[PATCH v4] net: cgroup: fix access the unallocated memory in netprio cgroup

there are some out of bound accesses in netprio cgroup.

now before accessing the dev->priomap.priomap array,we only check
if the dev->priomap exist.and because we don't want to see
additional bound checkings in fast path, so we should make sure
that dev->priomap is null or array size of dev->priomap.priomap
is equal to max_prioidx + 1;

so in write_priomap logic,we should call extend_netdev_table when
dev->priomap is null and dev->priomap.priomap_len < max_len.
and in cgrp_create->update_netdev_tables logic,we should call
extend_netdev_table only when dev->priomap exist and
dev->priomap.priomap_len < max_len.

and it's not needed to call update_netdev_tables in write_priomap,
we can only allocate the net device's priomap which we change through
net_prio.ifpriomap.

this patch also add a return value for update_netdev_tables &
extend_netdev_table, so when new_priomap is allocated failed,
write_priomap will stop to access the priomap,and return -ENOMEM
back to the userspace to tell the user what happend.

Change From v3:
1. add rtnl protect when reading max_prioidx in write_priomap.

2. only call extend_netdev_table when map->priomap_len < max_len,
   this will make sure array size of dev->map->priomap always
   bigger than any prioidx.

3. add a function write_update_netdev_table to make codes clear.

Change From v2:
1. protect extend_netdev_table by RTNL.
2. when extend_netdev_table failed,call dev_put to reduce device's refcount.

Signed-off-by: Gao feng <redacted>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Eric Dumazet <edumazet@google.com>
---
 net/core/netprio_cgroup.c |   71 ++++++++++++++++++++++++++++++++++-----------
 1 files changed, 54 insertions(+), 17 deletions(-)

diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index aa907ed..9b17d54 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c

@@ -65,7 +65,7 @@ static void put_prioidx(u32 idx)
 	spin_unlock_irqrestore(&prioidx_map_lock, flags);
 }
 
-static void extend_netdev_table(struct net_device *dev, u32 new_len)
+static int extend_netdev_table(struct net_device *dev, u32 new_len)
 {
 	size_t new_size = sizeof(struct netprio_map) +
 			   ((sizeof(u32) * new_len));

@@ -77,7 +77,7 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len)
 
 	if (!new_priomap) {
 		pr_warn("Unable to alloc new priomap!\n");
-		return;
+		return -ENOMEM;
 	}
 
 	for (i = 0;

@@ -90,46 +90,79 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len)
 	rcu_assign_pointer(dev->priomap, new_priomap);
 	if (old_priomap)
 		kfree_rcu(old_priomap, rcu);
+	return 0;
 }
 
-static void update_netdev_tables(void)
+static int write_update_netdev_table(struct net_device *dev)
 {
+	int ret = 0;
+	u32 max_len;
+	struct netprio_map *map;
+
+	rtnl_lock();
+	max_len = atomic_read(&max_prioidx) + 1;
+	map = rtnl_dereference(dev->priomap);
+	if (!map || map->priomap_len < max_len)
+		ret = extend_netdev_table(dev, max_len);
+	rtnl_unlock();
+
+	return ret;
+}
+
+static int update_netdev_tables(void)
+{
+	int ret = 0;
 	struct net_device *dev;
-	u32 max_len = atomic_read(&max_prioidx) + 1;
+	u32 max_len;
 	struct netprio_map *map;
 
 	rtnl_lock();
+	max_len = atomic_read(&max_prioidx) + 1;
 	for_each_netdev(&init_net, dev) {
 		map = rtnl_dereference(dev->priomap);
-		if ((!map) ||
-		    (map->priomap_len < max_len))
-			extend_netdev_table(dev, max_len);
+		/*
+		 * don't allocate priomap if we didn't
+		 * change net_prio.ifpriomap (map == NULL),
+		 * this will speed up skb_update_prio.
+		 */
+		if (map && map->priomap_len < max_len) {
+			ret = extend_netdev_table(dev, max_len);
+			if (ret < 0)
+				break;
+		}
 	}
 	rtnl_unlock();
+	return ret;
 }
 
 static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
 {
 	struct cgroup_netprio_state *cs;
-	int ret;
+	int ret = -EINVAL;
 
 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
 
-	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) {
-		kfree(cs);
-		return ERR_PTR(-EINVAL);
-	}
+	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
+		goto out;
 
 	ret = get_prioidx(&cs->prioidx);
-	if (ret != 0) {
+	if (ret < 0) {
 		pr_warn("No space in priority index array\n");
-		kfree(cs);
-		return ERR_PTR(ret);
+		goto out;
+	}
+
+	ret = update_netdev_tables();
+	if (ret < 0) {
+		put_prioidx(cs->prioidx);
+		goto out;
 	}
 
 	return &cs->css;
+out:
+	kfree(cs);
+	return ERR_PTR(ret);
 }
 
 static void cgrp_destroy(struct cgroup *cgrp)

@@ -221,13 +254,17 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
 	if (!dev)
 		goto out_free_devname;
 
-	update_netdev_tables();
-	ret = 0;
+	ret = write_update_netdev_table(dev);
+	if (ret < 0)
+		goto out_put_dev;
+
 	rcu_read_lock();
 	map = rcu_dereference(dev->priomap);
 	if (map)
 		map->priomap[prioidx] = priority;
 	rcu_read_unlock();
+
+out_put_dev:
 	dev_put(dev);
 
 out_free_devname:

-- 
1.7.7.6

On Thu, Jul 12, 2012 at 03:50:15PM +0800, Gao feng wrote:

there are some out of bound accesses in netprio cgroup.

now before accessing the dev->priomap.priomap array,we only check
if the dev->priomap exist.and because we don't want to see
additional bound checkings in fast path, so we should make sure
that dev->priomap is null or array size of dev->priomap.priomap
is equal to max_prioidx + 1;

so in write_priomap logic,we should call extend_netdev_table when
dev->priomap is null and dev->priomap.priomap_len < max_len.
and in cgrp_create->update_netdev_tables logic,we should call
extend_netdev_table only when dev->priomap exist and
dev->priomap.priomap_len < max_len.

and it's not needed to call update_netdev_tables in write_priomap,
we can only allocate the net device's priomap which we change through
net_prio.ifpriomap.

this patch also add a return value for update_netdev_tables &
extend_netdev_table, so when new_priomap is allocated failed,
write_priomap will stop to access the priomap,and return -ENOMEM
back to the userspace to tell the user what happend.

Change From v3:
1. add rtnl protect when reading max_prioidx in write_priomap.

2. only call extend_netdev_table when map->priomap_len < max_len,
   this will make sure array size of dev->map->priomap always
   bigger than any prioidx.

3. add a function write_update_netdev_table to make codes clear.

Change From v2:
1. protect extend_netdev_table by RTNL.
2. when extend_netdev_table failed,call dev_put to reduce device's refcount.

Signed-off-by: Gao feng <redacted>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Eric Dumazet <edumazet@google.com>

Thank you Gao.
Acked-by: Neil Horman <nhorman@tuxdriver.com>

From: Neil Horman <nhorman@tuxdriver.com>
Date: Thu, 12 Jul 2012 06:56:11 -0400

On Thu, Jul 12, 2012 at 03:50:15PM +0800, Gao feng wrote:

quoted

there are some out of bound accesses in netprio cgroup.

 ...

quoted

Signed-off-by: Gao feng <redacted>

Acked-by: Neil Horman <nhorman@tuxdriver.com>

Applied to 'net', thanks.

On 7/12/2012 12:50 AM, Gao feng wrote:

there are some out of bound accesses in netprio cgroup.

now before accessing the dev->priomap.priomap array,we only check
if the dev->priomap exist.and because we don't want to see
additional bound checkings in fast path, so we should make sure
that dev->priomap is null or array size of dev->priomap.priomap
is equal to max_prioidx + 1;

so in write_priomap logic,we should call extend_netdev_table when
dev->priomap is null and dev->priomap.priomap_len < max_len.
and in cgrp_create->update_netdev_tables logic,we should call
extend_netdev_table only when dev->priomap exist and
dev->priomap.priomap_len < max_len.

and it's not needed to call update_netdev_tables in write_priomap,
we can only allocate the net device's priomap which we change through
net_prio.ifpriomap.

this patch also add a return value for update_netdev_tables &
extend_netdev_table, so when new_priomap is allocated failed,
write_priomap will stop to access the priomap,and return -ENOMEM
back to the userspace to tell the user what happend.

Change From v3:
1. add rtnl protect when reading max_prioidx in write_priomap.

2. only call extend_netdev_table when map->priomap_len < max_len,
    this will make sure array size of dev->map->priomap always
    bigger than any prioidx.

3. add a function write_update_netdev_table to make codes clear.

Change From v2:
1. protect extend_netdev_table by RTNL.
2. when extend_netdev_table failed,call dev_put to reduce device's refcount.

Signed-off-by: Gao feng <redacted>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Eric Dumazet <edumazet@google.com>
---
  net/core/netprio_cgroup.c |   71 ++++++++++++++++++++++++++++++++++-----------
  1 files changed, 54 insertions(+), 17 deletions(-)

[...]

+
+static int update_netdev_tables(void)
+{
+	int ret = 0;
  	struct net_device *dev;
-	u32 max_len = atomic_read(&max_prioidx) + 1;
+	u32 max_len;
  	struct netprio_map *map;

need to check if net subsystem is initialized before we try
to use it here...

	if (some_check)     -> need to lookup what this check is
		return ret;

  	rtnl_lock();
+	max_len = atomic_read(&max_prioidx) + 1;
  	for_each_netdev(&init_net, dev) {
  		map = rtnl_dereference(dev->priomap);
-		if ((!map) ||
-		    (map->priomap_len < max_len))
-			extend_netdev_table(dev, max_len);
+		/*
+		 * don't allocate priomap if we didn't
+		 * change net_prio.ifpriomap (map == NULL),
+		 * this will speed up skb_update_prio.
+		 */
+		if (map && map->priomap_len < max_len) {
+			ret = extend_netdev_table(dev, max_len);
+			if (ret < 0)
+				break;
+		}
  	}
  	rtnl_unlock();
+	return ret;
  }

  static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
  {
  	struct cgroup_netprio_state *cs;
-	int ret;
+	int ret = -EINVAL;

  	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
  	if (!cs)
  		return ERR_PTR(-ENOMEM);

-	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) {
-		kfree(cs);
-		return ERR_PTR(-EINVAL);
-	}
+	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
+		goto out;

  	ret = get_prioidx(&cs->prioidx);
-	if (ret != 0) {
+	if (ret < 0) {
  		pr_warn("No space in priority index array\n");
-		kfree(cs);
-		return ERR_PTR(ret);
+		goto out;
+	}
+
+	ret = update_netdev_tables();
+	if (ret < 0) {
+		put_prioidx(cs->prioidx);
+		goto out;
  	}

Gao,

This introduces a null ptr dereference when netprio_cgroup is built
into the kernel because update_netdev_tables() depends on init_net.
However cgrp_create is being called by cgroup_init before
do_initcalls() is called and before net_dev_init().

.John

On Tue, Jul 17, 2012 at 01:47:25PM -0700, John Fastabend wrote:

On 7/12/2012 12:50 AM, Gao feng wrote:

quoted

there are some out of bound accesses in netprio cgroup.

now before accessing the dev->priomap.priomap array,we only check
if the dev->priomap exist.and because we don't want to see
additional bound checkings in fast path, so we should make sure
that dev->priomap is null or array size of dev->priomap.priomap
is equal to max_prioidx + 1;

so in write_priomap logic,we should call extend_netdev_table when
dev->priomap is null and dev->priomap.priomap_len < max_len.
and in cgrp_create->update_netdev_tables logic,we should call
extend_netdev_table only when dev->priomap exist and
dev->priomap.priomap_len < max_len.

and it's not needed to call update_netdev_tables in write_priomap,
we can only allocate the net device's priomap which we change through
net_prio.ifpriomap.

this patch also add a return value for update_netdev_tables &
extend_netdev_table, so when new_priomap is allocated failed,
write_priomap will stop to access the priomap,and return -ENOMEM
back to the userspace to tell the user what happend.

Change From v3:
1. add rtnl protect when reading max_prioidx in write_priomap.

2. only call extend_netdev_table when map->priomap_len < max_len,
   this will make sure array size of dev->map->priomap always
   bigger than any prioidx.

3. add a function write_update_netdev_table to make codes clear.

Change From v2:
1. protect extend_netdev_table by RTNL.
2. when extend_netdev_table failed,call dev_put to reduce device's refcount.

Signed-off-by: Gao feng <redacted>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Eric Dumazet <edumazet@google.com>
---
 net/core/netprio_cgroup.c |   71 ++++++++++++++++++++++++++++++++++-----------
 1 files changed, 54 insertions(+), 17 deletions(-)

[...]

quoted

+
+static int update_netdev_tables(void)
+{
+	int ret = 0;
 	struct net_device *dev;
-	u32 max_len = atomic_read(&max_prioidx) + 1;
+	u32 max_len;
 	struct netprio_map *map;

need to check if net subsystem is initialized before we try
to use it here...

	if (some_check)     -> need to lookup what this check is
		return ret;

quoted

 	rtnl_lock();
+	max_len = atomic_read(&max_prioidx) + 1;
 	for_each_netdev(&init_net, dev) {
 		map = rtnl_dereference(dev->priomap);
-		if ((!map) ||
-		    (map->priomap_len < max_len))
-			extend_netdev_table(dev, max_len);
+		/*
+		 * don't allocate priomap if we didn't
+		 * change net_prio.ifpriomap (map == NULL),
+		 * this will speed up skb_update_prio.
+		 */
+		if (map && map->priomap_len < max_len) {
+			ret = extend_netdev_table(dev, max_len);
+			if (ret < 0)
+				break;
+		}
 	}
 	rtnl_unlock();
+	return ret;
 }

 static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
 {
 	struct cgroup_netprio_state *cs;
-	int ret;
+	int ret = -EINVAL;

 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);

-	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) {
-		kfree(cs);
-		return ERR_PTR(-EINVAL);
-	}
+	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
+		goto out;

 	ret = get_prioidx(&cs->prioidx);
-	if (ret != 0) {
+	if (ret < 0) {
 		pr_warn("No space in priority index array\n");
-		kfree(cs);
-		return ERR_PTR(ret);
+		goto out;
+	}
+
+	ret = update_netdev_tables();
+	if (ret < 0) {
+		put_prioidx(cs->prioidx);
+		goto out;
 	}

Gao,

This introduces a null ptr dereference when netprio_cgroup is built
into the kernel because update_netdev_tables() depends on init_net.
However cgrp_create is being called by cgroup_init before
do_initcalls() is called and before net_dev_init().

.John

Not sure I follow here John.  Shouldn't init_net be initialized prior to any
network devices getting registered?  In other words, shouldn't for_each_netdev
just result in zero iterations through the loop?
Neil

On 7/18/2012 5:21 AM, Neil Horman wrote:

On Tue, Jul 17, 2012 at 01:47:25PM -0700, John Fastabend wrote:

quoted

On 7/12/2012 12:50 AM, Gao feng wrote:

quoted

there are some out of bound accesses in netprio cgroup.

now before accessing the dev->priomap.priomap array,we only check
if the dev->priomap exist.and because we don't want to see
additional bound checkings in fast path, so we should make sure
that dev->priomap is null or array size of dev->priomap.priomap
is equal to max_prioidx + 1;

so in write_priomap logic,we should call extend_netdev_table when
dev->priomap is null and dev->priomap.priomap_len < max_len.
and in cgrp_create->update_netdev_tables logic,we should call
extend_netdev_table only when dev->priomap exist and
dev->priomap.priomap_len < max_len.

and it's not needed to call update_netdev_tables in write_priomap,
we can only allocate the net device's priomap which we change through
net_prio.ifpriomap.

this patch also add a return value for update_netdev_tables &
extend_netdev_table, so when new_priomap is allocated failed,
write_priomap will stop to access the priomap,and return -ENOMEM
back to the userspace to tell the user what happend.

Change From v3:
1. add rtnl protect when reading max_prioidx in write_priomap.

2. only call extend_netdev_table when map->priomap_len < max_len,
    this will make sure array size of dev->map->priomap always
    bigger than any prioidx.

3. add a function write_update_netdev_table to make codes clear.

Change From v2:
1. protect extend_netdev_table by RTNL.
2. when extend_netdev_table failed,call dev_put to reduce device's refcount.

Signed-off-by: Gao feng <redacted>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Eric Dumazet <edumazet@google.com>
---
  net/core/netprio_cgroup.c |   71 ++++++++++++++++++++++++++++++++++-----------
  1 files changed, 54 insertions(+), 17 deletions(-)

[...]

quoted

+
+static int update_netdev_tables(void)
+{
+	int ret = 0;
  	struct net_device *dev;
-	u32 max_len = atomic_read(&max_prioidx) + 1;
+	u32 max_len;
  	struct netprio_map *map;

need to check if net subsystem is initialized before we try
to use it here...

	if (some_check)     -> need to lookup what this check is
		return ret;

quoted

  	rtnl_lock();
+	max_len = atomic_read(&max_prioidx) + 1;
  	for_each_netdev(&init_net, dev) {
  		map = rtnl_dereference(dev->priomap);
-		if ((!map) ||
-		    (map->priomap_len < max_len))
-			extend_netdev_table(dev, max_len);
+		/*
+		 * don't allocate priomap if we didn't
+		 * change net_prio.ifpriomap (map == NULL),
+		 * this will speed up skb_update_prio.
+		 */
+		if (map && map->priomap_len < max_len) {
+			ret = extend_netdev_table(dev, max_len);
+			if (ret < 0)
+				break;
+		}
  	}
  	rtnl_unlock();
+	return ret;
  }

  static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
  {
  	struct cgroup_netprio_state *cs;
-	int ret;
+	int ret = -EINVAL;

  	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
  	if (!cs)
  		return ERR_PTR(-ENOMEM);

-	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) {
-		kfree(cs);
-		return ERR_PTR(-EINVAL);
-	}
+	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
+		goto out;

  	ret = get_prioidx(&cs->prioidx);
-	if (ret != 0) {
+	if (ret < 0) {
  		pr_warn("No space in priority index array\n");
-		kfree(cs);
-		return ERR_PTR(ret);
+		goto out;
+	}
+
+	ret = update_netdev_tables();
+	if (ret < 0) {
+		put_prioidx(cs->prioidx);
+		goto out;
  	}

Gao,

This introduces a null ptr dereference when netprio_cgroup is built
into the kernel because update_netdev_tables() depends on init_net.
However cgrp_create is being called by cgroup_init before
do_initcalls() is called and before net_dev_init().

.John

Not sure I follow here John.  Shouldn't init_net be initialized prior to any
network devices getting registered?  In other words, shouldn't for_each_netdev
just result in zero iterations through the loop?
Neil

init_net _is_ initialized prior to any network devices getting
registered but not before cgrp_create called via cgroup_init.

#define for_each_netdev(net, d)         \
                 list_for_each_entry(d, &(net)->dev_base_head, dev_list)

but dev_base_head is zeroed at this time. In netdev_init we have,

         INIT_LIST_HEAD(&net->dev_base_head);

but we haven't got that far yet because cgroup_init is called
before do_initcalls().

On Wed, Jul 18, 2012 at 07:10:18AM -0700, John Fastabend wrote:

On 7/18/2012 5:21 AM, Neil Horman wrote:

quoted

On Tue, Jul 17, 2012 at 01:47:25PM -0700, John Fastabend wrote:

quoted

On 7/12/2012 12:50 AM, Gao feng wrote:

quoted

there are some out of bound accesses in netprio cgroup.

now before accessing the dev->priomap.priomap array,we only check
if the dev->priomap exist.and because we don't want to see
additional bound checkings in fast path, so we should make sure
that dev->priomap is null or array size of dev->priomap.priomap
is equal to max_prioidx + 1;

so in write_priomap logic,we should call extend_netdev_table when
dev->priomap is null and dev->priomap.priomap_len < max_len.
and in cgrp_create->update_netdev_tables logic,we should call
extend_netdev_table only when dev->priomap exist and
dev->priomap.priomap_len < max_len.

and it's not needed to call update_netdev_tables in write_priomap,
we can only allocate the net device's priomap which we change through
net_prio.ifpriomap.

this patch also add a return value for update_netdev_tables &
extend_netdev_table, so when new_priomap is allocated failed,
write_priomap will stop to access the priomap,and return -ENOMEM
back to the userspace to tell the user what happend.

Change From v3:
1. add rtnl protect when reading max_prioidx in write_priomap.

2. only call extend_netdev_table when map->priomap_len < max_len,
   this will make sure array size of dev->map->priomap always
   bigger than any prioidx.

3. add a function write_update_netdev_table to make codes clear.

Change From v2:
1. protect extend_netdev_table by RTNL.
2. when extend_netdev_table failed,call dev_put to reduce device's refcount.

Signed-off-by: Gao feng <redacted>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Eric Dumazet <edumazet@google.com>
---
 net/core/netprio_cgroup.c |   71 ++++++++++++++++++++++++++++++++++-----------
 1 files changed, 54 insertions(+), 17 deletions(-)

[...]

quoted

+
+static int update_netdev_tables(void)
+{
+	int ret = 0;
 	struct net_device *dev;
-	u32 max_len = atomic_read(&max_prioidx) + 1;
+	u32 max_len;
 	struct netprio_map *map;

need to check if net subsystem is initialized before we try
to use it here...

if (some_check)     -> need to lookup what this check is
	return ret;

quoted

 	rtnl_lock();
+	max_len = atomic_read(&max_prioidx) + 1;
 	for_each_netdev(&init_net, dev) {
 		map = rtnl_dereference(dev->priomap);
-		if ((!map) ||
-		    (map->priomap_len < max_len))
-			extend_netdev_table(dev, max_len);
+		/*
+		 * don't allocate priomap if we didn't
+		 * change net_prio.ifpriomap (map == NULL),
+		 * this will speed up skb_update_prio.
+		 */
+		if (map && map->priomap_len < max_len) {
+			ret = extend_netdev_table(dev, max_len);
+			if (ret < 0)
+				break;
+		}
 	}
 	rtnl_unlock();
+	return ret;
 }

 static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
 {
 	struct cgroup_netprio_state *cs;
-	int ret;
+	int ret = -EINVAL;

 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);

-	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) {
-		kfree(cs);
-		return ERR_PTR(-EINVAL);
-	}
+	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
+		goto out;

 	ret = get_prioidx(&cs->prioidx);
-	if (ret != 0) {
+	if (ret < 0) {
 		pr_warn("No space in priority index array\n");
-		kfree(cs);
-		return ERR_PTR(ret);
+		goto out;
+	}
+
+	ret = update_netdev_tables();
+	if (ret < 0) {
+		put_prioidx(cs->prioidx);
+		goto out;
 	}

Gao,

This introduces a null ptr dereference when netprio_cgroup is built
into the kernel because update_netdev_tables() depends on init_net.
However cgrp_create is being called by cgroup_init before
do_initcalls() is called and before net_dev_init().

.John

Not sure I follow here John.  Shouldn't init_net be initialized prior to any
network devices getting registered?  In other words, shouldn't for_each_netdev
just result in zero iterations through the loop?
Neil

init_net _is_ initialized prior to any network devices getting
registered but not before cgrp_create called via cgroup_init.

#define for_each_netdev(net, d)         \
                list_for_each_entry(d, &(net)->dev_base_head, dev_list)

but dev_base_head is zeroed at this time. In netdev_init we have,

        INIT_LIST_HEAD(&net->dev_base_head);

but we haven't got that far yet because cgroup_init is called
before do_initcalls().

ok, I see that, and it makes sense, but at this point I'm more concerned with
cgroups getting initalized twice.  The early_init flag is clear in the
cgroup_subsystem for netprio, so we really shouldn't be getting initalized from
cgroup_init.  We should be getting initalized from the module_init() call that
we register
Neil

quoted

quoted

quoted

quoted

 static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)

quoted

quoted

quoted

quoted

 {
 	struct cgroup_netprio_state *cs;
-	int ret;
+	int ret = -EINVAL;

 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);

-	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) {
-		kfree(cs);
-		return ERR_PTR(-EINVAL);
-	}
+	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
+		goto out;

 	ret = get_prioidx(&cs->prioidx);
-	if (ret != 0) {
+	if (ret < 0) {
 		pr_warn("No space in priority index array\n");
-		kfree(cs);
-		return ERR_PTR(ret);
+		goto out;
+	}
+
+	ret = update_netdev_tables();
+	if (ret < 0) {
+		put_prioidx(cs->prioidx);
+		goto out;
 	}

Gao,

This introduces a null ptr dereference when netprio_cgroup is built
into the kernel because update_netdev_tables() depends on init_net.
However cgrp_create is being called by cgroup_init before
do_initcalls() is called and before net_dev_init().

.John

Not sure I follow here John.  Shouldn't init_net be initialized prior to any
network devices getting registered?  In other words, shouldn't for_each_netdev
just result in zero iterations through the loop?
Neil

init_net _is_ initialized prior to any network devices getting
registered but not before cgrp_create called via cgroup_init.

#define for_each_netdev(net, d)         \
                list_for_each_entry(d, &(net)->dev_base_head, dev_list)

but dev_base_head is zeroed at this time. In netdev_init we have,

        INIT_LIST_HEAD(&net->dev_base_head);

but we haven't got that far yet because cgroup_init is called
before do_initcalls().

ok, I see that, and it makes sense, but at this point I'm more concerned with
cgroups getting initalized twice.  The early_init flag is clear in the
cgroup_subsystem for netprio, so we really shouldn't be getting initalized from
cgroup_init. We should be getting initalized from the module_init() call that

we register

If the early_init flag is set, a cgroup subsys will be initialized from
cgroup_early_init(), otherwise cgroup_init().

If netprio is built as a module, the subsys will be initailized from module_init(),
otherwise cgroup_init() (in this case cgroup_load_subsys() called in module_init()
is a no-op).

So it won't get initialized twice.

On Thu, Jul 19, 2012 at 09:00:51AM +0800, Li Zefan wrote:

quoted

quoted

quoted

quoted

quoted

 static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)

quoted

quoted

quoted

quoted

quoted

 {
 	struct cgroup_netprio_state *cs;
-	int ret;
+	int ret = -EINVAL;

 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);

-	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) {
-		kfree(cs);
-		return ERR_PTR(-EINVAL);
-	}
+	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
+		goto out;

 	ret = get_prioidx(&cs->prioidx);
-	if (ret != 0) {
+	if (ret < 0) {
 		pr_warn("No space in priority index array\n");
-		kfree(cs);
-		return ERR_PTR(ret);
+		goto out;
+	}
+
+	ret = update_netdev_tables();
+	if (ret < 0) {
+		put_prioidx(cs->prioidx);
+		goto out;
 	}

Gao,

This introduces a null ptr dereference when netprio_cgroup is built
into the kernel because update_netdev_tables() depends on init_net.
However cgrp_create is being called by cgroup_init before
do_initcalls() is called and before net_dev_init().

.John

Not sure I follow here John.  Shouldn't init_net be initialized prior to any
network devices getting registered?  In other words, shouldn't for_each_netdev
just result in zero iterations through the loop?
Neil

init_net _is_ initialized prior to any network devices getting
registered but not before cgrp_create called via cgroup_init.

#define for_each_netdev(net, d)         \
                list_for_each_entry(d, &(net)->dev_base_head, dev_list)

but dev_base_head is zeroed at this time. In netdev_init we have,

        INIT_LIST_HEAD(&net->dev_base_head);

but we haven't got that far yet because cgroup_init is called
before do_initcalls().

ok, I see that, and it makes sense, but at this point I'm more concerned with
cgroups getting initalized twice.  The early_init flag is clear in the
cgroup_subsystem for netprio, so we really shouldn't be getting initalized from
cgroup_init. We should be getting initalized from the module_init() call that

quoted

we register

If the early_init flag is set, a cgroup subsys will be initialized from
cgroup_early_init(), otherwise cgroup_init().

If netprio is built as a module, the subsys will be initailized from module_init(),
otherwise cgroup_init() (in this case cgroup_load_subsys() called in module_init()
is a no-op).

So it won't get initialized twice.

Yeah, we already figured that out :).

Still its not a sane interface.  If you create a module_init function for a bit
of code, you expect that function to be called before the rest of your code ever
gets executed.  The way cgroup_init works, ss->cgroup_create gets called before
the module_init routine does when the module is built monolithically.  So no, no
double initalization, but definately some behavior that is going to be prone to
mistakes.
Neil