From 20fb0c8272bbb102d15bdd11aa64f828619dd7cc Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:52 +0200 Subject: Revert "printk: Wait for the global console lock when the system is going down" This reverts commit b87f02307d3cfbda768520f0687c51ca77e14fc3. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-2-pmladek@suse.com --- kernel/panic.c | 2 -- kernel/printk/internal.h | 2 -- kernel/printk/printk.c | 4 ---- kernel/printk/printk_safe.c | 32 -------------------------------- kernel/reboot.c | 2 -- 5 files changed, 42 deletions(-) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index fe73d18ecdf0..6737b2332275 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -273,7 +273,6 @@ 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 { /* @@ -281,7 +280,6 @@ 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 e7d8578860ad..d947ca6c84f9 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -20,8 +20,6 @@ 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 b095fb5f5f61..45c6c2b0b104 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -250,9 +250,6 @@ 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. @@ -3733,7 +3730,6 @@ 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 caac4de1ea59..ef0f9a2044da 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -8,9 +8,7 @@ #include #include #include -#include #include -#include #include "internal.h" @@ -52,33 +50,3 @@ 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 310363685502..4177645e74d6 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -74,7 +74,6 @@ 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(); } @@ -263,7 +262,6 @@ 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 From 05c96b3713aa2a406d0c4ef0505bf80a6748fedb Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:53 +0200 Subject: Revert "printk: Block console kthreads when direct printing will be required" This reverts commit c3230283e2819a69dad2cf7a63143fde8bab8b5c. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-3-pmladek@suse.com --- kernel/printk/printk.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 45c6c2b0b104..ea3dd55709e7 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3729,9 +3729,7 @@ static bool printer_should_wake(struct console *con, u64 seq) return true; if (con->blocked || - console_kthreads_atomically_blocked() || - system_state > SYSTEM_RUNNING || - oops_in_progress) { + console_kthreads_atomically_blocked()) { return false; } -- cgit From 007eeab7e9f03a3108c300c03e11a6c151e430c9 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:54 +0200 Subject: Revert "printk: remove @console_locked" This reverts commit ab406816fca009349b89cbde885daf68a8c77e33. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-4-pmladek@suse.com --- kernel/printk/printk.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ea3dd55709e7..dfd1a19b95d6 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -340,7 +340,15 @@ static void console_kthreads_unblock(void) console_kthreads_blocked = false; } -static int console_suspended; +/* + * This is used for debugging the mess that is the VT code by + * keeping track if we have the console semaphore held. It's + * definitely not the perfect debug tool (we don't know if _WE_ + * hold it and are racing, but it helps tracking those weird code + * paths in the console code where we end up in places I want + * locked without the console semaphore held). + */ +static int console_locked, console_suspended; /* * Array of consoles built from command line options (console=) @@ -2711,6 +2719,7 @@ void console_lock(void) if (console_suspended) return; console_kthreads_block(); + console_locked = 1; console_may_schedule = 1; } EXPORT_SYMBOL(console_lock); @@ -2735,26 +2744,15 @@ int console_trylock(void) up_console_sem(); return 0; } + console_locked = 1; console_may_schedule = 0; return 1; } EXPORT_SYMBOL(console_trylock); -/* - * This is used to help to make sure that certain paths within the VT code are - * running with the console lock held. It is definitely not the perfect debug - * tool (it is not known if the VT code is the task holding the console lock), - * but it helps tracking those weird code paths in the console code such as - * when the console is suspended: where the console is not locked but no - * console printing may occur. - * - * Note: This returns true when the console is suspended but is not locked. - * This is intentional because the VT code must consider that situation - * the same as if the console was locked. - */ int is_console_locked(void) { - return (console_kthreads_blocked || atomic_read(&console_kthreads_active)); + return (console_locked || atomic_read(&console_kthreads_active)); } EXPORT_SYMBOL(is_console_locked); @@ -2810,6 +2808,8 @@ static inline bool console_is_usable(struct console *con) static void __console_unlock(void) { + console_locked = 0; + /* * Depending on whether console_lock() or console_trylock() was used, * appropriately allow the kthread printers to continue. @@ -3127,6 +3127,7 @@ void console_unblank(void) } else console_lock(); + console_locked = 1; console_may_schedule = 0; for_each_console(c) if ((c->flags & CON_ENABLED) && c->unblank) -- cgit From 2d9ef940f89e0ab4fde7ba6f769d82f2a450c35a Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:55 +0200 Subject: Revert "printk: extend console_lock for per-console locking" This reverts commit 8e274732115f63c1d09136284431b3555bd5cc56. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-5-pmladek@suse.com --- kernel/printk/printk.c | 261 +++++++++++-------------------------------------- 1 file changed, 56 insertions(+), 205 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index dfd1a19b95d6..ae489dc685a1 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -223,33 +223,6 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, /* Number of registered extended console drivers. */ static int nr_ext_console_drivers; -/* - * Used to synchronize printing kthreads against direct printing via - * console_trylock/console_unlock. - * - * Values: - * -1 = console kthreads atomically blocked (via global trylock) - * 0 = no kthread printing, console not locked (via trylock) - * >0 = kthread(s) actively printing - * - * Note: For synchronizing against direct printing via - * console_lock/console_unlock, see the @lock variable in - * struct console. - */ -static atomic_t console_kthreads_active = ATOMIC_INIT(0); - -#define console_kthreads_atomic_tryblock() \ - (atomic_cmpxchg(&console_kthreads_active, 0, -1) == 0) -#define console_kthreads_atomic_unblock() \ - atomic_cmpxchg(&console_kthreads_active, -1, 0) -#define console_kthreads_atomically_blocked() \ - (atomic_read(&console_kthreads_active) == -1) - -#define console_kthread_printing_tryenter() \ - atomic_inc_unless_negative(&console_kthreads_active) -#define console_kthread_printing_exit() \ - atomic_dec(&console_kthreads_active) - /* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. @@ -297,49 +270,6 @@ static bool panic_in_progress(void) return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID); } -/* - * Tracks whether kthread printers are all blocked. A value of true implies - * that the console is locked via console_lock() or the console is suspended. - * Writing to this variable requires holding @console_sem. - */ -static bool console_kthreads_blocked; - -/* - * Block all kthread printers from a schedulable context. - * - * Requires holding @console_sem. - */ -static void console_kthreads_block(void) -{ - struct console *con; - - for_each_console(con) { - mutex_lock(&con->lock); - con->blocked = true; - mutex_unlock(&con->lock); - } - - console_kthreads_blocked = true; -} - -/* - * Unblock all kthread printers from a schedulable context. - * - * Requires holding @console_sem. - */ -static void console_kthreads_unblock(void) -{ - struct console *con; - - for_each_console(con) { - mutex_lock(&con->lock); - con->blocked = false; - mutex_unlock(&con->lock); - } - - console_kthreads_blocked = false; -} - /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's @@ -2673,6 +2603,13 @@ void resume_console(void) down_console_sem(); console_suspended = 0; console_unlock(); + + /* + * While suspended, new records may have been added to the + * ringbuffer. Wake up the kthread printers to print them. + */ + wake_up_klogd(); + pr_flush(1000, true); } @@ -2691,14 +2628,9 @@ static int console_cpu_notify(unsigned int cpu) /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); - else { - /* - * If a new CPU comes online, the conditions for - * printer_should_wake() may have changed for some - * kthread printer with !CON_ANYTIME. - */ - wake_up_klogd(); - } + + /* Wake kthread printers. Some may have become usable. */ + wake_up_klogd(); } return 0; } @@ -2718,7 +2650,6 @@ void console_lock(void) down_console_sem(); if (console_suspended) return; - console_kthreads_block(); console_locked = 1; console_may_schedule = 1; } @@ -2740,10 +2671,6 @@ int console_trylock(void) up_console_sem(); return 0; } - if (!console_kthreads_atomic_tryblock()) { - up_console_sem(); - return 0; - } console_locked = 1; console_may_schedule = 0; return 1; @@ -2752,7 +2679,7 @@ EXPORT_SYMBOL(console_trylock); int is_console_locked(void) { - return (console_locked || atomic_read(&console_kthreads_active)); + return console_locked; } EXPORT_SYMBOL(is_console_locked); @@ -2796,7 +2723,7 @@ static inline bool __console_is_usable(short flags) * Check if the given console is currently capable and allowed to print * records. * - * Requires holding the console_lock. + * Requires the console_lock. */ static inline bool console_is_usable(struct console *con) { @@ -2809,22 +2736,6 @@ static inline bool console_is_usable(struct console *con) static void __console_unlock(void) { console_locked = 0; - - /* - * Depending on whether console_lock() or console_trylock() was used, - * appropriately allow the kthread printers to continue. - */ - if (console_kthreads_blocked) - console_kthreads_unblock(); - else - console_kthreads_atomic_unblock(); - - /* - * New records may have arrived while the console was locked. - * Wake the kthread printers to print them. - */ - wake_up_klogd(); - up_console_sem(); } @@ -2842,19 +2753,17 @@ static void __console_unlock(void) * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding the - * console_lock. Otherwise it is set to false. A NULL pointer may be provided - * to disable allowing the console_lock to be taken over by a printk waiter. + * console_lock. Otherwise it is set to false. * * Returns false if the given console has no next record to print, otherwise * true. * - * Requires the console_lock if @handover is non-NULL. - * Requires con->lock otherwise. + * Requires the console_lock. */ -static bool __console_emit_next_record(struct console *con, char *text, char *ext_text, - char *dropped_text, bool *handover) +static bool console_emit_next_record(struct console *con, char *text, char *ext_text, + char *dropped_text, bool *handover) { - static atomic_t panic_console_dropped = ATOMIC_INIT(0); + static int panic_console_dropped; struct printk_info info; struct printk_record r; unsigned long flags; @@ -2863,8 +2772,7 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); - if (handover) - *handover = false; + *handover = false; if (!prb_read_valid(prb, con->seq, &r)) return false; @@ -2872,8 +2780,7 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex if (con->seq != r.info->seq) { con->dropped += r.info->seq - con->seq; con->seq = r.info->seq; - if (panic_in_progress() && - atomic_fetch_inc_relaxed(&panic_console_dropped) > 10) { + if (panic_in_progress() && panic_console_dropped++ > 10) { suppress_panic_printk = 1; pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n"); } @@ -2895,61 +2802,31 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); } - if (handover) { - /* - * While actively printing out messages, if another printk() - * were to occur on another CPU, it may wait for this one to - * finish. This task can not be preempted if there is a - * waiter waiting to take over. - * - * Interrupts are disabled because the hand over to a waiter - * must not be interrupted until the hand over is completed - * (@console_waiter is cleared). - */ - printk_safe_enter_irqsave(flags); - console_lock_spinning_enable(); - - /* don't trace irqsoff print latency */ - stop_critical_timings(); - } + /* + * While actively printing out messages, if another printk() + * were to occur on another CPU, it may wait for this one to + * finish. This task can not be preempted if there is a + * waiter waiting to take over. + * + * Interrupts are disabled because the hand over to a waiter + * must not be interrupted until the hand over is completed + * (@console_waiter is cleared). + */ + printk_safe_enter_irqsave(flags); + console_lock_spinning_enable(); + stop_critical_timings(); /* don't trace print latency */ call_console_driver(con, write_text, len, dropped_text); + start_critical_timings(); con->seq++; - if (handover) { - start_critical_timings(); - *handover = console_lock_spinning_disable_and_check(); - printk_safe_exit_irqrestore(flags); - } + *handover = console_lock_spinning_disable_and_check(); + printk_safe_exit_irqrestore(flags); skip: return true; } -/* - * Print a record for a given console, but allow another printk() caller to - * take over the console_lock and continue printing. - * - * Requires the console_lock, but depending on @handover after the call, the - * caller may no longer have the console_lock. - * - * See __console_emit_next_record() for argument and return details. - */ -static bool console_emit_next_record_transferable(struct console *con, char *text, char *ext_text, - char *dropped_text, bool *handover) -{ - /* - * Handovers are only supported if threaded printers are atomically - * blocked. The context taking over the console_lock may be atomic. - */ - if (!console_kthreads_atomically_blocked()) { - *handover = false; - handover = NULL; - } - - return __console_emit_next_record(con, text, ext_text, dropped_text, handover); -} - /* * Print out all remaining records to all consoles. * @@ -3001,11 +2878,13 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove if (con->flags & CON_EXTENDED) { /* Extended consoles do not print "dropped messages". */ - progress = console_emit_next_record_transferable(con, &text[0], - &ext_text[0], NULL, handover); + progress = console_emit_next_record(con, &text[0], + &ext_text[0], NULL, + handover); } else { - progress = console_emit_next_record_transferable(con, &text[0], - NULL, &dropped_text[0], handover); + progress = console_emit_next_record(con, &text[0], + NULL, &dropped_text[0], + handover); } if (*handover) return false; @@ -3120,10 +2999,6 @@ void console_unblank(void) if (oops_in_progress) { if (down_trylock_console_sem() != 0) return; - if (!console_kthreads_atomic_tryblock()) { - up_console_sem(); - return; - } } else console_lock(); @@ -3206,6 +3081,10 @@ void console_start(struct console *console) console_lock(); console->flags |= CON_ENABLED; console_unlock(); + + /* Wake the newly enabled kthread printer. */ + wake_up_klogd(); + __pr_flush(console, 1000, true); } EXPORT_SYMBOL(console_start); @@ -3407,8 +3286,6 @@ void register_console(struct console *newcon) newcon->dropped = 0; newcon->thread = NULL; - newcon->blocked = true; - mutex_init(&newcon->lock); if (newcon->flags & CON_PRINTBUFFER) { /* Get a consistent copy of @syslog_seq. */ @@ -3709,19 +3586,6 @@ static void printk_fallback_preferred_direct(void) console_unlock(); } -/* - * Print a record for a given console, not allowing another printk() caller - * to take over. This is appropriate for contexts that do not have the - * console_lock. - * - * See __console_emit_next_record() for argument and return details. - */ -static bool console_emit_next_record(struct console *con, char *text, char *ext_text, - char *dropped_text) -{ - return __console_emit_next_record(con, text, ext_text, dropped_text, NULL); -} - static bool printer_should_wake(struct console *con, u64 seq) { short flags; @@ -3729,10 +3593,8 @@ static bool printer_should_wake(struct console *con, u64 seq) if (kthread_should_stop() || !printk_kthreads_available) return true; - if (con->blocked || - console_kthreads_atomically_blocked()) { + if (console_suspended) return false; - } /* * This is an unsafe read from con->flags, but a false positive is @@ -3753,6 +3615,7 @@ static int printk_kthread_func(void *data) struct console *con = data; char *dropped_text = NULL; char *ext_text = NULL; + bool handover; u64 seq = 0; char *text; int error; @@ -3802,27 +3665,15 @@ static int printk_kthread_func(void *data) if (error) continue; - error = mutex_lock_interruptible(&con->lock); - if (error) - continue; + console_lock(); - if (con->blocked || - !console_kthread_printing_tryenter()) { - /* Another context has locked the console_lock. */ - mutex_unlock(&con->lock); + if (console_suspended) { + up_console_sem(); continue; } - /* - * Although this context has not locked the console_lock, it - * is known that the console_lock is not locked and it is not - * possible for any other context to lock the console_lock. - * Therefore it is safe to read con->flags. - */ - - if (!__console_is_usable(con->flags)) { - console_kthread_printing_exit(); - mutex_unlock(&con->lock); + if (!console_is_usable(con)) { + __console_unlock(); continue; } @@ -3835,13 +3686,13 @@ static int printk_kthread_func(void *data) * which can conditionally invoke cond_resched(). */ console_may_schedule = 0; - console_emit_next_record(con, text, ext_text, dropped_text); + console_emit_next_record(con, text, ext_text, dropped_text, &handover); + if (handover) + continue; seq = con->seq; - console_kthread_printing_exit(); - - mutex_unlock(&con->lock); + __console_unlock(); } con_printk(KERN_INFO, con, "printing thread stopped\n"); -- cgit From 5831788afb17b89c5b531fb60cbd798613ccbb63 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:56 +0200 Subject: Revert "printk: add kthread console printers" This reverts commit 09c5ba0aa2fcfdadb17d045c3ee6f86d69270df7. This reverts commit b87f02307d3cfbda768520f0687c51ca77e14fc3. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-6-pmladek@suse.com --- kernel/printk/printk.c | 329 ++++--------------------------------------------- 1 file changed, 22 insertions(+), 307 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ae489dc685a1..5a6273e56b4e 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -361,13 +361,6 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; /* syslog_lock protects syslog_* variables and write access to clear_seq. */ static DEFINE_MUTEX(syslog_lock); -/* - * A flag to signify if printk_activate_kthreads() has already started the - * kthread printers. If true, any later registered consoles must start their - * own kthread directly. The flag is write protected by the console_lock. - */ -static bool printk_kthreads_available; - #ifdef CONFIG_PRINTK static atomic_t printk_prefer_direct = ATOMIC_INIT(0); @@ -397,39 +390,6 @@ void printk_prefer_direct_exit(void) WARN_ON(atomic_dec_if_positive(&printk_prefer_direct) < 0); } -/* - * Calling printk() always wakes kthread printers so that they can - * flush the new message to their respective consoles. Also, if direct - * printing is allowed, printk() tries to flush the messages directly. - * - * Direct printing is allowed in situations when the kthreads - * are not available or the system is in a problematic state. - * - * See the implementation about possible races. - */ -static inline bool allow_direct_printing(void) -{ - /* - * Checking kthread availability is a possible race because the - * kthread printers can become permanently disabled during runtime. - * However, doing that requires holding the console_lock, so any - * pending messages will be direct printed by console_unlock(). - */ - if (!printk_kthreads_available) - return true; - - /* - * Prefer direct printing when the system is in a problematic state. - * The context that sets this state will always see the updated value. - * The other contexts do not care. Anyway, direct printing is just a - * best effort. The direct output is only possible when console_lock - * is not already taken and no kthread printers are actively printing. - */ - return (system_state > SYSTEM_RUNNING || - oops_in_progress || - atomic_read(&printk_prefer_direct)); -} - DECLARE_WAIT_QUEUE_HEAD(log_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ @@ -2320,10 +2280,10 @@ asmlinkage int vprintk_emit(int facility, int level, printed_len = vprintk_store(facility, level, dev_info, fmt, args); /* If called from the scheduler, we can not call up(). */ - if (!in_sched && allow_direct_printing()) { + if (!in_sched) { /* * The caller may be holding system-critical or - * timing-sensitive locks. Disable preemption during direct + * timing-sensitive locks. Disable preemption during * printing of all remaining records to all consoles so that * this context can return as soon as possible. Hopefully * another printk() caller will take over the printing. @@ -2366,8 +2326,6 @@ EXPORT_SYMBOL(_printk); static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress); -static void printk_start_kthread(struct console *con); - #else /* CONFIG_PRINTK */ #define CONSOLE_LOG_MAX 0 @@ -2401,8 +2359,6 @@ static void call_console_driver(struct console *con, const char *text, size_t le } static bool suppress_message_printing(int level) { return false; } static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; } -static void printk_start_kthread(struct console *con) { } -static bool allow_direct_printing(void) { return true; } #endif /* CONFIG_PRINTK */ @@ -2603,13 +2559,6 @@ void resume_console(void) down_console_sem(); console_suspended = 0; console_unlock(); - - /* - * While suspended, new records may have been added to the - * ringbuffer. Wake up the kthread printers to print them. - */ - wake_up_klogd(); - pr_flush(1000, true); } @@ -2628,9 +2577,6 @@ static int console_cpu_notify(unsigned int cpu) /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); - - /* Wake kthread printers. Some may have become usable. */ - wake_up_klogd(); } return 0; } @@ -2702,9 +2648,18 @@ static bool abandon_console_lock_in_panic(void) return atomic_read(&panic_cpu) != raw_smp_processor_id(); } -static inline bool __console_is_usable(short flags) +/* + * Check if the given console is currently capable and allowed to print + * records. + * + * Requires the console_lock. + */ +static inline bool console_is_usable(struct console *con) { - if (!(flags & CON_ENABLED)) + if (!(con->flags & CON_ENABLED)) + return false; + + if (!con->write) return false; /* @@ -2713,26 +2668,12 @@ static inline bool __console_is_usable(short flags) * cope (CON_ANYTIME) don't call them until this CPU is officially up. */ if (!cpu_online(raw_smp_processor_id()) && - !(flags & CON_ANYTIME)) + !(con->flags & CON_ANYTIME)) return false; return true; } -/* - * Check if the given console is currently capable and allowed to print - * records. - * - * Requires the console_lock. - */ -static inline bool console_is_usable(struct console *con) -{ - if (!con->write) - return false; - - return __console_is_usable(con->flags); -} - static void __console_unlock(void) { console_locked = 0; @@ -2845,8 +2786,8 @@ skip: * were flushed to all usable consoles. A returned false informs the caller * that everything was not flushed (either there were no usable consoles or * another context has taken over printing or it is a panic situation and this - * is not the panic CPU or direct printing is not preferred). Regardless the - * reason, the caller should assume it is not useful to immediately try again. + * is not the panic CPU). Regardless the reason, the caller should assume it + * is not useful to immediately try again. * * Requires the console_lock. */ @@ -2863,10 +2804,6 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove *handover = false; do { - /* Let the kthread printers do the work if they can. */ - if (!allow_direct_printing()) - return false; - any_progress = false; for_each_console(con) { @@ -3081,10 +3018,6 @@ void console_start(struct console *console) console_lock(); console->flags |= CON_ENABLED; console_unlock(); - - /* Wake the newly enabled kthread printer. */ - wake_up_klogd(); - __pr_flush(console, 1000, true); } EXPORT_SYMBOL(console_start); @@ -3285,8 +3218,6 @@ void register_console(struct console *newcon) nr_ext_console_drivers++; newcon->dropped = 0; - newcon->thread = NULL; - if (newcon->flags & CON_PRINTBUFFER) { /* Get a consistent copy of @syslog_seq. */ mutex_lock(&syslog_lock); @@ -3296,10 +3227,6 @@ void register_console(struct console *newcon) /* Begin with next message. */ newcon->seq = prb_next_seq(prb); } - - if (printk_kthreads_available) - printk_start_kthread(newcon); - console_unlock(); console_sysfs_notify(); @@ -3326,7 +3253,6 @@ EXPORT_SYMBOL(register_console); int unregister_console(struct console *console) { - struct task_struct *thd; struct console *con; int res; @@ -3367,20 +3293,7 @@ int unregister_console(struct console *console) console_drivers->flags |= CON_CONSDEV; console->flags &= ~CON_ENABLED; - - /* - * console->thread can only be cleared under the console lock. But - * stopping the thread must be done without the console lock. The - * task that clears @thread is the task that stops the kthread. - */ - thd = console->thread; - console->thread = NULL; - console_unlock(); - - if (thd) - kthread_stop(thd); - console_sysfs_notify(); if (console->exit) @@ -3476,20 +3389,6 @@ static int __init printk_late_init(void) } late_initcall(printk_late_init); -static int __init printk_activate_kthreads(void) -{ - struct console *con; - - console_lock(); - printk_kthreads_available = true; - for_each_console(con) - printk_start_kthread(con); - console_unlock(); - - return 0; -} -early_initcall(printk_activate_kthreads); - #if defined CONFIG_PRINTK /* If @con is specified, only wait for that console. Otherwise wait for all. */ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) @@ -3564,180 +3463,11 @@ bool pr_flush(int timeout_ms, bool reset_on_progress) } EXPORT_SYMBOL(pr_flush); -static void __printk_fallback_preferred_direct(void) -{ - printk_prefer_direct_enter(); - pr_err("falling back to preferred direct printing\n"); - printk_kthreads_available = false; -} - -/* - * Enter preferred direct printing, but never exit. Mark console threads as - * unavailable. The system is then forever in preferred direct printing and - * any printing threads will exit. - * - * Must *not* be called under console_lock. Use - * __printk_fallback_preferred_direct() if already holding console_lock. - */ -static void printk_fallback_preferred_direct(void) -{ - console_lock(); - __printk_fallback_preferred_direct(); - console_unlock(); -} - -static bool printer_should_wake(struct console *con, u64 seq) -{ - short flags; - - if (kthread_should_stop() || !printk_kthreads_available) - return true; - - if (console_suspended) - return false; - - /* - * This is an unsafe read from con->flags, but a false positive is - * not a problem. Worst case it would allow the printer to wake up - * although it is disabled. But the printer will notice that when - * attempting to print and instead go back to sleep. - */ - flags = data_race(READ_ONCE(con->flags)); - - if (!__console_is_usable(flags)) - return false; - - return prb_read_valid(prb, seq, NULL); -} - -static int printk_kthread_func(void *data) -{ - struct console *con = data; - char *dropped_text = NULL; - char *ext_text = NULL; - bool handover; - u64 seq = 0; - char *text; - int error; - - text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); - if (!text) { - con_printk(KERN_ERR, con, "failed to allocate text buffer\n"); - printk_fallback_preferred_direct(); - goto out; - } - - if (con->flags & CON_EXTENDED) { - ext_text = kmalloc(CONSOLE_EXT_LOG_MAX, GFP_KERNEL); - if (!ext_text) { - con_printk(KERN_ERR, con, "failed to allocate ext_text buffer\n"); - printk_fallback_preferred_direct(); - goto out; - } - } else { - dropped_text = kmalloc(DROPPED_TEXT_MAX, GFP_KERNEL); - if (!dropped_text) { - con_printk(KERN_ERR, con, "failed to allocate dropped_text buffer\n"); - printk_fallback_preferred_direct(); - goto out; - } - } - - con_printk(KERN_INFO, con, "printing thread started\n"); - - for (;;) { - /* - * Guarantee this task is visible on the waitqueue before - * checking the wake condition. - * - * The full memory barrier within set_current_state() of - * prepare_to_wait_event() pairs with the full memory barrier - * within wq_has_sleeper(). - * - * This pairs with __wake_up_klogd:A. - */ - error = wait_event_interruptible(log_wait, - printer_should_wake(con, seq)); /* LMM(printk_kthread_func:A) */ - - if (kthread_should_stop() || !printk_kthreads_available) - break; - - if (error) - continue; - - console_lock(); - - if (console_suspended) { - up_console_sem(); - continue; - } - - if (!console_is_usable(con)) { - __console_unlock(); - continue; - } - - /* - * Even though the printk kthread is always preemptible, it is - * still not allowed to call cond_resched() from within - * console drivers. The task may become non-preemptible in the - * console driver call chain. For example, vt_console_print() - * takes a spinlock and then can call into fbcon_redraw(), - * which can conditionally invoke cond_resched(). - */ - console_may_schedule = 0; - console_emit_next_record(con, text, ext_text, dropped_text, &handover); - if (handover) - continue; - - seq = con->seq; - - __console_unlock(); - } - - con_printk(KERN_INFO, con, "printing thread stopped\n"); -out: - kfree(dropped_text); - kfree(ext_text); - kfree(text); - - console_lock(); - /* - * If this kthread is being stopped by another task, con->thread will - * already be NULL. That is fine. The important thing is that it is - * NULL after the kthread exits. - */ - con->thread = NULL; - console_unlock(); - - return 0; -} - -/* Must be called under console_lock. */ -static void printk_start_kthread(struct console *con) -{ - /* - * Do not start a kthread if there is no write() callback. The - * kthreads assume the write() callback exists. - */ - if (!con->write) - return; - - con->thread = kthread_run(printk_kthread_func, con, - "pr/%s%d", con->name, con->index); - if (IS_ERR(con->thread)) { - con->thread = NULL; - con_printk(KERN_ERR, con, "unable to start printing thread\n"); - __printk_fallback_preferred_direct(); - return; - } -} - /* * Delayed printk version, for scheduler-internal messages: */ -#define PRINTK_PENDING_WAKEUP 0x01 -#define PRINTK_PENDING_DIRECT_OUTPUT 0x02 +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); @@ -3745,14 +3475,10 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = this_cpu_xchg(printk_pending, 0); - if (pending & PRINTK_PENDING_DIRECT_OUTPUT) { - printk_prefer_direct_enter(); - + if (pending & PRINTK_PENDING_OUTPUT) { /* If trylock fails, someone else is doing the printing */ if (console_trylock()) console_unlock(); - - printk_prefer_direct_exit(); } if (pending & PRINTK_PENDING_WAKEUP) @@ -3777,11 +3503,10 @@ static void __wake_up_klogd(int val) * prepare_to_wait_event(), which is called after ___wait_event() adds * the waiter but before it has checked the wait condition. * - * This pairs with devkmsg_read:A, syslog_print:A, and - * printk_kthread_func:A. + * This pairs with devkmsg_read:A and syslog_print:A. */ if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */ - (val & PRINTK_PENDING_DIRECT_OUTPUT)) { + (val & PRINTK_PENDING_OUTPUT)) { this_cpu_or(printk_pending, val); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } @@ -3799,17 +3524,7 @@ void defer_console_output(void) * New messages may have been added directly to the ringbuffer * using vprintk_store(), so wake any waiters as well. */ - int val = PRINTK_PENDING_WAKEUP; - - /* - * Make sure that some context will print the messages when direct - * printing is allowed. This happens in situations when the kthreads - * may not be as reliable or perhaps unusable. - */ - if (allow_direct_printing()) - val |= PRINTK_PENDING_DIRECT_OUTPUT; - - __wake_up_klogd(val); + __wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT); } void printk_trigger_flush(void) -- cgit From 07a22b61946f0b80065b0ddcc703b715f84355f5 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:57 +0200 Subject: Revert "printk: add functions to prefer direct printing" This reverts commit 2bb2b7b57f81255c13f4395ea911d6bdc70c9fe2. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-7-pmladek@suse.com --- kernel/hung_task.c | 11 +---------- kernel/panic.c | 4 ---- kernel/printk/printk.c | 28 ---------------------------- kernel/rcu/tree_stall.h | 2 -- kernel/reboot.c | 14 +------------- kernel/watchdog.c | 4 ---- kernel/watchdog_hld.c | 4 ---- 7 files changed, 2 insertions(+), 65 deletions(-) (limited to 'kernel') diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 02a65d554340..52501e5f7655 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -127,8 +127,6 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) * complain: */ if (sysctl_hung_task_warnings) { - printk_prefer_direct_enter(); - if (sysctl_hung_task_warnings > 0) sysctl_hung_task_warnings--; pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", @@ -144,8 +142,6 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) if (sysctl_hung_task_all_cpu_backtrace) hung_task_show_all_bt = true; - - printk_prefer_direct_exit(); } touch_nmi_watchdog(); @@ -208,17 +204,12 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) } unlock: rcu_read_unlock(); - if (hung_task_show_lock) { - printk_prefer_direct_enter(); + if (hung_task_show_lock) debug_show_all_locks(); - printk_prefer_direct_exit(); - } if (hung_task_show_all_bt) { hung_task_show_all_bt = false; - printk_prefer_direct_enter(); trigger_all_cpu_backtrace(); - printk_prefer_direct_exit(); } if (hung_task_call_panic) diff --git a/kernel/panic.c b/kernel/panic.c index 6737b2332275..8355b19676f8 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -579,8 +579,6 @@ void __warn(const char *file, int line, void *caller, unsigned taint, { disable_trace_on_warning(); - printk_prefer_direct_enter(); - if (file) pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n", raw_smp_processor_id(), current->pid, file, line, @@ -610,8 +608,6 @@ void __warn(const char *file, int line, void *caller, unsigned taint, /* Just a warning, don't kill lockdep. */ add_taint(taint, LOCKDEP_STILL_OK); - - printk_prefer_direct_exit(); } #ifndef __WARN_FLAGS diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 5a6273e56b4e..b49c6ff6dca0 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -362,34 +362,6 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; static DEFINE_MUTEX(syslog_lock); #ifdef CONFIG_PRINTK -static atomic_t printk_prefer_direct = ATOMIC_INIT(0); - -/** - * printk_prefer_direct_enter - cause printk() calls to attempt direct - * printing to all enabled consoles - * - * Since it is not possible to call into the console printing code from any - * context, there is no guarantee that direct printing will occur. - * - * This globally effects all printk() callers. - * - * Context: Any context. - */ -void printk_prefer_direct_enter(void) -{ - atomic_inc(&printk_prefer_direct); -} - -/** - * printk_prefer_direct_exit - restore printk() behavior - * - * Context: Any context. - */ -void printk_prefer_direct_exit(void) -{ - WARN_ON(atomic_dec_if_positive(&printk_prefer_direct) < 0); -} - DECLARE_WAIT_QUEUE_HEAD(log_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 4995c078cff9..a001e1e7a992 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -647,7 +647,6 @@ static void print_cpu_stall(unsigned long gps) * See Documentation/RCU/stallwarn.rst for info on how to debug * RCU CPU stall warnings. */ - printk_prefer_direct_enter(); trace_rcu_stall_warning(rcu_state.name, TPS("SelfDetected")); pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name); raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags); @@ -685,7 +684,6 @@ static void print_cpu_stall(unsigned long gps) */ set_tsk_need_resched(current); set_preempt_need_resched(); - printk_prefer_direct_exit(); } static void check_cpu_stall(struct rcu_data *rdp) diff --git a/kernel/reboot.c b/kernel/reboot.c index 4177645e74d6..6bcc5d6a6572 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -447,11 +447,9 @@ static int __orderly_reboot(void) ret = run_cmd(reboot_cmd); if (ret) { - printk_prefer_direct_enter(); pr_warn("Failed to start orderly reboot: forcing the issue\n"); emergency_sync(); kernel_restart(NULL); - printk_prefer_direct_exit(); } return ret; @@ -464,7 +462,6 @@ static int __orderly_poweroff(bool force) ret = run_cmd(poweroff_cmd); if (ret && force) { - printk_prefer_direct_enter(); pr_warn("Failed to start orderly shutdown: forcing the issue\n"); /* @@ -474,7 +471,6 @@ static int __orderly_poweroff(bool force) */ emergency_sync(); kernel_power_off(); - printk_prefer_direct_exit(); } return ret; @@ -532,8 +528,6 @@ EXPORT_SYMBOL_GPL(orderly_reboot); */ static void hw_failure_emergency_poweroff_func(struct work_struct *work) { - printk_prefer_direct_enter(); - /* * We have reached here after the emergency shutdown waiting period has * expired. This means orderly_poweroff has not been able to shut off @@ -550,8 +544,6 @@ static void hw_failure_emergency_poweroff_func(struct work_struct *work) */ pr_emerg("Hardware protection shutdown failed. Trying emergency restart\n"); emergency_restart(); - - printk_prefer_direct_exit(); } static DECLARE_DELAYED_WORK(hw_failure_emergency_poweroff_work, @@ -590,13 +582,11 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced) { static atomic_t allow_proceed = ATOMIC_INIT(1); - printk_prefer_direct_enter(); - pr_emerg("HARDWARE PROTECTION shutdown (%s)\n", reason); /* Shutdown should be initiated only once. */ if (!atomic_dec_and_test(&allow_proceed)) - goto out; + return; /* * Queue a backup emergency shutdown in the event of @@ -604,8 +594,6 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced) */ hw_failure_emergency_poweroff(ms_until_forced); orderly_poweroff(true); -out: - printk_prefer_direct_exit(); } EXPORT_SYMBOL_GPL(hw_protection_shutdown); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 40024e03d422..9166220457bc 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -424,8 +424,6 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) /* Start period for the next softlockup warning. */ update_report_ts(); - printk_prefer_direct_enter(); - pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); @@ -444,8 +442,6 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); if (softlockup_panic) panic("softlockup: hung tasks"); - - printk_prefer_direct_exit(); } return HRTIMER_RESTART; diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 701f35f0e2d4..247bf0b1582c 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -135,8 +135,6 @@ static void watchdog_overflow_callback(struct perf_event *event, if (__this_cpu_read(hard_watchdog_warn) == true) return; - printk_prefer_direct_enter(); - pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", this_cpu); print_modules(); @@ -157,8 +155,6 @@ static void watchdog_overflow_callback(struct perf_event *event, if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); - printk_prefer_direct_exit(); - __this_cpu_write(hard_watchdog_warn, true); return; } -- cgit