| From: Jinchao Wang <wangjinchao600@gmail.com> |
| Subject: panic: introduce helper functions for panic state |
| Date: Mon, 25 Aug 2025 10:29:29 +0800 |
| |
| Patch series "panic: introduce panic status function family", v2. |
| |
| This series introduces a family of helper functions to manage panic state |
| and updates existing code to use them. |
| |
| Before this series, panic state helpers were scattered and inconsistent. |
| For example, panic_in_progress() was defined in printk/printk.c, not in |
| panic.c or panic.h. As a result, developers had to look in unexpected |
| places to understand or re-use panic state logic. Other checks were open- |
| coded, duplicating logic across panic, crash, and watchdog paths. |
| |
| The new helpers centralize the functionality in panic.c/panic.h: |
| - panic_try_start() |
| - panic_reset() |
| - panic_in_progress() |
| - panic_on_this_cpu() |
| - panic_on_other_cpu() |
| |
| Patches 1–8 add the helpers and convert panic/crash and printk/nbcon |
| code to use them. |
| |
| Patch 9 fixes a bug in the watchdog subsystem by skipping checks when a |
| panic is in progress, avoiding interference with the panic CPU. |
| |
| Together, this makes panic state handling simpler, more discoverable, and |
| more robust. |
| |
| |
| This patch (of 9): |
| |
| This patch introduces four new helper functions to abstract the management |
| of the panic_cpu variable. These functions will be used in subsequent |
| patches to refactor existing code. |
| |
| The direct use of panic_cpu can be error-prone and ambiguous, as it |
| requires manual checks to determine which CPU is handling the panic. The |
| new helpers clarify intent: |
| |
| panic_try_start(): |
| Atomically sets the current CPU as the panicking CPU. |
| |
| panic_reset(): |
| Reset panic_cpu to PANIC_CPU_INVALID. |
| |
| panic_in_progress(): |
| Checks if a panic has been triggered. |
| |
| panic_on_this_cpu(): |
| Returns true if the current CPU is the panic originator. |
| |
| panic_on_other_cpu(): |
| Returns true if a panic is on another CPU. |
| |
| This change lays the groundwork for improved code readability |
| and robustness in the panic handling subsystem. |
| |
| Link: https://lkml.kernel.org/r/20250825022947.1596226-1-wangjinchao600@gmail.com |
| Link: https://lkml.kernel.org/r/20250825022947.1596226-2-wangjinchao600@gmail.com |
| Signed-off-by: Jinchao Wang <wangjinchao600@gmail.com> |
| Cc: Anna Schumaker <anna.schumaker@oracle.com> |
| Cc: Baoquan He <bhe@redhat.com> |
| Cc: "Darrick J. Wong" <djwong@kernel.org> |
| Cc: Dave Young <dyoung@redhat.com> |
| Cc: Doug Anderson <dianders@chromium.org> |
| Cc: "Guilherme G. Piccoli" <gpiccoli@igalia.com> |
| Cc: Helge Deller <deller@gmx.de> |
| Cc: Ingo Molnar <mingo@kernel.org> |
| Cc: Jason Gunthorpe <jgg@ziepe.ca> |
| Cc: Joanthan Cameron <Jonathan.Cameron@huawei.com> |
| Cc: Joel Granados <joel.granados@kernel.org> |
| Cc: John Ogness <john.ogness@linutronix.de> |
| Cc: Kees Cook <kees@kernel.org> |
| Cc: Li Huafei <lihuafei1@huawei.com> |
| Cc: "Luck, Tony" <tony.luck@intel.com> |
| Cc: Luo Gengkun <luogengkun@huaweicloud.com> |
| Cc: Max Kellermann <max.kellermann@ionos.com> |
| Cc: Nam Cao <namcao@linutronix.de> |
| Cc: oushixiong <oushixiong@kylinos.cn> |
| Cc: Petr Mladek <pmladek@suse.com> |
| Cc: Qianqiang Liu <qianqiang.liu@163.com> |
| Cc: Sergey Senozhatsky <senozhatsky@chromium.org> |
| Cc: Sohil Mehta <sohil.mehta@intel.com> |
| Cc: Steven Rostedt <rostedt@goodmis.org> |
| Cc: Tejun Heo <tj@kernel.org> |
| Cc: Thomas Gleinxer <tglx@linutronix.de> |
| Cc: Thomas Zimemrmann <tzimmermann@suse.de> |
| Cc: Thorsten Blum <thorsten.blum@linux.dev> |
| Cc: Ville Syrjala <ville.syrjala@linux.intel.com> |
| Cc: Vivek Goyal <vgoyal@redhat.com> |
| Cc: Yicong Yang <yangyicong@hisilicon.com> |
| Cc: Yunhui Cui <cuiyunhui@bytedance.com> |
| Cc: Yury Norov (NVIDIA) <yury.norov@gmail.com>b |
| Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
| --- |
| |
| include/linux/panic.h | 6 ++++ |
| kernel/panic.c | 53 +++++++++++++++++++++++++++++++++++++++ |
| kernel/printk/printk.c | 5 --- |
| 3 files changed, 59 insertions(+), 5 deletions(-) |
| |
| --- a/include/linux/panic.h~panic-introduce-helper-functions-for-panic-state |
| +++ a/include/linux/panic.h |
| @@ -43,6 +43,12 @@ void abort(void); |
| extern atomic_t panic_cpu; |
| #define PANIC_CPU_INVALID -1 |
| |
| +bool panic_try_start(void); |
| +void panic_reset(void); |
| +bool panic_in_progress(void); |
| +bool panic_on_this_cpu(void); |
| +bool panic_on_other_cpu(void); |
| + |
| /* |
| * Only to be used by arch init code. If the user over-wrote the default |
| * CONFIG_PANIC_TIMEOUT, honor it. |
| --- a/kernel/panic.c~panic-introduce-helper-functions-for-panic-state |
| +++ a/kernel/panic.c |
| @@ -299,6 +299,59 @@ void __weak crash_smp_send_stop(void) |
| |
| atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); |
| |
| +bool panic_try_start(void) |
| +{ |
| + int old_cpu, this_cpu; |
| + |
| + /* |
| + * Only one CPU is allowed to execute the crash_kexec() code as with |
| + * panic(). Otherwise parallel calls of panic() and crash_kexec() |
| + * may stop each other. To exclude them, we use panic_cpu here too. |
| + */ |
| + old_cpu = PANIC_CPU_INVALID; |
| + this_cpu = raw_smp_processor_id(); |
| + |
| + return atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu); |
| +} |
| +EXPORT_SYMBOL(panic_try_start); |
| + |
| +void panic_reset(void) |
| +{ |
| + atomic_set(&panic_cpu, PANIC_CPU_INVALID); |
| +} |
| +EXPORT_SYMBOL(panic_reset); |
| + |
| +bool panic_in_progress(void) |
| +{ |
| + return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID); |
| +} |
| +EXPORT_SYMBOL(panic_in_progress); |
| + |
| +/* Return true if a panic is in progress on the current CPU. */ |
| +bool panic_on_this_cpu(void) |
| +{ |
| + /* |
| + * 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 unlikely(atomic_read(&panic_cpu) == raw_smp_processor_id()); |
| +} |
| +EXPORT_SYMBOL(panic_on_this_cpu); |
| + |
| +/* |
| + * Return true if a panic is in progress on a remote CPU. |
| + * |
| + * On true, the local CPU should immediately release any printing resources |
| + * that may be needed by the panic CPU. |
| + */ |
| +bool panic_on_other_cpu(void) |
| +{ |
| + return (panic_in_progress() && !this_cpu_in_panic()); |
| +} |
| +EXPORT_SYMBOL(panic_on_other_cpu); |
| + |
| /* |
| * A variant of panic() called from NMI context. We return if we've already |
| * panicked on this CPU. If another CPU already panicked, loop in |
| --- a/kernel/printk/printk.c~panic-introduce-helper-functions-for-panic-state |
| +++ a/kernel/printk/printk.c |
| @@ -345,11 +345,6 @@ static void __up_console_sem(unsigned lo |
| } |
| #define up_console_sem() __up_console_sem(_RET_IP_) |
| |
| -static bool panic_in_progress(void) |
| -{ |
| - return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID); |
| -} |
| - |
| /* Return true if a panic is in progress on the current CPU. */ |
| bool this_cpu_in_panic(void) |
| { |
| _ |