16 files changed, 100 insertions, 57 deletions

diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 67f1cc47325..1ebc24cf9a5 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -454,6 +454,11 @@ x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
                    latencies, as described in "Latency
                    trace format".
 
+  overwrite - This controls what happens when the trace buffer is
+              full. If "1" (default), the oldest events are
+              discarded and overwritten. If "0", then the newest
+              events are discarded.
+
 ftrace_enabled
 --------------
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 382eb2936d4..a93742a5746 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -437,18 +437,19 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
                 return;
         }
 
-        if (ftrace_push_return_trace(old, self_addr, &trace.depth,
-                    frame_pointer) == -EBUSY) {
-                *parent = old;
-                return;
-        }
-
         trace.func = self_addr;
+        trace.depth = current->curr_ret_stack + 1;
 
         /* Only trace if the calling function expects to */
         if (!ftrace_graph_entry(&trace)) {
-                current->curr_ret_stack--;
                 *parent = old;
+                return;
+        }
+
+        if (ftrace_push_return_trace(old, self_addr, &trace.depth,
+                    frame_pointer) == -EBUSY) {
+                *parent = old;
+                return;
         }
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 1357d7cf4ec..db932760ea8 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -62,21 +62,21 @@ TRACE_EVENT(kvm_hv_hypercall,
         TP_ARGS(code, fast, rep_cnt, rep_idx, ingpa, outgpa),
 
         TP_STRUCT__entry(
-                __field(        __u16,          code            )
-                __field(        bool,           fast            )
                 __field(        __u16,          rep_cnt         )
                 __field(        __u16,          rep_idx         )
                 __field(        __u64,          ingpa           )
                 __field(        __u64,          outgpa          )
+                __field(        __u16,          code            )
+                __field(        bool,           fast            )
         ),
 
         TP_fast_assign(
-                __entry->code           = code;
-                __entry->fast           = fast;
                 __entry->rep_cnt        = rep_cnt;
                 __entry->rep_idx        = rep_idx;
                 __entry->ingpa          = ingpa;
                 __entry->outgpa         = outgpa;
+                __entry->code           = code;
+                __entry->fast           = fast;
         ),
 
         TP_printk("code 0x%x %s cnt 0x%x idx 0x%x in 0x%llx out 0x%llx",
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 1a99e7939c2..22b32af1b5e 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -37,7 +37,6 @@ struct trace_entry {
         unsigned char           flags;
         unsigned char           preempt_count;
         int                     pid;
-        int                     lock_depth;
 };
 
 #define FTRACE_MAX_EVENT                                                \
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 8d3a2486544..ab38ac80b0f 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -100,6 +100,8 @@ void ring_buffer_free(struct ring_buffer *buffer);
 
 int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
 
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val);
+
 struct ring_buffer_event *ring_buffer_lock_reserve(struct ring_buffer *buffer,
                                                    unsigned long length);
 int ring_buffer_unlock_commit(struct ring_buffer *buffer,
diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h
index 7eee77895cb..4cbbcef6baa 100644
--- a/include/trace/events/mce.h
+++ b/include/trace/events/mce.h
@@ -17,36 +17,36 @@ TRACE_EVENT(mce_record,
         TP_STRUCT__entry(
                 __field(        u64,            mcgcap          )
                 __field(        u64,            mcgstatus       )
-                __field(        u8,             bank            )
                 __field(        u64,            status          )
                 __field(        u64,            addr            )
                 __field(        u64,            misc            )
                 __field(        u64,            ip              )
-                __field(        u8,             cs              )
                 __field(        u64,            tsc             )
                 __field(        u64,            walltime        )
                 __field(        u32,            cpu             )
                 __field(        u32,            cpuid           )
                 __field(        u32,            apicid          )
                 __field(        u32,            socketid        )
+                __field(        u8,             cs              )
+                __field(        u8,             bank            )
                 __field(        u8,             cpuvendor       )
         ),
 
         TP_fast_assign(
                 __entry->mcgcap         = m->mcgcap;
                 __entry->mcgstatus      = m->mcgstatus;
-                __entry->bank           = m->bank;
                 __entry->status         = m->status;
                 __entry->addr           = m->addr;
                 __entry->misc           = m->misc;
                 __entry->ip             = m->ip;
-                __entry->cs             = m->cs;
                 __entry->tsc            = m->tsc;
                 __entry->walltime       = m->time;
                 __entry->cpu            = m->extcpu;
                 __entry->cpuid          = m->cpuid;
                 __entry->apicid         = m->apicid;
                 __entry->socketid       = m->socketid;
+                __entry->cs             = m->cs;
+                __entry->bank           = m->bank;
                 __entry->cpuvendor      = m->cpuvendor;
         ),
 
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index c6bae36547e..21a546d27c0 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -108,14 +108,14 @@ TRACE_EVENT(module_request,
         TP_ARGS(name, wait, ip),
 
         TP_STRUCT__entry(
-                __field(        bool,           wait            )
                 __field(        unsigned long,  ip              )
+                __field(        bool,           wait            )
                 __string(       name,           name            )
         ),
 
         TP_fast_assign(
-                __entry->wait   = wait;
                 __entry->ip     = ip;
+                __entry->wait   = wait;
                 __assign_str(name, name);
         ),
 
@@ -129,4 +129,3 @@ TRACE_EVENT(module_request,
 
 /* This part must be outside protection */
 #include <trace/define_trace.h>
-
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index f10293c41b1..0c68ae22da2 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -19,14 +19,14 @@ TRACE_EVENT(kfree_skb,
 
         TP_STRUCT__entry(
                 __field(        void *,         skbaddr         )
-                __field(        unsigned short, protocol        )
                 __field(        void *,         location        )
+                __field(        unsigned short, protocol        )
         ),
 
         TP_fast_assign(
                 __entry->skbaddr = skb;
-                __entry->protocol = ntohs(skb->protocol);
                 __entry->location = location;
+                __entry->protocol = ntohs(skb->protocol);
         ),
 
         TP_printk("skbaddr=%p protocol=%u location=%p",
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bd1c35a4fbc..db7b439d23e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5,7 +5,6 @@
  */
 #include <linux/ring_buffer.h>
 #include <linux/trace_clock.h>
-#include <linux/ftrace_irq.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
@@ -1429,6 +1428,17 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
+{
+        mutex_lock(&buffer->mutex);
+        if (val)
+                buffer->flags |= RB_FL_OVERWRITE;
+        else
+                buffer->flags &= ~RB_FL_OVERWRITE;
+        mutex_unlock(&buffer->mutex);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);
+
 static inline void *
 __rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
 {
@@ -2162,11 +2172,19 @@ rb_reserve_next_event(struct ring_buffer *buffer,
         if (likely(ts >= cpu_buffer->write_stamp)) {
                 delta = diff;
                 if (unlikely(test_time_stamp(delta))) {
+                        int local_clock_stable = 1;
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+                        local_clock_stable = sched_clock_stable;
+#endif
                         WARN_ONCE(delta > (1ULL << 59),
-                                  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
+                                  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
                                   (unsigned long long)delta,
                                   (unsigned long long)ts,
-                                  (unsigned long long)cpu_buffer->write_stamp);
+                                  (unsigned long long)cpu_buffer->write_stamp,
+                                  local_clock_stable ? "" :
+                                  "If you just came from a suspend/resume,\n"
+                                  "please switch to the trace global clock:\n"
+                                  "  echo global > /sys/kernel/debug/tracing/trace_clock\n");
                         add_timestamp = 1;
                 }
         }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8dc8da6733f..9541c27c1cf 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -41,8 +41,6 @@
 #include "trace.h"
 #include "trace_output.h"
 
-#define TRACE_BUFFER_FLAGS      (RB_FL_OVERWRITE)
-
 /*
  * On boot up, the ring buffer is set to the minimum size, so that
  * we do not waste memory on systems that are not using tracing.
@@ -340,7 +338,7 @@ 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 |
-        TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD;
+        TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE;
 
 static int trace_stop_count;
 static DEFINE_SPINLOCK(tracing_start_lock);
@@ -425,6 +423,7 @@ static const char *trace_options[] = {
         "sleep-time",
         "graph-time",
         "record-cmd",
+        "overwrite",
         NULL
 };
 
@@ -780,6 +779,11 @@ __acquires(kernel_lock)
                 tracing_reset_online_cpus(tr);
 
                 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);
+
                 /* the test is responsible for initializing and enabling */
                 pr_info("Testing tracer %s: ", type->name);
                 ret = type->selftest(type, tr);
@@ -792,6 +796,10 @@ __acquires(kernel_lock)
                 /* 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);
+
                 printk(KERN_CONT "PASSED\n");
         }
 #endif
@@ -1102,7 +1110,6 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
         entry->preempt_count            = pc & 0xff;
         entry->pid                      = (tsk) ? tsk->pid : 0;
-        entry->lock_depth               = (tsk) ? tsk->lock_depth : 0;
         entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
                 (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -1749,10 +1756,9 @@ static void print_lat_help_header(struct seq_file *m)
         seq_puts(m, "#                | / _----=> need-resched    \n");
         seq_puts(m, "#                || / _---=> hardirq/softirq \n");
         seq_puts(m, "#                ||| / _--=> preempt-depth   \n");
-        seq_puts(m, "#                |||| /_--=> lock-depth       \n");
-        seq_puts(m, "#                |||||/     delay             \n");
-        seq_puts(m, "#  cmd     pid   |||||| time  |   caller      \n");
-        seq_puts(m, "#     \\   /      ||||||   \\   |   /           \n");
+        seq_puts(m, "#                |||| /     delay             \n");
+        seq_puts(m, "#  cmd     pid   ||||| time  |   caller      \n");
+        seq_puts(m, "#     \\   /      |||||  \\    |   /           \n");
 }
 
 static void print_func_help_header(struct seq_file *m)
@@ -2529,6 +2535,9 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 
         if (mask == TRACE_ITER_RECORD_CMD)
                 trace_event_enable_cmd_record(enabled);
+
+        if (mask == TRACE_ITER_OVERWRITE)
+                ring_buffer_change_overwrite(global_trace.buffer, enabled);
 }
 
 static ssize_t
@@ -4555,9 +4564,11 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 __init static int tracer_alloc_buffers(void)
 {
         int ring_buf_size;
+        enum ring_buffer_flags rb_flags;
         int i;
         int ret = -ENOMEM;
 
+
         if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
                 goto out;
 
@@ -4570,12 +4581,13 @@ __init static int tracer_alloc_buffers(void)
         else
                 ring_buf_size = 1;
 
+        rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+
         cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
         cpumask_copy(tracing_cpumask, cpu_all_mask);
 
         /* TODO: make the number of buffers hot pluggable with CPUS */
-        global_trace.buffer = ring_buffer_alloc(ring_buf_size,
-                                                   TRACE_BUFFER_FLAGS);
+        global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags);
         if (!global_trace.buffer) {
                 printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
                 WARN_ON(1);
@@ -4585,7 +4597,7 @@ __init static int tracer_alloc_buffers(void)
 
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-        max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS);
+        max_tr.buffer = ring_buffer_alloc(1, rb_flags);
         if (!max_tr.buffer) {
                 printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
                 WARN_ON(1);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 856e73cc1d3..5e9dfc6286d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -272,8 +272,8 @@ struct tracer {
         /* If you handled the flag setting, return 0 */
         int                     (*set_flag)(u32 old_flags, u32 bit, int set);
         struct tracer           *next;
-        int                     print_max;
         struct tracer_flags     *flags;
+        int                     print_max;
         int                     use_max_tr;
 };
 
@@ -606,6 +606,7 @@ enum trace_iterator_flags {
         TRACE_ITER_SLEEP_TIME           = 0x40000,
         TRACE_ITER_GRAPH_TIME           = 0x80000,
         TRACE_ITER_RECORD_CMD           = 0x100000,
+        TRACE_ITER_OVERWRITE            = 0x200000,
 };
 
 /*
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 6cf223764be..1516cb3ec54 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -109,12 +109,12 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
  */
 #define FTRACE_CTX_FIELDS                                       \
         __field(        unsigned int,   prev_pid        )       \
+        __field(        unsigned int,   next_pid        )       \
+        __field(        unsigned int,   next_cpu        )       \
         __field(        unsigned char,  prev_prio       )       \
         __field(        unsigned char,  prev_state      )       \
-        __field(        unsigned int,   next_pid        )       \
         __field(        unsigned char,  next_prio       )       \
-        __field(        unsigned char,  next_state      )       \
-        __field(        unsigned int,   next_cpu        )
+        __field(        unsigned char,  next_state      )
 
 FTRACE_ENTRY(context_switch, ctx_switch_entry,
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 5f499e0438a..e88f74fe1d4 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,7 +116,6 @@ static int trace_define_common_fields(void)
         __common_field(unsigned char, flags);
         __common_field(unsigned char, preempt_count);
         __common_field(int, pid);
-        __common_field(int, lock_depth);
 
         return ret;
 }
@@ -326,6 +325,7 @@ int trace_set_clr_event(const char *system, const char *event, int set)
 {
         return __ftrace_set_clr_event(NULL, system, event, set);
 }
+EXPORT_SYMBOL_GPL(trace_set_clr_event);
 
 /* 128 should be much more than enough */
 #define EVENT_BUF_SIZE          127
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 02272baa220..456be9063c2 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -529,24 +529,34 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
  * @entry: The trace entry field from the ring buffer
  *
  * Prints the generic fields of irqs off, in hard or softirq, preempt
- * count and lock depth.
+ * count.
  */
 int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 {
-        int hardirq, softirq;
+        char hardsoft_irq;
+        char need_resched;
+        char irqs_off;
+        int hardirq;
+        int softirq;
         int ret;
 
         hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
         softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
 
+        irqs_off =
+                (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
+                (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' :
+                '.';
+        need_resched =
+                (entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.';
+        hardsoft_irq =
+                (hardirq && softirq) ? 'H' :
+                hardirq ? 'h' :
+                softirq ? 's' :
+                '.';
+
         if (!trace_seq_printf(s, "%c%c%c",
-                              (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
-                                (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
-                                  'X' : '.',
-                              (entry->flags & TRACE_FLAG_NEED_RESCHED) ?
-                                'N' : '.',
-                              (hardirq && softirq) ? 'H' :
-                                hardirq ? 'h' : softirq ? 's' : '.'))
+                              irqs_off, need_resched, hardsoft_irq))
                 return 0;
 
         if (entry->preempt_count)
@@ -554,13 +564,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
         else
                 ret = trace_seq_putc(s, '.');
 
-        if (!ret)
-                return 0;
-
-        if (entry->lock_depth < 0)
-                return trace_seq_putc(s, '.');
-
-        return trace_seq_printf(s, "%d", entry->lock_depth);
+        return ret;
 }
 
 static int
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 038b3d1e298..f9f6f52db77 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -206,7 +206,8 @@ static uint32_t (*w2)(uint16_t);
 static int
 is_mcounted_section_name(char const *const txtname)
 {
-        return 0 == strcmp(".text",          txtname) ||
+        return 0 == strcmp(".text",           txtname) ||
+                0 == strcmp(".ref.text",      txtname) ||
                 0 == strcmp(".sched.text",    txtname) ||
                 0 == strcmp(".spinlock.text", txtname) ||
                 0 == strcmp(".irqentry.text", txtname) ||
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 1d7963f4ee7..4be0deea71c 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -130,6 +130,7 @@ if ($inputfile =~ m,kernel/trace/ftrace\.o$,) {
 # Acceptable sections to record.
 my %text_sections = (
      ".text" => 1,
+     ".ref.text" => 1,
      ".sched.text" => 1,
      ".spinlock.text" => 1,
      ".irqentry.text" => 1,