Message ID | 90ee131c643a5033d117b556c0792de65129d4c3.1710220326.git.sreenath.vijayan@sony.com |
---|---|
State | New |
Headers | show |
Series | Add support to replay kernel log on consoles via sysrq | expand |
On Wed 2024-03-13 15:50:52, Sreenath Vijayan wrote: > Add a generic function console_replay_all() for replaying > the kernel log on consoles, in any context. It would allow > viewing the logs on an unresponsive terminal via sysrq. > > Reuse the existing code from console_flush_on_panic() for > resetting the sequence numbers, by introducing a new helper > function __console_rewind_all(). It is safe to be called > under console_lock(). > > Try to acquire lock on the console subsystem without waiting. > If successful, reset the sequence number to oldest available > record on all consoles and call console_unlock() which will > automatically flush the messages to the consoles. > > --- a/kernel/printk/printk.c > +++ b/kernel/printk/printk.c > @@ -4259,6 +4271,23 @@ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) > } > EXPORT_SYMBOL_GPL(kmsg_dump_rewind); > > +/** > + * console_replay_all - replay kernel log on consoles It should rather be called "console_try_replay_all()" to make it clear that it is just the best effort. > + * > + * Try to obtain lock on console subsystem and replay all > + * available records in printk buffer on the consoles. > + * Does nothing if lock is not obtained. > + * > + * Context: Any context. This should be: * Context: Any, except for NMI Basically only lockless code is safe in NMI which is not the case here. > + */ > +void console_replay_all(void) > +{ > + if (console_trylock()) { > + __console_rewind_all(); > + /* Consoles are flushed as part of console_unlock(). */ > + console_unlock(); > + } > +} > #endif Otherwise, it looks good. With the two changes: Reviewed-by: Petr Mladek <pmladek@suse.com> I am sorry for the late review. I have been snowed under tasks. Also I had healthy problems. I have seen a mail that Greg has queued the patch in tty-next. I am not sure if it still can be fixed. It will be perfectly fine to change this by a followup patch. Best Regards, Petr
On Wed, May 22, 2024 at 05:18:13PM +0200, Petr Mladek wrote: > > On Wed 2024-03-13 15:50:52, Sreenath Vijayan wrote: > > Add a generic function console_replay_all() for replaying > > the kernel log on consoles, in any context. It would allow > > viewing the logs on an unresponsive terminal via sysrq. > > > > Reuse the existing code from console_flush_on_panic() for > > resetting the sequence numbers, by introducing a new helper > > function __console_rewind_all(). It is safe to be called > > under console_lock(). > > > > Try to acquire lock on the console subsystem without waiting. > > If successful, reset the sequence number to oldest available > > record on all consoles and call console_unlock() which will > > automatically flush the messages to the consoles. > > > > --- a/kernel/printk/printk.c > > +++ b/kernel/printk/printk.c > > @@ -4259,6 +4271,23 @@ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) > > } > > EXPORT_SYMBOL_GPL(kmsg_dump_rewind); > > > > +/** > > + * console_replay_all - replay kernel log on consoles > > It should rather be called "console_try_replay_all()" to make it clear > that it is just the best effort. > Ok, noted. > > + * > > + * Try to obtain lock on console subsystem and replay all > > + * available records in printk buffer on the consoles. > > + * Does nothing if lock is not obtained. > > + * > > + * Context: Any context. > > This should be: > > * Context: Any, except for NMI > > Basically only lockless code is safe in NMI which is not the case here. > Understood. > > + */ > > +void console_replay_all(void) > > +{ > > + if (console_trylock()) { > > + __console_rewind_all(); > > + /* Consoles are flushed as part of console_unlock(). */ > > + console_unlock(); > > + } > > +} > > #endif > > Otherwise, it looks good. With the two changes: > > Reviewed-by: Petr Mladek <pmladek@suse.com> > > I am sorry for the late review. I have been snowed under tasks. > Also I had healthy problems. > > I have seen a mail that Greg has queued the patch in tty-next. > I am not sure if it still can be fixed. It will be perfectly fine > to change this by a followup patch. > > Best Regards, > Petr Thank you for the review comments. As the patch has been merged to mainline, I will soon send a followup patch with "Fixes:" tag. Regards, Sreenath
diff --git a/include/linux/printk.h b/include/linux/printk.h index 8ef499ab3c1e..8df2ac6c0e1f 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -192,6 +192,7 @@ void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; void printk_trigger_flush(void); +void console_replay_all(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -271,6 +272,9 @@ static inline void dump_stack(void) static inline void printk_trigger_flush(void) { } +static inline void console_replay_all(void) +{ +} #endif #ifdef CONFIG_SMP diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index f2444b581e16..9e38cf0c1002 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3134,6 +3134,40 @@ void console_unblank(void) pr_flush(1000, true); } +/* + * Rewind all consoles to the oldest available record. + * + * IMPORTANT: The function is safe only when called under + * console_lock(). It is not enforced because + * it is used as a best effort in panic(). + */ +static void __console_rewind_all(void) +{ + struct console *c; + short flags; + int cookie; + u64 seq; + + seq = prb_first_valid_seq(prb); + + cookie = console_srcu_read_lock(); + for_each_console_srcu(c) { + flags = console_srcu_read_flags(c); + + if (flags & CON_NBCON) { + nbcon_seq_force(c, seq); + } else { + /* + * This assignment is safe only when called under + * console_lock(). On panic, legacy consoles are + * only best effort. + */ + c->seq = seq; + } + } + console_srcu_read_unlock(cookie); +} + /** * console_flush_on_panic - flush console content on panic * @mode: flush all messages in buffer or just the pending ones @@ -3162,30 +3196,8 @@ void console_flush_on_panic(enum con_flush_mode mode) */ console_may_schedule = 0; - if (mode == CONSOLE_REPLAY_ALL) { - struct console *c; - short flags; - int cookie; - u64 seq; - - seq = prb_first_valid_seq(prb); - - cookie = console_srcu_read_lock(); - for_each_console_srcu(c) { - flags = console_srcu_read_flags(c); - - if (flags & CON_NBCON) { - nbcon_seq_force(c, seq); - } else { - /* - * This is an unsynchronized assignment. On - * panic legacy consoles are only best effort. - */ - c->seq = seq; - } - } - console_srcu_read_unlock(cookie); - } + if (mode == CONSOLE_REPLAY_ALL) + __console_rewind_all(); console_flush_all(false, &next_seq, &handover); } @@ -4259,6 +4271,23 @@ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); +/** + * console_replay_all - replay kernel log on consoles + * + * Try to obtain lock on console subsystem and replay all + * available records in printk buffer on the consoles. + * Does nothing if lock is not obtained. + * + * Context: Any context. + */ +void console_replay_all(void) +{ + if (console_trylock()) { + __console_rewind_all(); + /* Consoles are flushed as part of console_unlock(). */ + console_unlock(); + } +} #endif #ifdef CONFIG_SMP