OpenCloudOS-Kernel/net/bridge/br_ioctl.c

403 lines
9.0 KiB
C
Raw Normal View History

/*
* Ioctl handler
* Linux ethernet bridge
*
* Authors:
* Lennert Buytenhek <buytenh@gnu.org>
*
* 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.
*/
#include <linux/capability.h>
#include <linux/kernel.h>
#include <linux/if_bridge.h>
#include <linux/netdevice.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/times.h>
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-18 02:56:21 +08:00
#include <net/net_namespace.h>
#include <linux/uaccess.h>
#include "br_private.h"
static int get_bridge_ifindices(struct net *net, int *indices, int num)
{
struct net_device *dev;
int i = 0;
net: bridge: fix old ioctl unlocked net device walk get_bridge_ifindices() is used from the old "deviceless" bridge ioctl calls which aren't called with rtnl held. The comment above says that it is called with rtnl but that is not really the case. Here's a sample output from a test ASSERT_RTNL() which I put in get_bridge_ifindices and executed "brctl show": [ 957.422726] RTNL: assertion failed at net/bridge//br_ioctl.c (30) [ 957.422925] CPU: 0 PID: 1862 Comm: brctl Tainted: G W O 4.6.0-rc4+ #157 [ 957.423009] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014 [ 957.423009] 0000000000000000 ffff880058adfdf0 ffffffff8138dec5 0000000000000400 [ 957.423009] ffffffff81ce8380 ffff880058adfe58 ffffffffa05ead32 0000000000000001 [ 957.423009] 00007ffec1a444b0 0000000000000400 ffff880053c19130 0000000000008940 [ 957.423009] Call Trace: [ 957.423009] [<ffffffff8138dec5>] dump_stack+0x85/0xc0 [ 957.423009] [<ffffffffa05ead32>] br_ioctl_deviceless_stub+0x212/0x2e0 [bridge] [ 957.423009] [<ffffffff81515beb>] sock_ioctl+0x22b/0x290 [ 957.423009] [<ffffffff8126ba75>] do_vfs_ioctl+0x95/0x700 [ 957.423009] [<ffffffff8126c159>] SyS_ioctl+0x79/0x90 [ 957.423009] [<ffffffff8163a4c0>] entry_SYSCALL_64_fastpath+0x23/0xc1 Since it only reads bridge ifindices, we can use rcu to safely walk the net device list. Also remove the wrong rtnl comment above. Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-04 22:18:45 +08:00
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
if (i >= num)
break;
if (dev->priv_flags & IFF_EBRIDGE)
indices[i++] = dev->ifindex;
}
net: bridge: fix old ioctl unlocked net device walk get_bridge_ifindices() is used from the old "deviceless" bridge ioctl calls which aren't called with rtnl held. The comment above says that it is called with rtnl but that is not really the case. Here's a sample output from a test ASSERT_RTNL() which I put in get_bridge_ifindices and executed "brctl show": [ 957.422726] RTNL: assertion failed at net/bridge//br_ioctl.c (30) [ 957.422925] CPU: 0 PID: 1862 Comm: brctl Tainted: G W O 4.6.0-rc4+ #157 [ 957.423009] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014 [ 957.423009] 0000000000000000 ffff880058adfdf0 ffffffff8138dec5 0000000000000400 [ 957.423009] ffffffff81ce8380 ffff880058adfe58 ffffffffa05ead32 0000000000000001 [ 957.423009] 00007ffec1a444b0 0000000000000400 ffff880053c19130 0000000000008940 [ 957.423009] Call Trace: [ 957.423009] [<ffffffff8138dec5>] dump_stack+0x85/0xc0 [ 957.423009] [<ffffffffa05ead32>] br_ioctl_deviceless_stub+0x212/0x2e0 [bridge] [ 957.423009] [<ffffffff81515beb>] sock_ioctl+0x22b/0x290 [ 957.423009] [<ffffffff8126ba75>] do_vfs_ioctl+0x95/0x700 [ 957.423009] [<ffffffff8126c159>] SyS_ioctl+0x79/0x90 [ 957.423009] [<ffffffff8163a4c0>] entry_SYSCALL_64_fastpath+0x23/0xc1 Since it only reads bridge ifindices, we can use rcu to safely walk the net device list. Also remove the wrong rtnl comment above. Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-04 22:18:45 +08:00
rcu_read_unlock();
return i;
}
/* called with RTNL */
static void get_port_ifindices(struct net_bridge *br, int *ifindices, int num)
{
struct net_bridge_port *p;
list_for_each_entry(p, &br->port_list, list) {
if (p->port_no < num)
ifindices[p->port_no] = p->dev->ifindex;
}
}
/*
* Format up to a page worth of forwarding table entries
* userbuf -- where to copy result
* maxnum -- maximum number of entries desired
* (limited to a page for sanity)
* offset -- number of records to skip
*/
static int get_fdb_entries(struct net_bridge *br, void __user *userbuf,
unsigned long maxnum, unsigned long offset)
{
int num;
void *buf;
size_t size;
/* Clamp size to PAGE_SIZE, test maxnum to avoid overflow */
if (maxnum > PAGE_SIZE/sizeof(struct __fdb_entry))
maxnum = PAGE_SIZE/sizeof(struct __fdb_entry);
size = maxnum * sizeof(struct __fdb_entry);
buf = kmalloc(size, GFP_USER);
if (!buf)
return -ENOMEM;
num = br_fdb_fillbuf(br, buf, maxnum, offset);
if (num > 0) {
if (copy_to_user(userbuf, buf, num*sizeof(struct __fdb_entry)))
num = -EFAULT;
}
kfree(buf);
return num;
}
/* called with RTNL */
static int add_del_if(struct net_bridge *br, int ifindex, int isadd)
{
struct net *net = dev_net(br->dev);
struct net_device *dev;
int ret;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
dev = __dev_get_by_index(net, ifindex);
if (dev == NULL)
return -EINVAL;
if (isadd)
ret = br_add_if(br, dev);
else
ret = br_del_if(br, dev);
return ret;
}
/*
* Legacy ioctl's through SIOCDEVPRIVATE
* This interface is deprecated because it was too difficult to
* to do the translation for 32/64bit ioctl compatibility.
*/
static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{
struct net_bridge *br = netdev_priv(dev);
struct net_bridge_port *p = NULL;
unsigned long args[4];
int ret = -EOPNOTSUPP;
if (copy_from_user(args, rq->ifr_data, sizeof(args)))
return -EFAULT;
switch (args[0]) {
case BRCTL_ADD_IF:
case BRCTL_DEL_IF:
return add_del_if(br, args[1], args[0] == BRCTL_ADD_IF);
case BRCTL_GET_BRIDGE_INFO:
{
struct __bridge_info b;
memset(&b, 0, sizeof(struct __bridge_info));
rcu_read_lock();
memcpy(&b.designated_root, &br->designated_root, 8);
memcpy(&b.bridge_id, &br->bridge_id, 8);
b.root_path_cost = br->root_path_cost;
b.max_age = jiffies_to_clock_t(br->max_age);
b.hello_time = jiffies_to_clock_t(br->hello_time);
b.forward_delay = br->forward_delay;
b.bridge_max_age = br->bridge_max_age;
b.bridge_hello_time = br->bridge_hello_time;
b.bridge_forward_delay = jiffies_to_clock_t(br->bridge_forward_delay);
b.topology_change = br->topology_change;
b.topology_change_detected = br->topology_change_detected;
b.root_port = br->root_port;
b.stp_enabled = (br->stp_enabled != BR_NO_STP);
b.ageing_time = jiffies_to_clock_t(br->ageing_time);
b.hello_timer_value = br_timer_value(&br->hello_timer);
b.tcn_timer_value = br_timer_value(&br->tcn_timer);
b.topology_change_timer_value = br_timer_value(&br->topology_change_timer);
b.gc_timer_value = br_timer_value(&br->gc_timer);
rcu_read_unlock();
if (copy_to_user((void __user *)args[1], &b, sizeof(b)))
return -EFAULT;
return 0;
}
case BRCTL_GET_PORT_LIST:
{
int num, *indices;
num = args[2];
if (num < 0)
return -EINVAL;
if (num == 0)
num = 256;
if (num > BR_MAX_PORTS)
num = BR_MAX_PORTS;
indices = kcalloc(num, sizeof(int), GFP_KERNEL);
if (indices == NULL)
return -ENOMEM;
get_port_ifindices(br, indices, num);
if (copy_to_user((void __user *)args[1], indices, num*sizeof(int)))
num = -EFAULT;
kfree(indices);
return num;
}
case BRCTL_SET_BRIDGE_FORWARD_DELAY:
if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
ret = br_set_forward_delay(br, args[1]);
break;
case BRCTL_SET_BRIDGE_HELLO_TIME:
if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
ret = br_set_hello_time(br, args[1]);
break;
case BRCTL_SET_BRIDGE_MAX_AGE:
if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
ret = br_set_max_age(br, args[1]);
break;
case BRCTL_SET_AGEING_TIME:
if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
ret = br_set_ageing_time(br, args[1]);
break;
case BRCTL_GET_PORT_INFO:
{
struct __port_info p;
struct net_bridge_port *pt;
rcu_read_lock();
if ((pt = br_get_port(br, args[2])) == NULL) {
rcu_read_unlock();
return -EINVAL;
}
memset(&p, 0, sizeof(struct __port_info));
memcpy(&p.designated_root, &pt->designated_root, 8);
memcpy(&p.designated_bridge, &pt->designated_bridge, 8);
p.port_id = pt->port_id;
p.designated_port = pt->designated_port;
p.path_cost = pt->path_cost;
p.designated_cost = pt->designated_cost;
p.state = pt->state;
p.top_change_ack = pt->topology_change_ack;
p.config_pending = pt->config_pending;
p.message_age_timer_value = br_timer_value(&pt->message_age_timer);
p.forward_delay_timer_value = br_timer_value(&pt->forward_delay_timer);
p.hold_timer_value = br_timer_value(&pt->hold_timer);
rcu_read_unlock();
if (copy_to_user((void __user *)args[1], &p, sizeof(p)))
return -EFAULT;
return 0;
}
case BRCTL_SET_BRIDGE_STP_STATE:
if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
br_stp_set_enabled(br, args[1]);
ret = 0;
break;
case BRCTL_SET_BRIDGE_PRIORITY:
if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
br_stp_set_bridge_priority(br, args[1]);
ret = 0;
break;
case BRCTL_SET_PORT_PRIORITY:
{
if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
spin_lock_bh(&br->lock);
if ((p = br_get_port(br, args[1])) == NULL)
ret = -EINVAL;
else
ret = br_stp_set_port_priority(p, args[2]);
spin_unlock_bh(&br->lock);
break;
}
case BRCTL_SET_PATH_COST:
{
if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
spin_lock_bh(&br->lock);
if ((p = br_get_port(br, args[1])) == NULL)
ret = -EINVAL;
else
ret = br_stp_set_path_cost(p, args[2]);
spin_unlock_bh(&br->lock);
break;
}
case BRCTL_GET_FDB_ENTRIES:
return get_fdb_entries(br, (void __user *)args[1],
args[2], args[3]);
}
if (!ret) {
if (p)
br_ifinfo_notify(RTM_NEWLINK, p);
else
netdev_state_change(br->dev);
}
return ret;
}
static int old_deviceless(struct net *net, void __user *uarg)
{
unsigned long args[3];
if (copy_from_user(args, uarg, sizeof(args)))
return -EFAULT;
switch (args[0]) {
case BRCTL_GET_VERSION:
return BRCTL_VERSION;
case BRCTL_GET_BRIDGES:
{
int *indices;
int ret = 0;
if (args[2] >= 2048)
return -ENOMEM;
indices = kcalloc(args[2], sizeof(int), GFP_KERNEL);
if (indices == NULL)
return -ENOMEM;
args[2] = get_bridge_ifindices(net, indices, args[2]);
ret = copy_to_user((void __user *)args[1], indices, args[2]*sizeof(int))
? -EFAULT : args[2];
kfree(indices);
return ret;
}
case BRCTL_ADD_BRIDGE:
case BRCTL_DEL_BRIDGE:
{
char buf[IFNAMSIZ];
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
if (copy_from_user(buf, (void __user *)args[1], IFNAMSIZ))
return -EFAULT;
buf[IFNAMSIZ-1] = 0;
if (args[0] == BRCTL_ADD_BRIDGE)
return br_add_bridge(net, buf);
return br_del_bridge(net, buf);
}
}
return -EOPNOTSUPP;
}
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-18 02:56:21 +08:00
int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *uarg)
{
switch (cmd) {
case SIOCGIFBR:
case SIOCSIFBR:
return old_deviceless(net, uarg);
case SIOCBRADDBR:
case SIOCBRDELBR:
{
char buf[IFNAMSIZ];
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
if (copy_from_user(buf, uarg, IFNAMSIZ))
return -EFAULT;
buf[IFNAMSIZ-1] = 0;
if (cmd == SIOCBRADDBR)
return br_add_bridge(net, buf);
return br_del_bridge(net, buf);
}
}
return -EOPNOTSUPP;
}
int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{
struct net_bridge *br = netdev_priv(dev);
switch (cmd) {
case SIOCDEVPRIVATE:
return old_dev_ioctl(dev, rq, cmd);
case SIOCBRADDIF:
case SIOCBRDELIF:
return add_del_if(br, rq->ifr_ifindex, cmd == SIOCBRADDIF);
}
br_debug(br, "Bridge does not support ioctl 0x%x\n", cmd);
return -EOPNOTSUPP;
}