From c3230283e2819a69dad2cf7a63143fde8bab8b5c Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 15 Jun 2022 18:28:04 +0200 Subject: printk: Block console kthreads when direct printing will be required There are known situations when the console kthreads are not reliable or does not work in principle, for example, early boot, panic, shutdown. For these situations there is the direct (legacy) mode when printk() tries to get console_lock() and flush the messages directly. It works very well during the early boot when the console kthreads are not available at all. It gets more complicated in the other situations when console kthreads might be actively printing and block console_trylock() in printk(). The same problem is in the legacy code as well. Any console_lock() owner could block console_trylock() in printk(). It is solved by a trick that the current console_lock() owner is responsible for printing all pending messages. It is actually the reason why there is the risk of softlockups and why the console kthreads were introduced. The console kthreads use the same approach. They are responsible for printing the messages by definition. So that they handle the messages anytime when they are awake and see new ones. The global console_lock is available when there is nothing to do. It should work well when the problematic context is correctly detected and printk() switches to the direct mode. But it seems that it is not enough in practice. There are reports that the messages are not printed during panic() or shutdown() even though printk() tries to use the direct mode here. The problem seems to be that console kthreads become active in these situation as well. They steel the job before other CPUs are stopped. Then they are stopped in the middle of the job and block the global console_lock. First part of the solution is to block console kthreads when the system is in a problematic state and requires the direct printk() mode. Link: https://lore.kernel.org/r/20220610205038.GA3050413@paulmck-ThinkPad-P17-Gen-1 Link: https://lore.kernel.org/r/CAMdYzYpF4FNTBPZsEFeWRuEwSies36QM_As8osPWZSr2q-viEA@mail.gmail.com Suggested-by: John Ogness Tested-by: Paul E. McKenney Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220615162805.27962-2-pmladek@suse.com --- kernel/printk/printk.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ea3dd55709e7..45c6c2b0b104 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3729,7 +3729,9 @@ static bool printer_should_wake(struct console *con, u64 seq) return true; if (con->blocked || - console_kthreads_atomically_blocked()) { + console_kthreads_atomically_blocked() || + system_state > SYSTEM_RUNNING || + oops_in_progress) { return false; } -- cgit From b87f02307d3cfbda768520f0687c51ca77e14fc3 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 15 Jun 2022 18:28:05 +0200 Subject: printk: Wait for the global console lock when the system is going down There are reports that the console kthreads block the global console lock when the system is going down, for example, reboot, panic. First part of the solution was to block kthreads in these problematic system states so they stopped handling newly added messages. Second part of the solution is to wait when for the kthreads when they are actively printing. It solves the problem when a message was printed before the system entered the problematic state and the kthreads managed to step in. A busy waiting has to be used because panic() can be called in any context and in an unknown state of the scheduler. There must be a timeout because the kthread might get stuck or sleeping and never release the lock. The timeout 10s is an arbitrary value inspired by the softlockup timeout. Link: https://lore.kernel.org/r/20220610205038.GA3050413@paulmck-ThinkPad-P17-Gen-1 Link: https://lore.kernel.org/r/CAMdYzYpF4FNTBPZsEFeWRuEwSies36QM_As8osPWZSr2q-viEA@mail.gmail.com Signed-off-by: Petr Mladek Tested-by: Paul E. McKenney Link: https://lore.kernel.org/r/20220615162805.27962-3-pmladek@suse.com --- include/linux/printk.h | 5 +++++ kernel/panic.c | 2 ++ kernel/printk/internal.h | 2 ++ kernel/printk/printk.c | 4 ++++ kernel/printk/printk_safe.c | 32 ++++++++++++++++++++++++++++++++ kernel/reboot.c | 2 ++ 6 files changed, 47 insertions(+) diff --git a/include/linux/printk.h b/include/linux/printk.h index cd26aab0ab2a..c1e07c0652c7 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -174,6 +174,7 @@ extern void printk_prefer_direct_enter(void); extern void printk_prefer_direct_exit(void); extern bool pr_flush(int timeout_ms, bool reset_on_progress); +extern void try_block_console_kthreads(int timeout_ms); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -238,6 +239,10 @@ static inline bool pr_flush(int timeout_ms, bool reset_on_progress) return true; } +static inline void try_block_console_kthreads(int timeout_ms) +{ +} + static inline int printk_ratelimit(void) { return 0; diff --git a/kernel/panic.c b/kernel/panic.c index 6737b2332275..fe73d18ecdf0 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -273,6 +273,7 @@ void panic(const char *fmt, ...) * unfortunately means it may not be hardened to work in a * panic situation. */ + try_block_console_kthreads(10000); smp_send_stop(); } else { /* @@ -280,6 +281,7 @@ void panic(const char *fmt, ...) * kmsg_dump, we will need architecture dependent extra * works in addition to stopping other CPUs. */ + try_block_console_kthreads(10000); crash_smp_send_stop(); } diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index d947ca6c84f9..e7d8578860ad 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -20,6 +20,8 @@ enum printk_info_flags { LOG_CONT = 8, /* text is a fragment of a continuation line */ }; +extern bool block_console_kthreads; + __printf(4, 0) int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 45c6c2b0b104..b095fb5f5f61 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -250,6 +250,9 @@ static atomic_t console_kthreads_active = ATOMIC_INIT(0); #define console_kthread_printing_exit() \ atomic_dec(&console_kthreads_active) +/* Block console kthreads to avoid processing new messages. */ +bool block_console_kthreads; + /* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. @@ -3730,6 +3733,7 @@ static bool printer_should_wake(struct console *con, u64 seq) if (con->blocked || console_kthreads_atomically_blocked() || + block_console_kthreads || system_state > SYSTEM_RUNNING || oops_in_progress) { return false; diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index ef0f9a2044da..caac4de1ea59 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -8,7 +8,9 @@ #include #include #include +#include #include +#include #include "internal.h" @@ -50,3 +52,33 @@ asmlinkage int vprintk(const char *fmt, va_list args) return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); + +/** + * try_block_console_kthreads() - Try to block console kthreads and + * make the global console_lock() avaialble + * + * @timeout_ms: The maximum time (in ms) to wait. + * + * Prevent console kthreads from starting processing new messages. Wait + * until the global console_lock() become available. + * + * Context: Can be called in any context. + */ +void try_block_console_kthreads(int timeout_ms) +{ + block_console_kthreads = true; + + /* Do not wait when the console lock could not be safely taken. */ + if (this_cpu_read(printk_context) || in_nmi()) + return; + + while (timeout_ms > 0) { + if (console_trylock()) { + console_unlock(); + return; + } + + udelay(1000); + timeout_ms -= 1; + } +} diff --git a/kernel/reboot.c b/kernel/reboot.c index 4177645e74d6..310363685502 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -74,6 +74,7 @@ void kernel_restart_prepare(char *cmd) { blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); system_state = SYSTEM_RESTART; + try_block_console_kthreads(10000); usermodehelper_disable(); device_shutdown(); } @@ -262,6 +263,7 @@ static void kernel_shutdown_prepare(enum system_states state) blocking_notifier_call_chain(&reboot_notifier_list, (state == SYSTEM_HALT) ? SYS_HALT : SYS_POWER_OFF, NULL); system_state = state; + try_block_console_kthreads(10000); usermodehelper_disable(); device_shutdown(); } -- cgit