From: Steven Rostedt <rostedt@goodmis.org>
To: linux-kernel@vger.kernel.org
Cc: Ingo Molnar <mingo@elte.hu>, Thomas Gleixner <tglx@linutronix.de>,
Peter Zijlstra <peterz@infradead.org>,
Andrew Morton <akpm@linux-foundation.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Mathieu Desnoyers <compudj@krystal.dyndns.org>,
Steven Rostedt <srostedt@redhat.com>
Subject: [PATCH 3/3] ftrace: make some tracers reentrant
Date: Sat, 04 Oct 2008 02:01:00 -0400 [thread overview]
Message-ID: <20081004060211.867050767@goodmis.org> (raw)
In-Reply-To: 20081004060057.660306328@goodmis.org
[-- Attachment #1: ftrace-disable-less.patch --]
[-- Type: text/plain, Size: 3588 bytes --]
Now that the ring buffer is reentrant, some of the ftrace tracers
(sched_swich, debugging traces) can also be reentrant.
Note: Never make the function tracer reentrant, that can cause
recursion problems all over the kernel. The function tracer
must disable reentrancy.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
---
kernel/trace/trace.c | 10 ++--------
kernel/trace/trace_sched_switch.c | 10 ++--------
2 files changed, 4 insertions(+), 16 deletions(-)
Index: linux-tip.git/kernel/trace/trace.c
===================================================================
--- linux-tip.git.orig/kernel/trace/trace.c 2008-10-04 01:14:30.000000000 -0400
+++ linux-tip.git/kernel/trace/trace.c 2008-10-04 01:49:35.000000000 -0400
@@ -839,7 +839,6 @@ ftrace_special(unsigned long arg1, unsig
{
struct trace_array *tr = &global_trace;
struct trace_array_cpu *data;
- long disabled;
int cpu;
int pc;
@@ -850,12 +849,10 @@ ftrace_special(unsigned long arg1, unsig
preempt_disable_notrace();
cpu = raw_smp_processor_id();
data = tr->data[cpu];
- disabled = atomic_inc_return(&data->disabled);
- if (likely(disabled == 1))
+ if (likely(!atomic_read(&data->disabled)))
ftrace_trace_special(tr, data, arg1, arg2, arg3, pc);
- atomic_dec(&data->disabled);
preempt_enable_notrace();
}
@@ -2961,7 +2958,6 @@ int trace_vprintk(unsigned long ip, cons
struct trace_array_cpu *data;
struct print_entry *entry;
unsigned long flags, irq_flags;
- long disabled;
int cpu, len = 0, size, pc;
if (!tr->ctrl || tracing_disabled)
@@ -2971,9 +2967,8 @@ int trace_vprintk(unsigned long ip, cons
preempt_disable_notrace();
cpu = raw_smp_processor_id();
data = tr->data[cpu];
- disabled = atomic_inc_return(&data->disabled);
- if (unlikely(disabled != 1))
+ if (unlikely(atomic_read(&data->disabled)))
goto out;
spin_lock_irqsave(&trace_buf_lock, flags);
@@ -2999,7 +2994,6 @@ int trace_vprintk(unsigned long ip, cons
spin_unlock_irqrestore(&trace_buf_lock, flags);
out:
- atomic_dec(&data->disabled);
preempt_enable_notrace();
return len;
Index: linux-tip.git/kernel/trace/trace_sched_switch.c
===================================================================
--- linux-tip.git.orig/kernel/trace/trace_sched_switch.c 2008-10-04 01:14:30.000000000 -0400
+++ linux-tip.git/kernel/trace/trace_sched_switch.c 2008-10-04 01:49:35.000000000 -0400
@@ -24,7 +24,6 @@ probe_sched_switch(struct rq *__rq, stru
{
struct trace_array_cpu *data;
unsigned long flags;
- long disabled;
int cpu;
int pc;
@@ -41,12 +40,10 @@ probe_sched_switch(struct rq *__rq, stru
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = ctx_trace->data[cpu];
- disabled = atomic_inc_return(&data->disabled);
- if (likely(disabled == 1))
+ if (likely(!atomic_read(&data->disabled)))
tracing_sched_switch_trace(ctx_trace, data, prev, next, flags, pc);
- atomic_dec(&data->disabled);
local_irq_restore(flags);
}
@@ -55,7 +52,6 @@ probe_sched_wakeup(struct rq *__rq, stru
{
struct trace_array_cpu *data;
unsigned long flags;
- long disabled;
int cpu, pc;
if (!likely(tracer_enabled))
@@ -67,13 +63,11 @@ probe_sched_wakeup(struct rq *__rq, stru
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = ctx_trace->data[cpu];
- disabled = atomic_inc_return(&data->disabled);
- if (likely(disabled == 1))
+ if (likely(!atomic_read(&data->disabled)))
tracing_sched_wakeup_trace(ctx_trace, data, wakee, current,
flags, pc);
- atomic_dec(&data->disabled);
local_irq_restore(flags);
}
--
next prev parent reply other threads:[~2008-10-04 6:02 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-10-04 6:00 [PATCH 0/3] ring-buffer: less locking and only disable preemption Steven Rostedt
2008-10-04 6:00 ` [PATCH 1/3] ring-buffer: move page indexes into page headers Steven Rostedt
2008-10-04 6:00 ` [PATCH 2/3] ring-buffer: make reentrant Steven Rostedt
2008-10-04 6:01 ` Steven Rostedt [this message]
2008-10-04 8:40 ` [PATCH 0/3] ring-buffer: less locking and only disable preemption Ingo Molnar
2008-10-04 14:34 ` Steven Rostedt
2008-10-04 14:44 ` Ingo Molnar
2008-10-04 17:41 ` Ingo Molnar
2008-10-04 22:27 ` Mathieu Desnoyers
2008-10-04 23:21 ` Steven Rostedt
2008-10-06 17:10 ` Mathieu Desnoyers
2008-10-05 10:13 ` Ingo Molnar
2008-10-06 13:53 ` Mathieu Desnoyers
2008-10-04 16:33 ` Mathieu Desnoyers
2008-10-04 17:18 ` Steven Rostedt
2008-10-06 17:13 ` Mathieu Desnoyers
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20081004060211.867050767@goodmis.org \
--to=rostedt@goodmis.org \
--cc=akpm@linux-foundation.org \
--cc=compudj@krystal.dyndns.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=peterz@infradead.org \
--cc=srostedt@redhat.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox