korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-24 12:44:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
Alexei Starovoitov says:

====================
pull-request: bpf-next 2021-04-23

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

We've added 69 non-merge commits during the last 22 day(s) which contain
a total of 69 files changed, 3141 insertions(+), 866 deletions(-).

The main changes are:

1) Add BPF static linker support for extern resolution of global, from Andrii.

2) Refine retval for bpf_get_task_stack helper, from Dave.

3) Add a bpf_snprintf helper, from Florent.

4) A bunch of miscellaneous improvements from many developers.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2021-04-25 18:02:32 -07:00
commit 5f6c2f536d
69 changed files with 3154 additions and 879 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
Documentation/bpf/bpf_devel_QA.rst
View File

@ -29,7 +29,7 @@ list:
This may also include issues related to XDP, BPF tracing, etc.
Given netdev has a high volume of traffic, please also add the BPF
maintainers to Cc (from kernel MAINTAINERS_ file):
maintainers to Cc (from kernel ``MAINTAINERS`` file):
* Alexei Starovoitov <ast@kernel.org>
* Daniel Borkmann <daniel@iogearbox.net>
@ -234,11 +234,11 @@ be subject to change.
Q: samples/bpf preference vs selftests?
---------------------------------------
Q: When should I add code to `samples/bpf/`_ and when to BPF kernel
selftests_ ?
Q: When should I add code to ``samples/bpf/`` and when to BPF kernel
selftests_?
A: In general, we prefer additions to BPF kernel selftests_ rather than
`samples/bpf/`_. The rationale is very simple: kernel selftests are
``samples/bpf/``. The rationale is very simple: kernel selftests are
regularly run by various bots to test for kernel regressions.
The more test cases we add to BPF selftests, the better the coverage
@ -246,9 +246,9 @@ and the less likely it is that those could accidentally break. It is
not that BPF kernel selftests cannot demo how a specific feature can
be used.
That said, `samples/bpf/`_ may be a good place for people to get started,
That said, ``samples/bpf/`` may be a good place for people to get started,
so it might be advisable that simple demos of features could go into
`samples/bpf/`_, but advanced functional and corner-case testing rather
``samples/bpf/``, but advanced functional and corner-case testing rather
into kernel selftests.
If your sample looks like a test case, then go for BPF kernel selftests
@ -449,6 +449,19 @@ from source at
https://github.com/acmel/dwarves
pahole starts to use libbpf definitions and APIs since v1.13 after the
commit 21507cd3e97b ("pahole: add libbpf as submodule under lib/bpf").
It works well with the git repository because the libbpf submodule will
use "git submodule update --init --recursive" to update.
Unfortunately, the default github release source code does not contain
libbpf submodule source code and this will cause build issues, the tarball
from https://git.kernel.org/pub/scm/devel/pahole/pahole.git/ is same with
github, you can get the source tarball with corresponding libbpf submodule
codes from
https://fedorapeople.org/~acme/dwarves
Some distros have pahole version 1.16 packaged already, e.g.
Fedora, Gentoo.
@ -645,10 +658,9 @@ when:
.. Links
.. _Documentation/process/: https://www.kernel.org/doc/html/latest/process/
.. _MAINTAINERS: ../../MAINTAINERS
.. _netdev-FAQ: ../networking/netdev-FAQ.rst
.. _samples/bpf/: ../../samples/bpf/
.. _selftests: ../../tools/testing/selftests/bpf/
.. _selftests:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/bpf/
.. _Documentation/dev-tools/kselftest.rst:
https://www.kernel.org/doc/html/latest/dev-tools/kselftest.html
.. _Documentation/bpf/btf.rst: btf.rst

1
include/linux/bpf-cgroup.h
View File

@ -458,7 +458,6 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr);
#else
struct bpf_prog;
struct cgroup_bpf {};
static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
static inline void cgroup_bpf_offline(struct cgroup *cgrp) {}

23
include/linux/bpf.h
View File

@ -310,6 +310,7 @@ enum bpf_arg_type {
ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */
ARG_PTR_TO_FUNC, /* pointer to a bpf program function */
ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */
ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */
__BPF_ARG_TYPE_MAX,
};
@ -930,7 +931,6 @@ struct bpf_link_primer {
};
struct bpf_struct_ops_value;
struct btf_type;
struct btf_member;
#define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64
@ -1955,6 +1955,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
extern const struct bpf_func_proto bpf_copy_from_user_proto;
extern const struct bpf_func_proto bpf_snprintf_btf_proto;
extern const struct bpf_func_proto bpf_snprintf_proto;
extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto;
@ -2080,4 +2081,24 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
struct btf_id_set;
bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
enum bpf_printf_mod_type {
BPF_PRINTF_INT,
BPF_PRINTF_LONG,
BPF_PRINTF_LONG_LONG,
};
/* Workaround for getting va_list handling working with different argument type
* combinations generically for 32 and 64 bit archs.
*/
#define BPF_CAST_FMT_ARG(arg_nb, args, mod) \
(mod[arg_nb] == BPF_PRINTF_LONG_LONG || \
(mod[arg_nb] == BPF_PRINTF_LONG && __BITS_PER_LONG == 64) \
? (u64)args[arg_nb] \
: (u32)args[arg_nb])
int bpf_printf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
u64 *final_args, enum bpf_printf_mod_type *mod,
u32 num_args);
void bpf_printf_cleanup(void);
#endif /* _LINUX_BPF_H */

9
include/linux/bpf_verifier.h
View File

@ -487,6 +487,15 @@ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,
return ((u64)btf_obj_id(btf) << 32) | 0x80000000 | btf_id;
}
/* unpack the IDs from the key as constructed above */
static inline void bpf_trampoline_unpack_key(u64 key, u32 *obj_id, u32 *btf_id)
{
if (obj_id)
*obj_id = key >> 32;
if (btf_id)
*btf_id = key & 0x7FFFFFFF;
}
int bpf_check_attach_target(struct bpf_verifier_log *log,
const struct bpf_prog *prog,
const struct bpf_prog *tgt_prog,

5
include/linux/skmsg.h
View File

@ -99,7 +99,8 @@ struct sk_psock {
void (*saved_close)(struct sock *sk, long timeout);
void (*saved_write_space)(struct sock *sk);
void (*saved_data_ready)(struct sock *sk);
int (*psock_update_sk_prot)(struct sock *sk, bool restore);
int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock,
bool restore);
struct proto *sk_proto;
struct mutex work_mutex;
struct sk_psock_work_state work_state;
@ -404,7 +405,7 @@ static inline void sk_psock_restore_proto(struct sock *sk,
struct sk_psock *psock)
{
if (psock->psock_update_sk_prot)
psock->psock_update_sk_prot(sk, true);
psock->psock_update_sk_prot(sk, psock, true);
}
static inline void sk_psock_set_state(struct sk_psock *psock,

5
include/net/sock.h
View File

@ -1118,6 +1118,7 @@ struct inet_hashinfo;
struct raw_hashinfo;
struct smc_hashinfo;
struct module;
struct sk_psock;
/*
* caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes
@ -1189,7 +1190,9 @@ struct proto {
void (*rehash)(struct sock *sk);
int (*get_port)(struct sock *sk, unsigned short snum);
#ifdef CONFIG_BPF_SYSCALL
int (*psock_update_sk_prot)(struct sock *sk, bool restore);
int (*psock_update_sk_prot)(struct sock *sk,
struct sk_psock *psock,
bool restore);
#endif
/* Keeping track of sockets in use */

2
include/net/tcp.h
View File

@ -2215,7 +2215,7 @@ struct sk_psock;
#ifdef CONFIG_BPF_SYSCALL
struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
int tcp_bpf_update_proto(struct sock *sk, bool restore);
int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
void tcp_bpf_clone(const struct sock *sk, struct sock *newsk);
#endif /* CONFIG_BPF_SYSCALL */

2
include/net/udp.h
View File

@ -543,7 +543,7 @@ static inline void udp_post_segment_fix_csum(struct sk_buff *skb)
#ifdef CONFIG_BPF_SYSCALL
struct sk_psock;
struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
int udp_bpf_update_proto(struct sock *sk, bool restore);
int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
#endif
#endif /* _UDP_H */

67
include/uapi/linux/bpf.h
View File

@ -312,6 +312,27 @@ union bpf_iter_link_info {
* *ctx_out*, *data_out* (for example, packet data), result of the
* execution *retval*, and *duration* of the test run.
*
* The sizes of the buffers provided as input and output
* parameters *ctx_in*, *ctx_out*, *data_in*, and *data_out* must
* be provided in the corresponding variables *ctx_size_in*,
* *ctx_size_out*, *data_size_in*, and/or *data_size_out*. If any
* of these parameters are not provided (ie set to NULL), the
* corresponding size field must be zero.
*
* Some program types have particular requirements:
*
* **BPF_PROG_TYPE_SK_LOOKUP**
* *data_in* and *data_out* must be NULL.
*
* **BPF_PROG_TYPE_XDP**
* *ctx_in* and *ctx_out* must be NULL.
*
* **BPF_PROG_TYPE_RAW_TRACEPOINT**,
* **BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE**
*
* *ctx_out*, *data_in* and *data_out* must be NULL.
* *repeat* must be zero.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
@ -4061,12 +4082,20 @@ union bpf_attr {
* of new data availability is sent.
* If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
* of new data availability is sent unconditionally.
* If **0** is specified in *flags*, an adaptive notification
* of new data availability is sent.
*
* An adaptive notification is a notification sent whenever the user-space
* process has caught up and consumed all available payloads. In case the user-space
* process is still processing a previous payload, then no notification is needed
* as it will process the newly added payload automatically.
* Return
* 0 on success, or a negative error in case of failure.
*
* void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags)
* Description
* Reserve *size* bytes of payload in a ring buffer *ringbuf*.
* *flags* must be 0.
* Return
* Valid pointer with *size* bytes of memory available; NULL,
* otherwise.
@ -4078,6 +4107,10 @@ union bpf_attr {
* of new data availability is sent.
* If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
* of new data availability is sent unconditionally.
* If **0** is specified in *flags*, an adaptive notification
* of new data availability is sent.
*
* See 'bpf_ringbuf_output()' for the definition of adaptive notification.
* Return
* Nothing. Always succeeds.
*
@ -4088,6 +4121,10 @@ union bpf_attr {
* of new data availability is sent.
* If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
* of new data availability is sent unconditionally.
* If **0** is specified in *flags*, an adaptive notification
* of new data availability is sent.
*
* See 'bpf_ringbuf_output()' for the definition of adaptive notification.
* Return
* Nothing. Always succeeds.
*
@ -4671,6 +4708,33 @@ union bpf_attr {
* Return
* The number of traversed map elements for success, **-EINVAL** for
* invalid **flags**.
*
* long bpf_snprintf(char *str, u32 str_size, const char *fmt, u64 *data, u32 data_len)
* Description
* Outputs a string into the **str** buffer of size **str_size**
* based on a format string stored in a read-only map pointed by
* **fmt**.
*
* Each format specifier in **fmt** corresponds to one u64 element
* in the **data** array. For strings and pointers where pointees
* are accessed, only the pointer values are stored in the *data*
* array. The *data_len* is the size of *data* in bytes.
*
* Formats **%s** and **%p{i,I}{4,6}** require to read kernel
* memory. Reading kernel memory may fail due to either invalid
* address or valid address but requiring a major memory fault. If
* reading kernel memory fails, the string for **%s** will be an
* empty string, and the ip address for **%p{i,I}{4,6}** will be 0.
* Not returning error to bpf program is consistent with what
* **bpf_trace_printk**\ () does for now.
*
* Return
* The strictly positive length of the formatted string, including
* the trailing zero character. If the return value is greater than
* **str_size**, **str** contains a truncated string, guaranteed to
* be zero-terminated except when **str_size** is 0.
*
* Or **-EBUSY** if the per-CPU memory copy buffer is busy.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@ -4838,6 +4902,7 @@ union bpf_attr {
FN(sock_from_file), \
FN(check_mtu), \
FN(for_each_map_elem), \
FN(snprintf), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@ -5379,6 +5444,8 @@ struct bpf_link_info {
} raw_tracepoint;
struct {
__u32 attach_type;
__u32 target_obj_id; /* prog_id for PROG_EXT, otherwise btf object id */
__u32 target_btf_id; /* BTF type id inside the object */
} tracing;
struct {
__u64 cgroup_id;

7
kernel/bpf/core.c
View File

@ -1363,11 +1363,10 @@ u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
* __bpf_prog_run - run eBPF program on a given context
* @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
* @insn: is the array of eBPF instructions
* @stack: is the eBPF storage stack
*
* Decode and execute eBPF instructions.
*/
static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
{
#define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y
#define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
@ -1701,7 +1700,7 @@ static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn
\
FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
ARG1 = (u64) (unsigned long) ctx; \
return ___bpf_prog_run(regs, insn, stack); \
return ___bpf_prog_run(regs, insn); \
}
#define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size
@ -1718,7 +1717,7 @@ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \
BPF_R3 = r3; \
BPF_R4 = r4; \
BPF_R5 = r5; \
return ___bpf_prog_run(regs, insn, stack); \
return ___bpf_prog_run(regs, insn); \
}
#define EVAL1(FN, X) FN(X)

306
kernel/bpf/helpers.c
View File

@ -669,6 +669,310 @@ const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
.arg1_type = ARG_PTR_TO_PERCPU_BTF_ID,
};
static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
size_t bufsz)
{
void __user *user_ptr = (__force void __user *)unsafe_ptr;
buf[0] = 0;
switch (fmt_ptype) {
case 's':
#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
if ((unsigned long)unsafe_ptr < TASK_SIZE)
return strncpy_from_user_nofault(buf, user_ptr, bufsz);
fallthrough;
#endif
case 'k':
return strncpy_from_kernel_nofault(buf, unsafe_ptr, bufsz);
case 'u':
return strncpy_from_user_nofault(buf, user_ptr, bufsz);
}
return -EINVAL;
}
/* Per-cpu temp buffers which can be used by printf-like helpers for %s or %p
*/
#define MAX_PRINTF_BUF_LEN 512
struct bpf_printf_buf {
char tmp_buf[MAX_PRINTF_BUF_LEN];
};
static DEFINE_PER_CPU(struct bpf_printf_buf, bpf_printf_buf);
static DEFINE_PER_CPU(int, bpf_printf_buf_used);
static int try_get_fmt_tmp_buf(char **tmp_buf)
{
struct bpf_printf_buf *bufs;
int used;
if (*tmp_buf)
return 0;
preempt_disable();
used = this_cpu_inc_return(bpf_printf_buf_used);
if (WARN_ON_ONCE(used > 1)) {
this_cpu_dec(bpf_printf_buf_used);
preempt_enable();
return -EBUSY;
}
bufs = this_cpu_ptr(&bpf_printf_buf);
*tmp_buf = bufs->tmp_buf;
return 0;
}
void bpf_printf_cleanup(void)
{
if (this_cpu_read(bpf_printf_buf_used)) {
this_cpu_dec(bpf_printf_buf_used);
preempt_enable();
}
}
/*
* bpf_parse_fmt_str - Generic pass on format strings for printf-like helpers
*
* Returns a negative value if fmt is an invalid format string or 0 otherwise.
*
* This can be used in two ways:
* - Format string verification only: when final_args and mod are NULL
* - Arguments preparation: in addition to the above verification, it writes in
* final_args a copy of raw_args where pointers from BPF have been sanitized
* into pointers safe to use by snprintf. This also writes in the mod array
* the size requirement of each argument, usable by BPF_CAST_FMT_ARG for ex.
*
* In argument preparation mode, if 0 is returned, safe temporary buffers are
* allocated and bpf_printf_cleanup should be called to free them after use.
*/
int bpf_printf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
u64 *final_args, enum bpf_printf_mod_type *mod,
u32 num_args)
{
char *unsafe_ptr = NULL, *tmp_buf = NULL, *fmt_end;
size_t tmp_buf_len = MAX_PRINTF_BUF_LEN;
int err, i, num_spec = 0, copy_size;
enum bpf_printf_mod_type cur_mod;
u64 cur_arg;
char fmt_ptype;
if (!!final_args != !!mod)
return -EINVAL;
fmt_end = strnchr(fmt, fmt_size, 0);
if (!fmt_end)
return -EINVAL;
fmt_size = fmt_end - fmt;
for (i = 0; i < fmt_size; i++) {
if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
err = -EINVAL;
goto cleanup;
}
if (fmt[i] != '%')
continue;
if (fmt[i + 1] == '%') {
i++;
continue;
}
if (num_spec >= num_args) {
err = -EINVAL;
goto cleanup;
}
/* The string is zero-terminated so if fmt[i] != 0, we can
* always access fmt[i + 1], in the worst case it will be a 0
*/
i++;
/* skip optional "[0 +-][num]" width formatting field */
while (fmt[i] == '0' || fmt[i] == '+' || fmt[i] == '-' ||
fmt[i] == ' ')
i++;
if (fmt[i] >= '1' && fmt[i] <= '9') {
i++;
while (fmt[i] >= '0' && fmt[i] <= '9')
i++;
}
if (fmt[i] == 'p') {
cur_mod = BPF_PRINTF_LONG;
if ((fmt[i + 1] == 'k' || fmt[i + 1] == 'u') &&
fmt[i + 2] == 's') {
fmt_ptype = fmt[i + 1];
i += 2;
goto fmt_str;
}
if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) ||
ispunct(fmt[i + 1]) || fmt[i + 1] == 'K' ||
fmt[i + 1] == 'x' || fmt[i + 1] == 'B' ||
fmt[i + 1] == 's' || fmt[i + 1] == 'S') {
/* just kernel pointers */
if (final_args)
cur_arg = raw_args[num_spec];
goto fmt_next;
}
/* only support "%pI4", "%pi4", "%pI6" and "%pi6". */
if ((fmt[i + 1] != 'i' && fmt[i + 1] != 'I') ||
(fmt[i + 2] != '4' && fmt[i + 2] != '6')) {
err = -EINVAL;
goto cleanup;
}
i += 2;
if (!final_args)
goto fmt_next;
if (try_get_fmt_tmp_buf(&tmp_buf)) {
err = -EBUSY;
goto out;
}
copy_size = (fmt[i + 2] == '4') ? 4 : 16;
if (tmp_buf_len < copy_size) {
err = -ENOSPC;
goto cleanup;
}
unsafe_ptr = (char *)(long)raw_args[num_spec];
err = copy_from_kernel_nofault(tmp_buf, unsafe_ptr,
copy_size);
if (err < 0)
memset(tmp_buf, 0, copy_size);
cur_arg = (u64)(long)tmp_buf;
tmp_buf += copy_size;
tmp_buf_len -= copy_size;
goto fmt_next;
} else if (fmt[i] == 's') {
cur_mod = BPF_PRINTF_LONG;
fmt_ptype = fmt[i];
fmt_str:
if (fmt[i + 1] != 0 &&
!isspace(fmt[i + 1]) &&
!ispunct(fmt[i + 1])) {
err = -EINVAL;
goto cleanup;
}
if (!final_args)
goto fmt_next;
if (try_get_fmt_tmp_buf(&tmp_buf)) {
err = -EBUSY;
goto out;
}
if (!tmp_buf_len) {
err = -ENOSPC;
goto cleanup;
}
unsafe_ptr = (char *)(long)raw_args[num_spec];
err = bpf_trace_copy_string(tmp_buf, unsafe_ptr,
fmt_ptype, tmp_buf_len);
if (err < 0) {
tmp_buf[0] = '\0';
err = 1;
}
cur_arg = (u64)(long)tmp_buf;
tmp_buf += err;
tmp_buf_len -= err;
goto fmt_next;
}
cur_mod = BPF_PRINTF_INT;
if (fmt[i] == 'l') {
cur_mod = BPF_PRINTF_LONG;
i++;
}
if (fmt[i] == 'l') {
cur_mod = BPF_PRINTF_LONG_LONG;
i++;
}
if (fmt[i] != 'i' && fmt[i] != 'd' && fmt[i] != 'u' &&
fmt[i] != 'x' && fmt[i] != 'X') {
err = -EINVAL;
goto cleanup;
}
if (final_args)
cur_arg = raw_args[num_spec];
fmt_next:
if (final_args) {
mod[num_spec] = cur_mod;
final_args[num_spec] = cur_arg;
}
num_spec++;
}
err = 0;
cleanup:
if (err)
bpf_printf_cleanup();
out:
return err;
}
#define MAX_SNPRINTF_VARARGS 12
BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt,
const void *, data, u32, data_len)
{
enum bpf_printf_mod_type mod[MAX_SNPRINTF_VARARGS];
u64 args[MAX_SNPRINTF_VARARGS];
int err, num_args;
if (data_len % 8 || data_len > MAX_SNPRINTF_VARARGS * 8 ||
(data_len && !data))
return -EINVAL;
num_args = data_len / 8;
/* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we
* can safely give an unbounded size.
*/
err = bpf_printf_prepare(fmt, UINT_MAX, data, args, mod, num_args);
if (err < 0)
return err;
/* Maximumly we can have MAX_SNPRINTF_VARARGS parameters, just give
* all of them to snprintf().
*/
err = snprintf(str, str_size, fmt, BPF_CAST_FMT_ARG(0, args, mod),
BPF_CAST_FMT_ARG(1, args, mod), BPF_CAST_FMT_ARG(2, args, mod),
BPF_CAST_FMT_ARG(3, args, mod), BPF_CAST_FMT_ARG(4, args, mod),
BPF_CAST_FMT_ARG(5, args, mod), BPF_CAST_FMT_ARG(6, args, mod),
BPF_CAST_FMT_ARG(7, args, mod), BPF_CAST_FMT_ARG(8, args, mod),
BPF_CAST_FMT_ARG(9, args, mod), BPF_CAST_FMT_ARG(10, args, mod),
BPF_CAST_FMT_ARG(11, args, mod));
bpf_printf_cleanup();
return err + 1;
}
const struct bpf_func_proto bpf_snprintf_proto = {
.func = bpf_snprintf,
.gpl_only = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_MEM_OR_NULL,
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
.arg3_type = ARG_PTR_TO_CONST_STR,
.arg4_type = ARG_PTR_TO_MEM_OR_NULL,
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
const struct bpf_func_proto bpf_get_current_task_proto __weak;
const struct bpf_func_proto bpf_probe_read_user_proto __weak;
const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
@ -757,6 +1061,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
return &bpf_probe_read_kernel_str_proto;
case BPF_FUNC_snprintf_btf:
return &bpf_snprintf_btf_proto;
case BPF_FUNC_snprintf:
return &bpf_snprintf_proto;
default:
return NULL;
}

2
kernel/bpf/inode.c
View File

@ -816,8 +816,6 @@ static int __init bpf_init(void)
{
int ret;
mutex_init(&bpf_preload_lock);
ret = sysfs_create_mount_point(fs_kobj, "bpf");
if (ret)
return ret;

3
kernel/bpf/syscall.c
View File

@ -2551,6 +2551,9 @@ static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
container_of(link, struct bpf_tracing_link, link);
info->tracing.attach_type = tr_link->attach_type;
bpf_trampoline_unpack_key(tr_link->trampoline->key,
&info->tracing.target_obj_id,
&info->tracing.target_btf_id);
return 0;
}

84
kernel/bpf/verifier.c
View File

@ -4787,6 +4787,7 @@ static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALU
static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_PERCPU_BTF_ID } };
static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } };
static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } };
static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } };
static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
[ARG_PTR_TO_MAP_KEY] = &map_key_value_types,
@ -4817,6 +4818,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
[ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types,
[ARG_PTR_TO_FUNC] = &func_ptr_types,
[ARG_PTR_TO_STACK_OR_NULL] = &stack_ptr_types,
[ARG_PTR_TO_CONST_STR] = &const_str_ptr_types,
};
static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
@ -5067,6 +5069,44 @@ skip_type_check:
if (err)
return err;
err = check_ptr_alignment(env, reg, 0, size, true);
} else if (arg_type == ARG_PTR_TO_CONST_STR) {
struct bpf_map *map = reg->map_ptr;
int map_off;
u64 map_addr;
char *str_ptr;
if (!bpf_map_is_rdonly(map)) {
verbose(env, "R%d does not point to a readonly map'\n", regno);
return -EACCES;
}
if (!tnum_is_const(reg->var_off)) {
verbose(env, "R%d is not a constant address'\n", regno);
return -EACCES;
}
if (!map->ops->map_direct_value_addr) {
verbose(env, "no direct value access support for this map type\n");
return -EACCES;
}
err = check_map_access(env, regno, reg->off,
map->value_size - reg->off, false);
if (err)
return err;
map_off = reg->off + reg->var_off.value;
err = map->ops->map_direct_value_addr(map, &map_addr, map_off);
if (err) {
verbose(env, "direct value access on string failed\n");
return err;
}
str_ptr = (char *)(long)(map_addr);
if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) {
verbose(env, "string is not zero-terminated\n");
return -EINVAL;
}
}
return err;
@ -5767,6 +5807,7 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
if (ret_type != RET_INTEGER ||
(func_id != BPF_FUNC_get_stack &&
func_id != BPF_FUNC_get_task_stack &&
func_id != BPF_FUNC_probe_read_str &&
func_id != BPF_FUNC_probe_read_kernel_str &&
func_id != BPF_FUNC_probe_read_user_str))
@ -5877,6 +5918,43 @@ static int check_reference_leak(struct bpf_verifier_env *env)
return state->acquired_refs ? -EINVAL : 0;
}
static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
struct bpf_reg_state *regs)
{
struct bpf_reg_state *fmt_reg = &regs[BPF_REG_3];
struct bpf_reg_state *data_len_reg = &regs[BPF_REG_5];
struct bpf_map *fmt_map = fmt_reg->map_ptr;
int err, fmt_map_off, num_args;
u64 fmt_addr;
char *fmt;
/* data must be an array of u64 */
if (data_len_reg->var_off.value % 8)
return -EINVAL;
num_args = data_len_reg->var_off.value / 8;
/* fmt being ARG_PTR_TO_CONST_STR guarantees that var_off is const
* and map_direct_value_addr is set.
*/
fmt_map_off = fmt_reg->off + fmt_reg->var_off.value;
err = fmt_map->ops->map_direct_value_addr(fmt_map, &fmt_addr,
fmt_map_off);
if (err) {
verbose(env, "verifier bug\n");
return -EFAULT;
}
fmt = (char *)(long)fmt_addr + fmt_map_off;
/* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we
* can focus on validating the format specifiers.
*/
err = bpf_printf_prepare(fmt, UINT_MAX, NULL, NULL, NULL, num_args);
if (err < 0)
verbose(env, "Invalid format string\n");
return err;
}
static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx_p)
{
@ -5991,6 +6069,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
return -EINVAL;
}
if (func_id == BPF_FUNC_snprintf) {
err = check_bpf_snprintf_call(env, regs);
if (err < 0)
return err;
}
/* reset caller saved regs */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);

379
kernel/trace/bpf_trace.c
View File

@ -372,188 +372,38 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
return &bpf_probe_write_user_proto;
}
static void bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
size_t bufsz)
{
void __user *user_ptr = (__force void __user *)unsafe_ptr;
buf[0] = 0;
switch (fmt_ptype) {
case 's':
#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
if ((unsigned long)unsafe_ptr < TASK_SIZE) {
strncpy_from_user_nofault(buf, user_ptr, bufsz);
break;
}
fallthrough;
#endif
case 'k':
strncpy_from_kernel_nofault(buf, unsafe_ptr, bufsz);
break;
case 'u':
strncpy_from_user_nofault(buf, user_ptr, bufsz);
break;
}
}
static DEFINE_RAW_SPINLOCK(trace_printk_lock);
#define BPF_TRACE_PRINTK_SIZE 1024
#define MAX_TRACE_PRINTK_VARARGS 3
#define BPF_TRACE_PRINTK_SIZE 1024
static __printf(1, 0) int bpf_do_trace_printk(const char *fmt, ...)
{
static char buf[BPF_TRACE_PRINTK_SIZE];
unsigned long flags;
va_list ap;
int ret;
raw_spin_lock_irqsave(&trace_printk_lock, flags);
va_start(ap, fmt);
ret = vsnprintf(buf, sizeof(buf), fmt, ap);
va_end(ap);
/* vsnprintf() will not append null for zero-length strings */
if (ret == 0)
buf[0] = '\0';
trace_bpf_trace_printk(buf);
raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
return ret;
}
/*
* Only limited trace_printk() conversion specifiers allowed:
* %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pB %pks %pus %s
*/
BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
u64, arg2, u64, arg3)
{
int i, mod[3] = {}, fmt_cnt = 0;
char buf[64], fmt_ptype;
void *unsafe_ptr = NULL;
bool str_seen = false;
u64 args[MAX_TRACE_PRINTK_VARARGS] = { arg1, arg2, arg3 };
enum bpf_printf_mod_type mod[MAX_TRACE_PRINTK_VARARGS];
static char buf[BPF_TRACE_PRINTK_SIZE];
unsigned long flags;
int ret;
/*
* bpf_check()->check_func_arg()->check_stack_boundary()
* guarantees that fmt points to bpf program stack,
* fmt_size bytes of it were initialized and fmt_size > 0
*/
if (fmt[--fmt_size] != 0)
return -EINVAL;
ret = bpf_printf_prepare(fmt, fmt_size, args, args, mod,
MAX_TRACE_PRINTK_VARARGS);
if (ret < 0)
return ret;
/* check format string for allowed specifiers */
for (i = 0; i < fmt_size; i++) {
if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i]))
return -EINVAL;
ret = snprintf(buf, sizeof(buf), fmt, BPF_CAST_FMT_ARG(0, args, mod),
BPF_CAST_FMT_ARG(1, args, mod), BPF_CAST_FMT_ARG(2, args, mod));
/* snprintf() will not append null for zero-length strings */
if (ret == 0)
buf[0] = '\0';
if (fmt[i] != '%')
continue;
raw_spin_lock_irqsave(&trace_printk_lock, flags);
trace_bpf_trace_printk(buf);
raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
if (fmt_cnt >= 3)
return -EINVAL;
bpf_printf_cleanup();
/* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */
i++;
if (fmt[i] == 'l') {
mod[fmt_cnt]++;
i++;
} else if (fmt[i] == 'p') {
mod[fmt_cnt]++;
if ((fmt[i + 1] == 'k' ||
fmt[i + 1] == 'u') &&
fmt[i + 2] == 's') {
fmt_ptype = fmt[i + 1];
i += 2;
goto fmt_str;
}
if (fmt[i + 1] == 'B') {
i++;
goto fmt_next;
}
/* disallow any further format extensions */
if (fmt[i + 1] != 0 &&
!isspace(fmt[i + 1]) &&
!ispunct(fmt[i + 1]))
return -EINVAL;
goto fmt_next;
} else if (fmt[i] == 's') {
mod[fmt_cnt]++;
fmt_ptype = fmt[i];
fmt_str:
if (str_seen)
/* allow only one '%s' per fmt string */
return -EINVAL;
str_seen = true;
if (fmt[i + 1] != 0 &&
!isspace(fmt[i + 1]) &&
!ispunct(fmt[i + 1]))
return -EINVAL;
switch (fmt_cnt) {
case 0:
unsafe_ptr = (void *)(long)arg1;
arg1 = (long)buf;
break;
case 1:
unsafe_ptr = (void *)(long)arg2;
arg2 = (long)buf;
break;
case 2:
unsafe_ptr = (void *)(long)arg3;
arg3 = (long)buf;
break;
}
bpf_trace_copy_string(buf, unsafe_ptr, fmt_ptype,
sizeof(buf));
goto fmt_next;
}
if (fmt[i] == 'l') {
mod[fmt_cnt]++;
i++;
}
if (fmt[i] != 'i' && fmt[i] != 'd' &&
fmt[i] != 'u' && fmt[i] != 'x')
return -EINVAL;
fmt_next:
fmt_cnt++;
}
/* Horrid workaround for getting va_list handling working with different
* argument type combinations generically for 32 and 64 bit archs.
*/
#define __BPF_TP_EMIT() __BPF_ARG3_TP()
#define __BPF_TP(...) \
bpf_do_trace_printk(fmt, ##__VA_ARGS__)
#define __BPF_ARG1_TP(...) \
((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64)) \
? __BPF_TP(arg1, ##__VA_ARGS__) \
: ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32)) \
? __BPF_TP((long)arg1, ##__VA_ARGS__) \
: __BPF_TP((u32)arg1, ##__VA_ARGS__)))
#define __BPF_ARG2_TP(...) \
((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64)) \
? __BPF_ARG1_TP(arg2, ##__VA_ARGS__) \
: ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32)) \
? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__) \
: __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__)))
#define __BPF_ARG3_TP(...) \
((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64)) \
? __BPF_ARG2_TP(arg3, ##__VA_ARGS__) \
: ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32)) \
? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__) \
: __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__)))
return __BPF_TP_EMIT();
return ret;
}
static const struct bpf_func_proto bpf_trace_printk_proto = {
@ -581,184 +431,37 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
}
#define MAX_SEQ_PRINTF_VARARGS 12
#define MAX_SEQ_PRINTF_MAX_MEMCPY 6
#define MAX_SEQ_PRINTF_STR_LEN 128
struct bpf_seq_printf_buf {
char buf[MAX_SEQ_PRINTF_MAX_MEMCPY][MAX_SEQ_PRINTF_STR_LEN];
};
static DEFINE_PER_CPU(struct bpf_seq_printf_buf, bpf_seq_printf_buf);
static DEFINE_PER_CPU(int, bpf_seq_printf_buf_used);
BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
const void *, data, u32, data_len)
{
int err = -EINVAL, fmt_cnt = 0, memcpy_cnt = 0;
int i, buf_used, copy_size, num_args;
u64 params[MAX_SEQ_PRINTF_VARARGS];
struct bpf_seq_printf_buf *bufs;
const u64 *args = data;
buf_used = this_cpu_inc_return(bpf_seq_printf_buf_used);
if (WARN_ON_ONCE(buf_used > 1)) {
err = -EBUSY;
goto out;
}
bufs = this_cpu_ptr(&bpf_seq_printf_buf);
/*
* bpf_check()->check_func_arg()->check_stack_boundary()
* guarantees that fmt points to bpf program stack,
* fmt_size bytes of it were initialized and fmt_size > 0
*/
if (fmt[--fmt_size] != 0)
goto out;
if (data_len & 7)
goto out;
for (i = 0; i < fmt_size; i++) {
if (fmt[i] == '%') {
if (fmt[i + 1] == '%')
i++;
else if (!data || !data_len)
goto out;
}
}
enum bpf_printf_mod_type mod[MAX_SEQ_PRINTF_VARARGS];
u64 args[MAX_SEQ_PRINTF_VARARGS];
int err, num_args;
if (data_len & 7 || data_len > MAX_SEQ_PRINTF_VARARGS * 8 ||
(data_len && !data))
return -EINVAL;
num_args = data_len / 8;
/* check format string for allowed specifiers */
for (i = 0; i < fmt_size; i++) {
/* only printable ascii for now. */
if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
err = -EINVAL;
goto out;
}
if (fmt[i] != '%')
continue;
if (fmt[i + 1] == '%') {
i++;
continue;
}
if (fmt_cnt >= MAX_SEQ_PRINTF_VARARGS) {
err = -E2BIG;
goto out;
}
if (fmt_cnt >= num_args) {
err = -EINVAL;
goto out;
}
/* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */
i++;
/* skip optional "[0 +-][num]" width formating field */
while (fmt[i] == '0' || fmt[i] == '+' || fmt[i] == '-' ||
fmt[i] == ' ')
i++;
if (fmt[i] >= '1' && fmt[i] <= '9') {
i++;
while (fmt[i] >= '0' && fmt[i] <= '9')
i++;
}
if (fmt[i] == 's') {
void *unsafe_ptr;
/* try our best to copy */
if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) {
err = -E2BIG;
goto out;
}
unsafe_ptr = (void *)(long)args[fmt_cnt];
err = strncpy_from_kernel_nofault(bufs->buf[memcpy_cnt],
unsafe_ptr, MAX_SEQ_PRINTF_STR_LEN);
if (err < 0)
bufs->buf[memcpy_cnt][0] = '\0';
params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt];
fmt_cnt++;
memcpy_cnt++;
continue;
}
if (fmt[i] == 'p') {
if (fmt[i + 1] == 0 ||
fmt[i + 1] == 'K' ||
fmt[i + 1] == 'x' ||
fmt[i + 1] == 'B') {
/* just kernel pointers */
params[fmt_cnt] = args[fmt_cnt];
fmt_cnt++;
continue;
}
/* only support "%pI4", "%pi4", "%pI6" and "%pi6". */
if (fmt[i + 1] != 'i' && fmt[i + 1] != 'I') {
err = -EINVAL;
goto out;
}
if (fmt[i + 2] != '4' && fmt[i + 2] != '6') {
err = -EINVAL;
goto out;
}
if (memcpy_cnt >= MAX_SEQ_PRINTF_MAX_MEMCPY) {
err = -E2BIG;
goto out;
}
copy_size = (fmt[i + 2] == '4') ? 4 : 16;
err = copy_from_kernel_nofault(bufs->buf[memcpy_cnt],
(void *) (long) args[fmt_cnt],
copy_size);
if (err < 0)
memset(bufs->buf[memcpy_cnt], 0, copy_size);
params[fmt_cnt] = (u64)(long)bufs->buf[memcpy_cnt];
i += 2;
fmt_cnt++;
memcpy_cnt++;
continue;
}
if (fmt[i] == 'l') {
i++;
if (fmt[i] == 'l')
i++;
}
if (fmt[i] != 'i' && fmt[i] != 'd' &&
fmt[i] != 'u' && fmt[i] != 'x' &&
fmt[i] != 'X') {
err = -EINVAL;
goto out;
}
params[fmt_cnt] = args[fmt_cnt];
fmt_cnt++;
}
err = bpf_printf_prepare(fmt, fmt_size, data, args, mod, num_args);
if (err < 0)
return err;
/* Maximumly we can have MAX_SEQ_PRINTF_VARARGS parameter, just give
* all of them to seq_printf().
*/
seq_printf(m, fmt, params[0], params[1], params[2], params[3],
params[4], params[5], params[6], params[7], params[8],
params[9], params[10], params[11]);
seq_printf(m, fmt, BPF_CAST_FMT_ARG(0, args, mod),
BPF_CAST_FMT_ARG(1, args, mod), BPF_CAST_FMT_ARG(2, args, mod),
BPF_CAST_FMT_ARG(3, args, mod), BPF_CAST_FMT_ARG(4, args, mod),
BPF_CAST_FMT_ARG(5, args, mod), BPF_CAST_FMT_ARG(6, args, mod),
BPF_CAST_FMT_ARG(7, args, mod), BPF_CAST_FMT_ARG(8, args, mod),
BPF_CAST_FMT_ARG(9, args, mod), BPF_CAST_FMT_ARG(10, args, mod),
BPF_CAST_FMT_ARG(11, args, mod));
err = seq_has_overflowed(m) ? -EOVERFLOW : 0;
out:
this_cpu_dec(bpf_seq_printf_buf_used);
return err;
bpf_printf_cleanup();
return seq_has_overflowed(m) ? -EOVERFLOW : 0;
}
BTF_ID_LIST_SINGLE(btf_seq_file_ids, struct, seq_file)
@ -1373,6 +1076,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_task_storage_delete_proto;
case BPF_FUNC_for_each_map_elem:
return &bpf_for_each_map_elem_proto;
case BPF_FUNC_snprintf:
return &bpf_snprintf_proto;
default:
return NULL;
}

6
net/core/dev.c
View File

@ -4723,10 +4723,10 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
void *orig_data, *orig_data_end, *hard_start;
struct netdev_rx_queue *rxqueue;
u32 metalen, act = XDP_DROP;
bool orig_bcast, orig_host;
u32 mac_len, frame_sz;
__be16 orig_eth_type;
struct ethhdr *eth;
bool orig_bcast;
int off;
/* Reinjected packets coming from act_mirred or similar should
@ -4773,6 +4773,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
orig_data_end = xdp->data_end;
orig_data = xdp->data;
eth = (struct ethhdr *)xdp->data;
orig_host = ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr);
orig_bcast = is_multicast_ether_addr_64bits(eth->h_dest);
orig_eth_type = eth->h_proto;
@ -4800,8 +4801,11 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
/* check if XDP changed eth hdr such SKB needs update */
eth = (struct ethhdr *)xdp->data;
if ((orig_eth_type != eth->h_proto) ||
(orig_host != ether_addr_equal_64bits(eth->h_dest,
skb->dev->dev_addr)) ||
(orig_bcast != is_multicast_ether_addr_64bits(eth->h_dest))) {
__skb_push(skb, ETH_HLEN);
skb->pkt_type = PACKET_HOST;
skb->protocol = eth_type_trans(skb, skb->dev);
}

5
net/core/sock_map.c
View File

@ -188,7 +188,7 @@ static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock)
if (!sk->sk_prot->psock_update_sk_prot)
return -EINVAL;
psock->psock_update_sk_prot = sk->sk_prot->psock_update_sk_prot;
return sk->sk_prot->psock_update_sk_prot(sk, false);
return sk->sk_prot->psock_update_sk_prot(sk, psock, false);
}
static struct sk_psock *sock_map_psock_get_checked(struct sock *sk)
@ -1521,7 +1521,7 @@ void sock_map_close(struct sock *sk, long timeout)
lock_sock(sk);
rcu_read_lock();
psock = sk_psock(sk);
psock = sk_psock_get(sk);
if (unlikely(!psock)) {
rcu_read_unlock();
release_sock(sk);
@ -1532,6 +1532,7 @@ void sock_map_close(struct sock *sk, long timeout)
sock_map_remove_links(sk, psock);
rcu_read_unlock();
sk_psock_stop(psock, true);
sk_psock_put(sk, psock);
release_sock(sk);
saved_close(sk, timeout);
}

3
net/ipv4/tcp_bpf.c
View File

@ -499,9 +499,8 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops)
ops->sendpage == tcp_sendpage ? 0 : -ENOTSUPP;
}
int tcp_bpf_update_proto(struct sock *sk, bool restore)
int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
struct sk_psock *psock = sk_psock(sk);
int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE;

5
net/ipv4/udp_bpf.c
View File

@ -103,14 +103,12 @@ static int __init udp_bpf_v4_build_proto(void)
}
core_initcall(udp_bpf_v4_build_proto);
int udp_bpf_update_proto(struct sock *sk, bool restore)
int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
struct sk_psock *psock = sk_psock(sk);
if (restore) {
sk->sk_write_space = psock->saved_write_space;
/* Pairs with lockless read in sk_clone_lock() */
WRITE_ONCE(sk->sk_prot, psock->sk_proto);
return 0;
}
@ -118,7 +116,6 @@ int udp_bpf_update_proto(struct sock *sk, bool restore)
if (sk->sk_family == AF_INET6)
udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
/* Pairs with lockless read in sk_clone_lock() */
WRITE_ONCE(sk->sk_prot, &udp_bpf_prots[family]);
return 0;
}

2
net/xdp/xsk.c
View File

@ -30,7 +30,7 @@
#include "xdp_umem.h"
#include "xsk.h"
#define TX_BATCH_SIZE 16
#define TX_BATCH_SIZE 32
static DEFINE_PER_CPU(struct list_head, xskmap_flush_list);

4
samples/bpf/tracex1_kern.c
View File

@ -26,7 +26,7 @@
SEC("kprobe/__netif_receive_skb_core")
int bpf_prog1(struct pt_regs *ctx)
{
/* attaches to kprobe netif_receive_skb,
/* attaches to kprobe __netif_receive_skb_core,
* looks for packets on loobpack device and prints them
*/
char devname[IFNAMSIZ];
@ -35,7 +35,7 @@ int bpf_prog1(struct pt_regs *ctx)
int len;
/* non-portable! works for the given kernel only */
skb = (struct sk_buff *) PT_REGS_PARM1(ctx);
bpf_probe_read_kernel(&skb, sizeof(skb), (void *)PT_REGS_PARM1(ctx));
dev = _(skb->dev);
len = _(skb->len);

7
scripts/link-vmlinux.sh
View File

@ -213,6 +213,7 @@ vmlinux_link()
gen_btf()
{
local pahole_ver
local extra_paholeopt=
if ! [ -x "$(command -v ${PAHOLE})" ]; then
echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available"
@ -227,8 +228,12 @@ gen_btf()
vmlinux_link ${1}
if [ "${pahole_ver}" -ge "121" ]; then
extra_paholeopt="${extra_paholeopt} --btf_gen_floats"
fi
info "BTF" ${2}
LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${1}
LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${extra_paholeopt} ${1}
# Create ${2} which contains just .BTF section but no symbols. Add
# SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all

30
tools/bpf/bpftool/btf.c
View File

@ -71,7 +71,9 @@ static const char *btf_var_linkage_str(__u32 linkage)
case BTF_VAR_STATIC:
return "static";
case BTF_VAR_GLOBAL_ALLOCATED:
return "global-alloc";
return "global";
case BTF_VAR_GLOBAL_EXTERN:
return "extern";
default:
return "(unknown)";
}
@ -98,26 +100,28 @@ static const char *btf_str(const struct btf *btf, __u32 off)
return btf__name_by_offset(btf, off) ? : "(invalid)";
}
static int btf_kind_safe(int kind)
{
return kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN;
}
static int dump_btf_type(const struct btf *btf, __u32 id,
const struct btf_type *t)
{
json_writer_t *w = json_wtr;
int kind, safe_kind;
kind = BTF_INFO_KIND(t->info);
safe_kind = kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN;
int kind = btf_kind(t);
if (json_output) {
jsonw_start_object(w);
jsonw_uint_field(w, "id", id);
jsonw_string_field(w, "kind", btf_kind_str[safe_kind]);
jsonw_string_field(w, "kind", btf_kind_str[btf_kind_safe(kind)]);
jsonw_string_field(w, "name", btf_str(btf, t->name_off));
} else {
printf("[%u] %s '%s'", id, btf_kind_str[safe_kind],
printf("[%u] %s '%s'", id, btf_kind_str[btf_kind_safe(kind)],
btf_str(btf, t->name_off));
}
switch (BTF_INFO_KIND(t->info)) {
switch (kind) {
case BTF_KIND_INT: {
__u32 v = *(__u32 *)(t + 1);
const char *enc;
@ -300,7 +304,8 @@ static int dump_btf_type(const struct btf *btf, __u32 id,
break;
}
case BTF_KIND_DATASEC: {
const struct btf_var_secinfo *v = (const void *)(t+1);
const struct btf_var_secinfo *v = (const void *)(t + 1);
const struct btf_type *vt;
__u16 vlen = BTF_INFO_VLEN(t->info);
int i;
@ -322,6 +327,13 @@ static int dump_btf_type(const struct btf *btf, __u32 id,
} else {
printf("\n\ttype_id=%u offset=%u size=%u",
v->type, v->offset, v->size);
if (v->type <= btf__get_nr_types(btf)) {
vt = btf__type_by_id(btf, v->type);
printf(" (%s '%s')",
btf_kind_str[btf_kind_safe(btf_kind(vt))],
btf_str(btf, vt->name_off));
}
}
}
if (json_output)

2
tools/bpf/bpftool/net.c
View File

@ -157,7 +157,7 @@ static int netlink_recv(int sock, __u32 nl_pid, __u32 seq,
if (len == 0)
break;
for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, (unsigned int)len);
nh = NLMSG_NEXT(nh, len)) {
if (nh->nlmsg_pid != nl_pid) {
ret = -LIBBPF_ERRNO__WRNGPID;

83
tools/include/uapi/linux/bpf.h
View File

@ -312,6 +312,27 @@ union bpf_iter_link_info {
* *ctx_out*, *data_out* (for example, packet data), result of the
* execution *retval*, and *duration* of the test run.
*
* The sizes of the buffers provided as input and output
* parameters *ctx_in*, *ctx_out*, *data_in*, and *data_out* must
* be provided in the corresponding variables *ctx_size_in*,
* *ctx_size_out*, *data_size_in*, and/or *data_size_out*. If any
* of these parameters are not provided (ie set to NULL), the
* corresponding size field must be zero.
*
* Some program types have particular requirements:
*
* **BPF_PROG_TYPE_SK_LOOKUP**
* *data_in* and *data_out* must be NULL.
*
* **BPF_PROG_TYPE_XDP**
* *ctx_in* and *ctx_out* must be NULL.
*
* **BPF_PROG_TYPE_RAW_TRACEPOINT**,
* **BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE**
*
* *ctx_out*, *data_in* and *data_out* must be NULL.
* *repeat* must be zero.
*
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
@ -4061,12 +4082,20 @@ union bpf_attr {
* of new data availability is sent.
* If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
* of new data availability is sent unconditionally.
* If **0** is specified in *flags*, an adaptive notification
* of new data availability is sent.
*
* An adaptive notification is a notification sent whenever the user-space
* process has caught up and consumed all available payloads. In case the user-space
* process is still processing a previous payload, then no notification is needed
* as it will process the newly added payload automatically.
* Return
* 0 on success, or a negative error in case of failure.
*
* void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags)
* Description
* Reserve *size* bytes of payload in a ring buffer *ringbuf*.
* *flags* must be 0.
* Return
* Valid pointer with *size* bytes of memory available; NULL,
* otherwise.
@ -4078,6 +4107,10 @@ union bpf_attr {
* of new data availability is sent.
* If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
* of new data availability is sent unconditionally.
* If **0** is specified in *flags*, an adaptive notification
* of new data availability is sent.
*
* See 'bpf_ringbuf_output()' for the definition of adaptive notification.
* Return
* Nothing. Always succeeds.
*
@ -4088,6 +4121,10 @@ union bpf_attr {
* of new data availability is sent.
* If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
* of new data availability is sent unconditionally.
* If **0** is specified in *flags*, an adaptive notification
* of new data availability is sent.
*
* See 'bpf_ringbuf_output()' for the definition of adaptive notification.
* Return
* Nothing. Always succeeds.
*
@ -4578,7 +4615,7 @@ union bpf_attr {
*
* long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
* Description
* Check ctx packet size against exceeding MTU of net device (based
* Check packet size against exceeding MTU of net device (based
* on *ifindex*). This helper will likely be used in combination
* with helpers that adjust/change the packet size.
*
@ -4595,6 +4632,14 @@ union bpf_attr {
* against the current net device. This is practical if this isn't
* used prior to redirect.
*
* On input *mtu_len* must be a valid pointer, else verifier will
* reject BPF program. If the value *mtu_len* is initialized to
* zero then the ctx packet size is use. When value *mtu_len* is
* provided as input this specify the L3 length that the MTU check
* is done against. Remember XDP and TC length operate at L2, but
* this value is L3 as this correlate to MTU and IP-header tot_len
* values which are L3 (similar behavior as bpf_fib_lookup).
*
* The Linux kernel route table can configure MTUs on a more
* specific per route level, which is not provided by this helper.
* For route level MTU checks use the **bpf_fib_lookup**\ ()
@ -4619,11 +4664,9 @@ union bpf_attr {
*
* On return *mtu_len* pointer contains the MTU value of the net
* device. Remember the net device configured MTU is the L3 size,
* which is returned here and XDP and TX length operate at L2.
* which is returned here and XDP and TC length operate at L2.
* Helper take this into account for you, but remember when using
* MTU value in your BPF-code. On input *mtu_len* must be a valid
* pointer and be initialized (to zero), else verifier will reject
* BPF program.
* MTU value in your BPF-code.
*
* Return
* * 0 on success, and populate MTU value in *mtu_len* pointer.
@ -4665,6 +4708,33 @@ union bpf_attr {
* Return
* The number of traversed map elements for success, **-EINVAL** for
* invalid **flags**.
*
* long bpf_snprintf(char *str, u32 str_size, const char *fmt, u64 *data, u32 data_len)
* Description
* Outputs a string into the **str** buffer of size **str_size**
* based on a format string stored in a read-only map pointed by
* **fmt**.
*
* Each format specifier in **fmt** corresponds to one u64 element
* in the **data** array. For strings and pointers where pointees
* are accessed, only the pointer values are stored in the *data*
* array. The *data_len* is the size of *data* in bytes.
*
* Formats **%s** and **%p{i,I}{4,6}** require to read kernel
* memory. Reading kernel memory may fail due to either invalid
* address or valid address but requiring a major memory fault. If
* reading kernel memory fails, the string for **%s** will be an
* empty string, and the ip address for **%p{i,I}{4,6}** will be 0.
* Not returning error to bpf program is consistent with what
* **bpf_trace_printk**\ () does for now.
*
* Return
* The strictly positive length of the formatted string, including
* the trailing zero character. If the return value is greater than
* **str_size**, **str** contains a truncated string, guaranteed to
* be zero-terminated except when **str_size** is 0.
*
* Or **-EBUSY** if the per-CPU memory copy buffer is busy.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@ -4832,6 +4902,7 @@ union bpf_attr {
FN(sock_from_file), \
FN(check_mtu), \
FN(for_each_map_elem), \
FN(snprintf), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@ -5373,6 +5444,8 @@ struct bpf_link_info {
} raw_tracepoint;
struct {
__u32 attach_type;
__u32 target_obj_id; /* prog_id for PROG_EXT, otherwise btf object id */
__u32 target_btf_id; /* BTF type id inside the object */
} tracing;
struct {
__u64 cgroup_id;

21
tools/lib/bpf/bpf_helpers.h
View File

@ -25,9 +25,16 @@
/*
* Helper macro to place programs, maps, license in
* different sections in elf_bpf file. Section names
* are interpreted by elf_bpf loader
* are interpreted by libbpf depending on the context (BPF programs, BPF maps,
* extern variables, etc).
* To allow use of SEC() with externs (e.g., for extern .maps declarations),
* make sure __attribute__((unused)) doesn't trigger compilation warning.
*/
#define SEC(NAME) __attribute__((section(NAME), used))
#define SEC(name) \
_Pragma("GCC diagnostic push") \
_Pragma("GCC diagnostic ignored \"-Wignored-attributes\"") \
__attribute__((section(name), used)) \
_Pragma("GCC diagnostic pop") \
/* Avoid 'linux/stddef.h' definition of '__always_inline'. */
#undef __always_inline
@ -40,6 +47,14 @@
#define __weak __attribute__((weak))
#endif
/*
* Use __hidden attribute to mark a non-static BPF subprogram effectively
* static for BPF verifier's verification algorithm purposes, allowing more
* extensive and permissive BPF verification process, taking into account
* subprogram's caller context.
*/
#define __hidden __attribute__((visibility("hidden")))
/* When utilizing vmlinux.h with BPF CO-RE, user BPF programs can't include
* any system-level headers (such as stddef.h, linux/version.h, etc), and
* commonly-used macros like NULL and KERNEL_VERSION aren't available through
@ -51,7 +66,7 @@
#endif
#ifndef KERNEL_VERSION
#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + ((c) > 255 ? 255 : (c))
#define KERNEL_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + ((c) > 255 ? 255 : (c)))
#endif
/*

58
tools/lib/bpf/bpf_tracing.h
View File

@ -413,20 +413,56 @@ typeof(name(0)) name(struct pt_regs *ctx) \
} \
static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
#define ___bpf_fill0(arr, p, x) do {} while (0)
#define ___bpf_fill1(arr, p, x) arr[p] = x
#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args)
#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args)
#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args)
#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args)
#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args)
#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args)
#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args)
#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args)
#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args)
#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args)
#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args)
#define ___bpf_fill(arr, args...) \
___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args)
/*
* BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values
* in a structure.
*/
#define BPF_SEQ_PRINTF(seq, fmt, args...) \
({ \
_Pragma("GCC diagnostic push") \
_Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
static const char ___fmt[] = fmt; \
unsigned long long ___param[] = { args }; \
_Pragma("GCC diagnostic pop") \
int ___ret = bpf_seq_printf(seq, ___fmt, sizeof(___fmt), \
___param, sizeof(___param)); \
___ret; \
})
#define BPF_SEQ_PRINTF(seq, fmt, args...) \
({ \
static const char ___fmt[] = fmt; \
unsigned long long ___param[___bpf_narg(args)]; \
\
_Pragma("GCC diagnostic push") \
_Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
___bpf_fill(___param, args); \
_Pragma("GCC diagnostic pop") \
\
bpf_seq_printf(seq, ___fmt, sizeof(___fmt), \
___param, sizeof(___param)); \
})
/*
* BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of
* an array of u64.
*/
#define BPF_SNPRINTF(out, out_size, fmt, args...) \
({ \
static const char ___fmt[] = fmt; \
unsigned long long ___param[___bpf_narg(args)]; \
\
_Pragma("GCC diagnostic push") \
_Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
___bpf_fill(___param, args); \
_Pragma("GCC diagnostic pop") \
\
bpf_snprintf(out, out_size, ___fmt, \
___param, sizeof(___param)); \
})
#endif

5
tools/lib/bpf/btf.c
View File

@ -1605,11 +1605,6 @@ static void *btf_add_type_mem(struct btf *btf, size_t add_sz)
btf->hdr->type_len, UINT_MAX, add_sz);
}
static __u32 btf_type_info(int kind, int vlen, int kflag)
{
return (kflag << 31) | (kind << 24) | vlen;
}
static void btf_type_inc_vlen(struct btf_type *t)
{
t->info = btf_type_info(btf_kind(t), btf_vlen(t) + 1, btf_kflag(t));

396
tools/lib/bpf/libbpf.c
View File

@ -69,8 +69,7 @@
#define __printf(a, b) __attribute__((format(printf, a, b)))
static struct bpf_map *bpf_object__add_map(struct bpf_object *obj);
static const struct btf_type *
skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog);
static int __base_pr(enum libbpf_print_level level, const char *format,
va_list args)
@ -195,7 +194,6 @@ struct reloc_desc {
int insn_idx;
int map_idx;
int sym_off;
bool processed;
};
struct bpf_sec_def;
@ -275,6 +273,7 @@ struct bpf_program {
bpf_program_clear_priv_t clear_priv;
bool load;
bool mark_btf_static;
enum bpf_prog_type type;
enum bpf_attach_type expected_attach_type;
int prog_ifindex;
@ -501,8 +500,6 @@ static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name);
static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr);
static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn);
static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn);
static int elf_sym_by_sec_off(const struct bpf_object *obj, size_t sec_idx,
size_t off, __u32 sym_type, GElf_Sym *sym);
void bpf_program__unload(struct bpf_program *prog)
{
@ -643,25 +640,29 @@ static int
bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
const char *sec_name, int sec_idx)
{
Elf_Data *symbols = obj->efile.symbols;
struct bpf_program *prog, *progs;
void *data = sec_data->d_buf;
size_t sec_sz = sec_data->d_size, sec_off, prog_sz;
int nr_progs, err;
size_t sec_sz = sec_data->d_size, sec_off, prog_sz, nr_syms;
int nr_progs, err, i;
const char *name;
GElf_Sym sym;
progs = obj->programs;
nr_progs = obj->nr_programs;
nr_syms = symbols->d_size / sizeof(GElf_Sym);
sec_off = 0;
while (sec_off < sec_sz) {
if (elf_sym_by_sec_off(obj, sec_idx, sec_off, STT_FUNC, &sym)) {
pr_warn("sec '%s': failed to find program symbol at offset %zu\n",
sec_name, sec_off);
return -LIBBPF_ERRNO__FORMAT;
}
for (i = 0; i < nr_syms; i++) {
if (!gelf_getsym(symbols, i, &sym))
continue;
if (sym.st_shndx != sec_idx)
continue;
if (GELF_ST_TYPE(sym.st_info) != STT_FUNC)
continue;
prog_sz = sym.st_size;
sec_off = sym.st_value;
name = elf_sym_str(obj, sym.st_name);
if (!name) {
@ -699,10 +700,17 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
if (err)
return err;
/* if function is a global/weak symbol, but has hidden
* visibility (STV_HIDDEN), mark its BTF FUNC as static to
* enable more permissive BPF verification mode with more
* outside context available to BPF verifier
*/
if (GELF_ST_BIND(sym.st_info) != STB_LOCAL
&& GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN)
prog->mark_btf_static = true;
nr_progs++;
obj->nr_programs = nr_progs;
sec_off += prog_sz;
}
return 0;
@ -1896,7 +1904,7 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
return 0;
}
static const struct btf_type *
const struct btf_type *
skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id)
{
const struct btf_type *t = btf__type_by_id(btf, id);
@ -1951,16 +1959,11 @@ static const char *__btf_kind_str(__u16 kind)
}
}
static const char *btf_kind_str(const struct btf_type *t)
const char *btf_kind_str(const struct btf_type *t)
{
return __btf_kind_str(btf_kind(t));
}
static enum btf_func_linkage btf_func_linkage(const struct btf_type *t)
{
return (enum btf_func_linkage)BTF_INFO_VLEN(t->info);
}
/*
* Fetch integer attribute of BTF map definition. Such attributes are
* represented using a pointer to an array, in which dimensionality of array
@ -2015,254 +2018,262 @@ static int build_map_pin_path(struct bpf_map *map, const char *path)
return bpf_map__set_pin_path(map, buf);
}
static int parse_btf_map_def(struct bpf_object *obj,
struct bpf_map *map,
const struct btf_type *def,
bool strict, bool is_inner,
const char *pin_root_path)
int parse_btf_map_def(const char *map_name, struct btf *btf,
const struct btf_type *def_t, bool strict,
struct btf_map_def *map_def, struct btf_map_def *inner_def)
{
const struct btf_type *t;
const struct btf_member *m;
bool is_inner = inner_def == NULL;
int vlen, i;
vlen = btf_vlen(def);
m = btf_members(def);
vlen = btf_vlen(def_t);
m = btf_members(def_t);
for (i = 0; i < vlen; i++, m++) {
const char *name = btf__name_by_offset(obj->btf, m->name_off);
const char *name = btf__name_by_offset(btf, m->name_off);
if (!name) {
pr_warn("map '%s': invalid field #%d.\n", map->name, i);
pr_warn("map '%s': invalid field #%d.\n", map_name, i);
return -EINVAL;
}
if (strcmp(name, "type") == 0) {
if (!get_map_field_int(map->name, obj->btf, m,
&map->def.type))
if (!get_map_field_int(map_name, btf, m, &map_def->map_type))
return -EINVAL;
pr_debug("map '%s': found type = %u.\n",
map->name, map->def.type);
map_def->parts |= MAP_DEF_MAP_TYPE;
} else if (strcmp(name, "max_entries") == 0) {
if (!get_map_field_int(map->name, obj->btf, m,
&map->def.max_entries))
if (!get_map_field_int(map_name, btf, m, &map_def->max_entries))
return -EINVAL;
pr_debug("map '%s': found max_entries = %u.\n",
map->name, map->def.max_entries);
map_def->parts |= MAP_DEF_MAX_ENTRIES;
} else if (strcmp(name, "map_flags") == 0) {
if (!get_map_field_int(map->name, obj->btf, m,
&map->def.map_flags))
if (!get_map_field_int(map_name, btf, m, &map_def->map_flags))
return -EINVAL;
pr_debug("map '%s': found map_flags = %u.\n",
map->name, map->def.map_flags);
map_def->parts |= MAP_DEF_MAP_FLAGS;
} else if (strcmp(name, "numa_node") == 0) {
if (!get_map_field_int(map->name, obj->btf, m, &map->numa_node))
if (!get_map_field_int(map_name, btf, m, &map_def->numa_node))
return -EINVAL;
pr_debug("map '%s': found numa_node = %u.\n", map->name, map->numa_node);
map_def->parts |= MAP_DEF_NUMA_NODE;
} else if (strcmp(name, "key_size") == 0) {
__u32 sz;
if (!get_map_field_int(map->name, obj->btf, m, &sz))
if (!get_map_field_int(map_name, btf, m, &sz))
return -EINVAL;
pr_debug("map '%s': found key_size = %u.\n",
map->name, sz);
if (map->def.key_size && map->def.key_size != sz) {
if (map_def->key_size && map_def->key_size != sz) {
pr_warn("map '%s': conflicting key size %u != %u.\n",
map->name, map->def.key_size, sz);
map_name, map_def->key_size, sz);
return -EINVAL;
}
map->def.key_size = sz;
map_def->key_size = sz;
map_def->parts |= MAP_DEF_KEY_SIZE;
} else if (strcmp(name, "key") == 0) {
__s64 sz;
t = btf__type_by_id(obj->btf, m->type);
t = btf__type_by_id(btf, m->type);
if (!t) {
pr_warn("map '%s': key type [%d] not found.\n",
map->name, m->type);
map_name, m->type);
return -EINVAL;
}
if (!btf_is_ptr(t)) {
pr_warn("map '%s': key spec is not PTR: %s.\n",
map->name, btf_kind_str(t));
map_name, btf_kind_str(t));
return -EINVAL;
}
sz = btf__resolve_size(obj->btf, t->type);
sz = btf__resolve_size(btf, t->type);
if (sz < 0) {
pr_warn("map '%s': can't determine key size for type [%u]: %zd.\n",
map->name, t->type, (ssize_t)sz);
map_name, t->type, (ssize_t)sz);
return sz;
}
pr_debug("map '%s': found key [%u], sz = %zd.\n",
map->name, t->type, (ssize_t)sz);
if (map->def.key_size && map->def.key_size != sz) {
if (map_def->key_size && map_def->key_size != sz) {
pr_warn("map '%s': conflicting key size %u != %zd.\n",
map->name, map->def.key_size, (ssize_t)sz);
map_name, map_def->key_size, (ssize_t)sz);
return -EINVAL;
}
map->def.key_size = sz;
map->btf_key_type_id = t->type;
map_def->key_size = sz;
map_def->key_type_id = t->type;
map_def->parts |= MAP_DEF_KEY_SIZE | MAP_DEF_KEY_TYPE;
} else if (strcmp(name, "value_size") == 0) {
__u32 sz;
if (!get_map_field_int(map->name, obj->btf, m, &sz))
if (!get_map_field_int(map_name, btf, m, &sz))
return -EINVAL;
pr_debug("map '%s': found value_size = %u.\n",
map->name, sz);
if (map->def.value_size && map->def.value_size != sz) {
if (map_def->value_size && map_def->value_size != sz) {
pr_warn("map '%s': conflicting value size %u != %u.\n",
map->name, map->def.value_size, sz);
map_name, map_def->value_size, sz);
return -EINVAL;
}
map->def.value_size = sz;
map_def->value_size = sz;
map_def->parts |= MAP_DEF_VALUE_SIZE;
} else if (strcmp(name, "value") == 0) {
__s64 sz;
t = btf__type_by_id(obj->btf, m->type);
t = btf__type_by_id(btf, m->type);
if (!t) {
pr_warn("map '%s': value type [%d] not found.\n",
map->name, m->type);
map_name, m->type);
return -EINVAL;
}
if (!btf_is_ptr(t)) {
pr_warn("map '%s': value spec is not PTR: %s.\n",
map->name, btf_kind_str(t));
map_name, btf_kind_str(t));
return -EINVAL;
}
sz = btf__resolve_size(obj->btf, t->type);
sz = btf__resolve_size(btf, t->type);
if (sz < 0) {
pr_warn("map '%s': can't determine value size for type [%u]: %zd.\n",
map->name, t->type, (ssize_t)sz);
map_name, t->type, (ssize_t)sz);
return sz;
}
pr_debug("map '%s': found value [%u], sz = %zd.\n",
map->name, t->type, (ssize_t)sz);
if (map->def.value_size && map->def.value_size != sz) {
if (map_def->value_size && map_def->value_size != sz) {
pr_warn("map '%s': conflicting value size %u != %zd.\n",
map->name, map->def.value_size, (ssize_t)sz);
map_name, map_def->value_size, (ssize_t)sz);
return -EINVAL;
}
map->def.value_size = sz;
map->btf_value_type_id = t->type;
map_def->value_size = sz;
map_def->value_type_id = t->type;
map_def->parts |= MAP_DEF_VALUE_SIZE | MAP_DEF_VALUE_TYPE;
}
else if (strcmp(name, "values") == 0) {
char inner_map_name[128];
int err;
if (is_inner) {
pr_warn("map '%s': multi-level inner maps not supported.\n",
map->name);
map_name);
return -ENOTSUP;
}
if (i != vlen - 1) {
pr_warn("map '%s': '%s' member should be last.\n",
map->name, name);
map_name, name);
return -EINVAL;
}
if (!bpf_map_type__is_map_in_map(map->def.type)) {
if (!bpf_map_type__is_map_in_map(map_def->map_type)) {
pr_warn("map '%s': should be map-in-map.\n",
map->name);
map_name);
return -ENOTSUP;
}
if (map->def.value_size && map->def.value_size != 4) {
if (map_def->value_size && map_def->value_size != 4) {
pr_warn("map '%s': conflicting value size %u != 4.\n",
map->name, map->def.value_size);
map_name, map_def->value_size);
return -EINVAL;
}
map->def.value_size = 4;
t = btf__type_by_id(obj->btf, m->type);
map_def->value_size = 4;
t = btf__type_by_id(btf, m->type);
if (!t) {
pr_warn("map '%s': map-in-map inner type [%d] not found.\n",
map->name, m->type);
map_name, m->type);
return -EINVAL;
}
if (!btf_is_array(t) || btf_array(t)->nelems) {
pr_warn("map '%s': map-in-map inner spec is not a zero-sized array.\n",
map->name);
map_name);
return -EINVAL;
}
t = skip_mods_and_typedefs(obj->btf, btf_array(t)->type,
NULL);
t = skip_mods_and_typedefs(btf, btf_array(t)->type, NULL);
if (!btf_is_ptr(t)) {
pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n",
map->name, btf_kind_str(t));
map_name, btf_kind_str(t));
return -EINVAL;
}
t = skip_mods_and_typedefs(obj->btf, t->type, NULL);
t = skip_mods_and_typedefs(btf, t->type, NULL);
if (!btf_is_struct(t)) {
pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n",
map->name, btf_kind_str(t));
map_name, btf_kind_str(t));
return -EINVAL;
}
map->inner_map = calloc(1, sizeof(*map->inner_map));
if (!map->inner_map)
return -ENOMEM;
map->inner_map->sec_idx = obj->efile.btf_maps_shndx;
map->inner_map->name = malloc(strlen(map->name) +
sizeof(".inner") + 1);
if (!map->inner_map->name)
return -ENOMEM;
sprintf(map->inner_map->name, "%s.inner", map->name);
err = parse_btf_map_def(obj, map->inner_map, t, strict,
true /* is_inner */, NULL);
snprintf(inner_map_name, sizeof(inner_map_name), "%s.inner", map_name);
err = parse_btf_map_def(inner_map_name, btf, t, strict, inner_def, NULL);
if (err)
return err;
map_def->parts |= MAP_DEF_INNER_MAP;
} else if (strcmp(name, "pinning") == 0) {
__u32 val;
int err;
if (is_inner) {
pr_debug("map '%s': inner def can't be pinned.\n",
map->name);
pr_warn("map '%s': inner def can't be pinned.\n", map_name);
return -EINVAL;
}
if (!get_map_field_int(map->name, obj->btf, m, &val))
if (!get_map_field_int(map_name, btf, m, &val))
return -EINVAL;
pr_debug("map '%s': found pinning = %u.\n",
map->name, val);
if (val != LIBBPF_PIN_NONE &&
val != LIBBPF_PIN_BY_NAME) {
if (val != LIBBPF_PIN_NONE && val != LIBBPF_PIN_BY_NAME) {
pr_warn("map '%s': invalid pinning value %u.\n",
map->name, val);
map_name, val);
return -EINVAL;
}
if (val == LIBBPF_PIN_BY_NAME) {
err = build_map_pin_path(map, pin_root_path);
if (err) {
pr_warn("map '%s': couldn't build pin path.\n",
map->name);
return err;
}
}
map_def->pinning = val;
map_def->parts |= MAP_DEF_PINNING;
} else {
if (strict) {
pr_warn("map '%s': unknown field '%s'.\n",
map->name, name);
pr_warn("map '%s': unknown field '%s'.\n", map_name, name);
return -ENOTSUP;
}
pr_debug("map '%s': ignoring unknown field '%s'.\n",
map->name, name);
pr_debug("map '%s': ignoring unknown field '%s'.\n", map_name, name);
}
}
if (map->def.type == BPF_MAP_TYPE_UNSPEC) {
pr_warn("map '%s': map type isn't specified.\n", map->name);
if (map_def->map_type == BPF_MAP_TYPE_UNSPEC) {
pr_warn("map '%s': map type isn't specified.\n", map_name);
return -EINVAL;
}
return 0;
}
static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def)
{
map->def.type = def->map_type;
map->def.key_size = def->key_size;
map->def.value_size = def->value_size;
map->def.max_entries = def->max_entries;
map->def.map_flags = def->map_flags;
map->numa_node = def->numa_node;
map->btf_key_type_id = def->key_type_id;
map->btf_value_type_id = def->value_type_id;
if (def->parts & MAP_DEF_MAP_TYPE)
pr_debug("map '%s': found type = %u.\n", map->name, def->map_type);
if (def->parts & MAP_DEF_KEY_TYPE)
pr_debug("map '%s': found key [%u], sz = %u.\n",
map->name, def->key_type_id, def->key_size);
else if (def->parts & MAP_DEF_KEY_SIZE)
pr_debug("map '%s': found key_size = %u.\n", map->name, def->key_size);
if (def->parts & MAP_DEF_VALUE_TYPE)
pr_debug("map '%s': found value [%u], sz = %u.\n",
map->name, def->value_type_id, def->value_size);
else if (def->parts & MAP_DEF_VALUE_SIZE)
pr_debug("map '%s': found value_size = %u.\n", map->name, def->value_size);
if (def->parts & MAP_DEF_MAX_ENTRIES)
pr_debug("map '%s': found max_entries = %u.\n", map->name, def->max_entries);
if (def->parts & MAP_DEF_MAP_FLAGS)
pr_debug("map '%s': found map_flags = %u.\n", map->name, def->map_flags);
if (def->parts & MAP_DEF_PINNING)
pr_debug("map '%s': found pinning = %u.\n", map->name, def->pinning);
if (def->parts & MAP_DEF_NUMA_NODE)
pr_debug("map '%s': found numa_node = %u.\n", map->name, def->numa_node);
if (def->parts & MAP_DEF_INNER_MAP)
pr_debug("map '%s': found inner map definition.\n", map->name);
}
static int bpf_object__init_user_btf_map(struct bpf_object *obj,
const struct btf_type *sec,
int var_idx, int sec_idx,
const Elf_Data *data, bool strict,
const char *pin_root_path)
{
struct btf_map_def map_def = {}, inner_def = {};
const struct btf_type *var, *def;
const struct btf_var_secinfo *vi;
const struct btf_var *var_extra;
const char *map_name;
struct bpf_map *map;
int err;
vi = btf_var_secinfos(sec) + var_idx;
var = btf__type_by_id(obj->btf, vi->type);
@ -2316,7 +2327,35 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
pr_debug("map '%s': at sec_idx %d, offset %zu.\n",
map_name, map->sec_idx, map->sec_offset);
return parse_btf_map_def(obj, map, def, strict, false, pin_root_path);
err = parse_btf_map_def(map->name, obj->btf, def, strict, &map_def, &inner_def);
if (err)
return err;
fill_map_from_def(map, &map_def);
if (map_def.pinning == LIBBPF_PIN_BY_NAME) {
err = build_map_pin_path(map, pin_root_path);
if (err) {
pr_warn("map '%s': couldn't build pin path.\n", map->name);
return err;
}
}
if (map_def.parts & MAP_DEF_INNER_MAP) {
map->inner_map = calloc(1, sizeof(*map->inner_map));
if (!map->inner_map)
return -ENOMEM;
map->inner_map->fd = -1;
map->inner_map->sec_idx = sec_idx;
map->inner_map->name = malloc(strlen(map_name) + sizeof(".inner") + 1);
if (!map->inner_map->name)
return -ENOMEM;
sprintf(map->inner_map->name, "%s.inner", map_name);
fill_map_from_def(map->inner_map, &inner_def);
}
return 0;
}
static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
@ -2618,7 +2657,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
{
struct btf *kern_btf = obj->btf;
bool btf_mandatory, sanitize;
int err = 0;
int i, err = 0;
if (!obj->btf)
return 0;
@ -2632,6 +2671,38 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
return 0;
}
/* Even though some subprogs are global/weak, user might prefer more
* permissive BPF verification process that BPF verifier performs for
* static functions, taking into account more context from the caller
* functions. In such case, they need to mark such subprogs with
* __attribute__((visibility("hidden"))) and libbpf will adjust
* corresponding FUNC BTF type to be marked as static and trigger more
* involved BPF verification process.
*/
for (i = 0; i < obj->nr_programs; i++) {
struct bpf_program *prog = &obj->programs[i];
struct btf_type *t;
const char *name;
int j, n;
if (!prog->mark_btf_static || !prog_is_subprog(obj, prog))
continue;
n = btf__get_nr_types(obj->btf);
for (j = 1; j <= n; j++) {
t = btf_type_by_id(obj->btf, j);
if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL)
continue;
name = btf__str_by_offset(obj->btf, t->name_off);
if (strcmp(name, prog->name) != 0)
continue;
t->info = btf_type_info(BTF_KIND_FUNC, BTF_FUNC_STATIC, 0);
break;
}
}
sanitize = btf_needs_sanitization(obj);
if (sanitize) {
const void *raw_data;
@ -2782,26 +2853,6 @@ static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn)
return data;
}
static int elf_sym_by_sec_off(const struct bpf_object *obj, size_t sec_idx,
size_t off, __u32 sym_type, GElf_Sym *sym)
{
Elf_Data *symbols = obj->efile.symbols;
size_t n = symbols->d_size / sizeof(GElf_Sym);
int i;
for (i = 0; i < n; i++) {
if (!gelf_getsym(symbols, i, sym))
continue;
if (sym->st_shndx != sec_idx || sym->st_value != off)
continue;
if (GELF_ST_TYPE(sym->st_info) != sym_type)
continue;
return 0;
}
return -ENOENT;
}
static bool is_sec_name_dwarf(const char *name)
{
/* approximation, but the actual list is too long */
@ -3498,8 +3549,6 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
const char *sym_sec_name;
struct bpf_map *map;
reloc_desc->processed = false;
if (!is_call_insn(insn) && !is_ldimm64_insn(insn)) {
pr_warn("prog '%s': invalid relo against '%s' for insns[%d].code 0x%x\n",
prog->name, sym_name, insn_idx, insn->code);
@ -3682,11 +3731,16 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
int err, i, nrels;
const char *sym_name;
__u32 insn_idx;
Elf_Scn *scn;
Elf_Data *scn_data;
GElf_Sym sym;
GElf_Rel rel;
scn = elf_sec_by_idx(obj, sec_idx);
scn_data = elf_sec_data(obj, scn);
relo_sec_name = elf_sec_str(obj, shdr->sh_name);
sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
sec_name = elf_sec_name(obj, scn);
if (!relo_sec_name || !sec_name)
return -EINVAL;
@ -3704,7 +3758,8 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i);
return -LIBBPF_ERRNO__FORMAT;
}
if (rel.r_offset % BPF_INSN_SZ) {
if (rel.r_offset % BPF_INSN_SZ || rel.r_offset >= scn_data->d_size) {
pr_warn("sec '%s': invalid offset 0x%zx for relo #%d\n",
relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i);
return -LIBBPF_ERRNO__FORMAT;
@ -3728,9 +3783,9 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx);
if (!prog) {
pr_warn("sec '%s': relo #%d: program not found in section '%s' for insn #%u\n",
pr_debug("sec '%s': relo #%d: couldn't find program in section '%s' for insn #%u, probably overridden weak function, skipping...\n",
relo_sec_name, i, sec_name, insn_idx);
return -LIBBPF_ERRNO__RELOC;
continue;
}
relos = libbpf_reallocarray(prog->reloc_desc,
@ -3845,6 +3900,14 @@ __u32 bpf_map__max_entries(const struct bpf_map *map)
return map->def.max_entries;
}
struct bpf_map *bpf_map__inner_map(struct bpf_map *map)
{
if (!bpf_map_type__is_map_in_map(map->def.type))
return NULL;
return map->inner_map;
}
int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
{
if (map->fd >= 0)
@ -6305,13 +6368,11 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
case RELO_LD64:
insn[0].src_reg = BPF_PSEUDO_MAP_FD;
insn[0].imm = obj->maps[relo->map_idx].fd;
relo->processed = true;
break;
case RELO_DATA:
insn[0].src_reg = BPF_PSEUDO_MAP_VALUE;
insn[1].imm = insn[0].imm + relo->sym_off;
insn[0].imm = obj->maps[relo->map_idx].fd;
relo->processed = true;
break;
case RELO_EXTERN_VAR:
ext = &obj->externs[relo->sym_off];
@ -6329,13 +6390,11 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
insn[1].imm = ext->ksym.addr >> 32;
}
}
relo->processed = true;
break;
case RELO_EXTERN_FUNC:
ext = &obj->externs[relo->sym_off];
insn[0].src_reg = BPF_PSEUDO_KFUNC_CALL;
insn[0].imm = ext->ksym.kernel_btf_id;
relo->processed = true;
break;
case RELO_SUBPROG_ADDR:
insn[0].src_reg = BPF_PSEUDO_FUNC;
@ -6621,9 +6680,6 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
* different main programs */
insn->imm = subprog->sub_insn_off - (prog->sub_insn_off + insn_idx) - 1;
if (relo)
relo->processed = true;
pr_debug("prog '%s': insn #%zu relocated, imm %d points to subprog '%s' (now at %zu offset)\n",
prog->name, insn_idx, insn->imm, subprog->name, subprog->sub_insn_off);
}
@ -6716,7 +6772,7 @@ static int
bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog)
{
struct bpf_program *subprog;
int i, j, err;
int i, err;
/* mark all subprogs as not relocated (yet) within the context of
* current main program
@ -6727,9 +6783,6 @@ bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog)
continue;
subprog->sub_insn_off = 0;
for (j = 0; j < subprog->nr_reloc; j++)
if (subprog->reloc_desc[j].type == RELO_CALL)
subprog->reloc_desc[j].processed = false;
}
err = bpf_object__reloc_code(obj, prog, prog);
@ -6976,7 +7029,7 @@ static bool insn_is_helper_call(struct bpf_insn *insn, enum bpf_func_id *func_id
return false;
}
static int bpf_object__sanitize_prog(struct bpf_object* obj, struct bpf_program *prog)
static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program *prog)
{
struct bpf_insn *insn = prog->insns;
enum bpf_func_id func_id;
@ -9476,6 +9529,7 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd)
pr_warn("error: inner_map_fd already specified\n");
return -EINVAL;
}
zfree(&map->inner_map);
map->inner_map_fd = fd;
return 0;
}

1
tools/lib/bpf/libbpf.h
View File

@ -480,6 +480,7 @@ LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd);
LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map);
LIBBPF_API long libbpf_get_error(const void *ptr);

1
tools/lib/bpf/libbpf.map
View File

@ -359,5 +359,6 @@ LIBBPF_0.4.0 {
bpf_linker__finalize;
bpf_linker__free;
bpf_linker__new;
bpf_map__inner_map;
bpf_object__set_kversion;
} LIBBPF_0.3.0;

45
tools/lib/bpf/libbpf_internal.h
View File

@ -19,6 +19,7 @@
#pragma GCC poison reallocarray
#include "libbpf.h"
#include "btf.h"
#ifndef EM_BPF
#define EM_BPF 247
@ -131,6 +132,50 @@ struct btf;
struct btf_type;
struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id);
const char *btf_kind_str(const struct btf_type *t);
const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id);
static inline enum btf_func_linkage btf_func_linkage(const struct btf_type *t)
{
return (enum btf_func_linkage)(int)btf_vlen(t);
}
static inline __u32 btf_type_info(int kind, int vlen, int kflag)
{
return (kflag << 31) | (kind << 24) | vlen;
}
enum map_def_parts {
MAP_DEF_MAP_TYPE = 0x001,
MAP_DEF_KEY_TYPE = 0x002,
MAP_DEF_KEY_SIZE = 0x004,
MAP_DEF_VALUE_TYPE = 0x008,
MAP_DEF_VALUE_SIZE = 0x010,
MAP_DEF_MAX_ENTRIES = 0x020,
MAP_DEF_MAP_FLAGS = 0x040,
MAP_DEF_NUMA_NODE = 0x080,
MAP_DEF_PINNING = 0x100,
MAP_DEF_INNER_MAP = 0x200,
MAP_DEF_ALL = 0x3ff, /* combination of all above */
};
struct btf_map_def {
enum map_def_parts parts;
__u32 map_type;
__u32 key_type_id;
__u32 key_size;
__u32 value_type_id;
__u32 value_size;
__u32 max_entries;
__u32 map_flags;
__u32 numa_node;
__u32 pinning;
};
int parse_btf_map_def(const char *map_name, struct btf *btf,
const struct btf_type *def_t, bool strict,
struct btf_map_def *map_def, struct btf_map_def *inner_def);
void *libbpf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
size_t cur_cnt, size_t max_cnt, size_t add_cnt);

1292
tools/lib/bpf/linker.c
View File

File diff suppressed because it is too large Load Diff

12
tools/scripts/Makefile.include
View File

@ -39,8 +39,6 @@ EXTRA_WARNINGS += -Wundef
EXTRA_WARNINGS += -Wwrite-strings
EXTRA_WARNINGS += -Wformat
CC_NO_CLANG := $(shell $(CC) -dM -E -x c /dev/null | grep -Fq "__clang__"; echo $$?)
# Makefiles suck: This macro sets a default value of $(2) for the
# variable named by $(1), unless the variable has been set by
# environment or command line. This is necessary for CC and AR
@ -52,12 +50,22 @@ define allow-override
$(eval $(1) = $(2)))
endef
ifneq ($(LLVM),)
$(call allow-override,CC,clang)
$(call allow-override,AR,llvm-ar)
$(call allow-override,LD,ld.lld)
$(call allow-override,CXX,clang++)
$(call allow-override,STRIP,llvm-strip)
else
# Allow setting various cross-compile vars or setting CROSS_COMPILE as a prefix.
$(call allow-override,CC,$(CROSS_COMPILE)gcc)
$(call allow-override,AR,$(CROSS_COMPILE)ar)
$(call allow-override,LD,$(CROSS_COMPILE)ld)
$(call allow-override,CXX,$(CROSS_COMPILE)g++)
$(call allow-override,STRIP,$(CROSS_COMPILE)strip)
endif
CC_NO_CLANG := $(shell $(CC) -dM -E -x c /dev/null | grep -Fq "__clang__"; echo $$?)
ifneq ($(LLVM),)
HOSTAR ?= llvm-ar

28
tools/testing/selftests/bpf/Makefile
View File

@ -21,13 +21,18 @@ endif
BPF_GCC ?= $(shell command -v bpf-gcc;)
SAN_CFLAGS ?=
CFLAGS += -g -Og -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS) \
CFLAGS += -g -O0 -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS) \
-I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \
-I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) \
-Dbpf_prog_load=bpf_prog_test_load \
-Dbpf_load_program=bpf_test_load_program
LDLIBS += -lcap -lelf -lz -lrt -lpthread
# Silence some warnings when compiled with clang
ifneq ($(LLVM),)
CFLAGS += -Wno-unused-command-line-argument
endif
# 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_verifier_log test_dev_cgroup \
@ -182,7 +187,6 @@ $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL)
cp $(SCRATCH_DIR)/runqslower $@
$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ)
$(TEST_GEN_FILES): docs
$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
$(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c
@ -201,10 +205,12 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \
$(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
$(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \
CC=$(HOSTCC) LD=$(HOSTLD) \
EXTRA_CFLAGS='-g -Og' \
EXTRA_CFLAGS='-g -O0' \
OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \
prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install
all: docs
docs:
$(Q)RST2MAN_OPTS="--exit-status=1" $(MAKE) $(submake_extras) \
-f Makefile.docs \
@ -219,7 +225,7 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \
../../../include/uapi/linux/bpf.h \
| $(INCLUDE_DIR) $(BUILD_DIR)/libbpf
$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
EXTRA_CFLAGS='-g -Og' \
EXTRA_CFLAGS='-g -O0' \
DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
ifneq ($(BPFOBJ),$(HOST_BPFOBJ))
@ -227,7 +233,7 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \
../../../include/uapi/linux/bpf.h \
| $(INCLUDE_DIR) $(HOST_BUILD_DIR)/libbpf
$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) \
EXTRA_CFLAGS='-g -Og' \
EXTRA_CFLAGS='-g -O0' \
OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \
DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
endif
@ -303,9 +309,15 @@ endef
SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
LINKED_SKELS := test_static_linked.skel.h
LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \
linked_vars.skel.h linked_maps.skel.h
test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
linked_funcs.skel.h-deps := linked_funcs1.o linked_funcs2.o
linked_vars.skel.h-deps := linked_vars1.o linked_vars2.o
linked_maps.skel.h-deps := linked_maps1.o linked_maps2.o
LINKED_BPF_SRCS := $(patsubst %.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
# Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on
# $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
@ -325,7 +337,7 @@ TRUNNER_TESTS_HDR := $(TRUNNER_TESTS_DIR)/tests.h
TRUNNER_BPF_SRCS := $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c))
TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS))
TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \
$$(filter-out $(SKEL_BLACKLIST), \
$$(filter-out $(SKEL_BLACKLIST) $(LINKED_BPF_SRCS),\
$$(TRUNNER_BPF_SRCS)))
TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS))
TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS)
@ -481,7 +493,7 @@ $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT)
# Make sure we are able to include and link libbpf against c++.
$(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
$(call msg,CXX,,$@)
$(Q)$(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@
$(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
# Benchmark runner
$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h

9
tools/testing/selftests/bpf/README.rst
View File

@ -193,3 +193,12 @@ Without it, the error from compiling bpf selftests looks like:
libbpf: failed to find BTF for extern 'tcp_slow_start' [25] section: -2
__ https://reviews.llvm.org/D93563
Clang dependencies for static linking tests
===========================================
linked_vars, linked_maps, and linked_funcs tests depend on `Clang fix`__ to
generate valid BTF information for weak variables. Please make sure you use
Clang that contains the fix.
__ https://reviews.llvm.org/D100362

2
tools/testing/selftests/bpf/config
View File

@ -44,3 +44,5 @@ CONFIG_SECURITYFS=y
CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_READ_POLICY=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_FUNCTION_TRACER=y
CONFIG_DYNAMIC_FTRACE=y

1
tools/testing/selftests/bpf/prog_tests/bpf_iter.c
View File

@ -147,6 +147,7 @@ static void test_task_stack(void)
return;
do_dummy_read(skel->progs.dump_task_stack);
do_dummy_read(skel->progs.get_task_user_stacks);
bpf_iter_task_stack__destroy(skel);
}

58
tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
View File

@ -58,42 +58,73 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
test_cb cb)
{
struct bpf_object *obj = NULL, *tgt_obj;
__u32 retval, tgt_prog_id, info_len;
struct bpf_prog_info prog_info = {};
struct bpf_program **prog = NULL;
struct bpf_link **link = NULL;
__u32 duration = 0, retval;
int err, tgt_fd, i;
struct btf *btf;
err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC,
&tgt_obj, &tgt_fd);
if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n",
target_obj_file, err, errno))
if (!ASSERT_OK(err, "tgt_prog_load"))
return;
DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
.attach_prog_fd = tgt_fd,
);
info_len = sizeof(prog_info);
err = bpf_obj_get_info_by_fd(tgt_fd, &prog_info, &info_len);
if (!ASSERT_OK(err, "tgt_fd_get_info"))
goto close_prog;
tgt_prog_id = prog_info.id;
btf = bpf_object__btf(tgt_obj);
link = calloc(sizeof(struct bpf_link *), prog_cnt);
if (!ASSERT_OK_PTR(link, "link_ptr"))
goto close_prog;
prog = calloc(sizeof(struct bpf_program *), prog_cnt);
if (CHECK(!link || !prog, "alloc_memory", "failed to alloc memory"))
if (!ASSERT_OK_PTR(prog, "prog_ptr"))
goto close_prog;
obj = bpf_object__open_file(obj_file, &opts);
if (CHECK(IS_ERR_OR_NULL(obj), "obj_open",
"failed to open %s: %ld\n", obj_file,
PTR_ERR(obj)))
if (!ASSERT_OK_PTR(obj, "obj_open"))
goto close_prog;
err = bpf_object__load(obj);
if (CHECK(err, "obj_load", "err %d\n", err))
if (!ASSERT_OK(err, "obj_load"))
goto close_prog;
for (i = 0; i < prog_cnt; i++) {
struct bpf_link_info link_info;
char *tgt_name;
__s32 btf_id;
tgt_name = strstr(prog_name[i], "/");
if (!ASSERT_OK_PTR(tgt_name, "tgt_name"))
goto close_prog;
btf_id = btf__find_by_name_kind(btf, tgt_name + 1, BTF_KIND_FUNC);
prog[i] = bpf_object__find_program_by_title(obj, prog_name[i]);
if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name[i]))
if (!ASSERT_OK_PTR(prog[i], prog_name[i]))
goto close_prog;
link[i] = bpf_program__attach_trace(prog[i]);
if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
if (!ASSERT_OK_PTR(link[i], "attach_trace"))
goto close_prog;
info_len = sizeof(link_info);
memset(&link_info, 0, sizeof(link_info));
err = bpf_obj_get_info_by_fd(bpf_link__fd(link[i]),
&link_info, &info_len);
ASSERT_OK(err, "link_fd_get_info");
ASSERT_EQ(link_info.tracing.attach_type,
bpf_program__get_expected_attach_type(prog[i]),
"link_attach_type");
ASSERT_EQ(link_info.tracing.target_obj_id, tgt_prog_id, "link_tgt_obj_id");
ASSERT_EQ(link_info.tracing.target_btf_id, btf_id, "link_tgt_btf_id");
}
if (cb) {
@ -106,10 +137,9 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
goto close_prog;
err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6),
NULL, NULL, &retval, &duration);
CHECK(err || retval, "ipv6",
"err %d errno %d retval %d duration %d\n",
err, errno, retval, duration);
NULL, NULL, &retval, NULL);
ASSERT_OK(err, "prog_run");
ASSERT_EQ(retval, 0, "prog_run_ret");
if (check_data_map(obj, prog_cnt, false))
goto close_prog;

4
tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
View File

@ -39,7 +39,7 @@ void test_fexit_sleep(void)
goto cleanup;
cpid = clone(do_sleep, child_stack + STACK_SIZE, CLONE_FILES | SIGCHLD, fexit_skel);
if (CHECK(cpid == -1, "clone", strerror(errno)))
if (CHECK(cpid == -1, "clone", "%s\n", strerror(errno)))
goto cleanup;
/* wait until first sys_nanosleep ends and second sys_nanosleep starts */
@ -65,7 +65,7 @@ void test_fexit_sleep(void)
/* kill the thread to unwind sys_nanosleep stack through the trampoline */
kill(cpid, 9);
if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", strerror(errno)))
if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", "%s\n", strerror(errno)))
goto cleanup;
if (CHECK(WEXITSTATUS(wstatus) != 0, "exitstatus", "failed"))
goto cleanup;

42
tools/testing/selftests/bpf/prog_tests/linked_funcs.c Normal file
View File

@ -0,0 +1,42 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Facebook */
#include <test_progs.h>
#include <sys/syscall.h>
#include "linked_funcs.skel.h"
void test_linked_funcs(void)
{
int err;
struct linked_funcs *skel;
skel = linked_funcs__open();
if (!ASSERT_OK_PTR(skel, "skel_open"))
return;
skel->rodata->my_tid = syscall(SYS_gettid);
skel->bss->syscall_id = SYS_getpgid;
err = linked_funcs__load(skel);
if (!ASSERT_OK(err, "skel_load"))
goto cleanup;
err = linked_funcs__attach(skel);
if (!ASSERT_OK(err, "skel_attach"))
goto cleanup;
/* trigger */
syscall(SYS_getpgid);
ASSERT_EQ(skel->bss->output_val1, 2000 + 2000, "output_val1");
ASSERT_EQ(skel->bss->output_ctx1, SYS_getpgid, "output_ctx1");
ASSERT_EQ(skel->bss->output_weak1, 42, "output_weak1");
ASSERT_EQ(skel->bss->output_val2, 2 * 1000 + 2 * (2 * 1000), "output_val2");
ASSERT_EQ(skel->bss->output_ctx2, SYS_getpgid, "output_ctx2");
/* output_weak2 should never be updated */
ASSERT_EQ(skel->bss->output_weak2, 0, "output_weak2");
cleanup:
linked_funcs__destroy(skel);
}

30
tools/testing/selftests/bpf/prog_tests/linked_maps.c Normal file
View File

@ -0,0 +1,30 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Facebook */
#include <test_progs.h>
#include <sys/syscall.h>
#include "linked_maps.skel.h"
void test_linked_maps(void)
{
int err;
struct linked_maps *skel;
skel = linked_maps__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_open"))
return;
err = linked_maps__attach(skel);
if (!ASSERT_OK(err, "skel_attach"))
goto cleanup;
/* trigger */
syscall(SYS_getpgid);
ASSERT_EQ(skel->bss->output_first1, 2000, "output_first1");
ASSERT_EQ(skel->bss->output_second1, 2, "output_second1");
ASSERT_EQ(skel->bss->output_weak1, 2, "output_weak1");
cleanup:
linked_maps__destroy(skel);
}

43
tools/testing/selftests/bpf/prog_tests/linked_vars.c Normal file
View File

@ -0,0 +1,43 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Facebook */
#include <test_progs.h>
#include <sys/syscall.h>
#include "linked_vars.skel.h"
void test_linked_vars(void)
{
int err;
struct linked_vars *skel;
skel = linked_vars__open();
if (!ASSERT_OK_PTR(skel, "skel_open"))
return;
skel->bss->input_bss1 = 1000;
skel->bss->input_bss2 = 2000;
skel->bss->input_bss_weak = 3000;
err = linked_vars__load(skel);
if (!ASSERT_OK(err, "skel_load"))
goto cleanup;
err = linked_vars__attach(skel);
if (!ASSERT_OK(err, "skel_attach"))
goto cleanup;
/* trigger */
syscall(SYS_getpgid);
ASSERT_EQ(skel->bss->output_bss1, 1000 + 2000 + 3000, "output_bss1");
ASSERT_EQ(skel->bss->output_bss2, 1000 + 2000 + 3000, "output_bss2");
/* 10 comes from "winner" input_data_weak in first obj file */
ASSERT_EQ(skel->bss->output_data1, 1 + 2 + 10, "output_bss1");
ASSERT_EQ(skel->bss->output_data2, 1 + 2 + 10, "output_bss2");
/* 100 comes from "winner" input_rodata_weak in first obj file */
ASSERT_EQ(skel->bss->output_rodata1, 11 + 22 + 100, "output_weak1");
ASSERT_EQ(skel->bss->output_rodata2, 11 + 22 + 100, "output_weak2");
cleanup:
linked_vars__destroy(skel);
}

15
tools/testing/selftests/bpf/prog_tests/map_ptr.c
View File

@ -12,11 +12,22 @@ void test_map_ptr(void)
__u32 duration = 0, retval;
char buf[128];
int err;
int page_size = getpagesize();
skel = map_ptr_kern__open_and_load();
if (CHECK(!skel, "skel_open_load", "open_load failed\n"))
skel = map_ptr_kern__open();
if (!ASSERT_OK_PTR(skel, "skel_open"))
return;
err = bpf_map__set_max_entries(skel->maps.m_ringbuf, page_size);
if (!ASSERT_OK(err, "bpf_map__set_max_entries"))
goto cleanup;
err = map_ptr_kern__load(skel);
if (!ASSERT_OK(err, "skel_load"))
goto cleanup;
skel->bss->page_size = page_size;
err = bpf_prog_test_run(bpf_program__fd(skel->progs.cg_skb), 1, &pkt_v4,
sizeof(pkt_v4), buf, NULL, &retval, NULL);

24
tools/testing/selftests/bpf/prog_tests/mmap.c
View File

@ -29,22 +29,36 @@ void test_mmap(void)
struct test_mmap *skel;
__u64 val = 0;
skel = test_mmap__open_and_load();
if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n"))
skel = test_mmap__open();
if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
return;
err = bpf_map__set_max_entries(skel->maps.rdonly_map, page_size);
if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
goto cleanup;
/* at least 4 pages of data */
err = bpf_map__set_max_entries(skel->maps.data_map,
4 * (page_size / sizeof(u64)));
if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
goto cleanup;
err = test_mmap__load(skel);
if (CHECK(err != 0, "skel_load", "skeleton load failed\n"))
goto cleanup;
bss_map = skel->maps.bss;
data_map = skel->maps.data_map;
data_map_fd = bpf_map__fd(data_map);
rdmap_fd = bpf_map__fd(skel->maps.rdonly_map);
tmp1 = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_SHARED, rdmap_fd, 0);
tmp1 = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rdmap_fd, 0);
if (CHECK(tmp1 != MAP_FAILED, "rdonly_write_mmap", "unexpected success\n")) {
munmap(tmp1, 4096);
munmap(tmp1, page_size);
goto cleanup;
}
/* now double-check if it's mmap()'able at all */
tmp1 = mmap(NULL, 4096, PROT_READ, MAP_SHARED, rdmap_fd, 0);
tmp1 = mmap(NULL, page_size, PROT_READ, MAP_SHARED, rdmap_fd, 0);
if (CHECK(tmp1 == MAP_FAILED, "rdonly_read_mmap", "failed: %d\n", errno))
goto cleanup;

4
tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
View File

@ -68,10 +68,10 @@ static void test_ns_current_pid_tgid_new_ns(void)
cpid = clone(test_current_pid_tgid, child_stack + STACK_SIZE,
CLONE_NEWPID | SIGCHLD, NULL);
if (CHECK(cpid == -1, "clone", strerror(errno)))
if (CHECK(cpid == -1, "clone", "%s\n", strerror(errno)))
return;
if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", strerror(errno)))
if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", "%s\n", strerror(errno)))
return;
if (CHECK(WEXITSTATUS(wstatus) != 0, "newns_pidtgid", "failed"))

17
tools/testing/selftests/bpf/prog_tests/ringbuf.c
View File

@ -87,11 +87,20 @@ void test_ringbuf(void)
pthread_t thread;
long bg_ret = -1;
int err, cnt;
int page_size = getpagesize();
skel = test_ringbuf__open_and_load();
if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n"))
skel = test_ringbuf__open();
if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
return;
err = bpf_map__set_max_entries(skel->maps.ringbuf, page_size);
if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
goto cleanup;
err = test_ringbuf__load(skel);
if (CHECK(err != 0, "skel_load", "skeleton load failed\n"))
goto cleanup;
/* only trigger BPF program for current process */
skel->bss->pid = getpid();
@ -110,9 +119,9 @@ void test_ringbuf(void)
CHECK(skel->bss->avail_data != 3 * rec_sz,
"err_avail_size", "exp %ld, got %ld\n",
3L * rec_sz, skel->bss->avail_data);
CHECK(skel->bss->ring_size != 4096,
CHECK(skel->bss->ring_size != page_size,
"err_ring_size", "exp %ld, got %ld\n",
4096L, skel->bss->ring_size);
(long)page_size, skel->bss->ring_size);
CHECK(skel->bss->cons_pos != 0,
"err_cons_pos", "exp %ld, got %ld\n",
0L, skel->bss->cons_pos);

37
tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
View File

@ -41,13 +41,42 @@ static int process_sample(void *ctx, void *data, size_t len)
void test_ringbuf_multi(void)
{
struct test_ringbuf_multi *skel;
struct ring_buffer *ringbuf;
struct ring_buffer *ringbuf = NULL;
int err;
int page_size = getpagesize();
int proto_fd = -1;
skel = test_ringbuf_multi__open_and_load();
if (CHECK(!skel, "skel_open_load", "skeleton open&load failed\n"))
skel = test_ringbuf_multi__open();
if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
return;
err = bpf_map__set_max_entries(skel->maps.ringbuf1, page_size);
if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
goto cleanup;
err = bpf_map__set_max_entries(skel->maps.ringbuf2, page_size);
if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
goto cleanup;
err = bpf_map__set_max_entries(bpf_map__inner_map(skel->maps.ringbuf_arr), page_size);
if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n"))
goto cleanup;
proto_fd = bpf_create_map(BPF_MAP_TYPE_RINGBUF, 0, 0, page_size, 0);
if (CHECK(proto_fd == -1, "bpf_create_map", "bpf_create_map failed\n"))
goto cleanup;
err = bpf_map__set_inner_map_fd(skel->maps.ringbuf_hash, proto_fd);
if (CHECK(err != 0, "bpf_map__set_inner_map_fd", "bpf_map__set_inner_map_fd failed\n"))
goto cleanup;
err = test_ringbuf_multi__load(skel);
if (CHECK(err != 0, "skel_load", "skeleton load failed\n"))
goto cleanup;
close(proto_fd);
proto_fd = -1;
/* only trigger BPF program for current process */
skel->bss->pid = getpid();
@ -97,6 +126,8 @@ void test_ringbuf_multi(void)
2L, skel->bss->total);
cleanup:
if (proto_fd >= 0)
close(proto_fd);
ring_buffer__free(ringbuf);
test_ringbuf_multi__destroy(skel);
}

125
tools/testing/selftests/bpf/prog_tests/snprintf.c Normal file
View File

@ -0,0 +1,125 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Google LLC. */
#include <test_progs.h>
#include "test_snprintf.skel.h"
#include "test_snprintf_single.skel.h"
#define EXP_NUM_OUT "-8 9 96 -424242 1337 DABBAD00"
#define EXP_NUM_RET sizeof(EXP_NUM_OUT)
#define EXP_IP_OUT "127.000.000.001 0000:0000:0000:0000:0000:0000:0000:0001"
#define EXP_IP_RET sizeof(EXP_IP_OUT)
/* The third specifier, %pB, depends on compiler inlining so don't check it */
#define EXP_SYM_OUT "schedule schedule+0x0/"
#define MIN_SYM_RET sizeof(EXP_SYM_OUT)
/* The third specifier, %p, is a hashed pointer which changes on every reboot */
#define EXP_ADDR_OUT "0000000000000000 ffff00000add4e55 "
#define EXP_ADDR_RET sizeof(EXP_ADDR_OUT "unknownhashedptr")
#define EXP_STR_OUT "str1 longstr"
#define EXP_STR_RET sizeof(EXP_STR_OUT)
#define EXP_OVER_OUT "%over"
#define EXP_OVER_RET 10
#define EXP_PAD_OUT " 4 000"
#define EXP_PAD_RET 900007
#define EXP_NO_ARG_OUT "simple case"
#define EXP_NO_ARG_RET 12
#define EXP_NO_BUF_RET 29
void test_snprintf_positive(void)
{
char exp_addr_out[] = EXP_ADDR_OUT;
char exp_sym_out[] = EXP_SYM_OUT;
struct test_snprintf *skel;
skel = test_snprintf__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_open"))
return;
if (!ASSERT_OK(test_snprintf__attach(skel), "skel_attach"))
goto cleanup;
/* trigger tracepoint */
usleep(1);
ASSERT_STREQ(skel->bss->num_out, EXP_NUM_OUT, "num_out");
ASSERT_EQ(skel->bss->num_ret, EXP_NUM_RET, "num_ret");
ASSERT_STREQ(skel->bss->ip_out, EXP_IP_OUT, "ip_out");
ASSERT_EQ(skel->bss->ip_ret, EXP_IP_RET, "ip_ret");
ASSERT_OK(memcmp(skel->bss->sym_out, exp_sym_out,
sizeof(exp_sym_out) - 1), "sym_out");
ASSERT_LT(MIN_SYM_RET, skel->bss->sym_ret, "sym_ret");
ASSERT_OK(memcmp(skel->bss->addr_out, exp_addr_out,
sizeof(exp_addr_out) - 1), "addr_out");
ASSERT_EQ(skel->bss->addr_ret, EXP_ADDR_RET, "addr_ret");
ASSERT_STREQ(skel->bss->str_out, EXP_STR_OUT, "str_out");
ASSERT_EQ(skel->bss->str_ret, EXP_STR_RET, "str_ret");
ASSERT_STREQ(skel->bss->over_out, EXP_OVER_OUT, "over_out");
ASSERT_EQ(skel->bss->over_ret, EXP_OVER_RET, "over_ret");
ASSERT_STREQ(skel->bss->pad_out, EXP_PAD_OUT, "pad_out");
ASSERT_EQ(skel->bss->pad_ret, EXP_PAD_RET, "pad_ret");
ASSERT_STREQ(skel->bss->noarg_out, EXP_NO_ARG_OUT, "no_arg_out");
ASSERT_EQ(skel->bss->noarg_ret, EXP_NO_ARG_RET, "no_arg_ret");
ASSERT_EQ(skel->bss->nobuf_ret, EXP_NO_BUF_RET, "no_buf_ret");
cleanup:
test_snprintf__destroy(skel);
}
#define min(a, b) ((a) < (b) ? (a) : (b))
/* Loads an eBPF object calling bpf_snprintf with up to 10 characters of fmt */
static int load_single_snprintf(char *fmt)
{
struct test_snprintf_single *skel;
int ret;
skel = test_snprintf_single__open();
if (!skel)
return -EINVAL;
memcpy(skel->rodata->fmt, fmt, min(strlen(fmt) + 1, 10));
ret = test_snprintf_single__load(skel);
test_snprintf_single__destroy(skel);
return ret;
}
void test_snprintf_negative(void)
{
ASSERT_OK(load_single_snprintf("valid %d"), "valid usage");
ASSERT_ERR(load_single_snprintf("0123456789"), "no terminating zero");
ASSERT_ERR(load_single_snprintf("%d %d"), "too many specifiers");
ASSERT_ERR(load_single_snprintf("%pi5"), "invalid specifier 1");
ASSERT_ERR(load_single_snprintf("%a"), "invalid specifier 2");
ASSERT_ERR(load_single_snprintf("%"), "invalid specifier 3");
ASSERT_ERR(load_single_snprintf("%12345678"), "invalid specifier 4");
ASSERT_ERR(load_single_snprintf("%--------"), "invalid specifier 5");
ASSERT_ERR(load_single_snprintf("\x80"), "non ascii character");
ASSERT_ERR(load_single_snprintf("\x1"), "non printable character");
}
void test_snprintf(void)
{
if (test__start_subtest("snprintf_positive"))
test_snprintf_positive();
if (test__start_subtest("snprintf_negative"))
test_snprintf_negative();
}

65
tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
View File

@ -3,6 +3,7 @@
#include "cgroup_helpers.h"
#include <linux/tcp.h>
#include "sockopt_sk.skel.h"
#ifndef SOL_TCP
#define SOL_TCP IPPROTO_TCP
@ -191,60 +192,30 @@ err:
return -1;
}
static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
{
enum bpf_attach_type attach_type;
enum bpf_prog_type prog_type;
struct bpf_program *prog;
int err;
err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
if (err) {
log_err("Failed to deduct types for %s BPF program", title);
return -1;
}
prog = bpf_object__find_program_by_title(obj, title);
if (!prog) {
log_err("Failed to find %s BPF program", title);
return -1;
}
err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd,
attach_type, 0);
if (err) {
log_err("Failed to attach %s BPF program", title);
return -1;
}
return 0;
}
static void run_test(int cgroup_fd)
{
struct bpf_prog_load_attr attr = {
.file = "./sockopt_sk.o",
};
struct bpf_object *obj;
int ignored;
int err;
struct sockopt_sk *skel;
err = bpf_prog_load_xattr(&attr, &obj, &ignored);
if (CHECK_FAIL(err))
return;
skel = sockopt_sk__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_load"))
goto cleanup;
err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt");
if (CHECK_FAIL(err))
goto close_bpf_object;
skel->bss->page_size = getpagesize();
err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt");
if (CHECK_FAIL(err))
goto close_bpf_object;
skel->links._setsockopt =
bpf_program__attach_cgroup(skel->progs._setsockopt, cgroup_fd);
if (!ASSERT_OK_PTR(skel->links._setsockopt, "setsockopt_link"))
goto cleanup;
CHECK_FAIL(getsetsockopt());
skel->links._getsockopt =
bpf_program__attach_cgroup(skel->progs._getsockopt, cgroup_fd);
if (!ASSERT_OK_PTR(skel->links._getsockopt, "getsockopt_link"))
goto cleanup;
close_bpf_object:
bpf_object__close(obj);
ASSERT_OK(getsetsockopt(), "getsetsockopt");
cleanup:
sockopt_sk__destroy(skel);
}
void test_sockopt_sk(void)

27
tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
View File

@ -35,3 +35,30 @@ int dump_task_stack(struct bpf_iter__task *ctx)
return 0;
}
SEC("iter/task")
int get_task_user_stacks(struct bpf_iter__task *ctx)
{
struct seq_file *seq = ctx->meta->seq;
struct task_struct *task = ctx->task;
uint64_t buf_sz = 0;
int64_t res;
if (task == (void *)0)
return 0;
res = bpf_get_task_stack(task, entries,
MAX_STACK_TRACE_DEPTH * SIZE_OF_ULONG, BPF_F_USER_STACK);
if (res <= 0)
return 0;
buf_sz += res;
/* If the verifier doesn't refine bpf_get_task_stack res, and instead
* assumes res is entirely unknown, this program will fail to load as
* the verifier will believe that max buf_sz value allows reading
* past the end of entries in bpf_seq_write call
*/
bpf_seq_write(seq, &entries, buf_sz);
return 0;
}

73
tools/testing/selftests/bpf/progs/linked_funcs1.c Normal file
View File

@ -0,0 +1,73 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Facebook */
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
/* weak and shared between two files */
const volatile int my_tid __weak;
long syscall_id __weak;
int output_val1;
int output_ctx1;
int output_weak1;
/* same "subprog" name in all files, but it's ok because they all are static */
static __noinline int subprog(int x)
{
/* but different formula */
return x * 1;
}
/* Global functions can't be void */
int set_output_val1(int x)
{
output_val1 = x + subprog(x);
return x;
}
/* This function can't be verified as global, as it assumes raw_tp/sys_enter
* context and accesses syscall id (second argument). So we mark it as
* __hidden, so that libbpf will mark it as static in the final object file,
* right before verifying it in the kernel.
*
* But we don't mark it as __hidden here, rather at extern site. __hidden is
* "contaminating" visibility, so it will get propagated from either extern or
* actual definition (including from the losing __weak definition).
*/
void set_output_ctx1(__u64 *ctx)
{
output_ctx1 = ctx[1]; /* long id, same as in BPF_PROG below */
}
/* this weak instance should win because it's the first one */
__weak int set_output_weak(int x)
{
output_weak1 = x;
return x;
}
extern int set_output_val2(int x);
/* here we'll force set_output_ctx2() to be __hidden in the final obj file */
__hidden extern void set_output_ctx2(__u64 *ctx);
SEC("raw_tp/sys_enter")
int BPF_PROG(handler1, struct pt_regs *regs, long id)
{
if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id)
return 0;
set_output_val2(1000);
set_output_ctx2(ctx); /* ctx definition is hidden in BPF_PROG macro */
/* keep input value the same across both files to avoid dependency on
* handler call order; differentiate by output_weak1 vs output_weak2.
*/
set_output_weak(42);
return 0;
}
char LICENSE[] SEC("license") = "GPL";

73
tools/testing/selftests/bpf/progs/linked_funcs2.c Normal file
View File

@ -0,0 +1,73 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Facebook */
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
/* weak and shared between both files */
const volatile int my_tid __weak;
long syscall_id __weak;
int output_val2;
int output_ctx2;
int output_weak2; /* should stay zero */
/* same "subprog" name in all files, but it's ok because they all are static */
static __noinline int subprog(int x)
{
/* but different formula */
return x * 2;
}
/* Global functions can't be void */
int set_output_val2(int x)
{
output_val2 = 2 * x + 2 * subprog(x);
return 2 * x;
}
/* This function can't be verified as global, as it assumes raw_tp/sys_enter
* context and accesses syscall id (second argument). So we mark it as
* __hidden, so that libbpf will mark it as static in the final object file,
* right before verifying it in the kernel.
*
* But we don't mark it as __hidden here, rather at extern site. __hidden is
* "contaminating" visibility, so it will get propagated from either extern or
* actual definition (including from the losing __weak definition).
*/
void set_output_ctx2(__u64 *ctx)
{
output_ctx2 = ctx[1]; /* long id, same as in BPF_PROG below */
}
/* this weak instance should lose, because it will be processed second */
__weak int set_output_weak(int x)
{
output_weak2 = x;
return 2 * x;
}
extern int set_output_val1(int x);
/* here we'll force set_output_ctx1() to be __hidden in the final obj file */
__hidden extern void set_output_ctx1(__u64 *ctx);
SEC("raw_tp/sys_enter")
int BPF_PROG(handler2, struct pt_regs *regs, long id)
{
if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id)
return 0;
set_output_val1(2000);
set_output_ctx1(ctx); /* ctx definition is hidden in BPF_PROG macro */
/* keep input value the same across both files to avoid dependency on
* handler call order; differentiate by output_weak1 vs output_weak2.
*/
set_output_weak(42);
return 0;
}
char LICENSE[] SEC("license") = "GPL";

82
tools/testing/selftests/bpf/progs/linked_maps1.c Normal file
View File

@ -0,0 +1,82 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Facebook */
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
struct my_key { long x; };
struct my_value { long x; };
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__type(key, struct my_key);
__type(value, struct my_value);
__uint(max_entries, 16);
} map1 SEC(".maps");
/* Matches map2 definition in linked_maps2.c. Order of the attributes doesn't
* matter.
*/
typedef struct {
__uint(max_entries, 8);
__type(key, int);
__type(value, int);
__uint(type, BPF_MAP_TYPE_ARRAY);
} map2_t;
extern map2_t map2 SEC(".maps");
/* This should be the winning map definition, but we have no way of verifying,
* so we just make sure that it links and works without errors
*/
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, int);
__type(value, int);
__uint(max_entries, 16);
} map_weak __weak SEC(".maps");
int output_first1;
int output_second1;
int output_weak1;
SEC("raw_tp/sys_enter")
int BPF_PROG(handler_enter1)
{
/* update values with key = 1 */
int key = 1, val = 1;
struct my_key key_struct = { .x = 1 };
struct my_value val_struct = { .x = 1000 };
bpf_map_update_elem(&map1, &key_struct, &val_struct, 0);
bpf_map_update_elem(&map2, &key, &val, 0);
bpf_map_update_elem(&map_weak, &key, &val, 0);
return 0;
}
SEC("raw_tp/sys_exit")
int BPF_PROG(handler_exit1)
{
/* lookup values with key = 2, set in another file */
int key = 2, *val;
struct my_key key_struct = { .x = 2 };
struct my_value *value_struct;
value_struct = bpf_map_lookup_elem(&map1, &key_struct);
if (value_struct)
output_first1 = value_struct->x;
val = bpf_map_lookup_elem(&map2, &key);
if (val)
output_second1 = *val;
val = bpf_map_lookup_elem(&map_weak, &key);
if (val)
output_weak1 = *val;
return 0;
}
char LICENSE[] SEC("license") = "GPL";

76
tools/testing/selftests/bpf/progs/linked_maps2.c Normal file
View File

@ -0,0 +1,76 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Facebook */
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
/* modifiers and typedefs are ignored when comparing key/value types */
typedef struct my_key { long x; } key_type;
typedef struct my_value { long x; } value_type;
extern struct {
__uint(max_entries, 16);
__type(key, key_type);
__type(value, value_type);
__uint(type, BPF_MAP_TYPE_HASH);
} map1 SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, int);
__type(value, int);
__uint(max_entries, 8);
} map2 SEC(".maps");
/* this definition will lose, but it has to exactly match the winner */
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__type(key, int);
__type(value, int);
__uint(max_entries, 16);
} map_weak __weak SEC(".maps");
int output_first2;
int output_second2;
int output_weak2;
SEC("raw_tp/sys_enter")
int BPF_PROG(handler_enter2)
{
/* update values with key = 2 */
int key = 2, val = 2;
key_type key_struct = { .x = 2 };
value_type val_struct = { .x = 2000 };
bpf_map_update_elem(&map1, &key_struct, &val_struct, 0);
bpf_map_update_elem(&map2, &key, &val, 0);
bpf_map_update_elem(&map_weak, &key, &val, 0);
return 0;
}
SEC("raw_tp/sys_exit")
int BPF_PROG(handler_exit2)
{
/* lookup values with key = 1, set in another file */
int key = 1, *val;
key_type key_struct = { .x = 1 };
value_type *value_struct;
value_struct = bpf_map_lookup_elem(&map1, &key_struct);
if (value_struct)
output_first2 = value_struct->x;
val = bpf_map_lookup_elem(&map2, &key);
if (val)
output_second2 = *val;
val = bpf_map_lookup_elem(&map_weak, &key);
if (val)
output_weak2 = *val;
return 0;
}
char LICENSE[] SEC("license") = "GPL";

54
tools/testing/selftests/bpf/progs/linked_vars1.c Normal file
View File

@ -0,0 +1,54 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Facebook */
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
extern int LINUX_KERNEL_VERSION __kconfig;
/* this weak extern will be strict due to the other file's strong extern */
extern bool CONFIG_BPF_SYSCALL __kconfig __weak;
extern const void bpf_link_fops __ksym __weak;
int input_bss1;
int input_data1 = 1;
const volatile int input_rodata1 = 11;
int input_bss_weak __weak;
/* these two definitions should win */
int input_data_weak __weak = 10;
const volatile int input_rodata_weak __weak = 100;
extern int input_bss2;
extern int input_data2;
extern const int input_rodata2;
int output_bss1;
int output_data1;
int output_rodata1;
long output_sink1;
static __noinline int get_bss_res(void)
{
/* just make sure all the relocations work against .text as well */
return input_bss1 + input_bss2 + input_bss_weak;
}
SEC("raw_tp/sys_enter")
int BPF_PROG(handler1)
{
output_bss1 = get_bss_res();
output_data1 = input_data1 + input_data2 + input_data_weak;
output_rodata1 = input_rodata1 + input_rodata2 + input_rodata_weak;
/* make sure we actually use above special externs, otherwise compiler
* will optimize them out
*/
output_sink1 = LINUX_KERNEL_VERSION
+ CONFIG_BPF_SYSCALL
+ (long)&bpf_link_fops;
return 0;
}
char LICENSE[] SEC("license") = "GPL";

55
tools/testing/selftests/bpf/progs/linked_vars2.c Normal file
View File

@ -0,0 +1,55 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Facebook */
#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
extern int LINUX_KERNEL_VERSION __kconfig;
/* when an extern is defined as both strong and weak, resulting symbol will be strong */
extern bool CONFIG_BPF_SYSCALL __kconfig;
extern const void __start_BTF __ksym;
int input_bss2;
int input_data2 = 2;
const volatile int input_rodata2 = 22;
int input_bss_weak __weak;
/* these two weak variables should lose */
int input_data_weak __weak = 20;
const volatile int input_rodata_weak __weak = 200;
extern int input_bss1;
extern int input_data1;
extern const int input_rodata1;
int output_bss2;
int output_data2;
int output_rodata2;
int output_sink2;
static __noinline int get_data_res(void)
{
/* just make sure all the relocations work against .text as well */
return input_data1 + input_data2 + input_data_weak;
}
SEC("raw_tp/sys_enter")
int BPF_PROG(handler2)
{
output_bss2 = input_bss1 + input_bss2 + input_bss_weak;
output_data2 = get_data_res();
output_rodata2 = input_rodata1 + input_rodata2 + input_rodata_weak;
/* make sure we actually use above special externs, otherwise compiler
* will optimize them out
*/
output_sink2 = LINUX_KERNEL_VERSION
+ CONFIG_BPF_SYSCALL
+ (long)&__start_BTF;
return 0;
}
char LICENSE[] SEC("license") = "GPL";

4
tools/testing/selftests/bpf/progs/map_ptr_kern.c
View File

@ -12,6 +12,7 @@ _Static_assert(MAX_ENTRIES < LOOP_BOUND, "MAX_ENTRIES must be < LOOP_BOUND");
enum bpf_map_type g_map_type = BPF_MAP_TYPE_UNSPEC;
__u32 g_line = 0;
int page_size = 0; /* userspace should set it */
#define VERIFY_TYPE(type, func) ({ \
g_map_type = type; \
@ -635,7 +636,6 @@ struct bpf_ringbuf_map {
struct {
__uint(type, BPF_MAP_TYPE_RINGBUF);
__uint(max_entries, 1 << 12);
} m_ringbuf SEC(".maps");
static inline int check_ringbuf(void)
@ -643,7 +643,7 @@ static inline int check_ringbuf(void)
struct bpf_ringbuf_map *ringbuf = (struct bpf_ringbuf_map *)&m_ringbuf;
struct bpf_map *map = (struct bpf_map *)&m_ringbuf;
VERIFY(check(&ringbuf->map, map, 0, 0, 1 << 12));
VERIFY(check(&ringbuf->map, map, 0, 0, page_size));
return 1;
}

12
tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
View File

@ -8,18 +8,6 @@ int _version SEC("version") = 1;
SEC("sk_msg1")
int bpf_prog1(struct sk_msg_md *msg)
{
void *data_end = (void *)(long) msg->data_end;
void *data = (void *)(long) msg->data;
char *d;
if (data + 8 > data_end)
return SK_DROP;
bpf_printk("data length %i\n", (__u64)msg->data_end - (__u64)msg->data);
d = (char *)data;
bpf_printk("hello sendmsg hook %i %i\n", d[0], d[1]);
return SK_PASS;
}

11
tools/testing/selftests/bpf/progs/sockopt_sk.c
View File

@ -6,11 +6,8 @@
#include <bpf/bpf_helpers.h>
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1;
#ifndef PAGE_SIZE
#define PAGE_SIZE 4096
#endif
int page_size = 0; /* userspace should set it */
#ifndef SOL_TCP
#define SOL_TCP IPPROTO_TCP
@ -90,7 +87,7 @@ int _getsockopt(struct bpf_sockopt *ctx)
* program can only see the first PAGE_SIZE
* bytes of data.
*/
if (optval_end - optval != PAGE_SIZE)
if (optval_end - optval != page_size)
return 0; /* EPERM, unexpected data size */
return 1;
@ -161,7 +158,7 @@ int _setsockopt(struct bpf_sockopt *ctx)
if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
/* Original optlen is larger than PAGE_SIZE. */
if (ctx->optlen != PAGE_SIZE * 2)
if (ctx->optlen != page_size * 2)
return 0; /* EPERM, unexpected data size */
if (optval + 1 > optval_end)
@ -175,7 +172,7 @@ int _setsockopt(struct bpf_sockopt *ctx)
* program can only see the first PAGE_SIZE
* bytes of data.
*/
if (optval_end - optval != PAGE_SIZE)
if (optval_end - optval != page_size)
return 0; /* EPERM, unexpected data size */
return 1;

2
tools/testing/selftests/bpf/progs/test_mmap.c
View File

@ -9,7 +9,6 @@ char _license[] SEC("license") = "GPL";
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, 4096);
__uint(map_flags, BPF_F_MMAPABLE | BPF_F_RDONLY_PROG);
__type(key, __u32);
__type(value, char);
@ -17,7 +16,6 @@ struct {
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, 512 * 4); /* at least 4 pages of data */
__uint(map_flags, BPF_F_MMAPABLE);
__type(key, __u32);
__type(value, __u64);

1
tools/testing/selftests/bpf/progs/test_ringbuf.c
View File

@ -15,7 +15,6 @@ struct sample {
struct {
__uint(type, BPF_MAP_TYPE_RINGBUF);
__uint(max_entries, 1 << 12);
} ringbuf SEC(".maps");
/* inputs */

12
tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
View File

@ -15,7 +15,6 @@ struct sample {
struct ringbuf_map {
__uint(type, BPF_MAP_TYPE_RINGBUF);
__uint(max_entries, 1 << 12);
} ringbuf1 SEC(".maps"),
ringbuf2 SEC(".maps");
@ -31,6 +30,17 @@ struct {
},
};
struct {
__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
__uint(max_entries, 1);
__type(key, int);
__array(values, struct ringbuf_map);
} ringbuf_hash SEC(".maps") = {
.values = {
[0] = &ringbuf1,
},
};
/* inputs */
int pid = 0;
int target_ring = 0;

73
tools/testing/selftests/bpf/progs/test_snprintf.c Normal file
View File

@ -0,0 +1,73 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Google LLC. */
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
char num_out[64] = {};
long num_ret = 0;
char ip_out[64] = {};
long ip_ret = 0;
char sym_out[64] = {};
long sym_ret = 0;
char addr_out[64] = {};
long addr_ret = 0;
char str_out[64] = {};
long str_ret = 0;
char over_out[6] = {};
long over_ret = 0;
char pad_out[10] = {};
long pad_ret = 0;
char noarg_out[64] = {};
long noarg_ret = 0;
long nobuf_ret = 0;
extern const void schedule __ksym;
SEC("raw_tp/sys_enter")
int handler(const void *ctx)
{
/* Convenient values to pretty-print */
const __u8 ex_ipv4[] = {127, 0, 0, 1};
const __u8 ex_ipv6[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1};
static const char str1[] = "str1";
static const char longstr[] = "longstr";
/* Integer types */
num_ret = BPF_SNPRINTF(num_out, sizeof(num_out),
"%d %u %x %li %llu %lX",
-8, 9, 150, -424242, 1337, 0xDABBAD00);
/* IP addresses */
ip_ret = BPF_SNPRINTF(ip_out, sizeof(ip_out), "%pi4 %pI6",
&ex_ipv4, &ex_ipv6);
/* Symbol lookup formatting */
sym_ret = BPF_SNPRINTF(sym_out, sizeof(sym_out), "%ps %pS %pB",
&schedule, &schedule, &schedule);
/* Kernel pointers */
addr_ret = BPF_SNPRINTF(addr_out, sizeof(addr_out), "%pK %px %p",
0, 0xFFFF00000ADD4E55, 0xFFFF00000ADD4E55);
/* Strings embedding */
str_ret = BPF_SNPRINTF(str_out, sizeof(str_out), "%s %+05s",
str1, longstr);
/* Overflow */
over_ret = BPF_SNPRINTF(over_out, sizeof(over_out), "%%overflow");
/* Padding of fixed width numbers */
pad_ret = BPF_SNPRINTF(pad_out, sizeof(pad_out), "%5d %0900000X", 4, 4);
/* No args */
noarg_ret = BPF_SNPRINTF(noarg_out, sizeof(noarg_out), "simple case");
/* No buffer */
nobuf_ret = BPF_SNPRINTF(NULL, 0, "only interested in length %d", 60);
return 0;
}
char _license[] SEC("license") = "GPL";

20
tools/testing/selftests/bpf/progs/test_snprintf_single.c Normal file
View File

@ -0,0 +1,20 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Google LLC. */
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
/* The format string is filled from the userspace such that loading fails */
static const char fmt[10];
SEC("raw_tp/sys_enter")
int handler(const void *ctx)
{
unsigned long long arg = 42;
bpf_snprintf(NULL, 0, fmt, &arg, sizeof(arg));
return 0;
}
char _license[] SEC("license") = "GPL";

2
tools/testing/selftests/bpf/progs/test_tunnel_kern.c
View File

@ -396,7 +396,7 @@ int _ip6vxlan_get_tunnel(struct __sk_buff *skb)
SEC("geneve_set_tunnel")
int _geneve_set_tunnel(struct __sk_buff *skb)
{
int ret, ret2;
int ret;
struct bpf_tunnel_key key;
struct geneve_opt gopt;

2
tools/testing/selftests/bpf/test_progs.h
View File

@ -210,7 +210,7 @@ extern int test__join_cgroup(const char *path);
#define ASSERT_ERR_PTR(ptr, name) ({ \
static int duration = 0; \
const void *___res = (ptr); \
bool ___ok = IS_ERR(___res) \
bool ___ok = IS_ERR(___res); \
CHECK(!___ok, (name), "unexpected pointer: %p\n", ___res); \
___ok; \
})

43
tools/testing/selftests/bpf/verifier/bpf_get_stack.c
View File

@ -42,3 +42,46 @@
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
"bpf_get_task_stack return R0 range is refined",
.insns = {
BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_6, 0), // ctx->meta->seq
BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, 8), // ctx->task
BPF_LD_MAP_FD(BPF_REG_1, 0), // fixup_map_array_48b
BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), // keep buf for seq_write
BPF_MOV64_IMM(BPF_REG_3, 48),
BPF_MOV64_IMM(BPF_REG_4, 0),
BPF_EMIT_CALL(BPF_FUNC_get_task_stack),
BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 0, 2),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
BPF_MOV64_REG(BPF_REG_2, BPF_REG_9),
BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
BPF_EMIT_CALL(BPF_FUNC_seq_write),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACING,
.expected_attach_type = BPF_TRACE_ITER,
.kfunc = "task",
.runs = -1, // Don't run, just load
.fixup_map_array_48b = { 3 },
},

4
tools/testing/selftests/lib.mk
View File

@ -1,6 +1,10 @@
# This mimics the top-level Makefile. We do it explicitly here so that this
# Makefile can operate with or without the kbuild infrastructure.
ifneq ($(LLVM),)
CC := clang
else
CC := $(CROSS_COMPILE)gcc
endif
ifeq (0,$(MAKELEVEL))
ifeq ($(OUTPUT),)