From 98587c2d894c34c9af5cd84ca169e1cd493aa692 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Tue, 30 Apr 2019 12:33:45 +0200 Subject: s390: simplify disabled_wait The disabled_wait() function uses its argument as the PSW address when it stops the CPU with a wait PSW that is disabled for interrupts. The different callers sometimes use a specific number like 0xdeadbeef to indicate a specific failure, the early boot code uses 0 and some other calls sites use __builtin_return_address(0). At the time a dump is created the current PSW and the registers of a CPU are written to lowcore to make them avaiable to the dump analysis tool. For a CPU stopped with disabled_wait the PSW and the registers do not really make sense together, the PSW address does not point to the function the registers belong to. Simplify disabled_wait() by using _THIS_IP_ for the PSW address and drop the argument to the function. Signed-off-by: Martin Schwidefsky --- kernel/panic.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'kernel/panic.c') diff --git a/kernel/panic.c b/kernel/panic.c index 0ae0d7332f12..c1fcaad337b7 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -318,12 +318,7 @@ void panic(const char *fmt, ...) } #endif #if defined(CONFIG_S390) - { - unsigned long caller; - - caller = (unsigned long)__builtin_return_address(0); - disabled_wait(caller); - } + disabled_wait(); #endif pr_emerg("---[ end Kernel panic - not syncing: %s ]---\n", buf); local_irq_enable(); -- cgit v1.2.3 From c39ea0b9dd24bf1bf2baa5cdbfa1905f3065347b Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Tue, 14 May 2019 15:45:34 -0700 Subject: 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: 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 Suggested-by: Petr Mladek Reviewed-by: Petr Mladek Acked-by: Steven Rostedt (VMware) Acked-by: Sergey Senozhatsky Cc: Thomas Gleixner Cc: Kees Cook Cc: Borislav Petkov Cc: Andi Kleen Cc: Peter Zijlstra Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: Sasha Levin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/tty/sysrq.c | 6 ++++++ include/linux/printk.h | 2 ++ kernel/panic.c | 3 +++ kernel/printk/printk.c | 10 ++++++++++ 4 files changed, 21 insertions(+) (limited to 'kernel/panic.c') diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 59e82e6d776d..573b2055173c 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -527,8 +527,12 @@ void __handle_sysrq(int key, bool check_mask) { struct sysrq_key_op *op_p; int orig_log_level; + int orig_suppress_printk; int i; + orig_suppress_printk = suppress_printk; + suppress_printk = 0; + rcu_sysrq_start(); rcu_read_lock(); /* @@ -574,6 +578,8 @@ void __handle_sysrq(int key, bool check_mask) } rcu_read_unlock(); rcu_sysrq_end(); + + suppress_printk = orig_suppress_printk; } void handle_sysrq(int key) diff --git a/include/linux/printk.h b/include/linux/printk.h index 84ea4d094af3..cefd374c47b1 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -82,6 +82,8 @@ static inline void console_verbose(void) extern char devkmsg_log_str[]; struct ctl_table; +extern int suppress_printk; + struct va_format { const char *fmt; va_list *va; diff --git a/kernel/panic.c b/kernel/panic.c index c1fcaad337b7..a6145050a8da 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -321,6 +321,9 @@ void panic(const char *fmt, ...) disabled_wait(); #endif pr_emerg("---[ end Kernel panic - not syncing: %s ]---\n", buf); + + /* Do not scroll important messages printed above */ + suppress_printk = 1; local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 02ca827b8fac..17102fd4c136 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -86,6 +86,12 @@ static DEFINE_SEMAPHORE(console_sem); struct console *console_drivers; EXPORT_SYMBOL_GPL(console_drivers); +/* + * System may need to suppress printk message under certain + * circumstances, like after kernel panic happens. + */ +int __read_mostly suppress_printk; + #ifdef CONFIG_LOCKDEP static struct lockdep_map console_lock_dep_map = { .name = "console_lock" @@ -1943,6 +1949,10 @@ asmlinkage int vprintk_emit(int facility, int level, unsigned long flags; u64 curr_log_seq; + /* Suppress unimportant messages after panic happens */ + if (unlikely(suppress_printk)) + return 0; + if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; in_sched = true; -- cgit v1.2.3 From b287a25a7148a89d977c819c1f7d6584f875b682 Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Tue, 14 May 2019 15:45:37 -0700 Subject: panic/reboot: allow specifying reboot_mode for panic only Allow specifying reboot_mode for panic only. This is needed on systems where ramoops is used to store panic logs, and user wants to use warm reset to preserve those, while still having cold reset on normal reboots. Link: http://lkml.kernel.org/r/20190322004735.27702-1-aaro.koskinen@iki.fi Signed-off-by: Aaro Koskinen Reviewed-by: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 4 +++- include/linux/reboot.h | 2 ++ kernel/panic.c | 2 ++ kernel/reboot.c | 20 +++++++++++++++----- 4 files changed, 22 insertions(+), 6 deletions(-) (limited to 'kernel/panic.c') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 5be4d3ff5e70..80e40de446c0 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4064,7 +4064,9 @@ [[,]s[mp]#### \ [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \ [[,]f[orce] - Where reboot_mode is one of warm (soft) or cold (hard) or gpio, + Where reboot_mode is one of warm (soft) or cold (hard) or gpio + (prefix with 'panic_' to set mode for panic + reboot only), reboot_type is one of bios, acpi, kbd, triple, efi, or pci, reboot_force is either force or not specified, reboot_cpu is s[mp]#### with #### being the processor diff --git a/include/linux/reboot.h b/include/linux/reboot.h index e63799a6e895..3734cd8f38a8 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -14,6 +14,7 @@ struct device; #define SYS_POWER_OFF 0x0003 /* Notify of system power off */ enum reboot_mode { + REBOOT_UNDEFINED = -1, REBOOT_COLD = 0, REBOOT_WARM, REBOOT_HARD, @@ -21,6 +22,7 @@ enum reboot_mode { REBOOT_GPIO, }; extern enum reboot_mode reboot_mode; +extern enum reboot_mode panic_reboot_mode; enum reboot_type { BOOT_TRIPLE = 't', diff --git a/kernel/panic.c b/kernel/panic.c index a6145050a8da..8779d64bace0 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -306,6 +306,8 @@ void panic(const char *fmt, ...) * shutting down. But if there is a chance of * rebooting the system it will be rebooted. */ + if (panic_reboot_mode != REBOOT_UNDEFINED) + reboot_mode = panic_reboot_mode; emergency_restart(); } #ifdef __sparc__ diff --git a/kernel/reboot.c b/kernel/reboot.c index e1b79b6a2735..b9e79e8c7226 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -31,6 +31,7 @@ EXPORT_SYMBOL(cad_pid); #define DEFAULT_REBOOT_MODE #endif enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE; +enum reboot_mode panic_reboot_mode = REBOOT_UNDEFINED; /* * This variable is used privately to keep track of whether or not @@ -519,6 +520,8 @@ EXPORT_SYMBOL_GPL(orderly_reboot); static int __init reboot_setup(char *str) { for (;;) { + enum reboot_mode *mode; + /* * Having anything passed on the command line via * reboot= will cause us to disable DMI checking @@ -526,17 +529,24 @@ static int __init reboot_setup(char *str) */ reboot_default = 0; + if (!strncmp(str, "panic_", 6)) { + mode = &panic_reboot_mode; + str += 6; + } else { + mode = &reboot_mode; + } + switch (*str) { case 'w': - reboot_mode = REBOOT_WARM; + *mode = REBOOT_WARM; break; case 'c': - reboot_mode = REBOOT_COLD; + *mode = REBOOT_COLD; break; case 'h': - reboot_mode = REBOOT_HARD; + *mode = REBOOT_HARD; break; case 's': @@ -553,11 +563,11 @@ static int __init reboot_setup(char *str) if (rc) return rc; } else - reboot_mode = REBOOT_SOFT; + *mode = REBOOT_SOFT; break; } case 'g': - reboot_mode = REBOOT_GPIO; + *mode = REBOOT_GPIO; break; case 'b': -- cgit v1.2.3 From de6da1e8bcf0dd2058b950b127491821207679dc Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Fri, 17 May 2019 14:31:50 -0700 Subject: panic: add an option to replay all the printk message in buffer Currently on panic, kernel will lower the loglevel and print out pending printk msg only with console_flush_on_panic(). Add an option for users to configure the "panic_print" to replay all dmesg in buffer, some of which they may have never seen due to the loglevel setting, which will help panic debugging . [feng.tang@intel.com: keep the original console_flush_on_panic() inside panic()] Link: http://lkml.kernel.org/r/1556199137-14163-1-git-send-email-feng.tang@intel.com [feng.tang@intel.com: use logbuf lock to protect the console log index] Link: http://lkml.kernel.org/r/1556269868-22654-1-git-send-email-feng.tang@intel.com Link: http://lkml.kernel.org/r/1556095872-36838-1-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang Reviewed-by: Petr Mladek Cc: Aaro Koskinen Cc: Petr Mladek Cc: Steven Rostedt Cc: Sergey Senozhatsky Cc: Kees Cook Cc: Borislav Petkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 1 + arch/powerpc/kernel/traps.c | 2 +- include/linux/console.h | 7 ++++++- kernel/panic.c | 6 +++++- kernel/printk/printk.c | 12 +++++++++++- 5 files changed, 24 insertions(+), 4 deletions(-) (limited to 'kernel/panic.c') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 52e6fbb042cc..138f6664b2e2 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3212,6 +3212,7 @@ bit 2: print timer info bit 3: print locks info if CONFIG_LOCKDEP is on bit 4: print ftrace buffer + bit 5: print all printk messages in buffer panic_on_warn panic() instead of WARN(). Useful to cause kdump on a WARN(). diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 665f294725cb..83e59fdaa62d 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -179,7 +179,7 @@ extern void panic_flush_kmsg_end(void) kmsg_dump(KMSG_DUMP_PANIC); bust_spinlocks(0); debug_locks_off(); - console_flush_on_panic(); + console_flush_on_panic(CONSOLE_FLUSH_PENDING); } static unsigned long oops_begin(struct pt_regs *regs) diff --git a/include/linux/console.h b/include/linux/console.h index ec9bdb3d7bab..d09951d5a94e 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -166,6 +166,11 @@ struct console { extern int console_set_on_cmdline; extern struct console *early_console; +enum con_flush_mode { + CONSOLE_FLUSH_PENDING, + CONSOLE_REPLAY_ALL, +}; + extern int add_preferred_console(char *name, int idx, char *options); extern void register_console(struct console *); extern int unregister_console(struct console *); @@ -175,7 +180,7 @@ extern int console_trylock(void); extern void console_unlock(void); extern void console_conditional_schedule(void); extern void console_unblank(void); -extern void console_flush_on_panic(void); +extern void console_flush_on_panic(enum con_flush_mode mode); extern struct tty_driver *console_device(int *); extern void console_stop(struct console *); extern void console_start(struct console *); diff --git a/kernel/panic.c b/kernel/panic.c index 8779d64bace0..b4543a31a495 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -51,6 +51,7 @@ EXPORT_SYMBOL_GPL(panic_timeout); #define PANIC_PRINT_TIMER_INFO 0x00000004 #define PANIC_PRINT_LOCK_INFO 0x00000008 #define PANIC_PRINT_FTRACE_INFO 0x00000010 +#define PANIC_PRINT_ALL_PRINTK_MSG 0x00000020 unsigned long panic_print; ATOMIC_NOTIFIER_HEAD(panic_notifier_list); @@ -134,6 +135,9 @@ EXPORT_SYMBOL(nmi_panic); static void panic_print_sys_info(void) { + if (panic_print & PANIC_PRINT_ALL_PRINTK_MSG) + console_flush_on_panic(CONSOLE_REPLAY_ALL); + if (panic_print & PANIC_PRINT_TASK_INFO) show_state(); @@ -277,7 +281,7 @@ void panic(const char *fmt, ...) * panic() is not being callled from OOPS. */ debug_locks_off(); - console_flush_on_panic(); + console_flush_on_panic(CONSOLE_FLUSH_PENDING); panic_print_sys_info(); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 17102fd4c136..a6e06fe38e41 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2535,10 +2535,11 @@ void console_unblank(void) /** * console_flush_on_panic - flush console content on panic + * @mode: flush all messages in buffer or just the pending ones * * Immediately output all pending messages no matter what. */ -void console_flush_on_panic(void) +void console_flush_on_panic(enum con_flush_mode mode) { /* * If someone else is holding the console lock, trylock will fail @@ -2549,6 +2550,15 @@ void console_flush_on_panic(void) */ console_trylock(); console_may_schedule = 0; + + if (mode == CONSOLE_REPLAY_ALL) { + unsigned long flags; + + logbuf_lock_irqsave(flags); + console_seq = log_first_seq; + console_idx = log_first_idx; + logbuf_unlock_irqrestore(flags); + } console_unlock(); } -- cgit v1.2.3