From 42a0bb3f71383b457a7db362f1c69e7afb96732b Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Fri, 20 May 2016 17:00:33 -0700 Subject: printk/nmi: generic solution for safe printk in NMI printk() takes some locks and could not be used a safe way in NMI context. The chance of a deadlock is real especially when printing stacks from all CPUs. This particular problem has been addressed on x86 by the commit a9edc8809328 ("x86/nmi: Perform a safe NMI stack trace on all CPUs"). The patchset brings two big advantages. First, it makes the NMI backtraces safe on all architectures for free. Second, it makes all NMI messages almost safe on all architectures (the temporary buffer is limited. We still should keep the number of messages in NMI context at minimum). Note that there already are several messages printed in NMI context: WARN_ON(in_nmi()), BUG_ON(in_nmi()), anything being printed out from MCE handlers. These are not easy to avoid. This patch reuses most of the code and makes it generic. It is useful for all messages and architectures that support NMI. The alternative printk_func is set when entering and is reseted when leaving NMI context. It queues IRQ work to copy the messages into the main ring buffer in a safe context. __printk_nmi_flush() copies all available messages and reset the buffer. Then we could use a simple cmpxchg operations to get synchronized with writers. There is also used a spinlock to get synchronized with other flushers. We do not longer use seq_buf because it depends on external lock. It would be hard to make all supported operations safe for a lockless use. It would be confusing and error prone to make only some operations safe. The code is put into separate printk/nmi.c as suggested by Steven Rostedt. It needs a per-CPU buffer and is compiled only on architectures that call nmi_enter(). This is achieved by the new HAVE_NMI Kconfig flag. The are MN10300 and Xtensa architectures. We need to clean up NMI handling there first. Let's do it separately. The patch is heavily based on the draft from Peter Zijlstra, see https://lkml.org/lkml/2015/6/10/327 [arnd@arndb.de: printk-nmi: use %zu format string for size_t] [akpm@linux-foundation.org: min_t->min - all types are size_t here] Signed-off-by: Petr Mladek Suggested-by: Peter Zijlstra Suggested-by: Steven Rostedt Cc: Jan Kara Acked-by: Russell King [arm part] Cc: Daniel Thompson Cc: Jiri Kosina Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Martin Schwidefsky Cc: David Miller Cc: Daniel Thompson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux/printk.h') diff --git a/include/linux/printk.h b/include/linux/printk.h index 9ccbdf2c1453..51dd6b824fe2 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -122,7 +122,17 @@ static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } #endif -typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args); +#ifdef CONFIG_PRINTK_NMI +extern void printk_nmi_init(void); +extern void printk_nmi_enter(void); +extern void printk_nmi_exit(void); +extern void printk_nmi_flush(void); +#else +static inline void printk_nmi_init(void) { } +static inline void printk_nmi_enter(void) { } +static inline void printk_nmi_exit(void) { } +static inline void printk_nmi_flush(void) { } +#endif /* PRINTK_NMI */ #ifdef CONFIG_PRINTK asmlinkage __printf(5, 0) -- cgit v1.2.3 From cf9b1106c81c45cde02208fca49d3f3e4ab6ee74 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Fri, 20 May 2016 17:00:42 -0700 Subject: printk/nmi: flush NMI messages on the system panic In NMI context, printk() messages are stored into per-CPU buffers to avoid a possible deadlock. They are normally flushed to the main ring buffer via an IRQ work. But the work is never called when the system calls panic() in the very same NMI handler. This patch tries to flush NMI buffers before the crash dump is generated. In this case it does not risk a double release and bails out when the logbuf_lock is already taken. The aim is to get the messages into the main ring buffer when possible. It makes them better accessible in the vmcore. Then the patch tries to flush the buffers second time when other CPUs are down. It might be more aggressive and reset logbuf_lock. The aim is to get the messages available for the consequent kmsg_dump() and console_flush_on_panic() calls. The patch causes vprintk_emit() to be called even in NMI context again. But it is done via printk_deferred() so that the console handling is skipped. Consoles use internal locks and we could not prevent a deadlock easily. They are explicitly called later when the crash dump is not generated, see console_flush_on_panic(). Signed-off-by: Petr Mladek Cc: Benjamin Herrenschmidt Cc: Daniel Thompson Cc: David Miller Cc: Ingo Molnar Cc: Jan Kara Cc: Jiri Kosina Cc: Martin Schwidefsky Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Russell King Cc: Steven Rostedt Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 2 ++ kernel/kexec_core.c | 1 + kernel/panic.c | 6 +++++- kernel/printk/internal.h | 2 ++ kernel/printk/nmi.c | 39 ++++++++++++++++++++++++++++++++++++++- kernel/printk/printk.c | 2 +- 6 files changed, 49 insertions(+), 3 deletions(-) (limited to 'include/linux/printk.h') diff --git a/include/linux/printk.h b/include/linux/printk.h index 51dd6b824fe2..f4da695fd615 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -127,11 +127,13 @@ extern void printk_nmi_init(void); extern void printk_nmi_enter(void); extern void printk_nmi_exit(void); extern void printk_nmi_flush(void); +extern void printk_nmi_flush_on_panic(void); #else static inline void printk_nmi_init(void) { } static inline void printk_nmi_enter(void) { } static inline void printk_nmi_exit(void) { } static inline void printk_nmi_flush(void) { } +static inline void printk_nmi_flush_on_panic(void) { } #endif /* PRINTK_NMI */ #ifdef CONFIG_PRINTK diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 1c03dfb4abfd..d5d408252992 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -893,6 +893,7 @@ void crash_kexec(struct pt_regs *regs) old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu); if (old_cpu == PANIC_CPU_INVALID) { /* This is the 1st CPU which comes here, so go ahead. */ + printk_nmi_flush_on_panic(); __crash_kexec(regs); /* diff --git a/kernel/panic.c b/kernel/panic.c index 535c96510a44..8aa74497cc5a 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -160,8 +160,10 @@ void panic(const char *fmt, ...) * * Bypass the panic_cpu check and call __crash_kexec directly. */ - if (!crash_kexec_post_notifiers) + if (!crash_kexec_post_notifiers) { + printk_nmi_flush_on_panic(); __crash_kexec(NULL); + } /* * Note smp_send_stop is the usual smp shutdown function, which @@ -176,6 +178,8 @@ void panic(const char *fmt, ...) */ atomic_notifier_call_chain(&panic_notifier_list, 0, buf); + /* Call flush even twice. It tries harder with a single online CPU */ + printk_nmi_flush_on_panic(); kmsg_dump(KMSG_DUMP_PANIC); /* diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 341bedccc065..7fd2838fa417 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -22,6 +22,8 @@ int __printf(1, 0) vprintk_default(const char *fmt, va_list args); #ifdef CONFIG_PRINTK_NMI +extern raw_spinlock_t logbuf_lock; + /* * printk() could not take logbuf_lock in NMI context. Instead, * it temporary stores the strings into a per-CPU buffer. diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c index bf08557d7e3d..b69eb8a2876f 100644 --- a/kernel/printk/nmi.c +++ b/kernel/printk/nmi.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include @@ -106,7 +107,16 @@ static void print_nmi_seq_line(struct nmi_seq_buf *s, int start, int end) { const char *buf = s->buffer + start; - printk("%.*s", (end - start) + 1, buf); + /* + * The buffers are flushed in NMI only on panic. The messages must + * go only into the ring buffer at this stage. Consoles will get + * explicitly called later when a crashdump is not generated. + */ + if (in_nmi()) + printk_deferred("%.*s", (end - start) + 1, buf); + else + printk("%.*s", (end - start) + 1, buf); + } /* @@ -194,6 +204,33 @@ void printk_nmi_flush(void) __printk_nmi_flush(&per_cpu(nmi_print_seq, cpu).work); } +/** + * printk_nmi_flush_on_panic - flush all per-cpu nmi buffers when the system + * goes down. + * + * Similar to printk_nmi_flush() but it can be called even in NMI context when + * the system goes down. It does the best effort to get NMI messages into + * the main ring buffer. + * + * Note that it could try harder when there is only one CPU online. + */ +void printk_nmi_flush_on_panic(void) +{ + /* + * Make sure that we could access the main ring buffer. + * Do not risk a double release when more CPUs are up. + */ + if (in_nmi() && raw_spin_is_locked(&logbuf_lock)) { + if (num_online_cpus() > 1) + return; + + debug_locks_off(); + raw_spin_lock_init(&logbuf_lock); + } + + printk_nmi_flush(); +} + void __init printk_nmi_init(void) { int cpu; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index e38579d730f4..60cdf6386763 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -245,7 +245,7 @@ __packed __aligned(4) * within the scheduler's rq lock. It must be released before calling * console_unlock() or anything else that might wake up a process. */ -static DEFINE_RAW_SPINLOCK(logbuf_lock); +DEFINE_RAW_SPINLOCK(logbuf_lock); #ifdef CONFIG_PRINTK DECLARE_WAIT_QUEUE_HEAD(log_wait); -- cgit v1.2.3