From 4fe757dd48a9e95e1a071291f15dda5421dacb66 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Feb 2011 22:26:07 +0100 Subject: perf: Fix throttle logic It was possible to call pmu::start() on an already running event. In particular this lead so some wreckage as the hrtimer events would re-initialize active timers. This was due to throttled events being activated again by scheduling. Scheduling in a context would add and force start events, resulting in running events with a possible throttle status. The next tick to hit that task will then try to unthrottle the event and call ->start() on an already running event. Reported-by: Jeff Moyer Cc: Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 999835b6112b..656222fcf767 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -782,6 +782,10 @@ retry: raw_spin_unlock_irq(&ctx->lock); } +#define MAX_INTERRUPTS (~0ULL) + +static void perf_log_throttle(struct perf_event *event, int enable); + static int event_sched_in(struct perf_event *event, struct perf_cpu_context *cpuctx, @@ -794,6 +798,17 @@ event_sched_in(struct perf_event *event, event->state = PERF_EVENT_STATE_ACTIVE; event->oncpu = smp_processor_id(); + + /* + * Unthrottle events, since we scheduled we might have missed several + * ticks already, also for a heavily scheduling task there is little + * guarantee it'll get a tick in a timely manner. + */ + if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) { + perf_log_throttle(event, 1); + event->hw.interrupts = 0; + } + /* * The new state must be visible before we turn it on in the hardware: */ @@ -1596,10 +1611,6 @@ void __perf_event_task_sched_in(struct task_struct *task) } } -#define MAX_INTERRUPTS (~0ULL) - -static void perf_log_throttle(struct perf_event *event, int enable); - static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count) { u64 frequency = event->attr.sample_freq; -- cgit v1.2.3 From c1ee6264280e740a9d3ff3feef38642cf0a57013 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 17 Feb 2011 17:45:15 +0100 Subject: genirq: Prevent access beyond allocated_irqs bitmap Lars-Peter Clausen pointed out: I stumbled upon this while looking through the existing archs using SPARSE_IRQ. Even with SPARSE_IRQ the NR_IRQS is still the upper limit for the number of IRQs. Both PXA and MMP set NR_IRQS to IRQ_BOARD_START, with IRQ_BOARD_START being the number of IRQs used by the core. In various machine files the nr_irqs field of the ARM machine defintion struct is then set to "IRQ_BOARD_START + NR_BOARD_IRQS". As a result "nr_irqs" will greater then NR_IRQS which then again causes the "allocated_irqs" bitmap in the core irq code to be accessed beyond its size overwriting unrelated data. The core code really misses a sanity check there. This went unnoticed so far as by chance the compiler/linker places data behind that bitmap which gets initialized later on those affected platforms. So the obvious fix would be to add a sanity check in early_irq_init() and break all affected platforms. Though that check wants to be backported to stable as well, which will require to fix all known problematic platforms and probably some more yet not known ones as well. Lots of churn. A way simpler solution is to allocate a slightly larger bitmap and avoid the whole churn w/o breaking anything. Add a few warnings when an arch returns utter crap. Reported-by: Lars-Peter Clausen Signed-off-by: Thomas Gleixner Cc: stable@kernel.org # .37 Cc: Haojian Zhuang Cc: Eric Miao Cc: Peter Zijlstra --- kernel/irq/internals.h | 6 ++++++ kernel/irq/irqdesc.c | 11 ++++++++++- kernel/irq/resend.c | 2 +- 3 files changed, 17 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 4571ae7e085a..99c3bc8a6fb4 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -3,6 +3,12 @@ */ #include +#ifdef CONFIG_SPARSE_IRQ +# define IRQ_BITMAP_BITS (NR_IRQS + 8196) +#else +# define IRQ_BITMAP_BITS NR_IRQS +#endif + extern int noirqdebug; #define irq_data_to_desc(data) container_of(data, struct irq_desc, irq_data) diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 282f20230e67..2039bea31bdf 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -94,7 +94,7 @@ int nr_irqs = NR_IRQS; EXPORT_SYMBOL_GPL(nr_irqs); static DEFINE_MUTEX(sparse_irq_lock); -static DECLARE_BITMAP(allocated_irqs, NR_IRQS); +static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS); #ifdef CONFIG_SPARSE_IRQ @@ -217,6 +217,15 @@ int __init early_irq_init(void) initcnt = arch_probe_nr_irqs(); printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt); + if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS)) + nr_irqs = IRQ_BITMAP_BITS; + + if (WARN_ON(initcnt > IRQ_BITMAP_BITS)) + initcnt = IRQ_BITMAP_BITS; + + if (initcnt > nr_irqs) + nr_irqs = initcnt; + for (i = 0; i < initcnt; i++) { desc = alloc_desc(i, node); set_bit(i, allocated_irqs); diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index 891115a929aa..dc49358b73fa 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -23,7 +23,7 @@ #ifdef CONFIG_HARDIRQS_SW_RESEND /* Bitmap to handle software resend of interrupts: */ -static DECLARE_BITMAP(irqs_resend, NR_IRQS); +static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS); /* * Run software resends of IRQ's -- cgit v1.2.3 From 6d83f94db95cfe65d2a6359cccdf61cf087c2598 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 18 Feb 2011 23:27:23 +0100 Subject: genirq: Disable the SHIRQ_DEBUG call in request_threaded_irq for now With CONFIG_SHIRQ_DEBUG=y we call a newly installed interrupt handler in request_threaded_irq(). The original implementation (commit a304e1b8) called the handler _BEFORE_ it was installed, but that caused problems with handlers calling disable_irq_nosync(). See commit 377bf1e4. It's braindead in the first place to call disable_irq_nosync in shared handlers, but .... Moving this call after we installed the handler looks innocent, but it is very subtle broken on SMP. Interrupt handlers rely on the fact, that the irq core prevents reentrancy. Now this debug call violates that promise because we run the handler w/o the IRQ_INPROGRESS protection - which we cannot apply here because that would result in a possibly forever masked interrupt line. A concurrent real hardware interrupt on a different CPU results in handler reentrancy and can lead to complete wreckage, which was unfortunately observed in reality and took a fricking long time to debug. Leave the code here for now. We want this debug feature, but that's not easy to fix. We really should get rid of those disable_irq_nosync() abusers and remove that function completely. Signed-off-by: Thomas Gleixner Cc: Anton Vorontsov Cc: David Woodhouse Cc: Arjan van de Ven Cc: stable@kernel.org # .28 -> .37 --- kernel/irq/manage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0caa59f747dd..9033c1c70828 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1100,7 +1100,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, if (retval) kfree(action); -#ifdef CONFIG_DEBUG_SHIRQ +#ifdef CONFIG_DEBUG_SHIRQ_FIXME if (!retval && (irqflags & IRQF_SHARED)) { /* * It's a shared IRQ -- the driver ought to be prepared for it -- cgit v1.2.3 From 3a142a0672b48a853f00af61f184c7341ac9c99d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 Feb 2011 22:34:23 +0100 Subject: clockevents: Prevent oneshot mode when broadcast device is periodic When the per cpu timer is marked CLOCK_EVT_FEAT_C3STOP, then we only can switch into oneshot mode, when the backup broadcast device supports oneshot mode as well. Otherwise we would try to switch the broadcast device into an unsupported mode unconditionally. This went unnoticed so far as the current available broadcast devices support oneshot mode. Seth unearthed this problem while debugging and working around an hpet related BIOS wreckage. Add the necessary check to tick_is_oneshot_available(). Reported-and-tested-by: Seth Forshee Signed-off-by: Thomas Gleixner LKML-Reference: Cc: stable@kernel.org # .21 -> --- kernel/time/tick-broadcast.c | 10 ++++++++++ kernel/time/tick-common.c | 6 +++++- kernel/time/tick-internal.h | 3 +++ 3 files changed, 18 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 48b2761b5668..a3b5aff62606 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -600,4 +600,14 @@ int tick_broadcast_oneshot_active(void) return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT; } +/* + * Check whether the broadcast device supports oneshot. + */ +bool tick_broadcast_oneshot_available(void) +{ + struct clock_event_device *bc = tick_broadcast_device.evtdev; + + return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false; +} + #endif diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 051bc80a0c43..ed228ef6f6b8 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -51,7 +51,11 @@ int tick_is_oneshot_available(void) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); - return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT); + if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT)) + return 0; + if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) + return 1; + return tick_broadcast_oneshot_available(); } /* diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 290eefbc1f60..f65d3a723a64 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -36,6 +36,7 @@ extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup); extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc); extern int tick_broadcast_oneshot_active(void); extern void tick_check_oneshot_broadcast(int cpu); +bool tick_broadcast_oneshot_available(void); # else /* BROADCAST */ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { @@ -46,6 +47,7 @@ static inline void tick_broadcast_switch_to_oneshot(void) { } static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } static inline void tick_check_oneshot_broadcast(int cpu) { } +static inline bool tick_broadcast_oneshot_available(void) { return true; } # endif /* !BROADCAST */ #else /* !ONESHOT */ @@ -76,6 +78,7 @@ static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc) return 0; } static inline int tick_broadcast_oneshot_active(void) { return 0; } +static inline bool tick_broadcast_oneshot_available(void) { return false; } #endif /* !TICK_ONESHOT */ /* -- cgit v1.2.3 From 2d3a8497f8cc5aca14b722cd37d51f6c15ff9f74 Mon Sep 17 00:00:00 2001 From: Tao Ma Date: Thu, 3 Mar 2011 10:53:20 -0500 Subject: blktrace: Remove blk_fill_rwbs_rq. If we enable trace events to trace block actions, We use blk_fill_rwbs_rq to analyze the corresponding actions in request's cmd_flags, but we only choose the minor 2 bits from it, so most of other flags(e.g, REQ_SYNC) are missing. For example, with a sync write we get: write_test-2409 [001] 160.013869: block_rq_insert: 3,64 W 0 () 258135 + = 8 [write_test] Since now we have integrated the flags of both bio and request, it is safe to pass rq->cmd_flags directly to blk_fill_rwbs and blk_fill_rwbs_rq isn't needed any more. With this patch, after a sync write we get: write_test-2417 [000] 226.603878: block_rq_insert: 3,64 WS 0 () 258135 += 8 [write_test] Signed-off-by: Tao Ma Acked-by: Jeff Moyer Signed-off-by: Jens Axboe --- kernel/trace/blktrace.c | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index d95721f33702..cbafed7d4f38 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1827,21 +1827,5 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) rwbs[i] = '\0'; } -void blk_fill_rwbs_rq(char *rwbs, struct request *rq) -{ - int rw = rq->cmd_flags & 0x03; - int bytes; - - if (rq->cmd_flags & REQ_DISCARD) - rw |= REQ_DISCARD; - - if (rq->cmd_flags & REQ_SECURE) - rw |= REQ_SECURE; - - bytes = blk_rq_bytes(rq); - - blk_fill_rwbs(rwbs, rw, bytes); -} - #endif /* CONFIG_EVENT_TRACING */ -- cgit v1.2.3