7 files changed, 121 insertions, 44 deletions

diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c
index ce0d9da52a8a..94966edfb44d 100644
--- a/drivers/char/sysrq.c
+++ b/drivers/char/sysrq.c
@@ -274,6 +274,22 @@ static struct sysrq_key_op sysrq_showstate_blocked_op = {
         .enable_mask    = SYSRQ_ENABLE_DUMP,
 };
 
+#ifdef CONFIG_TRACING
+#include <linux/ftrace.h>
+
+static void sysrq_ftrace_dump(int key, struct tty_struct *tty)
+{
+        ftrace_dump();
+}
+static struct sysrq_key_op sysrq_ftrace_dump_op = {
+        .handler        = sysrq_ftrace_dump,
+        .help_msg       = "dumpZ-ftrace-buffer",
+        .action_msg     = "Dump ftrace buffer",
+        .enable_mask    = SYSRQ_ENABLE_DUMP,
+};
+#else
+#define sysrq_ftrace_dump_op (*(struct sysrq_key_op *)0)
+#endif
 
 static void sysrq_handle_showmem(int key, struct tty_struct *tty)
 {
@@ -406,7 +422,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = {
         NULL,                           /* x */
         /* y: May be registered on sparc64 for global register dump */
         NULL,                           /* y */
-        NULL                            /* z */
+        &sysrq_ftrace_dump_op,          /* z */
 };
 
 /* key2index calculation, -1 on invalid index */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6b6b727258b5..65d4a9ba79e4 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -487,7 +487,7 @@ static struct ctl_table kern_table[] = {
 #ifdef CONFIG_TRACING
         {
                 .ctl_name       = CTL_UNNUMBERED,
-                .procname       = "ftrace_dump_on_opps",
+                .procname       = "ftrace_dump_on_oops",
                 .data           = &ftrace_dump_on_oops,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index cedf4e268285..151f6a748676 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -16,6 +16,8 @@
 #include <linux/list.h>
 #include <linux/fs.h>
 
+#include "trace.h"
+
 /* Up this if you want to test the TIME_EXTENTS and normalization */
 #define DEBUG_SHIFT 0
 
@@ -1122,8 +1124,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
                 return NULL;
 
         /* If we are tracing schedule, we don't want to recurse */
-        resched = need_resched();
-        preempt_disable_notrace();
+        resched = ftrace_preempt_disable();
 
         cpu = raw_smp_processor_id();
 
@@ -1154,10 +1155,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
         return event;
 
  out:
-        if (resched)
-                preempt_enable_notrace();
-        else
-                preempt_enable_notrace();
+        ftrace_preempt_enable(resched);
         return NULL;
 }
 
@@ -1199,12 +1197,9 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
         /*
          * Only the last preempt count needs to restore preemption.
          */
-        if (preempt_count() == 1) {
-                if (per_cpu(rb_need_resched, cpu))
-                        preempt_enable_no_resched_notrace();
-                else
-                        preempt_enable_notrace();
-        } else
+        if (preempt_count() == 1)
+                ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+        else
                 preempt_enable_no_resched_notrace();
 
         return 0;
@@ -1237,8 +1232,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
         if (atomic_read(&buffer->record_disabled))
                 return -EBUSY;
 
-        resched = need_resched();
-        preempt_disable_notrace();
+        resched = ftrace_preempt_disable();
 
         cpu = raw_smp_processor_id();
 
@@ -1264,10 +1258,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
         ret = 0;
  out:
-        if (resched)
-                preempt_enable_no_resched_notrace();
-        else
-                preempt_enable_notrace();
+        ftrace_preempt_enable(resched);
 
         return ret;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 50d7018163f6..29ab40a764c8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -244,6 +244,7 @@ static const char *trace_options[] = {
         "stacktrace",
         "sched-tree",
         "ftrace_printk",
+        "ftrace_preempt",
         NULL
 };
 
@@ -891,7 +892,7 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
 
 #ifdef CONFIG_FUNCTION_TRACER
 static void
-function_trace_call(unsigned long ip, unsigned long parent_ip)
+function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
 {
         struct trace_array *tr = &global_trace;
         struct trace_array_cpu *data;
@@ -904,8 +905,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
                 return;
 
         pc = preempt_count();
-        resched = need_resched();
-        preempt_disable_notrace();
+        resched = ftrace_preempt_disable();
         local_save_flags(flags);
         cpu = raw_smp_processor_id();
         data = tr->data[cpu];
@@ -915,10 +915,38 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
                 trace_function(tr, data, ip, parent_ip, flags, pc);
 
         atomic_dec(&data->disabled);
-        if (resched)
-                preempt_enable_no_resched_notrace();
-        else
-                preempt_enable_notrace();
+        ftrace_preempt_enable(resched);
+}
+
+static void
+function_trace_call(unsigned long ip, unsigned long parent_ip)
+{
+        struct trace_array *tr = &global_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        long disabled;
+        int cpu;
+        int pc;
+
+        if (unlikely(!ftrace_function_enabled))
+                return;
+
+        /*
+         * Need to use raw, since this must be called before the
+         * recursive protection is performed.
+         */
+        raw_local_irq_save(flags);
+        cpu = raw_smp_processor_id();
+        data = tr->data[cpu];
+        disabled = atomic_inc_return(&data->disabled);
+
+        if (likely(disabled == 1)) {
+                pc = preempt_count();
+                trace_function(tr, data, ip, parent_ip, flags, pc);
+        }
+
+        atomic_dec(&data->disabled);
+        raw_local_irq_restore(flags);
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
@@ -929,6 +957,12 @@ static struct ftrace_ops trace_ops __read_mostly =
 void tracing_start_function_trace(void)
 {
         ftrace_function_enabled = 0;
+
+        if (trace_flags & TRACE_ITER_PREEMPTONLY)
+                trace_ops.func = function_trace_call_preempt_only;
+        else
+                trace_ops.func = function_trace_call;
+
         register_ftrace_function(&trace_ops);
         if (tracer_enabled)
                 ftrace_function_enabled = 1;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 9911277b268b..cc14a6bc1094 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -416,8 +416,57 @@ enum trace_iterator_flags {
         TRACE_ITER_STACKTRACE           = 0x100,
         TRACE_ITER_SCHED_TREE           = 0x200,
         TRACE_ITER_PRINTK               = 0x400,
+        TRACE_ITER_PREEMPTONLY          = 0x800,
 };
 
 extern struct tracer nop_trace;
 
+/**
+ * ftrace_preempt_disable - disable preemption scheduler safe
+ *
+ * When tracing can happen inside the scheduler, there exists
+ * cases that the tracing might happen before the need_resched
+ * flag is checked. If this happens and the tracer calls
+ * preempt_enable (after a disable), a schedule might take place
+ * causing an infinite recursion.
+ *
+ * To prevent this, we read the need_recshed flag before
+ * disabling preemption. When we want to enable preemption we
+ * check the flag, if it is set, then we call preempt_enable_no_resched.
+ * Otherwise, we call preempt_enable.
+ *
+ * The rational for doing the above is that if need resched is set
+ * and we have yet to reschedule, we are either in an atomic location
+ * (where we do not need to check for scheduling) or we are inside
+ * the scheduler and do not want to resched.
+ */
+static inline int ftrace_preempt_disable(void)
+{
+        int resched;
+
+        resched = need_resched();
+        preempt_disable_notrace();
+
+        return resched;
+}
+
+/**
+ * ftrace_preempt_enable - enable preemption scheduler safe
+ * @resched: the return value from ftrace_preempt_disable
+ *
+ * This is a scheduler safe way to enable preemption and not miss
+ * any preemption checks. The disabled saved the state of preemption.
+ * If resched is set, then we were either inside an atomic or
+ * are inside the scheduler (we would have already scheduled
+ * otherwise). In this case, we do not want to call normal
+ * preempt_enable, but preempt_enable_no_resched instead.
+ */
+static inline void ftrace_preempt_enable(int resched)
+{
+        if (resched)
+                preempt_enable_no_resched_notrace();
+        else
+                preempt_enable_notrace();
+}
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 3ae93f16b565..7bc4abf6fca8 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -50,8 +50,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
                 return;
 
         pc = preempt_count();
-        resched = need_resched();
-        preempt_disable_notrace();
+        resched = ftrace_preempt_disable();
 
         cpu = raw_smp_processor_id();
         data = tr->data[cpu];
@@ -81,15 +80,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
  out:
         atomic_dec(&data->disabled);
 
-        /*
-         * To prevent recursion from the scheduler, if the
-         * resched flag was set before we entered, then
-         * don't reschedule.
-         */
-        if (resched)
-                preempt_enable_no_resched_notrace();
-        else
-                preempt_enable_notrace();
+        ftrace_preempt_enable(resched);
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index be682b62fe58..d39e8b7de6a2 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -107,8 +107,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
         if (unlikely(!ftrace_enabled || stack_trace_disabled))
                 return;
 
-        resched = need_resched();
-        preempt_disable_notrace();
+        resched = ftrace_preempt_disable();
 
         cpu = raw_smp_processor_id();
         /* no atomic needed, we only modify this variable by this cpu */
@@ -120,10 +119,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
  out:
         per_cpu(trace_active, cpu)--;
         /* prevent recursion in schedule */
-        if (resched)
-                preempt_enable_no_resched_notrace();
-        else
-                preempt_enable_notrace();
+        ftrace_preempt_enable(resched);
 }
 
 static struct ftrace_ops trace_ops __read_mostly =