The patch titled
memrlimit: add memrlimit controller accounting and control
has been added to the -mm tree. Its filename is
memrlimit-add-memrlimit-controller-accounting-and-control.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: memrlimit: add memrlimit controller accounting and control
From: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
This patch adds support for accounting and control of virtual address space
limits. The accounting is done via the rlimit_cgroup_(un)charge_as functions.
The core of the accounting takes place during fork time in copy_process(),
may_expand_vm(), remove_vma_list() and exit_mmap().
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: Pavel Emelianov <xemul@xxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Vivek Goyal <vgoyal@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/x86/kernel/ptrace.c | 18 ++++-
include/linux/memrlimitcgroup.h | 21 ++++++
kernel/fork.c | 8 ++
mm/memrlimitcgroup.c | 92 ++++++++++++++++++++++++++++++
mm/mmap.c | 17 ++++-
5 files changed, 149 insertions(+), 7 deletions(-)
diff -puN arch/x86/kernel/ptrace.c~memrlimit-add-memrlimit-controller-accounting-and-control arch/x86/kernel/ptrace.c
--- a/arch/x86/kernel/ptrace.c~memrlimit-add-memrlimit-controller-accounting-and-control
+++ a/arch/x86/kernel/ptrace.c
@@ -20,6 +20,7 @@
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <linux/signal.h>
+#include <linux/memrlimitcgroup.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -782,21 +783,25 @@ static int ptrace_bts_realloc(struct tas
current->mm->total_vm -= old_size;
current->mm->locked_vm -= old_size;
+ memrlimit_cgroup_uncharge_as(mm, old_size);
if (size == 0)
goto out;
+ if (memrlimit_cgroup_charge_as(current->mm, size))
+ goto out;
+
rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
vm = current->mm->total_vm + size;
if (rlim < vm) {
ret = -ENOMEM;
if (!reduce_size)
- goto out;
+ goto out_uncharge;
size = rlim - current->mm->total_vm;
if (size <= 0)
- goto out;
+ goto out_uncharge;
}
rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
@@ -805,21 +810,24 @@ static int ptrace_bts_realloc(struct tas
ret = -ENOMEM;
if (!reduce_size)
- goto out;
+ goto out_uncharge;
size = rlim - current->mm->locked_vm;
if (size <= 0)
- goto out;
+ goto out_uncharge;
}
ret = ds_allocate((void **)&child->thread.ds_area_msr,
size << PAGE_SHIFT);
if (ret < 0)
- goto out;
+ goto out_uncharge;
current->mm->total_vm += size;
current->mm->locked_vm += size;
+out_uncharge:
+ if (ret < 0)
+ memrlimit_cgroup_uncharge_as(mm, size);
out:
if (child->thread.ds_area_msr)
set_tsk_thread_flag(child, TIF_DS_AREA_MSR);
diff -puN include/linux/memrlimitcgroup.h~memrlimit-add-memrlimit-controller-accounting-and-control include/linux/memrlimitcgroup.h
--- a/include/linux/memrlimitcgroup.h~memrlimit-add-memrlimit-controller-accounting-and-control
+++ a/include/linux/memrlimitcgroup.h
@@ -16,4 +16,25 @@
#ifndef LINUX_MEMRLIMITCGROUP_H
#define LINUX_MEMRLIMITCGROUP_H
+#ifdef CONFIG_CGROUP_MEMRLIMIT_CTLR
+
+int memrlimit_cgroup_charge_as(struct mm_struct *mm, unsigned long nr_pages);
+void memrlimit_cgroup_uncharge_as(struct mm_struct *mm, unsigned long nr_pages);
+
+#else /* !CONFIG_CGROUP_RLIMIT_CTLR */
+
+static inline int
+memrlimit_cgroup_charge_as(struct mm_struct *mm, unsigned long nr_pages)
+{
+ return 0;
+}
+
+static inline void
+memrlimit_cgroup_uncharge_as(struct mm_struct *mm, unsigned long nr_pages)
+{
+}
+
+#endif /* CONFIG_CGROUP_RLIMIT_CTLR */
+
+
#endif /* LINUX_MEMRLIMITCGROUP_H */
diff -puN kernel/fork.c~memrlimit-add-memrlimit-controller-accounting-and-control kernel/fork.c
--- a/kernel/fork.c~memrlimit-add-memrlimit-controller-accounting-and-control
+++ a/kernel/fork.c
@@ -47,6 +47,7 @@
#include <linux/acct.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
+#include <linux/memrlimitcgroup.h>
#include <linux/freezer.h>
#include <linux/delayacct.h>
#include <linux/taskstats_kern.h>
@@ -272,6 +273,7 @@ static int dup_mmap(struct mm_struct *mm
mm->total_vm -= pages;
vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
-pages);
+ memrlimit_cgroup_uncharge_as(mm, pages);
continue;
}
charge = 0;
@@ -601,6 +603,12 @@ static int copy_mm(unsigned long clone_f
atomic_inc(&oldmm->mm_users);
mm = oldmm;
goto good_mm;
+ } else {
+ down_write(&oldmm->mmap_sem);
+ retval = memrlimit_cgroup_charge_as(oldmm, oldmm->total_vm);
+ up_write(&oldmm->mmap_sem);
+ if (retval)
+ goto fail_nomem;
}
retval = -ENOMEM;
diff -puN mm/memrlimitcgroup.c~memrlimit-add-memrlimit-controller-accounting-and-control mm/memrlimitcgroup.c
--- a/mm/memrlimitcgroup.c~memrlimit-add-memrlimit-controller-accounting-and-control
+++ a/mm/memrlimitcgroup.c
@@ -45,6 +45,38 @@ static struct memrlimit_cgroup *memrlimi
struct memrlimit_cgroup, css);
}
+static struct memrlimit_cgroup *
+memrlimit_cgroup_from_task(struct task_struct *p)
+{
+ return container_of(task_subsys_state(p, memrlimit_cgroup_subsys_id),
+ struct memrlimit_cgroup, css);
+}
+
+/*
+ * Charge the cgroup for address space usage - mmap(), malloc() (through
+ * brk(), sbrk()), stack expansion, mremap(), etc - called with
+ * mmap_sem held.
+ */
+int memrlimit_cgroup_charge_as(struct mm_struct *mm, unsigned long nr_pages)
+{
+ struct memrlimit_cgroup *memrcg;
+
+ memrcg = memrlimit_cgroup_from_task(mm->owner);
+ return res_counter_charge(&memrcg->as_res, (nr_pages << PAGE_SHIFT));
+}
+
+/*
+ * Uncharge the cgroup, as the address space of one of the tasks is
+ * decreasing - called with mmap_sem held.
+ */
+void memrlimit_cgroup_uncharge_as(struct mm_struct *mm, unsigned long nr_pages)
+{
+ struct memrlimit_cgroup *memrcg;
+
+ memrcg = memrlimit_cgroup_from_task(mm->owner);
+ res_counter_uncharge(&memrcg->as_res, (nr_pages << PAGE_SHIFT));
+}
+
static struct cgroup_subsys_state *
memrlimit_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
{
@@ -134,11 +166,71 @@ static int memrlimit_cgroup_populate(str
ARRAY_SIZE(memrlimit_cgroup_files));
}
+static void memrlimit_cgroup_move_task(struct cgroup_subsys *ss,
+ struct cgroup *cgrp,
+ struct cgroup *old_cgrp,
+ struct task_struct *p)
+{
+ struct mm_struct *mm;
+ struct memrlimit_cgroup *memrcg, *old_memrcg;
+
+ mm = get_task_mm(p);
+ if (mm == NULL)
+ return;
+
+ /*
+ * Hold mmap_sem, so that total_vm does not change underneath us
+ */
+ down_read(&mm->mmap_sem);
+
+ rcu_read_lock();
+ if (p != rcu_dereference(mm->owner))
+ goto out;
+
+ memrcg = memrlimit_cgroup_from_cgrp(cgrp);
+ old_memrcg = memrlimit_cgroup_from_cgrp(old_cgrp);
+
+ if (memrcg == old_memrcg)
+ goto out;
+
+ if (res_counter_charge(&memrcg->as_res, (mm->total_vm << PAGE_SHIFT)))
+ goto out;
+ res_counter_uncharge(&old_memrcg->as_res, (mm->total_vm << PAGE_SHIFT));
+out:
+ rcu_read_unlock();
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+}
+
+/*
+ * This callback is called with mmap_sem held
+ */
+static void memrlimit_cgroup_mm_owner_changed(struct cgroup_subsys *ss,
+ struct cgroup *cgrp,
+ struct cgroup *old_cgrp,
+ struct task_struct *p)
+{
+ struct memrlimit_cgroup *memrcg, *old_memrcg;
+ struct mm_struct *mm = get_task_mm(p);
+
+ BUG_ON(!mm);
+ memrcg = memrlimit_cgroup_from_cgrp(cgrp);
+ old_memrcg = memrlimit_cgroup_from_cgrp(old_cgrp);
+
+ if (res_counter_charge(&memrcg->as_res, (mm->total_vm << PAGE_SHIFT)))
+ goto out;
+ res_counter_uncharge(&old_memrcg->as_res, (mm->total_vm << PAGE_SHIFT));
+out:
+ mmput(mm);
+}
+
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,
+ .attach = memrlimit_cgroup_move_task,
+ .mm_owner_changed = memrlimit_cgroup_mm_owner_changed,
.early_init = 0,
};
diff -puN mm/mmap.c~memrlimit-add-memrlimit-controller-accounting-and-control mm/mmap.c
--- a/mm/mmap.c~memrlimit-add-memrlimit-controller-accounting-and-control
+++ a/mm/mmap.c
@@ -26,6 +26,7 @@
#include <linux/mount.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
+#include <linux/memrlimitcgroup.h>
#include <asm/uaccess.h>
#include <asm/cacheflush.h>
@@ -1732,6 +1733,7 @@ static void remove_vma_list(struct mm_st
long nrpages = vma_pages(vma);
mm->total_vm -= nrpages;
+ memrlimit_cgroup_uncharge_as(mm, nrpages);
if (vma->vm_flags & VM_LOCKED)
mm->locked_vm -= nrpages;
vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages);
@@ -1758,6 +1760,7 @@ static void unmap_region(struct mm_struc
update_hiwater_rss(mm);
unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL);
vm_unacct_memory(nr_accounted);
+ memrlimit_cgroup_uncharge_as(mm, mm->total_vm);
free_pgtables(tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS,
next? next->vm_start: 0);
tlb_finish_mmu(tlb, start, end);
@@ -2080,6 +2083,9 @@ int insert_vm_struct(struct mm_struct *
struct vm_area_struct * __vma, * prev;
struct rb_node ** rb_link, * rb_parent;
+ if (memrlimit_cgroup_charge_as(mm, vma_pages(vma)))
+ return -ENOMEM;
+
/*
* The vm_pgoff of a purely anonymous vma should be irrelevant
* until its first write fault, when page's anon_vma and index
@@ -2098,12 +2104,15 @@ int insert_vm_struct(struct mm_struct *
}
__vma = find_vma_prepare(mm,vma->vm_start,&prev,&rb_link,&rb_parent);
if (__vma && __vma->vm_start < vma->vm_end)
- return -ENOMEM;
+ goto err;
if ((vma->vm_flags & VM_ACCOUNT) &&
security_vm_enough_memory_mm(mm, vma_pages(vma)))
- return -ENOMEM;
+ goto err;
vma_link(mm, vma, prev, rb_link, rb_parent);
return 0;
+err:
+ memrlimit_cgroup_uncharge_as(mm, vma_pages(vma));
+ return -ENOMEM;
}
/*
@@ -2176,6 +2185,10 @@ int may_expand_vm(struct mm_struct *mm,
if (cur + npages > lim)
return 0;
+
+ if (memrlimit_cgroup_charge_as(mm, npages))
+ return 0;
+
return 1;
}
_
Patches currently in -mm which might be from balbir@xxxxxxxxxxxxxxxxxx are
linux-next.patch
cgroup-use-read-lock-to-guard-find_existing_css_set.patch
mark-res_counter_charge_locked-with-__must_check.patch
memcg-make-global-var-read_mostly.patch
memcg-avoid-unnecessary-initialization.patch
memrlimit-add-memrlimit-controller-documentation.patch
memrlimit-setup-the-memrlimit-controller.patch
memrlimit-cgroup-mm-owner-callback-changes-to-add-task-info.patch
memrlimit-add-memrlimit-controller-accounting-and-control.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
