OpenCloudOS-Kernel/include/linux/printk.h

502 lines
14 KiB
C
Raw Normal View History

#ifndef __KERNEL_PRINTK__
#define __KERNEL_PRINTK__
#include <stdarg.h>
#include <linux/init.h>
#include <linux/kern_levels.h>
Add include dependencies to <linux/printk.h>. If <linux/linkage.h> has not been included before <linux/printk.h>, a build error like the below one will result: CC arch/mips/kernel/idle.o In file included from arch/mips/kernel/idle.c:17:0: include/linux/printk.h:109:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:109:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:110:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:110:1: error: expected ‘,’ or ‘;’ before ‘int’ include/linux/printk.h:114:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:114:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:115:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:115:1: error: expected ‘,’ or ‘;’ before ‘int’ include/linux/printk.h:117:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:117:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:118:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:118:1: error: ‘__cold__’ attribute ignored [-Werror=attributes] include/linux/printk.h:118:1: error: expected ‘,’ or ‘;’ before ‘asmlinkage’ include/linux/printk.h:122:1: error: data definition has no type or storage class [-Werror] include/linux/printk.h:122:1: error: type defaults to ‘int’ in declaration of ‘asmlinkage’ [-Werror=implicit-int] include/linux/printk.h:123:1: error: ‘format’ attribute only applies to function types [-Werror=attributes] include/linux/printk.h:123:1: error: ‘__cold__’ attribute ignored [-Werror=attributes] include/linux/printk.h:123:1: error: expected ‘,’ or ‘;’ before ‘int’ In file included from include/linux/kernel.h:14:0, from include/linux/sched.h:15, from arch/mips/kernel/idle.c:18: include/linux/dynamic_debug.h: In function ‘ddebug_dyndbg_module_param_cb’: include/linux/dynamic_debug.h:124:3: error: implicit declaration of function ‘printk’ [-Werror=implicit-function-declaration] Fixed by including <linux/linkage.h>. Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2013-05-21 16:51:10 +08:00
#include <linux/linkage.h>
#include <linux/cache.h>
extern const char linux_banner[];
extern const char linux_proc_banner[];
static inline int printk_get_level(const char *buffer)
{
if (buffer[0] == KERN_SOH_ASCII && buffer[1]) {
switch (buffer[1]) {
case '0' ... '7':
case 'd': /* KERN_DEFAULT */
return buffer[1];
}
}
return 0;
}
static inline const char *printk_skip_level(const char *buffer)
{
if (printk_get_level(buffer))
return buffer + 2;
return buffer;
}
#define CONSOLE_EXT_LOG_MAX 8192
/* printk's without a loglevel use this.. */
#define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT
/* We show everything that is MORE important than this.. */
#define CONSOLE_LOGLEVEL_SILENT 0 /* Mum's the word */
#define CONSOLE_LOGLEVEL_MIN 1 /* Minimum loglevel we let people use */
#define CONSOLE_LOGLEVEL_QUIET 4 /* Shhh ..., when booted with "quiet" */
#define CONSOLE_LOGLEVEL_DEFAULT 7 /* anything MORE serious than KERN_DEBUG */
#define CONSOLE_LOGLEVEL_DEBUG 10 /* issue debug messages */
#define CONSOLE_LOGLEVEL_MOTORMOUTH 15 /* You can't shut this one up */
extern int console_printk[];
#define console_loglevel (console_printk[0])
#define default_message_loglevel (console_printk[1])
#define minimum_console_loglevel (console_printk[2])
#define default_console_loglevel (console_printk[3])
static inline void console_silent(void)
{
console_loglevel = CONSOLE_LOGLEVEL_SILENT;
}
static inline void console_verbose(void)
{
if (console_loglevel)
console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
}
printk: add kernel parameter to control writes to /dev/kmsg Add a "printk.devkmsg" kernel command line parameter which controls how userspace writes into /dev/kmsg. It has three options: * ratelimit - ratelimit logging from userspace. * on - unlimited logging from userspace * off - logging from userspace gets ignored The default setting is to ratelimit the messages written to it. This changes the kernel default setting of "on" to "ratelimit" and we do that because we want to keep userspace spamming /dev/kmsg to sane levels. This is especially moot when a small kernel log buffer wraps around and messages get lost. So the ratelimiting setting should be a sane setting where kernel messages should have a bit higher chance of survival from all the spamming. It additionally does not limit logging to /dev/kmsg while the system is booting if we haven't disabled it on the command line. Furthermore, we can control the logging from a lower priority sysctl interface - kernel.printk_devkmsg. That interface will succeed only if printk.devkmsg *hasn't* been supplied on the command line. If it has, then printk.devkmsg is a one-time setting which remains for the duration of the system lifetime. This "locking" of the setting is to prevent userspace from changing the logging on us through sysctl(2). This patch is based on previous patches from Linus and Steven. [bp@suse.de: fixes] Link: http://lkml.kernel.org/r/20160719072344.GC25563@nazgul.tnic Link: http://lkml.kernel.org/r/20160716061745.15795-3-bp@alien8.de Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Dave Young <dyoung@redhat.com> Cc: Franck Bui <fbui@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-08-03 05:04:07 +08:00
/* strlen("ratelimit") + 1 */
#define DEVKMSG_STR_MAX_SIZE 10
extern char devkmsg_log_str[];
struct ctl_table;
struct va_format {
const char *fmt;
va_list *va;
};
/*
* FW_BUG
* Add this to a message where you are sure the firmware is buggy or behaves
* really stupid or out of spec. Be aware that the responsible BIOS developer
* should be able to fix this issue or at least get a concrete idea of the
* problem by reading your message without the need of looking at the kernel
* code.
*
* Use it for definite and high priority BIOS bugs.
*
* FW_WARN
* Use it for not that clear (e.g. could the kernel messed up things already?)
* and medium priority BIOS bugs.
*
* FW_INFO
* Use this one if you want to tell the user or vendor about something
* suspicious, but generally harmless related to the firmware.
*
* Use it for information or very low priority BIOS bugs.
*/
#define FW_BUG "[Firmware Bug]: "
#define FW_WARN "[Firmware Warn]: "
#define FW_INFO "[Firmware Info]: "
/*
* HW_ERR
* Add this to a message for hardware errors, so that user can report
* it to hardware vendor instead of LKML or software vendor.
*/
#define HW_ERR "[Hardware Error]: "
/*
* DEPRECATED
* Add this to a message whenever you want to warn user space about the use
* of a deprecated aspect of an API so they can stop using it
*/
#define DEPRECATED "[Deprecated]: "
/*
* Dummy printk for disabled debugging statements to use whilst maintaining
* gcc's format checking.
*/
#define no_printk(fmt, ...) \
({ \
do { \
if (0) \
printk(fmt, ##__VA_ARGS__); \
} while (0); \
0; \
})
#ifdef CONFIG_EARLY_PRINTK
extern asmlinkage __printf(1, 2)
void early_printk(const char *fmt, ...);
#else
static inline __printf(1, 2) __cold
void early_printk(const char *s, ...) { }
#endif
printk/nmi: generic solution for safe printk in NMI printk() takes some locks and could not be used a safe way in NMI context. The chance of a deadlock is real especially when printing stacks from all CPUs. This particular problem has been addressed on x86 by the commit a9edc8809328 ("x86/nmi: Perform a safe NMI stack trace on all CPUs"). The patchset brings two big advantages. First, it makes the NMI backtraces safe on all architectures for free. Second, it makes all NMI messages almost safe on all architectures (the temporary buffer is limited. We still should keep the number of messages in NMI context at minimum). Note that there already are several messages printed in NMI context: WARN_ON(in_nmi()), BUG_ON(in_nmi()), anything being printed out from MCE handlers. These are not easy to avoid. This patch reuses most of the code and makes it generic. It is useful for all messages and architectures that support NMI. The alternative printk_func is set when entering and is reseted when leaving NMI context. It queues IRQ work to copy the messages into the main ring buffer in a safe context. __printk_nmi_flush() copies all available messages and reset the buffer. Then we could use a simple cmpxchg operations to get synchronized with writers. There is also used a spinlock to get synchronized with other flushers. We do not longer use seq_buf because it depends on external lock. It would be hard to make all supported operations safe for a lockless use. It would be confusing and error prone to make only some operations safe. The code is put into separate printk/nmi.c as suggested by Steven Rostedt. It needs a per-CPU buffer and is compiled only on architectures that call nmi_enter(). This is achieved by the new HAVE_NMI Kconfig flag. The are MN10300 and Xtensa architectures. We need to clean up NMI handling there first. Let's do it separately. The patch is heavily based on the draft from Peter Zijlstra, see https://lkml.org/lkml/2015/6/10/327 [arnd@arndb.de: printk-nmi: use %zu format string for size_t] [akpm@linux-foundation.org: min_t->min - all types are size_t here] Signed-off-by: Petr Mladek <pmladek@suse.com> Suggested-by: Peter Zijlstra <peterz@infradead.org> Suggested-by: Steven Rostedt <rostedt@goodmis.org> Cc: Jan Kara <jack@suse.cz> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> [arm part] Cc: Daniel Thompson <daniel.thompson@linaro.org> Cc: Jiri Kosina <jkosina@suse.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: David Miller <davem@davemloft.net> Cc: Daniel Thompson <daniel.thompson@linaro.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-21 08:00:33 +08:00
#ifdef CONFIG_PRINTK_NMI
extern void printk_nmi_init(void);
extern void printk_nmi_enter(void);
extern void printk_nmi_exit(void);
extern void printk_nmi_flush(void);
printk/nmi: flush NMI messages on the system panic In NMI context, printk() messages are stored into per-CPU buffers to avoid a possible deadlock. They are normally flushed to the main ring buffer via an IRQ work. But the work is never called when the system calls panic() in the very same NMI handler. This patch tries to flush NMI buffers before the crash dump is generated. In this case it does not risk a double release and bails out when the logbuf_lock is already taken. The aim is to get the messages into the main ring buffer when possible. It makes them better accessible in the vmcore. Then the patch tries to flush the buffers second time when other CPUs are down. It might be more aggressive and reset logbuf_lock. The aim is to get the messages available for the consequent kmsg_dump() and console_flush_on_panic() calls. The patch causes vprintk_emit() to be called even in NMI context again. But it is done via printk_deferred() so that the console handling is skipped. Consoles use internal locks and we could not prevent a deadlock easily. They are explicitly called later when the crash dump is not generated, see console_flush_on_panic(). Signed-off-by: Petr Mladek <pmladek@suse.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Daniel Thompson <daniel.thompson@linaro.org> Cc: David Miller <davem@davemloft.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiri Kosina <jkosina@suse.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <rmk+kernel@arm.linux.org.uk> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-21 08:00:42 +08:00
extern void printk_nmi_flush_on_panic(void);
printk/nmi: generic solution for safe printk in NMI printk() takes some locks and could not be used a safe way in NMI context. The chance of a deadlock is real especially when printing stacks from all CPUs. This particular problem has been addressed on x86 by the commit a9edc8809328 ("x86/nmi: Perform a safe NMI stack trace on all CPUs"). The patchset brings two big advantages. First, it makes the NMI backtraces safe on all architectures for free. Second, it makes all NMI messages almost safe on all architectures (the temporary buffer is limited. We still should keep the number of messages in NMI context at minimum). Note that there already are several messages printed in NMI context: WARN_ON(in_nmi()), BUG_ON(in_nmi()), anything being printed out from MCE handlers. These are not easy to avoid. This patch reuses most of the code and makes it generic. It is useful for all messages and architectures that support NMI. The alternative printk_func is set when entering and is reseted when leaving NMI context. It queues IRQ work to copy the messages into the main ring buffer in a safe context. __printk_nmi_flush() copies all available messages and reset the buffer. Then we could use a simple cmpxchg operations to get synchronized with writers. There is also used a spinlock to get synchronized with other flushers. We do not longer use seq_buf because it depends on external lock. It would be hard to make all supported operations safe for a lockless use. It would be confusing and error prone to make only some operations safe. The code is put into separate printk/nmi.c as suggested by Steven Rostedt. It needs a per-CPU buffer and is compiled only on architectures that call nmi_enter(). This is achieved by the new HAVE_NMI Kconfig flag. The are MN10300 and Xtensa architectures. We need to clean up NMI handling there first. Let's do it separately. The patch is heavily based on the draft from Peter Zijlstra, see https://lkml.org/lkml/2015/6/10/327 [arnd@arndb.de: printk-nmi: use %zu format string for size_t] [akpm@linux-foundation.org: min_t->min - all types are size_t here] Signed-off-by: Petr Mladek <pmladek@suse.com> Suggested-by: Peter Zijlstra <peterz@infradead.org> Suggested-by: Steven Rostedt <rostedt@goodmis.org> Cc: Jan Kara <jack@suse.cz> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> [arm part] Cc: Daniel Thompson <daniel.thompson@linaro.org> Cc: Jiri Kosina <jkosina@suse.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: David Miller <davem@davemloft.net> Cc: Daniel Thompson <daniel.thompson@linaro.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-21 08:00:33 +08:00
#else
static inline void printk_nmi_init(void) { }
static inline void printk_nmi_enter(void) { }
static inline void printk_nmi_exit(void) { }
static inline void printk_nmi_flush(void) { }
printk/nmi: flush NMI messages on the system panic In NMI context, printk() messages are stored into per-CPU buffers to avoid a possible deadlock. They are normally flushed to the main ring buffer via an IRQ work. But the work is never called when the system calls panic() in the very same NMI handler. This patch tries to flush NMI buffers before the crash dump is generated. In this case it does not risk a double release and bails out when the logbuf_lock is already taken. The aim is to get the messages into the main ring buffer when possible. It makes them better accessible in the vmcore. Then the patch tries to flush the buffers second time when other CPUs are down. It might be more aggressive and reset logbuf_lock. The aim is to get the messages available for the consequent kmsg_dump() and console_flush_on_panic() calls. The patch causes vprintk_emit() to be called even in NMI context again. But it is done via printk_deferred() so that the console handling is skipped. Consoles use internal locks and we could not prevent a deadlock easily. They are explicitly called later when the crash dump is not generated, see console_flush_on_panic(). Signed-off-by: Petr Mladek <pmladek@suse.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Daniel Thompson <daniel.thompson@linaro.org> Cc: David Miller <davem@davemloft.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiri Kosina <jkosina@suse.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Russell King <rmk+kernel@arm.linux.org.uk> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-21 08:00:42 +08:00
static inline void printk_nmi_flush_on_panic(void) { }
printk/nmi: generic solution for safe printk in NMI printk() takes some locks and could not be used a safe way in NMI context. The chance of a deadlock is real especially when printing stacks from all CPUs. This particular problem has been addressed on x86 by the commit a9edc8809328 ("x86/nmi: Perform a safe NMI stack trace on all CPUs"). The patchset brings two big advantages. First, it makes the NMI backtraces safe on all architectures for free. Second, it makes all NMI messages almost safe on all architectures (the temporary buffer is limited. We still should keep the number of messages in NMI context at minimum). Note that there already are several messages printed in NMI context: WARN_ON(in_nmi()), BUG_ON(in_nmi()), anything being printed out from MCE handlers. These are not easy to avoid. This patch reuses most of the code and makes it generic. It is useful for all messages and architectures that support NMI. The alternative printk_func is set when entering and is reseted when leaving NMI context. It queues IRQ work to copy the messages into the main ring buffer in a safe context. __printk_nmi_flush() copies all available messages and reset the buffer. Then we could use a simple cmpxchg operations to get synchronized with writers. There is also used a spinlock to get synchronized with other flushers. We do not longer use seq_buf because it depends on external lock. It would be hard to make all supported operations safe for a lockless use. It would be confusing and error prone to make only some operations safe. The code is put into separate printk/nmi.c as suggested by Steven Rostedt. It needs a per-CPU buffer and is compiled only on architectures that call nmi_enter(). This is achieved by the new HAVE_NMI Kconfig flag. The are MN10300 and Xtensa architectures. We need to clean up NMI handling there first. Let's do it separately. The patch is heavily based on the draft from Peter Zijlstra, see https://lkml.org/lkml/2015/6/10/327 [arnd@arndb.de: printk-nmi: use %zu format string for size_t] [akpm@linux-foundation.org: min_t->min - all types are size_t here] Signed-off-by: Petr Mladek <pmladek@suse.com> Suggested-by: Peter Zijlstra <peterz@infradead.org> Suggested-by: Steven Rostedt <rostedt@goodmis.org> Cc: Jan Kara <jack@suse.cz> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> [arm part] Cc: Daniel Thompson <daniel.thompson@linaro.org> Cc: Jiri Kosina <jkosina@suse.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: David Miller <davem@davemloft.net> Cc: Daniel Thompson <daniel.thompson@linaro.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-21 08:00:33 +08:00
#endif /* PRINTK_NMI */
#ifdef CONFIG_PRINTK
printk: convert byte-buffer to variable-length record buffer - Record-based stream instead of the traditional byte stream buffer. All records carry a 64 bit timestamp, the syslog facility and priority in the record header. - Records consume almost the same amount, sometimes less memory than the traditional byte stream buffer (if printk_time is enabled). The record header is 16 bytes long, plus some padding bytes at the end if needed. The byte-stream buffer needed 3 chars for the syslog prefix, 15 char for the timestamp and a newline. - Buffer management is based on message sequence numbers. When records need to be discarded, the reading heads move on to the next full record. Unlike the byte-stream buffer, no old logged lines get truncated or partly overwritten by new ones. Sequence numbers also allow consumers of the log stream to get notified if any message in the stream they are about to read gets discarded during the time of reading. - Better buffered IO support for KERN_CONT continuation lines, when printk() is called multiple times for a single line. The use of KERN_CONT is now mandatory to use continuation; a few places in the kernel need trivial fixes here. The buffering could possibly be extended to per-cpu variables to allow better thread-safety for multiple printk() invocations for a single line. - Full-featured syslog facility value support. Different facilities can tag their messages. All userspace-injected messages enforce a facility value > 0 now, to be able to reliably distinguish them from the kernel-generated messages. Independent subsystems like a baseband processor running its own firmware, or a kernel-related userspace process can use their own unique facility values. Multiple independent log streams can co-exist that way in the same buffer. All share the same global sequence number counter to ensure proper ordering (and interleaving) and to allow the consumers of the log to reliably correlate the events from different facilities. Tested-by: William Douglas <william.douglas@intel.com> Signed-off-by: Kay Sievers <kay@vrfy.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-05-03 08:29:13 +08:00
asmlinkage __printf(5, 0)
int vprintk_emit(int facility, int level,
const char *dict, size_t dictlen,
const char *fmt, va_list args);
asmlinkage __printf(1, 0)
int vprintk(const char *fmt, va_list args);
printk: convert byte-buffer to variable-length record buffer - Record-based stream instead of the traditional byte stream buffer. All records carry a 64 bit timestamp, the syslog facility and priority in the record header. - Records consume almost the same amount, sometimes less memory than the traditional byte stream buffer (if printk_time is enabled). The record header is 16 bytes long, plus some padding bytes at the end if needed. The byte-stream buffer needed 3 chars for the syslog prefix, 15 char for the timestamp and a newline. - Buffer management is based on message sequence numbers. When records need to be discarded, the reading heads move on to the next full record. Unlike the byte-stream buffer, no old logged lines get truncated or partly overwritten by new ones. Sequence numbers also allow consumers of the log stream to get notified if any message in the stream they are about to read gets discarded during the time of reading. - Better buffered IO support for KERN_CONT continuation lines, when printk() is called multiple times for a single line. The use of KERN_CONT is now mandatory to use continuation; a few places in the kernel need trivial fixes here. The buffering could possibly be extended to per-cpu variables to allow better thread-safety for multiple printk() invocations for a single line. - Full-featured syslog facility value support. Different facilities can tag their messages. All userspace-injected messages enforce a facility value > 0 now, to be able to reliably distinguish them from the kernel-generated messages. Independent subsystems like a baseband processor running its own firmware, or a kernel-related userspace process can use their own unique facility values. Multiple independent log streams can co-exist that way in the same buffer. All share the same global sequence number counter to ensure proper ordering (and interleaving) and to allow the consumers of the log to reliably correlate the events from different facilities. Tested-by: William Douglas <william.douglas@intel.com> Signed-off-by: Kay Sievers <kay@vrfy.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-05-03 08:29:13 +08:00
asmlinkage __printf(5, 6) __cold
int printk_emit(int facility, int level,
const char *dict, size_t dictlen,
const char *fmt, ...);
printk: convert byte-buffer to variable-length record buffer - Record-based stream instead of the traditional byte stream buffer. All records carry a 64 bit timestamp, the syslog facility and priority in the record header. - Records consume almost the same amount, sometimes less memory than the traditional byte stream buffer (if printk_time is enabled). The record header is 16 bytes long, plus some padding bytes at the end if needed. The byte-stream buffer needed 3 chars for the syslog prefix, 15 char for the timestamp and a newline. - Buffer management is based on message sequence numbers. When records need to be discarded, the reading heads move on to the next full record. Unlike the byte-stream buffer, no old logged lines get truncated or partly overwritten by new ones. Sequence numbers also allow consumers of the log stream to get notified if any message in the stream they are about to read gets discarded during the time of reading. - Better buffered IO support for KERN_CONT continuation lines, when printk() is called multiple times for a single line. The use of KERN_CONT is now mandatory to use continuation; a few places in the kernel need trivial fixes here. The buffering could possibly be extended to per-cpu variables to allow better thread-safety for multiple printk() invocations for a single line. - Full-featured syslog facility value support. Different facilities can tag their messages. All userspace-injected messages enforce a facility value > 0 now, to be able to reliably distinguish them from the kernel-generated messages. Independent subsystems like a baseband processor running its own firmware, or a kernel-related userspace process can use their own unique facility values. Multiple independent log streams can co-exist that way in the same buffer. All share the same global sequence number counter to ensure proper ordering (and interleaving) and to allow the consumers of the log to reliably correlate the events from different facilities. Tested-by: William Douglas <william.douglas@intel.com> Signed-off-by: Kay Sievers <kay@vrfy.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-05-03 08:29:13 +08:00
asmlinkage __printf(1, 2) __cold
int printk(const char *fmt, ...);
/*
* Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ !
*/
__printf(1, 2) __cold int printk_deferred(const char *fmt, ...);
/*
* Please don't use printk_ratelimit(), because it shares ratelimiting state
* with all other unrelated printk_ratelimit() callsites. Instead use
* printk_ratelimited() or plain old __ratelimit().
*/
extern int __printk_ratelimit(const char *func);
#define printk_ratelimit() __printk_ratelimit(__func__)
extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
unsigned int interval_msec);
extern int printk_delay_msec;
extern int dmesg_restrict;
kptr_restrict for hiding kernel pointers from unprivileged users Add the %pK printk format specifier and the /proc/sys/kernel/kptr_restrict sysctl. The %pK format specifier is designed to hide exposed kernel pointers, specifically via /proc interfaces. Exposing these pointers provides an easy target for kernel write vulnerabilities, since they reveal the locations of writable structures containing easily triggerable function pointers. The behavior of %pK depends on the kptr_restrict sysctl. If kptr_restrict is set to 0, no deviation from the standard %p behavior occurs. If kptr_restrict is set to 1, the default, if the current user (intended to be a reader via seq_printf(), etc.) does not have CAP_SYSLOG (currently in the LSM tree), kernel pointers using %pK are printed as 0's. If kptr_restrict is set to 2, kernel pointers using %pK are printed as 0's regardless of privileges. Replacing with 0's was chosen over the default "(null)", which cannot be parsed by userland %p, which expects "(nil)". [akpm@linux-foundation.org: check for IRQ context when !kptr_restrict, save an indent level, s/WARN/WARN_ONCE/] [akpm@linux-foundation.org: coding-style fixup] [randy.dunlap@oracle.com: fix kernel/sysctl.c warning] Signed-off-by: Dan Rosenberg <drosenberg@vsecurity.com> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: James Morris <jmorris@namei.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Thomas Graf <tgraf@infradead.org> Cc: Eugene Teo <eugeneteo@kernel.org> Cc: Kees Cook <kees.cook@canonical.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: David S. Miller <davem@davemloft.net> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Eric Paris <eparis@parisplace.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-13 08:59:41 +08:00
extern int kptr_restrict;
printk: add kernel parameter to control writes to /dev/kmsg Add a "printk.devkmsg" kernel command line parameter which controls how userspace writes into /dev/kmsg. It has three options: * ratelimit - ratelimit logging from userspace. * on - unlimited logging from userspace * off - logging from userspace gets ignored The default setting is to ratelimit the messages written to it. This changes the kernel default setting of "on" to "ratelimit" and we do that because we want to keep userspace spamming /dev/kmsg to sane levels. This is especially moot when a small kernel log buffer wraps around and messages get lost. So the ratelimiting setting should be a sane setting where kernel messages should have a bit higher chance of survival from all the spamming. It additionally does not limit logging to /dev/kmsg while the system is booting if we haven't disabled it on the command line. Furthermore, we can control the logging from a lower priority sysctl interface - kernel.printk_devkmsg. That interface will succeed only if printk.devkmsg *hasn't* been supplied on the command line. If it has, then printk.devkmsg is a one-time setting which remains for the duration of the system lifetime. This "locking" of the setting is to prevent userspace from changing the logging on us through sysctl(2). This patch is based on previous patches from Linus and Steven. [bp@suse.de: fixes] Link: http://lkml.kernel.org/r/20160719072344.GC25563@nazgul.tnic Link: http://lkml.kernel.org/r/20160716061745.15795-3-bp@alien8.de Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Dave Young <dyoung@redhat.com> Cc: Franck Bui <fbui@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-08-03 05:04:07 +08:00
extern int
devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void __user *buf,
size_t *lenp, loff_t *ppos);
extern void wake_up_klogd(void);
char *log_buf_addr_get(void);
u32 log_buf_len_get(void);
void log_buf_kexec_setup(void);
void __init setup_log_buf(int early);
__printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...);
dump_stack: consolidate dump_stack() implementations and unify their behaviors Both dump_stack() and show_stack() are currently implemented by each architecture. show_stack(NULL, NULL) dumps the backtrace for the current task as does dump_stack(). On some archs, dump_stack() prints extra information - pid, utsname and so on - in addition to the backtrace while the two are identical on other archs. The usages in arch-independent code of the two functions indicate show_stack(NULL, NULL) should print out bare backtrace while dump_stack() is used for debugging purposes when something went wrong, so it does make sense to print additional information on the task which triggered dump_stack(). There's no reason to require archs to implement two separate but mostly identical functions. It leads to unnecessary subtle information. This patch expands the dummy fallback dump_stack() implementation in lib/dump_stack.c such that it prints out debug information (taken from x86) and invokes show_stack(NULL, NULL) and drops arch-specific dump_stack() implementations in all archs except blackfin. Blackfin's dump_stack() does something wonky that I don't understand. Debug information can be printed separately by calling dump_stack_print_info() so that arch-specific dump_stack() implementation can still emit the same debug information. This is used in blackfin. This patch brings the following behavior changes. * On some archs, an extra level in backtrace for show_stack() could be printed. This is because the top frame was determined in dump_stack() on those archs while generic dump_stack() can't do that reliably. It can be compensated by inlining dump_stack() but not sure whether that'd be necessary. * Most archs didn't use to print debug info on dump_stack(). They do now. An example WARN dump follows. WARNING: at kernel/workqueue.c:4841 init_workqueues+0x35/0x505() Hardware name: empty Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #9 0000000000000009 ffff88007c861e08 ffffffff81c614dc ffff88007c861e48 ffffffff8108f50f ffffffff82228240 0000000000000040 ffffffff8234a03c 0000000000000000 0000000000000000 0000000000000000 ffff88007c861e58 Call Trace: [<ffffffff81c614dc>] dump_stack+0x19/0x1b [<ffffffff8108f50f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff8108f56a>] warn_slowpath_null+0x1a/0x20 [<ffffffff8234a071>] init_workqueues+0x35/0x505 ... v2: CPU number added to the generic debug info as requested by s390 folks and dropped the s390 specific dump_stack(). This loses %ksp from the debug message which the maintainers think isn't important enough to keep the s390-specific dump_stack() implementation. dump_stack_print_info() is moved to kernel/printk.c from lib/dump_stack.c. Because linkage is per objecct file, dump_stack_print_info() living in the same lib file as generic dump_stack() means that archs which implement custom dump_stack() - at this point, only blackfin - can't use dump_stack_print_info() as that will bring in the generic version of dump_stack() too. v1 The v1 patch broke build on blackfin due to this issue. The build breakage was reported by Fengguang Wu. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Vineet Gupta <vgupta@synopsys.com> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: Vineet Gupta <vgupta@synopsys.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> [s390 bits] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Sam Ravnborg <sam@ravnborg.org> Acked-by: Richard Kuo <rkuo@codeaurora.org> [hexagon bits] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:12 +08:00
void dump_stack_print_info(const char *log_lvl);
dump_stack: unify debug information printed by show_regs() show_regs() is inherently arch-dependent but it does make sense to print generic debug information and some archs already do albeit in slightly different forms. This patch introduces a generic function to print debug information from show_regs() so that different archs print out the same information and it's much easier to modify what's printed. show_regs_print_info() prints out the same debug info as dump_stack() does plus task and thread_info pointers. * Archs which didn't print debug info now do. alpha, arc, blackfin, c6x, cris, frv, h8300, hexagon, ia64, m32r, metag, microblaze, mn10300, openrisc, parisc, score, sh64, sparc, um, xtensa * Already prints debug info. Replaced with show_regs_print_info(). The printed information is superset of what used to be there. arm, arm64, avr32, mips, powerpc, sh32, tile, unicore32, x86 * s390 is special in that it used to print arch-specific information along with generic debug info. Heiko and Martin think that the arch-specific extra isn't worth keeping s390 specfic implementation. Converted to use the generic version. Note that now all archs print the debug info before actual register dumps. An example BUG() dump follows. kernel BUG at /work/os/work/kernel/workqueue.c:4841! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #7 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 task: ffff88007c85e040 ti: ffff88007c860000 task.ti: ffff88007c860000 RIP: 0010:[<ffffffff8234a07e>] [<ffffffff8234a07e>] init_workqueues+0x4/0x6 RSP: 0000:ffff88007c861ec8 EFLAGS: 00010246 RAX: ffff88007c861fd8 RBX: ffffffff824466a8 RCX: 0000000000000001 RDX: 0000000000000046 RSI: 0000000000000001 RDI: ffffffff8234a07a RBP: ffff88007c861ec8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff8234a07a R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffff88015f7ff000 CR3: 00000000021f1000 CR4: 00000000000007f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: ffff88007c861ef8 ffffffff81000312 ffffffff824466a8 ffff88007c85e650 0000000000000003 0000000000000000 ffff88007c861f38 ffffffff82335e5d ffff88007c862080 ffffffff8223d8c0 ffff88007c862080 ffffffff81c47760 Call Trace: [<ffffffff81000312>] do_one_initcall+0x122/0x170 [<ffffffff82335e5d>] kernel_init_freeable+0x9b/0x1c8 [<ffffffff81c47760>] ? rest_init+0x140/0x140 [<ffffffff81c4776e>] kernel_init+0xe/0xf0 [<ffffffff81c6be9c>] ret_from_fork+0x7c/0xb0 [<ffffffff81c47760>] ? rest_init+0x140/0x140 ... v2: Typo fix in x86-32. v3: CPU number dropped from show_regs_print_info() as dump_stack_print_info() has been updated to print it. s390 specific implementation dropped as requested by s390 maintainers. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Sam Ravnborg <sam@ravnborg.org> Acked-by: Chris Metcalf <cmetcalf@tilera.com> [tile bits] Acked-by: Richard Kuo <rkuo@codeaurora.org> [hexagon bits] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:17 +08:00
void show_regs_print_info(const char *log_lvl);
#else
static inline __printf(1, 0)
int vprintk(const char *s, va_list args)
{
return 0;
}
static inline __printf(1, 2) __cold
int printk(const char *s, ...)
{
return 0;
}
static inline __printf(1, 2) __cold
int printk_deferred(const char *s, ...)
{
return 0;
}
static inline int printk_ratelimit(void)
{
return 0;
}
static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies,
unsigned int interval_msec)
{
return false;
}
static inline void wake_up_klogd(void)
{
}
static inline char *log_buf_addr_get(void)
{
return NULL;
}
static inline u32 log_buf_len_get(void)
{
return 0;
}
static inline void log_buf_kexec_setup(void)
{
}
static inline void setup_log_buf(int early)
{
}
dump_stack: consolidate dump_stack() implementations and unify their behaviors Both dump_stack() and show_stack() are currently implemented by each architecture. show_stack(NULL, NULL) dumps the backtrace for the current task as does dump_stack(). On some archs, dump_stack() prints extra information - pid, utsname and so on - in addition to the backtrace while the two are identical on other archs. The usages in arch-independent code of the two functions indicate show_stack(NULL, NULL) should print out bare backtrace while dump_stack() is used for debugging purposes when something went wrong, so it does make sense to print additional information on the task which triggered dump_stack(). There's no reason to require archs to implement two separate but mostly identical functions. It leads to unnecessary subtle information. This patch expands the dummy fallback dump_stack() implementation in lib/dump_stack.c such that it prints out debug information (taken from x86) and invokes show_stack(NULL, NULL) and drops arch-specific dump_stack() implementations in all archs except blackfin. Blackfin's dump_stack() does something wonky that I don't understand. Debug information can be printed separately by calling dump_stack_print_info() so that arch-specific dump_stack() implementation can still emit the same debug information. This is used in blackfin. This patch brings the following behavior changes. * On some archs, an extra level in backtrace for show_stack() could be printed. This is because the top frame was determined in dump_stack() on those archs while generic dump_stack() can't do that reliably. It can be compensated by inlining dump_stack() but not sure whether that'd be necessary. * Most archs didn't use to print debug info on dump_stack(). They do now. An example WARN dump follows. WARNING: at kernel/workqueue.c:4841 init_workqueues+0x35/0x505() Hardware name: empty Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #9 0000000000000009 ffff88007c861e08 ffffffff81c614dc ffff88007c861e48 ffffffff8108f50f ffffffff82228240 0000000000000040 ffffffff8234a03c 0000000000000000 0000000000000000 0000000000000000 ffff88007c861e58 Call Trace: [<ffffffff81c614dc>] dump_stack+0x19/0x1b [<ffffffff8108f50f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff8108f56a>] warn_slowpath_null+0x1a/0x20 [<ffffffff8234a071>] init_workqueues+0x35/0x505 ... v2: CPU number added to the generic debug info as requested by s390 folks and dropped the s390 specific dump_stack(). This loses %ksp from the debug message which the maintainers think isn't important enough to keep the s390-specific dump_stack() implementation. dump_stack_print_info() is moved to kernel/printk.c from lib/dump_stack.c. Because linkage is per objecct file, dump_stack_print_info() living in the same lib file as generic dump_stack() means that archs which implement custom dump_stack() - at this point, only blackfin - can't use dump_stack_print_info() as that will bring in the generic version of dump_stack() too. v1 The v1 patch broke build on blackfin due to this issue. The build breakage was reported by Fengguang Wu. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Vineet Gupta <vgupta@synopsys.com> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: Vineet Gupta <vgupta@synopsys.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> [s390 bits] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Sam Ravnborg <sam@ravnborg.org> Acked-by: Richard Kuo <rkuo@codeaurora.org> [hexagon bits] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:12 +08:00
static inline __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...)
dump_stack: implement arch-specific hardware description in task dumps x86 and ia64 can acquire extra hardware identification information from DMI and print it along with task dumps; however, the usage isn't consistent. * x86 show_regs() collects vendor, product and board strings and print them out with PID, comm and utsname. Some of the information is printed again later in the same dump. * warn_slowpath_common() explicitly accesses the DMI board and prints it out with "Hardware name:" label. This applies to both x86 and ia64 but is irrelevant on all other archs. * ia64 doesn't show DMI information on other non-WARN dumps. This patch introduces arch-specific hardware description used by dump_stack(). It can be set by calling dump_stack_set_arch_desc() during boot and, if exists, printed out in a separate line with "Hardware name:" label. dmi_set_dump_stack_arch_desc() is added which sets arch-specific description from DMI data. It uses dmi_ids_string[] which is set from dmi_present() used for DMI debug message. It is superset of the information x86 show_regs() is using. The function is called from x86 and ia64 boot code right after dmi_scan_machine(). This makes the explicit DMI handling in warn_slowpath_common() unnecessary. Removed. show_regs() isn't yet converted to use generic debug information printing and this patch doesn't remove the duplicate DMI handling in x86 show_regs(). The next patch will unify show_regs() handling and remove the duplication. An example WARN dump follows. WARNING: at kernel/workqueue.c:4841 init_workqueues+0x35/0x505() Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #3 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 0000000000000009 ffff88007c861e08 ffffffff81c614dc ffff88007c861e48 ffffffff8108f500 ffffffff82228240 0000000000000040 ffffffff8234a08e 0000000000000000 0000000000000000 0000000000000000 ffff88007c861e58 Call Trace: [<ffffffff81c614dc>] dump_stack+0x19/0x1b [<ffffffff8108f500>] warn_slowpath_common+0x70/0xa0 [<ffffffff8108f54a>] warn_slowpath_null+0x1a/0x20 [<ffffffff8234a0c3>] init_workqueues+0x35/0x505 ... v2: Use the same string as the debug message from dmi_present() which also contains BIOS information. Move hardware name into its own line as warn_slowpath_common() did. This change was suggested by Bjorn Helgaas. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: David S. Miller <davem@davemloft.net> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:15 +08:00
{
}
dump_stack: consolidate dump_stack() implementations and unify their behaviors Both dump_stack() and show_stack() are currently implemented by each architecture. show_stack(NULL, NULL) dumps the backtrace for the current task as does dump_stack(). On some archs, dump_stack() prints extra information - pid, utsname and so on - in addition to the backtrace while the two are identical on other archs. The usages in arch-independent code of the two functions indicate show_stack(NULL, NULL) should print out bare backtrace while dump_stack() is used for debugging purposes when something went wrong, so it does make sense to print additional information on the task which triggered dump_stack(). There's no reason to require archs to implement two separate but mostly identical functions. It leads to unnecessary subtle information. This patch expands the dummy fallback dump_stack() implementation in lib/dump_stack.c such that it prints out debug information (taken from x86) and invokes show_stack(NULL, NULL) and drops arch-specific dump_stack() implementations in all archs except blackfin. Blackfin's dump_stack() does something wonky that I don't understand. Debug information can be printed separately by calling dump_stack_print_info() so that arch-specific dump_stack() implementation can still emit the same debug information. This is used in blackfin. This patch brings the following behavior changes. * On some archs, an extra level in backtrace for show_stack() could be printed. This is because the top frame was determined in dump_stack() on those archs while generic dump_stack() can't do that reliably. It can be compensated by inlining dump_stack() but not sure whether that'd be necessary. * Most archs didn't use to print debug info on dump_stack(). They do now. An example WARN dump follows. WARNING: at kernel/workqueue.c:4841 init_workqueues+0x35/0x505() Hardware name: empty Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #9 0000000000000009 ffff88007c861e08 ffffffff81c614dc ffff88007c861e48 ffffffff8108f50f ffffffff82228240 0000000000000040 ffffffff8234a03c 0000000000000000 0000000000000000 0000000000000000 ffff88007c861e58 Call Trace: [<ffffffff81c614dc>] dump_stack+0x19/0x1b [<ffffffff8108f50f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff8108f56a>] warn_slowpath_null+0x1a/0x20 [<ffffffff8234a071>] init_workqueues+0x35/0x505 ... v2: CPU number added to the generic debug info as requested by s390 folks and dropped the s390 specific dump_stack(). This loses %ksp from the debug message which the maintainers think isn't important enough to keep the s390-specific dump_stack() implementation. dump_stack_print_info() is moved to kernel/printk.c from lib/dump_stack.c. Because linkage is per objecct file, dump_stack_print_info() living in the same lib file as generic dump_stack() means that archs which implement custom dump_stack() - at this point, only blackfin - can't use dump_stack_print_info() as that will bring in the generic version of dump_stack() too. v1 The v1 patch broke build on blackfin due to this issue. The build breakage was reported by Fengguang Wu. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Vineet Gupta <vgupta@synopsys.com> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: Vineet Gupta <vgupta@synopsys.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> [s390 bits] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Sam Ravnborg <sam@ravnborg.org> Acked-by: Richard Kuo <rkuo@codeaurora.org> [hexagon bits] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:12 +08:00
static inline void dump_stack_print_info(const char *log_lvl)
{
}
dump_stack: unify debug information printed by show_regs() show_regs() is inherently arch-dependent but it does make sense to print generic debug information and some archs already do albeit in slightly different forms. This patch introduces a generic function to print debug information from show_regs() so that different archs print out the same information and it's much easier to modify what's printed. show_regs_print_info() prints out the same debug info as dump_stack() does plus task and thread_info pointers. * Archs which didn't print debug info now do. alpha, arc, blackfin, c6x, cris, frv, h8300, hexagon, ia64, m32r, metag, microblaze, mn10300, openrisc, parisc, score, sh64, sparc, um, xtensa * Already prints debug info. Replaced with show_regs_print_info(). The printed information is superset of what used to be there. arm, arm64, avr32, mips, powerpc, sh32, tile, unicore32, x86 * s390 is special in that it used to print arch-specific information along with generic debug info. Heiko and Martin think that the arch-specific extra isn't worth keeping s390 specfic implementation. Converted to use the generic version. Note that now all archs print the debug info before actual register dumps. An example BUG() dump follows. kernel BUG at /work/os/work/kernel/workqueue.c:4841! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #7 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 task: ffff88007c85e040 ti: ffff88007c860000 task.ti: ffff88007c860000 RIP: 0010:[<ffffffff8234a07e>] [<ffffffff8234a07e>] init_workqueues+0x4/0x6 RSP: 0000:ffff88007c861ec8 EFLAGS: 00010246 RAX: ffff88007c861fd8 RBX: ffffffff824466a8 RCX: 0000000000000001 RDX: 0000000000000046 RSI: 0000000000000001 RDI: ffffffff8234a07a RBP: ffff88007c861ec8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff8234a07a R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffff88015f7ff000 CR3: 00000000021f1000 CR4: 00000000000007f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: ffff88007c861ef8 ffffffff81000312 ffffffff824466a8 ffff88007c85e650 0000000000000003 0000000000000000 ffff88007c861f38 ffffffff82335e5d ffff88007c862080 ffffffff8223d8c0 ffff88007c862080 ffffffff81c47760 Call Trace: [<ffffffff81000312>] do_one_initcall+0x122/0x170 [<ffffffff82335e5d>] kernel_init_freeable+0x9b/0x1c8 [<ffffffff81c47760>] ? rest_init+0x140/0x140 [<ffffffff81c4776e>] kernel_init+0xe/0xf0 [<ffffffff81c6be9c>] ret_from_fork+0x7c/0xb0 [<ffffffff81c47760>] ? rest_init+0x140/0x140 ... v2: Typo fix in x86-32. v3: CPU number dropped from show_regs_print_info() as dump_stack_print_info() has been updated to print it. s390 specific implementation dropped as requested by s390 maintainers. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Sam Ravnborg <sam@ravnborg.org> Acked-by: Chris Metcalf <cmetcalf@tilera.com> [tile bits] Acked-by: Richard Kuo <rkuo@codeaurora.org> [hexagon bits] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:27:17 +08:00
static inline void show_regs_print_info(const char *log_lvl)
{
}
#endif
extern asmlinkage void dump_stack(void) __cold;
#ifndef pr_fmt
#define pr_fmt(fmt) fmt
#endif
/*
* These can be used to print at the various log levels.
* All of these will print unconditionally, although note that pr_debug()
* and other debug macros are compiled out unless either DEBUG is defined
* or CONFIG_DYNAMIC_DEBUG is set.
*/
#define pr_emerg(fmt, ...) \
printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
#define pr_alert(fmt, ...) \
printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_crit(fmt, ...) \
printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_err(fmt, ...) \
printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
#define pr_warning(fmt, ...) \
printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
#define pr_warn pr_warning
#define pr_notice(fmt, ...) \
printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
#define pr_info(fmt, ...) \
printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
/*
* Like KERN_CONT, pr_cont() should only be used when continuing
* a line with no newline ('\n') enclosed. Otherwise it defaults
* back to KERN_DEFAULT.
*/
#define pr_cont(fmt, ...) \
printk(KERN_CONT fmt, ##__VA_ARGS__)
/* pr_devel() should produce zero code unless DEBUG is defined */
#ifdef DEBUG
#define pr_devel(fmt, ...) \
printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_devel(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
/* If you are writing a driver, please use dev_dbg instead */
#if defined(CONFIG_DYNAMIC_DEBUG)
#include <linux/dynamic_debug.h>
/* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */
#define pr_debug(fmt, ...) \
dynamic_pr_debug(fmt, ##__VA_ARGS__)
#elif defined(DEBUG)
#define pr_debug(fmt, ...) \
printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_debug(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
/*
* Print a one-time message (analogous to WARN_ONCE() et al):
*/
#ifdef CONFIG_PRINTK
#define printk_once(fmt, ...) \
({ \
static bool __print_once __read_mostly; \
bool __ret_print_once = !__print_once; \
\
if (!__print_once) { \
__print_once = true; \
printk(fmt, ##__VA_ARGS__); \
} \
unlikely(__ret_print_once); \
})
#define printk_deferred_once(fmt, ...) \
({ \
static bool __print_once __read_mostly; \
bool __ret_print_once = !__print_once; \
\
if (!__print_once) { \
__print_once = true; \
printk_deferred(fmt, ##__VA_ARGS__); \
} \
unlikely(__ret_print_once); \
})
#else
#define printk_once(fmt, ...) \
no_printk(fmt, ##__VA_ARGS__)
#define printk_deferred_once(fmt, ...) \
no_printk(fmt, ##__VA_ARGS__)
#endif
#define pr_emerg_once(fmt, ...) \
printk_once(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
#define pr_alert_once(fmt, ...) \
printk_once(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_crit_once(fmt, ...) \
printk_once(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_err_once(fmt, ...) \
printk_once(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
#define pr_warn_once(fmt, ...) \
printk_once(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
#define pr_notice_once(fmt, ...) \
printk_once(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
#define pr_info_once(fmt, ...) \
printk_once(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
#define pr_cont_once(fmt, ...) \
printk_once(KERN_CONT pr_fmt(fmt), ##__VA_ARGS__)
#if defined(DEBUG)
#define pr_devel_once(fmt, ...) \
printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_devel_once(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
/* If you are writing a driver, please use dev_dbg instead */
#if defined(DEBUG)
#define pr_debug_once(fmt, ...) \
printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_debug_once(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
/*
* ratelimited messages with local ratelimit_state,
* no local ratelimit_state used in the !PRINTK case
*/
#ifdef CONFIG_PRINTK
#define printk_ratelimited(fmt, ...) \
({ \
static DEFINE_RATELIMIT_STATE(_rs, \
DEFAULT_RATELIMIT_INTERVAL, \
DEFAULT_RATELIMIT_BURST); \
\
if (__ratelimit(&_rs)) \
printk(fmt, ##__VA_ARGS__); \
})
#else
#define printk_ratelimited(fmt, ...) \
no_printk(fmt, ##__VA_ARGS__)
#endif
#define pr_emerg_ratelimited(fmt, ...) \
printk_ratelimited(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
#define pr_alert_ratelimited(fmt, ...) \
printk_ratelimited(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_crit_ratelimited(fmt, ...) \
printk_ratelimited(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
#define pr_err_ratelimited(fmt, ...) \
printk_ratelimited(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
#define pr_warn_ratelimited(fmt, ...) \
printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
#define pr_notice_ratelimited(fmt, ...) \
printk_ratelimited(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
#define pr_info_ratelimited(fmt, ...) \
printk_ratelimited(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
/* no pr_cont_ratelimited, don't do that... */
#if defined(DEBUG)
#define pr_devel_ratelimited(fmt, ...) \
printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_devel_ratelimited(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
/* If you are writing a driver, please use dev_dbg instead */
#if defined(CONFIG_DYNAMIC_DEBUG)
/* descriptor check is first to prevent flooding with "callbacks suppressed" */
#define pr_debug_ratelimited(fmt, ...) \
do { \
static DEFINE_RATELIMIT_STATE(_rs, \
DEFAULT_RATELIMIT_INTERVAL, \
DEFAULT_RATELIMIT_BURST); \
DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, pr_fmt(fmt)); \
if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \
__ratelimit(&_rs)) \
__dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__); \
} while (0)
#elif defined(DEBUG)
#define pr_debug_ratelimited(fmt, ...) \
printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#else
#define pr_debug_ratelimited(fmt, ...) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
#endif
kmsg: export printk records to the /dev/kmsg interface Support for multiple concurrent readers of /dev/kmsg, with read(), seek(), poll() support. Output of message sequence numbers, to allow userspace log consumers to reliably reconnect and reconstruct their state at any given time. After open("/dev/kmsg"), read() always returns *all* buffered records. If only future messages should be read, SEEK_END can be used. In case records get overwritten while /dev/kmsg is held open, or records get faster overwritten than they are read, the next read() will return -EPIPE and the current reading position gets updated to the next available record. The passed sequence numbers allow the log consumer to calculate the amount of lost messages. [root@mop ~]# cat /dev/kmsg 5,0,0;Linux version 3.4.0-rc1+ (kay@mop) (gcc version 4.7.0 20120315 ... 6,159,423091;ACPI: PCI Root Bridge [PCI0] (domain 0000 [bus 00-ff]) 7,160,424069;pci_root PNP0A03:00: host bridge window [io 0x0000-0x0cf7] (ignored) SUBSYSTEM=acpi DEVICE=+acpi:PNP0A03:00 6,339,5140900;NET: Registered protocol family 10 30,340,5690716;udevd[80]: starting version 181 6,341,6081421;FDC 0 is a S82078B 6,345,6154686;microcode: CPU0 sig=0x623, pf=0x0, revision=0x0 7,346,6156968;sr 1:0:0:0: Attached scsi CD-ROM sr0 SUBSYSTEM=scsi DEVICE=+scsi:1:0:0:0 6,347,6289375;microcode: CPU1 sig=0x623, pf=0x0, revision=0x0 Cc: Karel Zak <kzak@redhat.com> Tested-by: William Douglas <william.douglas@intel.com> Signed-off-by: Kay Sievers <kay@vrfy.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-05-03 08:29:41 +08:00
extern const struct file_operations kmsg_fops;
enum {
DUMP_PREFIX_NONE,
DUMP_PREFIX_ADDRESS,
DUMP_PREFIX_OFFSET
};
extern int hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
int groupsize, char *linebuf, size_t linebuflen,
bool ascii);
#ifdef CONFIG_PRINTK
extern void print_hex_dump(const char *level, const char *prefix_str,
int prefix_type, int rowsize, int groupsize,
const void *buf, size_t len, bool ascii);
#if defined(CONFIG_DYNAMIC_DEBUG)
#define print_hex_dump_bytes(prefix_str, prefix_type, buf, len) \
dynamic_hex_dump(prefix_str, prefix_type, 16, 1, buf, len, true)
#else
extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type,
const void *buf, size_t len);
#endif /* defined(CONFIG_DYNAMIC_DEBUG) */
#else
static inline void print_hex_dump(const char *level, const char *prefix_str,
int prefix_type, int rowsize, int groupsize,
const void *buf, size_t len, bool ascii)
{
}
static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type,
const void *buf, size_t len)
{
}
#endif
#if defined(CONFIG_DYNAMIC_DEBUG)
#define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \
groupsize, buf, len, ascii) \
dynamic_hex_dump(prefix_str, prefix_type, rowsize, \
groupsize, buf, len, ascii)
#elif defined(DEBUG)
#define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \
groupsize, buf, len, ascii) \
print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, rowsize, \
groupsize, buf, len, ascii)
#else
static inline void print_hex_dump_debug(const char *prefix_str, int prefix_type,
int rowsize, int groupsize,
const void *buf, size_t len, bool ascii)
{
}
#endif
#endif