diff options
author | Andrey Konovalov <andrey.konovalov@linaro.org> | 2013-11-12 21:45:40 +0400 |
---|---|---|
committer | Andrey Konovalov <andrey.konovalov@linaro.org> | 2013-11-12 21:45:40 +0400 |
commit | f68e76fa868d731b51ebb827224d9b0f54aa7037 (patch) | |
tree | 83ebb01778647d36d19f52c35b654f6cc55264d6 /kernel | |
parent | 59ed7734412167f79f98ec58dc11f869a1db38ba (diff) | |
parent | 15c3debfd37238963933f57ac571c506a276caf1 (diff) |
Merge branch 'tracking-linaro-android-3.12' into merge-linux-linaro-core-tracking
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/cpu.c | 20 | ||||
-rw-r--r-- | kernel/debug/debug_core.c | 12 | ||||
-rw-r--r-- | kernel/debug/kdb/kdb_io.c | 12 | ||||
-rw-r--r-- | kernel/fork.c | 19 | ||||
-rw-r--r-- | kernel/irq/pm.c | 12 | ||||
-rw-r--r-- | kernel/panic.c | 13 | ||||
-rw-r--r-- | kernel/power/Kconfig | 15 | ||||
-rw-r--r-- | kernel/power/Makefile | 1 | ||||
-rw-r--r-- | kernel/power/suspend.c | 15 | ||||
-rw-r--r-- | kernel/power/suspend_time.c | 111 | ||||
-rw-r--r-- | kernel/printk.c | 2924 | ||||
-rw-r--r-- | kernel/sched/core.c | 13 | ||||
-rw-r--r-- | kernel/sys.c | 145 | ||||
-rw-r--r-- | kernel/sysctl.c | 17 | ||||
-rw-r--r-- | kernel/time/alarmtimer.c | 2 | ||||
-rw-r--r-- | kernel/trace/Kconfig | 3 | ||||
-rw-r--r-- | kernel/trace/Makefile | 1 | ||||
-rw-r--r-- | kernel/trace/gpu-traces.c | 23 | ||||
-rw-r--r-- | kernel/trace/trace.c | 104 | ||||
-rw-r--r-- | kernel/trace/trace.h | 2 | ||||
-rw-r--r-- | kernel/trace/trace_functions_graph.c | 12 | ||||
-rw-r--r-- | kernel/trace/trace_output.c | 182 | ||||
-rw-r--r-- | kernel/watchdog.c | 123 |
23 files changed, 3756 insertions, 25 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c index d7f07a2da5a6..63d5342f0f01 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -723,3 +723,23 @@ void init_cpu_online(const struct cpumask *src) { cpumask_copy(to_cpumask(cpu_online_bits), src); } + +static ATOMIC_NOTIFIER_HEAD(idle_notifier); + +void idle_notifier_register(struct notifier_block *n) +{ + atomic_notifier_chain_register(&idle_notifier, n); +} +EXPORT_SYMBOL_GPL(idle_notifier_register); + +void idle_notifier_unregister(struct notifier_block *n) +{ + atomic_notifier_chain_unregister(&idle_notifier, n); +} +EXPORT_SYMBOL_GPL(idle_notifier_unregister); + +void idle_notifier_call_chain(unsigned long val) +{ + atomic_notifier_call_chain(&idle_notifier, val, NULL); +} +EXPORT_SYMBOL_GPL(idle_notifier_call_chain); diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 0506d447aed2..2d4438b14b42 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -86,6 +86,10 @@ static int kgdb_use_con; bool dbg_is_early = true; /* Next cpu to become the master debug core */ int dbg_switch_cpu; +/* Flag for entering kdb when a panic occurs */ +static bool break_on_panic = true; +/* Flag for entering kdb when an exception occurs */ +static bool break_on_exception = true; /* Use kdb or gdbserver mode */ int dbg_kdb_mode = 1; @@ -100,6 +104,8 @@ early_param("kgdbcon", opt_kgdb_con); module_param(kgdb_use_con, int, 0644); module_param(kgdbreboot, int, 0644); +module_param(break_on_panic, bool, 0644); +module_param(break_on_exception, bool, 0644); /* * Holds information about breakpoints in a kernel. These breakpoints are @@ -678,6 +684,9 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs) if (arch_kgdb_ops.enable_nmi) arch_kgdb_ops.enable_nmi(0); + if (unlikely(signo != SIGTRAP && !break_on_exception)) + return 1; + ks->cpu = raw_smp_processor_id(); ks->ex_vector = evector; ks->signo = signo; @@ -784,6 +793,9 @@ static int kgdb_panic_event(struct notifier_block *self, unsigned long val, void *data) { + if (!break_on_panic) + return NOTIFY_DONE; + if (dbg_kdb_mode) kdb_printf("PANIC: %s\n", (char *)data); kgdb_breakpoint(); diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 14ff4849262c..4b0fb2fb779c 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -216,7 +216,7 @@ static char *kdb_read(char *buffer, size_t bufsize) int i; int diag, dtab_count; int key; - + static int last_crlf; diag = kdbgetintenv("DTABCOUNT", &dtab_count); if (diag) @@ -237,6 +237,9 @@ poll_again: return buffer; if (key != 9) tab = 0; + if (key != 10 && key != 13) + last_crlf = 0; + switch (key) { case 8: /* backspace */ if (cp > buffer) { @@ -254,7 +257,12 @@ poll_again: *cp = tmp; } break; - case 13: /* enter */ + case 10: /* new line */ + case 13: /* carriage return */ + /* handle \n after \r */ + if (last_crlf && last_crlf != key) + break; + last_crlf = key; *lastchar++ = '\n'; *lastchar++ = '\0'; if (!KDB_STATE(KGDB_TRANS)) { diff --git a/kernel/fork.c b/kernel/fork.c index 086fe73ad6bd..33da8588c898 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -198,6 +198,9 @@ struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; +/* Notifier list called when a task struct is freed */ +static ATOMIC_NOTIFIER_HEAD(task_free_notifier); + static void account_kernel_stack(struct thread_info *ti, int account) { struct zone *zone = page_zone(virt_to_page(ti)); @@ -231,6 +234,18 @@ static inline void put_signal_struct(struct signal_struct *sig) free_signal_struct(sig); } +int task_free_register(struct notifier_block *n) +{ + return atomic_notifier_chain_register(&task_free_notifier, n); +} +EXPORT_SYMBOL(task_free_register); + +int task_free_unregister(struct notifier_block *n) +{ + return atomic_notifier_chain_unregister(&task_free_notifier, n); +} +EXPORT_SYMBOL(task_free_unregister); + void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); @@ -242,6 +257,7 @@ void __put_task_struct(struct task_struct *tsk) delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); + atomic_notifier_call_chain(&task_free_notifier, 0, tsk); if (!profile_handoff_task(tsk)) free_task(tsk); } @@ -689,7 +705,8 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) mm = get_task_mm(task); if (mm && mm != current->mm && - !ptrace_may_access(task, mode)) { + !ptrace_may_access(task, mode) && + !capable(CAP_SYS_RESOURCE)) { mmput(mm); mm = ERR_PTR(-EACCES); } diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index cb228bf21760..fe4b09cf829c 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -103,14 +103,14 @@ int check_wakeup_irqs(void) int irq; for_each_irq_desc(irq, desc) { - /* - * Only interrupts which are marked as wakeup source - * and have not been disabled before the suspend check - * can abort suspend. - */ if (irqd_is_wakeup_set(&desc->irq_data)) { - if (desc->depth == 1 && desc->istate & IRQS_PENDING) + if (desc->istate & IRQS_PENDING) { + pr_info("Wakeup IRQ %d %s pending, suspend aborted\n", + irq, + desc->action && desc->action->name ? + desc->action->name : ""); return -EBUSY; + } continue; } /* diff --git a/kernel/panic.c b/kernel/panic.c index b6c482ccc5db..3efc6c1b85ca 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -27,13 +27,19 @@ #define PANIC_TIMER_STEP 100 #define PANIC_BLINK_SPD 18 +/* Machine specific panic information string */ +char *mach_panic_string; + int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE; static unsigned long tainted_mask; static int pause_on_oops; static int pause_on_oops_flag; static DEFINE_SPINLOCK(pause_on_oops_lock); -int panic_timeout; +#ifndef CONFIG_PANIC_TIMEOUT +#define CONFIG_PANIC_TIMEOUT 0 +#endif +int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); ATOMIC_NOTIFIER_HEAD(panic_notifier_list); @@ -380,6 +386,11 @@ late_initcall(init_oops_id); void print_oops_end_marker(void) { init_oops_id(); + + if (mach_panic_string) + printk(KERN_WARNING "Board Information: %s\n", + mach_panic_string); + printk(KERN_WARNING "---[ end trace %016llx ]---\n", (unsigned long long)oops_id); } diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index d444c4e834f4..461af1caa235 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -18,6 +18,14 @@ config SUSPEND_FREEZER Turning OFF this setting is NOT recommended! If in doubt, say Y. +config HAS_WAKELOCK + bool + default y + +config WAKELOCK + bool + default y + config HIBERNATE_CALLBACKS bool @@ -293,3 +301,10 @@ config PM_GENERIC_DOMAINS_RUNTIME config CPU_PM bool depends on SUSPEND || CPU_IDLE + +config SUSPEND_TIME + bool "Log time spent in suspend" + ---help--- + Prints the time spent in suspend in the kernel log, and + keeps statistics on the time spent in suspend in + /sys/kernel/debug/suspend_time diff --git a/kernel/power/Makefile b/kernel/power/Makefile index 29472bff11ef..8450b85d33c0 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -11,5 +11,6 @@ obj-$(CONFIG_HIBERNATION) += hibernate.o snapshot.o swap.o user.o \ block_io.o obj-$(CONFIG_PM_AUTOSLEEP) += autosleep.o obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o +obj-$(CONFIG_SUSPEND_TIME) += suspend_time.o obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 62ee437b5c7e..4f1e813a2a58 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -25,6 +25,7 @@ #include <linux/suspend.h> #include <linux/syscore_ops.h> #include <linux/ftrace.h> +#include <linux/rtc.h> #include <trace/events/power.h> #include "power.h" @@ -358,6 +359,18 @@ static int enter_state(suspend_state_t state) return error; } +static void pm_suspend_marker(char *annotation) +{ + struct timespec ts; + struct rtc_time tm; + + getnstimeofday(&ts); + rtc_time_to_tm(ts.tv_sec, &tm); + pr_info("PM: suspend %s %d-%02d-%02d %02d:%02d:%02d.%09lu UTC\n", + annotation, tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, + tm.tm_hour, tm.tm_min, tm.tm_sec, ts.tv_nsec); +} + /** * pm_suspend - Externally visible function for suspending the system. * @state: System sleep state to enter. @@ -372,6 +385,7 @@ int pm_suspend(suspend_state_t state) if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX) return -EINVAL; + pm_suspend_marker("entry"); error = enter_state(state); if (error) { suspend_stats.fail++; @@ -379,6 +393,7 @@ int pm_suspend(suspend_state_t state) } else { suspend_stats.success++; } + pm_suspend_marker("exit"); return error; } EXPORT_SYMBOL(pm_suspend); diff --git a/kernel/power/suspend_time.c b/kernel/power/suspend_time.c new file mode 100644 index 000000000000..d2a65da9f22c --- /dev/null +++ b/kernel/power/suspend_time.c @@ -0,0 +1,111 @@ +/* + * debugfs file to track time spent in suspend + * + * Copyright (c) 2011, Google, Inc. + * + * 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. + */ + +#include <linux/debugfs.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/seq_file.h> +#include <linux/syscore_ops.h> +#include <linux/time.h> + +static struct timespec suspend_time_before; +static unsigned int time_in_suspend_bins[32]; + +#ifdef CONFIG_DEBUG_FS +static int suspend_time_debug_show(struct seq_file *s, void *data) +{ + int bin; + seq_printf(s, "time (secs) count\n"); + seq_printf(s, "------------------\n"); + for (bin = 0; bin < 32; bin++) { + if (time_in_suspend_bins[bin] == 0) + continue; + seq_printf(s, "%4d - %4d %4u\n", + bin ? 1 << (bin - 1) : 0, 1 << bin, + time_in_suspend_bins[bin]); + } + return 0; +} + +static int suspend_time_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, suspend_time_debug_show, NULL); +} + +static const struct file_operations suspend_time_debug_fops = { + .open = suspend_time_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init suspend_time_debug_init(void) +{ + struct dentry *d; + + d = debugfs_create_file("suspend_time", 0755, NULL, NULL, + &suspend_time_debug_fops); + if (!d) { + pr_err("Failed to create suspend_time debug file\n"); + return -ENOMEM; + } + + return 0; +} + +late_initcall(suspend_time_debug_init); +#endif + +static int suspend_time_syscore_suspend(void) +{ + read_persistent_clock(&suspend_time_before); + + return 0; +} + +static void suspend_time_syscore_resume(void) +{ + struct timespec after; + + read_persistent_clock(&after); + + after = timespec_sub(after, suspend_time_before); + + time_in_suspend_bins[fls(after.tv_sec)]++; + + pr_info("Suspended for %lu.%03lu seconds\n", after.tv_sec, + after.tv_nsec / NSEC_PER_MSEC); +} + +static struct syscore_ops suspend_time_syscore_ops = { + .suspend = suspend_time_syscore_suspend, + .resume = suspend_time_syscore_resume, +}; + +static int suspend_time_syscore_init(void) +{ + register_syscore_ops(&suspend_time_syscore_ops); + + return 0; +} + +static void suspend_time_syscore_exit(void) +{ + unregister_syscore_ops(&suspend_time_syscore_ops); +} +module_init(suspend_time_syscore_init); +module_exit(suspend_time_syscore_exit); diff --git a/kernel/printk.c b/kernel/printk.c new file mode 100644 index 000000000000..8212c1aef125 --- /dev/null +++ b/kernel/printk.c @@ -0,0 +1,2924 @@ +/* + * linux/kernel/printk.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Modified to make sys_syslog() more flexible: added commands to + * return the last 4k of kernel messages, regardless of whether + * they've been read or not. Added option to suppress kernel printk's + * to the console. Added hook for sending the console messages + * elsewhere, in preparation for a serial line console (someday). + * Ted Ts'o, 2/11/93. + * Modified for sysctl support, 1/8/97, Chris Horn. + * Fixed SMP synchronization, 08/08/99, Manfred Spraul + * manfred@colorfullife.com + * Rewrote bits to get rid of console_lock + * 01Mar01 Andrew Morton + */ + +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/tty.h> +#include <linux/tty_driver.h> +#include <linux/console.h> +#include <linux/init.h> +#include <linux/jiffies.h> +#include <linux/nmi.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/interrupt.h> /* For in_interrupt() */ +#include <linux/delay.h> +#include <linux/smp.h> +#include <linux/security.h> +#include <linux/bootmem.h> +#include <linux/memblock.h> +#include <linux/aio.h> +#include <linux/syscalls.h> +#include <linux/kexec.h> +#include <linux/kdb.h> +#include <linux/ratelimit.h> +#include <linux/kmsg_dump.h> +#include <linux/syslog.h> +#include <linux/cpu.h> +#include <linux/notifier.h> +#include <linux/rculist.h> +#include <linux/poll.h> +#include <linux/irq_work.h> +#include <linux/utsname.h> + +#include <asm/uaccess.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/printk.h> + +/* printk's without a loglevel use this.. */ +#define DEFAULT_MESSAGE_LOGLEVEL CONFIG_DEFAULT_MESSAGE_LOGLEVEL + +/* We show everything that is MORE important than this.. */ +#define MINIMUM_CONSOLE_LOGLEVEL 1 /* Minimum loglevel we let people use */ +#define DEFAULT_CONSOLE_LOGLEVEL 7 /* anything MORE serious than KERN_DEBUG */ + +int console_printk[4] = { + DEFAULT_CONSOLE_LOGLEVEL, /* console_loglevel */ + DEFAULT_MESSAGE_LOGLEVEL, /* default_message_loglevel */ + MINIMUM_CONSOLE_LOGLEVEL, /* minimum_console_loglevel */ + DEFAULT_CONSOLE_LOGLEVEL, /* default_console_loglevel */ +}; + +/* + * Low level drivers may need that to know if they can schedule in + * their unblank() callback or not. So let's export it. + */ +int oops_in_progress; +EXPORT_SYMBOL(oops_in_progress); + +/* + * console_sem protects the console_drivers list, and also + * provides serialisation for access to the entire console + * driver system. + */ +static DEFINE_SEMAPHORE(console_sem); +struct console *console_drivers; +EXPORT_SYMBOL_GPL(console_drivers); + +#ifdef CONFIG_LOCKDEP +static struct lockdep_map console_lock_dep_map = { + .name = "console_lock" +}; +#endif + +/* + * This is used for debugging the mess that is the VT code by + * keeping track if we have the console semaphore held. It's + * definitely not the perfect debug tool (we don't know if _WE_ + * hold it are racing, but it helps tracking those weird code + * path in the console code where we end up in places I want + * locked without the console sempahore held + */ +static int console_locked, console_suspended; + +/* + * If exclusive_console is non-NULL then only this console is to be printed to. + */ +static struct console *exclusive_console; + +/* + * Array of consoles built from command line options (console=) + */ +struct console_cmdline +{ + char name[8]; /* Name of the driver */ + int index; /* Minor dev. to use */ + char *options; /* Options for the driver */ +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + char *brl_options; /* Options for braille driver */ +#endif +}; + +#define MAX_CMDLINECONSOLES 8 + +static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; +static int selected_console = -1; +static int preferred_console = -1; +int console_set_on_cmdline; +EXPORT_SYMBOL(console_set_on_cmdline); + +/* Flag: console code may call schedule() */ +static int console_may_schedule; + +/* + * The printk log buffer consists of a chain of concatenated variable + * length records. Every record starts with a record header, containing + * the overall length of the record. + * + * The heads to the first and last entry in the buffer, as well as the + * sequence numbers of these both entries are maintained when messages + * are stored.. + * + * If the heads indicate available messages, the length in the header + * tells the start next message. A length == 0 for the next message + * indicates a wrap-around to the beginning of the buffer. + * + * Every record carries the monotonic timestamp in microseconds, as well as + * the standard userspace syslog level and syslog facility. The usual + * kernel messages use LOG_KERN; userspace-injected messages always carry + * a matching syslog facility, by default LOG_USER. The origin of every + * message can be reliably determined that way. + * + * The human readable log message directly follows the message header. The + * length of the message text is stored in the header, the stored message + * is not terminated. + * + * Optionally, a message can carry a dictionary of properties (key/value pairs), + * to provide userspace with a machine-readable message context. + * + * Examples for well-defined, commonly used property names are: + * DEVICE=b12:8 device identifier + * b12:8 block dev_t + * c127:3 char dev_t + * n8 netdev ifindex + * +sound:card0 subsystem:devname + * SUBSYSTEM=pci driver-core subsystem name + * + * Valid characters in property names are [a-zA-Z0-9.-_]. The plain text value + * follows directly after a '=' character. Every property is terminated by + * a '\0' character. The last property is not terminated. + * + * Example of a message structure: + * 0000 ff 8f 00 00 00 00 00 00 monotonic time in nsec + * 0008 34 00 record is 52 bytes long + * 000a 0b 00 text is 11 bytes long + * 000c 1f 00 dictionary is 23 bytes long + * 000e 03 00 LOG_KERN (facility) LOG_ERR (level) + * 0010 69 74 27 73 20 61 20 6c "it's a l" + * 69 6e 65 "ine" + * 001b 44 45 56 49 43 "DEVIC" + * 45 3d 62 38 3a 32 00 44 "E=b8:2\0D" + * 52 49 56 45 52 3d 62 75 "RIVER=bu" + * 67 "g" + * 0032 00 00 00 padding to next message header + * + * The 'struct log' buffer header must never be directly exported to + * userspace, it is a kernel-private implementation detail that might + * need to be changed in the future, when the requirements change. + * + * /dev/kmsg exports the structured data in the following line format: + * "level,sequnum,timestamp;<message text>\n" + * + * The optional key/value pairs are attached as continuation lines starting + * with a space character and terminated by a newline. All possible + * non-prinatable characters are escaped in the "\xff" notation. + * + * Users of the export format should ignore possible additional values + * separated by ',', and find the message after the ';' character. + */ + +enum log_flags { + LOG_NOCONS = 1, /* already flushed, do not print to console */ + LOG_NEWLINE = 2, /* text ended with a newline */ + LOG_PREFIX = 4, /* text started with a prefix */ + LOG_CONT = 8, /* text is a fragment of a continuation line */ +}; + +struct log { + u64 ts_nsec; /* timestamp in nanoseconds */ + u16 len; /* length of entire record */ + u16 text_len; /* length of text buffer */ + u16 dict_len; /* length of dictionary buffer */ + u8 facility; /* syslog facility */ + u8 flags:5; /* internal record flags */ + u8 level:3; /* syslog level */ +}; + +/* + * The logbuf_lock protects kmsg buffer, indices, counters. It is also + * used in interesting ways to provide interlocking in console_unlock(); + */ +static DEFINE_RAW_SPINLOCK(logbuf_lock); + +#ifdef CONFIG_PRINTK +DECLARE_WAIT_QUEUE_HEAD(log_wait); +/* the next printk record to read by syslog(READ) or /proc/kmsg */ +static u64 syslog_seq; +static u32 syslog_idx; +static enum log_flags syslog_prev; +static size_t syslog_partial; + +/* index and sequence number of the first record stored in the buffer */ +static u64 log_first_seq; +static u32 log_first_idx; + +/* index and sequence number of the next record to store in the buffer */ +static u64 log_next_seq; +static u32 log_next_idx; + +/* the next printk record to write to the console */ +static u64 console_seq; +static u32 console_idx; +static enum log_flags console_prev; + +/* the next printk record to read after the last 'clear' command */ +static u64 clear_seq; +static u32 clear_idx; + +#define PREFIX_MAX 32 +#define LOG_LINE_MAX 1024 - PREFIX_MAX + +/* record buffer */ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) +#define LOG_ALIGN 4 +#else +#define LOG_ALIGN __alignof__(struct log) +#endif +#define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) +static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); +static char *log_buf = __log_buf; +static u32 log_buf_len = __LOG_BUF_LEN; + +/* cpu currently holding logbuf_lock */ +static volatile unsigned int logbuf_cpu = UINT_MAX; + +/* human readable text of the record */ +static char *log_text(const struct log *msg) +{ + return (char *)msg + sizeof(struct log); +} + +/* optional key/value pair dictionary attached to the record */ +static char *log_dict(const struct log *msg) +{ + return (char *)msg + sizeof(struct log) + msg->text_len; +} + +/* get record by index; idx must point to valid msg */ +static struct log *log_from_idx(u32 idx) +{ + struct log *msg = (struct log *)(log_buf + idx); + + /* + * A length == 0 record is the end of buffer marker. Wrap around and + * read the message at the start of the buffer. + */ + if (!msg->len) + return (struct log *)log_buf; + return msg; +} + +/* get next record; idx must point to valid msg */ +static u32 log_next(u32 idx) +{ + struct log *msg = (struct log *)(log_buf + idx); + + /* length == 0 indicates the end of the buffer; wrap */ + /* + * A length == 0 record is the end of buffer marker. Wrap around and + * read the message at the start of the buffer as *this* one, and + * return the one after that. + */ + if (!msg->len) { + msg = (struct log *)log_buf; + return msg->len; + } + return idx + msg->len; +} + +/* insert record into the buffer, discard old ones, update heads */ +static void log_store(int facility, int level, + enum log_flags flags, u64 ts_nsec, + const char *dict, u16 dict_len, + const char *text, u16 text_len) +{ + struct log *msg; + u32 size, pad_len; + + /* number of '\0' padding bytes to next message */ + size = sizeof(struct log) + text_len + dict_len; + pad_len = (-size) & (LOG_ALIGN - 1); + size += pad_len; + + while (log_first_seq < log_next_seq) { + u32 free; + + if (log_next_idx > log_first_idx) + free = max(log_buf_len - log_next_idx, log_first_idx); + else + free = log_first_idx - log_next_idx; + + if (free > size + sizeof(struct log)) + break; + + /* drop old messages until we have enough contiuous space */ + log_first_idx = log_next(log_first_idx); + log_first_seq++; + } + + if (log_next_idx + size + sizeof(struct log) >= log_buf_len) { + /* + * This message + an additional empty header does not fit + * at the end of the buffer. Add an empty header with len == 0 + * to signify a wrap around. + */ + memset(log_buf + log_next_idx, 0, sizeof(struct log)); + log_next_idx = 0; + } + + /* fill message */ + msg = (struct log *)(log_buf + log_next_idx); + memcpy(log_text(msg), text, text_len); + msg->text_len = text_len; + memcpy(log_dict(msg), dict, dict_len); + msg->dict_len = dict_len; + msg->facility = facility; + msg->level = level & 7; + msg->flags = flags & 0x1f; + if (ts_nsec > 0) + msg->ts_nsec = ts_nsec; + else + msg->ts_nsec = local_clock(); + memset(log_dict(msg) + dict_len, 0, pad_len); + msg->len = sizeof(struct log) + text_len + dict_len + pad_len; + + /* insert message */ + log_next_idx += msg->len; + log_next_seq++; +} + +#ifdef CONFIG_SECURITY_DMESG_RESTRICT +int dmesg_restrict = 1; +#else +int dmesg_restrict; +#endif + +static int syslog_action_restricted(int type) +{ + if (dmesg_restrict) + return 1; + /* + * Unless restricted, we allow "read all" and "get buffer size" + * for everybody. + */ + return type != SYSLOG_ACTION_READ_ALL && + type != SYSLOG_ACTION_SIZE_BUFFER; +} + +static int check_syslog_permissions(int type, bool from_file) +{ + /* + * If this is from /proc/kmsg and we've already opened it, then we've + * already done the capabilities checks at open time. + */ + if (from_file && type != SYSLOG_ACTION_OPEN) + return 0; + + if (syslog_action_restricted(type)) { + if (capable(CAP_SYSLOG)) + return 0; + /* + * For historical reasons, accept CAP_SYS_ADMIN too, with + * a warning. + */ + if (capable(CAP_SYS_ADMIN)) { + pr_warn_once("%s (%d): Attempt to access syslog with " + "CAP_SYS_ADMIN but no CAP_SYSLOG " + "(deprecated).\n", + current->comm, task_pid_nr(current)); + return 0; + } + return -EPERM; + } + return security_syslog(type); +} + + +/* /dev/kmsg - userspace message inject/listen interface */ +struct devkmsg_user { + u64 seq; + u32 idx; + enum log_flags prev; + struct mutex lock; + char buf[8192]; +}; + +static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) +{ + char *buf, *line; + int i; + int level = default_message_loglevel; + int facility = 1; /* LOG_USER */ + size_t len = iov_length(iv, count); + ssize_t ret = len; + + if (len > LOG_LINE_MAX) + return -EINVAL; + buf = kmalloc(len+1, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + line = buf; + for (i = 0; i < count; i++) { + if (copy_from_user(line, iv[i].iov_base, iv[i].iov_len)) { + ret = -EFAULT; + goto out; + } + line += iv[i].iov_len; + } + + /* + * Extract and skip the syslog prefix <[0-9]*>. Coming from userspace + * the decimal value represents 32bit, the lower 3 bit are the log + * level, the rest are the log facility. + * + * If no prefix or no userspace facility is specified, we + * enforce LOG_USER, to be able to reliably distinguish + * kernel-generated messages from userspace-injected ones. + */ + line = buf; + if (line[0] == '<') { + char *endp = NULL; + + i = simple_strtoul(line+1, &endp, 10); + if (endp && endp[0] == '>') { + level = i & 7; + if (i >> 3) + facility = i >> 3; + endp++; + len -= endp - line; + line = endp; + } + } + line[len] = '\0'; + + printk_emit(facility, level, NULL, 0, "%s", line); +out: + kfree(buf); + return ret; +} + +static ssize_t devkmsg_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct devkmsg_user *user = file->private_data; + struct log *msg; + u64 ts_usec; + size_t i; + char cont = '-'; + size_t len; + ssize_t ret; + + if (!user) + return -EBADF; + + ret = mutex_lock_interruptible(&user->lock); + if (ret) + return ret; + raw_spin_lock_irq(&logbuf_lock); + while (user->seq == log_next_seq) { + if (file->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + raw_spin_unlock_irq(&logbuf_lock); + goto out; + } + + raw_spin_unlock_irq(&logbuf_lock); + ret = wait_event_interruptible(log_wait, + user->seq != log_next_seq); + if (ret) + goto out; + raw_spin_lock_irq(&logbuf_lock); + } + + if (user->seq < log_first_seq) { + /* our last seen message is gone, return error and reset */ + user->idx = log_first_idx; + user->seq = log_first_seq; + ret = -EPIPE; + raw_spin_unlock_irq(&logbuf_lock); + goto out; + } + + msg = log_from_idx(user->idx); + ts_usec = msg->ts_nsec; + do_div(ts_usec, 1000); + + /* + * If we couldn't merge continuation line fragments during the print, + * export the stored flags to allow an optional external merge of the + * records. Merging the records isn't always neccessarily correct, like + * when we hit a race during printing. In most cases though, it produces + * better readable output. 'c' in the record flags mark the first + * fragment of a line, '+' the following. + */ + if (msg->flags & LOG_CONT && !(user->prev & LOG_CONT)) + cont = 'c'; + else if ((msg->flags & LOG_CONT) || + ((user->prev & LOG_CONT) && !(msg->flags & LOG_PREFIX))) + cont = '+'; + + len = sprintf(user->buf, "%u,%llu,%llu,%c;", + (msg->facility << 3) | msg->level, + user->seq, ts_usec, cont); + user->prev = msg->flags; + + /* escape non-printable characters */ + for (i = 0; i < msg->text_len; i++) { + unsigned char c = log_text(msg)[i]; + + if (c < ' ' || c >= 127 || c == '\\') + len += sprintf(user->buf + len, "\\x%02x", c); + else + user->buf[len++] = c; + } + user->buf[len++] = '\n'; + + if (msg->dict_len) { + bool line = true; + + for (i = 0; i < msg->dict_len; i++) { + unsigned char c = log_dict(msg)[i]; + + if (line) { + user->buf[len++] = ' '; + line = false; + } + + if (c == '\0') { + user->buf[len++] = '\n'; + line = true; + continue; + } + + if (c < ' ' || c >= 127 || c == '\\') { + len += sprintf(user->buf + len, "\\x%02x", c); + continue; + } + + user->buf[len++] = c; + } + user->buf[len++] = '\n'; + } + + user->idx = log_next(user->idx); + user->seq++; + raw_spin_unlock_irq(&logbuf_lock); + + if (len > count) { + ret = -EINVAL; + goto out; + } + + if (copy_to_user(buf, user->buf, len)) { + ret = -EFAULT; + goto out; + } + ret = len; +out: + mutex_unlock(&user->lock); + return ret; +} + +static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) +{ + struct devkmsg_user *user = file->private_data; + loff_t ret = 0; + + if (!user) + return -EBADF; + if (offset) + return -ESPIPE; + + raw_spin_lock_irq(&logbuf_lock); + switch (whence) { + case SEEK_SET: + /* the first record */ + user->idx = log_first_idx; + user->seq = log_first_seq; + break; + case SEEK_DATA: + /* + * The first record after the last SYSLOG_ACTION_CLEAR, + * like issued by 'dmesg -c'. Reading /dev/kmsg itself + * changes no global state, and does not clear anything. + */ + user->idx = clear_idx; + user->seq = clear_seq; + break; + case SEEK_END: + /* after the last record */ + user->idx = log_next_idx; + user->seq = log_next_seq; + break; + default: + ret = -EINVAL; + } + raw_spin_unlock_irq(&logbuf_lock); + return ret; +} + +static unsigned int devkmsg_poll(struct file *file, poll_table *wait) +{ + struct devkmsg_user *user = file->private_data; + int ret = 0; + + if (!user) + return POLLERR|POLLNVAL; + + poll_wait(file, &log_wait, wait); + + raw_spin_lock_irq(&logbuf_lock); + if (user->seq < log_next_seq) { + /* return error when data has vanished underneath us */ + if (user->seq < log_first_seq) + ret = POLLIN|POLLRDNORM|POLLERR|POLLPRI; + else + ret = POLLIN|POLLRDNORM; + } + raw_spin_unlock_irq(&logbuf_lock); + + return ret; +} + +static int devkmsg_open(struct inode *inode, struct file *file) +{ + struct devkmsg_user *user; + int err; + + /* write-only does not need any file context */ + if ((file->f_flags & O_ACCMODE) == O_WRONLY) + return 0; + + err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, + SYSLOG_FROM_READER); + if (err) + return err; + + user = kmalloc(sizeof(struct devkmsg_user), GFP_KERNEL); + if (!user) + return -ENOMEM; + + mutex_init(&user->lock); + + raw_spin_lock_irq(&logbuf_lock); + user->idx = log_first_idx; + user->seq = log_first_seq; + raw_spin_unlock_irq(&logbuf_lock); + + file->private_data = user; + return 0; +} + +static int devkmsg_release(struct inode *inode, struct file *file) +{ + struct devkmsg_user *user = file->private_data; + + if (!user) + return 0; + + mutex_destroy(&user->lock); + kfree(user); + return 0; +} + +const struct file_operations kmsg_fops = { + .open = devkmsg_open, + .read = devkmsg_read, + .aio_write = devkmsg_writev, + .llseek = devkmsg_llseek, + .poll = devkmsg_poll, + .release = devkmsg_release, +}; + +#ifdef CONFIG_KEXEC +/* + * This appends the listed symbols to /proc/vmcoreinfo + * + * /proc/vmcoreinfo is used by various utiilties, like crash and makedumpfile to + * obtain access to symbols that are otherwise very difficult to locate. These + * symbols are specifically used so that utilities can access and extract the + * dmesg log from a vmcore file after a crash. + */ +void log_buf_kexec_setup(void) +{ + VMCOREINFO_SYMBOL(log_buf); + VMCOREINFO_SYMBOL(log_buf_len); + VMCOREINFO_SYMBOL(log_first_idx); + VMCOREINFO_SYMBOL(log_next_idx); + /* + * Export struct log size and field offsets. User space tools can + * parse it and detect any changes to structure down the line. + */ + VMCOREINFO_STRUCT_SIZE(log); + VMCOREINFO_OFFSET(log, ts_nsec); + VMCOREINFO_OFFSET(log, len); + VMCOREINFO_OFFSET(log, text_len); + VMCOREINFO_OFFSET(log, dict_len); +} +#endif + +/* requested log_buf_len from kernel cmdline */ +static unsigned long __initdata new_log_buf_len; + +/* save requested log_buf_len since it's too early to process it */ +static int __init log_buf_len_setup(char *str) +{ + unsigned size = memparse(str, &str); + + if (size) + size = roundup_pow_of_two(size); + if (size > log_buf_len) + new_log_buf_len = size; + + return 0; +} +early_param("log_buf_len", log_buf_len_setup); + +void __init setup_log_buf(int early) +{ + unsigned long flags; + char *new_log_buf; + int free; + + if (!new_log_buf_len) + return; + + if (early) { + unsigned long mem; + + mem = memblock_alloc(new_log_buf_len, PAGE_SIZE); + if (!mem) + return; + new_log_buf = __va(mem); + } else { + new_log_buf = alloc_bootmem_nopanic(new_log_buf_len); + } + + if (unlikely(!new_log_buf)) { + pr_err("log_buf_len: %ld bytes not available\n", + new_log_buf_len); + return; + } + + raw_spin_lock_irqsave(&logbuf_lock, flags); + log_buf_len = new_log_buf_len; + log_buf = new_log_buf; + new_log_buf_len = 0; + free = __LOG_BUF_LEN - log_next_idx; + memcpy(log_buf, __log_buf, __LOG_BUF_LEN); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + pr_info("log_buf_len: %d\n", log_buf_len); + pr_info("early log buf free: %d(%d%%)\n", + free, (free * 100) / __LOG_BUF_LEN); +} + +static bool __read_mostly ignore_loglevel; + +static int __init ignore_loglevel_setup(char *str) +{ + ignore_loglevel = 1; + printk(KERN_INFO "debug: ignoring loglevel setting.\n"); + + return 0; +} + +early_param("ignore_loglevel", ignore_loglevel_setup); +module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to" + "print all kernel messages to the console."); + +#ifdef CONFIG_BOOT_PRINTK_DELAY + +static int boot_delay; /* msecs delay after each printk during bootup */ +static unsigned long long loops_per_msec; /* based on boot_delay */ + +static int __init boot_delay_setup(char *str) +{ + unsigned long lpj; + + lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */ + loops_per_msec = (unsigned long long)lpj / 1000 * HZ; + + get_option(&str, &boot_delay); + if (boot_delay > 10 * 1000) + boot_delay = 0; + + pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, " + "HZ: %d, loops_per_msec: %llu\n", + boot_delay, preset_lpj, lpj, HZ, loops_per_msec); + return 1; +} +__setup("boot_delay=", boot_delay_setup); + +static void boot_delay_msec(int level) +{ + unsigned long long k; + unsigned long timeout; + + if ((boot_delay == 0 || system_state != SYSTEM_BOOTING) + || (level >= console_loglevel && !ignore_loglevel)) { + return; + } + + k = (unsigned long long)loops_per_msec * boot_delay; + + timeout = jiffies + msecs_to_jiffies(boot_delay); + while (k) { + k--; + cpu_relax(); + /* + * use (volatile) jiffies to prevent + * compiler reduction; loop termination via jiffies + * is secondary and may or may not happen. + */ + if (time_after(jiffies, timeout)) + break; + touch_nmi_watchdog(); + } +} +#else +static inline void boot_delay_msec(int level) +{ +} +#endif + +#if defined(CONFIG_PRINTK_TIME) +static bool printk_time = 1; +#else +static bool printk_time; +#endif +module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); + +static size_t print_time(u64 ts, char *buf) +{ + unsigned long rem_nsec; + + if (!printk_time) + return 0; + + rem_nsec = do_div(ts, 1000000000); + + if (!buf) + return snprintf(NULL, 0, "[%5lu.000000] ", (unsigned long)ts); + + return sprintf(buf, "[%5lu.%06lu] ", + (unsigned long)ts, rem_nsec / 1000); +} + +static size_t print_prefix(const struct log *msg, bool syslog, char *buf) +{ + size_t len = 0; + unsigned int prefix = (msg->facility << 3) | msg->level; + + if (syslog) { + if (buf) { + len += sprintf(buf, "<%u>", prefix); + } else { + len += 3; + if (prefix > 999) + len += 3; + else if (prefix > 99) + len += 2; + else if (prefix > 9) + len++; + } + } + + len += print_time(msg->ts_nsec, buf ? buf + len : NULL); + return len; +} + +static size_t msg_print_text(const struct log *msg, enum log_flags prev, + bool syslog, char *buf, size_t size) +{ + const char *text = log_text(msg); + size_t text_size = msg->text_len; + bool prefix = true; + bool newline = true; + size_t len = 0; + + if ((prev & LOG_CONT) && !(msg->flags & LOG_PREFIX)) + prefix = false; + + if (msg->flags & LOG_CONT) { + if ((prev & LOG_CONT) && !(prev & LOG_NEWLINE)) + prefix = false; + + if (!(msg->flags & LOG_NEWLINE)) + newline = false; + } + + do { + const char *next = memchr(text, '\n', text_size); + size_t text_len; + + if (next) { + text_len = next - text; + next++; + text_size -= next - text; + } else { + text_len = text_size; + } + + if (buf) { + if (print_prefix(msg, syslog, NULL) + + text_len + 1 >= size - len) + break; + + if (prefix) + len += print_prefix(msg, syslog, buf + len); + memcpy(buf + len, text, text_len); + len += text_len; + if (next || newline) + buf[len++] = '\n'; + } else { + /* SYSLOG_ACTION_* buffer size only calculation */ + if (prefix) + len += print_prefix(msg, syslog, NULL); + len += text_len; + if (next || newline) + len++; + } + + prefix = true; + text = next; + } while (text); + + return len; +} + +static int syslog_print(char __user *buf, int size) +{ + char *text; + struct log *msg; + int len = 0; + + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + if (!text) + return -ENOMEM; + + while (size > 0) { + size_t n; + size_t skip; + + raw_spin_lock_irq(&logbuf_lock); + if (syslog_seq < log_first_seq) { + /* messages are gone, move to first one */ + syslog_seq = log_first_seq; + syslog_idx = log_first_idx; + syslog_prev = 0; + syslog_partial = 0; + } + if (syslog_seq == log_next_seq) { + raw_spin_unlock_irq(&logbuf_lock); + break; + } + + skip = syslog_partial; + msg = log_from_idx(syslog_idx); + n = msg_print_text(msg, syslog_prev, true, text, + LOG_LINE_MAX + PREFIX_MAX); + if (n - syslog_partial <= size) { + /* message fits into buffer, move forward */ + syslog_idx = log_next(syslog_idx); + syslog_seq++; + syslog_prev = msg->flags; + n -= syslog_partial; + syslog_partial = 0; + } else if (!len){ + /* partial read(), remember position */ + n = size; + syslog_partial += n; + } else + n = 0; + raw_spin_unlock_irq(&logbuf_lock); + + if (!n) + break; + + if (copy_to_user(buf, text + skip, n)) { + if (!len) + len = -EFAULT; + break; + } + + len += n; + size -= n; + buf += n; + } + + kfree(text); + return len; +} + +static int syslog_print_all(char __user *buf, int size, bool clear) +{ + char *text; + int len = 0; + + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + if (!text) + return -ENOMEM; + + raw_spin_lock_irq(&logbuf_lock); + if (buf) { + u64 next_seq; + u64 seq; + u32 idx; + enum log_flags prev; + + if (clear_seq < log_first_seq) { + /* messages are gone, move to first available one */ + clear_seq = log_first_seq; + clear_idx = log_first_idx; + } + + /* + * Find first record that fits, including all following records, + * into the user-provided buffer for this dump. + */ + seq = clear_seq; + idx = clear_idx; + prev = 0; + while (seq < log_next_seq) { + struct log *msg = log_from_idx(idx); + + len += msg_print_text(msg, prev, true, NULL, 0); + prev = msg->flags; + idx = log_next(idx); + seq++; + } + + /* move first record forward until length fits into the buffer */ + seq = clear_seq; + idx = clear_idx; + prev = 0; + while (len > size && seq < log_next_seq) { + struct log *msg = log_from_idx(idx); + + len -= msg_print_text(msg, prev, true, NULL, 0); + prev = msg->flags; + idx = log_next(idx); + seq++; + } + + /* last message fitting into this dump */ + next_seq = log_next_seq; + + len = 0; + prev = 0; + while (len >= 0 && seq < next_seq) { + struct log *msg = log_from_idx(idx); + int textlen; + + textlen = msg_print_text(msg, prev, true, text, + LOG_LINE_MAX + PREFIX_MAX); + if (textlen < 0) { + len = textlen; + break; + } + idx = log_next(idx); + seq++; + prev = msg->flags; + + raw_spin_unlock_irq(&logbuf_lock); + if (copy_to_user(buf + len, text, textlen)) + len = -EFAULT; + else + len += textlen; + raw_spin_lock_irq(&logbuf_lock); + + if (seq < log_first_seq) { + /* messages are gone, move to next one */ + seq = log_first_seq; + idx = log_first_idx; + prev = 0; + } + } + } + + if (clear) { + clear_seq = log_next_seq; + clear_idx = log_next_idx; + } + raw_spin_unlock_irq(&logbuf_lock); + + kfree(text); + return len; +} + +int do_syslog(int type, char __user *buf, int len, bool from_file) +{ + bool clear = false; + static int saved_console_loglevel = -1; + int error; + + error = check_syslog_permissions(type, from_file); + if (error) + goto out; + + error = security_syslog(type); + if (error) + return error; + + switch (type) { + case SYSLOG_ACTION_CLOSE: /* Close log */ + break; + case SYSLOG_ACTION_OPEN: /* Open log */ + break; + case SYSLOG_ACTION_READ: /* Read from log */ + error = -EINVAL; + if (!buf || len < 0) + goto out; + error = 0; + if (!len) + goto out; + if (!access_ok(VERIFY_WRITE, buf, len)) { + error = -EFAULT; + goto out; + } + error = wait_event_interruptible(log_wait, + syslog_seq != log_next_seq); + if (error) + goto out; + error = syslog_print(buf, len); + break; + /* Read/clear last kernel messages */ + case SYSLOG_ACTION_READ_CLEAR: + clear = true; + /* FALL THRU */ + /* Read last kernel messages */ + case SYSLOG_ACTION_READ_ALL: + error = -EINVAL; + if (!buf || len < 0) + goto out; + error = 0; + if (!len) + goto out; + if (!access_ok(VERIFY_WRITE, buf, len)) { + error = -EFAULT; + goto out; + } + error = syslog_print_all(buf, len, clear); + break; + /* Clear ring buffer */ + case SYSLOG_ACTION_CLEAR: + syslog_print_all(NULL, 0, true); + break; + /* Disable logging to console */ + case SYSLOG_ACTION_CONSOLE_OFF: + if (saved_console_loglevel == -1) + saved_console_loglevel = console_loglevel; + console_loglevel = minimum_console_loglevel; + break; + /* Enable logging to console */ + case SYSLOG_ACTION_CONSOLE_ON: + if (saved_console_loglevel != -1) { + console_loglevel = saved_console_loglevel; + saved_console_loglevel = -1; + } + break; + /* Set level of messages printed to console */ + case SYSLOG_ACTION_CONSOLE_LEVEL: + error = -EINVAL; + if (len < 1 || len > 8) + goto out; + if (len < minimum_console_loglevel) + len = minimum_console_loglevel; + console_loglevel = len; + /* Implicitly re-enable logging to console */ + saved_console_loglevel = -1; + error = 0; + break; + /* Number of chars in the log buffer */ + case SYSLOG_ACTION_SIZE_UNREAD: + raw_spin_lock_irq(&logbuf_lock); + if (syslog_seq < log_first_seq) { + /* messages are gone, move to first one */ + syslog_seq = log_first_seq; + syslog_idx = log_first_idx; + syslog_prev = 0; + syslog_partial = 0; + } + if (from_file) { + /* + * Short-cut for poll(/"proc/kmsg") which simply checks + * for pending data, not the size; return the count of + * records, not the length. + */ + error = log_next_idx - syslog_idx; + } else { + u64 seq = syslog_seq; + u32 idx = syslog_idx; + enum log_flags prev = syslog_prev; + + error = 0; + while (seq < log_next_seq) { + struct log *msg = log_from_idx(idx); + + error += msg_print_text(msg, prev, true, NULL, 0); + idx = log_next(idx); + seq++; + prev = msg->flags; + } + error -= syslog_partial; + } + raw_spin_unlock_irq(&logbuf_lock); + break; + /* Size of the log buffer */ + case SYSLOG_ACTION_SIZE_BUFFER: + error = log_buf_len; + break; + default: + error = -EINVAL; + break; + } +out: + return error; +} + +SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) +{ + return do_syslog(type, buf, len, SYSLOG_FROM_READER); +} + +/* + * Call the console drivers, asking them to write out + * log_buf[start] to log_buf[end - 1]. + * The console_lock must be held. + */ +static void call_console_drivers(int level, const char *text, size_t len) +{ + struct console *con; + + trace_console(text, len); + + if (level >= console_loglevel && !ignore_loglevel) + return; + if (!console_drivers) + return; + + for_each_console(con) { + if (exclusive_console && con != exclusive_console) + continue; + if (!(con->flags & CON_ENABLED)) + continue; + if (!con->write) + continue; + if (!cpu_online(smp_processor_id()) && + !(con->flags & CON_ANYTIME)) + continue; + con->write(con, text, len); + } +} + +/* + * Zap console related locks when oopsing. Only zap at most once + * every 10 seconds, to leave time for slow consoles to print a + * full oops. + */ +static void zap_locks(void) +{ + static unsigned long oops_timestamp; + + if (time_after_eq(jiffies, oops_timestamp) && + !time_after(jiffies, oops_timestamp + 30 * HZ)) + return; + + oops_timestamp = jiffies; + + debug_locks_off(); + /* If a crash is occurring, make sure we can't deadlock */ + raw_spin_lock_init(&logbuf_lock); + /* And make sure that we print immediately */ + sema_init(&console_sem, 1); +} + +/* Check if we have any console registered that can be called early in boot. */ +static int have_callable_console(void) +{ + struct console *con; + + for_each_console(con) + if (con->flags & CON_ANYTIME) + return 1; + + return 0; +} + +/* + * Can we actually use the console at this time on this cpu? + * + * Console drivers may assume that per-cpu resources have + * been allocated. So unless they're explicitly marked as + * being able to cope (CON_ANYTIME) don't call them until + * this CPU is officially up. + */ +static inline int can_use_console(unsigned int cpu) +{ + return cpu_online(cpu) || have_callable_console(); +} + +/* + * Try to get console ownership to actually show the kernel + * messages from a 'printk'. Return true (and with the + * console_lock held, and 'console_locked' set) if it + * is successful, false otherwise. + * + * This gets called with the 'logbuf_lock' spinlock held and + * interrupts disabled. It should return with 'lockbuf_lock' + * released but interrupts still disabled. + */ +static int console_trylock_for_printk(unsigned int cpu) + __releases(&logbuf_lock) +{ + int retval = 0, wake = 0; + + if (console_trylock()) { + retval = 1; + + /* + * If we can't use the console, we need to release + * the console semaphore by hand to avoid flushing + * the buffer. We need to hold the console semaphore + * in order to do this test safely. + */ + if (!can_use_console(cpu)) { + console_locked = 0; + wake = 1; + retval = 0; + } + } + logbuf_cpu = UINT_MAX; + if (wake) + up(&console_sem); + raw_spin_unlock(&logbuf_lock); + return retval; +} + +int printk_delay_msec __read_mostly; + +static inline void printk_delay(void) +{ + if (unlikely(printk_delay_msec)) { + int m = printk_delay_msec; + + while (m--) { + mdelay(1); + touch_nmi_watchdog(); + } + } +} + +/* + * Continuation lines are buffered, and not committed to the record buffer + * until the line is complete, or a race forces it. The line fragments + * though, are printed immediately to the consoles to ensure everything has + * reached the console in case of a kernel crash. + */ +static struct cont { + char buf[LOG_LINE_MAX]; + size_t len; /* length == 0 means unused buffer */ + size_t cons; /* bytes written to console */ + struct task_struct *owner; /* task of first print*/ + u64 ts_nsec; /* time of first print */ + u8 level; /* log level of first message */ + u8 facility; /* log level of first message */ + enum log_flags flags; /* prefix, newline flags */ + bool flushed:1; /* buffer sealed and committed */ +} cont; + +static void cont_flush(enum log_flags flags) +{ + if (cont.flushed) + return; + if (cont.len == 0) + return; + + if (cont.cons) { + /* + * If a fragment of this line was directly flushed to the + * console; wait for the console to pick up the rest of the + * line. LOG_NOCONS suppresses a duplicated output. + */ + log_store(cont.facility, cont.level, flags | LOG_NOCONS, + cont.ts_nsec, NULL, 0, cont.buf, cont.len); + cont.flags = flags; + cont.flushed = true; + } else { + /* + * If no fragment of this line ever reached the console, + * just submit it to the store and free the buffer. + */ + log_store(cont.facility, cont.level, flags, 0, + NULL, 0, cont.buf, cont.len); + cont.len = 0; + } +} + +static bool cont_add(int facility, int level, const char *text, size_t len) +{ + if (cont.len && cont.flushed) + return false; + + if (cont.len + len > sizeof(cont.buf)) { + /* the line gets too long, split it up in separate records */ + cont_flush(LOG_CONT); + return false; + } + + if (!cont.len) { + cont.facility = facility; + cont.level = level; + cont.owner = current; + cont.ts_nsec = local_clock(); + cont.flags = 0; + cont.cons = 0; + cont.flushed = false; + } + + memcpy(cont.buf + cont.len, text, len); + cont.len += len; + + if (cont.len > (sizeof(cont.buf) * 80) / 100) + cont_flush(LOG_CONT); + + return true; +} + +static size_t cont_print_text(char *text, size_t size) +{ + size_t textlen = 0; + size_t len; + + if (cont.cons == 0 && (console_prev & LOG_NEWLINE)) { + textlen += print_time(cont.ts_nsec, text); + size -= textlen; + } + + len = cont.len - cont.cons; + if (len > 0) { + if (len+1 > size) + len = size-1; + memcpy(text + textlen, cont.buf + cont.cons, len); + textlen += len; + cont.cons = cont.len; + } + + if (cont.flushed) { + if (cont.flags & LOG_NEWLINE) + text[textlen++] = '\n'; + /* got everything, release buffer */ + cont.len = 0; + } + return textlen; +} + +asmlinkage int vprintk_emit(int facility, int level, + const char *dict, size_t dictlen, + const char *fmt, va_list args) +{ + static int recursion_bug; + static char textbuf[LOG_LINE_MAX]; + char *text = textbuf; + size_t text_len; + enum log_flags lflags = 0; + unsigned long flags; + int this_cpu; + int printed_len = 0; + + boot_delay_msec(level); + printk_delay(); + + /* This stops the holder of console_sem just where we want him */ + local_irq_save(flags); + this_cpu = smp_processor_id(); + + /* + * Ouch, printk recursed into itself! + */ + if (unlikely(logbuf_cpu == this_cpu)) { + /* + * If a crash is occurring during printk() on this CPU, + * then try to get the crash message out but make sure + * we can't deadlock. Otherwise just return to avoid the + * recursion and return - but flag the recursion so that + * it can be printed at the next appropriate moment: + */ + if (!oops_in_progress && !lockdep_recursing(current)) { + recursion_bug = 1; + goto out_restore_irqs; + } + zap_locks(); + } + + lockdep_off(); + raw_spin_lock(&logbuf_lock); + logbuf_cpu = this_cpu; + + if (recursion_bug) { + static const char recursion_msg[] = + "BUG: recent printk recursion!"; + + recursion_bug = 0; + printed_len += strlen(recursion_msg); + /* emit KERN_CRIT message */ + log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0, + NULL, 0, recursion_msg, printed_len); + } + + /* + * The printf needs to come first; we need the syslog + * prefix which might be passed-in as a parameter. + */ + text_len = vscnprintf(text, sizeof(textbuf), fmt, args); + + /* mark and strip a trailing newline */ + if (text_len && text[text_len-1] == '\n') { + text_len--; + lflags |= LOG_NEWLINE; + } + + /* strip kernel syslog prefix and extract log level or control flags */ + if (facility == 0) { + int kern_level = printk_get_level(text); + + if (kern_level) { + const char *end_of_header = printk_skip_level(text); + switch (kern_level) { + case '0' ... '7': + if (level == -1) + level = kern_level - '0'; + case 'd': /* KERN_DEFAULT */ + lflags |= LOG_PREFIX; + case 'c': /* KERN_CONT */ + break; + } + text_len -= end_of_header - text; + text = (char *)end_of_header; + } + } + + if (level == -1) + level = default_message_loglevel; + + if (dict) + lflags |= LOG_PREFIX|LOG_NEWLINE; + + if (!(lflags & LOG_NEWLINE)) { + /* + * Flush the conflicting buffer. An earlier newline was missing, + * or another task also prints continuation lines. + */ + if (cont.len && (lflags & LOG_PREFIX || cont.owner != current)) + cont_flush(LOG_NEWLINE); + + /* buffer line if possible, otherwise store it right away */ + if (!cont_add(facility, level, text, text_len)) + log_store(facility, level, lflags | LOG_CONT, 0, + dict, dictlen, text, text_len); + } else { + bool stored = false; + + /* + * If an earlier newline was missing and it was the same task, + * either merge it with the current buffer and flush, or if + * there was a race with interrupts (prefix == true) then just + * flush it out and store this line separately. + */ + if (cont.len && cont.owner == current) { + if (!(lflags & LOG_PREFIX)) + stored = cont_add(facility, level, text, text_len); + cont_flush(LOG_NEWLINE); + } + + if (!stored) + log_store(facility, level, lflags, 0, + dict, dictlen, text, text_len); + } + printed_len += text_len; + + /* + * Try to acquire and then immediately release the console semaphore. + * The release will print out buffers and wake up /dev/kmsg and syslog() + * users. + * + * The console_trylock_for_printk() function will release 'logbuf_lock' + * regardless of whether it actually gets the console semaphore or not. + */ + if (console_trylock_for_printk(this_cpu)) + console_unlock(); + + lockdep_on(); +out_restore_irqs: + local_irq_restore(flags); + + return printed_len; +} +EXPORT_SYMBOL(vprintk_emit); + +asmlinkage int vprintk(const char *fmt, va_list args) +{ + return vprintk_emit(0, -1, NULL, 0, fmt, args); +} +EXPORT_SYMBOL(vprintk); + +asmlinkage int printk_emit(int facility, int level, + const char *dict, size_t dictlen, + const char *fmt, ...) +{ + va_list args; + int r; + + va_start(args, fmt); + r = vprintk_emit(facility, level, dict, dictlen, fmt, args); + va_end(args); + + return r; +} +EXPORT_SYMBOL(printk_emit); + +/** + * printk - print a kernel message + * @fmt: format string + * + * This is printk(). It can be called from any context. We want it to work. + * + * We try to grab the console_lock. If we succeed, it's easy - we log the + * output and call the console drivers. If we fail to get the semaphore, we + * place the output into the log buffer and return. The current holder of + * the console_sem will notice the new output in console_unlock(); and will + * send it to the consoles before releasing the lock. + * + * One effect of this deferred printing is that code which calls printk() and + * then changes console_loglevel may break. This is because console_loglevel + * is inspected when the actual printing occurs. + * + * See also: + * printf(3) + * + * See the vsnprintf() documentation for format string extensions over C99. + */ +asmlinkage int printk(const char *fmt, ...) +{ + va_list args; + int r; + +#ifdef CONFIG_KGDB_KDB + if (unlikely(kdb_trap_printk)) { + va_start(args, fmt); + r = vkdb_printf(fmt, args); + va_end(args); + return r; + } +#endif + va_start(args, fmt); + r = vprintk_emit(0, -1, NULL, 0, fmt, args); + va_end(args); + + return r; +} +EXPORT_SYMBOL(printk); + +#else /* CONFIG_PRINTK */ + +#define LOG_LINE_MAX 0 +#define PREFIX_MAX 0 +#define LOG_LINE_MAX 0 +static u64 syslog_seq; +static u32 syslog_idx; +static u64 console_seq; +static u32 console_idx; +static enum log_flags syslog_prev; +static u64 log_first_seq; +static u32 log_first_idx; +static u64 log_next_seq; +static enum log_flags console_prev; +static struct cont { + size_t len; + size_t cons; + u8 level; + bool flushed:1; +} cont; +static struct log *log_from_idx(u32 idx) { return NULL; } +static u32 log_next(u32 idx) { return 0; } +static void call_console_drivers(int level, const char *text, size_t len) {} +static size_t msg_print_text(const struct log *msg, enum log_flags prev, + bool syslog, char *buf, size_t size) { return 0; } +static size_t cont_print_text(char *text, size_t size) { return 0; } + +#endif /* CONFIG_PRINTK */ + +#ifdef CONFIG_EARLY_PRINTK +struct console *early_console; + +void early_vprintk(const char *fmt, va_list ap) +{ + if (early_console) { + char buf[512]; + int n = vscnprintf(buf, sizeof(buf), fmt, ap); + + early_console->write(early_console, buf, n); + } +} + +asmlinkage void early_printk(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + early_vprintk(fmt, ap); + va_end(ap); +} +#endif + +static int __add_preferred_console(char *name, int idx, char *options, + char *brl_options) +{ + struct console_cmdline *c; + int i; + + /* + * See if this tty is not yet registered, and + * if we have a slot free. + */ + for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0]; i++) + if (strcmp(console_cmdline[i].name, name) == 0 && + console_cmdline[i].index == idx) { + if (!brl_options) + selected_console = i; + return 0; + } + if (i == MAX_CMDLINECONSOLES) + return -E2BIG; + if (!brl_options) + selected_console = i; + c = &console_cmdline[i]; + strlcpy(c->name, name, sizeof(c->name)); + c->options = options; +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + c->brl_options = brl_options; +#endif + c->index = idx; + return 0; +} +/* + * Set up a list of consoles. Called from init/main.c + */ +static int __init console_setup(char *str) +{ + char buf[sizeof(console_cmdline[0].name) + 4]; /* 4 for index */ + char *s, *options, *brl_options = NULL; + int idx; + +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + if (!memcmp(str, "brl,", 4)) { + brl_options = ""; + str += 4; + } else if (!memcmp(str, "brl=", 4)) { + brl_options = str + 4; + str = strchr(brl_options, ','); + if (!str) { + printk(KERN_ERR "need port name after brl=\n"); + return 1; + } + *(str++) = 0; + } +#endif + + /* + * Decode str into name, index, options. + */ + if (str[0] >= '0' && str[0] <= '9') { + strcpy(buf, "ttyS"); + strncpy(buf + 4, str, sizeof(buf) - 5); + } else { + strncpy(buf, str, sizeof(buf) - 1); + } + buf[sizeof(buf) - 1] = 0; + if ((options = strchr(str, ',')) != NULL) + *(options++) = 0; +#ifdef __sparc__ + if (!strcmp(str, "ttya")) + strcpy(buf, "ttyS0"); + if (!strcmp(str, "ttyb")) + strcpy(buf, "ttyS1"); +#endif + for (s = buf; *s; s++) + if ((*s >= '0' && *s <= '9') || *s == ',') + break; + idx = simple_strtoul(s, NULL, 10); + *s = 0; + + __add_preferred_console(buf, idx, options, brl_options); + console_set_on_cmdline = 1; + return 1; +} +__setup("console=", console_setup); + +/** + * add_preferred_console - add a device to the list of preferred consoles. + * @name: device name + * @idx: device index + * @options: options for this console + * + * The last preferred console added will be used for kernel messages + * and stdin/out/err for init. Normally this is used by console_setup + * above to handle user-supplied console arguments; however it can also + * be used by arch-specific code either to override the user or more + * commonly to provide a default console (ie from PROM variables) when + * the user has not supplied one. + */ +int add_preferred_console(char *name, int idx, char *options) +{ + return __add_preferred_console(name, idx, options, NULL); +} + +int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, char *options) +{ + struct console_cmdline *c; + int i; + + for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0]; i++) + if (strcmp(console_cmdline[i].name, name) == 0 && + console_cmdline[i].index == idx) { + c = &console_cmdline[i]; + strlcpy(c->name, name_new, sizeof(c->name)); + c->name[sizeof(c->name) - 1] = 0; + c->options = options; + c->index = idx_new; + return i; + } + /* not found */ + return -1; +} + +bool console_suspend_enabled = 1; +EXPORT_SYMBOL(console_suspend_enabled); + +static int __init console_suspend_disable(char *str) +{ + console_suspend_enabled = 0; + return 1; +} +__setup("no_console_suspend", console_suspend_disable); +module_param_named(console_suspend, console_suspend_enabled, + bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(console_suspend, "suspend console during suspend" + " and hibernate operations"); + +/** + * suspend_console - suspend the console subsystem + * + * This disables printk() while we go into suspend states + */ +void suspend_console(void) +{ + if (!console_suspend_enabled) + return; + printk("Suspending console(s) (use no_console_suspend to debug)\n"); + console_lock(); + console_suspended = 1; + up(&console_sem); +} + +void resume_console(void) +{ + if (!console_suspend_enabled) + return; + down(&console_sem); + console_suspended = 0; + console_unlock(); +} + +/** + * console_cpu_notify - print deferred console messages after CPU hotplug + * @self: notifier struct + * @action: CPU hotplug event + * @hcpu: unused + * + * If printk() is called from a CPU that is not online yet, the messages + * will be spooled but will not show up on the console. This function is + * called when a new CPU comes online (or fails to come up), and ensures + * that any such output gets printed. + */ +static int __cpuinit console_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + switch (action) { + case CPU_ONLINE: + case CPU_DEAD: + case CPU_DOWN_FAILED: + case CPU_UP_CANCELED: + console_lock(); + console_unlock(); + } + return NOTIFY_OK; +} + +/** + * console_lock - lock the console system for exclusive use. + * + * Acquires a lock which guarantees that the caller has + * exclusive access to the console system and the console_drivers list. + * + * Can sleep, returns nothing. + */ +void console_lock(void) +{ + might_sleep(); + + down(&console_sem); + if (console_suspended) + return; + console_locked = 1; + console_may_schedule = 1; + mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_); +} +EXPORT_SYMBOL(console_lock); + +/** + * console_trylock - try to lock the console system for exclusive use. + * + * Tried to acquire a lock which guarantees that the caller has + * exclusive access to the console system and the console_drivers list. + * + * returns 1 on success, and 0 on failure to acquire the lock. + */ +int console_trylock(void) +{ + if (down_trylock(&console_sem)) + return 0; + if (console_suspended) { + up(&console_sem); + return 0; + } + console_locked = 1; + console_may_schedule = 0; + mutex_acquire(&console_lock_dep_map, 0, 1, _RET_IP_); + return 1; +} +EXPORT_SYMBOL(console_trylock); + +int is_console_locked(void) +{ + return console_locked; +} + +static void console_cont_flush(char *text, size_t size) +{ + unsigned long flags; + size_t len; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + + if (!cont.len) + goto out; + + /* + * We still queue earlier records, likely because the console was + * busy. The earlier ones need to be printed before this one, we + * did not flush any fragment so far, so just let it queue up. + */ + if (console_seq < log_next_seq && !cont.cons) + goto out; + + len = cont_print_text(text, size); + raw_spin_unlock(&logbuf_lock); + stop_critical_timings(); + call_console_drivers(cont.level, text, len); + start_critical_timings(); + local_irq_restore(flags); + return; +out: + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +} + +/** + * console_unlock - unlock the console system + * + * Releases the console_lock which the caller holds on the console system + * and the console driver list. + * + * While the console_lock was held, console output may have been buffered + * by printk(). If this is the case, console_unlock(); emits + * the output prior to releasing the lock. + * + * If there is output waiting, we wake /dev/kmsg and syslog() users. + * + * console_unlock(); may be called from any context. + */ +void console_unlock(void) +{ + static char text[LOG_LINE_MAX + PREFIX_MAX]; + static u64 seen_seq; + unsigned long flags; + bool wake_klogd = false; + bool retry; + + if (console_suspended) { + up(&console_sem); + return; + } + + console_may_schedule = 0; + + /* flush buffered message fragment immediately to console */ + console_cont_flush(text, sizeof(text)); +again: + for (;;) { + struct log *msg; + size_t len; + int level; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + if (seen_seq != log_next_seq) { + wake_klogd = true; + seen_seq = log_next_seq; + } + + if (console_seq < log_first_seq) { + /* messages are gone, move to first one */ + console_seq = log_first_seq; + console_idx = log_first_idx; + console_prev = 0; + } +skip: + if (console_seq == log_next_seq) + break; + + msg = log_from_idx(console_idx); + if (msg->flags & LOG_NOCONS) { + /* + * Skip record we have buffered and already printed + * directly to the console when we received it. + */ + console_idx = log_next(console_idx); + console_seq++; + /* + * We will get here again when we register a new + * CON_PRINTBUFFER console. Clear the flag so we + * will properly dump everything later. + */ + msg->flags &= ~LOG_NOCONS; + console_prev = msg->flags; + goto skip; + } + + level = msg->level; + len = msg_print_text(msg, console_prev, false, + text, sizeof(text)); + console_idx = log_next(console_idx); + console_seq++; + console_prev = msg->flags; + raw_spin_unlock(&logbuf_lock); + + stop_critical_timings(); /* don't trace print latency */ + call_console_drivers(level, text, len); + start_critical_timings(); + local_irq_restore(flags); + } + console_locked = 0; + mutex_release(&console_lock_dep_map, 1, _RET_IP_); + + /* Release the exclusive_console once it is used */ + if (unlikely(exclusive_console)) + exclusive_console = NULL; + + raw_spin_unlock(&logbuf_lock); + + up(&console_sem); + + /* + * Someone could have filled up the buffer again, so re-check if there's + * something to flush. In case we cannot trylock the console_sem again, + * there's a new owner and the console_unlock() from them will do the + * flush, no worries. + */ + raw_spin_lock(&logbuf_lock); + retry = console_seq != log_next_seq; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + if (retry && console_trylock()) + goto again; + + if (wake_klogd) + wake_up_klogd(); +} +EXPORT_SYMBOL(console_unlock); + +/** + * console_conditional_schedule - yield the CPU if required + * + * If the console code is currently allowed to sleep, and + * if this CPU should yield the CPU to another task, do + * so here. + * + * Must be called within console_lock();. + */ +void __sched console_conditional_schedule(void) +{ + if (console_may_schedule) + cond_resched(); +} +EXPORT_SYMBOL(console_conditional_schedule); + +void console_unblank(void) +{ + struct console *c; + + /* + * console_unblank can no longer be called in interrupt context unless + * oops_in_progress is set to 1.. + */ + if (oops_in_progress) { + if (down_trylock(&console_sem) != 0) + return; + } else + console_lock(); + + console_locked = 1; + console_may_schedule = 0; + for_each_console(c) + if ((c->flags & CON_ENABLED) && c->unblank) + c->unblank(); + console_unlock(); +} + +/* + * Return the console tty driver structure and its associated index + */ +struct tty_driver *console_device(int *index) +{ + struct console *c; + struct tty_driver *driver = NULL; + + console_lock(); + for_each_console(c) { + if (!c->device) + continue; + driver = c->device(c, index); + if (driver) + break; + } + console_unlock(); + return driver; +} + +/* + * Prevent further output on the passed console device so that (for example) + * serial drivers can disable console output before suspending a port, and can + * re-enable output afterwards. + */ +void console_stop(struct console *console) +{ + console_lock(); + console->flags &= ~CON_ENABLED; + console_unlock(); +} +EXPORT_SYMBOL(console_stop); + +void console_start(struct console *console) +{ + console_lock(); + console->flags |= CON_ENABLED; + console_unlock(); +} +EXPORT_SYMBOL(console_start); + +static int __read_mostly keep_bootcon; + +static int __init keep_bootcon_setup(char *str) +{ + keep_bootcon = 1; + printk(KERN_INFO "debug: skip boot console de-registration.\n"); + + return 0; +} + +early_param("keep_bootcon", keep_bootcon_setup); + +/* + * The console driver calls this routine during kernel initialization + * to register the console printing procedure with printk() and to + * print any messages that were printed by the kernel before the + * console driver was initialized. + * + * This can happen pretty early during the boot process (because of + * early_printk) - sometimes before setup_arch() completes - be careful + * of what kernel features are used - they may not be initialised yet. + * + * There are two types of consoles - bootconsoles (early_printk) and + * "real" consoles (everything which is not a bootconsole) which are + * handled differently. + * - Any number of bootconsoles can be registered at any time. + * - As soon as a "real" console is registered, all bootconsoles + * will be unregistered automatically. + * - Once a "real" console is registered, any attempt to register a + * bootconsoles will be rejected + */ +void register_console(struct console *newcon) +{ + int i; + unsigned long flags; + struct console *bcon = NULL; + + /* + * before we register a new CON_BOOT console, make sure we don't + * already have a valid console + */ + if (console_drivers && newcon->flags & CON_BOOT) { + /* find the last or real console */ + for_each_console(bcon) { + if (!(bcon->flags & CON_BOOT)) { + printk(KERN_INFO "Too late to register bootconsole %s%d\n", + newcon->name, newcon->index); + return; + } + } + } + + if (console_drivers && console_drivers->flags & CON_BOOT) + bcon = console_drivers; + + if (preferred_console < 0 || bcon || !console_drivers) + preferred_console = selected_console; + + if (newcon->early_setup) + newcon->early_setup(); + + /* + * See if we want to use this console driver. If we + * didn't select a console we take the first one + * that registers here. + */ + if (preferred_console < 0) { + if (newcon->index < 0) + newcon->index = 0; + if (newcon->setup == NULL || + newcon->setup(newcon, NULL) == 0) { + newcon->flags |= CON_ENABLED; + if (newcon->device) { + newcon->flags |= CON_CONSDEV; + preferred_console = 0; + } + } + } + + /* + * See if this console matches one we selected on + * the command line. + */ + for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0]; + i++) { + if (strcmp(console_cmdline[i].name, newcon->name) != 0) + continue; + if (newcon->index >= 0 && + newcon->index != console_cmdline[i].index) + continue; + if (newcon->index < 0) + newcon->index = console_cmdline[i].index; +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + if (console_cmdline[i].brl_options) { + newcon->flags |= CON_BRL; + braille_register_console(newcon, + console_cmdline[i].index, + console_cmdline[i].options, + console_cmdline[i].brl_options); + return; + } +#endif + if (newcon->setup && + newcon->setup(newcon, console_cmdline[i].options) != 0) + break; + newcon->flags |= CON_ENABLED; + newcon->index = console_cmdline[i].index; + if (i == selected_console) { + newcon->flags |= CON_CONSDEV; + preferred_console = selected_console; + } + break; + } + + if (!(newcon->flags & CON_ENABLED)) + return; + + /* + * If we have a bootconsole, and are switching to a real console, + * don't print everything out again, since when the boot console, and + * the real console are the same physical device, it's annoying to + * see the beginning boot messages twice + */ + if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) + newcon->flags &= ~CON_PRINTBUFFER; + + /* + * Put this console in the list - keep the + * preferred driver at the head of the list. + */ + console_lock(); + if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) { + newcon->next = console_drivers; + console_drivers = newcon; + if (newcon->next) + newcon->next->flags &= ~CON_CONSDEV; + } else { + newcon->next = console_drivers->next; + console_drivers->next = newcon; + } + if (newcon->flags & CON_PRINTBUFFER) { + /* + * console_unlock(); will print out the buffered messages + * for us. + */ + raw_spin_lock_irqsave(&logbuf_lock, flags); + console_seq = syslog_seq; + console_idx = syslog_idx; + console_prev = syslog_prev; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + /* + * We're about to replay the log buffer. Only do this to the + * just-registered console to avoid excessive message spam to + * the already-registered consoles. + */ + exclusive_console = newcon; + } + console_unlock(); + console_sysfs_notify(); + + /* + * By unregistering the bootconsoles after we enable the real console + * we get the "console xxx enabled" message on all the consoles - + * boot consoles, real consoles, etc - this is to ensure that end + * users know there might be something in the kernel's log buffer that + * went to the bootconsole (that they do not see on the real console) + */ + if (bcon && + ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && + !keep_bootcon) { + /* we need to iterate through twice, to make sure we print + * everything out, before we unregister the console(s) + */ + printk(KERN_INFO "console [%s%d] enabled, bootconsole disabled\n", + newcon->name, newcon->index); + for_each_console(bcon) + if (bcon->flags & CON_BOOT) + unregister_console(bcon); + } else { + printk(KERN_INFO "%sconsole [%s%d] enabled\n", + (newcon->flags & CON_BOOT) ? "boot" : "" , + newcon->name, newcon->index); + } +} +EXPORT_SYMBOL(register_console); + +int unregister_console(struct console *console) +{ + struct console *a, *b; + int res = 1; + +#ifdef CONFIG_A11Y_BRAILLE_CONSOLE + if (console->flags & CON_BRL) + return braille_unregister_console(console); +#endif + + console_lock(); + if (console_drivers == console) { + console_drivers=console->next; + res = 0; + } else if (console_drivers) { + for (a=console_drivers->next, b=console_drivers ; + a; b=a, a=b->next) { + if (a == console) { + b->next = a->next; + res = 0; + break; + } + } + } + + /* + * If this isn't the last console and it has CON_CONSDEV set, we + * need to set it on the next preferred console. + */ + if (console_drivers != NULL && console->flags & CON_CONSDEV) + console_drivers->flags |= CON_CONSDEV; + + console_unlock(); + console_sysfs_notify(); + return res; +} +EXPORT_SYMBOL(unregister_console); + +static int __init printk_late_init(void) +{ + struct console *con; + + for_each_console(con) { + if (!keep_bootcon && con->flags & CON_BOOT) { + printk(KERN_INFO "turn off boot console %s%d\n", + con->name, con->index); + unregister_console(con); + } + } + hotcpu_notifier(console_cpu_notify, 0); + return 0; +} +late_initcall(printk_late_init); + +#if defined CONFIG_PRINTK +/* + * Delayed printk version, for scheduler-internal messages: + */ +#define PRINTK_BUF_SIZE 512 + +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_SCHED 0x02 + +static DEFINE_PER_CPU(int, printk_pending); +static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf); + +static void wake_up_klogd_work_func(struct irq_work *irq_work) +{ + int pending = __this_cpu_xchg(printk_pending, 0); + + if (pending & PRINTK_PENDING_SCHED) { + char *buf = __get_cpu_var(printk_sched_buf); + printk(KERN_WARNING "[sched_delayed] %s", buf); + } + + if (pending & PRINTK_PENDING_WAKEUP) + wake_up_interruptible(&log_wait); +} + +static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { + .func = wake_up_klogd_work_func, + .flags = IRQ_WORK_LAZY, +}; + +void wake_up_klogd(void) +{ + preempt_disable(); + if (waitqueue_active(&log_wait)) { + this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); + irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); + } + preempt_enable(); +} + +int printk_sched(const char *fmt, ...) +{ + unsigned long flags; + va_list args; + char *buf; + int r; + + local_irq_save(flags); + buf = __get_cpu_var(printk_sched_buf); + + va_start(args, fmt); + r = vsnprintf(buf, PRINTK_BUF_SIZE, fmt, args); + va_end(args); + + __this_cpu_or(printk_pending, PRINTK_PENDING_SCHED); + irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); + local_irq_restore(flags); + + return r; +} + +/* + * printk rate limiting, lifted from the networking subsystem. + * + * This enforces a rate limit: not more than 10 kernel messages + * every 5s to make a denial-of-service attack impossible. + */ +DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); + +int __printk_ratelimit(const char *func) +{ + return ___ratelimit(&printk_ratelimit_state, func); +} +EXPORT_SYMBOL(__printk_ratelimit); + +/** + * printk_timed_ratelimit - caller-controlled printk ratelimiting + * @caller_jiffies: pointer to caller's state + * @interval_msecs: minimum interval between prints + * + * printk_timed_ratelimit() returns true if more than @interval_msecs + * milliseconds have elapsed since the last time printk_timed_ratelimit() + * returned true. + */ +bool printk_timed_ratelimit(unsigned long *caller_jiffies, + unsigned int interval_msecs) +{ + if (*caller_jiffies == 0 + || !time_in_range(jiffies, *caller_jiffies, + *caller_jiffies + + msecs_to_jiffies(interval_msecs))) { + *caller_jiffies = jiffies; + return true; + } + return false; +} +EXPORT_SYMBOL(printk_timed_ratelimit); + +static DEFINE_SPINLOCK(dump_list_lock); +static LIST_HEAD(dump_list); + +/** + * kmsg_dump_register - register a kernel log dumper. + * @dumper: pointer to the kmsg_dumper structure + * + * Adds a kernel log dumper to the system. The dump callback in the + * structure will be called when the kernel oopses or panics and must be + * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise. + */ +int kmsg_dump_register(struct kmsg_dumper *dumper) +{ + unsigned long flags; + int err = -EBUSY; + + /* The dump callback needs to be set */ + if (!dumper->dump) + return -EINVAL; + + spin_lock_irqsave(&dump_list_lock, flags); + /* Don't allow registering multiple times */ + if (!dumper->registered) { + dumper->registered = 1; + list_add_tail_rcu(&dumper->list, &dump_list); + err = 0; + } + spin_unlock_irqrestore(&dump_list_lock, flags); + + return err; +} +EXPORT_SYMBOL_GPL(kmsg_dump_register); + +/** + * kmsg_dump_unregister - unregister a kmsg dumper. + * @dumper: pointer to the kmsg_dumper structure + * + * Removes a dump device from the system. Returns zero on success and + * %-EINVAL otherwise. + */ +int kmsg_dump_unregister(struct kmsg_dumper *dumper) +{ + unsigned long flags; + int err = -EINVAL; + + spin_lock_irqsave(&dump_list_lock, flags); + if (dumper->registered) { + dumper->registered = 0; + list_del_rcu(&dumper->list); + err = 0; + } + spin_unlock_irqrestore(&dump_list_lock, flags); + synchronize_rcu(); + + return err; +} +EXPORT_SYMBOL_GPL(kmsg_dump_unregister); + +static bool always_kmsg_dump; +module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); + +/** + * kmsg_dump - dump kernel log to kernel message dumpers. + * @reason: the reason (oops, panic etc) for dumping + * + * Call each of the registered dumper's dump() callback, which can + * retrieve the kmsg records with kmsg_dump_get_line() or + * kmsg_dump_get_buffer(). + */ +void kmsg_dump(enum kmsg_dump_reason reason) +{ + struct kmsg_dumper *dumper; + unsigned long flags; + + if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump) + return; + + rcu_read_lock(); + list_for_each_entry_rcu(dumper, &dump_list, list) { + if (dumper->max_reason && reason > dumper->max_reason) + continue; + + /* initialize iterator with data about the stored records */ + dumper->active = true; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + /* invoke dumper which will iterate over records */ + dumper->dump(dumper, reason); + + /* reset iterator */ + dumper->active = false; + } + rcu_read_unlock(); +} + +/** + * kmsg_dump_get_line_nolock - retrieve one kmsg log line (unlocked version) + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the beginning of the kmsg buffer, with the oldest kmsg + * record, and copy one record into the provided buffer. + * + * Consecutive calls will return the next available record moving + * towards the end of the buffer with the youngest messages. + * + * A return value of FALSE indicates that there are no more records to + * read. + * + * The function is similar to kmsg_dump_get_line(), but grabs no locks. + */ +bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) +{ + struct log *msg; + size_t l = 0; + bool ret = false; + + if (!dumper->active) + goto out; + + if (dumper->cur_seq < log_first_seq) { + /* messages are gone, move to first available one */ + dumper->cur_seq = log_first_seq; + dumper->cur_idx = log_first_idx; + } + + /* last entry */ + if (dumper->cur_seq >= log_next_seq) + goto out; + + msg = log_from_idx(dumper->cur_idx); + l = msg_print_text(msg, 0, syslog, line, size); + + dumper->cur_idx = log_next(dumper->cur_idx); + dumper->cur_seq++; + ret = true; +out: + if (len) + *len = l; + return ret; +} + +/** + * kmsg_dump_get_line - retrieve one kmsg log line + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the beginning of the kmsg buffer, with the oldest kmsg + * record, and copy one record into the provided buffer. + * + * Consecutive calls will return the next available record moving + * towards the end of the buffer with the youngest messages. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) +{ + unsigned long flags; + bool ret; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + ret = kmsg_dump_get_line_nolock(dumper, syslog, line, size, len); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(kmsg_dump_get_line); + +/** + * kmsg_dump_get_buffer - copy kmsg log lines + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @buf: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the end of the kmsg buffer and fill the provided buffer + * with as many of the the *youngest* kmsg records that fit into it. + * If the buffer is large enough, all available kmsg records will be + * copied with a single call. + * + * Consecutive calls will fill the buffer with the next block of + * available older records, not including the earlier retrieved ones. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, + char *buf, size_t size, size_t *len) +{ + unsigned long flags; + u64 seq; + u32 idx; + u64 next_seq; + u32 next_idx; + enum log_flags prev; + size_t l = 0; + bool ret = false; + + if (!dumper->active) + goto out; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + if (dumper->cur_seq < log_first_seq) { + /* messages are gone, move to first available one */ + dumper->cur_seq = log_first_seq; + dumper->cur_idx = log_first_idx; + } + + /* last entry */ + if (dumper->cur_seq >= dumper->next_seq) { + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + goto out; + } + + /* calculate length of entire buffer */ + seq = dumper->cur_seq; + idx = dumper->cur_idx; + prev = 0; + while (seq < dumper->next_seq) { + struct log *msg = log_from_idx(idx); + + l += msg_print_text(msg, prev, true, NULL, 0); + idx = log_next(idx); + seq++; + prev = msg->flags; + } + + /* move first record forward until length fits into the buffer */ + seq = dumper->cur_seq; + idx = dumper->cur_idx; + prev = 0; + while (l > size && seq < dumper->next_seq) { + struct log *msg = log_from_idx(idx); + + l -= msg_print_text(msg, prev, true, NULL, 0); + idx = log_next(idx); + seq++; + prev = msg->flags; + } + + /* last message in next interation */ + next_seq = seq; + next_idx = idx; + + l = 0; + prev = 0; + while (seq < dumper->next_seq) { + struct log *msg = log_from_idx(idx); + + l += msg_print_text(msg, prev, syslog, buf + l, size - l); + idx = log_next(idx); + seq++; + prev = msg->flags; + } + + dumper->next_seq = next_seq; + dumper->next_idx = next_idx; + ret = true; + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +out: + if (len) + *len = l; + return ret; +} +EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); + +/** + * kmsg_dump_rewind_nolock - reset the interator (unlocked version) + * @dumper: registered kmsg dumper + * + * Reset the dumper's iterator so that kmsg_dump_get_line() and + * kmsg_dump_get_buffer() can be called again and used multiple + * times within the same dumper.dump() callback. + * + * The function is similar to kmsg_dump_rewind(), but grabs no locks. + */ +void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) +{ + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; +} + +/** + * kmsg_dump_rewind - reset the interator + * @dumper: registered kmsg dumper + * + * Reset the dumper's iterator so that kmsg_dump_get_line() and + * kmsg_dump_get_buffer() can be called again and used multiple + * times within the same dumper.dump() callback. + */ +void kmsg_dump_rewind(struct kmsg_dumper *dumper) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + kmsg_dump_rewind_nolock(dumper); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +} +EXPORT_SYMBOL_GPL(kmsg_dump_rewind); + +static char dump_stack_arch_desc_str[128]; + +/** + * dump_stack_set_arch_desc - set arch-specific str to show with task dumps + * @fmt: printf-style format string + * @...: arguments for the format string + * + * The configured string will be printed right after utsname during task + * dumps. Usually used to add arch-specific system identifiers. If an + * arch wants to make use of such an ID string, it should initialize this + * as soon as possible during boot. + */ +void __init dump_stack_set_arch_desc(const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vsnprintf(dump_stack_arch_desc_str, sizeof(dump_stack_arch_desc_str), + fmt, args); + va_end(args); +} + +/** + * dump_stack_print_info - print generic debug info for dump_stack() + * @log_lvl: log level + * + * Arch-specific dump_stack() implementations can use this function to + * print out the same debug information as the generic dump_stack(). + */ +void dump_stack_print_info(const char *log_lvl) +{ + printk("%sCPU: %d PID: %d Comm: %.20s %s %s %.*s\n", + log_lvl, raw_smp_processor_id(), current->pid, current->comm, + print_tainted(), init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + + if (dump_stack_arch_desc_str[0] != '\0') + printk("%sHardware name: %s\n", + log_lvl, dump_stack_arch_desc_str); + + print_worker_info(log_lvl, current); +} + +/** + * show_regs_print_info - print generic debug info for show_regs() + * @log_lvl: log level + * + * show_regs() implementations can use this function to print out generic + * debug information. + */ +void show_regs_print_info(const char *log_lvl) +{ + dump_stack_print_info(log_lvl); + + printk("%stask: %p ti: %p task.ti: %p\n", + log_lvl, current, current_thread_info(), + task_thread_info(current)); +} + +#endif diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5ac63c9a995a..f462df1da410 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6571,13 +6571,24 @@ static inline int preempt_count_equals(int preempt_offset) return (nested == preempt_offset); } +static int __might_sleep_init_called; +int __init __might_sleep_init(void) +{ + __might_sleep_init_called = 1; + return 0; +} +early_initcall(__might_sleep_init); + void __might_sleep(const char *file, int line, int preempt_offset) { static unsigned long prev_jiffy; /* ratelimiting */ rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || - system_state != SYSTEM_RUNNING || oops_in_progress) + oops_in_progress) + return; + if (system_state != SYSTEM_RUNNING && + (!__might_sleep_init_called || system_state != SYSTEM_BOOTING)) return; if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) return; diff --git a/kernel/sys.c b/kernel/sys.c index c18ecca575b4..eced15d4e26d 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -42,6 +42,8 @@ #include <linux/syscore_ops.h> #include <linux/version.h> #include <linux/ctype.h> +#include <linux/mm.h> +#include <linux/mempolicy.h> #include <linux/compat.h> #include <linux/syscalls.h> @@ -1836,6 +1838,146 @@ static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) } #endif + +static int prctl_update_vma_anon_name(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end, + const char __user *name_addr) +{ + struct mm_struct * mm = vma->vm_mm; + int error = 0; + pgoff_t pgoff; + + if (name_addr == vma_get_anon_name(vma)) { + *prev = vma; + goto out; + } + + pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); + *prev = vma_merge(mm, *prev, start, end, vma->vm_flags, vma->anon_vma, + vma->vm_file, pgoff, vma_policy(vma), + name_addr); + if (*prev) { + vma = *prev; + goto success; + } + + *prev = vma; + + if (start != vma->vm_start) { + error = split_vma(mm, vma, start, 1); + if (error) + goto out; + } + + if (end != vma->vm_end) { + error = split_vma(mm, vma, end, 0); + if (error) + goto out; + } + +success: + if (!vma->vm_file) + vma->shared.anon_name = name_addr; + +out: + if (error == -ENOMEM) + error = -EAGAIN; + return error; +} + +static int prctl_set_vma_anon_name(unsigned long start, unsigned long end, + unsigned long arg) +{ + unsigned long tmp; + struct vm_area_struct * vma, *prev; + int unmapped_error = 0; + int error = -EINVAL; + + /* + * If the interval [start,end) covers some unmapped address + * ranges, just ignore them, but return -ENOMEM at the end. + * - this matches the handling in madvise. + */ + vma = find_vma_prev(current->mm, start, &prev); + if (vma && start > vma->vm_start) + prev = vma; + + for (;;) { + /* Still start < end. */ + error = -ENOMEM; + if (!vma) + return error; + + /* Here start < (end|vma->vm_end). */ + if (start < vma->vm_start) { + unmapped_error = -ENOMEM; + start = vma->vm_start; + if (start >= end) + return error; + } + + /* Here vma->vm_start <= start < (end|vma->vm_end) */ + tmp = vma->vm_end; + if (end < tmp) + tmp = end; + + /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */ + error = prctl_update_vma_anon_name(vma, &prev, start, end, + (const char __user *)arg); + if (error) + return error; + start = tmp; + if (prev && start < prev->vm_end) + start = prev->vm_end; + error = unmapped_error; + if (start >= end) + return error; + if (prev) + vma = prev->vm_next; + else /* madvise_remove dropped mmap_sem */ + vma = find_vma(current->mm, start); + } +} + +static int prctl_set_vma(unsigned long opt, unsigned long start, + unsigned long len_in, unsigned long arg) +{ + struct mm_struct *mm = current->mm; + int error; + unsigned long len; + unsigned long end; + + if (start & ~PAGE_MASK) + return -EINVAL; + len = (len_in + ~PAGE_MASK) & PAGE_MASK; + + /* Check to see whether len was rounded up from small -ve to zero */ + if (len_in && !len) + return -EINVAL; + + end = start + len; + if (end < start) + return -EINVAL; + + if (end == start) + return 0; + + down_write(&mm->mmap_sem); + + switch (opt) { + case PR_SET_VMA_ANON_NAME: + error = prctl_set_vma_anon_name(start, end, arg); + break; + default: + error = -EINVAL; + } + + up_write(&mm->mmap_sem); + + return error; +} + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -1963,6 +2105,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, else return -EINVAL; break; + case PR_SET_VMA: + error = prctl_set_vma(arg2, arg3, arg4, arg5); + break; default: return -EINVAL; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b2f06f3c6a3f..b43d4e3e1176 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -105,6 +105,8 @@ extern char core_pattern[]; extern unsigned int core_pipe_limit; #endif extern int pid_max; +extern int extra_free_kbytes; +extern int min_free_order_shift; extern int pid_max_min, pid_max_max; extern int percpu_pagelist_fraction; extern int compat_log; @@ -1281,6 +1283,21 @@ static struct ctl_table vm_table[] = { .extra1 = &zero, }, { + .procname = "extra_free_kbytes", + .data = &extra_free_kbytes, + .maxlen = sizeof(extra_free_kbytes), + .mode = 0644, + .proc_handler = min_free_kbytes_sysctl_handler, + .extra1 = &zero, + }, + { + .procname = "min_free_order_shift", + .data = &min_free_order_shift, + .maxlen = sizeof(min_free_order_shift), + .mode = 0644, + .proc_handler = &proc_dointvec + }, + { .procname = "percpu_pagelist_fraction", .data = &percpu_pagelist_fraction, .maxlen = sizeof(percpu_pagelist_fraction), diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index eec50fcef9e4..d17b4d0ed8f4 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -345,7 +345,6 @@ int alarm_start_relative(struct alarm *alarm, ktime_t start) start = ktime_add(start, base->gettime()); return alarm_start(alarm, start); } -EXPORT_SYMBOL_GPL(alarm_start_relative); void alarm_restart(struct alarm *alarm) { @@ -358,7 +357,6 @@ void alarm_restart(struct alarm *alarm) alarmtimer_enqueue(base, alarm); spin_unlock_irqrestore(&base->lock, flags); } -EXPORT_SYMBOL_GPL(alarm_restart); /** * alarm_try_to_cancel - Tries to cancel an alarm timer diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 015f85aaca08..e24c188cbbcc 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -82,6 +82,9 @@ config EVENT_TRACING select CONTEXT_SWITCH_TRACER bool +config GPU_TRACEPOINTS + bool + config CONTEXT_SWITCH_TRACER bool diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index d7e2068e4b71..45012122fbb6 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -60,5 +60,6 @@ obj-$(CONFIG_KGDB_KDB) += trace_kdb.o endif obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o +obj-$(CONFIG_GPU_TRACEPOINTS) += gpu-traces.o libftrace-y := ftrace.o diff --git a/kernel/trace/gpu-traces.c b/kernel/trace/gpu-traces.c new file mode 100644 index 000000000000..a4b3f00faee3 --- /dev/null +++ b/kernel/trace/gpu-traces.c @@ -0,0 +1,23 @@ +/* + * GPU tracepoints + * + * Copyright (C) 2013 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * 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. + * + */ + +#include <linux/module.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/gpu.h> + +EXPORT_TRACEPOINT_SYMBOL(gpu_sched_switch); +EXPORT_TRACEPOINT_SYMBOL(gpu_job_enqueue); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 7974ba20557d..64042c0be0f3 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -733,6 +733,7 @@ static const char *trace_options[] = { "irq-info", "markers", "function-trace", + "print-tgid", NULL }; @@ -1242,6 +1243,7 @@ void tracing_reset_all_online_cpus(void) static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; static unsigned map_cmdline_to_pid[SAVED_CMDLINES]; static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN]; +static unsigned saved_tgids[SAVED_CMDLINES]; static int cmdline_idx; static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED; @@ -1445,6 +1447,7 @@ static void trace_save_cmdline(struct task_struct *tsk) } memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN); + saved_tgids[idx] = tsk->tgid; arch_spin_unlock(&trace_cmdline_lock); } @@ -1480,6 +1483,25 @@ void trace_find_cmdline(int pid, char comm[]) preempt_enable(); } +int trace_find_tgid(int pid) +{ + unsigned map; + int tgid; + + preempt_disable(); + arch_spin_lock(&trace_cmdline_lock); + map = map_pid_to_cmdline[pid]; + if (map != NO_CMDLINE_MAP) + tgid = saved_tgids[map]; + else + tgid = -1; + + arch_spin_unlock(&trace_cmdline_lock); + preempt_enable(); + + return tgid; +} + void tracing_record_cmdline(struct task_struct *tsk) { if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on()) @@ -2427,6 +2449,13 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m) seq_puts(m, "# | | | | |\n"); } +static void print_func_help_header_tgid(struct trace_buffer *buf, struct seq_file *m) +{ + print_event_info(buf, m); + seq_puts(m, "# TASK-PID TGID CPU# TIMESTAMP FUNCTION\n"); + seq_puts(m, "# | | | | | |\n"); +} + static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m) { print_event_info(buf, m); @@ -2439,6 +2468,18 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file seq_puts(m, "# | | | |||| | |\n"); } +static void print_func_help_header_irq_tgid(struct trace_buffer *buf, struct seq_file *m) +{ + print_event_info(buf, m); + seq_puts(m, "# _-----=> irqs-off\n"); + seq_puts(m, "# / _----=> need-resched\n"); + seq_puts(m, "# | / _---=> hardirq/softirq\n"); + seq_puts(m, "# || / _--=> preempt-depth\n"); + seq_puts(m, "# ||| / delay\n"); + seq_puts(m, "# TASK-PID TGID CPU# |||| TIMESTAMP FUNCTION\n"); + seq_puts(m, "# | | | | |||| | |\n"); +} + void print_trace_header(struct seq_file *m, struct trace_iterator *iter) { @@ -2739,9 +2780,15 @@ void trace_default_header(struct seq_file *m) } else { if (!(trace_flags & TRACE_ITER_VERBOSE)) { if (trace_flags & TRACE_ITER_IRQ_INFO) - print_func_help_header_irq(iter->trace_buffer, m); + if (trace_flags & TRACE_ITER_TGID) + print_func_help_header_irq_tgid(iter->trace_buffer, m); + else + print_func_help_header_irq(iter->trace_buffer, m); else - print_func_help_header(iter->trace_buffer, m); + if (trace_flags & TRACE_ITER_TGID) + print_func_help_header_tgid(iter->trace_buffer, m); + else + print_func_help_header(iter->trace_buffer, m); } } } @@ -3590,9 +3637,53 @@ tracing_saved_cmdlines_read(struct file *file, char __user *ubuf, } static const struct file_operations tracing_saved_cmdlines_fops = { - .open = tracing_open_generic, - .read = tracing_saved_cmdlines_read, - .llseek = generic_file_llseek, + .open = tracing_open_generic, + .read = tracing_saved_cmdlines_read, + .llseek = generic_file_llseek, +}; + +static ssize_t +tracing_saved_tgids_read(struct file *file, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char *file_buf; + char *buf; + int len = 0; + int pid; + int i; + + file_buf = kmalloc(SAVED_CMDLINES*(16+1+16), GFP_KERNEL); + if (!file_buf) + return -ENOMEM; + + buf = file_buf; + + for (i = 0; i < SAVED_CMDLINES; i++) { + int tgid; + int r; + + pid = map_cmdline_to_pid[i]; + if (pid == -1 || pid == NO_CMDLINE_MAP) + continue; + + tgid = trace_find_tgid(pid); + r = sprintf(buf, "%d %d\n", pid, tgid); + buf += r; + len += r; + } + + len = simple_read_from_buffer(ubuf, cnt, ppos, + file_buf, len); + + kfree(file_buf); + + return len; +} + +static const struct file_operations tracing_saved_tgids_fops = { + .open = tracing_open_generic, + .read = tracing_saved_tgids_read, + .llseek = generic_file_llseek, }; static ssize_t @@ -6125,6 +6216,9 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer) trace_create_file("trace_marker", 0220, d_tracer, tr, &tracing_mark_fops); + trace_create_file("saved_tgids", 0444, d_tracer, + tr, &tracing_saved_tgids_fops); + trace_create_file("trace_clock", 0644, d_tracer, tr, &trace_clock_fops); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 10c86fb7a2b4..aaf5ff3632a1 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -640,6 +640,7 @@ static inline void __trace_stack(struct trace_array *tr, unsigned long flags, extern cycle_t ftrace_now(int cpu); extern void trace_find_cmdline(int pid, char comm[]); +extern int trace_find_tgid(int pid); #ifdef CONFIG_DYNAMIC_FTRACE extern unsigned long ftrace_update_tot_cnt; @@ -863,6 +864,7 @@ enum trace_iterator_flags { TRACE_ITER_IRQ_INFO = 0x800000, TRACE_ITER_MARKERS = 0x1000000, TRACE_ITER_FUNCTION = 0x2000000, + TRACE_ITER_TGID = 0x4000000, }; /* diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index b5c09242683d..4afc1ca69e1e 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -46,6 +46,8 @@ struct fgraph_data { #define TRACE_GRAPH_PRINT_DURATION 0x10 #define TRACE_GRAPH_PRINT_ABS_TIME 0x20 #define TRACE_GRAPH_PRINT_IRQS 0x40 +#define TRACE_GRAPH_PRINT_FLAT 0x80 + static unsigned int max_depth; @@ -64,6 +66,8 @@ static struct tracer_opt trace_opts[] = { { TRACER_OPT(funcgraph-abstime, TRACE_GRAPH_PRINT_ABS_TIME) }, /* Display interrupts */ { TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) }, + /* Use standard trace formatting rather than hierarchical */ + { TRACER_OPT(funcgraph-flat, TRACE_GRAPH_PRINT_FLAT) }, { } /* Empty entry */ }; @@ -1234,6 +1238,9 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags) int cpu = iter->cpu; int ret; + if (flags & TRACE_GRAPH_PRINT_FLAT) + return TRACE_TYPE_UNHANDLED; + if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) { per_cpu_ptr(data->cpu_data, cpu)->ignore = 0; return TRACE_TYPE_HANDLED; @@ -1364,6 +1371,11 @@ void print_graph_headers_flags(struct seq_file *s, u32 flags) { struct trace_iterator *iter = s->private; + if (flags & TRACE_GRAPH_PRINT_FLAT) { + trace_default_header(s); + return; + } + if (!(trace_flags & TRACE_ITER_CONTEXT_INFO)) return; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 34e7cbac0c9c..df2ce5bb56ea 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -702,11 +702,25 @@ int trace_print_context(struct trace_iterator *iter) unsigned long secs, usec_rem; char comm[TASK_COMM_LEN]; int ret; + int tgid; trace_find_cmdline(entry->pid, comm); - ret = trace_seq_printf(s, "%16s-%-5d [%03d] ", - comm, entry->pid, iter->cpu); + ret = trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid); + if (!ret) + return 0; + + if (trace_flags & TRACE_ITER_TGID) { + tgid = trace_find_tgid(entry->pid); + if (tgid < 0) + ret = trace_seq_puts(s, "(-----) "); + else + ret = trace_seq_printf(s, "(%5d) ", tgid); + if (!ret) + return 0; + } + + ret = trace_seq_printf(s, "[%03d] ", iter->cpu); if (!ret) return 0; @@ -1035,6 +1049,168 @@ static struct trace_event trace_fn_event = { .funcs = &trace_fn_funcs, }; +/* TRACE_GRAPH_ENT */ +static enum print_line_t trace_graph_ent_trace(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct trace_seq *s = &iter->seq; + struct ftrace_graph_ent_entry *field; + + trace_assign_type(field, iter->ent); + + if (!trace_seq_puts(s, "graph_ent: func=")) + return TRACE_TYPE_PARTIAL_LINE; + + if (!seq_print_ip_sym(s, field->graph_ent.func, flags)) + return TRACE_TYPE_PARTIAL_LINE; + + if (!trace_seq_puts(s, "\n")) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ent_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ent_entry *field; + + trace_assign_type(field, iter->ent); + + if (!trace_seq_printf(&iter->seq, "%lx %d\n", + field->graph_ent.func, + field->graph_ent.depth)) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ent_hex(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ent_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_HEX_FIELD_RET(s, field->graph_ent.func); + SEQ_PUT_HEX_FIELD_RET(s, field->graph_ent.depth); + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ent_bin(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ent_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_FIELD_RET(s, field->graph_ent.func); + SEQ_PUT_FIELD_RET(s, field->graph_ent.depth); + + return TRACE_TYPE_HANDLED; +} + +static struct trace_event_functions trace_graph_ent_funcs = { + .trace = trace_graph_ent_trace, + .raw = trace_graph_ent_raw, + .hex = trace_graph_ent_hex, + .binary = trace_graph_ent_bin, +}; + +static struct trace_event trace_graph_ent_event = { + .type = TRACE_GRAPH_ENT, + .funcs = &trace_graph_ent_funcs, +}; + +/* TRACE_GRAPH_RET */ +static enum print_line_t trace_graph_ret_trace(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + struct ftrace_graph_ret_entry *field; + + trace_assign_type(field, entry); + + if (!trace_seq_puts(s, "graph_ret: func=")) + return TRACE_TYPE_PARTIAL_LINE; + + if (!seq_print_ip_sym(s, field->ret.func, flags)) + return TRACE_TYPE_PARTIAL_LINE; + + if (!trace_seq_puts(s, "\n")) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ret_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ret_entry *field; + + trace_assign_type(field, iter->ent); + + if (!trace_seq_printf(&iter->seq, "%lx %lld %lld %ld %d\n", + field->ret.func, + field->ret.calltime, + field->ret.rettime, + field->ret.overrun, + field->ret.depth)); + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ret_hex(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ret_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_HEX_FIELD_RET(s, field->ret.func); + SEQ_PUT_HEX_FIELD_RET(s, field->ret.calltime); + SEQ_PUT_HEX_FIELD_RET(s, field->ret.rettime); + SEQ_PUT_HEX_FIELD_RET(s, field->ret.overrun); + SEQ_PUT_HEX_FIELD_RET(s, field->ret.depth); + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ret_bin(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ret_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_FIELD_RET(s, field->ret.func); + SEQ_PUT_FIELD_RET(s, field->ret.calltime); + SEQ_PUT_FIELD_RET(s, field->ret.rettime); + SEQ_PUT_FIELD_RET(s, field->ret.overrun); + SEQ_PUT_FIELD_RET(s, field->ret.depth); + + return TRACE_TYPE_HANDLED; +} + +static struct trace_event_functions trace_graph_ret_funcs = { + .trace = trace_graph_ret_trace, + .raw = trace_graph_ret_raw, + .hex = trace_graph_ret_hex, + .binary = trace_graph_ret_bin, +}; + +static struct trace_event trace_graph_ret_event = { + .type = TRACE_GRAPH_RET, + .funcs = &trace_graph_ret_funcs, +}; + /* TRACE_CTX an TRACE_WAKE */ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, char *delim) @@ -1425,6 +1601,8 @@ static struct trace_event trace_print_event = { static struct trace_event *events[] __initdata = { &trace_fn_event, + &trace_graph_ent_event, + &trace_graph_ret_event, &trace_ctx_event, &trace_wake_event, &trace_stack_event, diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 4431610f049a..68fbd3f169f1 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -45,6 +45,11 @@ static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt); static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); +#endif +#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU +static cpumask_t __read_mostly watchdog_cpus; +#endif +#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); #endif @@ -178,7 +183,7 @@ void touch_softlockup_watchdog_sync(void) __raw_get_cpu_var(watchdog_touch_ts) = 0; } -#ifdef CONFIG_HARDLOCKUP_DETECTOR +#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI /* watchdog detector functions */ static int is_hardlockup(void) { @@ -192,6 +197,76 @@ static int is_hardlockup(void) } #endif +#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU +static unsigned int watchdog_next_cpu(unsigned int cpu) +{ + cpumask_t cpus = watchdog_cpus; + unsigned int next_cpu; + + next_cpu = cpumask_next(cpu, &cpus); + if (next_cpu >= nr_cpu_ids) + next_cpu = cpumask_first(&cpus); + + if (next_cpu == cpu) + return nr_cpu_ids; + + return next_cpu; +} + +static int is_hardlockup_other_cpu(unsigned int cpu) +{ + unsigned long hrint = per_cpu(hrtimer_interrupts, cpu); + + if (per_cpu(hrtimer_interrupts_saved, cpu) == hrint) + return 1; + + per_cpu(hrtimer_interrupts_saved, cpu) = hrint; + return 0; +} + +static void watchdog_check_hardlockup_other_cpu(void) +{ + unsigned int next_cpu; + + /* + * Test for hardlockups every 3 samples. The sample period is + * watchdog_thresh * 2 / 5, so 3 samples gets us back to slightly over + * watchdog_thresh (over by 20%). + */ + if (__this_cpu_read(hrtimer_interrupts) % 3 != 0) + return; + + /* check for a hardlockup on the next cpu */ + next_cpu = watchdog_next_cpu(smp_processor_id()); + if (next_cpu >= nr_cpu_ids) + return; + + smp_rmb(); + + if (per_cpu(watchdog_nmi_touch, next_cpu) == true) { + per_cpu(watchdog_nmi_touch, next_cpu) = false; + return; + } + + if (is_hardlockup_other_cpu(next_cpu)) { + /* only warn once */ + if (per_cpu(hard_watchdog_warn, next_cpu) == true) + return; + + if (hardlockup_panic) + panic("Watchdog detected hard LOCKUP on cpu %u", next_cpu); + else + WARN(1, "Watchdog detected hard LOCKUP on cpu %u", next_cpu); + + per_cpu(hard_watchdog_warn, next_cpu) = true; + } else { + per_cpu(hard_watchdog_warn, next_cpu) = false; + } +} +#else +static inline void watchdog_check_hardlockup_other_cpu(void) { return; } +#endif + static int is_softlockup(unsigned long touch_ts) { unsigned long now = get_timestamp(); @@ -203,7 +278,7 @@ static int is_softlockup(unsigned long touch_ts) return 0; } -#ifdef CONFIG_HARDLOCKUP_DETECTOR +#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, @@ -251,7 +326,7 @@ static void watchdog_overflow_callback(struct perf_event *event, __this_cpu_write(hard_watchdog_warn, false); return; } -#endif /* CONFIG_HARDLOCKUP_DETECTOR */ +#endif /* CONFIG_HARDLOCKUP_DETECTOR_NMI */ static void watchdog_interrupt_count(void) { @@ -271,6 +346,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) /* kick the hardlockup detector */ watchdog_interrupt_count(); + /* test for hardlockups on the next cpu */ + watchdog_check_hardlockup_other_cpu(); + /* kick the softlockup detector */ wake_up_process(__this_cpu_read(softlockup_watchdog)); @@ -395,7 +473,7 @@ static void watchdog(unsigned int cpu) __touch_watchdog(); } -#ifdef CONFIG_HARDLOCKUP_DETECTOR +#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI /* * People like the simple clean cpu node info on boot. * Reduce the watchdog noise by only printing messages @@ -471,9 +549,44 @@ static void watchdog_nmi_disable(unsigned int cpu) return; } #else +#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU +static int watchdog_nmi_enable(unsigned int cpu) +{ + /* + * The new cpu will be marked online before the first hrtimer interrupt + * runs on it. If another cpu tests for a hardlockup on the new cpu + * before it has run its first hrtimer, it will get a false positive. + * Touch the watchdog on the new cpu to delay the first check for at + * least 3 sampling periods to guarantee one hrtimer has run on the new + * cpu. + */ + per_cpu(watchdog_nmi_touch, cpu) = true; + smp_wmb(); + cpumask_set_cpu(cpu, &watchdog_cpus); + return 0; +} + +static void watchdog_nmi_disable(unsigned int cpu) +{ + unsigned int next_cpu = watchdog_next_cpu(cpu); + + /* + * Offlining this cpu will cause the cpu before this one to start + * checking the one after this one. If this cpu just finished checking + * the next cpu and updating hrtimer_interrupts_saved, and then the + * previous cpu checks it within one sample period, it will trigger a + * false positive. Touch the watchdog on the next cpu to prevent it. + */ + if (next_cpu < nr_cpu_ids) + per_cpu(watchdog_nmi_touch, next_cpu) = true; + smp_wmb(); + cpumask_clear_cpu(cpu, &watchdog_cpus); +} +#else static int watchdog_nmi_enable(unsigned int cpu) { return 0; } static void watchdog_nmi_disable(unsigned int cpu) { return; } -#endif /* CONFIG_HARDLOCKUP_DETECTOR */ +#endif /* CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU */ +#endif /* CONFIG_HARDLOCKUP_DETECTOR_NMI */ static struct smp_hotplug_thread watchdog_threads = { .store = &softlockup_watchdog, |