Merge tag 'perf-kprobes-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf/kprobes updates from Ingo Molnar:
 "This prepares to unify the kretprobe trampoline handler and make
  kretprobe lockless (those patches are still work in progress)"

* tag 'perf-kprobes-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  kprobes: Fix to check probe enabled before disarm_kprobe_ftrace()
  kprobes: Make local functions static
  kprobes: Free kretprobe_instance with RCU callback
  kprobes: Remove NMI context check
  sparc: kprobes: Use generic kretprobe trampoline handler
  sh: kprobes: Use generic kretprobe trampoline handler
  s390: kprobes: Use generic kretprobe trampoline handler
  powerpc: kprobes: Use generic kretprobe trampoline handler
  parisc: kprobes: Use generic kretprobe trampoline handler
  mips: kprobes: Use generic kretprobe trampoline handler
  ia64: kprobes: Use generic kretprobe trampoline handler
  csky: kprobes: Use generic kretprobe trampoline handler
  arc: kprobes: Use generic kretprobe trampoline handler
  arm64: kprobes: Use generic kretprobe trampoline handler
  arm: kprobes: Use generic kretprobe trampoline handler
  x86/kprobes: Use generic kretprobe trampoline handler
  kprobes: Add generic kretprobe trampoline handler

14 files changed, 166 insertions, 856 deletions

diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
index 7d3efe83cba7..cabef45f11df 100644
--- a/arch/arc/kernel/kprobes.c
+++ b/arch/arc/kernel/kprobes.c
@@ -388,6 +388,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 {
 
 	ri->ret_addr = (kprobe_opcode_t *) regs->blink;
+	ri->fp = NULL;
 
 	/* Replace the return addr with trampoline addr */
 	regs->blink = (unsigned long)&kretprobe_trampoline;
@@ -396,58 +397,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 static int __kprobes trampoline_probe_handler(struct kprobe *p,
 					      struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
-
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because an multiple functions in the call path
-	 * have a return probe installed on them, and/or more than one return
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always inserted at the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *       function, the first instance's ret_addr will point to the
-	 *       real return address, and all the rest will point to
-	 *       kretprobe_trampoline
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		if (ri->rp && ri->rp->handler)
-			ri->rp->handler(ri, regs);
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address) {
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-		}
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-	regs->ret = orig_ret_address;
-
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
+	regs->ret = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL);
 
 	/* By returning a non zero value, we are telling the kprobe handler
 	 * that we don't want the post_handler to run
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index feefa2055eba..a9653117ca0d 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -413,87 +413,15 @@ void __naked __kprobes kretprobe_trampoline(void)
 /* Called from kretprobe_trampoline */
 static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
-	kprobe_opcode_t *correct_ret_addr = NULL;
-
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because multiple functions in the call path have
-	 * a return probe installed on them, and/or more than one return
-	 * probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always inserted at the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *       function, the first instance's ret_addr will point to the
-	 *       real return address, and all the rest will point to
-	 *       kretprobe_trampoline
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
-	correct_ret_addr = ri->ret_addr;
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		if (ri->rp && ri->rp->handler) {
-			__this_cpu_write(current_kprobe, &ri->rp->kp);
-			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
-			ri->ret_addr = correct_ret_addr;
-			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, NULL);
-		}
-
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
-
-	return (void *)orig_ret_address;
+	return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline,
+						    (void *)regs->ARM_fp);
 }
 
 void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *)regs->ARM_lr;
+	ri->fp = (void *)regs->ARM_fp;
 
 	/* Replace the return addr with trampoline addr. */
 	regs->ARM_lr = (unsigned long)&kretprobe_trampoline;
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 5290f17a4d80..deba738142ed 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -464,87 +464,15 @@ int __init arch_populate_kprobe_blacklist(void)
 
 void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address =
-		(unsigned long)&kretprobe_trampoline;
-	kprobe_opcode_t *correct_ret_addr = NULL;
-
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because multiple functions in the call path have
-	 * return probes installed on them, and/or more than one
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always pushed into the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *	 function, the (chronologically) first instance's ret_addr
-	 *	 will be the real return address, and all the rest will
-	 *	 point to kretprobe_trampoline.
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
-	correct_ret_addr = ri->ret_addr;
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		if (ri->rp && ri->rp->handler) {
-			__this_cpu_write(current_kprobe, &ri->rp->kp);
-			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
-			ri->ret_addr = correct_ret_addr;
-			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, NULL);
-		}
-
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
-	return (void *)orig_ret_address;
+	return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline,
+					(void *)kernel_stack_pointer(regs));
 }
 
 void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *)regs->regs[30];
+	ri->fp = (void *)kernel_stack_pointer(regs);
 
 	/* replace return addr (x30) with trampoline */
 	regs->regs[30] = (long)&kretprobe_trampoline;
diff --git a/arch/csky/kernel/probes/kprobes.c b/arch/csky/kernel/probes/kprobes.c
index f0f733b7ac5a..589f090f48b9 100644
--- a/arch/csky/kernel/probes/kprobes.c
+++ b/arch/csky/kernel/probes/kprobes.c
@@ -404,87 +404,14 @@ int __init arch_populate_kprobe_blacklist(void)
 
 void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address =
-		(unsigned long)&kretprobe_trampoline;
-	kprobe_opcode_t *correct_ret_addr = NULL;
-
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because multiple functions in the call path have
-	 * return probes installed on them, and/or more than one
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always pushed into the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *	 function, the (chronologically) first instance's ret_addr
-	 *	 will be the real return address, and all the rest will
-	 *	 point to kretprobe_trampoline.
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
-	correct_ret_addr = ri->ret_addr;
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		if (ri->rp && ri->rp->handler) {
-			__this_cpu_write(current_kprobe, &ri->rp->kp);
-			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
-			ri->ret_addr = correct_ret_addr;
-			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, NULL);
-		}
-
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
-	return (void *)orig_ret_address;
+	return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL);
 }
 
 void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *)regs->lr;
+	ri->fp = NULL;
 	regs->lr = (unsigned long) &kretprobe_trampoline;
 }
 
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 7a7df944d798..fc1ff8a4d7de 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -396,83 +396,9 @@ static void kretprobe_trampoline(void)
 {
 }
 
-/*
- * At this point the target function has been tricked into
- * returning into our trampoline.  Lookup the associated instance
- * and then:
- *    - call the handler function
- *    - cleanup by marking the instance as unused
- *    - long jump back to the original return address
- */
 int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address =
-		((struct fnptr *)kretprobe_trampoline)->ip;
-
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because an multiple functions in the call path
-	 * have a return probe installed on them, and/or more than one return
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always inserted at the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *       function, the first instance's ret_addr will point to the
-	 *       real return address, and all the rest will point to
-	 *       kretprobe_trampoline
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	regs->cr_iip = orig_ret_address;
-
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		if (ri->rp && ri->rp->handler)
-			ri->rp->handler(ri, regs);
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
+	regs->cr_iip = __kretprobe_trampoline_handler(regs, kretprobe_trampoline, NULL);
 	/*
 	 * By returning a non-zero value, we are telling
 	 * kprobe_handler() that we don't want the post_handler
@@ -485,6 +411,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *)regs->b0;
+	ri->fp = NULL;
 
 	/* Replace the return addr with trampoline addr */
 	regs->b0 = ((struct fnptr *)kretprobe_trampoline)->ip;
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index d043c2f897fc..54dfba8fa77c 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -477,6 +477,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *) regs->regs[31];
+	ri->fp = NULL;
 
 	/* Replace the return addr with trampoline addr */
 	regs->regs[31] = (unsigned long)kretprobe_trampoline;
@@ -488,57 +489,8 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 static int __kprobes trampoline_probe_handler(struct kprobe *p,
 						struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address = (unsigned long)kretprobe_trampoline;
-
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because an multiple functions in the call path
-	 * have a return probe installed on them, and/or more than one return
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always inserted at the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *	 function, the first instance's ret_addr will point to the
-	 *	 real return address, and all the rest will point to
-	 *	 kretprobe_trampoline
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		if (ri->rp && ri->rp->handler)
-			ri->rp->handler(ri, regs);
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-	instruction_pointer(regs) = orig_ret_address;
-
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
+	instruction_pointer(regs) = __kretprobe_trampoline_handler(regs,
+						kretprobe_trampoline, NULL);
 	/*
 	 * By returning a non-zero value, we are telling
 	 * kprobe_handler() that we don't want the post_handler
diff --git a/arch/parisc/kernel/kprobes.c b/arch/parisc/kernel/kprobes.c
index 77ec51818916..6d21a515eea5 100644
--- a/arch/parisc/kernel/kprobes.c
+++ b/arch/parisc/kernel/kprobes.c
@@ -191,80 +191,11 @@ static struct kprobe trampoline_p = {
 static int __kprobes trampoline_probe_handler(struct kprobe *p,
 					      struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address = (unsigned long)trampoline_p.addr;
-	kprobe_opcode_t *correct_ret_addr = NULL;
-
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because multiple functions in the call path have
-	 * a return probe installed on them, and/or more than one return
-	 * probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always inserted at the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *       function, the first instance's ret_addr will point to the
-	 *       real return address, and all the rest will point to
-	 *       kretprobe_trampoline
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
-	correct_ret_addr = ri->ret_addr;
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		if (ri->rp && ri->rp->handler) {
-			__this_cpu_write(current_kprobe, &ri->rp->kp);
-			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
-			ri->ret_addr = correct_ret_addr;
-			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, NULL);
-		}
-
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
+	unsigned long orig_ret_address;
 
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
+	orig_ret_address = __kretprobe_trampoline_handler(regs, trampoline_p.addr, NULL);
 	instruction_pointer_set(regs, orig_ret_address);
+
 	return 1;
 }
 
@@ -272,6 +203,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *)regs->gr[2];
+	ri->fp = NULL;
 
 	/* Replace the return addr with trampoline addr. */
 	regs->gr[2] = (unsigned long)trampoline_p.addr;
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 6ab9b4d037c3..01ab2163659e 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -218,6 +218,7 @@ bool arch_kprobe_on_func_entry(unsigned long offset)
 void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *)regs->link;
+	ri->fp = NULL;
 
 	/* Replace the return addr with trampoline addr */
 	regs->link = (unsigned long)kretprobe_trampoline;
@@ -396,50 +397,9 @@ asm(".global kretprobe_trampoline\n"
  */
 static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
-
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because an multiple functions in the call path
-	 * have a return probe installed on them, and/or more than one return
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always inserted at the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *       function, the first instance's ret_addr will point to the
-	 *       real return address, and all the rest will point to
-	 *       kretprobe_trampoline
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		if (ri->rp && ri->rp->handler)
-			ri->rp->handler(ri, regs);
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+	unsigned long orig_ret_address;
 
+	orig_ret_address = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL);
 	/*
 	 * We get here through one of two paths:
 	 * 1. by taking a trap -> kprobe_handler() -> here
@@ -458,13 +418,6 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->nip = orig_ret_address - 4;
 	regs->link = orig_ret_address;
 
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
-
 	return 0;
 }
 NOKPROBE_SYMBOL(trampoline_probe_handler);
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index d2a71d872638..fc30e799bd84 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -228,6 +228,7 @@ NOKPROBE_SYMBOL(pop_kprobe);
 void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *) regs->gprs[14];
+	ri->fp = NULL;
 
 	/* Replace the return addr with trampoline addr */
 	regs->gprs[14] = (unsigned long) &kretprobe_trampoline;
@@ -331,83 +332,7 @@ static void __used kretprobe_trampoline_holder(void)
  */
 static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address;
-	unsigned long trampoline_address;
-	kprobe_opcode_t *correct_ret_addr;
-
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because an multiple functions in the call path
-	 * have a return probe installed on them, and/or more than one return
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always inserted at the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *	 function, the first instance's ret_addr will point to the
-	 *	 real return address, and all the rest will point to
-	 *	 kretprobe_trampoline
-	 */
-	ri = NULL;
-	orig_ret_address = 0;
-	correct_ret_addr = NULL;
-	trampoline_address = (unsigned long) &kretprobe_trampoline;
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		orig_ret_address = (unsigned long) ri->ret_addr;
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
-	correct_ret_addr = ri->ret_addr;
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		orig_ret_address = (unsigned long) ri->ret_addr;
-
-		if (ri->rp && ri->rp->handler) {
-			ri->ret_addr = correct_ret_addr;
-			ri->rp->handler(ri, regs);
-		}
-
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	regs->psw.addr = orig_ret_address;
-
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
+	regs->psw.addr = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL);
 	/*
 	 * By returning a non-zero value, we are telling
 	 * kprobe_handler() that we don't want the post_handler
diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c
index 318296f48f1a..756100b01e84 100644
--- a/arch/sh/kernel/kprobes.c
+++ b/arch/sh/kernel/kprobes.c
@@ -204,6 +204,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *) regs->pr;
+	ri->fp = NULL;
 
 	/* Replace the return addr with trampoline addr */
 	regs->pr = (unsigned long)kretprobe_trampoline;
@@ -302,62 +303,9 @@ static void __used kretprobe_trampoline_holder(void)
  */
 int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+	regs->pc = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL);
 
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because an multiple functions in the call path
-	 * have a return probe installed on them, and/or more then one return
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always inserted at the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *       function, the first instance's ret_addr will point to the
-	 *       real return address, and all the rest will point to
-	 *       kretprobe_trampoline
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		if (ri->rp && ri->rp->handler) {
-			__this_cpu_write(current_kprobe, &ri->rp->kp);
-			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, NULL);
-		}
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
-	regs->pc = orig_ret_address;
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
-
-	return orig_ret_address;
+	return 1;
 }
 
 static int __kprobes post_kprobe_handler(struct pt_regs *regs)
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index dfbca2470536..217c21a6986a 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -453,6 +453,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
 	ri->ret_addr = (kprobe_opcode_t *)(regs->u_regs[UREG_RETPC] + 8);
+	ri->fp = NULL;
 
 	/* Replace the return addr with trampoline addr */
 	regs->u_regs[UREG_RETPC] =
@@ -465,58 +466,12 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 static int __kprobes trampoline_probe_handler(struct kprobe *p,
 					      struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
+	unsigned long orig_ret_address = 0;
 
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
-
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because an multiple functions in the call path
-	 * have a return probe installed on them, and/or more than one return
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always inserted at the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *       function, the first instance's ret_addr will point to the
-	 *       real return address, and all the rest will point to
-	 *       kretprobe_trampoline
-	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-
-		if (ri->rp && ri->rp->handler)
-			ri->rp->handler(ri, regs);
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+	orig_ret_address = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL);
 	regs->tpc = orig_ret_address;
 	regs->tnpc = orig_ret_address + 4;
 
-	kretprobe_hash_unlock(current, &flags);
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
 	/*
 	 * By returning a non-zero value, we are telling
 	 * kprobe_handler() that we don't want the post_handler
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index fdadc37d72af..882b95313ad6 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -767,124 +767,22 @@ asm(
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
+
 /*
  * Called from kretprobe_trampoline
  */
 __used __visible void *trampoline_handler(struct pt_regs *regs)
 {
-	struct kretprobe_instance *ri = NULL;
-	struct hlist_head *head, empty_rp;
-	struct hlist_node *tmp;
-	unsigned long flags, orig_ret_address = 0;
-	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
-	kprobe_opcode_t *correct_ret_addr = NULL;
-	void *frame_pointer;
-	bool skipped = false;
-
-	/*
-	 * Set a dummy kprobe for avoiding kretprobe recursion.
-	 * Since kretprobe never run in kprobe handler, kprobe must not
-	 * be running at this point.
-	 */
-	kprobe_busy_begin();
-
-	INIT_HLIST_HEAD(&empty_rp);
-	kretprobe_hash_lock(current, &head, &flags);
 	/* fixup registers */
 	regs->cs = __KERNEL_CS;
 #ifdef CONFIG_X86_32
 	regs->cs |= get_kernel_rpl();
 	regs->gs = 0;
 #endif
-	/* We use pt_regs->sp for return address holder. */
-	frame_pointer = &regs->sp;
-	regs->ip = trampoline_address;
+	regs->ip = (unsigned long)&kretprobe_trampoline;
 	regs->orig_ax = ~0UL;
 
-	/*
-	 * It is possible to have multiple instances associated with a given
-	 * task either because multiple functions in the call path have
-	 * return probes installed on them, and/or more than one
-	 * return probe was registered for a target function.
-	 *
-	 * We can handle this because:
-	 *     - instances are always pushed into the head of the list
-	 *     - when multiple return probes are registered for the same
-	 *	 function, the (chronologically) first instance's ret_addr
-	 *	 will be the real return address, and all the rest will
-	 *	 point to kretprobe_trampoline.
-	 */
-	hlist_for_each_entry(ri, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-		/*
-		 * Return probes must be pushed on this hash list correct
-		 * order (same as return order) so that it can be popped
-		 * correctly. However, if we find it is pushed it incorrect
-		 * order, this means we find a function which should not be
-		 * probed, because the wrong order entry is pushed on the
-		 * path of processing other kretprobe itself.
-		 */
-		if (ri->fp != frame_pointer) {
-			if (!skipped)
-				pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
-			skipped = true;
-			continue;
-		}
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		if (skipped)
-			pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
-				ri->rp->kp.addr);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
-	correct_ret_addr = ri->ret_addr;
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-		if (ri->task != current)
-			/* another task is sharing our hash bucket */
-			continue;
-		if (ri->fp != frame_pointer)
-			continue;
-
-		orig_ret_address = (unsigned long)ri->ret_addr;
-		if (ri->rp && ri->rp->handler) {
-			__this_cpu_write(current_kprobe, &ri->rp->kp);
-			ri->ret_addr = correct_ret_addr;
-			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, &kprobe_busy);
-		}
-
-		recycle_rp_inst(ri, &empty_rp);
-
-		if (orig_ret_address != trampoline_address)
-			/*
-			 * This is the real return address. Any other
-			 * instances associated with this task are for
-			 * other calls deeper on the call stack
-			 */
-			break;
-	}
-
-	kretprobe_hash_unlock(current, &flags);
-
-	kprobe_busy_end();
-
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
-	return (void *)orig_ret_address;
+	return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, &regs->sp);
 }
 NOKPROBE_SYMBOL(trampoline_handler);
 
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 8aab327b5539..629abaf25681 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -156,7 +156,10 @@ struct kretprobe {
 };
 
 struct kretprobe_instance {
-	struct hlist_node hlist;
+	union {
+		struct hlist_node hlist;
+		struct rcu_head rcu;
+	};
 	struct kretprobe *rp;
 	kprobe_opcode_t *ret_addr;
 	struct task_struct *task;
@@ -187,10 +190,37 @@ static inline int kprobes_built_in(void)
 	return 1;
 }
 
+extern void kprobe_busy_begin(void);
+extern void kprobe_busy_end(void);
+
 #ifdef CONFIG_KRETPROBES
 extern void arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				   struct pt_regs *regs);
 extern int arch_trampoline_kprobe(struct kprobe *p);
+
+/* If the trampoline handler called from a kprobe, use this version */
+unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
+				void *trampoline_address,
+				void *frame_pointer);
+
+static nokprobe_inline
+unsigned long kretprobe_trampoline_handler(struct pt_regs *regs,
+				void *trampoline_address,
+				void *frame_pointer)
+{
+	unsigned long ret;
+	/*
+	 * Set a dummy kprobe for avoiding kretprobe recursion.
+	 * Since kretprobe never runs in kprobe handler, no kprobe must
+	 * be running at this point.
+	 */
+	kprobe_busy_begin();
+	ret = __kretprobe_trampoline_handler(regs, trampoline_address, frame_pointer);
+	kprobe_busy_end();
+
+	return ret;
+}
+
 #else /* CONFIG_KRETPROBES */
 static inline void arch_prepare_kretprobe(struct kretprobe *rp,
 					struct pt_regs *regs)
@@ -204,16 +234,6 @@ static inline int arch_trampoline_kprobe(struct kprobe *p)
 
 extern struct kretprobe_blackpoint kretprobe_blacklist[];
 
-static inline void kretprobe_assert(struct kretprobe_instance *ri,
-	unsigned long orig_ret_address, unsigned long trampoline_address)
-{
-	if (!orig_ret_address || (orig_ret_address == trampoline_address)) {
-		printk("kretprobe BUG!: Processing kretprobe %p @ %p\n",
-				ri->rp, ri->rp->kp.addr);
-		BUG();
-	}
-}
-
 #ifdef CONFIG_KPROBES_SANITY_TEST
 extern int init_test_probes(void);
 #else
@@ -333,10 +353,6 @@ int arch_check_ftrace_location(struct kprobe *p);
 
 /* Get the kprobe at this addr (if any) - called with preemption disabled */
 struct kprobe *get_kprobe(void *addr);
-void kretprobe_hash_lock(struct task_struct *tsk,
-			 struct hlist_head **head, unsigned long *flags);
-void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags);
-struct hlist_head * kretprobe_inst_table_head(struct task_struct *tsk);
 
 /* kprobe_running() will just return the current_kprobe on this CPU */
 static inline struct kprobe *kprobe_running(void)
@@ -354,10 +370,6 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
 	return this_cpu_ptr(&kprobe_ctlblk);
 }
 
-extern struct kprobe kprobe_busy;
-void kprobe_busy_begin(void);
-void kprobe_busy_end(void);
-
 kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset);
 int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
@@ -371,7 +383,6 @@ int register_kretprobes(struct kretprobe **rps, int num);
 void unregister_kretprobes(struct kretprobe **rps, int num);
 
 void kprobe_flush_task(struct task_struct *tk);
-void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
 
 void kprobe_free_init_mem(void);
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index c16c3236f6cf..789002da7766 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1224,8 +1224,7 @@ void kprobes_inc_nmissed_count(struct kprobe *p)
 }
 NOKPROBE_SYMBOL(kprobes_inc_nmissed_count);
 
-void recycle_rp_inst(struct kretprobe_instance *ri,
-		     struct hlist_head *head)
+static void recycle_rp_inst(struct kretprobe_instance *ri)
 {
 	struct kretprobe *rp = ri->rp;
 
@@ -1237,12 +1236,11 @@ void recycle_rp_inst(struct kretprobe_instance *ri,
 		hlist_add_head(&ri->hlist, &rp->free_instances);
 		raw_spin_unlock(&rp->lock);
 	} else
-		/* Unregistering */
-		hlist_add_head(&ri->hlist, head);
+		kfree_rcu(ri, rcu);
 }
 NOKPROBE_SYMBOL(recycle_rp_inst);
 
-void kretprobe_hash_lock(struct task_struct *tsk,
+static void kretprobe_hash_lock(struct task_struct *tsk,
 			 struct hlist_head **head, unsigned long *flags)
 __acquires(hlist_lock)
 {
@@ -1264,7 +1262,7 @@ __acquires(hlist_lock)
 }
 NOKPROBE_SYMBOL(kretprobe_table_lock);
 
-void kretprobe_hash_unlock(struct task_struct *tsk,
+static void kretprobe_hash_unlock(struct task_struct *tsk,
 			   unsigned long *flags)
 __releases(hlist_lock)
 {
@@ -1285,7 +1283,7 @@ __releases(hlist_lock)
 }
 NOKPROBE_SYMBOL(kretprobe_table_unlock);
 
-struct kprobe kprobe_busy = {
+static struct kprobe kprobe_busy = {
 	.addr = (void *) get_kprobe,
 };
 
@@ -1314,7 +1312,7 @@ void kprobe_busy_end(void)
 void kprobe_flush_task(struct task_struct *tk)
 {
 	struct kretprobe_instance *ri;
-	struct hlist_head *head, empty_rp;
+	struct hlist_head *head;
 	struct hlist_node *tmp;
 	unsigned long hash, flags = 0;
 
@@ -1324,19 +1322,14 @@ void kprobe_flush_task(struct task_struct *tk)
 
 	kprobe_busy_begin();
 
-	INIT_HLIST_HEAD(&empty_rp);
 	hash = hash_ptr(tk, KPROBE_HASH_BITS);
 	head = &kretprobe_inst_table[hash];
 	kretprobe_table_lock(hash, &flags);
 	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
 		if (ri->task == tk)
-			recycle_rp_inst(ri, &empty_rp);
+			recycle_rp_inst(ri);
 	}
 	kretprobe_table_unlock(hash, &flags);
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
 
 	kprobe_busy_end();
 }
@@ -1360,7 +1353,8 @@ static void cleanup_rp_inst(struct kretprobe *rp)
 	struct hlist_node *next;
 	struct hlist_head *head;
 
-	/* No race here */
+	/* To avoid recursive kretprobe by NMI, set kprobe busy here */
+	kprobe_busy_begin();
 	for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) {
 		kretprobe_table_lock(hash, &flags);
 		head = &kretprobe_inst_table[hash];
@@ -1370,6 +1364,8 @@ static void cleanup_rp_inst(struct kretprobe *rp)
 		}
 		kretprobe_table_unlock(hash, &flags);
 	}
+	kprobe_busy_end();
+
 	free_rp_inst(rp);
 }
 NOKPROBE_SYMBOL(cleanup_rp_inst);
@@ -1929,6 +1925,97 @@ unsigned long __weak arch_deref_entry_point(void *entry)
 }
 
 #ifdef CONFIG_KRETPROBES
+
+unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
+					     void *trampoline_address,
+					     void *frame_pointer)
+{
+	struct kretprobe_instance *ri = NULL, *last = NULL;
+	struct hlist_head *head;
+	struct hlist_node *tmp;
+	unsigned long flags;
+	kprobe_opcode_t *correct_ret_addr = NULL;
+	bool skipped = false;
+
+	kretprobe_hash_lock(current, &head, &flags);
+
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because multiple functions in the call path have
+	 * return probes installed on them, and/or more than one
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always pushed into the head of the list
+	 *     - when multiple return probes are registered for the same
+	 *	 function, the (chronologically) first instance's ret_addr
+	 *	 will be the real return address, and all the rest will
+	 *	 point to kretprobe_trampoline.
+	 */
+	hlist_for_each_entry(ri, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+		/*
+		 * Return probes must be pushed on this hash list correct
+		 * order (same as return order) so that it can be popped
+		 * correctly. However, if we find it is pushed it incorrect
+		 * order, this means we find a function which should not be
+		 * probed, because the wrong order entry is pushed on the
+		 * path of processing other kretprobe itself.
+		 */
+		if (ri->fp != frame_pointer) {
+			if (!skipped)
+				pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+			skipped = true;
+			continue;
+		}
+
+		correct_ret_addr = ri->ret_addr;
+		if (skipped)
+			pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+				ri->rp->kp.addr);
+
+		if (correct_ret_addr != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	BUG_ON(!correct_ret_addr || (correct_ret_addr == trampoline_address));
+	last = ri;
+
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+		if (ri->fp != frame_pointer)
+			continue;
+
+		if (ri->rp && ri->rp->handler) {
+			struct kprobe *prev = kprobe_running();
+
+			__this_cpu_write(current_kprobe, &ri->rp->kp);
+			ri->ret_addr = correct_ret_addr;
+			ri->rp->handler(ri, regs);
+			__this_cpu_write(current_kprobe, prev);
+		}
+
+		recycle_rp_inst(ri);
+
+		if (ri == last)
+			break;
+	}
+
+	kretprobe_hash_unlock(current, &flags);
+
+	return (unsigned long)correct_ret_addr;
+}
+NOKPROBE_SYMBOL(__kretprobe_trampoline_handler)
+
 /*
  * This kprobe pre_handler is registered with every kretprobe. When probe
  * hits it will set up the return probe.
@@ -1939,17 +2026,6 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 	unsigned long hash, flags = 0;
 	struct kretprobe_instance *ri;
 
-	/*
-	 * To avoid deadlocks, prohibit return probing in NMI contexts,
-	 * just skip the probe and increase the (inexact) 'nmissed'
-	 * statistical counter, so that the user is informed that
-	 * something happened:
-	 */
-	if (unlikely(in_nmi())) {
-		rp->nmissed++;
-		return 0;
-	}
-
 	/* TODO: consider to only swap the RA after the last pre_handler fired */
 	hash = hash_ptr(current, KPROBE_HASH_BITS);
 	raw_spin_lock_irqsave(&rp->lock, flags);