linux/kernel/trace/trace_sched_switch.c
Delyan Kratunov 9c2136be08 sched/tracing: Append prev_state to tp args instead
Commit fa2c3254d7 (sched/tracing: Don't re-read p->state when emitting
sched_switch event, 2022-01-20) added a new prev_state argument to the
sched_switch tracepoint, before the prev task_struct pointer.

This reordering of arguments broke BPF programs that use the raw
tracepoint (e.g. tp_btf programs). The type of the second argument has
changed and existing programs that assume a task_struct* argument
(e.g. for bpf_task_storage access) will now fail to verify.

If we instead append the new argument to the end, all existing programs
would continue to work and can conditionally extract the prev_state
argument on supported kernel versions.

Fixes: fa2c3254d7 (sched/tracing: Don't re-read p->state when emitting sched_switch event, 2022-01-20)
Signed-off-by: Delyan Kratunov <delyank@fb.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/c8a6930dfdd58a4a5755fc01732675472979732b.camel@fb.com
2022-05-12 00:37:11 +02:00

151 lines
3.1 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* trace context switch
*
* Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com>
*
*/
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <trace/events/sched.h>
#include "trace.h"
#define RECORD_CMDLINE 1
#define RECORD_TGID 2
static int sched_cmdline_ref;
static int sched_tgid_ref;
static DEFINE_MUTEX(sched_register_mutex);
static void
probe_sched_switch(void *ignore, bool preempt,
struct task_struct *prev, struct task_struct *next,
unsigned int prev_state)
{
int flags;
flags = (RECORD_TGID * !!sched_tgid_ref) +
(RECORD_CMDLINE * !!sched_cmdline_ref);
if (!flags)
return;
tracing_record_taskinfo_sched_switch(prev, next, flags);
}
static void
probe_sched_wakeup(void *ignore, struct task_struct *wakee)
{
int flags;
flags = (RECORD_TGID * !!sched_tgid_ref) +
(RECORD_CMDLINE * !!sched_cmdline_ref);
if (!flags)
return;
tracing_record_taskinfo_sched_switch(current, wakee, flags);
}
static int tracing_sched_register(void)
{
int ret;
ret = register_trace_sched_wakeup(probe_sched_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup\n");
return ret;
}
ret = register_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup_new\n");
goto fail_deprobe;
}
ret = register_trace_sched_switch(probe_sched_switch, NULL);
if (ret) {
pr_info("sched trace: Couldn't activate tracepoint"
" probe to kernel_sched_switch\n");
goto fail_deprobe_wake_new;
}
return ret;
fail_deprobe_wake_new:
unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
fail_deprobe:
unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
return ret;
}
static void tracing_sched_unregister(void)
{
unregister_trace_sched_switch(probe_sched_switch, NULL);
unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
}
static void tracing_start_sched_switch(int ops)
{
bool sched_register;
mutex_lock(&sched_register_mutex);
sched_register = (!sched_cmdline_ref && !sched_tgid_ref);
switch (ops) {
case RECORD_CMDLINE:
sched_cmdline_ref++;
break;
case RECORD_TGID:
sched_tgid_ref++;
break;
}
if (sched_register && (sched_cmdline_ref || sched_tgid_ref))
tracing_sched_register();
mutex_unlock(&sched_register_mutex);
}
static void tracing_stop_sched_switch(int ops)
{
mutex_lock(&sched_register_mutex);
switch (ops) {
case RECORD_CMDLINE:
sched_cmdline_ref--;
break;
case RECORD_TGID:
sched_tgid_ref--;
break;
}
if (!sched_cmdline_ref && !sched_tgid_ref)
tracing_sched_unregister();
mutex_unlock(&sched_register_mutex);
}
void tracing_start_cmdline_record(void)
{
tracing_start_sched_switch(RECORD_CMDLINE);
}
void tracing_stop_cmdline_record(void)
{
tracing_stop_sched_switch(RECORD_CMDLINE);
}
void tracing_start_tgid_record(void)
{
tracing_start_sched_switch(RECORD_TGID);
}
void tracing_stop_tgid_record(void)
{
tracing_stop_sched_switch(RECORD_TGID);
}