Merge commit 'v2.6.29-rc1' into perfcounters/core

Conflicts:
	include/linux/kernel_stat.h

1 files changed, 204 insertions, 87 deletions

diff --git a/init/Kconfig b/init/Kconfig
index c38ae71a5e19..a588cdc274bc 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -271,59 +271,6 @@ config LOG_BUF_SHIFT
                      13 =>  8 KB
                      12 =>  4 KB
 
-config CGROUPS
-        bool "Control Group support"
-        help
-          This option will let you use process cgroup subsystems
-          such as Cpusets
-
-          Say N if unsure.
-
-config CGROUP_DEBUG
-        bool "Example debug cgroup subsystem"
-        depends on CGROUPS
-        default n
-        help
-          This option enables a simple cgroup subsystem that
-          exports useful debugging information about the cgroups
-          framework
-
-          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.
-
-config CGROUP_FREEZER
-        bool "control group freezer 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 SMP && CGROUPS
-        help
-          This option will let you create and manage CPUSETs which
-          allow dynamically partitioning a system into sets of CPUs and
-          Memory Nodes and assigning tasks to run only within those sets.
-          This is primarily useful on large SMP or NUMA systems.
-
-          Say N if unsure.
-
 #
 # Architectures with an unreliable sched_clock() should select this:
 #
@@ -337,6 +284,8 @@ config GROUP_SCHED
         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"
@@ -379,6 +328,66 @@ config CGROUP_SCHED
 
 endchoice
 
+menu "Control Group support"
+config CGROUPS
+        bool "Control Group support"
+        help
+          This option add 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)
+
+          Say N if unsure.
+
+config CGROUP_DEBUG
+        bool "Example debug cgroup subsystem"
+        depends on CGROUPS
+        default n
+        help
+          This option enables a simple cgroup subsystem that
+          exports useful debugging information about the cgroups
+          framework
+
+          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.
+
+config CGROUP_FREEZER
+        bool "control group freezer 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 SMP && CGROUPS
+        help
+          This option will let you create and manage CPUSETs which
+          allow dynamically partitioning a system into sets of CPUs and
+          Memory Nodes and assigning tasks to run only within those sets.
+          This is primarily useful on large SMP or NUMA systems.
+
+          Say N if unsure.
+
 config CGROUP_CPUACCT
         bool "Simple CPU accounting cgroup subsystem"
         depends on CGROUPS
@@ -393,9 +402,6 @@ config RESOURCE_COUNTERS
           infrastructure that works with cgroups
         depends on CGROUPS
 
-config MM_OWNER
-        bool
-
 config CGROUP_MEM_RES_CTLR
         bool "Memory Resource Controller for Control Groups"
         depends on CGROUPS && RESOURCE_COUNTERS
@@ -414,36 +420,68 @@ config CGROUP_MEM_RES_CTLR
           sure you need the memory resource controller. Even when you enable
           this, you can set "cgroup_disable=memory" at your boot option to
           disable memory resource controller and you can avoid overheads.
-          (and lose benefits of memory resource contoller)
+          (and lose benefits of memory resource controller)
 
           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
+        help
+          Add swap management feature to memory resource controller. When you
+          enable this, you can limit mem+swap usage per cgroup. In other words,
+          when you disable this, memory resource controller has no cares to
+          usage of swap...a process can exhaust all of the swap. This extension
+          is useful when you want to avoid exhaustion swap but this itself
+          adds more overheads and consumes memory for remembering information.
+          Especially if you use 32bit system or small memory system, please
+          be careful about enabling this. When memory resource controller
+          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.
+
+
+endmenu
+
 config SYSFS_DEPRECATED
         bool
 
 config SYSFS_DEPRECATED_V2
-        bool "Create deprecated sysfs files"
+        bool "Create deprecated sysfs layout for older userspace tools"
         depends on SYSFS
         default y
         select SYSFS_DEPRECATED
         help
-          This option creates deprecated symlinks such as the
-          "device"-link, the <subsystem>:<name>-link, and the
-          "bus"-link. It may also add deprecated key in the
-          uevent environment.
-          None of these features or values should be used today, as
-          they export driver core implementation details to userspace
-          or export properties which can't be kept stable across kernel
-          releases.
-
-          If enabled, this option will also move any device structures
-          that belong to a class, back into the /sys/class hierarchy, in
-          order to support older versions of udev and some userspace
-          programs.
-
-          If you are using a distro with the most recent userspace
-          packages, it should be safe to say N here.
+          This option switches the layout of sysfs to the deprecated
+          version.
+
+          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 PROC_PID_CPUSET
         bool "Include legacy /proc/<pid>/cpuset file"
@@ -868,10 +906,6 @@ config RT_MUTEXES
         boolean
         select PLIST
 
-config TINY_SHMEM
-        default !SHMEM
-        bool
-
 config BASE_SMALL
         int
         default 0 if BASE_FULL
@@ -946,14 +980,17 @@ config MODULE_SRCVERSION_ALL
           the version).  With this option, such a "srcversion" field
           will be created for all modules.  If unsure, say N.
 
-config KMOD
-        def_bool y
-        help
-          This is being removed soon.  These days, CONFIG_MODULES
-          implies CONFIG_KMOD, so use that instead.
-
 endif # MODULES
 
+config INIT_ALL_POSSIBLE
+        bool
+        help
+          Back when each arch used to define their own cpu_online_map and
+          cpu_possible_map, some of them chose to initialize cpu_possible_map
+          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.
+
 config STOP_MACHINE
         bool
         default y
@@ -966,10 +1003,90 @@ source "block/Kconfig"
 config PREEMPT_NOTIFIERS
         bool
 
+choice
+        prompt "RCU Implementation"
+        default CLASSIC_RCU
+
 config CLASSIC_RCU
-        def_bool !PREEMPT_RCU
+        bool "Classic RCU"
         help
           This option selects the classic RCU implementation that is
           designed for best read-side performance on non-realtime
-          systems.  Classic RCU is the default.  Note that the
-          PREEMPT_RCU symbol is used to select/deselect this option.
+          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.