Merge branch 'sched/urgent' into sched/core

Pick up the latest fixes before applying new changes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

17 files changed, 110 insertions, 60 deletions

diff --git a/kernel/.gitignore b/kernel/.gitignore
index b3097bde4e9c..790d83c7d160 100644
--- a/kernel/.gitignore
+++ b/kernel/.gitignore
@@ -5,3 +5,4 @@ config_data.h
 config_data.gz
 timeconst.h
 hz.bc
+x509_certificate_list
diff --git a/kernel/Makefile b/kernel/Makefile
index bbaf7d59c1bb..bc010ee272b6 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -137,9 +137,10 @@ $(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
 ###############################################################################
 ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y)
 X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509)
-X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += signing_key.x509
-X509_CERTIFICATES := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
+X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += $(objtree)/signing_key.x509
+X509_CERTIFICATES-raw := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
 				$(or $(realpath $(CERT)),$(CERT))))
+X509_CERTIFICATES := $(subst $(realpath $(objtree))/,,$(X509_CERTIFICATES-raw))
 
 ifeq ($(X509_CERTIFICATES),)
 $(warning *** No X.509 certificates found ***)
@@ -164,9 +165,9 @@ $(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list
 targets += $(obj)/.x509.list
 $(obj)/.x509.list:
 	@echo $(X509_CERTIFICATES) >$@
+endif
 
 clean-files := x509_certificate_list .x509.list
-endif
 
 ifeq ($(CONFIG_MODULE_SIG),y)
 ###############################################################################
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 5253204afdca..9fd4246b04b8 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -22,6 +22,6 @@ void foo(void)
 #ifdef CONFIG_SMP
 	DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
 #endif
-	DEFINE(BLOATED_SPINLOCKS, sizeof(spinlock_t) > sizeof(int));
+	DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
 	/* End of constants */
 }
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8b729c278b64..bc1dcabe9217 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -890,6 +890,16 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		struct cgroup *cgrp = dentry->d_fsdata;
 
 		BUG_ON(!(cgroup_is_dead(cgrp)));
+
+		/*
+		 * XXX: cgrp->id is only used to look up css's.  As cgroup
+		 * and css's lifetimes will be decoupled, it should be made
+		 * per-subsystem and moved to css->id so that lookups are
+		 * successful until the target css is released.
+		 */
+		idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+		cgrp->id = -1;
+
 		call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
 	} else {
 		struct cfent *cfe = __d_cfe(dentry);
@@ -4268,6 +4278,7 @@ static void css_release(struct percpu_ref *ref)
 	struct cgroup_subsys_state *css =
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
+	rcu_assign_pointer(css->cgroup->subsys[css->ss->subsys_id], NULL);
 	call_rcu(&css->rcu_head, css_free_rcu_fn);
 }
 
@@ -4426,14 +4437,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
 	root->number_of_cgroups++;
 
-	/* each css holds a ref to the cgroup's dentry and the parent css */
-	for_each_root_subsys(root, ss) {
-		struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
-		dget(dentry);
-		css_get(css->parent);
-	}
-
 	/* hold a ref to the parent's dentry */
 	dget(parent->dentry);
 
@@ -4445,6 +4448,13 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 		if (err)
 			goto err_destroy;
 
+		/* each css holds a ref to the cgroup's dentry and parent css */
+		dget(dentry);
+		css_get(css->parent);
+
+		/* mark it consumed for error path */
+		css_ar[ss->subsys_id] = NULL;
+
 		if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
 		    parent->parent) {
 			pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
@@ -4491,6 +4501,14 @@ err_free_cgrp:
 	return err;
 
 err_destroy:
+	for_each_root_subsys(root, ss) {
+		struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
+
+		if (css) {
+			percpu_ref_cancel_init(&css->refcnt);
+			ss->css_free(css);
+		}
+	}
 	cgroup_destroy_locked(cgrp);
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&dentry->d_inode->i_mutex);
@@ -4652,8 +4670,12 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	 * will be invoked to perform the rest of destruction once the
 	 * percpu refs of all css's are confirmed to be killed.
 	 */
-	for_each_root_subsys(cgrp->root, ss)
-		kill_css(cgroup_css(cgrp, ss));
+	for_each_root_subsys(cgrp->root, ss) {
+		struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
+
+		if (css)
+			kill_css(css);
+	}
 
 	/*
 	 * Mark @cgrp dead.  This prevents further task migration and child
@@ -4722,14 +4744,6 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp)
 	/* delete this cgroup from parent->children */
 	list_del_rcu(&cgrp->sibling);
 
-	/*
-	 * We should remove the cgroup object from idr before its grace
-	 * period starts, so we won't be looking up a cgroup while the
-	 * cgroup is being freed.
-	 */
-	idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
-	cgrp->id = -1;
-
 	dput(d);
 
 	set_bit(CGRP_RELEASABLE, &parent->flags);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 72348dc192c1..f5744010a8d2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1396,6 +1396,8 @@ event_sched_out(struct perf_event *event,
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
 		return;
 
+	perf_pmu_disable(event->pmu);
+
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	if (event->pending_disable) {
 		event->pending_disable = 0;
@@ -1412,6 +1414,8 @@ event_sched_out(struct perf_event *event,
 		ctx->nr_freq--;
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
 		cpuctx->exclusive = 0;
+
+	perf_pmu_enable(event->pmu);
 }
 
 static void
@@ -1652,6 +1656,7 @@ event_sched_in(struct perf_event *event,
 		 struct perf_event_context *ctx)
 {
 	u64 tstamp = perf_event_time(event);
+	int ret = 0;
 
 	if (event->state <= PERF_EVENT_STATE_OFF)
 		return 0;
@@ -1674,10 +1679,13 @@ event_sched_in(struct perf_event *event,
 	 */
 	smp_wmb();
 
+	perf_pmu_disable(event->pmu);
+
 	if (event->pmu->add(event, PERF_EF_START)) {
 		event->state = PERF_EVENT_STATE_INACTIVE;
 		event->oncpu = -1;
-		return -EAGAIN;
+		ret = -EAGAIN;
+		goto out;
 	}
 
 	event->tstamp_running += tstamp - event->tstamp_stopped;
@@ -1693,7 +1701,10 @@ event_sched_in(struct perf_event *event,
 	if (event->attr.exclusive)
 		cpuctx->exclusive = 1;
 
-	return 0;
+out:
+	perf_pmu_enable(event->pmu);
+
+	return ret;
 }
 
 static int
@@ -2743,6 +2754,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 		if (!event_filter_match(event))
 			continue;
 
+		perf_pmu_disable(event->pmu);
+
 		hwc = &event->hw;
 
 		if (hwc->interrupts == MAX_INTERRUPTS) {
@@ -2752,7 +2765,7 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 		}
 
 		if (!event->attr.freq || !event->attr.sample_freq)
-			continue;
+			goto next;
 
 		/*
 		 * stop the event and update event->count
@@ -2774,6 +2787,8 @@ static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx,
 			perf_adjust_period(event, period, delta, false);
 
 		event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
+	next:
+		perf_pmu_enable(event->pmu);
 	}
 
 	perf_pmu_enable(ctx->pmu);
diff --git a/kernel/fork.c b/kernel/fork.c
index b3080823a24d..6023d150a305 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -537,6 +537,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	spin_lock_init(&mm->page_table_lock);
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	clear_tlb_flush_pending(mm);
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;
diff --git a/kernel/freezer.c b/kernel/freezer.c
index b462fa197517..aa6a8aadb911 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -19,6 +19,12 @@ EXPORT_SYMBOL(system_freezing_cnt);
 bool pm_freezing;
 bool pm_nosig_freezing;
 
+/*
+ * Temporary export for the deadlock workaround in ata_scsi_hotplug().
+ * Remove once the hack becomes unnecessary.
+ */
+EXPORT_SYMBOL_GPL(pm_freezing);
+
 /* protects freezing and frozen transitions */
 static DEFINE_SPINLOCK(freezer_lock);
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 80ba086f021d..f6ff0191ecf7 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -251,6 +251,9 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 		return -EINVAL;
 	address -= key->both.offset;
 
+	if (unlikely(!access_ok(rw, uaddr, sizeof(u32))))
+		return -EFAULT;
+
 	/*
 	 * PROCESS_PRIVATE futexes are fast.
 	 * As the mm cannot disappear under us and the 'key' only needs
@@ -259,8 +262,6 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 	 *        but access_ok() should be faster than find_vma()
 	 */
 	if (!fshared) {
-		if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))))
-			return -EFAULT;
 		key->private.mm = mm;
 		key->private.address = address;
 		get_futex_key_refs(key);
@@ -288,7 +289,7 @@ again:
 		put_page(page);
 		/* serialize against __split_huge_page_splitting() */
 		local_irq_disable();
-		if (likely(__get_user_pages_fast(address, 1, 1, &page) == 1)) {
+		if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) {
 			page_head = compound_head(page);
 			/*
 			 * page_head is valid pointer but we must pin
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 490afc03627e..9c970167e402 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -47,6 +47,9 @@ u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
 size_t vmcoreinfo_size;
 size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
 
+/* Flag to indicate we are going to kexec a new kernel */
+bool kexec_in_progress = false;
+
 /* Location of the reserved area for the crash kernel */
 struct resource crashk_res = {
 	.name  = "Crash kernel",
@@ -1675,7 +1678,9 @@ int kernel_kexec(void)
 	} else
 #endif
 	{
+		kexec_in_progress = true;
 		kernel_restart_prepare(NULL);
+		migrate_to_reboot_cpu();
 		printk(KERN_EMERG "Starting new kernel\n");
 		machine_shutdown();
 	}
diff --git a/kernel/power/console.c b/kernel/power/console.c
index 463aa6736751..eacb8bd8cab4 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -81,6 +81,7 @@ void pm_vt_switch_unregister(struct device *dev)
 	list_for_each_entry(tmp, &pm_vt_switch_list, head) {
 		if (tmp->dev == dev) {
 			list_del(&tmp->head);
+			kfree(tmp);
 			break;
 		}
 	}
diff --git a/kernel/reboot.c b/kernel/reboot.c
index f813b3474646..662c83fc16b7 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -104,7 +104,7 @@ int unregister_reboot_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_reboot_notifier);
 
-static void migrate_to_reboot_cpu(void)
+void migrate_to_reboot_cpu(void)
 {
 	/* The boot cpu is always logical cpu 0 */
 	int cpu = reboot_cpu;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4316af287f60..b73f4ba62b24 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1729,6 +1729,13 @@ void task_numa_work(struct callback_head *work)
 		    (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
 			continue;
 
+		/*
+		 * Skip inaccessible VMAs to avoid any confusion between
+		 * PROT_NONE and NUMA hinting ptes
+		 */
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+			continue;
+
 		do {
 			start = max(start, vma->vm_start);
 			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
@@ -3907,7 +3914,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 {
 	struct sched_entity *se = tg->se[cpu];
 
-	if (!tg->parent || !wl)	/* the trivial, non-cgroup case */
+	if (!tg->parent)	/* the trivial, non-cgroup case */
 		return wl;
 
 	for_each_sched_entity(se) {
diff --git a/kernel/system_certificates.S b/kernel/system_certificates.S
index 4aef390671cb..3e9868d47535 100644
--- a/kernel/system_certificates.S
+++ b/kernel/system_certificates.S
@@ -3,8 +3,18 @@
 
 	__INITRODATA
 
+	.align 8
 	.globl VMLINUX_SYMBOL(system_certificate_list)
 VMLINUX_SYMBOL(system_certificate_list):
+__cert_list_start:
 	.incbin "kernel/x509_certificate_list"
-	.globl VMLINUX_SYMBOL(system_certificate_list_end)
-VMLINUX_SYMBOL(system_certificate_list_end):
+__cert_list_end:
+
+	.align 8
+	.globl VMLINUX_SYMBOL(system_certificate_list_size)
+VMLINUX_SYMBOL(system_certificate_list_size):
+#ifdef CONFIG_64BIT
+	.quad __cert_list_end - __cert_list_start
+#else
+	.long __cert_list_end - __cert_list_start
+#endif
diff --git a/kernel/system_keyring.c b/kernel/system_keyring.c
index 564dd93430a2..52ebc70263f4 100644
--- a/kernel/system_keyring.c
+++ b/kernel/system_keyring.c
@@ -22,7 +22,7 @@ struct key *system_trusted_keyring;
 EXPORT_SYMBOL_GPL(system_trusted_keyring);
 
 extern __initconst const u8 system_certificate_list[];
-extern __initconst const u8 system_certificate_list_end[];
+extern __initconst const unsigned long system_certificate_list_size;
 
 /*
  * Load the compiled-in keys
@@ -60,8 +60,8 @@ static __init int load_system_certificate_list(void)
 
 	pr_notice("Loading compiled-in X.509 certificates\n");
 
-	end = system_certificate_list_end;
 	p = system_certificate_list;
+	end = p + system_certificate_list_size;
 	while (p < end) {
 		/* Each cert begins with an ASN.1 SEQUENCE tag and must be more
 		 * than 256 bytes in size.
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0e9f9eaade2f..72a0f81dc5a8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -775,7 +775,7 @@ static int ftrace_profile_init(void)
 	int cpu;
 	int ret = 0;
 
-	for_each_online_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		ret = ftrace_profile_init_cpu(cpu);
 		if (ret)
 			break;
diff --git a/kernel/user.c b/kernel/user.c
index a3a0dbfda329..c006131beb77 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,9 +51,9 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
-#ifdef CONFIG_KEYS_KERBEROS_CACHE
-	.krb_cache_register_sem =
-	__RWSEM_INITIALIZER(init_user_ns.krb_cache_register_sem),
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	.persistent_keyring_register_sem =
+	__RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
 #endif
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c66912be990f..b010eac595d2 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2851,19 +2851,6 @@ already_gone:
 	return false;
 }
 
-static bool __flush_work(struct work_struct *work)
-{
-	struct wq_barrier barr;
-
-	if (start_flush_work(work, &barr)) {
-		wait_for_completion(&barr.done);
-		destroy_work_on_stack(&barr.work);
-		return true;
-	} else {
-		return false;
-	}
-}
-
 /**
  * flush_work - wait for a work to finish executing the last queueing instance
  * @work: the work to flush
@@ -2877,10 +2864,18 @@ static bool __flush_work(struct work_struct *work)
  */
 bool flush_work(struct work_struct *work)
 {
+	struct wq_barrier barr;
+
 	lock_map_acquire(&work->lockdep_map);
 	lock_map_release(&work->lockdep_map);
 
-	return __flush_work(work);
+	if (start_flush_work(work, &barr)) {
+		wait_for_completion(&barr.done);
+		destroy_work_on_stack(&barr.work);
+		return true;
+	} else {
+		return false;
+	}
 }
 EXPORT_SYMBOL_GPL(flush_work);
 
@@ -4832,14 +4827,7 @@ long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
 
 	INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn);
 	schedule_work_on(cpu, &wfc.work);
-
-	/*
-	 * The work item is on-stack and can't lead to deadlock through
-	 * flushing.  Use __flush_work() to avoid spurious lockdep warnings
-	 * when work_on_cpu()s are nested.
-	 */
-	__flush_work(&wfc.work);
-
+	flush_work(&wfc.work);
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);