Merge commit 'tip/tracing/core' into oprofile/core

Conflicts:
	drivers/oprofile/cpu_buffer.c

Signed-off-by: Robert Richter <robert.richter@amd.com>

5 files changed, 122 insertions, 18 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 41ca394feb22..5885cdfc41f3 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -319,6 +319,11 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 #define TS_MASK         ((1ULL << TS_SHIFT) - 1)
 #define TS_DELTA_TEST   (~TS_MASK)
 
+/* Flag when events were overwritten */
+#define RB_MISSED_EVENTS        (1 << 31)
+/* Missed count stored at end */
+#define RB_MISSED_STORED        (1 << 30)
+
 struct buffer_data_page {
         u64              time_stamp;    /* page time stamp */
         local_t          commit;        /* write committed index */
@@ -338,6 +343,7 @@ struct buffer_page {
         local_t          write;         /* index for next write */
         unsigned         read;          /* index for next read */
         local_t          entries;       /* entries on this page */
+        unsigned long    real_end;      /* real end of data */
         struct buffer_data_page *page;  /* Actual data page */
 };
 
@@ -417,6 +423,12 @@ int ring_buffer_print_page_header(struct trace_seq *s)
                                (unsigned int)sizeof(field.commit),
                                (unsigned int)is_signed_type(long));
 
+        ret = trace_seq_printf(s, "\tfield: int overwrite;\t"
+                               "offset:%u;\tsize:%u;\tsigned:%u;\n",
+                               (unsigned int)offsetof(typeof(field), commit),
+                               1,
+                               (unsigned int)is_signed_type(long));
+
         ret = trace_seq_printf(s, "\tfield: char data;\t"
                                "offset:%u;\tsize:%u;\tsigned:%u;\n",
                                (unsigned int)offsetof(typeof(field), data),
@@ -440,6 +452,8 @@ struct ring_buffer_per_cpu {
         struct buffer_page              *tail_page;     /* write to tail */
         struct buffer_page              *commit_page;   /* committed pages */
         struct buffer_page              *reader_page;
+        unsigned long                   lost_events;
+        unsigned long                   last_overrun;
         local_t                         commit_overrun;
         local_t                         overrun;
         local_t                         entries;
@@ -1762,6 +1776,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
         kmemcheck_annotate_bitfield(event, bitfield);
 
         /*
+         * Save the original length to the meta data.
+         * This will be used by the reader to add lost event
+         * counter.
+         */
+        tail_page->real_end = tail;
+
+        /*
          * If this event is bigger than the minimum size, then
          * we need to be careful that we don't subtract the
          * write counter enough to allow another writer to slip
@@ -2838,6 +2859,7 @@ static struct buffer_page *
 rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
         struct buffer_page *reader = NULL;
+        unsigned long overwrite;
         unsigned long flags;
         int nr_loops = 0;
         int ret;
@@ -2879,6 +2901,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         local_set(&cpu_buffer->reader_page->write, 0);
         local_set(&cpu_buffer->reader_page->entries, 0);
         local_set(&cpu_buffer->reader_page->page->commit, 0);
+        cpu_buffer->reader_page->real_end = 0;
 
  spin:
         /*
@@ -2899,6 +2922,18 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);
 
         /*
+         * We want to make sure we read the overruns after we set up our
+         * pointers to the next object. The writer side does a
+         * cmpxchg to cross pages which acts as the mb on the writer
+         * side. Note, the reader will constantly fail the swap
+         * while the writer is updating the pointers, so this
+         * guarantees that the overwrite recorded here is the one we
+         * want to compare with the last_overrun.
+         */
+        smp_mb();
+        overwrite = local_read(&(cpu_buffer->overrun));
+
+        /*
          * Here's the tricky part.
          *
          * We need to move the pointer past the header page.
@@ -2929,6 +2964,11 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         cpu_buffer->reader_page = reader;
         rb_reset_reader_page(cpu_buffer);
 
+        if (overwrite != cpu_buffer->last_overrun) {
+                cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun;
+                cpu_buffer->last_overrun = overwrite;
+        }
+
         goto again;
 
  out:
@@ -3005,8 +3045,14 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
                 rb_advance_iter(iter);
 }
 
+static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        return cpu_buffer->lost_events;
+}
+
 static struct ring_buffer_event *
-rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
+rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
+               unsigned long *lost_events)
 {
         struct ring_buffer_event *event;
         struct buffer_page *reader;
@@ -3058,6 +3104,8 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
                         ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
                                                          cpu_buffer->cpu, ts);
                 }
+                if (lost_events)
+                        *lost_events = rb_lost_events(cpu_buffer);
                 return event;
 
         default:
@@ -3168,12 +3216,14 @@ static inline int rb_ok_to_lock(void)
  * @buffer: The ring buffer to read
  * @cpu: The cpu to peak at
  * @ts: The timestamp counter of this event.
+ * @lost_events: a variable to store if events were lost (may be NULL)
  *
  * This will return the event that will be read next, but does
  * not consume the data.
  */
 struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
+                 unsigned long *lost_events)
 {
         struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
         struct ring_buffer_event *event;
@@ -3188,7 +3238,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
         local_irq_save(flags);
         if (dolock)
                 spin_lock(&cpu_buffer->reader_lock);
-        event = rb_buffer_peek(cpu_buffer, ts);
+        event = rb_buffer_peek(cpu_buffer, ts, lost_events);
         if (event && event->type_len == RINGBUF_TYPE_PADDING)
                 rb_advance_reader(cpu_buffer);
         if (dolock)
@@ -3230,13 +3280,17 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 /**
  * ring_buffer_consume - return an event and consume it
  * @buffer: The ring buffer to get the next event from
+ * @cpu: the cpu to read the buffer from
+ * @ts: a variable to store the timestamp (may be NULL)
+ * @lost_events: a variable to store if events were lost (may be NULL)
  *
  * Returns the next event in the ring buffer, and that event is consumed.
  * Meaning, that sequential reads will keep returning a different event,
  * and eventually empty the ring buffer if the producer is slower.
  */
 struct ring_buffer_event *
-ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
+                    unsigned long *lost_events)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
         struct ring_buffer_event *event = NULL;
@@ -3257,9 +3311,11 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
         if (dolock)
                 spin_lock(&cpu_buffer->reader_lock);
 
-        event = rb_buffer_peek(cpu_buffer, ts);
-        if (event)
+        event = rb_buffer_peek(cpu_buffer, ts, lost_events);
+        if (event) {
+                cpu_buffer->lost_events = 0;
                 rb_advance_reader(cpu_buffer);
+        }
 
         if (dolock)
                 spin_unlock(&cpu_buffer->reader_lock);
@@ -3408,6 +3464,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
         cpu_buffer->write_stamp = 0;
         cpu_buffer->read_stamp = 0;
 
+        cpu_buffer->lost_events = 0;
+        cpu_buffer->last_overrun = 0;
+
         rb_head_page_activate(cpu_buffer);
 }
 
@@ -3683,6 +3742,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
         struct ring_buffer_event *event;
         struct buffer_data_page *bpage;
         struct buffer_page *reader;
+        unsigned long missed_events;
         unsigned long flags;
         unsigned int commit;
         unsigned int read;
@@ -3719,6 +3779,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
         read = reader->read;
         commit = rb_page_commit(reader);
 
+        /* Check if any events were dropped */
+        missed_events = cpu_buffer->lost_events;
+
         /*
          * If this page has been partially read or
          * if len is not big enough to read the rest of the page or
@@ -3779,9 +3842,35 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
                 local_set(&reader->entries, 0);
                 reader->read = 0;
                 *data_page = bpage;
+
+                /*
+                 * Use the real_end for the data size,
+                 * This gives us a chance to store the lost events
+                 * on the page.
+                 */
+                if (reader->real_end)
+                        local_set(&bpage->commit, reader->real_end);
         }
         ret = read;
 
+        cpu_buffer->lost_events = 0;
+        /*
+         * Set a flag in the commit field if we lost events
+         */
+        if (missed_events) {
+                commit = local_read(&bpage->commit);
+
+                /* If there is room at the end of the page to save the
+                 * missed events, then record it there.
+                 */
+                if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
+                        memcpy(&bpage->data[commit], &missed_events,
+                               sizeof(missed_events));
+                        local_add(RB_MISSED_STORED, &bpage->commit);
+                }
+                local_add(RB_MISSED_EVENTS, &bpage->commit);
+        }
+
  out_unlock:
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index df74c7982255..dc56556b55a2 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -81,7 +81,7 @@ static enum event_status read_event(int cpu)
         int *entry;
         u64 ts;
 
-        event = ring_buffer_consume(buffer, cpu, &ts);
+        event = ring_buffer_consume(buffer, cpu, &ts, NULL);
         if (!event)
                 return EVENT_DROPPED;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 44f916a04065..60f3b6289731 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1545,7 +1545,8 @@ static void trace_iterator_increment(struct trace_iterator *iter)
 }
 
 static struct trace_entry *
-peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
+                unsigned long *lost_events)
 {
         struct ring_buffer_event *event;
         struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
@@ -1556,7 +1557,8 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
         if (buf_iter)
                 event = ring_buffer_iter_peek(buf_iter, ts);
         else
-                event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+                event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+                                         lost_events);
 
         ftrace_enable_cpu();
 
@@ -1564,10 +1566,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 }
 
 static struct trace_entry *
-__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu,
+                  unsigned long *missing_events, u64 *ent_ts)
 {
         struct ring_buffer *buffer = iter->tr->buffer;
         struct trace_entry *ent, *next = NULL;
+        unsigned long lost_events, next_lost = 0;
         int cpu_file = iter->cpu_file;
         u64 next_ts = 0, ts;
         int next_cpu = -1;
@@ -1580,7 +1584,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
         if (cpu_file > TRACE_PIPE_ALL_CPU) {
                 if (ring_buffer_empty_cpu(buffer, cpu_file))
                         return NULL;
-                ent = peek_next_entry(iter, cpu_file, ent_ts);
+                ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
                 if (ent_cpu)
                         *ent_cpu = cpu_file;
 
@@ -1592,7 +1596,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
                 if (ring_buffer_empty_cpu(buffer, cpu))
                         continue;
 
-                ent = peek_next_entry(iter, cpu, &ts);
+                ent = peek_next_entry(iter, cpu, &ts, &lost_events);
 
                 /*
                  * Pick the entry with the smallest timestamp:
@@ -1601,6 +1605,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
                         next = ent;
                         next_cpu = cpu;
                         next_ts = ts;
+                        next_lost = lost_events;
                 }
         }
 
@@ -1610,6 +1615,9 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
         if (ent_ts)
                 *ent_ts = next_ts;
 
+        if (missing_events)
+                *missing_events = next_lost;
+
         return next;
 }
 
@@ -1617,13 +1625,14 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
                                           int *ent_cpu, u64 *ent_ts)
 {
-        return __find_next_entry(iter, ent_cpu, ent_ts);
+        return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
 static void *find_next_entry_inc(struct trace_iterator *iter)
 {
-        iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
+        iter->ent = __find_next_entry(iter, &iter->cpu,
+                                      &iter->lost_events, &iter->ts);
 
         if (iter->ent)
                 trace_iterator_increment(iter);
@@ -1635,7 +1644,8 @@ static void trace_consume(struct trace_iterator *iter)
 {
         /* Don't allow ftrace to trace into the ring buffers */
         ftrace_disable_cpu();
-        ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+        ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+                            &iter->lost_events);
         ftrace_enable_cpu();
 }
 
@@ -2030,6 +2040,10 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
         enum print_line_t ret;
 
+        if (iter->lost_events)
+                trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+                                 iter->cpu, iter->lost_events);
+
         if (iter->trace && iter->trace->print_line) {
                 ret = iter->trace->print_line(iter);
                 if (ret != TRACE_TYPE_UNHANDLED)
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 9aed1a5cf553..669b9c31861d 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -490,9 +490,10 @@ get_return_for_leaf(struct trace_iterator *iter,
                          * We need to consume the current entry to see
                          * the next one.
                          */
-                        ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+                        ring_buffer_consume(iter->tr->buffer, iter->cpu,
+                                            NULL, NULL);
                         event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
-                                                 NULL);
+                                                 NULL, NULL);
                 }
 
                 if (!event)
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 81003b4d617f..9398034f814a 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -30,7 +30,7 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
         struct trace_entry *entry;
         unsigned int loops = 0;
 
-        while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
+        while ((event = ring_buffer_consume(tr->buffer, cpu, NULL, NULL))) {
                 entry = ring_buffer_event_data(event);
 
                 /*