[PATCH v14 04/22] tracing: Add hist trigger support for compound keys

[Tom Zanussi <tom.zanussi@linux.intel.com>]

Allow users to specify multiple trace event fields to use in keys by
allowing multiple fields in the 'keys=' keyword.  With this addition,
any unique combination of any of the fields named in the 'keys'
keyword will result in a new entry being added to the hash table.

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
---
 kernel/trace/trace.c             | 10 ++++++----
 kernel/trace/trace_events_hist.c | 41 +++++++++++++++++++++++++++++-----------
 2 files changed, 36 insertions(+), 15 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 86cd8e6..1a97671 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3824,7 +3824,7 @@ static const char readme_msg[] =
 	"\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    Format: hist:keys=<field1[,field2,...]>\n"
 	"\t            [:values=<field1[,field2,...]>]\n"
 	"\t            [:size=#entries]\n"
 	"\t            [if <filter>]\n\n"
@@ -3832,9 +3832,11 @@ static const char readme_msg[] =
 	"\t    table using the key(s) and value(s) named, and the value of a\n"
 	"\t    sum called 'hitcount' is incremented.  Keys and values\n"
 	"\t    correspond to fields in the event's format description.  Keys\n"
-	"\t    can be any field.  Values must correspond to numeric fields.\n"
-	"\t    The 'size' parameter can be  used to specify more or fewer\n"
-	"\t    than the default 2048 entries for the hashtable size.\n\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    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"
 	"\t    table in its entirety to stdout."
 #endif
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 55e363d..cbd72f0 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -32,6 +32,7 @@ struct hist_field {
 	unsigned long			flags;
 	hist_field_fn_t			fn;
 	unsigned int			size;
+	unsigned int			offset;
 };
 
 static u64 hist_field_counter(struct hist_field *field, void *event)
@@ -73,8 +74,7 @@ DEFINE_HIST_FIELD_FN(u8);
 	for ((i) = (hist_data)->n_vals; (i) < (hist_data)->n_fields; (i)++)
 
 #define HITCOUNT_IDX		0
-#define HIST_KEY_MAX		1
-#define HIST_KEY_SIZE_MAX	MAX_FILTER_STR_VAL
+#define HIST_KEY_SIZE_MAX	(MAX_FILTER_STR_VAL + sizeof(u64))
 
 enum hist_field_flags {
 	HIST_FIELD_FL_HITCOUNT	= 1,
@@ -347,6 +347,7 @@ static int create_val_fields(struct hist_trigger_data *hist_data,
 
 static int create_key_field(struct hist_trigger_data *hist_data,
 			    unsigned int key_idx,
+			    unsigned int key_offset,
 			    struct trace_event_file *file,
 			    char *field_str)
 {
@@ -376,7 +377,8 @@ static int create_key_field(struct hist_trigger_data *hist_data,
 
 	key_size = ALIGN(key_size, sizeof(u64));
 	hist_data->fields[key_idx]->size = key_size;
-	hist_data->key_size = key_size;
+	hist_data->fields[key_idx]->offset = key_offset;
+	hist_data->key_size += key_size;
 	if (hist_data->key_size > HIST_KEY_SIZE_MAX) {
 		ret = -EINVAL;
 		goto out;
@@ -393,7 +395,7 @@ static int create_key_field(struct hist_trigger_data *hist_data,
 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;
+	unsigned int i, key_offset = 0, n_vals = hist_data->n_vals;
 	char *fields_str, *field_str;
 	int ret = -EINVAL;
 
@@ -405,13 +407,15 @@ static int create_key_fields(struct hist_trigger_data *hist_data,
 	if (!fields_str)
 		goto out;
 
-	for (i = n_vals; i < n_vals + HIST_KEY_MAX; i++) {
+	for (i = n_vals; i < n_vals + TRACING_MAP_KEYS_MAX; i++) {
 		field_str = strsep(&fields_str, ",");
 		if (!field_str)
 			break;
-		ret = create_key_field(hist_data, i, file, field_str);
+		ret = create_key_field(hist_data, i, key_offset,
+				       file, field_str);
 		if (ret < 0)
 			goto out;
+		key_offset += ret;
 	}
 	if (fields_str) {
 		ret = -EINVAL;
@@ -476,7 +480,10 @@ static int create_tracing_map_fields(struct hist_trigger_data *hist_data)
 			else
 				cmp_fn = tracing_map_cmp_num(field->size,
 							     field->is_signed);
-			idx = tracing_map_add_key_field(map, 0, cmp_fn);
+			idx = tracing_map_add_key_field(map,
+							hist_field->offset,
+							cmp_fn);
+
 		} else
 			idx = tracing_map_add_sum_field(map);
 
@@ -556,12 +563,16 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
 static void event_hist_trigger(struct event_trigger_data *data, void *rec)
 {
 	struct hist_trigger_data *hist_data = data->private_data;
+	char compound_key[HIST_KEY_SIZE_MAX];
 	struct hist_field *key_field;
 	struct tracing_map_elt *elt;
 	u64 field_contents;
 	void *key = NULL;
 	unsigned int i;
 
+	if (hist_data->n_keys > 1)
+		memset(compound_key, 0, hist_data->key_size);
+
 	for_each_hist_key_field(i, hist_data) {
 		key_field = hist_data->fields[i];
 
@@ -570,8 +581,16 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec)
 			key = (void *)(unsigned long)field_contents;
 		else
 			key = (void *)&field_contents;
+
+		if (hist_data->n_keys > 1) {
+			memcpy(compound_key + key_field->offset, key,
+			       key_field->size);
+		}
 	}
 
+	if (hist_data->n_keys > 1)
+		key = compound_key;
+
 	elt = tracing_map_insert(hist_data->map, key);
 	if (elt)
 		hist_trigger_elt_update(hist_data, elt, rec);
@@ -596,11 +615,11 @@ hist_trigger_entry_print(struct seq_file *m,
 
 		if (key_field->flags & HIST_FIELD_FL_STRING) {
 			seq_printf(m, "%s: %-50s", key_field->field->name,
-				   (char *)key);
+				   (char *)(key + key_field->offset));
 		} else {
-			uval = *(u64 *)key;
-			seq_printf(m, "%s: %10llu",
-				   key_field->field->name, uval);
+			uval = *(u64 *)(key + key_field->offset);
+			seq_printf(m, "%s: %10llu", key_field->field->name,
+				   uval);
 		}
 	}
 
-- 
1.9.3