[PATCH v12 13/30] tracing: Add hist trigger support for user-defined sorting ('sort=' param)

[Tom Zanussi]

Allow users to specify keys and/or values to sort on.  With this
addition, keys and values specified using the 'keys=' and 'vals='
keywords can be used to sort the hist trigger output via a new 'sort='
keyword.  If multiple sort keys are specified, the output will be
sorted using the second key as a secondary sort key, etc.  The default
sort order is ascending; if the user wants a different sort order,
'.descending' can be appended to the specific sort key.  Before this
addition, output was always sorted by 'hitcount' in ascending order.

This expands the hist trigger syntax from this:

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

to this:

    # echo hist:keys=xxx:vals=yyy:sort=zzz.descending \
          [ if filter] > event/trigger

Signed-off-by: Tom Zanussi <tom.zanussi@xxxxxxxxxxxxxxx>
Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
---
 kernel/trace/trace.c             |   6 ++-
 kernel/trace/trace_events_hist.c | 103 ++++++++++++++++++++++++++++++++++++++-
 2 files changed, 106 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 50ea2f5..267655c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3826,6 +3826,7 @@ static const char readme_msg[] =
 	"      hist trigger\t- If set, event hits are aggregated into a hash table\n"
 	"\t    Format: hist:keys=<field1[,field2,...]>\n"
 	"\t            [:values=<field1[,field2,...]>]\n"
+	"\t            [:sort=<field1[,field2,...]>]\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"
@@ -3834,7 +3835,10 @@ static const char readme_msg[] =
 	"\t    correspond to fields in the event's format description.  Keys\n"
 	"\t    can be any field.  Compound keys consisting of up to two\n"
 	"\t    fields can be specified by the 'keys' keyword.  Values must\n"
-	"\t    correspond to numeric fields.  The 'size' parameter can be\n"
+	"\t    correspond to numeric fields.  Sort keys consisting of up to\n"
+	"\t    two fields can be specified using the 'sort' keyword.  The\n"
+	"\t    sort direction can be modified by appending '.descending' or\n"
+	"\t    '.ascending' to a sort field.  The 'size' parameter can be\n"
 	"\t    used to specify more or fewer than the default 2048 entries\n"
 	"\t    for the hashtable size.\n\n"
 	"\t    Reading the 'hist' file for the event will dump the hash\n"
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 888c67c..117484b 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -86,6 +86,7 @@ enum hist_field_flags {
 struct hist_trigger_attrs {
 	char		*keys_str;
 	char		*vals_str;
+	char		*sort_key_str;
 	unsigned int	map_bits;
 };
 
@@ -166,6 +167,7 @@ static void destroy_hist_trigger_attrs(struct hist_trigger_attrs *attrs)
 	if (!attrs)
 		return;
 
+	kfree(attrs->sort_key_str);
 	kfree(attrs->keys_str);
 	kfree(attrs->vals_str);
 	kfree(attrs);
@@ -190,6 +192,8 @@ static struct hist_trigger_attrs *parse_hist_trigger_attrs(char *trigger_str)
 			 !strncmp(str, "vals", strlen("vals")) ||
 			 !strncmp(str, "val", strlen("val")))
 			attrs->vals_str = kstrdup(str, GFP_KERNEL);
+		else if (!strncmp(str, "sort", strlen("sort")))
+			attrs->sort_key_str = kstrdup(str, GFP_KERNEL);
 		else if (!strncmp(str, "size", strlen("size"))) {
 			int map_bits = parse_map_size(str);
 
@@ -435,12 +439,88 @@ static int create_hist_fields(struct hist_trigger_data *hist_data,
 	return ret;
 }
 
+static int is_descending(const char *str)
+{
+	if (!str)
+		return 0;
+
+	if (!strcmp(str, "descending"))
+		return 1;
+
+	if (!strcmp(str, "ascending"))
+		return 0;
+
+	return -EINVAL;
+}
+
 static int create_sort_keys(struct hist_trigger_data *hist_data)
 {
+	char *fields_str = hist_data->attrs->sort_key_str;
+	struct ftrace_event_field *field = NULL;
+	struct tracing_map_sort_key *sort_key;
+	unsigned int i, j;
 	int ret = 0;
 
-	hist_data->n_sort_keys = 1; /* sort_keys[0] is always hitcount */
+	hist_data->n_sort_keys = 1; /* we always have at least one, hitcount */
+
+	if (!fields_str)
+		goto out;
+
+	strsep(&fields_str, "=");
+	if (!fields_str) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (i = 0; i < TRACING_MAP_SORT_KEYS_MAX; i++) {
+		char *field_str, *field_name;
+
+		sort_key = &hist_data->sort_keys[i];
+
+		field_str = strsep(&fields_str, ",");
+		if (!field_str) {
+			if (i == 0)
+				ret = -EINVAL;
+			break;
+		}
+
+		if ((i == TRACING_MAP_SORT_KEYS_MAX - 1) && fields_str) {
+			ret = -EINVAL;
+			break;
+		}
 
+		field_name = strsep(&field_str, ".");
+		if (!field_name) {
+			ret = -EINVAL;
+			break;
+		}
+
+		if (!strcmp(field_name, "hitcount")) {
+			ret = is_descending(field_str);
+			if (ret < 0)
+				break;
+			sort_key->descending = ret;
+			continue;
+		}
+
+		for (j = 1; j < hist_data->n_fields; j++) {
+			field = hist_data->fields[j]->field;
+			if (field && !strcmp(field_name, field->name)) {
+				sort_key->field_idx = j;
+				ret = is_descending(field_str);
+				if (ret < 0)
+					goto out;
+				sort_key->descending = ret;
+				break;
+			}
+		}
+		if (j == hist_data->n_fields) {
+			ret = -EINVAL;
+			break;
+		}
+	}
+	hist_data->n_sort_keys = i;
+ out:
 	return ret;
 }
 
@@ -745,7 +825,26 @@ static int event_hist_trigger_print(struct seq_file *m,
 	}
 
 	seq_puts(m, ":sort=");
-	seq_puts(m, "hitcount");
+
+	for (i = 0; i < hist_data->n_sort_keys; i++) {
+		struct tracing_map_sort_key *sort_key;
+
+		sort_key = &hist_data->sort_keys[i];
+
+		if (i > 0)
+			seq_puts(m, ",");
+
+		if (sort_key->field_idx == HITCOUNT_IDX)
+			seq_puts(m, "hitcount");
+		else {
+			unsigned int idx = sort_key->field_idx;
+
+			hist_field_print(m, hist_data->fields[idx]);
+		}
+
+		if (sort_key->descending)
+			seq_puts(m, ".descending");
+	}
 
 	seq_printf(m, ":size=%u", (1 << hist_data->map->map_bits));
 
-- 
1.9.3

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