From: Lai Jiangshan <laijs@cn.fujitsu.com>
To: Ingo Molnar <mingo@elte.hu>, Steven Rostedt <srostedt@redhat.com>,
LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH] ftrace: protect executing nmi
Date: Mon, 16 Mar 2009 20:54:15 +0800 [thread overview]
Message-ID: <49BE4BF7.6050407@cn.fujitsu.com> (raw)
When I review the sensitive code ftrace_nmi_enter(), I found
the atomic variable nmi_running does protect NMI VS do_ftrace_mod_code(),
but it can not protects NMI(entered nmi) VS NMI(ftrace_nmi_enter()).
cpu#1 | cpu#2 | cpu#3
ftrace_nmi_enter() | do_ftrace_mod_code() |
not modify | |
------------------------|-----------------------|--
executing | set mod_code_write = 1|
executing --|-----------------------|--------------------
executing | | ftrace_nmi_enter()
executing | | do modify
------------------------|-----------------------|-----------------
ftrace_nmi_exit() | |
cpu#3 may be being modified the code which is still being executed on cpu#1,
it will have undefined results and possibly take a GPF, this patch
prevents it occurred.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
---
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 1d0d7f4..e016f5e 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -87,7 +87,8 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
*
* If an NMI is executed, the first thing it does is to call
* "ftrace_nmi_enter". This will check if the flag is set to write
- * and if it is, it will write what is in the IP and "code" buffers.
+ * and if it is, and there is no executing nmi, it will write
+ * what is in the IP and "code" buffers.
*
* The trick is, it does not matter if everyone is writing the same
* content to the code location. Also, if a CPU is executing code
@@ -96,6 +97,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
*/
static atomic_t nmi_running = ATOMIC_INIT(0);
+static atomic_t nmi_executing = ATOMIC_INIT(0);
static int mod_code_status; /* holds return value of text write */
static int mod_code_write; /* set when NMI should do the write */
static void *mod_code_ip; /* holds the IP to write to */
@@ -135,14 +137,18 @@ void ftrace_nmi_enter(void)
atomic_inc(&nmi_running);
/* Must have nmi_running seen before reading write flag */
smp_mb();
- if (mod_code_write) {
+ if (!atomic_read(&nmi_executing) && mod_code_write) {
ftrace_mod_code();
atomic_inc(&nmi_update_count);
}
+ atomic_inc(&nmi_executing);
+ smp_mb();
}
void ftrace_nmi_exit(void)
{
+ smp_mb();
+ atomic_dec(&nmi_executing);
/* Finish all executions before clearing nmi_running */
smp_wmb();
atomic_dec(&nmi_running);
next reply other threads:[~2009-03-16 12:55 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-03-16 12:54 Lai Jiangshan [this message]
2009-03-16 17:42 ` [PATCH] ftrace: protect executing nmi Steven Rostedt
2009-03-17 12:54 ` [PATCH 1/2] ftrace: protect running nmi Lai Jiangshan
2009-03-17 12:58 ` [PATCH 2/2] ftrace: fast path for do_ftrace_mod_code() Lai Jiangshan
2009-03-17 14:39 ` Steven Rostedt
2009-03-18 7:02 ` Lai Jiangshan
2009-03-18 8:42 ` [PATCH] ftrace: protect running nmi (V3) Lai Jiangshan
2009-03-19 0:33 ` Steven Rostedt
2009-03-19 2:02 ` Lai Jiangshan
2009-03-20 10:18 ` [tip:tracing/ftrace] " Lai Jiangshan
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=49BE4BF7.6050407@cn.fujitsu.com \
--to=laijs@cn.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=srostedt@redhat.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.