leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Browse Source 
Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-01-22

The following pull-request contains BPF updates for your *net-next* tree.

We've added 92 non-merge commits during the last 16 day(s) which contain
a total of 320 files changed, 7532 insertions(+), 1448 deletions(-).

The main changes are:

1) function by function verification and program extensions from Alexei.

2) massive cleanup of selftests/bpf from Toke and Andrii.

3) batched bpf map operations from Brian and Yonghong.

4) tcp congestion control in bpf from Martin.

5) bulking for non-map xdp_redirect form Toke.

6) bpf_send_signal_thread helper from Yonghong.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2020-01-23 08:10:16 +01:00
commit 954b3c4397
320 changed files with 7525 additions and 1441 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
arch/x86/net/bpf_jit_comp.c
View File

@ -1328,7 +1328,7 @@ emit_jmp:
return proglen;
}
static void save_regs(struct btf_func_model *m, u8 **prog, int nr_args,
static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
int stack_size)
{
int i;
@ -1344,7 +1344,7 @@ static void save_regs(struct btf_func_model *m, u8 **prog, int nr_args,
-(stack_size - i * 8));
}
static void restore_regs(struct btf_func_model *m, u8 **prog, int nr_args,
static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
int stack_size)
{
int i;
@ -1361,7 +1361,7 @@ static void restore_regs(struct btf_func_model *m, u8 **prog, int nr_args,
-(stack_size - i * 8));
}
static int invoke_bpf(struct btf_func_model *m, u8 **pprog,
static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
struct bpf_prog **progs, int prog_cnt, int stack_size)
{
u8 *prog = *pprog;
@ -1456,7 +1456,8 @@ static int invoke_bpf(struct btf_func_model *m, u8 **pprog,
* add rsp, 8 // skip eth_type_trans's frame
* ret // return to its caller
*/
int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
int arch_prepare_bpf_trampoline(void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
struct bpf_prog **fentry_progs, int fentry_cnt,
struct bpf_prog **fexit_progs, int fexit_cnt,
void *orig_call)
@ -1523,13 +1524,10 @@ int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags
/* skip our return address and return to parent */
EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
EMIT1(0xC3); /* ret */
/* One half of the page has active running trampoline.
* Another half is an area for next trampoline.
* Make sure the trampoline generation logic doesn't overflow.
*/
if (WARN_ON_ONCE(prog - (u8 *)image > PAGE_SIZE / 2 - BPF_INSN_SAFETY))
/* Make sure the trampoline generation logic doesn't overflow */
if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY))
return -EFAULT;
return 0;
return prog - (u8 *)image;
}
static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)

4
drivers/net/tun.c
View File

@ -1718,7 +1718,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
if (err < 0)
goto err_xdp;
if (err == XDP_REDIRECT)
xdp_do_flush_map();
xdp_do_flush();
if (err != XDP_PASS)
goto out;
@ -2549,7 +2549,7 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
}
if (flush)
xdp_do_flush_map();
xdp_do_flush();
rcu_read_unlock();
local_bh_enable();

2
drivers/net/veth.c
View File

@ -769,7 +769,7 @@ static int veth_poll(struct napi_struct *napi, int budget)
if (xdp_xmit & VETH_XDP_TX)
veth_xdp_flush(rq->dev, &bq);
if (xdp_xmit & VETH_XDP_REDIR)
xdp_do_flush_map();
xdp_do_flush();
xdp_clear_return_frame_no_direct();
return done;

2
drivers/net/virtio_net.c
View File

@ -1432,7 +1432,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
virtqueue_napi_complete(napi, rq->vq, received);
if (xdp_xmit & VIRTIO_XDP_REDIR)
xdp_do_flush_map();
xdp_do_flush();
if (xdp_xmit & VIRTIO_XDP_TX) {
sq = virtnet_xdp_sq(vi);

128
include/linux/bpf.h
View File

@ -17,6 +17,7 @@
#include <linux/u64_stats_sync.h>
#include <linux/refcount.h>
#include <linux/mutex.h>
#include <linux/module.h>
struct bpf_verifier_env;
struct bpf_verifier_log;
@ -43,6 +44,15 @@ struct bpf_map_ops {
int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
void (*map_release_uref)(struct bpf_map *map);
void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key);
int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr,
union bpf_attr __user *uattr);
int (*map_lookup_and_delete_batch)(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr,
union bpf_attr __user *uattr);
int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr,
union bpf_attr __user *uattr);
/* funcs callable from userspace and from eBPF programs */
void *(*map_lookup_elem)(struct bpf_map *map, void *key);
@ -106,6 +116,7 @@ struct bpf_map {
struct btf *btf;
struct bpf_map_memory memory;
char name[BPF_OBJ_NAME_LEN];
u32 btf_vmlinux_value_type_id;
bool unpriv_array;
bool frozen; /* write-once; write-protected by freeze_mutex */
/* 22 bytes hole */
@ -183,7 +194,8 @@ static inline bool bpf_map_offload_neutral(const struct bpf_map *map)
static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
{
return map->btf && map->ops->map_seq_show_elem;
return (map->btf_value_type_id || map->btf_vmlinux_value_type_id) &&
map->ops->map_seq_show_elem;
}
int map_check_no_btf(const struct bpf_map *map,
@ -349,6 +361,10 @@ struct bpf_verifier_ops {
const struct bpf_insn *src,
struct bpf_insn *dst,
struct bpf_prog *prog, u32 *target_size);
int (*btf_struct_access)(struct bpf_verifier_log *log,
const struct btf_type *t, int off, int size,
enum bpf_access_type atype,
u32 *next_btf_id);
};
struct bpf_prog_offload_ops {
@ -437,7 +453,8 @@ struct btf_func_model {
* fentry = a set of program to run before calling original function
* fexit = a set of program to run after original function
*/
int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
int arch_prepare_bpf_trampoline(void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
struct bpf_prog **fentry_progs, int fentry_cnt,
struct bpf_prog **fexit_progs, int fexit_cnt,
void *orig_call);
@ -448,7 +465,8 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
enum bpf_tramp_prog_type {
BPF_TRAMP_FENTRY,
BPF_TRAMP_FEXIT,
BPF_TRAMP_MAX
BPF_TRAMP_MAX,
BPF_TRAMP_REPLACE, /* more than MAX */
};
struct bpf_trampoline {
@ -463,6 +481,11 @@ struct bpf_trampoline {
void *addr;
bool ftrace_managed;
} func;
/* if !NULL this is BPF_PROG_TYPE_EXT program that extends another BPF
* program by replacing one of its functions. func.addr is the address
* of the function it replaced.
*/
struct bpf_prog *extension_prog;
/* list of BPF programs using this trampoline */
struct hlist_head progs_hlist[BPF_TRAMP_MAX];
/* Number of attached programs. A counter per kind. */
@ -558,6 +581,7 @@ static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d,
#endif
struct bpf_func_info_aux {
u16 linkage;
bool unreliable;
};
@ -668,6 +692,73 @@ struct bpf_array_aux {
struct work_struct work;
};
struct bpf_struct_ops_value;
struct btf_type;
struct btf_member;
#define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64
struct bpf_struct_ops {
const struct bpf_verifier_ops *verifier_ops;
int (*init)(struct btf *btf);
int (*check_member)(const struct btf_type *t,
const struct btf_member *member);
int (*init_member)(const struct btf_type *t,
const struct btf_member *member,
void *kdata, const void *udata);
int (*reg)(void *kdata);
void (*unreg)(void *kdata);
const struct btf_type *type;
const struct btf_type *value_type;
const char *name;
struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS];
u32 type_id;
u32 value_id;
};
#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
#define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA))
const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id);
void bpf_struct_ops_init(struct btf *btf);
bool bpf_struct_ops_get(const void *kdata);
void bpf_struct_ops_put(const void *kdata);
int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
void *value);
static inline bool bpf_try_module_get(const void *data, struct module *owner)
{
if (owner == BPF_MODULE_OWNER)
return bpf_struct_ops_get(data);
else
return try_module_get(owner);
}
static inline void bpf_module_put(const void *data, struct module *owner)
{
if (owner == BPF_MODULE_OWNER)
bpf_struct_ops_put(data);
else
module_put(owner);
}
#else
static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
{
return NULL;
}
static inline void bpf_struct_ops_init(struct btf *btf) { }
static inline bool bpf_try_module_get(const void *data, struct module *owner)
{
return try_module_get(owner);
}
static inline void bpf_module_put(const void *data, struct module *owner)
{
module_put(owner);
}
static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map,
void *key,
void *value)
{
return -EINVAL;
}
#endif
struct bpf_array {
struct bpf_map map;
u32 elem_size;
@ -906,6 +997,15 @@ void *bpf_map_area_alloc(u64 size, int numa_node);
void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
void bpf_map_area_free(void *base);
void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
int generic_map_lookup_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
int generic_map_update_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
int generic_map_delete_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
extern int sysctl_unprivileged_bpf_disabled;
@ -962,7 +1062,9 @@ struct sk_buff;
struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key);
void __dev_map_flush(void);
void __dev_flush(void);
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx);
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx);
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
@ -1006,7 +1108,13 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
const char *func_name,
struct btf_func_model *m);
int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog);
struct bpf_reg_state;
int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
struct bpf_reg_state *regs);
int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
struct bpf_reg_state *reg);
int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
struct btf *btf, const struct btf_type *t);
struct bpf_prog *bpf_prog_by_id(u32 id);
@ -1071,13 +1179,20 @@ static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map
return NULL;
}
static inline void __dev_map_flush(void)
static inline void __dev_flush(void)
{
}
struct xdp_buff;
struct bpf_dtab_netdev;
static inline
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
return 0;
}
static inline
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx)
@ -1299,6 +1414,7 @@ extern const struct bpf_func_proto bpf_get_local_storage_proto;
extern const struct bpf_func_proto bpf_strtol_proto;
extern const struct bpf_func_proto bpf_strtoul_proto;
extern const struct bpf_func_proto bpf_tcp_sock_proto;
extern const struct bpf_func_proto bpf_jiffies64_proto;
/* Shared helpers among cBPF and eBPF. */
void bpf_user_rnd_init_once(void);

9
include/linux/bpf_types.h
View File

@ -65,6 +65,12 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2,
BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport,
struct sk_reuseport_md, struct sk_reuseport_kern)
#endif
#if defined(CONFIG_BPF_JIT)
BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops,
void *, void *)
BPF_PROG_TYPE(BPF_PROG_TYPE_EXT, bpf_extension,
void *, void *)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops)
@ -105,3 +111,6 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops)
#if defined(CONFIG_BPF_JIT)
BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops)
#endif

10
include/linux/bpf_verifier.h
View File

@ -304,11 +304,13 @@ struct bpf_insn_aux_data {
u64 map_key_state; /* constant (32 bit) key tracking for maps */
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
int sanitize_stack_off; /* stack slot to be cleared */
bool seen; /* this insn was processed by the verifier */
u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
bool zext_dst; /* this insn zero extends dst reg */
u8 alu_state; /* used in combination with alu_limit */
bool prune_point;
/* below fields are initialized once */
unsigned int orig_idx; /* original instruction index */
bool prune_point;
};
#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
@ -379,6 +381,7 @@ struct bpf_verifier_env {
int *insn_stack;
int cur_stack;
} cfg;
u32 pass_cnt; /* number of times do_check() was called */
u32 subprog_cnt;
/* number of instructions analyzed by the verifier */
u32 prev_insn_processed, insn_processed;
@ -428,4 +431,7 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off,
void
bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
int check_ctx_reg(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int regno);
#endif /* _LINUX_BPF_VERIFIER_H */

52
include/linux/btf.h
View File

@ -7,6 +7,8 @@
#include <linux/types.h>
#include <uapi/linux/btf.h>
#define BTF_TYPE_EMIT(type) ((void)(type *)0)
struct btf;
struct btf_member;
struct btf_type;
@ -53,6 +55,22 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
u32 expected_offset, u32 expected_size);
int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
bool btf_type_is_void(const struct btf_type *t);
s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind);
const struct btf_type *btf_type_skip_modifiers(const struct btf *btf,
u32 id, u32 *res_id);
const struct btf_type *btf_type_resolve_ptr(const struct btf *btf,
u32 id, u32 *res_id);
const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf,
u32 id, u32 *res_id);
const struct btf_type *
btf_resolve_size(const struct btf *btf, const struct btf_type *type,
u32 *type_size, const struct btf_type **elem_type,
u32 *total_nelems);
#define for_each_member(i, struct_type, member) \
for (i = 0, member = btf_type_member(struct_type); \
i < btf_type_vlen(struct_type); \
i++, member++)
static inline bool btf_type_is_ptr(const struct btf_type *t)
{
@ -84,6 +102,40 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t)
return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO;
}
static inline u16 btf_type_vlen(const struct btf_type *t)
{
return BTF_INFO_VLEN(t->info);
}
static inline u16 btf_func_linkage(const struct btf_type *t)
{
return BTF_INFO_VLEN(t->info);
}
static inline bool btf_type_kflag(const struct btf_type *t)
{
return BTF_INFO_KFLAG(t->info);
}
static inline u32 btf_member_bit_offset(const struct btf_type *struct_type,
const struct btf_member *member)
{
return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset)
: member->offset;
}
static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type,
const struct btf_member *member)
{
return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset)
: 0;
}
static inline const struct btf_member *btf_type_member(const struct btf_type *t)
{
return (const struct btf_member *)(t + 1);
}
#ifdef CONFIG_BPF_SYSCALL
const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
const char *btf_name_by_offset(const struct btf *btf, u32 offset);

12
include/linux/filter.h
View File

@ -843,6 +843,8 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
bpf_aux_classic_check_t trans, bool save_orig);
void bpf_prog_destroy(struct bpf_prog *fp);
const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id);
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
int sk_attach_bpf(u32 ufd, struct sock *sk);
@ -916,7 +918,7 @@ static inline int xdp_ok_fwd_dev(const struct net_device *fwd,
return 0;
}
/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the
/* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the
* same cpu context. Further for best results no more than a single map
* for the do_redirect/do_flush pair should be used. This limitation is
* because we only track one map and force a flush when the map changes.
@ -927,7 +929,13 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
int xdp_do_redirect(struct net_device *dev,
struct xdp_buff *xdp,
struct bpf_prog *prog);
void xdp_do_flush_map(void);
void xdp_do_flush(void);
/* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as
* it is no longer only flushing maps. Keep this define for compatibility
* until all drivers are updated - do not use xdp_do_flush_map() in new code!
*/
#define xdp_do_flush_map xdp_do_flush
void bpf_warn_invalid_xdp_action(u32 act);

13
include/linux/netdevice.h
View File

@ -876,6 +876,7 @@ enum bpf_netdev_command {
struct bpf_prog_offload_ops;
struct netlink_ext_ack;
struct xdp_umem;
struct xdp_dev_bulk_queue;
struct netdev_bpf {
enum bpf_netdev_command command;
@ -1986,12 +1987,10 @@ struct net_device {
unsigned int num_tx_queues;
unsigned int real_num_tx_queues;
struct Qdisc *qdisc;
#ifdef CONFIG_NET_SCHED
DECLARE_HASHTABLE (qdisc_hash, 4);
#endif
unsigned int tx_queue_len;
spinlock_t tx_global_lock;
int watchdog_timeo;
struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
#ifdef CONFIG_XPS
struct xps_dev_maps __rcu *xps_cpus_map;
@ -2001,11 +2000,15 @@ struct net_device {
struct mini_Qdisc __rcu *miniq_egress;
#endif
#ifdef CONFIG_NET_SCHED
DECLARE_HASHTABLE (qdisc_hash, 4);
#endif
/* These may be needed for future network-power-down code. */
struct timer_list watchdog_timer;
int watchdog_timeo;
int __percpu *pcpu_refcnt;
struct list_head todo_list;
int __percpu *pcpu_refcnt;
struct list_head link_watch_list;

2
include/net/sock.h
View File

@ -2597,4 +2597,6 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif)
return false;
}
void sock_def_readable(struct sock *sk);
#endif /* _SOCK_H */

2
include/net/tcp.h
View File

@ -1019,6 +1019,7 @@ enum tcp_ca_ack_event_flags {
#define TCP_CONG_NON_RESTRICTED 0x1
/* Requires ECN/ECT set on all packets */
#define TCP_CONG_NEEDS_ECN 0x2
#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN)
union tcp_cc_info;
@ -1113,6 +1114,7 @@ u32 tcp_reno_undo_cwnd(struct sock *sk);
void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
extern struct tcp_congestion_ops tcp_reno;
struct tcp_congestion_ops *tcp_ca_find(const char *name);
struct tcp_congestion_ops *tcp_ca_find_key(u32 key);
u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca);
#ifdef CONFIG_INET

130
include/trace/events/xdp.h
View File

@ -79,14 +79,26 @@ TRACE_EVENT(xdp_bulk_tx,
__entry->sent, __entry->drops, __entry->err)
);
#ifndef __DEVMAP_OBJ_TYPE
#define __DEVMAP_OBJ_TYPE
struct _bpf_dtab_netdev {
struct net_device *dev;
};
#endif /* __DEVMAP_OBJ_TYPE */
#define devmap_ifindex(tgt, map) \
(((map->map_type == BPF_MAP_TYPE_DEVMAP || \
map->map_type == BPF_MAP_TYPE_DEVMAP_HASH)) ? \
((struct _bpf_dtab_netdev *)tgt)->dev->ifindex : 0)
DECLARE_EVENT_CLASS(xdp_redirect_template,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
int to_ifindex, int err,
const struct bpf_map *map, u32 map_index),
const void *tgt, int err,
const struct bpf_map *map, u32 index),
TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
TP_ARGS(dev, xdp, tgt, err, map, index),
TP_STRUCT__entry(
__field(int, prog_id)
@ -103,90 +115,65 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
__entry->act = XDP_REDIRECT;
__entry->ifindex = dev->ifindex;
__entry->err = err;
__entry->to_ifindex = to_ifindex;
__entry->to_ifindex = map ? devmap_ifindex(tgt, map) :
index;
__entry->map_id = map ? map->id : 0;
__entry->map_index = map_index;
__entry->map_index = map ? index : 0;
),
TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d",
TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
" map_id=%d map_index=%d",
__entry->prog_id,
__print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
__entry->ifindex, __entry->to_ifindex,
__entry->err)
__entry->err, __entry->map_id, __entry->map_index)
);
DEFINE_EVENT(xdp_redirect_template, xdp_redirect,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
int to_ifindex, int err,
const struct bpf_map *map, u32 map_index),
TP_ARGS(dev, xdp, to_ifindex, err, map, map_index)
const void *tgt, int err,
const struct bpf_map *map, u32 index),
TP_ARGS(dev, xdp, tgt, err, map, index)
);
DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
int to_ifindex, int err,
const struct bpf_map *map, u32 map_index),
TP_ARGS(dev, xdp, to_ifindex, err, map, map_index)
const void *tgt, int err,
const struct bpf_map *map, u32 index),
TP_ARGS(dev, xdp, tgt, err, map, index)
);
#define _trace_xdp_redirect(dev, xdp, to) \
trace_xdp_redirect(dev, xdp, to, 0, NULL, 0);
trace_xdp_redirect(dev, xdp, NULL, 0, NULL, to);
#define _trace_xdp_redirect_err(dev, xdp, to, err) \
trace_xdp_redirect_err(dev, xdp, to, err, NULL, 0);
trace_xdp_redirect_err(dev, xdp, NULL, err, NULL, to);
DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map,
#define _trace_xdp_redirect_map(dev, xdp, to, map, index) \
trace_xdp_redirect(dev, xdp, to, 0, map, index);
#define _trace_xdp_redirect_map_err(dev, xdp, to, map, index, err) \
trace_xdp_redirect_err(dev, xdp, to, err, map, index);
/* not used anymore, but kept around so as not to break old programs */
DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
int to_ifindex, int err,
const struct bpf_map *map, u32 map_index),
TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
" map_id=%d map_index=%d",
__entry->prog_id,
__print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
__entry->ifindex, __entry->to_ifindex,
__entry->err,
__entry->map_id, __entry->map_index)
const void *tgt, int err,
const struct bpf_map *map, u32 index),
TP_ARGS(dev, xdp, tgt, err, map, index)
);
DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
int to_ifindex, int err,
const struct bpf_map *map, u32 map_index),
TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
" map_id=%d map_index=%d",
__entry->prog_id,
__print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
__entry->ifindex, __entry->to_ifindex,
__entry->err,
__entry->map_id, __entry->map_index)
const void *tgt, int err,
const struct bpf_map *map, u32 index),
TP_ARGS(dev, xdp, tgt, err, map, index)
);
#ifndef __DEVMAP_OBJ_TYPE
#define __DEVMAP_OBJ_TYPE
struct _bpf_dtab_netdev {
struct net_device *dev;
};
#endif /* __DEVMAP_OBJ_TYPE */
#define devmap_ifindex(fwd, map) \
((map->map_type == BPF_MAP_TYPE_DEVMAP || \
map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) ? \
((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0)
#define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \
trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \
0, map, idx)
#define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err) \
trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map), \
err, map, idx)
TRACE_EVENT(xdp_cpumap_kthread,
TP_PROTO(int map_id, unsigned int processed, unsigned int drops,
@ -259,43 +246,38 @@ TRACE_EVENT(xdp_cpumap_enqueue,
TRACE_EVENT(xdp_devmap_xmit,
TP_PROTO(const struct bpf_map *map, u32 map_index,
int sent, int drops,
const struct net_device *from_dev,
const struct net_device *to_dev, int err),
TP_PROTO(const struct net_device *from_dev,
const struct net_device *to_dev,
int sent, int drops, int err),
TP_ARGS(map, map_index, sent, drops, from_dev, to_dev, err),
TP_ARGS(from_dev, to_dev, sent, drops, err),
TP_STRUCT__entry(
__field(int, map_id)
__field(int, from_ifindex)
__field(u32, act)
__field(u32, map_index)
__field(int, to_ifindex)
__field(int, drops)
__field(int, sent)
__field(int, from_ifindex)
__field(int, to_ifindex)
__field(int, err)
),
TP_fast_assign(
__entry->map_id = map->id;
__entry->from_ifindex = from_dev->ifindex;
__entry->act = XDP_REDIRECT;
__entry->map_index = map_index;
__entry->to_ifindex = to_dev->ifindex;
__entry->drops = drops;
__entry->sent = sent;
__entry->from_ifindex = from_dev->ifindex;
__entry->to_ifindex = to_dev->ifindex;
__entry->err = err;
),
TP_printk("ndo_xdp_xmit"
" map_id=%d map_index=%d action=%s"
" from_ifindex=%d to_ifindex=%d action=%s"
" sent=%d drops=%d"
" from_ifindex=%d to_ifindex=%d err=%d",
__entry->map_id, __entry->map_index,
" err=%d",
__entry->from_ifindex, __entry->to_ifindex,
__print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
__entry->sent, __entry->drops,
__entry->from_ifindex, __entry->to_ifindex, __entry->err)
__entry->err)
);
/* Expect users already include <net/xdp.h>, but not xdp_priv.h */

72
include/uapi/linux/bpf.h
View File

@ -107,6 +107,10 @@ enum bpf_cmd {
BPF_MAP_LOOKUP_AND_DELETE_ELEM,
BPF_MAP_FREEZE,
BPF_BTF_GET_NEXT_ID,
BPF_MAP_LOOKUP_BATCH,
BPF_MAP_LOOKUP_AND_DELETE_BATCH,
BPF_MAP_UPDATE_BATCH,
BPF_MAP_DELETE_BATCH,
};
enum bpf_map_type {
@ -136,6 +140,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_STACK,
BPF_MAP_TYPE_SK_STORAGE,
BPF_MAP_TYPE_DEVMAP_HASH,
BPF_MAP_TYPE_STRUCT_OPS,
};
/* Note that tracing related programs such as
@ -174,6 +179,8 @@ enum bpf_prog_type {
BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
BPF_PROG_TYPE_CGROUP_SOCKOPT,
BPF_PROG_TYPE_TRACING,
BPF_PROG_TYPE_STRUCT_OPS,
BPF_PROG_TYPE_EXT,
};
enum bpf_attach_type {
@ -357,7 +364,12 @@ enum bpf_attach_type {
/* Enable memory-mapping BPF map */
#define BPF_F_MMAPABLE (1U << 10)
/* flags for BPF_PROG_QUERY */
/* Flags for BPF_PROG_QUERY. */
/* Query effective (directly attached + inherited from ancestor cgroups)
* programs that will be executed for events within a cgroup.
* attach_flags with this flag are returned only for directly attached programs.
*/
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
enum bpf_stack_build_id_status {
@ -397,6 +409,10 @@ union bpf_attr {
__u32 btf_fd; /* fd pointing to a BTF type data */
__u32 btf_key_type_id; /* BTF type_id of the key */
__u32 btf_value_type_id; /* BTF type_id of the value */
__u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel-
* struct stored as the
* map value
*/
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@ -409,6 +425,23 @@ union bpf_attr {
__u64 flags;
};
struct { /* struct used by BPF_MAP_*_BATCH commands */
__aligned_u64 in_batch; /* start batch,
* NULL to start from beginning
*/
__aligned_u64 out_batch; /* output: next start batch */
__aligned_u64 keys;
__aligned_u64 values;
__u32 count; /* input/output:
* input: # of key/value
* elements
* output: # of filled elements
*/
__u32 map_fd;
__u64 elem_flags;
__u64 flags;
} batch;
struct { /* anonymous struct used by BPF_PROG_LOAD command */
__u32 prog_type; /* one of enum bpf_prog_type */
__u32 insn_cnt;
@ -2703,7 +2736,8 @@ union bpf_attr {
*
* int bpf_send_signal(u32 sig)
* Description
* Send signal *sig* to the current task.
* Send signal *sig* to the process of the current task.
* The signal may be delivered to any of this process's threads.
* Return
* 0 on success or successfully queued.
*
@ -2831,6 +2865,33 @@ union bpf_attr {
* Return
* On success, the strictly positive length of the string, including
* the trailing NUL character. On error, a negative value.
*
* int bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
* Description
* Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock.
* *rcv_nxt* is the ack_seq to be sent out.
* Return
* 0 on success, or a negative error in case of failure.
*
* int bpf_send_signal_thread(u32 sig)
* Description
* Send signal *sig* to the thread corresponding to the current task.
* Return
* 0 on success or successfully queued.
*
* **-EBUSY** if work queue under nmi is full.
*
* **-EINVAL** if *sig* is invalid.
*
* **-EPERM** if no permission to send the *sig*.
*
* **-EAGAIN** if bpf program can try again.
*
* u64 bpf_jiffies64(void)
* Description
* Obtain the 64bit jiffies
* Return
* The 64 bit jiffies
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@ -2948,7 +3009,10 @@ union bpf_attr {
FN(probe_read_user), \
FN(probe_read_kernel), \
FN(probe_read_user_str), \
FN(probe_read_kernel_str),
FN(probe_read_kernel_str), \
FN(tcp_send_ack), \
FN(send_signal_thread), \
FN(jiffies64),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@ -3349,7 +3413,7 @@ struct bpf_map_info {
__u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
__u32 :32;
__u32 btf_vmlinux_value_type_id;
__u64 netns_dev;
__u64 netns_ino;
__u32 btf_id;

6
include/uapi/linux/btf.h
View File

@ -146,6 +146,12 @@ enum {
BTF_VAR_GLOBAL_EXTERN = 2,
};
enum btf_func_linkage {
BTF_FUNC_STATIC = 0,
BTF_FUNC_GLOBAL = 1,
BTF_FUNC_EXTERN = 2,
};
/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
* additional information related to the variable such as its linkage.
*/

3
kernel/bpf/Makefile
View File

@ -27,3 +27,6 @@ endif
ifeq ($(CONFIG_SYSFS),y)
obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o
endif
ifeq ($(CONFIG_BPF_JIT),y)
obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
endif

2
kernel/bpf/arraymap.c
View File

@ -503,6 +503,8 @@ const struct bpf_map_ops array_map_ops = {
.map_mmap = array_map_mmap,
.map_seq_show_elem = array_map_seq_show_elem,
.map_check_btf = array_map_check_btf,
.map_lookup_batch = generic_map_lookup_batch,
.map_update_batch = generic_map_update_batch,
};
const struct bpf_map_ops percpu_array_map_ops = {

634
kernel/bpf/bpf_struct_ops.c Normal file
View File

@ -0,0 +1,634 @@
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2019 Facebook */
#include <linux/bpf.h>
#include <linux/bpf_verifier.h>
#include <linux/btf.h>
#include <linux/filter.h>
#include <linux/slab.h>
#include <linux/numa.h>
#include <linux/seq_file.h>
#include <linux/refcount.h>
#include <linux/mutex.h>
enum bpf_struct_ops_state {
BPF_STRUCT_OPS_STATE_INIT,
BPF_STRUCT_OPS_STATE_INUSE,
BPF_STRUCT_OPS_STATE_TOBEFREE,
};
#define BPF_STRUCT_OPS_COMMON_VALUE \
refcount_t refcnt; \
enum bpf_struct_ops_state state
struct bpf_struct_ops_value {
BPF_STRUCT_OPS_COMMON_VALUE;
char data[0] ____cacheline_aligned_in_smp;
};
struct bpf_struct_ops_map {
struct bpf_map map;
const struct bpf_struct_ops *st_ops;
/* protect map_update */
struct mutex lock;
/* progs has all the bpf_prog that is populated
* to the func ptr of the kernel's struct
* (in kvalue.data).
*/
struct bpf_prog **progs;
/* image is a page that has all the trampolines
* that stores the func args before calling the bpf_prog.
* A PAGE_SIZE "image" is enough to store all trampoline for
* "progs[]".
*/
void *image;
/* uvalue->data stores the kernel struct
* (e.g. tcp_congestion_ops) that is more useful
* to userspace than the kvalue. For example,
* the bpf_prog's id is stored instead of the kernel
* address of a func ptr.
*/
struct bpf_struct_ops_value *uvalue;
/* kvalue.data stores the actual kernel's struct
* (e.g. tcp_congestion_ops) that will be
* registered to the kernel subsystem.
*/
struct bpf_struct_ops_value kvalue;
};
#define VALUE_PREFIX "bpf_struct_ops_"
#define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1)
/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is
* the map's value exposed to the userspace and its btf-type-id is
* stored at the map->btf_vmlinux_value_type_id.
*
*/
#define BPF_STRUCT_OPS_TYPE(_name) \
extern struct bpf_struct_ops bpf_##_name; \
\
struct bpf_struct_ops_##_name { \
BPF_STRUCT_OPS_COMMON_VALUE; \
struct _name data ____cacheline_aligned_in_smp; \
};
#include "bpf_struct_ops_types.h"
#undef BPF_STRUCT_OPS_TYPE
enum {
#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name,
#include "bpf_struct_ops_types.h"
#undef BPF_STRUCT_OPS_TYPE
__NR_BPF_STRUCT_OPS_TYPE,
};
static struct bpf_struct_ops * const bpf_struct_ops[] = {
#define BPF_STRUCT_OPS_TYPE(_name) \
[BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name,
#include "bpf_struct_ops_types.h"
#undef BPF_STRUCT_OPS_TYPE
};
const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = {
};
const struct bpf_prog_ops bpf_struct_ops_prog_ops = {
};
static const struct btf_type *module_type;
void bpf_struct_ops_init(struct btf *btf)
{
s32 type_id, value_id, module_id;
const struct btf_member *member;
struct bpf_struct_ops *st_ops;
struct bpf_verifier_log log = {};
const struct btf_type *t;
char value_name[128];
const char *mname;
u32 i, j;
/* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */
#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name);
#include "bpf_struct_ops_types.h"
#undef BPF_STRUCT_OPS_TYPE
module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT);
if (module_id < 0) {
pr_warn("Cannot find struct module in btf_vmlinux\n");
return;
}
module_type = btf_type_by_id(btf, module_id);
for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) {
st_ops = bpf_struct_ops[i];
if (strlen(st_ops->name) + VALUE_PREFIX_LEN >=
sizeof(value_name)) {
pr_warn("struct_ops name %s is too long\n",
st_ops->name);
continue;
}
sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name);
value_id = btf_find_by_name_kind(btf, value_name,
BTF_KIND_STRUCT);
if (value_id < 0) {
pr_warn("Cannot find struct %s in btf_vmlinux\n",
value_name);
continue;
}
type_id = btf_find_by_name_kind(btf, st_ops->name,
BTF_KIND_STRUCT);
if (type_id < 0) {
pr_warn("Cannot find struct %s in btf_vmlinux\n",
st_ops->name);
continue;
}
t = btf_type_by_id(btf, type_id);
if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) {
pr_warn("Cannot support #%u members in struct %s\n",
btf_type_vlen(t), st_ops->name);
continue;
}
for_each_member(j, t, member) {
const struct btf_type *func_proto;
mname = btf_name_by_offset(btf, member->name_off);
if (!*mname) {
pr_warn("anon member in struct %s is not supported\n",
st_ops->name);
break;
}
if (btf_member_bitfield_size(t, member)) {
pr_warn("bit field member %s in struct %s is not supported\n",
mname, st_ops->name);
break;
}
func_proto = btf_type_resolve_func_ptr(btf,
member->type,
NULL);
if (func_proto &&
btf_distill_func_proto(&log, btf,
func_proto, mname,
&st_ops->func_models[j])) {
pr_warn("Error in parsing func ptr %s in struct %s\n",
mname, st_ops->name);
break;
}
}
if (j == btf_type_vlen(t)) {
if (st_ops->init(btf)) {
pr_warn("Error in init bpf_struct_ops %s\n",
st_ops->name);
} else {
st_ops->type_id = type_id;
st_ops->type = t;
st_ops->value_id = value_id;
st_ops->value_type = btf_type_by_id(btf,
value_id);
}
}
}
}
extern struct btf *btf_vmlinux;
static const struct bpf_struct_ops *
bpf_struct_ops_find_value(u32 value_id)
{
unsigned int i;
if (!value_id || !btf_vmlinux)
return NULL;
for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) {
if (bpf_struct_ops[i]->value_id == value_id)
return bpf_struct_ops[i];
}
return NULL;
}
const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
{
unsigned int i;
if (!type_id || !btf_vmlinux)
return NULL;
for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) {
if (bpf_struct_ops[i]->type_id == type_id)
return bpf_struct_ops[i];
}
return NULL;
}
static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key,
void *next_key)
{
if (key && *(u32 *)key == 0)
return -ENOENT;
*(u32 *)next_key = 0;
return 0;
}
int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
void *value)
{
struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
struct bpf_struct_ops_value *uvalue, *kvalue;
enum bpf_struct_ops_state state;
if (unlikely(*(u32 *)key != 0))
return -ENOENT;
kvalue = &st_map->kvalue;
/* Pair with smp_store_release() during map_update */
state = smp_load_acquire(&kvalue->state);
if (state == BPF_STRUCT_OPS_STATE_INIT) {
memset(value, 0, map->value_size);
return 0;
}
/* No lock is needed. state and refcnt do not need
* to be updated together under atomic context.
*/
uvalue = (struct bpf_struct_ops_value *)value;
memcpy(uvalue, st_map->uvalue, map->value_size);
uvalue->state = state;
refcount_set(&uvalue->refcnt, refcount_read(&kvalue->refcnt));
return 0;
}
static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key)
{
return ERR_PTR(-EINVAL);
}
static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map)
{
const struct btf_type *t = st_map->st_ops->type;
u32 i;
for (i = 0; i < btf_type_vlen(t); i++) {
if (st_map->progs[i]) {
bpf_prog_put(st_map->progs[i]);
st_map->progs[i] = NULL;
}
}
}
static int check_zero_holes(const struct btf_type *t, void *data)
{
const struct btf_member *member;
u32 i, moff, msize, prev_mend = 0;
const struct btf_type *mtype;
for_each_member(i, t, member) {
moff = btf_member_bit_offset(t, member) / 8;
if (moff > prev_mend &&
memchr_inv(data + prev_mend, 0, moff - prev_mend))
return -EINVAL;
mtype = btf_type_by_id(btf_vmlinux, member->type);
mtype = btf_resolve_size(btf_vmlinux, mtype, &msize,
NULL, NULL);
if (IS_ERR(mtype))
return PTR_ERR(mtype);
prev_mend = moff + msize;
}
if (t->size > prev_mend &&
memchr_inv(data + prev_mend, 0, t->size - prev_mend))
return -EINVAL;
return 0;
}
static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
void *value, u64 flags)
{
struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
const struct bpf_struct_ops *st_ops = st_map->st_ops;
struct bpf_struct_ops_value *uvalue, *kvalue;
const struct btf_member *member;
const struct btf_type *t = st_ops->type;
void *udata, *kdata;
int prog_fd, err = 0;
void *image;
u32 i;
if (flags)
return -EINVAL;
if (*(u32 *)key != 0)
return -E2BIG;
err = check_zero_holes(st_ops->value_type, value);
if (err)
return err;
uvalue = (struct bpf_struct_ops_value *)value;
err = check_zero_holes(t, uvalue->data);
if (err)
return err;
if (uvalue->state || refcount_read(&uvalue->refcnt))
return -EINVAL;
uvalue = (struct bpf_struct_ops_value *)st_map->uvalue;
kvalue = (struct bpf_struct_ops_value *)&st_map->kvalue;
mutex_lock(&st_map->lock);
if (kvalue->state != BPF_STRUCT_OPS_STATE_INIT) {
err = -EBUSY;
goto unlock;
}
memcpy(uvalue, value, map->value_size);
udata = &uvalue->data;
kdata = &kvalue->data;
image = st_map->image;
for_each_member(i, t, member) {
const struct btf_type *mtype, *ptype;
struct bpf_prog *prog;
u32 moff;
moff = btf_member_bit_offset(t, member) / 8;
ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL);
if (ptype == module_type) {
if (*(void **)(udata + moff))
goto reset_unlock;
*(void **)(kdata + moff) = BPF_MODULE_OWNER;
continue;
}
err = st_ops->init_member(t, member, kdata, udata);
if (err < 0)
goto reset_unlock;
/* The ->init_member() has handled this member */
if (err > 0)
continue;
/* If st_ops->init_member does not handle it,
* we will only handle func ptrs and zero-ed members
* here. Reject everything else.
*/
/* All non func ptr member must be 0 */
if (!ptype || !btf_type_is_func_proto(ptype)) {
u32 msize;
mtype = btf_type_by_id(btf_vmlinux, member->type);
mtype = btf_resolve_size(btf_vmlinux, mtype, &msize,
NULL, NULL);
if (IS_ERR(mtype)) {
err = PTR_ERR(mtype);
goto reset_unlock;
}
if (memchr_inv(udata + moff, 0, msize)) {
err = -EINVAL;
goto reset_unlock;
}
continue;
}
prog_fd = (int)(*(unsigned long *)(udata + moff));
/* Similar check as the attr->attach_prog_fd */
if (!prog_fd)
continue;
prog = bpf_prog_get(prog_fd);
if (IS_ERR(prog)) {
err = PTR_ERR(prog);
goto reset_unlock;
}
st_map->progs[i] = prog;
if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
prog->aux->attach_btf_id != st_ops->type_id ||
prog->expected_attach_type != i) {
err = -EINVAL;
goto reset_unlock;
}
err = arch_prepare_bpf_trampoline(image,
st_map->image + PAGE_SIZE,
&st_ops->func_models[i], 0,
&prog, 1, NULL, 0, NULL);
if (err < 0)
goto reset_unlock;
*(void **)(kdata + moff) = image;
image += err;
/* put prog_id to udata */
*(unsigned long *)(udata + moff) = prog->aux->id;
}
refcount_set(&kvalue->refcnt, 1);
bpf_map_inc(map);
set_memory_ro((long)st_map->image, 1);
set_memory_x((long)st_map->image, 1);
err = st_ops->reg(kdata);
if (likely(!err)) {
/* Pair with smp_load_acquire() during lookup_elem().
* It ensures the above udata updates (e.g. prog->aux->id)
* can be seen once BPF_STRUCT_OPS_STATE_INUSE is set.
*/
smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE);
goto unlock;
}
/* Error during st_ops->reg(). It is very unlikely since
* the above init_member() should have caught it earlier
* before reg(). The only possibility is if there was a race
* in registering the struct_ops (under the same name) to
* a sub-system through different struct_ops's maps.
*/
set_memory_nx((long)st_map->image, 1);
set_memory_rw((long)st_map->image, 1);
bpf_map_put(map);
reset_unlock:
bpf_struct_ops_map_put_progs(st_map);
memset(uvalue, 0, map->value_size);
memset(kvalue, 0, map->value_size);
unlock:
mutex_unlock(&st_map->lock);
return err;
}
static int bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key)
{
enum bpf_struct_ops_state prev_state;
struct bpf_struct_ops_map *st_map;
st_map = (struct bpf_struct_ops_map *)map;
prev_state = cmpxchg(&st_map->kvalue.state,
BPF_STRUCT_OPS_STATE_INUSE,
BPF_STRUCT_OPS_STATE_TOBEFREE);
if (prev_state == BPF_STRUCT_OPS_STATE_INUSE) {
st_map->st_ops->unreg(&st_map->kvalue.data);
if (refcount_dec_and_test(&st_map->kvalue.refcnt))
bpf_map_put(map);
}
return 0;
}
static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key,
struct seq_file *m)
{
void *value;
int err;
value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
if (!value)
return;
err = bpf_struct_ops_map_sys_lookup_elem(map, key, value);
if (!err) {
btf_type_seq_show(btf_vmlinux, map->btf_vmlinux_value_type_id,
value, m);
seq_puts(m, "\n");
}
kfree(value);
}
static void bpf_struct_ops_map_free(struct bpf_map *map)
{
struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
if (st_map->progs)
bpf_struct_ops_map_put_progs(st_map);
bpf_map_area_free(st_map->progs);
bpf_jit_free_exec(st_map->image);
bpf_map_area_free(st_map->uvalue);
bpf_map_area_free(st_map);
}
static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr)
{
if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 ||
attr->map_flags || !attr->btf_vmlinux_value_type_id)
return -EINVAL;
return 0;
}
static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
{
const struct bpf_struct_ops *st_ops;
size_t map_total_size, st_map_size;
struct bpf_struct_ops_map *st_map;
const struct btf_type *t, *vt;
struct bpf_map_memory mem;
struct bpf_map *map;
int err;
if (!capable(CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id);
if (!st_ops)
return ERR_PTR(-ENOTSUPP);
vt = st_ops->value_type;
if (attr->value_size != vt->size)
return ERR_PTR(-EINVAL);
t = st_ops->type;
st_map_size = sizeof(*st_map) +
/* kvalue stores the
* struct bpf_struct_ops_tcp_congestions_ops
*/
(vt->size - sizeof(struct bpf_struct_ops_value));
map_total_size = st_map_size +
/* uvalue */
sizeof(vt->size) +
/* struct bpf_progs **progs */
btf_type_vlen(t) * sizeof(struct bpf_prog *);
err = bpf_map_charge_init(&mem, map_total_size);
if (err < 0)
return ERR_PTR(err);
st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE);
if (!st_map) {
bpf_map_charge_finish(&mem);
return ERR_PTR(-ENOMEM);
}
st_map->st_ops = st_ops;
map = &st_map->map;
st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
st_map->progs =
bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_prog *),
NUMA_NO_NODE);
st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
if (!st_map->uvalue || !st_map->progs || !st_map->image) {
bpf_struct_ops_map_free(map);
bpf_map_charge_finish(&mem);
return ERR_PTR(-ENOMEM);
}
mutex_init(&st_map->lock);
set_vm_flush_reset_perms(st_map->image);
bpf_map_init_from_attr(map, attr);
bpf_map_charge_move(&map->memory, &mem);
return map;
}
const struct bpf_map_ops bpf_struct_ops_map_ops = {
.map_alloc_check = bpf_struct_ops_map_alloc_check,
.map_alloc = bpf_struct_ops_map_alloc,
.map_free = bpf_struct_ops_map_free,
.map_get_next_key = bpf_struct_ops_map_get_next_key,
.map_lookup_elem = bpf_struct_ops_map_lookup_elem,
.map_delete_elem = bpf_struct_ops_map_delete_elem,
.map_update_elem = bpf_struct_ops_map_update_elem,
.map_seq_show_elem = bpf_struct_ops_map_seq_show_elem,
};
/* "const void *" because some subsystem is
* passing a const (e.g. const struct tcp_congestion_ops *)
*/
bool bpf_struct_ops_get(const void *kdata)
{
struct bpf_struct_ops_value *kvalue;
kvalue = container_of(kdata, struct bpf_struct_ops_value, data);
return refcount_inc_not_zero(&kvalue->refcnt);
}
void bpf_struct_ops_put(const void *kdata)
{
struct bpf_struct_ops_value *kvalue;
kvalue = container_of(kdata, struct bpf_struct_ops_value, data);
if (refcount_dec_and_test(&kvalue->refcnt)) {
struct bpf_struct_ops_map *st_map;
st_map = container_of(kvalue, struct bpf_struct_ops_map,
kvalue);
bpf_map_put(&st_map->map);
}
}

9
kernel/bpf/bpf_struct_ops_types.h Normal file
View File

@ -0,0 +1,9 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* internal file - do not include directly */
#ifdef CONFIG_BPF_JIT
#ifdef CONFIG_INET
#include <net/tcp.h>
BPF_STRUCT_OPS_TYPE(tcp_congestion_ops)
#endif
#endif

488
kernel/bpf/btf.c
View File

@ -180,11 +180,6 @@
*/
#define BTF_MAX_SIZE (16 * 1024 * 1024)
#define for_each_member(i, struct_type, member) \
for (i = 0, member = btf_type_member(struct_type); \
i < btf_type_vlen(struct_type); \
i++, member++)
#define for_each_member_from(i, from, struct_type, member) \
for (i = from, member = btf_type_member(struct_type) + from; \
i < btf_type_vlen(struct_type); \
@ -281,6 +276,11 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
[BTF_KIND_DATASEC] = "DATASEC",
};
static const char *btf_type_str(const struct btf_type *t)
{
return btf_kind_str[BTF_INFO_KIND(t->info)];
}
struct btf_kind_operations {
s32 (*check_meta)(struct btf_verifier_env *env,
const struct btf_type *t,
@ -382,6 +382,65 @@ static bool btf_type_is_datasec(const struct btf_type *t)
return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
}
s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind)
{
const struct btf_type *t;
const char *tname;
u32 i;
for (i = 1; i <= btf->nr_types; i++) {
t = btf->types[i];
if (BTF_INFO_KIND(t->info) != kind)
continue;
tname = btf_name_by_offset(btf, t->name_off);
if (!strcmp(tname, name))
return i;
}
return -ENOENT;
}
const struct btf_type *btf_type_skip_modifiers(const struct btf *btf,
u32 id, u32 *res_id)
{
const struct btf_type *t = btf_type_by_id(btf, id);
while (btf_type_is_modifier(t)) {
id = t->type;
t = btf_type_by_id(btf, t->type);
}
if (res_id)
*res_id = id;
return t;
}
const struct btf_type *btf_type_resolve_ptr(const struct btf *btf,
u32 id, u32 *res_id)
{
const struct btf_type *t;
t = btf_type_skip_modifiers(btf, id, NULL);
if (!btf_type_is_ptr(t))
return NULL;
return btf_type_skip_modifiers(btf, t->type, res_id);
}
const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf,
u32 id, u32 *res_id)
{
const struct btf_type *ptype;
ptype = btf_type_resolve_ptr(btf, id, res_id);
if (ptype && btf_type_is_func_proto(ptype))
return ptype;
return NULL;
}
/* Types that act only as a source, not sink or intermediate
* type when resolving.
*/
@ -446,30 +505,6 @@ static const char *btf_int_encoding_str(u8 encoding)
return "UNKN";
}
static u16 btf_type_vlen(const struct btf_type *t)
{
return BTF_INFO_VLEN(t->info);
}
static bool btf_type_kflag(const struct btf_type *t)
{
return BTF_INFO_KFLAG(t->info);
}
static u32 btf_member_bit_offset(const struct btf_type *struct_type,
const struct btf_member *member)
{
return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset)
: member->offset;
}
static u32 btf_member_bitfield_size(const struct btf_type *struct_type,
const struct btf_member *member)
{
return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset)
: 0;
}
static u32 btf_type_int(const struct btf_type *t)
{
return *(u32 *)(t + 1);
@ -480,11 +515,6 @@ static const struct btf_array *btf_type_array(const struct btf_type *t)
return (const struct btf_array *)(t + 1);
}
static const struct btf_member *btf_type_member(const struct btf_type *t)
{
return (const struct btf_member *)(t + 1);
}
static const struct btf_enum *btf_type_enum(const struct btf_type *t)
{
return (const struct btf_enum *)(t + 1);
@ -1057,7 +1087,7 @@ static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env)
* *elem_type: same as return type ("struct X")
* *total_nelems: 1
*/
static const struct btf_type *
const struct btf_type *
btf_resolve_size(const struct btf *btf, const struct btf_type *type,
u32 *type_size, const struct btf_type **elem_type,
u32 *total_nelems)
@ -1111,8 +1141,10 @@ resolved:
return ERR_PTR(-EINVAL);
*type_size = nelems * size;
*total_nelems = nelems;
*elem_type = type;
if (total_nelems)
*total_nelems = nelems;
if (elem_type)
*elem_type = type;
return array_type ? : type;
}
@ -1826,7 +1858,10 @@ static void btf_modifier_seq_show(const struct btf *btf,
u32 type_id, void *data,
u8 bits_offset, struct seq_file *m)
{
t = btf_type_id_resolve(btf, &type_id);
if (btf->resolved_ids)
t = btf_type_id_resolve(btf, &type_id);
else
t = btf_type_skip_modifiers(btf, type_id, NULL);
btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
}
@ -2621,8 +2656,8 @@ static s32 btf_func_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
if (btf_type_vlen(t)) {
btf_verifier_log_type(env, t, "vlen != 0");
if (btf_type_vlen(t) > BTF_FUNC_GLOBAL) {
btf_verifier_log_type(env, t, "Invalid func linkage");
return -EINVAL;
}
@ -3476,7 +3511,8 @@ static u8 bpf_ctx_convert_map[] = {
static const struct btf_member *
btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
const struct btf_type *t, enum bpf_prog_type prog_type)
const struct btf_type *t, enum bpf_prog_type prog_type,
int arg)
{
const struct btf_type *conv_struct;
const struct btf_type *ctx_struct;
@ -3497,12 +3533,13 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
* is not supported yet.
* BPF_PROG_TYPE_RAW_TRACEPOINT is fine.
*/
bpf_log(log, "BPF program ctx type is not a struct\n");
if (log->level & BPF_LOG_LEVEL)
bpf_log(log, "arg#%d type is not a struct\n", arg);
return NULL;
}
tname = btf_name_by_offset(btf, t->name_off);
if (!tname) {
bpf_log(log, "BPF program ctx struct doesn't have a name\n");
bpf_log(log, "arg#%d struct doesn't have a name\n", arg);
return NULL;
}
/* prog_type is valid bpf program type. No need for bounds check. */
@ -3535,11 +3572,12 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf,
static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
struct btf *btf,
const struct btf_type *t,
enum bpf_prog_type prog_type)
enum bpf_prog_type prog_type,
int arg)
{
const struct btf_member *prog_ctx_type, *kern_ctx_type;
prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type);
prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg);
if (!prog_ctx_type)
return -ENOENT;
kern_ctx_type = prog_ctx_type + 1;
@ -3605,6 +3643,8 @@ struct btf *btf_parse_vmlinux(void)
goto errout;
}
bpf_struct_ops_init(btf);
btf_verifier_env_free(env);
refcount_set(&btf->refcnt, 1);
return btf;
@ -3677,7 +3717,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
/* skip modifiers */
while (btf_type_is_modifier(t))
t = btf_type_by_id(btf, t->type);
if (btf_type_is_int(t))
if (btf_type_is_int(t) || btf_type_is_enum(t))
/* accessing a scalar */
return true;
if (!btf_type_is_ptr(t)) {
@ -3697,10 +3737,9 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
/* this is a pointer to another type */
info->reg_type = PTR_TO_BTF_ID;
info->btf_id = t->type;
if (tgt_prog) {
ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type);
ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type, arg);
if (ret > 0) {
info->btf_id = ret;
return true;
@ -3708,10 +3747,14 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
return false;
}
}
info->btf_id = t->type;
t = btf_type_by_id(btf, t->type);
/* skip modifiers */
while (btf_type_is_modifier(t))
while (btf_type_is_modifier(t)) {
info->btf_id = t->type;
t = btf_type_by_id(btf, t->type);
}
if (!btf_type_is_struct(t)) {
bpf_log(log,
"func '%s' arg%d type %s is not a struct\n",
@ -3737,23 +3780,57 @@ int btf_struct_access(struct bpf_verifier_log *log,
again:
tname = __btf_name_by_offset(btf_vmlinux, t->name_off);
if (!btf_type_is_struct(t)) {
bpf_log(log, "Type '%s' is not a struct", tname);
bpf_log(log, "Type '%s' is not a struct\n", tname);
return -EINVAL;
}
for_each_member(i, t, member) {
if (btf_member_bitfield_size(t, member))
/* bitfields are not supported yet */
continue;
if (off + size > t->size) {
bpf_log(log, "access beyond struct %s at off %u size %u\n",
tname, off, size);
return -EACCES;
}
for_each_member(i, t, member) {
/* offset of the field in bytes */
moff = btf_member_bit_offset(t, member) / 8;
if (off + size <= moff)
/* won't find anything, field is already too far */
break;
if (btf_member_bitfield_size(t, member)) {
u32 end_bit = btf_member_bit_offset(t, member) +
btf_member_bitfield_size(t, member);
/* off <= moff instead of off == moff because clang
* does not generate a BTF member for anonymous
* bitfield like the ":16" here:
* struct {
* int :16;
* int x:8;
* };
*/
if (off <= moff &&
BITS_ROUNDUP_BYTES(end_bit) <= off + size)
return SCALAR_VALUE;
/* off may be accessing a following member
*
* or
*
* Doing partial access at either end of this
* bitfield. Continue on this case also to
* treat it as not accessing this bitfield
* and eventually error out as field not
* found to keep it simple.
* It could be relaxed if there was a legit
* partial access case later.
*/
continue;
}
/* In case of "off" is pointing to holes of a struct */
if (off < moff)
continue;
break;
/* type of the field */
mtype = btf_type_by_id(btf_vmlinux, member->type);
@ -4043,11 +4120,158 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
return 0;
}
int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog)
/* Compare BTFs of two functions assuming only scalars and pointers to context.
* t1 points to BTF_KIND_FUNC in btf1
* t2 points to BTF_KIND_FUNC in btf2
* Returns:
* EINVAL - function prototype mismatch
* EFAULT - verifier bug
* 0 - 99% match. The last 1% is validated by the verifier.
*/
int btf_check_func_type_match(struct bpf_verifier_log *log,
struct btf *btf1, const struct btf_type *t1,
struct btf *btf2, const struct btf_type *t2)
{
const struct btf_param *args1, *args2;
const char *fn1, *fn2, *s1, *s2;
u32 nargs1, nargs2, i;
fn1 = btf_name_by_offset(btf1, t1->name_off);
fn2 = btf_name_by_offset(btf2, t2->name_off);
if (btf_func_linkage(t1) != BTF_FUNC_GLOBAL) {
bpf_log(log, "%s() is not a global function\n", fn1);
return -EINVAL;
}
if (btf_func_linkage(t2) != BTF_FUNC_GLOBAL) {
bpf_log(log, "%s() is not a global function\n", fn2);
return -EINVAL;
}
t1 = btf_type_by_id(btf1, t1->type);
if (!t1 || !btf_type_is_func_proto(t1))
return -EFAULT;
t2 = btf_type_by_id(btf2, t2->type);
if (!t2 || !btf_type_is_func_proto(t2))
return -EFAULT;
args1 = (const struct btf_param *)(t1 + 1);
nargs1 = btf_type_vlen(t1);
args2 = (const struct btf_param *)(t2 + 1);
nargs2 = btf_type_vlen(t2);
if (nargs1 != nargs2) {
bpf_log(log, "%s() has %d args while %s() has %d args\n",
fn1, nargs1, fn2, nargs2);
return -EINVAL;
}
t1 = btf_type_skip_modifiers(btf1, t1->type, NULL);
t2 = btf_type_skip_modifiers(btf2, t2->type, NULL);
if (t1->info != t2->info) {
bpf_log(log,
"Return type %s of %s() doesn't match type %s of %s()\n",
btf_type_str(t1), fn1,
btf_type_str(t2), fn2);
return -EINVAL;
}
for (i = 0; i < nargs1; i++) {
t1 = btf_type_skip_modifiers(btf1, args1[i].type, NULL);
t2 = btf_type_skip_modifiers(btf2, args2[i].type, NULL);
if (t1->info != t2->info) {
bpf_log(log, "arg%d in %s() is %s while %s() has %s\n",
i, fn1, btf_type_str(t1),
fn2, btf_type_str(t2));
return -EINVAL;
}
if (btf_type_has_size(t1) && t1->size != t2->size) {
bpf_log(log,
"arg%d in %s() has size %d while %s() has %d\n",
i, fn1, t1->size,
fn2, t2->size);
return -EINVAL;
}
/* global functions are validated with scalars and pointers
* to context only. And only global functions can be replaced.
* Hence type check only those types.
*/
if (btf_type_is_int(t1) || btf_type_is_enum(t1))
continue;
if (!btf_type_is_ptr(t1)) {
bpf_log(log,
"arg%d in %s() has unrecognized type\n",
i, fn1);
return -EINVAL;
}
t1 = btf_type_skip_modifiers(btf1, t1->type, NULL);
t2 = btf_type_skip_modifiers(btf2, t2->type, NULL);
if (!btf_type_is_struct(t1)) {
bpf_log(log,
"arg%d in %s() is not a pointer to context\n",
i, fn1);
return -EINVAL;
}
if (!btf_type_is_struct(t2)) {
bpf_log(log,
"arg%d in %s() is not a pointer to context\n",
i, fn2);
return -EINVAL;
}
/* This is an optional check to make program writing easier.
* Compare names of structs and report an error to the user.
* btf_prepare_func_args() already checked that t2 struct
* is a context type. btf_prepare_func_args() will check
* later that t1 struct is a context type as well.
*/
s1 = btf_name_by_offset(btf1, t1->name_off);
s2 = btf_name_by_offset(btf2, t2->name_off);
if (strcmp(s1, s2)) {
bpf_log(log,
"arg%d %s(struct %s *) doesn't match %s(struct %s *)\n",
i, fn1, s1, fn2, s2);
return -EINVAL;
}
}
return 0;
}
/* Compare BTFs of given program with BTF of target program */
int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
struct btf *btf2, const struct btf_type *t2)
{
struct btf *btf1 = prog->aux->btf;
const struct btf_type *t1;
u32 btf_id = 0;
if (!prog->aux->func_info) {
bpf_log(&env->log, "Program extension requires BTF\n");
return -EINVAL;
}
btf_id = prog->aux->func_info[0].type_id;
if (!btf_id)
return -EFAULT;
t1 = btf_type_by_id(btf1, btf_id);
if (!t1 || !btf_type_is_func(t1))
return -EFAULT;
return btf_check_func_type_match(&env->log, btf1, t1, btf2, t2);
}
/* Compare BTF of a function with given bpf_reg_state.
* Returns:
* EFAULT - there is a verifier bug. Abort verification.
* EINVAL - there is a type mismatch or BTF is not available.
* 0 - BTF matches with what bpf_reg_state expects.
* Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
*/
int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
struct bpf_reg_state *reg)
{
struct bpf_verifier_state *st = env->cur_state;
struct bpf_func_state *func = st->frame[st->curframe];
struct bpf_reg_state *reg = func->regs;
struct bpf_verifier_log *log = &env->log;
struct bpf_prog *prog = env->prog;
struct btf *btf = prog->aux->btf;
@ -4057,27 +4281,30 @@ int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog)
const char *tname;
if (!prog->aux->func_info)
return 0;
return -EINVAL;
btf_id = prog->aux->func_info[subprog].type_id;
if (!btf_id)
return 0;
return -EFAULT;
if (prog->aux->func_info_aux[subprog].unreliable)
return 0;
return -EINVAL;
t = btf_type_by_id(btf, btf_id);
if (!t || !btf_type_is_func(t)) {
bpf_log(log, "BTF of subprog %d doesn't point to KIND_FUNC\n",
/* These checks were already done by the verifier while loading
* struct bpf_func_info
*/
bpf_log(log, "BTF of func#%d doesn't point to KIND_FUNC\n",
subprog);
return -EINVAL;
return -EFAULT;
}
tname = btf_name_by_offset(btf, t->name_off);
t = btf_type_by_id(btf, t->type);
if (!t || !btf_type_is_func_proto(t)) {
bpf_log(log, "Invalid type of func %s\n", tname);
return -EINVAL;
bpf_log(log, "Invalid BTF of func %s\n", tname);
return -EFAULT;
}
args = (const struct btf_param *)(t + 1);
nargs = btf_type_vlen(t);
@ -4103,25 +4330,130 @@ int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog)
bpf_log(log, "R%d is not a pointer\n", i + 1);
goto out;
}
/* If program is passing PTR_TO_CTX into subprogram
* check that BTF type matches.
/* If function expects ctx type in BTF check that caller
* is passing PTR_TO_CTX.
*/
if (reg[i + 1].type == PTR_TO_CTX &&
!btf_get_prog_ctx_type(log, btf, t, prog->type))
goto out;
/* All other pointers are ok */
continue;
if (btf_get_prog_ctx_type(log, btf, t, prog->type, i)) {
if (reg[i + 1].type != PTR_TO_CTX) {
bpf_log(log,
"arg#%d expected pointer to ctx, but got %s\n",
i, btf_kind_str[BTF_INFO_KIND(t->info)]);
goto out;
}
if (check_ctx_reg(env, &reg[i + 1], i + 1))
goto out;
continue;
}
}
bpf_log(log, "Unrecognized argument type %s\n",
btf_kind_str[BTF_INFO_KIND(t->info)]);
bpf_log(log, "Unrecognized arg#%d type %s\n",
i, btf_kind_str[BTF_INFO_KIND(t->info)]);
goto out;
}
return 0;
out:
/* LLVM optimizations can remove arguments from static functions. */
bpf_log(log,
"Type info disagrees with actual arguments due to compiler optimizations\n");
/* Compiler optimizations can remove arguments from static functions
* or mismatched type can be passed into a global function.
* In such cases mark the function as unreliable from BTF point of view.
*/
prog->aux->func_info_aux[subprog].unreliable = true;
return -EINVAL;
}
/* Convert BTF of a function into bpf_reg_state if possible
* Returns:
* EFAULT - there is a verifier bug. Abort verification.
* EINVAL - cannot convert BTF.
* 0 - Successfully converted BTF into bpf_reg_state
* (either PTR_TO_CTX or SCALAR_VALUE).
*/
int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
struct bpf_reg_state *reg)
{
struct bpf_verifier_log *log = &env->log;
struct bpf_prog *prog = env->prog;
enum bpf_prog_type prog_type = prog->type;
struct btf *btf = prog->aux->btf;
const struct btf_param *args;
const struct btf_type *t;
u32 i, nargs, btf_id;
const char *tname;
if (!prog->aux->func_info ||
prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) {
bpf_log(log, "Verifier bug\n");
return -EFAULT;
}
btf_id = prog->aux->func_info[subprog].type_id;
if (!btf_id) {
bpf_log(log, "Global functions need valid BTF\n");
return -EFAULT;
}
t = btf_type_by_id(btf, btf_id);
if (!t || !btf_type_is_func(t)) {
/* These checks were already done by the verifier while loading
* struct bpf_func_info
*/
bpf_log(log, "BTF of func#%d doesn't point to KIND_FUNC\n",
subprog);
return -EFAULT;
}
tname = btf_name_by_offset(btf, t->name_off);
if (log->level & BPF_LOG_LEVEL)
bpf_log(log, "Validating %s() func#%d...\n",
tname, subprog);
if (prog->aux->func_info_aux[subprog].unreliable) {
bpf_log(log, "Verifier bug in function %s()\n", tname);
return -EFAULT;
}
if (prog_type == BPF_PROG_TYPE_EXT)
prog_type = prog->aux->linked_prog->type;
t = btf_type_by_id(btf, t->type);
if (!t || !btf_type_is_func_proto(t)) {
bpf_log(log, "Invalid type of function %s()\n", tname);
return -EFAULT;
}
args = (const struct btf_param *)(t + 1);
nargs = btf_type_vlen(t);
if (nargs > 5) {
bpf_log(log, "Global function %s() with %d > 5 args. Buggy compiler.\n",
tname, nargs);
return -EINVAL;
}
/* check that function returns int */
t = btf_type_by_id(btf, t->type);
while (btf_type_is_modifier(t))
t = btf_type_by_id(btf, t->type);
if (!btf_type_is_int(t) && !btf_type_is_enum(t)) {
bpf_log(log,
"Global function %s() doesn't return scalar. Only those are supported.\n",
tname);
return -EINVAL;
}
/* Convert BTF function arguments into verifier types.
* Only PTR_TO_CTX and SCALAR are supported atm.
*/
for (i = 0; i < nargs; i++) {
t = btf_type_by_id(btf, args[i].type);
while (btf_type_is_modifier(t))
t = btf_type_by_id(btf, t->type);
if (btf_type_is_int(t) || btf_type_is_enum(t)) {
reg[i + 1].type = SCALAR_VALUE;
continue;
}
if (btf_type_is_ptr(t) &&
btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
reg[i + 1].type = PTR_TO_CTX;
continue;
}
bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n",
i, btf_kind_str[BTF_INFO_KIND(t->info)], tname);
return -EINVAL;
}
return 0;
}

1
kernel/bpf/core.c
View File

@ -2137,6 +2137,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto __weak;
const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
const struct bpf_func_proto bpf_spin_lock_proto __weak;
const struct bpf_func_proto bpf_spin_unlock_proto __weak;
const struct bpf_func_proto bpf_jiffies64_proto __weak;
const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;

95
kernel/bpf/devmap.c
View File

@ -53,13 +53,11 @@
(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
#define DEV_MAP_BULK_SIZE 16
struct bpf_dtab_netdev;
struct xdp_bulk_queue {
struct xdp_dev_bulk_queue {
struct xdp_frame *q[DEV_MAP_BULK_SIZE];
struct list_head flush_node;
struct net_device *dev;
struct net_device *dev_rx;
struct bpf_dtab_netdev *obj;
unsigned int count;
};
@ -67,9 +65,8 @@ struct bpf_dtab_netdev {
struct net_device *dev; /* must be first member, due to tracepoint */
struct hlist_node index_hlist;
struct bpf_dtab *dtab;
struct xdp_bulk_queue __percpu *bulkq;
struct rcu_head rcu;
unsigned int idx; /* keep track of map index for tracepoint */
unsigned int idx;
};
struct bpf_dtab {
@ -84,7 +81,7 @@ struct bpf_dtab {
u32 n_buckets;
};
static DEFINE_PER_CPU(struct list_head, dev_map_flush_list);
static DEFINE_PER_CPU(struct list_head, dev_flush_list);
static DEFINE_SPINLOCK(dev_map_lock);
static LIST_HEAD(dev_map_list);
@ -219,7 +216,6 @@ static void dev_map_free(struct bpf_map *map)
hlist_for_each_entry_safe(dev, next, head, index_hlist) {
hlist_del_rcu(&dev->index_hlist);
free_percpu(dev->bulkq);
dev_put(dev->dev);
kfree(dev);
}
@ -234,7 +230,6 @@ static void dev_map_free(struct bpf_map *map)
if (!dev)
continue;
free_percpu(dev->bulkq);
dev_put(dev->dev);
kfree(dev);
}
@ -320,10 +315,9 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
return -ENOENT;
}
static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags)
static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
{
struct bpf_dtab_netdev *obj = bq->obj;
struct net_device *dev = obj->dev;
struct net_device *dev = bq->dev;
int sent = 0, drops = 0, err = 0;
int i;
@ -346,8 +340,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags)
out:
bq->count = 0;
trace_xdp_devmap_xmit(&obj->dtab->map, obj->idx,
sent, drops, bq->dev_rx, dev, err);
trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, drops, err);
bq->dev_rx = NULL;
__list_del_clearprev(&bq->flush_node);
return 0;
@ -364,17 +357,17 @@ error:
goto out;
}
/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled
/* __dev_flush is called from xdp_do_flush() which _must_ be signaled
* from the driver before returning from its napi->poll() routine. The poll()
* routine is called either from busy_poll context or net_rx_action signaled
* from NET_RX_SOFTIRQ. Either way the poll routine must complete before the
* net device can be torn down. On devmap tear down we ensure the flush list
* is empty before completing to ensure all flush operations have completed.
*/
void __dev_map_flush(void)
void __dev_flush(void)
{
struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list);
struct xdp_bulk_queue *bq, *tmp;
struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
struct xdp_dev_bulk_queue *bq, *tmp;
rcu_read_lock();
list_for_each_entry_safe(bq, tmp, flush_list, flush_node)
@ -401,12 +394,11 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
/* Runs under RCU-read-side, plus in softirq under NAPI protection.
* Thus, safe percpu variable access.
*/
static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
struct net_device *dev_rx)
{
struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list);
struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
bq_xmit_all(bq, 0);
@ -426,10 +418,9 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
return 0;
}
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx)
static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
struct net_device *dev = dst->dev;
struct xdp_frame *xdpf;
int err;
@ -444,7 +435,21 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
if (unlikely(!xdpf))
return -EOVERFLOW;
return bq_enqueue(dst, xdpf, dev_rx);
return bq_enqueue(dev, xdpf, dev_rx);
}
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
return __xdp_enqueue(dev, xdp, dev_rx);
}
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
struct net_device *dev = dst->dev;
return __xdp_enqueue(dev, xdp, dev_rx);
}
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
@ -483,7 +488,6 @@ static void __dev_map_entry_free(struct rcu_head *rcu)
struct bpf_dtab_netdev *dev;
dev = container_of(rcu, struct bpf_dtab_netdev, rcu);
free_percpu(dev->bulkq);
dev_put(dev->dev);
kfree(dev);
}
@ -538,30 +542,15 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
u32 ifindex,
unsigned int idx)
{
gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
struct bpf_dtab_netdev *dev;
struct xdp_bulk_queue *bq;
int cpu;
dev = kmalloc_node(sizeof(*dev), gfp, dtab->map.numa_node);
dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN,
dtab->map.numa_node);
if (!dev)
return ERR_PTR(-ENOMEM);
dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq),
sizeof(void *), gfp);
if (!dev->bulkq) {
kfree(dev);
return ERR_PTR(-ENOMEM);
}
for_each_possible_cpu(cpu) {
bq = per_cpu_ptr(dev->bulkq, cpu);
bq->obj = dev;
}
dev->dev = dev_get_by_index(net, ifindex);
if (!dev->dev) {
free_percpu(dev->bulkq);
kfree(dev);
return ERR_PTR(-EINVAL);
}
@ -721,9 +710,23 @@ static int dev_map_notification(struct notifier_block *notifier,
{
struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
struct bpf_dtab *dtab;
int i;
int i, cpu;
switch (event) {
case NETDEV_REGISTER:
if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq)
break;
/* will be freed in free_netdev() */
netdev->xdp_bulkq =
__alloc_percpu_gfp(sizeof(struct xdp_dev_bulk_queue),
sizeof(void *), GFP_ATOMIC);
if (!netdev->xdp_bulkq)
return NOTIFY_BAD;
for_each_possible_cpu(cpu)
per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev;
break;
case NETDEV_UNREGISTER:
/* This rcu_read_lock/unlock pair is needed because
* dev_map_list is an RCU list AND to ensure a delete
@ -771,7 +774,7 @@ static int __init dev_map_init(void)
register_netdevice_notifier(&dev_map_notifier);
for_each_possible_cpu(cpu)
INIT_LIST_HEAD(&per_cpu(dev_map_flush_list, cpu));
INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu));
return 0;
}

264
kernel/bpf/hashtab.c
View File

@ -17,6 +17,16 @@
(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \
BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED)
#define BATCH_OPS(_name) \
.map_lookup_batch = \
_name##_map_lookup_batch, \
.map_lookup_and_delete_batch = \
_name##_map_lookup_and_delete_batch, \
.map_update_batch = \
generic_map_update_batch, \
.map_delete_batch = \
generic_map_delete_batch
struct bucket {
struct hlist_nulls_head head;
raw_spinlock_t lock;
@ -1232,6 +1242,256 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key,
rcu_read_unlock();
}
static int
__htab_map_lookup_and_delete_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr,
bool do_delete, bool is_lru_map,
bool is_percpu)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
u32 bucket_cnt, total, key_size, value_size, roundup_key_size;
void *keys = NULL, *values = NULL, *value, *dst_key, *dst_val;
void __user *uvalues = u64_to_user_ptr(attr->batch.values);
void __user *ukeys = u64_to_user_ptr(attr->batch.keys);
void *ubatch = u64_to_user_ptr(attr->batch.in_batch);
u32 batch, max_count, size, bucket_size;
u64 elem_map_flags, map_flags;
struct hlist_nulls_head *head;
struct hlist_nulls_node *n;
unsigned long flags;
struct htab_elem *l;
struct bucket *b;
int ret = 0;
elem_map_flags = attr->batch.elem_flags;
if ((elem_map_flags & ~BPF_F_LOCK) ||
((elem_map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
return -EINVAL;
map_flags = attr->batch.flags;
if (map_flags)
return -EINVAL;
max_count = attr->batch.count;
if (!max_count)
return 0;
if (put_user(0, &uattr->batch.count))
return -EFAULT;
batch = 0;
if (ubatch && copy_from_user(&batch, ubatch, sizeof(batch)))
return -EFAULT;
if (batch >= htab->n_buckets)
return -ENOENT;
key_size = htab->map.key_size;
roundup_key_size = round_up(htab->map.key_size, 8);
value_size = htab->map.value_size;
size = round_up(value_size, 8);
if (is_percpu)
value_size = size * num_possible_cpus();
total = 0;
/* while experimenting with hash tables with sizes ranging from 10 to
* 1000, it was observed that a bucket can have upto 5 entries.
*/
bucket_size = 5;
alloc:
/* We cannot do copy_from_user or copy_to_user inside
* the rcu_read_lock. Allocate enough space here.
*/
keys = kvmalloc(key_size * bucket_size, GFP_USER | __GFP_NOWARN);
values = kvmalloc(value_size * bucket_size, GFP_USER | __GFP_NOWARN);
if (!keys || !values) {
ret = -ENOMEM;
goto after_loop;
}
again:
preempt_disable();
this_cpu_inc(bpf_prog_active);
rcu_read_lock();
again_nocopy:
dst_key = keys;
dst_val = values;
b = &htab->buckets[batch];
head = &b->head;
raw_spin_lock_irqsave(&b->lock, flags);
bucket_cnt = 0;
hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
bucket_cnt++;
if (bucket_cnt > (max_count - total)) {
if (total == 0)
ret = -ENOSPC;
raw_spin_unlock_irqrestore(&b->lock, flags);
rcu_read_unlock();
this_cpu_dec(bpf_prog_active);
preempt_enable();
goto after_loop;
}
if (bucket_cnt > bucket_size) {
bucket_size = bucket_cnt;
raw_spin_unlock_irqrestore(&b->lock, flags);
rcu_read_unlock();
this_cpu_dec(bpf_prog_active);
preempt_enable();
kvfree(keys);
kvfree(values);
goto alloc;
}
hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
memcpy(dst_key, l->key, key_size);
if (is_percpu) {
int off = 0, cpu;
void __percpu *pptr;
pptr = htab_elem_get_ptr(l, map->key_size);
for_each_possible_cpu(cpu) {
bpf_long_memcpy(dst_val + off,
per_cpu_ptr(pptr, cpu), size);
off += size;
}
} else {
value = l->key + roundup_key_size;
if (elem_map_flags & BPF_F_LOCK)
copy_map_value_locked(map, dst_val, value,
true);
else
copy_map_value(map, dst_val, value);
check_and_init_map_lock(map, dst_val);
}
if (do_delete) {
hlist_nulls_del_rcu(&l->hash_node);
if (is_lru_map)
bpf_lru_push_free(&htab->lru, &l->lru_node);
else
free_htab_elem(htab, l);
}
dst_key += key_size;
dst_val += value_size;
}
raw_spin_unlock_irqrestore(&b->lock, flags);
/* If we are not copying data, we can go to next bucket and avoid
* unlocking the rcu.
*/
if (!bucket_cnt && (batch + 1 < htab->n_buckets)) {
batch++;
goto again_nocopy;
}
rcu_read_unlock();
this_cpu_dec(bpf_prog_active);
preempt_enable();
if (bucket_cnt && (copy_to_user(ukeys + total * key_size, keys,
key_size * bucket_cnt) ||
copy_to_user(uvalues + total * value_size, values,
value_size * bucket_cnt))) {
ret = -EFAULT;
goto after_loop;
}
total += bucket_cnt;
batch++;
if (batch >= htab->n_buckets) {
ret = -ENOENT;
goto after_loop;
}
goto again;
after_loop:
if (ret == -EFAULT)
goto out;
/* copy # of entries and next batch */
ubatch = u64_to_user_ptr(attr->batch.out_batch);
if (copy_to_user(ubatch, &batch, sizeof(batch)) ||
put_user(total, &uattr->batch.count))
ret = -EFAULT;
out:
kvfree(keys);
kvfree(values);
return ret;
}
static int
htab_percpu_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
return __htab_map_lookup_and_delete_batch(map, attr, uattr, false,
false, true);
}
static int
htab_percpu_map_lookup_and_delete_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
return __htab_map_lookup_and_delete_batch(map, attr, uattr, true,
false, true);
}
static int
htab_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
return __htab_map_lookup_and_delete_batch(map, attr, uattr, false,
false, false);
}
static int
htab_map_lookup_and_delete_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
return __htab_map_lookup_and_delete_batch(map, attr, uattr, true,
false, false);
}
static int
htab_lru_percpu_map_lookup_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
return __htab_map_lookup_and_delete_batch(map, attr, uattr, false,
true, true);
}
static int
htab_lru_percpu_map_lookup_and_delete_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
return __htab_map_lookup_and_delete_batch(map, attr, uattr, true,
true, true);
}
static int
htab_lru_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
return __htab_map_lookup_and_delete_batch(map, attr, uattr, false,
true, false);
}
static int
htab_lru_map_lookup_and_delete_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
return __htab_map_lookup_and_delete_batch(map, attr, uattr, true,
true, false);
}
const struct bpf_map_ops htab_map_ops = {
.map_alloc_check = htab_map_alloc_check,
.map_alloc = htab_map_alloc,
@ -1242,6 +1502,7 @@ const struct bpf_map_ops htab_map_ops = {
.map_delete_elem = htab_map_delete_elem,
.map_gen_lookup = htab_map_gen_lookup,
.map_seq_show_elem = htab_map_seq_show_elem,
BATCH_OPS(htab),
};
const struct bpf_map_ops htab_lru_map_ops = {
@ -1255,6 +1516,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
.map_delete_elem = htab_lru_map_delete_elem,
.map_gen_lookup = htab_lru_map_gen_lookup,
.map_seq_show_elem = htab_map_seq_show_elem,
BATCH_OPS(htab_lru),
};
/* Called from eBPF program */
@ -1368,6 +1630,7 @@ const struct bpf_map_ops htab_percpu_map_ops = {
.map_update_elem = htab_percpu_map_update_elem,
.map_delete_elem = htab_map_delete_elem,
.map_seq_show_elem = htab_percpu_map_seq_show_elem,
BATCH_OPS(htab_percpu),
};
const struct bpf_map_ops htab_lru_percpu_map_ops = {
@ -1379,6 +1642,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
.map_update_elem = htab_lru_percpu_map_update_elem,
.map_delete_elem = htab_lru_map_delete_elem,
.map_seq_show_elem = htab_percpu_map_seq_show_elem,
BATCH_OPS(htab_lru_percpu),
};
static int fd_htab_map_alloc_check(union bpf_attr *attr)

12
kernel/bpf/helpers.c
View File

@ -11,6 +11,7 @@
#include <linux/uidgid.h>
#include <linux/filter.h>
#include <linux/ctype.h>
#include <linux/jiffies.h>
#include "../../lib/kstrtox.h"
@ -312,6 +313,17 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
preempt_enable();
}
BPF_CALL_0(bpf_jiffies64)
{
return get_jiffies_64();
}
const struct bpf_func_proto bpf_jiffies64_proto = {
.func = bpf_jiffies64,
.gpl_only = false,
.ret_type = RET_INTEGER,
};
#ifdef CONFIG_CGROUPS
BPF_CALL_0(bpf_get_current_cgroup_id)
{

43
kernel/bpf/inode.c
View File

@ -380,7 +380,7 @@ static const struct inode_operations bpf_dir_iops = {
.unlink = simple_unlink,
};
static int bpf_obj_do_pin(const struct filename *pathname, void *raw,
static int bpf_obj_do_pin(const char __user *pathname, void *raw,
enum bpf_type type)
{
struct dentry *dentry;
@ -389,7 +389,7 @@ static int bpf_obj_do_pin(const struct filename *pathname, void *raw,
umode_t mode;
int ret;
dentry = kern_path_create(AT_FDCWD, pathname->name, &path, 0);
dentry = user_path_create(AT_FDCWD, pathname, &path, 0);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
@ -422,30 +422,22 @@ out:
int bpf_obj_pin_user(u32 ufd, const char __user *pathname)
{
struct filename *pname;
enum bpf_type type;
void *raw;
int ret;
pname = getname(pathname);
if (IS_ERR(pname))
return PTR_ERR(pname);
raw = bpf_fd_probe_obj(ufd, &type);
if (IS_ERR(raw)) {
ret = PTR_ERR(raw);
goto out;
}
if (IS_ERR(raw))
return PTR_ERR(raw);
ret = bpf_obj_do_pin(pname, raw, type);
ret = bpf_obj_do_pin(pathname, raw, type);
if (ret != 0)
bpf_any_put(raw, type);
out:
putname(pname);
return ret;
}
static void *bpf_obj_do_get(const struct filename *pathname,
static void *bpf_obj_do_get(const char __user *pathname,
enum bpf_type *type, int flags)
{
struct inode *inode;
@ -453,7 +445,7 @@ static void *bpf_obj_do_get(const struct filename *pathname,
void *raw;
int ret;
ret = kern_path(pathname->name, LOOKUP_FOLLOW, &path);
ret = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW, &path);
if (ret)
return ERR_PTR(ret);
@ -480,36 +472,27 @@ out:
int bpf_obj_get_user(const char __user *pathname, int flags)
{
enum bpf_type type = BPF_TYPE_UNSPEC;
struct filename *pname;
int ret = -ENOENT;
int f_flags;
void *raw;
int ret;
f_flags = bpf_get_file_flag(flags);
if (f_flags < 0)
return f_flags;
pname = getname(pathname);
if (IS_ERR(pname))
return PTR_ERR(pname);
raw = bpf_obj_do_get(pname, &type, f_flags);
if (IS_ERR(raw)) {
ret = PTR_ERR(raw);
goto out;
}
raw = bpf_obj_do_get(pathname, &type, f_flags);
if (IS_ERR(raw))
return PTR_ERR(raw);
if (type == BPF_TYPE_PROG)
ret = bpf_prog_new_fd(raw);
else if (type == BPF_TYPE_MAP)
ret = bpf_map_new_fd(raw, f_flags);
else
goto out;
return -ENOENT;
if (ret < 0)
bpf_any_put(raw, type);
out:
putname(pname);
return ret;
}

3
kernel/bpf/map_in_map.c
View File

@ -22,7 +22,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
*/
if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE ||
inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE ||
inner_map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
fdput(f);
return ERR_PTR(-ENOTSUPP);
}

632
kernel/bpf/syscall.c
View File

@ -129,6 +129,152 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
return map;
}
static u32 bpf_map_value_size(struct bpf_map *map)
{
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)
return round_up(map->value_size, 8) * num_possible_cpus();
else if (IS_FD_MAP(map))
return sizeof(u32);
else
return map->value_size;
}
static void maybe_wait_bpf_programs(struct bpf_map *map)
{
/* Wait for any running BPF programs to complete so that
* userspace, when we return to it, knows that all programs
* that could be running use the new map value.
*/
if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
synchronize_rcu();
}
static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key,
void *value, __u64 flags)
{
int err;
/* Need to create a kthread, thus must support schedule */
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 (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);
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);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_update(map, key, value, flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
err = bpf_percpu_cgroup_storage_update(map, key, value,
flags);
} else if (IS_FD_ARRAY(map)) {
rcu_read_lock();
err = bpf_fd_array_map_update_elem(map, f.file, key, value,
flags);
rcu_read_unlock();
} else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
rcu_read_lock();
err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
flags);
rcu_read_unlock();
} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
/* rcu_read_lock() is not needed */
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) {
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();
maybe_wait_bpf_programs(map);
return err;
}
static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
__u64 flags)
{
void *ptr;
int err;
if (bpf_map_is_dev_bound(map))
return bpf_map_offload_lookup_elem(map, key, value);
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_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_PERCPU_CGROUP_STORAGE) {
err = bpf_percpu_cgroup_storage_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) || IS_FD_PROG_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 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) {
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" */
err = bpf_struct_ops_map_sys_lookup_elem(map, key, value);
} else {
rcu_read_lock();
if (map->ops->map_lookup_elem_sys_only)
ptr = map->ops->map_lookup_elem_sys_only(map, key);
else
ptr = map->ops->map_lookup_elem(map, key);
if (IS_ERR(ptr)) {
err = PTR_ERR(ptr);
} else if (!ptr) {
err = -ENOENT;
} else {
err = 0;
if (flags & BPF_F_LOCK)
/* lock 'ptr' and copy everything but lock */
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);
}
rcu_read_unlock();
}
this_cpu_dec(bpf_prog_active);
preempt_enable();
maybe_wait_bpf_programs(map);
return err;
}
static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
{
/* We really just want to fail instead of triggering OOM killer
@ -628,7 +774,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
return ret;
}
#define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id
#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
@ -642,6 +788,14 @@ static int map_create(union bpf_attr *attr)
if (err)
return -EINVAL;
if (attr->btf_vmlinux_value_type_id) {
if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS ||
attr->btf_key_type_id || attr->btf_value_type_id)
return -EINVAL;
} else if (attr->btf_key_type_id && !attr->btf_value_type_id) {
return -EINVAL;
}
f_flags = bpf_get_file_flag(attr->map_flags);
if (f_flags < 0)
return f_flags;
@ -664,32 +818,35 @@ static int map_create(union bpf_attr *attr)
atomic64_set(&map->usercnt, 1);
mutex_init(&map->freeze_mutex);
if (attr->btf_key_type_id || attr->btf_value_type_id) {
map->spin_lock_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
* to figure out the corresponding kernel's
* counter part. Thus, attr->btf_fd has
* to be valid also.
*/
attr->btf_vmlinux_value_type_id) {
struct btf *btf;
if (!attr->btf_value_type_id) {
err = -EINVAL;
goto free_map;
}
btf = btf_get_by_fd(attr->btf_fd);
if (IS_ERR(btf)) {
err = PTR_ERR(btf);
goto free_map;
}
map->btf = btf;
err = map_check_btf(map, btf, attr->btf_key_type_id,
attr->btf_value_type_id);
if (err) {
btf_put(btf);
goto free_map;
if (attr->btf_value_type_id) {
err = map_check_btf(map, btf, attr->btf_key_type_id,
attr->btf_value_type_id);
if (err)
goto free_map;
}
map->btf = btf;
map->btf_key_type_id = attr->btf_key_type_id;
map->btf_value_type_id = attr->btf_value_type_id;
} else {
map->spin_lock_off = -EINVAL;
map->btf_vmlinux_value_type_id =
attr->btf_vmlinux_value_type_id;
}
err = security_bpf_map_alloc(map);
@ -816,7 +973,7 @@ static int map_lookup_elem(union bpf_attr *attr)
void __user *uvalue = u64_to_user_ptr(attr->value);
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value, *ptr;
void *key, *value;
u32 value_size;
struct fd f;
int err;
@ -848,72 +1005,14 @@ static int map_lookup_elem(union bpf_attr *attr)
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 if (IS_FD_MAP(map))
value_size = sizeof(u32);
else
value_size = map->value_size;
value_size = bpf_map_value_size(map);
err = -ENOMEM;
value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
if (!value)
goto free_key;
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_lookup_elem(map, key, value);
goto done;
}
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_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_PERCPU_CGROUP_STORAGE) {
err = bpf_percpu_cgroup_storage_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) || IS_FD_PROG_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 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) {
err = map->ops->map_peek_elem(map, value);
} else {
rcu_read_lock();
if (map->ops->map_lookup_elem_sys_only)
ptr = map->ops->map_lookup_elem_sys_only(map, key);
else
ptr = map->ops->map_lookup_elem(map, key);
if (IS_ERR(ptr)) {
err = PTR_ERR(ptr);
} else if (!ptr) {
err = -ENOENT;
} else {
err = 0;
if (attr->flags & BPF_F_LOCK)
/* lock 'ptr' and copy everything but lock */
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);
}
rcu_read_unlock();
}
this_cpu_dec(bpf_prog_active);
preempt_enable();
done:
err = bpf_map_copy_value(map, key, value, attr->flags);
if (err)
goto free_value;
@ -932,16 +1031,6 @@ err_put:
return err;
}
static void maybe_wait_bpf_programs(struct bpf_map *map)
{
/* Wait for any running BPF programs to complete so that
* userspace, when we return to it, knows that all programs
* that could be running use the new map value.
*/
if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
synchronize_rcu();
}
#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
@ -997,60 +1086,8 @@ static int map_update_elem(union bpf_attr *attr)
if (copy_from_user(value, uvalue, value_size) != 0)
goto free_value;
/* Need to create a kthread, thus must support schedule */
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_update_elem(map, key, value, attr->flags);
goto out;
} else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
map->map_type == BPF_MAP_TYPE_SOCKHASH ||
map->map_type == BPF_MAP_TYPE_SOCKMAP) {
err = map->ops->map_update_elem(map, key, value, attr->flags);
goto out;
} else if (IS_FD_PROG_ARRAY(map)) {
err = bpf_fd_array_map_update_elem(map, f.file, key, value,
attr->flags);
goto out;
}
err = bpf_map_update_value(map, f, key, value, attr->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);
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);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_update(map, key, value, attr->flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
err = bpf_percpu_cgroup_storage_update(map, key, value,
attr->flags);
} else if (IS_FD_ARRAY(map)) {
rcu_read_lock();
err = bpf_fd_array_map_update_elem(map, f.file, key, value,
attr->flags);
rcu_read_unlock();
} else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
rcu_read_lock();
err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
attr->flags);
rcu_read_unlock();
} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
/* rcu_read_lock() is not needed */
err = bpf_fd_reuseport_array_update_elem(map, key, value,
attr->flags);
} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
map->map_type == BPF_MAP_TYPE_STACK) {
err = map->ops->map_push_elem(map, value, attr->flags);
} else {
rcu_read_lock();
err = map->ops->map_update_elem(map, key, value, attr->flags);
rcu_read_unlock();
}
__this_cpu_dec(bpf_prog_active);
preempt_enable();
maybe_wait_bpf_programs(map);
out:
free_value:
kfree(value);
free_key:
@ -1092,7 +1129,9 @@ static int map_delete_elem(union bpf_attr *attr)
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_delete_elem(map, key);
goto out;
} else if (IS_FD_PROG_ARRAY(map)) {
} else if (IS_FD_PROG_ARRAY(map) ||
map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
/* These maps require sleepable context */
err = map->ops->map_delete_elem(map, key);
goto out;
}
@ -1179,6 +1218,220 @@ err_put:
return err;
}
int generic_map_delete_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
void __user *keys = u64_to_user_ptr(attr->batch.keys);
u32 cp, max_count;
int err = 0;
void *key;
if (attr->batch.elem_flags & ~BPF_F_LOCK)
return -EINVAL;
if ((attr->batch.elem_flags & BPF_F_LOCK) &&
!map_value_has_spin_lock(map)) {
return -EINVAL;
}
max_count = attr->batch.count;
if (!max_count)
return 0;
key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
if (!key)
return -ENOMEM;
for (cp = 0; cp < max_count; cp++) {
err = -EFAULT;
if (copy_from_user(key, keys + cp * map->key_size,
map->key_size))
break;
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_delete_elem(map, key);
break;
}
preempt_disable();
__this_cpu_inc(bpf_prog_active);
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);
if (err)
break;
}
if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
err = -EFAULT;
kfree(key);
return err;
}
int generic_map_update_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
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;
void *key, *value;
struct fd f;
int err = 0;
f = fdget(ufd);
if (attr->batch.elem_flags & ~BPF_F_LOCK)
return -EINVAL;
if ((attr->batch.elem_flags & BPF_F_LOCK) &&
!map_value_has_spin_lock(map)) {
return -EINVAL;
}
value_size = bpf_map_value_size(map);
max_count = attr->batch.count;
if (!max_count)
return 0;
key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
if (!key)
return -ENOMEM;
value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
if (!value) {
kfree(key);
return -ENOMEM;
}
for (cp = 0; cp < max_count; cp++) {
err = -EFAULT;
if (copy_from_user(key, keys + cp * map->key_size,
map->key_size) ||
copy_from_user(value, values + cp * value_size, value_size))
break;
err = bpf_map_update_value(map, f, key, value,
attr->batch.elem_flags);
if (err)
break;
}
if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
err = -EFAULT;
kfree(value);
kfree(key);
return err;
}
#define MAP_LOOKUP_RETRIES 3
int generic_map_lookup_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
void __user *uobatch = u64_to_user_ptr(attr->batch.out_batch);
void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch);
void __user *values = u64_to_user_ptr(attr->batch.values);
void __user *keys = u64_to_user_ptr(attr->batch.keys);
void *buf, *buf_prevkey, *prev_key, *key, *value;
int err, retry = MAP_LOOKUP_RETRIES;
u32 value_size, cp, max_count;
if (attr->batch.elem_flags & ~BPF_F_LOCK)
return -EINVAL;
if ((attr->batch.elem_flags & BPF_F_LOCK) &&
!map_value_has_spin_lock(map))
return -EINVAL;
value_size = bpf_map_value_size(map);
max_count = attr->batch.count;
if (!max_count)
return 0;
if (put_user(0, &uattr->batch.count))
return -EFAULT;
buf_prevkey = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
if (!buf_prevkey)
return -ENOMEM;
buf = kmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN);
if (!buf) {
kvfree(buf_prevkey);
return -ENOMEM;
}
err = -EFAULT;
prev_key = NULL;
if (ubatch && copy_from_user(buf_prevkey, ubatch, map->key_size))
goto free_buf;
key = buf;
value = key + map->key_size;
if (ubatch)
prev_key = buf_prevkey;
for (cp = 0; cp < max_count;) {
rcu_read_lock();
err = map->ops->map_get_next_key(map, prev_key, key);
rcu_read_unlock();
if (err)
break;
err = bpf_map_copy_value(map, key, value,
attr->batch.elem_flags);
if (err == -ENOENT) {
if (retry) {
retry--;
continue;
}
err = -EINTR;
break;
}
if (err)
goto free_buf;
if (copy_to_user(keys + cp * map->key_size, key,
map->key_size)) {
err = -EFAULT;
goto free_buf;
}
if (copy_to_user(values + cp * value_size, value, value_size)) {
err = -EFAULT;
goto free_buf;
}
if (!prev_key)
prev_key = buf_prevkey;
swap(prev_key, key);
retry = MAP_LOOKUP_RETRIES;
cp++;
}
if (err == -EFAULT)
goto free_buf;
if ((copy_to_user(&uattr->batch.count, &cp, sizeof(cp)) ||
(cp && copy_to_user(uobatch, prev_key, map->key_size))))
err = -EFAULT;
free_buf:
kfree(buf_prevkey);
kfree(buf);
return err;
}
#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value
static int map_lookup_and_delete_elem(union bpf_attr *attr)
@ -1672,17 +1925,24 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
enum bpf_attach_type expected_attach_type,
u32 btf_id, u32 prog_fd)
{
switch (prog_type) {
case BPF_PROG_TYPE_TRACING:
if (btf_id) {
if (btf_id > BTF_MAX_TYPE)
return -EINVAL;
break;
default:
if (btf_id || prog_fd)
switch (prog_type) {
case BPF_PROG_TYPE_TRACING:
case BPF_PROG_TYPE_STRUCT_OPS:
case BPF_PROG_TYPE_EXT:
break;
default:
return -EINVAL;
break;
}
}
if (prog_fd && prog_type != BPF_PROG_TYPE_TRACING &&
prog_type != BPF_PROG_TYPE_EXT)
return -EINVAL;
switch (prog_type) {
case BPF_PROG_TYPE_CGROUP_SOCK:
switch (expected_attach_type) {
@ -1723,6 +1983,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
default:
return -EINVAL;
}
case BPF_PROG_TYPE_EXT:
if (expected_attach_type)
return -EINVAL;
/* fallthrough */
default:
return 0;
}
@ -1925,7 +2189,8 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
int tr_fd, err;
if (prog->expected_attach_type != BPF_TRACE_FENTRY &&
prog->expected_attach_type != BPF_TRACE_FEXIT) {
prog->expected_attach_type != BPF_TRACE_FEXIT &&
prog->type != BPF_PROG_TYPE_EXT) {
err = -EINVAL;
goto out_put_prog;
}
@ -1992,12 +2257,14 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT &&
prog->type != BPF_PROG_TYPE_TRACING &&
prog->type != BPF_PROG_TYPE_EXT &&
prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) {
err = -EINVAL;
goto out_put_prog;
}
if (prog->type == BPF_PROG_TYPE_TRACING) {
if (prog->type == BPF_PROG_TYPE_TRACING ||
prog->type == BPF_PROG_TYPE_EXT) {
if (attr->raw_tracepoint.name) {
/* The attach point for this category of programs
* should be specified via btf_id during program load.
@ -2817,6 +3084,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
info.btf_key_type_id = map->btf_key_type_id;
info.btf_value_type_id = map->btf_value_type_id;
}
info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id;
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_info_fill(&info, map);
@ -3029,6 +3297,61 @@ out:
return err;
}
#define BPF_MAP_BATCH_LAST_FIELD batch.flags
#define BPF_DO_BATCH(fn) \
do { \
if (!fn) { \
err = -ENOTSUPP; \
goto err_put; \
} \
err = fn(map, attr, uattr); \
} while (0)
static int bpf_map_do_batch(const union bpf_attr *attr,
union bpf_attr __user *uattr,
int cmd)
{
struct bpf_map *map;
int err, ufd;
struct fd f;
if (CHECK_ATTR(BPF_MAP_BATCH))
return -EINVAL;
ufd = attr->batch.map_fd;
f = fdget(ufd);
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)) {
err = -EPERM;
goto err_put;
}
if (cmd != BPF_MAP_LOOKUP_BATCH &&
!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
}
if (cmd == BPF_MAP_LOOKUP_BATCH)
BPF_DO_BATCH(map->ops->map_lookup_batch);
else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH)
BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch);
else if (cmd == BPF_MAP_UPDATE_BATCH)
BPF_DO_BATCH(map->ops->map_update_batch);
else
BPF_DO_BATCH(map->ops->map_delete_batch);
err_put:
fdput(f);
return err;
}
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
@ -3126,6 +3449,19 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
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);
break;
case BPF_MAP_LOOKUP_AND_DELETE_BATCH:
err = bpf_map_do_batch(&attr, uattr,
BPF_MAP_LOOKUP_AND_DELETE_BATCH);
break;
case BPF_MAP_UPDATE_BATCH:
err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH);
break;
case BPF_MAP_DELETE_BATCH:
err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH);
break;
default:
err = -EINVAL;
break;

59
kernel/bpf/trampoline.c
View File

@ -5,6 +5,12 @@
#include <linux/filter.h>
#include <linux/ftrace.h>
/* dummy _ops. The verifier will operate on target program's ops. */
const struct bpf_verifier_ops bpf_extension_verifier_ops = {
};
const struct bpf_prog_ops bpf_extension_prog_ops = {
};
/* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */
#define TRAMPOLINE_HASH_BITS 10
#define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS)
@ -160,11 +166,20 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
if (fexit_cnt)
flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
err = arch_prepare_bpf_trampoline(new_image, &tr->func.model, flags,
/* Though the second half of trampoline page is unused a task could be
* preempted in the middle of the first half of trampoline and two
* updates to trampoline would change the code from underneath the
* preempted task. Hence wait for tasks to voluntarily schedule or go
* to userspace.
*/
synchronize_rcu_tasks();
err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2,
&tr->func.model, flags,
fentry, fentry_cnt,
fexit, fexit_cnt,
tr->func.addr);
if (err)
if (err < 0)
goto out;
if (tr->selector)
@ -185,8 +200,10 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t)
switch (t) {
case BPF_TRACE_FENTRY:
return BPF_TRAMP_FENTRY;
default:
case BPF_TRACE_FEXIT:
return BPF_TRAMP_FEXIT;
default:
return BPF_TRAMP_REPLACE;
}
}
@ -195,12 +212,31 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog)
enum bpf_tramp_prog_type kind;
struct bpf_trampoline *tr;
int err = 0;
int cnt;
tr = prog->aux->trampoline;
kind = bpf_attach_type_to_tramp(prog->expected_attach_type);
mutex_lock(&tr->mutex);
if (tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT]
>= BPF_MAX_TRAMP_PROGS) {
if (tr->extension_prog) {
/* cannot attach fentry/fexit if extension prog is attached.
* cannot overwrite extension prog either.
*/
err = -EBUSY;
goto out;
}
cnt = tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT];
if (kind == BPF_TRAMP_REPLACE) {
/* Cannot attach extension if fentry/fexit are in use. */
if (cnt) {
err = -EBUSY;
goto out;
}
tr->extension_prog = prog;
err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL,
prog->bpf_func);
goto out;
}
if (cnt >= BPF_MAX_TRAMP_PROGS) {
err = -E2BIG;
goto out;
}
@ -231,9 +267,17 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
tr = prog->aux->trampoline;
kind = bpf_attach_type_to_tramp(prog->expected_attach_type);
mutex_lock(&tr->mutex);
if (kind == BPF_TRAMP_REPLACE) {
WARN_ON_ONCE(!tr->extension_prog);
err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP,
tr->extension_prog->bpf_func, NULL);
tr->extension_prog = NULL;
goto out;
}
hlist_del(&prog->aux->tramp_hlist);
tr->progs_cnt[kind]--;
err = bpf_trampoline_update(prog->aux->trampoline);
out:
mutex_unlock(&tr->mutex);
return err;
}
@ -250,6 +294,8 @@ void bpf_trampoline_put(struct bpf_trampoline *tr)
goto out;
if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT])))
goto out;
/* wait for tasks to get out of trampoline before freeing it */
synchronize_rcu_tasks();
bpf_jit_free_exec(tr->image);
hlist_del(&tr->hlist);
kfree(tr);
@ -296,7 +342,8 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
}
int __weak
arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
arch_prepare_bpf_trampoline(void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
struct bpf_prog **fentry_progs, int fentry_cnt,
struct bpf_prog **fexit_progs, int fexit_cnt,
void *orig_call)

504
kernel/bpf/verifier.c
View File

@ -1122,10 +1122,6 @@ static void init_reg_state(struct bpf_verifier_env *env,
regs[BPF_REG_FP].type = PTR_TO_STACK;
mark_reg_known_zero(env, regs, BPF_REG_FP);
regs[BPF_REG_FP].frameno = state->frameno;
/* 1st arg to a function */
regs[BPF_REG_1].type = PTR_TO_CTX;
mark_reg_known_zero(env, regs, BPF_REG_1);
}
#define BPF_MAIN_FUNC (-1)
@ -1916,6 +1912,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
case PTR_TO_TCP_SOCK:
case PTR_TO_TCP_SOCK_OR_NULL:
case PTR_TO_XDP_SOCK:
case PTR_TO_BTF_ID:
return true;
default:
return false;
@ -2738,8 +2735,8 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env,
}
#endif
static int check_ctx_reg(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int regno)
int check_ctx_reg(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int regno)
{
/* Access to ctx or passing it to a helper is only allowed in
* its original, unmodified form.
@ -2858,11 +2855,6 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
u32 btf_id;
int ret;
if (atype != BPF_READ) {
verbose(env, "only read is supported\n");
return -EACCES;
}
if (off < 0) {
verbose(env,
"R%d is ptr_%s invalid negative access: off=%d\n",
@ -2879,17 +2871,32 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
return -EACCES;
}
ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id);
if (env->ops->btf_struct_access) {
ret = env->ops->btf_struct_access(&env->log, t, off, size,
atype, &btf_id);
} else {
if (atype != BPF_READ) {
verbose(env, "only read is supported\n");
return -EACCES;
}
ret = btf_struct_access(&env->log, t, off, size, atype,
&btf_id);
}
if (ret < 0)
return ret;
if (ret == SCALAR_VALUE) {
mark_reg_unknown(env, regs, value_regno);
return 0;
if (atype == BPF_READ) {
if (ret == SCALAR_VALUE) {
mark_reg_unknown(env, regs, value_regno);
return 0;
}
mark_reg_known_zero(env, regs, value_regno);
regs[value_regno].type = PTR_TO_BTF_ID;
regs[value_regno].btf_id = btf_id;
}
mark_reg_known_zero(env, regs, value_regno);
regs[value_regno].type = PTR_TO_BTF_ID;
regs[value_regno].btf_id = btf_id;
return 0;
}
@ -3945,12 +3952,26 @@ static int release_reference(struct bpf_verifier_env *env,
return 0;
}
static void clear_caller_saved_regs(struct bpf_verifier_env *env,
struct bpf_reg_state *regs)
{
int i;
/* after the call registers r0 - r5 were scratched */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
}
}
static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx)
{
struct bpf_verifier_state *state = env->cur_state;
struct bpf_func_info_aux *func_info_aux;
struct bpf_func_state *caller, *callee;
int i, err, subprog, target_insn;
bool is_global = false;
if (state->curframe + 1 >= MAX_CALL_FRAMES) {
verbose(env, "the call stack of %d frames is too deep\n",
@ -3973,6 +3994,32 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return -EFAULT;
}
func_info_aux = env->prog->aux->func_info_aux;
if (func_info_aux)
is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
err = btf_check_func_arg_match(env, subprog, caller->regs);
if (err == -EFAULT)
return err;
if (is_global) {
if (err) {
verbose(env, "Caller passes invalid args into func#%d\n",
subprog);
return err;
} else {
if (env->log.level & BPF_LOG_LEVEL)
verbose(env,
"Func#%d is global and valid. Skipping.\n",
subprog);
clear_caller_saved_regs(env, caller->regs);
/* All global functions return SCALAR_VALUE */
mark_reg_unknown(env, caller->regs, BPF_REG_0);
/* continue with next insn after call */
return 0;
}
}
callee = kzalloc(sizeof(*callee), GFP_KERNEL);
if (!callee)
return -ENOMEM;
@ -3999,18 +4046,11 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
for (i = BPF_REG_1; i <= BPF_REG_5; i++)
callee->regs[i] = caller->regs[i];
/* after the call registers r0 - r5 were scratched */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, caller->regs, caller_saved[i]);
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
}
clear_caller_saved_regs(env, caller->regs);
/* only increment it after check_reg_arg() finished */
state->curframe++;
if (btf_check_func_arg_match(env, subprog))
return -EINVAL;
/* and go analyze first insn of the callee */
*insn_idx = target_insn;
@ -6360,8 +6400,30 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
static int check_return_code(struct bpf_verifier_env *env)
{
struct tnum enforce_attach_type_range = tnum_unknown;
const struct bpf_prog *prog = env->prog;
struct bpf_reg_state *reg;
struct tnum range = tnum_range(0, 1);
int err;
/* The struct_ops func-ptr's return type could be "void" */
if (env->prog->type == BPF_PROG_TYPE_STRUCT_OPS &&
!prog->aux->attach_func_proto->type)
return 0;
/* eBPF calling convetion is such that R0 is used
* to return the value from eBPF program.
* Make sure that it's readable at this time
* of bpf_exit, which means that program wrote
* something into it earlier
*/
err = check_reg_arg(env, BPF_REG_0, SRC_OP);
if (err)
return err;
if (is_pointer_value(env, BPF_REG_0)) {
verbose(env, "R0 leaks addr as return value\n");
return -EACCES;
}
switch (env->prog->type) {
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
@ -6750,12 +6812,13 @@ static int check_btf_func(struct bpf_verifier_env *env,
/* check type_id */
type = btf_type_by_id(btf, krecord[i].type_id);
if (!type || BTF_INFO_KIND(type->info) != BTF_KIND_FUNC) {
if (!type || !btf_type_is_func(type)) {
verbose(env, "invalid type id %d in func info",
krecord[i].type_id);
ret = -EINVAL;
goto err_free;
}
info_aux[i].linkage = BTF_INFO_VLEN(type->info);
prev_offset = krecord[i].insn_off;
urecord += urec_size;
}
@ -7735,35 +7798,13 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev)
static int do_check(struct bpf_verifier_env *env)
{
struct bpf_verifier_state *state;
struct bpf_verifier_state *state = env->cur_state;
struct bpf_insn *insns = env->prog->insnsi;
struct bpf_reg_state *regs;
int insn_cnt = env->prog->len;
bool do_print_state = false;
int prev_insn_idx = -1;
env->prev_linfo = NULL;
state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
if (!state)
return -ENOMEM;
state->curframe = 0;
state->speculative = false;
state->branches = 1;
state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
if (!state->frame[0]) {
kfree(state);
return -ENOMEM;
}
env->cur_state = state;
init_func_state(env, state->frame[0],
BPF_MAIN_FUNC /* callsite */,
0 /* frameno */,
0 /* subprogno, zero == main subprog */);
if (btf_check_func_arg_match(env, 0))
return -EINVAL;
for (;;) {
struct bpf_insn *insn;
u8 class;
@ -7841,7 +7882,7 @@ static int do_check(struct bpf_verifier_env *env)
}
regs = cur_regs(env);
env->insn_aux_data[env->insn_idx].seen = true;
env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
prev_insn_idx = env->insn_idx;
if (class == BPF_ALU || class == BPF_ALU64) {
@ -8027,21 +8068,6 @@ static int do_check(struct bpf_verifier_env *env)
if (err)
return err;
/* eBPF calling convetion is such that R0 is used
* to return the value from eBPF program.
* Make sure that it's readable at this time
* of bpf_exit, which means that program wrote
* something into it earlier
*/
err = check_reg_arg(env, BPF_REG_0, SRC_OP);
if (err)
return err;
if (is_pointer_value(env, BPF_REG_0)) {
verbose(env, "R0 leaks addr as return value\n");
return -EACCES;
}
err = check_return_code(env);
if (err)
return err;
@ -8076,7 +8102,7 @@ process_bpf_exit:
return err;
env->insn_idx++;
env->insn_aux_data[env->insn_idx].seen = true;
env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
} else {
verbose(env, "invalid BPF_LD mode\n");
return -EINVAL;
@ -8089,7 +8115,6 @@ process_bpf_exit:
env->insn_idx++;
}
env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return 0;
}
@ -8149,6 +8174,11 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
return -EINVAL;
}
if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
verbose(env, "bpf_struct_ops map cannot be used in prog\n");
return -EINVAL;
}
return 0;
}
@ -8361,7 +8391,7 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env,
memcpy(new_data + off + cnt - 1, old_data + off,
sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
for (i = off; i < off + cnt - 1; i++) {
new_data[i].seen = true;
new_data[i].seen = env->pass_cnt;
new_data[i].zext_dst = insn_has_def32(env, insn + i);
}
env->insn_aux_data = new_data;
@ -8840,12 +8870,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
convert_ctx_access = bpf_xdp_sock_convert_ctx_access;
break;
case PTR_TO_BTF_ID:
if (type == BPF_WRITE) {
if (type == BPF_READ) {
insn->code = BPF_LDX | BPF_PROBE_MEM |
BPF_SIZE((insn)->code);
env->prog->aux->num_exentries++;
} else if (env->prog->type != BPF_PROG_TYPE_STRUCT_OPS) {
verbose(env, "Writes through BTF pointers are not allowed\n");
return -EINVAL;
}
insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code);
env->prog->aux->num_exentries++;
continue;
default:
continue;
@ -9425,6 +9457,30 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
goto patch_call_imm;
}
if (prog->jit_requested && BITS_PER_LONG == 64 &&
insn->imm == BPF_FUNC_jiffies64) {
struct bpf_insn ld_jiffies_addr[2] = {
BPF_LD_IMM64(BPF_REG_0,
(unsigned long)&jiffies),
};
insn_buf[0] = ld_jiffies_addr[0];
insn_buf[1] = ld_jiffies_addr[1];
insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0,
BPF_REG_0, 0);
cnt = 3;
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf,
cnt);
if (!new_prog)
return -ENOMEM;
delta += cnt - 1;
env->prog = prog = new_prog;
insn = new_prog->insnsi + i + delta;
continue;
}
patch_call_imm:
fn = env->ops->get_func_proto(insn->imm, env->prog);
/* all functions that have prototype and verifier allowed
@ -9471,6 +9527,7 @@ static void free_states(struct bpf_verifier_env *env)
kfree(sl);
sl = sln;
}
env->free_list = NULL;
if (!env->explored_states)
return;
@ -9484,11 +9541,164 @@ static void free_states(struct bpf_verifier_env *env)
kfree(sl);
sl = sln;
}
env->explored_states[i] = NULL;
}
}
/* The verifier is using insn_aux_data[] to store temporary data during
* verification and to store information for passes that run after the
* verification like dead code sanitization. do_check_common() for subprogram N
* may analyze many other subprograms. sanitize_insn_aux_data() clears all
* temporary data after do_check_common() finds that subprogram N cannot be
* verified independently. pass_cnt counts the number of times
* do_check_common() was run and insn->aux->seen tells the pass number
* insn_aux_data was touched. These variables are compared to clear temporary
* data from failed pass. For testing and experiments do_check_common() can be
* run multiple times even when prior attempt to verify is unsuccessful.
*/
static void sanitize_insn_aux_data(struct bpf_verifier_env *env)
{
struct bpf_insn *insn = env->prog->insnsi;
struct bpf_insn_aux_data *aux;
int i, class;
for (i = 0; i < env->prog->len; i++) {
class = BPF_CLASS(insn[i].code);
if (class != BPF_LDX && class != BPF_STX)
continue;
aux = &env->insn_aux_data[i];
if (aux->seen != env->pass_cnt)
continue;
memset(aux, 0, offsetof(typeof(*aux), orig_idx));
}
}
static int do_check_common(struct bpf_verifier_env *env, int subprog)
{
struct bpf_verifier_state *state;
struct bpf_reg_state *regs;
int ret, i;
env->prev_linfo = NULL;
env->pass_cnt++;
state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
if (!state)
return -ENOMEM;
state->curframe = 0;
state->speculative = false;
state->branches = 1;
state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
if (!state->frame[0]) {
kfree(state);
return -ENOMEM;
}
env->cur_state = state;
init_func_state(env, state->frame[0],
BPF_MAIN_FUNC /* callsite */,
0 /* frameno */,
subprog);
regs = state->frame[state->curframe]->regs;
if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
ret = btf_prepare_func_args(env, subprog, regs);
if (ret)
goto out;
for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
if (regs[i].type == PTR_TO_CTX)
mark_reg_known_zero(env, regs, i);
else if (regs[i].type == SCALAR_VALUE)
mark_reg_unknown(env, regs, i);
}
} else {
/* 1st arg to a function */
regs[BPF_REG_1].type = PTR_TO_CTX;
mark_reg_known_zero(env, regs, BPF_REG_1);
ret = btf_check_func_arg_match(env, subprog, regs);
if (ret == -EFAULT)
/* unlikely verifier bug. abort.
* ret == 0 and ret < 0 are sadly acceptable for
* main() function due to backward compatibility.
* Like socket filter program may be written as:
* int bpf_prog(struct pt_regs *ctx)
* and never dereference that ctx in the program.
* 'struct pt_regs' is a type mismatch for socket
* filter that should be using 'struct __sk_buff'.
*/
goto out;
}
kvfree(env->explored_states);
ret = do_check(env);
out:
/* check for NULL is necessary, since cur_state can be freed inside
* do_check() under memory pressure.
*/
if (env->cur_state) {
free_verifier_state(env->cur_state, true);
env->cur_state = NULL;
}
while (!pop_stack(env, NULL, NULL));
free_states(env);
if (ret)
/* clean aux data in case subprog was rejected */
sanitize_insn_aux_data(env);
return ret;
}
/* Verify all global functions in a BPF program one by one based on their BTF.
* All global functions must pass verification. Otherwise the whole program is rejected.
* Consider:
* int bar(int);
* int foo(int f)
* {
* return bar(f);
* }
* int bar(int b)
* {
* ...
* }
* foo() will be verified first for R1=any_scalar_value. During verification it
* will be assumed that bar() already verified successfully and call to bar()
* from foo() will be checked for type match only. Later bar() will be verified
* independently to check that it's safe for R1=any_scalar_value.
*/
static int do_check_subprogs(struct bpf_verifier_env *env)
{
struct bpf_prog_aux *aux = env->prog->aux;
int i, ret;
if (!aux->func_info)
return 0;
for (i = 1; i < env->subprog_cnt; i++) {
if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL)
continue;
env->insn_idx = env->subprog_info[i].start;
WARN_ON_ONCE(env->insn_idx == 0);
ret = do_check_common(env, i);
if (ret) {
return ret;
} else if (env->log.level & BPF_LOG_LEVEL) {
verbose(env,
"Func#%d is safe for any args that match its prototype\n",
i);
}
}
return 0;
}
static int do_check_main(struct bpf_verifier_env *env)
{
int ret;
env->insn_idx = 0;
ret = do_check_common(env, 0);
if (!ret)
env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return ret;
}
static void print_verification_stats(struct bpf_verifier_env *env)
{
int i;
@ -9513,9 +9723,62 @@ static void print_verification_stats(struct bpf_verifier_env *env)
env->peak_states, env->longest_mark_read_walk);
}
static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
{
const struct btf_type *t, *func_proto;
const struct bpf_struct_ops *st_ops;
const struct btf_member *member;
struct bpf_prog *prog = env->prog;
u32 btf_id, member_idx;
const char *mname;
btf_id = prog->aux->attach_btf_id;
st_ops = bpf_struct_ops_find(btf_id);
if (!st_ops) {
verbose(env, "attach_btf_id %u is not a supported struct\n",
btf_id);
return -ENOTSUPP;
}
t = st_ops->type;
member_idx = prog->expected_attach_type;
if (member_idx >= btf_type_vlen(t)) {
verbose(env, "attach to invalid member idx %u of struct %s\n",
member_idx, st_ops->name);
return -EINVAL;
}
member = &btf_type_member(t)[member_idx];
mname = btf_name_by_offset(btf_vmlinux, member->name_off);
func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type,
NULL);
if (!func_proto) {
verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n",
mname, member_idx, st_ops->name);
return -EINVAL;
}
if (st_ops->check_member) {
int err = st_ops->check_member(t, member);
if (err) {
verbose(env, "attach to unsupported member %s of struct %s\n",
mname, st_ops->name);
return err;
}
}
prog->aux->attach_func_proto = func_proto;
prog->aux->attach_func_name = mname;
env->ops = st_ops->verifier_ops;
return 0;
}
static int check_attach_btf_id(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog;
bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
struct bpf_prog *tgt_prog = prog->aux->linked_prog;
u32 btf_id = prog->aux->attach_btf_id;
const char prefix[] = "btf_trace_";
@ -9528,7 +9791,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
long addr;
u64 key;
if (prog->type != BPF_PROG_TYPE_TRACING)
if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
return check_struct_ops_btf_id(env);
if (prog->type != BPF_PROG_TYPE_TRACING && !prog_extension)
return 0;
if (!btf_id) {
@ -9564,8 +9830,59 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
return -EINVAL;
}
conservative = aux->func_info_aux[subprog].unreliable;
if (prog_extension) {
if (conservative) {
verbose(env,
"Cannot replace static functions\n");
return -EINVAL;
}
if (!prog->jit_requested) {
verbose(env,
"Extension programs should be JITed\n");
return -EINVAL;
}
env->ops = bpf_verifier_ops[tgt_prog->type];
}
if (!tgt_prog->jited) {
verbose(env, "Can attach to only JITed progs\n");
return -EINVAL;
}
if (tgt_prog->type == prog->type) {
/* Cannot fentry/fexit another fentry/fexit program.
* Cannot attach program extension to another extension.
* It's ok to attach fentry/fexit to extension program.
*/
verbose(env, "Cannot recursively attach\n");
return -EINVAL;
}
if (tgt_prog->type == BPF_PROG_TYPE_TRACING &&
prog_extension &&
(tgt_prog->expected_attach_type == BPF_TRACE_FENTRY ||
tgt_prog->expected_attach_type == BPF_TRACE_FEXIT)) {
/* Program extensions can extend all program types
* except fentry/fexit. The reason is the following.
* The fentry/fexit programs are used for performance
* analysis, stats and can be attached to any program
* type except themselves. When extension program is
* replacing XDP function it is necessary to allow
* performance analysis of all functions. Both original
* XDP program and its program extension. Hence
* attaching fentry/fexit to BPF_PROG_TYPE_EXT is
* allowed. If extending of fentry/fexit was allowed it
* would be possible to create long call chain
* fentry->extension->fentry->extension beyond
* reasonable stack size. Hence extending fentry is not
* allowed.
*/
verbose(env, "Cannot extend fentry/fexit\n");
return -EINVAL;
}
key = ((u64)aux->id) << 32 | btf_id;
} else {
if (prog_extension) {
verbose(env, "Cannot replace kernel functions\n");
return -EINVAL;
}
key = btf_id;
}
@ -9603,6 +9920,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
prog->aux->attach_func_proto = t;
prog->aux->attach_btf_trace = true;
return 0;
default:
if (!prog_extension)
return -EINVAL;
/* fallthrough */
case BPF_TRACE_FENTRY:
case BPF_TRACE_FEXIT:
if (!btf_type_is_func(t)) {
@ -9610,6 +9931,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
btf_id);
return -EINVAL;
}
if (prog_extension &&
btf_check_type_match(env, prog, btf, t))
return -EINVAL;
t = btf_type_by_id(btf, t->type);
if (!btf_type_is_func_proto(t))
return -EINVAL;
@ -9633,18 +9957,6 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
if (ret < 0)
goto out;
if (tgt_prog) {
if (!tgt_prog->jited) {
/* for now */
verbose(env, "Can trace only JITed BPF progs\n");
ret = -EINVAL;
goto out;
}
if (tgt_prog->type == BPF_PROG_TYPE_TRACING) {
/* prevent cycles */
verbose(env, "Cannot recursively attach\n");
ret = -EINVAL;
goto out;
}
if (subprog == 0)
addr = (long) tgt_prog->bpf_func;
else
@ -9666,8 +9978,6 @@ out:
if (ret)
bpf_trampoline_put(tr);
return ret;
default:
return -EINVAL;
}
}
@ -9737,10 +10047,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
goto skip_full_check;
}
ret = check_attach_btf_id(env);
if (ret)
goto skip_full_check;
env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
env->strict_alignment = true;
@ -9777,22 +10083,22 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
if (ret < 0)
goto skip_full_check;
ret = check_attach_btf_id(env);
if (ret)
goto skip_full_check;
ret = check_cfg(env);
if (ret < 0)
goto skip_full_check;
ret = do_check(env);
if (env->cur_state) {
free_verifier_state(env->cur_state, true);
env->cur_state = NULL;
}
ret = do_check_subprogs(env);
ret = ret ?: do_check_main(env);
if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux))
ret = bpf_prog_offload_finalize(env);
skip_full_check:
while (!pop_stack(env, NULL, NULL));
free_states(env);
kvfree(env->explored_states);
if (ret == 0)
ret = check_max_stack_depth(env);

27
kernel/trace/bpf_trace.c
View File

@ -703,6 +703,7 @@ struct send_signal_irq_work {
struct irq_work irq_work;
struct task_struct *task;
u32 sig;
enum pid_type type;
};
static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work);
@ -712,10 +713,10 @@ static void do_bpf_send_signal(struct irq_work *entry)
struct send_signal_irq_work *work;
work = container_of(entry, struct send_signal_irq_work, irq_work);
group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, PIDTYPE_TGID);
group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type);
}
BPF_CALL_1(bpf_send_signal, u32, sig)
static int bpf_send_signal_common(u32 sig, enum pid_type type)
{
struct send_signal_irq_work *work = NULL;
@ -748,11 +749,17 @@ BPF_CALL_1(bpf_send_signal, u32, sig)
*/
work->task = current;
work->sig = sig;
work->type = type;
irq_work_queue(&work->irq_work);
return 0;
}
return group_send_sig_info(sig, SEND_SIG_PRIV, current, PIDTYPE_TGID);
return group_send_sig_info(sig, SEND_SIG_PRIV, current, type);
}
BPF_CALL_1(bpf_send_signal, u32, sig)
{
return bpf_send_signal_common(sig, PIDTYPE_TGID);
}
static const struct bpf_func_proto bpf_send_signal_proto = {
@ -762,6 +769,18 @@ static const struct bpf_func_proto bpf_send_signal_proto = {
.arg1_type = ARG_ANYTHING,
};
BPF_CALL_1(bpf_send_signal_thread, u32, sig)
{
return bpf_send_signal_common(sig, PIDTYPE_PID);
}
static const struct bpf_func_proto bpf_send_signal_thread_proto = {
.func = bpf_send_signal_thread,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_ANYTHING,
};
static const struct bpf_func_proto *
tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
@ -822,6 +841,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
#endif
case BPF_FUNC_send_signal:
return &bpf_send_signal_proto;
case BPF_FUNC_send_signal_thread:
return &bpf_send_signal_thread_proto;
default:
return NULL;
}

2
net/core/dev.c
View File

@ -9835,6 +9835,8 @@ void free_netdev(struct net_device *dev)
free_percpu(dev->pcpu_refcnt);
dev->pcpu_refcnt = NULL;
free_percpu(dev->xdp_bulkq);
dev->xdp_bulkq = NULL;
netdev_unregister_lockdep_key(dev);

96
net/core/filter.c
View File

@ -3459,58 +3459,6 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
.arg2_type = ARG_ANYTHING,
};
static int __bpf_tx_xdp(struct net_device *dev,
struct bpf_map *map,
struct xdp_buff *xdp,
u32 index)
{
struct xdp_frame *xdpf;
int err, sent;
if (!dev->netdev_ops->ndo_xdp_xmit) {
return -EOPNOTSUPP;
}
err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
if (unlikely(err))
return err;
xdpf = convert_to_xdp_frame(xdp);
if (unlikely(!xdpf))
return -EOVERFLOW;
sent = dev->netdev_ops->ndo_xdp_xmit(dev, 1, &xdpf, XDP_XMIT_FLUSH);
if (sent <= 0)
return sent;
return 0;
}
static noinline int
xdp_do_redirect_slow(struct net_device *dev, struct xdp_buff *xdp,
struct bpf_prog *xdp_prog, struct bpf_redirect_info *ri)
{
struct net_device *fwd;
u32 index = ri->tgt_index;
int err;
fwd = dev_get_by_index_rcu(dev_net(dev), index);
ri->tgt_index = 0;
if (unlikely(!fwd)) {
err = -EINVAL;
goto err;
}
err = __bpf_tx_xdp(fwd, NULL, xdp, 0);
if (unlikely(err))
goto err;
_trace_xdp_redirect(dev, xdp_prog, index);
return 0;
err:
_trace_xdp_redirect_err(dev, xdp_prog, index, err);
return err;
}
static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
struct bpf_map *map, struct xdp_buff *xdp)
{
@ -3523,18 +3471,18 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
case BPF_MAP_TYPE_XSKMAP:
return __xsk_map_redirect(fwd, xdp);
default:
break;
return -EBADRQC;
}
return 0;
}
void xdp_do_flush_map(void)
void xdp_do_flush(void)
{
__dev_map_flush();
__dev_flush();
__cpu_map_flush();
__xsk_map_flush();
}
EXPORT_SYMBOL_GPL(xdp_do_flush_map);
EXPORT_SYMBOL_GPL(xdp_do_flush);
static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
{
@ -3569,10 +3517,11 @@ void bpf_clear_redirect_map(struct bpf_map *map)
}
}
static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
struct bpf_prog *xdp_prog, struct bpf_map *map,
struct bpf_redirect_info *ri)
int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
struct bpf_map *map = READ_ONCE(ri->map);
u32 index = ri->tgt_index;
void *fwd = ri->tgt_value;
int err;
@ -3581,7 +3530,18 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
ri->tgt_value = NULL;
WRITE_ONCE(ri->map, NULL);
err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
if (unlikely(!map)) {
fwd = dev_get_by_index_rcu(dev_net(dev), index);
if (unlikely(!fwd)) {
err = -EINVAL;
goto err;
}
err = dev_xdp_enqueue(fwd, xdp, dev);
} else {
err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
}
if (unlikely(err))
goto err;
@ -3591,18 +3551,6 @@ err:
_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
return err;
}
int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
struct bpf_map *map = READ_ONCE(ri->map);
if (likely(map))
return xdp_do_redirect_map(dev, xdp, xdp_prog, map, ri);
return xdp_do_redirect_slow(dev, xdp, xdp_prog, ri);
}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
static int xdp_do_generic_redirect_map(struct net_device *dev,
@ -5935,7 +5883,7 @@ bool bpf_helper_changes_pkt_data(void *func)
return false;
}
static const struct bpf_func_proto *
const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
switch (func_id) {
@ -5975,6 +5923,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
return &bpf_spin_unlock_proto;
case BPF_FUNC_trace_printk:
return bpf_get_trace_printk_proto();
case BPF_FUNC_jiffies64:
return &bpf_jiffies64_proto;
default:
return NULL;
}

2
net/core/sock.c
View File

@ -2786,7 +2786,7 @@ static void sock_def_error_report(struct sock *sk)
rcu_read_unlock();
}
static void sock_def_readable(struct sock *sk)
void sock_def_readable(struct sock *sk)
{
struct socket_wq *wq;

4
net/ipv4/Makefile
View File

@ -65,3 +65,7 @@ obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
xfrm4_output.o xfrm4_protocol.o
ifeq ($(CONFIG_BPF_JIT),y)
obj-$(CONFIG_BPF_SYSCALL) += bpf_tcp_ca.o
endif

252
net/ipv4/bpf_tcp_ca.c Normal file
View File

@ -0,0 +1,252 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <linux/types.h>
#include <linux/bpf_verifier.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/filter.h>
#include <net/tcp.h>
static u32 optional_ops[] = {
offsetof(struct tcp_congestion_ops, init),
offsetof(struct tcp_congestion_ops, release),
offsetof(struct tcp_congestion_ops, set_state),
offsetof(struct tcp_congestion_ops, cwnd_event),
offsetof(struct tcp_congestion_ops, in_ack_event),
offsetof(struct tcp_congestion_ops, pkts_acked),
offsetof(struct tcp_congestion_ops, min_tso_segs),
offsetof(struct tcp_congestion_ops, sndbuf_expand),
offsetof(struct tcp_congestion_ops, cong_control),
};
static u32 unsupported_ops[] = {
offsetof(struct tcp_congestion_ops, get_info),
};
static const struct btf_type *tcp_sock_type;
static u32 tcp_sock_id, sock_id;
static int bpf_tcp_ca_init(struct btf *btf)
{
s32 type_id;
type_id = btf_find_by_name_kind(btf, "sock", BTF_KIND_STRUCT);
if (type_id < 0)
return -EINVAL;
sock_id = type_id;
type_id = btf_find_by_name_kind(btf, "tcp_sock", BTF_KIND_STRUCT);
if (type_id < 0)
return -EINVAL;
tcp_sock_id = type_id;
tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);
return 0;
}
static bool is_optional(u32 member_offset)
{
unsigned int i;
for (i = 0; i < ARRAY_SIZE(optional_ops); i++) {
if (member_offset == optional_ops[i])
return true;
}
return false;
}
static bool is_unsupported(u32 member_offset)
{
unsigned int i;
for (i = 0; i < ARRAY_SIZE(unsupported_ops); i++) {
if (member_offset == unsupported_ops[i])
return true;
}
return false;
}
extern struct btf *btf_vmlinux;
static bool bpf_tcp_ca_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 >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
return false;
if (type != BPF_READ)
return false;
if (off % size != 0)
return false;
if (!btf_ctx_access(off, size, type, prog, info))
return false;
if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id)
/* promote it to tcp_sock */
info->btf_id = tcp_sock_id;
return true;
}
static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
const struct btf_type *t, int off,
int size, enum bpf_access_type atype,
u32 *next_btf_id)
{
size_t end;
if (atype == BPF_READ)
return btf_struct_access(log, t, off, size, atype, next_btf_id);
if (t != tcp_sock_type) {
bpf_log(log, "only read is supported\n");
return -EACCES;
}
switch (off) {
case bpf_ctx_range(struct inet_connection_sock, icsk_ca_priv):
end = offsetofend(struct inet_connection_sock, icsk_ca_priv);
break;
case offsetof(struct inet_connection_sock, icsk_ack.pending):
end = offsetofend(struct inet_connection_sock,
icsk_ack.pending);
break;
case offsetof(struct tcp_sock, snd_cwnd):
end = offsetofend(struct tcp_sock, snd_cwnd);
break;
case offsetof(struct tcp_sock, snd_cwnd_cnt):
end = offsetofend(struct tcp_sock, snd_cwnd_cnt);
break;
case offsetof(struct tcp_sock, snd_ssthresh):
end = offsetofend(struct tcp_sock, snd_ssthresh);
break;
case offsetof(struct tcp_sock, ecn_flags):
end = offsetofend(struct tcp_sock, ecn_flags);
break;
default:
bpf_log(log, "no write support to tcp_sock at off %d\n", off);
return -EACCES;
}
if (off + size > end) {
bpf_log(log,
"write access at off %d with size %d beyond the member of tcp_sock ended at %zu\n",
off, size, end);
return -EACCES;
}
return NOT_INIT;
}
BPF_CALL_2(bpf_tcp_send_ack, struct tcp_sock *, tp, u32, rcv_nxt)
{
/* bpf_tcp_ca prog cannot have NULL tp */
__tcp_send_ack((struct sock *)tp, rcv_nxt);
return 0;
}
static const struct bpf_func_proto bpf_tcp_send_ack_proto = {
.func = bpf_tcp_send_ack,
.gpl_only = false,
/* In case we want to report error later */
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg2_type = ARG_ANYTHING,
.btf_id = &tcp_sock_id,
};
static const struct bpf_func_proto *
bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_tcp_send_ack:
return &bpf_tcp_send_ack_proto;
default:
return bpf_base_func_proto(func_id);
}
}
static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = {
.get_func_proto = bpf_tcp_ca_get_func_proto,
.is_valid_access = bpf_tcp_ca_is_valid_access,
.btf_struct_access = bpf_tcp_ca_btf_struct_access,
};
static int bpf_tcp_ca_init_member(const struct btf_type *t,
const struct btf_member *member,
void *kdata, const void *udata)
{
const struct tcp_congestion_ops *utcp_ca;
struct tcp_congestion_ops *tcp_ca;
size_t tcp_ca_name_len;
int prog_fd;
u32 moff;
utcp_ca = (const struct tcp_congestion_ops *)udata;
tcp_ca = (struct tcp_congestion_ops *)kdata;
moff = btf_member_bit_offset(t, member) / 8;
switch (moff) {
case offsetof(struct tcp_congestion_ops, flags):
if (utcp_ca->flags & ~TCP_CONG_MASK)
return -EINVAL;
tcp_ca->flags = utcp_ca->flags;
return 1;
case offsetof(struct tcp_congestion_ops, name):
tcp_ca_name_len = strnlen(utcp_ca->name, sizeof(utcp_ca->name));
if (!tcp_ca_name_len ||
tcp_ca_name_len == sizeof(utcp_ca->name))
return -EINVAL;
if (tcp_ca_find(utcp_ca->name))
return -EEXIST;
memcpy(tcp_ca->name, utcp_ca->name, sizeof(tcp_ca->name));
return 1;
}
if (!btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL))
return 0;
/* Ensure bpf_prog is provided for compulsory func ptr */
prog_fd = (int)(*(unsigned long *)(udata + moff));
if (!prog_fd && !is_optional(moff) && !is_unsupported(moff))
return -EINVAL;
return 0;
}
static int bpf_tcp_ca_check_member(const struct btf_type *t,
const struct btf_member *member)
{
if (is_unsupported(btf_member_bit_offset(t, member) / 8))
return -ENOTSUPP;
return 0;
}
static int bpf_tcp_ca_reg(void *kdata)
{
return tcp_register_congestion_control(kdata);
}
static void bpf_tcp_ca_unreg(void *kdata)
{
tcp_unregister_congestion_control(kdata);
}
/* Avoid sparse warning. It is only used in bpf_struct_ops.c. */
extern struct bpf_struct_ops bpf_tcp_congestion_ops;
struct bpf_struct_ops bpf_tcp_congestion_ops = {
.verifier_ops = &bpf_tcp_ca_verifier_ops,
.reg = bpf_tcp_ca_reg,
.unreg = bpf_tcp_ca_unreg,
.check_member = bpf_tcp_ca_check_member,
.init_member = bpf_tcp_ca_init_member,
.init = bpf_tcp_ca_init,
.name = "tcp_congestion_ops",
};

16
net/ipv4/tcp_cong.c
View File

@ -21,7 +21,7 @@ static DEFINE_SPINLOCK(tcp_cong_list_lock);
static LIST_HEAD(tcp_cong_list);
/* Simple linear search, don't expect many entries! */
static struct tcp_congestion_ops *tcp_ca_find(const char *name)
struct tcp_congestion_ops *tcp_ca_find(const char *name)
{
struct tcp_congestion_ops *e;
@ -162,7 +162,7 @@ void tcp_assign_congestion_control(struct sock *sk)
rcu_read_lock();
ca = rcu_dereference(net->ipv4.tcp_congestion_control);
if (unlikely(!try_module_get(ca->owner)))
if (unlikely(!bpf_try_module_get(ca, ca->owner)))
ca = &tcp_reno;
icsk->icsk_ca_ops = ca;
rcu_read_unlock();
@ -208,7 +208,7 @@ void tcp_cleanup_congestion_control(struct sock *sk)
if (icsk->icsk_ca_ops->release)
icsk->icsk_ca_ops->release(sk);
module_put(icsk->icsk_ca_ops->owner);
bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner);
}
/* Used by sysctl to change default congestion control */
@ -222,12 +222,12 @@ int tcp_set_default_congestion_control(struct net *net, const char *name)
ca = tcp_ca_find_autoload(net, name);
if (!ca) {
ret = -ENOENT;
} else if (!try_module_get(ca->owner)) {
} else if (!bpf_try_module_get(ca, ca->owner)) {
ret = -EBUSY;
} else {
prev = xchg(&net->ipv4.tcp_congestion_control, ca);
if (prev)
module_put(prev->owner);
bpf_module_put(prev, prev->owner);
ca->flags |= TCP_CONG_NON_RESTRICTED;
ret = 0;
@ -366,19 +366,19 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
} else if (!load) {
const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops;
if (try_module_get(ca->owner)) {
if (bpf_try_module_get(ca, ca->owner)) {
if (reinit) {
tcp_reinit_congestion_control(sk, ca);
} else {
icsk->icsk_ca_ops = ca;
module_put(old_ca->owner);
bpf_module_put(old_ca, old_ca->owner);
}
} else {
err = -EBUSY;
}
} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) {
err = -EPERM;
} else if (!try_module_get(ca->owner)) {
} else if (!bpf_try_module_get(ca, ca->owner)) {
err = -EBUSY;
} else {
tcp_reinit_congestion_control(sk, ca);

6
net/ipv4/tcp_ipv4.c
View File

@ -2678,7 +2678,8 @@ static void __net_exit tcp_sk_exit(struct net *net)
int cpu;
if (net->ipv4.tcp_congestion_control)
module_put(net->ipv4.tcp_congestion_control->owner);
bpf_module_put(net->ipv4.tcp_congestion_control,
net->ipv4.tcp_congestion_control->owner);
for_each_possible_cpu(cpu)
inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
@ -2785,7 +2786,8 @@ static int __net_init tcp_sk_init(struct net *net)
/* Reno is always built in */
if (!net_eq(net, &init_net) &&
try_module_get(init_net.ipv4.tcp_congestion_control->owner))
bpf_try_module_get(init_net.ipv4.tcp_congestion_control,
init_net.ipv4.tcp_congestion_control->owner))
net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control;
else
net->ipv4.tcp_congestion_control = &tcp_reno;

4
net/ipv4/tcp_minisocks.c
View File

@ -414,7 +414,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
rcu_read_lock();
ca = tcp_ca_find_key(ca_key);
if (likely(ca && try_module_get(ca->owner))) {
if (likely(ca && bpf_try_module_get(ca, ca->owner))) {
icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
icsk->icsk_ca_ops = ca;
ca_got_dst = true;
@ -425,7 +425,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
/* If no valid choice made yet, assign current system default ca. */
if (!ca_got_dst &&
(!icsk->icsk_ca_setsockopt ||
!try_module_get(icsk->icsk_ca_ops->owner)))
!bpf_try_module_get(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner)))
tcp_assign_congestion_control(sk);
tcp_set_ca_state(sk, TCP_CA_Open);

4
net/ipv4/tcp_output.c
View File

@ -3372,8 +3372,8 @@ static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst)
rcu_read_lock();
ca = tcp_ca_find_key(ca_key);
if (likely(ca && try_module_get(ca->owner))) {
module_put(icsk->icsk_ca_ops->owner);
if (likely(ca && bpf_try_module_get(ca, ca->owner))) {
bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner);
icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
icsk->icsk_ca_ops = ca;
}

7
net/xdp/xdp_umem.c
View File

@ -249,7 +249,7 @@ static void xdp_umem_release(struct xdp_umem *umem)
xdp_umem_unmap_pages(umem);
xdp_umem_unpin_pages(umem);
kfree(umem->pages);
kvfree(umem->pages);
umem->pages = NULL;
xdp_umem_unaccount_pages(umem);
@ -409,7 +409,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
if (err)
goto out_account;
umem->pages = kcalloc(umem->npgs, sizeof(*umem->pages), GFP_KERNEL);
umem->pages = kvcalloc(umem->npgs, sizeof(*umem->pages),
GFP_KERNEL_ACCOUNT);
if (!umem->pages) {
err = -ENOMEM;
goto out_pin;
@ -419,7 +420,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
if (!err)
return 0;
kfree(umem->pages);
kvfree(umem->pages);
out_pin:
xdp_umem_unpin_pages(umem);

2
net/xdp/xsk.c
View File

@ -217,7 +217,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
static void xsk_flush(struct xdp_sock *xs)
{
xskq_prod_submit(xs->rx);
xs->sk.sk_data_ready(&xs->sk);
sock_def_readable(&xs->sk);
}
int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)

5
samples/bpf/Makefile
View File

@ -184,7 +184,6 @@ TPROGS_CFLAGS += -Wmissing-prototypes
TPROGS_CFLAGS += -Wstrict-prototypes
TPROGS_CFLAGS += -I$(objtree)/usr/include
TPROGS_CFLAGS += -I$(srctree)/tools/lib/bpf/
TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
TPROGS_CFLAGS += -I$(srctree)/tools/lib/
TPROGS_CFLAGS += -I$(srctree)/tools/include
@ -254,7 +253,7 @@ all:
clean:
$(MAKE) -C ../../ M=$(CURDIR) clean
@rm -f *~
@find $(CURDIR) -type f -name '*~' -delete
$(LIBBPF): FORCE
# Fix up variables inherited from Kbuild that tools/ build system won't like
@ -305,7 +304,7 @@ $(obj)/%.o: $(src)/%.c
@echo " CLANG-bpf " $@
$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \
-I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \
-I$(srctree)/tools/lib/bpf/ \
-I$(srctree)/tools/lib/ \
-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
-D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \

2
samples/bpf/cpustat_kern.c
View File

@ -3,7 +3,7 @@
#include <linux/version.h>
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
/*
* The CPU number, cstate number and pstate number are based

2
samples/bpf/fds_example.c
View File

@ -14,7 +14,7 @@
#include <bpf/bpf.h>
#include "libbpf.h"
#include <bpf/libbpf.h>
#include "bpf_insn.h"
#include "sock_example.h"

4
samples/bpf/hbm.c
View File

@ -50,8 +50,8 @@
#include "cgroup_helpers.h"
#include "hbm.h"
#include "bpf_util.h"
#include "bpf.h"
#include "libbpf.h"
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
bool outFlag = true;
int minRate = 1000; /* cgroup rate limit in Mbps */

4
samples/bpf/hbm_kern.h
View File

@ -22,8 +22,8 @@
#include <uapi/linux/pkt_cls.h>
#include <net/ipv6.h>
#include <net/inet_ecn.h>
#include "bpf_endian.h"
#include "bpf_helpers.h"
#include <bpf/bpf_endian.h>
#include <bpf/bpf_helpers.h>
#include "hbm.h"
#define DROP_PKT 0

2
samples/bpf/ibumad_kern.c
View File

@ -13,7 +13,7 @@
#define KBUILD_MODNAME "ibumad_count_pkts_by_class"
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
struct bpf_map_def SEC("maps") read_count = {

2
samples/bpf/ibumad_user.c
View File

@ -25,7 +25,7 @@
#include "bpf_load.h"
#include "bpf_util.h"
#include "libbpf.h"
#include <bpf/libbpf.h>
static void dump_counts(int fd)
{

2
samples/bpf/lathist_kern.c
View File

@ -8,7 +8,7 @@
#include <linux/version.h>
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#define MAX_ENTRIES 20
#define MAX_CPU 4

2
samples/bpf/lwt_len_hist_kern.c
View File

@ -14,7 +14,7 @@
#include <uapi/linux/if_ether.h>
#include <uapi/linux/ip.h>
#include <uapi/linux/in.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
# define printk(fmt, ...) \
({ \

4
samples/bpf/map_perf_test_kern.c
View File

@ -8,9 +8,9 @@
#include <linux/netdevice.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
#include "bpf_tracing.h"
#include <bpf/bpf_tracing.h>
#define MAX_ENTRIES 1000
#define MAX_NR_CPUS 1024

4
samples/bpf/offwaketime_kern.c
View File

@ -5,8 +5,8 @@
* License as published by the Free Software Foundation.
*/
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include "bpf_tracing.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include <uapi/linux/ptrace.h>
#include <uapi/linux/perf_event.h>
#include <linux/version.h>

2
samples/bpf/offwaketime_user.c
View File

@ -12,7 +12,7 @@
#include <assert.h>
#include <stdbool.h>
#include <sys/resource.h>
#include "libbpf.h"
#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "trace_helpers.h"

2
samples/bpf/parse_ldabs.c
View File

@ -11,7 +11,7 @@
#include <linux/tcp.h>
#include <linux/udp.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
#define DEFAULT_PKTGEN_UDP_PORT 9

2
samples/bpf/parse_simple.c
View File

@ -12,7 +12,7 @@
#include <linux/udp.h>
#include <uapi/linux/bpf.h>
#include <net/ip.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#define DEFAULT_PKTGEN_UDP_PORT 9

2
samples/bpf/parse_varlen.c
View File

@ -14,7 +14,7 @@
#include <linux/udp.h>
#include <uapi/linux/bpf.h>
#include <net/ip.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#define DEFAULT_PKTGEN_UDP_PORT 9
#define DEBUG 0

4
samples/bpf/sampleip_kern.c
View File

@ -8,8 +8,8 @@
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/bpf_perf_event.h>
#include "bpf_helpers.h"
#include "bpf_tracing.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#define MAX_IPS 8192

2
samples/bpf/sampleip_user.c
View File

@ -15,7 +15,7 @@
#include <linux/ptrace.h>
#include <linux/bpf.h>
#include <sys/ioctl.h>
#include "libbpf.h"
#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "perf-sys.h"
#include "trace_helpers.h"

2
samples/bpf/sock_flags_kern.c
View File

@ -3,7 +3,7 @@
#include <linux/net.h>
#include <uapi/linux/in.h>
#include <uapi/linux/in6.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
SEC("cgroup/sock1")
int bpf_prog1(struct bpf_sock *sk)

2
samples/bpf/sockex1_kern.c
View File

@ -2,7 +2,7 @@
#include <uapi/linux/if_ether.h>
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
struct {

2
samples/bpf/sockex1_user.c
View File

@ -3,7 +3,7 @@
#include <assert.h>
#include <linux/bpf.h>
#include <bpf/bpf.h>
#include "libbpf.h"
#include <bpf/libbpf.h>
#include "sock_example.h"
#include <unistd.h>
#include <arpa/inet.h>

2
samples/bpf/sockex2_kern.c
View File

@ -1,5 +1,5 @@
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
#include <uapi/linux/in.h>
#include <uapi/linux/if.h>

2
samples/bpf/sockex2_user.c
View File

@ -3,7 +3,7 @@
#include <assert.h>
#include <linux/bpf.h>
#include <bpf/bpf.h>
#include "libbpf.h"
#include <bpf/libbpf.h>
#include "sock_example.h"
#include <unistd.h>
#include <arpa/inet.h>

2
samples/bpf/sockex3_kern.c
View File

@ -5,7 +5,7 @@
* License as published by the Free Software Foundation.
*/
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
#include <uapi/linux/in.h>
#include <uapi/linux/if.h>

4
samples/bpf/spintest_kern.c
View File

@ -9,8 +9,8 @@
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/perf_event.h>
#include "bpf_helpers.h"
#include "bpf_tracing.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,

2
samples/bpf/spintest_user.c
View File

@ -5,7 +5,7 @@
#include <string.h>
#include <assert.h>
#include <sys/resource.h>
#include "libbpf.h"
#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "trace_helpers.h"

2
samples/bpf/syscall_tp_kern.c
View File

@ -2,7 +2,7 @@
/* Copyright (c) 2017 Facebook
*/
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
struct syscalls_enter_open_args {
unsigned long long unused;

2
samples/bpf/task_fd_query_kern.c
View File

@ -2,7 +2,7 @@
#include <linux/version.h>
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
SEC("kprobe/blk_mq_start_request")
int bpf_prog1(struct pt_regs *ctx)

2
samples/bpf/task_fd_query_user.c
View File

@ -15,7 +15,7 @@
#include <sys/stat.h>
#include <linux/perf_event.h>
#include "libbpf.h"
#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "bpf_util.h"
#include "perf-sys.h"

2
samples/bpf/tc_l2_redirect_kern.c
View File

@ -15,7 +15,7 @@
#include <uapi/linux/filter.h>
#include <uapi/linux/pkt_cls.h>
#include <net/ipv6.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#define _htonl __builtin_bswap32

2
samples/bpf/tcbpf1_kern.c
View File

@ -7,7 +7,7 @@
#include <uapi/linux/tcp.h>
#include <uapi/linux/filter.h>
#include <uapi/linux/pkt_cls.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
/* compiler workaround */

4
samples/bpf/tcp_basertt_kern.c
View File

@ -16,8 +16,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#define DEBUG 1

4
samples/bpf/tcp_bufs_kern.c
View File

@ -17,8 +17,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#define DEBUG 1

4
samples/bpf/tcp_clamp_kern.c
View File

@ -17,8 +17,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#define DEBUG 1

4
samples/bpf/tcp_cong_kern.c
View File

@ -16,8 +16,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#define DEBUG 1

4
samples/bpf/tcp_dumpstats_kern.c
View File

@ -4,8 +4,8 @@
*/
#include <linux/bpf.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#define INTERVAL 1000000000ULL

4
samples/bpf/tcp_iw_kern.c
View File

@ -17,8 +17,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#define DEBUG 1

4
samples/bpf/tcp_rwnd_kern.c
View File

@ -16,8 +16,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#define DEBUG 1

4
samples/bpf/tcp_synrto_kern.c
View File

@ -16,8 +16,8 @@
#include <uapi/linux/if_packet.h>
#include <uapi/linux/ip.h>
#include <linux/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#define DEBUG 1

4
samples/bpf/tcp_tos_reflect_kern.c
View File

@ -15,8 +15,8 @@
#include <uapi/linux/ipv6.h>
#include <uapi/linux/in.h>
#include <linux/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
#define DEBUG 1

2
samples/bpf/test_cgrp2_tc_kern.c
View File

@ -10,7 +10,7 @@
#include <uapi/linux/ipv6.h>
#include <uapi/linux/pkt_cls.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
/* copy of 'struct ethhdr' without __packed */
struct eth_hdr {

2
samples/bpf/test_current_task_under_cgroup_kern.c
View File

@ -8,7 +8,7 @@
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
#include <linux/version.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#include <uapi/linux/utsname.h>
struct bpf_map_def SEC("maps") cgroup_map = {

2
samples/bpf/test_lwt_bpf.c
View File

@ -20,7 +20,7 @@
#include <linux/udp.h>
#include <linux/icmpv6.h>
#include <linux/if_ether.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#include <string.h>
# define printk(fmt, ...) \

4
samples/bpf/test_map_in_map_kern.c
View File

@ -10,9 +10,9 @@
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/in6.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
#include "bpf_tracing.h"
#include <bpf/bpf_tracing.h>
#define MAX_NR_PORTS 65536

4
samples/bpf/test_overhead_kprobe_kern.c
View File

@ -7,8 +7,8 @@
#include <linux/version.h>
#include <linux/ptrace.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include "bpf_tracing.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})

2
samples/bpf/test_overhead_raw_tp_kern.c
View File

@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2018 Facebook */
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
SEC("raw_tracepoint/task_rename")
int prog(struct bpf_raw_tracepoint_args *ctx)

2
samples/bpf/test_overhead_tp_kern.c
View File

@ -5,7 +5,7 @@
* License as published by the Free Software Foundation.
*/
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
/* from /sys/kernel/debug/tracing/events/task/task_rename/format */
struct task_rename {

4
samples/bpf/test_probe_write_user_kern.c
View File

@ -8,8 +8,8 @@
#include <linux/netdevice.h>
#include <uapi/linux/bpf.h>
#include <linux/version.h>
#include "bpf_helpers.h"
#include "bpf_tracing.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
struct bpf_map_def SEC("maps") dnat_map = {
.type = BPF_MAP_TYPE_HASH,

4
samples/bpf/trace_event_kern.c
View File

@ -9,8 +9,8 @@
#include <uapi/linux/bpf.h>
#include <uapi/linux/bpf_perf_event.h>
#include <uapi/linux/perf_event.h>
#include "bpf_helpers.h"
#include "bpf_tracing.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
struct key_t {
char comm[TASK_COMM_LEN];

2
samples/bpf/trace_event_user.c
View File

@ -15,7 +15,7 @@
#include <assert.h>
#include <errno.h>
#include <sys/resource.h>
#include "libbpf.h"
#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "perf-sys.h"
#include "trace_helpers.h"

2
samples/bpf/trace_output_kern.c
View File

@ -1,7 +1,7 @@
#include <linux/ptrace.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,

2
samples/bpf/trace_output_user.c
View File

@ -15,7 +15,7 @@
#include <sys/mman.h>
#include <time.h>
#include <signal.h>
#include <libbpf.h>
#include <bpf/libbpf.h>
#include "bpf_load.h"
#include "perf-sys.h"

4
samples/bpf/tracex1_kern.c
View File

@ -8,8 +8,8 @@
#include <linux/netdevice.h>
#include <uapi/linux/bpf.h>
#include <linux/version.h>
#include "bpf_helpers.h"
#include "bpf_tracing.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})

4
samples/bpf/tracex2_kern.c
View File

@ -8,8 +8,8 @@
#include <linux/netdevice.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include "bpf_tracing.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,

4
samples/bpf/tracex3_kern.c
View File

@ -8,8 +8,8 @@
#include <linux/netdevice.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include "bpf_tracing.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,

4
samples/bpf/tracex4_kern.c
View File

@ -7,8 +7,8 @@
#include <linux/ptrace.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include "bpf_tracing.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
struct pair {
u64 val;

4
samples/bpf/tracex5_kern.c
View File

@ -10,8 +10,8 @@
#include <uapi/linux/seccomp.h>
#include <uapi/linux/unistd.h>
#include "syscall_nrs.h"
#include "bpf_helpers.h"
#include "bpf_tracing.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F

2
samples/bpf/tracex6_kern.c
View File

@ -1,7 +1,7 @@
#include <linux/ptrace.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
struct bpf_map_def SEC("maps") counters = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,

2
samples/bpf/tracex7_kern.c
View File

@ -1,7 +1,7 @@
#include <uapi/linux/ptrace.h>
#include <uapi/linux/bpf.h>
#include <linux/version.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
SEC("kprobe/open_ctree")
int bpf_prog1(struct pt_regs *ctx)

2
samples/bpf/xdp1_kern.c
View File

@ -12,7 +12,7 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include "bpf_helpers.h"
#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);

Some files were not shown because too many files have changed in this diff Show More