/* * tracing clocks * * Copyright (C) 2009 Red Hat, Inc., Ingo Molnar * * Implements 3 trace clock variants, with differing scalability/precision * tradeoffs: * * - local: CPU-local trace clock * - medium: scalable global clock with some jitter * - global: globally monotonic, serialized clock * * Tracer plugins will chose a default from these clocks. */ #include #include #include #include #include #include #include #include /* * trace_clock_local(): the simplest and least coherent tracing clock. * * Useful for tracing that does not cross to other CPUs nor * does it go through idle events. */ u64 notrace trace_clock_local(void) { u64 clock; /* * sched_clock() is an architecture implemented, fast, scalable, * lockless clock. It is not guaranteed to be coherent across * CPUs, nor across CPU idle events. */ preempt_disable_notrace(); clock = sched_clock(); preempt_enable_notrace(); return clock; } EXPORT_SYMBOL_GPL(trace_clock_local); /* * trace_clock(): 'between' trace clock. Not completely serialized, * but not completely incorrect when crossing CPUs either. * * This is based on cpu_clock(), which will allow at most ~1 jiffy of * jitter between CPUs. So it's a pretty scalable clock, but there * can be offsets in the trace data. */ u64 notrace trace_clock(void) { return local_clock(); } EXPORT_SYMBOL_GPL(trace_clock); /* * trace_jiffy_clock(): Simply use jiffies as a clock counter. * Note that this use of jiffies_64 is not completely safe on * 32-bit systems. But the window is tiny, and the effect if * we are affected is that we will have an obviously bogus * timestamp on a trace event - i.e. not life threatening. */ u64 notrace trace_clock_jiffies(void) { return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES); } EXPORT_SYMBOL_GPL(trace_clock_jiffies); /* * trace_clock_global(): special globally coherent trace clock * * It has higher overhead than the other trace clocks but is still * an order of magnitude faster than GTOD derived hardware clocks. * * Used by plugins that need globally coherent timestamps. */ /* keep prev_time and lock in the same cacheline. */ static struct { u64 prev_time; arch_spinlock_t lock; } trace_clock_struct ____cacheline_aligned_in_smp = { .lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED, }; u64 notrace trace_clock_global(void) { unsigned long flags; int this_cpu; u64 now; local_irq_save(flags); this_cpu = raw_smp_processor_id(); now = sched_clock_cpu(this_cpu); /* * If in an NMI context then dont risk lockups and return the * cpu_clock() time: */ if (unlikely(in_nmi())) goto out; arch_spin_lock(&trace_clock_struct.lock); /* * TODO: if this happens often then maybe we should reset * my_scd->clock to prev_time+1, to make sure * we start ticking with the local clock from now on? */ if ((s64)(now - trace_clock_struct.prev_time) < 0) now = trace_clock_struct.prev_time + 1; trace_clock_struct.prev_time = now; arch_spin_unlock(&trace_clock_struct.lock); out: local_irq_restore(flags); return now; } EXPORT_SYMBOL_GPL(trace_clock_global); static atomic64_t trace_counter; /* * trace_clock_counter(): simply an atomic counter. * Use the trace_counter "counter" for cases where you do not care * about timings, but are interested in strict ordering. */ u64 notrace trace_clock_counter(void) { return atomic64_add_return(1, &trace_counter); } value='7'>7space:mode:
authorDouglas Miller <dougmill@linux.vnet.ibm.com>2017-01-28 06:42:20 -0600
committerTejun Heo <tj@kernel.org>2017-01-28 07:49:42 -0500
commit966d2b04e070bc040319aaebfec09e0144dc3341 (patch)
tree4b96156e3d1dd4dfd6039b7c219c9dc4616da52d /net/mac80211/debug.h
parent1b1bc42c1692e9b62756323c675a44cb1a1f9dbd (diff)
percpu-refcount: fix reference leak during percpu-atomic transition
percpu_ref_tryget() and percpu_ref_tryget_live() should return "true" IFF they acquire a reference. But the return value from atomic_long_inc_not_zero() is a long and may have high bits set, e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines is bool so the reference may actually be acquired but the routines return "false" which results in a reference leak since the caller assumes it does not need to do a corresponding percpu_ref_put(). This was seen when performing CPU hotplug during I/O, as hangs in blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start) raced with percpu_ref_tryget (blk_mq_timeout_work). Sample stack trace: __switch_to+0x2c0/0x450 __schedule+0x2f8/0x970 schedule+0x48/0xc0 blk_mq_freeze_queue_wait+0x94/0x120 blk_mq_queue_reinit_work+0xb8/0x180 blk_mq_queue_reinit_prepare+0x84/0xa0 cpuhp_invoke_callback+0x17c/0x600 cpuhp_up_callbacks+0x58/0x150 _cpu_up+0xf0/0x1c0 do_cpu_up+0x120/0x150 cpu_subsys_online+0x64/0xe0 device_online+0xb4/0x120 online_store+0xb4/0xc0 dev_attr_store+0x68/0xa0 sysfs_kf_write+0x80/0xb0 kernfs_fop_write+0x17c/0x250 __vfs_write+0x6c/0x1e0 vfs_write+0xd0/0x270 SyS_write+0x6c/0x110 system_call+0x38/0xe0 Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS, and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests. However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0 and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set. The fix is to make the tryget routines use an actual boolean internally instead of the atomic long result truncated to a int. Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751 Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com> Reviewed-by: Jens Axboe <axboe@fb.com> Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints") Cc: stable@vger.kernel.org # v3.18+
Diffstat (limited to 'net/mac80211/debug.h')