The patch titled
memrlimit: setup the memrlimit controller
has been removed from the -mm tree. Its filename was
memrlimit-setup-the-memrlimit-controller.patch
This patch was dropped because of lack of enthusiasm
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: memrlimit: setup the memrlimit controller
From: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
This patch sets up the rlimit cgroup controller. It adds the basic create,
destroy and populate functionality. The user interface provided is very
similar to the memory resource controller. The rlimit controller can be
enhanced easily in the future to control mlocked pages.
[menage@xxxxxxxxxx: convert res_counter_write() to be a cgroups write_string() handler]
[balbir@xxxxxxxxxxxxxxxxxx: correct mremap and move_vma accounting]
Acked-by: Pavel Emelyanov <xemul@xxxxxxxxxx>
Signed-off-by: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Cc: Sudhir Kumar <skumar@xxxxxxxxxxxxxxxxxx>
Cc: YAMAMOTO Takashi <yamamoto@xxxxxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: Li Zefan <lizf@xxxxxxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Vivek Goyal <vgoyal@xxxxxxxxxx>
Signed-off-by: Paul Menage <menage@xxxxxxxxxx>
Signed-off-by: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/cgroup_subsys.h | 4
include/linux/memrlimitcgroup.h | 19 ++++
init/Kconfig | 10 ++
kernel/cgroup.c | 5 -
kernel/exit.c | 2
mm/Makefile | 1
mm/memrlimitcgroup.c | 131 ++++++++++++++++++++++++++++++
mm/mremap.c | 9 +-
8 files changed, 177 insertions(+), 4 deletions(-)
diff -puN include/linux/cgroup_subsys.h~memrlimit-setup-the-memrlimit-controller include/linux/cgroup_subsys.h
--- a/include/linux/cgroup_subsys.h~memrlimit-setup-the-memrlimit-controller
+++ a/include/linux/cgroup_subsys.h
@@ -53,4 +53,8 @@ SUBSYS(devices)
SUBSYS(freezer)
#endif
+#ifdef CONFIG_CGROUP_MEMRLIMIT_CTLR
+SUBSYS(memrlimit_cgroup)
+#endif
+
/* */
diff -puN /dev/null include/linux/memrlimitcgroup.h
--- /dev/null
+++ a/include/linux/memrlimitcgroup.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright © International Business Machines Corp., 2008
+ *
+ * Author: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
+ *
+ * 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_MEMRLIMITCGROUP_H
+#define LINUX_MEMRLIMITCGROUP_H
+
+#endif /* LINUX_MEMRLIMITCGROUP_H */
diff -puN init/Kconfig~memrlimit-setup-the-memrlimit-controller init/Kconfig
--- a/init/Kconfig~memrlimit-setup-the-memrlimit-controller
+++ a/init/Kconfig
@@ -415,6 +415,16 @@ config CGROUP_MEM_RES_CTLR
This config option also selects MM_OWNER config option, which
could in turn add some fork/exit overhead.
+config CGROUP_MEMRLIMIT_CTLR
+ bool "Memory resource limit controls for cgroups"
+ depends on CGROUPS && RESOURCE_COUNTERS && MMU
+ select MM_OWNER
+ help
+ Provides resource limits for all the tasks belonging to a
+ control group. CGROUP_MEM_RES_CTLR provides support for physical
+ memory RSS and Page Cache control. Virtual address space control
+ is provided by this controller.
+
config SYSFS_DEPRECATED
bool
diff -puN mm/Makefile~memrlimit-setup-the-memrlimit-controller mm/Makefile
--- a/mm/Makefile~memrlimit-setup-the-memrlimit-controller
+++ a/mm/Makefile
@@ -35,4 +35,5 @@ obj-$(CONFIG_MIGRATION) += migrate.o
obj-$(CONFIG_SMP) += allocpercpu.o
obj-$(CONFIG_QUICKLIST) += quicklist.o
obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
+obj-$(CONFIG_CGROUP_MEMRLIMIT_CTLR) += memrlimitcgroup.o
obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
diff -puN /dev/null mm/memrlimitcgroup.c
--- /dev/null
+++ a/mm/memrlimitcgroup.c
@@ -0,0 +1,131 @@
+/*
+ * Copyright © International Business Machines Corp., 2008
+ *
+ * Author: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
+ *
+ * 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.
+ *
+ * Provide memory resource limits for tasks in a control group. A lot of code is
+ * duplicated from the memory controller (this code is common to almost
+ * all controllers). TODO: Consider writing a tool that can generate this
+ * code.
+ */
+#include <linux/cgroup.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/rcupdate.h>
+#include <linux/slab.h>
+#include <linux/swap.h>
+#include <linux/spinlock.h>
+#include <linux/fs.h>
+#include <linux/res_counter.h>
+#include <linux/memrlimitcgroup.h>
+
+struct cgroup_subsys memrlimit_cgroup_subsys;
+
+struct memrlimit_cgroup {
+ struct cgroup_subsys_state css;
+ struct res_counter as_res; /* address space counter */
+};
+
+static struct memrlimit_cgroup init_memrlimit_cgroup;
+
+static struct memrlimit_cgroup *memrlimit_cgroup_from_cgrp(struct cgroup *cgrp)
+{
+ return container_of(cgroup_subsys_state(cgrp,
+ memrlimit_cgroup_subsys_id),
+ struct memrlimit_cgroup, css);
+}
+
+static struct cgroup_subsys_state *
+memrlimit_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+ struct memrlimit_cgroup *memrcg;
+
+ if (unlikely(cgrp->parent == NULL))
+ memrcg = &init_memrlimit_cgroup;
+ else {
+ memrcg = kzalloc(sizeof(*memrcg), GFP_KERNEL);
+ if (!memrcg)
+ return ERR_PTR(-ENOMEM);
+ }
+ res_counter_init(&memrcg->as_res);
+ return &memrcg->css;
+}
+
+static void memrlimit_cgroup_destroy(struct cgroup_subsys *ss,
+ struct cgroup *cgrp)
+{
+ kfree(memrlimit_cgroup_from_cgrp(cgrp));
+}
+
+static int memrlimit_cgroup_reset(struct cgroup *cgrp, unsigned int event)
+{
+ struct memrlimit_cgroup *memrcg;
+
+ memrcg = memrlimit_cgroup_from_cgrp(cgrp);
+ switch (event) {
+ case RES_FAILCNT:
+ res_counter_reset_failcnt(&memrcg->as_res);
+ break;
+ }
+ return 0;
+}
+
+static u64 memrlimit_cgroup_read(struct cgroup *cgrp, struct cftype *cft)
+{
+ return res_counter_read_u64(&memrlimit_cgroup_from_cgrp(cgrp)->as_res,
+ cft->private);
+}
+
+static int memrlimit_cgroup_write(struct cgroup *cgrp, struct cftype *cft,
+ const char *buffer)
+{
+ return res_counter_write(&memrlimit_cgroup_from_cgrp(cgrp)->as_res,
+ cft->private, buffer,
+ res_counter_memparse_write_strategy);
+}
+
+static struct cftype memrlimit_cgroup_files[] = {
+ {
+ .name = "usage_in_bytes",
+ .private = RES_USAGE,
+ .read_u64 = memrlimit_cgroup_read,
+ },
+ {
+ .name = "limit_in_bytes",
+ .private = RES_LIMIT,
+ .write_string = memrlimit_cgroup_write,
+ .read_u64 = memrlimit_cgroup_read,
+ },
+ {
+ .name = "failcnt",
+ .private = RES_FAILCNT,
+ .trigger = memrlimit_cgroup_reset,
+ .read_u64 = memrlimit_cgroup_read,
+ },
+};
+
+static int memrlimit_cgroup_populate(struct cgroup_subsys *ss,
+ struct cgroup *cgrp)
+{
+ return cgroup_add_files(cgrp, ss, memrlimit_cgroup_files,
+ ARRAY_SIZE(memrlimit_cgroup_files));
+}
+
+struct cgroup_subsys memrlimit_cgroup_subsys = {
+ .name = "memrlimit",
+ .subsys_id = memrlimit_cgroup_subsys_id,
+ .create = memrlimit_cgroup_create,
+ .destroy = memrlimit_cgroup_destroy,
+ .populate = memrlimit_cgroup_populate,
+ .early_init = 0,
+};
diff -puN mm/mremap.c~memrlimit-setup-the-memrlimit-controller mm/mremap.c
--- a/mm/mremap.c~memrlimit-setup-the-memrlimit-controller
+++ a/mm/mremap.c
@@ -182,10 +182,15 @@ static unsigned long move_vma(struct vm_
if (mm->map_count >= sysctl_max_map_count - 3)
return -ENOMEM;
+ if (memrlimit_cgroup_charge_as(mm, new_len >> PAGE_SHIFT))
+ return -ENOMEM;
+
new_pgoff = vma->vm_pgoff + ((old_addr - vma->vm_start) >> PAGE_SHIFT);
new_vma = copy_vma(&vma, new_addr, new_len, new_pgoff);
- if (!new_vma)
+ if (!new_vma) {
+ memrlimit_cgroup_uncharge_as(mm, new_len >> PAGE_SHIFT);
return -ENOMEM;
+ }
moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len);
if (moved_len < old_len) {
@@ -389,6 +394,8 @@ unsigned long do_mremap(unsigned long ad
}
}
+ memrlimit_cgroup_uncharge_as(mm, (new_len - old_len) >> PAGE_SHIFT);
+
/*
* We weren't able to just expand or shrink the area,
* we need to create a new one and move it..
diff -puN kernel/cgroup.c~memrlimit-setup-the-memrlimit-controller kernel/cgroup.c
--- a/kernel/cgroup.c~memrlimit-setup-the-memrlimit-controller
+++ a/kernel/cgroup.c
@@ -2796,13 +2796,14 @@ void cgroup_fork_callbacks(struct task_s
*/
void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
{
- struct cgroup *oldcgrp, *newcgrp = NULL;
+ struct cgroup *oldcgrp = NULL, *newcgrp = NULL;
if (need_mm_owner_callback) {
int i;
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
- oldcgrp = task_cgroup(old, ss->subsys_id);
+ if (old)
+ oldcgrp = task_cgroup(old, ss->subsys_id);
if (new)
newcgrp = task_cgroup(new, ss->subsys_id);
if (oldcgrp == newcgrp)
diff -puN kernel/exit.c~memrlimit-setup-the-memrlimit-controller kernel/exit.c
--- a/kernel/exit.c~memrlimit-setup-the-memrlimit-controller
+++ a/kernel/exit.c
@@ -638,8 +638,8 @@ retry:
* so that subsystems can understand the callback and take action.
*/
down_write(&mm->mmap_sem);
- cgroup_mm_owner_callbacks(mm->owner, NULL);
mm->owner = NULL;
+ cgroup_mm_owner_callbacks(mm->owner, NULL);
up_write(&mm->mmap_sem);
return;
_
Patches currently in -mm which might be from balbir@xxxxxxxxxxxxxxxxxx are
origin.patch
linux-next.patch
memrlimit-setup-the-memrlimit-controller.patch
memrlimit-add-memrlimit-controller-accounting-and-control.patch
memrlimit-handle-attach_task-failure-add-can_attach-callback.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
