diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 02d5e5e..895ae51 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -339,7 +339,7 @@ static int __init twd_local_timer_common_register(struct device_node *np)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_TWD_STARTING,
-				  "AP_ARM_TWD_STARTING",
+				  "arm/timer/twd:starting",
 				  twd_timer_starting_cpu, twd_timer_dying_cpu);
 
 	twd_get_clock(np);
diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index ba96bf9..6991577 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -60,6 +60,7 @@
 
 #define to_mmdc_pmu(p) container_of(p, struct mmdc_pmu, pmu)
 
+static enum cpuhp_state cpuhp_mmdc_state;
 static int ddr_type;
 
 struct fsl_mmdc_devtype_data {
@@ -451,8 +452,8 @@ static int imx_mmdc_remove(struct platform_device *pdev)
 {
 	struct mmdc_pmu *pmu_mmdc = platform_get_drvdata(pdev);
 
+	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	perf_pmu_unregister(&pmu_mmdc->pmu);
-	cpuhp_remove_state_nocalls(CPUHP_ONLINE);
 	kfree(pmu_mmdc);
 	return 0;
 }
@@ -472,6 +473,18 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 		return -ENOMEM;
 	}
 
+	/* The first instance registers the hotplug state */
+	if (!cpuhp_mmdc_state) {
+		ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+					      "perf/arm/mmdc:online", NULL,
+					      mmdc_pmu_offline_cpu);
+		if (ret < 0) {
+			pr_err("cpuhp_setup_state_multi failed\n");
+			goto pmu_free;
+		}
+		cpuhp_mmdc_state = ret;
+	}
+
 	mmdc_num = mmdc_pmu_init(pmu_mmdc, mmdc_base, &pdev->dev);
 	if (mmdc_num == 0)
 		name = "mmdc";
@@ -485,26 +498,23 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b
 			HRTIMER_MODE_REL);
 	pmu_mmdc->hrtimer.function = mmdc_pmu_timer_handler;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_ONLINE,
-					 &pmu_mmdc->node);
-	cpumask_set_cpu(smp_processor_id(), &pmu_mmdc->cpu);
-	ret = cpuhp_setup_state_multi(CPUHP_AP_NOTIFY_ONLINE,
-				      "MMDC_ONLINE", NULL,
-				      mmdc_pmu_offline_cpu);
-	if (ret) {
-		pr_err("cpuhp_setup_state_multi failure\n");
-		goto pmu_register_err;
-	}
+	cpumask_set_cpu(raw_smp_processor_id(), &pmu_mmdc->cpu);
+
+	/* Register the pmu instance for cpu hotplug */
+	cpuhp_state_add_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 
 	ret = perf_pmu_register(&(pmu_mmdc->pmu), name, -1);
-	platform_set_drvdata(pdev, pmu_mmdc);
 	if (ret)
 		goto pmu_register_err;
+
+	platform_set_drvdata(pdev, pmu_mmdc);
 	return 0;
 
 pmu_register_err:
 	pr_warn("MMDC Perf PMU failed (%d), disabled\n", ret);
+	cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
 	hrtimer_cancel(&pmu_mmdc->hrtimer);
+pmu_free:
 	kfree(pmu_mmdc);
 	return ret;
 }
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index ae2a018..8f8748a 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -148,7 +148,7 @@ static void __init armada_370_coherency_init(struct device_node *np)
 	of_node_put(cpu_config_np);
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_MVEBU_COHERENCY,
-				  "AP_ARM_MVEBU_COHERENCY",
+				  "arm/mvebu/coherency:starting",
 				  armada_xp_clear_l2_starting, NULL);
 exit:
 	set_cpu_coherent();
diff --git a/arch/arm/mm/cache-l2x0-pmu.c b/arch/arm/mm/cache-l2x0-pmu.c
index 976d305..0a1e228 100644
--- a/arch/arm/mm/cache-l2x0-pmu.c
+++ b/arch/arm/mm/cache-l2x0-pmu.c
@@ -563,7 +563,7 @@ static __init int l2x0_pmu_init(void)
 
 	cpumask_set_cpu(0, &pmu_cpu);
 	ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE,
-					"AP_PERF_ARM_L2X0_ONLINE", NULL,
+					"perf/arm/l2x0:online", NULL,
 					l2x0_pmu_offline_cpu);
 	if (ret)
 		goto out_pmu;
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index d1870c7..2290be3 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -683,7 +683,7 @@ static void __init l2c310_enable(void __iomem *base, unsigned num_lock)
 
 	if (aux & L310_AUX_CTRL_FULL_LINE_ZERO)
 		cpuhp_setup_state(CPUHP_AP_ARM_L2X0_STARTING,
-				  "AP_ARM_L2X0_STARTING", l2c310_starting_cpu,
+				  "arm/l2x0:starting", l2c310_starting_cpu,
 				  l2c310_dying_cpu);
 }
 
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 0351f56..569d5a6 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -799,7 +799,7 @@ static int __init vfp_init(void)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM_VFP_STARTING,
-				  "AP_ARM_VFP_STARTING", vfp_starting_cpu,
+				  "arm/vfp:starting", vfp_starting_cpu,
 				  vfp_dying_cpu);
 
 	vfp_vector = vfp_support_entry;
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 4986dc0..11d9f28 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -412,7 +412,7 @@ static int __init xen_guest_init(void)
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 
 	return cpuhp_setup_state(CPUHP_AP_ARM_XEN_STARTING,
-				 "AP_ARM_XEN_STARTING", xen_starting_cpu,
+				 "arm/xen:starting", xen_starting_cpu,
 				 xen_dying_cpu);
 }
 early_initcall(xen_guest_init);
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index fde04f0..ecf9298 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -640,7 +640,7 @@ static int __init armv8_deprecated_init(void)
 	}
 
 	cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING,
-				  "AP_ARM64_ISNDEP_STARTING",
+				  "arm64/isndep:starting",
 				  run_all_insn_set_hw_mode, NULL);
 	register_insn_emulation_sysctl(ctl_abi);
 
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 605df76..2bd4264 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -140,7 +140,7 @@ static int clear_os_lock(unsigned int cpu)
 static int debug_monitors_init(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
-				 "CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING",
+				 "arm64/debug_monitors:starting",
 				 clear_os_lock, NULL);
 }
 postcore_initcall(debug_monitors_init);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 1b3c747..0296e79 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -1001,7 +1001,7 @@ static int __init arch_hw_breakpoint_init(void)
 	 * debugger will leave the world in a nice state for us.
 	 */
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
-			  "CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING",
+			  "perf/arm64/hw_breakpoint:starting",
 			  hw_breakpoint_reset, NULL);
 	if (ret)
 		pr_err("failed to register CPU hotplug notifier: %d\n", ret);
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 6355e97..6a9524a 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -475,7 +475,7 @@ static int __init bfin_pmu_init(void)
 
 	ret = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 	if (!ret)
-		cpuhp_setup_state(CPUHP_PERF_BFIN, "PERF_BFIN",
+		cpuhp_setup_state(CPUHP_PERF_BFIN,"perf/bfin:starting",
 				  bfin_pmu_prepare_cpu, NULL);
 	return ret;
 }
diff --git a/arch/metag/kernel/perf/perf_event.c b/arch/metag/kernel/perf/perf_event.c
index 052cba2..7e793eb 100644
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -868,7 +868,7 @@ static int __init init_hw_perf_events(void)
 	metag_out32(0, PERF_COUNT(1));
 
 	cpuhp_setup_state(CPUHP_AP_PERF_METAG_STARTING,
-			  "AP_PERF_METAG_STARTING", metag_pmu_starting_cpu,
+			  "perf/metag:starting", metag_pmu_starting_cpu,
 			  NULL);
 
 	ret = perf_pmu_register(&pmu, metag_pmu->name, PERF_TYPE_RAW);
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index 7cf653e..5f928c3 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -713,7 +713,7 @@ static int __init cps_pm_init(void)
 		pr_warn("pm-cps: no CPC, clock & power gating unavailable\n");
 	}
 
-	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PM_CPS_CPU_ONLINE",
+	return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mips/cps_pm:online",
 				 cps_pm_online_cpu, NULL);
 }
 arch_initcall(cps_pm_init);
diff --git a/arch/mips/oprofile/op_model_loongson3.c b/arch/mips/oprofile/op_model_loongson3.c
index 4066039..436b1fc 100644
--- a/arch/mips/oprofile/op_model_loongson3.c
+++ b/arch/mips/oprofile/op_model_loongson3.c
@@ -186,7 +186,7 @@ static int __init loongson3_init(void)
 {
 	on_each_cpu(reset_counters, NULL, 1);
 	cpuhp_setup_state_nocalls(CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
-				  "AP_MIPS_OP_LOONGSON3_STARTING",
+				  "mips/oprofile/loongson3:starting",
 				  loongson3_starting_cpu, loongson3_dying_cpu);
 	save_perf_irq = perf_irq;
 	perf_irq = loongson3_perfcount_handler;
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 0cb6bd8..b1099cb 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -944,7 +944,7 @@ void __init initmem_init(void)
 	 * _nocalls() + manual invocation is used because cpuhp is not yet
 	 * initialized for the boot CPU.
 	 */
-	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "POWER_NUMA_PREPARE",
+	cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "powerpc/numa:prepare",
 				  ppc_numa_cpu_prepare, ppc_numa_cpu_dead);
 	for_each_present_cpu(cpu)
 		numa_setup_cpu(cpu);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 72c27b8..fd3e403 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2189,7 +2189,7 @@ int register_power_pmu(struct power_pmu *pmu)
 #endif /* CONFIG_PPC64 */
 
 	perf_pmu_register(&power_pmu, "cpu", PERF_TYPE_RAW);
-	cpuhp_setup_state(CPUHP_PERF_POWER, "PERF_POWER",
+	cpuhp_setup_state(CPUHP_PERF_POWER, "perf/powerpc:prepare",
 			  power_pmu_prepare_cpu, NULL);
 	return 0;
 }
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 037c2a2..1aba10e 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -711,7 +711,7 @@ static int __init cpumf_pmu_init(void)
 		return rc;
 	}
 	return cpuhp_setup_state(CPUHP_AP_PERF_S390_CF_ONLINE,
-				 "AP_PERF_S390_CF_ONLINE",
+				 "perf/s390/cf:online",
 				 s390_pmu_online_cpu, s390_pmu_offline_cpu);
 }
 early_initcall(cpumf_pmu_init);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 763dec1..1c0b585 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1623,7 +1623,7 @@ static int __init init_cpum_sampling_pmu(void)
 		goto out;
 	}
 
-	cpuhp_setup_state(CPUHP_AP_PERF_S390_SF_ONLINE, "AP_PERF_S390_SF_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_PERF_S390_SF_ONLINE, "perf/s390/sf:online",
 			  s390_pmu_sf_online_cpu, s390_pmu_sf_offline_cpu);
 out:
 	return err;
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 40121d1..10820f6 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -371,7 +371,7 @@ static int __init init_vdso(void)
 
 	/* notifier priority > KVM */
 	return cpuhp_setup_state(CPUHP_AP_X86_VDSO_VMA_ONLINE,
-				 "AP_X86_VDSO_VMA_ONLINE", vgetcpu_online, NULL);
+				 "x86/vdso/vma:online", vgetcpu_online, NULL);
 }
 subsys_initcall(init_vdso);
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index b26ee32..05612a2 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1010,7 +1010,7 @@ static __init int amd_ibs_init(void)
 	 * all online cpus.
 	 */
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
-			  "AP_PERF_X86_AMD_IBS_STARTING",
+			  "perf/x86/amd/ibs:STARTING",
 			  x86_pmu_amd_ibs_starting_cpu,
 			  x86_pmu_amd_ibs_dying_cpu);
 
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index 9842270..a6eee5a 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -291,7 +291,7 @@ static int __init amd_power_pmu_init(void)
 
 
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
-			  "AP_PERF_X86_AMD_POWER_ONLINE",
+			  "perf/x86/amd/power:online",
 			  power_cpu_init, power_cpu_exit);
 
 	ret = perf_pmu_register(&pmu_class, "power", -1);
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 65577f0..a0b1bdb 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -527,16 +527,16 @@ static int __init amd_uncore_init(void)
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
 	if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
-			      "PERF_X86_AMD_UNCORE_PREP",
+			      "perf/x86/amd/uncore:prepare",
 			      amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
 		goto fail_l2;
 
 	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
-			      "AP_PERF_X86_AMD_UNCORE_STARTING",
+			      "perf/x86/amd/uncore:starting",
 			      amd_uncore_cpu_starting, NULL))
 		goto fail_prep;
 	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
-			      "AP_PERF_X86_AMD_UNCORE_ONLINE",
+			      "perf/x86/amd/uncore:online",
 			      amd_uncore_cpu_online,
 			      amd_uncore_cpu_down_prepare))
 		goto fail_start;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index f1c2258..019c588 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1820,18 +1820,18 @@ static int __init init_hw_perf_events(void)
 	 * Install callbacks. Core will call them for each online
 	 * cpu.
 	 */
-	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "PERF_X86_PREPARE",
+	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "perf/x86:prepare",
 				x86_pmu_prepare_cpu, x86_pmu_dead_cpu);
 	if (err)
 		return err;
 
 	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_STARTING,
-				"AP_PERF_X86_STARTING", x86_pmu_starting_cpu,
+				"perf/x86:starting", x86_pmu_starting_cpu,
 				x86_pmu_dying_cpu);
 	if (err)
 		goto out;
 
-	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "AP_PERF_X86_ONLINE",
+	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "perf/x86:online",
 				x86_pmu_online_cpu, NULL);
 	if (err)
 		goto out1;
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 0c45cc8..8c00dc0 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -1747,9 +1747,9 @@ static int __init intel_cqm_init(void)
 	 * is enabled to avoid notifier leak.
 	 */
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING,
-			  "AP_PERF_X86_CQM_STARTING",
+			  "perf/x86/cqm:starting",
 			  intel_cqm_cpu_starting, NULL);
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "AP_PERF_X86_CQM_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "perf/x86/cqm:online",
 			  NULL, intel_cqm_cpu_exit);
 
 out:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index da51e5a..fec8a46 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -594,6 +594,9 @@ static int __init cstate_probe(const struct cstate_model *cm)
 
 static inline void cstate_cleanup(void)
 {
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_ONLINE);
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_STARTING);
+
 	if (has_cstate_core)
 		perf_pmu_unregister(&cstate_core_pmu);
 
@@ -606,16 +609,16 @@ static int __init cstate_init(void)
 	int err;
 
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_STARTING,
-			  "AP_PERF_X86_CSTATE_STARTING", cstate_cpu_init,
-			  NULL);
+			  "perf/x86/cstate:starting", cstate_cpu_init, NULL);
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_ONLINE,
-			  "AP_PERF_X86_CSTATE_ONLINE", NULL, cstate_cpu_exit);
+			  "perf/x86/cstate:online", NULL, cstate_cpu_exit);
 
 	if (has_cstate_core) {
 		err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1);
 		if (err) {
 			has_cstate_core = false;
 			pr_info("Failed to register cstate core pmu\n");
+			cstate_cleanup();
 			return err;
 		}
 	}
@@ -629,8 +632,7 @@ static int __init cstate_init(void)
 			return err;
 		}
 	}
-
-	return err;
+	return 0;
 }
 
 static int __init cstate_pmu_init(void)
@@ -655,8 +657,6 @@ module_init(cstate_pmu_init);
 
 static void __exit cstate_pmu_exit(void)
 {
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_STARTING);
 	cstate_cleanup();
 }
 module_exit(cstate_pmu_exit);
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 0a535ce..bd34124 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -803,13 +803,13 @@ static int __init rapl_pmu_init(void)
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
 
-	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "PERF_X86_RAPL_PREP",
+	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
 				rapl_cpu_prepare, NULL);
 	if (ret)
 		goto out;
 
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
-				"AP_PERF_X86_RAPL_ONLINE",
+				"perf/x86/rapl:online",
 				rapl_cpu_online, rapl_cpu_offline);
 	if (ret)
 		goto out1;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index dbaaf7dc..97c246f 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1398,22 +1398,22 @@ static int __init intel_uncore_init(void)
 	 */
 	if (!cret) {
 	       ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
-					"PERF_X86_UNCORE_PREP",
-					uncore_cpu_prepare, NULL);
+				       "perf/x86/intel/uncore:prepare",
+				       uncore_cpu_prepare, NULL);
 		if (ret)
 			goto err;
 	} else {
 		cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
-					  "PERF_X86_UNCORE_PREP",
+					  "perf/x86/intel/uncore:prepare",
 					  uncore_cpu_prepare, NULL);
 	}
 	first_init = 1;
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
-			  "AP_PERF_X86_UNCORE_STARTING",
+			  "perf/x86/uncore:starting",
 			  uncore_cpu_starting, uncore_cpu_dying);
 	first_init = 0;
 	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
-			  "AP_PERF_X86_UNCORE_ONLINE",
+			  "perf/x86/uncore:online",
 			  uncore_event_cpu_online, uncore_event_cpu_offline);
 	return 0;
 
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 092ea66..65721dc 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -234,7 +234,7 @@ static __init int apbt_late_init(void)
 	if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ||
 		!apb_timer_block_enabled)
 		return 0;
-	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "X86_APB_DEAD", NULL,
+	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "x86/apb:dead", NULL,
 				 apbt_cpu_dead);
 }
 fs_initcall(apbt_late_init);
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 200af5a..5a35f20 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -191,7 +191,7 @@ static int x2apic_cluster_probe(void)
 	if (!x2apic_mode)
 		return 0;
 
-	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare",
 				x2apic_prepare_cpu, x2apic_dead_cpu);
 	if (ret < 0) {
 		pr_err("Failed to register X2APIC_PREPARE\n");
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 367756d..85e87b4 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1051,11 +1051,11 @@ static __init int hpet_late_init(void)
 		return 0;
 
 	/* This notifier should be called after workqueue is ready */
-	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "AP_X86_HPET_ONLINE",
+	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "x86/hpet:online",
 				hpet_cpuhp_online, NULL);
 	if (ret)
 		return ret;
-	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "X86_HPET_DEAD", NULL,
+	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "x86/hpet:dead", NULL,
 				hpet_cpuhp_dead);
 	if (ret)
 		goto err_cpuhp;
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index f5e3ff8..ef68880 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -224,7 +224,6 @@ static int __init msr_init(void)
 	return 0;
 
 out_class:
-	cpuhp_remove_state(cpuhp_msr_state);
 	class_destroy(msr_class);
 out_chrdev:
 	__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 8402907..b868fa1 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -408,7 +408,7 @@ static __init int tboot_late_init(void)
 	tboot_create_trampoline();
 
 	atomic_set(&ap_wfs_count, 0);
-	cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "AP_X86_TBOOT_DYING", NULL,
+	cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "x86/tboot:dying", NULL,
 			  tboot_dying_cpu);
 #ifdef CONFIG_DEBUG_FS
 	debugfs_create_file("tboot_log", S_IRUSR,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ed04398..51ccfe0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5855,7 +5855,7 @@ static void kvm_timer_init(void)
 	}
 	pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
 
-	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "AP_X86_KVM_CLK_ONLINE",
+	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
 			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
 }
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ced7027..51ef952 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1529,11 +1529,11 @@ static int xen_cpuhp_setup(void)
 	int rc;
 
 	rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE,
-				       "XEN_HVM_GUEST_PREPARE",
+				       "x86/xen/hvm_guest:prepare",
 				       xen_cpu_up_prepare, xen_cpu_dead);
 	if (rc >= 0) {
 		rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-					       "XEN_HVM_GUEST_ONLINE",
+					       "x86/xen/hvm_guest:online",
 					       xen_cpu_up_online, NULL);
 		if (rc < 0)
 			cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE);
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index 0fecc8a..ff1d813 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -422,7 +422,7 @@ static int __init xtensa_pmu_init(void)
 	int irq = irq_create_mapping(NULL, XCHAL_PROFILING_INTERRUPT);
 
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_XTENSA_STARTING,
-				"AP_PERF_XTENSA_STARTING", xtensa_pmu_setup,
+				"perf/xtensa:starting", xtensa_pmu_setup,
 				NULL);
 	if (ret) {
 		pr_err("xtensa_pmu: failed to register CPU-hotplug.\n");
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 2316333..c49da15 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -1796,7 +1796,7 @@ static int __init cci_platform_init(void)
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCI_ONLINE,
-				      "AP_PERF_ARM_CCI_ONLINE", NULL,
+				      "perf/arm/cci:online", NULL,
 				      cci_pmu_offline_cpu);
 	if (ret)
 		return ret;
diff --git a/drivers/bus/arm-ccn.c b/drivers/bus/arm-ccn.c
index d1074d9..4d6a2b7 100644
--- a/drivers/bus/arm-ccn.c
+++ b/drivers/bus/arm-ccn.c
@@ -1562,7 +1562,7 @@ static int __init arm_ccn_init(void)
 	int i, ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCN_ONLINE,
-				      "AP_PERF_ARM_CCN_ONLINE", NULL,
+				      "perf/arm/ccn:online", NULL,
 				      arm_ccn_pmu_offline_cpu);
 	if (ret)
 		return ret;
@@ -1570,7 +1570,10 @@ static int __init arm_ccn_init(void)
 	for (i = 0; i < ARRAY_SIZE(arm_ccn_pmu_events); i++)
 		arm_ccn_pmu_events_attrs[i] = &arm_ccn_pmu_events[i].attr.attr;
 
-	return platform_driver_register(&arm_ccn_driver);
+	ret = platform_driver_register(&arm_ccn_driver);
+	if (ret)
+		cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_CCN_ONLINE);
+	return ret;
 }
 
 static void __exit arm_ccn_exit(void)
diff --git a/drivers/clocksource/arc_timer.c b/drivers/clocksource/arc_timer.c
index 3ea4634..7517f95 100644
--- a/drivers/clocksource/arc_timer.c
+++ b/drivers/clocksource/arc_timer.c
@@ -309,7 +309,7 @@ static int __init arc_clockevent_setup(struct device_node *node)
 	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_ARC_TIMER_STARTING,
-				"AP_ARC_TIMER_STARTING",
+				"clockevents/arc/timer:starting",
 				arc_timer_starting_cpu,
 				arc_timer_dying_cpu);
 	if (ret) {
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 394e417..4c8c3fb 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -738,7 +738,7 @@ static int __init arch_timer_register(void)
 
 	/* Register and immediately configure the timer on the boot CPU */
 	err = cpuhp_setup_state(CPUHP_AP_ARM_ARCH_TIMER_STARTING,
-				"AP_ARM_ARCH_TIMER_STARTING",
+				"clockevents/arm/arch_timer:starting",
 				arch_timer_starting_cpu, arch_timer_dying_cpu);
 	if (err)
 		goto out_unreg_cpupm;
diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c
index 570cc58..123ed20 100644
--- a/drivers/clocksource/arm_global_timer.c
+++ b/drivers/clocksource/arm_global_timer.c
@@ -316,7 +316,7 @@ static int __init global_timer_of_register(struct device_node *np)
 		goto out_irq;
 	
 	err = cpuhp_setup_state(CPUHP_AP_ARM_GLOBAL_TIMER_STARTING,
-				"AP_ARM_GLOBAL_TIMER_STARTING",
+				"clockevents/arm/global_timer:starting",
 				gt_starting_cpu, gt_dying_cpu);
 	if (err)
 		goto out_irq;
diff --git a/drivers/clocksource/dummy_timer.c b/drivers/clocksource/dummy_timer.c
index 89f1c2e..01f3f5a 100644
--- a/drivers/clocksource/dummy_timer.c
+++ b/drivers/clocksource/dummy_timer.c
@@ -34,7 +34,7 @@ static int dummy_timer_starting_cpu(unsigned int cpu)
 static int __init dummy_timer_register(void)
 {
 	return cpuhp_setup_state(CPUHP_AP_DUMMY_TIMER_STARTING,
-				 "AP_DUMMY_TIMER_STARTING",
+				 "clockevents/dummy_timer:starting",
 				 dummy_timer_starting_cpu, NULL);
 }
 early_initcall(dummy_timer_register);
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index c8b9f834..4da1dc2 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -552,7 +552,7 @@ static int __init exynos4_timer_resources(struct device_node *np, void __iomem *
 
 	/* Install hotplug callbacks which configure the timer on this CPU */
 	err = cpuhp_setup_state(CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
-				"AP_EXYNOS4_MCT_TIMER_STARTING",
+				"clockevents/exynos4/mct_timer:starting",
 				exynos4_mct_starting_cpu,
 				exynos4_mct_dying_cpu);
 	if (err)
diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c
index e90a6cf..7c61226 100644
--- a/drivers/clocksource/jcore-pit.c
+++ b/drivers/clocksource/jcore-pit.c
@@ -240,7 +240,7 @@ static int __init jcore_pit_init(struct device_node *node)
 	}
 
 	cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING,
-			  "AP_JCORE_TIMER_STARTING",
+			  "clockevents/jcore:starting",
 			  jcore_pit_local_init, NULL);
 
 	return 0;
diff --git a/drivers/clocksource/metag_generic.c b/drivers/clocksource/metag_generic.c
index 8d06a0f..6fcf965 100644
--- a/drivers/clocksource/metag_generic.c
+++ b/drivers/clocksource/metag_generic.c
@@ -154,6 +154,6 @@ int __init metag_generic_timer_init(void)
 
 	/* Hook cpu boot to configure the CPU's timers */
 	return cpuhp_setup_state(CPUHP_AP_METAG_TIMER_STARTING,
-				 "AP_METAG_TIMER_STARTING",
+				 "clockevents/metag:starting",
 				 arch_timer_starting_cpu, NULL);
 }
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index 7b86d07..d9ef7a6 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -120,8 +120,8 @@ static int gic_clockevent_init(void)
 	}
 
 	cpuhp_setup_state(CPUHP_AP_MIPS_GIC_TIMER_STARTING,
-			  "AP_MIPS_GIC_TIMER_STARTING", gic_starting_cpu,
-			  gic_dying_cpu);
+			  "clockevents/mips/gic/timer:starting",
+			  gic_starting_cpu, gic_dying_cpu);
 	return 0;
 }
 
diff --git a/drivers/clocksource/qcom-timer.c b/drivers/clocksource/qcom-timer.c
index d5d048d..ee358cd 100644
--- a/drivers/clocksource/qcom-timer.c
+++ b/drivers/clocksource/qcom-timer.c
@@ -182,7 +182,7 @@ static int __init msm_timer_init(u32 dgt_hz, int sched_bits, int irq,
 	} else {
 		/* Install and invoke hotplug callbacks */
 		res = cpuhp_setup_state(CPUHP_AP_QCOM_TIMER_STARTING,
-					"AP_QCOM_TIMER_STARTING",
+					"clockevents/qcom/timer:starting",
 					msm_local_timer_starting_cpu,
 					msm_local_timer_dying_cpu);
 		if (res) {
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index 3c39e6f..4440aef 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -320,7 +320,7 @@ static int __init armada_370_xp_timer_common_init(struct device_node *np)
 	}
 
 	res = cpuhp_setup_state(CPUHP_AP_ARMADA_TIMER_STARTING,
-				"AP_ARMADA_TIMER_STARTING",
+				"clockevents/armada:starting",
 				armada_370_xp_timer_starting_cpu,
 				armada_370_xp_timer_dying_cpu);
 	if (res) {
diff --git a/drivers/clocksource/timer-atlas7.c b/drivers/clocksource/timer-atlas7.c
index db0f21e..3d8a181 100644
--- a/drivers/clocksource/timer-atlas7.c
+++ b/drivers/clocksource/timer-atlas7.c
@@ -221,7 +221,7 @@ static int __init sirfsoc_clockevent_init(void)
 
 	/* Install and invoke hotplug callbacks */
 	return cpuhp_setup_state(CPUHP_AP_MARCO_TIMER_STARTING,
-				 "AP_MARCO_TIMER_STARTING",
+				 "clockevents/marco:starting",
 				 sirfsoc_local_timer_starting_cpu,
 				 sirfsoc_local_timer_dying_cpu);
 }
diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x.c
index 3fe368b..a51b6b6 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -804,10 +804,10 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 
 	if (!etm_count++) {
 		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
-					  "AP_ARM_CORESIGHT_STARTING",
+					  "arm/coresight:starting",
 					  etm_starting_cpu, etm_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"AP_ARM_CORESIGHT_ONLINE",
+						"arm/coresight:online",
 						etm_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index 4db8d6a..031480f 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -986,11 +986,11 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_err(dev, "ETM arch init failed\n");
 
 	if (!etm4_count++) {
-		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING,
-					  "AP_ARM_CORESIGHT4_STARTING",
+		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
+					  "arm/coresight4:starting",
 					  etm4_starting_cpu, etm4_dying_cpu);
 		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"AP_ARM_CORESIGHT4_ONLINE",
+						"arm/coresight4:online",
 						etm4_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
@@ -1037,7 +1037,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 err_arch_supported:
 	if (--etm4_count == 0) {
-		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT4_STARTING);
+		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING);
 		if (hp_online)
 			cpuhp_remove_state_nocalls(hp_online);
 	}
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 8bcee65..eb0d4d4 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -578,13 +578,13 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 #ifdef CONFIG_SMP
 		set_smp_cross_call(armada_mpic_send_doorbell);
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
-					  "AP_IRQ_ARMADA_XP_STARTING",
+					  "irqchip/armada/ipi:starting",
 					  armada_xp_mpic_starting_cpu, NULL);
 #endif
 	} else {
 #ifdef CONFIG_SMP
-		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
-					  "AP_IRQ_ARMADA_CASC_STARTING",
+		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
+					  "irqchip/armada/cascade:starting",
 					  mpic_cascaded_starting_cpu, NULL);
 #endif
 		irq_set_chained_handler(parent_irq,
diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c
index d96b2c9..e7463e3 100644
--- a/drivers/irqchip/irq-bcm2836.c
+++ b/drivers/irqchip/irq-bcm2836.c
@@ -245,7 +245,7 @@ bcm2836_arm_irqchip_smp_init(void)
 #ifdef CONFIG_SMP
 	/* Unmask IPIs to the boot CPU. */
 	cpuhp_setup_state(CPUHP_AP_IRQ_BCM2836_STARTING,
-			  "AP_IRQ_BCM2836_STARTING", bcm2836_cpu_starting,
+			  "irqchip/bcm2836:starting", bcm2836_cpu_starting,
 			  bcm2836_cpu_dying);
 
 	set_smp_cross_call(bcm2836_arm_irqchip_send_ipi);
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 26e1d7f..c132f29 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -632,9 +632,9 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 static void gic_smp_init(void)
 {
 	set_smp_cross_call(gic_raise_softirq);
-	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GICV3_STARTING,
-				  "AP_IRQ_GICV3_STARTING", gic_starting_cpu,
-				  NULL);
+	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
+				  "irqchip/arm/gicv3:starting",
+				  gic_starting_cpu, NULL);
 }
 
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index d6c404b..1b1df4f 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1191,7 +1191,7 @@ static int __init __gic_init_bases(struct gic_chip_data *gic,
 		set_smp_cross_call(gic_raise_softirq);
 #endif
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
-					  "AP_IRQ_GIC_STARTING",
+					  "irqchip/arm/gic:starting",
 					  gic_starting_cpu, NULL);
 		set_handle_irq(gic_handle_irq);
 		if (static_key_true(&supports_deactivate))
diff --git a/drivers/irqchip/irq-hip04.c b/drivers/irqchip/irq-hip04.c
index 021b0e0..c1b4ee9 100644
--- a/drivers/irqchip/irq-hip04.c
+++ b/drivers/irqchip/irq-hip04.c
@@ -407,7 +407,7 @@ hip04_of_init(struct device_node *node, struct device_node *parent)
 	set_handle_irq(hip04_handle_irq);
 
 	hip04_irq_dist_init(&hip04_data);
-	cpuhp_setup_state(CPUHP_AP_IRQ_HIP04_STARTING, "AP_IRQ_HIP04_STARTING",
+	cpuhp_setup_state(CPUHP_AP_IRQ_HIP04_STARTING, "irqchip/hip04:starting",
 			  hip04_irq_starting_cpu, NULL);
 	return 0;
 }
diff --git a/drivers/leds/trigger/ledtrig-cpu.c b/drivers/leds/trigger/ledtrig-cpu.c
index 9719caf..a418964 100644
--- a/drivers/leds/trigger/ledtrig-cpu.c
+++ b/drivers/leds/trigger/ledtrig-cpu.c
@@ -127,7 +127,7 @@ static int __init ledtrig_cpu_init(void)
 
 	register_syscore_ops(&ledtrig_cpu_syscore_ops);
 
-	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_LEDTRIG_STARTING",
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "leds/trigger:starting",
 				ledtrig_online_cpu, ledtrig_prepare_down_cpu);
 	if (ret < 0)
 		pr_err("CPU hotplug notifier for ledtrig-cpu could not be registered: %d\n",
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5deeda6..4a10500 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2484,13 +2484,13 @@ static __init int virtio_net_driver_init(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "AP_VIRT_NET_ONLINE",
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "virtio/net:online",
 				      virtnet_cpu_online,
 				      virtnet_cpu_down_prep);
 	if (ret < 0)
 		goto out;
 	virtionet_online = ret;
-	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "VIRT_NET_DEAD",
+	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "virtio/net:dead",
 				      NULL, virtnet_cpu_dead);
 	if (ret)
 		goto err_dead;
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index b37b572..6d93358 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -1084,7 +1084,7 @@ static int arm_pmu_hp_init(void)
 	int ret;
 
 	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_STARTING,
-				      "AP_PERF_ARM_STARTING",
+				      "perf/arm/pmu:starting",
 				      arm_perf_starting_cpu, NULL);
 	if (ret)
 		pr_err("CPU hotplug notifier for ARM PMU could not be registered: %d\n",
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 0990130..c639d5a0 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -127,13 +127,6 @@ module_param_named(log_fka, bnx2fc_log_fka, uint, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(log_fka, " Print message to kernel log when fcoe is "
 	"initiating a FIP keep alive when debug logging is enabled.");
 
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2fc_cpu_notifier = {
-	.notifier_call = bnx2fc_cpu_callback,
-};
-
 static inline struct net_device *bnx2fc_netdev(const struct fc_lport *lport)
 {
 	return ((struct bnx2fc_interface *)
@@ -2622,37 +2615,19 @@ static void bnx2fc_percpu_thread_destroy(unsigned int cpu)
 		kthread_stop(thread);
 }
 
-/**
- * bnx2fc_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:    The callback data block
- * @action: The event triggering the callback
- * @hcpu:   The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for fcoe
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2fc_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu)
-{
-	unsigned cpu = (unsigned long)hcpu;
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(PFX "CPU %x online: Create Rx thread\n", cpu);
-		bnx2fc_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2fc_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+static int bnx2fc_cpu_online(unsigned int cpu)
+{
+	printk(PFX "CPU %x online: Create Rx thread\n", cpu);
+	bnx2fc_percpu_thread_create(cpu);
+	return 0;
+}
+
+static int bnx2fc_cpu_dead(unsigned int cpu)
+{
+	printk(PFX "CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2fc_percpu_thread_destroy(cpu);
+	return 0;
 }
 
 static int bnx2fc_slave_configure(struct scsi_device *sdev)
@@ -2664,6 +2639,8 @@ static int bnx2fc_slave_configure(struct scsi_device *sdev)
 	return 0;
 }
 
+static enum cpuhp_state bnx2fc_online_state;
+
 /**
  * bnx2fc_mod_init - module init entry point
  *
@@ -2724,21 +2701,31 @@ static int __init bnx2fc_mod_init(void)
 		spin_lock_init(&p->fp_work_lock);
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
-	for_each_online_cpu(cpu) {
+	for_each_online_cpu(cpu)
 		bnx2fc_percpu_thread_create(cpu);
-	}
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2fc_cpu_notifier);
+	rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2fc:online",
+				       bnx2fc_cpu_online, NULL);
+	if (rc < 0)
+		goto stop_threads;
+	bnx2fc_online_state = rc;
 
-	cpu_notifier_register_done();
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD, "scsi/bnx2fc:dead",
+				  NULL, bnx2fc_cpu_dead);
+	put_online_cpus();
 
 	cnic_register_driver(CNIC_ULP_FCOE, &bnx2fc_cnic_cb);
 
 	return 0;
 
+stop_threads:
+	for_each_online_cpu(cpu)
+		bnx2fc_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	kthread_stop(l2_thread);
 free_wq:
 	destroy_workqueue(bnx2fc_wq);
 release_bt:
@@ -2797,16 +2784,16 @@ static void __exit bnx2fc_mod_exit(void)
 	if (l2_thread)
 		kthread_stop(l2_thread);
 
-	cpu_notifier_register_begin();
-
+	get_online_cpus();
 	/* Destroy per cpu threads */
 	for_each_online_cpu(cpu) {
 		bnx2fc_percpu_thread_destroy(cpu);
 	}
 
-	__unregister_hotcpu_notifier(&bnx2fc_cpu_notifier);
+	cpuhp_remove_state_nocalls(bnx2fc_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2FC_DEAD);
 
-	cpu_notifier_register_done();
+	put_online_cpus();
 
 	destroy_workqueue(bnx2fc_wq);
 	/*
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index c8b410c..86afc00 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
+++ b/drivers/scsi/bnx2i/bnx2i_init.c
@@ -70,14 +70,6 @@ u64 iscsi_error_mask = 0x00;
 
 DEFINE_PER_CPU(struct bnx2i_percpu_s, bnx2i_percpu);
 
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu);
-/* notification function for CPU hotplug events */
-static struct notifier_block bnx2i_cpu_notifier = {
-	.notifier_call = bnx2i_cpu_callback,
-};
-
-
 /**
  * bnx2i_identify_device - identifies NetXtreme II device type
  * @hba: 		Adapter structure pointer
@@ -461,41 +453,21 @@ static void bnx2i_percpu_thread_destroy(unsigned int cpu)
 		kthread_stop(thread);
 }
 
-
-/**
- * bnx2i_cpu_callback - Handler for CPU hotplug events
- *
- * @nfb:	The callback data block
- * @action:	The event triggering the callback
- * @hcpu:	The index of the CPU that the event is for
- *
- * This creates or destroys per-CPU data for iSCSI
- *
- * Returns NOTIFY_OK always.
- */
-static int bnx2i_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action, void *hcpu)
+static int bnx2i_cpu_online(unsigned int cpu)
 {
-	unsigned cpu = (unsigned long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		printk(KERN_INFO "bnx2i: CPU %x online: Create Rx thread\n",
-			cpu);
-		bnx2i_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		printk(KERN_INFO "CPU %x offline: Remove Rx thread\n", cpu);
-		bnx2i_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+	pr_info("bnx2i: CPU %x online: Create Rx thread\n", cpu);
+	bnx2i_percpu_thread_create(cpu);
+	return 0;
 }
 
+static int bnx2i_cpu_dead(unsigned int cpu)
+{
+	pr_info("CPU %x offline: Remove Rx thread\n", cpu);
+	bnx2i_percpu_thread_destroy(cpu);
+	return 0;
+}
+
+static enum cpuhp_state bnx2i_online_state;
 
 /**
  * bnx2i_mod_init - module init entry point
@@ -539,18 +511,28 @@ static int __init bnx2i_mod_init(void)
 		p->iothread = NULL;
 	}
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_create(cpu);
 
-	/* Initialize per CPU interrupt thread */
-	__register_hotcpu_notifier(&bnx2i_cpu_notifier);
+	err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				       "scsi/bnx2i:online",
+				       bnx2i_cpu_online, NULL);
+	if (err < 0)
+		goto remove_threads;
+	bnx2i_online_state = err;
 
-	cpu_notifier_register_done();
-
+	cpuhp_setup_state_nocalls(CPUHP_SCSI_BNX2I_DEAD, "scsi/bnx2i:dead",
+				  NULL, bnx2i_cpu_dead);
+	put_online_cpus();
 	return 0;
 
+remove_threads:
+	for_each_online_cpu(cpu)
+		bnx2i_percpu_thread_destroy(cpu);
+	put_online_cpus();
+	cnic_unregister_driver(CNIC_ULP_ISCSI);
 unreg_xport:
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 out:
@@ -587,14 +569,14 @@ static void __exit bnx2i_mod_exit(void)
 	}
 	mutex_unlock(&bnx2i_dev_lock);
 
-	cpu_notifier_register_begin();
+	get_online_cpus();
 
 	for_each_online_cpu(cpu)
 		bnx2i_percpu_thread_destroy(cpu);
 
-	__unregister_hotcpu_notifier(&bnx2i_cpu_notifier);
-
-	cpu_notifier_register_done();
+	cpuhp_remove_state_nocalls(bnx2i_online_state);
+	cpuhp_remove_state_nocalls(CPUHP_SCSI_BNX2I_DEAD);
+	put_online_cpus();
 
 	iscsi_unregister_transport(&bnx2i_iscsi_transport);
 	cnic_unregister_driver(CNIC_ULP_ISCSI);
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index 19ead8d..5eda21d 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -1612,30 +1612,29 @@ static int qedi_percpu_io_thread(void *arg)
 	return 0;
 }
 
-static void qedi_percpu_thread_create(unsigned int cpu)
+static int qedi_cpu_online(unsigned int cpu)
 {
-	struct qedi_percpu_s *p;
+	struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu);
 	struct task_struct *thread;
 
-	p = &per_cpu(qedi_percpu, cpu);
-
 	thread = kthread_create_on_node(qedi_percpu_io_thread, (void *)p,
 					cpu_to_node(cpu),
 					"qedi_thread/%d", cpu);
-	if (likely(!IS_ERR(thread))) {
-		kthread_bind(thread, cpu);
-		p->iothread = thread;
-		wake_up_process(thread);
-	}
+	if (IS_ERR(thread))
+		return PTR_ERR(thread);
+
+	kthread_bind(thread, cpu);
+	p->iothread = thread;
+	wake_up_process(thread);
+	return 0;
 }
 
-static void qedi_percpu_thread_destroy(unsigned int cpu)
+static int qedi_cpu_offline(unsigned int cpu)
 {
-	struct qedi_percpu_s *p;
-	struct task_struct *thread;
+	struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu);
 	struct qedi_work *work, *tmp;
+	struct task_struct *thread;
 
-	p = &per_cpu(qedi_percpu, cpu);
 	spin_lock_bh(&p->p_work_lock);
 	thread = p->iothread;
 	p->iothread = NULL;
@@ -1650,35 +1649,9 @@ static void qedi_percpu_thread_destroy(unsigned int cpu)
 	spin_unlock_bh(&p->p_work_lock);
 	if (thread)
 		kthread_stop(thread);
+	return 0;
 }
 
-static int qedi_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		QEDI_ERR(NULL, "CPU %d online.\n", cpu);
-		qedi_percpu_thread_create(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		QEDI_ERR(NULL, "CPU %d offline.\n", cpu);
-		qedi_percpu_thread_destroy(cpu);
-		break;
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block qedi_cpu_notifier = {
-	.notifier_call = qedi_cpu_callback,
-};
-
 void qedi_reset_host_mtu(struct qedi_ctx *qedi, u16 mtu)
 {
 	struct qed_ll2_params params;
@@ -2038,6 +2011,8 @@ static struct pci_device_id qedi_pci_tbl[] = {
 };
 MODULE_DEVICE_TABLE(pci, qedi_pci_tbl);
 
+static enum cpuhp_state qedi_cpuhp_state;
+
 static struct pci_driver qedi_pci_driver = {
 	.name = QEDI_MODULE_NAME,
 	.id_table = qedi_pci_tbl,
@@ -2047,16 +2022,13 @@ static struct pci_driver qedi_pci_driver = {
 
 static int __init qedi_init(void)
 {
-	int rc = 0;
-	int ret;
 	struct qedi_percpu_s *p;
-	unsigned int cpu = 0;
+	int cpu, rc = 0;
 
 	qedi_ops = qed_get_iscsi_ops();
 	if (!qedi_ops) {
 		QEDI_ERR(NULL, "Failed to get qed iSCSI operations\n");
-		rc = -EINVAL;
-		goto exit_qedi_init_0;
+		return -EINVAL;
 	}
 
 #ifdef CONFIG_DEBUG_FS
@@ -2070,15 +2042,6 @@ static int __init qedi_init(void)
 		goto exit_qedi_init_1;
 	}
 
-	register_hotcpu_notifier(&qedi_cpu_notifier);
-
-	ret = pci_register_driver(&qedi_pci_driver);
-	if (ret) {
-		QEDI_ERR(NULL, "Failed to register driver\n");
-		rc = -EINVAL;
-		goto exit_qedi_init_2;
-	}
-
 	for_each_possible_cpu(cpu) {
 		p = &per_cpu(qedi_percpu, cpu);
 		INIT_LIST_HEAD(&p->work_list);
@@ -2086,11 +2049,22 @@ static int __init qedi_init(void)
 		p->iothread = NULL;
 	}
 
-	for_each_online_cpu(cpu)
-		qedi_percpu_thread_create(cpu);
+	rc = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "scsi/qedi:online",
+			       qedi_cpu_online, qedi_cpu_offline);
+	if (rc < 0)
+		goto exit_qedi_init_2;
+	qedi_cpuhp_state = rc;
 
-	return rc;
+	rc = pci_register_driver(&qedi_pci_driver);
+	if (rc) {
+		QEDI_ERR(NULL, "Failed to register driver\n");
+		goto exit_qedi_hp;
+	}
 
+	return 0;
+
+exit_qedi_hp:
+	cpuhp_remove_state(qedi_cpuhp_state);
 exit_qedi_init_2:
 	iscsi_unregister_transport(&qedi_iscsi_transport);
 exit_qedi_init_1:
@@ -2098,19 +2072,13 @@ static int __init qedi_init(void)
 	qedi_dbg_exit();
 #endif
 	qed_put_iscsi_ops();
-exit_qedi_init_0:
 	return rc;
 }
 
 static void __exit qedi_cleanup(void)
 {
-	unsigned int cpu = 0;
-
-	for_each_online_cpu(cpu)
-		qedi_percpu_thread_destroy(cpu);
-
 	pci_unregister_driver(&qedi_pci_driver);
-	unregister_hotcpu_notifier(&qedi_cpu_notifier);
+	cpuhp_remove_state(qedi_cpuhp_state);
 	iscsi_unregister_transport(&qedi_iscsi_transport);
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
index 6b9cf06..427e219 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c
@@ -967,48 +967,38 @@ cfs_cpt_table_create_pattern(char *pattern)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int
-cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+static enum cpuhp_state lustre_cpu_online;
+
+static void cfs_cpu_incr_cpt_version(void)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-	bool warn;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		spin_lock(&cpt_data.cpt_lock);
-		cpt_data.cpt_version++;
-		spin_unlock(&cpt_data.cpt_lock);
-		/* Fall through */
-	default:
-		if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) {
-			CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n",
-			       cpu, action);
-			break;
-		}
-
-		mutex_lock(&cpt_data.cpt_mutex);
-		/* if all HTs in a core are offline, it may break affinity */
-		cpumask_copy(cpt_data.cpt_cpumask,
-			     topology_sibling_cpumask(cpu));
-		warn = cpumask_any_and(cpt_data.cpt_cpumask,
-				       cpu_online_mask) >= nr_cpu_ids;
-		mutex_unlock(&cpt_data.cpt_mutex);
-		CDEBUG(warn ? D_WARNING : D_INFO,
-		       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n",
-		       cpu, action);
-	}
-
-	return NOTIFY_OK;
+	spin_lock(&cpt_data.cpt_lock);
+	cpt_data.cpt_version++;
+	spin_unlock(&cpt_data.cpt_lock);
 }
 
-static struct notifier_block cfs_cpu_notifier = {
-	.notifier_call	= cfs_cpu_notify,
-	.priority	= 0
-};
+static int cfs_cpu_online(unsigned int cpu)
+{
+	cfs_cpu_incr_cpt_version();
+	return 0;
+}
 
+static int cfs_cpu_dead(unsigned int cpu)
+{
+	bool warn;
+
+	cfs_cpu_incr_cpt_version();
+
+	mutex_lock(&cpt_data.cpt_mutex);
+	/* if all HTs in a core are offline, it may break affinity */
+	cpumask_copy(cpt_data.cpt_cpumask, topology_sibling_cpumask(cpu));
+	warn = cpumask_any_and(cpt_data.cpt_cpumask,
+			       cpu_online_mask) >= nr_cpu_ids;
+	mutex_unlock(&cpt_data.cpt_mutex);
+	CDEBUG(warn ? D_WARNING : D_INFO,
+	       "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u]\n",
+	       cpu);
+	return 0;
+}
 #endif
 
 void
@@ -1018,7 +1008,9 @@ cfs_cpu_fini(void)
 		cfs_cpt_table_free(cfs_cpt_table);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&cfs_cpu_notifier);
+	if (lustre_cpu_online > 0)
+		cpuhp_remove_state_nocalls(lustre_cpu_online);
+	cpuhp_remove_state_nocalls(CPUHP_LUSTRE_CFS_DEAD);
 #endif
 	if (cpt_data.cpt_cpumask)
 		LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size());
@@ -1027,6 +1019,8 @@ cfs_cpu_fini(void)
 int
 cfs_cpu_init(void)
 {
+	int ret = 0;
+
 	LASSERT(!cfs_cpt_table);
 
 	memset(&cpt_data, 0, sizeof(cpt_data));
@@ -1041,8 +1035,19 @@ cfs_cpu_init(void)
 	mutex_init(&cpt_data.cpt_mutex);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	register_hotcpu_notifier(&cfs_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_LUSTRE_CFS_DEAD,
+					"staging/lustre/cfe:dead", NULL,
+					cfs_cpu_dead);
+	if (ret < 0)
+		goto failed;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"staging/lustre/cfe:online",
+					cfs_cpu_online, NULL);
+	if (ret < 0)
+		goto failed;
+	lustre_cpu_online = ret;
 #endif
+	ret = -EINVAL;
 
 	if (*cpu_pattern) {
 		cfs_cpt_table = cfs_cpt_table_create_pattern(cpu_pattern);
@@ -1075,7 +1080,7 @@ cfs_cpu_init(void)
 
  failed:
 	cfs_cpu_fini();
-	return -1;
+	return ret;
 }
 
 #endif
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index 7ef27c6..c03f9c8 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -445,7 +445,7 @@ int __init xen_evtchn_fifo_init(void)
 	evtchn_ops = &evtchn_ops_fifo;
 
 	cpuhp_setup_state_nocalls(CPUHP_XEN_EVTCHN_PREPARE,
-				  "CPUHP_XEN_EVTCHN_PREPARE",
+				  "xen/evtchn:prepare",
 				  xen_evtchn_cpu_prepare, xen_evtchn_cpu_dead);
 out:
 	put_cpu();
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 09807c2..21f9c74 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -57,9 +57,6 @@ struct notifier_block;
 
 #define CPU_ONLINE		0x0002 /* CPU (unsigned)v is up */
 #define CPU_UP_PREPARE		0x0003 /* CPU (unsigned)v coming up */
-#define CPU_UP_CANCELED		0x0004 /* CPU (unsigned)v NOT coming up */
-#define CPU_DOWN_PREPARE	0x0005 /* CPU (unsigned)v going down */
-#define CPU_DOWN_FAILED		0x0006 /* CPU (unsigned)v NOT going down */
 #define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
 #define CPU_POST_DEAD		0x0009 /* CPU (unsigned)v dead, cpu_hotplug
 					* lock is dropped */
@@ -80,80 +77,14 @@ struct notifier_block;
 
 #ifdef CONFIG_SMP
 extern bool cpuhp_tasks_frozen;
-/* Need to know about CPUs going up/down? */
-#if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
-#define cpu_notifier(fn, pri) {					\
-	static struct notifier_block fn##_nb =			\
-		{ .notifier_call = fn, .priority = pri };	\
-	register_cpu_notifier(&fn##_nb);			\
-}
-
-#define __cpu_notifier(fn, pri) {				\
-	static struct notifier_block fn##_nb =			\
-		{ .notifier_call = fn, .priority = pri };	\
-	__register_cpu_notifier(&fn##_nb);			\
-}
-
-extern int register_cpu_notifier(struct notifier_block *nb);
-extern int __register_cpu_notifier(struct notifier_block *nb);
-extern void unregister_cpu_notifier(struct notifier_block *nb);
-extern void __unregister_cpu_notifier(struct notifier_block *nb);
-
-#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-
-static inline int register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline void unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
-static inline void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-#endif
-
 int cpu_up(unsigned int cpu);
 void notify_cpu_starting(unsigned int cpu);
 extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);
 
-#define cpu_notifier_register_begin	cpu_maps_update_begin
-#define cpu_notifier_register_done	cpu_maps_update_done
-
 #else	/* CONFIG_SMP */
 #define cpuhp_tasks_frozen	0
 
-#define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-
-static inline int register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-
-static inline void unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
-static inline void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-}
-
 static inline void cpu_maps_update_begin(void)
 {
 }
@@ -162,14 +93,6 @@ static inline void cpu_maps_update_done(void)
 {
 }
 
-static inline void cpu_notifier_register_begin(void)
-{
-}
-
-static inline void cpu_notifier_register_done(void)
-{
-}
-
 #endif /* CONFIG_SMP */
 extern struct bus_type cpu_subsys;
 
@@ -182,12 +105,6 @@ extern void get_online_cpus(void);
 extern void put_online_cpus(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
-#define hotcpu_notifier(fn, pri)	cpu_notifier(fn, pri)
-#define __hotcpu_notifier(fn, pri)	__cpu_notifier(fn, pri)
-#define register_hotcpu_notifier(nb)	register_cpu_notifier(nb)
-#define __register_hotcpu_notifier(nb)	__register_cpu_notifier(nb)
-#define unregister_hotcpu_notifier(nb)	unregister_cpu_notifier(nb)
-#define __unregister_hotcpu_notifier(nb)	__unregister_cpu_notifier(nb)
 void clear_tasks_mm_cpumask(int cpu);
 int cpu_down(unsigned int cpu);
 
@@ -199,13 +116,6 @@ static inline void cpu_hotplug_done(void) {}
 #define put_online_cpus()	do { } while (0)
 #define cpu_hotplug_disable()	do { } while (0)
 #define cpu_hotplug_enable()	do { } while (0)
-#define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-#define __hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
-/* These aren't inline functions due to a GCC bug. */
-#define register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define __register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
-#define unregister_hotcpu_notifier(nb)	({ (void)(nb); })
-#define __unregister_hotcpu_notifier(nb)	({ (void)(nb); })
 #endif		/* CONFIG_HOTPLUG_CPU */
 
 #ifdef CONFIG_PM_SLEEP_SMP
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 2ab7bf5..20bfefb 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -41,6 +41,9 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
+	CPUHP_LUSTRE_CFS_DEAD,
+	CPUHP_SCSI_BNX2FC_DEAD,
+	CPUHP_SCSI_BNX2I_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
@@ -56,7 +59,6 @@ enum cpuhp_state {
 	CPUHP_POWERPC_MMU_CTX_PREPARE,
 	CPUHP_XEN_PREPARE,
 	CPUHP_XEN_EVTCHN_PREPARE,
-	CPUHP_NOTIFY_PREPARE,
 	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
 	CPUHP_SH_SH3X_PREPARE,
 	CPUHP_BLK_MQ_PREPARE,
@@ -71,7 +73,6 @@ enum cpuhp_state {
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_DEAD,
-	CPUHP_NOTF_ERR_INJ_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
 	CPUHP_BRINGUP_CPU,
 	CPUHP_AP_IDLE_DEAD,
@@ -79,10 +80,8 @@ enum cpuhp_state {
 	CPUHP_AP_SCHED_STARTING,
 	CPUHP_AP_RCUTREE_DYING,
 	CPUHP_AP_IRQ_GIC_STARTING,
-	CPUHP_AP_IRQ_GICV3_STARTING,
 	CPUHP_AP_IRQ_HIP04_STARTING,
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
-	CPUHP_AP_IRQ_ARMADA_CASC_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
 	CPUHP_AP_PERF_X86_UNCORE_STARTING,
@@ -118,7 +117,6 @@ enum cpuhp_state {
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_STARTING,
-	CPUHP_AP_ARM_CORESIGHT4_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
 	CPUHP_AP_X86_TBOOT_DYING,
@@ -142,7 +140,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_ARM_L2X0_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
-	CPUHP_AP_NOTIFY_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
 	CPUHP_AP_X86_HPET_ONLINE,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4424784..fe6b403 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1758,6 +1758,8 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
 	return ptl;
 }
 
+extern void __init pagecache_init(void);
+
 extern void free_area_init(unsigned long * zones_size);
 extern void free_area_init_node(int nid, unsigned long * zones_size,
 		unsigned long zone_start_pfn, unsigned long *zholes_size);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 74e4dda..c56b398 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -73,6 +73,7 @@
  */
 enum pageflags {
 	PG_locked,		/* Page is locked. Don't touch. */
+	PG_waiters,		/* Page has waiters, check its waitqueue */
 	PG_error,
 	PG_referenced,
 	PG_uptodate,
@@ -87,7 +88,6 @@ enum pageflags {
 	PG_private_2,		/* If pagecache, has fs aux data */
 	PG_writeback,		/* Page is under writeback */
 	PG_head,		/* A head page */
-	PG_swapcache,		/* Swap page: swp_entry_t in private */
 	PG_mappedtodisk,	/* Has blocks allocated on-disk */
 	PG_reclaim,		/* To be reclaimed asap */
 	PG_swapbacked,		/* Page is backed by RAM/swap */
@@ -110,6 +110,9 @@ enum pageflags {
 	/* Filesystems */
 	PG_checked = PG_owner_priv_1,
 
+	/* SwapBacked */
+	PG_swapcache = PG_owner_priv_1,	/* Swap page: swp_entry_t in private */
+
 	/* Two page bits are conscripted by FS-Cache to maintain local caching
 	 * state.  These bits are set on pages belonging to the netfs's inodes
 	 * when those inodes are being locally cached.
@@ -167,6 +170,9 @@ static __always_inline int PageCompound(struct page *page)
  *     for compound page all operations related to the page flag applied to
  *     head page.
  *
+ * PF_ONLY_HEAD:
+ *     for compound page, callers only ever operate on the head page.
+ *
  * PF_NO_TAIL:
  *     modifications of the page flag must be done on small or head pages,
  *     checks can be done on tail pages too.
@@ -176,6 +182,9 @@ static __always_inline int PageCompound(struct page *page)
  */
 #define PF_ANY(page, enforce)	page
 #define PF_HEAD(page, enforce)	compound_head(page)
+#define PF_ONLY_HEAD(page, enforce) ({					\
+		VM_BUG_ON_PGFLAGS(PageTail(page), page);		\
+		page;})
 #define PF_NO_TAIL(page, enforce) ({					\
 		VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page);	\
 		compound_head(page);})
@@ -253,6 +262,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; }
 	TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
 
 __PAGEFLAG(Locked, locked, PF_NO_TAIL)
+PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD)
 PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND)
 PAGEFLAG(Referenced, referenced, PF_HEAD)
 	TESTCLEARFLAG(Referenced, referenced, PF_HEAD)
@@ -314,7 +324,13 @@ PAGEFLAG_FALSE(HighMem)
 #endif
 
 #ifdef CONFIG_SWAP
-PAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
+static __always_inline int PageSwapCache(struct page *page)
+{
+	return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags);
+
+}
+SETPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
+CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
 #else
 PAGEFLAG_FALSE(SwapCache)
 #endif
@@ -701,12 +717,12 @@ static inline void ClearPageSlabPfmemalloc(struct page *page)
  * Flags checked when a page is freed.  Pages being freed should not have
  * these flags set.  It they are, there is a problem.
  */
-#define PAGE_FLAGS_CHECK_AT_FREE \
-	(1UL << PG_lru	 | 1UL << PG_locked    | \
-	 1UL << PG_private | 1UL << PG_private_2 | \
-	 1UL << PG_writeback | 1UL << PG_reserved | \
-	 1UL << PG_slab	 | 1UL << PG_swapcache | 1UL << PG_active | \
-	 1UL << PG_unevictable | __PG_MLOCKED)
+#define PAGE_FLAGS_CHECK_AT_FREE				\
+	(1UL << PG_lru		| 1UL << PG_locked	|	\
+	 1UL << PG_private	| 1UL << PG_private_2	|	\
+	 1UL << PG_writeback	| 1UL << PG_reserved	|	\
+	 1UL << PG_slab		| 1UL << PG_active 	|	\
+	 1UL << PG_unevictable	| __PG_MLOCKED)
 
 /*
  * Flags checked when a page is prepped for return by the page allocator.
@@ -735,6 +751,7 @@ static inline int page_has_private(struct page *page)
 
 #undef PF_ANY
 #undef PF_HEAD
+#undef PF_ONLY_HEAD
 #undef PF_NO_TAIL
 #undef PF_NO_COMPOUND
 #endif /* !__GENERATING_BOUNDS_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index f29f80f..324c8dba 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -486,22 +486,14 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
  * and for filesystems which need to wait on PG_private.
  */
 extern void wait_on_page_bit(struct page *page, int bit_nr);
-
 extern int wait_on_page_bit_killable(struct page *page, int bit_nr);
-extern int wait_on_page_bit_killable_timeout(struct page *page,
-					     int bit_nr, unsigned long timeout);
+extern void wake_up_page_bit(struct page *page, int bit_nr);
 
-static inline int wait_on_page_locked_killable(struct page *page)
-{
-	if (!PageLocked(page))
-		return 0;
-	return wait_on_page_bit_killable(compound_head(page), PG_locked);
-}
-
-extern wait_queue_head_t *page_waitqueue(struct page *page);
 static inline void wake_up_page(struct page *page, int bit)
 {
-	__wake_up_bit(page_waitqueue(page), &page->flags, bit);
+	if (!PageWaiters(page))
+		return;
+	wake_up_page_bit(page, bit);
 }
 
 /* 
@@ -517,6 +509,13 @@ static inline void wait_on_page_locked(struct page *page)
 		wait_on_page_bit(compound_head(page), PG_locked);
 }
 
+static inline int wait_on_page_locked_killable(struct page *page)
+{
+	if (!PageLocked(page))
+		return 0;
+	return wait_on_page_bit_killable(compound_head(page), PG_locked);
+}
+
 /* 
  * Wait for a page to complete writeback
  */
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index c78f9f0..5527d91 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -375,7 +375,6 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
 unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh);
 
 void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time);
-void page_writeback_init(void);
 void balance_dirty_pages_ratelimited(struct address_space *mapping);
 bool wb_over_bg_thresh(struct bdi_writeback *wb);
 
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 5a81ab4..9e687ca 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -81,6 +81,7 @@
 
 #define __def_pageflag_names						\
 	{1UL << PG_locked,		"locked"	},		\
+	{1UL << PG_waiters,		"waiters"	},		\
 	{1UL << PG_error,		"error"		},		\
 	{1UL << PG_referenced,		"referenced"	},		\
 	{1UL << PG_uptodate,		"uptodate"	},		\
@@ -95,7 +96,6 @@
 	{1UL << PG_private_2,		"private_2"	},		\
 	{1UL << PG_writeback,		"writeback"	},		\
 	{1UL << PG_head,		"head"		},		\
-	{1UL << PG_swapcache,		"swapcache"	},		\
 	{1UL << PG_mappedtodisk,	"mappedtodisk"	},		\
 	{1UL << PG_reclaim,		"reclaim"	},		\
 	{1UL << PG_swapbacked,		"swapbacked"	},		\
diff --git a/init/main.c b/init/main.c
index c81c9fa..b0c9d6f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -647,9 +647,8 @@ asmlinkage __visible void __init start_kernel(void)
 	security_init();
 	dbg_late_init();
 	vfs_caches_init();
+	pagecache_init();
 	signals_init();
-	/* rootfs populating might need page-writeback */
-	page_writeback_init();
 	proc_root_init();
 	nsfs_init();
 	cpuset_init();
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5339aca..042fd7e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -183,23 +183,16 @@ EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);
 /*
  * The following two APIs (cpu_maps_update_begin/done) must be used when
  * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
- * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
- * hotplug callback (un)registration performed using __register_cpu_notifier()
- * or __unregister_cpu_notifier().
  */
 void cpu_maps_update_begin(void)
 {
 	mutex_lock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_begin);
 
 void cpu_maps_update_done(void)
 {
 	mutex_unlock(&cpu_add_remove_lock);
 }
-EXPORT_SYMBOL(cpu_notifier_register_done);
-
-static RAW_NOTIFIER_HEAD(cpu_chain);
 
 /* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
  * Should always be manipulated under cpu_add_remove_lock
@@ -349,66 +342,7 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
-/* Need to know about CPUs going up/down? */
-int register_cpu_notifier(struct notifier_block *nb)
-{
-	int ret;
-	cpu_maps_update_begin();
-	ret = raw_notifier_chain_register(&cpu_chain, nb);
-	cpu_maps_update_done();
-	return ret;
-}
-
-int __register_cpu_notifier(struct notifier_block *nb)
-{
-	return raw_notifier_chain_register(&cpu_chain, nb);
-}
-
-static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call,
-			int *nr_calls)
-{
-	unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0;
-	void *hcpu = (void *)(long)cpu;
-
-	int ret;
-
-	ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call,
-					nr_calls);
-
-	return notifier_to_errno(ret);
-}
-
-static int cpu_notify(unsigned long val, unsigned int cpu)
-{
-	return __cpu_notify(val, cpu, -1, NULL);
-}
-
-static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
-{
-	BUG_ON(cpu_notify(val, cpu));
-}
-
 /* Notifier wrappers for transitioning to state machine */
-static int notify_prepare(unsigned int cpu)
-{
-	int nr_calls = 0;
-	int ret;
-
-	ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls);
-	if (ret) {
-		nr_calls--;
-		printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
-				__func__, cpu);
-		__cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL);
-	}
-	return ret;
-}
-
-static int notify_online(unsigned int cpu)
-{
-	cpu_notify(CPU_ONLINE, cpu);
-	return 0;
-}
 
 static int bringup_wait_for_ap(unsigned int cpu)
 {
@@ -433,10 +367,8 @@ static int bringup_cpu(unsigned int cpu)
 	/* Arch-specific enabling code. */
 	ret = __cpu_up(cpu, idle);
 	irq_unlock_sparse();
-	if (ret) {
-		cpu_notify(CPU_UP_CANCELED, cpu);
+	if (ret)
 		return ret;
-	}
 	ret = bringup_wait_for_ap(cpu);
 	BUG_ON(!cpu_online(cpu));
 	return ret;
@@ -565,11 +497,6 @@ static void cpuhp_thread_fun(unsigned int cpu)
 		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
 
 		undo_cpu_down(cpu, st);
-		/*
-		 * This is a momentary workaround to keep the notifier users
-		 * happy. Will go away once we got rid of the notifiers.
-		 */
-		cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
 		st->rollback = false;
 	} else {
 		/* Cannot happen .... */
@@ -659,22 +586,6 @@ void __init cpuhp_threads_init(void)
 	kthread_unpark(this_cpu_read(cpuhp_state.thread));
 }
 
-EXPORT_SYMBOL(register_cpu_notifier);
-EXPORT_SYMBOL(__register_cpu_notifier);
-void unregister_cpu_notifier(struct notifier_block *nb)
-{
-	cpu_maps_update_begin();
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-	cpu_maps_update_done();
-}
-EXPORT_SYMBOL(unregister_cpu_notifier);
-
-void __unregister_cpu_notifier(struct notifier_block *nb)
-{
-	raw_notifier_chain_unregister(&cpu_chain, nb);
-}
-EXPORT_SYMBOL(__unregister_cpu_notifier);
-
 #ifdef CONFIG_HOTPLUG_CPU
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
@@ -741,20 +652,6 @@ static inline void check_for_tasks(int dead_cpu)
 	read_unlock(&tasklist_lock);
 }
 
-static int notify_down_prepare(unsigned int cpu)
-{
-	int err, nr_calls = 0;
-
-	err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls);
-	if (err) {
-		nr_calls--;
-		__cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL);
-		pr_warn("%s: attempt to take down CPU %u failed\n",
-				__func__, cpu);
-	}
-	return err;
-}
-
 /* Take this CPU down. */
 static int take_cpu_down(void *_param)
 {
@@ -833,13 +730,6 @@ static int takedown_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int notify_dead(unsigned int cpu)
-{
-	cpu_notify_nofail(CPU_DEAD, cpu);
-	check_for_tasks(cpu);
-	return 0;
-}
-
 static void cpuhp_complete_idle_dead(void *arg)
 {
 	struct cpuhp_cpu_state *st = arg;
@@ -863,9 +753,7 @@ void cpuhp_report_idle_dead(void)
 }
 
 #else
-#define notify_down_prepare	NULL
 #define takedown_cpu		NULL
-#define notify_dead		NULL
 #endif
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -924,9 +812,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
 out:
 	cpu_hotplug_done();
-	/* This post dead nonsense must die */
-	if (!ret && hasdied)
-		cpu_notify_nofail(CPU_POST_DEAD, cpu);
 	return ret;
 }
 
@@ -1292,17 +1177,6 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 		.teardown.single	= rcutree_dead_cpu,
 	},
 	/*
-	 * Preparatory and dead notifiers. Will be replaced once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_NOTIFY_PREPARE] = {
-		.name			= "notify:prepare",
-		.startup.single		= notify_prepare,
-		.teardown.single	= notify_dead,
-		.skip_onerr		= true,
-		.cant_stop		= true,
-	},
-	/*
 	 * On the tear-down path, timers_dead_cpu() must be invoked
 	 * before blk_mq_queue_reinit_notify() from notify_dead(),
 	 * otherwise a RCU stall occurs.
@@ -1391,17 +1265,6 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 		.startup.single		= rcutree_online_cpu,
 		.teardown.single	= rcutree_offline_cpu,
 	},
-
-	/*
-	 * Online/down_prepare notifiers. Will be removed once the notifiers
-	 * are converted to states.
-	 */
-	[CPUHP_AP_NOTIFY_ONLINE] = {
-		.name			= "notify:online",
-		.startup.single		= notify_online,
-		.teardown.single	= notify_down_prepare,
-		.skip_onerr		= true,
-	},
 #endif
 	/*
 	 * The dynamically registered state space is here
@@ -1432,23 +1295,53 @@ static int cpuhp_cb_check(enum cpuhp_state state)
 	return 0;
 }
 
-static void cpuhp_store_callbacks(enum cpuhp_state state,
-				  const char *name,
-				  int (*startup)(unsigned int cpu),
-				  int (*teardown)(unsigned int cpu),
-				  bool multi_instance)
+/*
+ * Returns a free for dynamic slot assignment of the Online state. The states
+ * are protected by the cpuhp_slot_states mutex and an empty slot is identified
+ * by having no name assigned.
+ */
+static int cpuhp_reserve_state(enum cpuhp_state state)
+{
+	enum cpuhp_state i;
+
+	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
+		if (!cpuhp_ap_states[i].name)
+			return i;
+	}
+	WARN(1, "No more dynamic states available for CPU hotplug\n");
+	return -ENOSPC;
+}
+
+static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
+				 int (*startup)(unsigned int cpu),
+				 int (*teardown)(unsigned int cpu),
+				 bool multi_instance)
 {
 	/* (Un)Install the callbacks for further cpu hotplug operations */
 	struct cpuhp_step *sp;
+	int ret = 0;
 
 	mutex_lock(&cpuhp_state_mutex);
+
+	if (state == CPUHP_AP_ONLINE_DYN) {
+		ret = cpuhp_reserve_state(state);
+		if (ret < 0)
+			goto out;
+		state = ret;
+	}
 	sp = cpuhp_get_step(state);
+	if (name && sp->name) {
+		ret = -EBUSY;
+		goto out;
+	}
 	sp->startup.single = startup;
 	sp->teardown.single = teardown;
 	sp->name = name;
 	sp->multi_instance = multi_instance;
 	INIT_HLIST_HEAD(&sp->list);
+out:
 	mutex_unlock(&cpuhp_state_mutex);
+	return ret;
 }
 
 static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
@@ -1509,29 +1402,6 @@ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
 	}
 }
 
-/*
- * Returns a free for dynamic slot assignment of the Online state. The states
- * are protected by the cpuhp_slot_states mutex and an empty slot is identified
- * by having no name assigned.
- */
-static int cpuhp_reserve_state(enum cpuhp_state state)
-{
-	enum cpuhp_state i;
-
-	mutex_lock(&cpuhp_state_mutex);
-	for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
-		if (cpuhp_ap_states[i].name)
-			continue;
-
-		cpuhp_ap_states[i].name = "Reserved";
-		mutex_unlock(&cpuhp_state_mutex);
-		return i;
-	}
-	mutex_unlock(&cpuhp_state_mutex);
-	WARN(1, "No more dynamic states available for CPU hotplug\n");
-	return -ENOSPC;
-}
-
 int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 			       bool invoke)
 {
@@ -1580,11 +1450,13 @@ EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
 
 /**
  * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
- * @state:	The state to setup
- * @invoke:	If true, the startup function is invoked for cpus where
- *		cpu state >= @state
- * @startup:	startup callback function
- * @teardown:	teardown callback function
+ * @state:		The state to setup
+ * @invoke:		If true, the startup function is invoked for cpus where
+ *			cpu state >= @state
+ * @startup:		startup callback function
+ * @teardown:		teardown callback function
+ * @multi_instance:	State is set up for multiple instances which get
+ *			added afterwards.
  *
  * Returns:
  *   On success:
@@ -1599,25 +1471,16 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 			bool multi_instance)
 {
 	int cpu, ret = 0;
-	int dyn_state = 0;
 
 	if (cpuhp_cb_check(state) || !name)
 		return -EINVAL;
 
 	get_online_cpus();
 
-	/* currently assignments for the ONLINE state are possible */
-	if (state == CPUHP_AP_ONLINE_DYN) {
-		dyn_state = 1;
-		ret = cpuhp_reserve_state(state);
-		if (ret < 0)
-			goto out;
-		state = ret;
-	}
+	ret = cpuhp_store_callbacks(state, name, startup, teardown,
+				    multi_instance);
 
-	cpuhp_store_callbacks(state, name, startup, teardown, multi_instance);
-
-	if (!invoke || !startup)
+	if (ret || !invoke || !startup)
 		goto out;
 
 	/*
@@ -1641,7 +1504,11 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 	}
 out:
 	put_online_cpus();
-	if (!ret && dyn_state)
+	/*
+	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
+	 * dynamically allocated state in case of success.
+	 */
+	if (!ret && state == CPUHP_AP_ONLINE_DYN)
 		return state;
 	return ret;
 }
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index cb66a46..b06848a 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1538,30 +1538,6 @@
 
 	  Say N if unsure.
 
-config CPU_NOTIFIER_ERROR_INJECT
-	tristate "CPU notifier error injection module"
-	depends on HOTPLUG_CPU && NOTIFIER_ERROR_INJECTION
-	help
-	  This option provides a kernel module that can be used to test
-	  the error handling of the cpu notifiers by injecting artificial
-	  errors to CPU notifier chain callbacks.  It is controlled through
-	  debugfs interface under /sys/kernel/debug/notifier-error-inject/cpu
-
-	  If the notifier call chain should be failed with some events
-	  notified, write the error code to "actions/<notifier event>/error".
-
-	  Example: Inject CPU offline error (-1 == -EPERM)
-
-	  # cd /sys/kernel/debug/notifier-error-inject/cpu
-	  # echo -1 > actions/CPU_DOWN_PREPARE/error
-	  # echo 0 > /sys/devices/system/cpu/cpu1/online
-	  bash: echo: write error: Operation not permitted
-
-	  To compile this code as a module, choose M here: the module will
-	  be called cpu-notifier-error-inject.
-
-	  If unsure, say N.
-
 config PM_NOTIFIER_ERROR_INJECT
 	tristate "PM notifier error injection module"
 	depends on PM && NOTIFIER_ERROR_INJECTION
diff --git a/lib/Makefile b/lib/Makefile
index 50144a3..bc4073a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -128,7 +128,6 @@
 obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o iommu-common.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
 obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
-obj-$(CONFIG_CPU_NOTIFIER_ERROR_INJECT) += cpu-notifier-error-inject.o
 obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
 obj-$(CONFIG_NETDEV_NOTIFIER_ERROR_INJECT) += netdev-notifier-error-inject.o
 obj-$(CONFIG_MEMORY_NOTIFIER_ERROR_INJECT) += memory-notifier-error-inject.o
diff --git a/lib/cpu-notifier-error-inject.c b/lib/cpu-notifier-error-inject.c
deleted file mode 100644
index 0e2c9a1..0000000
--- a/lib/cpu-notifier-error-inject.c
+++ /dev/null
@@ -1,84 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-
-#include "notifier-error-inject.h"
-
-static int priority;
-module_param(priority, int, 0);
-MODULE_PARM_DESC(priority, "specify cpu notifier priority");
-
-#define UP_PREPARE 0
-#define UP_PREPARE_FROZEN 0
-#define DOWN_PREPARE 0
-#define DOWN_PREPARE_FROZEN 0
-
-static struct notifier_err_inject cpu_notifier_err_inject = {
-	.actions = {
-		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE_FROZEN) },
-		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE_FROZEN) },
-		{}
-	}
-};
-
-static int notf_err_handle(struct notifier_err_inject_action *action)
-{
-	int ret;
-
-	ret = action->error;
-	if (ret)
-		pr_info("Injecting error (%d) to %s\n", ret, action->name);
-	return ret;
-}
-
-static int notf_err_inj_up_prepare(unsigned int cpu)
-{
-	if (!cpuhp_tasks_frozen)
-		return notf_err_handle(&cpu_notifier_err_inject.actions[0]);
-	else
-		return notf_err_handle(&cpu_notifier_err_inject.actions[1]);
-}
-
-static int notf_err_inj_dead(unsigned int cpu)
-{
-	if (!cpuhp_tasks_frozen)
-		return notf_err_handle(&cpu_notifier_err_inject.actions[2]);
-	else
-		return notf_err_handle(&cpu_notifier_err_inject.actions[3]);
-}
-
-static struct dentry *dir;
-
-static int err_inject_init(void)
-{
-	int err;
-
-	dir = notifier_err_inject_init("cpu", notifier_err_inject_dir,
-					&cpu_notifier_err_inject, priority);
-	if (IS_ERR(dir))
-		return PTR_ERR(dir);
-
-	err = cpuhp_setup_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE,
-					"cpu-err-notif:prepare",
-					notf_err_inj_up_prepare,
-					notf_err_inj_dead);
-	if (err)
-		debugfs_remove_recursive(dir);
-
-	return err;
-}
-
-static void err_inject_exit(void)
-{
-	cpuhp_remove_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE);
-	debugfs_remove_recursive(dir);
-}
-
-module_init(err_inject_init);
-module_exit(err_inject_exit);
-
-MODULE_DESCRIPTION("CPU notifier error injection module");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Akinobu Mita <akinobu.mita@gmail.com>");
diff --git a/mm/filemap.c b/mm/filemap.c
index 32be3c8..82f26cd 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -739,46 +739,160 @@ EXPORT_SYMBOL(__page_cache_alloc);
  * at a cost of "thundering herd" phenomena during rare hash
  * collisions.
  */
-wait_queue_head_t *page_waitqueue(struct page *page)
+#define PAGE_WAIT_TABLE_BITS 8
+#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
+static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
+
+static wait_queue_head_t *page_waitqueue(struct page *page)
 {
-	return bit_waitqueue(page, 0);
+	return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)];
 }
-EXPORT_SYMBOL(page_waitqueue);
+
+void __init pagecache_init(void)
+{
+	int i;
+
+	for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
+		init_waitqueue_head(&page_wait_table[i]);
+
+	page_writeback_init();
+}
+
+struct wait_page_key {
+	struct page *page;
+	int bit_nr;
+	int page_match;
+};
+
+struct wait_page_queue {
+	struct page *page;
+	int bit_nr;
+	wait_queue_t wait;
+};
+
+static int wake_page_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
+{
+	struct wait_page_key *key = arg;
+	struct wait_page_queue *wait_page
+		= container_of(wait, struct wait_page_queue, wait);
+
+	if (wait_page->page != key->page)
+	       return 0;
+	key->page_match = 1;
+
+	if (wait_page->bit_nr != key->bit_nr)
+		return 0;
+	if (test_bit(key->bit_nr, &key->page->flags))
+		return 0;
+
+	return autoremove_wake_function(wait, mode, sync, key);
+}
+
+void wake_up_page_bit(struct page *page, int bit_nr)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	struct wait_page_key key;
+	unsigned long flags;
+
+	key.page = page;
+	key.bit_nr = bit_nr;
+	key.page_match = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_locked_key(q, TASK_NORMAL, &key);
+	/*
+	 * It is possible for other pages to have collided on the waitqueue
+	 * hash, so in that case check for a page match. That prevents a long-
+	 * term waiter
+	 *
+	 * It is still possible to miss a case here, when we woke page waiters
+	 * and removed them from the waitqueue, but there are still other
+	 * page waiters.
+	 */
+	if (!waitqueue_active(q) || !key.page_match) {
+		ClearPageWaiters(page);
+		/*
+		 * It's possible to miss clearing Waiters here, when we woke
+		 * our page waiters, but the hashed waitqueue has waiters for
+		 * other pages on it.
+		 *
+		 * That's okay, it's a rare case. The next waker will clear it.
+		 */
+	}
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(wake_up_page_bit);
+
+static inline int wait_on_page_bit_common(wait_queue_head_t *q,
+		struct page *page, int bit_nr, int state, bool lock)
+{
+	struct wait_page_queue wait_page;
+	wait_queue_t *wait = &wait_page.wait;
+	int ret = 0;
+
+	init_wait(wait);
+	wait->func = wake_page_function;
+	wait_page.page = page;
+	wait_page.bit_nr = bit_nr;
+
+	for (;;) {
+		spin_lock_irq(&q->lock);
+
+		if (likely(list_empty(&wait->task_list))) {
+			if (lock)
+				__add_wait_queue_tail_exclusive(q, wait);
+			else
+				__add_wait_queue(q, wait);
+			SetPageWaiters(page);
+		}
+
+		set_current_state(state);
+
+		spin_unlock_irq(&q->lock);
+
+		if (likely(test_bit(bit_nr, &page->flags))) {
+			io_schedule();
+			if (unlikely(signal_pending_state(state, current))) {
+				ret = -EINTR;
+				break;
+			}
+		}
+
+		if (lock) {
+			if (!test_and_set_bit_lock(bit_nr, &page->flags))
+				break;
+		} else {
+			if (!test_bit(bit_nr, &page->flags))
+				break;
+		}
+	}
+
+	finish_wait(q, wait);
+
+	/*
+	 * A signal could leave PageWaiters set. Clearing it here if
+	 * !waitqueue_active would be possible (by open-coding finish_wait),
+	 * but still fail to catch it in the case of wait hash collision. We
+	 * already can fail to clear wait hash collision cases, so don't
+	 * bother with signals either.
+	 */
+
+	return ret;
+}
 
 void wait_on_page_bit(struct page *page, int bit_nr)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
-
-	if (test_bit(bit_nr, &page->flags))
-		__wait_on_bit(page_waitqueue(page), &wait, bit_wait_io,
-							TASK_UNINTERRUPTIBLE);
+	wait_queue_head_t *q = page_waitqueue(page);
+	wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, false);
 }
 EXPORT_SYMBOL(wait_on_page_bit);
 
 int wait_on_page_bit_killable(struct page *page, int bit_nr)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
-
-	if (!test_bit(bit_nr, &page->flags))
-		return 0;
-
-	return __wait_on_bit(page_waitqueue(page), &wait,
-			     bit_wait_io, TASK_KILLABLE);
+	wait_queue_head_t *q = page_waitqueue(page);
+	return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, false);
 }
 
-int wait_on_page_bit_killable_timeout(struct page *page,
-				       int bit_nr, unsigned long timeout)
-{
-	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
-
-	wait.key.timeout = jiffies + timeout;
-	if (!test_bit(bit_nr, &page->flags))
-		return 0;
-	return __wait_on_bit(page_waitqueue(page), &wait,
-			     bit_wait_io_timeout, TASK_KILLABLE);
-}
-EXPORT_SYMBOL_GPL(wait_on_page_bit_killable_timeout);
-
 /**
  * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
  * @page: Page defining the wait queue of interest
@@ -793,6 +907,7 @@ void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
 
 	spin_lock_irqsave(&q->lock, flags);
 	__add_wait_queue(q, waiter);
+	SetPageWaiters(page);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL_GPL(add_page_wait_queue);
@@ -874,23 +989,19 @@ EXPORT_SYMBOL_GPL(page_endio);
  * __lock_page - get a lock on the page, assuming we need to sleep to get it
  * @page: the page to lock
  */
-void __lock_page(struct page *page)
+void __lock_page(struct page *__page)
 {
-	struct page *page_head = compound_head(page);
-	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
-
-	__wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io,
-							TASK_UNINTERRUPTIBLE);
+	struct page *page = compound_head(__page);
+	wait_queue_head_t *q = page_waitqueue(page);
+	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, true);
 }
 EXPORT_SYMBOL(__lock_page);
 
-int __lock_page_killable(struct page *page)
+int __lock_page_killable(struct page *__page)
 {
-	struct page *page_head = compound_head(page);
-	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
-
-	return __wait_on_bit_lock(page_waitqueue(page_head), &wait,
-					bit_wait_io, TASK_KILLABLE);
+	struct page *page = compound_head(__page);
+	wait_queue_head_t *q = page_waitqueue(page);
+	return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, true);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
 
diff --git a/mm/internal.h b/mm/internal.h
index 44d6889..7aa2ea0 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -36,6 +36,8 @@
 /* Do not use these with a slab allocator */
 #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
 
+void page_writeback_init(void);
+
 int do_swap_page(struct vm_fault *vmf);
 
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 19e796d..f283c7e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -764,12 +764,11 @@ static int me_huge_page(struct page *p, unsigned long pfn)
  */
 
 #define dirty		(1UL << PG_dirty)
-#define sc		(1UL << PG_swapcache)
+#define sc		((1UL << PG_swapcache) | (1UL << PG_swapbacked))
 #define unevict		(1UL << PG_unevictable)
 #define mlock		(1UL << PG_mlocked)
 #define writeback	(1UL << PG_writeback)
 #define lru		(1UL << PG_lru)
-#define swapbacked	(1UL << PG_swapbacked)
 #define head		(1UL << PG_head)
 #define slab		(1UL << PG_slab)
 #define reserved	(1UL << PG_reserved)
@@ -819,7 +818,6 @@ static struct page_state {
 #undef mlock
 #undef writeback
 #undef lru
-#undef swapbacked
 #undef head
 #undef slab
 #undef reserved
diff --git a/mm/migrate.c b/mm/migrate.c
index 0ed24b1..87f4d0f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -466,13 +466,15 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	 */
 	newpage->index = page->index;
 	newpage->mapping = page->mapping;
-	if (PageSwapBacked(page))
-		__SetPageSwapBacked(newpage);
-
 	get_page(newpage);	/* add cache reference */
-	if (PageSwapCache(page)) {
-		SetPageSwapCache(newpage);
-		set_page_private(newpage, page_private(page));
+	if (PageSwapBacked(page)) {
+		__SetPageSwapBacked(newpage);
+		if (PageSwapCache(page)) {
+			SetPageSwapCache(newpage);
+			set_page_private(newpage, page_private(page));
+		}
+	} else {
+		VM_BUG_ON_PAGE(PageSwapCache(page), page);
 	}
 
 	/* Move dirty while page refs frozen and newpage not yet exposed */
diff --git a/mm/swap.c b/mm/swap.c
index 4dcf852..844baed 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -69,6 +69,7 @@ static void __page_cache_release(struct page *page)
 		del_page_from_lru_list(page, lruvec, page_off_lru(page));
 		spin_unlock_irqrestore(zone_lru_lock(zone), flags);
 	}
+	__ClearPageWaiters(page);
 	mem_cgroup_uncharge(page);
 }
 
@@ -784,6 +785,7 @@ void release_pages(struct page **pages, int nr, bool cold)
 
 		/* Clear Active bit in case of parallel mark_page_accessed */
 		__ClearPageActive(page);
+		__ClearPageWaiters(page);
 
 		list_add(&page->lru, &pages_to_free);
 	}
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index 8561e7d..8792ad8 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -10,6 +10,7 @@
 turbostat : turbostat.c
 CFLAGS +=	-Wall
 CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
+CFLAGS +=	-DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"'
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 492e84f..03cb639 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -25,9 +25,27 @@
 .SS Options
 Options can be specified with a single or double '-', and only as much of the option
 name as necessary to disambiguate it from others is necessary.  Note that options are case-sensitive.
-\fB--Counter MSR#\fP shows the delta of the specified 64-bit MSR counter.
 .PP
-\fB--counter MSR#\fP shows the delta of the specified 32-bit MSR counter.
+\fB--add attributes\fP add column with counter having specified 'attributes'.  The 'location' attribute is required, all others are optional.
+.nf
+	location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP}
+		msrDDD is a decimal offset, eg. msr16
+		msr0xXXX is a hex offset, eg. msr0x10
+
+	scope: {\fBcpu\fP | \fBcore\fP | \fBpackage\fP}
+		sample and print the counter for every cpu, core, or package.
+		default: cpu
+
+	size: {\fBu32\fP | \fBu64\fP }
+		MSRs are read as 64-bits, u32 truncates the displayed value to 32-bits.
+		default: u64
+
+	format: {\fBraw\fP | \fBdelta\fP | \fBpercent\fP}
+		'raw' shows the MSR contents in hex.
+		'delta' shows the difference in values during the measurement interval.
+		'percent' shows the delta as a percentage of the cycles elapsed.
+		default: delta
+.fi
 .PP
 \fB--Dump\fP displays the raw counter values.
 .PP
@@ -43,10 +61,6 @@
 .PP
 \fB--Joules\fP displays energy in Joules, rather than dividing Joules by time to print power in Watts.
 .PP
-\fB--MSR MSR#\fP shows the specified 64-bit MSR value.
-.PP
-\fB--msr MSR#\fP shows the specified 32-bit MSR value.
-.PP
 \fB--Package\fP limits output to the system summary plus the 1st thread in each Package.
 .PP
 \fB--processor\fP limits output to the system summary plus the 1st thread in each processor of each package.  Ie. it skips hyper-threaded siblings.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 3e199b5..f13f61b 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -21,6 +21,7 @@
 
 #define _GNU_SOURCE
 #include MSRHEADER
+#include INTEL_FAMILY_HEADER
 #include <stdarg.h>
 #include <stdio.h>
 #include <err.h>
@@ -51,8 +52,6 @@ unsigned int debug;
 unsigned int rapl_joules;
 unsigned int summary_only;
 unsigned int dump_only;
-unsigned int skip_c0;
-unsigned int skip_c1;
 unsigned int do_nhm_cstates;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
@@ -72,10 +71,6 @@ unsigned int units = 1000000;	/* MHz etc */
 unsigned int genuine_intel;
 unsigned int has_invariant_tsc;
 unsigned int do_nhm_platform_info;
-unsigned int extra_msr_offset32;
-unsigned int extra_msr_offset64;
-unsigned int extra_delta_offset32;
-unsigned int extra_delta_offset64;
 unsigned int aperf_mperf_multiplier = 1;
 int do_irq = 1;
 int do_smi;
@@ -131,9 +126,8 @@ unsigned int has_hwp_pkg;		/* IA32_HWP_REQUEST_PKG */
 #define RAPL_DRAM_POWER_INFO	(1 << 5)
 					/* 0x61c MSR_DRAM_POWER_INFO */
 
-#define RAPL_CORES		(1 << 6)
+#define RAPL_CORES_POWER_LIMIT	(1 << 6)
 					/* 0x638 MSR_PP0_POWER_LIMIT */
-					/* 0x639 MSR_PP0_ENERGY_STATUS */
 #define RAPL_CORE_POLICY	(1 << 7)
 					/* 0x63a MSR_PP0_POLICY */
 
@@ -141,11 +135,20 @@ unsigned int has_hwp_pkg;		/* IA32_HWP_REQUEST_PKG */
 					/* 0x640 MSR_PP1_POWER_LIMIT */
 					/* 0x641 MSR_PP1_ENERGY_STATUS */
 					/* 0x642 MSR_PP1_POLICY */
+
+#define RAPL_CORES_ENERGY_STATUS	(1 << 9)
+					/* 0x639 MSR_PP0_ENERGY_STATUS */
+#define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT)
 #define	TJMAX_DEFAULT	100
 
 #define MAX(a, b) ((a) > (b) ? (a) : (b))
 
-int aperf_mperf_unstable;
+/*
+ * buffer size used by sscanf() for added column names
+ * Usually truncated to 7 characters, but also handles 18 columns for raw 64-bit counters
+ */
+#define	NAME_BYTES 20
+
 int backwards_count;
 char *progname;
 
@@ -157,16 +160,13 @@ struct thread_data {
 	unsigned long long aperf;
 	unsigned long long mperf;
 	unsigned long long c1;
-	unsigned long long extra_msr64;
-	unsigned long long extra_delta64;
-	unsigned long long extra_msr32;
-	unsigned long long extra_delta32;
 	unsigned int irq_count;
 	unsigned int smi_count;
 	unsigned int cpu_id;
 	unsigned int flags;
 #define CPU_IS_FIRST_THREAD_IN_CORE	0x2
 #define CPU_IS_FIRST_CORE_IN_PACKAGE	0x4
+	unsigned long long counter[1];
 } *thread_even, *thread_odd;
 
 struct core_data {
@@ -175,6 +175,7 @@ struct core_data {
 	unsigned long long c7;
 	unsigned int core_temp_c;
 	unsigned int core_id;
+	unsigned long long counter[1];
 } *core_even, *core_odd;
 
 struct pkg_data {
@@ -199,7 +200,7 @@ struct pkg_data {
 	unsigned int rapl_pkg_perf_status;	/* MSR_PKG_PERF_STATUS */
 	unsigned int rapl_dram_perf_status;	/* MSR_DRAM_PERF_STATUS */
 	unsigned int pkg_temp_c;
-
+	unsigned long long counter[1];
 } *package_even, *package_odd;
 
 #define ODD_COUNTERS thread_odd, core_odd, package_odd
@@ -213,11 +214,33 @@ struct pkg_data {
 	(core_base + (pkg_no) * topo.num_cores_per_pkg + (core_no))
 #define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no)
 
+enum counter_scope {SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE};
+enum counter_type {COUNTER_CYCLES, COUNTER_SECONDS};
+enum counter_format {FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT};
+
+struct msr_counter {
+	unsigned int msr_num;
+	char name[NAME_BYTES];
+	unsigned int width;
+	enum counter_type type;
+	enum counter_format format;
+	struct msr_counter *next;
+};
+
+struct sys_counters {
+	unsigned int thread_counter_bytes;
+	unsigned int core_counter_bytes;
+	unsigned int package_counter_bytes;
+	struct msr_counter *tp;
+	struct msr_counter *cp;
+	struct msr_counter *pp;
+} sys;
+
 struct system_summary {
 	struct thread_data threads;
 	struct core_data cores;
 	struct pkg_data packages;
-} sum, average;
+} average;
 
 
 struct topo_params {
@@ -319,120 +342,148 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 /*
  * Example Format w/ field column widths:
  *
- *  Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     IRQ   SMI   Busy% CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 CoreTmp  PkgTmp  GFXMHz Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
+ *  Package    Core     CPU Avg_MHz Bzy_MHz TSC_MHz     IRQ   SMI   Busy% CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 ThreadC CoreTmp  CoreCnt PkgTmp  GFXMHz Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt PkgCnt
  * 12345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678
  */
 
 void print_header(void)
 {
-	if (show_pkg)
-		outp += sprintf(outp, " Package");
-	if (show_core)
-		outp += sprintf(outp, "    Core");
-	if (show_cpu)
-		outp += sprintf(outp, "     CPU");
-	if (has_aperf)
-		outp += sprintf(outp, " Avg_MHz");
-	if (has_aperf)
-		outp += sprintf(outp, "   Busy%%");
-	if (has_aperf)
-		outp += sprintf(outp, " Bzy_MHz");
-	outp += sprintf(outp, " TSC_MHz");
+	struct msr_counter *mp;
 
-	if (extra_delta_offset32)
-		outp += sprintf(outp, "  count 0x%03X", extra_delta_offset32);
-	if (extra_delta_offset64)
-		outp += sprintf(outp, "  COUNT 0x%03X", extra_delta_offset64);
-	if (extra_msr_offset32)
-		outp += sprintf(outp, "   MSR 0x%03X", extra_msr_offset32);
-	if (extra_msr_offset64)
-		outp += sprintf(outp, "           MSR 0x%03X", extra_msr_offset64);
+	if (show_pkg)
+		outp += sprintf(outp, "\tPackage");
+	if (show_core)
+		outp += sprintf(outp, "\tCore");
+	if (show_cpu)
+		outp += sprintf(outp, "\tCPU");
+	if (has_aperf)
+		outp += sprintf(outp, "\tAvg_MHz");
+	if (has_aperf)
+		outp += sprintf(outp, "\tBusy%%");
+	if (has_aperf)
+		outp += sprintf(outp, "\tBzy_MHz");
+	outp += sprintf(outp, "\tTSC_MHz");
 
 	if (!debug)
 		goto done;
 
 	if (do_irq)
-		outp += sprintf(outp, "     IRQ");
+		outp += sprintf(outp, "\tIRQ");
 	if (do_smi)
-		outp += sprintf(outp, "     SMI");
+		outp += sprintf(outp, "\tSMI");
 
 	if (do_nhm_cstates)
-		outp += sprintf(outp, "  CPU%%c1");
+		outp += sprintf(outp, "\tCPU%%c1");
 	if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
-		outp += sprintf(outp, "  CPU%%c3");
+		outp += sprintf(outp, "\tCPU%%c3");
 	if (do_nhm_cstates)
-		outp += sprintf(outp, "  CPU%%c6");
+		outp += sprintf(outp, "\tCPU%%c6");
 	if (do_snb_cstates)
-		outp += sprintf(outp, "  CPU%%c7");
+		outp += sprintf(outp, "\tCPU%%c7");
+
+	for (mp = sys.tp; mp; mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 64)
+				outp += sprintf(outp, "\t%18.18s", mp->name);
+			else
+				outp += sprintf(outp, "\t%10.10s", mp->name);
+		} else {
+			outp += sprintf(outp, "\t%-7.7s", mp->name);
+		}
+	}
 
 	if (do_dts)
-		outp += sprintf(outp, " CoreTmp");
+		outp += sprintf(outp, "\tCoreTmp");
+
+	for (mp = sys.cp; mp; mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 64)
+				outp += sprintf(outp, "\t%18.18s", mp->name);
+			else
+				outp += sprintf(outp, "\t%10.10s", mp->name);
+		} else {
+			outp += sprintf(outp, "\t%-7.7s", mp->name);
+		}
+	}
+
 	if (do_ptm)
-		outp += sprintf(outp, "  PkgTmp");
+		outp += sprintf(outp, "\tPkgTmp");
 
 	if (do_gfx_rc6_ms)
-		outp += sprintf(outp, " GFX%%rc6");
+		outp += sprintf(outp, "\tGFX%%rc6");
 
 	if (do_gfx_mhz)
-		outp += sprintf(outp, "  GFXMHz");
+		outp += sprintf(outp, "\tGFXMHz");
 
 	if (do_skl_residency) {
-		outp += sprintf(outp, " Totl%%C0");
-		outp += sprintf(outp, "  Any%%C0");
-		outp += sprintf(outp, "  GFX%%C0");
-		outp += sprintf(outp, " CPUGFX%%");
+		outp += sprintf(outp, "\tTotl%%C0");
+		outp += sprintf(outp, "\tAny%%C0");
+		outp += sprintf(outp, "\tGFX%%C0");
+		outp += sprintf(outp, "\tCPUGFX%%");
 	}
 
 	if (do_pc2)
-		outp += sprintf(outp, " Pkg%%pc2");
+		outp += sprintf(outp, "\tPkg%%pc2");
 	if (do_pc3)
-		outp += sprintf(outp, " Pkg%%pc3");
+		outp += sprintf(outp, "\tPkg%%pc3");
 	if (do_pc6)
-		outp += sprintf(outp, " Pkg%%pc6");
+		outp += sprintf(outp, "\tPkg%%pc6");
 	if (do_pc7)
-		outp += sprintf(outp, " Pkg%%pc7");
+		outp += sprintf(outp, "\tPkg%%pc7");
 	if (do_c8_c9_c10) {
-		outp += sprintf(outp, " Pkg%%pc8");
-		outp += sprintf(outp, " Pkg%%pc9");
-		outp += sprintf(outp, " Pk%%pc10");
+		outp += sprintf(outp, "\tPkg%%pc8");
+		outp += sprintf(outp, "\tPkg%%pc9");
+		outp += sprintf(outp, "\tPk%%pc10");
 	}
 
 	if (do_rapl && !rapl_joules) {
 		if (do_rapl & RAPL_PKG)
-			outp += sprintf(outp, " PkgWatt");
-		if (do_rapl & RAPL_CORES)
-			outp += sprintf(outp, " CorWatt");
+			outp += sprintf(outp, "\tPkgWatt");
+		if (do_rapl & RAPL_CORES_ENERGY_STATUS)
+			outp += sprintf(outp, "\tCorWatt");
 		if (do_rapl & RAPL_GFX)
-			outp += sprintf(outp, " GFXWatt");
+			outp += sprintf(outp, "\tGFXWatt");
 		if (do_rapl & RAPL_DRAM)
-			outp += sprintf(outp, " RAMWatt");
+			outp += sprintf(outp, "\tRAMWatt");
 		if (do_rapl & RAPL_PKG_PERF_STATUS)
-			outp += sprintf(outp, "   PKG_%%");
+			outp += sprintf(outp, "\tPKG_%%");
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
-			outp += sprintf(outp, "   RAM_%%");
+			outp += sprintf(outp, "\tRAM_%%");
 	} else if (do_rapl && rapl_joules) {
 		if (do_rapl & RAPL_PKG)
-			outp += sprintf(outp, "   Pkg_J");
-		if (do_rapl & RAPL_CORES)
-			outp += sprintf(outp, "   Cor_J");
+			outp += sprintf(outp, "\tPkg_J");
+		if (do_rapl & RAPL_CORES_ENERGY_STATUS)
+			outp += sprintf(outp, "\tCor_J");
 		if (do_rapl & RAPL_GFX)
-			outp += sprintf(outp, "   GFX_J");
+			outp += sprintf(outp, "\tGFX_J");
 		if (do_rapl & RAPL_DRAM)
-			outp += sprintf(outp, "   RAM_J");
+			outp += sprintf(outp, "\tRAM_J");
 		if (do_rapl & RAPL_PKG_PERF_STATUS)
-			outp += sprintf(outp, "   PKG_%%");
+			outp += sprintf(outp, "\tPKG_%%");
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
-			outp += sprintf(outp, "   RAM_%%");
-		outp += sprintf(outp, "   time");
-
+			outp += sprintf(outp, "\tRAM_%%");
 	}
-    done:
+	for (mp = sys.pp; mp; mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 64)
+				outp += sprintf(outp, "\t%18.18s", mp->name);
+			else
+				outp += sprintf(outp, "\t%10.10s", mp->name);
+		} else {
+			outp += sprintf(outp, "\t%-7.7s", mp->name);
+		}
+	}
+
+done:
 	outp += sprintf(outp, "\n");
 }
 
 int dump_counters(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
 {
+	int i;
+	struct msr_counter *mp;
+
 	outp += sprintf(outp, "t %p, c %p, p %p\n", t, c, p);
 
 	if (t) {
@@ -442,18 +493,16 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "aperf: %016llX\n", t->aperf);
 		outp += sprintf(outp, "mperf: %016llX\n", t->mperf);
 		outp += sprintf(outp, "c1: %016llX\n", t->c1);
-		outp += sprintf(outp, "msr0x%x: %08llX\n",
-			extra_delta_offset32, t->extra_delta32);
-		outp += sprintf(outp, "msr0x%x: %016llX\n",
-			extra_delta_offset64, t->extra_delta64);
-		outp += sprintf(outp, "msr0x%x: %08llX\n",
-			extra_msr_offset32, t->extra_msr32);
-		outp += sprintf(outp, "msr0x%x: %016llX\n",
-			extra_msr_offset64, t->extra_msr64);
+
 		if (do_irq)
 			outp += sprintf(outp, "IRQ: %08X\n", t->irq_count);
 		if (do_smi)
 			outp += sprintf(outp, "SMI: %08X\n", t->smi_count);
+
+		for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+			outp += sprintf(outp, "tADDED [%d] msr0x%x: %08llX\n",
+				i, mp->msr_num, t->counter[i]);
+		}
 	}
 
 	if (c) {
@@ -462,6 +511,11 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "c6: %016llX\n", c->c6);
 		outp += sprintf(outp, "c7: %016llX\n", c->c7);
 		outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
+
+		for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+			outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n",
+				i, mp->msr_num, c->counter[i]);
+		}
 	}
 
 	if (p) {
@@ -491,6 +545,11 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "Throttle RAM: %0X\n",
 			p->rapl_dram_perf_status);
 		outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c);
+
+		for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+			outp += sprintf(outp, "pADDED [%d] msr0x%x: %08llX\n",
+				i, mp->msr_num, p->counter[i]);
+		}
 	}
 
 	outp += sprintf(outp, "\n");
@@ -506,6 +565,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
 {
 	double interval_float;
 	char *fmt8;
+	int i;
+	struct msr_counter *mp;
 
 	 /* if showing only 1st thread in core and this isn't one, bail out */
 	if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
@@ -520,99 +581,103 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	/* topo columns, print blanks on 1st (average) line */
 	if (t == &average.threads) {
 		if (show_pkg)
-			outp += sprintf(outp, "       -");
+			outp += sprintf(outp, "\t-");
 		if (show_core)
-			outp += sprintf(outp, "       -");
+			outp += sprintf(outp, "\t-");
 		if (show_cpu)
-			outp += sprintf(outp, "       -");
+			outp += sprintf(outp, "\t-");
 	} else {
 		if (show_pkg) {
 			if (p)
-				outp += sprintf(outp, "%8d", p->package_id);
+				outp += sprintf(outp, "\t%d", p->package_id);
 			else
-				outp += sprintf(outp, "       -");
+				outp += sprintf(outp, "\t-");
 		}
 		if (show_core) {
 			if (c)
-				outp += sprintf(outp, "%8d", c->core_id);
+				outp += sprintf(outp, "\t%d", c->core_id);
 			else
-				outp += sprintf(outp, "       -");
+				outp += sprintf(outp, "\t-");
 		}
 		if (show_cpu)
-			outp += sprintf(outp, "%8d", t->cpu_id);
+			outp += sprintf(outp, "\t%d", t->cpu_id);
 	}
 
 	/* Avg_MHz */
 	if (has_aperf)
-		outp += sprintf(outp, "%8.0f",
+		outp += sprintf(outp, "\t%.0f",
 			1.0 / units * t->aperf / interval_float);
 
 	/* Busy% */
-	if (has_aperf) {
-		if (!skip_c0)
-			outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
-		else
-			outp += sprintf(outp, "********");
-	}
+	if (has_aperf)
+		outp += sprintf(outp, "\t%.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
 
 	/* Bzy_MHz */
 	if (has_aperf) {
 		if (has_base_hz)
-			outp += sprintf(outp, "%8.0f", base_hz / units * t->aperf / t->mperf);
+			outp += sprintf(outp, "\t%.0f", base_hz / units * t->aperf / t->mperf);
 		else
-			outp += sprintf(outp, "%8.0f",
+			outp += sprintf(outp, "\t%.0f",
 				1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
 	}
 
 	/* TSC_MHz */
-	outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float);
-
-	/* delta */
-	if (extra_delta_offset32)
-		outp += sprintf(outp, "  %11llu", t->extra_delta32);
-
-	/* DELTA */
-	if (extra_delta_offset64)
-		outp += sprintf(outp, "  %11llu", t->extra_delta64);
-	/* msr */
-	if (extra_msr_offset32)
-		outp += sprintf(outp, "  0x%08llx", t->extra_msr32);
-
-	/* MSR */
-	if (extra_msr_offset64)
-		outp += sprintf(outp, "  0x%016llx", t->extra_msr64);
+	outp += sprintf(outp, "\t%.0f", 1.0 * t->tsc/units/interval_float);
 
 	if (!debug)
 		goto done;
 
 	/* IRQ */
 	if (do_irq)
-		outp += sprintf(outp, "%8d", t->irq_count);
+		outp += sprintf(outp, "\t%d", t->irq_count);
 
 	/* SMI */
 	if (do_smi)
-		outp += sprintf(outp, "%8d", t->smi_count);
+		outp += sprintf(outp, "\t%d", t->smi_count);
 
-	if (do_nhm_cstates) {
-		if (!skip_c1)
-			outp += sprintf(outp, "%8.2f", 100.0 * t->c1/t->tsc);
-		else
-			outp += sprintf(outp, "********");
-	}
+	if (do_nhm_cstates)
+		outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/t->tsc);
 
 	/* print per-core data only for 1st thread in core */
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
 	if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
-		outp += sprintf(outp, "%8.2f", 100.0 * c->c3/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c3/t->tsc);
 	if (do_nhm_cstates)
-		outp += sprintf(outp, "%8.2f", 100.0 * c->c6/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c6/t->tsc);
 	if (do_snb_cstates)
-		outp += sprintf(outp, "%8.2f", 100.0 * c->c7/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/t->tsc);
+
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 32)
+				outp += sprintf(outp, "\t0x%08lx", (unsigned long) t->counter[i]);
+			else
+				outp += sprintf(outp, "\t0x%016llx", t->counter[i]);
+		} else if (mp->format == FORMAT_DELTA) {
+			outp += sprintf(outp, "\t%8lld", t->counter[i]);
+		} else if (mp->format == FORMAT_PERCENT) {
+			outp += sprintf(outp, "\t%.2f", 100.0 * t->counter[i]/t->tsc);
+		}
+	}
+
 
 	if (do_dts)
-		outp += sprintf(outp, "%8d", c->core_temp_c);
+		outp += sprintf(outp, "\t%d", c->core_temp_c);
+
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 32)
+				outp += sprintf(outp, "\t0x%08lx", (unsigned long) c->counter[i]);
+			else
+				outp += sprintf(outp, "\t0x%016llx", c->counter[i]);
+		} else if (mp->format == FORMAT_DELTA) {
+			outp += sprintf(outp, "\t%8lld", c->counter[i]);
+		} else if (mp->format == FORMAT_PERCENT) {
+			outp += sprintf(outp, "\t%.2f", 100.0 * c->counter[i]/t->tsc);
+		}
+	}
 
 	/* print per-package data only for 1st core in package */
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
@@ -620,42 +685,42 @@ int format_counters(struct thread_data *t, struct core_data *c,
 
 	/* PkgTmp */
 	if (do_ptm)
-		outp += sprintf(outp, "%8d", p->pkg_temp_c);
+		outp += sprintf(outp, "\t%d", p->pkg_temp_c);
 
 	/* GFXrc6 */
 	if (do_gfx_rc6_ms) {
-		if (p->gfx_rc6_ms == -1) {	/* detect counter reset */
-			outp += sprintf(outp, "  ***.**");
+		if (p->gfx_rc6_ms == -1) {	/* detect GFX counter reset */
+			outp += sprintf(outp, "\t**.**");
 		} else {
-			outp += sprintf(outp, "%8.2f",
+			outp += sprintf(outp, "\t%.2f",
 				p->gfx_rc6_ms / 10.0 / interval_float);
 		}
 	}
 
 	/* GFXMHz */
 	if (do_gfx_mhz)
-		outp += sprintf(outp, "%8d", p->gfx_mhz);
+		outp += sprintf(outp, "\t%d", p->gfx_mhz);
 
 	/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
 	if (do_skl_residency) {
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_wtd_core_c0/t->tsc);
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_any_core_c0/t->tsc);
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_any_gfxe_c0/t->tsc);
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pkg_both_core_gfxe_c0/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_wtd_core_c0/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_core_c0/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_gfxe_c0/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_both_core_gfxe_c0/t->tsc);
 	}
 
 	if (do_pc2)
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc2/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc2/t->tsc);
 	if (do_pc3)
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc3/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc3/t->tsc);
 	if (do_pc6)
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc6/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc6/t->tsc);
 	if (do_pc7)
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc7/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc7/t->tsc);
 	if (do_c8_c9_c10) {
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc8/t->tsc);
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc9/t->tsc);
-		outp += sprintf(outp, "%8.2f", 100.0 * p->pc10/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc8/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc9/t->tsc);
+		outp += sprintf(outp, "\t%.2f", 100.0 * p->pc10/t->tsc);
 	}
 
 	/*
@@ -663,14 +728,14 @@ int format_counters(struct thread_data *t, struct core_data *c,
  	 * indicate that results are suspect by printing "**" in fraction place.
  	 */
 	if (interval_float < rapl_joule_counter_range)
-		fmt8 = "%8.2f";
+		fmt8 = "\t%.2f";
 	else
-		fmt8 = " %6.0f**";
+		fmt8 = "%6.0f**";
 
 	if (do_rapl && !rapl_joules) {
 		if (do_rapl & RAPL_PKG)
 			outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units / interval_float);
-		if (do_rapl & RAPL_CORES)
+		if (do_rapl & RAPL_CORES_ENERGY_STATUS)
 			outp += sprintf(outp, fmt8, p->energy_cores * rapl_energy_units / interval_float);
 		if (do_rapl & RAPL_GFX)
 			outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units / interval_float);
@@ -697,9 +762,20 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
 		if (do_rapl & RAPL_DRAM_PERF_STATUS)
 			outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
-
-		outp += sprintf(outp, fmt8, interval_float);
 	}
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW) {
+			if (mp->width == 32)
+				outp += sprintf(outp, "\t0x%08lx", (unsigned long) p->counter[i]);
+			else
+				outp += sprintf(outp, "\t0x%016llx", p->counter[i]);
+		} else if (mp->format == FORMAT_DELTA) {
+			outp += sprintf(outp, "\t%8lld", p->counter[i]);
+		} else if (mp->format == FORMAT_PERCENT) {
+			outp += sprintf(outp, "\t%.2f", 100.0 * p->counter[i]/t->tsc);
+		}
+	}
+
 done:
 	outp += sprintf(outp, "\n");
 
@@ -752,9 +828,11 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_
 		old = 0x100000000 + new - old;	\
 	}
 
-void
+int
 delta_package(struct pkg_data *new, struct pkg_data *old)
 {
+	int i;
+	struct msr_counter *mp;
 
 	if (do_skl_residency) {
 		old->pkg_wtd_core_c0 = new->pkg_wtd_core_c0 - old->pkg_wtd_core_c0;
@@ -788,24 +866,46 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
 	DELTA_WRAP32(new->energy_dram, old->energy_dram);
 	DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status);
 	DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status);
+
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			old->counter[i] = new->counter[i];
+		else
+			old->counter[i] = new->counter[i] - old->counter[i];
+	}
+
+	return 0;
 }
 
 void
 delta_core(struct core_data *new, struct core_data *old)
 {
+	int i;
+	struct msr_counter *mp;
+
 	old->c3 = new->c3 - old->c3;
 	old->c6 = new->c6 - old->c6;
 	old->c7 = new->c7 - old->c7;
 	old->core_temp_c = new->core_temp_c;
+
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			old->counter[i] = new->counter[i];
+		else
+			old->counter[i] = new->counter[i] - old->counter[i];
+	}
 }
 
 /*
  * old = new - old
  */
-void
+int
 delta_thread(struct thread_data *new, struct thread_data *old,
 	struct core_data *core_delta)
 {
+	int i;
+	struct msr_counter *mp;
+
 	old->tsc = new->tsc - old->tsc;
 
 	/* check for TSC < 1 Mcycles over interval */
@@ -821,20 +921,7 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 			old->aperf = new->aperf - old->aperf;
 			old->mperf = new->mperf - old->mperf;
 		} else {
-
-			if (!aperf_mperf_unstable) {
-				fprintf(outf, "%s: APERF or MPERF went backwards *\n", progname);
-				fprintf(outf, "* Frequency results do not cover entire interval *\n");
-				fprintf(outf, "* fix this by running Linux-2.6.30 or later *\n");
-
-				aperf_mperf_unstable = 1;
-			}
-			/*
-			 * mperf delta is likely a huge "positive" number
-			 * can not use it for calculating c0 time
-			 */
-			skip_c0 = 1;
-			skip_c1 = 1;
+			return -1;
 		}
 	}
 
@@ -865,52 +952,53 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 		old->mperf = 1;	/* divide by 0 protection */
 	}
 
-	old->extra_delta32 = new->extra_delta32 - old->extra_delta32;
-	old->extra_delta32 &= 0xFFFFFFFF;
-
-	old->extra_delta64 = new->extra_delta64 - old->extra_delta64;
-
-	/*
-	 * Extra MSR is just a snapshot, simply copy latest w/o subtracting
-	 */
-	old->extra_msr32 = new->extra_msr32;
-	old->extra_msr64 = new->extra_msr64;
-
 	if (do_irq)
 		old->irq_count = new->irq_count - old->irq_count;
 
 	if (do_smi)
 		old->smi_count = new->smi_count - old->smi_count;
+
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			old->counter[i] = new->counter[i];
+		else
+			old->counter[i] = new->counter[i] - old->counter[i];
+	}
+	return 0;
 }
 
 int delta_cpu(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p, struct thread_data *t2,
 	struct core_data *c2, struct pkg_data *p2)
 {
+	int retval = 0;
+
 	/* calculate core delta only for 1st thread in core */
 	if (t->flags & CPU_IS_FIRST_THREAD_IN_CORE)
 		delta_core(c, c2);
 
 	/* always calculate thread delta */
-	delta_thread(t, t2, c2);	/* c2 is core delta */
+	retval = delta_thread(t, t2, c2);	/* c2 is core delta */
+	if (retval)
+		return retval;
 
 	/* calculate package delta only for 1st core in package */
 	if (t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)
-		delta_package(p, p2);
+		retval = delta_package(p, p2);
 
-	return 0;
+	return retval;
 }
 
 void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
+	int i;
+	struct msr_counter  *mp;
+
 	t->tsc = 0;
 	t->aperf = 0;
 	t->mperf = 0;
 	t->c1 = 0;
 
-	t->extra_delta32 = 0;
-	t->extra_delta64 = 0;
-
 	t->irq_count = 0;
 	t->smi_count = 0;
 
@@ -948,21 +1036,36 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	p->gfx_rc6_ms = 0;
 	p->gfx_mhz = 0;
+
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next)
+		t->counter[i] = 0;
+
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next)
+		c->counter[i] = 0;
+
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next)
+		p->counter[i] = 0;
 }
 int sum_counters(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
 {
+	int i;
+	struct msr_counter *mp;
+
 	average.threads.tsc += t->tsc;
 	average.threads.aperf += t->aperf;
 	average.threads.mperf += t->mperf;
 	average.threads.c1 += t->c1;
 
-	average.threads.extra_delta32 += t->extra_delta32;
-	average.threads.extra_delta64 += t->extra_delta64;
-
 	average.threads.irq_count += t->irq_count;
 	average.threads.smi_count += t->smi_count;
 
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.threads.counter[i] += t->counter[i];
+	}
+
 	/* sum per-core values only for 1st thread in core */
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		return 0;
@@ -973,6 +1076,12 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 
 	average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
 
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.cores.counter[i] += c->counter[i];
+	}
+
 	/* sum per-pkg values only for 1st core in pkg */
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		return 0;
@@ -1007,6 +1116,12 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 
 	average.packages.rapl_pkg_perf_status += p->rapl_pkg_perf_status;
 	average.packages.rapl_dram_perf_status += p->rapl_dram_perf_status;
+
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.packages.counter[i] += p->counter[i];
+	}
 	return 0;
 }
 /*
@@ -1016,6 +1131,9 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 void compute_average(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
 {
+	int i;
+	struct msr_counter *mp;
+
 	clear_counters(&average.threads, &average.cores, &average.packages);
 
 	for_all_cpus(sum_counters, t, c, p);
@@ -1025,11 +1143,6 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	average.threads.mperf /= topo.num_cpus;
 	average.threads.c1 /= topo.num_cpus;
 
-	average.threads.extra_delta32 /= topo.num_cpus;
-	average.threads.extra_delta32 &= 0xFFFFFFFF;
-
-	average.threads.extra_delta64 /= topo.num_cpus;
-
 	average.cores.c3 /= topo.num_cores;
 	average.cores.c6 /= topo.num_cores;
 	average.cores.c7 /= topo.num_cores;
@@ -1052,6 +1165,22 @@ void compute_average(struct thread_data *t, struct core_data *c,
 	average.packages.pc8 /= topo.num_packages;
 	average.packages.pc9 /= topo.num_packages;
 	average.packages.pc10 /= topo.num_packages;
+
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.threads.counter[i] /= topo.num_cpus;
+	}
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.cores.counter[i] /= topo.num_cores;
+	}
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+		if (mp->format == FORMAT_RAW)
+			continue;
+		average.packages.counter[i] /= topo.num_packages;
+	}
 }
 
 static unsigned long long rdtsc(void)
@@ -1073,6 +1202,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	int cpu = t->cpu_id;
 	unsigned long long msr;
 	int aperf_mperf_retry_count = 0;
+	struct msr_counter *mp;
+	int i;
 
 	if (cpu_migrate(cpu)) {
 		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
@@ -1145,31 +1276,18 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -5;
 		t->smi_count = msr & 0xFFFFFFFF;
 	}
-	if (extra_delta_offset32) {
-		if (get_msr(cpu, extra_delta_offset32, &msr))
-			return -5;
-		t->extra_delta32 = msr & 0xFFFFFFFF;
-	}
-
-	if (extra_delta_offset64)
-		if (get_msr(cpu, extra_delta_offset64, &t->extra_delta64))
-			return -5;
-
-	if (extra_msr_offset32) {
-		if (get_msr(cpu, extra_msr_offset32, &msr))
-			return -5;
-		t->extra_msr32 = msr & 0xFFFFFFFF;
-	}
-
-	if (extra_msr_offset64)
-		if (get_msr(cpu, extra_msr_offset64, &t->extra_msr64))
-			return -5;
 
 	if (use_c1_residency_msr) {
 		if (get_msr(cpu, MSR_CORE_C1_RES, &t->c1))
 			return -6;
 	}
 
+	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
+		if (get_msr(cpu, mp->msr_num, &t->counter[i]))
+			return -10;
+	}
+
+
 	/* collect core counters only for 1st thread in core */
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		return 0;
@@ -1197,6 +1315,10 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
 	}
 
+	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
+		if (get_msr(cpu, mp->msr_num, &c->counter[i]))
+			return -10;
+	}
 
 	/* collect package counters only for 1st core in package */
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
@@ -1237,7 +1359,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -13;
 		p->energy_pkg = msr & 0xFFFFFFFF;
 	}
-	if (do_rapl & RAPL_CORES) {
+	if (do_rapl & RAPL_CORES_ENERGY_STATUS) {
 		if (get_msr(cpu, MSR_PP0_ENERGY_STATUS, &msr))
 			return -14;
 		p->energy_cores = msr & 0xFFFFFFFF;
@@ -1274,6 +1396,11 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	if (do_gfx_mhz)
 		p->gfx_mhz = gfx_cur_mhz;
 
+	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
+		if (get_msr(cpu, mp->msr_num, &p->counter[i]))
+			return -10;
+	}
+
 	return 0;
 }
 
@@ -1310,6 +1437,7 @@ int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV,
 int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 
 
 static void
@@ -1638,7 +1766,7 @@ void free_fd_percpu(void)
 {
 	int i;
 
-	for (i = 0; i < topo.max_cpu_num; ++i) {
+	for (i = 0; i < topo.max_cpu_num + 1; ++i) {
 		if (fd_percpu[i] != 0)
 			close(fd_percpu[i]);
 	}
@@ -2071,7 +2199,10 @@ void turbostat_loop()
 		}
 		gettimeofday(&tv_odd, (struct timezone *)NULL);
 		timersub(&tv_odd, &tv_even, &tv_delta);
-		for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS);
+		if (for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS)) {
+			re_initialize();
+			goto restart;
+		}
 		compute_average(EVEN_COUNTERS);
 		format_all_counters(EVEN_COUNTERS);
 		flush_output_stdout();
@@ -2087,7 +2218,10 @@ void turbostat_loop()
 		}
 		gettimeofday(&tv_even, (struct timezone *)NULL);
 		timersub(&tv_even, &tv_odd, &tv_delta);
-		for_all_cpus_2(delta_cpu, EVEN_COUNTERS, ODD_COUNTERS);
+		if (for_all_cpus_2(delta_cpu, EVEN_COUNTERS, ODD_COUNTERS)) {
+			re_initialize();
+			goto restart;
+		}
 		compute_average(ODD_COUNTERS);
 		format_all_counters(ODD_COUNTERS);
 		flush_output_stdout();
@@ -2174,47 +2308,51 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
 	bclk = discover_bclk(family, model);
 
 	switch (model) {
-	case 0x1A:	/* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */
-	case 0x1E:	/* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */
+	case INTEL_FAM6_NEHALEM_EP:	/* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */
+	case INTEL_FAM6_NEHALEM:	/* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */
 	case 0x1F:	/* Core i7 and i5 Processor - Nehalem */
-	case 0x25:	/* Westmere Client - Clarkdale, Arrandale */
-	case 0x2C:	/* Westmere EP - Gulftown */
-	case 0x2E:	/* Nehalem-EX Xeon - Beckton */
-	case 0x2F:	/* Westmere-EX Xeon - Eagleton */
+	case INTEL_FAM6_WESTMERE:	/* Westmere Client - Clarkdale, Arrandale */
+	case INTEL_FAM6_WESTMERE_EP:	/* Westmere EP - Gulftown */
+	case INTEL_FAM6_NEHALEM_EX:	/* Nehalem-EX Xeon - Beckton */
+	case INTEL_FAM6_WESTMERE_EX:	/* Westmere-EX Xeon - Eagleton */
 		pkg_cstate_limits = nhm_pkg_cstate_limits;
 		break;
-	case 0x2A:	/* SNB */
-	case 0x2D:	/* SNB Xeon */
-	case 0x3A:	/* IVB */
-	case 0x3E:	/* IVB Xeon */
+	case INTEL_FAM6_SANDYBRIDGE:	/* SNB */
+	case INTEL_FAM6_SANDYBRIDGE_X:	/* SNB Xeon */
+	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
+	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
 		pkg_cstate_limits = snb_pkg_cstate_limits;
 		break;
-	case 0x3C:	/* HSW */
-	case 0x3F:	/* HSX */
-	case 0x45:	/* HSW */
-	case 0x46:	/* HSW */
-	case 0x3D:	/* BDW */
-	case 0x47:	/* BDW */
-	case 0x4F:	/* BDX */
-	case 0x56:	/* BDX-DE */
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
-	case 0x55:	/* SKX */
+	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_X:	/* HSX */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
+	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
+	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
+	case INTEL_FAM6_BROADWELL_X:	/* BDX */
+	case INTEL_FAM6_BROADWELL_XEON_D:	/* BDX-DE */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 		pkg_cstate_limits = hsw_pkg_cstate_limits;
 		break;
-	case 0x37:	/* BYT */
-	case 0x4D:	/* AVN */
+	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
+		pkg_cstate_limits = skx_pkg_cstate_limits;
+		break;
+	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
 		pkg_cstate_limits = slv_pkg_cstate_limits;
 		break;
-	case 0x4C:	/* AMT */
+	case INTEL_FAM6_ATOM_AIRMONT:	/* AMT */
 		pkg_cstate_limits = amt_pkg_cstate_limits;
 		break;
-	case 0x57:	/* PHI */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* PHI */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		pkg_cstate_limits = phi_pkg_cstate_limits;
 		break;
-	case 0x5C:	/* BXT */
+	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
+	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
 		pkg_cstate_limits = bxt_pkg_cstate_limits;
 		break;
 	default:
@@ -2234,9 +2372,10 @@ int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
 {
 	switch (model) {
 	/* Nehalem compatible, but do not include turbo-ratio limit support */
-	case 0x2E:	/* Nehalem-EX Xeon - Beckton */
-	case 0x2F:	/* Westmere-EX Xeon - Eagleton */
-	case 0x57:	/* PHI - Knights Landing (different MSR definition) */
+	case INTEL_FAM6_NEHALEM_EX:	/* Nehalem-EX Xeon - Beckton */
+	case INTEL_FAM6_WESTMERE_EX:	/* Westmere-EX Xeon - Eagleton */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* PHI - Knights Landing (different MSR definition) */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		return 0;
 	default:
 		return 1;
@@ -2251,8 +2390,8 @@ int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x3E:	/* IVB Xeon */
-	case 0x3F:	/* HSW Xeon */
+	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
+	case INTEL_FAM6_HASWELL_X:	/* HSW Xeon */
 		return 1;
 	default:
 		return 0;
@@ -2267,7 +2406,7 @@ int has_hsw_turbo_ratio_limit(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x3F:	/* HSW Xeon */
+	case INTEL_FAM6_HASWELL_X:	/* HSW Xeon */
 		return 1;
 	default:
 		return 0;
@@ -2283,7 +2422,8 @@ int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x57:	/* Knights Landing */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* Knights Landing */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		return 1;
 	default:
 		return 0;
@@ -2298,22 +2438,23 @@ int has_config_tdp(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x3A:	/* IVB */
-	case 0x3C:	/* HSW */
-	case 0x3F:	/* HSX */
-	case 0x45:	/* HSW */
-	case 0x46:	/* HSW */
-	case 0x3D:	/* BDW */
-	case 0x47:	/* BDW */
-	case 0x4F:	/* BDX */
-	case 0x56:	/* BDX-DE */
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
-	case 0x55:	/* SKX */
+	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
+	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_X:	/* HSX */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
+	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
+	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
+	case INTEL_FAM6_BROADWELL_X:	/* BDX */
+	case INTEL_FAM6_BROADWELL_XEON_D:	/* BDX-DE */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
 
-	case 0x57:	/* Knights Landing */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* Knights Landing */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		return 1;
 	default:
 		return 0;
@@ -2593,8 +2734,8 @@ double get_tdp(unsigned int model)
 			return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
 
 	switch (model) {
-	case 0x37:
-	case 0x4D:
+	case INTEL_FAM6_ATOM_SILVERMONT1:
+	case INTEL_FAM6_ATOM_SILVERMONT2:
 		return 30.0;
 	default:
 		return 135.0;
@@ -2611,10 +2752,11 @@ rapl_dram_energy_units_probe(int  model, double rapl_energy_units)
 	/* only called for genuine_intel, family 6 */
 
 	switch (model) {
-	case 0x3F:	/* HSX */
-	case 0x4F:	/* BDX */
-	case 0x56:	/* BDX-DE */
-	case 0x57:	/* KNL */
+	case INTEL_FAM6_HASWELL_X:	/* HSX */
+	case INTEL_FAM6_BROADWELL_X:	/* BDX */
+	case INTEL_FAM6_BROADWELL_XEON_D:	/* BDX-DE */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		return (rapl_dram_energy_units = 15.3 / 1000000);
 	default:
 		return (rapl_energy_units);
@@ -2640,38 +2782,42 @@ void rapl_probe(unsigned int family, unsigned int model)
 		return;
 
 	switch (model) {
-	case 0x2A:
-	case 0x3A:
-	case 0x3C:	/* HSW */
-	case 0x45:	/* HSW */
-	case 0x46:	/* HSW */
-	case 0x3D:	/* BDW */
-	case 0x47:	/* BDW */
+	case INTEL_FAM6_SANDYBRIDGE:
+	case INTEL_FAM6_IVYBRIDGE:
+	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
+	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
+	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
 		break;
-	case 0x5C:	/* BXT */
+	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
 		do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO;
 		break;
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
 		break;
-	case 0x3F:	/* HSX */
-	case 0x4F:	/* BDX */
-	case 0x56:	/* BDX-DE */
-	case 0x55:	/* SKX */
-	case 0x57:	/* KNL */
+	case INTEL_FAM6_HASWELL_X:	/* HSX */
+	case INTEL_FAM6_BROADWELL_X:	/* BDX */
+	case INTEL_FAM6_BROADWELL_XEON_D:	/* BDX-DE */
+	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
 		break;
-	case 0x2D:
-	case 0x3E:
+	case INTEL_FAM6_SANDYBRIDGE_X:
+	case INTEL_FAM6_IVYBRIDGE_X:
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO;
 		break;
-	case 0x37:	/* BYT */
-	case 0x4D:	/* AVN */
-		do_rapl = RAPL_PKG | RAPL_CORES ;
+	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
+		do_rapl = RAPL_PKG | RAPL_CORES;
+		break;
+	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
+		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS;
 		break;
 	default:
 		return;
@@ -2682,7 +2828,7 @@ void rapl_probe(unsigned int family, unsigned int model)
 		return;
 
 	rapl_power_units = 1.0 / (1 << (msr & 0xF));
-	if (model == 0x37)
+	if (model == INTEL_FAM6_ATOM_SILVERMONT1)
 		rapl_energy_units = 1.0 * (1 << (msr >> 8 & 0x1F)) / 1000000;
 	else
 		rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F));
@@ -2713,11 +2859,11 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model)
 		return;
 
 	switch (model) {
-	case 0x3C:	/* HSW */
-	case 0x45:	/* HSW */
-	case 0x46:	/* HSW */
+	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
 		do_gfx_perf_limit_reasons = 1;
-	case 0x3F:	/* HSX */
+	case INTEL_FAM6_HASWELL_X:	/* HSX */
 		do_core_perf_limit_reasons = 1;
 		do_ring_perf_limit_reasons = 1;
 	default:
@@ -2737,7 +2883,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
 	cpu = t->cpu_id;
 
 	/* DTS is per-core, no need to print for each thread */
-	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) 
+	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		return 0;
 
 	if (cpu_migrate(cpu)) {
@@ -2886,9 +3032,8 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF);
 		}
 	}
-	if (do_rapl & RAPL_CORES) {
+	if (do_rapl & RAPL_CORES_POWER_LIMIT) {
 		if (debug) {
-
 			if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr))
 				return -9;
 			fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n",
@@ -2927,24 +3072,25 @@ int has_snb_msrs(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x2A:
-	case 0x2D:
-	case 0x3A:	/* IVB */
-	case 0x3E:	/* IVB Xeon */
-	case 0x3C:	/* HSW */
-	case 0x3F:	/* HSW */
-	case 0x45:	/* HSW */
-	case 0x46:	/* HSW */
-	case 0x3D:	/* BDW */
-	case 0x47:	/* BDW */
-	case 0x4F:	/* BDX */
-	case 0x56:	/* BDX-DE */
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
-	case 0x55:	/* SKX */
-	case 0x5C:	/* BXT */
+	case INTEL_FAM6_SANDYBRIDGE:
+	case INTEL_FAM6_SANDYBRIDGE_X:
+	case INTEL_FAM6_IVYBRIDGE:	/* IVB */
+	case INTEL_FAM6_IVYBRIDGE_X:	/* IVB Xeon */
+	case INTEL_FAM6_HASWELL_CORE:	/* HSW */
+	case INTEL_FAM6_HASWELL_X:	/* HSW */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_HASWELL_GT3E:	/* HSW */
+	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
+	case INTEL_FAM6_BROADWELL_GT3E:	/* BDW */
+	case INTEL_FAM6_BROADWELL_X:	/* BDX */
+	case INTEL_FAM6_BROADWELL_XEON_D:	/* BDX-DE */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_SKYLAKE_X:	/* SKX */
+	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
+	case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
 		return 1;
 	}
 	return 0;
@@ -2968,13 +3114,13 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x45:	/* HSW */
-	case 0x3D:	/* BDW */
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
-	case 0x5C:	/* BXT */
+	case INTEL_FAM6_HASWELL_ULT:	/* HSW */
+	case INTEL_FAM6_BROADWELL_CORE:	/* BDW */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
+	case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
 		return 1;
 	}
 	return 0;
@@ -2994,10 +3140,10 @@ int has_skl_msrs(unsigned int family, unsigned int model)
 		return 0;
 
 	switch (model) {
-	case 0x4E:	/* SKL */
-	case 0x5E:	/* SKL */
-	case 0x8E:	/* KBL */
-	case 0x9E:	/* KBL */
+	case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+	case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+	case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+	case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 		return 1;
 	}
 	return 0;
@@ -3010,8 +3156,8 @@ int is_slm(unsigned int family, unsigned int model)
 	if (!genuine_intel)
 		return 0;
 	switch (model) {
-	case 0x37:	/* BYT */
-	case 0x4D:	/* AVN */
+	case INTEL_FAM6_ATOM_SILVERMONT1:	/* BYT */
+	case INTEL_FAM6_ATOM_SILVERMONT2:	/* AVN */
 		return 1;
 	}
 	return 0;
@@ -3022,7 +3168,8 @@ int is_knl(unsigned int family, unsigned int model)
 	if (!genuine_intel)
 		return 0;
 	switch (model) {
-	case 0x57:	/* KNL */
+	case INTEL_FAM6_XEON_PHI_KNL:	/* KNL */
+	case INTEL_FAM6_XEON_PHI_KNM:
 		return 1;
 	}
 	return 0;
@@ -3050,7 +3197,7 @@ double slm_bclk(void)
 	i = msr & 0xf;
 	if (i >= SLM_BCLK_FREQS) {
 		fprintf(outf, "SLM BCLK[%d] invalid\n", i);
-		msr = 3;
+		i = 3;
 	}
 	freq = slm_freq_table[i];
 
@@ -3174,10 +3321,11 @@ void decode_misc_pwr_mgmt_msr(void)
 		return;
 
 	if (!get_msr(base_cpu, MSR_MISC_PWR_MGMT, &msr))
-		fprintf(outf, "cpu%d: MSR_MISC_PWR_MGMT: 0x%08llx (%sable-EIST_Coordination %sable-EPB)\n",
+		fprintf(outf, "cpu%d: MSR_MISC_PWR_MGMT: 0x%08llx (%sable-EIST_Coordination %sable-EPB %sable-OOB)\n",
 			base_cpu, msr,
 			msr & (1 << 0) ? "DIS" : "EN",
-			msr & (1 << 1) ? "EN" : "DIS");
+			msr & (1 << 1) ? "EN" : "DIS",
+			msr & (1 << 8) ? "EN" : "DIS");
 }
 
 void process_cpuid()
@@ -3303,16 +3451,17 @@ void process_cpuid()
 
 			if (crystal_hz == 0)
 				switch(model) {
-				case 0x4E:	/* SKL */
-				case 0x5E:	/* SKL */
-				case 0x8E:	/* KBL */
-				case 0x9E:	/* KBL */
+				case INTEL_FAM6_SKYLAKE_MOBILE:	/* SKL */
+				case INTEL_FAM6_SKYLAKE_DESKTOP:	/* SKL */
+				case INTEL_FAM6_KABYLAKE_MOBILE:	/* KBL */
+				case INTEL_FAM6_KABYLAKE_DESKTOP:	/* KBL */
 					crystal_hz = 24000000;	/* 24.0 MHz */
 					break;
-				case 0x55:	/* SKX */
+				case INTEL_FAM6_SKYLAKE_X:	/* SKX */
+				case INTEL_FAM6_ATOM_DENVERTON:	/* DNV */
 					crystal_hz = 25000000;	/* 25.0 MHz */
 					break;
-				case 0x5C:	/* BXT */
+				case INTEL_FAM6_ATOM_GOLDMONT:	/* BXT */
 					crystal_hz = 19200000;	/* 19.2 MHz */
 					break;
 				default:
@@ -3385,14 +3534,12 @@ void help()
 	"when COMMAND completes.\n"
 	"If no COMMAND is specified, turbostat wakes every 5-seconds\n"
 	"to print statistics, until interrupted.\n"
+	"--add		add a counter\n"
+	"		eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
 	"--debug	run in \"debug\" mode\n"
 	"--interval sec	Override default 5-second measurement interval\n"
 	"--help		print this help message\n"
-	"--counter msr	print 32-bit counter at address \"msr\"\n"
-	"--Counter msr	print 64-bit Counter at address \"msr\"\n"
 	"--out file	create or truncate \"file\" for all output\n"
-	"--msr msr	print 32-bit value at address \"msr\"\n"
-	"--MSR msr	print 64-bit Value at address \"msr\"\n"
 	"--version	print version information\n"
 	"\n"
 	"For more help, run \"man turbostat\"\n");
@@ -3515,7 +3662,7 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data
 	int i;
 
 	*t = calloc(topo.num_threads_per_core * topo.num_cores_per_pkg *
-		topo.num_packages, sizeof(struct thread_data));
+		topo.num_packages, sizeof(struct thread_data) + sys.thread_counter_bytes);
 	if (*t == NULL)
 		goto error;
 
@@ -3524,14 +3671,14 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data
 		(*t)[i].cpu_id = -1;
 
 	*c = calloc(topo.num_cores_per_pkg * topo.num_packages,
-		sizeof(struct core_data));
+		sizeof(struct core_data) + sys.core_counter_bytes);
 	if (*c == NULL)
 		goto error;
 
 	for (i = 0; i < topo.num_cores_per_pkg * topo.num_packages; i++)
 		(*c)[i].core_id = -1;
 
-	*p = calloc(topo.num_packages, sizeof(struct pkg_data));
+	*p = calloc(topo.num_packages, sizeof(struct pkg_data) + sys.package_counter_bytes);
 	if (*p == NULL)
 		goto error;
 
@@ -3598,7 +3745,7 @@ void allocate_output_buffer()
 }
 void allocate_fd_percpu(void)
 {
-	fd_percpu = calloc(topo.max_cpu_num, sizeof(int));
+	fd_percpu = calloc(topo.max_cpu_num + 1, sizeof(int));
 	if (fd_percpu == NULL)
 		err(-1, "calloc fd_percpu");
 }
@@ -3608,9 +3755,9 @@ void allocate_irq_buffers(void)
 	if (irq_column_2_cpu == NULL)
 		err(-1, "calloc %d", topo.num_cpus);
 
-	irqs_per_cpu = calloc(topo.max_cpu_num, sizeof(int));
+	irqs_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int));
 	if (irqs_per_cpu == NULL)
-		err(-1, "calloc %d", topo.max_cpu_num);
+		err(-1, "calloc %d", topo.max_cpu_num + 1);
 }
 void setup_all_buffers(void)
 {
@@ -3697,9 +3844,12 @@ int fork_it(char **argv)
 	for_all_cpus(get_counters, ODD_COUNTERS);
 	gettimeofday(&tv_odd, (struct timezone *)NULL);
 	timersub(&tv_odd, &tv_even, &tv_delta);
-	for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS);
-	compute_average(EVEN_COUNTERS);
-	format_all_counters(EVEN_COUNTERS);
+	if (for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS))
+		fprintf(outf, "%s: Counter reset detected\n", progname);
+	else {
+		compute_average(EVEN_COUNTERS);
+		format_all_counters(EVEN_COUNTERS);
+	}
 
 	fprintf(outf, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);
 
@@ -3726,24 +3876,170 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 4.12 5 Apr 2016"
+	fprintf(outf, "turbostat version 4.16 24 Dec 2016"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
+int add_counter(unsigned int msr_num, char *name, unsigned int width,
+	enum counter_scope scope, enum counter_type type,
+	enum counter_format format)
+{
+	struct msr_counter *msrp;
+
+	msrp = calloc(1, sizeof(struct msr_counter));
+	if (msrp == NULL) {
+		perror("calloc");
+		exit(1);
+	}
+
+	msrp->msr_num = msr_num;
+	strncpy(msrp->name, name, NAME_BYTES);
+	msrp->width = width;
+	msrp->type = type;
+	msrp->format = format;
+
+	switch (scope) {
+
+	case SCOPE_CPU:
+		sys.thread_counter_bytes += 64;
+		msrp->next = sys.tp;
+		sys.tp = msrp;
+		sys.thread_counter_bytes += sizeof(unsigned long long);
+		break;
+
+	case SCOPE_CORE:
+		sys.core_counter_bytes += 64;
+		msrp->next = sys.cp;
+		sys.cp = msrp;
+		sys.core_counter_bytes += sizeof(unsigned long long);
+		break;
+
+	case SCOPE_PACKAGE:
+		sys.package_counter_bytes += 64;
+		msrp->next = sys.pp;
+		sys.pp = msrp;
+		sys.package_counter_bytes += sizeof(unsigned long long);
+		break;
+	}
+
+	return 0;
+}
+
+void parse_add_command(char *add_command)
+{
+	int msr_num = 0;
+	char name_buffer[NAME_BYTES];
+	int width = 64;
+	int fail = 0;
+	enum counter_scope scope = SCOPE_CPU;
+	enum counter_type type = COUNTER_CYCLES;
+	enum counter_format format = FORMAT_DELTA;
+
+	while (add_command) {
+
+		if (sscanf(add_command, "msr0x%x", &msr_num) == 1)
+			goto next;
+
+		if (sscanf(add_command, "msr%d", &msr_num) == 1)
+			goto next;
+
+		if (sscanf(add_command, "u%d", &width) == 1) {
+			if ((width == 32) || (width == 64))
+				goto next;
+			width = 64;
+		}
+		if (!strncmp(add_command, "cpu", strlen("cpu"))) {
+			scope = SCOPE_CPU;
+			goto next;
+		}
+		if (!strncmp(add_command, "core", strlen("core"))) {
+			scope = SCOPE_CORE;
+			goto next;
+		}
+		if (!strncmp(add_command, "package", strlen("package"))) {
+			scope = SCOPE_PACKAGE;
+			goto next;
+		}
+		if (!strncmp(add_command, "cycles", strlen("cycles"))) {
+			type = COUNTER_CYCLES;
+			goto next;
+		}
+		if (!strncmp(add_command, "seconds", strlen("seconds"))) {
+			type = COUNTER_SECONDS;
+			goto next;
+		}
+		if (!strncmp(add_command, "raw", strlen("raw"))) {
+			format = FORMAT_RAW;
+			goto next;
+		}
+		if (!strncmp(add_command, "delta", strlen("delta"))) {
+			format = FORMAT_DELTA;
+			goto next;
+		}
+		if (!strncmp(add_command, "percent", strlen("percent"))) {
+			format = FORMAT_PERCENT;
+			goto next;
+		}
+
+		if (sscanf(add_command, "%18s,%*s", name_buffer) == 1) {	/* 18 < NAME_BYTES */
+			char *eos;
+
+			eos = strchr(name_buffer, ',');
+			if (eos)
+				*eos = '\0';
+			goto next;
+		}
+
+next:
+		add_command = strchr(add_command, ',');
+		if (add_command)
+			add_command++;
+
+	}
+	if (msr_num == 0) {
+		fprintf(stderr, "--add: (msrDDD | msr0xXXX) required\n");
+		fail++;
+	}
+
+	/* generate default column header */
+	if (*name_buffer == '\0') {
+		if (format == FORMAT_RAW) {
+			if (width == 32)
+				sprintf(name_buffer, "msr%d", msr_num);
+			else
+				sprintf(name_buffer, "MSR%d", msr_num);
+		} else if (format == FORMAT_DELTA) {
+			if (width == 32)
+				sprintf(name_buffer, "cnt%d", msr_num);
+			else
+				sprintf(name_buffer, "CNT%d", msr_num);
+		} else if (format == FORMAT_PERCENT) {
+			if (width == 32)
+				sprintf(name_buffer, "msr%d%%", msr_num);
+			else
+				sprintf(name_buffer, "MSR%d%%", msr_num);
+		}
+	}
+
+	if (add_counter(msr_num, name_buffer, width, scope, type, format))
+		fail++;
+
+	if (fail) {
+		help();
+		exit(1);
+	}
+}
 void cmdline(int argc, char **argv)
 {
 	int opt;
 	int option_index = 0;
 	static struct option long_options[] = {
-		{"Counter",	required_argument,	0, 'C'},
-		{"counter",	required_argument,	0, 'c'},
+		{"add",		required_argument,	0, 'a'},
 		{"Dump",	no_argument,		0, 'D'},
 		{"debug",	no_argument,		0, 'd'},
 		{"interval",	required_argument,	0, 'i'},
 		{"help",	no_argument,		0, 'h'},
 		{"Joules",	no_argument,		0, 'J'},
-		{"MSR",		required_argument,	0, 'M'},
-		{"msr",		required_argument,	0, 'm'},
 		{"out",		required_argument,	0, 'o'},
 		{"Package",	no_argument,		0, 'p'},
 		{"processor",	no_argument,		0, 'p'},
@@ -3758,11 +4054,8 @@ void cmdline(int argc, char **argv)
 	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:PpST:v",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
-		case 'C':
-			sscanf(optarg, "%x", &extra_delta_offset64);
-			break;
-		case 'c':
-			sscanf(optarg, "%x", &extra_delta_offset32);
+		case 'a':
+			parse_add_command(optarg);
 			break;
 		case 'D':
 			dump_only++;
@@ -3791,12 +4084,6 @@ void cmdline(int argc, char **argv)
 		case 'J':
 			rapl_joules++;
 			break;
-		case 'M':
-			sscanf(optarg, "%x", &extra_msr_offset64);
-			break;
-		case 'm':
-			sscanf(optarg, "%x", &extra_msr_offset32);
-			break;
 		case 'o':
 			outf = fopen_or_die(optarg, "w");
 			break;
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 97b657a..a2dbbcc 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -456,7 +456,7 @@ int kvm_timer_hyp_init(void)
 	kvm_info("virtual timer IRQ%d\n", host_vtimer_irq);
 
 	cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING,
-			  "AP_KVM_ARM_TIMER_STARTING", kvm_timer_starting_cpu,
+			  "kvm/arm/timer:starting", kvm_timer_starting_cpu,
 			  kvm_timer_dying_cpu);
 	return err;
 }
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 8cebfbc..5114391 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -428,7 +428,7 @@ int kvm_vgic_hyp_init(void)
 	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
-				"AP_KVM_ARM_VGIC_INIT_STARTING",
+				"kvm/arm/vgic:starting",
 				vgic_init_cpu_starting, vgic_init_cpu_dying);
 	if (ret) {
 		kvm_err("Cannot register vgic CPU notifier\n");
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 994f81f..482612b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3944,7 +3944,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 			goto out_free_1;
 	}
 
-	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "AP_KVM_STARTING",
+	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting",
 				      kvm_starting_cpu, kvm_dying_cpu);
 	if (r)
 		goto out_free_2;