Message-Id: <4912007a2c10ba09a34e5edafa7325377a4795d5.1437066836.git.tom.zanussi@linux.intel.com>
Date:	Thu, 16 Jul 2015 12:22:41 -0500
From:	Tom Zanussi <tom.zanussi@...ux.intel.com>
To:	rostedt@...dmis.org
Cc:	daniel.wagner@...-carit.de, masami.hiramatsu.pt@...achi.com,
	namhyung@...nel.org, josh@...htriplett.org, andi@...stfloor.org,
	linux-kernel@...r.kernel.org,
	Tom Zanussi <tom.zanussi@...ux.intel.com>
Subject: [PATCH v9 08/22] tracing: Add 'hist' event trigger command

'hist' triggers allow users to continually aggregate trace events,
which can then be viewed afterwards by simply reading a 'hist' file
containing the aggregation in a human-readable format.

The basic idea is very simple and boils down to a mechanism whereby
trace events, rather than being exhaustively dumped in raw form and
viewed directly, are automatically 'compressed' into meaningful tables
completely defined by the user.

This is done strictly via single-line command-line commands and
without the aid of any kind of programming language or interpreter.

A surprising number of typical use cases can be accomplished by users
via this simple mechanism.  In fact, a large number of the tasks that
users typically do using the more complicated script-based tracing
tools, at least during the initial stages of an investigation, can be
accomplished by simply specifying a set of keys and values to be used
in the creation of a hash table.

The Linux kernel trace event subsystem happens to provide an extensive
list of keys and values ready-made for such a purpose in the form of
the event format files associated with each trace event.  By simply
consulting the format file for field names of interest and by plugging
them into the hist trigger command, users can create an endless number
of useful aggregations to help with investigating various properties
of the system.  See Documentation/trace/events.txt for examples.

hist triggers are implemented on top of the existing event trigger
infrastructure, and as such are consistent with the existing triggers
from a user's perspective as well.

The basic syntax follows the existing trigger syntax.  Users start an
aggregation by writing a 'hist' trigger to the event of interest's
trigger file:

  # echo hist:keys=xxx [ if filter] > event/trigger

Once a hist trigger has been set up, by default it continually
aggregates every matching event into a hash table using the event key
and a value field named 'hitcount'.

To view the aggregation at any point in time, simply read the 'hist'
file in the same directory as the 'trigger' file:

  # cat event/hist

The detailed syntax provides additional options for user control, and
is described exhaustively in Documentation/trace/events.txt and in the
virtual tracing/README file in the tracing subsystem.

Signed-off-by: Tom Zanussi <tom.zanussi@...ux.intel.com>
---
 include/linux/trace_events.h        |   1 +
 kernel/trace/Kconfig                |  14 +
 kernel/trace/Makefile               |   1 +
 kernel/trace/trace.c                |  29 ++
 kernel/trace/trace.h                |   7 +
 kernel/trace/trace_events.c         |   4 +
 kernel/trace/trace_events_hist.c    | 832 ++++++++++++++++++++++++++++++++++++
 kernel/trace/trace_events_trigger.c |   1 +
 8 files changed, 889 insertions(+)
 create mode 100644 kernel/trace/trace_events_hist.c

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index d9b0f89..0faf48b 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -410,6 +410,7 @@ enum event_trigger_type {
 	ETT_SNAPSHOT		= (1 << 1),
 	ETT_STACKTRACE		= (1 << 2),
 	ETT_EVENT_ENABLE	= (1 << 3),
+	ETT_EVENT_HIST		= (1 << 4),
 };
 
 extern int filter_match_preds(struct event_filter *filter, void *rec);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 3b9a48a..85f8025 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -528,6 +528,20 @@ config MMIOTRACE
 	  See Documentation/trace/mmiotrace.txt.
 	  If you are not helping to develop drivers, say N.
 
+config HIST_TRIGGERS
+	bool "Histogram triggers"
+	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
+	help
+	  Hist triggers allow one or more arbitrary trace event fields
+	  to be aggregated into hash tables and dumped to stdout by
+	  reading a debugfs/tracefs file.  They're useful for
+	  gathering quick and dirty (though precise) summaries of
+	  event activity as an initial guide for further investigation
+	  using more advanced tools.
+
+	  See Documentation/trace/events.txt.
+	  If in doubt, say N.
+
 config MMIOTRACE_TEST
 	tristate "Test module for mmiotrace"
 	depends on MMIOTRACE && m
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 3b26cfb..7faace3 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -54,6 +54,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
 endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
+obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index abcbf7f..f6fdda2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3767,6 +3767,9 @@ static const char readme_msg[] =
 #ifdef CONFIG_TRACER_SNAPSHOT
 	"\t\t    snapshot\n"
 #endif
+#ifdef CONFIG_HIST_TRIGGERS
+	"\t\t    hist (see below)\n"
+#endif
 	"\t   example: echo traceoff > events/block/block_unplug/trigger\n"
 	"\t            echo traceoff:3 > events/block/block_unplug/trigger\n"
 	"\t            echo 'enable_event:kmem:kmalloc:3 if nr_rq > 1' > \\\n"
@@ -3782,6 +3785,32 @@ static const char readme_msg[] =
 	"\t   To remove a trigger with a count:\n"
 	"\t     echo '!<trigger>:0 > <system>/<event>/trigger\n"
 	"\t   Filters can be ignored when removing a trigger.\n"
+#ifdef CONFIG_HIST_TRIGGERS
+	"      hist trigger\t- If set, event hits are aggregated into a hash table\n"
+	"\t    Format: hist:keys=<field1>\n"
+	"\t            [:size=#entries]\n"
+	"\t            [if <filter>]\n\n"
+	"\t    When a matching event is hit, an entry is added to a hash\n"
+	"\t    table using the key named.  Keys correspond to fields in the\n"
+	"\t    event's format description.  On an event hit, the value of a\n"
+	"\t    sum called 'hitcount' is incremented, which is simply a count\n"
+	"\t    of event hits.  Keys can be any field.\n\n"
+	"\t    Reading the 'hist' file for the event will dump the hash\n"
+	"\t    table in its entirety to stdout.  Each printed hash table\n"
+	"\t    entry is a simple list of the keys and values comprising the\n"
+	"\t    entry; keys are printed first and are delineated by curly\n"
+	"\t    braces, and are followed by the set of value fields for the\n"
+	"\t    entry.  Numeric fields are displayed as base-10 integers.\n"
+	"\t    By default, the size of the hash table is 2048 entries.  The\n"
+	"\t    'size' param can be used to specify more or fewer than that.\n"
+	"\t    The units are in terms of hashtable entries - if a run uses\n"
+	"\t    more entries than specified, the results will show the number\n"
+	"\t    of 'drops', the number of hits that were ignored.  The size\n"
+	"\t    should be a power of 2 between 128 and 131072 (any non-\n"
+	"\t    power-of-2 number specified will be rounded up).\n\n"
+	"\t    The entries are sorted by 'hitcount' and the sort order is\n"
+	"\t    'ascending'.\n\n"
+#endif
 ;
 
 static ssize_t
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 5e675b2..e6cb781 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1098,6 +1098,13 @@ extern struct mutex event_mutex;
 extern struct list_head ftrace_events;
 
 extern const struct file_operations event_trigger_fops;
+extern const struct file_operations event_hist_fops;
+
+#ifdef CONFIG_HIST_TRIGGERS
+extern int register_trigger_hist_cmd(void);
+#else
+static inline int register_trigger_hist_cmd(void) { return 0; }
+#endif
 
 extern int register_trigger_cmds(void);
 extern void clear_event_triggers(struct trace_array *tr);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 404a372..2bf0465 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1628,6 +1628,10 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file)
 	trace_create_file("trigger", 0644, file->dir, file,
 			  &event_trigger_fops);
 
+#ifdef CONFIG_HIST_TRIGGERS
+	trace_create_file("hist", 0444, file->dir, file,
+			  &event_hist_fops);
+#endif
 	trace_create_file("format", 0444, file->dir, call,
 			  &ftrace_event_format_fops);
 
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
new file mode 100644
index 0000000..ded348b
--- /dev/null
+++ b/kernel/trace/trace_events_hist.c
@@ -0,0 +1,832 @@
+/*
+ * trace_events_hist - trace event hist triggers
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2015 Tom Zanussi <tom.zanussi@...ux.intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/stacktrace.h>
+
+#include "tracing_map.h"
+#include "trace.h"
+
+struct hist_field;
+
+typedef u64 (*hist_field_fn_t) (struct hist_field *field, void *event);
+
+struct hist_field {
+	struct ftrace_event_field	*field;
+	unsigned long			flags;
+	hist_field_fn_t			fn;
+	unsigned int			size;
+};
+
+static u64 hist_field_counter(struct hist_field *field, void *event)
+{
+	return 1;
+}
+
+static u64 hist_field_string(struct hist_field *hist_field, void *event)
+{
+	char *addr = (char *)(event + hist_field->field->offset);
+
+	return (u64)addr;
+}
+
+#define DEFINE_HIST_FIELD_FN(type)					\
+static u64 hist_field_##type(struct hist_field *hist_field, void *event)\
+{									\
+	type *addr = (type *)(event + hist_field->field->offset);	\
+									\
+	return (u64)*addr;						\
+}
+
+DEFINE_HIST_FIELD_FN(s64);
+DEFINE_HIST_FIELD_FN(u64);
+DEFINE_HIST_FIELD_FN(s32);
+DEFINE_HIST_FIELD_FN(u32);
+DEFINE_HIST_FIELD_FN(s16);
+DEFINE_HIST_FIELD_FN(u16);
+DEFINE_HIST_FIELD_FN(s8);
+DEFINE_HIST_FIELD_FN(u8);
+
+#define HITCOUNT_IDX		0
+#define HIST_KEY_MAX		1
+#define HIST_KEY_SIZE_MAX	MAX_FILTER_STR_VAL
+
+enum hist_field_flags {
+	HIST_FIELD_HITCOUNT	= 1,
+	HIST_FIELD_KEY		= 2,
+	HIST_FIELD_STRING	= 4,
+};
+
+struct hist_trigger_attrs {
+	char		*keys_str;
+	unsigned int	map_bits;
+};
+
+struct hist_trigger_data {
+	atomic64_t			total_hits;
+	struct hist_field               *fields[TRACING_MAP_FIELDS_MAX];
+	unsigned int			n_vals;
+	unsigned int			n_keys;
+	unsigned int			n_fields;
+	unsigned int			key_size;
+	struct tracing_map_sort_key	sort_keys[TRACING_MAP_SORT_KEYS_MAX];
+	unsigned int			n_sort_keys;
+	struct trace_event_file		*event_file;
+	atomic64_t			drops;
+	struct hist_trigger_attrs	*attrs;
+	struct tracing_map		*map;
+};
+
+static hist_field_fn_t select_value_fn(int field_size, int field_is_signed)
+{
+	hist_field_fn_t fn = NULL;
+
+	switch (field_size) {
+	case 8:
+		if (field_is_signed)
+			fn = hist_field_s64;
+		else
+			fn = hist_field_u64;
+		break;
+	case 4:
+		if (field_is_signed)
+			fn = hist_field_s32;
+		else
+			fn = hist_field_u32;
+		break;
+	case 2:
+		if (field_is_signed)
+			fn = hist_field_s16;
+		else
+			fn = hist_field_u16;
+		break;
+	case 1:
+		if (field_is_signed)
+			fn = hist_field_s8;
+		else
+			fn = hist_field_u8;
+		break;
+	}
+
+	return fn;
+}
+
+static int parse_map_size(char *str)
+{
+	unsigned long size, map_bits;
+	int ret;
+
+	strsep(&str, "=");
+	if (!str) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = kstrtoul(str, 0, &size);
+	if (ret)
+		goto out;
+
+	map_bits = ilog2(roundup_pow_of_two(size));
+	if (map_bits < TRACING_MAP_BITS_MIN ||
+	    map_bits > TRACING_MAP_BITS_MAX)
+		ret = -EINVAL;
+	else
+		ret = map_bits;
+ out:
+	return ret;
+}
+
+static void destroy_hist_trigger_attrs(struct hist_trigger_attrs *attrs)
+{
+	kfree(attrs->keys_str);
+	kfree(attrs);
+}
+
+static struct hist_trigger_attrs *parse_hist_trigger_attrs(char *trigger_str)
+{
+	struct hist_trigger_attrs *attrs;
+	int ret = 0;
+
+	attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
+	if (!attrs)
+		return ERR_PTR(-ENOMEM);
+
+	while (trigger_str) {
+		char *str = strsep(&trigger_str, ":");
+
+		if (!strncmp(str, "keys", strlen("keys")) ||
+		    !strncmp(str, "key", strlen("key")))
+			attrs->keys_str = kstrdup(str, GFP_KERNEL);
+		else if (!strncmp(str, "size", strlen("size"))) {
+			int map_bits = parse_map_size(str);
+
+			if (map_bits < 0) {
+				ret = map_bits;
+				goto free;
+			}
+			attrs->map_bits = map_bits;
+		} else {
+			ret = -EINVAL;
+			goto free;
+		}
+	}
+
+	return attrs;
+ free:
+	destroy_hist_trigger_attrs(attrs);
+
+	return ERR_PTR(ret);
+}
+
+static void destroy_hist_field(struct hist_field *hist_field)
+{
+	kfree(hist_field);
+}
+
+static struct hist_field *create_hist_field(struct ftrace_event_field *field,
+					    unsigned long flags)
+{
+	struct hist_field *hist_field;
+
+	if (field && is_function_field(field))
+		return NULL;
+
+	hist_field = kzalloc(sizeof(struct hist_field), GFP_KERNEL);
+	if (!hist_field)
+		return NULL;
+
+	if (flags & HIST_FIELD_HITCOUNT) {
+		hist_field->fn = hist_field_counter;
+		goto out;
+	}
+
+	if (is_string_field(field)) {
+		flags |= HIST_FIELD_STRING;
+		hist_field->fn = hist_field_string;
+	} else {
+		hist_field->fn = select_value_fn(field->size,
+						 field->is_signed);
+		if (!hist_field->fn) {
+			destroy_hist_field(hist_field);
+			return NULL;
+		}
+	}
+ out:
+	hist_field->field = field;
+	hist_field->flags = flags;
+
+	return hist_field;
+}
+
+static void destroy_hist_fields(struct hist_trigger_data *hist_data)
+{
+	unsigned int i;
+
+	for (i = 0; i < hist_data->n_fields; i++) {
+		destroy_hist_field(hist_data->fields[i]);
+		hist_data->fields[i] = NULL;
+	}
+}
+
+static int create_hitcount_val(struct hist_trigger_data *hist_data)
+{
+	hist_data->fields[HITCOUNT_IDX] =
+		create_hist_field(NULL, HIST_FIELD_HITCOUNT);
+	if (!hist_data->fields[HITCOUNT_IDX])
+		return -ENOMEM;
+
+	hist_data->n_vals++;
+
+	return 0;
+}
+
+static int create_val_fields(struct hist_trigger_data *hist_data,
+			     struct trace_event_file *file)
+{
+	int ret;
+
+	ret = create_hitcount_val(hist_data);
+
+	return ret;
+}
+
+static int create_key_field(struct hist_trigger_data *hist_data,
+			    unsigned int key_idx,
+			    struct trace_event_file *file,
+			    char *field_str)
+{
+	struct ftrace_event_field *field = NULL;
+	unsigned long flags = 0;
+	unsigned int key_size;
+	int ret = 0;
+
+	flags |= HIST_FIELD_KEY;
+
+	field = trace_find_event_field(file->event_call, field_str);
+	if (!field) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	key_size = field->size;
+
+	hist_data->fields[key_idx] = create_hist_field(field, flags);
+	if (!hist_data->fields[key_idx]) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	key_size = ALIGN(key_size, sizeof(u64));
+	hist_data->fields[key_idx]->size = key_size;
+	hist_data->key_size = key_size;
+	if (hist_data->key_size > HIST_KEY_SIZE_MAX) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	hist_data->n_keys++;
+	ret = key_size;
+ out:
+	return ret;
+}
+
+static int create_key_fields(struct hist_trigger_data *hist_data,
+			     struct trace_event_file *file)
+{
+	unsigned int i, n_vals = hist_data->n_vals;
+	char *fields_str, *field_str;
+	int ret = -EINVAL;
+
+	fields_str = hist_data->attrs->keys_str;
+	if (!fields_str)
+		goto out;
+
+	strsep(&fields_str, "=");
+	if (!fields_str)
+		goto out;
+
+	for (i = n_vals; i < n_vals + HIST_KEY_MAX; i++) {
+		field_str = strsep(&fields_str, ",");
+		if (!field_str)
+			break;
+		ret = create_key_field(hist_data, i, file, field_str);
+		if (ret < 0)
+			goto out;
+	}
+	if (fields_str) {
+		ret = -EINVAL;
+		goto out;
+	}
+	ret = 0;
+ out:
+	return ret;
+}
+
+static int create_hist_fields(struct hist_trigger_data *hist_data,
+			      struct trace_event_file *file)
+{
+	int ret;
+
+	ret = create_val_fields(hist_data, file);
+	if (ret)
+		goto out;
+
+	ret = create_key_fields(hist_data, file);
+	if (ret)
+		goto out;
+
+	hist_data->n_fields = hist_data->n_vals + hist_data->n_keys;
+ out:
+	return ret;
+}
+
+static int create_sort_keys(struct hist_trigger_data *hist_data)
+{
+	int ret = 0;
+
+	hist_data->n_sort_keys = 1; /* sort_keys[0] is always hitcount */
+
+	return ret;
+}
+
+static void destroy_hist_data(struct hist_trigger_data *hist_data)
+{
+	destroy_hist_trigger_attrs(hist_data->attrs);
+	destroy_hist_fields(hist_data);
+	tracing_map_destroy(hist_data->map);
+	kfree(hist_data);
+}
+
+static int create_tracing_map_fields(struct hist_trigger_data *hist_data)
+{
+	struct tracing_map *map = hist_data->map;
+	struct ftrace_event_field *field;
+	struct hist_field *hist_field;
+	unsigned int i, idx;
+
+	for (i = 0; i < hist_data->n_fields; i++) {
+		hist_field = hist_data->fields[i];
+		if (hist_field->flags & HIST_FIELD_KEY) {
+			tracing_map_cmp_fn_t cmp_fn;
+
+			field = hist_field->field;
+
+			if (is_string_field(field))
+				cmp_fn = tracing_map_cmp_string;
+			else
+				cmp_fn = tracing_map_cmp_num(field->size,
+							     field->is_signed);
+			idx = tracing_map_add_key_field(map, 0, cmp_fn);
+		} else
+			idx = tracing_map_add_sum_field(map);
+
+		if (idx < 0)
+			return idx;
+	}
+
+	return 0;
+}
+
+static struct hist_trigger_data *
+create_hist_data(unsigned int map_bits,
+		 struct hist_trigger_attrs *attrs,
+		 struct trace_event_file *file)
+{
+	struct hist_trigger_data *hist_data;
+	int ret = 0;
+
+	hist_data = kzalloc(sizeof(*hist_data), GFP_KERNEL);
+	if (!hist_data)
+		return ERR_PTR(-ENOMEM);
+
+	hist_data->attrs = attrs;
+
+	ret = create_hist_fields(hist_data, file);
+	if (ret < 0)
+		goto free;
+
+	ret = create_sort_keys(hist_data);
+	if (ret < 0)
+		goto free;
+
+	hist_data->map = tracing_map_create(map_bits, hist_data->key_size,
+					    NULL, hist_data);
+	if (IS_ERR(hist_data->map)) {
+		ret = PTR_ERR(hist_data->map);
+		hist_data->map = NULL;
+		goto free;
+	}
+
+	ret = create_tracing_map_fields(hist_data);
+	if (ret)
+		goto free;
+
+	ret = tracing_map_init(hist_data->map);
+	if (ret)
+		goto free;
+
+	hist_data->event_file = file;
+ out:
+	return hist_data;
+ free:
+	destroy_hist_data(hist_data);
+	if (ret)
+		hist_data = ERR_PTR(ret);
+	else
+		hist_data = NULL;
+
+	goto out;
+}
+
+static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
+				    struct tracing_map_elt *elt,
+				    void *rec)
+{
+	struct hist_field *hist_field;
+	unsigned int i;
+	u64 hist_val;
+
+	for (i = 0; i < hist_data->n_vals; i++) {
+		hist_field = hist_data->fields[i];
+		hist_val = hist_field->fn(hist_field, rec);
+		tracing_map_update_sum(elt, i, hist_val);
+	}
+}
+
+static void event_hist_trigger(struct event_trigger_data *data, void *rec)
+{
+	struct hist_trigger_data *hist_data = data->private_data;
+	struct hist_field *key_field;
+	struct tracing_map_elt *elt;
+	u64 field_contents;
+	void *key = NULL;
+	unsigned int i;
+
+	if (atomic64_read(&hist_data->drops)) {
+		atomic64_inc(&hist_data->drops);
+		return;
+	}
+
+	for (i = hist_data->n_vals; i < hist_data->n_fields; i++) {
+		key_field = hist_data->fields[i];
+
+		field_contents = key_field->fn(key_field, rec);
+		if (key_field->flags & HIST_FIELD_STRING)
+			key = (void *)field_contents;
+		else
+			key = (void *)&field_contents;
+	}
+
+	elt = tracing_map_insert(hist_data->map, key);
+	if (elt)
+		hist_trigger_elt_update(hist_data, elt, rec);
+	else
+		atomic64_inc(&hist_data->drops);
+
+	atomic64_inc(&hist_data->total_hits);
+}
+
+static void
+hist_trigger_entry_print(struct seq_file *m,
+			 struct hist_trigger_data *hist_data, void *key,
+			 struct tracing_map_elt *elt)
+{
+	struct hist_field *key_field;
+	unsigned int i;
+	u64 uval;
+
+	seq_puts(m, "{ ");
+
+	for (i = hist_data->n_vals; i < hist_data->n_fields; i++) {
+		key_field = hist_data->fields[i];
+
+		if (i > hist_data->n_vals)
+			seq_puts(m, ", ");
+
+		if (key_field->flags & HIST_FIELD_STRING) {
+			seq_printf(m, "%s: %-35s", key_field->field->name,
+				   (char *)key);
+		} else {
+			uval = *(u64 *)key;
+			seq_printf(m, "%s: %10llu",
+				   key_field->field->name, uval);
+		}
+	}
+
+	seq_puts(m, " }");
+
+	seq_printf(m, " hitcount: %10llu",
+		   tracing_map_read_sum(elt, HITCOUNT_IDX));
+
+	seq_puts(m, "\n");
+}
+
+static int print_entries(struct seq_file *m,
+			 struct hist_trigger_data *hist_data)
+{
+	struct tracing_map_sort_entry **sort_entries = NULL;
+	struct tracing_map *map = hist_data->map;
+	unsigned int i, n_entries;
+
+	n_entries = tracing_map_sort_entries(map, hist_data->sort_keys,
+					     hist_data->n_sort_keys,
+					     &sort_entries);
+	if (n_entries < 0)
+		return n_entries;
+
+	for (i = 0; i < n_entries; i++)
+		hist_trigger_entry_print(m, hist_data,
+					 sort_entries[i]->key,
+					 sort_entries[i]->elt);
+
+	tracing_map_destroy_sort_entries(sort_entries, n_entries);
+
+	return n_entries;
+}
+
+static int hist_show(struct seq_file *m, void *v)
+{
+	struct event_trigger_data *test, *data = NULL;
+	struct trace_event_file *event_file;
+	struct hist_trigger_data *hist_data;
+	int n_entries, ret = 0;
+
+	mutex_lock(&event_mutex);
+
+	event_file = event_file_data(m->private);
+	if (unlikely(!event_file)) {
+		ret = -ENODEV;
+		goto out_unlock;
+	}
+
+	list_for_each_entry_rcu(test, &event_file->triggers, list) {
+		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+			data = test;
+			break;
+		}
+	}
+	if (!data)
+		goto out_unlock;
+
+	seq_puts(m, "# trigger info: ");
+	data->ops->print(m, data->ops, data);
+	seq_puts(m, "\n");
+
+	hist_data = data->private_data;
+	n_entries = print_entries(m, hist_data);
+	if (n_entries < 0) {
+		ret = n_entries;
+		n_entries = 0;
+	}
+
+	seq_printf(m, "\nTotals:\n    Hits: %lu\n    Entries: %u\n    Dropped: %lu\n",
+		   atomic64_read(&hist_data->total_hits),
+		   n_entries, atomic64_read(&hist_data->drops));
+ out_unlock:
+	mutex_unlock(&event_mutex);
+
+	return ret;
+}
+
+static int event_hist_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hist_show, file);
+}
+
+const struct file_operations event_hist_fops = {
+	.open = event_hist_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
+{
+	seq_printf(m, "%s", hist_field->field->name);
+}
+
+static int event_hist_trigger_print(struct seq_file *m,
+				    struct event_trigger_ops *ops,
+				    struct event_trigger_data *data)
+{
+	struct hist_trigger_data *hist_data = data->private_data;
+	struct hist_field *key_field;
+	unsigned int i;
+
+	seq_puts(m, "hist:keys=");
+
+	for (i = hist_data->n_vals; i < hist_data->n_fields; i++) {
+		key_field = hist_data->fields[i];
+
+		if (i > hist_data->n_vals)
+			seq_puts(m, ",");
+
+		hist_field_print(m, key_field);
+	}
+
+	seq_puts(m, ":vals=");
+	seq_puts(m, "hitcount");
+
+	seq_puts(m, ":sort=");
+	seq_puts(m, "hitcount");
+
+	seq_printf(m, ":size=%u", (1 << hist_data->map->map_bits));
+
+	if (data->filter_str)
+		seq_printf(m, " if %s", data->filter_str);
+
+	seq_puts(m, " [active]");
+
+	seq_putc(m, '\n');
+
+	return 0;
+}
+
+static void event_hist_trigger_free(struct event_trigger_ops *ops,
+				    struct event_trigger_data *data)
+{
+	struct hist_trigger_data *hist_data = data->private_data;
+
+	if (WARN_ON_ONCE(data->ref <= 0))
+		return;
+
+	data->ref--;
+	if (!data->ref) {
+		trigger_data_free(data);
+		destroy_hist_data(hist_data);
+	}
+}
+
+static struct event_trigger_ops event_hist_trigger_ops = {
+	.func			= event_hist_trigger,
+	.print			= event_hist_trigger_print,
+	.init			= event_trigger_init,
+	.free			= event_hist_trigger_free,
+};
+
+static struct event_trigger_ops *event_hist_get_trigger_ops(char *cmd,
+							    char *param)
+{
+	return &event_hist_trigger_ops;
+}
+
+static int hist_register_trigger(char *glob, struct event_trigger_ops *ops,
+				 struct event_trigger_data *data,
+				 struct trace_event_file *file)
+{
+	struct event_trigger_data *test;
+	int ret = 0;
+
+	list_for_each_entry_rcu(test, &file->triggers, list) {
+		if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+			ret = -EEXIST;
+			goto out;
+		}
+	}
+
+	if (data->ops->init) {
+		ret = data->ops->init(data->ops, data);
+		if (ret < 0)
+			goto out;
+	}
+
+	list_add_rcu(&data->list, &file->triggers);
+	ret++;
+
+	update_cond_flag(file);
+	if (trace_event_trigger_enable_disable(file, 1) < 0) {
+		list_del_rcu(&data->list);
+		update_cond_flag(file);
+		ret--;
+	}
+ out:
+	return ret;
+}
+
+static int event_hist_trigger_func(struct event_command *cmd_ops,
+				   struct trace_event_file *file,
+				   char *glob, char *cmd, char *param)
+{
+	unsigned int hist_trigger_bits = TRACING_MAP_BITS_DEFAULT;
+	struct event_trigger_data *trigger_data;
+	struct hist_trigger_attrs *attrs;
+	struct event_trigger_ops *trigger_ops;
+	struct hist_trigger_data *hist_data;
+	char *trigger;
+	int ret = 0;
+
+	if (!param)
+		return -EINVAL;
+
+	/* separate the trigger from the filter (k:v [if filter]) */
+	trigger = strsep(&param, " \t");
+	if (!trigger)
+		return -EINVAL;
+
+	attrs = parse_hist_trigger_attrs(trigger);
+	if (IS_ERR(attrs))
+		return PTR_ERR(attrs);
+
+	if (!attrs->keys_str)
+		return -EINVAL;
+
+	if (attrs->map_bits)
+		hist_trigger_bits = attrs->map_bits;
+
+	hist_data = create_hist_data(hist_trigger_bits, attrs, file);
+	if (IS_ERR(hist_data))
+		return PTR_ERR(hist_data);
+
+	trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger);
+
+	ret = -ENOMEM;
+	trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL);
+	if (!trigger_data)
+		goto out;
+
+	trigger_data->count = -1;
+	trigger_data->ops = trigger_ops;
+	trigger_data->cmd_ops = cmd_ops;
+
+	INIT_LIST_HEAD(&trigger_data->list);
+	RCU_INIT_POINTER(trigger_data->filter, NULL);
+
+	trigger_data->private_data = hist_data;
+
+	if (glob[0] == '!') {
+		cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
+		ret = 0;
+		goto out_free;
+	}
+
+	if (!param) /* if param is non-empty, it's supposed to be a filter */
+		goto out_reg;
+
+	if (!cmd_ops->set_filter)
+		goto out_reg;
+
+	ret = cmd_ops->set_filter(param, trigger_data, file);
+	if (ret < 0)
+		goto out_free;
+ out_reg:
+	ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
+	/*
+	 * The above returns on success the # of triggers registered,
+	 * but if it didn't register any it returns zero.  Consider no
+	 * triggers registered a failure too.
+	 */
+	if (!ret) {
+		ret = -ENOENT;
+		goto out_free;
+	} else if (ret < 0)
+		goto out_free;
+	/* Just return zero, not the number of registered triggers */
+	ret = 0;
+ out:
+	return ret;
+ out_free:
+	if (cmd_ops->set_filter)
+		cmd_ops->set_filter(NULL, trigger_data, NULL);
+
+	kfree(trigger_data);
+
+	destroy_hist_data(hist_data);
+	goto out;
+}
+
+static struct event_command trigger_hist_cmd = {
+	.name			= "hist",
+	.trigger_type		= ETT_EVENT_HIST,
+	.post_trigger		= true, /* need non-NULL rec */
+	.func			= event_hist_trigger_func,
+	.reg			= hist_register_trigger,
+	.unreg			= unregister_trigger,
+	.get_trigger_ops	= event_hist_get_trigger_ops,
+	.set_filter		= set_trigger_filter,
+};
+
+__init int register_trigger_hist_cmd(void)
+{
+	int ret;
+
+	ret = register_event_command(&trigger_hist_cmd);
+	WARN_ON(ret < 0);
+
+	return ret;
+}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 5f632ff..e80f30b 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1437,6 +1437,7 @@ __init int register_trigger_cmds(void)
 	register_trigger_snapshot_cmd();
 	register_trigger_stacktrace_cmd();
 	register_trigger_enable_disable_cmds();
+	register_trigger_hist_cmd();
 
 	return 0;
 }
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists