2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 05:34:00 +08:00
linux-next/kernel/trace/ring_buffer_benchmark.c
Steven Rostedt (VMware) a7e52ad7ed ring-buffer: Have ring_buffer_alloc_read_page() return error on offline CPU
Chunyu Hu reported:
  "per_cpu trace directories and files are created for all possible cpus,
   but only the cpus which have ever been on-lined have their own per cpu
   ring buffer (allocated by cpuhp threads). While trace_buffers_open, the
   open handler for trace file 'trace_pipe_raw' is always trying to access
   field of ring_buffer_per_cpu, and would panic with the NULL pointer.

   Align the behavior of trace_pipe_raw with trace_pipe, that returns -NODEV
   when openning it if that cpu does not have trace ring buffer.

   Reproduce:
   cat /sys/kernel/debug/tracing/per_cpu/cpu31/trace_pipe_raw
   (cpu31 is never on-lined, this is a 16 cores x86_64 box)

   Tested with:
   1) boot with maxcpus=14, read trace_pipe_raw of cpu15.
      Got -NODEV.
   2) oneline cpu15, read trace_pipe_raw of cpu15.
      Get the raw trace data.

   Call trace:
   [ 5760.950995] RIP: 0010:ring_buffer_alloc_read_page+0x32/0xe0
   [ 5760.961678]  tracing_buffers_read+0x1f6/0x230
   [ 5760.962695]  __vfs_read+0x37/0x160
   [ 5760.963498]  ? __vfs_read+0x5/0x160
   [ 5760.964339]  ? security_file_permission+0x9d/0xc0
   [ 5760.965451]  ? __vfs_read+0x5/0x160
   [ 5760.966280]  vfs_read+0x8c/0x130
   [ 5760.967070]  SyS_read+0x55/0xc0
   [ 5760.967779]  do_syscall_64+0x67/0x150
   [ 5760.968687]  entry_SYSCALL64_slow_path+0x25/0x25"

This was introduced by the addition of the feature to reuse reader pages
instead of re-allocating them. The problem is that the allocation of a
reader page (which is per cpu) does not check if the cpu is online and set
up for the ring buffer.

Link: http://lkml.kernel.org/r/1500880866-1177-1-git-send-email-chuhu@redhat.com

Cc: stable@vger.kernel.org
Fixes: 73a757e631 ("ring-buffer: Return reader page back into existing ring buffer")
Reported-by: Chunyu Hu <chuhu@redhat.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-08-02 14:23:02 -04:00

499 lines
11 KiB
C

/*
* ring buffer tester and benchmark
*
* Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
*/
#include <linux/ring_buffer.h>
#include <linux/completion.h>
#include <linux/kthread.h>
#include <uapi/linux/sched/types.h>
#include <linux/module.h>
#include <linux/ktime.h>
#include <asm/local.h>
struct rb_page {
u64 ts;
local_t commit;
char data[4080];
};
/* run time and sleep time in seconds */
#define RUN_TIME 10ULL
#define SLEEP_TIME 10
/* number of events for writer to wake up the reader */
static int wakeup_interval = 100;
static int reader_finish;
static DECLARE_COMPLETION(read_start);
static DECLARE_COMPLETION(read_done);
static struct ring_buffer *buffer;
static struct task_struct *producer;
static struct task_struct *consumer;
static unsigned long read;
static unsigned int disable_reader;
module_param(disable_reader, uint, 0644);
MODULE_PARM_DESC(disable_reader, "only run producer");
static unsigned int write_iteration = 50;
module_param(write_iteration, uint, 0644);
MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
static int producer_nice = MAX_NICE;
static int consumer_nice = MAX_NICE;
static int producer_fifo = -1;
static int consumer_fifo = -1;
module_param(producer_nice, int, 0644);
MODULE_PARM_DESC(producer_nice, "nice prio for producer");
module_param(consumer_nice, int, 0644);
MODULE_PARM_DESC(consumer_nice, "nice prio for consumer");
module_param(producer_fifo, int, 0644);
MODULE_PARM_DESC(producer_fifo, "fifo prio for producer");
module_param(consumer_fifo, int, 0644);
MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer");
static int read_events;
static int test_error;
#define TEST_ERROR() \
do { \
if (!test_error) { \
test_error = 1; \
WARN_ON(1); \
} \
} while (0)
enum event_status {
EVENT_FOUND,
EVENT_DROPPED,
};
static bool break_test(void)
{
return test_error || kthread_should_stop();
}
static enum event_status read_event(int cpu)
{
struct ring_buffer_event *event;
int *entry;
u64 ts;
event = ring_buffer_consume(buffer, cpu, &ts, NULL);
if (!event)
return EVENT_DROPPED;
entry = ring_buffer_event_data(event);
if (*entry != cpu) {
TEST_ERROR();
return EVENT_DROPPED;
}
read++;
return EVENT_FOUND;
}
static enum event_status read_page(int cpu)
{
struct ring_buffer_event *event;
struct rb_page *rpage;
unsigned long commit;
void *bpage;
int *entry;
int ret;
int inc;
int i;
bpage = ring_buffer_alloc_read_page(buffer, cpu);
if (IS_ERR(bpage))
return EVENT_DROPPED;
ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
if (ret >= 0) {
rpage = bpage;
/* The commit may have missed event flags set, clear them */
commit = local_read(&rpage->commit) & 0xfffff;
for (i = 0; i < commit && !test_error ; i += inc) {
if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
TEST_ERROR();
break;
}
inc = -1;
event = (void *)&rpage->data[i];
switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
/* failed writes may be discarded events */
if (!event->time_delta)
TEST_ERROR();
inc = event->array[0] + 4;
break;
case RINGBUF_TYPE_TIME_EXTEND:
inc = 8;
break;
case 0:
entry = ring_buffer_event_data(event);
if (*entry != cpu) {
TEST_ERROR();
break;
}
read++;
if (!event->array[0]) {
TEST_ERROR();
break;
}
inc = event->array[0] + 4;
break;
default:
entry = ring_buffer_event_data(event);
if (*entry != cpu) {
TEST_ERROR();
break;
}
read++;
inc = ((event->type_len + 1) * 4);
}
if (test_error)
break;
if (inc <= 0) {
TEST_ERROR();
break;
}
}
}
ring_buffer_free_read_page(buffer, cpu, bpage);
if (ret < 0)
return EVENT_DROPPED;
return EVENT_FOUND;
}
static void ring_buffer_consumer(void)
{
/* toggle between reading pages and events */
read_events ^= 1;
read = 0;
/*
* Continue running until the producer specifically asks to stop
* and is ready for the completion.
*/
while (!READ_ONCE(reader_finish)) {
int found = 1;
while (found && !test_error) {
int cpu;
found = 0;
for_each_online_cpu(cpu) {
enum event_status stat;
if (read_events)
stat = read_event(cpu);
else
stat = read_page(cpu);
if (test_error)
break;
if (stat == EVENT_FOUND)
found = 1;
}
}
/* Wait till the producer wakes us up when there is more data
* available or when the producer wants us to finish reading.
*/
set_current_state(TASK_INTERRUPTIBLE);
if (reader_finish)
break;
schedule();
}
__set_current_state(TASK_RUNNING);
reader_finish = 0;
complete(&read_done);
}
static void ring_buffer_producer(void)
{
ktime_t start_time, end_time, timeout;
unsigned long long time;
unsigned long long entries;
unsigned long long overruns;
unsigned long missed = 0;
unsigned long hit = 0;
unsigned long avg;
int cnt = 0;
/*
* Hammer the buffer for 10 secs (this may
* make the system stall)
*/
trace_printk("Starting ring buffer hammer\n");
start_time = ktime_get();
timeout = ktime_add_ns(start_time, RUN_TIME * NSEC_PER_SEC);
do {
struct ring_buffer_event *event;
int *entry;
int i;
for (i = 0; i < write_iteration; i++) {
event = ring_buffer_lock_reserve(buffer, 10);
if (!event) {
missed++;
} else {
hit++;
entry = ring_buffer_event_data(event);
*entry = smp_processor_id();
ring_buffer_unlock_commit(buffer, event);
}
}
end_time = ktime_get();
cnt++;
if (consumer && !(cnt % wakeup_interval))
wake_up_process(consumer);
#ifndef CONFIG_PREEMPT
/*
* If we are a non preempt kernel, the 10 second run will
* stop everything while it runs. Instead, we will call
* cond_resched and also add any time that was lost by a
* rescedule.
*
* Do a cond resched at the same frequency we would wake up
* the reader.
*/
if (cnt % wakeup_interval)
cond_resched();
#endif
} while (ktime_before(end_time, timeout) && !break_test());
trace_printk("End ring buffer hammer\n");
if (consumer) {
/* Init both completions here to avoid races */
init_completion(&read_start);
init_completion(&read_done);
/* the completions must be visible before the finish var */
smp_wmb();
reader_finish = 1;
wake_up_process(consumer);
wait_for_completion(&read_done);
}
time = ktime_us_delta(end_time, start_time);
entries = ring_buffer_entries(buffer);
overruns = ring_buffer_overruns(buffer);
if (test_error)
trace_printk("ERROR!\n");
if (!disable_reader) {
if (consumer_fifo < 0)
trace_printk("Running Consumer at nice: %d\n",
consumer_nice);
else
trace_printk("Running Consumer at SCHED_FIFO %d\n",
consumer_fifo);
}
if (producer_fifo < 0)
trace_printk("Running Producer at nice: %d\n",
producer_nice);
else
trace_printk("Running Producer at SCHED_FIFO %d\n",
producer_fifo);
/* Let the user know that the test is running at low priority */
if (producer_fifo < 0 && consumer_fifo < 0 &&
producer_nice == MAX_NICE && consumer_nice == MAX_NICE)
trace_printk("WARNING!!! This test is running at lowest priority.\n");
trace_printk("Time: %lld (usecs)\n", time);
trace_printk("Overruns: %lld\n", overruns);
if (disable_reader)
trace_printk("Read: (reader disabled)\n");
else
trace_printk("Read: %ld (by %s)\n", read,
read_events ? "events" : "pages");
trace_printk("Entries: %lld\n", entries);
trace_printk("Total: %lld\n", entries + overruns + read);
trace_printk("Missed: %ld\n", missed);
trace_printk("Hit: %ld\n", hit);
/* Convert time from usecs to millisecs */
do_div(time, USEC_PER_MSEC);
if (time)
hit /= (long)time;
else
trace_printk("TIME IS ZERO??\n");
trace_printk("Entries per millisec: %ld\n", hit);
if (hit) {
/* Calculate the average time in nanosecs */
avg = NSEC_PER_MSEC / hit;
trace_printk("%ld ns per entry\n", avg);
}
if (missed) {
if (time)
missed /= (long)time;
trace_printk("Total iterations per millisec: %ld\n",
hit + missed);
/* it is possible that hit + missed will overflow and be zero */
if (!(hit + missed)) {
trace_printk("hit + missed overflowed and totalled zero!\n");
hit--; /* make it non zero */
}
/* Caculate the average time in nanosecs */
avg = NSEC_PER_MSEC / (hit + missed);
trace_printk("%ld ns per entry\n", avg);
}
}
static void wait_to_die(void)
{
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
schedule();
set_current_state(TASK_INTERRUPTIBLE);
}
__set_current_state(TASK_RUNNING);
}
static int ring_buffer_consumer_thread(void *arg)
{
while (!break_test()) {
complete(&read_start);
ring_buffer_consumer();
set_current_state(TASK_INTERRUPTIBLE);
if (break_test())
break;
schedule();
}
__set_current_state(TASK_RUNNING);
if (!kthread_should_stop())
wait_to_die();
return 0;
}
static int ring_buffer_producer_thread(void *arg)
{
while (!break_test()) {
ring_buffer_reset(buffer);
if (consumer) {
wake_up_process(consumer);
wait_for_completion(&read_start);
}
ring_buffer_producer();
if (break_test())
goto out_kill;
trace_printk("Sleeping for 10 secs\n");
set_current_state(TASK_INTERRUPTIBLE);
if (break_test())
goto out_kill;
schedule_timeout(HZ * SLEEP_TIME);
}
out_kill:
__set_current_state(TASK_RUNNING);
if (!kthread_should_stop())
wait_to_die();
return 0;
}
static int __init ring_buffer_benchmark_init(void)
{
int ret;
/* make a one meg buffer in overwite mode */
buffer = ring_buffer_alloc(1000000, RB_FL_OVERWRITE);
if (!buffer)
return -ENOMEM;
if (!disable_reader) {
consumer = kthread_create(ring_buffer_consumer_thread,
NULL, "rb_consumer");
ret = PTR_ERR(consumer);
if (IS_ERR(consumer))
goto out_fail;
}
producer = kthread_run(ring_buffer_producer_thread,
NULL, "rb_producer");
ret = PTR_ERR(producer);
if (IS_ERR(producer))
goto out_kill;
/*
* Run them as low-prio background tasks by default:
*/
if (!disable_reader) {
if (consumer_fifo >= 0) {
struct sched_param param = {
.sched_priority = consumer_fifo
};
sched_setscheduler(consumer, SCHED_FIFO, &param);
} else
set_user_nice(consumer, consumer_nice);
}
if (producer_fifo >= 0) {
struct sched_param param = {
.sched_priority = producer_fifo
};
sched_setscheduler(producer, SCHED_FIFO, &param);
} else
set_user_nice(producer, producer_nice);
return 0;
out_kill:
if (consumer)
kthread_stop(consumer);
out_fail:
ring_buffer_free(buffer);
return ret;
}
static void __exit ring_buffer_benchmark_exit(void)
{
kthread_stop(producer);
if (consumer)
kthread_stop(consumer);
ring_buffer_free(buffer);
}
module_init(ring_buffer_benchmark_init);
module_exit(ring_buffer_benchmark_exit);
MODULE_AUTHOR("Steven Rostedt");
MODULE_DESCRIPTION("ring_buffer_benchmark");
MODULE_LICENSE("GPL");