#include <trace/events/sched.h>
+#include <asm/sections.h>
#include <asm/setup.h>
#include "trace_output.h"
struct ftrace_func_probe {
struct hlist_node node;
struct ftrace_probe_ops *ops;
- unsigned long flags;
unsigned long ip;
void *data;
struct list_head free_list;
* callers are done before leaving this function.
* The same goes for freeing the per_cpu data of the per_cpu
* ops.
- *
- * Again, normal synchronize_sched() is not good enough.
- * We need to do a hard force of sched synchronization.
- * This is because we use preempt_disable() to do RCU, but
- * the function tracers can be called where RCU is not watching
- * (like before user_exit()). We can not rely on the RCU
- * infrastructure to do the synchronization, thus we must do it
- * ourselves.
*/
if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU)) {
+ /*
+ * We need to do a hard force of sched synchronization.
+ * This is because we use preempt_disable() to do RCU, but
+ * the function tracers can be called where RCU is not watching
+ * (like before user_exit()). We can not rely on the RCU
+ * infrastructure to do the synchronization, thus we must do it
+ * ourselves.
+ */
schedule_on_each_cpu(ftrace_sync);
+ /*
+ * When the kernel is preeptive, tasks can be preempted
+ * while on a ftrace trampoline. Just scheduling a task on
+ * a CPU is not good enough to flush them. Calling
+ * synchornize_rcu_tasks() will wait for those tasks to
+ * execute and either schedule voluntarily or enter user space.
+ */
+ if (IS_ENABLED(CONFIG_PREEMPT))
+ synchronize_rcu_tasks();
+
arch_ftrace_trampoline_free(ops);
if (ops->flags & FTRACE_OPS_FL_PER_CPU)
}
static void *
-t_next(struct seq_file *m, void *v, loff_t *pos)
+t_func_next(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
- struct ftrace_ops *ops = iter->ops;
struct dyn_ftrace *rec = NULL;
- if (unlikely(ftrace_disabled))
- return NULL;
-
- if (iter->flags & FTRACE_ITER_HASH)
- return t_hash_next(m, pos);
-
(*pos)++;
- iter->pos = iter->func_pos = *pos;
-
- if (iter->flags & FTRACE_ITER_PRINTALL)
- return t_hash_start(m, pos);
retry:
if (iter->idx >= iter->pg->index) {
}
} else {
rec = &iter->pg->records[iter->idx++];
- if (((iter->flags & FTRACE_ITER_FILTER) &&
- !(ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))) ||
-
- ((iter->flags & FTRACE_ITER_NOTRACE) &&
- !ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip)) ||
+ if (((iter->flags & (FTRACE_ITER_FILTER | FTRACE_ITER_NOTRACE)) &&
+ !ftrace_lookup_ip(iter->hash, rec->ip)) ||
((iter->flags & FTRACE_ITER_ENABLED) &&
!(rec->flags & FTRACE_FL_ENABLED))) {
}
if (!rec)
- return t_hash_start(m, pos);
+ return NULL;
+ iter->pos = iter->func_pos = *pos;
iter->func = rec;
return iter;
}
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct ftrace_iterator *iter = m->private;
+ loff_t l = *pos; /* t_hash_start() must use original pos */
+ void *ret;
+
+ if (unlikely(ftrace_disabled))
+ return NULL;
+
+ if (iter->flags & FTRACE_ITER_HASH)
+ return t_hash_next(m, pos);
+
+ if (iter->flags & FTRACE_ITER_PRINTALL) {
+ /* next must increment pos, and t_hash_start does not */
+ (*pos)++;
+ return t_hash_start(m, &l);
+ }
+
+ ret = t_func_next(m, pos);
+
+ if (!ret)
+ return t_hash_start(m, &l);
+
+ return ret;
+}
+
static void reset_iter_read(struct ftrace_iterator *iter)
{
iter->pos = 0;
static void *t_start(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
- struct ftrace_ops *ops = iter->ops;
void *p = NULL;
loff_t l;
* off, we can short cut and just print out that all
* functions are enabled.
*/
- if ((iter->flags & FTRACE_ITER_FILTER &&
- ftrace_hash_empty(ops->func_hash->filter_hash)) ||
- (iter->flags & FTRACE_ITER_NOTRACE &&
- ftrace_hash_empty(ops->func_hash->notrace_hash))) {
+ if ((iter->flags & (FTRACE_ITER_FILTER | FTRACE_ITER_NOTRACE)) &&
+ ftrace_hash_empty(iter->hash)) {
+ iter->func_pos = 1; /* Account for the message */
if (*pos > 0)
return t_hash_start(m, pos);
iter->flags |= FTRACE_ITER_PRINTALL;
iter->pg = ftrace_pages_start;
iter->idx = 0;
for (l = 0; l <= *pos; ) {
- p = t_next(m, p, &l);
+ p = t_func_next(m, &l);
if (!p)
break;
}
return -ENODEV;
iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
- if (iter) {
- iter->pg = ftrace_pages_start;
- iter->ops = &global_ops;
- }
+ if (!iter)
+ return -ENOMEM;
+
+ iter->pg = ftrace_pages_start;
+ iter->ops = &global_ops;
- return iter ? 0 : -ENOMEM;
+ return 0;
}
static int
struct ftrace_iterator *iter;
iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
- if (iter) {
- iter->pg = ftrace_pages_start;
- iter->flags = FTRACE_ITER_ENABLED;
- iter->ops = &global_ops;
- }
+ if (!iter)
+ return -ENOMEM;
+
+ iter->pg = ftrace_pages_start;
+ iter->flags = FTRACE_ITER_ENABLED;
+ iter->ops = &global_ops;
- return iter ? 0 : -ENOMEM;
+ return 0;
}
/**
ret = -ENOMEM;
goto out_unlock;
}
- }
+ } else
+ iter->hash = hash;
if (file->f_mode & FMODE_READ) {
iter->pg = ftrace_pages_start;
preempt_disable_notrace();
hlist_for_each_entry_rcu_notrace(entry, hhd, node) {
if (entry->ip == ip)
- entry->ops->func(ip, parent_ip, &entry->data);
+ entry->ops->func(ip, parent_ip, entry->ops, &entry->data);
}
preempt_enable_notrace();
}
ftrace_probe_registered = 1;
}
-static void __disable_ftrace_function_probe(void)
+static bool __disable_ftrace_function_probe(void)
{
int i;
if (!ftrace_probe_registered)
- return;
+ return false;
for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
struct hlist_head *hhd = &ftrace_func_hash[i];
if (hhd->first)
- return;
+ return false;
}
/* no more funcs left */
ftrace_shutdown(&trace_probe_ops, 0);
ftrace_probe_registered = 0;
+ return true;
}
kfree(entry);
}
+struct ftrace_func_map {
+ struct ftrace_func_entry entry;
+ void *data;
+};
+
+struct ftrace_func_mapper {
+ struct ftrace_hash hash;
+};
+
+/**
+ * allocate_ftrace_func_mapper - allocate a new ftrace_func_mapper
+ *
+ * Returns a ftrace_func_mapper descriptor that can be used to map ips to data.
+ */
+struct ftrace_func_mapper *allocate_ftrace_func_mapper(void)
+{
+ struct ftrace_hash *hash;
+
+ /*
+ * The mapper is simply a ftrace_hash, but since the entries
+ * in the hash are not ftrace_func_entry type, we define it
+ * as a separate structure.
+ */
+ hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
+ return (struct ftrace_func_mapper *)hash;
+}
+
+/**
+ * ftrace_func_mapper_find_ip - Find some data mapped to an ip
+ * @mapper: The mapper that has the ip maps
+ * @ip: the instruction pointer to find the data for
+ *
+ * Returns the data mapped to @ip if found otherwise NULL. The return
+ * is actually the address of the mapper data pointer. The address is
+ * returned for use cases where the data is no bigger than a long, and
+ * the user can use the data pointer as its data instead of having to
+ * allocate more memory for the reference.
+ */
+void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper,
+ unsigned long ip)
+{
+ struct ftrace_func_entry *entry;
+ struct ftrace_func_map *map;
+
+ entry = ftrace_lookup_ip(&mapper->hash, ip);
+ if (!entry)
+ return NULL;
+
+ map = (struct ftrace_func_map *)entry;
+ return &map->data;
+}
+
+/**
+ * ftrace_func_mapper_add_ip - Map some data to an ip
+ * @mapper: The mapper that has the ip maps
+ * @ip: The instruction pointer address to map @data to
+ * @data: The data to map to @ip
+ *
+ * Returns 0 on succes otherwise an error.
+ */
+int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
+ unsigned long ip, void *data)
+{
+ struct ftrace_func_entry *entry;
+ struct ftrace_func_map *map;
+
+ entry = ftrace_lookup_ip(&mapper->hash, ip);
+ if (entry)
+ return -EBUSY;
+
+ map = kmalloc(sizeof(*map), GFP_KERNEL);
+ if (!map)
+ return -ENOMEM;
+
+ map->entry.ip = ip;
+ map->data = data;
+
+ __add_hash_entry(&mapper->hash, &map->entry);
+
+ return 0;
+}
+
+/**
+ * ftrace_func_mapper_remove_ip - Remove an ip from the mapping
+ * @mapper: The mapper that has the ip maps
+ * @ip: The instruction pointer address to remove the data from
+ *
+ * Returns the data if it is found, otherwise NULL.
+ * Note, if the data pointer is used as the data itself, (see
+ * ftrace_func_mapper_find_ip(), then the return value may be meaningless,
+ * if the data pointer was set to zero.
+ */
+void *ftrace_func_mapper_remove_ip(struct ftrace_func_mapper *mapper,
+ unsigned long ip)
+{
+ struct ftrace_func_entry *entry;
+ struct ftrace_func_map *map;
+ void *data;
+
+ entry = ftrace_lookup_ip(&mapper->hash, ip);
+ if (!entry)
+ return NULL;
+
+ map = (struct ftrace_func_map *)entry;
+ data = map->data;
+
+ remove_hash_entry(&mapper->hash, entry);
+ kfree(entry);
+
+ return data;
+}
+
+/**
+ * free_ftrace_func_mapper - free a mapping of ips and data
+ * @mapper: The mapper that has the ip maps
+ * @free_func: A function to be called on each data item.
+ *
+ * This is used to free the function mapper. The @free_func is optional
+ * and can be used if the data needs to be freed as well.
+ */
+void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper,
+ ftrace_mapper_func free_func)
+{
+ struct ftrace_func_entry *entry;
+ struct ftrace_func_map *map;
+ struct hlist_head *hhd;
+ int size = 1 << mapper->hash.size_bits;
+ int i;
+
+ if (free_func && mapper->hash.count) {
+ for (i = 0; i < size; i++) {
+ hhd = &mapper->hash.buckets[i];
+ hlist_for_each_entry(entry, hhd, hlist) {
+ map = (struct ftrace_func_map *)entry;
+ free_func(map);
+ }
+ }
+ }
+ free_ftrace_hash(&mapper->hash);
+}
+
int
register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
void *data)
__unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
void *data, int flags)
{
+ struct ftrace_ops_hash old_hash_ops;
struct ftrace_func_entry *rec_entry;
struct ftrace_func_probe *entry;
struct ftrace_func_probe *p;
struct hlist_node *tmp;
char str[KSYM_SYMBOL_LEN];
int i, ret;
+ bool disabled;
if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
func_g.search = NULL;
mutex_lock(&trace_probe_ops.func_hash->regex_lock);
+ old_hash_ops.filter_hash = old_hash;
+ /* Probes only have filters */
+ old_hash_ops.notrace_hash = NULL;
+
hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
if (!hash)
/* Hmm, should report this somehow */
}
}
mutex_lock(&ftrace_lock);
- __disable_ftrace_function_probe();
+ disabled = __disable_ftrace_function_probe();
/*
* Remove after the disable is called. Otherwise, if the last
* probe is removed, a null hash means *all enabled*.
*/
ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+
+ /* still need to update the function call sites */
+ if (ftrace_enabled && !disabled)
+ ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS,
+ &old_hash_ops);
synchronize_sched();
if (!ret)
free_ftrace_hash_rcu(old_hash);
free_ftrace_hash_rcu(old_hash);
}
mutex_unlock(&ftrace_lock);
+ } else {
+ /* For read only, the hash is the ops hash */
+ iter->hash = NULL;
}
mutex_unlock(&iter->ops->func_hash->regex_lock);
}
#endif /* CONFIG_MODULES */
+void __init ftrace_free_init_mem(void)
+{
+ unsigned long start = (unsigned long)(&__init_begin);
+ unsigned long end = (unsigned long)(&__init_end);
+ struct ftrace_page **last_pg = &ftrace_pages_start;
+ struct ftrace_page *pg;
+ struct dyn_ftrace *rec;
+ struct dyn_ftrace key;
+ int order;
+
+ key.ip = start;
+ key.flags = end; /* overload flags, as it is unsigned long */
+
+ mutex_lock(&ftrace_lock);
+
+ for (pg = ftrace_pages_start; pg; last_pg = &pg->next, pg = *last_pg) {
+ if (end < pg->records[0].ip ||
+ start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE))
+ continue;
+ again:
+ rec = bsearch(&key, pg->records, pg->index,
+ sizeof(struct dyn_ftrace),
+ ftrace_cmp_recs);
+ if (!rec)
+ continue;
+ pg->index--;
+ if (!pg->index) {
+ *last_pg = pg->next;
+ order = get_count_order(pg->size / ENTRIES_PER_PAGE);
+ free_pages((unsigned long)pg->records, order);
+ kfree(pg);
+ pg = container_of(last_pg, struct ftrace_page, next);
+ if (!(*last_pg))
+ ftrace_pages = pg;
+ continue;
+ }
+ memmove(rec, rec + 1,
+ (pg->index - (rec - pg->records)) * sizeof(*rec));
+ /* More than one function may be in this block */
+ goto again;
+ }
+ mutex_unlock(&ftrace_lock);
+}
+
void __init ftrace_init(void)
{
extern unsigned long __start_mcount_loc[];
static void ftrace_update_trampoline(struct ftrace_ops *ops)
{
-
-/*
- * Currently there's no safe way to free a trampoline when the kernel
- * is configured with PREEMPT. That is because a task could be preempted
- * when it jumped to the trampoline, it may be preempted for a long time
- * depending on the system load, and currently there's no way to know
- * when it will be off the trampoline. If the trampoline is freed
- * too early, when the task runs again, it will be executing on freed
- * memory and crash.
- */
-#ifdef CONFIG_PREEMPT
- /* Currently, only non dynamic ops can have a trampoline */
- if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
- return;
-#endif
-
arch_ftrace_update_trampoline(ops);
}
trace_ignore_this_task(pid_list, next));
}
+static void
+ftrace_pid_follow_sched_process_fork(void *data,
+ struct task_struct *self,
+ struct task_struct *task)
+{
+ struct trace_pid_list *pid_list;
+ struct trace_array *tr = data;
+
+ pid_list = rcu_dereference_sched(tr->function_pids);
+ trace_filter_add_remove_task(pid_list, self, task);
+}
+
+static void
+ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task)
+{
+ struct trace_pid_list *pid_list;
+ struct trace_array *tr = data;
+
+ pid_list = rcu_dereference_sched(tr->function_pids);
+ trace_filter_add_remove_task(pid_list, NULL, task);
+}
+
+void ftrace_pid_follow_fork(struct trace_array *tr, bool enable)
+{
+ if (enable) {
+ register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
+ tr);
+ register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+ tr);
+ } else {
+ unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
+ tr);
+ unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+ tr);
+ }
+}
+
static void clear_ftrace_pids(struct trace_array *tr)
{
struct trace_pid_list *pid_list;
projects / linux.git / blobdiff