The patch titled
devcgroup: relax white-list protection down to RCU
has been removed from the -mm tree. Its filename was
devcgroup-relax-white-list-protection-down-to-rcu.patch
This patch was dropped because it was merged into mainline or a subsystem tree
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: devcgroup: relax white-list protection down to RCU
From: Pavel Emelyanov <xemul@xxxxxxxxxx>
Currently this list is protected with a simple spinlock, even for reading
from one. This is OK, but can be better.
Actually I want it to be better very much, since after replacing the
OpenVZ device permissions engine with the cgroup-based one I noticed, that
we set 12 default device permissions for each newly created container (for
/dev/null, full, terminals, ect devices), and people sometimes have up to
20 perms more, so traversing the ~30-40 elements list under a spinlock
doesn't seem very good.
Here's the RCU protection for white-list - dev_whitelist_item-s are added
and removed under the devcg->lock, but are looked up in permissions
checking under the rcu_read_lock.
Signed-off-by: Pavel Emelyanov <xemul@xxxxxxxxxx>
Acked-by: Serge Hallyn <serue@xxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
security/device_cgroup.c | 35 ++++++++++++++++++++++-------------
1 file changed, 22 insertions(+), 13 deletions(-)
diff -puN security/device_cgroup.c~devcgroup-relax-white-list-protection-down-to-rcu security/device_cgroup.c
--- a/security/device_cgroup.c~devcgroup-relax-white-list-protection-down-to-rcu
+++ a/security/device_cgroup.c
@@ -41,6 +41,7 @@ struct dev_whitelist_item {
short type;
short access;
struct list_head list;
+ struct rcu_head rcu;
};
struct dev_cgroup {
@@ -133,11 +134,19 @@ static int dev_whitelist_add(struct dev_
}
if (whcopy != NULL)
- list_add_tail(&whcopy->list, &dev_cgroup->whitelist);
+ list_add_tail_rcu(&whcopy->list, &dev_cgroup->whitelist);
spin_unlock(&dev_cgroup->lock);
return 0;
}
+static void whitelist_item_free(struct rcu_head *rcu)
+{
+ struct dev_whitelist_item *item;
+
+ item = container_of(rcu, struct dev_whitelist_item, rcu);
+ kfree(item);
+}
+
/*
* called under cgroup_lock()
* since the list is visible to other tasks, we need the spinlock also
@@ -161,8 +170,8 @@ static void dev_whitelist_rm(struct dev_
remove:
walk->access &= ~wh->access;
if (!walk->access) {
- list_del(&walk->list);
- kfree(walk);
+ list_del_rcu(&walk->list);
+ call_rcu(&walk->rcu, whitelist_item_free);
}
}
spin_unlock(&dev_cgroup->lock);
@@ -269,15 +278,15 @@ static int devcgroup_seq_read(struct cgr
struct dev_whitelist_item *wh;
char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN];
- spin_lock(&devcgroup->lock);
- list_for_each_entry(wh, &devcgroup->whitelist, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(wh, &devcgroup->whitelist, list) {
set_access(acc, wh->access);
set_majmin(maj, wh->major);
set_majmin(min, wh->minor);
seq_printf(m, "%c %s:%s %s\n", type_to_char(wh->type),
maj, min, acc);
}
- spin_unlock(&devcgroup->lock);
+ rcu_read_unlock();
return 0;
}
@@ -510,8 +519,8 @@ int devcgroup_inode_permission(struct in
if (!dev_cgroup)
return 0;
- spin_lock(&dev_cgroup->lock);
- list_for_each_entry(wh, &dev_cgroup->whitelist, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(wh, &dev_cgroup->whitelist, list) {
if (wh->type & DEV_ALL)
goto acc_check;
if ((wh->type & DEV_BLOCK) && !S_ISBLK(inode->i_mode))
@@ -527,10 +536,10 @@ acc_check:
continue;
if ((mask & MAY_READ) && !(wh->access & ACC_READ))
continue;
- spin_unlock(&dev_cgroup->lock);
+ rcu_read_unlock();
return 0;
}
- spin_unlock(&dev_cgroup->lock);
+ rcu_read_unlock();
return -EPERM;
}
@@ -545,7 +554,7 @@ int devcgroup_inode_mknod(int mode, dev_
if (!dev_cgroup)
return 0;
- spin_lock(&dev_cgroup->lock);
+ rcu_read_lock();
list_for_each_entry(wh, &dev_cgroup->whitelist, list) {
if (wh->type & DEV_ALL)
goto acc_check;
@@ -560,9 +569,9 @@ int devcgroup_inode_mknod(int mode, dev_
acc_check:
if (!(wh->access & ACC_MKNOD))
continue;
- spin_unlock(&dev_cgroup->lock);
+ rcu_read_unlock();
return 0;
}
- spin_unlock(&dev_cgroup->lock);
+ rcu_read_unlock();
return -EPERM;
}
_
Patches currently in -mm which might be from xemul@xxxxxxxxxx are
origin.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
memrlimit-improve-error-handling.patch
memrlimit-improve-error-handling-update.patch
memrlimit-handle-attach_task-failure-add-can_attach-callback.patch
reiser4.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
