Merge tag 'v3.5-rc1'

Linux 3.5-rc1

Conflicts:
	net/ceph/messenger.c

10 files changed, 364 insertions, 80 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 3f42cd66f0f8..d07dcf9fc8a9 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -27,6 +27,9 @@ config IRQ_WORK
 	bool
 	depends on HAVE_IRQ_WORK
 
+config BUILDTIME_EXTABLE_SORT
+	bool
+
 menu "General setup"
 
 config EXPERIMENTAL
@@ -164,7 +167,7 @@ config KERNEL_BZIP2
 	depends on HAVE_KERNEL_BZIP2
 	help
 	  Its compression ratio and speed is intermediate.
-	  Decompression speed is slowest among the three.  The kernel
+	  Decompression speed is slowest among the choices.  The kernel
 	  size is about 10% smaller with bzip2, in comparison to gzip.
 	  Bzip2 uses a large amount of memory. For modern kernels you
 	  will need at least 8MB RAM or more for booting.
@@ -173,10 +176,9 @@ config KERNEL_LZMA
 	bool "LZMA"
 	depends on HAVE_KERNEL_LZMA
 	help
-	  The most recent compression algorithm.
-	  Its ratio is best, decompression speed is between the other
-	  two. Compression is slowest.	The kernel size is about 33%
-	  smaller with LZMA in comparison to gzip.
+	  This compression algorithm's ratio is best.  Decompression speed
+	  is between gzip and bzip2.  Compression is slowest.
+	  The kernel size is about 33% smaller with LZMA in comparison to gzip.
 
 config KERNEL_XZ
 	bool "XZ"
@@ -197,7 +199,7 @@ config KERNEL_LZO
 	bool "LZO"
 	depends on HAVE_KERNEL_LZO
 	help
-	  Its compression ratio is the poorest among the 4. The kernel
+	  Its compression ratio is the poorest among the choices. The kernel
 	  size is about 10% bigger than gzip; however its speed
 	  (both compression and decompression) is the fastest.
 
@@ -387,6 +389,7 @@ config AUDIT_LOGINUID_IMMUTABLE
 	  but may not be backwards compatible with older init systems.
 
 source "kernel/irq/Kconfig"
+source "kernel/time/Kconfig"
 
 menu "RCU Subsystem"
 
@@ -438,15 +441,6 @@ config PREEMPT_RCU
 	  This option enables preemptible-RCU code that is common between
 	  the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
 
-config RCU_TRACE
-	bool "Enable tracing for RCU"
-	help
-	  This option provides tracing in RCU which presents stats
-	  in debugfs for debugging RCU implementation.
-
-	  Say Y here if you want to enable RCU tracing
-	  Say N if you are unsure.
-
 config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
 	range 2 64 if 64BIT
@@ -467,6 +461,33 @@ config RCU_FANOUT
 	  Select a specific number if testing RCU itself.
 	  Take the default if unsure.
 
+config RCU_FANOUT_LEAF
+	int "Tree-based hierarchical RCU leaf-level fanout value"
+	range 2 RCU_FANOUT if 64BIT
+	range 2 RCU_FANOUT if !64BIT
+	depends on TREE_RCU || TREE_PREEMPT_RCU
+	default 16
+	help
+	  This option controls the leaf-level fanout of hierarchical
+	  implementations of RCU, and allows trading off cache misses
+	  against lock contention.  Systems that synchronize their
+	  scheduling-clock interrupts for energy-efficiency reasons will
+	  want the default because the smaller leaf-level fanout keeps
+	  lock contention levels acceptably low.  Very large systems
+	  (hundreds or thousands of CPUs) will instead want to set this
+	  value to the maximum value possible in order to reduce the
+	  number of cache misses incurred during RCU's grace-period
+	  initialization.  These systems tend to run CPU-bound, and thus
+	  are not helped by synchronized interrupts, and thus tend to
+	  skew them, which reduces lock contention enough that large
+	  leaf-level fanouts work well.
+
+	  Select a specific number if testing RCU itself.
+
+	  Select the maximum permissible value for large systems.
+
+	  Take the default if unsure.
+
 config RCU_FANOUT_EXACT
 	bool "Disable tree-based hierarchical RCU auto-balancing"
 	depends on TREE_RCU || TREE_PREEMPT_RCU
@@ -524,10 +545,25 @@ config RCU_BOOST_PRIO
 	depends on RCU_BOOST
 	default 1
 	help
-	  This option specifies the real-time priority to which preempted
-	  RCU readers are to be boosted.  If you are working with CPU-bound
-	  real-time applications, you should specify a priority higher then
-	  the highest-priority CPU-bound application.
+	  This option specifies the real-time priority to which long-term
+	  preempted RCU readers are to be boosted.  If you are working
+	  with a real-time application that has one or more CPU-bound
+	  threads running at a real-time priority level, you should set
+	  RCU_BOOST_PRIO to a priority higher then the highest-priority
+	  real-time CPU-bound thread.  The default RCU_BOOST_PRIO value
+	  of 1 is appropriate in the common case, which is real-time
+	  applications that do not have any CPU-bound threads.
+
+	  Some real-time applications might not have a single real-time
+	  thread that saturates a given CPU, but instead might have
+	  multiple real-time threads that, taken together, fully utilize
+	  that CPU.  In this case, you should set RCU_BOOST_PRIO to
+	  a priority higher than the lowest-priority thread that is
+	  conspiring to prevent the CPU from running any non-real-time
+	  tasks.  For example, if one thread at priority 10 and another
+	  thread at priority 5 are between themselves fully consuming
+	  the CPU time on a given CPU, then RCU_BOOST_PRIO should be
+	  set to priority 6 or higher.
 
 	  Specify the real-time priority, or take the default if unsure.
 
@@ -766,7 +802,7 @@ config RT_GROUP_SCHED
 endif #CGROUP_SCHED
 
 config BLK_CGROUP
-	tristate "Block IO controller"
+	bool "Block IO controller"
 	depends on BLOCK
 	default n
 	---help---
@@ -837,7 +873,10 @@ config IPC_NS
 config USER_NS
 	bool "User namespace (EXPERIMENTAL)"
 	depends on EXPERIMENTAL
-	default y
+	depends on UIDGID_CONVERTED
+	select UIDGID_STRICT_TYPE_CHECKS
+
+	default n
 	help
 	  This allows containers, i.e. vservers, to use user namespaces
 	  to provide different user info for different servers.
@@ -861,6 +900,131 @@ config NET_NS
 
 endif # NAMESPACES
 
+config UIDGID_CONVERTED
+	# True if all of the selected software conmponents are known
+	# to have uid_t and gid_t converted to kuid_t and kgid_t
+	# where appropriate and are otherwise safe to use with
+	# the user namespace.
+	bool
+	default y
+
+	# List of kernel pieces that need user namespace work
+	# Features
+	depends on SYSVIPC = n
+	depends on IMA = n
+	depends on EVM = n
+	depends on KEYS = n
+	depends on AUDIT = n
+	depends on AUDITSYSCALL = n
+	depends on TASKSTATS = n
+	depends on TRACING = n
+	depends on FS_POSIX_ACL = n
+	depends on QUOTA = n
+	depends on QUOTACTL = n
+	depends on DEBUG_CREDENTIALS = n
+	depends on BSD_PROCESS_ACCT = n
+	depends on DRM = n
+	depends on PROC_EVENTS = n
+
+	# Networking
+	depends on NET = n
+	depends on NET_9P = n
+	depends on IPX = n
+	depends on PHONET = n
+	depends on NET_CLS_FLOW = n
+	depends on NETFILTER_XT_MATCH_OWNER = n
+	depends on NETFILTER_XT_MATCH_RECENT = n
+	depends on NETFILTER_XT_TARGET_LOG = n
+	depends on NETFILTER_NETLINK_LOG = n
+	depends on INET = n
+	depends on IPV6 = n
+	depends on IP_SCTP = n
+	depends on AF_RXRPC = n
+	depends on LLC2 = n
+	depends on NET_KEY = n
+	depends on INET_DIAG = n
+	depends on DNS_RESOLVER = n
+	depends on AX25 = n
+	depends on ATALK = n
+
+	# Filesystems
+	depends on USB_DEVICEFS = n
+	depends on USB_GADGETFS = n
+	depends on USB_FUNCTIONFS = n
+	depends on DEVTMPFS = n
+	depends on XENFS = n
+
+	depends on 9P_FS = n
+	depends on ADFS_FS = n
+	depends on AFFS_FS = n
+	depends on AFS_FS = n
+	depends on AUTOFS4_FS = n
+	depends on BEFS_FS = n
+	depends on BFS_FS = n
+	depends on BTRFS_FS = n
+	depends on CEPH_FS = n
+	depends on CIFS = n
+	depends on CODA_FS = n
+	depends on CONFIGFS_FS = n
+	depends on CRAMFS = n
+	depends on DEBUG_FS = n
+	depends on ECRYPT_FS = n
+	depends on EFS_FS = n
+	depends on EXOFS_FS = n
+	depends on FAT_FS = n
+	depends on FUSE_FS = n
+	depends on GFS2_FS = n
+	depends on HFS_FS = n
+	depends on HFSPLUS_FS = n
+	depends on HPFS_FS = n
+	depends on HUGETLBFS = n
+	depends on ISO9660_FS = n
+	depends on JFFS2_FS = n
+	depends on JFS_FS = n
+	depends on LOGFS = n
+	depends on MINIX_FS = n
+	depends on NCP_FS = n
+	depends on NFSD = n
+	depends on NFS_FS = n
+	depends on NILFS2_FS = n
+	depends on NTFS_FS = n
+	depends on OCFS2_FS = n
+	depends on OMFS_FS = n
+	depends on QNX4FS_FS = n
+	depends on QNX6FS_FS = n
+	depends on REISERFS_FS = n
+	depends on SQUASHFS = n
+	depends on SYSV_FS = n
+	depends on UBIFS_FS = n
+	depends on UDF_FS = n
+	depends on UFS_FS = n
+	depends on VXFS_FS = n
+	depends on XFS_FS = n
+
+	depends on !UML || HOSTFS = n
+
+	# The rare drivers that won't build
+	depends on AIRO = n
+	depends on AIRO_CS = n
+	depends on TUN = n
+	depends on INFINIBAND_QIB = n
+	depends on BLK_DEV_LOOP = n
+	depends on ANDROID_BINDER_IPC = n
+
+	# Security modules
+	depends on SECURITY_TOMOYO = n
+	depends on SECURITY_APPARMOR = n
+
+config UIDGID_STRICT_TYPE_CHECKS
+	bool "Require conversions between uid/gids and their internal representation"
+	depends on UIDGID_CONVERTED
+	default n
+	help
+	 While the nececessary conversions are being added to all subsystems this option allows
+	 the code to continue to build for unconverted subsystems.
+
+	 Say Y here if you want the strict type checking enabled
+
 config SCHED_AUTOGROUP
 	bool "Automatic process group scheduling"
 	select EVENTFD
@@ -1165,7 +1329,7 @@ menu "Kernel Performance Events And Counters"
 
 config PERF_EVENTS
 	bool "Kernel performance events and counters"
-	default y if (PROFILING || PERF_COUNTERS)
+	default y if PROFILING
 	depends on HAVE_PERF_EVENTS
 	select ANON_INODES
 	select IRQ_WORK
@@ -1192,18 +1356,6 @@ config PERF_EVENTS
 
 	  Say Y if unsure.
 
-config PERF_COUNTERS
-	bool "Kernel performance counters (old config option)"
-	depends on HAVE_PERF_EVENTS
-	help
-	  This config has been obsoleted by the PERF_EVENTS
-	  config option - please see that one for details.
-
-	  It has no effect on the kernel whether you enable
-	  it or not, it is a compatibility placeholder.
-
-	  Say N if unsure.
-
 config DEBUG_PERF_USE_VMALLOC
 	default n
 	bool "Debug: use vmalloc to back perf mmap() buffers"
@@ -1423,8 +1575,8 @@ endif # MODULES
 config INIT_ALL_POSSIBLE
 	bool
 	help
-	  Back when each arch used to define their own cpu_online_map and
-	  cpu_possible_map, some of them chose to initialize cpu_possible_map
+	  Back when each arch used to define their own cpu_online_mask and
+	  cpu_possible_mask, some of them chose to initialize cpu_possible_mask
 	  with all 1s, and others with all 0s.  When they were centralised,
 	  it was better to provide this option than to break all the archs
 	  and have several arch maintainers pursuing me down dark alleys.
diff --git a/init/Makefile b/init/Makefile
index 0bf677aa0872..7bc47ee31c36 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -10,6 +10,10 @@ obj-$(CONFIG_BLK_DEV_INITRD)   += initramfs.o
 endif
 obj-$(CONFIG_GENERIC_CALIBRATE_DELAY) += calibrate.o
 
+ifneq ($(CONFIG_ARCH_INIT_TASK),y)
+obj-y                          += init_task.o
+endif
+
 mounts-y			:= do_mounts.o
 mounts-$(CONFIG_BLK_DEV_RAM)	+= do_mounts_rd.o
 mounts-$(CONFIG_BLK_DEV_INITRD)	+= do_mounts_initrd.o
diff --git a/init/calibrate.c b/init/calibrate.c
index 5f117ca9e069..fda0a7b0f06c 100644
--- a/init/calibrate.c
+++ b/init/calibrate.c
@@ -267,7 +267,8 @@ void __cpuinit calibrate_delay(void)
 
 	if (per_cpu(cpu_loops_per_jiffy, this_cpu)) {
 		lpj = per_cpu(cpu_loops_per_jiffy, this_cpu);
-		pr_info("Calibrating delay loop (skipped) "
+		if (!printed)
+			pr_info("Calibrating delay loop (skipped) "
 				"already calibrated this CPU");
 	} else if (preset_lpj) {
 		lpj = preset_lpj;
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 2974c8b3b351..d3f0aeed2d39 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -1,3 +1,13 @@
+/*
+ * Many of the syscalls used in this file expect some of the arguments
+ * to be __user pointers not __kernel pointers.  To limit the sparse
+ * noise, turn off sparse checking for this file.
+ */
+#ifdef __CHECKER__
+#undef __CHECKER__
+#warning "Sparse checking disabled for this file"
+#endif
+
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/ctype.h>
@@ -330,7 +340,7 @@ static int __init do_mount_root(char *name, char *fs, int flags, void *data)
 	if (err)
 		return err;
 
-	sys_chdir((const char __user __force *)"/root");
+	sys_chdir("/root");
 	s = current->fs->pwd.dentry->d_sb;
 	ROOT_DEV = s->s_dev;
 	printk(KERN_INFO
@@ -373,8 +383,8 @@ retry:
 #ifdef CONFIG_BLOCK
 		__bdevname(ROOT_DEV, b);
 #endif
-		printk("VFS: Cannot open root device \"%s\" or %s\n",
-				root_device_name, b);
+		printk("VFS: Cannot open root device \"%s\" or %s: error %d\n",
+				root_device_name, b, err);
 		printk("Please append a correct \"root=\" boot option; here are the available partitions:\n");
 
 		printk_all_partitions();
@@ -472,7 +482,7 @@ void __init change_floppy(char *fmt, ...)
 void __init mount_root(void)
 {
 #ifdef CONFIG_ROOT_NFS
-	if (MAJOR(ROOT_DEV) == UNNAMED_MAJOR) {
+	if (ROOT_DEV == Root_NFS) {
 		if (mount_nfs_root())
 			return;
 
@@ -556,5 +566,5 @@ void __init prepare_namespace(void)
 out:
 	devtmpfs_mount("dev");
 	sys_mount(".", "/", NULL, MS_MOVE, NULL);
-	sys_chroot((const char __user __force *)".");
+	sys_chroot(".");
 }
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 3098a38f3ae1..135959a276be 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -1,8 +1,17 @@
+/*
+ * Many of the syscalls used in this file expect some of the arguments
+ * to be __user pointers not __kernel pointers.  To limit the sparse
+ * noise, turn off sparse checking for this file.
+ */
+#ifdef __CHECKER__
+#undef __CHECKER__
+#warning "Sparse checking disabled for this file"
+#endif
+
 #include <linux/unistd.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/minix_fs.h>
-#include <linux/ext2_fs.h>
 #include <linux/romfs_fs.h>
 #include <linux/initrd.h>
 #include <linux/sched.h>
diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c
index 32c4799b8c91..8cb6db54285b 100644
--- a/init/do_mounts_md.c
+++ b/init/do_mounts_md.c
@@ -1,3 +1,13 @@
+/*
+ * Many of the syscalls used in this file expect some of the arguments
+ * to be __user pointers not __kernel pointers.  To limit the sparse
+ * noise, turn off sparse checking for this file.
+ */
+#ifdef __CHECKER__
+#undef __CHECKER__
+#warning "Sparse checking disabled for this file"
+#endif
+
 #include <linux/delay.h>
 #include <linux/raid/md_u.h>
 #include <linux/raid/md_p.h>
@@ -283,7 +293,7 @@ static void __init autodetect_raid(void)
 
 	wait_for_device_probe();
 
-	fd = sys_open((const char __user __force *) "/dev/md0", 0, 0);
+	fd = sys_open("/dev/md0", 0, 0);
 	if (fd >= 0) {
 		sys_ioctl(fd, RAID_AUTORUN, raid_autopart);
 		sys_close(fd);
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index 887629e24c54..6be2879cca66 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -1,3 +1,12 @@
+/*
+ * Many of the syscalls used in this file expect some of the arguments
+ * to be __user pointers not __kernel pointers.  To limit the sparse
+ * noise, turn off sparse checking for this file.
+ */
+#ifdef __CHECKER__
+#undef __CHECKER__
+#warning "Sparse checking disabled for this file"
+#endif
 
 #include <linux/kernel.h>
 #include <linux/fs.h>
@@ -54,20 +63,19 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 {
 	const int size = 512;
 	struct minix_super_block *minixsb;
-	struct ext2_super_block *ext2sb;
 	struct romfs_super_block *romfsb;
 	struct cramfs_super *cramfsb;
 	struct squashfs_super_block *squashfsb;
 	int nblocks = -1;
 	unsigned char *buf;
 	const char *compress_name;
+	unsigned long n;
 
 	buf = kmalloc(size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
 	minixsb = (struct minix_super_block *) buf;
-	ext2sb = (struct ext2_super_block *) buf;
 	romfsb = (struct romfs_super_block *) buf;
 	cramfsb = (struct cramfs_super *) buf;
 	squashfsb = (struct squashfs_super_block *) buf;
@@ -150,12 +158,12 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 	}
 
 	/* Try ext2 */
-	if (ext2sb->s_magic == cpu_to_le16(EXT2_SUPER_MAGIC)) {
+	n = ext2_image_size(buf);
+	if (n) {
 		printk(KERN_NOTICE
 		       "RAMDISK: ext2 filesystem found at block %d\n",
 		       start_block);
-		nblocks = le32_to_cpu(ext2sb->s_blocks_count) <<
-			le32_to_cpu(ext2sb->s_log_block_size);
+		nblocks = n;
 		goto done;
 	}
 
@@ -178,11 +186,11 @@ int __init rd_load_image(char *from)
 	char *buf = NULL;
 	unsigned short rotate = 0;
 	decompress_fn decompressor = NULL;
-#if !defined(CONFIG_S390) && !defined(CONFIG_PPC_ISERIES)
+#if !defined(CONFIG_S390)
 	char rotator[4] = { '|' , '/' , '-' , '\\' };
 #endif
 
-	out_fd = sys_open((const char __user __force *) "/dev/ram", O_RDWR, 0);
+	out_fd = sys_open("/dev/ram", O_RDWR, 0);
 	if (out_fd < 0)
 		goto out;
 
@@ -264,7 +272,7 @@ int __init rd_load_image(char *from)
 		}
 		sys_read(in_fd, buf, BLOCK_SIZE);
 		sys_write(out_fd, buf, BLOCK_SIZE);
-#if !defined(CONFIG_S390) && !defined(CONFIG_PPC_ISERIES)
+#if !defined(CONFIG_S390)
 		if (!(i % 16)) {
 			printk("%c\b", rotator[rotate & 0x3]);
 			rotate++;
@@ -281,7 +289,7 @@ noclose_input:
 	sys_close(out_fd);
 out:
 	kfree(buf);
-	sys_unlink((const char __user __force *) "/dev/ram");
+	sys_unlink("/dev/ram");
 	return res;
 }
 
diff --git a/init/init_task.c b/init/init_task.c
new file mode 100644
index 000000000000..8b2f3996b035
--- /dev/null
+++ b/init/init_task.c
@@ -0,0 +1,24 @@
+#include <linux/init_task.h>
+#include <linux/export.h>
+#include <linux/mqueue.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+#include <asm/pgtable.h>
+#include <asm/uaccess.h>
+
+static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
+static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
+
+/* Initial task structure */
+struct task_struct init_task = INIT_TASK(init_task);
+EXPORT_SYMBOL(init_task);
+
+/*
+ * Initial thread structure. Alignment of this is handled by a special
+ * linker map entry.
+ */
+union thread_union init_thread_union __init_task_data =
+	{ INIT_THREAD_INFO(init_task) };
diff --git a/init/initramfs.c b/init/initramfs.c
index 8216c303b082..84c6bf111300 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -1,3 +1,13 @@
+/*
+ * Many of the syscalls used in this file expect some of the arguments
+ * to be __user pointers not __kernel pointers.  To limit the sparse
+ * noise, turn off sparse checking for this file.
+ */
+#ifdef __CHECKER__
+#undef __CHECKER__
+#warning "Sparse checking disabled for this file"
+#endif
+
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
@@ -74,7 +84,7 @@ static void __init free_hash(void)
 	}
 }
 
-static long __init do_utime(char __user *filename, time_t mtime)
+static long __init do_utime(char *filename, time_t mtime)
 {
 	struct timespec t[2];
 
@@ -529,7 +539,7 @@ static void __init clean_rootfs(void)
 	struct linux_dirent64 *dirp;
 	int num;
 
-	fd = sys_open((const char __user __force *) "/", O_RDONLY, 0);
+	fd = sys_open("/", O_RDONLY, 0);
 	WARN_ON(fd < 0);
 	if (fd < 0)
 		return;
@@ -589,7 +599,7 @@ static int __init populate_rootfs(void)
 		}
 		printk(KERN_INFO "rootfs image is not initramfs (%s)"
 				"; looks like an initrd\n", err);
-		fd = sys_open((const char __user __force *) "/initrd.image",
+		fd = sys_open("/initrd.image",
 			      O_WRONLY|O_CREAT, 0700);
 		if (fd >= 0) {
 			sys_write(fd, (char *)initrd_start,
diff --git a/init/main.c b/init/main.c
index ff49a6dacfbb..1ca6b32c4828 100644
--- a/init/main.c
+++ b/init/main.c
@@ -87,7 +87,6 @@ extern void mca_init(void);
 extern void sbus_init(void);
 extern void prio_tree_init(void);
 extern void radix_tree_init(void);
-extern void free_initmem(void);
 #ifndef CONFIG_DEBUG_RODATA
 static inline void mark_rodata_ro(void) { }
 #endif
@@ -226,13 +225,9 @@ static int __init loglevel(char *str)
 
 early_param("loglevel", loglevel);
 
-/*
- * Unknown boot options get handed to init, unless they look like
- * unused parameters (modprobe will find them in /proc/cmdline).
- */
-static int __init unknown_bootoption(char *param, char *val)
+/* Change NUL term back to "=", to make "param" the whole string. */
+static int __init repair_env_string(char *param, char *val, const char *unused)
 {
-	/* Change NUL term back to "=", to make "param" the whole string. */
 	if (val) {
 		/* param=val or param="val"? */
 		if (val == param+strlen(param)+1)
@@ -244,6 +239,16 @@ static int __init unknown_bootoption(char *param, char *val)
 		} else
 			BUG();
 	}
+	return 0;
+}
+
+/*
+ * Unknown boot options get handed to init, unless they look like
+ * unused parameters (modprobe will find them in /proc/cmdline).
+ */
+static int __init unknown_bootoption(char *param, char *val, const char *unused)
+{
+	repair_env_string(param, val, unused);
 
 	/* Handle obsolete-style parameters */
 	if (obsolete_checksetup(param))
@@ -374,16 +379,13 @@ static noinline void __init_refok rest_init(void)
 	 * at least once to get things moving:
 	 */
 	init_idle_bootup_task(current);
-	preempt_enable_no_resched();
-	schedule();
-
+	schedule_preempt_disabled();
 	/* Call into cpu_idle with preempt disabled */
-	preempt_disable();
 	cpu_idle();
 }
 
 /* Check for early params. */
-static int __init do_early_param(char *param, char *val)
+static int __init do_early_param(char *param, char *val, const char *unused)
 {
 	const struct obs_kernel_param *p;
 
@@ -403,7 +405,7 @@ static int __init do_early_param(char *param, char *val)
 
 void __init parse_early_options(char *cmdline)
 {
-	parse_args("early options", cmdline, NULL, 0, do_early_param);
+	parse_args("early options", cmdline, NULL, 0, 0, 0, do_early_param);
 }
 
 /* Arch code calls this early on, or if not, just before other parsing. */
@@ -449,8 +451,8 @@ void __init __weak thread_info_cache_init(void)
 static void __init mm_init(void)
 {
 	/*
-	 * page_cgroup requires countinous pages as memmap
-	 * and it's bigger than MAX_ORDER unless SPARSEMEM.
+	 * page_cgroup requires contiguous pages,
+	 * bigger than MAX_ORDER unless SPARSEMEM.
 	 */
 	page_cgroup_init_flatmem();
 	mem_init();
@@ -506,7 +508,7 @@ asmlinkage void __init start_kernel(void)
 	parse_early_param();
 	parse_args("Booting kernel", static_command_line, __start___param,
 		   __stop___param - __start___param,
-		   &unknown_bootoption);
+		   0, 0, &unknown_bootoption);
 
 	jump_label_init();
 
@@ -558,9 +560,6 @@ asmlinkage void __init start_kernel(void)
 	early_boot_irqs_disabled = false;
 	local_irq_enable();
 
-	/* Interrupts are enabled now so all GFP allocations are safe. */
-	gfp_allowed_mask = __GFP_BITS_MASK;
-
 	kmem_cache_init_late();
 
 	/*
@@ -702,16 +701,69 @@ int __init_or_module do_one_initcall(initcall_t fn)
 }
 
 
-extern initcall_t __initcall_start[], __initcall_end[], __early_initcall_end[];
-
-static void __init do_initcalls(void)
+extern initcall_t __initcall_start[];
+extern initcall_t __initcall0_start[];
+extern initcall_t __initcall1_start[];
+extern initcall_t __initcall2_start[];
+extern initcall_t __initcall3_start[];
+extern initcall_t __initcall4_start[];
+extern initcall_t __initcall5_start[];
+extern initcall_t __initcall6_start[];
+extern initcall_t __initcall7_start[];
+extern initcall_t __initcall_end[];
+
+static initcall_t *initcall_levels[] __initdata = {
+	__initcall0_start,
+	__initcall1_start,
+	__initcall2_start,
+	__initcall3_start,
+	__initcall4_start,
+	__initcall5_start,
+	__initcall6_start,
+	__initcall7_start,
+	__initcall_end,
+};
+
+static char *initcall_level_names[] __initdata = {
+	"early",
+	"core",
+	"postcore",
+	"arch",
+	"subsys",
+	"fs",
+	"device",
+	"late",
+};
+
+static void __init do_initcall_level(int level)
 {
+	extern const struct kernel_param __start___param[], __stop___param[];
 	initcall_t *fn;
 
-	for (fn = __early_initcall_end; fn < __initcall_end; fn++)
+	strcpy(static_command_line, saved_command_line);
+	parse_args(initcall_level_names[level],
+		   static_command_line, __start___param,
+		   __stop___param - __start___param,
+		   level, level,
+		   &repair_env_string);
+
+	for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++)
 		do_one_initcall(*fn);
 }
 
+static void __init do_initcalls(void)
+{
+	int level;
+
+	for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++) {
+		pr_info("initlevel:%d=%s, %d registered initcalls\n",
+			level, initcall_level_names[level],
+			(int) (initcall_levels[level+1]
+				- initcall_levels[level]));
+		do_initcall_level(level);
+	}
+}
+
 /*
  * Ok, the machine is now initialized. None of the devices
  * have been touched yet, but the CPU subsystem is up and
@@ -735,7 +787,7 @@ static void __init do_pre_smp_initcalls(void)
 {
 	initcall_t *fn;
 
-	for (fn = __initcall_start; fn < __early_initcall_end; fn++)
+	for (fn = __initcall_start; fn < __initcall0_start; fn++)
 		do_one_initcall(*fn);
 }
 
@@ -792,6 +844,10 @@ static int __init kernel_init(void * unused)
 	 * Wait until kthreadd is all set-up.
 	 */
 	wait_for_completion(&kthreadd_done);
+
+	/* Now the scheduler is fully set up and can do blocking allocations */
+	gfp_allowed_mask = __GFP_BITS_MASK;
+
 	/*
 	 * init can allocate pages on any node
 	 */