Merge branch 'linus' into perf/urgent

Merge reason: Include most of the merge window trees, to do fixes on top.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

16 files changed, 860 insertions, 488 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 908038f57440..c3e4575e7829 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -32,7 +32,6 @@
 
 #include <trace/events/sched.h>
 
-#include <asm/ftrace.h>
 #include <asm/setup.h>
 
 #include "trace_output.h"
@@ -82,14 +81,14 @@ static int ftrace_disabled __read_mostly;
 
 static DEFINE_MUTEX(ftrace_lock);
 
-static struct ftrace_ops ftrace_list_end __read_mostly =
-{
+static struct ftrace_ops ftrace_list_end __read_mostly = {
         .func           = ftrace_stub,
 };
 
 static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
+static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub;
 ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
@@ -148,9 +147,11 @@ void clear_ftrace_function(void)
 {
         ftrace_trace_function = ftrace_stub;
         __ftrace_trace_function = ftrace_stub;
+        __ftrace_trace_function_delay = ftrace_stub;
         ftrace_pid_function = ftrace_stub;
 }
 
+#undef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 #ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 /*
  * For those archs that do not test ftrace_trace_stop in their
@@ -210,7 +211,12 @@ static void update_ftrace_function(void)
 #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
         ftrace_trace_function = func;
 #else
+#ifdef CONFIG_DYNAMIC_FTRACE
+        /* do not update till all functions have been modified */
+        __ftrace_trace_function_delay = func;
+#else
         __ftrace_trace_function = func;
+#endif
         ftrace_trace_function = ftrace_test_stop_func;
 #endif
 }
@@ -785,8 +791,7 @@ static void unregister_ftrace_profiler(void)
         unregister_ftrace_graph();
 }
 #else
-static struct ftrace_ops ftrace_profile_ops __read_mostly =
-{
+static struct ftrace_ops ftrace_profile_ops __read_mostly = {
         .func           = function_profile_call,
 };
 
@@ -806,19 +811,10 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
                      size_t cnt, loff_t *ppos)
 {
         unsigned long val;
-        char buf[64];           /* big enough to hold a number */
         int ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         val = !!val;
@@ -1182,8 +1178,14 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
         return NULL;
 }
 
+static void
+ftrace_hash_rec_disable(struct ftrace_ops *ops, int filter_hash);
+static void
+ftrace_hash_rec_enable(struct ftrace_ops *ops, int filter_hash);
+
 static int
-ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
+ftrace_hash_move(struct ftrace_ops *ops, int enable,
+                 struct ftrace_hash **dst, struct ftrace_hash *src)
 {
         struct ftrace_func_entry *entry;
         struct hlist_node *tp, *tn;
@@ -1193,9 +1195,16 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
         unsigned long key;
         int size = src->count;
         int bits = 0;
+        int ret;
         int i;
 
         /*
+         * Remove the current set, update the hash and add
+         * them back.
+         */
+        ftrace_hash_rec_disable(ops, enable);
+
+        /*
          * If the new source is empty, just free dst and assign it
          * the empty_hash.
          */
@@ -1215,9 +1224,10 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
         if (bits > FTRACE_HASH_MAX_BITS)
                 bits = FTRACE_HASH_MAX_BITS;
 
+        ret = -ENOMEM;
         new_hash = alloc_ftrace_hash(bits);
         if (!new_hash)
-                return -ENOMEM;
+                goto out;
 
         size = 1 << src->size_bits;
         for (i = 0; i < size; i++) {
@@ -1236,7 +1246,16 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
         rcu_assign_pointer(*dst, new_hash);
         free_ftrace_hash_rcu(old_hash);
 
-        return 0;
+        ret = 0;
+ out:
+        /*
+         * Enable regardless of ret:
+         *  On success, we enable the new hash.
+         *  On failure, we re-enable the original hash.
+         */
+        ftrace_hash_rec_enable(ops, enable);
+
+        return ret;
 }
 
 /*
@@ -1596,6 +1615,12 @@ static int __ftrace_modify_code(void *data)
 {
         int *command = data;
 
+        /*
+         * Do not call function tracer while we update the code.
+         * We are in stop machine, no worrying about races.
+         */
+        function_trace_stop++;
+
         if (*command & FTRACE_ENABLE_CALLS)
                 ftrace_replace_code(1);
         else if (*command & FTRACE_DISABLE_CALLS)
@@ -1609,6 +1634,18 @@ static int __ftrace_modify_code(void *data)
         else if (*command & FTRACE_STOP_FUNC_RET)
                 ftrace_disable_ftrace_graph_caller();
 
+#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+        /*
+         * For archs that call ftrace_test_stop_func(), we must
+         * wait till after we update all the function callers
+         * before we update the callback. This keeps different
+         * ops that record different functions from corrupting
+         * each other.
+         */
+        __ftrace_trace_function = __ftrace_trace_function_delay;
+#endif
+        function_trace_stop--;
+
         return 0;
 }
 
@@ -1744,10 +1781,36 @@ static cycle_t		ftrace_update_time;
 static unsigned long    ftrace_update_cnt;
 unsigned long           ftrace_update_tot_cnt;
 
+static int ops_traces_mod(struct ftrace_ops *ops)
+{
+        struct ftrace_hash *hash;
+
+        hash = ops->filter_hash;
+        return !!(!hash || !hash->count);
+}
+
 static int ftrace_update_code(struct module *mod)
 {
         struct dyn_ftrace *p;
         cycle_t start, stop;
+        unsigned long ref = 0;
+
+        /*
+         * When adding a module, we need to check if tracers are
+         * currently enabled and if they are set to trace all functions.
+         * If they are, we need to enable the module functions as well
+         * as update the reference counts for those function records.
+         */
+        if (mod) {
+                struct ftrace_ops *ops;
+
+                for (ops = ftrace_ops_list;
+                     ops != &ftrace_list_end; ops = ops->next) {
+                        if (ops->flags & FTRACE_OPS_FL_ENABLED &&
+                            ops_traces_mod(ops))
+                                ref++;
+                }
+        }
 
         start = ftrace_now(raw_smp_processor_id());
         ftrace_update_cnt = 0;
@@ -1760,7 +1823,7 @@ static int ftrace_update_code(struct module *mod)
 
                 p = ftrace_new_addrs;
                 ftrace_new_addrs = p->newlist;
-                p->flags = 0L;
+                p->flags = ref;
 
                 /*
                  * Do the initial record conversion from mcount jump
@@ -1783,7 +1846,7 @@ static int ftrace_update_code(struct module *mod)
                  * conversion puts the module to the correct state, thus
                  * passing the ftrace_make_call check.
                  */
-                if (ftrace_start_up) {
+                if (ftrace_start_up && ref) {
                         int failed = __ftrace_replace_code(p, 1);
                         if (failed) {
                                 ftrace_bug(failed, p->ip);
@@ -2407,10 +2470,9 @@ ftrace_match_module_records(struct ftrace_hash *hash, char *buff, char *mod)
  */
 
 static int
-ftrace_mod_callback(char *func, char *cmd, char *param, int enable)
+ftrace_mod_callback(struct ftrace_hash *hash,
+                    char *func, char *cmd, char *param, int enable)
 {
-        struct ftrace_ops *ops = &global_ops;
-        struct ftrace_hash *hash;
         char *mod;
         int ret = -EINVAL;
 
@@ -2430,11 +2492,6 @@ ftrace_mod_callback(char *func, char *cmd, char *param, int enable)
         if (!strlen(mod))
                 return ret;
 
-        if (enable)
-                hash = ops->filter_hash;
-        else
-                hash = ops->notrace_hash;
-
         ret = ftrace_match_module_records(hash, func, mod);
         if (!ret)
                 ret = -EINVAL;
@@ -2760,7 +2817,7 @@ static int ftrace_process_regex(struct ftrace_hash *hash,
         mutex_lock(&ftrace_cmd_mutex);
         list_for_each_entry(p, &ftrace_commands, list) {
                 if (strcmp(p->name, command) == 0) {
-                        ret = p->func(func, command, next, enable);
+                        ret = p->func(hash, func, command, next, enable);
                         goto out_unlock;
                 }
         }
@@ -2857,7 +2914,11 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
                 ftrace_match_records(hash, buf, len);
 
         mutex_lock(&ftrace_lock);
-        ret = ftrace_hash_move(orig_hash, hash);
+        ret = ftrace_hash_move(ops, enable, orig_hash, hash);
+        if (!ret && ops->flags & FTRACE_OPS_FL_ENABLED
+            && ftrace_enabled)
+                ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+
         mutex_unlock(&ftrace_lock);
 
         mutex_unlock(&ftrace_regex_lock);
@@ -3040,18 +3101,12 @@ ftrace_regex_release(struct inode *inode, struct file *file)
                         orig_hash = &iter->ops->notrace_hash;
 
                 mutex_lock(&ftrace_lock);
-                /*
-                 * Remove the current set, update the hash and add
-                 * them back.
-                 */
-                ftrace_hash_rec_disable(iter->ops, filter_hash);
-                ret = ftrace_hash_move(orig_hash, iter->hash);
-                if (!ret) {
-                        ftrace_hash_rec_enable(iter->ops, filter_hash);
-                        if (iter->ops->flags & FTRACE_OPS_FL_ENABLED
-                            && ftrace_enabled)
-                                ftrace_run_update_code(FTRACE_ENABLE_CALLS);
-                }
+                ret = ftrace_hash_move(iter->ops, filter_hash,
+                                       orig_hash, iter->hash);
+                if (!ret && (iter->ops->flags & FTRACE_OPS_FL_ENABLED)
+                    && ftrace_enabled)
+                        ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+
                 mutex_unlock(&ftrace_lock);
         }
         free_ftrace_hash(iter->hash);
@@ -3330,7 +3385,7 @@ static int ftrace_process_locs(struct module *mod,
 {
         unsigned long *p;
         unsigned long addr;
-        unsigned long flags;
+        unsigned long flags = 0; /* Shut up gcc */
 
         mutex_lock(&ftrace_lock);
         p = start;
@@ -3348,12 +3403,18 @@ static int ftrace_process_locs(struct module *mod,
         }
 
         /*
-         * Disable interrupts to prevent interrupts from executing
-         * code that is being modified.
+         * We only need to disable interrupts on start up
+         * because we are modifying code that an interrupt
+         * may execute, and the modification is not atomic.
+         * But for modules, nothing runs the code we modify
+         * until we are finished with it, and there's no
+         * reason to cause large interrupt latencies while we do it.
          */
-        local_irq_save(flags);
+        if (!mod)
+                local_irq_save(flags);
         ftrace_update_code(mod);
-        local_irq_restore(flags);
+        if (!mod)
+                local_irq_restore(flags);
         mutex_unlock(&ftrace_lock);
 
         return 0;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b0c7aa407943..731201bf4acc 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -997,15 +997,21 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
                              unsigned nr_pages)
 {
         struct buffer_page *bpage, *tmp;
-        unsigned long addr;
         LIST_HEAD(pages);
         unsigned i;
 
         WARN_ON(!nr_pages);
 
         for (i = 0; i < nr_pages; i++) {
+                struct page *page;
+                /*
+                 * __GFP_NORETRY flag makes sure that the allocation fails
+                 * gracefully without invoking oom-killer and the system is
+                 * not destabilized.
+                 */
                 bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
-                                    GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
+                                    GFP_KERNEL | __GFP_NORETRY,
+                                    cpu_to_node(cpu_buffer->cpu));
                 if (!bpage)
                         goto free_pages;
 
@@ -1013,10 +1019,11 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 
                 list_add(&bpage->list, &pages);
 
-                addr = __get_free_page(GFP_KERNEL);
-                if (!addr)
+                page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu),
+                                        GFP_KERNEL | __GFP_NORETRY, 0);
+                if (!page)
                         goto free_pages;
-                bpage->page = (void *)addr;
+                bpage->page = page_address(page);
                 rb_init_page(bpage->page);
         }
 
@@ -1045,7 +1052,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
         struct buffer_page *bpage;
-        unsigned long addr;
+        struct page *page;
         int ret;
 
         cpu_buffer = kzalloc_node(ALIGN(sizeof(*cpu_buffer), cache_line_size()),
@@ -1067,10 +1074,10 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
         rb_check_bpage(cpu_buffer, bpage);
 
         cpu_buffer->reader_page = bpage;
-        addr = __get_free_page(GFP_KERNEL);
-        if (!addr)
+        page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0);
+        if (!page)
                 goto fail_free_reader;
-        bpage->page = (void *)addr;
+        bpage->page = page_address(page);
         rb_init_page(bpage->page);
 
         INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
@@ -1314,7 +1321,6 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
         unsigned nr_pages, rm_pages, new_pages;
         struct buffer_page *bpage, *tmp;
         unsigned long buffer_size;
-        unsigned long addr;
         LIST_HEAD(pages);
         int i, cpu;
 
@@ -1375,16 +1381,24 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 
         for_each_buffer_cpu(buffer, cpu) {
                 for (i = 0; i < new_pages; i++) {
+                        struct page *page;
+                        /*
+                         * __GFP_NORETRY flag makes sure that the allocation
+                         * fails gracefully without invoking oom-killer and
+                         * the system is not destabilized.
+                         */
                         bpage = kzalloc_node(ALIGN(sizeof(*bpage),
                                                   cache_line_size()),
-                                            GFP_KERNEL, cpu_to_node(cpu));
+                                            GFP_KERNEL | __GFP_NORETRY,
+                                            cpu_to_node(cpu));
                         if (!bpage)
                                 goto free_pages;
                         list_add(&bpage->list, &pages);
-                        addr = __get_free_page(GFP_KERNEL);
-                        if (!addr)
+                        page = alloc_pages_node(cpu_to_node(cpu),
+                                                GFP_KERNEL | __GFP_NORETRY, 0);
+                        if (!page)
                                 goto free_pages;
-                        bpage->page = (void *)addr;
+                        bpage->page = page_address(page);
                         rb_init_page(bpage->page);
                 }
         }
@@ -3730,16 +3744,17 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
  * Returns:
  *  The page allocated, or NULL on error.
  */
-void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
+void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
 {
         struct buffer_data_page *bpage;
-        unsigned long addr;
+        struct page *page;
 
-        addr = __get_free_page(GFP_KERNEL);
-        if (!addr)
+        page = alloc_pages_node(cpu_to_node(cpu),
+                                GFP_KERNEL | __GFP_NORETRY, 0);
+        if (!page)
                 return NULL;
 
-        bpage = (void *)addr;
+        bpage = page_address(page);
 
         rb_init_page(bpage);
 
@@ -3978,20 +3993,11 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
                 size_t cnt, loff_t *ppos)
 {
         unsigned long *p = filp->private_data;
-        char buf[64];
         unsigned long val;
         int ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         if (val)
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 302f8a614635..a5457d577b98 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -106,7 +106,7 @@ static enum event_status read_page(int cpu)
         int inc;
         int i;
 
-        bpage = ring_buffer_alloc_read_page(buffer);
+        bpage = ring_buffer_alloc_read_page(buffer, cpu);
         if (!bpage)
                 return EVENT_DROPPED;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ee9c921d7f21..e5df02c69b1d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -343,26 +343,27 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 static int trace_stop_count;
 static DEFINE_SPINLOCK(tracing_start_lock);
 
+static void wakeup_work_handler(struct work_struct *work)
+{
+        wake_up(&trace_wait);
+}
+
+static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler);
+
 /**
  * trace_wake_up - wake up tasks waiting for trace input
  *
- * Simply wakes up any task that is blocked on the trace_wait
- * queue. These is used with trace_poll for tasks polling the trace.
+ * Schedules a delayed work to wake up any task that is blocked on the
+ * trace_wait queue. These is used with trace_poll for tasks polling the
+ * trace.
  */
 void trace_wake_up(void)
 {
-        int cpu;
+        const unsigned long delay = msecs_to_jiffies(2);
 
         if (trace_flags & TRACE_ITER_BLOCK)
                 return;
-        /*
-         * The runqueue_is_locked() can fail, but this is the best we
-         * have for now:
-         */
-        cpu = get_cpu();
-        if (!runqueue_is_locked(cpu))
-                wake_up(&trace_wait);
-        put_cpu();
+        schedule_delayed_work(&wakeup_work, delay);
 }
 
 static int __init set_buf_size(char *str)
@@ -424,6 +425,7 @@ static const char *trace_options[] = {
         "graph-time",
         "record-cmd",
         "overwrite",
+        "disable_on_free",
         NULL
 };
 
@@ -1191,6 +1193,18 @@ void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
 
+void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer,
+                                            struct ring_buffer_event *event,
+                                            unsigned long flags, int pc,
+                                            struct pt_regs *regs)
+{
+        ring_buffer_unlock_commit(buffer, event);
+
+        ftrace_trace_stack_regs(buffer, flags, 0, pc, regs);
+        ftrace_trace_userstack(buffer, flags, pc);
+}
+EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit_regs);
+
 void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
                                          struct ring_buffer_event *event)
 {
@@ -1234,30 +1248,103 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
 }
 
 #ifdef CONFIG_STACKTRACE
+
+#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long))
+struct ftrace_stack {
+        unsigned long           calls[FTRACE_STACK_MAX_ENTRIES];
+};
+
+static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack);
+static DEFINE_PER_CPU(int, ftrace_stack_reserve);
+
 static void __ftrace_trace_stack(struct ring_buffer *buffer,
                                  unsigned long flags,
-                                 int skip, int pc)
+                                 int skip, int pc, struct pt_regs *regs)
 {
         struct ftrace_event_call *call = &event_kernel_stack;
         struct ring_buffer_event *event;
         struct stack_entry *entry;
         struct stack_trace trace;
+        int use_stack;
+        int size = FTRACE_STACK_ENTRIES;
+
+        trace.nr_entries        = 0;
+        trace.skip              = skip;
+
+        /*
+         * Since events can happen in NMIs there's no safe way to
+         * use the per cpu ftrace_stacks. We reserve it and if an interrupt
+         * or NMI comes in, it will just have to use the default
+         * FTRACE_STACK_SIZE.
+         */
+        preempt_disable_notrace();
+
+        use_stack = ++__get_cpu_var(ftrace_stack_reserve);
+        /*
+         * We don't need any atomic variables, just a barrier.
+         * If an interrupt comes in, we don't care, because it would
+         * have exited and put the counter back to what we want.
+         * We just need a barrier to keep gcc from moving things
+         * around.
+         */
+        barrier();
+        if (use_stack == 1) {
+                trace.entries           = &__get_cpu_var(ftrace_stack).calls[0];
+                trace.max_entries       = FTRACE_STACK_MAX_ENTRIES;
+
+                if (regs)
+                        save_stack_trace_regs(regs, &trace);
+                else
+                        save_stack_trace(&trace);
+
+                if (trace.nr_entries > size)
+                        size = trace.nr_entries;
+        } else
+                /* From now on, use_stack is a boolean */
+                use_stack = 0;
+
+        size *= sizeof(unsigned long);
 
         event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
-                                          sizeof(*entry), flags, pc);
+                                          sizeof(*entry) + size, flags, pc);
         if (!event)
-                return;
-        entry   = ring_buffer_event_data(event);
-        memset(&entry->caller, 0, sizeof(entry->caller));
+                goto out;
+        entry = ring_buffer_event_data(event);
 
-        trace.nr_entries        = 0;
-        trace.max_entries       = FTRACE_STACK_ENTRIES;
-        trace.skip              = skip;
-        trace.entries           = entry->caller;
+        memset(&entry->caller, 0, size);
+
+        if (use_stack)
+                memcpy(&entry->caller, trace.entries,
+                       trace.nr_entries * sizeof(unsigned long));
+        else {
+                trace.max_entries       = FTRACE_STACK_ENTRIES;
+                trace.entries           = entry->caller;
+                if (regs)
+                        save_stack_trace_regs(regs, &trace);
+                else
+                        save_stack_trace(&trace);
+        }
+
+        entry->size = trace.nr_entries;
 
-        save_stack_trace(&trace);
         if (!filter_check_discard(call, entry, buffer, event))
                 ring_buffer_unlock_commit(buffer, event);
+
+ out:
+        /* Again, don't let gcc optimize things here */
+        barrier();
+        __get_cpu_var(ftrace_stack_reserve)--;
+        preempt_enable_notrace();
+
+}
+
+void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
+                             int skip, int pc, struct pt_regs *regs)
+{
+        if (!(trace_flags & TRACE_ITER_STACKTRACE))
+                return;
+
+        __ftrace_trace_stack(buffer, flags, skip, pc, regs);
 }
 
 void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
@@ -1266,13 +1353,13 @@ void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
         if (!(trace_flags & TRACE_ITER_STACKTRACE))
                 return;
 
-        __ftrace_trace_stack(buffer, flags, skip, pc);
+        __ftrace_trace_stack(buffer, flags, skip, pc, NULL);
 }
 
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
                    int pc)
 {
-        __ftrace_trace_stack(tr->buffer, flags, skip, pc);
+        __ftrace_trace_stack(tr->buffer, flags, skip, pc, NULL);
 }
 
 /**
@@ -1288,7 +1375,7 @@ void trace_dump_stack(void)
         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());
+        __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count(), NULL);
 }
 
 static DEFINE_PER_CPU(int, user_stack_count);
@@ -1536,7 +1623,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
 
         ftrace_enable_cpu();
 
-        return event ? ring_buffer_event_data(event) : NULL;
+        if (event) {
+                iter->ent_size = ring_buffer_event_length(event);
+                return ring_buffer_event_data(event);
+        }
+        iter->ent_size = 0;
+        return NULL;
 }
 
 static struct trace_entry *
@@ -2051,6 +2143,9 @@ void trace_default_header(struct seq_file *m)
 {
         struct trace_iterator *iter = m->private;
 
+        if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
+                return;
+
         if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
                 /* print nothing if the buffers are empty */
                 if (trace_empty(iter))
@@ -2701,20 +2796,11 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
                    size_t cnt, loff_t *ppos)
 {
         struct trace_array *tr = filp->private_data;
-        char buf[64];
         unsigned long val;
         int ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         val = !!val;
@@ -2767,7 +2853,7 @@ int tracer_init(struct tracer *t, struct trace_array *tr)
         return t->init(tr);
 }
 
-static int tracing_resize_ring_buffer(unsigned long size)
+static int __tracing_resize_ring_buffer(unsigned long size)
 {
         int ret;
 
@@ -2819,6 +2905,41 @@ static int tracing_resize_ring_buffer(unsigned long size)
         return ret;
 }
 
+static ssize_t tracing_resize_ring_buffer(unsigned long size)
+{
+        int cpu, ret = size;
+
+        mutex_lock(&trace_types_lock);
+
+        tracing_stop();
+
+        /* disable all cpu buffers */
+        for_each_tracing_cpu(cpu) {
+                if (global_trace.data[cpu])
+                        atomic_inc(&global_trace.data[cpu]->disabled);
+                if (max_tr.data[cpu])
+                        atomic_inc(&max_tr.data[cpu]->disabled);
+        }
+
+        if (size != global_trace.entries)
+                ret = __tracing_resize_ring_buffer(size);
+
+        if (ret < 0)
+                ret = -ENOMEM;
+
+        for_each_tracing_cpu(cpu) {
+                if (global_trace.data[cpu])
+                        atomic_dec(&global_trace.data[cpu]->disabled);
+                if (max_tr.data[cpu])
+                        atomic_dec(&max_tr.data[cpu]->disabled);
+        }
+
+        tracing_start();
+        mutex_unlock(&trace_types_lock);
+
+        return ret;
+}
+
 
 /**
  * tracing_update_buffers - used by tracing facility to expand ring buffers
@@ -2836,7 +2957,7 @@ int tracing_update_buffers(void)
 
         mutex_lock(&trace_types_lock);
         if (!ring_buffer_expanded)
-                ret = tracing_resize_ring_buffer(trace_buf_size);
+                ret = __tracing_resize_ring_buffer(trace_buf_size);
         mutex_unlock(&trace_types_lock);
 
         return ret;
@@ -2860,7 +2981,7 @@ static int tracing_set_tracer(const char *buf)
         mutex_lock(&trace_types_lock);
 
         if (!ring_buffer_expanded) {
-                ret = tracing_resize_ring_buffer(trace_buf_size);
+                ret = __tracing_resize_ring_buffer(trace_buf_size);
                 if (ret < 0)
                         goto out;
                 ret = 0;
@@ -2966,20 +3087,11 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
                       size_t cnt, loff_t *ppos)
 {
         unsigned long *ptr = filp->private_data;
-        char buf[64];
         unsigned long val;
         int ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         *ptr = val * 1000;
@@ -3434,67 +3546,54 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
                       size_t cnt, loff_t *ppos)
 {
         unsigned long val;
-        char buf[64];
-        int ret, cpu;
-
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
+        int ret;
 
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         /* must have at least 1 entry */
         if (!val)
                 return -EINVAL;
 
-        mutex_lock(&trace_types_lock);
-
-        tracing_stop();
-
-        /* disable all cpu buffers */
-        for_each_tracing_cpu(cpu) {
-                if (global_trace.data[cpu])
-                        atomic_inc(&global_trace.data[cpu]->disabled);
-                if (max_tr.data[cpu])
-                        atomic_inc(&max_tr.data[cpu]->disabled);
-        }
-
         /* value is in KB */
         val <<= 10;
 
-        if (val != global_trace.entries) {
-                ret = tracing_resize_ring_buffer(val);
-                if (ret < 0) {
-                        cnt = ret;
-                        goto out;
-                }
-        }
+        ret = tracing_resize_ring_buffer(val);
+        if (ret < 0)
+                return ret;
 
         *ppos += cnt;
 
-        /* If check pages failed, return ENOMEM */
-        if (tracing_disabled)
-                cnt = -ENOMEM;
- out:
-        for_each_tracing_cpu(cpu) {
-                if (global_trace.data[cpu])
-                        atomic_dec(&global_trace.data[cpu]->disabled);
-                if (max_tr.data[cpu])
-                        atomic_dec(&max_tr.data[cpu]->disabled);
-        }
+        return cnt;
+}
 
-        tracing_start();
-        mutex_unlock(&trace_types_lock);
+static ssize_t
+tracing_free_buffer_write(struct file *filp, const char __user *ubuf,
+                          size_t cnt, loff_t *ppos)
+{
+        /*
+         * There is no need to read what the user has written, this function
+         * is just to make sure that there is no error when "echo" is used
+         */
+
+        *ppos += cnt;
 
         return cnt;
 }
 
+static int
+tracing_free_buffer_release(struct inode *inode, struct file *filp)
+{
+        /* disable tracing ? */
+        if (trace_flags & TRACE_ITER_STOP_ON_FREE)
+                tracing_off();
+        /* resize the ring buffer to 0 */
+        tracing_resize_ring_buffer(0);
+
+        return 0;
+}
+
 static int mark_printk(const char *fmt, ...)
 {
         int ret;
@@ -3640,6 +3739,11 @@ static const struct file_operations tracing_entries_fops = {
         .llseek         = generic_file_llseek,
 };
 
+static const struct file_operations tracing_free_buffer_fops = {
+        .write          = tracing_free_buffer_write,
+        .release        = tracing_free_buffer_release,
+};
+
 static const struct file_operations tracing_mark_fops = {
         .open           = tracing_open_generic,
         .write          = tracing_mark_write,
@@ -3696,7 +3800,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
                 return 0;
 
         if (!info->spare)
-                info->spare = ring_buffer_alloc_read_page(info->tr->buffer);
+                info->spare = ring_buffer_alloc_read_page(info->tr->buffer, info->cpu);
         if (!info->spare)
                 return -ENOMEM;
 
@@ -3853,7 +3957,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 
                 ref->ref = 1;
                 ref->buffer = info->tr->buffer;
-                ref->page = ring_buffer_alloc_read_page(ref->buffer);
+                ref->page = ring_buffer_alloc_read_page(ref->buffer, info->cpu);
                 if (!ref->page) {
                         kfree(ref);
                         break;
@@ -3862,8 +3966,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
                 r = ring_buffer_read_page(ref->buffer, &ref->page,
                                           len, info->cpu, 1);
                 if (r < 0) {
-                        ring_buffer_free_read_page(ref->buffer,
-                                                   ref->page);
+                        ring_buffer_free_read_page(ref->buffer, ref->page);
                         kfree(ref);
                         break;
                 }
@@ -4099,19 +4202,10 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
 {
         struct trace_option_dentry *topt = filp->private_data;
         unsigned long val;
-        char buf[64];
         int ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         if (val != 0 && val != 1)
@@ -4159,20 +4253,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
                          loff_t *ppos)
 {
         long index = (long)filp->private_data;
-        char buf[64];
         unsigned long val;
         int ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         if (val != 0 && val != 1)
@@ -4365,6 +4450,9 @@ static __init int tracer_init_debugfs(void)
         trace_create_file("buffer_size_kb", 0644, d_tracer,
                         &global_trace, &tracing_entries_fops);
 
+        trace_create_file("free_buffer", 0644, d_tracer,
+                        &global_trace, &tracing_free_buffer_fops);
+
         trace_create_file("trace_marker", 0220, d_tracer,
                         NULL, &tracing_mark_fops);
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 229f8591f61d..616846bcfee5 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -2,7 +2,7 @@
 #define _LINUX_KERNEL_TRACE_H
 
 #include <linux/fs.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/sched.h>
 #include <linux/clocksource.h>
 #include <linux/ring_buffer.h>
@@ -278,6 +278,29 @@ struct tracer {
 };
 
 
+/* Only current can touch trace_recursion */
+#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
+#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
+
+/* Ring buffer has the 10 LSB bits to count */
+#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
+
+/* for function tracing recursion */
+#define TRACE_INTERNAL_BIT              (1<<11)
+#define TRACE_GLOBAL_BIT                (1<<12)
+/*
+ * Abuse of the trace_recursion.
+ * As we need a way to maintain state if we are tracing the function
+ * graph in irq because we want to trace a particular function that
+ * was called in irq context but we have irq tracing off. Since this
+ * can only be modified by current, we can reuse trace_recursion.
+ */
+#define TRACE_IRQ_BIT                   (1<<13)
+
+#define trace_recursion_set(bit)        do { (current)->trace_recursion |= (bit); } while (0)
+#define trace_recursion_clear(bit)      do { (current)->trace_recursion &= ~(bit); } while (0)
+#define trace_recursion_test(bit)       ((current)->trace_recursion & (bit))
+
 #define TRACE_PIPE_ALL_CPU      -1
 
 int tracer_init(struct tracer *t, struct trace_array *tr);
@@ -389,6 +412,9 @@ void update_max_tr_single(struct trace_array *tr,
 void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
                         int skip, int pc);
 
+void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
+                             int skip, int pc, struct pt_regs *regs);
+
 void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
                             int pc);
 
@@ -400,6 +426,12 @@ static inline void ftrace_trace_stack(struct ring_buffer *buffer,
 {
 }
 
+static inline void ftrace_trace_stack_regs(struct ring_buffer *buffer,
+                                           unsigned long flags, int skip,
+                                           int pc, struct pt_regs *regs)
+{
+}
+
 static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
                                           unsigned long flags, int pc)
 {
@@ -507,8 +539,18 @@ static inline int ftrace_graph_addr(unsigned long addr)
                 return 1;
 
         for (i = 0; i < ftrace_graph_count; i++) {
-                if (addr == ftrace_graph_funcs[i])
+                if (addr == ftrace_graph_funcs[i]) {
+                        /*
+                         * If no irqs are to be traced, but a set_graph_function
+                         * is set, and called by an interrupt handler, we still
+                         * want to trace it.
+                         */
+                        if (in_irq())
+                                trace_recursion_set(TRACE_IRQ_BIT);
+                        else
+                                trace_recursion_clear(TRACE_IRQ_BIT);
                         return 1;
+                }
         }
 
         return 0;
@@ -609,6 +651,7 @@ enum trace_iterator_flags {
         TRACE_ITER_GRAPH_TIME           = 0x80000,
         TRACE_ITER_RECORD_CMD           = 0x100000,
         TRACE_ITER_OVERWRITE            = 0x200000,
+        TRACE_ITER_STOP_ON_FREE         = 0x400000,
 };
 
 /*
@@ -677,6 +720,7 @@ struct event_subsystem {
         struct dentry           *entry;
         struct event_filter     *filter;
         int                     nr_events;
+        int                     ref_count;
 };
 
 #define FILTER_PRED_INVALID     ((unsigned short)-1)
@@ -784,19 +828,4 @@ extern const char *__stop___trace_bprintk_fmt[];
         FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
 #include "trace_entries.h"
 
-/* Only current can touch trace_recursion */
-#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
-#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
-
-/* Ring buffer has the 10 LSB bits to count */
-#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
-
-/* for function tracing recursion */
-#define TRACE_INTERNAL_BIT              (1<<11)
-#define TRACE_GLOBAL_BIT                (1<<12)
-
-#define trace_recursion_set(bit)        do { (current)->trace_recursion |= (bit); } while (0)
-#define trace_recursion_clear(bit)      do { (current)->trace_recursion &= ~(bit); } while (0)
-#define trace_recursion_test(bit)       ((current)->trace_recursion & (bit))
-
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index e32744c84d94..93365907f219 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -161,7 +161,8 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
         TRACE_STACK,
 
         F_STRUCT(
-                __array(        unsigned long,  caller, FTRACE_STACK_ENTRIES    )
+                __field(        int,            size    )
+                __dynamic_array(unsigned long,  caller  )
         ),
 
         F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 686ec399f2a8..581876f9f387 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -244,6 +244,35 @@ static void ftrace_clear_events(void)
         mutex_unlock(&event_mutex);
 }
 
+static void __put_system(struct event_subsystem *system)
+{
+        struct event_filter *filter = system->filter;
+
+        WARN_ON_ONCE(system->ref_count == 0);
+        if (--system->ref_count)
+                return;
+
+        if (filter) {
+                kfree(filter->filter_string);
+                kfree(filter);
+        }
+        kfree(system->name);
+        kfree(system);
+}
+
+static void __get_system(struct event_subsystem *system)
+{
+        WARN_ON_ONCE(system->ref_count == 0);
+        system->ref_count++;
+}
+
+static void put_system(struct event_subsystem *system)
+{
+        mutex_lock(&event_mutex);
+        __put_system(system);
+        mutex_unlock(&event_mutex);
+}
+
 /*
  * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
  */
@@ -486,20 +515,11 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
                    loff_t *ppos)
 {
         struct ftrace_event_call *call = filp->private_data;
-        char buf[64];
         unsigned long val;
         int ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         ret = tracing_update_buffers();
@@ -528,7 +548,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
                    loff_t *ppos)
 {
         const char set_to_char[4] = { '?', '0', '1', 'X' };
-        const char *system = filp->private_data;
+        struct event_subsystem *system = filp->private_data;
         struct ftrace_event_call *call;
         char buf[2];
         int set = 0;
@@ -539,7 +559,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
                 if (!call->name || !call->class || !call->class->reg)
                         continue;
 
-                if (system && strcmp(call->class->system, system) != 0)
+                if (system && strcmp(call->class->system, system->name) != 0)
                         continue;
 
                 /*
@@ -569,21 +589,13 @@ static ssize_t
 system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
                     loff_t *ppos)
 {
-        const char *system = filp->private_data;
+        struct event_subsystem *system = filp->private_data;
+        const char *name = NULL;
         unsigned long val;
-        char buf[64];
         ssize_t ret;
 
-        if (cnt >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, cnt))
-                return -EFAULT;
-
-        buf[cnt] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+        if (ret)
                 return ret;
 
         ret = tracing_update_buffers();
@@ -593,7 +605,14 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
         if (val != 0 && val != 1)
                 return -EINVAL;
 
-        ret = __ftrace_set_clr_event(NULL, system, NULL, val);
+        /*
+         * Opening of "enable" adds a ref count to system,
+         * so the name is safe to use.
+         */
+        if (system)
+                name = system->name;
+
+        ret = __ftrace_set_clr_event(NULL, name, NULL, val);
         if (ret)
                 goto out;
 
@@ -826,6 +845,52 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
         return cnt;
 }
 
+static LIST_HEAD(event_subsystems);
+
+static int subsystem_open(struct inode *inode, struct file *filp)
+{
+        struct event_subsystem *system = NULL;
+        int ret;
+
+        if (!inode->i_private)
+                goto skip_search;
+
+        /* Make sure the system still exists */
+        mutex_lock(&event_mutex);
+        list_for_each_entry(system, &event_subsystems, list) {
+                if (system == inode->i_private) {
+                        /* Don't open systems with no events */
+                        if (!system->nr_events) {
+                                system = NULL;
+                                break;
+                        }
+                        __get_system(system);
+                        break;
+                }
+        }
+        mutex_unlock(&event_mutex);
+
+        if (system != inode->i_private)
+                return -ENODEV;
+
+ skip_search:
+        ret = tracing_open_generic(inode, filp);
+        if (ret < 0 && system)
+                put_system(system);
+
+        return ret;
+}
+
+static int subsystem_release(struct inode *inode, struct file *file)
+{
+        struct event_subsystem *system = inode->i_private;
+
+        if (system)
+                put_system(system);
+
+        return 0;
+}
+
 static ssize_t
 subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
                       loff_t *ppos)
@@ -963,17 +1028,19 @@ static const struct file_operations ftrace_event_filter_fops = {
 };
 
 static const struct file_operations ftrace_subsystem_filter_fops = {
-        .open = tracing_open_generic,
+        .open = subsystem_open,
         .read = subsystem_filter_read,
         .write = subsystem_filter_write,
         .llseek = default_llseek,
+        .release = subsystem_release,
 };
 
 static const struct file_operations ftrace_system_enable_fops = {
-        .open = tracing_open_generic,
+        .open = subsystem_open,
         .read = system_enable_read,
         .write = system_enable_write,
         .llseek = default_llseek,
+        .release = subsystem_release,
 };
 
 static const struct file_operations ftrace_show_header_fops = {
@@ -1002,8 +1069,6 @@ static struct dentry *event_trace_events_dir(void)
         return d_events;
 }
 
-static LIST_HEAD(event_subsystems);
-
 static struct dentry *
 event_subsystem_dir(const char *name, struct dentry *d_events)
 {
@@ -1013,6 +1078,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
         /* First see if we did not already create this dir */
         list_for_each_entry(system, &event_subsystems, list) {
                 if (strcmp(system->name, name) == 0) {
+                        __get_system(system);
                         system->nr_events++;
                         return system->entry;
                 }
@@ -1035,6 +1101,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
         }
 
         system->nr_events = 1;
+        system->ref_count = 1;
         system->name = kstrdup(name, GFP_KERNEL);
         if (!system->name) {
                 debugfs_remove(system->entry);
@@ -1062,8 +1129,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
                            "'%s/filter' entry\n", name);
         }
 
-        trace_create_file("enable", 0644, system->entry,
-                          (void *)system->name,
+        trace_create_file("enable", 0644, system->entry, system,
                           &ftrace_system_enable_fops);
 
         return system->entry;
@@ -1184,16 +1250,9 @@ static void remove_subsystem_dir(const char *name)
         list_for_each_entry(system, &event_subsystems, list) {
                 if (strcmp(system->name, name) == 0) {
                         if (!--system->nr_events) {
-                                struct event_filter *filter = system->filter;
-
                                 debugfs_remove_recursive(system->entry);
                                 list_del(&system->list);
-                                if (filter) {
-                                        kfree(filter->filter_string);
-                                        kfree(filter);
-                                }
-                                kfree(system->name);
-                                kfree(system);
+                                __put_system(system);
                         }
                         break;
                 }
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 8008ddcfbf20..256764ecccd6 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1886,6 +1886,12 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 
         mutex_lock(&event_mutex);
 
+        /* Make sure the system still has events */
+        if (!system->nr_events) {
+                err = -ENODEV;
+                goto out_unlock;
+        }
+
         if (!strcmp(strstrip(filter_string), "0")) {
                 filter_free_subsystem_preds(system);
                 remove_filter_string(system->filter);
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 8d0e1cc4e974..c7b0c6a7db09 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -324,7 +324,8 @@ ftrace_trace_onoff_unreg(char *glob, char *cmd, char *param)
 }
 
 static int
-ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable)
+ftrace_trace_onoff_callback(struct ftrace_hash *hash,
+                            char *glob, char *cmd, char *param, int enable)
 {
         struct ftrace_probe_ops *ops;
         void *count = (void *)-1;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 962cdb24ed81..a7d2a4c653d8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -74,6 +74,20 @@ static struct tracer_flags tracer_flags = {
 
 static struct trace_array *graph_array;
 
+/*
+ * DURATION column is being also used to display IRQ signs,
+ * following values are used by print_graph_irq and others
+ * to fill in space into DURATION column.
+ */
+enum {
+        DURATION_FILL_FULL  = -1,
+        DURATION_FILL_START = -2,
+        DURATION_FILL_END   = -3,
+};
+
+static enum print_line_t
+print_graph_duration(unsigned long long duration, struct trace_seq *s,
+                     u32 flags);
 
 /* Add a function return address to the trace stack on thread info.*/
 int
@@ -213,7 +227,7 @@ int __trace_graph_entry(struct trace_array *tr,
 
 static inline int ftrace_graph_ignore_irqs(void)
 {
-        if (!ftrace_graph_skip_irqs)
+        if (!ftrace_graph_skip_irqs || trace_recursion_test(TRACE_IRQ_BIT))
                 return 0;
 
         return in_irq();
@@ -577,32 +591,6 @@ get_return_for_leaf(struct trace_iterator *iter,
         return next;
 }
 
-/* Signal a overhead of time execution to the output */
-static int
-print_graph_overhead(unsigned long long duration, struct trace_seq *s,
-                     u32 flags)
-{
-        /* If duration disappear, we don't need anything */
-        if (!(flags & TRACE_GRAPH_PRINT_DURATION))
-                return 1;
-
-        /* Non nested entry or return */
-        if (duration == -1)
-                return trace_seq_printf(s, "  ");
-
-        if (flags & TRACE_GRAPH_PRINT_OVERHEAD) {
-                /* Duration exceeded 100 msecs */
-                if (duration > 100000ULL)
-                        return trace_seq_printf(s, "! ");
-
-                /* Duration exceeded 10 msecs */
-                if (duration > 10000ULL)
-                        return trace_seq_printf(s, "+ ");
-        }
-
-        return trace_seq_printf(s, "  ");
-}
-
 static int print_graph_abs_time(u64 t, struct trace_seq *s)
 {
         unsigned long usecs_rem;
@@ -625,34 +613,36 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
                 addr >= (unsigned long)__irqentry_text_end)
                 return TRACE_TYPE_UNHANDLED;
 
-        /* Absolute time */
-        if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
-                ret = print_graph_abs_time(iter->ts, s);
-                if (!ret)
-                        return TRACE_TYPE_PARTIAL_LINE;
-        }
+        if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
+                /* Absolute time */
+                if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
+                        ret = print_graph_abs_time(iter->ts, s);
+                        if (!ret)
+                                return TRACE_TYPE_PARTIAL_LINE;
+                }
 
-        /* Cpu */
-        if (flags & TRACE_GRAPH_PRINT_CPU) {
-                ret = print_graph_cpu(s, cpu);
-                if (ret == TRACE_TYPE_PARTIAL_LINE)
-                        return TRACE_TYPE_PARTIAL_LINE;
-        }
+                /* Cpu */
+                if (flags & TRACE_GRAPH_PRINT_CPU) {
+                        ret = print_graph_cpu(s, cpu);
+                        if (ret == TRACE_TYPE_PARTIAL_LINE)
+                                return TRACE_TYPE_PARTIAL_LINE;
+                }
 
-        /* Proc */
-        if (flags & TRACE_GRAPH_PRINT_PROC) {
-                ret = print_graph_proc(s, pid);
-                if (ret == TRACE_TYPE_PARTIAL_LINE)
-                        return TRACE_TYPE_PARTIAL_LINE;
-                ret = trace_seq_printf(s, " | ");
-                if (!ret)
-                        return TRACE_TYPE_PARTIAL_LINE;
+                /* Proc */
+                if (flags & TRACE_GRAPH_PRINT_PROC) {
+                        ret = print_graph_proc(s, pid);
+                        if (ret == TRACE_TYPE_PARTIAL_LINE)
+                                return TRACE_TYPE_PARTIAL_LINE;
+                        ret = trace_seq_printf(s, " | ");
+                        if (!ret)
+                                return TRACE_TYPE_PARTIAL_LINE;
+                }
         }
 
         /* No overhead */
-        ret = print_graph_overhead(-1, s, flags);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
+        ret = print_graph_duration(DURATION_FILL_START, s, flags);
+        if (ret != TRACE_TYPE_HANDLED)
+                return ret;
 
         if (type == TRACE_GRAPH_ENT)
                 ret = trace_seq_printf(s, "==========>");
@@ -662,9 +652,10 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
-        /* Don't close the duration column if haven't one */
-        if (flags & TRACE_GRAPH_PRINT_DURATION)
-                trace_seq_printf(s, " |");
+        ret = print_graph_duration(DURATION_FILL_END, s, flags);
+        if (ret != TRACE_TYPE_HANDLED)
+                return ret;
+
         ret = trace_seq_printf(s, "\n");
 
         if (!ret)
@@ -716,9 +707,49 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
 }
 
 static enum print_line_t
-print_graph_duration(unsigned long long duration, struct trace_seq *s)
+print_graph_duration(unsigned long long duration, struct trace_seq *s,
+                     u32 flags)
 {
-        int ret;
+        int ret = -1;
+
+        if (!(flags & TRACE_GRAPH_PRINT_DURATION) ||
+            !(trace_flags & TRACE_ITER_CONTEXT_INFO))
+                        return TRACE_TYPE_HANDLED;
+
+        /* No real adata, just filling the column with spaces */
+        switch (duration) {
+        case DURATION_FILL_FULL:
+                ret = trace_seq_printf(s, "              |  ");
+                return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+        case DURATION_FILL_START:
+                ret = trace_seq_printf(s, "  ");
+                return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+        case DURATION_FILL_END:
+                ret = trace_seq_printf(s, " |");
+                return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+        }
+
+        /* Signal a overhead of time execution to the output */
+        if (flags & TRACE_GRAPH_PRINT_OVERHEAD) {
+                /* Duration exceeded 100 msecs */
+                if (duration > 100000ULL)
+                        ret = trace_seq_printf(s, "! ");
+                /* Duration exceeded 10 msecs */
+                else if (duration > 10000ULL)
+                        ret = trace_seq_printf(s, "+ ");
+        }
+
+        /*
+         * The -1 means we either did not exceed the duration tresholds
+         * or we dont want to print out the overhead. Either way we need
+         * to fill out the space.
+         */
+        if (ret == -1)
+                ret = trace_seq_printf(s, "  ");
+
+        /* Catching here any failure happenned above */
+        if (!ret)
+                return TRACE_TYPE_PARTIAL_LINE;
 
         ret = trace_print_graph_duration(duration, s);
         if (ret != TRACE_TYPE_HANDLED)
@@ -767,18 +798,11 @@ print_graph_entry_leaf(struct trace_iterator *iter,
                         cpu_data->enter_funcs[call->depth] = 0;
         }
 
-        /* Overhead */
-        ret = print_graph_overhead(duration, s, flags);
-        if (!ret)
+        /* Overhead and duration */
+        ret = print_graph_duration(duration, s, flags);
+        if (ret == TRACE_TYPE_PARTIAL_LINE)
                 return TRACE_TYPE_PARTIAL_LINE;
 
-        /* Duration */
-        if (flags & TRACE_GRAPH_PRINT_DURATION) {
-                ret = print_graph_duration(duration, s);
-                if (ret == TRACE_TYPE_PARTIAL_LINE)
-                        return TRACE_TYPE_PARTIAL_LINE;
-        }
-
         /* Function */
         for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
                 ret = trace_seq_printf(s, " ");
@@ -815,17 +839,10 @@ print_graph_entry_nested(struct trace_iterator *iter,
                         cpu_data->enter_funcs[call->depth] = call->func;
         }
 
-        /* No overhead */
-        ret = print_graph_overhead(-1, s, flags);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
         /* No time */
-        if (flags & TRACE_GRAPH_PRINT_DURATION) {
-                ret = trace_seq_printf(s, "            |  ");
-                if (!ret)
-                        return TRACE_TYPE_PARTIAL_LINE;
-        }
+        ret = print_graph_duration(DURATION_FILL_FULL, s, flags);
+        if (ret != TRACE_TYPE_HANDLED)
+                return ret;
 
         /* Function */
         for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
@@ -865,6 +882,9 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
+        if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
+                return 0;
+
         /* Absolute time */
         if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
                 ret = print_graph_abs_time(iter->ts, s);
@@ -1078,18 +1098,11 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
         if (print_graph_prologue(iter, s, 0, 0, flags))
                 return TRACE_TYPE_PARTIAL_LINE;
 
-        /* Overhead */
-        ret = print_graph_overhead(duration, s, flags);
-        if (!ret)
+        /* Overhead and duration */
+        ret = print_graph_duration(duration, s, flags);
+        if (ret == TRACE_TYPE_PARTIAL_LINE)
                 return TRACE_TYPE_PARTIAL_LINE;
 
-        /* Duration */
-        if (flags & TRACE_GRAPH_PRINT_DURATION) {
-                ret = print_graph_duration(duration, s);
-                if (ret == TRACE_TYPE_PARTIAL_LINE)
-                        return TRACE_TYPE_PARTIAL_LINE;
-        }
-
         /* Closing brace */
         for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) {
                 ret = trace_seq_printf(s, " ");
@@ -1146,17 +1159,10 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
         if (print_graph_prologue(iter, s, 0, 0, flags))
                 return TRACE_TYPE_PARTIAL_LINE;
 
-        /* No overhead */
-        ret = print_graph_overhead(-1, s, flags);
-        if (!ret)
-                return TRACE_TYPE_PARTIAL_LINE;
-
         /* No time */
-        if (flags & TRACE_GRAPH_PRINT_DURATION) {
-                ret = trace_seq_printf(s, "            |  ");
-                if (!ret)
-                        return TRACE_TYPE_PARTIAL_LINE;
-        }
+        ret = print_graph_duration(DURATION_FILL_FULL, s, flags);
+        if (ret != TRACE_TYPE_HANDLED)
+                return ret;
 
         /* Indentation */
         if (depth > 0)
@@ -1207,7 +1213,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 
 
 enum print_line_t
-__print_graph_function_flags(struct trace_iterator *iter, u32 flags)
+print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 {
         struct ftrace_graph_ent_entry *field;
         struct fgraph_data *data = iter->private;
@@ -1270,18 +1276,7 @@ __print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 static enum print_line_t
 print_graph_function(struct trace_iterator *iter)
 {
-        return __print_graph_function_flags(iter, tracer_flags.val);
-}
-
-enum print_line_t print_graph_function_flags(struct trace_iterator *iter,
-                                             u32 flags)
-{
-        if (trace_flags & TRACE_ITER_LATENCY_FMT)
-                flags |= TRACE_GRAPH_PRINT_DURATION;
-        else
-                flags |= TRACE_GRAPH_PRINT_ABS_TIME;
-
-        return __print_graph_function_flags(iter, flags);
+        return print_graph_function_flags(iter, tracer_flags.val);
 }
 
 static enum print_line_t
@@ -1309,8 +1304,7 @@ static void print_lat_header(struct seq_file *s, u32 flags)
         seq_printf(s, "#%.*s / _----=> need-resched    \n", size, spaces);
         seq_printf(s, "#%.*s| / _---=> hardirq/softirq \n", size, spaces);
         seq_printf(s, "#%.*s|| / _--=> preempt-depth   \n", size, spaces);
-        seq_printf(s, "#%.*s||| / _-=> lock-depth      \n", size, spaces);
-        seq_printf(s, "#%.*s|||| /                     \n", size, spaces);
+        seq_printf(s, "#%.*s||| /                      \n", size, spaces);
 }
 
 static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
@@ -1329,7 +1323,7 @@ static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
         if (flags & TRACE_GRAPH_PRINT_PROC)
                 seq_printf(s, "  TASK/PID       ");
         if (lat)
-                seq_printf(s, "|||||");
+                seq_printf(s, "||||");
         if (flags & TRACE_GRAPH_PRINT_DURATION)
                 seq_printf(s, "  DURATION   ");
         seq_printf(s, "               FUNCTION CALLS\n");
@@ -1343,7 +1337,7 @@ static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
         if (flags & TRACE_GRAPH_PRINT_PROC)
                 seq_printf(s, "   |    |        ");
         if (lat)
-                seq_printf(s, "|||||");
+                seq_printf(s, "||||");
         if (flags & TRACE_GRAPH_PRINT_DURATION)
                 seq_printf(s, "   |   |      ");
         seq_printf(s, "               |   |   |   |\n");
@@ -1358,15 +1352,16 @@ void print_graph_headers_flags(struct seq_file *s, u32 flags)
 {
         struct trace_iterator *iter = s->private;
 
+        if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
+                return;
+
         if (trace_flags & TRACE_ITER_LATENCY_FMT) {
                 /* print nothing if the buffers are empty */
                 if (trace_empty(iter))
                         return;
 
                 print_trace_header(s, iter);
-                flags |= TRACE_GRAPH_PRINT_DURATION;
-        } else
-                flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+        }
 
         __print_graph_headers_flags(s, flags);
 }
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index c77424be284d..667aa8cc0cfc 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -226,7 +226,9 @@ static void irqsoff_trace_close(struct trace_iterator *iter)
 }
 
 #define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_CPU | \
-                            TRACE_GRAPH_PRINT_PROC)
+                            TRACE_GRAPH_PRINT_PROC | \
+                            TRACE_GRAPH_PRINT_ABS_TIME | \
+                            TRACE_GRAPH_PRINT_DURATION)
 
 static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
 {
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 27d13b36b8be..5fb3697bf0e5 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -343,6 +343,14 @@ DEFINE_BASIC_FETCH_FUNCS(deref)
 DEFINE_FETCH_deref(string)
 DEFINE_FETCH_deref(string_size)
 
+static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data)
+{
+        if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+                update_deref_fetch_param(data->orig.data);
+        else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+                update_symbol_cache(data->orig.data);
+}
+
 static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
 {
         if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
@@ -377,6 +385,19 @@ DEFINE_BASIC_FETCH_FUNCS(bitfield)
 #define fetch_bitfield_string_size NULL
 
 static __kprobes void
+update_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+        /*
+         * Don't check the bitfield itself, because this must be the
+         * last fetch function.
+         */
+        if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+                update_deref_fetch_param(data->orig.data);
+        else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+                update_symbol_cache(data->orig.data);
+}
+
+static __kprobes void
 free_bitfield_fetch_param(struct bitfield_fetch_param *data)
 {
         /*
@@ -389,6 +410,7 @@ free_bitfield_fetch_param(struct bitfield_fetch_param *data)
                 free_symbol_cache(data->orig.data);
         kfree(data);
 }
+
 /* Default (unsigned long) fetch type */
 #define __DEFAULT_FETCH_TYPE(t) u##t
 #define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
@@ -536,6 +558,7 @@ struct probe_arg {
 /* Flags for trace_probe */
 #define TP_FLAG_TRACE   1
 #define TP_FLAG_PROFILE 2
+#define TP_FLAG_REGISTERED 4
 
 struct trace_probe {
         struct list_head        list;
@@ -555,16 +578,49 @@ struct trace_probe {
         (sizeof(struct probe_arg) * (n)))
 
 
-static __kprobes int probe_is_return(struct trace_probe *tp)
+static __kprobes int trace_probe_is_return(struct trace_probe *tp)
 {
         return tp->rp.handler != NULL;
 }
 
-static __kprobes const char *probe_symbol(struct trace_probe *tp)
+static __kprobes const char *trace_probe_symbol(struct trace_probe *tp)
 {
         return tp->symbol ? tp->symbol : "unknown";
 }
 
+static __kprobes unsigned long trace_probe_offset(struct trace_probe *tp)
+{
+        return tp->rp.kp.offset;
+}
+
+static __kprobes bool trace_probe_is_enabled(struct trace_probe *tp)
+{
+        return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
+}
+
+static __kprobes bool trace_probe_is_registered(struct trace_probe *tp)
+{
+        return !!(tp->flags & TP_FLAG_REGISTERED);
+}
+
+static __kprobes bool trace_probe_has_gone(struct trace_probe *tp)
+{
+        return !!(kprobe_gone(&tp->rp.kp));
+}
+
+static __kprobes bool trace_probe_within_module(struct trace_probe *tp,
+                                                struct module *mod)
+{
+        int len = strlen(mod->name);
+        const char *name = trace_probe_symbol(tp);
+        return strncmp(mod->name, name, len) == 0 && name[len] == ':';
+}
+
+static __kprobes bool trace_probe_is_on_module(struct trace_probe *tp)
+{
+        return !!strchr(trace_probe_symbol(tp), ':');
+}
+
 static int register_probe_event(struct trace_probe *tp);
 static void unregister_probe_event(struct trace_probe *tp);
 
@@ -646,6 +702,16 @@ error:
         return ERR_PTR(ret);
 }
 
+static void update_probe_arg(struct probe_arg *arg)
+{
+        if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
+                update_bitfield_fetch_param(arg->fetch.data);
+        else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+                update_deref_fetch_param(arg->fetch.data);
+        else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
+                update_symbol_cache(arg->fetch.data);
+}
+
 static void free_probe_arg(struct probe_arg *arg)
 {
         if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
@@ -671,7 +737,7 @@ static void free_trace_probe(struct trace_probe *tp)
         kfree(tp);
 }
 
-static struct trace_probe *find_probe_event(const char *event,
+static struct trace_probe *find_trace_probe(const char *event,
                                             const char *group)
 {
         struct trace_probe *tp;
@@ -683,13 +749,96 @@ static struct trace_probe *find_probe_event(const char *event,
         return NULL;
 }
 
+/* Enable trace_probe - @flag must be TP_FLAG_TRACE or TP_FLAG_PROFILE */
+static int enable_trace_probe(struct trace_probe *tp, int flag)
+{
+        int ret = 0;
+
+        tp->flags |= flag;
+        if (trace_probe_is_enabled(tp) && trace_probe_is_registered(tp) &&
+            !trace_probe_has_gone(tp)) {
+                if (trace_probe_is_return(tp))
+                        ret = enable_kretprobe(&tp->rp);
+                else
+                        ret = enable_kprobe(&tp->rp.kp);
+        }
+
+        return ret;
+}
+
+/* Disable trace_probe - @flag must be TP_FLAG_TRACE or TP_FLAG_PROFILE */
+static void disable_trace_probe(struct trace_probe *tp, int flag)
+{
+        tp->flags &= ~flag;
+        if (!trace_probe_is_enabled(tp) && trace_probe_is_registered(tp)) {
+                if (trace_probe_is_return(tp))
+                        disable_kretprobe(&tp->rp);
+                else
+                        disable_kprobe(&tp->rp.kp);
+        }
+}
+
+/* Internal register function - just handle k*probes and flags */
+static int __register_trace_probe(struct trace_probe *tp)
+{
+        int i, ret;
+
+        if (trace_probe_is_registered(tp))
+                return -EINVAL;
+
+        for (i = 0; i < tp->nr_args; i++)
+                update_probe_arg(&tp->args[i]);
+
+        /* Set/clear disabled flag according to tp->flag */
+        if (trace_probe_is_enabled(tp))
+                tp->rp.kp.flags &= ~KPROBE_FLAG_DISABLED;
+        else
+                tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
+
+        if (trace_probe_is_return(tp))
+                ret = register_kretprobe(&tp->rp);
+        else
+                ret = register_kprobe(&tp->rp.kp);
+
+        if (ret == 0)
+                tp->flags |= TP_FLAG_REGISTERED;
+        else {
+                pr_warning("Could not insert probe at %s+%lu: %d\n",
+                           trace_probe_symbol(tp), trace_probe_offset(tp), ret);
+                if (ret == -ENOENT && trace_probe_is_on_module(tp)) {
+                        pr_warning("This probe might be able to register after"
+                                   "target module is loaded. Continue.\n");
+                        ret = 0;
+                } else if (ret == -EILSEQ) {
+                        pr_warning("Probing address(0x%p) is not an "
+                                   "instruction boundary.\n",
+                                   tp->rp.kp.addr);
+                        ret = -EINVAL;
+                }
+        }
+
+        return ret;
+}
+
+/* Internal unregister function - just handle k*probes and flags */
+static void __unregister_trace_probe(struct trace_probe *tp)
+{
+        if (trace_probe_is_registered(tp)) {
+                if (trace_probe_is_return(tp))
+                        unregister_kretprobe(&tp->rp);
+                else
+                        unregister_kprobe(&tp->rp.kp);
+                tp->flags &= ~TP_FLAG_REGISTERED;
+                /* Cleanup kprobe for reuse */
+                if (tp->rp.kp.symbol_name)
+                        tp->rp.kp.addr = 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);
+        __unregister_trace_probe(tp);
         list_del(&tp->list);
         unregister_probe_event(tp);
 }
@@ -702,41 +851,65 @@ static int register_trace_probe(struct trace_probe *tp)
 
         mutex_lock(&probe_lock);
 
-        /* register as an event */
-        old_tp = find_probe_event(tp->call.name, tp->call.class->system);
+        /* Delete old (same name) event if exist */
+        old_tp = find_trace_probe(tp->call.name, tp->call.class->system);
         if (old_tp) {
-                /* delete old event */
                 unregister_trace_probe(old_tp);
                 free_trace_probe(old_tp);
         }
+
+        /* Register new event */
         ret = register_probe_event(tp);
         if (ret) {
                 pr_warning("Failed to register probe event(%d)\n", ret);
                 goto end;
         }
 
-        tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
-        if (probe_is_return(tp))
-                ret = register_kretprobe(&tp->rp);
-        else
-                ret = register_kprobe(&tp->rp.kp);
-
-        if (ret) {
-                pr_warning("Could not insert probe(%d)\n", ret);
-                if (ret == -EILSEQ) {
-                        pr_warning("Probing address(0x%p) is not an "
-                                   "instruction boundary.\n",
-                                   tp->rp.kp.addr);
-                        ret = -EINVAL;
-                }
+        /* Register k*probe */
+        ret = __register_trace_probe(tp);
+        if (ret < 0)
                 unregister_probe_event(tp);
-        } else
+        else
                 list_add_tail(&tp->list, &probe_list);
+
 end:
         mutex_unlock(&probe_lock);
         return ret;
 }
 
+/* Module notifier call back, checking event on the module */
+static int trace_probe_module_callback(struct notifier_block *nb,
+                                       unsigned long val, void *data)
+{
+        struct module *mod = data;
+        struct trace_probe *tp;
+        int ret;
+
+        if (val != MODULE_STATE_COMING)
+                return NOTIFY_DONE;
+
+        /* Update probes on coming module */
+        mutex_lock(&probe_lock);
+        list_for_each_entry(tp, &probe_list, list) {
+                if (trace_probe_within_module(tp, mod)) {
+                        __unregister_trace_probe(tp);
+                        ret = __register_trace_probe(tp);
+                        if (ret)
+                                pr_warning("Failed to re-register probe %s on"
+                                           "%s: %d\n",
+                                           tp->call.name, mod->name, ret);
+                }
+        }
+        mutex_unlock(&probe_lock);
+
+        return NOTIFY_DONE;
+}
+
+static struct notifier_block trace_probe_module_nb = {
+        .notifier_call = trace_probe_module_callback,
+        .priority = 1   /* Invoked after kprobe module callback */
+};
+
 /* Split symbol and offset. */
 static int split_symbol_offset(char *symbol, unsigned long *offset)
 {
@@ -962,8 +1135,8 @@ 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]
+         *  - Add kprobe: p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
+         *  - Add kretprobe: r[:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS]
          * Fetch args:
          *  $retval     : fetch return value
          *  $stack      : fetch stack address
@@ -1025,7 +1198,7 @@ static int create_trace_probe(int argc, char **argv)
                         return -EINVAL;
                 }
                 mutex_lock(&probe_lock);
-                tp = find_probe_event(event, group);
+                tp = find_trace_probe(event, group);
                 if (!tp) {
                         mutex_unlock(&probe_lock);
                         pr_info("Event %s/%s doesn't exist.\n", group, event);
@@ -1144,7 +1317,7 @@ error:
         return ret;
 }
 
-static void cleanup_all_probes(void)
+static void release_all_trace_probes(void)
 {
         struct trace_probe *tp;
 
@@ -1158,7 +1331,6 @@ static void cleanup_all_probes(void)
         mutex_unlock(&probe_lock);
 }
 
-
 /* Probes listing interfaces */
 static void *probes_seq_start(struct seq_file *m, loff_t *pos)
 {
@@ -1181,15 +1353,16 @@ static int probes_seq_show(struct seq_file *m, void *v)
         struct trace_probe *tp = v;
         int i;
 
-        seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
+        seq_printf(m, "%c", trace_probe_is_return(tp) ? 'r' : 'p');
         seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
 
         if (!tp->symbol)
                 seq_printf(m, " 0x%p", tp->rp.kp.addr);
         else if (tp->rp.kp.offset)
-                seq_printf(m, " %s+%u", probe_symbol(tp), tp->rp.kp.offset);
+                seq_printf(m, " %s+%u", trace_probe_symbol(tp),
+                           tp->rp.kp.offset);
         else
-                seq_printf(m, " %s", probe_symbol(tp));
+                seq_printf(m, " %s", trace_probe_symbol(tp));
 
         for (i = 0; i < tp->nr_args; i++)
                 seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm);
@@ -1209,7 +1382,7 @@ static int probes_open(struct inode *inode, struct file *file)
 {
         if ((file->f_mode & FMODE_WRITE) &&
             (file->f_flags & O_TRUNC))
-                cleanup_all_probes();
+                release_all_trace_probes();
 
         return seq_open(file, &probes_seq_op);
 }
@@ -1397,7 +1570,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
         store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
         if (!filter_current_check_discard(buffer, call, entry, event))
-                trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+                trace_nowake_buffer_unlock_commit_regs(buffer, event,
+                                                       irq_flags, pc, regs);
 }
 
 /* Kretprobe handler */
@@ -1429,7 +1603,8 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
         store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
         if (!filter_current_check_discard(buffer, call, entry, event))
-                trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+                trace_nowake_buffer_unlock_commit_regs(buffer, event,
+                                                       irq_flags, pc, regs);
 }
 
 /* Event entry printers */
@@ -1511,30 +1686,6 @@ partial:
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static int probe_event_enable(struct ftrace_event_call *call)
-{
-        struct trace_probe *tp = (struct trace_probe *)call->data;
-
-        tp->flags |= TP_FLAG_TRACE;
-        if (probe_is_return(tp))
-                return enable_kretprobe(&tp->rp);
-        else
-                return enable_kprobe(&tp->rp.kp);
-}
-
-static void probe_event_disable(struct ftrace_event_call *call)
-{
-        struct trace_probe *tp = (struct trace_probe *)call->data;
-
-        tp->flags &= ~TP_FLAG_TRACE;
-        if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) {
-                if (probe_is_return(tp))
-                        disable_kretprobe(&tp->rp);
-                else
-                        disable_kprobe(&tp->rp.kp);
-        }
-}
-
 #undef DEFINE_FIELD
 #define DEFINE_FIELD(type, item, name, is_signed)                       \
         do {                                                            \
@@ -1596,7 +1747,7 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
 
         const char *fmt, *arg;
 
-        if (!probe_is_return(tp)) {
+        if (!trace_probe_is_return(tp)) {
                 fmt = "(%lx)";
                 arg = "REC->" FIELD_STRING_IP;
         } else {
@@ -1713,49 +1864,25 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
         head = this_cpu_ptr(call->perf_events);
         perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
 }
-
-static int probe_perf_enable(struct ftrace_event_call *call)
-{
-        struct trace_probe *tp = (struct trace_probe *)call->data;
-
-        tp->flags |= TP_FLAG_PROFILE;
-
-        if (probe_is_return(tp))
-                return enable_kretprobe(&tp->rp);
-        else
-                return enable_kprobe(&tp->rp.kp);
-}
-
-static void probe_perf_disable(struct ftrace_event_call *call)
-{
-        struct trace_probe *tp = (struct trace_probe *)call->data;
-
-        tp->flags &= ~TP_FLAG_PROFILE;
-
-        if (!(tp->flags & TP_FLAG_TRACE)) {
-                if (probe_is_return(tp))
-                        disable_kretprobe(&tp->rp);
-                else
-                        disable_kprobe(&tp->rp.kp);
-        }
-}
 #endif  /* CONFIG_PERF_EVENTS */
 
 static __kprobes
 int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
 {
+        struct trace_probe *tp = (struct trace_probe *)event->data;
+
         switch (type) {
         case TRACE_REG_REGISTER:
-                return probe_event_enable(event);
+                return enable_trace_probe(tp, TP_FLAG_TRACE);
         case TRACE_REG_UNREGISTER:
-                probe_event_disable(event);
+                disable_trace_probe(tp, TP_FLAG_TRACE);
                 return 0;
 
 #ifdef CONFIG_PERF_EVENTS
         case TRACE_REG_PERF_REGISTER:
-                return probe_perf_enable(event);
+                return enable_trace_probe(tp, TP_FLAG_PROFILE);
         case TRACE_REG_PERF_UNREGISTER:
-                probe_perf_disable(event);
+                disable_trace_probe(tp, TP_FLAG_PROFILE);
                 return 0;
 #endif
         }
@@ -1805,7 +1932,7 @@ static int register_probe_event(struct trace_probe *tp)
 
         /* Initialize ftrace_event_call */
         INIT_LIST_HEAD(&call->class->fields);
-        if (probe_is_return(tp)) {
+        if (trace_probe_is_return(tp)) {
                 call->event.funcs = &kretprobe_funcs;
                 call->class->define_fields = kretprobe_event_define_fields;
         } else {
@@ -1844,6 +1971,9 @@ static __init int init_kprobe_trace(void)
         struct dentry *d_tracer;
         struct dentry *entry;
 
+        if (register_module_notifier(&trace_probe_module_nb))
+                return -EINVAL;
+
         d_tracer = tracing_init_dentry();
         if (!d_tracer)
                 return 0;
@@ -1897,12 +2027,12 @@ static __init int kprobe_trace_self_tests_init(void)
                 warn++;
         } else {
                 /* Enable trace point */
-                tp = find_probe_event("testprobe", KPROBE_EVENT_SYSTEM);
+                tp = find_trace_probe("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);
+                        enable_trace_probe(tp, TP_FLAG_TRACE);
         }
 
         ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
@@ -1912,12 +2042,12 @@ static __init int kprobe_trace_self_tests_init(void)
                 warn++;
         } else {
                 /* Enable trace point */
-                tp = find_probe_event("testprobe2", KPROBE_EVENT_SYSTEM);
+                tp = find_trace_probe("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);
+                        enable_trace_probe(tp, TP_FLAG_TRACE);
         }
 
         if (warn)
@@ -1938,7 +2068,7 @@ static __init int kprobe_trace_self_tests_init(void)
         }
 
 end:
-        cleanup_all_probes();
+        release_all_trace_probes();
         if (warn)
                 pr_cont("NG: Some tests are failed. Please check them.\n");
         else
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 017fa376505d..fd3c8aae55e5 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -12,7 +12,7 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 #include "trace.h"
 #include "trace_output.h"
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index e37de492a9e1..51999309a6cf 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1107,19 +1107,20 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 {
         struct stack_entry *field;
         struct trace_seq *s = &iter->seq;
-        int i;
+        unsigned long *p;
+        unsigned long *end;
 
         trace_assign_type(field, iter->ent);
+        end = (unsigned long *)((long)iter->ent + iter->ent_size);
 
         if (!trace_seq_puts(s, "<stack trace>\n"))
                 goto partial;
-        for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
-                if (!field->caller[i] || (field->caller[i] == ULONG_MAX))
-                        break;
+
+        for (p = field->caller; p && *p != ULONG_MAX && p < end; p++) {
                 if (!trace_seq_puts(s, " => "))
                         goto partial;
 
-                if (!seq_print_ip_sym(s, field->caller[i], flags))
+                if (!seq_print_ip_sym(s, *p, flags))
                         goto partial;
                 if (!trace_seq_puts(s, "\n"))
                         goto partial;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index f029dd4fd2ca..e4a70c0c71b6 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -227,7 +227,9 @@ static void wakeup_trace_close(struct trace_iterator *iter)
                 graph_trace_close(iter);
 }
 
-#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC)
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC | \
+                            TRACE_GRAPH_PRINT_ABS_TIME | \
+                            TRACE_GRAPH_PRINT_DURATION)
 
 static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
 {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index b0b53b8e4c25..77575b386d97 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -156,20 +156,11 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
 {
         long *ptr = filp->private_data;
         unsigned long val, flags;
-        char buf[64];
         int ret;
         int cpu;
 
-        if (count >= sizeof(buf))
-                return -EINVAL;
-
-        if (copy_from_user(&buf, ubuf, count))
-                return -EFAULT;
-
-        buf[count] = 0;
-
-        ret = strict_strtoul(buf, 10, &val);
-        if (ret < 0)
+        ret = kstrtoul_from_user(ubuf, count, 10, &val);
+        if (ret)
                 return ret;
 
         local_irq_save(flags);