[PATCH 16/32] tracing: Add variable support to hist triggers

From: Tom Zanussi
Date: Mon Jun 26 2017 - 18:54:03 EST

Add support for saving the value of a current event's event field by
assigning it to a variable that can be read by a subsequent event.

The basic syntax for saving a variable is to simply prefix a unique
variable name not corresponding to any keyword along with an '=' sign
to any event field.

Both keys and values can be saved and retrieved in this way:

# echo 'hist:keys=next_pid:vals=ts0=common_timestamp ...
# echo 'hist:key=timer_pid=common_pid ...'

If a variable isn't a key variable or prefixed with 'vals=', the
associated event field will be saved in a variable but won't be summed
as a value:

# echo 'hist:keys=next_pid:ts1=common_timestamp:...

Multiple variables can be assigned at the same time:

# echo 'hist:keys=pid:vals=ts0=common_timestamp,b=field1,field2 ...

Multiple (or single) variables can also be assigned at the same time
using separate assignments:

# echo 'hist:keys=pid:vals=ts0=common_timestamp:b=field1:c=field2 ...

Variables set as above can be used by being referenced from another
event, as described in a subsequent patch.

Signed-off-by: Tom Zanussi <tom.zanussi@xxxxxxxxxxxxxxx>
---
kernel/trace/trace_events_hist.c | 299 ++++++++++++++++++++++++++++++++++-----
1 file changed, 264 insertions(+), 35 deletions(-)

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 5c351d7..75cac76 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -30,6 +30,13 @@ typedef u64 (*hist_field_fn_t) (struct hist_field *field, void *event,
struct ring_buffer_event *rbe);

#define HIST_FIELD_OPERANDS_MAX 2
+#define HIST_FIELDS_MAX (TRACING_MAP_FIELDS_MAX + TRACING_MAP_VARS_MAX)
+
+struct hist_var {
+ char *name;
+ struct hist_trigger_data *hist_data;
+ unsigned int idx;
+};

struct hist_field {
struct ftrace_event_field *field;
@@ -40,6 +47,7 @@ struct hist_field {
unsigned int is_signed;
struct hist_field *operands[HIST_FIELD_OPERANDS_MAX];
struct hist_trigger_data *hist_data;
+ struct hist_var var;
};

static u64 hist_field_none(struct hist_field *field, void *event,
@@ -138,6 +146,8 @@ enum hist_field_flags {
HIST_FIELD_FL_LOG2 = 512,
HIST_FIELD_FL_TIMESTAMP = 1024,
HIST_FIELD_FL_TIMESTAMP_USECS = 2048,
+ HIST_FIELD_FL_VAR = 4096,
+ HIST_FIELD_FL_VAR_ONLY = 8192,
};

struct hist_trigger_attrs {
@@ -150,13 +160,18 @@ struct hist_trigger_attrs {
bool clear;
bool ts_in_usecs;
unsigned int map_bits;
+
+ char *assignment_str[TRACING_MAP_VARS_MAX];
+ unsigned int n_assignments;
};

struct hist_trigger_data {
- struct hist_field *fields[TRACING_MAP_FIELDS_MAX];
+ struct hist_field *fields[HIST_FIELDS_MAX];
unsigned int n_vals;
unsigned int n_keys;
unsigned int n_fields;
+ unsigned int n_vars;
+ unsigned int n_var_only;
unsigned int key_size;
struct tracing_map_sort_key sort_keys[TRACING_MAP_SORT_KEYS_MAX];
unsigned int n_sort_keys;
@@ -164,6 +179,7 @@ struct hist_trigger_data {
struct hist_trigger_attrs *attrs;
struct tracing_map *map;
bool enable_timestamps;
+ bool remove;
};

static u64 hist_field_timestamp(struct hist_field *hist_field, void *event,
@@ -262,9 +278,14 @@ static int parse_map_size(char *str)

static void destroy_hist_trigger_attrs(struct hist_trigger_attrs *attrs)
{
+ unsigned int i;
+
if (!attrs)
return;

+ for (i = 0; i < attrs->n_assignments; i++)
+ kfree(attrs->assignment_str[i]);
+
kfree(attrs->name);
kfree(attrs->sort_key_str);
kfree(attrs->keys_str);
@@ -295,8 +316,22 @@ static int parse_assignment(char *str, struct hist_trigger_attrs *attrs)
goto out;
}
attrs->map_bits = map_bits;
- } else
- ret = -EINVAL;
+ } else {
+ char *assignment;
+
+ if (attrs->n_assignments == TRACING_MAP_VARS_MAX) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ assignment = kstrdup(str, GFP_KERNEL);
+ if (!assignment) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ attrs->assignment_str[attrs->n_assignments++] = assignment;
+ }
out:
return ret;
}
@@ -423,12 +458,15 @@ static void destroy_hist_field(struct hist_field *hist_field,
for (i = 0; i < HIST_FIELD_OPERANDS_MAX; i++)
destroy_hist_field(hist_field->operands[i], ++level);

+ kfree(hist_field->var.name);
+
kfree(hist_field);
}

static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
struct ftrace_event_field *field,
- unsigned long flags)
+ unsigned long flags,
+ char *var_name)
{
struct hist_field *hist_field;

@@ -454,7 +492,7 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
if (flags & HIST_FIELD_FL_LOG2) {
unsigned long fl = flags & ~HIST_FIELD_FL_LOG2;
hist_field->fn = hist_field_log2;
- hist_field->operands[0] = create_hist_field(hist_data, field, fl);
+ hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
hist_field->size = hist_field->operands[0]->size;
goto out;
}
@@ -489,14 +527,23 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
hist_field->field = field;
hist_field->flags = flags;

+ if (var_name) {
+ hist_field->var.name = kstrdup(var_name, GFP_KERNEL);
+ if (!hist_field->var.name)
+ goto free;
+ }
+
return hist_field;
+ free:
+ destroy_hist_field(hist_field, 0);
+ return NULL;
}

static void destroy_hist_fields(struct hist_trigger_data *hist_data)
{
unsigned int i;

- for (i = 0; i < TRACING_MAP_FIELDS_MAX; i++) {
+ for (i = 0; i < HIST_FIELDS_MAX; i++) {
if (hist_data->fields[i]) {
destroy_hist_field(hist_data->fields[i], 0);
hist_data->fields[i] = NULL;
@@ -507,11 +554,12 @@ static void destroy_hist_fields(struct hist_trigger_data *hist_data)
static int create_hitcount_val(struct hist_trigger_data *hist_data)
{
hist_data->fields[HITCOUNT_IDX] =
- create_hist_field(hist_data, NULL, HIST_FIELD_FL_HITCOUNT);
+ create_hist_field(hist_data, NULL, HIST_FIELD_FL_HITCOUNT, NULL);
if (!hist_data->fields[HITCOUNT_IDX])
return -ENOMEM;

hist_data->n_vals++;
+ hist_data->n_fields++;

if (WARN_ON(hist_data->n_vals > TRACING_MAP_VALS_MAX))
return -EINVAL;
@@ -519,19 +567,81 @@ static int create_hitcount_val(struct hist_trigger_data *hist_data)
return 0;
}

+static struct hist_field *find_var_field(struct hist_trigger_data *hist_data,
+ const char *var_name)
+{
+ struct hist_field *hist_field, *found = NULL;
+ int i;
+
+ for_each_hist_field(i, hist_data) {
+ hist_field = hist_data->fields[i];
+ if (hist_field && hist_field->flags & HIST_FIELD_FL_VAR &&
+ strcmp(hist_field->var.name, var_name) == 0) {
+ found = hist_field;
+ break;
+ }
+ }
+
+ return found;
+}
+
+static struct hist_field *find_var(struct trace_event_file *file,
+ const char *var_name)
+{
+ struct hist_trigger_data *hist_data;
+ struct event_trigger_data *test;
+ struct hist_field *hist_field;
+
+ list_for_each_entry_rcu(test, &file->triggers, list) {
+ if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) {
+ hist_data = test->private_data;
+ hist_field = find_var_field(hist_data, var_name);
+ if (hist_field)
+ return hist_field;
+ }
+ }
+
+ return NULL;
+}
+
static int create_val_field(struct hist_trigger_data *hist_data,
unsigned int val_idx,
struct trace_event_file *file,
- char *field_str)
+ char *field_str, bool var_only)
{
struct ftrace_event_field *field = NULL;
+ char *field_name, *var_name;
unsigned long flags = 0;
- char *field_name;
int ret = 0;

- if (WARN_ON(val_idx >= TRACING_MAP_VALS_MAX))
+ if (WARN_ON(!var_only && val_idx >= TRACING_MAP_VALS_MAX))
return -EINVAL;

+ var_name = strsep(&field_str, "=");
+ if (field_str && var_name) {
+ if (find_var(file, var_name) &&
+ !hist_data->remove) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ flags |= HIST_FIELD_FL_VAR;
+ hist_data->n_vars++;
+ if (hist_data->n_vars > TRACING_MAP_VARS_MAX) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (var_only)
+ flags |= HIST_FIELD_FL_VAR_ONLY;
+ } else if (!var_only && var_name != NULL && field_str == NULL) {
+ field_str = var_name;
+ var_name = NULL;
+ } else {
+ ret = -EINVAL;
+ goto out;
+ }
+
field_name = strsep(&field_str, ".");
if (field_str) {
if (strcmp(field_str, "hex") == 0)
@@ -553,15 +663,19 @@ static int create_val_field(struct hist_trigger_data *hist_data,
}
}

- hist_data->fields[val_idx] = create_hist_field(hist_data, field, flags);
+ hist_data->fields[val_idx] = create_hist_field(hist_data, field, flags, var_name);
if (!hist_data->fields[val_idx]) {
ret = -ENOMEM;
goto out;
}

++hist_data->n_vals;
+ ++hist_data->n_fields;

- if (WARN_ON(hist_data->n_vals > TRACING_MAP_VALS_MAX))
+ if (hist_data->fields[val_idx]->flags & HIST_FIELD_FL_VAR_ONLY)
+ hist_data->n_var_only++;
+
+ if (WARN_ON(hist_data->n_vals > TRACING_MAP_VALS_MAX + TRACING_MAP_VARS_MAX))
ret = -EINVAL;
out:
return ret;
@@ -571,7 +685,7 @@ static int create_val_fields(struct hist_trigger_data *hist_data,
struct trace_event_file *file)
{
char *fields_str, *field_str;
- unsigned int i, j;
+ unsigned int i, j = 1;
int ret;

ret = create_hitcount_val(hist_data);
@@ -591,12 +705,15 @@ static int create_val_fields(struct hist_trigger_data *hist_data,
field_str = strsep(&fields_str, ",");
if (!field_str)
break;
+
if (strcmp(field_str, "hitcount") == 0)
continue;
- ret = create_val_field(hist_data, j++, file, field_str);
+
+ ret = create_val_field(hist_data, j++, file, field_str, false);
if (ret)
goto out;
}
+
if (fields_str && (strcmp(fields_str, "hitcount") != 0))
ret = -EINVAL;
out:
@@ -610,18 +727,32 @@ static int create_key_field(struct hist_trigger_data *hist_data,
char *field_str)
{
struct ftrace_event_field *field = NULL;
+ struct hist_field *hist_field = NULL;
unsigned long flags = 0;
unsigned int key_size;
+ char *var_name;
int ret = 0;

- if (WARN_ON(key_idx >= TRACING_MAP_FIELDS_MAX))
+ if (WARN_ON(key_idx >= HIST_FIELDS_MAX))
return -EINVAL;

flags |= HIST_FIELD_FL_KEY;

+ var_name = strsep(&field_str, "=");
+ if (field_str) {
+ if (find_var(file, var_name) &&
+ !hist_data->remove)
+ return -EINVAL;
+ flags |= HIST_FIELD_FL_VAR;
+ } else {
+ field_str = var_name;
+ var_name = NULL;
+ }
+
if (strcmp(field_str, "stacktrace") == 0) {
flags |= HIST_FIELD_FL_STACKTRACE;
key_size = sizeof(unsigned long) * HIST_STACKTRACE_DEPTH;
+ hist_field = create_hist_field(hist_data, NULL, flags, var_name);
} else {
char *field_name = strsep(&field_str, ".");

@@ -667,7 +798,7 @@ static int create_key_field(struct hist_trigger_data *hist_data,
}
}

- hist_data->fields[key_idx] = create_hist_field(hist_data, field, flags);
+ hist_data->fields[key_idx] = create_hist_field(hist_data, field, flags, var_name);
if (!hist_data->fields[key_idx]) {
ret = -ENOMEM;
goto out;
@@ -683,6 +814,7 @@ static int create_key_field(struct hist_trigger_data *hist_data,
}

hist_data->n_keys++;
+ hist_data->n_fields++;

if (WARN_ON(hist_data->n_keys > TRACING_MAP_KEYS_MAX))
return -EINVAL;
@@ -726,6 +858,29 @@ static int create_key_fields(struct hist_trigger_data *hist_data,
return ret;
}

+static int create_var_fields(struct hist_trigger_data *hist_data,
+ struct trace_event_file *file)
+{
+ unsigned int i, j, k = hist_data->n_vals;
+ char *str, *field_str;
+ int ret = 0;
+
+ for (i = 0; i < hist_data->attrs->n_assignments; i++) {
+ str = hist_data->attrs->assignment_str[i];
+
+ for (j = 0; j < TRACING_MAP_VARS_MAX; j++) {
+ field_str = strsep(&str, ",");
+ if (!field_str)
+ break;
+ ret = create_val_field(hist_data, k++, file, field_str, true);
+ if (ret)
+ goto out;
+ }
+ }
+ out:
+ return ret;
+}
+
static int create_hist_fields(struct hist_trigger_data *hist_data,
struct trace_event_file *file)
{
@@ -735,11 +890,13 @@ static int create_hist_fields(struct hist_trigger_data *hist_data,
if (ret)
goto out;

- ret = create_key_fields(hist_data, file);
+ ret = create_var_fields(hist_data, file);
if (ret)
goto out;

- hist_data->n_fields = hist_data->n_vals + hist_data->n_keys;
+ ret = create_key_fields(hist_data, file);
+ if (ret)
+ goto out;
out:
return ret;
}
@@ -763,7 +920,7 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
char *fields_str = hist_data->attrs->sort_key_str;
struct tracing_map_sort_key *sort_key;
int descending, ret = 0;
- unsigned int i, j;
+ unsigned int i, j, k;

hist_data->n_sort_keys = 1; /* we always have at least one, hitcount */

@@ -811,13 +968,21 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
continue;
}

- for (j = 1; j < hist_data->n_fields; j++) {
+ for (j = 1, k = 1; j < hist_data->n_fields; j++) {
+ unsigned idx;
+
hist_field = hist_data->fields[j];
+ if (hist_field->flags & HIST_FIELD_FL_VAR_ONLY)
+ continue;
+
+ idx = k++;
+
test_name = hist_field_name(hist_field, 0);
+
if (test_name == NULL)
continue;
if (strcmp(field_name, test_name) == 0) {
- sort_key->field_idx = j;
+ sort_key->field_idx = idx;
descending = is_descending(field_str);
if (descending < 0) {
ret = descending;
@@ -832,6 +997,7 @@ static int create_sort_keys(struct hist_trigger_data *hist_data)
break;
}
}
+
hist_data->n_sort_keys = i;
out:
return ret;
@@ -872,12 +1038,19 @@ static int create_tracing_map_fields(struct hist_trigger_data *hist_data)
idx = tracing_map_add_key_field(map,
hist_field->offset,
cmp_fn);
-
- } else
+ } else if (!(hist_field->flags & HIST_FIELD_FL_VAR))
idx = tracing_map_add_sum_field(map);

if (idx < 0)
return idx;
+
+ if (hist_field->flags & HIST_FIELD_FL_VAR) {
+ idx = tracing_map_add_var(map);
+ if (idx < 0)
+ return idx;
+ hist_field->var.idx = idx;
+ hist_field->var.hist_data = hist_data;
+ }
}

return 0;
@@ -901,7 +1074,8 @@ static bool need_tracing_map_ops(struct hist_trigger_data *hist_data)
static struct hist_trigger_data *
create_hist_data(unsigned int map_bits,
struct hist_trigger_attrs *attrs,
- struct trace_event_file *file)
+ struct trace_event_file *file,
+ bool remove)
{
const struct tracing_map_ops *map_ops = NULL;
struct hist_trigger_data *hist_data;
@@ -912,6 +1086,7 @@ static bool need_tracing_map_ops(struct hist_trigger_data *hist_data)
return ERR_PTR(-ENOMEM);

hist_data->attrs = attrs;
+ hist_data->remove = remove;

ret = create_hist_fields(hist_data, file);
if (ret)
@@ -958,14 +1133,29 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
struct ring_buffer_event *rbe)
{
struct hist_field *hist_field;
- unsigned int i;
+ unsigned int i, var_idx;
u64 hist_val;

for_each_hist_val_field(i, hist_data) {
hist_field = hist_data->fields[i];
- hist_val = hist_field->fn(hist_field, rec, rbe);
+ hist_val = hist_field->fn(hist_field, rbe, rec);
+ if (hist_field->flags & HIST_FIELD_FL_VAR) {
+ var_idx = hist_field->var.idx;
+ tracing_map_set_var(elt, var_idx, hist_val);
+ if (hist_field->flags & HIST_FIELD_FL_VAR_ONLY)
+ continue;
+ }
tracing_map_update_sum(elt, i, hist_val);
}
+
+ for_each_hist_key_field(i, hist_data) {
+ hist_field = hist_data->fields[i];
+ if (hist_field->flags & HIST_FIELD_FL_VAR) {
+ hist_val = hist_field->fn(hist_field, rbe, rec);
+ var_idx = hist_field->var.idx;
+ tracing_map_set_var(elt, var_idx, hist_val);
+ }
+ }
}

static inline void add_to_key(char *compound_key, void *key,
@@ -1140,6 +1330,9 @@ static void hist_trigger_stacktrace_print(struct seq_file *m,
for (i = 1; i < hist_data->n_vals; i++) {
field_name = hist_field_name(hist_data->fields[i], 0);

+ if (hist_data->fields[i]->flags & HIST_FIELD_FL_VAR)
+ continue;
+
if (hist_data->fields[i]->flags & HIST_FIELD_FL_HEX) {
seq_printf(m, " %s: %10llx", field_name,
tracing_map_read_sum(elt, i));
@@ -1263,6 +1456,9 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
{
const char *field_name = hist_field_name(hist_field, 0);

+ if (hist_field->var.name)
+ seq_printf(m, "%s=", hist_field->var.name);
+
if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP)
seq_puts(m, "$common_timestamp");
else if (field_name)
@@ -1281,7 +1477,8 @@ static int event_hist_trigger_print(struct seq_file *m,
struct event_trigger_data *data)
{
struct hist_trigger_data *hist_data = data->private_data;
- struct hist_field *key_field;
+ bool have_var_only = false;
+ struct hist_field *field;
unsigned int i;

seq_puts(m, "hist:");
@@ -1292,25 +1489,47 @@ static int event_hist_trigger_print(struct seq_file *m,
seq_puts(m, "keys=");

for_each_hist_key_field(i, hist_data) {
- key_field = hist_data->fields[i];
+ field = hist_data->fields[i];

if (i > hist_data->n_vals)
seq_puts(m, ",");

- if (key_field->flags & HIST_FIELD_FL_STACKTRACE)
+ if (field->flags & HIST_FIELD_FL_STACKTRACE)
seq_puts(m, "stacktrace");
else
- hist_field_print(m, key_field);
+ hist_field_print(m, field);
}

seq_puts(m, ":vals=");

for_each_hist_val_field(i, hist_data) {
+ field = hist_data->fields[i];
+ if (field->flags & HIST_FIELD_FL_VAR_ONLY) {
+ have_var_only = true;
+ continue;
+ }
+
if (i == HITCOUNT_IDX)
seq_puts(m, "hitcount");
else {
seq_puts(m, ",");
- hist_field_print(m, hist_data->fields[i]);
+ hist_field_print(m, field);
+ }
+ }
+
+ if (have_var_only) {
+ unsigned int n = 0;
+
+ seq_puts(m, ":");
+
+ for_each_hist_val_field(i, hist_data) {
+ field = hist_data->fields[i];
+
+ if (field->flags & HIST_FIELD_FL_VAR_ONLY) {
+ if (n++)
+ seq_puts(m, ",");
+ hist_field_print(m, field);
+ }
}
}

@@ -1318,7 +1537,10 @@ static int event_hist_trigger_print(struct seq_file *m,

for (i = 0; i < hist_data->n_sort_keys; i++) {
struct tracing_map_sort_key *sort_key;
- unsigned int idx;
+ unsigned int idx, first_key_idx;
+
+ /* skip VAR_ONLY vals */
+ first_key_idx = hist_data->n_vals - hist_data->n_var_only;

sort_key = &hist_data->sort_keys[i];
idx = sort_key->field_idx;
@@ -1331,8 +1553,11 @@ static int event_hist_trigger_print(struct seq_file *m,

if (idx == HITCOUNT_IDX)
seq_puts(m, "hitcount");
- else
+ else {
+ if (idx >= first_key_idx)
+ idx += hist_data->n_var_only;
hist_field_print(m, hist_data->fields[idx]);
+ }

if (sort_key->descending)
seq_puts(m, ".descending");
@@ -1656,12 +1881,16 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
struct hist_trigger_attrs *attrs;
struct event_trigger_ops *trigger_ops;
struct hist_trigger_data *hist_data;
+ bool remove = false;
char *trigger;
int ret = 0;

if (!param)
return -EINVAL;

+ if (glob[0] == '!')
+ remove = true;
+
/* separate the trigger from the filter (k:v [if filter]) */
trigger = strsep(&param, " \t");
if (!trigger)
@@ -1674,7 +1903,7 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
if (attrs->map_bits)
hist_trigger_bits = attrs->map_bits;

- hist_data = create_hist_data(hist_trigger_bits, attrs, file);
+ hist_data = create_hist_data(hist_trigger_bits, attrs, file, remove);
if (IS_ERR(hist_data)) {
destroy_hist_trigger_attrs(attrs);
return PTR_ERR(hist_data);
@@ -1703,7 +1932,7 @@ static int event_hist_trigger_func(struct event_command *cmd_ops,
goto out_free;
}

- if (glob[0] == '!') {
+ if (remove) {
cmd_ops->unreg(glob+1, trigger_ops, trigger_data, file);
ret = 0;
goto out_free;
--
1.9.3