Commit 79b17ea7 authored by Linus Torvalds's avatar Linus Torvalds

Merge tag 'trace-v4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "This release has no new tracing features, just clean ups, minor fixes
  and small optimizations"

* tag 'trace-v4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (25 commits)
  tracing: Remove outdated ring buffer comment
  tracing/probes: Fix a warning message to show correct maximum length
  tracing: Fix return value check in trace_benchmark_reg()
  tracing: Use modern function declaration
  jump_label: Reduce the size of struct static_key
  tracing/probe: Show subsystem name in messages
  tracing/hwlat: Update old comment about migration
  timers: Make flags output in the timer_start tracepoint useful
  tracing: Have traceprobe_probes_write() not access userspace unnecessarily
  tracing: Have COMM event filter key be treated as a string
  ftrace: Have set_graph_function handle multiple functions in one write
  ftrace: Do not hold references of ftrace_graph_{notrace_}hash out of graph_lock
  tracing: Reset parser->buffer to allow multiple "puts"
  ftrace: Have set_graph_functions handle write with RDWR
  ftrace: Reset fgd->hash in ftrace_graph_write()
  ftrace: Replace (void *)1 with a meaningful macro name FTRACE_GRAPH_EMPTY
  ftrace: Create a slight optimization on searching the ftrace_hash
  tracing: Add ftrace_hash_key() helper function
  ftrace: Convert graph filter to use hash tables
  ftrace: Expose ftrace_hash_empty and ftrace_lookup_ip
  ...
parents e5d56efc 67d04bb2
......@@ -155,7 +155,9 @@ or:
There are a few functions and macros that architectures must implement in order
to take advantage of this optimization. If there is no architecture support, we
simply fall back to a traditional, load, test, and jump sequence.
simply fall back to a traditional, load, test, and jump sequence. Also, the
struct jump_entry table must be at least 4-byte aligned because the
static_key->entry field makes use of the two least significant bits.
* select HAVE_ARCH_JUMP_LABEL, see: arch/x86/Kconfig
......
......@@ -105,29 +105,36 @@ struct ftrace_branch_data {
};
};
struct ftrace_likely_data {
struct ftrace_branch_data data;
unsigned long constant;
};
/*
* Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code
* to disable branch tracing on a per file basis.
*/
#if defined(CONFIG_TRACE_BRANCH_PROFILING) \
&& !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__)
void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
void ftrace_likely_update(struct ftrace_likely_data *f, int val,
int expect, int is_constant);
#define likely_notrace(x) __builtin_expect(!!(x), 1)
#define unlikely_notrace(x) __builtin_expect(!!(x), 0)
#define __branch_check__(x, expect) ({ \
#define __branch_check__(x, expect, is_constant) ({ \
int ______r; \
static struct ftrace_branch_data \
static struct ftrace_likely_data \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_annotated_branch"))) \
______f = { \
.func = __func__, \
.file = __FILE__, \
.line = __LINE__, \
.data.func = __func__, \
.data.file = __FILE__, \
.data.line = __LINE__, \
}; \
______r = likely_notrace(x); \
ftrace_likely_update(&______f, ______r, expect); \
______r = __builtin_expect(!!(x), expect); \
ftrace_likely_update(&______f, ______r, \
expect, is_constant); \
______r; \
})
......@@ -137,10 +144,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
* written by Daniel Walker.
*/
# ifndef likely
# define likely(x) (__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 1))
# define likely(x) (__branch_check__(x, 1, __builtin_constant_p(x)))
# endif
# ifndef unlikely
# define unlikely(x) (__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 0))
# define unlikely(x) (__branch_check__(x, 0, __builtin_constant_p(x)))
# endif
#ifdef CONFIG_PROFILE_ALL_BRANCHES
......
......@@ -89,11 +89,17 @@ extern bool static_key_initialized;
struct static_key {
atomic_t enabled;
/* Set lsb bit to 1 if branch is default true, 0 ot */
struct jump_entry *entries;
#ifdef CONFIG_MODULES
struct static_key_mod *next;
#endif
/*
* bit 0 => 1 if key is initially true
* 0 if initially false
* bit 1 => 1 if points to struct static_key_mod
* 0 if points to struct jump_entry
*/
union {
unsigned long type;
struct jump_entry *entries;
struct static_key_mod *next;
};
};
#else
......@@ -118,9 +124,10 @@ struct module;
#ifdef HAVE_JUMP_LABEL
#define JUMP_TYPE_FALSE 0UL
#define JUMP_TYPE_TRUE 1UL
#define JUMP_TYPE_MASK 1UL
#define JUMP_TYPE_FALSE 0UL
#define JUMP_TYPE_TRUE 1UL
#define JUMP_TYPE_LINKED 2UL
#define JUMP_TYPE_MASK 3UL
static __always_inline bool static_key_false(struct static_key *key)
{
......
......@@ -61,6 +61,8 @@ struct timer_list {
#define TIMER_ARRAYSHIFT 22
#define TIMER_ARRAYMASK 0xFFC00000
#define TIMER_TRACE_FLAGMASK (TIMER_MIGRATING | TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE)
#define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \
.entry = { .next = TIMER_ENTRY_STATIC }, \
.function = (_function), \
......
......@@ -36,6 +36,13 @@ DEFINE_EVENT(timer_class, timer_init,
TP_ARGS(timer)
);
#define decode_timer_flags(flags) \
__print_flags(flags, "|", \
{ TIMER_MIGRATING, "M" }, \
{ TIMER_DEFERRABLE, "D" }, \
{ TIMER_PINNED, "P" }, \
{ TIMER_IRQSAFE, "I" })
/**
* timer_start - called when the timer is started
* @timer: pointer to struct timer_list
......@@ -65,9 +72,12 @@ TRACE_EVENT(timer_start,
__entry->flags = flags;
),
TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] flags=0x%08x",
TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s",
__entry->timer, __entry->function, __entry->expires,
(long)__entry->expires - __entry->now, __entry->flags)
(long)__entry->expires - __entry->now,
__entry->flags & TIMER_CPUMASK,
__entry->flags >> TIMER_ARRAYSHIFT,
decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK))
);
/**
......
......@@ -236,12 +236,28 @@ void __weak __init_or_module arch_jump_label_transform_static(struct jump_entry
static inline struct jump_entry *static_key_entries(struct static_key *key)
{
return (struct jump_entry *)((unsigned long)key->entries & ~JUMP_TYPE_MASK);
WARN_ON_ONCE(key->type & JUMP_TYPE_LINKED);
return (struct jump_entry *)(key->type & ~JUMP_TYPE_MASK);
}
static inline bool static_key_type(struct static_key *key)
{
return (unsigned long)key->entries & JUMP_TYPE_MASK;
return key->type & JUMP_TYPE_TRUE;
}
static inline bool static_key_linked(struct static_key *key)
{
return key->type & JUMP_TYPE_LINKED;
}
static inline void static_key_clear_linked(struct static_key *key)
{
key->type &= ~JUMP_TYPE_LINKED;
}
static inline void static_key_set_linked(struct static_key *key)
{
key->type |= JUMP_TYPE_LINKED;
}
static inline struct static_key *jump_entry_key(struct jump_entry *entry)
......@@ -254,6 +270,26 @@ static bool jump_entry_branch(struct jump_entry *entry)
return (unsigned long)entry->key & 1UL;
}
/***
* A 'struct static_key' uses a union such that it either points directly
* to a table of 'struct jump_entry' or to a linked list of modules which in
* turn point to 'struct jump_entry' tables.
*
* The two lower bits of the pointer are used to keep track of which pointer
* type is in use and to store the initial branch direction, we use an access
* function which preserves these bits.
*/
static void static_key_set_entries(struct static_key *key,
struct jump_entry *entries)
{
unsigned long type;
WARN_ON_ONCE((unsigned long)entries & JUMP_TYPE_MASK);
type = key->type & JUMP_TYPE_MASK;
key->entries = entries;
key->type |= type;
}
static enum jump_label_type jump_label_type(struct jump_entry *entry)
{
struct static_key *key = jump_entry_key(entry);
......@@ -313,13 +349,7 @@ void __init jump_label_init(void)
continue;
key = iterk;
/*
* Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
*/
*((unsigned long *)&key->entries) += (unsigned long)iter;
#ifdef CONFIG_MODULES
key->next = NULL;
#endif
static_key_set_entries(key, iter);
}
static_key_initialized = true;
jump_label_unlock();
......@@ -343,6 +373,29 @@ struct static_key_mod {
struct module *mod;
};
static inline struct static_key_mod *static_key_mod(struct static_key *key)
{
WARN_ON_ONCE(!(key->type & JUMP_TYPE_LINKED));
return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK);
}
/***
* key->type and key->next are the same via union.
* This sets key->next and preserves the type bits.
*
* See additional comments above static_key_set_entries().
*/
static void static_key_set_mod(struct static_key *key,
struct static_key_mod *mod)
{
unsigned long type;
WARN_ON_ONCE((unsigned long)mod & JUMP_TYPE_MASK);
type = key->type & JUMP_TYPE_MASK;
key->next = mod;
key->type |= type;
}
static int __jump_label_mod_text_reserved(void *start, void *end)
{
struct module *mod;
......@@ -365,11 +418,23 @@ static void __jump_label_mod_update(struct static_key *key)
{
struct static_key_mod *mod;
for (mod = key->next; mod; mod = mod->next) {
struct module *m = mod->mod;
for (mod = static_key_mod(key); mod; mod = mod->next) {
struct jump_entry *stop;
struct module *m;
/*
* NULL if the static_key is defined in a module
* that does not use it
*/
if (!mod->entries)
continue;
__jump_label_update(key, mod->entries,
m->jump_entries + m->num_jump_entries);
m = mod->mod;
if (!m)
stop = __stop___jump_table;
else
stop = m->jump_entries + m->num_jump_entries;
__jump_label_update(key, mod->entries, stop);
}
}
......@@ -404,7 +469,7 @@ static int jump_label_add_module(struct module *mod)
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
struct static_key *key = NULL;
struct static_key_mod *jlm;
struct static_key_mod *jlm, *jlm2;
/* if the module doesn't have jump label entries, just return */
if (iter_start == iter_stop)
......@@ -421,20 +486,32 @@ static int jump_label_add_module(struct module *mod)
key = iterk;
if (within_module(iter->key, mod)) {
/*
* Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
*/
*((unsigned long *)&key->entries) += (unsigned long)iter;
key->next = NULL;
static_key_set_entries(key, iter);
continue;
}
jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL);
if (!jlm)
return -ENOMEM;
if (!static_key_linked(key)) {
jlm2 = kzalloc(sizeof(struct static_key_mod),
GFP_KERNEL);
if (!jlm2) {
kfree(jlm);
return -ENOMEM;
}
preempt_disable();
jlm2->mod = __module_address((unsigned long)key);
preempt_enable();
jlm2->entries = static_key_entries(key);
jlm2->next = NULL;
static_key_set_mod(key, jlm2);
static_key_set_linked(key);
}
jlm->mod = mod;
jlm->entries = iter;
jlm->next = key->next;
key->next = jlm;
jlm->next = static_key_mod(key);
static_key_set_mod(key, jlm);
static_key_set_linked(key);
/* Only update if we've changed from our initial state */
if (jump_label_type(iter) != jump_label_init_type(iter))
......@@ -461,16 +538,34 @@ static void jump_label_del_module(struct module *mod)
if (within_module(iter->key, mod))
continue;
/* No memory during module load */
if (WARN_ON(!static_key_linked(key)))
continue;
prev = &key->next;
jlm = key->next;
jlm = static_key_mod(key);
while (jlm && jlm->mod != mod) {
prev = &jlm->next;
jlm = jlm->next;
}
if (jlm) {
/* No memory during module load */
if (WARN_ON(!jlm))
continue;
if (prev == &key->next)
static_key_set_mod(key, jlm->next);
else
*prev = jlm->next;
kfree(jlm);
jlm = static_key_mod(key);
/* if only one etry is left, fold it back into the static_key */
if (jlm->next == NULL) {
static_key_set_entries(key, jlm->entries);
static_key_clear_linked(key);
kfree(jlm);
}
}
......@@ -499,8 +594,10 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val,
case MODULE_STATE_COMING:
jump_label_lock();
ret = jump_label_add_module(mod);
if (ret)
if (ret) {
WARN(1, "Failed to allocatote memory: jump_label may not work properly.\n");
jump_label_del_module(mod);
}
jump_label_unlock();
break;
case MODULE_STATE_GOING:
......@@ -561,11 +658,14 @@ int jump_label_text_reserved(void *start, void *end)
static void jump_label_update(struct static_key *key)
{
struct jump_entry *stop = __stop___jump_table;
struct jump_entry *entry = static_key_entries(key);
struct jump_entry *entry;
#ifdef CONFIG_MODULES
struct module *mod;
__jump_label_mod_update(key);
if (static_key_linked(key)) {
__jump_label_mod_update(key);
return;
}
preempt_disable();
mod = __module_address((unsigned long)key);
......@@ -573,6 +673,7 @@ static void jump_label_update(struct static_key *key)
stop = mod->jump_entries + mod->num_jump_entries;
preempt_enable();
#endif
entry = static_key_entries(key);
/* if there are no users, entry can be NULL */
if (entry)
__jump_label_update(key, entry, stop);
......
......@@ -1110,13 +1110,6 @@ struct ftrace_func_entry {
unsigned long ip;
};
struct ftrace_hash {
unsigned long size_bits;
struct hlist_head *buckets;
unsigned long count;
struct rcu_head rcu;
};
/*
* We make these constant because no one should touch them,
* but they are used as the default "empty hash", to avoid allocating
......@@ -1192,26 +1185,24 @@ struct ftrace_page {
static struct ftrace_page *ftrace_pages_start;
static struct ftrace_page *ftrace_pages;
static bool __always_inline ftrace_hash_empty(struct ftrace_hash *hash)
static __always_inline unsigned long
ftrace_hash_key(struct ftrace_hash *hash, unsigned long ip)
{
return !hash || !hash->count;
if (hash->size_bits > 0)
return hash_long(ip, hash->size_bits);
return 0;
}
static struct ftrace_func_entry *
ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip)
/* Only use this function if ftrace_hash_empty() has already been tested */
static __always_inline struct ftrace_func_entry *
__ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip)
{
unsigned long key;
struct ftrace_func_entry *entry;
struct hlist_head *hhd;
if (ftrace_hash_empty(hash))
return NULL;
if (hash->size_bits > 0)
key = hash_long(ip, hash->size_bits);
else
key = 0;
key = ftrace_hash_key(hash, ip);
hhd = &hash->buckets[key];
hlist_for_each_entry_rcu_notrace(entry, hhd, hlist) {
......@@ -1221,17 +1212,32 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip)
return NULL;
}
/**
* ftrace_lookup_ip - Test to see if an ip exists in an ftrace_hash
* @hash: The hash to look at
* @ip: The instruction pointer to test
*
* Search a given @hash to see if a given instruction pointer (@ip)
* exists in it.
*
* Returns the entry that holds the @ip if found. NULL otherwise.
*/
struct ftrace_func_entry *
ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip)
{
if (ftrace_hash_empty(hash))
return NULL;
return __ftrace_lookup_ip(hash, ip);
}
static void __add_hash_entry(struct ftrace_hash *hash,
struct ftrace_func_entry *entry)
{
struct hlist_head *hhd;
unsigned long key;
if (hash->size_bits)
key = hash_long(entry->ip, hash->size_bits);
else
key = 0;
key = ftrace_hash_key(hash, entry->ip);
hhd = &hash->buckets[key];
hlist_add_head(&entry->hlist, hhd);
hash->count++;
......@@ -1383,9 +1389,8 @@ ftrace_hash_rec_enable_modify(struct ftrace_ops *ops, int filter_hash);
static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops,
struct ftrace_hash *new_hash);
static int
ftrace_hash_move(struct ftrace_ops *ops, int enable,
struct ftrace_hash **dst, struct ftrace_hash *src)
static struct ftrace_hash *
__ftrace_hash_move(struct ftrace_hash *src)
{
struct ftrace_func_entry *entry;
struct hlist_node *tn;
......@@ -1393,21 +1398,13 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
struct ftrace_hash *new_hash;
int size = src->count;
int bits = 0;
int ret;
int i;
/* Reject setting notrace hash on IPMODIFY ftrace_ops */
if (ops->flags & FTRACE_OPS_FL_IPMODIFY && !enable)
return -EINVAL;
/*
* If the new source is empty, just free dst and assign it
* the empty_hash.
* If the new source is empty, just return the empty_hash.
*/
if (!src->count) {
new_hash = EMPTY_HASH;
goto update;
}
if (!src->count)
return EMPTY_HASH;
/*
* Make the hash size about 1/2 the # found
......@@ -1421,7 +1418,7 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
new_hash = alloc_ftrace_hash(bits);
if (!new_hash)
return -ENOMEM;
return NULL;
size = 1 << src->size_bits;
for (i = 0; i < size; i++) {
......@@ -1432,7 +1429,24 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
}
}
update:
return new_hash;
}
static int
ftrace_hash_move(struct ftrace_ops *ops, int enable,
struct ftrace_hash **dst, struct ftrace_hash *src)
{
struct ftrace_hash *new_hash;
int ret;
/* Reject setting notrace hash on IPMODIFY ftrace_ops */
if (ops->flags & FTRACE_OPS_FL_IPMODIFY && !enable)
return -EINVAL;
new_hash = __ftrace_hash_move(src);
if (!new_hash)
return -ENOMEM;
/* Make sure this can be applied if it is IPMODIFY ftrace_ops */
if (enable) {
/* IPMODIFY should be updated only when filter_hash updating */
......@@ -1466,9 +1480,9 @@ static bool hash_contains_ip(unsigned long ip,
* notrace hash is considered not in the notrace hash.
*/
return (ftrace_hash_empty(hash->filter_hash) ||
ftrace_lookup_ip(hash->filter_hash, ip)) &&
__ftrace_lookup_ip(hash->filter_hash, ip)) &&
(ftrace_hash_empty(hash->notrace_hash) ||
!ftrace_lookup_ip(hash->notrace_hash, ip));
!__ftrace_lookup_ip(hash->notrace_hash, ip));
}
/*
......@@ -2880,7 +2894,7 @@ ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
/* The function must be in the filter */
if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
!ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))
!__ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip))
return 0;
/* If in notrace hash, we ignore it too */
......@@ -4382,7 +4396,7 @@ __setup("ftrace_filter=", set_ftrace_filter);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
static int ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer);
static int ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer);
static unsigned long save_global_trampoline;
static unsigned long save_global_flags;
......@@ -4405,18 +4419,17 @@ static void __init set_ftrace_early_graph(char *buf, int enable)
{
int ret;
char *func;
unsigned long *table = ftrace_graph_funcs;
int *count = &ftrace_graph_count;
struct ftrace_hash *hash;
if (!enable) {
table = ftrace_graph_notrace_funcs;
count = &ftrace_graph_notrace_count;
}
if (enable)
hash = ftrace_graph_hash;
else
hash = ftrace_graph_notrace_hash;
while (buf) {
func = strsep(&buf, ",");
/* we allow only one expression at a time */
ret = ftrace_set_func(table, count, FTRACE_GRAPH_MAX_FUNCS, func);
ret = ftrace_graph_set_hash(hash, func);
if (ret)
printk(KERN_DEBUG "ftrace: function %s not "
"traceable\n", func);
......@@ -4540,26 +4553,55 @@ static const struct file_operations ftrace_notrace_fops = {
static DEFINE_MUTEX(graph_lock);
int ftrace_graph_count;
int ftrace_graph_notrace_count;
unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
struct ftrace_hash *ftrace_graph_hash = EMPTY_HASH;
struct ftrace_hash *ftrace_graph_notrace_hash = EMPTY_HASH;
enum graph_filter_type {
GRAPH_FILTER_NOTRACE = 0,
GRAPH_FILTER_FUNCTION,
};
#define FTRACE_GRAPH_EMPTY ((void *)1)
struct ftrace_graph_data {
unsigned long *table;
size_t size;
int *count;
const struct seq_operations *seq_ops;
struct ftrace_hash *hash;
struct ftrace_func_entry *entry;
int idx; /* for hash table iteration */
enum graph_filter_type type;
struct ftrace_hash *new_hash;
const struct seq_operations *seq_ops;
struct trace_parser parser;
};
static void *
__g_next(struct seq_file *m, loff_t *pos)
{
struct ftrace_graph_data *fgd = m->private;
struct ftrace_func_entry *entry = fgd->entry;
struct hlist_head *head;
int i, idx = fgd->idx;
if (*pos >= *fgd->count)
if (*pos >= fgd->hash->count)
return NULL;
return &fgd->table[*pos];
if (entry) {
hlist_for_each_entry_continue(entry, hlist) {
fgd->entry = entry;
return entry;
}
idx++;
}
for (i = idx; i < 1 << fgd->hash->size_bits; i++) {
head = &fgd->hash->buckets[i];
hlist_for_each_entry(entry, head, hlist) {
fgd->entry = entry;
fgd->idx = i;
return entry;
}
}
return NULL;
}
static void *
......@@ -4575,10 +4617,19 @@ static void *g_start(struct seq_file *m, loff_t *pos)
mutex_lock(&graph_lock);
if (fgd->type == GRAPH_FILTER_FUNCTION)
fgd->hash = rcu_dereference_protected(ftrace_graph_hash,
lockdep_is_held(&graph_lock));
else
fgd->hash = rcu_dereference_protected(ftrace_graph_notrace_hash,
lockdep_is_held(&graph_lock));
/* Nothing, tell g_show to print all functions are enabled */
if (!*fgd->count && !*pos)
return (void *)1;
if (ftrace_hash_empty(fgd->hash) && !*pos)
return FTRACE_GRAPH_EMPTY;
fgd->idx = 0;
fgd->entry = NULL;
return __g_next(m, pos);
}
......@@ -4589,22 +4640,22 @@ static void g_stop(struct seq_file *m, void *p)
static int g_show(struct seq_file *m, void *v)
{
unsigned long *ptr = v;
struct ftrace_func_entry *entry = v;
if (!ptr)
if (!entry)
return 0;
if (ptr == (unsigned long *)1) {
if (entry == FTRACE_GRAPH_EMPTY) {
struct ftrace_graph_data *fgd = m->private;
if (fgd->table == ftrace_graph_funcs)
if (fgd->type == GRAPH_FILTER_FUNCTION)
seq_puts(m, "#### all functions enabled ####\n");
else
seq_puts(m, "#### no functions disabled ####\n");
return 0;
}
seq_printf(m, "%ps\n", (void *)*ptr);
seq_printf(m, "%ps\n", (void *)entry->ip);
return 0;
}
......@@ -4621,24 +4672,51 @@ __ftrace_graph_open(struct inode *inode, struct file *file,
struct ftrace_graph_data *fgd)
{
int ret = 0;
struct ftrace_hash *new_hash = NULL;
mutex_lock(&graph_lock);
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC)) {
*fgd->count = 0;
memset(fgd->table, 0, fgd->size * sizeof(*fgd->table));
if (file->f_mode & FMODE_WRITE) {
const int size_bits = FTRACE_HASH_DEFAULT_BITS;
if (trace_parser_get_init(&fgd->parser, FTRACE_BUFF_MAX))
return -ENOMEM;
if (file->f_flags & O_TRUNC)
new_hash = alloc_ftrace_hash(size_bits);
else
new_hash = alloc_and_copy_ftrace_hash(size_bits,
fgd->hash);
if (!new_hash) {
ret = -ENOMEM;
goto out;
}
}
mutex_unlock(&graph_lock);
if (file->f_mode & FMODE_READ) {
ret = seq_open(file, fgd->seq_ops);
ret = seq_open(file, &ftrace_graph_seq_ops);
if (!ret) {
struct seq_file *m = file->private_data;
m->private = fgd;
} else {
/* Failed */
free_ftrace_hash(new_hash);
new_hash = NULL;
}
} else
file->private_data = fgd;
out:
if (ret < 0 && file->f_mode & FMODE_WRITE)
trace_parser_put(&fgd->parser);
fgd->new_hash = new_hash;
/*
* All uses of fgd->hash must be taken with the graph_lock
* held. The graph_lock is going to be released, so force
* fgd->hash to be reinitialized when it is taken again.
*/
fgd->hash = NULL;
return ret;
}
......@@ -4646,6 +4724,7 @@ static int
ftrace_graph_open(struct inode *inode, struct file *file)
{
struct ftrace_graph_data *fgd;
int ret;
if (unlikely(ftrace_disabled))
return -ENODEV;
......@@ -4654,18 +4733,26 @@ ftrace_graph_open(struct inode *inode, struct file *file)
if (fgd == NULL)
return -ENOMEM;
fgd->table = ftrace_graph_funcs;
fgd->size = FTRACE_GRAPH_MAX_FUNCS;
fgd->count = &ftrace_graph_count;
mutex_lock(&graph_lock);
fgd->hash = rcu_dereference_protected(ftrace_graph_hash,
lockdep_is_held(&graph_lock));
fgd->type = GRAPH_FILTER_FUNCTION;
fgd->seq_ops = &ftrace_graph_seq_ops;
return __ftrace_graph_open(inode, file, fgd);
ret = __ftrace_graph_open(inode, file, fgd);
if (ret < 0)
kfree(fgd);
mutex_unlock(&graph_lock);
return ret;
}
static int
ftrace_graph_notrace_open(struct inode *inode, struct file *file)
{
struct ftrace_graph_data *fgd;
int ret;
if (unlikely(ftrace_disabled))
return -ENODEV;
......@@ -4674,45 +4761,97 @@ ftrace_graph_notrace_open(struct inode *inode, struct file *file)
if (fgd == NULL)
return -ENOMEM;
fgd->table = ftrace_graph_notrace_funcs;
fgd->size = FTRACE_GRAPH_MAX_FUNCS;
fgd->count = &ftrace_graph_notrace_count;
mutex_lock(&graph_lock);
fgd->hash = rcu_dereference_protected(ftrace_graph_notrace_hash,
lockdep_is_held(&graph_lock));
fgd->type = GRAPH_FILTER_NOTRACE;
fgd->seq_ops = &ftrace_graph_seq_ops;
return __ftrace_graph_open(inode, file, fgd);
ret = __ftrace_graph_open(inode, file, fgd);
if (ret < 0)
kfree(fgd);
mutex_unlock(&graph_lock);
return ret;
}
static int
ftrace_graph_release(struct inode *inode, struct file *file)
{
struct ftrace_graph_data *fgd;
struct ftrace_hash *old_hash, *new_hash;
struct trace_parser *parser;
int ret = 0;
if (file->f_mode & FMODE_READ) {
struct seq_file *m = file->private_data;
kfree(m->private);
fgd = m->private;
seq_release(inode, file);
} else {
kfree(file->private_data);
fgd = file->private_data;
}
return 0;
if (file->f_mode & FMODE_WRITE) {
parser = &fgd->parser;
if (trace_parser_loaded((parser))) {
parser->buffer[parser->idx] = 0;
ret = ftrace_graph_set_hash(fgd->new_hash,
parser->buffer);
}
trace_parser_put(parser);
new_hash = __ftrace_hash_move(fgd->new_hash);
if (!new_hash) {
ret = -ENOMEM;
goto out;
}
mutex_lock(&graph_lock);
if (fgd->type == GRAPH_FILTER_FUNCTION) {
old_hash = rcu_dereference_protected(ftrace_graph_hash,
lockdep_is_held(&graph_lock));
rcu_assign_pointer(ftrace_graph_hash, new_hash);
} else {
old_hash = rcu_dereference_protected(ftrace_graph_notrace_hash,
lockdep_is_held(&graph_lock));
rcu_assign_pointer(ftrace_graph_notrace_hash, new_hash);
}
mutex_unlock(&graph_lock);
/* Wait till all users are no longer using the old hash */
synchronize_sched();
free_ftrace_hash(old_hash);
}
out:
kfree(fgd->new_hash);
kfree(fgd);
return ret;
}
static int
ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer)
ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer)
{
struct ftrace_glob func_g;
struct dyn_ftrace *rec;
struct ftrace_page *pg;
struct ftrace_func_entry *entry;
int fail = 1;
int not;
bool exists;
int i;
/* decode regex */
func_g.type = filter_parse_regex(buffer, strlen(buffer),
&func_g.search, &not);
if (!not && *idx >= size)
return -EBUSY;
func_g.len = strlen(func_g.search);
......@@ -4729,26 +4868,18 @@ ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer)
continue;
if (ftrace_match_record(rec, &func_g, NULL, 0)) {
/* if it is in the array */
exists = false;
for (i = 0; i < *idx; i++) {
if (array[i] == rec->ip) {
exists = true;
break;
}
}
entry = ftrace_lookup_ip(hash, rec->ip);
if (!not) {
fail = 0;
if (!exists) {
array[(*idx)++] = rec->ip;
if (*idx >= size)
goto out;
}
if (entry)
continue;
if (add_hash_entry(hash, rec->ip) < 0)
goto out;
} else {
if (exists) {
array[i] = array[--(*idx)];
array[*idx] = 0;
if (entry) {
free_hash_entry(hash, entry);
fail = 0;
}
}
......@@ -4767,35 +4898,34 @@ static ssize_t
ftrace_graph_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
struct trace_parser parser;
ssize_t read, ret = 0;
struct ftrace_graph_data *fgd = file->private_data;
struct trace_parser *parser;
if (!cnt)
return 0;
if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX))
return -ENOMEM;
read = trace_get_user(&parser, ubuf, cnt, ppos);
/* Read mode uses seq functions */
if (file->f_mode & FMODE_READ) {
struct seq_file *m = file->private_data;
fgd = m->private;
}
if (read >= 0 && trace_parser_loaded((&parser))) {
parser.buffer[parser.idx] = 0;
parser = &fgd->parser;
mutex_lock(&graph_lock);
read = trace_get_user(parser, ubuf, cnt, ppos);
/* we allow only one expression at a time */
ret = ftrace_set_func(fgd->table, fgd->count, fgd->size,
parser.buffer);
if (read >= 0 && trace_parser_loaded(parser) &&
!trace_parser_cont(parser)) {
mutex_unlock(&graph_lock);
ret = ftrace_graph_set_hash(fgd->new_hash,
parser->buffer);
trace_parser_clear(parser);
}
if (!ret)
ret = read;
trace_parser_put(&parser);
return ret;
}
......
......@@ -260,16 +260,8 @@ unsigned long long ns2usecs(u64 nsec)
TRACE_ITER_EVENT_FORK
/*
* The global_trace is the descriptor that holds the tracing
* buffers for the live tracing. For each CPU, it contains
* a link list of pages that will store trace entries. The
* page descriptor of the pages in the memory is used to hold
* the link list by linking the lru item in the page descriptor
* to each of the pages in the buffer per CPU.
*
* For each active CPU there is a data field that holds the
* pages for the buffer for that CPU. Each CPU has the same number
* of pages allocated for its buffer.
* The global_trace is the descriptor that holds the top-level tracing
* buffers for the live tracing.
*/
static struct trace_array global_trace = {
.trace_flags = TRACE_DEFAULT_FLAGS,
......@@ -1193,6 +1185,7 @@ int trace_parser_get_init(struct trace_parser *parser, int size)
void trace_parser_put(struct trace_parser *parser)
{
kfree(parser->buffer);
parser->buffer = NULL;
}
/*
......
......@@ -753,6 +753,21 @@ enum print_line_t print_trace_line(struct trace_iterator *iter);
extern char trace_find_mark(unsigned long long duration);
struct ftrace_hash {
unsigned long size_bits;
struct hlist_head *buckets;
unsigned long count;
struct rcu_head rcu;
};
struct ftrace_func_entry *
ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip);
static __always_inline bool ftrace_hash_empty(struct ftrace_hash *hash)
{
return !hash || !hash->count;
}
/* Standard output formatting function used for function return traces */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
......@@ -787,53 +802,50 @@ extern void __trace_graph_return(struct trace_array *tr,
struct ftrace_graph_ret *trace,
unsigned long flags, int pc);
#ifdef CONFIG_DYNAMIC_FTRACE
/* TODO: make this variable */
#define FTRACE_GRAPH_MAX_FUNCS 32
extern int ftrace_graph_count;
extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
extern int ftrace_graph_notrace_count;
extern unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS];
extern struct ftrace_hash *ftrace_graph_hash;
extern struct ftrace_hash *ftrace_graph_notrace_hash;
static inline int ftrace_graph_addr(unsigned long addr)
{
int i;
if (!ftrace_graph_count)
return 1;
for (i = 0; i < ftrace_graph_count; i++) {
if (addr == ftrace_graph_funcs[i]) {
/*
* If no irqs are to be traced, but a set_graph_function
* is set, and called by an interrupt handler, we still
* want to trace it.
*/
if (in_irq())
trace_recursion_set(TRACE_IRQ_BIT);
else
trace_recursion_clear(TRACE_IRQ_BIT);
return 1;
}
int ret = 0;
preempt_disable_notrace();
if (ftrace_hash_empty(ftrace_graph_hash)) {
ret = 1;
goto out;
}
return 0;
if (ftrace_lookup_ip(ftrace_graph_hash, addr)) {
/*
* If no irqs are to be traced, but a set_graph_function
* is set, and called by an interrupt handler, we still
* want to trace it.
*/
if (in_irq())
trace_recursion_set(TRACE_IRQ_BIT);
else
trace_recursion_clear(TRACE_IRQ_BIT);
ret = 1;
}
out:
preempt_enable_notrace();
return ret;
}
static inline int ftrace_graph_notrace_addr(unsigned long addr)
{
int i;
int ret = 0;
if (!ftrace_graph_notrace_count)
return 0;
preempt_disable_notrace();
for (i = 0; i < ftrace_graph_notrace_count; i++) {
if (addr == ftrace_graph_notrace_funcs[i])
return 1;
}
if (ftrace_lookup_ip(ftrace_graph_notrace_hash, addr))
ret = 1;
return 0;
preempt_enable_notrace();
return ret;
}
#else
static inline int ftrace_graph_addr(unsigned long addr)
......@@ -1300,7 +1312,8 @@ static inline bool is_string_field(struct ftrace_event_field *field)
{
return field->filter_type == FILTER_DYN_STRING ||
field->filter_type == FILTER_STATIC_STRING ||
field->filter_type == FILTER_PTR_STRING;
field->filter_type == FILTER_PTR_STRING ||
field->filter_type == FILTER_COMM;
}
static inline bool is_function_field(struct ftrace_event_field *field)
......
......@@ -175,9 +175,9 @@ int trace_benchmark_reg(void)
bm_event_thread = kthread_run(benchmark_event_kthread,
NULL, "event_benchmark");
if (!bm_event_thread) {
if (IS_ERR(bm_event_thread)) {
pr_warning("trace benchmark failed to create kernel thread\n");
return -ENOMEM;
return PTR_ERR(bm_event_thread);
}
return 0;
......
......@@ -27,7 +27,7 @@ static DEFINE_MUTEX(branch_tracing_mutex);
static struct trace_array *branch_tracer;
static void
probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
probe_likely_condition(struct ftrace_likely_data *f, int val, int expect)
{
struct trace_event_call *call = &event_branch;
struct trace_array *tr = branch_tracer;
......@@ -68,16 +68,17 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
entry = ring_buffer_event_data(event);
/* Strip off the path, only save the file */
p = f->file + strlen(f->file);
while (p >= f->file && *p != '/')
p = f->data.file + strlen(f->data.file);
while (p >= f->data.file && *p != '/')
p--;
p++;
strncpy(entry->func, f->func, TRACE_FUNC_SIZE);
strncpy(entry->func, f->data.func, TRACE_FUNC_SIZE);
strncpy(entry->file, p, TRACE_FILE_SIZE);
entry->func[TRACE_FUNC_SIZE] = 0;
entry->file[TRACE_FILE_SIZE] = 0;
entry->line = f->line;
entry->constant = f->constant;
entry->line = f->data.line;
entry->correct = val == expect;
if (!call_filter_check_discard(call, entry, buffer, event))
......@@ -89,7 +90,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
}
static inline
void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
void trace_likely_condition(struct ftrace_likely_data *f, int val, int expect)
{
if (!branch_tracing_enabled)
return;
......@@ -195,13 +196,19 @@ core_initcall(init_branch_tracer);
#else
static inline
void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
void trace_likely_condition(struct ftrace_likely_data *f, int val, int expect)
{
}
#endif /* CONFIG_BRANCH_TRACER */
void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect)
void ftrace_likely_update(struct ftrace_likely_data *f, int val,
int expect, int is_constant)
{
/* A constant is always correct */
if (is_constant) {
f->constant++;
val = expect;
}
/*
* I would love to have a trace point here instead, but the
* trace point code is so inundated with unlikely and likely
......@@ -212,9 +219,9 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect)
/* FIXME: Make this atomic! */
if (val == expect)
f->correct++;
f->data.correct++;
else
f->incorrect++;
f->data.incorrect++;
}
EXPORT_SYMBOL(ftrace_likely_update);
......@@ -245,29 +252,60 @@ static inline long get_incorrect_percent(struct ftrace_branch_data *p)
return percent;
}
static int branch_stat_show(struct seq_file *m, void *v)
static const char *branch_stat_process_file(struct ftrace_branch_data *p)
{
struct ftrace_branch_data *p = v;
const char *f;
long percent;
/* Only print the file, not the path */
f = p->file + strlen(p->file);
while (f >= p->file && *f != '/')
f--;
f++;
return ++f;
}
static void branch_stat_show(struct seq_file *m,
struct ftrace_branch_data *p, const char *f)
{
long percent;
/*
* The miss is overlayed on correct, and hit on incorrect.
*/
percent = get_incorrect_percent(p);
seq_printf(m, "%8lu %8lu ", p->correct, p->incorrect);
if (percent < 0)
seq_puts(m, " X ");
else
seq_printf(m, "%3ld ", percent);
seq_printf(m, "%-30.30s %-20.20s %d\n", p->func, f, p->line);
}
static int branch_stat_show_normal(struct seq_file *m,
struct ftrace_branch_data *p, const char *f)
{
seq_printf(m, "%8lu %8lu ", p->correct, p->incorrect);
branch_stat_show(m, p, f);
return 0;
}
static int annotate_branch_stat_show(struct seq_file *m, void *v)
{
struct ftrace_likely_data *p = v;
const char *f;
int l;
f = branch_stat_process_file(&p->data);
if (!p->constant)
return branch_stat_show_normal(m, &p->data, f);
l = snprintf(NULL, 0, "/%lu", p->constant);
l = l > 8 ? 0 : 8 - l;
seq_printf(m, "%8lu/%lu %*lu ",
p->data.correct, p->constant, l, p->data.incorrect);
branch_stat_show(m, &p->data, f);
return 0;
}
......@@ -279,7 +317,7 @@ static void *annotated_branch_stat_start(struct tracer_stat *trace)
static void *
annotated_branch_stat_next(void *v, int idx)
{
struct ftrace_branch_data *p = v;
struct ftrace_likely_data *p = v;
++p;
......@@ -328,7 +366,7 @@ static struct tracer_stat annotated_branch_stats = {
.stat_next = annotated_branch_stat_next,
.stat_cmp = annotated_branch_stat_cmp,
.stat_headers = annotated_branch_stat_headers,
.stat_show = branch_stat_show
.stat_show = annotate_branch_stat_show
};
__init static int init_annotated_branch_stats(void)
......@@ -379,12 +417,21 @@ all_branch_stat_next(void *v, int idx)
return p;
}
static int all_branch_stat_show(struct seq_file *m, void *v)
{
struct ftrace_branch_data *p = v;
const char *f;
f = branch_stat_process_file(p);
return branch_stat_show_normal(m, p, f);
}
static struct tracer_stat all_branch_stats = {
.name = "branch_all",
.stat_start = all_branch_stat_start,
.stat_next = all_branch_stat_next,
.stat_headers = all_branch_stat_headers,
.stat_show = branch_stat_show
.stat_show = all_branch_stat_show
};
__init static int all_annotated_branch_stats(void)
......
......@@ -328,11 +328,13 @@ FTRACE_ENTRY(branch, trace_branch,
__array( char, func, TRACE_FUNC_SIZE+1 )
__array( char, file, TRACE_FILE_SIZE+1 )
__field( char, correct )
__field( char, constant )
),
F_printk("%u:%s:%s (%u)",
F_printk("%u:%s:%s (%u)%s",
__entry->line,
__entry->func, __entry->file, __entry->correct),
__entry->func, __entry->file, __entry->correct,
__entry->constant ? " CONSTANT" : ""),
FILTER_OTHER
);
......
......@@ -322,10 +322,7 @@ static void move_to_next_cpu(bool initmask)
* need to ensure nothing else might be running (and thus preempting).
* Obviously this should never be used in production environments.
*
* Currently this runs on which ever CPU it was scheduled on, but most
* real-world hardware latency situations occur across several CPUs,
* but we might later generalize this if we find there are any actualy
* systems with alternate SMI delivery or other hardware latencies.
* Executes one loop interaction on each CPU in tracing_cpumask sysfs file.
*/
static int kthread_fn(void *data)
{
......
......@@ -16,6 +16,7 @@
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#define pr_fmt(fmt) "trace_kprobe: " fmt
#include <linux/module.h>
#include <linux/uaccess.h>
......
......@@ -21,6 +21,7 @@
* Copyright (C) IBM Corporation, 2010-2011
* Author: Srikar Dronamraju
*/
#define pr_fmt(fmt) "trace_probe: " fmt
#include "trace_probe.h"
......@@ -647,7 +648,7 @@ ssize_t traceprobe_probes_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos,
int (*createfn)(int, char **))
{
char *kbuf, *tmp;
char *kbuf, *buf, *tmp;
int ret = 0;
size_t done = 0;
size_t size;
......@@ -667,27 +668,38 @@ ssize_t traceprobe_probes_write(struct file *file, const char __user *buffer,
goto out;
}
kbuf[size] = '\0';
tmp = strchr(kbuf, '\n');
buf = kbuf;
do {
tmp = strchr(buf, '\n');
if (tmp) {
*tmp = '\0';
size = tmp - buf + 1;
} else {
size = strlen(buf);
if (done + size < count) {
if (buf != kbuf)
break;
/* This can accept WRITE_BUFSIZE - 2 ('\n' + '\0') */
pr_warn("Line length is too long: Should be less than %d\n",
WRITE_BUFSIZE - 2);
ret = -EINVAL;
goto out;
}
}
done += size;
if (tmp) {
*tmp = '\0';
size = tmp - kbuf + 1;
} else if (done + size < count) {
pr_warn("Line length is too long: Should be less than %d\n",
WRITE_BUFSIZE);
ret = -EINVAL;
goto out;
}
done += size;
/* Remove comments */
tmp = strchr(kbuf, '#');
/* Remove comments */
tmp = strchr(buf, '#');
if (tmp)
*tmp = '\0';
if (tmp)
*tmp = '\0';
ret = traceprobe_command(kbuf, createfn);
if (ret)
goto out;
ret = traceprobe_command(buf, createfn);
if (ret)
goto out;
buf += size;
} while (done < count);
}
ret = done;
......
......@@ -17,6 +17,7 @@
* Copyright (C) IBM Corporation, 2010-2012
* Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
*/
#define pr_fmt(fmt) "trace_kprobe: " fmt
#include <linux/module.h>
#include <linux/uaccess.h>
......@@ -431,7 +432,8 @@ static int create_trace_uprobe(int argc, char **argv)
pr_info("Probe point is not specified.\n");
return -EINVAL;
}
arg = strchr(argv[1], ':');
/* Find the last occurrence, in case the path contains ':' too. */
arg = strrchr(argv[1], ':');
if (!arg) {
ret = -EINVAL;
goto fail_address_parse;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment