Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf changes from Ingo Molnar:
 "There are lots of improvements, the biggest changes are:

  Main kernel side changes:

   - Improve uprobes performance by adding 'pre-filtering' support, by
     Oleg Nesterov.

   - Make some POWER7 events available in sysfs, equivalent to what was
     done on x86, from Sukadev Bhattiprolu.

   - tracing updates by Steve Rostedt - mostly misc fixes and smaller
     improvements.

   - Use perf/event tracing to report PCI Express advanced errors, by
     Tony Luck.

   - Enable northbridge performance counters on AMD family 15h, by Jacob
     Shin.

   - This tracing commit:

        tracing: Remove the extra 4 bytes of padding in events

     changes the ABI.  All involved parties (PowerTop in particular)
     seem to agree that it's safe to do now with the introduction of
     libtraceevent, but the devil is in the details ...

  Main tooling side changes:

   - Add 'event group view', from Namyung Kim:

     To use it, 'perf record' should group events when recording.  And
     then perf report parses the saved group relation from file header
     and prints them together if --group option is provided.  You can
     use the 'perf evlist' command to see event group information:

        $ perf record -e '{ref-cycles,cycles}' noploop 1
        [ perf record: Woken up 2 times to write data ]
        [ perf record: Captured and wrote 0.385 MB perf.data (~16807 samples) ]

        $ perf evlist --group
        {ref-cycles,cycles}

     With this example, default perf report will show you each event
     separately.

     You can use --group option to enable event group view:

        $ perf report --group
        ...
        # group: {ref-cycles,cycles}
        # ========
        # Samples: 7K of event 'anon group { ref-cycles, cycles }'
        # Event count (approx.): 6876107743
        #
        #         Overhead  Command      Shared Object                      Symbol
        # ................  .......  .................  ..........................
            99.84%  99.76%  noploop  noploop            [.] main
             0.07%   0.00%  noploop  ld-2.15.so         [.] strcmp
             0.03%   0.00%  noploop  [kernel.kallsyms]  [k] timerqueue_del
             0.03%   0.03%  noploop  [kernel.kallsyms]  [k] sched_clock_cpu
             0.02%   0.00%  noploop  [kernel.kallsyms]  [k] account_user_time
             0.01%   0.00%  noploop  [kernel.kallsyms]  [k] __alloc_pages_nodemask
             0.00%   0.00%  noploop  [kernel.kallsyms]  [k] native_write_msr_safe
             0.00%   0.11%  noploop  [kernel.kallsyms]  [k] _raw_spin_lock
             0.00%   0.06%  noploop  [kernel.kallsyms]  [k] find_get_page
             0.00%   0.02%  noploop  [kernel.kallsyms]  [k] rcu_check_callbacks
             0.00%   0.02%  noploop  [kernel.kallsyms]  [k] __current_kernel_time

     As you can see the Overhead column now contains both of ref-cycles
     and cycles and header line shows group information also - 'anon
     group { ref-cycles, cycles }'.  The output is sorted by period of
     group leader first.

   - Initial GTK+ annotate browser, from Namhyung Kim.

   - Add option for runtime switching perf data file in perf report,
     just press 's' and a menu with the valid files found in the current
     directory will be presented, from Feng Tang.

   - Add support to display whole group data for raw columns, from Jiri
     Olsa.

   - Add per processor socket count aggregation in perf stat, from
     Stephane Eranian.

   - Add interval printing in 'perf stat', from Stephane Eranian.

   - 'perf test' improvements

   - Add support for wildcards in tracepoint system name, from Jiri
     Olsa.

   - Add anonymous huge page recognition, from Joshua Zhu.

   - perf build-id cache now can show DSOs present in a perf.data file
     that are not in the cache, to integrate with build-id servers being
     put in place by organizations such as Fedora.

   - perf top now shares more of the evsel config/creation routines with
     'record', paving the way for further integration like 'top'
     snapshots, etc.

   - perf top now supports DWARF callchains.

   - Fix mmap limitations on 32-bit, fix from David Miller.

   - 'perf bench numa mem' NUMA performance measurement suite

   - ... and lots of fixes, performance improvements, cleanups and other
     improvements I failed to list - see the shortlog and git log for
     details."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (270 commits)
  perf/x86/amd: Enable northbridge performance counters on AMD family 15h
  perf/hwbp: Fix cleanup in case of kzalloc failure
  perf tools: Fix build with bison 2.3 and older.
  perf tools: Limit unwind support to x86 archs
  perf annotate: Make it to be able to skip unannotatable symbols
  perf gtk/annotate: Fail early if it can't annotate
  perf gtk/annotate: Show source lines with gray color
  perf gtk/annotate: Support multiple event annotation
  perf ui/gtk: Implement basic GTK2 annotation browser
  perf annotate: Fix warning message on a missing vmlinux
  perf buildid-cache: Add --update option
  uprobes/perf: Avoid uprobe_apply() whenever possible
  uprobes/perf: Teach trace_uprobe/perf code to use UPROBE_HANDLER_REMOVE
  uprobes/perf: Teach trace_uprobe/perf code to pre-filter
  uprobes/perf: Teach trace_uprobe/perf code to track the active perf_event's
  uprobes: Introduce uprobe_apply()
  perf: Introduce hw_perf_event->tp_target and ->tp_list
  uprobes/perf: Always increment trace_uprobe->nhit
  uprobes/tracing: Kill uprobe_trace_consumer, embed uprobe_consumer into trace_uprobe
  uprobes/tracing: Introduce is_trace_uprobe_enabled()
  ...

20 files changed, 992 insertions, 512 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7b6646a8c067..5c75791d7269 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6171,11 +6171,14 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	if (task) {
 		event->attach_state = PERF_ATTACH_TASK;
+
+		if (attr->type == PERF_TYPE_TRACEPOINT)
+			event->hw.tp_target = task;
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		/*
 		 * hw_breakpoint is a bit difficult here..
 		 */
-		if (attr->type == PERF_TYPE_BREAKPOINT)
+		else if (attr->type == PERF_TYPE_BREAKPOINT)
 			event->hw.bp_target = task;
 #endif
 	}
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index fe8a916507ed..a64f8aeb5c1f 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -676,7 +676,7 @@ int __init init_hw_breakpoint(void)
  err_alloc:
 	for_each_possible_cpu(err_cpu) {
 		for (i = 0; i < TYPE_MAX; i++)
-			kfree(per_cpu(nr_task_bp_pinned[i], cpu));
+			kfree(per_cpu(nr_task_bp_pinned[i], err_cpu));
 		if (err_cpu == cpu)
 			break;
 	}
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index dea7acfbb071..a567c8c7ef31 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -27,6 +27,7 @@
 #include <linux/pagemap.h>	/* read_mapping_page */
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/export.h>
 #include <linux/rmap.h>		/* anon_vma_prepare */
 #include <linux/mmu_notifier.h>	/* set_pte_at_notify */
 #include <linux/swap.h>		/* try_to_free_swap */
@@ -41,58 +42,31 @@
 #define MAX_UPROBE_XOL_SLOTS		UINSNS_PER_PAGE
 
 static struct rb_root uprobes_tree = RB_ROOT;
-
-static DEFINE_SPINLOCK(uprobes_treelock);	/* serialize rbtree access */
-
-#define UPROBES_HASH_SZ	13
-
 /*
- * We need separate register/unregister and mmap/munmap lock hashes because
- * of mmap_sem nesting.
- *
- * uprobe_register() needs to install probes on (potentially) all processes
- * and thus needs to acquire multiple mmap_sems (consequtively, not
- * concurrently), whereas uprobe_mmap() is called while holding mmap_sem
- * for the particular process doing the mmap.
- *
- * uprobe_register()->register_for_each_vma() needs to drop/acquire mmap_sem
- * because of lock order against i_mmap_mutex. This means there's a hole in
- * the register vma iteration where a mmap() can happen.
- *
- * Thus uprobe_register() can race with uprobe_mmap() and we can try and
- * install a probe where one is already installed.
+ * allows us to skip the uprobe_mmap if there are no uprobe events active
+ * at this time.  Probably a fine grained per inode count is better?
  */
+#define no_uprobe_events()	RB_EMPTY_ROOT(&uprobes_tree)
 
-/* serialize (un)register */
-static struct mutex uprobes_mutex[UPROBES_HASH_SZ];
-
-#define uprobes_hash(v)		(&uprobes_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ])
+static DEFINE_SPINLOCK(uprobes_treelock);	/* serialize rbtree access */
 
+#define UPROBES_HASH_SZ	13
 /* serialize uprobe->pending_list */
 static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ];
 #define uprobes_mmap_hash(v)	(&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ])
 
 static struct percpu_rw_semaphore dup_mmap_sem;
 
-/*
- * uprobe_events allows us to skip the uprobe_mmap if there are no uprobe
- * events active at this time.  Probably a fine grained per inode count is
- * better?
- */
-static atomic_t uprobe_events = ATOMIC_INIT(0);
-
 /* Have a copy of original instruction */
 #define UPROBE_COPY_INSN	0
-/* Dont run handlers when first register/ last unregister in progress*/
-#define UPROBE_RUN_HANDLER	1
 /* Can skip singlestep */
-#define UPROBE_SKIP_SSTEP	2
+#define UPROBE_SKIP_SSTEP	1
 
 struct uprobe {
 	struct rb_node		rb_node;	/* node in the rb tree */
 	atomic_t		ref;
+	struct rw_semaphore	register_rwsem;
 	struct rw_semaphore	consumer_rwsem;
-	struct mutex		copy_mutex;	/* TODO: kill me and UPROBE_COPY_INSN */
 	struct list_head	pending_list;
 	struct uprobe_consumer	*consumers;
 	struct inode		*inode;		/* Also hold a ref to inode */
@@ -430,9 +404,6 @@ static struct uprobe *insert_uprobe(struct uprobe *uprobe)
 	u = __insert_uprobe(uprobe);
 	spin_unlock(&uprobes_treelock);
 
-	/* For now assume that the instruction need not be single-stepped */
-	__set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
-
 	return u;
 }
 
@@ -452,8 +423,10 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
 
 	uprobe->inode = igrab(inode);
 	uprobe->offset = offset;
+	init_rwsem(&uprobe->register_rwsem);
 	init_rwsem(&uprobe->consumer_rwsem);
-	mutex_init(&uprobe->copy_mutex);
+	/* For now assume that the instruction need not be single-stepped */
+	__set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
 
 	/* add to uprobes_tree, sorted on inode:offset */
 	cur_uprobe = insert_uprobe(uprobe);
@@ -463,38 +436,17 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
 		kfree(uprobe);
 		uprobe = cur_uprobe;
 		iput(inode);
-	} else {
-		atomic_inc(&uprobe_events);
 	}
 
 	return uprobe;
 }
 
-static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
-{
-	struct uprobe_consumer *uc;
-
-	if (!test_bit(UPROBE_RUN_HANDLER, &uprobe->flags))
-		return;
-
-	down_read(&uprobe->consumer_rwsem);
-	for (uc = uprobe->consumers; uc; uc = uc->next) {
-		if (!uc->filter || uc->filter(uc, current))
-			uc->handler(uc, regs);
-	}
-	up_read(&uprobe->consumer_rwsem);
-}
-
-/* Returns the previous consumer */
-static struct uprobe_consumer *
-consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc)
+static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc)
 {
 	down_write(&uprobe->consumer_rwsem);
 	uc->next = uprobe->consumers;
 	uprobe->consumers = uc;
 	up_write(&uprobe->consumer_rwsem);
-
-	return uc->next;
 }
 
 /*
@@ -588,7 +540,8 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 	if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
 		return ret;
 
-	mutex_lock(&uprobe->copy_mutex);
+	/* TODO: move this into _register, until then we abuse this sem. */
+	down_write(&uprobe->consumer_rwsem);
 	if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
 		goto out;
 
@@ -612,7 +565,30 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 	set_bit(UPROBE_COPY_INSN, &uprobe->flags);
 
  out:
-	mutex_unlock(&uprobe->copy_mutex);
+	up_write(&uprobe->consumer_rwsem);
+
+	return ret;
+}
+
+static inline bool consumer_filter(struct uprobe_consumer *uc,
+				   enum uprobe_filter_ctx ctx, struct mm_struct *mm)
+{
+	return !uc->filter || uc->filter(uc, ctx, mm);
+}
+
+static bool filter_chain(struct uprobe *uprobe,
+			 enum uprobe_filter_ctx ctx, struct mm_struct *mm)
+{
+	struct uprobe_consumer *uc;
+	bool ret = false;
+
+	down_read(&uprobe->consumer_rwsem);
+	for (uc = uprobe->consumers; uc; uc = uc->next) {
+		ret = consumer_filter(uc, ctx, mm);
+		if (ret)
+			break;
+	}
+	up_read(&uprobe->consumer_rwsem);
 
 	return ret;
 }
@@ -624,16 +600,6 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	bool first_uprobe;
 	int ret;
 
-	/*
-	 * If probe is being deleted, unregister thread could be done with
-	 * the vma-rmap-walk through. Adding a probe now can be fatal since
-	 * nobody will be able to cleanup. Also we could be from fork or
-	 * mremap path, where the probe might have already been inserted.
-	 * Hence behave as if probe already existed.
-	 */
-	if (!uprobe->consumers)
-		return 0;
-
 	ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr);
 	if (ret)
 		return ret;
@@ -658,14 +624,14 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 static int
 remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	/* can happen if uprobe_register() fails */
-	if (!test_bit(MMF_HAS_UPROBES, &mm->flags))
-		return 0;
-
 	set_bit(MMF_RECALC_UPROBES, &mm->flags);
 	return set_orig_insn(&uprobe->arch, mm, vaddr);
 }
 
+static inline bool uprobe_is_active(struct uprobe *uprobe)
+{
+	return !RB_EMPTY_NODE(&uprobe->rb_node);
+}
 /*
  * There could be threads that have already hit the breakpoint. They
  * will recheck the current insn and restart if find_uprobe() fails.
@@ -673,12 +639,15 @@ remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vad
  */
 static void delete_uprobe(struct uprobe *uprobe)
 {
+	if (WARN_ON(!uprobe_is_active(uprobe)))
+		return;
+
 	spin_lock(&uprobes_treelock);
 	rb_erase(&uprobe->rb_node, &uprobes_tree);
 	spin_unlock(&uprobes_treelock);
+	RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */
 	iput(uprobe->inode);
 	put_uprobe(uprobe);
-	atomic_dec(&uprobe_events);
 }
 
 struct map_info {
@@ -764,8 +733,10 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
 	return curr;
 }
 
-static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
+static int
+register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
 {
+	bool is_register = !!new;
 	struct map_info *info;
 	int err = 0;
 
@@ -794,10 +765,16 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
 		    vaddr_to_offset(vma, info->vaddr) != uprobe->offset)
 			goto unlock;
 
-		if (is_register)
-			err = install_breakpoint(uprobe, mm, vma, info->vaddr);
-		else
-			err |= remove_breakpoint(uprobe, mm, info->vaddr);
+		if (is_register) {
+			/* consult only the "caller", new consumer. */
+			if (consumer_filter(new,
+					UPROBE_FILTER_REGISTER, mm))
+				err = install_breakpoint(uprobe, mm, vma, info->vaddr);
+		} else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) {
+			if (!filter_chain(uprobe,
+					UPROBE_FILTER_UNREGISTER, mm))
+				err |= remove_breakpoint(uprobe, mm, info->vaddr);
+		}
 
  unlock:
 		up_write(&mm->mmap_sem);
@@ -810,17 +787,23 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
 	return err;
 }
 
-static int __uprobe_register(struct uprobe *uprobe)
+static int __uprobe_register(struct uprobe *uprobe, struct uprobe_consumer *uc)
 {
-	return register_for_each_vma(uprobe, true);
+	consumer_add(uprobe, uc);
+	return register_for_each_vma(uprobe, uc);
 }
 
-static void __uprobe_unregister(struct uprobe *uprobe)
+static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
 {
-	if (!register_for_each_vma(uprobe, false))
-		delete_uprobe(uprobe);
+	int err;
+
+	if (!consumer_del(uprobe, uc))	/* WARN? */
+		return;
 
+	err = register_for_each_vma(uprobe, NULL);
 	/* TODO : cant unregister? schedule a worker thread */
+	if (!uprobe->consumers && !err)
+		delete_uprobe(uprobe);
 }
 
 /*
@@ -845,31 +828,59 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 	struct uprobe *uprobe;
 	int ret;
 
-	if (!inode || !uc || uc->next)
-		return -EINVAL;
-
+	/* Racy, just to catch the obvious mistakes */
 	if (offset > i_size_read(inode))
 		return -EINVAL;
 
-	ret = 0;
-	mutex_lock(uprobes_hash(inode));
+ retry:
 	uprobe = alloc_uprobe(inode, offset);
-
-	if (!uprobe) {
-		ret = -ENOMEM;
-	} else if (!consumer_add(uprobe, uc)) {
-		ret = __uprobe_register(uprobe);
-		if (ret) {
-			uprobe->consumers = NULL;
-			__uprobe_unregister(uprobe);
-		} else {
-			set_bit(UPROBE_RUN_HANDLER, &uprobe->flags);
-		}
+	if (!uprobe)
+		return -ENOMEM;
+	/*
+	 * We can race with uprobe_unregister()->delete_uprobe().
+	 * Check uprobe_is_active() and retry if it is false.
+	 */
+	down_write(&uprobe->register_rwsem);
+	ret = -EAGAIN;
+	if (likely(uprobe_is_active(uprobe))) {
+		ret = __uprobe_register(uprobe, uc);
+		if (ret)
+			__uprobe_unregister(uprobe, uc);
 	}
+	up_write(&uprobe->register_rwsem);
+	put_uprobe(uprobe);
 
-	mutex_unlock(uprobes_hash(inode));
-	if (uprobe)
-		put_uprobe(uprobe);
+	if (unlikely(ret == -EAGAIN))
+		goto retry;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(uprobe_register);
+
+/*
+ * uprobe_apply - unregister a already registered probe.
+ * @inode: the file in which the probe has to be removed.
+ * @offset: offset from the start of the file.
+ * @uc: consumer which wants to add more or remove some breakpoints
+ * @add: add or remove the breakpoints
+ */
+int uprobe_apply(struct inode *inode, loff_t offset,
+			struct uprobe_consumer *uc, bool add)
+{
+	struct uprobe *uprobe;
+	struct uprobe_consumer *con;
+	int ret = -ENOENT;
+
+	uprobe = find_uprobe(inode, offset);
+	if (!uprobe)
+		return ret;
+
+	down_write(&uprobe->register_rwsem);
+	for (con = uprobe->consumers; con && con != uc ; con = con->next)
+		;
+	if (con)
+		ret = register_for_each_vma(uprobe, add ? uc : NULL);
+	up_write(&uprobe->register_rwsem);
+	put_uprobe(uprobe);
 
 	return ret;
 }
@@ -884,25 +895,42 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume
 {
 	struct uprobe *uprobe;
 
-	if (!inode || !uc)
-		return;
-
 	uprobe = find_uprobe(inode, offset);
 	if (!uprobe)
 		return;
 
-	mutex_lock(uprobes_hash(inode));
+	down_write(&uprobe->register_rwsem);
+	__uprobe_unregister(uprobe, uc);
+	up_write(&uprobe->register_rwsem);
+	put_uprobe(uprobe);
+}
+EXPORT_SYMBOL_GPL(uprobe_unregister);
 
-	if (consumer_del(uprobe, uc)) {
-		if (!uprobe->consumers) {
-			__uprobe_unregister(uprobe);
-			clear_bit(UPROBE_RUN_HANDLER, &uprobe->flags);
-		}
+static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+	int err = 0;
+
+	down_read(&mm->mmap_sem);
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long vaddr;
+		loff_t offset;
+
+		if (!valid_vma(vma, false) ||
+		    vma->vm_file->f_mapping->host != uprobe->inode)
+			continue;
+
+		offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
+		if (uprobe->offset <  offset ||
+		    uprobe->offset >= offset + vma->vm_end - vma->vm_start)
+			continue;
+
+		vaddr = offset_to_vaddr(vma, uprobe->offset);
+		err |= remove_breakpoint(uprobe, mm, vaddr);
 	}
+	up_read(&mm->mmap_sem);
 
-	mutex_unlock(uprobes_hash(inode));
-	if (uprobe)
-		put_uprobe(uprobe);
+	return err;
 }
 
 static struct rb_node *
@@ -979,7 +1007,7 @@ int uprobe_mmap(struct vm_area_struct *vma)
 	struct uprobe *uprobe, *u;
 	struct inode *inode;
 
-	if (!atomic_read(&uprobe_events) || !valid_vma(vma, true))
+	if (no_uprobe_events() || !valid_vma(vma, true))
 		return 0;
 
 	inode = vma->vm_file->f_mapping->host;
@@ -988,9 +1016,14 @@ int uprobe_mmap(struct vm_area_struct *vma)
 
 	mutex_lock(uprobes_mmap_hash(inode));
 	build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list);
-
+	/*
+	 * We can race with uprobe_unregister(), this uprobe can be already
+	 * removed. But in this case filter_chain() must return false, all
+	 * consumers have gone away.
+	 */
 	list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
-		if (!fatal_signal_pending(current)) {
+		if (!fatal_signal_pending(current) &&
+		    filter_chain(uprobe, UPROBE_FILTER_MMAP, vma->vm_mm)) {
 			unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
 			install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
 		}
@@ -1025,7 +1058,7 @@ vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long e
  */
 void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
-	if (!atomic_read(&uprobe_events) || !valid_vma(vma, false))
+	if (no_uprobe_events() || !valid_vma(vma, false))
 		return;
 
 	if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */
@@ -1042,22 +1075,14 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon
 /* Slot allocation for XOL */
 static int xol_add_vma(struct xol_area *area)
 {
-	struct mm_struct *mm;
-	int ret;
-
-	area->page = alloc_page(GFP_HIGHUSER);
-	if (!area->page)
-		return -ENOMEM;
-
-	ret = -EALREADY;
-	mm = current->mm;
+	struct mm_struct *mm = current->mm;
+	int ret = -EALREADY;
 
 	down_write(&mm->mmap_sem);
 	if (mm->uprobes_state.xol_area)
 		goto fail;
 
 	ret = -ENOMEM;
-
 	/* Try to map as high as possible, this is only a hint. */
 	area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, PAGE_SIZE, 0, 0);
 	if (area->vaddr & ~PAGE_MASK) {
@@ -1073,54 +1098,53 @@ static int xol_add_vma(struct xol_area *area)
 	smp_wmb();	/* pairs with get_xol_area() */
 	mm->uprobes_state.xol_area = area;
 	ret = 0;
-
-fail:
+ fail:
 	up_write(&mm->mmap_sem);
-	if (ret)
-		__free_page(area->page);
 
 	return ret;
 }
 
-static struct xol_area *get_xol_area(struct mm_struct *mm)
-{
-	struct xol_area *area;
-
-	area = mm->uprobes_state.xol_area;
-	smp_read_barrier_depends();	/* pairs with wmb in xol_add_vma() */
-
-	return area;
-}
-
 /*
- * xol_alloc_area - Allocate process's xol_area.
- * This area will be used for storing instructions for execution out of
- * line.
+ * get_xol_area - Allocate process's xol_area if necessary.
+ * This area will be used for storing instructions for execution out of line.
  *
  * Returns the allocated area or NULL.
  */
-static struct xol_area *xol_alloc_area(void)
+static struct xol_area *get_xol_area(void)
 {
+	struct mm_struct *mm = current->mm;
 	struct xol_area *area;
 
+	area = mm->uprobes_state.xol_area;
+	if (area)
+		goto ret;
+
 	area = kzalloc(sizeof(*area), GFP_KERNEL);
 	if (unlikely(!area))
-		return NULL;
+		goto out;
 
 	area->bitmap = kzalloc(BITS_TO_LONGS(UINSNS_PER_PAGE) * sizeof(long), GFP_KERNEL);
-
 	if (!area->bitmap)
-		goto fail;
+		goto free_area;
+
+	area->page = alloc_page(GFP_HIGHUSER);
+	if (!area->page)
+		goto free_bitmap;
 
 	init_waitqueue_head(&area->wq);
 	if (!xol_add_vma(area))
 		return area;
 
-fail:
+	__free_page(area->page);
+ free_bitmap:
 	kfree(area->bitmap);
+ free_area:
 	kfree(area);
-
-	return get_xol_area(current->mm);
+ out:
+	area = mm->uprobes_state.xol_area;
+ ret:
+	smp_read_barrier_depends();     /* pairs with wmb in xol_add_vma() */
+	return area;
 }
 
 /*
@@ -1186,33 +1210,26 @@ static unsigned long xol_take_insn_slot(struct xol_area *area)
 }
 
 /*
- * xol_get_insn_slot - If was not allocated a slot, then
- * allocate a slot.
+ * xol_get_insn_slot - allocate a slot for xol.
  * Returns the allocated slot address or 0.
  */
-static unsigned long xol_get_insn_slot(struct uprobe *uprobe, unsigned long slot_addr)
+static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
 {
 	struct xol_area *area;
 	unsigned long offset;
+	unsigned long xol_vaddr;
 	void *vaddr;
 
-	area = get_xol_area(current->mm);
-	if (!area) {
-		area = xol_alloc_area();
-		if (!area)
-			return 0;
-	}
-	current->utask->xol_vaddr = xol_take_insn_slot(area);
+	area = get_xol_area();
+	if (!area)
+		return 0;
 
-	/*
-	 * Initialize the slot if xol_vaddr points to valid
-	 * instruction slot.
-	 */
-	if (unlikely(!current->utask->xol_vaddr))
+	xol_vaddr = xol_take_insn_slot(area);
+	if (unlikely(!xol_vaddr))
 		return 0;
 
-	current->utask->vaddr = slot_addr;
-	offset = current->utask->xol_vaddr & ~PAGE_MASK;
+	/* Initialize the slot */
+	offset = xol_vaddr & ~PAGE_MASK;
 	vaddr = kmap_atomic(area->page);
 	memcpy(vaddr + offset, uprobe->arch.insn, MAX_UINSN_BYTES);
 	kunmap_atomic(vaddr);
@@ -1222,7 +1239,7 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe, unsigned long slot
 	 */
 	flush_dcache_page(area->page);
 
-	return current->utask->xol_vaddr;
+	return xol_vaddr;
 }
 
 /*
@@ -1240,8 +1257,7 @@ static void xol_free_insn_slot(struct task_struct *tsk)
 		return;
 
 	slot_addr = tsk->utask->xol_vaddr;
-
-	if (unlikely(!slot_addr || IS_ERR_VALUE(slot_addr)))
+	if (unlikely(!slot_addr))
 		return;
 
 	area = tsk->mm->uprobes_state.xol_area;
@@ -1303,33 +1319,48 @@ void uprobe_copy_process(struct task_struct *t)
 }
 
 /*
- * Allocate a uprobe_task object for the task.
- * Called when the thread hits a breakpoint for the first time.
+ * Allocate a uprobe_task object for the task if if necessary.
+ * Called when the thread hits a breakpoint.
  *
  * Returns:
  * - pointer to new uprobe_task on success
  * - NULL otherwise
  */
-static struct uprobe_task *add_utask(void)
+static struct uprobe_task *get_utask(void)
 {
-	struct uprobe_task *utask;
-
-	utask = kzalloc(sizeof *utask, GFP_KERNEL);
-	if (unlikely(!utask))
-		return NULL;
-
-	current->utask = utask;
-	return utask;
+	if (!current->utask)
+		current->utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL);
+	return current->utask;
 }
 
 /* Prepare to single-step probed instruction out of line. */
 static int
-pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long vaddr)
+pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr)
 {
-	if (xol_get_insn_slot(uprobe, vaddr) && !arch_uprobe_pre_xol(&uprobe->arch, regs))
-		return 0;
+	struct uprobe_task *utask;
+	unsigned long xol_vaddr;
+	int err;
+
+	utask = get_utask();
+	if (!utask)
+		return -ENOMEM;
+
+	xol_vaddr = xol_get_insn_slot(uprobe);
+	if (!xol_vaddr)
+		return -ENOMEM;
+
+	utask->xol_vaddr = xol_vaddr;
+	utask->vaddr = bp_vaddr;
+
+	err = arch_uprobe_pre_xol(&uprobe->arch, regs);
+	if (unlikely(err)) {
+		xol_free_insn_slot(current);
+		return err;
+	}
 
-	return -EFAULT;
+	utask->active_uprobe = uprobe;
+	utask->state = UTASK_SSTEP;
+	return 0;
 }
 
 /*
@@ -1391,6 +1422,7 @@ static void mmf_recalc_uprobes(struct mm_struct *mm)
 		 * This is not strictly accurate, we can race with
 		 * uprobe_unregister() and see the already removed
 		 * uprobe if delete_uprobe() was not yet called.
+		 * Or this uprobe can be filtered out.
 		 */
 		if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end))
 			return;
@@ -1452,13 +1484,33 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
 	return uprobe;
 }
 
+static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
+{
+	struct uprobe_consumer *uc;
+	int remove = UPROBE_HANDLER_REMOVE;
+
+	down_read(&uprobe->register_rwsem);
+	for (uc = uprobe->consumers; uc; uc = uc->next) {
+		int rc = uc->handler(uc, regs);
+
+		WARN(rc & ~UPROBE_HANDLER_MASK,
+			"bad rc=0x%x from %pf()\n", rc, uc->handler);
+		remove &= rc;
+	}
+
+	if (remove && uprobe->consumers) {
+		WARN_ON(!uprobe_is_active(uprobe));
+		unapply_uprobe(uprobe, current->mm);
+	}
+	up_read(&uprobe->register_rwsem);
+}
+
 /*
  * Run handler and ask thread to singlestep.
  * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
  */
 static void handle_swbp(struct pt_regs *regs)
 {
-	struct uprobe_task *utask;
 	struct uprobe *uprobe;
 	unsigned long bp_vaddr;
 	int uninitialized_var(is_swbp);
@@ -1483,6 +1535,10 @@ static void handle_swbp(struct pt_regs *regs)
 		}
 		return;
 	}
+
+	/* change it in advance for ->handler() and restart */
+	instruction_pointer_set(regs, bp_vaddr);
+
 	/*
 	 * TODO: move copy_insn/etc into _register and remove this hack.
 	 * After we hit the bp, _unregister + _register can install the
@@ -1490,32 +1546,16 @@ static void handle_swbp(struct pt_regs *regs)
 	 */
 	smp_rmb(); /* pairs with wmb() in install_breakpoint() */
 	if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
-		goto restart;
-
-	utask = current->utask;
-	if (!utask) {
-		utask = add_utask();
-		/* Cannot allocate; re-execute the instruction. */
-		if (!utask)
-			goto restart;
-	}
+		goto out;
 
 	handler_chain(uprobe, regs);
 	if (can_skip_sstep(uprobe, regs))
 		goto out;
 
-	if (!pre_ssout(uprobe, regs, bp_vaddr)) {
-		utask->active_uprobe = uprobe;
-		utask->state = UTASK_SSTEP;
+	if (!pre_ssout(uprobe, regs, bp_vaddr))
 		return;
-	}
 
-restart:
-	/*
-	 * cannot singlestep; cannot skip instruction;
-	 * re-execute the instruction.
-	 */
-	instruction_pointer_set(regs, bp_vaddr);
+	/* can_skip_sstep() succeeded, or restart if can't singlestep */
 out:
 	put_uprobe(uprobe);
 }
@@ -1609,10 +1649,8 @@ static int __init init_uprobes(void)
 {
 	int i;
 
-	for (i = 0; i < UPROBES_HASH_SZ; i++) {
-		mutex_init(&uprobes_mutex[i]);
+	for (i = 0; i < UPROBES_HASH_SZ; i++)
 		mutex_init(&uprobes_mmap_mutex[i]);
-	}
 
 	if (percpu_init_rwsem(&dup_mmap_sem))
 		return -ENOMEM;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 098f396aa409..f423c3ef4a82 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -919,7 +919,7 @@ static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
 }
 #endif /* CONFIG_OPTPROBES */
 
-#ifdef KPROBES_CAN_USE_FTRACE
+#ifdef CONFIG_KPROBES_ON_FTRACE
 static struct ftrace_ops kprobe_ftrace_ops __read_mostly = {
 	.func = kprobe_ftrace_handler,
 	.flags = FTRACE_OPS_FL_SAVE_REGS,
@@ -964,7 +964,7 @@ static void __kprobes disarm_kprobe_ftrace(struct kprobe *p)
 			   (unsigned long)p->addr, 1, 0);
 	WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret);
 }
-#else	/* !KPROBES_CAN_USE_FTRACE */
+#else	/* !CONFIG_KPROBES_ON_FTRACE */
 #define prepare_kprobe(p)	arch_prepare_kprobe(p)
 #define arm_kprobe_ftrace(p)	do {} while (0)
 #define disarm_kprobe_ftrace(p)	do {} while (0)
@@ -1414,12 +1414,12 @@ static __kprobes int check_kprobe_address_safe(struct kprobe *p,
 	 */
 	ftrace_addr = ftrace_location((unsigned long)p->addr);
 	if (ftrace_addr) {
-#ifdef KPROBES_CAN_USE_FTRACE
+#ifdef CONFIG_KPROBES_ON_FTRACE
 		/* Given address is not on the instruction boundary */
 		if ((unsigned long)p->addr != ftrace_addr)
 			return -EILSEQ;
 		p->flags |= KPROBE_FLAG_FTRACE;
-#else	/* !KPROBES_CAN_USE_FTRACE */
+#else	/* !CONFIG_KPROBES_ON_FTRACE */
 		return -EINVAL;
 #endif
 	}
diff --git a/kernel/profile.c b/kernel/profile.c
index 1f391819c42f..dc3384ee874e 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -37,9 +37,6 @@ struct profile_hit {
 #define NR_PROFILE_HIT		(PAGE_SIZE/sizeof(struct profile_hit))
 #define NR_PROFILE_GRP		(NR_PROFILE_HIT/PROFILE_GRPSZ)
 
-/* Oprofile timer tick hook */
-static int (*timer_hook)(struct pt_regs *) __read_mostly;
-
 static atomic_t *prof_buffer;
 static unsigned long prof_len, prof_shift;
 
@@ -208,25 +205,6 @@ int profile_event_unregister(enum profile_type type, struct notifier_block *n)
 }
 EXPORT_SYMBOL_GPL(profile_event_unregister);
 
-int register_timer_hook(int (*hook)(struct pt_regs *))
-{
-	if (timer_hook)
-		return -EBUSY;
-	timer_hook = hook;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(register_timer_hook);
-
-void unregister_timer_hook(int (*hook)(struct pt_regs *))
-{
-	WARN_ON(hook != timer_hook);
-	timer_hook = NULL;
-	/* make sure all CPUs see the NULL hook */
-	synchronize_sched();  /* Allow ongoing interrupts to complete. */
-}
-EXPORT_SYMBOL_GPL(unregister_timer_hook);
-
-
 #ifdef CONFIG_SMP
 /*
  * Each cpu has a pair of open-addressed hashtables for pending
@@ -436,8 +414,6 @@ void profile_tick(int type)
 {
 	struct pt_regs *regs = get_irq_regs();
 
-	if (type == CPU_PROFILING && timer_hook)
-		timer_hook(regs);
 	if (!user_mode(regs) && prof_cpu_mask != NULL &&
 	    cpumask_test_cpu(smp_processor_id(), prof_cpu_mask))
 		profile_hit(type, (void *)profile_pc(regs));
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 6cbeaae4406d..acbd28424d81 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -712,6 +712,12 @@ static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
 					     kiov->iov_len, kiov->iov_base);
 }
 
+/*
+ * This is declared in linux/regset.h and defined in machine-dependent
+ * code.  We put the export here, near the primary machine-neutral use,
+ * to ensure no machine forgets it.
+ */
+EXPORT_SYMBOL_GPL(task_user_regset_view);
 #endif
 
 int ptrace_request(struct task_struct *child, long request,
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 5d89335a485f..36567564e221 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -39,6 +39,9 @@ config HAVE_DYNAMIC_FTRACE
 	help
 	  See Documentation/trace/ftrace-design.txt
 
+config HAVE_DYNAMIC_FTRACE_WITH_REGS
+	bool
+
 config HAVE_FTRACE_MCOUNT_RECORD
 	bool
 	help
@@ -250,6 +253,16 @@ config FTRACE_SYSCALLS
 	help
 	  Basic tracer to catch the syscall entry and exit events.
 
+config TRACER_SNAPSHOT
+	bool "Create a snapshot trace buffer"
+	select TRACER_MAX_TRACE
+	help
+	  Allow tracing users to take snapshot of the current buffer using the
+	  ftrace interface, e.g.:
+
+	      echo 1 > /sys/kernel/debug/tracing/snapshot
+	      cat snapshot
+
 config TRACE_BRANCH_PROFILING
 	bool
 	select GENERIC_TRACER
@@ -434,6 +447,11 @@ config DYNAMIC_FTRACE
 	  were made. If so, it runs stop_machine (stops all CPUS)
 	  and modifies the code to jump over the call to ftrace.
 
+config DYNAMIC_FTRACE_WITH_REGS
+	def_bool y
+	depends on DYNAMIC_FTRACE
+	depends on HAVE_DYNAMIC_FTRACE_WITH_REGS
+
 config FUNCTION_PROFILER
 	bool "Kernel function profiler"
 	depends on FUNCTION_TRACER
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c0bd0308741c..71259e2b6b61 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -147,7 +147,7 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
 		return;
 
 	local_irq_save(flags);
-	buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
+	buf = this_cpu_ptr(bt->msg_data);
 	va_start(args, fmt);
 	n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
 	va_end(args);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 41473b4ad7a4..ce8c3d68292f 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -111,6 +111,26 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
 #define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops)
 #endif
 
+/*
+ * Traverse the ftrace_global_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_global_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
+#define do_for_each_ftrace_op(op, list)			\
+	op = rcu_dereference_raw(list);			\
+	do
+
+/*
+ * Optimized for just a single item in the list (as that is the normal case).
+ */
+#define while_for_each_ftrace_op(op)				\
+	while (likely(op = rcu_dereference_raw((op)->next)) &&	\
+	       unlikely((op) != &ftrace_list_end))
+
 /**
  * ftrace_nr_registered_ops - return number of ops registered
  *
@@ -132,29 +152,21 @@ int ftrace_nr_registered_ops(void)
 	return cnt;
 }
 
-/*
- * Traverse the ftrace_global_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_global_list.
- *
- * Silly Alpha and silly pointer-speculation compiler optimizations!
- */
 static void
 ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
 			struct ftrace_ops *op, struct pt_regs *regs)
 {
-	if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
+	int bit;
+
+	bit = trace_test_and_set_recursion(TRACE_GLOBAL_START, TRACE_GLOBAL_MAX);
+	if (bit < 0)
 		return;
 
-	trace_recursion_set(TRACE_GLOBAL_BIT);
-	op = rcu_dereference_raw(ftrace_global_list); /*see above*/
-	while (op != &ftrace_list_end) {
+	do_for_each_ftrace_op(op, ftrace_global_list) {
 		op->func(ip, parent_ip, op, regs);
-		op = rcu_dereference_raw(op->next); /*see above*/
-	};
-	trace_recursion_clear(TRACE_GLOBAL_BIT);
+	} while_for_each_ftrace_op(op);
+
+	trace_clear_recursion(bit);
 }
 
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
@@ -221,10 +233,24 @@ static void update_global_ops(void)
 	 * registered callers.
 	 */
 	if (ftrace_global_list == &ftrace_list_end ||
-	    ftrace_global_list->next == &ftrace_list_end)
+	    ftrace_global_list->next == &ftrace_list_end) {
 		func = ftrace_global_list->func;
-	else
+		/*
+		 * As we are calling the function directly.
+		 * If it does not have recursion protection,
+		 * the function_trace_op needs to be updated
+		 * accordingly.
+		 */
+		if (ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE)
+			global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
+		else
+			global_ops.flags &= ~FTRACE_OPS_FL_RECURSION_SAFE;
+	} else {
 		func = ftrace_global_list_func;
+		/* The list has its own recursion protection. */
+		global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
+	}
+
 
 	/* If we filter on pids, update to use the pid function */
 	if (!list_empty(&ftrace_pids)) {
@@ -337,7 +363,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK)
 		return -EINVAL;
 
-#ifndef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 	/*
 	 * If the ftrace_ops specifies SAVE_REGS, then it only can be used
 	 * if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set.
@@ -4090,14 +4116,11 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 	 */
 	preempt_disable_notrace();
 	trace_recursion_set(TRACE_CONTROL_BIT);
-	op = rcu_dereference_raw(ftrace_control_list);
-	while (op != &ftrace_list_end) {
+	do_for_each_ftrace_op(op, ftrace_control_list) {
 		if (!ftrace_function_local_disabled(op) &&
 		    ftrace_ops_test(op, ip))
 			op->func(ip, parent_ip, op, regs);
-
-		op = rcu_dereference_raw(op->next);
-	};
+	} while_for_each_ftrace_op(op);
 	trace_recursion_clear(TRACE_CONTROL_BIT);
 	preempt_enable_notrace();
 }
@@ -4112,27 +4135,26 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *ignored, struct pt_regs *regs)
 {
 	struct ftrace_ops *op;
+	int bit;
 
 	if (function_trace_stop)
 		return;
 
-	if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT)))
+	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
+	if (bit < 0)
 		return;
 
-	trace_recursion_set(TRACE_INTERNAL_BIT);
 	/*
 	 * Some of the ops may be dynamically allocated,
 	 * they must be freed after a synchronize_sched().
 	 */
 	preempt_disable_notrace();
-	op = rcu_dereference_raw(ftrace_ops_list);
-	while (op != &ftrace_list_end) {
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
 		if (ftrace_ops_test(op, ip))
 			op->func(ip, parent_ip, op, regs);
-		op = rcu_dereference_raw(op->next);
-	};
+	} while_for_each_ftrace_op(op);
 	preempt_enable_notrace();
-	trace_recursion_clear(TRACE_INTERNAL_BIT);
+	trace_clear_recursion(bit);
 }
 
 /*
@@ -4143,8 +4165,8 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
  * Archs are to support both the regs and ftrace_ops at the same time.
  * If they support ftrace_ops, it is assumed they support regs.
  * If call backs want to use regs, they must either check for regs
- * being NULL, or ARCH_SUPPORTS_FTRACE_SAVE_REGS.
- * Note, ARCH_SUPPORT_SAVE_REGS expects a full regs to be saved.
+ * being NULL, or CONFIG_DYNAMIC_FTRACE_WITH_REGS.
+ * Note, CONFIG_DYNAMIC_FTRACE_WITH_REGS expects a full regs to be saved.
  * An architecture can pass partial regs with ftrace_ops and still
  * set the ARCH_SUPPORT_FTARCE_OPS.
  */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index ce8514feedcd..7244acde77b0 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3,8 +3,10 @@
  *
  * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
  */
+#include <linux/ftrace_event.h>
 #include <linux/ring_buffer.h>
 #include <linux/trace_clock.h>
+#include <linux/trace_seq.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
@@ -21,7 +23,6 @@
 #include <linux/fs.h>
 
 #include <asm/local.h>
-#include "trace.h"
 
 static void update_pages_handler(struct work_struct *work);
 
@@ -2432,41 +2433,76 @@ rb_reserve_next_event(struct ring_buffer *buffer,
 
 #ifdef CONFIG_TRACING
 
-#define TRACE_RECURSIVE_DEPTH 16
+/*
+ * The lock and unlock are done within a preempt disable section.
+ * The current_context per_cpu variable can only be modified
+ * by the current task between lock and unlock. But it can
+ * be modified more than once via an interrupt. To pass this
+ * information from the lock to the unlock without having to
+ * access the 'in_interrupt()' functions again (which do show
+ * a bit of overhead in something as critical as function tracing,
+ * we use a bitmask trick.
+ *
+ *  bit 0 =  NMI context
+ *  bit 1 =  IRQ context
+ *  bit 2 =  SoftIRQ context
+ *  bit 3 =  normal context.
+ *
+ * This works because this is the order of contexts that can
+ * preempt other contexts. A SoftIRQ never preempts an IRQ
+ * context.
+ *
+ * When the context is determined, the corresponding bit is
+ * checked and set (if it was set, then a recursion of that context
+ * happened).
+ *
+ * On unlock, we need to clear this bit. To do so, just subtract
+ * 1 from the current_context and AND it to itself.
+ *
+ * (binary)
+ *  101 - 1 = 100
+ *  101 & 100 = 100 (clearing bit zero)
+ *
+ *  1010 - 1 = 1001
+ *  1010 & 1001 = 1000 (clearing bit 1)
+ *
+ * The least significant bit can be cleared this way, and it
+ * just so happens that it is the same bit corresponding to
+ * the current context.
+ */
+static DEFINE_PER_CPU(unsigned int, current_context);
 
-/* Keep this code out of the fast path cache */
-static noinline void trace_recursive_fail(void)
+static __always_inline int trace_recursive_lock(void)
 {
-	/* Disable all tracing before we do anything else */
-	tracing_off_permanent();
-
-	printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
-		    "HC[%lu]:SC[%lu]:NMI[%lu]\n",
-		    trace_recursion_buffer(),
-		    hardirq_count() >> HARDIRQ_SHIFT,
-		    softirq_count() >> SOFTIRQ_SHIFT,
-		    in_nmi());
-
-	WARN_ON_ONCE(1);
-}
+	unsigned int val = this_cpu_read(current_context);
+	int bit;
 
-static inline int trace_recursive_lock(void)
-{
-	trace_recursion_inc();
+	if (in_interrupt()) {
+		if (in_nmi())
+			bit = 0;
+		else if (in_irq())
+			bit = 1;
+		else
+			bit = 2;
+	} else
+		bit = 3;
 
-	if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH))
-		return 0;
+	if (unlikely(val & (1 << bit)))
+		return 1;
 
-	trace_recursive_fail();
+	val |= (1 << bit);
+	this_cpu_write(current_context, val);
 
-	return -1;
+	return 0;
 }
 
-static inline void trace_recursive_unlock(void)
+static __always_inline void trace_recursive_unlock(void)
 {
-	WARN_ON_ONCE(!trace_recursion_buffer());
+	unsigned int val = this_cpu_read(current_context);
 
-	trace_recursion_dec();
+	val--;
+	val &= this_cpu_read(current_context);
+	this_cpu_write(current_context, val);
 }
 
 #else
@@ -3067,6 +3103,24 @@ ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu)
 EXPORT_SYMBOL_GPL(ring_buffer_dropped_events_cpu);
 
 /**
+ * ring_buffer_read_events_cpu - get the number of events successfully read
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of events read
+ */
+unsigned long
+ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	return cpu_buffer->read;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_events_cpu);
+
+/**
  * ring_buffer_entries - get the number of entries in a buffer
  * @buffer: The ring buffer
  *
@@ -3425,7 +3479,7 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 	/* check for end of page padding */
 	if ((iter->head >= rb_page_size(iter->head_page)) &&
 	    (iter->head_page != cpu_buffer->commit_page))
-		rb_advance_iter(iter);
+		rb_inc_iter(iter);
 }
 
 static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3c13e46d7d24..5d520b7bb4c5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -249,7 +249,7 @@ static unsigned long		trace_buf_size = TRACE_BUF_SIZE_DEFAULT;
 static struct tracer		*trace_types __read_mostly;
 
 /* current_trace points to the tracer that is currently active */
-static struct tracer		*current_trace __read_mostly;
+static struct tracer		*current_trace __read_mostly = &nop_trace;
 
 /*
  * trace_types_lock is used to protect the trace_types list.
@@ -709,10 +709,13 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
-	if (!current_trace->use_max_tr) {
-		WARN_ON_ONCE(1);
+
+	if (!current_trace->allocated_snapshot) {
+		/* Only the nop tracer should hit this when disabling */
+		WARN_ON_ONCE(current_trace != &nop_trace);
 		return;
 	}
+
 	arch_spin_lock(&ftrace_max_lock);
 
 	tr->buffer = max_tr.buffer;
@@ -739,10 +742,8 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
-	if (!current_trace->use_max_tr) {
-		WARN_ON_ONCE(1);
+	if (WARN_ON_ONCE(!current_trace->allocated_snapshot))
 		return;
-	}
 
 	arch_spin_lock(&ftrace_max_lock);
 
@@ -862,10 +863,13 @@ int register_tracer(struct tracer *type)
 
 		current_trace = type;
 
-		/* If we expanded the buffers, make sure the max is expanded too */
-		if (ring_buffer_expanded && type->use_max_tr)
-			ring_buffer_resize(max_tr.buffer, trace_buf_size,
-						RING_BUFFER_ALL_CPUS);
+		if (type->use_max_tr) {
+			/* If we expanded the buffers, make sure the max is expanded too */
+			if (ring_buffer_expanded)
+				ring_buffer_resize(max_tr.buffer, trace_buf_size,
+						   RING_BUFFER_ALL_CPUS);
+			type->allocated_snapshot = true;
+		}
 
 		/* the test is responsible for initializing and enabling */
 		pr_info("Testing tracer %s: ", type->name);
@@ -881,10 +885,14 @@ int register_tracer(struct tracer *type)
 		/* Only reset on passing, to avoid touching corrupted buffers */
 		tracing_reset_online_cpus(tr);
 
-		/* Shrink the max buffer again */
-		if (ring_buffer_expanded && type->use_max_tr)
-			ring_buffer_resize(max_tr.buffer, 1,
-						RING_BUFFER_ALL_CPUS);
+		if (type->use_max_tr) {
+			type->allocated_snapshot = false;
+
+			/* Shrink the max buffer again */
+			if (ring_buffer_expanded)
+				ring_buffer_resize(max_tr.buffer, 1,
+						   RING_BUFFER_ALL_CPUS);
+		}
 
 		printk(KERN_CONT "PASSED\n");
 	}
@@ -922,6 +930,9 @@ void tracing_reset(struct trace_array *tr, int cpu)
 {
 	struct ring_buffer *buffer = tr->buffer;
 
+	if (!buffer)
+		return;
+
 	ring_buffer_record_disable(buffer);
 
 	/* Make sure all commits have finished */
@@ -936,6 +947,9 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 	struct ring_buffer *buffer = tr->buffer;
 	int cpu;
 
+	if (!buffer)
+		return;
+
 	ring_buffer_record_disable(buffer);
 
 	/* Make sure all commits have finished */
@@ -1167,7 +1181,6 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
-	entry->padding			= 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -1335,7 +1348,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	 */
 	preempt_disable_notrace();
 
-	use_stack = ++__get_cpu_var(ftrace_stack_reserve);
+	use_stack = __this_cpu_inc_return(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
@@ -1389,7 +1402,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
  out:
 	/* Again, don't let gcc optimize things here */
 	barrier();
-	__get_cpu_var(ftrace_stack_reserve)--;
+	__this_cpu_dec(ftrace_stack_reserve);
 	preempt_enable_notrace();
 
 }
@@ -1517,7 +1530,6 @@ static struct trace_buffer_struct *trace_percpu_nmi_buffer;
 static char *get_trace_buf(void)
 {
 	struct trace_buffer_struct *percpu_buffer;
-	struct trace_buffer_struct *buffer;
 
 	/*
 	 * If we have allocated per cpu buffers, then we do not
@@ -1535,9 +1547,7 @@ static char *get_trace_buf(void)
 	if (!percpu_buffer)
 		return NULL;
 
-	buffer = per_cpu_ptr(percpu_buffer, smp_processor_id());
-
-	return buffer->buffer;
+	return this_cpu_ptr(&percpu_buffer->buffer[0]);
 }
 
 static int alloc_percpu_trace_buffer(void)
@@ -1942,21 +1952,27 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
 	struct trace_iterator *iter = m->private;
-	static struct tracer *old_tracer;
 	int cpu_file = iter->cpu_file;
 	void *p = NULL;
 	loff_t l = 0;
 	int cpu;
 
-	/* copy the tracer to avoid using a global lock all around */
+	/*
+	 * copy the tracer to avoid using a global lock all around.
+	 * iter->trace is a copy of current_trace, the pointer to the
+	 * name may be used instead of a strcmp(), as iter->trace->name
+	 * will point to the same string as current_trace->name.
+	 */
 	mutex_lock(&trace_types_lock);
-	if (unlikely(old_tracer != current_trace && current_trace)) {
-		old_tracer = current_trace;
+	if (unlikely(current_trace && iter->trace->name != current_trace->name))
 		*iter->trace = *current_trace;
-	}
 	mutex_unlock(&trace_types_lock);
 
-	atomic_inc(&trace_record_cmdline_disabled);
+	if (iter->snapshot && iter->trace->use_max_tr)
+		return ERR_PTR(-EBUSY);
+
+	if (!iter->snapshot)
+		atomic_inc(&trace_record_cmdline_disabled);
 
 	if (*pos != iter->pos) {
 		iter->ent = NULL;
@@ -1995,7 +2011,11 @@ static void s_stop(struct seq_file *m, void *p)
 {
 	struct trace_iterator *iter = m->private;
 
-	atomic_dec(&trace_record_cmdline_disabled);
+	if (iter->snapshot && iter->trace->use_max_tr)
+		return;
+
+	if (!iter->snapshot)
+		atomic_dec(&trace_record_cmdline_disabled);
 	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 }
@@ -2080,8 +2100,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 	unsigned long total;
 	const char *name = "preemption";
 
-	if (type)
-		name = type->name;
+	name = type->name;
 
 	get_total_entries(tr, &total, &entries);
 
@@ -2430,7 +2449,7 @@ static const struct seq_operations tracer_seq_ops = {
 };
 
 static struct trace_iterator *
-__tracing_open(struct inode *inode, struct file *file)
+__tracing_open(struct inode *inode, struct file *file, bool snapshot)
 {
 	long cpu_file = (long) inode->i_private;
 	struct trace_iterator *iter;
@@ -2457,16 +2476,16 @@ __tracing_open(struct inode *inode, struct file *file)
 	if (!iter->trace)
 		goto fail;
 
-	if (current_trace)
-		*iter->trace = *current_trace;
+	*iter->trace = *current_trace;
 
 	if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
 		goto fail;
 
-	if (current_trace && current_trace->print_max)
+	if (current_trace->print_max || snapshot)
 		iter->tr = &max_tr;
 	else
 		iter->tr = &global_trace;
+	iter->snapshot = snapshot;
 	iter->pos = -1;
 	mutex_init(&iter->mutex);
 	iter->cpu_file = cpu_file;
@@ -2483,8 +2502,9 @@ __tracing_open(struct inode *inode, struct file *file)
 	if (trace_clocks[trace_clock_id].in_ns)
 		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
 
-	/* stop the trace while dumping */
-	tracing_stop();
+	/* stop the trace while dumping if we are not opening "snapshot" */
+	if (!iter->snapshot)
+		tracing_stop();
 
 	if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
 		for_each_tracing_cpu(cpu) {
@@ -2547,8 +2567,9 @@ static int tracing_release(struct inode *inode, struct file *file)
 	if (iter->trace && iter->trace->close)
 		iter->trace->close(iter);
 
-	/* reenable tracing if it was previously enabled */
-	tracing_start();
+	if (!iter->snapshot)
+		/* reenable tracing if it was previously enabled */
+		tracing_start();
 	mutex_unlock(&trace_types_lock);
 
 	mutex_destroy(&iter->mutex);
@@ -2576,7 +2597,7 @@ static int tracing_open(struct inode *inode, struct file *file)
 	}
 
 	if (file->f_mode & FMODE_READ) {
-		iter = __tracing_open(inode, file);
+		iter = __tracing_open(inode, file, false);
 		if (IS_ERR(iter))
 			ret = PTR_ERR(iter);
 		else if (trace_flags & TRACE_ITER_LATENCY_FMT)
@@ -3014,10 +3035,7 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf,
 	int r;
 
 	mutex_lock(&trace_types_lock);
-	if (current_trace)
-		r = sprintf(buf, "%s\n", current_trace->name);
-	else
-		r = sprintf(buf, "\n");
+	r = sprintf(buf, "%s\n", current_trace->name);
 	mutex_unlock(&trace_types_lock);
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
@@ -3183,6 +3201,7 @@ static int tracing_set_tracer(const char *buf)
 	static struct trace_option_dentry *topts;
 	struct trace_array *tr = &global_trace;
 	struct tracer *t;
+	bool had_max_tr;
 	int ret = 0;
 
 	mutex_lock(&trace_types_lock);
@@ -3207,9 +3226,21 @@ static int tracing_set_tracer(const char *buf)
 		goto out;
 
 	trace_branch_disable();
-	if (current_trace && current_trace->reset)
+	if (current_trace->reset)
 		current_trace->reset(tr);
-	if (current_trace && current_trace->use_max_tr) {
+
+	had_max_tr = current_trace->allocated_snapshot;
+	current_trace = &nop_trace;
+
+	if (had_max_tr && !t->use_max_tr) {
+		/*
+		 * We need to make sure that the update_max_tr sees that
+		 * current_trace changed to nop_trace to keep it from
+		 * swapping the buffers after we resize it.
+		 * The update_max_tr is called from interrupts disabled
+		 * so a synchronized_sched() is sufficient.
+		 */
+		synchronize_sched();
 		/*
 		 * We don't free the ring buffer. instead, resize it because
 		 * The max_tr ring buffer has some state (e.g. ring->clock) and
@@ -3217,18 +3248,19 @@ static int tracing_set_tracer(const char *buf)
 		 */
 		ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS);
 		set_buffer_entries(&max_tr, 1);
+		tracing_reset_online_cpus(&max_tr);
+		current_trace->allocated_snapshot = false;
 	}
 	destroy_trace_option_files(topts);
 
-	current_trace = &nop_trace;
-
 	topts = create_trace_option_files(t);
-	if (t->use_max_tr) {
+	if (t->use_max_tr && !had_max_tr) {
 		/* we need to make per cpu buffer sizes equivalent */
 		ret = resize_buffer_duplicate_size(&max_tr, &global_trace,
 						   RING_BUFFER_ALL_CPUS);
 		if (ret < 0)
 			goto out;
+		t->allocated_snapshot = true;
 	}
 
 	if (t->init) {
@@ -3336,8 +3368,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 		ret = -ENOMEM;
 		goto fail;
 	}
-	if (current_trace)
-		*iter->trace = *current_trace;
+	*iter->trace = *current_trace;
 
 	if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) {
 		ret = -ENOMEM;
@@ -3477,7 +3508,6 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 		  size_t cnt, loff_t *ppos)
 {
 	struct trace_iterator *iter = filp->private_data;
-	static struct tracer *old_tracer;
 	ssize_t sret;
 
 	/* return any leftover data */
@@ -3489,10 +3519,8 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 
 	/* copy the tracer to avoid using a global lock all around */
 	mutex_lock(&trace_types_lock);
-	if (unlikely(old_tracer != current_trace && current_trace)) {
-		old_tracer = current_trace;
+	if (unlikely(iter->trace->name != current_trace->name))
 		*iter->trace = *current_trace;
-	}
 	mutex_unlock(&trace_types_lock);
 
 	/*
@@ -3648,7 +3676,6 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		.ops		= &tracing_pipe_buf_ops,
 		.spd_release	= tracing_spd_release_pipe,
 	};
-	static struct tracer *old_tracer;
 	ssize_t ret;
 	size_t rem;
 	unsigned int i;
@@ -3658,10 +3685,8 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 
 	/* copy the tracer to avoid using a global lock all around */
 	mutex_lock(&trace_types_lock);
-	if (unlikely(old_tracer != current_trace && current_trace)) {
-		old_tracer = current_trace;
+	if (unlikely(iter->trace->name != current_trace->name))
 		*iter->trace = *current_trace;
-	}
 	mutex_unlock(&trace_types_lock);
 
 	mutex_lock(&iter->mutex);
@@ -4037,8 +4062,7 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
 	 * Reset the buffer so that it doesn't have incomparable timestamps.
 	 */
 	tracing_reset_online_cpus(&global_trace);
-	if (max_tr.buffer)
-		tracing_reset_online_cpus(&max_tr);
+	tracing_reset_online_cpus(&max_tr);
 
 	mutex_unlock(&trace_types_lock);
 
@@ -4054,6 +4078,87 @@ static int tracing_clock_open(struct inode *inode, struct file *file)
 	return single_open(file, tracing_clock_show, NULL);
 }
 
+#ifdef CONFIG_TRACER_SNAPSHOT
+static int tracing_snapshot_open(struct inode *inode, struct file *file)
+{
+	struct trace_iterator *iter;
+	int ret = 0;
+
+	if (file->f_mode & FMODE_READ) {
+		iter = __tracing_open(inode, file, true);
+		if (IS_ERR(iter))
+			ret = PTR_ERR(iter);
+	}
+	return ret;
+}
+
+static ssize_t
+tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		       loff_t *ppos)
+{
+	unsigned long val;
+	int ret;
+
+	ret = tracing_update_buffers();
+	if (ret < 0)
+		return ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	mutex_lock(&trace_types_lock);
+
+	if (current_trace->use_max_tr) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	switch (val) {
+	case 0:
+		if (current_trace->allocated_snapshot) {
+			/* free spare buffer */
+			ring_buffer_resize(max_tr.buffer, 1,
+					   RING_BUFFER_ALL_CPUS);
+			set_buffer_entries(&max_tr, 1);
+			tracing_reset_online_cpus(&max_tr);
+			current_trace->allocated_snapshot = false;
+		}
+		break;
+	case 1:
+		if (!current_trace->allocated_snapshot) {
+			/* allocate spare buffer */
+			ret = resize_buffer_duplicate_size(&max_tr,
+					&global_trace, RING_BUFFER_ALL_CPUS);
+			if (ret < 0)
+				break;
+			current_trace->allocated_snapshot = true;
+		}
+
+		local_irq_disable();
+		/* Now, we're going to swap */
+		update_max_tr(&global_trace, current, smp_processor_id());
+		local_irq_enable();
+		break;
+	default:
+		if (current_trace->allocated_snapshot)
+			tracing_reset_online_cpus(&max_tr);
+		else
+			ret = -EINVAL;
+		break;
+	}
+
+	if (ret >= 0) {
+		*ppos += cnt;
+		ret = cnt;
+	}
+out:
+	mutex_unlock(&trace_types_lock);
+	return ret;
+}
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
+
 static const struct file_operations tracing_max_lat_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_max_lat_read,
@@ -4110,6 +4215,16 @@ static const struct file_operations trace_clock_fops = {
 	.write		= tracing_clock_write,
 };
 
+#ifdef CONFIG_TRACER_SNAPSHOT
+static const struct file_operations snapshot_fops = {
+	.open		= tracing_snapshot_open,
+	.read		= seq_read,
+	.write		= tracing_snapshot_write,
+	.llseek		= tracing_seek,
+	.release	= tracing_release,
+};
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
 struct ftrace_buffer_info {
 	struct trace_array	*tr;
 	void			*spare;
@@ -4414,6 +4529,9 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	cnt = ring_buffer_dropped_events_cpu(tr->buffer, cpu);
 	trace_seq_printf(s, "dropped events: %ld\n", cnt);
 
+	cnt = ring_buffer_read_events_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "read events: %ld\n", cnt);
+
 	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -4490,7 +4608,7 @@ struct dentry *tracing_init_dentry(void)
 
 static struct dentry *d_percpu;
 
-struct dentry *tracing_dentry_percpu(void)
+static struct dentry *tracing_dentry_percpu(void)
 {
 	static int once;
 	struct dentry *d_tracer;
@@ -4906,6 +5024,11 @@ static __init int tracer_init_debugfs(void)
 			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
 #endif
 
+#ifdef CONFIG_TRACER_SNAPSHOT
+	trace_create_file("snapshot", 0644, d_tracer,
+			  (void *) TRACE_PIPE_ALL_CPU, &snapshot_fops);
+#endif
+
 	create_trace_options_dir();
 
 	for_each_tracing_cpu(cpu)
@@ -5014,6 +5137,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 	if (disable_tracing)
 		ftrace_kill();
 
+	/* Simulate the iterator */
 	trace_init_global_iter(&iter);
 
 	for_each_tracing_cpu(cpu) {
@@ -5025,10 +5149,6 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 	/* don't look at user memory in panic mode */
 	trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
-	/* Simulate the iterator */
-	iter.tr = &global_trace;
-	iter.trace = current_trace;
-
 	switch (oops_dump_mode) {
 	case DUMP_ALL:
 		iter.cpu_file = TRACE_PIPE_ALL_CPU;
@@ -5173,7 +5293,7 @@ __init static int tracer_alloc_buffers(void)
 	init_irq_work(&trace_work_wakeup, trace_wake_up);
 
 	register_tracer(&nop_trace);
-	current_trace = &nop_trace;
+
 	/* All seems OK, enable tracing */
 	tracing_disabled = 0;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c75d7988902c..57d7e5397d56 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -287,20 +287,62 @@ struct tracer {
 	struct tracer_flags	*flags;
 	bool			print_max;
 	bool			use_max_tr;
+	bool			allocated_snapshot;
 };
 
 
 /* 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_CONTROL_BIT		(1<<13)
+/*
+ * For function tracing recursion:
+ *  The order of these bits are important.
+ *
+ *  When function tracing occurs, the following steps are made:
+ *   If arch does not support a ftrace feature:
+ *    call internal function (uses INTERNAL bits) which calls...
+ *   If callback is registered to the "global" list, the list
+ *    function is called and recursion checks the GLOBAL bits.
+ *    then this function calls...
+ *   The function callback, which can use the FTRACE bits to
+ *    check for recursion.
+ *
+ * Now if the arch does not suppport a feature, and it calls
+ * the global list function which calls the ftrace callback
+ * all three of these steps will do a recursion protection.
+ * There's no reason to do one if the previous caller already
+ * did. The recursion that we are protecting against will
+ * go through the same steps again.
+ *
+ * To prevent the multiple recursion checks, if a recursion
+ * bit is set that is higher than the MAX bit of the current
+ * check, then we know that the check was made by the previous
+ * caller, and we can skip the current check.
+ */
+enum {
+	TRACE_BUFFER_BIT,
+	TRACE_BUFFER_NMI_BIT,
+	TRACE_BUFFER_IRQ_BIT,
+	TRACE_BUFFER_SIRQ_BIT,
+
+	/* Start of function recursion bits */
+	TRACE_FTRACE_BIT,
+	TRACE_FTRACE_NMI_BIT,
+	TRACE_FTRACE_IRQ_BIT,
+	TRACE_FTRACE_SIRQ_BIT,
+
+	/* GLOBAL_BITs must be greater than FTRACE_BITs */
+	TRACE_GLOBAL_BIT,
+	TRACE_GLOBAL_NMI_BIT,
+	TRACE_GLOBAL_IRQ_BIT,
+	TRACE_GLOBAL_SIRQ_BIT,
+
+	/* INTERNAL_BITs must be greater than GLOBAL_BITs */
+	TRACE_INTERNAL_BIT,
+	TRACE_INTERNAL_NMI_BIT,
+	TRACE_INTERNAL_IRQ_BIT,
+	TRACE_INTERNAL_SIRQ_BIT,
+
+	TRACE_CONTROL_BIT,
 
 /*
  * Abuse of the trace_recursion.
@@ -309,11 +351,77 @@ struct tracer {
  * 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)
+	TRACE_IRQ_BIT,
+};
+
+#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (1<<(bit)); } while (0)
+#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(1<<(bit)); } while (0)
+#define trace_recursion_test(bit)	((current)->trace_recursion & (1<<(bit)))
+
+#define TRACE_CONTEXT_BITS	4
+
+#define TRACE_FTRACE_START	TRACE_FTRACE_BIT
+#define TRACE_FTRACE_MAX	((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1)
+
+#define TRACE_GLOBAL_START	TRACE_GLOBAL_BIT
+#define TRACE_GLOBAL_MAX	((1 << (TRACE_GLOBAL_START + TRACE_CONTEXT_BITS)) - 1)
+
+#define TRACE_LIST_START	TRACE_INTERNAL_BIT
+#define TRACE_LIST_MAX		((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)
+
+#define TRACE_CONTEXT_MASK	TRACE_LIST_MAX
+
+static __always_inline int trace_get_context_bit(void)
+{
+	int bit;
 
-#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))
+	if (in_interrupt()) {
+		if (in_nmi())
+			bit = 0;
+
+		else if (in_irq())
+			bit = 1;
+		else
+			bit = 2;
+	} else
+		bit = 3;
+
+	return bit;
+}
+
+static __always_inline int trace_test_and_set_recursion(int start, int max)
+{
+	unsigned int val = current->trace_recursion;
+	int bit;
+
+	/* A previous recursion check was made */
+	if ((val & TRACE_CONTEXT_MASK) > max)
+		return 0;
+
+	bit = trace_get_context_bit() + start;
+	if (unlikely(val & (1 << bit)))
+		return -1;
+
+	val |= 1 << bit;
+	current->trace_recursion = val;
+	barrier();
+
+	return bit;
+}
+
+static __always_inline void trace_clear_recursion(int bit)
+{
+	unsigned int val = current->trace_recursion;
+
+	if (!bit)
+		return;
+
+	bit = 1 << bit;
+	val &= ~bit;
+
+	barrier();
+	current->trace_recursion = val;
+}
 
 #define TRACE_PIPE_ALL_CPU	-1
 
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 1bbb1b200cec..aa8f5f48dae6 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -21,8 +21,6 @@
 #include <linux/ktime.h>
 #include <linux/trace_clock.h>
 
-#include "trace.h"
-
 /*
  * trace_clock_local(): the simplest and least coherent tracing clock.
  *
@@ -87,7 +85,7 @@ u64 notrace trace_clock_global(void)
 	local_irq_save(flags);
 
 	this_cpu = raw_smp_processor_id();
-	now = cpu_clock(this_cpu);
+	now = sched_clock_cpu(this_cpu);
 	/*
 	 * If in an NMI context then dont risk lockups and return the
 	 * cpu_clock() time:
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 880073d0b946..57e9b284250c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,7 +116,6 @@ static int trace_define_common_fields(void)
 	__common_field(unsigned char, flags);
 	__common_field(unsigned char, preempt_count);
 	__common_field(int, pid);
-	__common_field(int, padding);
 
 	return ret;
 }
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 8e3ad8082ab7..601152523326 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -47,34 +47,6 @@ static void function_trace_start(struct trace_array *tr)
 	tracing_reset_online_cpus(tr);
 }
 
-static void
-function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip,
-				 struct ftrace_ops *op, struct pt_regs *pt_regs)
-{
-	struct trace_array *tr = func_trace;
-	struct trace_array_cpu *data;
-	unsigned long flags;
-	long disabled;
-	int cpu;
-	int pc;
-
-	if (unlikely(!ftrace_function_enabled))
-		return;
-
-	pc = preempt_count();
-	preempt_disable_notrace();
-	local_save_flags(flags);
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
-
-	if (likely(disabled == 1))
-		trace_function(tr, ip, parent_ip, flags, pc);
-
-	atomic_dec(&data->disabled);
-	preempt_enable_notrace();
-}
-
 /* Our option */
 enum {
 	TRACE_FUNC_OPT_STACK	= 0x1,
@@ -85,34 +57,34 @@ static struct tracer_flags func_flags;
 static void
 function_trace_call(unsigned long ip, unsigned long parent_ip,
 		    struct ftrace_ops *op, struct pt_regs *pt_regs)
-
 {
 	struct trace_array *tr = func_trace;
 	struct trace_array_cpu *data;
 	unsigned long flags;
-	long disabled;
+	int bit;
 	int cpu;
 	int pc;
 
 	if (unlikely(!ftrace_function_enabled))
 		return;
 
-	/*
-	 * Need to use raw, since this must be called before the
-	 * recursive protection is performed.
-	 */
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
+	pc = preempt_count();
+	preempt_disable_notrace();
 
-	if (likely(disabled == 1)) {
-		pc = preempt_count();
+	bit = trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX);
+	if (bit < 0)
+		goto out;
+
+	cpu = smp_processor_id();
+	data = tr->data[cpu];
+	if (!atomic_read(&data->disabled)) {
+		local_save_flags(flags);
 		trace_function(tr, ip, parent_ip, flags, pc);
 	}
+	trace_clear_recursion(bit);
 
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
+ out:
+	preempt_enable_notrace();
 }
 
 static void
@@ -185,11 +157,6 @@ static void tracing_start_function_trace(void)
 {
 	ftrace_function_enabled = 0;
 
-	if (trace_flags & TRACE_ITER_PREEMPTONLY)
-		trace_ops.func = function_trace_call_preempt_only;
-	else
-		trace_ops.func = function_trace_call;
-
 	if (func_flags.val & TRACE_FUNC_OPT_STACK)
 		register_ftrace_function(&trace_stack_ops);
 	else
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 4edb4b74eb7e..39ada66389cc 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -47,6 +47,8 @@ struct fgraph_data {
 #define TRACE_GRAPH_PRINT_ABS_TIME	0x20
 #define TRACE_GRAPH_PRINT_IRQS		0x40
 
+static unsigned int max_depth;
+
 static struct tracer_opt trace_opts[] = {
 	/* Display overruns? (for self-debug purpose) */
 	{ TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) },
@@ -189,10 +191,16 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 
 	ftrace_pop_return_trace(&trace, &ret, frame_pointer);
 	trace.rettime = trace_clock_local();
-	ftrace_graph_return(&trace);
 	barrier();
 	current->curr_ret_stack--;
 
+	/*
+	 * The trace should run after decrementing the ret counter
+	 * in case an interrupt were to come in. We don't want to
+	 * lose the interrupt if max_depth is set.
+	 */
+	ftrace_graph_return(&trace);
+
 	if (unlikely(!ret)) {
 		ftrace_graph_stop();
 		WARN_ON(1);
@@ -250,8 +258,9 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 		return 0;
 
 	/* trace it when it is-nested-in or is a function enabled. */
-	if (!(trace->depth || ftrace_graph_addr(trace->func)) ||
-	      ftrace_graph_ignore_irqs())
+	if ((!(trace->depth || ftrace_graph_addr(trace->func)) ||
+	     ftrace_graph_ignore_irqs()) ||
+	    (max_depth && trace->depth >= max_depth))
 		return 0;
 
 	local_irq_save(flags);
@@ -1457,6 +1466,59 @@ static struct tracer graph_trace __read_mostly = {
 #endif
 };
 
+
+static ssize_t
+graph_depth_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		  loff_t *ppos)
+{
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	max_depth = val;
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static ssize_t
+graph_depth_read(struct file *filp, char __user *ubuf, size_t cnt,
+		 loff_t *ppos)
+{
+	char buf[15]; /* More than enough to hold UINT_MAX + "\n"*/
+	int n;
+
+	n = sprintf(buf, "%d\n", max_depth);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, n);
+}
+
+static const struct file_operations graph_depth_fops = {
+	.open		= tracing_open_generic,
+	.write		= graph_depth_write,
+	.read		= graph_depth_read,
+	.llseek		= generic_file_llseek,
+};
+
+static __init int init_graph_debugfs(void)
+{
+	struct dentry *d_tracer;
+
+	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
+
+	trace_create_file("max_graph_depth", 0644, d_tracer,
+			  NULL, &graph_depth_fops);
+
+	return 0;
+}
+fs_initcall(init_graph_debugfs);
+
 static __init int init_graph_trace(void)
 {
 	max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 933708677814..5c7e09d10d74 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -66,7 +66,6 @@
 #define TP_FLAG_TRACE		1
 #define TP_FLAG_PROFILE		2
 #define TP_FLAG_REGISTERED	4
-#define TP_FLAG_UPROBE		8
 
 
 /* data_rloc: data relative location, compatible with u32 */
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 47623169a815..51c819c12c29 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -415,7 +415,8 @@ static void trace_selftest_test_recursion_func(unsigned long ip,
 	 * The ftrace infrastructure should provide the recursion
 	 * protection. If not, this will crash the kernel!
 	 */
-	trace_selftest_recursion_cnt++;
+	if (trace_selftest_recursion_cnt++ > 10)
+		return;
 	DYN_FTRACE_TEST_NAME();
 }
 
@@ -452,7 +453,6 @@ trace_selftest_function_recursion(void)
 	char *func_name;
 	int len;
 	int ret;
-	int cnt;
 
 	/* The previous test PASSED */
 	pr_cont("PASSED\n");
@@ -510,19 +510,10 @@ trace_selftest_function_recursion(void)
 
 	unregister_ftrace_function(&test_recsafe_probe);
 
-	/*
-	 * If arch supports all ftrace features, and no other task
-	 * was on the list, we should be fine.
-	 */
-	if (!ftrace_nr_registered_ops() && !FTRACE_FORCE_LIST_FUNC)
-		cnt = 2; /* Should have recursed */
-	else
-		cnt = 1;
-
 	ret = -1;
-	if (trace_selftest_recursion_cnt != cnt) {
-		pr_cont("*callback not called expected %d times (%d)* ",
-			cnt, trace_selftest_recursion_cnt);
+	if (trace_selftest_recursion_cnt != 2) {
+		pr_cont("*callback not called expected 2 times (%d)* ",
+			trace_selftest_recursion_cnt);
 		goto out;
 	}
 
@@ -568,7 +559,7 @@ trace_selftest_function_regs(void)
 	int ret;
 	int supported = 0;
 
-#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 	supported = 1;
 #endif
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 7609dd6714c2..5329e13e74a1 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -77,7 +77,7 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr)
 	return syscalls_metadata[nr];
 }
 
-enum print_line_t
+static enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags,
 		    struct trace_event *event)
 {
@@ -130,7 +130,7 @@ end:
 	return TRACE_TYPE_HANDLED;
 }
 
-enum print_line_t
+static enum print_line_t
 print_syscall_exit(struct trace_iterator *iter, int flags,
 		   struct trace_event *event)
 {
@@ -270,7 +270,7 @@ static int syscall_exit_define_fields(struct ftrace_event_call *call)
 	return ret;
 }
 
-void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
+static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
 	struct syscall_trace_enter *entry;
 	struct syscall_metadata *sys_data;
@@ -305,7 +305,7 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
+static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 {
 	struct syscall_trace_exit *entry;
 	struct syscall_metadata *sys_data;
@@ -337,7 +337,7 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-int reg_event_syscall_enter(struct ftrace_event_call *call)
+static int reg_event_syscall_enter(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -356,7 +356,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call)
 	return ret;
 }
 
-void unreg_event_syscall_enter(struct ftrace_event_call *call)
+static void unreg_event_syscall_enter(struct ftrace_event_call *call)
 {
 	int num;
 
@@ -371,7 +371,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call)
 	mutex_unlock(&syscall_trace_lock);
 }
 
-int reg_event_syscall_exit(struct ftrace_event_call *call)
+static int reg_event_syscall_exit(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -390,7 +390,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call)
 	return ret;
 }
 
-void unreg_event_syscall_exit(struct ftrace_event_call *call)
+static void unreg_event_syscall_exit(struct ftrace_event_call *call)
 {
 	int num;
 
@@ -459,7 +459,7 @@ unsigned long __init __weak arch_syscall_addr(int nr)
 	return (unsigned long)sys_call_table[nr];
 }
 
-int __init init_ftrace_syscalls(void)
+static int __init init_ftrace_syscalls(void)
 {
 	struct syscall_metadata *meta;
 	unsigned long addr;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index c86e6d4f67fb..8dad2a92dee9 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -28,20 +28,21 @@
 
 #define UPROBE_EVENT_SYSTEM	"uprobes"
 
+struct trace_uprobe_filter {
+	rwlock_t		rwlock;
+	int			nr_systemwide;
+	struct list_head	perf_events;
+};
+
 /*
  * uprobe event core functions
  */
-struct trace_uprobe;
-struct uprobe_trace_consumer {
-	struct uprobe_consumer		cons;
-	struct trace_uprobe		*tu;
-};
-
 struct trace_uprobe {
 	struct list_head		list;
 	struct ftrace_event_class	class;
 	struct ftrace_event_call	call;
-	struct uprobe_trace_consumer	*consumer;
+	struct trace_uprobe_filter	filter;
+	struct uprobe_consumer		consumer;
 	struct inode			*inode;
 	char				*filename;
 	unsigned long			offset;
@@ -64,6 +65,18 @@ static LIST_HEAD(uprobe_list);
 
 static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
 
+static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter)
+{
+	rwlock_init(&filter->rwlock);
+	filter->nr_systemwide = 0;
+	INIT_LIST_HEAD(&filter->perf_events);
+}
+
+static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter)
+{
+	return !filter->nr_systemwide && list_empty(&filter->perf_events);
+}
+
 /*
  * Allocate new trace_uprobe and initialize it (including uprobes).
  */
@@ -92,6 +105,8 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs)
 		goto error;
 
 	INIT_LIST_HEAD(&tu->list);
+	tu->consumer.handler = uprobe_dispatcher;
+	init_trace_uprobe_filter(&tu->filter);
 	return tu;
 
 error:
@@ -253,12 +268,18 @@ static int create_trace_uprobe(int argc, char **argv)
 	if (ret)
 		goto fail_address_parse;
 
+	inode = igrab(path.dentry->d_inode);
+	path_put(&path);
+
+	if (!inode || !S_ISREG(inode->i_mode)) {
+		ret = -EINVAL;
+		goto fail_address_parse;
+	}
+
 	ret = kstrtoul(arg, 0, &offset);
 	if (ret)
 		goto fail_address_parse;
 
-	inode = igrab(path.dentry->d_inode);
-
 	argc -= 2;
 	argv += 2;
 
@@ -356,7 +377,7 @@ fail_address_parse:
 	if (inode)
 		iput(inode);
 
-	pr_info("Failed to parse address.\n");
+	pr_info("Failed to parse address or file.\n");
 
 	return ret;
 }
@@ -465,7 +486,7 @@ static const struct file_operations uprobe_profile_ops = {
 };
 
 /* uprobe handler */
-static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
 {
 	struct uprobe_trace_entry_head *entry;
 	struct ring_buffer_event *event;
@@ -475,8 +496,6 @@ static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
 	unsigned long irq_flags;
 	struct ftrace_event_call *call = &tu->call;
 
-	tu->nhit++;
-
 	local_save_flags(irq_flags);
 	pc = preempt_count();
 
@@ -485,16 +504,18 @@ static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
 	event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
 						  size, irq_flags, pc);
 	if (!event)
-		return;
+		return 0;
 
 	entry = ring_buffer_event_data(event);
-	entry->ip = uprobe_get_swbp_addr(task_pt_regs(current));
+	entry->ip = instruction_pointer(task_pt_regs(current));
 	data = (u8 *)&entry[1];
 	for (i = 0; i < tu->nr_args; i++)
 		call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
 		trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
+
+	return 0;
 }
 
 /* Event entry printers */
@@ -533,42 +554,43 @@ partial:
 	return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static int probe_event_enable(struct trace_uprobe *tu, int flag)
+static inline bool is_trace_uprobe_enabled(struct trace_uprobe *tu)
 {
-	struct uprobe_trace_consumer *utc;
-	int ret = 0;
+	return tu->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE);
+}
 
-	if (!tu->inode || tu->consumer)
-		return -EINTR;
+typedef bool (*filter_func_t)(struct uprobe_consumer *self,
+				enum uprobe_filter_ctx ctx,
+				struct mm_struct *mm);
 
-	utc = kzalloc(sizeof(struct uprobe_trace_consumer), GFP_KERNEL);
-	if (!utc)
+static int
+probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter)
+{
+	int ret = 0;
+
+	if (is_trace_uprobe_enabled(tu))
 		return -EINTR;
 
-	utc->cons.handler = uprobe_dispatcher;
-	utc->cons.filter = NULL;
-	ret = uprobe_register(tu->inode, tu->offset, &utc->cons);
-	if (ret) {
-		kfree(utc);
-		return ret;
-	}
+	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
 	tu->flags |= flag;
-	utc->tu = tu;
-	tu->consumer = utc;
+	tu->consumer.filter = filter;
+	ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
+	if (ret)
+		tu->flags &= ~flag;
 
-	return 0;
+	return ret;
 }
 
 static void probe_event_disable(struct trace_uprobe *tu, int flag)
 {
-	if (!tu->inode || !tu->consumer)
+	if (!is_trace_uprobe_enabled(tu))
 		return;
 
-	uprobe_unregister(tu->inode, tu->offset, &tu->consumer->cons);
+	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
+
+	uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
 	tu->flags &= ~flag;
-	kfree(tu->consumer);
-	tu->consumer = NULL;
 }
 
 static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
@@ -642,8 +664,96 @@ static int set_print_fmt(struct trace_uprobe *tu)
 }
 
 #ifdef CONFIG_PERF_EVENTS
+static bool
+__uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
+{
+	struct perf_event *event;
+
+	if (filter->nr_systemwide)
+		return true;
+
+	list_for_each_entry(event, &filter->perf_events, hw.tp_list) {
+		if (event->hw.tp_target->mm == mm)
+			return true;
+	}
+
+	return false;
+}
+
+static inline bool
+uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event)
+{
+	return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm);
+}
+
+static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
+{
+	bool done;
+
+	write_lock(&tu->filter.rwlock);
+	if (event->hw.tp_target) {
+		/*
+		 * event->parent != NULL means copy_process(), we can avoid
+		 * uprobe_apply(). current->mm must be probed and we can rely
+		 * on dup_mmap() which preserves the already installed bp's.
+		 *
+		 * attr.enable_on_exec means that exec/mmap will install the
+		 * breakpoints we need.
+		 */
+		done = tu->filter.nr_systemwide ||
+			event->parent || event->attr.enable_on_exec ||
+			uprobe_filter_event(tu, event);
+		list_add(&event->hw.tp_list, &tu->filter.perf_events);
+	} else {
+		done = tu->filter.nr_systemwide;
+		tu->filter.nr_systemwide++;
+	}
+	write_unlock(&tu->filter.rwlock);
+
+	if (!done)
+		uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+
+	return 0;
+}
+
+static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
+{
+	bool done;
+
+	write_lock(&tu->filter.rwlock);
+	if (event->hw.tp_target) {
+		list_del(&event->hw.tp_list);
+		done = tu->filter.nr_systemwide ||
+			(event->hw.tp_target->flags & PF_EXITING) ||
+			uprobe_filter_event(tu, event);
+	} else {
+		tu->filter.nr_systemwide--;
+		done = tu->filter.nr_systemwide;
+	}
+	write_unlock(&tu->filter.rwlock);
+
+	if (!done)
+		uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
+
+	return 0;
+}
+
+static bool uprobe_perf_filter(struct uprobe_consumer *uc,
+				enum uprobe_filter_ctx ctx, struct mm_struct *mm)
+{
+	struct trace_uprobe *tu;
+	int ret;
+
+	tu = container_of(uc, struct trace_uprobe, consumer);
+	read_lock(&tu->filter.rwlock);
+	ret = __uprobe_perf_filter(&tu->filter, mm);
+	read_unlock(&tu->filter.rwlock);
+
+	return ret;
+}
+
 /* uprobe profile handler */
-static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
 {
 	struct ftrace_event_call *call = &tu->call;
 	struct uprobe_trace_entry_head *entry;
@@ -652,11 +762,14 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
 	int size, __size, i;
 	int rctx;
 
+	if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
+		return UPROBE_HANDLER_REMOVE;
+
 	__size = sizeof(*entry) + tu->size;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
-		return;
+		return 0;
 
 	preempt_disable();
 
@@ -664,7 +777,7 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
 	if (!entry)
 		goto out;
 
-	entry->ip = uprobe_get_swbp_addr(task_pt_regs(current));
+	entry->ip = instruction_pointer(task_pt_regs(current));
 	data = (u8 *)&entry[1];
 	for (i = 0; i < tu->nr_args; i++)
 		call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
@@ -674,6 +787,7 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
 
  out:
 	preempt_enable();
+	return 0;
 }
 #endif	/* CONFIG_PERF_EVENTS */
 
@@ -684,7 +798,7 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type,
 
 	switch (type) {
 	case TRACE_REG_REGISTER:
-		return probe_event_enable(tu, TP_FLAG_TRACE);
+		return probe_event_enable(tu, TP_FLAG_TRACE, NULL);
 
 	case TRACE_REG_UNREGISTER:
 		probe_event_disable(tu, TP_FLAG_TRACE);
@@ -692,11 +806,18 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type,
 
 #ifdef CONFIG_PERF_EVENTS
 	case TRACE_REG_PERF_REGISTER:
-		return probe_event_enable(tu, TP_FLAG_PROFILE);
+		return probe_event_enable(tu, TP_FLAG_PROFILE, uprobe_perf_filter);
 
 	case TRACE_REG_PERF_UNREGISTER:
 		probe_event_disable(tu, TP_FLAG_PROFILE);
 		return 0;
+
+	case TRACE_REG_PERF_OPEN:
+		return uprobe_perf_open(tu, data);
+
+	case TRACE_REG_PERF_CLOSE:
+		return uprobe_perf_close(tu, data);
+
 #endif
 	default:
 		return 0;
@@ -706,22 +827,20 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type,
 
 static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 {
-	struct uprobe_trace_consumer *utc;
 	struct trace_uprobe *tu;
+	int ret = 0;
 
-	utc = container_of(con, struct uprobe_trace_consumer, cons);
-	tu = utc->tu;
-	if (!tu || tu->consumer != utc)
-		return 0;
+	tu = container_of(con, struct trace_uprobe, consumer);
+	tu->nhit++;
 
 	if (tu->flags & TP_FLAG_TRACE)
-		uprobe_trace_func(tu, regs);
+		ret |= uprobe_trace_func(tu, regs);
 
 #ifdef CONFIG_PERF_EVENTS
 	if (tu->flags & TP_FLAG_PROFILE)
-		uprobe_perf_func(tu, regs);
+		ret |= uprobe_perf_func(tu, regs);
 #endif
-	return 0;
+	return ret;
 }
 
 static struct trace_event_functions uprobe_funcs = {