From d0b6e0a8ef24b1b07078ababe5d91bcdf4f4264a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 12 Sep 2017 21:36:55 +0200 Subject: watchdog/hardlockup: Provide interface to stop/restart perf events Provide an interface to stop and restart perf NMI watchdog events on all CPUs. This is only usable during init and especially for handling the perf HT bug on Intel machines. It's safe to use it this way as nothing can start/stop the NMI watchdog in parallel. Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194146.167649596@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index a36abe2da13e..b24d4a58674a 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -75,7 +75,11 @@ static inline void hardlockup_detector_disable(void) {} #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) extern void arch_touch_nmi_watchdog(void); +extern void hardlockup_detector_perf_stop(void); +extern void hardlockup_detector_perf_restart(void); #else +static inline void hardlockup_detector_perf_stop(void) { } +static inline void hardlockup_detector_perf_restart(void) { } #if !defined(CONFIG_HAVE_NMI_WATCHDOG) static inline void arch_touch_nmi_watchdog(void) {} #endif -- cgit v1.2.3-71-gd317 From 6554fd8cf06db86f861bb24d7487b2873ca444c4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:36:57 +0200 Subject: watchdog/core: Provide interface to stop from poweroff() PARISC has a a busy looping power off routine. If the watchdog is enabled the watchdog timer will still fire, but the thread is not running, which causes the softlockup watchdog to trigger. Provide a interface which allows to turn the watchdog off. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Helge Deller Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Cc: linux-parisc@vger.kernel.org Link: http://lkml.kernel.org/r/20170912194146.327343752@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 6 +++--- kernel/watchdog.c | 14 +++++++++++++- 2 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index b24d4a58674a..85bb268be39c 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -12,10 +12,10 @@ #ifdef CONFIG_LOCKUP_DETECTOR void lockup_detector_init(void); +void lockup_detector_soft_poweroff(void); #else -static inline void lockup_detector_init(void) -{ -} +static inline void lockup_detector_init(void) { } +static inline void lockup_detector_soft_poweroff(void) { } #endif #ifdef CONFIG_SOFTLOCKUP_DETECTOR diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f5d52024f6b7..f23e373aa3bf 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -333,7 +333,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; - if (atomic_read(&watchdog_park_in_progress) != 0) + if (!watchdog_enabled || + atomic_read(&watchdog_park_in_progress) != 0) return HRTIMER_NORESTART; /* kick the hardlockup detector */ @@ -660,6 +661,17 @@ static void set_sample_period(void) } #endif /* SOFTLOCKUP */ +/** + * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) + * + * Special interface for parisc. It prevents lockup detector warnings from + * the default pm_poweroff() function which busy loops forever. + */ +void lockup_detector_soft_poweroff(void) +{ + watchdog_enabled = 0; +} + /* * Suspend the hard and soft lockup detector by parking the watchdog threads. */ -- cgit v1.2.3-71-gd317 From 5490125d77a43016b26f629d4b485e2c62172551 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:36:59 +0200 Subject: watchdog/core: Remove broken suspend/resume interfaces This interface has several issues: - It's causing recursive locking of the hotplug lock. - It's complete overkill to teardown all threads and then recreate them The same can be achieved with the simple hardlockup_detector_perf_stop / restart() interfaces. The abuse from the busy looping poweroff() loop of PARISC has been solved as well. Remove the cruft. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194146.487537732@linutronix.de Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/watchdog.c | 3 -- include/linux/nmi.h | 12 ------ kernel/watchdog.c | 89 +----------------------------------------- 3 files changed, 1 insertion(+), 103 deletions(-) (limited to 'include') diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 2f6eadd9408d..5ded171f02d6 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -310,9 +310,6 @@ static int start_wd_on_cpu(unsigned int cpu) if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) return 0; - if (watchdog_suspended) - return 0; - if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) return 0; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 85bb268be39c..7eefe7abf44b 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -164,7 +164,6 @@ extern int watchdog_thresh; extern unsigned long watchdog_enabled; extern struct cpumask watchdog_cpumask; extern unsigned long *watchdog_cpumask_bits; -extern int __read_mostly watchdog_suspended; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; @@ -192,17 +191,6 @@ extern int proc_watchdog_thresh(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int proc_watchdog_cpumask(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int lockup_detector_suspend(void); -extern void lockup_detector_resume(void); -#else -static inline int lockup_detector_suspend(void) -{ - return 0; -} - -static inline void lockup_detector_resume(void) -{ -} #endif #ifdef CONFIG_HAVE_ACPI_APEI_NMI diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f23e373aa3bf..b2d46757917e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -97,19 +97,6 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); * unregistered/stopped, so it is an indicator whether the threads exist. */ static int __read_mostly watchdog_running; -/* - * If a subsystem has a need to deactivate the watchdog temporarily, it - * can use the suspend/resume interface to achieve this. The content of - * the 'watchdog_suspended' variable reflects this state. Existing threads - * are parked/unparked by the lockup_detector_{suspend|resume} functions - * (see comment blocks pertaining to those functions for further details). - * - * 'watchdog_suspended' also prevents threads from being registered/started - * or unregistered/stopped via parameters in /proc/sys/kernel, so the state - * of 'watchdog_running' cannot change while the watchdog is deactivated - * temporarily (see related code in 'proc' handlers). - */ -int __read_mostly watchdog_suspended; /* * These functions can be overridden if an architecture implements its @@ -136,7 +123,6 @@ void __weak watchdog_nmi_disable(unsigned int cpu) * - watchdog_cpumask * - sysctl_hardlockup_all_cpu_backtrace * - hardlockup_panic - * - watchdog_suspended */ void __weak watchdog_nmi_reconfigure(void) { @@ -672,61 +658,6 @@ void lockup_detector_soft_poweroff(void) watchdog_enabled = 0; } -/* - * Suspend the hard and soft lockup detector by parking the watchdog threads. - */ -int lockup_detector_suspend(void) -{ - int ret = 0; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - /* - * Multiple suspend requests can be active in parallel (counted by - * the 'watchdog_suspended' variable). If the watchdog threads are - * running, the first caller takes care that they will be parked. - * The state of 'watchdog_running' cannot change while a suspend - * request is active (see related code in 'proc' handlers). - */ - if (watchdog_running && !watchdog_suspended) - ret = watchdog_park_threads(); - - if (ret == 0) - watchdog_suspended++; - else { - watchdog_disable_all_cpus(); - pr_err("Failed to suspend lockup detectors, disabled\n"); - watchdog_enabled = 0; - } - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - - return ret; -} - -/* - * Resume the hard and soft lockup detector by unparking the watchdog threads. - */ -void lockup_detector_resume(void) -{ - mutex_lock(&watchdog_proc_mutex); - - watchdog_suspended--; - /* - * The watchdog threads are unparked if they were previously running - * and if there is no more active suspend request. - */ - if (watchdog_running && !watchdog_suspended) - watchdog_unpark_threads(); - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); -} - #ifdef CONFIG_SYSCTL /* @@ -775,12 +706,6 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, get_online_cpus(); mutex_lock(&watchdog_proc_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } - /* * If the parameter is being read return the state of the corresponding * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the @@ -872,12 +797,6 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, get_online_cpus(); mutex_lock(&watchdog_proc_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } - old = ACCESS_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); @@ -917,12 +836,6 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, get_online_cpus(); mutex_lock(&watchdog_proc_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } - err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); if (!err && write) { /* Remove impossible cpus to keep sysctl output cleaner. */ @@ -941,7 +854,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, watchdog_nmi_reconfigure(); } -out: + mutex_unlock(&watchdog_proc_mutex); put_online_cpus(); return err; -- cgit v1.2.3-71-gd317 From 941154bd6937a710ae9193a3c733c0029e5ae7b8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:04 +0200 Subject: watchdog/hardlockup/perf: Prevent CPU hotplug deadlock The following deadlock is possible in the watchdog hotplug code: cpus_write_lock() ... takedown_cpu() smpboot_park_threads() smpboot_park_thread() kthread_park() ->park() := watchdog_disable() watchdog_nmi_disable() perf_event_release_kernel(); put_event() _free_event() ->destroy() := hw_perf_event_destroy() x86_release_hardware() release_ds_buffers() get_online_cpus() when a per cpu watchdog perf event is destroyed which drops the last reference to the PMU hardware. The cleanup code there invokes get_online_cpus() which instantly deadlocks because the hotplug percpu rwsem is write locked. To solve this add a deferring mechanism: cpus_write_lock() kthread_park() watchdog_nmi_disable(deferred) perf_event_disable(event); move_event_to_deferred(event); .... cpus_write_unlock() cleaup_deferred_events() perf_event_release_kernel() This is still properly serialized against concurrent hotplug via the cpu_add_remove_lock, which is held by the task which initiated the hotplug event. This is also used to handle event destruction when the watchdog threads are parked via other mechanisms than CPU hotplug. Analyzed-by: Peter Zijlstra Reported-by: Borislav Petkov Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194146.884469246@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 6 ++++++ kernel/cpu.c | 6 ++++++ kernel/watchdog.c | 25 +++++++++++++++++++++++++ kernel/watchdog_hld.c | 34 ++++++++++++++++++++++++++++------ 4 files changed, 65 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 7eefe7abf44b..80354e6fa86d 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -13,9 +13,11 @@ #ifdef CONFIG_LOCKUP_DETECTOR void lockup_detector_init(void); void lockup_detector_soft_poweroff(void); +void lockup_detector_cleanup(void); #else static inline void lockup_detector_init(void) { } static inline void lockup_detector_soft_poweroff(void) { } +static inline void lockup_detector_cleanup(void) { } #endif #ifdef CONFIG_SOFTLOCKUP_DETECTOR @@ -77,9 +79,13 @@ static inline void hardlockup_detector_disable(void) {} extern void arch_touch_nmi_watchdog(void); extern void hardlockup_detector_perf_stop(void); extern void hardlockup_detector_perf_restart(void); +extern void hardlockup_detector_perf_disable(void); +extern void hardlockup_detector_perf_cleanup(void); #else static inline void hardlockup_detector_perf_stop(void) { } static inline void hardlockup_detector_perf_restart(void) { } +static inline void hardlockup_detector_perf_disable(void) { } +static inline void hardlockup_detector_perf_cleanup(void) { } #if !defined(CONFIG_HAVE_NMI_WATCHDOG) static inline void arch_touch_nmi_watchdog(void) {} #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index acf5308fad51..a96b348591df 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -734,6 +735,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, out: cpus_write_unlock(); + /* + * Do post unplug cleanup. This is still protected against + * concurrent CPU hotplug via cpu_add_remove_lock. + */ + lockup_detector_cleanup(); return ret; } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index af000956286c..dd1fd59683c5 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -109,8 +109,10 @@ int __weak watchdog_nmi_enable(unsigned int cpu) { return 0; } + void __weak watchdog_nmi_disable(unsigned int cpu) { + hardlockup_detector_perf_disable(); } /* @@ -193,6 +195,8 @@ __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); #endif #endif +static void __lockup_detector_cleanup(void); + /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally @@ -631,6 +635,24 @@ static void set_sample_period(void) } #endif /* SOFTLOCKUP */ +static void __lockup_detector_cleanup(void) +{ + lockdep_assert_held(&watchdog_mutex); + hardlockup_detector_perf_cleanup(); +} + +/** + * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes + * + * Caller must not hold the cpu hotplug rwsem. + */ +void lockup_detector_cleanup(void) +{ + mutex_lock(&watchdog_mutex); + __lockup_detector_cleanup(); + mutex_unlock(&watchdog_mutex); +} + /** * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) * @@ -665,6 +687,8 @@ static int proc_watchdog_update(void) watchdog_nmi_reconfigure(); + __lockup_detector_cleanup(); + return err; } @@ -837,6 +861,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, } watchdog_nmi_reconfigure(); + __lockup_detector_cleanup(); } mutex_unlock(&watchdog_mutex); diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 7b602714ea53..94111ccb09b5 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -21,6 +21,8 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); +static DEFINE_PER_CPU(struct perf_event *, dead_event); +static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; static bool hardlockup_detector_disabled; @@ -239,16 +241,18 @@ out: return 0; } -void watchdog_nmi_disable(unsigned int cpu) +/** + * hardlockup_detector_perf_disable - Disable the local event + */ +void hardlockup_detector_perf_disable(void) { - struct perf_event *event = per_cpu(watchdog_ev, cpu); + struct perf_event *event = this_cpu_read(watchdog_ev); if (event) { perf_event_disable(event); - per_cpu(watchdog_ev, cpu) = NULL; - - /* should be in cleanup, but blocks oprofile */ - perf_event_release_kernel(event); + this_cpu_write(watchdog_ev, NULL); + this_cpu_write(dead_event, event); + cpumask_set_cpu(smp_processor_id(), &dead_events_mask); /* watchdog_nmi_enable() expects this to be zero initially. */ if (atomic_dec_and_test(&watchdog_cpus)) @@ -256,6 +260,24 @@ void watchdog_nmi_disable(unsigned int cpu) } } +/** + * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them + * + * Called from lockup_detector_cleanup(). Serialized by the caller. + */ +void hardlockup_detector_perf_cleanup(void) +{ + int cpu; + + for_each_cpu(cpu, &dead_events_mask) { + struct perf_event *event = per_cpu(dead_event, cpu); + + per_cpu(dead_event, cpu) = NULL; + perf_event_release_kernel(event); + } + cpumask_clear(&dead_events_mask); +} + /** * hardlockup_detector_perf_stop - Globally stop watchdog events * -- cgit v1.2.3-71-gd317 From 01f0a02701cbcf32d22cfc9d1ab9a3f0ff2ba68c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:05 +0200 Subject: watchdog/core: Remove the park_in_progress obfuscation Commit: b94f51183b06 ("kernel/watchdog: prevent false hardlockup on overloaded system") tries to fix the following issue: proc_write() set_sample_period() <--- New sample period becoms visible <----- Broken starts proc_watchdog_update() watchdog_enable_all_cpus() watchdog_hrtimer_fn() update_watchdog_all_cpus() restart_timer(sample_period) watchdog_park_threads() thread->park() disable_nmi() <----- Broken ends The reason why this is broken is that the update of the watchdog threshold becomes immediately effective and visible for the hrtimer function which uses that value to rearm the timer. But the NMI/perf side still uses the old value up to the point where it is disabled. If the rate has been lowered then the NMI can run fast enough to 'detect' a hard lockup because the timer has not fired due to the longer period. The patch 'fixed' this by adding a variable: proc_write() set_sample_period() <----- Broken starts proc_watchdog_update() watchdog_enable_all_cpus() watchdog_hrtimer_fn() update_watchdog_all_cpus() restart_timer(sample_period) watchdog_park_threads() park_in_progress = 1 <----- Broken ends nmi_watchdog() if (park_in_progress) return; The only effect of this variable was to make the window where the breakage can hit small enough that it was not longer observable in testing. From a correctness point of view it is a pointless bandaid which merily papers over the root cause: the unsychronized update of the variable. Looking deeper into the related code pathes unearthed similar problems in the watchdog_start()/stop() functions. watchdog_start() perf_nmi_event_start() hrtimer_start() watchdog_stop() hrtimer_cancel() perf_nmi_event_stop() In both cases the call order is wrong because if the tasks gets preempted or the VM gets scheduled out long enough after the first call, then there is a chance that the next NMI will see a stale hrtimer interrupt count and trigger a false positive hard lockup splat. Get rid of park_in_progress so the code can be gradually deobfuscated and pruned from several layers of duct tape papering over the root cause, which has been either ignored or not understood at all. Once this is removed the underlying problem will be fixed by rewriting the proc interface to do a proper synchronized update. Address the start/stop() ordering problem as well by reverting the call order, so this part is at least correct now. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1709052038270.2393@nanos Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 1 - kernel/watchdog.c | 37 +++++++++++++++++-------------------- kernel/watchdog_hld.c | 7 ++----- 3 files changed, 19 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 80354e6fa86d..91a3a4a4c8ae 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -27,7 +27,6 @@ extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; extern int soft_watchdog_enabled; -extern atomic_t watchdog_park_in_progress; #else static inline void touch_softlockup_watchdog_sched(void) { diff --git a/kernel/watchdog.c b/kernel/watchdog.c index dd1fd59683c5..c290135fb415 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -136,8 +136,6 @@ void __weak watchdog_nmi_reconfigure(void) #define for_each_watchdog_cpu(cpu) \ for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) -atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); - static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -322,8 +320,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; - if (!watchdog_enabled || - atomic_read(&watchdog_park_in_progress) != 0) + if (!watchdog_enabled) return HRTIMER_NORESTART; /* kick the hardlockup detector */ @@ -437,32 +434,37 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio) static void watchdog_enable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); - /* kick off the timer for the hardlockup detector */ + /* + * Start the timer first to prevent the NMI watchdog triggering + * before the timer has a chance to fire. + */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; + hrtimer_start(hrtimer, ns_to_ktime(sample_period), + HRTIMER_MODE_REL_PINNED); + /* Initialize timestamp */ + __touch_watchdog(); /* Enable the perf event */ watchdog_nmi_enable(cpu); - /* done here because hrtimer_start can only pin to smp_processor_id() */ - hrtimer_start(hrtimer, ns_to_ktime(sample_period), - HRTIMER_MODE_REL_PINNED); - - /* initialize timestamp */ watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); - __touch_watchdog(); } static void watchdog_disable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); watchdog_set_prio(SCHED_NORMAL, 0); - hrtimer_cancel(hrtimer); - /* disable the perf event */ + /* + * Disable the perf event first. That prevents that a large delay + * between disabling the timer and disabling the perf event causes + * the perf NMI to detect a false positive. + */ watchdog_nmi_disable(cpu); + hrtimer_cancel(hrtimer); } static void watchdog_cleanup(unsigned int cpu, bool online) @@ -518,16 +520,11 @@ static int watchdog_park_threads(void) { int cpu, ret = 0; - atomic_set(&watchdog_park_in_progress, 1); - for_each_watchdog_cpu(cpu) { ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); if (ret) break; } - - atomic_set(&watchdog_park_in_progress, 0); - return ret; } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 94111ccb09b5..0aa191ee3d51 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -106,15 +106,12 @@ static struct perf_event_attr wd_hw_attr = { /* Callback function for perf event subsystem */ static void watchdog_overflow_callback(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) + struct perf_sample_data *data, + struct pt_regs *regs) { /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; - if (atomic_read(&watchdog_park_in_progress) != 0) - return; - if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; -- cgit v1.2.3-71-gd317 From 0d85923c7a81719567311ba0eae8ecb2efd4c8a0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:09 +0200 Subject: smpboot/threads, watchdog/core: Avoid runtime allocation smpboot_update_cpumask_threads_percpu() allocates a temporary cpumask at runtime. This is suboptimal because the call site needs more code size for proper error handling than a statically allocated temporary mask requires data size. Add static temporary cpumask. The function is globaly serialized, so no further protection required. Remove the half baken error handling in the watchdog code and get rid of the export as there are no in tree modular users of that function. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.297288838@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/smpboot.h | 4 ++-- kernel/smpboot.c | 22 +++++++--------------- kernel/watchdog.c | 21 +++++---------------- 3 files changed, 14 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index 12910cf19869..c149aa7bedf3 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -55,7 +55,7 @@ smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) } void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread); -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *); +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *); #endif diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 1d71c051a951..ed7507b69b48 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -344,39 +344,31 @@ EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); * by the client, but only by calling this function. * This function can only be called on a registered smp_hotplug_thread. */ -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *new) +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *new) { struct cpumask *old = plug_thread->cpumask; - cpumask_var_t tmp; + static struct cpumask tmp; unsigned int cpu; - if (!alloc_cpumask_var(&tmp, GFP_KERNEL)) - return -ENOMEM; - get_online_cpus(); mutex_lock(&smpboot_threads_lock); /* Park threads that were exclusively enabled on the old mask. */ - cpumask_andnot(tmp, old, new); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, old, new); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_park_thread(plug_thread, cpu); /* Unpark threads that are exclusively enabled on the new mask. */ - cpumask_andnot(tmp, new, old); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, new, old); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_unpark_thread(plug_thread, cpu); cpumask_copy(old, new); mutex_unlock(&smpboot_threads_lock); put_online_cpus(); - - free_cpumask_var(tmp); - - return 0; } -EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread); static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index cedf45ab4d81..8935a3a4c2fb 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -787,31 +787,20 @@ out: return err; } -static int watchdog_update_cpus(void) +static void watchdog_update_cpus(void) { - if (IS_ENABLED(CONFIG_SOFTLOCKUP_DETECTOR)) { - return smpboot_update_cpumask_percpu_thread(&watchdog_threads, - &watchdog_cpumask); + if (IS_ENABLED(CONFIG_SOFTLOCKUP_DETECTOR) && watchdog_running) { + smpboot_update_cpumask_percpu_thread(&watchdog_threads, + &watchdog_cpumask); __lockup_detector_cleanup(); } - return 0; } static void proc_watchdog_cpumask_update(void) { /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); - - if (watchdog_running) { - /* - * Failure would be due to being unable to allocate a - * temporary cpumask, so we are likely not in a position to - * do much else to make things better. - */ - if (watchdog_update_cpus() != 0) - pr_err("cpumask update failed\n"); - } - + watchdog_update_cpus(); watchdog_nmi_reconfigure(); } -- cgit v1.2.3-71-gd317 From 3b371b5936e7777c819619c00ca60f196a8e13fa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:13 +0200 Subject: watchdog/core: Clean up header mess Having the same #ifdef in various places does not make it more readable. Collect stuff into one place. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.627096864@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 60 ++++++++++++++++++++++------------------------------- 1 file changed, 25 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 91a3a4a4c8ae..cfebb3bc4eed 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -14,11 +14,29 @@ void lockup_detector_init(void); void lockup_detector_soft_poweroff(void); void lockup_detector_cleanup(void); +bool is_hardlockup(void); + +extern int watchdog_user_enabled; +extern int nmi_watchdog_enabled; +extern int soft_watchdog_enabled; +extern int watchdog_thresh; +extern unsigned long watchdog_enabled; + +extern struct cpumask watchdog_cpumask; +extern unsigned long *watchdog_cpumask_bits; +#ifdef CONFIG_SMP +extern int sysctl_softlockup_all_cpu_backtrace; +extern int sysctl_hardlockup_all_cpu_backtrace; #else +#define sysctl_softlockup_all_cpu_backtrace 0 +#define sysctl_hardlockup_all_cpu_backtrace 0 +#endif /* !CONFIG_SMP */ + +#else /* CONFIG_LOCKUP_DETECTOR */ static inline void lockup_detector_init(void) { } static inline void lockup_detector_soft_poweroff(void) { } static inline void lockup_detector_cleanup(void) { } -#endif +#endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); @@ -26,28 +44,17 @@ extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; -extern int soft_watchdog_enabled; #else -static inline void touch_softlockup_watchdog_sched(void) -{ -} -static inline void touch_softlockup_watchdog(void) -{ -} -static inline void touch_softlockup_watchdog_sync(void) -{ -} -static inline void touch_all_softlockup_watchdogs(void) -{ -} +static inline void touch_softlockup_watchdog_sched(void) { } +static inline void touch_softlockup_watchdog(void) { } +static inline void touch_softlockup_watchdog_sync(void) { } +static inline void touch_all_softlockup_watchdogs(void) { } #endif #ifdef CONFIG_DETECT_HUNG_TASK void reset_hung_task_detector(void); #else -static inline void reset_hung_task_detector(void) -{ -} +static inline void reset_hung_task_detector(void) { } #endif /* @@ -92,7 +99,7 @@ static inline void arch_touch_nmi_watchdog(void) {} /** * touch_nmi_watchdog - restart NMI watchdog timeout. - * + * * If the architecture supports the NMI watchdog, touch_nmi_watchdog() * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. @@ -162,21 +169,6 @@ static inline bool trigger_single_cpu_backtrace(int cpu) u64 hw_nmi_get_sample_period(int watchdog_thresh); #endif -#ifdef CONFIG_LOCKUP_DETECTOR -extern int nmi_watchdog_enabled; -extern int watchdog_user_enabled; -extern int watchdog_thresh; -extern unsigned long watchdog_enabled; -extern struct cpumask watchdog_cpumask; -extern unsigned long *watchdog_cpumask_bits; -#ifdef CONFIG_SMP -extern int sysctl_softlockup_all_cpu_backtrace; -extern int sysctl_hardlockup_all_cpu_backtrace; -#else -#define sysctl_softlockup_all_cpu_backtrace 0 -#define sysctl_hardlockup_all_cpu_backtrace 0 -#endif - #if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ defined(CONFIG_HARDLOCKUP_DETECTOR) void watchdog_update_hrtimer_threshold(u64 period); @@ -184,7 +176,6 @@ void watchdog_update_hrtimer_threshold(u64 period); static inline void watchdog_update_hrtimer_threshold(u64 period) { } #endif -extern bool is_hardlockup(void); struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); @@ -196,7 +187,6 @@ extern int proc_watchdog_thresh(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int proc_watchdog_cpumask(struct ctl_table *, int, void __user *, size_t *, loff_t *); -#endif #ifdef CONFIG_HAVE_ACPI_APEI_NMI #include -- cgit v1.2.3-71-gd317 From 51d4052b01ca555e0d1d5fe297b309beb6c64aa0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:14 +0200 Subject: watchdog/sysctl: Get rid of the #ifdeffery The sysctl of the nmi_watchdog file prevents writes by setting: min = max = 0 if none of the users is enabled. That involves ifdeffery and is competely non obvious. If none of the facilities is enabeld, then the file can simply be made read only. Move the ifdeffery into the header and use a constant for file permissions. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.706073616@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 6 ++++++ kernel/sysctl.c | 6 +----- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index cfebb3bc4eed..5774b443dba1 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -81,6 +81,12 @@ extern unsigned int hardlockup_panic; static inline void hardlockup_detector_disable(void) {} #endif +#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) +# define NMI_WATCHDOG_SYSCTL_PERM 0644 +#else +# define NMI_WATCHDOG_SYSCTL_PERM 0444 +#endif + #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) extern void arch_touch_nmi_watchdog(void); extern void hardlockup_detector_perf_stop(void); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbbb8157..539cb4e97bb8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -891,14 +891,10 @@ static struct ctl_table kern_table[] = { .procname = "nmi_watchdog", .data = &nmi_watchdog_enabled, .maxlen = sizeof (int), - .mode = 0644, + .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, .extra1 = &zero, -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) .extra2 = &one, -#else - .extra2 = &zero, -#endif }, { .procname = "watchdog_cpumask", -- cgit v1.2.3-71-gd317 From 7feeb9cd4f5b34476ffb9e6d58d58c5416375b19 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:15 +0200 Subject: watchdog/sysctl: Clean up sysctl variable name space Reflect that these variables are user interface related and remove the whitespace damage in the sysctl table while at it. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.783210221@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 16 ++++++++-------- kernel/sysctl.c | 16 ++++++++-------- kernel/watchdog.c | 41 ++++++++++++++++++++--------------------- 3 files changed, 36 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 5774b443dba1..4a8d1037364e 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -17,8 +17,8 @@ void lockup_detector_cleanup(void); bool is_hardlockup(void); extern int watchdog_user_enabled; -extern int nmi_watchdog_enabled; -extern int soft_watchdog_enabled; +extern int nmi_watchdog_user_enabled; +extern int soft_watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; @@ -62,12 +62,12 @@ static inline void reset_hung_task_detector(void) { } * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit - * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector. * - * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled' - * are variables that are only used as an 'interface' between the parameters - * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The - * 'watchdog_thresh' variable is handled differently because its value is not - * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh' - * is equal zero. + * 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and + * 'soft_watchdog_user_enabled' are variables that are only used as an + * 'interface' between the parameters in /proc/sys/kernel and the internal + * state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is + * handled differently because its value is not boolean, and the lockup + * detectors are 'suspended' while 'watchdog_thresh' is equal zero. */ #define NMI_WATCHDOG_ENABLED_BIT 0 #define SOFT_WATCHDOG_ENABLED_BIT 1 diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 539cb4e97bb8..4c08ed4a379e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -871,9 +871,9 @@ static struct ctl_table kern_table[] = { #if defined(CONFIG_LOCKUP_DETECTOR) { .procname = "watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_watchdog, .extra1 = &zero, .extra2 = &one, @@ -889,8 +889,8 @@ static struct ctl_table kern_table[] = { }, { .procname = "nmi_watchdog", - .data = &nmi_watchdog_enabled, - .maxlen = sizeof (int), + .data = &nmi_watchdog_user_enabled, + .maxlen = sizeof(int), .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, .extra1 = &zero, @@ -906,9 +906,9 @@ static struct ctl_table kern_table[] = { #ifdef CONFIG_SOFTLOCKUP_DETECTOR { .procname = "soft_watchdog", - .data = &soft_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &soft_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_soft_watchdog, .extra1 = &zero, .extra2 = &one, diff --git a/kernel/watchdog.c b/kernel/watchdog.c index ca8747221e87..baae9fc95031 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -31,8 +31,6 @@ static DEFINE_MUTEX(watchdog_mutex); -int __read_mostly nmi_watchdog_enabled; - #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED; @@ -40,6 +38,17 @@ unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; #endif +int __read_mostly nmi_watchdog_user_enabled; +int __read_mostly soft_watchdog_user_enabled; +int __read_mostly watchdog_user_enabled; +int __read_mostly watchdog_thresh = 10; + +struct cpumask watchdog_allowed_mask __read_mostly; +static bool softlockup_threads_initialized __read_mostly; + +struct cpumask watchdog_cpumask __read_mostly; +unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); + #ifdef CONFIG_HARDLOCKUP_DETECTOR /* * Should we panic when a soft-lockup or hard-lockup occurs: @@ -85,12 +94,6 @@ __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); # endif /* CONFIG_SMP */ #endif /* CONFIG_HARDLOCKUP_DETECTOR */ -int __read_mostly watchdog_user_enabled; -int __read_mostly watchdog_thresh = 10; - -struct cpumask watchdog_cpumask __read_mostly; -unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); - /* * These functions can be overridden if an architecture implements its * own hardlockup detector. @@ -113,7 +116,7 @@ void __weak watchdog_nmi_disable(unsigned int cpu) * watchdog_nmi_reconfigure can be implemented to be notified after any * watchdog configuration change. The arch hardlockup watchdog should * respond to the following variables: - * - nmi_watchdog_enabled + * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask * - sysctl_hardlockup_all_cpu_backtrace @@ -126,10 +129,6 @@ void __weak watchdog_nmi_reconfigure(void) { } /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; -int __read_mostly soft_watchdog_enabled; - -struct cpumask watchdog_allowed_mask __read_mostly; -static bool softlockup_threads_initialized __read_mostly; static u64 __read_mostly sample_period; @@ -606,14 +605,14 @@ static void proc_watchdog_update(void) /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * - * caller | table->data points to | 'which' contains the flag(s) - * -------------------|-----------------------|----------------------------- - * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed - * | | with SOFT_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_nmi_watchdog | nmi_watchdog_enabled | NMI_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED + * caller | table->data points to | 'which' + * -------------------|----------------------------|-------------------------- + * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED | + * | | SOFT_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_nmi_watchdog | nmi_watchdog_user_enabled | NMI_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED */ static int proc_watchdog_common(int which, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) -- cgit v1.2.3-71-gd317 From 6592ad2fcc8f15b4f99b36c1db7d9f65510c203b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:16 +0200 Subject: watchdog/core, powerpc: Make watchdog_nmi_reconfigure() two stage Both the perf reconfiguration and the powerpc watchdog_nmi_reconfigure() need to be done in two steps. 1) Stop all NMIs 2) Read the new parameters and start NMIs Right now watchdog_nmi_reconfigure() is a combination of both. To allow a clean reconfiguration add a 'run' argument and split the functionality in powerpc. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20170912194147.862865570@linutronix.de Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/watchdog.c | 17 +++++++++-------- include/linux/nmi.h | 2 ++ kernel/watchdog.c | 31 ++++++++++++++++++++++--------- 3 files changed, 33 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 5ded171f02d6..291af79a9826 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -355,17 +355,18 @@ static void watchdog_calc_timeouts(void) wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5; } -void watchdog_nmi_reconfigure(void) +void watchdog_nmi_reconfigure(bool run) { int cpu; - watchdog_calc_timeouts(); - - for_each_cpu(cpu, &wd_cpus_enabled) - stop_wd_on_cpu(cpu); - - for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) - start_wd_on_cpu(cpu); + if (!run) { + for_each_cpu(cpu, &wd_cpus_enabled) + stop_wd_on_cpu(cpu); + } else { + watchdog_calc_timeouts(); + for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) + start_wd_on_cpu(cpu); + } } /* diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 4a8d1037364e..eee255bc0fd6 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -103,6 +103,8 @@ static inline void arch_touch_nmi_watchdog(void) {} #endif #endif +void watchdog_nmi_reconfigure(bool run); + /** * touch_nmi_watchdog - restart NMI watchdog timeout. * diff --git a/kernel/watchdog.c b/kernel/watchdog.c index baae9fc95031..5693afd2b8ea 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -112,17 +112,25 @@ void __weak watchdog_nmi_disable(unsigned int cpu) hardlockup_detector_perf_disable(); } -/* - * watchdog_nmi_reconfigure can be implemented to be notified after any - * watchdog configuration change. The arch hardlockup watchdog should - * respond to the following variables: +/** + * watchdog_nmi_reconfigure - Optional function to reconfigure NMI watchdogs + * @run: If false stop the watchdogs on all enabled CPUs + * If true start the watchdogs on all enabled CPUs + * + * The core call order is: + * watchdog_nmi_reconfigure(false); + * update_variables(); + * watchdog_nmi_reconfigure(true); + * + * The second call which starts the watchdogs again guarantees that the + * following variables are stable across the call. * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask - * - sysctl_hardlockup_all_cpu_backtrace - * - hardlockup_panic + * + * After the call the variables can be changed again. */ -void __weak watchdog_nmi_reconfigure(void) { } +void __weak watchdog_nmi_reconfigure(bool run) { } #ifdef CONFIG_SOFTLOCKUP_DETECTOR @@ -515,10 +523,12 @@ static void softlockup_unpark_threads(void) static void softlockup_reconfigure_threads(bool enabled) { + watchdog_nmi_reconfigure(false); softlockup_park_all_threads(); set_sample_period(); if (enabled) softlockup_unpark_threads(); + watchdog_nmi_reconfigure(true); } /* @@ -559,7 +569,11 @@ static inline void watchdog_unpark_threads(void) { } static inline int watchdog_enable_all_cpus(void) { return 0; } static inline void watchdog_disable_all_cpus(void) { } static inline void softlockup_init_threads(void) { } -static inline void softlockup_reconfigure_threads(bool enabled) { } +static void softlockup_reconfigure_threads(bool enabled) +{ + watchdog_nmi_reconfigure(false); + watchdog_nmi_reconfigure(true); +} #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_cleanup(void) @@ -599,7 +613,6 @@ static void proc_watchdog_update(void) /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); softlockup_reconfigure_threads(watchdog_enabled && watchdog_thresh); - watchdog_nmi_reconfigure(); } /* -- cgit v1.2.3-71-gd317 From 178b9f7a36d2c74a38274b66dd89f53611298a19 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:18 +0200 Subject: watchdog/hardlockup/perf: Implement init time perf validation The watchdog tries to create perf events even after it figured out that perf is not functional or the requested event is not supported. That's braindead as this can be done once at init time and if not supported the NMI watchdog can be turned off unconditonally. Implement the perf hardlockup detector functionality for that. This creates a new event create function, which will replace the unholy mess of the existing one in later patches. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194148.019090547@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 8 ++++++-- kernel/watchdog_hld.c | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index eee255bc0fd6..72c62a809e92 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -93,14 +93,18 @@ extern void hardlockup_detector_perf_stop(void); extern void hardlockup_detector_perf_restart(void); extern void hardlockup_detector_perf_disable(void); extern void hardlockup_detector_perf_cleanup(void); +extern int hardlockup_detector_perf_init(void); #else static inline void hardlockup_detector_perf_stop(void) { } static inline void hardlockup_detector_perf_restart(void) { } static inline void hardlockup_detector_perf_disable(void) { } static inline void hardlockup_detector_perf_cleanup(void) { } -#if !defined(CONFIG_HAVE_NMI_WATCHDOG) +# if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline int hardlockup_detector_perf_init(void) { return -ENODEV; } static inline void arch_touch_nmi_watchdog(void) {} -#endif +# else +static inline int hardlockup_detector_perf_init(void) { return 0; } +# endif #endif void watchdog_nmi_reconfigure(bool run); diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 0aa191ee3d51..f7e752e6e9b4 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -238,6 +238,27 @@ out: return 0; } +static int hardlockup_detector_event_create(void) +{ + unsigned int cpu = smp_processor_id(); + struct perf_event_attr *wd_attr; + struct perf_event *evt; + + wd_attr = &wd_hw_attr; + wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); + + /* Try to register using hardware perf events */ + evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, + watchdog_overflow_callback, NULL); + if (IS_ERR(evt)) { + pr_info("Perf event create on CPU %d failed with %ld\n", cpu, + PTR_ERR(evt)); + return PTR_ERR(evt); + } + this_cpu_write(watchdog_ev, evt); + return 0; +} + /** * hardlockup_detector_perf_disable - Disable the local event */ @@ -315,3 +336,19 @@ void __init hardlockup_detector_perf_restart(void) perf_event_enable(event); } } + +/** + * hardlockup_detector_perf_init - Probe whether NMI event is available at all + */ +int __init hardlockup_detector_perf_init(void) +{ + int ret = hardlockup_detector_event_create(); + + if (ret) { + pr_info("Perf NMI watchdog permanetely disabled\n"); + } else { + perf_event_release_kernel(this_cpu_read(watchdog_ev)); + this_cpu_write(watchdog_ev, NULL); + } + return ret; +} -- cgit v1.2.3-71-gd317 From 2a1b8ee4f5665b4291e43e4a25d964c3eb2f4c32 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:20 +0200 Subject: watchdog/hardlockup/perf: Implement CPU enable replacement watchdog_nmi_enable() is an unparseable mess, Provide a clean perf specific implementation, which will be used when the existing setup/teardown mess is replaced. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194148.180215498@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 2 ++ kernel/watchdog_hld.c | 11 +++++++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 72c62a809e92..89ba8b23c6fe 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -92,12 +92,14 @@ extern void arch_touch_nmi_watchdog(void); extern void hardlockup_detector_perf_stop(void); extern void hardlockup_detector_perf_restart(void); extern void hardlockup_detector_perf_disable(void); +extern void hardlockup_detector_perf_enable(void); extern void hardlockup_detector_perf_cleanup(void); extern int hardlockup_detector_perf_init(void); #else static inline void hardlockup_detector_perf_stop(void) { } static inline void hardlockup_detector_perf_restart(void) { } static inline void hardlockup_detector_perf_disable(void) { } +static inline void hardlockup_detector_perf_enable(void) { } static inline void hardlockup_detector_perf_cleanup(void) { } # if !defined(CONFIG_HAVE_NMI_WATCHDOG) static inline int hardlockup_detector_perf_init(void) { return -ENODEV; } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index f7e752e6e9b4..99a3f22e48cc 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -259,6 +259,17 @@ static int hardlockup_detector_event_create(void) return 0; } +/** + * hardlockup_detector_perf_enable - Enable the local event + */ +void hardlockup_detector_perf_enable(void) +{ + if (hardlockup_detector_event_create()) + return; + + perf_event_enable(this_cpu_read(watchdog_ev)); +} + /** * hardlockup_detector_perf_disable - Disable the local event */ -- cgit v1.2.3-71-gd317 From e6b72ee88a56bcfe63f72e9c30766484c45bec72 Mon Sep 17 00:00:00 2001 From: Artem Savkov Date: Tue, 26 Sep 2017 18:35:45 +0200 Subject: netfilter: ebtables: fix race condition in frame_filter_net_init() It is possible for ebt_in_hook to be triggered before ebt_table is assigned resulting in a NULL-pointer dereference. Make sure hooks are registered as the last step. Fixes: aee12a0a3727 ("ebtables: remove nf_hook_register usage") Signed-off-by: Artem Savkov Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge/ebtables.h | 7 ++++--- net/bridge/netfilter/ebtable_broute.c | 4 ++-- net/bridge/netfilter/ebtable_filter.c | 4 ++-- net/bridge/netfilter/ebtable_nat.c | 4 ++-- net/bridge/netfilter/ebtables.c | 17 +++++++++-------- 5 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 2c2a5514b0df..528b24c78308 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -108,9 +108,10 @@ struct ebt_table { #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ ~(__alignof__(struct _xt_align)-1)) -extern struct ebt_table *ebt_register_table(struct net *net, - const struct ebt_table *table, - const struct nf_hook_ops *); +extern int ebt_register_table(struct net *net, + const struct ebt_table *table, + const struct nf_hook_ops *ops, + struct ebt_table **res); extern void ebt_unregister_table(struct net *net, struct ebt_table *table, const struct nf_hook_ops *); extern unsigned int ebt_do_table(struct sk_buff *skb, diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 2585b100ebbb..276b60262981 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -65,8 +65,8 @@ static int ebt_broute(struct sk_buff *skb) static int __net_init broute_net_init(struct net *net) { - net->xt.broute_table = ebt_register_table(net, &broute_table, NULL); - return PTR_ERR_OR_ZERO(net->xt.broute_table); + return ebt_register_table(net, &broute_table, NULL, + &net->xt.broute_table); } static void __net_exit broute_net_exit(struct net *net) diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 45a00dbdbcad..c41da5fac84f 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -93,8 +93,8 @@ static const struct nf_hook_ops ebt_ops_filter[] = { static int __net_init frame_filter_net_init(struct net *net) { - net->xt.frame_filter = ebt_register_table(net, &frame_filter, ebt_ops_filter); - return PTR_ERR_OR_ZERO(net->xt.frame_filter); + return ebt_register_table(net, &frame_filter, ebt_ops_filter, + &net->xt.frame_filter); } static void __net_exit frame_filter_net_exit(struct net *net) diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 57cd5bb154e7..08df7406ecb3 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -93,8 +93,8 @@ static const struct nf_hook_ops ebt_ops_nat[] = { static int __net_init frame_nat_net_init(struct net *net) { - net->xt.frame_nat = ebt_register_table(net, &frame_nat, ebt_ops_nat); - return PTR_ERR_OR_ZERO(net->xt.frame_nat); + return ebt_register_table(net, &frame_nat, ebt_ops_nat, + &net->xt.frame_nat); } static void __net_exit frame_nat_net_exit(struct net *net) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 83951f978445..3b3dcf719e07 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1169,9 +1169,8 @@ static void __ebt_unregister_table(struct net *net, struct ebt_table *table) kfree(table); } -struct ebt_table * -ebt_register_table(struct net *net, const struct ebt_table *input_table, - const struct nf_hook_ops *ops) +int ebt_register_table(struct net *net, const struct ebt_table *input_table, + const struct nf_hook_ops *ops, struct ebt_table **res) { struct ebt_table_info *newinfo; struct ebt_table *t, *table; @@ -1183,7 +1182,7 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table, repl->entries == NULL || repl->entries_size == 0 || repl->counters != NULL || input_table->private != NULL) { BUGPRINT("Bad table data for ebt_register_table!!!\n"); - return ERR_PTR(-EINVAL); + return -EINVAL; } /* Don't add one table to multiple lists. */ @@ -1252,16 +1251,18 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table, list_add(&table->list, &net->xt.tables[NFPROTO_BRIDGE]); mutex_unlock(&ebt_mutex); + WRITE_ONCE(*res, table); + if (!ops) - return table; + return 0; ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); if (ret) { __ebt_unregister_table(net, table); - return ERR_PTR(ret); + *res = NULL; } - return table; + return ret; free_unlock: mutex_unlock(&ebt_mutex); free_chainstack: @@ -1276,7 +1277,7 @@ free_newinfo: free_table: kfree(table); out: - return ERR_PTR(ret); + return ret; } void ebt_unregister_table(struct net *net, struct ebt_table *table, -- cgit v1.2.3-71-gd317 From 28a0bc4120d38a394499382ba21d6965a67a3703 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 27 Sep 2017 21:35:12 -0400 Subject: scsi: sd: Implement blacklist option for WRITE SAME w/ UNMAP SBC-4 states: "A MAXIMUM UNMAP LBA COUNT field set to a non-zero value indicates the maximum number of LBAs that may be unmapped by an UNMAP command" "A MAXIMUM WRITE SAME LENGTH field set to a non-zero value indicates the maximum number of contiguous logical blocks that the device server allows to be unmapped or written in a single WRITE SAME command." Despite the spec being clear on the topic, some devices incorrectly expect WRITE SAME commands with the UNMAP bit set to be limited to the value reported in MAXIMUM UNMAP LBA COUNT in the Block Limits VPD. Implement a blacklist option that can be used to accommodate devices with this behavior. Cc: Reported-by: Bill Kuzeja Reported-by: Ewan D. Milne Reviewed-by: Ewan D. Milne Tested-by: Laurence Oberman Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_scan.c | 3 +++ drivers/scsi/sd.c | 16 ++++++++++++---- include/scsi/scsi_device.h | 1 + include/scsi/scsi_devinfo.h | 1 + 4 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index e7818afeda2b..15590a063ad9 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -956,6 +956,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, if (*bflags & BLIST_NO_DIF) sdev->no_dif = 1; + if (*bflags & BLIST_UNMAP_LIMIT_WS) + sdev->unmap_limit_for_ws = 1; + sdev->eh_timeout = SCSI_DEFAULT_EH_TIMEOUT; if (*bflags & BLIST_TRY_VPD_PAGES) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index fb9f8b5f4673..3d26a729825c 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -715,13 +715,21 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) break; case SD_LBP_WS16: - max_blocks = min_not_zero(sdkp->max_ws_blocks, - (u32)SD_MAX_WS16_BLOCKS); + if (sdkp->device->unmap_limit_for_ws) + max_blocks = sdkp->max_unmap_blocks; + else + max_blocks = sdkp->max_ws_blocks; + + max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS16_BLOCKS); break; case SD_LBP_WS10: - max_blocks = min_not_zero(sdkp->max_ws_blocks, - (u32)SD_MAX_WS10_BLOCKS); + if (sdkp->device->unmap_limit_for_ws) + max_blocks = sdkp->max_unmap_blocks; + else + max_blocks = sdkp->max_ws_blocks; + + max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS10_BLOCKS); break; case SD_LBP_ZERO: diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 82e93ee94708..67c5a9f223f7 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -192,6 +192,7 @@ struct scsi_device { unsigned no_dif:1; /* T10 PI (DIF) should be disabled */ unsigned broken_fua:1; /* Don't set FUA bit */ unsigned lun_in_cdb:1; /* Store LUN bits in CDB[1] */ + unsigned unmap_limit_for_ws:1; /* Use the UNMAP limit for WRITE SAME */ atomic_t disk_events_disable_depth; /* disable depth for disk events */ diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h index 9592570e092a..36b03013d629 100644 --- a/include/scsi/scsi_devinfo.h +++ b/include/scsi/scsi_devinfo.h @@ -29,5 +29,6 @@ #define BLIST_TRY_VPD_PAGES 0x10000000 /* Attempt to read VPD pages */ #define BLIST_NO_RSOC 0x20000000 /* don't try to issue RSOC */ #define BLIST_MAX_1024 0x40000000 /* maximum 1024 sector cdb length */ +#define BLIST_UNMAP_LIMIT_WS 0x80000000 /* Use UNMAP limit for WRITE SAME */ #endif -- cgit v1.2.3-71-gd317 From 1c048a250aae1aaab0ba9dbec908f0c6cdb8614f Mon Sep 17 00:00:00 2001 From: Khazhismel Kumykov Date: Thu, 13 Jul 2017 09:11:22 -0700 Subject: scsi: libiscsi: Remove iscsi_destroy_session iscsi_session_teardown was the only user of this function. Function currently is just short for iscsi_remove_session + iscsi_free_session. Signed-off-by: Khazhismel Kumykov Acked-by: Chris Leech Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_iscsi.c | 16 ---------------- include/scsi/scsi_transport_iscsi.h | 1 - 2 files changed, 17 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 0190aeff5f7f..7404d26895f5 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2210,22 +2210,6 @@ void iscsi_free_session(struct iscsi_cls_session *session) } EXPORT_SYMBOL_GPL(iscsi_free_session); -/** - * iscsi_destroy_session - destroy iscsi session - * @session: iscsi_session - * - * Can be called by a LLD or iscsi_transport. There must not be - * any running connections. - */ -int iscsi_destroy_session(struct iscsi_cls_session *session) -{ - iscsi_remove_session(session); - ISCSI_DBG_TRANS_SESSION(session, "Completing session destruction\n"); - iscsi_free_session(session); - return 0; -} -EXPORT_SYMBOL_GPL(iscsi_destroy_session); - /** * iscsi_create_conn - create iscsi class connection * @session: iscsi cls session diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 6183d20a01fb..b266d2a3bcb1 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -434,7 +434,6 @@ extern struct iscsi_cls_session *iscsi_create_session(struct Scsi_Host *shost, unsigned int target_id); extern void iscsi_remove_session(struct iscsi_cls_session *session); extern void iscsi_free_session(struct iscsi_cls_session *session); -extern int iscsi_destroy_session(struct iscsi_cls_session *session); extern struct iscsi_cls_conn *iscsi_create_conn(struct iscsi_cls_session *sess, int dd_size, uint32_t cid); extern int iscsi_destroy_conn(struct iscsi_cls_conn *conn); -- cgit v1.2.3-71-gd317 From de3ee99b097dd51938276e3af388cd4ad0f2750a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 20 Sep 2017 10:56:14 +0200 Subject: mmc: Delete bounce buffer handling In may, Steven sent a patch deleting the bounce buffer handling and the CONFIG_MMC_BLOCK_BOUNCE option. I chose the less invasive path of making it a runtime config option, and we merged that successfully for kernel v4.12. The code is however just standing in the way and taking up space for seemingly no gain on any systems in wide use today. Pierre says the code was there to improve speed on TI SDHCI controllers on certain HP laptops and possibly some Ricoh controllers as well. Early SDHCI controllers lacked the scatter-gather feature, which made software bounce buffers a significant speed boost. We are clearly talking about the list of SDHCI PCI-based MMC/SD card readers found in the pci_ids[] list in drivers/mmc/host/sdhci-pci-core.c. The TI SDHCI derivative is not supported by the upstream kernel. This leaves the Ricoh. What we can however notice is that the x86 defconfigs in the kernel did not enable CONFIG_MMC_BLOCK_BOUNCE option, which means that any such laptop would have to have a custom configured kernel to actually take advantage of this bounce buffer speed-up. It simply seems like there was a speed optimization for the Ricoh controllers that noone was using. (I have not checked the distro defconfigs but I am pretty sure the situation is the same there.) Bounce buffers increased performance on the OMAP HSMMC at one point, and was part of the original submission in commit a45c6cb81647 ("[ARM] 5369/1: omap mmc: Add new omap hsmmc controller for 2430 and 34xx, v3") This optimization was removed in commit 0ccd76d4c236 ("omap_hsmmc: Implement scatter-gather emulation") which found that scatter-gather emulation provided even better performance. The same was introduced for SDHCI in commit 2134a922c6e7 ("sdhci: scatter-gather (ADMA) support") I am pretty positively convinced that software scatter-gather emulation will do for any host controller what the bounce buffers were doing. Essentially, the bounce buffer was a reimplementation of software scatter-gather-emulation in the MMC subsystem, and it should be done away with. Cc: Pierre Ossman Cc: Juha Yrjola Cc: Steven J. Hill Cc: Shawn Lin Cc: Adrian Hunter Suggested-by: Steven J. Hill Suggested-by: Shawn Lin Signed-off-by: Linus Walleij Signed-off-by: Ulf Hansson --- drivers/mmc/core/block.c | 3 -- drivers/mmc/core/queue.c | 125 ++++------------------------------------------ drivers/mmc/core/queue.h | 6 --- drivers/mmc/host/cavium.c | 2 +- drivers/mmc/host/pxamci.c | 6 +-- include/linux/mmc/host.h | 2 +- 6 files changed, 12 insertions(+), 132 deletions(-) (limited to 'include') diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 29fc1e662891..2ad7b5c69156 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1634,8 +1634,6 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq, } mqrq->areq.mrq = &brq->mrq; - - mmc_queue_bounce_pre(mqrq); } static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, @@ -1829,7 +1827,6 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req) brq = &mq_rq->brq; old_req = mmc_queue_req_to_req(mq_rq); type = rq_data_dir(old_req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE; - mmc_queue_bounce_post(mq_rq); switch (status) { case MMC_BLK_SUCCESS: diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 74c663b1c0a7..0a4e77a5ba33 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -23,8 +23,6 @@ #include "core.h" #include "card.h" -#define MMC_QUEUE_BOUNCESZ 65536 - /* * Prepare a MMC request. This just filters out odd stuff. */ @@ -150,26 +148,6 @@ static void mmc_queue_setup_discard(struct request_queue *q, queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, q); } -static unsigned int mmc_queue_calc_bouncesz(struct mmc_host *host) -{ - unsigned int bouncesz = MMC_QUEUE_BOUNCESZ; - - if (host->max_segs != 1 || (host->caps & MMC_CAP_NO_BOUNCE_BUFF)) - return 0; - - if (bouncesz > host->max_req_size) - bouncesz = host->max_req_size; - if (bouncesz > host->max_seg_size) - bouncesz = host->max_seg_size; - if (bouncesz > host->max_blk_count * 512) - bouncesz = host->max_blk_count * 512; - - if (bouncesz <= 512) - return 0; - - return bouncesz; -} - /** * mmc_init_request() - initialize the MMC-specific per-request data * @q: the request queue @@ -184,26 +162,9 @@ static int mmc_init_request(struct request_queue *q, struct request *req, struct mmc_card *card = mq->card; struct mmc_host *host = card->host; - if (card->bouncesz) { - mq_rq->bounce_buf = kmalloc(card->bouncesz, gfp); - if (!mq_rq->bounce_buf) - return -ENOMEM; - if (card->bouncesz > 512) { - mq_rq->sg = mmc_alloc_sg(1, gfp); - if (!mq_rq->sg) - return -ENOMEM; - mq_rq->bounce_sg = mmc_alloc_sg(card->bouncesz / 512, - gfp); - if (!mq_rq->bounce_sg) - return -ENOMEM; - } - } else { - mq_rq->bounce_buf = NULL; - mq_rq->bounce_sg = NULL; - mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp); - if (!mq_rq->sg) - return -ENOMEM; - } + mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp); + if (!mq_rq->sg) + return -ENOMEM; return 0; } @@ -212,13 +173,6 @@ static void mmc_exit_request(struct request_queue *q, struct request *req) { struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req); - /* It is OK to kfree(NULL) so this will be smooth */ - kfree(mq_rq->bounce_sg); - mq_rq->bounce_sg = NULL; - - kfree(mq_rq->bounce_buf); - mq_rq->bounce_buf = NULL; - kfree(mq_rq->sg); mq_rq->sg = NULL; } @@ -242,12 +196,6 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask) limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT; - /* - * mmc_init_request() depends on card->bouncesz so it must be calculated - * before blk_init_allocated_queue() starts allocating requests. - */ - card->bouncesz = mmc_queue_calc_bouncesz(host); - mq->card = card; mq->queue = blk_alloc_queue(GFP_KERNEL); if (!mq->queue) @@ -271,17 +219,11 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, if (mmc_can_erase(card)) mmc_queue_setup_discard(mq->queue, card); - if (card->bouncesz) { - blk_queue_max_hw_sectors(mq->queue, card->bouncesz / 512); - blk_queue_max_segments(mq->queue, card->bouncesz / 512); - blk_queue_max_segment_size(mq->queue, card->bouncesz); - } else { - blk_queue_bounce_limit(mq->queue, limit); - blk_queue_max_hw_sectors(mq->queue, - min(host->max_blk_count, host->max_req_size / 512)); - blk_queue_max_segments(mq->queue, host->max_segs); - blk_queue_max_segment_size(mq->queue, host->max_seg_size); - } + blk_queue_bounce_limit(mq->queue, limit); + blk_queue_max_hw_sectors(mq->queue, + min(host->max_blk_count, host->max_req_size / 512)); + blk_queue_max_segments(mq->queue, host->max_segs); + blk_queue_max_segment_size(mq->queue, host->max_seg_size); sema_init(&mq->thread_sem, 1); @@ -370,56 +312,7 @@ void mmc_queue_resume(struct mmc_queue *mq) */ unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq) { - unsigned int sg_len; - size_t buflen; - struct scatterlist *sg; struct request *req = mmc_queue_req_to_req(mqrq); - int i; - - if (!mqrq->bounce_buf) - return blk_rq_map_sg(mq->queue, req, mqrq->sg); - - sg_len = blk_rq_map_sg(mq->queue, req, mqrq->bounce_sg); - - mqrq->bounce_sg_len = sg_len; - - buflen = 0; - for_each_sg(mqrq->bounce_sg, sg, sg_len, i) - buflen += sg->length; - - sg_init_one(mqrq->sg, mqrq->bounce_buf, buflen); - - return 1; -} - -/* - * If writing, bounce the data to the buffer before the request - * is sent to the host driver - */ -void mmc_queue_bounce_pre(struct mmc_queue_req *mqrq) -{ - if (!mqrq->bounce_buf) - return; - - if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != WRITE) - return; - - sg_copy_to_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len, - mqrq->bounce_buf, mqrq->sg[0].length); -} - -/* - * If reading, bounce the data from the buffer after the request - * has been handled by the host driver - */ -void mmc_queue_bounce_post(struct mmc_queue_req *mqrq) -{ - if (!mqrq->bounce_buf) - return; - - if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != READ) - return; - sg_copy_from_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len, - mqrq->bounce_buf, mqrq->sg[0].length); + return blk_rq_map_sg(mq->queue, req, mqrq->sg); } diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h index 04fc89360a7a..f18d3f656baa 100644 --- a/drivers/mmc/core/queue.h +++ b/drivers/mmc/core/queue.h @@ -49,9 +49,6 @@ enum mmc_drv_op { struct mmc_queue_req { struct mmc_blk_request brq; struct scatterlist *sg; - char *bounce_buf; - struct scatterlist *bounce_sg; - unsigned int bounce_sg_len; struct mmc_async_req areq; enum mmc_drv_op drv_op; int drv_op_result; @@ -81,11 +78,8 @@ extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *, extern void mmc_cleanup_queue(struct mmc_queue *); extern void mmc_queue_suspend(struct mmc_queue *); extern void mmc_queue_resume(struct mmc_queue *); - extern unsigned int mmc_queue_map_sg(struct mmc_queue *, struct mmc_queue_req *); -extern void mmc_queue_bounce_pre(struct mmc_queue_req *); -extern void mmc_queue_bounce_post(struct mmc_queue_req *); extern int mmc_access_rpmb(struct mmc_queue *); diff --git a/drivers/mmc/host/cavium.c b/drivers/mmc/host/cavium.c index 27fb625cbcf3..fbd29f00fca0 100644 --- a/drivers/mmc/host/cavium.c +++ b/drivers/mmc/host/cavium.c @@ -1038,7 +1038,7 @@ int cvm_mmc_of_slot_probe(struct device *dev, struct cvm_mmc_host *host) */ mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED | MMC_CAP_ERASE | MMC_CAP_CMD23 | MMC_CAP_POWER_OFF_CARD | - MMC_CAP_3_3V_DDR | MMC_CAP_NO_BOUNCE_BUFF; + MMC_CAP_3_3V_DDR; if (host->use_sg) mmc->max_segs = 16; diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index 59ab194cb009..c763b404510f 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -702,11 +702,7 @@ static int pxamci_probe(struct platform_device *pdev) pxamci_init_ocr(host); - /* - * This architecture used to disable bounce buffers through its - * defconfig, now it is done at runtime as a host property. - */ - mmc->caps = MMC_CAP_NO_BOUNCE_BUFF; + mmc->caps = 0; host->cmdat = 0; if (!cpu_is_pxa25x()) { mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_SDIO_IRQ; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index f3f2d07feb2a..9a43763a68ad 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -316,7 +316,7 @@ struct mmc_host { #define MMC_CAP_UHS_SDR50 (1 << 18) /* Host supports UHS SDR50 mode */ #define MMC_CAP_UHS_SDR104 (1 << 19) /* Host supports UHS SDR104 mode */ #define MMC_CAP_UHS_DDR50 (1 << 20) /* Host supports UHS DDR50 mode */ -#define MMC_CAP_NO_BOUNCE_BUFF (1 << 21) /* Disable bounce buffers on host */ +/* (1 << 21) is free for reuse */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ -- cgit v1.2.3-71-gd317 From 6b9dc4806b28214a4a260517e59439e0ac12a15e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 2 Oct 2017 12:34:50 +0200 Subject: watchdog/core, powerpc: Replace watchdog_nmi_reconfigure() The recent cleanup of the watchdog code split watchdog_nmi_reconfigure() into two stages. One to stop the NMI and one to restart it after reconfiguration. That was done by adding a boolean 'run' argument to the code, which is functionally correct but not necessarily a piece of art. Replace it by two explicit functions: watchdog_nmi_stop() and watchdog_nmi_start(). Fixes: 6592ad2fcc8f ("watchdog/core, powerpc: Make watchdog_nmi_reconfigure() two stage") Requested-by: Linus 'Nursing his pet-peeve' Torvalds Signed-off-by: Thomas 'Mopping up garbage' Gleixner Acked-by: Michael Ellerman Cc: Peter Zijlstra Cc: Don Zickus Cc: Benjamin Herrenschmidt Cc: Nicholas Piggin Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1710021957480.2114@nanos --- arch/powerpc/kernel/watchdog.c | 23 ++++++++++++++--------- include/linux/nmi.h | 3 ++- kernel/watchdog.c | 33 ++++++++++++++++++--------------- 3 files changed, 34 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index dfb067764480..2673ec8bec00 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -355,19 +355,24 @@ static void watchdog_calc_timeouts(void) wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5; } -void watchdog_nmi_reconfigure(bool run) +void watchdog_nmi_stop(void) { int cpu; cpus_read_lock(); - if (!run) { - for_each_cpu(cpu, &wd_cpus_enabled) - stop_wd_on_cpu(cpu); - } else { - watchdog_calc_timeouts(); - for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) - start_wd_on_cpu(cpu); - } + for_each_cpu(cpu, &wd_cpus_enabled) + stop_wd_on_cpu(cpu); + cpus_read_unlock(); +} + +void watchdog_nmi_start(void) +{ + int cpu; + + cpus_read_lock(); + watchdog_calc_timeouts(); + for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) + start_wd_on_cpu(cpu); cpus_read_unlock(); } diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 89ba8b23c6fe..0c9ed49fb21a 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -109,7 +109,8 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } # endif #endif -void watchdog_nmi_reconfigure(bool run); +void watchdog_nmi_stop(void); +void watchdog_nmi_start(void); /** * touch_nmi_watchdog - restart NMI watchdog timeout. diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f6ef163b72cd..6ad6226535d0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -123,24 +123,27 @@ int __weak __init watchdog_nmi_probe(void) } /** - * watchdog_nmi_reconfigure - Optional function to reconfigure NMI watchdogs - * @run: If false stop the watchdogs on all enabled CPUs - * If true start the watchdogs on all enabled CPUs + * watchdog_nmi_stop - Stop the watchdog for reconfiguration * - * The core call order is: - * watchdog_nmi_reconfigure(false); + * The reconfiguration steps are: + * watchdog_nmi_stop(); * update_variables(); - * watchdog_nmi_reconfigure(true); + * watchdog_nmi_start(); + */ +void __weak watchdog_nmi_stop(void) { } + +/** + * watchdog_nmi_start - Start the watchdog after reconfiguration * - * The second call which starts the watchdogs again guarantees that the - * following variables are stable across the call. + * Counterpart to watchdog_nmi_stop(). + * + * The following variables have been updated in update_variables() and + * contain the currently valid configuration: * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask - * - * After the call the variables can be changed again. */ -void __weak watchdog_nmi_reconfigure(bool run) { } +void __weak watchdog_nmi_start(void) { } /** * lockup_detector_update_enable - Update the sysctl enable bit @@ -551,13 +554,13 @@ static void softlockup_unpark_threads(void) static void softlockup_reconfigure_threads(void) { - watchdog_nmi_reconfigure(false); + watchdog_nmi_stop(); softlockup_park_all_threads(); set_sample_period(); lockup_detector_update_enable(); if (watchdog_enabled && watchdog_thresh) softlockup_unpark_threads(); - watchdog_nmi_reconfigure(true); + watchdog_nmi_start(); } /* @@ -602,9 +605,9 @@ static inline void watchdog_disable_all_cpus(void) { } static inline void softlockup_init_threads(void) { } static void softlockup_reconfigure_threads(void) { - watchdog_nmi_reconfigure(false); + watchdog_nmi_stop(); lockup_detector_update_enable(); - watchdog_nmi_reconfigure(true); + watchdog_nmi_start(); } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ -- cgit v1.2.3-71-gd317 From 34ddaa3e5c0096fef52485186c7eb6cf56ddc686 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 3 Oct 2017 16:39:02 +0200 Subject: powerpc/watchdog: Make use of watchdog_nmi_probe() The rework of the core hotplug code triggers the WARN_ON in start_wd_cpu() on powerpc because it is called multiple times for the boot CPU. The first call is via: start_wd_on_cpu+0x80/0x2f0 watchdog_nmi_reconfigure+0x124/0x170 softlockup_reconfigure_threads+0x110/0x130 lockup_detector_init+0xbc/0xe0 kernel_init_freeable+0x18c/0x37c kernel_init+0x2c/0x160 ret_from_kernel_thread+0x5c/0xbc And then again via the CPU hotplug registration: start_wd_on_cpu+0x80/0x2f0 cpuhp_invoke_callback+0x194/0x620 cpuhp_thread_fun+0x7c/0x1b0 smpboot_thread_fn+0x290/0x2a0 kthread+0x168/0x1b0 ret_from_kernel_thread+0x5c/0xbc This can be avoided by setting up the cpu hotplug state with nocalls and move the initialization to the watchdog_nmi_probe() function. That initializes the hotplug callbacks without invoking the callback and the following core initialization function then configures the watchdog for the online CPUs (in this case CPU0) via softlockup_reconfigure_threads(). Reported-and-tested-by: Michael Ellerman Signed-off-by: Thomas Gleixner Acked-by: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Nicholas Piggin Cc: linuxppc-dev@lists.ozlabs.org --- arch/powerpc/kernel/watchdog.c | 17 ++++++++--------- include/linux/nmi.h | 1 + kernel/watchdog.c | 5 ++++- 3 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index f9b4c6352d24..c702a8981452 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -373,22 +373,21 @@ void watchdog_nmi_start(void) } /* - * This runs after lockup_detector_init() which sets up watchdog_cpumask. + * Invoked from core watchdog init. */ -static int __init powerpc_watchdog_init(void) +int __init watchdog_nmi_probe(void) { int err; - watchdog_calc_timeouts(); - - err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/watchdog:online", - start_wd_on_cpu, stop_wd_on_cpu); - if (err < 0) + err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "powerpc/watchdog:online", + start_wd_on_cpu, stop_wd_on_cpu); + if (err < 0) { pr_warn("Watchdog could not be initialized"); - + return err; + } return 0; } -arch_initcall(powerpc_watchdog_init); static void handle_backtrace_ipi(struct pt_regs *regs) { diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 0c9ed49fb21a..27e249ed7c5c 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -111,6 +111,7 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } void watchdog_nmi_stop(void); void watchdog_nmi_start(void); +int watchdog_nmi_probe(void); /** * touch_nmi_watchdog - restart NMI watchdog timeout. diff --git a/kernel/watchdog.c b/kernel/watchdog.c index fff90fe10007..5c6fb7cd9ae8 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -608,7 +608,6 @@ static inline int watchdog_park_threads(void) { return 0; } static inline void watchdog_unpark_threads(void) { } static inline int watchdog_enable_all_cpus(void) { return 0; } static inline void watchdog_disable_all_cpus(void) { } -static inline void softlockup_init_threads(void) { } static void softlockup_reconfigure_threads(void) { cpus_read_lock(); @@ -617,6 +616,10 @@ static void softlockup_reconfigure_threads(void) watchdog_nmi_start(); cpus_read_unlock(); } +static inline void softlockup_init_threads(void) +{ + softlockup_reconfigure_threads(); +} #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_cleanup(void) -- cgit v1.2.3-71-gd317 From 98589a0998b8b13c4a8fa1ccb0e62751a019faa5 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Mon, 9 Oct 2017 15:27:15 +0300 Subject: netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1' Commit 2c16d6033264 ("netfilter: xt_bpf: support ebpf") introduced support for attaching an eBPF object by an fd, with the 'bpf_mt_check_v1' ABI expecting the '.fd' to be specified upon each IPT_SO_SET_REPLACE call. However this breaks subsequent iptables calls: # iptables -A INPUT -m bpf --object-pinned /sys/fs/bpf/xxx -j ACCEPT # iptables -A INPUT -s 5.6.7.8 -j ACCEPT iptables: Invalid argument. Run `dmesg' for more information. That's because iptables works by loading existing rules using IPT_SO_GET_ENTRIES to userspace, then issuing IPT_SO_SET_REPLACE with the replacement set. However, the loaded 'xt_bpf_info_v1' has an arbitrary '.fd' number (from the initial "iptables -m bpf" invocation) - so when 2nd invocation occurs, userspace passes a bogus fd number, which leads to 'bpf_mt_check_v1' to fail. One suggested solution [1] was to hack iptables userspace, to perform a "entries fixup" immediatley after IPT_SO_GET_ENTRIES, by opening a new, process-local fd per every 'xt_bpf_info_v1' entry seen. However, in [2] both Pablo Neira Ayuso and Willem de Bruijn suggested to depricate the xt_bpf_info_v1 ABI dealing with pinned ebpf objects. This fix changes the XT_BPF_MODE_FD_PINNED behavior to ignore the given '.fd' and instead perform an in-kernel lookup for the bpf object given the provided '.path'. It also defines an alias for the XT_BPF_MODE_FD_PINNED mode, named XT_BPF_MODE_PATH_PINNED, to better reflect the fact that the user is expected to provide the path of the pinned object. Existing XT_BPF_MODE_FD_ELF behavior (non-pinned fd mode) is preserved. References: [1] https://marc.info/?l=netfilter-devel&m=150564724607440&w=2 [2] https://marc.info/?l=netfilter-devel&m=150575727129880&w=2 Reported-by: Rafael Buchbinder Signed-off-by: Shmulik Ladkani Acked-by: Willem de Bruijn Acked-by: Daniel Borkmann Signed-off-by: Pablo Neira Ayuso --- include/linux/bpf.h | 5 +++++ include/uapi/linux/netfilter/xt_bpf.h | 1 + kernel/bpf/inode.c | 1 + net/netfilter/xt_bpf.c | 22 ++++++++++++++++++++-- 4 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8390859e79e7..f1af7d63d678 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -368,6 +368,11 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } +static inline int bpf_obj_get_user(const char __user *pathname) +{ + return -EOPNOTSUPP; +} + static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index b97725af2ac0..da161b56c79e 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -23,6 +23,7 @@ enum xt_bpf_modes { XT_BPF_MODE_FD_PINNED, XT_BPF_MODE_FD_ELF, }; +#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED struct xt_bpf_info_v1 { __u16 mode; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index e833ed914358..be1dde967208 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -363,6 +363,7 @@ out: putname(pname); return ret; } +EXPORT_SYMBOL_GPL(bpf_obj_get_user); static void bpf_evict_inode(struct inode *inode) { diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 38986a95216c..29123934887b 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -49,6 +50,22 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) return 0; } +static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) +{ + mm_segment_t oldfs = get_fs(); + int retval, fd; + + set_fs(KERNEL_DS); + fd = bpf_obj_get_user(path); + set_fs(oldfs); + if (fd < 0) + return fd; + + retval = __bpf_mt_check_fd(fd, ret); + sys_close(fd); + return retval; +} + static int bpf_mt_check(const struct xt_mtchk_param *par) { struct xt_bpf_info *info = par->matchinfo; @@ -66,9 +83,10 @@ static int bpf_mt_check_v1(const struct xt_mtchk_param *par) return __bpf_mt_check_bytecode(info->bpf_program, info->bpf_program_num_elem, &info->filter); - else if (info->mode == XT_BPF_MODE_FD_PINNED || - info->mode == XT_BPF_MODE_FD_ELF) + else if (info->mode == XT_BPF_MODE_FD_ELF) return __bpf_mt_check_fd(info->fd, &info->filter); + else if (info->mode == XT_BPF_MODE_PATH_PINNED) + return __bpf_mt_check_path(info->path, &info->filter); else return -EINVAL; } -- cgit v1.2.3-71-gd317