7 files changed, 191 insertions, 102 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 35518243c4bd..526ec1c7456a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -21,6 +21,13 @@ config CONSTRUCTORS
         depends on !UML
         default y
 
+config HAVE_IRQ_WORK
+        bool
+
+config IRQ_WORK
+        bool
+        depends on HAVE_IRQ_WORK
+
 menu "General setup"
 
 config EXPERIMENTAL
@@ -64,7 +71,7 @@ config BROKEN_ON_SMP
 
 config LOCK_KERNEL
         bool
-        depends on SMP || PREEMPT
+        depends on (SMP || PREEMPT) && BKL
         default y
 
 config INIT_ENV_ARG_LIMIT
@@ -179,7 +186,7 @@ config KERNEL_LZO
         depends on HAVE_KERNEL_LZO
         help
           Its compression ratio is the poorest among the 4. The kernel
-          size is about about 10% bigger than gzip; however its speed
+          size is about 10% bigger than gzip; however its speed
           (both compression and decompression) is the fastest.
 
 endchoice
@@ -332,6 +339,8 @@ config AUDIT_TREE
         depends on AUDITSYSCALL
         select FSNOTIFY
 
+source "kernel/irq/Kconfig"
+
 menu "RCU Subsystem"
 
 choice
@@ -562,7 +571,6 @@ if CGROUPS
 
 config CGROUP_DEBUG
         bool "Example debug cgroup subsystem"
-        depends on CGROUPS
         default n
         help
           This option enables a simple cgroup subsystem that
@@ -573,7 +581,6 @@ config CGROUP_DEBUG
 
 config CGROUP_NS
         bool "Namespace cgroup subsystem"
-        depends on CGROUPS
         help
           Provides a simple namespace cgroup subsystem to
           provide hierarchical naming of sets of namespaces,
@@ -582,21 +589,18 @@ config CGROUP_NS
 
 config CGROUP_FREEZER
         bool "Freezer cgroup subsystem"
-        depends on CGROUPS
         help
           Provides a way to freeze and unfreeze all tasks in a
           cgroup.
 
 config CGROUP_DEVICE
         bool "Device controller for cgroups"
-        depends on CGROUPS && EXPERIMENTAL
         help
           Provides a cgroup implementing whitelists for devices which
           a process in the cgroup can mknod or open.
 
 config CPUSETS
         bool "Cpuset support"
-        depends on CGROUPS
         help
           This option will let you create and manage CPUSETs which
           allow dynamically partitioning a system into sets of CPUs and
@@ -612,7 +616,6 @@ config PROC_PID_CPUSET
 
 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.
@@ -622,11 +625,10 @@ config RESOURCE_COUNTERS
         help
           This option enables controller independent resource accounting
           infrastructure that works with cgroups.
-        depends on CGROUPS
 
 config CGROUP_MEM_RES_CTLR
         bool "Memory Resource Controller for Control Groups"
-        depends on CGROUPS && RESOURCE_COUNTERS
+        depends on RESOURCE_COUNTERS
         select MM_OWNER
         help
           Provides a memory resource controller that manages both anonymous
@@ -664,10 +666,23 @@ config CGROUP_MEM_RES_CTLR_SWAP
           if boot option "noswapaccount" is set, swap will not be accounted.
           Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
           size is 4096bytes, 512k per 1Gbytes of swap.
+config CGROUP_MEM_RES_CTLR_SWAP_ENABLED
+        bool "Memory Resource Controller Swap Extension enabled by default"
+        depends on CGROUP_MEM_RES_CTLR_SWAP
+        default y
+        help
+          Memory Resource Controller Swap Extension comes with its price in
+          a bigger memory consumption. General purpose distribution kernels
+          which want to enable the feautre but keep it disabled by default
+          and let the user enable it by swapaccount boot command line
+          parameter should have this option unselected.
+          For those who want to have the feature enabled by default should
+          select this option (if, for some reason, they need to disable it
+          then noswapaccount does the trick).
 
 menuconfig CGROUP_SCHED
         bool "Group CPU scheduler"
-        depends on EXPERIMENTAL && CGROUPS
+        depends on EXPERIMENTAL
         default n
         help
           This feature lets CPU scheduler recognize task groups and control CPU
@@ -696,7 +711,7 @@ endif #CGROUP_SCHED
 
 config BLK_CGROUP
         tristate "Block IO controller"
-        depends on CGROUPS && BLOCK
+        depends on BLOCK
         default n
         ---help---
         Generic block IO controller cgroup interface. This is the common
@@ -705,11 +720,14 @@ config BLK_CGROUP
 
         Currently, CFQ IO scheduler uses it to recognize task groups and
         control disk bandwidth allocation (proportional time slice allocation)
-        to such task groups.
+        to such task groups. It is also used by bio throttling logic in
+        block layer to implement upper limit in IO rates on a device.
 
         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).
+        One needs to also enable actual IO controlling logic/policy. For
+        enabling proportional weight division of disk bandwidth in CFQ seti
+        CONFIG_CFQ_GROUP_IOSCHED=y and for enabling throttling policy set
+        CONFIG_BLK_THROTTLE=y.
 
         See Documentation/cgroups/blkio-controller.txt for more information.
 
@@ -723,57 +741,7 @@ config DEBUG_BLK_CGROUP
 
 endif # CGROUPS
 
-config MM_OWNER
-        bool
-
-config SYSFS_DEPRECATED
-        bool
-
-config SYSFS_DEPRECATED_V2
-        bool "enable deprecated sysfs features to support old userspace tools"
-        depends on SYSFS
-        default n
-        select SYSFS_DEPRECATED
-        help
-          This option switches the layout of sysfs to the deprecated
-          version. Do not use it on recent distributions.
-
-          The current sysfs layout features a unified device tree at
-          /sys/devices/, which is able to express a hierarchy between
-          class devices. If the deprecated option is set to Y, the
-          unified device tree is split into a bus device tree at
-          /sys/devices/ and several individual class device trees at
-          /sys/class/. The class and bus devices will be connected by
-          "<subsystem>:<name>" and the "device" links. The "block"
-          class devices, will not show up in /sys/class/block/. Some
-          subsystems will suppress the creation of some devices which
-          depend on the unified device tree.
-
-          This option is not a pure compatibility option that can
-          be safely enabled on newer distributions. It will change the
-          layout of sysfs to the non-extensible deprecated version,
-          and disable some features, which can not be exported without
-          confusing older userspace tools. Since 2007/2008 all major
-          distributions do not enable this option, and ship no tools which
-          depend on the deprecated layout or this option.
-
-          If you are using a new kernel on an older distribution, or use
-          older userspace tools, you might need to say Y here. Do not say Y,
-          if the original kernel, that came with your distribution, has
-          this option set to N.
-
-config RELAY
-        bool "Kernel->user space relay support (formerly relayfs)"
-        help
-          This option enables support for relay interface support in
-          certain file systems (such as debugfs).
-          It is designed to provide an efficient mechanism for tools and
-          facilities to relay large amounts of data from kernel space to
-          user space.
-
-          If unsure, say N.
-
-config NAMESPACES
+menuconfig NAMESPACES
         bool "Namespaces support" if EMBEDDED
         default !EMBEDDED
         help
@@ -782,48 +750,102 @@ config NAMESPACES
           or same user id or pid may refer to different tasks when used in
           different namespaces.
 
+if NAMESPACES
+
 config UTS_NS
         bool "UTS namespace"
-        depends on NAMESPACES
+        default y
         help
           In this namespace tasks see different info provided with the
           uname() system call
 
 config IPC_NS
         bool "IPC namespace"
-        depends on NAMESPACES && (SYSVIPC || POSIX_MQUEUE)
+        depends on (SYSVIPC || POSIX_MQUEUE)
+        default y
         help
           In this namespace tasks work with IPC ids which correspond to
           different IPC objects in different namespaces.
 
 config USER_NS
         bool "User namespace (EXPERIMENTAL)"
-        depends on NAMESPACES && EXPERIMENTAL
+        depends on EXPERIMENTAL
+        default y
         help
           This allows containers, i.e. 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 NAMESPACES && EXPERIMENTAL
+        bool "PID Namespaces"
+        default y
         help
           Support process id namespaces.  This allows having multiple
           processes 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 NET_NS
         bool "Network namespace"
-        default n
-        depends on NAMESPACES && EXPERIMENTAL && NET
+        depends on NET
+        default y
         help
           Allow user space to create what appear to be multiple instances
           of the network stack.
 
+endif # NAMESPACES
+
+config MM_OWNER
+        bool
+
+config SYSFS_DEPRECATED
+        bool "enable deprecated sysfs features to support old userspace tools"
+        depends on SYSFS
+        default n
+        help
+          This option adds code that switches the layout of the "block" class
+          devices, to not show up in /sys/class/block/, but only in
+          /sys/block/.
+
+          This switch is only active when the sysfs.deprecated=1 boot option is
+          passed or the SYSFS_DEPRECATED_V2 option is set.
+
+          This option allows new kernels to run on old distributions and tools,
+          which might get confused by /sys/class/block/. Since 2007/2008 all
+          major distributions and tools handle this just fine.
+
+          Recent distributions and userspace tools after 2009/2010 depend on
+          the existence of /sys/class/block/, and will not work with this
+          option enabled.
+
+          Only if you are using a new kernel on an old distribution, you might
+          need to say Y here.
+
+config SYSFS_DEPRECATED_V2
+        bool "enabled deprecated sysfs features by default"
+        default n
+        depends on SYSFS
+        depends on SYSFS_DEPRECATED
+        help
+          Enable deprecated sysfs by default.
+
+          See the CONFIG_SYSFS_DEPRECATED option for more details about this
+          option.
+
+          Only if you are using a new kernel on an old distribution, you might
+          need to say Y here. Even then, odds are you would not need it
+          enabled, you can always pass the boot option if absolutely necessary.
+
+config RELAY
+        bool "Kernel->user space relay support (formerly relayfs)"
+        help
+          This option enables support for relay interface support in
+          certain file systems (such as debugfs).
+          It is designed to provide an efficient mechanism for tools and
+          facilities to relay large amounts of data from kernel space to
+          user space.
+
+          If unsure, say N.
+
 config BLK_DEV_INITRD
         bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
         depends on BROKEN || !FRV
@@ -1058,6 +1080,7 @@ config PERF_EVENTS
         default y if (PROFILING || PERF_COUNTERS)
         depends on HAVE_PERF_EVENTS
         select ANON_INODES
+        select IRQ_WORK
         help
           Enable kernel support for various performance events provided
           by software and hardware.
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 02e3ca4fc527..830aaec9c7d5 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -58,6 +58,62 @@ static int __init readwrite(char *str)
 __setup("ro", readonly);
 __setup("rw", readwrite);
 
+#ifdef CONFIG_BLOCK
+/**
+ * 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
+ *
+ * Returns 1 if the device matches, and 0 otherwise.
+ */
+static int match_dev_by_uuid(struct device *dev, void *data)
+{
+        u8 *uuid = 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;
+
+        return 1;
+no_match:
+        return 0;
+}
+
+
+/**
+ * devt_from_partuuid - looks up the dev_t of a partition by its UUID
+ * @uuid:       36 byte char array containing a hex 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
+ * by filesystem UUIDs.
+ *
+ * Returns the matching dev_t on success or 0 on failure.
+ */
+static dev_t __init devt_from_partuuid(char *uuid_str)
+{
+        dev_t res = 0;
+        struct device *dev = NULL;
+        u8 uuid[16];
+
+        /* Pack the requested UUID in the expected format. */
+        part_pack_uuid(uuid_str, uuid);
+
+        dev = class_find_device(&block_class, NULL, uuid, &match_dev_by_uuid);
+        if (!dev)
+                goto done;
+
+        res = dev->devt;
+        put_device(dev);
+
+done:
+        return res;
+}
+#endif
+
 /*
  *      Convert a name into device number.  We accept the following variants:
  *
@@ -68,6 +124,8 @@ __setup("rw", readwrite);
  *         of partition - device number of disk plus the partition number
  *      5) /dev/<disk_name>p<decimal> - same as the above, that form is
  *         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.
  *
  *      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
@@ -82,6 +140,18 @@ dev_t name_to_dev_t(char *name)
         dev_t res = 0;
         int part;
 
+#ifdef CONFIG_BLOCK
+        if (strncmp(name, "PARTUUID=", 9) == 0) {
+                name += 9;
+                if (strlen(name) != 36)
+                        goto fail;
+                res = devt_from_partuuid(name);
+                if (!res)
+                        goto fail;
+                goto done;
+        }
+#endif
+
         if (strncmp(name, "/dev/", 5) != 0) {
                 unsigned maj, min;
 
@@ -221,7 +291,7 @@ static int __init do_mount_root(char *name, char *fs, int flags, void *data)
         if (err)
                 return err;
 
-        sys_chdir("/root");
+        sys_chdir((const char __user __force *)"/root");
         ROOT_DEV = current->fs->pwd.mnt->mnt_sb->s_dev;
         printk("VFS: Mounted root (%s filesystem)%s on device %u:%u.\n",
                current->fs->pwd.mnt->mnt_sb->s_type->name,
@@ -291,13 +361,13 @@ out:
 #ifdef CONFIG_ROOT_NFS
 static int __init mount_nfs_root(void)
 {
-        void *data = nfs_root_data();
+        char *root_dev, *root_data;
 
-        create_dev("/dev/root", ROOT_DEV);
-        if (data &&
-            do_mount_root("/dev/root", "nfs", root_mountflags, data) == 0)
-                return 1;
-        return 0;
+        if (nfs_root_data(&root_dev, &root_data) != 0)
+                return 0;
+        if (do_mount_root(root_dev, "nfs", root_mountflags, root_data) != 0)
+                return 0;
+        return 1;
 }
 #endif
 
@@ -418,5 +488,5 @@ void __init prepare_namespace(void)
 out:
         devtmpfs_mount("dev");
         sys_mount(".", "/", NULL, MS_MOVE, NULL);
-        sys_chroot(".");
+        sys_chroot((const char __user __force *)".");
 }
diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c
index 69aebbf8fd2d..32c4799b8c91 100644
--- a/init/do_mounts_md.c
+++ b/init/do_mounts_md.c
@@ -283,7 +283,7 @@ static void __init autodetect_raid(void)
 
         wait_for_device_probe();
 
-        fd = sys_open("/dev/md0", 0, 0);
+        fd = sys_open((const char __user __force *) "/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 bf3ef667bf36..6e1ee6987c78 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -168,7 +168,7 @@ int __init rd_load_image(char *from)
         char rotator[4] = { '|' , '/' , '-' , '\\' };
 #endif
 
-        out_fd = sys_open("/dev/ram", O_RDWR, 0);
+        out_fd = sys_open((const char __user __force *) "/dev/ram", O_RDWR, 0);
         if (out_fd < 0)
                 goto out;
 
@@ -267,7 +267,7 @@ noclose_input:
         sys_close(out_fd);
 out:
         kfree(buf);
-        sys_unlink("/dev/ram");
+        sys_unlink((const char __user __force *) "/dev/ram");
         return res;
 }
 
diff --git a/init/initramfs.c b/init/initramfs.c
index 4b9c20205092..2531811d42cb 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -483,7 +483,8 @@ static int __init retain_initrd_param(char *str)
 }
 __setup("retain_initrd", retain_initrd_param);
 
-extern char __initramfs_start[], __initramfs_end[];
+extern char __initramfs_start[];
+extern unsigned long __initramfs_size;
 #include <linux/initrd.h>
 #include <linux/kexec.h>
 
@@ -528,7 +529,7 @@ static void __init clean_rootfs(void)
         struct linux_dirent64 *dirp;
         int num;
 
-        fd = sys_open("/", O_RDONLY, 0);
+        fd = sys_open((const char __user __force *) "/", O_RDONLY, 0);
         WARN_ON(fd < 0);
         if (fd < 0)
                 return;
@@ -570,8 +571,7 @@ static void __init clean_rootfs(void)
 
 static int __init populate_rootfs(void)
 {
-        char *err = unpack_to_rootfs(__initramfs_start,
-                         __initramfs_end - __initramfs_start);
+        char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size);
         if (err)
                 panic(err);     /* Failed to decompress INTERNAL initramfs */
         if (initrd_start) {
@@ -585,12 +585,12 @@ static int __init populate_rootfs(void)
                         return 0;
                 } else {
                         clean_rootfs();
-                        unpack_to_rootfs(__initramfs_start,
-                                 __initramfs_end - __initramfs_start);
+                        unpack_to_rootfs(__initramfs_start, __initramfs_size);
                 }
                 printk(KERN_INFO "rootfs image is not initramfs (%s)"
                                 "; looks like an initrd\n", err);
-                fd = sys_open("/initrd.image", O_WRONLY|O_CREAT, 0700);
+                fd = sys_open((const char __user __force *) "/initrd.image",
+                              O_WRONLY|O_CREAT, 0700);
                 if (fd >= 0) {
                         sys_write(fd, (char *)initrd_start,
                                         initrd_end - initrd_start);
diff --git a/init/main.c b/init/main.c
index 94ab488039aa..8646401f7a0e 100644
--- a/init/main.c
+++ b/init/main.c
@@ -20,7 +20,6 @@
 #include <linux/delay.h>
 #include <linux/ioport.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <linux/initrd.h>
 #include <linux/bootmem.h>
 #include <linux/acpi.h>
@@ -424,7 +423,6 @@ static void __init setup_command_line(char *command_line)
 static __initdata DECLARE_COMPLETION(kthreadd_done);
 
 static noinline void __init_refok rest_init(void)
-        __releases(kernel_lock)
 {
         int pid;
 
@@ -556,7 +554,6 @@ asmlinkage void __init start_kernel(void)
 
         local_irq_disable();
         early_boot_irqs_off();
-        early_init_irq_lock_class();
 
 /*
  * Interrupts are still disabled. Do necessary setups, then
@@ -819,7 +816,6 @@ static void run_init_process(const char *init_filename)
  * makes it inline to init() and it becomes part of init.text section
  */
 static noinline int init_post(void)
-        __releases(kernel_lock)
 {
         /* need to finish all async __init code before freeing the memory */
         async_synchronize_full();
diff --git a/init/noinitramfs.c b/init/noinitramfs.c
index f4c1a3a1b8c5..267739d85179 100644
--- a/init/noinitramfs.c
+++ b/init/noinitramfs.c
@@ -29,17 +29,17 @@ static int __init default_rootfs(void)
 {
         int err;
 
-        err = sys_mkdir("/dev", 0755);
+        err = sys_mkdir((const char __user __force *) "/dev", 0755);
         if (err < 0)
                 goto out;
 
-        err = sys_mknod((const char __user *) "/dev/console",
+        err = sys_mknod((const char __user __force *) "/dev/console",
                         S_IFCHR | S_IRUSR | S_IWUSR,
                         new_encode_dev(MKDEV(5, 1)));
         if (err < 0)
                 goto out;
 
-        err = sys_mkdir("/root", 0700);
+        err = sys_mkdir((const char __user __force *) "/root", 0700);
         if (err < 0)
                 goto out;