[<prev] [next>] [day] [month] [year] [list]
Message-ID: <20140220140238.GB6897@htj.dyndns.org>
Date: Thu, 20 Feb 2014 09:02:38 -0500
From: Tejun Heo <tj@...nel.org>
To: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: linux-kernel@...r.kernel.org, Li Zefan <lizefan@...wei.com>,
containers@...ts.linux-foundation.org, cgroups@...r.kernel.org
Subject: [GIT PULL] cgroup fixes for v3.14-rc3
Hello, Linus.
Quite a few fixes this time. Three locking fixes, all marked for
-stable. A couple error path fixes and some misc fixes. Hugh found a
bug in memcg offlining sequence and we thought we could fix that from
cgroup core side but that turned out to be insufficient and got
reverted. A different fix has been applied to -mm.
The following changes since commit 38dbfb59d1175ef458d006556061adeaa8751b72:
Linus 3.14-rc1 (2014-02-02 16:42:13 -0800)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git for-3.14-fixes
for you to fetch changes up to 532de3fc72adc2a6525c4d53c07bf81e1732083d:
cgroup: update cgroup_enable_task_cg_lists() to grab siglock (2014-02-18 18:23:18 -0500)
Thanks.
----------------------------------------------------------------
Hugh Dickins (1):
cgroup: use an ordered workqueue for cgroup destruction
Li Zefan (2):
cpuset: update MAINTAINERS entry
cgroup: protect modifications to cgroup_idr with cgroup_mutex
Tejun Heo (7):
arm, pm, vmpressure: add missing slab.h includes
nfs: include xattr.h from fs/nfs/nfs3proc.c
cgroup: fix error return value in cgroup_mount()
cgroup: fix error return from cgroup_create()
cgroup: fix locking in cgroup_cfts_commit()
Revert "cgroup: use an ordered workqueue for cgroup destruction"
cgroup: update cgroup_enable_task_cg_lists() to grab siglock
MAINTAINERS | 2 ++
arch/arm/mach-tegra/pm.c | 1 +
fs/nfs/nfs3proc.c | 1 +
include/linux/cgroup.h | 2 ++
kernel/cgroup.c | 60 ++++++++++++++++++++++++++----------------------
kernel/power/console.c | 1 +
mm/vmpressure.c | 1 +
7 files changed, 40 insertions(+), 28 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index b2cf5cf..41e52c5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2408,8 +2408,10 @@ F: tools/power/cpupower/
CPUSETS
M: Li Zefan <lizefan@...wei.com>
+L: cgroups@...r.kernel.org
W: http://www.bullopensource.org/cpuset/
W: http://oss.sgi.com/projects/cpusets/
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git
S: Maintained
F: Documentation/cgroups/cpusets.txt
F: include/linux/cpuset.h
diff --git a/arch/arm/mach-tegra/pm.c b/arch/arm/mach-tegra/pm.c
index 4ae0286..f55b05a 100644
--- a/arch/arm/mach-tegra/pm.c
+++ b/arch/arm/mach-tegra/pm.c
@@ -24,6 +24,7 @@
#include <linux/cpu_pm.h>
#include <linux/suspend.h>
#include <linux/err.h>
+#include <linux/slab.h>
#include <linux/clk/tegra.h>
#include <asm/smp_plat.h>
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index aa9bc97..a462ef0 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -18,6 +18,7 @@
#include <linux/lockd/bind.h>
#include <linux/nfs_mount.h>
#include <linux/freezer.h>
+#include <linux/xattr.h>
#include "iostat.h"
#include "internal.h"
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 5c09759..9450f02 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -166,6 +166,8 @@ struct cgroup {
*
* The ID of the root cgroup is always 0, and a new cgroup
* will be assigned with a smallest available ID.
+ *
+ * Allocating/Removing ID must be protected by cgroup_mutex.
*/
int id;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e2f46ba..105f273 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -886,7 +886,9 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
* per-subsystem and moved to css->id so that lookups are
* successful until the target css is released.
*/
+ mutex_lock(&cgroup_mutex);
idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+ mutex_unlock(&cgroup_mutex);
cgrp->id = -1;
call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
@@ -1566,10 +1568,10 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
mutex_lock(&cgroup_mutex);
mutex_lock(&cgroup_root_mutex);
- root_cgrp->id = idr_alloc(&root->cgroup_idr, root_cgrp,
- 0, 1, GFP_KERNEL);
- if (root_cgrp->id < 0)
+ ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
+ if (ret < 0)
goto unlock_drop;
+ root_cgrp->id = ret;
/* Check for name clashes with existing mounts */
ret = -EBUSY;
@@ -2763,10 +2765,7 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
*/
update_before = cgroup_serial_nr_next;
- mutex_unlock(&cgroup_mutex);
-
/* add/rm files for all cgroups created before */
- rcu_read_lock();
css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
struct cgroup *cgrp = css->cgroup;
@@ -2775,23 +2774,19 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
inode = cgrp->dentry->d_inode;
dget(cgrp->dentry);
- rcu_read_unlock();
-
dput(prev);
prev = cgrp->dentry;
+ mutex_unlock(&cgroup_mutex);
mutex_lock(&inode->i_mutex);
mutex_lock(&cgroup_mutex);
if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp))
ret = cgroup_addrm_files(cgrp, cfts, is_add);
- mutex_unlock(&cgroup_mutex);
mutex_unlock(&inode->i_mutex);
-
- rcu_read_lock();
if (ret)
break;
}
- rcu_read_unlock();
+ mutex_unlock(&cgroup_mutex);
dput(prev);
deactivate_super(sb);
return ret;
@@ -2910,9 +2905,14 @@ static void cgroup_enable_task_cg_lists(void)
* We should check if the process is exiting, otherwise
* it will race with cgroup_exit() in that the list
* entry won't be deleted though the process has exited.
+ * Do it while holding siglock so that we don't end up
+ * racing against cgroup_exit().
*/
+ spin_lock_irq(&p->sighand->siglock);
if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
list_add(&p->cg_list, &task_css_set(p)->tasks);
+ spin_unlock_irq(&p->sighand->siglock);
+
task_unlock(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
@@ -4158,7 +4158,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
struct cgroup *cgrp;
struct cgroup_name *name;
struct cgroupfs_root *root = parent->root;
- int ssid, err = 0;
+ int ssid, err;
struct cgroup_subsys *ss;
struct super_block *sb = root->sb;
@@ -4168,19 +4168,13 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
return -ENOMEM;
name = cgroup_alloc_name(dentry);
- if (!name)
+ if (!name) {
+ err = -ENOMEM;
goto err_free_cgrp;
+ }
rcu_assign_pointer(cgrp->name, name);
/*
- * Temporarily set the pointer to NULL, so idr_find() won't return
- * a half-baked cgroup.
- */
- cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
- if (cgrp->id < 0)
- goto err_free_name;
-
- /*
* Only live parents can have children. Note that the liveliness
* check isn't strictly necessary because cgroup_mkdir() and
* cgroup_rmdir() are fully synchronized by i_mutex; however, do it
@@ -4189,7 +4183,17 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
*/
if (!cgroup_lock_live_group(parent)) {
err = -ENODEV;
- goto err_free_id;
+ goto err_free_name;
+ }
+
+ /*
+ * Temporarily set the pointer to NULL, so idr_find() won't return
+ * a half-baked cgroup.
+ */
+ cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
+ if (cgrp->id < 0) {
+ err = -ENOMEM;
+ goto err_unlock;
}
/* Grab a reference on the superblock so the hierarchy doesn't
@@ -4221,7 +4225,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
*/
err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
if (err < 0)
- goto err_unlock;
+ goto err_free_id;
lockdep_assert_held(&dentry->d_inode->i_mutex);
cgrp->serial_nr = cgroup_serial_nr_next++;
@@ -4257,12 +4261,12 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
return 0;
-err_unlock:
- mutex_unlock(&cgroup_mutex);
- /* Release the reference count that we took on the superblock */
- deactivate_super(sb);
err_free_id:
idr_remove(&root->cgroup_idr, cgrp->id);
+ /* Release the reference count that we took on the superblock */
+ deactivate_super(sb);
+err_unlock:
+ mutex_unlock(&cgroup_mutex);
err_free_name:
kfree(rcu_dereference_raw(cgrp->name));
err_free_cgrp:
diff --git a/kernel/power/console.c b/kernel/power/console.c
index eacb8bd..aba9c54 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -9,6 +9,7 @@
#include <linux/kbd_kern.h>
#include <linux/vt.h>
#include <linux/module.h>
+#include <linux/slab.h>
#include "power.h"
#define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1)
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 196970a..d4042e7 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -19,6 +19,7 @@
#include <linux/mm.h>
#include <linux/vmstat.h>
#include <linux/eventfd.h>
+#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/printk.h>
#include <linux/vmpressure.h>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists