Merge branch 'tip/tracing/ftrace' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/ftrace

9 files changed, 572 insertions, 49 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index c61fab1dd2f8..0add6b28c366 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -61,6 +61,14 @@
 #define BRANCH_PROFILE()
 #endif
 
+#ifdef CONFIG_EVENT_TRACER
+#define FTRACE_EVENTS() VMLINUX_SYMBOL(__start_ftrace_events) = .;      \
+                        *(_ftrace_events)                               \
+                        VMLINUX_SYMBOL(__stop_ftrace_events) = .;
+#else
+#define FTRACE_EVENTS()
+#endif
+
 /* .data section */
 #define DATA_DATA                                                       \
         *(.data)                                                        \
@@ -81,7 +89,8 @@
         *(__tracepoints)                                                \
         VMLINUX_SYMBOL(__stop___tracepoints) = .;                       \
         LIKELY_PROFILE()                                                \
-        BRANCH_PROFILE()
+        BRANCH_PROFILE()                                                \
+        FTRACE_EVENTS()
 
 #define RO_DATA(align)                                                  \
         . = ALIGN((align));                                             \
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 757005458366..34ae464effff 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -153,4 +153,7 @@ static inline void tracepoint_synchronize_unregister(void)
         synchronize_sched();
 }
 
+#define DEFINE_TRACE_FMT(name, proto, args, fmt)                \
+        DECLARE_TRACE(name, TPPROTO(proto), TPARGS(args))
+
 #endif
diff --git a/include/trace/sched.h b/include/trace/sched.h
index 0d81098ee9fc..4e372a1a29bf 100644
--- a/include/trace/sched.h
+++ b/include/trace/sched.h
@@ -4,53 +4,6 @@
 #include <linux/sched.h>
 #include <linux/tracepoint.h>
 
-DECLARE_TRACE(sched_kthread_stop,
-        TPPROTO(struct task_struct *t),
-                TPARGS(t));
-
-DECLARE_TRACE(sched_kthread_stop_ret,
-        TPPROTO(int ret),
-                TPARGS(ret));
-
-DECLARE_TRACE(sched_wait_task,
-        TPPROTO(struct rq *rq, struct task_struct *p),
-                TPARGS(rq, p));
-
-DECLARE_TRACE(sched_wakeup,
-        TPPROTO(struct rq *rq, struct task_struct *p, int success),
-                TPARGS(rq, p, success));
-
-DECLARE_TRACE(sched_wakeup_new,
-        TPPROTO(struct rq *rq, struct task_struct *p, int success),
-                TPARGS(rq, p, success));
-
-DECLARE_TRACE(sched_switch,
-        TPPROTO(struct rq *rq, struct task_struct *prev,
-                struct task_struct *next),
-                TPARGS(rq, prev, next));
-
-DECLARE_TRACE(sched_migrate_task,
-        TPPROTO(struct task_struct *p, int orig_cpu, int dest_cpu),
-                TPARGS(p, orig_cpu, dest_cpu));
-
-DECLARE_TRACE(sched_process_free,
-        TPPROTO(struct task_struct *p),
-                TPARGS(p));
-
-DECLARE_TRACE(sched_process_exit,
-        TPPROTO(struct task_struct *p),
-                TPARGS(p));
-
-DECLARE_TRACE(sched_process_wait,
-        TPPROTO(struct pid *pid),
-                TPARGS(pid));
-
-DECLARE_TRACE(sched_process_fork,
-        TPPROTO(struct task_struct *parent, struct task_struct *child),
-                TPARGS(parent, child));
-
-DECLARE_TRACE(sched_signal_send,
-        TPPROTO(int sig, struct task_struct *p),
-                TPARGS(sig, p));
+#include <trace/sched_event_types.h>
 
 #endif
diff --git a/include/trace/sched_event_types.h b/include/trace/sched_event_types.h
new file mode 100644
index 000000000000..a4f662940f4e
--- /dev/null
+++ b/include/trace/sched_event_types.h
@@ -0,0 +1,72 @@
+
+/* use <trace/sched.h> instead */
+#ifndef DEFINE_TRACE_FMT
+# error Do not include this file directly.
+# error Unless you know what you are doing.
+#endif
+
+DEFINE_TRACE_FMT(sched_kthread_stop,
+        TPPROTO(struct task_struct *t),
+        TPARGS(t),
+        TPFMT("task %s:%d", t->comm, t->pid));
+
+DEFINE_TRACE_FMT(sched_kthread_stop_ret,
+        TPPROTO(int ret),
+        TPARGS(ret),
+        TPFMT("ret=%d", ret));
+
+DEFINE_TRACE_FMT(sched_wait_task,
+        TPPROTO(struct rq *rq, struct task_struct *p),
+        TPARGS(rq, p),
+        TPFMT("task %s:%d", p->comm, p->pid));
+
+DEFINE_TRACE_FMT(sched_wakeup,
+        TPPROTO(struct rq *rq, struct task_struct *p, int success),
+        TPARGS(rq, p, success),
+        TPFMT("task %s:%d %s",
+              p->comm, p->pid, success?"succeeded":"failed"));
+
+DEFINE_TRACE_FMT(sched_wakeup_new,
+        TPPROTO(struct rq *rq, struct task_struct *p, int success),
+        TPARGS(rq, p, success),
+        TPFMT("task %s:%d",
+              p->comm, p->pid, success?"succeeded":"failed"));
+
+DEFINE_TRACE_FMT(sched_switch,
+        TPPROTO(struct rq *rq, struct task_struct *prev,
+                struct task_struct *next),
+        TPARGS(rq, prev, next),
+        TPFMT("task %s:%d ==> %s:%d",
+              prev->comm, prev->pid, next->comm, next->pid));
+
+DEFINE_TRACE_FMT(sched_migrate_task,
+        TPPROTO(struct task_struct *p, int orig_cpu, int dest_cpu),
+        TPARGS(p, orig_cpu, dest_cpu),
+        TPFMT("task %s:%d from: %d  to: %d",
+              p->comm, p->pid, orig_cpu, dest_cpu));
+
+DEFINE_TRACE_FMT(sched_process_free,
+        TPPROTO(struct task_struct *p),
+        TPARGS(p),
+        TPFMT("task %s:%d", p->comm, p->pid));
+
+DEFINE_TRACE_FMT(sched_process_exit,
+        TPPROTO(struct task_struct *p),
+        TPARGS(p),
+        TPFMT("task %s:%d", p->comm, p->pid));
+
+DEFINE_TRACE_FMT(sched_process_wait,
+        TPPROTO(struct pid *pid),
+        TPARGS(pid),
+        TPFMT("pid %d", pid));
+
+DEFINE_TRACE_FMT(sched_process_fork,
+        TPPROTO(struct task_struct *parent, struct task_struct *child),
+        TPARGS(parent, child),
+        TPFMT("parent %s:%d  child %s:%d",
+              parent->comm, parent->pid, child->comm, child->pid));
+
+DEFINE_TRACE_FMT(sched_signal_send,
+        TPPROTO(int sig, struct task_struct *p),
+        TPARGS(sig, p),
+        TPFMT("sig: %d   task %s:%d", sig, p->comm, p->pid));
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 07877f4b5233..999c6a2485df 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -159,6 +159,15 @@ config CONTEXT_SWITCH_TRACER
           This tracer gets called from the context switch and records
           all switching of tasks.
 
+config EVENT_TRACER
+        bool "Trace various events in the kernel"
+        depends on DEBUG_KERNEL
+        select TRACING
+        help
+          This tracer hooks to various trace points in the kernel
+          allowing the user to pick and choose which trace point they
+          want to trace.
+
 config BOOT_TRACER
         bool "Trace boot initcalls"
         depends on DEBUG_KERNEL
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 627090bc262d..664b6c0dc75a 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -38,5 +38,7 @@ obj-$(CONFIG_POWER_TRACER) += trace_power.o
 obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
 obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
 obj-$(CONFIG_BLK_DEV_IO_TRACE)  += blktrace.o
+obj-$(CONFIG_EVENT_TRACER) += trace_events.o
+obj-$(CONFIG_EVENT_TRACER) += events.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/events.c b/kernel/trace/events.c
new file mode 100644
index 000000000000..38c89eef99ee
--- /dev/null
+++ b/kernel/trace/events.c
@@ -0,0 +1,13 @@
+/*
+ * This is the place to register all trace points as events.
+ * Include the trace/<type>.h at the top.
+ * Include the trace/<type>_event_types.h at the bottom.
+ */
+
+/* trace/<type>.h here */
+#include <trace/sched.h>
+
+#include "trace_events.h"
+
+/* trace/<type>_event_types.h here */
+#include <trace/sched_event_types.h>
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
new file mode 100644
index 000000000000..3bcb9df93342
--- /dev/null
+++ b/kernel/trace/trace_events.c
@@ -0,0 +1,407 @@
+/*
+ * event tracer
+ *
+ * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+
+#include "trace_events.h"
+
+#define events_for_each(event)                                          \
+        for (event = __start_ftrace_events;                             \
+             (unsigned long)event < (unsigned long)__stop_ftrace_events; \
+             event++)
+
+void event_trace_printk(unsigned long ip, const char *fmt, ...)
+{
+        va_list ap;
+
+        va_start(ap, fmt);
+        tracing_record_cmdline(current);
+        trace_vprintk(ip, task_curr_ret_stack(current), fmt, ap);
+        va_end(ap);
+}
+
+static void ftrace_clear_events(void)
+{
+        struct ftrace_event_call *call = (void *)__start_ftrace_events;
+
+
+        while ((unsigned long)call < (unsigned long)__stop_ftrace_events) {
+
+                if (call->enabled) {
+                        call->enabled = 0;
+                        call->unregfunc();
+                }
+                call++;
+        }
+}
+
+static int ftrace_set_clr_event(char *buf, int set)
+{
+        struct ftrace_event_call *call = __start_ftrace_events;
+
+
+        events_for_each(call) {
+
+                if (!call->name)
+                        continue;
+
+                if (strcmp(buf, call->name) != 0)
+                        continue;
+
+                if (set) {
+                        /* Already set? */
+                        if (call->enabled)
+                                return 0;
+                        call->enabled = 1;
+                        call->regfunc();
+                } else {
+                        /* Already cleared? */
+                        if (!call->enabled)
+                                return 0;
+                        call->enabled = 0;
+                        call->unregfunc();
+                }
+                return 0;
+        }
+        return -EINVAL;
+}
+
+/* 128 should be much more than enough */
+#define EVENT_BUF_SIZE          127
+
+static ssize_t
+ftrace_event_write(struct file *file, const char __user *ubuf,
+                   size_t cnt, loff_t *ppos)
+{
+        size_t read = 0;
+        int i, set = 1;
+        ssize_t ret;
+        char *buf;
+        char ch;
+
+        if (!cnt || cnt < 0)
+                return 0;
+
+        ret = get_user(ch, ubuf++);
+        if (ret)
+                return ret;
+        read++;
+        cnt--;
+
+        /* skip white space */
+        while (cnt && isspace(ch)) {
+                ret = get_user(ch, ubuf++);
+                if (ret)
+                        return ret;
+                read++;
+                cnt--;
+        }
+
+        /* Only white space found? */
+        if (isspace(ch)) {
+                file->f_pos += read;
+                ret = read;
+                return ret;
+        }
+
+        buf = kmalloc(EVENT_BUF_SIZE+1, GFP_KERNEL);
+        if (!buf)
+                return -ENOMEM;
+
+        if (cnt > EVENT_BUF_SIZE)
+                cnt = EVENT_BUF_SIZE;
+
+        i = 0;
+        while (cnt && !isspace(ch)) {
+                if (!i && ch == '!')
+                        set = 0;
+                else
+                        buf[i++] = ch;
+
+                ret = get_user(ch, ubuf++);
+                if (ret)
+                        goto out_free;
+                read++;
+                cnt--;
+        }
+        buf[i] = 0;
+
+        file->f_pos += read;
+
+        ret = ftrace_set_clr_event(buf, set);
+        if (ret)
+                goto out_free;
+
+        ret = read;
+
+ out_free:
+        kfree(buf);
+
+        return ret;
+}
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        struct ftrace_event_call *call = m->private;
+        struct ftrace_event_call *next = call;
+
+        (*pos)++;
+
+        if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
+                return NULL;
+
+        m->private = ++next;
+
+        return call;
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+        return t_next(m, NULL, pos);
+}
+
+static void *
+s_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        struct ftrace_event_call *call = m->private;
+        struct ftrace_event_call *next;
+
+        (*pos)++;
+
+ retry:
+        if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
+                return NULL;
+
+        if (!call->enabled) {
+                call++;
+                goto retry;
+        }
+
+        next = call;
+        m->private = ++next;
+
+        return call;
+}
+
+static void *s_start(struct seq_file *m, loff_t *pos)
+{
+        return s_next(m, NULL, pos);
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+        struct ftrace_event_call *call = v;
+
+        seq_printf(m, "%s\n", call->name);
+
+        return 0;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+}
+
+static int
+ftrace_event_seq_open(struct inode *inode, struct file *file)
+{
+        int ret;
+        const struct seq_operations *seq_ops;
+
+        if ((file->f_mode & FMODE_WRITE) &&
+            !(file->f_flags & O_APPEND))
+                ftrace_clear_events();
+
+        seq_ops = inode->i_private;
+        ret = seq_open(file, seq_ops);
+        if (!ret) {
+                struct seq_file *m = file->private_data;
+
+                m->private = __start_ftrace_events;
+        }
+        return ret;
+}
+
+static ssize_t
+event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
+                  loff_t *ppos)
+{
+        struct ftrace_event_call *call = filp->private_data;
+        char *buf;
+
+        if (call->enabled)
+                buf = "1\n";
+        else
+                buf = "0\n";
+
+        return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
+}
+
+static ssize_t
+event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
+                   loff_t *ppos)
+{
+        struct ftrace_event_call *call = filp->private_data;
+        char buf[64];
+        unsigned long val;
+        int ret;
+
+        if (cnt >= sizeof(buf))
+                return -EINVAL;
+
+        if (copy_from_user(&buf, ubuf, cnt))
+                return -EFAULT;
+
+        buf[cnt] = 0;
+
+        ret = strict_strtoul(buf, 10, &val);
+        if (ret < 0)
+                return ret;
+
+        switch (val) {
+        case 0:
+                if (!call->enabled)
+                        break;
+
+                call->enabled = 0;
+                call->unregfunc();
+                break;
+        case 1:
+                if (call->enabled)
+                        break;
+
+                call->enabled = 1;
+                call->regfunc();
+                break;
+
+        default:
+                return -EINVAL;
+        }
+
+        *ppos += cnt;
+
+        return cnt;
+}
+
+static const struct seq_operations show_event_seq_ops = {
+        .start = t_start,
+        .next = t_next,
+        .show = t_show,
+        .stop = t_stop,
+};
+
+static const struct seq_operations show_set_event_seq_ops = {
+        .start = s_start,
+        .next = s_next,
+        .show = t_show,
+        .stop = t_stop,
+};
+
+static const struct file_operations ftrace_avail_fops = {
+        .open = ftrace_event_seq_open,
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .release = seq_release,
+};
+
+static const struct file_operations ftrace_set_event_fops = {
+        .open = ftrace_event_seq_open,
+        .read = seq_read,
+        .write = ftrace_event_write,
+        .llseek = seq_lseek,
+        .release = seq_release,
+};
+
+static const struct file_operations ftrace_enable_fops = {
+        .open = tracing_open_generic,
+        .read = event_enable_read,
+        .write = event_enable_write,
+};
+
+static struct dentry *event_trace_events_dir(void)
+{
+        static struct dentry *d_tracer;
+        static struct dentry *d_events;
+
+        if (d_events)
+                return d_events;
+
+        d_tracer = tracing_init_dentry();
+        if (!d_tracer)
+                return NULL;
+
+        d_events = debugfs_create_dir("events", d_tracer);
+        if (!d_events)
+                pr_warning("Could not create debugfs "
+                           "'events' directory\n");
+
+        return d_events;
+}
+
+static int
+event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
+{
+        struct dentry *entry;
+
+        call->dir = debugfs_create_dir(call->name, d_events);
+        if (!call->dir) {
+                pr_warning("Could not create debugfs "
+                           "'%s' directory\n", call->name);
+                return -1;
+        }
+
+        entry = debugfs_create_file("enable", 0644, call->dir, call,
+                                    &ftrace_enable_fops);
+        if (!entry)
+                pr_warning("Could not create debugfs "
+                           "'%s/enable' entry\n", call->name);
+
+        return 0;
+}
+
+static __init int event_trace_init(void)
+{
+        struct ftrace_event_call *call = __start_ftrace_events;
+        struct dentry *d_tracer;
+        struct dentry *entry;
+        struct dentry *d_events;
+
+        d_tracer = tracing_init_dentry();
+        if (!d_tracer)
+                return 0;
+
+        entry = debugfs_create_file("available_events", 0444, d_tracer,
+                                    (void *)&show_event_seq_ops,
+                                    &ftrace_avail_fops);
+        if (!entry)
+                pr_warning("Could not create debugfs "
+                           "'available_events' entry\n");
+
+        entry = debugfs_create_file("set_event", 0644, d_tracer,
+                                    (void *)&show_set_event_seq_ops,
+                                    &ftrace_set_event_fops);
+        if (!entry)
+                pr_warning("Could not create debugfs "
+                           "'set_event' entry\n");
+
+        d_events = event_trace_events_dir();
+        if (!d_events)
+                return 0;
+
+        events_for_each(call) {
+                /* The linker may leave blanks */
+                if (!call->name)
+                        continue;
+                event_create_dir(call, d_events);
+        }
+
+        return 0;
+}
+fs_initcall(event_trace_init);
diff --git a/kernel/trace/trace_events.h b/kernel/trace/trace_events.h
new file mode 100644
index 000000000000..cb8455b3ac9a
--- /dev/null
+++ b/kernel/trace/trace_events.h
@@ -0,0 +1,55 @@
+#ifndef _LINUX_KERNEL_TRACE_EVENTS_H
+#define _LINUX_KERNEL_TRACE_EVENTS_H
+
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include "trace.h"
+
+struct ftrace_event_call {
+        char            *name;
+        struct dentry   *dir;
+        int             enabled;
+        int             (*regfunc)(void);
+        void            (*unregfunc)(void);
+};
+
+
+#undef TPFMT
+#define TPFMT(fmt, args...)     fmt "\n", ##args
+
+#undef DEFINE_TRACE_FMT
+#define DEFINE_TRACE_FMT(call, proto, args, fmt)                        \
+static void ftrace_event_##call(proto)                                  \
+{                                                                       \
+        event_trace_printk(_RET_IP_, "(" #call ") " fmt);               \
+}                                                                       \
+                                                                        \
+static int ftrace_reg_event_##call(void)                                \
+{                                                                       \
+        int ret;                                                        \
+                                                                        \
+        ret = register_trace_##call(ftrace_event_##call);               \
+        if (!ret)                                                       \
+                pr_info("event trace: Could not activate trace point "  \
+                        "probe to " #call);                             \
+        return ret;                                                     \
+}                                                                       \
+                                                                        \
+static void ftrace_unreg_event_##call(void)                             \
+{                                                                       \
+        unregister_trace_##call(ftrace_event_##call);                   \
+}                                                                       \
+                                                                        \
+static struct ftrace_event_call __used                                  \
+__attribute__((__aligned__(4)))                                         \
+__attribute__((section("_ftrace_events"))) event_##call = {             \
+        .name                   = #call,                                \
+        .regfunc                = ftrace_reg_event_##call,              \
+        .unregfunc              = ftrace_unreg_event_##call,            \
+}
+
+void event_trace_printk(unsigned long ip, const char *fmt, ...);
+extern struct ftrace_event_call __start_ftrace_events[];
+extern struct ftrace_event_call __stop_ftrace_events[];
+
+#endif /* _LINUX_KERNEL_TRACE_EVENTS_H */