diff options
author | Petr Mladek <pmladek@suse.com> | 2016-12-15 02:05:58 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-12-15 03:04:08 +0300 |
commit | 34aaff40b42148b23dcde40152480e25c7d2d759 (patch) | |
tree | 796f3d19fb9e51e3f6bb73722dcae6e224a36d8f | |
parent | d5d8d3d0d4adcc3aec6e2e0fb656165014a712b7 (diff) | |
download | linux-34aaff40b42148b23dcde40152480e25c7d2d759.tar.xz |
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// using the outdated saved value: 0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.com
Signed-off-by: Petr 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: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r-- | include/linux/kdb.h | 1 | ||||
-rw-r--r-- | kernel/debug/kdb/kdb_io.c | 9 | ||||
-rw-r--r-- | kernel/printk/printk.c | 3 |
3 files changed, 5 insertions, 8 deletions
diff --git a/include/linux/kdb.h b/include/linux/kdb.h index eb706188dc23..68bd88223417 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -161,6 +161,7 @@ enum kdb_msgsrc { }; extern int kdb_trap_printk; +extern int kdb_printf_cpu; extern __printf(2, 0) int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list args); extern __printf(1, 2) int kdb_printf(const char *, ...); diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index daa76154fb1b..e74be38245ad 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -30,6 +30,7 @@ char kdb_prompt_str[CMD_BUFLEN]; int kdb_trap_printk; +int kdb_printf_cpu = -1; static int kgdb_transition_check(char *buffer) { @@ -554,24 +555,19 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) int linecount; int colcount; int logging, saved_loglevel = 0; - int saved_trap_printk; int retlen = 0; int fnd, len; int this_cpu, old_cpu; - static int kdb_printf_cpu = -1; char *cp, *cp2, *cphold = NULL, replaced_byte = ' '; char *moreprompt = "more> "; struct console *c = console_drivers; 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. * But if any cpu goes recursive in kdb, just print the output, * even if it is interleaved with any other text. */ + local_irq_save(flags); this_cpu = smp_processor_id(); for (;;) { old_cpu = cmpxchg(&kdb_printf_cpu, -1, this_cpu); @@ -849,7 +845,6 @@ kdb_print_out: console_loglevel = saved_loglevel; /* kdb_printf_cpu locked the code above. */ smp_store_release(&kdb_printf_cpu, old_cpu); - kdb_trap_printk = saved_trap_printk; local_irq_restore(flags); return retlen; } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 577f2288d19f..a3ce35e0fa1e 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1926,7 +1926,8 @@ int vprintk_default(const char *fmt, va_list args) int r; #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); return r; } |