tracing: Choose static tp_printk buffer by explicit nesting count

Currently, the trace_printk code chooses which static buffer to use based
on what type of atomic context (NMI, IRQ, etc) it's in.  Simplify the
code and make it more robust: simply count the nesting depth and choose
a buffer based on the current nesting depth.

The new code will only drop an event if we nest more than 4 deep,
and the old code was guaranteed to malfunction if that happened.

Link: http://lkml.kernel.org/r/07ab03aecfba25fcce8f9a211b14c9c5e2865c58.1464289095.git.luto@kernel.org
Acked-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index aa240551fc5d4b184adf0058d9d76ff726fb731c..45e6747589c66d3409f9955b22bc9d769426336b 100644 (file)
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2339,83 +2339,41 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags)
 
 /* created for use with alloc_percpu */
 struct trace_buffer_struct {
-       char buffer[TRACE_BUF_SIZE];
+       int nesting;
+       char buffer[4][TRACE_BUF_SIZE];
 };
 
 static struct trace_buffer_struct *trace_percpu_buffer;
-static struct trace_buffer_struct *trace_percpu_sirq_buffer;
-static struct trace_buffer_struct *trace_percpu_irq_buffer;
-static struct trace_buffer_struct *trace_percpu_nmi_buffer;
 
 /*
- * The buffer used is dependent on the context. There is a per cpu
- * buffer for normal context, softirq contex, hard irq context and
- * for NMI context. Thise allows for lockless recording.
- *
- * Note, if the buffers failed to be allocated, then this returns NULL
+ * Thise allows for lockless recording.  If we're nested too deeply, then
+ * this returns NULL.
  */
 static char *get_trace_buf(void)
 {
-       struct trace_buffer_struct *percpu_buffer;
-
-       /*
-        * If we have allocated per cpu buffers, then we do not
-        * need to do any locking.
-        */
-       if (in_nmi())
-               percpu_buffer = trace_percpu_nmi_buffer;
-       else if (in_irq())
-               percpu_buffer = trace_percpu_irq_buffer;
-       else if (in_softirq())
-               percpu_buffer = trace_percpu_sirq_buffer;
-       else
-               percpu_buffer = trace_percpu_buffer;
+       struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer);
 
-       if (!percpu_buffer)
+       if (!buffer || buffer->nesting >= 4)
                return NULL;
 
-       return this_cpu_ptr(&percpu_buffer->buffer[0]);
+       return &buffer->buffer[buffer->nesting++][0];
+}
+
+static void put_trace_buf(void)
+{
+       this_cpu_dec(trace_percpu_buffer->nesting);
 }
 
 static int alloc_percpu_trace_buffer(void)
 {
        struct trace_buffer_struct *buffers;
-       struct trace_buffer_struct *sirq_buffers;
-       struct trace_buffer_struct *irq_buffers;
-       struct trace_buffer_struct *nmi_buffers;
 
        buffers = alloc_percpu(struct trace_buffer_struct);
-       if (!buffers)
-               goto err_warn;
-
-       sirq_buffers = alloc_percpu(struct trace_buffer_struct);
-       if (!sirq_buffers)
-               goto err_sirq;
-
-       irq_buffers = alloc_percpu(struct trace_buffer_struct);
-       if (!irq_buffers)
-               goto err_irq;
-
-       nmi_buffers = alloc_percpu(struct trace_buffer_struct);
-       if (!nmi_buffers)
-               goto err_nmi;
+       if (WARN(!buffers, "Could not allocate percpu trace_printk buffer"))
+               return -ENOMEM;
 
        trace_percpu_buffer = buffers;
-       trace_percpu_sirq_buffer = sirq_buffers;
-       trace_percpu_irq_buffer = irq_buffers;
-       trace_percpu_nmi_buffer = nmi_buffers;
-
        return 0;
-
- err_nmi:
-       free_percpu(irq_buffers);
- err_irq:
-       free_percpu(sirq_buffers);
- err_sirq:
-       free_percpu(buffers);
- err_warn:
-       WARN(1, "Could not allocate percpu trace_printk buffer");
-       return -ENOMEM;
 }
 
 static int buffers_allocated;
@@ -2506,7 +2464,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
        tbuffer = get_trace_buf();
        if (!tbuffer) {
                len = 0;
-               goto out;
+               goto out_nobuffer;
        }
 
        len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args);
@@ -2532,6 +2490,9 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
        }
 
 out:
+       put_trace_buf();
+
+out_nobuffer:
        preempt_enable_notrace();
        unpause_graph_tracing();
 
@@ -2563,7 +2524,7 @@ __trace_array_vprintk(struct ring_buffer *buffer,
        tbuffer = get_trace_buf();
        if (!tbuffer) {
                len = 0;
-               goto out;
+               goto out_nobuffer;
        }
 
        len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args);
@@ -2582,7 +2543,11 @@ __trace_array_vprintk(struct ring_buffer *buffer,
                __buffer_unlock_commit(buffer, event);
                ftrace_trace_stack(&global_trace, buffer, flags, 6, pc, NULL);
        }
- out:
+
+out:
+       put_trace_buf();
+
+out_nobuffer:
        preempt_enable_notrace();
        unpause_graph_tracing();