Merge branch 'akpm-incoming-2'

* akpm-incoming-2: (139 commits)
  epoll: make epoll_wait() use the hrtimer range feature
  select: rename estimate_accuracy() to select_estimate_accuracy()
  Remove duplicate includes from many files
  ramoops: use the platform data structure instead of module params
  kernel/resource.c: handle reinsertion of an already-inserted resource
  kfifo: fix kfifo_alloc() to return a signed int value
  w1: don't allow arbitrary users to remove w1 devices
  alpha: remove dma64_addr_t usage
  mips: remove dma64_addr_t usage
  sparc: remove dma64_addr_t usage
  fuse: use release_pages()
  taskstats: use real microsecond granularity for CPU times
  taskstats: split fill_pid function
  taskstats: separate taskstats commands
  delayacct: align to 8 byte boundary on 64-bit systems
  delay-accounting: reimplement -c for getdelays.c to report information on a target command
  namespaces Kconfig: move namespace menu location after the cgroup
  namespaces Kconfig: remove the cgroup device whitelist experimental tag
  namespaces Kconfig: remove pointless cgroup dependency
  namespaces Kconfig: make namespace a submenu
  ...

5 files changed, 87 insertions, 11 deletions

diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index 6e25c2659e0a..a2976a6de033 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -21,6 +21,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/socket.h>
+#include <sys/wait.h>
 #include <signal.h>
 
 #include <linux/genetlink.h>
@@ -266,11 +267,13 @@ int main(int argc, char *argv[])
         int containerset = 0;
         char containerpath[1024];
         int cfd = 0;
+        int forking = 0;
+        sigset_t sigset;
 
         struct msgtemplate msg;
 
-        while (1) {
-                c = getopt(argc, argv, "qdiw:r:m:t:p:vlC:");
+        while (!forking) {
+                c = getopt(argc, argv, "qdiw:r:m:t:p:vlC:c:");
                 if (c < 0)
                         break;
 
@@ -319,6 +322,28 @@ int main(int argc, char *argv[])
                                 err(1, "Invalid pid\n");
                         cmd_type = TASKSTATS_CMD_ATTR_PID;
                         break;
+                case 'c':
+
+                        /* Block SIGCHLD for sigwait() later */
+                        if (sigemptyset(&sigset) == -1)
+                                err(1, "Failed to empty sigset");
+                        if (sigaddset(&sigset, SIGCHLD))
+                                err(1, "Failed to set sigchld in sigset");
+                        sigprocmask(SIG_BLOCK, &sigset, NULL);
+
+                        /* fork/exec a child */
+                        tid = fork();
+                        if (tid < 0)
+                                err(1, "Fork failed\n");
+                        if (tid == 0)
+                                if (execvp(argv[optind - 1],
+                                    &argv[optind - 1]) < 0)
+                                        exit(-1);
+
+                        /* Set the command type and avoid further processing */
+                        cmd_type = TASKSTATS_CMD_ATTR_PID;
+                        forking = 1;
+                        break;
                 case 'v':
                         printf("debug on\n");
                         dbg = 1;
@@ -370,6 +395,15 @@ int main(int argc, char *argv[])
                 goto err;
         }
 
+        /*
+         * If we forked a child, wait for it to exit. Cannot use waitpid()
+         * as all the delicious data would be reaped as part of the wait
+         */
+        if (tid && forking) {
+                int sig_received;
+                sigwait(&sigset, &sig_received);
+        }
+
         if (tid) {
                 rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET,
                               cmd_type, &tid, sizeof(__u32));
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index b34823ff1646..190018b0c649 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -18,7 +18,8 @@ CONTENTS:
   1.2 Why are cgroups needed ?
   1.3 How are cgroups implemented ?
   1.4 What does notify_on_release do ?
-  1.5 How do I use cgroups ?
+  1.5 What does clone_children do ?
+  1.6 How do I use cgroups ?
 2. Usage Examples and Syntax
   2.1 Basic Usage
   2.2 Attaching processes
@@ -293,7 +294,16 @@ notify_on_release in the root cgroup at system boot is disabled
 value of their parents notify_on_release setting. The default value of
 a cgroup hierarchy's release_agent path is empty.
 
-1.5 How do I use cgroups ?
+1.5 What does clone_children do ?
+---------------------------------
+
+If the clone_children flag is enabled (1) in a cgroup, then all
+cgroups created beneath will call the post_clone callbacks for each
+subsystem of the newly created cgroup. Usually when this callback is
+implemented for a subsystem, it copies the values of the parent
+subsystem, this is the case for the cpuset.
+
+1.6 How do I use cgroups ?
 --------------------------
 
 To start a new job that is to be contained within a cgroup, using
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index d2af87ba96e1..f3da8c0a3af2 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -526,6 +526,23 @@ Who:	FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
 
 ----------------------------
 
+What:   namespace cgroup (ns_cgroup)
+When:   2.6.38
+Why:    The ns_cgroup leads to some problems:
+        * cgroup creation is out-of-control
+        * cgroup name can conflict when pids are looping
+        * it is not possible to have a single process handling
+        a lot of namespaces without falling in a exponential creation time
+        * we may want to create a namespace without creating a cgroup
+
+        The ns_cgroup is replaced by a compatibility flag 'clone_children',
+        where a newly created cgroup will copy the parent cgroup values.
+        The userspace has to manually create a cgroup and add a task to
+        the 'tasks' file.
+Who:    Daniel Lezcano <daniel.lezcano@free.fr>
+
+----------------------------
+
 What:   iwlwifi disable_hw_scan module parameters
 When:   2.6.40
 Why:    Hareware scan is the prefer method for iwlwifi devices for
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index a563b74c7aef..e73df2722ff3 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -136,6 +136,7 @@ Table 1-1: Process specific entries in /proc
  statm          Process memory status information
  status         Process status in human readable form
  wchan          If CONFIG_KALLSYMS is set, a pre-decoded wchan
+ pagemap        Page table
  stack          Report full stack trace, enable via CONFIG_STACKTRACE
  smaps          a extension based on maps, showing the memory consumption of
                 each mapping
@@ -370,6 +371,7 @@ Shared_Dirty:          0 kB
 Private_Clean:         0 kB
 Private_Dirty:         0 kB
 Referenced:          892 kB
+Anonymous:             0 kB
 Swap:                  0 kB
 KernelPageSize:        4 kB
 MMUPageSize:           4 kB
@@ -378,9 +380,15 @@ The first of these lines shows the same information as is displayed for the
 mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
 (size), the amount of the mapping that is currently resident in RAM (RSS), the
 process' proportional share of this mapping (PSS), the number of clean and
-dirty shared pages in the mapping, and the number of clean and dirty private
-pages in the mapping.  The "Referenced" indicates the amount of memory
-currently marked as referenced or accessed.
+dirty private pages in the mapping.  Note that even a page which is part of a
+MAP_SHARED mapping, but has only a single pte mapped, i.e.  is currently used
+by only one process, is accounted as private and not as shared.  "Referenced"
+indicates the amount of memory currently marked as referenced or accessed.
+"Anonymous" shows the amount of memory that does not belong to any file.  Even
+a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
+and a page is modified, the file page is replaced by a private anonymous copy.
+"Swap" shows how much would-be-anonymous memory is also used, but out on
+swap.
 
 This file is only present if the CONFIG_MMU kernel configuration option is
 enabled.
@@ -397,6 +405,9 @@ To clear the bits for the file mapped pages associated with the process
     > echo 3 > /proc/PID/clear_refs
 Any other value written to /proc/PID/clear_refs will have no effect.
 
+The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
+using /proc/kpageflags and number of times a page is mapped using
+/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
 
 1.2 Kernel data
 ---------------
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index b606c2c4dd37..30289fab86eb 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -80,8 +80,10 @@ dirty_background_bytes
 Contains the amount of dirty memory at which the pdflush background writeback
 daemon will start writeback.
 
-If dirty_background_bytes is written, dirty_background_ratio becomes a function
-of its value (dirty_background_bytes / the amount of dirtyable system memory).
+Note: dirty_background_bytes is the counterpart of dirty_background_ratio. Only
+one of them may be specified at a time. When one sysctl is written it is
+immediately taken into account to evaluate the dirty memory limits and the
+other appears as 0 when read.
 
 ==============================================================
 
@@ -97,8 +99,10 @@ dirty_bytes
 Contains the amount of dirty memory at which a process generating disk writes
 will itself start writeback.
 
-If dirty_bytes is written, dirty_ratio becomes a function of its value
-(dirty_bytes / the amount of dirtyable system memory).
+Note: dirty_bytes is the counterpart of dirty_ratio. Only one of them may be
+specified at a time. When one sysctl is written it is immediately taken into
+account to evaluate the dirty memory limits and the other appears as 0 when
+read.
 
 Note: the minimum value allowed for dirty_bytes is two pages (in bytes); any
 value lower than this limit will be ignored and the old configuration will be