summaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig15
-rw-r--r--kernel/trace/Makefile2
-rw-r--r--kernel/trace/blktrace.c6
-rw-r--r--kernel/trace/ftrace.c82
-rw-r--r--kernel/trace/power-traces.c1
-rw-r--r--kernel/trace/ring_buffer.c64
-rw-r--r--kernel/trace/ring_buffer_benchmark.c1
-rw-r--r--kernel/trace/trace.c206
-rw-r--r--kernel/trace/trace.h11
-rw-r--r--kernel/trace/trace_branch.c19
-rw-r--r--kernel/trace/trace_clock.c5
-rw-r--r--kernel/trace/trace_event_perf.c (renamed from kernel/trace/trace_event_profile.c)63
-rw-r--r--kernel/trace/trace_events.c84
-rw-r--r--kernel/trace/trace_events_filter.c1
-rw-r--r--kernel/trace/trace_export.c87
-rw-r--r--kernel/trace/trace_functions_graph.c108
-rw-r--r--kernel/trace/trace_kprobe.c139
-rw-r--r--kernel/trace/trace_ksym.c1
-rw-r--r--kernel/trace/trace_mmiotrace.c1
-rw-r--r--kernel/trace/trace_selftest.c1
-rw-r--r--kernel/trace/trace_stack.c24
-rw-r--r--kernel/trace/trace_stat.c1
-rw-r--r--kernel/trace/trace_syscalls.c186
-rw-r--r--kernel/trace/trace_workqueue.c1
24 files changed, 645 insertions, 464 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 6c22d8a2f289..13e13d428cd3 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -27,9 +27,7 @@ config HAVE_FUNCTION_GRAPH_TRACER
config HAVE_FUNCTION_GRAPH_FP_TEST
bool
help
- An arch may pass in a unique value (frame pointer) to both the
- entering and exiting of a function. On exit, the value is compared
- and if it does not match, then it will panic the kernel.
+ See Documentation/trace/ftrace-design.txt
config HAVE_FUNCTION_TRACE_MCOUNT_TEST
bool
@@ -330,15 +328,6 @@ config BRANCH_TRACER
Say N if unsure.
-config POWER_TRACER
- bool "Trace power consumption behavior"
- depends on X86
- select GENERIC_TRACER
- help
- This tracer helps developers to analyze and optimize the kernel's
- power management decisions, specifically the C-state and P-state
- behavior.
-
config KSYM_TRACER
bool "Trace read and write access on kernel memory locations"
depends on HAVE_HW_BREAKPOINT
@@ -451,7 +440,7 @@ config BLK_DEV_IO_TRACE
config KPROBE_EVENT
depends on KPROBES
- depends on X86
+ depends on HAVE_REGS_AND_STACK_ACCESS_API
bool "Enable kprobes-based dynamic events"
select TRACING
default y
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index d00c6fe23f54..78edc6490038 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -52,7 +52,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events.o
obj-$(CONFIG_EVENT_TRACING) += trace_export.o
obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
ifeq ($(CONFIG_PERF_EVENTS),y)
-obj-$(CONFIG_EVENT_TRACING) += trace_event_profile.o
+obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
endif
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index d9d6206e0b14..b3bc91a3f510 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -21,6 +21,7 @@
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mutex.h>
+#include <linux/slab.h>
#include <linux/debugfs.h>
#include <linux/smp_lock.h>
#include <linux/time.h>
@@ -540,9 +541,10 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
if (ret)
return ret;
- if (copy_to_user(arg, &buts, sizeof(buts)))
+ if (copy_to_user(arg, &buts, sizeof(buts))) {
+ blk_trace_remove(q);
return -EFAULT;
-
+ }
return 0;
}
EXPORT_SYMBOL_GPL(blk_trace_setup);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1904797f4a8a..2404b59b3097 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -24,9 +24,11 @@
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/sysctl.h>
+#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/list.h>
#include <linux/hash.h>
+#include <linux/rcupdate.h>
#include <trace/events/sched.h>
@@ -84,22 +86,22 @@ 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
-
+/*
+ * Traverse the ftrace_list, invoking all entries. The reason that we
+ * can use rcu_dereference_raw() is that elements removed from this list
+ * are simply leaked, so there is no need to interact with a grace-period
+ * mechanism. The rcu_dereference_raw() calls are needed to handle
+ * concurrent insertions into the ftrace_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
{
- struct ftrace_ops *op = ftrace_list;
-
- /* in case someone actually ports this to alpha! */
- read_barrier_depends();
+ struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/
while (op != &ftrace_list_end) {
- /* silly alpha */
- read_barrier_depends();
op->func(ip, parent_ip);
- op = op->next;
+ op = rcu_dereference_raw(op->next); /*see above*/
};
}
@@ -154,8 +156,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
* the ops->next pointer is valid before another CPU sees
* the ops pointer included into the ftrace_list.
*/
- smp_wmb();
- ftrace_list = ops;
+ rcu_assign_pointer(ftrace_list, ops);
if (ftrace_enabled) {
ftrace_func_t func;
@@ -2276,6 +2277,8 @@ __setup("ftrace_filter=", set_ftrace_filter);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
+static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+
static int __init set_graph_function(char *str)
{
strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
@@ -2402,6 +2405,7 @@ static const struct file_operations ftrace_notrace_fops = {
static DEFINE_MUTEX(graph_lock);
int ftrace_graph_count;
+int ftrace_graph_filter_enabled;
unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
static void *
@@ -2424,7 +2428,7 @@ static void *g_start(struct seq_file *m, loff_t *pos)
mutex_lock(&graph_lock);
/* Nothing, tell g_show to print all functions are enabled */
- if (!ftrace_graph_count && !*pos)
+ if (!ftrace_graph_filter_enabled && !*pos)
return (void *)1;
return __g_next(m, pos);
@@ -2470,6 +2474,7 @@ ftrace_graph_open(struct inode *inode, struct file *file)
mutex_lock(&graph_lock);
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC)) {
+ ftrace_graph_filter_enabled = 0;
ftrace_graph_count = 0;
memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
}
@@ -2495,7 +2500,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
struct dyn_ftrace *rec;
struct ftrace_page *pg;
int search_len;
- int found = 0;
+ int fail = 1;
int type, not;
char *search;
bool exists;
@@ -2506,37 +2511,51 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
/* decode regex */
type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
- if (not)
- return -EINVAL;
+ if (!not && *idx >= FTRACE_GRAPH_MAX_FUNCS)
+ return -EBUSY;
search_len = strlen(search);
mutex_lock(&ftrace_lock);
do_for_each_ftrace_rec(pg, rec) {
- if (*idx >= FTRACE_GRAPH_MAX_FUNCS)
- break;
-
if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE))
continue;
if (ftrace_match_record(rec, search, search_len, type)) {
- /* ensure it is not already in the array */
+ /* if it is in the array */
exists = false;
- for (i = 0; i < *idx; i++)
+ for (i = 0; i < *idx; i++) {
if (array[i] == rec->ip) {
exists = true;
break;
}
- if (!exists)
- array[(*idx)++] = rec->ip;
- found = 1;
+ }
+
+ if (!not) {
+ fail = 0;
+ if (!exists) {
+ array[(*idx)++] = rec->ip;
+ if (*idx >= FTRACE_GRAPH_MAX_FUNCS)
+ goto out;
+ }
+ } else {
+ if (exists) {
+ array[i] = array[--(*idx)];
+ array[*idx] = 0;
+ fail = 0;
+ }
+ }
}
} while_for_each_ftrace_rec();
-
+out:
mutex_unlock(&ftrace_lock);
- return found ? 0 : -EINVAL;
+ if (fail)
+ return -EINVAL;
+
+ ftrace_graph_filter_enabled = 1;
+ return 0;
}
static ssize_t
@@ -2546,16 +2565,11 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
struct trace_parser parser;
ssize_t read, ret;
- if (!cnt || cnt < 0)
+ if (!cnt)
return 0;
mutex_lock(&graph_lock);
- if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) {
- ret = -EBUSY;
- goto out_unlock;
- }
-
if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
ret = -ENOMEM;
goto out_unlock;
@@ -3340,6 +3354,7 @@ void ftrace_graph_init_task(struct task_struct *t)
{
/* Make sure we do not use the parent ret_stack */
t->ret_stack = NULL;
+ t->curr_ret_stack = -1;
if (ftrace_graph_active) {
struct ftrace_ret_stack *ret_stack;
@@ -3349,7 +3364,6 @@ void ftrace_graph_init_task(struct task_struct *t)
GFP_KERNEL);
if (!ret_stack)
return;
- t->curr_ret_stack = -1;
atomic_set(&t->tracing_graph_pause, 0);
atomic_set(&t->trace_overrun, 0);
t->ftrace_timestamp = 0;
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index 9f4f565b01e6..a22582a06161 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -9,7 +9,6 @@
#include <linux/workqueue.h>
#include <linux/sched.h>
#include <linux/module.h>
-#include <linux/slab.h>
#define CREATE_TRACE_POINTS
#include <trace/events/power.h>
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index edefe3b2801b..41ca394feb22 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -14,12 +14,14 @@
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/mutex.h>
+#include <linux/slab.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/list.h>
#include <linux/cpu.h>
#include <linux/fs.h>
+#include <asm/local.h>
#include "trace.h"
/*
@@ -206,6 +208,14 @@ EXPORT_SYMBOL_GPL(tracing_is_on);
#define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
#define RB_EVNT_MIN_SIZE 8U /* two 32bit words */
+#if !defined(CONFIG_64BIT) || defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+# define RB_FORCE_8BYTE_ALIGNMENT 0
+# define RB_ARCH_ALIGNMENT RB_ALIGNMENT
+#else
+# define RB_FORCE_8BYTE_ALIGNMENT 1
+# define RB_ARCH_ALIGNMENT 8U
+#endif
+
/* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
#define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
@@ -464,6 +474,8 @@ struct ring_buffer_iter {
struct ring_buffer_per_cpu *cpu_buffer;
unsigned long head;
struct buffer_page *head_page;
+ struct buffer_page *cache_reader_page;
+ unsigned long cache_read;
u64 read_stamp;
};
@@ -1198,18 +1210,19 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
for (i = 0; i < nr_pages; i++) {
if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
- return;
+ goto out;
p = cpu_buffer->pages->next;
bpage = list_entry(p, struct buffer_page, list);
list_del_init(&bpage->list);
free_buffer_page(bpage);
}
if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
- return;
+ goto out;
rb_reset_cpu(cpu_buffer);
rb_check_pages(cpu_buffer);
+out:
spin_unlock_irq(&cpu_buffer->reader_lock);
}
@@ -1226,7 +1239,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
for (i = 0; i < nr_pages; i++) {
if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
- return;
+ goto out;
p = pages->next;
bpage = list_entry(p, struct buffer_page, list);
list_del_init(&bpage->list);
@@ -1235,6 +1248,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
rb_reset_cpu(cpu_buffer);
rb_check_pages(cpu_buffer);
+out:
spin_unlock_irq(&cpu_buffer->reader_lock);
}
@@ -1544,7 +1558,7 @@ rb_update_event(struct ring_buffer_event *event,
case 0:
length -= RB_EVNT_HDR_SIZE;
- if (length > RB_MAX_SMALL_DATA)
+ if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
event->array[0] = length;
else
event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
@@ -1719,11 +1733,11 @@ static unsigned rb_calculate_event_length(unsigned length)
if (!length)
length = 1;
- if (length > RB_MAX_SMALL_DATA)
+ if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
length += sizeof(event.array[0]);
length += RB_EVNT_HDR_SIZE;
- length = ALIGN(length, RB_ALIGNMENT);
+ length = ALIGN(length, RB_ARCH_ALIGNMENT);
return length;
}
@@ -2230,12 +2244,12 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
if (ring_buffer_flags != RB_BUFFERS_ON)
return NULL;
- if (atomic_read(&buffer->record_disabled))
- return NULL;
-
/* If we are tracing schedule, we don't want to recurse */
resched = ftrace_preempt_disable();
+ if (atomic_read(&buffer->record_disabled))
+ goto out_nocheck;
+
if (trace_recursive_lock())
goto out_nocheck;
@@ -2467,11 +2481,11 @@ int ring_buffer_write(struct ring_buffer *buffer,
if (ring_buffer_flags != RB_BUFFERS_ON)
return -EBUSY;
- if (atomic_read(&buffer->record_disabled))
- return -EBUSY;
-
resched = ftrace_preempt_disable();
+ if (atomic_read(&buffer->record_disabled))
+ goto out;
+
cpu = raw_smp_processor_id();
if (!cpumask_test_cpu(cpu, buffer->cpumask))
@@ -2539,7 +2553,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable);
* @buffer: The ring buffer to enable writes
*
* Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
*/
void ring_buffer_record_enable(struct ring_buffer *buffer)
{
@@ -2575,7 +2589,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);
* @cpu: The CPU to enable.
*
* Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
*/
void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
{
@@ -2716,6 +2730,8 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
iter->read_stamp = cpu_buffer->read_stamp;
else
iter->read_stamp = iter->head_page->page->time_stamp;
+ iter->cache_reader_page = cpu_buffer->reader_page;
+ iter->cache_read = cpu_buffer->read;
}
/**
@@ -3060,13 +3076,22 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
struct ring_buffer_event *event;
int nr_loops = 0;
- if (ring_buffer_iter_empty(iter))
- return NULL;
-
cpu_buffer = iter->cpu_buffer;
buffer = cpu_buffer->buffer;
+ /*
+ * Check if someone performed a consuming read to
+ * the buffer. A consuming read invalidates the iterator
+ * and we need to reset the iterator in this case.
+ */
+ if (unlikely(iter->cache_read != cpu_buffer->read ||
+ iter->cache_reader_page != cpu_buffer->reader_page))
+ rb_iter_reset(iter);
+
again:
+ if (ring_buffer_iter_empty(iter))
+ return NULL;
+
/*
* We repeat when a timestamp is encountered.
* We can get multiple timestamps by nested interrupts or also
@@ -3081,6 +3106,11 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
if (rb_per_cpu_empty(cpu_buffer))
return NULL;
+ if (iter->head >= local_read(&iter->head_page->page->commit)) {
+ rb_inc_iter(iter);
+ goto again;
+ }
+
event = rb_iter_head_event(iter);
switch (event->type_len) {
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index b2477caf09c2..df74c7982255 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -8,6 +8,7 @@
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/time.h>
+#include <asm/local.h>
struct rb_page {
u64 ts;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0df1b0f2cb9e..44f916a04065 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -32,10 +32,11 @@
#include <linux/splice.h>
#include <linux/kdebug.h>
#include <linux/string.h>
+#include <linux/rwsem.h>
+#include <linux/slab.h>
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/poll.h>
-#include <linux/gfp.h>
#include <linux/fs.h>
#include "trace.h"
@@ -91,20 +92,17 @@ DEFINE_PER_CPU(int, ftrace_cpu_disabled);
static inline void ftrace_disable_cpu(void)
{
preempt_disable();
- __this_cpu_inc(per_cpu_var(ftrace_cpu_disabled));
+ __this_cpu_inc(ftrace_cpu_disabled);
}
static inline void ftrace_enable_cpu(void)
{
- __this_cpu_dec(per_cpu_var(ftrace_cpu_disabled));
+ __this_cpu_dec(ftrace_cpu_disabled);
preempt_enable();
}
static cpumask_var_t __read_mostly tracing_buffer_mask;
-/* Define which cpu buffers are currently read in trace_pipe */
-static cpumask_var_t tracing_reader_cpumask;
-
#define for_each_tracing_cpu(cpu) \
for_each_cpu(cpu, tracing_buffer_mask)
@@ -243,12 +241,91 @@ static struct tracer *current_trace __read_mostly;
/*
* trace_types_lock is used to protect the trace_types list.
- * This lock is also used to keep user access serialized.
- * Accesses from userspace will grab this lock while userspace
- * activities happen inside the kernel.
*/
static DEFINE_MUTEX(trace_types_lock);
+/*
+ * serialize the access of the ring buffer
+ *
+ * ring buffer serializes readers, but it is low level protection.
+ * The validity of the events (which returns by ring_buffer_peek() ..etc)
+ * are not protected by ring buffer.
+ *
+ * The content of events may become garbage if we allow other process consumes
+ * these events concurrently:
+ * A) the page of the consumed events may become a normal page
+ * (not reader page) in ring buffer, and this page will be rewrited
+ * by events producer.
+ * B) The page of the consumed events may become a page for splice_read,
+ * and this page will be returned to system.
+ *
+ * These primitives allow multi process access to different cpu ring buffer
+ * concurrently.
+ *
+ * These primitives don't distinguish read-only and read-consume access.
+ * Multi read-only access are also serialized.
+ */
+
+#ifdef CONFIG_SMP
+static DECLARE_RWSEM(all_cpu_access_lock);
+static DEFINE_PER_CPU(struct mutex, cpu_access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+ if (cpu == TRACE_PIPE_ALL_CPU) {
+ /* gain it for accessing the whole ring buffer. */
+ down_write(&all_cpu_access_lock);
+ } else {
+ /* gain it for accessing a cpu ring buffer. */
+
+ /* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */
+ down_read(&all_cpu_access_lock);
+
+ /* Secondly block other access to this @cpu ring buffer. */
+ mutex_lock(&per_cpu(cpu_access_lock, cpu));
+ }
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+ if (cpu == TRACE_PIPE_ALL_CPU) {
+ up_write(&all_cpu_access_lock);
+ } else {
+ mutex_unlock(&per_cpu(cpu_access_lock, cpu));
+ up_read(&all_cpu_access_lock);
+ }
+}
+
+static inline void trace_access_lock_init(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ mutex_init(&per_cpu(cpu_access_lock, cpu));
+}
+
+#else
+
+static DEFINE_MUTEX(access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+ (void)cpu;
+ mutex_lock(&access_lock);
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+ (void)cpu;
+ mutex_unlock(&access_lock);
+}
+
+static inline void trace_access_lock_init(void)
+{
+}
+
+#endif
+
/* trace_wait is a waitqueue for tasks blocked on trace_poll */
static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
@@ -297,6 +374,21 @@ static int __init set_buf_size(char *str)
}
__setup("trace_buf_size=", set_buf_size);
+static int __init set_tracing_thresh(char *str)
+{
+ unsigned long threshhold;
+ int ret;
+
+ if (!str)
+ return 0;
+ ret = strict_strtoul(str, 0, &threshhold);
+ if (ret < 0)
+ return 0;
+ tracing_thresh = threshhold * 1000;
+ return 1;
+}
+__setup("tracing_thresh=", set_tracing_thresh);
+
unsigned long nsecs_to_usecs(unsigned long nsecs)
{
return nsecs / 1000;
@@ -502,9 +594,10 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
static arch_spinlock_t ftrace_max_lock =
(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+unsigned long __read_mostly tracing_thresh;
+
#ifdef CONFIG_TRACER_MAX_TRACE
unsigned long __read_mostly tracing_max_latency;
-unsigned long __read_mostly tracing_thresh;
/*
* Copy the new maximum trace into the separate maximum-trace
@@ -515,7 +608,7 @@ static void
__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
struct trace_array_cpu *data = tr->data[cpu];
- struct trace_array_cpu *max_data = tr->data[cpu];
+ struct trace_array_cpu *max_data;
max_tr.cpu = cpu;
max_tr.time_start = data->preempt_timestamp;
@@ -525,7 +618,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
max_data->critical_start = data->critical_start;
max_data->critical_end = data->critical_end;
- memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
+ memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
max_data->pid = tsk->pid;
max_data->uid = task_uid(tsk);
max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
@@ -747,10 +840,10 @@ out:
mutex_unlock(&trace_types_lock);
}
-static void __tracing_reset(struct trace_array *tr, int cpu)
+static void __tracing_reset(struct ring_buffer *buffer, int cpu)
{
ftrace_disable_cpu();
- ring_buffer_reset_cpu(tr->buffer, cpu);
+ ring_buffer_reset_cpu(buffer, cpu);
ftrace_enable_cpu();
}
@@ -762,7 +855,7 @@ void tracing_reset(struct trace_array *tr, int cpu)
/* Make sure all commits have finished */
synchronize_sched();
- __tracing_reset(tr, cpu);
+ __tracing_reset(buffer, cpu);
ring_buffer_record_enable(buffer);
}
@@ -780,7 +873,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
tr->time_start = ftrace_now(tr->cpu);
for_each_online_cpu(cpu)
- __tracing_reset(tr, cpu);
+ __tracing_reset(buffer, cpu);
ring_buffer_record_enable(buffer);
}
@@ -857,6 +950,8 @@ void tracing_start(void)
goto out;
}
+ /* Prevent the buffers from switching */
+ arch_spin_lock(&ftrace_max_lock);
buffer = global_trace.buffer;
if (buffer)
@@ -866,6 +961,8 @@ void tracing_start(void)
if (buffer)
ring_buffer_record_enable(buffer);
+ arch_spin_unlock(&ftrace_max_lock);
+
ftrace_start();
out:
spin_unlock_irqrestore(&tracing_start_lock, flags);
@@ -887,6 +984,9 @@ void tracing_stop(void)
if (trace_stop_count++)
goto out;
+ /* Prevent the buffers from switching */
+ arch_spin_lock(&ftrace_max_lock);
+
buffer = global_trace.buffer;
if (buffer)
ring_buffer_record_disable(buffer);
@@ -895,6 +995,8 @@ void tracing_stop(void)
if (buffer)
ring_buffer_record_disable(buffer);
+ arch_spin_unlock(&ftrace_max_lock);
+
out:
spin_unlock_irqrestore(&tracing_start_lock, flags);
}
@@ -951,6 +1053,11 @@ void trace_find_cmdline(int pid, char comm[])
return;
}
+ if (WARN_ON_ONCE(pid < 0)) {
+ strcpy(comm, "<XXX>");
+ return;
+ }
+
if (pid > PID_MAX_DEFAULT) {
strcpy(comm, "<...>");
return;
@@ -1084,7 +1191,7 @@ trace_function(struct trace_array *tr,
struct ftrace_entry *entry;
/* If we are reading the ring buffer, don't trace */
- if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
return;
event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
@@ -1177,6 +1284,13 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
return;
+ /*
+ * NMIs can not handle page faults, even with fix ups.
+ * The save user stack can (and often does) fault.
+ */
+ if (unlikely(in_nmi()))
+ return;
+
event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
sizeof(*entry), flags, pc);
if (!event)
@@ -1315,8 +1429,10 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
entry->fmt = fmt;
memcpy(entry->buf, trace_buf, sizeof(u32) * len);
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!filter_check_discard(call, entry, buffer, event)) {
ring_buffer_unlock_commit(buffer, event);
+ ftrace_trace_stack(buffer, flags, 6, pc);
+ }
out_unlock:
arch_spin_unlock(&trace_buf_lock);
@@ -1389,8 +1505,10 @@ int trace_array_vprintk(struct trace_array *tr,
memcpy(&entry->buf, trace_buf, len);
entry->buf[len] = '\0';
- if (!filter_check_discard(call, entry, buffer, event))
+ if (!filter_check_discard(call, entry, buffer, event)) {
ring_buffer_unlock_commit(buffer, event);
+ ftrace_trace_stack(buffer, irq_flags, 6, pc);
+ }
out_unlock:
arch_spin_unlock(&trace_buf_lock);
@@ -1580,12 +1698,6 @@ static void tracing_iter_reset(struct trace_iterator *iter, int cpu)
}
/*
- * No necessary locking here. The worst thing which can
- * happen is loosing events consumed at the same time
- * by a trace_pipe reader.
- * Other than that, we don't risk to crash the ring buffer
- * because it serializes the readers.
- *
* The current tracer is copied to avoid a global locking
* all around.
*/
@@ -1623,6 +1735,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
ftrace_enable_cpu();
+ iter->leftover = 0;
for (p = iter; p && l < *pos; p = s_next(m, p, &l))
;
@@ -1640,12 +1753,16 @@ static void *s_start(struct seq_file *m, loff_t *pos)
}
trace_event_read_lock();
+ trace_access_lock(cpu_file);
return p;
}
static void s_stop(struct seq_file *m, void *p)
{
+ struct trace_iterator *iter = m->private;
+
atomic_dec(&trace_record_cmdline_disabled);
+ trace_access_unlock(iter->cpu_file);
trace_event_read_unlock();
}
@@ -2836,22 +2953,6 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
mutex_lock(&trace_types_lock);
- /* We only allow one reader per cpu */
- if (cpu_file == TRACE_PIPE_ALL_CPU) {
- if (!cpumask_empty(tracing_reader_cpumask)) {
- ret = -EBUSY;
- goto out;
- }
- cpumask_setall(tracing_reader_cpumask);
- } else {
- if (!cpumask_test_cpu(cpu_file, tracing_reader_cpumask))
- cpumask_set_cpu(cpu_file, tracing_reader_cpumask);
- else {
- ret = -EBUSY;
- goto out;
- }
- }
-
/* create a buffer to store the information to pass to userspace */
iter = kzalloc(sizeof(*iter), GFP_KERNEL);
if (!iter) {
@@ -2907,12 +3008,6 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
mutex_lock(&trace_types_lock);
- if (iter->cpu_file == TRACE_PIPE_ALL_CPU)
- cpumask_clear(tracing_reader_cpumask);
- else
- cpumask_clear_cpu(iter->cpu_file, tracing_reader_cpumask);
-
-
if (iter->trace->pipe_close)
iter->trace->pipe_close(iter);
@@ -3074,6 +3169,7 @@ waitagain:
iter->pos = -1;
trace_event_read_lock();
+ trace_access_lock(iter->cpu_file);
while (find_next_entry_inc(iter) != NULL) {
enum print_line_t ret;
int len = iter->seq.len;
@@ -3090,6 +3186,7 @@ waitagain:
if (iter->seq.len >= cnt)
break;
}
+ trace_access_unlock(iter->cpu_file);
trace_event_read_unlock();
/* Now copy what we have to the user */
@@ -3215,6 +3312,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
}
trace_event_read_lock();
+ trace_access_lock(iter->cpu_file);
/* Fill as many pages as possible. */
for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
@@ -3238,6 +3336,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
trace_seq_init(&iter->seq);
}
+ trace_access_unlock(iter->cpu_file);
trace_event_read_unlock();
mutex_unlock(&iter->mutex);
@@ -3539,10 +3638,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
info->read = 0;
+ trace_access_lock(info->cpu);
ret = ring_buffer_read_page(info->tr->buffer,
&info->spare,
count,
info->cpu, 0);
+ trace_access_unlock(info->cpu);
if (ret < 0)
return 0;
@@ -3670,6 +3771,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
len &= PAGE_MASK;
}
+ trace_access_lock(info->cpu);
entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
@@ -3717,6 +3819,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
}
+ trace_access_unlock(info->cpu);
spd.nr_pages = i;
/* did we read anything? */
@@ -4153,6 +4256,8 @@ static __init int tracer_init_debugfs(void)
struct dentry *d_tracer;
int cpu;
+ trace_access_lock_init();
+
d_tracer = tracing_init_dentry();
trace_create_file("tracing_enabled", 0644, d_tracer,
@@ -4176,10 +4281,10 @@ static __init int tracer_init_debugfs(void)
#ifdef CONFIG_TRACER_MAX_TRACE
trace_create_file("tracing_max_latency", 0644, d_tracer,
&tracing_max_latency, &tracing_max_lat_fops);
+#endif
trace_create_file("tracing_thresh", 0644, d_tracer,
&tracing_thresh, &tracing_max_lat_fops);
-#endif
trace_create_file("README", 0444, d_tracer,
NULL, &tracing_readme_fops);
@@ -4387,9 +4492,6 @@ __init static int tracer_alloc_buffers(void)
if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
goto out_free_buffer_mask;
- if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
- goto out_free_tracing_cpumask;
-
/* To save memory, keep the ring buffer size to its minimum */
if (ring_buffer_expanded)
ring_buf_size = trace_buf_size;
@@ -4447,8 +4549,6 @@ __init static int tracer_alloc_buffers(void)
return 0;
out_free_cpumask:
- free_cpumask_var(tracing_reader_cpumask);
-out_free_tracing_cpumask:
free_cpumask_var(tracing_cpumask);
out_free_buffer_mask:
free_cpumask_var(tracing_buffer_mask);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 4df6a77eb196..2825ef2c0b15 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -396,9 +396,10 @@ extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
extern unsigned long nsecs_to_usecs(unsigned long nsecs);
+extern unsigned long tracing_thresh;
+
#ifdef CONFIG_TRACER_MAX_TRACE
extern unsigned long tracing_max_latency;
-extern unsigned long tracing_thresh;
void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
void update_max_tr_single(struct trace_array *tr,
@@ -497,6 +498,7 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
#ifdef CONFIG_DYNAMIC_FTRACE
/* TODO: make this variable */
#define FTRACE_GRAPH_MAX_FUNCS 32
+extern int ftrace_graph_filter_enabled;
extern int ftrace_graph_count;
extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
@@ -504,7 +506,7 @@ static inline int ftrace_graph_addr(unsigned long addr)
{
int i;
- if (!ftrace_graph_count || test_tsk_trace_graph(current))
+ if (!ftrace_graph_filter_enabled)
return 1;
for (i = 0; i < ftrace_graph_count; i++) {
@@ -549,7 +551,7 @@ static inline int ftrace_trace_task(struct task_struct *task)
* struct trace_parser - servers for reading the user input separated by spaces
* @cont: set if the input is not complete - no final space char was found
* @buffer: holds the parsed user input
- * @idx: user input lenght
+ * @idx: user input length
* @size: buffer size
*/
struct trace_parser {
@@ -791,7 +793,8 @@ extern const char *__stop___trace_bprintk_fmt[];
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \
- extern struct ftrace_event_call event_##call;
+ extern struct ftrace_event_call \
+ __attribute__((__aligned__(4))) event_##call;
#undef FTRACE_ENTRY_DUP
#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \
FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 4a194f08f88c..b9bc4d470177 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -307,8 +307,23 @@ static int annotated_branch_stat_cmp(void *p1, void *p2)
return -1;
if (percent_a > percent_b)
return 1;
- else
- return 0;
+
+ if (a->incorrect < b->incorrect)
+ return -1;
+ if (a->incorrect > b->incorrect)
+ return 1;
+
+ /*
+ * Since the above shows worse (incorrect) cases
+ * first, we continue that by showing best (correct)
+ * cases last.
+ */
+ if (a->correct > b->correct)
+ return -1;
+ if (a->correct < b->correct)
+ return 1;
+
+ return 0;
}
static struct tracer_stat annotated_branch_stats = {
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 84a3a7ba072a..9d589d8dcd1a 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -13,6 +13,7 @@
* Tracer plugins will chose a default from these clocks.
*/
#include <linux/spinlock.h>
+#include <linux/irqflags.h>
#include <linux/hardirq.h>
#include <linux/module.h>
#include <linux/percpu.h>
@@ -83,7 +84,7 @@ u64 notrace trace_clock_global(void)
int this_cpu;
u64 now;
- raw_local_irq_save(flags);
+ local_irq_save(flags);
this_cpu = raw_smp_processor_id();
now = cpu_clock(this_cpu);
@@ -109,7 +110,7 @@ u64 notrace trace_clock_global(void)
arch_spin_unlock(&trace_clock_struct.lock);
out:
- raw_local_irq_restore(flags);
+ local_irq_restore(flags);
return now;
}
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_perf.c
index f0d693005075..0565bb42566f 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_perf.c
@@ -1,32 +1,41 @@
/*
- * trace event based perf counter profiling
+ * trace event based perf event profiling/tracing
*
* Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
- *
+ * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
*/
#include <linux/module.h>
#include <linux/kprobes.h>
#include "trace.h"
+DEFINE_PER_CPU(struct pt_regs, perf_trace_regs);
+EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs);
+
+EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
static char *perf_trace_buf;
static char *perf_trace_buf_nmi;
-typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ;
+/*
+ * Force it to be aligned to unsigned long to avoid misaligned accesses
+ * suprises
+ */
+typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
+ perf_trace_t;
/* Count the events in use (per event id, not per instance) */
-static int total_profile_count;
+static int total_ref_count;
-static int ftrace_profile_enable_event(struct ftrace_event_call *event)
+static int perf_trace_event_enable(struct ftrace_event_call *event)
{
char *buf;
int ret = -ENOMEM;
- if (event->profile_count++ > 0)
+ if (event->perf_refcount++ > 0)
return 0;
- if (!total_profile_count) {
+ if (!total_ref_count) {
buf = (char *)alloc_percpu(perf_trace_t);
if (!buf)
goto fail_buf;
@@ -40,35 +49,35 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
rcu_assign_pointer(perf_trace_buf_nmi, buf);
}
- ret = event->profile_enable(event);
+ ret = event->perf_event_enable(event);
if (!ret) {
- total_profile_count++;
+ total_ref_count++;
return 0;
}
fail_buf_nmi:
- if (!total_profile_count) {
+ if (!total_ref_count) {
free_percpu(perf_trace_buf_nmi);
free_percpu(perf_trace_buf);
perf_trace_buf_nmi = NULL;
perf_trace_buf = NULL;
}
fail_buf:
- event->profile_count--;
+ event->perf_refcount--;
return ret;
}
-int ftrace_profile_enable(int event_id)
+int perf_trace_enable(int event_id)
{
struct ftrace_event_call *event;
int ret = -EINVAL;
mutex_lock(&event_mutex);
list_for_each_entry(event, &ftrace_events, list) {
- if (event->id == event_id && event->profile_enable &&
+ if (event->id == event_id && event->perf_event_enable &&
try_module_get(event->mod)) {
- ret = ftrace_profile_enable_event(event);
+ ret = perf_trace_event_enable(event);
break;
}
}
@@ -77,16 +86,16 @@ int ftrace_profile_enable(int event_id)
return ret;
}
-static void ftrace_profile_disable_event(struct ftrace_event_call *event)
+static void perf_trace_event_disable(struct ftrace_event_call *event)
{
char *buf, *nmi_buf;
- if (--event->profile_count > 0)
+ if (--event->perf_refcount > 0)
return;
- event->profile_disable(event);
+ event->perf_event_disable(event);
- if (!--total_profile_count) {
+ if (!--total_ref_count) {
buf = perf_trace_buf;
rcu_assign_pointer(perf_trace_buf, NULL);
@@ -104,14 +113,14 @@ static void ftrace_profile_disable_event(struct ftrace_event_call *event)
}
}
-void ftrace_profile_disable(int event_id)
+void perf_trace_disable(int event_id)
{
struct ftrace_event_call *event;
mutex_lock(&event_mutex);
list_for_each_entry(event, &ftrace_events, list) {
if (event->id == event_id) {
- ftrace_profile_disable_event(event);
+ perf_trace_event_disable(event);
module_put(event->mod);
break;
}
@@ -119,13 +128,15 @@ void ftrace_profile_disable(int event_id)
mutex_unlock(&event_mutex);
}
-__kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type,
- int *rctxp, unsigned long *irq_flags)
+__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
+ int *rctxp, unsigned long *irq_flags)
{
struct trace_entry *entry;
char *trace_buf, *raw_data;
int pc, cpu;
+ BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
+
pc = preempt_count();
/* Protect the per cpu buffer, begin the rcu read side */
@@ -138,9 +149,9 @@ __kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type,
cpu = smp_processor_id();
if (in_nmi())
- trace_buf = rcu_dereference(perf_trace_buf_nmi);
+ trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
else
- trace_buf = rcu_dereference(perf_trace_buf);
+ trace_buf = rcu_dereference_sched(perf_trace_buf);
if (!trace_buf)
goto err;
@@ -148,7 +159,7 @@ __kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type,
raw_data = per_cpu_ptr(trace_buf, cpu);
/* zero the dead bytes from align to not leak stack to user */
- *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+ memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
entry = (struct trace_entry *)raw_data;
tracing_generic_entry_update(entry, *irq_flags, pc);
@@ -161,4 +172,4 @@ err_recursion:
local_irq_restore(*irq_flags);
return NULL;
}
-EXPORT_SYMBOL_GPL(ftrace_perf_buf_prepare);
+EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 189b09baf4fb..c697c7043349 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -15,6 +15,7 @@
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
+#include <linux/slab.h>
#include <linux/delay.h>
#include <asm/setup.h>
@@ -60,10 +61,8 @@ int trace_define_field(struct ftrace_event_call *call, const char *type,
return 0;
err:
- if (field) {
+ if (field)
kfree(field->name);
- kfree(field->type);
- }
kfree(field);
return -ENOMEM;
@@ -520,41 +519,16 @@ out:
return ret;
}
-extern char *__bad_type_size(void);
-
-#undef FIELD
-#define FIELD(type, name) \
- sizeof(type) != sizeof(field.name) ? __bad_type_size() : \
- #type, "common_" #name, offsetof(typeof(field), name), \
- sizeof(field.name), is_signed_type(type)
-
-static int trace_write_header(struct trace_seq *s)
-{
- struct trace_entry field;
-
- /* struct trace_entry */
- return trace_seq_printf(s,
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
- "\n",
- FIELD(unsigned short, type),
- FIELD(unsigned char, flags),
- FIELD(unsigned char, preempt_count),
- FIELD(int, pid),
- FIELD(int, lock_depth));
-}
-
static ssize_t
event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
struct ftrace_event_call *call = filp->private_data;
+ struct ftrace_event_field *field;
struct trace_seq *s;
+ int common_field_count = 5;
char *buf;
- int r;
+ int r = 0;
if (*ppos)
return 0;
@@ -565,14 +539,48 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
trace_seq_init(s);
- /* If any of the first writes fail, so will the show_format. */
-
trace_seq_printf(s, "name: %s\n", call->name);
trace_seq_printf(s, "ID: %d\n", call->id);
trace_seq_printf(s, "format:\n");
- trace_write_header(s);
- r = call->show_format(call, s);
+ list_for_each_entry_reverse(field, &call->fields, link) {
+ /*
+ * Smartly shows the array type(except dynamic array).
+ * Normal:
+ * field:TYPE VAR
+ * If TYPE := TYPE[LEN], it is shown:
+ * field:TYPE VAR[LEN]
+ */
+ const char *array_descriptor = strchr(field->type, '[');
+
+ if (!strncmp(field->type, "__data_loc", 10))
+ array_descriptor = NULL;
+
+ if (!array_descriptor) {
+ r = trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
+ "\tsize:%u;\tsigned:%d;\n",
+ field->type, field->name, field->offset,
+ field->size, !!field->is_signed);
+ } else {
+ r = trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
+ "\tsize:%u;\tsigned:%d;\n",
+ (int)(array_descriptor - field->type),
+ field->type, field->name,
+ array_descriptor, field->offset,
+ field->size, !!field->is_signed);
+ }
+
+ if (--common_field_count == 0)
+ r = trace_seq_printf(s, "\n");
+
+ if (!r)
+ break;
+ }
+
+ if (r)
+ r = trace_seq_printf(s, "\nprint fmt: %s\n",
+ call->print_fmt);
+
if (!r) {
/*
* ug! The format output is bigger than a PAGE!!
@@ -931,7 +939,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
trace_create_file("enable", 0644, call->dir, call,
enable);
- if (call->id && call->profile_enable)
+ if (call->id && call->perf_event_enable)
trace_create_file("id", 0444, call->dir, call,
id);
@@ -948,10 +956,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
filter);
}
- /* A trace may not want to export its format */
- if (!call->show_format)
- return 0;
-
trace_create_file("format", 0444, call->dir, call,
format);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 4615f62a04f1..88c0b6dbd7fe 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -22,6 +22,7 @@
#include <linux/ctype.h>
#include <linux/mutex.h>
#include <linux/perf_event.h>
+#include <linux/slab.h>
#include "trace.h"
#include "trace_output.h"
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d4fa5dc1ee4e..e091f64ba6ce 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -62,78 +62,6 @@ static void __always_unused ____ftrace_check_##name(void) \
#include "trace_entries.h"
-
-#undef __field
-#define __field(type, item) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
- "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
- offsetof(typeof(field), item), \
- sizeof(field.item), is_signed_type(type)); \
- if (!ret) \
- return 0;
-
-#undef __field_desc
-#define __field_desc(type, container, item) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
- "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
- offsetof(typeof(field), container.item), \
- sizeof(field.container.item), \
- is_signed_type(type)); \
- if (!ret) \
- return 0;
-
-#undef __array
-#define __array(type, item, len) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
- "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
- offsetof(typeof(field), item), \
- sizeof(field.item), is_signed_type(type)); \
- if (!ret) \
- return 0;
-
-#undef __array_desc
-#define __array_desc(type, container, item, len) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
- "offset:%zu;\tsize:%zu;\tsigned:%u;\n", \
- offsetof(typeof(field), container.item), \
- sizeof(field.container.item), \
- is_signed_type(type)); \
- if (!ret) \
- return 0;
-
-#undef __dynamic_array
-#define __dynamic_array(type, item) \
- ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
- "offset:%zu;\tsize:0;\tsigned:%u;\n", \
- offsetof(typeof(field), item), \
- is_signed_type(type)); \
- if (!ret) \
- return 0;
-
-#undef F_printk
-#define F_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
-
-#undef __entry
-#define __entry REC
-
-#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
-static int \
-ftrace_format_##name(struct ftrace_event_call *unused, \
- struct trace_seq *s) \
-{ \
- struct struct_name field __attribute__((unused)); \
- int ret = 0; \
- \
- tstruct; \
- \
- trace_seq_printf(s, "\nprint fmt: " print); \
- \
- return ret; \
-}
-
-#include "trace_entries.h"
-
#undef __field
#define __field(type, item) \
ret = trace_define_field(event_call, #type, #item, \
@@ -175,7 +103,12 @@ ftrace_format_##name(struct ftrace_event_call *unused, \
return ret;
#undef __dynamic_array
-#define __dynamic_array(type, item)
+#define __dynamic_array(type, item) \
+ ret = trace_define_field(event_call, #type, #item, \
+ offsetof(typeof(field), item), \
+ 0, is_signed_type(type), FILTER_OTHER);\
+ if (ret) \
+ return ret;
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
@@ -198,6 +131,9 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
return 0;
}
+#undef __entry
+#define __entry REC
+
#undef __field
#define __field(type, item)
@@ -213,6 +149,9 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
#undef __dynamic_array
#define __dynamic_array(type, item)
+#undef F_printk
+#define F_printk(fmt, args...) #fmt ", " __stringify(args)
+
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \
\
@@ -223,7 +162,7 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
.id = type, \
.system = __stringify(TRACE_SYSTEM), \
.raw_init = ftrace_raw_init_event, \
- .show_format = ftrace_format_##call, \
+ .print_fmt = print, \
.define_fields = ftrace_define_fields_##call, \
}; \
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index b1342c5d37cf..9aed1a5cf553 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -9,6 +9,7 @@
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
+#include <linux/slab.h>
#include <linux/fs.h>
#include "trace.h"
@@ -18,6 +19,7 @@ struct fgraph_cpu_data {
pid_t last_pid;
int depth;
int ignore;
+ unsigned long enter_funcs[FTRACE_RETFUNC_DEPTH];
};
struct fgraph_data {
@@ -187,7 +189,7 @@ static int __trace_graph_entry(struct trace_array *tr,
struct ring_buffer *buffer = tr->buffer;
struct ftrace_graph_ent_entry *entry;
- if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
return 0;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
@@ -212,13 +214,11 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
int cpu;
int pc;
- if (unlikely(!tr))
- return 0;
-
if (!ftrace_trace_task(current))
return 0;
- if (!ftrace_graph_addr(trace->func))
+ /* trace it when it is-nested-in or is a function enabled. */
+ if (!(trace->depth || ftrace_graph_addr(trace->func)))
return 0;
local_irq_save(flags);
@@ -231,9 +231,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
} else {
ret = 0;
}
- /* Only do the atomic if it is not already set */
- if (!test_tsk_trace_graph(current))
- set_tsk_trace_graph(current);
atomic_dec(&data->disabled);
local_irq_restore(flags);
@@ -241,6 +238,14 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
return ret;
}
+int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
+{
+ if (tracing_thresh)
+ return 1;
+ else
+ return trace_graph_entry(trace);
+}
+
static void __trace_graph_return(struct trace_array *tr,
struct ftrace_graph_ret *trace,
unsigned long flags,
@@ -251,7 +256,7 @@ static void __trace_graph_return(struct trace_array *tr,
struct ring_buffer *buffer = tr->buffer;
struct ftrace_graph_ret_entry *entry;
- if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
return;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
@@ -281,19 +286,39 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
pc = preempt_count();
__trace_graph_return(tr, trace, flags, pc);
}
- if (!trace->depth)
- clear_tsk_trace_graph(current);
atomic_dec(&data->disabled);
local_irq_restore(flags);
}
+void set_graph_array(struct trace_array *tr)
+{
+ graph_array = tr;
+
+ /* Make graph_array visible before we start tracing */
+
+ smp_mb();
+}
+
+void trace_graph_thresh_return(struct ftrace_graph_ret *trace)
+{
+ if (tracing_thresh &&
+ (trace->rettime - trace->calltime < tracing_thresh))
+ return;
+ else
+ trace_graph_return(trace);
+}
+
static int graph_trace_init(struct trace_array *tr)
{
int ret;
- graph_array = tr;
- ret = register_ftrace_graph(&trace_graph_return,
- &trace_graph_entry);
+ set_graph_array(tr);
+ if (tracing_thresh)
+ ret = register_ftrace_graph(&trace_graph_thresh_return,
+ &trace_graph_thresh_entry);
+ else
+ ret = register_ftrace_graph(&trace_graph_return,
+ &trace_graph_entry);
if (ret)
return ret;
tracing_start_cmdline_record();
@@ -301,11 +326,6 @@ static int graph_trace_init(struct trace_array *tr)
return 0;
}
-void set_graph_array(struct trace_array *tr)
-{
- graph_array = tr;
-}
-
static void graph_trace_reset(struct trace_array *tr)
{
tracing_stop_cmdline_record();
@@ -673,15 +693,21 @@ print_graph_entry_leaf(struct trace_iterator *iter,
duration = graph_ret->rettime - graph_ret->calltime;
if (data) {
+ struct fgraph_cpu_data *cpu_data;
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+
+ cpu_data = per_cpu_ptr(data->cpu_data, cpu);
/*
* Comments display at + 1 to depth. Since
* this is a leaf function, keep the comments
* equal to this depth.
*/
- *depth = call->depth - 1;
+ cpu_data->depth = call->depth - 1;
+
+ /* No need to keep this function around for this depth */
+ if (call->depth < FTRACE_RETFUNC_DEPTH)
+ cpu_data->enter_funcs[call->depth] = 0;
}
/* Overhead */
@@ -721,10 +747,15 @@ print_graph_entry_nested(struct trace_iterator *iter,
int i;
if (data) {
+ struct fgraph_cpu_data *cpu_data;
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
- *depth = call->depth;
+ cpu_data = per_cpu_ptr(data->cpu_data, cpu);
+ cpu_data->depth = call->depth;
+
+ /* Save this function pointer to see if the exit matches */
+ if (call->depth < FTRACE_RETFUNC_DEPTH)
+ cpu_data->enter_funcs[call->depth] = call->func;
}
/* No overhead */
@@ -854,19 +885,28 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
struct fgraph_data *data = iter->private;
pid_t pid = ent->pid;
int cpu = iter->cpu;
+ int func_match = 1;
int ret;
int i;
if (data) {
+ struct fgraph_cpu_data *cpu_data;
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+
+ cpu_data = per_cpu_ptr(data->cpu_data, cpu);
/*
* Comments display at + 1 to depth. This is the
* return from a function, we now want the comments
* to display at the same level of the bracket.
*/
- *depth = trace->depth - 1;
+ cpu_data->depth = trace->depth - 1;
+
+ if (trace->depth < FTRACE_RETFUNC_DEPTH) {
+ if (cpu_data->enter_funcs[trace->depth] != trace->func)
+ func_match = 0;
+ cpu_data->enter_funcs[trace->depth] = 0;
+ }
}
if (print_graph_prologue(iter, s, 0, 0))
@@ -891,9 +931,21 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
return TRACE_TYPE_PARTIAL_LINE;
}
- ret = trace_seq_printf(s, "}\n");
- if (!ret)
- return TRACE_TYPE_PARTIAL_LINE;
+ /*
+ * If the return function does not have a matching entry,
+ * then the entry was lost. Instead of just printing
+ * the '}' and letting the user guess what function this
+ * belongs to, write out the function name.
+ */
+ if (func_match) {
+ ret = trace_seq_printf(s, "}\n");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ } else {
+ ret = trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
/* Overrun */
if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERRUN) {
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 6178abf3637e..1251e367bae9 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -635,12 +635,12 @@ static int create_trace_probe(int argc, char **argv)
event = strchr(group, '/') + 1;
event[-1] = '\0';
if (strlen(group) == 0) {
- pr_info("Group name is not specifiled\n");
+ pr_info("Group name is not specified\n");
return -EINVAL;
}
}
if (strlen(event) == 0) {
- pr_info("Event name is not specifiled\n");
+ pr_info("Event name is not specified\n");
return -EINVAL;
}
}
@@ -673,7 +673,7 @@ static int create_trace_probe(int argc, char **argv)
return -EINVAL;
}
/* an address specified */
- ret = strict_strtoul(&argv[0][2], 0, (unsigned long *)&addr);
+ ret = strict_strtoul(&argv[1][0], 0, (unsigned long *)&addr);
if (ret) {
pr_info("Failed to parse address.\n");
return ret;
@@ -1155,86 +1155,66 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
return 0;
}
-static int __probe_event_show_format(struct trace_seq *s,
- struct trace_probe *tp, const char *fmt,
- const char *arg)
+static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
{
int i;
+ int pos = 0;
- /* Show format */
- if (!trace_seq_printf(s, "\nprint fmt: \"%s", fmt))
- return 0;
+ const char *fmt, *arg;
- for (i = 0; i < tp->nr_args; i++)
- if (!trace_seq_printf(s, " %s=%%lx", tp->args[i].name))
- return 0;
+ if (!probe_is_return(tp)) {
+ fmt = "(%lx)";
+ arg = "REC->" FIELD_STRING_IP;
+ } else {
+ fmt = "(%lx <- %lx)";
+ arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+ }
- if (!trace_seq_printf(s, "\", %s", arg))
- return 0;
+ /* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
- for (i = 0; i < tp->nr_args; i++)
- if (!trace_seq_printf(s, ", REC->%s", tp->args[i].name))
- return 0;
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
- return trace_seq_puts(s, "\n");
-}
+ for (i = 0; i < tp->nr_args; i++) {
+ pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%%lx",
+ tp->args[i].name);
+ }
-#undef SHOW_FIELD
-#define SHOW_FIELD(type, item, name) \
- do { \
- ret = trace_seq_printf(s, "\tfield:" #type " %s;\t" \
- "offset:%u;\tsize:%u;\tsigned:%d;\n", name,\
- (unsigned int)offsetof(typeof(field), item),\
- (unsigned int)sizeof(type), \
- is_signed_type(type)); \
- if (!ret) \
- return 0; \
- } while (0)
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
-static int kprobe_event_show_format(struct ftrace_event_call *call,
- struct trace_seq *s)
-{
- struct kprobe_trace_entry field __attribute__((unused));
- int ret, i;
- struct trace_probe *tp = (struct trace_probe *)call->data;
-
- SHOW_FIELD(unsigned long, ip, FIELD_STRING_IP);
- SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+ for (i = 0; i < tp->nr_args; i++) {
+ pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+ tp->args[i].name);
+ }
- /* Show fields */
- for (i = 0; i < tp->nr_args; i++)
- SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
- trace_seq_puts(s, "\n");
+#undef LEN_OR_ZERO
- return __probe_event_show_format(s, tp, "(%lx)",
- "REC->" FIELD_STRING_IP);
+ /* return the length of print_fmt */
+ return pos;
}
-static int kretprobe_event_show_format(struct ftrace_event_call *call,
- struct trace_seq *s)
+static int set_print_fmt(struct trace_probe *tp)
{
- struct kretprobe_trace_entry field __attribute__((unused));
- int ret, i;
- struct trace_probe *tp = (struct trace_probe *)call->data;
+ int len;
+ char *print_fmt;
- SHOW_FIELD(unsigned long, func, FIELD_STRING_FUNC);
- SHOW_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP);
- SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+ /* First: called with 0 length to calculate the needed length */
+ len = __set_print_fmt(tp, NULL, 0);
+ print_fmt = kmalloc(len + 1, GFP_KERNEL);
+ if (!print_fmt)
+ return -ENOMEM;
- /* Show fields */
- for (i = 0; i < tp->nr_args; i++)
- SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
- trace_seq_puts(s, "\n");
+ /* Second: actually write the @print_fmt */
+ __set_print_fmt(tp, print_fmt, len + 1);
+ tp->call.print_fmt = print_fmt;
- return __probe_event_show_format(s, tp, "(%lx <- %lx)",
- "REC->" FIELD_STRING_FUNC
- ", REC->" FIELD_STRING_RETIP);
+ return 0;
}
#ifdef CONFIG_PERF_EVENTS
/* Kprobe profile handler */
-static __kprobes void kprobe_profile_func(struct kprobe *kp,
+static __kprobes void kprobe_perf_func(struct kprobe *kp,
struct pt_regs *regs)
{
struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
@@ -1247,11 +1227,11 @@ static __kprobes void kprobe_profile_func(struct kprobe *kp,
__size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
"profile buffer not large enough"))
return;
- entry = ftrace_perf_buf_prepare(size, call->id, &rctx, &irq_flags);
+ entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
if (!entry)
return;
@@ -1260,11 +1240,11 @@ static __kprobes void kprobe_profile_func(struct kprobe *kp,
for (i = 0; i < tp->nr_args; i++)
entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
- ftrace_perf_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags);
+ perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs);
}
/* Kretprobe profile handler */
-static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
+static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
struct pt_regs *regs)
{
struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
@@ -1277,11 +1257,11 @@ static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
__size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
size = ALIGN(__size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
"profile buffer not large enough"))
return;
- entry = ftrace_perf_buf_prepare(size, call->id, &rctx, &irq_flags);
+ entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
if (!entry)
return;
@@ -1291,10 +1271,11 @@ static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
for (i = 0; i < tp->nr_args; i++)
entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
- ftrace_perf_buf_submit(entry, size, rctx, entry->ret_ip, 1, irq_flags);
+ perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1,
+ irq_flags, regs);
}
-static int probe_profile_enable(struct ftrace_event_call *call)
+static int probe_perf_enable(struct ftrace_event_call *call)
{
struct trace_probe *tp = (struct trace_probe *)call->data;
@@ -1306,7 +1287,7 @@ static int probe_profile_enable(struct ftrace_event_call *call)
return enable_kprobe(&tp->rp.kp);
}
-static void probe_profile_disable(struct ftrace_event_call *call)
+static void probe_perf_disable(struct ftrace_event_call *call)
{
struct trace_probe *tp = (struct trace_probe *)call->data;
@@ -1331,7 +1312,7 @@ int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
kprobe_trace_func(kp, regs);
#ifdef CONFIG_PERF_EVENTS
if (tp->flags & TP_FLAG_PROFILE)
- kprobe_profile_func(kp, regs);
+ kprobe_perf_func(kp, regs);
#endif
return 0; /* We don't tweek kernel, so just return 0 */
}
@@ -1345,7 +1326,7 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
kretprobe_trace_func(ri, regs);
#ifdef CONFIG_PERF_EVENTS
if (tp->flags & TP_FLAG_PROFILE)
- kretprobe_profile_func(ri, regs);
+ kretprobe_perf_func(ri, regs);
#endif
return 0; /* We don't tweek kernel, so just return 0 */
}
@@ -1359,30 +1340,33 @@ static int register_probe_event(struct trace_probe *tp)
if (probe_is_return(tp)) {
tp->event.trace = print_kretprobe_event;
call->raw_init = probe_event_raw_init;
- call->show_format = kretprobe_event_show_format;
call->define_fields = kretprobe_event_define_fields;
} else {
tp->event.trace = print_kprobe_event;
call->raw_init = probe_event_raw_init;
- call->show_format = kprobe_event_show_format;
call->define_fields = kprobe_event_define_fields;
}
+ if (set_print_fmt(tp) < 0)
+ return -ENOMEM;
call->event = &tp->event;
call->id = register_ftrace_event(&tp->event);
- if (!call->id)
+ if (!call->id) {
+ kfree(call->print_fmt);
return -ENODEV;
+ }
call->enabled = 0;
call->regfunc = probe_event_enable;
call->unregfunc = probe_event_disable;
#ifdef CONFIG_PERF_EVENTS
- call->profile_enable = probe_profile_enable;
- call->profile_disable = probe_profile_disable;
+ call->perf_event_enable = probe_perf_enable;
+ call->perf_event_disable = probe_perf_disable;
#endif
call->data = tp;
ret = trace_add_event_call(call);
if (ret) {
pr_info("Failed to register kprobe event: %s\n", call->name);
+ kfree(call->print_fmt);
unregister_ftrace_event(&tp->event);
}
return ret;
@@ -1392,6 +1376,7 @@ static void unregister_probe_event(struct trace_probe *tp)
{
/* tp->event is unregistered in trace_remove_event_call() */
trace_remove_event_call(&tp->call);
+ kfree(tp->call.print_fmt);
}
/* Make a debugfs interface for controling probe points */
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
index 94103cdcf9d8..d59cd6879477 100644
--- a/kernel/trace/trace_ksym.c
+++ b/kernel/trace/trace_ksym.c
@@ -23,6 +23,7 @@
#include <linux/debugfs.h>
#include <linux/ftrace.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include <linux/fs.h>
#include "trace_output.h"
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 0acd834659ed..017fa376505d 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -9,6 +9,7 @@
#include <linux/kernel.h>
#include <linux/mmiotrace.h>
#include <linux/pci.h>
+#include <linux/slab.h>
#include <linux/time.h>
#include <asm/atomic.h>
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 280fea470d67..81003b4d617f 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -3,6 +3,7 @@
#include <linux/stringify.h>
#include <linux/kthread.h>
#include <linux/delay.h>
+#include <linux/slab.h>
static inline int trace_valid_entry(struct trace_entry *entry)
{
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 678a5120ee30..f4bc9b27de5f 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -157,6 +157,7 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
unsigned long val, flags;
char buf[64];
int ret;
+ int cpu;
if (count >= sizeof(buf))
return -EINVAL;
@@ -171,9 +172,20 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
return ret;
local_irq_save(flags);
+
+ /*
+ * In case we trace inside arch_spin_lock() or after (NMI),
+ * we will cause circular lock, so we also need to increase
+ * the percpu trace_active here.
+ */
+ cpu = smp_processor_id();
+ per_cpu(trace_active, cpu)++;
+
arch_spin_lock(&max_stack_lock);
*ptr = val;
arch_spin_unlock(&max_stack_lock);
+
+ per_cpu(trace_active, cpu)--;
local_irq_restore(flags);
return count;
@@ -206,7 +218,13 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
static void *t_start(struct seq_file *m, loff_t *pos)
{
+ int cpu;
+
local_irq_disable();
+
+ cpu = smp_processor_id();
+ per_cpu(trace_active, cpu)++;
+
arch_spin_lock(&max_stack_lock);
if (*pos == 0)
@@ -217,7 +235,13 @@ static void *t_start(struct seq_file *m, loff_t *pos)
static void t_stop(struct seq_file *m, void *p)
{
+ int cpu;
+
arch_spin_unlock(&max_stack_lock);
+
+ cpu = smp_processor_id();
+ per_cpu(trace_active, cpu)--;
+
local_irq_enable();
}
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index a4bb239eb987..96cffb269e73 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -10,6 +10,7 @@
#include <linux/list.h>
+#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/debugfs.h>
#include "trace_stat.h"
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 4e332b9e449c..4d6d711717f2 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,5 +1,6 @@
#include <trace/syscall.h>
#include <trace/events/syscalls.h>
+#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/ftrace.h>
#include <linux/perf_event.h>
@@ -143,70 +144,65 @@ extern char *__bad_type_size(void);
#type, #name, offsetof(typeof(trace), name), \
sizeof(trace.name), is_signed_type(type)
-int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
+static
+int __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
{
int i;
- int ret;
- struct syscall_metadata *entry = call->data;
- struct syscall_trace_enter trace;
- int offset = offsetof(struct syscall_trace_enter, args);
+ int pos = 0;
- ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
- "\tsigned:%u;\n",
- SYSCALL_FIELD(int, nr));
- if (!ret)
- return 0;
+ /* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
for (i = 0; i < entry->nb_args; i++) {
- ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
- entry->args[i]);
- if (!ret)
- return 0;
- ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;"
- "\tsigned:%u;\n", offset,
- sizeof(unsigned long),
- is_signed_type(unsigned long));
- if (!ret)
- return 0;
- offset += sizeof(unsigned long);
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s",
+ entry->args[i], sizeof(unsigned long),
+ i == entry->nb_args - 1 ? "" : ", ");
}
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
- trace_seq_puts(s, "\nprint fmt: \"");
for (i = 0; i < entry->nb_args; i++) {
- ret = trace_seq_printf(s, "%s: 0x%%0%zulx%s", entry->args[i],
- sizeof(unsigned long),
- i == entry->nb_args - 1 ? "" : ", ");
- if (!ret)
- return 0;
+ pos += snprintf(buf + pos, LEN_OR_ZERO,
+ ", ((unsigned long)(REC->%s))", entry->args[i]);
}
- trace_seq_putc(s, '"');
- for (i = 0; i < entry->nb_args; i++) {
- ret = trace_seq_printf(s, ", ((unsigned long)(REC->%s))",
- entry->args[i]);
- if (!ret)
- return 0;
- }
+#undef LEN_OR_ZERO
- return trace_seq_putc(s, '\n');
+ /* return the length of print_fmt */
+ return pos;
}
-int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
+static int set_syscall_print_fmt(struct ftrace_event_call *call)
{
- int ret;
- struct syscall_trace_exit trace;
+ char *print_fmt;
+ int len;
+ struct syscall_metadata *entry = call->data;
- ret = trace_seq_printf(s,
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
- "\tsigned:%u;\n"
- "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
- "\tsigned:%u;\n",
- SYSCALL_FIELD(int, nr),
- SYSCALL_FIELD(long, ret));
- if (!ret)
+ if (entry->enter_event != call) {
+ call->print_fmt = "\"0x%lx\", REC->ret";
return 0;
+ }
- return trace_seq_printf(s, "\nprint fmt: \"0x%%lx\", REC->ret\n");
+ /* First: called with 0 length to calculate the needed length */
+ len = __set_enter_print_fmt(entry, NULL, 0);
+
+ print_fmt = kmalloc(len + 1, GFP_KERNEL);
+ if (!print_fmt)
+ return -ENOMEM;
+
+ /* Second: actually write the @print_fmt */
+ __set_enter_print_fmt(entry, print_fmt, len + 1);
+ call->print_fmt = print_fmt;
+
+ return 0;
+}
+
+static void free_syscall_print_fmt(struct ftrace_event_call *call)
+{
+ struct syscall_metadata *entry = call->data;
+
+ if (entry->enter_event == call)
+ kfree(call->print_fmt);
}
int syscall_enter_define_fields(struct ftrace_event_call *call)
@@ -386,12 +382,22 @@ int init_syscall_trace(struct ftrace_event_call *call)
{
int id;
- id = register_ftrace_event(call->event);
- if (!id)
- return -ENODEV;
- call->id = id;
- INIT_LIST_HEAD(&call->fields);
- return 0;
+ if (set_syscall_print_fmt(call) < 0)
+ return -ENOMEM;
+
+ id = trace_event_raw_init(call);
+
+ if (id < 0) {
+ free_syscall_print_fmt(call);
+ return id;
+ }
+
+ return id;
+}
+
+unsigned long __init arch_syscall_addr(int nr)
+{
+ return (unsigned long)sys_call_table[nr];
}
int __init init_ftrace_syscalls(void)
@@ -423,12 +429,12 @@ core_initcall(init_ftrace_syscalls);
#ifdef CONFIG_PERF_EVENTS
-static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
-static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls);
-static int sys_prof_refcount_enter;
-static int sys_prof_refcount_exit;
+static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
+static int sys_perf_refcount_enter;
+static int sys_perf_refcount_exit;
-static void prof_syscall_enter(struct pt_regs *regs, long id)
+static void perf_syscall_enter(struct pt_regs *regs, long id)
{
struct syscall_metadata *sys_data;
struct syscall_trace_enter *rec;
@@ -438,7 +444,7 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
int size;
syscall_nr = syscall_get_nr(current, regs);
- if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
+ if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
@@ -450,11 +456,11 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
size = ALIGN(size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
- "profile buffer not large enough"))
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+ "perf buffer not large enough"))
return;
- rec = (struct syscall_trace_enter *)ftrace_perf_buf_prepare(size,
+ rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
sys_data->enter_event->id, &rctx, &flags);
if (!rec)
return;
@@ -462,10 +468,10 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
rec->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args,
(unsigned long *)&rec->args);
- ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags);
+ perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
}
-int prof_sysenter_enable(struct ftrace_event_call *call)
+int perf_sysenter_enable(struct ftrace_event_call *call)
{
int ret = 0;
int num;
@@ -473,34 +479,34 @@ int prof_sysenter_enable(struct ftrace_event_call *call)
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
- if (!sys_prof_refcount_enter)
- ret = register_trace_sys_enter(prof_syscall_enter);
+ if (!sys_perf_refcount_enter)
+ ret = register_trace_sys_enter(perf_syscall_enter);
if (ret) {
pr_info("event trace: Could not activate"
"syscall entry trace point");
} else {
- set_bit(num, enabled_prof_enter_syscalls);
- sys_prof_refcount_enter++;
+ set_bit(num, enabled_perf_enter_syscalls);
+ sys_perf_refcount_enter++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
-void prof_sysenter_disable(struct ftrace_event_call *call)
+void perf_sysenter_disable(struct ftrace_event_call *call)
{
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
- sys_prof_refcount_enter--;
- clear_bit(num, enabled_prof_enter_syscalls);
- if (!sys_prof_refcount_enter)
- unregister_trace_sys_enter(prof_syscall_enter);
+ sys_perf_refcount_enter--;
+ clear_bit(num, enabled_perf_enter_syscalls);
+ if (!sys_perf_refcount_enter)
+ unregister_trace_sys_enter(perf_syscall_enter);
mutex_unlock(&syscall_trace_lock);
}
-static void prof_syscall_exit(struct pt_regs *regs, long ret)
+static void perf_syscall_exit(struct pt_regs *regs, long ret)
{
struct syscall_metadata *sys_data;
struct syscall_trace_exit *rec;
@@ -510,7 +516,7 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
int size;
syscall_nr = syscall_get_nr(current, regs);
- if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
+ if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
@@ -525,11 +531,11 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
* Impossible, but be paranoid with the future
* How to put this check outside runtime?
*/
- if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
- "exit event has grown above profile buffer size"))
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+ "exit event has grown above perf buffer size"))
return;
- rec = (struct syscall_trace_exit *)ftrace_perf_buf_prepare(size,
+ rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
sys_data->exit_event->id, &rctx, &flags);
if (!rec)
return;
@@ -537,10 +543,10 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
rec->nr = syscall_nr;
rec->ret = syscall_get_return_value(current, regs);
- ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags);
+ perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
}
-int prof_sysexit_enable(struct ftrace_event_call *call)
+int perf_sysexit_enable(struct ftrace_event_call *call)
{
int ret = 0;
int num;
@@ -548,30 +554,30 @@ int prof_sysexit_enable(struct ftrace_event_call *call)
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
- if (!sys_prof_refcount_exit)
- ret = register_trace_sys_exit(prof_syscall_exit);
+ if (!sys_perf_refcount_exit)
+ ret = register_trace_sys_exit(perf_syscall_exit);
if (ret) {
pr_info("event trace: Could not activate"
- "syscall entry trace point");
+ "syscall exit trace point");
} else {
- set_bit(num, enabled_prof_exit_syscalls);
- sys_prof_refcount_exit++;
+ set_bit(num, enabled_perf_exit_syscalls);
+ sys_perf_refcount_exit++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
-void prof_sysexit_disable(struct ftrace_event_call *call)
+void perf_sysexit_disable(struct ftrace_event_call *call)
{
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
- sys_prof_refcount_exit--;
- clear_bit(num, enabled_prof_exit_syscalls);
- if (!sys_prof_refcount_exit)
- unregister_trace_sys_exit(prof_syscall_exit);
+ sys_perf_refcount_exit--;
+ clear_bit(num, enabled_perf_exit_syscalls);
+ if (!sys_perf_refcount_exit)
+ unregister_trace_sys_exit(perf_syscall_exit);
mutex_unlock(&syscall_trace_lock);
}
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 40cafb07dffd..cc2d2faa7d9e 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -9,6 +9,7 @@
#include <trace/events/workqueue.h>
#include <linux/list.h>
#include <linux/percpu.h>
+#include <linux/slab.h>
#include <linux/kref.h>
#include "trace_stat.h"
#include "trace.h"
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-21 13:18:28 +0100