summaryrefslogtreecommitdiff
path: root/kernel/trace
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-12-05 09:53:36 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2009-12-05 09:53:36 -0800
commit96fa2b508d2d3fe040cf4ef2fffb955f0a537ea1 (patch)
tree3cec6d72a450735fe6b8ed996c7399f57c05a5cb /kernel/trace
parent7a797cdcca2b3c0031e580203f18d6c9483aaec5 (diff)
parentb8007ef7422270864eae523cb38d7522a53a94d3 (diff)
Merge branch 'tracing-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'tracing-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (40 commits) tracing: Separate raw syscall from syscall tracer ring-buffer-benchmark: Add parameters to set produce/consumer priorities tracing, function tracer: Clean up strstrip() usage ring-buffer benchmark: Run producer/consumer threads at nice +19 tracing: Remove the stale include/trace/power.h tracing: Only print objcopy version warning once from recordmcount tracing: Prevent build warning: 'ftrace_graph_buf' defined but not used ring-buffer: Move access to commit_page up into function used tracing: do not disable interrupts for trace_clock_local ring-buffer: Add multiple iterations between benchmark timestamps kprobes: Sanitize struct kretprobe_instance allocations tracing: Fix to use __always_unused attribute compiler: Introduce __always_unused tracing: Exit with error if a weak function is used in recordmcount.pl tracing: Move conditional into update_funcs() in recordmcount.pl tracing: Add regex for weak functions in recordmcount.pl tracing: Move mcount section search to front of loop in recordmcount.pl tracing: Fix objcopy revision check in recordmcount.pl tracing: Check absolute path of input file in recordmcount.pl tracing: Correct the check for number of arguments in recordmcount.pl ...
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/ftrace.c375
-rw-r--r--kernel/trace/ring_buffer.c9
-rw-r--r--kernel/trace/ring_buffer_benchmark.c85
-rw-r--r--kernel/trace/trace.c4
-rw-r--r--kernel/trace/trace.h44
-rw-r--r--kernel/trace/trace_clock.c8
-rw-r--r--kernel/trace/trace_events.c23
-rw-r--r--kernel/trace/trace_events_filter.c155
-rw-r--r--kernel/trace/trace_export.c4
-rw-r--r--kernel/trace/trace_syscalls.c86
10 files changed, 587 insertions, 206 deletions
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6dc4e5ef7a0..e51a1bcb7be 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -60,6 +60,13 @@ static int last_ftrace_enabled;
/* Quick disabling of function tracer. */
int function_trace_stop;
+/* List for set_ftrace_pid's pids. */
+LIST_HEAD(ftrace_pids);
+struct ftrace_pid {
+ struct list_head list;
+ struct pid *pid;
+};
+
/*
* ftrace_disabled is set when an anomaly is discovered.
* ftrace_disabled is much stronger than ftrace_enabled.
@@ -78,6 +85,10 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+#endif
+
static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
{
struct ftrace_ops *op = ftrace_list;
@@ -155,7 +166,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
else
func = ftrace_list_func;
- if (ftrace_pid_trace) {
+ if (!list_empty(&ftrace_pids)) {
set_ftrace_pid_function(func);
func = ftrace_pid_func;
}
@@ -203,7 +214,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
if (ftrace_list->next == &ftrace_list_end) {
ftrace_func_t func = ftrace_list->func;
- if (ftrace_pid_trace) {
+ if (!list_empty(&ftrace_pids)) {
set_ftrace_pid_function(func);
func = ftrace_pid_func;
}
@@ -231,7 +242,7 @@ static void ftrace_update_pid_func(void)
func = __ftrace_trace_function;
#endif
- if (ftrace_pid_trace) {
+ if (!list_empty(&ftrace_pids)) {
set_ftrace_pid_function(func);
func = ftrace_pid_func;
} else {
@@ -821,8 +832,6 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
}
#endif /* CONFIG_FUNCTION_PROFILER */
-/* set when tracing only a pid */
-struct pid *ftrace_pid_trace;
static struct pid * const ftrace_swapper_pid = &init_struct_pid;
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -1261,12 +1270,34 @@ static int ftrace_update_code(struct module *mod)
ftrace_new_addrs = p->newlist;
p->flags = 0L;
- /* convert record (i.e, patch mcount-call with NOP) */
- if (ftrace_code_disable(mod, p)) {
- p->flags |= FTRACE_FL_CONVERTED;
- ftrace_update_cnt++;
- } else
+ /*
+ * Do the initial record convertion from mcount jump
+ * to the NOP instructions.
+ */
+ if (!ftrace_code_disable(mod, p)) {
ftrace_free_rec(p);
+ continue;
+ }
+
+ p->flags |= FTRACE_FL_CONVERTED;
+ ftrace_update_cnt++;
+
+ /*
+ * If the tracing is enabled, go ahead and enable the record.
+ *
+ * The reason not to enable the record immediatelly is the
+ * inherent check of ftrace_make_nop/ftrace_make_call for
+ * correct previous instructions. Making first the NOP
+ * conversion puts the module to the correct state, thus
+ * passing the ftrace_make_call check.
+ */
+ if (ftrace_start_up) {
+ int failed = __ftrace_replace_code(p, 1);
+ if (failed) {
+ ftrace_bug(failed, p->ip);
+ ftrace_free_rec(p);
+ }
+ }
}
stop = ftrace_now(raw_smp_processor_id());
@@ -1656,60 +1687,6 @@ ftrace_regex_lseek(struct file *file, loff_t offset, int origin)
return ret;
}
-enum {
- MATCH_FULL,
- MATCH_FRONT_ONLY,
- MATCH_MIDDLE_ONLY,
- MATCH_END_ONLY,
-};
-
-/*
- * (static function - no need for kernel doc)
- *
- * Pass in a buffer containing a glob and this function will
- * set search to point to the search part of the buffer and
- * return the type of search it is (see enum above).
- * This does modify buff.
- *
- * Returns enum type.
- * search returns the pointer to use for comparison.
- * not returns 1 if buff started with a '!'
- * 0 otherwise.
- */
-static int
-ftrace_setup_glob(char *buff, int len, char **search, int *not)
-{
- int type = MATCH_FULL;
- int i;
-
- if (buff[0] == '!') {
- *not = 1;
- buff++;
- len--;
- } else
- *not = 0;
-
- *search = buff;
-
- for (i = 0; i < len; i++) {
- if (buff[i] == '*') {
- if (!i) {
- *search = buff + 1;
- type = MATCH_END_ONLY;
- } else {
- if (type == MATCH_END_ONLY)
- type = MATCH_MIDDLE_ONLY;
- else
- type = MATCH_FRONT_ONLY;
- buff[i] = 0;
- break;
- }
- }
- }
-
- return type;
-}
-
static int ftrace_match(char *str, char *regex, int len, int type)
{
int matched = 0;
@@ -1758,7 +1735,7 @@ static void ftrace_match_records(char *buff, int len, int enable)
int not;
flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
- type = ftrace_setup_glob(buff, len, &search, &not);
+ type = filter_parse_regex(buff, len, &search, &not);
search_len = strlen(search);
@@ -1826,7 +1803,7 @@ static void ftrace_match_module_records(char *buff, char *mod, int enable)
}
if (strlen(buff)) {
- type = ftrace_setup_glob(buff, strlen(buff), &search, &not);
+ type = filter_parse_regex(buff, strlen(buff), &search, &not);
search_len = strlen(search);
}
@@ -1991,7 +1968,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
int count = 0;
char *search;
- type = ftrace_setup_glob(glob, strlen(glob), &search, &not);
+ type = filter_parse_regex(glob, strlen(glob), &search, &not);
len = strlen(search);
/* we do not support '!' for function probes */
@@ -2068,7 +2045,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
else if (glob) {
int not;
- type = ftrace_setup_glob(glob, strlen(glob), &search, &not);
+ type = filter_parse_regex(glob, strlen(glob), &search, &not);
len = strlen(search);
/* we do not support '!' for function probes */
@@ -2312,6 +2289,32 @@ static int __init set_ftrace_filter(char *str)
}
__setup("ftrace_filter=", set_ftrace_filter);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
+static int __init set_graph_function(char *str)
+{
+ strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
+ return 1;
+}
+__setup("ftrace_graph_filter=", set_graph_function);
+
+static void __init set_ftrace_early_graph(char *buf)
+{
+ int ret;
+ char *func;
+
+ while (buf) {
+ func = strsep(&buf, ",");
+ /* we allow only one expression at a time */
+ ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
+ func);
+ if (ret)
+ printk(KERN_DEBUG "ftrace: function %s not "
+ "traceable\n", func);
+ }
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
static void __init set_ftrace_early_filter(char *buf, int enable)
{
char *func;
@@ -2328,6 +2331,10 @@ static void __init set_ftrace_early_filters(void)
set_ftrace_early_filter(ftrace_filter_buf, 1);
if (ftrace_notrace_buf[0])
set_ftrace_early_filter(ftrace_notrace_buf, 0);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ if (ftrace_graph_buf[0])
+ set_ftrace_early_graph(ftrace_graph_buf);
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
}
static int
@@ -2513,7 +2520,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
return -ENODEV;
/* decode regex */
- type = ftrace_setup_glob(buffer, strlen(buffer), &search, &not);
+ type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
if (not)
return -EINVAL;
@@ -2624,7 +2631,7 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
return 0;
}
-static int ftrace_convert_nops(struct module *mod,
+static int ftrace_process_locs(struct module *mod,
unsigned long *start,
unsigned long *end)
{
@@ -2684,7 +2691,7 @@ static void ftrace_init_module(struct module *mod,
{
if (ftrace_disabled || start == end)
return;
- ftrace_convert_nops(mod, start, end);
+ ftrace_process_locs(mod, start, end);
}
static int ftrace_module_notify(struct notifier_block *self,
@@ -2745,7 +2752,7 @@ void __init ftrace_init(void)
last_ftrace_enabled = ftrace_enabled = 1;
- ret = ftrace_convert_nops(NULL,
+ ret = ftrace_process_locs(NULL,
__start_mcount_loc,
__stop_mcount_loc);
@@ -2778,23 +2785,6 @@ static inline void ftrace_startup_enable(int command) { }
# define ftrace_shutdown_sysctl() do { } while (0)
#endif /* CONFIG_DYNAMIC_FTRACE */
-static ssize_t
-ftrace_pid_read(struct file *file, char __user *ubuf,
- size_t cnt, loff_t *ppos)
-{
- char buf[64];
- int r;
-
- if (ftrace_pid_trace == ftrace_swapper_pid)
- r = sprintf(buf, "swapper tasks\n");
- else if (ftrace_pid_trace)
- r = sprintf(buf, "%u\n", pid_vnr(ftrace_pid_trace));
- else
- r = sprintf(buf, "no pid\n");
-
- return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-}
-
static void clear_ftrace_swapper(void)
{
struct task_struct *p;
@@ -2845,14 +2835,12 @@ static void set_ftrace_pid(struct pid *pid)
rcu_read_unlock();
}
-static void clear_ftrace_pid_task(struct pid **pid)
+static void clear_ftrace_pid_task(struct pid *pid)
{
- if (*pid == ftrace_swapper_pid)
+ if (pid == ftrace_swapper_pid)
clear_ftrace_swapper();
else
- clear_ftrace_pid(*pid);
-
- *pid = NULL;
+ clear_ftrace_pid(pid);
}
static void set_ftrace_pid_task(struct pid *pid)
@@ -2863,74 +2851,184 @@ static void set_ftrace_pid_task(struct pid *pid)
set_ftrace_pid(pid);
}
-static ssize_t
-ftrace_pid_write(struct file *filp, const char __user *ubuf,
- size_t cnt, loff_t *ppos)
+static int ftrace_pid_add(int p)
{
struct pid *pid;
- char buf[64];
- long val;
- int ret;
+ struct ftrace_pid *fpid;
+ int ret = -EINVAL;
- if (cnt >= sizeof(buf))
- return -EINVAL;
+ mutex_lock(&ftrace_lock);
- if (copy_from_user(&buf, ubuf, cnt))
- return -EFAULT;
+ if (!p)
+ pid = ftrace_swapper_pid;
+ else
+ pid = find_get_pid(p);
- buf[cnt] = 0;
+ if (!pid)
+ goto out;
- ret = strict_strtol(buf, 10, &val);
- if (ret < 0)
- return ret;
+ ret = 0;
- mutex_lock(&ftrace_lock);
- if (val < 0) {
- /* disable pid tracing */
- if (!ftrace_pid_trace)
- goto out;
+ list_for_each_entry(fpid, &ftrace_pids, list)
+ if (fpid->pid == pid)
+ goto out_put;
- clear_ftrace_pid_task(&ftrace_pid_trace);
+ ret = -ENOMEM;
- } else {
- /* swapper task is special */
- if (!val) {
- pid = ftrace_swapper_pid;
- if (pid == ftrace_pid_trace)
- goto out;
- } else {
- pid = find_get_pid(val);
+ fpid = kmalloc(sizeof(*fpid), GFP_KERNEL);
+ if (!fpid)
+ goto out_put;
- if (pid == ftrace_pid_trace) {
- put_pid(pid);
- goto out;
- }
- }
+ list_add(&fpid->list, &ftrace_pids);
+ fpid->pid = pid;
- if (ftrace_pid_trace)
- clear_ftrace_pid_task(&ftrace_pid_trace);
+ set_ftrace_pid_task(pid);
- if (!pid)
- goto out;
+ ftrace_update_pid_func();
+ ftrace_startup_enable(0);
+
+ mutex_unlock(&ftrace_lock);
+ return 0;
+
+out_put:
+ if (pid != ftrace_swapper_pid)
+ put_pid(pid);
- ftrace_pid_trace = pid;
+out:
+ mutex_unlock(&ftrace_lock);
+ return ret;
+}
+
+static void ftrace_pid_reset(void)
+{
+ struct ftrace_pid *fpid, *safe;
- set_ftrace_pid_task(ftrace_pid_trace);
+ mutex_lock(&ftrace_lock);
+ list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) {
+ struct pid *pid = fpid->pid;
+
+ clear_ftrace_pid_task(pid);
+
+ list_del(&fpid->list);
+ kfree(fpid);
}
- /* update the function call */
ftrace_update_pid_func();
ftrace_startup_enable(0);
- out:
mutex_unlock(&ftrace_lock);
+}
- return cnt;
+static void *fpid_start(struct seq_file *m, loff_t *pos)
+{
+ mutex_lock(&ftrace_lock);
+
+ if (list_empty(&ftrace_pids) && (!*pos))
+ return (void *) 1;
+
+ return seq_list_start(&ftrace_pids, *pos);
+}
+
+static void *fpid_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ if (v == (void *)1)
+ return NULL;
+
+ return seq_list_next(v, &ftrace_pids, pos);
+}
+
+static void fpid_stop(struct seq_file *m, void *p)
+{
+ mutex_unlock(&ftrace_lock);
+}
+
+static int fpid_show(struct seq_file *m, void *v)
+{
+ const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list);
+
+ if (v == (void *)1) {
+ seq_printf(m, "no pid\n");
+ return 0;
+ }
+
+ if (fpid->pid == ftrace_swapper_pid)
+ seq_printf(m, "swapper tasks\n");
+ else
+ seq_printf(m, "%u\n", pid_vnr(fpid->pid));
+
+ return 0;
+}
+
+static const struct seq_operations ftrace_pid_sops = {
+ .start = fpid_start,
+ .next = fpid_next,
+ .stop = fpid_stop,
+ .show = fpid_show,
+};
+
+static int
+ftrace_pid_open(struct inode *inode, struct file *file)
+{
+ int ret = 0;
+
+ if ((file->f_mode & FMODE_WRITE) &&
+ (file->f_flags & O_TRUNC))
+ ftrace_pid_reset();
+
+ if (file->f_mode & FMODE_READ)
+ ret = seq_open(file, &ftrace_pid_sops);
+
+ return ret;
+}
+
+static ssize_t
+ftrace_pid_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[64], *tmp;
+ long val;
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ /*
+ * Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid"
+ * to clean the filter quietly.
+ */
+ tmp = strstrip(buf);
+ if (strlen(tmp) == 0)
+ return 1;
+
+ ret = strict_strtol(tmp, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ ret = ftrace_pid_add(val);
+
+ return ret ? ret : cnt;
+}
+
+static int
+ftrace_pid_release(struct inode *inode, struct file *file)
+{
+ if (file->f_mode & FMODE_READ)
+ seq_release(inode, file);
+
+ return 0;
}
static const struct file_operations ftrace_pid_fops = {
- .read = ftrace_pid_read,
- .write = ftrace_pid_write,
+ .open = ftrace_pid_open,
+ .write = ftrace_pid_write,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = ftrace_pid_release,
};
static __init int ftrace_init_debugfs(void)
@@ -3293,4 +3391,3 @@ void ftrace_graph_stop(void)
ftrace_stop();
}
#endif
-
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 5dd017fea6f..a72c6e03dee 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1787,9 +1787,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
static struct ring_buffer_event *
rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
unsigned long length, unsigned long tail,
- struct buffer_page *commit_page,
struct buffer_page *tail_page, u64 *ts)
{
+ struct buffer_page *commit_page = cpu_buffer->commit_page;
struct ring_buffer *buffer = cpu_buffer->buffer;
struct buffer_page *next_page;
int ret;
@@ -1892,13 +1892,10 @@ static struct ring_buffer_event *
__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
unsigned type, unsigned long length, u64 *ts)
{
- struct buffer_page *tail_page, *commit_page;
+ struct buffer_page *tail_page;
struct ring_buffer_event *event;
unsigned long tail, write;
- commit_page = cpu_buffer->commit_page;
- /* we just need to protect against interrupts */
- barrier();
tail_page = cpu_buffer->tail_page;
write = local_add_return(length, &tail_page->write);
@@ -1909,7 +1906,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
/* See if we shot pass the end of this buffer page */
if (write > BUF_PAGE_SIZE)
return rb_move_tail(cpu_buffer, length, tail,
- commit_page, tail_page, ts);
+ tail_page, ts);
/* We reserved something on the buffer */
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 573d3cc762c..b2477caf09c 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -35,6 +35,28 @@ static int disable_reader;
module_param(disable_reader, uint, 0644);
MODULE_PARM_DESC(disable_reader, "only run producer");
+static int write_iteration = 50;
+module_param(write_iteration, uint, 0644);
+MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
+
+static int producer_nice = 19;
+static int consumer_nice = 19;
+
+static int producer_fifo = -1;
+static int consumer_fifo = -1;
+
+module_param(producer_nice, uint, 0644);
+MODULE_PARM_DESC(producer_nice, "nice prio for producer");
+
+module_param(consumer_nice, uint, 0644);
+MODULE_PARM_DESC(consumer_nice, "nice prio for consumer");
+
+module_param(producer_fifo, uint, 0644);
+MODULE_PARM_DESC(producer_fifo, "fifo prio for producer");
+
+module_param(consumer_fifo, uint, 0644);
+MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer");
+
static int read_events;
static int kill_test;
@@ -208,15 +230,18 @@ static void ring_buffer_producer(void)
do {
struct ring_buffer_event *event;
int *entry;
-
- event = ring_buffer_lock_reserve(buffer, 10);
- if (!event) {
- missed++;
- } else {
- hit++;
- entry = ring_buffer_event_data(event);
- *entry = smp_processor_id();
- ring_buffer_unlock_commit(buffer, event);
+ int i;
+
+ for (i = 0; i < write_iteration; i++) {
+ event = ring_buffer_lock_reserve(buffer, 10);
+ if (!event) {
+ missed++;
+ } else {
+ hit++;
+ entry = ring_buffer_event_data(event);
+ *entry = smp_processor_id();
+ ring_buffer_unlock_commit(buffer, event);
+ }
}
do_gettimeofday(&end_tv);
@@ -263,6 +288,27 @@ static void ring_buffer_producer(void)
if (kill_test)
trace_printk("ERROR!\n");
+
+ if (!disable_reader) {
+ if (consumer_fifo < 0)
+ trace_printk("Running Consumer at nice: %d\n",
+ consumer_nice);
+ else
+ trace_printk("Running Consumer at SCHED_FIFO %d\n",
+ consumer_fifo);
+ }
+ if (producer_fifo < 0)
+ trace_printk("Running Producer at nice: %d\n",
+ producer_nice);
+ else
+ trace_printk("Running Producer at SCHED_FIFO %d\n",
+ producer_fifo);
+
+ /* Let the user know that the test is running at low priority */
+ if (producer_fifo < 0 && consumer_fifo < 0 &&
+ producer_nice == 19 && consumer_nice == 19)
+ trace_printk("WARNING!!! This test is running at lowest priority.\n");
+
trace_printk("Time: %lld (usecs)\n", time);
trace_printk("Overruns: %lld\n", overruns);
if (disable_reader)
@@ -392,6 +438,27 @@ static int __init ring_buffer_benchmark_init(void)
if (IS_ERR(producer))
goto out_kill;
+ /*
+ * Run them as low-prio background tasks by default:
+ */
+ if (!disable_reader) {
+ if (consumer_fifo >= 0) {
+ struct sched_param param = {
+ .sched_priority = consumer_fifo
+ };
+ sched_setscheduler(consumer, SCHED_FIFO, &param);
+ } else
+ set_user_nice(consumer, consumer_nice);
+ }
+
+ if (producer_fifo >= 0) {
+ struct sched_param param = {
+ .sched_priority = consumer_fifo
+ };
+ sched_setscheduler(producer, SCHED_FIFO, &param);
+ } else
+ set_user_nice(producer, producer_nice);
+
return 0;
out_kill:
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 12b49caedf8..874f2893cff 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -129,7 +129,7 @@ static int tracing_set_tracer(const char *buf);
static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
static char *default_bootup_tracer;
-static int __init set_ftrace(char *str)
+static int __init set_cmdline_ftrace(char *str)
{
strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
default_bootup_tracer = bootup_tracer_buf;
@@ -137,7 +137,7 @@ static int __init set_ftrace(char *str)
ring_buffer_expanded = 1;
return 1;
}
-__setup("ftrace=", set_ftrace);
+__setup("ftrace=", set_cmdline_ftrace);
static int __init set_ftrace_dump_on_oops(char *str)
{
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 405cb850b75..acef8b4636f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -483,10 +483,6 @@ static inline int ftrace_graph_addr(unsigned long addr)
return 0;
}
#else
-static inline int ftrace_trace_addr(unsigned long addr)
-{
- return 1;
-}
static inline int ftrace_graph_addr(unsigned long addr)
{
return 1;
@@ -500,12 +496,12 @@ print_graph_function(struct trace_iterator *iter)
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-extern struct pid *ftrace_pid_trace;
+extern struct list_head ftrace_pids;
#ifdef CONFIG_FUNCTION_TRACER
static inline int ftrace_trace_task(struct task_struct *task)
{
- if (!ftrace_pid_trace)
+ if (list_empty(&ftrace_pids))
return 1;
return test_tsk_trace_trace(task);
@@ -699,22 +695,40 @@ struct event_subsystem {
};
struct filter_pred;
+struct regex;
typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
int val1, int val2);
+typedef int (*regex_match_func)(char *str, struct regex *r, int len);
+
+enum regex_type {
+ MATCH_FULL,
+ MATCH_FRONT_ONLY,
+ MATCH_MIDDLE_ONLY,
+ MATCH_END_ONLY,
+};
+
+struct regex {
+ char pattern[MAX_FILTER_STR_VAL];
+ int len;
+ int field_len;
+ regex_match_func match;
+};
+
struct filter_pred {
- filter_pred_fn_t fn;
- u64 val;
- char str_val[MAX_FILTER_STR_VAL];
- int str_len;
- char *field_name;
- int offset;
- int not;
- int op;
- int pop_n;
+ filter_pred_fn_t fn;
+ u64 val;
+ struct regex regex;
+ char *field_name;
+ int offset;
+ int not;
+ int op;
+ int pop_n;
};
+extern enum regex_type
+filter_parse_regex(char *buff, int len, char **search, int *not);
extern void print_event_filter(struct ftrace_event_call *call,
struct trace_seq *s);
extern int apply_event_filter(struct ftrace_event_call *call,
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 20c5f92e28a..878c03f386b 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -20,6 +20,8 @@
#include <linux/ktime.h>
#include <linux/trace_clock.h>
+#include "trace.h"
+
/*
* trace_clock_local(): the simplest and least coherent tracing clock.
*
@@ -28,17 +30,17 @@
*/
u64 notrace trace_clock_local(void)
{
- unsigned long flags;
u64 clock;
+ int resched;
/*
* sched_clock() is an architecture implemented, fast, scalable,
* lockless clock. It is not guaranteed to be coherent across
* CPUs, nor across CPU idle events.
*/
- raw_local_irq_save(flags);
+ resched = ftrace_preempt_disable();
clock = sched_clock();
- raw_local_irq_restore(flags);
+ ftrace_preempt_enable(resched);
return clock;
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index d128f65778e..5e9ffc33f6d 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -878,9 +878,9 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
"'%s/filter' entry\n", name);
}
- entry = trace_create_file("enable", 0644, system->entry,
- (void *)system->name,
- &ftrace_system_enable_fops);
+ trace_create_file("enable", 0644, system->entry,
+ (void *)system->name,
+ &ftrace_system_enable_fops);
return system->entry;
}
@@ -892,7 +892,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
const struct file_operations *filter,
const struct file_operations *format)
{
- struct dentry *entry;
int ret;
/*
@@ -910,12 +909,12 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
}
if (call->regfunc)
- entry = trace_create_file("enable", 0644, call->dir, call,
- enable);
+ trace_create_file("enable", 0644, call->dir, call,
+ enable);
if (call->id && call->profile_enable)
- entry = trace_create_file("id", 0444, call->dir, call,
- id);
+ trace_create_file("id", 0444, call->dir, call,
+ id);
if (call->define_fields) {
ret = call->define_fields(call);
@@ -924,16 +923,16 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
" events/%s\n", call->name);
return ret;
}
- entry = trace_create_file("filter", 0644, call->dir, call,
- filter);
+ trace_create_file("filter", 0644, call->dir, call,
+ filter);
}
/* A trace may not want to export its format */
if (!call->show_format)
return 0;
- entry = trace_create_file("format", 0444, call->dir, call,
- format);
+ trace_create_file("format", 0444, call->dir, call,
+ format);
return 0;
}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 98a6cc5c64e..92672016da2 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -18,8 +18,6 @@
* Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
*/
-#include <linux/debugfs.h>
-#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/mutex.h>
@@ -197,9 +195,9 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
char *addr = (char *)(event + pred->offset);
int cmp, match;
- cmp = strncmp(addr, pred->str_val, pred->str_len);
+ cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len);
- match = (!cmp) ^ pred->not;
+ match = cmp ^ pred->not;
return match;
}
@@ -211,9 +209,9 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event,
char **addr = (char **)(event + pred->offset);
int cmp, match;
- cmp = strncmp(*addr, pred->str_val, pred->str_len);
+ cmp = pred->regex.match(*addr, &pred->regex, pred->regex.field_len);
- match = (!cmp) ^ pred->not;
+ match = cmp ^ pred->not;
return match;
}
@@ -237,9 +235,9 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event,
char *addr = (char *)(event + str_loc);
int cmp, match;
- cmp = strncmp(addr, pred->str_val, str_len);
+ cmp = pred->regex.match(addr, &pred->regex, str_len);
- match = (!cmp) ^ pred->not;
+ match = cmp ^ pred->not;
return match;
}
@@ -250,6 +248,124 @@ static int filter_pred_none(struct filter_pred *pred, void *event,
return 0;
}
+/* Basic regex callbacks */
+static int regex_match_full(char *str, struct regex *r, int len)
+{
+ if (strncmp(str, r->pattern, len) == 0)
+ return 1;
+ return 0;
+}
+
+static int regex_match_front(char *str, struct regex *r, int len)
+{
+ if (strncmp(str, r->pattern, len) == 0)
+ return 1;
+ return 0;
+}
+
+static int regex_match_middle(char *str, struct regex *r, int len)
+{
+ if (strstr(str, r->pattern))
+ return 1;
+ return 0;
+}
+
+static int regex_match_end(char *str, struct regex *r, int len)
+{
+ char *ptr = strstr(str, r->pattern);
+
+ if (ptr && (ptr[r->len] == 0))
+ return 1;
+ return 0;
+}
+
+/**
+ * filter_parse_regex - parse a basic regex
+ * @buff: the raw regex
+ * @len: length of the regex
+ * @search: will point to the beginning of the string to compare
+ * @not: tell whether the match will have to be inverted
+ *
+ * This passes in a buffer containing a regex and this function will
+ * set search to point to the search part of the buffer and
+ * return the type of search it is (see enum above).
+ * This does modify buff.
+ *
+ * Returns enum type.
+ * search returns the pointer to use for comparison.
+ * not returns 1 if buff started with a '!'
+ * 0 otherwise.
+ */
+enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
+{
+ int type = MATCH_FULL;
+ int i;
+
+ if (buff[0] == '!') {
+ *not = 1;
+ buff++;
+ len--;
+ } else
+ *not = 0;
+
+ *search = buff;
+
+ for (i = 0; i < len; i++) {
+ if (buff[i] == '*') {
+ if (!i) {
+ *search = buff + 1;
+ type = MATCH_END_ONLY;
+ } else {
+ if (type == MATCH_END_ONLY)
+ type = MATCH_MIDDLE_ONLY;
+ else
+ type = MATCH_FRONT_ONLY;
+ buff[i] = 0;
+ break;
+ }
+ }
+ }
+
+ return type;
+}
+
+static int filter_build_regex(struct filter_pred *pred)
+{
+ struct regex *r = &pred->regex;
+ char *search, *dup;
+ enum regex_type type;
+ int not;
+
+ type = filter_parse_regex(r->pattern, r->len, &search, &not);
+ dup = kstrdup(search, GFP_KERNEL);
+ if (!dup)
+ return -ENOMEM;
+
+ strcpy(r->pattern, dup);
+ kfree(dup);
+
+ r->len = strlen(r->pattern);
+
+ switch (type) {
+ case MATCH_FULL:
+ r->match = regex_match_full;
+ break;
+ case MATCH_FRONT_ONLY:
+ r->match = regex_match_front;
+ break;
+ case MATCH_MIDDLE_ONLY:
+ r->match = regex_match_middle;
+ break;
+ case MATCH_END_ONLY:
+ r->match = regex_match_end;
+ break;
+ }
+
+ pred->not ^= not;
+
+ return 0;
+}
+
/* return 1 if event matches, 0 otherwise (discard) */
int filter_match_preds(struct ftrace_event_call *call, void *rec)
{
@@ -396,7 +512,7 @@ static void filter_clear_pred(struct filter_pred *pred)
{
kfree(pred->field_name);
pred->field_name = NULL;
- pred->str_len = 0;
+ pred->regex.len = 0;
}
static int filter_set_pred(struct filter_pred *dest,
@@ -660,21 +776,24 @@ static int filter_add_pred(struct filter_parse_state *ps,
}
if (is_string_field(field)) {
- pred->str_len = field->size;
+ ret = filter_build_regex(pred);
+ if (ret)
+ return ret;
- if (field->filter_type == FILTER_STATIC_STRING)
+ if (field->filter_type == FILTER_STATIC_STRING) {
fn = filter_pred_string;
- else if (field->filter_type == FILTER_DYN_STRING)
- fn = filter_pred_strloc;
+ pred->regex.field_len = field->size;
+ } else if (field->filter_type == FILTER_DYN_STRING)
+ fn = filter_pred_strloc;
else {
fn = filter_pred_pchar;
- pred->str_len = strlen(pred->str_val);
+ pred->regex.field_len = strlen(pred->regex.pattern);
}
} else {
if (field->is_signed)
- ret = strict_strtoll(pred->str_val, 0, &val);
+ ret = strict_strtoll(pred->regex.pattern, 0, &val);
else
- ret = strict_strtoull(pred->str_val, 0, &val);
+ ret = strict_strtoull(pred->regex.pattern, 0, &val);
if (ret) {
parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
return -EINVAL;
@@ -1045,8 +1164,8 @@ static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
return NULL;
}
- strcpy(pred->str_val, operand2);
- pred->str_len = strlen(operand2);
+ strcpy(pred->regex.pattern, operand2);
+ pred->regex.len = strlen(pred->regex.pattern);
pred->op = op;
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 9753fcc61bc..c74848ddb85 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -48,11 +48,11 @@
struct ____ftrace_##name { \
tstruct \
}; \
-static void __used ____ftrace_check_##name(void) \
+static void __always_unused ____ftrace_check_##name(void) \
{ \
struct ____ftrace_##name *__entry = NULL; \
\
- /* force cmpile-time check on F_printk() */ \
+ /* force compile-time check on F_printk() */ \
printk(print); \
}
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 527e17eae57..ddee9c59373 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -14,6 +14,69 @@ static int sys_refcount_exit;
static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+{
+ struct syscall_metadata *start;
+ struct syscall_metadata *stop;
+ char str[KSYM_SYMBOL_LEN];
+
+
+ start = (struct syscall_metadata *)__start_syscalls_metadata;
+ stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+ kallsyms_lookup(syscall, NULL, NULL, NULL, str);
+
+ for ( ; start < stop; start++) {
+ /*
+ * Only compare after the "sys" prefix. Archs that use
+ * syscall wrappers may have syscalls symbols aliases prefixed
+ * with "SyS" instead of "sys", leading to an unwanted
+ * mismatch.
+ */
+ if (start->name && !strcmp(start->name + 3, str + 3))
+ return start;
+ }
+ return NULL;
+}
+
+static struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+ if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
+ return NULL;
+
+ return syscalls_metadata[nr];
+}
+
+int syscall_name_to_nr(char *name)
+{
+ int i;
+
+ if (!syscalls_metadata)
+ return -1;
+
+ for (i = 0; i < NR_syscalls; i++) {
+ if (syscalls_metadata[i]) {
+ if (!strcmp(syscalls_metadata[i]->name, name))
+ return i;
+ }
+ }
+ return -1;
+}
+
+void set_syscall_enter_id(int num, int id)
+{
+ syscalls_metadata[num]->enter_id = id;
+}
+
+void set_syscall_exit_id(int num, int id)
+{
+ syscalls_metadata[num]->exit_id = id;
+}
+
enum print_line_t
print_syscall_enter(struct trace_iterator *iter, int flags)
{
@@ -375,6 +438,29 @@ struct trace_event event_syscall_exit = {
.trace = print_syscall_exit,
};
+int __init init_ftrace_syscalls(void)
+{
+ struct syscall_metadata *meta;
+ unsigned long addr;
+ int i;
+
+ syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
+ NR_syscalls, GFP_KERNEL);
+ if (!syscalls_metadata) {
+ WARN_ON(1);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < NR_syscalls; i++) {
+ addr = arch_syscall_addr(i);
+ meta = find_syscall_meta(addr);
+ syscalls_metadata[i] = meta;
+ }
+
+ return 0;
+}
+core_initcall(init_ftrace_syscalls);
+
#ifdef CONFIG_EVENT_PROFILE
static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);