Merge branch 'akpm-current/current'

23 files changed, 448 insertions, 637 deletions

diff --git a/kernel/async.c b/kernel/async.c
index 33258e6e20f8..b8d7a663497f 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -78,6 +78,12 @@ static DECLARE_WAIT_QUEUE_HEAD(async_done);
 
 static atomic_t entry_count;
 
+static long long microseconds_since(ktime_t start)
+{
+	ktime_t now = ktime_get();
+	return ktime_to_ns(ktime_sub(now, start)) >> 10;
+}
+
 static async_cookie_t lowest_in_progress(struct async_domain *domain)
 {
 	struct async_entry *first = NULL;
@@ -111,24 +117,18 @@ static void async_run_entry_fn(struct work_struct *work)
 	struct async_entry *entry =
 		container_of(work, struct async_entry, work);
 	unsigned long flags;
-	ktime_t calltime, delta, rettime;
+	ktime_t calltime;
 
 	/* 1) run (and print duration) */
-	if (initcall_debug && system_state < SYSTEM_RUNNING) {
-		pr_debug("calling  %lli_%pS @ %i\n",
-			(long long)entry->cookie,
-			entry->func, task_pid_nr(current));
-		calltime = ktime_get();
-	}
+	pr_debug("calling  %lli_%pS @ %i\n", (long long)entry->cookie,
+		 entry->func, task_pid_nr(current));
+	calltime = ktime_get();
+
 	entry->func(entry->data, entry->cookie);
-	if (initcall_debug && system_state < SYSTEM_RUNNING) {
-		rettime = ktime_get();
-		delta = ktime_sub(rettime, calltime);
-		pr_debug("initcall %lli_%pS returned 0 after %lld usecs\n",
-			(long long)entry->cookie,
-			entry->func,
-			(long long)ktime_to_ns(delta) >> 10);
-	}
+
+	pr_debug("initcall %lli_%pS returned after %lld usecs\n",
+		 (long long)entry->cookie, entry->func,
+		 microseconds_since(calltime));
 
 	/* 2) remove self from the pending queues */
 	spin_lock_irqsave(&async_lock, flags);
@@ -246,24 +246,6 @@ void async_synchronize_full(void)
 EXPORT_SYMBOL_GPL(async_synchronize_full);
 
 /**
- * async_unregister_domain - ensure no more anonymous waiters on this domain
- * @domain: idle domain to flush out of any async_synchronize_full instances
- *
- * async_synchronize_{cookie|full}_domain() are not flushed since callers
- * of these routines should know the lifetime of @domain
- *
- * Prefer ASYNC_DOMAIN_EXCLUSIVE() declarations over flushing
- */
-void async_unregister_domain(struct async_domain *domain)
-{
-	spin_lock_irq(&async_lock);
-	WARN_ON(!domain->registered || !list_empty(&domain->pending));
-	domain->registered = 0;
-	spin_unlock_irq(&async_lock);
-}
-EXPORT_SYMBOL_GPL(async_unregister_domain);
-
-/**
  * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain
  * @domain: the domain to synchronize
  *
@@ -287,23 +269,15 @@ EXPORT_SYMBOL_GPL(async_synchronize_full_domain);
  */
 void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain)
 {
-	ktime_t starttime, delta, endtime;
+	ktime_t starttime;
 
-	if (initcall_debug && system_state < SYSTEM_RUNNING) {
-		pr_debug("async_waiting @ %i\n", task_pid_nr(current));
-		starttime = ktime_get();
-	}
+	pr_debug("async_waiting @ %i\n", task_pid_nr(current));
+	starttime = ktime_get();
 
 	wait_event(async_done, lowest_in_progress(domain) >= cookie);
 
-	if (initcall_debug && system_state < SYSTEM_RUNNING) {
-		endtime = ktime_get();
-		delta = ktime_sub(endtime, starttime);
-
-		pr_debug("async_continuing @ %i after %lli usec\n",
-			task_pid_nr(current),
-			(long long)ktime_to_ns(delta) >> 10);
-	}
+	pr_debug("async_continuing @ %i after %lli usec\n", task_pid_nr(current),
+		 microseconds_since(starttime));
 }
 EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain);
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 9153b20e5cc6..e049edd66776 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1339,6 +1339,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 
 	mutex_unlock(&cgroup_mutex);
 
+	cgroup_rstat_exit(cgrp);
 	kernfs_destroy_root(root->kf_root);
 	cgroup_free_root(root);
 }
@@ -1751,6 +1752,12 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
 				       &dcgrp->e_csets[ss->id]);
 		spin_unlock_irq(&css_set_lock);
 
+		if (ss->css_rstat_flush) {
+			list_del_rcu(&css->rstat_css_node);
+			list_add_rcu(&css->rstat_css_node,
+				     &dcgrp->rstat_css_list);
+		}
+
 		/* default hierarchy doesn't enable controllers by default */
 		dst_root->subsys_mask |= 1 << ssid;
 		if (dst_root == &cgrp_dfl_root) {
@@ -1971,10 +1978,14 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	if (ret)
 		goto destroy_root;
 
-	ret = rebind_subsystems(root, ss_mask);
+	ret = cgroup_rstat_init(root_cgrp);
 	if (ret)
 		goto destroy_root;
 
+	ret = rebind_subsystems(root, ss_mask);
+	if (ret)
+		goto exit_stats;
+
 	ret = cgroup_bpf_inherit(root_cgrp);
 	WARN_ON_ONCE(ret);
 
@@ -2006,6 +2017,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	ret = 0;
 	goto out;
 
+exit_stats:
+	cgroup_rstat_exit(root_cgrp);
 destroy_root:
 	kernfs_destroy_root(root->kf_root);
 	root->kf_root = NULL;
@@ -4934,8 +4947,7 @@ static void css_free_rwork_fn(struct work_struct *work)
 			cgroup_put(cgroup_parent(cgrp));
 			kernfs_put(cgrp->kn);
 			psi_cgroup_free(cgrp);
-			if (cgroup_on_dfl(cgrp))
-				cgroup_rstat_exit(cgrp);
+			cgroup_rstat_exit(cgrp);
 			kfree(cgrp);
 		} else {
 			/*
@@ -4976,8 +4988,7 @@ static void css_release_work_fn(struct work_struct *work)
 		/* cgroup release path */
 		TRACE_CGROUP_PATH(release, cgrp);
 
-		if (cgroup_on_dfl(cgrp))
-			cgroup_rstat_flush(cgrp);
+		cgroup_rstat_flush(cgrp);
 
 		spin_lock_irq(&css_set_lock);
 		for (tcgrp = cgroup_parent(cgrp); tcgrp;
@@ -5034,7 +5045,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 		css_get(css->parent);
 	}
 
-	if (cgroup_on_dfl(cgrp) && ss->css_rstat_flush)
+	if (ss->css_rstat_flush)
 		list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list);
 
 	BUG_ON(cgroup_css(cgrp, ss));
@@ -5159,11 +5170,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
 	if (ret)
 		goto out_free_cgrp;
 
-	if (cgroup_on_dfl(parent)) {
-		ret = cgroup_rstat_init(cgrp);
-		if (ret)
-			goto out_cancel_ref;
-	}
+	ret = cgroup_rstat_init(cgrp);
+	if (ret)
+		goto out_cancel_ref;
 
 	/* create the directory */
 	kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
@@ -5250,8 +5259,7 @@ out_psi_free:
 out_kernfs_remove:
 	kernfs_remove(cgrp->kn);
 out_stat_exit:
-	if (cgroup_on_dfl(parent))
-		cgroup_rstat_exit(cgrp);
+	cgroup_rstat_exit(cgrp);
 out_cancel_ref:
 	percpu_ref_exit(&cgrp->self.refcnt);
 out_free_cgrp:
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index d51175cedfca..3a3fd2993a65 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -25,13 +25,8 @@ static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu)
 void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 {
 	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
-	struct cgroup *parent;
 	unsigned long flags;
 
-	/* nothing to do for root */
-	if (!cgroup_parent(cgrp))
-		return;
-
 	/*
 	 * Speculative already-on-list test. This may race leading to
 	 * temporary inaccuracies, which is fine.
@@ -46,10 +41,10 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 	raw_spin_lock_irqsave(cpu_lock, flags);
 
 	/* put @cgrp and all ancestors on the corresponding updated lists */
-	for (parent = cgroup_parent(cgrp); parent;
-	     cgrp = parent, parent = cgroup_parent(cgrp)) {
+	while (true) {
 		struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
-		struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu);
+		struct cgroup *parent = cgroup_parent(cgrp);
+		struct cgroup_rstat_cpu *prstatc;
 
 		/*
 		 * Both additions and removals are bottom-up.  If a cgroup
@@ -58,8 +53,17 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu)
 		if (rstatc->updated_next)
 			break;
 
+		/* Root has no parent to link it to, but mark it busy */
+		if (!parent) {
+			rstatc->updated_next = cgrp;
+			break;
+		}
+
+		prstatc = cgroup_rstat_cpu(parent, cpu);
 		rstatc->updated_next = prstatc->updated_children;
 		prstatc->updated_children = cgrp;
+
+		cgrp = parent;
 	}
 
 	raw_spin_unlock_irqrestore(cpu_lock, flags);
@@ -113,23 +117,26 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 	 */
 	if (rstatc->updated_next) {
 		struct cgroup *parent = cgroup_parent(pos);
-		struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu);
-		struct cgroup_rstat_cpu *nrstatc;
-		struct cgroup **nextp;
-
-		nextp = &prstatc->updated_children;
-		while (true) {
-			nrstatc = cgroup_rstat_cpu(*nextp, cpu);
-			if (*nextp == pos)
-				break;
-
-			WARN_ON_ONCE(*nextp == parent);
-			nextp = &nrstatc->updated_next;
+
+		if (parent) {
+			struct cgroup_rstat_cpu *prstatc;
+			struct cgroup **nextp;
+
+			prstatc = cgroup_rstat_cpu(parent, cpu);
+			nextp = &prstatc->updated_children;
+			while (true) {
+				struct cgroup_rstat_cpu *nrstatc;
+
+				nrstatc = cgroup_rstat_cpu(*nextp, cpu);
+				if (*nextp == pos)
+					break;
+				WARN_ON_ONCE(*nextp == parent);
+				nextp = &nrstatc->updated_next;
+			}
+			*nextp = rstatc->updated_next;
 		}
 
-		*nextp = rstatc->updated_next;
 		rstatc->updated_next = NULL;
-
 		return pos;
 	}
 
@@ -285,8 +292,6 @@ void __init cgroup_rstat_boot(void)
 
 	for_each_possible_cpu(cpu)
 		raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu));
-
-	BUG_ON(cgroup_rstat_init(&cgrp_dfl_root.cgrp));
 }
 
 /*
@@ -311,11 +316,15 @@ static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat,
 
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
 {
-	struct cgroup *parent = cgroup_parent(cgrp);
 	struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu);
+	struct cgroup *parent = cgroup_parent(cgrp);
 	struct cgroup_base_stat cur, delta;
 	unsigned seq;
 
+	/* Root-level stats are sourced from system-wide CPU stats */
+	if (!parent)
+		return;
+
 	/* fetch the current per-cpu values */
 	do {
 		seq = __u64_stats_fetch_begin(&rstatc->bsync);
@@ -328,8 +337,8 @@ static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
 	cgroup_base_stat_add(&cgrp->bstat, &delta);
 	cgroup_base_stat_add(&rstatc->last_bstat, &delta);
 
-	/* propagate global delta to parent */
-	if (parent) {
+	/* propagate global delta to parent (unless that's root) */
+	if (cgroup_parent(parent)) {
 		delta = cgrp->bstat;
 		cgroup_base_stat_sub(&delta, &cgrp->last_bstat);
 		cgroup_base_stat_add(&parent->bstat, &delta);
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 825284baaf46..90f9e4bb6704 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -7,6 +7,7 @@
 #include <linux/crash_core.h>
 #include <linux/utsname.h>
 #include <linux/vmalloc.h>
+#include <linux/kexec.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -250,6 +251,12 @@ static int __init __parse_crashkernel(char *cmdline,
 	if (suffix)
 		return parse_crashkernel_suffix(ck_cmdline, crash_size,
 				suffix);
+#ifdef CONFIG_CRASH_AUTO_STR
+	if (strncmp(ck_cmdline, "auto", 4) == 0) {
+		ck_cmdline = CONFIG_CRASH_AUTO_STR;
+		pr_info("Using crashkernel=auto, the size chosen is a best effort estimation.\n");
+	}
+#endif
 	/*
 	 * if the commandline contains a ':', then that's the extended
 	 * syntax -- if not, it must be the classic syntax
diff --git a/kernel/cred.c b/kernel/cred.c
index 421b1149c651..e1d274cd741b 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -33,7 +33,7 @@ do {									\
 static struct kmem_cache *cred_jar;
 
 /* init to 2 - one for init_task, one to ensure it is never freed */
-struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
+static struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
 
 /*
  * The initial credentials for the initial task
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index 905c3fa005f1..b4526668072e 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -66,6 +66,5 @@ void dma_common_free_remap(void *cpu_addr, size_t size)
 		return;
 	}
 
-	unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size));
 	vunmap(cpu_addr);
 }
diff --git a/kernel/exit.c b/kernel/exit.c
index 04029e35e69a..65809fac3038 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1439,9 +1439,48 @@ void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
 			   TASK_INTERRUPTIBLE, p);
 }
 
+static bool is_effectively_child(struct wait_opts *wo, bool ptrace,
+				 struct task_struct *target)
+{
+	struct task_struct *parent =
+		!ptrace ? target->real_parent : target->parent;
+
+	return current == parent || (!(wo->wo_flags & __WNOTHREAD) &&
+				     same_thread_group(current, parent));
+}
+
+/*
+ * Optimization for waiting on PIDTYPE_PID. No need to iterate through child
+ * and tracee lists to find the target task.
+ */
+static int do_wait_pid(struct wait_opts *wo)
+{
+	bool ptrace;
+	struct task_struct *target;
+	int retval;
+
+	ptrace = false;
+	target = pid_task(wo->wo_pid, PIDTYPE_TGID);
+	if (target && is_effectively_child(wo, ptrace, target)) {
+		retval = wait_consider_task(wo, ptrace, target);
+		if (retval)
+			return retval;
+	}
+
+	ptrace = true;
+	target = pid_task(wo->wo_pid, PIDTYPE_PID);
+	if (target && target->ptrace &&
+	    is_effectively_child(wo, ptrace, target)) {
+		retval = wait_consider_task(wo, ptrace, target);
+		if (retval)
+			return retval;
+	}
+
+	return 0;
+}
+
 static long do_wait(struct wait_opts *wo)
 {
-	struct task_struct *tsk;
 	int retval;
 
 	trace_sched_process_wait(wo->wo_pid);
@@ -1463,19 +1502,27 @@ repeat:
 
 	set_current_state(TASK_INTERRUPTIBLE);
 	read_lock(&tasklist_lock);
-	tsk = current;
-	do {
-		retval = do_wait_thread(wo, tsk);
-		if (retval)
-			goto end;
 
-		retval = ptrace_do_wait(wo, tsk);
+	if (wo->wo_type == PIDTYPE_PID) {
+		retval = do_wait_pid(wo);
 		if (retval)
 			goto end;
+	} else {
+		struct task_struct *tsk = current;
+
+		do {
+			retval = do_wait_thread(wo, tsk);
+			if (retval)
+				goto end;
 
-		if (wo->wo_flags & __WNOTHREAD)
-			break;
-	} while_each_thread(current, tsk);
+			retval = ptrace_do_wait(wo, tsk);
+			if (retval)
+				goto end;
+
+			if (wo->wo_flags & __WNOTHREAD)
+				break;
+		} while_each_thread(current, tsk);
+	}
 	read_unlock(&tasklist_lock);
 
 notask:
diff --git a/kernel/fork.c b/kernel/fork.c
index 291b61c21e99..b317ef3b9e9a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -380,14 +380,17 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 	void *stack = task_stack_page(tsk);
 	struct vm_struct *vm = task_stack_vm_area(tsk);
 
+	if (vm) {
+		int i;
 
-	/* All stack pages are in the same node. */
-	if (vm)
-		mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
-				      account * (THREAD_SIZE / 1024));
-	else
+		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
+			mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB,
+					      account * (PAGE_SIZE / 1024));
+	} else {
+		/* All stack pages are in the same node. */
 		mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB,
 				      account * (THREAD_SIZE / 1024));
+	}
 }
 
 static int memcg_charge_kernel_stack(struct task_struct *tsk)
@@ -1141,7 +1144,7 @@ void mmput_async(struct mm_struct *mm)
  * invocations: in mmput() nobody alive left, in execve task is single
  * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the
  * mm->exe_file, but does so without using set_mm_exe_file() in order
- * to do avoid the need for any locks.
+ * to avoid the need for any locks.
  */
 void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
 {
@@ -1392,7 +1395,6 @@ fail_nomem:
 static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct mm_struct *mm, *oldmm;
-	int retval;
 
 	tsk->min_flt = tsk->maj_flt = 0;
 	tsk->nvcsw = tsk->nivcsw = 0;
@@ -1419,21 +1421,15 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 	if (clone_flags & CLONE_VM) {
 		mmget(oldmm);
 		mm = oldmm;
-		goto good_mm;
+	} else {
+		mm = dup_mm(tsk, current->mm);
+		if (!mm)
+			return -ENOMEM;
 	}
 
-	retval = -ENOMEM;
-	mm = dup_mm(tsk, current->mm);
-	if (!mm)
-		goto fail_nomem;
-
-good_mm:
 	tsk->mm = mm;
 	tsk->active_mm = mm;
 	return 0;
-
-fail_nomem:
-	return retval;
 }
 
 static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
@@ -1739,7 +1735,7 @@ static int pidfd_release(struct inode *inode, struct file *file)
  * /proc/<pid>/status where Pid and NSpid are always shown relative to
  * the  pid namespace of the procfs instance. The difference becomes
  * obvious when sending around a pidfd between pid namespaces from a
- * different branch of the tree, i.e. where no ancestoral relation is
+ * different branch of the tree, i.e. where no ancestral relation is
  * present between the pid namespaces:
  * - create two new pid namespaces ns1 and ns2 in the initial pid
  *   namespace (also take care to create new mount namespaces in the
@@ -2730,8 +2726,8 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs)
 		return false;
 
 	/*
-	 * - make the CLONE_DETACHED bit reuseable for clone3
-	 * - make the CSIGNAL bits reuseable for clone3
+	 * - make the CLONE_DETACHED bit reusable for clone3
+	 * - make the CSIGNAL bits reusable for clone3
 	 */
 	if (kargs->flags & (CLONE_DETACHED | CSIGNAL))
 		return false;
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index f62de2dea8a3..58f87a3092f3 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -4,6 +4,7 @@ menu "GCOV-based kernel profiling"
 config GCOV_KERNEL
 	bool "Enable gcov-based kernel profiling"
 	depends on DEBUG_FS
+	depends on !CC_IS_CLANG || CLANG_VERSION >= 110000
 	select CONSTRUCTORS
 	default n
 	help
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index 0ffe9f194080..073a3738c5e6 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -49,6 +49,55 @@ void gcov_enable_events(void)
 	mutex_unlock(&gcov_lock);
 }
 
+/**
+ * store_gcov_u32 - store 32 bit number in gcov format to buffer
+ * @buffer: target buffer or NULL
+ * @off: offset into the buffer
+ * @v: value to be stored
+ *
+ * Number format defined by gcc: numbers are recorded in the 32 bit
+ * unsigned binary form of the endianness of the machine generating the
+ * file. Returns the number of bytes stored. If @buffer is %NULL, doesn't
+ * store anything.
+ */
+size_t store_gcov_u32(void *buffer, size_t off, u32 v)
+{
+	u32 *data;
+
+	if (buffer) {
+		data = buffer + off;
+		*data = v;
+	}
+
+	return sizeof(*data);
+}
+
+/**
+ * store_gcov_u64 - store 64 bit number in gcov format to buffer
+ * @buffer: target buffer or NULL
+ * @off: offset into the buffer
+ * @v: value to be stored
+ *
+ * Number format defined by gcc: numbers are recorded in the 32 bit
+ * unsigned binary form of the endianness of the machine generating the
+ * file. 64 bit numbers are stored as two 32 bit numbers, the low part
+ * first. Returns the number of bytes stored. If @buffer is %NULL, doesn't store
+ * anything.
+ */
+size_t store_gcov_u64(void *buffer, size_t off, u64 v)
+{
+	u32 *data;
+
+	if (buffer) {
+		data = buffer + off;
+
+		data[0] = (v & 0xffffffffUL);
+		data[1] = (v >> 32);
+	}
+
+	return sizeof(*data) * 2;
+}
+
 #ifdef CONFIG_MODULES
 /* Update list and generate events when modules are unloaded. */
 static int gcov_module_notifier(struct notifier_block *nb, unsigned long event,
diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c
index 8743150db2ac..d41f5ecda9db 100644
--- a/kernel/gcov/clang.c
+++ b/kernel/gcov/clang.c
@@ -48,9 +48,8 @@
 #include <linux/list.h>
 #include <linux/printk.h>
 #include <linux/ratelimit.h>
-#include <linux/seq_file.h>
 #include <linux/slab.h>
-#include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include "gcov.h"
 
 typedef void (*llvm_gcov_callback)(void);
@@ -75,9 +74,6 @@ struct gcov_fn_info {
 
 	u32 num_counters;
 	u64 *counters;
-#if CONFIG_CLANG_VERSION < 110000
-	const char *function_name;
-#endif
 };
 
 static struct gcov_info *current_info;
@@ -107,16 +103,6 @@ void llvm_gcov_init(llvm_gcov_callback writeout, llvm_gcov_callback flush)
 }
 EXPORT_SYMBOL(llvm_gcov_init);
 
-#if CONFIG_CLANG_VERSION < 110000
-void llvm_gcda_start_file(const char *orig_filename, const char version[4],
-		u32 checksum)
-{
-	current_info->filename = orig_filename;
-	memcpy(&current_info->version, version, sizeof(current_info->version));
-	current_info->checksum = checksum;
-}
-EXPORT_SYMBOL(llvm_gcda_start_file);
-#else
 void llvm_gcda_start_file(const char *orig_filename, u32 version, u32 checksum)
 {
 	current_info->filename = orig_filename;
@@ -124,29 +110,7 @@ void llvm_gcda_start_file(const char *orig_filename, u32 version, u32 checksum)
 	current_info->checksum = checksum;
 }
 EXPORT_SYMBOL(llvm_gcda_start_file);
-#endif
-
-#if CONFIG_CLANG_VERSION < 110000
-void llvm_gcda_emit_function(u32 ident, const char *function_name,
-		u32 func_checksum, u8 use_extra_checksum, u32 cfg_checksum)
-{
-	struct gcov_fn_info *info = kzalloc(sizeof(*info), GFP_KERNEL);
-
-	if (!info)
-		return;
-
-	INIT_LIST_HEAD(&info->head);
-	info->ident = ident;
-	info->checksum = func_checksum;
-	info->use_extra_checksum = use_extra_checksum;
-	info->cfg_checksum = cfg_checksum;
-	if (function_name)
-		info->function_name = kstrdup(function_name, GFP_KERNEL);
 
-	list_add_tail(&info->head, &current_info->functions);
-}
-EXPORT_SYMBOL(llvm_gcda_emit_function);
-#else
 void llvm_gcda_emit_function(u32 ident, u32 func_checksum,
 		u8 use_extra_checksum, u32 cfg_checksum)
 {
@@ -163,7 +127,6 @@ void llvm_gcda_emit_function(u32 ident, u32 func_checksum,
 	list_add_tail(&info->head, &current_info->functions);
 }
 EXPORT_SYMBOL(llvm_gcda_emit_function);
-#endif
 
 void llvm_gcda_emit_arcs(u32 num_counters, u64 *counters)
 {
@@ -326,56 +289,23 @@ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src)
 	}
 }
 
-#if CONFIG_CLANG_VERSION < 110000
 static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn)
 {
 	size_t cv_size; /* counter values size */
-	struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn),
-			GFP_KERNEL);
-	if (!fn_dup)
-		return NULL;
-	INIT_LIST_HEAD(&fn_dup->head);
+	struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn), GFP_KERNEL);
 
-	fn_dup->function_name = kstrdup(fn->function_name, GFP_KERNEL);
-	if (!fn_dup->function_name)
-		goto err_name;
-
-	cv_size = fn->num_counters * sizeof(fn->counters[0]);
-	fn_dup->counters = vmalloc(cv_size);
-	if (!fn_dup->counters)
-		goto err_counters;
-	memcpy(fn_dup->counters, fn->counters, cv_size);
-
-	return fn_dup;
-
-err_counters:
-	kfree(fn_dup->function_name);
-err_name:
-	kfree(fn_dup);
-	return NULL;
-}
-#else
-static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn)
-{
-	size_t cv_size; /* counter values size */
-	struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn),
-			GFP_KERNEL);
 	if (!fn_dup)
 		return NULL;
 	INIT_LIST_HEAD(&fn_dup->head);
-
 	cv_size = fn->num_counters * sizeof(fn->counters[0]);
-	fn_dup->counters = vmalloc(cv_size);
+	fn_dup->counters = kvmalloc(cv_size, GFP_KERNEL);
 	if (!fn_dup->counters) {
 		kfree(fn_dup);
 		return NULL;
 	}
-
 	memcpy(fn_dup->counters, fn->counters, cv_size);
-
 	return fn_dup;
 }
-#endif
 
 /**
  * gcov_info_dup - duplicate profiling data set
@@ -416,99 +346,18 @@ err:
  * gcov_info_free - release memory for profiling data set duplicate
  * @info: profiling data set duplicate to free
  */
-#if CONFIG_CLANG_VERSION < 110000
 void gcov_info_free(struct gcov_info *info)
 {
 	struct gcov_fn_info *fn, *tmp;
 
 	list_for_each_entry_safe(fn, tmp, &info->functions, head) {
-		kfree(fn->function_name);
-		vfree(fn->counters);
+		kvfree(fn->counters);
 		list_del(&fn->head);
 		kfree(fn);
 	}
 	kfree(info->filename);
 	kfree(info);
 }
-#else
-void gcov_info_free(struct gcov_info *info)
-{
-	struct gcov_fn_info *fn, *tmp;
-
-	list_for_each_entry_safe(fn, tmp, &info->functions, head) {
-		vfree(fn->counters);
-		list_del(&fn->head);
-		kfree(fn);
-	}
-	kfree(info->filename);
-	kfree(info);
-}
-#endif
-
-#define ITER_STRIDE	PAGE_SIZE
-
-/**
- * struct gcov_iterator - specifies current file position in logical records
- * @info: associated profiling data
- * @buffer: buffer containing file data
- * @size: size of buffer
- * @pos: current position in file
- */
-struct gcov_iterator {
-	struct gcov_info *info;
-	void *buffer;
-	size_t size;
-	loff_t pos;
-};
-
-/**
- * store_gcov_u32 - store 32 bit number in gcov format to buffer
- * @buffer: target buffer or NULL
- * @off: offset into the buffer
- * @v: value to be stored
- *
- * Number format defined by gcc: numbers are recorded in the 32 bit
- * unsigned binary form of the endianness of the machine generating the
- * file. Returns the number of bytes stored. If @buffer is %NULL, doesn't
- * store anything.
- */
-static size_t store_gcov_u32(void *buffer, size_t off, u32 v)
-{
-	u32 *data;
-
-	if (buffer) {
-		data = buffer + off;
-		*data = v;
-	}
-
-	return sizeof(*data);
-}
-
-/**
- * store_gcov_u64 - store 64 bit number in gcov format to buffer
- * @buffer: target buffer or NULL
- * @off: offset into the buffer
- * @v: value to be stored
- *
- * Number format defined by gcc: numbers are recorded in the 32 bit
- * unsigned binary form of the endianness of the machine generating the
- * file. 64 bit numbers are stored as two 32 bit numbers, the low part
- * first. Returns the number of bytes stored. If @buffer is %NULL, doesn't store
- * anything.
- */
-static size_t store_gcov_u64(void *buffer, size_t off, u64 v)
-{
-	u32 *data;
-
-	if (buffer) {
-		data = buffer + off;
-
-		data[0] = (v & 0xffffffffUL);
-		data[1] = (v >> 32);
-	}
-
-	return sizeof(*data) * 2;
-}
 
 /**
  * convert_to_gcda - convert profiling data set to gcda file format
@@ -517,7 +366,7 @@ static size_t store_gcov_u64(void *buffer, size_t off, u64 v)
  *
  * Returns the number of bytes that were/would have been stored into the buffer.
  */
-static size_t convert_to_gcda(char *buffer, struct gcov_info *info)
+size_t convert_to_gcda(char *buffer, struct gcov_info *info)
 {
 	struct gcov_fn_info *fi_ptr;
 	size_t pos = 0;
@@ -549,102 +398,3 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info)
 
 	return pos;
 }
-
-/**
- * gcov_iter_new - allocate and initialize profiling data iterator
- * @info: profiling data set to be iterated
- *
- * Return file iterator on success, %NULL otherwise.
- */
-struct gcov_iterator *gcov_iter_new(struct gcov_info *info)
-{
-	struct gcov_iterator *iter;
-
-	iter = kzalloc(sizeof(struct gcov_iterator), GFP_KERNEL);
-	if (!iter)
-		goto err_free;
-
-	iter->info = info;
-	/* Dry-run to get the actual buffer size. */
-	iter->size = convert_to_gcda(NULL, info);
-	iter->buffer = vmalloc(iter->size);
-	if (!iter->buffer)
-		goto err_free;
-
-	convert_to_gcda(iter->buffer, info);
-
-	return iter;
-
-err_free:
-	kfree(iter);
-	return NULL;
-}
-
-
-/**
- * gcov_iter_get_info - return profiling data set for given file iterator
- * @iter: file iterator
- */
-void gcov_iter_free(struct gcov_iterator *iter)
-{
-	vfree(iter->buffer);
-	kfree(iter);
-}
-
-/**
- * gcov_iter_get_info - return profiling data set for given file iterator
- * @iter: file iterator
- */
-struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter)
-{
-	return iter->info;
-}
-
-/**
- * gcov_iter_start - reset file iterator to starting position
- * @iter: file iterator
- */
-void gcov_iter_start(struct gcov_iterator *iter)
-{
-	iter->pos = 0;
-}
-
-/**
- * gcov_iter_next - advance file iterator to next logical record
- * @iter: file iterator
- *
- * Return zero if new position is valid, non-zero if iterator has reached end.
- */
-int gcov_iter_next(struct gcov_iterator *iter)
-{
-	if (iter->pos < iter->size)
-		iter->pos += ITER_STRIDE;
-
-	if (iter->pos >= iter->size)
-		return -EINVAL;
-
-	return 0;
-}
-
-/**
- * gcov_iter_write - write data for current pos to seq_file
- * @iter: file iterator
- * @seq: seq_file handle
- *
- * Return zero on success, non-zero otherwise.
- */
-int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq)
-{
-	size_t len;
-
-	if (iter->pos >= iter->size)
-		return -EINVAL;
-
-	len = ITER_STRIDE;
-	if (iter->pos + len > iter->size)
-		len = iter->size - iter->pos;
-
-	seq_write(seq, iter->buffer + iter->pos, len);
-
-	return 0;
-}
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index 82babf5aa077..5c3086cad8f9 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -26,6 +26,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/seq_file.h>
+#include <linux/mm.h>
 #include "gcov.h"
 
 /**
@@ -85,6 +86,115 @@ static int __init gcov_persist_setup(char *str)
 }
 __setup("gcov_persist=", gcov_persist_setup);
 
+#define ITER_STRIDE	PAGE_SIZE
+
+/**
+ * struct gcov_iterator - specifies current file position in logical records
+ * @info: associated profiling data
+ * @buffer: buffer containing file data
+ * @size: size of buffer
+ * @pos: current position in file
+ */
+struct gcov_iterator {
+	struct gcov_info *info;
+	size_t size;
+	loff_t pos;
+	char buffer[];
+};
+
+/**
+ * gcov_iter_new - allocate and initialize profiling data iterator
+ * @info: profiling data set to be iterated
+ *
+ * Return file iterator on success, %NULL otherwise.
+ */
+static struct gcov_iterator *gcov_iter_new(struct gcov_info *info)
+{
+	struct gcov_iterator *iter;
+	size_t size;
+
+	/* Dry-run to get the actual buffer size. */
+	size = convert_to_gcda(NULL, info);
+
+	iter = kvmalloc(struct_size(iter, buffer, size), GFP_KERNEL);
+	if (!iter)
+		return NULL;
+
+	iter->info = info;
+	iter->size = size;
+	convert_to_gcda(iter->buffer, info);
+
+	return iter;
+}
+
+
+/**
+ * gcov_iter_free - free iterator data
+ * @iter: file iterator
+ */
+static void gcov_iter_free(struct gcov_iterator *iter)
+{
+	kvfree(iter);
+}
+
+/**
+ * gcov_iter_get_info - return profiling data set for given file iterator
+ * @iter: file iterator
+ */
+static struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter)
+{
+	return iter->info;
+}
+
+/**
+ * gcov_iter_start - reset file iterator to starting position
+ * @iter: file iterator
+ */
+static void gcov_iter_start(struct gcov_iterator *iter)
+{
+	iter->pos = 0;
+}
+
+/**
+ * gcov_iter_next - advance file iterator to next logical record
+ * @iter: file iterator
+ *
+ * Return zero if new position is valid, non-zero if iterator has reached end.
+ */
+static int gcov_iter_next(struct gcov_iterator *iter)
+{
+	if (iter->pos < iter->size)
+		iter->pos += ITER_STRIDE;
+
+	if (iter->pos >= iter->size)
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * gcov_iter_write - write data for current pos to seq_file
+ * @iter: file iterator
+ * @seq: seq_file handle
+ *
+ * Return zero on success, non-zero otherwise.
+ */
+static int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq)
+{
+	size_t len;
+
+	if (iter->pos >= iter->size)
+		return -EINVAL;
+
+	len = ITER_STRIDE;
+	if (iter->pos + len > iter->size)
+		len = iter->size - iter->pos;
+
+	seq_write(seq, iter->buffer + iter->pos, len);
+
+	return 0;
+}
+
 /*
  * seq_file.start() implementation for gcov data files. Note that the
  * gcov_iterator interface is designed to be more restrictive than seq_file
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index c53408a00d0b..460c12b7dfea 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -15,8 +15,7 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/seq_file.h>
-#include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include "gcov.h"
 
 #if (__GNUC__ >= 10)
@@ -310,7 +309,7 @@ struct gcov_info *gcov_info_dup(struct gcov_info *info)
 
 			cv_size = sizeof(gcov_type) * sci_ptr->num;
 
-			dci_ptr->values = vmalloc(cv_size);
+			dci_ptr->values = kvmalloc(cv_size, GFP_KERNEL);
 
 			if (!dci_ptr->values)
 				goto err_free;
@@ -352,7 +351,7 @@ void gcov_info_free(struct gcov_info *info)
 		ci_ptr = info->functions[fi_idx]->ctrs;
 
 		for (ct_idx = 0; ct_idx < active; ct_idx++, ci_ptr++)
-			vfree(ci_ptr->values);
+			kvfree(ci_ptr->values);
 
 		kfree(info->functions[fi_idx]);
 	}
@@ -363,71 +362,6 @@ free_info:
 	kfree(info);
 }
 
-#define ITER_STRIDE	PAGE_SIZE
-
-/**
- * struct gcov_iterator - specifies current file position in logical records
- * @info: associated profiling data
- * @buffer: buffer containing file data
- * @size: size of buffer
- * @pos: current position in file
- */
-struct gcov_iterator {
-	struct gcov_info *info;
-	void *buffer;
-	size_t size;
-	loff_t pos;
-};
-
-/**
- * store_gcov_u32 - store 32 bit number in gcov format to buffer
- * @buffer: target buffer or NULL
- * @off: offset into the buffer
- * @v: value to be stored
- *
- * Number format defined by gcc: numbers are recorded in the 32 bit
- * unsigned binary form of the endianness of the machine generating the
- * file. Returns the number of bytes stored. If @buffer is %NULL, doesn't
- * store anything.
- */
-static size_t store_gcov_u32(void *buffer, size_t off, u32 v)
-{
-	u32 *data;
-
-	if (buffer) {
-		data = buffer + off;
-		*data = v;
-	}
-
-	return sizeof(*data);
-}
-
-/**
- * store_gcov_u64 - store 64 bit number in gcov format to buffer
- * @buffer: target buffer or NULL
- * @off: offset into the buffer
- * @v: value to be stored
- *
- * Number format defined by gcc: numbers are recorded in the 32 bit
- * unsigned binary form of the endianness of the machine generating the
- * file. 64 bit numbers are stored as two 32 bit numbers, the low part
- * first. Returns the number of bytes stored. If @buffer is %NULL, doesn't store
- * anything.
- */
-static size_t store_gcov_u64(void *buffer, size_t off, u64 v)
-{
-	u32 *data;
-
-	if (buffer) {
-		data = buffer + off;
-
-		data[0] = (v & 0xffffffffUL);
-		data[1] = (v >> 32);
-	}
-
-	return sizeof(*data) * 2;
-}
-
 /**
  * convert_to_gcda - convert profiling data set to gcda file format
  * @buffer: the buffer to store file data or %NULL if no data should be stored
@@ -435,7 +369,7 @@ static size_t store_gcov_u64(void *buffer, size_t off, u64 v)
  *
  * Returns the number of bytes that were/would have been stored into the buffer.
  */
-static size_t convert_to_gcda(char *buffer, struct gcov_info *info)
+size_t convert_to_gcda(char *buffer, struct gcov_info *info)
 {
 	struct gcov_fn_info *fi_ptr;
 	struct gcov_ctr_info *ci_ptr;
@@ -481,102 +415,3 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info)
 
 	return pos;
 }
-
-/**
- * gcov_iter_new - allocate and initialize profiling data iterator
- * @info: profiling data set to be iterated
- *
- * Return file iterator on success, %NULL otherwise.
- */
-struct gcov_iterator *gcov_iter_new(struct gcov_info *info)
-{
-	struct gcov_iterator *iter;
-
-	iter = kzalloc(sizeof(struct gcov_iterator), GFP_KERNEL);
-	if (!iter)
-		goto err_free;
-
-	iter->info = info;
-	/* Dry-run to get the actual buffer size. */
-	iter->size = convert_to_gcda(NULL, info);
-	iter->buffer = vmalloc(iter->size);
-	if (!iter->buffer)
-		goto err_free;
-
-	convert_to_gcda(iter->buffer, info);
-
-	return iter;
-
-err_free:
-	kfree(iter);
-	return NULL;
-}
-
-
-/**
- * gcov_iter_get_info - return profiling data set for given file iterator
- * @iter: file iterator
- */
-void gcov_iter_free(struct gcov_iterator *iter)
-{
-	vfree(iter->buffer);
-	kfree(iter);
-}
-
-/**
- * gcov_iter_get_info - return profiling data set for given file iterator
- * @iter: file iterator
- */
-struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter)
-{
-	return iter->info;
-}
-
-/**
- * gcov_iter_start - reset file iterator to starting position
- * @iter: file iterator
- */
-void gcov_iter_start(struct gcov_iterator *iter)
-{
-	iter->pos = 0;
-}
-
-/**
- * gcov_iter_next - advance file iterator to next logical record
- * @iter: file iterator
- *
- * Return zero if new position is valid, non-zero if iterator has reached end.
- */
-int gcov_iter_next(struct gcov_iterator *iter)
-{
-	if (iter->pos < iter->size)
-		iter->pos += ITER_STRIDE;
-
-	if (iter->pos >= iter->size)
-		return -EINVAL;
-
-	return 0;
-}
-
-/**
- * gcov_iter_write - write data for current pos to seq_file
- * @iter: file iterator
- * @seq: seq_file handle
- *
- * Return zero on success, non-zero otherwise.
- */
-int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq)
-{
-	size_t len;
-
-	if (iter->pos >= iter->size)
-		return -EINVAL;
-
-	len = ITER_STRIDE;
-	if (iter->pos + len > iter->size)
-		len = iter->size - iter->pos;
-
-	seq_write(seq, iter->buffer + iter->pos, len);
-
-	return 0;
-}
diff --git a/kernel/gcov/gcov.h b/kernel/gcov/gcov.h
index 6ab2c1808c9d..912b8ea01d33 100644
--- a/kernel/gcov/gcov.h
+++ b/kernel/gcov/gcov.h
@@ -48,6 +48,7 @@ struct gcov_info *gcov_info_next(struct gcov_info *info);
 void gcov_info_link(struct gcov_info *info);
 void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info);
 bool gcov_info_within_module(struct gcov_info *info, struct module *mod);
+size_t convert_to_gcda(char *buffer, struct gcov_info *info);
 
 /* Base interface. */
 enum gcov_action {
@@ -58,16 +59,9 @@ enum gcov_action {
 void gcov_event(enum gcov_action action, struct gcov_info *info);
 void gcov_enable_events(void);
 
-/* Iterator control. */
-struct seq_file;
-struct gcov_iterator;
-
-struct gcov_iterator *gcov_iter_new(struct gcov_info *info);
-void gcov_iter_free(struct gcov_iterator *iter);
-void gcov_iter_start(struct gcov_iterator *iter);
-int gcov_iter_next(struct gcov_iterator *iter);
-int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq);
-struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter);
+/* writing helpers */
+size_t store_gcov_u32(void *buffer, size_t off, u32 v);
+size_t store_gcov_u64(void *buffer, size_t off, u64 v);
 
 /* gcov_info control. */
 void gcov_info_reset(struct gcov_info *info);
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 396ebaebea3f..bb2e3e15c84c 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -144,6 +144,47 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 	touch_nmi_watchdog();
 }
 
+static void check_killed_task(struct task_struct *t, unsigned long timeout)
+{
+	unsigned long stamp = t->killed_time;
+
+	/*
+	 * Ensure the task is not frozen.
+	 * Also, skip vfork and any other user process that freezer should skip.
+	 */
+	if (unlikely(t->flags & (PF_FROZEN | PF_FREEZER_SKIP)))
+		return;
+	/*
+	 * Skip threads which are already inside do_exit(), for exit_mm() etc.
+	 * might take many seconds.
+	 */
+	if (t->flags & PF_EXITING)
+		return;
+	if (!stamp) {
+		stamp = jiffies;
+		if (!stamp)
+			stamp++;
+		t->killed_time = stamp;
+		return;
+	}
+	if (time_is_after_jiffies(stamp + timeout * HZ))
+		return;
+	trace_sched_process_hang(t);
+	if (sysctl_hung_task_panic) {
+		console_verbose();
+		hung_task_call_panic = true;
+	}
+	/*
+	 * This thread failed to terminate for more than
+	 * sysctl_hung_task_timeout_secs seconds, complain:
+	 */
+	pr_err("INFO: task %s:%d can't die for more than %ld seconds.\n",
+	       t->comm, t->pid, (jiffies - stamp) / HZ);
+	sched_show_task(t);
+	hung_task_show_lock = true;
+	touch_nmi_watchdog();
+}
+
 /*
  * To avoid extending the RCU grace period for an unbounded amount of time,
  * periodically exit the critical section and enter a new one.
@@ -195,6 +236,9 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 				goto unlock;
 			last_break = jiffies;
 		}
+		/* Check threads which are about to terminate. */
+		if (unlikely(fatal_signal_pending(t)))
+			check_killed_task(t, timeout);
 		/* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
 		if (t->state == TASK_UNINTERRUPTIBLE)
 			check_hung_task(t, timeout);
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index a0b6780740c8..f099baee3578 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -37,6 +37,7 @@
 #include <linux/compiler.h>
 #include <linux/hugetlb.h>
 #include <linux/objtool.h>
+#include <linux/kmsg_dump.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -1165,7 +1166,7 @@ int kernel_kexec(void)
 #endif
 	{
 		kexec_in_progress = true;
-		kernel_restart_prepare(NULL);
+		kernel_restart_prepare("kexec reboot");
 		migrate_to_reboot_cpu();
 
 		/*
@@ -1179,6 +1180,7 @@ int kernel_kexec(void)
 		machine_shutdown();
 	}
 
+	kmsg_dump(KMSG_DUMP_SHUTDOWN);
 	machine_kexec(kexec_image);
 
 #ifdef CONFIG_KEXEC_JUMP
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 5c3447cf7ad5..33400ff051a8 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -740,8 +740,10 @@ static int kexec_calculate_store_digests(struct kimage *image)
 
 	sha_region_sz = KEXEC_SEGMENT_MAX * sizeof(struct kexec_sha_region);
 	sha_regions = vzalloc(sha_region_sz);
-	if (!sha_regions)
+	if (!sha_regions) {
+		ret = -ENOMEM;
 		goto out_free_desc;
+	}
 
 	desc->tfm   = tfm;
 
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 3cd075ce2a1e..b717134ebe17 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -58,7 +58,7 @@ static DECLARE_WAIT_QUEUE_HEAD(kmod_wq);
 /*
 	modprobe_path is set via /proc/sys.
 */
-char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";
+char modprobe_path[KMOD_PATH_LEN] = CONFIG_MODPROBE_PATH;
 
 static void free_modprobe_argv(struct subprocess_info *info)
 {
diff --git a/kernel/resource.c b/kernel/resource.c
index 627e61b0c124..7e00239a023a 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -64,12 +64,8 @@ static DEFINE_RWLOCK(resource_lock);
 static struct resource *bootmem_resource_free;
 static DEFINE_SPINLOCK(bootmem_resource_lock);
 
-static struct resource *next_resource(struct resource *p, bool sibling_only)
+static struct resource *next_resource(struct resource *p)
 {
-	/* Caller wants to traverse through siblings only */
-	if (sibling_only)
-		return p->sibling;
-
 	if (p->child)
 		return p->child;
 	while (!p->sibling && p->parent)
@@ -81,7 +77,7 @@ static void *r_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct resource *p = v;
 	(*pos)++;
-	return (void *)next_resource(p, false);
+	return (void *)next_resource(p);
 }
 
 #ifdef CONFIG_PROC_FS
@@ -330,14 +326,10 @@ EXPORT_SYMBOL(release_resource);
  * of the resource that's within [@start..@end]; if none is found, returns
  * -ENODEV.  Returns -EINVAL for invalid parameters.
  *
- * This function walks the whole tree and not just first level children
- * unless @first_lvl is true.
- *
  * @start:	start address of the resource searched for
  * @end:	end address of same resource
  * @flags:	flags which the resource must have
  * @desc:	descriptor the resource must have
- * @first_lvl:	walk only the first level children, if set
  * @res:	return ptr, if resource found
  *
  * The caller must specify @start, @end, @flags, and @desc
@@ -345,9 +337,8 @@ EXPORT_SYMBOL(release_resource);
  */
 static int find_next_iomem_res(resource_size_t start, resource_size_t end,
 			       unsigned long flags, unsigned long desc,
-			       bool first_lvl, struct resource *res)
+			       struct resource *res)
 {
-	bool siblings_only = true;
 	struct resource *p;
 
 	if (!res)
@@ -358,7 +349,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
 
 	read_lock(&resource_lock);
 
-	for (p = iomem_resource.child; p; p = next_resource(p, siblings_only)) {
+	for (p = iomem_resource.child; p; p = next_resource(p)) {
 		/* If we passed the resource we are looking for, stop */
 		if (p->start > end) {
 			p = NULL;
@@ -369,13 +360,6 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
 		if (p->end < start)
 			continue;
 
-		/*
-		 * Now that we found a range that matches what we look for,
-		 * check the flags and the descriptor. If we were not asked to
-		 * use only the first level, start looking at children as well.
-		 */
-		siblings_only = first_lvl;
-
 		if ((p->flags & flags) != flags)
 			continue;
 		if ((desc != IORES_DESC_NONE) && (desc != p->desc))
@@ -402,14 +386,14 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
 
 static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
 				 unsigned long flags, unsigned long desc,
-				 bool first_lvl, void *arg,
+				 void *arg,
 				 int (*func)(struct resource *, void *))
 {
 	struct resource res;
 	int ret = -EINVAL;
 
 	while (start < end &&
-	       !find_next_iomem_res(start, end, flags, desc, first_lvl, &res)) {
+	       !find_next_iomem_res(start, end, flags, desc, &res)) {
 		ret = (*func)(&res, arg);
 		if (ret)
 			break;
@@ -431,7 +415,6 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
  * @arg: function argument for the callback @func
  * @func: callback function that is called for each qualifying resource area
  *
- * This walks through whole tree and not just first level children.
  * All the memory ranges which overlap start,end and also match flags and
  * desc are valid candidates.
  *
@@ -441,7 +424,7 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
 int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
 		u64 end, void *arg, int (*func)(struct resource *, void *))
 {
-	return __walk_iomem_res_desc(start, end, flags, desc, false, arg, func);
+	return __walk_iomem_res_desc(start, end, flags, desc, arg, func);
 }
 EXPORT_SYMBOL_GPL(walk_iomem_res_desc);
 
@@ -457,8 +440,8 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
 {
 	unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
-	return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true,
-				     arg, func);
+	return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, arg,
+				     func);
 }
 
 /*
@@ -470,17 +453,14 @@ int walk_mem_res(u64 start, u64 end, void *arg,
 {
 	unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 
-	return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true,
-				     arg, func);
+	return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, arg,
+				     func);
 }
 
 /*
  * This function calls the @func callback against all memory ranges of type
  * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY.
  * It is to be used only for System RAM.
- *
- * This will find System RAM ranges that are children of top-level resources
- * in addition to top-level System RAM resources.
  */
 int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 			  void *arg, int (*func)(unsigned long, unsigned long, void *))
@@ -495,8 +475,7 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 	end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
 	flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 	while (start < end &&
-	       !find_next_iomem_res(start, end, flags, IORES_DESC_NONE,
-				    false, &res)) {
+	       !find_next_iomem_res(start, end, flags, IORES_DESC_NONE, &res)) {
 		pfn = PFN_UP(res.start);
 		end_pfn = PFN_DOWN(res.end + 1);
 		if (end_pfn > pfn)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7a299e90f94b..3601786ddaeb 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2924,7 +2924,7 @@ static struct ctl_table vm_table[] = {
 #ifdef CONFIG_COMPACTION
 	{
 		.procname	= "compact_memory",
-		.data		= &sysctl_compact_memory,
+		.data		= NULL,
 		.maxlen		= sizeof(int),
 		.mode		= 0200,
 		.proc_handler	= sysctl_compaction_handler,
@@ -3346,7 +3346,7 @@ static struct ctl_table fs_table[] = {
 		.procname	= "protected_symlinks",
 		.data		= &sysctl_protected_symlinks,
 		.maxlen		= sizeof(int),
-		.mode		= 0600,
+		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_ONE,
@@ -3355,7 +3355,7 @@ static struct ctl_table fs_table[] = {
 		.procname	= "protected_hardlinks",
 		.data		= &sysctl_protected_hardlinks,
 		.maxlen		= sizeof(int),
-		.mode		= 0600,
+		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_ONE,
@@ -3364,7 +3364,7 @@ static struct ctl_table fs_table[] = {
 		.procname	= "protected_fifos",
 		.data		= &sysctl_protected_fifos,
 		.maxlen		= sizeof(int),
-		.mode		= 0600,
+		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &two,
@@ -3373,7 +3373,7 @@ static struct ctl_table fs_table[] = {
 		.procname	= "protected_regular",
 		.data		= &sysctl_protected_regular,
 		.maxlen		= sizeof(int),
-		.mode		= 0600,
+		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &two,
diff --git a/kernel/task_work.c b/kernel/task_work.c
index e9316198c64b..1698fbe6f0e1 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -34,6 +34,9 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 {
 	struct callback_head *head;
 
+	/* record the work call stack in order to print it in KASAN reports */
+	kasan_record_aux_stack(work);
+
 	do {
 		head = READ_ONCE(task->task_works);
 		if (unlikely(head == &work_exited))
diff --git a/kernel/umh.c b/kernel/umh.c
index 3f646613a9d3..61f6b82c354b 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -27,6 +27,7 @@
 #include <linux/ptrace.h>
 #include <linux/async.h>
 #include <linux/uaccess.h>
+#include <linux/initrd.h>
 
 #include <trace/events/module.h>
 
@@ -107,6 +108,7 @@ static int call_usermodehelper_exec_async(void *data)
 
 	commit_creds(new);
 
+	wait_for_initramfs();
 	retval = kernel_execve(sub_info->path,
 			       (const char *const *)sub_info->argv,
 			       (const char *const *)sub_info->envp);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 107bc38b1945..7c397907d0e9 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -154,7 +154,11 @@ static void lockup_detector_update_enable(void)
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 
-#define SOFTLOCKUP_RESET	ULONG_MAX
+/*
+ * Delay the soflockup report when running a known slow code.
+ * It does _not_ affect the timestamp of the last successdul reschedule.
+ */
+#define SOFTLOCKUP_DELAY_REPORT	ULONG_MAX
 
 #ifdef CONFIG_SMP
 int __read_mostly sysctl_softlockup_all_cpu_backtrace;
@@ -169,10 +173,12 @@ unsigned int __read_mostly softlockup_panic =
 static bool softlockup_initialized __read_mostly;
 static u64 __read_mostly sample_period;
 
+/* Timestamp taken after the last successful reschedule. */
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
+/* Timestamp of the last softlockup report. */
+static DEFINE_PER_CPU(unsigned long, watchdog_report_ts);
 static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
 static DEFINE_PER_CPU(bool, softlockup_touch_sync);
-static DEFINE_PER_CPU(bool, soft_watchdog_warn);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static unsigned long soft_lockup_nmi_warn;
@@ -235,10 +241,16 @@ static void set_sample_period(void)
 	watchdog_update_hrtimer_threshold(sample_period);
 }
 
+static void update_report_ts(void)
+{
+	__this_cpu_write(watchdog_report_ts, get_timestamp());
+}
+
 /* Commands for resetting the watchdog */
-static void __touch_watchdog(void)
+static void update_touch_ts(void)
 {
 	__this_cpu_write(watchdog_touch_ts, get_timestamp());
+	update_report_ts();
 }
 
 /**
@@ -252,10 +264,10 @@ static void __touch_watchdog(void)
 notrace void touch_softlockup_watchdog_sched(void)
 {
 	/*
-	 * Preemption can be enabled.  It doesn't matter which CPU's timestamp
-	 * gets zeroed here, so use the raw_ operation.
+	 * Preemption can be enabled.  It doesn't matter which CPU's watchdog
+	 * report period gets restarted here, so use the raw_ operation.
 	 */
-	raw_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET);
+	raw_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT);
 }
 
 notrace void touch_softlockup_watchdog(void)
@@ -279,7 +291,7 @@ void touch_all_softlockup_watchdogs(void)
 	 * the softlockup check.
 	 */
 	for_each_cpu(cpu, &watchdog_allowed_mask) {
-		per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET;
+		per_cpu(watchdog_report_ts, cpu) = SOFTLOCKUP_DELAY_REPORT;
 		wq_watchdog_touch(cpu);
 	}
 }
@@ -287,16 +299,16 @@ void touch_all_softlockup_watchdogs(void)
 void touch_softlockup_watchdog_sync(void)
 {
 	__this_cpu_write(softlockup_touch_sync, true);
-	__this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET);
+	__this_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT);
 }
 
-static int is_softlockup(unsigned long touch_ts)
+static int is_softlockup(unsigned long touch_ts, unsigned long period_ts)
 {
 	unsigned long now = get_timestamp();
 
 	if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){
 		/* Warn about unreasonable delays. */
-		if (time_after(now, touch_ts + get_softlockup_thresh()))
+		if (time_after(now, period_ts + get_softlockup_thresh()))
 			return now - touch_ts;
 	}
 	return 0;
@@ -332,7 +344,7 @@ static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
  */
 static int softlockup_fn(void *data)
 {
-	__touch_watchdog();
+	update_touch_ts();
 	complete(this_cpu_ptr(&softlockup_completion));
 
 	return 0;
@@ -342,6 +354,7 @@ static int softlockup_fn(void *data)
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
 	unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts);
+	unsigned long period_ts = __this_cpu_read(watchdog_report_ts);
 	struct pt_regs *regs = get_irq_regs();
 	int duration;
 	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
@@ -363,7 +376,15 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	/* .. and repeat */
 	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
 
-	if (touch_ts == SOFTLOCKUP_RESET) {
+	/*
+	 * If a virtual machine is stopped by the host it can look to
+	 * the watchdog like a soft lockup. Check to see if the host
+	 * stopped the vm before we process the timestamps.
+	 */
+	kvm_check_and_clear_guest_paused();
+
+	/* Reset the interval when touched by known problematic code. */
+	if (period_ts == SOFTLOCKUP_DELAY_REPORT) {
 		if (unlikely(__this_cpu_read(softlockup_touch_sync))) {
 			/*
 			 * If the time stamp was touched atomically
@@ -373,9 +394,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 			sched_clock_tick();
 		}
 
-		/* Clear the guest paused flag on watchdog reset */
-		kvm_check_and_clear_guest_paused();
-		__touch_watchdog();
+		update_report_ts();
 		return HRTIMER_RESTART;
 	}
 
@@ -385,31 +404,20 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	 * indicate it is getting cpu time.  If it hasn't then
 	 * this is a good indication some task is hogging the cpu
 	 */
-	duration = is_softlockup(touch_ts);
+	duration = is_softlockup(touch_ts, period_ts);
 	if (unlikely(duration)) {
 		/*
-		 * If a virtual machine is stopped by the host it can look to
-		 * the watchdog like a soft lockup, check to see if the host
-		 * stopped the vm before we issue the warning
+		 * Prevent multiple soft-lockup reports if one cpu is already
+		 * engaged in dumping all cpu back traces.
 		 */
-		if (kvm_check_and_clear_guest_paused())
-			return HRTIMER_RESTART;
-
-		/* only warn once */
-		if (__this_cpu_read(soft_watchdog_warn) == true)
-			return HRTIMER_RESTART;
-
 		if (softlockup_all_cpu_backtrace) {
-			/* Prevent multiple soft-lockup reports if one cpu is already
-			 * engaged in dumping cpu back traces
-			 */
-			if (test_and_set_bit(0, &soft_lockup_nmi_warn)) {
-				/* Someone else will report us. Let's give up */
-				__this_cpu_write(soft_watchdog_warn, true);
+			if (test_and_set_bit_lock(0, &soft_lockup_nmi_warn))
 				return HRTIMER_RESTART;
-			}
 		}
 
+		/* Start period for the next softlockup warning. */
+		update_report_ts();
+
 		pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
@@ -421,22 +429,14 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 			dump_stack();
 
 		if (softlockup_all_cpu_backtrace) {
-			/* Avoid generating two back traces for current
-			 * given that one is already made above
-			 */
 			trigger_allbutself_cpu_backtrace();
-
-			clear_bit(0, &soft_lockup_nmi_warn);
-			/* Barrier to sync with other cpus */
-			smp_mb__after_atomic();
+			clear_bit_unlock(0, &soft_lockup_nmi_warn);
 		}
 
 		add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
 		if (softlockup_panic)
 			panic("softlockup: hung tasks");
-		__this_cpu_write(soft_watchdog_warn, true);
-	} else
-		__this_cpu_write(soft_watchdog_warn, false);
+	}
 
 	return HRTIMER_RESTART;
 }
@@ -461,7 +461,7 @@ static void watchdog_enable(unsigned int cpu)
 		      HRTIMER_MODE_REL_PINNED_HARD);
 
 	/* Initialize timestamp */
-	__touch_watchdog();
+	update_touch_ts();
 	/* Enable the perf event */
 	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
 		watchdog_nmi_enable(cpu);