提交 1b80f86e 编写于 作者: D David S. Miller

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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-04-21

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

The main changes are:

1) Initial work on BPF Type Format (BTF) is added, which is a meta
   data format which describes the data types of BPF programs / maps.
   BTF has its roots from CTF (Compact C-Type format) with a number
   of changes to it. First use case is to provide a generic pretty
   print capability for BPF maps inspection, later work will also
   add BTF to bpftool. pahole support to convert dwarf to BTF will
   be upstreamed as well (https://github.com/iamkafai/pahole/tree/btf),
   from Martin.

2) Add a new xdp_bpf_adjust_tail() BPF helper for XDP that allows
   for changing the data_end pointer. Only shrinking is currently
   supported which helps for crafting ICMP control messages. Minor
   changes in drivers have been added where needed so they recalc
   the packet's length also when data_end was adjusted, from Nikita.

3) Improve bpftool to make it easier to feed hex bytes via cmdline
   for map operations, from Quentin.

4) Add support for various missing BPF prog types and attach types
   that have been added to kernel recently but neither to bpftool
   nor libbpf yet. Doc and bash completion updates have been added
   as well for bpftool, from Andrey.

5) Proper fix for avoiding to leak info stored in frame data on page
   reuse for the two bpf_xdp_adjust_{head,meta} helpers by disallowing
   to move the pointers into struct xdp_frame area, from Jesper.

6) Follow-up compile fix from BTF in order to include stdbool.h in
   libbpf, from Björn.

7) Few fixes in BPF sample code, that is, a typo on the netdevice
   in a comment and fixup proper dump of XDP action code in the
   tracepoint exception, from Wang and Jesper.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
...@@ -113,10 +113,10 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, ...@@ -113,10 +113,10 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
if (tx_avail != bp->tx_ring_size) if (tx_avail != bp->tx_ring_size)
*event &= ~BNXT_RX_EVENT; *event &= ~BNXT_RX_EVENT;
*len = xdp.data_end - xdp.data;
if (orig_data != xdp.data) { if (orig_data != xdp.data) {
offset = xdp.data - xdp.data_hard_start; offset = xdp.data - xdp.data_hard_start;
*data_ptr = xdp.data_hard_start + offset; *data_ptr = xdp.data_hard_start + offset;
*len = xdp.data_end - xdp.data;
} }
switch (act) { switch (act) {
case XDP_PASS: case XDP_PASS:
......
...@@ -538,9 +538,9 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, ...@@ -538,9 +538,9 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
action = bpf_prog_run_xdp(prog, &xdp); action = bpf_prog_run_xdp(prog, &xdp);
rcu_read_unlock(); rcu_read_unlock();
len = xdp.data_end - xdp.data;
/* Check if XDP program has changed headers */ /* Check if XDP program has changed headers */
if (orig_data != xdp.data) { if (orig_data != xdp.data) {
len = xdp.data_end - xdp.data;
offset = orig_data - xdp.data; offset = orig_data - xdp.data;
dma_addr -= offset; dma_addr -= offset;
} }
......
...@@ -775,8 +775,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud ...@@ -775,8 +775,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
act = bpf_prog_run_xdp(xdp_prog, &xdp); act = bpf_prog_run_xdp(xdp_prog, &xdp);
length = xdp.data_end - xdp.data;
if (xdp.data != orig_data) { if (xdp.data != orig_data) {
length = xdp.data_end - xdp.data;
frags[0].page_offset = xdp.data - frags[0].page_offset = xdp.data -
xdp.data_hard_start; xdp.data_hard_start;
va = xdp.data; va = xdp.data;
......
...@@ -1722,7 +1722,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) ...@@ -1722,7 +1722,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
act = bpf_prog_run_xdp(xdp_prog, &xdp); act = bpf_prog_run_xdp(xdp_prog, &xdp);
pkt_len -= xdp.data - orig_data; pkt_len = xdp.data_end - xdp.data;
pkt_off += xdp.data - orig_data; pkt_off += xdp.data - orig_data;
switch (act) { switch (act) {
......
...@@ -1690,6 +1690,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, ...@@ -1690,6 +1690,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
return NULL; return NULL;
case XDP_PASS: case XDP_PASS:
delta = orig_data - xdp.data; delta = orig_data - xdp.data;
len = xdp.data_end - xdp.data;
break; break;
default: default:
bpf_warn_invalid_xdp_action(act); bpf_warn_invalid_xdp_action(act);
...@@ -1710,7 +1711,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, ...@@ -1710,7 +1711,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
} }
skb_reserve(skb, pad - delta); skb_reserve(skb, pad - delta);
skb_put(skb, len + delta); skb_put(skb, len);
get_page(alloc_frag->page); get_page(alloc_frag->page);
alloc_frag->offset += buflen; alloc_frag->offset += buflen;
......
...@@ -606,6 +606,7 @@ static struct sk_buff *receive_small(struct net_device *dev, ...@@ -606,6 +606,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
case XDP_PASS: case XDP_PASS:
/* Recalculate length in case bpf program changed it */ /* Recalculate length in case bpf program changed it */
delta = orig_data - xdp.data; delta = orig_data - xdp.data;
len = xdp.data_end - xdp.data;
break; break;
case XDP_TX: case XDP_TX:
xdpf = convert_to_xdp_frame(&xdp); xdpf = convert_to_xdp_frame(&xdp);
...@@ -642,7 +643,7 @@ static struct sk_buff *receive_small(struct net_device *dev, ...@@ -642,7 +643,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
goto err; goto err;
} }
skb_reserve(skb, headroom - delta); skb_reserve(skb, headroom - delta);
skb_put(skb, len + delta); skb_put(skb, len);
if (!delta) { if (!delta) {
buf += header_offset; buf += header_offset;
memcpy(skb_vnet_hdr(skb), buf, vi->hdr_len); memcpy(skb_vnet_hdr(skb), buf, vi->hdr_len);
...@@ -757,6 +758,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, ...@@ -757,6 +758,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
offset = xdp.data - offset = xdp.data -
page_address(xdp_page) - vi->hdr_len; page_address(xdp_page) - vi->hdr_len;
/* recalculate len if xdp.data or xdp.data_end were
* adjusted
*/
len = xdp.data_end - xdp.data;
/* We can only create skb based on xdp_page. */ /* We can only create skb based on xdp_page. */
if (unlikely(xdp_page != page)) { if (unlikely(xdp_page != page)) {
rcu_read_unlock(); rcu_read_unlock();
......
...@@ -22,6 +22,8 @@ struct perf_event; ...@@ -22,6 +22,8 @@ struct perf_event;
struct bpf_prog; struct bpf_prog;
struct bpf_map; struct bpf_map;
struct sock; struct sock;
struct seq_file;
struct btf;
/* map is generic key/value storage optionally accesible by eBPF programs */ /* map is generic key/value storage optionally accesible by eBPF programs */
struct bpf_map_ops { struct bpf_map_ops {
...@@ -43,10 +45,14 @@ struct bpf_map_ops { ...@@ -43,10 +45,14 @@ struct bpf_map_ops {
void (*map_fd_put_ptr)(void *ptr); void (*map_fd_put_ptr)(void *ptr);
u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
u32 (*map_fd_sys_lookup_elem)(void *ptr); u32 (*map_fd_sys_lookup_elem)(void *ptr);
void (*map_seq_show_elem)(struct bpf_map *map, void *key,
struct seq_file *m);
int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf,
u32 key_type_id, u32 value_type_id);
}; };
struct bpf_map { struct bpf_map {
/* 1st cacheline with read-mostly members of which some /* The first two cachelines with read-mostly members of which some
* are also accessed in fast-path (e.g. ops, max_entries). * are also accessed in fast-path (e.g. ops, max_entries).
*/ */
const struct bpf_map_ops *ops ____cacheline_aligned; const struct bpf_map_ops *ops ____cacheline_aligned;
...@@ -62,10 +68,13 @@ struct bpf_map { ...@@ -62,10 +68,13 @@ struct bpf_map {
u32 pages; u32 pages;
u32 id; u32 id;
int numa_node; int numa_node;
u32 btf_key_id;
u32 btf_value_id;
struct btf *btf;
bool unpriv_array; bool unpriv_array;
/* 7 bytes hole */ /* 55 bytes hole */
/* 2nd cacheline with misc members to avoid false sharing /* The 3rd and 4th cacheline with misc members to avoid false sharing
* particularly with refcounting. * particularly with refcounting.
*/ */
struct user_struct *user ____cacheline_aligned; struct user_struct *user ____cacheline_aligned;
...@@ -100,6 +109,11 @@ static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) ...@@ -100,6 +109,11 @@ static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map)
return container_of(map, struct bpf_offloaded_map, map); return container_of(map, struct bpf_offloaded_map, map);
} }
static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
{
return map->ops->map_seq_show_elem && map->ops->map_check_btf;
}
extern const struct bpf_map_ops bpf_map_offload_ops; extern const struct bpf_map_ops bpf_map_offload_ops;
/* function argument constraints */ /* function argument constraints */
......
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#ifndef _LINUX_BTF_H
#define _LINUX_BTF_H 1
#include <linux/types.h>
struct btf;
struct btf_type;
union bpf_attr;
extern const struct file_operations btf_fops;
void btf_put(struct btf *btf);
int btf_new_fd(const union bpf_attr *attr);
struct btf *btf_get_by_fd(int fd);
int btf_get_info_by_fd(const struct btf *btf,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
/* Figure out the size of a type_id. If type_id is a modifier
* (e.g. const), it will be resolved to find out the type with size.
*
* For example:
* In describing "const void *", type_id is "const" and "const"
* refers to "void *". The return type will be "void *".
*
* If type_id is a simple "int", then return type will be "int".
*
* @btf: struct btf object
* @type_id: Find out the size of type_id. The type_id of the return
* type is set to *type_id.
* @ret_size: It can be NULL. If not NULL, the size of the return
* type is set to *ret_size.
* Return: The btf_type (resolved to another type with size info if needed).
* NULL is returned if type_id itself does not have size info
* (e.g. void) or it cannot be resolved to another type that
* has size info.
* *type_id and *ret_size will not be changed in the
* NULL return case.
*/
const struct btf_type *btf_type_id_size(const struct btf *btf,
u32 *type_id,
u32 *ret_size);
void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
struct seq_file *m);
#endif
...@@ -95,6 +95,7 @@ enum bpf_cmd { ...@@ -95,6 +95,7 @@ enum bpf_cmd {
BPF_OBJ_GET_INFO_BY_FD, BPF_OBJ_GET_INFO_BY_FD,
BPF_PROG_QUERY, BPF_PROG_QUERY,
BPF_RAW_TRACEPOINT_OPEN, BPF_RAW_TRACEPOINT_OPEN,
BPF_BTF_LOAD,
}; };
enum bpf_map_type { enum bpf_map_type {
...@@ -279,6 +280,9 @@ union bpf_attr { ...@@ -279,6 +280,9 @@ union bpf_attr {
*/ */
char map_name[BPF_OBJ_NAME_LEN]; char map_name[BPF_OBJ_NAME_LEN];
__u32 map_ifindex; /* ifindex of netdev to create on */ __u32 map_ifindex; /* ifindex of netdev to create on */
__u32 btf_fd; /* fd pointing to a BTF type data */
__u32 btf_key_id; /* BTF type_id of the key */
__u32 btf_value_id; /* BTF type_id of the value */
}; };
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
...@@ -363,6 +367,14 @@ union bpf_attr { ...@@ -363,6 +367,14 @@ union bpf_attr {
__u64 name; __u64 name;
__u32 prog_fd; __u32 prog_fd;
} raw_tracepoint; } raw_tracepoint;
struct { /* anonymous struct for BPF_BTF_LOAD */
__aligned_u64 btf;
__aligned_u64 btf_log_buf;
__u32 btf_size;
__u32 btf_log_size;
__u32 btf_log_level;
};
} __attribute__((aligned(8))); } __attribute__((aligned(8)));
/* BPF helper function descriptions: /* BPF helper function descriptions:
...@@ -755,6 +767,13 @@ union bpf_attr { ...@@ -755,6 +767,13 @@ union bpf_attr {
* @addr: pointer to struct sockaddr to bind socket to * @addr: pointer to struct sockaddr to bind socket to
* @addr_len: length of sockaddr structure * @addr_len: length of sockaddr structure
* Return: 0 on success or negative error code * Return: 0 on success or negative error code
*
* int bpf_xdp_adjust_tail(xdp_md, delta)
* Adjust the xdp_md.data_end by delta. Only shrinking of packet's
* size is supported.
* @xdp_md: pointer to xdp_md
* @delta: A negative integer to be added to xdp_md.data_end
* Return: 0 on success or negative on error
*/ */
#define __BPF_FUNC_MAPPER(FN) \ #define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \ FN(unspec), \
...@@ -821,7 +840,8 @@ union bpf_attr { ...@@ -821,7 +840,8 @@ union bpf_attr {
FN(msg_apply_bytes), \ FN(msg_apply_bytes), \
FN(msg_cork_bytes), \ FN(msg_cork_bytes), \
FN(msg_pull_data), \ FN(msg_pull_data), \
FN(bind), FN(bind), \
FN(xdp_adjust_tail),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper /* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call * function eBPF program intends to call
......
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/* Copyright (c) 2018 Facebook */
#ifndef _UAPI__LINUX_BTF_H__
#define _UAPI__LINUX_BTF_H__
#include <linux/types.h>
#define BTF_MAGIC 0xeB9F
#define BTF_MAGIC_SWAP 0x9FeB
#define BTF_VERSION 1
#define BTF_FLAGS_COMPR 0x01
struct btf_header {
__u16 magic;
__u8 version;
__u8 flags;
__u32 parent_label;
__u32 parent_name;
/* All offsets are in bytes relative to the end of this header */
__u32 label_off; /* offset of label section */
__u32 object_off; /* offset of data object section*/
__u32 func_off; /* offset of function section */
__u32 type_off; /* offset of type section */
__u32 str_off; /* offset of string section */
__u32 str_len; /* length of string section */
};
/* Max # of type identifier */
#define BTF_MAX_TYPE 0x7fffffff
/* Max offset into the string section */
#define BTF_MAX_NAME_OFFSET 0x7fffffff
/* Max # of struct/union/enum members or func args */
#define BTF_MAX_VLEN 0xffff
/* The type id is referring to a parent BTF */
#define BTF_TYPE_PARENT(id) (((id) >> 31) & 0x1)
#define BTF_TYPE_ID(id) ((id) & BTF_MAX_TYPE)
/* String is in the ELF string section */
#define BTF_STR_TBL_ELF_ID(ref) (((ref) >> 31) & 0x1)
#define BTF_STR_OFFSET(ref) ((ref) & BTF_MAX_NAME_OFFSET)
struct btf_type {
__u32 name;
/* "info" bits arrangement
* bits 0-15: vlen (e.g. # of struct's members)
* bits 16-23: unused
* bits 24-28: kind (e.g. int, ptr, array...etc)
* bits 29-30: unused
* bits 31: root
*/
__u32 info;
/* "size" is used by INT, ENUM, STRUCT and UNION.
* "size" tells the size of the type it is describing.
*
* "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
* "type" is a type_id referring to another type.
*/
union {
__u32 size;
__u32 type;
};
};
#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f)
#define BTF_INFO_ISROOT(info) (!!(((info) >> 24) & 0x80))
#define BTF_INFO_VLEN(info) ((info) & 0xffff)
#define BTF_KIND_UNKN 0 /* Unknown */
#define BTF_KIND_INT 1 /* Integer */
#define BTF_KIND_PTR 2 /* Pointer */
#define BTF_KIND_ARRAY 3 /* Array */
#define BTF_KIND_STRUCT 4 /* Struct */
#define BTF_KIND_UNION 5 /* Union */
#define BTF_KIND_ENUM 6 /* Enumeration */
#define BTF_KIND_FWD 7 /* Forward */
#define BTF_KIND_TYPEDEF 8 /* Typedef */
#define BTF_KIND_VOLATILE 9 /* Volatile */
#define BTF_KIND_CONST 10 /* Const */
#define BTF_KIND_RESTRICT 11 /* Restrict */
#define BTF_KIND_MAX 11
#define NR_BTF_KINDS 12
/* For some specific BTF_KIND, "struct btf_type" is immediately
* followed by extra data.
*/
/* BTF_KIND_INT is followed by a u32 and the following
* is the 32 bits arrangement:
*/
#define BTF_INT_ENCODING(VAL) (((VAL) & 0xff000000) >> 24)
#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16)
#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff)
/* Attributes stored in the BTF_INT_ENCODING */
#define BTF_INT_SIGNED 0x1
#define BTF_INT_CHAR 0x2
#define BTF_INT_BOOL 0x4
#define BTF_INT_VARARGS 0x8
/* BTF_KIND_ENUM is followed by multiple "struct btf_enum".
* The exact number of btf_enum is stored in the vlen (of the
* info in "struct btf_type").
*/
struct btf_enum {
__u32 name;
__s32 val;
};
/* BTF_KIND_ARRAY is followed by one "struct btf_array" */
struct btf_array {
__u32 type;
__u32 index_type;
__u32 nelems;
};
/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed
* by multiple "struct btf_member". The exact number
* of btf_member is stored in the vlen (of the info in
* "struct btf_type").
*/
struct btf_member {
__u32 name;
__u32 type;
__u32 offset; /* offset in bits */
};
#endif /* _UAPI__LINUX_BTF_H__ */
...@@ -4,6 +4,7 @@ obj-y := core.o ...@@ -4,6 +4,7 @@ obj-y := core.o
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
obj-$(CONFIG_BPF_SYSCALL) += disasm.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o
obj-$(CONFIG_BPF_SYSCALL) += btf.o
ifeq ($(CONFIG_NET),y) ifeq ($(CONFIG_NET),y)
obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += devmap.o
obj-$(CONFIG_BPF_SYSCALL) += cpumap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
......
...@@ -11,11 +11,13 @@ ...@@ -11,11 +11,13 @@
* General Public License for more details. * General Public License for more details.
*/ */
#include <linux/bpf.h> #include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/err.h> #include <linux/err.h>
#include <linux/slab.h> #include <linux/slab.h>
#include <linux/mm.h> #include <linux/mm.h>
#include <linux/filter.h> #include <linux/filter.h>
#include <linux/perf_event.h> #include <linux/perf_event.h>
#include <uapi/linux/btf.h>
#include "map_in_map.h" #include "map_in_map.h"
...@@ -336,6 +338,52 @@ static void array_map_free(struct bpf_map *map) ...@@ -336,6 +338,52 @@ static void array_map_free(struct bpf_map *map)
bpf_map_area_free(array); bpf_map_area_free(array);
} }
static void array_map_seq_show_elem(struct bpf_map *map, void *key,
struct seq_file *m)
{
void *value;
rcu_read_lock();
value = array_map_lookup_elem(map, key);
if (!value) {
rcu_read_unlock();
return;
}
seq_printf(m, "%u: ", *(u32 *)key);
btf_type_seq_show(map->btf, map->btf_value_id, value, m);
seq_puts(m, "\n");
rcu_read_unlock();
}
static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf,
u32 btf_key_id, u32 btf_value_id)
{
const struct btf_type *key_type, *value_type;
u32 key_size, value_size;
u32 int_data;
key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
return -EINVAL;
int_data = *(u32 *)(key_type + 1);
/* bpf array can only take a u32 key. This check makes
* sure that the btf matches the attr used during map_create.
*/
if (BTF_INT_BITS(int_data) != 32 || key_size != 4 ||
BTF_INT_OFFSET(int_data))
return -EINVAL;
value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
if (!value_type || value_size > map->value_size)
return -EINVAL;
return 0;
}
const struct bpf_map_ops array_map_ops = { const struct bpf_map_ops array_map_ops = {
.map_alloc_check = array_map_alloc_check, .map_alloc_check = array_map_alloc_check,
.map_alloc = array_map_alloc, .map_alloc = array_map_alloc,
...@@ -345,6 +393,8 @@ const struct bpf_map_ops array_map_ops = { ...@@ -345,6 +393,8 @@ const struct bpf_map_ops array_map_ops = {
.map_update_elem = array_map_update_elem, .map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem, .map_delete_elem = array_map_delete_elem,
.map_gen_lookup = array_map_gen_lookup, .map_gen_lookup = array_map_gen_lookup,
.map_seq_show_elem = array_map_seq_show_elem,
.map_check_btf = array_map_check_btf,
}; };
const struct bpf_map_ops percpu_array_map_ops = { const struct bpf_map_ops percpu_array_map_ops = {
......
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <uapi/linux/btf.h>
#include <uapi/linux/types.h>
#include <linux/seq_file.h>
#include <linux/compiler.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
#include <linux/bpf_verifier.h>
#include <linux/btf.h>
/* BTF (BPF Type Format) is the meta data format which describes
* the data types of BPF program/map. Hence, it basically focus
* on the C programming language which the modern BPF is primary
* using.
*
* ELF Section:
* ~~~~~~~~~~~
* The BTF data is stored under the ".BTF" ELF section
*
* struct btf_type:
* ~~~~~~~~~~~~~~~
* Each 'struct btf_type' object describes a C data type.
* Depending on the type it is describing, a 'struct btf_type'
* object may be followed by more data. F.e.
* To describe an array, 'struct btf_type' is followed by
* 'struct btf_array'.
*
* 'struct btf_type' and any extra data following it are
* 4 bytes aligned.
*
* Type section:
* ~~~~~~~~~~~~~
* The BTF type section contains a list of 'struct btf_type' objects.
* Each one describes a C type. Recall from the above section
* that a 'struct btf_type' object could be immediately followed by extra
* data in order to desribe some particular C types.
*
* type_id:
* ~~~~~~~
* Each btf_type object is identified by a type_id. The type_id
* is implicitly implied by the location of the btf_type object in
* the BTF type section. The first one has type_id 1. The second
* one has type_id 2...etc. Hence, an earlier btf_type has
* a smaller type_id.
*
* A btf_type object may refer to another btf_type object by using
* type_id (i.e. the "type" in the "struct btf_type").
*
* NOTE that we cannot assume any reference-order.
* A btf_type object can refer to an earlier btf_type object
* but it can also refer to a later btf_type object.
*
* For example, to describe "const void *". A btf_type
* object describing "const" may refer to another btf_type
* object describing "void *". This type-reference is done
* by specifying type_id:
*
* [1] CONST (anon) type_id=2
* [2] PTR (anon) type_id=0
*
* The above is the btf_verifier debug log:
* - Each line started with "[?]" is a btf_type object
* - [?] is the type_id of the btf_type object.
* - CONST/PTR is the BTF_KIND_XXX
* - "(anon)" is the name of the type. It just
* happens that CONST and PTR has no name.
* - type_id=XXX is the 'u32 type' in btf_type
*
* NOTE: "void" has type_id 0
*
* String section:
* ~~~~~~~~~~~~~~
* The BTF string section contains the names used by the type section.
* Each string is referred by an "offset" from the beginning of the
* string section.
*
* Each string is '\0' terminated.
*
* The first character in the string section must be '\0'
* which is used to mean 'anonymous'. Some btf_type may not
* have a name.
*/
/* BTF verification:
*
* To verify BTF data, two passes are needed.
*
* Pass #1
* ~~~~~~~
* The first pass is to collect all btf_type objects to
* an array: "btf->types".
*
* Depending on the C type that a btf_type is describing,
* a btf_type may be followed by extra data. We don't know
* how many btf_type is there, and more importantly we don't
* know where each btf_type is located in the type section.
*
* Without knowing the location of each type_id, most verifications
* cannot be done. e.g. an earlier btf_type may refer to a later
* btf_type (recall the "const void *" above), so we cannot
* check this type-reference in the first pass.
*
* In the first pass, it still does some verifications (e.g.
* checking the name is a valid offset to the string section).
*
* Pass #2
* ~~~~~~~
* The main focus is to resolve a btf_type that is referring
* to another type.
*
* We have to ensure the referring type:
* 1) does exist in the BTF (i.e. in btf->types[])
* 2) does not cause a loop:
* struct A {
* struct B b;
* };
*
* struct B {
* struct A a;
* };
*
* btf_type_needs_resolve() decides if a btf_type needs
* to be resolved.
*
* The needs_resolve type implements the "resolve()" ops which
* essentially does a DFS and detects backedge.
*
* During resolve (or DFS), different C types have different
* "RESOLVED" conditions.
*
* When resolving a BTF_KIND_STRUCT, we need to resolve all its
* members because a member is always referring to another
* type. A struct's member can be treated as "RESOLVED" if
* it is referring to a BTF_KIND_PTR. Otherwise, the
* following valid C struct would be rejected:
*
* struct A {
* int m;
* struct A *a;
* };
*
* When resolving a BTF_KIND_PTR, it needs to keep resolving if
* it is referring to another BTF_KIND_PTR. Otherwise, we cannot
* detect a pointer loop, e.g.:
* BTF_KIND_CONST -> BTF_KIND_PTR -> BTF_KIND_CONST -> BTF_KIND_PTR +
* ^ |
* +-----------------------------------------+
*
*/
#define BITS_PER_U64 (sizeof(u64) * BITS_PER_BYTE)
#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1)
#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK)
#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3)
#define BITS_ROUNDUP_BYTES(bits) \
(BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits))
/* 16MB for 64k structs and each has 16 members and
* a few MB spaces for the string section.
* The hard limit is S32_MAX.
*/
#define BTF_MAX_SIZE (16 * 1024 * 1024)
/* 64k. We can raise it later. The hard limit is S32_MAX. */
#define BTF_MAX_NR_TYPES 65535
#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); \
i++, member++)
struct btf {
union {
struct btf_header *hdr;
void *data;
};
struct btf_type **types;
u32 *resolved_ids;
u32 *resolved_sizes;
const char *strings;
void *nohdr_data;
u32 nr_types;
u32 types_size;
u32 data_size;
refcount_t refcnt;
};
enum verifier_phase {
CHECK_META,
CHECK_TYPE,
};
struct resolve_vertex {
const struct btf_type *t;
u32 type_id;
u16 next_member;
};
enum visit_state {
NOT_VISITED,
VISITED,
RESOLVED,
};
enum resolve_mode {
RESOLVE_TBD, /* To Be Determined */
RESOLVE_PTR, /* Resolving for Pointer */
RESOLVE_STRUCT_OR_ARRAY, /* Resolving for struct/union
* or array
*/
};
#define MAX_RESOLVE_DEPTH 32
struct btf_verifier_env {
struct btf *btf;
u8 *visit_states;
struct resolve_vertex stack[MAX_RESOLVE_DEPTH];
struct bpf_verifier_log log;
u32 log_type_id;
u32 top_stack;
enum verifier_phase phase;
enum resolve_mode resolve_mode;
};
static const char * const btf_kind_str[NR_BTF_KINDS] = {
[BTF_KIND_UNKN] = "UNKNOWN",
[BTF_KIND_INT] = "INT",
[BTF_KIND_PTR] = "PTR",
[BTF_KIND_ARRAY] = "ARRAY",
[BTF_KIND_STRUCT] = "STRUCT",
[BTF_KIND_UNION] = "UNION",
[BTF_KIND_ENUM] = "ENUM",
[BTF_KIND_FWD] = "FWD",
[BTF_KIND_TYPEDEF] = "TYPEDEF",
[BTF_KIND_VOLATILE] = "VOLATILE",
[BTF_KIND_CONST] = "CONST",
[BTF_KIND_RESTRICT] = "RESTRICT",
};
struct btf_kind_operations {
s32 (*check_meta)(struct btf_verifier_env *env,
const struct btf_type *t,
u32 meta_left);
int (*resolve)(struct btf_verifier_env *env,
const struct resolve_vertex *v);
int (*check_member)(struct btf_verifier_env *env,
const struct btf_type *struct_type,
const struct btf_member *member,
const struct btf_type *member_type);
void (*log_details)(struct btf_verifier_env *env,
const struct btf_type *t);
void (*seq_show)(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offsets,
struct seq_file *m);
};
static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS];
static struct btf_type btf_void;
static bool btf_type_is_modifier(const struct btf_type *t)
{
/* Some of them is not strictly a C modifier
* but they are grouped into the same bucket
* for BTF concern:
* A type (t) that refers to another
* type through t->type AND its size cannot
* be determined without following the t->type.
*
* ptr does not fall into this bucket
* because its size is always sizeof(void *).
*/
switch (BTF_INFO_KIND(t->info)) {
case BTF_KIND_TYPEDEF:
case BTF_KIND_VOLATILE:
case BTF_KIND_CONST:
case BTF_KIND_RESTRICT:
return true;
}
return false;
}
static bool btf_type_is_void(const struct btf_type *t)
{
/* void => no type and size info.
* Hence, FWD is also treated as void.
*/
return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
}
static bool btf_type_is_void_or_null(const struct btf_type *t)
{
return !t || btf_type_is_void(t);
}
/* union is only a special case of struct:
* all its offsetof(member) == 0
*/
static bool btf_type_is_struct(const struct btf_type *t)
{
u8 kind = BTF_INFO_KIND(t->info);
return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
}
static bool btf_type_is_array(const struct btf_type *t)
{
return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
}
static bool btf_type_is_ptr(const struct btf_type *t)
{
return BTF_INFO_KIND(t->info) == BTF_KIND_PTR;
}
static bool btf_type_is_int(const struct btf_type *t)
{
return BTF_INFO_KIND(t->info) == BTF_KIND_INT;
}
/* What types need to be resolved?
*
* btf_type_is_modifier() is an obvious one.
*
* btf_type_is_struct() because its member refers to
* another type (through member->type).
* btf_type_is_array() because its element (array->type)
* refers to another type. Array can be thought of a
* special case of struct while array just has the same
* member-type repeated by array->nelems of times.
*/
static bool btf_type_needs_resolve(const struct btf_type *t)
{
return btf_type_is_modifier(t) ||
btf_type_is_ptr(t) ||
btf_type_is_struct(t) ||
btf_type_is_array(t);
}
/* t->size can be used */
static bool btf_type_has_size(const struct btf_type *t)
{
switch (BTF_INFO_KIND(t->info)) {
case BTF_KIND_INT:
case BTF_KIND_STRUCT:
case BTF_KIND_UNION:
case BTF_KIND_ENUM:
return true;
}
return false;
}
static const char *btf_int_encoding_str(u8 encoding)
{
if (encoding == 0)
return "(none)";
else if (encoding == BTF_INT_SIGNED)
return "SIGNED";
else if (encoding == BTF_INT_CHAR)
return "CHAR";
else if (encoding == BTF_INT_BOOL)
return "BOOL";
else if (encoding == BTF_INT_VARARGS)
return "VARARGS";
else
return "UNKN";
}
static u16 btf_type_vlen(const struct btf_type *t)
{
return BTF_INFO_VLEN(t->info);
}
static u32 btf_type_int(const struct btf_type *t)
{
return *(u32 *)(t + 1);
}
static const struct btf_array *btf_type_array(const struct btf_type *t)
{
return (const struct btf_array *)(t + 1);
}
static const struct btf_member *btf_type_member(const struct btf_type *t)
{
return (const struct btf_member *)(t + 1);
}
static const struct btf_enum *btf_type_enum(const struct btf_type *t)
{
return (const struct btf_enum *)(t + 1);
}
static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
{
return kind_ops[BTF_INFO_KIND(t->info)];
}
static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
{
return !BTF_STR_TBL_ELF_ID(offset) &&
BTF_STR_OFFSET(offset) < btf->hdr->str_len;
}
static const char *btf_name_by_offset(const struct btf *btf, u32 offset)
{
if (!BTF_STR_OFFSET(offset))
return "(anon)";
else if (BTF_STR_OFFSET(offset) < btf->hdr->str_len)
return &btf->strings[BTF_STR_OFFSET(offset)];
else
return "(invalid-name-offset)";
}
static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
{
if (type_id > btf->nr_types)
return NULL;
return btf->types[type_id];
}
__printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log,
const char *fmt, ...)
{
va_list args;
va_start(args, fmt);
bpf_verifier_vlog(log, fmt, args);
va_end(args);
}
__printf(2, 3) static void btf_verifier_log(struct btf_verifier_env *env,
const char *fmt, ...)
{
struct bpf_verifier_log *log = &env->log;
va_list args;
if (!bpf_verifier_log_needed(log))
return;
va_start(args, fmt);
bpf_verifier_vlog(log, fmt, args);
va_end(args);
}
__printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env,
const struct btf_type *t,
bool log_details,
const char *fmt, ...)
{
struct bpf_verifier_log *log = &env->log;
u8 kind = BTF_INFO_KIND(t->info);
struct btf *btf = env->btf;
va_list args;
if (!bpf_verifier_log_needed(log))
return;
__btf_verifier_log(log, "[%u] %s %s%s",
env->log_type_id,
btf_kind_str[kind],
btf_name_by_offset(btf, t->name),
log_details ? " " : "");
if (log_details)
btf_type_ops(t)->log_details(env, t);
if (fmt && *fmt) {
__btf_verifier_log(log, " ");
va_start(args, fmt);
bpf_verifier_vlog(log, fmt, args);
va_end(args);
}
__btf_verifier_log(log, "\n");
}
#define btf_verifier_log_type(env, t, ...) \
__btf_verifier_log_type((env), (t), true, __VA_ARGS__)
#define btf_verifier_log_basic(env, t, ...) \
__btf_verifier_log_type((env), (t), false, __VA_ARGS__)
__printf(4, 5)
static void btf_verifier_log_member(struct btf_verifier_env *env,
const struct btf_type *struct_type,
const struct btf_member *member,
const char *fmt, ...)
{
struct bpf_verifier_log *log = &env->log;
struct btf *btf = env->btf;
va_list args;
if (!bpf_verifier_log_needed(log))
return;
/* The CHECK_META phase already did a btf dump.
*
* If member is logged again, it must hit an error in
* parsing this member. It is useful to print out which
* struct this member belongs to.
*/
if (env->phase != CHECK_META)
btf_verifier_log_type(env, struct_type, NULL);
__btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
btf_name_by_offset(btf, member->name),
member->type, member->offset);
if (fmt && *fmt) {
__btf_verifier_log(log, " ");
va_start(args, fmt);
bpf_verifier_vlog(log, fmt, args);
va_end(args);
}
__btf_verifier_log(log, "\n");
}
static void btf_verifier_log_hdr(struct btf_verifier_env *env)
{
struct bpf_verifier_log *log = &env->log;
const struct btf *btf = env->btf;
const struct btf_header *hdr;
if (!bpf_verifier_log_needed(log))
return;
hdr = btf->hdr;
__btf_verifier_log(log, "magic: 0x%x\n", hdr->magic);
__btf_verifier_log(log, "version: %u\n", hdr->version);
__btf_verifier_log(log, "flags: 0x%x\n", hdr->flags);
__btf_verifier_log(log, "parent_label: %u\n", hdr->parent_label);
__btf_verifier_log(log, "parent_name: %u\n", hdr->parent_name);
__btf_verifier_log(log, "label_off: %u\n", hdr->label_off);
__btf_verifier_log(log, "object_off: %u\n", hdr->object_off);
__btf_verifier_log(log, "func_off: %u\n", hdr->func_off);
__btf_verifier_log(log, "type_off: %u\n", hdr->type_off);
__btf_verifier_log(log, "str_off: %u\n", hdr->str_off);
__btf_verifier_log(log, "str_len: %u\n", hdr->str_len);
__btf_verifier_log(log, "btf_total_size: %u\n", btf->data_size);
}
static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t)
{
struct btf *btf = env->btf;
/* < 2 because +1 for btf_void which is always in btf->types[0].
* btf_void is not accounted in btf->nr_types because btf_void
* does not come from the BTF file.
*/
if (btf->types_size - btf->nr_types < 2) {
/* Expand 'types' array */
struct btf_type **new_types;
u32 expand_by, new_size;
if (btf->types_size == BTF_MAX_NR_TYPES) {
btf_verifier_log(env, "Exceeded max num of types");
return -E2BIG;
}
expand_by = max_t(u32, btf->types_size >> 2, 16);
new_size = min_t(u32, BTF_MAX_NR_TYPES,
btf->types_size + expand_by);
new_types = kvzalloc(new_size * sizeof(*new_types),
GFP_KERNEL | __GFP_NOWARN);
if (!new_types)
return -ENOMEM;
if (btf->nr_types == 0)
new_types[0] = &btf_void;
else
memcpy(new_types, btf->types,
sizeof(*btf->types) * (btf->nr_types + 1));
kvfree(btf->types);
btf->types = new_types;
btf->types_size = new_size;
}
btf->types[++(btf->nr_types)] = t;
return 0;
}
static void btf_free(struct btf *btf)
{
kvfree(btf->types);
kvfree(btf->resolved_sizes);
kvfree(btf->resolved_ids);
kvfree(btf->data);
kfree(btf);
}
static void btf_get(struct btf *btf)
{
refcount_inc(&btf->refcnt);
}
void btf_put(struct btf *btf)
{
if (btf && refcount_dec_and_test(&btf->refcnt))
btf_free(btf);
}
static int env_resolve_init(struct btf_verifier_env *env)
{
struct btf *btf = env->btf;
u32 nr_types = btf->nr_types;
u32 *resolved_sizes = NULL;
u32 *resolved_ids = NULL;
u8 *visit_states = NULL;
/* +1 for btf_void */
resolved_sizes = kvzalloc((nr_types + 1) * sizeof(*resolved_sizes),
GFP_KERNEL | __GFP_NOWARN);
if (!resolved_sizes)
goto nomem;
resolved_ids = kvzalloc((nr_types + 1) * sizeof(*resolved_ids),
GFP_KERNEL | __GFP_NOWARN);
if (!resolved_ids)
goto nomem;
visit_states = kvzalloc((nr_types + 1) * sizeof(*visit_states),
GFP_KERNEL | __GFP_NOWARN);
if (!visit_states)
goto nomem;
btf->resolved_sizes = resolved_sizes;
btf->resolved_ids = resolved_ids;
env->visit_states = visit_states;
return 0;
nomem:
kvfree(resolved_sizes);
kvfree(resolved_ids);
kvfree(visit_states);
return -ENOMEM;
}
static void btf_verifier_env_free(struct btf_verifier_env *env)
{
kvfree(env->visit_states);
kfree(env);
}
static bool env_type_is_resolve_sink(const struct btf_verifier_env *env,
const struct btf_type *next_type)
{
switch (env->resolve_mode) {
case RESOLVE_TBD:
/* int, enum or void is a sink */
return !btf_type_needs_resolve(next_type);
case RESOLVE_PTR:
/* int, enum, void, struct or array is a sink for ptr */
return !btf_type_is_modifier(next_type) &&
!btf_type_is_ptr(next_type);
case RESOLVE_STRUCT_OR_ARRAY:
/* int, enum, void or ptr is a sink for struct and array */
return !btf_type_is_modifier(next_type) &&
!btf_type_is_array(next_type) &&
!btf_type_is_struct(next_type);
default:
BUG_ON(1);
}
}
static bool env_type_is_resolved(const struct btf_verifier_env *env,
u32 type_id)
{
return env->visit_states[type_id] == RESOLVED;
}
static int env_stack_push(struct btf_verifier_env *env,
const struct btf_type *t, u32 type_id)
{
struct resolve_vertex *v;
if (env->top_stack == MAX_RESOLVE_DEPTH)
return -E2BIG;
if (env->visit_states[type_id] != NOT_VISITED)
return -EEXIST;
env->visit_states[type_id] = VISITED;
v = &env->stack[env->top_stack++];
v->t = t;
v->type_id = type_id;
v->next_member = 0;
if (env->resolve_mode == RESOLVE_TBD) {
if (btf_type_is_ptr(t))
env->resolve_mode = RESOLVE_PTR;
else if (btf_type_is_struct(t) || btf_type_is_array(t))
env->resolve_mode = RESOLVE_STRUCT_OR_ARRAY;
}
return 0;
}
static void env_stack_set_next_member(struct btf_verifier_env *env,
u16 next_member)
{
env->stack[env->top_stack - 1].next_member = next_member;
}
static void env_stack_pop_resolved(struct btf_verifier_env *env,
u32 resolved_type_id,
u32 resolved_size)
{
u32 type_id = env->stack[--(env->top_stack)].type_id;
struct btf *btf = env->btf;
btf->resolved_sizes[type_id] = resolved_size;
btf->resolved_ids[type_id] = resolved_type_id;
env->visit_states[type_id] = RESOLVED;
}
static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env)
{
return env->top_stack ? &env->stack[env->top_stack - 1] : NULL;
}
/* The input param "type_id" must point to a needs_resolve type */
static const struct btf_type *btf_type_id_resolve(const struct btf *btf,
u32 *type_id)
{
*type_id = btf->resolved_ids[*type_id];
return btf_type_by_id(btf, *type_id);
}
const struct btf_type *btf_type_id_size(const struct btf *btf,
u32 *type_id, u32 *ret_size)
{
const struct btf_type *size_type;
u32 size_type_id = *type_id;
u32 size = 0;
size_type = btf_type_by_id(btf, size_type_id);
if (btf_type_is_void_or_null(size_type))
return NULL;
if (btf_type_has_size(size_type)) {
size = size_type->size;
} else if (btf_type_is_array(size_type)) {
size = btf->resolved_sizes[size_type_id];
} else if (btf_type_is_ptr(size_type)) {
size = sizeof(void *);
} else {
if (WARN_ON_ONCE(!btf_type_is_modifier(size_type)))
return NULL;
size = btf->resolved_sizes[size_type_id];
size_type_id = btf->resolved_ids[size_type_id];
size_type = btf_type_by_id(btf, size_type_id);
if (btf_type_is_void(size_type))
return NULL;
}
*type_id = size_type_id;
if (ret_size)
*ret_size = size;
return size_type;
}
static int btf_df_check_member(struct btf_verifier_env *env,
const struct btf_type *struct_type,
const struct btf_member *member,
const struct btf_type *member_type)
{
btf_verifier_log_basic(env, struct_type,
"Unsupported check_member");
return -EINVAL;
}
static int btf_df_resolve(struct btf_verifier_env *env,
const struct resolve_vertex *v)
{
btf_verifier_log_basic(env, v->t, "Unsupported resolve");
return -EINVAL;
}
static void btf_df_seq_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offsets,
struct seq_file *m)
{
seq_printf(m, "<unsupported kind:%u>", BTF_INFO_KIND(t->info));
}
static int btf_int_check_member(struct btf_verifier_env *env,
const struct btf_type *struct_type,
const struct btf_member *member,
const struct btf_type *member_type)
{
u32 int_data = btf_type_int(member_type);
u32 struct_bits_off = member->offset;
u32 struct_size = struct_type->size;
u32 nr_copy_bits;
u32 bytes_offset;
if (U32_MAX - struct_bits_off < BTF_INT_OFFSET(int_data)) {
btf_verifier_log_member(env, struct_type, member,
"bits_offset exceeds U32_MAX");
return -EINVAL;
}
struct_bits_off += BTF_INT_OFFSET(int_data);
bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
nr_copy_bits = BTF_INT_BITS(int_data) +
BITS_PER_BYTE_MASKED(struct_bits_off);
if (nr_copy_bits > BITS_PER_U64) {
btf_verifier_log_member(env, struct_type, member,
"nr_copy_bits exceeds 64");
return -EINVAL;
}
if (struct_size < bytes_offset ||
struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) {
btf_verifier_log_member(env, struct_type, member,
"Member exceeds struct_size");
return -EINVAL;
}
return 0;
}
static s32 btf_int_check_meta(struct btf_verifier_env *env,
const struct btf_type *t,
u32 meta_left)
{
u32 int_data, nr_bits, meta_needed = sizeof(int_data);
u16 encoding;
if (meta_left < meta_needed) {
btf_verifier_log_basic(env, t,
"meta_left:%u meta_needed:%u",
meta_left, meta_needed);
return -EINVAL;
}
if (btf_type_vlen(t)) {
btf_verifier_log_type(env, t, "vlen != 0");
return -EINVAL;
}
int_data = btf_type_int(t);
nr_bits = BTF_INT_BITS(int_data) + BTF_INT_OFFSET(int_data);
if (nr_bits > BITS_PER_U64) {
btf_verifier_log_type(env, t, "nr_bits exceeds %zu",
BITS_PER_U64);
return -EINVAL;
}
if (BITS_ROUNDUP_BYTES(nr_bits) > t->size) {
btf_verifier_log_type(env, t, "nr_bits exceeds type_size");
return -EINVAL;
}
encoding = BTF_INT_ENCODING(int_data);
if (encoding &&
encoding != BTF_INT_SIGNED &&
encoding != BTF_INT_CHAR &&
encoding != BTF_INT_BOOL &&
encoding != BTF_INT_VARARGS) {
btf_verifier_log_type(env, t, "Unsupported encoding");
return -ENOTSUPP;
}
btf_verifier_log_type(env, t, NULL);
return meta_needed;
}
static void btf_int_log(struct btf_verifier_env *env,
const struct btf_type *t)
{
int int_data = btf_type_int(t);
btf_verifier_log(env,
"size=%u bits_offset=%u nr_bits=%u encoding=%s",
t->size, BTF_INT_OFFSET(int_data),
BTF_INT_BITS(int_data),
btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
}
static void btf_int_bits_seq_show(const struct btf *btf,
const struct btf_type *t,
void *data, u8 bits_offset,
struct seq_file *m)
{
u32 int_data = btf_type_int(t);
u16 nr_bits = BTF_INT_BITS(int_data);
u16 total_bits_offset;
u16 nr_copy_bytes;
u16 nr_copy_bits;
u8 nr_upper_bits;
union {
u64 u64_num;
u8 u8_nums[8];
} print_num;
total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
nr_copy_bits = nr_bits + bits_offset;
nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
print_num.u64_num = 0;
memcpy(&print_num.u64_num, data, nr_copy_bytes);
/* Ditch the higher order bits */
nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
if (nr_upper_bits) {
/* We need to mask out some bits of the upper byte. */
u8 mask = (1 << nr_upper_bits) - 1;
print_num.u8_nums[nr_copy_bytes - 1] &= mask;
}
print_num.u64_num >>= bits_offset;
seq_printf(m, "0x%llx", print_num.u64_num);
}
static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offset,
struct seq_file *m)
{
u32 int_data = btf_type_int(t);
u8 encoding = BTF_INT_ENCODING(int_data);
bool sign = encoding & BTF_INT_SIGNED;
u32 nr_bits = BTF_INT_BITS(int_data);
if (bits_offset || BTF_INT_OFFSET(int_data) ||
BITS_PER_BYTE_MASKED(nr_bits)) {
btf_int_bits_seq_show(btf, t, data, bits_offset, m);
return;
}
switch (nr_bits) {
case 64:
if (sign)
seq_printf(m, "%lld", *(s64 *)data);
else
seq_printf(m, "%llu", *(u64 *)data);
break;
case 32:
if (sign)
seq_printf(m, "%d", *(s32 *)data);
else
seq_printf(m, "%u", *(u32 *)data);
break;
case 16:
if (sign)
seq_printf(m, "%d", *(s16 *)data);
else
seq_printf(m, "%u", *(u16 *)data);
break;
case 8:
if (sign)
seq_printf(m, "%d", *(s8 *)data);
else
seq_printf(m, "%u", *(u8 *)data);
break;
default:
btf_int_bits_seq_show(btf, t, data, bits_offset, m);
}
}
static const struct btf_kind_operations int_ops = {
.check_meta = btf_int_check_meta,
.resolve = btf_df_resolve,
.check_member = btf_int_check_member,
.log_details = btf_int_log,
.seq_show = btf_int_seq_show,
};
static int btf_modifier_check_member(struct btf_verifier_env *env,
const struct btf_type *struct_type,
const struct btf_member *member,
const struct btf_type *member_type)
{
const struct btf_type *resolved_type;
u32 resolved_type_id = member->type;
struct btf_member resolved_member;
struct btf *btf = env->btf;
resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL);
if (!resolved_type) {
btf_verifier_log_member(env, struct_type, member,
"Invalid member");
return -EINVAL;
}
resolved_member = *member;
resolved_member.type = resolved_type_id;
return btf_type_ops(resolved_type)->check_member(env, struct_type,
&resolved_member,
resolved_type);
}
static int btf_ptr_check_member(struct btf_verifier_env *env,
const struct btf_type *struct_type,
const struct btf_member *member,
const struct btf_type *member_type)
{
u32 struct_size, struct_bits_off, bytes_offset;
struct_size = struct_type->size;
struct_bits_off = member->offset;
bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
btf_verifier_log_member(env, struct_type, member,
"Member is not byte aligned");
return -EINVAL;
}
if (struct_size - bytes_offset < sizeof(void *)) {
btf_verifier_log_member(env, struct_type, member,
"Member exceeds struct_size");
return -EINVAL;
}
return 0;
}
static int btf_ref_type_check_meta(struct btf_verifier_env *env,
const struct btf_type *t,
u32 meta_left)
{
if (btf_type_vlen(t)) {
btf_verifier_log_type(env, t, "vlen != 0");
return -EINVAL;
}
if (BTF_TYPE_PARENT(t->type)) {
btf_verifier_log_type(env, t, "Invalid type_id");
return -EINVAL;
}
btf_verifier_log_type(env, t, NULL);
return 0;
}
static int btf_modifier_resolve(struct btf_verifier_env *env,
const struct resolve_vertex *v)
{
const struct btf_type *t = v->t;
const struct btf_type *next_type;
u32 next_type_id = t->type;
struct btf *btf = env->btf;
u32 next_type_size = 0;
next_type = btf_type_by_id(btf, next_type_id);
if (!next_type) {
btf_verifier_log_type(env, v->t, "Invalid type_id");
return -EINVAL;
}
/* "typedef void new_void", "const void"...etc */
if (btf_type_is_void(next_type))
goto resolved;
if (!env_type_is_resolve_sink(env, next_type) &&
!env_type_is_resolved(env, next_type_id))
return env_stack_push(env, next_type, next_type_id);
/* Figure out the resolved next_type_id with size.
* They will be stored in the current modifier's
* resolved_ids and resolved_sizes such that it can
* save us a few type-following when we use it later (e.g. in
* pretty print).
*/
if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
!btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) {
btf_verifier_log_type(env, v->t, "Invalid type_id");
return -EINVAL;
}
resolved:
env_stack_pop_resolved(env, next_type_id, next_type_size);
return 0;
}
static int btf_ptr_resolve(struct btf_verifier_env *env,
const struct resolve_vertex *v)
{
const struct btf_type *next_type;
const struct btf_type *t = v->t;
u32 next_type_id = t->type;
struct btf *btf = env->btf;
u32 next_type_size = 0;
next_type = btf_type_by_id(btf, next_type_id);
if (!next_type) {
btf_verifier_log_type(env, v->t, "Invalid type_id");
return -EINVAL;
}
/* "void *" */
if (btf_type_is_void(next_type))
goto resolved;
if (!env_type_is_resolve_sink(env, next_type) &&
!env_type_is_resolved(env, next_type_id))
return env_stack_push(env, next_type, next_type_id);
/* If the modifier was RESOLVED during RESOLVE_STRUCT_OR_ARRAY,
* the modifier may have stopped resolving when it was resolved
* to a ptr (last-resolved-ptr).
*
* We now need to continue from the last-resolved-ptr to
* ensure the last-resolved-ptr will not referring back to
* the currenct ptr (t).
*/
if (btf_type_is_modifier(next_type)) {
const struct btf_type *resolved_type;
u32 resolved_type_id;
resolved_type_id = next_type_id;
resolved_type = btf_type_id_resolve(btf, &resolved_type_id);
if (btf_type_is_ptr(resolved_type) &&
!env_type_is_resolve_sink(env, resolved_type) &&
!env_type_is_resolved(env, resolved_type_id))
return env_stack_push(env, resolved_type,
resolved_type_id);
}
if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
!btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) {
btf_verifier_log_type(env, v->t, "Invalid type_id");
return -EINVAL;
}
resolved:
env_stack_pop_resolved(env, next_type_id, 0);
return 0;
}
static void btf_modifier_seq_show(const struct btf *btf,
const struct btf_type *t,
u32 type_id, void *data,
u8 bits_offset, struct seq_file *m)
{
t = btf_type_id_resolve(btf, &type_id);
btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
}
static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offset,
struct seq_file *m)
{
/* It is a hashed value */
seq_printf(m, "%p", *(void **)data);
}
static void btf_ref_type_log(struct btf_verifier_env *env,
const struct btf_type *t)
{
btf_verifier_log(env, "type_id=%u", t->type);
}
static struct btf_kind_operations modifier_ops = {
.check_meta = btf_ref_type_check_meta,
.resolve = btf_modifier_resolve,
.check_member = btf_modifier_check_member,
.log_details = btf_ref_type_log,
.seq_show = btf_modifier_seq_show,
};
static struct btf_kind_operations ptr_ops = {
.check_meta = btf_ref_type_check_meta,
.resolve = btf_ptr_resolve,
.check_member = btf_ptr_check_member,
.log_details = btf_ref_type_log,
.seq_show = btf_ptr_seq_show,
};
static struct btf_kind_operations fwd_ops = {
.check_meta = btf_ref_type_check_meta,
.resolve = btf_df_resolve,
.check_member = btf_df_check_member,
.log_details = btf_ref_type_log,
.seq_show = btf_df_seq_show,
};
static int btf_array_check_member(struct btf_verifier_env *env,
const struct btf_type *struct_type,
const struct btf_member *member,
const struct btf_type *member_type)
{
u32 struct_bits_off = member->offset;
u32 struct_size, bytes_offset;
u32 array_type_id, array_size;
struct btf *btf = env->btf;
if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
btf_verifier_log_member(env, struct_type, member,
"Member is not byte aligned");
return -EINVAL;
}
array_type_id = member->type;
btf_type_id_size(btf, &array_type_id, &array_size);
struct_size = struct_type->size;
bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
if (struct_size - bytes_offset < array_size) {
btf_verifier_log_member(env, struct_type, member,
"Member exceeds struct_size");
return -EINVAL;
}
return 0;
}
static s32 btf_array_check_meta(struct btf_verifier_env *env,
const struct btf_type *t,
u32 meta_left)
{
const struct btf_array *array = btf_type_array(t);
u32 meta_needed = sizeof(*array);
if (meta_left < meta_needed) {
btf_verifier_log_basic(env, t,
"meta_left:%u meta_needed:%u",
meta_left, meta_needed);
return -EINVAL;
}
if (btf_type_vlen(t)) {
btf_verifier_log_type(env, t, "vlen != 0");
return -EINVAL;
}
/* We are a little forgiving on array->index_type since
* the kernel is not using it.
*/
/* Array elem cannot be in type void,
* so !array->type is not allowed.
*/
if (!array->type || BTF_TYPE_PARENT(array->type)) {
btf_verifier_log_type(env, t, "Invalid type_id");
return -EINVAL;
}
btf_verifier_log_type(env, t, NULL);
return meta_needed;
}
static int btf_array_resolve(struct btf_verifier_env *env,
const struct resolve_vertex *v)
{
const struct btf_array *array = btf_type_array(v->t);
const struct btf_type *elem_type;
u32 elem_type_id = array->type;
struct btf *btf = env->btf;
u32 elem_size;
elem_type = btf_type_by_id(btf, elem_type_id);
if (btf_type_is_void_or_null(elem_type)) {
btf_verifier_log_type(env, v->t,
"Invalid elem");
return -EINVAL;
}
if (!env_type_is_resolve_sink(env, elem_type) &&
!env_type_is_resolved(env, elem_type_id))
return env_stack_push(env, elem_type, elem_type_id);
elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
if (!elem_type) {
btf_verifier_log_type(env, v->t, "Invalid elem");
return -EINVAL;
}
if (btf_type_is_int(elem_type)) {
int int_type_data = btf_type_int(elem_type);
u16 nr_bits = BTF_INT_BITS(int_type_data);
u16 nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
/* Put more restriction on array of int. The int cannot
* be a bit field and it must be either u8/u16/u32/u64.
*/
if (BITS_PER_BYTE_MASKED(nr_bits) ||
BTF_INT_OFFSET(int_type_data) ||
(nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) &&
nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64))) {
btf_verifier_log_type(env, v->t,
"Invalid array of int");
return -EINVAL;
}
}
if (array->nelems && elem_size > U32_MAX / array->nelems) {
btf_verifier_log_type(env, v->t,
"Array size overflows U32_MAX");
return -EINVAL;
}
env_stack_pop_resolved(env, elem_type_id, elem_size * array->nelems);
return 0;
}
static void btf_array_log(struct btf_verifier_env *env,
const struct btf_type *t)
{
const struct btf_array *array = btf_type_array(t);
btf_verifier_log(env, "type_id=%u index_type_id=%u nr_elems=%u",
array->type, array->index_type, array->nelems);
}
static void btf_array_seq_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offset,
struct seq_file *m)
{
const struct btf_array *array = btf_type_array(t);
const struct btf_kind_operations *elem_ops;
const struct btf_type *elem_type;
u32 i, elem_size, elem_type_id;
elem_type_id = array->type;
elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
elem_ops = btf_type_ops(elem_type);
seq_puts(m, "[");
for (i = 0; i < array->nelems; i++) {
if (i)
seq_puts(m, ",");
elem_ops->seq_show(btf, elem_type, elem_type_id, data,
bits_offset, m);
data += elem_size;
}
seq_puts(m, "]");
}
static struct btf_kind_operations array_ops = {
.check_meta = btf_array_check_meta,
.resolve = btf_array_resolve,
.check_member = btf_array_check_member,
.log_details = btf_array_log,
.seq_show = btf_array_seq_show,
};
static int btf_struct_check_member(struct btf_verifier_env *env,
const struct btf_type *struct_type,
const struct btf_member *member,
const struct btf_type *member_type)
{
u32 struct_bits_off = member->offset;
u32 struct_size, bytes_offset;
if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
btf_verifier_log_member(env, struct_type, member,
"Member is not byte aligned");
return -EINVAL;
}
struct_size = struct_type->size;
bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
if (struct_size - bytes_offset < member_type->size) {
btf_verifier_log_member(env, struct_type, member,
"Member exceeds struct_size");
return -EINVAL;
}
return 0;
}
static s32 btf_struct_check_meta(struct btf_verifier_env *env,
const struct btf_type *t,
u32 meta_left)
{
bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION;
const struct btf_member *member;
struct btf *btf = env->btf;
u32 struct_size = t->size;
u32 meta_needed;
u16 i;
meta_needed = btf_type_vlen(t) * sizeof(*member);
if (meta_left < meta_needed) {
btf_verifier_log_basic(env, t,
"meta_left:%u meta_needed:%u",
meta_left, meta_needed);
return -EINVAL;
}
btf_verifier_log_type(env, t, NULL);
for_each_member(i, t, member) {
if (!btf_name_offset_valid(btf, member->name)) {
btf_verifier_log_member(env, t, member,
"Invalid member name_offset:%u",
member->name);
return -EINVAL;
}
/* A member cannot be in type void */
if (!member->type || BTF_TYPE_PARENT(member->type)) {
btf_verifier_log_member(env, t, member,
"Invalid type_id");
return -EINVAL;
}
if (is_union && member->offset) {
btf_verifier_log_member(env, t, member,
"Invalid member bits_offset");
return -EINVAL;
}
if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
btf_verifier_log_member(env, t, member,
"Memmber bits_offset exceeds its struct size");
return -EINVAL;
}
btf_verifier_log_member(env, t, member, NULL);
}
return meta_needed;
}
static int btf_struct_resolve(struct btf_verifier_env *env,
const struct resolve_vertex *v)
{
const struct btf_member *member;
int err;
u16 i;
/* Before continue resolving the next_member,
* ensure the last member is indeed resolved to a
* type with size info.
*/
if (v->next_member) {
const struct btf_type *last_member_type;
const struct btf_member *last_member;
u16 last_member_type_id;
last_member = btf_type_member(v->t) + v->next_member - 1;
last_member_type_id = last_member->type;
if (WARN_ON_ONCE(!env_type_is_resolved(env,
last_member_type_id)))
return -EINVAL;
last_member_type = btf_type_by_id(env->btf,
last_member_type_id);
err = btf_type_ops(last_member_type)->check_member(env, v->t,
last_member,
last_member_type);
if (err)
return err;
}
for_each_member_from(i, v->next_member, v->t, member) {
u32 member_type_id = member->type;
const struct btf_type *member_type = btf_type_by_id(env->btf,
member_type_id);
if (btf_type_is_void_or_null(member_type)) {
btf_verifier_log_member(env, v->t, member,
"Invalid member");
return -EINVAL;
}
if (!env_type_is_resolve_sink(env, member_type) &&
!env_type_is_resolved(env, member_type_id)) {
env_stack_set_next_member(env, i + 1);
return env_stack_push(env, member_type, member_type_id);
}
err = btf_type_ops(member_type)->check_member(env, v->t,
member,
member_type);
if (err)
return err;
}
env_stack_pop_resolved(env, 0, 0);
return 0;
}
static void btf_struct_log(struct btf_verifier_env *env,
const struct btf_type *t)
{
btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
}
static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offset,
struct seq_file *m)
{
const char *seq = BTF_INFO_KIND(t->info) == BTF_KIND_UNION ? "|" : ",";
const struct btf_member *member;
u32 i;
seq_puts(m, "{");
for_each_member(i, t, member) {
const struct btf_type *member_type = btf_type_by_id(btf,
member->type);
u32 member_offset = member->offset;
u32 bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
u8 bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
const struct btf_kind_operations *ops;
if (i)
seq_puts(m, seq);
ops = btf_type_ops(member_type);
ops->seq_show(btf, member_type, member->type,
data + bytes_offset, bits8_offset, m);
}
seq_puts(m, "}");
}
static struct btf_kind_operations struct_ops = {
.check_meta = btf_struct_check_meta,
.resolve = btf_struct_resolve,
.check_member = btf_struct_check_member,
.log_details = btf_struct_log,
.seq_show = btf_struct_seq_show,
};
static int btf_enum_check_member(struct btf_verifier_env *env,
const struct btf_type *struct_type,
const struct btf_member *member,
const struct btf_type *member_type)
{
u32 struct_bits_off = member->offset;
u32 struct_size, bytes_offset;
if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
btf_verifier_log_member(env, struct_type, member,
"Member is not byte aligned");
return -EINVAL;
}
struct_size = struct_type->size;
bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
if (struct_size - bytes_offset < sizeof(int)) {
btf_verifier_log_member(env, struct_type, member,
"Member exceeds struct_size");
return -EINVAL;
}
return 0;
}
static s32 btf_enum_check_meta(struct btf_verifier_env *env,
const struct btf_type *t,
u32 meta_left)
{
const struct btf_enum *enums = btf_type_enum(t);
struct btf *btf = env->btf;
u16 i, nr_enums;
u32 meta_needed;
nr_enums = btf_type_vlen(t);
meta_needed = nr_enums * sizeof(*enums);
if (meta_left < meta_needed) {
btf_verifier_log_basic(env, t,
"meta_left:%u meta_needed:%u",
meta_left, meta_needed);
return -EINVAL;
}
if (t->size != sizeof(int)) {
btf_verifier_log_type(env, t, "Expected size:%zu",
sizeof(int));
return -EINVAL;
}
btf_verifier_log_type(env, t, NULL);
for (i = 0; i < nr_enums; i++) {
if (!btf_name_offset_valid(btf, enums[i].name)) {
btf_verifier_log(env, "\tInvalid name_offset:%u",
enums[i].name);
return -EINVAL;
}
btf_verifier_log(env, "\t%s val=%d\n",
btf_name_by_offset(btf, enums[i].name),
enums[i].val);
}
return meta_needed;
}
static void btf_enum_log(struct btf_verifier_env *env,
const struct btf_type *t)
{
btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
}
static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offset,
struct seq_file *m)
{
const struct btf_enum *enums = btf_type_enum(t);
u32 i, nr_enums = btf_type_vlen(t);
int v = *(int *)data;
for (i = 0; i < nr_enums; i++) {
if (v == enums[i].val) {
seq_printf(m, "%s",
btf_name_by_offset(btf, enums[i].name));
return;
}
}
seq_printf(m, "%d", v);
}
static struct btf_kind_operations enum_ops = {
.check_meta = btf_enum_check_meta,
.resolve = btf_df_resolve,
.check_member = btf_enum_check_member,
.log_details = btf_enum_log,
.seq_show = btf_enum_seq_show,
};
static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
[BTF_KIND_INT] = &int_ops,
[BTF_KIND_PTR] = &ptr_ops,
[BTF_KIND_ARRAY] = &array_ops,
[BTF_KIND_STRUCT] = &struct_ops,
[BTF_KIND_UNION] = &struct_ops,
[BTF_KIND_ENUM] = &enum_ops,
[BTF_KIND_FWD] = &fwd_ops,
[BTF_KIND_TYPEDEF] = &modifier_ops,
[BTF_KIND_VOLATILE] = &modifier_ops,
[BTF_KIND_CONST] = &modifier_ops,
[BTF_KIND_RESTRICT] = &modifier_ops,
};
static s32 btf_check_meta(struct btf_verifier_env *env,
const struct btf_type *t,
u32 meta_left)
{
u32 saved_meta_left = meta_left;
s32 var_meta_size;
if (meta_left < sizeof(*t)) {
btf_verifier_log(env, "[%u] meta_left:%u meta_needed:%zu",
env->log_type_id, meta_left, sizeof(*t));
return -EINVAL;
}
meta_left -= sizeof(*t);
if (BTF_INFO_KIND(t->info) > BTF_KIND_MAX ||
BTF_INFO_KIND(t->info) == BTF_KIND_UNKN) {
btf_verifier_log(env, "[%u] Invalid kind:%u",
env->log_type_id, BTF_INFO_KIND(t->info));
return -EINVAL;
}
if (!btf_name_offset_valid(env->btf, t->name)) {
btf_verifier_log(env, "[%u] Invalid name_offset:%u",
env->log_type_id, t->name);
return -EINVAL;
}
var_meta_size = btf_type_ops(t)->check_meta(env, t, meta_left);
if (var_meta_size < 0)
return var_meta_size;
meta_left -= var_meta_size;
return saved_meta_left - meta_left;
}
static int btf_check_all_metas(struct btf_verifier_env *env)
{
struct btf *btf = env->btf;
struct btf_header *hdr;
void *cur, *end;
hdr = btf->hdr;
cur = btf->nohdr_data + hdr->type_off;
end = btf->nohdr_data + hdr->str_off;
env->log_type_id = 1;
while (cur < end) {
struct btf_type *t = cur;
s32 meta_size;
meta_size = btf_check_meta(env, t, end - cur);
if (meta_size < 0)
return meta_size;
btf_add_type(env, t);
cur += meta_size;
env->log_type_id++;
}
return 0;
}
static int btf_resolve(struct btf_verifier_env *env,
const struct btf_type *t, u32 type_id)
{
const struct resolve_vertex *v;
int err = 0;
env->resolve_mode = RESOLVE_TBD;
env_stack_push(env, t, type_id);
while (!err && (v = env_stack_peak(env))) {
env->log_type_id = v->type_id;
err = btf_type_ops(v->t)->resolve(env, v);
}
env->log_type_id = type_id;
if (err == -E2BIG)
btf_verifier_log_type(env, t,
"Exceeded max resolving depth:%u",
MAX_RESOLVE_DEPTH);
else if (err == -EEXIST)
btf_verifier_log_type(env, t, "Loop detected");
return err;
}
static bool btf_resolve_valid(struct btf_verifier_env *env,
const struct btf_type *t,
u32 type_id)
{
struct btf *btf = env->btf;
if (!env_type_is_resolved(env, type_id))
return false;
if (btf_type_is_struct(t))
return !btf->resolved_ids[type_id] &&
!btf->resolved_sizes[type_id];
if (btf_type_is_modifier(t) || btf_type_is_ptr(t)) {
t = btf_type_id_resolve(btf, &type_id);
return t && !btf_type_is_modifier(t);
}
if (btf_type_is_array(t)) {
const struct btf_array *array = btf_type_array(t);
const struct btf_type *elem_type;
u32 elem_type_id = array->type;
u32 elem_size;
elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
return elem_type && !btf_type_is_modifier(elem_type) &&
(array->nelems * elem_size ==
btf->resolved_sizes[type_id]);
}
return false;
}
static int btf_check_all_types(struct btf_verifier_env *env)
{
struct btf *btf = env->btf;
u32 type_id;
int err;
err = env_resolve_init(env);
if (err)
return err;
env->phase++;
for (type_id = 1; type_id <= btf->nr_types; type_id++) {
const struct btf_type *t = btf_type_by_id(btf, type_id);
env->log_type_id = type_id;
if (btf_type_needs_resolve(t) &&
!env_type_is_resolved(env, type_id)) {
err = btf_resolve(env, t, type_id);
if (err)
return err;
}
if (btf_type_needs_resolve(t) &&
!btf_resolve_valid(env, t, type_id)) {
btf_verifier_log_type(env, t, "Invalid resolve state");
return -EINVAL;
}
}
return 0;
}
static int btf_parse_type_sec(struct btf_verifier_env *env)
{
int err;
err = btf_check_all_metas(env);
if (err)
return err;
return btf_check_all_types(env);
}
static int btf_parse_str_sec(struct btf_verifier_env *env)
{
const struct btf_header *hdr;
struct btf *btf = env->btf;
const char *start, *end;
hdr = btf->hdr;
start = btf->nohdr_data + hdr->str_off;
end = start + hdr->str_len;
if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET ||
start[0] || end[-1]) {
btf_verifier_log(env, "Invalid string section");
return -EINVAL;
}
btf->strings = start;
return 0;
}
static int btf_parse_hdr(struct btf_verifier_env *env)
{
const struct btf_header *hdr;
struct btf *btf = env->btf;
u32 meta_left;
if (btf->data_size < sizeof(*hdr)) {
btf_verifier_log(env, "btf_header not found");
return -EINVAL;
}
btf_verifier_log_hdr(env);
hdr = btf->hdr;
if (hdr->magic != BTF_MAGIC) {
btf_verifier_log(env, "Invalid magic");
return -EINVAL;
}
if (hdr->version != BTF_VERSION) {
btf_verifier_log(env, "Unsupported version");
return -ENOTSUPP;
}
if (hdr->flags) {
btf_verifier_log(env, "Unsupported flags");
return -ENOTSUPP;
}
meta_left = btf->data_size - sizeof(*hdr);
if (!meta_left) {
btf_verifier_log(env, "No data");
return -EINVAL;
}
if (meta_left < hdr->type_off || hdr->str_off <= hdr->type_off ||
/* Type section must align to 4 bytes */
hdr->type_off & (sizeof(u32) - 1)) {
btf_verifier_log(env, "Invalid type_off");
return -EINVAL;
}
if (meta_left < hdr->str_off ||
meta_left - hdr->str_off < hdr->str_len) {
btf_verifier_log(env, "Invalid str_off or str_len");
return -EINVAL;
}
btf->nohdr_data = btf->hdr + 1;
return 0;
}
static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
u32 log_level, char __user *log_ubuf, u32 log_size)
{
struct btf_verifier_env *env = NULL;
struct bpf_verifier_log *log;
struct btf *btf = NULL;
u8 *data;
int err;
if (btf_data_size > BTF_MAX_SIZE)
return ERR_PTR(-E2BIG);
env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
if (!env)
return ERR_PTR(-ENOMEM);
log = &env->log;
if (log_level || log_ubuf || log_size) {
/* user requested verbose verifier output
* and supplied buffer to store the verification trace
*/
log->level = log_level;
log->ubuf = log_ubuf;
log->len_total = log_size;
/* log attributes have to be sane */
if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
!log->level || !log->ubuf) {
err = -EINVAL;
goto errout;
}
}
btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN);
if (!btf) {
err = -ENOMEM;
goto errout;
}
data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN);
if (!data) {
err = -ENOMEM;
goto errout;
}
btf->data = data;
btf->data_size = btf_data_size;
if (copy_from_user(data, btf_data, btf_data_size)) {
err = -EFAULT;
goto errout;
}
env->btf = btf;
err = btf_parse_hdr(env);
if (err)
goto errout;
err = btf_parse_str_sec(env);
if (err)
goto errout;
err = btf_parse_type_sec(env);
if (err)
goto errout;
if (!err && log->level && bpf_verifier_log_full(log)) {
err = -ENOSPC;
goto errout;
}
if (!err) {
btf_verifier_env_free(env);
btf_get(btf);
return btf;
}
errout:
btf_verifier_env_free(env);
if (btf)
btf_free(btf);
return ERR_PTR(err);
}
void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
struct seq_file *m)
{
const struct btf_type *t = btf_type_by_id(btf, type_id);
btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m);
}
static int btf_release(struct inode *inode, struct file *filp)
{
btf_put(filp->private_data);
return 0;
}
const struct file_operations btf_fops = {
.release = btf_release,
};
int btf_new_fd(const union bpf_attr *attr)
{
struct btf *btf;
int fd;
btf = btf_parse(u64_to_user_ptr(attr->btf),
attr->btf_size, attr->btf_log_level,
u64_to_user_ptr(attr->btf_log_buf),
attr->btf_log_size);
if (IS_ERR(btf))
return PTR_ERR(btf);
fd = anon_inode_getfd("btf", &btf_fops, btf,
O_RDONLY | O_CLOEXEC);
if (fd < 0)
btf_put(btf);
return fd;
}
struct btf *btf_get_by_fd(int fd)
{
struct btf *btf;
struct fd f;
f = fdget(fd);
if (!f.file)
return ERR_PTR(-EBADF);
if (f.file->f_op != &btf_fops) {
fdput(f);
return ERR_PTR(-EINVAL);
}
btf = f.file->private_data;
btf_get(btf);
fdput(f);
return btf;
}
int btf_get_info_by_fd(const struct btf *btf,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
void __user *udata = u64_to_user_ptr(attr->info.info);
u32 copy_len = min_t(u32, btf->data_size,
attr->info.info_len);
if (copy_to_user(udata, btf->data, copy_len) ||
put_user(btf->data_size, &uattr->info.info_len))
return -EFAULT;
return 0;
}
...@@ -150,8 +150,154 @@ static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) ...@@ -150,8 +150,154 @@ static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
return 0; return 0;
} }
struct map_iter {
void *key;
bool done;
};
static struct map_iter *map_iter(struct seq_file *m)
{
return m->private;
}
static struct bpf_map *seq_file_to_map(struct seq_file *m)
{
return file_inode(m->file)->i_private;
}
static void map_iter_free(struct map_iter *iter)
{
if (iter) {
kfree(iter->key);
kfree(iter);
}
}
static struct map_iter *map_iter_alloc(struct bpf_map *map)
{
struct map_iter *iter;
iter = kzalloc(sizeof(*iter), GFP_KERNEL | __GFP_NOWARN);
if (!iter)
goto error;
iter->key = kzalloc(map->key_size, GFP_KERNEL | __GFP_NOWARN);
if (!iter->key)
goto error;
return iter;
error:
map_iter_free(iter);
return NULL;
}
static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
{
struct bpf_map *map = seq_file_to_map(m);
void *key = map_iter(m)->key;
if (map_iter(m)->done)
return NULL;
if (unlikely(v == SEQ_START_TOKEN))
goto done;
if (map->ops->map_get_next_key(map, key, key)) {
map_iter(m)->done = true;
return NULL;
}
done:
++(*pos);
return key;
}
static void *map_seq_start(struct seq_file *m, loff_t *pos)
{
if (map_iter(m)->done)
return NULL;
return *pos ? map_iter(m)->key : SEQ_START_TOKEN;
}
static void map_seq_stop(struct seq_file *m, void *v)
{
}
static int map_seq_show(struct seq_file *m, void *v)
{
struct bpf_map *map = seq_file_to_map(m);
void *key = map_iter(m)->key;
if (unlikely(v == SEQ_START_TOKEN)) {
seq_puts(m, "# WARNING!! The output is for debug purpose only\n");
seq_puts(m, "# WARNING!! The output format will change\n");
} else {
map->ops->map_seq_show_elem(map, key, m);
}
return 0;
}
static const struct seq_operations bpffs_map_seq_ops = {
.start = map_seq_start,
.next = map_seq_next,
.show = map_seq_show,
.stop = map_seq_stop,
};
static int bpffs_map_open(struct inode *inode, struct file *file)
{
struct bpf_map *map = inode->i_private;
struct map_iter *iter;
struct seq_file *m;
int err;
iter = map_iter_alloc(map);
if (!iter)
return -ENOMEM;
err = seq_open(file, &bpffs_map_seq_ops);
if (err) {
map_iter_free(iter);
return err;
}
m = file->private_data;
m->private = iter;
return 0;
}
static int bpffs_map_release(struct inode *inode, struct file *file)
{
struct seq_file *m = file->private_data;
map_iter_free(map_iter(m));
return seq_release(inode, file);
}
/* bpffs_map_fops should only implement the basic
* read operation for a BPF map. The purpose is to
* provide a simple user intuitive way to do
* "cat bpffs/pathto/a-pinned-map".
*
* Other operations (e.g. write, lookup...) should be realized by
* the userspace tools (e.g. bpftool) through the
* BPF_OBJ_GET_INFO_BY_FD and the map's lookup/update
* interface.
*/
static const struct file_operations bpffs_map_fops = {
.open = bpffs_map_open,
.read = seq_read,
.release = bpffs_map_release,
};
static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw,
const struct inode_operations *iops) const struct inode_operations *iops,
const struct file_operations *fops)
{ {
struct inode *dir = dentry->d_parent->d_inode; struct inode *dir = dentry->d_parent->d_inode;
struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode); struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode);
...@@ -159,6 +305,7 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, ...@@ -159,6 +305,7 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw,
return PTR_ERR(inode); return PTR_ERR(inode);
inode->i_op = iops; inode->i_op = iops;
inode->i_fop = fops;
inode->i_private = raw; inode->i_private = raw;
bpf_dentry_finalize(dentry, inode, dir); bpf_dentry_finalize(dentry, inode, dir);
...@@ -167,12 +314,15 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, ...@@ -167,12 +314,15 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw,
static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg) static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg)
{ {
return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops); return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops, NULL);
} }
static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg) static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
{ {
return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops); struct bpf_map *map = arg;
return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops,
map->btf ? &bpffs_map_fops : NULL);
} }
static struct dentry * static struct dentry *
......
...@@ -11,6 +11,7 @@ ...@@ -11,6 +11,7 @@
*/ */
#include <linux/bpf.h> #include <linux/bpf.h>
#include <linux/bpf_trace.h> #include <linux/bpf_trace.h>
#include <linux/btf.h>
#include <linux/syscalls.h> #include <linux/syscalls.h>
#include <linux/slab.h> #include <linux/slab.h>
#include <linux/sched/signal.h> #include <linux/sched/signal.h>
...@@ -26,6 +27,7 @@ ...@@ -26,6 +27,7 @@
#include <linux/cred.h> #include <linux/cred.h>
#include <linux/timekeeping.h> #include <linux/timekeeping.h>
#include <linux/ctype.h> #include <linux/ctype.h>
#include <linux/btf.h>
#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
(map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
...@@ -250,6 +252,7 @@ static void bpf_map_free_deferred(struct work_struct *work) ...@@ -250,6 +252,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
bpf_map_uncharge_memlock(map); bpf_map_uncharge_memlock(map);
security_bpf_map_free(map); security_bpf_map_free(map);
btf_put(map->btf);
/* implementation dependent freeing */ /* implementation dependent freeing */
map->ops->map_free(map); map->ops->map_free(map);
} }
...@@ -415,7 +418,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) ...@@ -415,7 +418,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
return 0; return 0;
} }
#define BPF_MAP_CREATE_LAST_FIELD map_ifindex #define BPF_MAP_CREATE_LAST_FIELD btf_value_id
/* called via syscall */ /* called via syscall */
static int map_create(union bpf_attr *attr) static int map_create(union bpf_attr *attr)
{ {
...@@ -449,6 +452,33 @@ static int map_create(union bpf_attr *attr) ...@@ -449,6 +452,33 @@ static int map_create(union bpf_attr *attr)
atomic_set(&map->refcnt, 1); atomic_set(&map->refcnt, 1);
atomic_set(&map->usercnt, 1); atomic_set(&map->usercnt, 1);
if (bpf_map_support_seq_show(map) &&
(attr->btf_key_id || attr->btf_value_id)) {
struct btf *btf;
if (!attr->btf_key_id || !attr->btf_value_id) {
err = -EINVAL;
goto free_map_nouncharge;
}
btf = btf_get_by_fd(attr->btf_fd);
if (IS_ERR(btf)) {
err = PTR_ERR(btf);
goto free_map_nouncharge;
}
err = map->ops->map_check_btf(map, btf, attr->btf_key_id,
attr->btf_value_id);
if (err) {
btf_put(btf);
goto free_map_nouncharge;
}
map->btf = btf;
map->btf_key_id = attr->btf_key_id;
map->btf_value_id = attr->btf_value_id;
}
err = security_bpf_map_alloc(map); err = security_bpf_map_alloc(map);
if (err) if (err)
goto free_map_nouncharge; goto free_map_nouncharge;
...@@ -481,6 +511,7 @@ static int map_create(union bpf_attr *attr) ...@@ -481,6 +511,7 @@ static int map_create(union bpf_attr *attr)
free_map_sec: free_map_sec:
security_bpf_map_free(map); security_bpf_map_free(map);
free_map_nouncharge: free_map_nouncharge:
btf_put(map->btf);
map->ops->map_free(map); map->ops->map_free(map);
return err; return err;
} }
...@@ -2016,6 +2047,8 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, ...@@ -2016,6 +2047,8 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
else if (f.file->f_op == &bpf_map_fops) else if (f.file->f_op == &bpf_map_fops)
err = bpf_map_get_info_by_fd(f.file->private_data, attr, err = bpf_map_get_info_by_fd(f.file->private_data, attr,
uattr); uattr);
else if (f.file->f_op == &btf_fops)
err = btf_get_info_by_fd(f.file->private_data, attr, uattr);
else else
err = -EINVAL; err = -EINVAL;
...@@ -2023,6 +2056,19 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, ...@@ -2023,6 +2056,19 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
return err; return err;
} }
#define BPF_BTF_LOAD_LAST_FIELD btf_log_level
static int bpf_btf_load(const union bpf_attr *attr)
{
if (CHECK_ATTR(BPF_BTF_LOAD))
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
return btf_new_fd(attr);
}
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{ {
union bpf_attr attr = {}; union bpf_attr attr = {};
...@@ -2103,6 +2149,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz ...@@ -2103,6 +2149,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_RAW_TRACEPOINT_OPEN: case BPF_RAW_TRACEPOINT_OPEN:
err = bpf_raw_tracepoint_open(&attr); err = bpf_raw_tracepoint_open(&attr);
break; break;
case BPF_BTF_LOAD:
err = bpf_btf_load(&attr);
break;
default: default:
err = -EINVAL; err = -EINVAL;
break; break;
......
...@@ -170,7 +170,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, ...@@ -170,7 +170,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
xdp.rxq = &rxqueue->xdp_rxq; xdp.rxq = &rxqueue->xdp_rxq;
retval = bpf_test_run(prog, &xdp, repeat, &duration); retval = bpf_test_run(prog, &xdp, repeat, &duration);
if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN) if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN ||
xdp.data_end != xdp.data + size)
size = xdp.data_end - xdp.data; size = xdp.data_end - xdp.data;
ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration); ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
kfree(data); kfree(data);
......
...@@ -3997,9 +3997,9 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, ...@@ -3997,9 +3997,9 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
struct bpf_prog *xdp_prog) struct bpf_prog *xdp_prog)
{ {
struct netdev_rx_queue *rxqueue; struct netdev_rx_queue *rxqueue;
void *orig_data, *orig_data_end;
u32 metalen, act = XDP_DROP; u32 metalen, act = XDP_DROP;
struct xdp_buff xdp; struct xdp_buff xdp;
void *orig_data;
int hlen, off; int hlen, off;
u32 mac_len; u32 mac_len;
...@@ -4038,6 +4038,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, ...@@ -4038,6 +4038,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
xdp.data_meta = xdp.data; xdp.data_meta = xdp.data;
xdp.data_end = xdp.data + hlen; xdp.data_end = xdp.data + hlen;
xdp.data_hard_start = skb->data - skb_headroom(skb); xdp.data_hard_start = skb->data - skb_headroom(skb);
orig_data_end = xdp.data_end;
orig_data = xdp.data; orig_data = xdp.data;
rxqueue = netif_get_rxqueue(skb); rxqueue = netif_get_rxqueue(skb);
...@@ -4052,6 +4053,13 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, ...@@ -4052,6 +4053,13 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
__skb_push(skb, -off); __skb_push(skb, -off);
skb->mac_header += off; skb->mac_header += off;
/* check if bpf_xdp_adjust_tail was used. it can only "shrink"
* pckt.
*/
off = orig_data_end - xdp.data_end;
if (off != 0)
skb_set_tail_pointer(skb, xdp.data_end - xdp.data);
switch (act) { switch (act) {
case XDP_REDIRECT: case XDP_REDIRECT:
case XDP_TX: case XDP_TX:
......
...@@ -2694,20 +2694,13 @@ BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) ...@@ -2694,20 +2694,13 @@ BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset)
{ {
void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame);
unsigned long metalen = xdp_get_metalen(xdp); unsigned long metalen = xdp_get_metalen(xdp);
void *data_start = xdp->data_hard_start + metalen; void *data_start = xdp_frame_end + metalen;
void *data = xdp->data + offset; void *data = xdp->data + offset;
if (unlikely(data < data_start || if (unlikely(data < data_start ||
data > xdp->data_end - ETH_HLEN)) data > xdp->data_end - ETH_HLEN))
return -EINVAL; return -EINVAL;
/* Avoid info leak, when reusing area prev used by xdp_frame */
if (data < xdp_frame_end) {
unsigned long clearlen = xdp_frame_end - data;
memset(data, 0, clearlen);
}
if (metalen) if (metalen)
memmove(xdp->data_meta + offset, memmove(xdp->data_meta + offset,
xdp->data_meta, metalen); xdp->data_meta, metalen);
...@@ -2725,14 +2718,39 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { ...@@ -2725,14 +2718,39 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
.arg2_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING,
}; };
BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset)
{
void *data_end = xdp->data_end + offset;
/* only shrinking is allowed for now. */
if (unlikely(offset >= 0))
return -EINVAL;
if (unlikely(data_end < xdp->data + ETH_HLEN))
return -EINVAL;
xdp->data_end = data_end;
return 0;
}
static const struct bpf_func_proto bpf_xdp_adjust_tail_proto = {
.func = bpf_xdp_adjust_tail,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
};
BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset)
{ {
void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame);
void *meta = xdp->data_meta + offset; void *meta = xdp->data_meta + offset;
unsigned long metalen = xdp->data - meta; unsigned long metalen = xdp->data - meta;
if (xdp_data_meta_unsupported(xdp)) if (xdp_data_meta_unsupported(xdp))
return -ENOTSUPP; return -ENOTSUPP;
if (unlikely(meta < xdp->data_hard_start || if (unlikely(meta < xdp_frame_end ||
meta > xdp->data)) meta > xdp->data))
return -EINVAL; return -EINVAL;
if (unlikely((metalen & (sizeof(__u32) - 1)) || if (unlikely((metalen & (sizeof(__u32) - 1)) ||
...@@ -3074,7 +3092,8 @@ bool bpf_helper_changes_pkt_data(void *func) ...@@ -3074,7 +3092,8 @@ bool bpf_helper_changes_pkt_data(void *func)
func == bpf_l4_csum_replace || func == bpf_l4_csum_replace ||
func == bpf_xdp_adjust_head || func == bpf_xdp_adjust_head ||
func == bpf_xdp_adjust_meta || func == bpf_xdp_adjust_meta ||
func == bpf_msg_pull_data) func == bpf_msg_pull_data ||
func == bpf_xdp_adjust_tail)
return true; return true;
return false; return false;
...@@ -3888,6 +3907,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) ...@@ -3888,6 +3907,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_xdp_redirect_proto; return &bpf_xdp_redirect_proto;
case BPF_FUNC_redirect_map: case BPF_FUNC_redirect_map:
return &bpf_xdp_redirect_map_proto; return &bpf_xdp_redirect_map_proto;
case BPF_FUNC_xdp_adjust_tail:
return &bpf_xdp_adjust_tail_proto;
default: default:
return bpf_base_func_proto(func_id); return bpf_base_func_proto(func_id);
} }
......
...@@ -44,6 +44,7 @@ hostprogs-y += xdp_monitor ...@@ -44,6 +44,7 @@ hostprogs-y += xdp_monitor
hostprogs-y += xdp_rxq_info hostprogs-y += xdp_rxq_info
hostprogs-y += syscall_tp hostprogs-y += syscall_tp
hostprogs-y += cpustat hostprogs-y += cpustat
hostprogs-y += xdp_adjust_tail
# Libbpf dependencies # Libbpf dependencies
LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
...@@ -95,6 +96,7 @@ xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o ...@@ -95,6 +96,7 @@ xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o
xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o
syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
cpustat-objs := bpf_load.o $(LIBBPF) cpustat_user.o cpustat-objs := bpf_load.o $(LIBBPF) cpustat_user.o
xdp_adjust_tail-objs := bpf_load.o $(LIBBPF) xdp_adjust_tail_user.o
# Tell kbuild to always build the programs # Tell kbuild to always build the programs
always := $(hostprogs-y) always := $(hostprogs-y)
...@@ -148,6 +150,7 @@ always += xdp_rxq_info_kern.o ...@@ -148,6 +150,7 @@ always += xdp_rxq_info_kern.o
always += xdp2skb_meta_kern.o always += xdp2skb_meta_kern.o
always += syscall_tp_kern.o always += syscall_tp_kern.o
always += cpustat_kern.o always += cpustat_kern.o
always += xdp_adjust_tail_kern.o
HOSTCFLAGS += -I$(objtree)/usr/include HOSTCFLAGS += -I$(objtree)/usr/include
HOSTCFLAGS += -I$(srctree)/tools/lib/ HOSTCFLAGS += -I$(srctree)/tools/lib/
...@@ -193,6 +196,7 @@ HOSTLOADLIBES_xdp_monitor += -lelf ...@@ -193,6 +196,7 @@ HOSTLOADLIBES_xdp_monitor += -lelf
HOSTLOADLIBES_xdp_rxq_info += -lelf HOSTLOADLIBES_xdp_rxq_info += -lelf
HOSTLOADLIBES_syscall_tp += -lelf HOSTLOADLIBES_syscall_tp += -lelf
HOSTLOADLIBES_cpustat += -lelf HOSTLOADLIBES_cpustat += -lelf
HOSTLOADLIBES_xdp_adjust_tail += -lelf
# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang # make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
......
...@@ -9,10 +9,10 @@ ...@@ -9,10 +9,10 @@
* if (value) * if (value)
* (*(u64*)value) += 1; * (*(u64*)value) += 1;
* *
* - attaches this program to eth0 raw socket * - attaches this program to loopback interface "lo" raw socket
* *
* - every second user space reads map[tcp], map[udp], map[icmp] to see * - every second user space reads map[tcp], map[udp], map[icmp] to see
* how many packets of given protocol were seen on eth0 * how many packets of given protocol were seen on "lo"
*/ */
#include <stdio.h> #include <stdio.h>
#include <unistd.h> #include <unistd.h>
......
/* SPDX-License-Identifier: GPL-2.0
* Copyright (c) 2018 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program shows how to use bpf_xdp_adjust_tail() by
* generating ICMPv4 "packet to big" (unreachable/ df bit set frag needed
* to be more preice in case of v4)" where receiving packets bigger then
* 600 bytes.
*/
#define KBUILD_MODNAME "foo"
#include <uapi/linux/bpf.h>
#include <linux/in.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include "bpf_helpers.h"
#define DEFAULT_TTL 64
#define MAX_PCKT_SIZE 600
#define ICMP_TOOBIG_SIZE 98
#define ICMP_TOOBIG_PAYLOAD_SIZE 92
struct bpf_map_def SEC("maps") icmpcnt = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u64),
.max_entries = 1,
};
static __always_inline void count_icmp(void)
{
u64 key = 0;
u64 *icmp_count;
icmp_count = bpf_map_lookup_elem(&icmpcnt, &key);
if (icmp_count)
*icmp_count += 1;
}
static __always_inline void swap_mac(void *data, struct ethhdr *orig_eth)
{
struct ethhdr *eth;
eth = data;
memcpy(eth->h_source, orig_eth->h_dest, ETH_ALEN);
memcpy(eth->h_dest, orig_eth->h_source, ETH_ALEN);
eth->h_proto = orig_eth->h_proto;
}
static __always_inline __u16 csum_fold_helper(__u32 csum)
{
return ~((csum & 0xffff) + (csum >> 16));
}
static __always_inline void ipv4_csum(void *data_start, int data_size,
__u32 *csum)
{
*csum = bpf_csum_diff(0, 0, data_start, data_size, *csum);
*csum = csum_fold_helper(*csum);
}
static __always_inline int send_icmp4_too_big(struct xdp_md *xdp)
{
int headroom = (int)sizeof(struct iphdr) + (int)sizeof(struct icmphdr);
if (bpf_xdp_adjust_head(xdp, 0 - headroom))
return XDP_DROP;
void *data = (void *)(long)xdp->data;
void *data_end = (void *)(long)xdp->data_end;
if (data + (ICMP_TOOBIG_SIZE + headroom) > data_end)
return XDP_DROP;
struct iphdr *iph, *orig_iph;
struct icmphdr *icmp_hdr;
struct ethhdr *orig_eth;
__u32 csum = 0;
__u64 off = 0;
orig_eth = data + headroom;
swap_mac(data, orig_eth);
off += sizeof(struct ethhdr);
iph = data + off;
off += sizeof(struct iphdr);
icmp_hdr = data + off;
off += sizeof(struct icmphdr);
orig_iph = data + off;
icmp_hdr->type = ICMP_DEST_UNREACH;
icmp_hdr->code = ICMP_FRAG_NEEDED;
icmp_hdr->un.frag.mtu = htons(MAX_PCKT_SIZE-sizeof(struct ethhdr));
icmp_hdr->checksum = 0;
ipv4_csum(icmp_hdr, ICMP_TOOBIG_PAYLOAD_SIZE, &csum);
icmp_hdr->checksum = csum;
iph->ttl = DEFAULT_TTL;
iph->daddr = orig_iph->saddr;
iph->saddr = orig_iph->daddr;
iph->version = 4;
iph->ihl = 5;
iph->protocol = IPPROTO_ICMP;
iph->tos = 0;
iph->tot_len = htons(
ICMP_TOOBIG_SIZE + headroom - sizeof(struct ethhdr));
iph->check = 0;
csum = 0;
ipv4_csum(iph, sizeof(struct iphdr), &csum);
iph->check = csum;
count_icmp();
return XDP_TX;
}
static __always_inline int handle_ipv4(struct xdp_md *xdp)
{
void *data_end = (void *)(long)xdp->data_end;
void *data = (void *)(long)xdp->data;
int pckt_size = data_end - data;
int offset;
if (pckt_size > MAX_PCKT_SIZE) {
offset = pckt_size - ICMP_TOOBIG_SIZE;
if (bpf_xdp_adjust_tail(xdp, 0 - offset))
return XDP_PASS;
return send_icmp4_too_big(xdp);
}
return XDP_PASS;
}
SEC("xdp_icmp")
int _xdp_icmp(struct xdp_md *xdp)
{
void *data_end = (void *)(long)xdp->data_end;
void *data = (void *)(long)xdp->data;
struct ethhdr *eth = data;
__u16 h_proto;
if (eth + 1 > data_end)
return XDP_DROP;
h_proto = eth->h_proto;
if (h_proto == htons(ETH_P_IP))
return handle_ipv4(xdp);
else
return XDP_PASS;
}
char _license[] SEC("license") = "GPL";
/* SPDX-License-Identifier: GPL-2.0
* Copyright (c) 2018 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <linux/bpf.h>
#include <linux/if_link.h>
#include <assert.h>
#include <errno.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/resource.h>
#include <arpa/inet.h>
#include <netinet/ether.h>
#include <unistd.h>
#include <time.h>
#include "bpf_load.h"
#include "libbpf.h"
#include "bpf_util.h"
#define STATS_INTERVAL_S 2U
static int ifindex = -1;
static __u32 xdp_flags;
static void int_exit(int sig)
{
if (ifindex > -1)
bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
exit(0);
}
/* simple "icmp packet too big sent" counter
*/
static void poll_stats(unsigned int kill_after_s)
{
time_t started_at = time(NULL);
__u64 value = 0;
int key = 0;
while (!kill_after_s || time(NULL) - started_at <= kill_after_s) {
sleep(STATS_INTERVAL_S);
assert(bpf_map_lookup_elem(map_fd[0], &key, &value) == 0);
printf("icmp \"packet too big\" sent: %10llu pkts\n", value);
}
}
static void usage(const char *cmd)
{
printf("Start a XDP prog which send ICMP \"packet too big\" \n"
"messages if ingress packet is bigger then MAX_SIZE bytes\n");
printf("Usage: %s [...]\n", cmd);
printf(" -i <ifindex> Interface Index\n");
printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n");
printf(" -S use skb-mode\n");
printf(" -N enforce native mode\n");
printf(" -h Display this help\n");
}
int main(int argc, char **argv)
{
unsigned char opt_flags[256] = {};
unsigned int kill_after_s = 0;
const char *optstr = "i:T:SNh";
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
char filename[256];
int opt;
int i;
for (i = 0; i < strlen(optstr); i++)
if (optstr[i] != 'h' && 'a' <= optstr[i] && optstr[i] <= 'z')
opt_flags[(unsigned char)optstr[i]] = 1;
while ((opt = getopt(argc, argv, optstr)) != -1) {
switch (opt) {
case 'i':
ifindex = atoi(optarg);
break;
case 'T':
kill_after_s = atoi(optarg);
break;
case 'S':
xdp_flags |= XDP_FLAGS_SKB_MODE;
break;
case 'N':
xdp_flags |= XDP_FLAGS_DRV_MODE;
break;
default:
usage(argv[0]);
return 1;
}
opt_flags[opt] = 0;
}
for (i = 0; i < strlen(optstr); i++) {
if (opt_flags[(unsigned int)optstr[i]]) {
fprintf(stderr, "Missing argument -%c\n", optstr[i]);
usage(argv[0]);
return 1;
}
}
if (setrlimit(RLIMIT_MEMLOCK, &r)) {
perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)");
return 1;
}
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
if (load_bpf_file(filename)) {
printf("%s", bpf_log_buf);
return 1;
}
if (!prog_fd[0]) {
printf("load_bpf_file: %s\n", strerror(errno));
return 1;
}
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
printf("link set xdp fd failed\n");
return 1;
}
poll_stats(kill_after_s);
bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
return 0;
}
...@@ -330,7 +330,7 @@ static void stats_print(struct stats_record *stats_rec, ...@@ -330,7 +330,7 @@ static void stats_print(struct stats_record *stats_rec,
pps = calc_pps_u64(r, p, t); pps = calc_pps_u64(r, p, t);
if (pps > 0) if (pps > 0)
printf(fmt1, "Exception", i, printf(fmt1, "Exception", i,
0.0, pps, err2str(rec_i)); 0.0, pps, action2str(rec_i));
} }
pps = calc_pps_u64(&rec->total, &prev->total, t); pps = calc_pps_u64(&rec->total, &prev->total, t);
if (pps > 0) if (pps > 0)
......
...@@ -26,7 +26,8 @@ MAP COMMANDS ...@@ -26,7 +26,8 @@ MAP COMMANDS
| **bpftool** **cgroup help** | **bpftool** **cgroup help**
| |
| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** } | *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** |
| **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** }
| *ATTACH_FLAGS* := { **multi** | **override** } | *ATTACH_FLAGS* := { **multi** | **override** }
DESCRIPTION DESCRIPTION
...@@ -63,7 +64,13 @@ DESCRIPTION ...@@ -63,7 +64,13 @@ DESCRIPTION
**egress** egress path of the inet socket (since 4.10); **egress** egress path of the inet socket (since 4.10);
**sock_create** opening of an inet socket (since 4.10); **sock_create** opening of an inet socket (since 4.10);
**sock_ops** various socket operations (since 4.12); **sock_ops** various socket operations (since 4.12);
**device** device access (since 4.15). **device** device access (since 4.15);
**bind4** call to bind(2) for an inet4 socket (since 4.17);
**bind6** call to bind(2) for an inet6 socket (since 4.17);
**post_bind4** return from bind(2) for an inet4 socket (since 4.17);
**post_bind6** return from bind(2) for an inet6 socket (since 4.17);
**connect4** call to connect(2) for an inet4 socket (since 4.17);
**connect6** call to connect(2) for an inet6 socket (since 4.17).
**bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
Detach *PROG* from the cgroup *CGROUP* and attach type Detach *PROG* from the cgroup *CGROUP* and attach type
......
...@@ -23,10 +23,10 @@ MAP COMMANDS ...@@ -23,10 +23,10 @@ MAP COMMANDS
| **bpftool** **map { show | list }** [*MAP*] | **bpftool** **map { show | list }** [*MAP*]
| **bpftool** **map dump** *MAP* | **bpftool** **map dump** *MAP*
| **bpftool** **map update** *MAP* **key** *BYTES* **value** *VALUE* [*UPDATE_FLAGS*] | **bpftool** **map update** *MAP* **key** [**hex**] *BYTES* **value** [**hex**] *VALUE* [*UPDATE_FLAGS*]
| **bpftool** **map lookup** *MAP* **key** *BYTES* | **bpftool** **map lookup** *MAP* **key** [**hex**] *BYTES*
| **bpftool** **map getnext** *MAP* [**key** *BYTES*] | **bpftool** **map getnext** *MAP* [**key** [**hex**] *BYTES*]
| **bpftool** **map delete** *MAP* **key** *BYTES* | **bpftool** **map delete** *MAP* **key** [**hex**] *BYTES*
| **bpftool** **map pin** *MAP* *FILE* | **bpftool** **map pin** *MAP* *FILE*
| **bpftool** **map help** | **bpftool** **map help**
| |
...@@ -48,20 +48,26 @@ DESCRIPTION ...@@ -48,20 +48,26 @@ DESCRIPTION
**bpftool map dump** *MAP* **bpftool map dump** *MAP*
Dump all entries in a given *MAP*. Dump all entries in a given *MAP*.
**bpftool map update** *MAP* **key** *BYTES* **value** *VALUE* [*UPDATE_FLAGS*] **bpftool map update** *MAP* **key** [**hex**] *BYTES* **value** [**hex**] *VALUE* [*UPDATE_FLAGS*]
Update map entry for a given *KEY*. Update map entry for a given *KEY*.
*UPDATE_FLAGS* can be one of: **any** update existing entry *UPDATE_FLAGS* can be one of: **any** update existing entry
or add if doesn't exit; **exist** update only if entry already or add if doesn't exit; **exist** update only if entry already
exists; **noexist** update only if entry doesn't exist. exists; **noexist** update only if entry doesn't exist.
**bpftool map lookup** *MAP* **key** *BYTES* If the **hex** keyword is provided in front of the bytes
sequence, the bytes are parsed as hexadeximal values, even if
no "0x" prefix is added. If the keyword is not provided, then
the bytes are parsed as decimal values, unless a "0x" prefix
(for hexadecimal) or a "0" prefix (for octal) is provided.
**bpftool map lookup** *MAP* **key** [**hex**] *BYTES*
Lookup **key** in the map. Lookup **key** in the map.
**bpftool map getnext** *MAP* [**key** *BYTES*] **bpftool map getnext** *MAP* [**key** [**hex**] *BYTES*]
Get next key. If *key* is not specified, get first key. Get next key. If *key* is not specified, get first key.
**bpftool map delete** *MAP* **key** *BYTES* **bpftool map delete** *MAP* **key** [**hex**] *BYTES*
Remove entry from the map. Remove entry from the map.
**bpftool map pin** *MAP* *FILE* **bpftool map pin** *MAP* *FILE*
...@@ -98,7 +104,12 @@ EXAMPLES ...@@ -98,7 +104,12 @@ EXAMPLES
10: hash name some_map flags 0x0 10: hash name some_map flags 0x0
key 4B value 8B max_entries 2048 memlock 167936B key 4B value 8B max_entries 2048 memlock 167936B
**# bpftool map update id 10 key 13 00 07 00 value 02 00 00 00 01 02 03 04** The following three commands are equivalent:
|
| **# bpftool map update id 10 key hex 20 c4 b7 00 value hex 0f ff ff ab 01 02 03 4c**
| **# bpftool map update id 10 key 0x20 0xc4 0xb7 0x00 value 0x0f 0xff 0xff 0xab 0x01 0x02 0x03 0x4c**
| **# bpftool map update id 10 key 32 196 183 0 value 15 255 255 171 1 2 3 76**
**# bpftool map lookup id 10 key 0 1 2 3** **# bpftool map lookup id 10 key 0 1 2 3**
......
...@@ -147,7 +147,7 @@ _bpftool() ...@@ -147,7 +147,7 @@ _bpftool()
# Deal with simplest keywords # Deal with simplest keywords
case $prev in case $prev in
help|key|opcodes|visual) help|hex|opcodes|visual)
return 0 return 0
;; ;;
tag) tag)
...@@ -283,7 +283,7 @@ _bpftool() ...@@ -283,7 +283,7 @@ _bpftool()
return 0 return 0
;; ;;
key) key)
return 0 COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) )
;; ;;
*) *)
_bpftool_once_attr 'key' _bpftool_once_attr 'key'
...@@ -302,7 +302,7 @@ _bpftool() ...@@ -302,7 +302,7 @@ _bpftool()
return 0 return 0
;; ;;
key) key)
return 0 COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) )
;; ;;
value) value)
# We can have bytes, or references to a prog or a # We can have bytes, or references to a prog or a
...@@ -321,6 +321,8 @@ _bpftool() ...@@ -321,6 +321,8 @@ _bpftool()
return 0 return 0
;; ;;
*) *)
COMPREPLY+=( $( compgen -W 'hex' \
-- "$cur" ) )
return 0 return 0
;; ;;
esac esac
...@@ -372,7 +374,8 @@ _bpftool() ...@@ -372,7 +374,8 @@ _bpftool()
;; ;;
attach|detach) attach|detach)
local ATTACH_TYPES='ingress egress sock_create sock_ops \ local ATTACH_TYPES='ingress egress sock_create sock_ops \
device' device bind4 bind6 post_bind4 post_bind6 connect4 \
connect6'
local ATTACH_FLAGS='multi override' local ATTACH_FLAGS='multi override'
local PROG_TYPE='id pinned tag' local PROG_TYPE='id pinned tag'
case $prev in case $prev in
...@@ -380,7 +383,8 @@ _bpftool() ...@@ -380,7 +383,8 @@ _bpftool()
_filedir _filedir
return 0 return 0
;; ;;
ingress|egress|sock_create|sock_ops|device) ingress|egress|sock_create|sock_ops|device|bind4|bind6|\
post_bind4|post_bind6|connect4|connect6)
COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \
"$cur" ) ) "$cur" ) )
return 0 return 0
......
...@@ -16,8 +16,11 @@ ...@@ -16,8 +16,11 @@
#define HELP_SPEC_ATTACH_FLAGS \ #define HELP_SPEC_ATTACH_FLAGS \
"ATTACH_FLAGS := { multi | override }" "ATTACH_FLAGS := { multi | override }"
#define HELP_SPEC_ATTACH_TYPES \ #define HELP_SPEC_ATTACH_TYPES \
"ATTACH_TYPE := { ingress | egress | sock_create | sock_ops | device }" " ATTACH_TYPE := { ingress | egress | sock_create |\n" \
" sock_ops | device | bind4 | bind6 |\n" \
" post_bind4 | post_bind6 | connect4 |\n" \
" connect6 }"
static const char * const attach_type_strings[] = { static const char * const attach_type_strings[] = {
[BPF_CGROUP_INET_INGRESS] = "ingress", [BPF_CGROUP_INET_INGRESS] = "ingress",
...@@ -25,6 +28,12 @@ static const char * const attach_type_strings[] = { ...@@ -25,6 +28,12 @@ static const char * const attach_type_strings[] = {
[BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create",
[BPF_CGROUP_SOCK_OPS] = "sock_ops", [BPF_CGROUP_SOCK_OPS] = "sock_ops",
[BPF_CGROUP_DEVICE] = "device", [BPF_CGROUP_DEVICE] = "device",
[BPF_CGROUP_INET4_BIND] = "bind4",
[BPF_CGROUP_INET6_BIND] = "bind6",
[BPF_CGROUP_INET4_CONNECT] = "connect4",
[BPF_CGROUP_INET6_CONNECT] = "connect6",
[BPF_CGROUP_INET4_POST_BIND] = "post_bind4",
[BPF_CGROUP_INET6_POST_BIND] = "post_bind6",
[__MAX_BPF_ATTACH_TYPE] = NULL, [__MAX_BPF_ATTACH_TYPE] = NULL,
}; };
...@@ -282,7 +291,7 @@ static int do_help(int argc, char **argv) ...@@ -282,7 +291,7 @@ static int do_help(int argc, char **argv)
" %s %s detach CGROUP ATTACH_TYPE PROG\n" " %s %s detach CGROUP ATTACH_TYPE PROG\n"
" %s %s help\n" " %s %s help\n"
"\n" "\n"
" " HELP_SPEC_ATTACH_TYPES "\n" HELP_SPEC_ATTACH_TYPES "\n"
" " HELP_SPEC_ATTACH_FLAGS "\n" " " HELP_SPEC_ATTACH_FLAGS "\n"
" " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_PROGRAM "\n"
" " HELP_SPEC_OPTIONS "\n" " " HELP_SPEC_OPTIONS "\n"
......
...@@ -283,11 +283,16 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, ...@@ -283,11 +283,16 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key,
static char **parse_bytes(char **argv, const char *name, unsigned char *val, static char **parse_bytes(char **argv, const char *name, unsigned char *val,
unsigned int n) unsigned int n)
{ {
unsigned int i = 0; unsigned int i = 0, base = 0;
char *endptr; char *endptr;
if (is_prefix(*argv, "hex")) {
base = 16;
argv++;
}
while (i < n && argv[i]) { while (i < n && argv[i]) {
val[i] = strtoul(argv[i], &endptr, 0); val[i] = strtoul(argv[i], &endptr, base);
if (*endptr) { if (*endptr) {
p_err("error parsing byte: %s", argv[i]); p_err("error parsing byte: %s", argv[i]);
return NULL; return NULL;
...@@ -869,10 +874,10 @@ static int do_help(int argc, char **argv) ...@@ -869,10 +874,10 @@ static int do_help(int argc, char **argv)
fprintf(stderr, fprintf(stderr,
"Usage: %s %s { show | list } [MAP]\n" "Usage: %s %s { show | list } [MAP]\n"
" %s %s dump MAP\n" " %s %s dump MAP\n"
" %s %s update MAP key BYTES value VALUE [UPDATE_FLAGS]\n" " %s %s update MAP key [hex] BYTES value [hex] VALUE [UPDATE_FLAGS]\n"
" %s %s lookup MAP key BYTES\n" " %s %s lookup MAP key [hex] BYTES\n"
" %s %s getnext MAP [key BYTES]\n" " %s %s getnext MAP [key [hex] BYTES]\n"
" %s %s delete MAP key BYTES\n" " %s %s delete MAP key [hex] BYTES\n"
" %s %s pin MAP FILE\n" " %s %s pin MAP FILE\n"
" %s %s help\n" " %s %s help\n"
"\n" "\n"
......
...@@ -68,6 +68,9 @@ static const char * const prog_type_name[] = { ...@@ -68,6 +68,9 @@ static const char * const prog_type_name[] = {
[BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops",
[BPF_PROG_TYPE_SK_SKB] = "sk_skb", [BPF_PROG_TYPE_SK_SKB] = "sk_skb",
[BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device",
[BPF_PROG_TYPE_SK_MSG] = "sk_msg",
[BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint",
[BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr",
}; };
static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
......
...@@ -95,6 +95,7 @@ enum bpf_cmd { ...@@ -95,6 +95,7 @@ enum bpf_cmd {
BPF_OBJ_GET_INFO_BY_FD, BPF_OBJ_GET_INFO_BY_FD,
BPF_PROG_QUERY, BPF_PROG_QUERY,
BPF_RAW_TRACEPOINT_OPEN, BPF_RAW_TRACEPOINT_OPEN,
BPF_BTF_LOAD,
}; };
enum bpf_map_type { enum bpf_map_type {
...@@ -279,6 +280,9 @@ union bpf_attr { ...@@ -279,6 +280,9 @@ union bpf_attr {
*/ */
char map_name[BPF_OBJ_NAME_LEN]; char map_name[BPF_OBJ_NAME_LEN];
__u32 map_ifindex; /* ifindex of netdev to create on */ __u32 map_ifindex; /* ifindex of netdev to create on */
__u32 btf_fd; /* fd pointing to a BTF type data */
__u32 btf_key_id; /* BTF type_id of the key */
__u32 btf_value_id; /* BTF type_id of the value */
}; };
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
...@@ -363,6 +367,14 @@ union bpf_attr { ...@@ -363,6 +367,14 @@ union bpf_attr {
__u64 name; __u64 name;
__u32 prog_fd; __u32 prog_fd;
} raw_tracepoint; } raw_tracepoint;
struct { /* anonymous struct for BPF_BTF_LOAD */
__aligned_u64 btf;
__aligned_u64 btf_log_buf;
__u32 btf_size;
__u32 btf_log_size;
__u32 btf_log_level;
};
} __attribute__((aligned(8))); } __attribute__((aligned(8)));
/* BPF helper function descriptions: /* BPF helper function descriptions:
...@@ -755,6 +767,13 @@ union bpf_attr { ...@@ -755,6 +767,13 @@ union bpf_attr {
* @addr: pointer to struct sockaddr to bind socket to * @addr: pointer to struct sockaddr to bind socket to
* @addr_len: length of sockaddr structure * @addr_len: length of sockaddr structure
* Return: 0 on success or negative error code * Return: 0 on success or negative error code
*
* int bpf_xdp_adjust_tail(xdp_md, delta)
* Adjust the xdp_md.data_end by delta. Only shrinking of packet's
* size is supported.
* @xdp_md: pointer to xdp_md
* @delta: A negative integer to be added to xdp_md.data_end
* Return: 0 on success or negative on error
*/ */
#define __BPF_FUNC_MAPPER(FN) \ #define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \ FN(unspec), \
...@@ -821,7 +840,8 @@ union bpf_attr { ...@@ -821,7 +840,8 @@ union bpf_attr {
FN(msg_apply_bytes), \ FN(msg_apply_bytes), \
FN(msg_cork_bytes), \ FN(msg_cork_bytes), \
FN(msg_pull_data), \ FN(msg_pull_data), \
FN(bind), FN(bind), \
FN(xdp_adjust_tail),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper /* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call * function eBPF program intends to call
......
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/* Copyright (c) 2018 Facebook */
#ifndef _UAPI__LINUX_BTF_H__
#define _UAPI__LINUX_BTF_H__
#include <linux/types.h>
#define BTF_MAGIC 0xeB9F
#define BTF_MAGIC_SWAP 0x9FeB
#define BTF_VERSION 1
#define BTF_FLAGS_COMPR 0x01
struct btf_header {
__u16 magic;
__u8 version;
__u8 flags;
__u32 parent_label;
__u32 parent_name;
/* All offsets are in bytes relative to the end of this header */
__u32 label_off; /* offset of label section */
__u32 object_off; /* offset of data object section*/
__u32 func_off; /* offset of function section */
__u32 type_off; /* offset of type section */
__u32 str_off; /* offset of string section */
__u32 str_len; /* length of string section */
};
/* Max # of type identifier */
#define BTF_MAX_TYPE 0x7fffffff
/* Max offset into the string section */
#define BTF_MAX_NAME_OFFSET 0x7fffffff
/* Max # of struct/union/enum members or func args */
#define BTF_MAX_VLEN 0xffff
/* The type id is referring to a parent BTF */
#define BTF_TYPE_PARENT(id) (((id) >> 31) & 0x1)
#define BTF_TYPE_ID(id) ((id) & BTF_MAX_TYPE)
/* String is in the ELF string section */
#define BTF_STR_TBL_ELF_ID(ref) (((ref) >> 31) & 0x1)
#define BTF_STR_OFFSET(ref) ((ref) & BTF_MAX_NAME_OFFSET)
struct btf_type {
__u32 name;
/* "info" bits arrangement
* bits 0-15: vlen (e.g. # of struct's members)
* bits 16-23: unused
* bits 24-28: kind (e.g. int, ptr, array...etc)
* bits 29-30: unused
* bits 31: root
*/
__u32 info;
/* "size" is used by INT, ENUM, STRUCT and UNION.
* "size" tells the size of the type it is describing.
*
* "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
* "type" is a type_id referring to another type.
*/
union {
__u32 size;
__u32 type;
};
};
#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f)
#define BTF_INFO_ISROOT(info) (!!(((info) >> 24) & 0x80))
#define BTF_INFO_VLEN(info) ((info) & 0xffff)
#define BTF_KIND_UNKN 0 /* Unknown */
#define BTF_KIND_INT 1 /* Integer */
#define BTF_KIND_PTR 2 /* Pointer */
#define BTF_KIND_ARRAY 3 /* Array */
#define BTF_KIND_STRUCT 4 /* Struct */
#define BTF_KIND_UNION 5 /* Union */
#define BTF_KIND_ENUM 6 /* Enumeration */
#define BTF_KIND_FWD 7 /* Forward */
#define BTF_KIND_TYPEDEF 8 /* Typedef */
#define BTF_KIND_VOLATILE 9 /* Volatile */
#define BTF_KIND_CONST 10 /* Const */
#define BTF_KIND_RESTRICT 11 /* Restrict */
#define BTF_KIND_MAX 11
#define NR_BTF_KINDS 12
/* For some specific BTF_KIND, "struct btf_type" is immediately
* followed by extra data.
*/
/* BTF_KIND_INT is followed by a u32 and the following
* is the 32 bits arrangement:
*/
#define BTF_INT_ENCODING(VAL) (((VAL) & 0xff000000) >> 24)
#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16)
#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff)
/* Attributes stored in the BTF_INT_ENCODING */
#define BTF_INT_SIGNED 0x1
#define BTF_INT_CHAR 0x2
#define BTF_INT_BOOL 0x4
#define BTF_INT_VARARGS 0x8
/* BTF_KIND_ENUM is followed by multiple "struct btf_enum".
* The exact number of btf_enum is stored in the vlen (of the
* info in "struct btf_type").
*/
struct btf_enum {
__u32 name;
__s32 val;
};
/* BTF_KIND_ARRAY is followed by one "struct btf_array" */
struct btf_array {
__u32 type;
__u32 index_type;
__u32 nelems;
};
/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed
* by multiple "struct btf_member". The exact number
* of btf_member is stored in the vlen (of the info in
* "struct btf_type").
*/
struct btf_member {
__u32 name;
__u32 type;
__u32 offset; /* offset in bits */
};
#endif /* _UAPI__LINUX_BTF_H__ */
libbpf-y := libbpf.o bpf.o nlattr.o libbpf-y := libbpf.o bpf.o nlattr.o btf.o
...@@ -73,43 +73,76 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, ...@@ -73,43 +73,76 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
return syscall(__NR_bpf, cmd, attr, size); return syscall(__NR_bpf, cmd, attr, size);
} }
int bpf_create_map_node(enum bpf_map_type map_type, const char *name, int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
int key_size, int value_size, int max_entries,
__u32 map_flags, int node)
{ {
__u32 name_len = name ? strlen(name) : 0; __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0;
union bpf_attr attr; union bpf_attr attr;
memset(&attr, '\0', sizeof(attr)); memset(&attr, '\0', sizeof(attr));
attr.map_type = map_type; attr.map_type = create_attr->map_type;
attr.key_size = key_size; attr.key_size = create_attr->key_size;
attr.value_size = value_size; attr.value_size = create_attr->value_size;
attr.max_entries = max_entries; attr.max_entries = create_attr->max_entries;
attr.map_flags = map_flags; attr.map_flags = create_attr->map_flags;
memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); memcpy(attr.map_name, create_attr->name,
min(name_len, BPF_OBJ_NAME_LEN - 1));
attr.numa_node = create_attr->numa_node;
attr.btf_fd = create_attr->btf_fd;
attr.btf_key_id = create_attr->btf_key_id;
attr.btf_value_id = create_attr->btf_value_id;
return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
}
int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
int key_size, int value_size, int max_entries,
__u32 map_flags, int node)
{
struct bpf_create_map_attr map_attr = {};
map_attr.name = name;
map_attr.map_type = map_type;
map_attr.map_flags = map_flags;
map_attr.key_size = key_size;
map_attr.value_size = value_size;
map_attr.max_entries = max_entries;
if (node >= 0) { if (node >= 0) {
attr.map_flags |= BPF_F_NUMA_NODE; map_attr.numa_node = node;
attr.numa_node = node; map_attr.map_flags |= BPF_F_NUMA_NODE;
} }
return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); return bpf_create_map_xattr(&map_attr);
} }
int bpf_create_map(enum bpf_map_type map_type, int key_size, int bpf_create_map(enum bpf_map_type map_type, int key_size,
int value_size, int max_entries, __u32 map_flags) int value_size, int max_entries, __u32 map_flags)
{ {
return bpf_create_map_node(map_type, NULL, key_size, value_size, struct bpf_create_map_attr map_attr = {};
max_entries, map_flags, -1);
map_attr.map_type = map_type;
map_attr.map_flags = map_flags;
map_attr.key_size = key_size;
map_attr.value_size = value_size;
map_attr.max_entries = max_entries;
return bpf_create_map_xattr(&map_attr);
} }
int bpf_create_map_name(enum bpf_map_type map_type, const char *name, int bpf_create_map_name(enum bpf_map_type map_type, const char *name,
int key_size, int value_size, int max_entries, int key_size, int value_size, int max_entries,
__u32 map_flags) __u32 map_flags)
{ {
return bpf_create_map_node(map_type, name, key_size, value_size, struct bpf_create_map_attr map_attr = {};
max_entries, map_flags, -1);
map_attr.name = name;
map_attr.map_type = map_type;
map_attr.map_flags = map_flags;
map_attr.key_size = key_size;
map_attr.value_size = value_size;
map_attr.max_entries = max_entries;
return bpf_create_map_xattr(&map_attr);
} }
int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
...@@ -573,3 +606,28 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) ...@@ -573,3 +606,28 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
close(sock); close(sock);
return ret; return ret;
} }
int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
bool do_log)
{
union bpf_attr attr = {};
int fd;
attr.btf = ptr_to_u64(btf);
attr.btf_size = btf_size;
retry:
if (do_log && log_buf && log_buf_size) {
attr.btf_log_level = 1;
attr.btf_log_size = log_buf_size;
attr.btf_log_buf = ptr_to_u64(log_buf);
}
fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr));
if (fd == -1 && !do_log && log_buf && log_buf_size) {
do_log = true;
goto retry;
}
return fd;
}
...@@ -24,8 +24,23 @@ ...@@ -24,8 +24,23 @@
#define __BPF_BPF_H #define __BPF_BPF_H
#include <linux/bpf.h> #include <linux/bpf.h>
#include <stdbool.h>
#include <stddef.h> #include <stddef.h>
struct bpf_create_map_attr {
const char *name;
enum bpf_map_type map_type;
__u32 map_flags;
__u32 key_size;
__u32 value_size;
__u32 max_entries;
__u32 numa_node;
__u32 btf_fd;
__u32 btf_key_id;
__u32 btf_value_id;
};
int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
int bpf_create_map_node(enum bpf_map_type map_type, const char *name, int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
int key_size, int value_size, int max_entries, int key_size, int value_size, int max_entries,
__u32 map_flags, int node); __u32 map_flags, int node);
...@@ -87,4 +102,6 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); ...@@ -87,4 +102,6 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
__u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
int bpf_raw_tracepoint_open(const char *name, int prog_fd); int bpf_raw_tracepoint_open(const char *name, int prog_fd);
int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
bool do_log);
#endif #endif
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <stdlib.h>
#include <stdint.h>
#include <string.h>
#include <unistd.h>
#include <errno.h>
#include <linux/err.h>
#include <linux/btf.h>
#include "btf.h"
#include "bpf.h"
#define elog(fmt, ...) { if (err_log) err_log(fmt, ##__VA_ARGS__); }
#define max(a, b) ((a) > (b) ? (a) : (b))
#define min(a, b) ((a) < (b) ? (a) : (b))
#define BTF_MAX_NR_TYPES 65535
static struct btf_type btf_void;
struct btf {
union {
struct btf_header *hdr;
void *data;
};
struct btf_type **types;
const char *strings;
void *nohdr_data;
uint32_t nr_types;
uint32_t types_size;
uint32_t data_size;
int fd;
};
static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset)
{
if (!BTF_STR_TBL_ELF_ID(offset) &&
BTF_STR_OFFSET(offset) < btf->hdr->str_len)
return &btf->strings[BTF_STR_OFFSET(offset)];
else
return NULL;
}
static int btf_add_type(struct btf *btf, struct btf_type *t)
{
if (btf->types_size - btf->nr_types < 2) {
struct btf_type **new_types;
u32 expand_by, new_size;
if (btf->types_size == BTF_MAX_NR_TYPES)
return -E2BIG;
expand_by = max(btf->types_size >> 2, 16);
new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by);
new_types = realloc(btf->types, sizeof(*new_types) * new_size);
if (!new_types)
return -ENOMEM;
if (btf->nr_types == 0)
new_types[0] = &btf_void;
btf->types = new_types;
btf->types_size = new_size;
}
btf->types[++(btf->nr_types)] = t;
return 0;
}
static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log)
{
const struct btf_header *hdr = btf->hdr;
u32 meta_left;
if (btf->data_size < sizeof(struct btf_header)) {
elog("BTF header not found\n");
return -EINVAL;
}
if (hdr->magic != BTF_MAGIC) {
elog("Invalid BTF magic:%x\n", hdr->magic);
return -EINVAL;
}
if (hdr->version != BTF_VERSION) {
elog("Unsupported BTF version:%u\n", hdr->version);
return -ENOTSUP;
}
if (hdr->flags) {
elog("Unsupported BTF flags:%x\n", hdr->flags);
return -ENOTSUP;
}
meta_left = btf->data_size - sizeof(*hdr);
if (!meta_left) {
elog("BTF has no data\n");
return -EINVAL;
}
if (meta_left < hdr->type_off) {
elog("Invalid BTF type section offset:%u\n", hdr->type_off);
return -EINVAL;
}
if (meta_left < hdr->str_off) {
elog("Invalid BTF string section offset:%u\n", hdr->str_off);
return -EINVAL;
}
if (hdr->type_off >= hdr->str_off) {
elog("BTF type section offset >= string section offset. No type?\n");
return -EINVAL;
}
if (hdr->type_off & 0x02) {
elog("BTF type section is not aligned to 4 bytes\n");
return -EINVAL;
}
btf->nohdr_data = btf->hdr + 1;
return 0;
}
static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log)
{
const struct btf_header *hdr = btf->hdr;
const char *start = btf->nohdr_data + hdr->str_off;
const char *end = start + btf->hdr->str_len;
if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET ||
start[0] || end[-1]) {
elog("Invalid BTF string section\n");
return -EINVAL;
}
btf->strings = start;
return 0;
}
static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
{
struct btf_header *hdr = btf->hdr;
void *nohdr_data = btf->nohdr_data;
void *next_type = nohdr_data + hdr->type_off;
void *end_type = nohdr_data + hdr->str_off;
while (next_type < end_type) {
struct btf_type *t = next_type;
uint16_t vlen = BTF_INFO_VLEN(t->info);
int err;
next_type += sizeof(*t);
switch (BTF_INFO_KIND(t->info)) {
case BTF_KIND_INT:
next_type += sizeof(int);
break;
case BTF_KIND_ARRAY:
next_type += sizeof(struct btf_array);
break;
case BTF_KIND_STRUCT:
case BTF_KIND_UNION:
next_type += vlen * sizeof(struct btf_member);
break;
case BTF_KIND_ENUM:
next_type += vlen * sizeof(struct btf_enum);
break;
case BTF_KIND_TYPEDEF:
case BTF_KIND_PTR:
case BTF_KIND_FWD:
case BTF_KIND_VOLATILE:
case BTF_KIND_CONST:
case BTF_KIND_RESTRICT:
break;
default:
elog("Unsupported BTF_KIND:%u\n",
BTF_INFO_KIND(t->info));
return -EINVAL;
}
err = btf_add_type(btf, t);
if (err)
return err;
}
return 0;
}
static const struct btf_type *btf_type_by_id(const struct btf *btf,
uint32_t type_id)
{
if (type_id > btf->nr_types)
return NULL;
return btf->types[type_id];
}
static bool btf_type_is_void(const struct btf_type *t)
{
return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
}
static bool btf_type_is_void_or_null(const struct btf_type *t)
{
return !t || btf_type_is_void(t);
}
static int64_t btf_type_size(const struct btf_type *t)
{
switch (BTF_INFO_KIND(t->info)) {
case BTF_KIND_INT:
case BTF_KIND_STRUCT:
case BTF_KIND_UNION:
case BTF_KIND_ENUM:
return t->size;
case BTF_KIND_PTR:
return sizeof(void *);
default:
return -EINVAL;
}
}
#define MAX_RESOLVE_DEPTH 32
int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
{
const struct btf_array *array;
const struct btf_type *t;
uint32_t nelems = 1;
int64_t size = -1;
int i;
t = btf_type_by_id(btf, type_id);
for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
i++) {
size = btf_type_size(t);
if (size >= 0)
break;
switch (BTF_INFO_KIND(t->info)) {
case BTF_KIND_TYPEDEF:
case BTF_KIND_VOLATILE:
case BTF_KIND_CONST:
case BTF_KIND_RESTRICT:
type_id = t->type;
break;
case BTF_KIND_ARRAY:
array = (const struct btf_array *)(t + 1);
if (nelems && array->nelems > UINT32_MAX / nelems)
return -E2BIG;
nelems *= array->nelems;
type_id = array->type;
break;
default:
return -EINVAL;
}
t = btf_type_by_id(btf, type_id);
}
if (size < 0)
return -EINVAL;
if (nelems && size > UINT32_MAX / nelems)
return -E2BIG;
return nelems * size;
}
int32_t btf__find_by_name(const struct btf *btf, const char *type_name)
{
uint32_t i;
if (!strcmp(type_name, "void"))
return 0;
for (i = 1; i <= btf->nr_types; i++) {
const struct btf_type *t = btf->types[i];
const char *name = btf_name_by_offset(btf, t->name);
if (name && !strcmp(type_name, name))
return i;
}
return -ENOENT;
}
void btf__free(struct btf *btf)
{
if (!btf)
return;
if (btf->fd != -1)
close(btf->fd);
free(btf->data);
free(btf->types);
free(btf);
}
struct btf *btf__new(uint8_t *data, uint32_t size,
btf_print_fn_t err_log)
{
uint32_t log_buf_size = 0;
char *log_buf = NULL;
struct btf *btf;
int err;
btf = calloc(1, sizeof(struct btf));
if (!btf)
return ERR_PTR(-ENOMEM);
btf->fd = -1;
if (err_log) {
log_buf = malloc(BPF_LOG_BUF_SIZE);
if (!log_buf) {
err = -ENOMEM;
goto done;
}
*log_buf = 0;
log_buf_size = BPF_LOG_BUF_SIZE;
}
btf->data = malloc(size);
if (!btf->data) {
err = -ENOMEM;
goto done;
}
memcpy(btf->data, data, size);
btf->data_size = size;
btf->fd = bpf_load_btf(btf->data, btf->data_size,
log_buf, log_buf_size, false);
if (btf->fd == -1) {
err = -errno;
elog("Error loading BTF: %s(%d)\n", strerror(errno), errno);
if (log_buf && *log_buf)
elog("%s\n", log_buf);
goto done;
}
err = btf_parse_hdr(btf, err_log);
if (err)
goto done;
err = btf_parse_str_sec(btf, err_log);
if (err)
goto done;
err = btf_parse_type_sec(btf, err_log);
done:
free(log_buf);
if (err) {
btf__free(btf);
return ERR_PTR(err);
}
return btf;
}
int btf__fd(const struct btf *btf)
{
return btf->fd;
}
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#ifndef __BPF_BTF_H
#define __BPF_BTF_H
#include <stdint.h>
#define BTF_ELF_SEC ".BTF"
struct btf;
typedef int (*btf_print_fn_t)(const char *, ...)
__attribute__((format(printf, 1, 2)));
void btf__free(struct btf *btf);
struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log);
int32_t btf__find_by_name(const struct btf *btf, const char *type_name);
int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id);
int btf__fd(const struct btf *btf);
#endif
...@@ -45,6 +45,7 @@ ...@@ -45,6 +45,7 @@
#include "libbpf.h" #include "libbpf.h"
#include "bpf.h" #include "bpf.h"
#include "btf.h"
#ifndef EM_BPF #ifndef EM_BPF
#define EM_BPF 247 #define EM_BPF 247
...@@ -212,6 +213,8 @@ struct bpf_map { ...@@ -212,6 +213,8 @@ struct bpf_map {
char *name; char *name;
size_t offset; size_t offset;
struct bpf_map_def def; struct bpf_map_def def;
uint32_t btf_key_id;
uint32_t btf_value_id;
void *priv; void *priv;
bpf_map_clear_priv_t clear_priv; bpf_map_clear_priv_t clear_priv;
}; };
...@@ -256,6 +259,8 @@ struct bpf_object { ...@@ -256,6 +259,8 @@ struct bpf_object {
*/ */
struct list_head list; struct list_head list;
struct btf *btf;
void *priv; void *priv;
bpf_object_clear_priv_t clear_priv; bpf_object_clear_priv_t clear_priv;
...@@ -819,7 +824,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj) ...@@ -819,7 +824,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
data->d_size); data->d_size);
else if (strcmp(name, "maps") == 0) else if (strcmp(name, "maps") == 0)
obj->efile.maps_shndx = idx; obj->efile.maps_shndx = idx;
else if (sh.sh_type == SHT_SYMTAB) { else if (strcmp(name, BTF_ELF_SEC) == 0) {
obj->btf = btf__new(data->d_buf, data->d_size,
__pr_debug);
if (IS_ERR(obj->btf)) {
pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
BTF_ELF_SEC, PTR_ERR(obj->btf));
obj->btf = NULL;
}
} else if (sh.sh_type == SHT_SYMTAB) {
if (obj->efile.symbols) { if (obj->efile.symbols) {
pr_warning("bpf: multiple SYMTAB in %s\n", pr_warning("bpf: multiple SYMTAB in %s\n",
obj->path); obj->path);
...@@ -996,33 +1009,126 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, ...@@ -996,33 +1009,126 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
return 0; return 0;
} }
static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
{
struct bpf_map_def *def = &map->def;
const size_t max_name = 256;
int64_t key_size, value_size;
int32_t key_id, value_id;
char name[max_name];
/* Find key type by name from BTF */
if (snprintf(name, max_name, "%s_key", map->name) == max_name) {
pr_warning("map:%s length of BTF key_type:%s_key is too long\n",
map->name, map->name);
return -EINVAL;
}
key_id = btf__find_by_name(btf, name);
if (key_id < 0) {
pr_debug("map:%s key_type:%s cannot be found in BTF\n",
map->name, name);
return key_id;
}
key_size = btf__resolve_size(btf, key_id);
if (key_size < 0) {
pr_warning("map:%s key_type:%s cannot get the BTF type_size\n",
map->name, name);
return key_size;
}
if (def->key_size != key_size) {
pr_warning("map:%s key_type:%s has BTF type_size:%ld != key_size:%u\n",
map->name, name, key_size, def->key_size);
return -EINVAL;
}
/* Find value type from BTF */
if (snprintf(name, max_name, "%s_value", map->name) == max_name) {
pr_warning("map:%s length of BTF value_type:%s_value is too long\n",
map->name, map->name);
return -EINVAL;
}
value_id = btf__find_by_name(btf, name);
if (value_id < 0) {
pr_debug("map:%s value_type:%s cannot be found in BTF\n",
map->name, name);
return value_id;
}
value_size = btf__resolve_size(btf, value_id);
if (value_size < 0) {
pr_warning("map:%s value_type:%s cannot get the BTF type_size\n",
map->name, name);
return value_size;
}
if (def->value_size != value_size) {
pr_warning("map:%s value_type:%s has BTF type_size:%ld != value_size:%u\n",
map->name, name, value_size, def->value_size);
return -EINVAL;
}
map->btf_key_id = key_id;
map->btf_value_id = value_id;
return 0;
}
static int static int
bpf_object__create_maps(struct bpf_object *obj) bpf_object__create_maps(struct bpf_object *obj)
{ {
struct bpf_create_map_attr create_attr = {};
unsigned int i; unsigned int i;
int err;
for (i = 0; i < obj->nr_maps; i++) { for (i = 0; i < obj->nr_maps; i++) {
struct bpf_map_def *def = &obj->maps[i].def; struct bpf_map *map = &obj->maps[i];
int *pfd = &obj->maps[i].fd; struct bpf_map_def *def = &map->def;
int *pfd = &map->fd;
*pfd = bpf_create_map_name(def->type,
obj->maps[i].name, create_attr.name = map->name;
def->key_size, create_attr.map_type = def->type;
def->value_size, create_attr.map_flags = def->map_flags;
def->max_entries, create_attr.key_size = def->key_size;
def->map_flags); create_attr.value_size = def->value_size;
create_attr.max_entries = def->max_entries;
create_attr.btf_fd = 0;
create_attr.btf_key_id = 0;
create_attr.btf_value_id = 0;
if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) {
create_attr.btf_fd = btf__fd(obj->btf);
create_attr.btf_key_id = map->btf_key_id;
create_attr.btf_value_id = map->btf_value_id;
}
*pfd = bpf_create_map_xattr(&create_attr);
if (*pfd < 0 && create_attr.btf_key_id) {
pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
map->name, strerror(errno), errno);
create_attr.btf_fd = 0;
create_attr.btf_key_id = 0;
create_attr.btf_value_id = 0;
map->btf_key_id = 0;
map->btf_value_id = 0;
*pfd = bpf_create_map_xattr(&create_attr);
}
if (*pfd < 0) { if (*pfd < 0) {
size_t j; size_t j;
int err = *pfd;
err = *pfd;
pr_warning("failed to create map (name: '%s'): %s\n", pr_warning("failed to create map (name: '%s'): %s\n",
obj->maps[i].name, map->name,
strerror(errno)); strerror(errno));
for (j = 0; j < i; j++) for (j = 0; j < i; j++)
zclose(obj->maps[j].fd); zclose(obj->maps[j].fd);
return err; return err;
} }
pr_debug("create map %s: fd=%d\n", obj->maps[i].name, *pfd); pr_debug("create map %s: fd=%d\n", map->name, *pfd);
} }
return 0; return 0;
...@@ -1641,6 +1747,7 @@ void bpf_object__close(struct bpf_object *obj) ...@@ -1641,6 +1747,7 @@ void bpf_object__close(struct bpf_object *obj)
bpf_object__elf_finish(obj); bpf_object__elf_finish(obj);
bpf_object__unload(obj); bpf_object__unload(obj);
btf__free(obj->btf);
for (i = 0; i < obj->nr_maps; i++) { for (i = 0; i < obj->nr_maps; i++) {
zfree(&obj->maps[i].name); zfree(&obj->maps[i].name);
...@@ -1692,6 +1799,11 @@ unsigned int bpf_object__kversion(struct bpf_object *obj) ...@@ -1692,6 +1799,11 @@ unsigned int bpf_object__kversion(struct bpf_object *obj)
return obj ? obj->kern_version : 0; return obj ? obj->kern_version : 0;
} }
int bpf_object__btf_fd(const struct bpf_object *obj)
{
return obj->btf ? btf__fd(obj->btf) : -1;
}
int bpf_object__set_priv(struct bpf_object *obj, void *priv, int bpf_object__set_priv(struct bpf_object *obj, void *priv,
bpf_object_clear_priv_t clear_priv) bpf_object_clear_priv_t clear_priv)
{ {
...@@ -1845,6 +1957,7 @@ BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); ...@@ -1845,6 +1957,7 @@ BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS); BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT); BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT);
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
...@@ -1859,6 +1972,9 @@ static void bpf_program__set_expected_attach_type(struct bpf_program *prog, ...@@ -1859,6 +1972,9 @@ static void bpf_program__set_expected_attach_type(struct bpf_program *prog,
#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_FULL(string, ptype, 0) #define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_FULL(string, ptype, 0)
#define BPF_S_PROG_SEC(string, ptype) \
BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK, ptype)
#define BPF_SA_PROG_SEC(string, ptype) \ #define BPF_SA_PROG_SEC(string, ptype) \
BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, ptype) BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, ptype)
...@@ -1874,6 +1990,7 @@ static const struct { ...@@ -1874,6 +1990,7 @@ static const struct {
BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS),
BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT),
BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT),
BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT),
BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP),
BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT),
BPF_PROG_SEC("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), BPF_PROG_SEC("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB),
...@@ -1889,10 +2006,13 @@ static const struct { ...@@ -1889,10 +2006,13 @@ static const struct {
BPF_SA_PROG_SEC("cgroup/bind6", BPF_CGROUP_INET6_BIND), BPF_SA_PROG_SEC("cgroup/bind6", BPF_CGROUP_INET6_BIND),
BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT), BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT),
BPF_SA_PROG_SEC("cgroup/connect6", BPF_CGROUP_INET6_CONNECT), BPF_SA_PROG_SEC("cgroup/connect6", BPF_CGROUP_INET6_CONNECT),
BPF_S_PROG_SEC("cgroup/post_bind4", BPF_CGROUP_INET4_POST_BIND),
BPF_S_PROG_SEC("cgroup/post_bind6", BPF_CGROUP_INET6_POST_BIND),
}; };
#undef BPF_PROG_SEC #undef BPF_PROG_SEC
#undef BPF_PROG_SEC_FULL #undef BPF_PROG_SEC_FULL
#undef BPF_S_PROG_SEC
#undef BPF_SA_PROG_SEC #undef BPF_SA_PROG_SEC
static int bpf_program__identify_section(struct bpf_program *prog) static int bpf_program__identify_section(struct bpf_program *prog)
...@@ -1929,6 +2049,16 @@ const char *bpf_map__name(struct bpf_map *map) ...@@ -1929,6 +2049,16 @@ const char *bpf_map__name(struct bpf_map *map)
return map ? map->name : NULL; return map ? map->name : NULL;
} }
uint32_t bpf_map__btf_key_id(const struct bpf_map *map)
{
return map ? map->btf_key_id : 0;
}
uint32_t bpf_map__btf_value_id(const struct bpf_map *map)
{
return map ? map->btf_value_id : 0;
}
int bpf_map__set_priv(struct bpf_map *map, void *priv, int bpf_map__set_priv(struct bpf_map *map, void *priv,
bpf_map_clear_priv_t clear_priv) bpf_map_clear_priv_t clear_priv)
{ {
......
...@@ -78,6 +78,7 @@ int bpf_object__load(struct bpf_object *obj); ...@@ -78,6 +78,7 @@ int bpf_object__load(struct bpf_object *obj);
int bpf_object__unload(struct bpf_object *obj); int bpf_object__unload(struct bpf_object *obj);
const char *bpf_object__name(struct bpf_object *obj); const char *bpf_object__name(struct bpf_object *obj);
unsigned int bpf_object__kversion(struct bpf_object *obj); unsigned int bpf_object__kversion(struct bpf_object *obj);
int bpf_object__btf_fd(const struct bpf_object *obj);
struct bpf_object *bpf_object__next(struct bpf_object *prev); struct bpf_object *bpf_object__next(struct bpf_object *prev);
#define bpf_object__for_each_safe(pos, tmp) \ #define bpf_object__for_each_safe(pos, tmp) \
...@@ -185,6 +186,7 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n); ...@@ -185,6 +186,7 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n);
*/ */
int bpf_program__set_socket_filter(struct bpf_program *prog); int bpf_program__set_socket_filter(struct bpf_program *prog);
int bpf_program__set_tracepoint(struct bpf_program *prog); int bpf_program__set_tracepoint(struct bpf_program *prog);
int bpf_program__set_raw_tracepoint(struct bpf_program *prog);
int bpf_program__set_kprobe(struct bpf_program *prog); int bpf_program__set_kprobe(struct bpf_program *prog);
int bpf_program__set_sched_cls(struct bpf_program *prog); int bpf_program__set_sched_cls(struct bpf_program *prog);
int bpf_program__set_sched_act(struct bpf_program *prog); int bpf_program__set_sched_act(struct bpf_program *prog);
...@@ -194,6 +196,7 @@ void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); ...@@ -194,6 +196,7 @@ void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type);
bool bpf_program__is_socket_filter(struct bpf_program *prog); bool bpf_program__is_socket_filter(struct bpf_program *prog);
bool bpf_program__is_tracepoint(struct bpf_program *prog); bool bpf_program__is_tracepoint(struct bpf_program *prog);
bool bpf_program__is_raw_tracepoint(struct bpf_program *prog);
bool bpf_program__is_kprobe(struct bpf_program *prog); bool bpf_program__is_kprobe(struct bpf_program *prog);
bool bpf_program__is_sched_cls(struct bpf_program *prog); bool bpf_program__is_sched_cls(struct bpf_program *prog);
bool bpf_program__is_sched_act(struct bpf_program *prog); bool bpf_program__is_sched_act(struct bpf_program *prog);
...@@ -239,6 +242,8 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); ...@@ -239,6 +242,8 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj);
int bpf_map__fd(struct bpf_map *map); int bpf_map__fd(struct bpf_map *map);
const struct bpf_map_def *bpf_map__def(struct bpf_map *map); const struct bpf_map_def *bpf_map__def(struct bpf_map *map);
const char *bpf_map__name(struct bpf_map *map); const char *bpf_map__name(struct bpf_map *map);
uint32_t bpf_map__btf_key_id(const struct bpf_map *map);
uint32_t bpf_map__btf_value_id(const struct bpf_map *map);
typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
int bpf_map__set_priv(struct bpf_map *map, void *priv, int bpf_map__set_priv(struct bpf_map *map, void *priv,
......
...@@ -24,14 +24,15 @@ urandom_read: urandom_read.c ...@@ -24,14 +24,15 @@ urandom_read: urandom_read.c
# Order correspond to 'make run_tests' order # Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
test_sock test_sock_addr test_sock test_sock_addr test_btf
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \ sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \ test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \ sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
test_btf_haskv.o test_btf_nokv.o
# Order correspond to 'make run_tests' order # Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \ TEST_PROGS := test_kmod.sh \
...@@ -66,6 +67,8 @@ $(BPFOBJ): force ...@@ -66,6 +67,8 @@ $(BPFOBJ): force
CLANG ?= clang CLANG ?= clang
LLC ?= llc LLC ?= llc
LLVM_OBJCOPY ?= llvm-objcopy
BTF_PAHOLE ?= pahole
PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
...@@ -83,9 +86,26 @@ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \ ...@@ -83,9 +86,26 @@ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
$(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
$(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help |& grep dwarfris)
BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help |& grep BTF)
BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version |& grep LLVM)
ifneq ($(BTF_LLC_PROBE),)
ifneq ($(BTF_PAHOLE_PROBE),)
ifneq ($(BTF_OBJCOPY_PROBE),)
CLANG_FLAGS += -g
LLC_FLAGS += -mattr=dwarfris
DWARF2BTF = y
endif
endif
endif
$(OUTPUT)/%.o: %.c $(OUTPUT)/%.o: %.c
$(CLANG) $(CLANG_FLAGS) \ $(CLANG) $(CLANG_FLAGS) \
-O2 -target bpf -emit-llvm -c $< -o - | \ -O2 -target bpf -emit-llvm -c $< -o - | \
$(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
ifeq ($(DWARF2BTF),y)
$(BTF_PAHOLE) -J $@
endif
EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) EXTRA_CLEAN := $(TEST_CUSTOM_PROGS)
...@@ -96,6 +96,9 @@ static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) = ...@@ -96,6 +96,9 @@ static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) =
(void *) BPF_FUNC_msg_pull_data; (void *) BPF_FUNC_msg_pull_data;
static int (*bpf_bind)(void *ctx, void *addr, int addr_len) = static int (*bpf_bind)(void *ctx, void *addr, int addr_len) =
(void *) BPF_FUNC_bind; (void *) BPF_FUNC_bind;
static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
(void *) BPF_FUNC_xdp_adjust_tail;
/* llvm builtin functions that eBPF C program may use to /* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions * emit BPF_LD_ABS and BPF_LD_IND instructions
...@@ -129,6 +132,8 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag ...@@ -129,6 +132,8 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag
(void *) BPF_FUNC_l3_csum_replace; (void *) BPF_FUNC_l3_csum_replace;
static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) = static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
(void *) BPF_FUNC_l4_csum_replace; (void *) BPF_FUNC_l4_csum_replace;
static int (*bpf_csum_diff)(void *from, int from_size, void *to, int to_size, int seed) =
(void *) BPF_FUNC_csum_diff;
static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) = static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
(void *) BPF_FUNC_skb_under_cgroup; (void *) BPF_FUNC_skb_under_cgroup;
static int (*bpf_skb_change_head)(void *, int len, int flags) = static int (*bpf_skb_change_head)(void *, int len, int flags) =
......
/* SPDX-License-Identifier: GPL-2.0
* Copyright (c) 2018 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include "bpf_helpers.h"
int _version SEC("version") = 1;
SEC("xdp_adjust_tail")
int _xdp_adjust_tail(struct xdp_md *xdp)
{
void *data_end = (void *)(long)xdp->data_end;
void *data = (void *)(long)xdp->data;
int offset = 0;
if (data_end - data == 54)
offset = 256;
else
offset = 20;
if (bpf_xdp_adjust_tail(xdp, 0 - offset))
return XDP_DROP;
return XDP_TX;
}
char _license[] SEC("license") = "GPL";
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/err.h>
#include <bpf/bpf.h>
#include <sys/resource.h>
#include <libelf.h>
#include <gelf.h>
#include <string.h>
#include <stdlib.h>
#include <stdio.h>
#include <stdarg.h>
#include <unistd.h>
#include <fcntl.h>
#include <errno.h>
#include <bpf/libbpf.h>
#include <bpf/btf.h>
#include "bpf_rlimit.h"
#define min(a, b) ((a) < (b) ? (a) : (b))
#define __printf(a, b) __attribute__((format(printf, a, b)))
__printf(1, 2)
static int __base_pr(const char *format, ...)
{
va_list args;
int err;
va_start(args, format);
err = vfprintf(stderr, format, args);
va_end(args);
return err;
}
#define BTF_INFO_ENC(kind, root, vlen) \
((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
#define BTF_TYPE_ENC(name, info, size_or_type) \
(name), (info), (size_or_type)
#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \
((encoding) << 24 | (bits_offset) << 16 | (nr_bits))
#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \
BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
BTF_INT_ENC(encoding, bits_offset, bits)
#define BTF_ARRAY_ENC(type, index_type, nr_elems) \
(type), (index_type), (nr_elems)
#define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \
BTF_ARRAY_ENC(type, index_type, nr_elems)
#define BTF_MEMBER_ENC(name, type, bits_offset) \
(name), (type), (bits_offset)
#define BTF_ENUM_ENC(name, val) (name), (val)
#define BTF_TYPEDEF_ENC(name, type) \
BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type)
#define BTF_PTR_ENC(name, type) \
BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type)
#define BTF_END_RAW 0xdeadbeef
#define NAME_TBD 0xdeadb33f
#define MAX_NR_RAW_TYPES 1024
#define BTF_LOG_BUF_SIZE 65535
#ifndef ARRAY_SIZE
# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
#endif
static struct args {
unsigned int raw_test_num;
unsigned int file_test_num;
unsigned int get_info_test_num;
bool raw_test;
bool file_test;
bool get_info_test;
bool pprint_test;
bool always_log;
} args;
static char btf_log_buf[BTF_LOG_BUF_SIZE];
static struct btf_header hdr_tmpl = {
.magic = BTF_MAGIC,
.version = BTF_VERSION,
};
struct btf_raw_test {
const char *descr;
const char *str_sec;
const char *map_name;
__u32 raw_types[MAX_NR_RAW_TYPES];
__u32 str_sec_size;
enum bpf_map_type map_type;
__u32 key_size;
__u32 value_size;
__u32 key_id;
__u32 value_id;
__u32 max_entries;
bool btf_load_err;
bool map_create_err;
int type_off_delta;
int str_off_delta;
int str_len_delta;
};
static struct btf_raw_test raw_tests[] = {
/* enum E {
* E0,
* E1,
* };
*
* struct A {
* int m;
* unsigned long long n;
* char o;
* [3 bytes hole]
* int p[8];
* int q[4][8];
* enum E r;
* };
*/
{
.descr = "struct test #1",
.raw_types = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* unsigned long long */
BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */
/* char */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */
/* int[8] */
BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */
/* struct A { */ /* [5] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 6), 180),
BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* unsigned long long n;*/
BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */
BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */
BTF_MEMBER_ENC(NAME_TBD, 6, 384),/* int q[4][8] */
BTF_MEMBER_ENC(NAME_TBD, 7, 1408), /* enum E r */
/* } */
/* int[4][8] */
BTF_TYPE_ARRAY_ENC(4, 1, 4), /* [6] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), sizeof(int)),
BTF_ENUM_ENC(NAME_TBD, 0),
BTF_ENUM_ENC(NAME_TBD, 1),
BTF_END_RAW,
},
.str_sec = "\0A\0m\0n\0o\0p\0q\0r\0E\0E0\0E1",
.str_sec_size = sizeof("\0A\0m\0n\0o\0p\0q\0r\0E\0E0\0E1"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "struct_test1_map",
.key_size = sizeof(int),
.value_size = 180,
.key_id = 1,
.value_id = 5,
.max_entries = 4,
},
/* typedef struct b Struct_B;
*
* struct A {
* int m;
* struct b n[4];
* const Struct_B o[4];
* };
*
* struct B {
* int m;
* int n;
* };
*/
{
.descr = "struct test #2",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
/* struct b [4] */ /* [2] */
BTF_TYPE_ARRAY_ENC(4, 1, 4),
/* struct A { */ /* [3] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 3), 68),
BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct B n[4] */
BTF_MEMBER_ENC(NAME_TBD, 8, 288),/* const Struct_B o[4];*/
/* } */
/* struct B { */ /* [4] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
BTF_MEMBER_ENC(NAME_TBD, 1, 32),/* int n; */
/* } */
/* const int */ /* [5] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 1),
/* typedef struct b Struct_B */ /* [6] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), 4),
/* const Struct_B */ /* [7] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 6),
/* const Struct_B [4] */ /* [8] */
BTF_TYPE_ARRAY_ENC(7, 1, 4),
BTF_END_RAW,
},
.str_sec = "\0A\0m\0n\0o\0B\0m\0n\0Struct_B",
.str_sec_size = sizeof("\0A\0m\0n\0o\0B\0m\0n\0Struct_B"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "struct_test2_map",
.key_size = sizeof(int),
.value_size = 68,
.key_id = 1,
.value_id = 3,
.max_entries = 4,
},
/* Test member exceeds the size of struct.
*
* struct A {
* int m;
* int n;
* };
*/
{
.descr = "size check test #1",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
/* struct A { */ /* [2] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2 - 1),
BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* int n; */
/* } */
BTF_END_RAW,
},
.str_sec = "\0A\0m\0n",
.str_sec_size = sizeof("\0A\0m\0n"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "size_check1_map",
.key_size = sizeof(int),
.value_size = 1,
.key_id = 1,
.value_id = 2,
.max_entries = 4,
.btf_load_err = true,
},
/* Test member exeeds the size of struct
*
* struct A {
* int m;
* int n[2];
* };
*/
{
.descr = "size check test #2",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)),
/* int[2] */ /* [2] */
BTF_TYPE_ARRAY_ENC(1, 1, 2),
/* struct A { */ /* [3] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 3 - 1),
BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* int n[2]; */
/* } */
BTF_END_RAW,
},
.str_sec = "\0A\0m\0n",
.str_sec_size = sizeof("\0A\0m\0n"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "size_check2_map",
.key_size = sizeof(int),
.value_size = 1,
.key_id = 1,
.value_id = 3,
.max_entries = 4,
.btf_load_err = true,
},
/* Test member exeeds the size of struct
*
* struct A {
* int m;
* void *n;
* };
*/
{
.descr = "size check test #3",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)),
/* void* */ /* [2] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0),
/* struct A { */ /* [3] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) + sizeof(void *) - 1),
BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* void *n; */
/* } */
BTF_END_RAW,
},
.str_sec = "\0A\0m\0n",
.str_sec_size = sizeof("\0A\0m\0n"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "size_check3_map",
.key_size = sizeof(int),
.value_size = 1,
.key_id = 1,
.value_id = 3,
.max_entries = 4,
.btf_load_err = true,
},
/* Test member exceeds the size of struct
*
* enum E {
* E0,
* E1,
* };
*
* struct A {
* int m;
* enum E n;
* };
*/
{
.descr = "size check test #4",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)),
/* enum E { */ /* [2] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), sizeof(int)),
BTF_ENUM_ENC(NAME_TBD, 0),
BTF_ENUM_ENC(NAME_TBD, 1),
/* } */
/* struct A { */ /* [3] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2 - 1),
BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* enum E n; */
/* } */
BTF_END_RAW,
},
.str_sec = "\0E\0E0\0E1\0A\0m\0n",
.str_sec_size = sizeof("\0E\0E0\0E1\0A\0m\0n"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "size_check4_map",
.key_size = sizeof(int),
.value_size = 1,
.key_id = 1,
.value_id = 3,
.max_entries = 4,
.btf_load_err = true,
},
/* typedef const void * const_void_ptr;
* struct A {
* const_void_ptr m;
* };
*/
{
.descr = "void test #1",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
/* const void */ /* [2] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0),
/* const void* */ /* [3] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2),
/* typedef const void * const_void_ptr */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3),
/* struct A { */ /* [4] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)),
/* const_void_ptr m; */
BTF_MEMBER_ENC(NAME_TBD, 3, 0),
/* } */
BTF_END_RAW,
},
.str_sec = "\0const_void_ptr\0A\0m",
.str_sec_size = sizeof("\0const_void_ptr\0A\0m"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "void_test1_map",
.key_size = sizeof(int),
.value_size = sizeof(void *),
.key_id = 1,
.value_id = 4,
.max_entries = 4,
},
/* struct A {
* const void m;
* };
*/
{
.descr = "void test #2",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
/* const void */ /* [2] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0),
/* struct A { */ /* [3] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 8),
/* const void m; */
BTF_MEMBER_ENC(NAME_TBD, 2, 0),
/* } */
BTF_END_RAW,
},
.str_sec = "\0A\0m",
.str_sec_size = sizeof("\0A\0m"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "void_test2_map",
.key_size = sizeof(int),
.value_size = sizeof(void *),
.key_id = 1,
.value_id = 3,
.max_entries = 4,
.btf_load_err = true,
},
/* typedef const void * const_void_ptr;
* const_void_ptr[4]
*/
{
.descr = "void test #3",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
/* const void */ /* [2] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0),
/* const void* */ /* [3] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2),
/* typedef const void * const_void_ptr */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3),
/* const_void_ptr[4] */ /* [4] */
BTF_TYPE_ARRAY_ENC(3, 1, 4),
BTF_END_RAW,
},
.str_sec = "\0const_void_ptr",
.str_sec_size = sizeof("\0const_void_ptr"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "void_test3_map",
.key_size = sizeof(int),
.value_size = sizeof(void *) * 4,
.key_id = 1,
.value_id = 4,
.max_entries = 4,
},
/* const void[4] */
{
.descr = "void test #4",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
/* const void */ /* [2] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0),
/* const void[4] */ /* [3] */
BTF_TYPE_ARRAY_ENC(2, 1, 4),
BTF_END_RAW,
},
.str_sec = "\0A\0m",
.str_sec_size = sizeof("\0A\0m"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "void_test4_map",
.key_size = sizeof(int),
.value_size = sizeof(void *) * 4,
.key_id = 1,
.value_id = 3,
.max_entries = 4,
.btf_load_err = true,
},
/* Array_A <------------------+
* elem_type == Array_B |
* | |
* | |
* Array_B <-------- + |
* elem_type == Array A --+
*/
{
.descr = "loop test #1",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
/* Array_A */ /* [2] */
BTF_TYPE_ARRAY_ENC(3, 1, 8),
/* Array_B */ /* [3] */
BTF_TYPE_ARRAY_ENC(2, 1, 8),
BTF_END_RAW,
},
.str_sec = "",
.str_sec_size = sizeof(""),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "loop_test1_map",
.key_size = sizeof(int),
.value_size = sizeof(sizeof(int) * 8),
.key_id = 1,
.value_id = 2,
.max_entries = 4,
.btf_load_err = true,
},
/* typedef is _before_ the BTF type of Array_A and Array_B
*
* typedef Array_B int_array;
*
* Array_A <------------------+
* elem_type == int_array |
* | |
* | |
* Array_B <-------- + |
* elem_type == Array_A --+
*/
{
.descr = "loop test #2",
.raw_types = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* typedef Array_B int_array */
BTF_TYPEDEF_ENC(1, 4), /* [2] */
/* Array_A */
BTF_TYPE_ARRAY_ENC(2, 1, 8), /* [3] */
/* Array_B */
BTF_TYPE_ARRAY_ENC(3, 1, 8), /* [4] */
BTF_END_RAW,
},
.str_sec = "\0int_array\0",
.str_sec_size = sizeof("\0int_array"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "loop_test2_map",
.key_size = sizeof(int),
.value_size = sizeof(sizeof(int) * 8),
.key_id = 1,
.value_id = 2,
.max_entries = 4,
.btf_load_err = true,
},
/* Array_A <------------------+
* elem_type == Array_B |
* | |
* | |
* Array_B <-------- + |
* elem_type == Array_A --+
*/
{
.descr = "loop test #3",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
/* Array_A */ /* [2] */
BTF_TYPE_ARRAY_ENC(3, 1, 8),
/* Array_B */ /* [3] */
BTF_TYPE_ARRAY_ENC(2, 1, 8),
BTF_END_RAW,
},
.str_sec = "",
.str_sec_size = sizeof(""),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "loop_test3_map",
.key_size = sizeof(int),
.value_size = sizeof(sizeof(int) * 8),
.key_id = 1,
.value_id = 2,
.max_entries = 4,
.btf_load_err = true,
},
/* typedef is _between_ the BTF type of Array_A and Array_B
*
* typedef Array_B int_array;
*
* Array_A <------------------+
* elem_type == int_array |
* | |
* | |
* Array_B <-------- + |
* elem_type == Array_A --+
*/
{
.descr = "loop test #4",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
/* Array_A */ /* [2] */
BTF_TYPE_ARRAY_ENC(3, 1, 8),
/* typedef Array_B int_array */ /* [3] */
BTF_TYPEDEF_ENC(NAME_TBD, 4),
/* Array_B */ /* [4] */
BTF_TYPE_ARRAY_ENC(2, 1, 8),
BTF_END_RAW,
},
.str_sec = "\0int_array\0",
.str_sec_size = sizeof("\0int_array"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "loop_test4_map",
.key_size = sizeof(int),
.value_size = sizeof(sizeof(int) * 8),
.key_id = 1,
.value_id = 2,
.max_entries = 4,
.btf_load_err = true,
},
/* typedef struct B Struct_B
*
* struct A {
* int x;
* Struct_B y;
* };
*
* struct B {
* int x;
* struct A y;
* };
*/
{
.descr = "loop test #5",
.raw_types = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* struct A */ /* [2] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */
BTF_MEMBER_ENC(NAME_TBD, 3, 32),/* Struct_B y; */
/* typedef struct B Struct_B */
BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */
/* struct B */ /* [4] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */
BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct A y; */
BTF_END_RAW,
},
.str_sec = "\0A\0x\0y\0Struct_B\0B\0x\0y",
.str_sec_size = sizeof("\0A\0x\0y\0Struct_B\0B\0x\0y"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "loop_test5_map",
.key_size = sizeof(int),
.value_size = 8,
.key_id = 1,
.value_id = 2,
.max_entries = 4,
.btf_load_err = true,
},
/* struct A {
* int x;
* struct A array_a[4];
* };
*/
{
.descr = "loop test #6",
.raw_types = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
BTF_TYPE_ARRAY_ENC(3, 1, 4), /* [2] */
/* struct A */ /* [3] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */
BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct A array_a[4]; */
BTF_END_RAW,
},
.str_sec = "\0A\0x\0y",
.str_sec_size = sizeof("\0A\0x\0y"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "loop_test6_map",
.key_size = sizeof(int),
.value_size = 8,
.key_id = 1,
.value_id = 2,
.max_entries = 4,
.btf_load_err = true,
},
{
.descr = "loop test #7",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
/* struct A { */ /* [2] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)),
/* const void *m; */
BTF_MEMBER_ENC(NAME_TBD, 3, 0),
/* CONST type_id=3 */ /* [3] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 4),
/* PTR type_id=2 */ /* [4] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3),
BTF_END_RAW,
},
.str_sec = "\0A\0m",
.str_sec_size = sizeof("\0A\0m"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "loop_test7_map",
.key_size = sizeof(int),
.value_size = sizeof(void *),
.key_id = 1,
.value_id = 2,
.max_entries = 4,
.btf_load_err = true,
},
{
.descr = "loop test #8",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
/* struct A { */ /* [2] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)),
/* const void *m; */
BTF_MEMBER_ENC(NAME_TBD, 4, 0),
/* struct B { */ /* [3] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)),
/* const void *n; */
BTF_MEMBER_ENC(NAME_TBD, 6, 0),
/* CONST type_id=5 */ /* [4] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 5),
/* PTR type_id=6 */ /* [5] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 6),
/* CONST type_id=7 */ /* [6] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 7),
/* PTR type_id=4 */ /* [7] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 4),
BTF_END_RAW,
},
.str_sec = "\0A\0m\0B\0n",
.str_sec_size = sizeof("\0A\0m\0B\0n"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "loop_test8_map",
.key_size = sizeof(int),
.value_size = sizeof(void *),
.key_id = 1,
.value_id = 2,
.max_entries = 4,
.btf_load_err = true,
},
{
.descr = "type_off == str_off",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
BTF_END_RAW,
},
.str_sec = "\0int",
.str_sec_size = sizeof("\0int"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "hdr_test_map",
.key_size = sizeof(int),
.value_size = sizeof(int),
.key_id = 1,
.value_id = 1,
.max_entries = 4,
.btf_load_err = true,
.type_off_delta = sizeof(struct btf_type) + sizeof(int) + sizeof("\0int"),
},
{
.descr = "Unaligned type_off",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
BTF_END_RAW,
},
.str_sec = "\0int",
.str_sec_size = sizeof("\0int"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "hdr_test_map",
.key_size = sizeof(int),
.value_size = sizeof(int),
.key_id = 1,
.value_id = 1,
.max_entries = 4,
.btf_load_err = true,
.type_off_delta = 1,
},
{
.descr = "str_off beyonds btf size",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
BTF_END_RAW,
},
.str_sec = "\0int",
.str_sec_size = sizeof("\0int"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "hdr_test_map",
.key_size = sizeof(int),
.value_size = sizeof(int),
.key_id = 1,
.value_id = 1,
.max_entries = 4,
.btf_load_err = true,
.str_off_delta = sizeof("\0int") + 1,
},
{
.descr = "str_len beyonds btf size",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
BTF_END_RAW,
},
.str_sec = "\0int",
.str_sec_size = sizeof("\0int"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "hdr_test_map",
.key_size = sizeof(int),
.value_size = sizeof(int),
.key_id = 1,
.value_id = 1,
.max_entries = 4,
.btf_load_err = true,
.str_len_delta = 1,
},
{
.descr = "String section does not end with null",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
BTF_END_RAW,
},
.str_sec = "\0int",
.str_sec_size = sizeof("\0int"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "hdr_test_map",
.key_size = sizeof(int),
.value_size = sizeof(int),
.key_id = 1,
.value_id = 1,
.max_entries = 4,
.btf_load_err = true,
.str_len_delta = -1,
},
{
.descr = "Empty string section",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
BTF_END_RAW,
},
.str_sec = "\0int",
.str_sec_size = sizeof("\0int"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "hdr_test_map",
.key_size = sizeof(int),
.value_size = sizeof(int),
.key_id = 1,
.value_id = 1,
.max_entries = 4,
.btf_load_err = true,
.str_len_delta = 0 - (int)sizeof("\0int"),
},
}; /* struct btf_raw_test raw_tests[] */
static const char *get_next_str(const char *start, const char *end)
{
return start < end - 1 ? start + 1 : NULL;
}
static int get_type_sec_size(const __u32 *raw_types)
{
int i;
for (i = MAX_NR_RAW_TYPES - 1;
i >= 0 && raw_types[i] != BTF_END_RAW;
i--)
;
return i < 0 ? i : i * sizeof(raw_types[0]);
}
static void *btf_raw_create(const struct btf_header *hdr,
const __u32 *raw_types,
const char *str,
unsigned int str_sec_size,
unsigned int *btf_size)
{
const char *next_str = str, *end_str = str + str_sec_size;
unsigned int size_needed, offset;
struct btf_header *ret_hdr;
int i, type_sec_size;
uint32_t *ret_types;
void *raw_btf;
type_sec_size = get_type_sec_size(raw_types);
if (type_sec_size < 0) {
fprintf(stderr, "Cannot get nr_raw_types\n");
return NULL;
}
size_needed = sizeof(*hdr) + type_sec_size + str_sec_size;
raw_btf = malloc(size_needed);
if (!raw_btf) {
fprintf(stderr, "Cannot allocate memory for raw_btf\n");
return NULL;
}
/* Copy header */
memcpy(raw_btf, hdr, sizeof(*hdr));
offset = sizeof(*hdr);
/* Copy type section */
ret_types = raw_btf + offset;
for (i = 0; i < type_sec_size / sizeof(raw_types[0]); i++) {
if (raw_types[i] == NAME_TBD) {
next_str = get_next_str(next_str, end_str);
if (!next_str) {
fprintf(stderr, "Error in getting next_str\n");
free(raw_btf);
return NULL;
}
ret_types[i] = next_str - str;
next_str += strlen(next_str);
} else {
ret_types[i] = raw_types[i];
}
}
offset += type_sec_size;
/* Copy string section */
memcpy(raw_btf + offset, str, str_sec_size);
ret_hdr = (struct btf_header *)raw_btf;
ret_hdr->str_off = type_sec_size;
ret_hdr->str_len = str_sec_size;
*btf_size = size_needed;
return raw_btf;
}
static int do_test_raw(unsigned int test_num)
{
struct btf_raw_test *test = &raw_tests[test_num - 1];
struct bpf_create_map_attr create_attr = {};
int map_fd = -1, btf_fd = -1;
unsigned int raw_btf_size;
struct btf_header *hdr;
void *raw_btf;
int err;
fprintf(stderr, "BTF raw test[%u] (%s): ", test_num, test->descr);
raw_btf = btf_raw_create(&hdr_tmpl,
test->raw_types,
test->str_sec,
test->str_sec_size,
&raw_btf_size);
if (!raw_btf)
return -1;
hdr = raw_btf;
hdr->type_off = (int)hdr->type_off + test->type_off_delta;
hdr->str_off = (int)hdr->str_off + test->str_off_delta;
hdr->str_len = (int)hdr->str_len + test->str_len_delta;
*btf_log_buf = '\0';
btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
btf_log_buf, BTF_LOG_BUF_SIZE,
args.always_log);
free(raw_btf);
err = ((btf_fd == -1) != test->btf_load_err);
if (err)
fprintf(stderr, "btf_load_err:%d btf_fd:%d\n",
test->btf_load_err, btf_fd);
if (err || btf_fd == -1)
goto done;
create_attr.name = test->map_name;
create_attr.map_type = test->map_type;
create_attr.key_size = test->key_size;
create_attr.value_size = test->value_size;
create_attr.max_entries = test->max_entries;
create_attr.btf_fd = btf_fd;
create_attr.btf_key_id = test->key_id;
create_attr.btf_value_id = test->value_id;
map_fd = bpf_create_map_xattr(&create_attr);
err = ((map_fd == -1) != test->map_create_err);
if (err)
fprintf(stderr, "map_create_err:%d map_fd:%d\n",
test->map_create_err, map_fd);
done:
if (!err)
fprintf(stderr, "OK\n");
if (*btf_log_buf && (err || args.always_log))
fprintf(stderr, "%s\n", btf_log_buf);
if (btf_fd != -1)
close(btf_fd);
if (map_fd != -1)
close(map_fd);
return err;
}
static int test_raw(void)
{
unsigned int i;
int err = 0;
if (args.raw_test_num)
return do_test_raw(args.raw_test_num);
for (i = 1; i <= ARRAY_SIZE(raw_tests); i++)
err |= do_test_raw(i);
return err;
}
struct btf_get_info_test {
const char *descr;
const char *str_sec;
__u32 raw_types[MAX_NR_RAW_TYPES];
__u32 str_sec_size;
int info_size_delta;
};
const struct btf_get_info_test get_info_tests[] = {
{
.descr = "== raw_btf_size+1",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
BTF_END_RAW,
},
.str_sec = "",
.str_sec_size = sizeof(""),
.info_size_delta = 1,
},
{
.descr = "== raw_btf_size-3",
.raw_types = {
/* int */ /* [1] */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
BTF_END_RAW,
},
.str_sec = "",
.str_sec_size = sizeof(""),
.info_size_delta = -3,
},
};
static int do_test_get_info(unsigned int test_num)
{
const struct btf_get_info_test *test = &get_info_tests[test_num - 1];
unsigned int raw_btf_size, user_btf_size, expected_nbytes;
uint8_t *raw_btf = NULL, *user_btf = NULL;
int btf_fd = -1, err;
fprintf(stderr, "BTF GET_INFO_BY_ID test[%u] (%s): ",
test_num, test->descr);
raw_btf = btf_raw_create(&hdr_tmpl,
test->raw_types,
test->str_sec,
test->str_sec_size,
&raw_btf_size);
if (!raw_btf)
return -1;
*btf_log_buf = '\0';
user_btf = malloc(raw_btf_size);
if (!user_btf) {
fprintf(stderr, "Cannot allocate memory for user_btf\n");
err = -1;
goto done;
}
btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
btf_log_buf, BTF_LOG_BUF_SIZE,
args.always_log);
if (btf_fd == -1) {
fprintf(stderr, "bpf_load_btf:%s(%d)\n",
strerror(errno), errno);
err = -1;
goto done;
}
user_btf_size = (int)raw_btf_size + test->info_size_delta;
expected_nbytes = min(raw_btf_size, user_btf_size);
if (raw_btf_size > expected_nbytes)
memset(user_btf + expected_nbytes, 0xff,
raw_btf_size - expected_nbytes);
err = bpf_obj_get_info_by_fd(btf_fd, user_btf, &user_btf_size);
if (err || user_btf_size != raw_btf_size ||
memcmp(raw_btf, user_btf, expected_nbytes)) {
fprintf(stderr,
"err:%d(errno:%d) raw_btf_size:%u user_btf_size:%u expected_nbytes:%u memcmp:%d\n",
err, errno,
raw_btf_size, user_btf_size, expected_nbytes,
memcmp(raw_btf, user_btf, expected_nbytes));
err = -1;
goto done;
}
while (expected_nbytes < raw_btf_size) {
fprintf(stderr, "%u...", expected_nbytes);
if (user_btf[expected_nbytes++] != 0xff) {
fprintf(stderr, "!= 0xff\n");
err = -1;
goto done;
}
}
fprintf(stderr, "OK\n");
done:
if (*btf_log_buf && (err || args.always_log))
fprintf(stderr, "%s\n", btf_log_buf);
free(raw_btf);
free(user_btf);
if (btf_fd != -1)
close(btf_fd);
return err;
}
static int test_get_info(void)
{
unsigned int i;
int err = 0;
if (args.get_info_test_num)
return do_test_get_info(args.get_info_test_num);
for (i = 1; i <= ARRAY_SIZE(get_info_tests); i++)
err |= do_test_get_info(i);
return err;
}
struct btf_file_test {
const char *file;
bool btf_kv_notfound;
};
static struct btf_file_test file_tests[] = {
{
.file = "test_btf_haskv.o",
},
{
.file = "test_btf_nokv.o",
.btf_kv_notfound = true,
},
};
static int file_has_btf_elf(const char *fn)
{
Elf_Scn *scn = NULL;
GElf_Ehdr ehdr;
int elf_fd;
Elf *elf;
int ret;
if (elf_version(EV_CURRENT) == EV_NONE) {
fprintf(stderr, "Failed to init libelf\n");
return -1;
}
elf_fd = open(fn, O_RDONLY);
if (elf_fd == -1) {
fprintf(stderr, "Cannot open file %s: %s(%d)\n",
fn, strerror(errno), errno);
return -1;
}
elf = elf_begin(elf_fd, ELF_C_READ, NULL);
if (!elf) {
fprintf(stderr, "Failed to read ELF from %s. %s\n", fn,
elf_errmsg(elf_errno()));
ret = -1;
goto done;
}
if (!gelf_getehdr(elf, &ehdr)) {
fprintf(stderr, "Failed to get EHDR from %s\n", fn);
ret = -1;
goto done;
}
while ((scn = elf_nextscn(elf, scn))) {
const char *sh_name;
GElf_Shdr sh;
if (gelf_getshdr(scn, &sh) != &sh) {
fprintf(stderr,
"Failed to get section header from %s\n", fn);
ret = -1;
goto done;
}
sh_name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
if (!strcmp(sh_name, BTF_ELF_SEC)) {
ret = 1;
goto done;
}
}
ret = 0;
done:
close(elf_fd);
elf_end(elf);
return ret;
}
static int do_test_file(unsigned int test_num)
{
const struct btf_file_test *test = &file_tests[test_num - 1];
struct bpf_object *obj = NULL;
struct bpf_program *prog;
struct bpf_map *map;
int err;
fprintf(stderr, "BTF libbpf test[%u] (%s): ", test_num,
test->file);
err = file_has_btf_elf(test->file);
if (err == -1)
return err;
if (err == 0) {
fprintf(stderr, "SKIP. No ELF %s found\n", BTF_ELF_SEC);
return 0;
}
obj = bpf_object__open(test->file);
if (IS_ERR(obj))
return PTR_ERR(obj);
err = bpf_object__btf_fd(obj);
if (err == -1) {
fprintf(stderr, "bpf_object__btf_fd: -1\n");
goto done;
}
prog = bpf_program__next(NULL, obj);
if (!prog) {
fprintf(stderr, "Cannot find bpf_prog\n");
err = -1;
goto done;
}
bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
err = bpf_object__load(obj);
if (err < 0) {
fprintf(stderr, "bpf_object__load: %d\n", err);
goto done;
}
map = bpf_object__find_map_by_name(obj, "btf_map");
if (!map) {
fprintf(stderr, "btf_map not found\n");
err = -1;
goto done;
}
err = (bpf_map__btf_key_id(map) == 0 || bpf_map__btf_value_id(map) == 0)
!= test->btf_kv_notfound;
if (err) {
fprintf(stderr,
"btf_kv_notfound:%u btf_key_id:%u btf_value_id:%u\n",
test->btf_kv_notfound,
bpf_map__btf_key_id(map),
bpf_map__btf_value_id(map));
goto done;
}
fprintf(stderr, "OK\n");
done:
bpf_object__close(obj);
return err;
}
static int test_file(void)
{
unsigned int i;
int err = 0;
if (args.file_test_num)
return do_test_file(args.file_test_num);
for (i = 1; i <= ARRAY_SIZE(file_tests); i++)
err |= do_test_file(i);
return err;
}
const char *pprint_enum_str[] = {
"ENUM_ZERO",
"ENUM_ONE",
"ENUM_TWO",
"ENUM_THREE",
};
struct pprint_mapv {
uint32_t ui32;
uint16_t ui16;
/* 2 bytes hole */
int32_t si32;
uint32_t unused_bits2a:2,
bits28:28,
unused_bits2b:2;
union {
uint64_t ui64;
uint8_t ui8a[8];
};
enum {
ENUM_ZERO,
ENUM_ONE,
ENUM_TWO,
ENUM_THREE,
} aenum;
};
static struct btf_raw_test pprint_test = {
.descr = "BTF pretty print test #1",
.raw_types = {
/* unsighed char */ /* [1] */
BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
/* unsigned short */ /* [2] */
BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
/* unsigned int */ /* [3] */
BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),
/* int */ /* [4] */
BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
/* unsigned long long */ /* [5] */
BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8),
/* 2 bits */ /* [6] */
BTF_TYPE_INT_ENC(0, 0, 0, 2, 2),
/* 28 bits */ /* [7] */
BTF_TYPE_INT_ENC(0, 0, 0, 28, 4),
/* uint8_t[8] */ /* [8] */
BTF_TYPE_ARRAY_ENC(9, 3, 8),
/* typedef unsigned char uint8_t */ /* [9] */
BTF_TYPEDEF_ENC(NAME_TBD, 1),
/* typedef unsigned short uint16_t */ /* [10] */
BTF_TYPEDEF_ENC(NAME_TBD, 2),
/* typedef unsigned int uint32_t */ /* [11] */
BTF_TYPEDEF_ENC(NAME_TBD, 3),
/* typedef int int32_t */ /* [12] */
BTF_TYPEDEF_ENC(NAME_TBD, 4),
/* typedef unsigned long long uint64_t *//* [13] */
BTF_TYPEDEF_ENC(NAME_TBD, 5),
/* union (anon) */ /* [14] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 0, 2), 8),
BTF_MEMBER_ENC(NAME_TBD, 13, 0),/* uint64_t ui64; */
BTF_MEMBER_ENC(NAME_TBD, 8, 0), /* uint8_t ui8a[8]; */
/* enum (anon) */ /* [15] */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 4), 4),
BTF_ENUM_ENC(NAME_TBD, 0),
BTF_ENUM_ENC(NAME_TBD, 1),
BTF_ENUM_ENC(NAME_TBD, 2),
BTF_ENUM_ENC(NAME_TBD, 3),
/* struct pprint_mapv */ /* [16] */
BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 28),
BTF_MEMBER_ENC(NAME_TBD, 11, 0), /* uint32_t ui32 */
BTF_MEMBER_ENC(NAME_TBD, 10, 32), /* uint16_t ui16 */
BTF_MEMBER_ENC(NAME_TBD, 12, 64), /* int32_t si32 */
BTF_MEMBER_ENC(NAME_TBD, 6, 96), /* unused_bits2a */
BTF_MEMBER_ENC(NAME_TBD, 7, 98), /* bits28 */
BTF_MEMBER_ENC(NAME_TBD, 6, 126), /* unused_bits2b */
BTF_MEMBER_ENC(0, 14, 128), /* union (anon) */
BTF_MEMBER_ENC(NAME_TBD, 15, 192), /* aenum */
BTF_END_RAW,
},
.str_sec = "\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum",
.str_sec_size = sizeof("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
.map_type = BPF_MAP_TYPE_ARRAY,
.map_name = "pprint_test",
.key_size = sizeof(unsigned int),
.value_size = sizeof(struct pprint_mapv),
.key_id = 3, /* unsigned int */
.value_id = 16, /* struct pprint_mapv */
.max_entries = 128 * 1024,
};
static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i)
{
v->ui32 = i;
v->si32 = -i;
v->unused_bits2a = 3;
v->bits28 = i;
v->unused_bits2b = 3;
v->ui64 = i;
v->aenum = i & 0x03;
}
static int test_pprint(void)
{
const struct btf_raw_test *test = &pprint_test;
struct bpf_create_map_attr create_attr = {};
int map_fd = -1, btf_fd = -1;
struct pprint_mapv mapv = {};
unsigned int raw_btf_size;
char expected_line[255];
FILE *pin_file = NULL;
char pin_path[255];
size_t line_len = 0;
char *line = NULL;
unsigned int key;
uint8_t *raw_btf;
ssize_t nread;
int err;
fprintf(stderr, "%s......", test->descr);
raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
test->str_sec, test->str_sec_size,
&raw_btf_size);
if (!raw_btf)
return -1;
*btf_log_buf = '\0';
btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
btf_log_buf, BTF_LOG_BUF_SIZE,
args.always_log);
free(raw_btf);
if (btf_fd == -1) {
err = -1;
fprintf(stderr, "bpf_load_btf: %s(%d)\n",
strerror(errno), errno);
goto done;
}
create_attr.name = test->map_name;
create_attr.map_type = test->map_type;
create_attr.key_size = test->key_size;
create_attr.value_size = test->value_size;
create_attr.max_entries = test->max_entries;
create_attr.btf_fd = btf_fd;
create_attr.btf_key_id = test->key_id;
create_attr.btf_value_id = test->value_id;
map_fd = bpf_create_map_xattr(&create_attr);
if (map_fd == -1) {
err = -1;
fprintf(stderr, "bpf_creat_map_btf: %s(%d)\n",
strerror(errno), errno);
goto done;
}
if (snprintf(pin_path, sizeof(pin_path), "%s/%s",
"/sys/fs/bpf", test->map_name) == sizeof(pin_path)) {
err = -1;
fprintf(stderr, "pin_path is too long\n");
goto done;
}
err = bpf_obj_pin(map_fd, pin_path);
if (err) {
fprintf(stderr, "Cannot pin to %s. %s(%d).\n", pin_path,
strerror(errno), errno);
goto done;
}
for (key = 0; key < test->max_entries; key++) {
set_pprint_mapv(&mapv, key);
bpf_map_update_elem(map_fd, &key, &mapv, 0);
}
pin_file = fopen(pin_path, "r");
if (!pin_file) {
err = -1;
fprintf(stderr, "fopen(%s): %s(%d)\n", pin_path,
strerror(errno), errno);
goto done;
}
/* Skip lines start with '#' */
while ((nread = getline(&line, &line_len, pin_file)) > 0 &&
*line == '#')
;
if (nread <= 0) {
err = -1;
fprintf(stderr, "Unexpected EOF\n");
goto done;
}
key = 0;
do {
ssize_t nexpected_line;
set_pprint_mapv(&mapv, key);
nexpected_line = snprintf(expected_line, sizeof(expected_line),
"%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n",
key,
mapv.ui32, mapv.si32,
mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b,
mapv.ui64,
mapv.ui8a[0], mapv.ui8a[1], mapv.ui8a[2], mapv.ui8a[3],
mapv.ui8a[4], mapv.ui8a[5], mapv.ui8a[6], mapv.ui8a[7],
pprint_enum_str[mapv.aenum]);
if (nexpected_line == sizeof(expected_line)) {
err = -1;
fprintf(stderr, "expected_line is too long\n");
goto done;
}
if (strcmp(expected_line, line)) {
err = -1;
fprintf(stderr, "unexpected pprint output\n");
fprintf(stderr, "expected: %s", expected_line);
fprintf(stderr, " read: %s", line);
goto done;
}
nread = getline(&line, &line_len, pin_file);
} while (++key < test->max_entries && nread > 0);
if (key < test->max_entries) {
err = -1;
fprintf(stderr, "Unexpected EOF\n");
goto done;
}
if (nread > 0) {
err = -1;
fprintf(stderr, "Unexpected extra pprint output: %s\n", line);
goto done;
}
err = 0;
done:
if (!err)
fprintf(stderr, "OK\n");
if (*btf_log_buf && (err || args.always_log))
fprintf(stderr, "%s\n", btf_log_buf);
if (btf_fd != -1)
close(btf_fd);
if (map_fd != -1)
close(map_fd);
if (pin_file)
fclose(pin_file);
unlink(pin_path);
free(line);
return err;
}
static void usage(const char *cmd)
{
fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] | [-g test_num (1 - %zu)] | [-f test_num (1 - %zu)] | [-p]]\n",
cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests),
ARRAY_SIZE(file_tests));
}
static int parse_args(int argc, char **argv)
{
const char *optstr = "lpf:r:g:";
int opt;
while ((opt = getopt(argc, argv, optstr)) != -1) {
switch (opt) {
case 'l':
args.always_log = true;
break;
case 'f':
args.file_test_num = atoi(optarg);
args.file_test = true;
break;
case 'r':
args.raw_test_num = atoi(optarg);
args.raw_test = true;
break;
case 'g':
args.get_info_test_num = atoi(optarg);
args.get_info_test = true;
break;
case 'p':
args.pprint_test = true;
break;
case 'h':
usage(argv[0]);
exit(0);
default:
usage(argv[0]);
return -1;
}
}
if (args.raw_test_num &&
(args.raw_test_num < 1 ||
args.raw_test_num > ARRAY_SIZE(raw_tests))) {
fprintf(stderr, "BTF raw test number must be [1 - %zu]\n",
ARRAY_SIZE(raw_tests));
return -1;
}
if (args.file_test_num &&
(args.file_test_num < 1 ||
args.file_test_num > ARRAY_SIZE(file_tests))) {
fprintf(stderr, "BTF file test number must be [1 - %zu]\n",
ARRAY_SIZE(file_tests));
return -1;
}
if (args.get_info_test_num &&
(args.get_info_test_num < 1 ||
args.get_info_test_num > ARRAY_SIZE(get_info_tests))) {
fprintf(stderr, "BTF get info test number must be [1 - %zu]\n",
ARRAY_SIZE(get_info_tests));
return -1;
}
return 0;
}
int main(int argc, char **argv)
{
int err = 0;
err = parse_args(argc, argv);
if (err)
return err;
if (args.always_log)
libbpf_set_print(__base_pr, __base_pr, __base_pr);
if (args.raw_test)
err |= test_raw();
if (args.get_info_test)
err |= test_get_info();
if (args.file_test)
err |= test_file();
if (args.pprint_test)
err |= test_pprint();
if (args.raw_test || args.get_info_test || args.file_test ||
args.pprint_test)
return err;
err |= test_raw();
err |= test_get_info();
err |= test_file();
return err;
}
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <linux/bpf.h>
#include "bpf_helpers.h"
int _version SEC("version") = 1;
struct ipv_counts {
unsigned int v4;
unsigned int v6;
};
typedef int btf_map_key;
typedef struct ipv_counts btf_map_value;
btf_map_key dumm_key;
btf_map_value dummy_value;
struct bpf_map_def SEC("maps") btf_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(struct ipv_counts),
.max_entries = 4,
};
struct dummy_tracepoint_args {
unsigned long long pad;
struct sock *sock;
};
SEC("dummy_tracepoint")
int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
{
struct ipv_counts *counts;
int key = 0;
if (!arg->sock)
return 0;
counts = bpf_map_lookup_elem(&btf_map, &key);
if (!counts)
return 0;
counts->v6++;
return 0;
}
char _license[] SEC("license") = "GPL";
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <linux/bpf.h>
#include "bpf_helpers.h"
int _version SEC("version") = 1;
struct ipv_counts {
unsigned int v4;
unsigned int v6;
};
struct bpf_map_def SEC("maps") btf_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(struct ipv_counts),
.max_entries = 4,
};
struct dummy_tracepoint_args {
unsigned long long pad;
struct sock *sock;
};
SEC("dummy_tracepoint")
int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
{
struct ipv_counts *counts;
int key = 0;
if (!arg->sock)
return 0;
counts = bpf_map_lookup_elem(&btf_map, &key);
if (!counts)
return 0;
counts->v6++;
return 0;
}
char _license[] SEC("license") = "GPL";
...@@ -166,6 +166,37 @@ static void test_xdp(void) ...@@ -166,6 +166,37 @@ static void test_xdp(void)
bpf_object__close(obj); bpf_object__close(obj);
} }
static void test_xdp_adjust_tail(void)
{
const char *file = "./test_adjust_tail.o";
struct bpf_object *obj;
char buf[128];
__u32 duration, retval, size;
int err, prog_fd;
err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
if (err) {
error_cnt++;
return;
}
err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
buf, &size, &retval, &duration);
CHECK(err || errno || retval != XDP_DROP,
"ipv4", "err %d errno %d retval %d size %d\n",
err, errno, retval, size);
err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
buf, &size, &retval, &duration);
CHECK(err || errno || retval != XDP_TX || size != 54,
"ipv6", "err %d errno %d retval %d size %d\n",
err, errno, retval, size);
bpf_object__close(obj);
}
#define MAGIC_VAL 0x1234 #define MAGIC_VAL 0x1234
#define NUM_ITER 100000 #define NUM_ITER 100000
#define VIP_NUM 5 #define VIP_NUM 5
...@@ -1177,6 +1208,7 @@ int main(void) ...@@ -1177,6 +1208,7 @@ int main(void)
{ {
test_pkt_access(); test_pkt_access();
test_xdp(); test_xdp();
test_xdp_adjust_tail();
test_l4lb_all(); test_l4lb_all();
test_xdp_noinline(); test_xdp_noinline();
test_tcp_estats(); test_tcp_estats();
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册