tracing: Add a proc file to stop tracing and free buffer

The proc file entry buffer_size_kb is used to set the size of tracing
buffer. The memory to expand the buffer size is kernel memory. Consider
a use case where tracing is handled by a user space utility, which acts
as a gate keeper for tracing requests. In an OOM condition, tracing is
considered a low priority task and if the utility gets killed the ring
buffer memory cannot be released back to the kernel.

This patch adds a proc file called "free_buffer" whose purpose is to
stop tracing and free up the ring buffer when it is closed.

The user space process can then set the desired size in buffer_size_kb
file and open the fd to the "free_buffer" file. Under OOM condition, if
the process gets killed, the kernel closes the file descriptor. The
release handler stops the tracing and releases the kernel memory
automatically.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Michael Rubin <mrubin@google.com>
Cc: David Sharp <dhsharp@google.com>
Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com>
Link: http://lkml.kernel.org/r/1308012717-11148-1-git-send-email-vnagarnaik@google.com
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 61fda6b..9c557ae 100644 (file)
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2768,7 +2768,7 @@ int tracer_init(struct tracer *t, struct trace_array *tr)
        return t->init(tr);
 }
 
-static int tracing_resize_ring_buffer(unsigned long size)
+static int __tracing_resize_ring_buffer(unsigned long size)
 {
        int ret;
 
@@ -2820,6 +2820,41 @@ static int tracing_resize_ring_buffer(unsigned long size)
        return ret;
 }
 
+static ssize_t tracing_resize_ring_buffer(unsigned long size)
+{
+       int cpu, ret = size;
+
+       mutex_lock(&trace_types_lock);
+
+       tracing_stop();
+
+       /* disable all cpu buffers */
+       for_each_tracing_cpu(cpu) {
+               if (global_trace.data[cpu])
+                       atomic_inc(&global_trace.data[cpu]->disabled);
+               if (max_tr.data[cpu])
+                       atomic_inc(&max_tr.data[cpu]->disabled);
+       }
+
+       if (size != global_trace.entries)
+               ret = __tracing_resize_ring_buffer(size);
+
+       if (ret < 0)
+               ret = -ENOMEM;
+
+       for_each_tracing_cpu(cpu) {
+               if (global_trace.data[cpu])
+                       atomic_dec(&global_trace.data[cpu]->disabled);
+               if (max_tr.data[cpu])
+                       atomic_dec(&max_tr.data[cpu]->disabled);
+       }
+
+       tracing_start();
+       mutex_unlock(&trace_types_lock);
+
+       return ret;
+}
+
 
 /**
  * tracing_update_buffers - used by tracing facility to expand ring buffers
@@ -2837,7 +2872,7 @@ int tracing_update_buffers(void)
 
        mutex_lock(&trace_types_lock);
        if (!ring_buffer_expanded)
-               ret = tracing_resize_ring_buffer(trace_buf_size);
+               ret = __tracing_resize_ring_buffer(trace_buf_size);
        mutex_unlock(&trace_types_lock);
 
        return ret;
@@ -2861,7 +2896,7 @@ static int tracing_set_tracer(const char *buf)
        mutex_lock(&trace_types_lock);
 
        if (!ring_buffer_expanded) {
-               ret = tracing_resize_ring_buffer(trace_buf_size);
+               ret = __tracing_resize_ring_buffer(trace_buf_size);
                if (ret < 0)
                        goto out;
                ret = 0;
@@ -3436,7 +3471,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 {
        unsigned long val;
        char buf[64];
-       int ret, cpu;
+       int ret;
 
        if (cnt >= sizeof(buf))
                return -EINVAL;
@@ -3454,48 +3489,43 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
        if (!val)
                return -EINVAL;
 
-       mutex_lock(&trace_types_lock);
-
-       tracing_stop();
-
-       /* disable all cpu buffers */
-       for_each_tracing_cpu(cpu) {
-               if (global_trace.data[cpu])
-                       atomic_inc(&global_trace.data[cpu]->disabled);
-               if (max_tr.data[cpu])
-                       atomic_inc(&max_tr.data[cpu]->disabled);
-       }
-
        /* value is in KB */
        val <<= 10;
 
-       if (val != global_trace.entries) {
-               ret = tracing_resize_ring_buffer(val);
-               if (ret < 0) {
-                       cnt = ret;
-                       goto out;
-               }
-       }
+       ret = tracing_resize_ring_buffer(val);
+       if (ret < 0)
+               return ret;
 
        *ppos += cnt;
 
-       /* If check pages failed, return ENOMEM */
-       if (tracing_disabled)
-               cnt = -ENOMEM;
- out:
-       for_each_tracing_cpu(cpu) {
-               if (global_trace.data[cpu])
-                       atomic_dec(&global_trace.data[cpu]->disabled);
-               if (max_tr.data[cpu])
-                       atomic_dec(&max_tr.data[cpu]->disabled);
-       }
+       return cnt;
+}
 
-       tracing_start();
-       mutex_unlock(&trace_types_lock);
+static ssize_t
+tracing_free_buffer_write(struct file *filp, const char __user *ubuf,
+                         size_t cnt, loff_t *ppos)
+{
+       /*
+        * There is no need to read what the user has written, this function
+        * is just to make sure that there is no error when "echo" is used
+        */
+
+       *ppos += cnt;
 
        return cnt;
 }
 
+static int
+tracing_free_buffer_release(struct inode *inode, struct file *filp)
+{
+       /* disable tracing */
+       tracing_off();
+       /* resize the ring buffer to 0 */
+       tracing_resize_ring_buffer(0);
+
+       return 0;
+}
+
 static int mark_printk(const char *fmt, ...)
 {
        int ret;
@@ -3641,6 +3671,11 @@ static const struct file_operations tracing_entries_fops = {
        .llseek         = generic_file_llseek,
 };
 
+static const struct file_operations tracing_free_buffer_fops = {
+       .write          = tracing_free_buffer_write,
+       .release        = tracing_free_buffer_release,
+};
+
 static const struct file_operations tracing_mark_fops = {
        .open           = tracing_open_generic,
        .write          = tracing_mark_write,
@@ -4365,6 +4400,9 @@ static __init int tracer_init_debugfs(void)
        trace_create_file("buffer_size_kb", 0644, d_tracer,
                        &global_trace, &tracing_entries_fops);
 
+       trace_create_file("free_buffer", 0644, d_tracer,
+                       &global_trace, &tracing_free_buffer_fops);
+
        trace_create_file("trace_marker", 0220, d_tracer,
                        NULL, &tracing_mark_fops);