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

Pull SMP hotplug updates from Thomas Gleixner:
 "This update is primarily a cleanup of the CPU hotplug locking code.

  The hotplug locking mechanism is an open coded RWSEM, which allows
  recursive locking. The main problem with that is the recursive nature
  as it evades the full lockdep coverage and hides potential deadlocks.

  The rework replaces the open coded RWSEM with a percpu RWSEM and
  establishes full lockdep coverage that way.

  The bulk of the changes fix up recursive locking issues and address
  the now fully reported potential deadlocks all over the place. Some of
  these deadlocks have been observed in the RT tree, but on mainline the
  probability was low enough to hide them away."

* 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
  cpu/hotplug: Constify attribute_group structures
  powerpc: Only obtain cpu_hotplug_lock if called by rtasd
  ARM/hw_breakpoint: Fix possible recursive locking for arch_hw_breakpoint_init
  cpu/hotplug: Remove unused check_for_tasks() function
  perf/core: Don't release cred_guard_mutex if not taken
  cpuhotplug: Link lock stacks for hotplug callbacks
  acpi/processor: Prevent cpu hotplug deadlock
  sched: Provide is_percpu_thread() helper
  cpu/hotplug: Convert hotplug locking to percpu rwsem
  s390: Prevent hotplug rwsem recursion
  arm: Prevent hotplug rwsem recursion
  arm64: Prevent cpu hotplug rwsem recursion
  kprobes: Cure hotplug lock ordering issues
  jump_label: Reorder hotplug lock and jump_label_lock
  perf/tracing/cpuhotplug: Fix locking order
  ACPI/processor: Use cpu_hotplug_disable() instead of get_online_cpus()
  PCI: Replace the racy recursion prevention
  PCI: Use cpu_hotplug_disable() instead of get_online_cpus()
  perf/x86/intel: Drop get_online_cpus() in intel_snb_check_microcode()
  x86/perf: Drop EXPORT of perf_check_microcode
  ...

21 files changed, 69 insertions, 56 deletions

diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index be3b3fbd382f..af2a7f1e3103 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -1090,7 +1090,7 @@ static int __init arch_hw_breakpoint_init(void)
 	 * driven low on this core and there isn't an architected way to
 	 * determine that.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	register_undef_hook(&debug_reg_hook);
 
 	/*
@@ -1098,15 +1098,16 @@ static int __init arch_hw_breakpoint_init(void)
 	 * assume that a halting debugger will leave the world in a nice state
 	 * for us.
 	 */
-	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm/hw_breakpoint:online",
-				dbg_reset_online, NULL);
+	ret = cpuhp_setup_state_cpuslocked(CPUHP_AP_ONLINE_DYN,
+					   "arm/hw_breakpoint:online",
+					   dbg_reset_online, NULL);
 	unregister_undef_hook(&debug_reg_hook);
 	if (WARN_ON(ret < 0) || !cpumask_empty(&debug_err_mask)) {
 		core_num_brps = 0;
 		core_num_wrps = 0;
 		if (ret > 0)
-			cpuhp_remove_state_nocalls(ret);
-		put_online_cpus();
+			cpuhp_remove_state_nocalls_cpuslocked(ret);
+		cpus_read_unlock();
 		return 0;
 	}
 
@@ -1124,7 +1125,7 @@ static int __init arch_hw_breakpoint_init(void)
 			TRAP_HWBKPT, "watchpoint debug exception");
 	hook_ifault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP,
 			TRAP_HWBKPT, "breakpoint debug exception");
-	put_online_cpus();
+	cpus_read_unlock();
 
 	/* Register PM notifiers. */
 	pm_init();
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
index 020560b2dcb7..a1a34722c655 100644
--- a/arch/arm/kernel/patch.c
+++ b/arch/arm/kernel/patch.c
@@ -124,5 +124,5 @@ void __kprobes patch_text(void *addr, unsigned int insn)
 		.insn = insn,
 	};
 
-	stop_machine(patch_text_stop_machine, &patch, NULL);
+	stop_machine_cpuslocked(patch_text_stop_machine, &patch, NULL);
 }
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index ad1f4e6a9e33..52d1cd14fda4 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -182,7 +182,8 @@ void __kprobes kprobes_remove_breakpoint(void *addr, unsigned int insn)
 		.addr = addr,
 		.insn = insn,
 	};
-	stop_machine(__kprobes_remove_breakpoint, &p, cpu_online_mask);
+	stop_machine_cpuslocked(__kprobes_remove_breakpoint, &p,
+				cpu_online_mask);
 }
 
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 29cb2ca756f6..4214c38d016b 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -433,7 +433,6 @@ u32 aarch64_set_branch_offset(u32 insn, s32 offset);
 bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
 
 int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
-int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
 int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
 
 s32 aarch64_insn_adrp_get_offset(u32 insn);
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index b884a926a632..cd872133e88e 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -255,6 +255,7 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
 	return ret;
 }
 
+static
 int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
 {
 	struct aarch64_insn_patch patch = {
@@ -267,8 +268,8 @@ int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
 	if (cnt <= 0)
 		return -EINVAL;
 
-	return stop_machine(aarch64_insn_patch_text_cb, &patch,
-			    cpu_online_mask);
+	return stop_machine_cpuslocked(aarch64_insn_patch_text_cb, &patch,
+				       cpu_online_mask);
 }
 
 int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
diff --git a/arch/mips/kernel/jump_label.c b/arch/mips/kernel/jump_label.c
index 3e586daa3a32..32e3168316cd 100644
--- a/arch/mips/kernel/jump_label.c
+++ b/arch/mips/kernel/jump_label.c
@@ -58,7 +58,6 @@ void arch_jump_label_transform(struct jump_entry *e,
 		insn.word = 0; /* nop */
 	}
 
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	if (IS_ENABLED(CONFIG_CPU_MICROMIPS)) {
 		insn_p->halfword[0] = insn.word >> 16;
@@ -70,7 +69,6 @@ void arch_jump_label_transform(struct jump_entry *e,
 			   (unsigned long)insn_p + sizeof(*insn_p));
 
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 #endif /* HAVE_JUMP_LABEL */
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 329771559cbb..dc4e15937ccf 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -43,6 +43,7 @@ extern void __init dump_numa_cpu_topology(void);
 
 extern int sysfs_add_device_to_node(struct device *dev, int nid);
 extern void sysfs_remove_device_from_node(struct device *dev, int nid);
+extern int numa_update_cpu_topology(bool cpus_locked);
 
 static inline int early_cpu_to_node(int cpu)
 {
@@ -71,6 +72,11 @@ static inline void sysfs_remove_device_from_node(struct device *dev,
 						int nid)
 {
 }
+
+static inline int numa_update_cpu_topology(bool cpus_locked)
+{
+	return 0;
+}
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 3650732639ed..0f0b1b2f3b60 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -283,7 +283,7 @@ static void prrn_work_fn(struct work_struct *work)
 	 * the RTAS event.
 	 */
 	pseries_devicetree_update(-prrn_update_scope);
-	arch_update_cpu_topology();
+	numa_update_cpu_topology(false);
 }
 
 static DECLARE_WORK(prrn_work, prrn_work_fn);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8d1a365b8edc..773b35d16a0b 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3368,7 +3368,7 @@ void kvmppc_alloc_host_rm_ops(void)
 		return;
 	}
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	for (cpu = 0; cpu < nr_cpu_ids; cpu += threads_per_core) {
 		if (!cpu_online(cpu))
@@ -3390,17 +3390,17 @@ void kvmppc_alloc_host_rm_ops(void)
 	l_ops = (unsigned long) ops;
 
 	if (cmpxchg64((unsigned long *)&kvmppc_host_rm_ops_hv, 0, l_ops)) {
-		put_online_cpus();
+		cpus_read_unlock();
 		kfree(ops->rm_core);
 		kfree(ops);
 		return;
 	}
 
-	cpuhp_setup_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE,
-				  "ppc/kvm_book3s:prepare",
-				  kvmppc_set_host_core,
-				  kvmppc_clear_host_core);
-	put_online_cpus();
+	cpuhp_setup_state_nocalls_cpuslocked(CPUHP_KVM_PPC_BOOK3S_PREPARE,
+					     "ppc/kvm_book3s:prepare",
+					     kvmppc_set_host_core,
+					     kvmppc_clear_host_core);
+	cpus_read_unlock();
 }
 
 void kvmppc_free_host_rm_ops(void)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 371792e4418f..b95c584ce19d 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1311,8 +1311,10 @@ static int update_lookup_table(void *data)
 /*
  * Update the node maps and sysfs entries for each cpu whose home node
  * has changed. Returns 1 when the topology has changed, and 0 otherwise.
+ *
+ * cpus_locked says whether we already hold cpu_hotplug_lock.
  */
-int arch_update_cpu_topology(void)
+int numa_update_cpu_topology(bool cpus_locked)
 {
 	unsigned int cpu, sibling, changed = 0;
 	struct topology_update_data *updates, *ud;
@@ -1400,15 +1402,23 @@ int arch_update_cpu_topology(void)
 	if (!cpumask_weight(&updated_cpus))
 		goto out;
 
-	stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
+	if (cpus_locked)
+		stop_machine_cpuslocked(update_cpu_topology, &updates[0],
+					&updated_cpus);
+	else
+		stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
 
 	/*
 	 * Update the numa-cpu lookup table with the new mappings, even for
 	 * offline CPUs. It is best to perform this update from the stop-
 	 * machine context.
 	 */
-	stop_machine(update_lookup_table, &updates[0],
+	if (cpus_locked)
+		stop_machine_cpuslocked(update_lookup_table, &updates[0],
 					cpumask_of(raw_smp_processor_id()));
+	else
+		stop_machine(update_lookup_table, &updates[0],
+			     cpumask_of(raw_smp_processor_id()));
 
 	for (ud = &updates[0]; ud; ud = ud->next) {
 		unregister_cpu_under_node(ud->cpu, ud->old_nid);
@@ -1426,6 +1436,12 @@ out:
 	return changed;
 }
 
+int arch_update_cpu_topology(void)
+{
+	lockdep_assert_cpus_held();
+	return numa_update_cpu_topology(true);
+}
+
 static void topology_work_fn(struct work_struct *work)
 {
 	rebuild_sched_domains();
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 8c6119280c13..309876d699e9 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -348,7 +348,7 @@ static int set_subcores_per_core(int new_mode)
 		state->master = 0;
 	}
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	/* This cpu will update the globals before exiting stop machine */
 	this_cpu_ptr(&split_state)->master = 1;
@@ -356,9 +356,10 @@ static int set_subcores_per_core(int new_mode)
 	/* Ensure state is consistent before we call the other cpus */
 	mb();
 
-	stop_machine(cpu_update_split_mode, &new_mode, cpu_online_mask);
+	stop_machine_cpuslocked(cpu_update_split_mode, &new_mode,
+				cpu_online_mask);
 
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 }
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index 6aa630a8d24f..262506cee4c3 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -93,7 +93,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 	args.entry = entry;
 	args.type = type;
 
-	stop_machine(__sm_arch_jump_label_transform, &args, NULL);
+	stop_machine_cpuslocked(__sm_arch_jump_label_transform, &args, NULL);
 }
 
 void arch_jump_label_transform_static(struct jump_entry *entry,
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 3d6a99746454..6842e4501e2e 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -196,7 +196,7 @@ void arch_arm_kprobe(struct kprobe *p)
 {
 	struct swap_insn_args args = {.p = p, .arm_kprobe = 1};
 
-	stop_machine(swap_instruction, &args, NULL);
+	stop_machine_cpuslocked(swap_instruction, &args, NULL);
 }
 NOKPROBE_SYMBOL(arch_arm_kprobe);
 
@@ -204,7 +204,7 @@ void arch_disarm_kprobe(struct kprobe *p)
 {
 	struct swap_insn_args args = {.p = p, .arm_kprobe = 0};
 
-	stop_machine(swap_instruction, &args, NULL);
+	stop_machine_cpuslocked(swap_instruction, &args, NULL);
 }
 NOKPROBE_SYMBOL(arch_disarm_kprobe);
 
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index c3a52f9a69a0..192efdfac918 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -636,10 +636,10 @@ static void stp_work_fn(struct work_struct *work)
 		goto out_unlock;
 
 	memset(&stp_sync, 0, sizeof(stp_sync));
-	get_online_cpus();
+	cpus_read_lock();
 	atomic_set(&stp_sync.cpus, num_online_cpus() - 1);
-	stop_machine(stp_sync_clock, &stp_sync, cpu_online_mask);
-	put_online_cpus();
+	stop_machine_cpuslocked(stp_sync_clock, &stp_sync, cpu_online_mask);
+	cpus_read_unlock();
 
 	if (!check_sync_clock())
 		/*
diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c
index 07933b9e9ce0..93adde1ac166 100644
--- a/arch/sparc/kernel/jump_label.c
+++ b/arch/sparc/kernel/jump_label.c
@@ -41,12 +41,10 @@ void arch_jump_label_transform(struct jump_entry *entry,
 		val = 0x01000000;
 	}
 
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	*insn = val;
 	flushi(insn);
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 #endif
diff --git a/arch/tile/kernel/jump_label.c b/arch/tile/kernel/jump_label.c
index 07802d586988..93931a46625b 100644
--- a/arch/tile/kernel/jump_label.c
+++ b/arch/tile/kernel/jump_label.c
@@ -45,14 +45,12 @@ static void __jump_label_transform(struct jump_entry *e,
 void arch_jump_label_transform(struct jump_entry *e,
 				enum jump_label_type type)
 {
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 
 	__jump_label_transform(e, type);
 	flush_icache_range(e->code, e->code + sizeof(tilegx_bundle_bits));
 
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 __init_or_module void arch_jump_label_transform_static(struct jump_entry *e,
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 2de0dd73830a..ff1ea2fb9705 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2233,7 +2233,6 @@ void perf_check_microcode(void)
 	if (x86_pmu.check_microcode)
 		x86_pmu.check_microcode();
 }
-EXPORT_SYMBOL_GPL(perf_check_microcode);
 
 static struct pmu pmu = {
 	.pmu_enable		= x86_pmu_enable,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 31acf2a98394..aa62437d1aa1 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3425,12 +3425,10 @@ static void intel_snb_check_microcode(void)
 	int pebs_broken = 0;
 	int cpu;
 
-	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		if ((pebs_broken = intel_snb_pebs_broken(cpu)))
 			break;
 	}
-	put_online_cpus();
 
 	if (pebs_broken == x86_pmu.pebs_broken)
 		return;
@@ -3503,7 +3501,9 @@ static bool check_msr(unsigned long msr, u64 mask)
 static __init void intel_sandybridge_quirk(void)
 {
 	x86_pmu.check_microcode = intel_snb_check_microcode;
+	cpus_read_lock();
 	intel_snb_check_microcode();
+	cpus_read_unlock();
 }
 
 static const struct { int id; char *name; } intel_arch_events_map[] __initconst = {
@@ -4175,13 +4175,12 @@ static __init int fixup_ht_bug(void)
 
 	lockup_detector_resume();
 
-	get_online_cpus();
+	cpus_read_lock();
 
-	for_each_online_cpu(c) {
+	for_each_online_cpu(c)
 		free_excl_cntrs(c);
-	}
 
-	put_online_cpus();
+	cpus_read_unlock();
 	pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n");
 	return 0;
 }
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 8c00dc09a5d2..2521f771f2f5 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -1682,7 +1682,7 @@ static int __init intel_cqm_init(void)
 	 *
 	 * Also, check that the scales match on all cpus.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(cpu) {
 		struct cpuinfo_x86 *c = &cpu_data(cpu);
 
@@ -1746,14 +1746,14 @@ static int __init intel_cqm_init(void)
 	 * Setup the hot cpu notifier once we are sure cqm
 	 * is enabled to avoid notifier leak.
 	 */
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING,
-			  "perf/x86/cqm:starting",
-			  intel_cqm_cpu_starting, NULL);
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "perf/x86/cqm:online",
-			  NULL, intel_cqm_cpu_exit);
-
+	cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_STARTING,
+				     "perf/x86/cqm:starting",
+				     intel_cqm_cpu_starting, NULL);
+	cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_ONLINE,
+				     "perf/x86/cqm:online",
+				     NULL, intel_cqm_cpu_exit);
 out:
-	put_online_cpus();
+	cpus_read_unlock();
 
 	if (ret) {
 		kfree(str);
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 2bce84d91c2b..c5bb63be4ba1 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -807,10 +807,8 @@ void mtrr_save_state(void)
 	if (!mtrr_enabled())
 		return;
 
-	get_online_cpus();
 	first_cpu = cpumask_first(cpu_online_mask);
 	smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1);
-	put_online_cpus();
 }
 
 void set_mtrr_aps_delayed_init(void)
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index c37bd0f39c70..ab4f491da2a9 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -105,11 +105,9 @@ static void __jump_label_transform(struct jump_entry *entry,
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	__jump_label_transform(entry, type, NULL, 0);
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 static enum {