From c7c3f05e341a9a2bd1a92993d4f996cfd6e7348e Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 25 Oct 2018 19:10:36 +0900 Subject: panic: avoid deadlocks in re-entrant console drivers From printk()/serial console point of view panic() is special, because it may force CPU to re-enter printk() or/and serial console driver. Therefore, some of serial consoles drivers are re-entrant. E.g. 8250: serial8250_console_write() { if (port->sysrq) locked = 0; else if (oops_in_progress) locked = spin_trylock_irqsave(&port->lock, flags); else spin_lock_irqsave(&port->lock, flags); ... } panic() does set oops_in_progress via bust_spinlocks(1), so in theory we should be able to re-enter serial console driver from panic(): CPU0 uart_console_write() serial8250_console_write() // if (oops_in_progress) // spin_trylock_irqsave() call_console_drivers() console_unlock() console_flush_on_panic() bust_spinlocks(1) // oops_in_progress++ panic() spin_lock_irqsave(&port->lock, flags) // spin_lock_irqsave() serial8250_console_write() call_console_drivers() console_unlock() printk() ... However, this does not happen and we deadlock in serial console on port->lock spinlock. And the problem is that console_flush_on_panic() called after bust_spinlocks(0): void panic(const char *fmt, ...) { bust_spinlocks(1); ... bust_spinlocks(0); console_flush_on_panic(); ... } bust_spinlocks(0) decrements oops_in_progress, so oops_in_progress can go back to zero. Thus even re-entrant console drivers will simply spin on port->lock spinlock. Given that port->lock may already be locked either by a stopped CPU, or by the very same CPU we execute panic() on (for instance, NMI panic() on printing CPU) the system deadlocks and does not reboot. Fix this by removing bust_spinlocks(0), so oops_in_progress is always set in panic() now and, thus, re-entrant console drivers will trylock the port->lock instead of spinning on it forever, when we call them from console_flush_on_panic(). Link: http://lkml.kernel.org/r/20181025101036.6823-1-sergey.senozhatsky@gmail.com Cc: Steven Rostedt Cc: Daniel Wang Cc: Peter Zijlstra Cc: Andrew Morton Cc: Linus Torvalds Cc: Greg Kroah-Hartman Cc: Alan Cox Cc: Jiri Slaby Cc: Peter Feiner Cc: linux-serial@vger.kernel.org Cc: Sergey Senozhatsky Cc: stable@vger.kernel.org Signed-off-by: Sergey Senozhatsky Signed-off-by: Petr Mladek --- kernel/panic.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel/panic.c') diff --git a/kernel/panic.c b/kernel/panic.c index 8b2e002d52eb..6a6df23acd1a 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -233,7 +234,10 @@ void panic(const char *fmt, ...) if (_crash_kexec_post_notifiers) __crash_kexec(NULL); - bust_spinlocks(0); +#ifdef CONFIG_VT + unblank_screen(); +#endif + console_unblank(); /* * We may have ended up stopping the CPU holding the lock (in -- cgit v1.3-7-g2ca7 From d999bd9392dea7c1a9ac43b8680b22c4425ae4c7 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Thu, 3 Jan 2019 15:28:17 -0800 Subject: panic: add options to print system info when panic happens Kernel panic issues are always painful to debug, partially because it's not easy to get enough information of the context when panic happens. And we have ramoops and kdump for that, while this commit tries to provide a easier way to show the system info by adding a cmdline parameter, referring some idea from sysrq handler. Link: http://lkml.kernel.org/r/1543398842-19295-2-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang Reviewed-by: Kees Cook Acked-by: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: John Stultz Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 8 +++++++ kernel/panic.c | 28 +++++++++++++++++++++++++ 2 files changed, 36 insertions(+) (limited to 'kernel/panic.c') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 408781ee142c..e7b5c49702bb 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3092,6 +3092,14 @@ timeout < 0: reboot immediately Format: + panic_print= Bitmask for printing system info when panic happens. + User can chose combination of the following bits: + bit 0: print all tasks info + bit 1: print system memory info + bit 2: print timer info + bit 3: print locks info if CONFIG_LOCKDEP is on + bit 4: print ftrace buffer + panic_on_warn panic() instead of WARN(). Useful to cause kdump on a WARN(). diff --git a/kernel/panic.c b/kernel/panic.c index d10c340c43b0..855f66738bc7 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -46,6 +46,13 @@ int panic_on_warn __read_mostly; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); +#define PANIC_PRINT_TASK_INFO 0x00000001 +#define PANIC_PRINT_MEM_INFO 0x00000002 +#define PANIC_PRINT_TIMER_INFO 0x00000004 +#define PANIC_PRINT_LOCK_INFO 0x00000008 +#define PANIC_PRINT_FTRACE_INFO 0x00000010 +static unsigned long panic_print; + ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); @@ -125,6 +132,24 @@ void nmi_panic(struct pt_regs *regs, const char *msg) } EXPORT_SYMBOL(nmi_panic); +static void panic_print_sys_info(void) +{ + if (panic_print & PANIC_PRINT_TASK_INFO) + show_state(); + + if (panic_print & PANIC_PRINT_MEM_INFO) + show_mem(0, NULL); + + if (panic_print & PANIC_PRINT_TIMER_INFO) + sysrq_timer_list_show(); + + if (panic_print & PANIC_PRINT_LOCK_INFO) + debug_show_all_locks(); + + if (panic_print & PANIC_PRINT_FTRACE_INFO) + ftrace_dump(DUMP_ALL); +} + /** * panic - halt the system * @fmt: The text string to print @@ -254,6 +279,8 @@ void panic(const char *fmt, ...) debug_locks_off(); console_flush_on_panic(); + panic_print_sys_info(); + if (!panic_blink) panic_blink = no_blink; @@ -658,6 +685,7 @@ void refcount_error_report(struct pt_regs *regs, const char *err) #endif core_param(panic, panic_timeout, int, 0644); +core_param(panic_print, panic_print, ulong, 0644); core_param(pause_on_oops, pause_on_oops, int, 0644); core_param(panic_on_warn, panic_on_warn, int, 0644); core_param(crash_kexec_post_notifiers, crash_kexec_post_notifiers, bool, 0644); -- cgit v1.3-7-g2ca7 From 81c9d43f94870be66146739c6e61df40dc17bb64 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Thu, 3 Jan 2019 15:28:20 -0800 Subject: kernel/sysctl: add panic_print into sysctl So that we can also runtime chose to print out the needed system info for panic, other than setting the kernel cmdline. Link: http://lkml.kernel.org/r/1543398842-19295-3-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang Suggested-by: Steven Rostedt Acked-by: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: John Stultz Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/kernel.txt | 17 +++++++++++++++++ include/linux/kernel.h | 1 + include/uapi/linux/sysctl.h | 1 + kernel/panic.c | 2 +- kernel/sysctl.c | 7 +++++++ kernel/sysctl_binary.c | 1 + 6 files changed, 28 insertions(+), 1 deletion(-) (limited to 'kernel/panic.c') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 1b8775298cf7..c0527d8a468a 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -60,6 +60,7 @@ show up in /proc/sys/kernel: - panic_on_stackoverflow - panic_on_unrecovered_nmi - panic_on_warn +- panic_print - panic_on_rcu_stall - perf_cpu_time_max_percent - perf_event_paranoid @@ -654,6 +655,22 @@ a kernel rebuild when attempting to kdump at the location of a WARN(). ============================================================== +panic_print: + +Bitmask for printing system info when panic happens. User can chose +combination of the following bits: + +bit 0: print all tasks info +bit 1: print system memory info +bit 2: print timer info +bit 3: print locks info if CONFIG_LOCKDEP is on +bit 4: print ftrace buffer + +So for example to print tasks and memory info on panic, user can: + echo 3 > /proc/sys/kernel/panic_print + +============================================================== + panic_on_rcu_stall: When set to 1, calls panic() after RCU stall detection messages. This diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d6aac75b51ba..8f0e68e250a7 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -527,6 +527,7 @@ static inline u32 int_sqrt64(u64 x) extern void bust_spinlocks(int yes); extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ extern int panic_timeout; +extern unsigned long panic_print; extern int panic_on_oops; extern int panic_on_unrecovered_nmi; extern int panic_on_io_nmi; diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index d71013fffaf6..87aa2a6d9125 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -153,6 +153,7 @@ enum KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */ KERN_PANIC_ON_NMI=76, /* int: whether we will panic on an unrecovered */ KERN_PANIC_ON_WARN=77, /* int: call panic() in WARN() functions */ + KERN_PANIC_PRINT=78, /* ulong: bitmask to print system info on panic */ }; diff --git a/kernel/panic.c b/kernel/panic.c index 855f66738bc7..f121e6ba7e11 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -51,7 +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 -static unsigned long panic_print; +unsigned long panic_print; ATOMIC_NOTIFIER_HEAD(panic_notifier_list); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7f6c1a3b3485..ba4d9e85feb8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -807,6 +807,13 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "panic_print", + .data = &panic_print, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, #if defined CONFIG_PRINTK { .procname = "printk", diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 07148b497451..73c132095a7b 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -140,6 +140,7 @@ static const struct bin_table bin_kern_table[] = { { CTL_INT, KERN_MAX_LOCK_DEPTH, "max_lock_depth" }, { CTL_INT, KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" }, { CTL_INT, KERN_PANIC_ON_WARN, "panic_on_warn" }, + { CTL_ULONG, KERN_PANIC_PRINT, "panic_print" }, {} }; -- cgit v1.3-7-g2ca7 From 4169680e9f7cdbf893f8885611b3235aeda94224 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 7 Mar 2019 16:26:36 -0800 Subject: kernel/panic.c: taint: fix debugfs_simple_attr.cocci warnings Use DEFINE_DEBUGFS_ATTRIBUTE rather than DEFINE_SIMPLE_ATTRIBUTE for debugfs files. Semantic patch information: Rationale: DEFINE_SIMPLE_ATTRIBUTE + debugfs_create_file() imposes some significant overhead as compared to DEFINE_DEBUGFS_ATTRIBUTE + debugfs_create_file_unsafe(). Generated by: scripts/coccinelle/api/debugfs/debugfs_simple_attr.cocci The _unsafe() part suggests that some of them "safeness responsibilities" are now panic.c responsibilities. The patch is OK since panic's clear_warn_once_fops struct file_operations is safe against removal, so we don't have to use otherwise necessary debugfs_file_get()/debugfs_file_put(). [sergey.senozhatsky.work@gmail.com: changelog addition] Link: http://lkml.kernel.org/r/1545990861-158097-1-git-send-email-yuehaibing@huawei.com Signed-off-by: YueHaibing Reviewed-by: Sergey Senozhatsky Cc: Kees Cook Cc: Borislav Petkov Cc: Steven Rostedt (VMware) Cc: Petr Mladek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/panic.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'kernel/panic.c') diff --git a/kernel/panic.c b/kernel/panic.c index f121e6ba7e11..0ae0d7332f12 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -642,16 +642,14 @@ static int clear_warn_once_set(void *data, u64 val) return 0; } -DEFINE_SIMPLE_ATTRIBUTE(clear_warn_once_fops, - NULL, - clear_warn_once_set, - "%lld\n"); +DEFINE_DEBUGFS_ATTRIBUTE(clear_warn_once_fops, NULL, clear_warn_once_set, + "%lld\n"); static __init int register_warn_debugfs(void) { /* Don't care about failure */ - debugfs_create_file("clear_warn_once", 0200, NULL, - NULL, &clear_warn_once_fops); + debugfs_create_file_unsafe("clear_warn_once", 0200, NULL, NULL, + &clear_warn_once_fops); return 0; } -- cgit v1.3-7-g2ca7