Merge branch 'next' into for-linus

Prepare first set of updates for 3.10 merge window.

7 files changed, 260 insertions, 121 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 6fdd6e339326..5341d7232c3a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -20,49 +20,14 @@ config CONSTRUCTORS
 	bool
 	depends on !UML
 
-config HAVE_IRQ_WORK
-	bool
-
 config IRQ_WORK
 	bool
-	depends on HAVE_IRQ_WORK
 
 config BUILDTIME_EXTABLE_SORT
 	bool
 
 menu "General setup"
 
-config EXPERIMENTAL
-	bool "Prompt for development and/or incomplete code/drivers"
-	---help---
-	  Some of the various things that Linux supports (such as network
-	  drivers, file systems, network protocols, etc.) can be in a state
-	  of development where the functionality, stability, or the level of
-	  testing is not yet high enough for general use. This is usually
-	  known as the "alpha-test" phase among developers. If a feature is
-	  currently in alpha-test, then the developers usually discourage
-	  uninformed widespread use of this feature by the general public to
-	  avoid "Why doesn't this work?" type mail messages. However, active
-	  testing and use of these systems is welcomed. Just be aware that it
-	  may not meet the normal level of reliability or it may fail to work
-	  in some special cases. Detailed bug reports from people familiar
-	  with the kernel internals are usually welcomed by the developers
-	  (before submitting bug reports, please read the documents
-	  <file:README>, <file:MAINTAINERS>, <file:REPORTING-BUGS>,
-	  <file:Documentation/BUG-HUNTING>, and
-	  <file:Documentation/oops-tracing.txt> in the kernel source).
-
-	  This option will also make obsoleted drivers available. These are
-	  drivers that have been replaced by something else, and/or are
-	  scheduled to be removed in a future kernel release.
-
-	  Unless you intend to help test and develop a feature or driver that
-	  falls into this category, or you have a situation that requires
-	  using these features, you should probably say N here, which will
-	  cause the configurator to present you with fewer choices. If
-	  you say Y here, you will be offered the choice of using features or
-	  drivers that are currently considered to be in the alpha-test phase.
-
 config BROKEN
 	bool
 
@@ -247,7 +212,7 @@ config SYSVIPC_SYSCTL
 
 config POSIX_MQUEUE
 	bool "POSIX Message Queues"
-	depends on NET && EXPERIMENTAL
+	depends on NET
 	---help---
 	  POSIX variant of message queues is a part of IPC. In POSIX message
 	  queues every message has a priority which decides about succession
@@ -326,10 +291,13 @@ source "kernel/time/Kconfig"
 
 menu "CPU/Task time and stats accounting"
 
+config VIRT_CPU_ACCOUNTING
+	bool
+
 choice
 	prompt "Cputime accounting"
 	default TICK_CPU_ACCOUNTING if !PPC64
-	default VIRT_CPU_ACCOUNTING if PPC64
+	default VIRT_CPU_ACCOUNTING_NATIVE if PPC64
 
 # Kind of a stub config for the pure tick based cputime accounting
 config TICK_CPU_ACCOUNTING
@@ -342,9 +310,10 @@ config TICK_CPU_ACCOUNTING
 
 	  If unsure, say Y.
 
-config VIRT_CPU_ACCOUNTING
+config VIRT_CPU_ACCOUNTING_NATIVE
 	bool "Deterministic task and CPU time accounting"
 	depends on HAVE_VIRT_CPU_ACCOUNTING
+	select VIRT_CPU_ACCOUNTING
 	help
 	  Select this option to enable more accurate task and CPU time
 	  accounting.  This is done by reading a CPU counter on each
@@ -354,6 +323,23 @@ config VIRT_CPU_ACCOUNTING
 	  this also enables accounting of stolen time on logically-partitioned
 	  systems.
 
+config VIRT_CPU_ACCOUNTING_GEN
+	bool "Full dynticks CPU time accounting"
+	depends on HAVE_CONTEXT_TRACKING && 64BIT
+	select VIRT_CPU_ACCOUNTING
+	select CONTEXT_TRACKING
+	help
+	  Select this option to enable task and CPU time accounting on full
+	  dynticks systems. This accounting is implemented by watching every
+	  kernel-user boundaries using the context tracking subsystem.
+	  The accounting is thus performed at the expense of some significant
+	  overhead.
+
+	  For now this is only useful if you are working on the full
+	  dynticks subsystem development.
+
+	  If unsure, say N.
+
 config IRQ_TIME_ACCOUNTING
 	bool "Fine granularity task level IRQ time accounting"
 	depends on HAVE_IRQ_TIME_ACCOUNTING
@@ -393,7 +379,7 @@ config BSD_PROCESS_ACCT_V3
 	  at <http://www.gnu.org/software/acct/>.
 
 config TASKSTATS
-	bool "Export task/process statistics through netlink (EXPERIMENTAL)"
+	bool "Export task/process statistics through netlink"
 	depends on NET
 	default n
 	help
@@ -406,7 +392,7 @@ config TASKSTATS
 	  Say N if unsure.
 
 config TASK_DELAY_ACCT
-	bool "Enable per-task delay accounting (EXPERIMENTAL)"
+	bool "Enable per-task delay accounting"
 	depends on TASKSTATS
 	help
 	  Collect information on time spent by a task waiting for system
@@ -417,7 +403,7 @@ config TASK_DELAY_ACCT
 	  Say N if unsure.
 
 config TASK_XACCT
-	bool "Enable extended accounting over taskstats (EXPERIMENTAL)"
+	bool "Enable extended accounting over taskstats"
 	depends on TASKSTATS
 	help
 	  Collect extended task accounting data and send the data
@@ -426,7 +412,7 @@ config TASK_XACCT
 	  Say N if unsure.
 
 config TASK_IO_ACCOUNTING
-	bool "Enable per-task storage I/O accounting (EXPERIMENTAL)"
+	bool "Enable per-task storage I/O accounting"
 	depends on TASK_XACCT
 	help
 	  Collect information on the number of bytes of storage I/O which this
@@ -453,7 +439,7 @@ config TREE_RCU
 
 config TREE_PREEMPT_RCU
 	bool "Preemptible tree-based hierarchical RCU"
-	depends on PREEMPT && SMP
+	depends on PREEMPT
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or
@@ -461,6 +447,8 @@ config TREE_PREEMPT_RCU
 	  is also required.  It also scales down nicely to
 	  smaller systems.
 
+	  Select this option if you are unsure.
+
 config TINY_RCU
 	bool "UP-only small-memory-footprint RCU"
 	depends on !PREEMPT && !SMP
@@ -486,35 +474,43 @@ config PREEMPT_RCU
 	  This option enables preemptible-RCU code that is common between
 	  the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
 
+config RCU_STALL_COMMON
+	def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE )
+	help
+	  This option enables RCU CPU stall code that is common between
+	  the TINY and TREE variants of RCU.  The purpose is to allow
+	  the tiny variants to disable RCU CPU stall warnings, while
+	  making these warnings mandatory for the tree variants.
+
+config CONTEXT_TRACKING
+       bool
+
 config RCU_USER_QS
 	bool "Consider userspace as in RCU extended quiescent state"
-	depends on HAVE_RCU_USER_QS && SMP
+	depends on HAVE_CONTEXT_TRACKING && SMP
+	select CONTEXT_TRACKING
 	help
 	  This option sets hooks on kernel / userspace boundaries and
 	  puts RCU in extended quiescent state when the CPU runs in
 	  userspace. It means that when a CPU runs in userspace, it is
 	  excluded from the global RCU state machine and thus doesn't
-	  to keep the timer tick on for RCU.
+	  try to keep the timer tick on for RCU.
 
 	  Unless you want to hack and help the development of the full
-	  tickless feature, you shouldn't enable this option. It adds
-	  unnecessary overhead.
+	  dynticks mode, you shouldn't enable this option.  It also
+	  adds unnecessary overhead.
 
 	  If unsure say N
 
-config RCU_USER_QS_FORCE
-	bool "Force userspace extended QS by default"
-	depends on RCU_USER_QS
+config CONTEXT_TRACKING_FORCE
+	bool "Force context tracking"
+	depends on CONTEXT_TRACKING
 	help
-	  Set the hooks in user/kernel boundaries by default in order to
-	  test this feature that treats userspace as an extended quiescent
-	  state until we have a real user like a full adaptive nohz option.
-
-	  Unless you want to hack and help the development of the full
-	  tickless feature, you shouldn't enable this option. It adds
-	  unnecessary overhead.
-
-	  If unsure say N
+	  Probe on user/kernel boundaries by default in order to
+	  test the features that rely on it such as userspace RCU extended
+	  quiescent states.
+	  This test is there for debugging until we have a real user like the
+	  full dynticks mode.
 
 config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
@@ -582,14 +578,13 @@ config RCU_FAST_NO_HZ
 	depends on NO_HZ && SMP
 	default n
 	help
-	  This option causes RCU to attempt to accelerate grace periods
-	  in order to allow CPUs to enter dynticks-idle state more
-	  quickly.  On the other hand, this option increases the overhead
-	  of the dynticks-idle checking, particularly on systems with
-	  large numbers of CPUs.
+	  This option causes RCU to attempt to accelerate grace periods in
+	  order to allow CPUs to enter dynticks-idle state more quickly.
+	  On the other hand, this option increases the overhead of the
+	  dynticks-idle checking, thus degrading scheduling latency.
 
-	  Say Y if energy efficiency is critically important, particularly
-	  	if you have relatively few CPUs.
+	  Say Y if energy efficiency is critically important, and you don't
+	  	care about real-time response.
 
 	  Say N if you are unsure.
 
@@ -655,6 +650,28 @@ config RCU_BOOST_DELAY
 
 	  Accept the default if unsure.
 
+config RCU_NOCB_CPU
+	bool "Offload RCU callback processing from boot-selected CPUs"
+	depends on TREE_RCU || TREE_PREEMPT_RCU
+	default n
+	help
+	  Use this option to reduce OS jitter for aggressive HPC or
+	  real-time workloads.	It can also be used to offload RCU
+	  callback invocation to energy-efficient CPUs in battery-powered
+	  asymmetric multiprocessors.
+
+	  This option offloads callback invocation from the set of
+	  CPUs specified at boot time by the rcu_nocbs parameter.
+	  For each such CPU, a kthread ("rcuoN") will be created to
+	  invoke callbacks, where the "N" is the CPU being offloaded.
+	  Nothing prevents this kthread from running on the specified
+	  CPUs, but (1) the kthreads may be preempted between each
+	  callback, and (2) affinity or cgroups can be used to force
+	  the kthreads to run on whatever set of CPUs is desired.
+
+	  Say Y here if you want reduced OS jitter on selected CPUs.
+	  Say N here if you are unsure.
+
 endmenu # "RCU Subsystem"
 
 config IKCONFIG
@@ -696,6 +713,50 @@ config LOG_BUF_SHIFT
 config HAVE_UNSTABLE_SCHED_CLOCK
 	bool
 
+#
+# For architectures that want to enable the support for NUMA-affine scheduler
+# balancing logic:
+#
+config ARCH_SUPPORTS_NUMA_BALANCING
+	bool
+
+# For architectures that (ab)use NUMA to represent different memory regions
+# all cpu-local but of different latencies, such as SuperH.
+#
+config ARCH_WANT_NUMA_VARIABLE_LOCALITY
+	bool
+
+#
+# For architectures that are willing to define _PAGE_NUMA as _PAGE_PROTNONE
+config ARCH_WANTS_PROT_NUMA_PROT_NONE
+	bool
+
+config ARCH_USES_NUMA_PROT_NONE
+	bool
+	default y
+	depends on ARCH_WANTS_PROT_NUMA_PROT_NONE
+	depends on NUMA_BALANCING
+
+config NUMA_BALANCING_DEFAULT_ENABLED
+	bool "Automatically enable NUMA aware memory/task placement"
+	default y
+	depends on NUMA_BALANCING
+	help
+	  If set, autonumic NUMA balancing will be enabled if running on a NUMA
+	  machine.
+
+config NUMA_BALANCING
+	bool "Memory placement aware NUMA scheduler"
+	depends on ARCH_SUPPORTS_NUMA_BALANCING
+	depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
+	depends on SMP && NUMA && MIGRATION
+	help
+	  This option adds support for automatic NUMA aware memory/task placement.
+	  The mechanism is quite primitive and is based on migrating memory when
+	  it is references to the node the task is running on.
+
+	  This system will be inactive on UMA systems.
+
 menuconfig CGROUPS
 	boolean "Control Group support"
 	depends on EVENTFD
@@ -815,9 +876,9 @@ config MEMCG_SWAP_ENABLED
 	  select this option (if, for some reason, they need to disable it
 	  then swapaccount=0 does the trick).
 config MEMCG_KMEM
-	bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)"
-	depends on MEMCG && EXPERIMENTAL
-	default n
+	bool "Memory Resource Controller Kernel Memory accounting"
+	depends on MEMCG
+	depends on SLUB || SLAB
 	help
 	  The Kernel Memory extension for Memory Resource Controller can limit
 	  the amount of memory used by kernel objects in the system. Those are
@@ -828,7 +889,7 @@ config MEMCG_KMEM
 
 config CGROUP_HUGETLB
 	bool "HugeTLB Resource Controller for Control Groups"
-	depends on RESOURCE_COUNTERS && HUGETLB_PAGE && EXPERIMENTAL
+	depends on RESOURCE_COUNTERS && HUGETLB_PAGE
 	default n
 	help
 	  Provides a cgroup Resource Controller for HugeTLB pages.
@@ -867,7 +928,6 @@ config FAIR_GROUP_SCHED
 
 config CFS_BANDWIDTH
 	bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
-	depends on EXPERIMENTAL
 	depends on FAIR_GROUP_SCHED
 	default n
 	help
@@ -879,7 +939,6 @@ config CFS_BANDWIDTH
 
 config RT_GROUP_SCHED
 	bool "Group scheduling for SCHED_RR/FIFO"
-	depends on EXPERIMENTAL
 	depends on CGROUP_SCHED
 	default n
 	help
@@ -961,8 +1020,7 @@ config IPC_NS
 	  different IPC objects in different namespaces.
 
 config USER_NS
-	bool "User namespace (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	bool "User namespace"
 	depends on UIDGID_CONVERTED
 	select UIDGID_STRICT_TYPE_CHECKS
 
@@ -970,6 +1028,13 @@ config USER_NS
 	help
 	  This allows containers, i.e. vservers, to use user namespaces
 	  to provide different user info for different servers.
+
+	  When user namespaces are enabled in the kernel it is
+	  recommended that the MEMCG and MEMCG_KMEM options also be
+	  enabled and that user-space use the memory control groups to
+	  limit the amount of memory a memory unprivileged users can
+	  use.
+
 	  If unsure, say N.
 
 config PID_NS
@@ -998,22 +1063,7 @@ config UIDGID_CONVERTED
 	bool
 	default y
 
-	# Networking
-	depends on NET_9P = n
-
 	# Filesystems
-	depends on 9P_FS = n
-	depends on AFS_FS = n
-	depends on AUTOFS4_FS = n
-	depends on CEPH_FS = n
-	depends on CIFS = n
-	depends on CODA_FS = n
-	depends on FUSE_FS = n
-	depends on GFS2_FS = n
-	depends on NCP_FS = n
-	depends on NFSD = n
-	depends on NFS_FS = n
-	depends on OCFS2_FS = n
 	depends on XFS_FS = n
 
 config UIDGID_STRICT_TYPE_CHECKS
@@ -1119,7 +1169,7 @@ config CC_OPTIMIZE_FOR_SIZE
 	  Enabling this option will pass "-Os" instead of "-O2" to gcc
 	  resulting in a smaller kernel.
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 config SYSCTL
 	bool
@@ -1169,6 +1219,21 @@ config SYSCTL_EXCEPTION_TRACE
 	help
 	  Enable support for /proc/sys/debug/exception-trace.
 
+config SYSCTL_ARCH_UNALIGN_NO_WARN
+	bool
+	help
+	  Enable support for /proc/sys/kernel/ignore-unaligned-usertrap
+	  Allows arch to define/use @no_unaligned_warning to possibly warn
+	  about unaligned access emulation going on under the hood.
+
+config SYSCTL_ARCH_UNALIGN_ALLOW
+	bool
+	help
+	  Enable support for /proc/sys/kernel/unaligned-trap
+	  Allows arches to define/use @unaligned_enabled to runtime toggle
+	  the unaligned access emulation.
+	  see arch/parisc/kernel/unaligned.c for reference
+
 config KALLSYMS
 	 bool "Load all symbols for debugging/ksymoops" if EXPERT
 	 default y
@@ -1200,6 +1265,7 @@ config HOTPLUG
 config PRINTK
 	default y
 	bool "Enable support for printk" if EXPERT
+	select IRQ_WORK
 	help
 	  This option enables normal printk support. Removing it
 	  eliminates most of the message strings from the kernel image
@@ -1545,7 +1611,7 @@ config MODULE_UNLOAD
 
 config MODULE_FORCE_UNLOAD
 	bool "Forced module unloading"
-	depends on MODULE_UNLOAD && EXPERIMENTAL
+	depends on MODULE_UNLOAD
 	help
 	  This option allows you to force a module to unload, even if the
 	  kernel believes it is unsafe: the kernel will remove the module
@@ -1602,6 +1668,17 @@ config MODULE_SIG_FORCE
 	  Reject unsigned modules or signed modules for which we don't have a
 	  key.  Without this, such modules will simply taint the kernel.
 
+config MODULE_SIG_ALL
+	bool "Automatically sign all modules"
+	default y
+	depends on MODULE_SIG
+	help
+	  Sign all modules during make modules_install. Without this option,
+	  modules must be signed manually, using the scripts/sign-file tool.
+
+comment "Do not forget to sign required modules with scripts/sign-file"
+	depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL
+
 choice
 	prompt "Which hash algorithm should modules be signed with?"
 	depends on MODULE_SIG
@@ -1634,6 +1711,15 @@ config MODULE_SIG_SHA512
 
 endchoice
 
+config MODULE_SIG_HASH
+	string
+	depends on MODULE_SIG
+	default "sha1" if MODULE_SIG_SHA1
+	default "sha224" if MODULE_SIG_SHA224
+	default "sha256" if MODULE_SIG_SHA256
+	default "sha384" if MODULE_SIG_SHA384
+	default "sha512" if MODULE_SIG_SHA512
+
 endif # MODULES
 
 config INIT_ALL_POSSIBLE
diff --git a/init/do_mounts.c b/init/do_mounts.c
index f8a66424360d..a2b49f2c1bd8 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -69,23 +69,28 @@ __setup("ro", readonly);
 __setup("rw", readwrite);
 
 #ifdef CONFIG_BLOCK
+struct uuidcmp {
+	const char *uuid;
+	int len;
+};
+
 /**
  * match_dev_by_uuid - callback for finding a partition using its uuid
  * @dev:	device passed in by the caller
- * @data:	opaque pointer to a 36 byte char array with a UUID
+ * @data:	opaque pointer to the desired struct uuidcmp to match
  *
  * Returns 1 if the device matches, and 0 otherwise.
  */
-static int match_dev_by_uuid(struct device *dev, void *data)
+static int match_dev_by_uuid(struct device *dev, const void *data)
 {
-	u8 *uuid = data;
+	const struct uuidcmp *cmp = data;
 	struct hd_struct *part = dev_to_part(dev);
 
 	if (!part->info)
 		goto no_match;
 
-	if (memcmp(uuid, part->info->uuid, sizeof(part->info->uuid)))
-			goto no_match;
+	if (strncasecmp(cmp->uuid, part->info->uuid, cmp->len))
+		goto no_match;
 
 	return 1;
 no_match:
@@ -95,7 +100,7 @@ no_match:
 
 /**
  * devt_from_partuuid - looks up the dev_t of a partition by its UUID
- * @uuid:	min 36 byte char array containing a hex ascii UUID
+ * @uuid:	char array containing ascii UUID
  *
  * The function will return the first partition which contains a matching
  * UUID value in its partition_meta_info struct.  This does not search
@@ -106,38 +111,41 @@ no_match:
  *
  * Returns the matching dev_t on success or 0 on failure.
  */
-static dev_t devt_from_partuuid(char *uuid_str)
+static dev_t devt_from_partuuid(const char *uuid_str)
 {
 	dev_t res = 0;
+	struct uuidcmp cmp;
 	struct device *dev = NULL;
-	u8 uuid[16];
 	struct gendisk *disk;
 	struct hd_struct *part;
 	int offset = 0;
+	bool clear_root_wait = false;
+	char *slash;
 
-	if (strlen(uuid_str) < 36)
-		goto done;
+	cmp.uuid = uuid_str;
 
+	slash = strchr(uuid_str, '/');
 	/* Check for optional partition number offset attributes. */
-	if (uuid_str[36]) {
+	if (slash) {
 		char c = 0;
 		/* Explicitly fail on poor PARTUUID syntax. */
-		if (sscanf(&uuid_str[36],
-			   "/PARTNROFF=%d%c", &offset, &c) != 1) {
-			printk(KERN_ERR "VFS: PARTUUID= is invalid.\n"
-			 "Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n");
-			if (root_wait)
-				printk(KERN_ERR
-				     "Disabling rootwait; root= is invalid.\n");
-			root_wait = 0;
+		if (sscanf(slash + 1,
+			   "PARTNROFF=%d%c", &offset, &c) != 1) {
+			clear_root_wait = true;
 			goto done;
 		}
+		cmp.len = slash - uuid_str;
+	} else {
+		cmp.len = strlen(uuid_str);
 	}
 
-	/* Pack the requested UUID in the expected format. */
-	part_pack_uuid(uuid_str, uuid);
+	if (!cmp.len) {
+		clear_root_wait = true;
+		goto done;
+	}
 
-	dev = class_find_device(&block_class, NULL, uuid, &match_dev_by_uuid);
+	dev = class_find_device(&block_class, NULL, &cmp,
+				&match_dev_by_uuid);
 	if (!dev)
 		goto done;
 
@@ -158,6 +166,13 @@ static dev_t devt_from_partuuid(char *uuid_str)
 no_offset:
 	put_device(dev);
 done:
+	if (clear_root_wait) {
+		pr_err("VFS: PARTUUID= is invalid.\n"
+		       "Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n");
+		if (root_wait)
+			pr_err("Disabling rootwait; root= is invalid.\n");
+		root_wait = 0;
+	}
 	return res;
 }
 #endif
@@ -174,6 +189,10 @@ done:
  *	   used when disk name of partitioned disk ends on a digit.
  *	6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the
  *	   unique id of a partition if the partition table provides it.
+ *	   The UUID may be either an EFI/GPT UUID, or refer to an MSDOS
+ *	   partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero-
+ *	   filled hex representation of the 32-bit "NT disk signature", and PP
+ *	   is a zero-filled hex representation of the 1-based partition number.
  *	7) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to
  *	   a partition with a known unique id.
  *
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 5e4ded51788e..a32ec1ce882b 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -36,6 +36,10 @@ __setup("noinitrd", no_initrd);
 static int init_linuxrc(struct subprocess_info *info, struct cred *new)
 {
 	sys_unshare(CLONE_FS | CLONE_FILES);
+	/* stdin/stdout/stderr for /linuxrc */
+	sys_open("/dev/console", O_RDWR, 0);
+	sys_dup(0);
+	sys_dup(0);
 	/* move initrd over / and chdir/chroot in initrd root */
 	sys_chdir("/root");
 	sys_mount(".", "/", NULL, MS_MOVE, NULL);
@@ -57,6 +61,9 @@ static void __init handle_initrd(void)
 	sys_mkdir("/old", 0700);
 	sys_chdir("/old");
 
+	/* try loading default modules from initrd */
+	load_default_modules();
+
 	/*
 	 * In case that a resume from disk is carried out by linuxrc or one of
 	 * its children, we need to tell the freezer not to wait for us.
diff --git a/init/init_task.c b/init/init_task.c
index 8b2f3996b035..ba0a7f362d9e 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -2,6 +2,8 @@
 #include <linux/export.h>
 #include <linux/mqueue.h>
 #include <linux/sched.h>
+#include <linux/sched/sysctl.h>
+#include <linux/sched/rt.h>
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
diff --git a/init/initramfs.c b/init/initramfs.c
index 84c6bf111300..a67ef9dbda9d 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -592,7 +592,7 @@ static int __init populate_rootfs(void)
 			initrd_end - initrd_start);
 		if (!err) {
 			free_initrd();
-			return 0;
+			goto done;
 		} else {
 			clean_rootfs();
 			unpack_to_rootfs(__initramfs_start, __initramfs_size);
@@ -607,6 +607,7 @@ static int __init populate_rootfs(void)
 			sys_close(fd);
 			free_initrd();
 		}
+	done:
 #else
 		printk(KERN_INFO "Unpacking initramfs...\n");
 		err = unpack_to_rootfs((char *)initrd_start,
@@ -615,6 +616,11 @@ static int __init populate_rootfs(void)
 			printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err);
 		free_initrd();
 #endif
+		/*
+		 * Try loading default modules from initramfs.  This gives
+		 * us a chance to load before device_initcalls.
+		 */
+		load_default_modules();
 	}
 	return 0;
 }
diff --git a/init/main.c b/init/main.c
index e33e09df3cbc..63534a141b4e 100644
--- a/init/main.c
+++ b/init/main.c
@@ -70,6 +70,8 @@
 #include <linux/perf_event.h>
 #include <linux/file.h>
 #include <linux/ptrace.h>
+#include <linux/blkdev.h>
+#include <linux/elevator.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -604,7 +606,7 @@ asmlinkage void __init start_kernel(void)
 	pidmap_init();
 	anon_vma_init();
 #ifdef CONFIG_X86
-	if (efi_enabled)
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
 #endif
 	thread_info_cache_init();
@@ -632,7 +634,7 @@ asmlinkage void __init start_kernel(void)
 	acpi_early_init(); /* before LAPIC and SMP init */
 	sfi_init_late();
 
-	if (efi_enabled) {
+	if (efi_enabled(EFI_RUNTIME_SERVICES)) {
 		efi_late_init();
 		efi_free_boot_services();
 	}
@@ -794,13 +796,26 @@ static void __init do_pre_smp_initcalls(void)
 		do_one_initcall(*fn);
 }
 
+/*
+ * This function requests modules which should be loaded by default and is
+ * called twice right after initrd is mounted and right before init is
+ * exec'd.  If such modules are on either initrd or rootfs, they will be
+ * loaded before control is passed to userland.
+ */
+void __init load_default_modules(void)
+{
+	load_default_elevator_module();
+}
+
 static int run_init_process(const char *init_filename)
 {
 	argv_init[0] = init_filename;
-	return kernel_execve(init_filename, argv_init, envp_init);
+	return do_execve(init_filename,
+		(const char __user *const __user *)argv_init,
+		(const char __user *const __user *)envp_init);
 }
 
-static void __init kernel_init_freeable(void);
+static noinline void __init kernel_init_freeable(void);
 
 static int __ref kernel_init(void *unused)
 {
@@ -812,7 +827,6 @@ static int __ref kernel_init(void *unused)
 	system_state = SYSTEM_RUNNING;
 	numa_default_policy();
 
-	current->signal->flags |= SIGNAL_UNKILLABLE;
 	flush_delayed_fput();
 
 	if (ramdisk_execute_command) {
@@ -844,7 +858,7 @@ static int __ref kernel_init(void *unused)
 	      "See Linux Documentation/init.txt for guidance.");
 }
 
-static void __init kernel_init_freeable(void)
+static noinline void __init kernel_init_freeable(void)
 {
 	/*
 	 * Wait until kthreadd is all set-up.
@@ -857,7 +871,7 @@ static void __init kernel_init_freeable(void)
 	/*
 	 * init can allocate pages on any node
 	 */
-	set_mems_allowed(node_states[N_HIGH_MEMORY]);
+	set_mems_allowed(node_states[N_MEMORY]);
 	/*
 	 * init can run on any cpu.
 	 */
@@ -899,4 +913,7 @@ static void __init kernel_init_freeable(void)
 	 * we're essentially up and running. Get rid of the
 	 * initmem segments and start the user-mode stuff..
 	 */
+
+	/* rootfs is available now, try loading default modules */
+	load_default_modules();
 }
diff --git a/init/version.c b/init/version.c
index 86fe0ccb997a..58170f18912d 100644
--- a/init/version.c
+++ b/init/version.c
@@ -12,6 +12,7 @@
 #include <linux/utsname.h>
 #include <generated/utsrelease.h>
 #include <linux/version.h>
+#include <linux/proc_fs.h>
 
 #ifndef CONFIG_KALLSYMS
 #define version(a) Version_ ## a
@@ -34,6 +35,7 @@ struct uts_namespace init_uts_ns = {
 		.domainname	= UTS_DOMAINNAME,
 	},
 	.user_ns = &init_user_ns,
+	.proc_inum = PROC_UTS_INIT_INO,
 };
 EXPORT_SYMBOL_GPL(init_uts_ns);