From f92bac3b141b8233e34ddf32d227e12bfba07b48 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Tue, 27 Dec 2016 23:16:05 +0900 Subject: printk: rename nmi.c and exported api A preparation patch for printk_safe work. No functional change. - rename nmi.c to print_safe.c - add `printk_safe' prefix to some (which used both by printk-safe and printk-nmi) of the exported functions. Link: http://lkml.kernel.org/r/20161227141611.940-3-sergey.senozhatsky@gmail.com Cc: Andrew Morton Cc: Linus Torvalds Cc: Jan Kara Cc: Tejun Heo Cc: Calvin Owens Cc: Steven Rostedt Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Peter Hurley Cc: linux-kernel@vger.kernel.org Signed-off-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- include/linux/printk.h | 12 +- init/Kconfig | 16 +-- init/main.c | 2 +- kernel/kexec_core.c | 2 +- kernel/panic.c | 4 +- kernel/printk/Makefile | 2 +- kernel/printk/nmi.c | 291 -------------------------------------------- kernel/printk/printk_safe.c | 291 ++++++++++++++++++++++++++++++++++++++++++++ lib/nmi_backtrace.c | 2 +- 9 files changed, 312 insertions(+), 310 deletions(-) delete mode 100644 kernel/printk/nmi.c create mode 100644 kernel/printk/printk_safe.c diff --git a/include/linux/printk.h b/include/linux/printk.h index 3472cc6b7a60..37e933eeffb2 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -147,17 +147,17 @@ void early_printk(const char *s, ...) { } #endif #ifdef CONFIG_PRINTK_NMI -extern void printk_nmi_init(void); +extern void printk_safe_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); +extern void printk_safe_flush(void); +extern void printk_safe_flush_on_panic(void); #else -static inline void printk_nmi_init(void) { } +static inline void printk_safe_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) { } +static inline void printk_safe_flush(void) { } +static inline void printk_safe_flush_on_panic(void) { } #endif /* PRINTK_NMI */ #ifdef CONFIG_PRINTK diff --git a/init/Kconfig b/init/Kconfig index 223b734abccd..760b7d0bc9d7 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -875,17 +875,19 @@ config LOG_CPU_MAX_BUF_SHIFT 13 => 8 KB for each CPU 12 => 4 KB for each CPU -config NMI_LOG_BUF_SHIFT - int "Temporary per-CPU NMI log buffer size (12 => 4KB, 13 => 8KB)" +config PRINTK_SAFE_LOG_BUF_SHIFT + int "Temporary per-CPU printk log buffer size (12 => 4KB, 13 => 8KB)" range 10 21 default 13 - depends on PRINTK_NMI + depends on PRINTK help - Select the size of a per-CPU buffer where NMI messages are temporary - stored. They are copied to the main log buffer in a safe context - to avoid a deadlock. The value defines the size as a power of 2. + Select the size of an alternate printk per-CPU buffer where messages + printed from usafe contexts are temporary stored. One example would + be NMI messages, another one - printk recursion. The messages are + copied to the main log buffer in a safe context to avoid a deadlock. + The value defines the size as a power of 2. - NMI messages are rare and limited. The largest one is when + Those messages are rare and limited. The largest one is when a backtrace is printed. It usually fits into 4KB. Select 8KB if you want to be on the safe side. diff --git a/init/main.c b/init/main.c index b0c9d6facef9..b4ca17d9bdeb 100644 --- a/init/main.c +++ b/init/main.c @@ -580,7 +580,7 @@ asmlinkage __visible void __init start_kernel(void) timekeeping_init(); time_init(); sched_clock_postinit(); - printk_nmi_init(); + printk_safe_init(); perf_event_init(); profile_init(); call_function_init(); diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 5617cc412444..14bb9eb76665 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -916,7 +916,7 @@ 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(); + printk_safe_flush_on_panic(); __crash_kexec(regs); /* diff --git a/kernel/panic.c b/kernel/panic.c index c51edaa04fce..8c8efcd310e7 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -188,7 +188,7 @@ void panic(const char *fmt, ...) * Bypass the panic_cpu check and call __crash_kexec directly. */ if (!_crash_kexec_post_notifiers) { - printk_nmi_flush_on_panic(); + printk_safe_flush_on_panic(); __crash_kexec(NULL); /* @@ -213,7 +213,7 @@ 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(); + printk_safe_flush_on_panic(); kmsg_dump(KMSG_DUMP_PANIC); /* diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile index abb0042a427b..607928119f26 100644 --- a/kernel/printk/Makefile +++ b/kernel/printk/Makefile @@ -1,3 +1,3 @@ obj-y = printk.o -obj-$(CONFIG_PRINTK_NMI) += nmi.o +obj-$(CONFIG_PRINTK_NMI) += printk_safe.o obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c deleted file mode 100644 index f011aaef583c..000000000000 --- a/kernel/printk/nmi.c +++ /dev/null @@ -1,291 +0,0 @@ -/* - * 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 . - */ - -#include -#include -#include -#include -#include -#include -#include - -#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; -atomic_t nmi_message_lost; - -#define NMI_LOG_BUF_LEN ((1 << CONFIG_NMI_LOG_BUF_SHIFT) - \ - 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); - - /* The trailing '\0' is not counted into len. */ - if (len >= sizeof(s->buffer) - 1) { - atomic_inc(&nmi_message_lost); - 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 = vscnprintf(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; -} - -static void printk_nmi_flush_line(const char *text, int len) -{ - /* - * 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", len, text); - else - printk("%.*s", len, text); - -} - -/* printk part of the temporary buffer line by line */ -static int printk_nmi_flush_buffer(const char *start, size_t len) -{ - const char *c, *end; - bool header; - - c = start; - end = start + len; - header = true; - - /* Print line by line. */ - while (c < end) { - if (*c == '\n') { - printk_nmi_flush_line(start, c - start + 1); - start = ++c; - header = true; - continue; - } - - /* Handle continuous lines or missing new line. */ - if ((c + 1 < end) && printk_get_level(c)) { - if (header) { - c = printk_skip_level(c); - continue; - } - - printk_nmi_flush_line(start, c - start); - start = c++; - header = true; - continue; - } - - header = false; - c++; - } - - /* Check if there was a partial line. Ignore pure header. */ - if (start < end && !header) { - static const char newline[] = KERN_CONT "\n"; - - printk_nmi_flush_line(start, end - start); - printk_nmi_flush_line(newline, strlen(newline)); - } - - return len; -} - -/* - * 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; - int 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. Also it should never overflow the - * buffer size. - */ - if ((i && i >= len) || len > sizeof(s->buffer)) { - const char *msg = "printk_nmi_flush: internal error\n"; - - printk_nmi_flush_line(msg, strlen(msg)); - len = 0; - } - - if (!len) - goto out; /* Someone else has already flushed the buffer. */ - - /* Make sure that data has been written up to the @len */ - smp_rmb(); - i += printk_nmi_flush_buffer(s->buffer + i, len - i); - - /* - * 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); -} - -/** - * 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; - - 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_safe.c b/kernel/printk/printk_safe.c new file mode 100644 index 000000000000..fc80359dcd78 --- /dev/null +++ b/kernel/printk/printk_safe.c @@ -0,0 +1,291 @@ +/* + * printk_safe.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 . + */ + +#include +#include +#include +#include +#include +#include +#include + +#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_safe_irq_ready; +atomic_t nmi_message_lost; + +#define SAFE_LOG_BUF_LEN ((1 << CONFIG_PRINTK_SAFE_LOG_BUF_SHIFT) - \ + sizeof(atomic_t) - sizeof(struct irq_work)) + +struct printk_safe_seq_buf { + atomic_t len; /* length of written data */ + struct irq_work work; /* IRQ work that flushes the buffer */ + unsigned char buffer[SAFE_LOG_BUF_LEN]; +}; +static DEFINE_PER_CPU(struct printk_safe_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 printk_safe_seq_buf *s = this_cpu_ptr(&nmi_print_seq); + int add = 0; + size_t len; + +again: + len = atomic_read(&s->len); + + /* The trailing '\0' is not counted into len. */ + if (len >= sizeof(s->buffer) - 1) { + atomic_inc(&nmi_message_lost); + 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 = vscnprintf(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_safe_irq_ready) { + /* Make sure that IRQ work is really initialized. */ + smp_rmb(); + irq_work_queue(&s->work); + } + + return add; +} + +static void printk_safe_flush_line(const char *text, int len) +{ + /* + * 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", len, text); + else + printk("%.*s", len, text); +} + +/* printk part of the temporary buffer line by line */ +static int printk_safe_flush_buffer(const char *start, size_t len) +{ + const char *c, *end; + bool header; + + c = start; + end = start + len; + header = true; + + /* Print line by line. */ + while (c < end) { + if (*c == '\n') { + printk_safe_flush_line(start, c - start + 1); + start = ++c; + header = true; + continue; + } + + /* Handle continuous lines or missing new line. */ + if ((c + 1 < end) && printk_get_level(c)) { + if (header) { + c = printk_skip_level(c); + continue; + } + + printk_safe_flush_line(start, c - start); + start = c++; + header = true; + continue; + } + + header = false; + c++; + } + + /* Check if there was a partial line. Ignore pure header. */ + if (start < end && !header) { + static const char newline[] = KERN_CONT "\n"; + + printk_safe_flush_line(start, end - start); + printk_safe_flush_line(newline, strlen(newline)); + } + + return len; +} + +/* + * Flush data from the associated per_CPU buffer. The function + * can be called either via IRQ work or independently. + */ +static void __printk_safe_flush(struct irq_work *work) +{ + static raw_spinlock_t read_lock = + __RAW_SPIN_LOCK_INITIALIZER(read_lock); + struct printk_safe_seq_buf *s = + container_of(work, struct printk_safe_seq_buf, work); + unsigned long flags; + size_t len; + int 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. Also it should never overflow the + * buffer size. + */ + if ((i && i >= len) || len > sizeof(s->buffer)) { + const char *msg = "printk_safe_flush: internal error\n"; + + printk_safe_flush_line(msg, strlen(msg)); + len = 0; + } + + if (!len) + goto out; /* Someone else has already flushed the buffer. */ + + /* Make sure that data has been written up to the @len */ + smp_rmb(); + i += printk_safe_flush_buffer(s->buffer + i, len - i); + + /* + * 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_safe_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_safe_flush(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + __printk_safe_flush(&per_cpu(nmi_print_seq, cpu).work); +} + +/** + * printk_safe_flush_on_panic - flush all per-cpu nmi buffers when the system + * goes down. + * + * Similar to printk_safe_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_safe_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_safe_flush(); +} + +void __init printk_safe_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct printk_safe_seq_buf *s = &per_cpu(nmi_print_seq, cpu); + + init_irq_work(&s->work, __printk_safe_flush); + } + + /* Make sure that IRQ works are initialized before enabling. */ + smp_wmb(); + printk_safe_irq_ready = 1; + + /* Flush pending messages that did not have scheduled IRQ works. */ + printk_safe_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/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index 75554754eadf..5f7999eacad5 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -77,7 +77,7 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, * Force flush any remote buffers that might be stuck in IRQ context * and therefore could not run their irq_work. */ - printk_nmi_flush(); + printk_safe_flush(); clear_bit_unlock(0, &backtrace_flag); put_cpu(); -- cgit