tracing: Make a snapshot feature available from userspace

Ftrace has a snapshot feature available from kernel space and
latency tracers (e.g. irqsoff) are using it. This patch enables
user applictions to take a snapshot via debugfs.

Add "snapshot" debugfs file in "tracing" directory.

  snapshot:
    This is used to take a snapshot and to read the output of the
    snapshot.

     # echo 1 > snapshot

    This will allocate the spare buffer for snapshot (if it is
    not allocated), and take a snapshot.

     # cat snapshot

    This will show contents of the snapshot.

     # echo 0 > snapshot

    This will free the snapshot if it is allocated.

    Any other positive values will clear the snapshot contents if
    the snapshot is allocated, or return EINVAL if it is not allocated.

Link: http://lkml.kernel.org/r/20121226025300.3252.86850.stgit@liselsia

Cc: Jiri Olsa <jolsa@redhat.com>
Cc: David Sharp <dhsharp@google.com>
Signed-off-by: Hiraku Toyooka <hiraku.toyooka.gu@hitachi.com>
[
   Fixed irqsoff selftest and also a conflict with a change
   that fixes the update_max_tr.
]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

4 files changed, 154 insertions, 26 deletions

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 6f8d0b77006b..13a54d0bdfa8 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -83,6 +83,9 @@ struct trace_iterator {
         long                    idx;
 
         cpumask_var_t           started;
+
+        /* it's true when current open file is snapshot */
+        bool                    snapshot;
 };
 
 enum trace_iter_flags {
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index cdc9d284d24e..36567564e221 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -253,6 +253,16 @@ config FTRACE_SYSCALLS
         help
           Basic tracer to catch the syscall entry and exit events.
 
+config TRACER_SNAPSHOT
+        bool "Create a snapshot trace buffer"
+        select TRACER_MAX_TRACE
+        help
+          Allow tracing users to take snapshot of the current buffer using the
+          ftrace interface, e.g.:
+
+              echo 1 > /sys/kernel/debug/tracing/snapshot
+              cat snapshot
+
 config TRACE_BRANCH_PROFILING
         bool
         select GENERIC_TRACER
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2c724662a3e8..70dce64b9ecf 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -710,12 +710,11 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
         WARN_ON_ONCE(!irqs_disabled());
 
-        /* If we disabled the tracer, stop now */
-        if (current_trace == &nop_trace)
-                return;
-
-        if (WARN_ON_ONCE(!current_trace->use_max_tr))
+        if (!current_trace->allocated_snapshot) {
+                /* Only the nop tracer should hit this when disabling */
+                WARN_ON_ONCE(current_trace != &nop_trace);
                 return;
+        }
 
         arch_spin_lock(&ftrace_max_lock);
 
@@ -743,10 +742,8 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
                 return;
 
         WARN_ON_ONCE(!irqs_disabled());
-        if (!current_trace->use_max_tr) {
-                WARN_ON_ONCE(1);
+        if (WARN_ON_ONCE(!current_trace->allocated_snapshot))
                 return;
-        }
 
         arch_spin_lock(&ftrace_max_lock);
 
@@ -866,10 +863,13 @@ int register_tracer(struct tracer *type)
 
                 current_trace = type;
 
-                /* If we expanded the buffers, make sure the max is expanded too */
-                if (ring_buffer_expanded && type->use_max_tr)
-                        ring_buffer_resize(max_tr.buffer, trace_buf_size,
-                                                RING_BUFFER_ALL_CPUS);
+                if (type->use_max_tr) {
+                        /* If we expanded the buffers, make sure the max is expanded too */
+                        if (ring_buffer_expanded)
+                                ring_buffer_resize(max_tr.buffer, trace_buf_size,
+                                                   RING_BUFFER_ALL_CPUS);
+                        type->allocated_snapshot = true;
+                }
 
                 /* the test is responsible for initializing and enabling */
                 pr_info("Testing tracer %s: ", type->name);
@@ -885,10 +885,14 @@ int register_tracer(struct tracer *type)
                 /* Only reset on passing, to avoid touching corrupted buffers */
                 tracing_reset_online_cpus(tr);
 
-                /* Shrink the max buffer again */
-                if (ring_buffer_expanded && type->use_max_tr)
-                        ring_buffer_resize(max_tr.buffer, 1,
-                                                RING_BUFFER_ALL_CPUS);
+                if (type->use_max_tr) {
+                        type->allocated_snapshot = false;
+
+                        /* Shrink the max buffer again */
+                        if (ring_buffer_expanded)
+                                ring_buffer_resize(max_tr.buffer, 1,
+                                                   RING_BUFFER_ALL_CPUS);
+                }
 
                 printk(KERN_CONT "PASSED\n");
         }
@@ -1964,7 +1968,11 @@ static void *s_start(struct seq_file *m, loff_t *pos)
                 *iter->trace = *current_trace;
         mutex_unlock(&trace_types_lock);
 
-        atomic_inc(&trace_record_cmdline_disabled);
+        if (iter->snapshot && iter->trace->use_max_tr)
+                return ERR_PTR(-EBUSY);
+
+        if (!iter->snapshot)
+                atomic_inc(&trace_record_cmdline_disabled);
 
         if (*pos != iter->pos) {
                 iter->ent = NULL;
@@ -2003,7 +2011,11 @@ static void s_stop(struct seq_file *m, void *p)
 {
         struct trace_iterator *iter = m->private;
 
-        atomic_dec(&trace_record_cmdline_disabled);
+        if (iter->snapshot && iter->trace->use_max_tr)
+                return;
+
+        if (!iter->snapshot)
+                atomic_dec(&trace_record_cmdline_disabled);
         trace_access_unlock(iter->cpu_file);
         trace_event_read_unlock();
 }
@@ -2438,7 +2450,7 @@ static const struct seq_operations tracer_seq_ops = {
 };
 
 static struct trace_iterator *
-__tracing_open(struct inode *inode, struct file *file)
+__tracing_open(struct inode *inode, struct file *file, bool snapshot)
 {
         long cpu_file = (long) inode->i_private;
         struct trace_iterator *iter;
@@ -2471,10 +2483,11 @@ __tracing_open(struct inode *inode, struct file *file)
         if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
                 goto fail;
 
-        if (current_trace && current_trace->print_max)
+        if ((current_trace && current_trace->print_max) || snapshot)
                 iter->tr = &max_tr;
         else
                 iter->tr = &global_trace;
+        iter->snapshot = snapshot;
         iter->pos = -1;
         mutex_init(&iter->mutex);
         iter->cpu_file = cpu_file;
@@ -2491,8 +2504,9 @@ __tracing_open(struct inode *inode, struct file *file)
         if (trace_clocks[trace_clock_id].in_ns)
                 iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
 
-        /* stop the trace while dumping */
-        tracing_stop();
+        /* stop the trace while dumping if we are not opening "snapshot" */
+        if (!iter->snapshot)
+                tracing_stop();
 
         if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
                 for_each_tracing_cpu(cpu) {
@@ -2555,8 +2569,9 @@ static int tracing_release(struct inode *inode, struct file *file)
         if (iter->trace && iter->trace->close)
                 iter->trace->close(iter);
 
-        /* reenable tracing if it was previously enabled */
+        if (!iter