// SPDX-License-Identifier: GPL-2.0/* * trace_hwlat.c - A simple Hardware Latency detector. * * Use this tracer to detect large system latencies induced by the behavior of * certain underlying system hardware or firmware, independent of Linux itself. * The code was developed originally to detect the presence of SMIs on Intel * and AMD systems, although there is no dependency upon x86 herein. * * The classical example usage of this tracer is in detecting the presence of * SMIs or System Management Interrupts on Intel and AMD systems. An SMI is a * somewhat special form of hardware interrupt spawned from earlier CPU debug * modes in which the (BIOS/EFI/etc.) firmware arranges for the South Bridge * LPC (or other device) to generate a special interrupt under certain * circumstances, for example, upon expiration of a special SMI timer device, * due to certain external thermal readings, on certain I/O address accesses, * and other situations. An SMI hits a special CPU pin, triggers a special * SMI mode (complete with special memory map), and the OS is unaware. * * Although certain hardware-inducing latencies are necessary (for example, * a modern system often requires an SMI handler for correct thermal control * and remote management) they can wreak havoc upon any OS-level performance * guarantees toward low-latency, especially when the OS is not even made * aware of the presence of these interrupts. For this reason, we need a * somewhat brute force mechanism to detect these interrupts. In this case, * we do it by hogging all of the CPU(s) for configurable timer intervals, * sampling the built-in CPU timer, looking for discontiguous readings. * * WARNING: This implementation necessarily introduces latencies. Therefore, * you should NEVER use this tracer while running in a production * environment requiring any kind of low-latency performance * guarantee(s). * * Copyright (C) 2008-2009 Jon Masters, Red Hat, Inc. <jcm@redhat.com> * Copyright (C) 2013-2016 Steven Rostedt, Red Hat, Inc. <srostedt@redhat.com> * * Includes useful feedback from Clark Williams <williams@redhat.com> * */#include <linux/kthread.h>#include <linux/tracefs.h>#include <linux/uaccess.h>#include <linux/cpumask.h>#include <linux/delay.h>#include <linux/sched/clock.h>#include "trace.h" static struct trace_array *hwlat_trace; #define U64STR_SIZE 22 /* 20 digits max */ #define BANNER "hwlat_detector: "#define DEFAULT_SAMPLE_WINDOW 1000000 /* 1s */#define DEFAULT_SAMPLE_WIDTH 500000 /* 0.5s */#define DEFAULT_LAT_THRESHOLD 10 /* 10us */ static struct dentry *hwlat_sample_width; /* sample width us */static struct dentry *hwlat_sample_window; /* sample window us */static struct dentry *hwlat_thread_mode; /* hwlat thread mode */ enum { MODE_NONE = 0, MODE_ROUND_ROBIN, MODE_PER_CPU, MODE_MAX};static char *thread_mode_str[] = { "none", "round-robin", "per-cpu" }; /* Save the previous tracing_thresh value */static unsigned long save_tracing_thresh; /* runtime kthread data */struct hwlat_kthread_data { struct task_struct *kthread; /* NMI timestamp counters */ u64 nmi_ts_start; u64 nmi_total_ts; int nmi_count; int nmi_cpu;}; static struct hwlat_kthread_data hwlat_single_cpu_data;static DEFINE_PER_CPU(struct hwlat_kthread_data, hwlat_per_cpu_data); /* Tells NMIs to call back to the hwlat tracer to record timestamps */bool trace_hwlat_callback_enabled; /* If the user changed threshold, remember it */static u64 last_tracing_thresh = DEFAULT_LAT_THRESHOLD * NSEC_PER_USEC; /* Individual latency samples are stored here when detected. */struct hwlat_sample { u64 seqnum; /* unique sequence */ u64 duration; /* delta */ u64 outer_duration; /* delta (outer loop) */ u64 nmi_total_ts; /* Total time spent in NMIs */ struct timespec64 timestamp; /* wall time */ int nmi_count; /* # NMIs during this sample */ int count; /* # of iterations over thresh */}; /* keep the global state somewhere. */static struct hwlat_data { struct mutex lock; /* protect changes */ atomic64_t count; /* total since reset */ u64 sample_window; /* total sampling window (on+off) */ u64 sample_width; /* active sampling portion of window */ int thread_mode; /* thread mode */ } hwlat_data = { .sample_window = DEFAULT_SAMPLE_WINDOW, .sample_width = DEFAULT_SAMPLE_WIDTH, .thread_mode = MODE_ROUND_ROBIN}; static struct hwlat_kthread_data *get_cpu_data(void){ if (hwlat_data.thread_mode == MODE_PER_CPU) return this_cpu_ptr(&hwlat_per_cpu_data); else return &hwlat_single_cpu_data;} static bool hwlat_busy; static void trace_hwlat_sample(struct hwlat_sample *sample){ struct trace_array *tr = hwlat_trace; struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct hwlat_entry *entry; event = trace_buffer_lock_reserve(buffer, TRACE_HWLAT, sizeof(*entry), tracing_gen_ctx()); if (!event) return; entry = ring_buffer_event_data(event); entry->seqnum = sample->seqnum; entry->duration = sample->duration; entry->outer_duration = sample->outer_duration; entry->timestamp = sample->timestamp; entry->nmi_total_ts = sample->nmi_total_ts; entry->nmi_count = sample->nmi_count; entry->count = sample->count; trace_buffer_unlock_commit_nostack(buffer, event);} /* Macros to encapsulate the time capturing infrastructure */#define time_type u64#define time_get() trace_clock_local()#define time_to_us(x) div_u64(x, 1000)#define time_sub(a, b) ((a) - (b))#define init_time(a, b) (a = b)#define time_u64(a) a void trace_hwlat_callback(bool enter){ struct hwlat_kthread_data *kdata = get_cpu_data(); if (!kdata->kthread) return; /* * Currently trace_clock_local() calls sched_clock() and the * generic version is not NMI safe. */ if (!IS_ENABLED(CONFIG_GENERIC_SCHED_CLOCK)) { if (enter) kdata->nmi_ts_start = time_get(); else kdata->nmi_total_ts += time_get() - kdata->nmi_ts_start; } if (enter) kdata->nmi_count++;} /* * hwlat_err - report a hwlat error. */#define hwlat_err(msg) ({ \ struct trace_array *tr = hwlat_trace; \ \ trace_array_printk_buf(tr->array_buffer.buffer, _THIS_IP_, msg); \}) /** * get_sample - sample the CPU TSC and look for likely hardware latencies * * Used to repeatedly capture the CPU TSC (or similar), looking for potential * hardware-induced latency. Called with interrupts disabled. */static int get_sample(void){ struct hwlat_kthread_data *kdata = get_cpu_data(); struct trace_array *tr = hwlat_trace; struct hwlat_sample s; time_type start, t1, t2, last_t2; s64 diff, outer_diff, total, last_total = 0; u64 sample = 0; u64 sample_width = READ_ONCE(hwlat_data.sample_width); u64 thresh = tracing_thresh; u64 outer_sample = 0; int ret = -1; unsigned int count = 0; do_div(thresh, NSEC_PER_USEC); /* modifies interval value */ kdata->nmi_total_ts = 0; kdata->nmi_count = 0; /* Make sure NMIs see this first */ barrier(); trace_hwlat_callback_enabled = true; init_time(last_t2, 0); start = time_get(); /* start timestamp */ outer_diff = 0; do { t1 = time_get(); /* we'll look for a discontinuity */ t2 = time_get(); if (time_u64(last_t2)) { /* Check the delta from outer loop (t2 to next t1) */ outer_diff = time_to_us(time_sub(t1, last_t2)); /* This shouldn't happen */ if (outer_diff < 0) { hwlat_err(BANNER "time running backwards\n"); goto out; } if (outer_diff > outer_sample) outer_sample = outer_diff; } last_t2 = t2; total = time_to_us(time_sub(t2, start)); /* sample width */ /* Check for possible overflows */ if (total < last_total) { hwlat_err("Time total overflowed\n"); break; } last_total = total; /* This checks the inner loop (t1 to t2) */ diff = time_to_us(time_sub(t2, t1)); /* current diff */ if (diff > thresh || outer_diff > thresh) { if (!count) ktime_get_real_ts64(&s.timestamp); count++; } /* This shouldn't happen */ if (diff < 0) { hwlat_err(BANNER "time running backwards\n"); goto out; } if (diff > sample) sample = diff; /* only want highest value */ } while (total <= sample_width); barrier(); /* finish the above in the view for NMIs */ trace_hwlat_callback_enabled = false; barrier(); /* Make sure nmi_total_ts is no longer updated */ ret = 0; /* If we exceed the threshold value, we have found a hardware latency */ if (sample > thresh || outer_sample > thresh) { u64 latency; ret = 1; /* We read in microseconds */ if (kdata->nmi_total_ts) do_div(kdata->nmi_total_ts, NSEC_PER_USEC); s.seqnum = atomic64_inc_return(&hwlat_data.count); s.duration = sample; s.outer_duration = outer_sample; s.nmi_total_ts = kdata->nmi_total_ts; s.nmi_count = kdata->nmi_count; s.count = count; trace_hwlat_sample(&s); latency = max(sample, outer_sample); /* Keep a running maximum ever recorded hardware latency */ if (latency > tr->max_latency) { tr->max_latency = latency; latency_fsnotify(tr); } } out: return ret;} static struct cpumask save_cpumask; static void move_to_next_cpu(void){ struct cpumask *current_mask = &save_cpumask; struct trace_array *tr = hwlat_trace; int next_cpu; /* * If for some reason the user modifies the CPU affinity * of this thread, then stop migrating for the duration * of the current test. */ if (!cpumask_equal(current_mask, current->cpus_ptr)) goto change_mode; cpus_read_lock(); cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask); next_cpu = cpumask_next_wrap(raw_smp_processor_id(), current_mask); cpus_read_unlock(); if (next_cpu >= nr_cpu_ids) /* Shouldn't happen! */ goto change_mode; cpumask_clear(current_mask); cpumask_set_cpu(next_cpu, current_mask); set_cpus_allowed_ptr(current, current_mask); return; change_mode: hwlat_data.thread_mode = MODE_NONE; pr_info(BANNER "cpumask changed while in round-robin mode, switching to mode none\n");} /* * kthread_fn - The CPU time sampling/hardware latency detection kernel thread * * Used to periodically sample the CPU TSC via a call to get_sample. We * disable interrupts, which does (intentionally) introduce latency since we * need to ensure nothing else might be running (and thus preempting). * Obviously this should never be used in production environments. * * Executes one loop interaction on each CPU in tracing_cpumask sysfs file. */static int kthread_fn(void *data){ u64 interval; while (!kthread_should_stop()) { if (hwlat_data.thread_mode == MODE_ROUND_ROBIN) move_to_next_cpu(); local_irq_disable(); get_sample(); local_irq_enable(); mutex_lock(&hwlat_data.lock); interval = hwlat_data.sample_window - hwlat_data.sample_width; mutex_unlock(&hwlat_data.lock); do_div(interval, USEC_PER_MSEC); /* modifies interval value */ /* Always sleep for at least 1ms */ if (interval < 1) interval = 1; if (msleep_interruptible(interval)) break; } return 0;} /* * stop_stop_kthread - Inform the hardware latency sampling/detector kthread to stop * * This kicks the running hardware latency sampling/detector kernel thread and * tells it to stop sampling now. Use this on unload and at system shutdown. */static void stop_single_kthread(void){ struct hwlat_kthread_data *kdata = get_cpu_data(); struct task_struct *kthread; cpus_read_lock(); kthread = kdata->kthread; if (!kthread) goto out_put_cpus; kthread_stop(kthread); kdata->kthread = NULL; out_put_cpus: cpus_read_unlock();} /* * start_single_kthread - Kick off the hardware latency sampling/detector kthread * * This starts the kernel thread that will sit and sample the CPU timestamp * counter (TSC or similar) and look for potential hardware latencies. */static int start_single_kthread(struct trace_array *tr){ struct hwlat_kthread_data *kdata = get_cpu_data(); struct cpumask *current_mask = &save_cpumask; struct task_struct *kthread; int next_cpu; cpus_read_lock(); if (kdata->kthread) goto out_put_cpus; kthread = kthread_create(kthread_fn, NULL, "hwlatd"); if (IS_ERR(kthread)) { pr_err(BANNER "could not start sampling thread\n"); cpus_read_unlock(); return -ENOMEM; } /* Just pick the first CPU on first iteration */ cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask); if (hwlat_data.thread_mode == MODE_ROUND_ROBIN) { next_cpu = cpumask_first(current_mask); cpumask_clear(current_mask); cpumask_set_cpu(next_cpu, current_mask); } set_cpus_allowed_ptr(kthread, current_mask); kdata->kthread = kthread; wake_up_process(kthread); out_put_cpus: cpus_read_unlock(); return 0;} /* * stop_cpu_kthread - Stop a hwlat cpu kthread */static void stop_cpu_kthread(unsigned int cpu){ struct task_struct *kthread; kthread = per_cpu(hwlat_per_cpu_data, cpu).kthread; if (kthread) kthread_stop(kthread); per_cpu(hwlat_per_cpu_data, cpu).kthread = NULL;} /* * stop_per_cpu_kthreads - Inform the hardware latency sampling/detector kthread to stop * * This kicks the running hardware latency sampling/detector kernel threads and * tells it to stop sampling now. Use this on unload and at system shutdown. */static void stop_per_cpu_kthreads(void){ unsigned int cpu; cpus_read_lock(); for_each_online_cpu(cpu) stop_cpu_kthread(cpu); cpus_read_unlock();} /* * start_cpu_kthread - Start a hwlat cpu kthread */static int start_cpu_kthread(unsigned int cpu){ struct task_struct *kthread; /* Do not start a new hwlatd thread if it is already running */ if (per_cpu(hwlat_per_cpu_data, cpu).kthread) return 0; kthread = kthread_run_on_cpu(kthread_fn, NULL, cpu, "hwlatd/%u"); if (IS_ERR(kthread)) { pr_err(BANNER "could not start sampling thread\n"); return -ENOMEM; } per_cpu(hwlat_per_cpu_data, cpu).kthread = kthread; Lines 1–500 of 887. Load more
// SPDX-License-Identifier: GPL-2.0 /* * trace_hwlat.c - A simple Hardware Latency detector. * * Use this tracer to detect large system latencies induced by the behavior of * certain underlying system hardware or firmware, independent of Linux itself. * The code was developed originally to detect the presence of SMIs on Intel * and AMD systems, although there is no dependency upon x86 herein. * * The classical example usage of this tracer is in detecting the presence of * SMIs or System Management Interrupts on Intel and AMD systems. An SMI is a * somewhat special form of hardware interrupt spawned from earlier CPU debug * modes in which the (BIOS/EFI/etc.) firmware arranges for the South Bridge * LPC (or other device) to generate a special interrupt under certain * circumstances, for example, upon expiration of a special SMI timer device, * due to certain external thermal readings, on certain I/O address accesses, * and other situations. An SMI hits a special CPU pin, triggers a special * SMI mode (complete with special memory map), and the OS is unaware. * * Although certain hardware-inducing latencies are necessary (for example, * a modern system often requires an SMI handler for correct thermal control * and remote management) they can wreak havoc upon any OS-level performance * guarantees toward low-latency, especially when the OS is not even made * aware of the presence of these interrupts. For this reason, we need a * somewhat brute force mechanism to detect these interrupts. In this case, * we do it by hogging all of the CPU(s) for configurable timer intervals, * sampling the built-in CPU timer, looking for discontiguous readings. * * WARNING: This implementation necessarily introduces latencies. Therefore, * you should NEVER use this tracer while running in a production * environment requiring any kind of low-latency performance * guarantee(s). * * Copyright (C) 2008-2009 Jon Masters, Red Hat, Inc. <jcm@redhat.com> * Copyright (C) 2013-2016 Steven Rostedt, Red Hat, Inc. <srostedt@redhat.com> * * Includes useful feedback from Clark Williams <williams@redhat.com> * */ #include <linux/kthread.h> #include <linux/tracefs.h> #include <linux/uaccess.h> #include <linux/cpumask.h> #include <linux/delay.h> #include <linux/sched/clock.h> #include "trace.h" static struct trace_array *hwlat_trace; #define U64STR_SIZE 22 /* 20 digits max */ #define BANNER "hwlat_detector: " #define DEFAULT_SAMPLE_WINDOW 1000000 /* 1s */ #define DEFAULT_SAMPLE_WIDTH 500000 /* 0.5s */ #define DEFAULT_LAT_THRESHOLD 10 /* 10us */ static struct dentry *hwlat_sample_width; /* sample width us */ static struct dentry *hwlat_sample_window; /* sample window us */ static struct dentry *hwlat_thread_mode; /* hwlat thread mode */ enum { MODE_NONE = 0, MODE_ROUND_ROBIN, MODE_PER_CPU, MODE_MAX }; static char *thread_mode_str[] = { "none", "round-robin", "per-cpu" }; /* Save the previous tracing_thresh value */ static unsigned long save_tracing_thresh; /* runtime kthread data */ struct hwlat_kthread_data { struct task_struct *kthread; /* NMI timestamp counters */ u64 nmi_ts_start; u64 nmi_total_ts; int nmi_count; int nmi_cpu; }; static struct hwlat_kthread_data hwlat_single_cpu_data; static DEFINE_PER_CPU(struct hwlat_kthread_data, hwlat_per_cpu_data); /* Tells NMIs to call back to the hwlat tracer to record timestamps */ bool trace_hwlat_callback_enabled; /* If the user changed threshold, remember it */ static u64 last_tracing_thresh = DEFAULT_LAT_THRESHOLD * NSEC_PER_USEC; /* Individual latency samples are stored here when detected. */ struct hwlat_sample { u64 seqnum; /* unique sequence */ u64 duration; /* delta */ u64 outer_duration; /* delta (outer loop) */ u64 nmi_total_ts; /* Total time spent in NMIs */ struct timespec64 timestamp; /* wall time */ int nmi_count; /* # NMIs during this sample */ int count; /* # of iterations over thresh */ }; /* keep the global state somewhere. */ static struct hwlat_data { struct mutex lock; /* protect changes */ atomic64_t count; /* total since reset */ u64 sample_window; /* total sampling window (on+off) */ u64 sample_width; /* active sampling portion of window */ int thread_mode; /* thread mode */ } hwlat_data = { .sample_window = DEFAULT_SAMPLE_WINDOW, .sample_width = DEFAULT_SAMPLE_WIDTH, .thread_mode = MODE_ROUND_ROBIN }; static struct hwlat_kthread_data *get_cpu_data(void) { if (hwlat_data.thread_mode == MODE_PER_CPU) return this_cpu_ptr(&hwlat_per_cpu_data); else return &hwlat_single_cpu_data; } static bool hwlat_busy; static void trace_hwlat_sample(struct hwlat_sample *sample) { struct trace_array *tr = hwlat_trace; struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct hwlat_entry *entry; event = trace_buffer_lock_reserve(buffer, TRACE_HWLAT, sizeof(*entry), tracing_gen_ctx()); if (!event) return; entry = ring_buffer_event_data(event); entry->seqnum = sample->seqnum; entry->duration = sample->duration; entry->outer_duration = sample->outer_duration; entry->timestamp = sample->timestamp; entry->nmi_total_ts = sample->nmi_total_ts; entry->nmi_count = sample->nmi_count; entry->count = sample->count; trace_buffer_unlock_commit_nostack(buffer, event); } /* Macros to encapsulate the time capturing infrastructure */ #define time_type u64 #define time_get() trace_clock_local() #define time_to_us(x) div_u64(x, 1000) #define time_sub(a, b) ((a) - (b)) #define init_time(a, b) (a = b) #define time_u64(a) a void trace_hwlat_callback(bool enter) { struct hwlat_kthread_data *kdata = get_cpu_data(); if (!kdata->kthread) return; /* * Currently trace_clock_local() calls sched_clock() and the * generic version is not NMI safe. */ if (!IS_ENABLED(CONFIG_GENERIC_SCHED_CLOCK)) { if (enter) kdata->nmi_ts_start = time_get(); else kdata->nmi_total_ts += time_get() - kdata->nmi_ts_start; } if (enter) kdata->nmi_count++; } /* * hwlat_err - report a hwlat error. */ #define hwlat_err(msg) ({ \ struct trace_array *tr = hwlat_trace; \ \ trace_array_printk_buf(tr->array_buffer.buffer, _THIS_IP_, msg); \ }) /** * get_sample - sample the CPU TSC and look for likely hardware latencies * * Used to repeatedly capture the CPU TSC (or similar), looking for potential * hardware-induced latency. Called with interrupts disabled. */ static int get_sample(void) { struct hwlat_kthread_data *kdata = get_cpu_data(); struct trace_array *tr = hwlat_trace; struct hwlat_sample s; time_type start, t1, t2, last_t2; s64 diff, outer_diff, total, last_total = 0; u64 sample = 0; u64 sample_width = READ_ONCE(hwlat_data.sample_width); u64 thresh = tracing_thresh; u64 outer_sample = 0; int ret = -1; unsigned int count = 0; do_div(thresh, NSEC_PER_USEC); /* modifies interval value */ kdata->nmi_total_ts = 0; kdata->nmi_count = 0; /* Make sure NMIs see this first */ barrier(); trace_hwlat_callback_enabled = true; init_time(last_t2, 0); start = time_get(); /* start timestamp */ outer_diff = 0; do { t1 = time_get(); /* we'll look for a discontinuity */ t2 = time_get(); if (time_u64(last_t2)) { /* Check the delta from outer loop (t2 to next t1) */ outer_diff = time_to_us(time_sub(t1, last_t2)); /* This shouldn't happen */ if (outer_diff < 0) { hwlat_err(BANNER "time running backwards\n"); goto out; } if (outer_diff > outer_sample) outer_sample = outer_diff; } last_t2 = t2; total = time_to_us(time_sub(t2, start)); /* sample width */ /* Check for possible overflows */ if (total < last_total) { hwlat_err("Time total overflowed\n"); break; } last_total = total; /* This checks the inner loop (t1 to t2) */ diff = time_to_us(time_sub(t2, t1)); /* current diff */ if (diff > thresh || outer_diff > thresh) { if (!count) ktime_get_real_ts64(&s.timestamp); count++; } /* This shouldn't happen */ if (diff < 0) { hwlat_err(BANNER "time running backwards\n"); goto out; } if (diff > sample) sample = diff; /* only want highest value */ } while (total <= sample_width); barrier(); /* finish the above in the view for NMIs */ trace_hwlat_callback_enabled = false; barrier(); /* Make sure nmi_total_ts is no longer updated */ ret = 0; /* If we exceed the threshold value, we have found a hardware latency */ if (sample > thresh || outer_sample > thresh) { u64 latency; ret = 1; /* We read in microseconds */ if (kdata->nmi_total_ts) do_div(kdata->nmi_total_ts, NSEC_PER_USEC); s.seqnum = atomic64_inc_return(&hwlat_data.count); s.duration = sample; s.outer_duration = outer_sample; s.nmi_total_ts = kdata->nmi_total_ts; s.nmi_count = kdata->nmi_count; s.count = count; trace_hwlat_sample(&s); latency = max(sample, outer_sample); /* Keep a running maximum ever recorded hardware latency */ if (latency > tr->max_latency) { tr->max_latency = latency; latency_fsnotify(tr); } } out: return ret; } static struct cpumask save_cpumask; static void move_to_next_cpu(void) { struct cpumask *current_mask = &save_cpumask; struct trace_array *tr = hwlat_trace; int next_cpu; /* * If for some reason the user modifies the CPU affinity * of this thread, then stop migrating for the duration * of the current test. */ if (!cpumask_equal(current_mask, current->cpus_ptr)) goto change_mode; cpus_read_lock(); cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask); next_cpu = cpumask_next_wrap(raw_smp_processor_id(), current_mask); cpus_read_unlock(); if (next_cpu >= nr_cpu_ids) /* Shouldn't happen! */ goto change_mode; cpumask_clear(current_mask); cpumask_set_cpu(next_cpu, current_mask); set_cpus_allowed_ptr(current, current_mask); return; change_mode: hwlat_data.thread_mode = MODE_NONE; pr_info(BANNER "cpumask changed while in round-robin mode, switching to mode none\n"); } /* * kthread_fn - The CPU time sampling/hardware latency detection kernel thread * * Used to periodically sample the CPU TSC via a call to get_sample. We * disable interrupts, which does (intentionally) introduce latency since we * need to ensure nothing else might be running (and thus preempting). * Obviously this should never be used in production environments. * * Executes one loop interaction on each CPU in tracing_cpumask sysfs file. */ static int kthread_fn(void *data) { u64 interval; while (!kthread_should_stop()) { if (hwlat_data.thread_mode == MODE_ROUND_ROBIN) move_to_next_cpu(); local_irq_disable(); get_sample(); local_irq_enable(); mutex_lock(&hwlat_data.lock); interval = hwlat_data.sample_window - hwlat_data.sample_width; mutex_unlock(&hwlat_data.lock); do_div(interval, USEC_PER_MSEC); /* modifies interval value */ /* Always sleep for at least 1ms */ if (interval < 1) interval = 1; if (msleep_interruptible(interval)) break; } return 0; } /* * stop_stop_kthread - Inform the hardware latency sampling/detector kthread to stop * * This kicks the running hardware latency sampling/detector kernel thread and * tells it to stop sampling now. Use this on unload and at system shutdown. */ static void stop_single_kthread(void) { struct hwlat_kthread_data *kdata = get_cpu_data(); struct task_struct *kthread; cpus_read_lock(); kthread = kdata->kthread; if (!kthread) goto out_put_cpus; kthread_stop(kthread); kdata->kthread = NULL; out_put_cpus: cpus_read_unlock(); } /* * start_single_kthread - Kick off the hardware latency sampling/detector kthread * * This starts the kernel thread that will sit and sample the CPU timestamp * counter (TSC or similar) and look for potential hardware latencies. */ static int start_single_kthread(struct trace_array *tr) { struct hwlat_kthread_data *kdata = get_cpu_data(); struct cpumask *current_mask = &save_cpumask; struct task_struct *kthread; int next_cpu; cpus_read_lock(); if (kdata->kthread) goto out_put_cpus; kthread = kthread_create(kthread_fn, NULL, "hwlatd"); if (IS_ERR(kthread)) { pr_err(BANNER "could not start sampling thread\n"); cpus_read_unlock(); return -ENOMEM; } /* Just pick the first CPU on first iteration */ cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask); if (hwlat_data.thread_mode == MODE_ROUND_ROBIN) { next_cpu = cpumask_first(current_mask); cpumask_clear(current_mask); cpumask_set_cpu(next_cpu, current_mask); } set_cpus_allowed_ptr(kthread, current_mask); kdata->kthread = kthread; wake_up_process(kthread); out_put_cpus: cpus_read_unlock(); return 0; } /* * stop_cpu_kthread - Stop a hwlat cpu kthread */ static void stop_cpu_kthread(unsigned int cpu) { struct task_struct *kthread; kthread = per_cpu(hwlat_per_cpu_data, cpu).kthread; if (kthread) kthread_stop(kthread); per_cpu(hwlat_per_cpu_data, cpu).kthread = NULL; } /* * stop_per_cpu_kthreads - Inform the hardware latency sampling/detector kthread to stop * * This kicks the running hardware latency sampling/detector kernel threads and * tells it to stop sampling now. Use this on unload and at system shutdown. */ static void stop_per_cpu_kthreads(void) { unsigned int cpu; cpus_read_lock(); for_each_online_cpu(cpu) stop_cpu_kthread(cpu); cpus_read_unlock(); } /* * start_cpu_kthread - Start a hwlat cpu kthread */ static int start_cpu_kthread(unsigned int cpu) { struct task_struct *kthread; /* Do not start a new hwlatd thread if it is already running */ if (per_cpu(hwlat_per_cpu_data, cpu).kthread) return 0; kthread = kthread_run_on_cpu(kthread_fn, NULL, cpu, "hwlatd/%u"); if (IS_ERR(kthread)) { pr_err(BANNER "could not start sampling thread\n"); return -ENOMEM; } per_cpu(hwlat_per_cpu_data, cpu).kthread = kthread;