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;
-(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;
-(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;
* 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)
/* 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)
if (err < 0)
goto err_xdp;
if (err == XDP_REDIRECT)
- xdp_do_flush_map();
+ xdp_do_flush();
if (err != XDP_PASS)
goto out;
}
if (flush)
- xdp_do_flush_map();
+ xdp_do_flush();
rcu_read_unlock();
local_bh_enable();
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;
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);
#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;
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);
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 */
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,
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 {
* 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);
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 {
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. */
#endif
struct bpf_func_info_aux {
+ u16 linkage;
bool unreliable;
};
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;
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;
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,
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);
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)
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);
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)
#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
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 */
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;
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 */
#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;
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)
{
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);
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);
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.
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);
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;
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;
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;
return false;
}
+void sock_def_readable(struct sock *sk);
+
#endif /* _SOCK_H */
#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;
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
__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)
__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,
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 */
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 {
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
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 {
/* 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 {
__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 */
__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;
*
* 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.
*
* 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), \
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
__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;
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.
*/
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
.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 = {
--- /dev/null
+// 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);
+ }
+}
--- /dev/null
+/* 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
*/
#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); \
[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,
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.
*/
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);
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);
* *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)
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;
}
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);
}
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;
}
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;
* 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. */
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;
goto errout;
}
+ bpf_struct_ops_init(btf);
+
btf_verifier_env_free(env);
refcount_set(&btf->refcnt, 1);
return btf;
/* 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)) {
/* 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;
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",
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);
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;
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);
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, ®[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;
}
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;
(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;
};
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 {
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);
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);
}
if (!dev)
continue;
- free_percpu(dev->bulkq);
dev_put(dev->dev);
kfree(dev);
}
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;
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;
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)
/* 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);
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;
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,
struct bpf_dtab_netdev *dev;
dev = container_of(rcu, struct bpf_dtab_netdev, rcu);
- free_percpu(dev->bulkq);
dev_put(dev->dev);
kfree(dev);
}
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);
}
{
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
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;
}
(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;
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,
.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 = {
.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 */
.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 = {
.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)
#include <linux/uidgid.h>
#include <linux/filter.h>
#include <linux/ctype.h>
+#include <linux/jiffies.h>
#include "../../lib/kstrtox.h"
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)
{
.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;
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);
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;
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);
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;
}
*/
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);
}
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
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)
{
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;
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);
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;
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;
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
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:
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;
}
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)
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) {
default:
return -EINVAL;
}
+ case BPF_PROG_TYPE_EXT:
+ if (expected_attach_type)
+ return -EINVAL;
+ /* fallthrough */
default:
return 0;
}
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;
}
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.
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);
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 = {};
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;
#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)
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)
switch (t) {
case BPF_TRACE_FENTRY:
return BPF_TRAMP_FENTRY;
- default:
+ case BPF_TRACE_FEXIT:
return BPF_TRAMP_FEXIT;
+ default:
+ return BPF_TRAMP_REPLACE;
}
}
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;
}
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;
}
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);
}
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)
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)
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;
}
#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.
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",
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;
}
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",
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;
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;
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:
/* 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;
}
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;
}
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) {
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;
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;
env->insn_idx++;
}
- env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return 0;
}
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;
}
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;
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;
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
kfree(sl);
sl = sln;
}
+ env->free_list = NULL;
if (!env->explored_states)
return;
kfree(sl);
sl = sln;
}
+ env->explored_states[i] = NULL;
}
+}
- kvfree(env->explored_states);
+/* 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;
+ }
+
+ 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;
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_";
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) {
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;
}
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)) {
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;
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
if (ret)
bpf_trampoline_put(tr);
return ret;
- default:
- return -EINVAL;
}
}
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;
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);
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);
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;
*/
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 = {
.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)
{
#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;
}
free_percpu(dev->pcpu_refcnt);
dev->pcpu_refcnt = NULL;
+ free_percpu(dev->xdp_bulkq);
+ dev->xdp_bulkq = NULL;
netdev_unregister_lockdep_key(dev);
.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)
{
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)
{
}
}
-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;
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;
_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,
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) {
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;
}
rcu_read_unlock();
}
-static void sock_def_readable(struct sock *sk)
+void sock_def_readable(struct sock *sk)
{
struct socket_wq *wq;
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
--- /dev/null
+// 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",
+};
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;
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();
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 */
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;
} 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);
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));
/* 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;
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;
/* 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);
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;
}
xdp_umem_unmap_pages(umem);
xdp_umem_unpin_pages(umem);
- kfree(umem->pages);
+ kvfree(umem->pages);
umem->pages = NULL;
xdp_umem_unaccount_pages(umem);
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;
if (!err)
return 0;
- kfree(umem->pages);
+ kvfree(umem->pages);
out_pin:
xdp_umem_unpin_pages(umem);
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)
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
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
@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 \
#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
#include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include "bpf_insn.h"
#include "sock_example.h"
#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 */
#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
#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 = {
#include "bpf_load.h"
#include "bpf_util.h"
-#include "libbpf.h"
+#include <bpf/libbpf.h>
static void dump_counts(int fd)
{
#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
#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, ...) \
({ \
#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
* 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>
#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"
#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
#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
#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
#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
#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"
#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)
#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 {
#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>
#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>
#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>
* 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>
#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,
#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"
/* 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;
#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)
#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"
#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
#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 */
#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
#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
#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
#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
*/
#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
#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
#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
#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
#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
#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 {
#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 = {
#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, ...) \
#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
#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;})
// 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)
* 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 {
#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,
#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];
#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"
#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,
#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"
#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;})
#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,
#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,
#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;
#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
#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,
#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)
#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);
#include <net/if.h>
#include "bpf_util.h"
-#include "bpf.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
static int ifindex;
static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
#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);
#include <uapi/linux/bpf.h>
#include <uapi/linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/*
* This struct is stored in the XDP 'data_meta' area, which is located
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/icmp.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define DEFAULT_TTL 64
#define MAX_PCKT_SIZE 600
#include <netinet/ether.h>
#include <unistd.h>
#include <time.h>
-#include "bpf.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#define STATS_INTERVAL_S 2U
#define MAX_PCKT_SIZE 600
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF)
#include <fcntl.h>
#include <libgen.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include <bpf/bpf.h>
static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
* XDP monitor tool, based on tracepoints
*/
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct bpf_map_def SEC("maps") redirect_err_cnt = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
*/
struct devmap_xmit_ctx {
u64 __pad; // First 8 bytes are not accessible by bpf code
- int map_id; // offset:8; size:4; signed:1;
+ int from_ifindex; // offset:8; size:4; signed:1;
u32 act; // offset:12; size:4; signed:0;
- u32 map_index; // offset:16; size:4; signed:0;
+ int to_ifindex; // offset:16; size:4; signed:1;
int drops; // offset:20; size:4; signed:1;
int sent; // offset:24; size:4; signed:1;
- int from_ifindex; // offset:28; size:4; signed:1;
- int to_ifindex; // offset:32; size:4; signed:1;
- int err; // offset:36; size:4; signed:1;
+ int err; // offset:28; size:4; signed:1;
};
SEC("tracepoint/xdp/xdp_devmap_xmit")
#include <uapi/linux/udp.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "hash_func01.h"
#define MAX_CPUS 64 /* WARNING - sync with _user.c */
#define MAX_PROG 6
#include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include "bpf_util.h"
#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_ARRAY);
#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_DEVMAP);
#include "bpf_util.h"
#include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
static int ifindex_in;
static int ifindex_out;
#include "bpf_util.h"
#include <bpf/bpf.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
static int ifindex_in;
static int ifindex_out;
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include <linux/slab.h>
#include <net/ip_fib.h>
#include <sys/ioctl.h>
#include <sys/syscall.h>
#include "bpf_util.h"
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include <sys/resource.h>
#include <libgen.h>
#include <uapi/linux/bpf.h>
#include <uapi/linux/if_ether.h>
#include <uapi/linux/in.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* Config setup from with userspace
*
#include <arpa/inet.h>
#include <linux/if_link.h>
-#include "bpf.h"
-#include "libbpf.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#include "bpf_util.h"
static int ifindex = -1;
#include <linux/ptrace.h>
#include <linux/version.h>
#include <uapi/linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define SAMPLE_SIZE 64ul
#define MAX_CPUS 128
#include <sys/sysinfo.h>
#include <sys/ioctl.h>
#include <signal.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
#include <bpf/bpf.h>
#include <sys/resource.h>
#include <libgen.h>
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "xdp_tx_iptunnel_common.h"
struct {
#include <netinet/ether.h>
#include <unistd.h>
#include <time.h>
-#include "libbpf.h"
+#include <bpf/libbpf.h>
#include <bpf/bpf.h>
#include "bpf_util.h"
#include "xdp_tx_iptunnel_common.h"
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "xdpsock.h"
/* This XDP program is only needed for the XDP_SHARED_UMEM mode.
#include <time.h>
#include <unistd.h>
-#include "libbpf.h"
-#include "xsk.h"
-#include "xdpsock.h"
+#include <bpf/libbpf.h>
+#include <bpf/xsk.h>
#include <bpf/bpf.h>
+#include "xdpsock.h"
#ifndef SOL_XDP
#define SOL_XDP 283
break
self.reader.close()
- print('Parsed description of %d helper function(s)' % len(self.helpers),
- file=sys.stderr)
###############################################################################
local bin_arch
if ! [ -x "$(command -v ${PAHOLE})" ]; then
- info "BTF" "${1}: pahole (${PAHOLE}) is not available"
+ echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available"
return 1
fi
pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/')
if [ "${pahole_ver}" -lt "113" ]; then
- info "BTF" "${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13"
+ echo >&2 "BTF: ${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13"
return 1
fi
FEATURE_DISPLAY = libbfd disassembler-four-args
check_feat := 1
-NON_CHECK_FEAT_TARGETS := clean bpftool_clean
+NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean
ifdef MAKECMDGOALS
ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),)
check_feat := 0
PROGS = $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg $(OUTPUT)bpf_asm
-all: $(PROGS) bpftool
+all: $(PROGS) bpftool runqslower
$(OUTPUT)bpf_jit_disasm: CFLAGS += -DPACKAGE='bpf_jit_disasm'
$(OUTPUT)bpf_jit_disasm: $(OUTPUT)bpf_jit_disasm.o
$(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c
$(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c
-clean: bpftool_clean
+clean: bpftool_clean runqslower_clean
$(call QUIET_CLEAN, bpf-progs)
$(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \
$(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.*
$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf
$(Q)$(RM) -r -- $(OUTPUT)feature
-install: $(PROGS) bpftool_install
+install: $(PROGS) bpftool_install runqslower_install
$(call QUIET_INSTALL, bpf_jit_disasm)
$(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/bin
$(Q)$(INSTALL) $(OUTPUT)bpf_jit_disasm $(DESTDIR)$(prefix)/bin/bpf_jit_disasm
bpftool_clean:
$(call descend,bpftool,clean)
-.PHONY: all install clean bpftool bpftool_install bpftool_clean
+runqslower:
+ $(call descend,runqslower)
+
+runqslower_install:
+ $(call descend,runqslower,install)
+
+runqslower_clean:
+ $(call descend,runqslower,clean)
+
+.PHONY: all install clean bpftool bpftool_install bpftool_clean \
+ runqslower runqslower_install runqslower_clean
#define __EXAMPLE_SKEL_H__
#include <stdlib.h>
- #include <libbpf.h>
+ #include <bpf/libbpf.h>
struct example {
struct bpf_object_skeleton *skeleton;
-I$(srctree)/kernel/bpf/ \
-I$(srctree)/tools/include \
-I$(srctree)/tools/include/uapi \
- -I$(srctree)/tools/lib/bpf \
+ -I$(srctree)/tools/lib \
-I$(srctree)/tools/perf
CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
ifneq ($(EXTRA_CFLAGS),)
#include <stdio.h>
#include <string.h>
#include <unistd.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
#include <linux/btf.h>
#include <linux/hashtable.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
-#include "btf.h"
#include "json_writer.h"
#include "main.h"
if (IS_ERR(d))
return PTR_ERR(d);
+ printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
+ printf("#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)\n");
+ printf("#endif\n\n");
+
if (root_type_cnt) {
for (i = 0; i < root_type_cnt; i++) {
err = btf_dump__dump_type(d, root_type_ids[i]);
}
}
+ printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n");
+ printf("#pragma clang attribute pop\n");
+ printf("#endif\n");
+
done:
btf_dump__free(d);
return err;
if (IS_ERR(btf)) {
err = PTR_ERR(btf);
btf = NULL;
- p_err("failed to load BTF from %s: %s",
+ p_err("failed to load BTF from %s: %s",
*argv, strerror(err));
goto done;
}
#include <linux/bitops.h>
#include <linux/btf.h>
#include <linux/err.h>
+#include <bpf/btf.h>
-#include "btf.h"
#include "json_writer.h"
#include "main.h"
#include <sys/types.h>
#include <unistd.h>
-#include <bpf.h>
+#include <bpf/bpf.h>
#include "main.h"
#include <sys/stat.h>
#include <sys/vfs.h>
-#include <bpf.h>
-#include <libbpf.h> /* libbpf_num_possible_cpus */
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
#include "main.h"
#include <linux/filter.h>
#include <linux/limits.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#include <zlib.h>
#include "main.h"
printf("\n");
}
+static void
+probe_large_insn_limit(const char *define_prefix, __u32 ifindex)
+{
+ bool res;
+
+ res = bpf_probe_large_insn_limit(ifindex);
+ print_bool_feature("have_large_insn_limit",
+ "Large program size limit",
+ "HAVE_LARGE_INSN_LIMIT",
+ res, define_prefix);
+}
+
static int do_probe(int argc, char **argv)
{
enum probe_component target = COMPONENT_UNSPEC;
probe_helpers_for_progtype(i, supported_types[i],
define_prefix, ifindex);
+ print_end_then_start_section("misc",
+ "Scanning miscellaneous eBPF features...",
+ "/*** eBPF misc features ***/",
+ define_prefix);
+ probe_large_insn_limit(define_prefix, ifindex);
+
exit_close_json:
if (json_output) {
/* End current "section" of probes */
#include <stdio.h>
#include <string.h>
#include <unistd.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/mman.h>
#include <unistd.h>
+#include <bpf/btf.h>
-#include "btf.h"
-#include "libbpf_internal.h"
+#include "bpf/libbpf_internal.h"
#include "json_writer.h"
#include "main.h"
#define %2$s \n\
\n\
#include <stdlib.h> \n\
- #include <libbpf.h> \n\
+ #include <bpf/libbpf.h> \n\
\n\
struct %1$s { \n\
struct bpf_object_skeleton *skeleton; \n\
#include <dis-asm.h>
#include <sys/stat.h>
#include <limits.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
#include "json_writer.h"
#include "main.h"
#include <stdlib.h>
#include <string.h>
-#include <bpf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#include "main.h"
#include <sys/types.h>
#include <sys/stat.h>
-#include <bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
-#include "btf.h"
#include "json_writer.h"
#include "main.h"
[BPF_MAP_TYPE_QUEUE] = "queue",
[BPF_MAP_TYPE_STACK] = "stack",
[BPF_MAP_TYPE_SK_STORAGE] = "sk_storage",
+ [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops",
};
const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
struct bpf_map_info *map_info, void *key,
void *value)
{
+ __u32 value_id;
int ret;
/* start of key-value pair */
goto err_end_obj;
}
+ value_id = map_info->btf_vmlinux_value_type_id ?
+ : map_info->btf_value_type_id;
+
if (!map_is_per_cpu(map_info->type)) {
jsonw_name(d->jw, "value");
- ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+ ret = btf_dumper_type(d, value_id, value);
} else {
unsigned int i, n, step;
jsonw_start_object(d->jw);
jsonw_int_field(d->jw, "cpu", i);
jsonw_name(d->jw, "value");
- ret = btf_dumper_type(d, map_info->btf_value_type_id,
- value + i * step);
+ ret = btf_dumper_type(d, value_id, value + i * step);
jsonw_end_object(d->jw);
if (ret)
break;
{
struct bpf_map_info info = {};
__u32 len = sizeof(info);
- struct btf *btf = NULL;
int err, i;
for (i = 0; i < nb_fds; i++) {
err = bpf_obj_get_info_by_fd(fds[i], &info, &len);
if (err) {
p_err("can't get map info: %s", strerror(errno));
- goto err_close;
- }
-
- err = btf__get_from_id(info.btf_id, &btf);
- if (err) {
- p_err("failed to get btf");
- goto err_close;
+ return -1;
}
- if (!btf)
+ if (!info.btf_id)
return 0;
}
return 1;
+}
-err_close:
- for (; i < nb_fds; i++)
- close(fds[i]);
- return -1;
+static struct btf *btf_vmlinux;
+
+static struct btf *get_map_kv_btf(const struct bpf_map_info *info)
+{
+ struct btf *btf = NULL;
+
+ if (info->btf_vmlinux_value_type_id) {
+ if (!btf_vmlinux) {
+ btf_vmlinux = libbpf_find_kernel_btf();
+ if (IS_ERR(btf_vmlinux))
+ p_err("failed to get kernel btf");
+ }
+ return btf_vmlinux;
+ } else if (info->btf_value_type_id) {
+ int err;
+
+ err = btf__get_from_id(info->btf_id, &btf);
+ if (err || !btf) {
+ p_err("failed to get btf");
+ btf = err ? ERR_PTR(err) : ERR_PTR(-ESRCH);
+ }
+ }
+
+ return btf;
+}
+
+static void free_map_kv_btf(struct btf *btf)
+{
+ if (!IS_ERR(btf) && btf != btf_vmlinux)
+ btf__free(btf);
+}
+
+static void free_btf_vmlinux(void)
+{
+ if (!IS_ERR(btf_vmlinux))
+ btf__free(btf_vmlinux);
}
static int
map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr,
- bool enable_btf, bool show_header)
+ bool show_header)
{
void *key, *value, *prev_key;
unsigned int num_elems = 0;
prev_key = NULL;
- if (enable_btf) {
- err = btf__get_from_id(info->btf_id, &btf);
- if (err || !btf) {
- /* enable_btf is true only if we've already checked
- * that all maps have BTF information.
- */
- p_err("failed to get btf");
+ if (wtr) {
+ btf = get_map_kv_btf(info);
+ if (IS_ERR(btf)) {
+ err = PTR_ERR(btf);
goto exit_free;
}
- }
- if (wtr) {
if (show_header) {
jsonw_start_object(wtr); /* map object */
show_map_header_json(info, wtr);
free(key);
free(value);
close(fd);
- btf__free(btf);
+ free_map_kv_btf(btf);
return err;
}
{
json_writer_t *wtr = NULL, *btf_wtr = NULL;
struct bpf_map_info info = {};
- int nb_fds, i = 0, btf = 0;
+ int nb_fds, i = 0;
__u32 len = sizeof(info);
int *fds = NULL;
int err = -1;
if (json_output) {
wtr = json_wtr;
} else {
- btf = maps_have_btf(fds, nb_fds);
- if (btf < 0)
+ int do_plain_btf;
+
+ do_plain_btf = maps_have_btf(fds, nb_fds);
+ if (do_plain_btf < 0)
goto exit_close;
- if (btf) {
+
+ if (do_plain_btf) {
btf_wtr = get_btf_writer();
- if (btf_wtr) {
- wtr = btf_wtr;
- } else {
+ wtr = btf_wtr;
+ if (!btf_wtr)
p_info("failed to create json writer for btf. falling back to plain output");
- btf = 0;
- }
}
}
p_err("can't get map info: %s", strerror(errno));
break;
}
- err = map_dump(fds[i], &info, wtr, btf, nb_fds > 1);
+ err = map_dump(fds[i], &info, wtr, nb_fds > 1);
if (!wtr && i != nb_fds - 1)
printf("\n");
if (wtr && nb_fds > 1)
jsonw_end_array(wtr); /* root array */
- if (btf)
+ if (btf_wtr)
jsonw_destroy(&btf_wtr);
exit_close:
for (; i < nb_fds; i++)
close(fds[i]);
exit_free:
free(fds);
+ free_btf_vmlinux();
return err;
}
*/
#include <errno.h>
#include <fcntl.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
#include <poll.h>
#include <signal.h>
#include <stdbool.h>
#include <sys/mman.h>
#include <sys/syscall.h>
-#include <bpf.h>
+#include <bpf/bpf.h>
#include <perf-sys.h>
#include "main.h"
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
#include <net/if.h>
#include <linux/if.h>
#include <linux/rtnetlink.h>
#include <sys/stat.h>
#include <sys/types.h>
-#include <bpf.h>
-#include <nlattr.h>
-#include "libbpf_internal.h"
+#include "bpf/nlattr.h"
+#include "bpf/libbpf_internal.h"
#include "main.h"
#include "netlink_dumper.h"
#include <stdlib.h>
#include <string.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
#include <linux/rtnetlink.h>
#include <linux/tc_act/tc_bpf.h>
-#include <nlattr.h>
+#include "bpf/nlattr.h"
#include "main.h"
#include "netlink_dumper.h"
#include <unistd.h>
#include <ftw.h>
-#include <bpf.h>
+#include <bpf/bpf.h>
#include "main.h"
#include <linux/err.h>
#include <linux/sizes.h>
-#include <bpf.h>
-#include <btf.h>
-#include <libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
#include "cfg.h"
#include "main.h"
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
-#include <libbpf.h>
+#include <bpf/libbpf.h>
#include "disasm.h"
#include "json_writer.h"
--- /dev/null
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+OUTPUT := .output
+CLANG := clang
+LLC := llc
+LLVM_STRIP := llvm-strip
+DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+LIBBPF_SRC := $(abspath ../../lib/bpf)
+BPFOBJ := $(OUTPUT)/libbpf.a
+BPF_INCLUDE := $(OUTPUT)
+INCLUDES := -I$(BPF_INCLUDE) -I$(OUTPUT) -I$(abspath ../../lib)
+CFLAGS := -g -Wall
+
+# Try to detect best kernel BTF source
+KERNEL_REL := $(shell uname -r)
+VMLINUX_BTF_PATHS := /sys/kernel/btf/vmlinux /boot/vmlinux-$(KERNEL_REL)
+VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword \
+ $(wildcard $(VMLINUX_BTF_PATHS))))
+
+abs_out := $(abspath $(OUTPUT))
+ifeq ($(V),1)
+Q =
+msg =
+else
+Q = @
+msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))";
+MAKEFLAGS += --no-print-directory
+submake_extras := feature_display=0
+endif
+
+.DELETE_ON_ERROR:
+
+.PHONY: all clean runqslower
+all: runqslower
+
+runqslower: $(OUTPUT)/runqslower
+
+clean:
+ $(call msg,CLEAN)
+ $(Q)rm -rf $(OUTPUT) runqslower
+
+$(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ)
+ $(call msg,BINARY,$@)
+ $(Q)$(CC) $(CFLAGS) -lelf -lz $^ -o $@
+
+$(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \
+ $(OUTPUT)/runqslower.bpf.o
+
+$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h
+
+$(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL)
+ $(call msg,GEN-SKEL,$@)
+ $(Q)$(BPFTOOL) gen skeleton $< > $@
+
+$(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT)
+ $(call msg,BPF,$@)
+ $(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES) \
+ -c $(filter %.c,$^) -o $@ && \
+ $(LLVM_STRIP) -g $@
+
+$(OUTPUT)/%.o: %.c | $(OUTPUT)
+ $(call msg,CC,$@)
+ $(Q)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@
+
+$(OUTPUT):
+ $(call msg,MKDIR,$@)
+ $(Q)mkdir -p $(OUTPUT)
+
+$(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL)
+ $(call msg,GEN,$@)
+ $(Q)if [ ! -e "$(VMLINUX_BTF_PATH)" ] ; then \
+ echo "Couldn't find kernel BTF; set VMLINUX_BTF to" \
+ "specify its location." >&2; \
+ exit 1;\
+ fi
+ $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@
+
+$(BPFOBJ): | $(OUTPUT)
+ $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \
+ OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
+
+$(DEFAULT_BPFTOOL):
+ $(Q)$(MAKE) $(submake_extras) -C ../bpftool \
+ prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "runqslower.h"
+
+#define TASK_RUNNING 0
+
+#define BPF_F_INDEX_MASK 0xffffffffULL
+#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK
+
+const volatile __u64 min_us = 0;
+const volatile pid_t targ_pid = 0;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 10240);
+ __type(key, u32);
+ __type(value, u64);
+} start SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+ __uint(key_size, sizeof(u32));
+ __uint(value_size, sizeof(u32));
+} events SEC(".maps");
+
+/* record enqueue timestamp */
+__always_inline
+static int trace_enqueue(u32 tgid, u32 pid)
+{
+ u64 ts;
+
+ if (!pid || (targ_pid && targ_pid != pid))
+ return 0;
+
+ ts = bpf_ktime_get_ns();
+ bpf_map_update_elem(&start, &pid, &ts, 0);
+ return 0;
+}
+
+SEC("tp_btf/sched_wakeup")
+int handle__sched_wakeup(u64 *ctx)
+{
+ /* TP_PROTO(struct task_struct *p) */
+ struct task_struct *p = (void *)ctx[0];
+
+ return trace_enqueue(p->tgid, p->pid);
+}
+
+SEC("tp_btf/sched_wakeup_new")
+int handle__sched_wakeup_new(u64 *ctx)
+{
+ /* TP_PROTO(struct task_struct *p) */
+ struct task_struct *p = (void *)ctx[0];
+
+ return trace_enqueue(p->tgid, p->pid);
+}
+
+SEC("tp_btf/sched_switch")
+int handle__sched_switch(u64 *ctx)
+{
+ /* TP_PROTO(bool preempt, struct task_struct *prev,
+ * struct task_struct *next)
+ */
+ struct task_struct *prev = (struct task_struct *)ctx[1];
+ struct task_struct *next = (struct task_struct *)ctx[2];
+ struct event event = {};
+ u64 *tsp, delta_us;
+ long state;
+ u32 pid;
+
+ /* ivcsw: treat like an enqueue event and store timestamp */
+ if (prev->state == TASK_RUNNING)
+ trace_enqueue(prev->tgid, prev->pid);
+
+ pid = next->pid;
+
+ /* fetch timestamp and calculate delta */
+ tsp = bpf_map_lookup_elem(&start, &pid);
+ if (!tsp)
+ return 0; /* missed enqueue */
+
+ delta_us = (bpf_ktime_get_ns() - *tsp) / 1000;
+ if (min_us && delta_us <= min_us)
+ return 0;
+
+ event.pid = pid;
+ event.delta_us = delta_us;
+ bpf_get_current_comm(&event.task, sizeof(event.task));
+
+ /* output */
+ bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU,
+ &event, sizeof(event));
+
+ bpf_map_delete_elem(&start, &pid);
+ return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+// Copyright (c) 2019 Facebook
+#include <argp.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <time.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+#include "runqslower.h"
+#include "runqslower.skel.h"
+
+struct env {
+ pid_t pid;
+ __u64 min_us;
+ bool verbose;
+} env = {
+ .min_us = 10000,
+};
+
+const char *argp_program_version = "runqslower 0.1";
+const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
+const char argp_program_doc[] =
+"runqslower Trace long process scheduling delays.\n"
+" For Linux, uses eBPF, BPF CO-RE, libbpf, BTF.\n"
+"\n"
+"This script traces high scheduling delays between tasks being\n"
+"ready to run and them running on CPU after that.\n"
+"\n"
+"USAGE: runqslower [-p PID] [min_us]\n"
+"\n"
+"EXAMPLES:\n"
+" runqslower # trace run queue latency higher than 10000 us (default)\n"
+" runqslower 1000 # trace run queue latency higher than 1000 us\n"
+" runqslower -p 123 # trace pid 123 only\n";
+
+static const struct argp_option opts[] = {
+ { "pid", 'p', "PID", 0, "Process PID to trace"},
+ { "verbose", 'v', NULL, 0, "Verbose debug output" },
+ {},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+ static int pos_args;
+ int pid;
+ long long min_us;
+
+ switch (key) {
+ case 'v':
+ env.verbose = true;
+ break;
+ case 'p':
+ errno = 0;
+ pid = strtol(arg, NULL, 10);
+ if (errno || pid <= 0) {
+ fprintf(stderr, "Invalid PID: %s\n", arg);
+ argp_usage(state);
+ }
+ env.pid = pid;
+ break;
+ case ARGP_KEY_ARG:
+ if (pos_args++) {
+ fprintf(stderr,
+ "Unrecognized positional argument: %s\n", arg);
+ argp_usage(state);
+ }
+ errno = 0;
+ min_us = strtoll(arg, NULL, 10);
+ if (errno || min_us <= 0) {
+ fprintf(stderr, "Invalid delay (in us): %s\n", arg);
+ argp_usage(state);
+ }
+ env.min_us = min_us;
+ break;
+ default:
+ return ARGP_ERR_UNKNOWN;
+ }
+ return 0;
+}
+
+int libbpf_print_fn(enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ if (level == LIBBPF_DEBUG && !env.verbose)
+ return 0;
+ return vfprintf(stderr, format, args);
+}
+
+static int bump_memlock_rlimit(void)
+{
+ struct rlimit rlim_new = {
+ .rlim_cur = RLIM_INFINITY,
+ .rlim_max = RLIM_INFINITY,
+ };
+
+ return setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+}
+
+void handle_event(void *ctx, int cpu, void *data, __u32 data_sz)
+{
+ const struct event *e = data;
+ struct tm *tm;
+ char ts[32];
+ time_t t;
+
+ time(&t);
+ tm = localtime(&t);
+ strftime(ts, sizeof(ts), "%H:%M:%S", tm);
+ printf("%-8s %-16s %-6d %14llu\n", ts, e->task, e->pid, e->delta_us);
+}
+
+void handle_lost_events(void *ctx, int cpu, __u64 lost_cnt)
+{
+ printf("Lost %llu events on CPU #%d!\n", lost_cnt, cpu);
+}
+
+int main(int argc, char **argv)
+{
+ static const struct argp argp = {
+ .options = opts,
+ .parser = parse_arg,
+ .doc = argp_program_doc,
+ };
+ struct perf_buffer_opts pb_opts;
+ struct perf_buffer *pb = NULL;
+ struct runqslower_bpf *obj;
+ int err;
+
+ err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
+ if (err)
+ return err;
+
+ libbpf_set_print(libbpf_print_fn);
+
+ err = bump_memlock_rlimit();
+ if (err) {
+ fprintf(stderr, "failed to increase rlimit: %d", err);
+ return 1;
+ }
+
+ obj = runqslower_bpf__open();
+ if (!obj) {
+ fprintf(stderr, "failed to open and/or load BPF object\n");
+ return 1;
+ }
+
+ /* initialize global data (filtering options) */
+ obj->rodata->targ_pid = env.pid;
+ obj->rodata->min_us = env.min_us;
+
+ err = runqslower_bpf__load(obj);
+ if (err) {
+ fprintf(stderr, "failed to load BPF object: %d\n", err);
+ goto cleanup;
+ }
+
+ err = runqslower_bpf__attach(obj);
+ if (err) {
+ fprintf(stderr, "failed to attach BPF programs\n");
+ goto cleanup;
+ }
+
+ printf("Tracing run queue latency higher than %llu us\n", env.min_us);
+ printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)");
+
+ pb_opts.sample_cb = handle_event;
+ pb_opts.lost_cb = handle_lost_events;
+ pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, &pb_opts);
+ err = libbpf_get_error(pb);
+ if (err) {
+ pb = NULL;
+ fprintf(stderr, "failed to open perf buffer: %d\n", err);
+ goto cleanup;
+ }
+
+ while ((err = perf_buffer__poll(pb, 100)) >= 0)
+ ;
+ printf("Error polling perf buffer: %d\n", err);
+
+cleanup:
+ perf_buffer__free(pb);
+ runqslower_bpf__destroy(obj);
+
+ return err != 0;
+}
--- /dev/null
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __RUNQSLOWER_H
+#define __RUNQSLOWER_H
+
+#define TASK_COMM_LEN 16
+
+struct event {
+ char task[TASK_COMM_LEN];
+ __u64 delta_us;
+ pid_t pid;
+};
+
+#endif /* __RUNQSLOWER_H */
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 {
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
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 {
/* 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 {
__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 */
__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;
*
* 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.
*
* 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), \
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
__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;
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.
*/
IFLA_MAX_MTU,
IFLA_PROP_LIST,
IFLA_ALT_IFNAME, /* Alternative ifname */
+ IFLA_PERM_ADDRESS,
__IFLA_MAX
};
$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
$(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
- $(Q)$(srctree)/scripts/bpf_helpers_doc.py --header \
+ $(QUIET_GEN)$(srctree)/scripts/bpf_helpers_doc.py --header \
--file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS)
$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
clean:
- $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \
- *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \
- *.pc LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \
- $(SHARED_OBJDIR) $(STATIC_OBJDIR)
+ $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \
+ *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \
+ $(SHARED_OBJDIR) $(STATIC_OBJDIR) \
+ $(addprefix $(OUTPUT), \
+ *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc)
$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
#include "libbpf.h"
#include "libbpf_internal.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
/*
* When building perf, unistd.h is overridden. __NR_bpf is
* required to be defined explicitly.
attr.btf_key_type_id = create_attr->btf_key_type_id;
attr.btf_value_type_id = create_attr->btf_value_type_id;
attr.map_ifindex = create_attr->map_ifindex;
- attr.inner_map_fd = create_attr->inner_map_fd;
+ if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS)
+ attr.btf_vmlinux_value_type_id =
+ create_attr->btf_vmlinux_value_type_id;
+ else
+ attr.inner_map_fd = create_attr->inner_map_fd;
return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}
memset(&attr, 0, sizeof(attr));
attr.prog_type = load_attr->prog_type;
attr.expected_attach_type = load_attr->expected_attach_type;
- if (attr.prog_type == BPF_PROG_TYPE_TRACING) {
+ if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS) {
+ attr.attach_btf_id = load_attr->attach_btf_id;
+ } else if (attr.prog_type == BPF_PROG_TYPE_TRACING ||
+ attr.prog_type == BPF_PROG_TYPE_EXT) {
attr.attach_btf_id = load_attr->attach_btf_id;
attr.attach_prog_fd = load_attr->attach_prog_fd;
} else {
return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
}
+static int bpf_map_batch_common(int cmd, int fd, void *in_batch,
+ void *out_batch, void *keys, void *values,
+ __u32 *count,
+ const struct bpf_map_batch_opts *opts)
+{
+ union bpf_attr attr;
+ int ret;
+
+ if (!OPTS_VALID(opts, bpf_map_batch_opts))
+ return -EINVAL;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.batch.map_fd = fd;
+ attr.batch.in_batch = ptr_to_u64(in_batch);
+ attr.batch.out_batch = ptr_to_u64(out_batch);
+ attr.batch.keys = ptr_to_u64(keys);
+ attr.batch.values = ptr_to_u64(values);
+ attr.batch.count = *count;
+ attr.batch.elem_flags = OPTS_GET(opts, elem_flags, 0);
+ attr.batch.flags = OPTS_GET(opts, flags, 0);
+
+ ret = sys_bpf(cmd, &attr, sizeof(attr));
+ *count = attr.batch.count;
+
+ return ret;
+}
+
+int bpf_map_delete_batch(int fd, void *keys, __u32 *count,
+ const struct bpf_map_batch_opts *opts)
+{
+ return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL,
+ NULL, keys, NULL, count, opts);
+}
+
+int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys,
+ void *values, __u32 *count,
+ const struct bpf_map_batch_opts *opts)
+{
+ return bpf_map_batch_common(BPF_MAP_LOOKUP_BATCH, fd, in_batch,
+ out_batch, keys, values, count, opts);
+}
+
+int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch,
+ void *keys, void *values, __u32 *count,
+ const struct bpf_map_batch_opts *opts)
+{
+ return bpf_map_batch_common(BPF_MAP_LOOKUP_AND_DELETE_BATCH,
+ fd, in_batch, out_batch, keys, values,
+ count, opts);
+}
+
+int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count,
+ const struct bpf_map_batch_opts *opts)
+{
+ return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL,
+ keys, values, count, opts);
+}
+
int bpf_obj_pin(int fd, const char *pathname)
{
union bpf_attr attr;
__u32 btf_key_type_id;
__u32 btf_value_type_id;
__u32 map_ifindex;
- __u32 inner_map_fd;
+ union {
+ __u32 inner_map_fd;
+ __u32 btf_vmlinux_value_type_id;
+ };
};
LIBBPF_API int
LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
LIBBPF_API int bpf_map_freeze(int fd);
+
+struct bpf_map_batch_opts {
+ size_t sz; /* size of this struct for forward/backward compatibility */
+ __u64 elem_flags;
+ __u64 flags;
+};
+#define bpf_map_batch_opts__last_field flags
+
+LIBBPF_API int bpf_map_delete_batch(int fd, void *keys,
+ __u32 *count,
+ const struct bpf_map_batch_opts *opts);
+LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch,
+ void *keys, void *values, __u32 *count,
+ const struct bpf_map_batch_opts *opts);
+LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch,
+ void *out_batch, void *keys,
+ void *values, __u32 *count,
+ const struct bpf_map_batch_opts *opts);
+LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values,
+ __u32 *count,
+ const struct bpf_map_batch_opts *opts);
+
LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
LIBBPF_API int bpf_obj_get(const char *pathname);
#include "libbpf.h"
#include "libbpf_internal.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
struct bpf_prog_linfo {
void *raw_linfo;
void *raw_jited_linfo;
#include <fcntl.h>
#include <unistd.h>
#include <errno.h>
+#include <sys/utsname.h>
+#include <sys/param.h>
+#include <sys/stat.h>
+#include <linux/kernel.h>
#include <linux/err.h>
#include <linux/btf.h>
#include <gelf.h>
#include "libbpf_internal.h"
#include "hashmap.h"
-#define BTF_MAX_NR_TYPES 0x7fffffff
-#define BTF_MAX_STR_OFFSET 0x7fffffff
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
+#define BTF_MAX_NR_TYPES 0x7fffffffU
+#define BTF_MAX_STR_OFFSET 0x7fffffffU
static struct btf_type btf_void;
if (btf->types_size == BTF_MAX_NR_TYPES)
return -E2BIG;
- expand_by = max(btf->types_size >> 2, 16);
+ expand_by = max(btf->types_size >> 2, 16U);
new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by);
new_types = realloc(btf->types, sizeof(*new_types) * new_size);
switch (kind) {
case BTF_KIND_INT:
case BTF_KIND_ENUM:
- return min(sizeof(void *), t->size);
+ return min(sizeof(void *), (size_t)t->size);
case BTF_KIND_PTR:
return sizeof(void *);
case BTF_KIND_TYPEDEF:
if (d->hypot_cnt == d->hypot_cap) {
__u32 *new_list;
- d->hypot_cap += max(16, d->hypot_cap / 2);
+ d->hypot_cap += max((size_t)16, d->hypot_cap / 2);
new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap);
if (!new_list)
return -ENOMEM;
if (strs.cnt + 1 > strs.cap) {
struct btf_str_ptr *new_ptrs;
- strs.cap += max(strs.cnt / 2, 16);
+ strs.cap += max(strs.cnt / 2, 16U);
new_ptrs = realloc(strs.ptrs,
sizeof(strs.ptrs[0]) * strs.cap);
if (!new_ptrs) {
}
return 0;
}
+
+static struct btf *btf_load_raw(const char *path)
+{
+ struct btf *btf;
+ size_t read_cnt;
+ struct stat st;
+ void *data;
+ FILE *f;
+
+ if (stat(path, &st))
+ return ERR_PTR(-errno);
+
+ data = malloc(st.st_size);
+ if (!data)
+ return ERR_PTR(-ENOMEM);
+
+ f = fopen(path, "rb");
+ if (!f) {
+ btf = ERR_PTR(-errno);
+ goto cleanup;
+ }
+
+ read_cnt = fread(data, 1, st.st_size, f);
+ fclose(f);
+ if (read_cnt < st.st_size) {
+ btf = ERR_PTR(-EBADF);
+ goto cleanup;
+ }
+
+ btf = btf__new(data, read_cnt);
+
+cleanup:
+ free(data);
+ return btf;
+}
+
+/*
+ * Probe few well-known locations for vmlinux kernel image and try to load BTF
+ * data out of it to use for target BTF.
+ */
+struct btf *libbpf_find_kernel_btf(void)
+{
+ struct {
+ const char *path_fmt;
+ bool raw_btf;
+ } locations[] = {
+ /* try canonical vmlinux BTF through sysfs first */
+ { "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
+ /* fall back to trying to find vmlinux ELF on disk otherwise */
+ { "/boot/vmlinux-%1$s" },
+ { "/lib/modules/%1$s/vmlinux-%1$s" },
+ { "/lib/modules/%1$s/build/vmlinux" },
+ { "/usr/lib/modules/%1$s/kernel/vmlinux" },
+ { "/usr/lib/debug/boot/vmlinux-%1$s" },
+ { "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
+ { "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
+ };
+ char path[PATH_MAX + 1];
+ struct utsname buf;
+ struct btf *btf;
+ int i;
+
+ uname(&buf);
+
+ for (i = 0; i < ARRAY_SIZE(locations); i++) {
+ snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);
+
+ if (access(path, R_OK))
+ continue;
+
+ if (locations[i].raw_btf)
+ btf = btf_load_raw(path);
+ else
+ btf = btf__parse_elf(path, NULL);
+
+ pr_debug("loading kernel BTF '%s': %ld\n",
+ path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
+ if (IS_ERR(btf))
+ continue;
+
+ return btf;
+ }
+
+ pr_warn("failed to find valid kernel BTF\n");
+ return ERR_PTR(-ESRCH);
+}
LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext);
LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext);
+LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
+
struct btf_dedup_opts {
unsigned int dedup_table_size;
bool dont_resolve_fwds;
#include "libbpf.h"
#include "libbpf_internal.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t";
static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1;
if (IS_ERR(d->type_names)) {
err = PTR_ERR(d->type_names);
d->type_names = NULL;
+ goto err;
}
d->ident_names = hashmap__new(str_hash_fn, str_equal_fn, NULL);
if (IS_ERR(d->ident_names)) {
#include <linux/err.h>
#include "hashmap.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
/* start with 4 buckets */
#define HASHMAP_MIN_CAP_BITS 2
#include "libbpf_internal.h"
#include "hashmap.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
#ifndef EM_BPF
#define EM_BPF 247
#endif
#define __printf(a, b) __attribute__((format(printf, a, b)))
+static struct bpf_map *bpf_object__add_map(struct bpf_object *obj);
+static struct bpf_program *bpf_object__find_prog_by_idx(struct bpf_object *obj,
+ int idx);
+static const struct btf_type *
+skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
+
static int __base_pr(enum libbpf_print_level level, const char *format,
va_list args)
{
__u32 btf_datasec:1;
/* BPF_F_MMAPABLE is supported for arrays */
__u32 array_mmap:1;
+ /* BTF_FUNC_GLOBAL is supported */
+ __u32 btf_func_global:1;
};
enum reloc_type {
__u32 prog_flags;
};
+struct bpf_struct_ops {
+ const char *tname;
+ const struct btf_type *type;
+ struct bpf_program **progs;
+ __u32 *kern_func_off;
+ /* e.g. struct tcp_congestion_ops in bpf_prog's btf format */
+ void *data;
+ /* e.g. struct bpf_struct_ops_tcp_congestion_ops in
+ * btf_vmlinux's format.
+ * struct bpf_struct_ops_tcp_congestion_ops {
+ * [... some other kernel fields ...]
+ * struct tcp_congestion_ops data;
+ * }
+ * kern_vdata-size == sizeof(struct bpf_struct_ops_tcp_congestion_ops)
+ * bpf_map__init_kern_struct_ops() will populate the "kern_vdata"
+ * from "data".
+ */
+ void *kern_vdata;
+ __u32 type_id;
+};
+
#define DATA_SEC ".data"
#define BSS_SEC ".bss"
#define RODATA_SEC ".rodata"
#define KCONFIG_SEC ".kconfig"
+#define STRUCT_OPS_SEC ".struct_ops"
enum libbpf_map_type {
LIBBPF_MAP_UNSPEC,
struct bpf_map_def def;
__u32 btf_key_type_id;
__u32 btf_value_type_id;
+ __u32 btf_vmlinux_value_type_id;
void *priv;
bpf_map_clear_priv_t clear_priv;
enum libbpf_map_type libbpf_type;
void *mmaped;
+ struct bpf_struct_ops *st_ops;
char *pin_path;
bool pinned;
bool reused;
Elf_Data *data;
Elf_Data *rodata;
Elf_Data *bss;
+ Elf_Data *st_ops_data;
size_t strtabidx;
struct {
GElf_Shdr shdr;
int data_shndx;
int rodata_shndx;
int bss_shndx;
+ int st_ops_shndx;
} efile;
/*
* All loaded bpf_object is linked in a list, which is
struct list_head list;
struct btf *btf;
+ /* Parse and load BTF vmlinux if any of the programs in the object need
+ * it at load time.
+ */
+ struct btf *btf_vmlinux;
struct btf_ext *btf_ext;
void *priv;
return KERNEL_VERSION(major, minor, patch);
}
+static const struct btf_member *
+find_member_by_offset(const struct btf_type *t, __u32 bit_offset)
+{
+ struct btf_member *m;
+ int i;
+
+ for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
+ if (btf_member_bit_offset(t, i) == bit_offset)
+ return m;
+ }
+
+ return NULL;
+}
+
+static const struct btf_member *
+find_member_by_name(const struct btf *btf, const struct btf_type *t,
+ const char *name)
+{
+ struct btf_member *m;
+ int i;
+
+ for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) {
+ if (!strcmp(btf__name_by_offset(btf, m->name_off), name))
+ return m;
+ }
+
+ return NULL;
+}
+
+#define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_"
+static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
+ const char *name, __u32 kind);
+
+static int
+find_struct_ops_kern_types(const struct btf *btf, const char *tname,
+ const struct btf_type **type, __u32 *type_id,
+ const struct btf_type **vtype, __u32 *vtype_id,
+ const struct btf_member **data_member)
+{
+ const struct btf_type *kern_type, *kern_vtype;
+ const struct btf_member *kern_data_member;
+ __s32 kern_vtype_id, kern_type_id;
+ __u32 i;
+
+ kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+ if (kern_type_id < 0) {
+ pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n",
+ tname);
+ return kern_type_id;
+ }
+ kern_type = btf__type_by_id(btf, kern_type_id);
+
+ /* Find the corresponding "map_value" type that will be used
+ * in map_update(BPF_MAP_TYPE_STRUCT_OPS). For example,
+ * find "struct bpf_struct_ops_tcp_congestion_ops" from the
+ * btf_vmlinux.
+ */
+ kern_vtype_id = find_btf_by_prefix_kind(btf, STRUCT_OPS_VALUE_PREFIX,
+ tname, BTF_KIND_STRUCT);
+ if (kern_vtype_id < 0) {
+ pr_warn("struct_ops init_kern: struct %s%s is not found in kernel BTF\n",
+ STRUCT_OPS_VALUE_PREFIX, tname);
+ return kern_vtype_id;
+ }
+ kern_vtype = btf__type_by_id(btf, kern_vtype_id);
+
+ /* Find "struct tcp_congestion_ops" from
+ * struct bpf_struct_ops_tcp_congestion_ops {
+ * [ ... ]
+ * struct tcp_congestion_ops data;
+ * }
+ */
+ kern_data_member = btf_members(kern_vtype);
+ for (i = 0; i < btf_vlen(kern_vtype); i++, kern_data_member++) {
+ if (kern_data_member->type == kern_type_id)
+ break;
+ }
+ if (i == btf_vlen(kern_vtype)) {
+ pr_warn("struct_ops init_kern: struct %s data is not found in struct %s%s\n",
+ tname, STRUCT_OPS_VALUE_PREFIX, tname);
+ return -EINVAL;
+ }
+
+ *type = kern_type;
+ *type_id = kern_type_id;
+ *vtype = kern_vtype;
+ *vtype_id = kern_vtype_id;
+ *data_member = kern_data_member;
+
+ return 0;
+}
+
+static bool bpf_map__is_struct_ops(const struct bpf_map *map)
+{
+ return map->def.type == BPF_MAP_TYPE_STRUCT_OPS;
+}
+
+/* Init the map's fields that depend on kern_btf */
+static int bpf_map__init_kern_struct_ops(struct bpf_map *map,
+ const struct btf *btf,
+ const struct btf *kern_btf)
+{
+ const struct btf_member *member, *kern_member, *kern_data_member;
+ const struct btf_type *type, *kern_type, *kern_vtype;
+ __u32 i, kern_type_id, kern_vtype_id, kern_data_off;
+ struct bpf_struct_ops *st_ops;
+ void *data, *kern_data;
+ const char *tname;
+ int err;
+
+ st_ops = map->st_ops;
+ type = st_ops->type;
+ tname = st_ops->tname;
+ err = find_struct_ops_kern_types(kern_btf, tname,
+ &kern_type, &kern_type_id,
+ &kern_vtype, &kern_vtype_id,
+ &kern_data_member);
+ if (err)
+ return err;
+
+ pr_debug("struct_ops init_kern %s: type_id:%u kern_type_id:%u kern_vtype_id:%u\n",
+ map->name, st_ops->type_id, kern_type_id, kern_vtype_id);
+
+ map->def.value_size = kern_vtype->size;
+ map->btf_vmlinux_value_type_id = kern_vtype_id;
+
+ st_ops->kern_vdata = calloc(1, kern_vtype->size);
+ if (!st_ops->kern_vdata)
+ return -ENOMEM;
+
+ data = st_ops->data;
+ kern_data_off = kern_data_member->offset / 8;
+ kern_data = st_ops->kern_vdata + kern_data_off;
+
+ member = btf_members(type);
+ for (i = 0; i < btf_vlen(type); i++, member++) {
+ const struct btf_type *mtype, *kern_mtype;
+ __u32 mtype_id, kern_mtype_id;
+ void *mdata, *kern_mdata;
+ __s64 msize, kern_msize;
+ __u32 moff, kern_moff;
+ __u32 kern_member_idx;
+ const char *mname;
+
+ mname = btf__name_by_offset(btf, member->name_off);
+ kern_member = find_member_by_name(kern_btf, kern_type, mname);
+ if (!kern_member) {
+ pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n",
+ map->name, mname);
+ return -ENOTSUP;
+ }
+
+ kern_member_idx = kern_member - btf_members(kern_type);
+ if (btf_member_bitfield_size(type, i) ||
+ btf_member_bitfield_size(kern_type, kern_member_idx)) {
+ pr_warn("struct_ops init_kern %s: bitfield %s is not supported\n",
+ map->name, mname);
+ return -ENOTSUP;
+ }
+
+ moff = member->offset / 8;
+ kern_moff = kern_member->offset / 8;
+
+ mdata = data + moff;
+ kern_mdata = kern_data + kern_moff;
+
+ mtype = skip_mods_and_typedefs(btf, member->type, &mtype_id);
+ kern_mtype = skip_mods_and_typedefs(kern_btf, kern_member->type,
+ &kern_mtype_id);
+ if (BTF_INFO_KIND(mtype->info) !=
+ BTF_INFO_KIND(kern_mtype->info)) {
+ pr_warn("struct_ops init_kern %s: Unmatched member type %s %u != %u(kernel)\n",
+ map->name, mname, BTF_INFO_KIND(mtype->info),
+ BTF_INFO_KIND(kern_mtype->info));
+ return -ENOTSUP;
+ }
+
+ if (btf_is_ptr(mtype)) {
+ struct bpf_program *prog;
+
+ mtype = skip_mods_and_typedefs(btf, mtype->type, &mtype_id);
+ kern_mtype = skip_mods_and_typedefs(kern_btf,
+ kern_mtype->type,
+ &kern_mtype_id);
+ if (!btf_is_func_proto(mtype) ||
+ !btf_is_func_proto(kern_mtype)) {
+ pr_warn("struct_ops init_kern %s: non func ptr %s is not supported\n",
+ map->name, mname);
+ return -ENOTSUP;
+ }
+
+ prog = st_ops->progs[i];
+ if (!prog) {
+ pr_debug("struct_ops init_kern %s: func ptr %s is not set\n",
+ map->name, mname);
+ continue;
+ }
+
+ prog->attach_btf_id = kern_type_id;
+ prog->expected_attach_type = kern_member_idx;
+
+ st_ops->kern_func_off[i] = kern_data_off + kern_moff;
+
+ pr_debug("struct_ops init_kern %s: func ptr %s is set to prog %s from data(+%u) to kern_data(+%u)\n",
+ map->name, mname, prog->name, moff,
+ kern_moff);
+
+ continue;
+ }
+
+ msize = btf__resolve_size(btf, mtype_id);
+ kern_msize = btf__resolve_size(kern_btf, kern_mtype_id);
+ if (msize < 0 || kern_msize < 0 || msize != kern_msize) {
+ pr_warn("struct_ops init_kern %s: Error in size of member %s: %zd != %zd(kernel)\n",
+ map->name, mname, (ssize_t)msize,
+ (ssize_t)kern_msize);
+ return -ENOTSUP;
+ }
+
+ pr_debug("struct_ops init_kern %s: copy %s %u bytes from data(+%u) to kern_data(+%u)\n",
+ map->name, mname, (unsigned int)msize,
+ moff, kern_moff);
+ memcpy(kern_mdata, mdata, msize);
+ }
+
+ return 0;
+}
+
+static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj)
+{
+ struct bpf_map *map;
+ size_t i;
+ int err;
+
+ for (i = 0; i < obj->nr_maps; i++) {
+ map = &obj->maps[i];
+
+ if (!bpf_map__is_struct_ops(map))
+ continue;
+
+ err = bpf_map__init_kern_struct_ops(map, obj->btf,
+ obj->btf_vmlinux);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int bpf_object__init_struct_ops_maps(struct bpf_object *obj)
+{
+ const struct btf_type *type, *datasec;
+ const struct btf_var_secinfo *vsi;
+ struct bpf_struct_ops *st_ops;
+ const char *tname, *var_name;
+ __s32 type_id, datasec_id;
+ const struct btf *btf;
+ struct bpf_map *map;
+ __u32 i;
+
+ if (obj->efile.st_ops_shndx == -1)
+ return 0;
+
+ btf = obj->btf;
+ datasec_id = btf__find_by_name_kind(btf, STRUCT_OPS_SEC,
+ BTF_KIND_DATASEC);
+ if (datasec_id < 0) {
+ pr_warn("struct_ops init: DATASEC %s not found\n",
+ STRUCT_OPS_SEC);
+ return -EINVAL;
+ }
+
+ datasec = btf__type_by_id(btf, datasec_id);
+ vsi = btf_var_secinfos(datasec);
+ for (i = 0; i < btf_vlen(datasec); i++, vsi++) {
+ type = btf__type_by_id(obj->btf, vsi->type);
+ var_name = btf__name_by_offset(obj->btf, type->name_off);
+
+ type_id = btf__resolve_type(obj->btf, vsi->type);
+ if (type_id < 0) {
+ pr_warn("struct_ops init: Cannot resolve var type_id %u in DATASEC %s\n",
+ vsi->type, STRUCT_OPS_SEC);
+ return -EINVAL;
+ }
+
+ type = btf__type_by_id(obj->btf, type_id);
+ tname = btf__name_by_offset(obj->btf, type->name_off);
+ if (!tname[0]) {
+ pr_warn("struct_ops init: anonymous type is not supported\n");
+ return -ENOTSUP;
+ }
+ if (!btf_is_struct(type)) {
+ pr_warn("struct_ops init: %s is not a struct\n", tname);
+ return -EINVAL;
+ }
+
+ map = bpf_object__add_map(obj);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ map->sec_idx = obj->efile.st_ops_shndx;
+ map->sec_offset = vsi->offset;
+ map->name = strdup(var_name);
+ if (!map->name)
+ return -ENOMEM;
+
+ map->def.type = BPF_MAP_TYPE_STRUCT_OPS;
+ map->def.key_size = sizeof(int);
+ map->def.value_size = type->size;
+ map->def.max_entries = 1;
+
+ map->st_ops = calloc(1, sizeof(*map->st_ops));
+ if (!map->st_ops)
+ return -ENOMEM;
+ st_ops = map->st_ops;
+ st_ops->data = malloc(type->size);
+ st_ops->progs = calloc(btf_vlen(type), sizeof(*st_ops->progs));
+ st_ops->kern_func_off = malloc(btf_vlen(type) *
+ sizeof(*st_ops->kern_func_off));
+ if (!st_ops->data || !st_ops->progs || !st_ops->kern_func_off)
+ return -ENOMEM;
+
+ if (vsi->offset + type->size > obj->efile.st_ops_data->d_size) {
+ pr_warn("struct_ops init: var %s is beyond the end of DATASEC %s\n",
+ var_name, STRUCT_OPS_SEC);
+ return -EINVAL;
+ }
+
+ memcpy(st_ops->data,
+ obj->efile.st_ops_data->d_buf + vsi->offset,
+ type->size);
+ st_ops->tname = tname;
+ st_ops->type = type;
+ st_ops->type_id = type_id;
+
+ pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n",
+ tname, type_id, var_name, vsi->offset);
+ }
+
+ return 0;
+}
+
static struct bpf_object *bpf_object__new(const char *path,
const void *obj_buf,
size_t obj_buf_sz,
obj->efile.data_shndx = -1;
obj->efile.rodata_shndx = -1;
obj->efile.bss_shndx = -1;
+ obj->efile.st_ops_shndx = -1;
obj->kconfig_map_idx = -1;
obj->kern_version = get_kernel_version();
obj->efile.data = NULL;
obj->efile.rodata = NULL;
obj->efile.bss = NULL;
+ obj->efile.st_ops_data = NULL;
zfree(&obj->efile.reloc_sects);
obj->efile.nr_reloc_sects = 0;
return 0;
}
-static int compare_bpf_map(const void *_a, const void *_b)
-{
- const struct bpf_map *a = _a;
- const struct bpf_map *b = _b;
-
- if (a->sec_idx != b->sec_idx)
- return a->sec_idx - b->sec_idx;
- return a->sec_offset - b->sec_offset;
-}
-
static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
{
if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
} else if (!strcmp(name, RODATA_SEC)) {
if (obj->efile.rodata)
*size = obj->efile.rodata->d_size;
+ } else if (!strcmp(name, STRUCT_OPS_SEC)) {
+ if (obj->efile.st_ops_data)
+ *size = obj->efile.st_ops_data->d_size;
} else {
ret = bpf_object_search_section_size(obj, name, &d_size);
if (!ret)
long page_sz = sysconf(_SC_PAGE_SIZE);
size_t map_sz;
- map_sz = roundup(map->def.value_size, 8) * map->def.max_entries;
+ map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries;
map_sz = roundup(map_sz, page_sz);
return map_sz;
}
return t;
}
+static const struct btf_type *
+resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id)
+{
+ const struct btf_type *t;
+
+ t = skip_mods_and_typedefs(btf, id, NULL);
+ if (!btf_is_ptr(t))
+ return NULL;
+
+ t = skip_mods_and_typedefs(btf, t->type, res_id);
+
+ return btf_is_func_proto(t) ? t : NULL;
+}
+
/*
* Fetch integer attribute of BTF map definition. Such attributes are
* represented using a pointer to an array, in which dimensionality of array
err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path);
err = err ?: bpf_object__init_global_data_maps(obj);
err = err ?: bpf_object__init_kconfig_map(obj);
+ err = err ?: bpf_object__init_struct_ops_maps(obj);
if (err)
return err;
- if (obj->nr_maps) {
- qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
- compare_bpf_map);
- }
return 0;
}
static void bpf_object__sanitize_btf(struct bpf_object *obj)
{
+ bool has_func_global = obj->caps.btf_func_global;
bool has_datasec = obj->caps.btf_datasec;
bool has_func = obj->caps.btf_func;
struct btf *btf = obj->btf;
struct btf_type *t;
int i, j, vlen;
- if (!obj->btf || (has_func && has_datasec))
+ if (!obj->btf || (has_func && has_datasec && has_func_global))
return;
for (i = 1; i <= btf__get_nr_types(btf); i++) {
} else if (!has_func && btf_is_func(t)) {
/* replace FUNC with TYPEDEF */
t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0);
+ } else if (!has_func_global && btf_is_func(t)) {
+ /* replace BTF_FUNC_GLOBAL with BTF_FUNC_STATIC */
+ t->info = BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0);
}
}
}
static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
{
return obj->efile.btf_maps_shndx >= 0 ||
- obj->nr_extern > 0;
+ obj->efile.st_ops_shndx >= 0 ||
+ obj->nr_extern > 0;
}
static int bpf_object__init_btf(struct bpf_object *obj,
Elf_Data *btf_data,
Elf_Data *btf_ext_data)
{
- bool btf_required = bpf_object__is_btf_mandatory(obj);
- int err = 0;
+ int err = -ENOENT;
if (btf_data) {
obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
if (IS_ERR(obj->btf)) {
+ err = PTR_ERR(obj->btf);
+ obj->btf = NULL;
pr_warn("Error loading ELF section %s: %d.\n",
BTF_ELF_SEC, err);
goto out;
}
+ err = 0;
}
if (btf_ext_data) {
if (!obj->btf) {
}
}
out:
- if (err || IS_ERR(obj->btf)) {
- if (btf_required)
- err = err ? : PTR_ERR(obj->btf);
- else
- err = 0;
- if (!IS_ERR_OR_NULL(obj->btf))
- btf__free(obj->btf);
- obj->btf = NULL;
- }
- if (btf_required && !obj->btf) {
+ if (err && bpf_object__is_btf_mandatory(obj)) {
pr_warn("BTF is required, but is missing or corrupted.\n");
- return err == 0 ? -ENOENT : err;
+ return err;
}
return 0;
}
return 0;
}
+static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog)
+{
+ if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
+ return true;
+
+ /* BPF_PROG_TYPE_TRACING programs which do not attach to other programs
+ * also need vmlinux BTF
+ */
+ if (prog->type == BPF_PROG_TYPE_TRACING && !prog->attach_prog_fd)
+ return true;
+
+ return false;
+}
+
+static int bpf_object__load_vmlinux_btf(struct bpf_object *obj)
+{
+ struct bpf_program *prog;
+ int err;
+
+ bpf_object__for_each_program(prog, obj) {
+ if (libbpf_prog_needs_vmlinux_btf(prog)) {
+ obj->btf_vmlinux = libbpf_find_kernel_btf();
+ if (IS_ERR(obj->btf_vmlinux)) {
+ err = PTR_ERR(obj->btf_vmlinux);
+ pr_warn("Error loading vmlinux BTF: %d\n", err);
+ obj->btf_vmlinux = NULL;
+ return err;
+ }
+ return 0;
+ }
+ }
+
+ return 0;
+}
+
static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
{
int err = 0;
} else if (strcmp(name, RODATA_SEC) == 0) {
obj->efile.rodata = data;
obj->efile.rodata_shndx = idx;
+ } else if (strcmp(name, STRUCT_OPS_SEC) == 0) {
+ obj->efile.st_ops_data = data;
+ obj->efile.st_ops_shndx = idx;
} else {
pr_debug("skip section(%d) %s\n", idx, name);
}
int sec = sh.sh_info; /* points to other section */
/* Only do relo for section with exec instructions */
- if (!section_have_execinstr(obj, sec)) {
+ if (!section_have_execinstr(obj, sec) &&
+ strcmp(name, ".rel" STRUCT_OPS_SEC)) {
pr_debug("skip relo %s(%d) for section(%d)\n",
name, idx, sec);
continue;
__u32 key_type_id = 0, value_type_id = 0;
int ret;
- /* if it's BTF-defined map, we don't need to search for type IDs */
- if (map->sec_idx == obj->efile.btf_maps_shndx)
+ /* if it's BTF-defined map, we don't need to search for type IDs.
+ * For struct_ops map, it does not need btf_key_type_id and
+ * btf_value_type_id.
+ */
+ if (map->sec_idx == obj->efile.btf_maps_shndx ||
+ bpf_map__is_struct_ops(map))
return 0;
if (!bpf_map__is_internal(map)) {
return 0;
}
+static int bpf_object__probe_btf_func_global(struct bpf_object *obj)
+{
+ static const char strs[] = "\0int\0x\0a";
+ /* static void x(int a) {} */
+ __u32 types[] = {
+ /* int */
+ BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* FUNC_PROTO */ /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
+ BTF_PARAM_ENC(7, 1),
+ /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */
+ BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
+ };
+ int btf_fd;
+
+ btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types),
+ strs, sizeof(strs));
+ if (btf_fd >= 0) {
+ obj->caps.btf_func_global = 1;
+ close(btf_fd);
+ return 1;
+ }
+
+ return 0;
+}
+
static int bpf_object__probe_btf_datasec(struct bpf_object *obj)
{
static const char strs[] = "\0x\0.data";
bpf_object__probe_name,
bpf_object__probe_global_data,
bpf_object__probe_btf_func,
+ bpf_object__probe_btf_func_global,
bpf_object__probe_btf_datasec,
bpf_object__probe_array_mmap,
};
if (bpf_map_type__is_map_in_map(def->type) &&
map->inner_map_fd >= 0)
create_attr.inner_map_fd = map->inner_map_fd;
+ if (bpf_map__is_struct_ops(map))
+ create_attr.btf_vmlinux_value_type_id =
+ map->btf_vmlinux_value_type_id;
if (obj->btf && !bpf_map_find_btf_info(obj, map)) {
create_attr.btf_fd = btf__fd(obj->btf);
return 0;
}
-static struct btf *btf_load_raw(const char *path)
-{
- struct btf *btf;
- size_t read_cnt;
- struct stat st;
- void *data;
- FILE *f;
-
- if (stat(path, &st))
- return ERR_PTR(-errno);
-
- data = malloc(st.st_size);
- if (!data)
- return ERR_PTR(-ENOMEM);
-
- f = fopen(path, "rb");
- if (!f) {
- btf = ERR_PTR(-errno);
- goto cleanup;
- }
-
- read_cnt = fread(data, 1, st.st_size, f);
- fclose(f);
- if (read_cnt < st.st_size) {
- btf = ERR_PTR(-EBADF);
- goto cleanup;
- }
-
- btf = btf__new(data, read_cnt);
-
-cleanup:
- free(data);
- return btf;
-}
-
-/*
- * Probe few well-known locations for vmlinux kernel image and try to load BTF
- * data out of it to use for target BTF.
- */
-static struct btf *bpf_core_find_kernel_btf(void)
-{
- struct {
- const char *path_fmt;
- bool raw_btf;
- } locations[] = {
- /* try canonical vmlinux BTF through sysfs first */
- { "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
- /* fall back to trying to find vmlinux ELF on disk otherwise */
- { "/boot/vmlinux-%1$s" },
- { "/lib/modules/%1$s/vmlinux-%1$s" },
- { "/lib/modules/%1$s/build/vmlinux" },
- { "/usr/lib/modules/%1$s/kernel/vmlinux" },
- { "/usr/lib/debug/boot/vmlinux-%1$s" },
- { "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
- { "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
- };
- char path[PATH_MAX + 1];
- struct utsname buf;
- struct btf *btf;
- int i;
-
- uname(&buf);
-
- for (i = 0; i < ARRAY_SIZE(locations); i++) {
- snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);
-
- if (access(path, R_OK))
- continue;
-
- if (locations[i].raw_btf)
- btf = btf_load_raw(path);
- else
- btf = btf__parse_elf(path, NULL);
-
- pr_debug("loading kernel BTF '%s': %ld\n",
- path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
- if (IS_ERR(btf))
- continue;
-
- return btf;
- }
-
- pr_warn("failed to find valid kernel BTF\n");
- return ERR_PTR(-ESRCH);
-}
-
/* Output spec definition in the format:
* [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>,
* where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b
if (targ_btf_path)
targ_btf = btf__parse_elf(targ_btf_path, NULL);
else
- targ_btf = bpf_core_find_kernel_btf();
+ targ_btf = libbpf_find_kernel_btf();
if (IS_ERR(targ_btf)) {
pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf));
return PTR_ERR(targ_btf);
size_t new_cnt;
int err;
- if (prog->idx == obj->efile.text_shndx) {
- pr_warn("relo in .text insn %d into off %d (insn #%d)\n",
- relo->insn_idx, relo->sym_off, relo->sym_off / 8);
- return -LIBBPF_ERRNO__RELOC;
- }
-
- if (prog->main_prog_cnt == 0) {
+ if (prog->idx != obj->efile.text_shndx && prog->main_prog_cnt == 0) {
text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx);
if (!text) {
pr_warn("no .text section found yet relo into text exist\n");
text->insns_cnt, text->section_name,
prog->section_name);
}
+
insn = &prog->insns[relo->insn_idx];
insn->imm += relo->sym_off / 8 + prog->main_prog_cnt - relo->insn_idx;
return 0;
return err;
}
}
+ /* ensure .text is relocated first, as it's going to be copied as-is
+ * later for sub-program calls
+ */
+ for (i = 0; i < obj->nr_programs; i++) {
+ prog = &obj->programs[i];
+ if (prog->idx != obj->efile.text_shndx)
+ continue;
+
+ err = bpf_program__relocate(prog, obj);
+ if (err) {
+ pr_warn("failed to relocate '%s'\n", prog->section_name);
+ return err;
+ }
+ break;
+ }
+ /* now relocate everything but .text, which by now is relocated
+ * properly, so we can copy raw sub-program instructions as is safely
+ */
for (i = 0; i < obj->nr_programs; i++) {
prog = &obj->programs[i];
+ if (prog->idx == obj->efile.text_shndx)
+ continue;
err = bpf_program__relocate(prog, obj);
if (err) {
return 0;
}
+static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj,
+ GElf_Shdr *shdr,
+ Elf_Data *data);
+
static int bpf_object__collect_reloc(struct bpf_object *obj)
{
int i, err;
return -LIBBPF_ERRNO__INTERNAL;
}
+ if (idx == obj->efile.st_ops_shndx) {
+ err = bpf_object__collect_struct_ops_map_reloc(obj,
+ shdr,
+ data);
+ if (err)
+ return err;
+ continue;
+ }
+
prog = bpf_object__find_prog_by_idx(obj, idx);
if (!prog) {
pr_warn("relocation failed: no section(%d)\n", idx);
load_attr.insns = insns;
load_attr.insns_cnt = insns_cnt;
load_attr.license = license;
- if (prog->type == BPF_PROG_TYPE_TRACING) {
+ if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) {
+ load_attr.attach_btf_id = prog->attach_btf_id;
+ } else if (prog->type == BPF_PROG_TYPE_TRACING ||
+ prog->type == BPF_PROG_TYPE_EXT) {
load_attr.attach_prog_fd = prog->attach_prog_fd;
load_attr.attach_btf_id = prog->attach_btf_id;
} else {
return ret;
}
-static int libbpf_find_attach_btf_id(const char *name,
- enum bpf_attach_type attach_type,
- __u32 attach_prog_fd);
+static int libbpf_find_attach_btf_id(struct bpf_program *prog);
int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
{
int err = 0, fd, i, btf_id;
- if (prog->type == BPF_PROG_TYPE_TRACING) {
- btf_id = libbpf_find_attach_btf_id(prog->section_name,
- prog->expected_attach_type,
- prog->attach_prog_fd);
+ if (prog->type == BPF_PROG_TYPE_TRACING ||
+ prog->type == BPF_PROG_TYPE_EXT) {
+ btf_id = libbpf_find_attach_btf_id(prog);
if (btf_id <= 0)
return btf_id;
prog->attach_btf_id = btf_id;
enum bpf_prog_type prog_type;
enum bpf_attach_type attach_type;
+ if (prog->type != BPF_PROG_TYPE_UNSPEC)
+ continue;
+
err = libbpf_prog_type_by_name(prog->section_name, &prog_type,
&attach_type);
if (err == -ESRCH)
bpf_program__set_type(prog, prog_type);
bpf_program__set_expected_attach_type(prog, attach_type);
- if (prog_type == BPF_PROG_TYPE_TRACING)
+ if (prog_type == BPF_PROG_TYPE_TRACING ||
+ prog_type == BPF_PROG_TYPE_EXT)
prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
}
if (!obj)
return -EINVAL;
- for (i = 0; i < obj->nr_maps; i++)
+ for (i = 0; i < obj->nr_maps; i++) {
zclose(obj->maps[i].fd);
+ if (obj->maps[i].st_ops)
+ zfree(&obj->maps[i].st_ops->kern_vdata);
+ }
for (i = 0; i < obj->nr_programs; i++)
bpf_program__unload(&obj->programs[i]);
err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
err = err ? : bpf_object__sanitize_and_load_btf(obj);
err = err ? : bpf_object__sanitize_maps(obj);
+ err = err ? : bpf_object__load_vmlinux_btf(obj);
+ err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
err = err ? : bpf_object__create_maps(obj);
err = err ? : bpf_object__relocate(obj, attr->target_btf_path);
err = err ? : bpf_object__load_progs(obj, attr->log_level);
+
+ btf__free(obj->btf_vmlinux);
+ obj->btf_vmlinux = NULL;
+
if (err)
goto out;
map->mmaped = NULL;
}
+ if (map->st_ops) {
+ zfree(&map->st_ops->data);
+ zfree(&map->st_ops->progs);
+ zfree(&map->st_ops->kern_func_off);
+ zfree(&map->st_ops);
+ }
+
zfree(&map->name);
zfree(&map->pin_path);
}
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING);
+BPF_PROG_TYPE_FNS(struct_ops, BPF_PROG_TYPE_STRUCT_OPS);
+BPF_PROG_TYPE_FNS(extension, BPF_PROG_TYPE_EXT);
enum bpf_attach_type
bpf_program__get_expected_attach_type(struct bpf_program *prog)
.expected_attach_type = BPF_TRACE_FEXIT,
.is_attach_btf = true,
.attach_fn = attach_trace),
+ SEC_DEF("freplace/", EXT,
+ .is_attach_btf = true,
+ .attach_fn = attach_trace),
BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP),
BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT),
BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN),
BPF_CGROUP_GETSOCKOPT),
BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT,
BPF_CGROUP_SETSOCKOPT),
+ BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS),
};
#undef BPF_PROG_SEC_IMPL
return -ESRCH;
}
-#define BTF_PREFIX "btf_trace_"
+static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
+ size_t offset)
+{
+ struct bpf_map *map;
+ size_t i;
+
+ for (i = 0; i < obj->nr_maps; i++) {
+ map = &obj->maps[i];
+ if (!bpf_map__is_struct_ops(map))
+ continue;
+ if (map->sec_offset <= offset &&
+ offset - map->sec_offset < map->def.value_size)
+ return map;
+ }
+
+ return NULL;
+}
+
+/* Collect the reloc from ELF and populate the st_ops->progs[] */
+static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj,
+ GElf_Shdr *shdr,
+ Elf_Data *data)
+{
+ const struct btf_member *member;
+ struct bpf_struct_ops *st_ops;
+ struct bpf_program *prog;
+ unsigned int shdr_idx;
+ const struct btf *btf;
+ struct bpf_map *map;
+ Elf_Data *symbols;
+ unsigned int moff;
+ const char *name;
+ __u32 member_idx;
+ GElf_Sym sym;
+ GElf_Rel rel;
+ int i, nrels;
+
+ symbols = obj->efile.symbols;
+ btf = obj->btf;
+ nrels = shdr->sh_size / shdr->sh_entsize;
+ for (i = 0; i < nrels; i++) {
+ if (!gelf_getrel(data, i, &rel)) {
+ pr_warn("struct_ops reloc: failed to get %d reloc\n", i);
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+ pr_warn("struct_ops reloc: symbol %zx not found\n",
+ (size_t)GELF_R_SYM(rel.r_info));
+ return -LIBBPF_ERRNO__FORMAT;
+ }
+
+ name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+ sym.st_name) ? : "<?>";
+ map = find_struct_ops_map_by_offset(obj, rel.r_offset);
+ if (!map) {
+ pr_warn("struct_ops reloc: cannot find map at rel.r_offset %zu\n",
+ (size_t)rel.r_offset);
+ return -EINVAL;
+ }
+
+ moff = rel.r_offset - map->sec_offset;
+ shdr_idx = sym.st_shndx;
+ st_ops = map->st_ops;
+ pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel.r_offset %zu map->sec_offset %zu name %d (\'%s\')\n",
+ map->name,
+ (long long)(rel.r_info >> 32),
+ (long long)sym.st_value,
+ shdr_idx, (size_t)rel.r_offset,
+ map->sec_offset, sym.st_name, name);
+
+ if (shdr_idx >= SHN_LORESERVE) {
+ pr_warn("struct_ops reloc %s: rel.r_offset %zu shdr_idx %u unsupported non-static function\n",
+ map->name, (size_t)rel.r_offset, shdr_idx);
+ return -LIBBPF_ERRNO__RELOC;
+ }
+
+ member = find_member_by_offset(st_ops->type, moff * 8);
+ if (!member) {
+ pr_warn("struct_ops reloc %s: cannot find member at moff %u\n",
+ map->name, moff);
+ return -EINVAL;
+ }
+ member_idx = member - btf_members(st_ops->type);
+ name = btf__name_by_offset(btf, member->name_off);
+
+ if (!resolve_func_ptr(btf, member->type, NULL)) {
+ pr_warn("struct_ops reloc %s: cannot relocate non func ptr %s\n",
+ map->name, name);
+ return -EINVAL;
+ }
+
+ prog = bpf_object__find_prog_by_idx(obj, shdr_idx);
+ if (!prog) {
+ pr_warn("struct_ops reloc %s: cannot find prog at shdr_idx %u to relocate func ptr %s\n",
+ map->name, shdr_idx, name);
+ return -EINVAL;
+ }
+
+ if (prog->type == BPF_PROG_TYPE_UNSPEC) {
+ const struct bpf_sec_def *sec_def;
+
+ sec_def = find_sec_def(prog->section_name);
+ if (sec_def &&
+ sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) {
+ /* for pr_warn */
+ prog->type = sec_def->prog_type;
+ goto invalid_prog;
+ }
+
+ prog->type = BPF_PROG_TYPE_STRUCT_OPS;
+ prog->attach_btf_id = st_ops->type_id;
+ prog->expected_attach_type = member_idx;
+ } else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
+ prog->attach_btf_id != st_ops->type_id ||
+ prog->expected_attach_type != member_idx) {
+ goto invalid_prog;
+ }
+ st_ops->progs[member_idx] = prog;
+ }
+
+ return 0;
+
+invalid_prog:
+ pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n",
+ map->name, prog->name, prog->section_name, prog->type,
+ prog->attach_btf_id, prog->expected_attach_type, name);
+ return -EINVAL;
+}
+
+#define BTF_TRACE_PREFIX "btf_trace_"
+#define BTF_MAX_NAME_SIZE 128
+
+static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix,
+ const char *name, __u32 kind)
+{
+ char btf_type_name[BTF_MAX_NAME_SIZE];
+ int ret;
+
+ ret = snprintf(btf_type_name, sizeof(btf_type_name),
+ "%s%s", prefix, name);
+ /* snprintf returns the number of characters written excluding the
+ * the terminating null. So, if >= BTF_MAX_NAME_SIZE are written, it
+ * indicates truncation.
+ */
+ if (ret < 0 || ret >= sizeof(btf_type_name))
+ return -ENAMETOOLONG;
+ return btf__find_by_name_kind(btf, btf_type_name, kind);
+}
+
+static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name,
+ enum bpf_attach_type attach_type)
+{
+ int err;
+
+ if (attach_type == BPF_TRACE_RAW_TP)
+ err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name,
+ BTF_KIND_TYPEDEF);
+ else
+ err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
+
+ return err;
+}
+
int libbpf_find_vmlinux_btf_id(const char *name,
enum bpf_attach_type attach_type)
{
- struct btf *btf = bpf_core_find_kernel_btf();
- char raw_tp_btf[128] = BTF_PREFIX;
- char *dst = raw_tp_btf + sizeof(BTF_PREFIX) - 1;
- const char *btf_name;
- int err = -EINVAL;
- __u32 kind;
+ struct btf *btf;
+ btf = libbpf_find_kernel_btf();
if (IS_ERR(btf)) {
pr_warn("vmlinux BTF is not found\n");
return -EINVAL;
}
- if (attach_type == BPF_TRACE_RAW_TP) {
- /* prepend "btf_trace_" prefix per kernel convention */
- strncat(dst, name, sizeof(raw_tp_btf) - sizeof(BTF_PREFIX));
- btf_name = raw_tp_btf;
- kind = BTF_KIND_TYPEDEF;
- } else {
- btf_name = name;
- kind = BTF_KIND_FUNC;
- }
- err = btf__find_by_name_kind(btf, btf_name, kind);
- btf__free(btf);
- return err;
+ return __find_vmlinux_btf_id(btf, name, attach_type);
}
static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
return err;
}
-static int libbpf_find_attach_btf_id(const char *name,
- enum bpf_attach_type attach_type,
- __u32 attach_prog_fd)
+static int libbpf_find_attach_btf_id(struct bpf_program *prog)
{
+ enum bpf_attach_type attach_type = prog->expected_attach_type;
+ __u32 attach_prog_fd = prog->attach_prog_fd;
+ const char *name = prog->section_name;
int i, err;
if (!name)
err = libbpf_find_prog_btf_id(name + section_defs[i].len,
attach_prog_fd);
else
- err = libbpf_find_vmlinux_btf_id(name + section_defs[i].len,
- attach_type);
+ err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux,
+ name + section_defs[i].len,
+ attach_type);
if (err <= 0)
pr_warn("%s is not found in vmlinux BTF\n", name);
return err;
return sec_def->attach_fn(sec_def, prog);
}
+static int bpf_link__detach_struct_ops(struct bpf_link *link)
+{
+ struct bpf_link_fd *l = (void *)link;
+ __u32 zero = 0;
+
+ if (bpf_map_delete_elem(l->fd, &zero))
+ return -errno;
+
+ return 0;
+}
+
+struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
+{
+ struct bpf_struct_ops *st_ops;
+ struct bpf_link_fd *link;
+ __u32 i, zero = 0;
+ int err;
+
+ if (!bpf_map__is_struct_ops(map) || map->fd == -1)
+ return ERR_PTR(-EINVAL);
+
+ link = calloc(1, sizeof(*link));
+ if (!link)
+ return ERR_PTR(-EINVAL);
+
+ st_ops = map->st_ops;
+ for (i = 0; i < btf_vlen(st_ops->type); i++) {
+ struct bpf_program *prog = st_ops->progs[i];
+ void *kern_data;
+ int prog_fd;
+
+ if (!prog)
+ continue;
+
+ prog_fd = bpf_program__fd(prog);
+ kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i];
+ *(unsigned long *)kern_data = prog_fd;
+ }
+
+ err = bpf_map_update_elem(map->fd, &zero, st_ops->kern_vdata, 0);
+ if (err) {
+ err = -errno;
+ free(link);
+ return ERR_PTR(err);
+ }
+
+ link->link.detach = bpf_link__detach_struct_ops;
+ link->fd = map->fd;
+
+ return (struct bpf_link *)link;
+}
+
enum bpf_perf_event_ret
bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
void **copy_mem, size_t *copy_size,
LIBBPF_API struct bpf_link *
bpf_program__attach_trace(struct bpf_program *prog);
+struct bpf_map;
+LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
struct bpf_insn;
/*
LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog);
LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog);
+LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog);
LIBBPF_API enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog);
LIBBPF_API void bpf_program__set_type(struct bpf_program *prog,
LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog);
LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog);
+LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog);
/*
* No need for __attribute__((packed)), all members of 'bpf_map_def'
* The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel,
* so no need to worry about a name clash.
*/
-struct bpf_map;
LIBBPF_API struct bpf_map *
bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name);
LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex);
LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id,
enum bpf_prog_type prog_type, __u32 ifindex);
+LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex);
/*
* Get bpf_prog_info in continuous memory
global:
btf_dump__emit_type_decl;
bpf_link__disconnect;
+ bpf_map__attach_struct_ops;
+ bpf_map_delete_batch;
+ bpf_map_lookup_and_delete_batch;
+ bpf_map_lookup_batch;
+ bpf_map_update_batch;
bpf_object__find_program_by_name;
bpf_object__attach_skeleton;
bpf_object__destroy_skeleton;
bpf_object__detach_skeleton;
bpf_object__load_skeleton;
bpf_object__open_skeleton;
+ bpf_probe_large_insn_limit;
bpf_prog_attach_xattr;
bpf_program__attach;
bpf_program__name;
+ bpf_program__is_extension;
+ bpf_program__is_struct_ops;
+ bpf_program__set_extension;
+ bpf_program__set_struct_ops;
btf__align_of;
+ libbpf_find_kernel_btf;
} LIBBPF_0.0.6;
#include "libbpf.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START)
#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c)
#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
#include "libbpf.h"
#include "libbpf_internal.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
static bool grep(const char *buffer, const char *pattern)
{
return !!strstr(buffer, pattern);
case BPF_PROG_TYPE_CGROUP_SYSCTL:
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
case BPF_PROG_TYPE_TRACING:
+ case BPF_PROG_TYPE_STRUCT_OPS:
+ case BPF_PROG_TYPE_EXT:
default:
break;
}
case BPF_MAP_TYPE_XSKMAP:
case BPF_MAP_TYPE_SOCKHASH:
case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+ case BPF_MAP_TYPE_STRUCT_OPS:
default:
break;
}
return res;
}
+
+/*
+ * Probe for availability of kernel commit (5.3):
+ *
+ * c04c0d2b968a ("bpf: increase complexity limit and maximum program size")
+ */
+bool bpf_probe_large_insn_limit(__u32 ifindex)
+{
+ struct bpf_insn insns[BPF_MAXINSNS + 1];
+ int i;
+
+ for (i = 0; i < BPF_MAXINSNS; i++)
+ insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1);
+ insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
+
+ errno = 0;
+ probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
+ ifindex);
+
+ return errno != E2BIG && errno != EINVAL;
+}
#include "libbpf_internal.h"
#include "nlattr.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
#ifndef SOL_NETLINK
#define SOL_NETLINK 270
#endif
#include <string.h>
#include <stdio.h>
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = {
[LIBBPF_NLA_U8] = sizeof(uint8_t),
[LIBBPF_NLA_U16] = sizeof(uint16_t),
#include <stdio.h>
#include "str_error.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
/*
* Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl
* libc, while checking strerror_r() return to avoid having to check this in
#include "libbpf_internal.h"
#include "xsk.h"
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
#ifndef SOL_XDP
#define SOL_XDP 283
#endif
Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
*/
-#include <bpf.h>
+#include <bpf/bpf.h>
int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
{
-#include <bpf.h>
+#include <bpf/bpf.h>
license(GPL);
* the return value.
*/
-#include <bpf.h>
+#include <bpf/bpf.h>
struct syscall_enter_openat_args {
unsigned long long unused;
#ifndef _PERF_BPF_PID_FILTER_
#define _PERF_BPF_PID_FILTER_
-#include <bpf.h>
+#include <bpf/bpf.h>
#define pid_filter(name) pid_map(name, bool)
// SPDX-License-Identifier: GPL-2.0
-#include <bpf.h>
+#include <bpf/bpf.h>
struct bpf_map SEC("maps") __bpf_stdout__ = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
// SPDX-License-Identifier: LGPL-2.1
-#include <bpf.h>
+#include <bpf/bpf.h>
static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid;
test_skb_cgroup_id_user
test_socket_cookie
test_cgroup_storage
-test_select_reuseport
test_flow_dissector
flow_dissector_load
test_netcnt
-test_section_names
test_tcpnotify_user
test_libbpf
test_tcp_check_syncookie_user
test_sysctl
-libbpf.pc
-libbpf.so.*
test_hashmap
test_btf_dump
xdping
/no_alu32
/bpf_gcc
/tools
-bpf_helper_defs.h
+
LLC ?= llc
LLVM_OBJCOPY ?= llvm-objcopy
BPF_GCC ?= $(shell command -v bpf-gcc;)
-CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) \
- -I$(GENDIR) -I$(TOOLSINCDIR) -I$(CURDIR) \
+CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(CURDIR) -I$(APIDIR) \
+ -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR) \
-Dbpf_prog_load=bpf_prog_test_load \
-Dbpf_load_program=bpf_test_load_program
LDLIBS += -lcap -lelf -lz -lrt -lpthread
# Compile but not part of 'make run_tests'
TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
- test_lirc_mode2_user xdping test_cpp
+ test_lirc_mode2_user xdping test_cpp runqslower
TEST_CUSTOM_PROGS = urandom_read
# $3 - target (assumed to be file); only file name will be emitted;
# $4 - optional extra arg, emitted as-is, if provided.
ifeq ($(V),1)
+Q =
msg =
else
-msg = @$(info $(1)$(if $(2), [$(2)]) $(notdir $(3)))$(if $(4), $(4))
+Q = @
+msg = @printf ' %-8s%s %s%s\n' "$(1)" "$(if $(2), [$(2)])" "$(notdir $(3))" "$(if $(4), $(4))";
+MAKEFLAGS += --no-print-directory
+submake_extras := feature_display=0
endif
# override lib.mk's default rules
OVERRIDE_TARGETS := 1
override define CLEAN
- $(call msg, CLEAN)
+ $(call msg,CLEAN)
$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
endef
include ../lib.mk
+SCRATCH_DIR := $(OUTPUT)/tools
+BUILD_DIR := $(SCRATCH_DIR)/build
+INCLUDE_DIR := $(SCRATCH_DIR)/include
+BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a
+
# Define simple and short `make test_progs`, `make test_sysctl`, etc targets
# to build individual tests.
# NOTE: Semicolon at the end is critical to override lib.mk's default static
$(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ;
$(OUTPUT)/%:%.c
- $(call msg, BINARY,,$@)
+ $(call msg,BINARY,,$@)
$(LINK.c) $^ $(LDLIBS) -o $@
$(OUTPUT)/urandom_read: urandom_read.c
- $(call msg, BINARY,,$@)
- $(CC) -o $@ $< -Wl,--build-id
+ $(call msg,BINARY,,$@)
+ $(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id
-$(OUTPUT)/test_stub.o: test_stub.c
- $(call msg, CC,,$@)
+$(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ)
+ $(call msg,CC,,$@)
$(CC) -c $(CFLAGS) -o $@ $<
-BPFOBJ := $(OUTPUT)/libbpf.a
+VMLINUX_BTF_PATHS := $(abspath ../../../../vmlinux) \
+ /sys/kernel/btf/vmlinux \
+ /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF:= $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))
+$(OUTPUT)/runqslower: $(BPFOBJ)
+ $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \
+ OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF) \
+ BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR)
$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ)
$(OUTPUT)/test_sock_fields: cgroup_helpers.c
$(OUTPUT)/test_sysctl: cgroup_helpers.c
-.PHONY: force
-
-# force a rebuild of BPFOBJ when its dependencies are updated
-force:
-
-DEFAULT_BPFTOOL := $(OUTPUT)/tools/usr/local/sbin/bpftool
+DEFAULT_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool
BPFTOOL ?= $(DEFAULT_BPFTOOL)
+$(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BUILD_DIR)/bpftool
+ $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \
+ OUTPUT=$(BUILD_DIR)/bpftool/ \
+ prefix= DESTDIR=$(SCRATCH_DIR)/ install
-$(DEFAULT_BPFTOOL): force
- $(MAKE) -C $(BPFTOOLDIR) DESTDIR=$(OUTPUT)/tools install
-
-$(BPFOBJ): force
- $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
+$(BPFOBJ): $(wildcard $(BPFDIR)/*.c $(BPFDIR)/*.h $(BPFDIR)/Makefile) \
+ ../../../include/uapi/linux/bpf.h \
+ | $(INCLUDE_DIR) $(BUILD_DIR)/libbpf
+ $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
+ DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
-BPF_HELPERS := $(OUTPUT)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h)
-$(OUTPUT)/bpf_helper_defs.h:
- $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ $(OUTPUT)/bpf_helper_defs.h
+$(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR):
+ $(call msg,MKDIR,,$@)
+ mkdir -p $@
# Get Clang's default includes on this system, as opposed to those seen by
# '-target bpf'. This fixes "missing" files on some architectures/distros,
CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \
- -I. -I./include/uapi -I$(APIDIR) \
- -I$(BPFDIR) -I$(abspath $(OUTPUT)/../usr/include)
+ -I$(INCLUDE_DIR) -I$(CURDIR) -I$(CURDIR)/include/uapi \
+ -I$(APIDIR) -I$(abspath $(OUTPUT)/../usr/include)
CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
-Wno-compare-distinct-pointer-types
# $3 - CFLAGS
# $4 - LDFLAGS
define CLANG_BPF_BUILD_RULE
- $(call msg, CLANG-LLC,$(TRUNNER_BINARY),$2)
+ $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
($(CLANG) $3 -O2 -target bpf -emit-llvm \
-c $1 -o - || echo "BPF obj compilation failed") | \
$(LLC) -mattr=dwarfris -march=bpf -mcpu=probe $4 -filetype=obj -o $2
endef
# Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
define CLANG_NOALU32_BPF_BUILD_RULE
- $(call msg, CLANG-LLC,$(TRUNNER_BINARY),$2)
+ $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
($(CLANG) $3 -O2 -target bpf -emit-llvm \
-c $1 -o - || echo "BPF obj compilation failed") | \
$(LLC) -march=bpf -mcpu=v2 $4 -filetype=obj -o $2
endef
# Similar to CLANG_BPF_BUILD_RULE, but using native Clang and bpf LLC
define CLANG_NATIVE_BPF_BUILD_RULE
- $(call msg, CLANG-BPF,$(TRUNNER_BINARY),$2)
+ $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
($(CLANG) $3 -O2 -emit-llvm \
-c $1 -o - || echo "BPF obj compilation failed") | \
$(LLC) -march=bpf -mcpu=probe $4 -filetype=obj -o $2
endef
# Build BPF object using GCC
define GCC_BPF_BUILD_RULE
- $(call msg, GCC-BPF,$(TRUNNER_BINARY),$2)
+ $(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
$(BPF_GCC) $3 $4 -O2 -c $1 -o $2
endef
ifeq ($($(TRUNNER_OUTPUT)-dir),)
$(TRUNNER_OUTPUT)-dir := y
$(TRUNNER_OUTPUT):
+ $$(call msg,MKDIR,,$$@)
mkdir -p $$@
endif
$(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \
$(TRUNNER_BPF_PROGS_DIR)/%.c \
$(TRUNNER_BPF_PROGS_DIR)/*.h \
- $$(BPF_HELPERS) | $(TRUNNER_OUTPUT)
+ $$(BPFOBJ) | $(TRUNNER_OUTPUT)
$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \
$(TRUNNER_BPF_CFLAGS), \
$(TRUNNER_BPF_LDFLAGS))
$(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h: \
$(TRUNNER_OUTPUT)/%.o \
| $(BPFTOOL) $(TRUNNER_OUTPUT)
- $$(call msg, GEN-SKEL,$(TRUNNER_BINARY),$$@)
+ $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
$$(BPFTOOL) gen skeleton $$< > $$@
endif
ifeq ($($(TRUNNER_TESTS_DIR)-tests-hdr),)
$(TRUNNER_TESTS_DIR)-tests-hdr := y
$(TRUNNER_TESTS_HDR): $(TRUNNER_TESTS_DIR)/*.c
- $$(call msg, TEST-HDR,$(TRUNNER_BINARY),$$@)
+ $$(call msg,TEST-HDR,$(TRUNNER_BINARY),$$@)
$$(shell ( cd $(TRUNNER_TESTS_DIR); \
echo '/* Generated header, do not edit */'; \
ls *.c 2> /dev/null | \
$(TRUNNER_BPF_OBJS) \
$(TRUNNER_BPF_SKELS) \
$$(BPFOBJ) | $(TRUNNER_OUTPUT)
- $$(call msg, TEST-OBJ,$(TRUNNER_BINARY),$$@)
+ $$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
cd $$(@D) && $$(CC) $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
$(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \
$(TRUNNER_EXTRA_HDRS) \
$(TRUNNER_TESTS_HDR) \
$$(BPFOBJ) | $(TRUNNER_OUTPUT)
- $$(call msg, EXTRA-OBJ,$(TRUNNER_BINARY),$$@)
+ $$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@)
$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@
# only copy extra resources if in flavored build
$(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT)
ifneq ($2,)
- $$(call msg, EXTRAS-CP,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES))
+ $$(call msg,EXT-COPY,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES))
cp -a $$^ $(TRUNNER_OUTPUT)/
endif
$(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \
$(TRUNNER_EXTRA_OBJS) $$(BPFOBJ) \
| $(TRUNNER_BINARY)-extras
- $$(call msg, BINARY,,$$@)
+ $$(call msg,BINARY,,$$@)
$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@
endef
TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \
$(wildcard progs/btf_dump_test_case_*.c)
TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
-TRUNNER_BPF_CFLAGS := -I. -I$(OUTPUT) $(BPF_CFLAGS) $(CLANG_CFLAGS)
+TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
TRUNNER_BPF_LDFLAGS := -mattr=+alu32
$(eval $(call DEFINE_TEST_RUNNER,test_progs))
echo '#endif' \
) > verifier/tests.h)
$(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT)
- $(call msg, BINARY,,$@)
+ $(call msg,BINARY,,$@)
$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
# Make sure we are able to include and link libbpf against c++.
$(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
- $(call msg, CXX,,$@)
+ $(call msg,CXX,,$@)
$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@
-EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) \
+EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) \
prog_tests/tests.h map_tests/tests.h verifier/tests.h \
- feature $(OUTPUT)/*.o $(OUTPUT)/no_alu32 $(OUTPUT)/bpf_gcc \
- tools *.skel.h
+ feature \
+ $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc)
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_TCP_HELPERS_H
+#define __BPF_TCP_HELPERS_H
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_trace_helpers.h"
+
+#define BPF_STRUCT_OPS(name, args...) \
+SEC("struct_ops/"#name) \
+BPF_PROG(name, args)
+
+#define tcp_jiffies32 ((__u32)bpf_jiffies64())
+
+struct sock_common {
+ unsigned char skc_state;
+} __attribute__((preserve_access_index));
+
+enum sk_pacing {
+ SK_PACING_NONE = 0,
+ SK_PACING_NEEDED = 1,
+ SK_PACING_FQ = 2,
+};
+
+struct sock {
+ struct sock_common __sk_common;
+ unsigned long sk_pacing_rate;
+ __u32 sk_pacing_status; /* see enum sk_pacing */
+} __attribute__((preserve_access_index));
+
+struct inet_sock {
+ struct sock sk;
+} __attribute__((preserve_access_index));
+
+struct inet_connection_sock {
+ struct inet_sock icsk_inet;
+ __u8 icsk_ca_state:6,
+ icsk_ca_setsockopt:1,
+ icsk_ca_dst_locked:1;
+ struct {
+ __u8 pending;
+ } icsk_ack;
+ __u64 icsk_ca_priv[104 / sizeof(__u64)];
+} __attribute__((preserve_access_index));
+
+struct tcp_sock {
+ struct inet_connection_sock inet_conn;
+
+ __u32 rcv_nxt;
+ __u32 snd_nxt;
+ __u32 snd_una;
+ __u8 ecn_flags;
+ __u32 delivered;
+ __u32 delivered_ce;
+ __u32 snd_cwnd;
+ __u32 snd_cwnd_cnt;
+ __u32 snd_cwnd_clamp;
+ __u32 snd_ssthresh;
+ __u8 syn_data:1, /* SYN includes data */
+ syn_fastopen:1, /* SYN includes Fast Open option */
+ syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
+ syn_fastopen_ch:1, /* Active TFO re-enabling probe */
+ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
+ save_syn:1, /* Save headers of SYN packet */
+ is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
+ syn_smc:1; /* SYN includes SMC */
+ __u32 max_packets_out;
+ __u32 lsndtime;
+ __u32 prior_cwnd;
+ __u64 tcp_mstamp; /* most recent packet received/sent */
+} __attribute__((preserve_access_index));
+
+static __always_inline struct inet_connection_sock *inet_csk(const struct sock *sk)
+{
+ return (struct inet_connection_sock *)sk;
+}
+
+static __always_inline void *inet_csk_ca(const struct sock *sk)
+{
+ return (void *)inet_csk(sk)->icsk_ca_priv;
+}
+
+static __always_inline struct tcp_sock *tcp_sk(const struct sock *sk)
+{
+ return (struct tcp_sock *)sk;
+}
+
+static __always_inline bool before(__u32 seq1, __u32 seq2)
+{
+ return (__s32)(seq1-seq2) < 0;
+}
+#define after(seq2, seq1) before(seq1, seq2)
+
+#define TCP_ECN_OK 1
+#define TCP_ECN_QUEUE_CWR 2
+#define TCP_ECN_DEMAND_CWR 4
+#define TCP_ECN_SEEN 8
+
+enum inet_csk_ack_state_t {
+ ICSK_ACK_SCHED = 1,
+ ICSK_ACK_TIMER = 2,
+ ICSK_ACK_PUSHED = 4,
+ ICSK_ACK_PUSHED2 = 8,
+ ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */
+};
+
+enum tcp_ca_event {
+ CA_EVENT_TX_START = 0,
+ CA_EVENT_CWND_RESTART = 1,
+ CA_EVENT_COMPLETE_CWR = 2,
+ CA_EVENT_LOSS = 3,
+ CA_EVENT_ECN_NO_CE = 4,
+ CA_EVENT_ECN_IS_CE = 5,
+};
+
+enum tcp_ca_state {
+ TCP_CA_Open = 0,
+ TCP_CA_Disorder = 1,
+ TCP_CA_CWR = 2,
+ TCP_CA_Recovery = 3,
+ TCP_CA_Loss = 4
+};
+
+struct ack_sample {
+ __u32 pkts_acked;
+ __s32 rtt_us;
+ __u32 in_flight;
+} __attribute__((preserve_access_index));
+
+struct rate_sample {
+ __u64 prior_mstamp; /* starting timestamp for interval */
+ __u32 prior_delivered; /* tp->delivered at "prior_mstamp" */
+ __s32 delivered; /* number of packets delivered over interval */
+ long interval_us; /* time for tp->delivered to incr "delivered" */
+ __u32 snd_interval_us; /* snd interval for delivered packets */
+ __u32 rcv_interval_us; /* rcv interval for delivered packets */
+ long rtt_us; /* RTT of last (S)ACKed packet (or -1) */
+ int losses; /* number of packets marked lost upon ACK */
+ __u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */
+ __u32 prior_in_flight; /* in flight before this ACK */
+ bool is_app_limited; /* is sample from packet with bubble in pipe? */
+ bool is_retrans; /* is sample from retransmission? */
+ bool is_ack_delayed; /* is this (likely) a delayed ACK? */
+} __attribute__((preserve_access_index));
+
+#define TCP_CA_NAME_MAX 16
+#define TCP_CONG_NEEDS_ECN 0x2
+
+struct tcp_congestion_ops {
+ char name[TCP_CA_NAME_MAX];
+ __u32 flags;
+
+ /* initialize private data (optional) */
+ void (*init)(struct sock *sk);
+ /* cleanup private data (optional) */
+ void (*release)(struct sock *sk);
+
+ /* return slow start threshold (required) */
+ __u32 (*ssthresh)(struct sock *sk);
+ /* do new cwnd calculation (required) */
+ void (*cong_avoid)(struct sock *sk, __u32 ack, __u32 acked);
+ /* call before changing ca_state (optional) */
+ void (*set_state)(struct sock *sk, __u8 new_state);
+ /* call when cwnd event occurs (optional) */
+ void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
+ /* call when ack arrives (optional) */
+ void (*in_ack_event)(struct sock *sk, __u32 flags);
+ /* new value of cwnd after loss (required) */
+ __u32 (*undo_cwnd)(struct sock *sk);
+ /* hook for packet ack accounting (optional) */
+ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
+ /* override sysctl_tcp_min_tso_segs */
+ __u32 (*min_tso_segs)(struct sock *sk);
+ /* returns the multiplier used in tcp_sndbuf_expand (optional) */
+ __u32 (*sndbuf_expand)(struct sock *sk);
+ /* call when packets are delivered to update cwnd and pacing rate,
+ * after all the ca_state processing. (optional)
+ */
+ void (*cong_control)(struct sock *sk, const struct rate_sample *rs);
+};
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+#define max(a, b) ((a) > (b) ? (a) : (b))
+#define min_not_zero(x, y) ({ \
+ typeof(x) __x = (x); \
+ typeof(y) __y = (y); \
+ __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
+
+static __always_inline __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked)
+{
+ __u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh);
+
+ acked -= cwnd - tp->snd_cwnd;
+ tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
+
+ return acked;
+}
+
+static __always_inline bool tcp_in_slow_start(const struct tcp_sock *tp)
+{
+ return tp->snd_cwnd < tp->snd_ssthresh;
+}
+
+static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+
+ /* If in slow start, ensure cwnd grows to twice what was ACKed. */
+ if (tcp_in_slow_start(tp))
+ return tp->snd_cwnd < 2 * tp->max_packets_out;
+
+ return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited);
+}
+
+static __always_inline void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked)
+{
+ /* If credits accumulated at a higher w, apply them gently now. */
+ if (tp->snd_cwnd_cnt >= w) {
+ tp->snd_cwnd_cnt = 0;
+ tp->snd_cwnd++;
+ }
+
+ tp->snd_cwnd_cnt += acked;
+ if (tp->snd_cwnd_cnt >= w) {
+ __u32 delta = tp->snd_cwnd_cnt / w;
+
+ tp->snd_cwnd_cnt -= delta * w;
+ tp->snd_cwnd += delta;
+ }
+ tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
+}
+
+#endif
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
#ifndef __BPF_TRACE_HELPERS_H
#define __BPF_TRACE_HELPERS_H
-#include "bpf_helpers.h"
-
-#define __BPF_MAP_0(i, m, v, ...) v
-#define __BPF_MAP_1(i, m, v, t, a, ...) m(t, a, ctx[i])
-#define __BPF_MAP_2(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_1(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_3(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_2(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_4(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_3(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_5(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_4(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_6(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_5(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_7(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_6(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_8(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_7(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_9(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_8(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_10(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_9(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_11(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_10(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP_12(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_11(i+1, m, v, __VA_ARGS__)
-#define __BPF_MAP(n, ...) __BPF_MAP_##n(0, __VA_ARGS__)
-
-/* BPF sizeof(void *) is always 8, so no need to cast to long first
- * for ptr to avoid compiler warning.
+#include <bpf/bpf_helpers.h>
+
+#define ___bpf_concat(a, b) a ## b
+#define ___bpf_apply(fn, n) ___bpf_concat(fn, n)
+#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N
+#define ___bpf_narg(...) \
+ ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#define ___bpf_empty(...) \
+ ___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0)
+
+#define ___bpf_ctx_cast0() ctx
+#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0]
+#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1]
+#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2]
+#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3]
+#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4]
+#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5]
+#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6]
+#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7]
+#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8]
+#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9]
+#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10]
+#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11]
+#define ___bpf_ctx_cast(args...) \
+ ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args)
+
+/*
+ * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and
+ * similar kinds of BPF programs, that accept input arguments as a single
+ * pointer to untyped u64 array, where each u64 can actually be a typed
+ * pointer or integer of different size. Instead of requring user to write
+ * manual casts and work with array elements by index, BPF_PROG macro
+ * allows user to declare a list of named and typed input arguments in the
+ * same syntax as for normal C function. All the casting is hidden and
+ * performed transparently, while user code can just assume working with
+ * function arguments of specified type and name.
+ *
+ * Original raw context argument is preserved as well as 'ctx' argument.
+ * This is useful when using BPF helpers that expect original context
+ * as one of the parameters (e.g., for bpf_perf_event_output()).
*/
-#define __BPF_CAST(t, a, ctx) (t) ctx
-#define __BPF_V void
-#define __BPF_N
-
-#define __BPF_DECL_ARGS(t, a, ctx) t a
-
-#define BPF_TRACE_x(x, sec_name, fname, ret_type, ...) \
-static __always_inline ret_type \
-____##fname(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \
- \
-SEC(sec_name) \
-ret_type fname(__u64 *ctx) \
-{ \
- return ____##fname(__BPF_MAP(x, __BPF_CAST, __BPF_N, __VA_ARGS__));\
-} \
- \
-static __always_inline \
-ret_type ____##fname(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__))
-
-#define BPF_TRACE_0(sec, fname, ...) BPF_TRACE_x(0, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_1(sec, fname, ...) BPF_TRACE_x(1, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_2(sec, fname, ...) BPF_TRACE_x(2, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_3(sec, fname, ...) BPF_TRACE_x(3, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_4(sec, fname, ...) BPF_TRACE_x(4, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_5(sec, fname, ...) BPF_TRACE_x(5, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_6(sec, fname, ...) BPF_TRACE_x(6, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_7(sec, fname, ...) BPF_TRACE_x(7, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_8(sec, fname, ...) BPF_TRACE_x(8, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_9(sec, fname, ...) BPF_TRACE_x(9, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_10(sec, fname, ...) BPF_TRACE_x(10, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_11(sec, fname, ...) BPF_TRACE_x(11, sec, fname, int, __VA_ARGS__)
-#define BPF_TRACE_12(sec, fname, ...) BPF_TRACE_x(12, sec, fname, int, __VA_ARGS__)
+#define BPF_PROG(name, args...) \
+name(unsigned long long *ctx); \
+static __always_inline typeof(name(0)) \
+____##name(unsigned long long *ctx, ##args); \
+typeof(name(0)) name(unsigned long long *ctx) \
+{ \
+ _Pragma("GCC diagnostic push") \
+ _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
+ return ____##name(___bpf_ctx_cast(args)); \
+ _Pragma("GCC diagnostic pop") \
+} \
+static __always_inline typeof(name(0)) \
+____##name(unsigned long long *ctx, ##args)
+
+struct pt_regs;
+
+#define ___bpf_kprobe_args0() ctx
+#define ___bpf_kprobe_args1(x) \
+ ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx)
+#define ___bpf_kprobe_args2(x, args...) \
+ ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx)
+#define ___bpf_kprobe_args3(x, args...) \
+ ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx)
+#define ___bpf_kprobe_args4(x, args...) \
+ ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx)
+#define ___bpf_kprobe_args5(x, args...) \
+ ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx)
+#define ___bpf_kprobe_args(args...) \
+ ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args)
+/*
+ * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for
+ * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific
+ * low-level way of getting kprobe input arguments from struct pt_regs, and
+ * provides a familiar typed and named function arguments syntax and
+ * semantics of accessing kprobe input paremeters.
+ *
+ * Original struct pt_regs* context is preserved as 'ctx' argument. This might
+ * be necessary when using BPF helpers like bpf_perf_event_output().
+ */
+#define BPF_KPROBE(name, args...) \
+name(struct pt_regs *ctx); \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\
+typeof(name(0)) name(struct pt_regs *ctx) \
+{ \
+ _Pragma("GCC diagnostic push") \
+ _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
+ return ____##name(___bpf_kprobe_args(args)); \
+ _Pragma("GCC diagnostic pop") \
+} \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
+
+#define ___bpf_kretprobe_args0() ctx
+#define ___bpf_kretprobe_argsN(x, args...) \
+ ___bpf_kprobe_args(args), (void *)PT_REGS_RET(ctx)
+#define ___bpf_kretprobe_args(args...) \
+ ___bpf_apply(___bpf_kretprobe_args, ___bpf_empty(args))(args)
+
+/*
+ * BPF_KRETPROBE is similar to BPF_KPROBE, except, in addition to listing all
+ * input kprobe arguments, one last extra argument has to be specified, which
+ * captures kprobe return value.
+ */
+#define BPF_KRETPROBE(name, args...) \
+name(struct pt_regs *ctx); \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\
+typeof(name(0)) name(struct pt_regs *ctx) \
+{ \
+ _Pragma("GCC diagnostic push") \
+ _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
+ return ____##name(___bpf_kretprobe_args(args)); \
+ _Pragma("GCC diagnostic pop") \
+} \
+static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
#endif
#include <stdlib.h>
#include <string.h>
#include <errno.h>
-#include <libbpf.h> /* libbpf_num_possible_cpus */
+#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
static inline unsigned int bpf_num_possible_cpus(void)
{
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <test_maps.h>
+
+static void map_batch_update(int map_fd, __u32 max_entries, int *keys,
+ int *values)
+{
+ int i, err;
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ for (i = 0; i < max_entries; i++) {
+ keys[i] = i;
+ values[i] = i + 1;
+ }
+
+ err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts);
+ CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno));
+}
+
+static void map_batch_verify(int *visited, __u32 max_entries,
+ int *keys, int *values)
+{
+ int i;
+
+ memset(visited, 0, max_entries * sizeof(*visited));
+ for (i = 0; i < max_entries; i++) {
+ CHECK(keys[i] + 1 != values[i], "key/value checking",
+ "error: i %d key %d value %d\n", i, keys[i], values[i]);
+ visited[i] = 1;
+ }
+ for (i = 0; i < max_entries; i++) {
+ CHECK(visited[i] != 1, "visited checking",
+ "error: keys array at index %d missing\n", i);
+ }
+}
+
+void test_array_map_batch_ops(void)
+{
+ struct bpf_create_map_attr xattr = {
+ .name = "array_map",
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ };
+ int map_fd, *keys, *values, *visited;
+ __u32 count, total, total_success;
+ const __u32 max_entries = 10;
+ bool nospace_err;
+ __u64 batch = 0;
+ int err, step;
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ xattr.max_entries = max_entries;
+ map_fd = bpf_create_map_xattr(&xattr);
+ CHECK(map_fd == -1,
+ "bpf_create_map_xattr()", "error:%s\n", strerror(errno));
+
+ keys = malloc(max_entries * sizeof(int));
+ values = malloc(max_entries * sizeof(int));
+ visited = malloc(max_entries * sizeof(int));
+ CHECK(!keys || !values || !visited, "malloc()", "error:%s\n",
+ strerror(errno));
+
+ /* populate elements to the map */
+ map_batch_update(map_fd, max_entries, keys, values);
+
+ /* test 1: lookup in a loop with various steps. */
+ total_success = 0;
+ for (step = 1; step < max_entries; step++) {
+ map_batch_update(map_fd, max_entries, keys, values);
+ map_batch_verify(visited, max_entries, keys, values);
+ memset(keys, 0, max_entries * sizeof(*keys));
+ memset(values, 0, max_entries * sizeof(*values));
+ batch = 0;
+ total = 0;
+ /* iteratively lookup/delete elements with 'step'
+ * elements each.
+ */
+ count = step;
+ nospace_err = false;
+ while (true) {
+ err = bpf_map_lookup_batch(map_fd,
+ total ? &batch : NULL, &batch,
+ keys + total,
+ values + total,
+ &count, &opts);
+
+ CHECK((err && errno != ENOENT), "lookup with steps",
+ "error: %s\n", strerror(errno));
+
+ total += count;
+ if (err)
+ break;
+
+ }
+
+ if (nospace_err == true)
+ continue;
+
+ CHECK(total != max_entries, "lookup with steps",
+ "total = %u, max_entries = %u\n", total, max_entries);
+
+ map_batch_verify(visited, max_entries, keys, values);
+
+ total_success++;
+ }
+
+ CHECK(total_success == 0, "check total_success",
+ "unexpected failure\n");
+
+ printf("%s:PASS\n", __func__);
+
+ free(keys);
+ free(values);
+ free(visited);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <bpf_util.h>
+#include <test_maps.h>
+
+static void map_batch_update(int map_fd, __u32 max_entries, int *keys,
+ void *values, bool is_pcpu)
+{
+ typedef BPF_DECLARE_PERCPU(int, value);
+ value *v = NULL;
+ int i, j, err;
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ if (is_pcpu)
+ v = (value *)values;
+
+ for (i = 0; i < max_entries; i++) {
+ keys[i] = i + 1;
+ if (is_pcpu)
+ for (j = 0; j < bpf_num_possible_cpus(); j++)
+ bpf_percpu(v[i], j) = i + 2 + j;
+ else
+ ((int *)values)[i] = i + 2;
+ }
+
+ err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts);
+ CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno));
+}
+
+static void map_batch_verify(int *visited, __u32 max_entries,
+ int *keys, void *values, bool is_pcpu)
+{
+ typedef BPF_DECLARE_PERCPU(int, value);
+ value *v = NULL;
+ int i, j;
+
+ if (is_pcpu)
+ v = (value *)values;
+
+ memset(visited, 0, max_entries * sizeof(*visited));
+ for (i = 0; i < max_entries; i++) {
+
+ if (is_pcpu) {
+ for (j = 0; j < bpf_num_possible_cpus(); j++) {
+ CHECK(keys[i] + 1 + j != bpf_percpu(v[i], j),
+ "key/value checking",
+ "error: i %d j %d key %d value %d\n",
+ i, j, keys[i], bpf_percpu(v[i], j));
+ }
+ } else {
+ CHECK(keys[i] + 1 != ((int *)values)[i],
+ "key/value checking",
+ "error: i %d key %d value %d\n", i, keys[i],
+ ((int *)values)[i]);
+ }
+
+ visited[i] = 1;
+
+ }
+ for (i = 0; i < max_entries; i++) {
+ CHECK(visited[i] != 1, "visited checking",
+ "error: keys array at index %d missing\n", i);
+ }
+}
+
+void __test_map_lookup_and_delete_batch(bool is_pcpu)
+{
+ __u32 batch, count, total, total_success;
+ typedef BPF_DECLARE_PERCPU(int, value);
+ int map_fd, *keys, *visited, key;
+ const __u32 max_entries = 10;
+ value pcpu_values[max_entries];
+ int err, step, value_size;
+ bool nospace_err;
+ void *values;
+ struct bpf_create_map_attr xattr = {
+ .name = "hash_map",
+ .map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH :
+ BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ };
+ DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+ .elem_flags = 0,
+ .flags = 0,
+ );
+
+ xattr.max_entries = max_entries;
+ map_fd = bpf_create_map_xattr(&xattr);
+ CHECK(map_fd == -1,
+ "bpf_create_map_xattr()", "error:%s\n", strerror(errno));
+
+ value_size = is_pcpu ? sizeof(value) : sizeof(int);
+ keys = malloc(max_entries * sizeof(int));
+ if (is_pcpu)
+ values = pcpu_values;
+ else
+ values = malloc(max_entries * sizeof(int));
+ visited = malloc(max_entries * sizeof(int));
+ CHECK(!keys || !values || !visited, "malloc()",
+ "error:%s\n", strerror(errno));
+
+ /* test 1: lookup/delete an empty hash table, -ENOENT */
+ count = max_entries;
+ err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys,
+ values, &count, &opts);
+ CHECK((err && errno != ENOENT), "empty map",
+ "error: %s\n", strerror(errno));
+
+ /* populate elements to the map */
+ map_batch_update(map_fd, max_entries, keys, values, is_pcpu);
+
+ /* test 2: lookup/delete with count = 0, success */
+ count = 0;
+ err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys,
+ values, &count, &opts);
+ CHECK(err, "count = 0", "error: %s\n", strerror(errno));
+
+ /* test 3: lookup/delete with count = max_entries, success */
+ memset(keys, 0, max_entries * sizeof(*keys));
+ memset(values, 0, max_entries * value_size);
+ count = max_entries;
+ err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys,
+ values, &count, &opts);
+ CHECK((err && errno != ENOENT), "count = max_entries",
+ "error: %s\n", strerror(errno));
+ CHECK(count != max_entries, "count = max_entries",
+ "count = %u, max_entries = %u\n", count, max_entries);
+ map_batch_verify(visited, max_entries, keys, values, is_pcpu);
+
+ /* bpf_map_get_next_key() should return -ENOENT for an empty map. */
+ err = bpf_map_get_next_key(map_fd, NULL, &key);
+ CHECK(!err, "bpf_map_get_next_key()", "error: %s\n", strerror(errno));
+
+ /* test 4: lookup/delete in a loop with various steps. */
+ total_success = 0;
+ for (step = 1; step < max_entries; step++) {
+ map_batch_update(map_fd, max_entries, keys, values, is_pcpu);
+ memset(keys, 0, max_entries * sizeof(*keys));
+ memset(values, 0, max_entries * value_size);
+ total = 0;
+ /* iteratively lookup/delete elements with 'step'
+ * elements each
+ */
+ count = step;
+ nospace_err = false;
+ while (true) {
+ err = bpf_map_lookup_batch(map_fd,
+ total ? &batch : NULL,
+ &batch, keys + total,
+ values +
+ total * value_size,
+ &count, &opts);
+ /* It is possible that we are failing due to buffer size
+ * not big enough. In such cases, let us just exit and
+ * go with large steps. Not that a buffer size with
+ * max_entries should always work.
+ */
+ if (err && errno == ENOSPC) {
+ nospace_err = true;
+ break;
+ }
+
+ CHECK((err && errno != ENOENT), "lookup with steps",
+ "error: %s\n", strerror(errno));
+
+ total += count;
+ if (err)
+ break;
+
+ }
+ if (nospace_err == true)
+ continue;
+
+ CHECK(total != max_entries, "lookup with steps",
+ "total = %u, max_entries = %u\n", total, max_entries);
+ map_batch_verify(visited, max_entries, keys, values, is_pcpu);
+
+ total = 0;
+ count = step;
+ while (total < max_entries) {
+ if (max_entries - total < step)
+ count = max_entries - total;
+ err = bpf_map_delete_batch(map_fd,
+ keys + total,
+ &count, &opts);
+ CHECK((err && errno != ENOENT), "delete batch",
+ "error: %s\n", strerror(errno));
+ total += count;
+ if (err)
+ break;
+ }
+ CHECK(total != max_entries, "delete with steps",
+ "total = %u, max_entries = %u\n", total, max_entries);
+
+ /* check map is empty, errono == ENOENT */
+ err = bpf_map_get_next_key(map_fd, NULL, &key);
+ CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()",
+ "error: %s\n", strerror(errno));
+
+ /* iteratively lookup/delete elements with 'step'
+ * elements each
+ */
+ map_batch_update(map_fd, max_entries, keys, values, is_pcpu);
+ memset(keys, 0, max_entries * sizeof(*keys));
+ memset(values, 0, max_entries * value_size);
+ total = 0;
+ count = step;
+ nospace_err = false;
+ while (true) {
+ err = bpf_map_lookup_and_delete_batch(map_fd,
+ total ? &batch : NULL,
+ &batch, keys + total,
+ values +
+ total * value_size,
+ &count, &opts);
+ /* It is possible that we are failing due to buffer size
+ * not big enough. In such cases, let us just exit and
+ * go with large steps. Not that a buffer size with
+ * max_entries should always work.
+ */
+ if (err && errno == ENOSPC) {
+ nospace_err = true;
+ break;
+ }
+
+ CHECK((err && errno != ENOENT), "lookup with steps",
+ "error: %s\n", strerror(errno));
+
+ total += count;
+ if (err)
+ break;
+ }
+
+ if (nospace_err == true)
+ continue;
+
+ CHECK(total != max_entries, "lookup/delete with steps",
+ "total = %u, max_entries = %u\n", total, max_entries);
+
+ map_batch_verify(visited, max_entries, keys, values, is_pcpu);
+ err = bpf_map_get_next_key(map_fd, NULL, &key);
+ CHECK(!err, "bpf_map_get_next_key()", "error: %s\n",
+ strerror(errno));
+
+ total_success++;
+ }
+
+ CHECK(total_success == 0, "check total_success",
+ "unexpected failure\n");
+ free(keys);
+ free(visited);
+ if (!is_pcpu)
+ free(values);
+}
+
+void htab_map_batch_ops(void)
+{
+ __test_map_lookup_and_delete_batch(false);
+ printf("test_%s:PASS\n", __func__);
+}
+
+void htab_percpu_map_batch_ops(void)
+{
+ __test_map_lookup_and_delete_batch(true);
+ printf("test_%s:PASS\n", __func__);
+}
+
+void test_htab_map_batch_ops(void)
+{
+ htab_map_batch_ops();
+ htab_percpu_map_batch_ops();
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <linux/err.h>
+#include <test_progs.h>
+#include "bpf_dctcp.skel.h"
+#include "bpf_cubic.skel.h"
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+static const struct timeval timeo_sec = { .tv_sec = 10 };
+static const size_t timeo_optlen = sizeof(timeo_sec);
+static int stop, duration;
+
+static int settimeo(int fd)
+{
+ int err;
+
+ err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
+ timeo_optlen);
+ if (CHECK(err == -1, "setsockopt(fd, SO_RCVTIMEO)", "errno:%d\n",
+ errno))
+ return -1;
+
+ err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec,
+ timeo_optlen);
+ if (CHECK(err == -1, "setsockopt(fd, SO_SNDTIMEO)", "errno:%d\n",
+ errno))
+ return -1;
+
+ return 0;
+}
+
+static int settcpca(int fd, const char *tcp_ca)
+{
+ int err;
+
+ err = setsockopt(fd, IPPROTO_TCP, TCP_CONGESTION, tcp_ca, strlen(tcp_ca));
+ if (CHECK(err == -1, "setsockopt(fd, TCP_CONGESTION)", "errno:%d\n",
+ errno))
+ return -1;
+
+ return 0;
+}
+
+static void *server(void *arg)
+{
+ int lfd = (int)(long)arg, err = 0, fd;
+ ssize_t nr_sent = 0, bytes = 0;
+ char batch[1500];
+
+ fd = accept(lfd, NULL, NULL);
+ while (fd == -1) {
+ if (errno == EINTR)
+ continue;
+ err = -errno;
+ goto done;
+ }
+
+ if (settimeo(fd)) {
+ err = -errno;
+ goto done;
+ }
+
+ while (bytes < total_bytes && !READ_ONCE(stop)) {
+ nr_sent = send(fd, &batch,
+ min(total_bytes - bytes, sizeof(batch)), 0);
+ if (nr_sent == -1 && errno == EINTR)
+ continue;
+ if (nr_sent == -1) {
+ err = -errno;
+ break;
+ }
+ bytes += nr_sent;
+ }
+
+ CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n",
+ bytes, total_bytes, nr_sent, errno);
+
+done:
+ if (fd != -1)
+ close(fd);
+ if (err) {
+ WRITE_ONCE(stop, 1);
+ return ERR_PTR(err);
+ }
+ return NULL;
+}
+
+static void do_test(const char *tcp_ca)
+{
+ struct sockaddr_in6 sa6 = {};
+ ssize_t nr_recv = 0, bytes = 0;
+ int lfd = -1, fd = -1;
+ pthread_t srv_thread;
+ socklen_t addrlen = sizeof(sa6);
+ void *thread_ret;
+ char batch[1500];
+ int err;
+
+ WRITE_ONCE(stop, 0);
+
+ lfd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (CHECK(lfd == -1, "socket", "errno:%d\n", errno))
+ return;
+ fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) {
+ close(lfd);
+ return;
+ }
+
+ if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) ||
+ settimeo(lfd) || settimeo(fd))
+ goto done;
+
+ /* bind, listen and start server thread to accept */
+ sa6.sin6_family = AF_INET6;
+ sa6.sin6_addr = in6addr_loopback;
+ err = bind(lfd, (struct sockaddr *)&sa6, addrlen);
+ if (CHECK(err == -1, "bind", "errno:%d\n", errno))
+ goto done;
+ err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen);
+ if (CHECK(err == -1, "getsockname", "errno:%d\n", errno))
+ goto done;
+ err = listen(lfd, 1);
+ if (CHECK(err == -1, "listen", "errno:%d\n", errno))
+ goto done;
+ err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd);
+ if (CHECK(err != 0, "pthread_create", "err:%d\n", err))
+ goto done;
+
+ /* connect to server */
+ err = connect(fd, (struct sockaddr *)&sa6, addrlen);
+ if (CHECK(err == -1, "connect", "errno:%d\n", errno))
+ goto wait_thread;
+
+ /* recv total_bytes */
+ while (bytes < total_bytes && !READ_ONCE(stop)) {
+ nr_recv = recv(fd, &batch,
+ min(total_bytes - bytes, sizeof(batch)), 0);
+ if (nr_recv == -1 && errno == EINTR)
+ continue;
+ if (nr_recv == -1)
+ break;
+ bytes += nr_recv;
+ }
+
+ CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n",
+ bytes, total_bytes, nr_recv, errno);
+
+wait_thread:
+ WRITE_ONCE(stop, 1);
+ pthread_join(srv_thread, &thread_ret);
+ CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld",
+ PTR_ERR(thread_ret));
+done:
+ close(lfd);
+ close(fd);
+}
+
+static void test_cubic(void)
+{
+ struct bpf_cubic *cubic_skel;
+ struct bpf_link *link;
+
+ cubic_skel = bpf_cubic__open_and_load();
+ if (CHECK(!cubic_skel, "bpf_cubic__open_and_load", "failed\n"))
+ return;
+
+ link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic);
+ if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n",
+ PTR_ERR(link))) {
+ bpf_cubic__destroy(cubic_skel);
+ return;
+ }
+
+ do_test("bpf_cubic");
+
+ bpf_link__destroy(link);
+ bpf_cubic__destroy(cubic_skel);
+}
+
+static void test_dctcp(void)
+{
+ struct bpf_dctcp *dctcp_skel;
+ struct bpf_link *link;
+
+ dctcp_skel = bpf_dctcp__open_and_load();
+ if (CHECK(!dctcp_skel, "bpf_dctcp__open_and_load", "failed\n"))
+ return;
+
+ link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp);
+ if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n",
+ PTR_ERR(link))) {
+ bpf_dctcp__destroy(dctcp_skel);
+ return;
+ }
+
+ do_test("bpf_dctcp");
+
+ bpf_link__destroy(link);
+ bpf_dctcp__destroy(dctcp_skel);
+}
+
+void test_bpf_tcp_ca(void)
+{
+ if (test__start_subtest("dctcp"))
+ test_dctcp();
+ if (test__start_subtest("cubic"))
+ test_cubic();
+}
{ "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS },
{ "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS },
+ { "pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
+
/* full unroll by llvm */
{ "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
{ "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
#include <bpf/btf.h>
-#include "libbpf_internal.h"
+#include "bpf/libbpf_internal.h"
static int duration = 0;
link = calloc(sizeof(struct bpf_link *), prog_cnt);
prog = calloc(sizeof(struct bpf_program *), prog_cnt);
- result = malloc(prog_cnt * sizeof(u64));
+ result = malloc((prog_cnt + 32 /* spare */) * sizeof(u64));
if (CHECK(!link || !prog || !result, "alloc_memory",
"failed to alloc memory"))
goto close_prog;
"fexit/test_pkt_access",
"fexit/test_pkt_access_subprog1",
"fexit/test_pkt_access_subprog2",
+ "fexit/test_pkt_access_subprog3",
+ };
+ test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
+ "./test_pkt_access.o",
+ ARRAY_SIZE(prog_name),
+ prog_name);
+}
+
+static void test_func_replace(void)
+{
+ const char *prog_name[] = {
+ "fexit/test_pkt_access",
+ "fexit/test_pkt_access_subprog1",
+ "fexit/test_pkt_access_subprog2",
+ "fexit/test_pkt_access_subprog3",
+ "freplace/get_skb_len",
+ "freplace/get_skb_ifindex",
+ "freplace/get_constant",
};
test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
"./test_pkt_access.o",
{
test_target_no_callees();
test_target_yes_callees();
+ test_func_replace();
}
#include <sched.h>
#include <sys/socket.h>
#include <test_progs.h>
-#include "libbpf_internal.h"
+#include "bpf/libbpf_internal.h"
static void on_sample(void *ctx, int cpu, void *data, __u32 size)
{
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
+#include "test_send_signal_kern.skel.h"
static volatile int sigusr1_received = 0;
}
static void test_send_signal_common(struct perf_event_attr *attr,
- int prog_type,
+ bool signal_thread,
const char *test_name)
{
- int err = -1, pmu_fd, prog_fd, info_map_fd, status_map_fd;
- const char *file = "./test_send_signal_kern.o";
- struct bpf_object *obj = NULL;
+ struct test_send_signal_kern *skel;
int pipe_c2p[2], pipe_p2c[2];
- __u32 key = 0, duration = 0;
+ int err = -1, pmu_fd = -1;
+ __u32 duration = 0;
char buf[256];
pid_t pid;
- __u64 val;
if (CHECK(pipe(pipe_c2p), test_name,
"pipe pipe_c2p error: %s\n", strerror(errno)))
close(pipe_c2p[1]); /* close write */
close(pipe_p2c[0]); /* close read */
- err = bpf_prog_load(file, prog_type, &obj, &prog_fd);
- if (CHECK(err < 0, test_name, "bpf_prog_load error: %s\n",
- strerror(errno)))
- goto prog_load_failure;
-
- pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1,
- -1 /* group id */, 0 /* flags */);
- if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n",
- strerror(errno))) {
- err = -1;
- goto close_prog;
- }
+ skel = test_send_signal_kern__open_and_load();
+ if (CHECK(!skel, "skel_open_and_load", "skeleton open_and_load failed\n"))
+ goto skel_open_load_failure;
- err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
- if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_enable error: %s\n",
- strerror(errno)))
- goto disable_pmu;
-
- err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
- if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_set_bpf error: %s\n",
- strerror(errno)))
- goto disable_pmu;
-
- err = -1;
- info_map_fd = bpf_object__find_map_fd_by_name(obj, "info_map");
- if (CHECK(info_map_fd < 0, test_name, "find map %s error\n", "info_map"))
- goto disable_pmu;
+ if (!attr) {
+ err = test_send_signal_kern__attach(skel);
+ if (CHECK(err, "skel_attach", "skeleton attach failed\n")) {
+ err = -1;
+ goto destroy_skel;
+ }
+ } else {
+ pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1,
+ -1 /* group id */, 0 /* flags */);
+ if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n",
+ strerror(errno))) {
+ err = -1;
+ goto destroy_skel;
+ }
- status_map_fd = bpf_object__find_map_fd_by_name(obj, "status_map");
- if (CHECK(status_map_fd < 0, test_name, "find map %s error\n", "status_map"))
- goto disable_pmu;
+ skel->links.send_signal_perf =
+ bpf_program__attach_perf_event(skel->progs.send_signal_perf, pmu_fd);
+ if (CHECK(IS_ERR(skel->links.send_signal_perf), "attach_perf_event",
+ "err %ld\n", PTR_ERR(skel->links.send_signal_perf)))
+ goto disable_pmu;
+ }
/* wait until child signal handler installed */
read(pipe_c2p[0], buf, 1);
/* trigger the bpf send_signal */
- key = 0;
- val = (((__u64)(SIGUSR1)) << 32) | pid;
- bpf_map_update_elem(info_map_fd, &key, &val, 0);
+ skel->bss->pid = pid;
+ skel->bss->sig = SIGUSR1;
+ skel->bss->signal_thread = signal_thread;
/* notify child that bpf program can send_signal now */
write(pipe_p2c[1], buf, 1);
disable_pmu:
close(pmu_fd);
-close_prog:
- bpf_object__close(obj);
-prog_load_failure:
+destroy_skel:
+ test_send_signal_kern__destroy(skel);
+skel_open_load_failure:
close(pipe_c2p[0]);
close(pipe_p2c[1]);
wait(NULL);
}
-static void test_send_signal_tracepoint(void)
+static void test_send_signal_tracepoint(bool signal_thread)
{
- const char *id_path = "/sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id";
- struct perf_event_attr attr = {
- .type = PERF_TYPE_TRACEPOINT,
- .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN,
- .sample_period = 1,
- .wakeup_events = 1,
- };
- __u32 duration = 0;
- int bytes, efd;
- char buf[256];
-
- efd = open(id_path, O_RDONLY, 0);
- if (CHECK(efd < 0, "tracepoint",
- "open syscalls/sys_enter_nanosleep/id failure: %s\n",
- strerror(errno)))
- return;
-
- bytes = read(efd, buf, sizeof(buf));
- close(efd);
- if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "tracepoint",
- "read syscalls/sys_enter_nanosleep/id failure: %s\n",
- strerror(errno)))
- return;
-
- attr.config = strtol(buf, NULL, 0);
-
- test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint");
+ test_send_signal_common(NULL, signal_thread, "tracepoint");
}
-static void test_send_signal_perf(void)
+static void test_send_signal_perf(bool signal_thread)
{
struct perf_event_attr attr = {
.sample_period = 1,
.config = PERF_COUNT_SW_CPU_CLOCK,
};
- test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
- "perf_sw_event");
+ test_send_signal_common(&attr, signal_thread, "perf_sw_event");
}
-static void test_send_signal_nmi(void)
+static void test_send_signal_nmi(bool signal_thread)
{
struct perf_event_attr attr = {
- .sample_freq = 50,
- .freq = 1,
+ .sample_period = 1,
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES,
};
close(pmu_fd);
}
- test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
- "perf_hw_event");
+ test_send_signal_common(&attr, signal_thread, "perf_hw_event");
}
void test_send_signal(void)
{
if (test__start_subtest("send_signal_tracepoint"))
- test_send_signal_tracepoint();
+ test_send_signal_tracepoint(false);
if (test__start_subtest("send_signal_perf"))
- test_send_signal_perf();
+ test_send_signal_perf(false);
if (test__start_subtest("send_signal_nmi"))
- test_send_signal_nmi();
+ test_send_signal_nmi(false);
+ if (test__start_subtest("send_signal_tracepoint_thread"))
+ test_send_signal_tracepoint(true);
+ if (test__start_subtest("send_signal_perf_thread"))
+ test_send_signal_perf(true);
+ if (test__start_subtest("send_signal_nmi_thread"))
+ test_send_signal_nmi(true);
}
pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
0 /* cpu 0 */, -1 /* group id */,
0 /* flags */);
- if (CHECK(pmu_fd < 0, "perf_event_open",
- "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n",
+ if (pmu_fd < 0 && errno == ENOENT) {
+ printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__);
+ test__skip();
+ goto cleanup;
+ }
+ if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
pmu_fd, errno))
goto cleanup;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+
+const char *err_str;
+bool found;
+
+static int libbpf_debug_print(enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ char *log_buf;
+
+ if (level != LIBBPF_WARN ||
+ strcmp(format, "libbpf: \n%s\n")) {
+ vprintf(format, args);
+ return 0;
+ }
+
+ log_buf = va_arg(args, char *);
+ if (!log_buf)
+ goto out;
+ if (strstr(log_buf, err_str) == 0)
+ found = true;
+out:
+ printf(format, log_buf);
+ return 0;
+}
+
+extern int extra_prog_load_log_flags;
+
+static int check_load(const char *file)
+{
+ struct bpf_prog_load_attr attr;
+ struct bpf_object *obj = NULL;
+ int err, prog_fd;
+
+ memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
+ attr.file = file;
+ attr.prog_type = BPF_PROG_TYPE_UNSPEC;
+ attr.log_level = extra_prog_load_log_flags;
+ attr.prog_flags = BPF_F_TEST_RND_HI32;
+ found = false;
+ err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+ bpf_object__close(obj);
+ return err;
+}
+
+struct test_def {
+ const char *file;
+ const char *err_str;
+};
+
+void test_test_global_funcs(void)
+{
+ struct test_def tests[] = {
+ { "test_global_func1.o", "combined stack size of 4 calls is 544" },
+ { "test_global_func2.o" },
+ { "test_global_func3.o" , "the call stack of 8 frames" },
+ { "test_global_func4.o" },
+ { "test_global_func5.o" , "expected pointer to ctx, but got PTR" },
+ { "test_global_func6.o" , "modified ctx ptr R2" },
+ { "test_global_func7.o" , "foo() doesn't return scalar" },
+ };
+ libbpf_print_fn_t old_print_fn = NULL;
+ int err, i, duration = 0;
+
+ old_print_fn = libbpf_set_print(libbpf_debug_print);
+
+ for (i = 0; i < ARRAY_SIZE(tests); i++) {
+ const struct test_def *test = &tests[i];
+
+ if (!test__start_subtest(test->file))
+ continue;
+
+ err_str = test->err_str;
+ err = check_load(test->file);
+ CHECK_FAIL(!!err ^ !!err_str);
+ if (err_str)
+ CHECK(found, "", "expected string '%s'", err_str);
+ }
+ libbpf_set_print(old_print_fn);
+}
/* Copyright (c) 2019 Facebook */
#define _GNU_SOURCE
#include <sched.h>
+#include <sys/prctl.h>
#include <test_progs.h>
#define MAX_CNT 100000
static int test_task_rename(const char *prog)
{
int i, fd, duration = 0, err;
- char buf[] = "test\n";
+ char buf[] = "test_overhead";
__u64 start_time;
fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
struct bpf_object *obj;
struct bpf_link *link;
int err, duration = 0;
+ char comm[16] = {};
+
+ if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L)))
+ return;
obj = bpf_object__open_file("./test_overhead.o", NULL);
if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj)))
test_run("fexit");
bpf_link__destroy(link);
cleanup:
+ prctl(PR_SET_NAME, comm, 0L, 0L, 0L);
bpf_object__close(obj);
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <net/if.h>
+#include "test_xdp.skel.h"
+#include "test_xdp_bpf2bpf.skel.h"
+
+void test_xdp_bpf2bpf(void)
+{
+ __u32 duration = 0, retval, size;
+ char buf[128];
+ int err, pkt_fd, map_fd;
+ struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+ struct iptnl_info value4 = {.family = AF_INET};
+ struct test_xdp *pkt_skel = NULL;
+ struct test_xdp_bpf2bpf *ftrace_skel = NULL;
+ struct vip key4 = {.protocol = 6, .family = AF_INET};
+ DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+
+ /* Load XDP program to introspect */
+ pkt_skel = test_xdp__open_and_load();
+ if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp skeleton failed\n"))
+ return;
+
+ pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_tx_iptunnel);
+
+ map_fd = bpf_map__fd(pkt_skel->maps.vip2tnl);
+ bpf_map_update_elem(map_fd, &key4, &value4, 0);
+
+ /* Load trace program */
+ opts.attach_prog_fd = pkt_fd,
+ ftrace_skel = test_xdp_bpf2bpf__open_opts(&opts);
+ if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n"))
+ goto out;
+
+ err = test_xdp_bpf2bpf__load(ftrace_skel);
+ if (CHECK(err, "__load", "ftrace skeleton failed\n"))
+ goto out;
+
+ err = test_xdp_bpf2bpf__attach(ftrace_skel);
+ if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err))
+ goto out;
+
+ /* Run test program */
+ err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ buf, &size, &retval, &duration);
+
+ if (CHECK(err || retval != XDP_TX || size != 74 ||
+ iph->protocol != IPPROTO_IPIP, "ipv4",
+ "err %d errno %d retval %d size %d\n",
+ err, errno, retval, size))
+ goto out;
+
+ /* Verify test results */
+ if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"),
+ "result", "fentry failed err %llu\n",
+ ftrace_skel->bss->test_result_fentry))
+ goto out;
+
+ CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result",
+ "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit);
+
+out:
+ test_xdp__destroy(pkt_skel);
+ test_xdp_bpf2bpf__destroy(ftrace_skel);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* WARNING: This implemenation is not necessarily the same
+ * as the tcp_cubic.c. The purpose is mainly for testing
+ * the kernel BPF logic.
+ *
+ * Highlights:
+ * 1. CONFIG_HZ .kconfig map is used.
+ * 2. In bictcp_update(), calculation is changed to use usec
+ * resolution (i.e. USEC_PER_JIFFY) instead of using jiffies.
+ * Thus, usecs_to_jiffies() is not used in the bpf_cubic.c.
+ * 3. In bitctcp_update() [under tcp_friendliness], the original
+ * "while (ca->ack_cnt > delta)" loop is changed to the equivalent
+ * "ca->ack_cnt / delta" operation.
+ */
+
+#include <linux/bpf.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
+
+#define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation
+ * max_cwnd = snd_cwnd * beta
+ */
+#define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */
+
+/* Two methods of hybrid slow start */
+#define HYSTART_ACK_TRAIN 0x1
+#define HYSTART_DELAY 0x2
+
+/* Number of delay samples for detecting the increase of delay */
+#define HYSTART_MIN_SAMPLES 8
+#define HYSTART_DELAY_MIN (4000U) /* 4ms */
+#define HYSTART_DELAY_MAX (16000U) /* 16 ms */
+#define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX)
+
+static int fast_convergence = 1;
+static const int beta = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */
+static int initial_ssthresh;
+static const int bic_scale = 41;
+static int tcp_friendliness = 1;
+
+static int hystart = 1;
+static int hystart_detect = HYSTART_ACK_TRAIN | HYSTART_DELAY;
+static int hystart_low_window = 16;
+static int hystart_ack_delta_us = 2000;
+
+static const __u32 cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */
+static const __u32 beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3
+ / (BICTCP_BETA_SCALE - beta);
+/* calculate the "K" for (wmax-cwnd) = c/rtt * K^3
+ * so K = cubic_root( (wmax-cwnd)*rtt/c )
+ * the unit of K is bictcp_HZ=2^10, not HZ
+ *
+ * c = bic_scale >> 10
+ * rtt = 100ms
+ *
+ * the following code has been designed and tested for
+ * cwnd < 1 million packets
+ * RTT < 100 seconds
+ * HZ < 1,000,00 (corresponding to 10 nano-second)
+ */
+
+/* 1/c * 2^2*bictcp_HZ * srtt, 2^40 */
+static const __u64 cube_factor = (__u64)(1ull << (10+3*BICTCP_HZ))
+ / (bic_scale * 10);
+
+/* BIC TCP Parameters */
+struct bictcp {
+ __u32 cnt; /* increase cwnd by 1 after ACKs */
+ __u32 last_max_cwnd; /* last maximum snd_cwnd */
+ __u32 last_cwnd; /* the last snd_cwnd */
+ __u32 last_time; /* time when updated last_cwnd */
+ __u32 bic_origin_point;/* origin point of bic function */
+ __u32 bic_K; /* time to origin point
+ from the beginning of the current epoch */
+ __u32 delay_min; /* min delay (usec) */
+ __u32 epoch_start; /* beginning of an epoch */
+ __u32 ack_cnt; /* number of acks */
+ __u32 tcp_cwnd; /* estimated tcp cwnd */
+ __u16 unused;
+ __u8 sample_cnt; /* number of samples to decide curr_rtt */
+ __u8 found; /* the exit point is found? */
+ __u32 round_start; /* beginning of each round */
+ __u32 end_seq; /* end_seq of the round */
+ __u32 last_ack; /* last time when the ACK spacing is close */
+ __u32 curr_rtt; /* the minimum rtt of current round */
+};
+
+static inline void bictcp_reset(struct bictcp *ca)
+{
+ ca->cnt = 0;
+ ca->last_max_cwnd = 0;
+ ca->last_cwnd = 0;
+ ca->last_time = 0;
+ ca->bic_origin_point = 0;
+ ca->bic_K = 0;
+ ca->delay_min = 0;
+ ca->epoch_start = 0;
+ ca->ack_cnt = 0;
+ ca->tcp_cwnd = 0;
+ ca->found = 0;
+}
+
+extern unsigned long CONFIG_HZ __kconfig;
+#define HZ CONFIG_HZ
+#define USEC_PER_MSEC 1000UL
+#define USEC_PER_SEC 1000000UL
+#define USEC_PER_JIFFY (USEC_PER_SEC / HZ)
+
+static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor)
+{
+ return dividend / divisor;
+}
+
+#define div64_ul div64_u64
+
+#define BITS_PER_U64 (sizeof(__u64) * 8)
+static __always_inline int fls64(__u64 x)
+{
+ int num = BITS_PER_U64 - 1;
+
+ if (x == 0)
+ return 0;
+
+ if (!(x & (~0ull << (BITS_PER_U64-32)))) {
+ num -= 32;
+ x <<= 32;
+ }
+ if (!(x & (~0ull << (BITS_PER_U64-16)))) {
+ num -= 16;
+ x <<= 16;
+ }
+ if (!(x & (~0ull << (BITS_PER_U64-8)))) {
+ num -= 8;
+ x <<= 8;
+ }
+ if (!(x & (~0ull << (BITS_PER_U64-4)))) {
+ num -= 4;
+ x <<= 4;
+ }
+ if (!(x & (~0ull << (BITS_PER_U64-2)))) {
+ num -= 2;
+ x <<= 2;
+ }
+ if (!(x & (~0ull << (BITS_PER_U64-1))))
+ num -= 1;
+
+ return num + 1;
+}
+
+static __always_inline __u32 bictcp_clock_us(const struct sock *sk)
+{
+ return tcp_sk(sk)->tcp_mstamp;
+}
+
+static __always_inline void bictcp_hystart_reset(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct bictcp *ca = inet_csk_ca(sk);
+
+ ca->round_start = ca->last_ack = bictcp_clock_us(sk);
+ ca->end_seq = tp->snd_nxt;
+ ca->curr_rtt = ~0U;
+ ca->sample_cnt = 0;
+}
+
+/* "struct_ops/" prefix is not a requirement
+ * It will be recognized as BPF_PROG_TYPE_STRUCT_OPS
+ * as long as it is used in one of the func ptr
+ * under SEC(".struct_ops").
+ */
+SEC("struct_ops/bictcp_init")
+void BPF_PROG(bictcp_init, struct sock *sk)
+{
+ struct bictcp *ca = inet_csk_ca(sk);
+
+ bictcp_reset(ca);
+
+ if (hystart)
+ bictcp_hystart_reset(sk);
+
+ if (!hystart && initial_ssthresh)
+ tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
+}
+
+/* No prefix in SEC will also work.
+ * The remaining tcp-cubic functions have an easier way.
+ */
+SEC("no-sec-prefix-bictcp_cwnd_event")
+void BPF_PROG(bictcp_cwnd_event, struct sock *sk, enum tcp_ca_event event)
+{
+ if (event == CA_EVENT_TX_START) {
+ struct bictcp *ca = inet_csk_ca(sk);
+ __u32 now = tcp_jiffies32;
+ __s32 delta;
+
+ delta = now - tcp_sk(sk)->lsndtime;
+
+ /* We were application limited (idle) for a while.
+ * Shift epoch_start to keep cwnd growth to cubic curve.
+ */
+ if (ca->epoch_start && delta > 0) {
+ ca->epoch_start += delta;
+ if (after(ca->epoch_start, now))
+ ca->epoch_start = now;
+ }
+ return;
+ }
+}
+
+/*
+ * cbrt(x) MSB values for x MSB values in [0..63].
+ * Precomputed then refined by hand - Willy Tarreau
+ *
+ * For x in [0..63],
+ * v = cbrt(x << 18) - 1
+ * cbrt(x) = (v[x] + 10) >> 6
+ */
+static const __u8 v[] = {
+ /* 0x00 */ 0, 54, 54, 54, 118, 118, 118, 118,
+ /* 0x08 */ 123, 129, 134, 138, 143, 147, 151, 156,
+ /* 0x10 */ 157, 161, 164, 168, 170, 173, 176, 179,
+ /* 0x18 */ 181, 185, 187, 190, 192, 194, 197, 199,
+ /* 0x20 */ 200, 202, 204, 206, 209, 211, 213, 215,
+ /* 0x28 */ 217, 219, 221, 222, 224, 225, 227, 229,
+ /* 0x30 */ 231, 232, 234, 236, 237, 239, 240, 242,
+ /* 0x38 */ 244, 245, 246, 248, 250, 251, 252, 254,
+};
+
+/* calculate the cubic root of x using a table lookup followed by one
+ * Newton-Raphson iteration.
+ * Avg err ~= 0.195%
+ */
+static __always_inline __u32 cubic_root(__u64 a)
+{
+ __u32 x, b, shift;
+
+ if (a < 64) {
+ /* a in [0..63] */
+ return ((__u32)v[(__u32)a] + 35) >> 6;
+ }
+
+ b = fls64(a);
+ b = ((b * 84) >> 8) - 1;
+ shift = (a >> (b * 3));
+
+ /* it is needed for verifier's bound check on v */
+ if (shift >= 64)
+ return 0;
+
+ x = ((__u32)(((__u32)v[shift] + 10) << b)) >> 6;
+
+ /*
+ * Newton-Raphson iteration
+ * 2
+ * x = ( 2 * x + a / x ) / 3
+ * k+1 k k
+ */
+ x = (2 * x + (__u32)div64_u64(a, (__u64)x * (__u64)(x - 1)));
+ x = ((x * 341) >> 10);
+ return x;
+}
+
+/*
+ * Compute congestion window to use.
+ */
+static __always_inline void bictcp_update(struct bictcp *ca, __u32 cwnd,
+ __u32 acked)
+{
+ __u32 delta, bic_target, max_cnt;
+ __u64 offs, t;
+
+ ca->ack_cnt += acked; /* count the number of ACKed packets */
+
+ if (ca->last_cwnd == cwnd &&
+ (__s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32)
+ return;
+
+ /* The CUBIC function can update ca->cnt at most once per jiffy.
+ * On all cwnd reduction events, ca->epoch_start is set to 0,
+ * which will force a recalculation of ca->cnt.
+ */
+ if (ca->epoch_start && tcp_jiffies32 == ca->last_time)
+ goto tcp_friendliness;
+
+ ca->last_cwnd = cwnd;
+ ca->last_time = tcp_jiffies32;
+
+ if (ca->epoch_start == 0) {
+ ca->epoch_start = tcp_jiffies32; /* record beginning */
+ ca->ack_cnt = acked; /* start counting */
+ ca->tcp_cwnd = cwnd; /* syn with cubic */
+
+ if (ca->last_max_cwnd <= cwnd) {
+ ca->bic_K = 0;
+ ca->bic_origin_point = cwnd;
+ } else {
+ /* Compute new K based on
+ * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ)
+ */
+ ca->bic_K = cubic_root(cube_factor
+ * (ca->last_max_cwnd - cwnd));
+ ca->bic_origin_point = ca->last_max_cwnd;
+ }
+ }
+
+ /* cubic function - calc*/
+ /* calculate c * time^3 / rtt,
+ * while considering overflow in calculation of time^3
+ * (so time^3 is done by using 64 bit)
+ * and without the support of division of 64bit numbers
+ * (so all divisions are done by using 32 bit)
+ * also NOTE the unit of those veriables
+ * time = (t - K) / 2^bictcp_HZ
+ * c = bic_scale >> 10
+ * rtt = (srtt >> 3) / HZ
+ * !!! The following code does not have overflow problems,
+ * if the cwnd < 1 million packets !!!
+ */
+
+ t = (__s32)(tcp_jiffies32 - ca->epoch_start) * USEC_PER_JIFFY;
+ t += ca->delay_min;
+ /* change the unit from usec to bictcp_HZ */
+ t <<= BICTCP_HZ;
+ t /= USEC_PER_SEC;
+
+ if (t < ca->bic_K) /* t - K */
+ offs = ca->bic_K - t;
+ else
+ offs = t - ca->bic_K;
+
+ /* c/rtt * (t-K)^3 */
+ delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ);
+ if (t < ca->bic_K) /* below origin*/
+ bic_target = ca->bic_origin_point - delta;
+ else /* above origin*/
+ bic_target = ca->bic_origin_point + delta;
+
+ /* cubic function - calc bictcp_cnt*/
+ if (bic_target > cwnd) {
+ ca->cnt = cwnd / (bic_target - cwnd);
+ } else {
+ ca->cnt = 100 * cwnd; /* very small increment*/
+ }
+
+ /*
+ * The initial growth of cubic function may be too conservative
+ * when the available bandwidth is still unknown.
+ */
+ if (ca->last_max_cwnd == 0 && ca->cnt > 20)
+ ca->cnt = 20; /* increase cwnd 5% per RTT */
+
+tcp_friendliness:
+ /* TCP Friendly */
+ if (tcp_friendliness) {
+ __u32 scale = beta_scale;
+ __u32 n;
+
+ /* update tcp cwnd */
+ delta = (cwnd * scale) >> 3;
+ if (ca->ack_cnt > delta && delta) {
+ n = ca->ack_cnt / delta;
+ ca->ack_cnt -= n * delta;
+ ca->tcp_cwnd += n;
+ }
+
+ if (ca->tcp_cwnd > cwnd) { /* if bic is slower than tcp */
+ delta = ca->tcp_cwnd - cwnd;
+ max_cnt = cwnd / delta;
+ if (ca->cnt > max_cnt)
+ ca->cnt = max_cnt;
+ }
+ }
+
+ /* The maximum rate of cwnd increase CUBIC allows is 1 packet per
+ * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT.
+ */
+ ca->cnt = max(ca->cnt, 2U);
+}
+
+/* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */
+void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct bictcp *ca = inet_csk_ca(sk);
+
+ if (!tcp_is_cwnd_limited(sk))
+ return;
+
+ if (tcp_in_slow_start(tp)) {
+ if (hystart && after(ack, ca->end_seq))
+ bictcp_hystart_reset(sk);
+ acked = tcp_slow_start(tp, acked);
+ if (!acked)
+ return;
+ }
+ bictcp_update(ca, tp->snd_cwnd, acked);
+ tcp_cong_avoid_ai(tp, ca->cnt, acked);
+}
+
+__u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct bictcp *ca = inet_csk_ca(sk);
+
+ ca->epoch_start = 0; /* end of epoch */
+
+ /* Wmax and fast convergence */
+ if (tp->snd_cwnd < ca->last_max_cwnd && fast_convergence)
+ ca->last_max_cwnd = (tp->snd_cwnd * (BICTCP_BETA_SCALE + beta))
+ / (2 * BICTCP_BETA_SCALE);
+ else
+ ca->last_max_cwnd = tp->snd_cwnd;
+
+ return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
+}
+
+void BPF_STRUCT_OPS(bictcp_state, struct sock *sk, __u8 new_state)
+{
+ if (new_state == TCP_CA_Loss) {
+ bictcp_reset(inet_csk_ca(sk));
+ bictcp_hystart_reset(sk);
+ }
+}
+
+#define GSO_MAX_SIZE 65536
+
+/* Account for TSO/GRO delays.
+ * Otherwise short RTT flows could get too small ssthresh, since during
+ * slow start we begin with small TSO packets and ca->delay_min would
+ * not account for long aggregation delay when TSO packets get bigger.
+ * Ideally even with a very small RTT we would like to have at least one
+ * TSO packet being sent and received by GRO, and another one in qdisc layer.
+ * We apply another 100% factor because @rate is doubled at this point.
+ * We cap the cushion to 1ms.
+ */
+static __always_inline __u32 hystart_ack_delay(struct sock *sk)
+{
+ unsigned long rate;
+
+ rate = sk->sk_pacing_rate;
+ if (!rate)
+ return 0;
+ return min((__u64)USEC_PER_MSEC,
+ div64_ul((__u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate));
+}
+
+static __always_inline void hystart_update(struct sock *sk, __u32 delay)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct bictcp *ca = inet_csk_ca(sk);
+ __u32 threshold;
+
+ if (hystart_detect & HYSTART_ACK_TRAIN) {
+ __u32 now = bictcp_clock_us(sk);
+
+ /* first detection parameter - ack-train detection */
+ if ((__s32)(now - ca->last_ack) <= hystart_ack_delta_us) {
+ ca->last_ack = now;
+
+ threshold = ca->delay_min + hystart_ack_delay(sk);
+
+ /* Hystart ack train triggers if we get ack past
+ * ca->delay_min/2.
+ * Pacing might have delayed packets up to RTT/2
+ * during slow start.
+ */
+ if (sk->sk_pacing_status == SK_PACING_NONE)
+ threshold >>= 1;
+
+ if ((__s32)(now - ca->round_start) > threshold) {
+ ca->found = 1;
+ tp->snd_ssthresh = tp->snd_cwnd;
+ }
+ }
+ }
+
+ if (hystart_detect & HYSTART_DELAY) {
+ /* obtain the minimum delay of more than sampling packets */
+ if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
+ if (ca->curr_rtt > delay)
+ ca->curr_rtt = delay;
+
+ ca->sample_cnt++;
+ } else {
+ if (ca->curr_rtt > ca->delay_min +
+ HYSTART_DELAY_THRESH(ca->delay_min >> 3)) {
+ ca->found = 1;
+ tp->snd_ssthresh = tp->snd_cwnd;
+ }
+ }
+ }
+}
+
+void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk,
+ const struct ack_sample *sample)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct bictcp *ca = inet_csk_ca(sk);
+ __u32 delay;
+
+ /* Some calls are for duplicates without timetamps */
+ if (sample->rtt_us < 0)
+ return;
+
+ /* Discard delay samples right after fast recovery */
+ if (ca->epoch_start && (__s32)(tcp_jiffies32 - ca->epoch_start) < HZ)
+ return;
+
+ delay = sample->rtt_us;
+ if (delay == 0)
+ delay = 1;
+
+ /* first time call or link delay decreases */
+ if (ca->delay_min == 0 || ca->delay_min > delay)
+ ca->delay_min = delay;
+
+ /* hystart triggers when cwnd is larger than some threshold */
+ if (!ca->found && tcp_in_slow_start(tp) && hystart &&
+ tp->snd_cwnd >= hystart_low_window)
+ hystart_update(sk, delay);
+}
+
+__u32 BPF_STRUCT_OPS(tcp_reno_undo_cwnd, struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+
+ return max(tp->snd_cwnd, tp->prior_cwnd);
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops cubic = {
+ .init = (void *)bictcp_init,
+ .ssthresh = (void *)bictcp_recalc_ssthresh,
+ .cong_avoid = (void *)bictcp_cong_avoid,
+ .set_state = (void *)bictcp_state,
+ .undo_cwnd = (void *)tcp_reno_undo_cwnd,
+ .cwnd_event = (void *)bictcp_cwnd_event,
+ .pkts_acked = (void *)bictcp_acked,
+ .name = "bpf_cubic",
+};
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+/* WARNING: This implemenation is not necessarily the same
+ * as the tcp_dctcp.c. The purpose is mainly for testing
+ * the kernel BPF logic.
+ */
+
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_trace_helpers.h"
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define DCTCP_MAX_ALPHA 1024U
+
+struct dctcp {
+ __u32 old_delivered;
+ __u32 old_delivered_ce;
+ __u32 prior_rcv_nxt;
+ __u32 dctcp_alpha;
+ __u32 next_seq;
+ __u32 ce_state;
+ __u32 loss_cwnd;
+};
+
+static unsigned int dctcp_shift_g = 4; /* g = 1/2^4 */
+static unsigned int dctcp_alpha_on_init = DCTCP_MAX_ALPHA;
+
+static __always_inline void dctcp_reset(const struct tcp_sock *tp,
+ struct dctcp *ca)
+{
+ ca->next_seq = tp->snd_nxt;
+
+ ca->old_delivered = tp->delivered;
+ ca->old_delivered_ce = tp->delivered_ce;
+}
+
+SEC("struct_ops/dctcp_init")
+void BPF_PROG(dctcp_init, struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ ca->prior_rcv_nxt = tp->rcv_nxt;
+ ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
+ ca->loss_cwnd = 0;
+ ca->ce_state = 0;
+
+ dctcp_reset(tp, ca);
+}
+
+SEC("struct_ops/dctcp_ssthresh")
+__u32 BPF_PROG(dctcp_ssthresh, struct sock *sk)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ ca->loss_cwnd = tp->snd_cwnd;
+ return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
+}
+
+SEC("struct_ops/dctcp_update_alpha")
+void BPF_PROG(dctcp_update_alpha, struct sock *sk, __u32 flags)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ /* Expired RTT */
+ if (!before(tp->snd_una, ca->next_seq)) {
+ __u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce;
+ __u32 alpha = ca->dctcp_alpha;
+
+ /* alpha = (1 - g) * alpha + g * F */
+
+ alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
+ if (delivered_ce) {
+ __u32 delivered = tp->delivered - ca->old_delivered;
+
+ /* If dctcp_shift_g == 1, a 32bit value would overflow
+ * after 8 M packets.
+ */
+ delivered_ce <<= (10 - dctcp_shift_g);
+ delivered_ce /= max(1U, delivered);
+
+ alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA);
+ }
+ ca->dctcp_alpha = alpha;
+ dctcp_reset(tp, ca);
+ }
+}
+
+static __always_inline void dctcp_react_to_loss(struct sock *sk)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ ca->loss_cwnd = tp->snd_cwnd;
+ tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+SEC("struct_ops/dctcp_state")
+void BPF_PROG(dctcp_state, struct sock *sk, __u8 new_state)
+{
+ if (new_state == TCP_CA_Recovery &&
+ new_state != BPF_CORE_READ_BITFIELD(inet_csk(sk), icsk_ca_state))
+ dctcp_react_to_loss(sk);
+ /* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+ * one loss-adjustment per RTT.
+ */
+}
+
+static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (ce_state == 1)
+ tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+ else
+ tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+}
+
+/* Minimal DCTP CE state machine:
+ *
+ * S: 0 <- last pkt was non-CE
+ * 1 <- last pkt was CE
+ */
+static __always_inline
+void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt,
+ __u32 *prior_rcv_nxt, __u32 *ce_state)
+{
+ __u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0;
+
+ if (*ce_state != new_ce_state) {
+ /* CE state has changed, force an immediate ACK to
+ * reflect the new CE state. If an ACK was delayed,
+ * send that first to reflect the prior CE state.
+ */
+ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
+ dctcp_ece_ack_cwr(sk, *ce_state);
+ bpf_tcp_send_ack(sk, *prior_rcv_nxt);
+ }
+ inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
+ }
+ *prior_rcv_nxt = tcp_sk(sk)->rcv_nxt;
+ *ce_state = new_ce_state;
+ dctcp_ece_ack_cwr(sk, new_ce_state);
+}
+
+SEC("struct_ops/dctcp_cwnd_event")
+void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev)
+{
+ struct dctcp *ca = inet_csk_ca(sk);
+
+ switch (ev) {
+ case CA_EVENT_ECN_IS_CE:
+ case CA_EVENT_ECN_NO_CE:
+ dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
+ break;
+ case CA_EVENT_LOSS:
+ dctcp_react_to_loss(sk);
+ break;
+ default:
+ /* Don't care for the rest. */
+ break;
+ }
+}
+
+SEC("struct_ops/dctcp_cwnd_undo")
+__u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk)
+{
+ const struct dctcp *ca = inet_csk_ca(sk);
+
+ return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
+SEC("struct_ops/tcp_reno_cong_avoid")
+void BPF_PROG(tcp_reno_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (!tcp_is_cwnd_limited(sk))
+ return;
+
+ /* In "safe" area, increase. */
+ if (tcp_in_slow_start(tp)) {
+ acked = tcp_slow_start(tp, acked);
+ if (!acked)
+ return;
+ }
+ /* In dangerous area, increase slowly. */
+ tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops dctcp_nouse = {
+ .init = (void *)dctcp_init,
+ .set_state = (void *)dctcp_state,
+ .flags = TCP_CONG_NEEDS_ECN,
+ .name = "bpf_dctcp_nouse",
+};
+
+SEC(".struct_ops")
+struct tcp_congestion_ops dctcp = {
+ .init = (void *)dctcp_init,
+ .in_ack_event = (void *)dctcp_update_alpha,
+ .cwnd_event = (void *)dctcp_cwnd_event,
+ .ssthresh = (void *)dctcp_ssthresh,
+ .cong_avoid = (void *)tcp_reno_cong_avoid,
+ .undo_cwnd = (void *)dctcp_cwnd_undo,
+ .set_state = (void *)dctcp_state,
+ .flags = TCP_CONG_NEEDS_ECN,
+ .name = "bpf_dctcp",
+};
#include <sys/socket.h>
#include <linux/if_tunnel.h>
#include <linux/mpls.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
#define PROG(F) SEC(#F) int bpf_func_##F
#include <linux/in6.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define SRC_REWRITE_IP4 0x7f000004U
#define DST_REWRITE_IP4 0x7f000001U
#include <linux/in6.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define SRC_REWRITE_IP6_0 0
#define SRC_REWRITE_IP6_1 0
#include <linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("cgroup/dev")
int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx)
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_trace_helpers.h"
char _license[] SEC("license") = "GPL";
__u64 test1_result = 0;
-BPF_TRACE_1("fentry/bpf_fentry_test1", test1, int, a)
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test1, int a)
{
test1_result = a == 1;
return 0;
}
__u64 test2_result = 0;
-BPF_TRACE_2("fentry/bpf_fentry_test2", test2, int, a, __u64, b)
+SEC("fentry/bpf_fentry_test2")
+int BPF_PROG(test2, int a, __u64 b)
{
test2_result = a == 2 && b == 3;
return 0;
}
__u64 test3_result = 0;
-BPF_TRACE_3("fentry/bpf_fentry_test3", test3, char, a, int, b, __u64, c)
+SEC("fentry/bpf_fentry_test3")
+int BPF_PROG(test3, char a, int b, __u64 c)
{
test3_result = a == 4 && b == 5 && c == 6;
return 0;
}
__u64 test4_result = 0;
-BPF_TRACE_4("fentry/bpf_fentry_test4", test4,
- void *, a, char, b, int, c, __u64, d)
+SEC("fentry/bpf_fentry_test4")
+int BPF_PROG(test4, void *a, char b, int c, __u64 d)
{
test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10;
return 0;
}
__u64 test5_result = 0;
-BPF_TRACE_5("fentry/bpf_fentry_test5", test5,
- __u64, a, void *, b, short, c, int, d, __u64, e)
+SEC("fentry/bpf_fentry_test5")
+int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e)
{
test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 &&
e == 15;
}
__u64 test6_result = 0;
-BPF_TRACE_6("fentry/bpf_fentry_test6", test6,
- __u64, a, void *, b, short, c, int, d, void *, e, __u64, f)
+SEC("fentry/bpf_fentry_test6")
+int BPF_PROG(test6, __u64 a, void *b, short c, int d, void * e, __u64 f)
{
test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
e == (void *)20 && f == 21;
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
+#include <linux/stddef.h>
+#include <linux/ipv6.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "bpf_trace_helpers.h"
struct sk_buff {
};
__u64 test_result = 0;
-BPF_TRACE_2("fexit/test_pkt_access", test_main,
- struct sk_buff *, skb, int, ret)
+SEC("fexit/test_pkt_access")
+int BPF_PROG(test_main, struct sk_buff *skb, int ret)
{
int len;
}
__u64 test_result_subprog1 = 0;
-BPF_TRACE_2("fexit/test_pkt_access_subprog1", test_subprog1,
- struct sk_buff *, skb, int, ret)
+SEC("fexit/test_pkt_access_subprog1")
+int BPF_PROG(test_subprog1, struct sk_buff *skb, int ret)
{
int len;
test_result_subprog2 = 1;
return 0;
}
+
+__u64 test_result_subprog3 = 0;
+SEC("fexit/test_pkt_access_subprog3")
+int BPF_PROG(test_subprog3, int val, struct sk_buff *skb, int ret)
+{
+ int len;
+
+ __builtin_preserve_access_index(({
+ len = skb->len;
+ }));
+ if (len != 74 || ret != 74 * val || val != 3)
+ return 0;
+ test_result_subprog3 = 1;
+ return 0;
+}
+
+__u64 test_get_skb_len = 0;
+SEC("freplace/get_skb_len")
+int new_get_skb_len(struct __sk_buff *skb)
+{
+ int len = skb->len;
+
+ if (len != 74)
+ return 0;
+ test_get_skb_len = 1;
+ return 74; /* original get_skb_len() returns skb->len */
+}
+
+__u64 test_get_skb_ifindex = 0;
+SEC("freplace/get_skb_ifindex")
+int new_get_skb_ifindex(int val, struct __sk_buff *skb, int var)
+{
+ void *data_end = (void *)(long)skb->data_end;
+ void *data = (void *)(long)skb->data;
+ struct ipv6hdr ip6, *ip6p;
+ int ifindex = skb->ifindex;
+ __u32 eth_proto;
+ __u32 nh_off;
+
+ /* check that BPF extension can read packet via direct packet access */
+ if (data + 14 + sizeof(ip6) > data_end)
+ return 0;
+ ip6p = data + 14;
+
+ if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123))
+ return 0;
+
+ /* check that legacy packet access helper works too */
+ if (bpf_skb_load_bytes(skb, 14, &ip6, sizeof(ip6)) < 0)
+ return 0;
+ ip6p = &ip6;
+ if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123))
+ return 0;
+
+ if (ifindex != 1 || val != 3 || var != 1)
+ return 0;
+ test_get_skb_ifindex = 1;
+ return 3; /* original get_skb_ifindex() returns val * ifindex * var */
+}
+
+volatile __u64 test_get_constant = 0;
+SEC("freplace/get_constant")
+int new_get_constant(long val)
+{
+ if (val != 123)
+ return 0;
+ test_get_constant = 1;
+ return test_get_constant; /* original get_constant() returns val - 122 */
+}
char _license[] SEC("license") = "GPL";
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_trace_helpers.h"
struct sk_buff {
};
__u64 test_result = 0;
-BPF_TRACE_2("fexit/test_pkt_md_access", test_main2,
- struct sk_buff *, skb, int, ret)
+
+SEC("fexit/test_pkt_md_access")
+int BPF_PROG(test_main2, struct sk_buff *skb, int ret)
{
int len;
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_trace_helpers.h"
char _license[] SEC("license") = "GPL";
__u64 test1_result = 0;
-BPF_TRACE_2("fexit/bpf_fentry_test1", test1, int, a, int, ret)
+SEC("fexit/bpf_fentry_test1")
+int BPF_PROG(test1, int a, int ret)
{
test1_result = a == 1 && ret == 2;
return 0;
}
__u64 test2_result = 0;
-BPF_TRACE_3("fexit/bpf_fentry_test2", test2, int, a, __u64, b, int, ret)
+SEC("fexit/bpf_fentry_test2")
+int BPF_PROG(test2, int a, __u64 b, int ret)
{
test2_result = a == 2 && b == 3 && ret == 5;
return 0;
}
__u64 test3_result = 0;
-BPF_TRACE_4("fexit/bpf_fentry_test3", test3, char, a, int, b, __u64, c, int, ret)
+SEC("fexit/bpf_fentry_test3")
+int BPF_PROG(test3, char a, int b, __u64 c, int ret)
{
test3_result = a == 4 && b == 5 && c == 6 && ret == 15;
return 0;
}
__u64 test4_result = 0;
-BPF_TRACE_5("fexit/bpf_fentry_test4", test4,
- void *, a, char, b, int, c, __u64, d, int, ret)
+SEC("fexit/bpf_fentry_test4")
+int BPF_PROG(test4, void *a, char b, int c, __u64 d, int ret)
{
-
test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10 &&
ret == 34;
return 0;
}
__u64 test5_result = 0;
-BPF_TRACE_6("fexit/bpf_fentry_test5", test5,
- __u64, a, void *, b, short, c, int, d, __u64, e, int, ret)
+SEC("fexit/bpf_fentry_test5")
+int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e, int ret)
{
test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 &&
e == 15 && ret == 65;
}
__u64 test6_result = 0;
-BPF_TRACE_7("fexit/bpf_fentry_test6", test6,
- __u64, a, void *, b, short, c, int, d, void *, e, __u64, f,
- int, ret)
+SEC("fexit/bpf_fentry_test6")
+int BPF_PROG(test6, __u64 a, void *b, short c, int d, void *e, __u64 f, int ret)
{
test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
e == (void *)20 && f == 21 && ret == 111;
// Copyright (c) 2018 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
#include <stdbool.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "bpf_trace_helpers.h"
char _license[] SEC("license") = "GPL";
/* TRACE_EVENT(kfree_skb,
* TP_PROTO(struct sk_buff *skb, void *location),
*/
-BPF_TRACE_2("tp_btf/kfree_skb", trace_kfree_skb,
- struct sk_buff *, skb, void *, location)
+SEC("tp_btf/kfree_skb")
+int BPF_PROG(trace_kfree_skb, struct sk_buff *skb, void *location)
{
struct net_device *dev;
struct callback_head *ptr;
bool fexit_test_ok;
} result;
-BPF_TRACE_3("fentry/eth_type_trans", fentry_eth_type_trans,
- struct sk_buff *, skb, struct net_device *, dev,
- unsigned short, protocol)
+SEC("fentry/eth_type_trans")
+int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, struct net_device *dev,
+ unsigned short protocol)
{
int len, ifindex;
return 0;
}
-BPF_TRACE_3("fexit/eth_type_trans", fexit_eth_type_trans,
- struct sk_buff *, skb, struct net_device *, dev,
- unsigned short, protocol)
+SEC("fexit/eth_type_trans")
+int BPF_PROG(fexit_eth_type_trans, struct sk_buff *skb, struct net_device *dev,
+ unsigned short protocol)
{
int len, ifindex;
#include <stddef.h>
#include <stdbool.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
char _license[] SEC("license") = "GPL";
#include <stddef.h>
#include <stdbool.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
char _license[] SEC("license") = "GPL";
#include <stddef.h>
#include <stdbool.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
char _license[] SEC("license") = "GPL";
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define barrier() __asm__ __volatile__("": : :"memory")
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "netcnt_common.h"
#define MAX_BPS (3 * 1024 * 1024)
#include <stddef.h>
#include <stdbool.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define FUNCTION_NAME_LEN 64
#define FILE_NAME_LEN 128
__uint(value_size, sizeof(long long) * 127);
} stackmap SEC(".maps");
-static __always_inline int __on_event(struct pt_regs *ctx)
+#ifdef GLOBAL_FUNC
+__attribute__((noinline))
+#else
+static __always_inline
+#endif
+int __on_event(struct bpf_raw_tracepoint_args *ctx)
{
uint64_t pid_tgid = bpf_get_current_pid_tgid();
pid_t pid = (pid_t)(pid_tgid >> 32);
}
SEC("raw_tracepoint/kfree_skb")
-int on_event(struct pt_regs* ctx)
+int on_event(struct bpf_raw_tracepoint_args* ctx)
{
int i, ret = 0;
ret |= __on_event(ctx);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define STACK_MAX_LEN 50
+#define GLOBAL_FUNC
+#include "pyperf.h"
/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct bpf_map_def SEC("maps") htab = {
.type = BPF_MAP_TYPE_HASH,
#include <linux/bpf.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define SRC1_IP4 0xAC100001U /* 172.16.0.1 */
#define SRC2_IP4 0x00000000U
#include <linux/bpf.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define SRC_REWRITE_IP6_0 0
#define SRC_REWRITE_IP6_1 0
#include <linux/bpf.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
struct socket_cookie {
__u64 cookie_key;
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1;
// SPDX-License-Identifier: GPL-2.0
#include <netinet/in.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1;
#include <netinet/in.h>
#include <netinet/tcp.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1;
#include <linux/ptrace.h>
#include <linux/sched.h>
#include <linux/types.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
typedef uint32_t pid_t;
struct task_struct {};
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1;
*/
#include <linux/bpf.h>
#include <linux/if_ether.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
#include <linux/ptrace.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int kprobe_res = 0;
int kretprobe_res = 0;
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
int _version SEC("version") = 1;
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "bpf_legacy.h"
int _version SEC("version") = 1;
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
#include <stdbool.h>
#include <linux/ptrace.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* non-existing BPF helper, to test dead code elimination */
static int (*bpf_missing_helper)(const void *arg1, int arg2) = (void *) 999;
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
-#include "bpf_core_read.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
char _license[] SEC("license") = "GPL";
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* Permit pretty deep stack traces */
#define MAX_STACK_RAWTP 100
#include <linux/pkt_cls.h>
#include <string.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#ifndef MAX_STACK
+#define MAX_STACK (512 - 3 * 32 + 8)
+#endif
+
+static __attribute__ ((noinline))
+int f0(int var, struct __sk_buff *skb)
+{
+ return skb->len;
+}
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+ volatile char buf[MAX_STACK] = {};
+
+ return f0(0, skb) + skb->len;
+}
+
+int f3(int, struct __sk_buff *skb, int);
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+ return f1(skb) + f3(val, skb, 1);
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb, int var)
+{
+ volatile char buf[MAX_STACK] = {};
+
+ return skb->ifindex * val * var;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+ return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#define MAX_STACK (512 - 3 * 32)
+#include "test_global_func1.c"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+ return skb->len;
+}
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+ return f1(skb) + val;
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb, int var)
+{
+ return f2(var, skb) + val;
+}
+
+__attribute__ ((noinline))
+int f4(struct __sk_buff *skb)
+{
+ return f3(1, skb, 2);
+}
+
+__attribute__ ((noinline))
+int f5(struct __sk_buff *skb)
+{
+ return f4(skb);
+}
+
+__attribute__ ((noinline))
+int f6(struct __sk_buff *skb)
+{
+ return f5(skb);
+}
+
+__attribute__ ((noinline))
+int f7(struct __sk_buff *skb)
+{
+ return f6(skb);
+}
+
+#ifndef NO_FN8
+__attribute__ ((noinline))
+int f8(struct __sk_buff *skb)
+{
+ return f7(skb);
+}
+#endif
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+#ifndef NO_FN8
+ return f8(skb);
+#else
+ return f7(skb);
+#endif
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#define NO_FN8
+#include "test_global_func3.c"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+ return skb->len;
+}
+
+int f3(int, struct __sk_buff *skb);
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+ return f1(skb) + f3(val, (void *)&val); /* type mismatch */
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb)
+{
+ return skb->ifindex * val;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+ return f1(skb) + f2(2, skb) + f3(3, skb);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+ return skb->len;
+}
+
+int f3(int, struct __sk_buff *skb);
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+ return f1(skb) + f3(val, skb + 1); /* type mismatch */
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb)
+{
+ return skb->ifindex * val;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+ return f1(skb) + f2(2, skb) + f3(3, skb);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__attribute__ ((noinline))
+void foo(struct __sk_buff *skb)
+{
+ skb->tc_index = 0;
+}
+
+SEC("classifier/test")
+int test_cls(struct __sk_buff *skb)
+{
+ foo(skb);
+ return 0;
+}
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "test_iptunnel_common.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#include "test_iptunnel_common.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
#include <linux/bpf.h>
#include <linux/lirc.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("lirc_mode2")
int bpf_decoder(unsigned int *sample)
#include <linux/bpf.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
struct grehdr {
__be16 flags;
#include <errno.h>
#include <linux/seg6_local.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
/* Packet parsing state machine helpers. */
#define cursor_advance(_cursor, _len) \
#include <stddef.h>
#include <linux/bpf.h>
#include <linux/types.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define VAR_NUM 16
#include <linux/bpf.h>
#include <stdint.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
#include <stddef.h>
#include <linux/bpf.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* It is a dumb bpf program such that it must have no
* issue to be loaded since testing the verifier is
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
+#include <stdbool.h>
+#include <stddef.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <linux/ptrace.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
#include "bpf_trace_helpers.h"
+struct task_struct;
+
SEC("kprobe/__set_task_comm")
-int prog1(struct pt_regs *ctx)
+int BPF_KPROBE(prog1, struct task_struct *tsk, const char *buf, bool exec)
{
- return 0;
+ return !tsk;
}
SEC("kretprobe/__set_task_comm")
-int prog2(struct pt_regs *ctx)
+int BPF_KRETPROBE(prog2,
+ struct task_struct *tsk, const char *buf, bool exec,
+ int ret)
{
- return 0;
+ return !PT_REGS_PARM1(ctx) && ret;
}
SEC("raw_tp/task_rename")
int prog3(struct bpf_raw_tracepoint_args *ctx)
{
- return 0;
+ return !ctx->args[0];
}
-struct task_struct;
-BPF_TRACE_3("fentry/__set_task_comm", prog4,
- struct task_struct *, tsk, const char *, buf, __u8, exec)
+SEC("fentry/__set_task_comm")
+int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec)
{
- return 0;
+ return !tsk;
}
-BPF_TRACE_3("fexit/__set_task_comm", prog5,
- struct task_struct *, tsk, const char *, buf, __u8, exec)
+SEC("fexit/__set_task_comm")
+int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec)
{
- return 0;
+ return !tsk;
}
char _license[] SEC("license") = "GPL";
#include <linux/ptrace.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_trace_helpers.h"
struct {
__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
} perf_buf_map SEC(".maps");
SEC("kprobe/sys_nanosleep")
-int handle_sys_nanosleep_entry(struct pt_regs *ctx)
+int BPF_KPROBE(handle_sys_nanosleep_entry)
{
int cpu = bpf_get_smp_processor_id();
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define barrier() __asm__ __volatile__("": : :"memory")
int _version SEC("version") = 1;
return skb->len * val;
}
+#define MAX_STACK (512 - 2 * 32)
+
+__attribute__ ((noinline))
+int get_skb_len(struct __sk_buff *skb)
+{
+ volatile char buf[MAX_STACK] = {};
+
+ return skb->len;
+}
+
+__attribute__ ((noinline))
+int get_constant(long val)
+{
+ return val - 122;
+}
+
+int get_skb_ifindex(int, struct __sk_buff *skb, int);
+
+__attribute__ ((noinline))
+int test_pkt_access_subprog3(int val, struct __sk_buff *skb)
+{
+ return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123));
+}
+
+__attribute__ ((noinline))
+int get_skb_ifindex(int val, struct __sk_buff *skb, int var)
+{
+ volatile char buf[MAX_STACK] = {};
+
+ return skb->ifindex * val * var;
+}
+
SEC("classifier/test_pkt_access")
int test_pkt_access(struct __sk_buff *skb)
{
return TC_ACT_SHOT;
if (test_pkt_access_subprog2(2, skb) != skb->len * 2)
return TC_ACT_SHOT;
+ if (test_pkt_access_subprog3(3, skb) != skb->len * 3 * skb->ifindex)
+ return TC_ACT_SHOT;
if (tcp) {
if (((void *)(tcp) + 20) > data_end || proto != 6)
return TC_ACT_SHOT;
#include <string.h>
#include <linux/bpf.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
#include <netinet/in.h>
-#include "bpf_helpers.h"
-#include "bpf_tracing.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_trace_helpers.h"
static struct sockaddr_in old;
SEC("kprobe/__sys_connect")
-int handle_sys_connect(struct pt_regs *ctx)
+int BPF_KPROBE(handle_sys_connect)
{
void *ptr = (void *)PT_REGS_PARM2(ctx);
struct sockaddr_in new;
#include <linux/if_ether.h>
#include <linux/ip.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
#include <linux/ptrace.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
static volatile const struct {
unsigned a[4];
#include <errno.h>
#include <linux/seg6_local.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
/* Packet parsing state machine helpers. */
#define cursor_advance(_cursor, _len) \
#include <linux/types.h>
#include <linux/if_ether.h>
-#include "bpf_endian.h"
-#include "bpf_helpers.h"
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
#include "test_select_reuseport_common.h"
int _version SEC("version") = 1;
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
-
-struct {
- __uint(type, BPF_MAP_TYPE_ARRAY);
- __uint(max_entries, 1);
- __type(key, __u32);
- __type(value, __u64);
-} info_map SEC(".maps");
-
-struct {
- __uint(type, BPF_MAP_TYPE_ARRAY);
- __uint(max_entries, 1);
- __type(key, __u32);
- __type(value, __u64);
-} status_map SEC(".maps");
-
-SEC("send_signal_demo")
-int bpf_send_signal_test(void *ctx)
+#include <bpf/bpf_helpers.h>
+
+__u32 sig = 0, pid = 0, status = 0, signal_thread = 0;
+
+static __always_inline int bpf_send_signal_test(void *ctx)
{
- __u64 *info_val, *status_val;
- __u32 key = 0, pid, sig;
int ret;
- status_val = bpf_map_lookup_elem(&status_map, &key);
- if (!status_val || *status_val != 0)
- return 0;
-
- info_val = bpf_map_lookup_elem(&info_map, &key);
- if (!info_val || *info_val == 0)
+ if (status != 0 || sig == 0 || pid == 0)
return 0;
- sig = *info_val >> 32;
- pid = *info_val & 0xffffFFFF;
-
if ((bpf_get_current_pid_tgid() >> 32) == pid) {
- ret = bpf_send_signal(sig);
+ if (signal_thread)
+ ret = bpf_send_signal_thread(sig);
+ else
+ ret = bpf_send_signal(sig);
if (ret == 0)
- *status_val = 1;
+ status = 1;
}
return 0;
}
+
+SEC("tracepoint/syscalls/sys_enter_nanosleep")
+int send_signal_tp(void *ctx)
+{
+ return bpf_send_signal_test(ctx);
+}
+
+SEC("perf_event")
+int send_signal_perf(void *ctx)
+{
+ return bpf_send_signal_test(ctx);
+}
+
char __license[] SEC("license") = "GPL";
#include <linux/pkt_cls.h>
#include <linux/tcp.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
int _version SEC("version") = 1;
char _license[] SEC("license") = "GPL";
#include <string.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define NUM_CGROUP_LEVELS 4
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
char _license[] SEC("license") = "GPL";
#include <stdbool.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct s {
int a;
#include <netinet/in.h>
#include <stdbool.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
enum bpf_addr_array_idx {
ADDR_SRV_IDX,
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
#include <linux/version.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct hmap_elem {
volatile int cnt;
// Copyright (c) 2018 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#ifndef PERF_MAX_STACK_DEPTH
#define PERF_MAX_STACK_DEPTH 127
// Copyright (c) 2018 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#ifndef PERF_MAX_STACK_DEPTH
#define PERF_MAX_STACK_DEPTH 127
#include <linux/stddef.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#ifndef ARRAY_SIZE
#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
#include <linux/stddef.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#ifndef ARRAY_SIZE
#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
#include <linux/stddef.h>
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */
#define MAX_ULONG_STR_LEN 0xF
#include <linux/ip.h>
#include <linux/pkt_cls.h>
#include <linux/tcp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
/* the maximum delay we are willing to add (drop packets beyond that) */
#define TIME_HORIZON_NS (2000 * 1000 * 1000)
#include <linux/pkt_cls.h>
#include <linux/types.h>
-#include "bpf_endian.h"
-#include "bpf_helpers.h"
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
static const int cfg_port = 8000;
#include <sys/socket.h>
#include <linux/tcp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
struct bpf_map_def SEC("maps") results = {
.type = BPF_MAP_TYPE_ARRAY,
#include <linux/ipv6.h>
#include <linux/version.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define _(P) ({typeof(P) val = 0; bpf_probe_read_kernel(&val, sizeof(val), &P); val;})
#define TCP_ESTATS_MAGIC 0xBAADBEEF
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/tcp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "test_tcpbpf.h"
struct {
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/tcp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "test_tcpnotify.h"
struct {
// Copyright (c) 2017 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
#include <linux/socket.h>
#include <linux/pkt_cls.h>
#include <linux/erspan.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#define ERROR(ret) do {\
char fmt[] = "ERROR line:%d ret:%d\n";\
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define ATTR __attribute__((noinline))
#include "test_jhash.h"
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define ATTR __always_inline
#include "test_jhash.h"
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define ATTR __attribute__((noinline))
#include "test_jhash.h"
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "test_iptunnel_common.h"
int _version SEC("version") = 1;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_trace_helpers.h"
+
+struct net_device {
+ /* Structure does not need to contain all entries,
+ * as "preserve_access_index" will use BTF to fix this...
+ */
+ int ifindex;
+} __attribute__((preserve_access_index));
+
+struct xdp_rxq_info {
+ /* Structure does not need to contain all entries,
+ * as "preserve_access_index" will use BTF to fix this...
+ */
+ struct net_device *dev;
+ __u32 queue_index;
+} __attribute__((preserve_access_index));
+
+struct xdp_buff {
+ void *data;
+ void *data_end;
+ void *data_meta;
+ void *data_hard_start;
+ unsigned long handle;
+ struct xdp_rxq_info *rxq;
+} __attribute__((preserve_access_index));
+
+__u64 test_result_fentry = 0;
+SEC("fentry/_xdp_tx_iptunnel")
+int BPF_PROG(trace_on_entry, struct xdp_buff *xdp)
+{
+ test_result_fentry = xdp->rxq->dev->ifindex;
+ return 0;
+}
+
+__u64 test_result_fexit = 0;
+SEC("fexit/_xdp_tx_iptunnel")
+int BPF_PROG(trace_on_exit, struct xdp_buff *xdp, int ret)
+{
+ test_result_fexit = ret;
+ return 0;
+}
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "test_iptunnel_common.h"
int _version SEC("version") = 1;
#include <linux/if_ether.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
#define __round_mask(x, y) ((__typeof__(x))((y) - 1))
#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
static __u32 rol32(__u32 word, unsigned int shift)
{
return c;
}
-static __attribute__ ((noinline))
+__attribute__ ((noinline))
u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
{
a += initval;
return c;
}
-static __attribute__ ((noinline))
+__attribute__ ((noinline))
u32 jhash_2words(u32 a, u32 b, u32 initval)
{
return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
* General Public License for more details.
*/
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
int _version SEC("version") = 1;
#include <linux/in.h>
#include <linux/pkt_cls.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
/* linux/if_vlan.h have not exposed this as UAPI, thus mirror some here
*
#define KBUILD_MODNAME "xdp_dummy"
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("xdp_dummy")
int xdp_dummy_prog(struct xdp_md *ctx)
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
struct {
__uint(type, BPF_MAP_TYPE_DEVMAP);
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
-#include "bpf_helpers.h"
+#include <bpf/bpf_helpers.h>
SEC("tx")
int xdp_tx(struct xdp_md *xdp)
#include <linux/if_vlan.h>
#include <linux/ip.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
#include "xdping.h"
if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj)))
return PTR_ERR(obj);
- err = bpf_object__btf_fd(obj);
- if (CHECK(err == -1, "bpf_object__btf_fd: -1"))
- goto done;
-
prog = bpf_program__next(NULL, obj);
if (CHECK(!prog, "Cannot find bpf_prog")) {
err = -1;
/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
#include <iostream>
-#include "libbpf.h"
-#include "bpf.h"
-#include "btf.h"
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
#include "test_core_extern.skel.h"
/* do nothing, just make sure we can link successfully */
#include <stdio.h>
#include <errno.h>
#include <linux/err.h>
-#include "hashmap.h"
+#include "bpf/hashmap.h"
#define CHECK(condition, format...) ({ \
int __ret = !!(condition); \
#include <string.h>
/* defined in test_progs.h */
-struct test_env env;
+struct test_env env = {};
struct prog_test_def {
const char *test_name;
static bool should_run(struct test_selector *sel, int num, const char *name)
{
- if (sel->name && sel->name[0] && !strstr(name, sel->name))
- return false;
+ int i;
+
+ for (i = 0; i < sel->blacklist.cnt; i++) {
+ if (strstr(name, sel->blacklist.strs[i]))
+ return false;
+ }
- if (!sel->num_set)
+ for (i = 0; i < sel->whitelist.cnt; i++) {
+ if (strstr(name, sel->whitelist.strs[i]))
+ return true;
+ }
+
+ if (!sel->whitelist.cnt && !sel->num_set)
return true;
return num < sel->num_set_len && sel->num_set[num];
enum ARG_KEYS {
ARG_TEST_NUM = 'n',
ARG_TEST_NAME = 't',
+ ARG_TEST_NAME_BLACKLIST = 'b',
ARG_VERIFIER_STATS = 's',
ARG_VERBOSE = 'v',
};
static const struct argp_option opts[] = {
{ "num", ARG_TEST_NUM, "NUM", 0,
"Run test number NUM only " },
- { "name", ARG_TEST_NAME, "NAME", 0,
- "Run tests with names containing NAME" },
+ { "name", ARG_TEST_NAME, "NAMES", 0,
+ "Run tests with names containing any string from NAMES list" },
+ { "name-blacklist", ARG_TEST_NAME_BLACKLIST, "NAMES", 0,
+ "Don't run tests with names containing any string from NAMES list" },
{ "verifier-stats", ARG_VERIFIER_STATS, NULL, 0,
"Output verifier statistics", },
{ "verbose", ARG_VERBOSE, "LEVEL", OPTION_ARG_OPTIONAL,
return 0;
}
+static int parse_str_list(const char *s, struct str_set *set)
+{
+ char *input, *state = NULL, *next, **tmp, **strs = NULL;
+ int cnt = 0;
+
+ input = strdup(s);
+ if (!input)
+ return -ENOMEM;
+
+ set->cnt = 0;
+ set->strs = NULL;
+
+ while ((next = strtok_r(state ? NULL : input, ",", &state))) {
+ tmp = realloc(strs, sizeof(*strs) * (cnt + 1));
+ if (!tmp)
+ goto err;
+ strs = tmp;
+
+ strs[cnt] = strdup(next);
+ if (!strs[cnt])
+ goto err;
+
+ cnt++;
+ }
+
+ set->cnt = cnt;
+ set->strs = (const char **)strs;
+ free(input);
+ return 0;
+err:
+ free(strs);
+ free(input);
+ return -ENOMEM;
+}
+
int parse_num_list(const char *s, struct test_selector *sel)
{
int i, set_len = 0, num, start = 0, end = -1;
if (subtest_str) {
*subtest_str = '\0';
- env->subtest_selector.name = strdup(subtest_str + 1);
- if (!env->subtest_selector.name)
+ if (parse_str_list(subtest_str + 1,
+ &env->subtest_selector.whitelist))
+ return -ENOMEM;
+ }
+ if (parse_str_list(arg, &env->test_selector.whitelist))
+ return -ENOMEM;
+ break;
+ }
+ case ARG_TEST_NAME_BLACKLIST: {
+ char *subtest_str = strchr(arg, '/');
+
+ if (subtest_str) {
+ *subtest_str = '\0';
+ if (parse_str_list(subtest_str + 1,
+ &env->subtest_selector.blacklist))
return -ENOMEM;
}
- env->test_selector.name = strdup(arg);
- if (!env->test_selector.name)
+ if (parse_str_list(arg, &env->test_selector.blacklist))
return -ENOMEM;
break;
}
printf("Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
+ free(env.test_selector.blacklist.strs);
+ free(env.test_selector.whitelist.strs);
free(env.test_selector.num_set);
+ free(env.subtest_selector.blacklist.strs);
+ free(env.subtest_selector.whitelist.strs);
free(env.subtest_selector.num_set);
return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
#include "test_iptunnel_common.h"
#include "bpf_util.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
#include "trace_helpers.h"
#include "flow_dissector_load.h"
VERBOSE_SUPER,
};
+struct str_set {
+ const char **strs;
+ int cnt;
+};
+
struct test_selector {
- const char *name;
+ struct str_set whitelist;
+ struct str_set blacklist;
bool *num_set;
int num_set_len;
};
#include <bpf/bpf.h>
#include "cgroup_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
#include "bpf_rlimit.h"
#include "bpf_util.h"
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
#include <sys/socket.h>
-#include "bpf_helpers.h"
-#include "bpf_endian.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
/* Sockmap sample program connects a client and a backend together
* using cgroups.
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
-#include "bpf_endian.h"
+#include <bpf/bpf_endian.h>
#include "bpf_rlimit.h"
#include "bpf_util.h"
#include "cgroup_helpers.h"
#ifndef __TRACE_HELPER_H
#define __TRACE_HELPER_H
-#include <libbpf.h>
+#include <bpf/libbpf.h>
struct ksym {
long addr;
git.samba.org / sfrench / cifs-2.6.git / commitdiff