Commit 34aaff40 authored by Petr Mladek's avatar Petr Mladek Committed by Linus Torvalds

kdb: call vkdb_printf() from vprintk_default() only when wanted

kdb_trap_printk allows to pass normal printk() messages to kdb via
vkdb_printk().  For example, it is used to get backtrace using the
classic show_stack(), see kdb_show_stack().

vkdb_printf() tries to avoid a potential infinite loop by disabling the
trap.  But this approach is racy, for example:

CPU1					CPU2

vkdb_printf()
  // assume that kdb_trap_printk == 0
  saved_trap_printk = kdb_trap_printk;
  kdb_trap_printk = 0;

					kdb_show_stack()
					  kdb_trap_printk++;

Problem1: Now, a nested printk() on CPU0 calls vkdb_printf()
	  even when it should have been disabled. It will not
	  cause a deadlock but...

   // using the outdated saved value: 0
   kdb_trap_printk = saved_trap_printk;

					  kdb_trap_printk--;

Problem2: Now, kdb_trap_printk == -1 and will stay like this.
   It means that all messages will get passed to kdb from
   now on.

This patch removes the racy saved_trap_printk handling.  Instead, the
recursion is prevented by a check for the locked CPU.

The solution is still kind of racy.  A non-related printk(), from
another process, might get trapped by vkdb_printf().  And the wanted
printk() might not get trapped because kdb_printf_cpu is assigned.  But
this problem existed even with the original code.

A proper solution would be to get_cpu() before setting kdb_trap_printk
and trap messages only from this CPU.  I am not sure if it is worth the
effort, though.

In fact, the race is very theoretical.  When kdb is running any of the
commands that use kdb_trap_printk there is a single active CPU and the
other CPUs should be in a holding pen inside kgdb_cpu_enter().

The only time this is violated is when there is a timeout waiting for
the other CPUs to report to the holding pen.

Finally, note that the situation is a bit schizophrenic.  vkdb_printf()
explicitly allows recursion but only from KDB code that calls
kdb_printf() directly.  On the other hand, the generic printk()
recursion is not allowed because it might cause an infinite loop.  This
is why we could not hide the decision inside vkdb_printf() easily.

Link: http://lkml.kernel.org/r/1480412276-16690-4-git-send-email-pmladek@suse.comSigned-off-by: default avatarPetr Mladek <pmladek@suse.com>
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Jason Wessel <jason.wessel@windriver.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent d5d8d3d0
...@@ -161,6 +161,7 @@ enum kdb_msgsrc { ...@@ -161,6 +161,7 @@ enum kdb_msgsrc {
}; };
extern int kdb_trap_printk; extern int kdb_trap_printk;
extern int kdb_printf_cpu;
extern __printf(2, 0) int vkdb_printf(enum kdb_msgsrc src, const char *fmt, extern __printf(2, 0) int vkdb_printf(enum kdb_msgsrc src, const char *fmt,
va_list args); va_list args);
extern __printf(1, 2) int kdb_printf(const char *, ...); extern __printf(1, 2) int kdb_printf(const char *, ...);
......
...@@ -30,6 +30,7 @@ ...@@ -30,6 +30,7 @@
char kdb_prompt_str[CMD_BUFLEN]; char kdb_prompt_str[CMD_BUFLEN];
int kdb_trap_printk; int kdb_trap_printk;
int kdb_printf_cpu = -1;
static int kgdb_transition_check(char *buffer) static int kgdb_transition_check(char *buffer)
{ {
...@@ -554,24 +555,19 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) ...@@ -554,24 +555,19 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap)
int linecount; int linecount;
int colcount; int colcount;
int logging, saved_loglevel = 0; int logging, saved_loglevel = 0;
int saved_trap_printk;
int retlen = 0; int retlen = 0;
int fnd, len; int fnd, len;
int this_cpu, old_cpu; int this_cpu, old_cpu;
static int kdb_printf_cpu = -1;
char *cp, *cp2, *cphold = NULL, replaced_byte = ' '; char *cp, *cp2, *cphold = NULL, replaced_byte = ' ';
char *moreprompt = "more> "; char *moreprompt = "more> ";
struct console *c = console_drivers; struct console *c = console_drivers;
unsigned long uninitialized_var(flags); unsigned long uninitialized_var(flags);
local_irq_save(flags);
saved_trap_printk = kdb_trap_printk;
kdb_trap_printk = 0;
/* Serialize kdb_printf if multiple cpus try to write at once. /* Serialize kdb_printf if multiple cpus try to write at once.
* But if any cpu goes recursive in kdb, just print the output, * But if any cpu goes recursive in kdb, just print the output,
* even if it is interleaved with any other text. * even if it is interleaved with any other text.
*/ */
local_irq_save(flags);
this_cpu = smp_processor_id(); this_cpu = smp_processor_id();
for (;;) { for (;;) {
old_cpu = cmpxchg(&kdb_printf_cpu, -1, this_cpu); old_cpu = cmpxchg(&kdb_printf_cpu, -1, this_cpu);
...@@ -849,7 +845,6 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) ...@@ -849,7 +845,6 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap)
console_loglevel = saved_loglevel; console_loglevel = saved_loglevel;
/* kdb_printf_cpu locked the code above. */ /* kdb_printf_cpu locked the code above. */
smp_store_release(&kdb_printf_cpu, old_cpu); smp_store_release(&kdb_printf_cpu, old_cpu);
kdb_trap_printk = saved_trap_printk;
local_irq_restore(flags); local_irq_restore(flags);
return retlen; return retlen;
} }
......
...@@ -1926,7 +1926,8 @@ int vprintk_default(const char *fmt, va_list args) ...@@ -1926,7 +1926,8 @@ int vprintk_default(const char *fmt, va_list args)
int r; int r;
#ifdef CONFIG_KGDB_KDB #ifdef CONFIG_KGDB_KDB
if (unlikely(kdb_trap_printk)) { /* Allow to pass printk() to kdb but avoid a recursion. */
if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) {
r = vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); r = vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args);
return r; return r;
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment