diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 214ac860ebe0d26df806999f880633919d1ad816..d8d86d01400866c6320001fb715301276747cd52 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -491,33 +491,78 @@ static void intel_pmu_enable_all(int added)
  *   Intel Errata AAP53  (model 30)
  *   Intel Errata BD53   (model 44)
  *
- * These chips need to be 'reset' when adding counters by programming
- * the magic three (non counting) events 0x4300D2, 0x4300B1 and 0x4300B5
- * either in sequence on the same PMC or on different PMCs.
+ * The official story:
+ *   These chips need to be 'reset' when adding counters by programming the
+ *   magic three (non-counting) events 0x4300B5, 0x4300D2, and 0x4300B1 either
+ *   in sequence on the same PMC or on different PMCs.
+ *
+ * In practise it appears some of these events do in fact count, and
+ * we need to programm all 4 events.
  */
-static void intel_pmu_nhm_enable_all(int added)
+static void intel_pmu_nhm_workaround(void)
 {
-	if (added) {
-		struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-		int i;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	static const unsigned long nhm_magic[4] = {
+		0x4300B5,
+		0x4300D2,
+		0x4300B1,
+		0x4300B1
+	};
+	struct perf_event *event;
+	int i;
+
+	/*
+	 * The Errata requires below steps:
+	 * 1) Clear MSR_IA32_PEBS_ENABLE and MSR_CORE_PERF_GLOBAL_CTRL;
+	 * 2) Configure 4 PERFEVTSELx with the magic events and clear
+	 *    the corresponding PMCx;
+	 * 3) set bit0~bit3 of MSR_CORE_PERF_GLOBAL_CTRL;
+	 * 4) Clear MSR_CORE_PERF_GLOBAL_CTRL;
+	 * 5) Clear 4 pairs of ERFEVTSELx and PMCx;
+	 */
+
+	/*
+	 * The real steps we choose are a little different from above.
+	 * A) To reduce MSR operations, we don't run step 1) as they
+	 *    are already cleared before this function is called;
+	 * B) Call x86_perf_event_update to save PMCx before configuring
+	 *    PERFEVTSELx with magic number;
+	 * C) With step 5), we do clear only when the PERFEVTSELx is
+	 *    not used currently.
+	 * D) Call x86_perf_event_set_period to restore PMCx;
+	 */
 
-		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 0, 0x4300D2);
-		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x4300B1);
-		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x4300B5);
+	/* We always operate 4 pairs of PERF Counters */
+	for (i = 0; i < 4; i++) {
+		event = cpuc->events[i];
+		if (event)
+			x86_perf_event_update(event);
+	}
 
-		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x3);
-		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
+	for (i = 0; i < 4; i++) {
+		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, nhm_magic[i]);
+		wrmsrl(MSR_ARCH_PERFMON_PERFCTR0 + i, 0x0);
+	}
 
-		for (i = 0; i < 3; i++) {
-			struct perf_event *event = cpuc->events[i];
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0xf);
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
 
-			if (!event)
-				continue;
+	for (i = 0; i < 4; i++) {
+		event = cpuc->events[i];
 
+		if (event) {
+			x86_perf_event_set_period(event);
 			__x86_pmu_enable_event(&event->hw,
-					       ARCH_PERFMON_EVENTSEL_ENABLE);
-		}
+					ARCH_PERFMON_EVENTSEL_ENABLE);
+		} else
+			wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, 0x0);
 	}
+}
+
+static void intel_pmu_nhm_enable_all(int added)
+{
+	if (added)
+		intel_pmu_nhm_workaround();
 	intel_pmu_enable_all(added);
 }
 
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 1bfb6cf4dd55d67aeeebbbf89d0bb60283a94c94..770ebfb349e93efe3367cf0c6caff93b61b8b884 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -709,6 +709,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	struct hlist_node *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);
@@ -740,14 +741,34 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			/* 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, node, 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) {
 			__get_cpu_var(current_kprobe) = &ri->rp->kp;
 			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
 			__get_cpu_var(current_kprobe) = NULL;
 		}
 
-		orig_ret_address = (unsigned long)ri->ret_addr;
 		recycle_rp_inst(ri, &empty_rp);
 
 		if (orig_ret_address != trampoline_address)
@@ -759,8 +780,6 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			break;
 	}
 
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
-
 	kretprobe_hash_unlock(current, &flags);
 
 	hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index dcb9700b88d2ec86c456c1185e99cf8b4619dfe4..4f1fa77c1feb0b7a854ab8a85bd21682cbc66377 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -5,6 +5,12 @@ endif
 # The default target of this Makefile is...
 all::
 
+ifneq ($(OUTPUT),)
+# check that the output directory actually exists
+OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
+$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
+endif
+
 # Define V=1 to have a more verbose compile.
 # Define V=2 to have an even more verbose compile.
 #
@@ -931,15 +937,15 @@ $(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
 	$(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
 
 $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
-	$(QUIET_GEN)$(RM) $@ $@+ && \
+	$(QUIET_GEN)$(RM) $(OUTPUT)$@ $(OUTPUT)$@+ && \
 	sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \
 	    -e 's|@SHELL_PATH@|$(SHELL_PATH_SQ)|' \
 	    -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \
 	    -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
 	    -e 's/@@NO_CURL@@/$(NO_CURL)/g' \
-	    $@.sh >$@+ && \
-	chmod +x $@+ && \
-	mv $@+ $(OUTPUT)$@
+	    $@.sh > $(OUTPUT)$@+ && \
+	chmod +x $(OUTPUT)$@+ && \
+	mv $(OUTPUT)$@+ $(OUTPUT)$@
 
 configure: configure.ac
 	$(QUIET_GEN)$(RM) $@ $<+ && \
diff --git a/tools/perf/feature-tests.mak b/tools/perf/feature-tests.mak
index ddb68e601f0ec2f67558afef92d3506f7661cd82..7a7b6085905382c791834b0c0f35ed5f39658e26 100644
--- a/tools/perf/feature-tests.mak
+++ b/tools/perf/feature-tests.mak
@@ -113,7 +113,7 @@ endef
 # try-cc
 # Usage: option = $(call try-cc, source-to-build, cc-options)
 try-cc = $(shell sh -c						  \
-	'TMP="$(TMPOUT).$$$$";			 		  \
+	'TMP="$(OUTPUT)$(TMPOUT).$$$$";				  \
 	 echo "$(1)" |						  \
 	 $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
 	 rm -f "$$TMP"')