BPF syscall and maps BPF syscall is a multiplexor for a range of different operations on eBPF. This patch introduces syscall with single command to create a map. Next patch adds commands to access maps. 'maps' is a generic storage of different types for sharing data between kernel and userspace. Userspace example: /* this syscall wrapper creates a map with given type and attributes * and returns map_fd on success. * use close(map_fd) to delete the map */ int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries) { union bpf_attr attr = { .map_type = map_type, .key_size = key_size, .value_size = value_size, .max_entries = max_entries }; return bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } 'union bpf_attr' is backwards compatible with future extensions. More details in Documentation/networking/filter.txt and in manpage Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:16:57 +08:00
default:
err = -EINVAL;
break;
}
return err;
}