linux-hardened/include/linux/trace_seq.h

118 lines
2.9 KiB
C
Raw Normal View History

#ifndef _LINUX_TRACE_SEQ_H
#define _LINUX_TRACE_SEQ_H
#include <linux/fs.h>
#include <asm/page.h>
/*
* Trace sequences are used to allow a function to call several other functions
* to create a string of data to use (up to a max of PAGE_SIZE).
*/
struct trace_seq {
unsigned char buffer[PAGE_SIZE];
unsigned int len;
unsigned int readpos;
int full;
};
static inline void
trace_seq_init(struct trace_seq *s)
{
s->len = 0;
s->readpos = 0;
s->full = 0;
}
/**
* trace_seq_buffer_ptr - return pointer to next location in buffer
* @s: trace sequence descriptor
*
* Returns the pointer to the buffer where the next write to
* the buffer will happen. This is useful to save the location
* that is about to be written to and then return the result
* of that write.
*/
static inline unsigned char *
trace_seq_buffer_ptr(struct trace_seq *s)
{
return s->buffer + s->len;
}
/*
* Currently only defined when tracing is enabled.
*/
#ifdef CONFIG_TRACING
extern __printf(2, 3)
int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
extern __printf(2, 0)
int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args);
extern int
trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
tracing: Buffer the output of seq_file in case of filled buffer If the seq_read fills the buffer it will call s_start again on the next itertation with the same position. This causes a problem with the function_graph tracer because it consumes the iteration in order to determine leaf functions. What happens is that the iterator stores the entry, and the function graph plugin will look at the next entry. If that next entry is a return of the same function and task, then the function is a leaf and the function_graph plugin calls ring_buffer_read which moves the ring buffer iterator forward (the trace iterator still points to the function start entry). The copying of the trace_seq to the seq_file buffer will fail if the seq_file buffer is full. The seq_read will not show this entry. The next read by userspace will cause seq_read to again call s_start which will reuse the trace iterator entry (the function start entry). But the function return entry was already consumed. The function graph plugin will think that this entry is a nested function and not a leaf. To solve this, the trace code now checks the return status of the seq_printf (trace_print_seq). If the writing to the seq_file buffer fails, we set a flag in the iterator (leftover) and we do not reset the trace_seq buffer. On the next call to s_start, we check the leftover flag, and if it is set, we just reuse the trace_seq buffer and do not call into the plugin print functions. Before this patch: 2) | fput() { 2) | __fput() { 2) 0.550 us | inotify_inode_queue_event(); 2) | __fsnotify_parent() { 2) 0.540 us | inotify_dentry_parent_queue_event(); After the patch: 2) | fput() { 2) | __fput() { 2) 0.550 us | inotify_inode_queue_event(); 2) 0.548 us | __fsnotify_parent(); 2) 0.540 us | inotify_dentry_parent_queue_event(); [ Updated the patch to fix a missing return 0 from the trace_print_seq() stub when CONFIG_TRACING is disabled. Reported-by: Ingo Molnar <mingo@elte.hu> ] Reported-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-12-07 15:11:39 +01:00
extern int trace_print_seq(struct seq_file *m, struct trace_seq *s);
extern int trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
int cnt);
extern int trace_seq_puts(struct trace_seq *s, const char *str);
extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
extern int trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len);
extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
unsigned int len);
extern int trace_seq_path(struct trace_seq *s, const struct path *path);
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 19:10:24 +02:00
extern int trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
int nmaskbits);
#else /* CONFIG_TRACING */
static inline int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
{
return 0;
}
static inline int
trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
{
return 0;
}
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 19:10:24 +02:00
static inline int
trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
int nmaskbits)
{
return 0;
}
tracing: Buffer the output of seq_file in case of filled buffer If the seq_read fills the buffer it will call s_start again on the next itertation with the same position. This causes a problem with the function_graph tracer because it consumes the iteration in order to determine leaf functions. What happens is that the iterator stores the entry, and the function graph plugin will look at the next entry. If that next entry is a return of the same function and task, then the function is a leaf and the function_graph plugin calls ring_buffer_read which moves the ring buffer iterator forward (the trace iterator still points to the function start entry). The copying of the trace_seq to the seq_file buffer will fail if the seq_file buffer is full. The seq_read will not show this entry. The next read by userspace will cause seq_read to again call s_start which will reuse the trace iterator entry (the function start entry). But the function return entry was already consumed. The function graph plugin will think that this entry is a nested function and not a leaf. To solve this, the trace code now checks the return status of the seq_printf (trace_print_seq). If the writing to the seq_file buffer fails, we set a flag in the iterator (leftover) and we do not reset the trace_seq buffer. On the next call to s_start, we check the leftover flag, and if it is set, we just reuse the trace_seq buffer and do not call into the plugin print functions. Before this patch: 2) | fput() { 2) | __fput() { 2) 0.550 us | inotify_inode_queue_event(); 2) | __fsnotify_parent() { 2) 0.540 us | inotify_dentry_parent_queue_event(); After the patch: 2) | fput() { 2) | __fput() { 2) 0.550 us | inotify_inode_queue_event(); 2) 0.548 us | __fsnotify_parent(); 2) 0.540 us | inotify_dentry_parent_queue_event(); [ Updated the patch to fix a missing return 0 from the trace_print_seq() stub when CONFIG_TRACING is disabled. Reported-by: Ingo Molnar <mingo@elte.hu> ] Reported-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-12-07 15:11:39 +01:00
static inline int trace_print_seq(struct seq_file *m, struct trace_seq *s)
{
tracing: Buffer the output of seq_file in case of filled buffer If the seq_read fills the buffer it will call s_start again on the next itertation with the same position. This causes a problem with the function_graph tracer because it consumes the iteration in order to determine leaf functions. What happens is that the iterator stores the entry, and the function graph plugin will look at the next entry. If that next entry is a return of the same function and task, then the function is a leaf and the function_graph plugin calls ring_buffer_read which moves the ring buffer iterator forward (the trace iterator still points to the function start entry). The copying of the trace_seq to the seq_file buffer will fail if the seq_file buffer is full. The seq_read will not show this entry. The next read by userspace will cause seq_read to again call s_start which will reuse the trace iterator entry (the function start entry). But the function return entry was already consumed. The function graph plugin will think that this entry is a nested function and not a leaf. To solve this, the trace code now checks the return status of the seq_printf (trace_print_seq). If the writing to the seq_file buffer fails, we set a flag in the iterator (leftover) and we do not reset the trace_seq buffer. On the next call to s_start, we check the leftover flag, and if it is set, we just reuse the trace_seq buffer and do not call into the plugin print functions. Before this patch: 2) | fput() { 2) | __fput() { 2) 0.550 us | inotify_inode_queue_event(); 2) | __fsnotify_parent() { 2) 0.540 us | inotify_dentry_parent_queue_event(); After the patch: 2) | fput() { 2) | __fput() { 2) 0.550 us | inotify_inode_queue_event(); 2) 0.548 us | __fsnotify_parent(); 2) 0.540 us | inotify_dentry_parent_queue_event(); [ Updated the patch to fix a missing return 0 from the trace_print_seq() stub when CONFIG_TRACING is disabled. Reported-by: Ingo Molnar <mingo@elte.hu> ] Reported-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-12-07 15:11:39 +01:00
return 0;
}
static inline int trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
int cnt)
{
return 0;
}
static inline int trace_seq_puts(struct trace_seq *s, const char *str)
{
return 0;
}
static inline int trace_seq_putc(struct trace_seq *s, unsigned char c)
{
return 0;
}
static inline int
trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len)
{
return 0;
}
static inline int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
unsigned int len)
{
return 0;
}
static inline int trace_seq_path(struct trace_seq *s, const struct path *path)
{
return 0;
}
#endif /* CONFIG_TRACING */
#endif /* _LINUX_TRACE_SEQ_H */