Memory controller: cgroups setup

Setup the memory cgroup and add basic hooks and controls to integrate
and work with the cgroup.

Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Paul Menage <menage@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Kirill Korotaev <dev@sw.ru>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: David Rientjes <rientjes@google.com>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 161 insertions, 0 deletions

diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 9ec43186ba80..228235c5ae53 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -37,3 +37,8 @@ SUBSYS(cpuacct)
 
 /* */
 
+#ifdef CONFIG_CGROUP_MEM_CONT
+SUBSYS(mem_cgroup)
+#endif
+
+/* */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
new file mode 100644
index 000000000000..3f121b27677a
--- /dev/null
+++ b/include/linux/memcontrol.h
@@ -0,0 +1,21 @@
+/* memcontrol.h - Memory Controller
+ *
+ * Copyright IBM Corporation, 2007
+ * Author Balbir Singh <balbir@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _LINUX_MEMCONTROL_H
+#define _LINUX_MEMCONTROL_H
+
+#endif /* _LINUX_MEMCONTROL_H */
+
diff --git a/init/Kconfig b/init/Kconfig
index d372bd616b0c..95ac2657b0f4 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -397,6 +397,13 @@ config SYSFS_DEPRECATED
           If you are using a distro that was released in 2006 or later,
           it should be safe to say N here.
 
+config CGROUP_MEM_CONT
+        bool "Memory controller for cgroups"
+        depends on CGROUPS && RESOURCE_COUNTERS
+        help
+          Provides a memory controller that manages both page cache and
+          RSS memory.
+
 config PROC_PID_CPUSET
         bool "Include legacy /proc/<pid>/cpuset file"
         depends on CPUSETS
diff --git a/mm/Makefile b/mm/Makefile
index 4af5dff37277..9f117bab5322 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -32,4 +32,5 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_SMP) += allocpercpu.o
 obj-$(CONFIG_QUICKLIST) += quicklist.o
+obj-$(CONFIG_CGROUP_MEM_CONT) += memcontrol.o
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
new file mode 100644
index 000000000000..80e48cd9d0c7
--- /dev/null
+++ b/mm/memcontrol.c
@@ -0,0 +1,127 @@
+/* memcontrol.c - Memory Controller
+ *
+ * Copyright IBM Corporation, 2007
+ * Author Balbir Singh <balbir@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/res_counter.h>
+#include <linux/memcontrol.h>
+#include <linux/cgroup.h>
+
+struct cgroup_subsys mem_cgroup_subsys;
+
+/*
+ * The memory controller data structure. The memory controller controls both
+ * page cache and RSS per cgroup. We would eventually like to provide
+ * statistics based on the statistics developed by Rik Van Riel for clock-pro,
+ * to help the administrator determine what knobs to tune.
+ *
+ * TODO: Add a water mark for the memory controller. Reclaim will begin when
+ * we hit the water mark.
+ */
+struct mem_cgroup {
+        struct cgroup_subsys_state css;
+        /*
+         * the counter to account for memory usage
+         */
+        struct res_counter res;
+};
+
+/*
+ * A page_cgroup page is associated with every page descriptor. The
+ * page_cgroup helps us identify information about the cgroup
+ */
+struct page_cgroup {
+        struct list_head lru;           /* per cgroup LRU list */
+        struct page *page;
+        struct mem_cgroup *mem_cgroup;
+};
+
+
+static inline
+struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
+{
+        return container_of(cgroup_subsys_state(cont,
+                                mem_cgroup_subsys_id), struct mem_cgroup,
+                                css);
+}
+
+static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
+                        struct file *file, char __user *userbuf, size_t nbytes,
+                        loff_t *ppos)
+{
+        return res_counter_read(&mem_cgroup_from_cont(cont)->res,
+                                cft->private, userbuf, nbytes, ppos);
+}
+
+static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
+                                struct file *file, const char __user *userbuf,
+                                size_t nbytes, loff_t *ppos)
+{
+        return res_counter_write(&mem_cgroup_from_cont(cont)->res,
+                                cft->private, userbuf, nbytes, ppos);
+}
+
+static struct cftype mem_cgroup_files[] = {
+        {
+                .name = "usage",
+                .private = RES_USAGE,
+                .read = mem_cgroup_read,
+        },
+        {
+                .name = "limit",
+                .private = RES_LIMIT,
+                .write = mem_cgroup_write,
+                .read = mem_cgroup_read,
+        },
+        {
+                .name = "failcnt",
+                .private = RES_FAILCNT,
+                .read = mem_cgroup_read,
+        },
+};
+
+static struct cgroup_subsys_state *
+mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+        struct mem_cgroup *mem;
+
+        mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);
+        if (!mem)
+                return -ENOMEM;
+
+        res_counter_init(&mem->res);
+        return &mem->css;
+}
+
+static void mem_cgroup_destroy(struct cgroup_subsys *ss,
+                                struct cgroup *cont)
+{
+        kfree(mem_cgroup_from_cont(cont));
+}
+
+static int mem_cgroup_populate(struct cgroup_subsys *ss,
+                                struct cgroup *cont)
+{
+        return cgroup_add_files(cont, ss, mem_cgroup_files,
+                                        ARRAY_SIZE(mem_cgroup_files));
+}
+
+struct cgroup_subsys mem_cgroup_subsys = {
+        .name = "memory",
+        .subsys_id = mem_cgroup_subsys_id,
+        .create = mem_cgroup_create,
+        .destroy = mem_cgroup_destroy,
+        .populate = mem_cgroup_populate,
+        .early_init = 0,
+};