Skip to contentSkip to conversation

tracing: Updates for 4.3

GIT PULL Steven Rostedt 1 participant 1 message Sep 4, 2015

Subsystems (9)
Documentation x86 PowerPC Tracing +5 more subsystems
lore
Share & tools
lore

Steven Rostedt

author maintainer
#0 lore raw

Linus,

Mostly this is just clean ups and micro optimizations.

The changes with more meat are:

o Allowing the trace event filters to filter on CPU number and process ids

o Two new markers for trace output latency were added

    (10 and 100 msec latencies)

o Have tracing_thresh filter function profiling time

I also worked on modifying the ring buffer code for some future work, and moved the adding of the timestamp around. One of my changes caused a regression, and since other changes were built on top of it and already tested, I had to operate a revert of that change. Instead of rebasing, this change set has the code that caused a regression as well as the code to revert that change without touching the other changes that were made on top of it.

Please pull the latest trace-v4.3 tree, which can be found at:

git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
trace-v4.3

Tag SHA1: 55d8a4ef18a4afd78ab84536576c785b5712adfe Head SHA1: b7dc42fd79390c074e2bff3b172b585d5c2d80c2

Daniel Wagner (1):
tracing: Allow triggers to filter for CPU ids and process names

Gil Fruchter (2):
tracing: Prefer kcalloc over kzalloc with multiply
tracing: Fix for non-continuous cpu ids

Jungseok Lee (1):
tracing: Introduce two additional marks for delay

Minfei Huang (1):
ftrace: Format MCOUNT_ADDR address as type unsigned long

Sasha Levin (1):
tracing: Don't make assumptions about length of string on task rename

Steven Rostedt (Red Hat) (8):
ring-buffer: Add event descriptor to simplify passing data
ring-buffer: Move the adding of the extended timestamp out of line
ring-buffer: Get timestamp after event is allocated
ring-buffer: Make sure event has enough room for extend and padding
ring-buffer: Reorganize function locations
tracing: Clean up stack tracing and fix fentry updates
ftrace: Fix function_graph duration spacing with 7-digits
ring-buffer: Revert "ring-buffer: Get timestamp after event is allocated"

Umesh Tiwari (2):
ftrace: correct the counter increment for trace_buffer data
ftrace: add tracing_thresh to function profile

----

 Documentation/trace/ftrace.txt       |  51 ++-
 arch/metag/include/asm/ftrace.h      |   2 +-
 arch/microblaze/include/asm/ftrace.h |   2 +-
 arch/powerpc/include/asm/ftrace.h    |   2 +-
 arch/sh/include/asm/ftrace.h         |   2 +-
 arch/sparc/include/asm/ftrace.h      |   2 +-
 arch/x86/include/asm/ftrace.h        |   4 +-
 include/trace/events/task.h          |   2 +-
 kernel/trace/ftrace.c                |   9 +-
 kernel/trace/ring_buffer.c           | 790 ++++++++++++++++++-----------------
 kernel/trace/trace.c                 |   4 +-
 kernel/trace/trace_events.c          |  25 ++
 kernel/trace/trace_events_filter.c   |  54 ++-
 kernel/trace/trace_functions_graph.c |   4 +-
 kernel/trace/trace_output.c          |   4 +-
 kernel/trace/trace_stack.c           |  68 +--
 16 files changed, 575 insertions(+), 450 deletions(-)

---------------------------

Documentation/trace/ftrace.txt +38 -13
index 7ddb1e319f84..072d3c4d5753 100644
@@ -686,6 +686,8 @@ The above is mostly meaningful for kernel developers.
 	 The marks are determined by the difference between this
 	 current trace and the next trace.
 	  '$' - greater than 1 second
+	  '@' - greater than 100 milisecond
+	  '*' - greater than 10 milisecond
 	  '#' - greater than 1000 microsecond
 	  '!' - greater than 100 microsecond
 	  '+' - greater than 10 microsecond
@@ -1939,26 +1941,49 @@ want, depending on your needs.
 
   ie:
 
-  0)               |    up_write() {
-  0)   0.646 us    |      _spin_lock_irqsave();
-  0)   0.684 us    |      _spin_unlock_irqrestore();
-  0)   3.123 us    |    }
-  0)   0.548 us    |    fput();
-  0) + 58.628 us   |  }
+  3) # 1837.709 us |          } /* __switch_to */
+  3)               |          finish_task_switch() {
+  3)   0.313 us    |            _raw_spin_unlock_irq();
+  3)   3.177 us    |          }
+  3) # 1889.063 us |        } /* __schedule */
+  3) ! 140.417 us  |      } /* __schedule */
+  3) # 2034.948 us |    } /* schedule */
+  3) * 33998.59 us |  } /* schedule_preempt_disabled */
 
   [...]
 
-  0)               |      putname() {
-  0)               |        kmem_cache_free() {
-  0)   0.518 us    |          __phys_addr();
-  0)   1.757 us    |        }
-  0)   2.861 us    |      }
-  0) ! 115.305 us  |    }
-  0) ! 116.402 us  |  }
+  1)   0.260 us    |              msecs_to_jiffies();
+  1)   0.313 us    |              __rcu_read_unlock();
+  1) + 61.770 us   |            }
+  1) + 64.479 us   |          }
+  1)   0.313 us    |          rcu_bh_qs();
+  1)   0.313 us    |          __local_bh_enable();
+  1) ! 217.240 us  |        }
+  1)   0.365 us    |        idle_cpu();
+  1)               |        rcu_irq_exit() {
+  1)   0.417 us    |          rcu_eqs_enter_common.isra.47();
+  1)   3.125 us    |        }
+  1) ! 227.812 us  |      }
+  1) ! 457.395 us  |    }
+  1) @ 119760.2 us |  }
+
+  [...]
+
+  2)               |    handle_IPI() {
+  1)   6.979 us    |                  }
+  2)   0.417 us    |      scheduler_ipi();
+  1)   9.791 us    |                }
+  1) + 12.917 us   |              }
+  2)   3.490 us    |    }
+  1) + 15.729 us   |            }
+  1) + 18.542 us   |          }
+  2) $ 3594274 us  |  }
 
   + means that the function exceeded 10 usecs.
   ! means that the function exceeded 100 usecs.
   # means that the function exceeded 1000 usecs.
+  * means that the function exceeded 10 msecs.
+  @ means that the function exceeded 100 msecs.
   $ means that the function exceeded 1 sec.
 
 
arch/metag/include/asm/ftrace.h +1 -1
index 2901f0f7d944..a2269d60a945 100644
@@ -6,7 +6,7 @@
 
 #ifndef __ASSEMBLY__
 extern void mcount_wrapper(void);
-#define MCOUNT_ADDR		((long)(mcount_wrapper))
+#define MCOUNT_ADDR		((unsigned long)(mcount_wrapper))
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
arch/microblaze/include/asm/ftrace.h +1 -1
index fd2fa2eca62f..da0144f40d99 100644
@@ -3,7 +3,7 @@
 
 #ifdef CONFIG_FUNCTION_TRACER
 
-#define MCOUNT_ADDR		((long)(_mcount))
+#define MCOUNT_ADDR		((unsigned long)(_mcount))
 #define MCOUNT_INSN_SIZE	8 /* sizeof mcount call */
 
 #ifndef __ASSEMBLY__
arch/powerpc/include/asm/ftrace.h +1 -1
index e3661872fbea..ef89b1465573 100644
@@ -2,7 +2,7 @@
 #define _ASM_POWERPC_FTRACE
 
 #ifdef CONFIG_FUNCTION_TRACER
-#define MCOUNT_ADDR		((long)(_mcount))
+#define MCOUNT_ADDR		((unsigned long)(_mcount))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
 
 #ifdef __ASSEMBLY__
arch/sh/include/asm/ftrace.h +1 -1
index e79fb6ebaa42..1f157b86eaa7 100644
@@ -9,7 +9,7 @@
 #ifndef __ASSEMBLY__
 extern void mcount(void);
 
-#define MCOUNT_ADDR		((long)(mcount))
+#define MCOUNT_ADDR		((unsigned long)(mcount))
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define CALL_ADDR		((long)(ftrace_call))
arch/sparc/include/asm/ftrace.h +1 -1
index 9ec94ad116fb..3192a8e42fd6 100644
@@ -2,7 +2,7 @@
 #define _ASM_SPARC64_FTRACE
 
 #ifdef CONFIG_MCOUNT
-#define MCOUNT_ADDR		((long)(_mcount))
+#define MCOUNT_ADDR		((unsigned long)(_mcount))
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
 
 #ifndef __ASSEMBLY__
arch/x86/include/asm/ftrace.h +2 -2
index f45acad3c4b6..24938852db30 100644
@@ -3,9 +3,9 @@
 
 #ifdef CONFIG_FUNCTION_TRACER
 #ifdef CC_USING_FENTRY
-# define MCOUNT_ADDR		((long)(__fentry__))
+# define MCOUNT_ADDR		((unsigned long)(__fentry__))
 #else
-# define MCOUNT_ADDR		((long)(mcount))
+# define MCOUNT_ADDR		((unsigned long)(mcount))
 #endif
 #define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */
 
include/trace/events/task.h +1 -1
index dee3bb1d5a6b..2cca6cd342d8 100644
@@ -46,7 +46,7 @@ TRACE_EVENT(task_rename,
 	TP_fast_assign(
 		__entry->pid = task->pid;
 		memcpy(entry->oldcomm, task->comm, TASK_COMM_LEN);
-		memcpy(entry->newcomm, comm, TASK_COMM_LEN);
+		strlcpy(entry->newcomm, comm, TASK_COMM_LEN);
 		__entry->oom_score_adj = task->signal->oom_score_adj;
 	),
 
kernel/trace/ftrace.c +7 -2
index 02bece4a99ea..f46dbb5cdf76 100644
@@ -613,13 +613,18 @@ static int function_stat_show(struct seq_file *m, void *v)
 		goto out;
 	}
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	avg = rec->time;
+	do_div(avg, rec->counter);
+	if (tracing_thresh && (avg < tracing_thresh))
+		goto out;
+#endif
+
 	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
 	seq_printf(m, "  %-30.30s  %10lu", str, rec->counter);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	seq_puts(m, "    ");
-	avg = rec->time;
-	do_div(avg, rec->counter);
 
 	/* Sample standard deviation (s^2) */
 	if (rec->counter <= 1)
kernel/trace/ring_buffer.c +415 -375

904 lines not on this page · raw message

kernel/trace/trace.c +2 -2
index abcbf7ff8743..6e79408674aa 100644
@@ -3035,7 +3035,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 	if (!iter)
 		return ERR_PTR(-ENOMEM);
 
-	iter->buffer_iter = kzalloc(sizeof(*iter->buffer_iter) * num_possible_cpus(),
+	iter->buffer_iter = kcalloc(nr_cpu_ids, sizeof(*iter->buffer_iter),
 				    GFP_KERNEL);
 	if (!iter->buffer_iter)
 		goto release;
@@ -6990,7 +6990,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 	trace_init_global_iter(&iter);
 
 	for_each_tracing_cpu(cpu) {
-		atomic_inc(&per_cpu_ptr(iter.tr->trace_buffer.data, cpu)->disabled);
+		atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
 	}
 
 	old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ;
kernel/trace/trace_events.c +25 -0
index 404a372ad85a..7ca09cdc20c2 100644
@@ -30,6 +30,7 @@
 DEFINE_MUTEX(event_mutex);
 
 LIST_HEAD(ftrace_events);
+static LIST_HEAD(ftrace_generic_fields);
 static LIST_HEAD(ftrace_common_fields);
 
 #define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)
@@ -94,6 +95,10 @@ trace_find_event_field(struct trace_event_call *call, char *name)
 	struct ftrace_event_field *field;
 	struct list_head *head;
 
+	field = __find_event_field(&ftrace_generic_fields, name);
+	if (field)
+		return field;
+
 	field = __find_event_field(&ftrace_common_fields, name);
 	if (field)
 		return field;
@@ -144,6 +149,13 @@ int trace_define_field(struct trace_event_call *call, const char *type,
 }
 EXPORT_SYMBOL_GPL(trace_define_field);
 
+#define __generic_field(type, item, filter_type)			\
+	ret = __trace_define_field(&ftrace_generic_fields, #type,	\
+				   #item, 0, 0, is_signed_type(type),	\
+				   filter_type);			\
+	if (ret)							\
+		return ret;
+
 #define __common_field(type, item)					\
 	ret = __trace_define_field(&ftrace_common_fields, #type,	\
 				   "common_" #item,			\
@@ -153,6 +165,16 @@ EXPORT_SYMBOL_GPL(trace_define_field);
 	if (ret)							\
 		return ret;
 
+static int trace_define_generic_fields(void)
+{
+	int ret;
+
+	__generic_field(int, cpu, FILTER_OTHER);
+	__generic_field(char *, comm, FILTER_PTR_STRING);
+
+	return ret;
+}
+
 static int trace_define_common_fields(void)
 {
 	int ret;
@@ -2671,6 +2693,9 @@ static __init int event_trace_init(void)
 	if (!entry)
 		pr_warn("Could not create tracefs 'available_events' entry\n");
 
+	if (trace_define_generic_fields())
+		pr_warn("tracing: Failed to allocated generic fields");
+
 	if (trace_define_common_fields())
 		pr_warn("tracing: Failed to allocate common fields");
 
kernel/trace/trace_events_filter.c +52 -2

72 lines not on this page · raw message

kernel/trace/trace_functions_graph.c +2 -2
index 8968bf720c12..ca98445782ac 100644
@@ -715,13 +715,13 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
 
 		snprintf(nsecs_str, slen, "%03lu", nsecs_rem);
 		trace_seq_printf(s, ".%s", nsecs_str);
-		len += strlen(nsecs_str);
+		len += strlen(nsecs_str) + 1;
 	}
 
 	trace_seq_puts(s, " us ");
 
 	/* Print remaining spaces to fit the row's width */
-	for (i = len; i < 7; i++)
+	for (i = len; i < 8; i++)
 		trace_seq_putc(s, ' ');
 }
 
kernel/trace/trace_output.c +3 -1
index dfab253727dc..8e481a84aeea 100644
@@ -496,6 +496,8 @@ static const struct trace_mark {
 	char			sym;
 } mark[] = {
 	MARK(1000000000ULL	, '$'), /* 1 sec */
+	MARK(100000000ULL	, '@'), /* 100 msec */
+	MARK(10000000ULL	, '*'), /* 10 msec */
 	MARK(1000000ULL		, '#'), /* 1000 usecs */
 	MARK(100000ULL		, '!'), /* 100 usecs */
 	MARK(10000ULL		, '+'), /* 10 usecs */
@@ -508,7 +510,7 @@ char trace_find_mark(unsigned long long d)
 	int size = ARRAY_SIZE(mark);
 
 	for (i = 0; i < size; i++) {
-		if (d >= mark[i].val)
+		if (d > mark[i].val)
 			break;
 	}
 
kernel/trace/trace_stack.c +23 -45

145 lines not on this page · raw message