[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <49BF9D8A.4070200@cn.fujitsu.com>
Date: Tue, 17 Mar 2009 20:54:34 +0800
From: Lai Jiangshan <laijs@...fujitsu.com>
To: Steven Rostedt <srostedt@...hat.com>
CC: Ingo Molnar <mingo@...e.hu>, LKML <linux-kernel@...r.kernel.org>
Subject: [PATCH 1/2] ftrace: protect running nmi
Steven Rostedt wrote:
>> 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);
>> }
>
> Here we have another race window. If cpu#1 has that NMI and right here
> we get a SMI (something to make the race window bigger). cpu#2 could
> have set the mod_code_write and cpu#3 could have another NMI that sees
> it but does not see the nmi_executing flag. Now we are in the same
> scenario as you nicely described up above.
I missed this window.
> void ftrace_nmi_enter(void)
> {
> if (atomic_inc_return(&mod_code_write) > 10000) {
> ftrace_mod_code();
> atomic_inc(&nmi_update_count);
> }
> smp_mb();
> }
>
> void ftrace_nmi_exit(void)
> {
> smp_mb();
> atomic_dec(&mod_code_write);
> }
>
> Then in do_ftrace_mod_code ...
>
>
> while (atomic_cmpxchg(&mod_code_write, 0, 10001) != 0)
> ;
>
> [...]
>
>
> while (atomic_cmpxchg(&mode_code_write, 10001, 0) != 10001)
> ;
>
>
> Does this look like it would solve the issue?
>
It's very nice. The write-flag and the counter are put into an atomic
together. The write-flag is changed only when there is no running NMI.
So any NMI sees this flag, all other running NMIs also see this flag
when them were entering.
Subject: [PATCH 1/2] ftrace: protect running nmi (V2)
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@...fujitsu.com>
---
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 1d0d7f4..699a1c0 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -79,11 +79,11 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
*
* 1) Put the instruction pointer into the IP buffer
* and the new code into the "code" buffer.
- * 2) Set a flag that says we are modifying code
- * 3) Wait for any running NMIs to finish.
- * 4) Write the code
- * 5) clear the flag.
- * 6) Wait for any running NMIs to finish.
+ * 2) Wait for any running NMIs to finish and set a flag that says
+ * we are modifying code, it is done in an atomic operation.
+ * 3) Write the code
+ * 4) clear the flag and wait for any running NMIs to finish,
+ * it is also done in an atomic operation.
*
* 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
@@ -95,9 +95,9 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
* are the same as what exists.
*/
+#define MOD_CODE_WRITE_FLAG (1 << 31) /* set when NMI should do the write */
static atomic_t nmi_running = 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 */
static void *mod_code_newcode; /* holds the text to write to the IP */
@@ -124,40 +124,36 @@ static void ftrace_mod_code(void)
*/
mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
MCOUNT_INSN_SIZE);
-
- /* if we fail, then kill any new writers */
- if (mod_code_status)
- mod_code_write = 0;
}
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_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
+ smp_rmb();
ftrace_mod_code();
atomic_inc(&nmi_update_count);
}
+ /* Must have previous changes seen before executions */
+ smp_mb();
}
void ftrace_nmi_exit(void)
{
/* Finish all executions before clearing nmi_running */
- smp_wmb();
+ smp_mb();
atomic_dec(&nmi_running);
}
-static void wait_for_nmi(void)
+static void wait_and_set(int wait_val, int set_val)
{
- if (!atomic_read(&nmi_running))
- return;
+ int wait = 0;
- do {
+ while (atomic_cmpxchg(&nmi_running, wait_val, set_val) != wait_val) {
+ wait = 1;
cpu_relax();
- } while (atomic_read(&nmi_running));
+ }
- nmi_wait_count++;
+ nmi_wait_count += wait;
}
static int
@@ -166,15 +162,13 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
mod_code_ip = (void *)ip;
mod_code_newcode = new_code;
- /* The buffers need to be visible before we let NMIs write them */
- smp_wmb();
-
- mod_code_write = 1;
-
- /* Make sure write bit is visible before we wait on NMIs */
+ /*
+ * The previous variables need to be visible before NMIs sees
+ * the MOD_CODE_WRITE_FLAG.
+ */
smp_mb();
- wait_for_nmi();
+ wait_and_set(0, MOD_CODE_WRITE_FLAG);
/* Make sure all running NMIs have finished before we write the code */
smp_mb();
@@ -182,14 +176,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
ftrace_mod_code();
/* Make sure the write happens before clearing the bit */
- smp_wmb();
-
- mod_code_write = 0;
-
- /* make sure NMIs see the cleared bit */
smp_mb();
- wait_for_nmi();
+ wait_and_set(MOD_CODE_WRITE_FLAG, 0);
return mod_code_status;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists