OpenCloudOS-Kernel/kernel/printk/printk.c

3784 lines
96 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* 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
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#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/delay.h>
#include <linux/smp.h>
#include <linux/security.h>
#include <linux/memblock.h>
#include <linux/syscalls.h>
crash: move crashkernel parsing and vmcore related code under CONFIG_CRASH_CORE Patch series "kexec/fadump: remove dependency with CONFIG_KEXEC and reuse crashkernel parameter for fadump", v4. Traditionally, kdump is used to save vmcore in case of a crash. Some architectures like powerpc can save vmcore using architecture specific support instead of kexec/kdump mechanism. Such architecture specific support also needs to reserve memory, to be used by dump capture kernel. crashkernel parameter can be a reused, for memory reservation, by such architecture specific infrastructure. This patchset removes dependency with CONFIG_KEXEC for crashkernel parameter and vmcoreinfo related code as it can be reused without kexec support. Also, crashkernel parameter is reused instead of fadump_reserve_mem to reserve memory for fadump. The first patch moves crashkernel parameter parsing and vmcoreinfo related code under CONFIG_CRASH_CORE instead of CONFIG_KEXEC_CORE. The second patch reuses the definitions of append_elf_note() & final_note() functions under CONFIG_CRASH_CORE in IA64 arch code. The third patch removes dependency on CONFIG_KEXEC for firmware-assisted dump (fadump) in powerpc. The next patch reuses crashkernel parameter for reserving memory for fadump, instead of the fadump_reserve_mem parameter. This has the advantage of using all syntaxes crashkernel parameter supports, for fadump as well. The last patch updates fadump kernel documentation about use of crashkernel parameter. This patch (of 5): Traditionally, kdump is used to save vmcore in case of a crash. Some architectures like powerpc can save vmcore using architecture specific support instead of kexec/kdump mechanism. Such architecture specific support also needs to reserve memory, to be used by dump capture kernel. crashkernel parameter can be a reused, for memory reservation, by such architecture specific infrastructure. But currently, code related to vmcoreinfo and parsing of crashkernel parameter is built under CONFIG_KEXEC_CORE. This patch introduces CONFIG_CRASH_CORE and moves the above mentioned code under this config, allowing code reuse without dependency on CONFIG_KEXEC. There is no functional change with this patch. Link: http://lkml.kernel.org/r/149035338104.6881.4550894432615189948.stgit@hbathini.in.ibm.com Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com> Acked-by: Dave Young <dyoung@redhat.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-09 06:56:18 +08:00
#include <linux/crash_core.h>
#include <linux/ratelimit.h>
#include <linux/kmsg_dump.h>
#include <linux/syslog.h>
printk: fix delayed messages from CPU hotplug events When a secondary CPU is being brought up, it is not uncommon for printk() to be invoked when cpu_online(smp_processor_id()) == 0. The case that I witnessed personally was on MIPS: http://lkml.org/lkml/2010/5/30/4 If (can_use_console() == 0), printk() will spool its output to log_buf and it will be visible in "dmesg", but that output will NOT be echoed to the console until somebody calls release_console_sem() from a CPU that is online. Therefore, the boot time messages from the new CPU can get stuck in "limbo" for a long time, and might suddenly appear on the screen when a completely unrelated event (e.g. "eth0: link is down") occurs. This patch modifies the console code so that any pending messages are automatically flushed out to the console whenever a CPU hotplug operation completes successfully or aborts. The issue was seen on 2.6.34. Original patch by Kevin Cernekee with cleanups by akpm and additional fixes by Santosh Shilimkar. This patch superseeds https://patchwork.linux-mips.org/patch/1357/. Signed-off-by: Kevin Cernekee <cernekee@gmail.com> To: <mingo@elte.hu> To: <akpm@linux-foundation.org> To: <simon.kagstrom@netinsight.net> To: <David.Woodhouse@intel.com> To: <lethal@linux-sh.org> Cc: <linux-kernel@vger.kernel.org> Cc: <linux-mips@linux-mips.org> Reviewed-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Kevin Cernekee <cernekee@gmail.com> Patchwork: https://patchwork.linux-mips.org/patch/1534/ LKML-Reference: <ede63b5a20af951c755736f035d1e787772d7c28@localhost> LKML-Reference: <EAF47CD23C76F840A9E7FCE10091EFAB02C5DB6D1F@dbde02.ent.ti.com> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-06-04 13:11:25 +08:00
#include <linux/cpu.h>
#include <linux/rculist.h>
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
#include <linux/poll.h>
#include <linux/irq_work.h>
#include <linux/ctype.h>
#include <linux/uio.h>
#include <linux/sched/clock.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
#include <linux/uaccess.h>
#include <asm/sections.h>
#include <trace/events/initcall.h>
#define CREATE_TRACE_POINTS
#include <trace/events/printk.h>
#include "printk_ringbuffer.h"
#include "console_cmdline.h"
#include "braille.h"
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
#include "internal.h"
int console_printk[4] = {
CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */
MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */
CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */
CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */
};
EXPORT_SYMBOL_GPL(console_printk);
atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0);
EXPORT_SYMBOL(ignore_console_lock_warning);
/*
* 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);
panic: avoid the extra noise dmesg When kernel panic happens, it will first print the panic call stack, then the ending msg like: [ 35.743249] ---[ end Kernel panic - not syncing: Fatal exception [ 35.749975] ------------[ cut here ]------------ The above message are very useful for debugging. But if system is configured to not reboot on panic, say the "panic_timeout" parameter equals 0, it will likely print out many noisy message like WARN() call stack for each and every CPU except the panic one, messages like below: WARNING: CPU: 1 PID: 280 at kernel/sched/core.c:1198 set_task_cpu+0x183/0x190 Call Trace: <IRQ> try_to_wake_up default_wake_function autoremove_wake_function __wake_up_common __wake_up_common_lock __wake_up wake_up_klogd_work_func irq_work_run_list irq_work_tick update_process_times tick_sched_timer __hrtimer_run_queues hrtimer_interrupt smp_apic_timer_interrupt apic_timer_interrupt For people working in console mode, the screen will first show the panic call stack, but immediately overridden by these noisy extra messages, which makes debugging much more difficult, as the original context gets lost on screen. Also these noisy messages will confuse some users, as I have seen many bug reporters posted the noisy message into bugzilla, instead of the real panic call stack and context. Adding a flag "suppress_printk" which gets set in panic() to avoid those noisy messages, without changing current kernel behavior that both panic blinking and sysrq magic key can work as is, suggested by Petr Mladek. To verify this, make sure kernel is not configured to reboot on panic and in console # echo c > /proc/sysrq-trigger to see if console only prints out the panic call stack. Link: http://lkml.kernel.org/r/1551430186-24169-1-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang <feng.tang@intel.com> Suggested-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Kees Cook <keescook@chromium.org> Cc: Borislav Petkov <bp@suse.de> Cc: Andi Kleen <ak@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jiri Slaby <jslaby@suse.com> Cc: Sasha Levin <sashal@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-15 06:45:34 +08:00
/*
* System may need to suppress printk message under certain
* circumstances, like after kernel panic happens.
*/
int __read_mostly suppress_printk;
/*
* During panic, heavy printk by other CPUs can delay the
* panic and risk deadlock on console resources.
*/
static int __read_mostly suppress_panic_printk;
console: implement lockdep support for console_lock Dave Airlie recently discovered a locking bug in the fbcon layer, where a timer_del_sync (for the blinking cursor) deadlocks with the timer itself, since both (want to) hold the console_lock: https://lkml.org/lkml/2012/8/21/36 Unfortunately the console_lock isn't a plain mutex and hence has no lockdep support. Which resulted in a few days wasted of tracking down this bug (complicated by the fact that printk doesn't show anything when the console is locked) instead of noticing the bug much earlier with the lockdep splat. Hence I've figured I need to fix that for the next deadlock involving console_lock - and with kms/drm growing ever more complex locking that'll eventually happen. Now the console_lock has rather funky semantics, so after a quick irc discussion with Thomas Gleixner and Dave Airlie I've quickly ditched the original idead of switching to a real mutex (since it won't work) and instead opted to annotate the console_lock with lockdep information manually. There are a few special cases: - The console_lock state is protected by the console_sem, and usually grabbed/dropped at _lock/_unlock time. But the suspend/resume code drops the semaphore without dropping the console_lock (see suspend_console/resume_console). But since the same thread that did the suspend will do the resume, we don't need to fix up anything. - In the printk code there's a special trylock, only used to kick off the logbuffer printk'ing in console_unlock. But all that happens while lockdep is disable (since printk does a few other evil tricks). So no issue there, either. - The console_lock can also be acquired form irq context (but only with a trylock). lockdep already handles that. This all leaves us with annotating the normal console_lock, _unlock and _trylock functions. And yes, it works - simply unloading a drm kms driver resulted in lockdep complaining about the deadlock in fbcon_deinit: ====================================================== [ INFO: possible circular locking dependency detected ] 3.6.0-rc2+ #552 Not tainted ------------------------------------------------------- kms-reload/3577 is trying to acquire lock: ((&info->queue)){+.+...}, at: [<ffffffff81058c70>] wait_on_work+0x0/0xa7 but task is already holding lock: (console_lock){+.+.+.}, at: [<ffffffff81264686>] bind_con_driver+0x38/0x263 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (console_lock){+.+.+.}: [<ffffffff81087440>] lock_acquire+0x95/0x105 [<ffffffff81040190>] console_lock+0x59/0x5b [<ffffffff81209cb6>] fb_flashcursor+0x2e/0x12c [<ffffffff81057c3e>] process_one_work+0x1d9/0x3b4 [<ffffffff810584a2>] worker_thread+0x1a7/0x24b [<ffffffff8105ca29>] kthread+0x7f/0x87 [<ffffffff813b1204>] kernel_thread_helper+0x4/0x10 -> #0 ((&info->queue)){+.+...}: [<ffffffff81086cb3>] __lock_acquire+0x999/0xcf6 [<ffffffff81087440>] lock_acquire+0x95/0x105 [<ffffffff81058cab>] wait_on_work+0x3b/0xa7 [<ffffffff81058dd6>] __cancel_work_timer+0xbf/0x102 [<ffffffff81058e33>] cancel_work_sync+0xb/0xd [<ffffffff8120a3b3>] fbcon_deinit+0x11c/0x1dc [<ffffffff81264793>] bind_con_driver+0x145/0x263 [<ffffffff81264a45>] unbind_con_driver+0x14f/0x195 [<ffffffff8126540c>] store_bind+0x1ad/0x1c1 [<ffffffff8127cbb7>] dev_attr_store+0x13/0x1f [<ffffffff8116d884>] sysfs_write_file+0xe9/0x121 [<ffffffff811145b2>] vfs_write+0x9b/0xfd [<ffffffff811147b7>] sys_write+0x3e/0x6b [<ffffffff813b0039>] system_call_fastpath+0x16/0x1b other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(console_lock); lock((&info->queue)); lock(console_lock); lock((&info->queue)); *** DEADLOCK *** v2: Mark the lockdep_map static, noticed by Jani Nikula. Cc: Dave Airlie <airlied@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-09-23 01:52:11 +08:00
#ifdef CONFIG_LOCKDEP
static struct lockdep_map console_lock_dep_map = {
.name = "console_lock"
};
#endif
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
enum devkmsg_log_bits {
__DEVKMSG_LOG_BIT_ON = 0,
__DEVKMSG_LOG_BIT_OFF,
__DEVKMSG_LOG_BIT_LOCK,
};
enum devkmsg_log_masks {
DEVKMSG_LOG_MASK_ON = BIT(__DEVKMSG_LOG_BIT_ON),
DEVKMSG_LOG_MASK_OFF = BIT(__DEVKMSG_LOG_BIT_OFF),
DEVKMSG_LOG_MASK_LOCK = BIT(__DEVKMSG_LOG_BIT_LOCK),
};
/* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */
#define DEVKMSG_LOG_MASK_DEFAULT 0
static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT;
static int __control_devkmsg(char *str)
{
size_t len;
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
if (!str)
return -EINVAL;
len = str_has_prefix(str, "on");
if (len) {
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
devkmsg_log = DEVKMSG_LOG_MASK_ON;
return len;
}
len = str_has_prefix(str, "off");
if (len) {
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
devkmsg_log = DEVKMSG_LOG_MASK_OFF;
return len;
}
len = str_has_prefix(str, "ratelimit");
if (len) {
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
devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT;
return len;
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
}
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
return -EINVAL;
}
static int __init control_devkmsg(char *str)
{
if (__control_devkmsg(str) < 0) {
pr_warn("printk.devkmsg: bad option string '%s'\n", str);
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
return 1;
}
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
/*
* Set sysctl string accordingly:
*/
if (devkmsg_log == DEVKMSG_LOG_MASK_ON)
strcpy(devkmsg_log_str, "on");
else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF)
strcpy(devkmsg_log_str, "off");
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
/* else "ratelimit" which is set by default. */
/*
* Sysctl cannot change it anymore. The kernel command line setting of
* this parameter is to force the setting to be permanent throughout the
* runtime of the system. This is a precation measure against userspace
* trying to be a smarta** and attempting to change it up on us.
*/
devkmsg_log |= DEVKMSG_LOG_MASK_LOCK;
return 1;
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
}
__setup("printk.devkmsg=", control_devkmsg);
char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit";
#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL)
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
int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
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
{
char old_str[DEVKMSG_STR_MAX_SIZE];
unsigned int old;
int err;
if (write) {
if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK)
return -EINVAL;
old = devkmsg_log;
strncpy(old_str, devkmsg_log_str, DEVKMSG_STR_MAX_SIZE);
}
err = proc_dostring(table, write, buffer, lenp, ppos);
if (err)
return err;
if (write) {
err = __control_devkmsg(devkmsg_log_str);
/*
* Do not accept an unknown string OR a known string with
* trailing crap...
*/
if (err < 0 || (err + 1 != *lenp)) {
/* ... and restore old setting. */
devkmsg_log = old;
strncpy(devkmsg_log_str, old_str, DEVKMSG_STR_MAX_SIZE);
return -EINVAL;
}
}
return 0;
}
#endif /* CONFIG_PRINTK && CONFIG_SYSCTL */
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
printk: keep kernel cont support always enabled Since commit 5c2992ee7fd8a29 ("printk: remove console flushing special cases for partial buffered lines") we don't print cont fragments to the consoles; cont lines are now proper log_buf entries and there is no "consecutive continuation flag" anymore: we either have 'c' entries that mark continuation lines without fragments; or '-' entries that mark normal logbuf entries. There are no '+' entries anymore. However, we still have a small leftover - presence of ext_console drivers disables kernel cont support and we flush each pr_cont() and store it as a separate log_buf entry. Previously, it worked because msg_print_ext_header() had that "an optional external merge of the records" functionality: if (msg->flags & LOG_CONT) cont = (prev_flags & LOG_CONT) ? '+' : 'c'; We don't do this as of now, so keep kernel cont always enabled. Note from pmladek: The original purpose was to get full information including the metadata and dictionary via extended console drivers, see commit 6fe29354befe4c46e ("printk: implement support for extended console drivers"). The dictionary probably was the most important part but it was actually lost: static void cont_flush(void) { [...] log_store(cont.facility, cont.level, cont.flags, cont.ts_nsec, NULL, 0, cont.buf, cont.len); Nobody noticed because the only dictionary user is dev_printk() and dev_cont() is _not_ defined. Link: http://lkml.kernel.org/r/20181002023836.4487-2-sergey.senozhatsky@gmail.com To: Steven Rostedt <rostedt@goodmis.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Cc: Tejun Heo <tj@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> [pmladek@suse.com: Updated commit message] Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-10-02 10:38:34 +08:00
/* Number of registered extended console drivers. */
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
static int nr_ext_console_drivers;
/*
* Helper macros to handle lockdep when locking/unlocking console_sem. We use
* macros instead of functions so that _RET_IP_ contains useful information.
*/
#define down_console_sem() do { \
down(&console_sem);\
mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);\
} while (0)
static int __down_trylock_console_sem(unsigned long ip)
{
printk: use printk_safe buffers in printk Use printk_safe per-CPU buffers in printk recursion-prone blocks: -- around logbuf_lock protected sections in vprintk_emit() and console_unlock() -- around down_trylock_console_sem() and up_console_sem() Note that this solution addresses deadlocks caused by printk() recursive calls only. That is vprintk_emit() and console_unlock(). The rest will be converted in a followup patch. Another thing to note is that we now keep lockdep enabled in printk, because we are protected against the printk recursion caused by lockdep in vprintk_emit() by the printk-safe mechanism - we first switch to per-CPU buffers and only then access the deadlock-prone locks. Examples: 1) printk() from logbuf_lock spin_lock section Assume the following code: printk() raw_spin_lock(&logbuf_lock); WARN_ON(1); raw_spin_unlock(&logbuf_lock); which now produces: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 366 at kernel/printk/printk.c:1811 vprintk_emit CPU: 0 PID: 366 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f vprintk_emit+0x1cd/0x438 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 2) printk() from semaphore sem->lock spin_lock section Assume the following code printk() console_trylock() down_trylock() raw_spin_lock_irqsave(&sem->lock, flags); WARN_ON(1); raw_spin_unlock_irqrestore(&sem->lock, flags); which now produces: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 363 at kernel/locking/semaphore.c:141 down_trylock CPU: 1 PID: 363 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f down_trylock+0x3d/0x62 ? vprintk_emit+0x3f9/0x414 console_trylock+0x31/0xeb vprintk_emit+0x3f9/0x414 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 3) printk() from console_unlock() Assume the following code: printk() console_unlock() raw_spin_lock(&logbuf_lock); WARN_ON(1); raw_spin_unlock(&logbuf_lock); which now produces: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 329 at kernel/printk/printk.c:2384 console_unlock CPU: 1 PID: 329 Comm: bash Call Trace: warn_slowpath_null+0x18/0x1a console_unlock+0x12d/0x559 ? trace_hardirqs_on_caller+0x16d/0x189 ? trace_hardirqs_on+0xd/0xf vprintk_emit+0x363/0x374 vprintk_default+0x18/0x1a printk+0x43/0x4b [..] 4) printk() from try_to_wake_up() Assume the following code: printk() console_unlock() up() try_to_wake_up() raw_spin_lock_irqsave(&p->pi_lock, flags); WARN_ON(1); raw_spin_unlock_irqrestore(&p->pi_lock, flags); which now produces: ------------[ cut here ]------------ WARNING: CPU: 3 PID: 363 at kernel/sched/core.c:2028 try_to_wake_up CPU: 3 PID: 363 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f try_to_wake_up+0x7f/0x4f7 wake_up_process+0x15/0x17 __up.isra.0+0x56/0x63 up+0x32/0x42 __up_console_sem+0x37/0x55 console_unlock+0x21e/0x4c2 vprintk_emit+0x41c/0x462 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 5) printk() from call_console_drivers() Assume the following code: printk() console_unlock() call_console_drivers() ... WARN_ON(1); which now produces: ------------[ cut here ]------------ WARNING: CPU: 2 PID: 305 at kernel/printk/printk.c:1604 call_console_drivers CPU: 2 PID: 305 Comm: bash Call Trace: warn_slowpath_null+0x18/0x1a call_console_drivers.isra.6.constprop.16+0x3a/0xb0 console_unlock+0x471/0x48e vprintk_emit+0x1f4/0x206 vprintk_default+0x18/0x1a vprintk_func+0x6e/0x70 printk+0x3e/0x46 [..] 6) unsupported placeholder in printk() format now prints an actual warning from vscnprintf(), instead of 'BUG: recent printk recursion!'. ------------[ cut here ]------------ WARNING: CPU: 5 PID: 337 at lib/vsprintf.c:1900 format_decode Please remove unsupported % in format string CPU: 5 PID: 337 Comm: bash Call Trace: dump_stack+0x4f/0x65 __warn+0xc2/0xdd warn_slowpath_fmt+0x4b/0x53 format_decode+0x22c/0x308 vsnprintf+0x89/0x3b7 vscnprintf+0xd/0x26 vprintk_emit+0xb4/0x238 vprintk_default+0x1d/0x1f vprintk_func+0x6c/0x73 printk+0x43/0x4b [..] Link: http://lkml.kernel.org/r/20161227141611.940-7-sergey.senozhatsky@gmail.com Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Calvin Owens <calvinowens@fb.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2016-12-27 22:16:09 +08:00
int lock_failed;
unsigned long flags;
/*
* Here and in __up_console_sem() we need to be in safe mode,
* because spindump/WARN/etc from under console ->lock will
* deadlock in printk()->down_trylock_console_sem() otherwise.
*/
printk_safe_enter_irqsave(flags);
lock_failed = down_trylock(&console_sem);
printk_safe_exit_irqrestore(flags);
if (lock_failed)
return 1;
mutex_acquire(&console_lock_dep_map, 0, 1, ip);
return 0;
}
#define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_)
printk: use printk_safe buffers in printk Use printk_safe per-CPU buffers in printk recursion-prone blocks: -- around logbuf_lock protected sections in vprintk_emit() and console_unlock() -- around down_trylock_console_sem() and up_console_sem() Note that this solution addresses deadlocks caused by printk() recursive calls only. That is vprintk_emit() and console_unlock(). The rest will be converted in a followup patch. Another thing to note is that we now keep lockdep enabled in printk, because we are protected against the printk recursion caused by lockdep in vprintk_emit() by the printk-safe mechanism - we first switch to per-CPU buffers and only then access the deadlock-prone locks. Examples: 1) printk() from logbuf_lock spin_lock section Assume the following code: printk() raw_spin_lock(&logbuf_lock); WARN_ON(1); raw_spin_unlock(&logbuf_lock); which now produces: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 366 at kernel/printk/printk.c:1811 vprintk_emit CPU: 0 PID: 366 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f vprintk_emit+0x1cd/0x438 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 2) printk() from semaphore sem->lock spin_lock section Assume the following code printk() console_trylock() down_trylock() raw_spin_lock_irqsave(&sem->lock, flags); WARN_ON(1); raw_spin_unlock_irqrestore(&sem->lock, flags); which now produces: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 363 at kernel/locking/semaphore.c:141 down_trylock CPU: 1 PID: 363 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f down_trylock+0x3d/0x62 ? vprintk_emit+0x3f9/0x414 console_trylock+0x31/0xeb vprintk_emit+0x3f9/0x414 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 3) printk() from console_unlock() Assume the following code: printk() console_unlock() raw_spin_lock(&logbuf_lock); WARN_ON(1); raw_spin_unlock(&logbuf_lock); which now produces: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 329 at kernel/printk/printk.c:2384 console_unlock CPU: 1 PID: 329 Comm: bash Call Trace: warn_slowpath_null+0x18/0x1a console_unlock+0x12d/0x559 ? trace_hardirqs_on_caller+0x16d/0x189 ? trace_hardirqs_on+0xd/0xf vprintk_emit+0x363/0x374 vprintk_default+0x18/0x1a printk+0x43/0x4b [..] 4) printk() from try_to_wake_up() Assume the following code: printk() console_unlock() up() try_to_wake_up() raw_spin_lock_irqsave(&p->pi_lock, flags); WARN_ON(1); raw_spin_unlock_irqrestore(&p->pi_lock, flags); which now produces: ------------[ cut here ]------------ WARNING: CPU: 3 PID: 363 at kernel/sched/core.c:2028 try_to_wake_up CPU: 3 PID: 363 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f try_to_wake_up+0x7f/0x4f7 wake_up_process+0x15/0x17 __up.isra.0+0x56/0x63 up+0x32/0x42 __up_console_sem+0x37/0x55 console_unlock+0x21e/0x4c2 vprintk_emit+0x41c/0x462 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 5) printk() from call_console_drivers() Assume the following code: printk() console_unlock() call_console_drivers() ... WARN_ON(1); which now produces: ------------[ cut here ]------------ WARNING: CPU: 2 PID: 305 at kernel/printk/printk.c:1604 call_console_drivers CPU: 2 PID: 305 Comm: bash Call Trace: warn_slowpath_null+0x18/0x1a call_console_drivers.isra.6.constprop.16+0x3a/0xb0 console_unlock+0x471/0x48e vprintk_emit+0x1f4/0x206 vprintk_default+0x18/0x1a vprintk_func+0x6e/0x70 printk+0x3e/0x46 [..] 6) unsupported placeholder in printk() format now prints an actual warning from vscnprintf(), instead of 'BUG: recent printk recursion!'. ------------[ cut here ]------------ WARNING: CPU: 5 PID: 337 at lib/vsprintf.c:1900 format_decode Please remove unsupported % in format string CPU: 5 PID: 337 Comm: bash Call Trace: dump_stack+0x4f/0x65 __warn+0xc2/0xdd warn_slowpath_fmt+0x4b/0x53 format_decode+0x22c/0x308 vsnprintf+0x89/0x3b7 vscnprintf+0xd/0x26 vprintk_emit+0xb4/0x238 vprintk_default+0x1d/0x1f vprintk_func+0x6c/0x73 printk+0x43/0x4b [..] Link: http://lkml.kernel.org/r/20161227141611.940-7-sergey.senozhatsky@gmail.com Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Calvin Owens <calvinowens@fb.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2016-12-27 22:16:09 +08:00
static void __up_console_sem(unsigned long ip)
{
unsigned long flags;
2019-09-20 00:09:40 +08:00
mutex_release(&console_lock_dep_map, ip);
printk: use printk_safe buffers in printk Use printk_safe per-CPU buffers in printk recursion-prone blocks: -- around logbuf_lock protected sections in vprintk_emit() and console_unlock() -- around down_trylock_console_sem() and up_console_sem() Note that this solution addresses deadlocks caused by printk() recursive calls only. That is vprintk_emit() and console_unlock(). The rest will be converted in a followup patch. Another thing to note is that we now keep lockdep enabled in printk, because we are protected against the printk recursion caused by lockdep in vprintk_emit() by the printk-safe mechanism - we first switch to per-CPU buffers and only then access the deadlock-prone locks. Examples: 1) printk() from logbuf_lock spin_lock section Assume the following code: printk() raw_spin_lock(&logbuf_lock); WARN_ON(1); raw_spin_unlock(&logbuf_lock); which now produces: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 366 at kernel/printk/printk.c:1811 vprintk_emit CPU: 0 PID: 366 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f vprintk_emit+0x1cd/0x438 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 2) printk() from semaphore sem->lock spin_lock section Assume the following code printk() console_trylock() down_trylock() raw_spin_lock_irqsave(&sem->lock, flags); WARN_ON(1); raw_spin_unlock_irqrestore(&sem->lock, flags); which now produces: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 363 at kernel/locking/semaphore.c:141 down_trylock CPU: 1 PID: 363 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f down_trylock+0x3d/0x62 ? vprintk_emit+0x3f9/0x414 console_trylock+0x31/0xeb vprintk_emit+0x3f9/0x414 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 3) printk() from console_unlock() Assume the following code: printk() console_unlock() raw_spin_lock(&logbuf_lock); WARN_ON(1); raw_spin_unlock(&logbuf_lock); which now produces: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 329 at kernel/printk/printk.c:2384 console_unlock CPU: 1 PID: 329 Comm: bash Call Trace: warn_slowpath_null+0x18/0x1a console_unlock+0x12d/0x559 ? trace_hardirqs_on_caller+0x16d/0x189 ? trace_hardirqs_on+0xd/0xf vprintk_emit+0x363/0x374 vprintk_default+0x18/0x1a printk+0x43/0x4b [..] 4) printk() from try_to_wake_up() Assume the following code: printk() console_unlock() up() try_to_wake_up() raw_spin_lock_irqsave(&p->pi_lock, flags); WARN_ON(1); raw_spin_unlock_irqrestore(&p->pi_lock, flags); which now produces: ------------[ cut here ]------------ WARNING: CPU: 3 PID: 363 at kernel/sched/core.c:2028 try_to_wake_up CPU: 3 PID: 363 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f try_to_wake_up+0x7f/0x4f7 wake_up_process+0x15/0x17 __up.isra.0+0x56/0x63 up+0x32/0x42 __up_console_sem+0x37/0x55 console_unlock+0x21e/0x4c2 vprintk_emit+0x41c/0x462 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 5) printk() from call_console_drivers() Assume the following code: printk() console_unlock() call_console_drivers() ... WARN_ON(1); which now produces: ------------[ cut here ]------------ WARNING: CPU: 2 PID: 305 at kernel/printk/printk.c:1604 call_console_drivers CPU: 2 PID: 305 Comm: bash Call Trace: warn_slowpath_null+0x18/0x1a call_console_drivers.isra.6.constprop.16+0x3a/0xb0 console_unlock+0x471/0x48e vprintk_emit+0x1f4/0x206 vprintk_default+0x18/0x1a vprintk_func+0x6e/0x70 printk+0x3e/0x46 [..] 6) unsupported placeholder in printk() format now prints an actual warning from vscnprintf(), instead of 'BUG: recent printk recursion!'. ------------[ cut here ]------------ WARNING: CPU: 5 PID: 337 at lib/vsprintf.c:1900 format_decode Please remove unsupported % in format string CPU: 5 PID: 337 Comm: bash Call Trace: dump_stack+0x4f/0x65 __warn+0xc2/0xdd warn_slowpath_fmt+0x4b/0x53 format_decode+0x22c/0x308 vsnprintf+0x89/0x3b7 vscnprintf+0xd/0x26 vprintk_emit+0xb4/0x238 vprintk_default+0x1d/0x1f vprintk_func+0x6c/0x73 printk+0x43/0x4b [..] Link: http://lkml.kernel.org/r/20161227141611.940-7-sergey.senozhatsky@gmail.com Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Calvin Owens <calvinowens@fb.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2016-12-27 22:16:09 +08:00
printk_safe_enter_irqsave(flags);
up(&console_sem);
printk_safe_exit_irqrestore(flags);
}
#define up_console_sem() __up_console_sem(_RET_IP_)
static bool panic_in_progress(void)
{
return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID);
}
/*
* 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 and are racing, but it helps tracking those weird code
* paths in the console code where we end up in places I want
* locked without the console semaphore 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=)
*/
#define MAX_CMDLINECONSOLES 8
static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES];
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;
printk: add console_msg_format command line option 0day and kernelCI automatically parse kernel log - basically some sort of grepping using the pre-defined text patterns - in order to detect and report regressions/errors. There are several sources they get the kernel logs from: a) dmesg or /proc/ksmg This is the preferred way. Because `dmesg --raw' (see later Note) and /proc/kmsg output contains facility and log level, which greatly simplifies grepping for EMERG/ALERT/CRIT/ERR messages. b) serial consoles This option is harder to maintain, because serial console messages don't contain facility and log level. This patch introduces a `console_msg_format=' command line option, to switch between different message formatting on serial consoles. For the time being we have just two options - default and syslog. The "default" option just keeps the existing format. While the "syslog" option makes serial console messages to appear in syslog format [syslog() syscall], matching the `dmesg -S --raw' and `cat /proc/kmsg' output formats: - facility and log level - time stamp (depends on printk_time/PRINTK_TIME) - message <%u>[time stamp] text\n NOTE: while Kevin and Fengguang talk about "dmesg --raw", it's actually "dmesg -S --raw" that always prints messages in syslog format [per Petr Mladek]. Running "dmesg --raw" may produce output in non-syslog format sometimes. console_msg_format=syslog enables syslog format, thus in documentation we mention "dmesg -S --raw", not "dmesg --raw". Per Kevin Hilman: : Right now we can get this info from a "dmesg --raw" after bootup, : but it would be really nice in certain automation frameworks to : have a kernel command-line option to enable printing of loglevels : in default boot log. : : This is especially useful when ingesting kernel logs into advanced : search/analytics frameworks (I'm playing with and ELK stack: Elastic : Search, Logstash, Kibana). : : The other important reason for having this on the command line is that : for testing linux-next (and other bleeding edge developer branches), : it's common that we never make it to userspace, so can't even run : "dmesg --raw" (or equivalent.) So we really want this on the primary : boot (serial) console. Per Fengguang Wu, 0day scripts should quickly benefit from that feature, because they will be able to switch to a more reliable parsing, based on messages' facility and log levels [1]: `#{grep} -a -E -e '^<[0123]>' -e '^kern :(err |crit |alert |emerg )' instead of doing text pattern matching `#{grep} -a -F -f /lkp/printk-error-messages #{kmsg_file} | grep -a -v -E -f #{LKP_SRC}/etc/oops-pattern | grep -a -v -F -f #{LKP_SRC}/etc/kmsg-blacklist` [1] https://github.com/fengguang/lkp-tests/blob/master/lib/dmesg.rb Link: http://lkml.kernel.org/r/20171221054149.4398-1-sergey.senozhatsky@gmail.com To: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Kevin Hilman <khilman@baylibre.com> Cc: Mark Brown <broonie@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Fengguang Wu <fengguang.wu@intel.com> Reviewed-by: Kevin Hilman <khilman@baylibre.com> Tested-by: Kevin Hilman <khilman@baylibre.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-12-21 13:41:49 +08:00
enum con_msg_format_flags {
MSG_FORMAT_DEFAULT = 0,
MSG_FORMAT_SYSLOG = (1 << 0),
};
static int console_msg_format = MSG_FORMAT_DEFAULT;
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
/*
* The printk log buffer consists of a sequenced collection of records, each
* containing variable length message text. Every record also contains its
* own meta-data (@info).
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
*
* Every record meta-data carries the 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.
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
*
* The human readable log message of a record is available in @text, the
* length of the message text in @text_len. The stored message is not
* terminated.
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
*
* Optionally, a record can carry a dictionary of properties (key/value
* pairs), to provide userspace with a machine-readable message context.
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
*
* 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.-_]. Property names
* and values are terminated by a '\0' character.
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
*
* Example of record values:
* record.text_buf = "it's a line" (unterminated)
* record.info.seq = 56
* record.info.ts_nsec = 36863
* record.info.text_len = 11
* record.info.facility = 0 (LOG_KERN)
* record.info.flags = 0
* record.info.level = 3 (LOG_ERR)
* record.info.caller_id = 299 (task 299)
* record.info.dev_info.subsystem = "pci" (terminated)
* record.info.dev_info.device = "+pci:0000:00:01.0" (terminated)
*
* The 'struct printk_info' buffer must never be directly exported to
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
* 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>,<contflag>[,additional_values, ... ];<message text>\n"
*
* Users of the export format should ignore possible additional values
* separated by ',', and find the message after the ';' character.
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
*
* 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.
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
*/
/* syslog_lock protects syslog_* variables and write access to clear_seq. */
static DEFINE_MUTEX(syslog_lock);
#ifdef CONFIG_PRINTK
DECLARE_WAIT_QUEUE_HEAD(log_wait);
/* All 3 protected by @syslog_lock. */
/* the next printk record to read by syslog(READ) or /proc/kmsg */
static u64 syslog_seq;
static size_t syslog_partial;
static bool syslog_time;
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
/* All 3 protected by @console_sem. */
/* the next printk record to write to the console */
static u64 console_seq;
static u64 exclusive_console_stop_seq;
static unsigned long console_dropped;
struct latched_seq {
seqcount_latch_t latch;
u64 val[2];
};
/*
* The next printk record to read after the last 'clear' command. There are
* two copies (updated with seqcount_latch) so that reads can locklessly
* access a valid value. Writers are synchronized by @syslog_lock.
*/
static struct latched_seq clear_seq = {
.latch = SEQCNT_LATCH_ZERO(clear_seq.latch),
.val[0] = 0,
.val[1] = 0,
};
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
printk: Add caller information to printk() output. Sometimes we want to print a series of printk() messages to consoles without being disturbed by concurrent printk() from interrupts and/or other threads. But we can't enforce printk() callers to use their local buffers because we need to ask them to make too much changes. Also, even buffering up to one line inside printk() might cause failing to emit an important clue under critical situation. Therefore, instead of trying to help buffering, let's try to help reconstructing messages by saving caller information as of calling log_store() and adding it as "[T$thread_id]" or "[C$processor_id]" upon printing to consoles. Some examples for console output: [ 1.222773][ T1] x86: Booting SMP configuration: [ 2.779635][ T1] pci 0000:00:01.0: PCI bridge to [bus 01] [ 5.069193][ T268] Fusion MPT base driver 3.04.20 [ 9.316504][ C2] random: fast init done [ 13.413336][ T3355] Initialized host personality Some examples for /dev/kmsg output: 6,496,1222773,-,caller=T1;x86: Booting SMP configuration: 6,968,2779635,-,caller=T1;pci 0000:00:01.0: PCI bridge to [bus 01] SUBSYSTEM=pci DEVICE=+pci:0000:00:01.0 6,1353,5069193,-,caller=T268;Fusion MPT base driver 3.04.20 5,1526,9316504,-,caller=C2;random: fast init done 6,1575,13413336,-,caller=T3355;Initialized host personality Note that this patch changes max length of messages which can be printed by printk() or written to /dev/kmsg interface from 992 bytes to 976 bytes, based on an assumption that userspace won't try to write messages hitting that border line to /dev/kmsg interface. Link: http://lkml.kernel.org/r/93f19e57-5051-c67d-9af4-b17624062d44@i-love.sakura.ne.jp Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-12-18 05:05:04 +08:00
#ifdef CONFIG_PRINTK_CALLER
#define PREFIX_MAX 48
#else
#define PREFIX_MAX 32
printk: Add caller information to printk() output. Sometimes we want to print a series of printk() messages to consoles without being disturbed by concurrent printk() from interrupts and/or other threads. But we can't enforce printk() callers to use their local buffers because we need to ask them to make too much changes. Also, even buffering up to one line inside printk() might cause failing to emit an important clue under critical situation. Therefore, instead of trying to help buffering, let's try to help reconstructing messages by saving caller information as of calling log_store() and adding it as "[T$thread_id]" or "[C$processor_id]" upon printing to consoles. Some examples for console output: [ 1.222773][ T1] x86: Booting SMP configuration: [ 2.779635][ T1] pci 0000:00:01.0: PCI bridge to [bus 01] [ 5.069193][ T268] Fusion MPT base driver 3.04.20 [ 9.316504][ C2] random: fast init done [ 13.413336][ T3355] Initialized host personality Some examples for /dev/kmsg output: 6,496,1222773,-,caller=T1;x86: Booting SMP configuration: 6,968,2779635,-,caller=T1;pci 0000:00:01.0: PCI bridge to [bus 01] SUBSYSTEM=pci DEVICE=+pci:0000:00:01.0 6,1353,5069193,-,caller=T268;Fusion MPT base driver 3.04.20 5,1526,9316504,-,caller=C2;random: fast init done 6,1575,13413336,-,caller=T3355;Initialized host personality Note that this patch changes max length of messages which can be printed by printk() or written to /dev/kmsg interface from 992 bytes to 976 bytes, based on an assumption that userspace won't try to write messages hitting that border line to /dev/kmsg interface. Link: http://lkml.kernel.org/r/93f19e57-5051-c67d-9af4-b17624062d44@i-love.sakura.ne.jp Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-12-18 05:05:04 +08:00
#endif
/* the maximum size of a formatted record (i.e. with prefix added per line) */
#define CONSOLE_LOG_MAX 1024
/* the maximum size allowed to be reserved for a record */
#define LOG_LINE_MAX (CONSOLE_LOG_MAX - PREFIX_MAX)
printk: prevent userland from spoofing kernel messages The following statement of ABI/testing/dev-kmsg is not quite right: It is not possible to inject messages from userspace with the facility number LOG_KERN (0), to make sure that the origin of the messages can always be reliably determined. Userland actually can inject messages with a facility of 0 by abusing the fact that the facility is stored in a u8 data type. By using a facility which is a multiple of 256 the assignment of msg->facility in log_store() implicitly truncates it to 0, i.e. LOG_KERN, allowing users of /dev/kmsg to spoof kernel messages as shown below: The following call... # printf '<%d>Kernel panic - not syncing: beer empty\n' 0 >/dev/kmsg ...leads to the following log entry (dmesg -x | tail -n 1): user :emerg : [ 66.137758] Kernel panic - not syncing: beer empty However, this call... # printf '<%d>Kernel panic - not syncing: beer empty\n' 0x800 >/dev/kmsg ...leads to the slightly different log entry (note the kernel facility): kern :emerg : [ 74.177343] Kernel panic - not syncing: beer empty Fix that by limiting the user provided facility to 8 bit right from the beginning and catch the truncation early. Fixes: 7ff9554bb578 ("printk: convert byte-buffer to variable-length...") Signed-off-by: Mathias Krause <minipli@googlemail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Petr Mladek <pmladek@suse.cz> Cc: Alex Elder <elder@linaro.org> Cc: Joe Perches <joe@perches.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 08:30:38 +08:00
#define LOG_LEVEL(v) ((v) & 0x07)
#define LOG_FACILITY(v) ((v) >> 3 & 0xff)
/* record buffer */
#define LOG_ALIGN __alignof__(unsigned long)
#define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
#define LOG_BUF_LEN_MAX (u32)(1 << 31)
static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
static char *log_buf = __log_buf;
static u32 log_buf_len = __LOG_BUF_LEN;
/*
* Define the average message size. This only affects the number of
* descriptors that will be available. Underestimating is better than
* overestimating (too many available descriptors is better than not enough).
*/
#define PRB_AVGBITS 5 /* 32 character average length */
#if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS
#error CONFIG_LOG_BUF_SHIFT value too small.
#endif
_DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS,
PRB_AVGBITS, &__log_buf[0]);
static struct printk_ringbuffer printk_rb_dynamic;
static struct printk_ringbuffer *prb = &printk_rb_static;
printk: queue wake_up_klogd irq_work only if per-CPU areas are ready printk_deferred(), similarly to printk_safe/printk_nmi, does not immediately attempt to print a new message on the consoles, avoiding calls into non-reentrant kernel paths, e.g. scheduler or timekeeping, which potentially can deadlock the system. Those printk() flavors, instead, rely on per-CPU flush irq_work to print messages from safer contexts. For same reasons (recursive scheduler or timekeeping calls) printk() uses per-CPU irq_work in order to wake up user space syslog/kmsg readers. However, only printk_safe/printk_nmi do make sure that per-CPU areas have been initialised and that it's safe to modify per-CPU irq_work. This means that, for instance, should printk_deferred() be invoked "too early", that is before per-CPU areas are initialised, printk_deferred() will perform illegal per-CPU access. Lech Perczak [0] reports that after commit 1b710b1b10ef ("char/random: silence a lockdep splat with printk()") user-space syslog/kmsg readers are not able to read new kernel messages. The reason is printk_deferred() being called too early (as was pointed out by Petr and John). Fix printk_deferred() and do not queue per-CPU irq_work before per-CPU areas are initialized. Link: https://lore.kernel.org/lkml/aa0732c6-5c4e-8a8b-a1c1-75ebe3dca05b@camlintechnologies.com/ Reported-by: Lech Perczak <l.perczak@camlintechnologies.com> Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Tested-by: Jann Horn <jannh@google.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Theodore Ts'o <tytso@mit.edu> Cc: John Ogness <john.ogness@linutronix.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-03 19:30:02 +08:00
/*
* We cannot access per-CPU data (e.g. per-CPU flush irq_work) before
* per_cpu_areas are initialised. This variable is set to true when
* it's safe to access per-CPU data.
*/
static bool __printk_percpu_data_ready __read_mostly;
bool printk_percpu_data_ready(void)
{
return __printk_percpu_data_ready;
}
/* Must be called under syslog_lock. */
static void latched_seq_write(struct latched_seq *ls, u64 val)
{
raw_write_seqcount_latch(&ls->latch);
ls->val[0] = val;
raw_write_seqcount_latch(&ls->latch);
ls->val[1] = val;
}
/* Can be called from any context. */
static u64 latched_seq_read_nolock(struct latched_seq *ls)
{
unsigned int seq;
unsigned int idx;
u64 val;
do {
seq = raw_read_seqcount_latch(&ls->latch);
idx = seq & 0x1;
val = ls->val[idx];
} while (read_seqcount_latch_retry(&ls->latch, seq));
return val;
}
/* Return log buffer address */
char *log_buf_addr_get(void)
{
return log_buf;
}
/* Return log buffer size */
u32 log_buf_len_get(void)
{
return log_buf_len;
}
/*
* Define how much of the log buffer we could take at maximum. The value
* must be greater than two. Note that only half of the buffer is available
* when the index points to the middle.
*/
#define MAX_LOG_TAKE_PART 4
static const char trunc_msg[] = "<truncated>";
static void truncate_msg(u16 *text_len, u16 *trunc_msg_len)
{
/*
* The message should not take the whole buffer. Otherwise, it might
* get removed too soon.
*/
u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART;
if (*text_len > max_text_len)
*text_len = max_text_len;
/* enable the warning message (if there is room) */
*trunc_msg_len = strlen(trunc_msg);
if (*text_len >= *trunc_msg_len)
*text_len -= *trunc_msg_len;
else
*trunc_msg_len = 0;
}
int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT);
kmsg: honor dmesg_restrict sysctl on /dev/kmsg The dmesg_restrict sysctl currently covers the syslog method for access dmesg, however /dev/kmsg isn't covered by the same protections. Most people haven't noticed because util-linux dmesg(1) defaults to using the syslog method for access in older versions. With util-linux dmesg(1) defaults to reading directly from /dev/kmsg. To fix /dev/kmsg, let's compare the existing interfaces and what they allow: - /proc/kmsg allows: - open (SYSLOG_ACTION_OPEN) if CAP_SYSLOG since it uses a destructive single-reader interface (SYSLOG_ACTION_READ). - everything, after an open. - syslog syscall allows: - anything, if CAP_SYSLOG. - SYSLOG_ACTION_READ_ALL and SYSLOG_ACTION_SIZE_BUFFER, if dmesg_restrict==0. - nothing else (EPERM). The use-cases were: - dmesg(1) needs to do non-destructive SYSLOG_ACTION_READ_ALLs. - sysklog(1) needs to open /proc/kmsg, drop privs, and still issue the destructive SYSLOG_ACTION_READs. AIUI, dmesg(1) is moving to /dev/kmsg, and systemd-journald doesn't clear the ring buffer. Based on the comments in devkmsg_llseek, it sounds like actions besides reading aren't going to be supported by /dev/kmsg (i.e. SYSLOG_ACTION_CLEAR), so we have a strict subset of the non-destructive syslog syscall actions. To this end, move the check as Josh had done, but also rename the constants to reflect their new uses (SYSLOG_FROM_CALL becomes SYSLOG_FROM_READER, and SYSLOG_FROM_FILE becomes SYSLOG_FROM_PROC). SYSLOG_FROM_READER allows non-destructive actions, and SYSLOG_FROM_PROC allows destructive actions after a capabilities-constrained SYSLOG_ACTION_OPEN check. - /dev/kmsg allows: - open if CAP_SYSLOG or dmesg_restrict==0 - reading/polling, after open Addresses https://bugzilla.redhat.com/show_bug.cgi?id=903192 [akpm@linux-foundation.org: use pr_warn_once()] Signed-off-by: Kees Cook <keescook@chromium.org> Reported-by: Christian Kujau <lists@nerdbynature.de> Tested-by: Josh Boyer <jwboyer@redhat.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-06-13 05:04:39 +08:00
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, int source)
kmsg: honor dmesg_restrict sysctl on /dev/kmsg The dmesg_restrict sysctl currently covers the syslog method for access dmesg, however /dev/kmsg isn't covered by the same protections. Most people haven't noticed because util-linux dmesg(1) defaults to using the syslog method for access in older versions. With util-linux dmesg(1) defaults to reading directly from /dev/kmsg. To fix /dev/kmsg, let's compare the existing interfaces and what they allow: - /proc/kmsg allows: - open (SYSLOG_ACTION_OPEN) if CAP_SYSLOG since it uses a destructive single-reader interface (SYSLOG_ACTION_READ). - everything, after an open. - syslog syscall allows: - anything, if CAP_SYSLOG. - SYSLOG_ACTION_READ_ALL and SYSLOG_ACTION_SIZE_BUFFER, if dmesg_restrict==0. - nothing else (EPERM). The use-cases were: - dmesg(1) needs to do non-destructive SYSLOG_ACTION_READ_ALLs. - sysklog(1) needs to open /proc/kmsg, drop privs, and still issue the destructive SYSLOG_ACTION_READs. AIUI, dmesg(1) is moving to /dev/kmsg, and systemd-journald doesn't clear the ring buffer. Based on the comments in devkmsg_llseek, it sounds like actions besides reading aren't going to be supported by /dev/kmsg (i.e. SYSLOG_ACTION_CLEAR), so we have a strict subset of the non-destructive syslog syscall actions. To this end, move the check as Josh had done, but also rename the constants to reflect their new uses (SYSLOG_FROM_CALL becomes SYSLOG_FROM_READER, and SYSLOG_FROM_FILE becomes SYSLOG_FROM_PROC). SYSLOG_FROM_READER allows non-destructive actions, and SYSLOG_FROM_PROC allows destructive actions after a capabilities-constrained SYSLOG_ACTION_OPEN check. - /dev/kmsg allows: - open if CAP_SYSLOG or dmesg_restrict==0 - reading/polling, after open Addresses https://bugzilla.redhat.com/show_bug.cgi?id=903192 [akpm@linux-foundation.org: use pr_warn_once()] Signed-off-by: Kees Cook <keescook@chromium.org> Reported-by: Christian Kujau <lists@nerdbynature.de> Tested-by: Josh Boyer <jwboyer@redhat.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-06-13 05:04:39 +08:00
{
/*
* If this is from /proc/kmsg and we've already opened it, then we've
* already done the capabilities checks at open time.
*/
if (source == SYSLOG_FROM_PROC && type != SYSLOG_ACTION_OPEN)
goto ok;
kmsg: honor dmesg_restrict sysctl on /dev/kmsg The dmesg_restrict sysctl currently covers the syslog method for access dmesg, however /dev/kmsg isn't covered by the same protections. Most people haven't noticed because util-linux dmesg(1) defaults to using the syslog method for access in older versions. With util-linux dmesg(1) defaults to reading directly from /dev/kmsg. To fix /dev/kmsg, let's compare the existing interfaces and what they allow: - /proc/kmsg allows: - open (SYSLOG_ACTION_OPEN) if CAP_SYSLOG since it uses a destructive single-reader interface (SYSLOG_ACTION_READ). - everything, after an open. - syslog syscall allows: - anything, if CAP_SYSLOG. - SYSLOG_ACTION_READ_ALL and SYSLOG_ACTION_SIZE_BUFFER, if dmesg_restrict==0. - nothing else (EPERM). The use-cases were: - dmesg(1) needs to do non-destructive SYSLOG_ACTION_READ_ALLs. - sysklog(1) needs to open /proc/kmsg, drop privs, and still issue the destructive SYSLOG_ACTION_READs. AIUI, dmesg(1) is moving to /dev/kmsg, and systemd-journald doesn't clear the ring buffer. Based on the comments in devkmsg_llseek, it sounds like actions besides reading aren't going to be supported by /dev/kmsg (i.e. SYSLOG_ACTION_CLEAR), so we have a strict subset of the non-destructive syslog syscall actions. To this end, move the check as Josh had done, but also rename the constants to reflect their new uses (SYSLOG_FROM_CALL becomes SYSLOG_FROM_READER, and SYSLOG_FROM_FILE becomes SYSLOG_FROM_PROC). SYSLOG_FROM_READER allows non-destructive actions, and SYSLOG_FROM_PROC allows destructive actions after a capabilities-constrained SYSLOG_ACTION_OPEN check. - /dev/kmsg allows: - open if CAP_SYSLOG or dmesg_restrict==0 - reading/polling, after open Addresses https://bugzilla.redhat.com/show_bug.cgi?id=903192 [akpm@linux-foundation.org: use pr_warn_once()] Signed-off-by: Kees Cook <keescook@chromium.org> Reported-by: Christian Kujau <lists@nerdbynature.de> Tested-by: Josh Boyer <jwboyer@redhat.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-06-13 05:04:39 +08:00
if (syslog_action_restricted(type)) {
if (capable(CAP_SYSLOG))
goto ok;
kmsg: honor dmesg_restrict sysctl on /dev/kmsg The dmesg_restrict sysctl currently covers the syslog method for access dmesg, however /dev/kmsg isn't covered by the same protections. Most people haven't noticed because util-linux dmesg(1) defaults to using the syslog method for access in older versions. With util-linux dmesg(1) defaults to reading directly from /dev/kmsg. To fix /dev/kmsg, let's compare the existing interfaces and what they allow: - /proc/kmsg allows: - open (SYSLOG_ACTION_OPEN) if CAP_SYSLOG since it uses a destructive single-reader interface (SYSLOG_ACTION_READ). - everything, after an open. - syslog syscall allows: - anything, if CAP_SYSLOG. - SYSLOG_ACTION_READ_ALL and SYSLOG_ACTION_SIZE_BUFFER, if dmesg_restrict==0. - nothing else (EPERM). The use-cases were: - dmesg(1) needs to do non-destructive SYSLOG_ACTION_READ_ALLs. - sysklog(1) needs to open /proc/kmsg, drop privs, and still issue the destructive SYSLOG_ACTION_READs. AIUI, dmesg(1) is moving to /dev/kmsg, and systemd-journald doesn't clear the ring buffer. Based on the comments in devkmsg_llseek, it sounds like actions besides reading aren't going to be supported by /dev/kmsg (i.e. SYSLOG_ACTION_CLEAR), so we have a strict subset of the non-destructive syslog syscall actions. To this end, move the check as Josh had done, but also rename the constants to reflect their new uses (SYSLOG_FROM_CALL becomes SYSLOG_FROM_READER, and SYSLOG_FROM_FILE becomes SYSLOG_FROM_PROC). SYSLOG_FROM_READER allows non-destructive actions, and SYSLOG_FROM_PROC allows destructive actions after a capabilities-constrained SYSLOG_ACTION_OPEN check. - /dev/kmsg allows: - open if CAP_SYSLOG or dmesg_restrict==0 - reading/polling, after open Addresses https://bugzilla.redhat.com/show_bug.cgi?id=903192 [akpm@linux-foundation.org: use pr_warn_once()] Signed-off-by: Kees Cook <keescook@chromium.org> Reported-by: Christian Kujau <lists@nerdbynature.de> Tested-by: Josh Boyer <jwboyer@redhat.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-06-13 05:04:39 +08:00
/*
* 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));
goto ok;
kmsg: honor dmesg_restrict sysctl on /dev/kmsg The dmesg_restrict sysctl currently covers the syslog method for access dmesg, however /dev/kmsg isn't covered by the same protections. Most people haven't noticed because util-linux dmesg(1) defaults to using the syslog method for access in older versions. With util-linux dmesg(1) defaults to reading directly from /dev/kmsg. To fix /dev/kmsg, let's compare the existing interfaces and what they allow: - /proc/kmsg allows: - open (SYSLOG_ACTION_OPEN) if CAP_SYSLOG since it uses a destructive single-reader interface (SYSLOG_ACTION_READ). - everything, after an open. - syslog syscall allows: - anything, if CAP_SYSLOG. - SYSLOG_ACTION_READ_ALL and SYSLOG_ACTION_SIZE_BUFFER, if dmesg_restrict==0. - nothing else (EPERM). The use-cases were: - dmesg(1) needs to do non-destructive SYSLOG_ACTION_READ_ALLs. - sysklog(1) needs to open /proc/kmsg, drop privs, and still issue the destructive SYSLOG_ACTION_READs. AIUI, dmesg(1) is moving to /dev/kmsg, and systemd-journald doesn't clear the ring buffer. Based on the comments in devkmsg_llseek, it sounds like actions besides reading aren't going to be supported by /dev/kmsg (i.e. SYSLOG_ACTION_CLEAR), so we have a strict subset of the non-destructive syslog syscall actions. To this end, move the check as Josh had done, but also rename the constants to reflect their new uses (SYSLOG_FROM_CALL becomes SYSLOG_FROM_READER, and SYSLOG_FROM_FILE becomes SYSLOG_FROM_PROC). SYSLOG_FROM_READER allows non-destructive actions, and SYSLOG_FROM_PROC allows destructive actions after a capabilities-constrained SYSLOG_ACTION_OPEN check. - /dev/kmsg allows: - open if CAP_SYSLOG or dmesg_restrict==0 - reading/polling, after open Addresses https://bugzilla.redhat.com/show_bug.cgi?id=903192 [akpm@linux-foundation.org: use pr_warn_once()] Signed-off-by: Kees Cook <keescook@chromium.org> Reported-by: Christian Kujau <lists@nerdbynature.de> Tested-by: Josh Boyer <jwboyer@redhat.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-06-13 05:04:39 +08:00
}
return -EPERM;
}
ok:
kmsg: honor dmesg_restrict sysctl on /dev/kmsg The dmesg_restrict sysctl currently covers the syslog method for access dmesg, however /dev/kmsg isn't covered by the same protections. Most people haven't noticed because util-linux dmesg(1) defaults to using the syslog method for access in older versions. With util-linux dmesg(1) defaults to reading directly from /dev/kmsg. To fix /dev/kmsg, let's compare the existing interfaces and what they allow: - /proc/kmsg allows: - open (SYSLOG_ACTION_OPEN) if CAP_SYSLOG since it uses a destructive single-reader interface (SYSLOG_ACTION_READ). - everything, after an open. - syslog syscall allows: - anything, if CAP_SYSLOG. - SYSLOG_ACTION_READ_ALL and SYSLOG_ACTION_SIZE_BUFFER, if dmesg_restrict==0. - nothing else (EPERM). The use-cases were: - dmesg(1) needs to do non-destructive SYSLOG_ACTION_READ_ALLs. - sysklog(1) needs to open /proc/kmsg, drop privs, and still issue the destructive SYSLOG_ACTION_READs. AIUI, dmesg(1) is moving to /dev/kmsg, and systemd-journald doesn't clear the ring buffer. Based on the comments in devkmsg_llseek, it sounds like actions besides reading aren't going to be supported by /dev/kmsg (i.e. SYSLOG_ACTION_CLEAR), so we have a strict subset of the non-destructive syslog syscall actions. To this end, move the check as Josh had done, but also rename the constants to reflect their new uses (SYSLOG_FROM_CALL becomes SYSLOG_FROM_READER, and SYSLOG_FROM_FILE becomes SYSLOG_FROM_PROC). SYSLOG_FROM_READER allows non-destructive actions, and SYSLOG_FROM_PROC allows destructive actions after a capabilities-constrained SYSLOG_ACTION_OPEN check. - /dev/kmsg allows: - open if CAP_SYSLOG or dmesg_restrict==0 - reading/polling, after open Addresses https://bugzilla.redhat.com/show_bug.cgi?id=903192 [akpm@linux-foundation.org: use pr_warn_once()] Signed-off-by: Kees Cook <keescook@chromium.org> Reported-by: Christian Kujau <lists@nerdbynature.de> Tested-by: Josh Boyer <jwboyer@redhat.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-06-13 05:04:39 +08:00
return security_syslog(type);
}
static void append_char(char **pp, char *e, char c)
{
if (*pp < e)
*(*pp)++ = c;
}
kmsg: honor dmesg_restrict sysctl on /dev/kmsg The dmesg_restrict sysctl currently covers the syslog method for access dmesg, however /dev/kmsg isn't covered by the same protections. Most people haven't noticed because util-linux dmesg(1) defaults to using the syslog method for access in older versions. With util-linux dmesg(1) defaults to reading directly from /dev/kmsg. To fix /dev/kmsg, let's compare the existing interfaces and what they allow: - /proc/kmsg allows: - open (SYSLOG_ACTION_OPEN) if CAP_SYSLOG since it uses a destructive single-reader interface (SYSLOG_ACTION_READ). - everything, after an open. - syslog syscall allows: - anything, if CAP_SYSLOG. - SYSLOG_ACTION_READ_ALL and SYSLOG_ACTION_SIZE_BUFFER, if dmesg_restrict==0. - nothing else (EPERM). The use-cases were: - dmesg(1) needs to do non-destructive SYSLOG_ACTION_READ_ALLs. - sysklog(1) needs to open /proc/kmsg, drop privs, and still issue the destructive SYSLOG_ACTION_READs. AIUI, dmesg(1) is moving to /dev/kmsg, and systemd-journald doesn't clear the ring buffer. Based on the comments in devkmsg_llseek, it sounds like actions besides reading aren't going to be supported by /dev/kmsg (i.e. SYSLOG_ACTION_CLEAR), so we have a strict subset of the non-destructive syslog syscall actions. To this end, move the check as Josh had done, but also rename the constants to reflect their new uses (SYSLOG_FROM_CALL becomes SYSLOG_FROM_READER, and SYSLOG_FROM_FILE becomes SYSLOG_FROM_PROC). SYSLOG_FROM_READER allows non-destructive actions, and SYSLOG_FROM_PROC allows destructive actions after a capabilities-constrained SYSLOG_ACTION_OPEN check. - /dev/kmsg allows: - open if CAP_SYSLOG or dmesg_restrict==0 - reading/polling, after open Addresses https://bugzilla.redhat.com/show_bug.cgi?id=903192 [akpm@linux-foundation.org: use pr_warn_once()] Signed-off-by: Kees Cook <keescook@chromium.org> Reported-by: Christian Kujau <lists@nerdbynature.de> Tested-by: Josh Boyer <jwboyer@redhat.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-06-13 05:04:39 +08:00
static ssize_t info_print_ext_header(char *buf, size_t size,
struct printk_info *info)
{
u64 ts_usec = info->ts_nsec;
printk: Add caller information to printk() output. Sometimes we want to print a series of printk() messages to consoles without being disturbed by concurrent printk() from interrupts and/or other threads. But we can't enforce printk() callers to use their local buffers because we need to ask them to make too much changes. Also, even buffering up to one line inside printk() might cause failing to emit an important clue under critical situation. Therefore, instead of trying to help buffering, let's try to help reconstructing messages by saving caller information as of calling log_store() and adding it as "[T$thread_id]" or "[C$processor_id]" upon printing to consoles. Some examples for console output: [ 1.222773][ T1] x86: Booting SMP configuration: [ 2.779635][ T1] pci 0000:00:01.0: PCI bridge to [bus 01] [ 5.069193][ T268] Fusion MPT base driver 3.04.20 [ 9.316504][ C2] random: fast init done [ 13.413336][ T3355] Initialized host personality Some examples for /dev/kmsg output: 6,496,1222773,-,caller=T1;x86: Booting SMP configuration: 6,968,2779635,-,caller=T1;pci 0000:00:01.0: PCI bridge to [bus 01] SUBSYSTEM=pci DEVICE=+pci:0000:00:01.0 6,1353,5069193,-,caller=T268;Fusion MPT base driver 3.04.20 5,1526,9316504,-,caller=C2;random: fast init done 6,1575,13413336,-,caller=T3355;Initialized host personality Note that this patch changes max length of messages which can be printed by printk() or written to /dev/kmsg interface from 992 bytes to 976 bytes, based on an assumption that userspace won't try to write messages hitting that border line to /dev/kmsg interface. Link: http://lkml.kernel.org/r/93f19e57-5051-c67d-9af4-b17624062d44@i-love.sakura.ne.jp Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-12-18 05:05:04 +08:00
char caller[20];
#ifdef CONFIG_PRINTK_CALLER
u32 id = info->caller_id;
printk: Add caller information to printk() output. Sometimes we want to print a series of printk() messages to consoles without being disturbed by concurrent printk() from interrupts and/or other threads. But we can't enforce printk() callers to use their local buffers because we need to ask them to make too much changes. Also, even buffering up to one line inside printk() might cause failing to emit an important clue under critical situation. Therefore, instead of trying to help buffering, let's try to help reconstructing messages by saving caller information as of calling log_store() and adding it as "[T$thread_id]" or "[C$processor_id]" upon printing to consoles. Some examples for console output: [ 1.222773][ T1] x86: Booting SMP configuration: [ 2.779635][ T1] pci 0000:00:01.0: PCI bridge to [bus 01] [ 5.069193][ T268] Fusion MPT base driver 3.04.20 [ 9.316504][ C2] random: fast init done [ 13.413336][ T3355] Initialized host personality Some examples for /dev/kmsg output: 6,496,1222773,-,caller=T1;x86: Booting SMP configuration: 6,968,2779635,-,caller=T1;pci 0000:00:01.0: PCI bridge to [bus 01] SUBSYSTEM=pci DEVICE=+pci:0000:00:01.0 6,1353,5069193,-,caller=T268;Fusion MPT base driver 3.04.20 5,1526,9316504,-,caller=C2;random: fast init done 6,1575,13413336,-,caller=T3355;Initialized host personality Note that this patch changes max length of messages which can be printed by printk() or written to /dev/kmsg interface from 992 bytes to 976 bytes, based on an assumption that userspace won't try to write messages hitting that border line to /dev/kmsg interface. Link: http://lkml.kernel.org/r/93f19e57-5051-c67d-9af4-b17624062d44@i-love.sakura.ne.jp Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-12-18 05:05:04 +08:00
snprintf(caller, sizeof(caller), ",caller=%c%u",
id & 0x80000000 ? 'C' : 'T', id & ~0x80000000);
#else
caller[0] = '\0';
#endif
do_div(ts_usec, 1000);
printk: Add caller information to printk() output. Sometimes we want to print a series of printk() messages to consoles without being disturbed by concurrent printk() from interrupts and/or other threads. But we can't enforce printk() callers to use their local buffers because we need to ask them to make too much changes. Also, even buffering up to one line inside printk() might cause failing to emit an important clue under critical situation. Therefore, instead of trying to help buffering, let's try to help reconstructing messages by saving caller information as of calling log_store() and adding it as "[T$thread_id]" or "[C$processor_id]" upon printing to consoles. Some examples for console output: [ 1.222773][ T1] x86: Booting SMP configuration: [ 2.779635][ T1] pci 0000:00:01.0: PCI bridge to [bus 01] [ 5.069193][ T268] Fusion MPT base driver 3.04.20 [ 9.316504][ C2] random: fast init done [ 13.413336][ T3355] Initialized host personality Some examples for /dev/kmsg output: 6,496,1222773,-,caller=T1;x86: Booting SMP configuration: 6,968,2779635,-,caller=T1;pci 0000:00:01.0: PCI bridge to [bus 01] SUBSYSTEM=pci DEVICE=+pci:0000:00:01.0 6,1353,5069193,-,caller=T268;Fusion MPT base driver 3.04.20 5,1526,9316504,-,caller=C2;random: fast init done 6,1575,13413336,-,caller=T3355;Initialized host personality Note that this patch changes max length of messages which can be printed by printk() or written to /dev/kmsg interface from 992 bytes to 976 bytes, based on an assumption that userspace won't try to write messages hitting that border line to /dev/kmsg interface. Link: http://lkml.kernel.org/r/93f19e57-5051-c67d-9af4-b17624062d44@i-love.sakura.ne.jp Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-12-18 05:05:04 +08:00
return scnprintf(buf, size, "%u,%llu,%llu,%c%s;",
(info->facility << 3) | info->level, info->seq,
ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller);
}
static ssize_t msg_add_ext_text(char *buf, size_t size,
const char *text, size_t text_len,
unsigned char endc)
{
char *p = buf, *e = buf + size;
size_t i;
/* escape non-printable characters */
for (i = 0; i < text_len; i++) {
unsigned char c = text[i];
if (c < ' ' || c >= 127 || c == '\\')
p += scnprintf(p, e - p, "\\x%02x", c);
else
append_char(&p, e, c);
}
append_char(&p, e, endc);
return p - buf;
}
static ssize_t msg_add_dict_text(char *buf, size_t size,
const char *key, const char *val)
{
size_t val_len = strlen(val);
ssize_t len;
if (!val_len)
return 0;
len = msg_add_ext_text(buf, size, "", 0, ' '); /* dict prefix */
len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '=');
len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n');
return len;
}
static ssize_t msg_print_ext_body(char *buf, size_t size,
char *text, size_t text_len,
struct dev_printk_info *dev_info)
{
ssize_t len;
len = msg_add_ext_text(buf, size, text, text_len, '\n');
if (!dev_info)
goto out;
len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM",
dev_info->subsystem);
len += msg_add_dict_text(buf + len, size - len, "DEVICE",
dev_info->device);
out:
return len;
}
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
/* /dev/kmsg - userspace message inject/listen interface */
struct devkmsg_user {
atomic64_t seq;
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
struct ratelimit_state rs;
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
struct mutex lock;
char buf[CONSOLE_EXT_LOG_MAX];
struct printk_info info;
char text_buf[CONSOLE_EXT_LOG_MAX];
struct printk_record record;
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
};
static __printf(3, 4) __cold
int devkmsg_emit(int facility, int level, const char *fmt, ...)
{
va_list args;
int r;
va_start(args, fmt);
r = vprintk_emit(facility, level, NULL, fmt, args);
va_end(args);
return r;
}
static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
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
{
char *buf, *line;
int level = default_message_loglevel;
int facility = 1; /* LOG_USER */
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
struct file *file = iocb->ki_filp;
struct devkmsg_user *user = file->private_data;
size_t len = iov_iter_count(from);
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
ssize_t ret = len;
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
if (!user || len > LOG_LINE_MAX)
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
return -EINVAL;
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
/* Ignore when user logging is disabled. */
if (devkmsg_log & DEVKMSG_LOG_MASK_OFF)
return len;
/* Ratelimit when not explicitly enabled. */
if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) {
if (!___ratelimit(&user->rs, current->comm))
return ret;
}
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
buf = kmalloc(len+1, GFP_KERNEL);
if (buf == NULL)
return -ENOMEM;
buf[len] = '\0';
if (!copy_from_iter_full(buf, len, from)) {
kfree(buf);
return -EFAULT;
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
}
/*
* 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;
printk: prevent userland from spoofing kernel messages The following statement of ABI/testing/dev-kmsg is not quite right: It is not possible to inject messages from userspace with the facility number LOG_KERN (0), to make sure that the origin of the messages can always be reliably determined. Userland actually can inject messages with a facility of 0 by abusing the fact that the facility is stored in a u8 data type. By using a facility which is a multiple of 256 the assignment of msg->facility in log_store() implicitly truncates it to 0, i.e. LOG_KERN, allowing users of /dev/kmsg to spoof kernel messages as shown below: The following call... # printf '<%d>Kernel panic - not syncing: beer empty\n' 0 >/dev/kmsg ...leads to the following log entry (dmesg -x | tail -n 1): user :emerg : [ 66.137758] Kernel panic - not syncing: beer empty However, this call... # printf '<%d>Kernel panic - not syncing: beer empty\n' 0x800 >/dev/kmsg ...leads to the slightly different log entry (note the kernel facility): kern :emerg : [ 74.177343] Kernel panic - not syncing: beer empty Fix that by limiting the user provided facility to 8 bit right from the beginning and catch the truncation early. Fixes: 7ff9554bb578 ("printk: convert byte-buffer to variable-length...") Signed-off-by: Mathias Krause <minipli@googlemail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Petr Mladek <pmladek@suse.cz> Cc: Alex Elder <elder@linaro.org> Cc: Joe Perches <joe@perches.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 08:30:38 +08:00
unsigned int u;
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
printk: prevent userland from spoofing kernel messages The following statement of ABI/testing/dev-kmsg is not quite right: It is not possible to inject messages from userspace with the facility number LOG_KERN (0), to make sure that the origin of the messages can always be reliably determined. Userland actually can inject messages with a facility of 0 by abusing the fact that the facility is stored in a u8 data type. By using a facility which is a multiple of 256 the assignment of msg->facility in log_store() implicitly truncates it to 0, i.e. LOG_KERN, allowing users of /dev/kmsg to spoof kernel messages as shown below: The following call... # printf '<%d>Kernel panic - not syncing: beer empty\n' 0 >/dev/kmsg ...leads to the following log entry (dmesg -x | tail -n 1): user :emerg : [ 66.137758] Kernel panic - not syncing: beer empty However, this call... # printf '<%d>Kernel panic - not syncing: beer empty\n' 0x800 >/dev/kmsg ...leads to the slightly different log entry (note the kernel facility): kern :emerg : [ 74.177343] Kernel panic - not syncing: beer empty Fix that by limiting the user provided facility to 8 bit right from the beginning and catch the truncation early. Fixes: 7ff9554bb578 ("printk: convert byte-buffer to variable-length...") Signed-off-by: Mathias Krause <minipli@googlemail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Petr Mladek <pmladek@suse.cz> Cc: Alex Elder <elder@linaro.org> Cc: Joe Perches <joe@perches.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 08:30:38 +08:00
u = simple_strtoul(line + 1, &endp, 10);
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
if (endp && endp[0] == '>') {
printk: prevent userland from spoofing kernel messages The following statement of ABI/testing/dev-kmsg is not quite right: It is not possible to inject messages from userspace with the facility number LOG_KERN (0), to make sure that the origin of the messages can always be reliably determined. Userland actually can inject messages with a facility of 0 by abusing the fact that the facility is stored in a u8 data type. By using a facility which is a multiple of 256 the assignment of msg->facility in log_store() implicitly truncates it to 0, i.e. LOG_KERN, allowing users of /dev/kmsg to spoof kernel messages as shown below: The following call... # printf '<%d>Kernel panic - not syncing: beer empty\n' 0 >/dev/kmsg ...leads to the following log entry (dmesg -x | tail -n 1): user :emerg : [ 66.137758] Kernel panic - not syncing: beer empty However, this call... # printf '<%d>Kernel panic - not syncing: beer empty\n' 0x800 >/dev/kmsg ...leads to the slightly different log entry (note the kernel facility): kern :emerg : [ 74.177343] Kernel panic - not syncing: beer empty Fix that by limiting the user provided facility to 8 bit right from the beginning and catch the truncation early. Fixes: 7ff9554bb578 ("printk: convert byte-buffer to variable-length...") Signed-off-by: Mathias Krause <minipli@googlemail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Petr Mladek <pmladek@suse.cz> Cc: Alex Elder <elder@linaro.org> Cc: Joe Perches <joe@perches.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 08:30:38 +08:00
level = LOG_LEVEL(u);
if (LOG_FACILITY(u) != 0)
facility = LOG_FACILITY(u);
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
endp++;
line = endp;
}
}
devkmsg_emit(facility, level, "%s", line);
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
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 printk_record *r = &user->record;
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
size_t len;
ssize_t ret;
if (!user)
return -EBADF;
printk: use mutex lock to stop syslog_seq from going wild Although syslog_seq and log_next_seq stuff are protected by logbuf_lock spin log, it's not enough. Say we have two processes A and B, and let syslog_seq = N, while log_next_seq = N + 1, and the two processes both come to syslog_print at almost the same time. And No matter which process get the spin lock first, it will increase syslog_seq by one, then release spin lock; thus later, another process increase syslog_seq by one again. In this case, syslog_seq is bigger than syslog_next_seq. And latter, it would make: wait_event_interruptiable(log_wait, syslog != log_next_seq) don't wait any more even there is no new write comes. Thus it introduce a infinite loop reading. I can easily see this kind of issue by the following steps: # cat /proc/kmsg # at meantime, I don't kill rsyslog # So they are the two processes. # xinit # I added drm.debug=6 in the kernel parameter line, # so that it will produce lots of message and let that # issue happen It's 100% reproducable on my side. And my disk will be filled up by /var/log/messages in a quite short time. So, introduce a mutex_lock to stop syslog_seq from going wild just like what devkmsg_read() does. It does fix this issue as expected. v2: use mutex_lock_interruptiable() instead (comments from Kay) Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com> Reviewed-by: Fengguang Wu <fengguang.wu@intel.com> Acked-By: Kay Sievers <kay@vrfy.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-06-16 21:21:51 +08:00
ret = mutex_lock_interruptible(&user->lock);
if (ret)
return ret;
if (!prb_read_valid(prb, atomic64_read(&user->seq), r)) {
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
if (file->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
goto out;
}
ret = wait_event_interruptible(log_wait,
prb_read_valid(prb, atomic64_read(&user->seq), r));
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
if (ret)
goto out;
}
if (r->info->seq != atomic64_read(&user->seq)) {
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
/* our last seen message is gone, return error and reset */
atomic64_set(&user->seq, r->info->seq);
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
ret = -EPIPE;
goto out;
}
len = info_print_ext_header(user->buf, sizeof(user->buf), r->info);
len += msg_print_ext_body(user->buf + len, sizeof(user->buf) - len,
&r->text_buf[0], r->info->text_len,
&r->info->dev_info);
atomic64_set(&user->seq, r->info->seq + 1);
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
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;
}
/*
* Be careful when modifying this function!!!
*
* Only few operations are supported because the device works only with the
* entire variable length messages (records). Non-standard values are
* returned in the other cases and has been this way for quite some time.
* User space applications might depend on this behavior.
*/
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
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;
switch (whence) {
case SEEK_SET:
/* the first record */
atomic64_set(&user->seq, prb_first_valid_seq(prb));
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
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.
*/
atomic64_set(&user->seq, latched_seq_read_nolock(&clear_seq));
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
break;
case SEEK_END:
/* after the last record */
atomic64_set(&user->seq, prb_next_seq(prb));
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
break;
default:
ret = -EINVAL;
}
return ret;
}
static __poll_t devkmsg_poll(struct file *file, poll_table *wait)
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
{
struct devkmsg_user *user = file->private_data;
struct printk_info info;
__poll_t ret = 0;
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
if (!user)
return EPOLLERR|EPOLLNVAL;
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
poll_wait(file, &log_wait, wait);
if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) {
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
/* return error when data has vanished underneath us */
if (info.seq != atomic64_read(&user->seq))
ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI;
else
ret = EPOLLIN|EPOLLRDNORM;
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
}
return ret;
}
static int devkmsg_open(struct inode *inode, struct file *file)
{
struct devkmsg_user *user;
int err;
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
if (devkmsg_log & DEVKMSG_LOG_MASK_OFF)
return -EPERM;
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
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
/* write-only does not need any file context */
if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
SYSLOG_FROM_READER);
if (err)
return err;
}
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
2021-08-30 15:17:01 +08:00
user = kvmalloc(sizeof(struct devkmsg_user), GFP_KERNEL);
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
if (!user)
return -ENOMEM;
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
ratelimit_default_init(&user->rs);
ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE);
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
mutex_init(&user->lock);
prb_rec_init_rd(&user->record, &user->info,
&user->text_buf[0], sizeof(user->text_buf));
atomic64_set(&user->seq, prb_first_valid_seq(prb));
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
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;
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
ratelimit_state_exit(&user->rs);
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
mutex_destroy(&user->lock);
2021-08-30 15:17:01 +08:00
kvfree(user);
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
return 0;
}
const struct file_operations kmsg_fops = {
.open = devkmsg_open,
.read = devkmsg_read,
.write_iter = devkmsg_write,
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
.llseek = devkmsg_llseek,
.poll = devkmsg_poll,
.release = devkmsg_release,
};
crash: move crashkernel parsing and vmcore related code under CONFIG_CRASH_CORE Patch series "kexec/fadump: remove dependency with CONFIG_KEXEC and reuse crashkernel parameter for fadump", v4. Traditionally, kdump is used to save vmcore in case of a crash. Some architectures like powerpc can save vmcore using architecture specific support instead of kexec/kdump mechanism. Such architecture specific support also needs to reserve memory, to be used by dump capture kernel. crashkernel parameter can be a reused, for memory reservation, by such architecture specific infrastructure. This patchset removes dependency with CONFIG_KEXEC for crashkernel parameter and vmcoreinfo related code as it can be reused without kexec support. Also, crashkernel parameter is reused instead of fadump_reserve_mem to reserve memory for fadump. The first patch moves crashkernel parameter parsing and vmcoreinfo related code under CONFIG_CRASH_CORE instead of CONFIG_KEXEC_CORE. The second patch reuses the definitions of append_elf_note() & final_note() functions under CONFIG_CRASH_CORE in IA64 arch code. The third patch removes dependency on CONFIG_KEXEC for firmware-assisted dump (fadump) in powerpc. The next patch reuses crashkernel parameter for reserving memory for fadump, instead of the fadump_reserve_mem parameter. This has the advantage of using all syntaxes crashkernel parameter supports, for fadump as well. The last patch updates fadump kernel documentation about use of crashkernel parameter. This patch (of 5): Traditionally, kdump is used to save vmcore in case of a crash. Some architectures like powerpc can save vmcore using architecture specific support instead of kexec/kdump mechanism. Such architecture specific support also needs to reserve memory, to be used by dump capture kernel. crashkernel parameter can be a reused, for memory reservation, by such architecture specific infrastructure. But currently, code related to vmcoreinfo and parsing of crashkernel parameter is built under CONFIG_KEXEC_CORE. This patch introduces CONFIG_CRASH_CORE and moves the above mentioned code under this config, allowing code reuse without dependency on CONFIG_KEXEC. There is no functional change with this patch. Link: http://lkml.kernel.org/r/149035338104.6881.4550894432615189948.stgit@hbathini.in.ibm.com Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com> Acked-by: Dave Young <dyoung@redhat.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-09 06:56:18 +08:00
#ifdef CONFIG_CRASH_CORE
/*
* This appends the listed symbols to /proc/vmcore
*
* /proc/vmcore is used by various utilities, 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.
*/
crash: move crashkernel parsing and vmcore related code under CONFIG_CRASH_CORE Patch series "kexec/fadump: remove dependency with CONFIG_KEXEC and reuse crashkernel parameter for fadump", v4. Traditionally, kdump is used to save vmcore in case of a crash. Some architectures like powerpc can save vmcore using architecture specific support instead of kexec/kdump mechanism. Such architecture specific support also needs to reserve memory, to be used by dump capture kernel. crashkernel parameter can be a reused, for memory reservation, by such architecture specific infrastructure. This patchset removes dependency with CONFIG_KEXEC for crashkernel parameter and vmcoreinfo related code as it can be reused without kexec support. Also, crashkernel parameter is reused instead of fadump_reserve_mem to reserve memory for fadump. The first patch moves crashkernel parameter parsing and vmcoreinfo related code under CONFIG_CRASH_CORE instead of CONFIG_KEXEC_CORE. The second patch reuses the definitions of append_elf_note() & final_note() functions under CONFIG_CRASH_CORE in IA64 arch code. The third patch removes dependency on CONFIG_KEXEC for firmware-assisted dump (fadump) in powerpc. The next patch reuses crashkernel parameter for reserving memory for fadump, instead of the fadump_reserve_mem parameter. This has the advantage of using all syntaxes crashkernel parameter supports, for fadump as well. The last patch updates fadump kernel documentation about use of crashkernel parameter. This patch (of 5): Traditionally, kdump is used to save vmcore in case of a crash. Some architectures like powerpc can save vmcore using architecture specific support instead of kexec/kdump mechanism. Such architecture specific support also needs to reserve memory, to be used by dump capture kernel. crashkernel parameter can be a reused, for memory reservation, by such architecture specific infrastructure. But currently, code related to vmcoreinfo and parsing of crashkernel parameter is built under CONFIG_KEXEC_CORE. This patch introduces CONFIG_CRASH_CORE and moves the above mentioned code under this config, allowing code reuse without dependency on CONFIG_KEXEC. There is no functional change with this patch. Link: http://lkml.kernel.org/r/149035338104.6881.4550894432615189948.stgit@hbathini.in.ibm.com Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com> Acked-by: Dave Young <dyoung@redhat.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-09 06:56:18 +08:00
void log_buf_vmcoreinfo_setup(void)
{
struct dev_printk_info *dev_info = NULL;
VMCOREINFO_SYMBOL(prb);
VMCOREINFO_SYMBOL(printk_rb_static);
VMCOREINFO_SYMBOL(clear_seq);
/*
* Export struct size and field offsets. User space tools can
* parse it and detect any changes to structure down the line.
*/
VMCOREINFO_STRUCT_SIZE(printk_ringbuffer);
VMCOREINFO_OFFSET(printk_ringbuffer, desc_ring);
VMCOREINFO_OFFSET(printk_ringbuffer, text_data_ring);
VMCOREINFO_OFFSET(printk_ringbuffer, fail);
VMCOREINFO_STRUCT_SIZE(prb_desc_ring);
VMCOREINFO_OFFSET(prb_desc_ring, count_bits);
VMCOREINFO_OFFSET(prb_desc_ring, descs);
VMCOREINFO_OFFSET(prb_desc_ring, infos);
VMCOREINFO_OFFSET(prb_desc_ring, head_id);
VMCOREINFO_OFFSET(prb_desc_ring, tail_id);
VMCOREINFO_STRUCT_SIZE(prb_desc);
VMCOREINFO_OFFSET(prb_desc, state_var);
VMCOREINFO_OFFSET(prb_desc, text_blk_lpos);
VMCOREINFO_STRUCT_SIZE(prb_data_blk_lpos);
VMCOREINFO_OFFSET(prb_data_blk_lpos, begin);
VMCOREINFO_OFFSET(prb_data_blk_lpos, next);
VMCOREINFO_STRUCT_SIZE(printk_info);
VMCOREINFO_OFFSET(printk_info, seq);
VMCOREINFO_OFFSET(printk_info, ts_nsec);
VMCOREINFO_OFFSET(printk_info, text_len);
VMCOREINFO_OFFSET(printk_info, caller_id);
VMCOREINFO_OFFSET(printk_info, dev_info);
VMCOREINFO_STRUCT_SIZE(dev_printk_info);
VMCOREINFO_OFFSET(dev_printk_info, subsystem);
VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem));
VMCOREINFO_OFFSET(dev_printk_info, device);
VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device));
VMCOREINFO_STRUCT_SIZE(prb_data_ring);
VMCOREINFO_OFFSET(prb_data_ring, size_bits);
VMCOREINFO_OFFSET(prb_data_ring, data);
VMCOREINFO_OFFSET(prb_data_ring, head_lpos);
VMCOREINFO_OFFSET(prb_data_ring, tail_lpos);
VMCOREINFO_SIZE(atomic_long_t);
VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter);
VMCOREINFO_STRUCT_SIZE(latched_seq);
VMCOREINFO_OFFSET(latched_seq, val);
}
#endif
/* requested log_buf_len from kernel cmdline */
static unsigned long __initdata new_log_buf_len;
printk: move power of 2 practice of ring buffer size to a helper In practice the power of 2 practice of the size of the kernel ring buffer remains purely historical but not a requirement, specially now that we have LOG_ALIGN and use it for both static and dynamic allocations. It could have helped with implicit alignment back in the days given the even the dynamically sized ring buffer was guaranteed to be aligned so long as CONFIG_LOG_BUF_SHIFT was set to produce a __LOG_BUF_LEN which is architecture aligned, since log_buf_len=n would be allowed only if it was > __LOG_BUF_LEN and we always ended up rounding the log_buf_len=n to the next power of 2 with roundup_pow_of_two(), any multiple of 2 then should be also architecture aligned. These assumptions of course relied heavily on CONFIG_LOG_BUF_SHIFT producing an aligned value but users can always change this. We now have precise alignment requirements set for the log buffer size for both static and dynamic allocations, but lets upkeep the old practice of using powers of 2 for its size to help with easy expected scalable values and the allocators for dynamic allocations. We'll reuse this later so move this into a helper. Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com> Cc: Andrew Lunn <andrew@lunn.ch> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Petr Mladek <pmladek@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Arun KS <arunks.linux@gmail.com> Cc: Kees Cook <keescook@chromium.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:52 +08:00
/* we practice scaling the ring buffer by powers of 2 */
static void __init log_buf_len_update(u64 size)
{
if (size > (u64)LOG_BUF_LEN_MAX) {
size = (u64)LOG_BUF_LEN_MAX;
pr_err("log_buf over 2G is not supported.\n");
}
if (size)
size = roundup_pow_of_two(size);
if (size > log_buf_len)
new_log_buf_len = (unsigned long)size;
printk: move power of 2 practice of ring buffer size to a helper In practice the power of 2 practice of the size of the kernel ring buffer remains purely historical but not a requirement, specially now that we have LOG_ALIGN and use it for both static and dynamic allocations. It could have helped with implicit alignment back in the days given the even the dynamically sized ring buffer was guaranteed to be aligned so long as CONFIG_LOG_BUF_SHIFT was set to produce a __LOG_BUF_LEN which is architecture aligned, since log_buf_len=n would be allowed only if it was > __LOG_BUF_LEN and we always ended up rounding the log_buf_len=n to the next power of 2 with roundup_pow_of_two(), any multiple of 2 then should be also architecture aligned. These assumptions of course relied heavily on CONFIG_LOG_BUF_SHIFT producing an aligned value but users can always change this. We now have precise alignment requirements set for the log buffer size for both static and dynamic allocations, but lets upkeep the old practice of using powers of 2 for its size to help with easy expected scalable values and the allocators for dynamic allocations. We'll reuse this later so move this into a helper. Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com> Cc: Andrew Lunn <andrew@lunn.ch> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Petr Mladek <pmladek@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Arun KS <arunks.linux@gmail.com> Cc: Kees Cook <keescook@chromium.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:52 +08:00
}
/* save requested log_buf_len since it's too early to process it */
static int __init log_buf_len_setup(char *str)
{
u64 size;
if (!str)
return -EINVAL;
size = memparse(str, &str);
printk: move power of 2 practice of ring buffer size to a helper In practice the power of 2 practice of the size of the kernel ring buffer remains purely historical but not a requirement, specially now that we have LOG_ALIGN and use it for both static and dynamic allocations. It could have helped with implicit alignment back in the days given the even the dynamically sized ring buffer was guaranteed to be aligned so long as CONFIG_LOG_BUF_SHIFT was set to produce a __LOG_BUF_LEN which is architecture aligned, since log_buf_len=n would be allowed only if it was > __LOG_BUF_LEN and we always ended up rounding the log_buf_len=n to the next power of 2 with roundup_pow_of_two(), any multiple of 2 then should be also architecture aligned. These assumptions of course relied heavily on CONFIG_LOG_BUF_SHIFT producing an aligned value but users can always change this. We now have precise alignment requirements set for the log buffer size for both static and dynamic allocations, but lets upkeep the old practice of using powers of 2 for its size to help with easy expected scalable values and the allocators for dynamic allocations. We'll reuse this later so move this into a helper. Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com> Cc: Andrew Lunn <andrew@lunn.ch> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Petr Mladek <pmladek@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Arun KS <arunks.linux@gmail.com> Cc: Kees Cook <keescook@chromium.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:52 +08:00
log_buf_len_update(size);
return 0;
}
early_param("log_buf_len", log_buf_len_setup);
#ifdef CONFIG_SMP
#define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT)
printk: allow increasing the ring buffer depending on the number of CPUs The default size of the ring buffer is too small for machines with a large amount of CPUs under heavy load. What ends up happening when debugging is the ring buffer overlaps and chews up old messages making debugging impossible unless the size is passed as a kernel parameter. An idle system upon boot up will on average spew out only about one or two extra lines but where this really matters is on heavy load and that will vary widely depending on the system and environment. There are mechanisms to help increase the kernel ring buffer for tracing through debugfs, and those interfaces even allow growing the kernel ring buffer per CPU. We also have a static value which can be passed upon boot. Relying on debugfs however is not ideal for production, and relying on the value passed upon bootup is can only used *after* an issue has creeped up. Instead of being reactive this adds a proactive measure which lets you scale the amount of contributions you'd expect to the kernel ring buffer under load by each CPU in the worst case scenario. We use num_possible_cpus() to avoid complexities which could be introduced by dynamically changing the ring buffer size at run time, num_possible_cpus() lets us use the upper limit on possible number of CPUs therefore avoiding having to deal with hotplugging CPUs on and off. This introduces the kernel configuration option LOG_CPU_MAX_BUF_SHIFT which is used to specify the maximum amount of contributions to the kernel ring buffer in the worst case before the kernel ring buffer flips over, the size is specified as a power of 2. The total amount of contributions made by each CPU must be greater than half of the default kernel ring buffer size (1 << LOG_BUF_SHIFT bytes) in order to trigger an increase upon bootup. The kernel ring buffer is increased to the next power of two that would fit the required minimum kernel ring buffer size plus the additional CPU contribution. For example if LOG_BUF_SHIFT is 18 (256 KB) you'd require at least 128 KB contributions by other CPUs in order to trigger an increase of the kernel ring buffer. With a LOG_CPU_BUF_SHIFT of 12 (4 KB) you'd require at least anything over > 64 possible CPUs to trigger an increase. If you had 128 possible CPUs the amount of minimum required kernel ring buffer bumps to: ((1 << 18) + ((128 - 1) * (1 << 12))) / 1024 = 764 KB Since we require the ring buffer to be a power of two the new required size would be 1024 KB. This CPU contributions are ignored when the "log_buf_len" kernel parameter is used as it forces the exact size of the ring buffer to an expected power of two value. [pmladek@suse.cz: fix build] Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.cz> Tested-by: Davidlohr Bueso <davidlohr@hp.com> Tested-by: Petr Mladek <pmladek@suse.cz> Reviewed-by: Davidlohr Bueso <davidlohr@hp.com> Cc: Andrew Lunn <andrew@lunn.ch> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Petr Mladek <pmladek@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Arun KS <arunks.linux@gmail.com> Cc: Kees Cook <keescook@chromium.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:56 +08:00
static void __init log_buf_add_cpu(void)
{
unsigned int cpu_extra;
/*
* archs should set up cpu_possible_bits properly with
* set_cpu_possible() after setup_arch() but just in
* case lets ensure this is valid.
*/
if (num_possible_cpus() == 1)
return;
cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN;
/* by default this will only continue through for large > 64 CPUs */
if (cpu_extra <= __LOG_BUF_LEN / 2)
return;
pr_info("log_buf_len individual max cpu contribution: %d bytes\n",
__LOG_CPU_MAX_BUF_LEN);
pr_info("log_buf_len total cpu_extra contributions: %d bytes\n",
cpu_extra);
pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN);
log_buf_len_update(cpu_extra + __LOG_BUF_LEN);
}
#else /* !CONFIG_SMP */
static inline void log_buf_add_cpu(void) {}
#endif /* CONFIG_SMP */
printk: allow increasing the ring buffer depending on the number of CPUs The default size of the ring buffer is too small for machines with a large amount of CPUs under heavy load. What ends up happening when debugging is the ring buffer overlaps and chews up old messages making debugging impossible unless the size is passed as a kernel parameter. An idle system upon boot up will on average spew out only about one or two extra lines but where this really matters is on heavy load and that will vary widely depending on the system and environment. There are mechanisms to help increase the kernel ring buffer for tracing through debugfs, and those interfaces even allow growing the kernel ring buffer per CPU. We also have a static value which can be passed upon boot. Relying on debugfs however is not ideal for production, and relying on the value passed upon bootup is can only used *after* an issue has creeped up. Instead of being reactive this adds a proactive measure which lets you scale the amount of contributions you'd expect to the kernel ring buffer under load by each CPU in the worst case scenario. We use num_possible_cpus() to avoid complexities which could be introduced by dynamically changing the ring buffer size at run time, num_possible_cpus() lets us use the upper limit on possible number of CPUs therefore avoiding having to deal with hotplugging CPUs on and off. This introduces the kernel configuration option LOG_CPU_MAX_BUF_SHIFT which is used to specify the maximum amount of contributions to the kernel ring buffer in the worst case before the kernel ring buffer flips over, the size is specified as a power of 2. The total amount of contributions made by each CPU must be greater than half of the default kernel ring buffer size (1 << LOG_BUF_SHIFT bytes) in order to trigger an increase upon bootup. The kernel ring buffer is increased to the next power of two that would fit the required minimum kernel ring buffer size plus the additional CPU contribution. For example if LOG_BUF_SHIFT is 18 (256 KB) you'd require at least 128 KB contributions by other CPUs in order to trigger an increase of the kernel ring buffer. With a LOG_CPU_BUF_SHIFT of 12 (4 KB) you'd require at least anything over > 64 possible CPUs to trigger an increase. If you had 128 possible CPUs the amount of minimum required kernel ring buffer bumps to: ((1 << 18) + ((128 - 1) * (1 << 12))) / 1024 = 764 KB Since we require the ring buffer to be a power of two the new required size would be 1024 KB. This CPU contributions are ignored when the "log_buf_len" kernel parameter is used as it forces the exact size of the ring buffer to an expected power of two value. [pmladek@suse.cz: fix build] Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.cz> Tested-by: Davidlohr Bueso <davidlohr@hp.com> Tested-by: Petr Mladek <pmladek@suse.cz> Reviewed-by: Davidlohr Bueso <davidlohr@hp.com> Cc: Andrew Lunn <andrew@lunn.ch> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Petr Mladek <pmladek@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Arun KS <arunks.linux@gmail.com> Cc: Kees Cook <keescook@chromium.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:56 +08:00
printk: queue wake_up_klogd irq_work only if per-CPU areas are ready printk_deferred(), similarly to printk_safe/printk_nmi, does not immediately attempt to print a new message on the consoles, avoiding calls into non-reentrant kernel paths, e.g. scheduler or timekeeping, which potentially can deadlock the system. Those printk() flavors, instead, rely on per-CPU flush irq_work to print messages from safer contexts. For same reasons (recursive scheduler or timekeeping calls) printk() uses per-CPU irq_work in order to wake up user space syslog/kmsg readers. However, only printk_safe/printk_nmi do make sure that per-CPU areas have been initialised and that it's safe to modify per-CPU irq_work. This means that, for instance, should printk_deferred() be invoked "too early", that is before per-CPU areas are initialised, printk_deferred() will perform illegal per-CPU access. Lech Perczak [0] reports that after commit 1b710b1b10ef ("char/random: silence a lockdep splat with printk()") user-space syslog/kmsg readers are not able to read new kernel messages. The reason is printk_deferred() being called too early (as was pointed out by Petr and John). Fix printk_deferred() and do not queue per-CPU irq_work before per-CPU areas are initialized. Link: https://lore.kernel.org/lkml/aa0732c6-5c4e-8a8b-a1c1-75ebe3dca05b@camlintechnologies.com/ Reported-by: Lech Perczak <l.perczak@camlintechnologies.com> Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Tested-by: Jann Horn <jannh@google.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Theodore Ts'o <tytso@mit.edu> Cc: John Ogness <john.ogness@linutronix.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-03 19:30:02 +08:00
static void __init set_percpu_data_ready(void)
{
__printk_percpu_data_ready = true;
}
static unsigned int __init add_to_rb(struct printk_ringbuffer *rb,
struct printk_record *r)
{
struct prb_reserved_entry e;
struct printk_record dest_r;
prb_rec_init_wr(&dest_r, r->info->text_len);
if (!prb_reserve(&e, rb, &dest_r))
return 0;
memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len);
dest_r.info->text_len = r->info->text_len;
dest_r.info->facility = r->info->facility;
dest_r.info->level = r->info->level;
dest_r.info->flags = r->info->flags;
dest_r.info->ts_nsec = r->info->ts_nsec;
dest_r.info->caller_id = r->info->caller_id;
memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info));
prb_final_commit(&e);
return prb_record_text_space(&e);
}
static char setup_text_buf[LOG_LINE_MAX] __initdata;
void __init setup_log_buf(int early)
{
struct printk_info *new_infos;
unsigned int new_descs_count;
struct prb_desc *new_descs;
struct printk_info info;
struct printk_record r;
unsigned int text_size;
size_t new_descs_size;
size_t new_infos_size;
unsigned long flags;
char *new_log_buf;
unsigned int free;
u64 seq;
printk: queue wake_up_klogd irq_work only if per-CPU areas are ready printk_deferred(), similarly to printk_safe/printk_nmi, does not immediately attempt to print a new message on the consoles, avoiding calls into non-reentrant kernel paths, e.g. scheduler or timekeeping, which potentially can deadlock the system. Those printk() flavors, instead, rely on per-CPU flush irq_work to print messages from safer contexts. For same reasons (recursive scheduler or timekeeping calls) printk() uses per-CPU irq_work in order to wake up user space syslog/kmsg readers. However, only printk_safe/printk_nmi do make sure that per-CPU areas have been initialised and that it's safe to modify per-CPU irq_work. This means that, for instance, should printk_deferred() be invoked "too early", that is before per-CPU areas are initialised, printk_deferred() will perform illegal per-CPU access. Lech Perczak [0] reports that after commit 1b710b1b10ef ("char/random: silence a lockdep splat with printk()") user-space syslog/kmsg readers are not able to read new kernel messages. The reason is printk_deferred() being called too early (as was pointed out by Petr and John). Fix printk_deferred() and do not queue per-CPU irq_work before per-CPU areas are initialized. Link: https://lore.kernel.org/lkml/aa0732c6-5c4e-8a8b-a1c1-75ebe3dca05b@camlintechnologies.com/ Reported-by: Lech Perczak <l.perczak@camlintechnologies.com> Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Tested-by: Jann Horn <jannh@google.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Theodore Ts'o <tytso@mit.edu> Cc: John Ogness <john.ogness@linutronix.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-03 19:30:02 +08:00
/*
* Some archs call setup_log_buf() multiple times - first is very
* early, e.g. from setup_arch(), and second - when percpu_areas
* are initialised.
*/
if (!early)
set_percpu_data_ready();
printk: allow increasing the ring buffer depending on the number of CPUs The default size of the ring buffer is too small for machines with a large amount of CPUs under heavy load. What ends up happening when debugging is the ring buffer overlaps and chews up old messages making debugging impossible unless the size is passed as a kernel parameter. An idle system upon boot up will on average spew out only about one or two extra lines but where this really matters is on heavy load and that will vary widely depending on the system and environment. There are mechanisms to help increase the kernel ring buffer for tracing through debugfs, and those interfaces even allow growing the kernel ring buffer per CPU. We also have a static value which can be passed upon boot. Relying on debugfs however is not ideal for production, and relying on the value passed upon bootup is can only used *after* an issue has creeped up. Instead of being reactive this adds a proactive measure which lets you scale the amount of contributions you'd expect to the kernel ring buffer under load by each CPU in the worst case scenario. We use num_possible_cpus() to avoid complexities which could be introduced by dynamically changing the ring buffer size at run time, num_possible_cpus() lets us use the upper limit on possible number of CPUs therefore avoiding having to deal with hotplugging CPUs on and off. This introduces the kernel configuration option LOG_CPU_MAX_BUF_SHIFT which is used to specify the maximum amount of contributions to the kernel ring buffer in the worst case before the kernel ring buffer flips over, the size is specified as a power of 2. The total amount of contributions made by each CPU must be greater than half of the default kernel ring buffer size (1 << LOG_BUF_SHIFT bytes) in order to trigger an increase upon bootup. The kernel ring buffer is increased to the next power of two that would fit the required minimum kernel ring buffer size plus the additional CPU contribution. For example if LOG_BUF_SHIFT is 18 (256 KB) you'd require at least 128 KB contributions by other CPUs in order to trigger an increase of the kernel ring buffer. With a LOG_CPU_BUF_SHIFT of 12 (4 KB) you'd require at least anything over > 64 possible CPUs to trigger an increase. If you had 128 possible CPUs the amount of minimum required kernel ring buffer bumps to: ((1 << 18) + ((128 - 1) * (1 << 12))) / 1024 = 764 KB Since we require the ring buffer to be a power of two the new required size would be 1024 KB. This CPU contributions are ignored when the "log_buf_len" kernel parameter is used as it forces the exact size of the ring buffer to an expected power of two value. [pmladek@suse.cz: fix build] Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.cz> Tested-by: Davidlohr Bueso <davidlohr@hp.com> Tested-by: Petr Mladek <pmladek@suse.cz> Reviewed-by: Davidlohr Bueso <davidlohr@hp.com> Cc: Andrew Lunn <andrew@lunn.ch> Cc: Stephen Warren <swarren@wwwdotorg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Petr Mladek <pmladek@suse.cz> Cc: Joe Perches <joe@perches.com> Cc: Arun KS <arunks.linux@gmail.com> Cc: Kees Cook <keescook@chromium.org> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:56 +08:00
if (log_buf != __log_buf)
return;
if (!early && !new_log_buf_len)
log_buf_add_cpu();
if (!new_log_buf_len)
return;
new_descs_count = new_log_buf_len >> PRB_AVGBITS;
if (new_descs_count == 0) {
pr_err("new_log_buf_len: %lu too small\n", new_log_buf_len);
return;
}
memblock: drop memblock_alloc_*_nopanic() variants As all the memblock allocation functions return NULL in case of error rather than panic(), the duplicates with _nopanic suffix can be removed. Link: http://lkml.kernel.org/r/1548057848-15136-22-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Petr Mladek <pmladek@suse.com> [printk] Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Christoph Hellwig <hch@lst.de> Cc: "David S. Miller" <davem@davemloft.net> Cc: Dennis Zhou <dennis@kernel.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Guo Ren <ren_guo@c-sky.com> [c-sky] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Juergen Gross <jgross@suse.com> [Xen] Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Burton <paul.burton@mips.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-12 14:30:42 +08:00
new_log_buf = memblock_alloc(new_log_buf_len, LOG_ALIGN);
if (unlikely(!new_log_buf)) {
pr_err("log_buf_len: %lu text bytes not available\n",
new_log_buf_len);
return;
}
new_descs_size = new_descs_count * sizeof(struct prb_desc);
new_descs = memblock_alloc(new_descs_size, LOG_ALIGN);
if (unlikely(!new_descs)) {
pr_err("log_buf_len: %zu desc bytes not available\n",
new_descs_size);
goto err_free_log_buf;
}
new_infos_size = new_descs_count * sizeof(struct printk_info);
new_infos = memblock_alloc(new_infos_size, LOG_ALIGN);
if (unlikely(!new_infos)) {
pr_err("log_buf_len: %zu info bytes not available\n",
new_infos_size);
goto err_free_descs;
}
prb_rec_init_rd(&r, &info, &setup_text_buf[0], sizeof(setup_text_buf));
prb_init(&printk_rb_dynamic,
new_log_buf, ilog2(new_log_buf_len),
new_descs, ilog2(new_descs_count),
new_infos);
local_irq_save(flags);
log_buf_len = new_log_buf_len;
log_buf = new_log_buf;
new_log_buf_len = 0;
free = __LOG_BUF_LEN;
prb_for_each_record(0, &printk_rb_static, seq, &r) {
text_size = add_to_rb(&printk_rb_dynamic, &r);
if (text_size > free)
free = 0;
else
free -= text_size;
}
prb = &printk_rb_dynamic;
local_irq_restore(flags);
/*
* Copy any remaining messages that might have appeared from
* NMI context after copying but before switching to the
* dynamic buffer.
*/
prb_for_each_record(seq, &printk_rb_static, seq, &r) {
text_size = add_to_rb(&printk_rb_dynamic, &r);
if (text_size > free)
free = 0;
else
free -= text_size;
}
if (seq != prb_next_seq(&printk_rb_static)) {
pr_err("dropped %llu messages\n",
prb_next_seq(&printk_rb_static) - seq);
}
pr_info("log_buf_len: %u bytes\n", log_buf_len);
pr_info("early log buf free: %u(%u%%)\n",
free, (free * 100) / __LOG_BUF_LEN);
return;
err_free_descs:
memblock_free(new_descs, new_descs_size);
err_free_log_buf:
memblock_free(new_log_buf, new_log_buf_len);
}
static bool __read_mostly ignore_loglevel;
static int __init ignore_loglevel_setup(char *str)
{
ignore_loglevel = true;
pr_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 (prints all kernel messages to the console)");
printk: introduce suppress_message_printing() Messages' levels and console log level are inspected when the actual printing occurs, which may provoke console_unlock() and console_cont_flush() to waste CPU cycles on every message that has loglevel above the current console_loglevel. Schematically, console_unlock() does the following: console_unlock() { ... for (;;) { ... raw_spin_lock_irqsave(&logbuf_lock, flags); skip: msg = log_from_idx(console_idx); if (msg->flags & LOG_NOCONS) { ... goto skip; } level = msg->level; len += msg_print_text(); >> sprintfs memcpy, etc. if (nr_ext_console_drivers) { ext_len = msg_print_ext_header(); >> scnprintf ext_len += msg_print_ext_body(); >> scnprintfs etc. } ... raw_spin_unlock(&logbuf_lock); call_console_drivers(level, ext_text, ext_len, text, len) { if (level >= console_loglevel && >> drop the message !ignore_loglevel) return; console->write(...); } local_irq_restore(flags); } ... } The thing here is this deferred `level >= console_loglevel' check. We are wasting CPU cycles on sprintfs/memcpy/etc. preparing the messages that we will eventually drop. This can be huge when we register a new CON_PRINTBUFFER console, for instance. For every such a console register_console() resets the console_seq, console_idx, console_prev and sets a `exclusive console' pointer to replay the log buffer to that just-registered console. And there can be a lot of messages to replay, in the worst case most of which can be dropped after console_loglevel test. We know messages' levels long before we call msg_print_text() and friends, so we can just move console_loglevel check out of call_console_drivers() and format a new message only if we are sure that it won't be dropped. The patch factors out loglevel check into suppress_message_printing() function and tests message->level and console_loglevel before formatting functions in console_unlock() and console_cont_flush() are getting executed. This improves things not only for exclusive CON_PRINTBUFFER consoles, but for every console_unlock() that attempts to print a message of level above the console_loglevel. Link: http://lkml.kernel.org/r/20160627135012.8229-1-sergey.senozhatsky@gmail.com Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Tejun Heo <tj@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Calvin Owens <calvinowens@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-08-03 05:03:56 +08:00
static bool suppress_message_printing(int level)
{
return (level >= console_loglevel && !ignore_loglevel);
}
#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 0;
}
early_param("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_RUNNING)
printk: introduce suppress_message_printing() Messages' levels and console log level are inspected when the actual printing occurs, which may provoke console_unlock() and console_cont_flush() to waste CPU cycles on every message that has loglevel above the current console_loglevel. Schematically, console_unlock() does the following: console_unlock() { ... for (;;) { ... raw_spin_lock_irqsave(&logbuf_lock, flags); skip: msg = log_from_idx(console_idx); if (msg->flags & LOG_NOCONS) { ... goto skip; } level = msg->level; len += msg_print_text(); >> sprintfs memcpy, etc. if (nr_ext_console_drivers) { ext_len = msg_print_ext_header(); >> scnprintf ext_len += msg_print_ext_body(); >> scnprintfs etc. } ... raw_spin_unlock(&logbuf_lock); call_console_drivers(level, ext_text, ext_len, text, len) { if (level >= console_loglevel && >> drop the message !ignore_loglevel) return; console->write(...); } local_irq_restore(flags); } ... } The thing here is this deferred `level >= console_loglevel' check. We are wasting CPU cycles on sprintfs/memcpy/etc. preparing the messages that we will eventually drop. This can be huge when we register a new CON_PRINTBUFFER console, for instance. For every such a console register_console() resets the console_seq, console_idx, console_prev and sets a `exclusive console' pointer to replay the log buffer to that just-registered console. And there can be a lot of messages to replay, in the worst case most of which can be dropped after console_loglevel test. We know messages' levels long before we call msg_print_text() and friends, so we can just move console_loglevel check out of call_console_drivers() and format a new message only if we are sure that it won't be dropped. The patch factors out loglevel check into suppress_message_printing() function and tests message->level and console_loglevel before formatting functions in console_unlock() and console_cont_flush() are getting executed. This improves things not only for exclusive CON_PRINTBUFFER consoles, but for every console_unlock() that attempts to print a message of level above the console_loglevel. Link: http://lkml.kernel.org/r/20160627135012.8229-1-sergey.senozhatsky@gmail.com Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Tejun Heo <tj@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Calvin Owens <calvinowens@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-08-03 05:03:56 +08:00
|| suppress_message_printing(level)) {
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
static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME);
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
module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR);
static size_t print_syslog(unsigned int level, char *buf)
{
return sprintf(buf, "<%u>", level);
}
printk: fix incorrect length from print_time() when seconds > 99999 print_prefix() passes a NULL buf to print_time() to get the length of the time prefix; when printk times are enabled, the current code just returns the constant 15, which matches the format "[%5lu.%06lu] " used to print the time value. However, this is obviously incorrect when the whole seconds part of the time gets beyond 5 digits (100000 seconds is a bit more than a day of uptime). The simple fix is to use snprintf(NULL, 0, ...) to calculate the actual length of the time prefix. This could be micro-optimized but it seems better to have simpler, more readable code here. The bug leads to the syslog system call miscomputing which messages fit into the userspace buffer. If there are enough messages to fill log_buf_len and some have a timestamp >= 100000, dmesg may fail with: # dmesg klogctl: Bad address When this happens, strace shows that the failure is indeed EFAULT due to the kernel mistakenly accessing past the end of dmesg's buffer, since dmesg asks the kernel how big a buffer it needs, allocates a bit more, and then gets an error when it asks the kernel to fill it: syslog(0xa, 0, 0) = 1048576 mmap(NULL, 1052672, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7fa4d25d2000 syslog(0x3, 0x7fa4d25d2010, 0x100008) = -1 EFAULT (Bad address) As far as I can see, the bug has been there as long as print_time(), which comes from commit 084681d14e42 ("printk: flush continuation lines immediately to console") in 3.5-rc5. Signed-off-by: Roland Dreier <roland@purestorage.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Joe Perches <joe@perches.com> Cc: Sylvain Munaut <s.munaut@whatever-company.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-01-05 07:35:50 +08:00
static size_t print_time(u64 ts, char *buf)
{
unsigned long rem_nsec = do_div(ts, 1000000000);
printk: Add caller information to printk() output. Sometimes we want to print a series of printk() messages to consoles without being disturbed by concurrent printk() from interrupts and/or other threads. But we can't enforce printk() callers to use their local buffers because we need to ask them to make too much changes. Also, even buffering up to one line inside printk() might cause failing to emit an important clue under critical situation. Therefore, instead of trying to help buffering, let's try to help reconstructing messages by saving caller information as of calling log_store() and adding it as "[T$thread_id]" or "[C$processor_id]" upon printing to consoles. Some examples for console output: [ 1.222773][ T1] x86: Booting SMP configuration: [ 2.779635][ T1] pci 0000:00:01.0: PCI bridge to [bus 01] [ 5.069193][ T268] Fusion MPT base driver 3.04.20 [ 9.316504][ C2] random: fast init done [ 13.413336][ T3355] Initialized host personality Some examples for /dev/kmsg output: 6,496,1222773,-,caller=T1;x86: Booting SMP configuration: 6,968,2779635,-,caller=T1;pci 0000:00:01.0: PCI bridge to [bus 01] SUBSYSTEM=pci DEVICE=+pci:0000:00:01.0 6,1353,5069193,-,caller=T268;Fusion MPT base driver 3.04.20 5,1526,9316504,-,caller=C2;random: fast init done 6,1575,13413336,-,caller=T3355;Initialized host personality Note that this patch changes max length of messages which can be printed by printk() or written to /dev/kmsg interface from 992 bytes to 976 bytes, based on an assumption that userspace won't try to write messages hitting that border line to /dev/kmsg interface. Link: http://lkml.kernel.org/r/93f19e57-5051-c67d-9af4-b17624062d44@i-love.sakura.ne.jp Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-12-18 05:05:04 +08:00
return sprintf(buf, "[%5lu.%06lu]",
(unsigned long)ts, rem_nsec / 1000);
}
printk: Add caller information to printk() output. Sometimes we want to print a series of printk() messages to consoles without being disturbed by concurrent printk() from interrupts and/or other threads. But we can't enforce printk() callers to use their local buffers because we need to ask them to make too much changes. Also, even buffering up to one line inside printk() might cause failing to emit an important clue under critical situation. Therefore, instead of trying to help buffering, let's try to help reconstructing messages by saving caller information as of calling log_store() and adding it as "[T$thread_id]" or "[C$processor_id]" upon printing to consoles. Some examples for console output: [ 1.222773][ T1] x86: Booting SMP configuration: [ 2.779635][ T1] pci 0000:00:01.0: PCI bridge to [bus 01] [ 5.069193][ T268] Fusion MPT base driver 3.04.20 [ 9.316504][ C2] random: fast init done [ 13.413336][ T3355] Initialized host personality Some examples for /dev/kmsg output: 6,496,1222773,-,caller=T1;x86: Booting SMP configuration: 6,968,2779635,-,caller=T1;pci 0000:00:01.0: PCI bridge to [bus 01] SUBSYSTEM=pci DEVICE=+pci:0000:00:01.0 6,1353,5069193,-,caller=T268;Fusion MPT base driver 3.04.20 5,1526,9316504,-,caller=C2;random: fast init done 6,1575,13413336,-,caller=T3355;Initialized host personality Note that this patch changes max length of messages which can be printed by printk() or written to /dev/kmsg interface from 992 bytes to 976 bytes, based on an assumption that userspace won't try to write messages hitting that border line to /dev/kmsg interface. Link: http://lkml.kernel.org/r/93f19e57-5051-c67d-9af4-b17624062d44@i-love.sakura.ne.jp Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-12-18 05:05:04 +08:00
#ifdef CONFIG_PRINTK_CALLER
static size_t print_caller(u32 id, char *buf)
{
char caller[12];
snprintf(caller, sizeof(caller), "%c%u",
id & 0x80000000 ? 'C' : 'T', id & ~0x80000000);
return sprintf(buf, "[%6s]", caller);
}
#else
#define print_caller(id, buf) 0
#endif
static size_t info_print_prefix(const struct printk_info *info, bool syslog,
bool time, char *buf)
{
size_t len = 0;
if (syslog)
len = print_syslog((info->facility << 3) | info->level, buf);
printk: Add caller information to printk() output. Sometimes we want to print a series of printk() messages to consoles without being disturbed by concurrent printk() from interrupts and/or other threads. But we can't enforce printk() callers to use their local buffers because we need to ask them to make too much changes. Also, even buffering up to one line inside printk() might cause failing to emit an important clue under critical situation. Therefore, instead of trying to help buffering, let's try to help reconstructing messages by saving caller information as of calling log_store() and adding it as "[T$thread_id]" or "[C$processor_id]" upon printing to consoles. Some examples for console output: [ 1.222773][ T1] x86: Booting SMP configuration: [ 2.779635][ T1] pci 0000:00:01.0: PCI bridge to [bus 01] [ 5.069193][ T268] Fusion MPT base driver 3.04.20 [ 9.316504][ C2] random: fast init done [ 13.413336][ T3355] Initialized host personality Some examples for /dev/kmsg output: 6,496,1222773,-,caller=T1;x86: Booting SMP configuration: 6,968,2779635,-,caller=T1;pci 0000:00:01.0: PCI bridge to [bus 01] SUBSYSTEM=pci DEVICE=+pci:0000:00:01.0 6,1353,5069193,-,caller=T268;Fusion MPT base driver 3.04.20 5,1526,9316504,-,caller=C2;random: fast init done 6,1575,13413336,-,caller=T3355;Initialized host personality Note that this patch changes max length of messages which can be printed by printk() or written to /dev/kmsg interface from 992 bytes to 976 bytes, based on an assumption that userspace won't try to write messages hitting that border line to /dev/kmsg interface. Link: http://lkml.kernel.org/r/93f19e57-5051-c67d-9af4-b17624062d44@i-love.sakura.ne.jp Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-12-18 05:05:04 +08:00
if (time)
len += print_time(info->ts_nsec, buf + len);
printk: Add caller information to printk() output. Sometimes we want to print a series of printk() messages to consoles without being disturbed by concurrent printk() from interrupts and/or other threads. But we can't enforce printk() callers to use their local buffers because we need to ask them to make too much changes. Also, even buffering up to one line inside printk() might cause failing to emit an important clue under critical situation. Therefore, instead of trying to help buffering, let's try to help reconstructing messages by saving caller information as of calling log_store() and adding it as "[T$thread_id]" or "[C$processor_id]" upon printing to consoles. Some examples for console output: [ 1.222773][ T1] x86: Booting SMP configuration: [ 2.779635][ T1] pci 0000:00:01.0: PCI bridge to [bus 01] [ 5.069193][ T268] Fusion MPT base driver 3.04.20 [ 9.316504][ C2] random: fast init done [ 13.413336][ T3355] Initialized host personality Some examples for /dev/kmsg output: 6,496,1222773,-,caller=T1;x86: Booting SMP configuration: 6,968,2779635,-,caller=T1;pci 0000:00:01.0: PCI bridge to [bus 01] SUBSYSTEM=pci DEVICE=+pci:0000:00:01.0 6,1353,5069193,-,caller=T268;Fusion MPT base driver 3.04.20 5,1526,9316504,-,caller=C2;random: fast init done 6,1575,13413336,-,caller=T3355;Initialized host personality Note that this patch changes max length of messages which can be printed by printk() or written to /dev/kmsg interface from 992 bytes to 976 bytes, based on an assumption that userspace won't try to write messages hitting that border line to /dev/kmsg interface. Link: http://lkml.kernel.org/r/93f19e57-5051-c67d-9af4-b17624062d44@i-love.sakura.ne.jp Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-12-18 05:05:04 +08:00
len += print_caller(info->caller_id, buf + len);
printk: Add caller information to printk() output. Sometimes we want to print a series of printk() messages to consoles without being disturbed by concurrent printk() from interrupts and/or other threads. But we can't enforce printk() callers to use their local buffers because we need to ask them to make too much changes. Also, even buffering up to one line inside printk() might cause failing to emit an important clue under critical situation. Therefore, instead of trying to help buffering, let's try to help reconstructing messages by saving caller information as of calling log_store() and adding it as "[T$thread_id]" or "[C$processor_id]" upon printing to consoles. Some examples for console output: [ 1.222773][ T1] x86: Booting SMP configuration: [ 2.779635][ T1] pci 0000:00:01.0: PCI bridge to [bus 01] [ 5.069193][ T268] Fusion MPT base driver 3.04.20 [ 9.316504][ C2] random: fast init done [ 13.413336][ T3355] Initialized host personality Some examples for /dev/kmsg output: 6,496,1222773,-,caller=T1;x86: Booting SMP configuration: 6,968,2779635,-,caller=T1;pci 0000:00:01.0: PCI bridge to [bus 01] SUBSYSTEM=pci DEVICE=+pci:0000:00:01.0 6,1353,5069193,-,caller=T268;Fusion MPT base driver 3.04.20 5,1526,9316504,-,caller=C2;random: fast init done 6,1575,13413336,-,caller=T3355;Initialized host personality Note that this patch changes max length of messages which can be printed by printk() or written to /dev/kmsg interface from 992 bytes to 976 bytes, based on an assumption that userspace won't try to write messages hitting that border line to /dev/kmsg interface. Link: http://lkml.kernel.org/r/93f19e57-5051-c67d-9af4-b17624062d44@i-love.sakura.ne.jp Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: syzkaller <syzkaller@googlegroups.com> Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-12-18 05:05:04 +08:00
if (IS_ENABLED(CONFIG_PRINTK_CALLER) || time) {
buf[len++] = ' ';
buf[len] = '\0';
}
return len;
}
/*
* Prepare the record for printing. The text is shifted within the given
* buffer to avoid a need for another one. The following operations are
* done:
*
* - Add prefix for each line.
* - Drop truncated lines that no longer fit into the buffer.
* - Add the trailing newline that has been removed in vprintk_store().
* - Add a string terminator.
*
* Since the produced string is always terminated, the maximum possible
* return value is @r->text_buf_size - 1;
*
* Return: The length of the updated/prepared text, including the added
* prefixes and the newline. The terminator is not counted. The dropped
* line(s) are not counted.
*/
static size_t record_print_text(struct printk_record *r, bool syslog,
bool time)
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
{
size_t text_len = r->info->text_len;
size_t buf_size = r->text_buf_size;
char *text = r->text_buf;
char prefix[PREFIX_MAX];
bool truncated = false;
size_t prefix_len;
size_t line_len;
size_t len = 0;
char *next;
/*
* If the message was truncated because the buffer was not large
* enough, treat the available text as if it were the full text.
*/
if (text_len > buf_size)
text_len = buf_size;
prefix_len = info_print_prefix(r->info, syslog, time, prefix);
/*
* @text_len: bytes of unprocessed text
* @line_len: bytes of current line _without_ newline
* @text: pointer to beginning of current line
* @len: number of bytes prepared in r->text_buf
*/
for (;;) {
next = memchr(text, '\n', text_len);
if (next) {
line_len = next - text;
} else {
/* Drop truncated line(s). */
if (truncated)
break;
line_len = text_len;
}
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
/*
* Truncate the text if there is not enough space to add the
* prefix and a trailing newline and a terminator.
*/
if (len + prefix_len + text_len + 1 + 1 > buf_size) {
/* Drop even the current line if no space. */
if (len + prefix_len + line_len + 1 + 1 > buf_size)
break;
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
text_len = buf_size - len - prefix_len - 1 - 1;
truncated = true;
}
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
memmove(text + prefix_len, text, text_len);
memcpy(text, prefix, prefix_len);
/*
* Increment the prepared length to include the text and
* prefix that were just moved+copied. Also increment for the
* newline at the end of this line. If this is the last line,
* there is no newline, but it will be added immediately below.
*/
len += prefix_len + line_len + 1;
if (text_len == line_len) {
/*
* This is the last line. Add the trailing newline
* removed in vprintk_store().
*/
text[prefix_len + line_len] = '\n';
break;
}
/*
* Advance beyond the added prefix and the related line with
* its newline.
*/
text += prefix_len + line_len + 1;
/*
* The remaining text has only decreased by the line with its
* newline.
*
* Note that @text_len can become zero. It happens when @text
* ended with a newline (either due to truncation or the
* original string ending with "\n\n"). The loop is correctly
* repeated and (if not truncated) an empty line with a prefix
* will be prepared.
*/
text_len -= line_len + 1;
}
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
/*
* If a buffer was provided, it will be terminated. Space for the
* string terminator is guaranteed to be available. The terminator is
* not counted in the return value.
*/
if (buf_size > 0)
r->text_buf[len] = 0;
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
return len;
}
static size_t get_record_print_text_size(struct printk_info *info,
unsigned int line_count,
bool syslog, bool time)
{
char prefix[PREFIX_MAX];
size_t prefix_len;
prefix_len = info_print_prefix(info, syslog, time, prefix);
/*
* Each line will be preceded with a prefix. The intermediate
* newlines are already within the text, but a final trailing
* newline will be added.
*/
return ((prefix_len * line_count) + info->text_len + 1);
}
/*
* Beginning with @start_seq, find the first record where it and all following
* records up to (but not including) @max_seq fit into @size.
*
* @max_seq is simply an upper bound and does not need to exist. If the caller
* does not require an upper bound, -1 can be used for @max_seq.
*/
static u64 find_first_fitting_seq(u64 start_seq, u64 max_seq, size_t size,
bool syslog, bool time)
{
struct printk_info info;
unsigned int line_count;
size_t len = 0;
u64 seq;
/* Determine the size of the records up to @max_seq. */
prb_for_each_info(start_seq, prb, seq, &info, &line_count) {
if (info.seq >= max_seq)
break;
len += get_record_print_text_size(&info, line_count, syslog, time);
}
/*
* Adjust the upper bound for the next loop to avoid subtracting
* lengths that were never added.
*/
if (seq < max_seq)
max_seq = seq;
/*
* Move first record forward until length fits into the buffer. Ignore
* newest messages that were not counted in the above cycle. Messages
* might appear and get lost in the meantime. This is a best effort
* that prevents an infinite loop that could occur with a retry.
*/
prb_for_each_info(start_seq, prb, seq, &info, &line_count) {
if (len <= size || info.seq >= max_seq)
break;
len -= get_record_print_text_size(&info, line_count, syslog, time);
}
return seq;
}
/* The caller is responsible for making sure @size is greater than 0. */
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
static int syslog_print(char __user *buf, int size)
{
struct printk_info info;
struct printk_record r;
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
char *text;
int len = 0;
u64 seq;
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
text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL);
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
if (!text)
return -ENOMEM;
prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX);
mutex_lock(&syslog_lock);
/*
* Wait for the @syslog_seq record to be available. @syslog_seq may
* change while waiting.
*/
do {
seq = syslog_seq;
mutex_unlock(&syslog_lock);
len = wait_event_interruptible(log_wait, prb_read_valid(prb, seq, NULL));
mutex_lock(&syslog_lock);
if (len)
goto out;
} while (syslog_seq != seq);
/*
* Copy records that fit into the buffer. The above cycle makes sure
* that the first record is always available.
*/
do {
size_t n;
size_t skip;
int err;
if (!prb_read_valid(prb, syslog_seq, &r))
break;
if (r.info->seq != syslog_seq) {
/* message is gone, move to next valid one */
syslog_seq = r.info->seq;
syslog_partial = 0;
}
/*
* To keep reading/counting partial line consistent,
* use printk_time value as of the beginning of a line.
*/
if (!syslog_partial)
syslog_time = printk_time;
skip = syslog_partial;
n = record_print_text(&r, true, syslog_time);
if (n - syslog_partial <= size) {
/* message fits into buffer, move forward */
syslog_seq = r.info->seq + 1;
n -= syslog_partial;
syslog_partial = 0;
} else if (!len){
/* partial read(), remember position */
n = size;
syslog_partial += n;
} else
n = 0;
if (!n)
break;
mutex_unlock(&syslog_lock);
err = copy_to_user(buf, text + skip, n);
mutex_lock(&syslog_lock);
if (err) {
if (!len)
len = -EFAULT;
break;
}
len += n;
size -= n;
buf += n;
} while (size);
out:
mutex_unlock(&syslog_lock);
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
kfree(text);
return len;
}
static int syslog_print_all(char __user *buf, int size, bool clear)
{
struct printk_info info;
struct printk_record r;
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
char *text;
int len = 0;
u64 seq;
bool time;
text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL);
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
if (!text)
return -ENOMEM;
time = printk_time;
/*
* Find first record that fits, including all following records,
* into the user-provided buffer for this dump.
*/
seq = find_first_fitting_seq(latched_seq_read_nolock(&clear_seq), -1,
size, true, time);
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
prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX);
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
len = 0;
prb_for_each_record(seq, prb, seq, &r) {
int textlen;
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
textlen = record_print_text(&r, true, time);
if (len + textlen > size) {
seq--;
break;
}
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
if (copy_to_user(buf + len, text, textlen))
len = -EFAULT;
else
len += textlen;
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
if (len < 0)
break;
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
}
if (clear) {
mutex_lock(&syslog_lock);
latched_seq_write(&clear_seq, seq);
mutex_unlock(&syslog_lock);
}
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
kfree(text);
return len;
}
static void syslog_clear(void)
{
mutex_lock(&syslog_lock);
latched_seq_write(&clear_seq, prb_next_seq(prb));
mutex_unlock(&syslog_lock);
}
int do_syslog(int type, char __user *buf, int len, int source)
{
struct printk_info info;
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
bool clear = false;
static int saved_console_loglevel = LOGLEVEL_DEFAULT;
int error;
error = check_syslog_permissions(type, source);
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 */
if (!buf || len < 0)
return -EINVAL;
if (!len)
return 0;
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 10:57:57 +08:00
if (!access_ok(buf, len))
return -EFAULT;
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
error = syslog_print(buf, len);
break;
/* Read/clear last kernel messages */
case SYSLOG_ACTION_READ_CLEAR:
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
clear = true;
fallthrough;
/* Read last kernel messages */
case SYSLOG_ACTION_READ_ALL:
if (!buf || len < 0)
return -EINVAL;
if (!len)
return 0;
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 10:57:57 +08:00
if (!access_ok(buf, len))
return -EFAULT;
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
error = syslog_print_all(buf, len, clear);
break;
/* Clear ring buffer */
case SYSLOG_ACTION_CLEAR:
syslog_clear();
break;
/* Disable logging to console */
case SYSLOG_ACTION_CONSOLE_OFF:
if (saved_console_loglevel == LOGLEVEL_DEFAULT)
printk: Restore previous console_loglevel when re-enabling logging When logging to console is disabled from userspace using klogctl() and later re-enabled, console_loglevel gets set to the default log level instead to the previous value. This means that if the kernel was booted with 'quiet', the boot is suddenly no longer quiet after logging to console gets re-enabled. Save the current console_loglevel when logging is disabled and restore to that value. If the log level is set to a specific value while disabled, this is interpreted as an implicit re-enabling of the logging. The problem that prompted this patch is described in: http://lkml.org/lkml/2009/6/28/234 There are two variations possible on the patch below: 1) If klogctl(7) is called while logging is not disabled, then set level to default (partially preserving current functionality): case 7: /* Enable logging to console */ - console_loglevel = default_console_loglevel; + if (saved_console_loglevel == -1) + console_loglevel = default_console_loglevel; + else { + console_loglevel = saved_console_loglevel; + saved_console_loglevel = -1; + } 2) If klogctl(8) is called while logging is disabled, then don't enable logging, but remember the requested value for when logging does get enabled again: case 8: /* Set level of messages printed to console */ [...] - console_loglevel = len; + if (saved_console_loglevel == -1) + console_loglevel = len; + else + saved_console_loglevel = len; Yet another option would be to ignore the request. Signed-off-by: Frans Pop <elendil@planet.nl> Cc: cryptsetup@packages.debian.org Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <200907061331.49930.elendil@planet.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-06 19:31:48 +08:00
saved_console_loglevel = console_loglevel;
console_loglevel = minimum_console_loglevel;
break;
/* Enable logging to console */
case SYSLOG_ACTION_CONSOLE_ON:
if (saved_console_loglevel != LOGLEVEL_DEFAULT) {
printk: Restore previous console_loglevel when re-enabling logging When logging to console is disabled from userspace using klogctl() and later re-enabled, console_loglevel gets set to the default log level instead to the previous value. This means that if the kernel was booted with 'quiet', the boot is suddenly no longer quiet after logging to console gets re-enabled. Save the current console_loglevel when logging is disabled and restore to that value. If the log level is set to a specific value while disabled, this is interpreted as an implicit re-enabling of the logging. The problem that prompted this patch is described in: http://lkml.org/lkml/2009/6/28/234 There are two variations possible on the patch below: 1) If klogctl(7) is called while logging is not disabled, then set level to default (partially preserving current functionality): case 7: /* Enable logging to console */ - console_loglevel = default_console_loglevel; + if (saved_console_loglevel == -1) + console_loglevel = default_console_loglevel; + else { + console_loglevel = saved_console_loglevel; + saved_console_loglevel = -1; + } 2) If klogctl(8) is called while logging is disabled, then don't enable logging, but remember the requested value for when logging does get enabled again: case 8: /* Set level of messages printed to console */ [...] - console_loglevel = len; + if (saved_console_loglevel == -1) + console_loglevel = len; + else + saved_console_loglevel = len; Yet another option would be to ignore the request. Signed-off-by: Frans Pop <elendil@planet.nl> Cc: cryptsetup@packages.debian.org Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <200907061331.49930.elendil@planet.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-06 19:31:48 +08:00
console_loglevel = saved_console_loglevel;
saved_console_loglevel = LOGLEVEL_DEFAULT;
printk: Restore previous console_loglevel when re-enabling logging When logging to console is disabled from userspace using klogctl() and later re-enabled, console_loglevel gets set to the default log level instead to the previous value. This means that if the kernel was booted with 'quiet', the boot is suddenly no longer quiet after logging to console gets re-enabled. Save the current console_loglevel when logging is disabled and restore to that value. If the log level is set to a specific value while disabled, this is interpreted as an implicit re-enabling of the logging. The problem that prompted this patch is described in: http://lkml.org/lkml/2009/6/28/234 There are two variations possible on the patch below: 1) If klogctl(7) is called while logging is not disabled, then set level to default (partially preserving current functionality): case 7: /* Enable logging to console */ - console_loglevel = default_console_loglevel; + if (saved_console_loglevel == -1) + console_loglevel = default_console_loglevel; + else { + console_loglevel = saved_console_loglevel; + saved_console_loglevel = -1; + } 2) If klogctl(8) is called while logging is disabled, then don't enable logging, but remember the requested value for when logging does get enabled again: case 8: /* Set level of messages printed to console */ [...] - console_loglevel = len; + if (saved_console_loglevel == -1) + console_loglevel = len; + else + saved_console_loglevel = len; Yet another option would be to ignore the request. Signed-off-by: Frans Pop <elendil@planet.nl> Cc: cryptsetup@packages.debian.org Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <200907061331.49930.elendil@planet.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-06 19:31:48 +08:00
}
break;
/* Set level of messages printed to console */
case SYSLOG_ACTION_CONSOLE_LEVEL:
if (len < 1 || len > 8)
return -EINVAL;
if (len < minimum_console_loglevel)
len = minimum_console_loglevel;
console_loglevel = len;
printk: Restore previous console_loglevel when re-enabling logging When logging to console is disabled from userspace using klogctl() and later re-enabled, console_loglevel gets set to the default log level instead to the previous value. This means that if the kernel was booted with 'quiet', the boot is suddenly no longer quiet after logging to console gets re-enabled. Save the current console_loglevel when logging is disabled and restore to that value. If the log level is set to a specific value while disabled, this is interpreted as an implicit re-enabling of the logging. The problem that prompted this patch is described in: http://lkml.org/lkml/2009/6/28/234 There are two variations possible on the patch below: 1) If klogctl(7) is called while logging is not disabled, then set level to default (partially preserving current functionality): case 7: /* Enable logging to console */ - console_loglevel = default_console_loglevel; + if (saved_console_loglevel == -1) + console_loglevel = default_console_loglevel; + else { + console_loglevel = saved_console_loglevel; + saved_console_loglevel = -1; + } 2) If klogctl(8) is called while logging is disabled, then don't enable logging, but remember the requested value for when logging does get enabled again: case 8: /* Set level of messages printed to console */ [...] - console_loglevel = len; + if (saved_console_loglevel == -1) + console_loglevel = len; + else + saved_console_loglevel = len; Yet another option would be to ignore the request. Signed-off-by: Frans Pop <elendil@planet.nl> Cc: cryptsetup@packages.debian.org Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <200907061331.49930.elendil@planet.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-06 19:31:48 +08:00
/* Implicitly re-enable logging to console */
saved_console_loglevel = LOGLEVEL_DEFAULT;
break;
/* Number of chars in the log buffer */
case SYSLOG_ACTION_SIZE_UNREAD:
mutex_lock(&syslog_lock);
if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) {
/* No unread messages. */
mutex_unlock(&syslog_lock);
return 0;
}
if (info.seq != syslog_seq) {
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
/* messages are gone, move to first one */
syslog_seq = info.seq;
syslog_partial = 0;
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
}
if (source == SYSLOG_FROM_PROC) {
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
/*
* Short-cut for poll(/"proc/kmsg") which simply checks
* for pending data, not the size; return the count of
* records, not the length.
*/
error = prb_next_seq(prb) - syslog_seq;
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
} else {
bool time = syslog_partial ? syslog_time : printk_time;
unsigned int line_count;
u64 seq;
prb_for_each_info(syslog_seq, prb, seq, &info,
&line_count) {
error += get_record_print_text_size(&info, line_count,
true, time);
time = printk_time;
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
}
error -= syslog_partial;
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
}
mutex_unlock(&syslog_lock);
break;
/* Size of the log buffer */
case SYSLOG_ACTION_SIZE_BUFFER:
error = log_buf_len;
break;
default:
error = -EINVAL;
break;
}
return error;
}
SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
{
kmsg: honor dmesg_restrict sysctl on /dev/kmsg The dmesg_restrict sysctl currently covers the syslog method for access dmesg, however /dev/kmsg isn't covered by the same protections. Most people haven't noticed because util-linux dmesg(1) defaults to using the syslog method for access in older versions. With util-linux dmesg(1) defaults to reading directly from /dev/kmsg. To fix /dev/kmsg, let's compare the existing interfaces and what they allow: - /proc/kmsg allows: - open (SYSLOG_ACTION_OPEN) if CAP_SYSLOG since it uses a destructive single-reader interface (SYSLOG_ACTION_READ). - everything, after an open. - syslog syscall allows: - anything, if CAP_SYSLOG. - SYSLOG_ACTION_READ_ALL and SYSLOG_ACTION_SIZE_BUFFER, if dmesg_restrict==0. - nothing else (EPERM). The use-cases were: - dmesg(1) needs to do non-destructive SYSLOG_ACTION_READ_ALLs. - sysklog(1) needs to open /proc/kmsg, drop privs, and still issue the destructive SYSLOG_ACTION_READs. AIUI, dmesg(1) is moving to /dev/kmsg, and systemd-journald doesn't clear the ring buffer. Based on the comments in devkmsg_llseek, it sounds like actions besides reading aren't going to be supported by /dev/kmsg (i.e. SYSLOG_ACTION_CLEAR), so we have a strict subset of the non-destructive syslog syscall actions. To this end, move the check as Josh had done, but also rename the constants to reflect their new uses (SYSLOG_FROM_CALL becomes SYSLOG_FROM_READER, and SYSLOG_FROM_FILE becomes SYSLOG_FROM_PROC). SYSLOG_FROM_READER allows non-destructive actions, and SYSLOG_FROM_PROC allows destructive actions after a capabilities-constrained SYSLOG_ACTION_OPEN check. - /dev/kmsg allows: - open if CAP_SYSLOG or dmesg_restrict==0 - reading/polling, after open Addresses https://bugzilla.redhat.com/show_bug.cgi?id=903192 [akpm@linux-foundation.org: use pr_warn_once()] Signed-off-by: Kees Cook <keescook@chromium.org> Reported-by: Christian Kujau <lists@nerdbynature.de> Tested-by: Josh Boyer <jwboyer@redhat.com> Cc: Kay Sievers <kay@vrfy.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-06-13 05:04:39 +08:00
return do_syslog(type, buf, len, SYSLOG_FROM_READER);
}
/*
* Special console_lock variants that help to reduce the risk of soft-lockups.
* They allow to pass console_lock to another printk() call using a busy wait.
*/
#ifdef CONFIG_LOCKDEP
static struct lockdep_map console_owner_dep_map = {
.name = "console_owner"
};
#endif
static DEFINE_RAW_SPINLOCK(console_owner_lock);
static struct task_struct *console_owner;
static bool console_waiter;
/**
* console_lock_spinning_enable - mark beginning of code where another
* thread might safely busy wait
*
* This basically converts console_lock into a spinlock. This marks
* the section where the console_lock owner can not sleep, because
* there may be a waiter spinning (like a spinlock). Also it must be
* ready to hand over the lock at the end of the section.
*/
static void console_lock_spinning_enable(void)
{
raw_spin_lock(&console_owner_lock);
console_owner = current;
raw_spin_unlock(&console_owner_lock);
/* The waiter may spin on us after setting console_owner */
spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_);
}
/**
* console_lock_spinning_disable_and_check - mark end of code where another
* thread was able to busy wait and check if there is a waiter
*
* This is called at the end of the section where spinning is allowed.
* It has two functions. First, it is a signal that it is no longer
* safe to start busy waiting for the lock. Second, it checks if
* there is a busy waiter and passes the lock rights to her.
*
* Important: Callers lose the lock if there was a busy waiter.
* They must not touch items synchronized by console_lock
* in this case.
*
* Return: 1 if the lock rights were passed, 0 otherwise.
*/
static int console_lock_spinning_disable_and_check(void)
{
int waiter;
raw_spin_lock(&console_owner_lock);
waiter = READ_ONCE(console_waiter);
console_owner = NULL;
raw_spin_unlock(&console_owner_lock);
if (!waiter) {
2019-09-20 00:09:40 +08:00
spin_release(&console_owner_dep_map, _THIS_IP_);
return 0;
}
/* The waiter is now free to continue */
WRITE_ONCE(console_waiter, false);
2019-09-20 00:09:40 +08:00
spin_release(&console_owner_dep_map, _THIS_IP_);
/*
* Hand off console_lock to waiter. The waiter will perform
* the up(). After this, the waiter is the console_lock owner.
*/
2019-09-20 00:09:40 +08:00
mutex_release(&console_lock_dep_map, _THIS_IP_);
return 1;
}
/**
* console_trylock_spinning - try to get console_lock by busy waiting
*
* This allows to busy wait for the console_lock when the current
* owner is running in specially marked sections. It means that
* the current owner is running and cannot reschedule until it
* is ready to lose the lock.
*
* Return: 1 if we got the lock, 0 othrewise
*/
static int console_trylock_spinning(void)
{
struct task_struct *owner = NULL;
bool waiter;
bool spin = false;
unsigned long flags;
if (console_trylock())
return 1;
printk: disable optimistic spin during panic A CPU executing with console lock spinning enabled might be halted during a panic. Before the panicking CPU calls console_flush_on_panic(), it may call console_trylock(), which attempts to optimistically spin, deadlocking the panic CPU: CPU 0 (panic CPU) CPU 1 ----------------- ------ printk() { vprintk_func() { vprintk_default() { vprintk_emit() { console_unlock() { console_lock_spinning_enable(); ... printing to console ... panic() { crash_smp_send_stop() { NMI -------------------> HALT } atomic_notifier_call_chain() { printk() { ... console_trylock_spinnning() { // optimistic spin infinitely This hang during panic can be induced when a kdump kernel is loaded, and crash_kexec_post_notifiers=1 is present on the kernel command line. The following script which concurrently writes to /dev/kmsg, and triggers a panic, can result in this hang: #!/bin/bash date # 991 chars (based on log buffer size): chars="$(printf 'a%.0s' {1..991})" while :; do echo $chars > /dev/kmsg done & echo c > /proc/sysrq-trigger & date exit To avoid this deadlock, ensure that console_trylock_spinning() does not allow spinning once a panic has begun. Fixes: dbdda842fe96 ("printk: Add console owner and waiter logic to load balance console writes") Suggested-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Stephen Brennan <stephen.s.brennan@oracle.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20220202171821.179394-3-stephen.s.brennan@oracle.com
2022-02-03 01:18:19 +08:00
/*
* It's unsafe to spin once a panic has begun. If we are the
* panic CPU, we may have already halted the owner of the
* console_sem. If we are not the panic CPU, then we should
* avoid taking console_sem, so the panic CPU has a better
* chance of cleanly acquiring it later.
*/
if (panic_in_progress())
return 0;
printk_safe_enter_irqsave(flags);
raw_spin_lock(&console_owner_lock);
owner = READ_ONCE(console_owner);
waiter = READ_ONCE(console_waiter);
if (!waiter && owner && owner != current) {
WRITE_ONCE(console_waiter, true);
spin = true;
}
raw_spin_unlock(&console_owner_lock);
/*
* If there is an active printk() writing to the
* consoles, instead of having it write our data too,
* see if we can offload that load from the active
* printer, and do some printing ourselves.
* Go into a spin only if there isn't already a waiter
* spinning, and there is an active printer, and
* that active printer isn't us (recursive printk?).
*/
if (!spin) {
printk_safe_exit_irqrestore(flags);
return 0;
}
/* We spin waiting for the owner to release us */
spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_);
/* Owner will clear console_waiter on hand off */
while (READ_ONCE(console_waiter))
cpu_relax();
2019-09-20 00:09:40 +08:00
spin_release(&console_owner_dep_map, _THIS_IP_);
printk_safe_exit_irqrestore(flags);
/*
* The owner passed the console lock to us.
* Since we did not spin on console lock, annotate
* this as a trylock. Otherwise lockdep will
* complain.
*/
mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_);
return 1;
}
/*
* 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(const char *ext_text, size_t ext_len,
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
const char *text, size_t len)
{
static char dropped_text[64];
size_t dropped_len = 0;
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
struct console *con;
printk: use rcuidle console tracepoint Use rcuidle console tracepoint because, apparently, it may be issued from an idle CPU: hw-breakpoint: Failed to enable monitor mode on CPU 0. hw-breakpoint: CPU 0 failed to disable vector catch =============================== [ ERR: suspicious RCU usage. ] 4.10.0-rc8-next-20170215+ #119 Not tainted ------------------------------- ./include/trace/events/printk.h:32 suspicious rcu_dereference_check() usage! other info that might help us debug this: RCU used illegally from idle CPU! rcu_scheduler_active = 2, debug_locks = 0 RCU used illegally from extended quiescent state! 2 locks held by swapper/0/0: #0: (cpu_pm_notifier_lock){......}, at: [<c0237e2c>] cpu_pm_exit+0x10/0x54 #1: (console_lock){+.+.+.}, at: [<c01ab350>] vprintk_emit+0x264/0x474 stack backtrace: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.10.0-rc8-next-20170215+ #119 Hardware name: Generic OMAP4 (Flattened Device Tree) console_unlock vprintk_emit vprintk_default printk reset_ctrl_regs dbg_cpu_pm_notify notifier_call_chain cpu_pm_exit omap_enter_idle_coupled cpuidle_enter_state cpuidle_enter_state_coupled do_idle cpu_startup_entry start_kernel This RCU warning, however, is suppressed by lockdep_off() in printk(). lockdep_off() increments the ->lockdep_recursion counter and thus disables RCU_LOCKDEP_WARN() and debug_lockdep_rcu_enabled(), which want lockdep to be enabled "current->lockdep_recursion == 0". Link: http://lkml.kernel.org/r/20170217015932.11898-1-sergey.senozhatsky@gmail.com Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reported-by: Tony Lindgren <tony@atomide.com> Tested-by: Tony Lindgren <tony@atomide.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Lindgren <tony@atomide.com> Cc: Russell King <rmk@armlinux.org.uk> Cc: <stable@vger.kernel.org> [3.4+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-18 19:42:54 +08:00
trace_console_rcuidle(text, len);
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
if (!console_drivers)
return;
if (console_dropped) {
dropped_len = snprintf(dropped_text, sizeof(dropped_text),
"** %lu printk messages dropped **\n",
console_dropped);
console_dropped = 0;
}
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
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;
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
if (con->flags & CON_EXTENDED)
con->write(con, ext_text, ext_len);
else {
if (dropped_len)
con->write(con, dropped_text, dropped_len);
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
con->write(con, text, len);
}
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
}
}
/*
* Recursion is tracked separately on each CPU. If NMIs are supported, an
* additional NMI context per CPU is also separately tracked. Until per-CPU
* is available, a separate "early tracking" is performed.
*/
static DEFINE_PER_CPU(u8, printk_count);
static u8 printk_count_early;
#ifdef CONFIG_HAVE_NMI
static DEFINE_PER_CPU(u8, printk_count_nmi);
static u8 printk_count_nmi_early;
#endif
/*
* Recursion is limited to keep the output sane. printk() should not require
* more than 1 level of recursion (allowing, for example, printk() to trigger
* a WARN), but a higher value is used in case some printk-internal errors
* exist, such as the ringbuffer validation checks failing.
*/
#define PRINTK_MAX_RECURSION 3
/*
* Return a pointer to the dedicated counter for the CPU+context of the
* caller.
*/
static u8 *__printk_recursion_counter(void)
{
#ifdef CONFIG_HAVE_NMI
if (in_nmi()) {
if (printk_percpu_data_ready())
return this_cpu_ptr(&printk_count_nmi);
return &printk_count_nmi_early;
}
#endif
if (printk_percpu_data_ready())
return this_cpu_ptr(&printk_count);
return &printk_count_early;
}
/*
* Enter recursion tracking. Interrupts are disabled to simplify tracking.
* The caller must check the boolean return value to see if the recursion is
* allowed. On failure, interrupts are not disabled.
*
* @recursion_ptr must be a variable of type (u8 *) and is the same variable
* that is passed to printk_exit_irqrestore().
*/
#define printk_enter_irqsave(recursion_ptr, flags) \
({ \
bool success = true; \
\
typecheck(u8 *, recursion_ptr); \
local_irq_save(flags); \
(recursion_ptr) = __printk_recursion_counter(); \
if (*(recursion_ptr) > PRINTK_MAX_RECURSION) { \
local_irq_restore(flags); \
success = false; \
} else { \
(*(recursion_ptr))++; \
} \
success; \
})
/* Exit recursion tracking, restoring interrupts. */
#define printk_exit_irqrestore(recursion_ptr, flags) \
do { \
typecheck(u8 *, recursion_ptr); \
(*(recursion_ptr))--; \
local_irq_restore(flags); \
} while (0)
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();
}
}
}
static inline u32 printk_caller_id(void)
{
return in_task() ? task_pid_nr(current) :
0x80000000 + raw_smp_processor_id();
}
/**
* printk_parse_prefix - Parse level and control flags.
*
* @text: The terminated text message.
* @level: A pointer to the current level value, will be updated.
* @flags: A pointer to the current printk_info flags, will be updated.
*
* @level may be NULL if the caller is not interested in the parsed value.
* Otherwise the variable pointed to by @level must be set to
* LOGLEVEL_DEFAULT in order to be updated with the parsed value.
*
* @flags may be NULL if the caller is not interested in the parsed value.
* Otherwise the variable pointed to by @flags will be OR'd with the parsed
* value.
*
* Return: The length of the parsed level and control flags.
*/
u16 printk_parse_prefix(const char *text, int *level,
enum printk_info_flags *flags)
{
u16 prefix_len = 0;
int kern_level;
while (*text) {
kern_level = printk_get_level(text);
if (!kern_level)
break;
switch (kern_level) {
case '0' ... '7':
if (level && *level == LOGLEVEL_DEFAULT)
*level = kern_level - '0';
break;
case 'c': /* KERN_CONT */
if (flags)
*flags |= LOG_CONT;
}
prefix_len += 2;
text += 2;
}
return prefix_len;
}
__printf(5, 0)
static u16 printk_sprint(char *text, u16 size, int facility,
enum printk_info_flags *flags, const char *fmt,
va_list args)
{
u16 text_len;
text_len = vscnprintf(text, size, fmt, args);
/* Mark and strip a trailing newline. */
if (text_len && text[text_len - 1] == '\n') {
text_len--;
*flags |= LOG_NEWLINE;
}
/* Strip log level and control flags. */
if (facility == 0) {
u16 prefix_len;
prefix_len = printk_parse_prefix(text, NULL, NULL);
if (prefix_len) {
text_len -= prefix_len;
memmove(text, text + prefix_len, text_len);
}
}
return text_len;
}
__printf(4, 0)
int vprintk_store(int facility, int level,
const struct dev_printk_info *dev_info,
const char *fmt, va_list args)
{
const u32 caller_id = printk_caller_id();
struct prb_reserved_entry e;
enum printk_info_flags flags = 0;
struct printk_record r;
unsigned long irqflags;
u16 trunc_msg_len = 0;
char prefix_buf[8];
u8 *recursion_ptr;
u16 reserve_size;
va_list args2;
u16 text_len;
int ret = 0;
u64 ts_nsec;
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
/*
* Since the duration of printk() can vary depending on the message
* and state of the ringbuffer, grab the timestamp now so that it is
* close to the call of printk(). This provides a more deterministic
* timestamp with respect to the caller.
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
*/
ts_nsec = local_clock();
if (!printk_enter_irqsave(recursion_ptr, irqflags))
return 0;
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
/*
* The sprintf needs to come first since the syslog prefix might be
* passed in as a parameter. An extra byte must be reserved so that
* later the vscnprintf() into the reserved buffer has room for the
* terminating '\0', which is not counted by vsnprintf().
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
*/
va_copy(args2, args);
reserve_size = vsnprintf(&prefix_buf[0], sizeof(prefix_buf), fmt, args2) + 1;
va_end(args2);
if (reserve_size > LOG_LINE_MAX)
reserve_size = LOG_LINE_MAX;
/* Extract log level or control flags. */
if (facility == 0)
printk_parse_prefix(&prefix_buf[0], &level, &flags);
if (level == LOGLEVEL_DEFAULT)
printk() - isolate KERN_CONT users from ordinary complete lines Arrange the continuation printk() buffering to be fully separated from the ordinary full line users. Limit the exposure to races and wrong printk() line merges to users of continuation only. Ordinary full line users racing against continuation users will no longer affect each other. Multiple continuation users from different threads, racing against each other will not wrongly be merged into a single line, but printed as separate lines. Test output of a kernel module which starts two separate threads which race against each other, one of them printing a single full terminated line: printk("(AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA)\n"); The other one printing the line, every character separate in a continuation loop: printk("(C"); for (i = 0; i < 58; i++) printk(KERN_CONT "C"); printk(KERN_CONT "C)\n"); Behavior of single and non-thread-aware printk() buffer: # modprobe printk-race printk test init (CC(AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) C(AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) CC(AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) C(AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) CC(AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) C(AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) C(AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) CC(AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) C(AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) C(AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC) (CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC) New behavior with separate and thread-aware continuation buffer: # modprobe printk-race printk test init (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) (CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC) (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) (AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA) (CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC) (CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC) Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Joe Perches <joe@perches.com> Cc: Ted Ts'o <tytso@mit.edu> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Sasha Levin <levinsasha928@gmail.com> Signed-off-by: Kay Sievers <kay@vrfy.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-05-15 02:46:27 +08:00
level = default_message_loglevel;
if (dev_info)
flags |= LOG_NEWLINE;
if (flags & LOG_CONT) {
prb_rec_init_wr(&r, reserve_size);
if (prb_reserve_in_last(&e, prb, &r, caller_id, LOG_LINE_MAX)) {
text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size,
facility, &flags, fmt, args);
r.info->text_len += text_len;
if (flags & LOG_NEWLINE) {
r.info->flags |= LOG_NEWLINE;
prb_final_commit(&e);
} else {
prb_commit(&e);
}
printk: reinstate KERN_CONT for printing continuation lines Long long ago the kernel log buffer was a buffered stream of bytes, very much like stdio in user space. It supported log levels by scanning the stream and noticing the log level markers at the beginning of each line, but if you wanted to print a partial line in multiple chunks, you just did multiple printk() calls, and it just automatically worked. Except when it didn't, and you had very confusing output when different lines got all mixed up with each other. Then you got fragment lines mixing with each other, or with non-fragment lines, because it was traditionally impossible to tell whether a printk() call was a continuation or not. To at least help clarify the issue of continuation lines, we added a KERN_CONT marker back in 2007 to mark continuation lines: 474925277671 ("printk: add KERN_CONT annotation"). That continuation marker was initially an empty string, and didn't actuall make any semantic difference. But it at least made it possible to annotate the source code, and have check-patch notice that a printk() didn't need or want a log level marker, because it was a continuation of a previous line. To avoid the ambiguity between a continuation line that had that KERN_CONT marker, and a printk with no level information at all, we then in 2009 made KERN_CONT be a real log level marker which meant that we could now reliably tell the difference between the two cases. 5fd29d6ccbc9 ("printk: clean up handling of log-levels and newlines") and we could take advantage of that to make sure we didn't mix up continuation lines with lines that just didn't have any loglevel at all. Then, in 2012, the kernel log buffer was changed to be a "record" based log, where each line was a record that has a loglevel and a timestamp. You can see the beginning of that conversion in commits e11fea92e13f ("kmsg: export printk records to the /dev/kmsg interface") 7ff9554bb578 ("printk: convert byte-buffer to variable-length record buffer") with a number of follow-up commits to fix some painful fallout from that conversion. Over all, it took a couple of months to sort out most of it. But the upside was that you could have concurrent readers (and writers) of the kernel log and not have lines with mixed output in them. And one particular pain-point for the record-based kernel logging was exactly the fragmentary lines that are generated in smaller chunks. In order to still log them as one recrod, the continuation lines need to be attached to the previous record properly. However the explicit continuation record marker that is actually useful for this exact case was actually removed in aroundm the same time by commit 61e99ab8e35a ("printk: remove the now unnecessary "C" annotation for KERN_CONT") due to the incorrect belief that KERN_CONT wasn't meaningful. The ambiguity between "is this a continuation line" or "is this a plain printk with no log level information" was reintroduced, and in fact became an even bigger pain point because there was now the whole record-level merging of kernel messages going on. This patch reinstates the KERN_CONT as a real non-empty string marker, so that the ambiguity is fixed once again. But it's not a plain revert of that original removal: in the four years since we made KERN_CONT an empty string again, not only has the format of the log level markers changed, we've also had some usage changes in this area. For example, some ACPI code seems to use KERN_CONT _together_ with a log level, and now uses both the KERN_CONT marker and (for example) a KERN_INFO marker to show that it's an informational continuation of a line. Which is actually not a bad idea - if the continuation line cannot be attached to its predecessor, without the log level information we don't know what log level to assign to it (and we traditionally just assigned it the default loglevel). So having both a log level and the KERN_CONT marker is not necessarily a bad idea, but it does mean that we need to actually iterate over potentially multiple markers, rather than just a single one. Also, since KERN_CONT was still conceptually needed, and encouraged, but didn't actually _do_ anything, we've also had the reverse problem: rather than having too many annotations it has too few, and there is bit rot with code that no longer marks the continuation lines with the KERN_CONT marker. So this patch not only re-instates the non-empty KERN_CONT marker, it also fixes up the cases of bit-rot I noticed in my own logs. There are probably other cases where KERN_CONT will be needed to be added, either because it is new code that never dealt with the need for KERN_CONT, or old code that has bitrotted without anybody noticing. That said, we should strive to avoid the need for KERN_CONT. It does result in real problems for logging, and should generally not be seen as a good feature. If we some day can get rid of the feature entirely, because nobody does any fragmented printk calls, that would be lovely. But until that point, let's at mark the code that relies on the hacky multi-fragment kernel printk's. Not only does it avoid the ambiguity, it also annotates code as "maybe this would be good to fix some day". (That said, particularly during single-threaded bootup, the downsides of KERN_CONT are very limited. Things get much hairier when you have multiple threads going on and user level reading and writing logs too). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-09 11:32:40 +08:00
ret = text_len;
goto out;
}
}
/*
* Explicitly initialize the record before every prb_reserve() call.
* prb_reserve_in_last() and prb_reserve() purposely invalidate the
* structure when they fail.
*/
prb_rec_init_wr(&r, reserve_size);
if (!prb_reserve(&e, prb, &r)) {
/* truncate the message if it is too long for empty buffer */
truncate_msg(&reserve_size, &trunc_msg_len);
prb_rec_init_wr(&r, reserve_size + trunc_msg_len);
if (!prb_reserve(&e, prb, &r))
goto out;
}
/* fill message */
text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &flags, fmt, args);
if (trunc_msg_len)
memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len);
r.info->text_len = text_len + trunc_msg_len;
r.info->facility = facility;
r.info->level = level & 7;
r.info->flags = flags & 0x1f;
r.info->ts_nsec = ts_nsec;
r.info->caller_id = caller_id;
if (dev_info)
memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info));
/* A message without a trailing newline can be continued. */
if (!(flags & LOG_NEWLINE))
prb_commit(&e);
else
prb_final_commit(&e);
ret = text_len + trunc_msg_len;
out:
printk_exit_irqrestore(recursion_ptr, irqflags);
return ret;
}
asmlinkage int vprintk_emit(int facility, int level,
const struct dev_printk_info *dev_info,
const char *fmt, va_list args)
{
int printed_len;
bool in_sched = false;
panic: avoid the extra noise dmesg When kernel panic happens, it will first print the panic call stack, then the ending msg like: [ 35.743249] ---[ end Kernel panic - not syncing: Fatal exception [ 35.749975] ------------[ cut here ]------------ The above message are very useful for debugging. But if system is configured to not reboot on panic, say the "panic_timeout" parameter equals 0, it will likely print out many noisy message like WARN() call stack for each and every CPU except the panic one, messages like below: WARNING: CPU: 1 PID: 280 at kernel/sched/core.c:1198 set_task_cpu+0x183/0x190 Call Trace: <IRQ> try_to_wake_up default_wake_function autoremove_wake_function __wake_up_common __wake_up_common_lock __wake_up wake_up_klogd_work_func irq_work_run_list irq_work_tick update_process_times tick_sched_timer __hrtimer_run_queues hrtimer_interrupt smp_apic_timer_interrupt apic_timer_interrupt For people working in console mode, the screen will first show the panic call stack, but immediately overridden by these noisy extra messages, which makes debugging much more difficult, as the original context gets lost on screen. Also these noisy messages will confuse some users, as I have seen many bug reporters posted the noisy message into bugzilla, instead of the real panic call stack and context. Adding a flag "suppress_printk" which gets set in panic() to avoid those noisy messages, without changing current kernel behavior that both panic blinking and sysrq magic key can work as is, suggested by Petr Mladek. To verify this, make sure kernel is not configured to reboot on panic and in console # echo c > /proc/sysrq-trigger to see if console only prints out the panic call stack. Link: http://lkml.kernel.org/r/1551430186-24169-1-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang <feng.tang@intel.com> Suggested-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Kees Cook <keescook@chromium.org> Cc: Borislav Petkov <bp@suse.de> Cc: Andi Kleen <ak@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jiri Slaby <jslaby@suse.com> Cc: Sasha Levin <sashal@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-15 06:45:34 +08:00
/* Suppress unimportant messages after panic happens */
if (unlikely(suppress_printk))
return 0;
if (unlikely(suppress_panic_printk) &&
atomic_read(&panic_cpu) != raw_smp_processor_id())
return 0;
if (level == LOGLEVEL_SCHED) {
level = LOGLEVEL_DEFAULT;
in_sched = true;
}
boot_delay_msec(level);
printk_delay();
printed_len = vprintk_store(facility, level, dev_info, fmt, args);
printk: remove separate printk_sched buffers and use printk buf instead To prevent deadlocks with doing a printk inside the scheduler, printk_sched() was created. The issue is that printk has a console_sem that it can grab and release. The release does a wake up if there's a task pending on the sem, and this wake up grabs the rq locks that is held in the scheduler. This leads to a possible deadlock if the wake up uses the same rq as the one with the rq lock held already. What printk_sched() does is to save the printk write in a per cpu buffer and sets the PRINTK_PENDING_SCHED flag. On a timer tick, if this flag is set, the printk() is done against the buffer. There's a couple of issues with this approach. 1) If two printk_sched()s are called before the tick, the second one will overwrite the first one. 2) The temporary buffer is 512 bytes and is per cpu. This is a quite a bit of space wasted for something that is seldom used. In order to remove this, the printk_sched() can use the printk buffer instead, and delay the console_trylock()/console_unlock() to the queued work. Because printk_sched() would then be taking the logbuf_lock, the logbuf_lock must not be held while doing anything that may call into the scheduler functions, which includes wake ups. Unfortunately, printk() also has a console_sem that it uses, and on release, the up(&console_sem) may do a wake up of any pending waiters. This must be avoided while holding the logbuf_lock. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:11:38 +08:00
/* If called from the scheduler, we can not call up(). */
if (!in_sched) {
printk: Never set console_may_schedule in console_trylock() This patch, basically, reverts commit 6b97a20d3a79 ("printk: set may_schedule for some of console_trylock() callers"). That commit was a mistake, it introduced a big dependency on the scheduler, by enabling preemption under console_sem in printk()->console_unlock() path, which is rather too critical. The patch did not significantly reduce the possibilities of printk() lockups, but made it possible to stall printk(), as has been reported by Tetsuo Handa [1]. Another issues is that preemption under console_sem also messes up with Steven Rostedt's hand off scheme, by making it possible to sleep with console_sem both in console_unlock() and in vprintk_emit(), after acquiring the console_sem ownership (anywhere between printk_safe_exit_irqrestore() in console_trylock_spinning() and printk_safe_enter_irqsave() in console_unlock()). This makes hand off less likely and, at the same time, may result in a significant amount of pending logbuf messages. Preempted console_sem owner makes it impossible for other CPUs to emit logbuf messages, but does not make it impossible for other CPUs to append new messages to the logbuf. Reinstate the old behavior and make printk() non-preemptible. Should any printk() lockup reports arrive they must be handled in a different way. [1] http://lkml.kernel.org/r/201603022101.CAH73907.OVOOMFHFFtQJSL%20()%20I-love%20!%20SAKURA%20!%20ne%20!%20jp Fixes: 6b97a20d3a79 ("printk: set may_schedule for some of console_trylock() callers") Link: http://lkml.kernel.org/r/20180116044716.GE6607@jagdpanzerIV To: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: akpm@linux-foundation.org Cc: linux-mm@kvack.org Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: linux-kernel@vger.kernel.org Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-01-16 12:47:16 +08:00
/*
* Disable preemption to avoid being preempted while holding
* console_sem which would prevent anyone from printing to
* console
*/
preempt_disable();
/*
* Try to acquire and then immediately release the console
* semaphore. The release will print out buffers and wake up
* /dev/kmsg and syslog() users.
*/
if (console_trylock_spinning())
console_unlock();
printk: Never set console_may_schedule in console_trylock() This patch, basically, reverts commit 6b97a20d3a79 ("printk: set may_schedule for some of console_trylock() callers"). That commit was a mistake, it introduced a big dependency on the scheduler, by enabling preemption under console_sem in printk()->console_unlock() path, which is rather too critical. The patch did not significantly reduce the possibilities of printk() lockups, but made it possible to stall printk(), as has been reported by Tetsuo Handa [1]. Another issues is that preemption under console_sem also messes up with Steven Rostedt's hand off scheme, by making it possible to sleep with console_sem both in console_unlock() and in vprintk_emit(), after acquiring the console_sem ownership (anywhere between printk_safe_exit_irqrestore() in console_trylock_spinning() and printk_safe_enter_irqsave() in console_unlock()). This makes hand off less likely and, at the same time, may result in a significant amount of pending logbuf messages. Preempted console_sem owner makes it impossible for other CPUs to emit logbuf messages, but does not make it impossible for other CPUs to append new messages to the logbuf. Reinstate the old behavior and make printk() non-preemptible. Should any printk() lockup reports arrive they must be handled in a different way. [1] http://lkml.kernel.org/r/201603022101.CAH73907.OVOOMFHFFtQJSL%20()%20I-love%20!%20SAKURA%20!%20ne%20!%20jp Fixes: 6b97a20d3a79 ("printk: set may_schedule for some of console_trylock() callers") Link: http://lkml.kernel.org/r/20180116044716.GE6607@jagdpanzerIV To: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: akpm@linux-foundation.org Cc: linux-mm@kvack.org Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: linux-kernel@vger.kernel.org Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-01-16 12:47:16 +08:00
preempt_enable();
}
wake_up_klogd();
return printed_len;
}
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
EXPORT_SYMBOL(vprintk_emit);
int vprintk_default(const char *fmt, va_list args)
{
return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args);
}
EXPORT_SYMBOL_GPL(vprintk_default);
printk: Userspace format indexing support We have a number of systems industry-wide that have a subset of their functionality that works as follows: 1. Receive a message from local kmsg, serial console, or netconsole; 2. Apply a set of rules to classify the message; 3. Do something based on this classification (like scheduling a remediation for the machine), rinse, and repeat. As a couple of examples of places we have this implemented just inside Facebook, although this isn't a Facebook-specific problem, we have this inside our netconsole processing (for alarm classification), and as part of our machine health checking. We use these messages to determine fairly important metrics around production health, and it's important that we get them right. While for some kinds of issues we have counters, tracepoints, or metrics with a stable interface which can reliably indicate the issue, in order to react to production issues quickly we need to work with the interface which most kernel developers naturally use when developing: printk. Most production issues come from unexpected phenomena, and as such usually the code in question doesn't have easily usable tracepoints or other counters available for the specific problem being mitigated. We have a number of lines of monitoring defence against problems in production (host metrics, process metrics, service metrics, etc), and where it's not feasible to reliably monitor at another level, this kind of pragmatic netconsole monitoring is essential. As one would expect, monitoring using printk is rather brittle for a number of reasons -- most notably that the message might disappear entirely in a new version of the kernel, or that the message may change in some way that the regex or other classification methods start to silently fail. One factor that makes this even harder is that, under normal operation, many of these messages are never expected to be hit. For example, there may be a rare hardware bug which one wants to detect if it was to ever happen again, but its recurrence is not likely or anticipated. This precludes using something like checking whether the printk in question was printed somewhere fleetwide recently to determine whether the message in question is still present or not, since we don't anticipate that it should be printed anywhere, but still need to monitor for its future presence in the long-term. This class of issue has happened on a number of occasions, causing unhealthy machines with hardware issues to remain in production for longer than ideal. As a recent example, some monitoring around blk_update_request fell out of date and caused semi-broken machines to remain in production for longer than would be desirable. Searching through the codebase to find the message is also extremely fragile, because many of the messages are further constructed beyond their callsite (eg. btrfs_printk and other module-specific wrappers, each with their own functionality). Even if they aren't, guessing the format and formulation of the underlying message based on the aesthetics of the message emitted is not a recipe for success at scale, and our previous issues with fleetwide machine health checking demonstrate as much. This provides a solution to the issue of silently changed or deleted printks: we record pointers to all printk format strings known at compile time into a new .printk_index section, both in vmlinux and modules. At runtime, this can then be iterated by looking at <debugfs>/printk/index/<module>, which emits the following format, both readable by humans and able to be parsed by machines: $ head -1 vmlinux; shuf -n 5 vmlinux # <level[,flags]> filename:line function "format" <5> block/blk-settings.c:661 disk_stack_limits "%s: Warning: Device %s is misaligned\n" <4> kernel/trace/trace.c:8296 trace_create_file "Could not create tracefs '%s' entry\n" <6> arch/x86/kernel/hpet.c:144 _hpet_print_config "hpet: %s(%d):\n" <6> init/do_mounts.c:605 prepare_namespace "Waiting for root device %s...\n" <6> drivers/acpi/osl.c:1410 acpi_no_auto_serialize_setup "ACPI: auto-serialization disabled\n" This mitigates the majority of cases where we have a highly-specific printk which we want to match on, as we can now enumerate and check whether the format changed or the printk callsite disappeared entirely in userspace. This allows us to catch changes to printks we monitor earlier and decide what to do about it before it becomes problematic. There is no additional runtime cost for printk callers or printk itself, and the assembly generated is exactly the same. Signed-off-by: Chris Down <chris@chrisdown.name> Cc: Petr Mladek <pmladek@suse.com> Cc: Jessica Yu <jeyu@kernel.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: John Ogness <john.ogness@linutronix.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kees Cook <keescook@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Tested-by: Petr Mladek <pmladek@suse.com> Reported-by: kernel test robot <lkp@intel.com> Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com> Acked-by: Jessica Yu <jeyu@kernel.org> # for module.{c,h} Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/e42070983637ac5e384f17fbdbe86d19c7b212a5.1623775748.git.chris@chrisdown.name
2021-06-16 00:52:53 +08:00
asmlinkage __visible int _printk(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
{
va_list args;
int r;
va_start(args, fmt);
printk: rename vprintk_func to vprintk The printk code is already hard enough to understand. Remove an unnecessary indirection by renaming vprintk_func to vprintk (adding the asmlinkage annotation), and removing the vprintk definition from printk.c. That way, printk is implemented in terms of vprintk as one would expect, and there's no "vprintk_func, what's that? Some function pointer that gets set where?" The declaration of vprintk in linux/printk.h already has the __printf(1,0) attribute, there's no point repeating that with the definition - it's for diagnostics in callers. linux/printk.h already contains a static inline {return 0;} definition of vprintk when !CONFIG_PRINTK. Since the corresponding stub definition of vprintk_func was not marked "static inline", any translation unit including internal.h would get a definition of vprintk_func - it just so happens that for !CONFIG_PRINTK, there is precisely one such TU, namely printk.c. Had there been more, it would be a link error; now it's just a silly waste of a few bytes of .text, which one must assume are rather precious to anyone disabling PRINTK. $ objdump -dr kernel/printk/printk.o 00000330 <vprintk_func>: 330: 31 c0 xor %eax,%eax 332: c3 ret 333: 8d b4 26 00 00 00 00 lea 0x0(%esi,%eiz,1),%esi 33a: 8d b6 00 00 00 00 lea 0x0(%esi),%esi Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20210323144201.486050-1-linux@rasmusvillemoes.dk
2021-03-23 22:42:01 +08:00
r = vprintk(fmt, 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
va_end(args);
return r;
}
printk: Userspace format indexing support We have a number of systems industry-wide that have a subset of their functionality that works as follows: 1. Receive a message from local kmsg, serial console, or netconsole; 2. Apply a set of rules to classify the message; 3. Do something based on this classification (like scheduling a remediation for the machine), rinse, and repeat. As a couple of examples of places we have this implemented just inside Facebook, although this isn't a Facebook-specific problem, we have this inside our netconsole processing (for alarm classification), and as part of our machine health checking. We use these messages to determine fairly important metrics around production health, and it's important that we get them right. While for some kinds of issues we have counters, tracepoints, or metrics with a stable interface which can reliably indicate the issue, in order to react to production issues quickly we need to work with the interface which most kernel developers naturally use when developing: printk. Most production issues come from unexpected phenomena, and as such usually the code in question doesn't have easily usable tracepoints or other counters available for the specific problem being mitigated. We have a number of lines of monitoring defence against problems in production (host metrics, process metrics, service metrics, etc), and where it's not feasible to reliably monitor at another level, this kind of pragmatic netconsole monitoring is essential. As one would expect, monitoring using printk is rather brittle for a number of reasons -- most notably that the message might disappear entirely in a new version of the kernel, or that the message may change in some way that the regex or other classification methods start to silently fail. One factor that makes this even harder is that, under normal operation, many of these messages are never expected to be hit. For example, there may be a rare hardware bug which one wants to detect if it was to ever happen again, but its recurrence is not likely or anticipated. This precludes using something like checking whether the printk in question was printed somewhere fleetwide recently to determine whether the message in question is still present or not, since we don't anticipate that it should be printed anywhere, but still need to monitor for its future presence in the long-term. This class of issue has happened on a number of occasions, causing unhealthy machines with hardware issues to remain in production for longer than ideal. As a recent example, some monitoring around blk_update_request fell out of date and caused semi-broken machines to remain in production for longer than would be desirable. Searching through the codebase to find the message is also extremely fragile, because many of the messages are further constructed beyond their callsite (eg. btrfs_printk and other module-specific wrappers, each with their own functionality). Even if they aren't, guessing the format and formulation of the underlying message based on the aesthetics of the message emitted is not a recipe for success at scale, and our previous issues with fleetwide machine health checking demonstrate as much. This provides a solution to the issue of silently changed or deleted printks: we record pointers to all printk format strings known at compile time into a new .printk_index section, both in vmlinux and modules. At runtime, this can then be iterated by looking at <debugfs>/printk/index/<module>, which emits the following format, both readable by humans and able to be parsed by machines: $ head -1 vmlinux; shuf -n 5 vmlinux # <level[,flags]> filename:line function "format" <5> block/blk-settings.c:661 disk_stack_limits "%s: Warning: Device %s is misaligned\n" <4> kernel/trace/trace.c:8296 trace_create_file "Could not create tracefs '%s' entry\n" <6> arch/x86/kernel/hpet.c:144 _hpet_print_config "hpet: %s(%d):\n" <6> init/do_mounts.c:605 prepare_namespace "Waiting for root device %s...\n" <6> drivers/acpi/osl.c:1410 acpi_no_auto_serialize_setup "ACPI: auto-serialization disabled\n" This mitigates the majority of cases where we have a highly-specific printk which we want to match on, as we can now enumerate and check whether the format changed or the printk callsite disappeared entirely in userspace. This allows us to catch changes to printks we monitor earlier and decide what to do about it before it becomes problematic. There is no additional runtime cost for printk callers or printk itself, and the assembly generated is exactly the same. Signed-off-by: Chris Down <chris@chrisdown.name> Cc: Petr Mladek <pmladek@suse.com> Cc: Jessica Yu <jeyu@kernel.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: John Ogness <john.ogness@linutronix.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kees Cook <keescook@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Tested-by: Petr Mladek <pmladek@suse.com> Reported-by: kernel test robot <lkp@intel.com> Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com> Acked-by: Jessica Yu <jeyu@kernel.org> # for module.{c,h} Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/e42070983637ac5e384f17fbdbe86d19c7b212a5.1623775748.git.chris@chrisdown.name
2021-06-16 00:52:53 +08:00
EXPORT_SYMBOL(_printk);
#else /* CONFIG_PRINTK */
#define CONSOLE_LOG_MAX 0
#define printk_time false
#define prb_read_valid(rb, seq, r) false
#define prb_first_valid_seq(rb) 0
static u64 syslog_seq;
static u64 console_seq;
static u64 exclusive_console_stop_seq;
static unsigned long console_dropped;
static size_t record_print_text(const struct printk_record *r,
bool syslog, bool time)
{
return 0;
}
static ssize_t info_print_ext_header(char *buf, size_t size,
struct printk_info *info)
{
return 0;
}
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
static ssize_t msg_print_ext_body(char *buf, size_t size,
char *text, size_t text_len,
struct dev_printk_info *dev_info) { return 0; }
static void console_lock_spinning_enable(void) { }
static int console_lock_spinning_disable_and_check(void) { return 0; }
static void call_console_drivers(const char *ext_text, size_t ext_len,
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
const char *text, size_t len) {}
static bool suppress_message_printing(int level) { return false; }
#endif /* CONFIG_PRINTK */
#ifdef CONFIG_EARLY_PRINTK
struct console *early_console;
asmlinkage __visible void early_printk(const char *fmt, ...)
{
va_list ap;
char buf[512];
int n;
if (!early_console)
return;
va_start(ap, fmt);
n = vscnprintf(buf, sizeof(buf), fmt, ap);
va_end(ap);
early_console->write(early_console, buf, n);
}
#endif
static void set_user_specified(struct console_cmdline *c, bool user_specified)
{
if (!user_specified)
return;
/*
* @c console was defined by the user on the command line.
* Do not clear when added twice also by SPCR or the device tree.
*/
c->user_specified = true;
/* At least one console defined by the user on the command line. */
console_set_on_cmdline = 1;
}
static int __add_preferred_console(char *name, int idx, char *options,
printk: Fix preferred console selection with multiple matches In the following circumstances, the rule of selecting the console corresponding to the last "console=" entry on the command line as the preferred console (CON_CONSDEV, ie, /dev/console) fails. This is a specific example, but it could happen with different consoles that have a similar name aliasing mechanism. - The kernel command line has both console=tty0 and console=ttyS0 in that order (the latter with speed etc... arguments). This is common with some cloud setups such as Amazon Linux. - add_preferred_console is called early to register "uart0". In our case that happens from acpi_parse_spcr() on arm64 since the "enable_console" argument is true on that architecture. This causes "uart0" to become entry 0 of the console_cmdline array. Now, because of the above, what happens is: - add_preferred_console is called by the cmdline parsing for tty0 and ttyS0 respectively, thus occupying entries 1 and 2 of the console_cmdline array (since this happens after ACPI SPCR parsing). At that point preferred_console is set to 2 as expected. - When the tty layer kicks in, it will call register_console for tty0. This will match entry 1 in console_cmdline array. It isn't our preferred console but because it's our only console at this point, it will end up "first" in the consoles list. - When 8250 probes the actual serial port later on, it calls register_console for ttyS0. At that point the loop in register_console tries to match it with the entries in the console_cmdline array. Ideally this should match ttyS0 in entry 2, which is preferred, causing it to be inserted first and to replace tty0 as CONSDEV. However, 8250 provides a "match" hook in its struct console, and that hook will match "uart" as an alias to "ttyS". So we match uart0 at entry 0 in the array which is not the preferred console and will not match entry 2 which is since we break out of the loop on the first match. As a result, we don't set CONSDEV and don't insert it first, but second in the console list. As a result, we end up with tty0 remaining first in the array, and thus /dev/console going there instead of the last user specified one which is ttyS0. This tentative fix register_console() to scan first for consoles specified on the command line, and only if none is found, to then scan for consoles specified by the architecture. Link: https://lore.kernel.org/r/20200213095133.23176-3-pmladek@suse.com Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2020-02-13 17:51:32 +08:00
char *brl_options, bool user_specified)
{
struct console_cmdline *c;
int i;
/*
* See if this tty is not yet registered, and
* if we have a slot free.
*/
Revert "printk: fix double printing with earlycon" This reverts commit cf39bf58afdaabc0b86f141630fb3fd18190294e. The commit regression to users that define both console=ttyS1 and console=ttyS0 on the command line, see https://lkml.kernel.org/r/20170509082915.GA13236@bistromath.localdomain The kernel log messages always appeared only on one serial port. It is even documented in Documentation/admin-guide/serial-console.rst: "Note that you can only define one console per device type (serial, video)." The above mentioned commit changed the order in which the command line parameters are searched. As a result, the kernel log messages go to the last mentioned ttyS* instead of the first one. We long thought that using two console=ttyS* on the command line did not make sense. But then we realized that console= parameters were handled also by systemd, see http://0pointer.de/blog/projects/serial-console.html "By default systemd will instantiate one serial-getty@.service on the main kernel console, if it is not a virtual terminal." where "[4] If multiple kernel consoles are used simultaneously, the main console is the one listed first in /sys/class/tty/console/active, which is the last one listed on the kernel command line." This puts the original report into another light. The system is running in qemu. The first serial port is used to store the messages into a file. The second one is used to login to the system via a socket. It depends on systemd and the historic kernel behavior. By other words, systemd causes that it makes sense to define both console=ttyS1 console=ttyS0 on the command line. The kernel fix caused regression related to userspace (systemd) and need to be reverted. In addition, it went out that the fix helped only partially. The messages still were duplicated when the boot console was removed early by late_initcall(printk_late_init). Then the entire log was replayed when the same console was registered as a normal one. Link: 20170606160339.GC7604@pathway.suse.cz Cc: Aleksey Makarov <aleksey.makarov@linaro.org> Cc: Sabrina Dubroca <sd@queasysnail.net> Cc: Sudeep Holla <sudeep.holla@arm.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Jiri Slaby <jslaby@suse.com> Cc: Robin Murphy <robin.murphy@arm.com>, Cc: Steven Rostedt <rostedt@goodmis.org> Cc: "Nair, Jayachandran" <Jayachandran.Nair@cavium.com> Cc: linux-serial@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reported-by: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-06-08 18:01:30 +08:00
for (i = 0, c = console_cmdline;
i < MAX_CMDLINECONSOLES && c->name[0];
i++, c++) {
if (strcmp(c->name, name) == 0 && c->index == idx) {
Revert "printk: fix double printing with earlycon" This reverts commit cf39bf58afdaabc0b86f141630fb3fd18190294e. The commit regression to users that define both console=ttyS1 and console=ttyS0 on the command line, see https://lkml.kernel.org/r/20170509082915.GA13236@bistromath.localdomain The kernel log messages always appeared only on one serial port. It is even documented in Documentation/admin-guide/serial-console.rst: "Note that you can only define one console per device type (serial, video)." The above mentioned commit changed the order in which the command line parameters are searched. As a result, the kernel log messages go to the last mentioned ttyS* instead of the first one. We long thought that using two console=ttyS* on the command line did not make sense. But then we realized that console= parameters were handled also by systemd, see http://0pointer.de/blog/projects/serial-console.html "By default systemd will instantiate one serial-getty@.service on the main kernel console, if it is not a virtual terminal." where "[4] If multiple kernel consoles are used simultaneously, the main console is the one listed first in /sys/class/tty/console/active, which is the last one listed on the kernel command line." This puts the original report into another light. The system is running in qemu. The first serial port is used to store the messages into a file. The second one is used to login to the system via a socket. It depends on systemd and the historic kernel behavior. By other words, systemd causes that it makes sense to define both console=ttyS1 console=ttyS0 on the command line. The kernel fix caused regression related to userspace (systemd) and need to be reverted. In addition, it went out that the fix helped only partially. The messages still were duplicated when the boot console was removed early by late_initcall(printk_late_init). Then the entire log was replayed when the same console was registered as a normal one. Link: 20170606160339.GC7604@pathway.suse.cz Cc: Aleksey Makarov <aleksey.makarov@linaro.org> Cc: Sabrina Dubroca <sd@queasysnail.net> Cc: Sudeep Holla <sudeep.holla@arm.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Jiri Slaby <jslaby@suse.com> Cc: Robin Murphy <robin.murphy@arm.com>, Cc: Steven Rostedt <rostedt@goodmis.org> Cc: "Nair, Jayachandran" <Jayachandran.Nair@cavium.com> Cc: linux-serial@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reported-by: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-06-08 18:01:30 +08:00
if (!brl_options)
preferred_console = i;
set_user_specified(c, user_specified);
return 0;
}
}
if (i == MAX_CMDLINECONSOLES)
return -E2BIG;
if (!brl_options)
preferred_console = i;
strlcpy(c->name, name, sizeof(c->name));
c->options = options;
set_user_specified(c, user_specified);
braille_set_options(c, brl_options);
c->index = idx;
return 0;
}
printk: add console_msg_format command line option 0day and kernelCI automatically parse kernel log - basically some sort of grepping using the pre-defined text patterns - in order to detect and report regressions/errors. There are several sources they get the kernel logs from: a) dmesg or /proc/ksmg This is the preferred way. Because `dmesg --raw' (see later Note) and /proc/kmsg output contains facility and log level, which greatly simplifies grepping for EMERG/ALERT/CRIT/ERR messages. b) serial consoles This option is harder to maintain, because serial console messages don't contain facility and log level. This patch introduces a `console_msg_format=' command line option, to switch between different message formatting on serial consoles. For the time being we have just two options - default and syslog. The "default" option just keeps the existing format. While the "syslog" option makes serial console messages to appear in syslog format [syslog() syscall], matching the `dmesg -S --raw' and `cat /proc/kmsg' output formats: - facility and log level - time stamp (depends on printk_time/PRINTK_TIME) - message <%u>[time stamp] text\n NOTE: while Kevin and Fengguang talk about "dmesg --raw", it's actually "dmesg -S --raw" that always prints messages in syslog format [per Petr Mladek]. Running "dmesg --raw" may produce output in non-syslog format sometimes. console_msg_format=syslog enables syslog format, thus in documentation we mention "dmesg -S --raw", not "dmesg --raw". Per Kevin Hilman: : Right now we can get this info from a "dmesg --raw" after bootup, : but it would be really nice in certain automation frameworks to : have a kernel command-line option to enable printing of loglevels : in default boot log. : : This is especially useful when ingesting kernel logs into advanced : search/analytics frameworks (I'm playing with and ELK stack: Elastic : Search, Logstash, Kibana). : : The other important reason for having this on the command line is that : for testing linux-next (and other bleeding edge developer branches), : it's common that we never make it to userspace, so can't even run : "dmesg --raw" (or equivalent.) So we really want this on the primary : boot (serial) console. Per Fengguang Wu, 0day scripts should quickly benefit from that feature, because they will be able to switch to a more reliable parsing, based on messages' facility and log levels [1]: `#{grep} -a -E -e '^<[0123]>' -e '^kern :(err |crit |alert |emerg )' instead of doing text pattern matching `#{grep} -a -F -f /lkp/printk-error-messages #{kmsg_file} | grep -a -v -E -f #{LKP_SRC}/etc/oops-pattern | grep -a -v -F -f #{LKP_SRC}/etc/kmsg-blacklist` [1] https://github.com/fengguang/lkp-tests/blob/master/lib/dmesg.rb Link: http://lkml.kernel.org/r/20171221054149.4398-1-sergey.senozhatsky@gmail.com To: Steven Rostedt <rostedt@goodmis.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Kevin Hilman <khilman@baylibre.com> Cc: Mark Brown <broonie@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: LKML <linux-kernel@vger.kernel.org> Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Fengguang Wu <fengguang.wu@intel.com> Reviewed-by: Kevin Hilman <khilman@baylibre.com> Tested-by: Kevin Hilman <khilman@baylibre.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-12-21 13:41:49 +08:00
static int __init console_msg_format_setup(char *str)
{
if (!strcmp(str, "syslog"))
console_msg_format = MSG_FORMAT_SYSLOG;
if (!strcmp(str, "default"))
console_msg_format = MSG_FORMAT_DEFAULT;
return 1;
}
__setup("console_msg_format=", console_msg_format_setup);
/*
* Set up a console. Called via do_early_param() in init/main.c
* for each "console=" parameter in the boot command line.
*/
static int __init console_setup(char *str)
{
char buf[sizeof(console_cmdline[0].name) + 4]; /* 4 for "ttyS" */
char *s, *options, *brl_options = NULL;
int idx;
/*
* console="" or console=null have been suggested as a way to
* disable console output. Use ttynull that has been created
* for exactly this purpose.
*/
if (str[0] == 0 || strcmp(str, "null") == 0) {
__add_preferred_console("ttynull", 0, NULL, NULL, true);
return 1;
}
if (_braille_console_setup(&str, &brl_options))
return 1;
/*
* 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;
options = strchr(str, ',');
if (options)
*(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 (isdigit(*s) || *s == ',')
break;
idx = simple_strtoul(s, NULL, 10);
*s = 0;
printk: Fix preferred console selection with multiple matches In the following circumstances, the rule of selecting the console corresponding to the last "console=" entry on the command line as the preferred console (CON_CONSDEV, ie, /dev/console) fails. This is a specific example, but it could happen with different consoles that have a similar name aliasing mechanism. - The kernel command line has both console=tty0 and console=ttyS0 in that order (the latter with speed etc... arguments). This is common with some cloud setups such as Amazon Linux. - add_preferred_console is called early to register "uart0". In our case that happens from acpi_parse_spcr() on arm64 since the "enable_console" argument is true on that architecture. This causes "uart0" to become entry 0 of the console_cmdline array. Now, because of the above, what happens is: - add_preferred_console is called by the cmdline parsing for tty0 and ttyS0 respectively, thus occupying entries 1 and 2 of the console_cmdline array (since this happens after ACPI SPCR parsing). At that point preferred_console is set to 2 as expected. - When the tty layer kicks in, it will call register_console for tty0. This will match entry 1 in console_cmdline array. It isn't our preferred console but because it's our only console at this point, it will end up "first" in the consoles list. - When 8250 probes the actual serial port later on, it calls register_console for ttyS0. At that point the loop in register_console tries to match it with the entries in the console_cmdline array. Ideally this should match ttyS0 in entry 2, which is preferred, causing it to be inserted first and to replace tty0 as CONSDEV. However, 8250 provides a "match" hook in its struct console, and that hook will match "uart" as an alias to "ttyS". So we match uart0 at entry 0 in the array which is not the preferred console and will not match entry 2 which is since we break out of the loop on the first match. As a result, we don't set CONSDEV and don't insert it first, but second in the console list. As a result, we end up with tty0 remaining first in the array, and thus /dev/console going there instead of the last user specified one which is ttyS0. This tentative fix register_console() to scan first for consoles specified on the command line, and only if none is found, to then scan for consoles specified by the architecture. Link: https://lore.kernel.org/r/20200213095133.23176-3-pmladek@suse.com Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2020-02-13 17:51:32 +08:00
__add_preferred_console(buf, idx, options, brl_options, true);
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)
{
printk: Fix preferred console selection with multiple matches In the following circumstances, the rule of selecting the console corresponding to the last "console=" entry on the command line as the preferred console (CON_CONSDEV, ie, /dev/console) fails. This is a specific example, but it could happen with different consoles that have a similar name aliasing mechanism. - The kernel command line has both console=tty0 and console=ttyS0 in that order (the latter with speed etc... arguments). This is common with some cloud setups such as Amazon Linux. - add_preferred_console is called early to register "uart0". In our case that happens from acpi_parse_spcr() on arm64 since the "enable_console" argument is true on that architecture. This causes "uart0" to become entry 0 of the console_cmdline array. Now, because of the above, what happens is: - add_preferred_console is called by the cmdline parsing for tty0 and ttyS0 respectively, thus occupying entries 1 and 2 of the console_cmdline array (since this happens after ACPI SPCR parsing). At that point preferred_console is set to 2 as expected. - When the tty layer kicks in, it will call register_console for tty0. This will match entry 1 in console_cmdline array. It isn't our preferred console but because it's our only console at this point, it will end up "first" in the consoles list. - When 8250 probes the actual serial port later on, it calls register_console for ttyS0. At that point the loop in register_console tries to match it with the entries in the console_cmdline array. Ideally this should match ttyS0 in entry 2, which is preferred, causing it to be inserted first and to replace tty0 as CONSDEV. However, 8250 provides a "match" hook in its struct console, and that hook will match "uart" as an alias to "ttyS". So we match uart0 at entry 0 in the array which is not the preferred console and will not match entry 2 which is since we break out of the loop on the first match. As a result, we don't set CONSDEV and don't insert it first, but second in the console list. As a result, we end up with tty0 remaining first in the array, and thus /dev/console going there instead of the last user specified one which is ttyS0. This tentative fix register_console() to scan first for consoles specified on the command line, and only if none is found, to then scan for consoles specified by the architecture. Link: https://lore.kernel.org/r/20200213095133.23176-3-pmladek@suse.com Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2020-02-13 17:51:32 +08:00
return __add_preferred_console(name, idx, options, NULL, false);
}
bool console_suspend_enabled = true;
EXPORT_SYMBOL(console_suspend_enabled);
static int __init console_suspend_disable(char *str)
{
console_suspend_enabled = false;
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");
static bool printk_console_no_auto_verbose;
void console_verbose(void)
{
if (console_loglevel && !printk_console_no_auto_verbose)
console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
}
EXPORT_SYMBOL_GPL(console_verbose);
module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644);
MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc");
/**
* suspend_console - suspend the console subsystem
*
* This disables printk() while we go into suspend states
*/
void suspend_console(void)
{
if (!console_suspend_enabled)
return;
pr_info("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();
}
printk: fix delayed messages from CPU hotplug events When a secondary CPU is being brought up, it is not uncommon for printk() to be invoked when cpu_online(smp_processor_id()) == 0. The case that I witnessed personally was on MIPS: http://lkml.org/lkml/2010/5/30/4 If (can_use_console() == 0), printk() will spool its output to log_buf and it will be visible in "dmesg", but that output will NOT be echoed to the console until somebody calls release_console_sem() from a CPU that is online. Therefore, the boot time messages from the new CPU can get stuck in "limbo" for a long time, and might suddenly appear on the screen when a completely unrelated event (e.g. "eth0: link is down") occurs. This patch modifies the console code so that any pending messages are automatically flushed out to the console whenever a CPU hotplug operation completes successfully or aborts. The issue was seen on 2.6.34. Original patch by Kevin Cernekee with cleanups by akpm and additional fixes by Santosh Shilimkar. This patch superseeds https://patchwork.linux-mips.org/patch/1357/. Signed-off-by: Kevin Cernekee <cernekee@gmail.com> To: <mingo@elte.hu> To: <akpm@linux-foundation.org> To: <simon.kagstrom@netinsight.net> To: <David.Woodhouse@intel.com> To: <lethal@linux-sh.org> Cc: <linux-kernel@vger.kernel.org> Cc: <linux-mips@linux-mips.org> Reviewed-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Kevin Cernekee <cernekee@gmail.com> Patchwork: https://patchwork.linux-mips.org/patch/1534/ LKML-Reference: <ede63b5a20af951c755736f035d1e787772d7c28@localhost> LKML-Reference: <EAF47CD23C76F840A9E7FCE10091EFAB02C5DB6D1F@dbde02.ent.ti.com> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-06-04 13:11:25 +08:00
/**
* console_cpu_notify - print deferred console messages after CPU hotplug
* @cpu: unused
printk: fix delayed messages from CPU hotplug events When a secondary CPU is being brought up, it is not uncommon for printk() to be invoked when cpu_online(smp_processor_id()) == 0. The case that I witnessed personally was on MIPS: http://lkml.org/lkml/2010/5/30/4 If (can_use_console() == 0), printk() will spool its output to log_buf and it will be visible in "dmesg", but that output will NOT be echoed to the console until somebody calls release_console_sem() from a CPU that is online. Therefore, the boot time messages from the new CPU can get stuck in "limbo" for a long time, and might suddenly appear on the screen when a completely unrelated event (e.g. "eth0: link is down") occurs. This patch modifies the console code so that any pending messages are automatically flushed out to the console whenever a CPU hotplug operation completes successfully or aborts. The issue was seen on 2.6.34. Original patch by Kevin Cernekee with cleanups by akpm and additional fixes by Santosh Shilimkar. This patch superseeds https://patchwork.linux-mips.org/patch/1357/. Signed-off-by: Kevin Cernekee <cernekee@gmail.com> To: <mingo@elte.hu> To: <akpm@linux-foundation.org> To: <simon.kagstrom@netinsight.net> To: <David.Woodhouse@intel.com> To: <lethal@linux-sh.org> Cc: <linux-kernel@vger.kernel.org> Cc: <linux-mips@linux-mips.org> Reviewed-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Kevin Cernekee <cernekee@gmail.com> Patchwork: https://patchwork.linux-mips.org/patch/1534/ LKML-Reference: <ede63b5a20af951c755736f035d1e787772d7c28@localhost> LKML-Reference: <EAF47CD23C76F840A9E7FCE10091EFAB02C5DB6D1F@dbde02.ent.ti.com> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-06-04 13:11:25 +08:00
*
* If printk() is called from a CPU that is not online yet, the messages
* will be printed on the console only if there are CON_ANYTIME consoles.
* This function is called when a new CPU comes online (or fails to come
* up) or goes offline.
printk: fix delayed messages from CPU hotplug events When a secondary CPU is being brought up, it is not uncommon for printk() to be invoked when cpu_online(smp_processor_id()) == 0. The case that I witnessed personally was on MIPS: http://lkml.org/lkml/2010/5/30/4 If (can_use_console() == 0), printk() will spool its output to log_buf and it will be visible in "dmesg", but that output will NOT be echoed to the console until somebody calls release_console_sem() from a CPU that is online. Therefore, the boot time messages from the new CPU can get stuck in "limbo" for a long time, and might suddenly appear on the screen when a completely unrelated event (e.g. "eth0: link is down") occurs. This patch modifies the console code so that any pending messages are automatically flushed out to the console whenever a CPU hotplug operation completes successfully or aborts. The issue was seen on 2.6.34. Original patch by Kevin Cernekee with cleanups by akpm and additional fixes by Santosh Shilimkar. This patch superseeds https://patchwork.linux-mips.org/patch/1357/. Signed-off-by: Kevin Cernekee <cernekee@gmail.com> To: <mingo@elte.hu> To: <akpm@linux-foundation.org> To: <simon.kagstrom@netinsight.net> To: <David.Woodhouse@intel.com> To: <lethal@linux-sh.org> Cc: <linux-kernel@vger.kernel.org> Cc: <linux-mips@linux-mips.org> Reviewed-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Kevin Cernekee <cernekee@gmail.com> Patchwork: https://patchwork.linux-mips.org/patch/1534/ LKML-Reference: <ede63b5a20af951c755736f035d1e787772d7c28@localhost> LKML-Reference: <EAF47CD23C76F840A9E7FCE10091EFAB02C5DB6D1F@dbde02.ent.ti.com> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-06-04 13:11:25 +08:00
*/
static int console_cpu_notify(unsigned int cpu)
{
if (!cpuhp_tasks_frozen) {
/* If trylock fails, someone else is doing the printing */
if (console_trylock())
console_unlock();
printk: fix delayed messages from CPU hotplug events When a secondary CPU is being brought up, it is not uncommon for printk() to be invoked when cpu_online(smp_processor_id()) == 0. The case that I witnessed personally was on MIPS: http://lkml.org/lkml/2010/5/30/4 If (can_use_console() == 0), printk() will spool its output to log_buf and it will be visible in "dmesg", but that output will NOT be echoed to the console until somebody calls release_console_sem() from a CPU that is online. Therefore, the boot time messages from the new CPU can get stuck in "limbo" for a long time, and might suddenly appear on the screen when a completely unrelated event (e.g. "eth0: link is down") occurs. This patch modifies the console code so that any pending messages are automatically flushed out to the console whenever a CPU hotplug operation completes successfully or aborts. The issue was seen on 2.6.34. Original patch by Kevin Cernekee with cleanups by akpm and additional fixes by Santosh Shilimkar. This patch superseeds https://patchwork.linux-mips.org/patch/1357/. Signed-off-by: Kevin Cernekee <cernekee@gmail.com> To: <mingo@elte.hu> To: <akpm@linux-foundation.org> To: <simon.kagstrom@netinsight.net> To: <David.Woodhouse@intel.com> To: <lethal@linux-sh.org> Cc: <linux-kernel@vger.kernel.org> Cc: <linux-mips@linux-mips.org> Reviewed-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Kevin Cernekee <cernekee@gmail.com> Patchwork: https://patchwork.linux-mips.org/patch/1534/ LKML-Reference: <ede63b5a20af951c755736f035d1e787772d7c28@localhost> LKML-Reference: <EAF47CD23C76F840A9E7FCE10091EFAB02C5DB6D1F@dbde02.ent.ti.com> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-06-04 13:11:25 +08:00
}
return 0;
printk: fix delayed messages from CPU hotplug events When a secondary CPU is being brought up, it is not uncommon for printk() to be invoked when cpu_online(smp_processor_id()) == 0. The case that I witnessed personally was on MIPS: http://lkml.org/lkml/2010/5/30/4 If (can_use_console() == 0), printk() will spool its output to log_buf and it will be visible in "dmesg", but that output will NOT be echoed to the console until somebody calls release_console_sem() from a CPU that is online. Therefore, the boot time messages from the new CPU can get stuck in "limbo" for a long time, and might suddenly appear on the screen when a completely unrelated event (e.g. "eth0: link is down") occurs. This patch modifies the console code so that any pending messages are automatically flushed out to the console whenever a CPU hotplug operation completes successfully or aborts. The issue was seen on 2.6.34. Original patch by Kevin Cernekee with cleanups by akpm and additional fixes by Santosh Shilimkar. This patch superseeds https://patchwork.linux-mips.org/patch/1357/. Signed-off-by: Kevin Cernekee <cernekee@gmail.com> To: <mingo@elte.hu> To: <akpm@linux-foundation.org> To: <simon.kagstrom@netinsight.net> To: <David.Woodhouse@intel.com> To: <lethal@linux-sh.org> Cc: <linux-kernel@vger.kernel.org> Cc: <linux-mips@linux-mips.org> Reviewed-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Kevin Cernekee <cernekee@gmail.com> Patchwork: https://patchwork.linux-mips.org/patch/1534/ LKML-Reference: <ede63b5a20af951c755736f035d1e787772d7c28@localhost> LKML-Reference: <EAF47CD23C76F840A9E7FCE10091EFAB02C5DB6D1F@dbde02.ent.ti.com> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-06-04 13:11:25 +08:00
}
/**
* 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;
}
EXPORT_SYMBOL(console_lock);
/**
* console_trylock - try to lock the console system for exclusive use.
*
* Try 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;
printk: Never set console_may_schedule in console_trylock() This patch, basically, reverts commit 6b97a20d3a79 ("printk: set may_schedule for some of console_trylock() callers"). That commit was a mistake, it introduced a big dependency on the scheduler, by enabling preemption under console_sem in printk()->console_unlock() path, which is rather too critical. The patch did not significantly reduce the possibilities of printk() lockups, but made it possible to stall printk(), as has been reported by Tetsuo Handa [1]. Another issues is that preemption under console_sem also messes up with Steven Rostedt's hand off scheme, by making it possible to sleep with console_sem both in console_unlock() and in vprintk_emit(), after acquiring the console_sem ownership (anywhere between printk_safe_exit_irqrestore() in console_trylock_spinning() and printk_safe_enter_irqsave() in console_unlock()). This makes hand off less likely and, at the same time, may result in a significant amount of pending logbuf messages. Preempted console_sem owner makes it impossible for other CPUs to emit logbuf messages, but does not make it impossible for other CPUs to append new messages to the logbuf. Reinstate the old behavior and make printk() non-preemptible. Should any printk() lockup reports arrive they must be handled in a different way. [1] http://lkml.kernel.org/r/201603022101.CAH73907.OVOOMFHFFtQJSL%20()%20I-love%20!%20SAKURA%20!%20ne%20!%20jp Fixes: 6b97a20d3a79 ("printk: set may_schedule for some of console_trylock() callers") Link: http://lkml.kernel.org/r/20180116044716.GE6607@jagdpanzerIV To: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: akpm@linux-foundation.org Cc: linux-mm@kvack.org Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: linux-kernel@vger.kernel.org Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-01-16 12:47:16 +08:00
console_may_schedule = 0;
return 1;
}
EXPORT_SYMBOL(console_trylock);
int is_console_locked(void)
{
return console_locked;
}
EXPORT_SYMBOL(is_console_locked);
printk: move can_use_console() out of console_trylock_for_printk() console_unlock() allows to cond_resched() if its caller has set `console_may_schedule' to 1 (this functionality is present since 8d91f8b15361 ("printk: do cond_resched() between lines while outputting to consoles"). The rules are: -- console_lock() always sets `console_may_schedule' to 1 -- console_trylock() always sets `console_may_schedule' to 0 printk() calls console_unlock() with preemption desabled, which basically can lead to RCU stalls, watchdog soft lockups, etc. if something is simultaneously calling printk() frequent enough (IOW, console_sem owner always has new data to send to console divers and can't leave console_unlock() for a long time). printk()->console_trylock() callers do not necessarily execute in atomic contexts, and some of them can cond_resched() in console_unlock(). console_trylock() can set `console_may_schedule' to 1 (allow cond_resched() later in consoe_unlock()) when it's safe. This patch (of 3): vprintk_emit() disables preemption around console_trylock_for_printk() and console_unlock() calls for a strong reason -- can_use_console() check. The thing is that vprintl_emit() can be called on a CPU that is not fully brought up yet (!cpu_online()), which potentially can cause problems if console driver wants to access per-cpu data. A console driver can explicitly state that it's safe to call it from !online cpu by setting CON_ANYTIME bit in console ->flags. That's why for !cpu_online() can_use_console() iterates all the console to find out if there is a CON_ANYTIME console, otherwise console_unlock() must be avoided. can_use_console() ensures that console_unlock() call is safe in vprintk_emit() only; console_lock() and console_trylock() are not covered by this check. Even though call_console_drivers(), invoked from console_cont_flush() and console_unlock(), tests `!cpu_online() && CON_ANYTIME' for_each_console(), it may be too late, which can result in messages loss. Assume that we have 2 cpus -- CPU0 is online, CPU1 is !online, and no CON_ANYTIME consoles available. CPU0 online CPU1 !online console_trylock() ... console_unlock() console_cont_flush spin_lock logbuf_lock if (!cont.len) { spin_unlock logbuf_lock return } for (;;) { vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock spin_lock logbuf_lock !console_trylock_for_printk msg_print_text return console_idx = log_next() console_seq++ console_prev = msg->flags spin_unlock logbuf_lock call_console_drivers() for_each_console(con) { if (!cpu_online() && !(con->flags & CON_ANYTIME)) continue; } /* * no message printed, we lost it */ vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock !console_trylock_for_printk return /* * go to the beginning of the loop, * find out there are new messages, * lose it */ } console_trylock()/console_lock() call on CPU1 may come from cpu notifiers registered on that CPU. Since notifiers are not getting unregistered when CPU is going DOWN, all of the notifiers receive notifications during CPU UP. For example, on my x86_64, I see around 50 notification sent from offline CPU to itself [swapper/2] from cpu:2 to:2 action:CPU_STARTING hotplug_hrtick [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_main_cpu_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_queue_reinit_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING console_cpu_notify while doing echo 0 > /sys/devices/system/cpu/cpu2/online echo 1 > /sys/devices/system/cpu/cpu2/online So grabbing the console_sem lock while CPU is !online is possible, in theory. This patch moves can_use_console() check out of console_trylock_for_printk(). Instead it calls it in console_unlock(), so now console_lock()/console_unlock() are also 'protected' by can_use_console(). This also means that console_trylock_for_printk() is not really needed anymore and can be removed. Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Jan Kara <jack@suse.com> Cc: Tejun Heo <tj@kernel.org> Cc: Kyle McMartin <kyle@kernel.org> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Calvin Owens <calvinowens@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 05:21:20 +08:00
/*
* Check if we have any console that is capable of printing while cpu is
* booting or shutting down. Requires console_sem.
*/
static int have_callable_console(void)
{
struct console *con;
for_each_console(con)
if ((con->flags & CON_ENABLED) &&
(con->flags & CON_ANYTIME))
printk: move can_use_console() out of console_trylock_for_printk() console_unlock() allows to cond_resched() if its caller has set `console_may_schedule' to 1 (this functionality is present since 8d91f8b15361 ("printk: do cond_resched() between lines while outputting to consoles"). The rules are: -- console_lock() always sets `console_may_schedule' to 1 -- console_trylock() always sets `console_may_schedule' to 0 printk() calls console_unlock() with preemption desabled, which basically can lead to RCU stalls, watchdog soft lockups, etc. if something is simultaneously calling printk() frequent enough (IOW, console_sem owner always has new data to send to console divers and can't leave console_unlock() for a long time). printk()->console_trylock() callers do not necessarily execute in atomic contexts, and some of them can cond_resched() in console_unlock(). console_trylock() can set `console_may_schedule' to 1 (allow cond_resched() later in consoe_unlock()) when it's safe. This patch (of 3): vprintk_emit() disables preemption around console_trylock_for_printk() and console_unlock() calls for a strong reason -- can_use_console() check. The thing is that vprintl_emit() can be called on a CPU that is not fully brought up yet (!cpu_online()), which potentially can cause problems if console driver wants to access per-cpu data. A console driver can explicitly state that it's safe to call it from !online cpu by setting CON_ANYTIME bit in console ->flags. That's why for !cpu_online() can_use_console() iterates all the console to find out if there is a CON_ANYTIME console, otherwise console_unlock() must be avoided. can_use_console() ensures that console_unlock() call is safe in vprintk_emit() only; console_lock() and console_trylock() are not covered by this check. Even though call_console_drivers(), invoked from console_cont_flush() and console_unlock(), tests `!cpu_online() && CON_ANYTIME' for_each_console(), it may be too late, which can result in messages loss. Assume that we have 2 cpus -- CPU0 is online, CPU1 is !online, and no CON_ANYTIME consoles available. CPU0 online CPU1 !online console_trylock() ... console_unlock() console_cont_flush spin_lock logbuf_lock if (!cont.len) { spin_unlock logbuf_lock return } for (;;) { vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock spin_lock logbuf_lock !console_trylock_for_printk msg_print_text return console_idx = log_next() console_seq++ console_prev = msg->flags spin_unlock logbuf_lock call_console_drivers() for_each_console(con) { if (!cpu_online() && !(con->flags & CON_ANYTIME)) continue; } /* * no message printed, we lost it */ vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock !console_trylock_for_printk return /* * go to the beginning of the loop, * find out there are new messages, * lose it */ } console_trylock()/console_lock() call on CPU1 may come from cpu notifiers registered on that CPU. Since notifiers are not getting unregistered when CPU is going DOWN, all of the notifiers receive notifications during CPU UP. For example, on my x86_64, I see around 50 notification sent from offline CPU to itself [swapper/2] from cpu:2 to:2 action:CPU_STARTING hotplug_hrtick [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_main_cpu_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_queue_reinit_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING console_cpu_notify while doing echo 0 > /sys/devices/system/cpu/cpu2/online echo 1 > /sys/devices/system/cpu/cpu2/online So grabbing the console_sem lock while CPU is !online is possible, in theory. This patch moves can_use_console() check out of console_trylock_for_printk(). Instead it calls it in console_unlock(), so now console_lock()/console_unlock() are also 'protected' by can_use_console(). This also means that console_trylock_for_printk() is not really needed anymore and can be removed. Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Jan Kara <jack@suse.com> Cc: Tejun Heo <tj@kernel.org> Cc: Kyle McMartin <kyle@kernel.org> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Calvin Owens <calvinowens@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 05:21:20 +08:00
return 1;
return 0;
}
/*
* Return true when this CPU should unlock console_sem without pushing all
* messages to the console. This reduces the chance that the console is
* locked when the panic CPU tries to use it.
*/
static bool abandon_console_lock_in_panic(void)
{
if (!panic_in_progress())
return false;
/*
* We can use raw_smp_processor_id() here because it is impossible for
* the task to be migrated to the panic_cpu, or away from it. If
* panic_cpu has already been set, and we're not currently executing on
* that CPU, then we never will be.
*/
return atomic_read(&panic_cpu) != raw_smp_processor_id();
}
printk: move can_use_console() out of console_trylock_for_printk() console_unlock() allows to cond_resched() if its caller has set `console_may_schedule' to 1 (this functionality is present since 8d91f8b15361 ("printk: do cond_resched() between lines while outputting to consoles"). The rules are: -- console_lock() always sets `console_may_schedule' to 1 -- console_trylock() always sets `console_may_schedule' to 0 printk() calls console_unlock() with preemption desabled, which basically can lead to RCU stalls, watchdog soft lockups, etc. if something is simultaneously calling printk() frequent enough (IOW, console_sem owner always has new data to send to console divers and can't leave console_unlock() for a long time). printk()->console_trylock() callers do not necessarily execute in atomic contexts, and some of them can cond_resched() in console_unlock(). console_trylock() can set `console_may_schedule' to 1 (allow cond_resched() later in consoe_unlock()) when it's safe. This patch (of 3): vprintk_emit() disables preemption around console_trylock_for_printk() and console_unlock() calls for a strong reason -- can_use_console() check. The thing is that vprintl_emit() can be called on a CPU that is not fully brought up yet (!cpu_online()), which potentially can cause problems if console driver wants to access per-cpu data. A console driver can explicitly state that it's safe to call it from !online cpu by setting CON_ANYTIME bit in console ->flags. That's why for !cpu_online() can_use_console() iterates all the console to find out if there is a CON_ANYTIME console, otherwise console_unlock() must be avoided. can_use_console() ensures that console_unlock() call is safe in vprintk_emit() only; console_lock() and console_trylock() are not covered by this check. Even though call_console_drivers(), invoked from console_cont_flush() and console_unlock(), tests `!cpu_online() && CON_ANYTIME' for_each_console(), it may be too late, which can result in messages loss. Assume that we have 2 cpus -- CPU0 is online, CPU1 is !online, and no CON_ANYTIME consoles available. CPU0 online CPU1 !online console_trylock() ... console_unlock() console_cont_flush spin_lock logbuf_lock if (!cont.len) { spin_unlock logbuf_lock return } for (;;) { vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock spin_lock logbuf_lock !console_trylock_for_printk msg_print_text return console_idx = log_next() console_seq++ console_prev = msg->flags spin_unlock logbuf_lock call_console_drivers() for_each_console(con) { if (!cpu_online() && !(con->flags & CON_ANYTIME)) continue; } /* * no message printed, we lost it */ vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock !console_trylock_for_printk return /* * go to the beginning of the loop, * find out there are new messages, * lose it */ } console_trylock()/console_lock() call on CPU1 may come from cpu notifiers registered on that CPU. Since notifiers are not getting unregistered when CPU is going DOWN, all of the notifiers receive notifications during CPU UP. For example, on my x86_64, I see around 50 notification sent from offline CPU to itself [swapper/2] from cpu:2 to:2 action:CPU_STARTING hotplug_hrtick [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_main_cpu_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_queue_reinit_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING console_cpu_notify while doing echo 0 > /sys/devices/system/cpu/cpu2/online echo 1 > /sys/devices/system/cpu/cpu2/online So grabbing the console_sem lock while CPU is !online is possible, in theory. This patch moves can_use_console() check out of console_trylock_for_printk(). Instead it calls it in console_unlock(), so now console_lock()/console_unlock() are also 'protected' by can_use_console(). This also means that console_trylock_for_printk() is not really needed anymore and can be removed. Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Jan Kara <jack@suse.com> Cc: Tejun Heo <tj@kernel.org> Cc: Kyle McMartin <kyle@kernel.org> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Calvin Owens <calvinowens@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 05:21:20 +08:00
/*
* 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(void)
{
return cpu_online(raw_smp_processor_id()) || have_callable_console();
}
/**
* 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)
{
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
static char ext_text[CONSOLE_EXT_LOG_MAX];
static char text[CONSOLE_LOG_MAX];
static int panic_console_dropped;
unsigned long flags;
printk: do cond_resched() between lines while outputting to consoles @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Calvin Owens <calvinowens@fb.com> Acked-by: Jan Kara <jack@suse.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Kyle McMartin <kyle@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:58:24 +08:00
bool do_cond_resched, retry;
struct printk_info info;
struct printk_record r;
printk/console: Check consistent sequence number when handling race in console_unlock() The standard printk() tries to flush the message to the console immediately. It tries to take the console lock. If the lock is already taken then the current owner is responsible for flushing even the new message. There is a small race window between checking whether a new message is available and releasing the console lock. It is solved by re-checking the state after releasing the console lock. If the check is positive then console_unlock() tries to take the lock again and process the new message as well. The commit 996e966640ddea7b535c ("printk: remove logbuf_lock") causes that console_seq is not longer read atomically. As a result, the re-check might be done with an inconsistent 64-bit index. Solve it by using the last sequence number that has been checked under the console lock. In the worst case, it will take the lock again only to realized that the new message has already been proceed. But it was possible even before. The variable next_seq is marked as __maybe_unused to call down compiler warning when CONFIG_PRINTK is not defined. Fixes: commit 996e966640ddea7b535c ("printk: remove logbuf_lock") Reported-by: kernel test robot <lkp@intel.com> # unused next_seq warning Cc: stable@vger.kernel.org # 5.13 Signed-off-by: Petr Mladek <pmladek@suse.com> Acked-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: John Ogness <john.ogness@linutronix.de> Link: https://lore.kernel.org/r/20210702150657.26760-1-pmladek@suse.com
2021-07-02 23:06:57 +08:00
u64 __maybe_unused next_seq;
if (console_suspended) {
up_console_sem();
return;
}
[PATCH] vt: printk: Fix framebuffer console triggering might_sleep assertion Reported by: Dave Jones Whilst printk'ing to both console and serial console, I got this... (2.6.18rc1) BUG: sleeping function called from invalid context at kernel/sched.c:4438 in_atomic():0, irqs_disabled():1 Call Trace: [<ffffffff80271db8>] show_trace+0xaa/0x23d [<ffffffff80271f60>] dump_stack+0x15/0x17 [<ffffffff8020b9f8>] __might_sleep+0xb2/0xb4 [<ffffffff8029232e>] __cond_resched+0x15/0x55 [<ffffffff80267eb8>] cond_resched+0x3b/0x42 [<ffffffff80268c64>] console_conditional_schedule+0x12/0x14 [<ffffffff80368159>] fbcon_redraw+0xf6/0x160 [<ffffffff80369c58>] fbcon_scroll+0x5d9/0xb52 [<ffffffff803a43c4>] scrup+0x6b/0xd6 [<ffffffff803a4453>] lf+0x24/0x44 [<ffffffff803a7ff8>] vt_console_print+0x166/0x23d [<ffffffff80295528>] __call_console_drivers+0x65/0x76 [<ffffffff80295597>] _call_console_drivers+0x5e/0x62 [<ffffffff80217e3f>] release_console_sem+0x14b/0x232 [<ffffffff8036acd6>] fb_flashcursor+0x279/0x2a6 [<ffffffff80251e3f>] run_workqueue+0xa8/0xfb [<ffffffff8024e5e0>] worker_thread+0xef/0x122 [<ffffffff8023660f>] kthread+0x100/0x136 [<ffffffff8026419e>] child_rip+0x8/0x12 This can occur when release_console_sem() is called but the log buffer still has contents that need to be flushed. The console drivers are called while the console_may_schedule flag is still true. The might_sleep() is triggered when fbcon calls console_conditional_schedule(). Fix by setting console_may_schedule to zero earlier, before the call to the console drivers. Signed-off-by: Antonino Daplas <adaplas@pol.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-08-06 03:14:16 +08:00
prb_rec_init_rd(&r, &info, text, sizeof(text));
printk: do cond_resched() between lines while outputting to consoles @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Calvin Owens <calvinowens@fb.com> Acked-by: Jan Kara <jack@suse.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Kyle McMartin <kyle@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:58:24 +08:00
/*
printk: Correctly handle preemption in console_unlock() Some console drivers code calls console_conditional_schedule() that looks at @console_may_schedule. The value must be cleared when the drivers are called from console_unlock() with interrupts disabled. But rescheduling is fine when the same code is called, for example, from tty operations where the console semaphore is taken via console_lock(). This is why @console_may_schedule is cleared before calling console drivers. The original value is stored to decide if we could sleep between lines. Now, @console_may_schedule is not cleared when we call console_trylock() and jump back to the "again" goto label. This has become a problem, since the commit 6b97a20d3a7909daa066 ("printk: set may_schedule for some of console_trylock() callers"). @console_may_schedule might get enabled now. There is also the opposite problem. console_lock() can be called only from preemptive context. It can always enable scheduling in the console code. But console_trylock() is not able to detect it when CONFIG_PREEMPT_COUNT is disabled. Therefore we should use the original @console_may_schedule value after re-acquiring the console semaphore in console_unlock(). This patch solves both problems by moving the "again" goto label. Alternative solution was to clear and restore the value around call_console_drivers(). Then console_conditional_schedule() could be used also inside console_unlock(). But there was a potential race with console_flush_on_panic() as reported by Sergey Senozhatsky. That function should be called only where there is only one CPU and with interrupts disabled. But better be on the safe side because stopping CPUs might fail. Fixes: 6b97a20d3a7909 ("printk: set may_schedule for some of console_trylock() callers") Link: http://lkml.kernel.org/r/1490372045-22288-1-git-send-email-pmladek@suse.com Suggested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jiri Slaby <jslaby@suse.cz> Cc: linux-fbdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-03-25 00:14:05 +08:00
* Console drivers are called with interrupts disabled, so
printk: do cond_resched() between lines while outputting to consoles @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Calvin Owens <calvinowens@fb.com> Acked-by: Jan Kara <jack@suse.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Kyle McMartin <kyle@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:58:24 +08:00
* @console_may_schedule should be cleared before; however, we may
* end up dumping a lot of lines, for example, if called from
* console registration path, and should invoke cond_resched()
* between lines if allowable. Not doing so can cause a very long
* scheduling stall on a slow console leading to RCU stall and
* softlockup warnings which exacerbate the issue with more
* messages practically incapacitating the system.
printk: Correctly handle preemption in console_unlock() Some console drivers code calls console_conditional_schedule() that looks at @console_may_schedule. The value must be cleared when the drivers are called from console_unlock() with interrupts disabled. But rescheduling is fine when the same code is called, for example, from tty operations where the console semaphore is taken via console_lock(). This is why @console_may_schedule is cleared before calling console drivers. The original value is stored to decide if we could sleep between lines. Now, @console_may_schedule is not cleared when we call console_trylock() and jump back to the "again" goto label. This has become a problem, since the commit 6b97a20d3a7909daa066 ("printk: set may_schedule for some of console_trylock() callers"). @console_may_schedule might get enabled now. There is also the opposite problem. console_lock() can be called only from preemptive context. It can always enable scheduling in the console code. But console_trylock() is not able to detect it when CONFIG_PREEMPT_COUNT is disabled. Therefore we should use the original @console_may_schedule value after re-acquiring the console semaphore in console_unlock(). This patch solves both problems by moving the "again" goto label. Alternative solution was to clear and restore the value around call_console_drivers(). Then console_conditional_schedule() could be used also inside console_unlock(). But there was a potential race with console_flush_on_panic() as reported by Sergey Senozhatsky. That function should be called only where there is only one CPU and with interrupts disabled. But better be on the safe side because stopping CPUs might fail. Fixes: 6b97a20d3a7909 ("printk: set may_schedule for some of console_trylock() callers") Link: http://lkml.kernel.org/r/1490372045-22288-1-git-send-email-pmladek@suse.com Suggested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jiri Slaby <jslaby@suse.cz> Cc: linux-fbdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-03-25 00:14:05 +08:00
*
* console_trylock() is not able to detect the preemptive
* context reliably. Therefore the value must be stored before
* and cleared after the "again" goto label.
printk: do cond_resched() between lines while outputting to consoles @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Calvin Owens <calvinowens@fb.com> Acked-by: Jan Kara <jack@suse.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Kyle McMartin <kyle@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:58:24 +08:00
*/
do_cond_resched = console_may_schedule;
printk: Correctly handle preemption in console_unlock() Some console drivers code calls console_conditional_schedule() that looks at @console_may_schedule. The value must be cleared when the drivers are called from console_unlock() with interrupts disabled. But rescheduling is fine when the same code is called, for example, from tty operations where the console semaphore is taken via console_lock(). This is why @console_may_schedule is cleared before calling console drivers. The original value is stored to decide if we could sleep between lines. Now, @console_may_schedule is not cleared when we call console_trylock() and jump back to the "again" goto label. This has become a problem, since the commit 6b97a20d3a7909daa066 ("printk: set may_schedule for some of console_trylock() callers"). @console_may_schedule might get enabled now. There is also the opposite problem. console_lock() can be called only from preemptive context. It can always enable scheduling in the console code. But console_trylock() is not able to detect it when CONFIG_PREEMPT_COUNT is disabled. Therefore we should use the original @console_may_schedule value after re-acquiring the console semaphore in console_unlock(). This patch solves both problems by moving the "again" goto label. Alternative solution was to clear and restore the value around call_console_drivers(). Then console_conditional_schedule() could be used also inside console_unlock(). But there was a potential race with console_flush_on_panic() as reported by Sergey Senozhatsky. That function should be called only where there is only one CPU and with interrupts disabled. But better be on the safe side because stopping CPUs might fail. Fixes: 6b97a20d3a7909 ("printk: set may_schedule for some of console_trylock() callers") Link: http://lkml.kernel.org/r/1490372045-22288-1-git-send-email-pmladek@suse.com Suggested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jiri Slaby <jslaby@suse.cz> Cc: linux-fbdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-03-25 00:14:05 +08:00
again:
[PATCH] vt: printk: Fix framebuffer console triggering might_sleep assertion Reported by: Dave Jones Whilst printk'ing to both console and serial console, I got this... (2.6.18rc1) BUG: sleeping function called from invalid context at kernel/sched.c:4438 in_atomic():0, irqs_disabled():1 Call Trace: [<ffffffff80271db8>] show_trace+0xaa/0x23d [<ffffffff80271f60>] dump_stack+0x15/0x17 [<ffffffff8020b9f8>] __might_sleep+0xb2/0xb4 [<ffffffff8029232e>] __cond_resched+0x15/0x55 [<ffffffff80267eb8>] cond_resched+0x3b/0x42 [<ffffffff80268c64>] console_conditional_schedule+0x12/0x14 [<ffffffff80368159>] fbcon_redraw+0xf6/0x160 [<ffffffff80369c58>] fbcon_scroll+0x5d9/0xb52 [<ffffffff803a43c4>] scrup+0x6b/0xd6 [<ffffffff803a4453>] lf+0x24/0x44 [<ffffffff803a7ff8>] vt_console_print+0x166/0x23d [<ffffffff80295528>] __call_console_drivers+0x65/0x76 [<ffffffff80295597>] _call_console_drivers+0x5e/0x62 [<ffffffff80217e3f>] release_console_sem+0x14b/0x232 [<ffffffff8036acd6>] fb_flashcursor+0x279/0x2a6 [<ffffffff80251e3f>] run_workqueue+0xa8/0xfb [<ffffffff8024e5e0>] worker_thread+0xef/0x122 [<ffffffff8023660f>] kthread+0x100/0x136 [<ffffffff8026419e>] child_rip+0x8/0x12 This can occur when release_console_sem() is called but the log buffer still has contents that need to be flushed. The console drivers are called while the console_may_schedule flag is still true. The might_sleep() is triggered when fbcon calls console_conditional_schedule(). Fix by setting console_may_schedule to zero earlier, before the call to the console drivers. Signed-off-by: Antonino Daplas <adaplas@pol.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-08-06 03:14:16 +08:00
console_may_schedule = 0;
printk: move can_use_console() out of console_trylock_for_printk() console_unlock() allows to cond_resched() if its caller has set `console_may_schedule' to 1 (this functionality is present since 8d91f8b15361 ("printk: do cond_resched() between lines while outputting to consoles"). The rules are: -- console_lock() always sets `console_may_schedule' to 1 -- console_trylock() always sets `console_may_schedule' to 0 printk() calls console_unlock() with preemption desabled, which basically can lead to RCU stalls, watchdog soft lockups, etc. if something is simultaneously calling printk() frequent enough (IOW, console_sem owner always has new data to send to console divers and can't leave console_unlock() for a long time). printk()->console_trylock() callers do not necessarily execute in atomic contexts, and some of them can cond_resched() in console_unlock(). console_trylock() can set `console_may_schedule' to 1 (allow cond_resched() later in consoe_unlock()) when it's safe. This patch (of 3): vprintk_emit() disables preemption around console_trylock_for_printk() and console_unlock() calls for a strong reason -- can_use_console() check. The thing is that vprintl_emit() can be called on a CPU that is not fully brought up yet (!cpu_online()), which potentially can cause problems if console driver wants to access per-cpu data. A console driver can explicitly state that it's safe to call it from !online cpu by setting CON_ANYTIME bit in console ->flags. That's why for !cpu_online() can_use_console() iterates all the console to find out if there is a CON_ANYTIME console, otherwise console_unlock() must be avoided. can_use_console() ensures that console_unlock() call is safe in vprintk_emit() only; console_lock() and console_trylock() are not covered by this check. Even though call_console_drivers(), invoked from console_cont_flush() and console_unlock(), tests `!cpu_online() && CON_ANYTIME' for_each_console(), it may be too late, which can result in messages loss. Assume that we have 2 cpus -- CPU0 is online, CPU1 is !online, and no CON_ANYTIME consoles available. CPU0 online CPU1 !online console_trylock() ... console_unlock() console_cont_flush spin_lock logbuf_lock if (!cont.len) { spin_unlock logbuf_lock return } for (;;) { vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock spin_lock logbuf_lock !console_trylock_for_printk msg_print_text return console_idx = log_next() console_seq++ console_prev = msg->flags spin_unlock logbuf_lock call_console_drivers() for_each_console(con) { if (!cpu_online() && !(con->flags & CON_ANYTIME)) continue; } /* * no message printed, we lost it */ vprintk_emit spin_lock logbuf_lock log_store spin_unlock logbuf_lock !console_trylock_for_printk return /* * go to the beginning of the loop, * find out there are new messages, * lose it */ } console_trylock()/console_lock() call on CPU1 may come from cpu notifiers registered on that CPU. Since notifiers are not getting unregistered when CPU is going DOWN, all of the notifiers receive notifications during CPU UP. For example, on my x86_64, I see around 50 notification sent from offline CPU to itself [swapper/2] from cpu:2 to:2 action:CPU_STARTING hotplug_hrtick [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_main_cpu_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING blk_mq_queue_reinit_notify [swapper/2] from cpu:2 to:2 action:CPU_STARTING console_cpu_notify while doing echo 0 > /sys/devices/system/cpu/cpu2/online echo 1 > /sys/devices/system/cpu/cpu2/online So grabbing the console_sem lock while CPU is !online is possible, in theory. This patch moves can_use_console() check out of console_trylock_for_printk(). Instead it calls it in console_unlock(), so now console_lock()/console_unlock() are also 'protected' by can_use_console(). This also means that console_trylock_for_printk() is not really needed anymore and can be removed. Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Jan Kara <jack@suse.com> Cc: Tejun Heo <tj@kernel.org> Cc: Kyle McMartin <kyle@kernel.org> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Calvin Owens <calvinowens@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 05:21:20 +08:00
/*
* We released the console_sem lock, so we need to recheck if
* cpu is online and (if not) is there at least one CON_ANYTIME
* console.
*/
if (!can_use_console()) {
console_locked = 0;
up_console_sem();
return;
}
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
for (;;) {
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
size_t ext_len = 0;
int handover;
size_t len;
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
skip:
if (!prb_read_valid(prb, console_seq, &r))
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
break;
if (console_seq != r.info->seq) {
console_dropped += r.info->seq - console_seq;
console_seq = r.info->seq;
if (panic_in_progress() && panic_console_dropped++ > 10) {
suppress_panic_printk = 1;
pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n");
}
}
if (suppress_message_printing(r.info->level)) {
/*
* Skip record we have buffered and already printed
* directly to the console when we received it, and
* record that has level above the console loglevel.
*/
console_seq++;
goto skip;
}
/* Output to all consoles once old messages replayed. */
if (unlikely(exclusive_console &&
console_seq >= exclusive_console_stop_seq)) {
exclusive_console = NULL;
}
/*
* Handle extended console text first because later
* record_print_text() will modify the record buffer in-place.
*/
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
if (nr_ext_console_drivers) {
ext_len = info_print_ext_header(ext_text,
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
sizeof(ext_text),
r.info);
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
ext_len += msg_print_ext_body(ext_text + ext_len,
sizeof(ext_text) - ext_len,
&r.text_buf[0],
r.info->text_len,
&r.info->dev_info);
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
}
len = record_print_text(&r,
console_msg_format & MSG_FORMAT_SYSLOG,
printk_time);
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
console_seq++;
printk: Add console owner and waiter logic to load balance console writes This patch implements what I discussed in Kernel Summit. I added lockdep annotation (hopefully correctly), and it hasn't had any splats (since I fixed some bugs in the first iterations). It did catch problems when I had the owner covering too much. But now that the owner is only set when actively calling the consoles, lockdep has stayed quiet. Here's the design again: I added a "console_owner" which is set to a task that is actively writing to the consoles. It is *not* the same as the owner of the console_lock. It is only set when doing the calls to the console functions. It is protected by a console_owner_lock which is a raw spin lock. There is a console_waiter. This is set when there is an active console owner that is not current, and waiter is not set. This too is protected by console_owner_lock. In printk() when it tries to write to the consoles, we have: if (console_trylock()) console_unlock(); Now I added an else, which will check if there is an active owner, and no current waiter. If that is the case, then console_waiter is set, and the task goes into a spin until it is no longer set. When the active console owner finishes writing the current message to the consoles, it grabs the console_owner_lock and sees if there is a waiter, and clears console_owner. If there is a waiter, then it breaks out of the loop, clears the waiter flag (because that will release the waiter from its spin), and exits. Note, it does *not* release the console semaphore. Because it is a semaphore, there is no owner. Another task may release it. This means that the waiter is guaranteed to be the new console owner! Which it becomes. Then the waiter calls console_unlock() and continues to write to the consoles. If another task comes along and does a printk() it too can become the new waiter, and we wash rinse and repeat! By Petr Mladek about possible new deadlocks: The thing is that we move console_sem only to printk() call that normally calls console_unlock() as well. It means that the transferred owner should not bring new type of dependencies. As Steven said somewhere: "If there is a deadlock, it was there even before." We could look at it from this side. The possible deadlock would look like: CPU0 CPU1 console_unlock() console_owner = current; spin_lockA() printk() spin = true; while (...) call_console_drivers() spin_lockA() This would be a deadlock. CPU0 would wait for the lock A. While CPU1 would own the lockA and would wait for CPU0 to finish calling the console drivers and pass the console_sem owner. But if the above is true than the following scenario was already possible before: CPU0 spin_lockA() printk() console_unlock() call_console_drivers() spin_lockA() By other words, this deadlock was there even before. Such deadlocks are prevented by using printk_deferred() in the sections guarded by the lock A. By Steven Rostedt: To demonstrate the issue, this module has been shown to lock up a system with 4 CPUs and a slow console (like a serial console). It is also able to lock up a 8 CPU system with only a fast (VGA) console, by passing in "loops=100". The changes in this commit prevent this module from locking up the system. #include <linux/module.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/mutex.h> #include <linux/workqueue.h> #include <linux/hrtimer.h> static bool stop_testing; static unsigned int loops = 1; static void preempt_printk_workfn(struct work_struct *work) { int i; while (!READ_ONCE(stop_testing)) { for (i = 0; i < loops && !READ_ONCE(stop_testing); i++) { preempt_disable(); pr_emerg("%5d%-75s\n", smp_processor_id(), " XXX NOPREEMPT"); preempt_enable(); } msleep(1); } } static struct work_struct __percpu *works; static void finish(void) { int cpu; WRITE_ONCE(stop_testing, true); for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); free_percpu(works); } static int __init test_init(void) { int cpu; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; /* * This is just a test module. This will break if you * do any CPU hot plugging between loading and * unloading the module. */ for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, &preempt_printk_workfn); schedule_work_on(cpu, work); } return 0; } static void __exit test_exit(void) { finish(); } module_param(loops, uint, 0); module_init(test_init); module_exit(test_exit); MODULE_LICENSE("GPL"); Link: http://lkml.kernel.org/r/20180110132418.7080-2-pmladek@suse.com Cc: akpm@linux-foundation.org Cc: linux-mm@kvack.org Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Tejun Heo <tj@kernel.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: linux-kernel@vger.kernel.org Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> [pmladek@suse.com: Commit message about possible deadlocks] Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-01-10 21:24:17 +08:00
/*
* While actively printing out messages, if another printk()
* were to occur on another CPU, it may wait for this one to
* finish. This task can not be preempted if there is a
* waiter waiting to take over.
*
* Interrupts are disabled because the hand over to a waiter
* must not be interrupted until the hand over is completed
* (@console_waiter is cleared).
printk: Add console owner and waiter logic to load balance console writes This patch implements what I discussed in Kernel Summit. I added lockdep annotation (hopefully correctly), and it hasn't had any splats (since I fixed some bugs in the first iterations). It did catch problems when I had the owner covering too much. But now that the owner is only set when actively calling the consoles, lockdep has stayed quiet. Here's the design again: I added a "console_owner" which is set to a task that is actively writing to the consoles. It is *not* the same as the owner of the console_lock. It is only set when doing the calls to the console functions. It is protected by a console_owner_lock which is a raw spin lock. There is a console_waiter. This is set when there is an active console owner that is not current, and waiter is not set. This too is protected by console_owner_lock. In printk() when it tries to write to the consoles, we have: if (console_trylock()) console_unlock(); Now I added an else, which will check if there is an active owner, and no current waiter. If that is the case, then console_waiter is set, and the task goes into a spin until it is no longer set. When the active console owner finishes writing the current message to the consoles, it grabs the console_owner_lock and sees if there is a waiter, and clears console_owner. If there is a waiter, then it breaks out of the loop, clears the waiter flag (because that will release the waiter from its spin), and exits. Note, it does *not* release the console semaphore. Because it is a semaphore, there is no owner. Another task may release it. This means that the waiter is guaranteed to be the new console owner! Which it becomes. Then the waiter calls console_unlock() and continues to write to the consoles. If another task comes along and does a printk() it too can become the new waiter, and we wash rinse and repeat! By Petr Mladek about possible new deadlocks: The thing is that we move console_sem only to printk() call that normally calls console_unlock() as well. It means that the transferred owner should not bring new type of dependencies. As Steven said somewhere: "If there is a deadlock, it was there even before." We could look at it from this side. The possible deadlock would look like: CPU0 CPU1 console_unlock() console_owner = current; spin_lockA() printk() spin = true; while (...) call_console_drivers() spin_lockA() This would be a deadlock. CPU0 would wait for the lock A. While CPU1 would own the lockA and would wait for CPU0 to finish calling the console drivers and pass the console_sem owner. But if the above is true than the following scenario was already possible before: CPU0 spin_lockA() printk() console_unlock() call_console_drivers() spin_lockA() By other words, this deadlock was there even before. Such deadlocks are prevented by using printk_deferred() in the sections guarded by the lock A. By Steven Rostedt: To demonstrate the issue, this module has been shown to lock up a system with 4 CPUs and a slow console (like a serial console). It is also able to lock up a 8 CPU system with only a fast (VGA) console, by passing in "loops=100". The changes in this commit prevent this module from locking up the system. #include <linux/module.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/mutex.h> #include <linux/workqueue.h> #include <linux/hrtimer.h> static bool stop_testing; static unsigned int loops = 1; static void preempt_printk_workfn(struct work_struct *work) { int i; while (!READ_ONCE(stop_testing)) { for (i = 0; i < loops && !READ_ONCE(stop_testing); i++) { preempt_disable(); pr_emerg("%5d%-75s\n", smp_processor_id(), " XXX NOPREEMPT"); preempt_enable(); } msleep(1); } } static struct work_struct __percpu *works; static void finish(void) { int cpu; WRITE_ONCE(stop_testing, true); for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); free_percpu(works); } static int __init test_init(void) { int cpu; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; /* * This is just a test module. This will break if you * do any CPU hot plugging between loading and * unloading the module. */ for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, &preempt_printk_workfn); schedule_work_on(cpu, work); } return 0; } static void __exit test_exit(void) { finish(); } module_param(loops, uint, 0); module_init(test_init); module_exit(test_exit); MODULE_LICENSE("GPL"); Link: http://lkml.kernel.org/r/20180110132418.7080-2-pmladek@suse.com Cc: akpm@linux-foundation.org Cc: linux-mm@kvack.org Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Tejun Heo <tj@kernel.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: linux-kernel@vger.kernel.org Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> [pmladek@suse.com: Commit message about possible deadlocks] Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-01-10 21:24:17 +08:00
*/
printk_safe_enter_irqsave(flags);
console_lock_spinning_enable();
printk: Add console owner and waiter logic to load balance console writes This patch implements what I discussed in Kernel Summit. I added lockdep annotation (hopefully correctly), and it hasn't had any splats (since I fixed some bugs in the first iterations). It did catch problems when I had the owner covering too much. But now that the owner is only set when actively calling the consoles, lockdep has stayed quiet. Here's the design again: I added a "console_owner" which is set to a task that is actively writing to the consoles. It is *not* the same as the owner of the console_lock. It is only set when doing the calls to the console functions. It is protected by a console_owner_lock which is a raw spin lock. There is a console_waiter. This is set when there is an active console owner that is not current, and waiter is not set. This too is protected by console_owner_lock. In printk() when it tries to write to the consoles, we have: if (console_trylock()) console_unlock(); Now I added an else, which will check if there is an active owner, and no current waiter. If that is the case, then console_waiter is set, and the task goes into a spin until it is no longer set. When the active console owner finishes writing the current message to the consoles, it grabs the console_owner_lock and sees if there is a waiter, and clears console_owner. If there is a waiter, then it breaks out of the loop, clears the waiter flag (because that will release the waiter from its spin), and exits. Note, it does *not* release the console semaphore. Because it is a semaphore, there is no owner. Another task may release it. This means that the waiter is guaranteed to be the new console owner! Which it becomes. Then the waiter calls console_unlock() and continues to write to the consoles. If another task comes along and does a printk() it too can become the new waiter, and we wash rinse and repeat! By Petr Mladek about possible new deadlocks: The thing is that we move console_sem only to printk() call that normally calls console_unlock() as well. It means that the transferred owner should not bring new type of dependencies. As Steven said somewhere: "If there is a deadlock, it was there even before." We could look at it from this side. The possible deadlock would look like: CPU0 CPU1 console_unlock() console_owner = current; spin_lockA() printk() spin = true; while (...) call_console_drivers() spin_lockA() This would be a deadlock. CPU0 would wait for the lock A. While CPU1 would own the lockA and would wait for CPU0 to finish calling the console drivers and pass the console_sem owner. But if the above is true than the following scenario was already possible before: CPU0 spin_lockA() printk() console_unlock() call_console_drivers() spin_lockA() By other words, this deadlock was there even before. Such deadlocks are prevented by using printk_deferred() in the sections guarded by the lock A. By Steven Rostedt: To demonstrate the issue, this module has been shown to lock up a system with 4 CPUs and a slow console (like a serial console). It is also able to lock up a 8 CPU system with only a fast (VGA) console, by passing in "loops=100". The changes in this commit prevent this module from locking up the system. #include <linux/module.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/mutex.h> #include <linux/workqueue.h> #include <linux/hrtimer.h> static bool stop_testing; static unsigned int loops = 1; static void preempt_printk_workfn(struct work_struct *work) { int i; while (!READ_ONCE(stop_testing)) { for (i = 0; i < loops && !READ_ONCE(stop_testing); i++) { preempt_disable(); pr_emerg("%5d%-75s\n", smp_processor_id(), " XXX NOPREEMPT"); preempt_enable(); } msleep(1); } } static struct work_struct __percpu *works; static void finish(void) { int cpu; WRITE_ONCE(stop_testing, true); for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); free_percpu(works); } static int __init test_init(void) { int cpu; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; /* * This is just a test module. This will break if you * do any CPU hot plugging between loading and * unloading the module. */ for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, &preempt_printk_workfn); schedule_work_on(cpu, work); } return 0; } static void __exit test_exit(void) { finish(); } module_param(loops, uint, 0); module_init(test_init); module_exit(test_exit); MODULE_LICENSE("GPL"); Link: http://lkml.kernel.org/r/20180110132418.7080-2-pmladek@suse.com Cc: akpm@linux-foundation.org Cc: linux-mm@kvack.org Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Tejun Heo <tj@kernel.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: linux-kernel@vger.kernel.org Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> [pmladek@suse.com: Commit message about possible deadlocks] Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-01-10 21:24:17 +08:00
ftrace: trace irq disabled critical timings This patch adds latency tracing for critical timings (how long interrupts are disabled for). "irqsoff" is added to /debugfs/tracing/available_tracers Note: tracing_max_latency also holds the max latency for irqsoff (in usecs). (default to large number so one must start latency tracing) tracing_thresh threshold (in usecs) to always print out if irqs off is detected to be longer than stated here. If irq_thresh is non-zero, then max_irq_latency is ignored. Here's an example of a trace with ftrace_enabled = 0 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 100 us, #3/3, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1d.s3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1d.s3 100us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1d.s3 100us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= And this is a trace with ftrace_enabled == 1 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 -------------------------------------------------------------------- latency: 102 us, #12/12, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1dNs3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_read_phy_reg+0x16/0x225 [e1000] (e1000_update_stats+0x5e2/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_swfw_sync_acquire+0x10/0x99 [e1000] (e1000_read_phy_reg+0x49/0x225 [e1000]) swapper-0 1dNs3 46us : e1000_get_hw_eeprom_semaphore+0x12/0xa6 [e1000] (e1000_swfw_sync_acquire+0x36/0x99 [e1000]) swapper-0 1dNs3 47us : __const_udelay+0x9/0x47 (e1000_read_phy_reg+0x116/0x225 [e1000]) swapper-0 1dNs3 47us+: __delay+0x9/0x50 (__const_udelay+0x45/0x47) swapper-0 1dNs3 97us : preempt_schedule+0xc/0x84 (__delay+0x4e/0x50) swapper-0 1dNs3 98us : e1000_swfw_sync_release+0xc/0x55 [e1000] (e1000_read_phy_reg+0x211/0x225 [e1000]) swapper-0 1dNs3 99us+: e1000_put_hw_eeprom_semaphore+0x9/0x35 [e1000] (e1000_swfw_sync_release+0x50/0x55 [e1000]) swapper-0 1dNs3 101us : _spin_unlock_irqrestore+0xe/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
stop_critical_timings(); /* don't trace print latency */
call_console_drivers(ext_text, ext_len, text, len);
ftrace: trace irq disabled critical timings This patch adds latency tracing for critical timings (how long interrupts are disabled for). "irqsoff" is added to /debugfs/tracing/available_tracers Note: tracing_max_latency also holds the max latency for irqsoff (in usecs). (default to large number so one must start latency tracing) tracing_thresh threshold (in usecs) to always print out if irqs off is detected to be longer than stated here. If irq_thresh is non-zero, then max_irq_latency is ignored. Here's an example of a trace with ftrace_enabled = 0 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 100 us, #3/3, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1d.s3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1d.s3 100us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1d.s3 100us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= And this is a trace with ftrace_enabled == 1 ======= preemption latency trace v1.1.5 on 2.6.24-rc7 -------------------------------------------------------------------- latency: 102 us, #12/12, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0) ----------------- => started at: _spin_lock_irqsave+0x2a/0xb7 => ended at: _spin_unlock_irqrestore+0x32/0x5f _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / swapper-0 1dNs3 0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_read_phy_reg+0x16/0x225 [e1000] (e1000_update_stats+0x5e2/0x64c [e1000]) swapper-0 1dNs3 46us : e1000_swfw_sync_acquire+0x10/0x99 [e1000] (e1000_read_phy_reg+0x49/0x225 [e1000]) swapper-0 1dNs3 46us : e1000_get_hw_eeprom_semaphore+0x12/0xa6 [e1000] (e1000_swfw_sync_acquire+0x36/0x99 [e1000]) swapper-0 1dNs3 47us : __const_udelay+0x9/0x47 (e1000_read_phy_reg+0x116/0x225 [e1000]) swapper-0 1dNs3 47us+: __delay+0x9/0x50 (__const_udelay+0x45/0x47) swapper-0 1dNs3 97us : preempt_schedule+0xc/0x84 (__delay+0x4e/0x50) swapper-0 1dNs3 98us : e1000_swfw_sync_release+0xc/0x55 [e1000] (e1000_read_phy_reg+0x211/0x225 [e1000]) swapper-0 1dNs3 99us+: e1000_put_hw_eeprom_semaphore+0x9/0x35 [e1000] (e1000_swfw_sync_release+0x50/0x55 [e1000]) swapper-0 1dNs3 101us : _spin_unlock_irqrestore+0xe/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000]) swapper-0 1dNs3 102us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f) vim:ft=help ======= Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 03:20:42 +08:00
start_critical_timings();
printk: Add console owner and waiter logic to load balance console writes This patch implements what I discussed in Kernel Summit. I added lockdep annotation (hopefully correctly), and it hasn't had any splats (since I fixed some bugs in the first iterations). It did catch problems when I had the owner covering too much. But now that the owner is only set when actively calling the consoles, lockdep has stayed quiet. Here's the design again: I added a "console_owner" which is set to a task that is actively writing to the consoles. It is *not* the same as the owner of the console_lock. It is only set when doing the calls to the console functions. It is protected by a console_owner_lock which is a raw spin lock. There is a console_waiter. This is set when there is an active console owner that is not current, and waiter is not set. This too is protected by console_owner_lock. In printk() when it tries to write to the consoles, we have: if (console_trylock()) console_unlock(); Now I added an else, which will check if there is an active owner, and no current waiter. If that is the case, then console_waiter is set, and the task goes into a spin until it is no longer set. When the active console owner finishes writing the current message to the consoles, it grabs the console_owner_lock and sees if there is a waiter, and clears console_owner. If there is a waiter, then it breaks out of the loop, clears the waiter flag (because that will release the waiter from its spin), and exits. Note, it does *not* release the console semaphore. Because it is a semaphore, there is no owner. Another task may release it. This means that the waiter is guaranteed to be the new console owner! Which it becomes. Then the waiter calls console_unlock() and continues to write to the consoles. If another task comes along and does a printk() it too can become the new waiter, and we wash rinse and repeat! By Petr Mladek about possible new deadlocks: The thing is that we move console_sem only to printk() call that normally calls console_unlock() as well. It means that the transferred owner should not bring new type of dependencies. As Steven said somewhere: "If there is a deadlock, it was there even before." We could look at it from this side. The possible deadlock would look like: CPU0 CPU1 console_unlock() console_owner = current; spin_lockA() printk() spin = true; while (...) call_console_drivers() spin_lockA() This would be a deadlock. CPU0 would wait for the lock A. While CPU1 would own the lockA and would wait for CPU0 to finish calling the console drivers and pass the console_sem owner. But if the above is true than the following scenario was already possible before: CPU0 spin_lockA() printk() console_unlock() call_console_drivers() spin_lockA() By other words, this deadlock was there even before. Such deadlocks are prevented by using printk_deferred() in the sections guarded by the lock A. By Steven Rostedt: To demonstrate the issue, this module has been shown to lock up a system with 4 CPUs and a slow console (like a serial console). It is also able to lock up a 8 CPU system with only a fast (VGA) console, by passing in "loops=100". The changes in this commit prevent this module from locking up the system. #include <linux/module.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/mutex.h> #include <linux/workqueue.h> #include <linux/hrtimer.h> static bool stop_testing; static unsigned int loops = 1; static void preempt_printk_workfn(struct work_struct *work) { int i; while (!READ_ONCE(stop_testing)) { for (i = 0; i < loops && !READ_ONCE(stop_testing); i++) { preempt_disable(); pr_emerg("%5d%-75s\n", smp_processor_id(), " XXX NOPREEMPT"); preempt_enable(); } msleep(1); } } static struct work_struct __percpu *works; static void finish(void) { int cpu; WRITE_ONCE(stop_testing, true); for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); free_percpu(works); } static int __init test_init(void) { int cpu; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; /* * This is just a test module. This will break if you * do any CPU hot plugging between loading and * unloading the module. */ for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, &preempt_printk_workfn); schedule_work_on(cpu, work); } return 0; } static void __exit test_exit(void) { finish(); } module_param(loops, uint, 0); module_init(test_init); module_exit(test_exit); MODULE_LICENSE("GPL"); Link: http://lkml.kernel.org/r/20180110132418.7080-2-pmladek@suse.com Cc: akpm@linux-foundation.org Cc: linux-mm@kvack.org Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Tejun Heo <tj@kernel.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: linux-kernel@vger.kernel.org Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> [pmladek@suse.com: Commit message about possible deadlocks] Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-01-10 21:24:17 +08:00
handover = console_lock_spinning_disable_and_check();
printk: use printk_safe buffers in printk Use printk_safe per-CPU buffers in printk recursion-prone blocks: -- around logbuf_lock protected sections in vprintk_emit() and console_unlock() -- around down_trylock_console_sem() and up_console_sem() Note that this solution addresses deadlocks caused by printk() recursive calls only. That is vprintk_emit() and console_unlock(). The rest will be converted in a followup patch. Another thing to note is that we now keep lockdep enabled in printk, because we are protected against the printk recursion caused by lockdep in vprintk_emit() by the printk-safe mechanism - we first switch to per-CPU buffers and only then access the deadlock-prone locks. Examples: 1) printk() from logbuf_lock spin_lock section Assume the following code: printk() raw_spin_lock(&logbuf_lock); WARN_ON(1); raw_spin_unlock(&logbuf_lock); which now produces: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 366 at kernel/printk/printk.c:1811 vprintk_emit CPU: 0 PID: 366 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f vprintk_emit+0x1cd/0x438 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 2) printk() from semaphore sem->lock spin_lock section Assume the following code printk() console_trylock() down_trylock() raw_spin_lock_irqsave(&sem->lock, flags); WARN_ON(1); raw_spin_unlock_irqrestore(&sem->lock, flags); which now produces: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 363 at kernel/locking/semaphore.c:141 down_trylock CPU: 1 PID: 363 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f down_trylock+0x3d/0x62 ? vprintk_emit+0x3f9/0x414 console_trylock+0x31/0xeb vprintk_emit+0x3f9/0x414 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 3) printk() from console_unlock() Assume the following code: printk() console_unlock() raw_spin_lock(&logbuf_lock); WARN_ON(1); raw_spin_unlock(&logbuf_lock); which now produces: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 329 at kernel/printk/printk.c:2384 console_unlock CPU: 1 PID: 329 Comm: bash Call Trace: warn_slowpath_null+0x18/0x1a console_unlock+0x12d/0x559 ? trace_hardirqs_on_caller+0x16d/0x189 ? trace_hardirqs_on+0xd/0xf vprintk_emit+0x363/0x374 vprintk_default+0x18/0x1a printk+0x43/0x4b [..] 4) printk() from try_to_wake_up() Assume the following code: printk() console_unlock() up() try_to_wake_up() raw_spin_lock_irqsave(&p->pi_lock, flags); WARN_ON(1); raw_spin_unlock_irqrestore(&p->pi_lock, flags); which now produces: ------------[ cut here ]------------ WARNING: CPU: 3 PID: 363 at kernel/sched/core.c:2028 try_to_wake_up CPU: 3 PID: 363 Comm: bash Call Trace: warn_slowpath_null+0x1d/0x1f try_to_wake_up+0x7f/0x4f7 wake_up_process+0x15/0x17 __up.isra.0+0x56/0x63 up+0x32/0x42 __up_console_sem+0x37/0x55 console_unlock+0x21e/0x4c2 vprintk_emit+0x41c/0x462 vprintk_default+0x1d/0x1f printk+0x48/0x50 [..] 5) printk() from call_console_drivers() Assume the following code: printk() console_unlock() call_console_drivers() ... WARN_ON(1); which now produces: ------------[ cut here ]------------ WARNING: CPU: 2 PID: 305 at kernel/printk/printk.c:1604 call_console_drivers CPU: 2 PID: 305 Comm: bash Call Trace: warn_slowpath_null+0x18/0x1a call_console_drivers.isra.6.constprop.16+0x3a/0xb0 console_unlock+0x471/0x48e vprintk_emit+0x1f4/0x206 vprintk_default+0x18/0x1a vprintk_func+0x6e/0x70 printk+0x3e/0x46 [..] 6) unsupported placeholder in printk() format now prints an actual warning from vscnprintf(), instead of 'BUG: recent printk recursion!'. ------------[ cut here ]------------ WARNING: CPU: 5 PID: 337 at lib/vsprintf.c:1900 format_decode Please remove unsupported % in format string CPU: 5 PID: 337 Comm: bash Call Trace: dump_stack+0x4f/0x65 __warn+0xc2/0xdd warn_slowpath_fmt+0x4b/0x53 format_decode+0x22c/0x308 vsnprintf+0x89/0x3b7 vscnprintf+0xd/0x26 vprintk_emit+0xb4/0x238 vprintk_default+0x1d/0x1f vprintk_func+0x6c/0x73 printk+0x43/0x4b [..] Link: http://lkml.kernel.org/r/20161227141611.940-7-sergey.senozhatsky@gmail.com Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Calvin Owens <calvinowens@fb.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: linux-kernel@vger.kernel.org Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2016-12-27 22:16:09 +08:00
printk_safe_exit_irqrestore(flags);
if (handover)
return;
printk: do cond_resched() between lines while outputting to consoles @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Calvin Owens <calvinowens@fb.com> Acked-by: Jan Kara <jack@suse.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Kyle McMartin <kyle@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:58:24 +08:00
/* Allow panic_cpu to take over the consoles safely */
if (abandon_console_lock_in_panic())
break;
printk: do cond_resched() between lines while outputting to consoles @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Calvin Owens <calvinowens@fb.com> Acked-by: Jan Kara <jack@suse.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Kyle McMartin <kyle@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:58:24 +08:00
if (do_cond_resched)
cond_resched();
}
printk: Add console owner and waiter logic to load balance console writes This patch implements what I discussed in Kernel Summit. I added lockdep annotation (hopefully correctly), and it hasn't had any splats (since I fixed some bugs in the first iterations). It did catch problems when I had the owner covering too much. But now that the owner is only set when actively calling the consoles, lockdep has stayed quiet. Here's the design again: I added a "console_owner" which is set to a task that is actively writing to the consoles. It is *not* the same as the owner of the console_lock. It is only set when doing the calls to the console functions. It is protected by a console_owner_lock which is a raw spin lock. There is a console_waiter. This is set when there is an active console owner that is not current, and waiter is not set. This too is protected by console_owner_lock. In printk() when it tries to write to the consoles, we have: if (console_trylock()) console_unlock(); Now I added an else, which will check if there is an active owner, and no current waiter. If that is the case, then console_waiter is set, and the task goes into a spin until it is no longer set. When the active console owner finishes writing the current message to the consoles, it grabs the console_owner_lock and sees if there is a waiter, and clears console_owner. If there is a waiter, then it breaks out of the loop, clears the waiter flag (because that will release the waiter from its spin), and exits. Note, it does *not* release the console semaphore. Because it is a semaphore, there is no owner. Another task may release it. This means that the waiter is guaranteed to be the new console owner! Which it becomes. Then the waiter calls console_unlock() and continues to write to the consoles. If another task comes along and does a printk() it too can become the new waiter, and we wash rinse and repeat! By Petr Mladek about possible new deadlocks: The thing is that we move console_sem only to printk() call that normally calls console_unlock() as well. It means that the transferred owner should not bring new type of dependencies. As Steven said somewhere: "If there is a deadlock, it was there even before." We could look at it from this side. The possible deadlock would look like: CPU0 CPU1 console_unlock() console_owner = current; spin_lockA() printk() spin = true; while (...) call_console_drivers() spin_lockA() This would be a deadlock. CPU0 would wait for the lock A. While CPU1 would own the lockA and would wait for CPU0 to finish calling the console drivers and pass the console_sem owner. But if the above is true than the following scenario was already possible before: CPU0 spin_lockA() printk() console_unlock() call_console_drivers() spin_lockA() By other words, this deadlock was there even before. Such deadlocks are prevented by using printk_deferred() in the sections guarded by the lock A. By Steven Rostedt: To demonstrate the issue, this module has been shown to lock up a system with 4 CPUs and a slow console (like a serial console). It is also able to lock up a 8 CPU system with only a fast (VGA) console, by passing in "loops=100". The changes in this commit prevent this module from locking up the system. #include <linux/module.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/mutex.h> #include <linux/workqueue.h> #include <linux/hrtimer.h> static bool stop_testing; static unsigned int loops = 1; static void preempt_printk_workfn(struct work_struct *work) { int i; while (!READ_ONCE(stop_testing)) { for (i = 0; i < loops && !READ_ONCE(stop_testing); i++) { preempt_disable(); pr_emerg("%5d%-75s\n", smp_processor_id(), " XXX NOPREEMPT"); preempt_enable(); } msleep(1); } } static struct work_struct __percpu *works; static void finish(void) { int cpu; WRITE_ONCE(stop_testing, true); for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); free_percpu(works); } static int __init test_init(void) { int cpu; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; /* * This is just a test module. This will break if you * do any CPU hot plugging between loading and * unloading the module. */ for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, &preempt_printk_workfn); schedule_work_on(cpu, work); } return 0; } static void __exit test_exit(void) { finish(); } module_param(loops, uint, 0); module_init(test_init); module_exit(test_exit); MODULE_LICENSE("GPL"); Link: http://lkml.kernel.org/r/20180110132418.7080-2-pmladek@suse.com Cc: akpm@linux-foundation.org Cc: linux-mm@kvack.org Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Jan Kara <jack@suse.cz> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Tejun Heo <tj@kernel.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: linux-kernel@vger.kernel.org Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> [pmladek@suse.com: Commit message about possible deadlocks] Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-01-10 21:24:17 +08:00
printk/console: Check consistent sequence number when handling race in console_unlock() The standard printk() tries to flush the message to the console immediately. It tries to take the console lock. If the lock is already taken then the current owner is responsible for flushing even the new message. There is a small race window between checking whether a new message is available and releasing the console lock. It is solved by re-checking the state after releasing the console lock. If the check is positive then console_unlock() tries to take the lock again and process the new message as well. The commit 996e966640ddea7b535c ("printk: remove logbuf_lock") causes that console_seq is not longer read atomically. As a result, the re-check might be done with an inconsistent 64-bit index. Solve it by using the last sequence number that has been checked under the console lock. In the worst case, it will take the lock again only to realized that the new message has already been proceed. But it was possible even before. The variable next_seq is marked as __maybe_unused to call down compiler warning when CONFIG_PRINTK is not defined. Fixes: commit 996e966640ddea7b535c ("printk: remove logbuf_lock") Reported-by: kernel test robot <lkp@intel.com> # unused next_seq warning Cc: stable@vger.kernel.org # 5.13 Signed-off-by: Petr Mladek <pmladek@suse.com> Acked-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: John Ogness <john.ogness@linutronix.de> Link: https://lore.kernel.org/r/20210702150657.26760-1-pmladek@suse.com
2021-07-02 23:06:57 +08:00
/* Get consistent value of the next-to-be-used sequence number. */
next_seq = console_seq;
printk/console: Check consistent sequence number when handling race in console_unlock() The standard printk() tries to flush the message to the console immediately. It tries to take the console lock. If the lock is already taken then the current owner is responsible for flushing even the new message. There is a small race window between checking whether a new message is available and releasing the console lock. It is solved by re-checking the state after releasing the console lock. If the check is positive then console_unlock() tries to take the lock again and process the new message as well. The commit 996e966640ddea7b535c ("printk: remove logbuf_lock") causes that console_seq is not longer read atomically. As a result, the re-check might be done with an inconsistent 64-bit index. Solve it by using the last sequence number that has been checked under the console lock. In the worst case, it will take the lock again only to realized that the new message has already been proceed. But it was possible even before. The variable next_seq is marked as __maybe_unused to call down compiler warning when CONFIG_PRINTK is not defined. Fixes: commit 996e966640ddea7b535c ("printk: remove logbuf_lock") Reported-by: kernel test robot <lkp@intel.com> # unused next_seq warning Cc: stable@vger.kernel.org # 5.13 Signed-off-by: Petr Mladek <pmladek@suse.com> Acked-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: John Ogness <john.ogness@linutronix.de> Link: https://lore.kernel.org/r/20210702150657.26760-1-pmladek@suse.com
2021-07-02 23:06:57 +08:00
console_locked = 0;
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.
*/
printk/console: Check consistent sequence number when handling race in console_unlock() The standard printk() tries to flush the message to the console immediately. It tries to take the console lock. If the lock is already taken then the current owner is responsible for flushing even the new message. There is a small race window between checking whether a new message is available and releasing the console lock. It is solved by re-checking the state after releasing the console lock. If the check is positive then console_unlock() tries to take the lock again and process the new message as well. The commit 996e966640ddea7b535c ("printk: remove logbuf_lock") causes that console_seq is not longer read atomically. As a result, the re-check might be done with an inconsistent 64-bit index. Solve it by using the last sequence number that has been checked under the console lock. In the worst case, it will take the lock again only to realized that the new message has already been proceed. But it was possible even before. The variable next_seq is marked as __maybe_unused to call down compiler warning when CONFIG_PRINTK is not defined. Fixes: commit 996e966640ddea7b535c ("printk: remove logbuf_lock") Reported-by: kernel test robot <lkp@intel.com> # unused next_seq warning Cc: stable@vger.kernel.org # 5.13 Signed-off-by: Petr Mladek <pmladek@suse.com> Acked-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: John Ogness <john.ogness@linutronix.de> Link: https://lore.kernel.org/r/20210702150657.26760-1-pmladek@suse.com
2021-07-02 23:06:57 +08:00
retry = prb_read_valid(prb, next_seq, NULL);
if (retry && !abandon_console_lock_in_panic() && console_trylock())
goto again;
}
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;
printk: Enable the use of more than one CON_BOOT (early console) Today, register_console() assumes the following usage: - The first console to register with a flag set to CON_BOOT is the one and only bootconsole. - If another register_console() is called with an additional CON_BOOT, it is silently rejected. - As soon as a console without the CON_BOOT set calls registers the bootconsole is automatically unregistered. - Once there is a "real" console - register_console() will silently reject any consoles with it's CON_BOOT flag set. In many systems (alpha, blackfin, microblaze, mips, powerpc, sh, & x86), there are early_printk implementations, which use the CON_BOOT which come out serial ports, vga, usb, & memory buffers. In many embedded systems, it would be nice to have two bootconsoles - in case the primary fails, you always have access to a backup memory buffer - but this requires at least two CON_BOOT consoles... This patch enables that functionality. With the change applied, on boot you get (if you try to re-enable a boot console after the "real" console has been registered): root:/> dmesg | grep console bootconsole [early_shadow0] enabled bootconsole [early_BFuart0] enabled Kernel command line: root=/dev/mtdblock0 rw earlyprintk=serial,uart0,57600 console=ttyBF0,57600 nmi_debug=regs console handover:boot [early_BFuart0] boot [early_shadow0] -> real [ttyBF0] Too late to register bootconsole early_shadow0 or: root:/> dmesg | grep console Kernel command line: root=/dev/mtdblock0 rw console=ttyBF0,57600 console [ttyBF0] enabled Signed-off-by: Robin Getz <rgetz@blackfin.uclinux.org> Cc: "Linus Torvalds" <torvalds@linux-foundation.org> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Mike Frysinger" <vapier.adi@gmail.com> Cc: "Paul Mundt" <lethal@linux-sh.org> LKML-Reference: <200907012108.38030.rgetz@blackfin.uclinux.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 09:08:37 +08:00
for_each_console(c)
if ((c->flags & CON_ENABLED) && c->unblank)
c->unblank();
console_unlock();
}
printk: do cond_resched() between lines while outputting to consoles @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Calvin Owens <calvinowens@fb.com> Acked-by: Jan Kara <jack@suse.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Kyle McMartin <kyle@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:58:24 +08:00
/**
* console_flush_on_panic - flush console content on panic
* @mode: flush all messages in buffer or just the pending ones
printk: do cond_resched() between lines while outputting to consoles @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Calvin Owens <calvinowens@fb.com> Acked-by: Jan Kara <jack@suse.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Kyle McMartin <kyle@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:58:24 +08:00
*
* Immediately output all pending messages no matter what.
*/
void console_flush_on_panic(enum con_flush_mode mode)
printk: do cond_resched() between lines while outputting to consoles @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Calvin Owens <calvinowens@fb.com> Acked-by: Jan Kara <jack@suse.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Kyle McMartin <kyle@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:58:24 +08:00
{
/*
* If someone else is holding the console lock, trylock will fail
* and may_schedule may be set. Ignore and proceed to unlock so
* that messages are flushed out. As this can be called from any
* context and we don't want to get preempted while flushing,
* ensure may_schedule is cleared.
*/
console_trylock();
console_may_schedule = 0;
if (mode == CONSOLE_REPLAY_ALL)
console_seq = prb_first_valid_seq(prb);
printk: do cond_resched() between lines while outputting to consoles @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Calvin Owens <calvinowens@fb.com> Acked-by: Jan Kara <jack@suse.com> Cc: Dave Jones <davej@codemonkey.org.uk> Cc: Kyle McMartin <kyle@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:58:24 +08:00
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();
printk: Enable the use of more than one CON_BOOT (early console) Today, register_console() assumes the following usage: - The first console to register with a flag set to CON_BOOT is the one and only bootconsole. - If another register_console() is called with an additional CON_BOOT, it is silently rejected. - As soon as a console without the CON_BOOT set calls registers the bootconsole is automatically unregistered. - Once there is a "real" console - register_console() will silently reject any consoles with it's CON_BOOT flag set. In many systems (alpha, blackfin, microblaze, mips, powerpc, sh, & x86), there are early_printk implementations, which use the CON_BOOT which come out serial ports, vga, usb, & memory buffers. In many embedded systems, it would be nice to have two bootconsoles - in case the primary fails, you always have access to a backup memory buffer - but this requires at least two CON_BOOT consoles... This patch enables that functionality. With the change applied, on boot you get (if you try to re-enable a boot console after the "real" console has been registered): root:/> dmesg | grep console bootconsole [early_shadow0] enabled bootconsole [early_BFuart0] enabled Kernel command line: root=/dev/mtdblock0 rw earlyprintk=serial,uart0,57600 console=ttyBF0,57600 nmi_debug=regs console handover:boot [early_BFuart0] boot [early_shadow0] -> real [ttyBF0] Too late to register bootconsole early_shadow0 or: root:/> dmesg | grep console Kernel command line: root=/dev/mtdblock0 rw console=ttyBF0,57600 console [ttyBF0] enabled Signed-off-by: Robin Getz <rgetz@blackfin.uclinux.org> Cc: "Linus Torvalds" <torvalds@linux-foundation.org> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Mike Frysinger" <vapier.adi@gmail.com> Cc: "Paul Mundt" <lethal@linux-sh.org> LKML-Reference: <200907012108.38030.rgetz@blackfin.uclinux.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 09:08:37 +08:00
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;
pr_info("debug: skip boot console de-registration.\n");
return 0;
}
early_param("keep_bootcon", keep_bootcon_setup);
/*
* This is called by register_console() to try to match
* the newly registered console with any of the ones selected
* by either the command line or add_preferred_console() and
* setup/enable it.
*
* Care need to be taken with consoles that are statically
* enabled such as netconsole
*/
static int try_enable_preferred_console(struct console *newcon,
bool user_specified)
{
struct console_cmdline *c;
int i, err;
for (i = 0, c = console_cmdline;
i < MAX_CMDLINECONSOLES && c->name[0];
i++, c++) {
printk: Fix preferred console selection with multiple matches In the following circumstances, the rule of selecting the console corresponding to the last "console=" entry on the command line as the preferred console (CON_CONSDEV, ie, /dev/console) fails. This is a specific example, but it could happen with different consoles that have a similar name aliasing mechanism. - The kernel command line has both console=tty0 and console=ttyS0 in that order (the latter with speed etc... arguments). This is common with some cloud setups such as Amazon Linux. - add_preferred_console is called early to register "uart0". In our case that happens from acpi_parse_spcr() on arm64 since the "enable_console" argument is true on that architecture. This causes "uart0" to become entry 0 of the console_cmdline array. Now, because of the above, what happens is: - add_preferred_console is called by the cmdline parsing for tty0 and ttyS0 respectively, thus occupying entries 1 and 2 of the console_cmdline array (since this happens after ACPI SPCR parsing). At that point preferred_console is set to 2 as expected. - When the tty layer kicks in, it will call register_console for tty0. This will match entry 1 in console_cmdline array. It isn't our preferred console but because it's our only console at this point, it will end up "first" in the consoles list. - When 8250 probes the actual serial port later on, it calls register_console for ttyS0. At that point the loop in register_console tries to match it with the entries in the console_cmdline array. Ideally this should match ttyS0 in entry 2, which is preferred, causing it to be inserted first and to replace tty0 as CONSDEV. However, 8250 provides a "match" hook in its struct console, and that hook will match "uart" as an alias to "ttyS". So we match uart0 at entry 0 in the array which is not the preferred console and will not match entry 2 which is since we break out of the loop on the first match. As a result, we don't set CONSDEV and don't insert it first, but second in the console list. As a result, we end up with tty0 remaining first in the array, and thus /dev/console going there instead of the last user specified one which is ttyS0. This tentative fix register_console() to scan first for consoles specified on the command line, and only if none is found, to then scan for consoles specified by the architecture. Link: https://lore.kernel.org/r/20200213095133.23176-3-pmladek@suse.com Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2020-02-13 17:51:32 +08:00
if (c->user_specified != user_specified)
continue;
if (!newcon->match ||
newcon->match(newcon, c->name, c->index, c->options) != 0) {
/* default matching */
BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
if (strcmp(c->name, newcon->name) != 0)
continue;
if (newcon->index >= 0 &&
newcon->index != c->index)
continue;
if (newcon->index < 0)
newcon->index = c->index;
if (_braille_register_console(newcon, c))
return 0;
if (newcon->setup &&
(err = newcon->setup(newcon, c->options)) != 0)
return err;
}
newcon->flags |= CON_ENABLED;
if (i == preferred_console)
newcon->flags |= CON_CONSDEV;
return 0;
}
/*
* Some consoles, such as pstore and netconsole, can be enabled even
printk: Fix preferred console selection with multiple matches In the following circumstances, the rule of selecting the console corresponding to the last "console=" entry on the command line as the preferred console (CON_CONSDEV, ie, /dev/console) fails. This is a specific example, but it could happen with different consoles that have a similar name aliasing mechanism. - The kernel command line has both console=tty0 and console=ttyS0 in that order (the latter with speed etc... arguments). This is common with some cloud setups such as Amazon Linux. - add_preferred_console is called early to register "uart0". In our case that happens from acpi_parse_spcr() on arm64 since the "enable_console" argument is true on that architecture. This causes "uart0" to become entry 0 of the console_cmdline array. Now, because of the above, what happens is: - add_preferred_console is called by the cmdline parsing for tty0 and ttyS0 respectively, thus occupying entries 1 and 2 of the console_cmdline array (since this happens after ACPI SPCR parsing). At that point preferred_console is set to 2 as expected. - When the tty layer kicks in, it will call register_console for tty0. This will match entry 1 in console_cmdline array. It isn't our preferred console but because it's our only console at this point, it will end up "first" in the consoles list. - When 8250 probes the actual serial port later on, it calls register_console for ttyS0. At that point the loop in register_console tries to match it with the entries in the console_cmdline array. Ideally this should match ttyS0 in entry 2, which is preferred, causing it to be inserted first and to replace tty0 as CONSDEV. However, 8250 provides a "match" hook in its struct console, and that hook will match "uart" as an alias to "ttyS". So we match uart0 at entry 0 in the array which is not the preferred console and will not match entry 2 which is since we break out of the loop on the first match. As a result, we don't set CONSDEV and don't insert it first, but second in the console list. As a result, we end up with tty0 remaining first in the array, and thus /dev/console going there instead of the last user specified one which is ttyS0. This tentative fix register_console() to scan first for consoles specified on the command line, and only if none is found, to then scan for consoles specified by the architecture. Link: https://lore.kernel.org/r/20200213095133.23176-3-pmladek@suse.com Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2020-02-13 17:51:32 +08:00
* without matching. Accept the pre-enabled consoles only when match()
* and setup() had a chance to be called.
*/
printk: Fix preferred console selection with multiple matches In the following circumstances, the rule of selecting the console corresponding to the last "console=" entry on the command line as the preferred console (CON_CONSDEV, ie, /dev/console) fails. This is a specific example, but it could happen with different consoles that have a similar name aliasing mechanism. - The kernel command line has both console=tty0 and console=ttyS0 in that order (the latter with speed etc... arguments). This is common with some cloud setups such as Amazon Linux. - add_preferred_console is called early to register "uart0". In our case that happens from acpi_parse_spcr() on arm64 since the "enable_console" argument is true on that architecture. This causes "uart0" to become entry 0 of the console_cmdline array. Now, because of the above, what happens is: - add_preferred_console is called by the cmdline parsing for tty0 and ttyS0 respectively, thus occupying entries 1 and 2 of the console_cmdline array (since this happens after ACPI SPCR parsing). At that point preferred_console is set to 2 as expected. - When the tty layer kicks in, it will call register_console for tty0. This will match entry 1 in console_cmdline array. It isn't our preferred console but because it's our only console at this point, it will end up "first" in the consoles list. - When 8250 probes the actual serial port later on, it calls register_console for ttyS0. At that point the loop in register_console tries to match it with the entries in the console_cmdline array. Ideally this should match ttyS0 in entry 2, which is preferred, causing it to be inserted first and to replace tty0 as CONSDEV. However, 8250 provides a "match" hook in its struct console, and that hook will match "uart" as an alias to "ttyS". So we match uart0 at entry 0 in the array which is not the preferred console and will not match entry 2 which is since we break out of the loop on the first match. As a result, we don't set CONSDEV and don't insert it first, but second in the console list. As a result, we end up with tty0 remaining first in the array, and thus /dev/console going there instead of the last user specified one which is ttyS0. This tentative fix register_console() to scan first for consoles specified on the command line, and only if none is found, to then scan for consoles specified by the architecture. Link: https://lore.kernel.org/r/20200213095133.23176-3-pmladek@suse.com Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2020-02-13 17:51:32 +08:00
if (newcon->flags & CON_ENABLED && c->user_specified == user_specified)
return 0;
return -ENOENT;
}
/* Try to enable the console unconditionally */
static void try_enable_default_console(struct console *newcon)
{
if (newcon->index < 0)
newcon->index = 0;
if (newcon->setup && newcon->setup(newcon, NULL) != 0)
return;
newcon->flags |= CON_ENABLED;
printk/console: Remove need_default_console variable The variable @need_default_console is used to decide whether a newly registered console should get enabled by default. The logic is complicated. It can be modified in a register_console() call. But it is always re-evaluated in the next call by the following condition: if (need_default_console || bcon || !console_drivers) need_default_console = preferred_console < 0; In short, the value is updated when either of the condition is valid: + the value is still, or again, "true" + boot/early console is still the first in @console_driver list + @console_driver list is empty The value is updated according to @preferred_console. In particular, it is set to "false" when a @preferred_console was set by __add_preferred_console(). This happens when a non-braille console was added via the command line, device tree, or SPCR. It far from clear what this all means together. Let's look at @need_default_console from another angle: 1. The value is "true" by default. It means that it is always set according to @preferred_console during the first register_console() call. By other words, the first register_console() call will register the console by default only when none non-braille console was defined via the command line, device tree, or SPCR. 2. The value will always stay "false" when @preferred_console is set. By other words, try_enable_default_console() will never get called when a non-braille console is explicitly required. 4. The value might be set to "false" in try_enable_default_console() when a console with tty binding (driver) gets enabled. In this case CON_CONSDEV is set as well. It causes that the console will be inserted as first into the list @console_driver. It might be either real or boot/early console. 5. The value will be set _back_ to "true" in the next register_console() call when: + The console added by the previous register_console() had been a boot/early one. + The last console has been unregistered in the meantime and a boot/early console became first in @console_drivers list again. Or the list became empty. By other words, the value will stay "false" only when the last registered console was real, had tty binding, and was not removed in the mean time. The main logic looks clear: + Consoles are enabled by default only when no one is preferred via the command line, device tree, or SPCR. + By default, any console is enabled until a real console with tty binding gets registered. The behavior when the real console with tty binding is later removed is a bit unclear: + By default, any new console is registered again only when there is no console or the first console in the list is a boot one. The question is why the code is suddenly happy when a real console without tty binding is the first in the list. It looks like an overlook and bug. Conclusion: The state of @preferred_console and the first console in @console_driver list should be enough to decide whether we need to enable the given console by default. The rules are simple. New consoles are _not_ enabled by default when either of the following conditions is true: + @preferred_console is set. It means that a non-braille console is explicitly configured via the command line, device tree, or SPCR. + A real console with tty binding is registered. Such a console will have CON_CONSDEV flag set and will always be the first in @console_drivers list. Note: The new code does not use @bcon variable. The meaning of the variable is far from clear. The direct check of the first console in the list makes it more clear that only real console fulfills requirements of the default console. Behavior change: As already discussed above. There was one situation where the original code worked a strange way. Let's have: + console A: real console without tty binding + console B: real console with tty binding and do: register_console(A); /* 1st step */ register_console(B); /* 2nd step */ unregister_console(B); /* 3rd step */ register_console(B); /* 4th step */ The original code will not register the console B in the 4th step. @need_default_console is set to "false" in 2nd step. The real console with tty binding (driver) is then removed in the 3rd step. But @need_default_console will stay "false" in the 4th step because there is no boot/early console and @registered_consoles list is not empty. The new code will register the console B in the 4th step because it checks whether the first console has tty binding (->driver) This behavior change should acceptable: 1. The scenario requires manual intervention (console removal). The system should boot with the same consoles as before. 2. Console B is registered again probably because the user wants to use it. The most likely scenario is that the related module is reloaded. 3. It makes the behavior more consistent and predictable. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211122132649.12737-5-pmladek@suse.com
2021-11-22 21:26:48 +08:00
if (newcon->device)
newcon->flags |= CON_CONSDEV;
}
/*
* 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.
printk: Enable the use of more than one CON_BOOT (early console) Today, register_console() assumes the following usage: - The first console to register with a flag set to CON_BOOT is the one and only bootconsole. - If another register_console() is called with an additional CON_BOOT, it is silently rejected. - As soon as a console without the CON_BOOT set calls registers the bootconsole is automatically unregistered. - Once there is a "real" console - register_console() will silently reject any consoles with it's CON_BOOT flag set. In many systems (alpha, blackfin, microblaze, mips, powerpc, sh, & x86), there are early_printk implementations, which use the CON_BOOT which come out serial ports, vga, usb, & memory buffers. In many embedded systems, it would be nice to have two bootconsoles - in case the primary fails, you always have access to a backup memory buffer - but this requires at least two CON_BOOT consoles... This patch enables that functionality. With the change applied, on boot you get (if you try to re-enable a boot console after the "real" console has been registered): root:/> dmesg | grep console bootconsole [early_shadow0] enabled bootconsole [early_BFuart0] enabled Kernel command line: root=/dev/mtdblock0 rw earlyprintk=serial,uart0,57600 console=ttyBF0,57600 nmi_debug=regs console handover:boot [early_BFuart0] boot [early_shadow0] -> real [ttyBF0] Too late to register bootconsole early_shadow0 or: root:/> dmesg | grep console Kernel command line: root=/dev/mtdblock0 rw console=ttyBF0,57600 console [ttyBF0] enabled Signed-off-by: Robin Getz <rgetz@blackfin.uclinux.org> Cc: "Linus Torvalds" <torvalds@linux-foundation.org> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Mike Frysinger" <vapier.adi@gmail.com> Cc: "Paul Mundt" <lethal@linux-sh.org> LKML-Reference: <200907012108.38030.rgetz@blackfin.uclinux.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 09:08:37 +08:00
*
* 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
*/
printk: Enable the use of more than one CON_BOOT (early console) Today, register_console() assumes the following usage: - The first console to register with a flag set to CON_BOOT is the one and only bootconsole. - If another register_console() is called with an additional CON_BOOT, it is silently rejected. - As soon as a console without the CON_BOOT set calls registers the bootconsole is automatically unregistered. - Once there is a "real" console - register_console() will silently reject any consoles with it's CON_BOOT flag set. In many systems (alpha, blackfin, microblaze, mips, powerpc, sh, & x86), there are early_printk implementations, which use the CON_BOOT which come out serial ports, vga, usb, & memory buffers. In many embedded systems, it would be nice to have two bootconsoles - in case the primary fails, you always have access to a backup memory buffer - but this requires at least two CON_BOOT consoles... This patch enables that functionality. With the change applied, on boot you get (if you try to re-enable a boot console after the "real" console has been registered): root:/> dmesg | grep console bootconsole [early_shadow0] enabled bootconsole [early_BFuart0] enabled Kernel command line: root=/dev/mtdblock0 rw earlyprintk=serial,uart0,57600 console=ttyBF0,57600 nmi_debug=regs console handover:boot [early_BFuart0] boot [early_shadow0] -> real [ttyBF0] Too late to register bootconsole early_shadow0 or: root:/> dmesg | grep console Kernel command line: root=/dev/mtdblock0 rw console=ttyBF0,57600 console [ttyBF0] enabled Signed-off-by: Robin Getz <rgetz@blackfin.uclinux.org> Cc: "Linus Torvalds" <torvalds@linux-foundation.org> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Mike Frysinger" <vapier.adi@gmail.com> Cc: "Paul Mundt" <lethal@linux-sh.org> LKML-Reference: <200907012108.38030.rgetz@blackfin.uclinux.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 09:08:37 +08:00
void register_console(struct console *newcon)
{
printk/console: Clean up boot console handling in register_console() The variable @bcon has two meanings. It is used several times for iterating the list of registered consoles. In the meantime, it holds the information whether a boot console is first in @console_drivers list. The information about the 1st console driver used to be important for the decision whether to install the new console by default or not. It allowed to re-evaluate the variable @need_default_console when a real console with tty binding has been unregistered in the meantime. The decision about the default console is not longer affected by @bcon variable. The current code checks whether the first driver is real and has tty binding directly. The information about the first console is still used for two more decisions: 1. It prevents duplicate output on non-boot consoles with CON_CONSDEV flag set. 2. Early/boot consoles are unregistered when a real console with CON_CONSDEV is registered and @keep_bootcon is not set. The behavior in the real life is far from obvious. @bcon is set according to the first console @console_drivers list. But the first position in the list is special: 1. Consoles with CON_CONSDEV flag are put at the beginning of the list. It is either the preferred console or any console with tty binding registered by default. 2. Another console might become the first in the list when the first console in the list is unregistered. It might happen either explicitly or automatically when boot consoles are unregistered. There is one more important rule: + Boot consoles can't be registered when any real console is already registered. It is a puzzle. The main complication is the dependency on the first position is the list and the complicated rules around it. Let's try to make it easier: 1. Add variable @bootcon_enabled and set it by iterating all registered consoles. The variable has obvious meaning and more predictable behavior. Any speed optimization and other tricks are not worth it. 2. Use a generic name for the variable that is used to iterate the list on registered console drivers. Behavior change: No, maybe surprisingly, there is _no_ behavior change! Let's provide the proof by contradiction. Both operations, duplicate output prevention and boot consoles removal, are done only when the newly added console has CON_CONSDEV flag set. The behavior would change when the new @bootcon_enabled has different value than the original @bcon. By other words, the behavior would change when the following conditions are true: + a console with CON_CONSDEV flag is added + a real (non-boot) console is the first in the list + a boot console is later in the list Now, a real console might be first in the list only when: + It was the first registered console. In this case, there can't be any boot console because any later ones were rejected. + It was put at the first position because it had CON_CONSDEV flag set. It was either the preferred console or it was a console with tty binding registered by default. We are interested only in a real consoles here. And real console with tty binding fulfills conditions of the default console. Now, there is always only one console that is either preferred or fulfills conditions of the default console. It can't be already in the list and being registered at the same time. As a result, the above three conditions could newer be "true" at the same time. Therefore the behavior can't change. Final dilemma: OK, the new code has the same behavior. But is the change in the right direction? What if the handling of @console_drivers is updated in the future? OK, let's look at it from another angle: 1. The ordering of @console_drivers list is important only in console_device() function. The first console driver with tty binding gets associated with /dev/console. 2. CON_CONSDEV flag is shown in /proc/consoles. And it should be set for the driver that is returned by console_device(). 3. A boot console is removed and the duplicated output is prevented when the real console with CON_CONSDEV flag is registered. Now, in the ideal world: + The driver associated with /dev/console should be either a console preferred via the command line, device tree, or SPCR. Or it should be the first real console with tty binding registered by default. + The code should match the related boot and real console drivers. It should unregister only the obsolete boot driver. And the duplicated output should be prevented only on the related real driver. It is clear that it is not guaranteed by the current code. Instead, the current code looks like a maze of heuristics that try to achieve the above. It is result of adding several features over last few decades. For example, a possibility to register more consoles, unregister consoles, boot consoles, consoles without tty binding, device tree, SPCR, braille consoles. Anyway, there is no reason why the decision, about removing boot consoles and preventing duplicated output, should depend on the first console in the list. The current code does the decisions primary by CON_CONSDEV flag that is used for the preferred console. It looks like a good compromise. And the change seems to be in the right direction. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211122132649.12737-6-pmladek@suse.com
2021-11-22 21:26:49 +08:00
struct console *con;
bool bootcon_enabled = false;
bool realcon_enabled = false;
int err;
printk/console: Clean up boot console handling in register_console() The variable @bcon has two meanings. It is used several times for iterating the list of registered consoles. In the meantime, it holds the information whether a boot console is first in @console_drivers list. The information about the 1st console driver used to be important for the decision whether to install the new console by default or not. It allowed to re-evaluate the variable @need_default_console when a real console with tty binding has been unregistered in the meantime. The decision about the default console is not longer affected by @bcon variable. The current code checks whether the first driver is real and has tty binding directly. The information about the first console is still used for two more decisions: 1. It prevents duplicate output on non-boot consoles with CON_CONSDEV flag set. 2. Early/boot consoles are unregistered when a real console with CON_CONSDEV is registered and @keep_bootcon is not set. The behavior in the real life is far from obvious. @bcon is set according to the first console @console_drivers list. But the first position in the list is special: 1. Consoles with CON_CONSDEV flag are put at the beginning of the list. It is either the preferred console or any console with tty binding registered by default. 2. Another console might become the first in the list when the first console in the list is unregistered. It might happen either explicitly or automatically when boot consoles are unregistered. There is one more important rule: + Boot consoles can't be registered when any real console is already registered. It is a puzzle. The main complication is the dependency on the first position is the list and the complicated rules around it. Let's try to make it easier: 1. Add variable @bootcon_enabled and set it by iterating all registered consoles. The variable has obvious meaning and more predictable behavior. Any speed optimization and other tricks are not worth it. 2. Use a generic name for the variable that is used to iterate the list on registered console drivers. Behavior change: No, maybe surprisingly, there is _no_ behavior change! Let's provide the proof by contradiction. Both operations, duplicate output prevention and boot consoles removal, are done only when the newly added console has CON_CONSDEV flag set. The behavior would change when the new @bootcon_enabled has different value than the original @bcon. By other words, the behavior would change when the following conditions are true: + a console with CON_CONSDEV flag is added + a real (non-boot) console is the first in the list + a boot console is later in the list Now, a real console might be first in the list only when: + It was the first registered console. In this case, there can't be any boot console because any later ones were rejected. + It was put at the first position because it had CON_CONSDEV flag set. It was either the preferred console or it was a console with tty binding registered by default. We are interested only in a real consoles here. And real console with tty binding fulfills conditions of the default console. Now, there is always only one console that is either preferred or fulfills conditions of the default console. It can't be already in the list and being registered at the same time. As a result, the above three conditions could newer be "true" at the same time. Therefore the behavior can't change. Final dilemma: OK, the new code has the same behavior. But is the change in the right direction? What if the handling of @console_drivers is updated in the future? OK, let's look at it from another angle: 1. The ordering of @console_drivers list is important only in console_device() function. The first console driver with tty binding gets associated with /dev/console. 2. CON_CONSDEV flag is shown in /proc/consoles. And it should be set for the driver that is returned by console_device(). 3. A boot console is removed and the duplicated output is prevented when the real console with CON_CONSDEV flag is registered. Now, in the ideal world: + The driver associated with /dev/console should be either a console preferred via the command line, device tree, or SPCR. Or it should be the first real console with tty binding registered by default. + The code should match the related boot and real console drivers. It should unregister only the obsolete boot driver. And the duplicated output should be prevented only on the related real driver. It is clear that it is not guaranteed by the current code. Instead, the current code looks like a maze of heuristics that try to achieve the above. It is result of adding several features over last few decades. For example, a possibility to register more consoles, unregister consoles, boot consoles, consoles without tty binding, device tree, SPCR, braille consoles. Anyway, there is no reason why the decision, about removing boot consoles and preventing duplicated output, should depend on the first console in the list. The current code does the decisions primary by CON_CONSDEV flag that is used for the preferred console. It looks like a good compromise. And the change seems to be in the right direction. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211122132649.12737-6-pmladek@suse.com
2021-11-22 21:26:49 +08:00
for_each_console(con) {
if (WARN(con == newcon, "console '%s%d' already registered\n",
con->name, con->index))
return;
}
printk/console: Clean up boot console handling in register_console() The variable @bcon has two meanings. It is used several times for iterating the list of registered consoles. In the meantime, it holds the information whether a boot console is first in @console_drivers list. The information about the 1st console driver used to be important for the decision whether to install the new console by default or not. It allowed to re-evaluate the variable @need_default_console when a real console with tty binding has been unregistered in the meantime. The decision about the default console is not longer affected by @bcon variable. The current code checks whether the first driver is real and has tty binding directly. The information about the first console is still used for two more decisions: 1. It prevents duplicate output on non-boot consoles with CON_CONSDEV flag set. 2. Early/boot consoles are unregistered when a real console with CON_CONSDEV is registered and @keep_bootcon is not set. The behavior in the real life is far from obvious. @bcon is set according to the first console @console_drivers list. But the first position in the list is special: 1. Consoles with CON_CONSDEV flag are put at the beginning of the list. It is either the preferred console or any console with tty binding registered by default. 2. Another console might become the first in the list when the first console in the list is unregistered. It might happen either explicitly or automatically when boot consoles are unregistered. There is one more important rule: + Boot consoles can't be registered when any real console is already registered. It is a puzzle. The main complication is the dependency on the first position is the list and the complicated rules around it. Let's try to make it easier: 1. Add variable @bootcon_enabled and set it by iterating all registered consoles. The variable has obvious meaning and more predictable behavior. Any speed optimization and other tricks are not worth it. 2. Use a generic name for the variable that is used to iterate the list on registered console drivers. Behavior change: No, maybe surprisingly, there is _no_ behavior change! Let's provide the proof by contradiction. Both operations, duplicate output prevention and boot consoles removal, are done only when the newly added console has CON_CONSDEV flag set. The behavior would change when the new @bootcon_enabled has different value than the original @bcon. By other words, the behavior would change when the following conditions are true: + a console with CON_CONSDEV flag is added + a real (non-boot) console is the first in the list + a boot console is later in the list Now, a real console might be first in the list only when: + It was the first registered console. In this case, there can't be any boot console because any later ones were rejected. + It was put at the first position because it had CON_CONSDEV flag set. It was either the preferred console or it was a console with tty binding registered by default. We are interested only in a real consoles here. And real console with tty binding fulfills conditions of the default console. Now, there is always only one console that is either preferred or fulfills conditions of the default console. It can't be already in the list and being registered at the same time. As a result, the above three conditions could newer be "true" at the same time. Therefore the behavior can't change. Final dilemma: OK, the new code has the same behavior. But is the change in the right direction? What if the handling of @console_drivers is updated in the future? OK, let's look at it from another angle: 1. The ordering of @console_drivers list is important only in console_device() function. The first console driver with tty binding gets associated with /dev/console. 2. CON_CONSDEV flag is shown in /proc/consoles. And it should be set for the driver that is returned by console_device(). 3. A boot console is removed and the duplicated output is prevented when the real console with CON_CONSDEV flag is registered. Now, in the ideal world: + The driver associated with /dev/console should be either a console preferred via the command line, device tree, or SPCR. Or it should be the first real console with tty binding registered by default. + The code should match the related boot and real console drivers. It should unregister only the obsolete boot driver. And the duplicated output should be prevented only on the related real driver. It is clear that it is not guaranteed by the current code. Instead, the current code looks like a maze of heuristics that try to achieve the above. It is result of adding several features over last few decades. For example, a possibility to register more consoles, unregister consoles, boot consoles, consoles without tty binding, device tree, SPCR, braille consoles. Anyway, there is no reason why the decision, about removing boot consoles and preventing duplicated output, should depend on the first console in the list. The current code does the decisions primary by CON_CONSDEV flag that is used for the preferred console. It looks like a good compromise. And the change seems to be in the right direction. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211122132649.12737-6-pmladek@suse.com
2021-11-22 21:26:49 +08:00
for_each_console(con) {
if (con->flags & CON_BOOT)
bootcon_enabled = true;
else
realcon_enabled = true;
Fixes and cleanups for earlyprintk aka boot console The console subsystem already has an idea of a boot console, using the CON_BOOT flag. The implementation has some flaws though. The major problem is that presence of a boot console makes register_console() ignore any other console devices (unless explicitly specified on the kernel command line). This patch fixes the console selection code to *not* consider a boot console a full-featured one, so the first non-boot console registering will become the default console instead. This way the unregister call for the boot console in the register_console() function actually triggers and the handover from the boot console to the real console device works smoothly. Added a printk for the handover, so you know which console device the output goes to when the boot console stops printing messages. The disable_early_printk() call is obsolete with that patch, explicitly disabling the early console isn't needed any more as it works automagically with that patch. I've walked through the tree, dropped all disable_early_printk() instances found below arch/ and tagged the consoles with CON_BOOT if needed. The code is tested on x86, sh (thanks to Paul) and mips (thanks to Ralf). Changes to last version: Rediffed against -rc3, adapted to mips cleanups by Ralf, fixed "udbg-immortal" cmd line arg on powerpc. Signed-off-by: Gerd Hoffmann <kraxel@exsuse.de> Acked-by: Paul Mundt <lethal@linux-sh.org> Acked-by: Ralf Baechle <ralf@linux-mips.org> Cc: Andi Kleen <ak@suse.de> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:26:49 +08:00
}
printk/console: Clean up boot console handling in register_console() The variable @bcon has two meanings. It is used several times for iterating the list of registered consoles. In the meantime, it holds the information whether a boot console is first in @console_drivers list. The information about the 1st console driver used to be important for the decision whether to install the new console by default or not. It allowed to re-evaluate the variable @need_default_console when a real console with tty binding has been unregistered in the meantime. The decision about the default console is not longer affected by @bcon variable. The current code checks whether the first driver is real and has tty binding directly. The information about the first console is still used for two more decisions: 1. It prevents duplicate output on non-boot consoles with CON_CONSDEV flag set. 2. Early/boot consoles are unregistered when a real console with CON_CONSDEV is registered and @keep_bootcon is not set. The behavior in the real life is far from obvious. @bcon is set according to the first console @console_drivers list. But the first position in the list is special: 1. Consoles with CON_CONSDEV flag are put at the beginning of the list. It is either the preferred console or any console with tty binding registered by default. 2. Another console might become the first in the list when the first console in the list is unregistered. It might happen either explicitly or automatically when boot consoles are unregistered. There is one more important rule: + Boot consoles can't be registered when any real console is already registered. It is a puzzle. The main complication is the dependency on the first position is the list and the complicated rules around it. Let's try to make it easier: 1. Add variable @bootcon_enabled and set it by iterating all registered consoles. The variable has obvious meaning and more predictable behavior. Any speed optimization and other tricks are not worth it. 2. Use a generic name for the variable that is used to iterate the list on registered console drivers. Behavior change: No, maybe surprisingly, there is _no_ behavior change! Let's provide the proof by contradiction. Both operations, duplicate output prevention and boot consoles removal, are done only when the newly added console has CON_CONSDEV flag set. The behavior would change when the new @bootcon_enabled has different value than the original @bcon. By other words, the behavior would change when the following conditions are true: + a console with CON_CONSDEV flag is added + a real (non-boot) console is the first in the list + a boot console is later in the list Now, a real console might be first in the list only when: + It was the first registered console. In this case, there can't be any boot console because any later ones were rejected. + It was put at the first position because it had CON_CONSDEV flag set. It was either the preferred console or it was a console with tty binding registered by default. We are interested only in a real consoles here. And real console with tty binding fulfills conditions of the default console. Now, there is always only one console that is either preferred or fulfills conditions of the default console. It can't be already in the list and being registered at the same time. As a result, the above three conditions could newer be "true" at the same time. Therefore the behavior can't change. Final dilemma: OK, the new code has the same behavior. But is the change in the right direction? What if the handling of @console_drivers is updated in the future? OK, let's look at it from another angle: 1. The ordering of @console_drivers list is important only in console_device() function. The first console driver with tty binding gets associated with /dev/console. 2. CON_CONSDEV flag is shown in /proc/consoles. And it should be set for the driver that is returned by console_device(). 3. A boot console is removed and the duplicated output is prevented when the real console with CON_CONSDEV flag is registered. Now, in the ideal world: + The driver associated with /dev/console should be either a console preferred via the command line, device tree, or SPCR. Or it should be the first real console with tty binding registered by default. + The code should match the related boot and real console drivers. It should unregister only the obsolete boot driver. And the duplicated output should be prevented only on the related real driver. It is clear that it is not guaranteed by the current code. Instead, the current code looks like a maze of heuristics that try to achieve the above. It is result of adding several features over last few decades. For example, a possibility to register more consoles, unregister consoles, boot consoles, consoles without tty binding, device tree, SPCR, braille consoles. Anyway, there is no reason why the decision, about removing boot consoles and preventing duplicated output, should depend on the first console in the list. The current code does the decisions primary by CON_CONSDEV flag that is used for the preferred console. It looks like a good compromise. And the change seems to be in the right direction. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211122132649.12737-6-pmladek@suse.com
2021-11-22 21:26:49 +08:00
/* Do not register boot consoles when there already is a real one. */
if (newcon->flags & CON_BOOT && realcon_enabled) {
pr_info("Too late to register bootconsole %s%d\n",
newcon->name, newcon->index);
return;
}
printk: Enable the use of more than one CON_BOOT (early console) Today, register_console() assumes the following usage: - The first console to register with a flag set to CON_BOOT is the one and only bootconsole. - If another register_console() is called with an additional CON_BOOT, it is silently rejected. - As soon as a console without the CON_BOOT set calls registers the bootconsole is automatically unregistered. - Once there is a "real" console - register_console() will silently reject any consoles with it's CON_BOOT flag set. In many systems (alpha, blackfin, microblaze, mips, powerpc, sh, & x86), there are early_printk implementations, which use the CON_BOOT which come out serial ports, vga, usb, & memory buffers. In many embedded systems, it would be nice to have two bootconsoles - in case the primary fails, you always have access to a backup memory buffer - but this requires at least two CON_BOOT consoles... This patch enables that functionality. With the change applied, on boot you get (if you try to re-enable a boot console after the "real" console has been registered): root:/> dmesg | grep console bootconsole [early_shadow0] enabled bootconsole [early_BFuart0] enabled Kernel command line: root=/dev/mtdblock0 rw earlyprintk=serial,uart0,57600 console=ttyBF0,57600 nmi_debug=regs console handover:boot [early_BFuart0] boot [early_shadow0] -> real [ttyBF0] Too late to register bootconsole early_shadow0 or: root:/> dmesg | grep console Kernel command line: root=/dev/mtdblock0 rw console=ttyBF0,57600 console [ttyBF0] enabled Signed-off-by: Robin Getz <rgetz@blackfin.uclinux.org> Cc: "Linus Torvalds" <torvalds@linux-foundation.org> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Mike Frysinger" <vapier.adi@gmail.com> Cc: "Paul Mundt" <lethal@linux-sh.org> LKML-Reference: <200907012108.38030.rgetz@blackfin.uclinux.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 09:08:37 +08:00
/*
printk/console: Remove need_default_console variable The variable @need_default_console is used to decide whether a newly registered console should get enabled by default. The logic is complicated. It can be modified in a register_console() call. But it is always re-evaluated in the next call by the following condition: if (need_default_console || bcon || !console_drivers) need_default_console = preferred_console < 0; In short, the value is updated when either of the condition is valid: + the value is still, or again, "true" + boot/early console is still the first in @console_driver list + @console_driver list is empty The value is updated according to @preferred_console. In particular, it is set to "false" when a @preferred_console was set by __add_preferred_console(). This happens when a non-braille console was added via the command line, device tree, or SPCR. It far from clear what this all means together. Let's look at @need_default_console from another angle: 1. The value is "true" by default. It means that it is always set according to @preferred_console during the first register_console() call. By other words, the first register_console() call will register the console by default only when none non-braille console was defined via the command line, device tree, or SPCR. 2. The value will always stay "false" when @preferred_console is set. By other words, try_enable_default_console() will never get called when a non-braille console is explicitly required. 4. The value might be set to "false" in try_enable_default_console() when a console with tty binding (driver) gets enabled. In this case CON_CONSDEV is set as well. It causes that the console will be inserted as first into the list @console_driver. It might be either real or boot/early console. 5. The value will be set _back_ to "true" in the next register_console() call when: + The console added by the previous register_console() had been a boot/early one. + The last console has been unregistered in the meantime and a boot/early console became first in @console_drivers list again. Or the list became empty. By other words, the value will stay "false" only when the last registered console was real, had tty binding, and was not removed in the mean time. The main logic looks clear: + Consoles are enabled by default only when no one is preferred via the command line, device tree, or SPCR. + By default, any console is enabled until a real console with tty binding gets registered. The behavior when the real console with tty binding is later removed is a bit unclear: + By default, any new console is registered again only when there is no console or the first console in the list is a boot one. The question is why the code is suddenly happy when a real console without tty binding is the first in the list. It looks like an overlook and bug. Conclusion: The state of @preferred_console and the first console in @console_driver list should be enough to decide whether we need to enable the given console by default. The rules are simple. New consoles are _not_ enabled by default when either of the following conditions is true: + @preferred_console is set. It means that a non-braille console is explicitly configured via the command line, device tree, or SPCR. + A real console with tty binding is registered. Such a console will have CON_CONSDEV flag set and will always be the first in @console_drivers list. Note: The new code does not use @bcon variable. The meaning of the variable is far from clear. The direct check of the first console in the list makes it more clear that only real console fulfills requirements of the default console. Behavior change: As already discussed above. There was one situation where the original code worked a strange way. Let's have: + console A: real console without tty binding + console B: real console with tty binding and do: register_console(A); /* 1st step */ register_console(B); /* 2nd step */ unregister_console(B); /* 3rd step */ register_console(B); /* 4th step */ The original code will not register the console B in the 4th step. @need_default_console is set to "false" in 2nd step. The real console with tty binding (driver) is then removed in the 3rd step. But @need_default_console will stay "false" in the 4th step because there is no boot/early console and @registered_consoles list is not empty. The new code will register the console B in the 4th step because it checks whether the first console has tty binding (->driver) This behavior change should acceptable: 1. The scenario requires manual intervention (console removal). The system should boot with the same consoles as before. 2. Console B is registered again probably because the user wants to use it. The most likely scenario is that the related module is reloaded. 3. It makes the behavior more consistent and predictable. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211122132649.12737-5-pmladek@suse.com
2021-11-22 21:26:48 +08:00
* See if we want to enable this console driver by default.
*
* Nope when a console is preferred by the command line, device
* tree, or SPCR.
*
* The first real console with tty binding (driver) wins. More
* consoles might get enabled before the right one is found.
*
* Note that a console with tty binding will have CON_CONSDEV
* flag set and will be first in the list.
*/
printk/console: Remove need_default_console variable The variable @need_default_console is used to decide whether a newly registered console should get enabled by default. The logic is complicated. It can be modified in a register_console() call. But it is always re-evaluated in the next call by the following condition: if (need_default_console || bcon || !console_drivers) need_default_console = preferred_console < 0; In short, the value is updated when either of the condition is valid: + the value is still, or again, "true" + boot/early console is still the first in @console_driver list + @console_driver list is empty The value is updated according to @preferred_console. In particular, it is set to "false" when a @preferred_console was set by __add_preferred_console(). This happens when a non-braille console was added via the command line, device tree, or SPCR. It far from clear what this all means together. Let's look at @need_default_console from another angle: 1. The value is "true" by default. It means that it is always set according to @preferred_console during the first register_console() call. By other words, the first register_console() call will register the console by default only when none non-braille console was defined via the command line, device tree, or SPCR. 2. The value will always stay "false" when @preferred_console is set. By other words, try_enable_default_console() will never get called when a non-braille console is explicitly required. 4. The value might be set to "false" in try_enable_default_console() when a console with tty binding (driver) gets enabled. In this case CON_CONSDEV is set as well. It causes that the console will be inserted as first into the list @console_driver. It might be either real or boot/early console. 5. The value will be set _back_ to "true" in the next register_console() call when: + The console added by the previous register_console() had been a boot/early one. + The last console has been unregistered in the meantime and a boot/early console became first in @console_drivers list again. Or the list became empty. By other words, the value will stay "false" only when the last registered console was real, had tty binding, and was not removed in the mean time. The main logic looks clear: + Consoles are enabled by default only when no one is preferred via the command line, device tree, or SPCR. + By default, any console is enabled until a real console with tty binding gets registered. The behavior when the real console with tty binding is later removed is a bit unclear: + By default, any new console is registered again only when there is no console or the first console in the list is a boot one. The question is why the code is suddenly happy when a real console without tty binding is the first in the list. It looks like an overlook and bug. Conclusion: The state of @preferred_console and the first console in @console_driver list should be enough to decide whether we need to enable the given console by default. The rules are simple. New consoles are _not_ enabled by default when either of the following conditions is true: + @preferred_console is set. It means that a non-braille console is explicitly configured via the command line, device tree, or SPCR. + A real console with tty binding is registered. Such a console will have CON_CONSDEV flag set and will always be the first in @console_drivers list. Note: The new code does not use @bcon variable. The meaning of the variable is far from clear. The direct check of the first console in the list makes it more clear that only real console fulfills requirements of the default console. Behavior change: As already discussed above. There was one situation where the original code worked a strange way. Let's have: + console A: real console without tty binding + console B: real console with tty binding and do: register_console(A); /* 1st step */ register_console(B); /* 2nd step */ unregister_console(B); /* 3rd step */ register_console(B); /* 4th step */ The original code will not register the console B in the 4th step. @need_default_console is set to "false" in 2nd step. The real console with tty binding (driver) is then removed in the 3rd step. But @need_default_console will stay "false" in the 4th step because there is no boot/early console and @registered_consoles list is not empty. The new code will register the console B in the 4th step because it checks whether the first console has tty binding (->driver) This behavior change should acceptable: 1. The scenario requires manual intervention (console removal). The system should boot with the same consoles as before. 2. Console B is registered again probably because the user wants to use it. The most likely scenario is that the related module is reloaded. 3. It makes the behavior more consistent and predictable. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211122132649.12737-5-pmladek@suse.com
2021-11-22 21:26:48 +08:00
if (preferred_console < 0) {
if (!console_drivers || !console_drivers->device ||
console_drivers->flags & CON_BOOT) {
try_enable_default_console(newcon);
}
}
printk: Fix preferred console selection with multiple matches In the following circumstances, the rule of selecting the console corresponding to the last "console=" entry on the command line as the preferred console (CON_CONSDEV, ie, /dev/console) fails. This is a specific example, but it could happen with different consoles that have a similar name aliasing mechanism. - The kernel command line has both console=tty0 and console=ttyS0 in that order (the latter with speed etc... arguments). This is common with some cloud setups such as Amazon Linux. - add_preferred_console is called early to register "uart0". In our case that happens from acpi_parse_spcr() on arm64 since the "enable_console" argument is true on that architecture. This causes "uart0" to become entry 0 of the console_cmdline array. Now, because of the above, what happens is: - add_preferred_console is called by the cmdline parsing for tty0 and ttyS0 respectively, thus occupying entries 1 and 2 of the console_cmdline array (since this happens after ACPI SPCR parsing). At that point preferred_console is set to 2 as expected. - When the tty layer kicks in, it will call register_console for tty0. This will match entry 1 in console_cmdline array. It isn't our preferred console but because it's our only console at this point, it will end up "first" in the consoles list. - When 8250 probes the actual serial port later on, it calls register_console for ttyS0. At that point the loop in register_console tries to match it with the entries in the console_cmdline array. Ideally this should match ttyS0 in entry 2, which is preferred, causing it to be inserted first and to replace tty0 as CONSDEV. However, 8250 provides a "match" hook in its struct console, and that hook will match "uart" as an alias to "ttyS". So we match uart0 at entry 0 in the array which is not the preferred console and will not match entry 2 which is since we break out of the loop on the first match. As a result, we don't set CONSDEV and don't insert it first, but second in the console list. As a result, we end up with tty0 remaining first in the array, and thus /dev/console going there instead of the last user specified one which is ttyS0. This tentative fix register_console() to scan first for consoles specified on the command line, and only if none is found, to then scan for consoles specified by the architecture. Link: https://lore.kernel.org/r/20200213095133.23176-3-pmladek@suse.com Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2020-02-13 17:51:32 +08:00
/* See if this console matches one we selected on the command line */
err = try_enable_preferred_console(newcon, true);
printk: Fix preferred console selection with multiple matches In the following circumstances, the rule of selecting the console corresponding to the last "console=" entry on the command line as the preferred console (CON_CONSDEV, ie, /dev/console) fails. This is a specific example, but it could happen with different consoles that have a similar name aliasing mechanism. - The kernel command line has both console=tty0 and console=ttyS0 in that order (the latter with speed etc... arguments). This is common with some cloud setups such as Amazon Linux. - add_preferred_console is called early to register "uart0". In our case that happens from acpi_parse_spcr() on arm64 since the "enable_console" argument is true on that architecture. This causes "uart0" to become entry 0 of the console_cmdline array. Now, because of the above, what happens is: - add_preferred_console is called by the cmdline parsing for tty0 and ttyS0 respectively, thus occupying entries 1 and 2 of the console_cmdline array (since this happens after ACPI SPCR parsing). At that point preferred_console is set to 2 as expected. - When the tty layer kicks in, it will call register_console for tty0. This will match entry 1 in console_cmdline array. It isn't our preferred console but because it's our only console at this point, it will end up "first" in the consoles list. - When 8250 probes the actual serial port later on, it calls register_console for ttyS0. At that point the loop in register_console tries to match it with the entries in the console_cmdline array. Ideally this should match ttyS0 in entry 2, which is preferred, causing it to be inserted first and to replace tty0 as CONSDEV. However, 8250 provides a "match" hook in its struct console, and that hook will match "uart" as an alias to "ttyS". So we match uart0 at entry 0 in the array which is not the preferred console and will not match entry 2 which is since we break out of the loop on the first match. As a result, we don't set CONSDEV and don't insert it first, but second in the console list. As a result, we end up with tty0 remaining first in the array, and thus /dev/console going there instead of the last user specified one which is ttyS0. This tentative fix register_console() to scan first for consoles specified on the command line, and only if none is found, to then scan for consoles specified by the architecture. Link: https://lore.kernel.org/r/20200213095133.23176-3-pmladek@suse.com Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2020-02-13 17:51:32 +08:00
/* If not, try to match against the platform default(s) */
if (err == -ENOENT)
err = try_enable_preferred_console(newcon, false);
/* printk() messages are not printed to the Braille console. */
if (err || newcon->flags & CON_BRL)
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
*/
printk/console: Clean up boot console handling in register_console() The variable @bcon has two meanings. It is used several times for iterating the list of registered consoles. In the meantime, it holds the information whether a boot console is first in @console_drivers list. The information about the 1st console driver used to be important for the decision whether to install the new console by default or not. It allowed to re-evaluate the variable @need_default_console when a real console with tty binding has been unregistered in the meantime. The decision about the default console is not longer affected by @bcon variable. The current code checks whether the first driver is real and has tty binding directly. The information about the first console is still used for two more decisions: 1. It prevents duplicate output on non-boot consoles with CON_CONSDEV flag set. 2. Early/boot consoles are unregistered when a real console with CON_CONSDEV is registered and @keep_bootcon is not set. The behavior in the real life is far from obvious. @bcon is set according to the first console @console_drivers list. But the first position in the list is special: 1. Consoles with CON_CONSDEV flag are put at the beginning of the list. It is either the preferred console or any console with tty binding registered by default. 2. Another console might become the first in the list when the first console in the list is unregistered. It might happen either explicitly or automatically when boot consoles are unregistered. There is one more important rule: + Boot consoles can't be registered when any real console is already registered. It is a puzzle. The main complication is the dependency on the first position is the list and the complicated rules around it. Let's try to make it easier: 1. Add variable @bootcon_enabled and set it by iterating all registered consoles. The variable has obvious meaning and more predictable behavior. Any speed optimization and other tricks are not worth it. 2. Use a generic name for the variable that is used to iterate the list on registered console drivers. Behavior change: No, maybe surprisingly, there is _no_ behavior change! Let's provide the proof by contradiction. Both operations, duplicate output prevention and boot consoles removal, are done only when the newly added console has CON_CONSDEV flag set. The behavior would change when the new @bootcon_enabled has different value than the original @bcon. By other words, the behavior would change when the following conditions are true: + a console with CON_CONSDEV flag is added + a real (non-boot) console is the first in the list + a boot console is later in the list Now, a real console might be first in the list only when: + It was the first registered console. In this case, there can't be any boot console because any later ones were rejected. + It was put at the first position because it had CON_CONSDEV flag set. It was either the preferred console or it was a console with tty binding registered by default. We are interested only in a real consoles here. And real console with tty binding fulfills conditions of the default console. Now, there is always only one console that is either preferred or fulfills conditions of the default console. It can't be already in the list and being registered at the same time. As a result, the above three conditions could newer be "true" at the same time. Therefore the behavior can't change. Final dilemma: OK, the new code has the same behavior. But is the change in the right direction? What if the handling of @console_drivers is updated in the future? OK, let's look at it from another angle: 1. The ordering of @console_drivers list is important only in console_device() function. The first console driver with tty binding gets associated with /dev/console. 2. CON_CONSDEV flag is shown in /proc/consoles. And it should be set for the driver that is returned by console_device(). 3. A boot console is removed and the duplicated output is prevented when the real console with CON_CONSDEV flag is registered. Now, in the ideal world: + The driver associated with /dev/console should be either a console preferred via the command line, device tree, or SPCR. Or it should be the first real console with tty binding registered by default. + The code should match the related boot and real console drivers. It should unregister only the obsolete boot driver. And the duplicated output should be prevented only on the related real driver. It is clear that it is not guaranteed by the current code. Instead, the current code looks like a maze of heuristics that try to achieve the above. It is result of adding several features over last few decades. For example, a possibility to register more consoles, unregister consoles, boot consoles, consoles without tty binding, device tree, SPCR, braille consoles. Anyway, there is no reason why the decision, about removing boot consoles and preventing duplicated output, should depend on the first console in the list. The current code does the decisions primary by CON_CONSDEV flag that is used for the preferred console. It looks like a good compromise. And the change seems to be in the right direction. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211122132649.12737-6-pmladek@suse.com
2021-11-22 21:26:49 +08:00
if (bootcon_enabled &&
((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) {
printk: Enable the use of more than one CON_BOOT (early console) Today, register_console() assumes the following usage: - The first console to register with a flag set to CON_BOOT is the one and only bootconsole. - If another register_console() is called with an additional CON_BOOT, it is silently rejected. - As soon as a console without the CON_BOOT set calls registers the bootconsole is automatically unregistered. - Once there is a "real" console - register_console() will silently reject any consoles with it's CON_BOOT flag set. In many systems (alpha, blackfin, microblaze, mips, powerpc, sh, & x86), there are early_printk implementations, which use the CON_BOOT which come out serial ports, vga, usb, & memory buffers. In many embedded systems, it would be nice to have two bootconsoles - in case the primary fails, you always have access to a backup memory buffer - but this requires at least two CON_BOOT consoles... This patch enables that functionality. With the change applied, on boot you get (if you try to re-enable a boot console after the "real" console has been registered): root:/> dmesg | grep console bootconsole [early_shadow0] enabled bootconsole [early_BFuart0] enabled Kernel command line: root=/dev/mtdblock0 rw earlyprintk=serial,uart0,57600 console=ttyBF0,57600 nmi_debug=regs console handover:boot [early_BFuart0] boot [early_shadow0] -> real [ttyBF0] Too late to register bootconsole early_shadow0 or: root:/> dmesg | grep console Kernel command line: root=/dev/mtdblock0 rw console=ttyBF0,57600 console [ttyBF0] enabled Signed-off-by: Robin Getz <rgetz@blackfin.uclinux.org> Cc: "Linus Torvalds" <torvalds@linux-foundation.org> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Mike Frysinger" <vapier.adi@gmail.com> Cc: "Paul Mundt" <lethal@linux-sh.org> LKML-Reference: <200907012108.38030.rgetz@blackfin.uclinux.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 09:08:37 +08:00
newcon->flags &= ~CON_PRINTBUFFER;
printk/console: Clean up boot console handling in register_console() The variable @bcon has two meanings. It is used several times for iterating the list of registered consoles. In the meantime, it holds the information whether a boot console is first in @console_drivers list. The information about the 1st console driver used to be important for the decision whether to install the new console by default or not. It allowed to re-evaluate the variable @need_default_console when a real console with tty binding has been unregistered in the meantime. The decision about the default console is not longer affected by @bcon variable. The current code checks whether the first driver is real and has tty binding directly. The information about the first console is still used for two more decisions: 1. It prevents duplicate output on non-boot consoles with CON_CONSDEV flag set. 2. Early/boot consoles are unregistered when a real console with CON_CONSDEV is registered and @keep_bootcon is not set. The behavior in the real life is far from obvious. @bcon is set according to the first console @console_drivers list. But the first position in the list is special: 1. Consoles with CON_CONSDEV flag are put at the beginning of the list. It is either the preferred console or any console with tty binding registered by default. 2. Another console might become the first in the list when the first console in the list is unregistered. It might happen either explicitly or automatically when boot consoles are unregistered. There is one more important rule: + Boot consoles can't be registered when any real console is already registered. It is a puzzle. The main complication is the dependency on the first position is the list and the complicated rules around it. Let's try to make it easier: 1. Add variable @bootcon_enabled and set it by iterating all registered consoles. The variable has obvious meaning and more predictable behavior. Any speed optimization and other tricks are not worth it. 2. Use a generic name for the variable that is used to iterate the list on registered console drivers. Behavior change: No, maybe surprisingly, there is _no_ behavior change! Let's provide the proof by contradiction. Both operations, duplicate output prevention and boot consoles removal, are done only when the newly added console has CON_CONSDEV flag set. The behavior would change when the new @bootcon_enabled has different value than the original @bcon. By other words, the behavior would change when the following conditions are true: + a console with CON_CONSDEV flag is added + a real (non-boot) console is the first in the list + a boot console is later in the list Now, a real console might be first in the list only when: + It was the first registered console. In this case, there can't be any boot console because any later ones were rejected. + It was put at the first position because it had CON_CONSDEV flag set. It was either the preferred console or it was a console with tty binding registered by default. We are interested only in a real consoles here. And real console with tty binding fulfills conditions of the default console. Now, there is always only one console that is either preferred or fulfills conditions of the default console. It can't be already in the list and being registered at the same time. As a result, the above three conditions could newer be "true" at the same time. Therefore the behavior can't change. Final dilemma: OK, the new code has the same behavior. But is the change in the right direction? What if the handling of @console_drivers is updated in the future? OK, let's look at it from another angle: 1. The ordering of @console_drivers list is important only in console_device() function. The first console driver with tty binding gets associated with /dev/console. 2. CON_CONSDEV flag is shown in /proc/consoles. And it should be set for the driver that is returned by console_device(). 3. A boot console is removed and the duplicated output is prevented when the real console with CON_CONSDEV flag is registered. Now, in the ideal world: + The driver associated with /dev/console should be either a console preferred via the command line, device tree, or SPCR. Or it should be the first real console with tty binding registered by default. + The code should match the related boot and real console drivers. It should unregister only the obsolete boot driver. And the duplicated output should be prevented only on the related real driver. It is clear that it is not guaranteed by the current code. Instead, the current code looks like a maze of heuristics that try to achieve the above. It is result of adding several features over last few decades. For example, a possibility to register more consoles, unregister consoles, boot consoles, consoles without tty binding, device tree, SPCR, braille consoles. Anyway, there is no reason why the decision, about removing boot consoles and preventing duplicated output, should depend on the first console in the list. The current code does the decisions primary by CON_CONSDEV flag that is used for the preferred console. It looks like a good compromise. And the change seems to be in the right direction. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211122132649.12737-6-pmladek@suse.com
2021-11-22 21:26:49 +08:00
}
/*
* Put this console in the list - keep the
* preferred driver at the head of the list.
*/
console_lock();
printk: Enable the use of more than one CON_BOOT (early console) Today, register_console() assumes the following usage: - The first console to register with a flag set to CON_BOOT is the one and only bootconsole. - If another register_console() is called with an additional CON_BOOT, it is silently rejected. - As soon as a console without the CON_BOOT set calls registers the bootconsole is automatically unregistered. - Once there is a "real" console - register_console() will silently reject any consoles with it's CON_BOOT flag set. In many systems (alpha, blackfin, microblaze, mips, powerpc, sh, & x86), there are early_printk implementations, which use the CON_BOOT which come out serial ports, vga, usb, & memory buffers. In many embedded systems, it would be nice to have two bootconsoles - in case the primary fails, you always have access to a backup memory buffer - but this requires at least two CON_BOOT consoles... This patch enables that functionality. With the change applied, on boot you get (if you try to re-enable a boot console after the "real" console has been registered): root:/> dmesg | grep console bootconsole [early_shadow0] enabled bootconsole [early_BFuart0] enabled Kernel command line: root=/dev/mtdblock0 rw earlyprintk=serial,uart0,57600 console=ttyBF0,57600 nmi_debug=regs console handover:boot [early_BFuart0] boot [early_shadow0] -> real [ttyBF0] Too late to register bootconsole early_shadow0 or: root:/> dmesg | grep console Kernel command line: root=/dev/mtdblock0 rw console=ttyBF0,57600 console [ttyBF0] enabled Signed-off-by: Robin Getz <rgetz@blackfin.uclinux.org> Cc: "Linus Torvalds" <torvalds@linux-foundation.org> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Mike Frysinger" <vapier.adi@gmail.com> Cc: "Paul Mundt" <lethal@linux-sh.org> LKML-Reference: <200907012108.38030.rgetz@blackfin.uclinux.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 09:08:37 +08:00
if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) {
newcon->next = console_drivers;
console_drivers = newcon;
if (newcon->next)
newcon->next->flags &= ~CON_CONSDEV;
printk: Correctly set CON_CONSDEV even when preferred console was not registered CON_CONSDEV flag was historically used to put/keep the preferred console first in console_drivers list. Where the preferred console is the last on the command line. The ordering is important only when opening /dev/console: + tty_kopen() + tty_lookup_driver() + console_device() The flag was originally an implementation detail. But it was later made accessible from userspace via /proc/consoles. It was used, for example, by the tool "showconsole" to show the real tty accessible via /dev/console, see https://github.com/bitstreamout/showconsole Now, the current code sets CON_CONSDEV only for the preferred console or when a fallback console is added. The flag is not set when the preferred console is defined on the command line but it is not registered from some reasons. Simple solution is to set CON_CONSDEV flag for the first registered console. It will work most of the time because: + Most real consoles have console->device defined. + Boot consoles are removed in printk_late_init(). + unregister_console() moves CON_CONSDEV flag to the next console. Clean solution would require checking con->device when the preferred console is registered and in unregister_console(). Conclusion: Use the simple solution for now. It is better than the current state and good enough. The clean solution is not worth it. It would complicate the already complicated code without too much gain. Instead the code would deserve a complete rewrite. Link: https://lore.kernel.org/r/20200213095133.23176-4-pmladek@suse.com Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [pmladek@suse.com: Correct reasoning in the commit message, comment update.] Reviewed-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2020-02-13 17:51:33 +08:00
/* Ensure this flag is always set for the head of the list */
newcon->flags |= CON_CONSDEV;
} else {
printk: Enable the use of more than one CON_BOOT (early console) Today, register_console() assumes the following usage: - The first console to register with a flag set to CON_BOOT is the one and only bootconsole. - If another register_console() is called with an additional CON_BOOT, it is silently rejected. - As soon as a console without the CON_BOOT set calls registers the bootconsole is automatically unregistered. - Once there is a "real" console - register_console() will silently reject any consoles with it's CON_BOOT flag set. In many systems (alpha, blackfin, microblaze, mips, powerpc, sh, & x86), there are early_printk implementations, which use the CON_BOOT which come out serial ports, vga, usb, & memory buffers. In many embedded systems, it would be nice to have two bootconsoles - in case the primary fails, you always have access to a backup memory buffer - but this requires at least two CON_BOOT consoles... This patch enables that functionality. With the change applied, on boot you get (if you try to re-enable a boot console after the "real" console has been registered): root:/> dmesg | grep console bootconsole [early_shadow0] enabled bootconsole [early_BFuart0] enabled Kernel command line: root=/dev/mtdblock0 rw earlyprintk=serial,uart0,57600 console=ttyBF0,57600 nmi_debug=regs console handover:boot [early_BFuart0] boot [early_shadow0] -> real [ttyBF0] Too late to register bootconsole early_shadow0 or: root:/> dmesg | grep console Kernel command line: root=/dev/mtdblock0 rw console=ttyBF0,57600 console [ttyBF0] enabled Signed-off-by: Robin Getz <rgetz@blackfin.uclinux.org> Cc: "Linus Torvalds" <torvalds@linux-foundation.org> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Mike Frysinger" <vapier.adi@gmail.com> Cc: "Paul Mundt" <lethal@linux-sh.org> LKML-Reference: <200907012108.38030.rgetz@blackfin.uclinux.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 09:08:37 +08:00
newcon->next = console_drivers->next;
console_drivers->next = newcon;
}
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
if (newcon->flags & CON_EXTENDED)
printk: keep kernel cont support always enabled Since commit 5c2992ee7fd8a29 ("printk: remove console flushing special cases for partial buffered lines") we don't print cont fragments to the consoles; cont lines are now proper log_buf entries and there is no "consecutive continuation flag" anymore: we either have 'c' entries that mark continuation lines without fragments; or '-' entries that mark normal logbuf entries. There are no '+' entries anymore. However, we still have a small leftover - presence of ext_console drivers disables kernel cont support and we flush each pr_cont() and store it as a separate log_buf entry. Previously, it worked because msg_print_ext_header() had that "an optional external merge of the records" functionality: if (msg->flags & LOG_CONT) cont = (prev_flags & LOG_CONT) ? '+' : 'c'; We don't do this as of now, so keep kernel cont always enabled. Note from pmladek: The original purpose was to get full information including the metadata and dictionary via extended console drivers, see commit 6fe29354befe4c46e ("printk: implement support for extended console drivers"). The dictionary probably was the most important part but it was actually lost: static void cont_flush(void) { [...] log_store(cont.facility, cont.level, cont.flags, cont.ts_nsec, NULL, 0, cont.buf, cont.len); Nobody noticed because the only dictionary user is dev_printk() and dev_cont() is _not_ defined. Link: http://lkml.kernel.org/r/20181002023836.4487-2-sergey.senozhatsky@gmail.com To: Steven Rostedt <rostedt@goodmis.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Cc: Tejun Heo <tj@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: LKML <linux-kernel@vger.kernel.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> [pmladek@suse.com: Updated commit message] Signed-off-by: Petr Mladek <pmladek@suse.com>
2018-10-02 10:38:34 +08:00
nr_ext_console_drivers++;
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
printk: Enable the use of more than one CON_BOOT (early console) Today, register_console() assumes the following usage: - The first console to register with a flag set to CON_BOOT is the one and only bootconsole. - If another register_console() is called with an additional CON_BOOT, it is silently rejected. - As soon as a console without the CON_BOOT set calls registers the bootconsole is automatically unregistered. - Once there is a "real" console - register_console() will silently reject any consoles with it's CON_BOOT flag set. In many systems (alpha, blackfin, microblaze, mips, powerpc, sh, & x86), there are early_printk implementations, which use the CON_BOOT which come out serial ports, vga, usb, & memory buffers. In many embedded systems, it would be nice to have two bootconsoles - in case the primary fails, you always have access to a backup memory buffer - but this requires at least two CON_BOOT consoles... This patch enables that functionality. With the change applied, on boot you get (if you try to re-enable a boot console after the "real" console has been registered): root:/> dmesg | grep console bootconsole [early_shadow0] enabled bootconsole [early_BFuart0] enabled Kernel command line: root=/dev/mtdblock0 rw earlyprintk=serial,uart0,57600 console=ttyBF0,57600 nmi_debug=regs console handover:boot [early_BFuart0] boot [early_shadow0] -> real [ttyBF0] Too late to register bootconsole early_shadow0 or: root:/> dmesg | grep console Kernel command line: root=/dev/mtdblock0 rw console=ttyBF0,57600 console [ttyBF0] enabled Signed-off-by: Robin Getz <rgetz@blackfin.uclinux.org> Cc: "Linus Torvalds" <torvalds@linux-foundation.org> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Mike Frysinger" <vapier.adi@gmail.com> Cc: "Paul Mundt" <lethal@linux-sh.org> LKML-Reference: <200907012108.38030.rgetz@blackfin.uclinux.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 09:08:37 +08:00
if (newcon->flags & CON_PRINTBUFFER) {
/*
* console_unlock(); will print out the buffered messages
* for us.
*
* 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.
*
* Set exclusive_console with disabled interrupts to reduce
* race window with eventual console_flush_on_panic() that
* ignores console_lock.
*/
exclusive_console = newcon;
exclusive_console_stop_seq = console_seq;
/* Get a consistent copy of @syslog_seq. */
mutex_lock(&syslog_lock);
console_seq = syslog_seq;
mutex_unlock(&syslog_lock);
}
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)
*/
pr_info("%sconsole [%s%d] enabled\n",
(newcon->flags & CON_BOOT) ? "boot" : "" ,
newcon->name, newcon->index);
printk/console: Clean up boot console handling in register_console() The variable @bcon has two meanings. It is used several times for iterating the list of registered consoles. In the meantime, it holds the information whether a boot console is first in @console_drivers list. The information about the 1st console driver used to be important for the decision whether to install the new console by default or not. It allowed to re-evaluate the variable @need_default_console when a real console with tty binding has been unregistered in the meantime. The decision about the default console is not longer affected by @bcon variable. The current code checks whether the first driver is real and has tty binding directly. The information about the first console is still used for two more decisions: 1. It prevents duplicate output on non-boot consoles with CON_CONSDEV flag set. 2. Early/boot consoles are unregistered when a real console with CON_CONSDEV is registered and @keep_bootcon is not set. The behavior in the real life is far from obvious. @bcon is set according to the first console @console_drivers list. But the first position in the list is special: 1. Consoles with CON_CONSDEV flag are put at the beginning of the list. It is either the preferred console or any console with tty binding registered by default. 2. Another console might become the first in the list when the first console in the list is unregistered. It might happen either explicitly or automatically when boot consoles are unregistered. There is one more important rule: + Boot consoles can't be registered when any real console is already registered. It is a puzzle. The main complication is the dependency on the first position is the list and the complicated rules around it. Let's try to make it easier: 1. Add variable @bootcon_enabled and set it by iterating all registered consoles. The variable has obvious meaning and more predictable behavior. Any speed optimization and other tricks are not worth it. 2. Use a generic name for the variable that is used to iterate the list on registered console drivers. Behavior change: No, maybe surprisingly, there is _no_ behavior change! Let's provide the proof by contradiction. Both operations, duplicate output prevention and boot consoles removal, are done only when the newly added console has CON_CONSDEV flag set. The behavior would change when the new @bootcon_enabled has different value than the original @bcon. By other words, the behavior would change when the following conditions are true: + a console with CON_CONSDEV flag is added + a real (non-boot) console is the first in the list + a boot console is later in the list Now, a real console might be first in the list only when: + It was the first registered console. In this case, there can't be any boot console because any later ones were rejected. + It was put at the first position because it had CON_CONSDEV flag set. It was either the preferred console or it was a console with tty binding registered by default. We are interested only in a real consoles here. And real console with tty binding fulfills conditions of the default console. Now, there is always only one console that is either preferred or fulfills conditions of the default console. It can't be already in the list and being registered at the same time. As a result, the above three conditions could newer be "true" at the same time. Therefore the behavior can't change. Final dilemma: OK, the new code has the same behavior. But is the change in the right direction? What if the handling of @console_drivers is updated in the future? OK, let's look at it from another angle: 1. The ordering of @console_drivers list is important only in console_device() function. The first console driver with tty binding gets associated with /dev/console. 2. CON_CONSDEV flag is shown in /proc/consoles. And it should be set for the driver that is returned by console_device(). 3. A boot console is removed and the duplicated output is prevented when the real console with CON_CONSDEV flag is registered. Now, in the ideal world: + The driver associated with /dev/console should be either a console preferred via the command line, device tree, or SPCR. Or it should be the first real console with tty binding registered by default. + The code should match the related boot and real console drivers. It should unregister only the obsolete boot driver. And the duplicated output should be prevented only on the related real driver. It is clear that it is not guaranteed by the current code. Instead, the current code looks like a maze of heuristics that try to achieve the above. It is result of adding several features over last few decades. For example, a possibility to register more consoles, unregister consoles, boot consoles, consoles without tty binding, device tree, SPCR, braille consoles. Anyway, there is no reason why the decision, about removing boot consoles and preventing duplicated output, should depend on the first console in the list. The current code does the decisions primary by CON_CONSDEV flag that is used for the preferred console. It looks like a good compromise. And the change seems to be in the right direction. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211122132649.12737-6-pmladek@suse.com
2021-11-22 21:26:49 +08:00
if (bootcon_enabled &&
((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) &&
!keep_bootcon) {
/* We need to iterate through all boot consoles, to make
* sure we print everything out, before we unregister them.
*/
printk/console: Clean up boot console handling in register_console() The variable @bcon has two meanings. It is used several times for iterating the list of registered consoles. In the meantime, it holds the information whether a boot console is first in @console_drivers list. The information about the 1st console driver used to be important for the decision whether to install the new console by default or not. It allowed to re-evaluate the variable @need_default_console when a real console with tty binding has been unregistered in the meantime. The decision about the default console is not longer affected by @bcon variable. The current code checks whether the first driver is real and has tty binding directly. The information about the first console is still used for two more decisions: 1. It prevents duplicate output on non-boot consoles with CON_CONSDEV flag set. 2. Early/boot consoles are unregistered when a real console with CON_CONSDEV is registered and @keep_bootcon is not set. The behavior in the real life is far from obvious. @bcon is set according to the first console @console_drivers list. But the first position in the list is special: 1. Consoles with CON_CONSDEV flag are put at the beginning of the list. It is either the preferred console or any console with tty binding registered by default. 2. Another console might become the first in the list when the first console in the list is unregistered. It might happen either explicitly or automatically when boot consoles are unregistered. There is one more important rule: + Boot consoles can't be registered when any real console is already registered. It is a puzzle. The main complication is the dependency on the first position is the list and the complicated rules around it. Let's try to make it easier: 1. Add variable @bootcon_enabled and set it by iterating all registered consoles. The variable has obvious meaning and more predictable behavior. Any speed optimization and other tricks are not worth it. 2. Use a generic name for the variable that is used to iterate the list on registered console drivers. Behavior change: No, maybe surprisingly, there is _no_ behavior change! Let's provide the proof by contradiction. Both operations, duplicate output prevention and boot consoles removal, are done only when the newly added console has CON_CONSDEV flag set. The behavior would change when the new @bootcon_enabled has different value than the original @bcon. By other words, the behavior would change when the following conditions are true: + a console with CON_CONSDEV flag is added + a real (non-boot) console is the first in the list + a boot console is later in the list Now, a real console might be first in the list only when: + It was the first registered console. In this case, there can't be any boot console because any later ones were rejected. + It was put at the first position because it had CON_CONSDEV flag set. It was either the preferred console or it was a console with tty binding registered by default. We are interested only in a real consoles here. And real console with tty binding fulfills conditions of the default console. Now, there is always only one console that is either preferred or fulfills conditions of the default console. It can't be already in the list and being registered at the same time. As a result, the above three conditions could newer be "true" at the same time. Therefore the behavior can't change. Final dilemma: OK, the new code has the same behavior. But is the change in the right direction? What if the handling of @console_drivers is updated in the future? OK, let's look at it from another angle: 1. The ordering of @console_drivers list is important only in console_device() function. The first console driver with tty binding gets associated with /dev/console. 2. CON_CONSDEV flag is shown in /proc/consoles. And it should be set for the driver that is returned by console_device(). 3. A boot console is removed and the duplicated output is prevented when the real console with CON_CONSDEV flag is registered. Now, in the ideal world: + The driver associated with /dev/console should be either a console preferred via the command line, device tree, or SPCR. Or it should be the first real console with tty binding registered by default. + The code should match the related boot and real console drivers. It should unregister only the obsolete boot driver. And the duplicated output should be prevented only on the related real driver. It is clear that it is not guaranteed by the current code. Instead, the current code looks like a maze of heuristics that try to achieve the above. It is result of adding several features over last few decades. For example, a possibility to register more consoles, unregister consoles, boot consoles, consoles without tty binding, device tree, SPCR, braille consoles. Anyway, there is no reason why the decision, about removing boot consoles and preventing duplicated output, should depend on the first console in the list. The current code does the decisions primary by CON_CONSDEV flag that is used for the preferred console. It looks like a good compromise. And the change seems to be in the right direction. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211122132649.12737-6-pmladek@suse.com
2021-11-22 21:26:49 +08:00
for_each_console(con)
if (con->flags & CON_BOOT)
unregister_console(con);
}
}
EXPORT_SYMBOL(register_console);
int unregister_console(struct console *console)
{
struct console *con;
int res;
pr_info("%sconsole [%s%d] disabled\n",
(console->flags & CON_BOOT) ? "boot" : "" ,
console->name, console->index);
res = _braille_unregister_console(console);
if (res < 0)
return res;
if (res > 0)
return 0;
res = -ENODEV;
console_lock();
if (console_drivers == console) {
console_drivers=console->next;
res = 0;
} else {
for_each_console(con) {
if (con->next == console) {
con->next = console->next;
res = 0;
break;
}
}
}
if (res)
goto out_disable_unlock;
if (console->flags & CON_EXTENDED)
printk: implement support for extended console drivers printk log_buf keeps various metadata for each message including its sequence number and timestamp. The metadata is currently available only through /dev/kmsg and stripped out before passed onto console drivers. We want this metadata to be available to console drivers too so that console consumers can get full information including the metadata and dictionary, which among other things can be used to detect whether messages got lost in transit. This patch implements support for extended console drivers. Consoles can indicate that they want extended messages by setting the new CON_EXTENDED flag and they'll be fed messages formatted the same way as /dev/kmsg. "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" If extended consoles exist, in-kernel fragment assembly is disabled. This ensures that all messages emitted to consoles have full metadata including sequence number. The contflag carries enough information to reassemble the fragments from the reader side trivially. Note that this only affects /dev/kmsg. Regular console and /proc/kmsg outputs are not affected by this change. * Extended message formatting for console drivers is enabled iff there are registered extended consoles. * Comment describing /dev/kmsg message format updated to add missing contflag field and help distinguishing variable from verbatim terms. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: David Miller <davem@davemloft.net> Cc: Kay Sievers <kay@vrfy.org> Reviewed-by: Petr Mladek <pmladek@suse.cz> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:30 +08:00
nr_ext_console_drivers--;
Fixes and cleanups for earlyprintk aka boot console The console subsystem already has an idea of a boot console, using the CON_BOOT flag. The implementation has some flaws though. The major problem is that presence of a boot console makes register_console() ignore any other console devices (unless explicitly specified on the kernel command line). This patch fixes the console selection code to *not* consider a boot console a full-featured one, so the first non-boot console registering will become the default console instead. This way the unregister call for the boot console in the register_console() function actually triggers and the handover from the boot console to the real console device works smoothly. Added a printk for the handover, so you know which console device the output goes to when the boot console stops printing messages. The disable_early_printk() call is obsolete with that patch, explicitly disabling the early console isn't needed any more as it works automagically with that patch. I've walked through the tree, dropped all disable_early_printk() instances found below arch/ and tagged the consoles with CON_BOOT if needed. The code is tested on x86, sh (thanks to Paul) and mips (thanks to Ralf). Changes to last version: Rediffed against -rc3, adapted to mips cleanups by Ralf, fixed "udbg-immortal" cmd line arg on powerpc. Signed-off-by: Gerd Hoffmann <kraxel@exsuse.de> Acked-by: Paul Mundt <lethal@linux-sh.org> Acked-by: Ralf Baechle <ralf@linux-mips.org> Cc: Andi Kleen <ak@suse.de> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:26:49 +08:00
/*
[PATCH] CON_CONSDEV bit not set correctly on last console According to include/linux/console.h, CON_CONSDEV flag should be set on the last console specified on the boot command line: 86 #define CON_PRINTBUFFER (1) 87 #define CON_CONSDEV (2) /* Last on the command line */ 88 #define CON_ENABLED (4) 89 #define CON_BOOT (8) This does not currently happen if there is more than one console specified on the boot commandline. Instead, it gets set on the first console on the command line. This can cause problems for things like kdb that look for the CON_CONSDEV flag to see if the console is valid. Additionaly, it doesn't look like CON_CONSDEV is reassigned to the next preferred console at unregister time if the console being unregistered currently has that bit set. Example (from sn2 ia64): elilo vmlinuz root=<dev> console=ttyS0 console=ttySG0 in this case, the flags on ttySG console struct will be 0x4 (should be 0x6). Attached patch against bk fixes both issues for the cases I looked at. It uses selected_console (which gets incremented for each console specified on the command line) as the indicator of which console to set CON_CONSDEV on. When adding the console to the list, if the previous one had CON_CONSDEV set, it masks it out. Tested on ia64 and x86. The problem with the current behavior is it breaks overriding the default from the boot line. In the ia64 case, there may be a global append line defining console=a in elilo.conf. Then you want to boot your kernel, and want to override the default by passing console=b on the boot line. elilo constructs the kernel cmdline by starting with the value of the global append line, then tacks on whatever else you specify, which puts console=b last. Signed-off-by: Greg Edwards <edwardsg@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:09:05 +08:00
* If this isn't the last console and it has CON_CONSDEV set, we
* need to set it on the next preferred console.
*/
Fixes and cleanups for earlyprintk aka boot console The console subsystem already has an idea of a boot console, using the CON_BOOT flag. The implementation has some flaws though. The major problem is that presence of a boot console makes register_console() ignore any other console devices (unless explicitly specified on the kernel command line). This patch fixes the console selection code to *not* consider a boot console a full-featured one, so the first non-boot console registering will become the default console instead. This way the unregister call for the boot console in the register_console() function actually triggers and the handover from the boot console to the real console device works smoothly. Added a printk for the handover, so you know which console device the output goes to when the boot console stops printing messages. The disable_early_printk() call is obsolete with that patch, explicitly disabling the early console isn't needed any more as it works automagically with that patch. I've walked through the tree, dropped all disable_early_printk() instances found below arch/ and tagged the consoles with CON_BOOT if needed. The code is tested on x86, sh (thanks to Paul) and mips (thanks to Ralf). Changes to last version: Rediffed against -rc3, adapted to mips cleanups by Ralf, fixed "udbg-immortal" cmd line arg on powerpc. Signed-off-by: Gerd Hoffmann <kraxel@exsuse.de> Acked-by: Paul Mundt <lethal@linux-sh.org> Acked-by: Ralf Baechle <ralf@linux-mips.org> Cc: Andi Kleen <ak@suse.de> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:26:49 +08:00
if (console_drivers != NULL && console->flags & CON_CONSDEV)
[PATCH] CON_CONSDEV bit not set correctly on last console According to include/linux/console.h, CON_CONSDEV flag should be set on the last console specified on the boot command line: 86 #define CON_PRINTBUFFER (1) 87 #define CON_CONSDEV (2) /* Last on the command line */ 88 #define CON_ENABLED (4) 89 #define CON_BOOT (8) This does not currently happen if there is more than one console specified on the boot commandline. Instead, it gets set on the first console on the command line. This can cause problems for things like kdb that look for the CON_CONSDEV flag to see if the console is valid. Additionaly, it doesn't look like CON_CONSDEV is reassigned to the next preferred console at unregister time if the console being unregistered currently has that bit set. Example (from sn2 ia64): elilo vmlinuz root=<dev> console=ttyS0 console=ttySG0 in this case, the flags on ttySG console struct will be 0x4 (should be 0x6). Attached patch against bk fixes both issues for the cases I looked at. It uses selected_console (which gets incremented for each console specified on the command line) as the indicator of which console to set CON_CONSDEV on. When adding the console to the list, if the previous one had CON_CONSDEV set, it masks it out. Tested on ia64 and x86. The problem with the current behavior is it breaks overriding the default from the boot line. In the ia64 case, there may be a global append line defining console=a in elilo.conf. Then you want to boot your kernel, and want to override the default by passing console=b on the boot line. elilo constructs the kernel cmdline by starting with the value of the global append line, then tacks on whatever else you specify, which puts console=b last. Signed-off-by: Greg Edwards <edwardsg@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:09:05 +08:00
console_drivers->flags |= CON_CONSDEV;
printk/of_serial: fix serial console cessation part way through boot. Commit 5f5c9ae56c38942623f69c3e6dc6ec78e4da2076 "serial_core: Unregister console in uart_remove_one_port()" fixed a crash where a serial port was removed but not deregistered as a console. There is a side effect of that commit for platforms having serial consoles and of_serial configured (CONFIG_SERIAL_OF_PLATFORM). The serial console is disabled midway through the boot process. This cessation of the serial console affects PowerPC computers such as the MVME5100 and SAM440EP. The sequence is: bootconsole [udbg0] enabled .... serial8250/16550 driver initialises and registers its UARTS, one of these is the serial console. console [ttyS0] enabled .... of_serial probes "platform" devices, registering them as it goes. One of these is the serial console. console [ttyS0] disabled. The disabling of the serial console is due to: a. unregister_console in printk not clearing the CONS_ENABLED bit in the console flags, even though it has announced that the console is disabled; and b. of_platform_serial_probe in of_serial not setting the port type before it registers with serial8250_register_8250_port. This patch ensures that the serial console is re-enabled when of_serial registers a serial port that corresponds to the designated console. Signed-off-by: Stephen Chivers <schivers@csc.com> Tested-by: Stephen Chivers <schivers@csc.com> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> [unregister_console] Cc: stable <stable@vger.kernel.org> # 3.15 === The above failure was identified in Linux-3.15-rc2. Tested using MVME5100 and SAM440EP PowerPC computers with kernels built from Linux-3.15-rc5 and tty-next. The continued operation of the serial console is vital for computers such as the MVME5100 as that Single Board Computer does not have any grapical/display hardware. Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-14 06:04:39 +08:00
console->flags &= ~CON_ENABLED;
console_unlock();
console_sysfs_notify();
if (console->exit)
res = console->exit(console);
return res;
out_disable_unlock:
console->flags &= ~CON_ENABLED;
console_unlock();
return res;
}
EXPORT_SYMBOL(unregister_console);
/*
* Initialize the console device. This is called *early*, so
* we can't necessarily depend on lots of kernel help here.
* Just do some early initializations, and do the complex setup
* later.
*/
void __init console_init(void)
{
int ret;
initcall_t call;
initcall_entry_t *ce;
/* Setup the default TTY line discipline. */
n_tty_init();
/*
* set up the console device so that later boot sequences can
* inform about problems etc..
*/
ce = __con_initcall_start;
trace_initcall_level("console");
while (ce < __con_initcall_end) {
call = initcall_from_entry(ce);
trace_initcall_start(call);
ret = call();
trace_initcall_finish(call, ret);
ce++;
}
}
/*
* Some boot consoles access data that is in the init section and which will
* be discarded after the initcalls have been run. To make sure that no code
* will access this data, unregister the boot consoles in a late initcall.
*
* If for some reason, such as deferred probe or the driver being a loadable
* module, the real console hasn't registered yet at this point, there will
* be a brief interval in which no messages are logged to the console, which
* makes it difficult to diagnose problems that occur during this time.
*
* To mitigate this problem somewhat, only unregister consoles whose memory
printk/console: Always disable boot consoles that use init memory before it is freed Commit 4c30c6f566c0 ("kernel/printk: do not turn off bootconsole in printk_late_init() if keep_bootcon") added a check on keep_bootcon to ensure that boot consoles were kept around until the real console is registered. This can lead to problems if the boot console data and code are in the init section, since it can be freed before the boot console is unregistered. Commit 81cc26f2bd11 ("printk: only unregister boot consoles when necessary") fixed this a better way. It allowed to keep boot consoles that did not use init data. Unfortunately it did not remove the check of keep_bootcon. This can lead to crashes and weird panics when the bootconsole is accessed after free, especially if page poisoning is in use and the code / data have been overwritten with a poison value. To prevent this, always free the boot console if it is within the init section. In addition, print a warning about that the console is removed prematurely. Finally there is a new comment how to avoid the warning. It replaced an explanation that duplicated a more comprehensive function description few lines above. Fixes: 4c30c6f566c0 ("kernel/printk: do not turn off bootconsole in printk_late_init() if keep_bootcon") Link: http://lkml.kernel.org/r/1500036673-7122-2-git-send-email-pmladek@suse.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jiri Slaby <jslaby@suse.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk> Cc: "Fabio M. Di Nitto" <fdinitto@redhat.com> Cc: linux-serial@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Matt Redfearn <matt.redfearn@imgtec.com> [pmladek@suse.com: print the warning, code and comments clean up] Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-07-14 20:51:12 +08:00
* intersects with the init section. Note that all other boot consoles will
* get unregistered when the real preferred console is registered.
*/
printk: fix delayed messages from CPU hotplug events When a secondary CPU is being brought up, it is not uncommon for printk() to be invoked when cpu_online(smp_processor_id()) == 0. The case that I witnessed personally was on MIPS: http://lkml.org/lkml/2010/5/30/4 If (can_use_console() == 0), printk() will spool its output to log_buf and it will be visible in "dmesg", but that output will NOT be echoed to the console until somebody calls release_console_sem() from a CPU that is online. Therefore, the boot time messages from the new CPU can get stuck in "limbo" for a long time, and might suddenly appear on the screen when a completely unrelated event (e.g. "eth0: link is down") occurs. This patch modifies the console code so that any pending messages are automatically flushed out to the console whenever a CPU hotplug operation completes successfully or aborts. The issue was seen on 2.6.34. Original patch by Kevin Cernekee with cleanups by akpm and additional fixes by Santosh Shilimkar. This patch superseeds https://patchwork.linux-mips.org/patch/1357/. Signed-off-by: Kevin Cernekee <cernekee@gmail.com> To: <mingo@elte.hu> To: <akpm@linux-foundation.org> To: <simon.kagstrom@netinsight.net> To: <David.Woodhouse@intel.com> To: <lethal@linux-sh.org> Cc: <linux-kernel@vger.kernel.org> Cc: <linux-mips@linux-mips.org> Reviewed-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Kevin Cernekee <cernekee@gmail.com> Patchwork: https://patchwork.linux-mips.org/patch/1534/ LKML-Reference: <ede63b5a20af951c755736f035d1e787772d7c28@localhost> LKML-Reference: <EAF47CD23C76F840A9E7FCE10091EFAB02C5DB6D1F@dbde02.ent.ti.com> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-06-04 13:11:25 +08:00
static int __init printk_late_init(void)
{
printk: Enable the use of more than one CON_BOOT (early console) Today, register_console() assumes the following usage: - The first console to register with a flag set to CON_BOOT is the one and only bootconsole. - If another register_console() is called with an additional CON_BOOT, it is silently rejected. - As soon as a console without the CON_BOOT set calls registers the bootconsole is automatically unregistered. - Once there is a "real" console - register_console() will silently reject any consoles with it's CON_BOOT flag set. In many systems (alpha, blackfin, microblaze, mips, powerpc, sh, & x86), there are early_printk implementations, which use the CON_BOOT which come out serial ports, vga, usb, & memory buffers. In many embedded systems, it would be nice to have two bootconsoles - in case the primary fails, you always have access to a backup memory buffer - but this requires at least two CON_BOOT consoles... This patch enables that functionality. With the change applied, on boot you get (if you try to re-enable a boot console after the "real" console has been registered): root:/> dmesg | grep console bootconsole [early_shadow0] enabled bootconsole [early_BFuart0] enabled Kernel command line: root=/dev/mtdblock0 rw earlyprintk=serial,uart0,57600 console=ttyBF0,57600 nmi_debug=regs console handover:boot [early_BFuart0] boot [early_shadow0] -> real [ttyBF0] Too late to register bootconsole early_shadow0 or: root:/> dmesg | grep console Kernel command line: root=/dev/mtdblock0 rw console=ttyBF0,57600 console [ttyBF0] enabled Signed-off-by: Robin Getz <rgetz@blackfin.uclinux.org> Cc: "Linus Torvalds" <torvalds@linux-foundation.org> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Mike Frysinger" <vapier.adi@gmail.com> Cc: "Paul Mundt" <lethal@linux-sh.org> LKML-Reference: <200907012108.38030.rgetz@blackfin.uclinux.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 09:08:37 +08:00
struct console *con;
int ret;
printk: Enable the use of more than one CON_BOOT (early console) Today, register_console() assumes the following usage: - The first console to register with a flag set to CON_BOOT is the one and only bootconsole. - If another register_console() is called with an additional CON_BOOT, it is silently rejected. - As soon as a console without the CON_BOOT set calls registers the bootconsole is automatically unregistered. - Once there is a "real" console - register_console() will silently reject any consoles with it's CON_BOOT flag set. In many systems (alpha, blackfin, microblaze, mips, powerpc, sh, & x86), there are early_printk implementations, which use the CON_BOOT which come out serial ports, vga, usb, & memory buffers. In many embedded systems, it would be nice to have two bootconsoles - in case the primary fails, you always have access to a backup memory buffer - but this requires at least two CON_BOOT consoles... This patch enables that functionality. With the change applied, on boot you get (if you try to re-enable a boot console after the "real" console has been registered): root:/> dmesg | grep console bootconsole [early_shadow0] enabled bootconsole [early_BFuart0] enabled Kernel command line: root=/dev/mtdblock0 rw earlyprintk=serial,uart0,57600 console=ttyBF0,57600 nmi_debug=regs console handover:boot [early_BFuart0] boot [early_shadow0] -> real [ttyBF0] Too late to register bootconsole early_shadow0 or: root:/> dmesg | grep console Kernel command line: root=/dev/mtdblock0 rw console=ttyBF0,57600 console [ttyBF0] enabled Signed-off-by: Robin Getz <rgetz@blackfin.uclinux.org> Cc: "Linus Torvalds" <torvalds@linux-foundation.org> Cc: "Andrew Morton" <akpm@linux-foundation.org> Cc: "Mike Frysinger" <vapier.adi@gmail.com> Cc: "Paul Mundt" <lethal@linux-sh.org> LKML-Reference: <200907012108.38030.rgetz@blackfin.uclinux.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 09:08:37 +08:00
for_each_console(con) {
printk/console: Enhance the check for consoles using init memory printk_late_init() is responsible for disabling boot consoles that use init memory. It checks the address of struct console for this. But this is not enough. For example, there are several early consoles that have write() method in the init section and struct console in the normal section. They are not disabled and could cause fancy and hard to debug system states. It is even more complicated by the macros EARLYCON_DECLARE() and OF_EARLYCON_DECLARE() where various struct members are set at runtime by the provided setup() function. I have tried to reproduce this problem and forced the classic uart early console to stay using keep_bootcon parameter. In particular I used earlycon=uart,io,0x3f8 keep_bootcon console=ttyS0,115200. The system did not boot: [ 1.570496] PM: Image not found (code -22) [ 1.570496] PM: Image not found (code -22) [ 1.571886] PM: Hibernation image not present or could not be loaded. [ 1.571886] PM: Hibernation image not present or could not be loaded. [ 1.576407] Freeing unused kernel memory: 2528K [ 1.577244] kernel tried to execute NX-protected page - exploit attempt? (uid: 0) The double lines are caused by having both early uart console and ttyS0 console enabled at the same time. The early console stopped working when the init memory was freed. Fortunately, the invalid call was caught by the NX-protexted page check and did not cause any silent fancy problems. This patch adds a check for many other addresses stored in struct console. It omits setup() and match() that are used only when the console is registered. Therefore they have already been used at this point and there is no reason to use them again. Link: http://lkml.kernel.org/r/1500036673-7122-3-git-send-email-pmladek@suse.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Matt Redfearn <matt.redfearn@imgtec.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jiri Slaby <jslaby@suse.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk> Cc: "Fabio M. Di Nitto" <fdinitto@redhat.com> Cc: linux-serial@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-07-14 20:51:13 +08:00
if (!(con->flags & CON_BOOT))
continue;
/* Check addresses that might be used for enabled consoles. */
if (init_section_intersects(con, sizeof(*con)) ||
init_section_contains(con->write, 0) ||
init_section_contains(con->read, 0) ||
init_section_contains(con->device, 0) ||
init_section_contains(con->unblank, 0) ||
init_section_contains(con->data, 0)) {
/*
printk/console: Always disable boot consoles that use init memory before it is freed Commit 4c30c6f566c0 ("kernel/printk: do not turn off bootconsole in printk_late_init() if keep_bootcon") added a check on keep_bootcon to ensure that boot consoles were kept around until the real console is registered. This can lead to problems if the boot console data and code are in the init section, since it can be freed before the boot console is unregistered. Commit 81cc26f2bd11 ("printk: only unregister boot consoles when necessary") fixed this a better way. It allowed to keep boot consoles that did not use init data. Unfortunately it did not remove the check of keep_bootcon. This can lead to crashes and weird panics when the bootconsole is accessed after free, especially if page poisoning is in use and the code / data have been overwritten with a poison value. To prevent this, always free the boot console if it is within the init section. In addition, print a warning about that the console is removed prematurely. Finally there is a new comment how to avoid the warning. It replaced an explanation that duplicated a more comprehensive function description few lines above. Fixes: 4c30c6f566c0 ("kernel/printk: do not turn off bootconsole in printk_late_init() if keep_bootcon") Link: http://lkml.kernel.org/r/1500036673-7122-2-git-send-email-pmladek@suse.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jiri Slaby <jslaby@suse.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk> Cc: "Fabio M. Di Nitto" <fdinitto@redhat.com> Cc: linux-serial@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Matt Redfearn <matt.redfearn@imgtec.com> [pmladek@suse.com: print the warning, code and comments clean up] Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-07-14 20:51:12 +08:00
* Please, consider moving the reported consoles out
* of the init section.
*/
printk/console: Always disable boot consoles that use init memory before it is freed Commit 4c30c6f566c0 ("kernel/printk: do not turn off bootconsole in printk_late_init() if keep_bootcon") added a check on keep_bootcon to ensure that boot consoles were kept around until the real console is registered. This can lead to problems if the boot console data and code are in the init section, since it can be freed before the boot console is unregistered. Commit 81cc26f2bd11 ("printk: only unregister boot consoles when necessary") fixed this a better way. It allowed to keep boot consoles that did not use init data. Unfortunately it did not remove the check of keep_bootcon. This can lead to crashes and weird panics when the bootconsole is accessed after free, especially if page poisoning is in use and the code / data have been overwritten with a poison value. To prevent this, always free the boot console if it is within the init section. In addition, print a warning about that the console is removed prematurely. Finally there is a new comment how to avoid the warning. It replaced an explanation that duplicated a more comprehensive function description few lines above. Fixes: 4c30c6f566c0 ("kernel/printk: do not turn off bootconsole in printk_late_init() if keep_bootcon") Link: http://lkml.kernel.org/r/1500036673-7122-2-git-send-email-pmladek@suse.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Jiri Slaby <jslaby@suse.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk> Cc: "Fabio M. Di Nitto" <fdinitto@redhat.com> Cc: linux-serial@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Matt Redfearn <matt.redfearn@imgtec.com> [pmladek@suse.com: print the warning, code and comments clean up] Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-07-14 20:51:12 +08:00
pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n",
con->name, con->index);
unregister_console(con);
}
}
ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL,
console_cpu_notify);
WARN_ON(ret < 0);
ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online",
console_cpu_notify, NULL);
WARN_ON(ret < 0);
printk: move printk sysctl to printk/sysctl.c kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move printk sysctl from kernel/sysctl.c to kernel/printk/sysctl.c. Use register_sysctl() to register the sysctl interface. [mcgrof@kernel.org: fixed compile issues when PRINTK is not set, commit log update] Link: https://lkml.kernel.org/r/20211124231435.1445213-6-mcgrof@kernel.org Signed-off-by: Xiaoming Ni <nixiaoming@huawei.com> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Amir Goldstein <amir73il@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Antti Palosaari <crope@iki.fi> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Benjamin LaHaise <bcrl@kvack.org> Cc: Clemens Ladisch <clemens@ladisch.de> Cc: David Airlie <airlied@linux.ie> Cc: Douglas Gilbert <dgilbert@interlog.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Iurii Zaikin <yzaikin@google.com> Cc: James E.J. Bottomley <jejb@linux.ibm.com> Cc: Jani Nikula <jani.nikula@intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Joel Becker <jlbec@evilplan.org> Cc: John Ogness <john.ogness@linutronix.de> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Joseph Qi <joseph.qi@linux.alibaba.com> Cc: Julia Lawall <julia.lawall@inria.fr> Cc: Kees Cook <keescook@chromium.org> Cc: Lukas Middendorf <kernel@tuxforce.de> Cc: Mark Fasheh <mark@fasheh.com> Cc: Martin K. Petersen <martin.petersen@oracle.com> Cc: Paul Turner <pjt@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Phillip Potter <phil@philpotter.co.uk> Cc: Qing Wang <wangqing@vivo.com> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Sebastian Reichel <sre@kernel.org> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Stephen Kitt <steve@sk2.org> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: "Theodore Ts'o" <tytso@mit.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-22 14:12:33 +08:00
printk_sysctl_init();
return 0;
}
printk: fix delayed messages from CPU hotplug events When a secondary CPU is being brought up, it is not uncommon for printk() to be invoked when cpu_online(smp_processor_id()) == 0. The case that I witnessed personally was on MIPS: http://lkml.org/lkml/2010/5/30/4 If (can_use_console() == 0), printk() will spool its output to log_buf and it will be visible in "dmesg", but that output will NOT be echoed to the console until somebody calls release_console_sem() from a CPU that is online. Therefore, the boot time messages from the new CPU can get stuck in "limbo" for a long time, and might suddenly appear on the screen when a completely unrelated event (e.g. "eth0: link is down") occurs. This patch modifies the console code so that any pending messages are automatically flushed out to the console whenever a CPU hotplug operation completes successfully or aborts. The issue was seen on 2.6.34. Original patch by Kevin Cernekee with cleanups by akpm and additional fixes by Santosh Shilimkar. This patch superseeds https://patchwork.linux-mips.org/patch/1357/. Signed-off-by: Kevin Cernekee <cernekee@gmail.com> To: <mingo@elte.hu> To: <akpm@linux-foundation.org> To: <simon.kagstrom@netinsight.net> To: <David.Woodhouse@intel.com> To: <lethal@linux-sh.org> Cc: <linux-kernel@vger.kernel.org> Cc: <linux-mips@linux-mips.org> Reviewed-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Kevin Cernekee <cernekee@gmail.com> Patchwork: https://patchwork.linux-mips.org/patch/1534/ LKML-Reference: <ede63b5a20af951c755736f035d1e787772d7c28@localhost> LKML-Reference: <EAF47CD23C76F840A9E7FCE10091EFAB02C5DB6D1F@dbde02.ent.ti.com> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-06-04 13:11:25 +08:00
late_initcall(printk_late_init);
#if defined CONFIG_PRINTK
/*
* Delayed printk version, for scheduler-internal messages:
*/
#define PRINTK_PENDING_WAKEUP 0x01
printk: remove separate printk_sched buffers and use printk buf instead To prevent deadlocks with doing a printk inside the scheduler, printk_sched() was created. The issue is that printk has a console_sem that it can grab and release. The release does a wake up if there's a task pending on the sem, and this wake up grabs the rq locks that is held in the scheduler. This leads to a possible deadlock if the wake up uses the same rq as the one with the rq lock held already. What printk_sched() does is to save the printk write in a per cpu buffer and sets the PRINTK_PENDING_SCHED flag. On a timer tick, if this flag is set, the printk() is done against the buffer. There's a couple of issues with this approach. 1) If two printk_sched()s are called before the tick, the second one will overwrite the first one. 2) The temporary buffer is 512 bytes and is per cpu. This is a quite a bit of space wasted for something that is seldom used. In order to remove this, the printk_sched() can use the printk buffer instead, and delay the console_trylock()/console_unlock() to the queued work. Because printk_sched() would then be taking the logbuf_lock, the logbuf_lock must not be held while doing anything that may call into the scheduler functions, which includes wake ups. Unfortunately, printk() also has a console_sem that it uses, and on release, the up(&console_sem) may do a wake up of any pending waiters. This must be avoided while holding the logbuf_lock. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:11:38 +08:00
#define PRINTK_PENDING_OUTPUT 0x02
static DEFINE_PER_CPU(int, printk_pending);
static void wake_up_klogd_work_func(struct irq_work *irq_work)
{
int pending = this_cpu_xchg(printk_pending, 0);
printk: remove separate printk_sched buffers and use printk buf instead To prevent deadlocks with doing a printk inside the scheduler, printk_sched() was created. The issue is that printk has a console_sem that it can grab and release. The release does a wake up if there's a task pending on the sem, and this wake up grabs the rq locks that is held in the scheduler. This leads to a possible deadlock if the wake up uses the same rq as the one with the rq lock held already. What printk_sched() does is to save the printk write in a per cpu buffer and sets the PRINTK_PENDING_SCHED flag. On a timer tick, if this flag is set, the printk() is done against the buffer. There's a couple of issues with this approach. 1) If two printk_sched()s are called before the tick, the second one will overwrite the first one. 2) The temporary buffer is 512 bytes and is per cpu. This is a quite a bit of space wasted for something that is seldom used. In order to remove this, the printk_sched() can use the printk buffer instead, and delay the console_trylock()/console_unlock() to the queued work. Because printk_sched() would then be taking the logbuf_lock, the logbuf_lock must not be held while doing anything that may call into the scheduler functions, which includes wake ups. Unfortunately, printk() also has a console_sem that it uses, and on release, the up(&console_sem) may do a wake up of any pending waiters. This must be avoided while holding the logbuf_lock. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:11:38 +08:00
if (pending & PRINTK_PENDING_OUTPUT) {
/* If trylock fails, someone else is doing the printing */
if (console_trylock())
console_unlock();
}
if (pending & PRINTK_PENDING_WAKEUP)
wake_up_interruptible(&log_wait);
}
static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) =
IRQ_WORK_INIT_LAZY(wake_up_klogd_work_func);
void wake_up_klogd(void)
{
printk: queue wake_up_klogd irq_work only if per-CPU areas are ready printk_deferred(), similarly to printk_safe/printk_nmi, does not immediately attempt to print a new message on the consoles, avoiding calls into non-reentrant kernel paths, e.g. scheduler or timekeeping, which potentially can deadlock the system. Those printk() flavors, instead, rely on per-CPU flush irq_work to print messages from safer contexts. For same reasons (recursive scheduler or timekeeping calls) printk() uses per-CPU irq_work in order to wake up user space syslog/kmsg readers. However, only printk_safe/printk_nmi do make sure that per-CPU areas have been initialised and that it's safe to modify per-CPU irq_work. This means that, for instance, should printk_deferred() be invoked "too early", that is before per-CPU areas are initialised, printk_deferred() will perform illegal per-CPU access. Lech Perczak [0] reports that after commit 1b710b1b10ef ("char/random: silence a lockdep splat with printk()") user-space syslog/kmsg readers are not able to read new kernel messages. The reason is printk_deferred() being called too early (as was pointed out by Petr and John). Fix printk_deferred() and do not queue per-CPU irq_work before per-CPU areas are initialized. Link: https://lore.kernel.org/lkml/aa0732c6-5c4e-8a8b-a1c1-75ebe3dca05b@camlintechnologies.com/ Reported-by: Lech Perczak <l.perczak@camlintechnologies.com> Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Tested-by: Jann Horn <jannh@google.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Theodore Ts'o <tytso@mit.edu> Cc: John Ogness <john.ogness@linutronix.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-03 19:30:02 +08:00
if (!printk_percpu_data_ready())
return;
preempt_disable();
if (waitqueue_active(&log_wait)) {
this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
}
preempt_enable();
}
void defer_console_output(void)
{
printk: queue wake_up_klogd irq_work only if per-CPU areas are ready printk_deferred(), similarly to printk_safe/printk_nmi, does not immediately attempt to print a new message on the consoles, avoiding calls into non-reentrant kernel paths, e.g. scheduler or timekeeping, which potentially can deadlock the system. Those printk() flavors, instead, rely on per-CPU flush irq_work to print messages from safer contexts. For same reasons (recursive scheduler or timekeeping calls) printk() uses per-CPU irq_work in order to wake up user space syslog/kmsg readers. However, only printk_safe/printk_nmi do make sure that per-CPU areas have been initialised and that it's safe to modify per-CPU irq_work. This means that, for instance, should printk_deferred() be invoked "too early", that is before per-CPU areas are initialised, printk_deferred() will perform illegal per-CPU access. Lech Perczak [0] reports that after commit 1b710b1b10ef ("char/random: silence a lockdep splat with printk()") user-space syslog/kmsg readers are not able to read new kernel messages. The reason is printk_deferred() being called too early (as was pointed out by Petr and John). Fix printk_deferred() and do not queue per-CPU irq_work before per-CPU areas are initialized. Link: https://lore.kernel.org/lkml/aa0732c6-5c4e-8a8b-a1c1-75ebe3dca05b@camlintechnologies.com/ Reported-by: Lech Perczak <l.perczak@camlintechnologies.com> Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Tested-by: Jann Horn <jannh@google.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Theodore Ts'o <tytso@mit.edu> Cc: John Ogness <john.ogness@linutronix.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-03-03 19:30:02 +08:00
if (!printk_percpu_data_ready())
return;
printk: Use the main logbuf in NMI when logbuf_lock is available The commit 42a0bb3f71383b457a7d ("printk/nmi: generic solution for safe printk in NMI") caused that printk stores messages into a temporary buffer in NMI context. The buffer is per-CPU and therefore the size is rather limited. It works quite well for NMI backtraces. But there are longer logs that might get printed in NMI context, for example, lockdep warnings, ftrace_dump_on_oops. The temporary buffer is used to avoid deadlocks caused by logbuf_lock. Also it is needed to avoid races with the other temporary buffer that is used when PRINTK_SAFE_CONTEXT is entered. But the main buffer can be used in NMI if the lock is available and we did not interrupt PRINTK_SAFE_CONTEXT. The lock is checked using raw_spin_is_locked(). It might cause false negatives when the lock is taken on another CPU and this CPU is in the safe context from other reasons. Note that the safe context is used also to get console semaphore or when calling console drivers. For this reason, we do the check in printk_nmi_enter(). It makes the handling consistent for the entire NMI handler and avoids reshuffling of the messages. The patch also defines special printk context that allows to use printk_deferred() in NMI. Note that we could not flush the messages to the consoles because console drivers might use many other internal locks. The newly created vprintk_deferred() disables the preemption only around the irq work handling. It is needed there to keep the consistency between the two per-CPU variables. But there is no reason to disable preemption around vprintk_emit(). Finally, the patch puts back explicit serialization of the NMI backtraces from different CPUs. It was removed by the commit a9edc88093287183ac934b ("x86/nmi: Perform a safe NMI stack trace on all CPUs"). It was not needed because the flushing of the temporary per-CPU buffers was serialized. Link: http://lkml.kernel.org/r/1493912763-24873-1-git-send-email-pmladek@suse.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Russell King <rack+kernel@arm.linux.org.uk> Cc: Daniel Thompson <daniel.thompson@linaro.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: x86@kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Suggested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-04-20 16:52:31 +08:00
preempt_disable();
this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
preempt_enable();
}
void printk_trigger_flush(void)
{
defer_console_output();
}
int vprintk_deferred(const char *fmt, va_list args)
{
int r;
r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args);
defer_console_output();
return r;
}
printk: Userspace format indexing support We have a number of systems industry-wide that have a subset of their functionality that works as follows: 1. Receive a message from local kmsg, serial console, or netconsole; 2. Apply a set of rules to classify the message; 3. Do something based on this classification (like scheduling a remediation for the machine), rinse, and repeat. As a couple of examples of places we have this implemented just inside Facebook, although this isn't a Facebook-specific problem, we have this inside our netconsole processing (for alarm classification), and as part of our machine health checking. We use these messages to determine fairly important metrics around production health, and it's important that we get them right. While for some kinds of issues we have counters, tracepoints, or metrics with a stable interface which can reliably indicate the issue, in order to react to production issues quickly we need to work with the interface which most kernel developers naturally use when developing: printk. Most production issues come from unexpected phenomena, and as such usually the code in question doesn't have easily usable tracepoints or other counters available for the specific problem being mitigated. We have a number of lines of monitoring defence against problems in production (host metrics, process metrics, service metrics, etc), and where it's not feasible to reliably monitor at another level, this kind of pragmatic netconsole monitoring is essential. As one would expect, monitoring using printk is rather brittle for a number of reasons -- most notably that the message might disappear entirely in a new version of the kernel, or that the message may change in some way that the regex or other classification methods start to silently fail. One factor that makes this even harder is that, under normal operation, many of these messages are never expected to be hit. For example, there may be a rare hardware bug which one wants to detect if it was to ever happen again, but its recurrence is not likely or anticipated. This precludes using something like checking whether the printk in question was printed somewhere fleetwide recently to determine whether the message in question is still present or not, since we don't anticipate that it should be printed anywhere, but still need to monitor for its future presence in the long-term. This class of issue has happened on a number of occasions, causing unhealthy machines with hardware issues to remain in production for longer than ideal. As a recent example, some monitoring around blk_update_request fell out of date and caused semi-broken machines to remain in production for longer than would be desirable. Searching through the codebase to find the message is also extremely fragile, because many of the messages are further constructed beyond their callsite (eg. btrfs_printk and other module-specific wrappers, each with their own functionality). Even if they aren't, guessing the format and formulation of the underlying message based on the aesthetics of the message emitted is not a recipe for success at scale, and our previous issues with fleetwide machine health checking demonstrate as much. This provides a solution to the issue of silently changed or deleted printks: we record pointers to all printk format strings known at compile time into a new .printk_index section, both in vmlinux and modules. At runtime, this can then be iterated by looking at <debugfs>/printk/index/<module>, which emits the following format, both readable by humans and able to be parsed by machines: $ head -1 vmlinux; shuf -n 5 vmlinux # <level[,flags]> filename:line function "format" <5> block/blk-settings.c:661 disk_stack_limits "%s: Warning: Device %s is misaligned\n" <4> kernel/trace/trace.c:8296 trace_create_file "Could not create tracefs '%s' entry\n" <6> arch/x86/kernel/hpet.c:144 _hpet_print_config "hpet: %s(%d):\n" <6> init/do_mounts.c:605 prepare_namespace "Waiting for root device %s...\n" <6> drivers/acpi/osl.c:1410 acpi_no_auto_serialize_setup "ACPI: auto-serialization disabled\n" This mitigates the majority of cases where we have a highly-specific printk which we want to match on, as we can now enumerate and check whether the format changed or the printk callsite disappeared entirely in userspace. This allows us to catch changes to printks we monitor earlier and decide what to do about it before it becomes problematic. There is no additional runtime cost for printk callers or printk itself, and the assembly generated is exactly the same. Signed-off-by: Chris Down <chris@chrisdown.name> Cc: Petr Mladek <pmladek@suse.com> Cc: Jessica Yu <jeyu@kernel.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: John Ogness <john.ogness@linutronix.de> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kees Cook <keescook@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Tested-by: Petr Mladek <pmladek@suse.com> Reported-by: kernel test robot <lkp@intel.com> Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com> Acked-by: Jessica Yu <jeyu@kernel.org> # for module.{c,h} Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/e42070983637ac5e384f17fbdbe86d19c7b212a5.1623775748.git.chris@chrisdown.name
2021-06-16 00:52:53 +08:00
int _printk_deferred(const char *fmt, ...)
printk: Use the main logbuf in NMI when logbuf_lock is available The commit 42a0bb3f71383b457a7d ("printk/nmi: generic solution for safe printk in NMI") caused that printk stores messages into a temporary buffer in NMI context. The buffer is per-CPU and therefore the size is rather limited. It works quite well for NMI backtraces. But there are longer logs that might get printed in NMI context, for example, lockdep warnings, ftrace_dump_on_oops. The temporary buffer is used to avoid deadlocks caused by logbuf_lock. Also it is needed to avoid races with the other temporary buffer that is used when PRINTK_SAFE_CONTEXT is entered. But the main buffer can be used in NMI if the lock is available and we did not interrupt PRINTK_SAFE_CONTEXT. The lock is checked using raw_spin_is_locked(). It might cause false negatives when the lock is taken on another CPU and this CPU is in the safe context from other reasons. Note that the safe context is used also to get console semaphore or when calling console drivers. For this reason, we do the check in printk_nmi_enter(). It makes the handling consistent for the entire NMI handler and avoids reshuffling of the messages. The patch also defines special printk context that allows to use printk_deferred() in NMI. Note that we could not flush the messages to the consoles because console drivers might use many other internal locks. The newly created vprintk_deferred() disables the preemption only around the irq work handling. It is needed there to keep the consistency between the two per-CPU variables. But there is no reason to disable preemption around vprintk_emit(). Finally, the patch puts back explicit serialization of the NMI backtraces from different CPUs. It was removed by the commit a9edc88093287183ac934b ("x86/nmi: Perform a safe NMI stack trace on all CPUs"). It was not needed because the flushing of the temporary per-CPU buffers was serialized. Link: http://lkml.kernel.org/r/1493912763-24873-1-git-send-email-pmladek@suse.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Russell King <rack+kernel@arm.linux.org.uk> Cc: Daniel Thompson <daniel.thompson@linaro.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: x86@kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Suggested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-04-20 16:52:31 +08:00
{
va_list args;
int r;
va_start(args, fmt);
r = vprintk_deferred(fmt, args);
va_end(args);
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)
{
unsigned long elapsed = jiffies - *caller_jiffies;
if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs))
return false;
*caller_jiffies = jiffies;
return true;
}
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);
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
static bool always_kmsg_dump;
module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR);
const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason)
{
switch (reason) {
case KMSG_DUMP_PANIC:
return "Panic";
case KMSG_DUMP_OOPS:
return "Oops";
case KMSG_DUMP_EMERG:
return "Emergency";
case KMSG_DUMP_SHUTDOWN:
return "Shutdown";
default:
return "Unknown";
}
}
EXPORT_SYMBOL_GPL(kmsg_dump_reason_str);
/**
* 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;
rcu_read_lock();
list_for_each_entry_rcu(dumper, &dump_list, list) {
enum kmsg_dump_reason max_reason = dumper->max_reason;
/*
* If client has not provided a specific max_reason, default
* to KMSG_DUMP_OOPS, unless always_kmsg_dump was set.
*/
if (max_reason == KMSG_DUMP_UNDEF) {
max_reason = always_kmsg_dump ? KMSG_DUMP_MAX :
KMSG_DUMP_OOPS;
}
if (reason > max_reason)
continue;
/* invoke dumper which will iterate over records */
dumper->dump(dumper, reason);
}
rcu_read_unlock();
}
/**
* kmsg_dump_get_line - retrieve one kmsg log line
* @iter: kmsg dump iterator
* @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_dump_iter *iter, bool syslog,
char *line, size_t size, size_t *len)
{
u64 min_seq = latched_seq_read_nolock(&clear_seq);
struct printk_info info;
unsigned int line_count;
struct printk_record r;
size_t l = 0;
bool ret = false;
if (iter->cur_seq < min_seq)
iter->cur_seq = min_seq;
prb_rec_init_rd(&r, &info, line, size);
/* Read text or count text lines? */
if (line) {
if (!prb_read_valid(prb, iter->cur_seq, &r))
goto out;
l = record_print_text(&r, syslog, printk_time);
} else {
if (!prb_read_valid_info(prb, iter->cur_seq,
&info, &line_count)) {
goto out;
}
l = get_record_print_text_size(&info, line_count, syslog,
printk_time);
}
iter->cur_seq = r.info->seq + 1;
ret = true;
out:
if (len)
*len = l;
return ret;
}
EXPORT_SYMBOL_GPL(kmsg_dump_get_line);
/**
* kmsg_dump_get_buffer - copy kmsg log lines
* @iter: kmsg dump iterator
* @syslog: include the "<4>" prefixes
* @buf: buffer to copy the line to
* @size: maximum size of the buffer
* @len_out: length of line placed into buffer
*
* Start at the end of the kmsg buffer and fill the provided buffer
* with as many of 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_dump_iter *iter, bool syslog,
char *buf, size_t size, size_t *len_out)
{
u64 min_seq = latched_seq_read_nolock(&clear_seq);
struct printk_info info;
struct printk_record r;
u64 seq;
u64 next_seq;
size_t len = 0;
bool ret = false;
bool time = printk_time;
if (!buf || !size)
goto out;
if (iter->cur_seq < min_seq)
iter->cur_seq = min_seq;
if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) {
if (info.seq != iter->cur_seq) {
/* messages are gone, move to first available one */
iter->cur_seq = info.seq;
}
}
/* last entry */
if (iter->cur_seq >= iter->next_seq)
goto out;
/*
* Find first record that fits, including all following records,
* into the user-provided buffer for this dump. Pass in size-1
* because this function (by way of record_print_text()) will
* not write more than size-1 bytes of text into @buf.
*/
seq = find_first_fitting_seq(iter->cur_seq, iter->next_seq,
size - 1, syslog, time);
/*
* Next kmsg_dump_get_buffer() invocation will dump block of
* older records stored right before this one.
*/
next_seq = seq;
prb_rec_init_rd(&r, &info, buf, size);
len = 0;
prb_for_each_record(seq, prb, seq, &r) {
if (r.info->seq >= iter->next_seq)
break;
len += record_print_text(&r, syslog, time);
/* Adjust record to store to remaining buffer space. */
prb_rec_init_rd(&r, &info, buf + len, size - len);
}
iter->next_seq = next_seq;
ret = true;
out:
if (len_out)
*len_out = len;
return ret;
}
EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer);
/**
* kmsg_dump_rewind - reset the iterator
* @iter: kmsg dump iterator
*
* 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_dump_iter *iter)
{
iter->cur_seq = latched_seq_read_nolock(&clear_seq);
iter->next_seq = prb_next_seq(prb);
}
EXPORT_SYMBOL_GPL(kmsg_dump_rewind);
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
#endif
#ifdef CONFIG_SMP
static atomic_t printk_cpulock_owner = ATOMIC_INIT(-1);
static atomic_t printk_cpulock_nested = ATOMIC_INIT(0);
/**
* __printk_wait_on_cpu_lock() - Busy wait until the printk cpu-reentrant
* spinning lock is not owned by any CPU.
*
* Context: Any context.
*/
void __printk_wait_on_cpu_lock(void)
{
do {
cpu_relax();
} while (atomic_read(&printk_cpulock_owner) != -1);
}
EXPORT_SYMBOL(__printk_wait_on_cpu_lock);
/**
* __printk_cpu_trylock() - Try to acquire the printk cpu-reentrant
* spinning lock.
*
* If no processor has the lock, the calling processor takes the lock and
* becomes the owner. If the calling processor is already the owner of the
* lock, this function succeeds immediately.
*
* Context: Any context. Expects interrupts to be disabled.
* Return: 1 on success, otherwise 0.
*/
int __printk_cpu_trylock(void)
{
int cpu;
int old;
cpu = smp_processor_id();
/*
* Guarantee loads and stores from this CPU when it is the lock owner
* are _not_ visible to the previous lock owner. This pairs with
* __printk_cpu_unlock:B.
*
* Memory barrier involvement:
*
* If __printk_cpu_trylock:A reads from __printk_cpu_unlock:B, then
* __printk_cpu_unlock:A can never read from __printk_cpu_trylock:B.
*
* Relies on:
*
* RELEASE from __printk_cpu_unlock:A to __printk_cpu_unlock:B
* of the previous CPU
* matching
* ACQUIRE from __printk_cpu_trylock:A to __printk_cpu_trylock:B
* of this CPU
*/
old = atomic_cmpxchg_acquire(&printk_cpulock_owner, -1,
cpu); /* LMM(__printk_cpu_trylock:A) */
if (old == -1) {
/*
* This CPU is now the owner and begins loading/storing
* data: LMM(__printk_cpu_trylock:B)
*/
return 1;
} else if (old == cpu) {
/* This CPU is already the owner. */
atomic_inc(&printk_cpulock_nested);
return 1;
}
return 0;
}
EXPORT_SYMBOL(__printk_cpu_trylock);
/**
* __printk_cpu_unlock() - Release the printk cpu-reentrant spinning lock.
*
* The calling processor must be the owner of the lock.
*
* Context: Any context. Expects interrupts to be disabled.
*/
void __printk_cpu_unlock(void)
{
if (atomic_read(&printk_cpulock_nested)) {
atomic_dec(&printk_cpulock_nested);
return;
}
/*
* This CPU is finished loading/storing data:
* LMM(__printk_cpu_unlock:A)
*/
/*
* Guarantee loads and stores from this CPU when it was the
* lock owner are visible to the next lock owner. This pairs
* with __printk_cpu_trylock:A.
*
* Memory barrier involvement:
*
* If __printk_cpu_trylock:A reads from __printk_cpu_unlock:B,
* then __printk_cpu_trylock:B reads from __printk_cpu_unlock:A.
*
* Relies on:
*
* RELEASE from __printk_cpu_unlock:A to __printk_cpu_unlock:B
* of this CPU
* matching
* ACQUIRE from __printk_cpu_trylock:A to __printk_cpu_trylock:B
* of the next CPU
*/
atomic_set_release(&printk_cpulock_owner,
-1); /* LMM(__printk_cpu_unlock:B) */
}
EXPORT_SYMBOL(__printk_cpu_unlock);
#endif /* CONFIG_SMP */