tracing/ring-buffer: Move poll wake ups into ring buffer code

Move the logic to wake up on ring buffer data into the ring buffer
code itself. This simplifies the tracing code a lot and also has the
added benefit that waiters on one of the instance buffers can be woken
only when data is added to that instance instead of data added to
any instance.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 12 insertions, 71 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3ec146c96df4..b5b25b6575a9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -19,7 +19,6 @@
 #include <linux/seq_file.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
-#include <linux/irq_work.h>
 #include <linux/debugfs.h>
 #include <linux/pagemap.h>
 #include <linux/hardirq.h>
@@ -87,14 +86,6 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
 static DEFINE_PER_CPU(bool, trace_cmdline_save);
 
 /*
- * When a reader is waiting for data, then this variable is
- * set to true.
- */
-static bool trace_wakeup_needed;
-
-static struct irq_work trace_work_wakeup;
-
-/*
  * Kill all tracing for good (never come back).
  * It is initialized to 1 but will turn to zero if the initialization
  * of the tracer is successful. But that is the only place that sets
@@ -334,9 +325,6 @@ 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);
-
 /* trace_flags holds trace_options default values */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
         TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
@@ -344,19 +332,6 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
         TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS;
 
 /**
- * trace_wake_up - wake up tasks waiting for trace input
- *
- * Schedules a delayed work to wake up any task that is blocked on the
- * trace_wait queue. These is used with trace_poll for tasks polling the
- * trace.
- */
-static void trace_wake_up(struct irq_work *work)
-{
-        wake_up_all(&trace_wait);
-
-}
-
-/**
  * tracing_on - enable tracing buffers
  *
  * This function enables tracing buffers that may have been
@@ -763,36 +738,11 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 static void default_wait_pipe(struct trace_iterator *iter)
 {
-        DEFINE_WAIT(wait);
-
-        prepare_to_wait(&trace_wait, &wait, TASK_INTERRUPTIBLE);
-
-        /*
-         * The events can happen in critical sections where
-         * checking a work queue can cause deadlocks.
-         * After adding a task to the queue, this flag is set
-         * only to notify events to try to wake up the queue
-         * using irq_work.
-         *
-         * We don't clear it even if the buffer is no longer
-         * empty. The flag only causes the next event to run
-         * irq_work to do the work queue wake up. The worse
-         * that can happen if we race with !trace_empty() is that
-         * an event will cause an irq_work to try to wake up
-         * an empty queue.
-         *
-         * There's no reason to protect this flag either, as
-         * the work queue and irq_work logic will do the necessary
-         * synchronization for the wake ups. The only thing
-         * that is necessary is that the wake up happens after
-         * a task has been queued. It's OK for spurious wake ups.
-         */
-        trace_wakeup_needed = true;
-
-        if (trace_empty(iter))
-                schedule();
+        /* Iterators are static, they should be filled or empty */
+        if (trace_buffer_iter(iter, iter->cpu_file))
+                return;
 
-        finish_wait(&trace_wait, &wait);
+        ring_buffer_wait(iter->tr->buffer, iter->cpu_file);
 }
 
 /**
@@ -1262,11 +1212,6 @@ void
 __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
 {
         __this_cpu_write(trace_cmdline_save, true);
-        if (trace_wakeup_needed) {
-                trace_wakeup_needed = false;
-                /* irq_work_queue() supplies it's own memory barriers */
-                irq_work_queue(&trace_work_wakeup);
-        }
         ring_buffer_unlock_commit(buffer, event);
 }
 
@@ -3557,21 +3502,18 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 static unsigned int
 trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_table)
 {
-        if (trace_flags & TRACE_ITER_BLOCK) {
+        /* Iterators are static, they should be filled or empty */
+        if (trace_buffer_iter(iter, iter->cpu_file))
+                return POLLIN | POLLRDNORM;
+
+        if (trace_flags & TRACE_ITER_BLOCK)
                 /*
                  * Always select as readable when in blocking mode
                  */
                 return POLLIN | POLLRDNORM;
-        } else {
-                if (!trace_empty(iter))
-                        return POLLIN | POLLRDNORM;
-                trace_wakeup_needed = true;
-                poll_wait(filp, &trace_wait, poll_table);
-                if (!trace_empty(iter))
-                        return POLLIN | POLLRDNORM;
-
-                return 0;
-        }
+        else
+                return ring_buffer_poll_wait(iter->tr->buffer, iter->cpu_file,
+                                             filp, poll_table);
 }
 
 static unsigned int
@@ -5701,7 +5643,6 @@ __init static int tracer_alloc_buffers(void)
 #endif
 
         trace_init_cmdlines();
-        init_irq_work(&trace_work_wakeup, trace_wake_up);
 
         register_tracer(&nop_trace);