diff --git a/arch/Kconfig b/arch/Kconfig
index 0f298f9123dc5f9d4454036a0edbc18c9519efcb..8f84fd268dee6a2c4bf3792352c48ff11e2e6222 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -187,7 +187,11 @@ config HAVE_OPTPROBES
config HAVE_KPROBES_ON_FTRACE
bool
+config HAVE_NMI
+ bool
+
config HAVE_NMI_WATCHDOG
+ depends on HAVE_NMI
bool
#
# An arch should select this if it provides all these things:
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 956d3575426cc45f38b7ad07c2d426025415af9c..90542db1220dbcff5bc7f0d27ce233389a6d780d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -67,6 +67,7 @@ config ARM
select HAVE_KRETPROBES if (HAVE_KPROBES)
select HAVE_MEMBLOCK
select HAVE_MOD_ARCH_SPECIFIC
+ select HAVE_NMI
select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
select HAVE_OPTPROBES if !THUMB2_KERNEL
select HAVE_PERF_EVENTS
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index baee70267f2939367ab412a8adaa5df929bb3f10..df90bc59bfce2893328c3c79e12658c106897c90 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -644,9 +644,11 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
break;
case IPI_CPU_BACKTRACE:
+ printk_nmi_enter();
irq_enter();
nmi_cpu_backtrace(regs);
irq_exit();
+ printk_nmi_exit();
break;
default:
diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index e43519a2ca89b47b007e4935b03142a76800bf6b..7e75d45e20cdf271ce8f0025fc362e3c37048dfd 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -18,6 +18,7 @@ config AVR32
select GENERIC_CLOCKEVENTS
select HAVE_MOD_ARCH_SPECIFIC
select MODULES_USE_ELF_RELA
+ select HAVE_NMI
help
AVR32 is a high-performance 32-bit RISC microprocessor core,
designed for cost-sensitive embedded applications, with particular
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index a63c12259e77e03832c9d3c50da6ecbc9e62db18..28c63fea786d38b1e6f671296e908f784eb18a59 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -40,6 +40,7 @@ config BLACKFIN
select HAVE_MOD_ARCH_SPECIFIC
select MODULES_USE_ELF_RELA
select HAVE_DEBUG_STACKOVERFLOW
+ select HAVE_NMI
config GENERIC_CSUM
def_bool y
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index 5c0ca8ae929315b8c7acbcae5976a0f6bfde937c..deba2662b9f3d3d2fd13fdc6441bdb912eae3150 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -70,6 +70,7 @@ config CRIS
select GENERIC_CLOCKEVENTS if ETRAX_ARCH_V32
select GENERIC_SCHED_CLOCK if ETRAX_ARCH_V32
select HAVE_DEBUG_BUGVERBOSE if ETRAX_ARCH_V32
+ select HAVE_NMI
config HZ
int
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 5663f411c22565b3ba9fa8e717a5230135698732..8040fb1845b422ecad8b632671b8a5aedae7277d 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -48,6 +48,7 @@ config MIPS
select GENERIC_SCHED_CLOCK if !CAVIUM_OCTEON_SOC
select GENERIC_CMOS_UPDATE
select HAVE_MOD_ARCH_SPECIFIC
+ select HAVE_NMI
select VIRT_TO_BUS
select MODULES_USE_ELF_REL if MODULES
select MODULES_USE_ELF_RELA if MODULES && 64BIT
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index f0403b58ae8b131dda59e051d9c31e809648a0b3..01f7464d9fea68033b7ef8876e22e0352e365597 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -155,6 +155,7 @@ config PPC
select NO_BOOTMEM
select HAVE_GENERIC_RCU_GUP
select HAVE_PERF_EVENTS_NMI if PPC64
+ select HAVE_NMI if PERF_EVENTS
select EDAC_SUPPORT
select EDAC_ATOMIC_SCRUB
select ARCH_HAS_DMA_SET_COHERENT_MASK
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index e2c9aaaf64b22edca386b83519ed12c7a5a8e121..1c3c43d9d1b54f5d828c45f272e7dc0be882024f 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -166,6 +166,7 @@ config S390
select TTY
select VIRT_CPU_ACCOUNTING
select VIRT_TO_BUS
+ select HAVE_NMI
config SCHED_OMIT_FRAME_POINTER
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index cb93af8f80171ff29bcc07116859b70e096b638a..f6254341c065da7ac4606b02a342c13b70b8e243 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -44,6 +44,7 @@ config SUPERH
select OLD_SIGSUSPEND
select OLD_SIGACTION
select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_NMI
help
The SuperH is a RISC processor targeted for use in embedded systems
and consumer electronics; it was also used in the Sega Dreamcast
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 27b3a0ad40a0c8b1b75c449f322669fdebc37955..1012f7ffcdf5f5486ffe67ec185c356509d6f6b6 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -79,6 +79,7 @@ config SPARC64
select NO_BOOTMEM
select HAVE_ARCH_AUDITSYSCALL
select ARCH_SUPPORTS_ATOMIC_RMW
+ select HAVE_NMI
config ARCH_DEFCONFIG
string
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 174746225577aabc1131e7b8ffc9b2bd674e975c..76989b878f3ce63a1c1d6b9d67afef4396998a18 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -30,6 +30,7 @@ config TILE
select HAVE_DEBUG_STACKOVERFLOW
select ARCH_WANT_FRAME_POINTERS
select HAVE_CONTEXT_TRACKING
+ select HAVE_NMI if USE_PMC
select EDAC_SUPPORT
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ff5b3be95d46f0799bcefc9d75e2f99360c4e3a..0a7b885964baccd540f2c9e600dce014398bd987 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -131,6 +131,7 @@ config X86
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_MIXED_BREAKPOINTS_REGS
+ select HAVE_NMI
select HAVE_OPROFILE
select HAVE_OPTPROBES
select HAVE_PCSPKR_PLATFORM
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 045e424fb3680f67405849be4aaa5355f5b4f3ff..7788ce643bf4577d443b1007a1e4d37c8d28aaff 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -18,7 +18,6 @@
#include <linux/nmi.h>
#include <linux/module.h>
#include <linux/delay.h>
-#include <linux/seq_buf.h>
#ifdef CONFIG_HARDLOCKUP_DETECTOR
u64 hw_nmi_get_sample_period(int watchdog_thresh)
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index dfd59d6bc6f0f74ef89b0512a25180fd0077e2d3..c683996110b15f1ca45e9b7499fc983a036c5b96 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -61,6 +61,7 @@ extern void irq_exit(void);
#define nmi_enter() \
do { \
+ printk_nmi_enter(); \
lockdep_off(); \
ftrace_nmi_enter(); \
BUG_ON(in_nmi()); \
@@ -77,6 +78,7 @@ extern void irq_exit(void);
preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \
ftrace_nmi_exit(); \
lockdep_on(); \
+ printk_nmi_exit(); \
} while (0)
#endif /* LINUX_HARDIRQ_H */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 4bc6dafb703eaa6ec3d0f1d6deff3cbb82a82f06..56939d3f6e531baa21d7770e5ee8f256f3957c86 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -129,7 +129,4 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
(typeof(type) __percpu *)__alloc_percpu(sizeof(type), \
__alignof__(type))
-/* To avoid include hell, as printk can not declare this, we declare it here */
-DECLARE_PER_CPU(printk_func_t, printk_func);
-
#endif /* __LINUX_PERCPU_H */
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 9ccbdf2c1453f4897ea884d4a89ea5a8bb04ede8..51dd6b824fe24688cf6dc529478e5c2a8c2613f9 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)
diff --git a/init/Kconfig b/init/Kconfig
index 79a91a2c0444c72f8cb5c0435927d0ec06de5280..bccc1d607be540ebb44fe494446039ceffd6f577 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1454,6 +1454,11 @@ config PRINTK
very difficult to diagnose system problems, saying N here is
strongly discouraged.
+config PRINTK_NMI
+ def_bool y
+ depends on PRINTK
+ depends on HAVE_NMI
+
config BUG
bool "BUG() support" if EXPERT
default y
diff --git a/init/main.c b/init/main.c
index 2075fafaad595ac46fc1407c17edc61299e0f3ef..fa9b2bdde18372257d98ec6e724e86527927403a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -569,6 +569,7 @@ asmlinkage __visible void __init start_kernel(void)
timekeeping_init();
time_init();
sched_clock_postinit();
+ printk_nmi_init();
perf_event_init();
profile_init();
call_function_init();
diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile
index 85405bdcf2b326b4fcc3e6bcb1df24b9dcd4daee..abb0042a427ba3c4a60fc43e78cd348cda9042c6 100644
--- a/kernel/printk/Makefile
+++ b/kernel/printk/Makefile
@@ -1,2 +1,3 @@
obj-y = printk.o
+obj-$(CONFIG_PRINTK_NMI) += nmi.o
obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
new file mode 100644
index 0000000000000000000000000000000000000000..2de99faedfc1c78123f29ecfb9ce68d72e9eb42d
--- /dev/null
+++ b/kernel/printk/internal.h
@@ -0,0 +1,44 @@
+/*
+ * internal.h - printk internal definitions
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/percpu.h>
+
+typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args);
+
+int __printf(1, 0) vprintk_default(const char *fmt, va_list args);
+
+#ifdef CONFIG_PRINTK_NMI
+
+/*
+ * printk() could not take logbuf_lock in NMI context. Instead,
+ * it temporary stores the strings into a per-CPU buffer.
+ * The alternative implementation is chosen transparently
+ * via per-CPU variable.
+ */
+DECLARE_PER_CPU(printk_func_t, printk_func);
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
+{
+ return this_cpu_read(printk_func)(fmt, args);
+}
+
+#else /* CONFIG_PRINTK_NMI */
+
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
+{
+ return vprintk_default(fmt, args);
+}
+
+#endif /* CONFIG_PRINTK_NMI */
diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c
new file mode 100644
index 0000000000000000000000000000000000000000..303cf0d15e5757452a90300b86480a3b0b79b262
--- /dev/null
+++ b/kernel/printk/nmi.c
@@ -0,0 +1,219 @@
+/*
+ * nmi.c - Safe printk in NMI context
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/preempt.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/cpumask.h>
+#include <linux/irq_work.h>
+#include <linux/printk.h>
+
+#include "internal.h"
+
+/*
+ * printk() could not take logbuf_lock in NMI context. Instead,
+ * it uses an alternative implementation that temporary stores
+ * the strings into a per-CPU buffer. The content of the buffer
+ * is later flushed into the main ring buffer via IRQ work.
+ *
+ * The alternative implementation is chosen transparently
+ * via @printk_func per-CPU variable.
+ *
+ * The implementation allows to flush the strings also from another CPU.
+ * There are situations when we want to make sure that all buffers
+ * were handled or when IRQs are blocked.
+ */
+DEFINE_PER_CPU(printk_func_t, printk_func) = vprintk_default;
+static int printk_nmi_irq_ready;
+
+#define NMI_LOG_BUF_LEN (4096 - sizeof(atomic_t) - sizeof(struct irq_work))
+
+struct nmi_seq_buf {
+ atomic_t len; /* length of written data */
+ struct irq_work work; /* IRQ work that flushes the buffer */
+ unsigned char buffer[NMI_LOG_BUF_LEN];
+};
+static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
+
+/*
+ * Safe printk() for NMI context. It uses a per-CPU buffer to
+ * store the message. NMIs are not nested, so there is always only
+ * one writer running. But the buffer might get flushed from another
+ * CPU, so we need to be careful.
+ */
+static int vprintk_nmi(const char *fmt, va_list args)
+{
+ struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
+ int add = 0;
+ size_t len;
+
+again:
+ len = atomic_read(&s->len);
+
+ if (len >= sizeof(s->buffer))
+ return 0;
+
+ /*
+ * Make sure that all old data have been read before the buffer was
+ * reseted. This is not needed when we just append data.
+ */
+ if (!len)
+ smp_rmb();
+
+ add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args);
+
+ /*
+ * Do it once again if the buffer has been flushed in the meantime.
+ * Note that atomic_cmpxchg() is an implicit memory barrier that
+ * makes sure that the data were written before updating s->len.
+ */
+ if (atomic_cmpxchg(&s->len, len, len + add) != len)
+ goto again;
+
+ /* Get flushed in a more safe context. */
+ if (add && printk_nmi_irq_ready) {
+ /* Make sure that IRQ work is really initialized. */
+ smp_rmb();
+ irq_work_queue(&s->work);
+ }
+
+ return add;
+}
+
+/*
+ * printk one line from the temporary buffer from @start index until
+ * and including the @end index.
+ */
+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);
+}
+
+/*
+ * Flush data from the associated per_CPU buffer. The function
+ * can be called either via IRQ work or independently.
+ */
+static void __printk_nmi_flush(struct irq_work *work)
+{
+ static raw_spinlock_t read_lock =
+ __RAW_SPIN_LOCK_INITIALIZER(read_lock);
+ struct nmi_seq_buf *s = container_of(work, struct nmi_seq_buf, work);
+ unsigned long flags;
+ size_t len, size;
+ int i, last_i;
+
+ /*
+ * The lock has two functions. First, one reader has to flush all
+ * available message to make the lockless synchronization with
+ * writers easier. Second, we do not want to mix messages from
+ * different CPUs. This is especially important when printing
+ * a backtrace.
+ */
+ raw_spin_lock_irqsave(&read_lock, flags);
+
+ i = 0;
+more:
+ len = atomic_read(&s->len);
+
+ /*
+ * This is just a paranoid check that nobody has manipulated
+ * the buffer an unexpected way. If we printed something then
+ * @len must only increase.
+ */
+ if (i && i >= len)
+ pr_err("printk_nmi_flush: internal error: i=%d >= len=%zu\n",
+ i, len);
+
+ if (!len)
+ goto out; /* Someone else has already flushed the buffer. */
+
+ /* Make sure that data has been written up to the @len */
+ smp_rmb();
+
+ size = min(len, sizeof(s->buffer));
+ last_i = i;
+
+ /* Print line by line. */
+ for (; i < size; i++) {
+ if (s->buffer[i] == '\n') {
+ print_nmi_seq_line(s, last_i, i);
+ last_i = i + 1;
+ }
+ }
+ /* Check if there was a partial line. */
+ if (last_i < size) {
+ print_nmi_seq_line(s, last_i, size - 1);
+ pr_cont("\n");
+ }
+
+ /*
+ * Check that nothing has got added in the meantime and truncate
+ * the buffer. Note that atomic_cmpxchg() is an implicit memory
+ * barrier that makes sure that the data were copied before
+ * updating s->len.
+ */
+ if (atomic_cmpxchg(&s->len, len, 0) != len)
+ goto more;
+
+out:
+ raw_spin_unlock_irqrestore(&read_lock, flags);
+}
+
+/**
+ * printk_nmi_flush - flush all per-cpu nmi buffers.
+ *
+ * The buffers are flushed automatically via IRQ work. This function
+ * is useful only when someone wants to be sure that all buffers have
+ * been flushed at some point.
+ */
+void printk_nmi_flush(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ __printk_nmi_flush(&per_cpu(nmi_print_seq, cpu).work);
+}
+
+void __init printk_nmi_init(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct nmi_seq_buf *s = &per_cpu(nmi_print_seq, cpu);
+
+ init_irq_work(&s->work, __printk_nmi_flush);
+ }
+
+ /* Make sure that IRQ works are initialized before enabling. */
+ smp_wmb();
+ printk_nmi_irq_ready = 1;
+
+ /* Flush pending messages that did not have scheduled IRQ works. */
+ printk_nmi_flush();
+}
+
+void printk_nmi_enter(void)
+{
+ this_cpu_write(printk_func, vprintk_nmi);
+}
+
+void printk_nmi_exit(void)
+{
+ this_cpu_write(printk_func, vprintk_default);
+}
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index bfbf284e421864377f72d4d2cb22a9dde264f327..71eba060703461cba45cdebad150a2643304938f 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -55,6 +55,7 @@
#include "console_cmdline.h"
#include "braille.h"
+#include "internal.h"
int console_printk[4] = {
CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */
@@ -1807,14 +1808,6 @@ int vprintk_default(const char *fmt, va_list args)
}
EXPORT_SYMBOL_GPL(vprintk_default);
-/*
- * This allows printk to be diverted to another function per cpu.
- * This is useful for calling printk functions from within NMI
- * without worrying about race conditions that can lock up the
- * box.
- */
-DEFINE_PER_CPU(printk_func_t, printk_func) = vprintk_default;
-
/**
* printk - print a kernel message
* @fmt: format string
@@ -1838,21 +1831,11 @@ DEFINE_PER_CPU(printk_func_t, printk_func) = vprintk_default;
*/
asmlinkage __visible int printk(const char *fmt, ...)
{
- printk_func_t vprintk_func;
va_list args;
int r;
va_start(args, fmt);
-
- /*
- * If a caller overrides the per_cpu printk_func, then it needs
- * to disable preemption when calling printk(). Otherwise
- * the printk_func should be set to the default. No need to
- * disable preemption here.
- */
- vprintk_func = this_cpu_read(printk_func);
r = vprintk_func(fmt, args);
-
va_end(args);
return r;
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index 6019c53c669e176bcf36cf3e8bffb35c9b893432..26caf51cc2383e80bc1902c6c65b66102e8d5af0 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -16,33 +16,14 @@
#include <linux/delay.h>
#include <linux/kprobes.h>
#include <linux/nmi.h>
-#include <linux/seq_buf.h>
#ifdef arch_trigger_all_cpu_backtrace
/* For reliability, we're prepared to waste bits here. */
static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
-static cpumask_t printtrace_mask;
-
-#define NMI_BUF_SIZE 4096
-
-struct nmi_seq_buf {
- unsigned char buffer[NMI_BUF_SIZE];
- struct seq_buf seq;
-};
-
-/* Safe printing in NMI context */
-static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
/* "in progress" flag of arch_trigger_all_cpu_backtrace */
static unsigned long backtrace_flag;
-static void print_seq_line(struct nmi_seq_buf *s, int start, int end)
-{
- const char *buf = s->buffer + start;
-
- printk("%.*s", (end - start) + 1, buf);
-}
-
/*
* When raise() is called it will be is passed a pointer to the
* backtrace_mask. Architectures that call nmi_cpu_backtrace()
@@ -52,8 +33,7 @@ static void print_seq_line(struct nmi_seq_buf *s, int start, int end)
void nmi_trigger_all_cpu_backtrace(bool include_self,
void (*raise)(cpumask_t *mask))
{
- struct nmi_seq_buf *s;
- int i, cpu, this_cpu = get_cpu();
+ int i, this_cpu = get_cpu();
if (test_and_set_bit(0, &backtrace_flag)) {
/*
@@ -68,17 +48,6 @@ void nmi_trigger_all_cpu_backtrace(bool include_self,
if (!include_self)
cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask));
- cpumask_copy(&printtrace_mask, to_cpumask(backtrace_mask));
-
- /*
- * Set up per_cpu seq_buf buffers that the NMIs running on the other
- * CPUs will write to.
- */
- for_each_cpu(cpu, to_cpumask(backtrace_mask)) {
- s = &per_cpu(nmi_print_seq, cpu);
- seq_buf_init(&s->seq, s->buffer, NMI_BUF_SIZE);
- }
-
if (!cpumask_empty(to_cpumask(backtrace_mask))) {
pr_info("Sending NMI to %s CPUs:\n",
(include_self ? "all" : "other"));
@@ -94,73 +63,25 @@ void nmi_trigger_all_cpu_backtrace(bool include_self,
}
/*
- * Now that all the NMIs have triggered, we can dump out their
- * back traces safely to the console.
+ * Force flush any remote buffers that might be stuck in IRQ context
+ * and therefore could not run their irq_work.
*/
- for_each_cpu(cpu, &printtrace_mask) {
- int len, last_i = 0;
+ printk_nmi_flush();
- s = &per_cpu(nmi_print_seq, cpu);
- len = seq_buf_used(&s->seq);
- if (!len)
- continue;
-
- /* Print line by line. */
- for (i = 0; i < len; i++) {
- if (s->buffer[i] == '\n') {
- print_seq_line(s, last_i, i);
- last_i = i + 1;
- }
- }
- /* Check if there was a partial line. */
- if (last_i < len) {
- print_seq_line(s, last_i, len - 1);
- pr_cont("\n");
- }
- }
-
- clear_bit(0, &backtrace_flag);
- smp_mb__after_atomic();
+ clear_bit_unlock(0, &backtrace_flag);
put_cpu();
}
-/*
- * It is not safe to call printk() directly from NMI handlers.
- * It may be fine if the NMI detected a lock up and we have no choice
- * but to do so, but doing a NMI on all other CPUs to get a back trace
- * can be done with a sysrq-l. We don't want that to lock up, which
- * can happen if the NMI interrupts a printk in progress.
- *
- * Instead, we redirect the vprintk() to this nmi_vprintk() that writes
- * the content into a per cpu seq_buf buffer. Then when the NMIs are
- * all done, we can safely dump the contents of the seq_buf to a printk()
- * from a non NMI context.
- */
-static int nmi_vprintk(const char *fmt, va_list args)
-{
- struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
- unsigned int len = seq_buf_used(&s->seq);
-
- seq_buf_vprintf(&s->seq, fmt, args);
- return seq_buf_used(&s->seq) - len;
-}
-
bool nmi_cpu_backtrace(struct pt_regs *regs)
{
int cpu = smp_processor_id();
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
- printk_func_t printk_func_save = this_cpu_read(printk_func);
-
- /* Replace printk to write into the NMI seq */
- this_cpu_write(printk_func, nmi_vprintk);
pr_warn("NMI backtrace for cpu %d\n", cpu);
if (regs)
show_regs(regs);
else
dump_stack();
- this_cpu_write(printk_func, printk_func_save);
-
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
return true;
}