0
0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-12-29 05:55:02 +08:00
linux/include/trace/define_trace.h
Alexei Starovoitov c4f6699dfc bpf: introduce BPF_RAW_TRACEPOINT
Introduce BPF_PROG_TYPE_RAW_TRACEPOINT bpf program type to access
kernel internal arguments of the tracepoints in their raw form.

>From bpf program point of view the access to the arguments look like:
struct bpf_raw_tracepoint_args {
       __u64 args[0];
};

int bpf_prog(struct bpf_raw_tracepoint_args *ctx)
{
  // program can read args[N] where N depends on tracepoint
  // and statically verified at program load+attach time
}

kprobe+bpf infrastructure allows programs access function arguments.
This feature allows programs access raw tracepoint arguments.

Similar to proposed 'dynamic ftrace events' there are no abi guarantees
to what the tracepoints arguments are and what their meaning is.
The program needs to type cast args properly and use bpf_probe_read()
helper to access struct fields when argument is a pointer.

For every tracepoint __bpf_trace_##call function is prepared.
In assembler it looks like:
(gdb) disassemble __bpf_trace_xdp_exception
Dump of assembler code for function __bpf_trace_xdp_exception:
   0xffffffff81132080 <+0>:     mov    %ecx,%ecx
   0xffffffff81132082 <+2>:     jmpq   0xffffffff811231f0 <bpf_trace_run3>

where

TRACE_EVENT(xdp_exception,
        TP_PROTO(const struct net_device *dev,
                 const struct bpf_prog *xdp, u32 act),

The above assembler snippet is casting 32-bit 'act' field into 'u64'
to pass into bpf_trace_run3(), while 'dev' and 'xdp' args are passed as-is.
All of ~500 of __bpf_trace_*() functions are only 5-10 byte long
and in total this approach adds 7k bytes to .text.

This approach gives the lowest possible overhead
while calling trace_xdp_exception() from kernel C code and
transitioning into bpf land.
Since tracepoint+bpf are used at speeds of 1M+ events per second
this is valuable optimization.

The new BPF_RAW_TRACEPOINT_OPEN sys_bpf command is introduced
that returns anon_inode FD of 'bpf-raw-tracepoint' object.

The user space looks like:
// load bpf prog with BPF_PROG_TYPE_RAW_TRACEPOINT type
prog_fd = bpf_prog_load(...);
// receive anon_inode fd for given bpf_raw_tracepoint with prog attached
raw_tp_fd = bpf_raw_tracepoint_open("xdp_exception", prog_fd);

Ctrl-C of tracing daemon or cmdline tool that uses this feature
will automatically detach bpf program, unload it and
unregister tracepoint probe.

On the kernel side the __bpf_raw_tp_map section of pointers to
tracepoint definition and to __bpf_trace_*() probe function is used
to find a tracepoint with "xdp_exception" name and
corresponding __bpf_trace_xdp_exception() probe function
which are passed to tracepoint_probe_register() to connect probe
with tracepoint.

Addition of bpf_raw_tracepoint doesn't interfere with ftrace and perf
tracepoint mechanisms. perf_event_open() can be used in parallel
on the same tracepoint.
Multiple bpf_raw_tracepoint_open("xdp_exception", prog_fd) are permitted.
Each with its own bpf program. The kernel will execute
all tracepoint probes and all attached bpf programs.

In the future bpf_raw_tracepoints can be extended with
query/introspection logic.

__bpf_raw_tp_map section logic was contributed by Steven Rostedt

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-28 22:55:19 +02:00

128 lines
3.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Trace files that want to automate creation of all tracepoints defined
* in their file should include this file. The following are macros that the
* trace file may define:
*
* TRACE_SYSTEM defines the system the tracepoint is for
*
* TRACE_INCLUDE_FILE if the file name is something other than TRACE_SYSTEM.h
* This macro may be defined to tell define_trace.h what file to include.
* Note, leave off the ".h".
*
* TRACE_INCLUDE_PATH if the path is something other than core kernel include/trace
* then this macro can define the path to use. Note, the path is relative to
* define_trace.h, not the file including it. Full path names for out of tree
* modules must be used.
*/
#ifdef CREATE_TRACE_POINTS
/* Prevent recursion */
#undef CREATE_TRACE_POINTS
#include <linux/stringify.h>
#undef TRACE_EVENT
#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
DEFINE_TRACE(name)
#undef TRACE_EVENT_CONDITION
#define TRACE_EVENT_CONDITION(name, proto, args, cond, tstruct, assign, print) \
TRACE_EVENT(name, \
PARAMS(proto), \
PARAMS(args), \
PARAMS(tstruct), \
PARAMS(assign), \
PARAMS(print))
#undef TRACE_EVENT_FN
#define TRACE_EVENT_FN(name, proto, args, tstruct, \
assign, print, reg, unreg) \
DEFINE_TRACE_FN(name, reg, unreg)
#undef TRACE_EVENT_FN_COND
#define TRACE_EVENT_FN_COND(name, proto, args, cond, tstruct, \
assign, print, reg, unreg) \
DEFINE_TRACE_FN(name, reg, unreg)
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args) \
DEFINE_TRACE(name)
#undef DEFINE_EVENT_FN
#define DEFINE_EVENT_FN(template, name, proto, args, reg, unreg) \
DEFINE_TRACE_FN(name, reg, unreg)
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_TRACE(name)
#undef DEFINE_EVENT_CONDITION
#define DEFINE_EVENT_CONDITION(template, name, proto, args, cond) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
#undef DECLARE_TRACE
#define DECLARE_TRACE(name, proto, args) \
DEFINE_TRACE(name)
#undef TRACE_INCLUDE
#undef __TRACE_INCLUDE
#ifndef TRACE_INCLUDE_FILE
# define TRACE_INCLUDE_FILE TRACE_SYSTEM
# define UNDEF_TRACE_INCLUDE_FILE
#endif
#ifndef TRACE_INCLUDE_PATH
# define __TRACE_INCLUDE(system) <trace/events/system.h>
# define UNDEF_TRACE_INCLUDE_PATH
#else
# define __TRACE_INCLUDE(system) __stringify(TRACE_INCLUDE_PATH/system.h)
#endif
# define TRACE_INCLUDE(system) __TRACE_INCLUDE(system)
/* Let the trace headers be reread */
#define TRACE_HEADER_MULTI_READ
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
/* Make all open coded DECLARE_TRACE nops */
#undef DECLARE_TRACE
#define DECLARE_TRACE(name, proto, args)
#ifdef TRACEPOINTS_ENABLED
#include <trace/trace_events.h>
#include <trace/perf.h>
#include <trace/bpf_probe.h>
#endif
#undef TRACE_EVENT
#undef TRACE_EVENT_FN
#undef TRACE_EVENT_FN_COND
#undef TRACE_EVENT_CONDITION
#undef DECLARE_EVENT_CLASS
#undef DEFINE_EVENT
#undef DEFINE_EVENT_FN
#undef DEFINE_EVENT_PRINT
#undef DEFINE_EVENT_CONDITION
#undef TRACE_HEADER_MULTI_READ
#undef DECLARE_TRACE
/* Only undef what we defined in this file */
#ifdef UNDEF_TRACE_INCLUDE_FILE
# undef TRACE_INCLUDE_FILE
# undef UNDEF_TRACE_INCLUDE_FILE
#endif
#ifdef UNDEF_TRACE_INCLUDE_PATH
# undef TRACE_INCLUDE_PATH
# undef UNDEF_TRACE_INCLUDE_PATH
#endif
/* We may be processing more files */
#define CREATE_TRACE_POINTS
#endif /* CREATE_TRACE_POINTS */