Merge branch 'for-2.6.30' into for-2.6.31

7 files changed, 417 insertions, 405 deletions

diff --git a/init/Kconfig b/init/Kconfig
index a724a149bf3f..f2f9b5362b48 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -101,6 +101,66 @@ config LOCALVERSION_AUTO
 
           which is done within the script "scripts/setlocalversion".)
 
+config HAVE_KERNEL_GZIP
+        bool
+
+config HAVE_KERNEL_BZIP2
+        bool
+
+config HAVE_KERNEL_LZMA
+        bool
+
+choice
+        prompt "Kernel compression mode"
+        default KERNEL_GZIP
+        depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA
+        help
+          The linux kernel is a kind of self-extracting executable.
+          Several compression algorithms are available, which differ
+          in efficiency, compression and decompression speed.
+          Compression speed is only relevant when building a kernel.
+          Decompression speed is relevant at each boot.
+
+          If you have any problems with bzip2 or lzma compressed
+          kernels, mail me (Alain Knaff) <alain@knaff.lu>. (An older
+          version of this functionality (bzip2 only), for 2.4, was
+          supplied by Christian Ludwig)
+
+          High compression options are mostly useful for users, who
+          are low on disk space (embedded systems), but for whom ram
+          size matters less.
+
+          If in doubt, select 'gzip'
+
+config KERNEL_GZIP
+        bool "Gzip"
+        depends on HAVE_KERNEL_GZIP
+        help
+          The old and tried gzip compression. Its compression ratio is
+          the poorest among the 3 choices; however its speed (both
+          compression and decompression) is the fastest.
+
+config KERNEL_BZIP2
+        bool "Bzip2"
+        depends on HAVE_KERNEL_BZIP2
+        help
+          Its compression ratio and speed is intermediate.
+          Decompression speed is slowest among the three.  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.
+
+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.
+
+endchoice
+
 config SWAP
         bool "Support for paging of anonymous memory (swap)"
         depends on MMU && BLOCK
@@ -148,6 +208,12 @@ config POSIX_MQUEUE
 
           If unsure, say Y.
 
+config POSIX_MQUEUE_SYSCTL
+        bool
+        depends on POSIX_MQUEUE
+        depends on SYSCTL
+        default y
+
 config BSD_PROCESS_ACCT
         bool "BSD Process Accounting"
         help
@@ -238,6 +304,98 @@ config AUDIT_TREE
         def_bool y
         depends on AUDITSYSCALL && INOTIFY
 
+menu "RCU Subsystem"
+
+choice
+        prompt "RCU Implementation"
+        default CLASSIC_RCU
+
+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.
+
+          Select this option if you are unsure.
+
+config TREE_RCU
+        bool "Tree-based hierarchical RCU"
+        help
+          This option selects the RCU implementation that is
+          designed for very large SMP system with hundreds or
+          thousands of CPUs.
+
+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.
+
+endchoice
+
+config RCU_TRACE
+        bool "Enable tracing for RCU"
+        depends on TREE_RCU || PREEMPT_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
+        range 2 32 if !64BIT
+        depends on TREE_RCU
+        default 64 if 64BIT
+        default 32 if !64BIT
+        help
+          This option controls the fanout of hierarchical implementations
+          of RCU, allowing RCU to work efficiently on machines with
+          large numbers of CPUs.  This value must be at least the cube
+          root of NR_CPUS, which allows NR_CPUS up to 32,768 for 32-bit
+          systems and up to 262,144 for 64-bit systems.
+
+          Select a specific number if testing RCU itself.
+          Take the default if unsure.
+
+config RCU_FANOUT_EXACT
+        bool "Disable tree-based hierarchical RCU auto-balancing"
+        depends on TREE_RCU
+        default n
+        help
+          This option forces use of the exact RCU_FANOUT value specified,
+          regardless of imbalances in the hierarchy.  This is useful for
+          testing RCU itself, and might one day be useful on systems with
+          strong NUMA behavior.
+
+          Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
+
+          Say N if unsure.
+
+config TREE_RCU_TRACE
+        def_bool RCU_TRACE && TREE_RCU
+        select DEBUG_FS
+        help
+          This option provides tracing for the TREE_RCU implementation,
+          permitting Makefile to trivially select kernel/rcutree_trace.c.
+
+config PREEMPT_RCU_TRACE
+        def_bool RCU_TRACE && PREEMPT_RCU
+        select DEBUG_FS
+        help
+          This option provides tracing for the PREEMPT_RCU implementation,
+          permitting Makefile to trivially select kernel/rcupreempt_trace.c.
+
+endmenu # "RCU Subsystem"
+
 config IKCONFIG
         tristate "Kernel .config support"
         ---help---
@@ -323,26 +481,26 @@ config CGROUP_SCHED
           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.txt for more information
-          on "cgroup" pseudo filesystem.
+          Refer to Documentation/cgroups/cgroups.txt for more
+          information on "cgroup" pseudo filesystem.
 
 endchoice
 
-menu "Control Group support"
-config CGROUPS
-        bool "Control Group support"
+menuconfig CGROUPS
+        boolean "Control Group support"
         help
-          This option add support for grouping sets of processes together, for
+          This option adds support for grouping sets of processes together, for
           use with process control subsystems such as Cpusets, CFS, memory
           controls or device isolation.
           See
-                - Documentation/cpusets.txt     (Cpusets)
                 - Documentation/scheduler/sched-design-CFS.txt  (CFS)
-                - Documentation/cgroups/ (features for grouping, isolation)
-                - Documentation/controllers/ (features for resource control)
+                - Documentation/cgroups/ (features for grouping, isolation
+                                          and resource control)
 
           Say N if unsure.
 
+if CGROUPS
+
 config CGROUP_DEBUG
         bool "Example debug cgroup subsystem"
         depends on CGROUPS
@@ -350,24 +508,24 @@ config CGROUP_DEBUG
         help
           This option enables a simple cgroup subsystem that
           exports useful debugging information about the cgroups
-          framework
+          framework.
 
-          Say N if unsure
+          Say N if unsure.
 
 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,
-          for instance virtual servers and checkpoint/restart
-          jobs.
+        bool "Namespace cgroup subsystem"
+        depends on CGROUPS
+        help
+          Provides a simple namespace cgroup subsystem to
+          provide hierarchical naming of sets of namespaces,
+          for instance virtual servers and checkpoint/restart
+          jobs.
 
 config CGROUP_FREEZER
-        bool "control group freezer subsystem"
-        depends on CGROUPS
-        help
-          Provides a way to freeze and unfreeze all tasks in a
+        bool "Freezer cgroup subsystem"
+        depends on CGROUPS
+        help
+          Provides a way to freeze and unfreeze all tasks in a
           cgroup.
 
 config CGROUP_DEVICE
@@ -379,7 +537,7 @@ config CGROUP_DEVICE
 
 config CPUSETS
         bool "Cpuset support"
-        depends on SMP && CGROUPS
+        depends on CGROUPS
         help
           This option will let you create and manage CPUSETs which
           allow dynamically partitioning a system into sets of CPUs and
@@ -388,18 +546,23 @@ config CPUSETS
 
           Say N if unsure.
 
+config PROC_PID_CPUSET
+        bool "Include legacy /proc/<pid>/cpuset file"
+        depends on CPUSETS
+        default y
+
 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
+          total CPU consumed by the tasks in a cgroup.
 
 config RESOURCE_COUNTERS
         bool "Resource counters"
         help
           This option enables controller independent resource accounting
-          infrastructure that works with cgroups
+          infrastructure that works with cgroups.
         depends on CGROUPS
 
 config CGROUP_MEM_RES_CTLR
@@ -408,7 +571,7 @@ config CGROUP_MEM_RES_CTLR
         select MM_OWNER
         help
           Provides a memory resource controller that manages both anonymous
-          memory and page cache. (See Documentation/controllers/memory.txt)
+          memory and page cache. (See Documentation/cgroups/memory.txt)
 
           Note that setting this option increases fixed memory overhead
           associated with each page of memory in the system. By this,
@@ -425,9 +588,6 @@ config CGROUP_MEM_RES_CTLR
           This config option also selects MM_OWNER config option, which
           could in turn add some fork/exit overhead.
 
-config MM_OWNER
-        bool
-
 config CGROUP_MEM_RES_CTLR_SWAP
         bool "Memory Resource Controller Swap Extension(EXPERIMENTAL)"
         depends on CGROUP_MEM_RES_CTLR && SWAP && EXPERIMENTAL
@@ -443,9 +603,13 @@ config CGROUP_MEM_RES_CTLR_SWAP
           is disabled by boot option, this will be automatically disabled and
           there will be no overhead from this. Even when you set this config=y,
           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.
 
+endif # CGROUPS
 
-endmenu
+config MM_OWNER
+        bool
 
 config SYSFS_DEPRECATED
         bool
@@ -483,11 +647,6 @@ config SYSFS_DEPRECATED_V2
           if the original kernel, that came with your distribution, has
           this option set to N.
 
-config PROC_PID_CPUSET
-        bool "Include legacy /proc/<pid>/cpuset file"
-        depends on CPUSETS
-        default y
-
 config RELAY
         bool "Kernel->user space relay support (formerly relayfs)"
         help
@@ -517,10 +676,10 @@ config UTS_NS
 
 config IPC_NS
         bool "IPC namespace"
-        depends on NAMESPACES && SYSVIPC
+        depends on NAMESPACES && (SYSVIPC || POSIX_MQUEUE)
         help
           In this namespace tasks work with IPC ids which correspond to
-          different IPC objects in different namespaces
+          different IPC objects in different namespaces.
 
 config USER_NS
         bool "User namespace (EXPERIMENTAL)"
@@ -536,12 +695,20 @@ config PID_NS
         depends on NAMESPACES && EXPERIMENTAL
         help
           Support process id namespaces.  This allows having multiple
-          process with the same pid as long as they are in different
+          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
+        help
+          Allow user space to create what appear to be multiple instances
+          of the network stack.
+
 config BLK_DEV_INITRD
         bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
         depends on BROKEN || !FRV
@@ -576,6 +743,9 @@ config CC_OPTIMIZE_FOR_SIZE
 config SYSCTL
         bool
 
+config ANON_INODES
+        bool
+
 menuconfig EMBEDDED
         bool "Configure standard kernel features (for small systems)"
         help
@@ -626,13 +796,6 @@ config KALLSYMS_ALL
 
            Say N.
 
-config KALLSYMS_STRIP_GENERATED
-        bool "Strip machine generated symbols from kallsyms"
-        depends on KALLSYMS_ALL
-        default y
-        help
-          Say N if you want kallsyms to retain even machine generated symbols.
-
 config KALLSYMS_EXTRA_PASS
         bool "Do an extra kallsyms pass"
         depends on KALLSYMS
@@ -688,18 +851,6 @@ config PCSPKR_PLATFORM
           This option allows to disable the internal PC-Speaker
           support, saving some memory.
 
-config COMPAT_BRK
-        bool "Disable heap randomization"
-        default y
-        help
-          Randomizing heap placement makes heap exploits harder, but it
-          also breaks ancient binaries (including anything libc5 based).
-          This option changes the bootup default to heap randomization
-          disabled, and can be overriden runtime by setting
-          /proc/sys/kernel/randomize_va_space to 2.
-
-          On non-ancient distros (post-2000 ones) N is usually a safe choice.
-
 config BASE_FULL
         default y
         bool "Enable full-sized data structures for core" if EMBEDDED
@@ -717,9 +868,6 @@ config FUTEX
           support for "fast userspace mutexes".  The resulting kernel may not
           run glibc-based applications correctly.
 
-config ANON_INODES
-        bool
-
 config EPOLL
         bool "Enable eventpoll support" if EMBEDDED
         default y
@@ -805,6 +953,18 @@ config SLUB_DEBUG
           SLUB sysfs support. /sys/slab will not exist and there will be
           no support for cache validation etc.
 
+config COMPAT_BRK
+        bool "Disable heap randomization"
+        default y
+        help
+          Randomizing heap placement makes heap exploits harder, but it
+          also breaks ancient binaries (including anything libc5 based).
+          This option changes the bootup default to heap randomization
+          disabled, and can be overridden at runtime by setting
+          /proc/sys/kernel/randomize_va_space to 2.
+
+          On non-ancient distros (post-2000 ones) N is usually a safe choice.
+
 choice
         prompt "Choose SLAB allocator"
         default SLUB
@@ -853,13 +1013,27 @@ config TRACEPOINTS
 
 config MARKERS
         bool "Activate markers"
-        depends on TRACEPOINTS
+        select TRACEPOINTS
         help
           Place an empty function call at each marker site. Can be
           dynamically changed for a probe function.
 
 source "arch/Kconfig"
 
+config SLOW_WORK
+        default n
+        bool
+        help
+          The slow work thread pool provides a number of dynamically allocated
+          threads that can be used by the kernel to perform operations that
+          take a relatively long time.
+
+          An example of this would be CacheFiles doing a path lookup followed
+          by a series of mkdirs and a create call, all of which have to touch
+          disk.
+
+          See Documentation/slow-work.txt.
+
 endmenu         # General setup
 
 config HAVE_GENERIC_DMA_COHERENT
@@ -874,7 +1048,6 @@ config SLABINFO
 
 config RT_MUTEXES
         boolean
-        select PLIST
 
 config BASE_SMALL
         int
@@ -959,7 +1132,7 @@ config INIT_ALL_POSSIBLE
           cpu_possible_map, some of them chose to initialize cpu_possible_map
           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 persuing me down dark alleys.
+          and have several arch maintainers pursuing me down dark alleys.
 
 config STOP_MACHINE
         bool
@@ -973,90 +1146,3 @@ source "block/Kconfig"
 config PREEMPT_NOTIFIERS
         bool
 
-choice
-        prompt "RCU Implementation"
-        default CLASSIC_RCU
-
-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.
-
-          Select this option if you are unsure.
-
-config TREE_RCU
-        bool "Tree-based hierarchical RCU"
-        help
-          This option selects the RCU implementation that is
-          designed for very large SMP system with hundreds or
-          thousands of CPUs.
-
-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.
-
-endchoice
-
-config RCU_TRACE
-        bool "Enable tracing for RCU"
-        depends on TREE_RCU || PREEMPT_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
-        range 2 32 if !64BIT
-        depends on TREE_RCU
-        default 64 if 64BIT
-        default 32 if !64BIT
-        help
-          This option controls the fanout of hierarchical implementations
-          of RCU, allowing RCU to work efficiently on machines with
-          large numbers of CPUs.  This value must be at least the cube
-          root of NR_CPUS, which allows NR_CPUS up to 32,768 for 32-bit
-          systems and up to 262,144 for 64-bit systems.
-
-          Select a specific number if testing RCU itself.
-          Take the default if unsure.
-
-config RCU_FANOUT_EXACT
-        bool "Disable tree-based hierarchical RCU auto-balancing"
-        depends on TREE_RCU
-        default n
-        help
-          This option forces use of the exact RCU_FANOUT value specified,
-          regardless of imbalances in the hierarchy.  This is useful for
-          testing RCU itself, and might one day be useful on systems with
-          strong NUMA behavior.
-
-          Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
-
-          Say N if unsure.
-
-config TREE_RCU_TRACE
-        def_bool RCU_TRACE && TREE_RCU
-        select DEBUG_FS
-        help
-          This option provides tracing for the TREE_RCU implementation,
-          permitting Makefile to trivially select kernel/rcutree_trace.c.
-
-config PREEMPT_RCU_TRACE
-        def_bool RCU_TRACE && PREEMPT_RCU
-        select DEBUG_FS
-        help
-          This option provides tracing for the PREEMPT_RCU implementation,
-          permitting Makefile to trivially select kernel/rcupreempt_trace.c.
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 708105e163df..dd7ee5f203f3 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -14,6 +14,7 @@
 #include <linux/fs.h>
 #include <linux/initrd.h>
 #include <linux/async.h>
+#include <linux/fs_struct.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_fs_sb.h>
@@ -370,10 +371,14 @@ void __init prepare_namespace(void)
                 ssleep(root_delay);
         }
 
-        /* wait for the known devices to complete their probing */
-        while (driver_probe_done() != 0)
-                msleep(100);
-        async_synchronize_full();
+        /*
+         * wait for the known devices to complete their probing
+         *
+         * Note: this is a potential source of long boot delays.
+         * For example, it is not atypical to wait 5 seconds here
+         * for the touchpad of a laptop to initialize.
+         */
+        wait_for_device_probe();
 
         md_run_setup();
 
@@ -399,6 +404,7 @@ void __init prepare_namespace(void)
                 while (driver_probe_done() != 0 ||
                         (ROOT_DEV = name_to_dev_t(saved_root_name)) == 0)
                         msleep(100);
+                async_synchronize_full();
         }
 
         is_floppy = MAJOR(ROOT_DEV) == FLOPPY_MAJOR;
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 9aa968d54329..f5b978a9bb92 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -1,4 +1,5 @@
 #include <linux/kernel.h>
+#include <linux/blkdev.h>
 #include <linux/init.h>
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c
index ff95e3192884..69aebbf8fd2d 100644
--- a/init/do_mounts_md.c
+++ b/init/do_mounts_md.c
@@ -1,5 +1,6 @@
 #include <linux/delay.h>
-#include <linux/raid/md.h>
+#include <linux/raid/md_u.h>
+#include <linux/raid/md_p.h>
 
 #include "do_mounts.h"
 
@@ -112,8 +113,6 @@ static int __init md_setup(char *str)
         return 1;
 }
 
-#define MdpMinorShift 6
-
 static void __init md_setup_drive(void)
 {
         int minor, i, ent, partitioned;
@@ -281,8 +280,9 @@ static void __init autodetect_raid(void)
          */
         printk(KERN_INFO "md: Waiting for all devices to be available before autodetect\n");
         printk(KERN_INFO "md: If you don't use raid, use raid=noautodetect\n");
-        while (driver_probe_done() < 0)
-                msleep(100);
+
+        wait_for_device_probe();
+
         fd = sys_open("/dev/md0", 0, 0);
         if (fd >= 0) {
                 sys_ioctl(fd, RAID_AUTORUN, raid_autopart);
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index 0f0f0cf3ba9a..027a402708de 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -11,6 +11,9 @@
 #include "do_mounts.h"
 #include "../fs/squashfs/squashfs_fs.h"
 
+#include <linux/decompress/generic.h>
+
+
 int __initdata rd_prompt = 1;/* 1 = prompt for RAM disk, 0 = don't prompt */
 
 static int __init prompt_ramdisk(char *str)
@@ -29,7 +32,7 @@ static int __init ramdisk_start_setup(char *str)
 }
 __setup("ramdisk_start=", ramdisk_start_setup);
 
-static int __init crd_load(int in_fd, int out_fd);
+static int __init crd_load(int in_fd, int out_fd, decompress_fn deco);
 
 /*
  * This routine tries to find a RAM disk image to load, and returns the
@@ -38,15 +41,15 @@ static int __init crd_load(int in_fd, int out_fd);
  * numbers could not be found.
  *
  * We currently check for the following magic numbers:
- *      minix
- *      ext2
+ *      minix
+ *      ext2
  *      romfs
  *      cramfs
  *      squashfs
- *      gzip
+ *      gzip
  */
-static int __init 
-identify_ramdisk_image(int fd, int start_block)
+static int __init
+identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor)
 {
         const int size = 512;
         struct minix_super_block *minixsb;
@@ -56,6 +59,7 @@ identify_ramdisk_image(int fd, int start_block)
         struct squashfs_super_block *squashfsb;
         int nblocks = -1;
         unsigned char *buf;
+        const char *compress_name;
 
         buf = kmalloc(size, GFP_KERNEL);
         if (!buf)
@@ -69,18 +73,19 @@ identify_ramdisk_image(int fd, int start_block)
         memset(buf, 0xe5, size);
 
         /*
-         * Read block 0 to test for gzipped kernel
+         * Read block 0 to test for compressed kernel
          */
         sys_lseek(fd, start_block * BLOCK_SIZE, 0);
         sys_read(fd, buf, size);
 
-        /*
-         * If it matches the gzip magic numbers, return 0
-         */
-        if (buf[0] == 037 && ((buf[1] == 0213) || (buf[1] == 0236))) {
-                printk(KERN_NOTICE
-                       "RAMDISK: Compressed image found at block %d\n",
-                       start_block);
+        *decompressor = decompress_method(buf, size, &compress_name);
+        if (compress_name) {
+                printk(KERN_NOTICE "RAMDISK: %s image found at block %d\n",
+                       compress_name, start_block);
+                if (!*decompressor)
+                        printk(KERN_EMERG
+                               "RAMDISK: %s decompressor not configured!\n",
+                               compress_name);
                 nblocks = 0;
                 goto done;
         }
@@ -142,7 +147,7 @@ identify_ramdisk_image(int fd, int start_block)
         printk(KERN_NOTICE
                "RAMDISK: Couldn't find valid RAM disk image starting at %d.\n",
                start_block);
-        
+
 done:
         sys_lseek(fd, start_block * BLOCK_SIZE, 0);
         kfree(buf);
@@ -157,6 +162,7 @@ int __init rd_load_image(char *from)
         int nblocks, i, disk;
         char *buf = NULL;
         unsigned short rotate = 0;
+        decompress_fn decompressor = NULL;
 #if !defined(CONFIG_S390) && !defined(CONFIG_PPC_ISERIES)
         char rotator[4] = { '|' , '/' , '-' , '\\' };
 #endif
@@ -169,12 +175,12 @@ int __init rd_load_image(char *from)
         if (in_fd < 0)
                 goto noclose_input;
 
-        nblocks = identify_ramdisk_image(in_fd, rd_image_start);
+        nblocks = identify_ramdisk_image(in_fd, rd_image_start, &decompressor);
         if (nblocks < 0)
                 goto done;
 
         if (nblocks == 0) {
-                if (crd_load(in_fd, out_fd) == 0)
+                if (crd_load(in_fd, out_fd, decompressor) == 0)
                         goto successful_load;
                 goto done;
         }
@@ -200,7 +206,7 @@ int __init rd_load_image(char *from)
                        nblocks, rd_blocks);
                 goto done;
         }
-                
+
         /*
          * OK, time to copy in the data
          */
@@ -273,138 +279,48 @@ int __init rd_load_disk(int n)
         return rd_load_image("/dev/root");
 }
 
-/*
- * gzip declarations
- */
-
-#define OF(args)  args
-
-#ifndef memzero
-#define memzero(s, n)     memset ((s), 0, (n))
-#endif
-
-typedef unsigned char  uch;
-typedef unsigned short ush;
-typedef unsigned long  ulg;
-
-#define INBUFSIZ 4096
-#define WSIZE 0x8000    /* window size--must be a power of two, and */
-                        /*  at least 32K for zip's deflate method */
-
-static uch *inbuf;
-static uch *window;
-
-static unsigned insize;  /* valid bytes in inbuf */
-static unsigned inptr;   /* index of next byte to be processed in inbuf */
-static unsigned outcnt;  /* bytes in output buffer */
 static int exit_code;
-static int unzip_error;
-static long bytes_out;
+static int decompress_error;
 static int crd_infd, crd_outfd;
 
-#define get_byte()  (inptr < insize ? inbuf[inptr++] : fill_inbuf())
-                
-/* Diagnostic functions (stubbed out) */
-#define Assert(cond,msg)
-#define Trace(x)
-#define Tracev(x)
-#define Tracevv(x)
-#define Tracec(c,x)
-#define Tracecv(c,x)
-
-#define STATIC static
-#define INIT __init
-
-static int  __init fill_inbuf(void);
-static void __init flush_window(void);
-static void __init error(char *m);
-
-#define NO_INFLATE_MALLOC
-
-#include "../lib/inflate.c"
-
-/* ===========================================================================
- * Fill the input buffer. This is called only when the buffer is empty
- * and at least one byte is really needed.
- * Returning -1 does not guarantee that gunzip() will ever return.
- */
-static int __init fill_inbuf(void)
+static int __init compr_fill(void *buf, unsigned int len)
 {
-        if (exit_code) return -1;
-        
-        insize = sys_read(crd_infd, inbuf, INBUFSIZ);
-        if (insize == 0) {
-                error("RAMDISK: ran out of compressed data");
-                return -1;
-        }
-
-        inptr = 1;
-
-        return inbuf[0];
+        int r = sys_read(crd_infd, buf, len);
+        if (r < 0)
+                printk(KERN_ERR "RAMDISK: error while reading compressed data");
+        else if (r == 0)
+                printk(KERN_ERR "RAMDISK: EOF while reading compressed data");
+        return r;
 }
 
-/* ===========================================================================
- * Write the output window window[0..outcnt-1] and update crc and bytes_out.
- * (Used for the decompressed data only.)
- */
-static void __init flush_window(void)
+static int __init compr_flush(void *window, unsigned int outcnt)
 {
-    ulg c = crc;         /* temporary variable */
-    unsigned n, written;
-    uch *in, ch;
-    
-    written = sys_write(crd_outfd, window, outcnt);
-    if (written != outcnt && unzip_error == 0) {
-        printk(KERN_ERR "RAMDISK: incomplete write (%d != %d) %ld\n",
-               written, outcnt, bytes_out);
-        unzip_error = 1;
-    }
-    in = window;
-    for (n = 0; n < outcnt; n++) {
-            ch = *in++;
-            c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
-    }
-    crc = c;
-    bytes_out += (ulg)outcnt;
-    outcnt = 0;
+        int written = sys_write(crd_outfd, window, outcnt);
+        if (written != outcnt) {
+                if (decompress_error == 0)
+                        printk(KERN_ERR
+                               "RAMDISK: incomplete write (%d != %d)\n",
+                               written, outcnt);
+                decompress_error = 1;
+                return -1;
+        }
+        return outcnt;
 }
 
 static void __init error(char *x)
 {
         printk(KERN_ERR "%s\n", x);
         exit_code = 1;
-        unzip_error = 1;
+        decompress_error = 1;
 }
 
-static int __init crd_load(int in_fd, int out_fd)
+static int __init crd_load(int in_fd, int out_fd, decompress_fn deco)
 {
         int result;
-
-        insize = 0;             /* valid bytes in inbuf */
-        inptr = 0;              /* index of next byte to be processed in inbuf */
-        outcnt = 0;             /* bytes in output buffer */
-        exit_code = 0;
-        bytes_out = 0;
-        crc = (ulg)0xffffffffL; /* shift register contents */
-
         crd_infd = in_fd;
         crd_outfd = out_fd;
-        inbuf = kmalloc(INBUFSIZ, GFP_KERNEL);
-        if (!inbuf) {
-                printk(KERN_ERR "RAMDISK: Couldn't allocate gzip buffer\n");
-                return -1;
-        }
-        window = kmalloc(WSIZE, GFP_KERNEL);
-        if (!window) {
-                printk(KERN_ERR "RAMDISK: Couldn't allocate gzip window\n");
-                kfree(inbuf);
-                return -1;
-        }
-        makecrc();
-        result = gunzip();
-        if (unzip_error)
+        result = deco(NULL, 0, compr_fill, compr_flush, NULL, NULL, error);
+        if (decompress_error)
                 result = 1;
-        kfree(inbuf);
-        kfree(window);
         return result;
 }
diff --git a/init/initramfs.c b/init/initramfs.c
index d9c941c0c3ca..80cd713f6cc5 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -5,6 +5,7 @@
 #include <linux/fcntl.h>
 #include <linux/delay.h>
 #include <linux/string.h>
+#include <linux/dirent.h>
 #include <linux/syscalls.h>
 #include <linux/utime.h>
 
@@ -166,8 +167,6 @@ static __initdata char *victim;
 static __initdata unsigned count;
 static __initdata loff_t this_header, next_header;
 
-static __initdata int dry_run;
-
 static inline void __init eat(unsigned n)
 {
         victim += n;
@@ -229,10 +228,6 @@ static int __init do_header(void)
         parse_header(collected);
         next_header = this_header + N_ALIGN(name_len) + body_len;
         next_header = (next_header + 3) & ~3;
-        if (dry_run) {
-                read_into(name_buf, N_ALIGN(name_len), GotName);
-                return 0;
-        }
         state = SkipIt;
         if (name_len <= 0 || name_len > PATH_MAX)
                 return 0;
@@ -303,8 +298,6 @@ static int __init do_name(void)
                 free_hash();
                 return 0;
         }
-        if (dry_run)
-                return 0;
         clean_path(collected, mode);
         if (S_ISREG(mode)) {
                 int ml = maybe_link();
@@ -390,11 +383,13 @@ static int __init write_buffer(char *buf, unsigned len)
         return len - count;
 }
 
-static void __init flush_buffer(char *buf, unsigned len)
+static int __init flush_buffer(void *bufv, unsigned len)
 {
+        char *buf = (char *) bufv;
         int written;
+        int origLen = len;
         if (message)
-                return;
+                return -1;
         while ((written = write_buffer(buf, len)) < len && !message) {
                 char c = buf[written];
                 if (c == '0') {
@@ -408,84 +403,27 @@ static void __init flush_buffer(char *buf, unsigned len)
                 } else
                         error("junk in compressed archive");
         }
+        return origLen;
 }
 
-/*
- * gzip declarations
- */
-
-#define OF(args)  args
-
-#ifndef memzero
-#define memzero(s, n)     memset ((s), 0, (n))
-#endif
-
-typedef unsigned char  uch;
-typedef unsigned short ush;
-typedef unsigned long  ulg;
+static unsigned my_inptr;   /* index of next byte to be processed in inbuf */
 
-#define WSIZE 0x8000    /* window size--must be a power of two, and */
-                        /*  at least 32K for zip's deflate method */
-
-static uch *inbuf;
-static uch *window;
-
-static unsigned insize;  /* valid bytes in inbuf */
-static unsigned inptr;   /* index of next byte to be processed in inbuf */
-static unsigned outcnt;  /* bytes in output buffer */
-static long bytes_out;
-
-#define get_byte()  (inptr < insize ? inbuf[inptr++] : -1)
-                
-/* Diagnostic functions (stubbed out) */
-#define Assert(cond,msg)
-#define Trace(x)
-#define Tracev(x)
-#define Tracevv(x)
-#define Tracec(c,x)
-#define Tracecv(c,x)
-
-#define STATIC static
-#define INIT __init
-
-static void __init flush_window(void);
-static void __init error(char *m);
-
-#define NO_INFLATE_MALLOC
-
-#include "../lib/inflate.c"
-
-/* ===========================================================================
- * Write the output window window[0..outcnt-1] and update crc and bytes_out.
- * (Used for the decompressed data only.)
- */
-static void __init flush_window(void)
-{
-        ulg c = crc;         /* temporary variable */
-        unsigned n;
-        uch *in, ch;
-
-        flush_buffer(window, outcnt);
-        in = window;
-        for (n = 0; n < outcnt; n++) {
-                ch = *in++;
-                c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
-        }
-        crc = c;
-        bytes_out += (ulg)outcnt;
-        outcnt = 0;
-}
+#include <linux/decompress/generic.h>
 
-static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only)
+static char * __init unpack_to_rootfs(char *buf, unsigned len)
 {
         int written;
-        dry_run = check_only;
+        decompress_fn decompress;
+        const char *compress_name;
+        static __initdata char msg_buf[64];
+
         header_buf = kmalloc(110, GFP_KERNEL);
         symlink_buf = kmalloc(PATH_MAX + N_ALIGN(PATH_MAX) + 1, GFP_KERNEL);
         name_buf = kmalloc(N_ALIGN(PATH_MAX), GFP_KERNEL);
-        window = kmalloc(WSIZE, GFP_KERNEL);
-        if (!window || !header_buf || !symlink_buf || !name_buf)
+
+        if (!header_buf || !symlink_buf || !name_buf)
                 panic("can't allocate buffers");
+
         state = Start;
         this_header = 0;
         message = NULL;
@@ -505,22 +443,25 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only)
                         continue;
                 }
                 this_header = 0;
-                insize = len;
-                inbuf = buf;
-                inptr = 0;
-                outcnt = 0;             /* bytes in output buffer */
-                bytes_out = 0;
-                crc = (ulg)0xffffffffL; /* shift register contents */
-                makecrc();
-                gunzip();
+                decompress = decompress_method(buf, len, &compress_name);
+                if (decompress)
+                        decompress(buf, len, NULL, flush_buffer, NULL,
+                                   &my_inptr, error);
+                else if (compress_name) {
+                        if (!message) {
+                                snprintf(msg_buf, sizeof msg_buf,
+                                         "compression method %s not configured",
+                                         compress_name);
+                                message = msg_buf;
+                        }
+                }
                 if (state != Reset)
-                        error("junk in gzipped archive");
-                this_header = saved_offset + inptr;
-                buf += inptr;
-                len -= inptr;
+                        error("junk in compressed archive");
+                this_header = saved_offset + my_inptr;
+                buf += my_inptr;
+                len -= my_inptr;
         }
         dir_utime();
-        kfree(window);
         kfree(name_buf);
         kfree(symlink_buf);
         kfree(header_buf);
@@ -574,26 +515,76 @@ skip:
         initrd_end = 0;
 }
 
+#define BUF_SIZE 1024
+static void __init clean_rootfs(void)
+{
+        int fd;
+        void *buf;
+        struct linux_dirent64 *dirp;
+        int count;
+
+        fd = sys_open("/", O_RDONLY, 0);
+        WARN_ON(fd < 0);
+        if (fd < 0)
+                return;
+        buf = kzalloc(BUF_SIZE, GFP_KERNEL);
+        WARN_ON(!buf);
+        if (!buf) {
+                sys_close(fd);
+                return;
+        }
+
+        dirp = buf;
+        count = sys_getdents64(fd, dirp, BUF_SIZE);
+        while (count > 0) {
+                while (count > 0) {
+                        struct stat st;
+                        int ret;
+
+                        ret = sys_newlstat(dirp->d_name, &st);
+                        WARN_ON_ONCE(ret);
+                        if (!ret) {
+                                if (S_ISDIR(st.st_mode))
+                                        sys_rmdir(dirp->d_name);
+                                else
+                                        sys_unlink(dirp->d_name);
+                        }
+
+                        count -= dirp->d_reclen;
+                        dirp = (void *)dirp + dirp->d_reclen;
+                }
+                dirp = buf;
+                memset(buf, 0, BUF_SIZE);
+                count = sys_getdents64(fd, dirp, BUF_SIZE);
+        }
+
+        sys_close(fd);
+        kfree(buf);
+}
+
 static int __init populate_rootfs(void)
 {
         char *err = unpack_to_rootfs(__initramfs_start,
-                         __initramfs_end - __initramfs_start, 0);
+                         __initramfs_end - __initramfs_start);
         if (err)
-                panic(err);
+                panic(err);     /* Failed to decompress INTERNAL initramfs */
         if (initrd_start) {
 #ifdef CONFIG_BLK_DEV_RAM
                 int fd;
-                printk(KERN_INFO "checking if image is initramfs...");
+                printk(KERN_INFO "checking if image is initramfs...\n");
                 err = unpack_to_rootfs((char *)initrd_start,
-                        initrd_end - initrd_start, 1);
+                        initrd_end - initrd_start);
                 if (!err) {
-                        printk(" it is\n");
-                        unpack_to_rootfs((char *)initrd_start,
-                                initrd_end - initrd_start, 0);
+                        printk(KERN_INFO "rootfs image is initramfs; unpacking...\n");
                         free_initrd();
                         return 0;
+                } else {
+                        clean_rootfs();
+                        unpack_to_rootfs(__initramfs_start,
+                                 __initramfs_end - __initramfs_start);
                 }
-                printk("it isn't (%s); looks like an initrd\n", err);
+                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);
                 if (fd >= 0) {
                         sys_write(fd, (char *)initrd_start,
@@ -604,10 +595,13 @@ static int __init populate_rootfs(void)
 #else
                 printk(KERN_INFO "Unpacking initramfs...");
                 err = unpack_to_rootfs((char *)initrd_start,
-                        initrd_end - initrd_start, 0);
-                if (err)
-                        panic(err);
-                printk(" done\n");
+                        initrd_end - initrd_start);
+                if (err) {
+                        printk(" failed!\n");
+                        printk(KERN_EMERG "%s\n", err);
+                } else {
+                        printk(" done\n");
+                }
                 free_initrd();
 #endif
         }
diff --git a/init/main.c b/init/main.c
index 844209453c02..3585f073d636 100644
--- a/init/main.c
+++ b/init/main.c
@@ -14,6 +14,7 @@
 #include <linux/proc_fs.h>
 #include <linux/kernel.h>
 #include <linux/syscalls.h>
+#include <linux/stackprotector.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/delay.h>
@@ -70,6 +71,7 @@
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
+#include <trace/kmemtrace.h>
 
 #ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/smp.h>
@@ -97,7 +99,7 @@ static inline void mark_rodata_ro(void) { }
 extern void tc_init(void);
 #endif
 
-enum system_states system_state;
+enum system_states system_state __read_mostly;
 EXPORT_SYMBOL(system_state);
 
 /*
@@ -135,14 +137,14 @@ unsigned int __initdata setup_max_cpus = NR_CPUS;
  * greater than 0, limits the maximum number of CPUs activated in
  * SMP mode to <NUM>.
  */
-#ifndef CONFIG_X86_IO_APIC
-static inline void disable_ioapic_setup(void) {};
-#endif
+
+void __weak arch_disable_smp_support(void) { }
 
 static int __init nosmp(char *str)
 {
         setup_max_cpus = 0;
-        disable_ioapic_setup();
+        arch_disable_smp_support();
+
         return 0;
 }
 
@@ -152,14 +154,14 @@ static int __init maxcpus(char *str)
 {
         get_option(&str, &setup_max_cpus);
         if (setup_max_cpus == 0)
-                disable_ioapic_setup();
+                arch_disable_smp_support();
 
         return 0;
 }
 
 early_param("maxcpus", maxcpus);
 #else
-#define setup_max_cpus NR_CPUS
+const unsigned int setup_max_cpus = NR_CPUS;
 #endif
 
 /*
@@ -406,8 +408,7 @@ static void __init smp_init(void)
          * Set up the current CPU as possible to migrate to.
          * The other ones will be done by cpu_up/cpu_down()
          */
-        cpu = smp_processor_id();
-        cpu_set(cpu, cpu_active_map);
+        set_cpu_active(smp_processor_id(), true);
 
         /* FIXME: This should be done in userspace --RR */
         for_each_present_cpu(cpu) {
@@ -463,6 +464,7 @@ static noinline void __init_refok rest_init(void)
          * at least once to get things moving:
          */
         init_idle_bootup_task(current);
+        rcu_scheduler_starting();
         preempt_enable_no_resched();
         schedule();
         preempt_disable();
@@ -539,6 +541,12 @@ asmlinkage void __init start_kernel(void)
          */
         lockdep_init();
         debug_objects_early_init();
+
+        /*
+         * Set up the the initial canary ASAP:
+         */
+        boot_init_stack_canary();
+
         cgroup_init_early();
 
         local_irq_disable();
@@ -641,6 +649,7 @@ asmlinkage void __init start_kernel(void)
         enable_debug_pagealloc();
         cpu_hotplug_init();
         kmem_cache_init();
+        kmemtrace_init();
         debug_objects_mem_init();
         idr_init_cache();
         setup_per_cpu_pageset();
@@ -762,6 +771,7 @@ static void __init do_basic_setup(void)
 {
         rcu_init_sched(); /* needed by module_init stage. */
         init_workqueues();
+        cpuset_init_smp();
         usermodehelper_init();
         driver_init();
         init_irq_proc();
@@ -786,6 +796,7 @@ static void run_init_process(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();
@@ -834,7 +845,7 @@ static int __init kernel_init(void * unused)
         /*
          * init can run on any cpu.
          */
-        set_cpus_allowed_ptr(current, CPU_MASK_ALL_PTR);
+        set_cpus_allowed_ptr(current, cpu_all_mask);
         /*
          * Tell the world that we're going to be the grim
          * reaper of innocent orphaned children.
@@ -855,8 +866,6 @@ static int __init kernel_init(void * unused)
         smp_init();
         sched_init_smp();
 
-        cpuset_init_smp();
-
         do_basic_setup();
 
         /*