24 files changed, 1259 insertions, 407 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index e5602d3..5404911 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -97,7 +97,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o
 obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
-obj-$(CONFIG_X86_DS) += trace/
+obj-$(CONFIG_TRACE_CLOCK) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_TRACEPOINTS) += trace/
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 98d4597..c772061 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -159,6 +159,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 	int rctx;
 	struct perf_callchain_entry *entry;
 
+	int kernel = !event->attr.exclude_callchain_kernel;
+	int user   = !event->attr.exclude_callchain_user;
+
+	if (!kernel && !user)
+		return NULL;
 
 	entry = get_callchain_entry(&rctx);
 	if (rctx == -1)
@@ -169,24 +174,29 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 
 	entry->nr = 0;
 
-	if (!user_mode(regs)) {
+	if (kernel && !user_mode(regs)) {
 		perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 		perf_callchain_kernel(entry, regs);
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
 	}
 
-	if (regs) {
-		/*
-		 * Disallow cross-task user callchains.
-		 */
-		if (event->ctx->task && event->ctx->task != current)
-			goto exit_put;
-
-		perf_callchain_store(entry, PERF_CONTEXT_USER);
-		perf_callchain_user(entry, regs);
+	if (user) {
+		if (!user_mode(regs)) {
+			if  (current->mm)
+				regs = task_pt_regs(current);
+			else
+				regs = NULL;
+		}
+
+		if (regs) {
+			/*
+			 * Disallow cross-task user callchains.
+			 */
+			if (event->ctx->task && event->ctx->task != current)
+				goto exit_put;
+
+			perf_callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_user(entry, regs);
+		}
 	}
 
 exit_put:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7fee567..7b9df35 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -36,6 +36,7 @@
 #include <linux/perf_event.h>
 #include <linux/ftrace_event.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/mm_types.h>
 
 #include "internal.h"
 
@@ -3764,6 +3765,132 @@ int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
 }
 EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
 
+static void
+perf_output_sample_regs(struct perf_output_handle *handle,
+			struct pt_regs *regs, u64 mask)
+{
+	int bit;
+
+	for_each_set_bit(bit, (const unsigned long *) &mask,
+			 sizeof(mask) * BITS_PER_BYTE) {
+		u64 val;
+
+		val = perf_reg_value(regs, bit);
+		perf_output_put(handle, val);
+	}
+}
+
+static void perf_sample_regs_user(struct perf_regs_user *regs_user,
+				  struct pt_regs *regs)
+{
+	if (!user_mode(regs)) {
+		if (current->mm)
+			regs = task_pt_regs(current);
+		else
+			regs = NULL;
+	}
+
+	if (regs) {
+		regs_user->regs = regs;
+		regs_user->abi  = perf_reg_abi(current);
+	}
+}
+
+/*
+ * Get remaining task size from user stack pointer.
+ *
+ * It'd be better to take stack vma map and limit this more
+ * precisly, but there's no way to get it safely under interrupt,
+ * so using TASK_SIZE as limit.
+ */
+static u64 perf_ustack_task_size(struct pt_regs *regs)
+{
+	unsigned long addr = perf_user_stack_pointer(regs);
+
+	if (!addr || addr >= TASK_SIZE)
+		return 0;
+
+	return TASK_SIZE - addr;
+}
+
+static u16
+perf_sample_ustack_size(u16 stack_size, u16 header_size,
+			struct pt_regs *regs)
+{
+	u64 task_size;
+
+	/* No regs, no stack pointer, no dump. */
+	if (!regs)
+		return 0;
+
+	/*
+	 * Check if we fit in with the requested stack size into the:
+	 * - TASK_SIZE
+	 *   If we don't, we limit the size to the TASK_SIZE.
+	 *
+	 * - remaining sample size
+	 *   If we don't, we customize the stack size to
+	 *   fit in to the remaining sample size.
+	 */
+
+	task_size  = min((u64) USHRT_MAX, perf_ustack_task_size(regs));
+	stack_size = min(stack_size, (u16) task_size);
+
+	/* Current header size plus static size and dynamic size. */
+	header_size += 2 * sizeof(u64);
+
+	/* Do we fit in with the current stack dump size? */
+	if ((u16) (header_size + stack_size) < header_size) {
+		/*
+		 * If we overflow the maximum size for the sample,
+		 * we customize the stack dump size to fit in.
+		 */
+		stack_size = USHRT_MAX - header_size - sizeof(u64);
+		stack_size = round_up(stack_size, sizeof(u64));
+	}
+
+	return stack_size;
+}
+
+static void
+perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
+			  struct pt_regs *regs)
+{
+	/* Case of a kernel thread, nothing to dump */
+	if (!regs) {
+		u64 size = 0;
+		perf_output_put(handle, size);
+	} else {
+		unsigned long sp;
+		unsigned int rem;
+		u64 dyn_size;
+
+		/*
+		 * We dump:
+		 * static size
+		 *   - the size requested by user or the best one we can fit
+		 *     in to the sample max size
+		 * data
+		 *   - user stack dump data
+		 * dynamic size
+		 *   - the actual dumped size
+		 */
+
+		/* Static size. */
+		perf_output_put(handle, dump_size);
+
+		/* Data. */
+		sp = perf_user_stack_pointer(regs);
+		rem = __output_copy_user(handle, (void *) sp, dump_size);
+		dyn_size = dump_size - rem;
+
+		perf_output_skip(handle, rem);
+
+		/* Dynamic size. */
+		perf_output_put(handle, dyn_size);
+	}
+}
+
 static void __perf_event_header__init_id(struct perf_event_header *header,
 					 struct perf_sample_data *data,
 					 struct perf_event *event)
@@ -4024,6 +4151,28 @@ void perf_output_sample(struct perf_output_handle *handle,
 			perf_output_put(handle, nr);
 		}
 	}
+
+	if (sample_type & PERF_SAMPLE_REGS_USER) {
+		u64 abi = data->regs_user.abi;
+
+		/*
+		 * If there are no regs to dump, notice it through
+		 * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
+		 */
+		perf_output_put(handle, abi);
+
+		if (abi) {
+			u64 mask = event->attr.sample_regs_user;
+			perf_output_sample_regs(handle,
+						data->regs_user.regs,
+						mask);
+		}
+	}
+
+	if (sample_type & PERF_SAMPLE_STACK_USER)
+		perf_output_sample_ustack(handle,
+					  data->stack_user_size,
+					  data->regs_user.regs);
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
@@ -4075,6 +4224,49 @@ void perf_prepare_sample(struct perf_event_header *header,
 		}
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_REGS_USER) {
+		/* regs dump ABI info */
+		int size = sizeof(u64);
+
+		perf_sample_regs_user(&data->regs_user, regs);
+
+		if (data->regs_user.regs) {
+			u64 mask = event->attr.sample_regs_user;
+			size += hweight64(mask) * sizeof(u64);
+		}
+
+		header->size += size;
+	}
+
+	if (sample_type & PERF_SAMPLE_STACK_USER) {
+		/*
+		 * Either we need PERF_SAMPLE_STACK_USER bit to be allways
+		 * processed as the last one or have additional check added
+		 * in case new sample type is added, because we could eat
+		 * up the rest of the sample size.
+		 */
+		struct perf_regs_user *uregs = &data->regs_user;
+		u16 stack_size = event->attr.sample_stack_user;
+		u16 size = sizeof(u64);
+
+		if (!uregs->abi)
+			perf_sample_regs_user(uregs, regs);
+
+		stack_size = perf_sample_ustack_size(stack_size, header->size,
+						     uregs->regs);
+
+		/*
+		 * If there is something to dump, add space for the dump
+		 * itself and for the field that tells the dynamic size,
+		 * which is how many have been actually dumped.
+		 */
+		if (stack_size)
+			size += sizeof(u64) + stack_size;
+
+		data->stack_user_size = stack_size;
+		header->size += size;
+	}
 }
 
 static void perf_event_output(struct perf_event *event,
@@ -6151,6 +6343,28 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 			attr->branch_sample_type = mask;
 		}
 	}
+
+	if (attr->sample_type & PERF_SAMPLE_REGS_USER) {
+		ret = perf_reg_validate(attr->sample_regs_user);
+		if (ret)
+			return ret;
+	}
+
+	if (attr->sample_type & PERF_SAMPLE_STACK_USER) {
+		if (!arch_perf_have_user_stack_dump())
+			return -ENOSYS;
+
+		/*
+		 * We have __u32 type for the size, but so far
+		 * we can only use __u16 as maximum due to the
+		 * __u16 sample size limit.
+		 */
+		if (attr->sample_stack_user >= USHRT_MAX)
+			ret = -EINVAL;
+		else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
+			ret = -EINVAL;
+	}
+
 out:
 	return ret;
 
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index a096c19..d56a64c 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -2,6 +2,7 @@
 #define _KERNEL_EVENTS_INTERNAL_H
 
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 
 /* Buffer handling */
 
@@ -76,30 +77,53 @@ static inline unsigned long perf_data_size(struct ring_buffer *rb)
 	return rb->nr_pages << (PAGE_SHIFT + page_order(rb));
 }
 
-static inline void
-__output_copy(struct perf_output_handle *handle,
-		   const void *buf, unsigned int len)
+#define DEFINE_OUTPUT_COPY(func_name, memcpy_func)			\
+static inline unsigned int						\
+func_name(struct perf_output_handle *handle,				\
+	  const void *buf, unsigned int len)				\
+{									\
+	unsigned long size, written;					\
+									\
+	do {								\
+		size = min_t(unsigned long, handle->size, len);		\
+									\
+		written = memcpy_func(handle->addr, buf, size);		\
+									\
+		len -= written;						\
+		handle->addr += written;				\
+		buf += written;						\
+		handle->size -= written;				\
+		if (!handle->size) {					\
+			struct ring_buffer *rb = handle->rb;		\
+									\
+			handle->page++;					\
+			handle->page &= rb->nr_pages - 1;		\
+			handle->addr = rb->data_pages[handle->page];	\
+			handle->size = PAGE_SIZE << page_order(rb);	\
+		}							\
+	} while (len && written == size);				\
+									\
+	return len;							\
+}
+
+static inline int memcpy_common(void *dst, const void *src, size_t n)
 {
-	do {
-		unsigned long size = min_t(unsigned long, handle->size, len);
-
-		memcpy(handle->addr, buf, size);
-
-		len -= size;
-		handle->addr += size;
-		buf += size;
-		handle->size -= size;
-		if (!handle->size) {
-			struct ring_buffer *rb = handle->rb;
-
-			handle->page++;
-			handle->page &= rb->nr_pages - 1;
-			handle->addr = rb->data_pages[handle->page];
-			handle->size = PAGE_SIZE << page_order(rb);
-		}
-	} while (len);
+	memcpy(dst, src, n);
+	return n;
 }
 
+DEFINE_OUTPUT_COPY(__output_copy, memcpy_common)
+
+#define MEMCPY_SKIP(dst, src, n) (n)
+
+DEFINE_OUTPUT_COPY(__output_skip, MEMCPY_SKIP)
+
+#ifndef arch_perf_out_copy_user
+#define arch_perf_out_copy_user __copy_from_user_inatomic
+#endif
+
+DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
+
 /* Callchain handling */
 extern struct perf_callchain_entry *
 perf_callchain(struct perf_event *event, struct pt_regs *regs);
@@ -134,4 +158,20 @@ static inline void put_recursion_context(int *recursion, int rctx)
 	recursion[rctx]--;
 }
 
+#ifdef CONFIG_HAVE_PERF_USER_STACK_DUMP
+static inline bool arch_perf_have_user_stack_dump(void)
+{
+	return true;
+}
+
+#define perf_user_stack_pointer(regs) user_stack_pointer(regs)
+#else
+static inline bool arch_perf_have_user_stack_dump(void)
+{
+	return false;
+}
+
+#define perf_user_stack_pointer(regs) 0
+#endif /* CONFIG_HAVE_PERF_USER_STACK_DUMP */
+
 #endif /* _KERNEL_EVENTS_INTERNAL_H */
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 6ddaba4..23cb34f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -182,10 +182,16 @@ out:
 	return -ENOSPC;
 }
 
-void perf_output_copy(struct perf_output_handle *handle,
+unsigned int perf_output_copy(struct perf_output_handle *handle,
 		      const void *buf, unsigned int len)
 {
-	__output_copy(handle, buf, len);
+	return __output_copy(handle, buf, len);
+}
+
+unsigned int perf_output_skip(struct perf_output_handle *handle,
+			      unsigned int len)
+{
+	return __output_skip(handle, NULL, len);
 }
 
 void perf_output_end(struct perf_output_handle *handle)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index c08a22d..912ef48 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -280,12 +280,10 @@ static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_
 	if (ret <= 0)
 		return ret;
 
-	lock_page(page);
 	vaddr_new = kmap_atomic(page);
 	vaddr &= ~PAGE_MASK;
 	memcpy(opcode, vaddr_new + vaddr, UPROBE_SWBP_INSN_SIZE);
 	kunmap_atomic(vaddr_new);
-	unlock_page(page);
 
 	put_page(page);
 
@@ -334,7 +332,7 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
 	 */
 	result = is_swbp_at_addr(mm, vaddr);
 	if (result == 1)
-		return -EEXIST;
+		return 0;
 
 	if (result)
 		return result;
@@ -347,24 +345,22 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
  * @mm: the probed process address space.
  * @auprobe: arch specific probepoint information.
  * @vaddr: the virtual address to insert the opcode.
- * @verify: if true, verify existance of breakpoint instruction.
  *
  * For mm @mm, restore the original opcode (opcode) at @vaddr.
  * Return 0 (success) or a negative errno.
  */
 int __weak
-set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, bool verify)
+set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	if (verify) {
-		int result;
+	int result;
+
+	result = is_swbp_at_addr(mm, vaddr);
+	if (!result)
+		return -EINVAL;
 
-		result = is_swbp_at_addr(mm, vaddr);
-		if (!result)
-			return -EINVAL;
+	if (result != 1)
+		return result;
 
-		if (result != 1)
-			return result;
-	}
 	return write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
 }
 
@@ -415,11 +411,10 @@ static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset)
 static struct uprobe *find_uprobe(struct inode *inode, loff_t offset)
 {
 	struct uprobe *uprobe;
-	unsigned long flags;
 
-	spin_lock_irqsave(&uprobes_treelock, flags);
+	spin_lock(&uprobes_treelock);
 	uprobe = __find_uprobe(inode, offset);
-	spin_unlock_irqrestore(&uprobes_treelock, flags);
+	spin_unlock(&uprobes_treelock);
 
 	return uprobe;
 }
@@ -466,12 +461,11 @@ static struct uprobe *__insert_uprobe(struct uprobe *uprobe)
  */
 static struct uprobe *insert_uprobe(struct uprobe *uprobe)
 {
-	unsigned long flags;
 	struct uprobe *u;
 
-	spin_lock_irqsave(&uprobes_treelock, flags);
+	spin_lock(&uprobes_treelock);
 	u = __insert_uprobe(uprobe);
-	spin_unlock_irqrestore(&uprobes_treelock, flags);
+	spin_unlock(&uprobes_treelock);
 
 	/* For now assume that the instruction need not be single-stepped */
 	uprobe->flags |= UPROBE_SKIP_SSTEP;
@@ -649,6 +643,7 @@ static int
 install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 			struct vm_area_struct *vma, unsigned long vaddr)
 {
+	bool first_uprobe;
 	int ret;
 
 	/*
@@ -659,7 +654,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	 * Hence behave as if probe already existed.
 	 */
 	if (!uprobe->consumers)
-		return -EEXIST;
+		return 0;
 
 	if (!(uprobe->flags & UPROBE_COPY_INSN)) {
 		ret = copy_insn(uprobe, vma->vm_file);
@@ -681,17 +676,18 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 	}
 
 	/*
-	 * Ideally, should be updating the probe count after the breakpoint
-	 * has been successfully inserted. However a thread could hit the
-	 * breakpoint we just inserted even before the probe count is
-	 * incremented. If this is the first breakpoint placed, breakpoint
-	 * notifier might ignore uprobes and pass the trap to the thread.
-	 * Hence increment before and decrement on failure.
+	 * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(),
+	 * the task can hit this breakpoint right after __replace_page().
 	 */
-	atomic_inc(&mm->uprobes_state.count);
+	first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags);
+	if (first_uprobe)
+		set_bit(MMF_HAS_UPROBES, &mm->flags);
+
 	ret = set_swbp(&uprobe->arch, mm, vaddr);
-	if (ret)
-		atomic_dec(&mm->uprobes_state.count);
+	if (!ret)
+		clear_bit(MMF_RECALC_UPROBES, &mm->flags);
+	else if (first_uprobe)
+		clear_bit(MMF_HAS_UPROBES, &mm->flags);
 
 	return ret;
 }
@@ -699,8 +695,12 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
 static void
 remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	if (!set_orig_insn(&uprobe->arch, mm, vaddr, true))
-		atomic_dec(&mm->uprobes_state.count);
+	/* can happen if uprobe_register() fails */
+	if (!test_bit(MMF_HAS_UPROBES, &mm->flags))
+		return;
+
+	set_bit(MMF_RECALC_UPROBES, &mm->flags);
+	set_orig_insn(&uprobe->arch, mm, vaddr);
 }
 
 /*
@@ -710,11 +710,9 @@ remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vad
  */
 static void delete_uprobe(struct uprobe *uprobe)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&uprobes_treelock, flags);
+	spin_lock(&uprobes_treelock);
 	rb_erase(&uprobe->rb_node, &uprobes_tree);
-	spin_unlock_irqrestore(&uprobes_treelock, flags);
+	spin_unlock(&uprobes_treelock);
 	iput(uprobe->inode);
 	put_uprobe(uprobe);
 	atomic_dec(&uprobe_events);
@@ -831,17 +829,11 @@ 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) {
+		if (is_register)
 			err = install_breakpoint(uprobe, mm, vma, info->vaddr);
-			/*
-			 * We can race against uprobe_mmap(), see the
-			 * comment near uprobe_hash().
-			 */
-			if (err == -EEXIST)
-				err = 0;
-		} else {
+		else
 			remove_breakpoint(uprobe, mm, info->vaddr);
-		}
+
  unlock:
 		up_write(&mm->mmap_sem);
  free:
@@ -908,7 +900,8 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 	}
 
 	mutex_unlock(uprobes_hash(inode));
-	put_uprobe(uprobe);
+	if (uprobe)
+		put_uprobe(uprobe);
 
 	return ret;
 }
@@ -978,7 +971,6 @@ static void build_probe_list(struct inode *inode,
 				struct list_head *head)
 {
 	loff_t min, max;
-	unsigned long flags;
 	struct rb_node *n, *t;
 	struct uprobe *u;
 
@@ -986,7 +978,7 @@ static void build_probe_list(struct inode *inode,
 	min = vaddr_to_offset(vma, start);
 	max = min + (end - start) - 1;
 
-	spin_lock_irqsave(&uprobes_treelock, flags);
+	spin_lock(&uprobes_treelock);
 	n = find_node_in_range(inode, min, max);
 	if (n) {
 		for (t = n; t; t = rb_prev(t)) {
@@ -1004,27 +996,20 @@ static void build_probe_list(struct inode *inode,
 			atomic_inc(&u->ref);
 		}
 	}
-	spin_unlock_irqrestore(&uprobes_treelock, flags);
+	spin_unlock(&uprobes_treelock);
 }
 
 /*
- * Called from mmap_region.
- * called with mm->mmap_sem acquired.
+ * Called from mmap_region/vma_adjust with mm->mmap_sem acquired.
  *
- * Return -ve no if we fail to insert probes and we cannot
- * bail-out.
- * Return 0 otherwise. i.e:
- *
- *	- successful insertion of probes
- *	- (or) no possible probes to be inserted.
- *	- (or) insertion of probes failed but we can bail-out.
+ * Currently we ignore all errors and always return 0, the callers
+ * can't handle the failure anyway.
  */
 int uprobe_mmap(struct vm_area_struct *vma)
 {
 	struct list_head tmp_list;
 	struct uprobe *uprobe, *u;
 	struct inode *inode;
-	int ret, count;
 
 	if (!atomic_read(&uprobe_events) || !valid_vma(vma, true))
 		return 0;
@@ -1036,44 +1021,35 @@ 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);
 
-	ret = 0;
-	count = 0;
-
 	list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
-		if (!ret) {
+		if (!fatal_signal_pending(current)) {
 			unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
-
-			ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
-			/*
-			 * We can race against uprobe_register(), see the
-			 * comment near uprobe_hash().
-			 */
-			if (ret == -EEXIST) {
-				ret = 0;
-
-				if (!is_swbp_at_addr(vma->vm_mm, vaddr))
-					continue;
-
-				/*
-				 * Unable to insert a breakpoint, but
-				 * breakpoint lies underneath. Increment the
-				 * probe count.
-				 */
-				atomic_inc(&vma->vm_mm->uprobes_state.count);
-			}
-
-			if (!ret)
-				count++;
+			install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
 		}
 		put_uprobe(uprobe);
 	}
-
 	mutex_unlock(uprobes_mmap_hash(inode));
 
-	if (ret)
-		atomic_sub(count, &vma->vm_mm->uprobes_state.count);
+	return 0;
+}
 
-	return ret;
+static bool
+vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long end)
+{
+	loff_t min, max;
+	struct inode *inode;
+	struct rb_node *n;
+
+	inode = vma->vm_file->f_mapping->host;
+
+	min = vaddr_to_offset(vma, start);
+	max = min + (end - start) - 1;
+
+	spin_lock(&uprobes_treelock);
+	n = find_node_in_range(inode, min, max);
+	spin_unlock(&uprobes_treelock);
+
+	return !!n;
 }
 
 /*
@@ -1081,37 +1057,18 @@ int uprobe_mmap(struct vm_area_struct *vma)
  */
 void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
-	struct list_head tmp_list;
-	struct uprobe *uprobe, *u;
-	struct inode *inode;
-
 	if (!atomic_read(&uprobe_events) || !valid_vma(vma, false))
 		return;
 
 	if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */
 		return;
 
-	if (!atomic_read(&vma->vm_mm->uprobes_state.count))
-		return;
-
-	inode = vma->vm_file->f_mapping->host;
-	if (!inode)
+	if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags) ||
+	     test_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags))
 		return;
 
-	mutex_lock(uprobes_mmap_hash(inode));
-	build_probe_list(inode, vma, start, end, &tmp_list);
-
-	list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
-		unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
-		/*
-		 * An unregister could have removed the probe before
-		 * unmap. So check before we decrement the count.
-		 */
-		if (is_swbp_at_addr(vma->vm_mm, vaddr) == 1)
-			atomic_dec(&vma->vm_mm->uprobes_state.count);
-		put_uprobe(uprobe);
-	}
-	mutex_unlock(uprobes_mmap_hash(inode));
+	if (vma_has_uprobes(vma, start, end))
+		set_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags);
 }
 
 /* Slot allocation for XOL */
@@ -1213,13 +1170,15 @@ void uprobe_clear_state(struct mm_struct *mm)
 	kfree(area);
 }
 
-/*
- * uprobe_reset_state - Free the area allocated for slots.
- */
-void uprobe_reset_state(struct mm_struct *mm)
+void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
 {
-	mm->uprobes_state.xol_area = NULL;
-	atomic_set(&mm->uprobes_state.count, 0);
+	newmm->uprobes_state.xol_area = NULL;
+
+	if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) {
+		set_bit(MMF_HAS_UPROBES, &newmm->flags);
+		/* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */
+		set_bit(MMF_RECALC_UPROBES, &newmm->flags);
+	}
 }
 
 /*
@@ -1437,6 +1396,25 @@ static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs)
 	return false;
 }
 
+static void mmf_recalc_uprobes(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		if (!valid_vma(vma, false))
+			continue;
+		/*
+		 * This is not strictly accurate, we can race with
+		 * uprobe_unregister() and see the already removed
+		 * uprobe if delete_uprobe() was not yet called.
+		 */
+		if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end))
+			return;
+	}
+
+	clear_bit(MMF_HAS_UPROBES, &mm->flags);
+}
+
 static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
 {
 	struct mm_struct *mm = current->mm;
@@ -1458,11 +1436,24 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
 	} else {
 		*is_swbp = -EFAULT;
 	}
+
+	if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags))
+		mmf_recalc_uprobes(mm);
 	up_read(&mm->mmap_sem);
 
 	return uprobe;
 }
 
+void __weak arch_uprobe_enable_step(struct arch_uprobe *arch)
+{
+	user_enable_single_step(current);
+}
+
+void __weak arch_uprobe_disable_step(struct arch_uprobe *arch)
+{
+	user_disable_single_step(current);
+}
+
 /*
  * Run handler and ask thread to singlestep.
  * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
@@ -1509,7 +1500,7 @@ static void handle_swbp(struct pt_regs *regs)
 
 	utask->state = UTASK_SSTEP;
 	if (!pre_ssout(uprobe, regs, bp_vaddr)) {
-		user_enable_single_step(current);
+		arch_uprobe_enable_step(&uprobe->arch);
 		return;
 	}
 
@@ -1518,17 +1509,15 @@ cleanup_ret:
 		utask->active_uprobe = NULL;
 		utask->state = UTASK_RUNNING;
 	}
-	if (uprobe) {
-		if (!(uprobe->flags & UPROBE_SKIP_SSTEP))
+	if (!(uprobe->flags & UPROBE_SKIP_SSTEP))
 
-			/*
-			 * cannot singlestep; cannot skip instruction;
-			 * re-execute the instruction.
-			 */
-			instruction_pointer_set(regs, bp_vaddr);
+		/*
+		 * cannot singlestep; cannot skip instruction;
+		 * re-execute the instruction.
+		 */
+		instruction_pointer_set(regs, bp_vaddr);
 
-		put_uprobe(uprobe);
-	}
+	put_uprobe(uprobe);
 }
 
 /*
@@ -1547,10 +1536,10 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
 	else
 		WARN_ON_ONCE(1);
 
+	arch_uprobe_disable_step(&uprobe->arch);
 	put_uprobe(uprobe);
 	utask->active_uprobe = NULL;
 	utask->state = UTASK_RUNNING;
-	user_disable_single_step(current);
 	xol_free_insn_slot(current);
 
 	spin_lock_irq(&current->sighand->siglock);
@@ -1589,8 +1578,7 @@ int uprobe_pre_sstep_notifier(struct pt_regs *regs)
 {
 	struct uprobe_task *utask;
 
-	if (!current->mm || !atomic_read(&current->mm->uprobes_state.count))
-		/* task is currently not uprobed */
+	if (!current->mm || !test_bit(MMF_HAS_UPROBES, &current->mm->flags))
 		return 0;
 
 	utask = current->utask;
diff --git a/kernel/fork.c b/kernel/fork.c
index 2c8857e..2343c9e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -353,6 +353,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 
 	down_write(&oldmm->mmap_sem);
 	flush_cache_dup_mm(oldmm);
+	uprobe_dup_mmap(oldmm, mm);
 	/*
 	 * Not linked in yet - no deadlock potential:
 	 */
@@ -454,9 +455,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 
 		if (retval)
 			goto out;
-
-		if (file)
-			uprobe_mmap(tmp);
 	}
 	/* a new mm has just been created */
 	arch_dup_mmap(oldmm, mm);
@@ -839,8 +837,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	mm->pmd_huge_pte = NULL;
 #endif
-	uprobe_reset_state(mm);
-
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index c62b854..098f396 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -561,9 +561,9 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
 {
 	LIST_HEAD(free_list);
 
+	mutex_lock(&kprobe_mutex);
 	/* Lock modules while optimizing kprobes */
 	mutex_lock(&module_mutex);
-	mutex_lock(&kprobe_mutex);
 
 	/*
 	 * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed)
@@ -586,8 +586,8 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
 	/* Step 4: Free cleaned kprobes after quiesence period */
 	do_free_cleaned_kprobes(&free_list);
 
-	mutex_unlock(&kprobe_mutex);
 	mutex_unlock(&module_mutex);
+	mutex_unlock(&kprobe_mutex);
 
 	/* Step 5: Kick optimizer again if needed */
 	if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list))
@@ -759,20 +759,32 @@ static __kprobes void try_to_optimize_kprobe(struct kprobe *p)
 	struct kprobe *ap;
 	struct optimized_kprobe *op;
 
+	/* Impossible to optimize ftrace-based kprobe */
+	if (kprobe_ftrace(p))
+		return;
+
+	/* For preparing optimization, jump_label_text_reserved() is called */
+	jump_label_lock();
+	mutex_lock(&text_mutex);
+
 	ap = alloc_aggr_kprobe(p);
 	if (!ap)
-		return;
+		goto out;
 
 	op = container_of(ap, struct optimized_kprobe, kp);
 	if (!arch_prepared_optinsn(&op->optinsn)) {
 		/* If failed to setup optimizing, fallback to kprobe */
 		arch_remove_optimized_kprobe(op);
 		kfree(op);
-		return;
+		goto out;
 	}
 
 	init_aggr_kprobe(ap, p);
-	optimize_kprobe(ap);
+	optimize_kprobe(ap);	/* This just kicks optimizer thread */
+
+out:
+	mutex_unlock(&text_mutex);
+	jump_label_unlock();
 }
 
 #ifdef CONFIG_SYSCTL
@@ -907,9 +919,64 @@ static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
 }
 #endif /* CONFIG_OPTPROBES */
 
+#ifdef KPROBES_CAN_USE_FTRACE
+static struct ftrace_ops kprobe_ftrace_ops __read_mostly = {
+	.func = kprobe_ftrace_handler,
+	.flags = FTRACE_OPS_FL_SAVE_REGS,
+};
+static int kprobe_ftrace_enabled;
+
+/* Must ensure p->addr is really on ftrace */
+static int __kprobes prepare_kprobe(struct kprobe *p)
+{
+	if (!kprobe_ftrace(p))
+		return arch_prepare_kprobe(p);
+
+	return arch_prepare_kprobe_ftrace(p);
+}
+
+/* Caller must lock kprobe_mutex */
+static void __kprobes arm_kprobe_ftrace(struct kprobe *p)
+{
+	int ret;
+
+	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
+				   (unsigned long)p->addr, 0, 0);
+	WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+	kprobe_ftrace_enabled++;
+	if (kprobe_ftrace_enabled == 1) {
+		ret = register_ftrace_function(&kprobe_ftrace_ops);
+		WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret);
+	}
+}
+
+/* Caller must lock kprobe_mutex */
+static void __kprobes disarm_kprobe_ftrace(struct kprobe *p)
+{
+	int ret;
+
+	kprobe_ftrace_enabled--;
+	if (kprobe_ftrace_enabled == 0) {
+		ret = unregister_ftrace_function(&kprobe_ftrace_ops);
+		WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret);
+	}
+	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
+			   (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 */
+#define prepare_kprobe(p)	arch_prepare_kprobe(p)
+#define arm_kprobe_ftrace(p)	do {} while (0)
+#define disarm_kprobe_ftrace(p)	do {} while (0)
+#endif
+
 /* Arm a kprobe with text_mutex */
 static void __kprobes arm_kprobe(struct kprobe *kp)
 {
+	if (unlikely(kprobe_ftrace(kp))) {
+		arm_kprobe_ftrace(kp);
+		return;
+	}
 	/*
 	 * Here, since __arm_kprobe() doesn't use stop_machine(),
 	 * this doesn't cause deadlock on text_mutex. So, we don't
@@ -921,11 +988,15 @@ static void __kprobes arm_kprobe(struct kprobe *kp)
 }
 
 /* Disarm a kprobe with text_mutex */
-static void __kprobes disarm_kprobe(struct kprobe *kp)
+static void __kprobes disarm_kprobe(struct kprobe *kp, bool reopt)
 {
+	if (unlikely(kprobe_ftrace(kp))) {
+		disarm_kprobe_ftrace(kp);
+		return;
+	}
 	/* Ditto */
 	mutex_lock(&text_mutex);
-	__disarm_kprobe(kp, true);
+	__disarm_kprobe(kp, reopt);
 	mutex_unlock(&text_mutex);
 }
 
@@ -1144,12 +1215,6 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 	if (p->post_handler && !ap->post_handler)
 		ap->post_handler = aggr_post_handler;
 
-	if (kprobe_disabled(ap) && !kprobe_disabled(p)) {
-		ap->flags &= ~KPROBE_FLAG_DISABLED;
-		if (!kprobes_all_disarmed)
-			/* Arm the breakpoint again. */
-			__arm_kprobe(ap);
-	}
 	return 0;
 }
 
@@ -1189,11 +1254,22 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p,
 	int ret = 0;
 	struct kprobe *ap = orig_p;
 
+	/* For preparing optimization, jump_label_text_reserved() is called */
+	jump_label_lock();
+	/*
+	 * Get online CPUs to avoid text_mutex deadlock.with stop machine,
+	 * which is invoked by unoptimize_kprobe() in add_new_kprobe()
+	 */
+	get_online_cpus();
+	mutex_lock(&text_mutex);
+
 	if (!kprobe_aggrprobe(orig_p)) {
 		/* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */
 		ap = alloc_aggr_kprobe(orig_p);
-		if (!ap)
-			return -ENOMEM;
+		if (!ap) {
+			ret = -ENOMEM;
+			goto out;
+		}
 		init_aggr_kprobe(ap, orig_p);
 	} else if (kprobe_unused(ap))
 		/* This probe is going to die. Rescue it */
@@ -1213,7 +1289,7 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p,
 			 * free aggr_probe. It will be used next time, or
 			 * freed by unregister_kprobe.
 			 */
-			return ret;
+			goto out;
 
 		/* Prepare optimized instructions if possible. */
 		prepare_optimized_kprobe(ap);
@@ -1228,7 +1304,20 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p,
 
 	/* Copy ap's insn slot to p */
 	copy_kprobe(ap, p);
-	return add_new_kprobe(ap, p);
+	ret = add_new_kprobe(ap, p);
+
+out:
+	mutex_unlock(&text_mutex);
+	put_online_cpus();
+	jump_label_unlock();
+
+	if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) {
+		ap->flags &= ~KPROBE_FLAG_DISABLED;
+		if (!kprobes_all_disarmed)
+			/* Arm the breakpoint again. */
+			arm_kprobe(ap);
+	}
+	return ret;
 }
 
 static int __kprobes in_kprobes_functions(unsigned long addr)
@@ -1313,71 +1402,96 @@ static inline int check_kprobe_rereg(struct kprobe *p)
 	return ret;
 }
 
-int __kprobes register_kprobe(struct kprobe *p)
+static __kprobes int check_kprobe_address_safe(struct kprobe *p,
+					       struct module **probed_mod)
 {
 	int ret = 0;
-	struct kprobe *old_p;
-	struct module *probed_mod;
-	kprobe_opcode_t *addr;
-
-	addr = kprobe_addr(p);
-	if (IS_ERR(addr))
-		return PTR_ERR(addr);
-	p->addr = addr;
+	unsigned long ftrace_addr;
 
-	ret = check_kprobe_rereg(p);
-	if (ret)
-		return ret;
+	/*
+	 * If the address is located on a ftrace nop, set the
+	 * breakpoint to the following instruction.
+	 */
+	ftrace_addr = ftrace_location((unsigned long)p->addr);
+	if (ftrace_addr) {
+#ifdef KPROBES_CAN_USE_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 */
+		return -EINVAL;
+#endif
+	}
 
 	jump_label_lock();
 	preempt_disable();
+
+	/* Ensure it is not in reserved area nor out of text */
 	if (!kernel_text_address((unsigned long) p->addr) ||
 	    in_kprobes_functions((unsigned long) p->addr) ||
-	    ftrace_text_reserved(p->addr, p->addr) ||
 	    jump_label_text_reserved(p->addr, p->addr)) {
 		ret = -EINVAL;
-		goto cannot_probe;
+		goto out;
 	}
 
-	/* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */
-	p->flags &= KPROBE_FLAG_DISABLED;
-
-	/*
-	 * Check if are we probing a module.
-	 */
-	probed_mod = __module_text_address((unsigned long) p->addr);
-	if (probed_mod) {
-		/* Return -ENOENT if fail. */
-		ret = -ENOENT;
+	/* Check if are we probing a module */
+	*probed_mod = __module_text_address((unsigned long) p->addr);
+	if (*probed_mod) {
 		/*
 		 * We must hold a refcount of the probed module while updating
 		 * its code to prohibit unexpected unloading.
 		 */
-		if (unlikely(!try_module_get(probed_mod)))
-			goto cannot_probe;
+		if (unlikely(!try_module_get(*probed_mod))) {
+			ret = -ENOENT;
+			goto out;
+		}
 
 		/*
 		 * If the module freed .init.text, we couldn't insert
 		 * kprobes in there.
 		 */
-		if (within_module_init((unsigned long)p->addr, probed_mod) &&
-		    probed_mod->state != MODULE_STATE_COMING) {
-			module_put(probed_mod);
-			goto cannot_probe;
+		if (within_module_init((unsigned long)p->addr, *probed_mod) &&
+		    (*probed_mod)->state != MODULE_STATE_COMING) {
+			module_put(*probed_mod);
+			*probed_mod = NULL;
+			ret = -ENOENT;
 		}
-		/* ret will be updated by following code */
 	}
+out:
 	preempt_enable();
 	jump_label_unlock();
 
+	return ret;
+}
+
+int __kprobes register_kprobe(struct kprobe *p)
+{
+	int ret;
+	struct kprobe *old_p;
+	struct module *probed_mod;
+	kprobe_opcode_t *addr;
+
+	/* Adjust probe address from symbol */
+	addr = kprobe_addr(p);
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
+	p->addr = addr;
+
+	ret = check_kprobe_rereg(p);
+	if (ret)
+		return ret;
+
+	/* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */
+	p->flags &= KPROBE_FLAG_DISABLED;
 	p->nmissed = 0;
 	INIT_LIST_HEAD(&p->list);
-	mutex_lock(&kprobe_mutex);
 
-	jump_label_lock(); /* needed to call jump_label_text_reserved() */
+	ret = check_kprobe_address_safe(p, &probed_mod);
+	if (ret)
+		return ret;
 
-	get_online_cpus();	/* For avoiding text_mutex deadlock. */
-	mutex_lock(&text_mutex);
+	mutex_lock(&kprobe_mutex);
 
 	old_p = get_kprobe(p->addr);
 	if (old_p) {
@@ -1386,7 +1500,9 @@ int __kprobes register_kprobe(struct kprobe *p)
 		goto out;
 	}
 
-	ret = arch_prepare_kprobe(p);
+	mutex_lock(&text_mutex);	/* Avoiding text modification */
+	ret = prepare_kprobe(p);
+	mutex_unlock(&text_mutex);
 	if (ret)
 		goto out;
 
@@ -1395,26 +1511,18 @@ int __kprobes register_kprobe(struct kprobe *p)
 		       &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);
 
 	if (!kprobes_all_disarmed && !kprobe_disabled(p))
-		__arm_kprobe(p);
+		arm_kprobe(p);
 
 	/* Try to optimize kprobe */
 	try_to_optimize_kprobe(p);
 
 out:
-	mutex_unlock(&text_mutex);
-	put_online_cpus();
-	jump_label_unlock();
 	mutex_unlock(&kprobe_mutex);
 
 	if (probed_mod)
 		module_put(probed_mod);
 
 	return ret;
-
-cannot_probe:
-	preempt_enable();
-	jump_label_unlock();
-	return ret;
 }
 EXPORT_SYMBOL_GPL(register_kprobe);
 
@@ -1451,7 +1559,7 @@ static struct kprobe *__kprobes __disable_kprobe(struct kprobe *p)
 
 		/* Try to disarm and disable this/parent probe */
 		if (p == orig_p || aggr_kprobe_disabled(orig_p)) {
-			disarm_kprobe(orig_p);
+			disarm_kprobe(orig_p, true);
 			orig_p->flags |= KPROBE_FLAG_DISABLED;
 		}
 	}
@@ -2049,10 +2157,11 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
 
 	if (!pp)
 		pp = p;
-	seq_printf(pi, "%s%s%s\n",
+	seq_printf(pi, "%s%s%s%s\n",
 		(kprobe_gone(p) ? "[GONE]" : ""),
 		((kprobe_disabled(p) && !kprobe_gone(p)) ?  "[DISABLED]" : ""),
-		(kprobe_optimized(pp) ? "[OPTIMIZED]" : ""));
+		(kprobe_optimized(pp) ? "[OPTIMIZED]" : ""),
+		(kprobe_ftrace(pp) ? "[FTRACE]" : ""));
 }
 
 static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
@@ -2131,14 +2240,12 @@ static void __kprobes arm_all_kprobes(void)
 		goto already_enabled;
 
 	/* Arming kprobes doesn't optimize kprobe itself */
-	mutex_lock(&text_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		hlist_for_each_entry_rcu(p, node, head, hlist)
 			if (!kprobe_disabled(p))
-				__arm_kprobe(p);
+				arm_kprobe(p);
 	}
-	mutex_unlock(&text_mutex);
 
 	kprobes_all_disarmed = false;
 	printk(KERN_INFO "Kprobes globally enabled\n");
@@ -2166,15 +2273,13 @@ static void __kprobes disarm_all_kprobes(void)
 	kprobes_all_disarmed = true;
 	printk(KERN_INFO "Kprobes globally disabled\n");
 
-	mutex_lock(&text_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		hlist_for_each_entry_rcu(p, node, head, hlist) {
 			if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
-				__disarm_kprobe(p, false);
+				disarm_kprobe(p, false);
 		}
 	}
-	mutex_unlock(&text_mutex);
 	mutex_unlock(&kprobe_mutex);
 
 	/* Wait for disarming all kprobes by optimizer */
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 8c4c070..4cea4f4 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -49,6 +49,11 @@ config HAVE_SYSCALL_TRACEPOINTS
 	help
 	  See Documentation/trace/ftrace-design.txt
 
+config HAVE_FENTRY
+	bool
+	help
+	  Arch supports the gcc options -pg with -mfentry
+
 config HAVE_C_RECORDMCOUNT
 	bool
 	help
@@ -57,8 +62,12 @@ config HAVE_C_RECORDMCOUNT
 config TRACER_MAX_TRACE
 	bool
 
+config TRACE_CLOCK
+	bool
+
 config RING_BUFFER
 	bool
+	select TRACE_CLOCK
 
 config FTRACE_NMI_ENTER
        bool
@@ -109,6 +118,7 @@ config TRACING
 	select NOP_TRACER
 	select BINARY_PRINTF
 	select EVENT_TRACING
+	select TRACE_CLOCK
 
 config GENERIC_TRACER
 	bool
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index b831087..d7e2068 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -5,10 +5,12 @@ ifdef CONFIG_FUNCTION_TRACER
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
 KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS))
 
+ifdef CONFIG_FTRACE_SELFTEST
 # selftest needs instrumentation
 CFLAGS_trace_selftest_dynamic.o = -pg
 obj-y += trace_selftest_dynamic.o
 endif
+endif
 
 # If unlikely tracing is enabled, do not trace these files
 ifdef CONFIG_TRACING_BRANCHES
@@ -17,11 +19,7 @@ endif
 
 CFLAGS_trace_events_filter.o := -I$(src)
 
-#
-# Make the trace clocks available generally: it's infrastructure
-# relied on by ptrace for example:
-#
-obj-y += trace_clock.o
+obj-$(CONFIG_TRACE_CLOCK) += trace_clock.o
 
 obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
 obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b4f20fb..9dcf15d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -64,12 +64,20 @@
 
 #define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL)
 
+static struct ftrace_ops ftrace_list_end __read_mostly = {
+	.func		= ftrace_stub,
+	.flags		= FTRACE_OPS_FL_RECURSION_SAFE,
+};
+
 /* ftrace_enabled is a method to turn ftrace on or off */
 int ftrace_enabled __read_mostly;
 static int last_ftrace_enabled;
 
 /* Quick disabling of function tracer. */
-int function_trace_stop;
+int function_trace_stop __read_mostly;
+
+/* Current function tracing op */
+struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
 
 /* List for set_ftrace_pid's pids. */
 LIST_HEAD(ftrace_pids);
@@ -86,22 +94,43 @@ static int ftrace_disabled __read_mostly;
 
 static DEFINE_MUTEX(ftrace_lock);
 
-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_control_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;
 static struct ftrace_ops control_ops;
 
-static void
-ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
+#if ARCH_SUPPORTS_FTRACE_OPS
+static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+				 struct ftrace_ops *op, struct pt_regs *regs);
+#else
+/* See comment below, where ftrace_ops_list_func is defined */
+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
+
+/**
+ * ftrace_nr_registered_ops - return number of ops registered
+ *
+ * Returns the number of ftrace_ops registered and tracing functions
+ */
+int ftrace_nr_registered_ops(void)
+{
+	struct ftrace_ops *ops;
+	int cnt = 0;
+
+	mutex_lock(&ftrace_lock);
+
+	for (ops = ftrace_ops_list;
+	     ops != &ftrace_list_end; ops = ops->next)
+		cnt++;
+
+	mutex_unlock(&ftrace_lock);
+
+	return cnt;
+}
 
 /*
  * Traverse the ftrace_global_list, invoking all entries.  The reason that we
@@ -112,29 +141,29 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
  *
  * Silly Alpha and silly pointer-speculation compiler optimizations!
  */
-static void ftrace_global_list_func(unsigned long ip,
-				    unsigned long parent_ip)
+static void
+ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
+			struct ftrace_ops *op, struct pt_regs *regs)
 {
-	struct ftrace_ops *op;
-
 	if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
 		return;
 
 	trace_recursion_set(TRACE_GLOBAL_BIT);
 	op = rcu_dereference_raw(ftrace_global_list); /*see above*/
 	while (op != &ftrace_list_end) {
-		op->func(ip, parent_ip);
+		op->func(ip, parent_ip, op, regs);
 		op = rcu_dereference_raw(op->next); /*see above*/
 	};
 	trace_recursion_clear(TRACE_GLOBAL_BIT);
 }
 
-static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip)
+static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
+			    struct ftrace_ops *op, struct pt_regs *regs)
 {
 	if (!test_tsk_trace_trace(current))
 		return;
 
-	ftrace_pid_function(ip, parent_ip);
+	ftrace_pid_function(ip, parent_ip, op, regs);
 }
 
 static void set_ftrace_pid_function(ftrace_func_t func)
@@ -153,25 +182,9 @@ static void set_ftrace_pid_function(ftrace_func_t func)
 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;
 }
 
-#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-/*
- * For those archs that do not test ftrace_trace_stop in their
- * mcount call site, we need to do it from C.
- */
-static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
-{
-	if (function_trace_stop)
-		return;
-
-	__ftrace_trace_function(ip, parent_ip);
-}
-#endif
-
 static void control_ops_disable_all(struct ftrace_ops *ops)
 {
 	int cpu;
@@ -230,28 +243,27 @@ static void update_ftrace_function(void)
 
 	/*
 	 * If we are at the end of the list and this ops is
-	 * not dynamic, then have the mcount trampoline call
-	 * the function directly
+	 * recursion safe and not dynamic and the arch supports passing ops,
+	 * then have the mcount trampoline call the function directly.
 	 */
 	if (ftrace_ops_list == &ftrace_list_end ||
 	    (ftrace_ops_list->next == &ftrace_list_end &&
-	     !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC)))
+	     !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) &&
+	     (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) &&
+	     !FTRACE_FORCE_LIST_FUNC)) {
+		/* Set the ftrace_ops that the arch callback uses */
+		if (ftrace_ops_list == &global_ops)
+			function_trace_op = ftrace_global_list;
+		else
+			function_trace_op = ftrace_ops_list;
 		func = ftrace_ops_list->func;
-	else
+	} else {
+		/* Just use the default ftrace_ops */
+		function_trace_op = &ftrace_list_end;
 		func = ftrace_ops_list_func;
+	}
 
-#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 =
-		(func == ftrace_stub) ? func : ftrace_test_stop_func;
-#endif
 }
 
 static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
@@ -325,6 +337,20 @@ 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
+	/*
+	 * 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.
+	 * Setting SAVE_REGS_IF_SUPPORTED makes SAVE_REGS irrelevant.
+	 */
+	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS &&
+	    !(ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED))
+		return -EINVAL;
+
+	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED)
+		ops->flags |= FTRACE_OPS_FL_SAVE_REGS;
+#endif
+
 	if (!core_kernel_data((unsigned long)ops))
 		ops->flags |= FTRACE_OPS_FL_DYNAMIC;
 
@@ -773,7 +799,8 @@ ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)
 }
 
 static void
-function_profile_call(unsigned long ip, unsigned long parent_ip)
+function_profile_call(unsigned long ip, unsigned long parent_ip,
+		      struct ftrace_ops *ops, struct pt_regs *regs)
 {
 	struct ftrace_profile_stat *stat;
 	struct ftrace_profile *rec;
@@ -803,7 +830,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 static int profile_graph_entry(struct ftrace_graph_ent *trace)
 {
-	function_profile_call(trace->func, 0);
+	function_profile_call(trace->func, 0, NULL, NULL);
 	return 1;
 }
 
@@ -863,6 +890,7 @@ static void unregister_ftrace_profiler(void)
 #else
 static struct ftrace_ops ftrace_profile_ops __read_mostly = {
 	.func		= function_profile_call,
+	.flags		= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static int register_ftrace_profiler(void)
@@ -1045,6 +1073,7 @@ static struct ftrace_ops global_ops = {
 	.func			= ftrace_stub,
 	.notrace_hash		= EMPTY_HASH,
 	.filter_hash		= EMPTY_HASH,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static DEFINE_MUTEX(ftrace_regex_lock);
@@ -1525,6 +1554,12 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			rec->flags++;
 			if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX))
 				return;
+			/*
+			 * If any ops wants regs saved for this function
+			 * then all ops will get saved regs.
+			 */
+			if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+				rec->flags |= FTRACE_FL_REGS;
 		} else {
 			if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0))
 				return;
@@ -1616,18 +1651,59 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 	if (enable && (rec->flags & ~FTRACE_FL_MASK))
 		flag = FTRACE_FL_ENABLED;
 
+	/*
+	 * If enabling and the REGS flag does not match the REGS_EN, then
+	 * do not ignore this record. Set flags to fail the compare against
+	 * ENABLED.
+	 */
+	if (flag &&
+	    (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN)))
+		flag |= FTRACE_FL_REGS;
+
 	/* If the state of this record hasn't changed, then do nothing */
 	if ((rec->flags & FTRACE_FL_ENABLED) == flag)
 		return FTRACE_UPDATE_IGNORE;
 
 	if (flag) {
-		if (update)
+		/* Save off if rec is being enabled (for return value) */
+		flag ^= rec->flags & FTRACE_FL_ENABLED;
+
+		if (update) {
 			rec->flags |= FTRACE_FL_ENABLED;
-		return FTRACE_UPDATE_MAKE_CALL;
+			if (flag & FTRACE_FL_REGS) {
+				if (rec->flags & FTRACE_FL_REGS)
+					rec->flags |= FTRACE_FL_REGS_EN;
+				else
+					rec->flags &= ~FTRACE_FL_REGS_EN;
+			}
+		}
+
+		/*
+		 * If this record is being updated from a nop, then
+		 *   return UPDATE_MAKE_CALL.
+		 * Otherwise, if the EN flag is set, then return
+		 *   UPDATE_MODIFY_CALL_REGS to tell the caller to convert
+		 *   from the non-save regs, to a save regs function.
+		 * Otherwise,
+		 *   return UPDATE_MODIFY_CALL to tell the caller to convert
+		 *   from the save regs, to a non-save regs function.
+		 */
+		if (flag & FTRACE_FL_ENABLED)
+			return FTRACE_UPDATE_MAKE_CALL;
+		else if (rec->flags & FTRACE_FL_REGS_EN)
+			return FTRACE_UPDATE_MODIFY_CALL_REGS;
+		else
+			return FTRACE_UPDATE_MODIFY_CALL;
 	}
 
-	if (update)
-		rec->flags &= ~FTRACE_FL_ENABLED;
+	if (update) {
+		/* If there's no more users, clear all flags */
+		if (!(rec->flags & ~FTRACE_FL_MASK))
+			rec->flags = 0;
+		else
+			/* Just disable the record (keep REGS state) */
+			rec->flags &= ~FTRACE_FL_ENABLED;
+	}
 
 	return FTRACE_UPDATE_MAKE_NOP;
 }
@@ -1662,13 +1738,17 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable)
 static int
 __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 {
+	unsigned long ftrace_old_addr;
 	unsigned long ftrace_addr;
 	int ret;
 
-	ftrace_addr = (unsigned long)FTRACE_ADDR;
-
 	ret = ftrace_update_record(rec, enable);
 
+	if (rec->flags & FTRACE_FL_REGS)
+		ftrace_addr = (unsigned long)FTRACE_REGS_ADDR;
+	else
+		ftrace_addr = (unsigned long)FTRACE_ADDR;
+
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
 		return 0;
@@ -1678,6 +1758,15 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 
 	case FTRACE_UPDATE_MAKE_NOP:
 		return ftrace_make_nop(NULL, rec, ftrace_addr);
+
+	case FTRACE_UPDATE_MODIFY_CALL_REGS:
+	case FTRACE_UPDATE_MODIFY_CALL:
+		if (rec->flags & FTRACE_FL_REGS)
+			ftrace_old_addr = (unsigned long)FTRACE_ADDR;
+		else
+			ftrace_old_addr = (unsigned long)FTRACE_REGS_ADDR;
+
+		return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr);
 	}
 
 	return -1; /* unknow ftrace bug */
@@ -1882,16 +1971,6 @@ static void ftrace_run_update_code(int command)
 	 */
 	arch_ftrace_update_code(command);
 
-#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--;
 
 	ret = ftrace_arch_code_modify_post_process();
@@ -2441,8 +2520,9 @@ static int t_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "%ps", (void *)rec->ip);
 	if (iter->flags & FTRACE_ITER_ENABLED)
-		seq_printf(m, " (%ld)",
-			   rec->flags & ~FTRACE_FL_MASK);
+		seq_printf(m, " (%ld)%s",
+			   rec->flags & ~FTRACE_FL_MASK,
+			   rec->flags & FTRACE_FL_REGS ? " R" : "");
 	seq_printf(m, "\n");
 
 	return 0;
@@ -2790,8 +2870,8 @@ static int __init ftrace_mod_cmd_init(void)
 }
 device_initcall(ftrace_mod_cmd_init);
 
-static void
-function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
+static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip,
+				      struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	struct ftrace_func_probe *entry;
 	struct hlist_head *hhd;
@@ -3162,8 +3242,27 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf,
 }
 
 static int
-ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
-		 int reset, int enable)
+ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
+{
+	struct ftrace_func_entry *entry;
+
+	if (!ftrace_location(ip))
+		return -EINVAL;
+
+	if (remove) {
+		entry = ftrace_lookup_ip(hash, ip);
+		if (!entry)
+			return -ENOENT;
+		free_hash_entry(hash, entry);
+		return 0;
+	}
+
+	return add_hash_entry(hash, ip);
+}
+
+static int
+ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
+		unsigned long ip, int remove, int reset, int enable)
 {
 	struct ftrace_hash **orig_hash;
 	struct ftrace_hash *hash;
@@ -3192,6 +3291,11 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 		ret = -EINVAL;
 		goto out_regex_unlock;
 	}
+	if (ip) {
+		ret = ftrace_match_addr(hash, ip, remove);
+		if (ret < 0)
+			goto out_regex_unlock;
+	}
 
 	mutex_lock(&ftrace_lock);
 	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
@@ -3208,6 +3312,37 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 	return ret;
 }
 
+static int
+ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove,
+		int reset, int enable)
+{
+	return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable);
+}
+
+/**
+ * ftrace_set_filter_ip - set a function to filter on in ftrace by address
+ * @ops - the ops to set the filter with
+ * @ip - the address to add to or remove from the filter.
+ * @remove - non zero to remove the ip from the filter
+ * @reset - non zero to reset all filters before applying this filter.
+ *
+ * Filters denote which functions should be enabled when tracing is enabled
+ * If @ip is NULL, it failes to update filter.
+ */
+int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
+			 int remove, int reset)
+{
+	return ftrace_set_addr(ops, ip, remove, reset, 1);
+}
+EXPORT_SYMBOL_GPL(ftrace_set_filter_ip);
+
+static int
+ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
+		 int reset, int enable)
+{
+	return ftrace_set_hash(ops, buf, len, 0, 0, reset, enable);
+}
+
 /**
  * ftrace_set_filter - set a function to filter on in ftrace
  * @ops - the ops to set the filter with
@@ -3912,6 +4047,7 @@ void __init ftrace_init(void)
 
 static struct ftrace_ops global_ops = {
 	.func			= ftrace_stub,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static int __init ftrace_nodyn_init(void)
@@ -3942,10 +4078,9 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 static void
-ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip)
+ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
+			struct ftrace_ops *op, struct pt_regs *regs)
 {
-	struct ftrace_ops *op;
-
 	if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT)))
 		return;
 
@@ -3959,7 +4094,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip)
 	while (op != &ftrace_list_end) {
 		if (!ftrace_function_local_disabled(op) &&
 		    ftrace_ops_test(op, ip))
-			op->func(ip, parent_ip);
+			op->func(ip, parent_ip, op, regs);
 
 		op = rcu_dereference_raw(op->next);
 	};
@@ -3969,13 +4104,18 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip)
 
 static struct ftrace_ops control_ops = {
 	.func = ftrace_ops_control_func,
+	.flags = FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
-static void
-ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
+static inline void
+__ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *ignored, struct pt_regs *regs)
 {
 	struct ftrace_ops *op;
 
+	if (function_trace_stop)
+		return;
+
 	if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT)))
 		return;
 
@@ -3988,13 +4128,39 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 	op = rcu_dereference_raw(ftrace_ops_list);
 	while (op != &ftrace_list_end) {
 		if (ftrace_ops_test(op, ip))
-			op->func(ip, parent_ip);
+			op->func(ip, parent_ip, op, regs);
 		op = rcu_dereference_raw(op->next);
 	};
 	preempt_enable_notrace();
 	trace_recursion_clear(TRACE_INTERNAL_BIT);
 }
 
+/*
+ * Some archs only support passing ip and parent_ip. Even though
+ * the list function ignores the op parameter, we do not want any
+ * C side effects, where a function is called without the caller
+ * sending a third parameter.
+ * 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.
+ * An architecture can pass partial regs with ftrace_ops and still
+ * set the ARCH_SUPPORT_FTARCE_OPS.
+ */
+#if ARCH_SUPPORTS_FTRACE_OPS
+static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+				 struct ftrace_ops *op, struct pt_regs *regs)
+{
+	__ftrace_ops_list_func(ip, parent_ip, NULL, regs);
+}
+#else
+static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
+{
+	__ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
+}
+#endif
+
 static void clear_ftrace_swapper(void)
 {
 	struct task_struct *p;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 49491fa..b32ed0e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2816,7 +2816,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_enable);
  * to the buffer after this will fail and return NULL.
  *
  * This is different than ring_buffer_record_disable() as
- * it works like an on/off switch, where as the disable() verison
+ * it works like an on/off switch, where as the disable() version
  * must be paired with a enable().
  */
 void ring_buffer_record_off(struct ring_buffer *buffer)
@@ -2839,7 +2839,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_off);
  * ring_buffer_record_off().
  *
  * This is different than ring_buffer_record_enable() as
- * it works like an on/off switch, where as the enable() verison
+ * it works like an on/off switch, where as the enable() version
  * must be paired with a disable().
  */
 void ring_buffer_record_on(struct ring_buffer *buffer)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5c38c81..1ec5c1d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -328,7 +328,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
 	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |
-	TRACE_ITER_IRQ_INFO;
+	TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS;
 
 static int trace_stop_count;
 static DEFINE_RAW_SPINLOCK(tracing_start_lock);
@@ -426,15 +426,15 @@ __setup("trace_buf_size=", set_buf_size);
 
 static int __init set_tracing_thresh(char *str)
 {
-	unsigned long threshhold;
+	unsigned long threshold;
 	int ret;
 
 	if (!str)
 		return 0;
-	ret = strict_strtoul(str, 0, &threshhold);
+	ret = strict_strtoul(str, 0, &threshold);
 	if (ret < 0)
 		return 0;
-	tracing_thresh = threshhold * 1000;
+	tracing_thresh = threshold * 1000;
 	return 1;
 }
 __setup("tracing_thresh=", set_tracing_thresh);
@@ -470,6 +470,7 @@ static const char *trace_options[] = {
 	"overwrite",
 	"disable_on_free",
 	"irq-info",
+	"markers",
 	NULL
 };
 
@@ -3886,6 +3887,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (tracing_disabled)
 		return -EINVAL;
 
+	if (!(trace_flags & TRACE_ITER_MARKERS))
+		return -EINVAL;
+
 	if (cnt > TRACE_BUF_SIZE)
 		cnt = TRACE_BUF_SIZE;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 55e1f7f..63a2da0 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -472,11 +472,11 @@ extern void trace_find_cmdline(int pid, char comm[]);
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 extern unsigned long ftrace_update_tot_cnt;
+#endif
 #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
 extern int DYN_FTRACE_TEST_NAME(void);
 #define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
 extern int DYN_FTRACE_TEST_NAME2(void);
-#endif
 
 extern int ring_buffer_expanded;
 extern bool tracing_selftest_disabled;
@@ -680,6 +680,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_OVERWRITE		= 0x200000,
 	TRACE_ITER_STOP_ON_FREE		= 0x400000,
 	TRACE_ITER_IRQ_INFO		= 0x800000,
+	TRACE_ITER_MARKERS		= 0x1000000,
 };
 
 /*
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 8a6d2ee..84b1e04 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -258,7 +258,8 @@ EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
 
 #ifdef CONFIG_FUNCTION_TRACER
 static void
-perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip)
+perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
+			  struct ftrace_ops *ops, struct pt_regs *pt_regs)
 {
 	struct ftrace_entry *entry;
 	struct hlist_head *head;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 29111da..d608d09 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1199,6 +1199,31 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 	return 0;
 }
 
+static void event_remove(struct ftrace_event_call *call)
+{
+	ftrace_event_enable_disable(call, 0);
+	if (call->event.funcs)
+		__unregister_ftrace_event(&call->event);
+	list_del(&call->list);
+}
+
+static int event_init(struct ftrace_event_call *call)
+{
+	int ret = 0;
+
+	if (WARN_ON(!call->name))
+		return -EINVAL;
+
+	if (call->class->raw_init) {
+		ret = call->class->raw_init(call);
+		if (ret < 0 && ret != -ENOSYS)
+			pr_warn("Could not initialize trace events/%s\n",
+				call->name);
+	}
+
+	return ret;
+}
+
 static int
 __trace_add_event_call(struct ftrace_event_call *call, struct module *mod,
 		       const struct file_operations *id,
@@ -1209,19 +1234,9 @@ __trace_add_event_call(struct ftrace_event_call *call, struct module *mod,
 	struct dentry *d_events;
 	int ret;
 
-	/* The linker may leave blanks */
-	if (!call->name)
-		return -EINVAL;
-
-	if (call->class->raw_init) {
-		ret = call->class->raw_init(call);
-		if (ret < 0) {
-			if (ret != -ENOSYS)
-				pr_warning("Could not initialize trace events/%s\n",
-					   call->name);
-			return ret;
-		}
-	}
+	ret = event_init(call);
+	if (ret < 0)
+		return ret;
 
 	d_events = event_trace_events_dir();
 	if (!d_events)
@@ -1272,13 +1287,10 @@ static void remove_subsystem_dir(const char *name)
  */
 static void __trace_remove_event_call(struct ftrace_event_call *call)
 {
-	ftrace_event_enable_disable(call, 0);
-	if (call->event.funcs)
-		__unregister_ftrace_event(&call->event);
-	debugfs_remove_recursive(call->dir);
-	list_del(&call->list);
+	event_remove(call);
 	trace_destroy_fields(call);
 	destroy_preds(call);
+	debugfs_remove_recursive(call->dir);
 	remove_subsystem_dir(call->class->system);
 }
 
@@ -1450,15 +1462,43 @@ static __init int setup_trace_event(char *str)
 }
 __setup("trace_event=", setup_trace_event);
 
+static __init int event_trace_enable(void)
+{
+	struct ftrace_event_call **iter, *call;
+	char *buf = bootup_event_buf;
+	char *token;
+	int ret;
+
+	for_each_event(iter, __start_ftrace_events, __stop_ftrace_events) {
+
+		call = *iter;
+		ret = event_init(call);
+		if (!ret)
+			list_add(&call->list, &ftrace_events);
+	}
+
+	while (true) {
+		token = strsep(&buf, ",");
+
+		if (!token)
+			break;
+		if (!*token)
+			continue;
+
+		ret = ftrace_set_clr_event(token, 1);
+		if (ret)
+			pr_warn("Failed to enable trace event: %s\n", token);
+	}
+	return 0;
+}
+
 static __init int event_trace_init(void)
 {
-	struct ftrace_event_call **call;
+	struct ftrace_event_call *call;
 	struct dentry *d_tracer;
 	struct dentry *entry;
 	struct dentry *d_events;
 	int ret;
-	char *buf = bootup_event_buf;
-	char *token;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
@@ -1497,24 +1537,19 @@ static __init int event_trace_init(void)
 	if (trace_define_common_fields())
 		pr_warning("tracing: Failed to allocate common fields");
 
-	for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
-		__trace_add_event_call(*call, NULL, &ftrace_event_id_fops,
+	/*
+	 * Early initialization already enabled ftrace event.
+	 * Now it's only necessary to create the event directory.
+	 */
+	list_for_each_entry(call, &ftrace_events, list) {
+
+		ret = event_create_dir(call, d_events,
+				       &ftrace_event_id_fops,
 				       &ftrace_enable_fops,
 				       &ftrace_event_filter_fops,
 				       &ftrace_event_format_fops);
-	}
-
-	while (true) {
-		token = strsep(&buf, ",");
-
-		if (!token)
-			break;
-		if (!*token)
-			continue;
-
-		ret = ftrace_set_clr_event(token, 1);
-		if (ret)
-			pr_warning("Failed to enable trace event: %s\n", token);
+		if (ret < 0)
+			event_remove(call);
 	}
 
 	ret = register_module_notifier(&trace_module_nb);
@@ -1523,6 +1558,7 @@ static __init int event_trace_init(void)
 
 	return 0;
 }
+core_initcall(event_trace_enable);
 fs_initcall(event_trace_init);
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -1646,9 +1682,11 @@ static __init void event_trace_self_tests(void)
 		event_test_stuff();
 
 		ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0);
-		if (WARN_ON_ONCE(ret))
+		if (WARN_ON_ONCE(ret)) {
 			pr_warning("error disabling system %s\n",
 				   system->name);
+			continue;
+		}
 
 		pr_cont("OK\n");
 	}
@@ -1681,7 +1719,8 @@ static __init void event_trace_self_tests(void)
 static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable);
 
 static void
-function_test_events_call(unsigned long ip, unsigned long parent_ip)
+function_test_events_call(unsigned long ip, unsigned long parent_ip,
+			  struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
@@ -1720,6 +1759,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 static struct ftrace_ops trace_ops __initdata  =
 {
 	.func = function_test_events_call,
+	.flags = FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static __init void event_trace_self_test_with_function(void)
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 431dba8..c154797 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -2002,7 +2002,7 @@ static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter,
 static int __ftrace_function_set_filter(int filter, char *buf, int len,
 					struct function_filter_data *data)
 {
-	int i, re_cnt, ret;
+	int i, re_cnt, ret = -EINVAL;
 	int *reset;
 	char **re;
 
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index a426f41..483162a 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -49,7 +49,8 @@ static void function_trace_start(struct trace_array *tr)
 }
 
 static void
-function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
+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;
@@ -84,7 +85,9 @@ enum {
 static struct tracer_flags func_flags;
 
 static void
-function_trace_call(unsigned long ip, unsigned long parent_ip)
+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;
@@ -121,7 +124,8 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
 }
 
 static void
-function_stack_trace_call(unsigned long ip, unsigned long parent_ip)
+function_stack_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;
@@ -164,13 +168,13 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip)
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = function_trace_call,
-	.flags = FTRACE_OPS_FL_GLOBAL,
+	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static struct ftrace_ops trace_stack_ops __read_mostly =
 {
 	.func = function_stack_trace_call,
-	.flags = FTRACE_OPS_FL_GLOBAL,
+	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static struct tracer_opt func_opts[] = {
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index ce27c8b..99b4378 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -143,7 +143,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 		return;
 	}
 
-#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
+#if defined(CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST) && !defined(CC_USING_FENTRY)
 	/*
 	 * The arch may choose to record the frame pointer used
 	 * and check it here to make sure that it is what we expect it
@@ -154,6 +154,9 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 	 *
 	 * Currently, x86_32 with optimize for size (-Os) makes the latest
 	 * gcc do the above.
+	 *
+	 * Note, -mfentry does not use frame pointers, and this test
+	 *  is not needed if CC_USING_FENTRY is set.
 	 */
 	if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
 		ftrace_graph_stop();
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 99d20e9..d98ee82 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -136,7 +136,8 @@ static int func_prolog_dec(struct trace_array *tr,
  * irqsoff uses its own tracer function to keep the overhead down:
  */
 static void
-irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
+irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip,
+		    struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
@@ -153,7 +154,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = irqsoff_tracer_call,
-	.flags = FTRACE_OPS_FL_GLOBAL,
+	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index ff791ea..02170c0 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -108,7 +108,8 @@ out_enable:
  * wakeup uses its own tracer function to keep the overhead down:
  */
 static void
-wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
+wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
+		   struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
@@ -129,7 +130,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = wakeup_tracer_call,
-	.flags = FTRACE_OPS_FL_GLOBAL,
+	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 288541f..2c00a69 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -103,54 +103,67 @@ static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret)
 
 static int trace_selftest_test_probe1_cnt;
 static void trace_selftest_test_probe1_func(unsigned long ip,
-					    unsigned long pip)
+					    unsigned long pip,
+					    struct ftrace_ops *op,
+					    struct pt_regs *pt_regs)
 {
 	trace_selftest_test_probe1_cnt++;
 }
 
 static int trace_selftest_test_probe2_cnt;
 static void trace_selftest_test_probe2_func(unsigned long ip,
-					    unsigned long pip)
+					    unsigned long pip,
+					    struct ftrace_ops *op,
+					    struct pt_regs *pt_regs)
 {
 	trace_selftest_test_probe2_cnt++;
 }
 
 static int trace_selftest_test_probe3_cnt;
 static void trace_selftest_test_probe3_func(unsigned long ip,
-					    unsigned long pip)
+					    unsigned long pip,
+					    struct ftrace_ops *op,
+					    struct pt_regs *pt_regs)
 {
 	trace_selftest_test_probe3_cnt++;
 }
 
 static int trace_selftest_test_global_cnt;
 static void trace_selftest_test_global_func(unsigned long ip,
-					    unsigned long pip)
+					    unsigned long pip,
+					    struct ftrace_ops *op,
+					    struct pt_regs *pt_regs)
 {
 	trace_selftest_test_global_cnt++;
 }
 
 static int trace_selftest_test_dyn_cnt;
 static void trace_selftest_test_dyn_func(unsigned long ip,
-					 unsigned long pip)
+					 unsigned long pip,
+					 struct ftrace_ops *op,
+					 struct pt_regs *pt_regs)
 {
 	trace_selftest_test_dyn_cnt++;
 }
 
 static struct ftrace_ops test_probe1 = {
 	.func			= trace_selftest_test_probe1_func,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static struct ftrace_ops test_probe2 = {
 	.func			= trace_selftest_test_probe2_func,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static struct ftrace_ops test_probe3 = {
 	.func			= trace_selftest_test_probe3_func,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static struct ftrace_ops test_global = {
-	.func			= trace_selftest_test_global_func,
-	.flags			= FTRACE_OPS_FL_GLOBAL,
+	.func		= trace_selftest_test_global_func,
+	.flags		= FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static void print_counts(void)
@@ -393,10 +406,253 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 
 	return ret;
 }
+
+static int trace_selftest_recursion_cnt;
+static void trace_selftest_test_recursion_func(unsigned long ip,
+					       unsigned long pip,
+					       struct ftrace_ops *op,
+					       struct pt_regs *pt_regs)
+{
+	/*
+	 * This function is registered without the recursion safe flag.
+	 * The ftrace infrastructure should provide the recursion
+	 * protection. If not, this will crash the kernel!
+	 */
+	trace_selftest_recursion_cnt++;
+	DYN_FTRACE_TEST_NAME();
+}
+
+static void trace_selftest_test_recursion_safe_func(unsigned long ip,
+						    unsigned long pip,
+						    struct ftrace_ops *op,
+						    struct pt_regs *pt_regs)
+{
+	/*
+	 * We said we would provide our own recursion. By calling
+	 * this function again, we should recurse back into this function
+	 * and count again. But this only happens if the arch supports
+	 * all of ftrace features and nothing else is using the function
+	 * tracing utility.
+	 */
+	if (trace_selftest_recursion_cnt++)
+		return;
+	DYN_FTRACE_TEST_NAME();
+}
+
+static struct ftrace_ops test_rec_probe = {
+	.func			= trace_selftest_test_recursion_func,
+};
+
+static struct ftrace_ops test_recsafe_probe = {
+	.func			= trace_selftest_test_recursion_safe_func,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
+};
+
+static int
+trace_selftest_function_recursion(void)
+{
+	int save_ftrace_enabled = ftrace_enabled;
+	int save_tracer_enabled = tracer_enabled;
+	char *func_name;
+	int len;
+	int ret;
+	int cnt;
+
+	/* The previous test PASSED */
+	pr_cont("PASSED\n");
+	pr_info("Testing ftrace recursion: ");
+
+
+	/* enable tracing, and record the filter function */
+	ftrace_enabled = 1;
+	tracer_enabled = 1;
+
+	/* Handle PPC64 '.' name */
+	func_name = "*" __stringify(DYN_FTRACE_TEST_NAME);
+	len = strlen(func_name);
+
+	ret = ftrace_set_filter(&test_rec_probe, func_name, len, 1);
+	if (ret) {
+		pr_cont("*Could not set filter* ");
+		goto out;
+	}
+
+	ret = register_ftrace_function(&test_rec_probe);
+	if (ret) {
+		pr_cont("*could not register callback* ");
+		goto out;
+	}
+
+	DYN_FTRACE_TEST_NAME();
+
+	unregister_ftrace_function(&test_rec_probe);
+
+	ret = -1;
+	if (trace_selftest_recursion_cnt != 1) {
+		pr_cont("*callback not called once (%d)* ",
+			trace_selftest_recursion_cnt);
+		goto out;
+	}
+
+	trace_selftest_recursion_cnt = 1;
+
+	pr_cont("PASSED\n");
+	pr_info("Testing ftrace recursion safe: ");
+
+	ret = ftrace_set_filter(&test_recsafe_probe, func_name, len, 1);
+	if (ret) {
+		pr_cont("*Could not set filter* ");
+		goto out;
+	}
+
+	ret = register_ftrace_function(&test_recsafe_probe);
+	if (ret) {
+		pr_cont("*could not register callback* ");
+		goto out;
+	}
+
+	DYN_FTRACE_TEST_NAME();
+
+	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);
+		goto out;
+	}
+
+	ret = 0;
+out:
+	ftrace_enabled = save_ftrace_enabled;
+	tracer_enabled = save_tracer_enabled;
+
+	return ret;
+}
 #else
 # define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; })
+# define trace_selftest_function_recursion() ({ 0; })
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
+static enum {
+	TRACE_SELFTEST_REGS_START,
+	TRACE_SELFTEST_REGS_FOUND,
+	TRACE_SELFTEST_REGS_NOT_FOUND,
+} trace_selftest_regs_stat;
+
+static void trace_selftest_test_regs_func(unsigned long ip,
+					  unsigned long pip,
+					  struct ftrace_ops *op,
+					  struct pt_regs *pt_regs)
+{
+	if (pt_regs)
+		trace_selftest_regs_stat = TRACE_SELFTEST_REGS_FOUND;
+	else
+		trace_selftest_regs_stat = TRACE_SELFTEST_REGS_NOT_FOUND;
+}
+
+static struct ftrace_ops test_regs_probe = {
+	.func		= trace_selftest_test_regs_func,
+	.flags		= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_SAVE_REGS,
+};
+
+static int
+trace_selftest_function_regs(void)
+{
+	int save_ftrace_enabled = ftrace_enabled;
+	int save_tracer_enabled = tracer_enabled;
+	char *func_name;
+	int len;
+	int ret;
+	int supported = 0;
+
+#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+	supported = 1;
+#endif
+
+	/* The previous test PASSED */
+	pr_cont("PASSED\n");
+	pr_info("Testing ftrace regs%s: ",
+		!supported ? "(no arch support)" : "");
+
+	/* enable tracing, and record the filter function */
+	ftrace_enabled = 1;
+	tracer_enabled = 1;
+
+	/* Handle PPC64 '.' name */
+	func_name = "*" __stringify(DYN_FTRACE_TEST_NAME);
+	len = strlen(func_name);
+
+	ret = ftrace_set_filter(&test_regs_probe, func_name, len, 1);
+	/*
+	 * If DYNAMIC_FTRACE is not set, then we just trace all functions.
+	 * This test really doesn't care.
+	 */
+	if (ret && ret != -ENODEV) {
+		pr_cont("*Could not set filter* ");
+		goto out;
+	}
+
+	ret = register_ftrace_function(&test_regs_probe);
+	/*
+	 * Now if the arch does not support passing regs, then this should
+	 * have failed.
+	 */
+	if (!supported) {
+		if (!ret) {
+			pr_cont("*registered save-regs without arch support* ");
+			goto out;
+		}
+		test_regs_probe.flags |= FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED;
+		ret = register_ftrace_function(&test_regs_probe);
+	}
+	if (ret) {
+		pr_cont("*could not register callback* ");
+		goto out;
+	}
+
+
+	DYN_FTRACE_TEST_NAME();
+
+	unregister_ftrace_function(&test_regs_probe);
+
+	ret = -1;
+
+	switch (trace_selftest_regs_stat) {
+	case TRACE_SELFTEST_REGS_START:
+		pr_cont("*callback never called* ");
+		goto out;
+
+	case TRACE_SELFTEST_REGS_FOUND:
+		if (supported)
+			break;
+		pr_cont("*callback received regs without arch support* ");
+		goto out;
+
+	case TRACE_SELFTEST_REGS_NOT_FOUND:
+		if (!supported)
+			break;
+		pr_cont("*callback received NULL regs* ");
+		goto out;
+	}
+
+	ret = 0;
+out:
+	ftrace_enabled = save_ftrace_enabled;
+	tracer_enabled = save_tracer_enabled;
+
+	return ret;
+}
+
 /*
  * Simple verification test of ftrace function tracer.
  * Enable ftrace, sleep 1/10 second, and then read the trace
@@ -442,7 +698,14 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 
 	ret = trace_selftest_startup_dynamic_tracing(trace, tr,
 						     DYN_FTRACE_TEST_NAME);
+	if (ret)
+		goto out;
 
+	ret = trace_selftest_function_recursion();
+	if (ret)
+		goto out;
+
+	ret = trace_selftest_function_regs();
  out:
 	ftrace_enabled = save_ftrace_enabled;
 	tracer_enabled = save_tracer_enabled;
@@ -778,6 +1041,8 @@ static int trace_wakeup_test_thread(void *data)
 	set_current_state(TASK_INTERRUPTIBLE);
 	schedule();
 
+	complete(x);
+
 	/* we are awake, now wait to disappear */
 	while (!kthread_should_stop()) {
 		/*
@@ -821,24 +1086,21 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	/* reset the max latency */
 	tracing_max_latency = 0;
 
-	/* sleep to let the RT thread sleep too */
-	msleep(100);
+	while (p->on_rq) {
+		/*
+		 * Sleep to make sure the RT thread is asleep too.
+		 * On virtual machines we can't rely on timings,
+		 * but we want to make sure this test still works.
+		 */
+		msleep(100);
+	}
 
-	/*
-	 * Yes this is slightly racy. It is possible that for some
-	 * strange reason that the RT thread we created, did not
-	 * call schedule for 100ms after doing the completion,
-	 * and we do a wakeup on a task that already is awake.
-	 * But that is extremely unlikely, and the worst thing that
-	 * happens in such a case, is that we disable tracing.
-	 * Honestly, if this race does happen something is horrible
-	 * wrong with the system.
-	 */
+	init_completion(&isrt);
 
 	wake_up_process(p);
 
-	/* give a little time to let the thread wake up */
-	msleep(100);
+	/* Wait for the task to wake up */
+	wait_for_completion(&isrt);
 
 	/* stop the tracing. */
 	tracing_stop();
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index d4545f4..0c1b1657 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -111,7 +111,8 @@ static inline void check_stack(void)
 }
 
 static void
-stack_trace_call(unsigned long ip, unsigned long parent_ip)
+stack_trace_call(unsigned long ip, unsigned long parent_ip,
+		 struct ftrace_ops *op, struct pt_regs *pt_regs)
 {
 	int cpu;
 
@@ -136,6 +137,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
 static struct ftrace_ops trace_ops __read_mostly =
 {
 	.func = stack_trace_call,
+	.flags = FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
 static ssize_t
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 6b245f64..2485a7d 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -487,7 +487,7 @@ int __init init_ftrace_syscalls(void)
 
 	return 0;
 }
-core_initcall(init_ftrace_syscalls);
+early_initcall(init_ftrace_syscalls);
 
 #ifdef CONFIG_PERF_EVENTS