From 80d767d770fd9c697e434fd080c2db7b5c60c6dd Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Fri, 24 Jan 2014 16:41:36 -0500 Subject: time: Fix overflow when HZ is smaller than 60 When compiling for the IA-64 ski emulator, HZ is set to 32 because the emulation is slow and we don't want to waste too many cycles processing timers. Alpha also has an option to set HZ to 32. This causes integer underflow in kernel/time/jiffies.c: kernel/time/jiffies.c:66:2: warning: large integer implicitly truncated to unsigned type [-Woverflow] .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */ ^ This patch reduces the JIFFIES_SHIFT value to avoid the overflow. Signed-off-by: Mikulas Patocka Link: http://lkml.kernel.org/r/alpine.LRH.2.02.1401241639100.23871@file01.intranet.prod.int.rdu2.redhat.com Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner --- kernel/time/jiffies.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel') diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 7a925ba456fb..a6a5bf53e86d 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -51,7 +51,13 @@ * HZ shrinks, so values greater than 8 overflow 32bits when * HZ=100. */ +#if HZ < 34 +#define JIFFIES_SHIFT 6 +#elif HZ < 67 +#define JIFFIES_SHIFT 7 +#else #define JIFFIES_SHIFT 8 +#endif static cycle_t jiffies_read(struct clocksource *cs) { -- cgit v1.2.2 From 2c45aada341121438affc4cb8d5b4cfaa2813d3d Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Mon, 10 Feb 2014 13:39:53 -0500 Subject: genirq: Add missing irq_to_desc export for CONFIG_SPARSE_IRQ=n In allmodconfig builds for sparc and any other arch which does not set CONFIG_SPARSE_IRQ, the following will be seen at modpost: CC [M] lib/cpu-notifier-error-inject.o CC [M] lib/pm-notifier-error-inject.o ERROR: "irq_to_desc" [drivers/gpio/gpio-mcp23s08.ko] undefined! make[2]: *** [__modpost] Error 1 This happens because commit 3911ff30f5 ("genirq: export handle_edge_irq() and irq_to_desc()") added one export for it, but there were actually two instances of it, in an if/else clause for CONFIG_SPARSE_IRQ. Add the second one. Signed-off-by: Paul Gortmaker Cc: Jiri Kosina Cc: stable@vger.kernel.org # 3.4+ Link: http://lkml.kernel.org/r/1392057610-11514-1-git-send-email-paul.gortmaker@windriver.com Signed-off-by: Thomas Gleixner --- kernel/irq/irqdesc.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 192a302d6cfd..8ab8e9390297 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -274,6 +274,7 @@ struct irq_desc *irq_to_desc(unsigned int irq) { return (irq < NR_IRQS) ? irq_desc + irq : NULL; } +EXPORT_SYMBOL(irq_to_desc); static void free_desc(unsigned int irq) { -- cgit v1.2.2 From d651aa1d68a2f0a7ee65697b04c6a92f8c0a12f2 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 11 Feb 2014 13:38:54 -0500 Subject: ring-buffer: Fix first commit on sub-buffer having non-zero delta Each sub-buffer (buffer page) has a full 64 bit timestamp. The events on that page use a 27 bit delta against that timestamp in order to save on bits written to the ring buffer. If the time between events is larger than what the 27 bits can hold, a "time extend" event is added to hold the entire 64 bit timestamp again and the events after that hold a delta from that timestamp. As a "time extend" is always paired with an event, it is logical to just allocate the event with the time extend, to make things a bit more efficient. Unfortunately, when the pairing code was written, it removed the "delta = 0" from the first commit on a page, causing the events on the page to be slightly skewed. Fixes: 69d1b839f7ee "ring-buffer: Bind time extend and data events together" Cc: stable@vger.kernel.org # 2.6.37+ Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 294b8a271a04..fc4da2d97f9b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2397,6 +2397,13 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, write &= RB_WRITE_MASK; tail = write - length; + /* + * If this is the first commit on the page, then it has the same + * timestamp as the page itself. + */ + if (!tail) + delta = 0; + /* See if we shot pass the end of this buffer page */ if (unlikely(write > BUF_PAGE_SIZE)) return rb_move_tail(cpu_buffer, length, tail, -- cgit v1.2.2 From dd5fd9b91a77b4c9c28b7ef9c181b1a875820d0a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 11 Feb 2014 14:35:40 +0100 Subject: tick: Clear broadcast pending bit when switching to oneshot AMD systems which use the C1E workaround in the amd_e400_idle routine trigger the WARN_ON_ONCE in the broadcast code when onlining a CPU. The reason is that the idle routine of those AMD systems switches the cpu into forced broadcast mode early on before the newly brought up CPU can switch over to high resolution / NOHZ mode. The timer related CPU1 bringup looks like this: clockevent_register_device(local_apic); tick_setup(local_apic); ... idle() tick_broadcast_on_off(FORCE); tick_broadcast_oneshot_control(ENTER) cpumask_set(cpu, broadcast_oneshot_mask); halt(); Now the broadcast interrupt on CPU0 sets CPU1 in the broadcast_pending_mask and wakes CPU1. So CPU1 continues: local_apic_timer_interrupt() tick_handle_periodic(); softirq() tick_init_highres(); cpumask_clr(cpu, broadcast_oneshot_mask); tick_broadcast_oneshot_control(ENTER) WARN_ON(cpumask_test(cpu, broadcast_pending_mask); So while we remove CPU1 from the broadcast_oneshot_mask when we switch over to highres mode, we do not clear the pending bit, which then triggers the warning when we go back to idle. The reason why this is only visible on C1E affected AMD systems is that the other machines enter the deep sleep states via acpi_idle/intel_idle and exit the broadcast mode before executing the remote triggered local_apic_timer_interrupt. So the pending bit is already cleared when the switch over to highres mode is clearing the oneshot mask. The solution is simple: Clear the pending bit together with the mask bit when we switch over to highres mode. Stanislaw came up independently with the same patch by enforcing the C1E workaround and debugging the fallout. I picked mine, because mine has a changelog :) Reported-by: poma Debugged-by: Stanislaw Gruszka Signed-off-by: Thomas Gleixner Cc: Olaf Hering Cc: Dave Jones Cc: Justin M. Forbes Cc: Josh Boyer Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1402111434180.21991@ionos.tec.linutronix.de Cc: stable@vger.kernel.org # 3.10+ Signed-off-by: Thomas Gleixner --- kernel/time/tick-broadcast.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 43780ab5e279..98977a57ac72 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -756,6 +756,7 @@ out: static void tick_broadcast_clear_oneshot(int cpu) { cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); + cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); } static void tick_broadcast_init_next_event(struct cpumask *mask, -- cgit v1.2.2 From 18258f7239a61d8929b8e0c7b6d46c446459074c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 15 Feb 2014 00:55:18 +0000 Subject: genirq: Provide synchronize_hardirq() synchronize_irq() waits for hard irq and threaded handlers to complete before returning. For some special cases we only need to make sure that the hard interrupt part of the irq line is not in progress when we disabled the - possibly shared - interrupt at the device level. A proper use case for this was provided by Russell. The sdhci driver requires some irq triggered functions to be run in thread context. The current implementation of the thread context is a sdio private kthread construct, which has quite some shortcomings. These can be avoided when the thread is directly associated to the device interrupt via the generic threaded irq infrastructure. Though there is a corner case related to run time power management where one side disables the device interrupts at the device level and needs to make sure, that an already running hard interrupt handler has completed before proceeding further. Though that hard interrupt handler might wake the associated thread, which in turn can request the runtime PM to reenable the device. Using synchronize_irq() leads to an immediate deadlock of the irq thread waiting for the PM lock and the synchronize_irq() waiting for the irq thread to complete. Due to the fact that it is sufficient for this case to ensure that no hard irq handler is executing a new function which avoids the check for the thread is required. Add a function, which just monitors the hard irq parts and ignores the threaded handlers. Signed-off-by: Thomas Gleixner Tested-by: Russell King Cc: Chris Ball Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140215003823.653236081@linutronix.de --- kernel/irq/manage.c | 70 ++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 50 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 481a13c43b17..274ba9238fb7 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -32,24 +32,10 @@ static int __init setup_forced_irqthreads(char *arg) early_param("threadirqs", setup_forced_irqthreads); #endif -/** - * synchronize_irq - wait for pending IRQ handlers (on other CPUs) - * @irq: interrupt number to wait for - * - * This function waits for any pending IRQ handlers for this interrupt - * to complete before returning. If you use this function while - * holding a resource the IRQ handler may need you will deadlock. - * - * This function may be called - with care - from IRQ context. - */ -void synchronize_irq(unsigned int irq) +static void __synchronize_hardirq(struct irq_desc *desc) { - struct irq_desc *desc = irq_to_desc(irq); bool inprogress; - if (!desc) - return; - do { unsigned long flags; @@ -67,12 +53,56 @@ void synchronize_irq(unsigned int irq) /* Oops, that failed? */ } while (inprogress); +} - /* - * We made sure that no hardirq handler is running. Now verify - * that no threaded handlers are active. - */ - wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active)); +/** + * synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs) + * @irq: interrupt number to wait for + * + * This function waits for any pending hard IRQ handlers for this + * interrupt to complete before returning. If you use this + * function while holding a resource the IRQ handler may need you + * will deadlock. It does not take associated threaded handlers + * into account. + * + * Do not use this for shutdown scenarios where you must be sure + * that all parts (hardirq and threaded handler) have completed. + * + * This function may be called - with care - from IRQ context. + */ +void synchronize_hardirq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc) + __synchronize_hardirq(desc); +} +EXPORT_SYMBOL(synchronize_hardirq); + +/** + * synchronize_irq - wait for pending IRQ handlers (on other CPUs) + * @irq: interrupt number to wait for + * + * This function waits for any pending IRQ handlers for this interrupt + * to complete before returning. If you use this function while + * holding a resource the IRQ handler may need you will deadlock. + * + * This function may be called - with care - from IRQ context. + */ +void synchronize_irq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc) { + __synchronize_hardirq(desc); + /* + * We made sure that no hardirq handler is + * running. Now verify that no threaded handlers are + * active. + */ + wait_event(desc->wait_for_threads, + !atomic_read(&desc->threads_active)); + } } EXPORT_SYMBOL(synchronize_irq); -- cgit v1.2.2 From a92444c6b2225a9115d661c950cb48a22aeace20 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 15 Feb 2014 00:55:19 +0000 Subject: genirq: Provide irq_wake_thread() In course of the sdhci/sdio discussion with Russell about killing the sdio kthread hackery we discovered the need to be able to wake an interrupt thread from software. The rationale for this is, that sdio hardware can lack proper interrupt support for certain features. So the driver needs to poll the status registers, but at the same time it needs to be woken up by an hardware interrupt. To be able to get rid of the home brewn kthread construct of sdio we need a way to wake an irq thread independent of an actual hardware interrupt. Provide an irq_wake_thread() function which wakes up the thread which is associated to a given dev_id. This allows sdio to invoke the irq thread from the hardware irq handler via the IRQ_WAKE_THREAD return value and provides a possibility to wake it via a timer for the polling scenarios. That allows to simplify the sdio logic significantly. Signed-off-by: Thomas Gleixner Cc: Russell King Cc: Chris Ball Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140215003823.772565780@linutronix.de --- kernel/irq/handle.c | 4 ++-- kernel/irq/internals.h | 1 + kernel/irq/manage.c | 27 +++++++++++++++++++++++++++ 3 files changed, 30 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 131ca176b497..bfec453557b4 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -51,7 +51,7 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action) "but no thread function available.", irq, action->name); } -static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action) +void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action) { /* * In case the thread crashed and was killed we just pretend that @@ -157,7 +157,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) break; } - irq_wake_thread(desc, action); + __irq_wake_thread(desc, action); /* Fall through to add to randomness */ case IRQ_HANDLED: diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 001fa5bab490..d61ac29e32d0 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -82,6 +82,7 @@ irqreturn_t handle_irq_event(struct irq_desc *desc); /* Resending of interrupts :*/ void check_irq_resend(struct irq_desc *desc, unsigned int irq); bool irq_wait_for_poll(struct irq_desc *desc); +void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action); #ifdef CONFIG_PROC_FS extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 274ba9238fb7..54eb5c99351b 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -911,6 +911,33 @@ static int irq_thread(void *data) return 0; } +/** + * irq_wake_thread - wake the irq thread for the action identified by dev_id + * @irq: Interrupt line + * @dev_id: Device identity for which the thread should be woken + * + */ +void irq_wake_thread(unsigned int irq, void *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irqaction *action; + unsigned long flags; + + if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) + return; + + raw_spin_lock_irqsave(&desc->lock, flags); + for (action = desc->action; action; action = action->next) { + if (action->dev_id == dev_id) { + if (action->thread) + __irq_wake_thread(desc, action); + break; + } + } + raw_spin_unlock_irqrestore(&desc->lock, flags); +} +EXPORT_SYMBOL_GPL(irq_wake_thread); + static void irq_setup_forced_threading(struct irqaction *new) { if (!force_irqthreads) -- cgit v1.2.2