4 files changed, 268 insertions, 8 deletions

diff --git a/Documentation/cgroups/cgroup_event_listener.c b/Documentation/cgroups/cgroup_event_listener.c
new file mode 100644
index 00000000000..8c2bfc4a635
--- /dev/null
+++ b/Documentation/cgroups/cgroup_event_listener.c
@@ -0,0 +1,110 @@
+/*
+ * cgroup_event_listener.c - Simple listener of cgroup events
+ *
+ * Copyright (C) Kirill A. Shutemov <kirill@shutemov.name>
+ */
+
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <libgen.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/eventfd.h>
+
+#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>\n"
+
+int main(int argc, char **argv)
+{
+        int efd = -1;
+        int cfd = -1;
+        int event_control = -1;
+        char event_control_path[PATH_MAX];
+        char line[LINE_MAX];
+        int ret;
+
+        if (argc != 3) {
+                fputs(USAGE_STR, stderr);
+                return 1;
+        }
+
+        cfd = open(argv[1], O_RDONLY);
+        if (cfd == -1) {
+                fprintf(stderr, "Cannot open %s: %s\n", argv[1],
+                                strerror(errno));
+                goto out;
+        }
+
+        ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control",
+                        dirname(argv[1]));
+        if (ret >= PATH_MAX) {
+                fputs("Path to cgroup.event_control is too long\n", stderr);
+                goto out;
+        }
+
+        event_control = open(event_control_path, O_WRONLY);
+        if (event_control == -1) {
+                fprintf(stderr, "Cannot open %s: %s\n", event_control_path,
+                                strerror(errno));
+                goto out;
+        }
+
+        efd = eventfd(0, 0);
+        if (efd == -1) {
+                perror("eventfd() failed");
+                goto out;
+        }
+
+        ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]);
+        if (ret >= LINE_MAX) {
+                fputs("Arguments string is too long\n", stderr);
+                goto out;
+        }
+
+        ret = write(event_control, line, strlen(line) + 1);
+        if (ret == -1) {
+                perror("Cannot write to cgroup.event_control");
+                goto out;
+        }
+
+        while (1) {
+                uint64_t result;
+
+                ret = read(efd, &result, sizeof(result));
+                if (ret == -1) {
+                        if (errno == EINTR)
+                                continue;
+                        perror("Cannot read from eventfd");
+                        break;
+                }
+                assert(ret == sizeof(result));
+
+                ret = access(event_control_path, W_OK);
+                if ((ret == -1) && (errno == ENOENT)) {
+                                puts("The cgroup seems to have removed.");
+                                ret = 0;
+                                break;
+                }
+
+                if (ret == -1) {
+                        perror("cgroup.event_control "
+                                        "is not accessable any more");
+                        break;
+                }
+
+                printf("%s %s: crossed\n", argv[1], argv[2]);
+        }
+
+out:
+        if (efd >= 0)
+                close(efd);
+        if (event_control >= 0)
+                close(event_control);
+        if (cfd >= 0)
+                close(cfd);
+
+        return (ret != 0);
+}
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 0b33bfe7dde..fd588ff0e29 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -22,6 +22,8 @@ CONTENTS:
 2. Usage Examples and Syntax
   2.1 Basic Usage
   2.2 Attaching processes
+  2.3 Mounting hierarchies by name
+  2.4 Notification API
 3. Kernel API
   3.1 Overview
   3.2 Synchronization
@@ -434,6 +436,25 @@ you give a subsystem a name.
 The name of the subsystem appears as part of the hierarchy description
 in /proc/mounts and /proc/<pid>/cgroups.
 
+2.4 Notification API
+--------------------
+
+There is mechanism which allows to get notifications about changing
+status of a cgroup.
+
+To register new notification handler you need:
+ - create a file descriptor for event notification using eventfd(2);
+ - open a control file to be monitored (e.g. memory.usage_in_bytes);
+ - write "<event_fd> <control_fd> <args>" to cgroup.event_control.
+   Interpretation of args is defined by control file implementation;
+
+eventfd will be woken up by control file implementation or when the
+cgroup is removed.
+
+To unregister notification handler just close eventfd.
+
+NOTE: Support of notifications should be implemented for the control
+file. See documentation for the subsystem.
 
 3. Kernel API
 =============
@@ -488,6 +509,11 @@ Each subsystem should:
 - add an entry in linux/cgroup_subsys.h
 - define a cgroup_subsys object called <name>_subsys
 
+If a subsystem can be compiled as a module, it should also have in its
+module initcall a call to cgroup_load_subsys(), and in its exitcall a
+call to cgroup_unload_subsys(). It should also set its_subsys.module =
+THIS_MODULE in its .c file.
+
 Each subsystem may export the following methods. The only mandatory
 methods are create/destroy. Any others that are null are presumed to
 be successful no-ops.
@@ -536,10 +562,21 @@ returns an error, this will abort the attach operation.  If a NULL
 task is passed, then a successful result indicates that *any*
 unspecified task can be moved into the cgroup. Note that this isn't
 called on a fork. If this method returns 0 (success) then this should
-remain valid while the caller holds cgroup_mutex. If threadgroup is
+remain valid while the caller holds cgroup_mutex and it is ensured that either
+attach() or cancel_attach() will be called in future. If threadgroup is
 true, then a successful result indicates that all threads in the given
 thread's threadgroup can be moved together.
 
+void cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+               struct task_struct *task, bool threadgroup)
+(cgroup_mutex held by caller)
+
+Called when a task attach operation has failed after can_attach() has succeeded.
+A subsystem whose can_attach() has some side-effects should provide this
+function, so that the subsytem can implement a rollback. If not, not necessary.
+This will be called only about subsystems whose can_attach() operation have
+succeeded.
+
 void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
             struct cgroup *old_cgrp, struct task_struct *task,
             bool threadgroup)
diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
index 72db89ed060..f7f68b2ac19 100644
--- a/Documentation/cgroups/memcg_test.txt
+++ b/Documentation/cgroups/memcg_test.txt
@@ -1,6 +1,6 @@
 Memory Resource Controller(Memcg)  Implementation Memo.
-Last Updated: 2009/1/20
-Base Kernel Version: based on 2.6.29-rc2.
+Last Updated: 2010/2
+Base Kernel Version: based on 2.6.33-rc7-mm(candidate for 34).
 
 Because VM is getting complex (one of reasons is memcg...), memcg's behavior
 is complex. This is a document for memcg's internal behavior.
@@ -337,7 +337,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
         race and lock dependency with other cgroup subsystems.
 
         example)
-        # mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices
+        # mount -t cgroup none /cgroup -o cpuset,memory,cpu,devices
 
         and do task move, mkdir, rmdir etc...under this.
 
@@ -348,7 +348,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 
         For example, test like following is good.
         (Shell-A)
-        # mount -t cgroup none /cgroup -t memory
+        # mount -t cgroup none /cgroup -o memory
         # mkdir /cgroup/test
         # echo 40M > /cgroup/test/memory.limit_in_bytes
         # echo 0 > /cgroup/test/tasks
@@ -378,3 +378,42 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
         #echo 50M > memory.limit_in_bytes
         #echo 50M > memory.memsw.limit_in_bytes
         run 51M of malloc
+
+ 9.9 Move charges at task migration
+        Charges associated with a task can be moved along with task migration.
+
+        (Shell-A)
+        #mkdir /cgroup/A
+        #echo $$ >/cgroup/A/tasks
+        run some programs which uses some amount of memory in /cgroup/A.
+
+        (Shell-B)
+        #mkdir /cgroup/B
+        #echo 1 >/cgroup/B/memory.move_charge_at_immigrate
+        #echo "pid of the program running in group A" >/cgroup/B/tasks
+
+        You can see charges have been moved by reading *.usage_in_bytes or
+        memory.stat of both A and B.
+        See 8.2 of Documentation/cgroups/memory.txt to see what value should be
+        written to move_charge_at_immigrate.
+
+ 9.10 Memory thresholds
+        Memory controler implements memory thresholds using cgroups notification
+        API. You can use Documentation/cgroups/cgroup_event_listener.c to test
+        it.
+
+        (Shell-A) Create cgroup and run event listener
+        # mkdir /cgroup/A
+        # ./cgroup_event_listener /cgroup/A/memory.usage_in_bytes 5M
+
+        (Shell-B) Add task to cgroup and try to allocate and free memory
+        # echo $$ >/cgroup/A/tasks
+        # a="$(dd if=/dev/zero bs=1M count=10)"
+        # a=
+
+        You will see message from cgroup_event_listener every time you cross
+        the thresholds.
+
+        Use /cgroup/A/memory.memsw.usage_in_bytes to test memsw thresholds.
+
+        It's good idea to test root cgroup as well.
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index b871f2552b4..f8bc802d70b 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -182,6 +182,8 @@ list.
 NOTE: Reclaim does not work for the root cgroup, since we cannot set any
 limits on the root cgroup.
 
+Note2: When panic_on_oom is set to "2", the whole system will panic.
+
 2. Locking
 
 The memory controller uses the following hierarchy
@@ -262,10 +264,12 @@ some of the pages cached in the cgroup (page cache pages).
 4.2 Task migration
 
 When a task migrates from one cgroup to another, it's charge is not
-carried forward. The pages allocated from the original cgroup still
+carried forward by default. The pages allocated from the original cgroup still
 remain charged to it, the charge is dropped when the page is freed or
 reclaimed.
 
+Note: You can move charges of a task along with task migration. See 8.
+
 4.3 Removing a cgroup
 
 A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
@@ -377,7 +381,8 @@ The feature can be disabled by
 NOTE1: Enabling/disabling will fail if the cgroup already has other
 cgroups created below it.
 
-NOTE2: This feature can be enabled/disabled per subtree.
+NOTE2: When panic_on_oom is set to "2", the whole system will panic in
+case of an oom event in any cgroup.
 
 7. Soft limits
 
@@ -414,7 +419,76 @@ NOTE1: Soft limits take effect over a long period of time, since they involve
 NOTE2: It is recommended to set the soft limit always below the hard limit,
        otherwise the hard limit will take precedence.
 
-8. TODO
+8. Move charges at task migration
+
+Users can move charges associated with a task along with task migration, that
+is, uncharge task's pages from the old cgroup and charge them to the new cgroup.
+This feature is not supported in !CONFIG_MMU environments because of lack of
+page tables.
+
+8.1 Interface
+
+This feature is disabled by default. It can be enabled(and disabled again) by
+writing to memory.move_charge_at_immigrate of the destination cgroup.
+
+If you want to enable it:
+
+# echo (some positive value) > memory.move_charge_at_immigrate
+
+Note: Each bits of move_charge_at_immigrate has its own meaning about what type
+      of charges should be moved. See 8.2 for details.
+Note: Charges are moved only when you move mm->owner, IOW, a leader of a thread
+      group.
+Note: If we cannot find enough space for the task in the destination cgroup, we
+      try to make space by reclaiming memory. Task migration may fail if we
+      cannot make enough space.
+Note: It can take several seconds if you move charges in giga bytes order.
+
+And if you want disable it again:
+
+# echo 0 > memory.move_charge_at_immigrate
+
+8.2 Type of charges which can be move
+
+Each bits of move_charge_at_immigrate has its own meaning about what type of
+charges should be moved.
+
+  bit | what type of charges would be moved ?
+ -----+------------------------------------------------------------------------
+   0  | A charge of an anonymous page(or swap of it) used by the target task.
+      | Those pages and swaps must be used only by the target task. You must
+      | enable Swap Extension(see 2.4) to enable move of swap charges.
+
+Note: Those pages and swaps must be charged to the old cgroup.
+Note: More type of pages(e.g. file cache, shmem,) will be supported by other
+      bits in future.
+
+8.3 TODO
+
+- Add support for other types of pages(e.g. file cache, shmem, etc.).
+- Implement madvise(2) to let users decide the vma to be moved or not to be
+  moved.
+- All of moving charge operations are done under cgroup_mutex. It's not good
+  behavior to hold the mutex too long, so we may need some trick.
+
+9. Memory thresholds
+
+Memory controler implements memory thresholds using cgroups notification
+API (see cgroups.txt). It allows to register multiple memory and memsw
+thresholds and gets notifications when it crosses.
+
+To register a threshold application need:
+ - create an eventfd using eventfd(2);
+ - open memory.usage_in_bytes or memory.memsw.usage_in_bytes;
+ - write string like "<event_fd> <memory.usage_in_bytes> <threshold>" to
+   cgroup.event_control.
+
+Application will be notified through eventfd when memory usage crosses
+threshold in any direction.
+
+It's applicable for root and non-root cgroup.
+
+10. TODO
 
 1. Add support for accounting huge pages (as a separate controller)
 2. Make per-cgroup scanner reclaim not-shared pages first