Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git

4 files changed, 106 insertions, 126 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 8b88d0bedcb..dcc96a8c8c6 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1,3 +1,11 @@
+config ARCH
+	string
+	option env="ARCH"
+
+config KERNELVERSION
+	string
+	option env="KERNELVERSION"
+
 config DEFCONFIG_LIST
 	string
 	depends on !UML
@@ -215,6 +223,18 @@ config USER_NS
 	  vservers, to use user namespaces to provide different
 	  user info for different servers.  If unsure, say N.
 
+config PID_NS
+	bool "PID Namespaces (EXPERIMENTAL)"
+	default n
+	depends on EXPERIMENTAL
+	help
+	  Suport process id namespaces.  This allows having multiple
+	  process with the same pid as long as they are in different
+	  pid namespaces.  This is a building block of containers.
+
+	  Unless you want to work with an experimental feature
+	  say N here.
+
 config AUDIT
 	bool "Auditing support"
 	depends on NET
@@ -226,7 +246,7 @@ config AUDIT
 
 config AUDITSYSCALL
 	bool "Enable system-call auditing support"
-	depends on AUDIT && (X86 || PPC || PPC64 || S390 || IA64 || UML || SPARC64)
+	depends on AUDIT && (X86 || PPC || PPC64 || S390 || IA64 || UML || SPARC64|| SUPERH)
 	default y if SECURITY_SELINUX
 	help
 	  Enable low-overhead system-call auditing infrastructure that
@@ -301,13 +321,6 @@ config CGROUP_NS
           for instance virtual servers and checkpoint/restart
           jobs.
 
-config CGROUP_CPUACCT
-	bool "Simple CPU accounting cgroup subsystem"
-	depends on CGROUPS
-	help
-	  Provides a simple Resource Controller for monitoring the
-	  total CPU consumed by the tasks in a cgroup
-
 config CPUSETS
 	bool "Cpuset support"
 	depends on SMP && CGROUPS
@@ -349,8 +362,16 @@ config FAIR_CGROUP_SCHED
 
 endchoice
 
+config CGROUP_CPUACCT
+	bool "Simple CPU accounting cgroup subsystem"
+	depends on CGROUPS
+	help
+	  Provides a simple Resource Controller for monitoring the
+	  total CPU consumed by the tasks in a cgroup
+
 config SYSFS_DEPRECATED
 	bool "Create deprecated sysfs files"
+	depends on SYSFS
 	default y
 	help
 	  This option creates deprecated symlinks such as the
@@ -433,7 +454,7 @@ menuconfig EMBEDDED
 
 config UID16
 	bool "Enable 16-bit UID system calls" if EMBEDDED
-	depends on ARM || BFIN || CRIS || FRV || H8300 || X86_32 || M68K || (S390 && !64BIT) || SUPERH || SPARC32 || (SPARC64 && SPARC32_COMPAT) || UML || (X86_64 && IA32_EMULATION)
+	depends on ARM || BLACKFIN || CRIS || FRV || H8300 || X86_32 || M68K || (S390 && !64BIT) || SUPERH || SPARC32 || (SPARC64 && SPARC32_COMPAT) || UML || (X86_64 && IA32_EMULATION)
 	default y
 	help
 	  This enables the legacy 16-bit UID syscall wrappers.
@@ -646,6 +667,12 @@ endchoice
 
 endmenu		# General setup
 
+config SLABINFO
+	bool
+	depends on PROC_FS
+	depends on SLAB || SLUB
+	default y
+
 config RT_MUTEXES
 	boolean
 	select PLIST
@@ -744,3 +771,39 @@ source "block/Kconfig"
 
 config PREEMPT_NOTIFIERS
 	bool
+
+choice
+	prompt "RCU implementation type:"
+	default CLASSIC_RCU
+	help
+	  This allows you to choose either the classic RCU implementation
+	  that is designed for best read-side performance on non-realtime
+	  systems, or the preemptible RCU implementation for best latency
+	  on realtime systems.  Note that some kernel preemption modes
+	  will restrict your choice.
+
+	  Select the default if you are unsure.
+
+config CLASSIC_RCU
+	bool "Classic RCU"
+	help
+	  This option selects the classic RCU implementation that is
+	  designed for best read-side performance on non-realtime
+	  systems.
+
+	  Say Y if you are unsure.
+
+config PREEMPT_RCU
+	bool "Preemptible RCU"
+	depends on PREEMPT
+	help
+	  This option reduces the latency of the kernel by making certain
+	  RCU sections preemptible. Normally RCU code is non-preemptible, if
+	  this option is selected then read-only RCU sections become
+	  preemptible. This helps latency, but may expose bugs due to
+	  now-naive assumptions about each RCU read-side critical section
+	  remaining on a given CPU through its execution.
+
+	  Say N if you are unsure.
+
+endchoice
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 4efa1e5385e..1161dfd7b0d 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -55,69 +55,6 @@ static int __init readwrite(char *str)
 __setup("ro", readonly);
 __setup("rw", readwrite);
 
-static dev_t try_name(char *name, int part)
-{
-	char path[64];
-	char buf[32];
-	int range;
-	dev_t res;
-	char *s;
-	int len;
-	int fd;
-	unsigned int maj, min;
-
-	/* read device number from .../dev */
-
-	sprintf(path, "/sys/block/%s/dev", name);
-	fd = sys_open(path, 0, 0);
-	if (fd < 0)
-		goto fail;
-	len = sys_read(fd, buf, 32);
-	sys_close(fd);
-	if (len <= 0 || len == 32 || buf[len - 1] != '\n')
-		goto fail;
-	buf[len - 1] = '\0';
-	if (sscanf(buf, "%u:%u", &maj, &min) == 2) {
-		/*
-		 * Try the %u:%u format -- see print_dev_t()
-		 */
-		res = MKDEV(maj, min);
-		if (maj != MAJOR(res) || min != MINOR(res))
-			goto fail;
-	} else {
-		/*
-		 * Nope.  Try old-style "0321"
-		 */
-		res = new_decode_dev(simple_strtoul(buf, &s, 16));
-		if (*s)
-			goto fail;
-	}
-
-	/* if it's there and we are not looking for a partition - that's it */
-	if (!part)
-		return res;
-
-	/* otherwise read range from .../range */
-	sprintf(path, "/sys/block/%s/range", name);
-	fd = sys_open(path, 0, 0);
-	if (fd < 0)
-		goto fail;
-	len = sys_read(fd, buf, 32);
-	sys_close(fd);
-	if (len <= 0 || len == 32 || buf[len - 1] != '\n')
-		goto fail;
-	buf[len - 1] = '\0';
-	range = simple_strtoul(buf, &s, 10);
-	if (*s)
-		goto fail;
-
-	/* if partition is within range - we got it */
-	if (part < range)
-		return res + part;
-fail:
-	return 0;
-}
-
 /*
  *	Convert a name into device number.  We accept the following variants:
  *
@@ -129,12 +66,10 @@ fail:
  *	5) /dev/<disk_name>p<decimal> - same as the above, that form is
  *	   used when disk name of partitioned disk ends on a digit.
  *
- *	If name doesn't have fall into the categories above, we return 0.
- *	Sysfs is used to check if something is a disk name - it has
- *	all known disks under bus/block/devices.  If the disk name
- *	contains slashes, name of sysfs node has them replaced with
- *	bangs.  try_name() does the actual checks, assuming that sysfs
- *	is mounted on rootfs /sys.
+ *	If name doesn't have fall into the categories above, we return (0,0).
+ *	block_class is used to check if something is a disk name. If the disk
+ *	name contains slashes, the device name has them replaced with
+ *	bangs.
  */
 
 dev_t name_to_dev_t(char *name)
@@ -142,13 +77,6 @@ dev_t name_to_dev_t(char *name)
 	char s[32];
 	char *p;
 	dev_t res = 0;
-	int part;
-
-#ifdef CONFIG_SYSFS
-	int mkdir_err = sys_mkdir("/sys", 0700);
-	if (sys_mount("sysfs", "/sys", "sysfs", 0, NULL) < 0)
-		goto out;
-#endif
 
 	if (strncmp(name, "/dev/", 5) != 0) {
 		unsigned maj, min;
@@ -164,6 +92,7 @@ dev_t name_to_dev_t(char *name)
 		}
 		goto done;
 	}
+
 	name += 5;
 	res = Root_NFS;
 	if (strcmp(name, "nfs") == 0)
@@ -178,35 +107,14 @@ dev_t name_to_dev_t(char *name)
 	for (p = s; *p; p++)
 		if (*p == '/')
 			*p = '!';
-	res = try_name(s, 0);
+	res = blk_lookup_devt(s);
 	if (res)
 		goto done;
 
-	while (p > s && isdigit(p[-1]))
-		p--;
-	if (p == s || !*p || *p == '0')
-		goto fail;
-	part = simple_strtoul(p, NULL, 10);
-	*p = '\0';
-	res = try_name(s, part);
-	if (res)
-		goto done;
-
-	if (p < s + 2 || !isdigit(p[-2]) || p[-1] != 'p')
-		goto fail;
-	p[-1] = '\0';
-	res = try_name(s, part);
+fail:
+	return 0;
 done:
-#ifdef CONFIG_SYSFS
-	sys_umount("/sys", 0);
-out:
-	if (!mkdir_err)
-		sys_rmdir("/sys");
-#endif
 	return res;
-fail:
-	res = 0;
-	goto done;
 }
 
 static int __init root_dev_setup(char *line)
@@ -470,6 +378,5 @@ void __init prepare_namespace(void)
 out:
 	sys_mount(".", "/", NULL, MS_MOVE, NULL);
 	sys_chroot(".");
-	security_sb_post_mountroot();
 }
 
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index fd4fc12d262..614241b5200 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -55,12 +55,18 @@ static void __init handle_initrd(void)
 	sys_mount(".", "/", NULL, MS_MOVE, NULL);
 	sys_chroot(".");
 
+	/*
+	 * 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.
+	 */
+	current->flags |= PF_FREEZER_SKIP;
+
 	pid = kernel_thread(do_linuxrc, "/linuxrc", SIGCHLD);
 	if (pid > 0)
-		while (pid != sys_wait4(-1, NULL, 0, NULL)) {
-			try_to_freeze();
+		while (pid != sys_wait4(-1, NULL, 0, NULL))
 			yield();
-		}
+
+	current->flags &= ~PF_FREEZER_SKIP;
 
 	/* move initrd to rootfs' /old */
 	sys_fchdir(old_fd);
diff --git a/init/main.c b/init/main.c
index f605a969ea6..cb81ed116f6 100644
--- a/init/main.c
+++ b/init/main.c
@@ -56,6 +56,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/device.h>
 #include <linux/kthread.h>
+#include <linux/sched.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -127,7 +128,7 @@ static char *ramdisk_execute_command;
 
 #ifdef CONFIG_SMP
 /* Setup configured maximum number of CPUs to activate */
-static unsigned int __initdata max_cpus = NR_CPUS;
+unsigned int __initdata setup_max_cpus = NR_CPUS;
 
 /*
  * Setup routine for controlling SMP activation
@@ -145,7 +146,7 @@ static inline void disable_ioapic_setup(void) {};
 
 static int __init nosmp(char *str)
 {
-	max_cpus = 0;
+	setup_max_cpus = 0;
 	disable_ioapic_setup();
 	return 0;
 }
@@ -154,8 +155,8 @@ early_param("nosmp", nosmp);
 
 static int __init maxcpus(char *str)
 {
-	get_option(&str, &max_cpus);
-	if (max_cpus == 0)
+	get_option(&str, &setup_max_cpus);
+	if (setup_max_cpus == 0)
 		disable_ioapic_setup();
 
 	return 0;
@@ -163,7 +164,7 @@ static int __init maxcpus(char *str)
 
 early_param("maxcpus", maxcpus);
 #else
-#define max_cpus NR_CPUS
+#define setup_max_cpus NR_CPUS
 #endif
 
 /*
@@ -317,6 +318,10 @@ static int __init unknown_bootoption(char *param, char *val)
 	return 0;
 }
 
+#ifdef CONFIG_DEBUG_PAGEALLOC
+int __read_mostly debug_pagealloc_enabled = 0;
+#endif
+
 static int __init init_setup(char *str)
 {
 	unsigned int i;
@@ -362,7 +367,7 @@ static inline void smp_prepare_cpus(unsigned int maxcpus) { }
 
 #else
 
-#ifdef __GENERIC_PER_CPU
+#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 
 EXPORT_SYMBOL(__per_cpu_offset);
@@ -383,7 +388,7 @@ static void __init setup_per_cpu_areas(void)
 		ptr += size;
 	}
 }
-#endif /* !__GENERIC_PER_CPU */
+#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
 
 /* Called by boot processor to activate the rest. */
 static void __init smp_init(void)
@@ -392,7 +397,7 @@ static void __init smp_init(void)
 
 	/* FIXME: This should be done in userspace --RR */
 	for_each_present_cpu(cpu) {
-		if (num_online_cpus() >= max_cpus)
+		if (num_online_cpus() >= setup_max_cpus)
 			break;
 		if (!cpu_online(cpu))
 			cpu_up(cpu);
@@ -400,7 +405,7 @@ static void __init smp_init(void)
 
 	/* Any cleanup work */
 	printk(KERN_INFO "Brought up %ld CPUs\n", (long)num_online_cpus());
-	smp_cpus_done(max_cpus);
+	smp_cpus_done(setup_max_cpus);
 }
 
 #endif
@@ -551,6 +556,7 @@ asmlinkage void __init start_kernel(void)
 	preempt_disable();
 	build_all_zonelists();
 	page_alloc_init();
+	enable_debug_pagealloc();
 	printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
 	parse_early_param();
 	parse_args("Booting kernel", static_command_line, __start___param,
@@ -606,6 +612,7 @@ asmlinkage void __init start_kernel(void)
 	vfs_caches_init_early();
 	cpuset_init_early();
 	mem_init();
+	cpu_hotplug_init();
 	kmem_cache_init();
 	setup_per_cpu_pageset();
 	numa_policy_init();
@@ -747,11 +754,8 @@ __setup("nosoftlockup", nosoftlockup_setup);
 static void __init do_pre_smp_initcalls(void)
 {
 	extern int spawn_ksoftirqd(void);
-#ifdef CONFIG_SMP
-	extern int migration_init(void);
 
 	migration_init();
-#endif
 	spawn_ksoftirqd();
 	if (!nosoftlockup)
 		spawn_softlockup_task();
@@ -825,7 +829,7 @@ static int __init kernel_init(void * unused)
 	__set_special_pids(1, 1);
 	cad_pid = task_pid(current);
 
-	smp_prepare_cpus(max_cpus);
+	smp_prepare_cpus(setup_max_cpus);
 
 	do_pre_smp_initcalls();