Merge branch 'wip-2.6.34' into old-private-masterarchived-private-master

31 files changed, 4305 insertions, 1361 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index b416512ad17f..13e13d428cd3 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -12,39 +12,37 @@ config NOP_TRACER
 config HAVE_FTRACE_NMI_ENTER
         bool
         help
-          See Documentation/trace/ftrace-implementation.txt
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_FUNCTION_TRACER
         bool
         help
-          See Documentation/trace/ftrace-implementation.txt
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_FUNCTION_GRAPH_TRACER
         bool
         help
-          See Documentation/trace/ftrace-implementation.txt
+          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
-          See Documentation/trace/ftrace-implementation.txt
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_DYNAMIC_FTRACE
         bool
         help
-          See Documentation/trace/ftrace-implementation.txt
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_FTRACE_MCOUNT_RECORD
         bool
         help
-          See Documentation/trace/ftrace-implementation.txt
+          See Documentation/trace/ftrace-design.txt
 
 config HAVE_HW_BRANCH_TRACER
         bool
@@ -52,7 +50,7 @@ config HAVE_HW_BRANCH_TRACER
 config HAVE_SYSCALL_TRACEPOINTS
         bool
         help
-          See Documentation/trace/ftrace-implementation.txt
+          See Documentation/trace/ftrace-design.txt
 
 config TRACER_MAX_TRACE
         bool
@@ -83,7 +81,7 @@ config RING_BUFFER_ALLOW_SWAP
 # 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.
+# hiding of the automatic options.
 
 config TRACING
         bool
@@ -119,7 +117,7 @@ menuconfig FTRACE
         bool "Tracers"
         default y if DEBUG_KERNEL
         help
-         Enable the kernel tracing infrastructure.
+          Enable the kernel tracing infrastructure.
 
 if FTRACE
 
@@ -133,7 +131,7 @@ config FUNCTION_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
@@ -150,7 +148,7 @@ 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.
 
 
@@ -173,7 +171,7 @@ 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.)
 
@@ -186,7 +184,7 @@ config PREEMPT_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
@@ -195,7 +193,7 @@ 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.)
 
@@ -222,7 +220,7 @@ 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.
 
@@ -265,19 +263,19 @@ 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"
@@ -288,7 +286,7 @@ 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
@@ -305,7 +303,7 @@ 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
@@ -330,15 +328,27 @@ config BRANCH_TRACER
 
           Say N if unsure.
 
-config POWER_TRACER
-        bool "Trace power consumption behavior"
-        depends on X86
-        select GENERIC_TRACER
+config KSYM_TRACER
+        bool "Trace read and write access on kernel memory locations"
+        depends on HAVE_HW_BREAKPOINT
+        select TRACING
+        help
+          This tracer helps find read and write operations on any given kernel
+          symbol i.e. /proc/kallsyms.
+
+config PROFILE_KSYM_TRACER
+        bool "Profile all kernel memory accesses on 'watched' variables"
+        depends on KSYM_TRACER
         help
-          This tracer helps developers to analyze and optimize the kernels
-          power management decisions, specifically the C-state and P-state
-          behavior.
+          This tracer profiles kernel accesses on variables watched through the
+          ksym tracer ftrace plugin. Depending upon the hardware, all read
+          and write operations on kernel variables can be monitored for
+          accesses.
+
+          The results will be displayed in:
+          /debugfs/tracing/profile_ksym
 
+          Say N if unsure.
 
 config STACK_TRACER
         bool "Trace max stack"
@@ -370,14 +380,14 @@ config HW_BRANCH_TRACER
         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.
+          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
+          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
@@ -396,15 +406,15 @@ config WORKQUEUE_TRACER
         bool "Trace workqueues"
         select GENERIC_TRACER
         help
-          The workqueue tracer provides some statistical informations
+          The workqueue tracer provides some statistical information
           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.
+          to evaluate the amount of work each of them has to perform.
           For example it can help a developer to decide whether he should
-          choose a per cpu workqueue instead of a singlethreaded one.
+          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
@@ -428,38 +438,55 @@ 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
@@ -518,8 +545,8 @@ 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
@@ -528,7 +555,7 @@ 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 26f03ac07c2b..78edc6490038 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -51,8 +51,12 @@ 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-$(CONFIG_KSYM_TRACER) += trace_ksym.o
 obj-$(CONFIG_EVENT_TRACING) += power-traces.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index d9d6206e0b14..b3bc91a3f510 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/smp_lock.h>
 #include <linux/time.h>
@@ -540,9 +541,10 @@ 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);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6dc4e5ef7a01..2404b59b3097 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;
                         }
@@ -231,7 +242,7 @@ static void ftrace_update_pid_func(void)
         func = __ftrace_trace_function;
 #endif
 
-        if (ftrace_pid_trace) {
+        if (!list_empty(&ftrace_pids)) {
                 set_ftrace_pid_function(func);
                 func = ftrace_pid_func;
         } else {
@@ -821,8 +832,6 @@ 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
@@ -889,36 +898,6 @@ 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;
@@ -1016,6 +995,21 @@ 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)
 {
@@ -1067,14 +1061,6 @@ 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;
@@ -1261,12 +1247,34 @@ 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());
@@ -1656,64 +1664,10 @@ 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:
@@ -1729,8 +1683,8 @@ 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;
         }
@@ -1747,7 +1701,7 @@ 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;
@@ -1756,9 +1710,10 @@ 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);
 
@@ -1773,6 +1728,7 @@ 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
@@ -1782,6 +1738,8 @@ 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
@@ -1803,7 +1761,7 @@ 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;
@@ -1812,6 +1770,7 @@ 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;
 
@@ -1826,7 +1785,7 @@ 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);
         }
 
@@ -1842,12 +1801,15 @@ 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;
 }
 
 /*
@@ -1876,8 +1838,9 @@ 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 = {
@@ -1991,7 +1954,7 @@ 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 */
@@ -2068,7 +2031,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
         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 */
@@ -2174,8 +2137,9 @@ 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 */
@@ -2221,10 +2185,9 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
             !trace_parser_cont(parser)) {
                 ret = ftrace_process_regex(parser->buffer,
                                            parser->idx, enable);
+                trace_parser_clear(parser);
                 if (ret)
                         goto out_unlock;
-
-                trace_parser_clear(parser);
         }
 
         ret = read;
@@ -2312,6 +2275,34 @@ 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;
@@ -2328,6 +2319,10 @@ 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
@@ -2410,6 +2405,7 @@ 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 *
@@ -2432,7 +2428,7 @@ static void *g_start(struct seq_file *m, loff_t *pos)
         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;
 
         return __g_next(m, pos);
@@ -2478,6 +2474,7 @@ ftrace_graph_open(struct inode *inode, struct file *file)
         mutex_lock(&graph_lock);
         if ((file->f_mode & FMODE_WRITE) &&
             (file->f_flags & O_TRUNC)) {
+                ftrace_graph_filter_enabled = 0;
                 ftrace_graph_count = 0;
                 memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
         }
@@ -2503,7 +2500,7 @@ 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;
@@ -2513,39 +2510,52 @@ 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
@@ -2555,16 +2565,11 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
         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_unlock;
-        }
-
         if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
                 ret = -ENOMEM;
                 goto out_unlock;
@@ -2624,7 +2629,7 @@ 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)
 {
@@ -2684,7 +2689,7 @@ 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,
@@ -2745,7 +2750,7 @@ 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);
 
@@ -2778,23 +2783,6 @@ 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;
@@ -2845,14 +2833,12 @@ 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)
@@ -2863,74 +2849,184 @@ 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)
@@ -3258,6 +3354,7 @@ 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;
@@ -3267,7 +3364,6 @@ 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;
@@ -3293,4 +3389,3 @@ void ftrace_graph_stop(void)
         ftrace_stop();
 }
 #endif
-
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index e06c6e3d56a3..a22582a06161 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -9,12 +9,9 @@
 #include <linux/workqueue.h>
 #include <linux/sched.h>
 #include <linux/module.h>
-#include <linux/slab.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/power.h>
 
-EXPORT_TRACEPOINT_SYMBOL_GPL(power_start);
-EXPORT_TRACEPOINT_SYMBOL_GPL(power_end);
 EXPORT_TRACEPOINT_SYMBOL_GPL(power_frequency);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 5dd017fea6f5..41ca394feb22 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"
 
 /*
@@ -206,6 +208,14 @@ EXPORT_SYMBOL_GPL(tracing_is_on);
 #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
 
@@ -397,18 +407,21 @@ int ring_buffer_print_page_header(struct trace_seq *s)
         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)sizeof(field.commit),
+                               (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;
 }
@@ -420,7 +433,7 @@ struct ring_buffer_per_cpu {
         int                             cpu;
         struct ring_buffer              *buffer;
         spinlock_t                      reader_lock;    /* serialize readers */
-        raw_spinlock_t                  lock;
+        arch_spinlock_t                 lock;
         struct lock_class_key           lock_key;
         struct list_head                *pages;
         struct buffer_page              *head_page;     /* read from head */
@@ -461,6 +474,8 @@ 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;
 };
 
@@ -995,7 +1010,7 @@ 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;
+        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));
@@ -1190,30 +1205,25 @@ 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;
+                        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;
+                goto out;
 
         rb_reset_cpu(cpu_buffer);
-        spin_unlock_irq(&cpu_buffer->reader_lock);
-
         rb_check_pages(cpu_buffer);
 
-        atomic_dec(&cpu_buffer->record_disabled);
-
+out:
+        spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
 static void
@@ -1224,26 +1234,22 @@ 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);
         }
         rb_reset_cpu(cpu_buffer);
-        spin_unlock_irq(&cpu_buffer->reader_lock);
-
         rb_check_pages(cpu_buffer);
 
-        atomic_dec(&cpu_buffer->record_disabled);
+out:
+        spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
 /**
@@ -1251,11 +1257,6 @@ 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.
@@ -1287,6 +1288,11 @@ 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();
 
@@ -1349,6 +1355,8 @@ 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:
@@ -1358,6 +1366,7 @@ 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;
 
         /*
@@ -1367,6 +1376,7 @@ 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);
@@ -1548,7 +1558,7 @@ rb_update_event(struct ring_buffer_event *event,
 
         case 0:
                 length -= RB_EVNT_HDR_SIZE;
-                if (length > RB_MAX_SMALL_DATA)
+                if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
                         event->array[0] = length;
                 else
                         event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
@@ -1723,11 +1733,11 @@ 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;
 }
@@ -1787,9 +1797,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 static 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 *commit_page = cpu_buffer->commit_page;
         struct ring_buffer *buffer = cpu_buffer->buffer;
         struct buffer_page *next_page;
         int ret;
@@ -1892,13 +1902,10 @@ static struct ring_buffer_event *
 __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
                   unsigned type, unsigned long length, u64 *ts)
 {
-        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();
         tail_page = cpu_buffer->tail_page;
         write = local_add_return(length, &tail_page->write);
 
@@ -1909,7 +1916,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
         /* See if we shot pass the end of this buffer page */
         if (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 */
 
@@ -2237,12 +2244,12 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
         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();
 
+        if (atomic_read(&buffer->record_disabled))
+                goto out_nocheck;
+
         if (trace_recursive_lock())
                 goto out_nocheck;
 
@@ -2474,11 +2481,11 @@ int ring_buffer_write(struct ring_buffer *buffer,
         if (ring_buffer_flags != RB_BUFFERS_ON)
                 return -EBUSY;
 
-        if (atomic_read(&buffer->record_disabled))
-                return -EBUSY;
-
         resched = ftrace_preempt_disable();
 
+        if (atomic_read(&buffer->record_disabled))
+                goto out;
+
         cpu = raw_smp_processor_id();
 
         if (!cpumask_test_cpu(cpu, buffer->cpumask))
@@ -2546,7 +2553,7 @@ 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)
 {
@@ -2582,7 +2589,7 @@ 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)
 {
@@ -2723,6 +2730,8 @@ 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;
 }
 
 /**
@@ -2834,7 +2843,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         int ret;
 
         local_irq_save(flags);
-        __raw_spin_lock(&cpu_buffer->lock);
+        arch_spin_lock(&cpu_buffer->lock);
 
  again:
         /*
@@ -2876,7 +2885,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
          * Splice the empty reader page into the list around the head.
          */
         reader = rb_set_head_page(cpu_buffer);
-        cpu_buffer->reader_page->list.next = reader->list.next;
+        cpu_buffer->reader_page->list.next = rb_list_head(reader->list.next);
         cpu_buffer->reader_page->list.prev = reader->list.prev;
 
         /*
@@ -2913,7 +2922,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
          *
          * Now make the new head point back to the reader page.
          */
-        reader->list.next->prev = &cpu_buffer->reader_page->list;
+        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 */
@@ -2923,7 +2932,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         goto again;
 
  out:
-        __raw_spin_unlock(&cpu_buffer->lock);
+        arch_spin_unlock(&cpu_buffer->lock);
         local_irq_restore(flags);
 
         return reader;
@@ -3067,13 +3076,22 @@ 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
@@ -3088,6 +3106,11 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
         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) {
@@ -3286,9 +3309,9 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
         synchronize_sched();
 
         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;
@@ -3408,11 +3431,11 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
         if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
                 goto out;
 
-        __raw_spin_lock(&cpu_buffer->lock);
+        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);
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 573d3cc762c3..df74c7982255 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;
@@ -208,15 +231,18 @@ 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 +289,27 @@ 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 +439,27 @@ 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 b20d3ec75de9..44f916a04065 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>
@@ -32,10 +32,11 @@
 #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"
@@ -86,25 +87,22 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
  */
 static int tracing_disabled = 1;
 
-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)
 
@@ -129,7 +127,7 @@ static int tracing_set_tracer(const char *buf);
 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, MAX_TRACER_SIZE);
         default_bootup_tracer = bootup_tracer_buf;
@@ -137,7 +135,7 @@ static int __init set_ftrace(char *str)
         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)
 {
@@ -203,7 +201,7 @@ 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;
@@ -243,12 +241,91 @@ static struct tracer		*current_trace __read_mostly;
 
 /*
  * 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.
  */
 static DEFINE_MUTEX(trace_types_lock);
 
+/*
+ * 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.
+ */
+
+#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);
 
@@ -297,6 +374,21 @@ static int __init set_buf_size(char *str)
 }
 __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 +405,6 @@ static const char *trace_options[] = {
         "bin",
         "block",
         "stacktrace",
-        "sched-tree",
         "trace_printk",
         "ftrace_preempt",
         "branch",
@@ -493,19 +584,20 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
  * 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
+ * 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 raw_spinlock_t ftrace_max_lock =
-        (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+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;
-unsigned long __read_mostly     tracing_thresh;
 
 /*
  * Copy the new maximum trace into the separate maximum-trace
@@ -516,7 +608,7 @@ 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 = tr->data[cpu];
+        struct trace_array_cpu *max_data;
 
         max_tr.cpu = cpu;
         max_tr.time_start = data->preempt_timestamp;
@@ -526,7 +618,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
         max_data->critical_start = data->critical_start;
         max_data->critical_end = data->critical_end;
 
-        memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
+        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;
@@ -555,13 +647,13 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
                 return;
 
         WARN_ON_ONCE(!irqs_disabled());
-        __raw_spin_lock(&ftrace_max_lock);
+        arch_spin_lock(&ftrace_max_lock);
 
         tr->buffer = max_tr.buffer;
         max_tr.buffer = buf;
 
         __update_max_tr(tr, tsk, cpu);
-        __raw_spin_unlock(&ftrace_max_lock);
+        arch_spin_unlock(&ftrace_max_lock);
 }
 
 /**
@@ -581,7 +673,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
                 return;
 
         WARN_ON_ONCE(!irqs_disabled());
-        __raw_spin_lock(&ftrace_max_lock);
+        arch_spin_lock(&ftrace_max_lock);
 
         ftrace_disable_cpu();
 
@@ -603,7 +695,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
         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 */
 
@@ -748,10 +840,10 @@ out:
         mutex_unlock(&trace_types_lock);
 }
 
-static 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();
 }
 
@@ -763,7 +855,7 @@ void tracing_reset(struct trace_array *tr, int cpu)
 
         /* Make sure all commits have finished */
         synchronize_sched();
-        __tracing_reset(tr, cpu);
+        __tracing_reset(buffer, cpu);
 
         ring_buffer_record_enable(buffer);
 }
@@ -781,7 +873,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
         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);
 }
@@ -802,7 +894,7 @@ 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;
@@ -858,6 +950,8 @@ void tracing_start(void)
                 goto out;
         }
 
+        /* Prevent the buffers from switching */
+        arch_spin_lock(&ftrace_max_lock);
 
         buffer = global_trace.buffer;
         if (buffer)
@@ -867,6 +961,8 @@ 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);
@@ -888,6 +984,9 @@ 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);
@@ -896,6 +995,8 @@ 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);
 }
@@ -915,7 +1016,7 @@ 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];
@@ -940,7 +1041,7 @@ 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[])
@@ -952,20 +1053,25 @@ 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();
 }
 
@@ -1085,7 +1191,7 @@ trace_function(struct trace_array *tr,
         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(buffer, TRACE_FN, sizeof(*entry),
@@ -1151,6 +1257,22 @@ void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
         __ftrace_trace_stack(tr->buffer, flags, skip, 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());
+}
+
 void
 ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
@@ -1162,6 +1284,13 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
         if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
                 return;
 
+        /*
+         * NMIs can not handle page faults, even with fix ups.
+         * The save user stack can (and often does) fault.
+         */
+        if (unlikely(in_nmi()))
+                return;
+
         event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
                                           sizeof(*entry), flags, pc);
         if (!event)
@@ -1251,8 +1380,8 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
  */
 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;
@@ -1283,7 +1412,7 @@ 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)
@@ -1300,11 +1429,13 @@ 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, 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:
@@ -1334,7 +1465,7 @@ int trace_array_printk(struct trace_array *tr,
 int trace_array_vprintk(struct trace_array *tr,
                         unsigned long ip, const char *fmt, va_list args)
 {
-        static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
+        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;
@@ -1360,12 +1491,9 @@ int trace_array_vprintk(struct trace_array *tr,
 
         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;
         buffer = tr->buffer;
         event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
@@ -1373,15 +1501,17 @@ int trace_array_vprintk(struct trace_array *tr,
         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, 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:
@@ -1515,6 +1645,8 @@ 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 */
@@ -1566,12 +1698,6 @@ static void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 }
 
 /*
- * 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.
  */
@@ -1609,21 +1735,34 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
                 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();
 }
 
@@ -1922,6 +2061,7 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 static int s_show(struct seq_file *m, void *v)
 {
         struct trace_iterator *iter = v;
+        int ret;
 
         if (iter->ent == NULL) {
                 if (iter->tr) {
@@ -1941,9 +2081,27 @@ static int s_show(struct seq_file *m, void *v)
                         if (!(trace_flags & TRACE_ITER_VERBOSE))
                                 print_func_help_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;
@@ -2253,7 +2411,7 @@ 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
@@ -2268,7 +2426,7 @@ 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);
@@ -2290,67 +2448,49 @@ static const struct file_operations tracing_cpumask_fops = {
         .write          = tracing_cpumask_write,
 };
 
-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 */
-        }
-
-        /* +1 for \0 */
-        buf = kmalloc(len + 1, 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 + 1);
+        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 */
@@ -2358,33 +2498,17 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 {
         struct tracer_flags *tracer_flags = trace->flags;
         struct tracer_opt *opts = NULL;
-        int ret = 0, i = 0;
-        int len;
+        int i;
 
         for (i = 0; tracer_flags->opts[i].name; i++) {
                 opts = &tracer_flags->opts[i];
-                len = strlen(opts->name);
 
-                if (strncmp(cmp, opts->name, len) == 0) {
-                        ret = trace->set_flag(tracer_flags->val,
-                                opts->bit, !neg);
-                        break;
-                }
+                if (strcmp(cmp, opts->name) == 0)
+                        return __set_tracer_option(trace, trace->flags,
+                                                   opts, neg);
         }
-        /* Not found */
-        if (!tracer_flags->opts[i].name)
-                return -EINVAL;
-
-        /* Refused to handle */
-        if (ret)
-                return ret;
-
-        if (neg)
-                tracer_flags->val &= ~opts->bit;
-        else
-                tracer_flags->val |= opts->bit;
 
-        return 0;
+        return -EINVAL;
 }
 
 static void set_tracer_flags(unsigned int mask, int enabled)
@@ -2404,7 +2528,7 @@ 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;
@@ -2416,16 +2540,15 @@ 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;
                 }
@@ -2445,9 +2568,18 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
         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,
 };
 
@@ -2821,22 +2953,6 @@ 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) {
@@ -2892,10 +3008,8 @@ 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);
 
@@ -3055,6 +3169,7 @@ waitagain:
         iter->pos = -1;
 
         trace_event_read_lock();
+        trace_access_lock(iter->cpu_file);
         while (find_next_entry_inc(iter) != NULL) {
                 enum print_line_t ret;
                 int len = iter->seq.len;
@@ -3071,6 +3186,7 @@ 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 */
@@ -3103,7 +3219,7 @@ 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,
@@ -3196,6 +3312,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
         }
 
         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++) {
@@ -3219,6 +3336,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
                 trace_seq_init(&iter->seq);
         }
 
+        trace_access_unlock(iter->cpu_file);
         trace_event_read_unlock();
         mutex_unlock(&iter->mutex);
 
@@ -3334,7 +3452,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
                                         size_t cnt, loff_t *fpos)
 {
         char *buf;
-        char *end;
 
         if (tracing_disabled)
                 return -EINVAL;
@@ -3342,7 +3459,7 @@ 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;
 
@@ -3350,35 +3467,31 @@ 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);
+        cnt = mark_printk("%s", buf);
         kfree(buf);
         *fpos += cnt;
 
         return cnt;
 }
 
-static ssize_t tracing_clock_read(struct file *filp, char __user *ubuf,
-                                  size_t cnt, loff_t *ppos)
+static int tracing_clock_show(struct seq_file *m, void *v)
 {
-        char buf[64];
-        int bufiter = 0;
         int i;
 
         for (i = 0; i < ARRAY_SIZE(trace_clocks); i++)
-                bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter,
+                seq_printf(m,
                         "%s%s%s%s", i ? " " : "",
                         i == trace_clock_id ? "[" : "", trace_clocks[i].name,
                         i == trace_clock_id ? "]" : "");
-        bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter, "\n");
+        seq_putc(m, '\n');
 
-        return simple_read_from_buffer(ubuf, cnt, ppos, buf, bufiter);
+        return 0;
 }
 
 static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
@@ -3420,6 +3533,13 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
         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,
@@ -3458,8 +3578,10 @@ static const struct file_operations tracing_mark_fops = {
 };
 
 static const struct file_operations trace_clock_fops = {
-        .open           = tracing_open_generic,
-        .read           = tracing_clock_read,
+        .open           = tracing_clock_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
         .write          = tracing_clock_write,
 };
 
@@ -3516,10 +3638,12 @@ 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;
 
@@ -3589,7 +3713,7 @@ 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,
@@ -3647,6 +3771,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
                 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) {
@@ -3694,6 +3819,7 @@ 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? */
@@ -3730,7 +3856,7 @@ 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);
 
@@ -3920,39 +4046,16 @@ 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;
@@ -4153,6 +4256,8 @@ 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,
@@ -4176,10 +4281,10 @@ static __init int tracer_init_debugfs(void)
 #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);
-#endif
 
         trace_create_file("README", 0444, d_tracer,
                         NULL, &tracing_readme_fops);
@@ -4279,8 +4384,8 @@ trace_printk_seq(struct trace_seq *s)
 
 static void __ftrace_dump(bool disable_tracing)
 {
-        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;
@@ -4290,7 +4395,7 @@ 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;
 
@@ -4365,7 +4470,7 @@ static void __ftrace_dump(bool disable_tracing)
         }
 
  out:
-        __raw_spin_unlock(&ftrace_dump_lock);
+        arch_spin_unlock(&ftrace_dump_lock);
         local_irq_restore(flags);
 }
 
@@ -4387,9 +4492,6 @@ __init static int tracer_alloc_buffers(void)
         if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
                 goto out_free_buffer_mask;
 
-        if (!zalloc_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;
@@ -4426,7 +4528,7 @@ __init static int tracer_alloc_buffers(void)
         /* Allocate the first page for all buffers */
         for_each_tracing_cpu(i) {
                 global_trace.data[i] = &per_cpu(global_trace_cpu, i);
-                max_tr.data[i] = &per_cpu(max_data, i);
+                max_tr.data[i] = &per_cpu(max_tr_data, i);
         }
 
         trace_init_cmdlines();
@@ -4447,8 +4549,6 @@ __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 405cb850b75d..2825ef2c0b15 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -11,6 +11,7 @@
 #include <linux/ftrace.h>
 #include <trace/boot.h>
 #include <linux/kmemtrace.h>
+#include <linux/hw_breakpoint.h>
 
 #include <linux/trace_seq.h>
 #include <linux/ftrace_event.h>
@@ -37,6 +38,7 @@ enum trace_type {
         TRACE_KMEM_ALLOC,
         TRACE_KMEM_FREE,
         TRACE_BLK,
+        TRACE_KSYM,
 
         __TRACE_LAST_TYPE,
 };
@@ -98,9 +100,32 @@ struct syscall_trace_enter {
 struct syscall_trace_exit {
         struct trace_entry      ent;
         int                     nr;
-        unsigned long           ret;
+        long                    ret;
 };
 
+struct kprobe_trace_entry {
+        struct trace_entry      ent;
+        unsigned long           ip;
+        int                     nargs;
+        unsigned long           args[];
+};
+
+#define SIZEOF_KPROBE_TRACE_ENTRY(n)                    \
+        (offsetof(struct kprobe_trace_entry, args) +    \
+        (sizeof(unsigned long) * (n)))
+
+struct kretprobe_trace_entry {
+        struct trace_entry      ent;
+        unsigned long           func;
+        unsigned long           ret_ip;
+        int                     nargs;
+        unsigned long           args[];
+};
+
+#define SIZEOF_KRETPROBE_TRACE_ENTRY(n)                 \
+        (offsetof(struct kretprobe_trace_entry, args) + \
+        (sizeof(unsigned long) * (n)))
+
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
@@ -209,6 +234,7 @@ extern void __ftrace_bad_type(void);
                           TRACE_KMEM_ALLOC);    \
                 IF_ASSIGN(var, ent, struct kmemtrace_free_entry,        \
                           TRACE_KMEM_FREE);     \
+                IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\
                 __ftrace_bad_type();                                    \
         } while (0)
 
@@ -246,6 +272,7 @@ 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)
@@ -264,6 +291,7 @@ 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);
@@ -364,11 +392,14 @@ int register_tracer(struct tracer *type);
 void unregister_tracer(struct tracer *type);
 int is_tracing_stopped(void);
 
+extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
+
 extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
+extern unsigned long tracing_thresh;
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 extern unsigned long tracing_max_latency;
-extern unsigned long tracing_thresh;
 
 void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
@@ -413,7 +444,7 @@ extern int DYN_FTRACE_TEST_NAME(void);
 
 extern int ring_buffer_expanded;
 extern bool tracing_selftest_disabled;
-DECLARE_PER_CPU(local_t, ftrace_cpu_disabled);
+DECLARE_PER_CPU(int, ftrace_cpu_disabled);
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 extern int trace_selftest_startup_function(struct tracer *trace,
@@ -438,6 +469,8 @@ 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);
+extern int trace_selftest_startup_ksym(struct tracer *trace,
+                                         struct trace_array *tr);
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
@@ -465,6 +498,7 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
 #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];
 
@@ -472,7 +506,7 @@ 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++) {
@@ -483,10 +517,6 @@ 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;
@@ -500,12 +530,12 @@ print_graph_function(struct trace_iterator *iter)
 }
 #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);
@@ -521,7 +551,7 @@ static inline int ftrace_trace_task(struct task_struct *task)
  * 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 lenght
+ * @idx: user input length
  * @size: buffer size
  */
 struct trace_parser {
@@ -569,18 +599,17 @@ 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_SLEEP_TIME           = 0x80000,
-        TRACE_ITER_GRAPH_TIME           = 0x100000,
+        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,
 };
 
 /*
@@ -687,7 +716,6 @@ struct event_filter {
         int                     n_preds;
         struct filter_pred      **preds;
         char                    *filter_string;
-        bool                    no_reset;
 };
 
 struct event_subsystem {
@@ -699,22 +727,40 @@ struct event_subsystem {
 };
 
 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 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,
@@ -730,7 +776,8 @@ 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->filter_active) &&
+            !filter_match_preds(call->filter, rec)) {
                 ring_buffer_discard_commit(buffer, event);
                 return 1;
         }
@@ -746,7 +793,8 @@ extern const char *__stop___trace_bprintk_fmt[];
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, id, tstruct, print)             \
-        extern struct ftrace_event_call event_##call;
+        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))
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 4a194f08f88c..b9bc4d470177 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -307,8 +307,23 @@ 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 20c5f92e28a8..9d589d8dcd1a 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.
  *
@@ -28,17 +31,17 @@
  */
 u64 notrace trace_clock_local(void)
 {
-        unsigned long flags;
         u64 clock;
+        int resched;
 
         /*
          * sched_clock() is an architecture implemented, fast, scalable,
          * lockless clock. It is not guaranteed to be coherent across
          * CPUs, nor across CPU idle events.
          */
-        raw_local_irq_save(flags);
+        resched = ftrace_preempt_disable();
         clock = sched_clock();
-        raw_local_irq_restore(flags);
+        ftrace_preempt_enable(resched);
 
         return clock;
 }
@@ -69,10 +72,10 @@ u64 notrace trace_clock(void)
 /* keep prev_time and lock in the same cacheline. */
 static struct {
         u64 prev_time;
-        raw_spinlock_t lock;
+        arch_spinlock_t lock;
 } trace_clock_struct ____cacheline_aligned_in_smp =
         {
-                .lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED,
+                .lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED,
         };
 
 u64 notrace trace_clock_global(void)
@@ -81,7 +84,7 @@ 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);
@@ -92,7 +95,7 @@ u64 notrace trace_clock_global(void)
         if (unlikely(in_nmi()))
                 goto out;
 
-        __raw_spin_lock(&trace_clock_struct.lock);
+        arch_spin_lock(&trace_clock_struct.lock);
 
         /*
          * TODO: if this happens often then maybe we should reset
@@ -104,10 +107,10 @@ u64 notrace trace_clock_global(void)
 
         trace_clock_struct.prev_time = now;
 
-        __raw_spin_unlock(&trace_clock_struct.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
index ead3d724599d..c16a08f399df 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -364,3 +364,19 @@ FTRACE_ENTRY(kmem_free, kmemtrace_free_entry,
         F_printk("type:%u call_site:%lx ptr:%p",
                  __entry->type_id, __entry->call_site, __entry->ptr)
 );
+
+FTRACE_ENTRY(ksym_trace, ksym_trace_entry,
+
+        TRACE_KSYM,
+
+        F_STRUCT(
+                __field(        unsigned long,  ip                        )
+                __field(        unsigned char,  type                      )
+                __array(        char         ,  cmd,       TASK_COMM_LEN  )
+                __field(        unsigned long,  addr                      )
+        ),
+
+        F_printk("ip: %pF type: %d ksym_name: %pS cmd: %s",
+                (void *)__entry->ip, (unsigned int)__entry->type,
+                (void *)__entry->addr,  __entry->cmd)
+);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
new file mode 100644
index 000000000000..0565bb42566f
--- /dev/null
+++ b/kernel/trace/trace_event_perf.c
@@ -0,0 +1,175 @@
+/*
+ * 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"
+
+DEFINE_PER_CPU(struct pt_regs, perf_trace_regs);
+EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs);
+
+EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
+
+static char *perf_trace_buf;
+static char *perf_trace_buf_nmi;
+
+/*
+ * 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_enable(struct ftrace_event_call *event)
+{
+        char *buf;
+        int ret = -ENOMEM;
+
+        if (event->perf_refcount++ > 0)
+                return 0;
+
+        if (!total_ref_count) {
+                buf = (char *)alloc_percpu(perf_trace_t);
+                if (!buf)
+                        goto fail_buf;
+
+                rcu_assign_pointer(perf_trace_buf, buf);
+
+                buf = (char *)alloc_percpu(perf_trace_t);
+                if (!buf)
+                        goto fail_buf_nmi;
+
+                rcu_assign_pointer(perf_trace_buf_nmi, buf);
+        }
+
+        ret = event->perf_event_enable(event);
+        if (!ret) {
+                total_ref_count++;
+                return 0;
+        }
+
+fail_buf_nmi:
+        if (!total_ref_count) {
+                free_percpu(perf_trace_buf_nmi);
+                free_percpu(perf_trace_buf);
+                perf_trace_buf_nmi = NULL;
+                perf_trace_buf = NULL;
+        }
+fail_buf:
+        event->perf_refcount--;
+
+        return ret;
+}
+
+int perf_trace_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 && event->perf_event_enable &&
+                    try_module_get(event->mod)) {
+                        ret = perf_trace_event_enable(event);
+                        break;
+                }
+        }
+        mutex_unlock(&event_mutex);
+
+        return ret;
+}
+
+static void perf_trace_event_disable(struct ftrace_event_call *event)
+{
+        char *buf, *nmi_buf;
+
+        if (--event->perf_refcount > 0)
+                return;
+
+        event->perf_event_disable(event);
+
+        if (!--total_ref_count) {
+                buf = perf_trace_buf;
+                rcu_assign_pointer(perf_trace_buf, NULL);
+
+                nmi_buf = perf_trace_buf_nmi;
+                rcu_assign_pointer(perf_trace_buf_nmi, NULL);
+
+                /*
+                 * Ensure every events in profiling have finished before
+                 * releasing the buffers
+                 */
+                synchronize_sched();
+
+                free_percpu(buf);
+                free_percpu(nmi_buf);
+        }
+}
+
+void perf_trace_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) {
+                        perf_trace_event_disable(event);
+                        module_put(event->mod);
+                        break;
+                }
+        }
+        mutex_unlock(&event_mutex);
+}
+
+__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
+                                       int *rctxp, unsigned long *irq_flags)
+{
+        struct trace_entry *entry;
+        char *trace_buf, *raw_data;
+        int pc, cpu;
+
+        BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
+
+        pc = preempt_count();
+
+        /* Protect the per cpu buffer, begin the rcu read side */
+        local_irq_save(*irq_flags);
+
+        *rctxp = perf_swevent_get_recursion_context();
+        if (*rctxp < 0)
+                goto err_recursion;
+
+        cpu = smp_processor_id();
+
+        if (in_nmi())
+                trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
+        else
+                trace_buf = rcu_dereference_sched(perf_trace_buf);
+
+        if (!trace_buf)
+                goto err;
+
+        raw_data = per_cpu_ptr(trace_buf, cpu);
+
+        /* 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;
+        tracing_generic_entry_update(entry, *irq_flags, pc);
+        entry->type = type;
+
+        return raw_data;
+err:
+        perf_swevent_put_recursion_context(*rctxp);
+err_recursion:
+        local_irq_restore(*irq_flags);
+        return NULL;
+}
+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 8d5c171cc998..000000000000
--- a/kernel/trace/trace_event_profile.c
+++ /dev/null
@@ -1,125 +0,0 @@
-/*
- * trace event based perf counter profiling
- *
- * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
- *
- */
-
-#include <linux/module.h>
-#include "trace.h"
-
-/*
- * We can't use a size but a type in alloc_percpu()
- * So let's create a dummy type that matches the desired size
- */
-typedef struct {char buf[FTRACE_MAX_PROFILE_SIZE];} profile_buf_t;
-
-char            *trace_profile_buf;
-EXPORT_SYMBOL_GPL(trace_profile_buf);
-
-char            *trace_profile_buf_nmi;
-EXPORT_SYMBOL_GPL(trace_profile_buf_nmi);
-
-/* Count the events in use (per event id, not per instance) */
-static int      total_profile_count;
-
-static int ftrace_profile_enable_event(struct ftrace_event_call *event)
-{
-        char *buf;
-        int ret = -ENOMEM;
-
-        if (atomic_inc_return(&event->profile_count))
-                return 0;
-
-        if (!total_profile_count) {
-                buf = (char *)alloc_percpu(profile_buf_t);
-                if (!buf)
-                        goto fail_buf;
-
-                rcu_assign_pointer(trace_profile_buf, buf);
-
-                buf = (char *)alloc_percpu(profile_buf_t);
-                if (!buf)
-                        goto fail_buf_nmi;
-
-                rcu_assign_pointer(trace_profile_buf_nmi, buf);
-        }
-
-        ret = event->profile_enable();
-        if (!ret) {
-                total_profile_count++;
-                return 0;
-        }
-
-fail_buf_nmi:
-        if (!total_profile_count) {
-                free_percpu(trace_profile_buf_nmi);
-                free_percpu(trace_profile_buf);
-                trace_profile_buf_nmi = NULL;
-                trace_profile_buf = NULL;
-        }
-fail_buf:
-        atomic_dec(&event->profile_count);
-
-        return ret;
-}
-
-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 && event->profile_enable &&
-                    try_module_get(event->mod)) {
-                        ret = ftrace_profile_enable_event(event);
-                        break;
-                }
-        }
-        mutex_unlock(&event_mutex);
-
-        return ret;
-}
-
-static void ftrace_profile_disable_event(struct ftrace_event_call *event)
-{
-        char *buf, *nmi_buf;
-
-        if (!atomic_add_negative(-1, &event->profile_count))
-                return;
-
-        event->profile_disable();
-
-        if (!--total_profile_count) {
-                buf = trace_profile_buf;
-                rcu_assign_pointer(trace_profile_buf, NULL);
-
-                nmi_buf = trace_profile_buf_nmi;
-                rcu_assign_pointer(trace_profile_buf_nmi, NULL);
-
-                /*
-                 * Ensure every events in profiling have finished before
-                 * releasing the buffers
-                 */
-                synchronize_sched();
-
-                free_percpu(buf);
-                free_percpu(nmi_buf);
-        }
-}
-
-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) {
-                        ftrace_profile_disable_event(event);
-                        module_put(event->mod);
-                        break;
-                }
-        }
-        mutex_unlock(&event_mutex);
-}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index d128f65778e6..c697c7043349 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -15,6 +15,7 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/slab.h>
 #include <linux/delay.h>
 
 #include <asm/setup.h>
@@ -60,10 +61,8 @@ int trace_define_field(struct ftrace_event_call *call, const char *type,
         return 0;
 
 err:
-        if (field) {
+        if (field)
                 kfree(field->name);
-                kfree(field->type);
-        }
         kfree(field);
 
         return -ENOMEM;
@@ -78,7 +77,7 @@ EXPORT_SYMBOL_GPL(trace_define_field);
         if (ret)                                                        \
                 return ret;
 
-int trace_define_common_fields(struct ftrace_event_call *call)
+static int trace_define_common_fields(struct ftrace_event_call *call)
 {
         int ret;
         struct trace_entry ent;
@@ -91,11 +90,8 @@ int trace_define_common_fields(struct ftrace_event_call *call)
 
         return ret;
 }
-EXPORT_SYMBOL_GPL(trace_define_common_fields);
-
-#ifdef CONFIG_MODULES
 
-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;
 
@@ -107,27 +103,49 @@ 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;
 
-static void ftrace_event_enable_disable(struct ftrace_event_call *call,
+        id = register_ftrace_event(call->event);
+        if (!id)
+                return -ENODEV;
+        call->id = id;
+        INIT_LIST_HEAD(&call->fields);
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(trace_event_raw_init);
+
+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(call->data);
+                        call->unregfunc(call);
                 }
                 break;
         case 1:
                 if (!call->enabled) {
-                        call->enabled = 1;
                         tracing_start_cmdline_record();
-                        call->regfunc(call->data);
+                        ret = call->regfunc(call);
+                        if (ret) {
+                                tracing_stop_cmdline_record();
+                                pr_info("event trace: Could not enable event "
+                                        "%s\n", call->name);
+                                break;
+                        }
+                        call->enabled = 1;
                 }
                 break;
         }
+
+        return ret;
 }
 
 static void ftrace_clear_events(void)
@@ -406,7 +424,7 @@ 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;
 
@@ -416,7 +434,7 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
         *ppos += cnt;
 
-        return cnt;
+        return ret ? ret : cnt;
 }
 
 static ssize_t
@@ -501,41 +519,16 @@ out:
         return ret;
 }
 
-extern char *__bad_type_size(void);
-
-#undef FIELD
-#define FIELD(type, name)                                               \
-        sizeof(type) != sizeof(field.name) ? __bad_type_size() :        \
-        #type, "common_" #name, offsetof(typeof(field), name),          \
-                sizeof(field.name)
-
-static int trace_write_header(struct trace_seq *s)
-{
-        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, lock_depth));
-}
-
 static ssize_t
 event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
                   loff_t *ppos)
 {
         struct ftrace_event_call *call = filp->private_data;
+        struct ftrace_event_field *field;
         struct trace_seq *s;
+        int common_field_count = 5;
         char *buf;
-        int r;
+        int r = 0;
 
         if (*ppos)
                 return 0;
@@ -546,14 +539,48 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 
         trace_seq_init(s);
 
-        /* If any of the first writes fail, so will the show_format. */
-
         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);
 
-        r = call->show_format(call, s);
+        list_for_each_entry_reverse(field, &call->fields, link) {
+                /*
+                 * Smartly shows the array type(except dynamic array).
+                 * Normal:
+                 *      field:TYPE VAR
+                 * If TYPE := TYPE[LEN], it is shown:
+                 *      field:TYPE VAR[LEN]
+                 */
+                const char *array_descriptor = strchr(field->type, '[');
+
+                if (!strncmp(field->type, "__data_loc", 10))
+                        array_descriptor = NULL;
+
+                if (!array_descriptor) {
+                        r = trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
+                                        "\tsize:%u;\tsigned:%d;\n",
+                                        field->type, field->name, field->offset,
+                                        field->size, !!field->is_signed);
+                } else {
+                        r = trace_seq_printf(s, "\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);
+                }
+
+                if (--common_field_count == 0)
+                        r = trace_seq_printf(s, "\n");
+
+                if (!r)
+                        break;
+        }
+
+        if (r)
+                r = trace_seq_printf(s, "\nprint fmt: %s\n",
+                                call->print_fmt);
+
         if (!r) {
                 /*
                  * ug!  The format output is bigger than a PAGE!!
@@ -878,9 +905,9 @@ 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;
 }
@@ -892,7 +919,6 @@ 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;
         int ret;
 
         /*
@@ -910,55 +936,72 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
         }
 
         if (call->regfunc)
-                entry = trace_create_file("enable", 0644, call->dir, call,
-                                          enable);
+                trace_create_file("enable", 0644, call->dir, call,
+                                  enable);
 
-        if (call->id && call->profile_enable)
-                entry = trace_create_file("id", 0444, call->dir, call,
-                                          id);
+        if (call->id && call->perf_event_enable)
+                trace_create_file("id", 0444, call->dir, call,
+                                  id);
 
         if (call->define_fields) {
-                ret = call->define_fields(call);
+                ret = trace_define_common_fields(call);
+                if (!ret)
+                        ret = call->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;
 }
 
-#define for_each_event(event, start, end)                       \
-        for (event = start;                                     \
-             (unsigned long)event < (unsigned long)end;         \
-             event++)
+static int __trace_add_event_call(struct ftrace_event_call *call)
+{
+        struct dentry *d_events;
+        int ret;
 
-#ifdef CONFIG_MODULES
+        if (!call->name)
+                return -EINVAL;
 
-static LIST_HEAD(ftrace_module_file_list);
+        if (call->raw_init) {
+                ret = call->raw_init(call);
+                if (ret < 0) {
+                        if (ret != -ENOSYS)
+                                pr_warning("Could not initialize trace "
+                                "events/%s\n", call->name);
+                        return ret;
+                }
+        }
 
-/*
- * Modules must own their file_operations to keep up with
- * reference counting.
- */
-struct ftrace_module_file_ops {
-        struct list_head                list;
-        struct module                   *mod;
-        struct file_operations          id;
-        struct file_operations          enable;
-        struct file_operations          format;
-        struct file_operations          filter;
-};
+        d_events = event_trace_events_dir();
+        if (!d_events)
+                return -ENOENT;
+
+        ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+                                &ftrace_enable_fops, &ftrace_event_filter_fops,
+                                &ftrace_event_format_fops);
+        if (!ret)
+                list_add(&call->list, &ftrace_events);
+
+        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);
+        mutex_unlock(&event_mutex);
+        return ret;
+}
 
 static void remove_subsystem_dir(const char *name)
 {
@@ -986,6 +1029,53 @@ static void remove_subsystem_dir(const char *name)
         }
 }
 
+/*
+ * 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)
+                __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->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;         \
+             event++)
+
+#ifdef CONFIG_MODULES
+
+static LIST_HEAD(ftrace_module_file_list);
+
+/*
+ * Modules must own their file_operations to keep up with
+ * reference counting.
+ */
+struct ftrace_module_file_ops {
+        struct list_head                list;
+        struct module                   *mod;
+        struct file_operations          id;
+        struct file_operations          enable;
+        struct file_operations          format;
+        struct file_operations          filter;
+};
+
 static struct ftrace_module_file_ops *
 trace_create_file_ops(struct module *mod)
 {
@@ -1043,7 +1133,7 @@ static void trace_module_add_events(struct module *mod)
                 if (!call->name)
                         continue;
                 if (call->raw_init) {
-                        ret = call->raw_init();
+                        ret = call->raw_init(call);
                         if (ret < 0) {
                                 if (ret != -ENOSYS)
                                         pr_warning("Could not initialize trace "
@@ -1061,10 +1151,11 @@ static void trace_module_add_events(struct module *mod)
                                 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);
+                ret = event_create_dir(call, d_events,
+                                       &file_ops->id, &file_ops->enable,
+                                       &file_ops->filter, &file_ops->format);
+                if (!ret)
+                        list_add(&call->list, &ftrace_events);
         }
 }
 
@@ -1078,14 +1169,7 @@ 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);
-                        remove_subsystem_dir(call->system);
+                        __trace_remove_event_call(call);
                 }
         }
 
@@ -1203,7 +1287,7 @@ static __init int event_trace_init(void)
                 if (!call->name)
                         continue;
                 if (call->raw_init) {
-                        ret = call->raw_init();
+                        ret = call->raw_init(call);
                         if (ret < 0) {
                                 if (ret != -ENOSYS)
                                         pr_warning("Could not initialize trace "
@@ -1211,10 +1295,12 @@ static __init int event_trace_init(void)
                                 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 = event_create_dir(call, d_events, &ftrace_event_id_fops,
+                                       &ftrace_enable_fops,
+                                       &ftrace_event_filter_fops,
+                                       &ftrace_event_format_fops);
+                if (!ret)
+                        list_add(&call->list, &ftrace_events);
         }
 
         while (true) {
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 98a6cc5c64ed..88c0b6dbd7fe 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 {
@@ -197,9 +199,9 @@ 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;
 }
@@ -210,10 +212,11 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event,
 {
         char **addr = (char **)(event + pred->offset);
         int cmp, match;
+        int len = strlen(*addr) + 1;    /* including tailing '\0' */
 
-        cmp = strncmp(*addr, pred->str_val, pred->str_len);
+        cmp = pred->regex.match(*addr, &pred->regex, len);
 
-        match = (!cmp) ^ pred->not;
+        match = cmp ^ pred->not;
 
         return match;
 }
@@ -237,9 +240,9 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event,
         char *addr = (char *)(event + str_loc);
         int cmp, match;
 
-        cmp = strncmp(addr, pred->str_val, str_len);
+        cmp = pred->regex.match(addr, &pred->regex, str_len);
 
-        match = (!cmp) ^ pred->not;
+        match = cmp ^ pred->not;
 
         return match;
 }
@@ -250,10 +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;
@@ -396,7 +522,7 @@ 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,
@@ -426,9 +552,8 @@ static void filter_disable_preds(struct ftrace_event_call *call)
                 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)
@@ -441,21 +566,24 @@ 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->filter_active = 0;
 }
 
-static 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;
 
-        if (call->filter)
-                return 0;
-
-        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);
 
         filter->n_preds = 0;
 
@@ -471,12 +599,24 @@ static 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;
 
-        return -ENOMEM;
+        call->filter_active = 0;
+        call->filter = __alloc_preds();
+        if (IS_ERR(call->filter))
+                return PTR_ERR(call->filter);
+
+        return 0;
 }
 
 static int init_subsystem_preds(struct event_subsystem *system)
@@ -499,14 +639,7 @@ static int init_subsystem_preds(struct event_subsystem *system)
         return 0;
 }
 
-enum {
-        FILTER_DISABLE_ALL,
-        FILTER_INIT_NO_RESET,
-        FILTER_SKIP_NO_RESET,
-};
-
-static void filter_free_subsystem_preds(struct event_subsystem *system,
-                                        int flag)
+static void filter_free_subsystem_preds(struct event_subsystem *system)
 {
         struct ftrace_event_call *call;
 
@@ -517,14 +650,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system,
                 if (strcmp(call->system, system->name) != 0)
                         continue;
 
-                if (flag == FILTER_INIT_NO_RESET) {
-                        call->filter->no_reset = false;
-                        continue;
-                }
-
-                if (flag == FILTER_SKIP_NO_RESET && call->filter->no_reset)
-                        continue;
-
                 filter_disable_preds(call);
                 remove_filter_string(call->filter);
         }
@@ -532,10 +657,10 @@ static void filter_free_subsystem_preds(struct event_subsystem *system,
 
 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) {
@@ -550,7 +675,6 @@ static int filter_add_pred_fn(struct filter_parse_state *ps,
                 return err;
 
         filter->n_preds++;
-        call->filter_active = 1;
 
         return 0;
 }
@@ -575,7 +699,10 @@ static bool is_string_field(struct ftrace_event_field *field)
 
 static int is_legal_op(struct ftrace_event_field *field, int op)
 {
-        if (is_string_field(field) && (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;
@@ -626,6 +753,7 @@ 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 event_filter *filter,
                            struct filter_pred *pred,
                            bool dry_run)
 {
@@ -660,21 +788,20 @@ static int filter_add_pred(struct filter_parse_state *ps,
         }
 
         if (is_string_field(field)) {
-                pred->str_len = field->size;
+                filter_build_regex(pred);
 
-                if (field->filter_type == FILTER_STATIC_STRING)
+                if (field->filter_type == FILTER_STATIC_STRING) {
                         fn = filter_pred_string;
-                else if (field->filter_type == FILTER_DYN_STRING)
+                        pred->regex.field_len = field->size;
+                } else if (field->filter_type == FILTER_DYN_STRING)
                         fn = filter_pred_strloc;
-                else {
+                else
                         fn = filter_pred_pchar;
-                        pred->str_len = strlen(pred->str_val);
-                }
         } 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;
@@ -694,45 +821,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
 
 add_pred_fn:
         if (!dry_run)
-                return filter_add_pred_fn(ps, call, pred, fn);
-        return 0;
-}
-
-static int filter_add_subsystem_pred(struct filter_parse_state *ps,
-                                     struct event_subsystem *system,
-                                     struct filter_pred *pred,
-                                     char *filter_string,
-                                     bool dry_run)
-{
-        struct ftrace_event_call *call;
-        int err = 0;
-        bool fail = true;
-
-        list_for_each_entry(call, &ftrace_events, list) {
-
-                if (!call->define_fields)
-                        continue;
-
-                if (strcmp(call->system, system->name))
-                        continue;
-
-                if (call->filter->no_reset)
-                        continue;
-
-                err = filter_add_pred(ps, call, pred, dry_run);
-                if (err)
-                        call->filter->no_reset = true;
-                else
-                        fail = false;
-
-                if (!dry_run)
-                        replace_filter_string(call->filter, filter_string);
-        }
-
-        if (fail) {
-                parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
-                return err;
-        }
+                return filter_add_pred_fn(ps, call, filter, pred, fn);
         return 0;
 }
 
@@ -1045,8 +1134,8 @@ 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;
 
@@ -1090,8 +1179,8 @@ 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,
                          bool dry_run)
@@ -1138,11 +1227,7 @@ static int replace_preds(struct event_subsystem *system,
 add_pred:
                 if (!pred)
                         return -ENOMEM;
-                if (call)
-                        err = filter_add_pred(ps, call, pred, false);
-                else
-                        err = filter_add_subsystem_pred(ps, system, pred,
-                                                filter_string, dry_run);
+                err = filter_add_pred(ps, call, filter, pred, dry_run);
                 filter_free_pred(pred);
                 if (err)
                         return err;
@@ -1153,10 +1238,50 @@ add_pred:
         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 (!call->define_fields)
+                        continue;
+
+                if (strcmp(call->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->filter_active = 1;
+                        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);
@@ -1168,8 +1293,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
         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;
@@ -1187,10 +1311,11 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
                 goto out;
         }
 
-        err = replace_preds(NULL, call, ps, filter_string, false);
+        err = replace_preds(call, call->filter, ps, filter_string, false);
         if (err)
                 append_filter_err(ps, call->filter);
-
+        else
+                call->filter_active = 1;
 out:
         filter_opstack_clear(ps);
         postfix_clear(ps);
@@ -1205,7 +1330,6 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
                                  char *filter_string)
 {
         int err;
-
         struct filter_parse_state *ps;
 
         mutex_lock(&event_mutex);
@@ -1215,10 +1339,9 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
                 goto out_unlock;
 
         if (!strcmp(strstrip(filter_string), "0")) {
-                filter_free_subsystem_preds(system, FILTER_DISABLE_ALL);
+                filter_free_subsystem_preds(system);
                 remove_filter_string(system->filter);
-                mutex_unlock(&event_mutex);
-                return 0;
+                goto out_unlock;
         }
 
         err = -ENOMEM;
@@ -1235,31 +1358,87 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
                 goto out;
         }
 
-        filter_free_subsystem_preds(system, FILTER_INIT_NO_RESET);
-
-        /* try to see the filter can be applied to which events */
-        err = replace_preds(system, NULL, ps, filter_string, true);
-        if (err) {
+        err = replace_system_preds(system, ps, filter_string);
+        if (err)
                 append_filter_err(ps, system->filter);
-                goto out;
+
+out:
+        filter_opstack_clear(ps);
+        postfix_clear(ps);
+        kfree(ps);
+out_unlock:
+        mutex_unlock(&event_mutex);
+
+        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->id == event_id)
+                        break;
         }
 
-        filter_free_subsystem_preds(system, FILTER_SKIP_NO_RESET);
+        err = -EINVAL;
+        if (!call)
+                goto out_unlock;
+
+        err = -EEXIST;
+        if (event->filter)
+                goto out_unlock;
 
-        /* really apply the filter to the events */
-        err = replace_preds(system, NULL, ps, filter_string, false);
-        if (err) {
-                append_filter_err(ps, system->filter);
-                filter_free_subsystem_preds(system, 2);
+        filter = __alloc_preds();
+        if (IS_ERR(filter)) {
+                err = PTR_ERR(filter);
+                goto out_unlock;
         }
 
-out:
+        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 9753fcc61bc5..e091f64ba6ce 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -48,11 +48,11 @@
 struct ____ftrace_##name {                                      \
         tstruct                                                 \
 };                                                              \
-static void __used ____ftrace_check_##name(void)                \
+static void __always_unused ____ftrace_check_##name(void)       \
 {                                                               \
         struct ____ftrace_##name *__entry = NULL;               \
                                                                 \
-        /* force cmpile-time check on F_printk() */             \
+        /* force compile-time check on F_printk() */            \
         printk(print);                                          \
 }
 
@@ -62,76 +62,6 @@ static void __used ____ftrace_check_##name(void)		\
 
 #include "trace_entries.h"
 
-
-#undef __field
-#define __field(type, item)                                             \
-        ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"      \
-                               "offset:%zu;\tsize:%zu;\n",              \
-                               offsetof(typeof(field), item),           \
-                               sizeof(field.item));                     \
-        if (!ret)                                                       \
-                return 0;
-
-#undef __field_desc
-#define __field_desc(type, container, item)                             \
-        ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"      \
-                               "offset:%zu;\tsize:%zu;\n",              \
-                               offsetof(typeof(field), container.item), \
-                               sizeof(field.container.item));           \
-        if (!ret)                                                       \
-                return 0;
-
-#undef __array
-#define __array(type, item, len)                                        \
-        ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
-                               "offset:%zu;\tsize:%zu;\n",              \
-                               offsetof(typeof(field), item),   \
-                               sizeof(field.item));             \
-        if (!ret)                                                       \
-                return 0;
-
-#undef __array_desc
-#define __array_desc(type, container, item, len)                        \
-        ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
-                               "offset:%zu;\tsize:%zu;\n",              \
-                               offsetof(typeof(field), container.item), \
-                               sizeof(field.container.item));           \
-        if (!ret)                                                       \
-                return 0;
-
-#undef __dynamic_array
-#define __dynamic_array(type, item)                                     \
-        ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"      \
-                               "offset:%zu;\tsize:0;\n",                \
-                               offsetof(typeof(field), item));          \
-        if (!ret)                                                       \
-                return 0;
-
-#undef F_printk
-#define F_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
-
-#undef __entry
-#define __entry REC
-
-#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)             \
-static int                                                              \
-ftrace_format_##name(struct ftrace_event_call *unused,                  \
-                     struct trace_seq *s)                               \
-{                                                                       \
-        struct struct_name field __attribute__((unused));               \
-        int ret = 0;                                                    \
-                                                                        \
-        tstruct;                                                        \
-                                                                        \
-        trace_seq_printf(s, "\nprint fmt: " print);                     \
-                                                                        \
-        return ret;                                                     \
-}
-
-#include "trace_entries.h"
-
-
 #undef __field
 #define __field(type, item)                                             \
         ret = trace_define_field(event_call, #type, #item,              \
@@ -156,7 +86,8 @@ ftrace_format_##name(struct ftrace_event_call *unused,			\
         BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);                         \
         ret = trace_define_field(event_call, #type "[" #len "]", #item, \
                                  offsetof(typeof(field), item),         \
-                                 sizeof(field.item), 0, FILTER_OTHER);  \
+                                 sizeof(field.item),                    \
+                                 is_signed_type(type), FILTER_OTHER);   \
         if (ret)                                                        \
                 return ret;
 
@@ -166,13 +97,18 @@ ftrace_format_##name(struct ftrace_event_call *unused,			\
         ret = trace_define_field(event_call, #type "[" #len "]", #item, \
                                  offsetof(typeof(field),                \
                                           container.item),              \
-                                 sizeof(field.container.item), 0,       \
-                                 FILTER_OTHER);                         \
+                                 sizeof(field.container.item),          \
+                                 is_signed_type(type), FILTER_OTHER);   \
         if (ret)                                                        \
                 return ret;
 
 #undef __dynamic_array
-#define __dynamic_array(type, item)
+#define __dynamic_array(type, item)                                     \
+        ret = trace_define_field(event_call, #type, #item,              \
+                                 offsetof(typeof(field), item),         \
+                                 0, is_signed_type(type), FILTER_OTHER);\
+        if (ret)                                                        \
+                return ret;
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(name, struct_name, id, tstruct, print)             \
@@ -182,10 +118,6 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
         struct struct_name field;                                       \
         int ret;                                                        \
                                                                         \
-        ret = trace_define_common_fields(event_call);                   \
-        if (ret)                                                        \
-                return ret;                                             \
-                                                                        \
         tstruct;                                                        \
                                                                         \
         return ret;                                                     \
@@ -193,6 +125,14 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 
 #include "trace_entries.h"
 
+static int ftrace_raw_init_event(struct ftrace_event_call *call)
+{
+        INIT_LIST_HEAD(&call->fields);
+        return 0;
+}
+
+#undef __entry
+#define __entry REC
 
 #undef __field
 #define __field(type, item)
@@ -209,9 +149,11 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 #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, type, tstruct, print)           \
-static int ftrace_raw_init_event_##call(void);                          \
                                                                         \
 struct ftrace_event_call __used                                         \
 __attribute__((__aligned__(4)))                                         \
@@ -219,14 +161,9 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
         .name                   = #call,                                \
         .id                     = type,                                 \
         .system                 = __stringify(TRACE_SYSTEM),            \
-        .raw_init               = ftrace_raw_init_event_##call,         \
-        .show_format            = ftrace_format_##call,                 \
+        .raw_init               = ftrace_raw_init_event,                \
+        .print_fmt              = print,                                \
         .define_fields          = ftrace_define_fields_##call,          \
 };                                                                      \
-static int ftrace_raw_init_event_##call(void)                           \
-{                                                                       \
-        INIT_LIST_HEAD(&event_##call.fields);                           \
-        return 0;                                                       \
-}                                                                       \
 
 #include "trace_entries.h"
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 45e6c01b2e4d..9aed1a5cf553 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -9,14 +9,27 @@
 #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 {
+struct fgraph_cpu_data {
         pid_t           last_pid;
         int             depth;
+        int             ignore;
+        unsigned long   enter_funcs[FTRACE_RETFUNC_DEPTH];
+};
+
+struct fgraph_data {
+        struct fgraph_cpu_data          *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
@@ -176,7 +189,7 @@ static int __trace_graph_entry(struct trace_array *tr,
         struct ring_buffer *buffer = tr->buffer;
         struct ftrace_graph_ent_entry *entry;
 
-        if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+        if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
                 return 0;
 
         event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
@@ -201,13 +214,11 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
         int cpu;
         int pc;
 
-        if (unlikely(!tr))
-                return 0;
-
         if (!ftrace_trace_task(current))
                 return 0;
 
-        if (!ftrace_graph_addr(trace->func))
+        /* trace it when it is-nested-in or is a function enabled. */
+        if (!(trace->depth || ftrace_graph_addr(trace->func)))
                 return 0;
 
         local_irq_save(flags);
@@ -220,9 +231,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
         } 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);
@@ -230,6 +238,14 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
         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_return(struct trace_array *tr,
                                 struct ftrace_graph_ret *trace,
                                 unsigned long flags,
@@ -240,7 +256,7 @@ static void __trace_graph_return(struct trace_array *tr,
         struct ring_buffer *buffer = tr->buffer;
         struct ftrace_graph_ret_entry *entry;
 
-        if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+        if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
                 return;
 
         event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
@@ -270,19 +286,39 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
                 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);
 }
 
+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;
 
-        graph_array = tr;
-        ret = register_ftrace_graph(&trace_graph_return,
-                                    &trace_graph_entry);
+        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();
@@ -290,11 +326,6 @@ static int graph_trace_init(struct trace_array *tr)
         return 0;
 }
 
-void set_graph_array(struct trace_array *tr)
-{
-        graph_array = tr;
-}
-
 static void graph_trace_reset(struct trace_array *tr)
 {
         tracing_stop_cmdline_record();
@@ -384,7 +415,7 @@ 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;
@@ -435,26 +466,49 @@ 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 {
 
-        /* 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);
-        }
+                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);
+                        event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
+                                                 NULL);
+                }
 
-        if (!event)
-                return NULL;
+                if (!event)
+                        return NULL;
 
-        next = ring_buffer_event_data(event);
+                next = ring_buffer_event_data(event);
+
+                if (data) {
+                        /*
+                         * Save current and next entries for later reference
+                         * if the output fails.
+                         */
+                        data->ent = *curr;
+                        data->ret = *next;
+                }
+        }
 
         if (next->ent.type != TRACE_GRAPH_RET)
                 return NULL;
@@ -639,15 +693,21 @@ 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 */
@@ -687,10 +747,15 @@ 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 */
@@ -782,19 +847,34 @@ static enum print_line_t
 print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
                         struct trace_iterator *iter)
 {
-        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 (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func))
                 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);
         else
-                return print_graph_entry_nested(iter, field, s, cpu);
+                ret = print_graph_entry_nested(iter, field, s, cpu);
+
+        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
@@ -805,19 +885,28 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
         struct fgraph_data *data = iter->private;
         pid_t pid = ent->pid;
         int cpu = iter->cpu;
+        int func_match = 1;
         int ret;
         int i;
 
         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))
@@ -842,9 +931,21 @@ 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) {
@@ -873,7 +974,7 @@ 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))
                 return TRACE_TYPE_PARTIAL_LINE;
@@ -941,8 +1042,33 @@ print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
 enum print_line_t
 print_graph_function(struct trace_iterator *iter)
 {
+        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);
+                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: {
@@ -952,7 +1078,7 @@ print_graph_function(struct trace_iterator *iter)
                  * sizeof(struct ftrace_graph_ent_entry) is very small,
                  * it can be safely saved at the stack.
                  */
-                struct ftrace_graph_ent_entry *field, saved;
+                struct ftrace_graph_ent_entry saved;
                 trace_assign_type(field, entry);
                 saved = *field;
                 return print_graph_entry(&saved, s, iter);
@@ -1030,31 +1156,54 @@ static void print_graph_headers(struct seq_file *s)
 static 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);
+                *pid = -1;
+                *depth = 0;
+                *ignore = 0;
+        }
 
         iter->private = data;
+
+        return;
+
+ out_err_free:
+        kfree(data);
+ out_err:
+        pr_warning("function graph tracer: not enough memory\n");
 }
 
 static void graph_trace_close(struct trace_iterator *iter)
 {
-        free_percpu(iter->private);
+        struct fgraph_data *data = iter->private;
+
+        if (data) {
+                free_percpu(data->cpu_data);
+                kfree(data);
+        }
 }
 
 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,
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
index 69543a905cd5..7b97000745f5 100644
--- a/kernel/trace/trace_hw_branches.c
+++ b/kernel/trace/trace_hw_branches.c
@@ -20,10 +20,10 @@
 
 #define BTS_BUFFER_SIZE (1 << 13)
 
-static DEFINE_PER_CPU(struct bts_tracer *, tracer);
-static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], buffer);
+static DEFINE_PER_CPU(struct bts_tracer *, hwb_tracer);
+static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], hwb_buffer);
 
-#define this_tracer per_cpu(tracer, smp_processor_id())
+#define this_tracer per_cpu(hwb_tracer, smp_processor_id())
 
 static int trace_hw_branches_enabled __read_mostly;
 static int trace_hw_branches_suspended __read_mostly;
@@ -32,12 +32,13 @@ 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);
+        per_cpu(hwb_tracer, cpu) =
+                ds_request_bts_cpu(cpu, per_cpu(hwb_buffer, cpu),
+                                   BTS_BUFFER_SIZE, NULL, (size_t)-1,
+                                   BTS_KERNEL);
 
-        if (IS_ERR(per_cpu(tracer, cpu)))
-                per_cpu(tracer, cpu) = NULL;
+        if (IS_ERR(per_cpu(hwb_tracer, cpu)))
+                per_cpu(hwb_tracer, cpu) = NULL;
 }
 
 static int bts_trace_init(struct trace_array *tr)
@@ -51,7 +52,7 @@ static int bts_trace_init(struct trace_array *tr)
         for_each_online_cpu(cpu) {
                 bts_trace_init_cpu(cpu);
 
-                if (likely(per_cpu(tracer, cpu)))
+                if (likely(per_cpu(hwb_tracer, cpu)))
                         trace_hw_branches_enabled = 1;
         }
         trace_hw_branches_suspended = 0;
@@ -67,9 +68,9 @@ static void bts_trace_reset(struct trace_array *tr)
 
         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;
+                if (likely(per_cpu(hwb_tracer, cpu))) {
+                        ds_release_bts(per_cpu(hwb_tracer, cpu));
+                        per_cpu(hwb_tracer, cpu) = NULL;
                 }
         }
         trace_hw_branches_enabled = 0;
@@ -83,8 +84,8 @@ static void bts_trace_start(struct trace_array *tr)
 
         get_online_cpus();
         for_each_online_cpu(cpu)
-                if (likely(per_cpu(tracer, cpu)))
-                        ds_resume_bts(per_cpu(tracer, cpu));
+                if (likely(per_cpu(hwb_tracer, cpu)))
+                        ds_resume_bts(per_cpu(hwb_tracer, cpu));
         trace_hw_branches_suspended = 0;
         put_online_cpus();
 }
@@ -95,8 +96,8 @@ static void bts_trace_stop(struct trace_array *tr)
 
         get_online_cpus();
         for_each_online_cpu(cpu)
-                if (likely(per_cpu(tracer, cpu)))
-                        ds_suspend_bts(per_cpu(tracer, cpu));
+                if (likely(per_cpu(hwb_tracer, cpu)))
+                        ds_suspend_bts(per_cpu(hwb_tracer, cpu));
         trace_hw_branches_suspended = 1;
         put_online_cpus();
 }
@@ -114,16 +115,16 @@ static int __cpuinit bts_hotcpu_handler(struct notifier_block *nfb,
                         bts_trace_init_cpu(cpu);
 
                         if (trace_hw_branches_suspended &&
-                            likely(per_cpu(tracer, cpu)))
-                                ds_suspend_bts(per_cpu(tracer, cpu));
+                            likely(per_cpu(hwb_tracer, cpu)))
+                                ds_suspend_bts(per_cpu(hwb_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;
+                if (likely(per_cpu(hwb_tracer, cpu))) {
+                        ds_release_bts(per_cpu(hwb_tracer, cpu));
+                        per_cpu(hwb_tracer, cpu) = NULL;
                 }
         }
 
@@ -258,8 +259,8 @@ static void trace_bts_prepare(struct trace_iterator *iter)
 
         get_online_cpus();
         for_each_online_cpu(cpu)
-                if (likely(per_cpu(tracer, cpu)))
-                        ds_suspend_bts(per_cpu(tracer, cpu));
+                if (likely(per_cpu(hwb_tracer, cpu)))
+                        ds_suspend_bts(per_cpu(hwb_tracer, cpu));
         /*
          * We need to collect the trace on the respective cpu since ftrace
          * implicitly adds the record for the current cpu.
@@ -268,8 +269,8 @@ static void trace_bts_prepare(struct trace_iterator *iter)
         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));
+                if (likely(per_cpu(hwb_tracer, cpu)))
+                        ds_resume_bts(per_cpu(hwb_tracer, cpu));
         put_online_cpus();
 }
 
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 3aa7eaa2114c..2974bc7538c7 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -151,6 +151,8 @@ check_critical_timing(struct trace_array *tr,
                 goto out_unlock;
 
         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;
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
new file mode 100644
index 000000000000..1251e367bae9
--- /dev/null
+++ b/kernel/trace/trace_kprobe.c
@@ -0,0 +1,1488 @@
+/*
+ * 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 "trace.h"
+#include "trace_output.h"
+
+#define MAX_TRACE_ARGS 128
+#define MAX_ARGSTR_LEN 63
+#define MAX_EVENT_NAME_LEN 64
+#define KPROBE_EVENT_SYSTEM "kprobes"
+
+/* Reserved field names */
+#define FIELD_STRING_IP "__probe_ip"
+#define FIELD_STRING_NARGS "__probe_nargs"
+#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_NARGS,
+        FIELD_STRING_RETIP,
+        FIELD_STRING_FUNC,
+};
+
+struct fetch_func {
+        unsigned long (*func)(struct pt_regs *, void *);
+        void *data;
+};
+
+static __kprobes unsigned long call_fetch(struct fetch_func *f,
+                                          struct pt_regs *regs)
+{
+        return f->func(regs, f->data);
+}
+
+/* fetch handlers */
+static __kprobes unsigned long fetch_register(struct pt_regs *regs,
+                                              void *offset)
+{
+        return regs_get_register(regs, (unsigned int)((unsigned long)offset));
+}
+
+static __kprobes unsigned long fetch_stack(struct pt_regs *regs,
+                                           void *num)
+{
+        return regs_get_kernel_stack_nth(regs,
+                                         (unsigned int)((unsigned long)num));
+}
+
+static __kprobes unsigned long fetch_memory(struct pt_regs *regs, void *addr)
+{
+        unsigned long retval;
+
+        if (probe_kernel_address(addr, retval))
+                return 0;
+        return retval;
+}
+
+static __kprobes unsigned long fetch_retvalue(struct pt_regs *regs,
+                                              void *dummy)
+{
+        return regs_return_value(regs);
+}
+
+static __kprobes unsigned long fetch_stack_address(struct pt_regs *regs,
+                                                   void *dummy)
+{
+        return kernel_stack_pointer(regs);
+}
+
+/* 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;
+}
+
+static __kprobes unsigned long fetch_symbol(struct pt_regs *regs, void *data)
+{
+        struct symbol_cache *sc = data;
+
+        if (sc->addr)
+                return fetch_memory(regs, (void *)sc->addr);
+        else
+                return 0;
+}
+
+/* Special indirect memory access interface */
+struct indirect_fetch_data {
+        struct fetch_func orig;
+        long offset;
+};
+
+static __kprobes unsigned long fetch_indirect(struct pt_regs *regs, void *data)
+{
+        struct indirect_fetch_data *ind = data;
+        unsigned long addr;
+
+        addr = call_fetch(&ind->orig, regs);
+        if (addr) {
+                addr += ind->offset;
+                return fetch_memory(regs, (void *)addr);
+        } else
+                return 0;
+}
+
+static __kprobes void free_indirect_fetch_data(struct indirect_fetch_data *data)
+{
+        if (data->orig.func == fetch_indirect)
+                free_indirect_fetch_data(data->orig.data);
+        else if (data->orig.func == fetch_symbol)
+                free_symbol_cache(data->orig.data);
+        kfree(data);
+}
+
+/**
+ * Kprobe event core functions
+ */
+
+struct probe_arg {
+        struct fetch_func       fetch;
+        const char              *name;
+};
+
+/* 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_call        call;
+        struct trace_event              event;
+        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 probe_arg_string(char *buf, size_t n, struct fetch_func *ff)
+{
+        int ret = -EINVAL;
+
+        if (ff->func == fetch_register) {
+                const char *name;
+                name = regs_query_register_name((unsigned int)((long)ff->data));
+                ret = snprintf(buf, n, "%%%s", name);
+        } else if (ff->func == fetch_stack)
+                ret = snprintf(buf, n, "$stack%lu", (unsigned long)ff->data);
+        else if (ff->func == fetch_memory)
+                ret = snprintf(buf, n, "@0x%p", ff->data);
+        else if (ff->func == fetch_symbol) {
+                struct symbol_cache *sc = ff->data;
+                if (sc->offset)
+                        ret = snprintf(buf, n, "@%s%+ld", sc->symbol,
+                                        sc->offset);
+                else
+                        ret = snprintf(buf, n, "@%s", sc->symbol);
+        } else if (ff->func == fetch_retvalue)
+                ret = snprintf(buf, n, "$retval");
+        else if (ff->func == fetch_stack_address)
+                ret = snprintf(buf, n, "$stack");
+        else if (ff->func == fetch_indirect) {
+                struct indirect_fetch_data *id = ff->data;
+                size_t l = 0;
+                ret = snprintf(buf, n, "%+ld(", id->offset);
+                if (ret >= n)
+                        goto end;
+                l += ret;
+                ret = probe_arg_string(buf + l, n - l, &id->orig);
+                if (ret < 0)
+                        goto end;
+                l += ret;
+                ret = snprintf(buf + l, n - l, ")");
+                ret += l;
+        }
+end:
+        if (ret >= n)
+                return -ENOSPC;
+        return ret;
+}
+
+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 */
+static int check_event_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 || !check_event_name(event)) {
+                ret = -EINVAL;
+                goto error;
+        }
+
+        tp->call.name = kstrdup(event, GFP_KERNEL);
+        if (!tp->call.name)
+                goto error;
+
+        if (!group || !check_event_name(group)) {
+                ret = -EINVAL;
+                goto error;
+        }
+
+        tp->call.system = kstrdup(group, GFP_KERNEL);
+        if (!tp->call.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 (arg->fetch.func == fetch_symbol)
+                free_symbol_cache(arg->fetch.data);
+        else if (arg->fetch.func == fetch_indirect)
+                free_indirect_fetch_data(arg->fetch.data);
+        kfree(arg->name);
+}
+
+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.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.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.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("Faild 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, struct fetch_func *ff, int is_return)
+{
+        int ret = 0;
+        unsigned long param;
+
+        if (strcmp(arg, "retval") == 0) {
+                if (is_return) {
+                        ff->func = fetch_retvalue;
+                        ff->data = NULL;
+                } else
+                        ret = -EINVAL;
+        } else if (strncmp(arg, "stack", 5) == 0) {
+                if (arg[5] == '\0') {
+                        ff->func = fetch_stack_address;
+                        ff->data = NULL;
+                } else if (isdigit(arg[5])) {
+                        ret = strict_strtoul(arg + 5, 10, &param);
+                        if (ret || param > PARAM_MAX_STACK)
+                                ret = -EINVAL;
+                        else {
+                                ff->func = fetch_stack;
+                                ff->data = (void *)param;
+                        }
+                } else
+                        ret = -EINVAL;
+        } else
+                ret = -EINVAL;
+        return ret;
+}
+
+/* Recursive argument parser */
+static int __parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+{
+        int ret = 0;
+        unsigned long param;
+        long offset;
+        char *tmp;
+
+        switch (arg[0]) {
+        case '$':
+                ret = parse_probe_vars(arg + 1, ff, is_return);
+                break;
+        case '%':       /* named register */
+                ret = regs_query_register_offset(arg + 1);
+                if (ret >= 0) {
+                        ff->func = fetch_register;
+                        ff->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;
+                        ff->func = fetch_memory;
+                        ff->data = (void *)param;
+                } else {
+                        ret = split_symbol_offset(arg + 1, &offset);
+                        if (ret)
+                                break;
+                        ff->data = alloc_symbol_cache(arg + 1, offset);
+                        if (ff->data)
+                                ff->func = fetch_symbol;
+                        else
+                                ret = -EINVAL;
+                }
+                break;
+        case '+':       /* indirect memory */
+        case '-':
+                tmp = strchr(arg, '(');
+                if (!tmp) {
+                        ret = -EINVAL;
+                        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 indirect_fetch_data *id;
+                        *tmp = '\0';
+                        id = kzalloc(sizeof(struct indirect_fetch_data),
+                                     GFP_KERNEL);
+                        if (!id)
+                                return -ENOMEM;
+                        id->offset = offset;
+                        ret = __parse_probe_arg(arg, &id->orig, is_return);
+                        if (ret)
+                                kfree(id);
+                        else {
+                                ff->func = fetch_indirect;
+                                ff->data = (void *)id;
+                        }
+                } else
+                        ret = -EINVAL;
+                break;
+        default:
+                /* TODO: support custom handler */
+                ret = -EINVAL;
+        }
+        return ret;
+}
+
+/* String length checking wrapper */
+static int parse_probe_arg(char *arg, struct fetch_func *ff, int is_return)
+{
+        if (strlen(arg) > MAX_ARGSTR_LEN) {
+                pr_info("Argument is too long.: %s\n",  arg);
+                return -ENOSPC;
+        }
+        return __parse_probe_arg(arg, ff, is_return);
+}
+
+/* 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
+         * Indirect memory fetch:
+         *  +|-offs(ARG) : fetch memory at ARG +|- offs address.
+         * Alias name of args:
+         *  NAME=FETCHARG : set NAME as alias of FETCHARG.
+         */
+        struct trace_probe *tp;
+        int i, ret = 0;
+        int is_return = 0, is_delete = 0;
+        char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL;
+        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;
+                }
+                tp = find_probe_event(event, group);
+                if (!tp) {
+                        pr_info("Event %s/%s doesn't exist.\n", group, event);
+                        return -ENOENT;
+                }
+                /* delete an event */
+                unregister_trace_probe(tp);
+                free_trace_probe(tp);
+                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++) {
+                /* Parse argument name */
+                arg = strchr(argv[i], '=');
+                if (arg)
+                        *arg++ = '\0';
+                else
+                        arg = argv[i];
+
+                if (conflict_field_name(argv[i], tp->args, i)) {
+                        pr_info("Argument%d name '%s' conflicts with "
+                                "another field.\n", i, argv[i]);
+                        ret = -EINVAL;
+                        goto error;
+                }
+
+                tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+                if (!tp->args[i].name) {
+                        pr_info("Failed to allocate argument%d name '%s'.\n",
+                                i, argv[i]);
+                        ret = -ENOMEM;
+                        goto error;
+                }
+
+                /* Parse fetch argument */
+                ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return);
+                if (ret) {
+                        pr_info("Parse error at argument%d. (%d)\n", i, ret);
+                        kfree(tp->args[i].name);
+                        goto error;
+                }
+
+                tp->nr_args++;
+        }
+
+        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, ret;
+        char buf[MAX_ARGSTR_LEN + 1];
+
+        seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
+        seq_printf(m, ":%s/%s", tp->call.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++) {
+                ret = probe_arg_string(buf, MAX_ARGSTR_LEN, &tp->args[i].fetch);
+                if (ret < 0) {
+                        pr_warning("Argument%d decoding error(%d).\n", i, ret);
+                        return ret;
+                }
+                seq_printf(m, " %s=%s", tp->args[i].name, buf);
+        }
+        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,
+};
+
+/* 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 *entry;
+        struct ring_buffer_event *event;
+        struct ring_buffer *buffer;
+        int size, i, pc;
+        unsigned long irq_flags;
+        struct ftrace_event_call *call = &tp->call;
+
+        tp->nhit++;
+
+        local_save_flags(irq_flags);
+        pc = preempt_count();
+
+        size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+
+        event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
+                                                  irq_flags, pc);
+        if (!event)
+                return;
+
+        entry = ring_buffer_event_data(event);
+        entry->nargs = tp->nr_args;
+        entry->ip = (unsigned long)kp->addr;
+        for (i = 0; i < tp->nr_args; i++)
+                entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+        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 *entry;
+        struct ring_buffer_event *event;
+        struct ring_buffer *buffer;
+        int size, i, pc;
+        unsigned long irq_flags;
+        struct ftrace_event_call *call = &tp->call;
+
+        local_save_flags(irq_flags);
+        pc = preempt_count();
+
+        size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+
+        event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
+                                                  irq_flags, pc);
+        if (!event)
+                return;
+
+        entry = ring_buffer_event_data(event);
+        entry->nargs = tp->nr_args;
+        entry->func = (unsigned long)tp->rp.kp.addr;
+        entry->ret_ip = (unsigned long)ri->ret_addr;
+        for (i = 0; i < tp->nr_args; i++)
+                entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+        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 kprobe_trace_entry *field;
+        struct trace_seq *s = &iter->seq;
+        struct trace_event *event;
+        struct trace_probe *tp;
+        int i;
+
+        field = (struct kprobe_trace_entry *)iter->ent;
+        event = ftrace_find_event(field->ent.type);
+        tp = container_of(event, struct trace_probe, 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;
+
+        for (i = 0; i < field->nargs; i++)
+                if (!trace_seq_printf(s, " %s=%lx",
+                                      tp->args[i].name, field->args[i]))
+                        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 kretprobe_trace_entry *field;
+        struct trace_seq *s = &iter->seq;
+        struct trace_event *event;
+        struct trace_probe *tp;
+        int i;
+
+        field = (struct kretprobe_trace_entry *)iter->ent;
+        event = ftrace_find_event(field->ent.type);
+        tp = container_of(event, struct trace_probe, 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;
+
+        for (i = 0; i < field->nargs; i++)
+                if (!trace_seq_printf(s, " %s=%lx",
+                                      tp->args[i].name, field->args[i]))
+                        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);
+        }
+}
+
+static int probe_event_raw_init(struct ftrace_event_call *event_call)
+{
+        INIT_LIST_HEAD(&event_call->fields);
+
+        return 0;
+}
+
+#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 field;
+        struct trace_probe *tp = (struct trace_probe *)event_call->data;
+
+        DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+        DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+        /* Set argument names as fields */
+        for (i = 0; i < tp->nr_args; i++)
+                DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+        return 0;
+}
+
+static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+        int ret, i;
+        struct kretprobe_trace_entry 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);
+        DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
+        /* Set argument names as fields */
+        for (i = 0; i < tp->nr_args; i++)
+                DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
+        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=%%lx",
+                                tp->args[i].name);
+        }
+
+        pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
+
+        for (i = 0; i < tp->nr_args; i++) {
+                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 *entry;
+        int size, __size, i;
+        unsigned long irq_flags;
+        int rctx;
+
+        __size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
+        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->id, &rctx, &irq_flags);
+        if (!entry)
+                return;
+
+        entry->nargs = tp->nr_args;
+        entry->ip = (unsigned long)kp->addr;
+        for (i = 0; i < tp->nr_args; i++)
+                entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+        perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs);
+}
+
+/* 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 *entry;
+        int size, __size, i;
+        unsigned long irq_flags;
+        int rctx;
+
+        __size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
+        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->id, &rctx, &irq_flags);
+        if (!entry)
+                return;
+
+        entry->nargs = tp->nr_args;
+        entry->func = (unsigned long)tp->rp.kp.addr;
+        entry->ret_ip = (unsigned long)ri->ret_addr;
+        for (i = 0; i < tp->nr_args; i++)
+                entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
+
+        perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1,
+                               irq_flags, regs);
+}
+
+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_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 int register_probe_event(struct trace_probe *tp)
+{
+        struct ftrace_event_call *call = &tp->call;
+        int ret;
+
+        /* Initialize ftrace_event_call */
+        if (probe_is_return(tp)) {
+                tp->event.trace = print_kretprobe_event;
+                call->raw_init = probe_event_raw_init;
+                call->define_fields = kretprobe_event_define_fields;
+        } else {
+                tp->event.trace = print_kprobe_event;
+                call->raw_init = probe_event_raw_init;
+                call->define_fields = kprobe_event_define_fields;
+        }
+        if (set_print_fmt(tp) < 0)
+                return -ENOMEM;
+        call->event = &tp->event;
+        call->id = register_ftrace_event(&tp->event);
+        if (!call->id) {
+                kfree(call->print_fmt);
+                return -ENODEV;
+        }
+        call->enabled = 0;
+        call->regfunc = probe_event_enable;
+        call->unregfunc = probe_event_disable;
+
+#ifdef CONFIG_PERF_EVENTS
+        call->perf_event_enable = probe_perf_enable;
+        call->perf_event_disable = probe_perf_disable;
+#endif
+        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(&tp->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_ksym.c b/kernel/trace/trace_ksym.c
new file mode 100644
index 000000000000..d59cd6879477
--- /dev/null
+++ b/kernel/trace/trace_ksym.c
@@ -0,0 +1,520 @@
+/*
+ * trace_ksym.c - Kernel Symbol Tracer
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+
+#include "trace_output.h"
+#include "trace.h"
+
+#include <linux/hw_breakpoint.h>
+#include <asm/hw_breakpoint.h>
+
+#include <asm/atomic.h>
+
+/*
+ * For now, let us restrict the no. of symbols traced simultaneously to number
+ * of available hardware breakpoint registers.
+ */
+#define KSYM_TRACER_MAX HBP_NUM
+
+#define KSYM_TRACER_OP_LEN 3 /* rw- */
+
+struct trace_ksym {
+        struct perf_event       **ksym_hbp;
+        struct perf_event_attr  attr;
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+        atomic64_t              counter;
+#endif
+        struct hlist_node       ksym_hlist;
+};
+
+static struct trace_array *ksym_trace_array;
+
+static unsigned int ksym_filter_entry_count;
+static unsigned int ksym_tracing_enabled;
+
+static HLIST_HEAD(ksym_filter_head);
+
+static DEFINE_MUTEX(ksym_tracer_mutex);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+
+#define MAX_UL_INT 0xffffffff
+
+void ksym_collect_stats(unsigned long hbp_hit_addr)
+{
+        struct hlist_node *node;
+        struct trace_ksym *entry;
+
+        rcu_read_lock();
+        hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) {
+                if (entry->attr.bp_addr == hbp_hit_addr) {
+                        atomic64_inc(&entry->counter);
+                        break;
+                }
+        }
+        rcu_read_unlock();
+}
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+void ksym_hbp_handler(struct perf_event *hbp, int nmi,
+                      struct perf_sample_data *data,
+                      struct pt_regs *regs)
+{
+        struct ring_buffer_event *event;
+        struct ksym_trace_entry *entry;
+        struct ring_buffer *buffer;
+        int pc;
+
+        if (!ksym_tracing_enabled)
+                return;
+
+        buffer = ksym_trace_array->buffer;
+
+        pc = preempt_count();
+
+        event = trace_buffer_lock_reserve(buffer, TRACE_KSYM,
+                                                        sizeof(*entry), 0, pc);
+        if (!event)
+                return;
+
+        entry           = ring_buffer_event_data(event);
+        entry->ip       = instruction_pointer(regs);
+        entry->type     = hw_breakpoint_type(hbp);
+        entry->addr     = hw_breakpoint_addr(hbp);
+        strlcpy(entry->cmd, current->comm, TASK_COMM_LEN);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+        ksym_collect_stats(hw_breakpoint_addr(hbp));
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+        trace_buffer_unlock_commit(buffer, event, 0, pc);
+}
+
+/* Valid access types are represented as
+ *
+ * rw- : Set Read/Write Access Breakpoint
+ * -w- : Set Write Access Breakpoint
+ * --- : Clear Breakpoints
+ * --x : Set Execution Break points (Not available yet)
+ *
+ */
+static int ksym_trace_get_access_type(char *str)
+{
+        int access = 0;
+
+        if (str[0] == 'r')
+                access |= HW_BREAKPOINT_R;
+
+        if (str[1] == 'w')
+                access |= HW_BREAKPOINT_W;
+
+        if (str[2] == 'x')
+                access |= HW_BREAKPOINT_X;
+
+        switch (access) {
+        case HW_BREAKPOINT_R:
+        case HW_BREAKPOINT_W:
+        case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
+                return access;
+        default:
+                return -EINVAL;
+        }
+}
+
+/*
+ * There can be several possible malformed requests and we attempt to capture
+ * all of them. We enumerate some of the rules
+ * 1. We will not allow kernel symbols with ':' since it is used as a delimiter.
+ *    i.e. multiple ':' symbols disallowed. Possible uses are of the form
+ *    <module>:<ksym_name>:<op>.
+ * 2. No delimiter symbol ':' in the input string
+ * 3. Spurious operator symbols or symbols not in their respective positions
+ * 4. <ksym_name>:--- i.e. clear breakpoint request when ksym_name not in file
+ * 5. Kernel symbol not a part of /proc/kallsyms
+ * 6. Duplicate requests
+ */
+static int parse_ksym_trace_str(char *input_string, char **ksymname,
+                                                        unsigned long *addr)
+{
+        int ret;
+
+        *ksymname = strsep(&input_string, ":");
+        *addr = kallsyms_lookup_name(*ksymname);
+
+        /* Check for malformed request: (2), (1) and (5) */
+        if ((!input_string) ||
+            (strlen(input_string) != KSYM_TRACER_OP_LEN) ||
+            (*addr == 0))
+                return -EINVAL;;
+
+        ret = ksym_trace_get_access_type(input_string);
+
+        return ret;
+}
+
+int process_new_ksym_entry(char *ksymname, int op, unsigned long addr)
+{
+        struct trace_ksym *entry;
+        int ret = -ENOMEM;
+
+        if (ksym_filter_entry_count >= KSYM_TRACER_MAX) {
+                printk(KERN_ERR "ksym_tracer: Maximum limit:(%d) reached. No"
+                " new requests for tracing can be accepted now.\n",
+                        KSYM_TRACER_MAX);
+                return -ENOSPC;
+        }
+
+        entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL);
+        if (!entry)
+                return -ENOMEM;
+
+        hw_breakpoint_init(&entry->attr);
+
+        entry->attr.bp_type = op;
+        entry->attr.bp_addr = addr;
+        entry->attr.bp_len = HW_BREAKPOINT_LEN_4;
+
+        entry->ksym_hbp = register_wide_hw_breakpoint(&entry->attr,
+                                        ksym_hbp_handler);
+
+        if (IS_ERR(entry->ksym_hbp)) {
+                ret = PTR_ERR(entry->ksym_hbp);
+                printk(KERN_INFO "ksym_tracer request failed. Try again"
+                                        " later!!\n");
+                goto err;
+        }
+
+        hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head);
+        ksym_filter_entry_count++;
+
+        return 0;
+
+err:
+        kfree(entry);
+
+        return ret;
+}
+
+static ssize_t ksym_trace_filter_read(struct file *filp, char __user *ubuf,
+                                                size_t count, loff_t *ppos)
+{
+        struct trace_ksym *entry;
+        struct hlist_node *node;
+        struct trace_seq *s;
+        ssize_t cnt = 0;
+        int ret;
+
+        s = kmalloc(sizeof(*s), GFP_KERNEL);
+        if (!s)
+                return -ENOMEM;
+        trace_seq_init(s);
+
+        mutex_lock(&ksym_tracer_mutex);
+
+        hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+                ret = trace_seq_printf(s, "%pS:",
+                                (void *)(unsigned long)entry->attr.bp_addr);
+                if (entry->attr.bp_type == HW_BREAKPOINT_R)
+                        ret = trace_seq_puts(s, "r--\n");
+                else if (entry->attr.bp_type == HW_BREAKPOINT_W)
+                        ret = trace_seq_puts(s, "-w-\n");
+                else if (entry->attr.bp_type == (HW_BREAKPOINT_W | HW_BREAKPOINT_R))
+                        ret = trace_seq_puts(s, "rw-\n");
+                WARN_ON_ONCE(!ret);
+        }
+
+        cnt = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+
+        mutex_unlock(&ksym_tracer_mutex);
+
+        kfree(s);
+
+        return cnt;
+}
+
+static void __ksym_trace_reset(void)
+{
+        struct trace_ksym *entry;
+        struct hlist_node *node, *node1;
+
+        mutex_lock(&ksym_tracer_mutex);
+        hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head,
+                                                                ksym_hlist) {
+                unregister_wide_hw_breakpoint(entry->ksym_hbp);
+                ksym_filter_entry_count--;
+                hlist_del_rcu(&(entry->ksym_hlist));
+                synchronize_rcu();
+                kfree(entry);
+        }
+        mutex_unlock(&ksym_tracer_mutex);
+}
+
+static ssize_t ksym_trace_filter_write(struct file *file,
+                                        const char __user *buffer,
+                                                size_t count, loff_t *ppos)
+{
+        struct trace_ksym *entry;
+        struct hlist_node *node;
+        char *buf, *input_string, *ksymname = NULL;
+        unsigned long ksym_addr = 0;
+        int ret, op, changed = 0;
+
+        buf = kzalloc(count + 1, GFP_KERNEL);
+        if (!buf)
+                return -ENOMEM;
+
+        ret = -EFAULT;
+        if (copy_from_user(buf, buffer, count))
+                goto out;
+
+        buf[count] = '\0';
+        input_string = strstrip(buf);
+
+        /*
+         * Clear all breakpoints if:
+         * 1: echo > ksym_trace_filter
+         * 2: echo 0 > ksym_trace_filter
+         * 3: echo "*:---" > ksym_trace_filter
+         */
+        if (!input_string[0] || !strcmp(input_string, "0") ||
+            !strcmp(input_string, "*:---")) {
+                __ksym_trace_reset();
+                ret = 0;
+                goto out;
+        }
+
+        ret = op = parse_ksym_trace_str(input_string, &ksymname, &ksym_addr);
+        if (ret < 0)
+                goto out;
+
+        mutex_lock(&ksym_tracer_mutex);
+
+        ret = -EINVAL;
+        hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) {
+                if (entry->attr.bp_addr == ksym_addr) {
+                        /* Check for malformed request: (6) */
+                        if (entry->attr.bp_type != op)
+                                changed = 1;
+                        else
+                                goto out_unlock;
+                        break;
+                }
+        }
+        if (changed) {
+                unregister_wide_hw_breakpoint(entry->ksym_hbp);
+                entry->attr.bp_type = op;
+                ret = 0;
+                if (op > 0) {
+                        entry->ksym_hbp =
+                                register_wide_hw_breakpoint(&entry->attr,
+                                        ksym_hbp_handler);
+                        if (IS_ERR(entry->ksym_hbp))
+                                ret = PTR_ERR(entry->ksym_hbp);
+                        else
+                                goto out_unlock;
+                }
+                /* Error or "symbol:---" case: drop it */
+                ksym_filter_entry_count--;
+                hlist_del_rcu(&(entry->ksym_hlist));
+                synchronize_rcu();
+                kfree(entry);
+                goto out_unlock;
+        } else {
+                /* Check for malformed request: (4) */
+                if (op)
+                        ret = process_new_ksym_entry(ksymname, op, ksym_addr);
+        }
+out_unlock:
+        mutex_unlock(&ksym_tracer_mutex);
+out:
+        kfree(buf);
+        return !ret ? count : ret;
+}
+
+static const struct file_operations ksym_tracing_fops = {
+        .open           = tracing_open_generic,
+        .read           = ksym_trace_filter_read,
+        .write          = ksym_trace_filter_write,
+};
+
+static void ksym_trace_reset(struct trace_array *tr)
+{
+        ksym_tracing_enabled = 0;
+        __ksym_trace_reset();
+}
+
+static int ksym_trace_init(struct trace_array *tr)
+{
+        int cpu, ret = 0;
+
+        for_each_online_cpu(cpu)
+                tracing_reset(tr, cpu);
+        ksym_tracing_enabled = 1;
+        ksym_trace_array = tr;
+
+        return ret;
+}
+
+static void ksym_trace_print_header(struct seq_file *m)
+{
+        seq_puts(m,
+                 "#       TASK-PID   CPU#      Symbol                    "
+                 "Type    Function\n");
+        seq_puts(m,
+                 "#          |        |          |                       "
+                 " |         |\n");
+}
+
+static enum print_line_t ksym_trace_output(struct trace_iterator *iter)
+{
+        struct trace_entry *entry = iter->ent;
+        struct trace_seq *s = &iter->seq;
+        struct ksym_trace_entry *field;
+        char str[KSYM_SYMBOL_LEN];
+        int ret;
+
+        if (entry->type != TRACE_KSYM)
+                return TRACE_TYPE_UNHANDLED;
+
+        trace_assign_type(field, entry);
+
+        ret = trace_seq_printf(s, "%11s-%-5d [%03d] %pS", field->cmd,
+                                entry->pid, iter->cpu, (char *)field->addr);
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
+        switch (field->type) {
+        case HW_BREAKPOINT_R:
+                ret = trace_seq_printf(s, " R  ");
+                break;
+        case HW_BREAKPOINT_W:
+                ret = trace_seq_printf(s, " W  ");
+                break;
+        case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
+                ret = trace_seq_printf(s, " RW ");
+                break;
+        default:
+                return TRACE_TYPE_PARTIAL_LINE;
+        }
+
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
+        sprint_symbol(str, field->ip);
+        ret = trace_seq_printf(s, "%s\n", str);
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
+
+        return TRACE_TYPE_HANDLED;
+}
+
+struct tracer ksym_tracer __read_mostly =
+{
+        .name           = "ksym_tracer",
+        .init           = ksym_trace_init,
+        .reset          = ksym_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+        .selftest       = trace_selftest_startup_ksym,
+#endif
+        .print_header   = ksym_trace_print_header,
+        .print_line     = ksym_trace_output
+};
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+static int ksym_profile_show(struct seq_file *m, void *v)
+{
+        struct hlist_node *node;
+        struct trace_ksym *entry;
+        int access_type = 0;
+        char fn_name[KSYM_NAME_LEN];
+
+        seq_puts(m, "  Access Type ");
+        seq_puts(m, "  Symbol                                       Counter\n");
+        seq_puts(m, "  ----------- ");
+        seq_puts(m, "  ------                                       -------\n");
+
+        rcu_read_lock();
+        hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) {
+
+                access_type = entry->attr.bp_type;
+
+                switch (access_type) {
+                case HW_BREAKPOINT_R:
+                        seq_puts(m, "  R           ");
+                        break;
+                case HW_BREAKPOINT_W:
+                        seq_puts(m, "  W           ");
+                        break;
+                case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
+                        seq_puts(m, "  RW          ");
+                        break;
+                default:
+                        seq_puts(m, "  NA          ");
+                }
+
+                if (lookup_symbol_name(entry->attr.bp_addr, fn_name) >= 0)
+                        seq_printf(m, "  %-36s", fn_name);
+                else
+                        seq_printf(m, "  %-36s", "<NA>");
+                seq_printf(m, " %15llu\n",
+                           (unsigned long long)atomic64_read(&entry->counter));
+        }
+        rcu_read_unlock();
+
+        return 0;
+}
+
+static int ksym_profile_open(struct inode *node, struct file *file)
+{
+        return single_open(file, ksym_profile_show, NULL);
+}
+
+static const struct file_operations ksym_profile_fops = {
+        .open           = ksym_profile_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
+#endif /* CONFIG_PROFILE_KSYM_TRACER */
+
+__init static int init_ksym_trace(void)
+{
+        struct dentry *d_tracer;
+
+        d_tracer = tracing_init_dentry();
+
+        trace_create_file("ksym_trace_filter", 0644, d_tracer,
+                          NULL, &ksym_tracing_fops);
+
+#ifdef CONFIG_PROFILE_KSYM_TRACER
+        trace_create_file("ksym_profile", 0444, d_tracer,
+                          NULL, &ksym_profile_fops);
+#endif
+
+        return register_tracer(&ksym_tracer);
+}
+device_initcall(init_ksym_trace);
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 0acd834659ed..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>
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index b6c12c6a1bcd..8e46b3323cdc 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -23,13 +23,21 @@ 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;
+
+        ret = seq_write(m, s->buffer, len);
 
-        seq_write(m, s->buffer, len);
+        /*
+         * Only reset this buffer if we successfully wrote to the
+         * seq_file buffer.
+         */
+        if (!ret)
+                trace_seq_init(s);
 
-        trace_seq_init(s);
+        return ret;
 }
 
 enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
@@ -85,7 +93,7 @@ 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);
@@ -93,8 +101,10 @@ 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;
 
@@ -119,14 +129,16 @@ 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;
 
@@ -139,14 +151,16 @@ 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;
 
@@ -167,8 +181,13 @@ 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;
@@ -178,9 +197,14 @@ 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;
@@ -188,9 +212,14 @@ int trace_seq_putc(struct trace_seq *s, unsigned char c)
 
 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;
 
@@ -203,6 +232,9 @@ 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
@@ -220,8 +252,13 @@ void *trace_seq_reserve(struct trace_seq *s, size_t len)
 {
         void *ret;
 
-        if (len > ((PAGE_SIZE - 1) - s->len))
+        if (s->full)
+                return 0;
+
+        if (len > ((PAGE_SIZE - 1) - s->len)) {
+                s->full = 1;
                 return NULL;
+        }
 
         ret = s->buffer + s->len;
         s->len += len;
@@ -233,8 +270,14 @@ 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");
@@ -247,6 +290,7 @@ int trace_seq_path(struct trace_seq *s, struct path *path)
                 return 1;
         }
 
+        s->full = 1;
         return 0;
 }
 
@@ -373,6 +417,9 @@ 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;
 
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 26185d727676..0271742abb8d 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -28,8 +28,8 @@ 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);
 
@@ -143,7 +143,7 @@ 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))
@@ -169,7 +169,7 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
 
 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);
@@ -193,9 +193,9 @@ static void wakeup_reset(struct trace_array *tr)
         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);
 }
 
@@ -225,7 +225,7 @@ 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)
@@ -255,7 +255,7 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success)
         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);
 }
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index d2cdbabb4ead..81003b4d617f 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)
 {
@@ -17,6 +18,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
         case TRACE_GRAPH_ENT:
         case TRACE_GRAPH_RET:
         case TRACE_HW_BRANCHES:
+        case TRACE_KSYM:
                 return 1;
         }
         return 0;
@@ -66,7 +68,7 @@ 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 +86,7 @@ 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)
@@ -808,3 +810,57 @@ trace_selftest_startup_hw_branches(struct tracer *trace,
         return ret;
 }
 #endif /* CONFIG_HW_BRANCH_TRACER */
+
+#ifdef CONFIG_KSYM_TRACER
+static int ksym_selftest_dummy;
+
+int
+trace_selftest_startup_ksym(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;
+        }
+
+        ksym_selftest_dummy = 0;
+        /* Register the read-write tracing request */
+
+        ret = process_new_ksym_entry("ksym_selftest_dummy",
+                                     HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+                                        (unsigned long)(&ksym_selftest_dummy));
+
+        if (ret < 0) {
+                printk(KERN_CONT "ksym_trace read-write startup test failed\n");
+                goto ret_path;
+        }
+        /* Perform a read and a write operation over the dummy variable to
+         * trigger the tracer
+         */
+        if (ksym_selftest_dummy == 0)
+                ksym_selftest_dummy++;
+
+        /* stop the tracing. */
+        tracing_stop();
+        /* check the trace buffer */
+        ret = trace_test_buffer(tr, &count);
+        trace->reset(tr);
+        tracing_start();
+
+        /* read & write operations - one each is performed on the dummy variable
+         * triggering two entries in the trace buffer
+         */
+        if (!ret && count != 2) {
+                printk(KERN_CONT "Ksym tracer startup test failed");
+                ret = -1;
+        }
+
+ret_path:
+        return ret;
+}
+#endif /* CONFIG_KSYM_TRACER */
+
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 8504ac71e4e8..f4bc9b27de5f 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)
@@ -103,7 +103,7 @@ static inline void check_stack(void)
         }
 
  out:
-        __raw_spin_unlock(&max_stack_lock);
+        arch_spin_unlock(&max_stack_lock);
         local_irq_restore(flags);
 }
 
@@ -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;
@@ -206,8 +218,14 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
+        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;
@@ -217,7 +235,13 @@ static void *t_start(struct seq_file *m, loff_t *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();
 }
 
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index a4bb239eb987..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"
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 527e17eae575..4d6d711717f2 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,5 +1,6 @@
 #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>
@@ -14,6 +15,43 @@ static int sys_refcount_exit;
 static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
 static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
 
+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)
 {
@@ -30,7 +68,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags)
         if (!entry)
                 goto end;
 
-        if (entry->enter_id != ent->type) {
+        if (entry->enter_event->id != ent->type) {
                 WARN_ON_ONCE(1);
                 goto end;
         }
@@ -85,7 +123,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
                 return TRACE_TYPE_HANDLED;
         }
 
-        if (entry->exit_id != ent->type) {
+        if (entry->exit_event->id != ent->type) {
                 WARN_ON_ONCE(1);
                 return TRACE_TYPE_UNHANDLED;
         }
@@ -103,92 +141,79 @@ 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)
+                #type, #name, offsetof(typeof(trace), name),            \
+                sizeof(trace.name), is_signed_type(type)
 
-int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
+static
+int  __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
 {
         int i;
-        int nr;
-        int ret;
-        struct syscall_metadata *entry;
-        struct syscall_trace_enter trace;
-        int offset = offsetof(struct syscall_trace_enter, args);
+        int pos = 0;
 
-        nr = syscall_name_to_nr(call->data);
-        entry = syscall_nr_to_meta(nr);
-
-        if (!entry)
-                return 0;
-
-        ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
-                               SYSCALL_FIELD(int, nr));
-        if (!ret)
-                return 0;
+        /* 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++) {
-                ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
-                                        entry->args[i]);
-                if (!ret)
-                        return 0;
-                ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;\n", offset,
-                                       sizeof(unsigned long));
-                if (!ret)
-                        return 0;
-                offset += sizeof(unsigned long);
+                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, "\"");
 
-        trace_seq_puts(s, "\nprint fmt: \"");
         for (i = 0; i < entry->nb_args; i++) {
-                ret = trace_seq_printf(s, "%s: 0x%%0%zulx%s", entry->args[i],
-                                        sizeof(unsigned long),
-                                        i == entry->nb_args - 1 ? "" : ", ");
-                if (!ret)
-                        return 0;
+                pos += snprintf(buf + pos, LEN_OR_ZERO,
+                                ", ((unsigned long)(REC->%s))", entry->args[i]);
         }
-        trace_seq_putc(s, '"');
 
-        for (i = 0; i < entry->nb_args; i++) {
-                ret = trace_seq_printf(s, ", ((unsigned long)(REC->%s))",
-                                       entry->args[i]);
-                if (!ret)
-                        return 0;
-        }
+#undef LEN_OR_ZERO
 
-        return trace_seq_putc(s, '\n');
+        /* return the length of print_fmt */
+        return pos;
 }
 
-int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
+static int set_syscall_print_fmt(struct ftrace_event_call *call)
 {
-        int ret;
-        struct syscall_trace_exit trace;
+        char *print_fmt;
+        int len;
+        struct syscall_metadata *entry = call->data;
 
-        ret = trace_seq_printf(s,
-                               "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
-                               "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
-                               SYSCALL_FIELD(int, nr),
-                               SYSCALL_FIELD(long, ret));
-        if (!ret)
+        if (entry->enter_event != call) {
+                call->print_fmt = "\"0x%lx\", REC->ret";
                 return 0;
+        }
+
+        /* 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;
+}
+
+static void free_syscall_print_fmt(struct ftrace_event_call *call)
+{
+        struct syscall_metadata *entry = call->data;
 
-        return trace_seq_printf(s, "\nprint fmt: \"0x%%lx\", REC->ret\n");
+        if (entry->enter_event == call)
+                kfree(call->print_fmt);
 }
 
 int syscall_enter_define_fields(struct ftrace_event_call *call)
 {
         struct syscall_trace_enter trace;
-        struct syscall_metadata *meta;
+        struct syscall_metadata *meta = call->data;
         int ret;
-        int nr;
         int i;
         int offset = offsetof(typeof(trace), args);
 
-        nr = syscall_name_to_nr(call->data);
-        meta = syscall_nr_to_meta(nr);
-
-        if (!meta)
-                return 0;
-
-        ret = trace_define_common_fields(call);
+        ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
         if (ret)
                 return ret;
 
@@ -208,11 +233,11 @@ int syscall_exit_define_fields(struct ftrace_event_call *call)
         struct syscall_trace_exit trace;
         int ret;
 
-        ret = trace_define_common_fields(call);
+        ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
         if (ret)
                 return ret;
 
-        ret = trace_define_field(call, SYSCALL_FIELD(long, ret), 0,
+        ret = trace_define_field(call, SYSCALL_FIELD(long, ret),
                                  FILTER_OTHER);
 
         return ret;
@@ -239,8 +264,8 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
 
         size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
-        event = trace_current_buffer_lock_reserve(&buffer, sys_data->enter_id,
-                                                  size, 0, 0);
+        event = trace_current_buffer_lock_reserve(&buffer,
+                        sys_data->enter_event->id, size, 0, 0);
         if (!event)
                 return;
 
@@ -271,8 +296,8 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
         if (!sys_data)
                 return;
 
-        event = trace_current_buffer_lock_reserve(&buffer, sys_data->exit_id,
-                                sizeof(*entry), 0, 0);
+        event = trace_current_buffer_lock_reserve(&buffer,
+                        sys_data->exit_event->id, sizeof(*entry), 0, 0);
         if (!event)
                 return;
 
@@ -285,23 +310,18 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
                 trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-int reg_event_syscall_enter(void *ptr)
+int reg_event_syscall_enter(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        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);
-        if (ret) {
-                pr_info("event trace: Could not activate"
-                                "syscall entry trace point");
-        } else {
+        if (!ret) {
                 set_bit(num, enabled_enter_syscalls);
                 sys_refcount_enter++;
         }
@@ -309,13 +329,11 @@ int reg_event_syscall_enter(void *ptr)
         return ret;
 }
 
-void unreg_event_syscall_enter(void *ptr)
+void unreg_event_syscall_enter(struct ftrace_event_call *call)
 {
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
         if (num < 0 || num >= NR_syscalls)
                 return;
         mutex_lock(&syscall_trace_lock);
@@ -326,23 +344,18 @@ void unreg_event_syscall_enter(void *ptr)
         mutex_unlock(&syscall_trace_lock);
 }
 
-int reg_event_syscall_exit(void *ptr)
+int reg_event_syscall_exit(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        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);
-        if (ret) {
-                pr_info("event trace: Could not activate"
-                                "syscall exit trace point");
-        } else {
+        if (!ret) {
                 set_bit(num, enabled_exit_syscalls);
                 sys_refcount_exit++;
         }
@@ -350,13 +363,11 @@ int reg_event_syscall_exit(void *ptr)
         return ret;
 }
 
-void unreg_event_syscall_exit(void *ptr)
+void unreg_event_syscall_exit(struct ftrace_event_call *call)
 {
         int num;
-        char *name;
 
-        name = (char *)ptr;
-        num = syscall_name_to_nr(name);
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
         if (num < 0 || num >= NR_syscalls)
                 return;
         mutex_lock(&syscall_trace_lock);
@@ -367,33 +378,73 @@ void unreg_event_syscall_exit(void *ptr)
         mutex_unlock(&syscall_trace_lock);
 }
 
-struct trace_event event_syscall_enter = {
-        .trace                  = print_syscall_enter,
-};
+int init_syscall_trace(struct ftrace_event_call *call)
+{
+        int id;
+
+        if (set_syscall_print_fmt(call) < 0)
+                return -ENOMEM;
 
-struct trace_event event_syscall_exit = {
-        .trace                  = print_syscall_exit,
-};
+        id = trace_event_raw_init(call);
 
-#ifdef CONFIG_EVENT_PROFILE
+        if (id < 0) {
+                free_syscall_print_fmt(call);
+                return id;
+        }
 
-static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
-static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls);
-static int sys_prof_refcount_enter;
-static int sys_prof_refcount_exit;
+        return id;
+}
+
+unsigned long __init arch_syscall_addr(int nr)
+{
+        return (unsigned long)sys_call_table[nr];
+}
 
-static void prof_syscall_enter(struct pt_regs *regs, long id)
+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 perf_syscall_enter(struct pt_regs *regs, long id)
 {
         struct syscall_metadata *sys_data;
         struct syscall_trace_enter *rec;
         unsigned long flags;
-        char *raw_data;
         int syscall_nr;
+        int rctx;
         int size;
-        int cpu;
 
         syscall_nr = syscall_get_nr(current, regs);
-        if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
+        if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
                 return;
 
         sys_data = syscall_nr_to_meta(syscall_nr);
@@ -405,91 +456,67 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
         size = ALIGN(size + sizeof(u32), sizeof(u64));
         size -= sizeof(u32);
 
-        if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
-                      "profile buffer not large enough"))
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+                      "perf buffer not large enough"))
                 return;
 
-        /* Protect the per cpu buffer, begin the rcu read side */
-        local_irq_save(flags);
-
-        cpu = smp_processor_id();
-
-        if (in_nmi())
-                raw_data = rcu_dereference(trace_profile_buf_nmi);
-        else
-                raw_data = rcu_dereference(trace_profile_buf);
-
-        if (!raw_data)
-                goto end;
-
-        raw_data = per_cpu_ptr(raw_data, cpu);
-
-        /* zero the dead bytes from align to not leak stack to user */
-        *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+        rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
+                                sys_data->enter_event->id, &rctx, &flags);
+        if (!rec)
+                return;
 
-        rec = (struct syscall_trace_enter *) raw_data;
-        tracing_generic_entry_update(&rec->ent, 0, 0);
-        rec->ent.type = sys_data->enter_id;
         rec->nr = syscall_nr;
         syscall_get_arguments(current, regs, 0, sys_data->nb_args,
                                (unsigned long *)&rec->args);
-        perf_tp_event(sys_data->enter_id, 0, 1, rec, size);
-
-end:
-        local_irq_restore(flags);
+        perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
 }
 
-int reg_prof_syscall_enter(char *name)
+int perf_sysenter_enable(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return -ENOSYS;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        if (!sys_prof_refcount_enter)
-                ret = register_trace_sys_enter(prof_syscall_enter);
+        if (!sys_perf_refcount_enter)
+                ret = register_trace_sys_enter(perf_syscall_enter);
         if (ret) {
                 pr_info("event trace: Could not activate"
                                 "syscall entry trace point");
         } else {
-                set_bit(num, enabled_prof_enter_syscalls);
-                sys_prof_refcount_enter++;
+                set_bit(num, enabled_perf_enter_syscalls);
+                sys_perf_refcount_enter++;
         }
         mutex_unlock(&syscall_trace_lock);
         return ret;
 }
 
-void unreg_prof_syscall_enter(char *name)
+void perf_sysenter_disable(struct ftrace_event_call *call)
 {
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        sys_prof_refcount_enter--;
-        clear_bit(num, enabled_prof_enter_syscalls);
-        if (!sys_prof_refcount_enter)
-                unregister_trace_sys_enter(prof_syscall_enter);
+        sys_perf_refcount_enter--;
+        clear_bit(num, enabled_perf_enter_syscalls);
+        if (!sys_perf_refcount_enter)
+                unregister_trace_sys_enter(perf_syscall_enter);
         mutex_unlock(&syscall_trace_lock);
 }
 
-static void prof_syscall_exit(struct pt_regs *regs, long ret)
+static void perf_syscall_exit(struct pt_regs *regs, long ret)
 {
         struct syscall_metadata *sys_data;
         struct syscall_trace_exit *rec;
         unsigned long flags;
         int syscall_nr;
-        char *raw_data;
+        int rctx;
         int size;
-        int cpu;
 
         syscall_nr = syscall_get_nr(current, regs);
-        if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
+        if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
                 return;
 
         sys_data = syscall_nr_to_meta(syscall_nr);
@@ -504,79 +531,55 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
          * Impossible, but be paranoid with the future
          * How to put this check outside runtime?
          */
-        if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
-                "exit event has grown above profile buffer size"))
+        if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+                "exit event has grown above perf buffer size"))
                 return;
 
-        /* Protect the per cpu buffer, begin the rcu read side */
-        local_irq_save(flags);
-        cpu = smp_processor_id();
-
-        if (in_nmi())
-                raw_data = rcu_dereference(trace_profile_buf_nmi);
-        else
-                raw_data = rcu_dereference(trace_profile_buf);
-
-        if (!raw_data)
-                goto end;
-
-        raw_data = per_cpu_ptr(raw_data, cpu);
-
-        /* zero the dead bytes from align to not leak stack to user */
-        *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
-
-        rec = (struct syscall_trace_exit *)raw_data;
+        rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
+                                sys_data->exit_event->id, &rctx, &flags);
+        if (!rec)
+                return;
 
-        tracing_generic_entry_update(&rec->ent, 0, 0);
-        rec->ent.type = sys_data->exit_id;
         rec->nr = syscall_nr;
         rec->ret = syscall_get_return_value(current, regs);
 
-        perf_tp_event(sys_data->exit_id, 0, 1, rec, size);
-
-end:
-        local_irq_restore(flags);
+        perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
 }
 
-int reg_prof_syscall_exit(char *name)
+int perf_sysexit_enable(struct ftrace_event_call *call)
 {
         int ret = 0;
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return -ENOSYS;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        if (!sys_prof_refcount_exit)
-                ret = register_trace_sys_exit(prof_syscall_exit);
+        if (!sys_perf_refcount_exit)
+                ret = register_trace_sys_exit(perf_syscall_exit);
         if (ret) {
                 pr_info("event trace: Could not activate"
-                                "syscall entry trace point");
+                                "syscall exit trace point");
         } else {
-                set_bit(num, enabled_prof_exit_syscalls);
-                sys_prof_refcount_exit++;
+                set_bit(num, enabled_perf_exit_syscalls);
+                sys_perf_refcount_exit++;
         }
         mutex_unlock(&syscall_trace_lock);
         return ret;
 }
 
-void unreg_prof_syscall_exit(char *name)
+void perf_sysexit_disable(struct ftrace_event_call *call)
 {
         int num;
 
-        num = syscall_name_to_nr(name);
-        if (num < 0 || num >= NR_syscalls)
-                return;
+        num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
         mutex_lock(&syscall_trace_lock);
-        sys_prof_refcount_exit--;
-        clear_bit(num, enabled_prof_exit_syscalls);
-        if (!sys_prof_refcount_exit)
-                unregister_trace_sys_exit(prof_syscall_exit);
+        sys_perf_refcount_exit--;
+        clear_bit(num, enabled_perf_exit_syscalls);
+        if (!sys_perf_refcount_exit)
+                unregister_trace_sys_exit(perf_syscall_exit);
         mutex_unlock(&syscall_trace_lock);
 }
 
-#endif
-
+#endif /* CONFIG_PERF_EVENTS */
 
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index f6693969287d..a7974a552ca9 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -93,6 +93,7 @@ static const struct stacktrace_ops backtrace_ops = {
         .warning_symbol         = backtrace_warning_symbol,
         .stack                  = backtrace_stack,
         .address                = backtrace_address,
+        .walk_stack             = print_context_stack,
 };
 
 static int
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 40cafb07dffd..cc2d2faa7d9e 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -9,6 +9,7 @@
 #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"