UbiquitousOS
/
anolis-cloud-kernel
mirror of https://gitee.com/anolis/cloud-kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

bpf: introduce bpf subcommand BPF_TASK_FD_QUERY 

Currently, suppose a userspace application has loaded a bpf program
and attached it to a tracepoint/kprobe/uprobe, and a bpf
introspection tool, e.g., bpftool, wants to show which bpf program
is attached to which tracepoint/kprobe/uprobe. Such attachment
information will be really useful to understand the overall bpf
deployment in the system.

There is a name field (16 bytes) for each program, which could
be used to encode the attachment point. There are some drawbacks
for this approaches. First, bpftool user (e.g., an admin) may not
really understand the association between the name and the
attachment point. Second, if one program is attached to multiple
places, encoding a proper name which can imply all these
attachments becomes difficult.

This patch introduces a new bpf subcommand BPF_TASK_FD_QUERY.
Given a pid and fd, if the <pid, fd> is associated with a
tracepoint/kprobe/uprobe perf event, BPF_TASK_FD_QUERY will return
   . prog_id
   . tracepoint name, or
   . k[ret]probe funcname + offset or kernel addr, or
   . u[ret]probe filename + offset
to the userspace.
The user can use "bpftool prog" to find more information about
bpf program itself with prog_id.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This commit is contained in:
Yonghong Song 2018-05-24 11:21:09 -07:00 committed by Alexei Starovoitov
parent f8d959a5b1
commit 41bdc4b40e
6 changed files with 273 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
include/linux/trace_events.h
View File

@ -473,6 +473,9 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info);
int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name);
int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
u32 *fd_type, const char **buf,
u64 *probe_offset, u64 *probe_addr);
#else
static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
@ -504,6 +507,13 @@ static inline struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name
{
return NULL;
}
static inline int bpf_get_perf_event_info(const struct perf_event *event,
u32 *prog_id, u32 *fd_type,
const char **buf, u64 *probe_offset,
u64 *probe_addr)
{
return -EOPNOTSUPP;
}
#endif
enum {
@ -560,10 +570,17 @@ extern void perf_trace_del(struct perf_event *event, int flags);
#ifdef CONFIG_KPROBE_EVENTS
extern int perf_kprobe_init(struct perf_event *event, bool is_retprobe);
extern void perf_kprobe_destroy(struct perf_event *event);
extern int bpf_get_kprobe_info(const struct perf_event *event,
u32 *fd_type, const char **symbol,
u64 *probe_offset, u64 *probe_addr,
bool perf_type_tracepoint);
#endif
#ifdef CONFIG_UPROBE_EVENTS
extern int perf_uprobe_init(struct perf_event *event, bool is_retprobe);
extern void perf_uprobe_destroy(struct perf_event *event);
extern int bpf_get_uprobe_info(const struct perf_event *event,
u32 *fd_type, const char **filename,
u64 *probe_offset, bool perf_type_tracepoint);
#endif
extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
char *filter_str);

26
include/uapi/linux/bpf.h
View File

@ -97,6 +97,7 @@ enum bpf_cmd {
BPF_RAW_TRACEPOINT_OPEN,
BPF_BTF_LOAD,
BPF_BTF_GET_FD_BY_ID,
BPF_TASK_FD_QUERY,
};
enum bpf_map_type {
@ -380,6 +381,22 @@ union bpf_attr {
__u32 btf_log_size;
__u32 btf_log_level;
};
struct {
__u32 pid; /* input: pid */
__u32 fd; /* input: fd */
__u32 flags; /* input: flags */
__u32 buf_len; /* input/output: buf len */
__aligned_u64 buf; /* input/output:
* tp_name for tracepoint
* symbol for kprobe
* filename for uprobe
*/
__u32 prog_id; /* output: prod_id */
__u32 fd_type; /* output: BPF_FD_TYPE_* */
__u64 probe_offset; /* output: probe_offset */
__u64 probe_addr; /* output: probe_addr */
} task_fd_query;
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF
@ -2557,4 +2574,13 @@ struct bpf_fib_lookup {
__u8 dmac[6]; /* ETH_ALEN */
};
enum bpf_task_fd_type {
BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */
BPF_FD_TYPE_TRACEPOINT, /* tp name */
BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */
BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */
BPF_FD_TYPE_UPROBE, /* filename + offset */
BPF_FD_TYPE_URETPROBE, /* filename + offset */
};
#endif /* _UAPI__LINUX_BPF_H__ */

131
kernel/bpf/syscall.c
View File

@ -18,7 +18,9 @@
#include <linux/vmalloc.h>
#include <linux/mmzone.h>
#include <linux/anon_inodes.h>
#include <linux/fdtable.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/license.h>
#include <linux/filter.h>
#include <linux/version.h>
@ -2178,6 +2180,132 @@ static int bpf_btf_get_fd_by_id(const union bpf_attr *attr)
return btf_get_fd_by_id(attr->btf_id);
}
static int bpf_task_fd_query_copy(const union bpf_attr *attr,
union bpf_attr __user *uattr,
u32 prog_id, u32 fd_type,
const char *buf, u64 probe_offset,
u64 probe_addr)
{
char __user *ubuf = u64_to_user_ptr(attr->task_fd_query.buf);
u32 len = buf ? strlen(buf) : 0, input_len;
int err = 0;
if (put_user(len, &uattr->task_fd_query.buf_len))
return -EFAULT;
input_len = attr->task_fd_query.buf_len;
if (input_len && ubuf) {
if (!len) {
/* nothing to copy, just make ubuf NULL terminated */
char zero = '\0';
if (put_user(zero, ubuf))
return -EFAULT;
} else if (input_len >= len + 1) {
/* ubuf can hold the string with NULL terminator */
if (copy_to_user(ubuf, buf, len + 1))
return -EFAULT;
} else {
/* ubuf cannot hold the string with NULL terminator,
* do a partial copy with NULL terminator.
*/
char zero = '\0';
err = -ENOSPC;
if (copy_to_user(ubuf, buf, input_len - 1))
return -EFAULT;
if (put_user(zero, ubuf + input_len - 1))
return -EFAULT;
}
}
if (put_user(prog_id, &uattr->task_fd_query.prog_id) ||
put_user(fd_type, &uattr->task_fd_query.fd_type) ||
put_user(probe_offset, &uattr->task_fd_query.probe_offset) ||
put_user(probe_addr, &uattr->task_fd_query.probe_addr))
return -EFAULT;
return err;
}
#define BPF_TASK_FD_QUERY_LAST_FIELD task_fd_query.probe_addr
static int bpf_task_fd_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
pid_t pid = attr->task_fd_query.pid;
u32 fd = attr->task_fd_query.fd;
const struct perf_event *event;
struct files_struct *files;
struct task_struct *task;
struct file *file;
int err;
if (CHECK_ATTR(BPF_TASK_FD_QUERY))
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (attr->task_fd_query.flags != 0)
return -EINVAL;
task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
if (!task)
return -ENOENT;
files = get_files_struct(task);
put_task_struct(task);
if (!files)
return -ENOENT;
err = 0;
spin_lock(&files->file_lock);
file = fcheck_files(files, fd);
if (!file)
err = -EBADF;
else
get_file(file);
spin_unlock(&files->file_lock);
put_files_struct(files);
if (err)
goto out;
if (file->f_op == &bpf_raw_tp_fops) {
struct bpf_raw_tracepoint *raw_tp = file->private_data;
struct bpf_raw_event_map *btp = raw_tp->btp;
err = bpf_task_fd_query_copy(attr, uattr,
raw_tp->prog->aux->id,
BPF_FD_TYPE_RAW_TRACEPOINT,
btp->tp->name, 0, 0);
goto put_file;
}
event = perf_get_event(file);
if (!IS_ERR(event)) {
u64 probe_offset, probe_addr;
u32 prog_id, fd_type;
const char *buf;
err = bpf_get_perf_event_info(event, &prog_id, &fd_type,
&buf, &probe_offset,
&probe_addr);
if (!err)
err = bpf_task_fd_query_copy(attr, uattr, prog_id,
fd_type, buf,
probe_offset,
probe_addr);
goto put_file;
}
err = -ENOTSUPP;
put_file:
fput(file);
out:
return err;
}
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
@ -2264,6 +2392,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_BTF_GET_FD_BY_ID:
err = bpf_btf_get_fd_by_id(&attr);
break;
case BPF_TASK_FD_QUERY:
err = bpf_task_fd_query(&attr, uattr);
break;
default:
err = -EINVAL;
break;

48
kernel/trace/bpf_trace.c
View File

@ -14,6 +14,7 @@
#include <linux/uaccess.h>
#include <linux/ctype.h>
#include <linux/kprobes.h>
#include <linux/syscalls.h>
#include <linux/error-injection.h>
#include "trace_probe.h"
@ -1163,3 +1164,50 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
mutex_unlock(&bpf_event_mutex);
return err;
}
int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
u32 *fd_type, const char **buf,
u64 *probe_offset, u64 *probe_addr)
{
bool is_tracepoint, is_syscall_tp;
struct bpf_prog *prog;
int flags, err = 0;
prog = event->prog;
if (!prog)
return -ENOENT;
/* not supporting BPF_PROG_TYPE_PERF_EVENT yet */
if (prog->type == BPF_PROG_TYPE_PERF_EVENT)
return -EOPNOTSUPP;
*prog_id = prog->aux->id;
flags = event->tp_event->flags;
is_tracepoint = flags & TRACE_EVENT_FL_TRACEPOINT;
is_syscall_tp = is_syscall_trace_event(event->tp_event);
if (is_tracepoint || is_syscall_tp) {
*buf = is_tracepoint ? event->tp_event->tp->name
: event->tp_event->name;
*fd_type = BPF_FD_TYPE_TRACEPOINT;
*probe_offset = 0x0;
*probe_addr = 0x0;
} else {
/* kprobe/uprobe */
err = -EOPNOTSUPP;
#ifdef CONFIG_KPROBE_EVENTS
if (flags & TRACE_EVENT_FL_KPROBE)
err = bpf_get_kprobe_info(event, fd_type, buf,
probe_offset, probe_addr,
event->attr.type == PERF_TYPE_TRACEPOINT);
#endif
#ifdef CONFIG_UPROBE_EVENTS
if (flags & TRACE_EVENT_FL_UPROBE)
err = bpf_get_uprobe_info(event, fd_type, buf,
probe_offset,
event->attr.type == PERF_TYPE_TRACEPOINT);
#endif
}
return err;
}

29
kernel/trace/trace_kprobe.c
View File

@ -1287,6 +1287,35 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
head, NULL);
}
NOKPROBE_SYMBOL(kretprobe_perf_func);
int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type,
const char **symbol, u64 *probe_offset,
u64 *probe_addr, bool perf_type_tracepoint)
{
const char *pevent = trace_event_name(event->tp_event);
const char *group = event->tp_event->class->system;
struct trace_kprobe *tk;
if (perf_type_tracepoint)
tk = find_trace_kprobe(pevent, group);
else
tk = event->tp_event->data;
if (!tk)
return -EINVAL;
*fd_type = trace_kprobe_is_return(tk) ? BPF_FD_TYPE_KRETPROBE
: BPF_FD_TYPE_KPROBE;
if (tk->symbol) {
*symbol = tk->symbol;
*probe_offset = tk->rp.kp.offset;
*probe_addr = 0;
} else {
*symbol = NULL;
*probe_offset = 0;
*probe_addr = (unsigned long)tk->rp.kp.addr;
}
return 0;
}
#endif /* CONFIG_PERF_EVENTS */
/*

22
kernel/trace/trace_uprobe.c
View File

@ -1161,6 +1161,28 @@ static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func,
{
__uprobe_perf_func(tu, func, regs, ucb, dsize);
}
int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type,
const char **filename, u64 *probe_offset,
bool perf_type_tracepoint)
{
const char *pevent = trace_event_name(event->tp_event);
const char *group = event->tp_event->class->system;
struct trace_uprobe *tu;
if (perf_type_tracepoint)
tu = find_probe_event(pevent, group);
else
tu = event->tp_event->data;
if (!tu)
return -EINVAL;
*fd_type = is_ret_probe(tu) ? BPF_FD_TYPE_URETPROBE
: BPF_FD_TYPE_UPROBE;
*filename = tu->filename;
*probe_offset = tu->offset;
return 0;
}
#endif /* CONFIG_PERF_EVENTS */
static int