Merge commit 'v2.6.35' into kbuild/kbuild

Conflicts:
	arch/powerpc/Makefile

6 files changed, 135 insertions, 89 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 313506d8be6e..5cff9a980c39 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -404,6 +404,22 @@ config RCU_FANOUT_EXACT
 
 	  Say N if unsure.
 
+config RCU_FAST_NO_HZ
+	bool "Accelerate last non-dyntick-idle CPU's grace periods"
+	depends on TREE_RCU && NO_HZ && SMP
+	default n
+	help
+	  This option causes RCU to attempt to accelerate grace periods
+	  in order to allow the final CPU 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.
+
+	  Say Y if energy efficiency is critically important, particularly
+	  	if you have relatively few CPUs.
+
+	  Say N if you are unsure.
+
 config TREE_RCU_TRACE
 	def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU )
 	select DEBUG_FS
@@ -453,59 +469,9 @@ config LOG_BUF_SHIFT
 config HAVE_UNSTABLE_SCHED_CLOCK
 	bool
 
-config GROUP_SCHED
-	bool "Group CPU scheduler"
-	depends on EXPERIMENTAL
-	default n
-	help
-	  This feature lets CPU scheduler recognize task groups and control CPU
-	  bandwidth allocation to such task groups.
-	  In order to create a group from arbitrary set of processes, use
-	  CONFIG_CGROUPS. (See Control Group support.)
-
-config FAIR_GROUP_SCHED
-	bool "Group scheduling for SCHED_OTHER"
-	depends on GROUP_SCHED
-	default GROUP_SCHED
-
-config RT_GROUP_SCHED
-	bool "Group scheduling for SCHED_RR/FIFO"
-	depends on EXPERIMENTAL
-	depends on GROUP_SCHED
-	default n
-	help
-	  This feature lets you explicitly allocate real CPU bandwidth
-	  to users or control groups (depending on the "Basis for grouping tasks"
-	  setting below. If enabled, it will also make it impossible to
-	  schedule realtime tasks for non-root users until you allocate
-	  realtime bandwidth for them.
-	  See Documentation/scheduler/sched-rt-group.txt for more information.
-
-choice
-	depends on GROUP_SCHED
-	prompt "Basis for grouping tasks"
-	default USER_SCHED
-
-config USER_SCHED
-	bool "user id"
-	help
-	  This option will choose userid as the basis for grouping
-	  tasks, thus providing equal CPU bandwidth to each user.
-
-config CGROUP_SCHED
-	bool "Control groups"
- 	depends on CGROUPS
- 	help
-	  This option allows you to create arbitrary task groups
-	  using the "cgroup" pseudo filesystem and control
-	  the cpu bandwidth allocated to each such task group.
-	  Refer to Documentation/cgroups/cgroups.txt for more
-	  information on "cgroup" pseudo filesystem.
-
-endchoice
-
 menuconfig CGROUPS
 	boolean "Control Group support"
+	depends on EVENTFD
 	help
 	  This option adds support for grouping sets of processes together, for
 	  use with process control subsystems such as Cpusets, CFS, memory
@@ -624,6 +590,62 @@ config CGROUP_MEM_RES_CTLR_SWAP
 	  Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
 	  size is 4096bytes, 512k per 1Gbytes of swap.
 
+menuconfig CGROUP_SCHED
+	bool "Group CPU scheduler"
+	depends on EXPERIMENTAL && CGROUPS
+	default n
+	help
+	  This feature lets CPU scheduler recognize task groups and control CPU
+	  bandwidth allocation to such task groups. It uses cgroups to group
+	  tasks.
+
+if CGROUP_SCHED
+config FAIR_GROUP_SCHED
+	bool "Group scheduling for SCHED_OTHER"
+	depends on CGROUP_SCHED
+	default CGROUP_SCHED
+
+config RT_GROUP_SCHED
+	bool "Group scheduling for SCHED_RR/FIFO"
+	depends on EXPERIMENTAL
+	depends on CGROUP_SCHED
+	default n
+	help
+	  This feature lets you explicitly allocate real CPU bandwidth
+	  to task groups. If enabled, it will also make it impossible to
+	  schedule realtime tasks for non-root users until you allocate
+	  realtime bandwidth for them.
+	  See Documentation/scheduler/sched-rt-group.txt for more information.
+
+endif #CGROUP_SCHED
+
+config BLK_CGROUP
+	tristate "Block IO controller"
+	depends on CGROUPS && BLOCK
+	default n
+	---help---
+	Generic block IO controller cgroup interface. This is the common
+	cgroup interface which should be used by various IO controlling
+	policies.
+
+	Currently, CFQ IO scheduler uses it to recognize task groups and
+	control disk bandwidth allocation (proportional time slice allocation)
+	to such task groups.
+
+	This option only enables generic Block IO controller infrastructure.
+	One needs to also enable actual IO controlling logic in CFQ for it
+	to take effect. (CONFIG_CFQ_GROUP_IOSCHED=y).
+
+	See Documentation/cgroups/blkio-controller.txt for more information.
+
+config DEBUG_BLK_CGROUP
+	bool "Enable Block IO controller debugging"
+	depends on BLK_CGROUP
+	default n
+	---help---
+	Enable some debugging help. Currently it exports additional stat
+	files in a cgroup which can be useful for debugging.
+
 endif # CGROUPS
 
 config MM_OWNER
@@ -984,19 +1006,6 @@ config PERF_EVENTS
 
 	  Say Y if unsure.
 
-config EVENT_PROFILE
-	bool "Tracepoint profiling sources"
-	depends on PERF_EVENTS && EVENT_TRACING
-	default y
-	help
-	 Allow the use of tracepoints as software performance events.
-
-	 When this is enabled, you can create perf events based on
-	 tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID
-	 found in debugfs://tracing/events/*/*/id. (The -e/--events
-	 option to the perf tool can parse and interpret symbolic
-	 tracepoints, in the subsystem:tracepoint_name format.)
-
 config PERF_COUNTERS
 	bool "Kernel performance counters (old config option)"
 	depends on HAVE_PERF_EVENTS
@@ -1120,7 +1129,7 @@ config MMAP_ALLOW_UNINITIALIZED
 	  See Documentation/nommu-mmap.txt for more information.
 
 config PROFILING
-	bool "Profiling support (EXPERIMENTAL)"
+	bool "Profiling support"
 	help
 	  Say Y here to enable the extended profiling support mechanisms used
 	  by profilers such as OProfile.
@@ -1270,4 +1279,8 @@ source "block/Kconfig"
 config PREEMPT_NOTIFIERS
 	bool
 
+config PADATA
+	depends on SMP
+	bool
+
 source "kernel/Kconfig.locks"
diff --git a/init/do_mounts.c b/init/do_mounts.c
index bb008d064c1a..02e3ca4fc527 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -15,6 +15,7 @@
 #include <linux/initrd.h>
 #include <linux/async.h>
 #include <linux/fs_struct.h>
+#include <linux/slab.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_fs_sb.h>
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 614241b5200c..2b108538d0d9 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -30,11 +30,7 @@ static int __init do_linuxrc(void * shell)
 	extern char * envp_init[];
 
 	sys_close(old_fd);sys_close(root_fd);
-	sys_close(0);sys_close(1);sys_close(2);
 	sys_setsid();
-	(void) sys_open("/dev/console",O_RDWR,0);
-	(void) sys_dup(0);
-	(void) sys_dup(0);
 	return kernel_execve(shell, argv, envp_init);
 }
 
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index 027a402708de..bf3ef667bf36 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -7,6 +7,7 @@
 #include <linux/cramfs_fs.h>
 #include <linux/initrd.h>
 #include <linux/string.h>
+#include <linux/slab.h>
 
 #include "do_mounts.h"
 #include "../fs/squashfs/squashfs_fs.h"
diff --git a/init/initramfs.c b/init/initramfs.c
index b37d34beb90b..4b9c20205092 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -457,7 +457,8 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len)
 					 compress_name);
 				message = msg_buf;
 			}
-		}
+		} else
+			error("junk in compressed archive");
 		if (state != Reset)
 			error("junk in compressed archive");
 		this_header = saved_offset + my_inptr;
@@ -525,7 +526,7 @@ static void __init clean_rootfs(void)
 	int fd;
 	void *buf;
 	struct linux_dirent64 *dirp;
-	int count;
+	int num;
 
 	fd = sys_open("/", O_RDONLY, 0);
 	WARN_ON(fd < 0);
@@ -539,9 +540,9 @@ static void __init clean_rootfs(void)
 	}
 
 	dirp = buf;
-	count = sys_getdents64(fd, dirp, BUF_SIZE);
-	while (count > 0) {
-		while (count > 0) {
+	num = sys_getdents64(fd, dirp, BUF_SIZE);
+	while (num > 0) {
+		while (num > 0) {
 			struct stat st;
 			int ret;
 
@@ -554,12 +555,12 @@ static void __init clean_rootfs(void)
 					sys_unlink(dirp->d_name);
 			}
 
-			count -= dirp->d_reclen;
+			num -= dirp->d_reclen;
 			dirp = (void *)dirp + dirp->d_reclen;
 		}
 		dirp = buf;
 		memset(buf, 0, BUF_SIZE);
-		count = sys_getdents64(fd, dirp, BUF_SIZE);
+		num = sys_getdents64(fd, dirp, BUF_SIZE);
 	}
 
 	sys_close(fd);
diff --git a/init/main.c b/init/main.c
index dac44a9356a5..a42fdf4aeba9 100644
--- a/init/main.c
+++ b/init/main.c
@@ -25,7 +25,6 @@
 #include <linux/bootmem.h>
 #include <linux/acpi.h>
 #include <linux/tty.h>
-#include <linux/gfp.h>
 #include <linux/percpu.h>
 #include <linux/kmod.h>
 #include <linux/vmalloc.h>
@@ -63,12 +62,14 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/idr.h>
+#include <linux/kgdb.h>
 #include <linux/ftrace.h>
 #include <linux/async.h>
 #include <linux/kmemcheck.h>
 #include <linux/kmemtrace.h>
 #include <linux/sfi.h>
 #include <linux/shmem_fs.h>
+#include <linux/slab.h>
 #include <trace/boot.h>
 
 #include <asm/io.h>
@@ -124,7 +125,9 @@ static char *ramdisk_execute_command;
 
 #ifdef CONFIG_SMP
 /* Setup configured maximum number of CPUs to activate */
-unsigned int __initdata setup_max_cpus = NR_CPUS;
+unsigned int setup_max_cpus = NR_CPUS;
+EXPORT_SYMBOL(setup_max_cpus);
+
 
 /*
  * Setup routine for controlling SMP activation
@@ -149,6 +152,20 @@ static int __init nosmp(char *str)
 
 early_param("nosmp", nosmp);
 
+/* this is hard limit */
+static int __init nrcpus(char *str)
+{
+	int nr_cpus;
+
+	get_option(&str, &nr_cpus);
+	if (nr_cpus > 0 && nr_cpus < nr_cpu_ids)
+		nr_cpu_ids = nr_cpus;
+
+	return 0;
+}
+
+early_param("nr_cpus", nrcpus);
+
 static int __init maxcpus(char *str)
 {
 	get_option(&str, &setup_max_cpus);
@@ -160,7 +177,7 @@ static int __init maxcpus(char *str)
 
 early_param("maxcpus", maxcpus);
 #else
-const unsigned int setup_max_cpus = NR_CPUS;
+static const unsigned int setup_max_cpus = NR_CPUS;
 #endif
 
 /*
@@ -407,16 +424,26 @@ static void __init setup_command_line(char *command_line)
  * gcc-3.4 accidentally inlines this function, so use noinline.
  */
 
+static __initdata DECLARE_COMPLETION(kthreadd_done);
+
 static noinline void __init_refok rest_init(void)
 	__releases(kernel_lock)
 {
 	int pid;
 
 	rcu_scheduler_starting();
+	/*
+	 * We need to spawn init first so that it obtains pid 1, however
+	 * the init task will end up wanting to create kthreads, which, if
+	 * we schedule it before we create kthreadd, will OOPS.
+	 */
 	kernel_thread(kernel_init, NULL, CLONE_FS | CLONE_SIGHAND);
 	numa_default_policy();
 	pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
+	rcu_read_lock();
 	kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
+	rcu_read_unlock();
+	complete(&kthreadd_done);
 	unlock_kernel();
 
 	/*
@@ -550,7 +577,7 @@ asmlinkage void __init start_kernel(void)
 	setup_per_cpu_areas();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
 
-	build_all_zonelists();
+	build_all_zonelists(NULL);
 	page_alloc_init();
 
 	printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
@@ -584,6 +611,7 @@ asmlinkage void __init start_kernel(void)
 		local_irq_disable();
 	}
 	rcu_init();
+	radix_tree_init();
 	/* init some links before init_ISA_irqs() */
 	early_irq_init();
 	init_IRQ();
@@ -601,7 +629,7 @@ asmlinkage void __init start_kernel(void)
 	local_irq_enable();
 
 	/* Interrupts are enabled now so all GFP allocations are safe. */
-	set_gfp_allowed_mask(__GFP_BITS_MASK);
+	gfp_allowed_mask = __GFP_BITS_MASK;
 
 	kmem_cache_init_late();
 
@@ -658,8 +686,8 @@ asmlinkage void __init start_kernel(void)
 	buffer_init();
 	key_init();
 	security_init();
+	dbg_late_init();
 	vfs_caches_init(totalram_pages);
-	radix_tree_init();
 	signals_init();
 	/* rootfs populating might need page-writeback */
 	page_writeback_init();
@@ -806,11 +834,6 @@ static noinline int init_post(void)
 	system_state = SYSTEM_RUNNING;
 	numa_default_policy();
 
-	if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
-		printk(KERN_WARNING "Warning: unable to open an initial console.\n");
-
-	(void) sys_dup(0);
-	(void) sys_dup(0);
 
 	current->signal->flags |= SIGNAL_UNKILLABLE;
 
@@ -836,17 +859,22 @@ static noinline int init_post(void)
 	run_init_process("/bin/init");
 	run_init_process("/bin/sh");
 
-	panic("No init found.  Try passing init= option to kernel.");
+	panic("No init found.  Try passing init= option to kernel. "
+	      "See Linux Documentation/init.txt for guidance.");
 }
 
 static int __init kernel_init(void * unused)
 {
+	/*
+	 * Wait until kthreadd is all set-up.
+	 */
+	wait_for_completion(&kthreadd_done);
 	lock_kernel();
 
 	/*
 	 * init can allocate pages on any node
 	 */
-	set_mems_allowed(node_possible_map);
+	set_mems_allowed(node_states[N_HIGH_MEMORY]);
 	/*
 	 * init can run on any cpu.
 	 */
@@ -873,6 +901,12 @@ static int __init kernel_init(void * unused)
 
 	do_basic_setup();
 
+	/* Open the /dev/console on the rootfs, this should never fail */
+	if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
+		printk(KERN_WARNING "Warning: unable to open an initial console.\n");
+
+	(void) sys_dup(0);
+	(void) sys_dup(0);
 	/*
 	 * check if there is an early userspace init.  If yes, let it do all
 	 * the work