Merge tag 'v3.13-rc4' into core/locking

Merge Linux 3.13-rc4, to refresh this rather old tree with the latest fixes.

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

36 files changed, 602 insertions, 346 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 09a9c94f42bd..bbaf7d59c1bb 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -41,8 +41,9 @@ ifneq ($(CONFIG_SMP),y)
 obj-y += up.o
 endif
 obj-$(CONFIG_UID16) += uid16.o
+obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o
 obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o modsign_certificate.o
+obj-$(CONFIG_MODULE_SIG) += module_signing.o
 obj-$(CONFIG_KALLSYMS) += kallsyms.o
 obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
 obj-$(CONFIG_KEXEC) += kexec.o
@@ -122,19 +123,52 @@ targets += timeconst.h
 $(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE
 	$(call if_changed,bc)
 
-ifeq ($(CONFIG_MODULE_SIG),y)
+###############################################################################
+#
+# Roll all the X.509 certificates that we can find together and pull them into
+# the kernel so that they get loaded into the system trusted keyring during
+# boot.
 #
-# Pull the signing certificate and any extra certificates into the kernel
+# We look in the source root and the build root for all files whose name ends
+# in ".x509".  Unfortunately, this will generate duplicate filenames, so we
+# have make canonicalise the pathnames and then sort them to discard the
+# duplicates.
 #
+###############################################################################
+ifeq ($(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), \
+				$(or $(realpath $(CERT)),$(CERT))))
+
+ifeq ($(X509_CERTIFICATES),)
+$(warning *** No X.509 certificates found ***)
+endif
+
+ifneq ($(wildcard $(obj)/.x509.list),)
+ifneq ($(shell cat $(obj)/.x509.list),$(X509_CERTIFICATES))
+$(info X.509 certificate list changed)
+$(shell rm $(obj)/.x509.list)
+endif
+endif
+
+kernel/system_certificates.o: $(obj)/x509_certificate_list
 
-quiet_cmd_touch = TOUCH   $@
-      cmd_touch = touch   $@
+quiet_cmd_x509certs  = CERTS   $@
+      cmd_x509certs  = cat $(X509_CERTIFICATES) /dev/null >$@ $(foreach X509,$(X509_CERTIFICATES),; echo "  - Including cert $(X509)")
 
-extra_certificates:
-	$(call cmd,touch)
+targets += $(obj)/x509_certificate_list
+$(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list
+	$(call if_changed,x509certs)
 
-kernel/modsign_certificate.o: signing_key.x509 extra_certificates
+targets += $(obj)/.x509.list
+$(obj)/.x509.list:
+	@echo $(X509_CERTIFICATES) >$@
 
+clean-files := x509_certificate_list .x509.list
+endif
+
+ifeq ($(CONFIG_MODULE_SIG),y)
 ###############################################################################
 #
 # If module signing is requested, say by allyesconfig, but a key has not been
diff --git a/kernel/audit.c b/kernel/audit.c
index 7b0e23a740ce..906ae5a0233a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -60,7 +60,6 @@
 #ifdef CONFIG_SECURITY
 #include <linux/security.h>
 #endif
-#include <net/netlink.h>
 #include <linux/freezer.h>
 #include <linux/tty.h>
 #include <linux/pid_namespace.h>
@@ -140,6 +139,17 @@ static struct task_struct *kauditd_task;
 static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait);
 static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait);
 
+static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION,
+				   .mask = -1,
+				   .features = 0,
+				   .lock = 0,};
+
+static char *audit_feature_names[2] = {
+	"only_unset_loginuid",
+	"loginuid_immutable",
+};
+
+
 /* Serialize requests from userspace. */
 DEFINE_MUTEX(audit_cmd_mutex);
 
@@ -584,6 +594,8 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
 		return -EOPNOTSUPP;
 	case AUDIT_GET:
 	case AUDIT_SET:
+	case AUDIT_GET_FEATURE:
+	case AUDIT_SET_FEATURE:
 	case AUDIT_LIST_RULES:
 	case AUDIT_ADD_RULE:
 	case AUDIT_DEL_RULE:
@@ -613,7 +625,7 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type)
 	int rc = 0;
 	uid_t uid = from_kuid(&init_user_ns, current_uid());
 
-	if (!audit_enabled) {
+	if (!audit_enabled && msg_type != AUDIT_USER_AVC) {
 		*ab = NULL;
 		return rc;
 	}
@@ -628,6 +640,94 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type)
 	return rc;
 }
 
+int is_audit_feature_set(int i)
+{
+	return af.features & AUDIT_FEATURE_TO_MASK(i);
+}
+
+
+static int audit_get_feature(struct sk_buff *skb)
+{
+	u32 seq;
+
+	seq = nlmsg_hdr(skb)->nlmsg_seq;
+
+	audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
+			 &af, sizeof(af));
+
+	return 0;
+}
+
+static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature,
+				     u32 old_lock, u32 new_lock, int res)
+{
+	struct audit_buffer *ab;
+
+	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE);
+	audit_log_format(ab, "feature=%s new=%d old=%d old_lock=%d new_lock=%d res=%d",
+			 audit_feature_names[which], !!old_feature, !!new_feature,
+			 !!old_lock, !!new_lock, res);
+	audit_log_end(ab);
+}
+
+static int audit_set_feature(struct sk_buff *skb)
+{
+	struct audit_features *uaf;
+	int i;
+
+	BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > sizeof(audit_feature_names)/sizeof(audit_feature_names[0]));
+	uaf = nlmsg_data(nlmsg_hdr(skb));
+
+	/* if there is ever a version 2 we should handle that here */
+
+	for (i = 0; i <= AUDIT_LAST_FEATURE; i++) {
+		u32 feature = AUDIT_FEATURE_TO_MASK(i);
+		u32 old_feature, new_feature, old_lock, new_lock;
+
+		/* if we are not changing this feature, move along */
+		if (!(feature & uaf->mask))
+			continue;
+
+		old_feature = af.features & feature;
+		new_feature = uaf->features & feature;
+		new_lock = (uaf->lock | af.lock) & feature;
+		old_lock = af.lock & feature;
+
+		/* are we changing a locked feature? */
+		if ((af.lock & feature) && (new_feature != old_feature)) {
+			audit_log_feature_change(i, old_feature, new_feature,
+						 old_lock, new_lock, 0);
+			return -EPERM;
+		}
+	}
+	/* nothing invalid, do the changes */
+	for (i = 0; i <= AUDIT_LAST_FEATURE; i++) {
+		u32 feature = AUDIT_FEATURE_TO_MASK(i);
+		u32 old_feature, new_feature, old_lock, new_lock;
+
+		/* if we are not changing this feature, move along */
+		if (!(feature & uaf->mask))
+			continue;
+
+		old_feature = af.features & feature;
+		new_feature = uaf->features & feature;
+		old_lock = af.lock & feature;
+		new_lock = (uaf->lock | af.lock) & feature;
+
+		if (new_feature != old_feature)
+			audit_log_feature_change(i, old_feature, new_feature,
+						 old_lock, new_lock, 1);
+
+		if (new_feature)
+			af.features |= feature;
+		else
+			af.features &= ~feature;
+		af.lock |= new_lock;
+	}
+
+	return 0;
+}
+
 static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	u32			seq;
@@ -659,6 +759,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	switch (msg_type) {
 	case AUDIT_GET:
+		memset(&status_set, 0, sizeof(status_set));
 		status_set.enabled	 = audit_enabled;
 		status_set.failure	 = audit_failure;
 		status_set.pid		 = audit_pid;
@@ -670,7 +771,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 				 &status_set, sizeof(status_set));
 		break;
 	case AUDIT_SET:
-		if (nlh->nlmsg_len < sizeof(struct audit_status))
+		if (nlmsg_len(nlh) < sizeof(struct audit_status))
 			return -EINVAL;
 		status_get   = (struct audit_status *)data;
 		if (status_get->mask & AUDIT_STATUS_ENABLED) {
@@ -699,6 +800,16 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT)
 			err = audit_set_backlog_limit(status_get->backlog_limit);
 		break;
+	case AUDIT_GET_FEATURE:
+		err = audit_get_feature(skb);
+		if (err)
+			return err;
+		break;
+	case AUDIT_SET_FEATURE:
+		err = audit_set_feature(skb);
+		if (err)
+			return err;
+		break;
 	case AUDIT_USER:
 	case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
 	case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
@@ -715,7 +826,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			}
 			audit_log_common_recv_msg(&ab, msg_type);
 			if (msg_type != AUDIT_USER_TTY)
-				audit_log_format(ab, " msg='%.1024s'",
+				audit_log_format(ab, " msg='%.*s'",
+						 AUDIT_MESSAGE_TEXT_MAX,
 						 (char *)data);
 			else {
 				int size;
@@ -818,7 +930,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		struct task_struct *tsk = current;
 
 		spin_lock(&tsk->sighand->siglock);
-		s.enabled = tsk->signal->audit_tty != 0;
+		s.enabled = tsk->signal->audit_tty;
 		s.log_passwd = tsk->signal->audit_tty_log_passwd;
 		spin_unlock(&tsk->sighand->siglock);
 
@@ -832,7 +944,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 		memset(&s, 0, sizeof(s));
 		/* guard against past and future API changes */
-		memcpy(&s, data, min(sizeof(s), (size_t)nlh->nlmsg_len));
+		memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
 		if ((s.enabled != 0 && s.enabled != 1) ||
 		    (s.log_passwd != 0 && s.log_passwd != 1))
 			return -EINVAL;
@@ -1067,13 +1179,6 @@ static void wait_for_auditd(unsigned long sleep_time)
 	remove_wait_queue(&audit_backlog_wait, &wait);
 }
 
-/* Obtain an audit buffer.  This routine does locking to obtain the
- * audit buffer, but then no locking is required for calls to
- * audit_log_*format.  If the tsk is a task that is currently in a
- * syscall, then the syscall is marked as auditable and an audit record
- * will be written at syscall exit.  If there is no associated task, tsk
- * should be NULL. */
-
 /**
  * audit_log_start - obtain an audit buffer
  * @ctx: audit_context (may be NULL)
@@ -1389,7 +1494,7 @@ void audit_log_session_info(struct audit_buffer *ab)
 	u32 sessionid = audit_get_sessionid(current);
 	uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current));
 
-	audit_log_format(ab, " auid=%u ses=%u\n", auid, sessionid);
+	audit_log_format(ab, " auid=%u ses=%u", auid, sessionid);
 }
 
 void audit_log_key(struct audit_buffer *ab, char *key)
@@ -1536,6 +1641,26 @@ void audit_log_name(struct audit_context *context, struct audit_names *n,
 		}
 	}
 
+	/* log the audit_names record type */
+	audit_log_format(ab, " nametype=");
+	switch(n->type) {
+	case AUDIT_TYPE_NORMAL:
+		audit_log_format(ab, "NORMAL");
+		break;
+	case AUDIT_TYPE_PARENT:
+		audit_log_format(ab, "PARENT");
+		break;
+	case AUDIT_TYPE_CHILD_DELETE:
+		audit_log_format(ab, "DELETE");
+		break;
+	case AUDIT_TYPE_CHILD_CREATE:
+		audit_log_format(ab, "CREATE");
+		break;
+	default:
+		audit_log_format(ab, "UNKNOWN");
+		break;
+	}
+
 	audit_log_fcaps(ab, n);
 	audit_log_end(ab);
 }
diff --git a/kernel/audit.h b/kernel/audit.h
index 123c9b7c3979..b779642b29af 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -197,6 +197,9 @@ struct audit_context {
 			int			fd;
 			int			flags;
 		} mmap;
+		struct {
+			int			argc;
+		} execve;
 	};
 	int fds[2];
 
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index f7aee8be7fb2..51f3fd4c1ed3 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -343,6 +343,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f)
 	case AUDIT_DEVMINOR:
 	case AUDIT_EXIT:
 	case AUDIT_SUCCESS:
+	case AUDIT_INODE:
 		/* bit ops are only useful on syscall args */
 		if (f->op == Audit_bitmask || f->op == Audit_bittest)
 			return -EINVAL;
@@ -423,7 +424,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		f->lsm_rule = NULL;
 
 		/* Support legacy tests for a valid loginuid */
-		if ((f->type == AUDIT_LOGINUID) && (f->val == ~0U)) {
+		if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
 			f->type = AUDIT_LOGINUID_SET;
 			f->val = 0;
 		}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 9845cb32b60a..90594c9f7552 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -95,13 +95,6 @@ struct audit_aux_data {
 /* Number of target pids per aux struct. */
 #define AUDIT_AUX_PIDS	16
 
-struct audit_aux_data_execve {
-	struct audit_aux_data	d;
-	int argc;
-	int envc;
-	struct mm_struct *mm;
-};
-
 struct audit_aux_data_pids {
 	struct audit_aux_data	d;
 	pid_t			target_pid[AUDIT_AUX_PIDS];
@@ -121,12 +114,6 @@ struct audit_aux_data_bprm_fcaps {
 	struct audit_cap_data	new_pcap;
 };
 
-struct audit_aux_data_capset {
-	struct audit_aux_data	d;
-	pid_t			pid;
-	struct audit_cap_data	cap;
-};
-
 struct audit_tree_refs {
 	struct audit_tree_refs *next;
 	struct audit_chunk *c[31];
@@ -566,7 +553,7 @@ static int audit_filter_rules(struct task_struct *tsk,
 			break;
 		case AUDIT_INODE:
 			if (name)
-				result = (name->ino == f->val);
+				result = audit_comparator(name->ino, f->op, f->val);
 			else if (ctx) {
 				list_for_each_entry(n, &ctx->names_list, list) {
 					if (audit_comparator(n->ino, f->op, f->val)) {
@@ -943,8 +930,10 @@ int audit_alloc(struct task_struct *tsk)
 		return 0; /* Return if not auditing. */
 
 	state = audit_filter_task(tsk, &key);
-	if (state == AUDIT_DISABLED)
+	if (state == AUDIT_DISABLED) {
+		clear_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
 		return 0;
+	}
 
 	if (!(context = audit_alloc_context(state))) {
 		kfree(key);
@@ -1149,20 +1138,16 @@ static int audit_log_single_execve_arg(struct audit_context *context,
 }
 
 static void audit_log_execve_info(struct audit_context *context,
-				  struct audit_buffer **ab,
-				  struct audit_aux_data_execve *axi)
+				  struct audit_buffer **ab)
 {
 	int i, len;
 	size_t len_sent = 0;
 	const char __user *p;
 	char *buf;
 
-	if (axi->mm != current->mm)
-		return; /* execve failed, no additional info */
-
-	p = (const char __user *)axi->mm->arg_start;
+	p = (const char __user *)current->mm->arg_start;
 
-	audit_log_format(*ab, "argc=%d", axi->argc);
+	audit_log_format(*ab, "argc=%d", context->execve.argc);
 
 	/*
 	 * we need some kernel buffer to hold the userspace args.  Just
@@ -1176,7 +1161,7 @@ static void audit_log_execve_info(struct audit_context *context,
 		return;
 	}
 
-	for (i = 0; i < axi->argc; i++) {
+	for (i = 0; i < context->execve.argc; i++) {
 		len = audit_log_single_execve_arg(context, ab, i,
 						  &len_sent, p, buf);
 		if (len <= 0)
@@ -1279,6 +1264,9 @@ static void show_special(struct audit_context *context, int *call_panic)
 		audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd,
 				 context->mmap.flags);
 		break; }
+	case AUDIT_EXECVE: {
+		audit_log_execve_info(context, &ab);
+		break; }
 	}
 	audit_log_end(ab);
 }
@@ -1325,11 +1313,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 
 		switch (aux->type) {
 
-		case AUDIT_EXECVE: {
-			struct audit_aux_data_execve *axi = (void *)aux;
-			audit_log_execve_info(context, &ab, axi);
-			break; }
-
 		case AUDIT_BPRM_FCAPS: {
 			struct audit_aux_data_bprm_fcaps *axs = (void *)aux;
 			audit_log_format(ab, "fver=%x", axs->fcap_ver);
@@ -1964,6 +1947,43 @@ int auditsc_get_stamp(struct audit_context *ctx,
 /* global counter which is incremented every time something logs in */
 static atomic_t session_id = ATOMIC_INIT(0);
 
+static int audit_set_loginuid_perm(kuid_t loginuid)
+{
+	/* if we are unset, we don't need privs */
+	if (!audit_loginuid_set(current))
+		return 0;
+	/* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/
+	if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE))
+		return -EPERM;
+	/* it is set, you need permission */
+	if (!capable(CAP_AUDIT_CONTROL))
+		return -EPERM;
+	/* reject if this is not an unset and we don't allow that */
+	if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid))
+		return -EPERM;
+	return 0;
+}
+
+static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
+				   unsigned int oldsessionid, unsigned int sessionid,
+				   int rc)
+{
+	struct audit_buffer *ab;
+	uid_t uid, ologinuid, nloginuid;
+
+	uid = from_kuid(&init_user_ns, task_uid(current));
+	ologinuid = from_kuid(&init_user_ns, koldloginuid);
+	nloginuid = from_kuid(&init_user_ns, kloginuid),
+
+	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
+	if (!ab)
+		return;
+	audit_log_format(ab, "pid=%d uid=%u old auid=%u new auid=%u old "
+			 "ses=%u new ses=%u res=%d", current->pid, uid, ologinuid,
+			 nloginuid, oldsessionid, sessionid, !rc);
+	audit_log_end(ab);
+}
+
 /**
  * audit_set_loginuid - set current task's audit_context loginuid
  * @loginuid: loginuid value
@@ -1975,37 +1995,26 @@ static atomic_t session_id = ATOMIC_INIT(0);
 int audit_set_loginuid(kuid_t loginuid)
 {
 	struct task_struct *task = current;
-	struct audit_context *context = task->audit_context;
-	unsigned int sessionid;
+	unsigned int oldsessionid, sessionid = (unsigned int)-1;
+	kuid_t oldloginuid;
+	int rc;
 
-#ifdef CONFIG_AUDIT_LOGINUID_IMMUTABLE
-	if (audit_loginuid_set(task))
-		return -EPERM;
-#else /* CONFIG_AUDIT_LOGINUID_IMMUTABLE */
-	if (!capable(CAP_AUDIT_CONTROL))
-		return -EPERM;
-#endif  /* CONFIG_AUDIT_LOGINUID_IMMUTABLE */
+	oldloginuid = audit_get_loginuid(current);
+	oldsessionid = audit_get_sessionid(current);
 
-	sessionid = atomic_inc_return(&session_id);
-	if (context && context->in_syscall) {
-		struct audit_buffer *ab;
+	rc = audit_set_loginuid_perm(loginuid);
+	if (rc)
+		goto out;
+
+	/* are we setting or clearing? */
+	if (uid_valid(loginuid))
+		sessionid = atomic_inc_return(&session_id);
 
-		ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
-		if (ab) {
-			audit_log_format(ab, "login pid=%d uid=%u "
-				"old auid=%u new auid=%u"
-				" old ses=%u new ses=%u",
-				task->pid,
-				from_kuid(&init_user_ns, task_uid(task)),
-				from_kuid(&init_user_ns, task->loginuid),
-				from_kuid(&init_user_ns, loginuid),
-				task->sessionid, sessionid);
-			audit_log_end(ab);
-		}
-	}
 	task->sessionid = sessionid;
 	task->loginuid = loginuid;
-	return 0;
+out:
+	audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc);
+	return rc;
 }
 
 /**
@@ -2126,22 +2135,12 @@ void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mo
 	context->ipc.has_perm = 1;
 }
 
-int __audit_bprm(struct linux_binprm *bprm)
+void __audit_bprm(struct linux_binprm *bprm)
 {
-	struct audit_aux_data_execve *ax;
 	struct audit_context *context = current->audit_context;
 
-	ax = kmalloc(sizeof(*ax), GFP_KERNEL);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->argc = bprm->argc;
-	ax->envc = bprm->envc;
-	ax->mm = bprm->mm;
-	ax->d.type = AUDIT_EXECVE;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->type = AUDIT_EXECVE;
+	context->execve.argc = bprm->argc;
 }
 
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e0839bcd48c8..8b729c278b64 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -90,6 +90,14 @@ static DEFINE_MUTEX(cgroup_mutex);
 static DEFINE_MUTEX(cgroup_root_mutex);
 
 /*
+ * cgroup destruction makes heavy use of work items and there can be a lot
+ * of concurrent destructions.  Use a separate workqueue so that cgroup
+ * destruction work items don't end up filling up max_active of system_wq
+ * which may lead to deadlock.
+ */
+static struct workqueue_struct *cgroup_destroy_wq;
+
+/*
  * Generate an array of cgroup subsystem pointers. At boot time, this is
  * populated with the built in subsystems, and modular subsystems are
  * registered after that. The mutable section of this array is protected by
@@ -191,6 +199,7 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
 static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
 			      bool is_add);
+static int cgroup_file_release(struct inode *inode, struct file *file);
 
 /**
  * cgroup_css - obtain a cgroup's css for the specified subsystem
@@ -871,7 +880,7 @@ static void cgroup_free_rcu(struct rcu_head *head)
 	struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head);
 
 	INIT_WORK(&cgrp->destroy_work, cgroup_free_fn);
-	schedule_work(&cgrp->destroy_work);
+	queue_work(cgroup_destroy_wq, &cgrp->destroy_work);
 }
 
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
@@ -895,11 +904,6 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 	iput(inode);
 }
 
-static int cgroup_delete(const struct dentry *d)
-{
-	return 1;
-}
-
 static void remove_dir(struct dentry *d)
 {
 	struct dentry *parent = dget(d->d_parent);
@@ -1486,7 +1490,7 @@ static int cgroup_get_rootdir(struct super_block *sb)
 {
 	static const struct dentry_operations cgroup_dops = {
 		.d_iput = cgroup_diput,
-		.d_delete = cgroup_delete,
+		.d_delete = always_delete_dentry,
 	};
 
 	struct inode *inode =
@@ -2426,7 +2430,7 @@ static const struct file_operations cgroup_seqfile_operations = {
 	.read = seq_read,
 	.write = cgroup_file_write,
 	.llseek = seq_lseek,
-	.release = single_release,
+	.release = cgroup_file_release,
 };
 
 static int cgroup_file_open(struct inode *inode, struct file *file)
@@ -2487,6 +2491,8 @@ static int cgroup_file_release(struct inode *inode, struct file *file)
 		ret = cft->release(inode, file);
 	if (css->ss)
 		css_put(css);
+	if (file->f_op == &cgroup_seqfile_operations)
+		single_release(inode, file);
 	return ret;
 }
 
@@ -4254,7 +4260,7 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head)
 	 * css_put().  dput() requires process context which we don't have.
 	 */
 	INIT_WORK(&css->destroy_work, css_free_work_fn);
-	schedule_work(&css->destroy_work);
+	queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
 static void css_release(struct percpu_ref *ref)
@@ -4544,7 +4550,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
 	INIT_WORK(&css->destroy_work, css_killed_work_fn);
-	schedule_work(&css->destroy_work);
+	queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
 /**
@@ -5068,6 +5074,22 @@ out:
 	return err;
 }
 
+static int __init cgroup_wq_init(void)
+{
+	/*
+	 * There isn't much point in executing destruction path in
+	 * parallel.  Good chunk is serialized with cgroup_mutex anyway.
+	 * Use 1 for @max_active.
+	 *
+	 * We would prefer to do this in cgroup_init() above, but that
+	 * is called before init_workqueues(): so leave this until after.
+	 */
+	cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
+	BUG_ON(!cgroup_destroy_wq);
+	return 0;
+}
+core_initcall(cgroup_wq_init);
+
 /*
  * proc_cgroup_show()
  *  - Print task's cgroup paths into seq_file, one line for each hierarchy
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 6bf981e13c43..4772034b4b17 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1033,8 +1033,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	need_loop = task_has_mempolicy(tsk) ||
 			!nodes_intersects(*newmems, tsk->mems_allowed);
 
-	if (need_loop)
+	if (need_loop) {
+		local_irq_disable();
 		write_seqcount_begin(&tsk->mems_allowed_seq);
+	}
 
 	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
@@ -1042,8 +1044,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
 	tsk->mems_allowed = *newmems;
 
-	if (need_loop)
+	if (need_loop) {
 		write_seqcount_end(&tsk->mems_allowed_seq);
+		local_irq_enable();
+	}
 
 	task_unlock(tsk);
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d724e7757cd1..72348dc192c1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5680,11 +5680,6 @@ static void swevent_hlist_put(struct perf_event *event)
 {
 	int cpu;
 
-	if (event->cpu != -1) {
-		swevent_hlist_put_cpu(event, event->cpu);
-		return;
-	}
-
 	for_each_possible_cpu(cpu)
 		swevent_hlist_put_cpu(event, cpu);
 }
@@ -5718,9 +5713,6 @@ static int swevent_hlist_get(struct perf_event *event)
 	int err;
 	int cpu, failed_cpu;
 
-	if (event->cpu != -1)
-		return swevent_hlist_get_cpu(event, event->cpu);
-
 	get_online_cpus();
 	for_each_possible_cpu(cpu) {
 		err = swevent_hlist_get_cpu(event, cpu);
diff --git a/kernel/extable.c b/kernel/extable.c
index 832cb28105bb..763faf037ec1 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -61,7 +61,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
 static inline int init_kernel_text(unsigned long addr)
 {
 	if (addr >= (unsigned long)_sinittext &&
-	    addr <= (unsigned long)_einittext)
+	    addr < (unsigned long)_einittext)
 		return 1;
 	return 0;
 }
@@ -69,7 +69,7 @@ static inline int init_kernel_text(unsigned long addr)
 int core_kernel_text(unsigned long addr)
 {
 	if (addr >= (unsigned long)_stext &&
-	    addr <= (unsigned long)_etext)
+	    addr < (unsigned long)_etext)
 		return 1;
 
 	if (system_state == SYSTEM_BOOTING &&
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/irq/pm.c b/kernel/irq/pm.c
index cb228bf21760..abcd6ca86cb7 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -50,7 +50,7 @@ static void resume_irqs(bool want_early)
 		bool is_early = desc->action &&
 			desc->action->flags & IRQF_EARLY_RESUME;
 
-		if (is_early != want_early)
+		if (!is_early && want_early)
 			continue;
 
 		raw_spin_lock_irqsave(&desc->lock, flags);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 490afc03627e..d0d8fca54065 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",
@@ -1675,6 +1678,7 @@ int kernel_kexec(void)
 	} else
 #endif
 	{
+		kexec_in_progress = true;
 		kernel_restart_prepare(NULL);
 		printk(KERN_EMERG "Starting new kernel\n");
 		machine_shutdown();
diff --git a/kernel/modsign_certificate.S b/kernel/modsign_certificate.S
deleted file mode 100644
index 4a9a86d12c8b..000000000000
--- a/kernel/modsign_certificate.S
+++ /dev/null
@@ -1,12 +0,0 @@
-#include <linux/export.h>
-
-#define GLOBAL(name)	\
-	.globl VMLINUX_SYMBOL(name);	\
-	VMLINUX_SYMBOL(name):
-
-	.section ".init.data","aw"
-
-GLOBAL(modsign_certificate_list)
-	.incbin "signing_key.x509"
-	.incbin "extra_certificates"
-GLOBAL(modsign_certificate_list_end)
diff --git a/kernel/modsign_pubkey.c b/kernel/modsign_pubkey.c
deleted file mode 100644
index 7cbd4507a7e6..000000000000
--- a/kernel/modsign_pubkey.c
+++ /dev/null
@@ -1,104 +0,0 @@
-/* Public keys for module signature verification
- *
- * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/cred.h>
-#include <linux/err.h>
-#include <keys/asymmetric-type.h>
-#include "module-internal.h"
-
-struct key *modsign_keyring;
-
-extern __initconst const u8 modsign_certificate_list[];
-extern __initconst const u8 modsign_certificate_list_end[];
-
-/*
- * We need to make sure ccache doesn't cache the .o file as it doesn't notice
- * if modsign.pub changes.
- */
-static __initconst const char annoy_ccache[] = __TIME__ "foo";
-
-/*
- * Load the compiled-in keys
- */
-static __init int module_verify_init(void)
-{
-	pr_notice("Initialise module verification\n");
-
-	modsign_keyring = keyring_alloc(".module_sign",
-					KUIDT_INIT(0), KGIDT_INIT(0),
-					current_cred(),
-					((KEY_POS_ALL & ~KEY_POS_SETATTR) |
-					 KEY_USR_VIEW | KEY_USR_READ),
-					KEY_ALLOC_NOT_IN_QUOTA, NULL);
-	if (IS_ERR(modsign_keyring))
-		panic("Can't allocate module signing keyring\n");
-
-	return 0;
-}
-
-/*
- * Must be initialised before we try and load the keys into the keyring.
- */
-device_initcall(module_verify_init);
-
-/*
- * Load the compiled-in keys
- */
-static __init int load_module_signing_keys(void)
-{
-	key_ref_t key;
-	const u8 *p, *end;
-	size_t plen;
-
-	pr_notice("Loading module verification certificates\n");
-
-	end = modsign_certificate_list_end;
-	p = modsign_certificate_list;
-	while (p < end) {
-		/* Each cert begins with an ASN.1 SEQUENCE tag and must be more
-		 * than 256 bytes in size.
-		 */
-		if (end - p < 4)
-			goto dodgy_cert;
-		if (p[0] != 0x30 &&
-		    p[1] != 0x82)
-			goto dodgy_cert;
-		plen = (p[2] << 8) | p[3];
-		plen += 4;
-		if (plen > end - p)
-			goto dodgy_cert;
-
-		key = key_create_or_update(make_key_ref(modsign_keyring, 1),
-					   "asymmetric",
-					   NULL,
-					   p,
-					   plen,
-					   (KEY_POS_ALL & ~KEY_POS_SETATTR) |
-					   KEY_USR_VIEW,
-					   KEY_ALLOC_NOT_IN_QUOTA);
-		if (IS_ERR(key))
-			pr_err("MODSIGN: Problem loading in-kernel X.509 certificate (%ld)\n",
-			       PTR_ERR(key));
-		else
-			pr_notice("MODSIGN: Loaded cert '%s'\n",
-				  key_ref_to_ptr(key)->description);
-		p += plen;
-	}
-
-	return 0;
-
-dodgy_cert:
-	pr_err("MODSIGN: Problem parsing in-kernel X.509 certificate list\n");
-	return 0;
-}
-late_initcall(load_module_signing_keys);
diff --git a/kernel/module-internal.h b/kernel/module-internal.h
index 24f9247b7d02..915e123a430f 100644
--- a/kernel/module-internal.h
+++ b/kernel/module-internal.h
@@ -9,6 +9,4 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
-extern struct key *modsign_keyring;
-
 extern int mod_verify_sig(const void *mod, unsigned long *_modlen);
diff --git a/kernel/module_signing.c b/kernel/module_signing.c
index f2970bddc5ea..be5b8fac4bd0 100644
--- a/kernel/module_signing.c
+++ b/kernel/module_signing.c
@@ -14,6 +14,7 @@
 #include <crypto/public_key.h>
 #include <crypto/hash.h>
 #include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
 #include "module-internal.h"
 
 /*
@@ -28,7 +29,7 @@
  */
 struct module_signature {
 	u8	algo;		/* Public-key crypto algorithm [enum pkey_algo] */
-	u8	hash;		/* Digest algorithm [enum pkey_hash_algo] */
+	u8	hash;		/* Digest algorithm [enum hash_algo] */
 	u8	id_type;	/* Key identifier type [enum pkey_id_type] */
 	u8	signer_len;	/* Length of signer's name */
 	u8	key_id_len;	/* Length of key identifier */
@@ -39,7 +40,7 @@ struct module_signature {
 /*
  * Digest the module contents.
  */
-static struct public_key_signature *mod_make_digest(enum pkey_hash_algo hash,
+static struct public_key_signature *mod_make_digest(enum hash_algo hash,
 						    const void *mod,
 						    unsigned long modlen)
 {
@@ -54,7 +55,7 @@ static struct public_key_signature *mod_make_digest(enum pkey_hash_algo hash,
 	/* Allocate the hashing algorithm we're going to need and find out how
 	 * big the hash operational data will be.
 	 */
-	tfm = crypto_alloc_shash(pkey_hash_algo[hash], 0, 0);
+	tfm = crypto_alloc_shash(hash_algo_name[hash], 0, 0);
 	if (IS_ERR(tfm))
 		return (PTR_ERR(tfm) == -ENOENT) ? ERR_PTR(-ENOPKG) : ERR_CAST(tfm);
 
@@ -157,7 +158,7 @@ static struct key *request_asymmetric_key(const char *signer, size_t signer_len,
 
 	pr_debug("Look up: \"%s\"\n", id);
 
-	key = keyring_search(make_key_ref(modsign_keyring, 1),
+	key = keyring_search(make_key_ref(system_trusted_keyring, 1),
 			     &key_type_asymmetric, id);
 	if (IS_ERR(key))
 		pr_warn("Request for unknown module key '%s' err %ld\n",
@@ -217,7 +218,7 @@ int mod_verify_sig(const void *mod, unsigned long *_modlen)
 		return -ENOPKG;
 
 	if (ms.hash >= PKEY_HASH__LAST ||
-	    !pkey_hash_algo[ms.hash])
+	    !hash_algo_name[ms.hash])
 		return -ENOPKG;
 
 	key = request_asymmetric_key(sig, ms.signer_len,
diff --git a/kernel/padata.c b/kernel/padata.c
index 07af2c95dcfe..2abd25d79cc8 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -46,6 +46,7 @@ static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
 
 static int padata_cpu_hash(struct parallel_data *pd)
 {
+	unsigned int seq_nr;
 	int cpu_index;
 
 	/*
@@ -53,10 +54,8 @@ static int padata_cpu_hash(struct parallel_data *pd)
 	 * seq_nr mod. number of cpus in use.
 	 */
 
-	spin_lock(&pd->seq_lock);
-	cpu_index =  pd->seq_nr % cpumask_weight(pd->cpumask.pcpu);
-	pd->seq_nr++;
-	spin_unlock(&pd->seq_lock);
+	seq_nr = atomic_inc_return(&pd->seq_nr);
+	cpu_index = seq_nr % cpumask_weight(pd->cpumask.pcpu);
 
 	return padata_index_to_cpu(pd, cpu_index);
 }
@@ -429,7 +428,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
 	padata_init_pqueues(pd);
 	padata_init_squeues(pd);
 	setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd);
-	pd->seq_nr = 0;
+	atomic_set(&pd->seq_nr, -1);
 	atomic_set(&pd->reorder_objects, 0);
 	atomic_set(&pd->refcnt, 0);
 	pd->pinst = pinst;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 10c22cae83a0..b38109e204af 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -792,7 +792,8 @@ void free_basic_memory_bitmaps(void)
 {
 	struct memory_bitmap *bm1, *bm2;
 
-	BUG_ON(!(forbidden_pages_map && free_pages_map));
+	if (WARN_ON(!(forbidden_pages_map && free_pages_map)))
+		return;
 
 	bm1 = forbidden_pages_map;
 	bm2 = free_pages_map;
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 24850270c802..98d357584cd6 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -70,6 +70,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 		data->swap = swsusp_resume_device ?
 			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
 		data->mode = O_RDONLY;
+		data->free_bitmaps = false;
 		error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
 		if (error)
 			pm_notifier_call_chain(PM_POST_HIBERNATION);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index eb161d80cbde..506a7a97a2e2 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1643,7 +1643,7 @@ module_param(rcu_idle_gp_delay, int, 0644);
 static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY;
 module_param(rcu_idle_lazy_gp_delay, int, 0644);
 
-extern int tick_nohz_enabled;
+extern int tick_nohz_active;
 
 /*
  * Try to advance callbacks for all flavors of RCU on the current CPU, but
@@ -1740,7 +1740,7 @@ static void rcu_prepare_for_idle(int cpu)
 	int tne;
 
 	/* Handle nohz enablement switches conservatively. */
-	tne = ACCESS_ONCE(tick_nohz_enabled);
+	tne = ACCESS_ONCE(tick_nohz_active);
 	if (tne != rdtp->tick_nohz_enabled_snap) {
 		if (rcu_cpu_has_callbacks(cpu, NULL))
 			invoke_rcu_core(); /* force nohz to see update. */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c1808606ee5f..e85cda20ab2b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2660,6 +2660,7 @@ asmlinkage void __sched notrace preempt_schedule(void)
 	} while (need_resched());
 }
 EXPORT_SYMBOL(preempt_schedule);
+#endif /* CONFIG_PREEMPT */
 
 /*
  * this is the entry point to schedule() from kernel preemption
@@ -2693,8 +2694,6 @@ asmlinkage void __sched preempt_schedule_irq(void)
 	exception_exit(prev_state);
 }
 
-#endif /* CONFIG_PREEMPT */
-
 int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
 			  void *key)
 {
@@ -4762,7 +4761,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 		cpumask_clear_cpu(rq->cpu, old_rd->span);
 
 		/*
-		 * If we dont want to free the old_rt yet then
+		 * If we dont want to free the old_rd yet then
 		 * set old_rd to NULL to skip the freeing later
 		 * in this function:
 		 */
@@ -4910,8 +4909,9 @@ static void update_top_cache_domain(int cpu)
 	if (sd) {
 		id = cpumask_first(sched_domain_span(sd));
 		size = cpumask_weight(sched_domain_span(sd));
-		rcu_assign_pointer(per_cpu(sd_busy, cpu), sd->parent);
+		sd = sd->parent; /* sd_busy */
 	}
+	rcu_assign_pointer(per_cpu(sd_busy, cpu), sd);
 
 	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
 	per_cpu(sd_llc_size, cpu) = size;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e8b652ebe027..fd773ade1a31 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5379,10 +5379,31 @@ void update_group_power(struct sched_domain *sd, int cpu)
 		 */
 
 		for_each_cpu(cpu, sched_group_cpus(sdg)) {
-			struct sched_group *sg = cpu_rq(cpu)->sd->groups;
+			struct sched_group_power *sgp;
+			struct rq *rq = cpu_rq(cpu);
 
-			power_orig += sg->sgp->power_orig;
-			power += sg->sgp->power;
+			/*
+			 * build_sched_domains() -> init_sched_groups_power()
+			 * gets here before we've attached the domains to the
+			 * runqueues.
+			 *
+			 * Use power_of(), which is set irrespective of domains
+			 * in update_cpu_power().
+			 *
+			 * This avoids power/power_orig from being 0 and
+			 * causing divide-by-zero issues on boot.
+			 *
+			 * Runtime updates will correct power_orig.
+			 */
+			if (unlikely(!rq->sd)) {
+				power_orig += power_of(cpu);
+				power += power_of(cpu);
+				continue;
+			}
+
+			sgp = rq->sd->groups->sgp;
+			power_orig += sgp->power_orig;
+			power += sgp->power;
 		}
 	} else  {
 		/*
diff --git a/kernel/system_certificates.S b/kernel/system_certificates.S
new file mode 100644
index 000000000000..3e9868d47535
--- /dev/null
+++ b/kernel/system_certificates.S
@@ -0,0 +1,20 @@
+#include <linux/export.h>
+#include <linux/init.h>
+
+	__INITRODATA
+
+	.align 8
+	.globl VMLINUX_SYMBOL(system_certificate_list)
+VMLINUX_SYMBOL(system_certificate_list):
+__cert_list_start:
+	.incbin "kernel/x509_certificate_list"
+__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
new file mode 100644
index 000000000000..52ebc70263f4
--- /dev/null
+++ b/kernel/system_keyring.c
@@ -0,0 +1,105 @@
+/* System trusted keyring for trusted public keys
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+#include "module-internal.h"
+
+struct key *system_trusted_keyring;
+EXPORT_SYMBOL_GPL(system_trusted_keyring);
+
+extern __initconst const u8 system_certificate_list[];
+extern __initconst const unsigned long system_certificate_list_size;
+
+/*
+ * Load the compiled-in keys
+ */
+static __init int system_trusted_keyring_init(void)
+{
+	pr_notice("Initialise system trusted keyring\n");
+
+	system_trusted_keyring =
+		keyring_alloc(".system_keyring",
+			      KUIDT_INIT(0), KGIDT_INIT(0), current_cred(),
+			      ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+			      KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH),
+			      KEY_ALLOC_NOT_IN_QUOTA, NULL);
+	if (IS_ERR(system_trusted_keyring))
+		panic("Can't allocate system trusted keyring\n");
+
+	set_bit(KEY_FLAG_TRUSTED_ONLY, &system_trusted_keyring->flags);
+	return 0;
+}
+
+/*
+ * Must be initialised before we try and load the keys into the keyring.
+ */
+device_initcall(system_trusted_keyring_init);
+
+/*
+ * Load the compiled-in list of X.509 certificates.
+ */
+static __init int load_system_certificate_list(void)
+{
+	key_ref_t key;
+	const u8 *p, *end;
+	size_t plen;
+
+	pr_notice("Loading compiled-in X.509 certificates\n");
+
+	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.
+		 */
+		if (end - p < 4)
+			goto dodgy_cert;
+		if (p[0] != 0x30 &&
+		    p[1] != 0x82)
+			goto dodgy_cert;
+		plen = (p[2] << 8) | p[3];
+		plen += 4;
+		if (plen > end - p)
+			goto dodgy_cert;
+
+		key = key_create_or_update(make_key_ref(system_trusted_keyring, 1),
+					   "asymmetric",
+					   NULL,
+					   p,
+					   plen,
+					   ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+					   KEY_USR_VIEW | KEY_USR_READ),
+					   KEY_ALLOC_NOT_IN_QUOTA |
+					   KEY_ALLOC_TRUSTED);
+		if (IS_ERR(key)) {
+			pr_err("Problem loading in-kernel X.509 certificate (%ld)\n",
+			       PTR_ERR(key));
+		} else {
+			pr_notice("Loaded X.509 cert '%s'\n",
+				  key_ref_to_ptr(key)->description);
+			key_ref_put(key);
+		}
+		p += plen;
+	}
+
+	return 0;
+
+dodgy_cert:
+	pr_err("Problem parsing in-kernel X.509 certificate list\n");
+	return 0;
+}
+late_initcall(load_system_certificate_list);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 64522ecdfe0e..162b03ab0ad2 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -33,6 +33,21 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
  */
 ktime_t tick_next_period;
 ktime_t tick_period;
+
+/*
+ * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
+ * which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
+ * variable has two functions:
+ *
+ * 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
+ *    timekeeping lock all at once. Only the CPU which is assigned to do the
+ *    update is handling it.
+ *
+ * 2) Hand off the duty in the NOHZ idle case by setting the value to
+ *    TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
+ *    at it will take over and keep the time keeping alive.  The handover
+ *    procedure also covers cpu hotplug.
+ */
 int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
 
 /*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3612fc77f834..ea20f7d1ac2c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -361,8 +361,8 @@ void __init tick_nohz_init(void)
 /*
  * NO HZ enabled ?
  */
-int tick_nohz_enabled __read_mostly  = 1;
-
+static int tick_nohz_enabled __read_mostly  = 1;
+int tick_nohz_active  __read_mostly;
 /*
  * Enable / Disable tickless mode
  */
@@ -465,7 +465,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	ktime_t now, idle;
 
-	if (!tick_nohz_enabled)
+	if (!tick_nohz_active)
 		return -1;
 
 	now = ktime_get();
@@ -506,7 +506,7 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	ktime_t now, iowait;
 
-	if (!tick_nohz_enabled)
+	if (!tick_nohz_active)
 		return -1;
 
 	now = ktime_get();
@@ -711,8 +711,10 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 		return false;
 	}
 
-	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) {
+		ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ };
 		return false;
+	}
 
 	if (need_resched())
 		return false;
@@ -799,11 +801,6 @@ void tick_nohz_idle_enter(void)
 	local_irq_disable();
 
 	ts = &__get_cpu_var(tick_cpu_sched);
-	/*
-	 * set ts->inidle unconditionally. even if the system did not
-	 * switch to nohz mode the cpu frequency governers rely on the
-	 * update of the idle time accounting in tick_nohz_start_idle().
-	 */
 	ts->inidle = 1;
 	__tick_nohz_idle_enter(ts);
 
@@ -973,7 +970,7 @@ static void tick_nohz_switch_to_nohz(void)
 	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 	ktime_t next;
 
-	if (!tick_nohz_enabled)
+	if (!tick_nohz_active)
 		return;
 
 	local_irq_disable();
@@ -981,7 +978,7 @@ static void tick_nohz_switch_to_nohz(void)
 		local_irq_enable();
 		return;
 	}
-
+	tick_nohz_active = 1;
 	ts->nohz_mode = NOHZ_MODE_LOWRES;
 
 	/*
@@ -1139,8 +1136,10 @@ void tick_setup_sched_timer(void)
 	}
 
 #ifdef CONFIG_NO_HZ_COMMON
-	if (tick_nohz_enabled)
+	if (tick_nohz_enabled) {
 		ts->nohz_mode = NOHZ_MODE_HIGHRES;
+		tick_nohz_active = 1;
+	}
 #endif
 }
 #endif /* HIGH_RES_TIMERS */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3abf53418b67..87b4f00284c9 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1347,7 +1347,7 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
 	tk->xtime_nsec -= remainder;
 	tk->xtime_nsec += 1ULL << tk->shift;
 	tk->ntp_error += remainder << tk->ntp_error_shift;
-
+	tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift;
 }
 #else
 #define old_vsyscall_fixup(tk)
diff --git a/kernel/timer.c b/kernel/timer.c
index 6582b82fa966..accfd241b9e5 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1518,9 +1518,8 @@ static int init_timers_cpu(int cpu)
 			/*
 			 * The APs use this path later in boot
 			 */
-			base = kmalloc_node(sizeof(*base),
-						GFP_KERNEL | __GFP_ZERO,
-						cpu_to_node(cpu));
+			base = kzalloc_node(sizeof(*base), GFP_KERNEL,
+					    cpu_to_node(cpu));
 			if (!base)
 				return -ENOMEM;
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 22fa55696760..0e9f9eaade2f 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -367,9 +367,6 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list,
 
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
-	if (unlikely(ftrace_disabled))
-		return -ENODEV;
-
 	if (FTRACE_WARN_ON(ops == &global_ops))
 		return -EINVAL;
 
@@ -428,9 +425,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 {
 	int ret;
 
-	if (ftrace_disabled)
-		return -ENODEV;
-
 	if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED)))
 		return -EBUSY;
 
@@ -2088,10 +2082,15 @@ static void ftrace_startup_enable(int command)
 static int ftrace_startup(struct ftrace_ops *ops, int command)
 {
 	bool hash_enable = true;
+	int ret;
 
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
 
+	ret = __register_ftrace_function(ops);
+	if (ret)
+		return ret;
+
 	ftrace_start_up++;
 	command |= FTRACE_UPDATE_CALLS;
 
@@ -2113,12 +2112,17 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 	return 0;
 }
 
-static void ftrace_shutdown(struct ftrace_ops *ops, int command)
+static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 {
 	bool hash_disable = true;
+	int ret;
 
 	if (unlikely(ftrace_disabled))
-		return;
+		return -ENODEV;
+
+	ret = __unregister_ftrace_function(ops);
+	if (ret)
+		return ret;
 
 	ftrace_start_up--;
 	/*
@@ -2153,9 +2157,10 @@ static void ftrace_shutdown(struct ftrace_ops *ops, int command)
 	}
 
 	if (!command || !ftrace_enabled)
-		return;
+		return 0;
 
 	ftrace_run_update_code(command);
+	return 0;
 }
 
 static void ftrace_startup_sysctl(void)
@@ -3060,16 +3065,13 @@ static void __enable_ftrace_function_probe(void)
 	if (i == FTRACE_FUNC_HASHSIZE)
 		return;
 
-	ret = __register_ftrace_function(&trace_probe_ops);
-	if (!ret)
-		ret = ftrace_startup(&trace_probe_ops, 0);
+	ret = ftrace_startup(&trace_probe_ops, 0);
 
 	ftrace_probe_registered = 1;
 }
 
 static void __disable_ftrace_function_probe(void)
 {
-	int ret;
 	int i;
 
 	if (!ftrace_probe_registered)
@@ -3082,9 +3084,7 @@ static void __disable_ftrace_function_probe(void)
 	}
 
 	/* no more funcs left */
-	ret = __unregister_ftrace_function(&trace_probe_ops);
-	if (!ret)
-		ftrace_shutdown(&trace_probe_ops, 0);
+	ftrace_shutdown(&trace_probe_ops, 0);
 
 	ftrace_probe_registered = 0;
 }
@@ -4366,12 +4366,15 @@ core_initcall(ftrace_nodyn_init);
 static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
 static inline void ftrace_startup_enable(int command) { }
 /* Keep as macros so we do not need to define the commands */
-# define ftrace_startup(ops, command)			\
-	({						\
-		(ops)->flags |= FTRACE_OPS_FL_ENABLED;	\
-		0;					\
+# define ftrace_startup(ops, command)					\
+	({								\
+		int ___ret = __register_ftrace_function(ops);		\
+		if (!___ret)						\
+			(ops)->flags |= FTRACE_OPS_FL_ENABLED;		\
+		___ret;							\
 	})
-# define ftrace_shutdown(ops, command)	do { } while (0)
+# define ftrace_shutdown(ops, command) __unregister_ftrace_function(ops)
+
 # define ftrace_startup_sysctl()	do { } while (0)
 # define ftrace_shutdown_sysctl()	do { } while (0)
 
@@ -4780,9 +4783,7 @@ int register_ftrace_function(struct ftrace_ops *ops)
 
 	mutex_lock(&ftrace_lock);
 
-	ret = __register_ftrace_function(ops);
-	if (!ret)
-		ret = ftrace_startup(ops, 0);
+	ret = ftrace_startup(ops, 0);
 
 	mutex_unlock(&ftrace_lock);
 
@@ -4801,9 +4802,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
 	int ret;
 
 	mutex_lock(&ftrace_lock);
-	ret = __unregister_ftrace_function(ops);
-	if (!ret)
-		ftrace_shutdown(ops, 0);
+	ret = ftrace_shutdown(ops, 0);
 	mutex_unlock(&ftrace_lock);
 
 	return ret;
@@ -4997,6 +4996,13 @@ ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
 	return NOTIFY_DONE;
 }
 
+/* Just a place holder for function graph */
+static struct ftrace_ops fgraph_ops __read_mostly = {
+	.func		= ftrace_stub,
+	.flags		= FTRACE_OPS_FL_STUB | FTRACE_OPS_FL_GLOBAL |
+				FTRACE_OPS_FL_RECURSION_SAFE,
+};
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			trace_func_graph_ent_t entryfunc)
 {
@@ -5023,7 +5029,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	ftrace_graph_return = retfunc;
 	ftrace_graph_entry = entryfunc;
 
-	ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
+	ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET);
 
 out:
 	mutex_unlock(&ftrace_lock);
@@ -5040,7 +5046,7 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_active--;
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
-	ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET);
+	ftrace_shutdown(&fgraph_ops, FTRACE_STOP_FUNC_RET);
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 78e27e3b52ac..e854f420e033 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -24,6 +24,12 @@ static int	total_ref_count;
 static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
+	if (tp_event->perf_perm) {
+		int ret = tp_event->perf_perm(tp_event, p_event);
+		if (ret)
+			return ret;
+	}
+
 	/* The ftrace function trace is allowed only for root. */
 	if (ftrace_event_is_function(tp_event) &&
 	    perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
@@ -173,7 +179,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 int perf_trace_init(struct perf_event *p_event)
 {
 	struct ftrace_event_call *tp_event;
-	int event_id = p_event->attr.config;
+	u64 event_id = p_event->attr.config;
 	int ret = -EINVAL;
 
 	mutex_lock(&event_mutex);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f919a2e21bf3..a11800ae96de 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2314,6 +2314,9 @@ int event_trace_del_tracer(struct trace_array *tr)
 	/* Disable any running events */
 	__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
 
+	/* Access to events are within rcu_read_lock_sched() */
+	synchronize_sched();
+
 	down_write(&trace_event_sem);
 	__trace_remove_event_dirs(tr);
 	debugfs_remove_recursive(tr->event_dir);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index e4b6d11bdf78..ea90eb5f6f17 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -431,11 +431,6 @@ static void unreg_event_syscall_enter(struct ftrace_event_file *file,
 	if (!tr->sys_refcount_enter)
 		unregister_trace_sys_enter(ftrace_syscall_enter, tr);
 	mutex_unlock(&syscall_trace_lock);
-	/*
-	 * Callers expect the event to be completely disabled on
-	 * return, so wait for current handlers to finish.
-	 */
-	synchronize_sched();
 }
 
 static int reg_event_syscall_exit(struct ftrace_event_file *file,
@@ -474,11 +469,6 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file,
 	if (!tr->sys_refcount_exit)
 		unregister_trace_sys_exit(ftrace_syscall_exit, tr);
 	mutex_unlock(&syscall_trace_lock);
-	/*
-	 * Callers expect the event to be completely disabled on
-	 * return, so wait for current handlers to finish.
-	 */
-	synchronize_sched();
 }
 
 static int __init init_syscall_trace(struct ftrace_event_call *call)
diff --git a/kernel/user.c b/kernel/user.c
index 5bbb91988e69..a3a0dbfda329 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,10 @@ 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),
+#endif
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 13fb1134ba58..240fb62cf394 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -101,6 +101,9 @@ int create_user_ns(struct cred *new)
 
 	set_cred_user_ns(new, ns);
 
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	init_rwsem(&ns->persistent_keyring_register_sem);
+#endif
 	return 0;
 }
 
@@ -130,6 +133,9 @@ void free_user_ns(struct user_namespace *ns)
 
 	do {
 		parent = ns->parent;
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+		key_put(ns->persistent_keyring_register);
+#endif
 		proc_free_inum(ns->proc_inum);
 		kmem_cache_free(user_ns_cachep, ns);
 		ns = parent;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 987293d03ebc..b010eac595d2 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -305,6 +305,9 @@ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER);
 /* I: attributes used when instantiating standard unbound pools on demand */
 static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
 
+/* I: attributes used when instantiating ordered pools on demand */
+static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
+
 struct workqueue_struct *system_wq __read_mostly;
 EXPORT_SYMBOL(system_wq);
 struct workqueue_struct *system_highpri_wq __read_mostly;
@@ -518,14 +521,21 @@ static inline void debug_work_activate(struct work_struct *work) { }
 static inline void debug_work_deactivate(struct work_struct *work) { }
 #endif
 
-/* allocate ID and assign it to @pool */
+/**
+ * worker_pool_assign_id - allocate ID and assing it to @pool
+ * @pool: the pool pointer of interest
+ *
+ * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned
+ * successfully, -errno on failure.
+ */
 static int worker_pool_assign_id(struct worker_pool *pool)
 {
 	int ret;
 
 	lockdep_assert_held(&wq_pool_mutex);
 
-	ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
+	ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE,
+			GFP_KERNEL);
 	if (ret >= 0) {
 		pool->id = ret;
 		return 0;
@@ -1320,7 +1330,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 
 	debug_work_activate(work);
 
-	/* if dying, only works from the same workqueue are allowed */
+	/* if draining, only works from the same workqueue are allowed */
 	if (unlikely(wq->flags & __WQ_DRAINING) &&
 	    WARN_ON_ONCE(!is_chained_work(wq)))
 		return;
@@ -1736,16 +1746,17 @@ static struct worker *create_worker(struct worker_pool *pool)
 	if (IS_ERR(worker->task))
 		goto fail;
 
+	set_user_nice(worker->task, pool->attrs->nice);
+
+	/* prevent userland from meddling with cpumask of workqueue workers */
+	worker->task->flags |= PF_NO_SETAFFINITY;
+
 	/*
 	 * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
 	 * online CPUs.  It'll be re-applied when any of the CPUs come up.
 	 */
-	set_user_nice(worker->task, pool->attrs->nice);
 	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
 
-	/* prevent userland from meddling with cpumask of workqueue workers */
-	worker->task->flags |= PF_NO_SETAFFINITY;
-
 	/*
 	 * The caller is responsible for ensuring %POOL_DISASSOCIATED
 	 * remains stable across this function.  See the comments above the
@@ -2840,19 +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
@@ -2866,10 +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);
 
@@ -4106,7 +4112,7 @@ out_unlock:
 static int alloc_and_link_pwqs(struct workqueue_struct *wq)
 {
 	bool highpri = wq->flags & WQ_HIGHPRI;
-	int cpu;
+	int cpu, ret;
 
 	if (!(wq->flags & WQ_UNBOUND)) {
 		wq->cpu_pwqs = alloc_percpu(struct pool_workqueue);
@@ -4126,6 +4132,13 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq)
 			mutex_unlock(&wq->mutex);
 		}
 		return 0;
+	} else if (wq->flags & __WQ_ORDERED) {
+		ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
+		/* there should only be single pwq for ordering guarantee */
+		WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
+			      wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
+		     "ordering guarantee broken for workqueue %s\n", wq->name);
+		return ret;
 	} else {
 		return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
 	}
@@ -4814,14 +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);
@@ -5009,10 +5015,6 @@ static int __init init_workqueues(void)
 	int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
 	int i, cpu;
 
-	/* make sure we have enough bits for OFFQ pool ID */
-	BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT)) <
-		     WORK_CPU_END * NR_STD_WORKER_POOLS);
-
 	WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
 
 	pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
@@ -5051,13 +5053,23 @@ static int __init init_workqueues(void)
 		}
 	}
 
-	/* create default unbound wq attrs */
+	/* create default unbound and ordered wq attrs */
 	for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
 		struct workqueue_attrs *attrs;
 
 		BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
 		attrs->nice = std_nice[i];
 		unbound_std_wq_attrs[i] = attrs;
+
+		/*
+		 * An ordered wq should have only one pwq as ordering is
+		 * guaranteed by max_active which is enforced by pwqs.
+		 * Turn off NUMA so that dfl_pwq is used for all nodes.
+		 */
+		BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
+		attrs->nice = std_nice[i];
+		attrs->no_numa = true;
+		ordered_wq_attrs[i] = attrs;
 	}
 
 	system_wq = alloc_workqueue("events", 0, 0);