linux-stable/kernel/trace/trace_output.c

1752 lines
40 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* trace_output.c
*
* Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
*
*/
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/ftrace.h>
#include <linux/kprobes.h>
#include <linux/sched/clock.h>
#include <linux/sched/mm.h>
#include <linux/idr.h>
#include "trace_output.h"
/* must be a power of 2 */
#define EVENT_HASHSIZE 128
DECLARE_RWSEM(trace_event_sem);
static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
enum print_line_t trace_print_bputs_msg_only(struct trace_iterator *iter)
{
struct trace_seq *s = &iter->seq;
struct trace_entry *entry = iter->ent;
struct bputs_entry *field;
trace_assign_type(field, entry);
trace_seq_puts(s, field->str);
return trace_handle_return(s);
}
enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
{
struct trace_seq *s = &iter->seq;
struct trace_entry *entry = iter->ent;
struct bprint_entry *field;
trace_assign_type(field, entry);
trace_seq_bprintf(s, field->fmt, field->buf);
return trace_handle_return(s);
}
enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter)
{
struct trace_seq *s = &iter->seq;
struct trace_entry *entry = iter->ent;
struct print_entry *field;
trace_assign_type(field, entry);
trace_seq_puts(s, field->buf);
return trace_handle_return(s);
}
const char *
trace_print_flags_seq(struct trace_seq *p, const char *delim,
unsigned long flags,
const struct trace_print_flags *flag_array)
{
unsigned long mask;
const char *str;
const char *ret = trace_seq_buffer_ptr(p);
int i, first = 1;
for (i = 0; flag_array[i].name && flags; i++) {
mask = flag_array[i].mask;
if ((flags & mask) != mask)
continue;
str = flag_array[i].name;
flags &= ~mask;
if (!first && delim)
trace_seq_puts(p, delim);
else
first = 0;
trace_seq_puts(p, str);
}
/* check for left over flags */
if (flags) {
if (!first && delim)
trace_seq_puts(p, delim);
trace_seq_printf(p, "0x%lx", flags);
}
trace_seq_putc(p, 0);
return ret;
}
EXPORT_SYMBOL(trace_print_flags_seq);
const char *
trace_print_symbols_seq(struct trace_seq *p, unsigned long val,
const struct trace_print_flags *symbol_array)
{
int i;
const char *ret = trace_seq_buffer_ptr(p);
for (i = 0; symbol_array[i].name; i++) {
if (val != symbol_array[i].mask)
continue;
trace_seq_puts(p, symbol_array[i].name);
break;
}
if (ret == (const char *)(trace_seq_buffer_ptr(p)))
trace_seq_printf(p, "0x%lx", val);
tracing: Add additional marks to signal very large time deltas Currently, function graph tracer prints "!" or "+" just before function execution time to signal a function overhead, depending on the time. And some tracers tracing latency also print "!" or "+" just after time to signal overhead, depending on the interval between events. Even it is usually enough to do that, we sometimes need to signal for bigger execution time than 100 micro seconds. For example, I used function graph tracer to detect if there is any case that exit_mm() takes too much time. I did following steps in /sys/kernel/debug/tracing. It was easier to detect very large excution time with patched kernel than with original kernel. $ echo exit_mm > set_graph_function $ echo function_graph > current_tracer $ echo > trace $ cat trace_pipe > $LOGFILE ... (do something and terminate logging) $ grep "\\$" $LOGFILE 3) $ 22082032 us | } /* kernel_map_pages */ 3) $ 22082040 us | } /* free_pages_prepare */ 3) $ 22082113 us | } /* free_hot_cold_page */ 3) $ 22083455 us | } /* free_hot_cold_page_list */ 3) $ 22083895 us | } /* release_pages */ 3) $ 22177873 us | } /* free_pages_and_swap_cache */ 3) $ 22178929 us | } /* unmap_single_vma */ 3) $ 22198885 us | } /* unmap_vmas */ 3) $ 22206949 us | } /* exit_mmap */ 3) $ 22207659 us | } /* mmput */ 3) $ 22207793 us | } /* exit_mm */ And then, it was easy to find out that a schedule-out occured by sub_preempt_count() within kernel_map_pages(). To detect very large function exection time caused by either problematic function implementation or scheduling issues, this patch can be useful. Link: http://lkml.kernel.org/r/1416789259-24038-1-git-send-email-byungchul.park@lge.com Signed-off-by: Byungchul Park <byungchul.park@lge.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-11-24 00:34:19 +00:00
trace_seq_putc(p, 0);
return ret;
}
EXPORT_SYMBOL(trace_print_symbols_seq);
#if BITS_PER_LONG == 32
const char *
trace_print_flags_seq_u64(struct trace_seq *p, const char *delim,
unsigned long long flags,
const struct trace_print_flags_u64 *flag_array)
{
unsigned long long mask;
const char *str;
const char *ret = trace_seq_buffer_ptr(p);
int i, first = 1;
for (i = 0; flag_array[i].name && flags; i++) {
mask = flag_array[i].mask;
if ((flags & mask) != mask)
continue;
str = flag_array[i].name;
flags &= ~mask;
if (!first && delim)
trace_seq_puts(p, delim);
else
first = 0;
trace_seq_puts(p, str);
}
/* check for left over flags */
if (flags) {
if (!first && delim)
trace_seq_puts(p, delim);
trace_seq_printf(p, "0x%llx", flags);
}
trace_seq_putc(p, 0);
return ret;
}
EXPORT_SYMBOL(trace_print_flags_seq_u64);
const char *
trace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val,
const struct trace_print_flags_u64 *symbol_array)
{
int i;
const char *ret = trace_seq_buffer_ptr(p);
for (i = 0; symbol_array[i].name; i++) {
if (val != symbol_array[i].mask)
continue;
trace_seq_puts(p, symbol_array[i].name);
break;
}
if (ret == (const char *)(trace_seq_buffer_ptr(p)))
trace_seq_printf(p, "0x%llx", val);
trace_seq_putc(p, 0);
return ret;
}
EXPORT_SYMBOL(trace_print_symbols_seq_u64);
#endif
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-06 17:10:24 +00:00
const char *
trace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr,
unsigned int bitmask_size)
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-06 17:10:24 +00:00
{
const char *ret = trace_seq_buffer_ptr(p);
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-06 17:10:24 +00:00
trace_seq_bitmask(p, bitmask_ptr, bitmask_size * 8);
trace_seq_putc(p, 0);
return ret;
}
EXPORT_SYMBOL_GPL(trace_print_bitmask_seq);
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-06 17:10:24 +00:00
/**
* trace_print_hex_seq - print buffer as hex sequence
* @p: trace seq struct to write to
* @buf: The buffer to print
* @buf_len: Length of @buf in bytes
* @concatenate: Print @buf as single hex string or with spacing
*
* Prints the passed buffer as a hex sequence either as a whole,
* single hex string if @concatenate is true or with spacing after
* each byte in case @concatenate is false.
*/
const char *
trace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len,
bool concatenate)
{
int i;
const char *ret = trace_seq_buffer_ptr(p);
const char *fmt = concatenate ? "%*phN" : "%*ph";
for (i = 0; i < buf_len; i += 16) {
if (!concatenate && i != 0)
trace_seq_putc(p, ' ');
trace_seq_printf(p, fmt, min(buf_len - i, 16), &buf[i]);
}
trace_seq_putc(p, 0);
return ret;
}
EXPORT_SYMBOL(trace_print_hex_seq);
const char *
trace_print_array_seq(struct trace_seq *p, const void *buf, int count,
size_t el_size)
{
const char *ret = trace_seq_buffer_ptr(p);
const char *prefix = "";
void *ptr = (void *)buf;
size_t buf_len = count * el_size;
trace_seq_putc(p, '{');
while (ptr < buf + buf_len) {
switch (el_size) {
case 1:
trace_seq_printf(p, "%s0x%x", prefix,
*(u8 *)ptr);
break;
case 2:
trace_seq_printf(p, "%s0x%x", prefix,
*(u16 *)ptr);
break;
case 4:
trace_seq_printf(p, "%s0x%x", prefix,
*(u32 *)ptr);
break;
case 8:
trace_seq_printf(p, "%s0x%llx", prefix,
*(u64 *)ptr);
break;
default:
trace_seq_printf(p, "BAD SIZE:%zu 0x%x", el_size,
*(u8 *)ptr);
el_size = 1;
}
prefix = ",";
ptr += el_size;
}
trace_seq_putc(p, '}');
trace_seq_putc(p, 0);
return ret;
}
EXPORT_SYMBOL(trace_print_array_seq);
const char *
trace_print_hex_dump_seq(struct trace_seq *p, const char *prefix_str,
int prefix_type, int rowsize, int groupsize,
const void *buf, size_t len, bool ascii)
{
const char *ret = trace_seq_buffer_ptr(p);
trace_seq_putc(p, '\n');
trace_seq_hex_dump(p, prefix_str, prefix_type,
rowsize, groupsize, buf, len, ascii);
trace_seq_putc(p, 0);
return ret;
}
EXPORT_SYMBOL(trace_print_hex_dump_seq);
int trace_raw_output_prep(struct trace_iterator *iter,
struct trace_event *trace_event)
{
struct trace_event_call *event;
struct trace_seq *s = &iter->seq;
struct trace_seq *p = &iter->tmp_seq;
struct trace_entry *entry;
event = container_of(trace_event, struct trace_event_call, event);
entry = iter->ent;
if (entry->type != event->event.type) {
WARN_ON_ONCE(1);
return TRACE_TYPE_UNHANDLED;
}
trace_seq_init(p);
trace_seq_printf(s, "%s: ", trace_event_name(event));
return trace_handle_return(s);
}
EXPORT_SYMBOL(trace_raw_output_prep);
void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...)
{
tracing: Check "%s" dereference via the field and not the TP_printk format The TP_printk() portion of a trace event is executed at the time a event is read from the trace. This can happen seconds, minutes, hours, days, months, years possibly later since the event was recorded. If the print format contains a dereference to a string via "%s", and that string was allocated, there's a chance that string could be freed before it is read by the trace file. To protect against such bugs, there are two functions that verify the event. The first one is test_event_printk(), which is called when the event is created. It reads the TP_printk() format as well as its arguments to make sure nothing may be dereferencing a pointer that was not copied into the ring buffer along with the event. If it is, it will trigger a WARN_ON(). For strings that use "%s", it is not so easy. The string may not reside in the ring buffer but may still be valid. Strings that are static and part of the kernel proper which will not be freed for the life of the running system, are safe to dereference. But to know if it is a pointer to a static string or to something on the heap can not be determined until the event is triggered. This brings us to the second function that tests for the bad dereferencing of strings, trace_check_vprintf(). It would walk through the printf format looking for "%s", and when it finds it, it would validate that the pointer is safe to read. If not, it would produces a WARN_ON() as well and write into the ring buffer "[UNSAFE-MEMORY]". The problem with this is how it used va_list to have vsnprintf() handle all the cases that it didn't need to check. Instead of re-implementing vsnprintf(), it would make a copy of the format up to the %s part, and call vsnprintf() with the current va_list ap variable, where the ap would then be ready to point at the string in question. For architectures that passed va_list by reference this was possible. For architectures that passed it by copy it was not. A test_can_verify() function was used to differentiate between the two, and if it wasn't possible, it would disable it. Even for architectures where this was feasible, it was a stretch to rely on such a method that is undocumented, and could cause issues later on with new optimizations of the compiler. Instead, the first function test_event_printk() was updated to look at "%s" as well. If the "%s" argument is a pointer outside the event in the ring buffer, it would find the field type of the event that is the problem and mark the structure with a new flag called "needs_test". The event itself will be marked by TRACE_EVENT_FL_TEST_STR to let it be known that this event has a field that needs to be verified before the event can be printed using the printf format. When the event fields are created from the field type structure, the fields would copy the field type's "needs_test" value. Finally, before being printed, a new function ignore_event() is called which will check if the event has the TEST_STR flag set (if not, it returns false). If the flag is set, it then iterates through the events fields looking for the ones that have the "needs_test" flag set. Then it uses the offset field from the field structure to find the pointer in the ring buffer event. It runs the tests to make sure that pointer is safe to print and if not, it triggers the WARN_ON() and also adds to the trace output that the event in question has an unsafe memory access. The ignore_event() makes the trace_check_vprintf() obsolete so it is removed. Link: https://lore.kernel.org/all/CAHk-=wh3uOnqnZPpR0PeLZZtyWbZLboZ7cHLCKRWsocvs9Y7hQ@mail.gmail.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: https://lore.kernel.org/20241217024720.848621576@goodmis.org Fixes: 5013f454a352c ("tracing: Add check of trace event print fmts for dereferencing pointers") Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-12-17 02:41:22 +00:00
struct trace_seq *s = &iter->seq;
va_list ap;
tracing: Check "%s" dereference via the field and not the TP_printk format The TP_printk() portion of a trace event is executed at the time a event is read from the trace. This can happen seconds, minutes, hours, days, months, years possibly later since the event was recorded. If the print format contains a dereference to a string via "%s", and that string was allocated, there's a chance that string could be freed before it is read by the trace file. To protect against such bugs, there are two functions that verify the event. The first one is test_event_printk(), which is called when the event is created. It reads the TP_printk() format as well as its arguments to make sure nothing may be dereferencing a pointer that was not copied into the ring buffer along with the event. If it is, it will trigger a WARN_ON(). For strings that use "%s", it is not so easy. The string may not reside in the ring buffer but may still be valid. Strings that are static and part of the kernel proper which will not be freed for the life of the running system, are safe to dereference. But to know if it is a pointer to a static string or to something on the heap can not be determined until the event is triggered. This brings us to the second function that tests for the bad dereferencing of strings, trace_check_vprintf(). It would walk through the printf format looking for "%s", and when it finds it, it would validate that the pointer is safe to read. If not, it would produces a WARN_ON() as well and write into the ring buffer "[UNSAFE-MEMORY]". The problem with this is how it used va_list to have vsnprintf() handle all the cases that it didn't need to check. Instead of re-implementing vsnprintf(), it would make a copy of the format up to the %s part, and call vsnprintf() with the current va_list ap variable, where the ap would then be ready to point at the string in question. For architectures that passed va_list by reference this was possible. For architectures that passed it by copy it was not. A test_can_verify() function was used to differentiate between the two, and if it wasn't possible, it would disable it. Even for architectures where this was feasible, it was a stretch to rely on such a method that is undocumented, and could cause issues later on with new optimizations of the compiler. Instead, the first function test_event_printk() was updated to look at "%s" as well. If the "%s" argument is a pointer outside the event in the ring buffer, it would find the field type of the event that is the problem and mark the structure with a new flag called "needs_test". The event itself will be marked by TRACE_EVENT_FL_TEST_STR to let it be known that this event has a field that needs to be verified before the event can be printed using the printf format. When the event fields are created from the field type structure, the fields would copy the field type's "needs_test" value. Finally, before being printed, a new function ignore_event() is called which will check if the event has the TEST_STR flag set (if not, it returns false). If the flag is set, it then iterates through the events fields looking for the ones that have the "needs_test" flag set. Then it uses the offset field from the field structure to find the pointer in the ring buffer event. It runs the tests to make sure that pointer is safe to print and if not, it triggers the WARN_ON() and also adds to the trace output that the event in question has an unsafe memory access. The ignore_event() makes the trace_check_vprintf() obsolete so it is removed. Link: https://lore.kernel.org/all/CAHk-=wh3uOnqnZPpR0PeLZZtyWbZLboZ7cHLCKRWsocvs9Y7hQ@mail.gmail.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: https://lore.kernel.org/20241217024720.848621576@goodmis.org Fixes: 5013f454a352c ("tracing: Add check of trace event print fmts for dereferencing pointers") Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-12-17 02:41:22 +00:00
if (ignore_event(iter))
return;
va_start(ap, fmt);
tracing: Check "%s" dereference via the field and not the TP_printk format The TP_printk() portion of a trace event is executed at the time a event is read from the trace. This can happen seconds, minutes, hours, days, months, years possibly later since the event was recorded. If the print format contains a dereference to a string via "%s", and that string was allocated, there's a chance that string could be freed before it is read by the trace file. To protect against such bugs, there are two functions that verify the event. The first one is test_event_printk(), which is called when the event is created. It reads the TP_printk() format as well as its arguments to make sure nothing may be dereferencing a pointer that was not copied into the ring buffer along with the event. If it is, it will trigger a WARN_ON(). For strings that use "%s", it is not so easy. The string may not reside in the ring buffer but may still be valid. Strings that are static and part of the kernel proper which will not be freed for the life of the running system, are safe to dereference. But to know if it is a pointer to a static string or to something on the heap can not be determined until the event is triggered. This brings us to the second function that tests for the bad dereferencing of strings, trace_check_vprintf(). It would walk through the printf format looking for "%s", and when it finds it, it would validate that the pointer is safe to read. If not, it would produces a WARN_ON() as well and write into the ring buffer "[UNSAFE-MEMORY]". The problem with this is how it used va_list to have vsnprintf() handle all the cases that it didn't need to check. Instead of re-implementing vsnprintf(), it would make a copy of the format up to the %s part, and call vsnprintf() with the current va_list ap variable, where the ap would then be ready to point at the string in question. For architectures that passed va_list by reference this was possible. For architectures that passed it by copy it was not. A test_can_verify() function was used to differentiate between the two, and if it wasn't possible, it would disable it. Even for architectures where this was feasible, it was a stretch to rely on such a method that is undocumented, and could cause issues later on with new optimizations of the compiler. Instead, the first function test_event_printk() was updated to look at "%s" as well. If the "%s" argument is a pointer outside the event in the ring buffer, it would find the field type of the event that is the problem and mark the structure with a new flag called "needs_test". The event itself will be marked by TRACE_EVENT_FL_TEST_STR to let it be known that this event has a field that needs to be verified before the event can be printed using the printf format. When the event fields are created from the field type structure, the fields would copy the field type's "needs_test" value. Finally, before being printed, a new function ignore_event() is called which will check if the event has the TEST_STR flag set (if not, it returns false). If the flag is set, it then iterates through the events fields looking for the ones that have the "needs_test" flag set. Then it uses the offset field from the field structure to find the pointer in the ring buffer event. It runs the tests to make sure that pointer is safe to print and if not, it triggers the WARN_ON() and also adds to the trace output that the event in question has an unsafe memory access. The ignore_event() makes the trace_check_vprintf() obsolete so it is removed. Link: https://lore.kernel.org/all/CAHk-=wh3uOnqnZPpR0PeLZZtyWbZLboZ7cHLCKRWsocvs9Y7hQ@mail.gmail.com/ Cc: stable@vger.kernel.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: https://lore.kernel.org/20241217024720.848621576@goodmis.org Fixes: 5013f454a352c ("tracing: Add check of trace event print fmts for dereferencing pointers") Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-12-17 02:41:22 +00:00
trace_seq_vprintf(s, trace_event_format(iter, fmt), ap);
va_end(ap);
}
EXPORT_SYMBOL(trace_event_printf);
static __printf(3, 0)
int trace_output_raw(struct trace_iterator *iter, char *name,
char *fmt, va_list ap)
{
struct trace_seq *s = &iter->seq;
trace_seq_printf(s, "%s: ", name);
trace_seq_vprintf(s, trace_event_format(iter, fmt), ap);
return trace_handle_return(s);
}
int trace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...)
{
va_list ap;
int ret;
va_start(ap, fmt);
ret = trace_output_raw(iter, name, fmt, ap);
va_end(ap);
return ret;
}
EXPORT_SYMBOL_GPL(trace_output_call);
static inline const char *kretprobed(const char *name, unsigned long addr)
{
if (is_kretprobe_trampoline(addr))
return "[unknown/kretprobe'd]";
return name;
}
ftrace: Add recording of functions that caused recursion This adds CONFIG_FTRACE_RECORD_RECURSION that will record to a file "recursed_functions" all the functions that caused recursion while a callback to the function tracer was running. Link: https://lkml.kernel.org/r/20201106023548.102375687@goodmis.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Guo Ren <guoren@kernel.org> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Helge Deller <deller@gmx.de> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Borislav Petkov <bp@alien8.de> Cc: x86@kernel.org Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Anton Vorontsov <anton@enomsg.org> Cc: Colin Cross <ccross@android.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Jiri Kosina <jikos@kernel.org> Cc: Miroslav Benes <mbenes@suse.cz> Cc: Petr Mladek <pmladek@suse.com> Cc: Joe Lawrence <joe.lawrence@redhat.com> Cc: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com> Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-csky@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-s390@vger.kernel.org Cc: live-patching@vger.kernel.org Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2020-11-06 02:32:46 +00:00
void
trace_seq_print_sym(struct trace_seq *s, unsigned long address, bool offset)
{
tracing: Show address when function names are not found Currently, when a function is not found in kallsyms, instead of simply showing the function address, it shows nothing at all: # echo ':mod:kvm_intel' > /sys/kernel/tracing/set_ftrace_filter # echo function > /sys/kernel/tracing/set_ftrace_filter # qemu -enable-kvm /home/my-qemu-image <Ctrl-C> # rmmod kvm_intel # cat /sys/kernel/tracing/trace qemu-system-x86-2408 [001] d..2 135.013238: <-kvm_arch_hardware_enable qemu-system-x86-2408 [001] .... 135.014574: <-kvm_arch_vm_ioctl qemu-system-x86-2408 [001] .... 135.015420: <-kvm_vm_ioctl_check_extension qemu-system-x86-2408 [001] .... 135.045411: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: <-__do_cpuid_ent qemu-system-x86-2408 [001] ...1 135.045413: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045413: <-__do_cpuid_ent When it should show: qemu-system-x86-2408 [001] d..2 135.013238: 0xffffffffa02a39f0 <-kvm_arch_hardware_enable qemu-system-x86-2408 [001] .... 135.014574: 0xffffffffa02a2ba0 <-kvm_arch_vm_ioctl qemu-system-x86-2408 [001] .... 135.015420: 0xffffffffa029e4e0 <-kvm_vm_ioctl_check_extension qemu-system-x86-2408 [001] .... 135.045411: 0xffffffffa02a1380 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: 0xffffffffa029e160 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: 0xffffffffa029e180 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: 0xffffffffa029e520 <-__do_cpuid_ent qemu-system-x86-2408 [001] ...1 135.045413: 0xffffffffa02a13b0 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045413: 0xffffffffa02a1380 <-__do_cpuid_ent instead. Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-06-22 21:04:55 +00:00
#ifdef CONFIG_KALLSYMS
char str[KSYM_SYMBOL_LEN];
const char *name;
if (offset)
sprint_symbol(str, address);
else
kallsyms_lookup(address, NULL, NULL, NULL, str);
name = kretprobed(str, address);
tracing: Show address when function names are not found Currently, when a function is not found in kallsyms, instead of simply showing the function address, it shows nothing at all: # echo ':mod:kvm_intel' > /sys/kernel/tracing/set_ftrace_filter # echo function > /sys/kernel/tracing/set_ftrace_filter # qemu -enable-kvm /home/my-qemu-image <Ctrl-C> # rmmod kvm_intel # cat /sys/kernel/tracing/trace qemu-system-x86-2408 [001] d..2 135.013238: <-kvm_arch_hardware_enable qemu-system-x86-2408 [001] .... 135.014574: <-kvm_arch_vm_ioctl qemu-system-x86-2408 [001] .... 135.015420: <-kvm_vm_ioctl_check_extension qemu-system-x86-2408 [001] .... 135.045411: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: <-__do_cpuid_ent qemu-system-x86-2408 [001] ...1 135.045413: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045413: <-__do_cpuid_ent When it should show: qemu-system-x86-2408 [001] d..2 135.013238: 0xffffffffa02a39f0 <-kvm_arch_hardware_enable qemu-system-x86-2408 [001] .... 135.014574: 0xffffffffa02a2ba0 <-kvm_arch_vm_ioctl qemu-system-x86-2408 [001] .... 135.015420: 0xffffffffa029e4e0 <-kvm_vm_ioctl_check_extension qemu-system-x86-2408 [001] .... 135.045411: 0xffffffffa02a1380 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: 0xffffffffa029e160 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: 0xffffffffa029e180 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: 0xffffffffa029e520 <-__do_cpuid_ent qemu-system-x86-2408 [001] ...1 135.045413: 0xffffffffa02a13b0 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045413: 0xffffffffa02a1380 <-__do_cpuid_ent instead. Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-06-22 21:04:55 +00:00
if (name && strlen(name)) {
trace_seq_puts(s, name);
tracing: Show address when function names are not found Currently, when a function is not found in kallsyms, instead of simply showing the function address, it shows nothing at all: # echo ':mod:kvm_intel' > /sys/kernel/tracing/set_ftrace_filter # echo function > /sys/kernel/tracing/set_ftrace_filter # qemu -enable-kvm /home/my-qemu-image <Ctrl-C> # rmmod kvm_intel # cat /sys/kernel/tracing/trace qemu-system-x86-2408 [001] d..2 135.013238: <-kvm_arch_hardware_enable qemu-system-x86-2408 [001] .... 135.014574: <-kvm_arch_vm_ioctl qemu-system-x86-2408 [001] .... 135.015420: <-kvm_vm_ioctl_check_extension qemu-system-x86-2408 [001] .... 135.045411: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: <-__do_cpuid_ent qemu-system-x86-2408 [001] ...1 135.045413: <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045413: <-__do_cpuid_ent When it should show: qemu-system-x86-2408 [001] d..2 135.013238: 0xffffffffa02a39f0 <-kvm_arch_hardware_enable qemu-system-x86-2408 [001] .... 135.014574: 0xffffffffa02a2ba0 <-kvm_arch_vm_ioctl qemu-system-x86-2408 [001] .... 135.015420: 0xffffffffa029e4e0 <-kvm_vm_ioctl_check_extension qemu-system-x86-2408 [001] .... 135.045411: 0xffffffffa02a1380 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: 0xffffffffa029e160 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: 0xffffffffa029e180 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045412: 0xffffffffa029e520 <-__do_cpuid_ent qemu-system-x86-2408 [001] ...1 135.045413: 0xffffffffa02a13b0 <-__do_cpuid_ent qemu-system-x86-2408 [001] .... 135.045413: 0xffffffffa02a1380 <-__do_cpuid_ent instead. Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-06-22 21:04:55 +00:00
return;
}
#endif
trace_seq_printf(s, "0x%08lx", address);
}
#ifndef CONFIG_64BIT
# define IP_FMT "%08lx"
#else
# define IP_FMT "%016lx"
#endif
static int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
unsigned long ip, unsigned long sym_flags)
{
struct file *file = NULL;
unsigned long vmstart = 0;
int ret = 1;
if (s->full)
return 0;
if (mm) {
const struct vm_area_struct *vma;
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 04:33:25 +00:00
mmap_read_lock(mm);
vma = find_vma(mm, ip);
if (vma) {
file = vma->vm_file;
vmstart = vma->vm_start;
}
if (file) {
ret = trace_seq_path(s, file_user_path(file));
if (ret)
trace_seq_printf(s, "[+0x%lx]",
ip - vmstart);
}
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 04:33:25 +00:00
mmap_read_unlock(mm);
}
if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file))
trace_seq_printf(s, " <" IP_FMT ">", ip);
return !trace_seq_has_overflowed(s);
}
int
seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
{
if (!ip) {
trace_seq_putc(s, '0');
goto out;
}
ftrace: Add recording of functions that caused recursion This adds CONFIG_FTRACE_RECORD_RECURSION that will record to a file "recursed_functions" all the functions that caused recursion while a callback to the function tracer was running. Link: https://lkml.kernel.org/r/20201106023548.102375687@goodmis.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Guo Ren <guoren@kernel.org> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Helge Deller <deller@gmx.de> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Borislav Petkov <bp@alien8.de> Cc: x86@kernel.org Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Anton Vorontsov <anton@enomsg.org> Cc: Colin Cross <ccross@android.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Jiri Kosina <jikos@kernel.org> Cc: Miroslav Benes <mbenes@suse.cz> Cc: Petr Mladek <pmladek@suse.com> Cc: Joe Lawrence <joe.lawrence@redhat.com> Cc: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com> Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-csky@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-s390@vger.kernel.org Cc: live-patching@vger.kernel.org Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2020-11-06 02:32:46 +00:00
trace_seq_print_sym(s, ip, sym_flags & TRACE_ITER_SYM_OFFSET);
if (sym_flags & TRACE_ITER_SYM_ADDR)
trace_seq_printf(s, " <" IP_FMT ">", ip);
out:
return !trace_seq_has_overflowed(s);
}
/**
* trace_print_lat_fmt - print the irq, preempt and lockdep fields
* @s: trace seq struct to write to
* @entry: The trace entry field from the ring buffer
*
* Prints the generic fields of irqs off, in hard or softirq, preempt
* count.
*/
int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
{
char hardsoft_irq;
char need_resched;
char irqs_off;
int hardirq;
int softirq;
int bh_off;
int nmi;
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
nmi = entry->flags & TRACE_FLAG_NMI;
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
bh_off = entry->flags & TRACE_FLAG_BH_OFF;
irqs_off =
(entry->flags & TRACE_FLAG_IRQS_OFF && bh_off) ? 'D' :
(entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
bh_off ? 'b' :
'.';
switch (entry->flags & (TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY |
TRACE_FLAG_PREEMPT_RESCHED)) {
case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY | TRACE_FLAG_PREEMPT_RESCHED:
need_resched = 'B';
break;
case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_PREEMPT_RESCHED:
need_resched = 'N';
break;
case TRACE_FLAG_NEED_RESCHED_LAZY | TRACE_FLAG_PREEMPT_RESCHED:
need_resched = 'L';
break;
case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY:
need_resched = 'b';
break;
case TRACE_FLAG_NEED_RESCHED:
need_resched = 'n';
break;
case TRACE_FLAG_PREEMPT_RESCHED:
need_resched = 'p';
break;
case TRACE_FLAG_NEED_RESCHED_LAZY:
need_resched = 'l';
break;
default:
need_resched = '.';
break;
}
hardsoft_irq =
(nmi && hardirq) ? 'Z' :
nmi ? 'z' :
(hardirq && softirq) ? 'H' :
hardirq ? 'h' :
softirq ? 's' :
'.' ;
trace_seq_printf(s, "%c%c%c",
irqs_off, need_resched, hardsoft_irq);
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
tracing: Add migrate-disabled counter to tracing output. migrate_disable() forbids task migration to another CPU. It is available since v5.11 and has already users such as highmem or BPF. It is useful to observe this task state in tracing which already has other states like the preemption counter. Instead of adding the migrate disable counter as a new entry to struct trace_entry, which would extend the whole struct by four bytes, it is squashed into the preempt-disable counter. The lower four bits represent the preemption counter, the upper four bits represent the migrate disable counter. Both counter shouldn't exceed 15 but if they do, there is a safety net which caps the value at 15. Add the migrate-disable counter to the trace entry so it shows up in the trace. Due to the users mentioned above, it is already possible to observe it: | bash-1108 [000] ...21 73.950578: rss_stat: mm_id=2213312838 curr=0 type=MM_ANONPAGES size=8192B | bash-1108 [000] d..31 73.951222: irq_disable: caller=flush_tlb_mm_range+0x115/0x130 parent=ptep_clear_flush+0x42/0x50 | bash-1108 [000] d..31 73.951222: tlb_flush: pages:1 reason:local mm shootdown (3) The last value is the migrate-disable counter. Things that popped up: - trace_print_lat_context() does not print the migrate counter. Not sure if it should. It is used in "verbose" mode and uses 8 digits and I'm not sure ther is something processing the value. - trace_define_common_fields() now defines a different variable. This probably breaks things. No ide what to do in order to preserve the old behaviour. Since this is used as a filter it should be split somehow to be able to match both nibbles here. Link: https://lkml.kernel.org/r/20210810132625.ylssabmsrkygokuv@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de> [bigeasy: patch description.] Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> [ SDR: Removed change to common_preempt_count field name ] Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2021-08-10 13:26:25 +00:00
if (entry->preempt_count & 0xf)
trace_seq_printf(s, "%x", entry->preempt_count & 0xf);
else
trace_seq_putc(s, '.');
if (entry->preempt_count & 0xf0)
trace_seq_printf(s, "%x", entry->preempt_count >> 4);
else
trace_seq_putc(s, '.');
return !trace_seq_has_overflowed(s);
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
}
static int
lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
{
char comm[TASK_COMM_LEN];
trace_find_cmdline(entry->pid, comm);
trace_seq_printf(s, "%8.8s-%-7d %3d",
comm, entry->pid, cpu);
return trace_print_lat_fmt(s, entry);
}
tracing: Add additional marks to signal very large time deltas Currently, function graph tracer prints "!" or "+" just before function execution time to signal a function overhead, depending on the time. And some tracers tracing latency also print "!" or "+" just after time to signal overhead, depending on the interval between events. Even it is usually enough to do that, we sometimes need to signal for bigger execution time than 100 micro seconds. For example, I used function graph tracer to detect if there is any case that exit_mm() takes too much time. I did following steps in /sys/kernel/debug/tracing. It was easier to detect very large excution time with patched kernel than with original kernel. $ echo exit_mm > set_graph_function $ echo function_graph > current_tracer $ echo > trace $ cat trace_pipe > $LOGFILE ... (do something and terminate logging) $ grep "\\$" $LOGFILE 3) $ 22082032 us | } /* kernel_map_pages */ 3) $ 22082040 us | } /* free_pages_prepare */ 3) $ 22082113 us | } /* free_hot_cold_page */ 3) $ 22083455 us | } /* free_hot_cold_page_list */ 3) $ 22083895 us | } /* release_pages */ 3) $ 22177873 us | } /* free_pages_and_swap_cache */ 3) $ 22178929 us | } /* unmap_single_vma */ 3) $ 22198885 us | } /* unmap_vmas */ 3) $ 22206949 us | } /* exit_mmap */ 3) $ 22207659 us | } /* mmput */ 3) $ 22207793 us | } /* exit_mm */ And then, it was easy to find out that a schedule-out occured by sub_preempt_count() within kernel_map_pages(). To detect very large function exection time caused by either problematic function implementation or scheduling issues, this patch can be useful. Link: http://lkml.kernel.org/r/1416789259-24038-1-git-send-email-byungchul.park@lge.com Signed-off-by: Byungchul Park <byungchul.park@lge.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-11-24 00:34:19 +00:00
#undef MARK
#define MARK(v, s) {.val = v, .sym = s}
/* trace overhead mark */
static const struct trace_mark {
unsigned long long val; /* unit: nsec */
char sym;
} mark[] = {
MARK(1000000000ULL , '$'), /* 1 sec */
MARK(100000000ULL , '@'), /* 100 msec */
MARK(10000000ULL , '*'), /* 10 msec */
tracing: Add additional marks to signal very large time deltas Currently, function graph tracer prints "!" or "+" just before function execution time to signal a function overhead, depending on the time. And some tracers tracing latency also print "!" or "+" just after time to signal overhead, depending on the interval between events. Even it is usually enough to do that, we sometimes need to signal for bigger execution time than 100 micro seconds. For example, I used function graph tracer to detect if there is any case that exit_mm() takes too much time. I did following steps in /sys/kernel/debug/tracing. It was easier to detect very large excution time with patched kernel than with original kernel. $ echo exit_mm > set_graph_function $ echo function_graph > current_tracer $ echo > trace $ cat trace_pipe > $LOGFILE ... (do something and terminate logging) $ grep "\\$" $LOGFILE 3) $ 22082032 us | } /* kernel_map_pages */ 3) $ 22082040 us | } /* free_pages_prepare */ 3) $ 22082113 us | } /* free_hot_cold_page */ 3) $ 22083455 us | } /* free_hot_cold_page_list */ 3) $ 22083895 us | } /* release_pages */ 3) $ 22177873 us | } /* free_pages_and_swap_cache */ 3) $ 22178929 us | } /* unmap_single_vma */ 3) $ 22198885 us | } /* unmap_vmas */ 3) $ 22206949 us | } /* exit_mmap */ 3) $ 22207659 us | } /* mmput */ 3) $ 22207793 us | } /* exit_mm */ And then, it was easy to find out that a schedule-out occured by sub_preempt_count() within kernel_map_pages(). To detect very large function exection time caused by either problematic function implementation or scheduling issues, this patch can be useful. Link: http://lkml.kernel.org/r/1416789259-24038-1-git-send-email-byungchul.park@lge.com Signed-off-by: Byungchul Park <byungchul.park@lge.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-11-24 00:34:19 +00:00
MARK(1000000ULL , '#'), /* 1000 usecs */
MARK(100000ULL , '!'), /* 100 usecs */
MARK(10000ULL , '+'), /* 10 usecs */
};
#undef MARK
char trace_find_mark(unsigned long long d)
{
int i;
int size = ARRAY_SIZE(mark);
for (i = 0; i < size; i++) {
if (d > mark[i].val)
tracing: Add additional marks to signal very large time deltas Currently, function graph tracer prints "!" or "+" just before function execution time to signal a function overhead, depending on the time. And some tracers tracing latency also print "!" or "+" just after time to signal overhead, depending on the interval between events. Even it is usually enough to do that, we sometimes need to signal for bigger execution time than 100 micro seconds. For example, I used function graph tracer to detect if there is any case that exit_mm() takes too much time. I did following steps in /sys/kernel/debug/tracing. It was easier to detect very large excution time with patched kernel than with original kernel. $ echo exit_mm > set_graph_function $ echo function_graph > current_tracer $ echo > trace $ cat trace_pipe > $LOGFILE ... (do something and terminate logging) $ grep "\\$" $LOGFILE 3) $ 22082032 us | } /* kernel_map_pages */ 3) $ 22082040 us | } /* free_pages_prepare */ 3) $ 22082113 us | } /* free_hot_cold_page */ 3) $ 22083455 us | } /* free_hot_cold_page_list */ 3) $ 22083895 us | } /* release_pages */ 3) $ 22177873 us | } /* free_pages_and_swap_cache */ 3) $ 22178929 us | } /* unmap_single_vma */ 3) $ 22198885 us | } /* unmap_vmas */ 3) $ 22206949 us | } /* exit_mmap */ 3) $ 22207659 us | } /* mmput */ 3) $ 22207793 us | } /* exit_mm */ And then, it was easy to find out that a schedule-out occured by sub_preempt_count() within kernel_map_pages(). To detect very large function exection time caused by either problematic function implementation or scheduling issues, this patch can be useful. Link: http://lkml.kernel.org/r/1416789259-24038-1-git-send-email-byungchul.park@lge.com Signed-off-by: Byungchul Park <byungchul.park@lge.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-11-24 00:34:19 +00:00
break;
}
return (i == size) ? ' ' : mark[i].sym;
}
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
static int
tracing: Format non-nanosec times from tsc clock without a decimal point. With the addition of the "tsc" clock, formatting timestamps to look like fractional seconds is misleading. Mark clocks as either in nanoseconds or not, and format non-nanosecond timestamps as decimal integers. Tested: $ cd /sys/kernel/debug/tracing/ $ cat trace_clock [local] global tsc $ echo sched_switch > set_event $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ cat trace <idle>-0 [000] 6330.555552: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 [000] 6330.555628: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo 1 > options/latency-format $ cat trace <idle>-0 0 4104553247us+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 0 4104553322us+: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo tsc > trace_clock $ cat trace $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ echo 0 > options/latency-format $ cat trace <idle>-0 [000] 16490053398357: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 [000] 16490053588518: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... echo 1 > options/latency-format $ cat trace <idle>-0 0 91557653238+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 0 91557843399+: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... v2: Move arch-specific bits out of generic code. v4: Fix x86_32 build due to 64-bit division. Google-Bug-Id: 6980623 Link: http://lkml.kernel.org/r/1352837903-32191-2-git-send-email-dhsharp@google.com Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: David Sharp <dhsharp@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-11-13 20:18:22 +00:00
lat_print_timestamp(struct trace_iterator *iter, u64 next_ts)
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
{
struct trace_array *tr = iter->tr;
unsigned long verbose = tr->trace_flags & TRACE_ITER_VERBOSE;
tracing: Format non-nanosec times from tsc clock without a decimal point. With the addition of the "tsc" clock, formatting timestamps to look like fractional seconds is misleading. Mark clocks as either in nanoseconds or not, and format non-nanosecond timestamps as decimal integers. Tested: $ cd /sys/kernel/debug/tracing/ $ cat trace_clock [local] global tsc $ echo sched_switch > set_event $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ cat trace <idle>-0 [000] 6330.555552: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 [000] 6330.555628: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo 1 > options/latency-format $ cat trace <idle>-0 0 4104553247us+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 0 4104553322us+: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo tsc > trace_clock $ cat trace $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ echo 0 > options/latency-format $ cat trace <idle>-0 [000] 16490053398357: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 [000] 16490053588518: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... echo 1 > options/latency-format $ cat trace <idle>-0 0 91557653238+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 0 91557843399+: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... v2: Move arch-specific bits out of generic code. v4: Fix x86_32 build due to 64-bit division. Google-Bug-Id: 6980623 Link: http://lkml.kernel.org/r/1352837903-32191-2-git-send-email-dhsharp@google.com Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: David Sharp <dhsharp@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-11-13 20:18:22 +00:00
unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS;
unsigned long long abs_ts = iter->ts - iter->array_buffer->time_start;
tracing: Format non-nanosec times from tsc clock without a decimal point. With the addition of the "tsc" clock, formatting timestamps to look like fractional seconds is misleading. Mark clocks as either in nanoseconds or not, and format non-nanosecond timestamps as decimal integers. Tested: $ cd /sys/kernel/debug/tracing/ $ cat trace_clock [local] global tsc $ echo sched_switch > set_event $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ cat trace <idle>-0 [000] 6330.555552: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 [000] 6330.555628: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo 1 > options/latency-format $ cat trace <idle>-0 0 4104553247us+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 0 4104553322us+: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo tsc > trace_clock $ cat trace $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ echo 0 > options/latency-format $ cat trace <idle>-0 [000] 16490053398357: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 [000] 16490053588518: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... echo 1 > options/latency-format $ cat trace <idle>-0 0 91557653238+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 0 91557843399+: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... v2: Move arch-specific bits out of generic code. v4: Fix x86_32 build due to 64-bit division. Google-Bug-Id: 6980623 Link: http://lkml.kernel.org/r/1352837903-32191-2-git-send-email-dhsharp@google.com Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: David Sharp <dhsharp@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-11-13 20:18:22 +00:00
unsigned long long rel_ts = next_ts - iter->ts;
struct trace_seq *s = &iter->seq;
if (in_ns) {
abs_ts = ns2usecs(abs_ts);
rel_ts = ns2usecs(rel_ts);
}
if (verbose && in_ns) {
unsigned long abs_usec = do_div(abs_ts, USEC_PER_MSEC);
unsigned long abs_msec = (unsigned long)abs_ts;
unsigned long rel_usec = do_div(rel_ts, USEC_PER_MSEC);
unsigned long rel_msec = (unsigned long)rel_ts;
trace_seq_printf(
s, "[%08llx] %ld.%03ldms (+%ld.%03ldms): ",
ns2usecs(iter->ts),
abs_msec, abs_usec,
rel_msec, rel_usec);
tracing: Format non-nanosec times from tsc clock without a decimal point. With the addition of the "tsc" clock, formatting timestamps to look like fractional seconds is misleading. Mark clocks as either in nanoseconds or not, and format non-nanosecond timestamps as decimal integers. Tested: $ cd /sys/kernel/debug/tracing/ $ cat trace_clock [local] global tsc $ echo sched_switch > set_event $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ cat trace <idle>-0 [000] 6330.555552: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 [000] 6330.555628: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo 1 > options/latency-format $ cat trace <idle>-0 0 4104553247us+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 0 4104553322us+: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo tsc > trace_clock $ cat trace $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ echo 0 > options/latency-format $ cat trace <idle>-0 [000] 16490053398357: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 [000] 16490053588518: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... echo 1 > options/latency-format $ cat trace <idle>-0 0 91557653238+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 0 91557843399+: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... v2: Move arch-specific bits out of generic code. v4: Fix x86_32 build due to 64-bit division. Google-Bug-Id: 6980623 Link: http://lkml.kernel.org/r/1352837903-32191-2-git-send-email-dhsharp@google.com Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: David Sharp <dhsharp@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-11-13 20:18:22 +00:00
} else if (verbose && !in_ns) {
trace_seq_printf(
s, "[%016llx] %lld (+%lld): ",
iter->ts, abs_ts, rel_ts);
tracing: Format non-nanosec times from tsc clock without a decimal point. With the addition of the "tsc" clock, formatting timestamps to look like fractional seconds is misleading. Mark clocks as either in nanoseconds or not, and format non-nanosecond timestamps as decimal integers. Tested: $ cd /sys/kernel/debug/tracing/ $ cat trace_clock [local] global tsc $ echo sched_switch > set_event $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ cat trace <idle>-0 [000] 6330.555552: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 [000] 6330.555628: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo 1 > options/latency-format $ cat trace <idle>-0 0 4104553247us+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 0 4104553322us+: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo tsc > trace_clock $ cat trace $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ echo 0 > options/latency-format $ cat trace <idle>-0 [000] 16490053398357: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 [000] 16490053588518: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... echo 1 > options/latency-format $ cat trace <idle>-0 0 91557653238+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 0 91557843399+: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... v2: Move arch-specific bits out of generic code. v4: Fix x86_32 build due to 64-bit division. Google-Bug-Id: 6980623 Link: http://lkml.kernel.org/r/1352837903-32191-2-git-send-email-dhsharp@google.com Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: David Sharp <dhsharp@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-11-13 20:18:22 +00:00
} else if (!verbose && in_ns) {
trace_seq_printf(
s, " %4lldus%c: ",
abs_ts,
tracing: Add additional marks to signal very large time deltas Currently, function graph tracer prints "!" or "+" just before function execution time to signal a function overhead, depending on the time. And some tracers tracing latency also print "!" or "+" just after time to signal overhead, depending on the interval between events. Even it is usually enough to do that, we sometimes need to signal for bigger execution time than 100 micro seconds. For example, I used function graph tracer to detect if there is any case that exit_mm() takes too much time. I did following steps in /sys/kernel/debug/tracing. It was easier to detect very large excution time with patched kernel than with original kernel. $ echo exit_mm > set_graph_function $ echo function_graph > current_tracer $ echo > trace $ cat trace_pipe > $LOGFILE ... (do something and terminate logging) $ grep "\\$" $LOGFILE 3) $ 22082032 us | } /* kernel_map_pages */ 3) $ 22082040 us | } /* free_pages_prepare */ 3) $ 22082113 us | } /* free_hot_cold_page */ 3) $ 22083455 us | } /* free_hot_cold_page_list */ 3) $ 22083895 us | } /* release_pages */ 3) $ 22177873 us | } /* free_pages_and_swap_cache */ 3) $ 22178929 us | } /* unmap_single_vma */ 3) $ 22198885 us | } /* unmap_vmas */ 3) $ 22206949 us | } /* exit_mmap */ 3) $ 22207659 us | } /* mmput */ 3) $ 22207793 us | } /* exit_mm */ And then, it was easy to find out that a schedule-out occured by sub_preempt_count() within kernel_map_pages(). To detect very large function exection time caused by either problematic function implementation or scheduling issues, this patch can be useful. Link: http://lkml.kernel.org/r/1416789259-24038-1-git-send-email-byungchul.park@lge.com Signed-off-by: Byungchul Park <byungchul.park@lge.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-11-24 00:34:19 +00:00
trace_find_mark(rel_ts * NSEC_PER_USEC));
tracing: Format non-nanosec times from tsc clock without a decimal point. With the addition of the "tsc" clock, formatting timestamps to look like fractional seconds is misleading. Mark clocks as either in nanoseconds or not, and format non-nanosecond timestamps as decimal integers. Tested: $ cd /sys/kernel/debug/tracing/ $ cat trace_clock [local] global tsc $ echo sched_switch > set_event $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ cat trace <idle>-0 [000] 6330.555552: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 [000] 6330.555628: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo 1 > options/latency-format $ cat trace <idle>-0 0 4104553247us+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 0 4104553322us+: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo tsc > trace_clock $ cat trace $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ echo 0 > options/latency-format $ cat trace <idle>-0 [000] 16490053398357: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 [000] 16490053588518: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... echo 1 > options/latency-format $ cat trace <idle>-0 0 91557653238+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 0 91557843399+: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... v2: Move arch-specific bits out of generic code. v4: Fix x86_32 build due to 64-bit division. Google-Bug-Id: 6980623 Link: http://lkml.kernel.org/r/1352837903-32191-2-git-send-email-dhsharp@google.com Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: David Sharp <dhsharp@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-11-13 20:18:22 +00:00
} else { /* !verbose && !in_ns */
trace_seq_printf(s, " %4lld: ", abs_ts);
tracing: Format non-nanosec times from tsc clock without a decimal point. With the addition of the "tsc" clock, formatting timestamps to look like fractional seconds is misleading. Mark clocks as either in nanoseconds or not, and format non-nanosecond timestamps as decimal integers. Tested: $ cd /sys/kernel/debug/tracing/ $ cat trace_clock [local] global tsc $ echo sched_switch > set_event $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ cat trace <idle>-0 [000] 6330.555552: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 [000] 6330.555628: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo 1 > options/latency-format $ cat trace <idle>-0 0 4104553247us+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 0 4104553322us+: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo tsc > trace_clock $ cat trace $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ echo 0 > options/latency-format $ cat trace <idle>-0 [000] 16490053398357: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 [000] 16490053588518: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... echo 1 > options/latency-format $ cat trace <idle>-0 0 91557653238+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 0 91557843399+: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... v2: Move arch-specific bits out of generic code. v4: Fix x86_32 build due to 64-bit division. Google-Bug-Id: 6980623 Link: http://lkml.kernel.org/r/1352837903-32191-2-git-send-email-dhsharp@google.com Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: David Sharp <dhsharp@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-11-13 20:18:22 +00:00
}
return !trace_seq_has_overflowed(s);
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
}
static void trace_print_time(struct trace_seq *s, struct trace_iterator *iter,
unsigned long long ts)
{
unsigned long secs, usec_rem;
unsigned long long t;
if (iter->iter_flags & TRACE_FILE_TIME_IN_NS) {
t = ns2usecs(ts);
usec_rem = do_div(t, USEC_PER_SEC);
secs = (unsigned long)t;
trace_seq_printf(s, " %5lu.%06lu", secs, usec_rem);
} else
trace_seq_printf(s, " %12llu", ts);
}
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
int trace_print_context(struct trace_iterator *iter)
{
struct trace_array *tr = iter->tr;
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
struct trace_seq *s = &iter->seq;
struct trace_entry *entry = iter->ent;
char comm[TASK_COMM_LEN];
trace_find_cmdline(entry->pid, comm);
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
trace_seq_printf(s, "%16s-%-7d ", comm, entry->pid);
tracing: Add irq, preempt-count and need resched info to default trace output People keep asking how to get the preempt count, irq, and need resched info and we keep telling them to enable the latency format. Some developers think that traces without this info is completely useless, and for a lot of tasks it is useless. The first option was to enable the latency trace as the default format, but the header for the latency format is pretty useless for most tracers and it also does the timestamp in straight microseconds from the time the trace started. This is sometimes more difficult to read as the default trace is seconds from the start of boot up. Latency format: # tracer: nop # # nop latency trace v1.1.5 on 3.2.0-rc1-test+ # -------------------------------------------------------------------- # latency: 0 us, #159771/64234230, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) # ----------------- # | task: -0 (uid:0 nice:0 policy:0 rt_prio:0) # ----------------- # # _------=> CPU# # / _-----=> irqs-off # | / _----=> need-resched # || / _---=> hardirq/softirq # ||| / _--=> preempt-depth # |||| / delay # cmd pid ||||| time | caller # \ / ||||| \ | / migratio-6 0...2 41778231us+: rcu_note_context_switch <-__schedule migratio-6 0...2 41778233us : trace_rcu_utilization <-rcu_note_context_switch migratio-6 0...2 41778235us+: rcu_sched_qs <-rcu_note_context_switch migratio-6 0d..2 41778236us+: rcu_preempt_qs <-rcu_note_context_switch migratio-6 0...2 41778238us : trace_rcu_utilization <-rcu_note_context_switch migratio-6 0...2 41778239us+: debug_lockdep_rcu_enabled <-__schedule default format: # tracer: nop # # TASK-PID CPU# TIMESTAMP FUNCTION # | | | | | migration/0-6 [000] 50.025810: rcu_note_context_switch <-__schedule migration/0-6 [000] 50.025812: trace_rcu_utilization <-rcu_note_context_switch migration/0-6 [000] 50.025813: rcu_sched_qs <-rcu_note_context_switch migration/0-6 [000] 50.025815: rcu_preempt_qs <-rcu_note_context_switch migration/0-6 [000] 50.025817: trace_rcu_utilization <-rcu_note_context_switch migration/0-6 [000] 50.025818: debug_lockdep_rcu_enabled <-__schedule migration/0-6 [000] 50.025820: debug_lockdep_rcu_enabled <-__schedule The latency format header has latency information that is pretty meaningless for most tracers. Although some of the header is useful, and we can add that later to the default format as well. What is really useful with the latency format is the irqs-off, need-resched hard/softirq context and the preempt count. This commit adds the option irq-info which is on by default that adds this information: # tracer: nop # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU# |||| TIMESTAMP FUNCTION # | | | |||| | | <idle>-0 [000] d..2 49.309305: cpuidle_get_driver <-cpuidle_idle_call <idle>-0 [000] d..2 49.309307: mwait_idle <-cpu_idle <idle>-0 [000] d..2 49.309309: need_resched <-mwait_idle <idle>-0 [000] d..2 49.309310: test_ti_thread_flag <-need_resched <idle>-0 [000] d..2 49.309312: trace_power_start.constprop.13 <-mwait_idle <idle>-0 [000] d..2 49.309313: trace_cpu_idle <-mwait_idle <idle>-0 [000] d..2 49.309315: need_resched <-mwait_idle If a user wants the old format, they can disable the 'irq-info' option: # tracer: nop # # TASK-PID CPU# TIMESTAMP FUNCTION # | | | | | <idle>-0 [000] 49.309305: cpuidle_get_driver <-cpuidle_idle_call <idle>-0 [000] 49.309307: mwait_idle <-cpu_idle <idle>-0 [000] 49.309309: need_resched <-mwait_idle <idle>-0 [000] 49.309310: test_ti_thread_flag <-need_resched <idle>-0 [000] 49.309312: trace_power_start.constprop.13 <-mwait_idle <idle>-0 [000] 49.309313: trace_cpu_idle <-mwait_idle <idle>-0 [000] 49.309315: need_resched <-mwait_idle Requested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-11-17 14:34:33 +00:00
if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
unsigned int tgid = trace_find_tgid(entry->pid);
if (!tgid)
trace_seq_printf(s, "(-------) ");
else
trace_seq_printf(s, "(%7d) ", tgid);
}
tracing: Reorder display of TGID to be after PID Currently ftrace displays data in trace output like so: _-----=> irqs-off / _----=> need-resched | / _---=> hardirq/softirq || / _--=> preempt-depth ||| / delay TASK-PID CPU TGID |||| TIMESTAMP FUNCTION | | | | |||| | | bash-1091 [000] ( 1091) d..2 28.313544: sched_switch: However Android's trace visualization tools expect a slightly different format due to an out-of-tree patch patch that was been carried for a decade, notice that the TGID and CPU fields are reversed: _-----=> irqs-off / _----=> need-resched | / _---=> hardirq/softirq || / _--=> preempt-depth ||| / delay TASK-PID TGID CPU |||| TIMESTAMP FUNCTION | | | | |||| | | bash-1091 ( 1091) [002] d..2 64.965177: sched_switch: From kernel v4.13 onwards, during which TGID was introduced, tracing with systrace on all Android kernels will break (most Android kernels have been on 4.9 with Android patches, so this issues hasn't been seen yet). From v4.13 onwards things will break. The chrome browser's tracing tools also embed the systrace viewer which uses the legacy TGID format and updates to that are known to be difficult to make. Considering this, I suggest we make this change to the upstream kernel and backport it to all Android kernels. I believe this feature is merged recently enough into the upstream kernel that it shouldn't be a problem. Also logically, IMO it makes more sense to group the TGID with the TASK-PID and the CPU after these. Link: http://lkml.kernel.org/r/20180626000822.113931-1-joel@joelfernandes.org Cc: jreck@google.com Cc: tkjos@google.com Cc: stable@vger.kernel.org Fixes: 441dae8f2f29 ("tracing: Add support for display of tgid in trace output") Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2018-06-26 00:08:22 +00:00
trace_seq_printf(s, "[%03d] ", iter->cpu);
if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
trace_print_lat_fmt(s, entry);
tracing: Add irq, preempt-count and need resched info to default trace output People keep asking how to get the preempt count, irq, and need resched info and we keep telling them to enable the latency format. Some developers think that traces without this info is completely useless, and for a lot of tasks it is useless. The first option was to enable the latency trace as the default format, but the header for the latency format is pretty useless for most tracers and it also does the timestamp in straight microseconds from the time the trace started. This is sometimes more difficult to read as the default trace is seconds from the start of boot up. Latency format: # tracer: nop # # nop latency trace v1.1.5 on 3.2.0-rc1-test+ # -------------------------------------------------------------------- # latency: 0 us, #159771/64234230, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4) # ----------------- # | task: -0 (uid:0 nice:0 policy:0 rt_prio:0) # ----------------- # # _------=> CPU# # / _-----=> irqs-off # | / _----=> need-resched # || / _---=> hardirq/softirq # ||| / _--=> preempt-depth # |||| / delay # cmd pid ||||| time | caller # \ / ||||| \ | / migratio-6 0...2 41778231us+: rcu_note_context_switch <-__schedule migratio-6 0...2 41778233us : trace_rcu_utilization <-rcu_note_context_switch migratio-6 0...2 41778235us+: rcu_sched_qs <-rcu_note_context_switch migratio-6 0d..2 41778236us+: rcu_preempt_qs <-rcu_note_context_switch migratio-6 0...2 41778238us : trace_rcu_utilization <-rcu_note_context_switch migratio-6 0...2 41778239us+: debug_lockdep_rcu_enabled <-__schedule default format: # tracer: nop # # TASK-PID CPU# TIMESTAMP FUNCTION # | | | | | migration/0-6 [000] 50.025810: rcu_note_context_switch <-__schedule migration/0-6 [000] 50.025812: trace_rcu_utilization <-rcu_note_context_switch migration/0-6 [000] 50.025813: rcu_sched_qs <-rcu_note_context_switch migration/0-6 [000] 50.025815: rcu_preempt_qs <-rcu_note_context_switch migration/0-6 [000] 50.025817: trace_rcu_utilization <-rcu_note_context_switch migration/0-6 [000] 50.025818: debug_lockdep_rcu_enabled <-__schedule migration/0-6 [000] 50.025820: debug_lockdep_rcu_enabled <-__schedule The latency format header has latency information that is pretty meaningless for most tracers. Although some of the header is useful, and we can add that later to the default format as well. What is really useful with the latency format is the irqs-off, need-resched hard/softirq context and the preempt count. This commit adds the option irq-info which is on by default that adds this information: # tracer: nop # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU# |||| TIMESTAMP FUNCTION # | | | |||| | | <idle>-0 [000] d..2 49.309305: cpuidle_get_driver <-cpuidle_idle_call <idle>-0 [000] d..2 49.309307: mwait_idle <-cpu_idle <idle>-0 [000] d..2 49.309309: need_resched <-mwait_idle <idle>-0 [000] d..2 49.309310: test_ti_thread_flag <-need_resched <idle>-0 [000] d..2 49.309312: trace_power_start.constprop.13 <-mwait_idle <idle>-0 [000] d..2 49.309313: trace_cpu_idle <-mwait_idle <idle>-0 [000] d..2 49.309315: need_resched <-mwait_idle If a user wants the old format, they can disable the 'irq-info' option: # tracer: nop # # TASK-PID CPU# TIMESTAMP FUNCTION # | | | | | <idle>-0 [000] 49.309305: cpuidle_get_driver <-cpuidle_idle_call <idle>-0 [000] 49.309307: mwait_idle <-cpu_idle <idle>-0 [000] 49.309309: need_resched <-mwait_idle <idle>-0 [000] 49.309310: test_ti_thread_flag <-need_resched <idle>-0 [000] 49.309312: trace_power_start.constprop.13 <-mwait_idle <idle>-0 [000] 49.309313: trace_cpu_idle <-mwait_idle <idle>-0 [000] 49.309315: need_resched <-mwait_idle Requested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-11-17 14:34:33 +00:00
trace_print_time(s, iter, iter->ts);
trace_seq_puts(s, ": ");
return !trace_seq_has_overflowed(s);
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
}
int trace_print_lat_context(struct trace_iterator *iter)
{
struct trace_entry *entry, *next_entry;
struct trace_array *tr = iter->tr;
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
struct trace_seq *s = &iter->seq;
unsigned long verbose = (tr->trace_flags & TRACE_ITER_VERBOSE);
u64 next_ts;
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
next_entry = trace_find_next_entry(iter, NULL, &next_ts);
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
if (!next_entry)
next_ts = iter->ts;
/* trace_find_next_entry() may change iter->ent */
entry = iter->ent;
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
if (verbose) {
char comm[TASK_COMM_LEN];
trace_find_cmdline(entry->pid, comm);
trace_seq_printf(
s, "%16s %7d %3d %d %08x %08lx ",
comm, entry->pid, iter->cpu, entry->flags,
tracing: Add migrate-disabled counter to tracing output. migrate_disable() forbids task migration to another CPU. It is available since v5.11 and has already users such as highmem or BPF. It is useful to observe this task state in tracing which already has other states like the preemption counter. Instead of adding the migrate disable counter as a new entry to struct trace_entry, which would extend the whole struct by four bytes, it is squashed into the preempt-disable counter. The lower four bits represent the preemption counter, the upper four bits represent the migrate disable counter. Both counter shouldn't exceed 15 but if they do, there is a safety net which caps the value at 15. Add the migrate-disable counter to the trace entry so it shows up in the trace. Due to the users mentioned above, it is already possible to observe it: | bash-1108 [000] ...21 73.950578: rss_stat: mm_id=2213312838 curr=0 type=MM_ANONPAGES size=8192B | bash-1108 [000] d..31 73.951222: irq_disable: caller=flush_tlb_mm_range+0x115/0x130 parent=ptep_clear_flush+0x42/0x50 | bash-1108 [000] d..31 73.951222: tlb_flush: pages:1 reason:local mm shootdown (3) The last value is the migrate-disable counter. Things that popped up: - trace_print_lat_context() does not print the migrate counter. Not sure if it should. It is used in "verbose" mode and uses 8 digits and I'm not sure ther is something processing the value. - trace_define_common_fields() now defines a different variable. This probably breaks things. No ide what to do in order to preserve the old behaviour. Since this is used as a filter it should be split somehow to be able to match both nibbles here. Link: https://lkml.kernel.org/r/20210810132625.ylssabmsrkygokuv@linutronix.de Signed-off-by: Thomas Gleixner <tglx@linutronix.de> [bigeasy: patch description.] Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> [ SDR: Removed change to common_preempt_count field name ] Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2021-08-10 13:26:25 +00:00
entry->preempt_count & 0xf, iter->idx);
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
} else {
lat_print_generic(s, entry, iter->cpu);
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
}
lat_print_timestamp(iter, next_ts);
tracing: Format non-nanosec times from tsc clock without a decimal point. With the addition of the "tsc" clock, formatting timestamps to look like fractional seconds is misleading. Mark clocks as either in nanoseconds or not, and format non-nanosecond timestamps as decimal integers. Tested: $ cd /sys/kernel/debug/tracing/ $ cat trace_clock [local] global tsc $ echo sched_switch > set_event $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ cat trace <idle>-0 [000] 6330.555552: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 [000] 6330.555628: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo 1 > options/latency-format $ cat trace <idle>-0 0 4104553247us+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=29964 next_prio=120 sleep-29964 0 4104553322us+: sched_switch: prev_comm=bash prev_pid=29964 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... $ echo tsc > trace_clock $ cat trace $ echo 1 > tracing_on ; sleep 0.0005 ; echo 0 > tracing_on $ echo 0 > options/latency-format $ cat trace <idle>-0 [000] 16490053398357: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 [000] 16490053588518: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... echo 1 > options/latency-format $ cat trace <idle>-0 0 91557653238+: sched_switch: prev_comm=swapper prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=bash next_pid=31128 next_prio=120 sleep-31128 0 91557843399+: sched_switch: prev_comm=bash prev_pid=31128 prev_prio=120 prev_state=S ==> next_comm=swapper next_pid=0 next_prio=120 ... v2: Move arch-specific bits out of generic code. v4: Fix x86_32 build due to 64-bit division. Google-Bug-Id: 6980623 Link: http://lkml.kernel.org/r/1352837903-32191-2-git-send-email-dhsharp@google.com Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: David Sharp <dhsharp@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-11-13 20:18:22 +00:00
return !trace_seq_has_overflowed(s);
trace: better manage the context info for events Impact: make trace_event more convenient for tracers All tracers (for the moment) that use the struct trace_event want to have the context info printed before their own output: the pid/cmdline, cpu, and timestamp. But some other tracers that want to implement their trace_event callbacks will not necessary need these information or they may want to format them as they want. This patch adds a new default-enabled trace option: TRACE_ITER_CONTEXT_INFO When disabled through: echo nocontext-info > /debugfs/tracing/trace_options The pid, cpu and timestamps headers will not be printed. IE with the sched_switch tracer with context-info (default): bash-2935 [001] 100.356561: 2935:120:S ==> [001] 0:140:R <idle> <idle>-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0 <idle>-0 [000] 100.412816: 0:140:R ==> [000] 11:115:R events/0 events/0-11 [000] 100.412829: 11:115:S ==> [000] 0:140:R <idle> Without context-info: 2935:120:S ==> [001] 0:140:R <idle> 0:140:R + [000] 11:115:S events/0 0:140:R ==> [000] 11:115:R events/0 11:115:S ==> [000] 0:140:R <idle> A tracer can disable it at runtime by clearing the bit TRACE_ITER_CONTEXT_INFO in trace_flags. The print routines were renamed to trace_print_context and trace_print_lat_context, so that they can be used by tracers if they want to use them for one of the trace_event callbacks. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-02 22:29:21 +00:00
}
/**
* ftrace_find_event - find a registered event
* @type: the type of event to look for
*
* Returns an event of type @type otherwise NULL
* Called with trace_event_read_lock() held.
*/
struct trace_event *ftrace_find_event(int type)
{
struct trace_event *event;
unsigned key;
key = type & (EVENT_HASHSIZE - 1);
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry(event, &event_hash[key], node) {
if (event->type == type)
return event;
}
return NULL;
}
static DEFINE_IDA(trace_event_ida);
static void free_trace_event_type(int type)
{
if (type >= __TRACE_LAST_TYPE)
ida_free(&trace_event_ida, type);
}
static int alloc_trace_event_type(void)
{
int next;
/* Skip static defined type numbers */
next = ida_alloc_range(&trace_event_ida, __TRACE_LAST_TYPE,
TRACE_EVENT_TYPE_MAX, GFP_KERNEL);
if (next < 0)
return 0;
return next;
}
void trace_event_read_lock(void)
{
down_read(&trace_event_sem);
}
void trace_event_read_unlock(void)
{
up_read(&trace_event_sem);
}
/**
* register_trace_event - register output for an event type
* @event: the event type to register
*
* Event types are stored in a hash and this hash is used to
* find a way to print an event. If the @event->type is set
* then it will use that type, otherwise it will assign a
* type to use.
*
* If you assign your own type, please make sure it is added
* to the trace_type enum in trace.h, to avoid collisions
* with the dynamic types.
*
* Returns the event type number or zero on error.
*/
int register_trace_event(struct trace_event *event)
{
unsigned key;
int ret = 0;
down_write(&trace_event_sem);
if (WARN_ON(!event))
goto out;
if (WARN_ON(!event->funcs))
goto out;
if (!event->type) {
event->type = alloc_trace_event_type();
if (!event->type)
goto out;
} else if (WARN(event->type > __TRACE_LAST_TYPE,
"Need to add type to trace.h")) {
goto out;
} else {
/* Is this event already used */
if (ftrace_find_event(event->type))
goto out;
}
if (event->funcs->trace == NULL)
event->funcs->trace = trace_nop_print;
if (event->funcs->raw == NULL)
event->funcs->raw = trace_nop_print;
if (event->funcs->hex == NULL)
event->funcs->hex = trace_nop_print;
if (event->funcs->binary == NULL)
event->funcs->binary = trace_nop_print;
key = event->type & (EVENT_HASHSIZE - 1);
hlist_add_head(&event->node, &event_hash[key]);
ret = event->type;
out:
up_write(&trace_event_sem);
return ret;
}
EXPORT_SYMBOL_GPL(register_trace_event);
/*
* Used by module code with the trace_event_sem held for write.
*/
int __unregister_trace_event(struct trace_event *event)
{
hlist_del(&event->node);
free_trace_event_type(event->type);
return 0;
}
/**
* unregister_trace_event - remove a no longer used event
* @event: the event to remove
*/
int unregister_trace_event(struct trace_event *event)
{
down_write(&trace_event_sem);
__unregister_trace_event(event);
up_write(&trace_event_sem);
return 0;
}
EXPORT_SYMBOL_GPL(unregister_trace_event);
/*
* Standard events
*/
tracing: Add "fields" option to show raw trace event fields The hex, raw and bin formats come from the old PREEMPT_RT patch set latency tracer. That actually gave real alternatives to reading the ascii buffer. But they have started to bit rot and they do not give a good representation of the tracing data. Add "fields" option that will read the trace event fields and parse the data from how the fields are defined: With "fields" = 0 (default) echo 1 > events/sched/sched_switch/enable cat trace <idle>-0 [003] d..2. 540.078653: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/3:1 next_pid=83 next_prio=120 kworker/3:1-83 [003] d..2. 540.078860: sched_switch: prev_comm=kworker/3:1 prev_pid=83 prev_prio=120 prev_state=I ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [003] d..2. 540.206423: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=sshd next_pid=807 next_prio=120 sshd-807 [003] d..2. 540.206531: sched_switch: prev_comm=sshd prev_pid=807 prev_prio=120 prev_state=S ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [001] d..2. 540.206597: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206617: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206678: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206696: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206713: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 echo 1 > options/fields <...>-998 [002] d..2. 538.643732: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/2 prev_state=0x20 (32) prev_prio=0x78 (120) prev_pid=0x3e6 (998) prev_comm=trace-cmd <idle>-0 [001] d..2. 538.643806: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/1 bash-830 [001] d..2. 538.644106: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644130: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644180: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644185: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644204: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/1 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash <idle>-0 [003] d..2. 538.644211: sched_switch: next_prio=0x78 (120) next_pid=0x327 (807) next_comm=sshd prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/3 sshd-807 [003] d..2. 538.644340: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/3 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x327 (807) prev_comm=sshd It traces the data safely without using the trace print formatting. Link: https://lore.kernel.org/linux-trace-kernel/20230328145156.497651be@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-03-28 18:51:56 +00:00
static void print_array(struct trace_iterator *iter, void *pos,
struct ftrace_event_field *field)
{
int offset;
int len;
int i;
offset = *(int *)pos & 0xffff;
len = *(int *)pos >> 16;
if (field)
2023-04-19 21:41:40 +00:00
offset += field->offset + sizeof(int);
tracing: Add "fields" option to show raw trace event fields The hex, raw and bin formats come from the old PREEMPT_RT patch set latency tracer. That actually gave real alternatives to reading the ascii buffer. But they have started to bit rot and they do not give a good representation of the tracing data. Add "fields" option that will read the trace event fields and parse the data from how the fields are defined: With "fields" = 0 (default) echo 1 > events/sched/sched_switch/enable cat trace <idle>-0 [003] d..2. 540.078653: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/3:1 next_pid=83 next_prio=120 kworker/3:1-83 [003] d..2. 540.078860: sched_switch: prev_comm=kworker/3:1 prev_pid=83 prev_prio=120 prev_state=I ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [003] d..2. 540.206423: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=sshd next_pid=807 next_prio=120 sshd-807 [003] d..2. 540.206531: sched_switch: prev_comm=sshd prev_pid=807 prev_prio=120 prev_state=S ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [001] d..2. 540.206597: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206617: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206678: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206696: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206713: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 echo 1 > options/fields <...>-998 [002] d..2. 538.643732: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/2 prev_state=0x20 (32) prev_prio=0x78 (120) prev_pid=0x3e6 (998) prev_comm=trace-cmd <idle>-0 [001] d..2. 538.643806: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/1 bash-830 [001] d..2. 538.644106: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644130: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644180: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644185: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644204: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/1 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash <idle>-0 [003] d..2. 538.644211: sched_switch: next_prio=0x78 (120) next_pid=0x327 (807) next_comm=sshd prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/3 sshd-807 [003] d..2. 538.644340: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/3 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x327 (807) prev_comm=sshd It traces the data safely without using the trace print formatting. Link: https://lore.kernel.org/linux-trace-kernel/20230328145156.497651be@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-03-28 18:51:56 +00:00
2023-04-19 21:41:40 +00:00
if (offset + len > iter->ent_size) {
tracing: Add "fields" option to show raw trace event fields The hex, raw and bin formats come from the old PREEMPT_RT patch set latency tracer. That actually gave real alternatives to reading the ascii buffer. But they have started to bit rot and they do not give a good representation of the tracing data. Add "fields" option that will read the trace event fields and parse the data from how the fields are defined: With "fields" = 0 (default) echo 1 > events/sched/sched_switch/enable cat trace <idle>-0 [003] d..2. 540.078653: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/3:1 next_pid=83 next_prio=120 kworker/3:1-83 [003] d..2. 540.078860: sched_switch: prev_comm=kworker/3:1 prev_pid=83 prev_prio=120 prev_state=I ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [003] d..2. 540.206423: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=sshd next_pid=807 next_prio=120 sshd-807 [003] d..2. 540.206531: sched_switch: prev_comm=sshd prev_pid=807 prev_prio=120 prev_state=S ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [001] d..2. 540.206597: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206617: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206678: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206696: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206713: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 echo 1 > options/fields <...>-998 [002] d..2. 538.643732: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/2 prev_state=0x20 (32) prev_prio=0x78 (120) prev_pid=0x3e6 (998) prev_comm=trace-cmd <idle>-0 [001] d..2. 538.643806: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/1 bash-830 [001] d..2. 538.644106: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644130: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644180: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644185: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644204: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/1 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash <idle>-0 [003] d..2. 538.644211: sched_switch: next_prio=0x78 (120) next_pid=0x327 (807) next_comm=sshd prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/3 sshd-807 [003] d..2. 538.644340: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/3 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x327 (807) prev_comm=sshd It traces the data safely without using the trace print formatting. Link: https://lore.kernel.org/linux-trace-kernel/20230328145156.497651be@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-03-28 18:51:56 +00:00
trace_seq_puts(&iter->seq, "<OVERFLOW>");
return;
}
2023-04-19 21:41:40 +00:00
pos = (void *)iter->ent + offset;
tracing: Add "fields" option to show raw trace event fields The hex, raw and bin formats come from the old PREEMPT_RT patch set latency tracer. That actually gave real alternatives to reading the ascii buffer. But they have started to bit rot and they do not give a good representation of the tracing data. Add "fields" option that will read the trace event fields and parse the data from how the fields are defined: With "fields" = 0 (default) echo 1 > events/sched/sched_switch/enable cat trace <idle>-0 [003] d..2. 540.078653: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/3:1 next_pid=83 next_prio=120 kworker/3:1-83 [003] d..2. 540.078860: sched_switch: prev_comm=kworker/3:1 prev_pid=83 prev_prio=120 prev_state=I ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [003] d..2. 540.206423: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=sshd next_pid=807 next_prio=120 sshd-807 [003] d..2. 540.206531: sched_switch: prev_comm=sshd prev_pid=807 prev_prio=120 prev_state=S ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [001] d..2. 540.206597: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206617: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206678: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206696: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206713: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 echo 1 > options/fields <...>-998 [002] d..2. 538.643732: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/2 prev_state=0x20 (32) prev_prio=0x78 (120) prev_pid=0x3e6 (998) prev_comm=trace-cmd <idle>-0 [001] d..2. 538.643806: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/1 bash-830 [001] d..2. 538.644106: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644130: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644180: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644185: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644204: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/1 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash <idle>-0 [003] d..2. 538.644211: sched_switch: next_prio=0x78 (120) next_pid=0x327 (807) next_comm=sshd prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/3 sshd-807 [003] d..2. 538.644340: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/3 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x327 (807) prev_comm=sshd It traces the data safely without using the trace print formatting. Link: https://lore.kernel.org/linux-trace-kernel/20230328145156.497651be@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-03-28 18:51:56 +00:00
for (i = 0; i < len; i++, pos++) {
if (i)
trace_seq_putc(&iter->seq, ',');
trace_seq_printf(&iter->seq, "%02x", *(unsigned char *)pos);
}
}
static void print_fields(struct trace_iterator *iter, struct trace_event_call *call,
struct list_head *head)
{
struct ftrace_event_field *field;
int offset;
int len;
int ret;
void *pos;
list_for_each_entry_reverse(field, head, link) {
tracing: Add "fields" option to show raw trace event fields The hex, raw and bin formats come from the old PREEMPT_RT patch set latency tracer. That actually gave real alternatives to reading the ascii buffer. But they have started to bit rot and they do not give a good representation of the tracing data. Add "fields" option that will read the trace event fields and parse the data from how the fields are defined: With "fields" = 0 (default) echo 1 > events/sched/sched_switch/enable cat trace <idle>-0 [003] d..2. 540.078653: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/3:1 next_pid=83 next_prio=120 kworker/3:1-83 [003] d..2. 540.078860: sched_switch: prev_comm=kworker/3:1 prev_pid=83 prev_prio=120 prev_state=I ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [003] d..2. 540.206423: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=sshd next_pid=807 next_prio=120 sshd-807 [003] d..2. 540.206531: sched_switch: prev_comm=sshd prev_pid=807 prev_prio=120 prev_state=S ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [001] d..2. 540.206597: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206617: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206678: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206696: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206713: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 echo 1 > options/fields <...>-998 [002] d..2. 538.643732: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/2 prev_state=0x20 (32) prev_prio=0x78 (120) prev_pid=0x3e6 (998) prev_comm=trace-cmd <idle>-0 [001] d..2. 538.643806: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/1 bash-830 [001] d..2. 538.644106: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644130: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644180: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644185: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644204: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/1 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash <idle>-0 [003] d..2. 538.644211: sched_switch: next_prio=0x78 (120) next_pid=0x327 (807) next_comm=sshd prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/3 sshd-807 [003] d..2. 538.644340: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/3 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x327 (807) prev_comm=sshd It traces the data safely without using the trace print formatting. Link: https://lore.kernel.org/linux-trace-kernel/20230328145156.497651be@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-03-28 18:51:56 +00:00
trace_seq_printf(&iter->seq, " %s=", field->name);
if (field->offset + field->size > iter->ent_size) {
trace_seq_puts(&iter->seq, "<OVERFLOW>");
continue;
}
pos = (void *)iter->ent + field->offset;
switch (field->filter_type) {
case FILTER_COMM:
case FILTER_STATIC_STRING:
trace_seq_printf(&iter->seq, "%.*s", field->size, (char *)pos);
break;
case FILTER_RDYN_STRING:
case FILTER_DYN_STRING:
offset = *(int *)pos & 0xffff;
len = *(int *)pos >> 16;
if (field->filter_type == FILTER_RDYN_STRING)
2023-04-19 21:41:40 +00:00
offset += field->offset + sizeof(int);
tracing: Add "fields" option to show raw trace event fields The hex, raw and bin formats come from the old PREEMPT_RT patch set latency tracer. That actually gave real alternatives to reading the ascii buffer. But they have started to bit rot and they do not give a good representation of the tracing data. Add "fields" option that will read the trace event fields and parse the data from how the fields are defined: With "fields" = 0 (default) echo 1 > events/sched/sched_switch/enable cat trace <idle>-0 [003] d..2. 540.078653: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/3:1 next_pid=83 next_prio=120 kworker/3:1-83 [003] d..2. 540.078860: sched_switch: prev_comm=kworker/3:1 prev_pid=83 prev_prio=120 prev_state=I ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [003] d..2. 540.206423: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=sshd next_pid=807 next_prio=120 sshd-807 [003] d..2. 540.206531: sched_switch: prev_comm=sshd prev_pid=807 prev_prio=120 prev_state=S ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [001] d..2. 540.206597: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206617: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206678: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206696: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206713: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 echo 1 > options/fields <...>-998 [002] d..2. 538.643732: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/2 prev_state=0x20 (32) prev_prio=0x78 (120) prev_pid=0x3e6 (998) prev_comm=trace-cmd <idle>-0 [001] d..2. 538.643806: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/1 bash-830 [001] d..2. 538.644106: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644130: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644180: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644185: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644204: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/1 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash <idle>-0 [003] d..2. 538.644211: sched_switch: next_prio=0x78 (120) next_pid=0x327 (807) next_comm=sshd prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/3 sshd-807 [003] d..2. 538.644340: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/3 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x327 (807) prev_comm=sshd It traces the data safely without using the trace print formatting. Link: https://lore.kernel.org/linux-trace-kernel/20230328145156.497651be@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-03-28 18:51:56 +00:00
2023-04-19 21:41:40 +00:00
if (offset + len > iter->ent_size) {
tracing: Add "fields" option to show raw trace event fields The hex, raw and bin formats come from the old PREEMPT_RT patch set latency tracer. That actually gave real alternatives to reading the ascii buffer. But they have started to bit rot and they do not give a good representation of the tracing data. Add "fields" option that will read the trace event fields and parse the data from how the fields are defined: With "fields" = 0 (default) echo 1 > events/sched/sched_switch/enable cat trace <idle>-0 [003] d..2. 540.078653: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/3:1 next_pid=83 next_prio=120 kworker/3:1-83 [003] d..2. 540.078860: sched_switch: prev_comm=kworker/3:1 prev_pid=83 prev_prio=120 prev_state=I ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [003] d..2. 540.206423: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=sshd next_pid=807 next_prio=120 sshd-807 [003] d..2. 540.206531: sched_switch: prev_comm=sshd prev_pid=807 prev_prio=120 prev_state=S ==> next_comm=swapper/3 next_pid=0 next_prio=120 <idle>-0 [001] d..2. 540.206597: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206617: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206678: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206696: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206713: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 echo 1 > options/fields <...>-998 [002] d..2. 538.643732: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/2 prev_state=0x20 (32) prev_prio=0x78 (120) prev_pid=0x3e6 (998) prev_comm=trace-cmd <idle>-0 [001] d..2. 538.643806: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/1 bash-830 [001] d..2. 538.644106: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644130: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644180: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644185: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644204: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/1 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash <idle>-0 [003] d..2. 538.644211: sched_switch: next_prio=0x78 (120) next_pid=0x327 (807) next_comm=sshd prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/3 sshd-807 [003] d..2. 538.644340: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/3 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x327 (807) prev_comm=sshd It traces the data safely without using the trace print formatting. Link: https://lore.kernel.org/linux-trace-kernel/20230328145156.497651be@gandalf.local.home Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-03-28 18:51:56 +00:00
trace_seq_puts(&iter->seq, "<OVERFLOW>");
break;
}
pos = (void *)iter->ent + offset;
trace_seq_printf(&iter->seq, "%.*s", len, (char *)pos);
break;
case FILTER_PTR_STRING:
if (!iter->fmt_size)
trace_iter_expand_format(iter);
pos = *(void **)pos;
ret = strncpy_from_kernel_nofault(iter->fmt, pos,
iter->fmt_size);
if (ret < 0)
trace_seq_printf(&iter->seq, "(0x%px)", pos);
else
trace_seq_printf(&iter->seq, "(0x%px:%s)",
pos, iter->fmt);
break;
case FILTER_TRACE_FN:
pos = *(void **)pos;
trace_seq_printf(&iter->seq, "%pS", pos);
break;
case FILTER_CPU:
case FILTER_OTHER:
switch (field->size) {
case 1:
if (isprint(*(char *)pos)) {
trace_seq_printf(&iter->seq, "'%c'",
*(unsigned char *)pos);
}
trace_seq_printf(&iter->seq, "(%d)",
*(unsigned char *)pos);
break;
case 2:
trace_seq_printf(&iter->seq, "0x%x (%d)",
*(unsigned short *)pos,
*(unsigned short *)pos);
break;
case 4:
/* dynamic array info is 4 bytes */
if (strstr(field->type, "__data_loc")) {
print_array(iter, pos, NULL);
break;
}
if (strstr(field->type, "__rel_loc")) {
print_array(iter, pos, field);
break;
}
trace_seq_printf(&iter->seq, "0x%x (%d)",
*(unsigned int *)pos,
*(unsigned int *)pos);
break;
case 8:
trace_seq_printf(&iter->seq, "0x%llx (%lld)",
*(unsigned long long *)pos,
*(unsigned long long *)pos);
break;
default:
trace_seq_puts(&iter->seq, "<INVALID-SIZE>");
break;
}
break;
default:
trace_seq_puts(&iter->seq, "<INVALID-TYPE>");
}
}
trace_seq_putc(&iter->seq, '\n');
}
enum print_line_t print_event_fields(struct trace_iterator *iter,
struct trace_event *event)
{
struct trace_event_call *call;
struct list_head *head;
/* ftrace defined events have separate call structures */
if (event->type <= __TRACE_LAST_TYPE) {
bool found = false;
down_read(&trace_event_sem);
list_for_each_entry(call, &ftrace_events, list) {
if (call->event.type == event->type) {
found = true;
break;
}
/* No need to search all events */
if (call->event.type > __TRACE_LAST_TYPE)
break;
}
up_read(&trace_event_sem);
if (!found) {
trace_seq_printf(&iter->seq, "UNKNOWN TYPE %d\n", event->type);
goto out;
}
} else {
call = container_of(event, struct trace_event_call, event);
}
head = trace_get_fields(call);
trace_seq_printf(&iter->seq, "%s:", trace_event_name(call));
if (head && !list_empty(head))
print_fields(iter, call, head);
else
trace_seq_puts(&iter->seq, "No fields found\n");
out:
return trace_handle_return(&iter->seq);
}
enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
trace_seq_printf(&iter->seq, "type: %d\n", iter->ent->type);
return trace_handle_return(&iter->seq);
}
static void print_fn_trace(struct trace_seq *s, unsigned long ip,
tracing: Update function tracing output for previous boot buffer For a persistent ring buffer that is saved across boots, if function tracing was performed in the previous boot, it only saves the address of the functions and uses "%pS" to print their names. But the current boot, those functions may be in different locations. The persistent meta-data saves the text delta between the two boots and can be used to find the address of the saved function of where it is located in the current boot. Link: https://lkml.kernel.org/r/20240612232026.988226055@goodmis.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Vincent Donnefort <vdonnefort@google.com> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vineeth Pillai <vineeth@bitbyteword.org> Cc: Youssef Esmat <youssefesmat@google.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Cc: Alexander Graf <graf@amazon.com> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: David Howells <dhowells@redhat.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Ross Zwisler <zwisler@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-06-12 23:19:46 +00:00
unsigned long parent_ip, long delta, int flags)
{
tracing: Update function tracing output for previous boot buffer For a persistent ring buffer that is saved across boots, if function tracing was performed in the previous boot, it only saves the address of the functions and uses "%pS" to print their names. But the current boot, those functions may be in different locations. The persistent meta-data saves the text delta between the two boots and can be used to find the address of the saved function of where it is located in the current boot. Link: https://lkml.kernel.org/r/20240612232026.988226055@goodmis.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Vincent Donnefort <vdonnefort@google.com> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vineeth Pillai <vineeth@bitbyteword.org> Cc: Youssef Esmat <youssefesmat@google.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Cc: Alexander Graf <graf@amazon.com> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: David Howells <dhowells@redhat.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Ross Zwisler <zwisler@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-06-12 23:19:46 +00:00
ip += delta;
parent_ip += delta;
seq_print_ip_sym(s, ip, flags);
if ((flags & TRACE_ITER_PRINT_PARENT) && parent_ip) {
trace_seq_puts(s, " <-");
seq_print_ip_sym(s, parent_ip, flags);
}
}
/* TRACE_FN */
static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct ftrace_entry *field;
struct trace_seq *s = &iter->seq;
trace_assign_type(field, iter->ent);
tracing: Update function tracing output for previous boot buffer For a persistent ring buffer that is saved across boots, if function tracing was performed in the previous boot, it only saves the address of the functions and uses "%pS" to print their names. But the current boot, those functions may be in different locations. The persistent meta-data saves the text delta between the two boots and can be used to find the address of the saved function of where it is located in the current boot. Link: https://lkml.kernel.org/r/20240612232026.988226055@goodmis.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Vincent Donnefort <vdonnefort@google.com> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vineeth Pillai <vineeth@bitbyteword.org> Cc: Youssef Esmat <youssefesmat@google.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Cc: Alexander Graf <graf@amazon.com> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: David Howells <dhowells@redhat.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Ross Zwisler <zwisler@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-06-12 23:19:46 +00:00
print_fn_trace(s, field->ip, field->parent_ip, iter->tr->text_delta, flags);
trace_seq_putc(s, '\n');
return trace_handle_return(s);
}
static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct ftrace_entry *field;
trace_assign_type(field, iter->ent);
trace_seq_printf(&iter->seq, "%lx %lx\n",
field->ip,
field->parent_ip);
return trace_handle_return(&iter->seq);
}
static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct ftrace_entry *field;
struct trace_seq *s = &iter->seq;
trace_assign_type(field, iter->ent);
SEQ_PUT_HEX_FIELD(s, field->ip);
SEQ_PUT_HEX_FIELD(s, field->parent_ip);
return trace_handle_return(s);
}
static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct ftrace_entry *field;
struct trace_seq *s = &iter->seq;
trace_assign_type(field, iter->ent);
SEQ_PUT_FIELD(s, field->ip);
SEQ_PUT_FIELD(s, field->parent_ip);
return trace_handle_return(s);
}
static struct trace_event_functions trace_fn_funcs = {
.trace = trace_fn_trace,
.raw = trace_fn_raw,
.hex = trace_fn_hex,
.binary = trace_fn_bin,
};
static struct trace_event trace_fn_event = {
.type = TRACE_FN,
.funcs = &trace_fn_funcs,
};
/* TRACE_CTX an TRACE_WAKE */
static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
char *delim)
{
struct ctx_switch_entry *field;
char comm[TASK_COMM_LEN];
int S, T;
trace_assign_type(field, iter->ent);
T = task_index_to_char(field->next_state);
S = task_index_to_char(field->prev_state);
trace_find_cmdline(field->next_pid, comm);
trace_seq_printf(&iter->seq,
" %7d:%3d:%c %s [%03d] %7d:%3d:%c %s\n",
field->prev_pid,
field->prev_prio,
S, delim,
field->next_cpu,
field->next_pid,
field->next_prio,
T, comm);
return trace_handle_return(&iter->seq);
}
static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
return trace_ctxwake_print(iter, "==>");
}
static enum print_line_t trace_wake_print(struct trace_iterator *iter,
int flags, struct trace_event *event)
{
return trace_ctxwake_print(iter, " +");
}
static int trace_ctxwake_raw(struct trace_iterator *iter, char S)
{
struct ctx_switch_entry *field;
int T;
trace_assign_type(field, iter->ent);
if (!S)
S = task_index_to_char(field->prev_state);
T = task_index_to_char(field->next_state);
trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n",
field->prev_pid,
field->prev_prio,
S,
field->next_cpu,
field->next_pid,
field->next_prio,
T);
return trace_handle_return(&iter->seq);
}
static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
return trace_ctxwake_raw(iter, 0);
}
static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
return trace_ctxwake_raw(iter, '+');
}
static int trace_ctxwake_hex(struct trace_iterator *iter, char S)
{
struct ctx_switch_entry *field;
struct trace_seq *s = &iter->seq;
int T;
trace_assign_type(field, iter->ent);
if (!S)
S = task_index_to_char(field->prev_state);
T = task_index_to_char(field->next_state);
SEQ_PUT_HEX_FIELD(s, field->prev_pid);
SEQ_PUT_HEX_FIELD(s, field->prev_prio);
SEQ_PUT_HEX_FIELD(s, S);
SEQ_PUT_HEX_FIELD(s, field->next_cpu);
SEQ_PUT_HEX_FIELD(s, field->next_pid);
SEQ_PUT_HEX_FIELD(s, field->next_prio);
SEQ_PUT_HEX_FIELD(s, T);
return trace_handle_return(s);
}
static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
return trace_ctxwake_hex(iter, 0);
}
static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
return trace_ctxwake_hex(iter, '+');
}
static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter,
int flags, struct trace_event *event)
{
struct ctx_switch_entry *field;
struct trace_seq *s = &iter->seq;
trace_assign_type(field, iter->ent);
SEQ_PUT_FIELD(s, field->prev_pid);
SEQ_PUT_FIELD(s, field->prev_prio);
SEQ_PUT_FIELD(s, field->prev_state);
SEQ_PUT_FIELD(s, field->next_cpu);
SEQ_PUT_FIELD(s, field->next_pid);
SEQ_PUT_FIELD(s, field->next_prio);
SEQ_PUT_FIELD(s, field->next_state);
return trace_handle_return(s);
}
static struct trace_event_functions trace_ctx_funcs = {
.trace = trace_ctx_print,
.raw = trace_ctx_raw,
.hex = trace_ctx_hex,
.binary = trace_ctxwake_bin,
};
static struct trace_event trace_ctx_event = {
.type = TRACE_CTX,
.funcs = &trace_ctx_funcs,
};
static struct trace_event_functions trace_wake_funcs = {
.trace = trace_wake_print,
.raw = trace_wake_raw,
.hex = trace_wake_hex,
.binary = trace_ctxwake_bin,
};
static struct trace_event trace_wake_event = {
.type = TRACE_WAKE,
.funcs = &trace_wake_funcs,
};
/* TRACE_STACK */
static enum print_line_t trace_stack_print(struct trace_iterator *iter,
int flags, struct trace_event *event)
{
struct stack_entry *field;
struct trace_seq *s = &iter->seq;
unsigned long *p;
unsigned long *end;
tracing: Add last boot delta offset for stack traces The addresses of a stack trace event are relative to the kallsyms. As that can change between boots, when printing the stack trace from a buffer that was from the last boot, it needs all the addresses to be added to the "text_delta" that gives the delta between the addresses of the functions for the current boot compared to the address of the last boot. Then it can be passed to kallsyms to find the function name, otherwise it just shows a useless list of addresses. Link: https://lkml.kernel.org/r/20240612232027.145807384@goodmis.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Vincent Donnefort <vdonnefort@google.com> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vineeth Pillai <vineeth@bitbyteword.org> Cc: Youssef Esmat <youssefesmat@google.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Cc: Alexander Graf <graf@amazon.com> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: David Howells <dhowells@redhat.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Ross Zwisler <zwisler@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-06-12 23:19:47 +00:00
long delta = iter->tr->text_delta;
trace_assign_type(field, iter->ent);
end = (unsigned long *)((long)iter->ent + iter->ent_size);
trace_seq_puts(s, "<stack trace>\n");
tracing: Fix out-of-range read in trace_stack_print() Puts range check before dereferencing the pointer. Reproducer: # echo stacktrace > trace_options # echo 1 > events/enable # cat trace > /dev/null KASAN report: ================================================================== BUG: KASAN: use-after-free in trace_stack_print+0x26b/0x2c0 Read of size 8 at addr ffff888069d20000 by task cat/1953 CPU: 0 PID: 1953 Comm: cat Not tainted 5.2.0-rc3+ #5 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 Call Trace: dump_stack+0x8a/0xce print_address_description+0x60/0x224 ? trace_stack_print+0x26b/0x2c0 ? trace_stack_print+0x26b/0x2c0 __kasan_report.cold+0x1a/0x3e ? trace_stack_print+0x26b/0x2c0 kasan_report+0xe/0x20 trace_stack_print+0x26b/0x2c0 print_trace_line+0x6ea/0x14d0 ? tracing_buffers_read+0x700/0x700 ? trace_find_next_entry_inc+0x158/0x1d0 s_show+0xea/0x310 seq_read+0xaa7/0x10e0 ? seq_escape+0x230/0x230 __vfs_read+0x7c/0x100 vfs_read+0x16c/0x3a0 ksys_read+0x121/0x240 ? kernel_write+0x110/0x110 ? perf_trace_sys_enter+0x8a0/0x8a0 ? syscall_slow_exit_work+0xa9/0x410 do_syscall_64+0xb7/0x390 ? prepare_exit_to_usermode+0x165/0x200 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f867681f910 Code: b6 fe ff ff 48 8d 3d 0f be 08 00 48 83 ec 08 e8 06 db 01 00 66 0f 1f 44 00 00 83 3d f9 2d 2c 00 00 75 10 b8 00 00 00 00 04 RSP: 002b:00007ffdabf23488 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007f867681f910 RDX: 0000000000020000 RSI: 00007f8676cde000 RDI: 0000000000000003 RBP: 00007f8676cde000 R08: ffffffffffffffff R09: 0000000000000000 R10: 0000000000000871 R11: 0000000000000246 R12: 00007f8676cde000 R13: 0000000000000003 R14: 0000000000020000 R15: 0000000000000ec0 Allocated by task 1214: save_stack+0x1b/0x80 __kasan_kmalloc.constprop.0+0xc2/0xd0 kmem_cache_alloc+0xaf/0x1a0 getname_flags+0xd2/0x5b0 do_sys_open+0x277/0x5a0 do_syscall_64+0xb7/0x390 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 1214: save_stack+0x1b/0x80 __kasan_slab_free+0x12c/0x170 kmem_cache_free+0x8a/0x1c0 putname+0xe1/0x120 do_sys_open+0x2c5/0x5a0 do_syscall_64+0xb7/0x390 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The buggy address belongs to the object at ffff888069d20000 which belongs to the cache names_cache of size 4096 The buggy address is located 0 bytes inside of 4096-byte region [ffff888069d20000, ffff888069d21000) The buggy address belongs to the page: page:ffffea0001a74800 refcount:1 mapcount:0 mapping:ffff88806ccd1380 index:0x0 compound_mapcount: 0 flags: 0x100000000010200(slab|head) raw: 0100000000010200 dead000000000100 dead000000000200 ffff88806ccd1380 raw: 0000000000000000 0000000000070007 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888069d1ff00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff888069d1ff80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff888069d20000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888069d20080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888069d20100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Link: http://lkml.kernel.org/r/20190610040016.5598-1-devel@etsukata.com Fixes: 4285f2fcef80 ("tracing: Remove the ULONG_MAX stack trace hackery") Signed-off-by: Eiichi Tsukata <devel@etsukata.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2019-06-10 04:00:16 +00:00
for (p = field->caller; p && p < end && *p != ULONG_MAX; p++) {
if (trace_seq_has_overflowed(s))
break;
trace_seq_puts(s, " => ");
if ((*p) == FTRACE_TRAMPOLINE_MARKER) {
trace_seq_puts(s, "[FTRACE TRAMPOLINE]\n");
continue;
}
tracing: Add last boot delta offset for stack traces The addresses of a stack trace event are relative to the kallsyms. As that can change between boots, when printing the stack trace from a buffer that was from the last boot, it needs all the addresses to be added to the "text_delta" that gives the delta between the addresses of the functions for the current boot compared to the address of the last boot. Then it can be passed to kallsyms to find the function name, otherwise it just shows a useless list of addresses. Link: https://lkml.kernel.org/r/20240612232027.145807384@goodmis.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Vincent Donnefort <vdonnefort@google.com> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vineeth Pillai <vineeth@bitbyteword.org> Cc: Youssef Esmat <youssefesmat@google.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Cc: Alexander Graf <graf@amazon.com> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: David Howells <dhowells@redhat.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Ross Zwisler <zwisler@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-06-12 23:19:47 +00:00
seq_print_ip_sym(s, (*p) + delta, flags);
trace_seq_putc(s, '\n');
}
return trace_handle_return(s);
}
static struct trace_event_functions trace_stack_funcs = {
.trace = trace_stack_print,
};
static struct trace_event trace_stack_event = {
.type = TRACE_STACK,
.funcs = &trace_stack_funcs,
};
/* TRACE_USER_STACK */
static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
int flags, struct trace_event *event)
{
struct trace_array *tr = iter->tr;
struct userstack_entry *field;
struct trace_seq *s = &iter->seq;
struct mm_struct *mm = NULL;
unsigned int i;
trace_assign_type(field, iter->ent);
trace_seq_puts(s, "<user stack trace>\n");
if (tr->trace_flags & TRACE_ITER_SYM_USEROBJ) {
struct task_struct *task;
/*
* we do the lookup on the thread group leader,
* since individual threads might have already quit!
*/
rcu_read_lock();
task = find_task_by_vpid(field->tgid);
if (task)
mm = get_task_mm(task);
rcu_read_unlock();
}
for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
unsigned long ip = field->caller[i];
if (!ip || trace_seq_has_overflowed(s))
break;
trace_seq_puts(s, " => ");
seq_print_user_ip(s, mm, ip, flags);
trace_seq_putc(s, '\n');
}
if (mm)
mmput(mm);
return trace_handle_return(s);
}
static struct trace_event_functions trace_user_stack_funcs = {
.trace = trace_user_stack_print,
};
static struct trace_event trace_user_stack_event = {
.type = TRACE_USER_STACK,
.funcs = &trace_user_stack_funcs,
};
/* TRACE_HWLAT */
static enum print_line_t
trace_hwlat_print(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct trace_entry *entry = iter->ent;
struct trace_seq *s = &iter->seq;
struct hwlat_entry *field;
trace_assign_type(field, entry);
trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%lld.%09ld count:%d",
field->seqnum,
field->duration,
field->outer_duration,
(long long)field->timestamp.tv_sec,
field->timestamp.tv_nsec, field->count);
if (field->nmi_count) {
/*
* The generic sched_clock() is not NMI safe, thus
* we only record the count and not the time.
*/
if (!IS_ENABLED(CONFIG_GENERIC_SCHED_CLOCK))
trace_seq_printf(s, " nmi-total:%llu",
field->nmi_total_ts);
trace_seq_printf(s, " nmi-count:%u",
field->nmi_count);
}
trace_seq_putc(s, '\n');
return trace_handle_return(s);
}
static enum print_line_t
trace_hwlat_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct hwlat_entry *field;
struct trace_seq *s = &iter->seq;
trace_assign_type(field, iter->ent);
trace_seq_printf(s, "%llu %lld %lld %09ld %u\n",
field->duration,
field->outer_duration,
(long long)field->timestamp.tv_sec,
field->timestamp.tv_nsec,
field->seqnum);
return trace_handle_return(s);
}
static struct trace_event_functions trace_hwlat_funcs = {
.trace = trace_hwlat_print,
.raw = trace_hwlat_raw,
};
static struct trace_event trace_hwlat_event = {
.type = TRACE_HWLAT,
.funcs = &trace_hwlat_funcs,
};
trace: Add osnoise tracer In the context of high-performance computing (HPC), the Operating System Noise (*osnoise*) refers to the interference experienced by an application due to activities inside the operating system. In the context of Linux, NMIs, IRQs, SoftIRQs, and any other system thread can cause noise to the system. Moreover, hardware-related jobs can also cause noise, for example, via SMIs. The osnoise tracer leverages the hwlat_detector by running a similar loop with preemption, SoftIRQs and IRQs enabled, thus allowing all the sources of *osnoise* during its execution. Using the same approach of hwlat, osnoise takes note of the entry and exit point of any source of interferences, increasing a per-cpu interference counter. The osnoise tracer also saves an interference counter for each source of interference. The interference counter for NMI, IRQs, SoftIRQs, and threads is increased anytime the tool observes these interferences' entry events. When a noise happens without any interference from the operating system level, the hardware noise counter increases, pointing to a hardware-related noise. In this way, osnoise can account for any source of interference. At the end of the period, the osnoise tracer prints the sum of all noise, the max single noise, the percentage of CPU available for the thread, and the counters for the noise sources. Usage Write the ASCII text "osnoise" into the current_tracer file of the tracing system (generally mounted at /sys/kernel/tracing). For example:: [root@f32 ~]# cd /sys/kernel/tracing/ [root@f32 tracing]# echo osnoise > current_tracer It is possible to follow the trace by reading the trace trace file:: [root@f32 tracing]# cat trace # tracer: osnoise # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth MAX # || / SINGLE Interference counters: # |||| RUNTIME NOISE % OF CPU NOISE +-----------------------------+ # TASK-PID CPU# |||| TIMESTAMP IN US IN US AVAILABLE IN US HW NMI IRQ SIRQ THREAD # | | | |||| | | | | | | | | | | <...>-859 [000] .... 81.637220: 1000000 190 99.98100 9 18 0 1007 18 1 <...>-860 [001] .... 81.638154: 1000000 656 99.93440 74 23 0 1006 16 3 <...>-861 [002] .... 81.638193: 1000000 5675 99.43250 202 6 0 1013 25 21 <...>-862 [003] .... 81.638242: 1000000 125 99.98750 45 1 0 1011 23 0 <...>-863 [004] .... 81.638260: 1000000 1721 99.82790 168 7 0 1002 49 41 <...>-864 [005] .... 81.638286: 1000000 263 99.97370 57 6 0 1006 26 2 <...>-865 [006] .... 81.638302: 1000000 109 99.98910 21 3 0 1006 18 1 <...>-866 [007] .... 81.638326: 1000000 7816 99.21840 107 8 0 1016 39 19 In addition to the regular trace fields (from TASK-PID to TIMESTAMP), the tracer prints a message at the end of each period for each CPU that is running an osnoise/CPU thread. The osnoise specific fields report: - The RUNTIME IN USE reports the amount of time in microseconds that the osnoise thread kept looping reading the time. - The NOISE IN US reports the sum of noise in microseconds observed by the osnoise tracer during the associated runtime. - The % OF CPU AVAILABLE reports the percentage of CPU available for the osnoise thread during the runtime window. - The MAX SINGLE NOISE IN US reports the maximum single noise observed during the runtime window. - The Interference counters display how many each of the respective interference happened during the runtime window. Note that the example above shows a high number of HW noise samples. The reason being is that this sample was taken on a virtual machine, and the host interference is detected as a hardware interference. Tracer options The tracer has a set of options inside the osnoise directory, they are: - osnoise/cpus: CPUs at which a osnoise thread will execute. - osnoise/period_us: the period of the osnoise thread. - osnoise/runtime_us: how long an osnoise thread will look for noise. - osnoise/stop_tracing_us: stop the system tracing if a single noise higher than the configured value happens. Writing 0 disables this option. - osnoise/stop_tracing_total_us: stop the system tracing if total noise higher than the configured value happens. Writing 0 disables this option. - tracing_threshold: the minimum delta between two time() reads to be considered as noise, in us. When set to 0, the default value will be used, which is currently 5 us. Additional Tracing In addition to the tracer, a set of tracepoints were added to facilitate the identification of the osnoise source. - osnoise:sample_threshold: printed anytime a noise is higher than the configurable tolerance_ns. - osnoise:nmi_noise: noise from NMI, including the duration. - osnoise:irq_noise: noise from an IRQ, including the duration. - osnoise:softirq_noise: noise from a SoftIRQ, including the duration. - osnoise:thread_noise: noise from a thread, including the duration. Note that all the values are *net values*. For example, if while osnoise is running, another thread preempts the osnoise thread, it will start a thread_noise duration at the start. Then, an IRQ takes place, preempting the thread_noise, starting a irq_noise. When the IRQ ends its execution, it will compute its duration, and this duration will be subtracted from the thread_noise, in such a way as to avoid the double accounting of the IRQ execution. This logic is valid for all sources of noise. Here is one example of the usage of these tracepoints:: osnoise/8-961 [008] d.h. 5789.857532: irq_noise: local_timer:236 start 5789.857529929 duration 1845 ns osnoise/8-961 [008] dNh. 5789.858408: irq_noise: local_timer:236 start 5789.858404871 duration 2848 ns migration/8-54 [008] d... 5789.858413: thread_noise: migration/8:54 start 5789.858409300 duration 3068 ns osnoise/8-961 [008] .... 5789.858413: sample_threshold: start 5789.858404555 duration 8723 ns interferences 2 In this example, a noise sample of 8 microseconds was reported in the last line, pointing to two interferences. Looking backward in the trace, the two previous entries were about the migration thread running after a timer IRQ execution. The first event is not part of the noise because it took place one millisecond before. It is worth noticing that the sum of the duration reported in the tracepoints is smaller than eight us reported in the sample_threshold. The reason roots in the overhead of the entry and exit code that happens before and after any interference execution. This justifies the dual approach: measuring thread and tracing. Link: https://lkml.kernel.org/r/e649467042d60e7b62714c9c6751a56299d15119.1624372313.git.bristot@redhat.com Cc: Phil Auld <pauld@redhat.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Kate Carcia <kcarcia@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Alexandre Chartre <alexandre.chartre@oracle.com> Cc: Clark Willaims <williams@redhat.com> Cc: John Kacur <jkacur@redhat.com> Cc: Juri Lelli <juri.lelli@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> [ Made the following functions static: trace_irqentry_callback() trace_irqexit_callback() trace_intel_irqentry_callback() trace_intel_irqexit_callback() Added to include/trace.h: osnoise_arch_register() osnoise_arch_unregister() Fixed define logic for LATENCY_FS_NOTIFY Reported-by: kernel test robot <lkp@intel.com> ] Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2021-06-22 14:42:27 +00:00
/* TRACE_OSNOISE */
static enum print_line_t
trace_osnoise_print(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct trace_entry *entry = iter->ent;
struct trace_seq *s = &iter->seq;
struct osnoise_entry *field;
u64 ratio, ratio_dec;
u64 net_runtime;
trace_assign_type(field, entry);
/*
* compute the available % of cpu time.
*/
net_runtime = field->runtime - field->noise;
ratio = net_runtime * 10000000;
do_div(ratio, field->runtime);
ratio_dec = do_div(ratio, 100000);
trace_seq_printf(s, "%llu %10llu %3llu.%05llu %7llu",
field->runtime,
field->noise,
ratio, ratio_dec,
field->max_sample);
trace_seq_printf(s, " %6u", field->hw_count);
trace_seq_printf(s, " %6u", field->nmi_count);
trace_seq_printf(s, " %6u", field->irq_count);
trace_seq_printf(s, " %6u", field->softirq_count);
trace_seq_printf(s, " %6u", field->thread_count);
trace_seq_putc(s, '\n');
return trace_handle_return(s);
}
static enum print_line_t
trace_osnoise_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct osnoise_entry *field;
struct trace_seq *s = &iter->seq;
trace_assign_type(field, iter->ent);
trace_seq_printf(s, "%lld %llu %llu %u %u %u %u %u\n",
field->runtime,
field->noise,
field->max_sample,
field->hw_count,
field->nmi_count,
field->irq_count,
field->softirq_count,
field->thread_count);
return trace_handle_return(s);
}
static struct trace_event_functions trace_osnoise_funcs = {
.trace = trace_osnoise_print,
.raw = trace_osnoise_raw,
};
static struct trace_event trace_osnoise_event = {
.type = TRACE_OSNOISE,
.funcs = &trace_osnoise_funcs,
};
trace: Add timerlat tracer The timerlat tracer aims to help the preemptive kernel developers to found souces of wakeup latencies of real-time threads. Like cyclictest, the tracer sets a periodic timer that wakes up a thread. The thread then computes a *wakeup latency* value as the difference between the *current time* and the *absolute time* that the timer was set to expire. The main goal of timerlat is tracing in such a way to help kernel developers. Usage Write the ASCII text "timerlat" into the current_tracer file of the tracing system (generally mounted at /sys/kernel/tracing). For example: [root@f32 ~]# cd /sys/kernel/tracing/ [root@f32 tracing]# echo timerlat > current_tracer It is possible to follow the trace by reading the trace trace file: [root@f32 tracing]# cat trace # tracer: timerlat # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # || / # |||| ACTIVATION # TASK-PID CPU# |||| TIMESTAMP ID CONTEXT LATENCY # | | | |||| | | | | <idle>-0 [000] d.h1 54.029328: #1 context irq timer_latency 932 ns <...>-867 [000] .... 54.029339: #1 context thread timer_latency 11700 ns <idle>-0 [001] dNh1 54.029346: #1 context irq timer_latency 2833 ns <...>-868 [001] .... 54.029353: #1 context thread timer_latency 9820 ns <idle>-0 [000] d.h1 54.030328: #2 context irq timer_latency 769 ns <...>-867 [000] .... 54.030330: #2 context thread timer_latency 3070 ns <idle>-0 [001] d.h1 54.030344: #2 context irq timer_latency 935 ns <...>-868 [001] .... 54.030347: #2 context thread timer_latency 4351 ns The tracer creates a per-cpu kernel thread with real-time priority that prints two lines at every activation. The first is the *timer latency* observed at the *hardirq* context before the activation of the thread. The second is the *timer latency* observed by the thread, which is the same level that cyclictest reports. The ACTIVATION ID field serves to relate the *irq* execution to its respective *thread* execution. The irq/thread splitting is important to clarify at which context the unexpected high value is coming from. The *irq* context can be delayed by hardware related actions, such as SMIs, NMIs, IRQs or by a thread masking interrupts. Once the timer happens, the delay can also be influenced by blocking caused by threads. For example, by postponing the scheduler execution via preempt_disable(), by the scheduler execution, or by masking interrupts. Threads can also be delayed by the interference from other threads and IRQs. The timerlat can also take advantage of the osnoise: traceevents. For example: [root@f32 ~]# cd /sys/kernel/tracing/ [root@f32 tracing]# echo timerlat > current_tracer [root@f32 tracing]# echo osnoise > set_event [root@f32 tracing]# echo 25 > osnoise/stop_tracing_total_us [root@f32 tracing]# tail -10 trace cc1-87882 [005] d..h... 548.771078: #402268 context irq timer_latency 1585 ns cc1-87882 [005] dNLh1.. 548.771082: irq_noise: local_timer:236 start 548.771077442 duration 4597 ns cc1-87882 [005] dNLh2.. 548.771083: irq_noise: reschedule:253 start 548.771083017 duration 56 ns cc1-87882 [005] dNLh2.. 548.771086: irq_noise: call_function_single:251 start 548.771083811 duration 2048 ns cc1-87882 [005] dNLh2.. 548.771088: irq_noise: call_function_single:251 start 548.771086814 duration 1495 ns cc1-87882 [005] dNLh2.. 548.771091: irq_noise: call_function_single:251 start 548.771089194 duration 1558 ns cc1-87882 [005] dNLh2.. 548.771094: irq_noise: call_function_single:251 start 548.771091719 duration 1932 ns cc1-87882 [005] dNLh2.. 548.771096: irq_noise: call_function_single:251 start 548.771094696 duration 1050 ns cc1-87882 [005] d...3.. 548.771101: thread_noise: cc1:87882 start 548.771078243 duration 10909 ns timerlat/5-1035 [005] ....... 548.771103: #402268 context thread timer_latency 25960 ns For further information see: Documentation/trace/timerlat-tracer.rst Link: https://lkml.kernel.org/r/71f18efc013e1194bcaea1e54db957de2b19ba62.1624372313.git.bristot@redhat.com Cc: Phil Auld <pauld@redhat.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Kate Carcia <kcarcia@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Alexandre Chartre <alexandre.chartre@oracle.com> Cc: Clark Willaims <williams@redhat.com> Cc: John Kacur <jkacur@redhat.com> Cc: Juri Lelli <juri.lelli@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2021-06-22 14:42:28 +00:00
/* TRACE_TIMERLAT */
tracing/timerlat: Add user-space interface Going a step further, we propose a way to use any user-space workload as the task waiting for the timerlat timer. This is done via a per-CPU file named osnoise/cpu$id/timerlat_fd file. The tracef_fd allows a task to open at a time. When a task reads the file, the timerlat timer is armed for future osnoise/timerlat_period_us time. When the timer fires, it prints the IRQ latency and wakes up the user-space thread waiting in the timerlat_fd. The thread then starts to run, executes the timerlat measurement, prints the thread scheduling latency and returns to user-space. When the thread rereads the timerlat_fd, the tracer will print the user-ret(urn) latency, which is an additional metric. This additional metric is also traced by the tracer and can be used, for example of measuring the context switch overhead from kernel-to-user and user-to-kernel, or the response time for an arbitrary execution in user-space. The tracer supports one thread per CPU, the thread must be pinned to the CPU, and it cannot migrate while holding the timerlat_fd. The reason is that the tracer is per CPU (nothing prohibits the tracer from allowing migrations in the future). The tracer monitors the migration of the thread and disables the tracer if detected. The timerlat_fd is only available for opening/reading when timerlat tracer is enabled, and NO_OSNOISE_WORKLOAD is set. The simplest way to activate this feature from user-space is: -------------------------------- %< ----------------------------------- int main(void) { char buffer[1024]; int timerlat_fd; int retval; long cpu = 0; /* place in CPU 0 */ cpu_set_t set; CPU_ZERO(&set); CPU_SET(cpu, &set); if (sched_setaffinity(gettid(), sizeof(set), &set) == -1) return 1; snprintf(buffer, sizeof(buffer), "/sys/kernel/tracing/osnoise/per_cpu/cpu%ld/timerlat_fd", cpu); timerlat_fd = open(buffer, O_RDONLY); if (timerlat_fd < 0) { printf("error opening %s: %s\n", buffer, strerror(errno)); exit(1); } for (;;) { retval = read(timerlat_fd, buffer, 1024); if (retval < 0) break; } close(timerlat_fd); exit(0); } -------------------------------- >% ----------------------------------- When disabling timerlat, if there is a workload holding the timerlat_fd, the SIGKILL will be sent to the thread. Link: https://lkml.kernel.org/r/69fe66a863d2792ff4c3a149bf9e32e26468bb3a.1686063934.git.bristot@kernel.org Cc: Juri Lelli <juri.lelli@redhat.com> Cc: William White <chwhite@redhat.com> Cc: Daniel Bristot de Oliveira <bristot@kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-06-06 15:12:27 +00:00
static char *timerlat_lat_context[] = {"irq", "thread", "user-ret"};
trace: Add timerlat tracer The timerlat tracer aims to help the preemptive kernel developers to found souces of wakeup latencies of real-time threads. Like cyclictest, the tracer sets a periodic timer that wakes up a thread. The thread then computes a *wakeup latency* value as the difference between the *current time* and the *absolute time* that the timer was set to expire. The main goal of timerlat is tracing in such a way to help kernel developers. Usage Write the ASCII text "timerlat" into the current_tracer file of the tracing system (generally mounted at /sys/kernel/tracing). For example: [root@f32 ~]# cd /sys/kernel/tracing/ [root@f32 tracing]# echo timerlat > current_tracer It is possible to follow the trace by reading the trace trace file: [root@f32 tracing]# cat trace # tracer: timerlat # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # || / # |||| ACTIVATION # TASK-PID CPU# |||| TIMESTAMP ID CONTEXT LATENCY # | | | |||| | | | | <idle>-0 [000] d.h1 54.029328: #1 context irq timer_latency 932 ns <...>-867 [000] .... 54.029339: #1 context thread timer_latency 11700 ns <idle>-0 [001] dNh1 54.029346: #1 context irq timer_latency 2833 ns <...>-868 [001] .... 54.029353: #1 context thread timer_latency 9820 ns <idle>-0 [000] d.h1 54.030328: #2 context irq timer_latency 769 ns <...>-867 [000] .... 54.030330: #2 context thread timer_latency 3070 ns <idle>-0 [001] d.h1 54.030344: #2 context irq timer_latency 935 ns <...>-868 [001] .... 54.030347: #2 context thread timer_latency 4351 ns The tracer creates a per-cpu kernel thread with real-time priority that prints two lines at every activation. The first is the *timer latency* observed at the *hardirq* context before the activation of the thread. The second is the *timer latency* observed by the thread, which is the same level that cyclictest reports. The ACTIVATION ID field serves to relate the *irq* execution to its respective *thread* execution. The irq/thread splitting is important to clarify at which context the unexpected high value is coming from. The *irq* context can be delayed by hardware related actions, such as SMIs, NMIs, IRQs or by a thread masking interrupts. Once the timer happens, the delay can also be influenced by blocking caused by threads. For example, by postponing the scheduler execution via preempt_disable(), by the scheduler execution, or by masking interrupts. Threads can also be delayed by the interference from other threads and IRQs. The timerlat can also take advantage of the osnoise: traceevents. For example: [root@f32 ~]# cd /sys/kernel/tracing/ [root@f32 tracing]# echo timerlat > current_tracer [root@f32 tracing]# echo osnoise > set_event [root@f32 tracing]# echo 25 > osnoise/stop_tracing_total_us [root@f32 tracing]# tail -10 trace cc1-87882 [005] d..h... 548.771078: #402268 context irq timer_latency 1585 ns cc1-87882 [005] dNLh1.. 548.771082: irq_noise: local_timer:236 start 548.771077442 duration 4597 ns cc1-87882 [005] dNLh2.. 548.771083: irq_noise: reschedule:253 start 548.771083017 duration 56 ns cc1-87882 [005] dNLh2.. 548.771086: irq_noise: call_function_single:251 start 548.771083811 duration 2048 ns cc1-87882 [005] dNLh2.. 548.771088: irq_noise: call_function_single:251 start 548.771086814 duration 1495 ns cc1-87882 [005] dNLh2.. 548.771091: irq_noise: call_function_single:251 start 548.771089194 duration 1558 ns cc1-87882 [005] dNLh2.. 548.771094: irq_noise: call_function_single:251 start 548.771091719 duration 1932 ns cc1-87882 [005] dNLh2.. 548.771096: irq_noise: call_function_single:251 start 548.771094696 duration 1050 ns cc1-87882 [005] d...3.. 548.771101: thread_noise: cc1:87882 start 548.771078243 duration 10909 ns timerlat/5-1035 [005] ....... 548.771103: #402268 context thread timer_latency 25960 ns For further information see: Documentation/trace/timerlat-tracer.rst Link: https://lkml.kernel.org/r/71f18efc013e1194bcaea1e54db957de2b19ba62.1624372313.git.bristot@redhat.com Cc: Phil Auld <pauld@redhat.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Kate Carcia <kcarcia@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Alexandre Chartre <alexandre.chartre@oracle.com> Cc: Clark Willaims <williams@redhat.com> Cc: John Kacur <jkacur@redhat.com> Cc: Juri Lelli <juri.lelli@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2021-06-22 14:42:28 +00:00
static enum print_line_t
trace_timerlat_print(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct trace_entry *entry = iter->ent;
struct trace_seq *s = &iter->seq;
struct timerlat_entry *field;
trace_assign_type(field, entry);
trace_seq_printf(s, "#%-5u context %6s timer_latency %9llu ns\n",
field->seqnum,
tracing/timerlat: Add user-space interface Going a step further, we propose a way to use any user-space workload as the task waiting for the timerlat timer. This is done via a per-CPU file named osnoise/cpu$id/timerlat_fd file. The tracef_fd allows a task to open at a time. When a task reads the file, the timerlat timer is armed for future osnoise/timerlat_period_us time. When the timer fires, it prints the IRQ latency and wakes up the user-space thread waiting in the timerlat_fd. The thread then starts to run, executes the timerlat measurement, prints the thread scheduling latency and returns to user-space. When the thread rereads the timerlat_fd, the tracer will print the user-ret(urn) latency, which is an additional metric. This additional metric is also traced by the tracer and can be used, for example of measuring the context switch overhead from kernel-to-user and user-to-kernel, or the response time for an arbitrary execution in user-space. The tracer supports one thread per CPU, the thread must be pinned to the CPU, and it cannot migrate while holding the timerlat_fd. The reason is that the tracer is per CPU (nothing prohibits the tracer from allowing migrations in the future). The tracer monitors the migration of the thread and disables the tracer if detected. The timerlat_fd is only available for opening/reading when timerlat tracer is enabled, and NO_OSNOISE_WORKLOAD is set. The simplest way to activate this feature from user-space is: -------------------------------- %< ----------------------------------- int main(void) { char buffer[1024]; int timerlat_fd; int retval; long cpu = 0; /* place in CPU 0 */ cpu_set_t set; CPU_ZERO(&set); CPU_SET(cpu, &set); if (sched_setaffinity(gettid(), sizeof(set), &set) == -1) return 1; snprintf(buffer, sizeof(buffer), "/sys/kernel/tracing/osnoise/per_cpu/cpu%ld/timerlat_fd", cpu); timerlat_fd = open(buffer, O_RDONLY); if (timerlat_fd < 0) { printf("error opening %s: %s\n", buffer, strerror(errno)); exit(1); } for (;;) { retval = read(timerlat_fd, buffer, 1024); if (retval < 0) break; } close(timerlat_fd); exit(0); } -------------------------------- >% ----------------------------------- When disabling timerlat, if there is a workload holding the timerlat_fd, the SIGKILL will be sent to the thread. Link: https://lkml.kernel.org/r/69fe66a863d2792ff4c3a149bf9e32e26468bb3a.1686063934.git.bristot@kernel.org Cc: Juri Lelli <juri.lelli@redhat.com> Cc: William White <chwhite@redhat.com> Cc: Daniel Bristot de Oliveira <bristot@kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-06-06 15:12:27 +00:00
timerlat_lat_context[field->context],
trace: Add timerlat tracer The timerlat tracer aims to help the preemptive kernel developers to found souces of wakeup latencies of real-time threads. Like cyclictest, the tracer sets a periodic timer that wakes up a thread. The thread then computes a *wakeup latency* value as the difference between the *current time* and the *absolute time* that the timer was set to expire. The main goal of timerlat is tracing in such a way to help kernel developers. Usage Write the ASCII text "timerlat" into the current_tracer file of the tracing system (generally mounted at /sys/kernel/tracing). For example: [root@f32 ~]# cd /sys/kernel/tracing/ [root@f32 tracing]# echo timerlat > current_tracer It is possible to follow the trace by reading the trace trace file: [root@f32 tracing]# cat trace # tracer: timerlat # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # || / # |||| ACTIVATION # TASK-PID CPU# |||| TIMESTAMP ID CONTEXT LATENCY # | | | |||| | | | | <idle>-0 [000] d.h1 54.029328: #1 context irq timer_latency 932 ns <...>-867 [000] .... 54.029339: #1 context thread timer_latency 11700 ns <idle>-0 [001] dNh1 54.029346: #1 context irq timer_latency 2833 ns <...>-868 [001] .... 54.029353: #1 context thread timer_latency 9820 ns <idle>-0 [000] d.h1 54.030328: #2 context irq timer_latency 769 ns <...>-867 [000] .... 54.030330: #2 context thread timer_latency 3070 ns <idle>-0 [001] d.h1 54.030344: #2 context irq timer_latency 935 ns <...>-868 [001] .... 54.030347: #2 context thread timer_latency 4351 ns The tracer creates a per-cpu kernel thread with real-time priority that prints two lines at every activation. The first is the *timer latency* observed at the *hardirq* context before the activation of the thread. The second is the *timer latency* observed by the thread, which is the same level that cyclictest reports. The ACTIVATION ID field serves to relate the *irq* execution to its respective *thread* execution. The irq/thread splitting is important to clarify at which context the unexpected high value is coming from. The *irq* context can be delayed by hardware related actions, such as SMIs, NMIs, IRQs or by a thread masking interrupts. Once the timer happens, the delay can also be influenced by blocking caused by threads. For example, by postponing the scheduler execution via preempt_disable(), by the scheduler execution, or by masking interrupts. Threads can also be delayed by the interference from other threads and IRQs. The timerlat can also take advantage of the osnoise: traceevents. For example: [root@f32 ~]# cd /sys/kernel/tracing/ [root@f32 tracing]# echo timerlat > current_tracer [root@f32 tracing]# echo osnoise > set_event [root@f32 tracing]# echo 25 > osnoise/stop_tracing_total_us [root@f32 tracing]# tail -10 trace cc1-87882 [005] d..h... 548.771078: #402268 context irq timer_latency 1585 ns cc1-87882 [005] dNLh1.. 548.771082: irq_noise: local_timer:236 start 548.771077442 duration 4597 ns cc1-87882 [005] dNLh2.. 548.771083: irq_noise: reschedule:253 start 548.771083017 duration 56 ns cc1-87882 [005] dNLh2.. 548.771086: irq_noise: call_function_single:251 start 548.771083811 duration 2048 ns cc1-87882 [005] dNLh2.. 548.771088: irq_noise: call_function_single:251 start 548.771086814 duration 1495 ns cc1-87882 [005] dNLh2.. 548.771091: irq_noise: call_function_single:251 start 548.771089194 duration 1558 ns cc1-87882 [005] dNLh2.. 548.771094: irq_noise: call_function_single:251 start 548.771091719 duration 1932 ns cc1-87882 [005] dNLh2.. 548.771096: irq_noise: call_function_single:251 start 548.771094696 duration 1050 ns cc1-87882 [005] d...3.. 548.771101: thread_noise: cc1:87882 start 548.771078243 duration 10909 ns timerlat/5-1035 [005] ....... 548.771103: #402268 context thread timer_latency 25960 ns For further information see: Documentation/trace/timerlat-tracer.rst Link: https://lkml.kernel.org/r/71f18efc013e1194bcaea1e54db957de2b19ba62.1624372313.git.bristot@redhat.com Cc: Phil Auld <pauld@redhat.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Kate Carcia <kcarcia@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Alexandre Chartre <alexandre.chartre@oracle.com> Cc: Clark Willaims <williams@redhat.com> Cc: John Kacur <jkacur@redhat.com> Cc: Juri Lelli <juri.lelli@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2021-06-22 14:42:28 +00:00
field->timer_latency);
return trace_handle_return(s);
}
static enum print_line_t
trace_timerlat_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct timerlat_entry *field;
struct trace_seq *s = &iter->seq;
trace_assign_type(field, iter->ent);
trace_seq_printf(s, "%u %d %llu\n",
field->seqnum,
field->context,
field->timer_latency);
return trace_handle_return(s);
}
static struct trace_event_functions trace_timerlat_funcs = {
.trace = trace_timerlat_print,
.raw = trace_timerlat_raw,
};
static struct trace_event trace_timerlat_event = {
.type = TRACE_TIMERLAT,
.funcs = &trace_timerlat_funcs,
};
/* TRACE_BPUTS */
static enum print_line_t
trace_bputs_print(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct trace_entry *entry = iter->ent;
struct trace_seq *s = &iter->seq;
struct bputs_entry *field;
trace_assign_type(field, entry);
seq_print_ip_sym(s, field->ip, flags);
trace_seq_puts(s, ": ");
trace_seq_puts(s, field->str);
return trace_handle_return(s);
}
static enum print_line_t
trace_bputs_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct bputs_entry *field;
struct trace_seq *s = &iter->seq;
trace_assign_type(field, iter->ent);
trace_seq_printf(s, ": %lx : ", field->ip);
trace_seq_puts(s, field->str);
return trace_handle_return(s);
}
static struct trace_event_functions trace_bputs_funcs = {
.trace = trace_bputs_print,
.raw = trace_bputs_raw,
};
static struct trace_event trace_bputs_event = {
.type = TRACE_BPUTS,
.funcs = &trace_bputs_funcs,
};
/* TRACE_BPRINT */
static enum print_line_t
trace_bprint_print(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct trace_entry *entry = iter->ent;
struct trace_seq *s = &iter->seq;
struct bprint_entry *field;
trace_assign_type(field, entry);
seq_print_ip_sym(s, field->ip, flags);
trace_seq_puts(s, ": ");
trace_seq_bprintf(s, field->fmt, field->buf);
return trace_handle_return(s);
}
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-06 16:21:49 +00:00
static enum print_line_t
trace_bprint_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct bprint_entry *field;
struct trace_seq *s = &iter->seq;
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-06 16:21:49 +00:00
trace_assign_type(field, iter->ent);
trace_seq_printf(s, ": %lx : ", field->ip);
trace_seq_bprintf(s, field->fmt, field->buf);
return trace_handle_return(s);
}
static struct trace_event_functions trace_bprint_funcs = {
.trace = trace_bprint_print,
.raw = trace_bprint_raw,
};
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-06 16:21:49 +00:00
static struct trace_event trace_bprint_event = {
.type = TRACE_BPRINT,
.funcs = &trace_bprint_funcs,
};
/* TRACE_PRINT */
static enum print_line_t trace_print_print(struct trace_iterator *iter,
int flags, struct trace_event *event)
{
struct print_entry *field;
struct trace_seq *s = &iter->seq;
tracing: Have trace_printk not use binary prints if boot buffer If the persistent boot mapped ring buffer is used for trace_printk(), force it to not use the binary versions. trace_printk() by default uses bin_printf() that only saves the pointer to the format and not the format itself inside the ring buffer. But for a persistent buffer that is read after reboot, the pointers to the format strings may not be the same, or worse, not even exist! Instead, just force the more robust, but slower, version that does the formatting before saving into the ring buffer. The boot mapped buffer can now be used for trace_printk and friends! Using the trace_printk() and the persistent buffer was used to debug the issue with the osnoise tracer: Link: https://lore.kernel.org/all/20240822103443.6a6ae051@gandalf.local.home/ Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Vincent Donnefort <vdonnefort@google.com> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vineeth Pillai <vineeth@bitbyteword.org> Cc: Beau Belgrave <beaub@linux.microsoft.com> Cc: Alexander Graf <graf@amazon.com> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: David Howells <dhowells@redhat.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Ross Zwisler <zwisler@google.com> Cc: Kees Cook <keescook@chromium.org> Cc: Alexander Aring <aahringo@redhat.com> Cc: "Luis Claudio R. Goncalves" <lgoncalv@redhat.com> Cc: Tomas Glozar <tglozar@redhat.com> Cc: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: "Jonathan Corbet" <corbet@lwn.net> Link: https://lore.kernel.org/20240823014019.386925800@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-08-23 01:39:05 +00:00
unsigned long ip;
trace_assign_type(field, iter->ent);
tracing: Have trace_printk not use binary prints if boot buffer If the persistent boot mapped ring buffer is used for trace_printk(), force it to not use the binary versions. trace_printk() by default uses bin_printf() that only saves the pointer to the format and not the format itself inside the ring buffer. But for a persistent buffer that is read after reboot, the pointers to the format strings may not be the same, or worse, not even exist! Instead, just force the more robust, but slower, version that does the formatting before saving into the ring buffer. The boot mapped buffer can now be used for trace_printk and friends! Using the trace_printk() and the persistent buffer was used to debug the issue with the osnoise tracer: Link: https://lore.kernel.org/all/20240822103443.6a6ae051@gandalf.local.home/ Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Vincent Donnefort <vdonnefort@google.com> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vineeth Pillai <vineeth@bitbyteword.org> Cc: Beau Belgrave <beaub@linux.microsoft.com> Cc: Alexander Graf <graf@amazon.com> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: David Howells <dhowells@redhat.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Ross Zwisler <zwisler@google.com> Cc: Kees Cook <keescook@chromium.org> Cc: Alexander Aring <aahringo@redhat.com> Cc: "Luis Claudio R. Goncalves" <lgoncalv@redhat.com> Cc: Tomas Glozar <tglozar@redhat.com> Cc: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: "Jonathan Corbet" <corbet@lwn.net> Link: https://lore.kernel.org/20240823014019.386925800@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-08-23 01:39:05 +00:00
ip = field->ip + iter->tr->text_delta;
seq_print_ip_sym(s, ip, flags);
trace_seq_printf(s, ": %s", field->buf);
return trace_handle_return(s);
}
static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct print_entry *field;
trace_assign_type(field, iter->ent);
trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf);
return trace_handle_return(&iter->seq);
}
static struct trace_event_functions trace_print_funcs = {
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-06 16:21:49 +00:00
.trace = trace_print_print,
.raw = trace_print_raw,
};
static struct trace_event trace_print_event = {
.type = TRACE_PRINT,
.funcs = &trace_print_funcs,
};
static enum print_line_t trace_raw_data(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct raw_data_entry *field;
int i;
trace_assign_type(field, iter->ent);
trace_seq_printf(&iter->seq, "# %x buf:", field->id);
for (i = 0; i < iter->ent_size - offsetof(struct raw_data_entry, buf); i++)
trace_seq_printf(&iter->seq, " %02x",
(unsigned char)field->buf[i]);
trace_seq_putc(&iter->seq, '\n');
return trace_handle_return(&iter->seq);
}
static struct trace_event_functions trace_raw_data_funcs = {
.trace = trace_raw_data,
.raw = trace_raw_data,
};
static struct trace_event trace_raw_data_event = {
.type = TRACE_RAW_DATA,
.funcs = &trace_raw_data_funcs,
};
static enum print_line_t
trace_func_repeats_raw(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct func_repeats_entry *field;
struct trace_seq *s = &iter->seq;
trace_assign_type(field, iter->ent);
trace_seq_printf(s, "%lu %lu %u %llu\n",
field->ip,
field->parent_ip,
field->count,
FUNC_REPEATS_GET_DELTA_TS(field));
return trace_handle_return(s);
}
static enum print_line_t
trace_func_repeats_print(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
struct func_repeats_entry *field;
struct trace_seq *s = &iter->seq;
trace_assign_type(field, iter->ent);
tracing: Update function tracing output for previous boot buffer For a persistent ring buffer that is saved across boots, if function tracing was performed in the previous boot, it only saves the address of the functions and uses "%pS" to print their names. But the current boot, those functions may be in different locations. The persistent meta-data saves the text delta between the two boots and can be used to find the address of the saved function of where it is located in the current boot. Link: https://lkml.kernel.org/r/20240612232026.988226055@goodmis.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Vincent Donnefort <vdonnefort@google.com> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vineeth Pillai <vineeth@bitbyteword.org> Cc: Youssef Esmat <youssefesmat@google.com> Cc: Beau Belgrave <beaub@linux.microsoft.com> Cc: Alexander Graf <graf@amazon.com> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: David Howells <dhowells@redhat.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Ross Zwisler <zwisler@google.com> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2024-06-12 23:19:46 +00:00
print_fn_trace(s, field->ip, field->parent_ip, iter->tr->text_delta, flags);
trace_seq_printf(s, " (repeats: %u, last_ts:", field->count);
trace_print_time(s, iter,
iter->ts - FUNC_REPEATS_GET_DELTA_TS(field));
trace_seq_puts(s, ")\n");
return trace_handle_return(s);
}
static struct trace_event_functions trace_func_repeats_funcs = {
.trace = trace_func_repeats_print,
.raw = trace_func_repeats_raw,
};
static struct trace_event trace_func_repeats_event = {
.type = TRACE_FUNC_REPEATS,
.funcs = &trace_func_repeats_funcs,
};
static struct trace_event *events[] __initdata = {
&trace_fn_event,
&trace_ctx_event,
&trace_wake_event,
&trace_stack_event,
&trace_user_stack_event,
&trace_bputs_event,
&trace_bprint_event,
&trace_print_event,
&trace_hwlat_event,
trace: Add osnoise tracer In the context of high-performance computing (HPC), the Operating System Noise (*osnoise*) refers to the interference experienced by an application due to activities inside the operating system. In the context of Linux, NMIs, IRQs, SoftIRQs, and any other system thread can cause noise to the system. Moreover, hardware-related jobs can also cause noise, for example, via SMIs. The osnoise tracer leverages the hwlat_detector by running a similar loop with preemption, SoftIRQs and IRQs enabled, thus allowing all the sources of *osnoise* during its execution. Using the same approach of hwlat, osnoise takes note of the entry and exit point of any source of interferences, increasing a per-cpu interference counter. The osnoise tracer also saves an interference counter for each source of interference. The interference counter for NMI, IRQs, SoftIRQs, and threads is increased anytime the tool observes these interferences' entry events. When a noise happens without any interference from the operating system level, the hardware noise counter increases, pointing to a hardware-related noise. In this way, osnoise can account for any source of interference. At the end of the period, the osnoise tracer prints the sum of all noise, the max single noise, the percentage of CPU available for the thread, and the counters for the noise sources. Usage Write the ASCII text "osnoise" into the current_tracer file of the tracing system (generally mounted at /sys/kernel/tracing). For example:: [root@f32 ~]# cd /sys/kernel/tracing/ [root@f32 tracing]# echo osnoise > current_tracer It is possible to follow the trace by reading the trace trace file:: [root@f32 tracing]# cat trace # tracer: osnoise # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth MAX # || / SINGLE Interference counters: # |||| RUNTIME NOISE % OF CPU NOISE +-----------------------------+ # TASK-PID CPU# |||| TIMESTAMP IN US IN US AVAILABLE IN US HW NMI IRQ SIRQ THREAD # | | | |||| | | | | | | | | | | <...>-859 [000] .... 81.637220: 1000000 190 99.98100 9 18 0 1007 18 1 <...>-860 [001] .... 81.638154: 1000000 656 99.93440 74 23 0 1006 16 3 <...>-861 [002] .... 81.638193: 1000000 5675 99.43250 202 6 0 1013 25 21 <...>-862 [003] .... 81.638242: 1000000 125 99.98750 45 1 0 1011 23 0 <...>-863 [004] .... 81.638260: 1000000 1721 99.82790 168 7 0 1002 49 41 <...>-864 [005] .... 81.638286: 1000000 263 99.97370 57 6 0 1006 26 2 <...>-865 [006] .... 81.638302: 1000000 109 99.98910 21 3 0 1006 18 1 <...>-866 [007] .... 81.638326: 1000000 7816 99.21840 107 8 0 1016 39 19 In addition to the regular trace fields (from TASK-PID to TIMESTAMP), the tracer prints a message at the end of each period for each CPU that is running an osnoise/CPU thread. The osnoise specific fields report: - The RUNTIME IN USE reports the amount of time in microseconds that the osnoise thread kept looping reading the time. - The NOISE IN US reports the sum of noise in microseconds observed by the osnoise tracer during the associated runtime. - The % OF CPU AVAILABLE reports the percentage of CPU available for the osnoise thread during the runtime window. - The MAX SINGLE NOISE IN US reports the maximum single noise observed during the runtime window. - The Interference counters display how many each of the respective interference happened during the runtime window. Note that the example above shows a high number of HW noise samples. The reason being is that this sample was taken on a virtual machine, and the host interference is detected as a hardware interference. Tracer options The tracer has a set of options inside the osnoise directory, they are: - osnoise/cpus: CPUs at which a osnoise thread will execute. - osnoise/period_us: the period of the osnoise thread. - osnoise/runtime_us: how long an osnoise thread will look for noise. - osnoise/stop_tracing_us: stop the system tracing if a single noise higher than the configured value happens. Writing 0 disables this option. - osnoise/stop_tracing_total_us: stop the system tracing if total noise higher than the configured value happens. Writing 0 disables this option. - tracing_threshold: the minimum delta between two time() reads to be considered as noise, in us. When set to 0, the default value will be used, which is currently 5 us. Additional Tracing In addition to the tracer, a set of tracepoints were added to facilitate the identification of the osnoise source. - osnoise:sample_threshold: printed anytime a noise is higher than the configurable tolerance_ns. - osnoise:nmi_noise: noise from NMI, including the duration. - osnoise:irq_noise: noise from an IRQ, including the duration. - osnoise:softirq_noise: noise from a SoftIRQ, including the duration. - osnoise:thread_noise: noise from a thread, including the duration. Note that all the values are *net values*. For example, if while osnoise is running, another thread preempts the osnoise thread, it will start a thread_noise duration at the start. Then, an IRQ takes place, preempting the thread_noise, starting a irq_noise. When the IRQ ends its execution, it will compute its duration, and this duration will be subtracted from the thread_noise, in such a way as to avoid the double accounting of the IRQ execution. This logic is valid for all sources of noise. Here is one example of the usage of these tracepoints:: osnoise/8-961 [008] d.h. 5789.857532: irq_noise: local_timer:236 start 5789.857529929 duration 1845 ns osnoise/8-961 [008] dNh. 5789.858408: irq_noise: local_timer:236 start 5789.858404871 duration 2848 ns migration/8-54 [008] d... 5789.858413: thread_noise: migration/8:54 start 5789.858409300 duration 3068 ns osnoise/8-961 [008] .... 5789.858413: sample_threshold: start 5789.858404555 duration 8723 ns interferences 2 In this example, a noise sample of 8 microseconds was reported in the last line, pointing to two interferences. Looking backward in the trace, the two previous entries were about the migration thread running after a timer IRQ execution. The first event is not part of the noise because it took place one millisecond before. It is worth noticing that the sum of the duration reported in the tracepoints is smaller than eight us reported in the sample_threshold. The reason roots in the overhead of the entry and exit code that happens before and after any interference execution. This justifies the dual approach: measuring thread and tracing. Link: https://lkml.kernel.org/r/e649467042d60e7b62714c9c6751a56299d15119.1624372313.git.bristot@redhat.com Cc: Phil Auld <pauld@redhat.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Kate Carcia <kcarcia@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Alexandre Chartre <alexandre.chartre@oracle.com> Cc: Clark Willaims <williams@redhat.com> Cc: John Kacur <jkacur@redhat.com> Cc: Juri Lelli <juri.lelli@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> [ Made the following functions static: trace_irqentry_callback() trace_irqexit_callback() trace_intel_irqentry_callback() trace_intel_irqexit_callback() Added to include/trace.h: osnoise_arch_register() osnoise_arch_unregister() Fixed define logic for LATENCY_FS_NOTIFY Reported-by: kernel test robot <lkp@intel.com> ] Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2021-06-22 14:42:27 +00:00
&trace_osnoise_event,
trace: Add timerlat tracer The timerlat tracer aims to help the preemptive kernel developers to found souces of wakeup latencies of real-time threads. Like cyclictest, the tracer sets a periodic timer that wakes up a thread. The thread then computes a *wakeup latency* value as the difference between the *current time* and the *absolute time* that the timer was set to expire. The main goal of timerlat is tracing in such a way to help kernel developers. Usage Write the ASCII text "timerlat" into the current_tracer file of the tracing system (generally mounted at /sys/kernel/tracing). For example: [root@f32 ~]# cd /sys/kernel/tracing/ [root@f32 tracing]# echo timerlat > current_tracer It is possible to follow the trace by reading the trace trace file: [root@f32 tracing]# cat trace # tracer: timerlat # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # || / # |||| ACTIVATION # TASK-PID CPU# |||| TIMESTAMP ID CONTEXT LATENCY # | | | |||| | | | | <idle>-0 [000] d.h1 54.029328: #1 context irq timer_latency 932 ns <...>-867 [000] .... 54.029339: #1 context thread timer_latency 11700 ns <idle>-0 [001] dNh1 54.029346: #1 context irq timer_latency 2833 ns <...>-868 [001] .... 54.029353: #1 context thread timer_latency 9820 ns <idle>-0 [000] d.h1 54.030328: #2 context irq timer_latency 769 ns <...>-867 [000] .... 54.030330: #2 context thread timer_latency 3070 ns <idle>-0 [001] d.h1 54.030344: #2 context irq timer_latency 935 ns <...>-868 [001] .... 54.030347: #2 context thread timer_latency 4351 ns The tracer creates a per-cpu kernel thread with real-time priority that prints two lines at every activation. The first is the *timer latency* observed at the *hardirq* context before the activation of the thread. The second is the *timer latency* observed by the thread, which is the same level that cyclictest reports. The ACTIVATION ID field serves to relate the *irq* execution to its respective *thread* execution. The irq/thread splitting is important to clarify at which context the unexpected high value is coming from. The *irq* context can be delayed by hardware related actions, such as SMIs, NMIs, IRQs or by a thread masking interrupts. Once the timer happens, the delay can also be influenced by blocking caused by threads. For example, by postponing the scheduler execution via preempt_disable(), by the scheduler execution, or by masking interrupts. Threads can also be delayed by the interference from other threads and IRQs. The timerlat can also take advantage of the osnoise: traceevents. For example: [root@f32 ~]# cd /sys/kernel/tracing/ [root@f32 tracing]# echo timerlat > current_tracer [root@f32 tracing]# echo osnoise > set_event [root@f32 tracing]# echo 25 > osnoise/stop_tracing_total_us [root@f32 tracing]# tail -10 trace cc1-87882 [005] d..h... 548.771078: #402268 context irq timer_latency 1585 ns cc1-87882 [005] dNLh1.. 548.771082: irq_noise: local_timer:236 start 548.771077442 duration 4597 ns cc1-87882 [005] dNLh2.. 548.771083: irq_noise: reschedule:253 start 548.771083017 duration 56 ns cc1-87882 [005] dNLh2.. 548.771086: irq_noise: call_function_single:251 start 548.771083811 duration 2048 ns cc1-87882 [005] dNLh2.. 548.771088: irq_noise: call_function_single:251 start 548.771086814 duration 1495 ns cc1-87882 [005] dNLh2.. 548.771091: irq_noise: call_function_single:251 start 548.771089194 duration 1558 ns cc1-87882 [005] dNLh2.. 548.771094: irq_noise: call_function_single:251 start 548.771091719 duration 1932 ns cc1-87882 [005] dNLh2.. 548.771096: irq_noise: call_function_single:251 start 548.771094696 duration 1050 ns cc1-87882 [005] d...3.. 548.771101: thread_noise: cc1:87882 start 548.771078243 duration 10909 ns timerlat/5-1035 [005] ....... 548.771103: #402268 context thread timer_latency 25960 ns For further information see: Documentation/trace/timerlat-tracer.rst Link: https://lkml.kernel.org/r/71f18efc013e1194bcaea1e54db957de2b19ba62.1624372313.git.bristot@redhat.com Cc: Phil Auld <pauld@redhat.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Kate Carcia <kcarcia@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Alexandre Chartre <alexandre.chartre@oracle.com> Cc: Clark Willaims <williams@redhat.com> Cc: John Kacur <jkacur@redhat.com> Cc: Juri Lelli <juri.lelli@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2021-06-22 14:42:28 +00:00
&trace_timerlat_event,
&trace_raw_data_event,
&trace_func_repeats_event,
NULL
};
__init int init_events(void)
{
struct trace_event *event;
int i, ret;
for (i = 0; events[i]; i++) {
event = events[i];
ret = register_trace_event(event);
WARN_ONCE(!ret, "event %d failed to register", event->type);
}
return 0;
}