Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6 into common/serial-rework

Conflicts:
	arch/sh/kernel/cpu/sh2/setup-sh7619.c
	arch/sh/kernel/cpu/sh2a/setup-mxg.c
	arch/sh/kernel/cpu/sh2a/setup-sh7201.c
	arch/sh/kernel/cpu/sh2a/setup-sh7203.c
	arch/sh/kernel/cpu/sh2a/setup-sh7206.c
	arch/sh/kernel/cpu/sh3/setup-sh7705.c
	arch/sh/kernel/cpu/sh3/setup-sh770x.c
	arch/sh/kernel/cpu/sh3/setup-sh7710.c
	arch/sh/kernel/cpu/sh3/setup-sh7720.c
	arch/sh/kernel/cpu/sh4/setup-sh4-202.c
	arch/sh/kernel/cpu/sh4/setup-sh7750.c
	arch/sh/kernel/cpu/sh4/setup-sh7760.c
	arch/sh/kernel/cpu/sh4a/setup-sh7343.c
	arch/sh/kernel/cpu/sh4a/setup-sh7366.c
	arch/sh/kernel/cpu/sh4a/setup-sh7722.c
	arch/sh/kernel/cpu/sh4a/setup-sh7723.c
	arch/sh/kernel/cpu/sh4a/setup-sh7724.c
	arch/sh/kernel/cpu/sh4a/setup-sh7763.c
	arch/sh/kernel/cpu/sh4a/setup-sh7770.c
	arch/sh/kernel/cpu/sh4a/setup-sh7780.c
	arch/sh/kernel/cpu/sh4a/setup-sh7785.c
	arch/sh/kernel/cpu/sh4a/setup-sh7786.c
	arch/sh/kernel/cpu/sh4a/setup-shx3.c
	arch/sh/kernel/cpu/sh5/setup-sh5.c
	drivers/serial/sh-sci.c
	drivers/serial/sh-sci.h
	include/linux/serial_sci.h

40 files changed, 9416 insertions, 5378 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 1551f47e7669..14674dce77a6 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -11,38 +11,48 @@ config NOP_TRACER
 
 config HAVE_FTRACE_NMI_ENTER
         bool
+        help
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_FUNCTION_TRACER
         bool
+        help
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_FUNCTION_GRAPH_TRACER
         bool
+        help
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_FUNCTION_GRAPH_FP_TEST
         bool
         help
-         An arch may pass in a unique value (frame pointer) to both the
-         entering and exiting of a function. On exit, the value is compared
-         and if it does not match, then it will panic the kernel.
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_FUNCTION_TRACE_MCOUNT_TEST
         bool
         help
-         This gets selected when the arch tests the function_trace_stop
-         variable at the mcount call site. Otherwise, this variable
-         is tested by the called function.
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_DYNAMIC_FTRACE
         bool
+        help
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_FTRACE_MCOUNT_RECORD
         bool
+        help
+          See Documentation/trace/ftrace-design.txt
 
-config HAVE_HW_BRANCH_TRACER
+config HAVE_SYSCALL_TRACEPOINTS
         bool
+        help
+          See Documentation/trace/ftrace-design.txt
 
-config HAVE_FTRACE_SYSCALLS
+config HAVE_C_RECORDMCOUNT
         bool
+        help
+          C version of recordmcount available?
 
 config TRACER_MAX_TRACE
         bool
@@ -59,16 +69,36 @@ config EVENT_TRACING
         select CONTEXT_SWITCH_TRACER
         bool
 
+config EVENT_POWER_TRACING_DEPRECATED
+        depends on EVENT_TRACING
+        bool "Deprecated power event trace API, to be removed"
+        default y
+        help
+          Provides old power event types:
+          C-state/idle accounting events:
+          power:power_start
+          power:power_end
+          and old cpufreq accounting event:
+          power:power_frequency
+          This is for userspace compatibility
+          and will vanish after 5 kernel iterations,
+          namely 2.6.41.
+
 config CONTEXT_SWITCH_TRACER
-        select MARKERS
         bool
 
+config RING_BUFFER_ALLOW_SWAP
+        bool
+        help
+         Allow the use of ring_buffer_swap_cpu.
+         Adds a very slight overhead to tracing when enabled.
+
 # All tracer options should select GENERIC_TRACER. For those options that are
 # enabled by all tracers (context switch and event tracer) they select TRACING.
 # This allows those options to appear when no other tracer is selected. But the
 # options do not appear when something else selects it. We need the two options
 # GENERIC_TRACER and TRACING to avoid circular dependencies to accomplish the
-# hidding of the automatic options options.
+# hiding of the automatic options.
 
 config TRACING
         bool
@@ -104,21 +134,21 @@ menuconfig FTRACE
         bool "Tracers"
         default y if DEBUG_KERNEL
         help
-         Enable the kernel tracing infrastructure.
+          Enable the kernel tracing infrastructure.
 
 if FTRACE
 
 config FUNCTION_TRACER
         bool "Kernel Function Tracer"
         depends on HAVE_FUNCTION_TRACER
-        select FRAME_POINTER
+        select FRAME_POINTER if !ARM_UNWIND && !S390
         select KALLSYMS
         select GENERIC_TRACER
         select CONTEXT_SWITCH_TRACER
         help
           Enable the kernel to trace every kernel function. This is done
           by using a compiler feature to insert a small, 5-byte No-Operation
-          instruction to the beginning of every kernel function, which NOP
+          instruction at the beginning of every kernel function, which NOP
           sequence is then dynamically patched into a tracer call when
           tracing is enabled by the administrator. If it's runtime disabled
           (the bootup default), then the overhead of the instructions is very
@@ -135,7 +165,7 @@ config FUNCTION_GRAPH_TRACER
           and its entry.
           Its first purpose is to trace the duration of functions and
           draw a call graph for each thread with some information like
-          the return value. This is done by setting the current return 
+          the return value. This is done by setting the current return
           address on the current task structure into a stack of calls.
 
 
@@ -143,10 +173,11 @@ config IRQSOFF_TRACER
         bool "Interrupts-off Latency Tracer"
         default n
         depends on TRACE_IRQFLAGS_SUPPORT
-        depends on GENERIC_TIME
+        depends on !ARCH_USES_GETTIMEOFFSET
         select TRACE_IRQFLAGS
         select GENERIC_TRACER
         select TRACER_MAX_TRACE
+        select RING_BUFFER_ALLOW_SWAP
         help
           This option measures the time spent in irqs-off critical
           sections, with microsecond accuracy.
@@ -157,19 +188,20 @@ config IRQSOFF_TRACER
 
               echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
 
-          (Note that kernel size and overhead increases with this option
+          (Note that kernel size and overhead increase with this option
           enabled. This option and the preempt-off timing option can be
           used together or separately.)
 
 config PREEMPT_TRACER
         bool "Preemption-off Latency Tracer"
         default n
-        depends on GENERIC_TIME
+        depends on !ARCH_USES_GETTIMEOFFSET
         depends on PREEMPT
         select GENERIC_TRACER
         select TRACER_MAX_TRACE
+        select RING_BUFFER_ALLOW_SWAP
         help
-          This option measures the time spent in preemption off critical
+          This option measures the time spent in preemption-off critical
           sections, with microsecond accuracy.
 
           The default measurement method is a maximum search, which is
@@ -178,19 +210,10 @@ config PREEMPT_TRACER
 
               echo 0 > /sys/kernel/debug/tracing/tracing_max_latency
 
-          (Note that kernel size and overhead increases with this option
+          (Note that kernel size and overhead increase with this option
           enabled. This option and the irqs-off timing option can be
           used together or separately.)
 
-config SYSPROF_TRACER
-        bool "Sysprof Tracer"
-        depends on X86
-        select GENERIC_TRACER
-        select CONTEXT_SWITCH_TRACER
-        help
-          This tracer provides the trace needed by the 'Sysprof' userspace
-          tool.
-
 config SCHED_TRACER
         bool "Scheduling Latency Tracer"
         select GENERIC_TRACER
@@ -205,35 +228,18 @@ config ENABLE_DEFAULT_TRACERS
         depends on !GENERIC_TRACER
         select TRACING
         help
-          This tracer hooks to various trace points in the kernel
+          This tracer hooks to various trace points in the kernel,
           allowing the user to pick and choose which trace point they
           want to trace. It also includes the sched_switch tracer plugin.
 
 config FTRACE_SYSCALLS
         bool "Trace syscalls"
-        depends on HAVE_FTRACE_SYSCALLS
+        depends on HAVE_SYSCALL_TRACEPOINTS
         select GENERIC_TRACER
         select KALLSYMS
         help
           Basic tracer to catch the syscall entry and exit events.
 
-config BOOT_TRACER
-        bool "Trace boot initcalls"
-        select GENERIC_TRACER
-        select CONTEXT_SWITCH_TRACER
-        help
-          This tracer helps developers to optimize boot times: it records
-          the timings of the initcalls and traces key events and the identity
-          of tasks that can cause boot delays, such as context-switches.
-
-          Its aim is to be parsed by the /scripts/bootgraph.pl tool to
-          produce pretty graphics about boot inefficiencies, giving a visual
-          representation of the delays during initcalls - but the raw
-          /debug/tracing/trace text output is readable too.
-
-          You must pass in ftrace=initcall to the kernel command line
-          to enable this on bootup.
-
 config TRACE_BRANCH_PROFILING
         bool
         select GENERIC_TRACER
@@ -248,19 +254,19 @@ choice
          The likely/unlikely profiler only looks at the conditions that
          are annotated with a likely or unlikely macro.
 
-         The "all branch" profiler will profile every if statement in the
+         The "all branch" profiler will profile every if-statement in the
          kernel. This profiler will also enable the likely/unlikely
-         profiler as well.
+         profiler.
 
-         Either of the above profilers add a bit of overhead to the system.
-         If unsure choose "No branch profiling".
+         Either of the above profilers adds a bit of overhead to the system.
+         If unsure, choose "No branch profiling".
 
 config BRANCH_PROFILE_NONE
         bool "No branch profiling"
         help
-         No branch profiling. Branch profiling adds a bit of overhead.
-         Only enable it if you want to analyse the branching behavior.
-         Otherwise keep it disabled.
+          No branch profiling. Branch profiling adds a bit of overhead.
+          Only enable it if you want to analyse the branching behavior.
+          Otherwise keep it disabled.
 
 config PROFILE_ANNOTATED_BRANCHES
         bool "Trace likely/unlikely profiler"
@@ -271,7 +277,7 @@ config PROFILE_ANNOTATED_BRANCHES
 
           /sys/kernel/debug/tracing/profile_annotated_branch
 
-          Note: this will add a significant overhead, only turn this
+          Note: this will add a significant overhead; only turn this
           on if you need to profile the system's use of these macros.
 
 config PROFILE_ALL_BRANCHES
@@ -288,7 +294,7 @@ config PROFILE_ALL_BRANCHES
 
           This configuration, when enabled, will impose a great overhead
           on the system. This should only be enabled when the system
-          is to be analyzed
+          is to be analyzed in much detail.
 endchoice
 
 config TRACING_BRANCHES
@@ -313,16 +319,6 @@ config BRANCH_TRACER
 
           Say N if unsure.
 
-config POWER_TRACER
-        bool "Trace power consumption behavior"
-        depends on X86
-        select GENERIC_TRACER
-        help
-          This tracer helps developers to analyze and optimize the kernels
-          power management decisions, specifically the C-state and P-state
-          behavior.
-
-
 config STACK_TRACER
         bool "Trace max stack"
         depends on HAVE_FUNCTION_TRACER
@@ -347,47 +343,8 @@ config STACK_TRACER
 
           Say N if unsure.
 
-config HW_BRANCH_TRACER
-        depends on HAVE_HW_BRANCH_TRACER
-        bool "Trace hw branches"
-        select GENERIC_TRACER
-        help
-          This tracer records all branches on the system in a circular
-          buffer giving access to the last N branches for each cpu.
-
-config KMEMTRACE
-        bool "Trace SLAB allocations"
-        select GENERIC_TRACER
-        help
-          kmemtrace provides tracing for slab allocator functions, such as
-          kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected
-          data is then fed to the userspace application in order to analyse
-          allocation hotspots, internal fragmentation and so on, making it
-          possible to see how well an allocator performs, as well as debug
-          and profile kernel code.
-
-          This requires an userspace application to use. See
-          Documentation/trace/kmemtrace.txt for more information.
-
-          Saying Y will make the kernel somewhat larger and slower. However,
-          if you disable kmemtrace at run-time or boot-time, the performance
-          impact is minimal (depending on the arch the kernel is built for).
-
-          If unsure, say N.
-
-config WORKQUEUE_TRACER
-        bool "Trace workqueues"
-        select GENERIC_TRACER
-        help
-          The workqueue tracer provides some statistical informations
-          about each cpu workqueue thread such as the number of the
-          works inserted and executed since their creation. It can help
-          to evaluate the amount of work each of them have to perform.
-          For example it can help a developer to decide whether he should
-          choose a per cpu workqueue instead of a singlethreaded one.
-
 config BLK_DEV_IO_TRACE
-        bool "Support for tracing block io actions"
+        bool "Support for tracing block IO actions"
         depends on SYSFS
         depends on BLOCK
         select RELAY
@@ -411,38 +368,55 @@ config BLK_DEV_IO_TRACE
 
           If unsure, say N.
 
+config KPROBE_EVENT
+        depends on KPROBES
+        depends on HAVE_REGS_AND_STACK_ACCESS_API
+        bool "Enable kprobes-based dynamic events"
+        select TRACING
+        default y
+        help
+          This allows the user to add tracing events (similar to tracepoints)
+          on the fly via the ftrace interface. See
+          Documentation/trace/kprobetrace.txt for more details.
+
+          Those events can be inserted wherever kprobes can probe, and record
+          various register and memory values.
+
+          This option is also required by perf-probe subcommand of perf tools.
+          If you want to use perf tools, this option is strongly recommended.
+
 config DYNAMIC_FTRACE
         bool "enable/disable ftrace tracepoints dynamically"
         depends on FUNCTION_TRACER
         depends on HAVE_DYNAMIC_FTRACE
         default y
         help
-         This option will modify all the calls to ftrace dynamically
-         (will patch them out of the binary image and replaces them
-         with a No-Op instruction) as they are called. A table is
-         created to dynamically enable them again.
+          This option will modify all the calls to ftrace dynamically
+          (will patch them out of the binary image and replace them
+          with a No-Op instruction) as they are called. A table is
+          created to dynamically enable them again.
 
-         This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but otherwise
-         has native performance as long as no tracing is active.
+          This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
+          otherwise has native performance as long as no tracing is active.
 
-         The changes to the code are done by a kernel thread that
-         wakes up once a second and checks to see if any ftrace calls
-         were made. If so, it runs stop_machine (stops all CPUS)
-         and modifies the code to jump over the call to ftrace.
+          The changes to the code are done by a kernel thread that
+          wakes up once a second and checks to see if any ftrace calls
+          were made. If so, it runs stop_machine (stops all CPUS)
+          and modifies the code to jump over the call to ftrace.
 
 config FUNCTION_PROFILER
         bool "Kernel function profiler"
         depends on FUNCTION_TRACER
         default n
         help
-         This option enables the kernel function profiler. A file is created
-         in debugfs called function_profile_enabled which defaults to zero.
-         When a 1 is echoed into this file profiling begins, and when a
-         zero is entered, profiling stops. A file in the trace_stats
-         directory called functions, that show the list of functions that
-         have been hit and their counters.
+          This option enables the kernel function profiler. A file is created
+          in debugfs called function_profile_enabled which defaults to zero.
+          When a 1 is echoed into this file profiling begins, and when a
+          zero is entered, profiling stops. A "functions" file is created in
+          the trace_stats directory; this file shows the list of functions that
+          have been hit and their counters.
 
-         If in doubt, say N
+          If in doubt, say N.
 
 config FTRACE_MCOUNT_RECORD
         def_bool y
@@ -462,6 +436,18 @@ config FTRACE_STARTUP_TEST
           functioning properly. It will do tests on all the configured
           tracers of ftrace.
 
+config EVENT_TRACE_TEST_SYSCALLS
+        bool "Run selftest on syscall events"
+        depends on FTRACE_STARTUP_TEST
+        help
+         This option will also enable testing every syscall event.
+         It only enables the event and disables it and runs various loads
+         with the event enabled. This adds a bit more time for kernel boot
+         up since it runs this on every system call defined.
+
+         TBD - enable a way to actually call the syscalls as we test their
+               events
+
 config MMIOTRACE
         bool "Memory mapped IO tracing"
         depends on HAVE_MMIOTRACE_SUPPORT && PCI
@@ -489,8 +475,8 @@ config RING_BUFFER_BENCHMARK
         tristate "Ring buffer benchmark stress tester"
         depends on RING_BUFFER
         help
-          This option creates a test to stress the ring buffer and bench mark it.
-          It creates its own ring buffer such that it will not interfer with
+          This option creates a test to stress the ring buffer and benchmark it.
+          It creates its own ring buffer such that it will not interfere with
           any other users of the ring buffer (such as ftrace). It then creates
           a producer and consumer that will run for 10 seconds and sleep for
           10 seconds. Each interval it will print out the number of events
@@ -499,7 +485,7 @@ config RING_BUFFER_BENCHMARK
           It does not disable interrupts or raise its priority, so it may be
           affected by processes that are running.
 
-          If unsure, say N
+          If unsure, say N.
 
 endif # FTRACE
 
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 844164dca90a..761c510a06c5 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -30,7 +30,6 @@ obj-$(CONFIG_TRACING) += trace_output.o
 obj-$(CONFIG_TRACING) += trace_stat.o
 obj-$(CONFIG_TRACING) += trace_printk.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
-obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
 obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
@@ -38,12 +37,8 @@ obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
 obj-$(CONFIG_NOP_TRACER) += trace_nop.o
 obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
-obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
-obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
-obj-$(CONFIG_POWER_TRACER) += trace_power.o
-obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
 obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
 obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
 ifeq ($(CONFIG_BLOCK),y)
@@ -52,7 +47,14 @@ endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events.o
 obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
-obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
+ifeq ($(CONFIG_PERF_EVENTS),y)
+obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
+endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_TRACEPOINTS) += power-traces.o
+ifeq ($(CONFIG_TRACING),y)
+obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
+endif
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 39af8af6fc30..7b8ec0281548 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -21,6 +21,7 @@
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/debugfs.h>
 #include <linux/time.h>
 #include <linux/uaccess.h>
@@ -64,13 +65,15 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 {
         struct blk_io_trace *t;
         struct ring_buffer_event *event = NULL;
+        struct ring_buffer *buffer = NULL;
         int pc = 0;
         int cpu = smp_processor_id();
         bool blk_tracer = blk_tracer_enabled;
 
         if (blk_tracer) {
+                buffer = blk_tr->buffer;
                 pc = preempt_count();
-                event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+                event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
                                                   sizeof(*t) + len,
                                                   0, pc);
                 if (!event)
@@ -95,7 +98,7 @@ record_it:
                 memcpy((void *) t + sizeof(*t), data, len);
 
                 if (blk_tracer)
-                        trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+                        trace_buffer_unlock_commit(buffer, event, 0, pc);
         }
 }
 
@@ -165,9 +168,11 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
 static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
                                  BLK_TC_ACT(BLK_TC_WRITE) };
 
+#define BLK_TC_RAHEAD           BLK_TC_AHEAD
+
 /* The ilog2() calls fall out because they're constant */
-#define MASK_TC_BIT(rw, __name) ((rw & (1 << BIO_RW_ ## __name)) << \
-          (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - BIO_RW_ ## __name))
+#define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \
+          (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name))
 
 /*
  * The worker for the various blk_add_trace*() types. Fills out a
@@ -178,6 +183,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 {
         struct task_struct *tsk = current;
         struct ring_buffer_event *event = NULL;
+        struct ring_buffer *buffer = NULL;
         struct blk_io_trace *t;
         unsigned long flags = 0;
         unsigned long *sequence;
@@ -189,9 +195,8 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
                 return;
 
         what |= ddir_act[rw & WRITE];
-        what |= MASK_TC_BIT(rw, BARRIER);
-        what |= MASK_TC_BIT(rw, SYNCIO);
-        what |= MASK_TC_BIT(rw, AHEAD);
+        what |= MASK_TC_BIT(rw, SYNC);
+        what |= MASK_TC_BIT(rw, RAHEAD);
         what |= MASK_TC_BIT(rw, META);
         what |= MASK_TC_BIT(rw, DISCARD);
 
@@ -203,8 +208,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
         if (blk_tracer) {
                 tracing_record_cmdline(current);
 
+                buffer = blk_tr->buffer;
                 pc = preempt_count();
-                event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+                event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
                                                   sizeof(*t) + pdu_len,
                                                   0, pc);
                 if (!event)
@@ -251,7 +257,7 @@ record_it:
                         memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
 
                 if (blk_tracer) {
-                        trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+                        trace_buffer_unlock_commit(buffer, event, 0, pc);
                         return;
                 }
         }
@@ -266,8 +272,8 @@ static void blk_trace_free(struct blk_trace *bt)
 {
         debugfs_remove(bt->msg_file);
         debugfs_remove(bt->dropped_file);
-        debugfs_remove(bt->dir);
         relay_close(bt->rchan);
+        debugfs_remove(bt->dir);
         free_percpu(bt->sequence);
         free_percpu(bt->msg_data);
         kfree(bt);
@@ -317,6 +323,7 @@ static const struct file_operations blk_dropped_fops = {
         .owner =        THIS_MODULE,
         .open =         blk_dropped_open,
         .read =         blk_dropped_read,
+        .llseek =       default_llseek,
 };
 
 static int blk_msg_open(struct inode *inode, struct file *filp)
@@ -356,6 +363,7 @@ static const struct file_operations blk_msg_fops = {
         .owner =        THIS_MODULE,
         .open =         blk_msg_open,
         .write =        blk_msg_write,
+        .llseek =       noop_llseek,
 };
 
 /*
@@ -377,18 +385,8 @@ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
 
 static int blk_remove_buf_file_callback(struct dentry *dentry)
 {
-        struct dentry *parent = dentry->d_parent;
         debugfs_remove(dentry);
 
-        /*
-        * this will fail for all but the last file, but that is ok. what we
-        * care about is the top level buts->name directory going away, when
-        * the last trace file is gone. Then we don't have to rmdir() that
-        * manually on trace stop, so it nicely solves the issue with
-        * force killing of running traces.
-        */
-
-        debugfs_remove(parent);
         return 0;
 }
 
@@ -545,13 +543,49 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
         if (ret)
                 return ret;
 
-        if (copy_to_user(arg, &buts, sizeof(buts)))
+        if (copy_to_user(arg, &buts, sizeof(buts))) {
+                blk_trace_remove(q);
                 return -EFAULT;
-
+        }
         return 0;
 }
 EXPORT_SYMBOL_GPL(blk_trace_setup);
 
+#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
+static int compat_blk_trace_setup(struct request_queue *q, char *name,
+                                  dev_t dev, struct block_device *bdev,
+                                  char __user *arg)
+{
+        struct blk_user_trace_setup buts;
+        struct compat_blk_user_trace_setup cbuts;
+        int ret;
+
+        if (copy_from_user(&cbuts, arg, sizeof(cbuts)))
+                return -EFAULT;
+
+        buts = (struct blk_user_trace_setup) {
+                .act_mask = cbuts.act_mask,
+                .buf_size = cbuts.buf_size,
+                .buf_nr = cbuts.buf_nr,
+                .start_lba = cbuts.start_lba,
+                .end_lba = cbuts.end_lba,
+                .pid = cbuts.pid,
+        };
+        memcpy(&buts.name, &cbuts.name, 32);
+
+        ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
+        if (ret)
+                return ret;
+
+        if (copy_to_user(arg, &buts.name, 32)) {
+                blk_trace_remove(q);
+                return -EFAULT;
+        }
+
+        return 0;
+}
+#endif
+
 int blk_trace_startstop(struct request_queue *q, int start)
 {
         int ret;
@@ -611,6 +645,12 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
                 bdevname(bdev, b);
                 ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
                 break;
+#if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
+        case BLKTRACESETUP32:
+                bdevname(bdev, b);
+                ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
+                break;
+#endif
         case BLKTRACESTART:
                 start = 1;
         case BLKTRACESTOP:
@@ -664,10 +704,13 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
         if (likely(!bt))
                 return;
 
-        if (blk_discard_rq(rq))
-                rw |= (1 << BIO_RW_DISCARD);
+        if (rq->cmd_flags & REQ_DISCARD)
+                rw |= REQ_DISCARD;
+
+        if (rq->cmd_flags & REQ_SECURE)
+                rw |= REQ_SECURE;
 
-        if (blk_pc_request(rq)) {
+        if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
                 what |= BLK_TC_ACT(BLK_TC_PC);
                 __blk_add_trace(bt, 0, blk_rq_bytes(rq), rw,
                                 what, rq->errors, rq->cmd_len, rq->cmd);
@@ -678,28 +721,33 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
         }
 }
 
-static void blk_add_trace_rq_abort(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_abort(void *ignore,
+                                   struct request_queue *q, struct request *rq)
 {
         blk_add_trace_rq(q, rq, BLK_TA_ABORT);
 }
 
-static void blk_add_trace_rq_insert(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_insert(void *ignore,
+                                    struct request_queue *q, struct request *rq)
 {
         blk_add_trace_rq(q, rq, BLK_TA_INSERT);
 }
 
-static void blk_add_trace_rq_issue(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_issue(void *ignore,
+                                   struct request_queue *q, struct request *rq)
 {
         blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
 }
 
-static void blk_add_trace_rq_requeue(struct request_queue *q,
+static void blk_add_trace_rq_requeue(void *ignore,
+                                     struct request_queue *q,
                                      struct request *rq)
 {
         blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
 }
 
-static void blk_add_trace_rq_complete(struct request_queue *q,
+static void blk_add_trace_rq_complete(void *ignore,
+                                      struct request_queue *q,
                                       struct request *rq)
 {
         blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
@@ -727,34 +775,40 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
                         !bio_flagged(bio, BIO_UPTODATE), 0, NULL);
 }
 
-static void blk_add_trace_bio_bounce(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_bounce(void *ignore,
+                                     struct request_queue *q, struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_BOUNCE);
 }
 
-static void blk_add_trace_bio_complete(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_complete(void *ignore,
+                                       struct request_queue *q, struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_COMPLETE);
 }
 
-static void blk_add_trace_bio_backmerge(struct request_queue *q,
+static void blk_add_trace_bio_backmerge(void *ignore,
+                                        struct request_queue *q,
                                         struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
 }
 
-static void blk_add_trace_bio_frontmerge(struct request_queue *q,
+static void blk_add_trace_bio_frontmerge(void *ignore,
+                                         struct request_queue *q,
                                          struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
 }
 
-static void blk_add_trace_bio_queue(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_queue(void *ignore,
+                                    struct request_queue *q, struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
 }
 
-static void blk_add_trace_getrq(struct request_queue *q,
+static void blk_add_trace_getrq(void *ignore,
+                                struct request_queue *q,
                                 struct bio *bio, int rw)
 {
         if (bio)
@@ -768,7 +822,8 @@ static void blk_add_trace_getrq(struct request_queue *q,
 }
 
 
-static void blk_add_trace_sleeprq(struct request_queue *q,
+static void blk_add_trace_sleeprq(void *ignore,
+                                  struct request_queue *q,
                                   struct bio *bio, int rw)
 {
         if (bio)
@@ -782,7 +837,7 @@ static void blk_add_trace_sleeprq(struct request_queue *q,
         }
 }
 
-static void blk_add_trace_plug(struct request_queue *q)
+static void blk_add_trace_plug(void *ignore, struct request_queue *q)
 {
         struct blk_trace *bt = q->blk_trace;
 
@@ -790,7 +845,7 @@ static void blk_add_trace_plug(struct request_queue *q)
                 __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
 }
 
-static void blk_add_trace_unplug_io(struct request_queue *q)
+static void blk_add_trace_unplug_io(void *ignore, struct request_queue *q)
 {
         struct blk_trace *bt = q->blk_trace;
 
@@ -803,7 +858,7 @@ static void blk_add_trace_unplug_io(struct request_queue *q)
         }
 }
 
-static void blk_add_trace_unplug_timer(struct request_queue *q)
+static void blk_add_trace_unplug_timer(void *ignore, struct request_queue *q)
 {
         struct blk_trace *bt = q->blk_trace;
 
@@ -816,7 +871,8 @@ static void blk_add_trace_unplug_timer(struct request_queue *q)
         }
 }
 
-static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
+static void blk_add_trace_split(void *ignore,
+                                struct request_queue *q, struct bio *bio,
                                 unsigned int pdu)
 {
         struct blk_trace *bt = q->blk_trace;
@@ -832,6 +888,7 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
 
 /**
  * blk_add_trace_remap - Add a trace for a remap operation
+ * @ignore:     trace callback data parameter (not used)
  * @q:          queue the io is for
  * @bio:        the source bio
  * @dev:        target device
@@ -842,8 +899,9 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
  *     it spans a stripe (or similar). Add a trace for that action.
  *
  **/
-static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
-                                       dev_t dev, sector_t from)
+static void blk_add_trace_remap(void *ignore,
+                                struct request_queue *q, struct bio *bio,
+                                dev_t dev, sector_t from)
 {
         struct blk_trace *bt = q->blk_trace;
         struct blk_io_trace_remap r;
@@ -861,6 +919,39 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
 }
 
 /**
+ * blk_add_trace_rq_remap - Add a trace for a request-remap operation
+ * @ignore:     trace callback data parameter (not used)
+ * @q:          queue the io is for
+ * @rq:         the source request
+ * @dev:        target device
+ * @from:       source sector
+ *
+ * Description:
+ *     Device mapper remaps request to other devices.
+ *     Add a trace for that action.
+ *
+ **/
+static void blk_add_trace_rq_remap(void *ignore,
+                                   struct request_queue *q,
+                                   struct request *rq, dev_t dev,
+                                   sector_t from)
+{
+        struct blk_trace *bt = q->blk_trace;
+        struct blk_io_trace_remap r;
+
+        if (likely(!bt))
+                return;
+
+        r.device_from = cpu_to_be32(dev);
+        r.device_to   = cpu_to_be32(disk_devt(rq->rq_disk));
+        r.sector_from = cpu_to_be64(from);
+
+        __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+                        rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors,
+                        sizeof(r), &r);
+}
+
+/**
  * blk_add_driver_data - Add binary message with driver-specific data
  * @q:          queue the io is for
  * @rq:         io request
@@ -880,7 +971,7 @@ void blk_add_driver_data(struct request_queue *q,
         if (likely(!bt))
                 return;
 
-        if (blk_pc_request(rq))
+        if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
                 __blk_add_trace(bt, 0, blk_rq_bytes(rq), 0,
                                 BLK_TA_DRV_DATA, rq->errors, len, data);
         else
@@ -893,61 +984,64 @@ static void blk_register_tracepoints(void)
 {
         int ret;
 
-        ret = register_trace_block_rq_abort(blk_add_trace_rq_abort);
+        ret = register_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
+        WARN_ON(ret);
+        ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_rq_insert(blk_add_trace_rq_insert);
+        ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_rq_issue(blk_add_trace_rq_issue);
+        ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue);
+        ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_rq_complete(blk_add_trace_rq_complete);
+        ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce);
+        ret = register_trace_block_bio_complete(blk_add_trace_bio_complete, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_bio_complete(blk_add_trace_bio_complete);
+        ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
+        ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
+        ret = register_trace_block_bio_queue(blk_add_trace_bio_queue, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_bio_queue(blk_add_trace_bio_queue);
+        ret = register_trace_block_getrq(blk_add_trace_getrq, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_getrq(blk_add_trace_getrq);
+        ret = register_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_sleeprq(blk_add_trace_sleeprq);
+        ret = register_trace_block_plug(blk_add_trace_plug, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_plug(blk_add_trace_plug);
+        ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer);
+        ret = register_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_unplug_io(blk_add_trace_unplug_io);
+        ret = register_trace_block_split(blk_add_trace_split, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_split(blk_add_trace_split);
+        ret = register_trace_block_remap(blk_add_trace_remap, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_remap(blk_add_trace_remap);
+        ret = register_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
         WARN_ON(ret);
 }
 
 static void blk_unregister_tracepoints(void)
 {
-        unregister_trace_block_remap(blk_add_trace_remap);
-        unregister_trace_block_split(blk_add_trace_split);
-        unregister_trace_block_unplug_io(blk_add_trace_unplug_io);
-        unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer);
-        unregister_trace_block_plug(blk_add_trace_plug);
-        unregister_trace_block_sleeprq(blk_add_trace_sleeprq);
-        unregister_trace_block_getrq(blk_add_trace_getrq);
-        unregister_trace_block_bio_queue(blk_add_trace_bio_queue);
-        unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
-        unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
-        unregister_trace_block_bio_complete(blk_add_trace_bio_complete);
-        unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce);
-        unregister_trace_block_rq_complete(blk_add_trace_rq_complete);
-        unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue);
-        unregister_trace_block_rq_issue(blk_add_trace_rq_issue);
-        unregister_trace_block_rq_insert(blk_add_trace_rq_insert);
-        unregister_trace_block_rq_abort(blk_add_trace_rq_abort);
+        unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
+        unregister_trace_block_remap(blk_add_trace_remap, NULL);
+        unregister_trace_block_split(blk_add_trace_split, NULL);
+        unregister_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
+        unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
+        unregister_trace_block_plug(blk_add_trace_plug, NULL);
+        unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
+        unregister_trace_block_getrq(blk_add_trace_getrq, NULL);
+        unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL);
+        unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL);
+        unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL);
+        unregister_trace_block_bio_complete(blk_add_trace_bio_complete, NULL);
+        unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
+        unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
+        unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
+        unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
+        unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
+        unregister_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
 
         tracepoint_synchronize_unregister();
 }
@@ -1290,7 +1384,7 @@ out:
 }
 
 static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
-                                               int flags)
+                                               int flags, struct trace_event *event)
 {
         return print_one_line(iter, false);
 }
@@ -1312,7 +1406,8 @@ static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
 }
 
 static enum print_line_t
-blk_trace_event_print_binary(struct trace_iterator *iter, int flags)
+blk_trace_event_print_binary(struct trace_iterator *iter, int flags,
+                             struct trace_event *event)
 {
         return blk_trace_synthesize_old_trace(iter) ?
                         TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
@@ -1350,12 +1445,16 @@ static struct tracer blk_tracer __read_mostly = {
         .set_flag       = blk_tracer_set_flag,
 };
 
-static struct trace_event trace_blk_event = {
-        .type           = TRACE_BLK,
+static struct trace_event_functions trace_blk_event_funcs = {
         .trace          = blk_trace_event_print,
         .binary         = blk_trace_event_print_binary,
 };
 
+static struct trace_event trace_blk_event = {
+        .type           = TRACE_BLK,
+        .funcs          = &trace_blk_event_funcs,
+};
+
 static int __init init_blk_tracer(void)
 {
         if (!register_ftrace_event(&trace_blk_event)) {
@@ -1550,10 +1649,9 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
         struct block_device *bdev;
         ssize_t ret = -ENXIO;
 
-        lock_kernel();
         bdev = bdget(part_devt(p));
         if (bdev == NULL)
-                goto out_unlock_kernel;
+                goto out;
 
         q = blk_trace_get_queue(bdev);
         if (q == NULL)
@@ -1581,8 +1679,7 @@ out_unlock_bdev:
         mutex_unlock(&bdev->bd_mutex);
 out_bdput:
         bdput(bdev);
-out_unlock_kernel:
-        unlock_kernel();
+out:
         return ret;
 }
 
@@ -1612,11 +1709,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 
         ret = -ENXIO;
 
-        lock_kernel();
         p = dev_to_part(dev);
         bdev = bdget(part_devt(p));
         if (bdev == NULL)
-                goto out_unlock_kernel;
+                goto out;
 
         q = blk_trace_get_queue(bdev);
         if (q == NULL)
@@ -1651,8 +1747,6 @@ out_unlock_bdev:
         mutex_unlock(&bdev->bd_mutex);
 out_bdput:
         bdput(bdev);
-out_unlock_kernel:
-        unlock_kernel();
 out:
         return ret ? ret : count;
 }
@@ -1662,6 +1756,11 @@ int blk_trace_init_sysfs(struct device *dev)
         return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
 }
 
+void blk_trace_remove_sysfs(struct device *dev)
+{
+        sysfs_remove_group(&dev->kobj, &blk_trace_attr_group);
+}
+
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
 #ifdef CONFIG_EVENT_TRACING
@@ -1672,7 +1771,7 @@ void blk_dump_cmd(char *buf, struct request *rq)
         int len = rq->cmd_len;
         unsigned char *cmd = rq->cmd;
 
-        if (!blk_pc_request(rq)) {
+        if (rq->cmd_type != REQ_TYPE_BLOCK_PC) {
                 buf[0] = '\0';
                 return;
         }
@@ -1697,21 +1796,21 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 
         if (rw & WRITE)
                 rwbs[i++] = 'W';
-        else if (rw & 1 << BIO_RW_DISCARD)
+        else if (rw & REQ_DISCARD)
                 rwbs[i++] = 'D';
         else if (bytes)
                 rwbs[i++] = 'R';
         else
                 rwbs[i++] = 'N';
 
-        if (rw & 1 << BIO_RW_AHEAD)
+        if (rw & REQ_RAHEAD)
                 rwbs[i++] = 'A';
-        if (rw & 1 << BIO_RW_BARRIER)
-                rwbs[i++] = 'B';
-        if (rw & 1 << BIO_RW_SYNCIO)
+        if (rw & REQ_SYNC)
                 rwbs[i++] = 'S';
-        if (rw & 1 << BIO_RW_META)
+        if (rw & REQ_META)
                 rwbs[i++] = 'M';
+        if (rw & REQ_SECURE)
+                rwbs[i++] = 'E';
 
         rwbs[i] = '\0';
 }
@@ -1721,8 +1820,11 @@ void blk_fill_rwbs_rq(char *rwbs, struct request *rq)
         int rw = rq->cmd_flags & 0x03;
         int bytes;
 
-        if (blk_discard_rq(rq))
-                rw |= (1 << BIO_RW_DISCARD);
+        if (rq->cmd_flags & REQ_DISCARD)
+                rw |= REQ_DISCARD;
+
+        if (rq->cmd_flags & REQ_SECURE)
+                rw |= REQ_SECURE;
 
         bytes = blk_rq_bytes(rq);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 3718d55fb4c3..f3dadae83883 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -22,12 +22,13 @@
 #include <linux/hardirq.h>
 #include <linux/kthread.h>
 #include <linux/uaccess.h>
-#include <linux/kprobes.h>
 #include <linux/ftrace.h>
 #include <linux/sysctl.h>
+#include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/hash.h>
+#include <linux/rcupdate.h>
 
 #include <trace/events/sched.h>
 
@@ -60,6 +61,13 @@ static int last_ftrace_enabled;
 /* Quick disabling of function tracer. */
 int function_trace_stop;
 
+/* List for set_ftrace_pid's pids. */
+LIST_HEAD(ftrace_pids);
+struct ftrace_pid {
+        struct list_head list;
+        struct pid *pid;
+};
+
 /*
  * ftrace_disabled is set when an anomaly is discovered.
  * ftrace_disabled is much stronger than ftrace_enabled.
@@ -78,18 +86,22 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 
+/*
+ * Traverse the ftrace_list, invoking all entries.  The reason that we
+ * can use rcu_dereference_raw() is that elements removed from this list
+ * are simply leaked, so there is no need to interact with a grace-period
+ * mechanism.  The rcu_dereference_raw() calls are needed to handle
+ * concurrent insertions into the ftrace_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
 static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 {
-        struct ftrace_ops *op = ftrace_list;
-
-        /* in case someone actually ports this to alpha! */
-        read_barrier_depends();
+        struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/
 
         while (op != &ftrace_list_end) {
-                /* silly alpha */
-                read_barrier_depends();
                 op->func(ip, parent_ip);
-                op = op->next;
+                op = rcu_dereference_raw(op->next); /*see above*/
         };
 }
 
@@ -144,8 +156,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
          * the ops->next pointer is valid before another CPU sees
          * the ops pointer included into the ftrace_list.
          */
-        smp_wmb();
-        ftrace_list = ops;
+        rcu_assign_pointer(ftrace_list, ops);
 
         if (ftrace_enabled) {
                 ftrace_func_t func;
@@ -155,7 +166,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
                 else
                         func = ftrace_list_func;
 
-                if (ftrace_pid_trace) {
+                if (!list_empty(&ftrace_pids)) {
                         set_ftrace_pid_function(func);
                         func = ftrace_pid_func;
                 }
@@ -203,7 +214,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
                 if (ftrace_list->next == &ftrace_list_end) {
                         ftrace_func_t func = ftrace_list->func;
 
-                        if (ftrace_pid_trace) {
+                        if (!list_empty(&ftrace_pids)) {
                                 set_ftrace_pid_function(func);
                                 func = ftrace_pid_func;
                         }
@@ -225,9 +236,13 @@ static void ftrace_update_pid_func(void)
         if (ftrace_trace_function == ftrace_stub)
                 return;
 
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
         func = ftrace_trace_function;
+#else
+        func = __ftrace_trace_function;
+#endif
 
-        if (ftrace_pid_trace) {
+        if (!list_empty(&ftrace_pids)) {
                 set_ftrace_pid_function(func);
                 func = ftrace_pid_func;
         } else {
@@ -249,6 +264,7 @@ struct ftrace_profile {
         unsigned long                   counter;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
         unsigned long long              time;
+        unsigned long long              time_squared;
 #endif
 };
 
@@ -291,7 +307,9 @@ function_stat_next(void *v, int idx)
         pg = (struct ftrace_profile_page *)((unsigned long)rec & PAGE_MASK);
 
  again:
-        rec++;
+        if (idx != 0)
+                rec++;
+
         if ((void *)rec >= (void *)&pg->records[pg->index]) {
                 pg = pg->next;
                 if (!pg)
@@ -349,9 +367,9 @@ static int function_stat_headers(struct seq_file *m)
 {
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
         seq_printf(m, "  Function                               "
-                   "Hit    Time            Avg\n"
+                   "Hit    Time            Avg             s^2\n"
                       "  --------                               "
-                   "---    ----            ---\n");
+                   "---    ----            ---             ---\n");
 #else
         seq_printf(m, "  Function                               Hit\n"
                       "  --------                               ---\n");
@@ -363,11 +381,19 @@ static int function_stat_show(struct seq_file *m, void *v)
 {
         struct ftrace_profile *rec = v;
         char str[KSYM_SYMBOL_LEN];
+        int ret = 0;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-        static DEFINE_MUTEX(mutex);
         static struct trace_seq s;
         unsigned long long avg;
+        unsigned long long stddev;
 #endif
+        mutex_lock(&ftrace_profile_lock);
+
+        /* we raced with function_profile_reset() */
+        if (unlikely(rec->counter == 0)) {
+                ret = -EBUSY;
+                goto out;
+        }
 
         kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
         seq_printf(m, "  %-30.30s  %10lu", str, rec->counter);
@@ -377,17 +403,31 @@ static int function_stat_show(struct seq_file *m, void *v)
         avg = rec->time;
         do_div(avg, rec->counter);
 
-        mutex_lock(&mutex);
+        /* Sample standard deviation (s^2) */
+        if (rec->counter <= 1)
+                stddev = 0;
+        else {
+                stddev = rec->time_squared - rec->counter * avg * avg;
+                /*
+                 * Divide only 1000 for ns^2 -> us^2 conversion.
+                 * trace_print_graph_duration will divide 1000 again.
+                 */
+                do_div(stddev, (rec->counter - 1) * 1000);
+        }
+
         trace_seq_init(&s);
         trace_print_graph_duration(rec->time, &s);
         trace_seq_puts(&s, "    ");
         trace_print_graph_duration(avg, &s);
+        trace_seq_puts(&s, "    ");
+        trace_print_graph_duration(stddev, &s);
         trace_print_seq(m, &s);
-        mutex_unlock(&mutex);
 #endif
         seq_putc(m, '\n');
+out:
+        mutex_unlock(&ftrace_profile_lock);
 
-        return 0;
+        return ret;
 }
 
 static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
@@ -633,6 +673,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
         if (!stat->hash || !ftrace_profile_enabled)
                 goto out;
 
+        /* If the calltime was zero'd ignore it */
+        if (!trace->calltime)
+                goto out;
+
         calltime = trace->rettime - trace->calltime;
 
         if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
@@ -651,8 +695,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
         }
 
         rec = ftrace_find_profiled_func(stat, trace->func);
-        if (rec)
+        if (rec) {
                 rec->time += calltime;
+                rec->time_squared += calltime * calltime;
+        }
 
  out:
         local_irq_restore(flags);
@@ -734,7 +780,7 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
  out:
         mutex_unlock(&ftrace_profile_lock);
 
-        filp->f_pos += cnt;
+        *ppos += cnt;
 
         return cnt;
 }
@@ -754,6 +800,7 @@ static const struct file_operations ftrace_profile_fops = {
         .open           = tracing_open_generic,
         .read           = ftrace_profile_read,
         .write          = ftrace_profile_write,
+        .llseek         = default_llseek,
 };
 
 /* used to initialize the real stat files */
@@ -766,7 +813,7 @@ static struct tracer_stat function_stats __initdata = {
         .stat_show      = function_stat_show
 };
 
-static void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 {
         struct ftrace_profile_stat *stat;
         struct dentry *entry;
@@ -784,7 +831,6 @@ static void ftrace_profile_debugfs(struct dentry *d_tracer)
                          * The files created are permanent, if something happens
                          * we still do not free memory.
                          */
-                        kfree(stat);
                         WARN(1,
                              "Could not allocate stat file for cpu %d\n",
                              cpu);
@@ -811,13 +857,11 @@ static void ftrace_profile_debugfs(struct dentry *d_tracer)
 }
 
 #else /* CONFIG_FUNCTION_PROFILER */
-static void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 {
 }
 #endif /* CONFIG_FUNCTION_PROFILER */
 
-/* set when tracing only a pid */
-struct pid *ftrace_pid_trace;
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -841,10 +885,8 @@ enum {
         FTRACE_ENABLE_CALLS             = (1 << 0),
         FTRACE_DISABLE_CALLS            = (1 << 1),
         FTRACE_UPDATE_TRACE_FUNC        = (1 << 2),
-        FTRACE_ENABLE_MCOUNT            = (1 << 3),
-        FTRACE_DISABLE_MCOUNT           = (1 << 4),
-        FTRACE_START_FUNC_RET           = (1 << 5),
-        FTRACE_STOP_FUNC_RET            = (1 << 6),
+        FTRACE_START_FUNC_RET           = (1 << 3),
+        FTRACE_STOP_FUNC_RET            = (1 << 4),
 };
 
 static int ftrace_filtered;
@@ -884,36 +926,6 @@ static struct dyn_ftrace *ftrace_free_records;
                 }                               \
         }
 
-#ifdef CONFIG_KPROBES
-
-static int frozen_record_count;
-
-static inline void freeze_record(struct dyn_ftrace *rec)
-{
-        if (!(rec->flags & FTRACE_FL_FROZEN)) {
-                rec->flags |= FTRACE_FL_FROZEN;
-                frozen_record_count++;
-        }
-}
-
-static inline void unfreeze_record(struct dyn_ftrace *rec)
-{
-        if (rec->flags & FTRACE_FL_FROZEN) {
-                rec->flags &= ~FTRACE_FL_FROZEN;
-                frozen_record_count--;
-        }
-}
-
-static inline int record_frozen(struct dyn_ftrace *rec)
-{
-        return rec->flags & FTRACE_FL_FROZEN;
-}
-#else
-# define freeze_record(rec)                     ({ 0; })
-# define unfreeze_record(rec)                   ({ 0; })
-# define record_frozen(rec)                     ({ 0; })
-#endif /* CONFIG_KPROBES */
-
 static void ftrace_free_rec(struct dyn_ftrace *rec)
 {
         rec->freelist = ftrace_free_records;
@@ -1011,75 +1023,54 @@ static void ftrace_bug(int failed, unsigned long ip)
 }
 
 
+/* Return 1 if the address range is reserved for ftrace */
+int ftrace_text_reserved(void *start, void *end)
+{
+        struct dyn_ftrace *rec;
+        struct ftrace_page *pg;
+
+        do_for_each_ftrace_rec(pg, rec) {
+                if (rec->ip <= (unsigned long)end &&
+                    rec->ip + MCOUNT_INSN_SIZE > (unsigned long)start)
+                        return 1;
+        } while_for_each_ftrace_rec();
+        return 0;
+}
+
+
 static int
 __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 {
         unsigned long ftrace_addr;
-        unsigned long ip, fl;
+        unsigned long flag = 0UL;
 
         ftrace_addr = (unsigned long)FTRACE_ADDR;
 
-        ip = rec->ip;
-
         /*
-         * If this record is not to be traced and
-         * it is not enabled then do nothing.
+         * If this record is not to be traced or we want to disable it,
+         * then disable it.
          *
-         * If this record is not to be traced and
-         * it is enabled then disable it.
+         * If we want to enable it and filtering is off, then enable it.
          *
+         * If we want to enable it and filtering is on, enable it only if
+         * it's filtered
          */
-        if (rec->flags & FTRACE_FL_NOTRACE) {
-                if (rec->flags & FTRACE_FL_ENABLED)
-                        rec->flags &= ~FTRACE_FL_ENABLED;
-                else
-                        return 0;
-
-        } else if (ftrace_filtered && enable) {
-                /*
-                 * Filtering is on:
-                 */
-
-                fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_ENABLED);
-
-                /* Record is filtered and enabled, do nothing */
-                if (fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED))
-                        return 0;
-
-                /* Record is not filtered or enabled, do nothing */
-                if (!fl)
-                        return 0;
-
-                /* Record is not filtered but enabled, disable it */
-                if (fl == FTRACE_FL_ENABLED)
-                        rec->flags &= ~FTRACE_FL_ENABLED;
-                else
-                /* Otherwise record is filtered but not enabled, enable it */
-                        rec->flags |= FTRACE_FL_ENABLED;
-        } else {
-                /* Disable or not filtered */
-
-                if (enable) {
-                        /* if record is enabled, do nothing */
-                        if (rec->flags & FTRACE_FL_ENABLED)
-                                return 0;
-
-                        rec->flags |= FTRACE_FL_ENABLED;
-
-                } else {
+        if (enable && !(rec->flags & FTRACE_FL_NOTRACE)) {
+                if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER))
+                        flag = FTRACE_FL_ENABLED;
+        }
 
-                        /* if record is not enabled, do nothing */
-                        if (!(rec->flags & FTRACE_FL_ENABLED))
-                                return 0;
+        /* If the state of this record hasn't changed, then do nothing */
+        if ((rec->flags & FTRACE_FL_ENABLED) == flag)
+                return 0;
 
-                        rec->flags &= ~FTRACE_FL_ENABLED;
-                }
+        if (flag) {
+                rec->flags |= FTRACE_FL_ENABLED;
+                return ftrace_make_call(rec, ftrace_addr);
         }
 
-        if (rec->flags & FTRACE_FL_ENABLED)
-                return ftrace_make_call(rec, ftrace_addr);
-        else
-                return ftrace_make_nop(NULL, rec, ftrace_addr);
+        rec->flags &= ~FTRACE_FL_ENABLED;
+        return ftrace_make_nop(NULL, rec, ftrace_addr);
 }
 
 static void ftrace_replace_code(int enable)
@@ -1098,25 +1089,12 @@ static void ftrace_replace_code(int enable)
                     !(rec->flags & FTRACE_FL_CONVERTED))
                         continue;
 
-                /* ignore updates to this record's mcount site */
-                if (get_kprobe((void *)rec->ip)) {
-                        freeze_record(rec);
-                        continue;
-                } else {
-                        unfreeze_record(rec);
-                }
-
                 failed = __ftrace_replace_code(rec, enable);
                 if (failed) {
                         rec->flags |= FTRACE_FL_FAILED;
-                        if ((system_state == SYSTEM_BOOTING) ||
-                            !core_kernel_text(rec->ip)) {
-                                ftrace_free_rec(rec);
-                                } else {
-                                ftrace_bug(failed, rec->ip);
-                                        /* Stop processing */
-                                        return;
-                                }
+                        ftrace_bug(failed, rec->ip);
+                        /* Stop processing */
+                        return;
                 }
         } while_for_each_ftrace_rec();
 }
@@ -1247,8 +1225,6 @@ static void ftrace_shutdown(int command)
 
 static void ftrace_startup_sysctl(void)
 {
-        int command = FTRACE_ENABLE_MCOUNT;
-
         if (unlikely(ftrace_disabled))
                 return;
 
@@ -1256,23 +1232,17 @@ static void ftrace_startup_sysctl(void)
         saved_ftrace_func = NULL;
         /* ftrace_start_up is true if we want ftrace running */
         if (ftrace_start_up)
-                command |= FTRACE_ENABLE_CALLS;
-
-        ftrace_run_update_code(command);
+                ftrace_run_update_code(FTRACE_ENABLE_CALLS);
 }
 
 static void ftrace_shutdown_sysctl(void)
 {
-        int command = FTRACE_DISABLE_MCOUNT;
-
         if (unlikely(ftrace_disabled))
                 return;
 
         /* ftrace_start_up is true if ftrace is running */
         if (ftrace_start_up)
-                command |= FTRACE_DISABLE_CALLS;
-
-        ftrace_run_update_code(command);
+                ftrace_run_update_code(FTRACE_DISABLE_CALLS);
 }
 
 static cycle_t          ftrace_update_time;
@@ -1297,12 +1267,34 @@ static int ftrace_update_code(struct module *mod)
                 ftrace_new_addrs = p->newlist;
                 p->flags = 0L;
 
-                /* convert record (i.e, patch mcount-call with NOP) */
-                if (ftrace_code_disable(mod, p)) {
-                        p->flags |= FTRACE_FL_CONVERTED;
-                        ftrace_update_cnt++;
-                } else
+                /*
+                 * Do the initial record convertion from mcount jump
+                 * to the NOP instructions.
+                 */
+                if (!ftrace_code_disable(mod, p)) {
                         ftrace_free_rec(p);
+                        continue;
+                }
+
+                p->flags |= FTRACE_FL_CONVERTED;
+                ftrace_update_cnt++;
+
+                /*
+                 * If the tracing is enabled, go ahead and enable the record.
+                 *
+                 * The reason not to enable the record immediatelly is the
+                 * inherent check of ftrace_make_nop/ftrace_make_call for
+                 * correct previous instructions.  Making first the NOP
+                 * conversion puts the module to the correct state, thus
+                 * passing the ftrace_make_call check.
+                 */
+                if (ftrace_start_up) {
+                        int failed = __ftrace_replace_code(p, 1);
+                        if (failed) {
+                                ftrace_bug(failed, p->ip);
+                                ftrace_free_rec(p);
+                        }
+                }
         }
 
         stop = ftrace_now(raw_smp_processor_id());
@@ -1358,36 +1350,38 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init)
 
 enum {
         FTRACE_ITER_FILTER      = (1 << 0),
-        FTRACE_ITER_CONT        = (1 << 1),
-        FTRACE_ITER_NOTRACE     = (1 << 2),
-        FTRACE_ITER_FAILURES    = (1 << 3),
-        FTRACE_ITER_PRINTALL    = (1 << 4),
-        FTRACE_ITER_HASH        = (1 << 5),
+        FTRACE_ITER_NOTRACE     = (1 << 1),
+        FTRACE_ITER_FAILURES    = (1 << 2),
+        FTRACE_ITER_PRINTALL    = (1 << 3),
+        FTRACE_ITER_HASH        = (1 << 4),
 };
 
 #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */
 
 struct ftrace_iterator {
-        struct ftrace_page      *pg;
-        int                     hidx;
-        int                     idx;
-        unsigned                flags;
-        unsigned char           buffer[FTRACE_BUFF_MAX+1];
-        unsigned                buffer_idx;
-        unsigned                filtered;
+        loff_t                          pos;
+        loff_t                          func_pos;
+        struct ftrace_page              *pg;
+        struct dyn_ftrace               *func;
+        struct ftrace_func_probe        *probe;
+        struct trace_parser             parser;
+        int                             hidx;
+        int                             idx;
+        unsigned                        flags;
 };
 
 static void *
-t_hash_next(struct seq_file *m, void *v, loff_t *pos)
+t_hash_next(struct seq_file *m, loff_t *pos)
 {
         struct ftrace_iterator *iter = m->private;
-        struct hlist_node *hnd = v;
+        struct hlist_node *hnd = NULL;
         struct hlist_head *hhd;
 
-        WARN_ON(!(iter->flags & FTRACE_ITER_HASH));
-
         (*pos)++;
+        iter->pos = *pos;
 
+        if (iter->probe)
+                hnd = &iter->probe->node;
  retry:
         if (iter->hidx >= FTRACE_FUNC_HASHSIZE)
                 return NULL;
@@ -1410,35 +1404,51 @@ t_hash_next(struct seq_file *m, void *v, loff_t *pos)
                 }
         }
 
-        return hnd;
+        if (WARN_ON_ONCE(!hnd))
+                return NULL;
+
+        iter->probe = hlist_entry(hnd, struct ftrace_func_probe, node);
+
+        return iter;
 }
 
 static void *t_hash_start(struct seq_file *m, loff_t *pos)
 {
         struct ftrace_iterator *iter = m->private;
         void *p = NULL;
+        loff_t l;
 
+        if (iter->func_pos > *pos)
+                return NULL;
+
+        iter->hidx = 0;
+        for (l = 0; l <= (*pos - iter->func_pos); ) {
+                p = t_hash_next(m, &l);
+                if (!p)
+                        break;
+        }
+        if (!p)
+                return NULL;
+
+        /* Only set this if we have an item */
         iter->flags |= FTRACE_ITER_HASH;
 
-        return t_hash_next(m, p, pos);
+        return iter;
 }
 
-static int t_hash_show(struct seq_file *m, void *v)
+static int
+t_hash_show(struct seq_file *m, struct ftrace_iterator *iter)
 {
         struct ftrace_func_probe *rec;
-        struct hlist_node *hnd = v;
-        char str[KSYM_SYMBOL_LEN];
 
-        rec = hlist_entry(hnd, struct ftrace_func_probe, node);
+        rec = iter->probe;
+        if (WARN_ON_ONCE(!rec))
+                return -EIO;
 
         if (rec->ops->print)
                 return rec->ops->print(m, rec->ip, rec->ops, rec->data);
 
-        kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
-        seq_printf(m, "%s:", str);
-
-        kallsyms_lookup((unsigned long)rec->ops->func, NULL, NULL, NULL, str);
-        seq_printf(m, "%s", str);
+        seq_printf(m, "%ps:%ps", (void *)rec->ip, (void *)rec->ops->func);
 
         if (rec->data)
                 seq_printf(m, ":%p", rec->data);
@@ -1454,12 +1464,13 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
         struct dyn_ftrace *rec = NULL;
 
         if (iter->flags & FTRACE_ITER_HASH)
-                return t_hash_next(m, v, pos);
+                return t_hash_next(m, pos);
 
         (*pos)++;
+        iter->pos = *pos;
 
         if (iter->flags & FTRACE_ITER_PRINTALL)
-                return NULL;
+                return t_hash_start(m, pos);
 
  retry:
         if (iter->idx >= iter->pg->index) {
@@ -1467,8 +1478,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
                         iter->pg = iter->pg->next;
                         iter->idx = 0;
                         goto retry;
-                } else {
-                        iter->idx = -1;
                 }
         } else {
                 rec = &iter->pg->records[iter->idx++];
@@ -1490,16 +1499,36 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
                 }
         }
 
-        return rec;
+        if (!rec)
+                return t_hash_start(m, pos);
+
+        iter->func_pos = *pos;
+        iter->func = rec;
+
+        return iter;
+}
+
+static void reset_iter_read(struct ftrace_iterator *iter)
+{
+        iter->pos = 0;
+        iter->func_pos = 0;
+        iter->flags &= ~(FTRACE_ITER_PRINTALL & FTRACE_ITER_HASH);
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
         struct ftrace_iterator *iter = m->private;
         void *p = NULL;
+        loff_t l;
 
         mutex_lock(&ftrace_lock);
         /*
+         * If an lseek was done, then reset and start from beginning.
+         */
+        if (*pos < iter->pos)
+                reset_iter_read(iter);
+
+        /*
          * For set_ftrace_filter reading, if we have the filter
          * off, we can short cut and just print out that all
          * functions are enabled.
@@ -1508,26 +1537,35 @@ static void *t_start(struct seq_file *m, loff_t *pos)
                 if (*pos > 0)
                         return t_hash_start(m, pos);
                 iter->flags |= FTRACE_ITER_PRINTALL;
-                (*pos)++;
+                /* reset in case of seek/pread */
+                iter->flags &= ~FTRACE_ITER_HASH;
                 return iter;
         }
 
         if (iter->flags & FTRACE_ITER_HASH)
                 return t_hash_start(m, pos);
 
-        if (*pos > 0) {
-                if (iter->idx < 0)
-                        return p;
-                (*pos)--;
-                iter->idx--;
+        /*
+         * Unfortunately, we need to restart at ftrace_pages_start
+         * every time we let go of the ftrace_mutex. This is because
+         * those pointers can change without the lock.
+         */
+        iter->pg = ftrace_pages_start;
+        iter->idx = 0;
+        for (l = 0; l <= *pos; ) {
+                p = t_next(m, p, &l);
+                if (!p)
+                        break;
         }
 
-        p = t_next(m, p, pos);
+        if (!p) {
+                if (iter->flags & FTRACE_ITER_FILTER)
+                        return t_hash_start(m, pos);
 
-        if (!p)
-                return t_hash_start(m, pos);
+                return NULL;
+        }
 
-        return p;
+        return iter;
 }
 
 static void t_stop(struct seq_file *m, void *p)
@@ -1538,28 +1576,27 @@ static void t_stop(struct seq_file *m, void *p)
 static int t_show(struct seq_file *m, void *v)
 {
         struct ftrace_iterator *iter = m->private;
-        struct dyn_ftrace *rec = v;
-        char str[KSYM_SYMBOL_LEN];
+        struct dyn_ftrace *rec;
 
         if (iter->flags & FTRACE_ITER_HASH)
-                return t_hash_show(m, v);
+                return t_hash_show(m, iter);
 
         if (iter->flags & FTRACE_ITER_PRINTALL) {
                 seq_printf(m, "#### all functions enabled ####\n");
                 return 0;
         }
 
+        rec = iter->func;
+
         if (!rec)
                 return 0;
 
-        kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
-
-        seq_printf(m, "%s\n", str);
+        seq_printf(m, "%ps\n", (void *)rec->ip);
 
         return 0;
 }
 
-static struct seq_operations show_ftrace_seq_ops = {
+static const struct seq_operations show_ftrace_seq_ops = {
         .start = t_start,
         .next = t_next,
         .stop = t_stop,
@@ -1593,17 +1630,6 @@ ftrace_avail_open(struct inode *inode, struct file *file)
         return ret;
 }
 
-int ftrace_avail_release(struct inode *inode, struct file *file)
-{
-        struct seq_file *m = (struct seq_file *)file->private_data;
-        struct ftrace_iterator *iter = m->private;
-
-        seq_release(inode, file);
-        kfree(iter);
-
-        return 0;
-}
-
 static int
 ftrace_failures_open(struct inode *inode, struct file *file)
 {
@@ -1613,8 +1639,8 @@ ftrace_failures_open(struct inode *inode, struct file *file)
 
         ret = ftrace_avail_open(inode, file);
         if (!ret) {
-                m = (struct seq_file *)file->private_data;
-                iter = (struct ftrace_iterator *)m->private;
+                m = file->private_data;
+                iter = m->private;
                 iter->flags = FTRACE_ITER_FAILURES;
         }
 
@@ -1652,9 +1678,14 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
         if (!iter)
                 return -ENOMEM;
 
+        if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) {
+                kfree(iter);
+                return -ENOMEM;
+        }
+
         mutex_lock(&ftrace_regex_lock);
         if ((file->f_mode & FMODE_WRITE) &&
-            !(file->f_flags & O_APPEND))
+            (file->f_flags & O_TRUNC))
                 ftrace_filter_reset(enable);
 
         if (file->f_mode & FMODE_READ) {
@@ -1666,8 +1697,10 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
                 if (!ret) {
                         struct seq_file *m = file->private_data;
                         m->private = iter;
-                } else
+                } else {
+                        trace_parser_put(&iter->parser);
                         kfree(iter);
+                }
         } else
                 file->private_data = iter;
         mutex_unlock(&ftrace_regex_lock);
@@ -1700,64 +1733,10 @@ ftrace_regex_lseek(struct file *file, loff_t offset, int origin)
         return ret;
 }
 
-enum {
-        MATCH_FULL,
-        MATCH_FRONT_ONLY,
-        MATCH_MIDDLE_ONLY,
-        MATCH_END_ONLY,
-};
-
-/*
- * (static function - no need for kernel doc)
- *
- * Pass in a buffer containing a glob and this function will
- * set search to point to the search part of the buffer and
- * return the type of search it is (see enum above).
- * This does modify buff.
- *
- * Returns enum type.
- *  search returns the pointer to use for comparison.
- *  not returns 1 if buff started with a '!'
- *     0 otherwise.
- */
-static int
-ftrace_setup_glob(char *buff, int len, char **search, int *not)
-{
-        int type = MATCH_FULL;
-        int i;
-
-        if (buff[0] == '!') {
-                *not = 1;
-                buff++;
-                len--;
-        } else
-                *not = 0;
-
-        *search = buff;
-
-        for (i = 0; i < len; i++) {
-                if (buff[i] == '*') {
-                        if (!i) {
-                                *search = buff + 1;
-                                type = MATCH_END_ONLY;
-                        } else {
-                                if (type == MATCH_END_ONLY)
-                                        type = MATCH_MIDDLE_ONLY;
-                                else
-                                        type = MATCH_FRONT_ONLY;
-                                buff[i] = 0;
-                                break;
-                        }
-                }
-        }
-
-        return type;
-}
-
 static int ftrace_match(char *str, char *regex, int len, int type)
 {
         int matched = 0;
-        char *ptr;
+        int slen;
 
         switch (type) {
         case MATCH_FULL:
@@ -1773,8 +1752,8 @@ static int ftrace_match(char *str, char *regex, int len, int type)
                         matched = 1;
                 break;
         case MATCH_END_ONLY:
-                ptr = strstr(str, regex);
-                if (ptr && (ptr[len] == 0))
+                slen = strlen(str);
+                if (slen >= len && memcmp(str + slen - len, regex, len) == 0)
                         matched = 1;
                 break;
         }
@@ -1791,7 +1770,7 @@ ftrace_match_record(struct dyn_ftrace *rec, char *regex, int len, int type)
         return ftrace_match(str, regex, len, type);
 }
 
-static void ftrace_match_records(char *buff, int len, int enable)
+static int ftrace_match_records(char *buff, int len, int enable)
 {
         unsigned int search_len;
         struct ftrace_page *pg;
@@ -1800,9 +1779,10 @@ static void ftrace_match_records(char *buff, int len, int enable)
         char *search;
         int type;
         int not;
+        int found = 0;
 
         flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
-        type = ftrace_setup_glob(buff, len, &search, &not);
+        type = filter_parse_regex(buff, len, &search, &not);
 
         search_len = strlen(search);
 
@@ -1817,6 +1797,7 @@ static void ftrace_match_records(char *buff, int len, int enable)
                                 rec->flags &= ~flag;
                         else
                                 rec->flags |= flag;
+                        found = 1;
                 }
                 /*
                  * Only enable filtering if we have a function that
@@ -1826,6 +1807,8 @@ static void ftrace_match_records(char *buff, int len, int enable)
                         ftrace_filtered = 1;
         } while_for_each_ftrace_rec();
         mutex_unlock(&ftrace_lock);
+
+        return found;
 }
 
 static int
@@ -1847,7 +1830,7 @@ ftrace_match_module_record(struct dyn_ftrace *rec, char *mod,
                 return 1;
 }
 
-static void ftrace_match_module_records(char *buff, char *mod, int enable)
+static int ftrace_match_module_records(char *buff, char *mod, int enable)
 {
         unsigned search_len = 0;
         struct ftrace_page *pg;
@@ -1856,6 +1839,7 @@ static void ftrace_match_module_records(char *buff, char *mod, int enable)
         char *search = buff;
         unsigned long flag;
         int not = 0;
+        int found = 0;
 
         flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
 
@@ -1870,7 +1854,7 @@ static void ftrace_match_module_records(char *buff, char *mod, int enable)
         }
 
         if (strlen(buff)) {
-                type = ftrace_setup_glob(buff, strlen(buff), &search, &not);
+                type = filter_parse_regex(buff, strlen(buff), &search, &not);
                 search_len = strlen(search);
         }
 
@@ -1886,12 +1870,15 @@ static void ftrace_match_module_records(char *buff, char *mod, int enable)
                                 rec->flags &= ~flag;
                         else
                                 rec->flags |= flag;
+                        found = 1;
                 }
                 if (enable && (rec->flags & FTRACE_FL_FILTER))
                         ftrace_filtered = 1;
 
         } while_for_each_ftrace_rec();
         mutex_unlock(&ftrace_lock);
+
+        return found;
 }
 
 /*
@@ -1920,8 +1907,9 @@ ftrace_mod_callback(char *func, char *cmd, char *param, int enable)
         if (!strlen(mod))
                 return -EINVAL;
 
-        ftrace_match_module_records(func, mod, enable);
-        return 0;
+        if (ftrace_match_module_records(func, mod, enable))
+                return 0;
+        return -EINVAL;
 }
 
 static struct ftrace_func_command ftrace_mod_cmd = {
@@ -1942,7 +1930,6 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
         struct hlist_head *hhd;
         struct hlist_node *n;
         unsigned long key;
-        int resched;
 
         key = hash_long(ip, FTRACE_HASH_BITS);
 
@@ -1956,12 +1943,12 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
          * period. This syncs the hash iteration and freeing of items
          * on the hash. rcu_read_lock is too dangerous here.
          */
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
         hlist_for_each_entry_rcu(entry, n, hhd, node) {
                 if (entry->ip == ip)
                         entry->ops->func(ip, parent_ip, &entry->data);
         }
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_probe_ops __read_mostly =
@@ -2035,7 +2022,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
         int count = 0;
         char *search;
 
-        type = ftrace_setup_glob(glob, strlen(glob), &search, &not);
+        type = filter_parse_regex(glob, strlen(glob), &search, &not);
         len = strlen(search);
 
         /* we do not support '!' for function probes */
@@ -2107,12 +2094,12 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
         int i, len = 0;
         char *search;
 
-        if (glob && (strcmp(glob, "*") || !strlen(glob)))
+        if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
                 glob = NULL;
-        else {
+        else if (glob) {
                 int not;
 
-                type = ftrace_setup_glob(glob, strlen(glob), &search, &not);
+                type = filter_parse_regex(glob, strlen(glob), &search, &not);
                 len = strlen(search);
 
                 /* we do not support '!' for function probes */
@@ -2218,8 +2205,9 @@ static int ftrace_process_regex(char *buff, int len, int enable)
         func = strsep(&next, ":");
 
         if (!next) {
-                ftrace_match_records(func, len, enable);
-                return 0;
+                if (ftrace_match_records(func, len, enable))
+                        return 0;
+                return ret;
         }
 
         /* command found */
@@ -2244,11 +2232,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
                    size_t cnt, loff_t *ppos, int enable)
 {
         struct ftrace_iterator *iter;
-        char ch;
-        size_t read = 0;
-        ssize_t ret;
+        struct trace_parser *parser;
+        ssize_t ret, read;
 
-        if (!cnt || cnt < 0)
+        if (!cnt)
                 return 0;
 
         mutex_lock(&ftrace_regex_lock);
@@ -2259,66 +2246,20 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
         } else
                 iter = file->private_data;
 
-        if (!*ppos) {
-                iter->flags &= ~FTRACE_ITER_CONT;
-                iter->buffer_idx = 0;
-        }
-
-        ret = get_user(ch, ubuf++);
-        if (ret)
-                goto out;
-        read++;
-        cnt--;
-
-        if (!(iter->flags & ~FTRACE_ITER_CONT)) {
-                /* skip white space */
-                while (cnt && isspace(ch)) {
-                        ret = get_user(ch, ubuf++);
-                        if (ret)
-                                goto out;
-                        read++;
-                        cnt--;
-                }
+        parser = &iter->parser;
+        read = trace_get_user(parser, ubuf, cnt, ppos);
 
-                if (isspace(ch)) {
-                        file->f_pos += read;
-                        ret = read;
-                        goto out;
-                }
-
-                iter->buffer_idx = 0;
-        }
-
-        while (cnt && !isspace(ch)) {
-                if (iter->buffer_idx < FTRACE_BUFF_MAX)
-                        iter->buffer[iter->buffer_idx++] = ch;
-                else {
-                        ret = -EINVAL;
-                        goto out;
-                }
-                ret = get_user(ch, ubuf++);
+        if (read >= 0 && trace_parser_loaded(parser) &&
+            !trace_parser_cont(parser)) {
+                ret = ftrace_process_regex(parser->buffer,
+                                           parser->idx, enable);
+                trace_parser_clear(parser);
                 if (ret)
-                        goto out;
-                read++;
-                cnt--;
+                        goto out_unlock;
         }
 
-        if (isspace(ch)) {
-                iter->filtered++;
-                iter->buffer[iter->buffer_idx] = 0;
-                ret = ftrace_process_regex(iter->buffer,
-                                           iter->buffer_idx, enable);
-                if (ret)
-                        goto out;
-                iter->buffer_idx = 0;
-        } else
-                iter->flags |= FTRACE_ITER_CONT;
-
-
-        file->f_pos += read;
-
         ret = read;
- out:
+out_unlock:
         mutex_unlock(&ftrace_regex_lock);
 
         return ret;
@@ -2402,6 +2343,34 @@ static int __init set_ftrace_filter(char *str)
 }
 __setup("ftrace_filter=", set_ftrace_filter);
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
+static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+
+static int __init set_graph_function(char *str)
+{
+        strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
+        return 1;
+}
+__setup("ftrace_graph_filter=", set_graph_function);
+
+static void __init set_ftrace_early_graph(char *buf)
+{
+        int ret;
+        char *func;
+
+        while (buf) {
+                func = strsep(&buf, ",");
+                /* we allow only one expression at a time */
+                ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
+                                      func);
+                if (ret)
+                        printk(KERN_DEBUG "ftrace: function %s not "
+                                          "traceable\n", func);
+        }
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 static void __init set_ftrace_early_filter(char *buf, int enable)
 {
         char *func;
@@ -2418,6 +2387,10 @@ static void __init set_ftrace_early_filters(void)
                 set_ftrace_early_filter(ftrace_filter_buf, 1);
         if (ftrace_notrace_buf[0])
                 set_ftrace_early_filter(ftrace_notrace_buf, 0);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        if (ftrace_graph_buf[0])
+                set_ftrace_early_graph(ftrace_graph_buf);
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 }
 
 static int
@@ -2425,6 +2398,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 {
         struct seq_file *m = (struct seq_file *)file->private_data;
         struct ftrace_iterator *iter;
+        struct trace_parser *parser;
 
         mutex_lock(&ftrace_regex_lock);
         if (file->f_mode & FMODE_READ) {
@@ -2434,10 +2408,10 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
         } else
                 iter = file->private_data;
 
-        if (iter->buffer_idx) {
-                iter->filtered++;
-                iter->buffer[iter->buffer_idx] = 0;
-                ftrace_match_records(iter->buffer, iter->buffer_idx, enable);
+        parser = &iter->parser;
+        if (trace_parser_loaded(parser)) {
+                parser->buffer[parser->idx] = 0;
+                ftrace_match_records(parser->buffer, parser->idx, enable);
         }
 
         mutex_lock(&ftrace_lock);
@@ -2445,7 +2419,9 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
                 ftrace_run_update_code(FTRACE_ENABLE_CALLS);
         mutex_unlock(&ftrace_lock);
 
+        trace_parser_put(parser);
         kfree(iter);
+
         mutex_unlock(&ftrace_regex_lock);
         return 0;
 }
@@ -2466,14 +2442,14 @@ static const struct file_operations ftrace_avail_fops = {
         .open = ftrace_avail_open,
         .read = seq_read,
         .llseek = seq_lseek,
-        .release = ftrace_avail_release,
+        .release = seq_release_private,
 };
 
 static const struct file_operations ftrace_failures_fops = {
         .open = ftrace_failures_open,
         .read = seq_read,
         .llseek = seq_lseek,
-        .release = ftrace_avail_release,
+        .release = seq_release_private,
 };
 
 static const struct file_operations ftrace_filter_fops = {
@@ -2497,35 +2473,33 @@ static const struct file_operations ftrace_notrace_fops = {
 static DEFINE_MUTEX(graph_lock);
 
 int ftrace_graph_count;
+int ftrace_graph_filter_enabled;
 unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
 
 static void *
-g_next(struct seq_file *m, void *v, loff_t *pos)
+__g_next(struct seq_file *m, loff_t *pos)
 {
-        unsigned long *array = m->private;
-        int index = *pos;
-
-        (*pos)++;
-
-        if (index >= ftrace_graph_count)
+        if (*pos >= ftrace_graph_count)
                 return NULL;
+        return &ftrace_graph_funcs[*pos];
+}
 
-        return &array[index];
+static void *
+g_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        (*pos)++;
+        return __g_next(m, pos);
 }
 
 static void *g_start(struct seq_file *m, loff_t *pos)
 {
-        void *p = NULL;
-
         mutex_lock(&graph_lock);
 
         /* Nothing, tell g_show to print all functions are enabled */
-        if (!ftrace_graph_count && !*pos)
+        if (!ftrace_graph_filter_enabled && !*pos)
                 return (void *)1;
 
-        p = g_next(m, p, pos);
-
-        return p;
+        return __g_next(m, pos);
 }
 
 static void g_stop(struct seq_file *m, void *p)
@@ -2536,7 +2510,6 @@ static void g_stop(struct seq_file *m, void *p)
 static int g_show(struct seq_file *m, void *v)
 {
         unsigned long *ptr = v;
-        char str[KSYM_SYMBOL_LEN];
 
         if (!ptr)
                 return 0;
@@ -2546,14 +2519,12 @@ static int g_show(struct seq_file *m, void *v)
                 return 0;
         }
 
-        kallsyms_lookup(*ptr, NULL, NULL, NULL, str);
-
-        seq_printf(m, "%s\n", str);
+        seq_printf(m, "%ps\n", (void *)*ptr);
 
         return 0;
 }
 
-static struct seq_operations ftrace_graph_seq_ops = {
+static const struct seq_operations ftrace_graph_seq_ops = {
         .start = g_start,
         .next = g_next,
         .stop = g_stop,
@@ -2570,31 +2541,34 @@ ftrace_graph_open(struct inode *inode, struct file *file)
 
         mutex_lock(&graph_lock);
         if ((file->f_mode & FMODE_WRITE) &&
-            !(file->f_flags & O_APPEND)) {
+            (file->f_flags & O_TRUNC)) {
+                ftrace_graph_filter_enabled = 0;
                 ftrace_graph_count = 0;
                 memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
         }
+        mutex_unlock(&graph_lock);
 
-        if (file->f_mode & FMODE_READ) {
+        if (file->f_mode & FMODE_READ)
                 ret = seq_open(file, &ftrace_graph_seq_ops);
-                if (!ret) {
-                        struct seq_file *m = file->private_data;
-                        m->private = ftrace_graph_funcs;
-                }
-        } else
-                file->private_data = ftrace_graph_funcs;
-        mutex_unlock(&graph_lock);
 
         return ret;
 }
 
 static int
+ftrace_graph_release(struct inode *inode, struct file *file)
+{
+        if (file->f_mode & FMODE_READ)
+                seq_release(inode, file);
+        return 0;
+}
+
+static int
 ftrace_set_func(unsigned long *array, int *idx, char *buffer)
 {
         struct dyn_ftrace *rec;
         struct ftrace_page *pg;
         int search_len;
-        int found = 0;
+        int fail = 1;
         int type, not;
         char *search;
         bool exists;
@@ -2604,122 +2578,99 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
                 return -ENODEV;
 
         /* decode regex */
-        type = ftrace_setup_glob(buffer, strlen(buffer), &search, &not);
-        if (not)
-                return -EINVAL;
+        type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
+        if (!not && *idx >= FTRACE_GRAPH_MAX_FUNCS)
+                return -EBUSY;
 
         search_len = strlen(search);
 
         mutex_lock(&ftrace_lock);
         do_for_each_ftrace_rec(pg, rec) {
 
-                if (*idx >= FTRACE_GRAPH_MAX_FUNCS)
-                        break;
-
                 if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE))
                         continue;
 
                 if (ftrace_match_record(rec, search, search_len, type)) {
-                        /* ensure it is not already in the array */
+                        /* if it is in the array */
                         exists = false;
-                        for (i = 0; i < *idx; i++)
+                        for (i = 0; i < *idx; i++) {
                                 if (array[i] == rec->ip) {
                                         exists = true;
                                         break;
                                 }
-                        if (!exists) {
-                                array[(*idx)++] = rec->ip;
-                                found = 1;
+                        }
+
+                        if (!not) {
+                                fail = 0;
+                                if (!exists) {
+                                        array[(*idx)++] = rec->ip;
+                                        if (*idx >= FTRACE_GRAPH_MAX_FUNCS)
+                                                goto out;
+                                }
+                        } else {
+                                if (exists) {
+                                        array[i] = array[--(*idx)];
+                                        array[*idx] = 0;
+                                        fail = 0;
+                                }
                         }
                 }
         } while_for_each_ftrace_rec();
-
+out:
         mutex_unlock(&ftrace_lock);
 
-        return found ? 0 : -EINVAL;
+        if (fail)
+                return -EINVAL;
+
+        ftrace_graph_filter_enabled = 1;
+        return 0;
 }
 
 static ssize_t
 ftrace_graph_write(struct file *file, const char __user *ubuf,
                    size_t cnt, loff_t *ppos)
 {
-        unsigned char buffer[FTRACE_BUFF_MAX+1];
-        unsigned long *array;
-        size_t read = 0;
-        ssize_t ret;
-        int index = 0;
-        char ch;
+        struct trace_parser parser;
+        ssize_t read, ret;
 
-        if (!cnt || cnt < 0)
+        if (!cnt)
                 return 0;
 
         mutex_lock(&graph_lock);
 
-        if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) {
-                ret = -EBUSY;
-                goto out;
+        if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
+                ret = -ENOMEM;
+                goto out_unlock;
         }
 
-        if (file->f_mode & FMODE_READ) {
-                struct seq_file *m = file->private_data;
-                array = m->private;
-        } else
-                array = file->private_data;
+        read = trace_get_user(&parser, ubuf, cnt, ppos);
 
-        ret = get_user(ch, ubuf++);
-        if (ret)
-                goto out;
-        read++;
-        cnt--;
+        if (read >= 0 && trace_parser_loaded((&parser))) {
+                parser.buffer[parser.idx] = 0;
 
-        /* skip white space */
-        while (cnt && isspace(ch)) {
-                ret = get_user(ch, ubuf++);
+                /* we allow only one expression at a time */
+                ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
+                                        parser.buffer);
                 if (ret)
-                        goto out;
-                read++;
-                cnt--;
-        }
-
-        if (isspace(ch)) {
-                *ppos += read;
-                ret = read;
-                goto out;
-        }
-
-        while (cnt && !isspace(ch)) {
-                if (index < FTRACE_BUFF_MAX)
-                        buffer[index++] = ch;
-                else {
-                        ret = -EINVAL;
-                        goto out;
-                }
-                ret = get_user(ch, ubuf++);
-                if (ret)
-                        goto out;
-                read++;
-                cnt--;
+                        goto out_free;
         }
-        buffer[index] = 0;
-
-        /* we allow only one expression at a time */
-        ret = ftrace_set_func(array, &ftrace_graph_count, buffer);
-        if (ret)
-                goto out;
-
-        file->f_pos += read;
 
         ret = read;
- out:
+
+out_free:
+        trace_parser_put(&parser);
+out_unlock:
         mutex_unlock(&graph_lock);
 
         return ret;
 }
 
 static const struct file_operations ftrace_graph_fops = {
-        .open = ftrace_graph_open,
-        .read = seq_read,
-        .write = ftrace_graph_write,
+        .open           = ftrace_graph_open,
+        .read           = seq_read,
+        .write          = ftrace_graph_write,
+        .release        = ftrace_graph_release,
+        .llseek         = seq_lseek,
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -2747,7 +2698,7 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
         return 0;
 }
 
-static int ftrace_convert_nops(struct module *mod,
+static int ftrace_process_locs(struct module *mod,
                                unsigned long *start,
                                unsigned long *end)
 {
@@ -2780,19 +2731,17 @@ static int ftrace_convert_nops(struct module *mod,
 }
 
 #ifdef CONFIG_MODULES
-void ftrace_release(void *start, void *end)
+void ftrace_release_mod(struct module *mod)
 {
         struct dyn_ftrace *rec;
         struct ftrace_page *pg;
-        unsigned long s = (unsigned long)start;
-        unsigned long e = (unsigned long)end;
 
-        if (ftrace_disabled || !start || start == end)
+        if (ftrace_disabled)
                 return;
 
         mutex_lock(&ftrace_lock);
         do_for_each_ftrace_rec(pg, rec) {
-                if ((rec->ip >= s) && (rec->ip < e)) {
+                if (within_module_core(rec->ip, mod)) {
                         /*
                          * rec->ip is changed in ftrace_free_rec()
                          * It should not between s and e if record was freed.
@@ -2809,7 +2758,7 @@ static void ftrace_init_module(struct module *mod,
 {
         if (ftrace_disabled || start == end)
                 return;
-        ftrace_convert_nops(mod, start, end);
+        ftrace_process_locs(mod, start, end);
 }
 
 static int ftrace_module_notify(struct notifier_block *self,
@@ -2824,9 +2773,7 @@ static int ftrace_module_notify(struct notifier_block *self,
                                    mod->num_ftrace_callsites);
                 break;
         case MODULE_STATE_GOING:
-                ftrace_release(mod->ftrace_callsites,
-                               mod->ftrace_callsites +
-                               mod->num_ftrace_callsites);
+                ftrace_release_mod(mod);
                 break;
         }
 
@@ -2872,7 +2819,7 @@ void __init ftrace_init(void)
 
         last_ftrace_enabled = ftrace_enabled = 1;
 
-        ret = ftrace_convert_nops(NULL,
+        ret = ftrace_process_locs(NULL,
                                   __start_mcount_loc,
                                   __stop_mcount_loc);
 
@@ -2905,23 +2852,6 @@ static inline void ftrace_startup_enable(int command) { }
 # define ftrace_shutdown_sysctl()       do { } while (0)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
-static ssize_t
-ftrace_pid_read(struct file *file, char __user *ubuf,
-                       size_t cnt, loff_t *ppos)
-{
-        char buf[64];
-        int r;
-
-        if (ftrace_pid_trace == ftrace_swapper_pid)
-                r = sprintf(buf, "swapper tasks\n");
-        else if (ftrace_pid_trace)
-                r = sprintf(buf, "%u\n", pid_vnr(ftrace_pid_trace));
-        else
-                r = sprintf(buf, "no pid\n");
-
-        return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-}
-
 static void clear_ftrace_swapper(void)
 {
         struct task_struct *p;
@@ -2972,14 +2902,12 @@ static void set_ftrace_pid(struct pid *pid)
         rcu_read_unlock();
 }
 
-static void clear_ftrace_pid_task(struct pid **pid)
+static void clear_ftrace_pid_task(struct pid *pid)
 {
-        if (*pid == ftrace_swapper_pid)
+        if (pid == ftrace_swapper_pid)
                 clear_ftrace_swapper();
         else
-                clear_ftrace_pid(*pid);
-
-        *pid = NULL;
+                clear_ftrace_pid(pid);
 }
 
 static void set_ftrace_pid_task(struct pid *pid)
@@ -2990,74 +2918,184 @@ static void set_ftrace_pid_task(struct pid *pid)
                 set_ftrace_pid(pid);
 }
 
-static ssize_t
-ftrace_pid_write(struct file *filp, const char __user *ubuf,
-                   size_t cnt, loff_t *ppos)
+static int ftrace_pid_add(int p)
 {
         struct pid *pid;
-        char buf[64];
-        long val;
-        int ret;
+        struct ftrace_pid *fpid;
+        int ret = -EINVAL;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
+        mutex_lock(&ftrace_lock);
 
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
+        if (!p)
+                pid = ftrace_swapper_pid;
+        else
+                pid = find_get_pid(p);
 
-        buf[cnt] = 0;
+        if (!pid)
+                goto out;
 
-        ret = strict_strtol(buf, 10, &val);
-        if (ret < 0)
-                return ret;
+        ret = 0;
 
-        mutex_lock(&ftrace_lock);
-        if (val < 0) {
-                /* disable pid tracing */
-                if (!ftrace_pid_trace)
-                        goto out;
+        list_for_each_entry(fpid, &ftrace_pids, list)
+                if (fpid->pid == pid)
+                        goto out_put;
 
-                clear_ftrace_pid_task(&ftrace_pid_trace);
+        ret = -ENOMEM;
 
-        } else {
-                /* swapper task is special */
-                if (!val) {
-                        pid = ftrace_swapper_pid;
-                        if (pid == ftrace_pid_trace)
-                                goto out;
-                } else {
-                        pid = find_get_pid(val);
+        fpid = kmalloc(sizeof(*fpid), GFP_KERNEL);
+        if (!fpid)
+                goto out_put;
 
-                        if (pid == ftrace_pid_trace) {
-                                put_pid(pid);
-                                goto out;
-                        }
-                }
+        list_add(&fpid->list, &ftrace_pids);
+        fpid->pid = pid;
 
-                if (ftrace_pid_trace)
-                        clear_ftrace_pid_task(&ftrace_pid_trace);
+        set_ftrace_pid_task(pid);
 
-                if (!pid)
-                        goto out;
+        ftrace_update_pid_func();
+        ftrace_startup_enable(0);
+
+        mutex_unlock(&ftrace_lock);
+        return 0;
+
+out_put:
+        if (pid != ftrace_swapper_pid)
+                put_pid(pid);
+
+out:
+        mutex_unlock(&ftrace_lock);
+        return ret;
+}
+
+static void ftrace_pid_reset(void)
+{
+        struct ftrace_pid *fpid, *safe;
+
+        mutex_lock(&ftrace_lock);
+        list_for_each_entry_safe(fpid, safe, &ftrace_pids, list) {
+                struct pid *pid = fpid->pid;
 
-                ftrace_pid_trace = pid;
+                clear_ftrace_pid_task(pid);
 
-                set_ftrace_pid_task(ftrace_pid_trace);
+                list_del(&fpid->list);
+                kfree(fpid);
         }
 
-        /* update the function call */
         ftrace_update_pid_func();
         ftrace_startup_enable(0);
 
- out:
         mutex_unlock(&ftrace_lock);
+}
 
-        return cnt;
+static void *fpid_start(struct seq_file *m, loff_t *pos)
+{
+        mutex_lock(&ftrace_lock);
+
+        if (list_empty(&ftrace_pids) && (!*pos))
+                return (void *) 1;
+
+        return seq_list_start(&ftrace_pids, *pos);
+}
+
+static void *fpid_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        if (v == (void *)1)
+                return NULL;
+
+        return seq_list_next(v, &ftrace_pids, pos);
+}
+
+static void fpid_stop(struct seq_file *m, void *p)
+{
+        mutex_unlock(&ftrace_lock);
+}
+
+static int fpid_show(struct seq_file *m, void *v)
+{
+        const struct ftrace_pid *fpid = list_entry(v, struct ftrace_pid, list);
+
+        if (v == (void *)1) {
+                seq_printf(m, "no pid\n");
+                return 0;
+        }
+
+        if (fpid->pid == ftrace_swapper_pid)
+                seq_printf(m, "swapper tasks\n");
+        else
+                seq_printf(m, "%u\n", pid_vnr(fpid->pid));
+
+        return 0;
+}
+
+static const struct seq_operations ftrace_pid_sops = {
+        .start = fpid_start,
+        .next = fpid_next,
+        .stop = fpid_stop,
+        .show = fpid_show,
+};
+
+static int
+ftrace_pid_open(struct inode *inode, struct file *file)
+{
+        int ret = 0;
+
+        if ((file->f_mode & FMODE_WRITE) &&
+            (file->f_flags & O_TRUNC))
+                ftrace_pid_reset();
+
+        if (file->f_mode & FMODE_READ)
+                ret = seq_open(file, &ftrace_pid_sops);
+
+        return ret;
+}
+
+static ssize_t
+ftrace_pid_write(struct file *filp, const char __user *ubuf,
+                   size_t cnt, loff_t *ppos)
+{
+        char buf[64], *tmp;
+        long val;
+        int ret;
+
+        if (cnt >= sizeof(buf))
+                return -EINVAL;
+
+        if (copy_from_user(&buf, ubuf, cnt))
+                return -EFAULT;
+
+        buf[cnt] = 0;
+
+        /*
+         * Allow "echo > set_ftrace_pid" or "echo -n '' > set_ftrace_pid"
+         * to clean the filter quietly.
+         */
+        tmp = strstrip(buf);
+        if (strlen(tmp) == 0)
+                return 1;
+
+        ret = strict_strtol(tmp, 10, &val);
+        if (ret < 0)
+                return ret;
+
+        ret = ftrace_pid_add(val);
+
+        return ret ? ret : cnt;
+}
+
+static int
+ftrace_pid_release(struct inode *inode, struct file *file)
+{
+        if (file->f_mode & FMODE_READ)
+                seq_release(inode, file);
+
+        return 0;
 }
 
 static const struct file_operations ftrace_pid_fops = {
-        .read = ftrace_pid_read,
-        .write = ftrace_pid_write,
+        .open           = ftrace_pid_open,
+        .write          = ftrace_pid_write,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = ftrace_pid_release,
 };
 
 static __init int ftrace_init_debugfs(void)
@@ -3140,7 +3178,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 
 int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
-                     struct file *file, void __user *buffer, size_t *lenp,
+                     void __user *buffer, size_t *lenp,
                      loff_t *ppos)
 {
         int ret;
@@ -3150,12 +3188,12 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
         mutex_lock(&ftrace_lock);
 
-        ret  = proc_dointvec(table, write, file, buffer, lenp, ppos);
+        ret  = proc_dointvec(table, write, buffer, lenp, ppos);
 
-        if (ret || !write || (last_ftrace_enabled == ftrace_enabled))
+        if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
                 goto out;
 
-        last_ftrace_enabled = ftrace_enabled;
+        last_ftrace_enabled = !!ftrace_enabled;
 
         if (ftrace_enabled) {
 
@@ -3243,8 +3281,8 @@ free:
 }
 
 static void
-ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev,
-                                struct task_struct *next)
+ftrace_graph_probe_sched_switch(void *ignore,
+                        struct task_struct *prev, struct task_struct *next)
 {
         unsigned long long timestamp;
         int index;
@@ -3298,7 +3336,7 @@ static int start_graph_tracing(void)
         } while (ret == -EAGAIN);
 
         if (!ret) {
-                ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch);
+                ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
                 if (ret)
                         pr_info("ftrace_graph: Couldn't activate tracepoint"
                                 " probe to kernel_sched_switch\n");
@@ -3370,11 +3408,11 @@ void unregister_ftrace_graph(void)
                 goto out;
 
         ftrace_graph_active--;
-        unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
         ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
         ftrace_graph_entry = ftrace_graph_entry_stub;
         ftrace_shutdown(FTRACE_STOP_FUNC_RET);
         unregister_pm_notifier(&ftrace_suspend_notifier);
+        unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
  out:
         mutex_unlock(&ftrace_lock);
@@ -3385,6 +3423,7 @@ void ftrace_graph_init_task(struct task_struct *t)
 {
         /* Make sure we do not use the parent ret_stack */
         t->ret_stack = NULL;
+        t->curr_ret_stack = -1;
 
         if (ftrace_graph_active) {
                 struct ftrace_ret_stack *ret_stack;
@@ -3394,7 +3433,6 @@ void ftrace_graph_init_task(struct task_struct *t)
                                 GFP_KERNEL);
                 if (!ret_stack)
                         return;
-                t->curr_ret_stack = -1;
                 atomic_set(&t->tracing_graph_pause, 0);
                 atomic_set(&t->trace_overrun, 0);
                 t->ftrace_timestamp = 0;
@@ -3420,4 +3458,3 @@ void ftrace_graph_stop(void)
         ftrace_stop();
 }
 #endif
-
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
deleted file mode 100644
index 1edaa9516e81..000000000000
--- a/kernel/trace/kmemtrace.c
+++ /dev/null
@@ -1,468 +0,0 @@
-/*
- * Memory allocator tracing
- *
- * Copyright (C) 2008 Eduard - Gabriel Munteanu
- * Copyright (C) 2008 Pekka Enberg <penberg@cs.helsinki.fi>
- * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
- */
-
-#include <linux/tracepoint.h>
-#include <linux/seq_file.h>
-#include <linux/debugfs.h>
-#include <linux/dcache.h>
-#include <linux/fs.h>
-
-#include <linux/kmemtrace.h>
-
-#include "trace_output.h"
-#include "trace.h"
-
-/* Select an alternative, minimalistic output than the original one */
-#define TRACE_KMEM_OPT_MINIMAL  0x1
-
-static struct tracer_opt kmem_opts[] = {
-        /* Default disable the minimalistic output */
-        { TRACER_OPT(kmem_minimalistic, TRACE_KMEM_OPT_MINIMAL) },
-        { }
-};
-
-static struct tracer_flags kmem_tracer_flags = {
-        .val                    = 0,
-        .opts                   = kmem_opts
-};
-
-static struct trace_array *kmemtrace_array;
-
-/* Trace allocations */
-static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id,
-                                   unsigned long call_site,
-                                   const void *ptr,
-                                   size_t bytes_req,
-                                   size_t bytes_alloc,
-                                   gfp_t gfp_flags,
-                                   int node)
-{
-        struct ftrace_event_call *call = &event_kmem_alloc;
-        struct trace_array *tr = kmemtrace_array;
-        struct kmemtrace_alloc_entry *entry;
-        struct ring_buffer_event *event;
-
-        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
-        if (!event)
-                return;
-
-        entry = ring_buffer_event_data(event);
-        tracing_generic_entry_update(&entry->ent, 0, 0);
-
-        entry->ent.type         = TRACE_KMEM_ALLOC;
-        entry->type_id          = type_id;
-        entry->call_site        = call_site;
-        entry->ptr              = ptr;
-        entry->bytes_req        = bytes_req;
-        entry->bytes_alloc      = bytes_alloc;
-        entry->gfp_flags        = gfp_flags;
-        entry->node             = node;
-
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                ring_buffer_unlock_commit(tr->buffer, event);
-
-        trace_wake_up();
-}
-
-static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
-                                  unsigned long call_site,
-                                  const void *ptr)
-{
-        struct ftrace_event_call *call = &event_kmem_free;
-        struct trace_array *tr = kmemtrace_array;
-        struct kmemtrace_free_entry *entry;
-        struct ring_buffer_event *event;
-
-        event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry));
-        if (!event)
-                return;
-        entry   = ring_buffer_event_data(event);
-        tracing_generic_entry_update(&entry->ent, 0, 0);
-
-        entry->ent.type         = TRACE_KMEM_FREE;
-        entry->type_id          = type_id;
-        entry->call_site        = call_site;
-        entry->ptr              = ptr;
-
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                ring_buffer_unlock_commit(tr->buffer, event);
-
-        trace_wake_up();
-}
-
-static void kmemtrace_kmalloc(unsigned long call_site,
-                              const void *ptr,
-                              size_t bytes_req,
-                              size_t bytes_alloc,
-                              gfp_t gfp_flags)
-{
-        kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
-                        bytes_req, bytes_alloc, gfp_flags, -1);
-}
-
-static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
-                                       const void *ptr,
-                                       size_t bytes_req,
-                                       size_t bytes_alloc,
-                                       gfp_t gfp_flags)
-{
-        kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
-                        bytes_req, bytes_alloc, gfp_flags, -1);
-}
-
-static void kmemtrace_kmalloc_node(unsigned long call_site,
-                                   const void *ptr,
-                                   size_t bytes_req,
-                                   size_t bytes_alloc,
-                                   gfp_t gfp_flags,
-                                   int node)
-{
-        kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr,
-                        bytes_req, bytes_alloc, gfp_flags, node);
-}
-
-static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
-                                            const void *ptr,
-                                            size_t bytes_req,
-                                            size_t bytes_alloc,
-                                            gfp_t gfp_flags,
-                                            int node)
-{
-        kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr,
-                        bytes_req, bytes_alloc, gfp_flags, node);
-}
-
-static void kmemtrace_kfree(unsigned long call_site, const void *ptr)
-{
-        kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr);
-}
-
-static void kmemtrace_kmem_cache_free(unsigned long call_site, const void *ptr)
-{
-        kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr);
-}
-
-static int kmemtrace_start_probes(void)
-{
-        int err;
-
-        err = register_trace_kmalloc(kmemtrace_kmalloc);
-        if (err)
-                return err;
-        err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
-        if (err)
-                return err;
-        err = register_trace_kmalloc_node(kmemtrace_kmalloc_node);
-        if (err)
-                return err;
-        err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
-        if (err)
-                return err;
-        err = register_trace_kfree(kmemtrace_kfree);
-        if (err)
-                return err;
-        err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
-
-        return err;
-}
-
-static void kmemtrace_stop_probes(void)
-{
-        unregister_trace_kmalloc(kmemtrace_kmalloc);
-        unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
-        unregister_trace_kmalloc_node(kmemtrace_kmalloc_node);
-        unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
-        unregister_trace_kfree(kmemtrace_kfree);
-        unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
-}
-
-static int kmem_trace_init(struct trace_array *tr)
-{
-        int cpu;
-        kmemtrace_array = tr;
-
-        for_each_cpu(cpu, cpu_possible_mask)
-                tracing_reset(tr, cpu);
-
-        kmemtrace_start_probes();
-
-        return 0;
-}
-
-static void kmem_trace_reset(struct trace_array *tr)
-{
-        kmemtrace_stop_probes();
-}
-
-static void kmemtrace_headers(struct seq_file *s)
-{
-        /* Don't need headers for the original kmemtrace output */
-        if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
-                return;
-
-        seq_printf(s, "#\n");
-        seq_printf(s, "# ALLOC  TYPE  REQ   GIVEN  FLAGS     "
-                        "      POINTER         NODE    CALLER\n");
-        seq_printf(s, "# FREE   |      |     |       |       "
-                        "       |   |            |        |\n");
-        seq_printf(s, "# |\n\n");
-}
-
-/*
- * The following functions give the original output from kmemtrace,
- * plus the origin CPU, since reordering occurs in-kernel now.
- */
-
-#define KMEMTRACE_USER_ALLOC    0
-#define KMEMTRACE_USER_FREE     1
-
-struct kmemtrace_user_event {
-        u8                      event_id;
-        u8                      type_id;
-        u16                     event_size;
-        u32                     cpu;
-        u64                     timestamp;
-        unsigned long           call_site;
-        unsigned long           ptr;
-};
-
-struct kmemtrace_user_event_alloc {
-        size_t                  bytes_req;
-        size_t                  bytes_alloc;
-        unsigned                gfp_flags;
-        int                     node;
-};
-
-static enum print_line_t
-kmemtrace_print_alloc_user(struct trace_iterator *iter,
-                           struct kmemtrace_alloc_entry *entry)
-{
-        struct kmemtrace_user_event_alloc *ev_alloc;
-        struct trace_seq *s = &iter->seq;
-        struct kmemtrace_user_event *ev;
-
-        ev = trace_seq_reserve(s, sizeof(*ev));
-        if (!ev)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        ev->event_id            = KMEMTRACE_USER_ALLOC;
-        ev->type_id             = entry->type_id;
-        ev->event_size          = sizeof(*ev) + sizeof(*ev_alloc);
-        ev->cpu                 = iter->cpu;
-        ev->timestamp           = iter->ts;
-        ev->call_site           = entry->call_site;
-        ev->ptr                 = (unsigned long)entry->ptr;
-
-        ev_alloc = trace_seq_reserve(s, sizeof(*ev_alloc));
-        if (!ev_alloc)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        ev_alloc->bytes_req     = entry->bytes_req;
-        ev_alloc->bytes_alloc   = entry->bytes_alloc;
-        ev_alloc->gfp_flags     = entry->gfp_flags;
-        ev_alloc->node          = entry->node;
-
-        return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-kmemtrace_print_free_user(struct trace_iterator *iter,
-                          struct kmemtrace_free_entry *entry)
-{
-        struct trace_seq *s = &iter->seq;
-        struct kmemtrace_user_event *ev;
-
-        ev = trace_seq_reserve(s, sizeof(*ev));
-        if (!ev)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        ev->event_id            = KMEMTRACE_USER_FREE;
-        ev->type_id             = entry->type_id;
-        ev->event_size          = sizeof(*ev);
-        ev->cpu                 = iter->cpu;
-        ev->timestamp           = iter->ts;
-        ev->call_site           = entry->call_site;
-        ev->ptr                 = (unsigned long)entry->ptr;
-
-        return TRACE_TYPE_HANDLED;
-}
-
-/* The two other following provide a more minimalistic output */
-static enum print_line_t
-kmemtrace_print_alloc_compress(struct trace_iterator *iter,
-                                        struct kmemtrace_alloc_entry *entry)
-{
-        struct trace_seq *s = &iter->seq;
-        int ret;
-
-        /* Alloc entry */
-        ret = trace_seq_printf(s, "  +      ");
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Type */
-        switch (entry->type_id) {
-        case KMEMTRACE_TYPE_KMALLOC:
-                ret = trace_seq_printf(s, "K   ");
-                break;
-        case KMEMTRACE_TYPE_CACHE:
-                ret = trace_seq_printf(s, "C   ");
-                break;
-        case KMEMTRACE_TYPE_PAGES:
-                ret = trace_seq_printf(s, "P   ");
-                break;
-        default:
-                ret = trace_seq_printf(s, "?   ");
-        }
-
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Requested */
-        ret = trace_seq_printf(s, "%4zu   ", entry->bytes_req);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Allocated */
-        ret = trace_seq_printf(s, "%4zu   ", entry->bytes_alloc);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Flags
-         * TODO: would be better to see the name of the GFP flag names
-         */
-        ret = trace_seq_printf(s, "%08x   ", entry->gfp_flags);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Pointer to allocated */
-        ret = trace_seq_printf(s, "0x%tx   ", (ptrdiff_t)entry->ptr);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Node */
-        ret = trace_seq_printf(s, "%4d   ", entry->node);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Call site */
-        ret = seq_print_ip_sym(s, entry->call_site, 0);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        if (!trace_seq_printf(s, "\n"))
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-kmemtrace_print_free_compress(struct trace_iterator *iter,
-                              struct kmemtrace_free_entry *entry)
-{
-        struct trace_seq *s = &iter->seq;
-        int ret;
-
-        /* Free entry */
-        ret = trace_seq_printf(s, "  -      ");
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Type */
-        switch (entry->type_id) {
-        case KMEMTRACE_TYPE_KMALLOC:
-                ret = trace_seq_printf(s, "K     ");
-                break;
-        case KMEMTRACE_TYPE_CACHE:
-                ret = trace_seq_printf(s, "C     ");
-                break;
-        case KMEMTRACE_TYPE_PAGES:
-                ret = trace_seq_printf(s, "P     ");
-                break;
-        default:
-                ret = trace_seq_printf(s, "?     ");
-        }
-
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Skip requested/allocated/flags */
-        ret = trace_seq_printf(s, "                       ");
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Pointer to allocated */
-        ret = trace_seq_printf(s, "0x%tx   ", (ptrdiff_t)entry->ptr);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Skip node */
-        ret = trace_seq_printf(s, "       ");
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        /* Call site */
-        ret = seq_print_ip_sym(s, entry->call_site, 0);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        if (!trace_seq_printf(s, "\n"))
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
-{
-        struct trace_entry *entry = iter->ent;
-
-        switch (entry->type) {
-        case TRACE_KMEM_ALLOC: {
-                struct kmemtrace_alloc_entry *field;
-
-                trace_assign_type(field, entry);
-                if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
-                        return kmemtrace_print_alloc_compress(iter, field);
-                else
-                        return kmemtrace_print_alloc_user(iter, field);
-        }
-
-        case TRACE_KMEM_FREE: {
-                struct kmemtrace_free_entry *field;
-
-                trace_assign_type(field, entry);
-                if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
-                        return kmemtrace_print_free_compress(iter, field);
-                else
-                        return kmemtrace_print_free_user(iter, field);
-        }
-
-        default:
-                return TRACE_TYPE_UNHANDLED;
-        }
-}
-
-static struct tracer kmem_tracer __read_mostly = {
-        .name                   = "kmemtrace",
-        .init                   = kmem_trace_init,
-        .reset                  = kmem_trace_reset,
-        .print_line             = kmemtrace_print_line,
-        .print_header           = kmemtrace_headers,
-        .flags                  = &kmem_tracer_flags
-};
-
-void kmemtrace_init(void)
-{
-        /* earliest opportunity to start kmem tracing */
-}
-
-static int __init init_kmem_tracer(void)
-{
-        return register_tracer(&kmem_tracer);
-}
-device_initcall(init_kmem_tracer);
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
new file mode 100644
index 000000000000..f55fcf61b223
--- /dev/null
+++ b/kernel/trace/power-traces.c
@@ -0,0 +1,20 @@
+/*
+ * Power trace points
+ *
+ * Copyright (C) 2009 Arjan van de Ven <arjan@linux.intel.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/power.h>
+
+#ifdef EVENT_POWER_TRACING_DEPRECATED
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_start);
+#endif
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
+
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 04dac2638258..bd1c35a4fbcc 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -14,12 +14,14 @@
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/list.h>
 #include <linux/cpu.h>
 #include <linux/fs.h>
 
+#include <asm/local.h>
 #include "trace.h"
 
 /*
@@ -201,13 +203,19 @@ int tracing_is_on(void)
 }
 EXPORT_SYMBOL_GPL(tracing_is_on);
 
-#include "trace.h"
-
 #define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
 #define RB_ALIGNMENT            4U
 #define RB_MAX_SMALL_DATA       (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
 #define RB_EVNT_MIN_SIZE        8U      /* two 32bit words */
 
+#if !defined(CONFIG_64BIT) || defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+# define RB_FORCE_8BYTE_ALIGNMENT       0
+# define RB_ARCH_ALIGNMENT              RB_ALIGNMENT
+#else
+# define RB_FORCE_8BYTE_ALIGNMENT       1
+# define RB_ARCH_ALIGNMENT              8U
+#endif
+
 /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
 #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
 
@@ -216,19 +224,17 @@ enum {
         RB_LEN_TIME_STAMP = 16,
 };
 
-static inline int rb_null_event(struct ring_buffer_event *event)
-{
-        return event->type_len == RINGBUF_TYPE_PADDING
-                        && event->time_delta == 0;
-}
+#define skip_time_extend(event) \
+        ((struct ring_buffer_event *)((char *)event + RB_LEN_TIME_EXTEND))
 
-static inline int rb_discarded_event(struct ring_buffer_event *event)
+static inline int rb_null_event(struct ring_buffer_event *event)
 {
-        return event->type_len == RINGBUF_TYPE_PADDING && event->time_delta;
+        return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
 }
 
 static void rb_event_set_padding(struct ring_buffer_event *event)
 {
+        /* padding has a NULL time_delta */
         event->type_len = RINGBUF_TYPE_PADDING;
         event->time_delta = 0;
 }
@@ -245,8 +251,12 @@ rb_event_data_length(struct ring_buffer_event *event)
         return length + RB_EVNT_HDR_SIZE;
 }
 
-/* inline for ring buffer fast paths */
-static unsigned
+/*
+ * Return the length of the given event. Will return
+ * the length of the time extend if the event is a
+ * time extend.
+ */
+static inline unsigned
 rb_event_length(struct ring_buffer_event *event)
 {
         switch (event->type_len) {
@@ -271,13 +281,41 @@ rb_event_length(struct ring_buffer_event *event)
         return 0;
 }
 
+/*
+ * Return total length of time extend and data,
+ *   or just the event length for all other events.
+ */
+static inline unsigned
+rb_event_ts_length(struct ring_buffer_event *event)
+{
+        unsigned len = 0;
+
+        if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
+                /* time extends include the data event after it */
+                len = RB_LEN_TIME_EXTEND;
+                event = skip_time_extend(event);
+        }
+        return len + rb_event_length(event);
+}
+
 /**
  * ring_buffer_event_length - return the length of the event
  * @event: the event to get the length of
+ *
+ * Returns the size of the data load of a data event.
+ * If the event is something other than a data event, it
+ * returns the size of the event itself. With the exception
+ * of a TIME EXTEND, where it still returns the size of the
+ * data load of the data event after it.
  */
 unsigned ring_buffer_event_length(struct ring_buffer_event *event)
 {
-        unsigned length = rb_event_length(event);
+        unsigned length;
+
+        if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+                event = skip_time_extend(event);
+
+        length = rb_event_length(event);
         if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
                 return length;
         length -= RB_EVNT_HDR_SIZE;
@@ -291,6 +329,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_length);
 static void *
 rb_event_data(struct ring_buffer_event *event)
 {
+        if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+                event = skip_time_extend(event);
         BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
         /* If length is in len field, then array[0] has the data */
         if (event->type_len)
@@ -316,20 +356,49 @@ 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 */
         unsigned char    data[];        /* data of buffer page */
 };
 
+/*
+ * Note, the buffer_page list must be first. The buffer pages
+ * are allocated in cache lines, which means that each buffer
+ * page will be at the beginning of a cache line, and thus
+ * the least significant bits will be zero. We use this to
+ * add flags in the list struct pointers, to make the ring buffer
+ * lockless.
+ */
 struct buffer_page {
         struct list_head list;          /* list of buffer pages */
         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 */
 };
 
+/*
+ * The buffer page counters, write and entries, must be reset
+ * atomically when crossing page boundaries. To synchronize this
+ * update, two counters are inserted into the number. One is
+ * the actual counter for the write position or count on the page.
+ *
+ * The other is a counter of updaters. Before an update happens
+ * the update partition of the counter is incremented. This will
+ * allow the updater to update the counter atomically.
+ *
+ * The counter is 20 bits, and the state data is 12.
+ */
+#define RB_WRITE_MASK           0xfffff
+#define RB_WRITE_INTCNT         (1 << 20)
+
 static void rb_init_page(struct buffer_data_page *bpage)
 {
         local_set(&bpage->commit, 0);
@@ -372,27 +441,33 @@ static inline int test_time_stamp(u64 delta)
 /* Max payload is BUF_PAGE_SIZE - header (8bytes) */
 #define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
 
-/* Max number of timestamps that can fit on a page */
-#define RB_TIMESTAMPS_PER_PAGE  (BUF_PAGE_SIZE / RB_LEN_TIME_STAMP)
-
 int ring_buffer_print_page_header(struct trace_seq *s)
 {
         struct buffer_data_page field;
         int ret;
 
         ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t"
-                               "offset:0;\tsize:%u;\n",
-                               (unsigned int)sizeof(field.time_stamp));
+                               "offset:0;\tsize:%u;\tsigned:%u;\n",
+                               (unsigned int)sizeof(field.time_stamp),
+                               (unsigned int)is_signed_type(u64));
 
         ret = trace_seq_printf(s, "\tfield: local_t commit;\t"
-                               "offset:%u;\tsize:%u;\n",
+                               "offset:%u;\tsize:%u;\tsigned:%u;\n",
+                               (unsigned int)offsetof(typeof(field), commit),
+                               (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),
-                               (unsigned int)sizeof(field.commit));
+                               1,
+                               (unsigned int)is_signed_type(long));
 
         ret = trace_seq_printf(s, "\tfield: char data;\t"
-                               "offset:%u;\tsize:%u;\n",
+                               "offset:%u;\tsize:%u;\tsigned:%u;\n",
                                (unsigned int)offsetof(typeof(field), data),
-                               (unsigned int)BUF_PAGE_SIZE);
+                               (unsigned int)BUF_PAGE_SIZE,
+                               (unsigned int)is_signed_type(char));
 
         return ret;
 }
@@ -402,25 +477,26 @@ int ring_buffer_print_page_header(struct trace_seq *s)
  */
 struct ring_buffer_per_cpu {
         int                             cpu;
+        atomic_t                        record_disabled;
         struct ring_buffer              *buffer;
-        spinlock_t                      reader_lock; /* serialize readers */
-        raw_spinlock_t                  lock;
+        spinlock_t                      reader_lock;    /* serialize readers */
+        arch_spinlock_t                 lock;
         struct lock_class_key           lock_key;
-        struct list_head                pages;
+        struct list_head                *pages;
         struct buffer_page              *head_page;     /* read from head */
         struct buffer_page              *tail_page;     /* write to tail */
         struct buffer_page              *commit_page;   /* committed pages */
         struct buffer_page              *reader_page;
-        unsigned long                   nmi_dropped;
-        unsigned long                   commit_overrun;
-        unsigned long                   overrun;
-        unsigned long                   read;
+        unsigned long                   lost_events;
+        unsigned long                   last_overrun;
+        local_t                         commit_overrun;
+        local_t                         overrun;
         local_t                         entries;
         local_t                         committing;
         local_t                         commits;
+        unsigned long                   read;
         u64                             write_stamp;
         u64                             read_stamp;
-        atomic_t                        record_disabled;
 };
 
 struct ring_buffer {
@@ -446,24 +522,31 @@ struct ring_buffer_iter {
         struct ring_buffer_per_cpu      *cpu_buffer;
         unsigned long                   head;
         struct buffer_page              *head_page;
+        struct buffer_page              *cache_reader_page;
+        unsigned long                   cache_read;
         u64                             read_stamp;
 };
 
 /* buffer may be either ring_buffer or ring_buffer_per_cpu */
-#define RB_WARN_ON(buffer, cond)                                \
-        ({                                                      \
-                int _____ret = unlikely(cond);                  \
-                if (_____ret) {                                 \
-                        atomic_inc(&buffer->record_disabled);   \
-                        WARN_ON(1);                             \
-                }                                               \
-                _____ret;                                       \
+#define RB_WARN_ON(b, cond)                                             \
+        ({                                                              \
+                int _____ret = unlikely(cond);                          \
+                if (_____ret) {                                         \
+                        if (__same_type(*(b), struct ring_buffer_per_cpu)) { \
+                                struct ring_buffer_per_cpu *__b =       \
+                                        (void *)b;                      \
+                                atomic_inc(&__b->buffer->record_disabled); \
+                        } else                                          \
+                                atomic_inc(&b->record_disabled);        \
+                        WARN_ON(1);                                     \
+                }                                                       \
+                _____ret;                                               \
         })
 
 /* Up this if you want to test the TIME_EXTENTS and normalization */
 #define DEBUG_SHIFT 0
 
-static inline u64 rb_time_stamp(struct ring_buffer *buffer, int cpu)
+static inline u64 rb_time_stamp(struct ring_buffer *buffer)
 {
         /* shift to debug/test normalization and TIME_EXTENTS */
         return buffer->clock() << DEBUG_SHIFT;
@@ -474,7 +557,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
         u64 time;
 
         preempt_disable_notrace();
-        time = rb_time_stamp(buffer, cpu);
+        time = rb_time_stamp(buffer);
         preempt_enable_no_resched_notrace();
 
         return time;
@@ -489,6 +572,390 @@ void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
+/*
+ * Making the ring buffer lockless makes things tricky.
+ * Although writes only happen on the CPU that they are on,
+ * and they only need to worry about interrupts. Reads can
+ * happen on any CPU.
+ *
+ * The reader page is always off the ring buffer, but when the
+ * reader finishes with a page, it needs to swap its page with
+ * a new one from the buffer. The reader needs to take from
+ * the head (writes go to the tail). But if a writer is in overwrite
+ * mode and wraps, it must push the head page forward.
+ *
+ * Here lies the problem.
+ *
+ * The reader must be careful to replace only the head page, and
+ * not another one. As described at the top of the file in the
+ * ASCII art, the reader sets its old page to point to the next
+ * page after head. It then sets the page after head to point to
+ * the old reader page. But if the writer moves the head page
+ * during this operation, the reader could end up with the tail.
+ *
+ * We use cmpxchg to help prevent this race. We also do something
+ * special with the page before head. We set the LSB to 1.
+ *
+ * When the writer must push the page forward, it will clear the
+ * bit that points to the head page, move the head, and then set
+ * the bit that points to the new head page.
+ *
+ * We also don't want an interrupt coming in and moving the head
+ * page on another writer. Thus we use the second LSB to catch
+ * that too. Thus:
+ *
+ * head->list->prev->next        bit 1          bit 0
+ *                              -------        -------
+ * Normal page                     0              0
+ * Points to head page             0              1
+ * New head page                   1              0
+ *
+ * Note we can not trust the prev pointer of the head page, because:
+ *
+ * +----+       +-----+        +-----+
+ * |    |------>|  T  |---X--->|  N  |
+ * |    |<------|     |        |     |
+ * +----+       +-----+        +-----+
+ *   ^                           ^ |
+ *   |          +-----+          | |
+ *   +----------|  R  |----------+ |
+ *              |     |<-----------+
+ *              +-----+
+ *
+ * Key:  ---X-->  HEAD flag set in pointer
+ *         T      Tail page
+ *         R      Reader page
+ *         N      Next page
+ *
+ * (see __rb_reserve_next() to see where this happens)
+ *
+ *  What the above shows is that the reader just swapped out
+ *  the reader page with a page in the buffer, but before it
+ *  could make the new header point back to the new page added
+ *  it was preempted by a writer. The writer moved forward onto
+ *  the new page added by the reader and is about to move forward
+ *  again.
+ *
+ *  You can see, it is legitimate for the previous pointer of
+ *  the head (or any page) not to point back to itself. But only
+ *  temporarially.
+ */
+
+#define RB_PAGE_NORMAL          0UL
+#define RB_PAGE_HEAD            1UL
+#define RB_PAGE_UPDATE          2UL
+
+
+#define RB_FLAG_MASK            3UL
+
+/* PAGE_MOVED is not part of the mask */
+#define RB_PAGE_MOVED           4UL
+
+/*
+ * rb_list_head - remove any bit
+ */
+static struct list_head *rb_list_head(struct list_head *list)
+{
+        unsigned long val = (unsigned long)list;
+
+        return (struct list_head *)(val & ~RB_FLAG_MASK);
+}
+
+/*
+ * rb_is_head_page - test if the given page is the head page
+ *
+ * Because the reader may move the head_page pointer, we can
+ * not trust what the head page is (it may be pointing to
+ * the reader page). But if the next page is a header page,
+ * its flags will be non zero.
+ */
+static int inline
+rb_is_head_page(struct ring_buffer_per_cpu *cpu_buffer,
+                struct buffer_page *page, struct list_head *list)
+{
+        unsigned long val;
+
+        val = (unsigned long)list->next;
+
+        if ((val & ~RB_FLAG_MASK) != (unsigned long)&page->list)
+                return RB_PAGE_MOVED;
+
+        return val & RB_FLAG_MASK;
+}
+
+/*
+ * rb_is_reader_page
+ *
+ * The unique thing about the reader page, is that, if the
+ * writer is ever on it, the previous pointer never points
+ * back to the reader page.
+ */
+static int rb_is_reader_page(struct buffer_page *page)
+{
+        struct list_head *list = page->list.prev;
+
+        return rb_list_head(list->next) != &page->list;
+}
+
+/*
+ * rb_set_list_to_head - set a list_head to be pointing to head.
+ */
+static void rb_set_list_to_head(struct ring_buffer_per_cpu *cpu_buffer,
+                                struct list_head *list)
+{
+        unsigned long *ptr;
+
+        ptr = (unsigned long *)&list->next;
+        *ptr |= RB_PAGE_HEAD;
+        *ptr &= ~RB_PAGE_UPDATE;
+}
+
+/*
+ * rb_head_page_activate - sets up head page
+ */
+static void rb_head_page_activate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        struct buffer_page *head;
+
+        head = cpu_buffer->head_page;
+        if (!head)
+                return;
+
+        /*
+         * Set the previous list pointer to have the HEAD flag.
+         */
+        rb_set_list_to_head(cpu_buffer, head->list.prev);
+}
+
+static void rb_list_head_clear(struct list_head *list)
+{
+        unsigned long *ptr = (unsigned long *)&list->next;
+
+        *ptr &= ~RB_FLAG_MASK;
+}
+
+/*
+ * rb_head_page_dactivate - clears head page ptr (for free list)
+ */
+static void
+rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        struct list_head *hd;
+
+        /* Go through the whole list and clear any pointers found. */
+        rb_list_head_clear(cpu_buffer->pages);
+
+        list_for_each(hd, cpu_buffer->pages)
+                rb_list_head_clear(hd);
+}
+
+static int rb_head_page_set(struct ring_buffer_per_cpu *cpu_buffer,
+                            struct buffer_page *head,
+                            struct buffer_page *prev,
+                            int old_flag, int new_flag)
+{
+        struct list_head *list;
+        unsigned long val = (unsigned long)&head->list;
+        unsigned long ret;
+
+        list = &prev->list;
+
+        val &= ~RB_FLAG_MASK;
+
+        ret = cmpxchg((unsigned long *)&list->next,
+                      val | old_flag, val | new_flag);
+
+        /* check if the reader took the page */
+        if ((ret & ~RB_FLAG_MASK) != val)
+                return RB_PAGE_MOVED;
+
+        return ret & RB_FLAG_MASK;
+}
+
+static int rb_head_page_set_update(struct ring_buffer_per_cpu *cpu_buffer,
+                                   struct buffer_page *head,
+                                   struct buffer_page *prev,
+                                   int old_flag)
+{
+        return rb_head_page_set(cpu_buffer, head, prev,
+                                old_flag, RB_PAGE_UPDATE);
+}
+
+static int rb_head_page_set_head(struct ring_buffer_per_cpu *cpu_buffer,
+                                 struct buffer_page *head,
+                                 struct buffer_page *prev,
+                                 int old_flag)
+{
+        return rb_head_page_set(cpu_buffer, head, prev,
+                                old_flag, RB_PAGE_HEAD);
+}
+
+static int rb_head_page_set_normal(struct ring_buffer_per_cpu *cpu_buffer,
+                                   struct buffer_page *head,
+                                   struct buffer_page *prev,
+                                   int old_flag)
+{
+        return rb_head_page_set(cpu_buffer, head, prev,
+                                old_flag, RB_PAGE_NORMAL);
+}
+
+static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
+                               struct buffer_page **bpage)
+{
+        struct list_head *p = rb_list_head((*bpage)->list.next);
+
+        *bpage = list_entry(p, struct buffer_page, list);
+}
+
+static struct buffer_page *
+rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        struct buffer_page *head;
+        struct buffer_page *page;
+        struct list_head *list;
+        int i;
+
+        if (RB_WARN_ON(cpu_buffer, !cpu_buffer->head_page))
+                return NULL;
+
+        /* sanity check */
+        list = cpu_buffer->pages;
+        if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev->next) != list))
+                return NULL;
+
+        page = head = cpu_buffer->head_page;
+        /*
+         * It is possible that the writer moves the header behind
+         * where we started, and we miss in one loop.
+         * A second loop should grab the header, but we'll do
+         * three loops just because I'm paranoid.
+         */
+        for (i = 0; i < 3; i++) {
+                do {
+                        if (rb_is_head_page(cpu_buffer, page, page->list.prev)) {
+                                cpu_buffer->head_page = page;
+                                return page;
+                        }
+                        rb_inc_page(cpu_buffer, &page);
+                } while (page != head);
+        }
+
+        RB_WARN_ON(cpu_buffer, 1);
+
+        return NULL;
+}
+
+static int rb_head_page_replace(struct buffer_page *old,
+                                struct buffer_page *new)
+{
+        unsigned long *ptr = (unsigned long *)&old->list.prev->next;
+        unsigned long val;
+        unsigned long ret;
+
+        val = *ptr & ~RB_FLAG_MASK;
+        val |= RB_PAGE_HEAD;
+
+        ret = cmpxchg(ptr, val, (unsigned long)&new->list);
+
+        return ret == val;
+}
+
+/*
+ * rb_tail_page_update - move the tail page forward
+ *
+ * Returns 1 if moved tail page, 0 if someone else did.
+ */
+static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
+                               struct buffer_page *tail_page,
+                               struct buffer_page *next_page)
+{
+        struct buffer_page *old_tail;
+        unsigned long old_entries;
+        unsigned long old_write;
+        int ret = 0;
+
+        /*
+         * The tail page now needs to be moved forward.
+         *
+         * We need to reset the tail page, but without messing
+         * with possible erasing of data brought in by interrupts
+         * that have moved the tail page and are currently on it.
+         *
+         * We add a counter to the write field to denote this.
+         */
+        old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write);
+        old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries);
+
+        /*
+         * Just make sure we have seen our old_write and synchronize
+         * with any interrupts that come in.
+         */
+        barrier();
+
+        /*
+         * If the tail page is still the same as what we think
+         * it is, then it is up to us to update the tail
+         * pointer.
+         */
+        if (tail_page == cpu_buffer->tail_page) {
+                /* Zero the write counter */
+                unsigned long val = old_write & ~RB_WRITE_MASK;
+                unsigned long eval = old_entries & ~RB_WRITE_MASK;
+
+                /*
+                 * This will only succeed if an interrupt did
+                 * not come in and change it. In which case, we
+                 * do not want to modify it.
+                 *
+                 * We add (void) to let the compiler know that we do not care
+                 * about the return value of these functions. We use the
+                 * cmpxchg to only update if an interrupt did not already
+                 * do it for us. If the cmpxchg fails, we don't care.
+                 */
+                (void)local_cmpxchg(&next_page->write, old_write, val);
+                (void)local_cmpxchg(&next_page->entries, old_entries, eval);
+
+                /*
+                 * No need to worry about races with clearing out the commit.
+                 * it only can increment when a commit takes place. But that
+                 * only happens in the outer most nested commit.
+                 */
+                local_set(&next_page->page->commit, 0);
+
+                old_tail = cmpxchg(&cpu_buffer->tail_page,
+                                   tail_page, next_page);
+
+                if (old_tail == tail_page)
+                        ret = 1;
+        }
+
+        return ret;
+}
+
+static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
+                          struct buffer_page *bpage)
+{
+        unsigned long val = (unsigned long)bpage;
+
+        if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK))
+                return 1;
+
+        return 0;
+}
+
+/**
+ * rb_check_list - make sure a pointer to a list has the last bits zero
+ */
+static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer,
+                         struct list_head *list)
+{
+        if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev) != list->prev))
+                return 1;
+        if (RB_WARN_ON(cpu_buffer, rb_list_head(list->next) != list->next))
+                return 1;
+        return 0;
+}
+
 /**
  * check_pages - integrity check of buffer pages
  * @cpu_buffer: CPU buffer with pages to test
@@ -498,14 +965,19 @@ EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
  */
 static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
-        struct list_head *head = &cpu_buffer->pages;
+        struct list_head *head = cpu_buffer->pages;
         struct buffer_page *bpage, *tmp;
 
+        rb_head_page_deactivate(cpu_buffer);
+
         if (RB_WARN_ON(cpu_buffer, head->next->prev != head))
                 return -1;
         if (RB_WARN_ON(cpu_buffer, head->prev->next != head))
                 return -1;
 
+        if (rb_check_list(cpu_buffer, head))
+                return -1;
+
         list_for_each_entry_safe(bpage, tmp, head, list) {
                 if (RB_WARN_ON(cpu_buffer,
                                bpage->list.next->prev != &bpage->list))
@@ -513,25 +985,33 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
                 if (RB_WARN_ON(cpu_buffer,
                                bpage->list.prev->next != &bpage->list))
                         return -1;
+                if (rb_check_list(cpu_buffer, &bpage->list))
+                        return -1;
         }
 
+        rb_head_page_activate(cpu_buffer);
+
         return 0;
 }
 
 static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
                              unsigned nr_pages)
 {
-        struct list_head *head = &cpu_buffer->pages;
         struct buffer_page *bpage, *tmp;
         unsigned long addr;
         LIST_HEAD(pages);
         unsigned i;
 
+        WARN_ON(!nr_pages);
+
         for (i = 0; i < nr_pages; i++) {
                 bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
                                     GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
                 if (!bpage)
                         goto free_pages;
+
+                rb_check_bpage(cpu_buffer, bpage);
+
                 list_add(&bpage->list, &pages);
 
                 addr = __get_free_page(GFP_KERNEL);
@@ -541,7 +1021,13 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
                 rb_init_page(bpage->page);
         }
 
-        list_splice(&pages, head);
+        /*
+         * The ring buffer page list is a circular list that does not
+         * start and end with a list head. All page list items point to
+         * other pages.
+         */
+        cpu_buffer->pages = pages.next;
+        list_del(&pages);
 
         rb_check_pages(cpu_buffer);
 
@@ -572,14 +1058,15 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
         cpu_buffer->buffer = buffer;
         spin_lock_init(&cpu_buffer->reader_lock);
         lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
-        cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-        INIT_LIST_HEAD(&cpu_buffer->pages);
+        cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
         bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
                             GFP_KERNEL, cpu_to_node(cpu));
         if (!bpage)
                 goto fail_free_buffer;
 
+        rb_check_bpage(cpu_buffer, bpage);
+
         cpu_buffer->reader_page = bpage;
         addr = __get_free_page(GFP_KERNEL);
         if (!addr)
@@ -594,9 +1081,11 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
                 goto fail_free_reader;
 
         cpu_buffer->head_page
-                = list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+                = list_entry(cpu_buffer->pages, struct buffer_page, list);
         cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;
 
+        rb_head_page_activate(cpu_buffer);
+
         return cpu_buffer;
 
  fail_free_reader:
@@ -609,15 +1098,22 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 
 static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 {
-        struct list_head *head = &cpu_buffer->pages;
+        struct list_head *head = cpu_buffer->pages;
         struct buffer_page *bpage, *tmp;
 
         free_buffer_page(cpu_buffer->reader_page);
 
-        list_for_each_entry_safe(bpage, tmp, head, list) {
-                list_del_init(&bpage->list);
+        rb_head_page_deactivate(cpu_buffer);
+
+        if (head) {
+                list_for_each_entry_safe(bpage, tmp, head, list) {
+                        list_del_init(&bpage->list);
+                        free_buffer_page(bpage);
+                }
+                bpage = list_entry(head, struct buffer_page, list);
                 free_buffer_page(bpage);
         }
+
         kfree(cpu_buffer);
 }
 
@@ -735,6 +1231,7 @@ ring_buffer_free(struct ring_buffer *buffer)
 
         put_online_cpus();
 
+        kfree(buffer->buffers);
         free_cpumask_var(buffer->cpumask);
 
         kfree(buffer);
@@ -756,26 +1253,25 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
         struct list_head *p;
         unsigned i;
 
-        atomic_inc(&cpu_buffer->record_disabled);
-        synchronize_sched();
+        spin_lock_irq(&cpu_buffer->reader_lock);
+        rb_head_page_deactivate(cpu_buffer);
 
         for (i = 0; i < nr_pages; i++) {
-                if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
-                        return;
-                p = cpu_buffer->pages.next;
+                if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
+                        goto out;
+                p = cpu_buffer->pages->next;
                 bpage = list_entry(p, struct buffer_page, list);
                 list_del_init(&bpage->list);
                 free_buffer_page(bpage);
         }
-        if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
-                return;
+        if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
+                goto out;
 
         rb_reset_cpu(cpu_buffer);
-
         rb_check_pages(cpu_buffer);
 
-        atomic_dec(&cpu_buffer->record_disabled);
-
+out:
+        spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
 static void
@@ -786,22 +1282,22 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
         struct list_head *p;
         unsigned i;
 
-        atomic_inc(&cpu_buffer->record_disabled);
-        synchronize_sched();
+        spin_lock_irq(&cpu_buffer->reader_lock);
+        rb_head_page_deactivate(cpu_buffer);
 
         for (i = 0; i < nr_pages; i++) {
                 if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
-                        return;
+                        goto out;
                 p = pages->next;
                 bpage = list_entry(p, struct buffer_page, list);
                 list_del_init(&bpage->list);
-                list_add_tail(&bpage->list, &cpu_buffer->pages);
+                list_add_tail(&bpage->list, cpu_buffer->pages);
         }
         rb_reset_cpu(cpu_buffer);
-
         rb_check_pages(cpu_buffer);
 
-        atomic_dec(&cpu_buffer->record_disabled);
+out:
+        spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
 /**
@@ -809,11 +1305,6 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
  * @buffer: the buffer to resize.
  * @size: the new size.
  *
- * The tracer is responsible for making sure that the buffer is
- * not being used while changing the size.
- * Note: We may be able to change the above requirement by using
- *  RCU synchronizations.
- *
  * Minimum size is 2 * BUF_PAGE_SIZE.
  *
  * Returns -1 on failure.
@@ -845,6 +1336,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
         if (size == buffer_size)
                 return size;
 
+        atomic_inc(&buffer->record_disabled);
+
+        /* Make sure all writers are done with this buffer. */
+        synchronize_sched();
+
         mutex_lock(&buffer->mutex);
         get_online_cpus();
 
@@ -907,6 +1403,8 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
         put_online_cpus();
         mutex_unlock(&buffer->mutex);
 
+        atomic_dec(&buffer->record_disabled);
+
         return size;
 
  free_pages:
@@ -916,6 +1414,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
         }
         put_online_cpus();
         mutex_unlock(&buffer->mutex);
+        atomic_dec(&buffer->record_disabled);
         return -ENOMEM;
 
         /*
@@ -925,6 +1424,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
  out_fail:
         put_online_cpus();
         mutex_unlock(&buffer->mutex);
+        atomic_dec(&buffer->record_disabled);
         return -1;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
@@ -948,21 +1448,14 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
 }
 
 static inline struct ring_buffer_event *
-rb_head_event(struct ring_buffer_per_cpu *cpu_buffer)
-{
-        return __rb_page_index(cpu_buffer->head_page,
-                               cpu_buffer->head_page->read);
-}
-
-static inline struct ring_buffer_event *
 rb_iter_head_event(struct ring_buffer_iter *iter)
 {
         return __rb_page_index(iter->head_page, iter->head);
 }
 
-static inline unsigned rb_page_write(struct buffer_page *bpage)
+static inline unsigned long rb_page_write(struct buffer_page *bpage)
 {
-        return local_read(&bpage->write);
+        return local_read(&bpage->write) & RB_WRITE_MASK;
 }
 
 static inline unsigned rb_page_commit(struct buffer_page *bpage)
@@ -970,6 +1463,11 @@ static inline unsigned rb_page_commit(struct buffer_page *bpage)
         return local_read(&bpage->page->commit);
 }
 
+static inline unsigned long rb_page_entries(struct buffer_page *bpage)
+{
+        return local_read(&bpage->entries) & RB_WRITE_MASK;
+}
+
 /* Size is determined by what has been commited */
 static inline unsigned rb_page_size(struct buffer_page *bpage)
 {
@@ -982,22 +1480,6 @@ rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
         return rb_page_commit(cpu_buffer->commit_page);
 }
 
-static inline unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer)
-{
-        return rb_page_commit(cpu_buffer->head_page);
-}
-
-static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
-                               struct buffer_page **bpage)
-{
-        struct list_head *p = (*bpage)->list.next;
-
-        if (p == &cpu_buffer->pages)
-                p = p->next;
-
-        *bpage = list_entry(p, struct buffer_page, list);
-}
-
 static inline unsigned
 rb_event_index(struct ring_buffer_event *event)
 {
@@ -1023,6 +1505,8 @@ rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 static void
 rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 {
+        unsigned long max_count;
+
         /*
          * We only race with interrupts and NMIs on this CPU.
          * If we own the commit event, then we can commit
@@ -1032,9 +1516,16 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
          * assign the commit to the tail.
          */
  again:
+        max_count = cpu_buffer->buffer->pages * 100;
+
         while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
-                cpu_buffer->commit_page->page->commit =
-                        cpu_buffer->commit_page->write;
+                if (RB_WARN_ON(cpu_buffer, !(--max_count)))
+                        return;
+                if (RB_WARN_ON(cpu_buffer,
+                               rb_is_reader_page(cpu_buffer->tail_page)))
+                        return;
+                local_set(&cpu_buffer->commit_page->page->commit,
+                          rb_page_write(cpu_buffer->commit_page));
                 rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
                 cpu_buffer->write_stamp =
                         cpu_buffer->commit_page->page->time_stamp;
@@ -1043,8 +1534,12 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
         }
         while (rb_commit_index(cpu_buffer) !=
                rb_page_write(cpu_buffer->commit_page)) {
-                cpu_buffer->commit_page->page->commit =
-                        cpu_buffer->commit_page->write;
+
+                local_set(&cpu_buffer->commit_page->page->commit,
+                          rb_page_write(cpu_buffer->commit_page));
+                RB_WARN_ON(cpu_buffer,
+                           local_read(&cpu_buffer->commit_page->page->commit) &
+                           ~RB_WRITE_MASK);
                 barrier();
         }
 
@@ -1077,7 +1572,7 @@ static void rb_inc_iter(struct ring_buffer_iter *iter)
          * to the head page instead of next.
          */
         if (iter->head_page == cpu_buffer->reader_page)
-                iter->head_page = cpu_buffer->head_page;
+                iter->head_page = rb_set_head_page(cpu_buffer);
         else
                 rb_inc_page(cpu_buffer, &iter->head_page);
 
@@ -1085,6 +1580,25 @@ static void rb_inc_iter(struct ring_buffer_iter *iter)
         iter->head = 0;
 }
 
+/* Slow path, do not inline */
+static noinline struct ring_buffer_event *
+rb_add_time_stamp(struct ring_buffer_event *event, u64 delta)
+{
+        event->type_len = RINGBUF_TYPE_TIME_EXTEND;
+
+        /* Not the first event on the page? */
+        if (rb_event_index(event)) {
+                event->time_delta = delta & TS_MASK;
+                event->array[0] = delta >> TS_SHIFT;
+        } else {
+                /* nope, just zero it */
+                event->time_delta = 0;
+                event->array[0] = 0;
+        }
+
+        return skip_time_extend(event);
+}
+
 /**
  * ring_buffer_update_event - update event type and data
  * @event: the even to update
@@ -1097,28 +1611,188 @@ static void rb_inc_iter(struct ring_buffer_iter *iter)
  * data field.
  */
 static void
-rb_update_event(struct ring_buffer_event *event,
-                         unsigned type, unsigned length)
+rb_update_event(struct ring_buffer_per_cpu *cpu_buffer,
+                struct ring_buffer_event *event, unsigned length,
+                int add_timestamp, u64 delta)
 {
-        event->type_len = type;
+        /* Only a commit updates the timestamp */
+        if (unlikely(!rb_event_is_commit(cpu_buffer, event)))
+                delta = 0;
+
+        /*
+         * If we need to add a timestamp, then we
+         * add it to the start of the resevered space.
+         */
+        if (unlikely(add_timestamp)) {
+                event = rb_add_time_stamp(event, delta);
+                length -= RB_LEN_TIME_EXTEND;
+                delta = 0;
+        }
+
+        event->time_delta = delta;
+        length -= RB_EVNT_HDR_SIZE;
+        if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) {
+                event->type_len = 0;
+                event->array[0] = length;
+        } else
+                event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
+}
+
+/*
+ * rb_handle_head_page - writer hit the head page
+ *
+ * Returns: +1 to retry page
+ *           0 to continue
+ *          -1 on error
+ */
+static int
+rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
+                    struct buffer_page *tail_page,
+                    struct buffer_page *next_page)
+{
+        struct buffer_page *new_head;
+        int entries;
+        int type;
+        int ret;
+
+        entries = rb_page_entries(next_page);
+
+        /*
+         * The hard part is here. We need to move the head
+         * forward, and protect against both readers on
+         * other CPUs and writers coming in via interrupts.
+         */
+        type = rb_head_page_set_update(cpu_buffer, next_page, tail_page,
+                                       RB_PAGE_HEAD);
+
+        /*
+         * type can be one of four:
+         *  NORMAL - an interrupt already moved it for us
+         *  HEAD   - we are the first to get here.
+         *  UPDATE - we are the interrupt interrupting
+         *           a current move.
+         *  MOVED  - a reader on another CPU moved the next
+         *           pointer to its reader page. Give up
+         *           and try again.
+         */
 
         switch (type) {
+        case RB_PAGE_HEAD:
+                /*
+                 * We changed the head to UPDATE, thus
+                 * it is our responsibility to update
+                 * the counters.
+                 */
+                local_add(entries, &cpu_buffer->overrun);
 
-        case RINGBUF_TYPE_PADDING:
-        case RINGBUF_TYPE_TIME_EXTEND:
-        case RINGBUF_TYPE_TIME_STAMP:
+                /*
+                 * The entries will be zeroed out when we move the
+                 * tail page.
+                 */
+
+                /* still more to do */
                 break;
 
-        case 0:
-                length -= RB_EVNT_HDR_SIZE;
-                if (length > RB_MAX_SMALL_DATA)
-                        event->array[0] = length;
-                else
-                        event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
+        case RB_PAGE_UPDATE:
+                /*
+                 * This is an interrupt that interrupt the
+                 * previous update. Still more to do.
+                 */
                 break;
+        case RB_PAGE_NORMAL:
+                /*
+                 * An interrupt came in before the update
+                 * and processed this for us.
+                 * Nothing left to do.
+                 */
+                return 1;
+        case RB_PAGE_MOVED:
+                /*
+                 * The reader is on another CPU and just did
+                 * a swap with our next_page.
+                 * Try again.
+                 */
+                return 1;
         default:
-                BUG();
+                RB_WARN_ON(cpu_buffer, 1); /* WTF??? */
+                return -1;
+        }
+
+        /*
+         * Now that we are here, the old head pointer is
+         * set to UPDATE. This will keep the reader from
+         * swapping the head page with the reader page.
+         * The reader (on another CPU) will spin till
+         * we are finished.
+         *
+         * We just need to protect against interrupts
+         * doing the job. We will set the next pointer
+         * to HEAD. After that, we set the old pointer
+         * to NORMAL, but only if it was HEAD before.
+         * otherwise we are an interrupt, and only
+         * want the outer most commit to reset it.
+         */
+        new_head = next_page;
+        rb_inc_page(cpu_buffer, &new_head);
+
+        ret = rb_head_page_set_head(cpu_buffer, new_head, next_page,
+                                    RB_PAGE_NORMAL);
+
+        /*
+         * Valid returns are:
+         *  HEAD   - an interrupt came in and already set it.
+         *  NORMAL - One of two things:
+         *            1) We really set it.
+         *            2) A bunch of interrupts came in and moved
+         *               the page forward again.
+         */
+        switch (ret) {
+        case RB_PAGE_HEAD:
+        case RB_PAGE_NORMAL:
+                /* OK */
+                break;
+        default:
+                RB_WARN_ON(cpu_buffer, 1);
+                return -1;
         }
+
+        /*
+         * It is possible that an interrupt came in,
+         * set the head up, then more interrupts came in
+         * and moved it again. When we get back here,
+         * the page would have been set to NORMAL but we
+         * just set it back to HEAD.
+         *
+         * How do you detect this? Well, if that happened
+         * the tail page would have moved.
+         */
+        if (ret == RB_PAGE_NORMAL) {
+                /*
+                 * If the tail had moved passed next, then we need
+                 * to reset the pointer.
+                 */
+                if (cpu_buffer->tail_page != tail_page &&
+                    cpu_buffer->tail_page != next_page)
+                        rb_head_page_set_normal(cpu_buffer, new_head,
+                                                next_page,
+                                                RB_PAGE_HEAD);
+        }
+
+        /*
+         * If this was the outer most commit (the one that
+         * changed the original pointer from HEAD to UPDATE),
+         * then it is up to us to reset it to NORMAL.
+         */
+        if (type == RB_PAGE_HEAD) {
+                ret = rb_head_page_set_normal(cpu_buffer, next_page,
+                                              tail_page,
+                                              RB_PAGE_UPDATE);
+                if (RB_WARN_ON(cpu_buffer,
+                               ret != RB_PAGE_UPDATE))
+                        return -1;
+        }
+
+        return 0;
 }
 
 static unsigned rb_calculate_event_length(unsigned length)
@@ -1129,11 +1803,11 @@ static unsigned rb_calculate_event_length(unsigned length)
         if (!length)
                 length = 1;
 
-        if (length > RB_MAX_SMALL_DATA)
+        if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
                 length += sizeof(event.array[0]);
 
         length += RB_EVNT_HDR_SIZE;
-        length = ALIGN(length, RB_ALIGNMENT);
+        length = ALIGN(length, RB_ARCH_ALIGNMENT);
 
         return length;
 }
@@ -1150,6 +1824,14 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
          * must fill the old tail_page with padding.
          */
         if (tail >= BUF_PAGE_SIZE) {
+                /*
+                 * If the page was filled, then we still need
+                 * to update the real_end. Reset it to zero
+                 * and the reader will ignore it.
+                 */
+                if (tail == BUF_PAGE_SIZE)
+                        tail_page->real_end = 0;
+
                 local_sub(length, &tail_page->write);
                 return;
         }
@@ -1158,6 +1840,13 @@ 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
@@ -1184,111 +1873,108 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
         event->type_len = RINGBUF_TYPE_PADDING;
         /* time delta must be non zero */
         event->time_delta = 1;
-        /* Account for this as an entry */
-        local_inc(&tail_page->entries);
-        local_inc(&cpu_buffer->entries);
 
         /* Set write to end of buffer */
         length = (tail + length) - BUF_PAGE_SIZE;
         local_sub(length, &tail_page->write);
 }
 
-static struct ring_buffer_event *
+/*
+ * This is the slow path, force gcc not to inline it.
+ */
+static noinline struct ring_buffer_event *
 rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
              unsigned long length, unsigned long tail,
-             struct buffer_page *commit_page,
-             struct buffer_page *tail_page, u64 *ts)
+             struct buffer_page *tail_page, u64 ts)
 {
-        struct buffer_page *next_page, *head_page, *reader_page;
+        struct buffer_page *commit_page = cpu_buffer->commit_page;
         struct ring_buffer *buffer = cpu_buffer->buffer;
-        bool lock_taken = false;
-        unsigned long flags;
+        struct buffer_page *next_page;
+        int ret;
 
         next_page = tail_page;
 
-        local_irq_save(flags);
-        /*
-         * Since the write to the buffer is still not
-         * fully lockless, we must be careful with NMIs.
-         * The locks in the writers are taken when a write
-         * crosses to a new page. The locks protect against
-         * races with the readers (this will soon be fixed
-         * with a lockless solution).
-         *
-         * Because we can not protect against NMIs, and we
-         * want to keep traces reentrant, we need to manage
-         * what happens when we are in an NMI.
-         *
-         * NMIs can happen after we take the lock.
-         * If we are in an NMI, only take the lock
-         * if it is not already taken. Otherwise
-         * simply fail.
-         */
-        if (unlikely(in_nmi())) {
-                if (!__raw_spin_trylock(&cpu_buffer->lock)) {
-                        cpu_buffer->nmi_dropped++;
-                        goto out_reset;
-                }
-        } else
-                __raw_spin_lock(&cpu_buffer->lock);
-
-        lock_taken = true;
-
         rb_inc_page(cpu_buffer, &next_page);
 
-        head_page = cpu_buffer->head_page;
-        reader_page = cpu_buffer->reader_page;
-
-        /* we grabbed the lock before incrementing */
-        if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
-                goto out_reset;
-
         /*
          * If for some reason, we had an interrupt storm that made
          * it all the way around the buffer, bail, and warn
          * about it.
          */
         if (unlikely(next_page == commit_page)) {
-                cpu_buffer->commit_overrun++;
+                local_inc(&cpu_buffer->commit_overrun);
                 goto out_reset;
         }
 
-        if (next_page == head_page) {
-                if (!(buffer->flags & RB_FL_OVERWRITE))
-                        goto out_reset;
-
-                /* tail_page has not moved yet? */
-                if (tail_page == cpu_buffer->tail_page) {
-                        /* count overflows */
-                        cpu_buffer->overrun +=
-                                local_read(&head_page->entries);
+        /*
+         * This is where the fun begins!
+         *
+         * We are fighting against races between a reader that
+         * could be on another CPU trying to swap its reader
+         * page with the buffer head.
+         *
+         * We are also fighting against interrupts coming in and
+         * moving the head or tail on us as well.
+         *
+         * If the next page is the head page then we have filled
+         * the buffer, unless the commit page is still on the
+         * reader page.
+         */
+        if (rb_is_head_page(cpu_buffer, next_page, &tail_page->list)) {
 
-                        rb_inc_page(cpu_buffer, &head_page);
-                        cpu_buffer->head_page = head_page;
-                        cpu_buffer->head_page->read = 0;
+                /*
+                 * If the commit is not on the reader page, then
+                 * move the header page.
+                 */
+                if (!rb_is_reader_page(cpu_buffer->commit_page)) {
+                        /*
+                         * If we are not in overwrite mode,
+                         * this is easy, just stop here.
+                         */
+                        if (!(buffer->flags & RB_FL_OVERWRITE))
+                                goto out_reset;
+
+                        ret = rb_handle_head_page(cpu_buffer,
+                                                  tail_page,
+                                                  next_page);
+                        if (ret < 0)
+                                goto out_reset;
+                        if (ret)
+                                goto out_again;
+                } else {
+                        /*
+                         * We need to be careful here too. The
+                         * commit page could still be on the reader
+                         * page. We could have a small buffer, and
+                         * have filled up the buffer with events
+                         * from interrupts and such, and wrapped.
+                         *
+                         * Note, if the tail page is also the on the
+                         * reader_page, we let it move out.
+                         */
+                        if (unlikely((cpu_buffer->commit_page !=
+                                      cpu_buffer->tail_page) &&
+                                     (cpu_buffer->commit_page ==
+                                      cpu_buffer->reader_page))) {
+                                local_inc(&cpu_buffer->commit_overrun);
+                                goto out_reset;
+                        }
                 }
         }
 
-        /*
-         * If the tail page is still the same as what we think
-         * it is, then it is up to us to update the tail
-         * pointer.
-         */
-        if (tail_page == cpu_buffer->tail_page) {
-                local_set(&next_page->write, 0);
-                local_set(&next_page->entries, 0);
-                local_set(&next_page->page->commit, 0);
-                cpu_buffer->tail_page = next_page;
-
-                /* reread the time stamp */
-                *ts = rb_time_stamp(buffer, cpu_buffer->cpu);
-                cpu_buffer->tail_page->page->time_stamp = *ts;
+        ret = rb_tail_page_update(cpu_buffer, tail_page, next_page);
+        if (ret) {
+                /*
+                 * Nested commits always have zero deltas, so
+                 * just reread the time stamp
+                 */
+                ts = rb_time_stamp(buffer);
+                next_page->page->time_stamp = ts;
         }
 
-        rb_reset_tail(cpu_buffer, tail_page, tail, length);
+ out_again:
 
-        __raw_spin_unlock(&cpu_buffer->lock);
-        local_irq_restore(flags);
+        rb_reset_tail(cpu_buffer, tail_page, tail, length);
 
         /* fail and let the caller try again */
         return ERR_PTR(-EAGAIN);
@@ -1297,48 +1983,52 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
         /* reset write */
         rb_reset_tail(cpu_buffer, tail_page, tail, length);
 
-        if (likely(lock_taken))
-                __raw_spin_unlock(&cpu_buffer->lock);
-        local_irq_restore(flags);
         return NULL;
 }
 
 static struct ring_buffer_event *
 __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
-                  unsigned type, unsigned long length, u64 *ts)
+                  unsigned long length, u64 ts,
+                  u64 delta, int add_timestamp)
 {
-        struct buffer_page *tail_page, *commit_page;
+        struct buffer_page *tail_page;
         struct ring_buffer_event *event;
         unsigned long tail, write;
 
-        commit_page = cpu_buffer->commit_page;
-        /* we just need to protect against interrupts */
-        barrier();
+        /*
+         * If the time delta since the last event is too big to
+         * hold in the time field of the event, then we append a
+         * TIME EXTEND event ahead of the data event.
+         */
+        if (unlikely(add_timestamp))
+                length += RB_LEN_TIME_EXTEND;
+
         tail_page = cpu_buffer->tail_page;
         write = local_add_return(length, &tail_page->write);
+
+        /* set write to only the index of the write */
+        write &= RB_WRITE_MASK;
         tail = write - length;
 
         /* See if we shot pass the end of this buffer page */
-        if (write > BUF_PAGE_SIZE)
+        if (unlikely(write > BUF_PAGE_SIZE))
                 return rb_move_tail(cpu_buffer, length, tail,
-                                    commit_page, tail_page, ts);
+                                    tail_page, ts);
 
         /* We reserved something on the buffer */
 
         event = __rb_page_index(tail_page, tail);
         kmemcheck_annotate_bitfield(event, bitfield);
-        rb_update_event(event, type, length);
+        rb_update_event(cpu_buffer, event, length, add_timestamp, delta);
 
-        /* The passed in type is zero for DATA */
-        if (likely(!type))
-                local_inc(&tail_page->entries);
+        local_inc(&tail_page->entries);
 
         /*
          * If this is the first commit on the page, then update
          * its timestamp.
          */
         if (!tail)
-                tail_page->page->time_stamp = *ts;
+                tail_page->page->time_stamp = ts;
 
         return event;
 }
@@ -1353,19 +2043,23 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
         unsigned long addr;
 
         new_index = rb_event_index(event);
-        old_index = new_index + rb_event_length(event);
+        old_index = new_index + rb_event_ts_length(event);
         addr = (unsigned long)event;
         addr &= PAGE_MASK;
 
         bpage = cpu_buffer->tail_page;
 
         if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
+                unsigned long write_mask =
+                        local_read(&bpage->write) & ~RB_WRITE_MASK;
                 /*
                  * This is on the tail page. It is possible that
                  * a write could come in and move the tail page
                  * and write to the next page. That is fine
                  * because we just shorten what is on this page.
                  */
+                old_index += write_mask;
+                new_index += write_mask;
                 index = local_cmpxchg(&bpage->write, old_index, new_index);
                 if (index == old_index)
                         return 1;
@@ -1375,80 +2069,13 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
         return 0;
 }
 
-static int
-rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
-                  u64 *ts, u64 *delta)
-{
-        struct ring_buffer_event *event;
-        static int once;
-        int ret;
-
-        if (unlikely(*delta > (1ULL << 59) && !once++)) {
-                printk(KERN_WARNING "Delta way too big! %llu"
-                       " ts=%llu write stamp = %llu\n",
-                       (unsigned long long)*delta,
-                       (unsigned long long)*ts,
-                       (unsigned long long)cpu_buffer->write_stamp);
-                WARN_ON(1);
-        }
-
-        /*
-         * The delta is too big, we to add a
-         * new timestamp.
-         */
-        event = __rb_reserve_next(cpu_buffer,
-                                  RINGBUF_TYPE_TIME_EXTEND,
-                                  RB_LEN_TIME_EXTEND,
-                                  ts);
-        if (!event)
-                return -EBUSY;
-
-        if (PTR_ERR(event) == -EAGAIN)
-                return -EAGAIN;
-
-        /* Only a commited time event can update the write stamp */
-        if (rb_event_is_commit(cpu_buffer, event)) {
-                /*
-                 * If this is the first on the page, then it was
-                 * updated with the page itself. Try to discard it
-                 * and if we can't just make it zero.
-                 */
-                if (rb_event_index(event)) {
-                        event->time_delta = *delta & TS_MASK;
-                        event->array[0] = *delta >> TS_SHIFT;
-                } else {
-                        /* try to discard, since we do not need this */
-                        if (!rb_try_to_discard(cpu_buffer, event)) {
-                                /* nope, just zero it */
-                                event->time_delta = 0;
-                                event->array[0] = 0;
-                        }
-                }
-                cpu_buffer->write_stamp = *ts;
-                /* let the caller know this was the commit */
-                ret = 1;
-        } else {
-                /* Try to discard the event */
-                if (!rb_try_to_discard(cpu_buffer, event)) {
-                        /* Darn, this is just wasted space */
-                        event->time_delta = 0;
-                        event->array[0] = 0;
-                }
-                ret = 0;
-        }
-
-        *delta = 0;
-
-        return ret;
-}
-
 static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer)
 {
         local_inc(&cpu_buffer->committing);
         local_inc(&cpu_buffer->commits);
 }
 
-static void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
+static inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
 {
         unsigned long commits;
 
@@ -1481,18 +2108,38 @@ static void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
 }
 
 static struct ring_buffer_event *
-rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
+rb_reserve_next_event(struct ring_buffer *buffer,
+                      struct ring_buffer_per_cpu *cpu_buffer,
                       unsigned long length)
 {
         struct ring_buffer_event *event;
-        u64 ts, delta = 0;
-        int commit = 0;
+        u64 ts, delta;
         int nr_loops = 0;
+        int add_timestamp;
+        u64 diff;
 
         rb_start_commit(cpu_buffer);
 
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
+        /*
+         * Due to the ability to swap a cpu buffer from a buffer
+         * it is possible it was swapped before we committed.
+         * (committing stops a swap). We check for it here and
+         * if it happened, we have to fail the write.
+         */
+        barrier();
+        if (unlikely(ACCESS_ONCE(cpu_buffer->buffer) != buffer)) {
+                local_dec(&cpu_buffer->committing);
+                local_dec(&cpu_buffer->commits);
+                return NULL;
+        }
+#endif
+
         length = rb_calculate_event_length(length);
  again:
+        add_timestamp = 0;
+        delta = 0;
+
         /*
          * We allow for interrupts to reenter here and do a trace.
          * If one does, it will cause this original code to loop
@@ -1505,57 +2152,33 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
         if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
                 goto out_fail;
 
-        ts = rb_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
+        ts = rb_time_stamp(cpu_buffer->buffer);
+        diff = ts - cpu_buffer->write_stamp;
 
-        /*
-         * Only the first commit can update the timestamp.
-         * Yes there is a race here. If an interrupt comes in
-         * just after the conditional and it traces too, then it
-         * will also check the deltas. More than one timestamp may
-         * also be made. But only the entry that did the actual
-         * commit will be something other than zero.
-         */
-        if (likely(cpu_buffer->tail_page == cpu_buffer->commit_page &&
-                   rb_page_write(cpu_buffer->tail_page) ==
-                   rb_commit_index(cpu_buffer))) {
-                u64 diff;
-
-                diff = ts - cpu_buffer->write_stamp;
-
-                /* make sure this diff is calculated here */
-                barrier();
-
-                /* Did the write stamp get updated already? */
-                if (unlikely(ts < cpu_buffer->write_stamp))
-                        goto get_event;
+        /* make sure this diff is calculated here */
+        barrier();
 
+        /* Did the write stamp get updated already? */
+        if (likely(ts >= cpu_buffer->write_stamp)) {
                 delta = diff;
                 if (unlikely(test_time_stamp(delta))) {
-
-                        commit = rb_add_time_stamp(cpu_buffer, &ts, &delta);
-                        if (commit == -EBUSY)
-                                goto out_fail;
-
-                        if (commit == -EAGAIN)
-                                goto again;
-
-                        RB_WARN_ON(cpu_buffer, commit < 0);
+                        WARN_ONCE(delta > (1ULL << 59),
+                                  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
+                                  (unsigned long long)delta,
+                                  (unsigned long long)ts,
+                                  (unsigned long long)cpu_buffer->write_stamp);
+                        add_timestamp = 1;
                 }
         }
 
- get_event:
-        event = __rb_reserve_next(cpu_buffer, 0, length, &ts);
+        event = __rb_reserve_next(cpu_buffer, length, ts,
+                                  delta, add_timestamp);
         if (unlikely(PTR_ERR(event) == -EAGAIN))
                 goto again;
 
         if (!event)
                 goto out_fail;
 
-        if (!rb_event_is_commit(cpu_buffer, event))
-                delta = 0;
-
-        event->time_delta = delta;
-
         return event;
 
  out_fail:
@@ -1563,15 +2186,13 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
         return NULL;
 }
 
+#ifdef CONFIG_TRACING
+
 #define TRACE_RECURSIVE_DEPTH 16
 
-static int trace_recursive_lock(void)
+/* Keep this code out of the fast path cache */
+static noinline void trace_recursive_fail(void)
 {
-        current->trace_recursion++;
-
-        if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
-                return 0;
-
         /* Disable all tracing before we do anything else */
         tracing_off_permanent();
 
@@ -1583,17 +2204,33 @@ static int trace_recursive_lock(void)
                     in_nmi());
 
         WARN_ON_ONCE(1);
+}
+
+static inline int trace_recursive_lock(void)
+{
+        current->trace_recursion++;
+
+        if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+                return 0;
+
+        trace_recursive_fail();
+
         return -1;
 }
 
-static void trace_recursive_unlock(void)
+static inline void trace_recursive_unlock(void)
 {
         WARN_ON_ONCE(!current->trace_recursion);
 
         current->trace_recursion--;
 }
 
-static DEFINE_PER_CPU(int, rb_need_resched);
+#else
+
+#define trace_recursive_lock()          (0)
+#define trace_recursive_unlock()        do { } while (0)
+
+#endif
 
 /**
  * ring_buffer_lock_reserve - reserve a part of the buffer
@@ -1615,16 +2252,16 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
         struct ring_buffer_event *event;
-        int cpu, resched;
+        int cpu;
 
         if (ring_buffer_flags != RB_BUFFERS_ON)
                 return NULL;
 
-        if (atomic_read(&buffer->record_disabled))
-                return NULL;
-
         /* If we are tracing schedule, we don't want to recurse */
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
+
+        if (atomic_read(&buffer->record_disabled))
+                goto out_nocheck;
 
         if (trace_recursive_lock())
                 goto out_nocheck;
@@ -1642,41 +2279,54 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
         if (length > BUF_MAX_DATA_SIZE)
                 goto out;
 
-        event = rb_reserve_next_event(cpu_buffer, length);
+        event = rb_reserve_next_event(buffer, cpu_buffer, length);
         if (!event)
                 goto out;
 
-        /*
-         * Need to store resched state on this cpu.
-         * Only the first needs to.
-         */
-
-        if (preempt_count() == 1)
-                per_cpu(rb_need_resched, cpu) = resched;
-
         return event;
 
  out:
         trace_recursive_unlock();
 
  out_nocheck:
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
         return NULL;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
 
-static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
+static void
+rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer,
                       struct ring_buffer_event *event)
 {
-        local_inc(&cpu_buffer->entries);
+        u64 delta;
 
         /*
          * The event first in the commit queue updates the
          * time stamp.
          */
-        if (rb_event_is_commit(cpu_buffer, event))
-                cpu_buffer->write_stamp += event->time_delta;
+        if (rb_event_is_commit(cpu_buffer, event)) {
+                /*
+                 * A commit event that is first on a page
+                 * updates the write timestamp with the page stamp
+                 */
+                if (!rb_event_index(event))
+                        cpu_buffer->write_stamp =
+                                cpu_buffer->commit_page->page->time_stamp;
+                else if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
+                        delta = event->array[0];
+                        delta <<= TS_SHIFT;
+                        delta += event->time_delta;
+                        cpu_buffer->write_stamp += delta;
+                } else
+                        cpu_buffer->write_stamp += event->time_delta;
+        }
+}
 
+static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
+                      struct ring_buffer_event *event)
+{
+        local_inc(&cpu_buffer->entries);
+        rb_update_write_stamp(cpu_buffer, event);
         rb_end_commit(cpu_buffer);
 }
 
@@ -1701,13 +2351,7 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
         trace_recursive_unlock();
 
-        /*
-         * Only the last preempt count needs to restore preemption.
-         */
-        if (preempt_count() == 1)
-                ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
-        else
-                preempt_enable_no_resched_notrace();
+        preempt_enable_notrace();
 
         return 0;
 }
@@ -1715,6 +2359,9 @@ EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
 
 static inline void rb_event_discard(struct ring_buffer_event *event)
 {
+        if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
+                event = skip_time_extend(event);
+
         /* array[0] holds the actual length for the discarded event */
         event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE;
         event->type_len = RINGBUF_TYPE_PADDING;
@@ -1723,32 +2370,57 @@ static inline void rb_event_discard(struct ring_buffer_event *event)
                 event->time_delta = 1;
 }
 
-/**
- * ring_buffer_event_discard - discard any event in the ring buffer
- * @event: the event to discard
- *
- * Sometimes a event that is in the ring buffer needs to be ignored.
- * This function lets the user discard an event in the ring buffer
- * and then that event will not be read later.
- *
- * Note, it is up to the user to be careful with this, and protect
- * against races. If the user discards an event that has been consumed
- * it is possible that it could corrupt the ring buffer.
+/*
+ * Decrement the entries to the page that an event is on.
+ * The event does not even need to exist, only the pointer
+ * to the page it is on. This may only be called before the commit
+ * takes place.
  */
-void ring_buffer_event_discard(struct ring_buffer_event *event)
+static inline void
+rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer,
+                   struct ring_buffer_event *event)
 {
-        rb_event_discard(event);
+        unsigned long addr = (unsigned long)event;
+        struct buffer_page *bpage = cpu_buffer->commit_page;
+        struct buffer_page *start;
+
+        addr &= PAGE_MASK;
+
+        /* Do the likely case first */
+        if (likely(bpage->page == (void *)addr)) {
+                local_dec(&bpage->entries);
+                return;
+        }
+
+        /*
+         * Because the commit page may be on the reader page we
+         * start with the next page and check the end loop there.
+         */
+        rb_inc_page(cpu_buffer, &bpage);
+        start = bpage;
+        do {
+                if (bpage->page == (void *)addr) {
+                        local_dec(&bpage->entries);
+                        return;
+                }
+                rb_inc_page(cpu_buffer, &bpage);
+        } while (bpage != start);
+
+        /* commit not part of this buffer?? */
+        RB_WARN_ON(cpu_buffer, 1);
 }
-EXPORT_SYMBOL_GPL(ring_buffer_event_discard);
 
 /**
  * ring_buffer_commit_discard - discard an event that has not been committed
  * @buffer: the ring buffer
  * @event: non committed event to discard
  *
- * This is similar to ring_buffer_event_discard but must only be
- * performed on an event that has not been committed yet. The difference
- * is that this will also try to free the event from the ring buffer
+ * Sometimes an event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * This function only works if it is called before the the item has been
+ * committed. It will try to free the event from the ring buffer
  * if another event has not been added behind it.
  *
  * If another event has been added behind it, it will set the event
@@ -1776,26 +2448,21 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
          */
         RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing));
 
-        if (!rb_try_to_discard(cpu_buffer, event))
+        rb_decrement_entry(cpu_buffer, event);
+        if (rb_try_to_discard(cpu_buffer, event))
                 goto out;
 
         /*
          * The commit is still visible by the reader, so we
-         * must increment entries.
+         * must still update the timestamp.
          */
-        local_inc(&cpu_buffer->entries);
+        rb_update_write_stamp(cpu_buffer, event);
  out:
         rb_end_commit(cpu_buffer);
 
         trace_recursive_unlock();
 
-        /*
-         * Only the last preempt count needs to restore preemption.
-         */
-        if (preempt_count() == 1)
-                ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
-        else
-                preempt_enable_no_resched_notrace();
+        preempt_enable_notrace();
 
 }
 EXPORT_SYMBOL_GPL(ring_buffer_discard_commit);
@@ -1821,15 +2488,15 @@ int ring_buffer_write(struct ring_buffer *buffer,
         struct ring_buffer_event *event;
         void *body;
         int ret = -EBUSY;
-        int cpu, resched;
+        int cpu;
 
         if (ring_buffer_flags != RB_BUFFERS_ON)
                 return -EBUSY;
 
-        if (atomic_read(&buffer->record_disabled))
-                return -EBUSY;
+        preempt_disable_notrace();
 
-        resched = ftrace_preempt_disable();
+        if (atomic_read(&buffer->record_disabled))
+                goto out;
 
         cpu = raw_smp_processor_id();
 
@@ -1844,7 +2511,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
         if (length > BUF_MAX_DATA_SIZE)
                 goto out;
 
-        event = rb_reserve_next_event(cpu_buffer, length);
+        event = rb_reserve_next_event(buffer, cpu_buffer, length);
         if (!event)
                 goto out;
 
@@ -1856,7 +2523,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
         ret = 0;
  out:
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 
         return ret;
 }
@@ -1865,9 +2532,13 @@ EXPORT_SYMBOL_GPL(ring_buffer_write);
 static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
 {
         struct buffer_page *reader = cpu_buffer->reader_page;
-        struct buffer_page *head = cpu_buffer->head_page;
+        struct buffer_page *head = rb_set_head_page(cpu_buffer);
         struct buffer_page *commit = cpu_buffer->commit_page;
 
+        /* In case of error, head will be NULL */
+        if (unlikely(!head))
+                return 1;
+
         return reader->read == rb_page_commit(reader) &&
                 (commit == reader ||
                  (commit == head &&
@@ -1894,7 +2565,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable);
  * @buffer: The ring buffer to enable writes
  *
  * Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
  */
 void ring_buffer_record_enable(struct ring_buffer *buffer)
 {
@@ -1930,7 +2601,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);
  * @cpu: The CPU to enable.
  *
  * Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
  */
 void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
 {
@@ -1944,6 +2615,19 @@ void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);
 
+/*
+ * The total entries in the ring buffer is the running counter
+ * of entries entered into the ring buffer, minus the sum of
+ * the entries read from the ring buffer and the number of
+ * entries that were overwritten.
+ */
+static inline unsigned long
+rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        return local_read(&cpu_buffer->entries) -
+                (local_read(&cpu_buffer->overrun) + cpu_buffer->read);
+}
+
 /**
  * ring_buffer_entries_cpu - get the number of entries in a cpu buffer
  * @buffer: The ring buffer
@@ -1952,16 +2636,13 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
-        unsigned long ret;
 
         if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return 0;
 
         cpu_buffer = buffer->buffers[cpu];
-        ret = (local_read(&cpu_buffer->entries) - cpu_buffer->overrun)
-                - cpu_buffer->read;
 
-        return ret;
+        return rb_num_of_entries(cpu_buffer);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
 
@@ -1979,33 +2660,13 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
                 return 0;
 
         cpu_buffer = buffer->buffers[cpu];
-        ret = cpu_buffer->overrun;
+        ret = local_read(&cpu_buffer->overrun);
 
         return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
 
 /**
- * ring_buffer_nmi_dropped_cpu - get the number of nmis that were dropped
- * @buffer: The ring buffer
- * @cpu: The per CPU buffer to get the number of overruns from
- */
-unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu)
-{
-        struct ring_buffer_per_cpu *cpu_buffer;
-        unsigned long ret;
-
-        if (!cpumask_test_cpu(cpu, buffer->cpumask))
-                return 0;
-
-        cpu_buffer = buffer->buffers[cpu];
-        ret = cpu_buffer->nmi_dropped;
-
-        return ret;
-}
-EXPORT_SYMBOL_GPL(ring_buffer_nmi_dropped_cpu);
-
-/**
  * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
  * @buffer: The ring buffer
  * @cpu: The per CPU buffer to get the number of overruns from
@@ -2020,7 +2681,7 @@ ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
                 return 0;
 
         cpu_buffer = buffer->buffers[cpu];
-        ret = cpu_buffer->commit_overrun;
+        ret = local_read(&cpu_buffer->commit_overrun);
 
         return ret;
 }
@@ -2042,8 +2703,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
         /* if you care about this being correct, lock the buffer */
         for_each_buffer_cpu(buffer, cpu) {
                 cpu_buffer = buffer->buffers[cpu];
-                entries += (local_read(&cpu_buffer->entries) -
-                            cpu_buffer->overrun) - cpu_buffer->read;
+                entries += rb_num_of_entries(cpu_buffer);
         }
 
         return entries;
@@ -2051,7 +2711,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
 EXPORT_SYMBOL_GPL(ring_buffer_entries);
 
 /**
- * ring_buffer_overrun_cpu - get the number of overruns in buffer
+ * ring_buffer_overruns - get the number of overruns in buffer
  * @buffer: The ring buffer
  *
  * Returns the total number of overruns in the ring buffer
@@ -2066,7 +2726,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
         /* if you care about this being correct, lock the buffer */
         for_each_buffer_cpu(buffer, cpu) {
                 cpu_buffer = buffer->buffers[cpu];
-                overruns += cpu_buffer->overrun;
+                overruns += local_read(&cpu_buffer->overrun);
         }
 
         return overruns;
@@ -2079,8 +2739,10 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 
         /* Iterator usage is expected to have record disabled */
         if (list_empty(&cpu_buffer->reader_page->list)) {
-                iter->head_page = cpu_buffer->head_page;
-                iter->head = cpu_buffer->head_page->read;
+                iter->head_page = rb_set_head_page(cpu_buffer);
+                if (unlikely(!iter->head_page))
+                        return;
+                iter->head = iter->head_page->read;
         } else {
                 iter->head_page = cpu_buffer->reader_page;
                 iter->head = cpu_buffer->reader_page->read;
@@ -2089,6 +2751,8 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
                 iter->read_stamp = cpu_buffer->read_stamp;
         else
                 iter->read_stamp = iter->head_page->page->time_stamp;
+        iter->cache_reader_page = cpu_buffer->reader_page;
+        iter->cache_read = cpu_buffer->read;
 }
 
 /**
@@ -2195,11 +2859,13 @@ 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;
 
         local_irq_save(flags);
-        __raw_spin_lock(&cpu_buffer->lock);
+        arch_spin_lock(&cpu_buffer->lock);
 
  again:
         /*
@@ -2230,39 +2896,83 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
                 goto out;
 
         /*
-         * Splice the empty reader page into the list around the head.
          * Reset the reader page to size zero.
          */
-
-        reader = cpu_buffer->head_page;
-        cpu_buffer->reader_page->list.next = reader->list.next;
-        cpu_buffer->reader_page->list.prev = reader->list.prev;
-
         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:
+        /*
+         * Splice the empty reader page into the list around the head.
+         */
+        reader = rb_set_head_page(cpu_buffer);
+        cpu_buffer->reader_page->list.next = rb_list_head(reader->list.next);
+        cpu_buffer->reader_page->list.prev = reader->list.prev;
+
+        /*
+         * cpu_buffer->pages just needs to point to the buffer, it
+         *  has no specific buffer page to point to. Lets move it out
+         *  of our way so we don't accidently swap it.
+         */
+        cpu_buffer->pages = reader->list.prev;
 
-        /* Make the reader page now replace the head */
-        reader->list.prev->next = &cpu_buffer->reader_page->list;
-        reader->list.next->prev = &cpu_buffer->reader_page->list;
+        /* The reader page will be pointing to the new head */
+        rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);
 
         /*
-         * If the tail is on the reader, then we must set the head
-         * to the inserted page, otherwise we set it one before.
+         * 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.
          */
-        cpu_buffer->head_page = cpu_buffer->reader_page;
+        smp_mb();
+        overwrite = local_read(&(cpu_buffer->overrun));
 
-        if (cpu_buffer->commit_page != reader)
-                rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
+        /*
+         * Here's the tricky part.
+         *
+         * We need to move the pointer past the header page.
+         * But we can only do that if a writer is not currently
+         * moving it. The page before the header page has the
+         * flag bit '1' set if it is pointing to the page we want.
+         * but if the writer is in the process of moving it
+         * than it will be '2' or already moved '0'.
+         */
+
+        ret = rb_head_page_replace(reader, cpu_buffer->reader_page);
+
+        /*
+         * If we did not convert it, then we must try again.
+         */
+        if (!ret)
+                goto spin;
+
+        /*
+         * Yeah! We succeeded in replacing the page.
+         *
+         * Now make the new head point back to the reader page.
+         */
+        rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list;
+        rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
 
         /* Finally update the reader page to the new head */
         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:
-        __raw_spin_unlock(&cpu_buffer->lock);
+        arch_spin_unlock(&cpu_buffer->lock);
         local_irq_restore(flags);
 
         return reader;
@@ -2282,8 +2992,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
         event = rb_reader_event(cpu_buffer);
 
-        if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX
-                        || rb_discarded_event(event))
+        if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
                 cpu_buffer->read++;
 
         rb_update_read_stamp(cpu_buffer, event);
@@ -2294,13 +3003,11 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 
 static void rb_advance_iter(struct ring_buffer_iter *iter)
 {
-        struct ring_buffer *buffer;
         struct ring_buffer_per_cpu *cpu_buffer;
         struct ring_buffer_event *event;
         unsigned length;
 
         cpu_buffer = iter->cpu_buffer;
-        buffer = cpu_buffer->buffer;
 
         /*
          * Check if we are at the end of the buffer.
@@ -2336,24 +3043,27 @@ 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 *buffer, int cpu, u64 *ts)
+rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
+               unsigned long *lost_events)
 {
-        struct ring_buffer_per_cpu *cpu_buffer;
         struct ring_buffer_event *event;
         struct buffer_page *reader;
         int nr_loops = 0;
 
-        cpu_buffer = buffer->buffers[cpu];
-
  again:
         /*
-         * We repeat when a timestamp is encountered. It is possible
-         * to get multiple timestamps from an interrupt entering just
-         * as one timestamp is about to be written, or from discarded
-         * commits. The most that we can have is the number on a single page.
+         * We repeat when a time extend is encountered.
+         * Since the time extend is always attached to a data event,
+         * we should never loop more than once.
+         * (We never hit the following condition more than twice).
          */
-        if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
+        if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2))
                 return NULL;
 
         reader = rb_get_reader_page(cpu_buffer);
@@ -2374,7 +3084,6 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
                  * the box. Return the padding, and we will release
                  * the current locks, and try again.
                  */
-                rb_advance_reader(cpu_buffer);
                 return event;
 
         case RINGBUF_TYPE_TIME_EXTEND:
@@ -2390,9 +3099,11 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
         case RINGBUF_TYPE_DATA:
                 if (ts) {
                         *ts = cpu_buffer->read_stamp + event->time_delta;
-                        ring_buffer_normalize_time_stamp(buffer,
+                        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:
@@ -2411,27 +3122,39 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
         struct ring_buffer_event *event;
         int nr_loops = 0;
 
-        if (ring_buffer_iter_empty(iter))
-                return NULL;
-
         cpu_buffer = iter->cpu_buffer;
         buffer = cpu_buffer->buffer;
 
+        /*
+         * Check if someone performed a consuming read to
+         * the buffer. A consuming read invalidates the iterator
+         * and we need to reset the iterator in this case.
+         */
+        if (unlikely(iter->cache_read != cpu_buffer->read ||
+                     iter->cache_reader_page != cpu_buffer->reader_page))
+                rb_iter_reset(iter);
+
  again:
+        if (ring_buffer_iter_empty(iter))
+                return NULL;
+
         /*
-         * We repeat when a timestamp is encountered.
-         * We can get multiple timestamps by nested interrupts or also
-         * if filtering is on (discarding commits). Since discarding
-         * commits can be frequent we can get a lot of timestamps.
-         * But we limit them by not adding timestamps if they begin
-         * at the start of a page.
+         * We repeat when a time extend is encountered.
+         * Since the time extend is always attached to a data event,
+         * we should never loop more than once.
+         * (We never hit the following condition more than twice).
          */
-        if (RB_WARN_ON(cpu_buffer, ++nr_loops > RB_TIMESTAMPS_PER_PAGE))
+        if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2))
                 return NULL;
 
         if (rb_per_cpu_empty(cpu_buffer))
                 return NULL;
 
+        if (iter->head >= local_read(&iter->head_page->page->commit)) {
+                rb_inc_iter(iter);
+                goto again;
+        }
+
         event = rb_iter_head_event(iter);
 
         switch (event->type_len) {
@@ -2477,7 +3200,7 @@ static inline int rb_ok_to_lock(void)
          * buffer too. A one time deal is all you get from reading
          * the ring buffer from an NMI.
          */
-        if (likely(!in_nmi() && !oops_in_progress))
+        if (likely(!in_nmi()))
                 return 1;
 
         tracing_off_permanent();
@@ -2489,12 +3212,14 @@ 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;
@@ -2509,15 +3234,15 @@ 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(buffer, cpu, 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)
                 spin_unlock(&cpu_buffer->reader_lock);
         local_irq_restore(flags);
 
-        if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-                cpu_relax();
+        if (event && event->type_len == RINGBUF_TYPE_PADDING)
                 goto again;
-        }
 
         return event;
 }
@@ -2542,10 +3267,8 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
         event = rb_iter_peek(iter, ts);
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-        if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-                cpu_relax();
+        if (event && event->type_len == RINGBUF_TYPE_PADDING)
                 goto again;
-        }
 
         return event;
 }
@@ -2553,13 +3276,17 @@ 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;
@@ -2580,13 +3307,12 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
         if (dolock)
                 spin_lock(&cpu_buffer->reader_lock);
 
-        event = rb_buffer_peek(buffer, cpu, ts);
-        if (!event)
-                goto out_unlock;
-
-        rb_advance_reader(cpu_buffer);
+        event = rb_buffer_peek(cpu_buffer, ts, lost_events);
+        if (event) {
+                cpu_buffer->lost_events = 0;
+                rb_advance_reader(cpu_buffer);
+        }
 
- out_unlock:
         if (dolock)
                 spin_unlock(&cpu_buffer->reader_lock);
         local_irq_restore(flags);
@@ -2594,33 +3320,38 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
  out:
         preempt_enable();
 
-        if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-                cpu_relax();
+        if (event && event->type_len == RINGBUF_TYPE_PADDING)
                 goto again;
-        }
 
         return event;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_consume);
 
 /**
- * ring_buffer_read_start - start a non consuming read of the buffer
+ * ring_buffer_read_prepare - Prepare for a non consuming read of the buffer
  * @buffer: The ring buffer to read from
  * @cpu: The cpu buffer to iterate over
  *
- * This starts up an iteration through the buffer. It also disables
- * the recording to the buffer until the reading is finished.
- * This prevents the reading from being corrupted. This is not
- * a consuming read, so a producer is not expected.
+ * This performs the initial preparations necessary to iterate
+ * through the buffer.  Memory is allocated, buffer recording
+ * is disabled, and the iterator pointer is returned to the caller.
  *
- * Must be paired with ring_buffer_finish.
+ * Disabling buffer recordng prevents the reading from being
+ * corrupted. This is not a consuming read, so a producer is not
+ * expected.
+ *
+ * After a sequence of ring_buffer_read_prepare calls, the user is
+ * expected to make at least one call to ring_buffer_prepare_sync.
+ * Afterwards, ring_buffer_read_start is invoked to get things going
+ * for real.
+ *
+ * This overall must be paired with ring_buffer_finish.
  */
 struct ring_buffer_iter *
-ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
+ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
         struct ring_buffer_iter *iter;
-        unsigned long flags;
 
         if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return NULL;
@@ -2634,15 +3365,52 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
         iter->cpu_buffer = cpu_buffer;
 
         atomic_inc(&cpu_buffer->record_disabled);
+
+        return iter;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_prepare);
+
+/**
+ * ring_buffer_read_prepare_sync - Synchronize a set of prepare calls
+ *
+ * All previously invoked ring_buffer_read_prepare calls to prepare
+ * iterators will be synchronized.  Afterwards, read_buffer_read_start
+ * calls on those iterators are allowed.
+ */
+void
+ring_buffer_read_prepare_sync(void)
+{
         synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync);
+
+/**
+ * ring_buffer_read_start - start a non consuming read of the buffer
+ * @iter: The iterator returned by ring_buffer_read_prepare
+ *
+ * This finalizes the startup of an iteration through the buffer.
+ * The iterator comes from a call to ring_buffer_read_prepare and
+ * an intervening ring_buffer_read_prepare_sync must have been
+ * performed.
+ *
+ * Must be paired with ring_buffer_finish.
+ */
+void
+ring_buffer_read_start(struct ring_buffer_iter *iter)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        unsigned long flags;
+
+        if (!iter)
+                return;
+
+        cpu_buffer = iter->cpu_buffer;
 
         spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
-        __raw_spin_lock(&cpu_buffer->lock);
+        arch_spin_lock(&cpu_buffer->lock);
         rb_iter_reset(iter);
-        __raw_spin_unlock(&cpu_buffer->lock);
+        arch_spin_unlock(&cpu_buffer->lock);
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-
-        return iter;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_start);
 
@@ -2677,21 +3445,19 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
         struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
         unsigned long flags;
 
- again:
         spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ again:
         event = rb_iter_peek(iter, ts);
         if (!event)
                 goto out;
 
+        if (event->type_len == RINGBUF_TYPE_PADDING)
+                goto again;
+
         rb_advance_iter(iter);
  out:
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
-        if (event && event->type_len == RINGBUF_TYPE_PADDING) {
-                cpu_relax();
-                goto again;
-        }
-
         return event;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read);
@@ -2709,8 +3475,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_size);
 static void
 rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 {
+        rb_head_page_deactivate(cpu_buffer);
+
         cpu_buffer->head_page
-                = list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+                = list_entry(cpu_buffer->pages, struct buffer_page, list);
         local_set(&cpu_buffer->head_page->write, 0);
         local_set(&cpu_buffer->head_page->entries, 0);
         local_set(&cpu_buffer->head_page->page->commit, 0);
@@ -2726,16 +3494,20 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
         local_set(&cpu_buffer->reader_page->page->commit, 0);
         cpu_buffer->reader_page->read = 0;
 
-        cpu_buffer->nmi_dropped = 0;
-        cpu_buffer->commit_overrun = 0;
-        cpu_buffer->overrun = 0;
-        cpu_buffer->read = 0;
+        local_set(&cpu_buffer->commit_overrun, 0);
+        local_set(&cpu_buffer->overrun, 0);
         local_set(&cpu_buffer->entries, 0);
         local_set(&cpu_buffer->committing, 0);
         local_set(&cpu_buffer->commits, 0);
+        cpu_buffer->read = 0;
 
         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);
 }
 
 /**
@@ -2755,12 +3527,16 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 
         spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
-        __raw_spin_lock(&cpu_buffer->lock);
+        if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
+                goto out;
+
+        arch_spin_lock(&cpu_buffer->lock);
 
         rb_reset_cpu(cpu_buffer);
 
-        __raw_spin_unlock(&cpu_buffer->lock);
+        arch_spin_unlock(&cpu_buffer->lock);
 
+ out:
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
         atomic_dec(&cpu_buffer->record_disabled);
@@ -2843,6 +3619,7 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu);
 
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
 /**
  * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers
  * @buffer_a: One buffer to swap with
@@ -2897,20 +3674,28 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
         atomic_inc(&cpu_buffer_a->record_disabled);
         atomic_inc(&cpu_buffer_b->record_disabled);
 
+        ret = -EBUSY;
+        if (local_read(&cpu_buffer_a->committing))
+                goto out_dec;
+        if (local_read(&cpu_buffer_b->committing))
+                goto out_dec;
+
         buffer_a->buffers[cpu] = cpu_buffer_b;
         buffer_b->buffers[cpu] = cpu_buffer_a;
 
         cpu_buffer_b->buffer = buffer_a;
         cpu_buffer_a->buffer = buffer_b;
 
+        ret = 0;
+
+out_dec:
         atomic_dec(&cpu_buffer_a->record_disabled);
         atomic_dec(&cpu_buffer_b->record_disabled);
-
-        ret = 0;
 out:
         return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
+#endif /* CONFIG_RING_BUFFER_ALLOW_SWAP */
 
 /**
  * ring_buffer_alloc_read_page - allocate a page to read from buffer
@@ -2997,6 +3782,7 @@ 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;
@@ -3033,6 +3819,9 @@ 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
@@ -3053,7 +3842,8 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
                 if (len > (commit - read))
                         len = (commit - read);
 
-                size = rb_event_length(event);
+                /* Always keep the time extend and data together */
+                size = rb_event_ts_length(event);
 
                 if (len < size)
                         goto out_unlock;
@@ -3063,6 +3853,13 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 
                 /* Need to copy one event at a time */
                 do {
+                        /* We need the size of one event, because
+                         * rb_advance_reader only advances by one event,
+                         * whereas rb_event_ts_length may include the size of
+                         * one or two events.
+                         * We have already ensured there's enough space if this
+                         * is a time extend. */
+                        size = rb_event_length(event);
                         memcpy(bpage->data + pos, rpage->data + rpos, size);
 
                         len -= size;
@@ -3071,9 +3868,13 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
                         rpos = reader->read;
                         pos += size;
 
+                        if (rpos >= commit)
+                                break;
+
                         event = rb_reader_event(cpu_buffer);
-                        size = rb_event_length(event);
-                } while (len > size);
+                        /* Always keep the time extend and data together */
+                        size = rb_event_ts_length(event);
+                } while (len >= size);
 
                 /* update bpage */
                 local_set(&bpage->commit, pos);
@@ -3083,7 +3884,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
                 read = 0;
         } else {
                 /* update the entry counter */
-                cpu_buffer->read += local_read(&reader->entries);
+                cpu_buffer->read += rb_page_entries(reader);
 
                 /* swap the pages */
                 rb_init_page(bpage);
@@ -3093,9 +3894,42 @@ 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;
+
+        commit = local_read(&bpage->commit);
+        /*
+         * Set a flag in the commit field if we lost events
+         */
+        if (missed_events) {
+                /* 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);
+                        commit += sizeof(missed_events);
+                }
+                local_add(RB_MISSED_EVENTS, &bpage->commit);
+        }
+
+        /*
+         * This page may be off to user land. Zero it out here.
+         */
+        if (commit < BUF_PAGE_SIZE)
+                memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit);
+
  out_unlock:
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
@@ -3104,6 +3938,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
+#ifdef CONFIG_TRACING
 static ssize_t
 rb_simple_read(struct file *filp, char __user *ubuf,
                size_t cnt, loff_t *ppos)
@@ -3155,6 +3990,7 @@ static const struct file_operations rb_simple_fops = {
         .open           = tracing_open_generic,
         .read           = rb_simple_read,
         .write          = rb_simple_write,
+        .llseek         = default_llseek,
 };
 
 
@@ -3171,6 +4007,7 @@ static __init int rb_init_debugfs(void)
 }
 
 fs_initcall(rb_init_debugfs);
+#endif
 
 #ifdef CONFIG_HOTPLUG_CPU
 static int rb_cpu_notify(struct notifier_block *self,
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 573d3cc762c3..302f8a614635 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -8,6 +8,7 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/time.h>
+#include <asm/local.h>
 
 struct rb_page {
         u64             ts;
@@ -35,6 +36,28 @@ static int disable_reader;
 module_param(disable_reader, uint, 0644);
 MODULE_PARM_DESC(disable_reader, "only run producer");
 
+static int write_iteration = 50;
+module_param(write_iteration, uint, 0644);
+MODULE_PARM_DESC(write_iteration, "# of writes between timestamp readings");
+
+static int producer_nice = 19;
+static int consumer_nice = 19;
+
+static int producer_fifo = -1;
+static int consumer_fifo = -1;
+
+module_param(producer_nice, uint, 0644);
+MODULE_PARM_DESC(producer_nice, "nice prio for producer");
+
+module_param(consumer_nice, uint, 0644);
+MODULE_PARM_DESC(consumer_nice, "nice prio for consumer");
+
+module_param(producer_fifo, uint, 0644);
+MODULE_PARM_DESC(producer_fifo, "fifo prio for producer");
+
+module_param(consumer_fifo, uint, 0644);
+MODULE_PARM_DESC(consumer_fifo, "fifo prio for consumer");
+
 static int read_events;
 
 static int kill_test;
@@ -58,7 +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;
 
@@ -90,7 +113,8 @@ static enum event_status read_page(int cpu)
         ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
         if (ret >= 0) {
                 rpage = bpage;
-                commit = local_read(&rpage->commit);
+                /* The commit may have missed event flags set, clear them */
+                commit = local_read(&rpage->commit) & 0xfffff;
                 for (i = 0; i < commit && !kill_test; i += inc) {
 
                         if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
@@ -208,15 +232,18 @@ static void ring_buffer_producer(void)
         do {
                 struct ring_buffer_event *event;
                 int *entry;
-
-                event = ring_buffer_lock_reserve(buffer, 10);
-                if (!event) {
-                        missed++;
-                } else {
-                        hit++;
-                        entry = ring_buffer_event_data(event);
-                        *entry = smp_processor_id();
-                        ring_buffer_unlock_commit(buffer, event);
+                int i;
+
+                for (i = 0; i < write_iteration; i++) {
+                        event = ring_buffer_lock_reserve(buffer, 10);
+                        if (!event) {
+                                missed++;
+                        } else {
+                                hit++;
+                                entry = ring_buffer_event_data(event);
+                                *entry = smp_processor_id();
+                                ring_buffer_unlock_commit(buffer, event);
+                        }
                 }
                 do_gettimeofday(&end_tv);
 
@@ -263,6 +290,27 @@ static void ring_buffer_producer(void)
 
         if (kill_test)
                 trace_printk("ERROR!\n");
+
+        if (!disable_reader) {
+                if (consumer_fifo < 0)
+                        trace_printk("Running Consumer at nice: %d\n",
+                                     consumer_nice);
+                else
+                        trace_printk("Running Consumer at SCHED_FIFO %d\n",
+                                     consumer_fifo);
+        }
+        if (producer_fifo < 0)
+                trace_printk("Running Producer at nice: %d\n",
+                             producer_nice);
+        else
+                trace_printk("Running Producer at SCHED_FIFO %d\n",
+                             producer_fifo);
+
+        /* Let the user know that the test is running at low priority */
+        if (producer_fifo < 0 && consumer_fifo < 0 &&
+            producer_nice == 19 && consumer_nice == 19)
+                trace_printk("WARNING!!! This test is running at lowest priority.\n");
+
         trace_printk("Time:     %lld (usecs)\n", time);
         trace_printk("Overruns: %lld\n", overruns);
         if (disable_reader)
@@ -392,6 +440,27 @@ static int __init ring_buffer_benchmark_init(void)
         if (IS_ERR(producer))
                 goto out_kill;
 
+        /*
+         * Run them as low-prio background tasks by default:
+         */
+        if (!disable_reader) {
+                if (consumer_fifo >= 0) {
+                        struct sched_param param = {
+                                .sched_priority = consumer_fifo
+                        };
+                        sched_setscheduler(consumer, SCHED_FIFO, &param);
+                } else
+                        set_user_nice(consumer, consumer_nice);
+        }
+
+        if (producer_fifo >= 0) {
+                struct sched_param param = {
+                        .sched_priority = consumer_fifo
+                };
+                sched_setscheduler(producer, SCHED_FIFO, &param);
+        } else
+                set_user_nice(producer, producer_nice);
+
         return 0;
 
  out_kill:
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 076fa6f0ee48..dc53ecb80589 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -12,7 +12,7 @@
  *  Copyright (C) 2004 William Lee Irwin III
  */
 #include <linux/ring_buffer.h>
-#include <linux/utsrelease.h>
+#include <generated/utsrelease.h>
 #include <linux/stacktrace.h>
 #include <linux/writeback.h>
 #include <linux/kallsyms.h>
@@ -31,10 +31,11 @@
 #include <linux/splice.h>
 #include <linux/kdebug.h>
 #include <linux/string.h>
+#include <linux/rwsem.h>
+#include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
-#include <linux/gfp.h>
 #include <linux/fs.h>
 
 #include "trace.h"
@@ -42,14 +43,11 @@
 
 #define TRACE_BUFFER_FLAGS      (RB_FL_OVERWRITE)
 
-unsigned long __read_mostly     tracing_max_latency;
-unsigned long __read_mostly     tracing_thresh;
-
 /*
  * 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.
  */
-static int ring_buffer_expanded;
+int ring_buffer_expanded;
 
 /*
  * We need to change this state when a selftest is running.
@@ -63,7 +61,7 @@ static bool __read_mostly tracing_selftest_running;
 /*
  * If a tracer is running, we do not want to run SELFTEST.
  */
-static bool __read_mostly tracing_selftest_disabled;
+bool __read_mostly tracing_selftest_disabled;
 
 /* For tracers that don't implement custom flags */
 static struct tracer_opt dummy_tracer_opt[] = {
@@ -88,27 +86,21 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
  */
 static int tracing_disabled = 1;
 
-static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+DEFINE_PER_CPU(int, ftrace_cpu_disabled);
 
 static inline void ftrace_disable_cpu(void)
 {
         preempt_disable();
-        local_inc(&__get_cpu_var(ftrace_cpu_disabled));
+        __this_cpu_inc(ftrace_cpu_disabled);
 }
 
 static inline void ftrace_enable_cpu(void)
 {
-        local_dec(&__get_cpu_var(ftrace_cpu_disabled));
+        __this_cpu_dec(ftrace_cpu_disabled);
         preempt_enable();
 }
 
-static cpumask_var_t __read_mostly      tracing_buffer_mask;
-
-/* Define which cpu buffers are currently read in trace_pipe */
-static cpumask_var_t                    tracing_reader_cpumask;
-
-#define for_each_tracing_cpu(cpu)       \
-        for_each_cpu(cpu, tracing_buffer_mask)
+cpumask_var_t __read_mostly     tracing_buffer_mask;
 
 /*
  * ftrace_dump_on_oops - variable to dump ftrace buffer on oops
@@ -121,30 +113,42 @@ static cpumask_var_t			tracing_reader_cpumask;
  *
  * It is default off, but you can enable it with either specifying
  * "ftrace_dump_on_oops" in the kernel command line, or setting
- * /proc/sys/kernel/ftrace_dump_on_oops to true.
+ * /proc/sys/kernel/ftrace_dump_on_oops
+ * Set 1 if you want to dump buffers of all CPUs
+ * Set 2 if you want to dump the buffer of the CPU that triggered oops
  */
-int ftrace_dump_on_oops;
+
+enum ftrace_dump_mode ftrace_dump_on_oops;
 
 static int tracing_set_tracer(const char *buf);
 
-#define BOOTUP_TRACER_SIZE              100
-static char bootup_tracer_buf[BOOTUP_TRACER_SIZE] __initdata;
+#define MAX_TRACER_SIZE         100
+static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
 static char *default_bootup_tracer;
 
-static int __init set_ftrace(char *str)
+static int __init set_cmdline_ftrace(char *str)
 {
-        strncpy(bootup_tracer_buf, str, BOOTUP_TRACER_SIZE);
+        strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
         default_bootup_tracer = bootup_tracer_buf;
         /* We are using ftrace early, expand it */
         ring_buffer_expanded = 1;
         return 1;
 }
-__setup("ftrace=", set_ftrace);
+__setup("ftrace=", set_cmdline_ftrace);
 
 static int __init set_ftrace_dump_on_oops(char *str)
 {
-        ftrace_dump_on_oops = 1;
-        return 1;
+        if (*str++ != '=' || !*str) {
+                ftrace_dump_on_oops = DUMP_ALL;
+                return 1;
+        }
+
+        if (!strcmp("orig_cpu", str)) {
+                ftrace_dump_on_oops = DUMP_ORIG;
+                return 1;
+        }
+
+        return 0;
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
@@ -171,10 +175,11 @@ static struct trace_array	global_trace;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
-int filter_current_check_discard(struct ftrace_event_call *call, void *rec,
+int filter_current_check_discard(struct ring_buffer *buffer,
+                                 struct ftrace_event_call *call, void *rec,
                                  struct ring_buffer_event *event)
 {
-        return filter_check_discard(call, rec, global_trace.buffer, event);
+        return filter_check_discard(call, rec, buffer, event);
 }
 EXPORT_SYMBOL_GPL(filter_current_check_discard);
 
@@ -204,7 +209,7 @@ cycle_t ftrace_now(int cpu)
  */
 static struct trace_array       max_tr;
 
-static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
+static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data);
 
 /* tracer_enabled is used to toggle activation of a tracer */
 static int                      tracer_enabled = 1;
@@ -243,19 +248,91 @@ static struct tracer		*trace_types __read_mostly;
 static struct tracer            *current_trace __read_mostly;
 
 /*
- * max_tracer_type_len is used to simplify the allocating of
- * buffers to read userspace tracer names. We keep track of
- * the longest tracer name registered.
+ * trace_types_lock is used to protect the trace_types list.
  */
-static int                      max_tracer_type_len;
+static DEFINE_MUTEX(trace_types_lock);
 
 /*
- * trace_types_lock is used to protect the trace_types list.
- * This lock is also used to keep user access serialized.
- * Accesses from userspace will grab this lock while userspace
- * activities happen inside the kernel.
+ * serialize the access of the ring buffer
+ *
+ * ring buffer serializes readers, but it is low level protection.
+ * The validity of the events (which returns by ring_buffer_peek() ..etc)
+ * are not protected by ring buffer.
+ *
+ * The content of events may become garbage if we allow other process consumes
+ * these events concurrently:
+ *   A) the page of the consumed events may become a normal page
+ *      (not reader page) in ring buffer, and this page will be rewrited
+ *      by events producer.
+ *   B) The page of the consumed events may become a page for splice_read,
+ *      and this page will be returned to system.
+ *
+ * These primitives allow multi process access to different cpu ring buffer
+ * concurrently.
+ *
+ * These primitives don't distinguish read-only and read-consume access.
+ * Multi read-only access are also serialized.
  */
-static DEFINE_MUTEX(trace_types_lock);
+
+#ifdef CONFIG_SMP
+static DECLARE_RWSEM(all_cpu_access_lock);
+static DEFINE_PER_CPU(struct mutex, cpu_access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+        if (cpu == TRACE_PIPE_ALL_CPU) {
+                /* gain it for accessing the whole ring buffer. */
+                down_write(&all_cpu_access_lock);
+        } else {
+                /* gain it for accessing a cpu ring buffer. */
+
+                /* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */
+                down_read(&all_cpu_access_lock);
+
+                /* Secondly block other access to this @cpu ring buffer. */
+                mutex_lock(&per_cpu(cpu_access_lock, cpu));
+        }
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+        if (cpu == TRACE_PIPE_ALL_CPU) {
+                up_write(&all_cpu_access_lock);
+        } else {
+                mutex_unlock(&per_cpu(cpu_access_lock, cpu));
+                up_read(&all_cpu_access_lock);
+        }
+}
+
+static inline void trace_access_lock_init(void)
+{
+        int cpu;
+
+        for_each_possible_cpu(cpu)
+                mutex_init(&per_cpu(cpu_access_lock, cpu));
+}
+
+#else
+
+static DEFINE_MUTEX(access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+        (void)cpu;
+        mutex_lock(&access_lock);
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+        (void)cpu;
+        mutex_unlock(&access_lock);
+}
+
+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);
@@ -263,7 +340,10 @@ 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_GRAPH_TIME | TRACE_ITER_RECORD_CMD;
+
+static int trace_stop_count;
+static DEFINE_SPINLOCK(tracing_start_lock);
 
 /**
  * trace_wake_up - wake up tasks waiting for trace input
@@ -273,30 +353,50 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
  */
 void trace_wake_up(void)
 {
+        int cpu;
+
+        if (trace_flags & TRACE_ITER_BLOCK)
+                return;
         /*
          * The runqueue_is_locked() can fail, but this is the best we
          * have for now:
          */
-        if (!(trace_flags & TRACE_ITER_BLOCK) && !runqueue_is_locked())
+        cpu = get_cpu();
+        if (!runqueue_is_locked(cpu))
                 wake_up(&trace_wait);
+        put_cpu();
 }
 
 static int __init set_buf_size(char *str)
 {
         unsigned long buf_size;
-        int ret;
 
         if (!str)
                 return 0;
-        ret = strict_strtoul(str, 0, &buf_size);
+        buf_size = memparse(str, &str);
         /* nr_entries can not be zero */
-        if (ret < 0 || buf_size == 0)
+        if (buf_size == 0)
                 return 0;
         trace_buf_size = buf_size;
         return 1;
 }
 __setup("trace_buf_size=", set_buf_size);
 
+static int __init set_tracing_thresh(char *str)
+{
+        unsigned long threshhold;
+        int ret;
+
+        if (!str)
+                return 0;
+        ret = strict_strtoul(str, 0, &threshhold);
+        if (ret < 0)
+                return 0;
+        tracing_thresh = threshhold * 1000;
+        return 1;
+}
+__setup("tracing_thresh=", set_tracing_thresh);
+
 unsigned long nsecs_to_usecs(unsigned long nsecs)
 {
         return nsecs / 1000;
@@ -313,7 +413,6 @@ static const char *trace_options[] = {
         "bin",
         "block",
         "stacktrace",
-        "sched-tree",
         "trace_printk",
         "ftrace_preempt",
         "branch",
@@ -323,49 +422,126 @@ static const char *trace_options[] = {
         "printk-msg-only",
         "context-info",
         "latency-format",
-        "global-clock",
         "sleep-time",
         "graph-time",
+        "record-cmd",
         NULL
 };
 
+static struct {
+        u64 (*func)(void);
+        const char *name;
+} trace_clocks[] = {
+        { trace_clock_local,    "local" },
+        { trace_clock_global,   "global" },
+};
+
+int trace_clock_id;
+
 /*
- * ftrace_max_lock is used to protect the swapping of buffers
- * when taking a max snapshot. The buffers themselves are
- * protected by per_cpu spinlocks. But the action of the swap
- * needs its own lock.
- *
- * This is defined as a raw_spinlock_t in order to help
- * with performance when lockdep debugging is enabled.
+ * trace_parser_get_init - gets the buffer for trace parser
  */
-static raw_spinlock_t ftrace_max_lock =
-        (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+int trace_parser_get_init(struct trace_parser *parser, int size)
+{
+        memset(parser, 0, sizeof(*parser));
+
+        parser->buffer = kmalloc(size, GFP_KERNEL);
+        if (!parser->buffer)
+                return 1;
+
+        parser->size = size;
+        return 0;
+}
 
 /*
- * Copy the new maximum trace into the separate maximum-trace
- * structure. (this way the maximum trace is permanently saved,
- * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
+ * trace_parser_put - frees the buffer for trace parser
  */
-static void
-__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
+void trace_parser_put(struct trace_parser *parser)
 {
-        struct trace_array_cpu *data = tr->data[cpu];
+        kfree(parser->buffer);
+}
 
-        max_tr.cpu = cpu;
-        max_tr.time_start = data->preempt_timestamp;
+/*
+ * trace_get_user - reads the user input string separated by  space
+ * (matched by isspace(ch))
+ *
+ * For each string found the 'struct trace_parser' is updated,
+ * and the function returns.
+ *
+ * Returns number of bytes read.
+ *
+ * See kernel/trace/trace.h for 'struct trace_parser' details.
+ */
+int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
+        size_t cnt, loff_t *ppos)
+{
+        char ch;
+        size_t read = 0;
+        ssize_t ret;
+
+        if (!*ppos)
+                trace_parser_clear(parser);
 
-        data = max_tr.data[cpu];
-        data->saved_latency = tracing_max_latency;
+        ret = get_user(ch, ubuf++);
+        if (ret)
+                goto out;
 
-        memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
-        data->pid = tsk->pid;
-        data->uid = task_uid(tsk);
-        data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
-        data->policy = tsk->policy;
-        data->rt_priority = tsk->rt_priority;
+        read++;
+        cnt--;
 
-        /* record this tasks comm */
-        tracing_record_cmdline(tsk);
+        /*
+         * The parser is not finished with the last write,
+         * continue reading the user input without skipping spaces.
+         */
+        if (!parser->cont) {
+                /* skip white space */
+                while (cnt && isspace(ch)) {
+                        ret = get_user(ch, ubuf++);
+                        if (ret)
+                                goto out;
+                        read++;
+                        cnt--;
+                }
+
+                /* only spaces were written */
+                if (isspace(ch)) {
+                        *ppos += read;
+                        ret = read;
+                        goto out;
+                }
+
+                parser->idx = 0;
+        }
+
+        /* read the non-space input */
+        while (cnt && !isspace(ch)) {
+                if (parser->idx < parser->size - 1)
+                        parser->buffer[parser->idx++] = ch;
+                else {
+                        ret = -EINVAL;
+                        goto out;
+                }
+                ret = get_user(ch, ubuf++);
+                if (ret)
+                        goto out;
+                read++;
+                cnt--;
+        }
+
+        /* We either got finished input or we have to wait for another call. */
+        if (isspace(ch)) {
+                parser->buffer[parser->idx] = 0;
+                parser->cont = false;
+        } else {
+                parser->cont = true;
+                parser->buffer[parser->idx++] = ch;
+        }
+
+        *ppos += read;
+        ret = read;
+
+out:
+        return ret;
 }
 
 ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
@@ -411,6 +587,57 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
         return cnt;
 }
 
+/*
+ * ftrace_max_lock is used to protect the swapping of buffers
+ * when taking a max snapshot. The buffers themselves are
+ * protected by per_cpu spinlocks. But the action of the swap
+ * needs its own lock.
+ *
+ * This is defined as a arch_spinlock_t in order to help
+ * with performance when lockdep debugging is enabled.
+ *
+ * It is also used in other places outside the update_max_tr
+ * so it needs to be defined outside of the
+ * CONFIG_TRACER_MAX_TRACE.
+ */
+static arch_spinlock_t ftrace_max_lock =
+        (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+unsigned long __read_mostly     tracing_thresh;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+unsigned long __read_mostly     tracing_max_latency;
+
+/*
+ * Copy the new maximum trace into the separate maximum-trace
+ * structure. (this way the maximum trace is permanently saved,
+ * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
+ */
+static void
+__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
+{
+        struct trace_array_cpu *data = tr->data[cpu];
+        struct trace_array_cpu *max_data;
+
+        max_tr.cpu = cpu;
+        max_tr.time_start = data->preempt_timestamp;
+
+        max_data = max_tr.data[cpu];
+        max_data->saved_latency = tracing_max_latency;
+        max_data->critical_start = data->critical_start;
+        max_data->critical_end = data->critical_end;
+
+        memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
+        max_data->pid = tsk->pid;
+        max_data->uid = task_uid(tsk);
+        max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
+        max_data->policy = tsk->policy;
+        max_data->rt_priority = tsk->rt_priority;
+
+        /* record this tasks comm */
+        tracing_record_cmdline(tsk);
+}
+
 /**
  * update_max_tr - snapshot all trace buffers from global_trace to max_tr
  * @tr: tracer
@@ -425,18 +652,21 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
         struct ring_buffer *buf = tr->buffer;
 
+        if (trace_stop_count)
+                return;
+
         WARN_ON_ONCE(!irqs_disabled());
-        __raw_spin_lock(&ftrace_max_lock);
+        if (!current_trace->use_max_tr) {
+                WARN_ON_ONCE(1);
+                return;
+        }
+        arch_spin_lock(&ftrace_max_lock);
 
         tr->buffer = max_tr.buffer;
         max_tr.buffer = buf;
 
-        ftrace_disable_cpu();
-        ring_buffer_reset(tr->buffer);
-        ftrace_enable_cpu();
-
         __update_max_tr(tr, tsk, cpu);
-        __raw_spin_unlock(&ftrace_max_lock);
+        arch_spin_unlock(&ftrace_max_lock);
 }
 
 /**
@@ -452,21 +682,40 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
         int ret;
 
+        if (trace_stop_count)
+                return;
+
         WARN_ON_ONCE(!irqs_disabled());
-        __raw_spin_lock(&ftrace_max_lock);
+        if (!current_trace->use_max_tr) {
+                WARN_ON_ONCE(1);
+                return;
+        }
+
+        arch_spin_lock(&ftrace_max_lock);
 
         ftrace_disable_cpu();
 
-        ring_buffer_reset(max_tr.buffer);
         ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
 
+        if (ret == -EBUSY) {
+                /*
+                 * We failed to swap the buffer due to a commit taking
+                 * place on this CPU. We fail to record, but we reset
+                 * the max trace buffer (no one writes directly to it)
+                 * and flag that it failed.
+                 */
+                trace_array_printk(&max_tr, _THIS_IP_,
+                        "Failed to swap buffers due to commit in progress\n");
+        }
+
         ftrace_enable_cpu();
 
-        WARN_ON_ONCE(ret && ret != -EAGAIN);
+        WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
 
         __update_max_tr(tr, tsk, cpu);
-        __raw_spin_unlock(&ftrace_max_lock);
+        arch_spin_unlock(&ftrace_max_lock);
 }
+#endif /* CONFIG_TRACER_MAX_TRACE */
 
 /**
  * register_tracer - register a tracer with the ftrace system.
@@ -479,7 +728,6 @@ __releases(kernel_lock)
 __acquires(kernel_lock)
 {
         struct tracer *t;
-        int len;
         int ret = 0;
 
         if (!type->name) {
@@ -487,13 +735,11 @@ __acquires(kernel_lock)
                 return -1;
         }
 
-        /*
-         * When this gets called we hold the BKL which means that
-         * preemption is disabled. Various trace selftests however
-         * need to disable and enable preemption for successful tests.
-         * So we drop the BKL here and grab it after the tests again.
-         */
-        unlock_kernel();
+        if (strlen(type->name) >= MAX_TRACER_SIZE) {
+                pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE);
+                return -1;
+        }
+
         mutex_lock(&trace_types_lock);
 
         tracing_selftest_running = true;
@@ -501,7 +747,7 @@ __acquires(kernel_lock)
         for (t = trace_types; t; t = t->next) {
                 if (strcmp(type->name, t->name) == 0) {
                         /* already found */
-                        pr_info("Trace %s already registered\n",
+                        pr_info("Tracer %s already registered\n",
                                 type->name);
                         ret = -1;
                         goto out;
@@ -523,7 +769,6 @@ __acquires(kernel_lock)
         if (type->selftest && !tracing_selftest_disabled) {
                 struct tracer *saved_tracer = current_trace;
                 struct trace_array *tr = &global_trace;
-                int i;
 
                 /*
                  * Run a selftest on this tracer.
@@ -532,8 +777,7 @@ __acquires(kernel_lock)
                  * internal tracing to verify that everything is in order.
                  * If we fail, we do not register this tracer.
                  */
-                for_each_tracing_cpu(i)
-                        tracing_reset(tr, i);
+                tracing_reset_online_cpus(tr);
 
                 current_trace = type;
                 /* the test is responsible for initializing and enabling */
@@ -546,8 +790,7 @@ __acquires(kernel_lock)
                         goto out;
                 }
                 /* Only reset on passing, to avoid touching corrupted buffers */
-                for_each_tracing_cpu(i)
-                        tracing_reset(tr, i);
+                tracing_reset_online_cpus(tr);
 
                 printk(KERN_CONT "PASSED\n");
         }
@@ -555,9 +798,6 @@ __acquires(kernel_lock)
 
         type->next = trace_types;
         trace_types = type;
-        len = strlen(type->name);
-        if (len > max_tracer_type_len)
-                max_tracer_type_len = len;
 
  out:
         tracing_selftest_running = false;
@@ -566,7 +806,7 @@ __acquires(kernel_lock)
         if (ret || !default_bootup_tracer)
                 goto out_unlock;
 
-        if (strncmp(default_bootup_tracer, type->name, BOOTUP_TRACER_SIZE))
+        if (strncmp(default_bootup_tracer, type->name, MAX_TRACER_SIZE))
                 goto out_unlock;
 
         printk(KERN_INFO "Starting tracer '%s'\n", type->name);
@@ -581,21 +821,19 @@ __acquires(kernel_lock)
 #endif
 
  out_unlock:
-        lock_kernel();
         return ret;
 }
 
 void unregister_tracer(struct tracer *type)
 {
         struct tracer **t;
-        int len;
 
         mutex_lock(&trace_types_lock);
         for (t = &trace_types; *t; t = &(*t)->next) {
                 if (*t == type)
                         goto found;
         }
-        pr_info("Trace %s not registered\n", type->name);
+        pr_info("Tracer %s not registered\n", type->name);
         goto out;
 
  found:
@@ -608,35 +846,46 @@ void unregister_tracer(struct tracer *type)
                         current_trace->stop(&global_trace);
                 current_trace = &nop_trace;
         }
-
-        if (strlen(type->name) != max_tracer_type_len)
-                goto out;
-
-        max_tracer_type_len = 0;
-        for (t = &trace_types; *t; t = &(*t)->next) {
-                len = strlen((*t)->name);
-                if (len > max_tracer_type_len)
-                        max_tracer_type_len = len;
-        }
- out:
+out:
         mutex_unlock(&trace_types_lock);
 }
 
-void tracing_reset(struct trace_array *tr, int cpu)
+static void __tracing_reset(struct ring_buffer *buffer, int cpu)
 {
         ftrace_disable_cpu();
-        ring_buffer_reset_cpu(tr->buffer, cpu);
+        ring_buffer_reset_cpu(buffer, cpu);
         ftrace_enable_cpu();
 }
 
+void tracing_reset(struct trace_array *tr, int cpu)
+{
+        struct ring_buffer *buffer = tr->buffer;
+
+        ring_buffer_record_disable(buffer);
+
+        /* Make sure all commits have finished */
+        synchronize_sched();
+        __tracing_reset(buffer, cpu);
+
+        ring_buffer_record_enable(buffer);
+}
+
 void tracing_reset_online_cpus(struct trace_array *tr)
 {
+        struct ring_buffer *buffer = tr->buffer;
         int cpu;
 
+        ring_buffer_record_disable(buffer);
+
+        /* Make sure all commits have finished */
+        synchronize_sched();
+
         tr->time_start = ftrace_now(tr->cpu);
 
         for_each_online_cpu(cpu)
-                tracing_reset(tr, cpu);
+                __tracing_reset(buffer, cpu);
+
+        ring_buffer_record_enable(buffer);
 }
 
 void tracing_reset_current(int cpu)
@@ -655,7 +904,7 @@ static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
 static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
 static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
 static int cmdline_idx;
-static raw_spinlock_t trace_cmdline_lock = __RAW_SPIN_LOCK_UNLOCKED;
+static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
 
 /* temporary disable recording */
 static atomic_t trace_record_cmdline_disabled __read_mostly;
@@ -667,8 +916,10 @@ static void trace_init_cmdlines(void)
         cmdline_idx = 0;
 }
 
-static int trace_stop_count;
-static DEFINE_SPINLOCK(tracing_start_lock);
+int is_tracing_stopped(void)
+{
+        return trace_stop_count;
+}
 
 /**
  * ftrace_off_permanent - disable all ftrace code permanently
@@ -709,6 +960,8 @@ void tracing_start(void)
                 goto out;
         }
 
+        /* Prevent the buffers from switching */
+        arch_spin_lock(&ftrace_max_lock);
 
         buffer = global_trace.buffer;
         if (buffer)
@@ -718,6 +971,8 @@ void tracing_start(void)
         if (buffer)
                 ring_buffer_record_enable(buffer);
 
+        arch_spin_unlock(&ftrace_max_lock);
+
         ftrace_start();
  out:
         spin_unlock_irqrestore(&tracing_start_lock, flags);
@@ -739,6 +994,9 @@ void tracing_stop(void)
         if (trace_stop_count++)
                 goto out;
 
+        /* Prevent the buffers from switching */
+        arch_spin_lock(&ftrace_max_lock);
+
         buffer = global_trace.buffer;
         if (buffer)
                 ring_buffer_record_disable(buffer);
@@ -747,6 +1005,8 @@ void tracing_stop(void)
         if (buffer)
                 ring_buffer_record_disable(buffer);
 
+        arch_spin_unlock(&ftrace_max_lock);
+
  out:
         spin_unlock_irqrestore(&tracing_start_lock, flags);
 }
@@ -766,7 +1026,7 @@ static void trace_save_cmdline(struct task_struct *tsk)
          * nor do we want to disable interrupts,
          * so if we miss here, then better luck next time.
          */
-        if (!__raw_spin_trylock(&trace_cmdline_lock))
+        if (!arch_spin_trylock(&trace_cmdline_lock))
                 return;
 
         idx = map_pid_to_cmdline[tsk->pid];
@@ -791,7 +1051,7 @@ static void trace_save_cmdline(struct task_struct *tsk)
 
         memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
 
-        __raw_spin_unlock(&trace_cmdline_lock);
+        arch_spin_unlock(&trace_cmdline_lock);
 }
 
 void trace_find_cmdline(int pid, char comm[])
@@ -803,20 +1063,25 @@ void trace_find_cmdline(int pid, char comm[])
                 return;
         }
 
+        if (WARN_ON_ONCE(pid < 0)) {
+                strcpy(comm, "<XXX>");
+                return;
+        }
+
         if (pid > PID_MAX_DEFAULT) {
                 strcpy(comm, "<...>");
                 return;
         }
 
         preempt_disable();
-        __raw_spin_lock(&trace_cmdline_lock);
+        arch_spin_lock(&trace_cmdline_lock);
         map = map_pid_to_cmdline[pid];
         if (map != NO_CMDLINE_MAP)
                 strcpy(comm, saved_cmdlines[map]);
         else
                 strcpy(comm, "<...>");
 
-        __raw_spin_unlock(&trace_cmdline_lock);
+        arch_spin_unlock(&trace_cmdline_lock);
         preempt_enable();
 }
 
@@ -837,7 +1102,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
         entry->preempt_count            = pc & 0xff;
         entry->pid                      = (tsk) ? tsk->pid : 0;
-        entry->tgid                     = (tsk) ? tsk->tgid : 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) |
@@ -848,15 +1113,17 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
                 ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
                 (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
 }
+EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
 
-struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-                                                    int type,
-                                                    unsigned long len,
-                                                    unsigned long flags, int pc)
+struct ring_buffer_event *
+trace_buffer_lock_reserve(struct ring_buffer *buffer,
+                          int type,
+                          unsigned long len,
+                          unsigned long flags, int pc)
 {
         struct ring_buffer_event *event;
 
-        event = ring_buffer_lock_reserve(tr->buffer, len);
+        event = ring_buffer_lock_reserve(buffer, len);
         if (event != NULL) {
                 struct trace_entry *ent = ring_buffer_event_data(event);
 
@@ -866,58 +1133,60 @@ struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
 
         return event;
 }
-static void ftrace_trace_stack(struct trace_array *tr,
-                               unsigned long flags, int skip, int pc);
-static void ftrace_trace_userstack(struct trace_array *tr,
-                                   unsigned long flags, int pc);
 
-static inline void __trace_buffer_unlock_commit(struct trace_array *tr,
-                                        struct ring_buffer_event *event,
-                                        unsigned long flags, int pc,
-                                        int wake)
+static inline void
+__trace_buffer_unlock_commit(struct ring_buffer *buffer,
+                             struct ring_buffer_event *event,
+                             unsigned long flags, int pc,
+                             int wake)
 {
-        ring_buffer_unlock_commit(tr->buffer, event);
+        ring_buffer_unlock_commit(buffer, event);
 
-        ftrace_trace_stack(tr, flags, 6, pc);
-        ftrace_trace_userstack(tr, flags, pc);
+        ftrace_trace_stack(buffer, flags, 6, pc);
+        ftrace_trace_userstack(buffer, flags, pc);
 
         if (wake)
                 trace_wake_up();
 }
 
-void trace_buffer_unlock_commit(struct trace_array *tr,
-                                        struct ring_buffer_event *event,
-                                        unsigned long flags, int pc)
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
+                                struct ring_buffer_event *event,
+                                unsigned long flags, int pc)
 {
-        __trace_buffer_unlock_commit(tr, event, flags, pc, 1);
+        __trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
 }
 
 struct ring_buffer_event *
-trace_current_buffer_lock_reserve(int type, unsigned long len,
+trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
+                                  int type, unsigned long len,
                                   unsigned long flags, int pc)
 {
-        return trace_buffer_lock_reserve(&global_trace,
+        *current_rb = global_trace.buffer;
+        return trace_buffer_lock_reserve(*current_rb,
                                          type, len, flags, pc);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);
 
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
+                                        struct ring_buffer_event *event,
                                         unsigned long flags, int pc)
 {
-        __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+        __trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit);
 
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
-                                        unsigned long flags, int pc)
+void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
+                                       struct ring_buffer_event *event,
+                                       unsigned long flags, int pc)
 {
-        __trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
+        __trace_buffer_unlock_commit(buffer, event, flags, pc, 0);
 }
 EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
 
-void trace_current_buffer_discard_commit(struct ring_buffer_event *event)
+void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
+                                         struct ring_buffer_event *event)
 {
-        ring_buffer_discard_commit(global_trace.buffer, event);
+        ring_buffer_discard_commit(buffer, event);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit);
 
@@ -927,14 +1196,15 @@ trace_function(struct trace_array *tr,
                int pc)
 {
         struct ftrace_event_call *call = &event_function;
+        struct ring_buffer *buffer = tr->buffer;
         struct ring_buffer_event *event;
         struct ftrace_entry *entry;
 
         /* If we are reading the ring buffer, don't trace */
-        if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+        if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
                 return;
 
-        event = trace_buffer_lock_reserve(tr, TRACE_FN, sizeof(*entry),
+        event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
                                           flags, pc);
         if (!event)
                 return;
@@ -942,57 +1212,9 @@ trace_function(struct trace_array *tr,
         entry->ip                       = ip;
         entry->parent_ip                = parent_ip;
 
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                ring_buffer_unlock_commit(tr->buffer, event);
-}
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int __trace_graph_entry(struct trace_array *tr,
-                                struct ftrace_graph_ent *trace,
-                                unsigned long flags,
-                                int pc)
-{
-        struct ftrace_event_call *call = &event_funcgraph_entry;
-        struct ring_buffer_event *event;
-        struct ftrace_graph_ent_entry *entry;
-
-        if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
-                return 0;
-
-        event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT,
-                                          sizeof(*entry), flags, pc);
-        if (!event)
-                return 0;
-        entry   = ring_buffer_event_data(event);
-        entry->graph_ent                        = *trace;
-        if (!filter_current_check_discard(call, entry, event))
-                ring_buffer_unlock_commit(global_trace.buffer, event);
-
-        return 1;
-}
-
-static void __trace_graph_return(struct trace_array *tr,
-                                struct ftrace_graph_ret *trace,
-                                unsigned long flags,
-                                int pc)
-{
-        struct ftrace_event_call *call = &event_funcgraph_exit;
-        struct ring_buffer_event *event;
-        struct ftrace_graph_ret_entry *entry;
-
-        if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
-                return;
-
-        event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_RET,
-                                          sizeof(*entry), flags, pc);
-        if (!event)
-                return;
-        entry   = ring_buffer_event_data(event);
-        entry->ret                              = *trace;
-        if (!filter_current_check_discard(call, entry, event))
-                ring_buffer_unlock_commit(global_trace.buffer, event);
+        if (!filter_check_discard(call, entry, buffer, event))
+                ring_buffer_unlock_commit(buffer, event);
 }
-#endif
 
 void
 ftrace(struct trace_array *tr, struct trace_array_cpu *data,
@@ -1003,17 +1225,17 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
                 trace_function(tr, ip, parent_ip, flags, pc);
 }
 
-static void __ftrace_trace_stack(struct trace_array *tr,
+#ifdef CONFIG_STACKTRACE
+static void __ftrace_trace_stack(struct ring_buffer *buffer,
                                  unsigned long flags,
                                  int skip, int pc)
 {
-#ifdef CONFIG_STACKTRACE
         struct ftrace_event_call *call = &event_kernel_stack;
         struct ring_buffer_event *event;
         struct stack_entry *entry;
         struct stack_trace trace;
 
-        event = trace_buffer_lock_reserve(tr, TRACE_STACK,
+        event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
                                           sizeof(*entry), flags, pc);
         if (!event)
                 return;
@@ -1026,32 +1248,46 @@ static void __ftrace_trace_stack(struct trace_array *tr,
         trace.entries           = entry->caller;
 
         save_stack_trace(&trace);
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                ring_buffer_unlock_commit(tr->buffer, event);
-#endif
+        if (!filter_check_discard(call, entry, buffer, event))
+                ring_buffer_unlock_commit(buffer, event);
 }
 
-static void ftrace_trace_stack(struct trace_array *tr,
-                               unsigned long flags,
-                               int skip, int pc)
+void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
+                        int skip, int pc)
 {
         if (!(trace_flags & TRACE_ITER_STACKTRACE))
                 return;
 
-        __ftrace_trace_stack(tr, flags, skip, pc);
+        __ftrace_trace_stack(buffer, flags, skip, pc);
 }
 
-void __trace_stack(struct trace_array *tr,
-                   unsigned long flags,
-                   int skip, int pc)
+void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
+                   int pc)
 {
-        __ftrace_trace_stack(tr, flags, skip, pc);
+        __ftrace_trace_stack(tr->buffer, flags, skip, pc);
 }
 
-static void ftrace_trace_userstack(struct trace_array *tr,
-                                   unsigned long flags, int pc)
+/**
+ * trace_dump_stack - record a stack back trace in the trace buffer
+ */
+void trace_dump_stack(void)
+{
+        unsigned long flags;
+
+        if (tracing_disabled || tracing_selftest_running)
+                return;
+
+        local_save_flags(flags);
+
+        /* skipping 3 traces, seems to get us at the caller of this function */
+        __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
+}
+
+static DEFINE_PER_CPU(int, user_stack_count);
+
+void
+ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
-#ifdef CONFIG_STACKTRACE
         struct ftrace_event_call *call = &event_user_stack;
         struct ring_buffer_event *event;
         struct userstack_entry *entry;
@@ -1060,12 +1296,30 @@ static void ftrace_trace_userstack(struct trace_array *tr,
         if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
                 return;
 
-        event = trace_buffer_lock_reserve(tr, TRACE_USER_STACK,
+        /*
+         * NMIs can not handle page faults, even with fix ups.
+         * The save user stack can (and often does) fault.
+         */
+        if (unlikely(in_nmi()))
+                return;
+
+        /*
+         * prevent recursion, since the user stack tracing may
+         * trigger other kernel events.
+         */
+        preempt_disable();
+        if (__this_cpu_read(user_stack_count))
+                goto out;
+
+        __this_cpu_inc(user_stack_count);
+
+        event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
                                           sizeof(*entry), flags, pc);
         if (!event)
-                return;
+                goto out_drop_count;
         entry   = ring_buffer_event_data(event);
 
+        entry->tgid             = current->tgid;
         memset(&entry->caller, 0, sizeof(entry->caller));
 
         trace.nr_entries        = 0;
@@ -1074,9 +1328,13 @@ static void ftrace_trace_userstack(struct trace_array *tr,
         trace.entries           = entry->caller;
 
         save_stack_trace_user(&trace);
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                ring_buffer_unlock_commit(tr->buffer, event);
-#endif
+        if (!filter_check_discard(call, entry, buffer, event))
+                ring_buffer_unlock_commit(buffer, event);
+
+ out_drop_count:
+        __this_cpu_dec(user_stack_count);
+ out:
+        preempt_enable();
 }
 
 #ifdef UNUSED
@@ -1086,174 +1344,7 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags)
 }
 #endif /* UNUSED */
 
-static void
-ftrace_trace_special(void *__tr,
-                     unsigned long arg1, unsigned long arg2, unsigned long arg3,
-                     int pc)
-{
-        struct ring_buffer_event *event;
-        struct trace_array *tr = __tr;
-        struct special_entry *entry;
-
-        event = trace_buffer_lock_reserve(tr, TRACE_SPECIAL,
-                                          sizeof(*entry), 0, pc);
-        if (!event)
-                return;
-        entry   = ring_buffer_event_data(event);
-        entry->arg1                     = arg1;
-        entry->arg2                     = arg2;
-        entry->arg3                     = arg3;
-        trace_buffer_unlock_commit(tr, event, 0, pc);
-}
-
-void
-__trace_special(void *__tr, void *__data,
-                unsigned long arg1, unsigned long arg2, unsigned long arg3)
-{
-        ftrace_trace_special(__tr, arg1, arg2, arg3, preempt_count());
-}
-
-void
-tracing_sched_switch_trace(struct trace_array *tr,
-                           struct task_struct *prev,
-                           struct task_struct *next,
-                           unsigned long flags, int pc)
-{
-        struct ftrace_event_call *call = &event_context_switch;
-        struct ring_buffer_event *event;
-        struct ctx_switch_entry *entry;
-
-        event = trace_buffer_lock_reserve(tr, TRACE_CTX,
-                                          sizeof(*entry), flags, pc);
-        if (!event)
-                return;
-        entry   = ring_buffer_event_data(event);
-        entry->prev_pid                 = prev->pid;
-        entry->prev_prio                = prev->prio;
-        entry->prev_state               = prev->state;
-        entry->next_pid                 = next->pid;
-        entry->next_prio                = next->prio;
-        entry->next_state               = next->state;
-        entry->next_cpu = task_cpu(next);
-
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                trace_buffer_unlock_commit(tr, event, flags, pc);
-}
-
-void
-tracing_sched_wakeup_trace(struct trace_array *tr,
-                           struct task_struct *wakee,
-                           struct task_struct *curr,
-                           unsigned long flags, int pc)
-{
-        struct ftrace_event_call *call = &event_wakeup;
-        struct ring_buffer_event *event;
-        struct ctx_switch_entry *entry;
-
-        event = trace_buffer_lock_reserve(tr, TRACE_WAKE,
-                                          sizeof(*entry), flags, pc);
-        if (!event)
-                return;
-        entry   = ring_buffer_event_data(event);
-        entry->prev_pid                 = curr->pid;
-        entry->prev_prio                = curr->prio;
-        entry->prev_state               = curr->state;
-        entry->next_pid                 = wakee->pid;
-        entry->next_prio                = wakee->prio;
-        entry->next_state               = wakee->state;
-        entry->next_cpu                 = task_cpu(wakee);
-
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                ring_buffer_unlock_commit(tr->buffer, event);
-        ftrace_trace_stack(tr, flags, 6, pc);
-        ftrace_trace_userstack(tr, flags, pc);
-}
-
-void
-ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
-{
-        struct trace_array *tr = &global_trace;
-        struct trace_array_cpu *data;
-        unsigned long flags;
-        int cpu;
-        int pc;
-
-        if (tracing_disabled)
-                return;
-
-        pc = preempt_count();
-        local_irq_save(flags);
-        cpu = raw_smp_processor_id();
-        data = tr->data[cpu];
-
-        if (likely(atomic_inc_return(&data->disabled) == 1))
-                ftrace_trace_special(tr, arg1, arg2, arg3, pc);
-
-        atomic_dec(&data->disabled);
-        local_irq_restore(flags);
-}
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-int trace_graph_entry(struct ftrace_graph_ent *trace)
-{
-        struct trace_array *tr = &global_trace;
-        struct trace_array_cpu *data;
-        unsigned long flags;
-        long disabled;
-        int ret;
-        int cpu;
-        int pc;
-
-        if (!ftrace_trace_task(current))
-                return 0;
-
-        if (!ftrace_graph_addr(trace->func))
-                return 0;
-
-        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();
-                ret = __trace_graph_entry(tr, trace, flags, pc);
-        } else {
-                ret = 0;
-        }
-        /* Only do the atomic if it is not already set */
-        if (!test_tsk_trace_graph(current))
-                set_tsk_trace_graph(current);
-
-        atomic_dec(&data->disabled);
-        local_irq_restore(flags);
-
-        return ret;
-}
-
-void trace_graph_return(struct ftrace_graph_ret *trace)
-{
-        struct trace_array *tr = &global_trace;
-        struct trace_array_cpu *data;
-        unsigned long flags;
-        long disabled;
-        int cpu;
-        int pc;
-
-        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_graph_return(tr, trace, flags, pc);
-        }
-        if (!trace->depth)
-                clear_tsk_trace_graph(current);
-        atomic_dec(&data->disabled);
-        local_irq_restore(flags);
-}
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
+#endif /* CONFIG_STACKTRACE */
 
 /**
  * trace_vbprintk - write binary msg to tracing buffer
@@ -1261,18 +1352,18 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
  */
 int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 {
-        static raw_spinlock_t trace_buf_lock =
-                (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+        static arch_spinlock_t trace_buf_lock =
+                (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
         static u32 trace_buf[TRACE_BUF_SIZE];
 
         struct ftrace_event_call *call = &event_bprint;
         struct ring_buffer_event *event;
+        struct ring_buffer *buffer;
         struct trace_array *tr = &global_trace;
         struct trace_array_cpu *data;
         struct bprint_entry *entry;
         unsigned long flags;
         int disable;
-        int resched;
         int cpu, len = 0, size, pc;
 
         if (unlikely(tracing_selftest_running || tracing_disabled))
@@ -1282,7 +1373,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
         pause_graph_tracing();
 
         pc = preempt_count();
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
         cpu = raw_smp_processor_id();
         data = tr->data[cpu];
 
@@ -1292,14 +1383,16 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 
         /* Lockdep uses trace_printk for lock tracing */
         local_irq_save(flags);
-        __raw_spin_lock(&trace_buf_lock);
+        arch_spin_lock(&trace_buf_lock);
         len = vbin_printf(trace_buf, TRACE_BUF_SIZE, fmt, args);
 
         if (len > TRACE_BUF_SIZE || len < 0)
                 goto out_unlock;
 
         size = sizeof(*entry) + sizeof(u32) * len;
-        event = trace_buffer_lock_reserve(tr, TRACE_BPRINT, size, flags, pc);
+        buffer = tr->buffer;
+        event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
+                                          flags, pc);
         if (!event)
                 goto out_unlock;
         entry = ring_buffer_event_data(event);
@@ -1307,30 +1400,48 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
         entry->fmt                      = fmt;
 
         memcpy(entry->buf, trace_buf, sizeof(u32) * len);
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                ring_buffer_unlock_commit(tr->buffer, event);
+        if (!filter_check_discard(call, entry, buffer, event)) {
+                ring_buffer_unlock_commit(buffer, event);
+                ftrace_trace_stack(buffer, flags, 6, pc);
+        }
 
 out_unlock:
-        __raw_spin_unlock(&trace_buf_lock);
+        arch_spin_unlock(&trace_buf_lock);
         local_irq_restore(flags);
 
 out:
         atomic_dec_return(&data->disabled);
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
         unpause_graph_tracing();
 
         return len;
 }
 EXPORT_SYMBOL_GPL(trace_vbprintk);
 
-int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
+int trace_array_printk(struct trace_array *tr,
+                       unsigned long ip, const char *fmt, ...)
 {
-        static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
+        int ret;
+        va_list ap;
+
+        if (!(trace_flags & TRACE_ITER_PRINTK))
+                return 0;
+
+        va_start(ap, fmt);
+        ret = trace_array_vprintk(tr, ip, fmt, ap);
+        va_end(ap);
+        return ret;
+}
+
+int trace_array_vprintk(struct trace_array *tr,
+                        unsigned long ip, const char *fmt, va_list args)
+{
+        static arch_spinlock_t trace_buf_lock = __ARCH_SPIN_LOCK_UNLOCKED;
         static char trace_buf[TRACE_BUF_SIZE];
 
         struct ftrace_event_call *call = &event_print;
         struct ring_buffer_event *event;
-        struct trace_array *tr = &global_trace;
+        struct ring_buffer *buffer;
         struct trace_array_cpu *data;
         int cpu, len = 0, size, pc;
         struct print_entry *entry;
@@ -1351,26 +1462,27 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
         pause_graph_tracing();
         raw_local_irq_save(irq_flags);
-        __raw_spin_lock(&trace_buf_lock);
+        arch_spin_lock(&trace_buf_lock);
         len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
 
-        len = min(len, TRACE_BUF_SIZE-1);
-        trace_buf[len] = 0;
-
         size = sizeof(*entry) + len + 1;
-        event = trace_buffer_lock_reserve(tr, TRACE_PRINT, size, irq_flags, pc);
+        buffer = tr->buffer;
+        event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+                                          irq_flags, pc);
         if (!event)
                 goto out_unlock;
         entry = ring_buffer_event_data(event);
-        entry->ip                       = ip;
+        entry->ip = ip;
 
         memcpy(&entry->buf, trace_buf, len);
-        entry->buf[len] = 0;
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                ring_buffer_unlock_commit(tr->buffer, event);
+        entry->buf[len] = '\0';
+        if (!filter_check_discard(call, entry, buffer, event)) {
+                ring_buffer_unlock_commit(buffer, event);
+                ftrace_trace_stack(buffer, irq_flags, 6, pc);
+        }
 
  out_unlock:
-        __raw_spin_unlock(&trace_buf_lock);
+        arch_spin_unlock(&trace_buf_lock);
         raw_local_irq_restore(irq_flags);
         unpause_graph_tracing();
  out:
@@ -1379,12 +1491,12 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
         return len;
 }
-EXPORT_SYMBOL_GPL(trace_vprintk);
 
-enum trace_file_type {
-        TRACE_FILE_LAT_FMT      = 1,
-        TRACE_FILE_ANNOTATE     = 2,
-};
+int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
+{
+        return trace_array_vprintk(&global_trace, ip, fmt, args);
+}
+EXPORT_SYMBOL_GPL(trace_vprintk);
 
 static void trace_iterator_increment(struct trace_iterator *iter)
 {
@@ -1399,7 +1511,8 @@ 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];
@@ -1410,7 +1523,8 @@ 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();
 
@@ -1418,10 +1532,12 @@ 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 = 0, next_lost = 0;
         int cpu_file = iter->cpu_file;
         u64 next_ts = 0, ts;
         int next_cpu = -1;
@@ -1434,7 +1550,7 @@ __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;
 
@@ -1446,7 +1562,7 @@ __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:
@@ -1455,6 +1571,7 @@ __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;
                 }
         }
 
@@ -1464,6 +1581,9 @@ __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;
 }
 
@@ -1471,13 +1591,14 @@ __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)
+void *trace_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);
@@ -1489,7 +1610,8 @@ 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();
 }
 
@@ -1499,6 +1621,8 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
         int i = (int)*pos;
         void *ent;
 
+        WARN_ON_ONCE(iter->leftover);
+
         (*pos)++;
 
         /* can't go backwards */
@@ -1506,25 +1630,50 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
                 return NULL;
 
         if (iter->idx < 0)
-                ent = find_next_entry_inc(iter);
+                ent = trace_find_next_entry_inc(iter);
         else
                 ent = iter;
 
         while (ent && iter->idx < i)
-                ent = find_next_entry_inc(iter);
+                ent = trace_find_next_entry_inc(iter);
 
         iter->pos = *pos;
 
         return ent;
 }
 
+void tracing_iter_reset(struct trace_iterator *iter, int cpu)
+{
+        struct trace_array *tr = iter->tr;
+        struct ring_buffer_event *event;
+        struct ring_buffer_iter *buf_iter;
+        unsigned long entries = 0;
+        u64 ts;
+
+        tr->data[cpu]->skipped_entries = 0;
+
+        if (!iter->buffer_iter[cpu])
+                return;
+
+        buf_iter = iter->buffer_iter[cpu];
+        ring_buffer_iter_reset(buf_iter);
+
+        /*
+         * We could have the case with the max latency tracers
+         * that a reset never took place on a cpu. This is evident
+         * by the timestamp being before the start of the buffer.
+         */
+        while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
+                if (ts >= iter->tr->time_start)
+                        break;
+                entries++;
+                ring_buffer_read(buf_iter, NULL);
+        }
+
+        tr->data[cpu]->skipped_entries = entries;
+}
+
 /*
- * No necessary locking here. The worst thing which can
- * happen is loosing events consumed at the same time
- * by a trace_pipe reader.
- * Other than that, we don't risk to crash the ring buffer
- * because it serializes the readers.
- *
  * The current tracer is copied to avoid a global locking
  * all around.
  */
@@ -1556,28 +1705,40 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
                 if (cpu_file == TRACE_PIPE_ALL_CPU) {
                         for_each_tracing_cpu(cpu)
-                                ring_buffer_iter_reset(iter->buffer_iter[cpu]);
+                                tracing_iter_reset(iter, cpu);
                 } else
-                        ring_buffer_iter_reset(iter->buffer_iter[cpu_file]);
-
+                        tracing_iter_reset(iter, cpu_file);
 
                 ftrace_enable_cpu();
 
+                iter->leftover = 0;
                 for (p = iter; p && l < *pos; p = s_next(m, p, &l))
                         ;
 
         } else {
-                l = *pos - 1;
-                p = s_next(m, p, &l);
+                /*
+                 * If we overflowed the seq_file before, then we want
+                 * to just reuse the trace_seq buffer again.
+                 */
+                if (iter->leftover)
+                        p = iter;
+                else {
+                        l = *pos - 1;
+                        p = s_next(m, p, &l);
+                }
         }
 
         trace_event_read_lock();
+        trace_access_lock(cpu_file);
         return p;
 }
 
 static void s_stop(struct seq_file *m, void *p)
 {
+        struct trace_iterator *iter = m->private;
+
         atomic_dec(&trace_record_cmdline_disabled);
+        trace_access_unlock(iter->cpu_file);
         trace_event_read_unlock();
 }
 
@@ -1588,10 +1749,10 @@ 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, "#                |||| /                      \n");
-        seq_puts(m, "#                |||||     delay             \n");
-        seq_puts(m, "#  cmd     pid   ||||| time  |   caller      \n");
-        seq_puts(m, "#     \\   /      |||||   \\   |   /           \n");
+        seq_puts(m, "#                |||| /_--=> lock-depth       \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)
@@ -1601,23 +1762,39 @@ static void print_func_help_header(struct seq_file *m)
 }
 
 
-static void
+void
 print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 {
         unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
         struct trace_array *tr = iter->tr;
         struct trace_array_cpu *data = tr->data[tr->cpu];
         struct tracer *type = current_trace;
-        unsigned long total;
-        unsigned long entries;
+        unsigned long entries = 0;
+        unsigned long total = 0;
+        unsigned long count;
         const char *name = "preemption";
+        int cpu;
 
         if (type)
                 name = type->name;
 
-        entries = ring_buffer_entries(iter->tr->buffer);
-        total = entries +
-                ring_buffer_overruns(iter->tr->buffer);
+
+        for_each_tracing_cpu(cpu) {
+                count = ring_buffer_entries_cpu(tr->buffer, cpu);
+                /*
+                 * If this buffer has skipped entries, then we hold all
+                 * entries for the trace and we need to ignore the
+                 * ones before the time stamp.
+                 */
+                if (tr->data[cpu]->skipped_entries) {
+                        count -= tr->data[cpu]->skipped_entries;
+                        /* total is the same as the entries */
+                        total += count;
+                } else
+                        total += count +
+                                ring_buffer_overrun_cpu(tr->buffer, cpu);
+                entries += count;
+        }
 
         seq_printf(m, "# %s latency trace v1.1.5 on %s\n",
                    name, UTS_RELEASE);
@@ -1659,7 +1836,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
                 seq_puts(m, "\n#  => ended at:   ");
                 seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags);
                 trace_print_seq(m, &iter->seq);
-                seq_puts(m, "#\n");
+                seq_puts(m, "\n#\n");
         }
 
         seq_puts(m, "#\n");
@@ -1678,6 +1855,9 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
         if (cpumask_test_cpu(iter->cpu, iter->started))
                 return;
 
+        if (iter->tr->data[iter->cpu]->skipped_entries)
+                return;
+
         cpumask_set_cpu(iter->cpu, iter->started);
 
         /* Don't print started cpu buffer for the first entry of the trace */
@@ -1710,7 +1890,7 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
         }
 
         if (event)
-                return event->trace(iter, sym_flags);
+                return event->funcs->trace(iter, sym_flags, event);
 
         if (!trace_seq_printf(s, "Unknown type %d\n", entry->type))
                 goto partial;
@@ -1736,7 +1916,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 
         event = ftrace_find_event(entry->type);
         if (event)
-                return event->raw(iter, 0);
+                return event->funcs->raw(iter, 0, event);
 
         if (!trace_seq_printf(s, "%d ?\n", entry->type))
                 goto partial;
@@ -1763,7 +1943,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 
         event = ftrace_find_event(entry->type);
         if (event) {
-                enum print_line_t ret = event->hex(iter, 0);
+                enum print_line_t ret = event->funcs->hex(iter, 0, event);
                 if (ret != TRACE_TYPE_HANDLED)
                         return ret;
         }
@@ -1788,10 +1968,11 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
         }
 
         event = ftrace_find_event(entry->type);
-        return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED;
+        return event ? event->funcs->binary(iter, 0, event) :
+                TRACE_TYPE_HANDLED;
 }
 
-static int trace_empty(struct trace_iterator *iter)
+int trace_empty(struct trace_iterator *iter)
 {
         int cpu;
 
@@ -1822,10 +2003,14 @@ static int trace_empty(struct trace_iterator *iter)
 }
 
 /*  Called with trace_event_read_lock() held. */
-static enum print_line_t print_trace_line(struct trace_iterator *iter)
+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)
@@ -1854,9 +2039,27 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
         return print_trace_fmt(iter);
 }
 
+void trace_default_header(struct seq_file *m)
+{
+        struct trace_iterator *iter = m->private;
+
+        if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
+                /* print nothing if the buffers are empty */
+                if (trace_empty(iter))
+                        return;
+                print_trace_header(m, iter);
+                if (!(trace_flags & TRACE_ITER_VERBOSE))
+                        print_lat_help_header(m);
+        } else {
+                if (!(trace_flags & TRACE_ITER_VERBOSE))
+                        print_func_help_header(m);
+        }
+}
+
 static int s_show(struct seq_file *m, void *v)
 {
         struct trace_iterator *iter = v;
+        int ret;
 
         if (iter->ent == NULL) {
                 if (iter->tr) {
@@ -1865,26 +2068,36 @@ static int s_show(struct seq_file *m, void *v)
                 }
                 if (iter->trace && iter->trace->print_header)
                         iter->trace->print_header(m);
-                else if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
-                        /* print nothing if the buffers are empty */
-                        if (trace_empty(iter))
-                                return 0;
-                        print_trace_header(m, iter);
-                        if (!(trace_flags & TRACE_ITER_VERBOSE))
-                                print_lat_help_header(m);
-                } else {
-                        if (!(trace_flags & TRACE_ITER_VERBOSE))
-                                print_func_help_header(m);
-                }
+                else
+                        trace_default_header(m);
+
+        } else if (iter->leftover) {
+                /*
+                 * If we filled the seq_file buffer earlier, we
+                 * want to just show it now.
+                 */
+                ret = trace_print_seq(m, &iter->seq);
+
+                /* ret should this time be zero, but you never know */
+                iter->leftover = ret;
+
         } else {
                 print_trace_line(iter);
-                trace_print_seq(m, &iter->seq);
+                ret = trace_print_seq(m, &iter->seq);
+                /*
+                 * If we overflow the seq_file buffer, then it will
+                 * ask us for this data again at start up.
+                 * Use that instead.
+                 *  ret is 0 if seq_file write succeeded.
+                 *        -1 otherwise.
+                 */
+                iter->leftover = ret;
         }
 
         return 0;
 }
 
-static struct seq_operations tracer_seq_ops = {
+static const struct seq_operations tracer_seq_ops = {
         .start          = s_start,
         .next           = s_next,
         .stop           = s_stop,
@@ -1919,11 +2132,9 @@ __tracing_open(struct inode *inode, struct file *file)
         if (current_trace)
                 *iter->trace = *current_trace;
 
-        if (!alloc_cpumask_var(&iter->started, GFP_KERNEL))
+        if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
                 goto fail;
 
-        cpumask_clear(iter->started);
-
         if (current_trace && current_trace->print_max)
                 iter->tr = &max_tr;
         else
@@ -1940,19 +2151,28 @@ __tracing_open(struct inode *inode, struct file *file)
         if (ring_buffer_overruns(iter->tr->buffer))
                 iter->iter_flags |= TRACE_FILE_ANNOTATE;
 
+        /* stop the trace while dumping */
+        tracing_stop();
+
         if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
                 for_each_tracing_cpu(cpu) {
-
                         iter->buffer_iter[cpu] =
-                                ring_buffer_read_start(iter->tr->buffer, cpu);
+                                ring_buffer_read_prepare(iter->tr->buffer, cpu);
+                }
+                ring_buffer_read_prepare_sync();
+                for_each_tracing_cpu(cpu) {
+                        ring_buffer_read_start(iter->buffer_iter[cpu]);
+                        tracing_iter_reset(iter, cpu);
                 }
         } else {
                 cpu = iter->cpu_file;
                 iter->buffer_iter[cpu] =
-                                ring_buffer_read_start(iter->tr->buffer, cpu);
+                        ring_buffer_read_prepare(iter->tr->buffer, cpu);
+                ring_buffer_read_prepare_sync();
+                ring_buffer_read_start(iter->buffer_iter[cpu]);
+                tracing_iter_reset(iter, cpu);
         }
 
-        /* TODO stop tracer */
         ret = seq_open(file, &tracer_seq_ops);
         if (ret < 0) {
                 fail_ret = ERR_PTR(ret);
@@ -1962,9 +2182,6 @@ __tracing_open(struct inode *inode, struct file *file)
         m = file->private_data;
         m->private = iter;
 
-        /* stop the trace while dumping */
-        tracing_stop();
-
         mutex_unlock(&trace_types_lock);
 
         return iter;
@@ -1975,6 +2192,7 @@ __tracing_open(struct inode *inode, struct file *file)
                         ring_buffer_read_finish(iter->buffer_iter[cpu]);
         }
         free_cpumask_var(iter->started);
+        tracing_start();
  fail:
         mutex_unlock(&trace_types_lock);
         kfree(iter->trace);
@@ -1994,7 +2212,7 @@ int tracing_open_generic(struct inode *inode, struct file *filp)
 
 static int tracing_release(struct inode *inode, struct file *file)
 {
-        struct seq_file *m = (struct seq_file *)file->private_data;
+        struct seq_file *m = file->private_data;
         struct trace_iterator *iter;
         int cpu;
 
@@ -2031,7 +2249,7 @@ static int tracing_open(struct inode *inode, struct file *file)
 
         /* If this file was open for write, then erase contents */
         if ((file->f_mode & FMODE_WRITE) &&
-            !(file->f_flags & O_APPEND)) {
+            (file->f_flags & O_TRUNC)) {
                 long cpu = (long) inode->i_private;
 
                 if (cpu == TRACE_PIPE_ALL_CPU)
@@ -2053,25 +2271,23 @@ static int tracing_open(struct inode *inode, struct file *file)
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-        struct tracer *t = m->private;
+        struct tracer *t = v;
 
         (*pos)++;
 
         if (t)
                 t = t->next;
 
-        m->private = t;
-
         return t;
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-        struct tracer *t = m->private;
+        struct tracer *t;
         loff_t l = 0;
 
         mutex_lock(&trace_types_lock);
-        for (; t && l < *pos; t = t_next(m, t, &l))
+        for (t = trace_types; t && l < *pos; t = t_next(m, t, &l))
                 ;
 
         return t;
@@ -2098,7 +2314,7 @@ static int t_show(struct seq_file *m, void *v)
         return 0;
 }
 
-static struct seq_operations show_traces_seq_ops = {
+static const struct seq_operations show_traces_seq_ops = {
         .start          = t_start,
         .next           = t_next,
         .stop           = t_stop,
@@ -2107,18 +2323,10 @@ static struct seq_operations show_traces_seq_ops = {
 
 static int show_traces_open(struct inode *inode, struct file *file)
 {
-        int ret;
-
         if (tracing_disabled)
                 return -ENODEV;
 
-        ret = seq_open(file, &show_traces_seq_ops);
-        if (!ret) {
-                struct seq_file *m = file->private_data;
-                m->private = trace_types;
-        }
-
-        return ret;
+        return seq_open(file, &show_traces_seq_ops);
 }
 
 static ssize_t
@@ -2128,11 +2336,19 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
         return count;
 }
 
+static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
+{
+        if (file->f_mode & FMODE_READ)
+                return seq_lseek(file, offset, origin);
+        else
+                return 0;
+}
+
 static const struct file_operations tracing_fops = {
         .open           = tracing_open,
         .read           = seq_read,
         .write          = tracing_write_stub,
-        .llseek         = seq_lseek,
+        .llseek         = tracing_seek,
         .release        = tracing_release,
 };
 
@@ -2140,6 +2356,7 @@ static const struct file_operations show_traces_fops = {
         .open           = show_traces_open,
         .read           = seq_read,
         .release        = seq_release,
+        .llseek         = seq_lseek,
 };
 
 /*
@@ -2198,7 +2415,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
         mutex_lock(&tracing_cpumask_update_lock);
 
         local_irq_disable();
-        __raw_spin_lock(&ftrace_max_lock);
+        arch_spin_lock(&ftrace_max_lock);
         for_each_tracing_cpu(cpu) {
                 /*
                  * Increase/decrease the disabled counter if we are
@@ -2213,7 +2430,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
                         atomic_dec(&global_trace.data[cpu]->disabled);
                 }
         }
-        __raw_spin_unlock(&ftrace_max_lock);
+        arch_spin_unlock(&ftrace_max_lock);
         local_irq_enable();
 
         cpumask_copy(tracing_cpumask, tracing_cpumask_new);
@@ -2233,103 +2450,70 @@ static const struct file_operations tracing_cpumask_fops = {
         .open           = tracing_open_generic,
         .read           = tracing_cpumask_read,
         .write          = tracing_cpumask_write,
+        .llseek         = generic_file_llseek,
 };
 
-static ssize_t
-tracing_trace_options_read(struct file *filp, char __user *ubuf,
-                       size_t cnt, loff_t *ppos)
+static int tracing_trace_options_show(struct seq_file *m, void *v)
 {
         struct tracer_opt *trace_opts;
         u32 tracer_flags;
-        int len = 0;
-        char *buf;
-        int r = 0;
         int i;
 
-
-        /* calculate max size */
-        for (i = 0; trace_options[i]; i++) {
-                len += strlen(trace_options[i]);
-                len += 3; /* "no" and newline */
-        }
-
         mutex_lock(&trace_types_lock);
         tracer_flags = current_trace->flags->val;
         trace_opts = current_trace->flags->opts;
 
-        /*
-         * Increase the size with names of options specific
-         * of the current tracer.
-         */
-        for (i = 0; trace_opts[i].name; i++) {
-                len += strlen(trace_opts[i].name);
-                len += 3; /* "no" and newline */
-        }
-
-        /* +2 for \n and \0 */
-        buf = kmalloc(len + 2, GFP_KERNEL);
-        if (!buf) {
-                mutex_unlock(&trace_types_lock);
-                return -ENOMEM;
-        }
-
         for (i = 0; trace_options[i]; i++) {
                 if (trace_flags & (1 << i))
-                        r += sprintf(buf + r, "%s\n", trace_options[i]);
+                        seq_printf(m, "%s\n", trace_options[i]);
                 else
-                        r += sprintf(buf + r, "no%s\n", trace_options[i]);
+                        seq_printf(m, "no%s\n", trace_options[i]);
         }
 
         for (i = 0; trace_opts[i].name; i++) {
                 if (tracer_flags & trace_opts[i].bit)
-                        r += sprintf(buf + r, "%s\n",
-                                trace_opts[i].name);
+                        seq_printf(m, "%s\n", trace_opts[i].name);
                 else
-                        r += sprintf(buf + r, "no%s\n",
-                                trace_opts[i].name);
+                        seq_printf(m, "no%s\n", trace_opts[i].name);
         }
         mutex_unlock(&trace_types_lock);
 
-        WARN_ON(r >= len + 2);
+        return 0;
+}
 
-        r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+static int __set_tracer_option(struct tracer *trace,
+                               struct tracer_flags *tracer_flags,
+                               struct tracer_opt *opts, int neg)
+{
+        int ret;
 
-        kfree(buf);
-        return r;
+        ret = trace->set_flag(tracer_flags->val, opts->bit, !neg);
+        if (ret)
+                return ret;
+
+        if (neg)
+                tracer_flags->val &= ~opts->bit;
+        else
+                tracer_flags->val |= opts->bit;
+        return 0;
 }
 
 /* Try to assign a tracer specific option */
 static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 {
-        struct tracer_flags *trace_flags = trace->flags;
+        struct tracer_flags *tracer_flags = trace->flags;
         struct tracer_opt *opts = NULL;
-        int ret = 0, i = 0;
-        int len;
+        int i;
 
-        for (i = 0; trace_flags->opts[i].name; i++) {
-                opts = &trace_flags->opts[i];
-                len = strlen(opts->name);
+        for (i = 0; tracer_flags->opts[i].name; i++) {
+                opts = &tracer_flags->opts[i];
 
-                if (strncmp(cmp, opts->name, len) == 0) {
-                        ret = trace->set_flag(trace_flags->val,
-                                opts->bit, !neg);
-                        break;
-                }
+                if (strcmp(cmp, opts->name) == 0)
+                        return __set_tracer_option(trace, trace->flags,
+                                                   opts, neg);
         }
-        /* Not found */
-        if (!trace_flags->opts[i].name)
-                return -EINVAL;
-
-        /* Refused to handle */
-        if (ret)
-                return ret;
 
-        if (neg)
-                trace_flags->val &= ~opts->bit;
-        else
-                trace_flags->val |= opts->bit;
-
-        return 0;
+        return -EINVAL;
 }
 
 static void set_tracer_flags(unsigned int mask, int enabled)
@@ -2343,21 +2527,8 @@ static void set_tracer_flags(unsigned int mask, int enabled)
         else
                 trace_flags &= ~mask;
 
-        if (mask == TRACE_ITER_GLOBAL_CLK) {
-                u64 (*func)(void);
-
-                if (enabled)
-                        func = trace_clock_global;
-                else
-                        func = trace_clock_local;
-
-                mutex_lock(&trace_types_lock);
-                ring_buffer_set_clock(global_trace.buffer, func);
-
-                if (max_tr.buffer)
-                        ring_buffer_set_clock(max_tr.buffer, func);
-                mutex_unlock(&trace_types_lock);
-        }
+        if (mask == TRACE_ITER_RECORD_CMD)
+                trace_event_enable_cmd_record(enabled);
 }
 
 static ssize_t
@@ -2365,7 +2536,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
                         size_t cnt, loff_t *ppos)
 {
         char buf[64];
-        char *cmp = buf;
+        char *cmp;
         int neg = 0;
         int ret;
         int i;
@@ -2377,16 +2548,15 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
                 return -EFAULT;
 
         buf[cnt] = 0;
+        cmp = strstrip(buf);
 
-        if (strncmp(buf, "no", 2) == 0) {
+        if (strncmp(cmp, "no", 2) == 0) {
                 neg = 1;
                 cmp += 2;
         }
 
         for (i = 0; trace_options[i]; i++) {
-                int len = strlen(trace_options[i]);
-
-                if (strncmp(cmp, trace_options[i], len) == 0) {
+                if (strcmp(cmp, trace_options[i]) == 0) {
                         set_tracer_flags(1 << i, !neg);
                         break;
                 }
@@ -2401,14 +2571,23 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
                         return ret;
         }
 
-        filp->f_pos += cnt;
+        *ppos += cnt;
 
         return cnt;
 }
 
+static int tracing_trace_options_open(struct inode *inode, struct file *file)
+{
+        if (tracing_disabled)
+                return -ENODEV;
+        return single_open(file, tracing_trace_options_show, NULL);
+}
+
 static const struct file_operations tracing_iter_fops = {
-        .open           = tracing_open_generic,
-        .read           = tracing_trace_options_read,
+        .open           = tracing_trace_options_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
         .write          = tracing_trace_options_write,
 };
 
@@ -2441,6 +2620,7 @@ tracing_readme_read(struct file *filp, char __user *ubuf,
 static const struct file_operations tracing_readme_fops = {
         .open           = tracing_open_generic,
         .read           = tracing_readme_read,
+        .llseek         = generic_file_llseek,
 };
 
 static ssize_t
@@ -2491,6 +2671,7 @@ tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
 static const struct file_operations tracing_saved_cmdlines_fops = {
     .open       = tracing_open_generic,
     .read       = tracing_saved_cmdlines_read,
+    .llseek     = generic_file_llseek,
 };
 
 static ssize_t
@@ -2543,7 +2724,7 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
         }
         mutex_unlock(&trace_types_lock);
 
-        filp->f_pos += cnt;
+        *ppos += cnt;
 
         return cnt;
 }
@@ -2552,7 +2733,7 @@ static ssize_t
 tracing_set_trace_read(struct file *filp, char __user *ubuf,
                        size_t cnt, loff_t *ppos)
 {
-        char buf[max_tracer_type_len+2];
+        char buf[MAX_TRACER_SIZE+2];
         int r;
 
         mutex_lock(&trace_types_lock);
@@ -2586,6 +2767,9 @@ static int tracing_resize_ring_buffer(unsigned long size)
         if (ret < 0)
                 return ret;
 
+        if (!current_trace->use_max_tr)
+                goto out;
+
         ret = ring_buffer_resize(max_tr.buffer, size);
         if (ret < 0) {
                 int r;
@@ -2613,11 +2797,14 @@ static int tracing_resize_ring_buffer(unsigned long size)
                 return ret;
         }
 
+        max_tr.entries = size;
+ out:
         global_trace.entries = size;
 
         return ret;
 }
 
+
 /**
  * tracing_update_buffers - used by tracing facility to expand ring buffers
  *
@@ -2678,12 +2865,26 @@ static int tracing_set_tracer(const char *buf)
         trace_branch_disable();
         if (current_trace && current_trace->reset)
                 current_trace->reset(tr);
-
+        if (current_trace && current_trace->use_max_tr) {
+                /*
+                 * We don't free the ring buffer. instead, resize it because
+                 * The max_tr ring buffer has some state (e.g. ring->clock) and
+                 * we want preserve it.
+                 */
+                ring_buffer_resize(max_tr.buffer, 1);
+                max_tr.entries = 1;
+        }
         destroy_trace_option_files(topts);
 
         current_trace = t;
 
         topts = create_trace_option_files(current_trace);
+        if (current_trace->use_max_tr) {
+                ret = ring_buffer_resize(max_tr.buffer, global_trace.entries);
+                if (ret < 0)
+                        goto out;
+                max_tr.entries = global_trace.entries;
+        }
 
         if (t->init) {
                 ret = tracer_init(t, tr);
@@ -2702,15 +2903,15 @@ static ssize_t
 tracing_set_trace_write(struct file *filp, const char __user *ubuf,
                         size_t cnt, loff_t *ppos)
 {
-        char buf[max_tracer_type_len+1];
+        char buf[MAX_TRACER_SIZE+1];
         int i;
         size_t ret;
         int err;
 
         ret = cnt;
 
-        if (cnt > max_tracer_type_len)
-                cnt = max_tracer_type_len;
+        if (cnt > MAX_TRACER_SIZE)
+                cnt = MAX_TRACER_SIZE;
 
         if (copy_from_user(&buf, ubuf, cnt))
                 return -EFAULT;
@@ -2725,7 +2926,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
         if (err)
                 return err;
 
-        filp->f_pos += ret;
+        *ppos += ret;
 
         return ret;
 }
@@ -2782,22 +2983,6 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 
         mutex_lock(&trace_types_lock);
 
-        /* We only allow one reader per cpu */
-        if (cpu_file == TRACE_PIPE_ALL_CPU) {
-                if (!cpumask_empty(tracing_reader_cpumask)) {
-                        ret = -EBUSY;
-                        goto out;
-                }
-                cpumask_setall(tracing_reader_cpumask);
-        } else {
-                if (!cpumask_test_cpu(cpu_file, tracing_reader_cpumask))
-                        cpumask_set_cpu(cpu_file, tracing_reader_cpumask);
-                else {
-                        ret = -EBUSY;
-                        goto out;
-                }
-        }
-
         /* create a buffer to store the information to pass to userspace */
         iter = kzalloc(sizeof(*iter), GFP_KERNEL);
         if (!iter) {
@@ -2836,6 +3021,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
         if (iter->trace->pipe_open)
                 iter->trace->pipe_open(iter);
 
+        nonseekable_open(inode, filp);
 out:
         mutex_unlock(&trace_types_lock);
         return ret;
@@ -2853,10 +3039,8 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
         mutex_lock(&trace_types_lock);
 
-        if (iter->cpu_file == TRACE_PIPE_ALL_CPU)
-                cpumask_clear(tracing_reader_cpumask);
-        else
-                cpumask_clear_cpu(iter->cpu_file, tracing_reader_cpumask);
+        if (iter->trace->pipe_close)
+                iter->trace->pipe_close(iter);
 
         mutex_unlock(&trace_types_lock);
 
@@ -3016,7 +3200,8 @@ waitagain:
         iter->pos = -1;
 
         trace_event_read_lock();
-        while (find_next_entry_inc(iter) != NULL) {
+        trace_access_lock(iter->cpu_file);
+        while (trace_find_next_entry_inc(iter) != NULL) {
                 enum print_line_t ret;
                 int len = iter->seq.len;
 
@@ -3032,6 +3217,7 @@ waitagain:
                 if (iter->seq.len >= cnt)
                         break;
         }
+        trace_access_unlock(iter->cpu_file);
         trace_event_read_unlock();
 
         /* Now copy what we have to the user */
@@ -3064,7 +3250,7 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
         __free_page(spd->pages[idx]);
 }
 
-static struct pipe_buf_operations tracing_pipe_buf_ops = {
+static const struct pipe_buf_operations tracing_pipe_buf_ops = {
         .can_merge              = 0,
         .map                    = generic_pipe_buf_map,
         .unmap                  = generic_pipe_buf_unmap,
@@ -3095,9 +3281,10 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
                         break;
                 }
 
-                trace_consume(iter);
+                if (ret != TRACE_TYPE_NO_CONSUME)
+                        trace_consume(iter);
                 rem -= count;
-                if (!find_next_entry_inc(iter)) {
+                if (!trace_find_next_entry_inc(iter))   {
                         rem = 0;
                         iter->ent = NULL;
                         break;
@@ -3113,12 +3300,12 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
                                         size_t len,
                                         unsigned int flags)
 {
-        struct page *pages[PIPE_BUFFERS];
-        struct partial_page partial[PIPE_BUFFERS];
+        struct page *pages_def[PIPE_DEF_BUFFERS];
+        struct partial_page partial_def[PIPE_DEF_BUFFERS];
         struct trace_iterator *iter = filp->private_data;
         struct splice_pipe_desc spd = {
-                .pages          = pages,
-                .partial        = partial,
+                .pages          = pages_def,
+                .partial        = partial_def,
                 .nr_pages       = 0, /* This gets updated below. */
                 .flags          = flags,
                 .ops            = &tracing_pipe_buf_ops,
@@ -3129,6 +3316,9 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
         size_t rem;
         unsigned int i;
 
+        if (splice_grow_spd(pipe, &spd))
+                return -ENOMEM;
+
         /* copy the tracer to avoid using a global lock all around */
         mutex_lock(&trace_types_lock);
         if (unlikely(old_tracer != current_trace && current_trace)) {
@@ -3150,46 +3340,50 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
         if (ret <= 0)
                 goto out_err;
 
-        if (!iter->ent && !find_next_entry_inc(iter)) {
+        if (!iter->ent && !trace_find_next_entry_inc(iter)) {
                 ret = -EFAULT;
                 goto out_err;
         }
 
         trace_event_read_lock();
+        trace_access_lock(iter->cpu_file);
 
         /* Fill as many pages as possible. */
-        for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
-                pages[i] = alloc_page(GFP_KERNEL);
-                if (!pages[i])
+        for (i = 0, rem = len; i < pipe->buffers && rem; i++) {
+                spd.pages[i] = alloc_page(GFP_KERNEL);
+                if (!spd.pages[i])
                         break;
 
                 rem = tracing_fill_pipe_page(rem, iter);
 
                 /* Copy the data into the page, so we can start over. */
                 ret = trace_seq_to_buffer(&iter->seq,
-                                          page_address(pages[i]),
+                                          page_address(spd.pages[i]),
                                           iter->seq.len);
                 if (ret < 0) {
-                        __free_page(pages[i]);
+                        __free_page(spd.pages[i]);
                         break;
                 }
-                partial[i].offset = 0;
-                partial[i].len = iter->seq.len;
+                spd.partial[i].offset = 0;
+                spd.partial[i].len = iter->seq.len;
 
                 trace_seq_init(&iter->seq);
         }
 
+        trace_access_unlock(iter->cpu_file);
         trace_event_read_unlock();
         mutex_unlock(&iter->mutex);
 
         spd.nr_pages = i;
 
-        return splice_to_pipe(pipe, &spd);
+        ret = splice_to_pipe(pipe, &spd);
+out:
+        splice_shrink_spd(pipe, &spd);
+        return ret;
 
 out_err:
         mutex_unlock(&iter->mutex);
-
-        return ret;
+        goto out;
 }
 
 static ssize_t
@@ -3259,7 +3453,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
                 }
         }
 
-        filp->f_pos += cnt;
+        *ppos += cnt;
 
         /* If check pages failed, return ENOMEM */
         if (tracing_disabled)
@@ -3273,7 +3467,6 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
         }
 
         tracing_start();
-        max_tr.entries = global_trace.entries;
         mutex_unlock(&trace_types_lock);
 
         return cnt;
@@ -3294,7 +3487,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
                                         size_t cnt, loff_t *fpos)
 {
         char *buf;
-        char *end;
+        size_t written;
 
         if (tracing_disabled)
                 return -EINVAL;
@@ -3302,7 +3495,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
         if (cnt > TRACE_BUF_SIZE)
                 cnt = TRACE_BUF_SIZE;
 
-        buf = kmalloc(cnt + 1, GFP_KERNEL);
+        buf = kmalloc(cnt + 2, GFP_KERNEL);
         if (buf == NULL)
                 return -ENOMEM;
 
@@ -3310,36 +3503,102 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
                 kfree(buf);
                 return -EFAULT;
         }
+        if (buf[cnt-1] != '\n') {
+                buf[cnt] = '\n';
+                buf[cnt+1] = '\0';
+        } else
+                buf[cnt] = '\0';
 
-        /* Cut from the first nil or newline. */
-        buf[cnt] = '\0';
-        end = strchr(buf, '\n');
-        if (end)
-                *end = '\0';
-
-        cnt = mark_printk("%s\n", buf);
+        written = mark_printk("%s", buf);
         kfree(buf);
+        *fpos += written;
+
+        /* don't tell userspace we wrote more - it might confuse them */
+        if (written > cnt)
+                written = cnt;
+
+        return written;
+}
+
+static int tracing_clock_show(struct seq_file *m, void *v)
+{
+        int i;
+
+        for (i = 0; i < ARRAY_SIZE(trace_clocks); i++)
+                seq_printf(m,
+                        "%s%s%s%s", i ? " " : "",
+                        i == trace_clock_id ? "[" : "", trace_clocks[i].name,
+                        i == trace_clock_id ? "]" : "");
+        seq_putc(m, '\n');
+
+        return 0;
+}
+
+static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
+                                   size_t cnt, loff_t *fpos)
+{
+        char buf[64];
+        const char *clockstr;
+        int i;
+
+        if (cnt >= sizeof(buf))
+                return -EINVAL;
+
+        if (copy_from_user(&buf, ubuf, cnt))
+                return -EFAULT;
+
+        buf[cnt] = 0;
+
+        clockstr = strstrip(buf);
+
+        for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) {
+                if (strcmp(trace_clocks[i].name, clockstr) == 0)
+                        break;
+        }
+        if (i == ARRAY_SIZE(trace_clocks))
+                return -EINVAL;
+
+        trace_clock_id = i;
+
+        mutex_lock(&trace_types_lock);
+
+        ring_buffer_set_clock(global_trace.buffer, trace_clocks[i].func);
+        if (max_tr.buffer)
+                ring_buffer_set_clock(max_tr.buffer, trace_clocks[i].func);
+
+        mutex_unlock(&trace_types_lock);
+
         *fpos += cnt;
 
         return cnt;
 }
 
+static int tracing_clock_open(struct inode *inode, struct file *file)
+{
+        if (tracing_disabled)
+                return -ENODEV;
+        return single_open(file, tracing_clock_show, NULL);
+}
+
 static const struct file_operations tracing_max_lat_fops = {
         .open           = tracing_open_generic,
         .read           = tracing_max_lat_read,
         .write          = tracing_max_lat_write,
+        .llseek         = generic_file_llseek,
 };
 
 static const struct file_operations tracing_ctrl_fops = {
         .open           = tracing_open_generic,
         .read           = tracing_ctrl_read,
         .write          = tracing_ctrl_write,
+        .llseek         = generic_file_llseek,
 };
 
 static const struct file_operations set_tracer_fops = {
         .open           = tracing_open_generic,
         .read           = tracing_set_trace_read,
         .write          = tracing_set_trace_write,
+        .llseek         = generic_file_llseek,
 };
 
 static const struct file_operations tracing_pipe_fops = {
@@ -3348,17 +3607,28 @@ static const struct file_operations tracing_pipe_fops = {
         .read           = tracing_read_pipe,
         .splice_read    = tracing_splice_read_pipe,
         .release        = tracing_release_pipe,
+        .llseek         = no_llseek,
 };
 
 static const struct file_operations tracing_entries_fops = {
         .open           = tracing_open_generic,
         .read           = tracing_entries_read,
         .write          = tracing_entries_write,
+        .llseek         = generic_file_llseek,
 };
 
 static const struct file_operations tracing_mark_fops = {
         .open           = tracing_open_generic,
         .write          = tracing_mark_write,
+        .llseek         = generic_file_llseek,
+};
+
+static const struct file_operations trace_clock_fops = {
+        .open           = tracing_clock_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = tracing_clock_write,
 };
 
 struct ftrace_buffer_info {
@@ -3396,7 +3666,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
                      size_t count, loff_t *ppos)
 {
         struct ftrace_buffer_info *info = filp->private_data;
-        unsigned int pos;
         ssize_t ret;
         size_t size;
 
@@ -3414,18 +3683,15 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 
         info->read = 0;
 
+        trace_access_lock(info->cpu);
         ret = ring_buffer_read_page(info->tr->buffer,
                                     &info->spare,
                                     count,
                                     info->cpu, 0);
+        trace_access_unlock(info->cpu);
         if (ret < 0)
                 return 0;
 
-        pos = ring_buffer_page_len(info->spare);
-
-        if (pos < PAGE_SIZE)
-                memset(info->spare + pos, 0, PAGE_SIZE - pos);
-
 read:
         size = PAGE_SIZE - info->read;
         if (size > count)
@@ -3487,7 +3753,7 @@ static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 }
 
 /* Pipe buffer operations for a buffer. */
-static struct pipe_buf_operations buffer_pipe_buf_ops = {
+static const struct pipe_buf_operations buffer_pipe_buf_ops = {
         .can_merge              = 0,
         .map                    = generic_pipe_buf_map,
         .unmap                  = generic_pipe_buf_unmap,
@@ -3520,11 +3786,11 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
                             unsigned int flags)
 {
         struct ftrace_buffer_info *info = file->private_data;
-        struct partial_page partial[PIPE_BUFFERS];
-        struct page *pages[PIPE_BUFFERS];
+        struct partial_page partial_def[PIPE_DEF_BUFFERS];
+        struct page *pages_def[PIPE_DEF_BUFFERS];
         struct splice_pipe_desc spd = {
-                .pages          = pages,
-                .partial        = partial,
+                .pages          = pages_def,
+                .partial        = partial_def,
                 .flags          = flags,
                 .ops            = &buffer_pipe_buf_ops,
                 .spd_release    = buffer_spd_release,
@@ -3533,21 +3799,28 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
         int entries, size, i;
         size_t ret;
 
+        if (splice_grow_spd(pipe, &spd))
+                return -ENOMEM;
+
         if (*ppos & (PAGE_SIZE - 1)) {
                 WARN_ONCE(1, "Ftrace: previous read must page-align\n");
-                return -EINVAL;
+                ret = -EINVAL;
+                goto out;
         }
 
         if (len & (PAGE_SIZE - 1)) {
                 WARN_ONCE(1, "Ftrace: splice_read should page-align\n");
-                if (len < PAGE_SIZE)
-                        return -EINVAL;
+                if (len < PAGE_SIZE) {
+                        ret = -EINVAL;
+                        goto out;
+                }
                 len &= PAGE_MASK;
         }
 
+        trace_access_lock(info->cpu);
         entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
 
-        for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
+        for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) {
                 struct page *page;
                 int r;
 
@@ -3592,6 +3865,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
                 entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
         }
 
+        trace_access_unlock(info->cpu);
         spd.nr_pages = i;
 
         /* did we read anything? */
@@ -3601,11 +3875,12 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
                 else
                         ret = 0;
                 /* TODO: block */
-                return ret;
+                goto out;
         }
 
         ret = splice_to_pipe(pipe, &spd);
-
+        splice_shrink_spd(pipe, &spd);
+out:
         return ret;
 }
 
@@ -3628,7 +3903,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 
         s = kmalloc(sizeof(*s), GFP_KERNEL);
         if (!s)
-                return ENOMEM;
+                return -ENOMEM;
 
         trace_seq_init(s);
 
@@ -3641,9 +3916,6 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
         cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
         trace_seq_printf(s, "commit overrun: %ld\n", cnt);
 
-        cnt = ring_buffer_nmi_dropped_cpu(tr->buffer, cpu);
-        trace_seq_printf(s, "nmi dropped: %ld\n", cnt);
-
         count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
 
         kfree(s);
@@ -3654,6 +3926,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 static const struct file_operations tracing_stats_fops = {
         .open           = tracing_open_generic,
         .read           = tracing_stats_read,
+        .llseek         = generic_file_llseek,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -3690,6 +3963,7 @@ tracing_read_dyn_info(struct file *filp, char __user *ubuf,
 static const struct file_operations tracing_dyn_info_fops = {
         .open           = tracing_open_generic,
         .read           = tracing_read_dyn_info,
+        .llseek         = generic_file_llseek,
 };
 #endif
 
@@ -3746,13 +4020,9 @@ static void tracing_init_debugfs_percpu(long cpu)
 {
         struct dentry *d_percpu = tracing_dentry_percpu();
         struct dentry *d_cpu;
-        /* strlen(cpu) + MAX(log10(cpu)) + '\0' */
-        char cpu_dir[7];
-
-        if (cpu > 999 || cpu < 0)
-                return;
+        char cpu_dir[30]; /* 30 characters should be more than enough */
 
-        sprintf(cpu_dir, "cpu%ld", cpu);
+        snprintf(cpu_dir, 30, "cpu%ld", cpu);
         d_cpu = debugfs_create_dir(cpu_dir, d_percpu);
         if (!d_cpu) {
                 pr_warning("Could not create debugfs '%s' entry\n", cpu_dir);
@@ -3821,39 +4091,16 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
         if (ret < 0)
                 return ret;
 
-        ret = 0;
-        switch (val) {
-        case 0:
-                /* do nothing if already cleared */
-                if (!(topt->flags->val & topt->opt->bit))
-                        break;
-
-                mutex_lock(&trace_types_lock);
-                if (current_trace->set_flag)
-                        ret = current_trace->set_flag(topt->flags->val,
-                                                      topt->opt->bit, 0);
-                mutex_unlock(&trace_types_lock);
-                if (ret)
-                        return ret;
-                topt->flags->val &= ~topt->opt->bit;
-                break;
-        case 1:
-                /* do nothing if already set */
-                if (topt->flags->val & topt->opt->bit)
-                        break;
+        if (val != 0 && val != 1)
+                return -EINVAL;
 
+        if (!!(topt->flags->val & topt->opt->bit) != val) {
                 mutex_lock(&trace_types_lock);
-                if (current_trace->set_flag)
-                        ret = current_trace->set_flag(topt->flags->val,
-                                                      topt->opt->bit, 1);
+                ret = __set_tracer_option(current_trace, topt->flags,
+                                          topt->opt, !val);
                 mutex_unlock(&trace_types_lock);
                 if (ret)
                         return ret;
-                topt->flags->val |= topt->opt->bit;
-                break;
-
-        default:
-                return -EINVAL;
         }
 
         *ppos += cnt;
@@ -3866,6 +4113,7 @@ static const struct file_operations trace_options_fops = {
         .open = tracing_open_generic,
         .read = trace_options_read,
         .write = trace_options_write,
+        .llseek = generic_file_llseek,
 };
 
 static ssize_t
@@ -3904,17 +4152,9 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
         if (ret < 0)
                 return ret;
 
-        switch (val) {
-        case 0:
-                trace_flags &= ~(1 << index);
-                break;
-        case 1:
-                trace_flags |= 1 << index;
-                break;
-
-        default:
+        if (val != 0 && val != 1)
                 return -EINVAL;
-        }
+        set_tracer_flags(1 << index, val);
 
         *ppos += cnt;
 
@@ -3925,6 +4165,7 @@ static const struct file_operations trace_options_core_fops = {
         .open = tracing_open_generic,
         .read = trace_options_core_read,
         .write = trace_options_core_write,
+        .llseek = generic_file_llseek,
 };
 
 struct dentry *trace_create_file(const char *name,
@@ -4062,6 +4303,8 @@ static __init int tracer_init_debugfs(void)
         struct dentry *d_tracer;
         int cpu;
 
+        trace_access_lock_init();
+
         d_tracer = tracing_init_dentry();
 
         trace_create_file("tracing_enabled", 0644, d_tracer,
@@ -4082,8 +4325,10 @@ static __init int tracer_init_debugfs(void)
         trace_create_file("current_tracer", 0644, d_tracer,
                         &global_trace, &set_tracer_fops);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
         trace_create_file("tracing_max_latency", 0644, d_tracer,
                         &tracing_max_latency, &tracing_max_lat_fops);
+#endif
 
         trace_create_file("tracing_thresh", 0644, d_tracer,
                         &tracing_thresh, &tracing_max_lat_fops);
@@ -4103,13 +4348,13 @@ static __init int tracer_init_debugfs(void)
         trace_create_file("saved_cmdlines", 0444, d_tracer,
                         NULL, &tracing_saved_cmdlines_fops);
 
+        trace_create_file("trace_clock", 0644, d_tracer, NULL,
+                          &trace_clock_fops);
+
 #ifdef CONFIG_DYNAMIC_FTRACE
         trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
                         &ftrace_update_tot_cnt, &tracing_dyn_info_fops);
 #endif
-#ifdef CONFIG_SYSPROF_TRACER
-        init_tracer_sysprof_debugfs(d_tracer);
-#endif
 
         create_trace_options_dir();
 
@@ -4123,7 +4368,7 @@ static int trace_panic_handler(struct notifier_block *this,
                                unsigned long event, void *unused)
 {
         if (ftrace_dump_on_oops)
-                ftrace_dump();
+                ftrace_dump(ftrace_dump_on_oops);
         return NOTIFY_OK;
 }
 
@@ -4140,7 +4385,7 @@ static int trace_die_handler(struct notifier_block *self,
         switch (val) {
         case DIE_OOPS:
                 if (ftrace_dump_on_oops)
-                        ftrace_dump();
+                        ftrace_dump(ftrace_dump_on_oops);
                 break;
         default:
                 break;
@@ -4166,7 +4411,7 @@ static struct notifier_block trace_die_notifier = {
  */
 #define KERN_TRACE              KERN_EMERG
 
-static void
+void
 trace_printk_seq(struct trace_seq *s)
 {
         /* Probably should print a warning here. */
@@ -4181,10 +4426,18 @@ trace_printk_seq(struct trace_seq *s)
         trace_seq_init(s);
 }
 
-static void __ftrace_dump(bool disable_tracing)
+void trace_init_global_iter(struct trace_iterator *iter)
+{
+        iter->tr = &global_trace;
+        iter->trace = current_trace;
+        iter->cpu_file = TRACE_PIPE_ALL_CPU;
+}
+
+static void
+__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 {
-        static raw_spinlock_t ftrace_dump_lock =
-                (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+        static arch_spinlock_t ftrace_dump_lock =
+                (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
         /* use static because iter can be a bit big for the stack */
         static struct trace_iterator iter;
         unsigned int old_userobj;
@@ -4194,7 +4447,7 @@ static void __ftrace_dump(bool disable_tracing)
 
         /* only one dump */
         local_irq_save(flags);
-        __raw_spin_lock(&ftrace_dump_lock);
+        arch_spin_lock(&ftrace_dump_lock);
         if (dump_ran)
                 goto out;
 
@@ -4205,8 +4458,10 @@ static void __ftrace_dump(bool disable_tracing)
         if (disable_tracing)
                 ftrace_kill();
 
+        trace_init_global_iter(&iter);
+
         for_each_tracing_cpu(cpu) {
-                atomic_inc(&global_trace.data[cpu]->disabled);
+                atomic_inc(&iter.tr->data[cpu]->disabled);
         }
 
         old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ;
@@ -4214,12 +4469,25 @@ static void __ftrace_dump(bool disable_tracing)
         /* don't look at user memory in panic mode */
         trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
-        printk(KERN_TRACE "Dumping ftrace buffer:\n");
-
         /* Simulate the iterator */
         iter.tr = &global_trace;
         iter.trace = current_trace;
-        iter.cpu_file = TRACE_PIPE_ALL_CPU;
+
+        switch (oops_dump_mode) {
+        case DUMP_ALL:
+                iter.cpu_file = TRACE_PIPE_ALL_CPU;
+                break;
+        case DUMP_ORIG:
+                iter.cpu_file = raw_smp_processor_id();
+                break;
+        case DUMP_NONE:
+                goto out_enable;
+        default:
+                printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n");
+                iter.cpu_file = TRACE_PIPE_ALL_CPU;
+        }
+
+        printk(KERN_TRACE "Dumping ftrace buffer:\n");
 
         /*
          * We need to stop all tracing on all CPUS to read the
@@ -4242,9 +4510,12 @@ static void __ftrace_dump(bool disable_tracing)
                 iter.iter_flags |= TRACE_FILE_LAT_FMT;
                 iter.pos = -1;
 
-                if (find_next_entry_inc(&iter) != NULL) {
-                        print_trace_line(&iter);
-                        trace_consume(&iter);
+                if (trace_find_next_entry_inc(&iter) != NULL) {
+                        int ret;
+
+                        ret = print_trace_line(&iter);
+                        if (ret != TRACE_TYPE_NO_CONSUME)
+                                trace_consume(&iter);
                 }
 
                 trace_printk_seq(&iter.seq);
@@ -4255,30 +4526,30 @@ static void __ftrace_dump(bool disable_tracing)
         else
                 printk(KERN_TRACE "---------------------------------\n");
 
+ out_enable:
         /* Re-enable tracing if requested */
         if (!disable_tracing) {
                 trace_flags |= old_userobj;
 
                 for_each_tracing_cpu(cpu) {
-                        atomic_dec(&global_trace.data[cpu]->disabled);
+                        atomic_dec(&iter.tr->data[cpu]->disabled);
                 }
                 tracing_on();
         }
 
  out:
-        __raw_spin_unlock(&ftrace_dump_lock);
+        arch_spin_unlock(&ftrace_dump_lock);
         local_irq_restore(flags);
 }
 
 /* By default: disable tracing after the dump */
-void ftrace_dump(void)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 {
-        __ftrace_dump(true);
+        __ftrace_dump(true, oops_dump_mode);
 }
 
 __init static int tracer_alloc_buffers(void)
 {
-        struct trace_array_cpu *data;
         int ring_buf_size;
         int i;
         int ret = -ENOMEM;
@@ -4289,9 +4560,6 @@ __init static int tracer_alloc_buffers(void)
         if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
                 goto out_free_buffer_mask;
 
-        if (!alloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
-                goto out_free_tracing_cpumask;
-
         /* To save memory, keep the ring buffer size to its minimum */
         if (ring_buffer_expanded)
                 ring_buf_size = trace_buf_size;
@@ -4300,7 +4568,6 @@ __init static int tracer_alloc_buffers(void)
 
         cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
         cpumask_copy(tracing_cpumask, cpu_all_mask);
-        cpumask_clear(tracing_reader_cpumask);
 
         /* TODO: make the number of buffers hot pluggable with CPUS */
         global_trace.buffer = ring_buffer_alloc(ring_buf_size,
@@ -4314,31 +4581,26 @@ __init static int tracer_alloc_buffers(void)
 
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-        max_tr.buffer = ring_buffer_alloc(ring_buf_size,
-                                             TRACE_BUFFER_FLAGS);
+        max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS);
         if (!max_tr.buffer) {
                 printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
                 WARN_ON(1);
                 ring_buffer_free(global_trace.buffer);
                 goto out_free_cpumask;
         }
-        max_tr.entries = ring_buffer_size(max_tr.buffer);
-        WARN_ON(max_tr.entries != global_trace.entries);
+        max_tr.entries = 1;
 #endif
 
         /* Allocate the first page for all buffers */
         for_each_tracing_cpu(i) {
-                data = global_trace.data[i] = &per_cpu(global_trace_cpu, i);
-                max_tr.data[i] = &per_cpu(max_data, i);
+                global_trace.data[i] = &per_cpu(global_trace_cpu, i);
+                max_tr.data[i] = &per_cpu(max_tr_data, i);
         }
 
         trace_init_cmdlines();
 
         register_tracer(&nop_trace);
         current_trace = &nop_trace;
-#ifdef CONFIG_BOOT_TRACER
-        register_tracer(&boot_tracer);
-#endif
         /* All seems OK, enable tracing */
         tracing_disabled = 0;
 
@@ -4350,8 +4612,6 @@ __init static int tracer_alloc_buffers(void)
         return 0;
 
 out_free_cpumask:
-        free_cpumask_var(tracing_reader_cpumask);
-out_free_tracing_cpumask:
         free_cpumask_var(tracing_cpumask);
 out_free_buffer_mask:
         free_cpumask_var(tracing_buffer_mask);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6e735d4771f8..9021f8c0c0c3 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -7,11 +7,9 @@
 #include <linux/clocksource.h>
 #include <linux/ring_buffer.h>
 #include <linux/mmiotrace.h>
+#include <linux/tracepoint.h>
 #include <linux/ftrace.h>
-#include <trace/boot.h>
-#include <linux/kmemtrace.h>
-#include <trace/power.h>
-
+#include <linux/hw_breakpoint.h>
 #include <linux/trace_seq.h>
 #include <linux/ftrace_event.h>
 
@@ -24,177 +22,58 @@ enum trace_type {
         TRACE_STACK,
         TRACE_PRINT,
         TRACE_BPRINT,
-        TRACE_SPECIAL,
         TRACE_MMIO_RW,
         TRACE_MMIO_MAP,
         TRACE_BRANCH,
-        TRACE_BOOT_CALL,
-        TRACE_BOOT_RET,
         TRACE_GRAPH_RET,
         TRACE_GRAPH_ENT,
         TRACE_USER_STACK,
-        TRACE_HW_BRANCHES,
-        TRACE_SYSCALL_ENTER,
-        TRACE_SYSCALL_EXIT,
-        TRACE_KMEM_ALLOC,
-        TRACE_KMEM_FREE,
-        TRACE_POWER,
         TRACE_BLK,
 
         __TRACE_LAST_TYPE,
 };
 
-/*
- * Function trace entry - function address and parent function addres:
- */
-struct ftrace_entry {
-        struct trace_entry      ent;
-        unsigned long           ip;
-        unsigned long           parent_ip;
-};
-
-/* Function call entry */
-struct ftrace_graph_ent_entry {
-        struct trace_entry              ent;
-        struct ftrace_graph_ent         graph_ent;
-};
-
-/* Function return entry */
-struct ftrace_graph_ret_entry {
-        struct trace_entry              ent;
-        struct ftrace_graph_ret         ret;
-};
-extern struct tracer boot_tracer;
-
-/*
- * Context switch trace entry - which task (and prio) we switched from/to:
- */
-struct ctx_switch_entry {
-        struct trace_entry      ent;
-        unsigned int            prev_pid;
-        unsigned char           prev_prio;
-        unsigned char           prev_state;
-        unsigned int            next_pid;
-        unsigned char           next_prio;
-        unsigned char           next_state;
-        unsigned int            next_cpu;
-};
-
-/*
- * Special (free-form) trace entry:
- */
-struct special_entry {
-        struct trace_entry      ent;
-        unsigned long           arg1;
-        unsigned long           arg2;
-        unsigned long           arg3;
-};
-
-/*
- * Stack-trace entry:
- */
-
-#define FTRACE_STACK_ENTRIES    8
-
-struct stack_entry {
-        struct trace_entry      ent;
-        unsigned long           caller[FTRACE_STACK_ENTRIES];
-};
-
-struct userstack_entry {
-        struct trace_entry      ent;
-        unsigned long           caller[FTRACE_STACK_ENTRIES];
-};
-
-/*
- * trace_printk entry:
- */
-struct bprint_entry {
-        struct trace_entry      ent;
-        unsigned long           ip;
-        const char              *fmt;
-        u32                     buf[];
-};
-
-struct print_entry {
-        struct trace_entry      ent;
-        unsigned long           ip;
-        char                    buf[];
-};
-
-#define TRACE_OLD_SIZE          88
 
-struct trace_field_cont {
-        unsigned char           type;
-        /* Temporary till we get rid of this completely */
-        char                    buf[TRACE_OLD_SIZE - 1];
-};
+#undef __field
+#define __field(type, item)             type    item;
 
-struct trace_mmiotrace_rw {
-        struct trace_entry      ent;
-        struct mmiotrace_rw     rw;
-};
+#undef __field_struct
+#define __field_struct(type, item)      __field(type, item)
 
-struct trace_mmiotrace_map {
-        struct trace_entry      ent;
-        struct mmiotrace_map    map;
-};
+#undef __field_desc
+#define __field_desc(type, container, item)
 
-struct trace_boot_call {
-        struct trace_entry      ent;
-        struct boot_trace_call boot_call;
-};
+#undef __array
+#define __array(type, item, size)       type    item[size];
 
-struct trace_boot_ret {
-        struct trace_entry      ent;
-        struct boot_trace_ret boot_ret;
-};
+#undef __array_desc
+#define __array_desc(type, container, item, size)
 
-#define TRACE_FUNC_SIZE 30
-#define TRACE_FILE_SIZE 20
-struct trace_branch {
-        struct trace_entry      ent;
-        unsigned                line;
-        char                    func[TRACE_FUNC_SIZE+1];
-        char                    file[TRACE_FILE_SIZE+1];
-        char                    correct;
-};
+#undef __dynamic_array
+#define __dynamic_array(type, item)     type    item[];
 
-struct hw_branch_entry {
-        struct trace_entry      ent;
-        u64                     from;
-        u64                     to;
-};
+#undef F_STRUCT
+#define F_STRUCT(args...)               args
 
-struct trace_power {
-        struct trace_entry      ent;
-        struct power_trace      state_data;
-};
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)     \
+        struct struct_name {                                    \
+                struct trace_entry      ent;                    \
+                tstruct                                         \
+        }
 
-enum kmemtrace_type_id {
-        KMEMTRACE_TYPE_KMALLOC = 0,     /* kmalloc() or kfree(). */
-        KMEMTRACE_TYPE_CACHE,           /* kmem_cache_*(). */
-        KMEMTRACE_TYPE_PAGES,           /* __get_free_pages() and friends. */
-};
+#undef TP_ARGS
+#define TP_ARGS(args...)        args
 
-struct kmemtrace_alloc_entry {
-        struct trace_entry      ent;
-        enum kmemtrace_type_id type_id;
-        unsigned long call_site;
-        const void *ptr;
-        size_t bytes_req;
-        size_t bytes_alloc;
-        gfp_t gfp_flags;
-        int node;
-};
+#undef FTRACE_ENTRY_DUP
+#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk)
 
-struct kmemtrace_free_entry {
-        struct trace_entry      ent;
-        enum kmemtrace_type_id type_id;
-        unsigned long call_site;
-        const void *ptr;
-};
+#include "trace_entries.h"
 
+/*
+ * syscalls are special, and need special handling, this is why
+ * they are not included in trace_entries.h
+ */
 struct syscall_trace_enter {
         struct trace_entry      ent;
         int                     nr;
@@ -204,16 +83,26 @@ struct syscall_trace_enter {
 struct syscall_trace_exit {
         struct trace_entry      ent;
         int                     nr;
-        unsigned long           ret;
+        long                    ret;
 };
 
+struct kprobe_trace_entry_head {
+        struct trace_entry      ent;
+        unsigned long           ip;
+};
+
+struct kretprobe_trace_entry_head {
+        struct trace_entry      ent;
+        unsigned long           func;
+        unsigned long           ret_ip;
+};
 
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
  *  IRQS_OFF            - interrupts were disabled
  *  IRQS_NOSUPPORT      - arch does not support irqs_disabled_flags
- *  NEED_RESCED         - reschedule is requested
+ *  NEED_RESCHED        - reschedule is requested
  *  HARDIRQ             - inside an interrupt handler
  *  SOFTIRQ             - inside a softirq handler
  */
@@ -236,9 +125,6 @@ struct trace_array_cpu {
         atomic_t                disabled;
         void                    *buffer_page;   /* ring buffer spare */
 
-        /* these fields get copied into max-trace: */
-        unsigned long           trace_idx;
-        unsigned long           overrun;
         unsigned long           saved_latency;
         unsigned long           critical_start;
         unsigned long           critical_end;
@@ -246,6 +132,7 @@ struct trace_array_cpu {
         unsigned long           nice;
         unsigned long           policy;
         unsigned long           rt_priority;
+        unsigned long           skipped_entries;
         cycle_t                 preempt_timestamp;
         pid_t                   pid;
         uid_t                   uid;
@@ -301,28 +188,15 @@ extern void __ftrace_bad_type(void);
                 IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
                 IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);   \
                 IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT); \
-                IF_ASSIGN(var, ent, struct special_entry, 0);           \
                 IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,          \
                           TRACE_MMIO_RW);                               \
                 IF_ASSIGN(var, ent, struct trace_mmiotrace_map,         \
                           TRACE_MMIO_MAP);                              \
-                IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\
-                IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\
                 IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
                 IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry,      \
                           TRACE_GRAPH_ENT);             \
                 IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,      \
                           TRACE_GRAPH_RET);             \
-                IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
-                IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \
-                IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry,       \
-                          TRACE_KMEM_ALLOC);    \
-                IF_ASSIGN(var, ent, struct kmemtrace_free_entry,        \
-                          TRACE_KMEM_FREE);     \
-                IF_ASSIGN(var, ent, struct syscall_trace_enter,         \
-                          TRACE_SYSCALL_ENTER);                         \
-                IF_ASSIGN(var, ent, struct syscall_trace_exit,          \
-                          TRACE_SYSCALL_EXIT);                          \
                 __ftrace_bad_type();                                    \
         } while (0)
 
@@ -360,6 +234,7 @@ struct tracer_flags {
  * @pipe_open: called when the trace_pipe file is opened
  * @wait_pipe: override how the user waits for traces on trace_pipe
  * @close: called when the trace file is released
+ * @pipe_close: called when the trace_pipe file is released
  * @read: override the default read callback on trace_pipe
  * @splice_read: override the default splice_read callback on trace_pipe
  * @selftest: selftest to run on boot (see trace_selftest.c)
@@ -378,6 +253,7 @@ struct tracer {
         void                    (*pipe_open)(struct trace_iterator *iter);
         void                    (*wait_pipe)(struct trace_iterator *iter);
         void                    (*close)(struct trace_iterator *iter);
+        void                    (*pipe_close)(struct trace_iterator *iter);
         ssize_t                 (*read)(struct trace_iterator *iter,
                                         struct file *filp, char __user *ubuf,
                                         size_t cnt, loff_t *ppos);
@@ -398,7 +274,7 @@ struct tracer {
         struct tracer           *next;
         int                     print_max;
         struct tracer_flags     *flags;
-        struct tracer_stat      *stats;
+        int                     use_max_tr;
 };
 
 
@@ -419,16 +295,16 @@ struct dentry *trace_create_file(const char *name,
                                  const struct file_operations *fops);
 
 struct dentry *tracing_init_dentry(void);
-void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
 
 struct ring_buffer_event;
 
-struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-                                                    int type,
-                                                    unsigned long len,
-                                                    unsigned long flags,
-                                                    int pc);
-void trace_buffer_unlock_commit(struct trace_array *tr,
+struct ring_buffer_event *
+trace_buffer_lock_reserve(struct ring_buffer *buffer,
+                          int type,
+                          unsigned long len,
+                          unsigned long flags,
+                          int pc);
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
                                 struct ring_buffer_event *event,
                                 unsigned long flags, int pc);
 
@@ -438,9 +314,13 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
                                           int *ent_cpu, u64 *ent_ts);
 
-void tracing_generic_entry_update(struct trace_entry *entry,
-                                  unsigned long flags,
-                                  int pc);
+int trace_empty(struct trace_iterator *iter);
+
+void *trace_find_next_entry_inc(struct trace_iterator *iter);
+
+void trace_init_global_iter(struct trace_iterator *iter);
+
+void tracing_iter_reset(struct trace_iterator *iter, int cpu);
 
 void default_wait_pipe(struct trace_iterator *iter);
 void poll_wait_pipe(struct trace_iterator *iter);
@@ -459,18 +339,21 @@ void tracing_sched_wakeup_trace(struct trace_array *tr,
                                 struct task_struct *wakee,
                                 struct task_struct *cur,
                                 unsigned long flags, int pc);
-void trace_special(struct trace_array *tr,
-                   struct trace_array_cpu *data,
-                   unsigned long arg1,
-                   unsigned long arg2,
-                   unsigned long arg3, int pc);
 void trace_function(struct trace_array *tr,
                     unsigned long ip,
                     unsigned long parent_ip,
                     unsigned long flags, int pc);
+void trace_graph_function(struct trace_array *tr,
+                    unsigned long ip,
+                    unsigned long parent_ip,
+                    unsigned long flags, int pc);
+void trace_default_header(struct seq_file *m);
+void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
+int trace_empty(struct trace_iterator *iter);
 
 void trace_graph_return(struct ftrace_graph_ret *trace);
 int trace_graph_entry(struct ftrace_graph_ent *trace);
+void set_graph_array(struct trace_array *tr);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
@@ -479,35 +362,56 @@ void tracing_stop_sched_switch_record(void);
 void tracing_start_sched_switch_record(void);
 int register_tracer(struct tracer *type);
 void unregister_tracer(struct tracer *type);
+int is_tracing_stopped(void);
+enum trace_file_type {
+        TRACE_FILE_LAT_FMT      = 1,
+        TRACE_FILE_ANNOTATE     = 2,
+};
+
+extern cpumask_var_t __read_mostly tracing_buffer_mask;
+
+#define for_each_tracing_cpu(cpu)       \
+        for_each_cpu(cpu, tracing_buffer_mask)
 
 extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
-extern unsigned long tracing_max_latency;
 extern unsigned long tracing_thresh;
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+extern unsigned long tracing_max_latency;
+
 void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
                           struct task_struct *tsk, int cpu);
+#endif /* CONFIG_TRACER_MAX_TRACE */
 
-void __trace_stack(struct trace_array *tr,
-                   unsigned long flags,
-                   int skip, int pc);
+#ifdef CONFIG_STACKTRACE
+void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
+                        int skip, int pc);
 
-extern cycle_t ftrace_now(int cpu);
+void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
+                            int pc);
 
-#ifdef CONFIG_CONTEXT_SWITCH_TRACER
-typedef void
-(*tracer_switch_func_t)(void *private,
-                        void *__rq,
-                        struct task_struct *prev,
-                        struct task_struct *next);
-
-struct tracer_switch_ops {
-        tracer_switch_func_t            func;
-        void                            *private;
-        struct tracer_switch_ops        *next;
-};
-#endif /* CONFIG_CONTEXT_SWITCH_TRACER */
+void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
+                   int pc);
+#else
+static inline void ftrace_trace_stack(struct ring_buffer *buffer,
+                                      unsigned long flags, int skip, int pc)
+{
+}
+
+static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
+                                          unsigned long flags, int pc)
+{
+}
+
+static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
+                                 int skip, int pc)
+{
+}
+#endif /* CONFIG_STACKTRACE */
+
+extern cycle_t ftrace_now(int cpu);
 
 extern void trace_find_cmdline(int pid, char comm[]);
 
@@ -517,6 +421,10 @@ extern unsigned long ftrace_update_tot_cnt;
 extern int DYN_FTRACE_TEST_NAME(void);
 #endif
 
+extern int ring_buffer_expanded;
+extern bool tracing_selftest_disabled;
+DECLARE_PER_CPU(int, ftrace_cpu_disabled);
+
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 extern int trace_selftest_startup_function(struct tracer *trace,
                                            struct trace_array *tr);
@@ -534,12 +442,8 @@ extern int trace_selftest_startup_nop(struct tracer *trace,
                                          struct trace_array *tr);
 extern int trace_selftest_startup_sched_switch(struct tracer *trace,
                                                struct trace_array *tr);
-extern int trace_selftest_startup_sysprof(struct tracer *trace,
-                                               struct trace_array *tr);
 extern int trace_selftest_startup_branch(struct tracer *trace,
                                          struct trace_array *tr);
-extern int trace_selftest_startup_hw_branches(struct tracer *trace,
-                                              struct trace_array *tr);
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
@@ -548,18 +452,48 @@ extern int
 trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
 extern int
 trace_vprintk(unsigned long ip, const char *fmt, va_list args);
+extern int
+trace_array_vprintk(struct trace_array *tr,
+                    unsigned long ip, const char *fmt, va_list args);
+int trace_array_printk(struct trace_array *tr,
+                       unsigned long ip, const char *fmt, ...);
+void trace_printk_seq(struct trace_seq *s);
+enum print_line_t print_trace_line(struct trace_iterator *iter);
 
 extern unsigned long trace_flags;
 
+extern int trace_clock_id;
+
 /* Standard output formatting function used for function return traces */
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-extern enum print_line_t print_graph_function(struct trace_iterator *iter);
+
+/* Flag options */
+#define TRACE_GRAPH_PRINT_OVERRUN       0x1
+#define TRACE_GRAPH_PRINT_CPU           0x2
+#define TRACE_GRAPH_PRINT_OVERHEAD      0x4
+#define TRACE_GRAPH_PRINT_PROC          0x8
+#define TRACE_GRAPH_PRINT_DURATION      0x10
+#define TRACE_GRAPH_PRINT_ABS_TIME      0x20
+
+extern enum print_line_t
+print_graph_function_flags(struct trace_iterator *iter, u32 flags);
+extern void print_graph_headers_flags(struct seq_file *s, u32 flags);
 extern enum print_line_t
 trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
+extern void graph_trace_open(struct trace_iterator *iter);
+extern void graph_trace_close(struct trace_iterator *iter);
+extern int __trace_graph_entry(struct trace_array *tr,
+                               struct ftrace_graph_ent *trace,
+                               unsigned long flags, int pc);
+extern void __trace_graph_return(struct trace_array *tr,
+                                 struct ftrace_graph_ret *trace,
+                                 unsigned long flags, int pc);
+
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 /* TODO: make this variable */
 #define FTRACE_GRAPH_MAX_FUNCS          32
+extern int ftrace_graph_filter_enabled;
 extern int ftrace_graph_count;
 extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
 
@@ -567,7 +501,7 @@ static inline int ftrace_graph_addr(unsigned long addr)
 {
         int i;
 
-        if (!ftrace_graph_count || test_tsk_trace_graph(current))
+        if (!ftrace_graph_filter_enabled)
                 return 1;
 
         for (i = 0; i < ftrace_graph_count; i++) {
@@ -578,10 +512,6 @@ static inline int ftrace_graph_addr(unsigned long addr)
         return 0;
 }
 #else
-static inline int ftrace_trace_addr(unsigned long addr)
-{
-        return 1;
-}
 static inline int ftrace_graph_addr(unsigned long addr)
 {
         return 1;
@@ -589,21 +519,63 @@ static inline int ftrace_graph_addr(unsigned long addr)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #else /* CONFIG_FUNCTION_GRAPH_TRACER */
 static inline enum print_line_t
-print_graph_function(struct trace_iterator *iter)
+print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 {
         return TRACE_TYPE_UNHANDLED;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-extern struct pid *ftrace_pid_trace;
+extern struct list_head ftrace_pids;
 
+#ifdef CONFIG_FUNCTION_TRACER
 static inline int ftrace_trace_task(struct task_struct *task)
 {
-        if (!ftrace_pid_trace)
+        if (list_empty(&ftrace_pids))
                 return 1;
 
         return test_tsk_trace_trace(task);
 }
+#else
+static inline int ftrace_trace_task(struct task_struct *task)
+{
+        return 1;
+}
+#endif
+
+/*
+ * struct trace_parser - servers for reading the user input separated by spaces
+ * @cont: set if the input is not complete - no final space char was found
+ * @buffer: holds the parsed user input
+ * @idx: user input length
+ * @size: buffer size
+ */
+struct trace_parser {
+        bool            cont;
+        char            *buffer;
+        unsigned        idx;
+        unsigned        size;
+};
+
+static inline bool trace_parser_loaded(struct trace_parser *parser)
+{
+        return (parser->idx != 0);
+}
+
+static inline bool trace_parser_cont(struct trace_parser *parser)
+{
+        return parser->cont;
+}
+
+static inline void trace_parser_clear(struct trace_parser *parser)
+{
+        parser->cont = false;
+        parser->idx = 0;
+}
+
+extern int trace_parser_get_init(struct trace_parser *parser, int size);
+extern void trace_parser_put(struct trace_parser *parser);
+extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
+        size_t cnt, loff_t *ppos);
 
 /*
  * trace_iterator_flags is an enumeration that defines bit
@@ -622,19 +594,18 @@ enum trace_iterator_flags {
         TRACE_ITER_BIN                  = 0x40,
         TRACE_ITER_BLOCK                = 0x80,
         TRACE_ITER_STACKTRACE           = 0x100,
-        TRACE_ITER_SCHED_TREE           = 0x200,
-        TRACE_ITER_PRINTK               = 0x400,
-        TRACE_ITER_PREEMPTONLY          = 0x800,
-        TRACE_ITER_BRANCH               = 0x1000,
-        TRACE_ITER_ANNOTATE             = 0x2000,
-        TRACE_ITER_USERSTACKTRACE       = 0x4000,
-        TRACE_ITER_SYM_USEROBJ          = 0x8000,
-        TRACE_ITER_PRINTK_MSGONLY       = 0x10000,
-        TRACE_ITER_CONTEXT_INFO         = 0x20000, /* Print pid/cpu/time */
-        TRACE_ITER_LATENCY_FMT          = 0x40000,
-        TRACE_ITER_GLOBAL_CLK           = 0x80000,
-        TRACE_ITER_SLEEP_TIME           = 0x100000,
-        TRACE_ITER_GRAPH_TIME           = 0x200000,
+        TRACE_ITER_PRINTK               = 0x200,
+        TRACE_ITER_PREEMPTONLY          = 0x400,
+        TRACE_ITER_BRANCH               = 0x800,
+        TRACE_ITER_ANNOTATE             = 0x1000,
+        TRACE_ITER_USERSTACKTRACE       = 0x2000,
+        TRACE_ITER_SYM_USEROBJ          = 0x4000,
+        TRACE_ITER_PRINTK_MSGONLY       = 0x8000,
+        TRACE_ITER_CONTEXT_INFO         = 0x10000, /* Print pid/cpu/time */
+        TRACE_ITER_LATENCY_FMT          = 0x20000,
+        TRACE_ITER_SLEEP_TIME           = 0x40000,
+        TRACE_ITER_GRAPH_TIME           = 0x80000,
+        TRACE_ITER_RECORD_CMD           = 0x100000,
 };
 
 /*
@@ -646,54 +617,6 @@ enum trace_iterator_flags {
 
 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_resched 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 are 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();
-}
-
 #ifdef CONFIG_BRANCH_TRACER
 extern int enable_branch_tracing(struct trace_array *tr);
 extern void disable_branch_tracing(void);
@@ -731,6 +654,7 @@ struct ftrace_event_field {
         struct list_head        link;
         char                    *name;
         char                    *type;
+        int                     filter_type;
         int                     offset;
         int                     size;
         int                     is_signed;
@@ -746,26 +670,47 @@ struct event_subsystem {
         struct list_head        list;
         const char              *name;
         struct dentry           *entry;
-        void                    *filter;
+        struct event_filter     *filter;
+        int                     nr_events;
 };
 
 struct filter_pred;
+struct regex;
 
 typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
                                  int val1, int val2);
 
+typedef int (*regex_match_func)(char *str, struct regex *r, int len);
+
+enum regex_type {
+        MATCH_FULL = 0,
+        MATCH_FRONT_ONLY,
+        MATCH_MIDDLE_ONLY,
+        MATCH_END_ONLY,
+};
+
+struct regex {
+        char                    pattern[MAX_FILTER_STR_VAL];
+        int                     len;
+        int                     field_len;
+        regex_match_func        match;
+};
+
 struct filter_pred {
-        filter_pred_fn_t fn;
-        u64 val;
-        char str_val[MAX_FILTER_STR_VAL];
-        int str_len;
-        char *field_name;
-        int offset;
-        int not;
-        int op;
-        int pop_n;
+        filter_pred_fn_t        fn;
+        u64                     val;
+        struct regex            regex;
+        char                    *field_name;
+        int                     offset;
+        int                     not;
+        int                     op;
+        int                     pop_n;
 };
 
+extern struct list_head ftrace_common_fields;
+
+extern enum regex_type
+filter_parse_regex(char *buff, int len, char **search, int *not);
 extern void print_event_filter(struct ftrace_event_call *call,
                                struct trace_seq *s);
 extern int apply_event_filter(struct ftrace_event_call *call,
@@ -774,13 +719,18 @@ extern int apply_subsystem_event_filter(struct event_subsystem *system,
                                         char *filter_string);
 extern void print_subsystem_event_filter(struct event_subsystem *system,
                                          struct trace_seq *s);
+extern int filter_assign_type(const char *type);
+
+struct list_head *
+trace_get_fields(struct ftrace_event_call *event_call);
 
 static inline int
 filter_check_discard(struct ftrace_event_call *call, void *rec,
                      struct ring_buffer *buffer,
                      struct ring_buffer_event *event)
 {
-        if (unlikely(call->filter_active) && !filter_match_preds(call, rec)) {
+        if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
+            !filter_match_preds(call->filter, rec)) {
                 ring_buffer_discard_commit(buffer, event);
                 return 1;
         }
@@ -788,46 +738,7 @@ filter_check_discard(struct ftrace_event_call *call, void *rec,
         return 0;
 }
 
-#define DEFINE_COMPARISON_PRED(type)                                    \
-static int filter_pred_##type(struct filter_pred *pred, void *event,    \
-                              int val1, int val2)                       \
-{                                                                       \
-        type *addr = (type *)(event + pred->offset);                    \
-        type val = (type)pred->val;                                     \
-        int match = 0;                                                  \
-                                                                        \
-        switch (pred->op) {                                             \
-        case OP_LT:                                                     \
-                match = (*addr < val);                                  \
-                break;                                                  \
-        case OP_LE:                                                     \
-                match = (*addr <= val);                                 \
-                break;                                                  \
-        case OP_GT:                                                     \
-                match = (*addr > val);                                  \
-                break;                                                  \
-        case OP_GE:                                                     \
-                match = (*addr >= val);                                 \
-                break;                                                  \
-        default:                                                        \
-                break;                                                  \
-        }                                                               \
-                                                                        \
-        return match;                                                   \
-}
-
-#define DEFINE_EQUALITY_PRED(size)                                      \
-static int filter_pred_##size(struct filter_pred *pred, void *event,    \
-                              int val1, int val2)                       \
-{                                                                       \
-        u##size *addr = (u##size *)(event + pred->offset);              \
-        u##size val = (u##size)pred->val;                               \
-        int match;                                                      \
-                                                                        \
-        match = (val == *addr) ^ pred->not;                             \
-                                                                        \
-        return match;                                                   \
-}
+extern void trace_event_enable_cmd_record(bool enable);
 
 extern struct mutex event_mutex;
 extern struct list_head ftrace_events;
@@ -835,11 +746,13 @@ extern struct list_head ftrace_events;
 extern const char *__start___trace_bprintk_fmt[];
 extern const char *__stop___trace_bprintk_fmt[];
 
-#undef TRACE_EVENT_FORMAT
-#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)      \
-        extern struct ftrace_event_call event_##call;
-#undef TRACE_EVENT_FORMAT_NOFILTER
-#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, tpfmt)
-#include "trace_event_types.h"
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(call, struct_name, id, tstruct, print)             \
+        extern struct ftrace_event_call                                 \
+        __attribute__((__aligned__(4))) event_##call;
+#undef FTRACE_ENTRY_DUP
+#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print)         \
+        FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#include "trace_entries.h"
 
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
deleted file mode 100644
index a29ef23ffb47..000000000000
--- a/kernel/trace/trace_boot.c
+++ /dev/null
@@ -1,179 +0,0 @@
-/*
- * ring buffer based initcalls tracer
- *
- * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
- *
- */
-
-#include <linux/init.h>
-#include <linux/debugfs.h>
-#include <linux/ftrace.h>
-#include <linux/kallsyms.h>
-#include <linux/time.h>
-
-#include "trace.h"
-#include "trace_output.h"
-
-static struct trace_array *boot_trace;
-static bool pre_initcalls_finished;
-
-/* Tells the boot tracer that the pre_smp_initcalls are finished.
- * So we are ready .
- * It doesn't enable sched events tracing however.
- * You have to call enable_boot_trace to do so.
- */
-void start_boot_trace(void)
-{
-        pre_initcalls_finished = true;
-}
-
-void enable_boot_trace(void)
-{
-        if (boot_trace && pre_initcalls_finished)
-                tracing_start_sched_switch_record();
-}
-
-void disable_boot_trace(void)
-{
-        if (boot_trace && pre_initcalls_finished)
-                tracing_stop_sched_switch_record();
-}
-
-static int boot_trace_init(struct trace_array *tr)
-{
-        int cpu;
-        boot_trace = tr;
-
-        if (!tr)
-                return 0;
-
-        for_each_cpu(cpu, cpu_possible_mask)
-                tracing_reset(tr, cpu);
-
-        tracing_sched_switch_assign_trace(tr);
-        return 0;
-}
-
-static enum print_line_t
-initcall_call_print_line(struct trace_iterator *iter)
-{
-        struct trace_entry *entry = iter->ent;
-        struct trace_seq *s = &iter->seq;
-        struct trace_boot_call *field;
-        struct boot_trace_call *call;
-        u64 ts;
-        unsigned long nsec_rem;
-        int ret;
-
-        trace_assign_type(field, entry);
-        call = &field->boot_call;
-        ts = iter->ts;
-        nsec_rem = do_div(ts, NSEC_PER_SEC);
-
-        ret = trace_seq_printf(s, "[%5ld.%09ld] calling  %s @ %i\n",
-                        (unsigned long)ts, nsec_rem, call->func, call->caller);
-
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-        else
-                return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t
-initcall_ret_print_line(struct trace_iterator *iter)
-{
-        struct trace_entry *entry = iter->ent;
-        struct trace_seq *s = &iter->seq;
-        struct trace_boot_ret *field;
-        struct boot_trace_ret *init_ret;
-        u64 ts;
-        unsigned long nsec_rem;
-        int ret;
-
-        trace_assign_type(field, entry);
-        init_ret = &field->boot_ret;
-        ts = iter->ts;
-        nsec_rem = do_div(ts, NSEC_PER_SEC);
-
-        ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
-                        "returned %d after %llu msecs\n",
-                        (unsigned long) ts,
-                        nsec_rem,
-                        init_ret->func, init_ret->result, init_ret->duration);
-
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-        else
-                return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t initcall_print_line(struct trace_iterator *iter)
-{
-        struct trace_entry *entry = iter->ent;
-
-        switch (entry->type) {
-        case TRACE_BOOT_CALL:
-                return initcall_call_print_line(iter);
-        case TRACE_BOOT_RET:
-                return initcall_ret_print_line(iter);
-        default:
-                return TRACE_TYPE_UNHANDLED;
-        }
-}
-
-struct tracer boot_tracer __read_mostly =
-{
-        .name           = "initcall",
-        .init           = boot_trace_init,
-        .reset          = tracing_reset_online_cpus,
-        .print_line     = initcall_print_line,
-};
-
-void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
-{
-        struct ring_buffer_event *event;
-        struct trace_boot_call *entry;
-        struct trace_array *tr = boot_trace;
-
-        if (!tr || !pre_initcalls_finished)
-                return;
-
-        /* Get its name now since this function could
-         * disappear because it is in the .init section.
-         */
-        sprint_symbol(bt->func, (unsigned long)fn);
-        preempt_disable();
-
-        event = trace_buffer_lock_reserve(tr, TRACE_BOOT_CALL,
-                                          sizeof(*entry), 0, 0);
-        if (!event)
-                goto out;
-        entry   = ring_buffer_event_data(event);
-        entry->boot_call = *bt;
-        trace_buffer_unlock_commit(tr, event, 0, 0);
- out:
-        preempt_enable();
-}
-
-void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
-{
-        struct ring_buffer_event *event;
-        struct trace_boot_ret *entry;
-        struct trace_array *tr = boot_trace;
-
-        if (!tr || !pre_initcalls_finished)
-                return;
-
-        sprint_symbol(bt->func, (unsigned long)fn);
-        preempt_disable();
-
-        event = trace_buffer_lock_reserve(tr, TRACE_BOOT_RET,
-                                          sizeof(*entry), 0, 0);
-        if (!event)
-                goto out;
-        entry   = ring_buffer_event_data(event);
-        entry->boot_ret = *bt;
-        trace_buffer_unlock_commit(tr, event, 0, 0);
- out:
-        preempt_enable();
-}
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 7a7a9fd249a9..8d3538b4ea5f 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -34,6 +34,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
         struct trace_array *tr = branch_tracer;
         struct ring_buffer_event *event;
         struct trace_branch *entry;
+        struct ring_buffer *buffer;
         unsigned long flags;
         int cpu, pc;
         const char *p;
@@ -54,7 +55,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
                 goto out;
 
         pc = preempt_count();
-        event = trace_buffer_lock_reserve(tr, TRACE_BRANCH,
+        buffer = tr->buffer;
+        event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH,
                                           sizeof(*entry), flags, pc);
         if (!event)
                 goto out;
@@ -74,8 +76,8 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
         entry->line = f->line;
         entry->correct = val == expect;
 
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                ring_buffer_unlock_commit(tr->buffer, event);
+        if (!filter_check_discard(call, entry, buffer, event))
+                ring_buffer_unlock_commit(buffer, event);
 
  out:
         atomic_dec(&tr->data[cpu]->disabled);
@@ -141,7 +143,7 @@ static void branch_trace_reset(struct trace_array *tr)
 }
 
 static enum print_line_t trace_branch_print(struct trace_iterator *iter,
-                                            int flags)
+                                            int flags, struct trace_event *event)
 {
         struct trace_branch *field;
 
@@ -165,9 +167,13 @@ static void branch_print_header(struct seq_file *s)
                 "    |\n");
 }
 
+static struct trace_event_functions trace_branch_funcs = {
+        .trace          = trace_branch_print,
+};
+
 static struct trace_event trace_branch_event = {
         .type           = TRACE_BRANCH,
-        .trace          = trace_branch_print,
+        .funcs          = &trace_branch_funcs,
 };
 
 static struct tracer branch_trace __read_mostly =
@@ -305,8 +311,23 @@ static int annotated_branch_stat_cmp(void *p1, void *p2)
                 return -1;
         if (percent_a > percent_b)
                 return 1;
-        else
-                return 0;
+
+        if (a->incorrect < b->incorrect)
+                return -1;
+        if (a->incorrect > b->incorrect)
+                return 1;
+
+        /*
+         * Since the above shows worse (incorrect) cases
+         * first, we continue that by showing best (correct)
+         * cases last.
+         */
+        if (a->correct > b->correct)
+                return -1;
+        if (a->correct < b->correct)
+                return 1;
+
+        return 0;
 }
 
 static struct tracer_stat annotated_branch_stats = {
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index b588fd81f7f9..685a67d55db0 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -13,6 +13,7 @@
  * Tracer plugins will chose a default from these clocks.
  */
 #include <linux/spinlock.h>
+#include <linux/irqflags.h>
 #include <linux/hardirq.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
@@ -20,6 +21,8 @@
 #include <linux/ktime.h>
 #include <linux/trace_clock.h>
 
+#include "trace.h"
+
 /*
  * trace_clock_local(): the simplest and least coherent tracing clock.
  *
@@ -28,7 +31,6 @@
  */
 u64 notrace trace_clock_local(void)
 {
-        unsigned long flags;
         u64 clock;
 
         /*
@@ -36,9 +38,9 @@ u64 notrace trace_clock_local(void)
          * lockless clock. It is not guaranteed to be coherent across
          * CPUs, nor across CPU idle events.
          */
-        raw_local_irq_save(flags);
+        preempt_disable_notrace();
         clock = sched_clock();
-        raw_local_irq_restore(flags);
+        preempt_enable_notrace();
 
         return clock;
 }
@@ -53,7 +55,7 @@ u64 notrace trace_clock_local(void)
  */
 u64 notrace trace_clock(void)
 {
-        return cpu_clock(raw_smp_processor_id());
+        return local_clock();
 }
 
 
@@ -66,10 +68,14 @@ u64 notrace trace_clock(void)
  * Used by plugins that need globally coherent timestamps.
  */
 
-static u64 prev_trace_clock_time;
-
-static raw_spinlock_t trace_clock_lock ____cacheline_aligned_in_smp =
-        (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+/* keep prev_time and lock in the same cacheline. */
+static struct {
+        u64 prev_time;
+        arch_spinlock_t lock;
+} trace_clock_struct ____cacheline_aligned_in_smp =
+        {
+                .lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED,
+        };
 
 u64 notrace trace_clock_global(void)
 {
@@ -77,7 +83,7 @@ u64 notrace trace_clock_global(void)
         int this_cpu;
         u64 now;
 
-        raw_local_irq_save(flags);
+        local_irq_save(flags);
 
         this_cpu = raw_smp_processor_id();
         now = cpu_clock(this_cpu);
@@ -88,22 +94,22 @@ u64 notrace trace_clock_global(void)
         if (unlikely(in_nmi()))
                 goto out;
 
-        __raw_spin_lock(&trace_clock_lock);
+        arch_spin_lock(&trace_clock_struct.lock);
 
         /*
          * TODO: if this happens often then maybe we should reset
-         * my_scd->clock to prev_trace_clock_time+1, to make sure
+         * my_scd->clock to prev_time+1, to make sure
          * we start ticking with the local clock from now on?
          */
-        if ((s64)(now - prev_trace_clock_time) < 0)
-                now = prev_trace_clock_time + 1;
+        if ((s64)(now - trace_clock_struct.prev_time) < 0)
+                now = trace_clock_struct.prev_time + 1;
 
-        prev_trace_clock_time = now;
+        trace_clock_struct.prev_time = now;
 
-        __raw_spin_unlock(&trace_clock_lock);
+        arch_spin_unlock(&trace_clock_struct.lock);
 
  out:
-        raw_local_irq_restore(flags);
+        local_irq_restore(flags);
 
         return now;
 }
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
new file mode 100644
index 000000000000..e3dfecaf13e6
--- /dev/null
+++ b/kernel/trace/trace_entries.h
@@ -0,0 +1,276 @@
+/*
+ * This file defines the trace event structures that go into the ring
+ * buffer directly. They are created via macros so that changes for them
+ * appear in the format file. Using macros will automate this process.
+ *
+ * The macro used to create a ftrace data structure is:
+ *
+ * FTRACE_ENTRY( name, struct_name, id, structure, print )
+ *
+ * @name: the name used the event name, as well as the name of
+ *   the directory that holds the format file.
+ *
+ * @struct_name: the name of the structure that is created.
+ *
+ * @id: The event identifier that is used to detect what event
+ *    this is from the ring buffer.
+ *
+ * @structure: the structure layout
+ *
+ *  - __field(  type,   item    )
+ *        This is equivalent to declaring
+ *              type    item;
+ *        in the structure.
+ *  - __array(  type,   item,   size    )
+ *        This is equivalent to declaring
+ *              type    item[size];
+ *        in the structure.
+ *
+ *   * for structures within structures, the format of the internal
+ *      structure is layed out. This allows the internal structure
+ *      to be deciphered for the format file. Although these macros
+ *      may become out of sync with the internal structure, they
+ *      will create a compile error if it happens. Since the
+ *      internel structures are just tracing helpers, this is not
+ *      an issue.
+ *
+ *      When an internal structure is used, it should use:
+ *
+ *      __field_struct( type,   item    )
+ *
+ *      instead of __field. This will prevent it from being shown in
+ *      the output file. The fields in the structure should use.
+ *
+ *      __field_desc(   type,   container,      item            )
+ *      __array_desc(   type,   container,      item,   len     )
+ *
+ *      type, item and len are the same as __field and __array, but
+ *      container is added. This is the name of the item in
+ *      __field_struct that this is describing.
+ *
+ *
+ * @print: the print format shown to users in the format file.
+ */
+
+/*
+ * Function trace entry - function address and parent function addres:
+ */
+FTRACE_ENTRY(function, ftrace_entry,
+
+        TRACE_FN,
+
+        F_STRUCT(
+                __field(        unsigned long,  ip              )
+                __field(        unsigned long,  parent_ip       )
+        ),
+
+        F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip)
+);
+
+/* Function call entry */
+FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
+
+        TRACE_GRAPH_ENT,
+
+        F_STRUCT(
+                __field_struct( struct ftrace_graph_ent,        graph_ent       )
+                __field_desc(   unsigned long,  graph_ent,      func            )
+                __field_desc(   int,            graph_ent,      depth           )
+        ),
+
+        F_printk("--> %lx (%d)", __entry->func, __entry->depth)
+);
+
+/* Function return entry */
+FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
+
+        TRACE_GRAPH_RET,
+
+        F_STRUCT(
+                __field_struct( struct ftrace_graph_ret,        ret     )
+                __field_desc(   unsigned long,  ret,            func    )
+                __field_desc(   unsigned long long, ret,        calltime)
+                __field_desc(   unsigned long long, ret,        rettime )
+                __field_desc(   unsigned long,  ret,            overrun )
+                __field_desc(   int,            ret,            depth   )
+        ),
+
+        F_printk("<-- %lx (%d) (start: %llx  end: %llx) over: %d",
+                 __entry->func, __entry->depth,
+                 __entry->calltime, __entry->rettime,
+                 __entry->depth)
+);
+
+/*
+ * Context switch trace entry - which task (and prio) we switched from/to:
+ *
+ * This is used for both wakeup and context switches. We only want
+ * to create one structure, but we need two outputs for it.
+ */
+#define FTRACE_CTX_FIELDS                                       \
+        __field(        unsigned int,   prev_pid        )       \
+        __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        )
+
+FTRACE_ENTRY(context_switch, ctx_switch_entry,
+
+        TRACE_CTX,
+
+        F_STRUCT(
+                FTRACE_CTX_FIELDS
+        ),
+
+        F_printk("%u:%u:%u  ==> %u:%u:%u [%03u]",
+                 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
+                 __entry->next_pid, __entry->next_prio, __entry->next_state,
+                 __entry->next_cpu
+                )
+);
+
+/*
+ * FTRACE_ENTRY_DUP only creates the format file, it will not
+ *  create another structure.
+ */
+FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
+
+        TRACE_WAKE,
+
+        F_STRUCT(
+                FTRACE_CTX_FIELDS
+        ),
+
+        F_printk("%u:%u:%u  ==+ %u:%u:%u [%03u]",
+                 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
+                 __entry->next_pid, __entry->next_prio, __entry->next_state,
+                 __entry->next_cpu
+                )
+);
+
+/*
+ * Stack-trace entry:
+ */
+
+#define FTRACE_STACK_ENTRIES    8
+
+FTRACE_ENTRY(kernel_stack, stack_entry,
+
+        TRACE_STACK,
+
+        F_STRUCT(
+                __array(        unsigned long,  caller, FTRACE_STACK_ENTRIES    )
+        ),
+
+        F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
+                 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
+                 __entry->caller[0], __entry->caller[1], __entry->caller[2],
+                 __entry->caller[3], __entry->caller[4], __entry->caller[5],
+                 __entry->caller[6], __entry->caller[7])
+);
+
+FTRACE_ENTRY(user_stack, userstack_entry,
+
+        TRACE_USER_STACK,
+
+        F_STRUCT(
+                __field(        unsigned int,   tgid    )
+                __array(        unsigned long,  caller, FTRACE_STACK_ENTRIES    )
+        ),
+
+        F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
+                 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
+                 __entry->caller[0], __entry->caller[1], __entry->caller[2],
+                 __entry->caller[3], __entry->caller[4], __entry->caller[5],
+                 __entry->caller[6], __entry->caller[7])
+);
+
+/*
+ * trace_printk entry:
+ */
+FTRACE_ENTRY(bprint, bprint_entry,
+
+        TRACE_BPRINT,
+
+        F_STRUCT(
+                __field(        unsigned long,  ip      )
+                __field(        const char *,   fmt     )
+                __dynamic_array(        u32,    buf     )
+        ),
+
+        F_printk("%08lx fmt:%p",
+                 __entry->ip, __entry->fmt)
+);
+
+FTRACE_ENTRY(print, print_entry,
+
+        TRACE_PRINT,
+
+        F_STRUCT(
+                __field(        unsigned long,  ip      )
+                __dynamic_array(        char,   buf     )
+        ),
+
+        F_printk("%08lx %s",
+                 __entry->ip, __entry->buf)
+);
+
+FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
+
+        TRACE_MMIO_RW,
+
+        F_STRUCT(
+                __field_struct( struct mmiotrace_rw,    rw      )
+                __field_desc(   resource_size_t, rw,    phys    )
+                __field_desc(   unsigned long,  rw,     value   )
+                __field_desc(   unsigned long,  rw,     pc      )
+                __field_desc(   int,            rw,     map_id  )
+                __field_desc(   unsigned char,  rw,     opcode  )
+                __field_desc(   unsigned char,  rw,     width   )
+        ),
+
+        F_printk("%lx %lx %lx %d %x %x",
+                 (unsigned long)__entry->phys, __entry->value, __entry->pc,
+                 __entry->map_id, __entry->opcode, __entry->width)
+);
+
+FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
+
+        TRACE_MMIO_MAP,
+
+        F_STRUCT(
+                __field_struct( struct mmiotrace_map,   map     )
+                __field_desc(   resource_size_t, map,   phys    )
+                __field_desc(   unsigned long,  map,    virt    )
+                __field_desc(   unsigned long,  map,    len     )
+                __field_desc(   int,            map,    map_id  )
+                __field_desc(   unsigned char,  map,    opcode  )
+        ),
+
+        F_printk("%lx %lx %lx %d %x",
+                 (unsigned long)__entry->phys, __entry->virt, __entry->len,
+                 __entry->map_id, __entry->opcode)
+);
+
+
+#define TRACE_FUNC_SIZE 30
+#define TRACE_FILE_SIZE 20
+
+FTRACE_ENTRY(branch, trace_branch,
+
+        TRACE_BRANCH,
+
+        F_STRUCT(
+                __field(        unsigned int,   line                            )
+                __array(        char,           func,   TRACE_FUNC_SIZE+1       )
+                __array(        char,           file,   TRACE_FILE_SIZE+1       )
+                __field(        char,           correct                         )
+        ),
+
+        F_printk("%u:%s:%s (%u)",
+                 __entry->line,
+                 __entry->func, __entry->file, __entry->correct)
+);
+
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
new file mode 100644
index 000000000000..19a359d5e6d5
--- /dev/null
+++ b/kernel/trace/trace_event_perf.c
@@ -0,0 +1,216 @@
+/*
+ * trace event based perf event profiling/tracing
+ *
+ * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kprobes.h>
+#include "trace.h"
+
+static char __percpu *perf_trace_buf[PERF_NR_CONTEXTS];
+
+/*
+ * Force it to be aligned to unsigned long to avoid misaligned accesses
+ * suprises
+ */
+typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
+        perf_trace_t;
+
+/* Count the events in use (per event id, not per instance) */
+static int      total_ref_count;
+
+static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
+                                 struct perf_event *p_event)
+{
+        /* No tracing, just counting, so no obvious leak */
+        if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
+                return 0;
+
+        /* Some events are ok to be traced by non-root users... */
+        if (p_event->attach_state == PERF_ATTACH_TASK) {
+                if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY)
+                        return 0;
+        }
+
+        /*
+         * ...otherwise raw tracepoint data can be a severe data leak,
+         * only allow root to have these.
+         */
+        if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+                return -EPERM;
+
+        return 0;
+}
+
+static int perf_trace_event_init(struct ftrace_event_call *tp_event,
+                                 struct perf_event *p_event)
+{
+        struct hlist_head __percpu *list;
+        int ret;
+        int cpu;
+
+        ret = perf_trace_event_perm(tp_event, p_event);
+        if (ret)
+                return ret;
+
+        p_event->tp_event = tp_event;
+        if (tp_event->perf_refcount++ > 0)
+                return 0;
+
+        ret = -ENOMEM;
+
+        list = alloc_percpu(struct hlist_head);
+        if (!list)
+                goto fail;
+
+        for_each_possible_cpu(cpu)
+                INIT_HLIST_HEAD(per_cpu_ptr(list, cpu));
+
+        tp_event->perf_events = list;
+
+        if (!total_ref_count) {
+                char __percpu *buf;
+                int i;
+
+                for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+                        buf = (char __percpu *)alloc_percpu(perf_trace_t);
+                        if (!buf)
+                                goto fail;
+
+                        perf_trace_buf[i] = buf;
+                }
+        }
+
+        ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
+        if (ret)
+                goto fail;
+
+        total_ref_count++;
+        return 0;
+
+fail:
+        if (!total_ref_count) {
+                int i;
+
+                for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+                        free_percpu(perf_trace_buf[i]);
+                        perf_trace_buf[i] = NULL;
+                }
+        }
+
+        if (!--tp_event->perf_refcount) {
+                free_percpu(tp_event->perf_events);
+                tp_event->perf_events = NULL;
+        }
+
+        return ret;
+}
+
+int perf_trace_init(struct perf_event *p_event)
+{
+        struct ftrace_event_call *tp_event;
+        int event_id = p_event->attr.config;
+        int ret = -EINVAL;
+
+        mutex_lock(&event_mutex);
+        list_for_each_entry(tp_event, &ftrace_events, list) {
+                if (tp_event->event.type == event_id &&
+                    tp_event->class && tp_event->class->reg &&
+                    try_module_get(tp_event->mod)) {
+                        ret = perf_trace_event_init(tp_event, p_event);
+                        if (ret)
+                                module_put(tp_event->mod);
+                        break;
+                }
+        }
+        mutex_unlock(&event_mutex);
+
+        return ret;
+}
+
+int perf_trace_add(struct perf_event *p_event, int flags)
+{
+        struct ftrace_event_call *tp_event = p_event->tp_event;
+        struct hlist_head __percpu *pcpu_list;
+        struct hlist_head *list;
+
+        pcpu_list = tp_event->perf_events;
+        if (WARN_ON_ONCE(!pcpu_list))
+                return -EINVAL;
+
+        if (!(flags & PERF_EF_START))
+                p_event->hw.state = PERF_HES_STOPPED;
+
+        list = this_cpu_ptr(pcpu_list);
+        hlist_add_head_rcu(&p_event->hlist_entry, list);
+
+        return 0;
+}
+
+void perf_trace_del(struct perf_event *p_event, int flags)
+{
+        hlist_del_rcu(&p_event->hlist_entry);
+}
+
+void perf_trace_destroy(struct perf_event *p_event)
+{
+        struct ftrace_event_call *tp_event = p_event->tp_event;
+        int i;
+
+        mutex_lock(&event_mutex);
+        if (--tp_event->perf_refcount > 0)
+                goto out;
+
+        tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
+
+        /*
+         * Ensure our callback won't be called anymore. The buffers
+         * will be freed after that.
+         */
+        tracepoint_synchronize_unregister();
+
+        free_percpu(tp_event->perf_events);
+        tp_event->perf_events = NULL;
+
+        if (!--total_ref_count) {
+                for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+                        free_percpu(perf_trace_buf[i]);
+                        perf_trace_buf[i] = NULL;
+                }
+        }
+out:
+        module_put(tp_event->mod);
+        mutex_unlock(&event_mutex);
+}
+
+__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
+                                       struct pt_regs *regs, int *rctxp)
+{
+        struct trace_entry *entry;
+        unsigned long flags;
+        char *raw_data;
+        int pc;
+
+        BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
+
+        pc = preempt_count();
+
+        *rctxp = perf_swevent_get_recursion_context();
+        if (*rctxp < 0)
+                return NULL;
+
+        raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]);
+
+        /* zero the dead bytes from align to not leak stack to user */
+        memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
+
+        entry = (struct trace_entry *)raw_data;
+        local_save_flags(flags);
+        tracing_generic_entry_update(entry, flags, pc);
+        entry->type = type;
+
+        return raw_data;
+}
+EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c
deleted file mode 100644
index 5b5895afecfe..000000000000
--- a/kernel/trace/trace_event_profile.c
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * trace event based perf counter profiling
- *
- * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
- *
- */
-
-#include "trace.h"
-
-int ftrace_profile_enable(int event_id)
-{
-        struct ftrace_event_call *event;
-        int ret = -EINVAL;
-
-        mutex_lock(&event_mutex);
-        list_for_each_entry(event, &ftrace_events, list) {
-                if (event->id == event_id) {
-                        ret = event->profile_enable(event);
-                        break;
-                }
-        }
-        mutex_unlock(&event_mutex);
-
-        return ret;
-}
-
-void ftrace_profile_disable(int event_id)
-{
-        struct ftrace_event_call *event;
-
-        mutex_lock(&event_mutex);
-        list_for_each_entry(event, &ftrace_events, list) {
-                if (event->id == event_id) {
-                        event->profile_disable(event);
-                        break;
-                }
-        }
-        mutex_unlock(&event_mutex);
-}
diff --git a/kernel/trace/trace_event_types.h b/kernel/trace/trace_event_types.h
deleted file mode 100644
index 5e32e375134d..000000000000
--- a/kernel/trace/trace_event_types.h
+++ /dev/null
@@ -1,175 +0,0 @@
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM    ftrace
-
-/*
- * We cheat and use the proto type field as the ID
- * and args as the entry type (minus 'struct')
- */
-TRACE_EVENT_FORMAT(function, TRACE_FN, ftrace_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(unsigned long, ip, ip)
-                TRACE_FIELD(unsigned long, parent_ip, parent_ip)
-        ),
-        TP_RAW_FMT(" %lx <-- %lx")
-);
-
-TRACE_EVENT_FORMAT(funcgraph_entry, TRACE_GRAPH_ENT,
-                   ftrace_graph_ent_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(unsigned long, graph_ent.func, func)
-                TRACE_FIELD(int, graph_ent.depth, depth)
-        ),
-        TP_RAW_FMT("--> %lx (%d)")
-);
-
-TRACE_EVENT_FORMAT(funcgraph_exit, TRACE_GRAPH_RET,
-                   ftrace_graph_ret_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(unsigned long, ret.func, func)
-                TRACE_FIELD(int, ret.depth, depth)
-        ),
-        TP_RAW_FMT("<-- %lx (%d)")
-);
-
-TRACE_EVENT_FORMAT(wakeup, TRACE_WAKE, ctx_switch_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(unsigned int, prev_pid, prev_pid)
-                TRACE_FIELD(unsigned char, prev_prio, prev_prio)
-                TRACE_FIELD(unsigned char, prev_state, prev_state)
-                TRACE_FIELD(unsigned int, next_pid, next_pid)
-                TRACE_FIELD(unsigned char, next_prio, next_prio)
-                TRACE_FIELD(unsigned char, next_state, next_state)
-                TRACE_FIELD(unsigned int, next_cpu, next_cpu)
-        ),
-        TP_RAW_FMT("%u:%u:%u  ==+ %u:%u:%u [%03u]")
-);
-
-TRACE_EVENT_FORMAT(context_switch, TRACE_CTX, ctx_switch_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(unsigned int, prev_pid, prev_pid)
-                TRACE_FIELD(unsigned char, prev_prio, prev_prio)
-                TRACE_FIELD(unsigned char, prev_state, prev_state)
-                TRACE_FIELD(unsigned int, next_pid, next_pid)
-                TRACE_FIELD(unsigned char, next_prio, next_prio)
-                TRACE_FIELD(unsigned char, next_state, next_state)
-                TRACE_FIELD(unsigned int, next_cpu, next_cpu)
-        ),
-        TP_RAW_FMT("%u:%u:%u  ==+ %u:%u:%u [%03u]")
-);
-
-TRACE_EVENT_FORMAT_NOFILTER(special, TRACE_SPECIAL, special_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(unsigned long, arg1, arg1)
-                TRACE_FIELD(unsigned long, arg2, arg2)
-                TRACE_FIELD(unsigned long, arg3, arg3)
-        ),
-        TP_RAW_FMT("(%08lx) (%08lx) (%08lx)")
-);
-
-/*
- * Stack-trace entry:
- */
-
-/* #define FTRACE_STACK_ENTRIES   8 */
-
-TRACE_EVENT_FORMAT(kernel_stack, TRACE_STACK, stack_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(unsigned long, caller[0], stack0)
-                TRACE_FIELD(unsigned long, caller[1], stack1)
-                TRACE_FIELD(unsigned long, caller[2], stack2)
-                TRACE_FIELD(unsigned long, caller[3], stack3)
-                TRACE_FIELD(unsigned long, caller[4], stack4)
-                TRACE_FIELD(unsigned long, caller[5], stack5)
-                TRACE_FIELD(unsigned long, caller[6], stack6)
-                TRACE_FIELD(unsigned long, caller[7], stack7)
-        ),
-        TP_RAW_FMT("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
-                 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n")
-);
-
-TRACE_EVENT_FORMAT(user_stack, TRACE_USER_STACK, userstack_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(unsigned long, caller[0], stack0)
-                TRACE_FIELD(unsigned long, caller[1], stack1)
-                TRACE_FIELD(unsigned long, caller[2], stack2)
-                TRACE_FIELD(unsigned long, caller[3], stack3)
-                TRACE_FIELD(unsigned long, caller[4], stack4)
-                TRACE_FIELD(unsigned long, caller[5], stack5)
-                TRACE_FIELD(unsigned long, caller[6], stack6)
-                TRACE_FIELD(unsigned long, caller[7], stack7)
-        ),
-        TP_RAW_FMT("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
-                 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n")
-);
-
-TRACE_EVENT_FORMAT(bprint, TRACE_BPRINT, bprint_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(unsigned long, ip, ip)
-                TRACE_FIELD(char *, fmt, fmt)
-                TRACE_FIELD_ZERO_CHAR(buf)
-        ),
-        TP_RAW_FMT("%08lx (%d) fmt:%p %s")
-);
-
-TRACE_EVENT_FORMAT(print, TRACE_PRINT, print_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(unsigned long, ip, ip)
-                TRACE_FIELD_ZERO_CHAR(buf)
-        ),
-        TP_RAW_FMT("%08lx (%d) fmt:%p %s")
-);
-
-TRACE_EVENT_FORMAT(branch, TRACE_BRANCH, trace_branch, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(unsigned int, line, line)
-                TRACE_FIELD_SPECIAL(char func[TRACE_FUNC_SIZE+1], func,
-                                    TRACE_FUNC_SIZE+1, func)
-                TRACE_FIELD_SPECIAL(char file[TRACE_FUNC_SIZE+1], file,
-                                    TRACE_FUNC_SIZE+1, file)
-                TRACE_FIELD(char, correct, correct)
-        ),
-        TP_RAW_FMT("%u:%s:%s (%u)")
-);
-
-TRACE_EVENT_FORMAT(hw_branch, TRACE_HW_BRANCHES, hw_branch_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(u64, from, from)
-                TRACE_FIELD(u64, to, to)
-        ),
-        TP_RAW_FMT("from: %llx to: %llx")
-);
-
-TRACE_EVENT_FORMAT(power, TRACE_POWER, trace_power, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD_SIGN(ktime_t, state_data.stamp, stamp, 1)
-                TRACE_FIELD_SIGN(ktime_t, state_data.end, end, 1)
-                TRACE_FIELD(int, state_data.type, type)
-                TRACE_FIELD(int, state_data.state, state)
-        ),
-        TP_RAW_FMT("%llx->%llx type:%u state:%u")
-);
-
-TRACE_EVENT_FORMAT(kmem_alloc, TRACE_KMEM_ALLOC, kmemtrace_alloc_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(enum kmemtrace_type_id, type_id, type_id)
-                TRACE_FIELD(unsigned long, call_site, call_site)
-                TRACE_FIELD(const void *, ptr, ptr)
-                TRACE_FIELD(size_t, bytes_req, bytes_req)
-                TRACE_FIELD(size_t, bytes_alloc, bytes_alloc)
-                TRACE_FIELD(gfp_t, gfp_flags, gfp_flags)
-                TRACE_FIELD(int, node, node)
-        ),
-        TP_RAW_FMT("type:%u call_site:%lx ptr:%p req:%lu alloc:%lu"
-                 " flags:%x node:%d")
-);
-
-TRACE_EVENT_FORMAT(kmem_free, TRACE_KMEM_FREE, kmemtrace_free_entry, ignore,
-        TRACE_STRUCT(
-                TRACE_FIELD(enum kmemtrace_type_id, type_id, type_id)
-                TRACE_FIELD(unsigned long, call_site, call_site)
-                TRACE_FIELD(const void *, ptr, ptr)
-        ),
-        TP_RAW_FMT("type:%u call_site:%lx ptr:%p")
-);
-
-#undef TRACE_SYSTEM
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index aa08be69a1b6..35fde09b81de 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -15,18 +15,38 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/slab.h>
 #include <linux/delay.h>
 
+#include <asm/setup.h>
+
 #include "trace_output.h"
 
+#undef TRACE_SYSTEM
 #define TRACE_SYSTEM "TRACE_SYSTEM"
 
 DEFINE_MUTEX(event_mutex);
 
+DEFINE_MUTEX(event_storage_mutex);
+EXPORT_SYMBOL_GPL(event_storage_mutex);
+
+char event_storage[EVENT_STORAGE_SIZE];
+EXPORT_SYMBOL_GPL(event_storage);
+
 LIST_HEAD(ftrace_events);
+LIST_HEAD(ftrace_common_fields);
 
-int trace_define_field(struct ftrace_event_call *call, char *type,
-                       char *name, int offset, int size, int is_signed)
+struct list_head *
+trace_get_fields(struct ftrace_event_call *event_call)
+{
+        if (!event_call->class->get_fields)
+                return &event_call->class->fields;
+        return event_call->class->get_fields(event_call);
+}
+
+static int __trace_define_field(struct list_head *head, const char *type,
+                                const char *name, int offset, int size,
+                                int is_signed, int filter_type)
 {
         struct ftrace_event_field *field;
 
@@ -42,31 +62,72 @@ int trace_define_field(struct ftrace_event_call *call, char *type,
         if (!field->type)
                 goto err;
 
+        if (filter_type == FILTER_OTHER)
+                field->filter_type = filter_assign_type(type);
+        else
+                field->filter_type = filter_type;
+
         field->offset = offset;
         field->size = size;
         field->is_signed = is_signed;
-        list_add(&field->link, &call->fields);
+
+        list_add(&field->link, head);
 
         return 0;
 
 err:
-        if (field) {
+        if (field)
                 kfree(field->name);
-                kfree(field->type);
-        }
         kfree(field);
 
         return -ENOMEM;
 }
+
+int trace_define_field(struct ftrace_event_call *call, const char *type,
+                       const char *name, int offset, int size, int is_signed,
+                       int filter_type)
+{
+        struct list_head *head;
+
+        if (WARN_ON(!call->class))
+                return 0;
+
+        head = trace_get_fields(call);
+        return __trace_define_field(head, type, name, offset, size,
+                                    is_signed, filter_type);
+}
 EXPORT_SYMBOL_GPL(trace_define_field);
 
-#ifdef CONFIG_MODULES
+#define __common_field(type, item)                                      \
+        ret = __trace_define_field(&ftrace_common_fields, #type,        \
+                                   "common_" #item,                     \
+                                   offsetof(typeof(ent), item),         \
+                                   sizeof(ent.item),                    \
+                                   is_signed_type(type), FILTER_OTHER); \
+        if (ret)                                                        \
+                return ret;
+
+static int trace_define_common_fields(void)
+{
+        int ret;
+        struct trace_entry ent;
+
+        __common_field(unsigned short, type);
+        __common_field(unsigned char, flags);
+        __common_field(unsigned char, preempt_count);
+        __common_field(int, pid);
+        __common_field(int, lock_depth);
+
+        return ret;
+}
 
-static void trace_destroy_fields(struct ftrace_event_call *call)
+void trace_destroy_fields(struct ftrace_event_call *call)
 {
         struct ftrace_event_field *field, *next;
+        struct list_head *head;
 
-        list_for_each_entry_safe(field, next, &call->fields, link) {
+        head = trace_get_fields(call);
+        list_for_each_entry_safe(field, next, head, link) {
                 list_del(&field->link);
                 kfree(field->type);
                 kfree(field->name);
@@ -74,27 +135,102 @@ static void trace_destroy_fields(struct ftrace_event_call *call)
         }
 }
 
-#endif /* CONFIG_MODULES */
+int trace_event_raw_init(struct ftrace_event_call *call)
+{
+        int id;
+
+        id = register_ftrace_event(&call->event);
+        if (!id)
+                return -ENODEV;
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(trace_event_raw_init);
+
+int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
+{
+        switch (type) {
+        case TRACE_REG_REGISTER:
+                return tracepoint_probe_register(call->name,
+                                                 call->class->probe,
+                                                 call);
+        case TRACE_REG_UNREGISTER:
+                tracepoint_probe_unregister(call->name,
+                                            call->class->probe,
+                                            call);
+                return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+        case TRACE_REG_PERF_REGISTER:
+                return tracepoint_probe_register(call->name,
+                                                 call->class->perf_probe,
+                                                 call);
+        case TRACE_REG_PERF_UNREGISTER:
+                tracepoint_probe_unregister(call->name,
+                                            call->class->perf_probe,
+                                            call);
+                return 0;
+#endif
+        }
+        return 0;
+}
+EXPORT_SYMBOL_GPL(ftrace_event_reg);
+
+void trace_event_enable_cmd_record(bool enable)
+{
+        struct ftrace_event_call *call;
+
+        mutex_lock(&event_mutex);
+        list_for_each_entry(call, &ftrace_events, list) {
+                if (!(call->flags & TRACE_EVENT_FL_ENABLED))
+                        continue;
+
+                if (enable) {
+                        tracing_start_cmdline_record();
+                        call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
+                } else {
+                        tracing_stop_cmdline_record();
+                        call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
+                }
+        }
+        mutex_unlock(&event_mutex);
+}
 
-static void ftrace_event_enable_disable(struct ftrace_event_call *call,
+static int ftrace_event_enable_disable(struct ftrace_event_call *call,
                                         int enable)
 {
+        int ret = 0;
+
         switch (enable) {
         case 0:
-                if (call->enabled) {
-                        call->enabled = 0;
-                        tracing_stop_cmdline_record();
-                        call->unregfunc();
+                if (call->flags & TRACE_EVENT_FL_ENABLED) {
+                        call->flags &= ~TRACE_EVENT_FL_ENABLED;
+                        if (call->flags & TRACE_EVENT_FL_RECORDED_CMD) {
+                                tracing_stop_cmdline_record();
+                                call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
+                        }
+                        call->class->reg(call, TRACE_REG_UNREGISTER);
                 }
                 break;
         case 1:
-                if (!call->enabled) {
-                        call->enabled = 1;
-                        tracing_start_cmdline_record();
-                        call->regfunc();
+                if (!(call->flags & TRACE_EVENT_FL_ENABLED)) {
+                        if (trace_flags & TRACE_ITER_RECORD_CMD) {
+                                tracing_start_cmdline_record();
+                                call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
+                        }
+                        ret = call->class->reg(call, TRACE_REG_REGISTER);
+                        if (ret) {
+                                tracing_stop_cmdline_record();
+                                pr_info("event trace: Could not enable event "
+                                        "%s\n", call->name);
+                                break;
+                        }
+                        call->flags |= TRACE_EVENT_FL_ENABLED;
                 }
                 break;
         }
+
+        return ret;
 }
 
 static void ftrace_clear_events(void)
@@ -120,15 +256,15 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
         mutex_lock(&event_mutex);
         list_for_each_entry(call, &ftrace_events, list) {
 
-                if (!call->name || !call->regfunc)
+                if (!call->name || !call->class || !call->class->reg)
                         continue;
 
                 if (match &&
                     strcmp(match, call->name) != 0 &&
-                    strcmp(match, call->system) != 0)
+                    strcmp(match, call->class->system) != 0)
                         continue;
 
-                if (sub && strcmp(sub, call->system) != 0)
+                if (sub && strcmp(sub, call->class->system) != 0)
                         continue;
 
                 if (event && strcmp(event, call->name) != 0)
@@ -198,73 +334,38 @@ static ssize_t
 ftrace_event_write(struct file *file, const char __user *ubuf,
                    size_t cnt, loff_t *ppos)
 {
-        size_t read = 0;
-        int i, set = 1;
-        ssize_t ret;
-        char *buf;
-        char ch;
+        struct trace_parser parser;
+        ssize_t read, ret;
 
-        if (!cnt || cnt < 0)
+        if (!cnt)
                 return 0;
 
         ret = tracing_update_buffers();
         if (ret < 0)
                 return ret;
 
-        ret = get_user(ch, ubuf++);
-        if (ret)
-                return ret;
-        read++;
-        cnt--;
-
-        /* skip white space */
-        while (cnt && isspace(ch)) {
-                ret = get_user(ch, ubuf++);
-                if (ret)
-                        return ret;
-                read++;
-                cnt--;
-        }
-
-        /* Only white space found? */
-        if (isspace(ch)) {
-                file->f_pos += read;
-                ret = read;
-                return ret;
-        }
-
-        buf = kmalloc(EVENT_BUF_SIZE+1, GFP_KERNEL);
-        if (!buf)
+        if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1))
                 return -ENOMEM;
 
-        if (cnt > EVENT_BUF_SIZE)
-                cnt = EVENT_BUF_SIZE;
+        read = trace_get_user(&parser, ubuf, cnt, ppos);
 
-        i = 0;
-        while (cnt && !isspace(ch)) {
-                if (!i && ch == '!')
+        if (read >= 0 && trace_parser_loaded((&parser))) {
+                int set = 1;
+
+                if (*parser.buffer == '!')
                         set = 0;
-                else
-                        buf[i++] = ch;
 
-                ret = get_user(ch, ubuf++);
+                parser.buffer[parser.idx] = 0;
+
+                ret = ftrace_set_clr_event(parser.buffer + !set, set);
                 if (ret)
-                        goto out_free;
-                read++;
-                cnt--;
+                        goto out_put;
         }
-        buf[i] = 0;
-
-        file->f_pos += read;
-
-        ret = ftrace_set_clr_event(buf, set);
-        if (ret)
-                goto out_free;
 
         ret = read;
 
- out_free:
-        kfree(buf);
+ out_put:
+        trace_parser_put(&parser);
 
         return ret;
 }
@@ -272,78 +373,75 @@ ftrace_event_write(struct file *file, const char __user *ubuf,
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-        struct list_head *list = m->private;
-        struct ftrace_event_call *call;
+        struct ftrace_event_call *call = v;
 
         (*pos)++;
 
-        for (;;) {
-                if (list == &ftrace_events)
-                        return NULL;
-
-                call = list_entry(list, struct ftrace_event_call, list);
-
+        list_for_each_entry_continue(call, &ftrace_events, list) {
                 /*
                  * The ftrace subsystem is for showing formats only.
                  * They can not be enabled or disabled via the event files.
                  */
-                if (call->regfunc)
-                        break;
-
-                list = list->next;
+                if (call->class && call->class->reg)
+                        return call;
         }
 
-        m->private = list->next;
-
-        return call;
+        return NULL;
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
+        struct ftrace_event_call *call;
+        loff_t l;
+
         mutex_lock(&event_mutex);
-        if (*pos == 0)
-                m->private = ftrace_events.next;
-        return t_next(m, NULL, pos);
+
+        call = list_entry(&ftrace_events, struct ftrace_event_call, list);
+        for (l = 0; l <= *pos; ) {
+                call = t_next(m, call, &l);
+                if (!call)
+                        break;
+        }
+        return call;
 }
 
 static void *
 s_next(struct seq_file *m, void *v, loff_t *pos)
 {
-        struct list_head *list = m->private;
-        struct ftrace_event_call *call;
+        struct ftrace_event_call *call = v;
 
         (*pos)++;
 
- retry:
-        if (list == &ftrace_events)
-                return NULL;
-
-        call = list_entry(list, struct ftrace_event_call, list);
-
-        if (!call->enabled) {
-                list = list->next;
-                goto retry;
+        list_for_each_entry_continue(call, &ftrace_events, list) {
+                if (call->flags & TRACE_EVENT_FL_ENABLED)
+                        return call;
         }
 
-        m->private = list->next;
-
-        return call;
+        return NULL;
 }
 
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
+        struct ftrace_event_call *call;
+        loff_t l;
+
         mutex_lock(&event_mutex);
-        if (*pos == 0)
-                m->private = ftrace_events.next;
-        return s_next(m, NULL, pos);
+
+        call = list_entry(&ftrace_events, struct ftrace_event_call, list);
+        for (l = 0; l <= *pos; ) {
+                call = s_next(m, call, &l);
+                if (!call)
+                        break;
+        }
+        return call;
 }
 
 static int t_show(struct seq_file *m, void *v)
 {
         struct ftrace_event_call *call = v;
 
-        if (strcmp(call->system, TRACE_SYSTEM) != 0)
-                seq_printf(m, "%s:", call->system);
+        if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
+                seq_printf(m, "%s:", call->class->system);
         seq_printf(m, "%s\n", call->name);
 
         return 0;
@@ -360,7 +458,7 @@ ftrace_event_seq_open(struct inode *inode, struct file *file)
         const struct seq_operations *seq_ops;
 
         if ((file->f_mode & FMODE_WRITE) &&
-            !(file->f_flags & O_APPEND))
+            (file->f_flags & O_TRUNC))
                 ftrace_clear_events();
 
         seq_ops = inode->i_private;
@@ -374,7 +472,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
         struct ftrace_event_call *call = filp->private_data;
         char *buf;
 
-        if (call->enabled)
+        if (call->flags & TRACE_EVENT_FL_ENABLED)
                 buf = "1\n";
         else
                 buf = "0\n";
@@ -411,7 +509,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
         case 0:
         case 1:
                 mutex_lock(&event_mutex);
-                ftrace_event_enable_disable(call, val);
+                ret = ftrace_event_enable_disable(call, val);
                 mutex_unlock(&event_mutex);
                 break;
 
@@ -421,7 +519,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
         *ppos += cnt;
 
-        return cnt;
+        return ret ? ret : cnt;
 }
 
 static ssize_t
@@ -437,10 +535,10 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 
         mutex_lock(&event_mutex);
         list_for_each_entry(call, &ftrace_events, list) {
-                if (!call->name || !call->regfunc)
+                if (!call->name || !call->class || !call->class->reg)
                         continue;
 
-                if (system && strcmp(call->system, system) != 0)
+                if (system && strcmp(call->class->system, system) != 0)
                         continue;
 
                 /*
@@ -448,7 +546,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
                  * or if all events or cleared, or if we have
                  * a mixture.
                  */
-                set |= (1 << !!call->enabled);
+                set |= (1 << !!(call->flags & TRACE_EVENT_FL_ENABLED));
 
                 /*
                  * If we have a mixture, no need to look further.
@@ -506,74 +604,146 @@ out:
         return ret;
 }
 
-extern char *__bad_type_size(void);
+enum {
+        FORMAT_HEADER           = 1,
+        FORMAT_FIELD_SEPERATOR  = 2,
+        FORMAT_PRINTFMT         = 3,
+};
+
+static void *f_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        struct ftrace_event_call *call = m->private;
+        struct ftrace_event_field *field;
+        struct list_head *common_head = &ftrace_common_fields;
+        struct list_head *head = trace_get_fields(call);
+
+        (*pos)++;
+
+        switch ((unsigned long)v) {
+        case FORMAT_HEADER:
+                if (unlikely(list_empty(common_head)))
+                        return NULL;
+
+                field = list_entry(common_head->prev,
+                                   struct ftrace_event_field, link);
+                return field;
+
+        case FORMAT_FIELD_SEPERATOR:
+                if (unlikely(list_empty(head)))
+                        return NULL;
+
+                field = list_entry(head->prev, struct ftrace_event_field, link);
+                return field;
 
-#undef FIELD
-#define FIELD(type, name)                                               \
-        sizeof(type) != sizeof(field.name) ? __bad_type_size() :        \
-        #type, "common_" #name, offsetof(typeof(field), name),          \
-                sizeof(field.name)
+        case FORMAT_PRINTFMT:
+                /* all done */
+                return NULL;
+        }
+
+        field = v;
+        if (field->link.prev == common_head)
+                return (void *)FORMAT_FIELD_SEPERATOR;
+        else if (field->link.prev == head)
+                return (void *)FORMAT_PRINTFMT;
 
-static int trace_write_header(struct trace_seq *s)
+        field = list_entry(field->link.prev, struct ftrace_event_field, link);
+
+        return field;
+}
+
+static void *f_start(struct seq_file *m, loff_t *pos)
 {
-        struct trace_entry field;
-
-        /* struct trace_entry */
-        return trace_seq_printf(s,
-                                "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                                "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                                "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                                "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                                "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                                "\n",
-                                FIELD(unsigned short, type),
-                                FIELD(unsigned char, flags),
-                                FIELD(unsigned char, preempt_count),
-                                FIELD(int, pid),
-                                FIELD(int, tgid));
+        loff_t l = 0;
+        void *p;
+
+        /* Start by showing the header */
+        if (!*pos)
+                return (void *)FORMAT_HEADER;
+
+        p = (void *)FORMAT_HEADER;
+        do {
+                p = f_next(m, p, &l);
+        } while (p && l < *pos);
+
+        return p;
 }
 
-static ssize_t
-event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
-                  loff_t *ppos)
+static int f_show(struct seq_file *m, void *v)
 {
-        struct ftrace_event_call *call = filp->private_data;
-        struct trace_seq *s;
-        char *buf;
-        int r;
+        struct ftrace_event_call *call = m->private;
+        struct ftrace_event_field *field;
+        const char *array_descriptor;
 
-        if (*ppos)
+        switch ((unsigned long)v) {
+        case FORMAT_HEADER:
+                seq_printf(m, "name: %s\n", call->name);
+                seq_printf(m, "ID: %d\n", call->event.type);
+                seq_printf(m, "format:\n");
                 return 0;
 
-        s = kmalloc(sizeof(*s), GFP_KERNEL);
-        if (!s)
-                return -ENOMEM;
+        case FORMAT_FIELD_SEPERATOR:
+                seq_putc(m, '\n');
+                return 0;
 
-        trace_seq_init(s);
+        case FORMAT_PRINTFMT:
+                seq_printf(m, "\nprint fmt: %s\n",
+                           call->print_fmt);
+                return 0;
+        }
 
-        /* If any of the first writes fail, so will the show_format. */
+        field = v;
 
-        trace_seq_printf(s, "name: %s\n", call->name);
-        trace_seq_printf(s, "ID: %d\n", call->id);
-        trace_seq_printf(s, "format:\n");
-        trace_write_header(s);
+        /*
+         * Smartly shows the array type(except dynamic array).
+         * Normal:
+         *      field:TYPE VAR
+         * If TYPE := TYPE[LEN], it is shown:
+         *      field:TYPE VAR[LEN]
+         */
+        array_descriptor = strchr(field->type, '[');
 
-        r = call->show_format(s);
-        if (!r) {
-                /*
-                 * ug!  The format output is bigger than a PAGE!!
-                 */
-                buf = "FORMAT TOO BIG\n";
-                r = simple_read_from_buffer(ubuf, cnt, ppos,
-                                              buf, strlen(buf));
-                goto out;
-        }
+        if (!strncmp(field->type, "__data_loc", 10))
+                array_descriptor = NULL;
 
-        r = simple_read_from_buffer(ubuf, cnt, ppos,
-                                    s->buffer, s->len);
- out:
-        kfree(s);
-        return r;
+        if (!array_descriptor)
+                seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+                           field->type, field->name, field->offset,
+                           field->size, !!field->is_signed);
+        else
+                seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+                           (int)(array_descriptor - field->type),
+                           field->type, field->name,
+                           array_descriptor, field->offset,
+                           field->size, !!field->is_signed);
+
+        return 0;
+}
+
+static void f_stop(struct seq_file *m, void *p)
+{
+}
+
+static const struct seq_operations trace_format_seq_ops = {
+        .start          = f_start,
+        .next           = f_next,
+        .stop           = f_stop,
+        .show           = f_show,
+};
+
+static int trace_format_open(struct inode *inode, struct file *file)
+{
+        struct ftrace_event_call *call = inode->i_private;
+        struct seq_file *m;
+        int ret;
+
+        ret = seq_open(file, &trace_format_seq_ops);
+        if (ret < 0)
+                return ret;
+
+        m = file->private_data;
+        m->private = call;
+
+        return 0;
 }
 
 static ssize_t
@@ -591,7 +761,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
                 return -ENOMEM;
 
         trace_seq_init(s);
-        trace_seq_printf(s, "%d\n", call->id);
+        trace_seq_printf(s, "%d\n", call->event.type);
 
         r = simple_read_from_buffer(ubuf, cnt, ppos,
                                     s->buffer, s->len);
@@ -768,39 +938,47 @@ static const struct file_operations ftrace_enable_fops = {
         .open = tracing_open_generic,
         .read = event_enable_read,
         .write = event_enable_write,
+        .llseek = default_llseek,
 };
 
 static const struct file_operations ftrace_event_format_fops = {
-        .open = tracing_open_generic,
-        .read = event_format_read,
+        .open = trace_format_open,
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .release = seq_release,
 };
 
 static const struct file_operations ftrace_event_id_fops = {
         .open = tracing_open_generic,
         .read = event_id_read,
+        .llseek = default_llseek,
 };
 
 static const struct file_operations ftrace_event_filter_fops = {
         .open = tracing_open_generic,
         .read = event_filter_read,
         .write = event_filter_write,
+        .llseek = default_llseek,
 };
 
 static const struct file_operations ftrace_subsystem_filter_fops = {
         .open = tracing_open_generic,
         .read = subsystem_filter_read,
         .write = subsystem_filter_write,
+        .llseek = default_llseek,
 };
 
 static const struct file_operations ftrace_system_enable_fops = {
         .open = tracing_open_generic,
         .read = system_enable_read,
         .write = system_enable_write,
+        .llseek = default_llseek,
 };
 
 static const struct file_operations ftrace_show_header_fops = {
         .open = tracing_open_generic,
         .read = show_header,
+        .llseek = default_llseek,
 };
 
 static struct dentry *event_trace_events_dir(void)
@@ -833,8 +1011,10 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 
         /* First see if we did not already create this dir */
         list_for_each_entry(system, &event_subsystems, list) {
-                if (strcmp(system->name, name) == 0)
+                if (strcmp(system->name, name) == 0) {
+                        system->nr_events++;
                         return system->entry;
+                }
         }
 
         /* need to create new entry */
@@ -853,6 +1033,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
                 return d_events;
         }
 
+        system->nr_events = 1;
         system->name = kstrdup(name, GFP_KERNEL);
         if (!system->name) {
                 debugfs_remove(system->entry);
@@ -880,9 +1061,9 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
                            "'%s/filter' entry\n", name);
         }
 
-        entry = trace_create_file("enable", 0644, system->entry,
-                                  (void *)system->name,
-                                  &ftrace_system_enable_fops);
+        trace_create_file("enable", 0644, system->entry,
+                          (void *)system->name,
+                          &ftrace_system_enable_fops);
 
         return system->entry;
 }
@@ -894,24 +1075,15 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
                  const struct file_operations *filter,
                  const struct file_operations *format)
 {
-        struct dentry *entry;
+        struct list_head *head;
         int ret;
 
         /*
          * If the trace point header did not define TRACE_SYSTEM
          * then the system would be called "TRACE_SYSTEM".
          */
-        if (strcmp(call->system, TRACE_SYSTEM) != 0)
-                d_events = event_subsystem_dir(call->system, d_events);
-
-        if (call->raw_init) {
-                ret = call->raw_init();
-                if (ret < 0) {
-                        pr_warning("Could not initialize trace point"
-                                   " events/%s\n", call->name);
-                        return ret;
-                }
-        }
+        if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
+                d_events = event_subsystem_dir(call->class->system, d_events);
 
         call->dir = debugfs_create_dir(call->name, d_events);
         if (!call->dir) {
@@ -920,35 +1092,138 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
                 return -1;
         }
 
-        if (call->regfunc)
-                entry = trace_create_file("enable", 0644, call->dir, call,
-                                          enable);
+        if (call->class->reg)
+                trace_create_file("enable", 0644, call->dir, call,
+                                  enable);
 
-        if (call->id)
-                entry = trace_create_file("id", 0444, call->dir, call,
-                                          id);
+#ifdef CONFIG_PERF_EVENTS
+        if (call->event.type && call->class->reg)
+                trace_create_file("id", 0444, call->dir, call,
+                                  id);
+#endif
 
-        if (call->define_fields) {
-                ret = call->define_fields();
+        /*
+         * Other events may have the same class. Only update
+         * the fields if they are not already defined.
+         */
+        head = trace_get_fields(call);
+        if (list_empty(head)) {
+                ret = call->class->define_fields(call);
                 if (ret < 0) {
                         pr_warning("Could not initialize trace point"
                                    " events/%s\n", call->name);
                         return ret;
                 }
-                entry = trace_create_file("filter", 0644, call->dir, call,
-                                          filter);
         }
+        trace_create_file("filter", 0644, call->dir, call,
+                          filter);
 
-        /* A trace may not want to export its format */
-        if (!call->show_format)
-                return 0;
-
-        entry = trace_create_file("format", 0444, call->dir, call,
-                                  format);
+        trace_create_file("format", 0444, call->dir, call,
+                          format);
 
         return 0;
 }
 
+static int
+__trace_add_event_call(struct ftrace_event_call *call, struct module *mod,
+                       const struct file_operations *id,
+                       const struct file_operations *enable,
+                       const struct file_operations *filter,
+                       const struct file_operations *format)
+{
+        struct dentry *d_events;
+        int ret;
+
+        /* The linker may leave blanks */
+        if (!call->name)
+                return -EINVAL;
+
+        if (call->class->raw_init) {
+                ret = call->class->raw_init(call);
+                if (ret < 0) {
+                        if (ret != -ENOSYS)
+                                pr_warning("Could not initialize trace events/%s\n",
+                                           call->name);
+                        return ret;
+                }
+        }
+
+        d_events = event_trace_events_dir();
+        if (!d_events)
+                return -ENOENT;
+
+        ret = event_create_dir(call, d_events, id, enable, filter, format);
+        if (!ret)
+                list_add(&call->list, &ftrace_events);
+        call->mod = mod;
+
+        return ret;
+}
+
+/* Add an additional event_call dynamically */
+int trace_add_event_call(struct ftrace_event_call *call)
+{
+        int ret;
+        mutex_lock(&event_mutex);
+        ret = __trace_add_event_call(call, NULL, &ftrace_event_id_fops,
+                                     &ftrace_enable_fops,
+                                     &ftrace_event_filter_fops,
+                                     &ftrace_event_format_fops);
+        mutex_unlock(&event_mutex);
+        return ret;
+}
+
+static void remove_subsystem_dir(const char *name)
+{
+        struct event_subsystem *system;
+
+        if (strcmp(name, TRACE_SYSTEM) == 0)
+                return;
+
+        list_for_each_entry(system, &event_subsystems, list) {
+                if (strcmp(system->name, name) == 0) {
+                        if (!--system->nr_events) {
+                                struct event_filter *filter = system->filter;
+
+                                debugfs_remove_recursive(system->entry);
+                                list_del(&system->list);
+                                if (filter) {
+                                        kfree(filter->filter_string);
+                                        kfree(filter);
+                                }
+                                kfree(system->name);
+                                kfree(system);
+                        }
+                        break;
+                }
+        }
+}
+
+/*
+ * Must be called under locking both of event_mutex and trace_event_mutex.
+ */
+static void __trace_remove_event_call(struct ftrace_event_call *call)
+{
+        ftrace_event_enable_disable(call, 0);
+        if (call->event.funcs)
+                __unregister_ftrace_event(&call->event);
+        debugfs_remove_recursive(call->dir);
+        list_del(&call->list);
+        trace_destroy_fields(call);
+        destroy_preds(call);
+        remove_subsystem_dir(call->class->system);
+}
+
+/* Remove an event_call */
+void trace_remove_event_call(struct ftrace_event_call *call)
+{
+        mutex_lock(&event_mutex);
+        down_write(&trace_event_mutex);
+        __trace_remove_event_call(call);
+        up_write(&trace_event_mutex);
+        mutex_unlock(&event_mutex);
+}
+
 #define for_each_event(event, start, end)                       \
         for (event = start;                                     \
              (unsigned long)event < (unsigned long)end;         \
@@ -1010,7 +1285,6 @@ static void trace_module_add_events(struct module *mod)
 {
         struct ftrace_module_file_ops *file_ops = NULL;
         struct ftrace_event_call *call, *start, *end;
-        struct dentry *d_events;
 
         start = mod->trace_events;
         end = mod->trace_events + mod->num_trace_events;
@@ -1018,29 +1292,14 @@ static void trace_module_add_events(struct module *mod)
         if (start == end)
                 return;
 
-        d_events = event_trace_events_dir();
-        if (!d_events)
+        file_ops = trace_create_file_ops(mod);
+        if (!file_ops)
                 return;
 
         for_each_event(call, start, end) {
-                /* The linker may leave blanks */
-                if (!call->name)
-                        continue;
-
-                /*
-                 * This module has events, create file ops for this module
-                 * if not already done.
-                 */
-                if (!file_ops) {
-                        file_ops = trace_create_file_ops(mod);
-                        if (!file_ops)
-                                return;
-                }
-                call->mod = mod;
-                list_add(&call->list, &ftrace_events);
-                event_create_dir(call, d_events,
-                                 &file_ops->id, &file_ops->enable,
-                                 &file_ops->filter, &file_ops->format);
+                __trace_add_event_call(call, mod,
+                                       &file_ops->id, &file_ops->enable,
+                                       &file_ops->filter, &file_ops->format);
         }
 }
 
@@ -1054,13 +1313,7 @@ static void trace_module_remove_events(struct module *mod)
         list_for_each_entry_safe(call, p, &ftrace_events, list) {
                 if (call->mod == mod) {
                         found = true;
-                        ftrace_event_enable_disable(call, 0);
-                        if (call->event)
-                                __unregister_ftrace_event(call->event);
-                        debugfs_remove_recursive(call->dir);
-                        list_del(&call->list);
-                        trace_destroy_fields(call);
-                        destroy_preds(call);
+                        __trace_remove_event_call(call);
                 }
         }
 
@@ -1109,7 +1362,7 @@ static int trace_module_notify(struct notifier_block *self,
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block trace_module_nb = {
+static struct notifier_block trace_module_nb = {
         .notifier_call = trace_module_notify,
         .priority = 0,
 };
@@ -1117,6 +1370,18 @@ struct notifier_block trace_module_nb = {
 extern struct ftrace_event_call __start_ftrace_events[];
 extern struct ftrace_event_call __stop_ftrace_events[];
 
+static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
+
+static __init int setup_trace_event(char *str)
+{
+        strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
+        ring_buffer_expanded = 1;
+        tracing_selftest_disabled = 1;
+
+        return 1;
+}
+__setup("trace_event=", setup_trace_event);
+
 static __init int event_trace_init(void)
 {
         struct ftrace_event_call *call;
@@ -1124,6 +1389,8 @@ static __init int event_trace_init(void)
         struct dentry *entry;
         struct dentry *d_events;
         int ret;
+        char *buf = bootup_event_buf;
+        char *token;
 
         d_tracer = tracing_init_dentry();
         if (!d_tracer)
@@ -1159,14 +1426,27 @@ static __init int event_trace_init(void)
         trace_create_file("enable", 0644, d_events,
                           NULL, &ftrace_system_enable_fops);
 
+        if (trace_define_common_fields())
+                pr_warning("tracing: Failed to allocate common fields");
+
         for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
-                /* The linker may leave blanks */
-                if (!call->name)
+                __trace_add_event_call(call, NULL, &ftrace_event_id_fops,
+                                       &ftrace_enable_fops,
+                                       &ftrace_event_filter_fops,
+                                       &ftrace_event_format_fops);
+        }
+
+        while (true) {
+                token = strsep(&buf, ",");
+
+                if (!token)
+                        break;
+                if (!*token)
                         continue;
-                list_add(&call->list, &ftrace_events);
-                event_create_dir(call, d_events, &ftrace_event_id_fops,
-                                 &ftrace_enable_fops, &ftrace_event_filter_fops,
-                                 &ftrace_event_format_fops);
+
+                ret = ftrace_set_clr_event(token, 1);
+                if (ret)
+                        pr_warning("Failed to enable trace event: %s\n", token);
         }
 
         ret = register_module_notifier(&trace_module_nb);
@@ -1241,17 +1521,29 @@ static __init void event_trace_self_tests(void)
 
         list_for_each_entry(call, &ftrace_events, list) {
 
-                /* Only test those that have a regfunc */
-                if (!call->regfunc)
+                /* Only test those that have a probe */
+                if (!call->class || !call->class->probe)
                         continue;
 
+/*
+ * Testing syscall events here is pretty useless, but
+ * we still do it if configured. But this is time consuming.
+ * What we really need is a user thread to perform the
+ * syscalls as we test.
+ */
+#ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS
+                if (call->class->system &&
+                    strcmp(call->class->system, "syscalls") == 0)
+                        continue;
+#endif
+
                 pr_info("Testing event %s: ", call->name);
 
                 /*
                  * If an event is already enabled, someone is using
                  * it and the self test should not be on.
                  */
-                if (call->enabled) {
+                if (call->flags & TRACE_EVENT_FL_ENABLED) {
                         pr_warning("Enabled event during self test!\n");
                         WARN_ON_ONCE(1);
                         continue;
@@ -1318,30 +1610,31 @@ static __init void event_trace_self_tests(void)
 
 #ifdef CONFIG_FUNCTION_TRACER
 
-static DEFINE_PER_CPU(atomic_t, test_event_disable);
+static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable);
 
 static void
 function_test_events_call(unsigned long ip, unsigned long parent_ip)
 {
         struct ring_buffer_event *event;
+        struct ring_buffer *buffer;
         struct ftrace_entry *entry;
         unsigned long flags;
         long disabled;
-        int resched;
         int cpu;
         int pc;
 
         pc = preempt_count();
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
         cpu = raw_smp_processor_id();
-        disabled = atomic_inc_return(&per_cpu(test_event_disable, cpu));
+        disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu));
 
         if (disabled != 1)
                 goto out;
 
         local_save_flags(flags);
 
-        event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry),
+        event = trace_current_buffer_lock_reserve(&buffer,
+                                                  TRACE_FN, sizeof(*entry),
                                                   flags, pc);
         if (!event)
                 goto out;
@@ -1349,11 +1642,11 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
         entry->ip                       = ip;
         entry->parent_ip                = parent_ip;
 
-        trace_nowake_buffer_unlock_commit(event, flags, pc);
+        trace_nowake_buffer_unlock_commit(buffer, event, flags, pc);
 
  out:
-        atomic_dec(&per_cpu(test_event_disable, cpu));
-        ftrace_preempt_enable(resched);
+        atomic_dec(&per_cpu(ftrace_test_event_disable, cpu));
+        preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_ops __initdata  =
@@ -1376,10 +1669,10 @@ static __init void event_trace_self_test_with_function(void)
 
 static __init int event_trace_self_tests_init(void)
 {
-
-        event_trace_self_tests();
-
-        event_trace_self_test_with_function();
+        if (!tracing_selftest_disabled) {
+                event_trace_self_tests();
+                event_trace_self_test_with_function();
+        }
 
         return 0;
 }
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 936c621bbf46..36d40104b17f 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -18,11 +18,11 @@
  * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
  */
 
-#include <linux/debugfs.h>
-#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/mutex.h>
+#include <linux/perf_event.h>
+#include <linux/slab.h>
 
 #include "trace.h"
 #include "trace_output.h"
@@ -31,6 +31,7 @@ enum filter_op_ids
 {
         OP_OR,
         OP_AND,
+        OP_GLOB,
         OP_NE,
         OP_EQ,
         OP_LT,
@@ -48,16 +49,17 @@ struct filter_op {
 };
 
 static struct filter_op filter_ops[] = {
-        { OP_OR, "||", 1 },
-        { OP_AND, "&&", 2 },
-        { OP_NE, "!=", 4 },
-        { OP_EQ, "==", 4 },
-        { OP_LT, "<", 5 },
-        { OP_LE, "<=", 5 },
-        { OP_GT, ">", 5 },
-        { OP_GE, ">=", 5 },
-        { OP_NONE, "OP_NONE", 0 },
-        { OP_OPEN_PAREN, "(", 0 },
+        { OP_OR,        "||",           1 },
+        { OP_AND,       "&&",           2 },
+        { OP_GLOB,      "~",            4 },
+        { OP_NE,        "!=",           4 },
+        { OP_EQ,        "==",           4 },
+        { OP_LT,        "<",            5 },
+        { OP_LE,        "<=",           5 },
+        { OP_GT,        ">",            5 },
+        { OP_GE,        ">=",           5 },
+        { OP_NONE,      "OP_NONE",      0 },
+        { OP_OPEN_PAREN, "(",           0 },
 };
 
 enum {
@@ -121,6 +123,47 @@ struct filter_parse_state {
         } operand;
 };
 
+#define DEFINE_COMPARISON_PRED(type)                                    \
+static int filter_pred_##type(struct filter_pred *pred, void *event,    \
+                              int val1, int val2)                       \
+{                                                                       \
+        type *addr = (type *)(event + pred->offset);                    \
+        type val = (type)pred->val;                                     \
+        int match = 0;                                                  \
+                                                                        \
+        switch (pred->op) {                                             \
+        case OP_LT:                                                     \
+                match = (*addr < val);                                  \
+                break;                                                  \
+        case OP_LE:                                                     \
+                match = (*addr <= val);                                 \
+                break;                                                  \
+        case OP_GT:                                                     \
+                match = (*addr > val);                                  \
+                break;                                                  \
+        case OP_GE:                                                     \
+                match = (*addr >= val);                                 \
+                break;                                                  \
+        default:                                                        \
+                break;                                                  \
+        }                                                               \
+                                                                        \
+        return match;                                                   \
+}
+
+#define DEFINE_EQUALITY_PRED(size)                                      \
+static int filter_pred_##size(struct filter_pred *pred, void *event,    \
+                              int val1, int val2)                       \
+{                                                                       \
+        u##size *addr = (u##size *)(event + pred->offset);              \
+        u##size val = (u##size)pred->val;                               \
+        int match;                                                      \
+                                                                        \
+        match = (val == *addr) ^ pred->not;                             \
+                                                                        \
+        return match;                                                   \
+}
+
 DEFINE_COMPARISON_PRED(s64);
 DEFINE_COMPARISON_PRED(u64);
 DEFINE_COMPARISON_PRED(s32);
@@ -156,9 +199,24 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
         char *addr = (char *)(event + pred->offset);
         int cmp, match;
 
-        cmp = strncmp(addr, pred->str_val, pred->str_len);
+        cmp = pred->regex.match(addr, &pred->regex, pred->regex.field_len);
 
-        match = (!cmp) ^ pred->not;
+        match = cmp ^ pred->not;
+
+        return match;
+}
+
+/* Filter predicate for char * pointers */
+static int filter_pred_pchar(struct filter_pred *pred, void *event,
+                             int val1, int val2)
+{
+        char **addr = (char **)(event + pred->offset);
+        int cmp, match;
+        int len = strlen(*addr) + 1;    /* including tailing '\0' */
+
+        cmp = pred->regex.match(*addr, &pred->regex, len);
+
+        match = cmp ^ pred->not;
 
         return match;
 }
@@ -176,13 +234,15 @@ static int filter_pred_string(struct filter_pred *pred, void *event,
 static int filter_pred_strloc(struct filter_pred *pred, void *event,
                               int val1, int val2)
 {
-        unsigned short str_loc = *(unsigned short *)(event + pred->offset);
+        u32 str_item = *(u32 *)(event + pred->offset);
+        int str_loc = str_item & 0xffff;
+        int str_len = str_item >> 16;
         char *addr = (char *)(event + str_loc);
         int cmp, match;
 
-        cmp = strncmp(addr, pred->str_val, pred->str_len);
+        cmp = pred->regex.match(addr, &pred->regex, str_len);
 
-        match = (!cmp) ^ pred->not;
+        match = cmp ^ pred->not;
 
         return match;
 }
@@ -193,10 +253,133 @@ static int filter_pred_none(struct filter_pred *pred, void *event,
         return 0;
 }
 
+/*
+ * regex_match_foo - Basic regex callbacks
+ *
+ * @str: the string to be searched
+ * @r:   the regex structure containing the pattern string
+ * @len: the length of the string to be searched (including '\0')
+ *
+ * Note:
+ * - @str might not be NULL-terminated if it's of type DYN_STRING
+ *   or STATIC_STRING
+ */
+
+static int regex_match_full(char *str, struct regex *r, int len)
+{
+        if (strncmp(str, r->pattern, len) == 0)
+                return 1;
+        return 0;
+}
+
+static int regex_match_front(char *str, struct regex *r, int len)
+{
+        if (strncmp(str, r->pattern, r->len) == 0)
+                return 1;
+        return 0;
+}
+
+static int regex_match_middle(char *str, struct regex *r, int len)
+{
+        if (strnstr(str, r->pattern, len))
+                return 1;
+        return 0;
+}
+
+static int regex_match_end(char *str, struct regex *r, int len)
+{
+        int strlen = len - 1;
+
+        if (strlen >= r->len &&
+            memcmp(str + strlen - r->len, r->pattern, r->len) == 0)
+                return 1;
+        return 0;
+}
+
+/**
+ * filter_parse_regex - parse a basic regex
+ * @buff:   the raw regex
+ * @len:    length of the regex
+ * @search: will point to the beginning of the string to compare
+ * @not:    tell whether the match will have to be inverted
+ *
+ * This passes in a buffer containing a regex and this function will
+ * set search to point to the search part of the buffer and
+ * return the type of search it is (see enum above).
+ * This does modify buff.
+ *
+ * Returns enum type.
+ *  search returns the pointer to use for comparison.
+ *  not returns 1 if buff started with a '!'
+ *     0 otherwise.
+ */
+enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not)
+{
+        int type = MATCH_FULL;
+        int i;
+
+        if (buff[0] == '!') {
+                *not = 1;
+                buff++;
+                len--;
+        } else
+                *not = 0;
+
+        *search = buff;
+
+        for (i = 0; i < len; i++) {
+                if (buff[i] == '*') {
+                        if (!i) {
+                                *search = buff + 1;
+                                type = MATCH_END_ONLY;
+                        } else {
+                                if (type == MATCH_END_ONLY)
+                                        type = MATCH_MIDDLE_ONLY;
+                                else
+                                        type = MATCH_FRONT_ONLY;
+                                buff[i] = 0;
+                                break;
+                        }
+                }
+        }
+
+        return type;
+}
+
+static void filter_build_regex(struct filter_pred *pred)
+{
+        struct regex *r = &pred->regex;
+        char *search;
+        enum regex_type type = MATCH_FULL;
+        int not = 0;
+
+        if (pred->op == OP_GLOB) {
+                type = filter_parse_regex(r->pattern, r->len, &search, &not);
+                r->len = strlen(search);
+                memmove(r->pattern, search, r->len+1);
+        }
+
+        switch (type) {
+        case MATCH_FULL:
+                r->match = regex_match_full;
+                break;
+        case MATCH_FRONT_ONLY:
+                r->match = regex_match_front;
+                break;
+        case MATCH_MIDDLE_ONLY:
+                r->match = regex_match_middle;
+                break;
+        case MATCH_END_ONLY:
+                r->match = regex_match_end;
+                break;
+        }
+
+        pred->not ^= not;
+}
+
 /* return 1 if event matches, 0 otherwise (discard) */
-int filter_match_preds(struct ftrace_event_call *call, void *rec)
+int filter_match_preds(struct event_filter *filter, void *rec)
 {
-        struct event_filter *filter = call->filter;
         int match, top = 0, val1 = 0, val2 = 0;
         int stack[MAX_FILTER_PRED];
         struct filter_pred *pred;
@@ -293,7 +476,7 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
         struct event_filter *filter = call->filter;
 
         mutex_lock(&event_mutex);
-        if (filter->filter_string)
+        if (filter && filter->filter_string)
                 trace_seq_printf(s, "%s\n", filter->filter_string);
         else
                 trace_seq_printf(s, "none\n");
@@ -306,7 +489,7 @@ void print_subsystem_event_filter(struct event_subsystem *system,
         struct event_filter *filter = system->filter;
 
         mutex_lock(&event_mutex);
-        if (filter->filter_string)
+        if (filter && filter->filter_string)
                 trace_seq_printf(s, "%s\n", filter->filter_string);
         else
                 trace_seq_printf(s, "none\n");
@@ -314,11 +497,11 @@ void print_subsystem_event_filter(struct event_subsystem *system,
 }
 
 static struct ftrace_event_field *
-find_event_field(struct ftrace_event_call *call, char *name)
+__find_event_field(struct list_head *head, char *name)
 {
         struct ftrace_event_field *field;
 
-        list_for_each_entry(field, &call->fields, link) {
+        list_for_each_entry(field, head, link) {
                 if (!strcmp(field->name, name))
                         return field;
         }
@@ -326,6 +509,20 @@ find_event_field(struct ftrace_event_call *call, char *name)
         return NULL;
 }
 
+static struct ftrace_event_field *
+find_event_field(struct ftrace_event_call *call, char *name)
+{
+        struct ftrace_event_field *field;
+        struct list_head *head;
+
+        field = __find_event_field(&ftrace_common_fields, name);
+        if (field)
+                return field;
+
+        head = trace_get_fields(call);
+        return __find_event_field(head, name);
+}
+
 static void filter_free_pred(struct filter_pred *pred)
 {
         if (!pred)
@@ -339,7 +536,7 @@ static void filter_clear_pred(struct filter_pred *pred)
 {
         kfree(pred->field_name);
         pred->field_name = NULL;
-        pred->str_len = 0;
+        pred->regex.len = 0;
 }
 
 static int filter_set_pred(struct filter_pred *dest,
@@ -362,18 +559,20 @@ static void filter_disable_preds(struct ftrace_event_call *call)
         struct event_filter *filter = call->filter;
         int i;
 
-        call->filter_active = 0;
+        call->flags &= ~TRACE_EVENT_FL_FILTERED;
         filter->n_preds = 0;
 
         for (i = 0; i < MAX_FILTER_PRED; i++)
                 filter->preds[i]->fn = filter_pred_none;
 }
 
-void destroy_preds(struct ftrace_event_call *call)
+static void __free_preds(struct event_filter *filter)
 {
-        struct event_filter *filter = call->filter;
         int i;
 
+        if (!filter)
+                return;
+
         for (i = 0; i < MAX_FILTER_PRED; i++) {
                 if (filter->preds[i])
                         filter_free_pred(filter->preds[i]);
@@ -381,20 +580,25 @@ void destroy_preds(struct ftrace_event_call *call)
         kfree(filter->preds);
         kfree(filter->filter_string);
         kfree(filter);
+}
+
+void destroy_preds(struct ftrace_event_call *call)
+{
+        __free_preds(call->filter);
         call->filter = NULL;
+        call->flags &= ~TRACE_EVENT_FL_FILTERED;
 }
 
-int init_preds(struct ftrace_event_call *call)
+static struct event_filter *__alloc_preds(void)
 {
         struct event_filter *filter;
         struct filter_pred *pred;
         int i;
 
-        filter = call->filter = kzalloc(sizeof(*filter), GFP_KERNEL);
-        if (!call->filter)
-                return -ENOMEM;
+        filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+        if (!filter)
+                return ERR_PTR(-ENOMEM);
 
-        call->filter_active = 0;
         filter->n_preds = 0;
 
         filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL);
@@ -409,46 +613,62 @@ int init_preds(struct ftrace_event_call *call)
                 filter->preds[i] = pred;
         }
 
-        return 0;
+        return filter;
 
 oom:
-        destroy_preds(call);
+        __free_preds(filter);
+        return ERR_PTR(-ENOMEM);
+}
+
+static int init_preds(struct ftrace_event_call *call)
+{
+        if (call->filter)
+                return 0;
+
+        call->flags &= ~TRACE_EVENT_FL_FILTERED;
+        call->filter = __alloc_preds();
+        if (IS_ERR(call->filter))
+                return PTR_ERR(call->filter);
 
-        return -ENOMEM;
+        return 0;
 }
-EXPORT_SYMBOL_GPL(init_preds);
 
-static void filter_free_subsystem_preds(struct event_subsystem *system)
+static int init_subsystem_preds(struct event_subsystem *system)
 {
-        struct event_filter *filter = system->filter;
         struct ftrace_event_call *call;
-        int i;
+        int err;
 
-        if (filter->n_preds) {
-                for (i = 0; i < filter->n_preds; i++)
-                        filter_free_pred(filter->preds[i]);
-                kfree(filter->preds);
-                filter->preds = NULL;
-                filter->n_preds = 0;
+        list_for_each_entry(call, &ftrace_events, list) {
+                if (strcmp(call->class->system, system->name) != 0)
+                        continue;
+
+                err = init_preds(call);
+                if (err)
+                        return err;
         }
 
+        return 0;
+}
+
+static void filter_free_subsystem_preds(struct event_subsystem *system)
+{
+        struct ftrace_event_call *call;
+
         list_for_each_entry(call, &ftrace_events, list) {
-                if (!call->define_fields)
+                if (strcmp(call->class->system, system->name) != 0)
                         continue;
 
-                if (!strcmp(call->system, system->name)) {
-                        filter_disable_preds(call);
-                        remove_filter_string(call->filter);
-                }
+                filter_disable_preds(call);
+                remove_filter_string(call->filter);
         }
 }
 
 static int filter_add_pred_fn(struct filter_parse_state *ps,
                               struct ftrace_event_call *call,
+                              struct event_filter *filter,
                               struct filter_pred *pred,
                               filter_pred_fn_t fn)
 {
-        struct event_filter *filter = call->filter;
         int idx, err;
 
         if (filter->n_preds == MAX_FILTER_PRED) {
@@ -463,17 +683,11 @@ static int filter_add_pred_fn(struct filter_parse_state *ps,
                 return err;
 
         filter->n_preds++;
-        call->filter_active = 1;
 
         return 0;
 }
 
-enum {
-        FILTER_STATIC_STRING = 1,
-        FILTER_DYN_STRING
-};
-
-static int is_string_field(const char *type)
+int filter_assign_type(const char *type)
 {
         if (strstr(type, "__data_loc") && strstr(type, "char"))
                 return FILTER_DYN_STRING;
@@ -481,12 +695,22 @@ static int is_string_field(const char *type)
         if (strchr(type, '[') && strstr(type, "char"))
                 return FILTER_STATIC_STRING;
 
-        return 0;
+        return FILTER_OTHER;
+}
+
+static bool is_string_field(struct ftrace_event_field *field)
+{
+        return field->filter_type == FILTER_DYN_STRING ||
+               field->filter_type == FILTER_STATIC_STRING ||
+               field->filter_type == FILTER_PTR_STRING;
 }
 
 static int is_legal_op(struct ftrace_event_field *field, int op)
 {
-        if (is_string_field(field->type) && (op != OP_EQ && op != OP_NE))
+        if (is_string_field(field) &&
+            (op != OP_EQ && op != OP_NE && op != OP_GLOB))
+                return 0;
+        if (!is_string_field(field) && op == OP_GLOB)
                 return 0;
 
         return 1;
@@ -537,22 +761,25 @@ static filter_pred_fn_t select_comparison_fn(int op, int field_size,
 
 static int filter_add_pred(struct filter_parse_state *ps,
                            struct ftrace_event_call *call,
-                           struct filter_pred *pred)
+                           struct event_filter *filter,
+                           struct filter_pred *pred,
+                           bool dry_run)
 {
         struct ftrace_event_field *field;
         filter_pred_fn_t fn;
         unsigned long long val;
-        int string_type;
         int ret;
 
         pred->fn = filter_pred_none;
 
         if (pred->op == OP_AND) {
                 pred->pop_n = 2;
-                return filter_add_pred_fn(ps, call, pred, filter_pred_and);
+                fn = filter_pred_and;
+                goto add_pred_fn;
         } else if (pred->op == OP_OR) {
                 pred->pop_n = 2;
-                return filter_add_pred_fn(ps, call, pred, filter_pred_or);
+                fn = filter_pred_or;
+                goto add_pred_fn;
         }
 
         field = find_event_field(call, pred->field_name);
@@ -568,83 +795,42 @@ static int filter_add_pred(struct filter_parse_state *ps,
                 return -EINVAL;
         }
 
-        string_type = is_string_field(field->type);
-        if (string_type) {
-                if (string_type == FILTER_STATIC_STRING)
+        if (is_string_field(field)) {
+                filter_build_regex(pred);
+
+                if (field->filter_type == FILTER_STATIC_STRING) {
                         fn = filter_pred_string;
-                else
+                        pred->regex.field_len = field->size;
+                } else if (field->filter_type == FILTER_DYN_STRING)
                         fn = filter_pred_strloc;
-                pred->str_len = field->size;
-                if (pred->op == OP_NE)
-                        pred->not = 1;
-                return filter_add_pred_fn(ps, call, pred, fn);
+                else
+                        fn = filter_pred_pchar;
         } else {
                 if (field->is_signed)
-                        ret = strict_strtoll(pred->str_val, 0, &val);
+                        ret = strict_strtoll(pred->regex.pattern, 0, &val);
                 else
-                        ret = strict_strtoull(pred->str_val, 0, &val);
+                        ret = strict_strtoull(pred->regex.pattern, 0, &val);
                 if (ret) {
                         parse_error(ps, FILT_ERR_ILLEGAL_INTVAL, 0);
                         return -EINVAL;
                 }
                 pred->val = val;
-        }
 
-        fn = select_comparison_fn(pred->op, field->size, field->is_signed);
-        if (!fn) {
-                parse_error(ps, FILT_ERR_INVALID_OP, 0);
-                return -EINVAL;
+                fn = select_comparison_fn(pred->op, field->size,
+                                          field->is_signed);
+                if (!fn) {
+                        parse_error(ps, FILT_ERR_INVALID_OP, 0);
+                        return -EINVAL;
+                }
         }
 
         if (pred->op == OP_NE)
                 pred->not = 1;
 
-        return filter_add_pred_fn(ps, call, pred, fn);
-}
-
-static int filter_add_subsystem_pred(struct filter_parse_state *ps,
-                                     struct event_subsystem *system,
-                                     struct filter_pred *pred,
-                                     char *filter_string)
-{
-        struct event_filter *filter = system->filter;
-        struct ftrace_event_call *call;
-        int err = 0;
-
-        if (!filter->preds) {
-                filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred),
-                                        GFP_KERNEL);
-
-                if (!filter->preds)
-                        return -ENOMEM;
-        }
-
-        if (filter->n_preds == MAX_FILTER_PRED) {
-                parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
-                return -ENOSPC;
-        }
-
-        filter->preds[filter->n_preds] = pred;
-        filter->n_preds++;
-
-        list_for_each_entry(call, &ftrace_events, list) {
-
-                if (!call->define_fields)
-                        continue;
-
-                if (strcmp(call->system, system->name))
-                        continue;
-
-                err = filter_add_pred(ps, call, pred);
-                if (err) {
-                        filter_free_subsystem_preds(system);
-                        parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
-                        goto out;
-                }
-                replace_filter_string(call->filter, filter_string);
-        }
-out:
-        return err;
+add_pred_fn:
+        if (!dry_run)
+                return filter_add_pred_fn(ps, call, filter, pred, fn);
+        return 0;
 }
 
 static void parse_init(struct filter_parse_state *ps,
@@ -844,8 +1030,9 @@ static void postfix_clear(struct filter_parse_state *ps)
 
         while (!list_empty(&ps->postfix)) {
                 elt = list_first_entry(&ps->postfix, struct postfix_elt, list);
-                kfree(elt->operand);
                 list_del(&elt->list);
+                kfree(elt->operand);
+                kfree(elt);
         }
 }
 
@@ -955,8 +1142,8 @@ static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
                 return NULL;
         }
 
-        strcpy(pred->str_val, operand2);
-        pred->str_len = strlen(operand2);
+        strcpy(pred->regex.pattern, operand2);
+        pred->regex.len = strlen(pred->regex.pattern);
 
         pred->op = op;
 
@@ -1000,15 +1187,17 @@ static int check_preds(struct filter_parse_state *ps)
         return 0;
 }
 
-static int replace_preds(struct event_subsystem *system,
-                         struct ftrace_event_call *call,
+static int replace_preds(struct ftrace_event_call *call,
+                         struct event_filter *filter,
                          struct filter_parse_state *ps,
-                         char *filter_string)
+                         char *filter_string,
+                         bool dry_run)
 {
         char *operand1 = NULL, *operand2 = NULL;
         struct filter_pred *pred;
         struct postfix_elt *elt;
         int err;
+        int n_preds = 0;
 
         err = check_preds(ps);
         if (err)
@@ -1027,19 +1216,14 @@ static int replace_preds(struct event_subsystem *system,
                         continue;
                 }
 
+                if (n_preds++ == MAX_FILTER_PRED) {
+                        parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
+                        return -ENOSPC;
+                }
+
                 if (elt->op == OP_AND || elt->op == OP_OR) {
                         pred = create_logical_pred(elt->op);
-                        if (call) {
-                                err = filter_add_pred(ps, call, pred);
-                                filter_free_pred(pred);
-                        } else
-                                err = filter_add_subsystem_pred(ps, system,
-                                                        pred, filter_string);
-                        if (err)
-                                return err;
-
-                        operand1 = operand2 = NULL;
-                        continue;
+                        goto add_pred;
                 }
 
                 if (!operand1 || !operand2) {
@@ -1048,12 +1232,11 @@ static int replace_preds(struct event_subsystem *system,
                 }
 
                 pred = create_pred(elt->op, operand1, operand2);
-                if (call) {
-                        err = filter_add_pred(ps, call, pred);
-                        filter_free_pred(pred);
-                } else
-                        err = filter_add_subsystem_pred(ps, system, pred,
-                                                        filter_string);
+add_pred:
+                if (!pred)
+                        return -ENOMEM;
+                err = filter_add_pred(ps, call, filter, pred, dry_run);
+                filter_free_pred(pred);
                 if (err)
                         return err;
 
@@ -1063,19 +1246,59 @@ static int replace_preds(struct event_subsystem *system,
         return 0;
 }
 
-int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+static int replace_system_preds(struct event_subsystem *system,
+                                struct filter_parse_state *ps,
+                                char *filter_string)
 {
+        struct ftrace_event_call *call;
+        bool fail = true;
         int err;
 
+        list_for_each_entry(call, &ftrace_events, list) {
+                struct event_filter *filter = call->filter;
+
+                if (strcmp(call->class->system, system->name) != 0)
+                        continue;
+
+                /* try to see if the filter can be applied */
+                err = replace_preds(call, filter, ps, filter_string, true);
+                if (err)
+                        continue;
+
+                /* really apply the filter */
+                filter_disable_preds(call);
+                err = replace_preds(call, filter, ps, filter_string, false);
+                if (err)
+                        filter_disable_preds(call);
+                else {
+                        call->flags |= TRACE_EVENT_FL_FILTERED;
+                        replace_filter_string(filter, filter_string);
+                }
+                fail = false;
+        }
+
+        if (fail) {
+                parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
+                return -EINVAL;
+        }
+        return 0;
+}
+
+int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
+{
+        int err;
         struct filter_parse_state *ps;
 
         mutex_lock(&event_mutex);
 
+        err = init_preds(call);
+        if (err)
+                goto out_unlock;
+
         if (!strcmp(strstrip(filter_string), "0")) {
                 filter_disable_preds(call);
                 remove_filter_string(call->filter);
-                mutex_unlock(&event_mutex);
-                return 0;
+                goto out_unlock;
         }
 
         err = -ENOMEM;
@@ -1093,10 +1316,11 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
                 goto out;
         }
 
-        err = replace_preds(NULL, call, ps, filter_string);
+        err = replace_preds(call, call->filter, ps, filter_string, false);
         if (err)
                 append_filter_err(ps, call->filter);
-
+        else
+                call->flags |= TRACE_EVENT_FL_FILTERED;
 out:
         filter_opstack_clear(ps);
         postfix_clear(ps);
@@ -1111,16 +1335,18 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
                                  char *filter_string)
 {
         int err;
-
         struct filter_parse_state *ps;
 
         mutex_lock(&event_mutex);
 
+        err = init_subsystem_preds(system);
+        if (err)
+                goto out_unlock;
+
         if (!strcmp(strstrip(filter_string), "0")) {
                 filter_free_subsystem_preds(system);
                 remove_filter_string(system->filter);
-                mutex_unlock(&event_mutex);
-                return 0;
+                goto out_unlock;
         }
 
         err = -ENOMEM;
@@ -1128,7 +1354,6 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
         if (!ps)
                 goto out_unlock;
 
-        filter_free_subsystem_preds(system);
         replace_filter_string(system->filter, filter_string);
 
         parse_init(ps, filter_ops, filter_string);
@@ -1138,7 +1363,7 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
                 goto out;
         }
 
-        err = replace_preds(system, NULL, ps, filter_string);
+        err = replace_system_preds(system, ps, filter_string);
         if (err)
                 append_filter_err(ps, system->filter);
 
@@ -1152,3 +1377,73 @@ out_unlock:
         return err;
 }
 
+#ifdef CONFIG_PERF_EVENTS
+
+void ftrace_profile_free_filter(struct perf_event *event)
+{
+        struct event_filter *filter = event->filter;
+
+        event->filter = NULL;
+        __free_preds(filter);
+}
+
+int ftrace_profile_set_filter(struct perf_event *event, int event_id,
+                              char *filter_str)
+{
+        int err;
+        struct event_filter *filter;
+        struct filter_parse_state *ps;
+        struct ftrace_event_call *call = NULL;
+
+        mutex_lock(&event_mutex);
+
+        list_for_each_entry(call, &ftrace_events, list) {
+                if (call->event.type == event_id)
+                        break;
+        }
+
+        err = -EINVAL;
+        if (&call->list == &ftrace_events)
+                goto out_unlock;
+
+        err = -EEXIST;
+        if (event->filter)
+                goto out_unlock;
+
+        filter = __alloc_preds();
+        if (IS_ERR(filter)) {
+                err = PTR_ERR(filter);
+                goto out_unlock;
+        }
+
+        err = -ENOMEM;
+        ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+        if (!ps)
+                goto free_preds;
+
+        parse_init(ps, filter_ops, filter_str);
+        err = filter_parse(ps);
+        if (err)
+                goto free_ps;
+
+        err = replace_preds(call, filter, ps, filter_str, false);
+        if (!err)
+                event->filter = filter;
+
+free_ps:
+        filter_opstack_clear(ps);
+        postfix_clear(ps);
+        kfree(ps);
+
+free_preds:
+        if (err)
+                __free_preds(filter);
+
+out_unlock:
+        mutex_unlock(&event_mutex);
+
+        return err;
+}
+
+#endif /* CONFIG_PERF_EVENTS */
+
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d06cf898dc86..4b74d71705c0 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -15,192 +15,159 @@
 
 #include "trace_output.h"
 
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM    ftrace
 
-#undef TRACE_STRUCT
-#define TRACE_STRUCT(args...) args
-
-extern void __bad_type_size(void);
-
-#undef TRACE_FIELD
-#define TRACE_FIELD(type, item, assign)                                 \
-        if (sizeof(type) != sizeof(field.item))                         \
-                __bad_type_size();                                      \
-        ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"      \
-                               "offset:%u;\tsize:%u;\n",                \
-                               (unsigned int)offsetof(typeof(field), item), \
-                               (unsigned int)sizeof(field.item));       \
-        if (!ret)                                                       \
-                return 0;
-
-
-#undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd)                  \
-        ret = trace_seq_printf(s, "\tfield special:" #type_item ";\t"   \
-                               "offset:%u;\tsize:%u;\n",                \
-                               (unsigned int)offsetof(typeof(field), item), \
-                               (unsigned int)sizeof(field.item));       \
-        if (!ret)                                                       \
-                return 0;
-
-#undef TRACE_FIELD_ZERO_CHAR
-#define TRACE_FIELD_ZERO_CHAR(item)                                     \
-        ret = trace_seq_printf(s, "\tfield:char " #item ";\t"           \
-                               "offset:%u;\tsize:0;\n",                 \
-                               (unsigned int)offsetof(typeof(field), item)); \
-        if (!ret)                                                       \
-                return 0;
-
-#undef TRACE_FIELD_SIGN
-#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \
-        TRACE_FIELD(type, item, assign)
-
-#undef TP_RAW_FMT
-#define TP_RAW_FMT(args...) args
-
-#undef TRACE_EVENT_FORMAT
-#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)      \
-static int                                                              \
-ftrace_format_##call(struct trace_seq *s)                               \
-{                                                                       \
-        struct args field;                                              \
-        int ret;                                                        \
-                                                                        \
-        tstruct;                                                        \
-                                                                        \
-        trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt);            \
-                                                                        \
-        return ret;                                                     \
-}
+/* not needed for this file */
+#undef __field_struct
+#define __field_struct(type, item)
 
-#undef TRACE_EVENT_FORMAT_NOFILTER
-#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,    \
-                                    tpfmt)                              \
-static int                                                              \
-ftrace_format_##call(struct trace_seq *s)                               \
-{                                                                       \
-        struct args field;                                              \
-        int ret;                                                        \
-                                                                        \
-        tstruct;                                                        \
-                                                                        \
-        trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt);            \
-                                                                        \
-        return ret;                                                     \
-}
+#undef __field
+#define __field(type, item)                             type item;
 
-#include "trace_event_types.h"
+#undef __field_desc
+#define __field_desc(type, container, item)             type item;
 
-#undef TRACE_ZERO_CHAR
-#define TRACE_ZERO_CHAR(arg)
+#undef __array
+#define __array(type, item, size)                       type item[size];
 
-#undef TRACE_FIELD
-#define TRACE_FIELD(type, item, assign)\
-        entry->item = assign;
+#undef __array_desc
+#define __array_desc(type, container, item, size)       type item[size];
 
-#undef TRACE_FIELD
-#define TRACE_FIELD(type, item, assign)\
-        entry->item = assign;
+#undef __dynamic_array
+#define __dynamic_array(type, item)                     type item[];
 
-#undef TRACE_FIELD_SIGN
-#define TRACE_FIELD_SIGN(type, item, assign, is_signed) \
-        TRACE_FIELD(type, item, assign)
+#undef F_STRUCT
+#define F_STRUCT(args...)                               args
 
-#undef TP_CMD
-#define TP_CMD(cmd...)  cmd
+#undef F_printk
+#define F_printk(fmt, args...) fmt, args
 
-#undef TRACE_ENTRY
-#define TRACE_ENTRY     entry
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)     \
+struct ____ftrace_##name {                                      \
+        tstruct                                                 \
+};                                                              \
+static void __always_unused ____ftrace_check_##name(void)       \
+{                                                               \
+        struct ____ftrace_##name *__entry = NULL;               \
+                                                                \
+        /* force compile-time check on F_printk() */            \
+        printk(print);                                          \
+}
 
-#undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd)  \
-        cmd;
+#undef FTRACE_ENTRY_DUP
+#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \
+        FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
 
-#undef TRACE_EVENT_FORMAT
-#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)      \
-int ftrace_define_fields_##call(void);                                  \
-static int ftrace_raw_init_event_##call(void);                          \
-                                                                        \
-struct ftrace_event_call __used                                         \
-__attribute__((__aligned__(4)))                                         \
-__attribute__((section("_ftrace_events"))) event_##call = {             \
-        .name                   = #call,                                \
-        .id                     = proto,                                \
-        .system                 = __stringify(TRACE_SYSTEM),            \
-        .raw_init               = ftrace_raw_init_event_##call,         \
-        .show_format            = ftrace_format_##call,                 \
-        .define_fields          = ftrace_define_fields_##call,          \
-};                                                                      \
-static int ftrace_raw_init_event_##call(void)                           \
-{                                                                       \
-        INIT_LIST_HEAD(&event_##call.fields);                           \
-        init_preds(&event_##call);                                      \
-        return 0;                                                       \
-}                                                                       \
-
-#undef TRACE_EVENT_FORMAT_NOFILTER
-#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,    \
-                                    tpfmt)                              \
-                                                                        \
-struct ftrace_event_call __used                                         \
-__attribute__((__aligned__(4)))                                         \
-__attribute__((section("_ftrace_events"))) event_##call = {             \
-        .name                   = #call,                                \
-        .id                     = proto,                                \
-        .system                 = __stringify(TRACE_SYSTEM),            \
-        .show_format            = ftrace_format_##call,                 \
-};
+#include "trace_entries.h"
 
-#include "trace_event_types.h"
-
-#undef TRACE_FIELD
-#define TRACE_FIELD(type, item, assign)                                 \
+#undef __field
+#define __field(type, item)                                             \
         ret = trace_define_field(event_call, #type, #item,              \
                                  offsetof(typeof(field), item),         \
-                                 sizeof(field.item), is_signed_type(type));     \
+                                 sizeof(field.item),                    \
+                                 is_signed_type(type), FILTER_OTHER);   \
         if (ret)                                                        \
                 return ret;
 
-#undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type, item, len, cmd)                       \
-        ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+#undef __field_desc
+#define __field_desc(type, container, item)     \
+        ret = trace_define_field(event_call, #type, #item,              \
+                                 offsetof(typeof(field),                \
+                                          container.item),              \
+                                 sizeof(field.container.item),          \
+                                 is_signed_type(type), FILTER_OTHER);   \
+        if (ret)                                                        \
+                return ret;
+
+#undef __array
+#define __array(type, item, len)                                        \
+        do {                                                            \
+                BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);                 \
+                mutex_lock(&event_storage_mutex);                       \
+                snprintf(event_storage, sizeof(event_storage),          \
+                         "%s[%d]", #type, len);                         \
+                ret = trace_define_field(event_call, event_storage, #item, \
                                  offsetof(typeof(field), item),         \
-                                 sizeof(field.item), 0);                \
+                                 sizeof(field.item),                    \
+                                 is_signed_type(type), FILTER_OTHER);   \
+                mutex_unlock(&event_storage_mutex);                     \
+                if (ret)                                                \
+                        return ret;                                     \
+        } while (0);
+
+#undef __array_desc
+#define __array_desc(type, container, item, len)                        \
+        BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);                         \
+        ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+                                 offsetof(typeof(field),                \
+                                          container.item),              \
+                                 sizeof(field.container.item),          \
+                                 is_signed_type(type), FILTER_OTHER);   \
         if (ret)                                                        \
                 return ret;
 
-#undef TRACE_FIELD_SIGN
-#define TRACE_FIELD_SIGN(type, item, assign, is_signed)                 \
+#undef __dynamic_array
+#define __dynamic_array(type, item)                                     \
         ret = trace_define_field(event_call, #type, #item,              \
                                  offsetof(typeof(field), item),         \
-                                 sizeof(field.item), is_signed);        \
+                                 0, is_signed_type(type), FILTER_OTHER);\
         if (ret)                                                        \
                 return ret;
 
-#undef TRACE_FIELD_ZERO_CHAR
-#define TRACE_FIELD_ZERO_CHAR(item)
-
-#undef TRACE_EVENT_FORMAT
-#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt)      \
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)             \
 int                                                                     \
-ftrace_define_fields_##call(void)                                       \
+ftrace_define_fields_##name(struct ftrace_event_call *event_call)       \
 {                                                                       \
-        struct ftrace_event_call *event_call = &event_##call;           \
-        struct args field;                                              \
+        struct struct_name field;                                       \
         int ret;                                                        \
                                                                         \
-        __common_field(unsigned char, type, 0);                         \
-        __common_field(unsigned char, flags, 0);                        \
-        __common_field(unsigned char, preempt_count, 0);                \
-        __common_field(int, pid, 1);                                    \
-        __common_field(int, tgid, 1);                                   \
-                                                                        \
         tstruct;                                                        \
                                                                         \
         return ret;                                                     \
 }
 
-#undef TRACE_EVENT_FORMAT_NOFILTER
-#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct,    \
-                                    tpfmt)
+#include "trace_entries.h"
+
+#undef __entry
+#define __entry REC
+
+#undef __field
+#define __field(type, item)
+
+#undef __field_desc
+#define __field_desc(type, container, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __array_desc
+#define __array_desc(type, container, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item)
+
+#undef F_printk
+#define F_printk(fmt, args...) #fmt ", "  __stringify(args)
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print)          \
+                                                                        \
+struct ftrace_event_class event_class_ftrace_##call = {                 \
+        .system                 = __stringify(TRACE_SYSTEM),            \
+        .define_fields          = ftrace_define_fields_##call,          \
+        .fields                 = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
+};                                                                      \
+                                                                        \
+struct ftrace_event_call __used                                         \
+__attribute__((__aligned__(4)))                                         \
+__attribute__((section("_ftrace_events"))) event_##call = {             \
+        .name                   = #call,                                \
+        .event.type             = etype,                                \
+        .class                  = &event_class_ftrace_##call,           \
+        .print_fmt              = print,                                \
+};                                                                      \
 
-#include "trace_event_types.h"
+#include "trace_entries.h"
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 90f134764837..16aee4d44e8f 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -54,14 +54,14 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
         struct trace_array_cpu *data;
         unsigned long flags;
         long disabled;
-        int cpu, resched;
+        int cpu;
         int pc;
 
         if (unlikely(!ftrace_function_enabled))
                 return;
 
         pc = preempt_count();
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
         local_save_flags(flags);
         cpu = raw_smp_processor_id();
         data = tr->data[cpu];
@@ -71,7 +71,7 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
                 trace_function(tr, ip, parent_ip, flags, pc);
 
         atomic_dec(&data->disabled);
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 }
 
 static void
@@ -288,11 +288,9 @@ static int
 ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
                          struct ftrace_probe_ops *ops, void *data)
 {
-        char str[KSYM_SYMBOL_LEN];
         long count = (long)data;
 
-        kallsyms_lookup(ip, NULL, NULL, NULL, str);
-        seq_printf(m, "%s:", str);
+        seq_printf(m, "%ps:", (void *)ip);
 
         if (ops == &traceon_probe_ops)
                 seq_printf(m, "traceon");
@@ -302,8 +300,7 @@ ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
         if (count == -1)
                 seq_printf(m, ":unlimited\n");
         else
-                seq_printf(m, ":count=%ld", count);
-        seq_putc(m, '\n');
+                seq_printf(m, ":count=%ld\n", count);
 
         return 0;
 }
@@ -364,7 +361,7 @@ ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable)
  out_reg:
         ret = register_ftrace_function_probe(glob, ops, count);
 
-        return ret;
+        return ret < 0 ? ret : 0;
 }
 
 static struct ftrace_func_command ftrace_traceon_cmd = {
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index d2249abafb53..76b05980225c 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -9,14 +9,31 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
+#include <linux/slab.h>
 #include <linux/fs.h>
 
 #include "trace.h"
 #include "trace_output.h"
 
-struct fgraph_data {
+/* When set, irq functions will be ignored */
+static int ftrace_graph_skip_irqs;
+
+struct fgraph_cpu_data {
         pid_t           last_pid;
         int             depth;
+        int             depth_irq;
+        int             ignore;
+        unsigned long   enter_funcs[FTRACE_RETFUNC_DEPTH];
+};
+
+struct fgraph_data {
+        struct fgraph_cpu_data __percpu *cpu_data;
+
+        /* Place to preserve last processed entry. */
+        struct ftrace_graph_ent_entry   ent;
+        struct ftrace_graph_ret_entry   ret;
+        int                             failed;
+        int                             cpu;
 };
 
 #define TRACE_GRAPH_INDENT      2
@@ -27,7 +44,8 @@ struct fgraph_data {
 #define TRACE_GRAPH_PRINT_OVERHEAD      0x4
 #define TRACE_GRAPH_PRINT_PROC          0x8
 #define TRACE_GRAPH_PRINT_DURATION      0x10
-#define TRACE_GRAPH_PRINT_ABS_TIME      0X20
+#define TRACE_GRAPH_PRINT_ABS_TIME      0x20
+#define TRACE_GRAPH_PRINT_IRQS          0x40
 
 static struct tracer_opt trace_opts[] = {
         /* Display overruns? (for self-debug purpose) */
@@ -42,17 +60,19 @@ static struct tracer_opt trace_opts[] = {
         { TRACER_OPT(funcgraph-duration, TRACE_GRAPH_PRINT_DURATION) },
         /* Display absolute time of an entry */
         { TRACER_OPT(funcgraph-abstime, TRACE_GRAPH_PRINT_ABS_TIME) },
+        /* Display interrupts */
+        { TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) },
         { } /* Empty entry */
 };
 
 static struct tracer_flags tracer_flags = {
         /* Don't display overruns and proc by default */
         .val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD |
-               TRACE_GRAPH_PRINT_DURATION,
+               TRACE_GRAPH_PRINT_DURATION | TRACE_GRAPH_PRINT_IRQS,
         .opts = trace_opts
 };
 
-/* pid on the last trace processed */
+static struct trace_array *graph_array;
 
 
 /* Add a function return address to the trace stack on thread info.*/
@@ -124,7 +144,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
         if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
                 ftrace_graph_stop();
                 WARN(1, "Bad frame pointer: expected %lx, received %lx\n"
-                     "  from func %pF return to %lx\n",
+                     "  from func %ps return to %lx\n",
                      current->ret_stack[index].fp,
                      frame_pointer,
                      (void *)current->ret_stack[index].func,
@@ -166,10 +186,183 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
         return ret;
 }
 
+int __trace_graph_entry(struct trace_array *tr,
+                                struct ftrace_graph_ent *trace,
+                                unsigned long flags,
+                                int pc)
+{
+        struct ftrace_event_call *call = &event_funcgraph_entry;
+        struct ring_buffer_event *event;
+        struct ring_buffer *buffer = tr->buffer;
+        struct ftrace_graph_ent_entry *entry;
+
+        if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
+                return 0;
+
+        event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
+                                          sizeof(*entry), flags, pc);
+        if (!event)
+                return 0;
+        entry   = ring_buffer_event_data(event);
+        entry->graph_ent                        = *trace;
+        if (!filter_current_check_discard(buffer, call, entry, event))
+                ring_buffer_unlock_commit(buffer, event);
+
+        return 1;
+}
+
+static inline int ftrace_graph_ignore_irqs(void)
+{
+        if (!ftrace_graph_skip_irqs)
+                return 0;
+
+        return in_irq();
+}
+
+int trace_graph_entry(struct ftrace_graph_ent *trace)
+{
+        struct trace_array *tr = graph_array;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        long disabled;
+        int ret;
+        int cpu;
+        int pc;
+
+        if (!ftrace_trace_task(current))
+                return 0;
+
+        /* trace it when it is-nested-in or is a function enabled. */
+        if (!(trace->depth || ftrace_graph_addr(trace->func)) ||
+              ftrace_graph_ignore_irqs())
+                return 0;
+
+        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();
+                ret = __trace_graph_entry(tr, trace, flags, pc);
+        } else {
+                ret = 0;
+        }
+
+        atomic_dec(&data->disabled);
+        local_irq_restore(flags);
+
+        return ret;
+}
+
+int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
+{
+        if (tracing_thresh)
+                return 1;
+        else
+                return trace_graph_entry(trace);
+}
+
+static void
+__trace_graph_function(struct trace_array *tr,
+                unsigned long ip, unsigned long flags, int pc)
+{
+        u64 time = trace_clock_local();
+        struct ftrace_graph_ent ent = {
+                .func  = ip,
+                .depth = 0,
+        };
+        struct ftrace_graph_ret ret = {
+                .func     = ip,
+                .depth    = 0,
+                .calltime = time,
+                .rettime  = time,
+        };
+
+        __trace_graph_entry(tr, &ent, flags, pc);
+        __trace_graph_return(tr, &ret, flags, pc);
+}
+
+void
+trace_graph_function(struct trace_array *tr,
+                unsigned long ip, unsigned long parent_ip,
+                unsigned long flags, int pc)
+{
+        __trace_graph_function(tr, ip, flags, pc);
+}
+
+void __trace_graph_return(struct trace_array *tr,
+                                struct ftrace_graph_ret *trace,
+                                unsigned long flags,
+                                int pc)
+{
+        struct ftrace_event_call *call = &event_funcgraph_exit;
+        struct ring_buffer_event *event;
+        struct ring_buffer *buffer = tr->buffer;
+        struct ftrace_graph_ret_entry *entry;
+
+        if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
+                return;
+
+        event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
+                                          sizeof(*entry), flags, pc);
+        if (!event)
+                return;
+        entry   = ring_buffer_event_data(event);
+        entry->ret                              = *trace;
+        if (!filter_current_check_discard(buffer, call, entry, event))
+                ring_buffer_unlock_commit(buffer, event);
+}
+
+void trace_graph_return(struct ftrace_graph_ret *trace)
+{
+        struct trace_array *tr = graph_array;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        long disabled;
+        int cpu;
+        int pc;
+
+        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_graph_return(tr, trace, flags, pc);
+        }
+        atomic_dec(&data->disabled);
+        local_irq_restore(flags);
+}
+
+void set_graph_array(struct trace_array *tr)
+{
+        graph_array = tr;
+
+        /* Make graph_array visible before we start tracing */
+
+        smp_mb();
+}
+
+void trace_graph_thresh_return(struct ftrace_graph_ret *trace)
+{
+        if (tracing_thresh &&
+            (trace->rettime - trace->calltime < tracing_thresh))
+                return;
+        else
+                trace_graph_return(trace);
+}
+
 static int graph_trace_init(struct trace_array *tr)
 {
-        int ret = register_ftrace_graph(&trace_graph_return,
-                                        &trace_graph_entry);
+        int ret;
+
+        set_graph_array(tr);
+        if (tracing_thresh)
+                ret = register_ftrace_graph(&trace_graph_thresh_return,
+                                            &trace_graph_thresh_entry);
+        else
+                ret = register_ftrace_graph(&trace_graph_return,
+                                            &trace_graph_entry);
         if (ret)
                 return ret;
         tracing_start_cmdline_record();
@@ -183,43 +376,19 @@ static void graph_trace_reset(struct trace_array *tr)
         unregister_ftrace_graph();
 }
 
-static inline int log10_cpu(int nb)
-{
-        if (nb / 100)
-                return 3;
-        if (nb / 10)
-                return 2;
-        return 1;
-}
+static int max_bytes_for_cpu;
 
 static enum print_line_t
 print_graph_cpu(struct trace_seq *s, int cpu)
 {
-        int i;
         int ret;
-        int log10_this = log10_cpu(cpu);
-        int log10_all = log10_cpu(cpumask_weight(cpu_online_mask));
-
 
         /*
          * Start with a space character - to make it stand out
          * to the right a bit when trace output is pasted into
          * email:
          */
-        ret = trace_seq_printf(s, " ");
-
-        /*
-         * Tricky - we space the CPU field according to the max
-         * number of online CPUs. On a 2-cpu system it would take
-         * a maximum of 1 digit - on a 128 cpu system it would
-         * take up to 3 digits:
-         */
-        for (i = 0; i < log10_all - log10_this; i++) {
-                ret = trace_seq_printf(s, " ");
-                if (!ret)
-                        return TRACE_TYPE_PARTIAL_LINE;
-        }
-        ret = trace_seq_printf(s, "%d) ", cpu);
+        ret = trace_seq_printf(s, " %*d) ", max_bytes_for_cpu, cpu);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
@@ -270,6 +439,15 @@ print_graph_proc(struct trace_seq *s, pid_t pid)
 }
 
 
+static enum print_line_t
+print_graph_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
+{
+        if (!trace_seq_putc(s, ' '))
+                return 0;
+
+        return trace_print_lat_fmt(s, entry);
+}
+
 /* If the pid changed since the last trace, output this event */
 static enum print_line_t
 verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data)
@@ -281,7 +459,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data)
         if (!data)
                 return TRACE_TYPE_HANDLED;
 
-        last_pid = &(per_cpu_ptr(data, cpu)->last_pid);
+        last_pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
 
         if (*last_pid == pid)
                 return TRACE_TYPE_HANDLED;
@@ -332,27 +510,59 @@ static struct ftrace_graph_ret_entry *
 get_return_for_leaf(struct trace_iterator *iter,
                 struct ftrace_graph_ent_entry *curr)
 {
-        struct ring_buffer_iter *ring_iter;
+        struct fgraph_data *data = iter->private;
+        struct ring_buffer_iter *ring_iter = NULL;
         struct ring_buffer_event *event;
         struct ftrace_graph_ret_entry *next;
 
-        ring_iter = iter->buffer_iter[iter->cpu];
+        /*
+         * If the previous output failed to write to the seq buffer,
+         * then we just reuse the data from before.
+         */
+        if (data && data->failed) {
+                curr = &data->ent;
+                next = &data->ret;
+        } else {
+
+                ring_iter = iter->buffer_iter[iter->cpu];
+
+                /* First peek to compare current entry and the next one */
+                if (ring_iter)
+                        event = ring_buffer_iter_peek(ring_iter, NULL);
+                else {
+                        /*
+                         * We need to consume the current entry to see
+                         * the next one.
+                         */
+                        ring_buffer_consume(iter->tr->buffer, iter->cpu,
+                                            NULL, NULL);
+                        event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
+                                                 NULL, NULL);
+                }
 
-        /* First peek to compare current entry and the next one */
-        if (ring_iter)
-                event = ring_buffer_iter_peek(ring_iter, NULL);
-        else {
-        /* We need to consume the current entry to see the next one */
-                ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
-                event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
-                                        NULL);
+                if (!event)
+                        return NULL;
+
+                next = ring_buffer_event_data(event);
+
+                if (data) {
+                        /*
+                         * Save current and next entries for later reference
+                         * if the output fails.
+                         */
+                        data->ent = *curr;
+                        /*
+                         * If the next event is not a return type, then
+                         * we only care about what type it is. Otherwise we can
+                         * safely copy the entire event.
+                         */
+                        if (next->ent.type == TRACE_GRAPH_RET)
+                                data->ret = *next;
+                        else
+                                data->ret.ent.type = next->ent.type;
+                }
         }
 
-        if (!event)
-                return NULL;
-
-        next = ring_buffer_event_data(event);
-
         if (next->ent.type != TRACE_GRAPH_RET)
                 return NULL;
 
@@ -369,17 +579,18 @@ get_return_for_leaf(struct trace_iterator *iter,
 
 /* Signal a overhead of time execution to the output */
 static int
-print_graph_overhead(unsigned long long duration, struct trace_seq *s)
+print_graph_overhead(unsigned long long duration, struct trace_seq *s,
+                     u32 flags)
 {
         /* If duration disappear, we don't need anything */
-        if (!(tracer_flags.val & TRACE_GRAPH_PRINT_DURATION))
+        if (!(flags & TRACE_GRAPH_PRINT_DURATION))
                 return 1;
 
         /* Non nested entry or return */
         if (duration == -1)
                 return trace_seq_printf(s, "  ");
 
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+        if (flags & TRACE_GRAPH_PRINT_OVERHEAD) {
                 /* Duration exceeded 100 msecs */
                 if (duration > 100000ULL)
                         return trace_seq_printf(s, "! ");
@@ -405,7 +616,7 @@ static int print_graph_abs_time(u64 t, struct trace_seq *s)
 
 static enum print_line_t
 print_graph_irq(struct trace_iterator *iter, unsigned long addr,
-                enum trace_type type, int cpu, pid_t pid)
+                enum trace_type type, int cpu, pid_t pid, u32 flags)
 {
         int ret;
         struct trace_seq *s = &iter->seq;
@@ -415,20 +626,21 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
                 return TRACE_TYPE_UNHANDLED;
 
         /* Absolute time */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
+        if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
                 ret = print_graph_abs_time(iter->ts, s);
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
         /* Cpu */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+        if (flags & TRACE_GRAPH_PRINT_CPU) {
                 ret = print_graph_cpu(s, cpu);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
+
         /* Proc */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+        if (flags & TRACE_GRAPH_PRINT_PROC) {
                 ret = print_graph_proc(s, pid);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -438,7 +650,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
         }
 
         /* No overhead */
-        ret = print_graph_overhead(-1, s);
+        ret = print_graph_overhead(-1, s, flags);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
@@ -451,7 +663,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* Don't close the duration column if haven't one */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+        if (flags & TRACE_GRAPH_PRINT_DURATION)
                 trace_seq_printf(s, " |");
         ret = trace_seq_printf(s, "\n");
 
@@ -481,7 +693,9 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
 
         /* Print nsecs (we don't want to exceed 7 numbers) */
         if (len < 7) {
-                snprintf(nsecs_str, 8 - len, "%03lu", nsecs_rem);
+                size_t slen = min_t(size_t, sizeof(nsecs_str), 8UL - len);
+
+                snprintf(nsecs_str, slen, "%03lu", nsecs_rem);
                 ret = trace_seq_printf(s, ".%s", nsecs_str);
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -521,7 +735,8 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s)
 static enum print_line_t
 print_graph_entry_leaf(struct trace_iterator *iter,
                 struct ftrace_graph_ent_entry *entry,
-                struct ftrace_graph_ret_entry *ret_entry, struct trace_seq *s)
+                struct ftrace_graph_ret_entry *ret_entry,
+                struct trace_seq *s, u32 flags)
 {
         struct fgraph_data *data = iter->private;
         struct ftrace_graph_ret *graph_ret;
@@ -535,24 +750,30 @@ print_graph_entry_leaf(struct trace_iterator *iter,
         duration = graph_ret->rettime - graph_ret->calltime;
 
         if (data) {
+                struct fgraph_cpu_data *cpu_data;
                 int cpu = iter->cpu;
-                int *depth = &(per_cpu_ptr(data, cpu)->depth);
+
+                cpu_data = per_cpu_ptr(data->cpu_data, cpu);
 
                 /*
                  * Comments display at + 1 to depth. Since
                  * this is a leaf function, keep the comments
                  * equal to this depth.
                  */
-                *depth = call->depth - 1;
+                cpu_data->depth = call->depth - 1;
+
+                /* No need to keep this function around for this depth */
+                if (call->depth < FTRACE_RETFUNC_DEPTH)
+                        cpu_data->enter_funcs[call->depth] = 0;
         }
 
         /* Overhead */
-        ret = print_graph_overhead(duration, s);
+        ret = print_graph_overhead(duration, s, flags);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* Duration */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+        if (flags & TRACE_GRAPH_PRINT_DURATION) {
                 ret = print_graph_duration(duration, s);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -565,11 +786,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
-        ret = seq_print_ip_sym(s, call->func, 0);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        ret = trace_seq_printf(s, "();\n");
+        ret = trace_seq_printf(s, "%ps();\n", (void *)call->func);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
@@ -579,7 +796,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 static enum print_line_t
 print_graph_entry_nested(struct trace_iterator *iter,
                          struct ftrace_graph_ent_entry *entry,
-                         struct trace_seq *s, int cpu)
+                         struct trace_seq *s, int cpu, u32 flags)
 {
         struct ftrace_graph_ent *call = &entry->graph_ent;
         struct fgraph_data *data = iter->private;
@@ -587,19 +804,24 @@ print_graph_entry_nested(struct trace_iterator *iter,
         int i;
 
         if (data) {
+                struct fgraph_cpu_data *cpu_data;
                 int cpu = iter->cpu;
-                int *depth = &(per_cpu_ptr(data, cpu)->depth);
 
-                *depth = call->depth;
+                cpu_data = per_cpu_ptr(data->cpu_data, cpu);
+                cpu_data->depth = call->depth;
+
+                /* Save this function pointer to see if the exit matches */
+                if (call->depth < FTRACE_RETFUNC_DEPTH)
+                        cpu_data->enter_funcs[call->depth] = call->func;
         }
 
         /* No overhead */
-        ret = print_graph_overhead(-1, s);
+        ret = print_graph_overhead(-1, s, flags);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* No time */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+        if (flags & TRACE_GRAPH_PRINT_DURATION) {
                 ret = trace_seq_printf(s, "            |  ");
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -612,11 +834,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
-        ret = seq_print_ip_sym(s, call->func, 0);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        ret = trace_seq_printf(s, "() {\n");
+        ret = trace_seq_printf(s, "%ps() {\n", (void *)call->func);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
@@ -629,7 +847,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
 
 static enum print_line_t
 print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
-                     int type, unsigned long addr)
+                     int type, unsigned long addr, u32 flags)
 {
         struct fgraph_data *data = iter->private;
         struct trace_entry *ent = iter->ent;
@@ -642,27 +860,27 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 
         if (type) {
                 /* Interrupt */
-                ret = print_graph_irq(iter, addr, type, cpu, ent->pid);
+                ret = print_graph_irq(iter, addr, type, cpu, ent->pid, flags);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
         /* Absolute time */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
+        if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
                 ret = print_graph_abs_time(iter->ts, s);
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
         /* Cpu */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+        if (flags & TRACE_GRAPH_PRINT_CPU) {
                 ret = print_graph_cpu(s, cpu);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
         /* Proc */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+        if (flags & TRACE_GRAPH_PRINT_PROC) {
                 ret = print_graph_proc(s, ent->pid);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -672,61 +890,201 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
+        /* Latency format */
+        if (trace_flags & TRACE_ITER_LATENCY_FMT) {
+                ret = print_graph_lat_fmt(s, ent);
+                if (ret == TRACE_TYPE_PARTIAL_LINE)
+                        return TRACE_TYPE_PARTIAL_LINE;
+        }
+
         return 0;
 }
 
+/*
+ * Entry check for irq code
+ *
+ * returns 1 if
+ *  - we are inside irq code
+ *  - we just extered irq code
+ *
+ * retunns 0 if
+ *  - funcgraph-interrupts option is set
+ *  - we are not inside irq code
+ */
+static int
+check_irq_entry(struct trace_iterator *iter, u32 flags,
+                unsigned long addr, int depth)
+{
+        int cpu = iter->cpu;
+        int *depth_irq;
+        struct fgraph_data *data = iter->private;
+
+        /*
+         * If we are either displaying irqs, or we got called as
+         * a graph event and private data does not exist,
+         * then we bypass the irq check.
+         */
+        if ((flags & TRACE_GRAPH_PRINT_IRQS) ||
+            (!data))
+                return 0;
+
+        depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
+
+        /*
+         * We are inside the irq code
+         */
+        if (*depth_irq >= 0)
+                return 1;
+
+        if ((addr < (unsigned long)__irqentry_text_start) ||
+            (addr >= (unsigned long)__irqentry_text_end))
+                return 0;
+
+        /*
+         * We are entering irq code.
+         */
+        *depth_irq = depth;
+        return 1;
+}
+
+/*
+ * Return check for irq code
+ *
+ * returns 1 if
+ *  - we are inside irq code
+ *  - we just left irq code
+ *
+ * returns 0 if
+ *  - funcgraph-interrupts option is set
+ *  - we are not inside irq code
+ */
+static int
+check_irq_return(struct trace_iterator *iter, u32 flags, int depth)
+{
+        int cpu = iter->cpu;
+        int *depth_irq;
+        struct fgraph_data *data = iter->private;
+
+        /*
+         * If we are either displaying irqs, or we got called as
+         * a graph event and private data does not exist,
+         * then we bypass the irq check.
+         */
+        if ((flags & TRACE_GRAPH_PRINT_IRQS) ||
+            (!data))
+                return 0;
+
+        depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
+
+        /*
+         * We are not inside the irq code.
+         */
+        if (*depth_irq == -1)
+                return 0;
+
+        /*
+         * We are inside the irq code, and this is returning entry.
+         * Let's not trace it and clear the entry depth, since
+         * we are out of irq code.
+         *
+         * This condition ensures that we 'leave the irq code' once
+         * we are out of the entry depth. Thus protecting us from
+         * the RETURN entry loss.
+         */
+        if (*depth_irq >= depth) {
+                *depth_irq = -1;
+                return 1;
+        }
+
+        /*
+         * We are inside the irq code, and this is not the entry.
+         */
+        return 1;
+}
+
 static enum print_line_t
 print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
-                        struct trace_iterator *iter)
+                        struct trace_iterator *iter, u32 flags)
 {
-        int cpu = iter->cpu;
+        struct fgraph_data *data = iter->private;
         struct ftrace_graph_ent *call = &field->graph_ent;
         struct ftrace_graph_ret_entry *leaf_ret;
+        static enum print_line_t ret;
+        int cpu = iter->cpu;
+
+        if (check_irq_entry(iter, flags, call->func, call->depth))
+                return TRACE_TYPE_HANDLED;
 
-        if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func))
+        if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func, flags))
                 return TRACE_TYPE_PARTIAL_LINE;
 
         leaf_ret = get_return_for_leaf(iter, field);
         if (leaf_ret)
-                return print_graph_entry_leaf(iter, field, leaf_ret, s);
+                ret = print_graph_entry_leaf(iter, field, leaf_ret, s, flags);
         else
-                return print_graph_entry_nested(iter, field, s, cpu);
+                ret = print_graph_entry_nested(iter, field, s, cpu, flags);
+
+        if (data) {
+                /*
+                 * If we failed to write our output, then we need to make
+                 * note of it. Because we already consumed our entry.
+                 */
+                if (s->full) {
+                        data->failed = 1;
+                        data->cpu = cpu;
+                } else
+                        data->failed = 0;
+        }
 
+        return ret;
 }
 
 static enum print_line_t
 print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
-                   struct trace_entry *ent, struct trace_iterator *iter)
+                   struct trace_entry *ent, struct trace_iterator *iter,
+                   u32 flags)
 {
         unsigned long long duration = trace->rettime - trace->calltime;
         struct fgraph_data *data = iter->private;
         pid_t pid = ent->pid;
         int cpu = iter->cpu;
+        int func_match = 1;
         int ret;
         int i;
 
+        if (check_irq_return(iter, flags, trace->depth))
+                return TRACE_TYPE_HANDLED;
+
         if (data) {
+                struct fgraph_cpu_data *cpu_data;
                 int cpu = iter->cpu;
-                int *depth = &(per_cpu_ptr(data, cpu)->depth);
+
+                cpu_data = per_cpu_ptr(data->cpu_data, cpu);
 
                 /*
                  * Comments display at + 1 to depth. This is the
                  * return from a function, we now want the comments
                  * to display at the same level of the bracket.
                  */
-                *depth = trace->depth - 1;
+                cpu_data->depth = trace->depth - 1;
+
+                if (trace->depth < FTRACE_RETFUNC_DEPTH) {
+                        if (cpu_data->enter_funcs[trace->depth] != trace->func)
+                                func_match = 0;
+                        cpu_data->enter_funcs[trace->depth] = 0;
+                }
         }
 
-        if (print_graph_prologue(iter, s, 0, 0))
+        if (print_graph_prologue(iter, s, 0, 0, flags))
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* Overhead */
-        ret = print_graph_overhead(duration, s);
+        ret = print_graph_overhead(duration, s, flags);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* Duration */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+        if (flags & TRACE_GRAPH_PRINT_DURATION) {
                 ret = print_graph_duration(duration, s);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -739,19 +1097,32 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
-        ret = trace_seq_printf(s, "}\n");
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
+        /*
+         * If the return function does not have a matching entry,
+         * then the entry was lost. Instead of just printing
+         * the '}' and letting the user guess what function this
+         * belongs to, write out the function name.
+         */
+        if (func_match) {
+                ret = trace_seq_printf(s, "}\n");
+                if (!ret)
+                        return TRACE_TYPE_PARTIAL_LINE;
+        } else {
+                ret = trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
+                if (!ret)
+                        return TRACE_TYPE_PARTIAL_LINE;
+        }
 
         /* Overrun */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERRUN) {
+        if (flags & TRACE_GRAPH_PRINT_OVERRUN) {
                 ret = trace_seq_printf(s, " (Overruns: %lu)\n",
                                         trace->overrun);
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
-        ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET, cpu, pid);
+        ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET,
+                              cpu, pid, flags);
         if (ret == TRACE_TYPE_PARTIAL_LINE)
                 return TRACE_TYPE_PARTIAL_LINE;
 
@@ -759,8 +1130,8 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 }
 
 static enum print_line_t
-print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
-                    struct trace_iterator *iter)
+print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
+                    struct trace_iterator *iter, u32 flags)
 {
         unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
         struct fgraph_data *data = iter->private;
@@ -770,18 +1141,18 @@ print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
         int i;
 
         if (data)
-                depth = per_cpu_ptr(data, iter->cpu)->depth;
+                depth = per_cpu_ptr(data->cpu_data, iter->cpu)->depth;
 
-        if (print_graph_prologue(iter, s, 0, 0))
+        if (print_graph_prologue(iter, s, 0, 0, flags))
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* No overhead */
-        ret = print_graph_overhead(-1, s);
+        ret = print_graph_overhead(-1, s, flags);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* No time */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+        if (flags & TRACE_GRAPH_PRINT_DURATION) {
                 ret = trace_seq_printf(s, "            |  ");
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -816,7 +1187,7 @@ print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
                 if (!event)
                         return TRACE_TYPE_UNHANDLED;
 
-                ret = event->trace(iter, sym_flags);
+                ret = event->funcs->trace(iter, sym_flags, event);
                 if (ret != TRACE_TYPE_HANDLED)
                         return ret;
         }
@@ -836,90 +1207,253 @@ print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
 
 
 enum print_line_t
-print_graph_function(struct trace_iterator *iter)
+__print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 {
+        struct ftrace_graph_ent_entry *field;
+        struct fgraph_data *data = iter->private;
         struct trace_entry *entry = iter->ent;
         struct trace_seq *s = &iter->seq;
+        int cpu = iter->cpu;
+        int ret;
+
+        if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) {
+                per_cpu_ptr(data->cpu_data, cpu)->ignore = 0;
+                return TRACE_TYPE_HANDLED;
+        }
+
+        /*
+         * If the last output failed, there's a possibility we need
+         * to print out the missing entry which would never go out.
+         */
+        if (data && data->failed) {
+                field = &data->ent;
+                iter->cpu = data->cpu;
+                ret = print_graph_entry(field, s, iter, flags);
+                if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) {
+                        per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1;
+                        ret = TRACE_TYPE_NO_CONSUME;
+                }
+                iter->cpu = cpu;
+                return ret;
+        }
 
         switch (entry->type) {
         case TRACE_GRAPH_ENT: {
-                struct ftrace_graph_ent_entry *field;
+                /*
+                 * print_graph_entry() may consume the current event,
+                 * thus @field may become invalid, so we need to save it.
+                 * sizeof(struct ftrace_graph_ent_entry) is very small,
+                 * it can be safely saved at the stack.
+                 */
+                struct ftrace_graph_ent_entry saved;
                 trace_assign_type(field, entry);
-                return print_graph_entry(field, s, iter);
+                saved = *field;
+                return print_graph_entry(&saved, s, iter, flags);
         }
         case TRACE_GRAPH_RET: {
                 struct ftrace_graph_ret_entry *field;
                 trace_assign_type(field, entry);
-                return print_graph_return(&field->ret, s, entry, iter);
+                return print_graph_return(&field->ret, s, entry, iter, flags);
         }
+        case TRACE_STACK:
+        case TRACE_FN:
+                /* dont trace stack and functions as comments */
+                return TRACE_TYPE_UNHANDLED;
+
         default:
-                return print_graph_comment(s, entry, iter);
+                return print_graph_comment(s, entry, iter, flags);
         }
 
         return TRACE_TYPE_HANDLED;
 }
 
-static void print_graph_headers(struct seq_file *s)
+static enum print_line_t
+print_graph_function(struct trace_iterator *iter)
+{
+        return __print_graph_function_flags(iter, tracer_flags.val);
+}
+
+enum print_line_t print_graph_function_flags(struct trace_iterator *iter,
+                                             u32 flags)
+{
+        if (trace_flags & TRACE_ITER_LATENCY_FMT)
+                flags |= TRACE_GRAPH_PRINT_DURATION;
+        else
+                flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+        return __print_graph_function_flags(iter, flags);
+}
+
+static enum print_line_t
+print_graph_function_event(struct trace_iterator *iter, int flags,
+                           struct trace_event *event)
+{
+        return print_graph_function(iter);
+}
+
+static void print_lat_header(struct seq_file *s, u32 flags)
+{
+        static const char spaces[] = "                " /* 16 spaces */
+                "    "                                  /* 4 spaces */
+                "                 ";                    /* 17 spaces */
+        int size = 0;
+
+        if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
+                size += 16;
+        if (flags & TRACE_GRAPH_PRINT_CPU)
+                size += 4;
+        if (flags & TRACE_GRAPH_PRINT_PROC)
+                size += 17;
+
+        seq_printf(s, "#%.*s  _-----=> irqs-off        \n", size, spaces);
+        seq_printf(s, "#%.*s / _----=> need-resched    \n", size, spaces);
+        seq_printf(s, "#%.*s| / _---=> hardirq/softirq \n", size, spaces);
+        seq_printf(s, "#%.*s|| / _--=> preempt-depth   \n", size, spaces);
+        seq_printf(s, "#%.*s||| / _-=> lock-depth      \n", size, spaces);
+        seq_printf(s, "#%.*s|||| /                     \n", size, spaces);
+}
+
+static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
 {
+        int lat = trace_flags & TRACE_ITER_LATENCY_FMT;
+
+        if (lat)
+                print_lat_header(s, flags);
+
         /* 1st line */
-        seq_printf(s, "# ");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+        seq_printf(s, "#");
+        if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
                 seq_printf(s, "     TIME       ");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
-                seq_printf(s, "CPU");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
-                seq_printf(s, "  TASK/PID      ");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+        if (flags & TRACE_GRAPH_PRINT_CPU)
+                seq_printf(s, " CPU");
+        if (flags & TRACE_GRAPH_PRINT_PROC)
+                seq_printf(s, "  TASK/PID       ");
+        if (lat)
+                seq_printf(s, "|||||");
+        if (flags & TRACE_GRAPH_PRINT_DURATION)
                 seq_printf(s, "  DURATION   ");
         seq_printf(s, "               FUNCTION CALLS\n");
 
         /* 2nd line */
-        seq_printf(s, "# ");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+        seq_printf(s, "#");
+        if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
                 seq_printf(s, "      |         ");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
-                seq_printf(s, "|  ");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
-                seq_printf(s, "  |    |        ");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+        if (flags & TRACE_GRAPH_PRINT_CPU)
+                seq_printf(s, " |  ");
+        if (flags & TRACE_GRAPH_PRINT_PROC)
+                seq_printf(s, "   |    |        ");
+        if (lat)
+                seq_printf(s, "|||||");
+        if (flags & TRACE_GRAPH_PRINT_DURATION)
                 seq_printf(s, "   |   |      ");
         seq_printf(s, "               |   |   |   |\n");
 }
 
-static void graph_trace_open(struct trace_iterator *iter)
+void print_graph_headers(struct seq_file *s)
+{
+        print_graph_headers_flags(s, tracer_flags.val);
+}
+
+void print_graph_headers_flags(struct seq_file *s, u32 flags)
+{
+        struct trace_iterator *iter = s->private;
+
+        if (trace_flags & TRACE_ITER_LATENCY_FMT) {
+                /* print nothing if the buffers are empty */
+                if (trace_empty(iter))
+                        return;
+
+                print_trace_header(s, iter);
+                flags |= TRACE_GRAPH_PRINT_DURATION;
+        } else
+                flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+        __print_graph_headers_flags(s, flags);
+}
+
+void graph_trace_open(struct trace_iterator *iter)
 {
         /* pid and depth on the last trace processed */
-        struct fgraph_data *data = alloc_percpu(struct fgraph_data);
+        struct fgraph_data *data;
         int cpu;
 
+        iter->private = NULL;
+
+        data = kzalloc(sizeof(*data), GFP_KERNEL);
         if (!data)
-                pr_warning("function graph tracer: not enough memory\n");
-        else
-                for_each_possible_cpu(cpu) {
-                        pid_t *pid = &(per_cpu_ptr(data, cpu)->last_pid);
-                        int *depth = &(per_cpu_ptr(data, cpu)->depth);
-                        *pid = -1;
-                        *depth = 0;
-                }
+                goto out_err;
+
+        data->cpu_data = alloc_percpu(struct fgraph_cpu_data);
+        if (!data->cpu_data)
+                goto out_err_free;
+
+        for_each_possible_cpu(cpu) {
+                pid_t *pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
+                int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+                int *ignore = &(per_cpu_ptr(data->cpu_data, cpu)->ignore);
+                int *depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
+
+                *pid = -1;
+                *depth = 0;
+                *ignore = 0;
+                *depth_irq = -1;
+        }
 
         iter->private = data;
+
+        return;
+
+ out_err_free:
+        kfree(data);
+ out_err:
+        pr_warning("function graph tracer: not enough memory\n");
+}
+
+void graph_trace_close(struct trace_iterator *iter)
+{
+        struct fgraph_data *data = iter->private;
+
+        if (data) {
+                free_percpu(data->cpu_data);
+                kfree(data);
+        }
 }
 
-static void graph_trace_close(struct trace_iterator *iter)
+static int func_graph_set_flag(u32 old_flags, u32 bit, int set)
 {
-        free_percpu(iter->private);
+        if (bit == TRACE_GRAPH_PRINT_IRQS)
+                ftrace_graph_skip_irqs = !set;
+
+        return 0;
 }
 
+static struct trace_event_functions graph_functions = {
+        .trace          = print_graph_function_event,
+};
+
+static struct trace_event graph_trace_entry_event = {
+        .type           = TRACE_GRAPH_ENT,
+        .funcs          = &graph_functions,
+};
+
+static struct trace_event graph_trace_ret_event = {
+        .type           = TRACE_GRAPH_RET,
+        .funcs          = &graph_functions
+};
+
 static struct tracer graph_trace __read_mostly = {
         .name           = "function_graph",
         .open           = graph_trace_open,
+        .pipe_open      = graph_trace_open,
         .close          = graph_trace_close,
+        .pipe_close     = graph_trace_close,
         .wait_pipe      = poll_wait_pipe,
         .init           = graph_trace_init,
         .reset          = graph_trace_reset,
         .print_line     = print_graph_function,
         .print_header   = print_graph_headers,
         .flags          = &tracer_flags,
+        .set_flag       = func_graph_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest       = trace_selftest_startup_function_graph,
 #endif
@@ -927,6 +1461,18 @@ static struct tracer graph_trace __read_mostly = {
 
 static __init int init_graph_trace(void)
 {
+        max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
+
+        if (!register_ftrace_event(&graph_trace_entry_event)) {
+                pr_warning("Warning: could not register graph trace events\n");
+                return 1;
+        }
+
+        if (!register_ftrace_event(&graph_trace_ret_event)) {
+                pr_warning("Warning: could not register graph trace events\n");
+                return 1;
+        }
+
         return register_tracer(&graph_trace);
 }
 
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
deleted file mode 100644
index ca7d7c4d0c2a..000000000000
--- a/kernel/trace/trace_hw_branches.c
+++ /dev/null
@@ -1,309 +0,0 @@
-/*
- * h/w branch tracer for x86 based on BTS
- *
- * Copyright (C) 2008-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@gmail.com>, 2008-2009
- */
-#include <linux/kallsyms.h>
-#include <linux/debugfs.h>
-#include <linux/ftrace.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <linux/fs.h>
-
-#include <asm/ds.h>
-
-#include "trace_output.h"
-#include "trace.h"
-
-
-#define BTS_BUFFER_SIZE (1 << 13)
-
-static DEFINE_PER_CPU(struct bts_tracer *, tracer);
-static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], buffer);
-
-#define this_tracer per_cpu(tracer, smp_processor_id())
-
-static int trace_hw_branches_enabled __read_mostly;
-static int trace_hw_branches_suspended __read_mostly;
-static struct trace_array *hw_branch_trace __read_mostly;
-
-
-static void bts_trace_init_cpu(int cpu)
-{
-        per_cpu(tracer, cpu) =
-                ds_request_bts_cpu(cpu, per_cpu(buffer, cpu), BTS_BUFFER_SIZE,
-                                   NULL, (size_t)-1, BTS_KERNEL);
-
-        if (IS_ERR(per_cpu(tracer, cpu)))
-                per_cpu(tracer, cpu) = NULL;
-}
-
-static int bts_trace_init(struct trace_array *tr)
-{
-        int cpu;
-
-        hw_branch_trace = tr;
-        trace_hw_branches_enabled = 0;
-
-        get_online_cpus();
-        for_each_online_cpu(cpu) {
-                bts_trace_init_cpu(cpu);
-
-                if (likely(per_cpu(tracer, cpu)))
-                        trace_hw_branches_enabled = 1;
-        }
-        trace_hw_branches_suspended = 0;
-        put_online_cpus();
-
-        /* If we could not enable tracing on a single cpu, we fail. */
-        return trace_hw_branches_enabled ? 0 : -EOPNOTSUPP;
-}
-
-static void bts_trace_reset(struct trace_array *tr)
-{
-        int cpu;
-
-        get_online_cpus();
-        for_each_online_cpu(cpu) {
-                if (likely(per_cpu(tracer, cpu))) {
-                        ds_release_bts(per_cpu(tracer, cpu));
-                        per_cpu(tracer, cpu) = NULL;
-                }
-        }
-        trace_hw_branches_enabled = 0;
-        trace_hw_branches_suspended = 0;
-        put_online_cpus();
-}
-
-static void bts_trace_start(struct trace_array *tr)
-{
-        int cpu;
-
-        get_online_cpus();
-        for_each_online_cpu(cpu)
-                if (likely(per_cpu(tracer, cpu)))
-                        ds_resume_bts(per_cpu(tracer, cpu));
-        trace_hw_branches_suspended = 0;
-        put_online_cpus();
-}
-
-static void bts_trace_stop(struct trace_array *tr)
-{
-        int cpu;
-
-        get_online_cpus();
-        for_each_online_cpu(cpu)
-                if (likely(per_cpu(tracer, cpu)))
-                        ds_suspend_bts(per_cpu(tracer, cpu));
-        trace_hw_branches_suspended = 1;
-        put_online_cpus();
-}
-
-static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
-                                     unsigned long action, void *hcpu)
-{
-        int cpu = (long)hcpu;
-
-        switch (action) {
-        case CPU_ONLINE:
-        case CPU_DOWN_FAILED:
-                /* The notification is sent with interrupts enabled. */
-                if (trace_hw_branches_enabled) {
-                        bts_trace_init_cpu(cpu);
-
-                        if (trace_hw_branches_suspended &&
-                            likely(per_cpu(tracer, cpu)))
-                                ds_suspend_bts(per_cpu(tracer, cpu));
-                }
-                break;
-
-        case CPU_DOWN_PREPARE:
-                /* The notification is sent with interrupts enabled. */
-                if (likely(per_cpu(tracer, cpu))) {
-                        ds_release_bts(per_cpu(tracer, cpu));
-                        per_cpu(tracer, cpu) = NULL;
-                }
-        }
-
-        return NOTIFY_DONE;
-}
-
-static struct notifier_block bts_hotcpu_notifier __cpuinitdata = {
-        .notifier_call = bts_hotcpu_handler
-};
-
-static void bts_trace_print_header(struct seq_file *m)
-{
-        seq_puts(m, "# CPU#        TO  <-  FROM\n");
-}
-
-static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
-{
-        unsigned long symflags = TRACE_ITER_SYM_OFFSET;
-        struct trace_entry *entry = iter->ent;
-        struct trace_seq *seq = &iter->seq;
-        struct hw_branch_entry *it;
-
-        trace_assign_type(it, entry);
-
-        if (entry->type == TRACE_HW_BRANCHES) {
-                if (trace_seq_printf(seq, "%4d  ", iter->cpu) &&
-                    seq_print_ip_sym(seq, it->to, symflags) &&
-                    trace_seq_printf(seq, "\t  <-  ") &&
-                    seq_print_ip_sym(seq, it->from, symflags) &&
-                    trace_seq_printf(seq, "\n"))
-                        return TRACE_TYPE_HANDLED;
-                return TRACE_TYPE_PARTIAL_LINE;;
-        }
-        return TRACE_TYPE_UNHANDLED;
-}
-
-void trace_hw_branch(u64 from, u64 to)
-{
-        struct ftrace_event_call *call = &event_hw_branch;
-        struct trace_array *tr = hw_branch_trace;
-        struct ring_buffer_event *event;
-        struct hw_branch_entry *entry;
-        unsigned long irq1;
-        int cpu;
-
-        if (unlikely(!tr))
-                return;
-
-        if (unlikely(!trace_hw_branches_enabled))
-                return;
-
-        local_irq_save(irq1);
-        cpu = raw_smp_processor_id();
-        if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
-                goto out;
-
-        event = trace_buffer_lock_reserve(tr, TRACE_HW_BRANCHES,
-                                          sizeof(*entry), 0, 0);
-        if (!event)
-                goto out;
-        entry   = ring_buffer_event_data(event);
-        tracing_generic_entry_update(&entry->ent, 0, from);
-        entry->ent.type = TRACE_HW_BRANCHES;
-        entry->from = from;
-        entry->to   = to;
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                trace_buffer_unlock_commit(tr, event, 0, 0);
-
- out:
-        atomic_dec(&tr->data[cpu]->disabled);
-        local_irq_restore(irq1);
-}
-
-static void trace_bts_at(const struct bts_trace *trace, void *at)
-{
-        struct bts_struct bts;
-        int err = 0;
-
-        WARN_ON_ONCE(!trace->read);
-        if (!trace->read)
-                return;
-
-        err = trace->read(this_tracer, at, &bts);
-        if (err < 0)
-                return;
-
-        switch (bts.qualifier) {
-        case BTS_BRANCH:
-                trace_hw_branch(bts.variant.lbr.from, bts.variant.lbr.to);
-                break;
-        }
-}
-
-/*
- * Collect the trace on the current cpu and write it into the ftrace buffer.
- *
- * pre: tracing must be suspended on the current cpu
- */
-static void trace_bts_cpu(void *arg)
-{
-        struct trace_array *tr = (struct trace_array *)arg;
-        const struct bts_trace *trace;
-        unsigned char *at;
-
-        if (unlikely(!tr))
-                return;
-
-        if (unlikely(atomic_read(&tr->data[raw_smp_processor_id()]->disabled)))
-                return;
-
-        if (unlikely(!this_tracer))
-                return;
-
-        trace = ds_read_bts(this_tracer);
-        if (!trace)
-                return;
-
-        for (at = trace->ds.top; (void *)at < trace->ds.end;
-             at += trace->ds.size)
-                trace_bts_at(trace, at);
-
-        for (at = trace->ds.begin; (void *)at < trace->ds.top;
-             at += trace->ds.size)
-                trace_bts_at(trace, at);
-}
-
-static void trace_bts_prepare(struct trace_iterator *iter)
-{
-        int cpu;
-
-        get_online_cpus();
-        for_each_online_cpu(cpu)
-                if (likely(per_cpu(tracer, cpu)))
-                        ds_suspend_bts(per_cpu(tracer, cpu));
-        /*
-         * We need to collect the trace on the respective cpu since ftrace
-         * implicitly adds the record for the current cpu.
-         * Once that is more flexible, we could collect the data from any cpu.
-         */
-        on_each_cpu(trace_bts_cpu, iter->tr, 1);
-
-        for_each_online_cpu(cpu)
-                if (likely(per_cpu(tracer, cpu)))
-                        ds_resume_bts(per_cpu(tracer, cpu));
-        put_online_cpus();
-}
-
-static void trace_bts_close(struct trace_iterator *iter)
-{
-        tracing_reset_online_cpus(iter->tr);
-}
-
-void trace_hw_branch_oops(void)
-{
-        if (this_tracer) {
-                ds_suspend_bts_noirq(this_tracer);
-                trace_bts_cpu(hw_branch_trace);
-                ds_resume_bts_noirq(this_tracer);
-        }
-}
-
-struct tracer bts_tracer __read_mostly =
-{
-        .name           = "hw-branch-tracer",
-        .init           = bts_trace_init,
-        .reset          = bts_trace_reset,
-        .print_header   = bts_trace_print_header,
-        .print_line     = bts_trace_print_line,
-        .start          = bts_trace_start,
-        .stop           = bts_trace_stop,
-        .open           = trace_bts_prepare,
-        .close          = trace_bts_close,
-#ifdef CONFIG_FTRACE_SELFTEST
-        .selftest       = trace_selftest_startup_hw_branches,
-#endif /* CONFIG_FTRACE_SELFTEST */
-};
-
-__init static int init_bts_trace(void)
-{
-        register_hotcpu_notifier(&bts_hotcpu_notifier);
-        return register_tracer(&bts_tracer);
-}
-device_initcall(init_bts_trace);
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index b923d13e2fad..5cf8c602b880 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -34,6 +34,9 @@ static int trace_type __read_mostly;
 
 static int save_lat_flag;
 
+static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
+static int start_irqsoff_tracer(struct trace_array *tr, int graph);
+
 #ifdef CONFIG_PREEMPT_TRACER
 static inline int
 preempt_trace(void)
@@ -55,6 +58,23 @@ irq_trace(void)
 # define irq_trace() (0)
 #endif
 
+#define TRACE_DISPLAY_GRAPH     1
+
+static struct tracer_opt trace_opts[] = {
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        /* display latency trace as call graph */
+        { TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) },
+#endif
+        { } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+        .val  = 0,
+        .opts = trace_opts,
+};
+
+#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH)
+
 /*
  * Sequence count - we record it when starting a measurement and
  * skip the latency if the sequence has changed - some other section
@@ -67,14 +87,22 @@ static __cacheline_aligned_in_smp	unsigned long max_sequence;
 
 #ifdef CONFIG_FUNCTION_TRACER
 /*
- * irqsoff uses its own tracer function to keep the overhead down:
+ * Prologue for the preempt and irqs off function tracers.
+ *
+ * Returns 1 if it is OK to continue, and data->disabled is
+ *            incremented.
+ *         0 if the trace is to be ignored, and data->disabled
+ *            is kept the same.
+ *
+ * Note, this function is also used outside this ifdef but
+ *  inside the #ifdef of the function graph tracer below.
+ *  This is OK, since the function graph tracer is
+ *  dependent on the function tracer.
  */
-static void
-irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
+static int func_prolog_dec(struct trace_array *tr,
+                           struct trace_array_cpu **data,
+                           unsigned long *flags)
 {
-        struct trace_array *tr = irqsoff_trace;
-        struct trace_array_cpu *data;
-        unsigned long flags;
         long disabled;
         int cpu;
 
@@ -86,18 +114,38 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
          */
         cpu = raw_smp_processor_id();
         if (likely(!per_cpu(tracing_cpu, cpu)))
-                return;
+                return 0;
 
-        local_save_flags(flags);
+        local_save_flags(*flags);
         /* slight chance to get a false positive on tracing_cpu */
-        if (!irqs_disabled_flags(flags))
-                return;
+        if (!irqs_disabled_flags(*flags))
+                return 0;
 
-        data = tr->data[cpu];
-        disabled = atomic_inc_return(&data->disabled);
+        *data = tr->data[cpu];
+        disabled = atomic_inc_return(&(*data)->disabled);
 
         if (likely(disabled == 1))
-                trace_function(tr, ip, parent_ip, flags, preempt_count());
+                return 1;
+
+        atomic_dec(&(*data)->disabled);
+
+        return 0;
+}
+
+/*
+ * irqsoff uses its own tracer function to keep the overhead down:
+ */
+static void
+irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
+{
+        struct trace_array *tr = irqsoff_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+
+        if (!func_prolog_dec(tr, &data, &flags))
+                return;
+
+        trace_function(tr, ip, parent_ip, flags, preempt_count());
 
         atomic_dec(&data->disabled);
 }
@@ -108,6 +156,132 @@ static struct ftrace_ops trace_ops __read_mostly =
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+{
+        int cpu;
+
+        if (!(bit & TRACE_DISPLAY_GRAPH))
+                return -EINVAL;
+
+        if (!(is_graph() ^ set))
+                return 0;
+
+        stop_irqsoff_tracer(irqsoff_trace, !set);
+
+        for_each_possible_cpu(cpu)
+                per_cpu(tracing_cpu, cpu) = 0;
+
+        tracing_max_latency = 0;
+        tracing_reset_online_cpus(irqsoff_trace);
+
+        return start_irqsoff_tracer(irqsoff_trace, set);
+}
+
+static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
+{
+        struct trace_array *tr = irqsoff_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        int ret;
+        int pc;
+
+        if (!func_prolog_dec(tr, &data, &flags))
+                return 0;
+
+        pc = preempt_count();
+        ret = __trace_graph_entry(tr, trace, flags, pc);
+        atomic_dec(&data->disabled);
+
+        return ret;
+}
+
+static void irqsoff_graph_return(struct ftrace_graph_ret *trace)
+{
+        struct trace_array *tr = irqsoff_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        int pc;
+
+        if (!func_prolog_dec(tr, &data, &flags))
+                return;
+
+        pc = preempt_count();
+        __trace_graph_return(tr, trace, flags, pc);
+        atomic_dec(&data->disabled);
+}
+
+static void irqsoff_trace_open(struct trace_iterator *iter)
+{
+        if (is_graph())
+                graph_trace_open(iter);
+
+}
+
+static void irqsoff_trace_close(struct trace_iterator *iter)
+{
+        if (iter->private)
+                graph_trace_close(iter);
+}
+
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_CPU | \
+                            TRACE_GRAPH_PRINT_PROC)
+
+static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
+{
+        /*
+         * In graph mode call the graph tracer output function,
+         * otherwise go with the TRACE_FN event handler
+         */
+        if (is_graph())
+                return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);
+
+        return TRACE_TYPE_UNHANDLED;
+}
+
+static void irqsoff_print_header(struct seq_file *s)
+{
+        if (is_graph())
+                print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
+        else
+                trace_default_header(s);
+}
+
+static void
+__trace_function(struct trace_array *tr,
+                 unsigned long ip, unsigned long parent_ip,
+                 unsigned long flags, int pc)
+{
+        if (is_graph())
+                trace_graph_function(tr, ip, parent_ip, flags, pc);
+        else
+                trace_function(tr, ip, parent_ip, flags, pc);
+}
+
+#else
+#define __trace_function trace_function
+
+static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+{
+        return -EINVAL;
+}
+
+static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
+{
+        return -1;
+}
+
+static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
+{
+        return TRACE_TYPE_UNHANDLED;
+}
+
+static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { }
+static void irqsoff_print_header(struct seq_file *s) { }
+static void irqsoff_trace_open(struct trace_iterator *iter) { }
+static void irqsoff_trace_close(struct trace_iterator *iter) { }
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 /*
  * Should this new latency be reported/recorded?
  */
@@ -129,15 +303,10 @@ check_critical_timing(struct trace_array *tr,
                       unsigned long parent_ip,
                       int cpu)
 {
-        unsigned long latency, t0, t1;
         cycle_t T0, T1, delta;
         unsigned long flags;
         int pc;
 
-        /*
-         * usecs conversion is slow so we try to delay the conversion
-         * as long as possible:
-         */
         T0 = data->preempt_timestamp;
         T1 = ftrace_now(cpu);
         delta = T1-T0;
@@ -155,20 +324,19 @@ check_critical_timing(struct trace_array *tr,
         if (!report_latency(delta))
                 goto out_unlock;
 
-        trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
-
-        latency = nsecs_to_usecs(delta);
+        __trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+        /* Skip 5 functions to get to the irq/preempt enable function */
+        __trace_stack(tr, flags, 5, pc);
 
         if (data->critical_sequence != max_sequence)
                 goto out_unlock;
 
-        tracing_max_latency = delta;
-        t0 = nsecs_to_usecs(T0);
-        t1 = nsecs_to_usecs(T1);
-
         data->critical_end = parent_ip;
 
-        update_max_tr_single(tr, current, cpu);
+        if (likely(!is_tracing_stopped())) {
+                tracing_max_latency = delta;
+                update_max_tr_single(tr, current, cpu);
+        }
 
         max_sequence++;
 
@@ -178,8 +346,7 @@ out_unlock:
 out:
         data->critical_sequence = max_sequence;
         data->preempt_timestamp = ftrace_now(cpu);
-        tracing_reset(tr, cpu);
-        trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+        __trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
 }
 
 static inline void
@@ -208,11 +375,10 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
         data->critical_sequence = max_sequence;
         data->preempt_timestamp = ftrace_now(cpu);
         data->critical_start = parent_ip ? : ip;
-        tracing_reset(tr, cpu);
 
         local_save_flags(flags);
 
-        trace_function(tr, ip, parent_ip, flags, preempt_count());
+        __trace_function(tr, ip, parent_ip, flags, preempt_count());
 
         per_cpu(tracing_cpu, cpu) = 1;
 
@@ -246,7 +412,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
         atomic_inc(&data->disabled);
 
         local_save_flags(flags);
-        trace_function(tr, ip, parent_ip, flags, preempt_count());
+        __trace_function(tr, ip, parent_ip, flags, preempt_count());
         check_critical_timing(tr, data, parent_ip ? : ip, cpu);
         data->critical_start = 0;
         atomic_dec(&data->disabled);
@@ -355,19 +521,32 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
-static void start_irqsoff_tracer(struct trace_array *tr)
+static int start_irqsoff_tracer(struct trace_array *tr, int graph)
 {
-        register_ftrace_function(&trace_ops);
-        if (tracing_is_enabled())
+        int ret = 0;
+
+        if (!graph)
+                ret = register_ftrace_function(&trace_ops);
+        else
+                ret = register_ftrace_graph(&irqsoff_graph_return,
+                                            &irqsoff_graph_entry);
+
+        if (!ret && tracing_is_enabled())
                 tracer_enabled = 1;
         else
                 tracer_enabled = 0;
+
+        return ret;
 }
 
-static void stop_irqsoff_tracer(struct trace_array *tr)
+static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
 {
         tracer_enabled = 0;
-        unregister_ftrace_function(&trace_ops);
+
+        if (!graph)
+                unregister_ftrace_function(&trace_ops);
+        else
+                unregister_ftrace_graph();
 }
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
@@ -379,12 +558,15 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
         irqsoff_trace = tr;
         /* make sure that the tracer is visible */
         smp_wmb();
-        start_irqsoff_tracer(tr);
+        tracing_reset_online_cpus(tr);
+
+        if (start_irqsoff_tracer(tr, is_graph()))
+                printk(KERN_ERR "failed to start irqsoff tracer\n");
 }
 
 static void irqsoff_tracer_reset(struct trace_array *tr)
 {
-        stop_irqsoff_tracer(tr);
+        stop_irqsoff_tracer(tr, is_graph());
 
         if (!save_lat_flag)
                 trace_flags &= ~TRACE_ITER_LATENCY_FMT;
@@ -416,9 +598,16 @@ static struct tracer irqsoff_tracer __read_mostly =
         .start          = irqsoff_tracer_start,
         .stop           = irqsoff_tracer_stop,
         .print_max      = 1,
+        .print_header   = irqsoff_print_header,
+        .print_line     = irqsoff_print_line,
+        .flags          = &tracer_flags,
+        .set_flag       = irqsoff_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_irqsoff,
 #endif
+        .open           = irqsoff_trace_open,
+        .close          = irqsoff_trace_close,
+        .use_max_tr     = 1,
 };
 # define register_irqsoff(trace) register_tracer(&trace)
 #else
@@ -442,9 +631,16 @@ static struct tracer preemptoff_tracer __read_mostly =
         .start          = irqsoff_tracer_start,
         .stop           = irqsoff_tracer_stop,
         .print_max      = 1,
+        .print_header   = irqsoff_print_header,
+        .print_line     = irqsoff_print_line,
+        .flags          = &tracer_flags,
+        .set_flag       = irqsoff_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_preemptoff,
 #endif
+        .open           = irqsoff_trace_open,
+        .close          = irqsoff_trace_close,
+        .use_max_tr     = 1,
 };
 # define register_preemptoff(trace) register_tracer(&trace)
 #else
@@ -470,9 +666,16 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
         .start          = irqsoff_tracer_start,
         .stop           = irqsoff_tracer_stop,
         .print_max      = 1,
+        .print_header   = irqsoff_print_header,
+        .print_line     = irqsoff_print_line,
+        .flags          = &tracer_flags,
+        .set_flag       = irqsoff_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_preemptirqsoff,
 #endif
+        .open           = irqsoff_trace_open,
+        .close          = irqsoff_trace_close,
+        .use_max_tr     = 1,
 };
 
 # define register_preemptirqsoff(trace) register_tracer(&trace)
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
new file mode 100644
index 000000000000..3c5c5dfea0b3
--- /dev/null
+++ b/kernel/trace/trace_kdb.c
@@ -0,0 +1,135 @@
+/*
+ * kdb helper for dumping the ftrace buffer
+ *
+ * Copyright (C) 2010 Jason Wessel <jason.wessel@windriver.com>
+ *
+ * ftrace_dump_buf based on ftrace_dump:
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *
+ */
+#include <linux/init.h>
+#include <linux/kgdb.h>
+#include <linux/kdb.h>
+#include <linux/ftrace.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+static void ftrace_dump_buf(int skip_lines, long cpu_file)
+{
+        /* use static because iter can be a bit big for the stack */
+        static struct trace_iterator iter;
+        unsigned int old_userobj;
+        int cnt = 0, cpu;
+
+        trace_init_global_iter(&iter);
+
+        for_each_tracing_cpu(cpu) {
+                atomic_inc(&iter.tr->data[cpu]->disabled);
+        }
+
+        old_userobj = trace_flags;
+
+        /* don't look at user memory in panic mode */
+        trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
+
+        kdb_printf("Dumping ftrace buffer:\n");
+
+        /* reset all but tr, trace, and overruns */
+        memset(&iter.seq, 0,
+                   sizeof(struct trace_iterator) -
+                   offsetof(struct trace_iterator, seq));
+        iter.iter_flags |= TRACE_FILE_LAT_FMT;
+        iter.pos = -1;
+
+        if (cpu_file == TRACE_PIPE_ALL_CPU) {
+                for_each_tracing_cpu(cpu) {
+                        iter.buffer_iter[cpu] =
+                        ring_buffer_read_prepare(iter.tr->buffer, cpu);
+                        ring_buffer_read_start(iter.buffer_iter[cpu]);
+                        tracing_iter_reset(&iter, cpu);
+                }
+        } else {
+                iter.cpu_file = cpu_file;
+                iter.buffer_iter[cpu_file] =
+                        ring_buffer_read_prepare(iter.tr->buffer, cpu_file);
+                ring_buffer_read_start(iter.buffer_iter[cpu_file]);
+                tracing_iter_reset(&iter, cpu_file);
+        }
+        if (!trace_empty(&iter))
+                trace_find_next_entry_inc(&iter);
+        while (!trace_empty(&iter)) {
+                if (!cnt)
+                        kdb_printf("---------------------------------\n");
+                cnt++;
+
+                if (trace_find_next_entry_inc(&iter) != NULL && !skip_lines)
+                        print_trace_line(&iter);
+                if (!skip_lines)
+                        trace_printk_seq(&iter.seq);
+                else
+                        skip_lines--;
+                if (KDB_FLAG(CMD_INTERRUPT))
+                        goto out;
+        }
+
+        if (!cnt)
+                kdb_printf("   (ftrace buffer empty)\n");
+        else
+                kdb_printf("---------------------------------\n");
+
+out:
+        trace_flags = old_userobj;
+
+        for_each_tracing_cpu(cpu) {
+                atomic_dec(&iter.tr->data[cpu]->disabled);
+        }
+
+        for_each_tracing_cpu(cpu)
+                if (iter.buffer_iter[cpu])
+                        ring_buffer_read_finish(iter.buffer_iter[cpu]);
+}
+
+/*
+ * kdb_ftdump - Dump the ftrace log buffer
+ */
+static int kdb_ftdump(int argc, const char **argv)
+{
+        int skip_lines = 0;
+        long cpu_file;
+        char *cp;
+
+        if (argc > 2)
+                return KDB_ARGCOUNT;
+
+        if (argc) {
+                skip_lines = simple_strtol(argv[1], &cp, 0);
+                if (*cp)
+                        skip_lines = 0;
+        }
+
+        if (argc == 2) {
+                cpu_file = simple_strtol(argv[2], &cp, 0);
+                if (*cp || cpu_file >= NR_CPUS || cpu_file < 0 ||
+                    !cpu_online(cpu_file))
+                        return KDB_BADINT;
+        } else {
+                cpu_file = TRACE_PIPE_ALL_CPU;
+        }
+
+        kdb_trap_printk++;
+        ftrace_dump_buf(skip_lines, cpu_file);
+        kdb_trap_printk--;
+
+        return 0;
+}
+
+static __init int kdb_ftrace_register(void)
+{
+        kdb_register_repeat("ftdump", kdb_ftdump, "[skip_#lines] [cpu]",
+                            "Dump ftrace log", 0, KDB_REPEAT_NONE);
+        return 0;
+}
+
+late_initcall(kdb_ftrace_register);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
new file mode 100644
index 000000000000..2dec9bcde8b4
--- /dev/null
+++ b/kernel/trace/trace_kprobe.c
@@ -0,0 +1,1847 @@
+/*
+ * Kprobes-based tracing events
+ *
+ * Created by Masami Hiramatsu <mhiramat@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/debugfs.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/ptrace.h>
+#include <linux/perf_event.h>
+#include <linux/stringify.h>
+#include <linux/limits.h>
+#include <asm/bitsperlong.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+#define MAX_TRACE_ARGS 128
+#define MAX_ARGSTR_LEN 63
+#define MAX_EVENT_NAME_LEN 64
+#define MAX_STRING_SIZE PATH_MAX
+#define KPROBE_EVENT_SYSTEM "kprobes"
+
+/* Reserved field names */
+#define FIELD_STRING_IP "__probe_ip"
+#define FIELD_STRING_RETIP "__probe_ret_ip"
+#define FIELD_STRING_FUNC "__probe_func"
+
+const char *reserved_field_names[] = {
+        "common_type",
+        "common_flags",
+        "common_preempt_count",
+        "common_pid",
+        "common_tgid",
+        "common_lock_depth",
+        FIELD_STRING_IP,
+        FIELD_STRING_RETIP,
+        FIELD_STRING_FUNC,
+};
+
+/* Printing function type */
+typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *,
+                                 void *);
+#define PRINT_TYPE_FUNC_NAME(type)      print_type_##type
+#define PRINT_TYPE_FMT_NAME(type)       print_type_format_##type
+
+/* Printing  in basic type function template */
+#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast)                   \
+static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s,    \
+                                                const char *name,       \
+                                                void *data, void *ent)\
+{                                                                       \
+        return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\
+}                                                                       \
+static const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
+
+DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long)
+
+/* data_rloc: data relative location, compatible with u32 */
+#define make_data_rloc(len, roffs)      \
+        (((u32)(len) << 16) | ((u32)(roffs) & 0xffff))
+#define get_rloc_len(dl)        ((u32)(dl) >> 16)
+#define get_rloc_offs(dl)       ((u32)(dl) & 0xffff)
+
+static inline void *get_rloc_data(u32 *dl)
+{
+        return (u8 *)dl + get_rloc_offs(*dl);
+}
+
+/* For data_loc conversion */
+static inline void *get_loc_data(u32 *dl, void *ent)
+{
+        return (u8 *)ent + get_rloc_offs(*dl);
+}
+
+/*
+ * Convert data_rloc to data_loc:
+ *  data_rloc stores the offset from data_rloc itself, but data_loc
+ *  stores the offset from event entry.
+ */
+#define convert_rloc_to_loc(dl, offs)   ((u32)(dl) + (offs))
+
+/* For defining macros, define string/string_size types */
+typedef u32 string;
+typedef u32 string_size;
+
+/* Print type function for string type */
+static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
+                                                  const char *name,
+                                                  void *data, void *ent)
+{
+        int len = *(u32 *)data >> 16;
+
+        if (!len)
+                return trace_seq_printf(s, " %s=(fault)", name);
+        else
+                return trace_seq_printf(s, " %s=\"%s\"", name,
+                                        (const char *)get_loc_data(data, ent));
+}
+static const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
+
+/* Data fetch function type */
+typedef void (*fetch_func_t)(struct pt_regs *, void *, void *);
+
+struct fetch_param {
+        fetch_func_t    fn;
+        void *data;
+};
+
+static __kprobes void call_fetch(struct fetch_param *fprm,
+                                 struct pt_regs *regs, void *dest)
+{
+        return fprm->fn(regs, fprm->data, dest);
+}
+
+#define FETCH_FUNC_NAME(method, type)   fetch_##method##_##type
+/*
+ * Define macro for basic types - we don't need to define s* types, because
+ * we have to care only about bitwidth at recording time.
+ */
+#define DEFINE_BASIC_FETCH_FUNCS(method) \
+DEFINE_FETCH_##method(u8)               \
+DEFINE_FETCH_##method(u16)              \
+DEFINE_FETCH_##method(u32)              \
+DEFINE_FETCH_##method(u64)
+
+#define CHECK_FETCH_FUNCS(method, fn)                   \
+        (((FETCH_FUNC_NAME(method, u8) == fn) ||        \
+          (FETCH_FUNC_NAME(method, u16) == fn) ||       \
+          (FETCH_FUNC_NAME(method, u32) == fn) ||       \
+          (FETCH_FUNC_NAME(method, u64) == fn) ||       \
+          (FETCH_FUNC_NAME(method, string) == fn) ||    \
+          (FETCH_FUNC_NAME(method, string_size) == fn)) \
+         && (fn != NULL))
+
+/* Data fetch function templates */
+#define DEFINE_FETCH_reg(type)                                          \
+static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs,  \
+                                        void *offset, void *dest)       \
+{                                                                       \
+        *(type *)dest = (type)regs_get_register(regs,                   \
+                                (unsigned int)((unsigned long)offset)); \
+}
+DEFINE_BASIC_FETCH_FUNCS(reg)
+/* No string on the register */
+#define fetch_reg_string NULL
+#define fetch_reg_string_size NULL
+
+#define DEFINE_FETCH_stack(type)                                        \
+static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+                                          void *offset, void *dest)     \
+{                                                                       \
+        *(type *)dest = (type)regs_get_kernel_stack_nth(regs,           \
+                                (unsigned int)((unsigned long)offset)); \
+}
+DEFINE_BASIC_FETCH_FUNCS(stack)
+/* No string on the stack entry */
+#define fetch_stack_string NULL
+#define fetch_stack_string_size NULL
+
+#define DEFINE_FETCH_retval(type)                                       \
+static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\
+                                          void *dummy, void *dest)      \
+{                                                                       \
+        *(type *)dest = (type)regs_return_value(regs);                  \
+}
+DEFINE_BASIC_FETCH_FUNCS(retval)
+/* No string on the retval */
+#define fetch_retval_string NULL
+#define fetch_retval_string_size NULL
+
+#define DEFINE_FETCH_memory(type)                                       \
+static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+                                          void *addr, void *dest)       \
+{                                                                       \
+        type retval;                                                    \
+        if (probe_kernel_address(addr, retval))                         \
+                *(type *)dest = 0;                                      \
+        else                                                            \
+                *(type *)dest = retval;                                 \
+}
+DEFINE_BASIC_FETCH_FUNCS(memory)
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
+ * length and relative data location.
+ */
+static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
+                                                      void *addr, void *dest)
+{
+        long ret;
+        int maxlen = get_rloc_len(*(u32 *)dest);
+        u8 *dst = get_rloc_data(dest);
+        u8 *src = addr;
+        mm_segment_t old_fs = get_fs();
+        if (!maxlen)
+                return;
+        /*
+         * Try to get string again, since the string can be changed while
+         * probing.
+         */
+        set_fs(KERNEL_DS);
+        pagefault_disable();
+        do
+                ret = __copy_from_user_inatomic(dst++, src++, 1);
+        while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen);
+        dst[-1] = '\0';
+        pagefault_enable();
+        set_fs(old_fs);
+
+        if (ret < 0) {  /* Failed to fetch string */
+                ((u8 *)get_rloc_data(dest))[0] = '\0';
+                *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
+        } else
+                *(u32 *)dest = make_data_rloc(src - (u8 *)addr,
+                                              get_rloc_offs(*(u32 *)dest));
+}
+/* Return the length of string -- including null terminal byte */
+static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
+                                                        void *addr, void *dest)
+{
+        int ret, len = 0;
+        u8 c;
+        mm_segment_t old_fs = get_fs();
+
+        set_fs(KERNEL_DS);
+        pagefault_disable();
+        do {
+                ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
+                len++;
+        } while (c && ret == 0 && len < MAX_STRING_SIZE);
+        pagefault_enable();
+        set_fs(old_fs);
+
+        if (ret < 0)    /* Failed to check the length */
+                *(u32 *)dest = 0;
+        else
+                *(u32 *)dest = len;
+}
+
+/* Memory fetching by symbol */
+struct symbol_cache {
+        char *symbol;
+        long offset;
+        unsigned long addr;
+};
+
+static unsigned long update_symbol_cache(struct symbol_cache *sc)
+{
+        sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
+        if (sc->addr)
+                sc->addr += sc->offset;
+        return sc->addr;
+}
+
+static void free_symbol_cache(struct symbol_cache *sc)
+{
+        kfree(sc->symbol);
+        kfree(sc);
+}
+
+static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
+{
+        struct symbol_cache *sc;
+
+        if (!sym || strlen(sym) == 0)
+                return NULL;
+        sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
+        if (!sc)
+                return NULL;
+
+        sc->symbol = kstrdup(sym, GFP_KERNEL);
+        if (!sc->symbol) {
+                kfree(sc);
+                return NULL;
+        }
+        sc->offset = offset;
+
+        update_symbol_cache(sc);
+        return sc;
+}
+
+#define DEFINE_FETCH_symbol(type)                                       \
+static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\
+                                          void *data, void *dest)       \
+{                                                                       \
+        struct symbol_cache *sc = data;                                 \
+        if (sc->addr)                                                   \
+                fetch_memory_##type(regs, (void *)sc->addr, dest);      \
+        else                                                            \
+                *(type *)dest = 0;                                      \
+}
+DEFINE_BASIC_FETCH_FUNCS(symbol)
+DEFINE_FETCH_symbol(string)
+DEFINE_FETCH_symbol(string_size)
+
+/* Dereference memory access function */
+struct deref_fetch_param {
+        struct fetch_param orig;
+        long offset;
+};
+
+#define DEFINE_FETCH_deref(type)                                        \
+static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
+                                            void *data, void *dest)     \
+{                                                                       \
+        struct deref_fetch_param *dprm = data;                          \
+        unsigned long addr;                                             \
+        call_fetch(&dprm->orig, regs, &addr);                           \
+        if (addr) {                                                     \
+                addr += dprm->offset;                                   \
+                fetch_memory_##type(regs, (void *)addr, dest);          \
+        } else                                                          \
+                *(type *)dest = 0;                                      \
+}
+DEFINE_BASIC_FETCH_FUNCS(deref)
+DEFINE_FETCH_deref(string)
+DEFINE_FETCH_deref(string_size)
+
+static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
+{
+        if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+                free_deref_fetch_param(data->orig.data);
+        else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+                free_symbol_cache(data->orig.data);
+        kfree(data);
+}
+
+/* Default (unsigned long) fetch type */
+#define __DEFAULT_FETCH_TYPE(t) u##t
+#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
+#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
+#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
+
+/* Fetch types */
+enum {
+        FETCH_MTD_reg = 0,
+        FETCH_MTD_stack,
+        FETCH_MTD_retval,
+        FETCH_MTD_memory,
+        FETCH_MTD_symbol,
+        FETCH_MTD_deref,
+        FETCH_MTD_END,
+};
+
+#define ASSIGN_FETCH_FUNC(method, type) \
+        [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
+
+#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \
+        {.name = _name,                         \
+         .size = _size,                                 \
+         .is_signed = sign,                             \
+         .print = PRINT_TYPE_FUNC_NAME(ptype),          \
+         .fmt = PRINT_TYPE_FMT_NAME(ptype),             \
+         .fmttype = _fmttype,                           \
+         .fetch = {                                     \
+ASSIGN_FETCH_FUNC(reg, ftype),                          \
+ASSIGN_FETCH_FUNC(stack, ftype),                        \
+ASSIGN_FETCH_FUNC(retval, ftype),                       \
+ASSIGN_FETCH_FUNC(memory, ftype),                       \
+ASSIGN_FETCH_FUNC(symbol, ftype),                       \
+ASSIGN_FETCH_FUNC(deref, ftype),                        \
+          }                                             \
+        }
+
+#define ASSIGN_FETCH_TYPE(ptype, ftype, sign)                   \
+        __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
+
+#define FETCH_TYPE_STRING 0
+#define FETCH_TYPE_STRSIZE 1
+
+/* Fetch type information table */
+static const struct fetch_type {
+        const char      *name;          /* Name of type */
+        size_t          size;           /* Byte size of type */
+        int             is_signed;      /* Signed flag */
+        print_type_func_t       print;  /* Print functions */
+        const char      *fmt;           /* Fromat string */
+        const char      *fmttype;       /* Name in format file */
+        /* Fetch functions */
+        fetch_func_t    fetch[FETCH_MTD_END];
+} fetch_type_table[] = {
+        /* Special types */
+        [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
+                                        sizeof(u32), 1, "__data_loc char[]"),
+        [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
+                                        string_size, sizeof(u32), 0, "u32"),
+        /* Basic types */
+        ASSIGN_FETCH_TYPE(u8,  u8,  0),
+        ASSIGN_FETCH_TYPE(u16, u16, 0),
+        ASSIGN_FETCH_TYPE(u32, u32, 0),
+        ASSIGN_FETCH_TYPE(u64, u64, 0),
+        ASSIGN_FETCH_TYPE(s8,  u8,  1),
+        ASSIGN_FETCH_TYPE(s16, u16, 1),
+        ASSIGN_FETCH_TYPE(s32, u32, 1),
+        ASSIGN_FETCH_TYPE(s64, u64, 1),
+};
+
+static const struct fetch_type *find_fetch_type(const char *type)
+{
+        int i;
+
+        if (!type)
+                type = DEFAULT_FETCH_TYPE_STR;
+
+        for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
+                if (strcmp(type, fetch_type_table[i].name) == 0)
+                        return &fetch_type_table[i];
+        return NULL;
+}
+
+/* Special function : only accept unsigned long */
+static __kprobes void fetch_stack_address(struct pt_regs *regs,
+                                          void *dummy, void *dest)
+{
+        *(unsigned long *)dest = kernel_stack_pointer(regs);
+}
+
+static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
+                                            fetch_func_t orig_fn)
+{
+        int i;
+
+        if (type != &fetch_type_table[FETCH_TYPE_STRING])
+                return NULL;    /* Only string type needs size function */
+        for (i = 0; i < FETCH_MTD_END; i++)
+                if (type->fetch[i] == orig_fn)
+                        return fetch_type_table[FETCH_TYPE_STRSIZE].fetch[i];
+
+        WARN_ON(1);     /* This should not happen */
+        return NULL;
+}
+
+/**
+ * Kprobe event core functions
+ */
+
+struct probe_arg {
+        struct fetch_param      fetch;
+        struct fetch_param      fetch_size;
+        unsigned int            offset; /* Offset from argument entry */
+        const char              *name;  /* Name of this argument */
+        const char              *comm;  /* Command of this argument */
+        const struct fetch_type *type;  /* Type of this argument */
+};
+
+/* Flags for trace_probe */
+#define TP_FLAG_TRACE   1
+#define TP_FLAG_PROFILE 2
+
+struct trace_probe {
+        struct list_head        list;
+        struct kretprobe        rp;     /* Use rp.kp for kprobe use */
+        unsigned long           nhit;
+        unsigned int            flags;  /* For TP_FLAG_* */
+        const char              *symbol;        /* symbol name */
+        struct ftrace_event_class       class;
+        struct ftrace_event_call        call;
+        ssize_t                 size;           /* trace entry size */
+        unsigned int            nr_args;
+        struct probe_arg        args[];
+};
+
+#define SIZEOF_TRACE_PROBE(n)                   \
+        (offsetof(struct trace_probe, args) +   \
+        (sizeof(struct probe_arg) * (n)))
+
+
+static __kprobes int probe_is_return(struct trace_probe *tp)
+{
+        return tp->rp.handler != NULL;
+}
+
+static __kprobes const char *probe_symbol(struct trace_probe *tp)
+{
+        return tp->symbol ? tp->symbol : "unknown";
+}
+
+static int register_probe_event(struct trace_probe *tp);
+static void unregister_probe_event(struct trace_probe *tp);
+
+static DEFINE_MUTEX(probe_lock);
+static LIST_HEAD(probe_list);
+
+static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
+static int kretprobe_dispatcher(struct kretprobe_instance *ri,
+                                struct pt_regs *regs);
+
+/* Check the name is good for event/group/fields */
+static int is_good_name(const char *name)
+{
+        if (!isalpha(*name) && *name != '_')
+                return 0;
+        while (*++name != '\0') {
+                if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+                        return 0;
+        }
+        return 1;
+}
+
+/*
+ * Allocate new trace_probe and initialize it (including kprobes).
+ */
+static struct trace_probe *alloc_trace_probe(const char *group,
+                                             const char *event,
+                                             void *addr,
+                                             const char *symbol,
+                                             unsigned long offs,
+                                             int nargs, int is_return)
+{
+        struct trace_probe *tp;
+        int ret = -ENOMEM;
+
+        tp = kzalloc(SIZEOF_TRACE_PROBE(nargs), GFP_KERNEL);
+        if (!tp)
+                return ERR_PTR(ret);
+
+        if (symbol) {
+                tp->symbol = kstrdup(symbol, GFP_KERNEL);
+                if (!tp->symbol)
+                        goto error;
+                tp->rp.kp.symbol_name = tp->symbol;
+                tp->rp.kp.offset = offs;
+        } else
+                tp->rp.kp.addr = addr;
+
+        if (is_return)
+                tp->rp.handler = kretprobe_dispatcher;
+        else
+                tp->rp.kp.pre_handler = kprobe_dispatcher;
+
+        if (!event || !is_good_name(event)) {
+                ret = -EINVAL;
+                goto error;
+        }
+
+        tp->call.class = &tp->class;
+        tp->call.name = kstrdup(event, GFP_KERNEL);
+        if (!tp->call.name)
+                goto error;
+
+        if (!group || !is_good_name(group)) {
+                ret = -EINVAL;
+                goto error;
+        }
+
+        tp->class.system = kstrdup(group, GFP_KERNEL);
+        if (!tp->class.system)
+                goto error;
+
+        INIT_LIST_HEAD(&tp->list);
+        return tp;
+error:
+        kfree(tp->call.name);
+        kfree(tp->symbol);
+        kfree(tp);
+        return ERR_PTR(ret);
+}
+
+static void free_probe_arg(struct probe_arg *arg)
+{
+        if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+                free_deref_fetch_param(arg->fetch.data);
+        else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
+                free_symbol_cache(arg->fetch.data);
+        kfree(arg->name);
+        kfree(arg->comm);
+}
+
+static void free_trace_probe(struct trace_probe *tp)
+{
+        int i;
+
+        for (i = 0; i < tp->nr_args; i++)
+                free_probe_arg(&tp->args[i]);
+
+        kfree(tp->call.class->system);
+        kfree(tp->call.name);
+        kfree(tp->symbol);
+        kfree(tp);
+}
+
+static struct trace_probe *find_probe_event(const char *event,
+                                            const char *group)
+{
+        struct trace_probe *tp;
+
+        list_for_each_entry(tp, &probe_list, list)
+                if (strcmp(tp->call.name, event) == 0 &&
+                    strcmp(tp->call.class->system, group) == 0)
+                        return tp;
+        return NULL;
+}
+
+/* Unregister a trace_probe and probe_event: call with locking probe_lock */
+static void unregister_trace_probe(struct trace_probe *tp)
+{
+        if (probe_is_return(tp))
+                unregister_kretprobe(&tp->rp);
+        else
+                unregister_kprobe(&tp->rp.kp);
+        list_del(&tp->list);
+        unregister_probe_event(tp);
+}
+
+/* Register a trace_probe and probe_event */
+static int register_trace_probe(struct trace_probe *tp)
+{
+        struct trace_probe *old_tp;
+        int ret;
+
+        mutex_lock(&probe_lock);
+
+        /* register as an event */
+        old_tp = find_probe_event(tp->call.name, tp->call.class->system);
+        if (old_tp) {
+                /* delete old event */
+                unregister_trace_probe(old_tp);
+                free_trace_probe(old_tp);
+        }
+        ret = register_probe_event(tp);
+        if (ret) {
+                pr_warning("Failed to register probe event(%d)\n", ret);
+                goto end;
+        }
+
+        tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
+        if (probe_is_return(tp))
+                ret = register_kretprobe(&tp->rp);
+        else
+                ret = register_kprobe(&tp->rp.kp);
+
+        if (ret) {
+                pr_warning("Could not insert probe(%d)\n", ret);
+                if (ret == -EILSEQ) {
+                        pr_warning("Probing address(0x%p) is not an "
+                                   "instruction boundary.\n",
+                                   tp->rp.kp.addr);
+                        ret = -EINVAL;
+                }
+                unregister_probe_event(tp);
+        } else
+                list_add_tail(&tp->list, &probe_list);
+end:
+        mutex_unlock(&probe_lock);
+        return ret;
+}
+
+/* Split symbol and offset. */
+static int split_symbol_offset(char *symbol, unsigned long *offset)
+{
+        char *tmp;
+        int ret;
+
+        if (!offset)
+                return -EINVAL;
+
+        tmp = strchr(symbol, '+');
+        if (tmp) {
+                /* skip sign because strict_strtol doesn't accept '+' */
+                ret = strict_strtoul(tmp + 1, 0, offset);
+                if (ret)
+                        return ret;
+                *tmp = '\0';
+        } else
+                *offset = 0;
+        return 0;
+}
+
+#define PARAM_MAX_ARGS 16
+#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
+
+static int parse_probe_vars(char *arg, const struct fetch_type *t,
+                            struct fetch_param *f, int is_return)
+{
+        int ret = 0;
+        unsigned long param;
+
+        if (strcmp(arg, "retval") == 0) {
+                if (is_return)
+                        f->fn = t->fetch[FETCH_MTD_retval];
+                else
+                        ret = -EINVAL;
+        } else if (strncmp(arg, "stack", 5) == 0) {
+                if (arg[5] == '\0') {
+                        if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0)
+                                f->fn = fetch_stack_address;
+                        else
+                                ret = -EINVAL;
+                } else if (isdigit(arg[5])) {
+                        ret = strict_strtoul(arg + 5, 10, &param);
+                        if (ret || param > PARAM_MAX_STACK)
+                                ret = -EINVAL;
+                        else {
+                                f->fn = t->fetch[FETCH_MTD_stack];
+                                f->data = (void *)param;
+                        }
+                } else
+                        ret = -EINVAL;
+        } else
+                ret = -EINVAL;
+        return ret;
+}
+
+/* Recursive argument parser */
+static int __parse_probe_arg(char *arg, const struct fetch_type *t,
+                             struct fetch_param *f, int is_return)
+{
+        int ret = 0;
+        unsigned long param;
+        long offset;
+        char *tmp;
+
+        switch (arg[0]) {
+        case '$':
+                ret = parse_probe_vars(arg + 1, t, f, is_return);
+                break;
+        case '%':       /* named register */
+                ret = regs_query_register_offset(arg + 1);
+                if (ret >= 0) {
+                        f->fn = t->fetch[FETCH_MTD_reg];
+                        f->data = (void *)(unsigned long)ret;
+                        ret = 0;
+                }
+                break;
+        case '@':       /* memory or symbol */
+                if (isdigit(arg[1])) {
+                        ret = strict_strtoul(arg + 1, 0, &param);
+                        if (ret)
+                                break;
+                        f->fn = t->fetch[FETCH_MTD_memory];
+                        f->data = (void *)param;
+                } else {
+                        ret = split_symbol_offset(arg + 1, &offset);
+                        if (ret)
+                                break;
+                        f->data = alloc_symbol_cache(arg + 1, offset);
+                        if (f->data)
+                                f->fn = t->fetch[FETCH_MTD_symbol];
+                }
+                break;
+        case '+':       /* deref memory */
+        case '-':
+                tmp = strchr(arg, '(');
+                if (!tmp)
+                        break;
+                *tmp = '\0';
+                ret = strict_strtol(arg + 1, 0, &offset);
+                if (ret)
+                        break;
+                if (arg[0] == '-')
+                        offset = -offset;
+                arg = tmp + 1;
+                tmp = strrchr(arg, ')');
+                if (tmp) {
+                        struct deref_fetch_param *dprm;
+                        const struct fetch_type *t2 = find_fetch_type(NULL);
+                        *tmp = '\0';
+                        dprm = kzalloc(sizeof(struct deref_fetch_param),
+                                       GFP_KERNEL);
+                        if (!dprm)
+                                return -ENOMEM;
+                        dprm->offset = offset;
+                        ret = __parse_probe_arg(arg, t2, &dprm->orig,
+                                                is_return);
+                        if (ret)
+                                kfree(dprm);
+                        else {
+                                f->fn = t->fetch[FETCH_MTD_deref];
+                                f->data = (void *)dprm;
+                        }
+                }
+                break;
+        }
+        if (!ret && !f->fn) {   /* Parsed, but do not find fetch method */
+                pr_info("%s type has no corresponding fetch method.\n",
+                        t->name);
+                ret = -EINVAL;
+        }
+        return ret;
+}
+
+/* String length checking wrapper */
+static int parse_probe_arg(char *arg, struct trace_probe *tp,
+                           struct probe_arg *parg, int is_return)
+{
+        const char *t;
+        int ret;
+
+        if (strlen(arg) > MAX_ARGSTR_LEN) {
+                pr_info("Argument is too long.: %s\n",  arg);
+                return -ENOSPC;
+        }
+        parg->comm = kstrdup(arg, GFP_KERNEL);
+        if (!parg->comm) {
+                pr_info("Failed to allocate memory for command '%s'.\n", arg);
+                return -ENOMEM;
+        }
+        t = strchr(parg->comm, ':');
+        if (t) {
+                arg[t - parg->comm] = '\0';
+                t++;
+        }
+        parg->type = find_fetch_type(t);
+        if (!parg->type) {
+                pr_info("Unsupported type: %s\n", t);
+                return -EINVAL;
+        }
+        parg->offset = tp->size;
+        tp->size += parg->type->size;
+        ret = __parse_probe_arg(arg, parg->type, &parg->fetch, is_return);
+        if (ret >= 0) {
+                parg->fetch_size.fn = get_fetch_size_function(parg->type,
+                                                              parg->fetch.fn);
+                parg->fetch_size.data = parg->fetch.data;
+        }
+        return ret;
+}
+
+/* Return 1 if name is reserved or already used by another argument */
+static int conflict_field_name(const char *name,
+                               struct probe_arg *args, int narg)
+{
+        int i;
+        for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++)
+                if (strcmp(reserved_field_names[i], name) == 0)
+                        return 1;
+        for (i = 0; i < narg; i++)
+                if (strcmp(args[i].name, name) == 0)
+                        return 1;
+        return 0;
+}
+
+static int create_trace_probe(int argc, char **argv)
+{
+        /*
+         * Argument syntax:
+         *  - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS]
+         *  - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS]
+         * Fetch args:
+         *  $retval     : fetch return value
+         *  $stack      : fetch stack address
+         *  $stackN     : fetch Nth of stack (N:0-)
+         *  @ADDR       : fetch memory at ADDR (ADDR should be in kernel)
+         *  @SYM[+|-offs] : fetch memory at SYM +|- offs (SYM is a data symbol)
+         *  %REG        : fetch register REG
+         * Dereferencing memory fetch:
+         *  +|-offs(ARG) : fetch memory at ARG +|- offs address.
+         * Alias name of args:
+         *  NAME=FETCHARG : set NAME as alias of FETCHARG.
+         * Type of args:
+         *  FETCHARG:TYPE : use TYPE instead of unsigned long.
+         */
+        struct trace_probe *tp;
+        int i, ret = 0;
+        int is_return = 0, is_delete = 0;
+        char *symbol = NULL, *event = NULL, *group = NULL;
+        char *arg;
+        unsigned long offset = 0;
+        void *addr = NULL;
+        char buf[MAX_EVENT_NAME_LEN];
+
+        /* argc must be >= 1 */
+        if (argv[0][0] == 'p')
+                is_return = 0;
+        else if (argv[0][0] == 'r')
+                is_return = 1;
+        else if (argv[0][0] == '-')
+                is_delete = 1;
+        else {
+                pr_info("Probe definition must be started with 'p', 'r' or"
+                        " '-'.\n");
+                return -EINVAL;
+        }
+
+        if (argv[0][1] == ':') {
+                event = &argv[0][2];
+                if (strchr(event, '/')) {
+                        group = event;
+                        event = strchr(group, '/') + 1;
+                        event[-1] = '\0';
+                        if (strlen(group) == 0) {
+                                pr_info("Group name is not specified\n");
+                                return -EINVAL;
+                        }
+                }
+                if (strlen(event) == 0) {
+                        pr_info("Event name is not specified\n");
+                        return -EINVAL;
+                }
+        }
+        if (!group)
+                group = KPROBE_EVENT_SYSTEM;
+
+        if (is_delete) {
+                if (!event) {
+                        pr_info("Delete command needs an event name.\n");
+                        return -EINVAL;
+                }
+                mutex_lock(&probe_lock);
+                tp = find_probe_event(event, group);
+                if (!tp) {
+                        mutex_unlock(&probe_lock);
+                        pr_info("Event %s/%s doesn't exist.\n", group, event);
+                        return -ENOENT;
+                }
+                /* delete an event */
+                unregister_trace_probe(tp);
+                free_trace_probe(tp);
+                mutex_unlock(&probe_lock);
+                return 0;
+        }
+
+        if (argc < 2) {
+                pr_info("Probe point is not specified.\n");
+                return -EINVAL;
+        }
+        if (isdigit(argv[1][0])) {
+                if (is_return) {
+                        pr_info("Return probe point must be a symbol.\n");
+                        return -EINVAL;
+                }
+                /* an address specified */
+                ret = strict_strtoul(&argv[1][0], 0, (unsigned long *)&addr);
+                if (ret) {
+                        pr_info("Failed to parse address.\n");
+                        return ret;
+                }
+        } else {
+                /* a symbol specified */
+                symbol = argv[1];
+                /* TODO: support .init module functions */
+                ret = split_symbol_offset(symbol, &offset);
+                if (ret) {
+                        pr_info("Failed to parse symbol.\n");
+                        return ret;
+                }
+                if (offset && is_return) {
+                        pr_info("Return probe must be used without offset.\n");
+                        return -EINVAL;
+                }
+        }
+        argc -= 2; argv += 2;
+
+        /* setup a probe */
+        if (!event) {
+                /* Make a new event name */
+                if (symbol)
+                        snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_%ld",
+                                 is_return ? 'r' : 'p', symbol, offset);
+                else
+                        snprintf(buf, MAX_EVENT_NAME_LEN, "%c_0x%p",
+                                 is_return ? 'r' : 'p', addr);
+                event = buf;
+        }
+        tp = alloc_trace_probe(group, event, addr, symbol, offset, argc,
+                               is_return);
+        if (IS_ERR(tp)) {
+                pr_info("Failed to allocate trace_probe.(%d)\n",
+                        (int)PTR_ERR(tp));
+                return PTR_ERR(tp);
+        }
+
+        /* parse arguments */
+        ret = 0;
+        for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+                /* Increment count for freeing args in error case */
+                tp->nr_args++;
+
+                /* Parse argument name */
+                arg = strchr(argv[i], '=');
+                if (arg) {
+                        *arg++ = '\0';
+                        tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+                } else {
+                        arg = argv[i];
+                        /* If argument name is omitted, set "argN" */
+                        snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
+                        tp->args[i].name = kstrdup(buf, GFP_KERNEL);
+                }
+
+                if (!tp->args[i].name) {
+                        pr_info("Failed to allocate argument[%d] name.\n", i);
+                        ret = -ENOMEM;
+                        goto error;
+                }
+
+                if (!is_good_name(tp->args[i].name)) {
+                        pr_info("Invalid argument[%d] name: %s\n",
+                                i, tp->args[i].name);
+                        ret = -EINVAL;
+                        goto error;
+                }
+
+                if (conflict_field_name(tp->args[i].name, tp->args, i)) {
+                        pr_info("Argument[%d] name '%s' conflicts with "
+                                "another field.\n", i, argv[i]);
+                        ret = -EINVAL;
+                        goto error;
+                }
+
+                /* Parse fetch argument */
+                ret = parse_probe_arg(arg, tp, &tp->args[i], is_return);
+                if (ret) {
+                        pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
+                        goto error;
+                }
+        }
+
+        ret = register_trace_probe(tp);
+        if (ret)
+                goto error;
+        return 0;
+
+error:
+        free_trace_probe(tp);
+        return ret;
+}
+
+static void cleanup_all_probes(void)
+{
+        struct trace_probe *tp;
+
+        mutex_lock(&probe_lock);
+        /* TODO: Use batch unregistration */
+        while (!list_empty(&probe_list)) {
+                tp = list_entry(probe_list.next, struct trace_probe, list);
+                unregister_trace_probe(tp);
+                free_trace_probe(tp);
+        }
+        mutex_unlock(&probe_lock);
+}
+
+
+/* Probes listing interfaces */
+static void *probes_seq_start(struct seq_file *m, loff_t *pos)
+{
+        mutex_lock(&probe_lock);
+        return seq_list_start(&probe_list, *pos);
+}
+
+static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        return seq_list_next(v, &probe_list, pos);
+}
+
+static void probes_seq_stop(struct seq_file *m, void *v)
+{
+        mutex_unlock(&probe_lock);
+}
+
+static int probes_seq_show(struct seq_file *m, void *v)
+{
+        struct trace_probe *tp = v;
+        int i;
+
+        seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
+        seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
+
+        if (!tp->symbol)
+                seq_printf(m, " 0x%p", tp->rp.kp.addr);
+        else if (tp->rp.kp.offset)
+                seq_printf(m, " %s+%u", probe_symbol(tp), tp->rp.kp.offset);
+        else
+                seq_printf(m, " %s", probe_symbol(tp));
+
+        for (i = 0; i < tp->nr_args; i++)
+                seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm);
+        seq_printf(m, "\n");
+
+        return 0;
+}
+
+static const struct seq_operations probes_seq_op = {
+        .start  = probes_seq_start,
+        .next   = probes_seq_next,
+        .stop   = probes_seq_stop,
+        .show   = probes_seq_show
+};
+
+static int probes_open(struct inode *inode, struct file *file)
+{
+        if ((file->f_mode & FMODE_WRITE) &&
+            (file->f_flags & O_TRUNC))
+                cleanup_all_probes();
+
+        return seq_open(file, &probes_seq_op);
+}
+
+static int command_trace_probe(const char *buf)
+{
+        char **argv;
+        int argc = 0, ret = 0;
+
+        argv = argv_split(GFP_KERNEL, buf, &argc);
+        if (!argv)
+                return -ENOMEM;
+
+        if (argc)
+                ret = create_trace_probe(argc, argv);
+
+        argv_free(argv);
+        return ret;
+}
+
+#define WRITE_BUFSIZE 128
+
+static ssize_t probes_write(struct file *file, const char __user *buffer,
+                            size_t count, loff_t *ppos)
+{
+        char *kbuf, *tmp;
+        int ret;
+        size_t done;
+        size_t size;
+
+        kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
+        if (!kbuf)
+                return -ENOMEM;
+
+        ret = done = 0;
+        while (done < count) {
+                size = count - done;
+                if (size >= WRITE_BUFSIZE)
+                        size = WRITE_BUFSIZE - 1;
+                if (copy_from_user(kbuf, buffer + done, size)) {
+                        ret = -EFAULT;
+                        goto out;
+                }
+                kbuf[size] = '\0';
+                tmp = strchr(kbuf, '\n');
+                if (tmp) {
+                        *tmp = '\0';
+                        size = tmp - kbuf + 1;
+                } else if (done + size < count) {
+                        pr_warning("Line length is too long: "
+                                   "Should be less than %d.", WRITE_BUFSIZE);
+                        ret = -EINVAL;
+                        goto out;
+                }
+                done += size;
+                /* Remove comments */
+                tmp = strchr(kbuf, '#');
+                if (tmp)
+                        *tmp = '\0';
+
+                ret = command_trace_probe(kbuf);
+                if (ret)
+                        goto out;
+        }
+        ret = done;
+out:
+        kfree(kbuf);
+        return ret;
+}
+
+static const struct file_operations kprobe_events_ops = {
+        .owner          = THIS_MODULE,
+        .open           = probes_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+        .write          = probes_write,
+};
+
+/* Probes profiling interfaces */
+static int probes_profile_seq_show(struct seq_file *m, void *v)
+{
+        struct trace_probe *tp = v;
+
+        seq_printf(m, "  %-44s %15lu %15lu\n", tp->call.name, tp->nhit,
+                   tp->rp.kp.nmissed);
+
+        return 0;
+}
+
+static const struct seq_operations profile_seq_op = {
+        .start  = probes_seq_start,
+        .next   = probes_seq_next,
+        .stop   = probes_seq_stop,
+        .show   = probes_profile_seq_show
+};
+
+static int profile_open(struct inode *inode, struct file *file)
+{
+        return seq_open(file, &profile_seq_op);
+}
+
+static const struct file_operations kprobe_profile_ops = {
+        .owner          = THIS_MODULE,
+        .open           = profile_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
+
+/* Sum up total data length for dynamic arraies (strings) */
+static __kprobes int __get_data_size(struct trace_probe *tp,
+                                     struct pt_regs *regs)
+{
+        int i, ret = 0;
+        u32 len;
+
+        for (i = 0; i < tp->nr_args; i++)
+                if (unlikely(tp->args[i].fetch_size.fn)) {
+                        call_fetch(&tp->args[i].fetch_size, regs, &len);
+                        ret += len;
+                }
+
+        return ret;
+}
+
+/* Store the value of each argument */
+static __kprobes void store_trace_args(int ent_size, struct trace_probe *tp,
+                                       struct pt_regs *regs,
+                                       u8 *data, int maxlen)
+{
+        int i;
+        u32 end = tp->size;
+        u32 *dl;        /* Data (relative) location */
+
+        for (i = 0; i < tp->nr_args; i++) {
+                if (unlikely(tp->args[i].fetch_size.fn)) {
+                        /*
+                         * First, we set the relative location and
+                         * maximum data length to *dl
+                         */
+                        dl = (u32 *)(data + tp->args[i].offset);
+                        *dl = make_data_rloc(maxlen, end - tp->args[i].offset);
+                        /* Then try to fetch string or dynamic array data */
+                        call_fetch(&tp->args[i].fetch, regs, dl);
+                        /* Reduce maximum length */
+                        end += get_rloc_len(*dl);
+                        maxlen -= get_rloc_len(*dl);
+                        /* Trick here, convert data_rloc to data_loc */
+                        *dl = convert_rloc_to_loc(*dl,
+                                 ent_size + tp->args[i].offset);
+                } else
+                        /* Just fetching data normally */
+                        call_fetch(&tp->args[i].fetch, regs,
+                                   data + tp->args[i].offset);
+        }
+}
+
+/* Kprobe handler */
+static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+        struct kprobe_trace_entry_head *entry;
+        struct ring_buffer_event *event;
+        struct ring_buffer *buffer;
+        int size, dsize, pc;
+        unsigned long irq_flags;
+        struct ftrace_event_call *call = &tp->call;
+
+        tp->nhit++;
+
+        local_save_flags(irq_flags);
+        pc = preempt_count();
+
+        dsize = __get_data_size(tp, regs);
+        size = sizeof(*entry) + tp->size + dsize;
+
+        event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+                                                  size, irq_flags, pc);
+        if (!event)
+                return;
+
+        entry = ring_buffer_event_data(event);
+        entry->ip = (unsigned long)kp->addr;
+        store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+
+        if (!filter_current_check_discard(buffer, call, entry, event))
+                trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+}
+
+/* Kretprobe handler */
+static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
+                                          struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+        struct kretprobe_trace_entry_head *entry;
+        struct ring_buffer_event *event;
+        struct ring_buffer *buffer;
+        int size, pc, dsize;
+        unsigned long irq_flags;
+        struct ftrace_event_call *call = &tp->call;
+
+        local_save_flags(irq_flags);
+        pc = preempt_count();
+
+        dsize = __get_data_size(tp, regs);
+        size = sizeof(*entry) + tp->size + dsize;
+
+        event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+                                                  size, irq_flags, pc);
+        if (!event)
+                return;
+
+        entry = ring_buffer_event_data(event);
+        entry->func = (unsigned long)tp->rp.kp.addr;
+        entry->ret_ip = (unsigned long)ri->ret_addr;
+        store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+
+        if (!filter_current_check_discard(buffer, call, entry, event))
+                trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+}
+
+/* Event entry printers */
+enum print_line_t
+print_kprobe_event(struct trace_iterator *iter, int flags,
+                   struct trace_event *event)
+{
+        struct kprobe_trace_entry_head *field;
+        struct trace_seq *s = &iter->seq;
+        struct trace_probe *tp;
+        u8 *data;
+        int i;
+
+        field = (struct kprobe_trace_entry_head *)iter->ent;
+        tp = container_of(event, struct trace_probe, call.event);
+
+        if (!trace_seq_printf(s, "%s: (", tp->call.name))
+                goto partial;
+
+        if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
+                goto partial;
+
+        if (!trace_seq_puts(s, ")"))
+                goto partial;
+
+        data = (u8 *)&field[1];
+        for (i = 0; i < tp->nr_args; i++)
+                if (!tp->args[i].type->print(s, tp->args[i].name,
+                                             data + tp->args[i].offset, field))
+                        goto partial;
+
+        if (!trace_seq_puts(s, "\n"))
+                goto partial;
+
+        return TRACE_TYPE_HANDLED;
+partial:
+        return TRACE_TYPE_PARTIAL_LINE;
+}
+
+enum print_line_t
+print_kretprobe_event(struct trace_iterator *iter, int flags,
+                      struct trace_event *event)
+{
+        struct kretprobe_trace_entry_head *field;
+        struct trace_seq *s = &iter->seq;
+        struct trace_probe *tp;
+        u8 *data;
+        int i;
+
+        field = (struct kretprobe_trace_entry_head *)iter->ent;
+        tp = container_of(event, struct trace_probe, call.event);
+
+        if (!trace_seq_printf(s, "%s: (", tp->call.name))
+                goto partial;
+
+        if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET))
+                goto partial;
+
+        if (!trace_seq_puts(s, " <- "))
+                goto partial;
+
+        if (!seq_print_ip_sym(s, field->func, flags & ~TRACE_ITER_SYM_OFFSET))
+                goto partial;
+
+        if (!trace_seq_puts(s, ")"))
+                goto partial;
+
+        data = (u8 *)&field[1];
+        for (i = 0; i < tp->nr_args; i++)
+                if (!tp->args[i].type->print(s, tp->args[i].name,
+                                             data + tp->args[i].offset, field))
+                        goto partial;
+
+        if (!trace_seq_puts(s, "\n"))
+                goto partial;
+
+        return TRACE_TYPE_HANDLED;
+partial:
+        return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static int probe_event_enable(struct ftrace_event_call *call)
+{
+        struct trace_probe *tp = (struct trace_probe *)call->data;
+
+        tp->flags |= TP_FLAG_TRACE;
+        if (probe_is_return(tp))
+                return enable_kretprobe(&tp->rp);
+        else
+                return enable_kprobe(&tp->rp.kp);
+}
+
+static void probe_event_disable(struct ftrace_event_call *call)
+{
+        struct trace_probe *tp = (struct trace_probe *)call->data;
+
+        tp->flags &= ~TP_FLAG_TRACE;
+        if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) {
+                if (probe_is_return(tp))
+                        disable_kretprobe(&tp->rp);
+                else
+                        disable_kprobe(&tp->rp.kp);
+        }
+}
+
+#undef DEFINE_FIELD
+#define DEFINE_FIELD(type, item, name, is_signed)                       \
+        do {                                                            \
+                ret = trace_define_field(event_call, #type, name,       \
+                                         offsetof(typeof(field), item), \
+                                         sizeof(field.item), is_signed, \
+                                         FILTER_OTHER);                 \
+                if (ret)                                                \
+                        return ret;                                     \
+        } while (0)
+
+static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+        int ret, i;
+        struct kprobe_trace_entry_head field;
+        struct trace_probe *tp = (struct trace_probe *)event_call->data;
+
+        DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+        /* Set argument names as fields */
+        for (i = 0; i < tp->nr_args; i++) {
+                ret = trace_define_field(event_call, tp->args[i].type->fmttype,
+                                         tp->args[i].name,
+                                         sizeof(field) + tp->args[i].offset,
+                                         tp->args[i].type->size,
+                                         tp->args[i].type->is_signed,
+                                         FILTER_OTHER);
+                if (ret)
+                        return ret;
+        }
+        return 0;
+}
+
+static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+        int ret, i;
+        struct kretprobe_trace_entry_head field;
+        struct trace_probe *tp = (struct trace_probe *)event_call->data;
+
+        DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
+        DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
+        /* Set argument names as fields */
+        for (i = 0; i < tp->nr_args; i++) {
+                ret = trace_define_field(event_call, tp->args[i].type->fmttype,
+                                         tp->args[i].name,
+                                         sizeof(field) + tp->args[i].offset,
+                                         tp->args[i].type->size,
+                                         tp->args[i].type->is_signed,
+                                         FILTER_OTHER);
+                if (ret)
+                        return ret;
+        }
+        return 0;
+}
+
+static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
+{
+        int i;
+        int pos = 0;
+
+        const char *fmt, *arg;
+
+        if (!probe_is_return(tp)) {
+                fmt = "(%lx)";
+                arg = "REC->" FIELD_STRING_IP;
+        } else {
+                fmt = "(%lx <- %lx)";
+                arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+        }
+
+        /* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+        pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
+
+        for (i = 0; i < tp->nr_args; i++) {
+                pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
+                                tp->args[i].name, tp->args[i].type->fmt);
+        }
+
+        pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
+
+        for (i = 0; i < tp->nr_args; i++) {
+                if (strcmp(tp->args[i].type->name, "string") == 0)
+                        pos += snprintf(buf + pos, LEN_OR_ZERO,
+                                        ", __get_str(%s)",
+                                        tp->args[i].name);
+                else
+                        pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+                                        tp->args[i].name);
+        }
+
+#undef LEN_OR_ZERO
+
+        /* return the length of print_fmt */
+        return pos;
+}
+
+static int set_print_fmt(struct trace_probe *tp)
+{
+        int len;
+        char *print_fmt;
+
+        /* First: called with 0 length to calculate the needed length */
+        len = __set_print_fmt(tp, NULL, 0);
+        print_fmt = kmalloc(len + 1, GFP_KERNEL);
+        if (!print_fmt)
+                return -ENOMEM;
+
+        /* Second: actually write the @print_fmt */
+        __set_print_fmt(tp, print_fmt, len + 1);
+        tp->call.print_fmt = print_fmt;
+
+        return 0;
+}
+
+#ifdef CONFIG_PERF_EVENTS
+
+/* Kprobe profile handler */
+static __kprobes void kprobe_perf_func(struct kprobe *kp,
+                                         struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+        struct ftrace_event_call *call = &tp->call;
+        struct kprobe_trace_entry_head *entry;
+        struct hlist_head *head;
+        int size, __size, dsize;
+        int rctx;
+
+        dsize = __get_data_size(tp, regs);
+        __size = sizeof(*entry) + tp->size + dsize;
+        size = ALIGN(__size + sizeof(u32), sizeof(u64));
+        size -= sizeof(u32);
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+                     "profile buffer not large enough"))
+                return;
+
+        entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+        if (!entry)
+                return;
+
+        entry->ip = (unsigned long)kp->addr;
+        memset(&entry[1], 0, dsize);
+        store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+
+        head = this_cpu_ptr(call->perf_events);
+        perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
+}
+
+/* Kretprobe profile handler */
+static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
+                                            struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+        struct ftrace_event_call *call = &tp->call;
+        struct kretprobe_trace_entry_head *entry;
+        struct hlist_head *head;
+        int size, __size, dsize;
+        int rctx;
+
+        dsize = __get_data_size(tp, regs);
+        __size = sizeof(*entry) + tp->size + dsize;
+        size = ALIGN(__size + sizeof(u32), sizeof(u64));
+        size -= sizeof(u32);
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+                     "profile buffer not large enough"))
+                return;
+
+        entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+        if (!entry)
+                return;
+
+        entry->func = (unsigned long)tp->rp.kp.addr;
+        entry->ret_ip = (unsigned long)ri->ret_addr;
+        store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
+
+        head = this_cpu_ptr(call->perf_events);
+        perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
+}
+
+static int probe_perf_enable(struct ftrace_event_call *call)
+{
+        struct trace_probe *tp = (struct trace_probe *)call->data;
+
+        tp->flags |= TP_FLAG_PROFILE;
+
+        if (probe_is_return(tp))
+                return enable_kretprobe(&tp->rp);
+        else
+                return enable_kprobe(&tp->rp.kp);
+}
+
+static void probe_perf_disable(struct ftrace_event_call *call)
+{
+        struct trace_probe *tp = (struct trace_probe *)call->data;
+
+        tp->flags &= ~TP_FLAG_PROFILE;
+
+        if (!(tp->flags & TP_FLAG_TRACE)) {
+                if (probe_is_return(tp))
+                        disable_kretprobe(&tp->rp);
+                else
+                        disable_kprobe(&tp->rp.kp);
+        }
+}
+#endif  /* CONFIG_PERF_EVENTS */
+
+static __kprobes
+int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
+{
+        switch (type) {
+        case TRACE_REG_REGISTER:
+                return probe_event_enable(event);
+        case TRACE_REG_UNREGISTER:
+                probe_event_disable(event);
+                return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+        case TRACE_REG_PERF_REGISTER:
+                return probe_perf_enable(event);
+        case TRACE_REG_PERF_UNREGISTER:
+                probe_perf_disable(event);
+                return 0;
+#endif
+        }
+        return 0;
+}
+
+static __kprobes
+int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
+
+        if (tp->flags & TP_FLAG_TRACE)
+                kprobe_trace_func(kp, regs);
+#ifdef CONFIG_PERF_EVENTS
+        if (tp->flags & TP_FLAG_PROFILE)
+                kprobe_perf_func(kp, regs);
+#endif
+        return 0;       /* We don't tweek kernel, so just return 0 */
+}
+
+static __kprobes
+int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+        struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
+
+        if (tp->flags & TP_FLAG_TRACE)
+                kretprobe_trace_func(ri, regs);
+#ifdef CONFIG_PERF_EVENTS
+        if (tp->flags & TP_FLAG_PROFILE)
+                kretprobe_perf_func(ri, regs);
+#endif
+        return 0;       /* We don't tweek kernel, so just return 0 */
+}
+
+static struct trace_event_functions kretprobe_funcs = {
+        .trace          = print_kretprobe_event
+};
+
+static struct trace_event_functions kprobe_funcs = {
+        .trace          = print_kprobe_event
+};
+
+static int register_probe_event(struct trace_probe *tp)
+{
+        struct ftrace_event_call *call = &tp->call;
+        int ret;
+
+        /* Initialize ftrace_event_call */
+        INIT_LIST_HEAD(&call->class->fields);
+        if (probe_is_return(tp)) {
+                call->event.funcs = &kretprobe_funcs;
+                call->class->define_fields = kretprobe_event_define_fields;
+        } else {
+                call->event.funcs = &kprobe_funcs;
+                call->class->define_fields = kprobe_event_define_fields;
+        }
+        if (set_print_fmt(tp) < 0)
+                return -ENOMEM;
+        ret = register_ftrace_event(&call->event);
+        if (!ret) {
+                kfree(call->print_fmt);
+                return -ENODEV;
+        }
+        call->flags = 0;
+        call->class->reg = kprobe_register;
+        call->data = tp;
+        ret = trace_add_event_call(call);
+        if (ret) {
+                pr_info("Failed to register kprobe event: %s\n", call->name);
+                kfree(call->print_fmt);
+                unregister_ftrace_event(&call->event);
+        }
+        return ret;
+}
+
+static void unregister_probe_event(struct trace_probe *tp)
+{
+        /* tp->event is unregistered in trace_remove_event_call() */
+        trace_remove_event_call(&tp->call);
+        kfree(tp->call.print_fmt);
+}
+
+/* Make a debugfs interface for controling probe points */
+static __init int init_kprobe_trace(void)
+{
+        struct dentry *d_tracer;
+        struct dentry *entry;
+
+        d_tracer = tracing_init_dentry();
+        if (!d_tracer)
+                return 0;
+
+        entry = debugfs_create_file("kprobe_events", 0644, d_tracer,
+                                    NULL, &kprobe_events_ops);
+
+        /* Event list interface */
+        if (!entry)
+                pr_warning("Could not create debugfs "
+                           "'kprobe_events' entry\n");
+
+        /* Profile interface */
+        entry = debugfs_create_file("kprobe_profile", 0444, d_tracer,
+                                    NULL, &kprobe_profile_ops);
+
+        if (!entry)
+                pr_warning("Could not create debugfs "
+                           "'kprobe_profile' entry\n");
+        return 0;
+}
+fs_initcall(init_kprobe_trace);
+
+
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+
+static int kprobe_trace_selftest_target(int a1, int a2, int a3,
+                                        int a4, int a5, int a6)
+{
+        return a1 + a2 + a3 + a4 + a5 + a6;
+}
+
+static __init int kprobe_trace_self_tests_init(void)
+{
+        int ret, warn = 0;
+        int (*target)(int, int, int, int, int, int);
+        struct trace_probe *tp;
+
+        target = kprobe_trace_selftest_target;
+
+        pr_info("Testing kprobe tracing: ");
+
+        ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target "
+                                  "$stack $stack0 +0($stack)");
+        if (WARN_ON_ONCE(ret)) {
+                pr_warning("error on probing function entry.\n");
+                warn++;
+        } else {
+                /* Enable trace point */
+                tp = find_probe_event("testprobe", KPROBE_EVENT_SYSTEM);
+                if (WARN_ON_ONCE(tp == NULL)) {
+                        pr_warning("error on getting new probe.\n");
+                        warn++;
+                } else
+                        probe_event_enable(&tp->call);
+        }
+
+        ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
+                                  "$retval");
+        if (WARN_ON_ONCE(ret)) {
+                pr_warning("error on probing function return.\n");
+                warn++;
+        } else {
+                /* Enable trace point */
+                tp = find_probe_event("testprobe2", KPROBE_EVENT_SYSTEM);
+                if (WARN_ON_ONCE(tp == NULL)) {
+                        pr_warning("error on getting new probe.\n");
+                        warn++;
+                } else
+                        probe_event_enable(&tp->call);
+        }
+
+        if (warn)
+                goto end;
+
+        ret = target(1, 2, 3, 4, 5, 6);
+
+        ret = command_trace_probe("-:testprobe");
+        if (WARN_ON_ONCE(ret)) {
+                pr_warning("error on deleting a probe.\n");
+                warn++;
+        }
+
+        ret = command_trace_probe("-:testprobe2");
+        if (WARN_ON_ONCE(ret)) {
+                pr_warning("error on deleting a probe.\n");
+                warn++;
+        }
+
+end:
+        cleanup_all_probes();
+        if (warn)
+                pr_cont("NG: Some tests are failed. Please check them.\n");
+        else
+                pr_cont("OK\n");
+        return 0;
+}
+
+late_initcall(kprobe_trace_self_tests_init);
+
+#endif
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index d53b45ed0806..017fa376505d 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/mmiotrace.h>
 #include <linux/pci.h>
+#include <linux/slab.h>
 #include <linux/time.h>
 
 #include <asm/atomic.h>
@@ -307,11 +308,13 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
                                 struct trace_array_cpu *data,
                                 struct mmiotrace_rw *rw)
 {
+        struct ftrace_event_call *call = &event_mmiotrace_rw;
+        struct ring_buffer *buffer = tr->buffer;
         struct ring_buffer_event *event;
         struct trace_mmiotrace_rw *entry;
         int pc = preempt_count();
 
-        event = trace_buffer_lock_reserve(tr, TRACE_MMIO_RW,
+        event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_RW,
                                           sizeof(*entry), 0, pc);
         if (!event) {
                 atomic_inc(&dropped_count);
@@ -319,7 +322,9 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
         }
         entry   = ring_buffer_event_data(event);
         entry->rw                       = *rw;
-        trace_buffer_unlock_commit(tr, event, 0, pc);
+
+        if (!filter_check_discard(call, entry, buffer, event))
+                trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
 void mmio_trace_rw(struct mmiotrace_rw *rw)
@@ -333,11 +338,13 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
                                 struct trace_array_cpu *data,
                                 struct mmiotrace_map *map)
 {
+        struct ftrace_event_call *call = &event_mmiotrace_map;
+        struct ring_buffer *buffer = tr->buffer;
         struct ring_buffer_event *event;
         struct trace_mmiotrace_map *entry;
         int pc = preempt_count();
 
-        event = trace_buffer_lock_reserve(tr, TRACE_MMIO_MAP,
+        event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_MAP,
                                           sizeof(*entry), 0, pc);
         if (!event) {
                 atomic_inc(&dropped_count);
@@ -345,7 +352,9 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
         }
         entry   = ring_buffer_event_data(event);
         entry->map                      = *map;
-        trace_buffer_unlock_commit(tr, event, 0, pc);
+
+        if (!filter_check_discard(call, entry, buffer, event))
+                trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
 void mmio_trace_mapping(struct mmiotrace_map *map)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 7938f3ae93e3..02272baa2206 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -16,21 +16,25 @@
 
 DECLARE_RWSEM(trace_event_mutex);
 
-DEFINE_PER_CPU(struct trace_seq, ftrace_event_seq);
-EXPORT_PER_CPU_SYMBOL(ftrace_event_seq);
-
 static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
 static int next_event_type = __TRACE_LAST_TYPE + 1;
 
-void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+int trace_print_seq(struct seq_file *m, struct trace_seq *s)
 {
         int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
+        int ret;
 
-        s->buffer[len] = 0;
-        seq_puts(m, s->buffer);
+        ret = seq_write(m, s->buffer, len);
 
-        trace_seq_init(s);
+        /*
+         * Only reset this buffer if we successfully wrote to the
+         * seq_file buffer.
+         */
+        if (!ret)
+                trace_seq_init(s);
+
+        return ret;
 }
 
 enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
@@ -70,6 +74,9 @@ enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter)
  * @s: trace sequence descriptor
  * @fmt: printf format string
  *
+ * It returns 0 if the trace oversizes the buffer's free
+ * space, 1 otherwise.
+ *
  * The tracer may use either sequence operations or its own
  * copy to user routines. To simplify formating of a trace
  * trace_seq_printf is used to store strings into a special
@@ -83,7 +90,7 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
         va_list ap;
         int ret;
 
-        if (!len)
+        if (s->full || !len)
                 return 0;
 
         va_start(ap, fmt);
@@ -91,12 +98,14 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
         va_end(ap);
 
         /* If we can't write it all, don't bother writing anything */
-        if (ret >= len)
+        if (ret >= len) {
+                s->full = 1;
                 return 0;
+        }
 
         s->len += ret;
 
-        return len;
+        return 1;
 }
 EXPORT_SYMBOL_GPL(trace_seq_printf);
 
@@ -117,14 +126,16 @@ trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
         int len = (PAGE_SIZE - 1) - s->len;
         int ret;
 
-        if (!len)
+        if (s->full || !len)
                 return 0;
 
         ret = vsnprintf(s->buffer + s->len, len, fmt, args);
 
         /* If we can't write it all, don't bother writing anything */
-        if (ret >= len)
+        if (ret >= len) {
+                s->full = 1;
                 return 0;
+        }
 
         s->len += ret;
 
@@ -137,14 +148,16 @@ int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
         int len = (PAGE_SIZE - 1) - s->len;
         int ret;
 
-        if (!len)
+        if (s->full || !len)
                 return 0;
 
         ret = bstr_printf(s->buffer + s->len, len, fmt, binary);
 
         /* If we can't write it all, don't bother writing anything */
-        if (ret >= len)
+        if (ret >= len) {
+                s->full = 1;
                 return 0;
+        }
 
         s->len += ret;
 
@@ -165,9 +178,14 @@ int trace_seq_puts(struct trace_seq *s, const char *str)
 {
         int len = strlen(str);
 
-        if (len > ((PAGE_SIZE - 1) - s->len))
+        if (s->full)
                 return 0;
 
+        if (len > ((PAGE_SIZE - 1) - s->len)) {
+                s->full = 1;
+                return 0;
+        }
+
         memcpy(s->buffer + s->len, str, len);
         s->len += len;
 
@@ -176,19 +194,30 @@ int trace_seq_puts(struct trace_seq *s, const char *str)
 
 int trace_seq_putc(struct trace_seq *s, unsigned char c)
 {
-        if (s->len >= (PAGE_SIZE - 1))
+        if (s->full)
+                return 0;
+
+        if (s->len >= (PAGE_SIZE - 1)) {
+                s->full = 1;
                 return 0;
+        }
 
         s->buffer[s->len++] = c;
 
         return 1;
 }
+EXPORT_SYMBOL(trace_seq_putc);
 
 int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
 {
-        if (len > ((PAGE_SIZE - 1) - s->len))
+        if (s->full)
                 return 0;
 
+        if (len > ((PAGE_SIZE - 1) - s->len)) {
+                s->full = 1;
+                return 0;
+        }
+
         memcpy(s->buffer + s->len, mem, len);
         s->len += len;
 
@@ -201,6 +230,9 @@ int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, size_t len)
         const unsigned char *data = mem;
         int i, j;
 
+        if (s->full)
+                return 0;
+
 #ifdef __BIG_ENDIAN
         for (i = 0, j = 0; i < len; i++) {
 #else
@@ -218,9 +250,14 @@ void *trace_seq_reserve(struct trace_seq *s, size_t len)
 {
         void *ret;
 
-        if (len > ((PAGE_SIZE - 1) - s->len))
+        if (s->full)
                 return NULL;
 
+        if (len > ((PAGE_SIZE - 1) - s->len)) {
+                s->full = 1;
+                return NULL;
+        }
+
         ret = s->buffer + s->len;
         s->len += len;
 
@@ -231,8 +268,14 @@ int trace_seq_path(struct trace_seq *s, struct path *path)
 {
         unsigned char *p;
 
-        if (s->len >= (PAGE_SIZE - 1))
+        if (s->full)
+                return 0;
+
+        if (s->len >= (PAGE_SIZE - 1)) {
+                s->full = 1;
                 return 0;
+        }
+
         p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
         if (!IS_ERR(p)) {
                 p = mangle_path(s->buffer + s->len, p, "\n");
@@ -245,6 +288,7 @@ int trace_seq_path(struct trace_seq *s, struct path *path)
                 return 1;
         }
 
+        s->full = 1;
         return 0;
 }
 
@@ -309,6 +353,21 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 }
 EXPORT_SYMBOL(ftrace_print_symbols_seq);
 
+const char *
+ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
+{
+        int i;
+        const char *ret = p->buffer + p->len;
+
+        for (i = 0; i < buf_len; i++)
+                trace_seq_printf(p, "%s%2.2x", i == 0 ? "" : " ", buf[i]);
+
+        trace_seq_putc(p, 0);
+
+        return ret;
+}
+EXPORT_SYMBOL(ftrace_print_hex_seq);
+
 #ifdef CONFIG_KRETPROBES
 static inline const char *kretprobed(const char *name)
 {
@@ -371,6 +430,9 @@ int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
         unsigned long vmstart = 0;
         int ret = 1;
 
+        if (s->full)
+                return 0;
+
         if (mm) {
                 const struct vm_area_struct *vma;
 
@@ -408,7 +470,7 @@ seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
                  * since individual threads might have already quit!
                  */
                 rcu_read_lock();
-                task = find_task_by_vpid(entry->ent.tgid);
+                task = find_task_by_vpid(entry->tgid);
                 if (task)
                         mm = get_task_mm(task);
                 rcu_read_unlock();
@@ -461,18 +523,23 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
         return ret;
 }
 
-static int
-lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
+/**
+ * trace_print_lat_fmt - print the irq, preempt and lockdep fields
+ * @s: trace seq struct to write to
+ * @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.
+ */
+int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 {
         int hardirq, softirq;
-        char comm[TASK_COMM_LEN];
+        int ret;
 
-        trace_find_cmdline(entry->pid, comm);
         hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
         softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
 
-        if (!trace_seq_printf(s, "%8.8s-%-5d %3d%c%c%c",
-                              comm, entry->pid, cpu,
+        if (!trace_seq_printf(s, "%c%c%c",
                               (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
                                 (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ?
                                   'X' : '.',
@@ -483,8 +550,31 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
                 return 0;
 
         if (entry->preempt_count)
-                return trace_seq_printf(s, "%x", entry->preempt_count);
-        return trace_seq_puts(s, ".");
+                ret = trace_seq_printf(s, "%x", entry->preempt_count);
+        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);
+}
+
+static int
+lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
+{
+        char comm[TASK_COMM_LEN];
+
+        trace_find_cmdline(entry->pid, comm);
+
+        if (!trace_seq_printf(s, "%8.8s-%-5d %3d",
+                              comm, entry->pid, cpu))
+                return 0;
+
+        return trace_print_lat_fmt(s, entry);
 }
 
 static unsigned long preempt_mark_thresh = 100;
@@ -649,6 +739,9 @@ int register_ftrace_event(struct trace_event *event)
         if (WARN_ON(!event))
                 goto out;
 
+        if (WARN_ON(!event->funcs))
+                goto out;
+
         INIT_LIST_HEAD(&event->list);
 
         if (!event->type) {
@@ -681,14 +774,14 @@ int register_ftrace_event(struct trace_event *event)
                         goto out;
         }
 
-        if (event->trace == NULL)
-                event->trace = trace_nop_print;
-        if (event->raw == NULL)
-                event->raw = trace_nop_print;
-        if (event->hex == NULL)
-                event->hex = trace_nop_print;
-        if (event->binary == NULL)
-                event->binary = trace_nop_print;
+        if (event->funcs->trace == NULL)
+                event->funcs->trace = trace_nop_print;
+        if (event->funcs->raw == NULL)
+                event->funcs->raw = trace_nop_print;
+        if (event->funcs->hex == NULL)
+                event->funcs->hex = trace_nop_print;
+        if (event->funcs->binary == NULL)
+                event->funcs->binary = trace_nop_print;
 
         key = event->type & (EVENT_HASHSIZE - 1);
 
@@ -730,13 +823,15 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_event);
  * Standard events
  */
 
-enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags)
+enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags,
+                                  struct trace_event *event)
 {
         return TRACE_TYPE_HANDLED;
 }
 
 /* TRACE_FN */
-static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags,
+                                        struct trace_event *event)
 {
         struct ftrace_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -763,7 +858,8 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags,
+                                      struct trace_event *event)
 {
         struct ftrace_entry *field;
 
@@ -777,7 +873,8 @@ static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags,
+                                      struct trace_event *event)
 {
         struct ftrace_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -790,7 +887,8 @@ static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags,
+                                      struct trace_event *event)
 {
         struct ftrace_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -803,14 +901,18 @@ static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_HANDLED;
 }
 
-static struct trace_event trace_fn_event = {
-        .type           = TRACE_FN,
+static struct trace_event_functions trace_fn_funcs = {
         .trace          = trace_fn_trace,
         .raw            = trace_fn_raw,
         .hex            = trace_fn_hex,
         .binary         = trace_fn_bin,
 };
 
+static struct trace_event trace_fn_event = {
+        .type           = TRACE_FN,
+        .funcs          = &trace_fn_funcs,
+};
+
 /* TRACE_CTX an TRACE_WAKE */
 static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
                                              char *delim)
@@ -839,13 +941,14 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
         return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags,
+                                         struct trace_event *event)
 {
         return trace_ctxwake_print(iter, "==>");
 }
 
 static enum print_line_t trace_wake_print(struct trace_iterator *iter,
-                                          int flags)
+                                          int flags, struct trace_event *event)
 {
         return trace_ctxwake_print(iter, "  +");
 }
@@ -858,7 +961,7 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S)
         trace_assign_type(field, iter->ent);
 
         if (!S)
-                task_state_char(field->prev_state);
+                S = task_state_char(field->prev_state);
         T = task_state_char(field->next_state);
         if (!trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n",
                               field->prev_pid,
@@ -873,12 +976,14 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S)
         return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags,
+                                       struct trace_event *event)
 {
         return trace_ctxwake_raw(iter, 0);
 }
 
-static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags,
+                                        struct trace_event *event)
 {
         return trace_ctxwake_raw(iter, '+');
 }
@@ -893,7 +998,7 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S)
         trace_assign_type(field, iter->ent);
 
         if (!S)
-                task_state_char(field->prev_state);
+                S = task_state_char(field->prev_state);
         T = task_state_char(field->next_state);
 
         SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid);
@@ -907,18 +1012,20 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S)
         return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags,
+                                       struct trace_event *event)
 {
         return trace_ctxwake_hex(iter, 0);
 }
 
-static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags,
+                                        struct trace_event *event)
 {
         return trace_ctxwake_hex(iter, '+');
 }
 
 static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter,
-                                           int flags)
+                                           int flags, struct trace_event *event)
 {
         struct ctx_switch_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -935,81 +1042,34 @@ static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter,
         return TRACE_TYPE_HANDLED;
 }
 
-static struct trace_event trace_ctx_event = {
-        .type           = TRACE_CTX,
+static struct trace_event_functions trace_ctx_funcs = {
         .trace          = trace_ctx_print,
         .raw            = trace_ctx_raw,
         .hex            = trace_ctx_hex,
         .binary         = trace_ctxwake_bin,
 };
 
-static struct trace_event trace_wake_event = {
-        .type           = TRACE_WAKE,
+static struct trace_event trace_ctx_event = {
+        .type           = TRACE_CTX,
+        .funcs          = &trace_ctx_funcs,
+};
+
+static struct trace_event_functions trace_wake_funcs = {
         .trace          = trace_wake_print,
         .raw            = trace_wake_raw,
         .hex            = trace_wake_hex,
         .binary         = trace_ctxwake_bin,
 };
 
-/* TRACE_SPECIAL */
-static enum print_line_t trace_special_print(struct trace_iterator *iter,
-                                             int flags)
-{
-        struct special_entry *field;
-
-        trace_assign_type(field, iter->ent);
-
-        if (!trace_seq_printf(&iter->seq, "# %ld %ld %ld\n",
-                              field->arg1,
-                              field->arg2,
-                              field->arg3))
-                return TRACE_TYPE_PARTIAL_LINE;
-
-        return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t trace_special_hex(struct trace_iterator *iter,
-                                           int flags)
-{
-        struct special_entry *field;
-        struct trace_seq *s = &iter->seq;
-
-        trace_assign_type(field, iter->ent);
-
-        SEQ_PUT_HEX_FIELD_RET(s, field->arg1);
-        SEQ_PUT_HEX_FIELD_RET(s, field->arg2);
-        SEQ_PUT_HEX_FIELD_RET(s, field->arg3);
-
-        return TRACE_TYPE_HANDLED;
-}
-
-static enum print_line_t trace_special_bin(struct trace_iterator *iter,
-                                           int flags)
-{
-        struct special_entry *field;
-        struct trace_seq *s = &iter->seq;
-
-        trace_assign_type(field, iter->ent);
-
-        SEQ_PUT_FIELD_RET(s, field->arg1);
-        SEQ_PUT_FIELD_RET(s, field->arg2);
-        SEQ_PUT_FIELD_RET(s, field->arg3);
-
-        return TRACE_TYPE_HANDLED;
-}
-
-static struct trace_event trace_special_event = {
-        .type           = TRACE_SPECIAL,
-        .trace          = trace_special_print,
-        .raw            = trace_special_print,
-        .hex            = trace_special_hex,
-        .binary         = trace_special_bin,
+static struct trace_event trace_wake_event = {
+        .type           = TRACE_WAKE,
+        .funcs          = &trace_wake_funcs,
 };
 
 /* TRACE_STACK */
 
 static enum print_line_t trace_stack_print(struct trace_iterator *iter,
-                                           int flags)
+                                           int flags, struct trace_event *event)
 {
         struct stack_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -1037,17 +1097,18 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
+static struct trace_event_functions trace_stack_funcs = {
+        .trace          = trace_stack_print,
+};
+
 static struct trace_event trace_stack_event = {
         .type           = TRACE_STACK,
-        .trace          = trace_stack_print,
-        .raw            = trace_special_print,
-        .hex            = trace_special_hex,
-        .binary         = trace_special_bin,
+        .funcs          = &trace_stack_funcs,
 };
 
 /* TRACE_USER_STACK */
 static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
-                                                int flags)
+                                                int flags, struct trace_event *event)
 {
         struct userstack_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -1066,17 +1127,19 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
+static struct trace_event_functions trace_user_stack_funcs = {
+        .trace          = trace_user_stack_print,
+};
+
 static struct trace_event trace_user_stack_event = {
         .type           = TRACE_USER_STACK,
-        .trace          = trace_user_stack_print,
-        .raw            = trace_special_print,
-        .hex            = trace_special_hex,
-        .binary         = trace_special_bin,
+        .funcs          = &trace_user_stack_funcs,
 };
 
 /* TRACE_BPRINT */
 static enum print_line_t
-trace_bprint_print(struct trace_iterator *iter, int flags)
+trace_bprint_print(struct trace_iterator *iter, int flags,
+                   struct trace_event *event)
 {
         struct trace_entry *entry = iter->ent;
         struct trace_seq *s = &iter->seq;
@@ -1101,7 +1164,8 @@ trace_bprint_print(struct trace_iterator *iter, int flags)
 
 
 static enum print_line_t
-trace_bprint_raw(struct trace_iterator *iter, int flags)
+trace_bprint_raw(struct trace_iterator *iter, int flags,
+                 struct trace_event *event)
 {
         struct bprint_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -1120,16 +1184,19 @@ trace_bprint_raw(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
+static struct trace_event_functions trace_bprint_funcs = {
+        .trace          = trace_bprint_print,
+        .raw            = trace_bprint_raw,
+};
 
 static struct trace_event trace_bprint_event = {
         .type           = TRACE_BPRINT,
-        .trace          = trace_bprint_print,
-        .raw            = trace_bprint_raw,
+        .funcs          = &trace_bprint_funcs,
 };
 
 /* TRACE_PRINT */
 static enum print_line_t trace_print_print(struct trace_iterator *iter,
-                                           int flags)
+                                           int flags, struct trace_event *event)
 {
         struct print_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -1148,7 +1215,8 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
+                                         struct trace_event *event)
 {
         struct print_entry *field;
 
@@ -1163,18 +1231,21 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static struct trace_event trace_print_event = {
-        .type           = TRACE_PRINT,
+static struct trace_event_functions trace_print_funcs = {
         .trace          = trace_print_print,
         .raw            = trace_print_raw,
 };
 
+static struct trace_event trace_print_event = {
+        .type           = TRACE_PRINT,
+        .funcs          = &trace_print_funcs,
+};
+
 
 static struct trace_event *events[] __initdata = {
         &trace_fn_event,
         &trace_ctx_event,
         &trace_wake_event,
-        &trace_special_event,
         &trace_stack_event,
         &trace_user_stack_event,
         &trace_bprint_event,
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index d38bec4a9c30..c038eba0492b 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -25,7 +25,9 @@ extern void trace_event_read_unlock(void);
 extern struct trace_event *ftrace_find_event(int type);
 
 extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
-                                         int flags);
+                                         int flags, struct trace_event *event);
+extern int
+trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
 
 /* used by module unregistering */
 extern int __unregister_ftrace_event(struct trace_event *event);
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
deleted file mode 100644
index 8a30d9874cd4..000000000000
--- a/kernel/trace/trace_power.c
+++ /dev/null
@@ -1,214 +0,0 @@
-/*
- * ring buffer based C-state tracer
- *
- * Arjan van de Ven <arjan@linux.intel.com>
- * Copyright (C) 2008 Intel Corporation
- *
- * Much is borrowed from trace_boot.c which is
- * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
- *
- */
-
-#include <linux/init.h>
-#include <linux/debugfs.h>
-#include <trace/power.h>
-#include <linux/kallsyms.h>
-#include <linux/module.h>
-
-#include "trace.h"
-#include "trace_output.h"
-
-static struct trace_array *power_trace;
-static int __read_mostly trace_power_enabled;
-
-static void probe_power_start(struct power_trace *it, unsigned int type,
-                                unsigned int level)
-{
-        if (!trace_power_enabled)
-                return;
-
-        memset(it, 0, sizeof(struct power_trace));
-        it->state = level;
-        it->type = type;
-        it->stamp = ktime_get();
-}
-
-
-static void probe_power_end(struct power_trace *it)
-{
-        struct ftrace_event_call *call = &event_power;
-        struct ring_buffer_event *event;
-        struct trace_power *entry;
-        struct trace_array_cpu *data;
-        struct trace_array *tr = power_trace;
-
-        if (!trace_power_enabled)
-                return;
-
-        preempt_disable();
-        it->end = ktime_get();
-        data = tr->data[smp_processor_id()];
-
-        event = trace_buffer_lock_reserve(tr, TRACE_POWER,
-                                          sizeof(*entry), 0, 0);
-        if (!event)
-                goto out;
-        entry   = ring_buffer_event_data(event);
-        entry->state_data = *it;
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                trace_buffer_unlock_commit(tr, event, 0, 0);
- out:
-        preempt_enable();
-}
-
-static void probe_power_mark(struct power_trace *it, unsigned int type,
-                                unsigned int level)
-{
-        struct ftrace_event_call *call = &event_power;
-        struct ring_buffer_event *event;
-        struct trace_power *entry;
-        struct trace_array_cpu *data;
-        struct trace_array *tr = power_trace;
-
-        if (!trace_power_enabled)
-                return;
-
-        memset(it, 0, sizeof(struct power_trace));
-        it->state = level;
-        it->type = type;
-        it->stamp = ktime_get();
-        preempt_disable();
-        it->end = it->stamp;
-        data = tr->data[smp_processor_id()];
-
-        event = trace_buffer_lock_reserve(tr, TRACE_POWER,
-                                          sizeof(*entry), 0, 0);
-        if (!event)
-                goto out;
-        entry   = ring_buffer_event_data(event);
-        entry->state_data = *it;
-        if (!filter_check_discard(call, entry, tr->buffer, event))
-                trace_buffer_unlock_commit(tr, event, 0, 0);
- out:
-        preempt_enable();
-}
-
-static int tracing_power_register(void)
-{
-        int ret;
-
-        ret = register_trace_power_start(probe_power_start);
-        if (ret) {
-                pr_info("power trace: Couldn't activate tracepoint"
-                        " probe to trace_power_start\n");
-                return ret;
-        }
-        ret = register_trace_power_end(probe_power_end);
-        if (ret) {
-                pr_info("power trace: Couldn't activate tracepoint"
-                        " probe to trace_power_end\n");
-                goto fail_start;
-        }
-        ret = register_trace_power_mark(probe_power_mark);
-        if (ret) {
-                pr_info("power trace: Couldn't activate tracepoint"
-                        " probe to trace_power_mark\n");
-                goto fail_end;
-        }
-        return ret;
-fail_end:
-        unregister_trace_power_end(probe_power_end);
-fail_start:
-        unregister_trace_power_start(probe_power_start);
-        return ret;
-}
-
-static void start_power_trace(struct trace_array *tr)
-{
-        trace_power_enabled = 1;
-}
-
-static void stop_power_trace(struct trace_array *tr)
-{
-        trace_power_enabled = 0;
-}
-
-static void power_trace_reset(struct trace_array *tr)
-{
-        trace_power_enabled = 0;
-        unregister_trace_power_start(probe_power_start);
-        unregister_trace_power_end(probe_power_end);
-        unregister_trace_power_mark(probe_power_mark);
-}
-
-
-static int power_trace_init(struct trace_array *tr)
-{
-        int cpu;
-        power_trace = tr;
-
-        trace_power_enabled = 1;
-        tracing_power_register();
-
-        for_each_cpu(cpu, cpu_possible_mask)
-                tracing_reset(tr, cpu);
-        return 0;
-}
-
-static enum print_line_t power_print_line(struct trace_iterator *iter)
-{
-        int ret = 0;
-        struct trace_entry *entry = iter->ent;
-        struct trace_power *field ;
-        struct power_trace *it;
-        struct trace_seq *s = &iter->seq;
-        struct timespec stamp;
-        struct timespec duration;
-
-        trace_assign_type(field, entry);
-        it = &field->state_data;
-        stamp = ktime_to_timespec(it->stamp);
-        duration = ktime_to_timespec(ktime_sub(it->end, it->stamp));
-
-        if (entry->type == TRACE_POWER) {
-                if (it->type == POWER_CSTATE)
-                        ret = trace_seq_printf(s, "[%5ld.%09ld] CSTATE: Going to C%i on cpu %i for %ld.%09ld\n",
-                                          stamp.tv_sec,
-                                          stamp.tv_nsec,
-                                          it->state, iter->cpu,
-                                          duration.tv_sec,
-                                          duration.tv_nsec);
-                if (it->type == POWER_PSTATE)
-                        ret = trace_seq_printf(s, "[%5ld.%09ld] PSTATE: Going to P%i on cpu %i\n",
-                                          stamp.tv_sec,
-                                          stamp.tv_nsec,
-                                          it->state, iter->cpu);
-                if (!ret)
-                        return TRACE_TYPE_PARTIAL_LINE;
-                return TRACE_TYPE_HANDLED;
-        }
-        return TRACE_TYPE_UNHANDLED;
-}
-
-static void power_print_header(struct seq_file *s)
-{
-        seq_puts(s, "#   TIMESTAMP      STATE  EVENT\n");
-        seq_puts(s, "#       |            |      |\n");
-}
-
-static struct tracer power_tracer __read_mostly =
-{
-        .name           = "power",
-        .init           = power_trace_init,
-        .start          = start_power_trace,
-        .stop           = stop_power_trace,
-        .reset          = power_trace_reset,
-        .print_line     = power_print_line,
-        .print_header   = power_print_header,
-};
-
-static int init_power_trace(void)
-{
-        return register_tracer(&power_tracer);
-}
-device_initcall(init_power_trace);
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 9bece9687b62..2547d8813cf0 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -11,7 +11,6 @@
 #include <linux/ftrace.h>
 #include <linux/string.h>
 #include <linux/module.h>
-#include <linux/marker.h>
 #include <linux/mutex.h>
 #include <linux/ctype.h>
 #include <linux/list.h>
@@ -155,25 +154,19 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap)
 EXPORT_SYMBOL_GPL(__ftrace_vprintk);
 
 static void *
-t_next(struct seq_file *m, void *v, loff_t *pos)
+t_start(struct seq_file *m, loff_t *pos)
 {
-        const char **fmt = m->private;
-        const char **next = fmt;
-
-        (*pos)++;
+        const char **fmt = __start___trace_bprintk_fmt + *pos;
 
         if ((unsigned long)fmt >= (unsigned long)__stop___trace_bprintk_fmt)
                 return NULL;
-
-        next = fmt;
-        m->private = ++next;
-
         return fmt;
 }
 
-static void *t_start(struct seq_file *m, loff_t *pos)
+static void *t_next(struct seq_file *m, void * v, loff_t *pos)
 {
-        return t_next(m, NULL, pos);
+        (*pos)++;
+        return t_start(m, pos);
 }
 
 static int t_show(struct seq_file *m, void *v)
@@ -182,7 +175,7 @@ static int t_show(struct seq_file *m, void *v)
         const char *str = *fmt;
         int i;
 
-        seq_printf(m, "0x%lx : \"", (unsigned long)fmt);
+        seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt);
 
         /*
          * Tabs and new lines need to be converted.
@@ -224,15 +217,7 @@ static const struct seq_operations show_format_seq_ops = {
 static int
 ftrace_formats_open(struct inode *inode, struct file *file)
 {
-        int ret;
-
-        ret = seq_open(file, &show_format_seq_ops);
-        if (!ret) {
-                struct seq_file *m = file->private_data;
-
-                m->private = __start___trace_bprintk_fmt;
-        }
-        return ret;
+        return seq_open(file, &show_format_seq_ops);
 }
 
 static const struct file_operations ftrace_formats_fops = {
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index a98106dd979c..8f758d070c43 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -20,9 +20,37 @@ static int			sched_ref;
 static DEFINE_MUTEX(sched_register_mutex);
 static int                      sched_stopped;
 
+
+void
+tracing_sched_switch_trace(struct trace_array *tr,
+                           struct task_struct *prev,
+                           struct task_struct *next,
+                           unsigned long flags, int pc)
+{
+        struct ftrace_event_call *call = &event_context_switch;
+        struct ring_buffer *buffer = tr->buffer;
+        struct ring_buffer_event *event;
+        struct ctx_switch_entry *entry;
+
+        event = trace_buffer_lock_reserve(buffer, TRACE_CTX,
+                                          sizeof(*entry), flags, pc);
+        if (!event)
+                return;
+        entry   = ring_buffer_event_data(event);
+        entry->prev_pid                 = prev->pid;
+        entry->prev_prio                = prev->prio;
+        entry->prev_state               = prev->state;
+        entry->next_pid                 = next->pid;
+        entry->next_prio                = next->prio;
+        entry->next_state               = next->state;
+        entry->next_cpu = task_cpu(next);
+
+        if (!filter_check_discard(call, entry, buffer, event))
+                trace_buffer_unlock_commit(buffer, event, flags, pc);
+}
+
 static void
-probe_sched_switch(struct rq *__rq, struct task_struct *prev,
-                        struct task_struct *next)
+probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next)
 {
         struct trace_array_cpu *data;
         unsigned long flags;
@@ -49,8 +77,38 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
         local_irq_restore(flags);
 }
 
+void
+tracing_sched_wakeup_trace(struct trace_array *tr,
+                           struct task_struct *wakee,
+                           struct task_struct *curr,
+                           unsigned long flags, int pc)
+{
+        struct ftrace_event_call *call = &event_wakeup;
+        struct ring_buffer_event *event;
+        struct ctx_switch_entry *entry;
+        struct ring_buffer *buffer = tr->buffer;
+
+        event = trace_buffer_lock_reserve(buffer, TRACE_WAKE,
+                                          sizeof(*entry), flags, pc);
+        if (!event)
+                return;
+        entry   = ring_buffer_event_data(event);
+        entry->prev_pid                 = curr->pid;
+        entry->prev_prio                = curr->prio;
+        entry->prev_state               = curr->state;
+        entry->next_pid                 = wakee->pid;
+        entry->next_prio                = wakee->prio;
+        entry->next_state               = wakee->state;
+        entry->next_cpu                 = task_cpu(wakee);
+
+        if (!filter_check_discard(call, entry, buffer, event))
+                ring_buffer_unlock_commit(buffer, event);
+        ftrace_trace_stack(tr->buffer, flags, 6, pc);
+        ftrace_trace_userstack(tr->buffer, flags, pc);
+}
+
 static void
-probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
+probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
 {
         struct trace_array_cpu *data;
         unsigned long flags;
@@ -80,21 +138,21 @@ static int tracing_sched_register(void)
 {
         int ret;
 
-        ret = register_trace_sched_wakeup(probe_sched_wakeup);
+        ret = register_trace_sched_wakeup(probe_sched_wakeup, NULL);
         if (ret) {
                 pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup\n");
                 return ret;
         }
 
-        ret = register_trace_sched_wakeup_new(probe_sched_wakeup);
+        ret = register_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
         if (ret) {
                 pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup_new\n");
                 goto fail_deprobe;
         }
 
-        ret = register_trace_sched_switch(probe_sched_switch);
+        ret = register_trace_sched_switch(probe_sched_switch, NULL);
         if (ret) {
                 pr_info("sched trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_switch\n");
@@ -103,17 +161,17 @@ static int tracing_sched_register(void)
 
         return ret;
 fail_deprobe_wake_new:
-        unregister_trace_sched_wakeup_new(probe_sched_wakeup);
+        unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
 fail_deprobe:
-        unregister_trace_sched_wakeup(probe_sched_wakeup);
+        unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
         return ret;
 }
 
 static void tracing_sched_unregister(void)
 {
-        unregister_trace_sched_switch(probe_sched_switch);
-        unregister_trace_sched_wakeup_new(probe_sched_wakeup);
-        unregister_trace_sched_wakeup(probe_sched_wakeup);
+        unregister_trace_sched_switch(probe_sched_switch, NULL);
+        unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
+        unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
 }
 
 static void tracing_start_sched_switch(void)
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index eacb27225173..7319559ed59f 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -24,66 +24,106 @@ static int __read_mostly	tracer_enabled;
 
 static struct task_struct       *wakeup_task;
 static int                      wakeup_cpu;
+static int                      wakeup_current_cpu;
 static unsigned                 wakeup_prio = -1;
 static int                      wakeup_rt;
 
-static raw_spinlock_t wakeup_lock =
-        (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+static arch_spinlock_t wakeup_lock =
+        (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
+static void wakeup_reset(struct trace_array *tr);
 static void __wakeup_reset(struct trace_array *tr);
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
+static void wakeup_graph_return(struct ftrace_graph_ret *trace);
 
 static int save_lat_flag;
 
+#define TRACE_DISPLAY_GRAPH     1
+
+static struct tracer_opt trace_opts[] = {
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        /* display latency trace as call graph */
+        { TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) },
+#endif
+        { } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+        .val  = 0,
+        .opts = trace_opts,
+};
+
+#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH)
+
 #ifdef CONFIG_FUNCTION_TRACER
+
 /*
- * irqsoff uses its own tracer function to keep the overhead down:
+ * Prologue for the wakeup function tracers.
+ *
+ * Returns 1 if it is OK to continue, and preemption
+ *            is disabled and data->disabled is incremented.
+ *         0 if the trace is to be ignored, and preemption
+ *            is not disabled and data->disabled is
+ *            kept the same.
+ *
+ * Note, this function is also used outside this ifdef but
+ *  inside the #ifdef of the function graph tracer below.
+ *  This is OK, since the function graph tracer is
+ *  dependent on the function tracer.
  */
-static void
-wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
+static int
+func_prolog_preempt_disable(struct trace_array *tr,
+                            struct trace_array_cpu **data,
+                            int *pc)
 {
-        struct trace_array *tr = wakeup_trace;
-        struct trace_array_cpu *data;
-        unsigned long flags;
         long disabled;
-        int resched;
         int cpu;
-        int pc;
 
         if (likely(!wakeup_task))
-                return;
+                return 0;
 
-        pc = preempt_count();
-        resched = ftrace_preempt_disable();
+        *pc = preempt_count();
+        preempt_disable_notrace();
 
         cpu = raw_smp_processor_id();
-        data = tr->data[cpu];
-        disabled = atomic_inc_return(&data->disabled);
+        if (cpu != wakeup_current_cpu)
+                goto out_enable;
+
+        *data = tr->data[cpu];
+        disabled = atomic_inc_return(&(*data)->disabled);
         if (unlikely(disabled != 1))
                 goto out;
 
-        local_irq_save(flags);
-        __raw_spin_lock(&wakeup_lock);
+        return 1;
 
-        if (unlikely(!wakeup_task))
-                goto unlock;
+out:
+        atomic_dec(&(*data)->disabled);
 
-        /*
-         * The task can't disappear because it needs to
-         * wake up first, and we have the wakeup_lock.
-         */
-        if (task_cpu(wakeup_task) != cpu)
-                goto unlock;
+out_enable:
+        preempt_enable_notrace();
+        return 0;
+}
 
-        trace_function(tr, ip, parent_ip, flags, pc);
+/*
+ * wakeup uses its own tracer function to keep the overhead down:
+ */
+static void
+wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
+{
+        struct trace_array *tr = wakeup_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        int pc;
+
+        if (!func_prolog_preempt_disable(tr, &data, &pc))
+                return;
 
- unlock:
-        __raw_spin_unlock(&wakeup_lock);
+        local_irq_save(flags);
+        trace_function(tr, ip, parent_ip, flags, pc);
         local_irq_restore(flags);
 
- out:
         atomic_dec(&data->disabled);
-
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
@@ -92,6 +132,156 @@ static struct ftrace_ops trace_ops __read_mostly =
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
+static int start_func_tracer(int graph)
+{
+        int ret;
+
+        if (!graph)
+                ret = register_ftrace_function(&trace_ops);
+        else
+                ret = register_ftrace_graph(&wakeup_graph_return,
+                                            &wakeup_graph_entry);
+
+        if (!ret && tracing_is_enabled())
+                tracer_enabled = 1;
+        else
+                tracer_enabled = 0;
+
+        return ret;
+}
+
+static void stop_func_tracer(int graph)
+{
+        tracer_enabled = 0;
+
+        if (!graph)
+                unregister_ftrace_function(&trace_ops);
+        else
+                unregister_ftrace_graph();
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+{
+
+        if (!(bit & TRACE_DISPLAY_GRAPH))
+                return -EINVAL;
+
+        if (!(is_graph() ^ set))
+                return 0;
+
+        stop_func_tracer(!set);
+
+        wakeup_reset(wakeup_trace);
+        tracing_max_latency = 0;
+
+        return start_func_tracer(set);
+}
+
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
+{
+        struct trace_array *tr = wakeup_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        int pc, ret = 0;
+
+        if (!func_prolog_preempt_disable(tr, &data, &pc))
+                return 0;
+
+        local_save_flags(flags);
+        ret = __trace_graph_entry(tr, trace, flags, pc);
+        atomic_dec(&data->disabled);
+        preempt_enable_notrace();
+
+        return ret;
+}
+
+static void wakeup_graph_return(struct ftrace_graph_ret *trace)
+{
+        struct trace_array *tr = wakeup_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        int pc;
+
+        if (!func_prolog_preempt_disable(tr, &data, &pc))
+                return;
+
+        local_save_flags(flags);
+        __trace_graph_return(tr, trace, flags, pc);
+        atomic_dec(&data->disabled);
+
+        preempt_enable_notrace();
+        return;
+}
+
+static void wakeup_trace_open(struct trace_iterator *iter)
+{
+        if (is_graph())
+                graph_trace_open(iter);
+}
+
+static void wakeup_trace_close(struct trace_iterator *iter)
+{
+        if (iter->private)
+                graph_trace_close(iter);
+}
+
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC)
+
+static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
+{
+        /*
+         * In graph mode call the graph tracer output function,
+         * otherwise go with the TRACE_FN event handler
+         */
+        if (is_graph())
+                return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);
+
+        return TRACE_TYPE_UNHANDLED;
+}
+
+static void wakeup_print_header(struct seq_file *s)
+{
+        if (is_graph())
+                print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
+        else
+                trace_default_header(s);
+}
+
+static void
+__trace_function(struct trace_array *tr,
+                 unsigned long ip, unsigned long parent_ip,
+                 unsigned long flags, int pc)
+{
+        if (is_graph())
+                trace_graph_function(tr, ip, parent_ip, flags, pc);
+        else
+                trace_function(tr, ip, parent_ip, flags, pc);
+}
+#else
+#define __trace_function trace_function
+
+static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+{
+        return -EINVAL;
+}
+
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
+{
+        return -1;
+}
+
+static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
+{
+        return TRACE_TYPE_UNHANDLED;
+}
+
+static void wakeup_graph_return(struct ftrace_graph_ret *trace) { }
+static void wakeup_print_header(struct seq_file *s) { }
+static void wakeup_trace_open(struct trace_iterator *iter) { }
+static void wakeup_trace_close(struct trace_iterator *iter) { }
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 /*
  * Should this new latency be reported/recorded?
  */
@@ -107,11 +297,19 @@ static int report_latency(cycle_t delta)
         return 1;
 }
 
+static void
+probe_wakeup_migrate_task(void *ignore, struct task_struct *task, int cpu)
+{
+        if (task != wakeup_task)
+                return;
+
+        wakeup_current_cpu = cpu;
+}
+
 static void notrace
-probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
-        struct task_struct *next)
+probe_wakeup_sched_switch(void *ignore,
+                          struct task_struct *prev, struct task_struct *next)
 {
-        unsigned long latency = 0, t0 = 0, t1 = 0;
         struct trace_array_cpu *data;
         cycle_t T0, T1, delta;
         unsigned long flags;
@@ -145,7 +343,7 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
                 goto out;
 
         local_irq_save(flags);
-        __raw_spin_lock(&wakeup_lock);
+        arch_spin_lock(&wakeup_lock);
 
         /* We could race with grabbing wakeup_lock */
         if (unlikely(!tracer_enabled || next != wakeup_task))
@@ -154,13 +352,9 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
         /* The task we are waiting for is waking up */
         data = wakeup_trace->data[wakeup_cpu];
 
-        trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
+        __trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
         tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
 
-        /*
-         * usecs conversion is slow so we try to delay the conversion
-         * as long as possible:
-         */
         T0 = data->preempt_timestamp;
         T1 = ftrace_now(cpu);
         delta = T1-T0;
@@ -168,17 +362,14 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
         if (!report_latency(delta))
                 goto out_unlock;
 
-        latency = nsecs_to_usecs(delta);
-
-        tracing_max_latency = delta;
-        t0 = nsecs_to_usecs(T0);
-        t1 = nsecs_to_usecs(T1);
-
-        update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu);
+        if (likely(!is_tracing_stopped())) {
+                tracing_max_latency = delta;
+                update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu);
+        }
 
 out_unlock:
         __wakeup_reset(wakeup_trace);
-        __raw_spin_unlock(&wakeup_lock);
+        arch_spin_unlock(&wakeup_lock);
         local_irq_restore(flags);
 out:
         atomic_dec(&wakeup_trace->data[cpu]->disabled);
@@ -186,11 +377,6 @@ out:
 
 static void __wakeup_reset(struct trace_array *tr)
 {
-        int cpu;
-
-        for_each_possible_cpu(cpu)
-                tracing_reset(tr, cpu);
-
         wakeup_cpu = -1;
         wakeup_prio = -1;
 
@@ -204,15 +390,17 @@ static void wakeup_reset(struct trace_array *tr)
 {
         unsigned long flags;
 
+        tracing_reset_online_cpus(tr);
+
         local_irq_save(flags);
-        __raw_spin_lock(&wakeup_lock);
+        arch_spin_lock(&wakeup_lock);
         __wakeup_reset(tr);
-        __raw_spin_unlock(&wakeup_lock);
+        arch_spin_unlock(&wakeup_lock);
         local_irq_restore(flags);
 }
 
 static void
-probe_wakeup(struct rq *rq, struct task_struct *p, int success)
+probe_wakeup(void *ignore, struct task_struct *p, int success)
 {
         struct trace_array_cpu *data;
         int cpu = smp_processor_id();
@@ -237,7 +425,7 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success)
                 goto out;
 
         /* interrupts should be off from try_to_wake_up */
-        __raw_spin_lock(&wakeup_lock);
+        arch_spin_lock(&wakeup_lock);
 
         /* check for races. */
         if (!tracer_enabled || p->prio >= wakeup_prio)
@@ -247,6 +435,7 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success)
         __wakeup_reset(wakeup_trace);
 
         wakeup_cpu = task_cpu(p);
+        wakeup_current_cpu = wakeup_cpu;
         wakeup_prio = p->prio;
 
         wakeup_task = p;
@@ -263,10 +452,10 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success)
          * is not called by an assembly function  (where as schedule is)
          * it should be safe to use it here.
          */
-        trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
+        __trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
 
 out_locked:
-        __raw_spin_unlock(&wakeup_lock);
+        arch_spin_unlock(&wakeup_lock);
 out:
         atomic_dec(&wakeup_trace->data[cpu]->disabled);
 }
@@ -275,27 +464,34 @@ static void start_wakeup_tracer(struct trace_array *tr)
 {
         int ret;
 
-        ret = register_trace_sched_wakeup(probe_wakeup);
+        ret = register_trace_sched_wakeup(probe_wakeup, NULL);
         if (ret) {
                 pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup\n");
                 return;
         }
 
-        ret = register_trace_sched_wakeup_new(probe_wakeup);
+        ret = register_trace_sched_wakeup_new(probe_wakeup, NULL);
         if (ret) {
                 pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup_new\n");
                 goto fail_deprobe;
         }
 
-        ret = register_trace_sched_switch(probe_wakeup_sched_switch);
+        ret = register_trace_sched_switch(probe_wakeup_sched_switch, NULL);
         if (ret) {
                 pr_info("sched trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_switch\n");
                 goto fail_deprobe_wake_new;
         }
 
+        ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
+        if (ret) {
+                pr_info("wakeup trace: Couldn't activate tracepoint"
+                        " probe to kernel_sched_migrate_task\n");
+                return;
+        }
+
         wakeup_reset(tr);
 
         /*
@@ -307,27 +503,24 @@ static void start_wakeup_tracer(struct trace_array *tr)
          */
         smp_wmb();
 
-        register_ftrace_function(&trace_ops);
-
-        if (tracing_is_enabled())
-                tracer_enabled = 1;
-        else
-                tracer_enabled = 0;
+        if (start_func_tracer(is_graph()))
+                printk(KERN_ERR "failed to start wakeup tracer\n");
 
         return;
 fail_deprobe_wake_new:
-        unregister_trace_sched_wakeup_new(probe_wakeup);
+        unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
 fail_deprobe:
-        unregister_trace_sched_wakeup(probe_wakeup);
+        unregister_trace_sched_wakeup(probe_wakeup, NULL);
 }
 
 static void stop_wakeup_tracer(struct trace_array *tr)
 {
         tracer_enabled = 0;
-        unregister_ftrace_function(&trace_ops);
-        unregister_trace_sched_switch(probe_wakeup_sched_switch);
-        unregister_trace_sched_wakeup_new(probe_wakeup);
-        unregister_trace_sched_wakeup(probe_wakeup);
+        stop_func_tracer(is_graph());
+        unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
+        unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
+        unregister_trace_sched_wakeup(probe_wakeup, NULL);
+        unregister_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
 }
 
 static int __wakeup_tracer_init(struct trace_array *tr)
@@ -382,9 +575,16 @@ static struct tracer wakeup_tracer __read_mostly =
         .start          = wakeup_tracer_start,
         .stop           = wakeup_tracer_stop,
         .print_max      = 1,
+        .print_header   = wakeup_print_header,
+        .print_line     = wakeup_print_line,
+        .flags          = &tracer_flags,
+        .set_flag       = wakeup_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_wakeup,
 #endif
+        .open           = wakeup_trace_open,
+        .close          = wakeup_trace_close,
+        .use_max_tr     = 1,
 };
 
 static struct tracer wakeup_rt_tracer __read_mostly =
@@ -396,9 +596,16 @@ static struct tracer wakeup_rt_tracer __read_mostly =
         .stop           = wakeup_tracer_stop,
         .wait_pipe      = poll_wait_pipe,
         .print_max      = 1,
+        .print_header   = wakeup_print_header,
+        .print_line     = wakeup_print_line,
+        .flags          = &tracer_flags,
+        .set_flag       = wakeup_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_wakeup,
 #endif
+        .open           = wakeup_trace_open,
+        .close          = wakeup_trace_close,
+        .use_max_tr     = 1,
 };
 
 __init static int init_wakeup_tracer(void)
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 00dd6485bdd7..659732eba07c 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -3,6 +3,7 @@
 #include <linux/stringify.h>
 #include <linux/kthread.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 
 static inline int trace_valid_entry(struct trace_entry *entry)
 {
@@ -12,11 +13,9 @@ static inline int trace_valid_entry(struct trace_entry *entry)
         case TRACE_WAKE:
         case TRACE_STACK:
         case TRACE_PRINT:
-        case TRACE_SPECIAL:
         case TRACE_BRANCH:
         case TRACE_GRAPH_ENT:
         case TRACE_GRAPH_RET:
-        case TRACE_HW_BRANCHES:
                 return 1;
         }
         return 0;
@@ -28,7 +27,7 @@ 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);
 
                 /*
@@ -66,7 +65,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 
         /* Don't allow flipping of max traces now */
         local_irq_save(flags);
-        __raw_spin_lock(&ftrace_max_lock);
+        arch_spin_lock(&ftrace_max_lock);
 
         cnt = ring_buffer_entries(tr->buffer);
 
@@ -84,7 +83,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
                         break;
         }
         tracing_on();
-        __raw_spin_unlock(&ftrace_max_lock);
+        arch_spin_unlock(&ftrace_max_lock);
         local_irq_restore(flags);
 
         if (count)
@@ -254,7 +253,8 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 /* Maximum number of functions to trace before diagnosing a hang */
 #define GRAPH_MAX_FUNC_TEST     100000000
 
-static void __ftrace_dump(bool disable_tracing);
+static void
+__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode);
 static unsigned int graph_hang_thresh;
 
 /* Wrap the real function entry probe to avoid possible hanging */
@@ -265,7 +265,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
                 ftrace_graph_stop();
                 printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
                 if (ftrace_dump_on_oops)
-                        __ftrace_dump(false);
+                        __ftrace_dump(false, DUMP_ALL);
                 return 0;
         }
 
@@ -288,6 +288,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
          * to detect and recover from possible hangs
          */
         tracing_reset_online_cpus(tr);
+        set_graph_array(tr);
         ret = register_ftrace_graph(&trace_graph_return,
                                     &trace_graph_entry_watchdog);
         if (ret) {
@@ -557,7 +558,7 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
 static int trace_wakeup_test_thread(void *data)
 {
         /* Make this a RT thread, doesn't need to be too high */
-        struct sched_param param = { .sched_priority = 5 };
+        static const struct sched_param param = { .sched_priority = 5 };
         struct completion *x = data;
 
         sched_setscheduler(current, SCHED_FIFO, &param);
@@ -688,38 +689,6 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr
 }
 #endif /* CONFIG_CONTEXT_SWITCH_TRACER */
 
-#ifdef CONFIG_SYSPROF_TRACER
-int
-trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr)
-{
-        unsigned long count;
-        int ret;
-
-        /* start the tracing */
-        ret = tracer_init(trace, tr);
-        if (ret) {
-                warn_failed_init_tracer(trace, ret);
-                return ret;
-        }
-
-        /* Sleep for a 1/10 of a second */
-        msleep(100);
-        /* stop the tracing. */
-        tracing_stop();
-        /* check the trace buffer */
-        ret = trace_test_buffer(tr, &count);
-        trace->reset(tr);
-        tracing_start();
-
-        if (!ret && !count) {
-                printk(KERN_CONT ".. no entries found ..");
-                ret = -1;
-        }
-
-        return ret;
-}
-#endif /* CONFIG_SYSPROF_TRACER */
-
 #ifdef CONFIG_BRANCH_TRACER
 int
 trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
@@ -752,58 +721,3 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
 }
 #endif /* CONFIG_BRANCH_TRACER */
 
-#ifdef CONFIG_HW_BRANCH_TRACER
-int
-trace_selftest_startup_hw_branches(struct tracer *trace,
-                                   struct trace_array *tr)
-{
-        struct trace_iterator *iter;
-        struct tracer tracer;
-        unsigned long count;
-        int ret;
-
-        if (!trace->open) {
-                printk(KERN_CONT "missing open function...");
-                return -1;
-        }
-
-        ret = tracer_init(trace, tr);
-        if (ret) {
-                warn_failed_init_tracer(trace, ret);
-                return ret;
-        }
-
-        /*
-         * The hw-branch tracer needs to collect the trace from the various
-         * cpu trace buffers - before tracing is stopped.
-         */
-        iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-        if (!iter)
-                return -ENOMEM;
-
-        memcpy(&tracer, trace, sizeof(tracer));
-
-        iter->trace = &tracer;
-        iter->tr = tr;
-        iter->pos = -1;
-        mutex_init(&iter->mutex);
-
-        trace->open(iter);
-
-        mutex_destroy(&iter->mutex);
-        kfree(iter);
-
-        tracing_stop();
-
-        ret = trace_test_buffer(tr, &count);
-        trace->reset(tr);
-        tracing_start();
-
-        if (!ret && !count) {
-                printk(KERN_CONT "no entries found..");
-                ret = -1;
-        }
-
-        return ret;
-}
-#endif /* CONFIG_HW_BRANCH_TRACER */
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 2d7aebd71dbd..4c5dead0c239 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -27,8 +27,8 @@ static struct stack_trace max_stack_trace = {
 };
 
 static unsigned long max_stack_size;
-static raw_spinlock_t max_stack_lock =
-        (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+static arch_spinlock_t max_stack_lock =
+        (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
 static int stack_trace_disabled __read_mostly;
 static DEFINE_PER_CPU(int, trace_active);
@@ -54,7 +54,7 @@ static inline void check_stack(void)
                 return;
 
         local_irq_save(flags);
-        __raw_spin_lock(&max_stack_lock);
+        arch_spin_lock(&max_stack_lock);
 
         /* a race could have already updated it */
         if (this_size <= max_stack_size)
@@ -103,19 +103,19 @@ static inline void check_stack(void)
         }
 
  out:
-        __raw_spin_unlock(&max_stack_lock);
+        arch_spin_unlock(&max_stack_lock);
         local_irq_restore(flags);
 }
 
 static void
 stack_trace_call(unsigned long ip, unsigned long parent_ip)
 {
-        int cpu, resched;
+        int cpu;
 
         if (unlikely(!ftrace_enabled || stack_trace_disabled))
                 return;
 
-        resched = ftrace_preempt_disable();
+        preempt_disable_notrace();
 
         cpu = raw_smp_processor_id();
         /* no atomic needed, we only modify this variable by this cpu */
@@ -127,7 +127,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
  out:
         per_cpu(trace_active, cpu)--;
         /* prevent recursion in schedule */
-        ftrace_preempt_enable(resched);
+        preempt_enable_notrace();
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
@@ -157,6 +157,7 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
         unsigned long val, flags;
         char buf[64];
         int ret;
+        int cpu;
 
         if (count >= sizeof(buf))
                 return -EINVAL;
@@ -171,9 +172,20 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
                 return ret;
 
         local_irq_save(flags);
-        __raw_spin_lock(&max_stack_lock);
+
+        /*
+         * In case we trace inside arch_spin_lock() or after (NMI),
+         * we will cause circular lock, so we also need to increase
+         * the percpu trace_active here.
+         */
+        cpu = smp_processor_id();
+        per_cpu(trace_active, cpu)++;
+
+        arch_spin_lock(&max_stack_lock);
         *ptr = val;
-        __raw_spin_unlock(&max_stack_lock);
+        arch_spin_unlock(&max_stack_lock);
+
+        per_cpu(trace_active, cpu)--;
         local_irq_restore(flags);
 
         return count;
@@ -183,66 +195,62 @@ static const struct file_operations stack_max_size_fops = {
         .open           = tracing_open_generic,
         .read           = stack_max_size_read,
         .write          = stack_max_size_write,
+        .llseek         = default_llseek,
 };
 
 static void *
-t_next(struct seq_file *m, void *v, loff_t *pos)
+__next(struct seq_file *m, loff_t *pos)
 {
-        long i;
+        long n = *pos - 1;
 
-        (*pos)++;
-
-        if (v == SEQ_START_TOKEN)
-                i = 0;
-        else {
-                i = *(long *)v;
-                i++;
-        }
-
-        if (i >= max_stack_trace.nr_entries ||
-            stack_dump_trace[i] == ULONG_MAX)
+        if (n >= max_stack_trace.nr_entries || stack_dump_trace[n] == ULONG_MAX)
                 return NULL;
 
-        m->private = (void *)i;
-
+        m->private = (void *)n;
         return &m->private;
 }
 
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        (*pos)++;
+        return __next(m, pos);
+}
+
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-        void *t = SEQ_START_TOKEN;
-        loff_t l = 0;
+        int cpu;
 
         local_irq_disable();
-        __raw_spin_lock(&max_stack_lock);
+
+        cpu = smp_processor_id();
+        per_cpu(trace_active, cpu)++;
+
+        arch_spin_lock(&max_stack_lock);
 
         if (*pos == 0)
                 return SEQ_START_TOKEN;
 
-        for (; t && l < *pos; t = t_next(m, t, &l))
-                ;
-
-        return t;
+        return __next(m, pos);
 }
 
 static void t_stop(struct seq_file *m, void *p)
 {
-        __raw_spin_unlock(&max_stack_lock);
+        int cpu;
+
+        arch_spin_unlock(&max_stack_lock);
+
+        cpu = smp_processor_id();
+        per_cpu(trace_active, cpu)--;
+
         local_irq_enable();
 }
 
 static int trace_lookup_stack(struct seq_file *m, long i)
 {
         unsigned long addr = stack_dump_trace[i];
-#ifdef CONFIG_KALLSYMS
-        char str[KSYM_SYMBOL_LEN];
-
-        sprint_symbol(str, addr);
 
-        return seq_printf(m, "%s\n", str);
-#else
-        return seq_printf(m, "%p\n", (void*)addr);
-#endif
+        return seq_printf(m, "%pS\n", (void *)addr);
 }
 
 static void print_disabled(struct seq_file *m)
@@ -301,35 +309,32 @@ static const struct seq_operations stack_trace_seq_ops = {
 
 static int stack_trace_open(struct inode *inode, struct file *file)
 {
-        int ret;
-
-        ret = seq_open(file, &stack_trace_seq_ops);
-
-        return ret;
+        return seq_open(file, &stack_trace_seq_ops);
 }
 
 static const struct file_operations stack_trace_fops = {
         .open           = stack_trace_open,
         .read           = seq_read,
         .llseek         = seq_lseek,
+        .release        = seq_release,
 };
 
 int
 stack_trace_sysctl(struct ctl_table *table, int write,
-                   struct file *file, void __user *buffer, size_t *lenp,
+                   void __user *buffer, size_t *lenp,
                    loff_t *ppos)
 {
         int ret;
 
         mutex_lock(&stack_sysctl_mutex);
 
-        ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
+        ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
         if (ret || !write ||
-            (last_stack_tracer_enabled == stack_tracer_enabled))
+            (last_stack_tracer_enabled == !!stack_tracer_enabled))
                 goto out;
 
-        last_stack_tracer_enabled = stack_tracer_enabled;
+        last_stack_tracer_enabled = !!stack_tracer_enabled;
 
         if (stack_tracer_enabled)
                 register_ftrace_function(&trace_ops);
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index c00643733f4c..96cffb269e73 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -10,6 +10,7 @@
 
 
 #include <linux/list.h>
+#include <linux/slab.h>
 #include <linux/rbtree.h>
 #include <linux/debugfs.h>
 #include "trace_stat.h"
@@ -49,7 +50,8 @@ static struct dentry		*stat_dir;
  * but it will at least advance closer to the next one
  * to be released.
  */
-static struct rb_node *release_next(struct rb_node *node)
+static struct rb_node *release_next(struct tracer_stat *ts,
+                                    struct rb_node *node)
 {
         struct stat_node *snode;
         struct rb_node *parent = rb_parent(node);
@@ -67,26 +69,35 @@ static struct rb_node *release_next(struct rb_node *node)
                         parent->rb_right = NULL;
 
                 snode = container_of(node, struct stat_node, node);
+                if (ts->stat_release)
+                        ts->stat_release(snode->stat);
                 kfree(snode);
 
                 return parent;
         }
 }
 
-static void reset_stat_session(struct stat_session *session)
+static void __reset_stat_session(struct stat_session *session)
 {
         struct rb_node *node = session->stat_root.rb_node;
 
         while (node)
-                node = release_next(node);
+                node = release_next(session->ts, node);
 
         session->stat_root = RB_ROOT;
 }
 
+static void reset_stat_session(struct stat_session *session)
+{
+        mutex_lock(&session->stat_mutex);
+        __reset_stat_session(session);
+        mutex_unlock(&session->stat_mutex);
+}
+
 static void destroy_session(struct stat_session *session)
 {
         debugfs_remove(session->file);
-        reset_stat_session(session);
+        __reset_stat_session(session);
         mutex_destroy(&session->stat_mutex);
         kfree(session);
 }
@@ -150,7 +161,7 @@ static int stat_seq_init(struct stat_session *session)
         int i;
 
         mutex_lock(&session->stat_mutex);
-        reset_stat_session(session);
+        __reset_stat_session(session);
 
         if (!ts->stat_cmp)
                 ts->stat_cmp = dummy_cmp;
@@ -183,7 +194,7 @@ exit:
         return ret;
 
 exit_free_rbtree:
-        reset_stat_session(session);
+        __reset_stat_session(session);
         mutex_unlock(&session->stat_mutex);
         return ret;
 }
@@ -193,23 +204,23 @@ static void *stat_seq_start(struct seq_file *s, loff_t *pos)
 {
         struct stat_session *session = s->private;
         struct rb_node *node;
+        int n = *pos;
         int i;
 
         /* Prevent from tracer switch or rbtree modification */
         mutex_lock(&session->stat_mutex);
 
         /* If we are in the beginning of the file, print the headers */
-        if (!*pos && session->ts->stat_headers) {
-                (*pos)++;
-                return SEQ_START_TOKEN;
+        if (session->ts->stat_headers) {
+                if (n == 0)
+                        return SEQ_START_TOKEN;
+                n--;
         }
 
         node = rb_first(&session->stat_root);
-        for (i = 0; node && i < *pos; i++)
+        for (i = 0; node && i < n; i++)
                 node = rb_next(node);
 
-        (*pos)++;
-
         return node;
 }
 
@@ -254,16 +265,21 @@ static const struct seq_operations trace_stat_seq_ops = {
 static int tracing_stat_open(struct inode *inode, struct file *file)
 {
         int ret;
-
+        struct seq_file *m;
         struct stat_session *session = inode->i_private;
 
+        ret = stat_seq_init(session);
+        if (ret)
+                return ret;
+
         ret = seq_open(file, &trace_stat_seq_ops);
-        if (!ret) {
-                struct seq_file *m = file->private_data;
-                m->private = session;
-                ret = stat_seq_init(session);
+        if (ret) {
+                reset_stat_session(session);
+                return ret;
         }
 
+        m = file->private_data;
+        m->private = session;
         return ret;
 }
 
@@ -274,11 +290,9 @@ static int tracing_stat_release(struct inode *i, struct file *f)
 {
         struct stat_session *session = i->i_private;
 
-        mutex_lock(&session->stat_mutex);
         reset_stat_session(session);
-        mutex_unlock(&session->stat_mutex);
 
-        return 0;
+        return seq_release(i, f);
 }
 
 static const struct file_operations tracing_stat_fops = {
diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h
index f3546a2cd826..8f03914b9a6a 100644
--- a/kernel/trace/trace_stat.h
+++ b/kernel/trace/trace_stat.h
@@ -18,6 +18,8 @@ struct tracer_stat {
         int                     (*stat_cmp)(void *p1, void *p2);
         /* Print a stat entry */
         int                     (*stat_show)(struct seq_file *s, void *p);
+        /* Release an entry */
+        void                    (*stat_release)(void *stat);
         /* Print the headers of your stat entries */
         int                     (*stat_headers)(struct seq_file *s);
 };
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5e579645ac86..bac752f0cfb5 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,33 +1,109 @@
 #include <trace/syscall.h>
+#include <trace/events/syscalls.h>
+#include <linux/slab.h>
 #include <linux/kernel.h>
+#include <linux/ftrace.h>
+#include <linux/perf_event.h>
 #include <asm/syscall.h>
 
 #include "trace_output.h"
 #include "trace.h"
 
-/* Keep a counter of the syscall tracing users */
-static int refcount;
-
-/* Prevent from races on thread flags toggling */
 static DEFINE_MUTEX(syscall_trace_lock);
+static int sys_refcount_enter;
+static int sys_refcount_exit;
+static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+
+static int syscall_enter_register(struct ftrace_event_call *event,
+                                 enum trace_reg type);
+static int syscall_exit_register(struct ftrace_event_call *event,
+                                 enum trace_reg type);
+
+static int syscall_enter_define_fields(struct ftrace_event_call *call);
+static int syscall_exit_define_fields(struct ftrace_event_call *call);
+
+/* All syscall exit events have the same fields */
+static LIST_HEAD(syscall_exit_fields);
+
+static struct list_head *
+syscall_get_enter_fields(struct ftrace_event_call *call)
+{
+        struct syscall_metadata *entry = call->data;
+
+        return &entry->enter_fields;
+}
+
+static struct list_head *
+syscall_get_exit_fields(struct ftrace_event_call *call)
+{
+        return &syscall_exit_fields;
+}
+
+struct trace_event_functions enter_syscall_print_funcs = {
+        .trace                  = print_syscall_enter,
+};
 
-/* Option to display the parameters types */
-enum {
-        TRACE_SYSCALLS_OPT_TYPES = 0x1,
+struct trace_event_functions exit_syscall_print_funcs = {
+        .trace                  = print_syscall_exit,
 };
 
-static struct tracer_opt syscalls_opts[] = {
-        { TRACER_OPT(syscall_arg_type, TRACE_SYSCALLS_OPT_TYPES) },
-        { }
+struct ftrace_event_class event_class_syscall_enter = {
+        .system                 = "syscalls",
+        .reg                    = syscall_enter_register,
+        .define_fields          = syscall_enter_define_fields,
+        .get_fields             = syscall_get_enter_fields,
+        .raw_init               = init_syscall_trace,
 };
 
-static struct tracer_flags syscalls_flags = {
-        .val = 0, /* By default: no parameters types */
-        .opts = syscalls_opts
+struct ftrace_event_class event_class_syscall_exit = {
+        .system                 = "syscalls",
+        .reg                    = syscall_exit_register,
+        .define_fields          = syscall_exit_define_fields,
+        .get_fields             = syscall_get_exit_fields,
+        .raw_init               = init_syscall_trace,
 };
 
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+{
+        struct syscall_metadata *start;
+        struct syscall_metadata *stop;
+        char str[KSYM_SYMBOL_LEN];
+
+
+        start = (struct syscall_metadata *)__start_syscalls_metadata;
+        stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+        kallsyms_lookup(syscall, NULL, NULL, NULL, str);
+
+        for ( ; start < stop; start++) {
+                /*
+                 * Only compare after the "sys" prefix. Archs that use
+                 * syscall wrappers may have syscalls symbols aliases prefixed
+                 * with "SyS" instead of "sys", leading to an unwanted
+                 * mismatch.
+                 */
+                if (start->name && !strcmp(start->name + 3, str + 3))
+                        return start;
+        }
+        return NULL;
+}
+
+static struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+        if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
+                return NULL;
+
+        return syscalls_metadata[nr];
+}
+
 enum print_line_t
-print_syscall_enter(struct trace_iterator *iter, int flags)
+print_syscall_enter(struct trace_iterator *iter, int flags,
+                    struct trace_event *event)
 {
         struct trace_seq *s = &iter->seq;
         struct trace_entry *ent = iter->ent;
@@ -35,40 +111,52 @@ print_syscall_enter(struct trace_iterator *iter, int flags)
         struct syscall_metadata *entry;
         int i, ret, syscall;
 
-        trace_assign_type(trace, ent);
-
+        trace = (typeof(trace))ent;
         syscall = trace->nr;
-
         entry = syscall_nr_to_meta(syscall);
+
         if (!entry)
                 goto end;
 
+        if (entry->enter_event->event.type != ent->type) {
+                WARN_ON_ONCE(1);
+                goto end;
+        }
+
         ret = trace_seq_printf(s, "%s(", entry->name);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
         for (i = 0; i < entry->nb_args; i++) {
                 /* parameter types */
-                if (syscalls_flags.val & TRACE_SYSCALLS_OPT_TYPES) {
+                if (trace_flags & TRACE_ITER_VERBOSE) {
                         ret = trace_seq_printf(s, "%s ", entry->types[i]);
                         if (!ret)
                                 return TRACE_TYPE_PARTIAL_LINE;
                 }
                 /* parameter values */
-                ret = trace_seq_printf(s, "%s: %lx%s ", entry->args[i],
+                ret = trace_seq_printf(s, "%s: %lx%s", entry->args[i],
                                        trace->args[i],
-                                       i == entry->nb_args - 1 ? ")" : ",");
+                                       i == entry->nb_args - 1 ? "" : ", ");
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
+        ret = trace_seq_putc(s, ')');
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
 end:
-        trace_seq_printf(s, "\n");
+        ret =  trace_seq_putc(s, '\n');
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
         return TRACE_TYPE_HANDLED;
 }
 
 enum print_line_t
-print_syscall_exit(struct trace_iterator *iter, int flags)
+print_syscall_exit(struct trace_iterator *iter, int flags,
+                   struct trace_event *event)
 {
         struct trace_seq *s = &iter->seq;
         struct trace_entry *ent = iter->ent;
@@ -77,16 +165,20 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
         struct syscall_metadata *entry;
         int ret;
 
-        trace_assign_type(trace, ent);
-
+        trace = (typeof(trace))ent;
         syscall = trace->nr;
-
         entry = syscall_nr_to_meta(syscall);
+
         if (!entry) {
                 trace_seq_printf(s, "\n");
                 return TRACE_TYPE_HANDLED;
         }
 
+        if (entry->exit_event->event.type != ent->type) {
+                WARN_ON_ONCE(1);
+                return TRACE_TYPE_UNHANDLED;
+        }
+
         ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name,
                                 trace->ret);
         if (!ret)
@@ -95,62 +187,127 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_HANDLED;
 }
 
-void start_ftrace_syscalls(void)
+extern char *__bad_type_size(void);
+
+#define SYSCALL_FIELD(type, name)                                       \
+        sizeof(type) != sizeof(trace.name) ?                            \
+                __bad_type_size() :                                     \
+                #type, #name, offsetof(typeof(trace), name),            \
+                sizeof(trace.name), is_signed_type(type)
+
+static
+int  __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
 {
-        unsigned long flags;
-        struct task_struct *g, *t;
+        int i;
+        int pos = 0;
 
-        mutex_lock(&syscall_trace_lock);
+        /* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
+
+        pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+        for (i = 0; i < entry->nb_args; i++) {
+                pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s",
+                                entry->args[i], sizeof(unsigned long),
+                                i == entry->nb_args - 1 ? "" : ", ");
+        }
+        pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
+
+        for (i = 0; i < entry->nb_args; i++) {
+                pos += snprintf(buf + pos, LEN_OR_ZERO,
+                                ", ((unsigned long)(REC->%s))", entry->args[i]);
+        }
 
-        /* Don't enable the flag on the tasks twice */
-        if (++refcount != 1)
-                goto unlock;
+#undef LEN_OR_ZERO
 
-        arch_init_ftrace_syscalls();
-        read_lock_irqsave(&tasklist_lock, flags);
+        /* return the length of print_fmt */
+        return pos;
+}
 
-        do_each_thread(g, t) {
-                set_tsk_thread_flag(t, TIF_SYSCALL_FTRACE);
-        } while_each_thread(g, t);
+static int set_syscall_print_fmt(struct ftrace_event_call *call)
+{
+        char *print_fmt;
+        int len;
+        struct syscall_metadata *entry = call->data;
 
-        read_unlock_irqrestore(&tasklist_lock, flags);
+        if (entry->enter_event != call) {
+                call->print_fmt = "\"0x%lx\", REC->ret";
+                return 0;
+        }
 
-unlock:
-        mutex_unlock(&syscall_trace_lock);
+        /* First: called with 0 length to calculate the needed length */
+        len = __set_enter_print_fmt(entry, NULL, 0);
+
+        print_fmt = kmalloc(len + 1, GFP_KERNEL);
+        if (!print_fmt)
+                return -ENOMEM;
+
+        /* Second: actually write the @print_fmt */
+        __set_enter_print_fmt(entry, print_fmt, len + 1);
+        call->print_fmt = print_fmt;
+
+        return 0;
 }
 
-void stop_ftrace_syscalls(void)
+static void free_syscall_print_fmt(struct ftrace_event_call *call)
 {
-        unsigned long flags;
-        struct task_struct *g, *t;
+        struct syscall_metadata *entry = call->data;
 
-        mutex_lock(&syscall_trace_lock);
+        if (entry->enter_event == call)
+                kfree(call->print_fmt);
+}
 
-        /* There are perhaps still some users */
-        if (--refcount)
-                goto unlock;
+static int syscall_enter_define_fields(struct ftrace_event_call *call)
+{
+        struct syscall_trace_enter trace;
+        struct syscall_metadata *meta = call->data;
+        int ret;
+        int i;
+        int offset = offsetof(typeof(trace), args);
+
+        ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+        if (ret)
+                return ret;
+
+        for (i = 0; i < meta->nb_args; i++) {
+                ret = trace_define_field(call, meta->types[i],
+                                         meta->args[i], offset,
+                                         sizeof(unsigned long), 0,
+                                         FILTER_OTHER);
+                offset += sizeof(unsigned long);
+        }
 
-        read_lock_irqsave(&tasklist_lock, flags);
+        return ret;
+}
 
-        do_each_thread(g, t) {
-                clear_tsk_thread_flag(t, TIF_SYSCALL_FTRACE);
-        } while_each_thread(g, t);
+static int syscall_exit_define_fields(struct ftrace_event_call *call)
+{
+        struct syscall_trace_exit trace;
+        int ret;
 
-        read_unlock_irqrestore(&tasklist_lock, flags);
+        ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
+        if (ret)
+                return ret;
 
-unlock:
-        mutex_unlock(&syscall_trace_lock);
+        ret = trace_define_field(call, SYSCALL_FIELD(long, ret),
+                                 FILTER_OTHER);
+
+        return ret;
 }
 
-void ftrace_syscall_enter(struct pt_regs *regs)
+void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
         struct syscall_trace_enter *entry;
         struct syscall_metadata *sys_data;
         struct ring_buffer_event *event;
+        struct ring_buffer *buffer;
         int size;
         int syscall_nr;
 
         syscall_nr = syscall_get_nr(current, regs);
+        if (syscall_nr < 0)
+                return;
+        if (!test_bit(syscall_nr, enabled_enter_syscalls))
+                return;
 
         sys_data = syscall_nr_to_meta(syscall_nr);
         if (!sys_data)
@@ -158,8 +315,8 @@ void ftrace_syscall_enter(struct pt_regs *regs)
 
         size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
-        event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_ENTER, size,
-                                                        0, 0);
+        event = trace_current_buffer_lock_reserve(&buffer,
+                        sys_data->enter_event->event.type, size, 0, 0);
         if (!event)
                 return;
 
@@ -167,25 +324,31 @@ void ftrace_syscall_enter(struct pt_regs *regs)
         entry->nr = syscall_nr;
         syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
 
-        trace_current_buffer_unlock_commit(event, 0, 0);
-        trace_wake_up();
+        if (!filter_current_check_discard(buffer, sys_data->enter_event,
+                                          entry, event))
+                trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-void ftrace_syscall_exit(struct pt_regs *regs)
+void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 {
         struct syscall_trace_exit *entry;
         struct syscall_metadata *sys_data;
         struct ring_buffer_event *event;
+        struct ring_buffer *buffer;
         int syscall_nr;
 
         syscall_nr = syscall_get_nr(current, regs);
+        if (syscall_nr < 0)
+                return;
+        if (!test_bit(syscall_nr, enabled_exit_syscalls))
+                return;
 
         sys_data = syscall_nr_to_meta(syscall_nr);
         if (!sys_data)
                 return;
 
-        event = trace_current_buffer_lock_reserve(TRACE_SYSCALL_EXIT,
-                                sizeof(*entry), 0, 0);
+        event = trace_current_buffer_lock_reserve(&buffer,
+                        sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
         if (!event)
                 return;
 
@@ -193,58 +356,325 @@ void ftrace_syscall_exit(struct pt_regs *regs)
         entry->nr = syscall_nr;
         entry->ret = syscall_get_return_value(current, regs);
 
-        trace_current_buffer_unlock_commit(event, 0, 0);
-        trace_wake_up();
+        if (!filter_current_check_discard(buffer, sys_data->exit_event,
+                                          entry, event))
+                trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-static int init_syscall_tracer(struct trace_array *tr)
+int reg_event_syscall_enter(struct ftrace_event_call *call)
 {
-        start_ftrace_syscalls();
+        int ret = 0;
+        int num;
+
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
+        if (num < 0 || num >= NR_syscalls)
+                return -ENOSYS;
+        mutex_lock(&syscall_trace_lock);
+        if (!sys_refcount_enter)
+                ret = register_trace_sys_enter(ftrace_syscall_enter, NULL);
+        if (!ret) {
+                set_bit(num, enabled_enter_syscalls);
+                sys_refcount_enter++;
+        }
+        mutex_unlock(&syscall_trace_lock);
+        return ret;
+}
+
+void unreg_event_syscall_enter(struct ftrace_event_call *call)
+{
+        int num;
+
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
+        if (num < 0 || num >= NR_syscalls)
+                return;
+        mutex_lock(&syscall_trace_lock);
+        sys_refcount_enter--;
+        clear_bit(num, enabled_enter_syscalls);
+        if (!sys_refcount_enter)
+                unregister_trace_sys_enter(ftrace_syscall_enter, NULL);
+        mutex_unlock(&syscall_trace_lock);
+}
+
+int reg_event_syscall_exit(struct ftrace_event_call *call)
+{
+        int ret = 0;
+        int num;
+
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
+        if (num < 0 || num >= NR_syscalls)
+                return -ENOSYS;
+        mutex_lock(&syscall_trace_lock);
+        if (!sys_refcount_exit)
+                ret = register_trace_sys_exit(ftrace_syscall_exit, NULL);
+        if (!ret) {
+                set_bit(num, enabled_exit_syscalls);
+                sys_refcount_exit++;
+        }
+        mutex_unlock(&syscall_trace_lock);
+        return ret;
+}
+
+void unreg_event_syscall_exit(struct ftrace_event_call *call)
+{
+        int num;
+
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
+        if (num < 0 || num >= NR_syscalls)
+                return;
+        mutex_lock(&syscall_trace_lock);
+        sys_refcount_exit--;
+        clear_bit(num, enabled_exit_syscalls);
+        if (!sys_refcount_exit)
+                unregister_trace_sys_exit(ftrace_syscall_exit, NULL);
+        mutex_unlock(&syscall_trace_lock);
+}
+
+int init_syscall_trace(struct ftrace_event_call *call)
+{
+        int id;
+
+        if (set_syscall_print_fmt(call) < 0)
+                return -ENOMEM;
+
+        id = trace_event_raw_init(call);
+
+        if (id < 0) {
+                free_syscall_print_fmt(call);
+                return id;
+        }
+
+        return id;
+}
+
+unsigned long __init arch_syscall_addr(int nr)
+{
+        return (unsigned long)sys_call_table[nr];
+}
+
+int __init init_ftrace_syscalls(void)
+{
+        struct syscall_metadata *meta;
+        unsigned long addr;
+        int i;
+
+        syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
+                                        NR_syscalls, GFP_KERNEL);
+        if (!syscalls_metadata) {
+                WARN_ON(1);
+                return -ENOMEM;
+        }
+
+        for (i = 0; i < NR_syscalls; i++) {
+                addr = arch_syscall_addr(i);
+                meta = find_syscall_meta(addr);
+                if (!meta)
+                        continue;
+
+                meta->syscall_nr = i;
+                syscalls_metadata[i] = meta;
+        }
 
         return 0;
 }
+core_initcall(init_ftrace_syscalls);
+
+#ifdef CONFIG_PERF_EVENTS
+
+static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
+static int sys_perf_refcount_enter;
+static int sys_perf_refcount_exit;
 
-static void reset_syscall_tracer(struct trace_array *tr)
+static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
-        stop_ftrace_syscalls();
-        tracing_reset_online_cpus(tr);
+        struct syscall_metadata *sys_data;
+        struct syscall_trace_enter *rec;
+        struct hlist_head *head;
+        int syscall_nr;
+        int rctx;
+        int size;
+
+        syscall_nr = syscall_get_nr(current, regs);
+        if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
+                return;
+
+        sys_data = syscall_nr_to_meta(syscall_nr);
+        if (!sys_data)
+                return;
+
+        /* get the size after alignment with the u32 buffer size field */
+        size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
+        size = ALIGN(size + sizeof(u32), sizeof(u64));
+        size -= sizeof(u32);
+
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+                      "perf buffer not large enough"))
+                return;
+
+        rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
+                                sys_data->enter_event->event.type, regs, &rctx);
+        if (!rec)
+                return;
+
+        rec->nr = syscall_nr;
+        syscall_get_arguments(current, regs, 0, sys_data->nb_args,
+                               (unsigned long *)&rec->args);
+
+        head = this_cpu_ptr(sys_data->enter_event->perf_events);
+        perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
 }
 
-static struct trace_event syscall_enter_event = {
-        .type           = TRACE_SYSCALL_ENTER,
-        .trace          = print_syscall_enter,
-};
+int perf_sysenter_enable(struct ftrace_event_call *call)
+{
+        int ret = 0;
+        int num;
 
-static struct trace_event syscall_exit_event = {
-        .type           = TRACE_SYSCALL_EXIT,
-        .trace          = print_syscall_exit,
-};
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
-static struct tracer syscall_tracer __read_mostly = {
-        .name           = "syscall",
-        .init           = init_syscall_tracer,
-        .reset          = reset_syscall_tracer,
-        .flags          = &syscalls_flags,
-};
+        mutex_lock(&syscall_trace_lock);
+        if (!sys_perf_refcount_enter)
+                ret = register_trace_sys_enter(perf_syscall_enter, NULL);
+        if (ret) {
+                pr_info("event trace: Could not activate"
+                                "syscall entry trace point");
+        } else {
+                set_bit(num, enabled_perf_enter_syscalls);
+                sys_perf_refcount_enter++;
+        }
+        mutex_unlock(&syscall_trace_lock);
+        return ret;
+}
 
-__init int register_ftrace_syscalls(void)
+void perf_sysenter_disable(struct ftrace_event_call *call)
 {
-        int ret;
+        int num;
 
-        ret = register_ftrace_event(&syscall_enter_event);
-        if (!ret) {
-                printk(KERN_WARNING "event %d failed to register\n",
-                       syscall_enter_event.type);
-                WARN_ON_ONCE(1);
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
+
+        mutex_lock(&syscall_trace_lock);
+        sys_perf_refcount_enter--;
+        clear_bit(num, enabled_perf_enter_syscalls);
+        if (!sys_perf_refcount_enter)
+                unregister_trace_sys_enter(perf_syscall_enter, NULL);
+        mutex_unlock(&syscall_trace_lock);
+}
+
+static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
+{
+        struct syscall_metadata *sys_data;
+        struct syscall_trace_exit *rec;
+        struct hlist_head *head;
+        int syscall_nr;
+        int rctx;
+        int size;
+
+        syscall_nr = syscall_get_nr(current, regs);
+        if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
+                return;
+
+        sys_data = syscall_nr_to_meta(syscall_nr);
+        if (!sys_data)
+                return;
+
+        /* We can probably do that at build time */
+        size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
+        size -= sizeof(u32);
+
+        /*
+         * Impossible, but be paranoid with the future
+         * How to put this check outside runtime?
+         */
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+                "exit event has grown above perf buffer size"))
+                return;
+
+        rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
+                                sys_data->exit_event->event.type, regs, &rctx);
+        if (!rec)
+                return;
+
+        rec->nr = syscall_nr;
+        rec->ret = syscall_get_return_value(current, regs);
+
+        head = this_cpu_ptr(sys_data->exit_event->perf_events);
+        perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head);
+}
+
+int perf_sysexit_enable(struct ftrace_event_call *call)
+{
+        int ret = 0;
+        int num;
+
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
+
+        mutex_lock(&syscall_trace_lock);
+        if (!sys_perf_refcount_exit)
+                ret = register_trace_sys_exit(perf_syscall_exit, NULL);
+        if (ret) {
+                pr_info("event trace: Could not activate"
+                                "syscall exit trace point");
+        } else {
+                set_bit(num, enabled_perf_exit_syscalls);
+                sys_perf_refcount_exit++;
         }
+        mutex_unlock(&syscall_trace_lock);
+        return ret;
+}
 
-        ret = register_ftrace_event(&syscall_exit_event);
-        if (!ret) {
-                printk(KERN_WARNING "event %d failed to register\n",
-                       syscall_exit_event.type);
-                WARN_ON_ONCE(1);
+void perf_sysexit_disable(struct ftrace_event_call *call)
+{
+        int num;
+
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
+
+        mutex_lock(&syscall_trace_lock);
+        sys_perf_refcount_exit--;
+        clear_bit(num, enabled_perf_exit_syscalls);
+        if (!sys_perf_refcount_exit)
+                unregister_trace_sys_exit(perf_syscall_exit, NULL);
+        mutex_unlock(&syscall_trace_lock);
+}
+
+#endif /* CONFIG_PERF_EVENTS */
+
+static int syscall_enter_register(struct ftrace_event_call *event,
+                                 enum trace_reg type)
+{
+        switch (type) {
+        case TRACE_REG_REGISTER:
+                return reg_event_syscall_enter(event);
+        case TRACE_REG_UNREGISTER:
+                unreg_event_syscall_enter(event);
+                return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+        case TRACE_REG_PERF_REGISTER:
+                return perf_sysenter_enable(event);
+        case TRACE_REG_PERF_UNREGISTER:
+                perf_sysenter_disable(event);
+                return 0;
+#endif
         }
+        return 0;
+}
 
-        return register_tracer(&syscall_tracer);
+static int syscall_exit_register(struct ftrace_event_call *event,
+                                 enum trace_reg type)
+{
+        switch (type) {
+        case TRACE_REG_REGISTER:
+                return reg_event_syscall_exit(event);
+        case TRACE_REG_UNREGISTER:
+                unreg_event_syscall_exit(event);
+                return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+        case TRACE_REG_PERF_REGISTER:
+                return perf_sysexit_enable(event);
+        case TRACE_REG_PERF_UNREGISTER:
+                perf_sysexit_disable(event);
+                return 0;
+#endif
+        }
+        return 0;
 }
-device_initcall(register_ftrace_syscalls);
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
deleted file mode 100644
index f6693969287d..000000000000
--- a/kernel/trace/trace_sysprof.c
+++ /dev/null
@@ -1,328 +0,0 @@
-/*
- * trace stack traces
- *
- * Copyright (C) 2004-2008, Soeren Sandmann
- * Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com>
- * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
- */
-#include <linux/kallsyms.h>
-#include <linux/debugfs.h>
-#include <linux/hrtimer.h>
-#include <linux/uaccess.h>
-#include <linux/ftrace.h>
-#include <linux/module.h>
-#include <linux/irq.h>
-#include <linux/fs.h>
-
-#include <asm/stacktrace.h>
-
-#include "trace.h"
-
-static struct trace_array       *sysprof_trace;
-static int __read_mostly        tracer_enabled;
-
-/*
- * 1 msec sample interval by default:
- */
-static unsigned long sample_period = 1000000;
-static const unsigned int sample_max_depth = 512;
-
-static DEFINE_MUTEX(sample_timer_lock);
-/*
- * Per CPU hrtimers that do the profiling:
- */
-static DEFINE_PER_CPU(struct hrtimer, stack_trace_hrtimer);
-
-struct stack_frame {
-        const void __user       *next_fp;
-        unsigned long           return_address;
-};
-
-static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
-{
-        int ret;
-
-        if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
-                return 0;
-
-        ret = 1;
-        pagefault_disable();
-        if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
-                ret = 0;
-        pagefault_enable();
-
-        return ret;
-}
-
-struct backtrace_info {
-        struct trace_array_cpu  *data;
-        struct trace_array      *tr;
-        int                     pos;
-};
-
-static void
-backtrace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-        /* Ignore warnings */
-}
-
-static void backtrace_warning(void *data, char *msg)
-{
-        /* Ignore warnings */
-}
-
-static int backtrace_stack(void *data, char *name)
-{
-        /* Don't bother with IRQ stacks for now */
-        return -1;
-}
-
-static void backtrace_address(void *data, unsigned long addr, int reliable)
-{
-        struct backtrace_info *info = data;
-
-        if (info->pos < sample_max_depth && reliable) {
-                __trace_special(info->tr, info->data, 1, addr, 0);
-
-                info->pos++;
-        }
-}
-
-static const struct stacktrace_ops backtrace_ops = {
-        .warning                = backtrace_warning,
-        .warning_symbol         = backtrace_warning_symbol,
-        .stack                  = backtrace_stack,
-        .address                = backtrace_address,
-};
-
-static int
-trace_kernel(struct pt_regs *regs, struct trace_array *tr,
-             struct trace_array_cpu *data)
-{
-        struct backtrace_info info;
-        unsigned long bp;
-        char *stack;
-
-        info.tr = tr;
-        info.data = data;
-        info.pos = 1;
-
-        __trace_special(info.tr, info.data, 1, regs->ip, 0);
-
-        stack = ((char *)regs + sizeof(struct pt_regs));
-#ifdef CONFIG_FRAME_POINTER
-        bp = regs->bp;
-#else
-        bp = 0;
-#endif
-
-        dump_trace(NULL, regs, (void *)stack, bp, &backtrace_ops, &info);
-
-        return info.pos;
-}
-
-static void timer_notify(struct pt_regs *regs, int cpu)
-{
-        struct trace_array_cpu *data;
-        struct stack_frame frame;
-        struct trace_array *tr;
-        const void __user *fp;
-        int is_user;
-        int i;
-
-        if (!regs)
-                return;
-
-        tr = sysprof_trace;
-        data = tr->data[cpu];
-        is_user = user_mode(regs);
-
-        if (!current || current->pid == 0)
-                return;
-
-        if (is_user && current->state != TASK_RUNNING)
-                return;
-
-        __trace_special(tr, data, 0, 0, current->pid);
-
-        if (!is_user)
-                i = trace_kernel(regs, tr, data);
-        else
-                i = 0;
-
-        /*
-         * Trace user stack if we are not a kernel thread
-         */
-        if (current->mm && i < sample_max_depth) {
-                regs = (struct pt_regs *)current->thread.sp0 - 1;
-
-                fp = (void __user *)regs->bp;
-
-                __trace_special(tr, data, 2, regs->ip, 0);
-
-                while (i < sample_max_depth) {
-                        frame.next_fp = NULL;
-                        frame.return_address = 0;
-                        if (!copy_stack_frame(fp, &frame))
-                                break;
-                        if ((unsigned long)fp < regs->sp)
-                                break;
-
-                        __trace_special(tr, data, 2, frame.return_address,
-                                        (unsigned long)fp);
-                        fp = frame.next_fp;
-
-                        i++;
-                }
-
-        }
-
-        /*
-         * Special trace entry if we overflow the max depth:
-         */
-        if (i == sample_max_depth)
-                __trace_special(tr, data, -1, -1, -1);
-
-        __trace_special(tr, data, 3, current->pid, i);
-}
-
-static enum hrtimer_restart stack_trace_timer_fn(struct hrtimer *hrtimer)
-{
-        /* trace here */
-        timer_notify(get_irq_regs(), smp_processor_id());
-
-        hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
-
-        return HRTIMER_RESTART;
-}
-
-static void start_stack_timer(void *unused)
-{
-        struct hrtimer *hrtimer = &__get_cpu_var(stack_trace_hrtimer);
-
-        hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-        hrtimer->function = stack_trace_timer_fn;
-
-        hrtimer_start(hrtimer, ns_to_ktime(sample_period),
-                      HRTIMER_MODE_REL_PINNED);
-}
-
-static void start_stack_timers(void)
-{
-        on_each_cpu(start_stack_timer, NULL, 1);
-}
-
-static void stop_stack_timer(int cpu)
-{
-        struct hrtimer *hrtimer = &per_cpu(stack_trace_hrtimer, cpu);
-
-        hrtimer_cancel(hrtimer);
-}
-
-static void stop_stack_timers(void)
-{
-        int cpu;
-
-        for_each_online_cpu(cpu)
-                stop_stack_timer(cpu);
-}
-
-static void stop_stack_trace(struct trace_array *tr)
-{
-        mutex_lock(&sample_timer_lock);
-        stop_stack_timers();
-        tracer_enabled = 0;
-        mutex_unlock(&sample_timer_lock);
-}
-
-static int stack_trace_init(struct trace_array *tr)
-{
-        sysprof_trace = tr;
-
-        tracing_start_cmdline_record();
-
-        mutex_lock(&sample_timer_lock);
-        start_stack_timers();
-        tracer_enabled = 1;
-        mutex_unlock(&sample_timer_lock);
-        return 0;
-}
-
-static void stack_trace_reset(struct trace_array *tr)
-{
-        tracing_stop_cmdline_record();
-        stop_stack_trace(tr);
-}
-
-static struct tracer stack_trace __read_mostly =
-{
-        .name           = "sysprof",
-        .init           = stack_trace_init,
-        .reset          = stack_trace_reset,
-#ifdef CONFIG_FTRACE_SELFTEST
-        .selftest    = trace_selftest_startup_sysprof,
-#endif
-};
-
-__init static int init_stack_trace(void)
-{
-        return register_tracer(&stack_trace);
-}
-device_initcall(init_stack_trace);
-
-#define MAX_LONG_DIGITS 22
-
-static ssize_t
-sysprof_sample_read(struct file *filp, char __user *ubuf,
-                    size_t cnt, loff_t *ppos)
-{
-        char buf[MAX_LONG_DIGITS];
-        int r;
-
-        r = sprintf(buf, "%ld\n", nsecs_to_usecs(sample_period));
-
-        return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-}
-
-static ssize_t
-sysprof_sample_write(struct file *filp, const char __user *ubuf,
-                     size_t cnt, loff_t *ppos)
-{
-        char buf[MAX_LONG_DIGITS];
-        unsigned long val;
-
-        if (cnt > MAX_LONG_DIGITS-1)
-                cnt = MAX_LONG_DIGITS-1;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        val = simple_strtoul(buf, NULL, 10);
-        /*
-         * Enforce a minimum sample period of 100 usecs:
-         */
-        if (val < 100)
-                val = 100;
-
-        mutex_lock(&sample_timer_lock);
-        stop_stack_timers();
-        sample_period = val * 1000;
-        start_stack_timers();
-        mutex_unlock(&sample_timer_lock);
-
-        return cnt;
-}
-
-static const struct file_operations sysprof_sample_fops = {
-        .read           = sysprof_sample_read,
-        .write          = sysprof_sample_write,
-};
-
-void init_tracer_sysprof_debugfs(struct dentry *d_tracer)
-{
-
-        trace_create_file("sysprof_sample_period", 0644,
-                        d_tracer, NULL, &sysprof_sample_fops);
-}
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 97fcea4acce1..209b379a4721 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -9,6 +9,8 @@
 #include <trace/events/workqueue.h>
 #include <linux/list.h>
 #include <linux/percpu.h>
+#include <linux/slab.h>
+#include <linux/kref.h>
 #include "trace_stat.h"
 #include "trace.h"
 
@@ -16,6 +18,7 @@
 /* A cpu workqueue thread */
 struct cpu_workqueue_stats {
         struct list_head            list;
+        struct kref                 kref;
         int                         cpu;
         pid_t                       pid;
 /* Can be inserted from interrupt or user context, need to be atomic */
@@ -39,9 +42,15 @@ struct workqueue_global_stats {
 static DEFINE_PER_CPU(struct workqueue_global_stats, all_workqueue_stat);
 #define workqueue_cpu_stat(cpu) (&per_cpu(all_workqueue_stat, cpu))
 
+static void cpu_workqueue_stat_free(struct kref *kref)
+{
+        kfree(container_of(kref, struct cpu_workqueue_stats, kref));
+}
+
 /* Insertion of a work */
 static void
-probe_workqueue_insertion(struct task_struct *wq_thread,
+probe_workqueue_insertion(void *ignore,
+                          struct task_struct *wq_thread,
                           struct work_struct *work)
 {
         int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -62,7 +71,8 @@ found:
 
 /* Execution of a work */
 static void
-probe_workqueue_execution(struct task_struct *wq_thread,
+probe_workqueue_execution(void *ignore,
+                          struct task_struct *wq_thread,
                           struct work_struct *work)
 {
         int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -82,7 +92,8 @@ found:
 }
 
 /* Creation of a cpu workqueue thread */
-static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
+static void probe_workqueue_creation(void *ignore,
+                                     struct task_struct *wq_thread, int cpu)
 {
         struct cpu_workqueue_stats *cws;
         unsigned long flags;
@@ -96,8 +107,8 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
                 return;
         }
         INIT_LIST_HEAD(&cws->list);
+        kref_init(&cws->kref);
         cws->cpu = cpu;
-
         cws->pid = wq_thread->pid;
 
         spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
@@ -106,7 +117,8 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
 }
 
 /* Destruction of a cpu workqueue thread */
-static void probe_workqueue_destruction(struct task_struct *wq_thread)
+static void
+probe_workqueue_destruction(void *ignore, struct task_struct *wq_thread)
 {
         /* Workqueue only execute on one cpu */
         int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -118,7 +130,7 @@ static void probe_workqueue_destruction(struct task_struct *wq_thread)
                                                         list) {
                 if (node->pid == wq_thread->pid) {
                         list_del(&node->list);
-                        kfree(node);
+                        kref_put(&node->kref, cpu_workqueue_stat_free);
                         goto found;
                 }
         }
@@ -137,9 +149,11 @@ static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu)
 
         spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
 
-        if (!list_empty(&workqueue_cpu_stat(cpu)->list))
+        if (!list_empty(&workqueue_cpu_stat(cpu)->list)) {
                 ret = list_entry(workqueue_cpu_stat(cpu)->list.next,
                                  struct cpu_workqueue_stats, list);
+                kref_get(&ret->kref);
+        }
 
         spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
 
@@ -162,9 +176,9 @@ static void *workqueue_stat_start(struct tracer_stat *trace)
 static void *workqueue_stat_next(void *prev, int idx)
 {
         struct cpu_workqueue_stats *prev_cws = prev;
+        struct cpu_workqueue_stats *ret;
         int cpu = prev_cws->cpu;
         unsigned long flags;
-        void *ret = NULL;
 
         spin_lock_irqsave(&workqueue_cpu_stat(cpu)->lock, flags);
         if (list_is_last(&prev_cws->list, &workqueue_cpu_stat(cpu)->list)) {
@@ -175,11 +189,14 @@ static void *workqueue_stat_next(void *prev, int idx)
                                 return NULL;
                 } while (!(ret = workqueue_stat_start_cpu(cpu)));
                 return ret;
+        } else {
+                ret = list_entry(prev_cws->list.next,
+                                 struct cpu_workqueue_stats, list);
+                kref_get(&ret->kref);
         }
         spin_unlock_irqrestore(&workqueue_cpu_stat(cpu)->lock, flags);
 
-        return list_entry(prev_cws->list.next, struct cpu_workqueue_stats,
-                          list);
+        return ret;
 }
 
 static int workqueue_stat_show(struct seq_file *s, void *p)
@@ -203,6 +220,13 @@ static int workqueue_stat_show(struct seq_file *s, void *p)
         return 0;
 }
 
+static void workqueue_stat_release(void *stat)
+{
+        struct cpu_workqueue_stats *node = stat;
+
+        kref_put(&node->kref, cpu_workqueue_stat_free);
+}
+
 static int workqueue_stat_headers(struct seq_file *s)
 {
         seq_printf(s, "# CPU  INSERTED  EXECUTED   NAME\n");
@@ -215,6 +239,7 @@ struct tracer_stat workqueue_stats __read_mostly = {
         .stat_start = workqueue_stat_start,
         .stat_next = workqueue_stat_next,
         .stat_show = workqueue_stat_show,
+        .stat_release = workqueue_stat_release,
         .stat_headers = workqueue_stat_headers
 };
 
@@ -238,35 +263,35 @@ int __init trace_workqueue_early_init(void)
 {
         int ret, cpu;
 
-        ret = register_trace_workqueue_insertion(probe_workqueue_insertion);
+        for_each_possible_cpu(cpu) {
+                spin_lock_init(&workqueue_cpu_stat(cpu)->lock);
+                INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list);
+        }
+
+        ret = register_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
         if (ret)
                 goto out;
 
-        ret = register_trace_workqueue_execution(probe_workqueue_execution);
+        ret = register_trace_workqueue_execution(probe_workqueue_execution, NULL);
         if (ret)
                 goto no_insertion;
 
-        ret = register_trace_workqueue_creation(probe_workqueue_creation);
+        ret = register_trace_workqueue_creation(probe_workqueue_creation, NULL);
         if (ret)
                 goto no_execution;
 
-        ret = register_trace_workqueue_destruction(probe_workqueue_destruction);
+        ret = register_trace_workqueue_destruction(probe_workqueue_destruction, NULL);
         if (ret)
                 goto no_creation;
 
-        for_each_possible_cpu(cpu) {
-                spin_lock_init(&workqueue_cpu_stat(cpu)->lock);
-                INIT_LIST_HEAD(&workqueue_cpu_stat(cpu)->list);
-        }
-
         return 0;
 
 no_creation:
-        unregister_trace_workqueue_creation(probe_workqueue_creation);
+        unregister_trace_workqueue_creation(probe_workqueue_creation, NULL);
 no_execution:
-        unregister_trace_workqueue_execution(probe_workqueue_execution);
+        unregister_trace_workqueue_execution(probe_workqueue_execution, NULL);
 no_insertion:
-        unregister_trace_workqueue_insertion(probe_workqueue_insertion);
+        unregister_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
 out:
         pr_warning("trace_workqueue: unable to trace workqueues\n");