linux/net/ipv4/devinet.c

2438 lines
60 KiB
C
Raw Normal View History

/*
* NET3 IP device support routines.
*
* 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.
*
* Derived from the IP parts of dev.c 1.0.19
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
*
* Additional Authors:
* Alan Cox, <gw4pts@gw4pts.ampr.org>
* Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* Changes:
* Alexey Kuznetsov: pa_* fields are replaced with ifaddr
* lists.
* Cyrus Durgin: updated for kmod
* Matthias Andree: in devinet_ioctl, compare label and
* address (4.4BSD alias style support),
* fall back to comparing just the label
* if no match found.
*/
#include <asm/uaccess.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/if_addr.h>
#include <linux/if_ether.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/inetdevice.h>
#include <linux/igmp.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 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/hash.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/kmod.h>
#include <linux/netconf.h>
#include <net/arp.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/ip_fib.h>
#include <net/rtnetlink.h>
#include <net/net_namespace.h>
#include <net/addrconf.h>
#include "fib_lookup.h"
static struct ipv4_devconf ipv4_devconf = {
.data = {
[IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SHARED_MEDIA - 1] = 1,
net: igmp: Allow user-space configuration of igmp unsolicited report interval Adds the new procfs knobs: /proc/sys/net/ipv4/conf/*/igmpv2_unsolicited_report_interval /proc/sys/net/ipv4/conf/*/igmpv3_unsolicited_report_interval Which will allow userspace configuration of the IGMP unsolicited report interval (see below) in milliseconds. The defaults are 10000ms for IGMPv2 and 1000ms for IGMPv3 in accordance with RFC2236 and RFC3376. Background: If an IGMP join packet is lost you will not receive data sent to the multicast group so if no data arrives from that multicast group in a period of time after the IGMP join a second IGMP join will be sent. The delay between joins is the "IGMP Unsolicited Report Interval". Prior to this patch this value was hard coded in the kernel to 10s for IGMPv2 and 1s for IGMPv3. 10s is unsuitable for some use-cases, such as IPTV as it can cause channel change to be slow in the presence of packet loss. This patch allows the value to be overridden from userspace for both IGMPv2 and IGMPv3 such that it can be tuned accoding to the network. Tested with Wireshark and a simple program to join a (non-existent) multicast group. The distribution of timings for the second join differ based upon setting the procfs knobs. igmpvX_unsolicited_report_interval is intended to follow the pattern established by force_igmp_version, and while a procfs entry has been added a corresponding sysctl knob has not as it is my understanding that sysctl is deprecated[1]. [1]: http://lwn.net/Articles/247243/ Signed-off-by: William Manley <william.manley@youview.com> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Benjamin LaHaise <bcrl@kvack.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-06 18:03:15 +00:00
[IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/,
[IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/,
},
};
static struct ipv4_devconf ipv4_devconf_dflt = {
.data = {
[IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SHARED_MEDIA - 1] = 1,
[IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1,
net: igmp: Allow user-space configuration of igmp unsolicited report interval Adds the new procfs knobs: /proc/sys/net/ipv4/conf/*/igmpv2_unsolicited_report_interval /proc/sys/net/ipv4/conf/*/igmpv3_unsolicited_report_interval Which will allow userspace configuration of the IGMP unsolicited report interval (see below) in milliseconds. The defaults are 10000ms for IGMPv2 and 1000ms for IGMPv3 in accordance with RFC2236 and RFC3376. Background: If an IGMP join packet is lost you will not receive data sent to the multicast group so if no data arrives from that multicast group in a period of time after the IGMP join a second IGMP join will be sent. The delay between joins is the "IGMP Unsolicited Report Interval". Prior to this patch this value was hard coded in the kernel to 10s for IGMPv2 and 1s for IGMPv3. 10s is unsuitable for some use-cases, such as IPTV as it can cause channel change to be slow in the presence of packet loss. This patch allows the value to be overridden from userspace for both IGMPv2 and IGMPv3 such that it can be tuned accoding to the network. Tested with Wireshark and a simple program to join a (non-existent) multicast group. The distribution of timings for the second join differ based upon setting the procfs knobs. igmpvX_unsolicited_report_interval is intended to follow the pattern established by force_igmp_version, and while a procfs entry has been added a corresponding sysctl knob has not as it is my understanding that sysctl is deprecated[1]. [1]: http://lwn.net/Articles/247243/ Signed-off-by: William Manley <william.manley@youview.com> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Benjamin LaHaise <bcrl@kvack.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-06 18:03:15 +00:00
[IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/,
[IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/,
},
};
#define IPV4_DEVCONF_DFLT(net, attr) \
IPV4_DEVCONF((*net->ipv4.devconf_dflt), attr)
static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
[IFA_LOCAL] = { .type = NLA_U32 },
[IFA_ADDRESS] = { .type = NLA_U32 },
[IFA_BROADCAST] = { .type = NLA_U32 },
[IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
[IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) },
[IFA_FLAGS] = { .type = NLA_U32 },
};
#define IN4_ADDR_HSIZE_SHIFT 8
#define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT)
static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE];
static u32 inet_addr_hash(const struct net *net, __be32 addr)
{
u32 val = (__force u32) addr ^ net_hash_mix(net);
return hash_32(val, IN4_ADDR_HSIZE_SHIFT);
}
static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa)
{
u32 hash = inet_addr_hash(net, ifa->ifa_local);
ASSERT_RTNL();
hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]);
}
static void inet_hash_remove(struct in_ifaddr *ifa)
{
ASSERT_RTNL();
hlist_del_init_rcu(&ifa->hash);
}
/**
* __ip_dev_find - find the first device with a given source address.
* @net: the net namespace
* @addr: the source address
* @devref: if true, take a reference on the found device
*
* If a caller uses devref=false, it should be protected by RCU, or RTNL
*/
struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
{
u32 hash = inet_addr_hash(net, addr);
struct net_device *result = NULL;
struct in_ifaddr *ifa;
rcu_read_lock();
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) {
if (ifa->ifa_local == addr) {
struct net_device *dev = ifa->ifa_dev->dev;
if (!net_eq(dev_net(dev), net))
continue;
result = dev;
break;
}
}
if (!result) {
struct flowi4 fl4 = { .daddr = addr };
struct fib_result res = { 0 };
struct fib_table *local;
/* Fallback to FIB local table so that communication
* over loopback subnets work.
*/
local = fib_get_table(net, RT_TABLE_LOCAL);
if (local &&
!fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) &&
res.type == RTN_LOCAL)
result = FIB_RES_DEV(res);
}
if (result && devref)
dev_hold(result);
rcu_read_unlock();
return result;
}
EXPORT_SYMBOL(__ip_dev_find);
static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 09:16:30 +00:00
static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
int destroy);
#ifdef CONFIG_SYSCTL
static int devinet_sysctl_register(struct in_device *idev);
static void devinet_sysctl_unregister(struct in_device *idev);
#else
static int devinet_sysctl_register(struct in_device *idev)
{
return 0;
}
static void devinet_sysctl_unregister(struct in_device *idev)
{
}
#endif
/* Locks all the inet devices. */
static struct in_ifaddr *inet_alloc_ifa(void)
{
return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL);
}
static void inet_rcu_free_ifa(struct rcu_head *head)
{
struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head);
if (ifa->ifa_dev)
in_dev_put(ifa->ifa_dev);
kfree(ifa);
}
static void inet_free_ifa(struct in_ifaddr *ifa)
{
call_rcu(&ifa->rcu_head, inet_rcu_free_ifa);
}
void in_dev_finish_destroy(struct in_device *idev)
{
struct net_device *dev = idev->dev;
WARN_ON(idev->ifa_list);
WARN_ON(idev->mc_list);
kfree(rcu_dereference_protected(idev->mc_hash, 1));
#ifdef NET_REFCNT_DEBUG
pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL");
#endif
dev_put(dev);
if (!idev->dead)
pr_err("Freeing alive in_device %p\n", idev);
else
kfree(idev);
}
EXPORT_SYMBOL(in_dev_finish_destroy);
static struct in_device *inetdev_init(struct net_device *dev)
{
struct in_device *in_dev;
int err = -ENOMEM;
ASSERT_RTNL();
in_dev = kzalloc(sizeof(*in_dev), GFP_KERNEL);
if (!in_dev)
goto out;
memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt,
sizeof(in_dev->cnf));
in_dev->cnf.sysctl = NULL;
in_dev->dev = dev;
in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl);
if (!in_dev->arp_parms)
goto out_kfree;
if (IPV4_DEVCONF(in_dev->cnf, FORWARDING))
dev_disable_lro(dev);
/* Reference in_dev->dev */
dev_hold(dev);
/* Account for reference dev->ip_ptr (below) */
in_dev_hold(in_dev);
err = devinet_sysctl_register(in_dev);
if (err) {
in_dev->dead = 1;
in_dev_put(in_dev);
in_dev = NULL;
goto out;
}
ip_mc_init_dev(in_dev);
if (dev->flags & IFF_UP)
ip_mc_up(in_dev);
/* we can receive as soon as ip_ptr is set -- do this last */
rcu_assign_pointer(dev->ip_ptr, in_dev);
out:
return in_dev ?: ERR_PTR(err);
out_kfree:
kfree(in_dev);
in_dev = NULL;
goto out;
}
static void in_dev_rcu_put(struct rcu_head *head)
{
struct in_device *idev = container_of(head, struct in_device, rcu_head);
in_dev_put(idev);
}
static void inetdev_destroy(struct in_device *in_dev)
{
struct in_ifaddr *ifa;
struct net_device *dev;
ASSERT_RTNL();
dev = in_dev->dev;
in_dev->dead = 1;
ip_mc_destroy_dev(in_dev);
while ((ifa = in_dev->ifa_list) != NULL) {
inet_del_ifa(in_dev, &in_dev->ifa_list, 0);
inet_free_ifa(ifa);
}
RCU_INIT_POINTER(dev->ip_ptr, NULL);
devinet_sysctl_unregister(in_dev);
neigh_parms_release(&arp_tbl, in_dev->arp_parms);
arp_ifdown(dev);
call_rcu(&in_dev->rcu_head, in_dev_rcu_put);
}
int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b)
{
rcu_read_lock();
for_primary_ifa(in_dev) {
if (inet_ifa_match(a, ifa)) {
if (!b || inet_ifa_match(b, ifa)) {
rcu_read_unlock();
return 1;
}
}
} endfor_ifa(in_dev);
rcu_read_unlock();
return 0;
}
static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
int destroy, struct nlmsghdr *nlh, u32 portid)
{
struct in_ifaddr *promote = NULL;
struct in_ifaddr *ifa, *ifa1 = *ifap;
struct in_ifaddr *last_prim = in_dev->ifa_list;
struct in_ifaddr *prev_prom = NULL;
int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev);
ASSERT_RTNL();
if (in_dev->dead)
goto no_promotions;
/* 1. Deleting primary ifaddr forces deletion all secondaries
* unless alias promotion is set
**/
if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) {
struct in_ifaddr **ifap1 = &ifa1->ifa_next;
while ((ifa = *ifap1) != NULL) {
if (!(ifa->ifa_flags & IFA_F_SECONDARY) &&
ifa1->ifa_scope <= ifa->ifa_scope)
last_prim = ifa;
if (!(ifa->ifa_flags & IFA_F_SECONDARY) ||
ifa1->ifa_mask != ifa->ifa_mask ||
!inet_ifa_match(ifa1->ifa_address, ifa)) {
ifap1 = &ifa->ifa_next;
prev_prom = ifa;
continue;
}
if (!do_promote) {
inet_hash_remove(ifa);
*ifap1 = ifa->ifa_next;
rtmsg_ifa(RTM_DELADDR, ifa, nlh, portid);
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 09:16:30 +00:00
blocking_notifier_call_chain(&inetaddr_chain,
NETDEV_DOWN, ifa);
inet_free_ifa(ifa);
} else {
promote = ifa;
break;
}
}
}
/* On promotion all secondaries from subnet are changing
* the primary IP, we must remove all their routes silently
* and later to add them back with new prefsrc. Do this
* while all addresses are on the device list.
*/
for (ifa = promote; ifa; ifa = ifa->ifa_next) {
if (ifa1->ifa_mask == ifa->ifa_mask &&
inet_ifa_match(ifa1->ifa_address, ifa))
fib_del_ifaddr(ifa, ifa1);
}
no_promotions:
/* 2. Unlink it */
*ifap = ifa1->ifa_next;
inet_hash_remove(ifa1);
/* 3. Announce address deletion */
/* Send message first, then call notifier.
At first sight, FIB update triggered by notifier
will refer to already deleted ifaddr, that could confuse
netlink listeners. It is not true: look, gated sees
that route deleted and if it still thinks that ifaddr
is valid, it will try to restore deleted routes... Grr.
So that, this order is correct.
*/
rtmsg_ifa(RTM_DELADDR, ifa1, nlh, portid);
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 09:16:30 +00:00
blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1);
if (promote) {
struct in_ifaddr *next_sec = promote->ifa_next;
if (prev_prom) {
prev_prom->ifa_next = promote->ifa_next;
promote->ifa_next = last_prim->ifa_next;
last_prim->ifa_next = promote;
}
promote->ifa_flags &= ~IFA_F_SECONDARY;
rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid);
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 09:16:30 +00:00
blocking_notifier_call_chain(&inetaddr_chain,
NETDEV_UP, promote);
for (ifa = next_sec; ifa; ifa = ifa->ifa_next) {
if (ifa1->ifa_mask != ifa->ifa_mask ||
!inet_ifa_match(ifa1->ifa_address, ifa))
continue;
fib_add_ifaddr(ifa);
}
}
if (destroy)
inet_free_ifa(ifa1);
}
static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
int destroy)
{
__inet_del_ifa(in_dev, ifap, destroy, NULL, 0);
}
static void check_lifetime(struct work_struct *work);
static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime);
static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh,
u32 portid)
{
struct in_device *in_dev = ifa->ifa_dev;
struct in_ifaddr *ifa1, **ifap, **last_primary;
ASSERT_RTNL();
if (!ifa->ifa_local) {
inet_free_ifa(ifa);
return 0;
}
ifa->ifa_flags &= ~IFA_F_SECONDARY;
last_primary = &in_dev->ifa_list;
for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL;
ifap = &ifa1->ifa_next) {
if (!(ifa1->ifa_flags & IFA_F_SECONDARY) &&
ifa->ifa_scope <= ifa1->ifa_scope)
last_primary = &ifa1->ifa_next;
if (ifa1->ifa_mask == ifa->ifa_mask &&
inet_ifa_match(ifa1->ifa_address, ifa)) {
if (ifa1->ifa_local == ifa->ifa_local) {
inet_free_ifa(ifa);
return -EEXIST;
}
if (ifa1->ifa_scope != ifa->ifa_scope) {
inet_free_ifa(ifa);
return -EINVAL;
}
ifa->ifa_flags |= IFA_F_SECONDARY;
}
}
if (!(ifa->ifa_flags & IFA_F_SECONDARY)) {
prandom_seed((__force u32) ifa->ifa_local);
ifap = last_primary;
}
ifa->ifa_next = *ifap;
*ifap = ifa;
inet_hash_insert(dev_net(in_dev->dev), ifa);
cancel_delayed_work(&check_lifetime_work);
queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0);
/* Send message first, then call notifier.
Notifier will trigger FIB update, so that
listeners of netlink will know about new ifaddr */
rtmsg_ifa(RTM_NEWADDR, ifa, nlh, portid);
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 09:16:30 +00:00
blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
return 0;
}
static int inet_insert_ifa(struct in_ifaddr *ifa)
{
return __inet_insert_ifa(ifa, NULL, 0);
}
static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
{
struct in_device *in_dev = __in_dev_get_rtnl(dev);
ASSERT_RTNL();
if (!in_dev) {
inet_free_ifa(ifa);
return -ENOBUFS;
}
ipv4_devconf_setall(in_dev);
neigh_parms_data_state_setall(in_dev->arp_parms);
if (ifa->ifa_dev != in_dev) {
WARN_ON(ifa->ifa_dev);
in_dev_hold(in_dev);
ifa->ifa_dev = in_dev;
}
if (ipv4_is_loopback(ifa->ifa_local))
ifa->ifa_scope = RT_SCOPE_HOST;
return inet_insert_ifa(ifa);
}
/* Caller must hold RCU or RTNL :
* We dont take a reference on found in_device
*/
struct in_device *inetdev_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
struct in_device *in_dev = NULL;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, ifindex);
if (dev)
in_dev = rcu_dereference_rtnl(dev->ip_ptr);
rcu_read_unlock();
return in_dev;
}
EXPORT_SYMBOL(inetdev_by_index);
/* Called only from RTNL semaphored context. No locks. */
struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
__be32 mask)
{
ASSERT_RTNL();
for_primary_ifa(in_dev) {
if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa))
return ifa;
} endfor_ifa(in_dev);
return NULL;
}
static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa)
{
struct ip_mreqn mreq = {
.imr_multiaddr.s_addr = ifa->ifa_address,
.imr_ifindex = ifa->ifa_dev->dev->ifindex,
};
int ret;
ASSERT_RTNL();
lock_sock(sk);
if (join)
ret = ip_mc_join_group(sk, &mreq);
else
ret = ip_mc_leave_group(sk, &mreq);
release_sock(sk);
return ret;
}
static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct nlattr *tb[IFA_MAX+1];
struct in_device *in_dev;
struct ifaddrmsg *ifm;
struct in_ifaddr *ifa, **ifap;
int err = -EINVAL;
ASSERT_RTNL();
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
if (err < 0)
goto errout;
ifm = nlmsg_data(nlh);
in_dev = inetdev_by_index(net, ifm->ifa_index);
if (!in_dev) {
err = -ENODEV;
goto errout;
}
for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
ifap = &ifa->ifa_next) {
if (tb[IFA_LOCAL] &&
ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL]))
continue;
if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label))
continue;
if (tb[IFA_ADDRESS] &&
(ifm->ifa_prefixlen != ifa->ifa_prefixlen ||
!inet_ifa_match(nla_get_in_addr(tb[IFA_ADDRESS]), ifa)))
continue;
if (ipv4_is_multicast(ifa->ifa_address))
ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa);
__inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid);
return 0;
}
err = -EADDRNOTAVAIL;
errout:
return err;
}
#define INFINITY_LIFE_TIME 0xFFFFFFFF
static void check_lifetime(struct work_struct *work)
{
unsigned long now, next, next_sec, next_sched;
struct in_ifaddr *ifa;
struct hlist_node *n;
int i;
now = jiffies;
next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);
for (i = 0; i < IN4_ADDR_HSIZE; i++) {
bool change_needed = false;
rcu_read_lock();
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) {
unsigned long age;
if (ifa->ifa_flags & IFA_F_PERMANENT)
continue;
/* We try to batch several events at once. */
age = (now - ifa->ifa_tstamp +
ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME &&
age >= ifa->ifa_valid_lft) {
change_needed = true;
} else if (ifa->ifa_preferred_lft ==
INFINITY_LIFE_TIME) {
continue;
} else if (age >= ifa->ifa_preferred_lft) {
if (time_before(ifa->ifa_tstamp +
ifa->ifa_valid_lft * HZ, next))
next = ifa->ifa_tstamp +
ifa->ifa_valid_lft * HZ;
if (!(ifa->ifa_flags & IFA_F_DEPRECATED))
change_needed = true;
} else if (time_before(ifa->ifa_tstamp +
ifa->ifa_preferred_lft * HZ,
next)) {
next = ifa->ifa_tstamp +
ifa->ifa_preferred_lft * HZ;
}
}
rcu_read_unlock();
if (!change_needed)
continue;
rtnl_lock();
hlist_for_each_entry_safe(ifa, n, &inet_addr_lst[i], hash) {
unsigned long age;
if (ifa->ifa_flags & IFA_F_PERMANENT)
continue;
/* We try to batch several events at once. */
age = (now - ifa->ifa_tstamp +
ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME &&
age >= ifa->ifa_valid_lft) {
struct in_ifaddr **ifap;
for (ifap = &ifa->ifa_dev->ifa_list;
*ifap != NULL; ifap = &(*ifap)->ifa_next) {
if (*ifap == ifa) {
inet_del_ifa(ifa->ifa_dev,
ifap, 1);
break;
}
}
} else if (ifa->ifa_preferred_lft !=
INFINITY_LIFE_TIME &&
age >= ifa->ifa_preferred_lft &&
!(ifa->ifa_flags & IFA_F_DEPRECATED)) {
ifa->ifa_flags |= IFA_F_DEPRECATED;
rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
}
}
rtnl_unlock();
}
next_sec = round_jiffies_up(next);
next_sched = next;
/* If rounded timeout is accurate enough, accept it. */
if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ))
next_sched = next_sec;
now = jiffies;
/* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */
if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX))
next_sched = now + ADDRCONF_TIMER_FUZZ_MAX;
queue_delayed_work(system_power_efficient_wq, &check_lifetime_work,
next_sched - now);
}
static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft,
__u32 prefered_lft)
{
unsigned long timeout;
ifa->ifa_flags &= ~(IFA_F_PERMANENT | IFA_F_DEPRECATED);
timeout = addrconf_timeout_fixup(valid_lft, HZ);
if (addrconf_finite_timeout(timeout))
ifa->ifa_valid_lft = timeout;
else
ifa->ifa_flags |= IFA_F_PERMANENT;
timeout = addrconf_timeout_fixup(prefered_lft, HZ);
if (addrconf_finite_timeout(timeout)) {
if (timeout == 0)
ifa->ifa_flags |= IFA_F_DEPRECATED;
ifa->ifa_preferred_lft = timeout;
}
ifa->ifa_tstamp = jiffies;
if (!ifa->ifa_cstamp)
ifa->ifa_cstamp = ifa->ifa_tstamp;
}
static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
__u32 *pvalid_lft, __u32 *pprefered_lft)
{
struct nlattr *tb[IFA_MAX+1];
struct in_ifaddr *ifa;
struct ifaddrmsg *ifm;
struct net_device *dev;
struct in_device *in_dev;
int err;
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
if (err < 0)
goto errout;
ifm = nlmsg_data(nlh);
err = -EINVAL;
if (ifm->ifa_prefixlen > 32 || !tb[IFA_LOCAL])
goto errout;
dev = __dev_get_by_index(net, ifm->ifa_index);
err = -ENODEV;
if (!dev)
goto errout;
in_dev = __in_dev_get_rtnl(dev);
err = -ENOBUFS;
if (!in_dev)
goto errout;
ifa = inet_alloc_ifa();
if (!ifa)
/*
* A potential indev allocation can be left alive, it stays
* assigned to its device and is destroy with it.
*/
goto errout;
ipv4_devconf_setall(in_dev);
neigh_parms_data_state_setall(in_dev->arp_parms);
in_dev_hold(in_dev);
if (!tb[IFA_ADDRESS])
tb[IFA_ADDRESS] = tb[IFA_LOCAL];
INIT_HLIST_NODE(&ifa->hash);
ifa->ifa_prefixlen = ifm->ifa_prefixlen;
ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen);
ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) :
ifm->ifa_flags;
ifa->ifa_scope = ifm->ifa_scope;
ifa->ifa_dev = in_dev;
ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]);
ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]);
if (tb[IFA_BROADCAST])
ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]);
if (tb[IFA_LABEL])
nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
if (tb[IFA_CACHEINFO]) {
struct ifa_cacheinfo *ci;
ci = nla_data(tb[IFA_CACHEINFO]);
if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) {
err = -EINVAL;
goto errout_free;
}
*pvalid_lft = ci->ifa_valid;
*pprefered_lft = ci->ifa_prefered;
}
return ifa;
errout_free:
inet_free_ifa(ifa);
errout:
return ERR_PTR(err);
}
static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa)
{
struct in_device *in_dev = ifa->ifa_dev;
struct in_ifaddr *ifa1, **ifap;
if (!ifa->ifa_local)
return NULL;
for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL;
ifap = &ifa1->ifa_next) {
if (ifa1->ifa_mask == ifa->ifa_mask &&
inet_ifa_match(ifa1->ifa_address, ifa) &&
ifa1->ifa_local == ifa->ifa_local)
return ifa1;
}
return NULL;
}
static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct in_ifaddr *ifa;
struct in_ifaddr *ifa_existing;
__u32 valid_lft = INFINITY_LIFE_TIME;
__u32 prefered_lft = INFINITY_LIFE_TIME;
ASSERT_RTNL();
ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft);
if (IS_ERR(ifa))
return PTR_ERR(ifa);
ifa_existing = find_matching_ifa(ifa);
if (!ifa_existing) {
/* It would be best to check for !NLM_F_CREATE here but
* userspace already relies on not having to provide this.
*/
set_ifa_lifetime(ifa, valid_lft, prefered_lft);
if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) {
int ret = ip_mc_config(net->ipv4.mc_autojoin_sk,
true, ifa);
if (ret < 0) {
inet_free_ifa(ifa);
return ret;
}
}
return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid);
} else {
inet_free_ifa(ifa);
if (nlh->nlmsg_flags & NLM_F_EXCL ||
!(nlh->nlmsg_flags & NLM_F_REPLACE))
return -EEXIST;
ifa = ifa_existing;
set_ifa_lifetime(ifa, valid_lft, prefered_lft);
cancel_delayed_work(&check_lifetime_work);
queue_delayed_work(system_power_efficient_wq,
&check_lifetime_work, 0);
rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
}
return 0;
}
/*
* Determine a default network mask, based on the IP address.
*/
static int inet_abc_len(__be32 addr)
{
int rc = -1; /* Something else, probably a multicast. */
if (ipv4_is_zeronet(addr))
rc = 0;
else {
__u32 haddr = ntohl(addr);
if (IN_CLASSA(haddr))
rc = 8;
else if (IN_CLASSB(haddr))
rc = 16;
else if (IN_CLASSC(haddr))
rc = 24;
}
return rc;
}
int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
struct ifreq ifr;
struct sockaddr_in sin_orig;
struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;
struct in_device *in_dev;
struct in_ifaddr **ifap = NULL;
struct in_ifaddr *ifa = NULL;
struct net_device *dev;
char *colon;
int ret = -EFAULT;
int tryaddrmatch = 0;
/*
* Fetch the caller's info block into kernel space
*/
if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
goto out;
ifr.ifr_name[IFNAMSIZ - 1] = 0;
/* save original address for comparison */
memcpy(&sin_orig, sin, sizeof(*sin));
colon = strchr(ifr.ifr_name, ':');
if (colon)
*colon = 0;
dev_load(net, ifr.ifr_name);
switch (cmd) {
case SIOCGIFADDR: /* Get interface address */
case SIOCGIFBRDADDR: /* Get the broadcast address */
case SIOCGIFDSTADDR: /* Get the destination address */
case SIOCGIFNETMASK: /* Get the netmask for the interface */
/* Note that these ioctls will not sleep,
so that we do not impose a lock.
One day we will be forced to put shlock here (I mean SMP)
*/
tryaddrmatch = (sin_orig.sin_family == AF_INET);
memset(sin, 0, sizeof(*sin));
sin->sin_family = AF_INET;
break;
case SIOCSIFFLAGS:
ret = -EPERM;
net: Allow userns root to control ipv4 Allow an unpriviled user who has created a user namespace, and then created a network namespace to effectively use the new network namespace, by reducing capable(CAP_NET_ADMIN) and capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns, CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls. Settings that merely control a single network device are allowed. Either the network device is a logical network device where restrictions make no difference or the network device is hardware NIC that has been explicity moved from the initial network namespace. In general policy and network stack state changes are allowed while resource control is left unchanged. Allow creating raw sockets. Allow the SIOCSARP ioctl to control the arp cache. Allow the SIOCSIFFLAG ioctl to allow setting network device flags. Allow the SIOCSIFADDR ioctl to allow setting a netdevice ipv4 address. Allow the SIOCSIFBRDADDR ioctl to allow setting a netdevice ipv4 broadcast address. Allow the SIOCSIFDSTADDR ioctl to allow setting a netdevice ipv4 destination address. Allow the SIOCSIFNETMASK ioctl to allow setting a netdevice ipv4 netmask. Allow the SIOCADDRT and SIOCDELRT ioctls to allow adding and deleting ipv4 routes. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting gre tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipip tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipsec virtual tunnel interfaces. Allow setting the MRT_INIT, MRT_DONE, MRT_ADD_VIF, MRT_DEL_VIF, MRT_ADD_MFC, MRT_DEL_MFC, MRT_ASSERT, MRT_PIM, MRT_TABLE socket options on multicast routing sockets. Allow setting and receiving IPOPT_CIPSO, IP_OPT_SEC, IP_OPT_SID and arbitrary ip options. Allow setting IP_SEC_POLICY/IP_XFRM_POLICY ipv4 socket option. Allow setting the IP_TRANSPARENT ipv4 socket option. Allow setting the TCP_REPAIR socket option. Allow setting the TCP_CONGESTION socket option. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-16 03:03:05 +00:00
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
goto out;
break;
case SIOCSIFADDR: /* Set interface address (and family) */
case SIOCSIFBRDADDR: /* Set the broadcast address */
case SIOCSIFDSTADDR: /* Set the destination address */
case SIOCSIFNETMASK: /* Set the netmask for the interface */
ret = -EPERM;
net: Allow userns root to control ipv4 Allow an unpriviled user who has created a user namespace, and then created a network namespace to effectively use the new network namespace, by reducing capable(CAP_NET_ADMIN) and capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns, CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls. Settings that merely control a single network device are allowed. Either the network device is a logical network device where restrictions make no difference or the network device is hardware NIC that has been explicity moved from the initial network namespace. In general policy and network stack state changes are allowed while resource control is left unchanged. Allow creating raw sockets. Allow the SIOCSARP ioctl to control the arp cache. Allow the SIOCSIFFLAG ioctl to allow setting network device flags. Allow the SIOCSIFADDR ioctl to allow setting a netdevice ipv4 address. Allow the SIOCSIFBRDADDR ioctl to allow setting a netdevice ipv4 broadcast address. Allow the SIOCSIFDSTADDR ioctl to allow setting a netdevice ipv4 destination address. Allow the SIOCSIFNETMASK ioctl to allow setting a netdevice ipv4 netmask. Allow the SIOCADDRT and SIOCDELRT ioctls to allow adding and deleting ipv4 routes. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting gre tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipip tunnels. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for adding, changing and deleting ipsec virtual tunnel interfaces. Allow setting the MRT_INIT, MRT_DONE, MRT_ADD_VIF, MRT_DEL_VIF, MRT_ADD_MFC, MRT_DEL_MFC, MRT_ASSERT, MRT_PIM, MRT_TABLE socket options on multicast routing sockets. Allow setting and receiving IPOPT_CIPSO, IP_OPT_SEC, IP_OPT_SID and arbitrary ip options. Allow setting IP_SEC_POLICY/IP_XFRM_POLICY ipv4 socket option. Allow setting the IP_TRANSPARENT ipv4 socket option. Allow setting the TCP_REPAIR socket option. Allow setting the TCP_CONGESTION socket option. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-16 03:03:05 +00:00
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
goto out;
ret = -EINVAL;
if (sin->sin_family != AF_INET)
goto out;
break;
default:
ret = -EINVAL;
goto out;
}
rtnl_lock();
ret = -ENODEV;
dev = __dev_get_by_name(net, ifr.ifr_name);
if (!dev)
goto done;
if (colon)
*colon = ':';
in_dev = __in_dev_get_rtnl(dev);
if (in_dev) {
if (tryaddrmatch) {
/* Matthias Andree */
/* compare label and address (4.4BSD style) */
/* note: we only do this for a limited set of ioctls
and only if the original address family was AF_INET.
This is checked above. */
for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
ifap = &ifa->ifa_next) {
if (!strcmp(ifr.ifr_name, ifa->ifa_label) &&
sin_orig.sin_addr.s_addr ==
ifa->ifa_local) {
break; /* found */
}
}
}
/* we didn't get a match, maybe the application is
4.3BSD-style and passed in junk so we fall back to
comparing just the label */
if (!ifa) {
for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
ifap = &ifa->ifa_next)
if (!strcmp(ifr.ifr_name, ifa->ifa_label))
break;
}
}
ret = -EADDRNOTAVAIL;
if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS)
goto done;
switch (cmd) {
case SIOCGIFADDR: /* Get interface address */
sin->sin_addr.s_addr = ifa->ifa_local;
goto rarok;
case SIOCGIFBRDADDR: /* Get the broadcast address */
sin->sin_addr.s_addr = ifa->ifa_broadcast;
goto rarok;
case SIOCGIFDSTADDR: /* Get the destination address */
sin->sin_addr.s_addr = ifa->ifa_address;
goto rarok;
case SIOCGIFNETMASK: /* Get the netmask for the interface */
sin->sin_addr.s_addr = ifa->ifa_mask;
goto rarok;
case SIOCSIFFLAGS:
if (colon) {
ret = -EADDRNOTAVAIL;
if (!ifa)
break;
ret = 0;
if (!(ifr.ifr_flags & IFF_UP))
inet_del_ifa(in_dev, ifap, 1);
break;
}
ret = dev_change_flags(dev, ifr.ifr_flags);
break;
case SIOCSIFADDR: /* Set interface address (and family) */
ret = -EINVAL;
if (inet_abc_len(sin->sin_addr.s_addr) < 0)
break;
if (!ifa) {
ret = -ENOBUFS;
ifa = inet_alloc_ifa();
if (!ifa)
break;
INIT_HLIST_NODE(&ifa->hash);
if (colon)
memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ);
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
} else {
ret = 0;
if (ifa->ifa_local == sin->sin_addr.s_addr)
break;
inet_del_ifa(in_dev, ifap, 0);
ifa->ifa_broadcast = 0;
ifa->ifa_scope = 0;
}
ifa->ifa_address = ifa->ifa_local = sin->sin_addr.s_addr;
if (!(dev->flags & IFF_POINTOPOINT)) {
ifa->ifa_prefixlen = inet_abc_len(ifa->ifa_address);
ifa->ifa_mask = inet_make_mask(ifa->ifa_prefixlen);
if ((dev->flags & IFF_BROADCAST) &&
ifa->ifa_prefixlen < 31)
ifa->ifa_broadcast = ifa->ifa_address |
~ifa->ifa_mask;
} else {
ifa->ifa_prefixlen = 32;
ifa->ifa_mask = inet_make_mask(32);
}
set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
ret = inet_set_ifa(dev, ifa);
break;
case SIOCSIFBRDADDR: /* Set the broadcast address */
ret = 0;
if (ifa->ifa_broadcast != sin->sin_addr.s_addr) {
inet_del_ifa(in_dev, ifap, 0);
ifa->ifa_broadcast = sin->sin_addr.s_addr;
inet_insert_ifa(ifa);
}
break;
case SIOCSIFDSTADDR: /* Set the destination address */
ret = 0;
if (ifa->ifa_address == sin->sin_addr.s_addr)
break;
ret = -EINVAL;
if (inet_abc_len(sin->sin_addr.s_addr) < 0)
break;
ret = 0;
inet_del_ifa(in_dev, ifap, 0);
ifa->ifa_address = sin->sin_addr.s_addr;
inet_insert_ifa(ifa);
break;
case SIOCSIFNETMASK: /* Set the netmask for the interface */
/*
* The mask we set must be legal.
*/
ret = -EINVAL;
if (bad_mask(sin->sin_addr.s_addr, 0))
break;
ret = 0;
if (ifa->ifa_mask != sin->sin_addr.s_addr) {
__be32 old_mask = ifa->ifa_mask;
inet_del_ifa(in_dev, ifap, 0);
ifa->ifa_mask = sin->sin_addr.s_addr;
ifa->ifa_prefixlen = inet_mask_len(ifa->ifa_mask);
/* See if current broadcast address matches
* with current netmask, then recalculate
* the broadcast address. Otherwise it's a
* funny address, so don't touch it since
* the user seems to know what (s)he's doing...
*/
if ((dev->flags & IFF_BROADCAST) &&
(ifa->ifa_prefixlen < 31) &&
(ifa->ifa_broadcast ==
(ifa->ifa_local|~old_mask))) {
ifa->ifa_broadcast = (ifa->ifa_local |
~sin->sin_addr.s_addr);
}
inet_insert_ifa(ifa);
}
break;
}
done:
rtnl_unlock();
out:
return ret;
rarok:
rtnl_unlock();
ret = copy_to_user(arg, &ifr, sizeof(struct ifreq)) ? -EFAULT : 0;
goto out;
}
static int inet_gifconf(struct net_device *dev, char __user *buf, int len)
{
struct in_device *in_dev = __in_dev_get_rtnl(dev);
struct in_ifaddr *ifa;
struct ifreq ifr;
int done = 0;
if (!in_dev)
goto out;
for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
if (!buf) {
done += sizeof(ifr);
continue;
}
if (len < (int) sizeof(ifr))
break;
memset(&ifr, 0, sizeof(struct ifreq));
strcpy(ifr.ifr_name, ifa->ifa_label);
(*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET;
(*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr =
ifa->ifa_local;
if (copy_to_user(buf, &ifr, sizeof(struct ifreq))) {
done = -EFAULT;
break;
}
buf += sizeof(struct ifreq);
len -= sizeof(struct ifreq);
done += sizeof(struct ifreq);
}
out:
return done;
}
__be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
{
__be32 addr = 0;
struct in_device *in_dev;
struct net *net = dev_net(dev);
net: l3mdev: address selection should only consider devices in L3 domain David Lamparter noted a use case where the source address selection fails to pick an address from a VRF interface - unnumbered interfaces. Relevant commands from his script: ip addr add 9.9.9.9/32 dev lo ip link set lo up ip link add name vrf0 type vrf table 101 ip rule add oif vrf0 table 101 ip rule add iif vrf0 table 101 ip link set vrf0 up ip addr add 10.0.0.3/32 dev vrf0 ip link add name dummy2 type dummy ip link set dummy2 master vrf0 up --> note dummy2 has no address - unnumbered device ip route add 10.2.2.2/32 dev dummy2 table 101 ip neigh add 10.2.2.2 dev dummy2 lladdr 02:00:00:00:00:02 tcpdump -ni dummy2 & And using ping instead of his socat example: $ ping -I vrf0 -c1 10.2.2.2 ping: Warning: source address might be selected on device other than vrf0. PING 10.2.2.2 (10.2.2.2) from 9.9.9.9 vrf0: 56(84) bytes of data. >From tcpdump: 12:57:29.449128 IP 9.9.9.9 > 10.2.2.2: ICMP echo request, id 2491, seq 1, length 64 Note the source address is from lo and is not a VRF local address. With this patch: $ ping -I vrf0 -c1 10.2.2.2 PING 10.2.2.2 (10.2.2.2) from 10.0.0.3 vrf0: 56(84) bytes of data. >From tcpdump: 12:59:25.096426 IP 10.0.0.3 > 10.2.2.2: ICMP echo request, id 2113, seq 1, length 64 Now the source address comes from vrf0. The ipv4 function for selecting source address takes a const argument. Removing the const requires touching a lot of places, so instead l3mdev_master_ifindex_rcu is changed to take a const argument and then do the typecast to non-const as required by netdev_master_upper_dev_get_rcu. This is similar to what l3mdev_fib_table_rcu does. IPv6 for unnumbered interfaces appears to be selecting the addresses properly. Cc: David Lamparter <david@opensourcerouting.org> Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-24 19:47:02 +00:00
int master_idx;
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
goto no_in_dev;
for_primary_ifa(in_dev) {
if (ifa->ifa_scope > scope)
continue;
if (!dst || inet_ifa_match(dst, ifa)) {
addr = ifa->ifa_local;
break;
}
if (!addr)
addr = ifa->ifa_local;
} endfor_ifa(in_dev);
if (addr)
goto out_unlock;
no_in_dev:
net: l3mdev: address selection should only consider devices in L3 domain David Lamparter noted a use case where the source address selection fails to pick an address from a VRF interface - unnumbered interfaces. Relevant commands from his script: ip addr add 9.9.9.9/32 dev lo ip link set lo up ip link add name vrf0 type vrf table 101 ip rule add oif vrf0 table 101 ip rule add iif vrf0 table 101 ip link set vrf0 up ip addr add 10.0.0.3/32 dev vrf0 ip link add name dummy2 type dummy ip link set dummy2 master vrf0 up --> note dummy2 has no address - unnumbered device ip route add 10.2.2.2/32 dev dummy2 table 101 ip neigh add 10.2.2.2 dev dummy2 lladdr 02:00:00:00:00:02 tcpdump -ni dummy2 & And using ping instead of his socat example: $ ping -I vrf0 -c1 10.2.2.2 ping: Warning: source address might be selected on device other than vrf0. PING 10.2.2.2 (10.2.2.2) from 9.9.9.9 vrf0: 56(84) bytes of data. >From tcpdump: 12:57:29.449128 IP 9.9.9.9 > 10.2.2.2: ICMP echo request, id 2491, seq 1, length 64 Note the source address is from lo and is not a VRF local address. With this patch: $ ping -I vrf0 -c1 10.2.2.2 PING 10.2.2.2 (10.2.2.2) from 10.0.0.3 vrf0: 56(84) bytes of data. >From tcpdump: 12:59:25.096426 IP 10.0.0.3 > 10.2.2.2: ICMP echo request, id 2113, seq 1, length 64 Now the source address comes from vrf0. The ipv4 function for selecting source address takes a const argument. Removing the const requires touching a lot of places, so instead l3mdev_master_ifindex_rcu is changed to take a const argument and then do the typecast to non-const as required by netdev_master_upper_dev_get_rcu. This is similar to what l3mdev_fib_table_rcu does. IPv6 for unnumbered interfaces appears to be selecting the addresses properly. Cc: David Lamparter <david@opensourcerouting.org> Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-24 19:47:02 +00:00
master_idx = l3mdev_master_ifindex_rcu(dev);
/* For VRFs, the VRF device takes the place of the loopback device,
* with addresses on it being preferred. Note in such cases the
* loopback device will be among the devices that fail the master_idx
* equality check in the loop below.
*/
if (master_idx &&
(dev = dev_get_by_index_rcu(net, master_idx)) &&
(in_dev = __in_dev_get_rcu(dev))) {
for_primary_ifa(in_dev) {
if (ifa->ifa_scope != RT_SCOPE_LINK &&
ifa->ifa_scope <= scope) {
addr = ifa->ifa_local;
goto out_unlock;
}
} endfor_ifa(in_dev);
}
/* Not loopback addresses on loopback should be preferred
in this case. It is important that lo is the first interface
in dev_base list.
*/
for_each_netdev_rcu(net, dev) {
net: l3mdev: address selection should only consider devices in L3 domain David Lamparter noted a use case where the source address selection fails to pick an address from a VRF interface - unnumbered interfaces. Relevant commands from his script: ip addr add 9.9.9.9/32 dev lo ip link set lo up ip link add name vrf0 type vrf table 101 ip rule add oif vrf0 table 101 ip rule add iif vrf0 table 101 ip link set vrf0 up ip addr add 10.0.0.3/32 dev vrf0 ip link add name dummy2 type dummy ip link set dummy2 master vrf0 up --> note dummy2 has no address - unnumbered device ip route add 10.2.2.2/32 dev dummy2 table 101 ip neigh add 10.2.2.2 dev dummy2 lladdr 02:00:00:00:00:02 tcpdump -ni dummy2 & And using ping instead of his socat example: $ ping -I vrf0 -c1 10.2.2.2 ping: Warning: source address might be selected on device other than vrf0. PING 10.2.2.2 (10.2.2.2) from 9.9.9.9 vrf0: 56(84) bytes of data. >From tcpdump: 12:57:29.449128 IP 9.9.9.9 > 10.2.2.2: ICMP echo request, id 2491, seq 1, length 64 Note the source address is from lo and is not a VRF local address. With this patch: $ ping -I vrf0 -c1 10.2.2.2 PING 10.2.2.2 (10.2.2.2) from 10.0.0.3 vrf0: 56(84) bytes of data. >From tcpdump: 12:59:25.096426 IP 10.0.0.3 > 10.2.2.2: ICMP echo request, id 2113, seq 1, length 64 Now the source address comes from vrf0. The ipv4 function for selecting source address takes a const argument. Removing the const requires touching a lot of places, so instead l3mdev_master_ifindex_rcu is changed to take a const argument and then do the typecast to non-const as required by netdev_master_upper_dev_get_rcu. This is similar to what l3mdev_fib_table_rcu does. IPv6 for unnumbered interfaces appears to be selecting the addresses properly. Cc: David Lamparter <david@opensourcerouting.org> Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-02-24 19:47:02 +00:00
if (l3mdev_master_ifindex_rcu(dev) != master_idx)
continue;
in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
continue;
for_primary_ifa(in_dev) {
if (ifa->ifa_scope != RT_SCOPE_LINK &&
ifa->ifa_scope <= scope) {
addr = ifa->ifa_local;
goto out_unlock;
}
} endfor_ifa(in_dev);
}
out_unlock:
rcu_read_unlock();
return addr;
}
EXPORT_SYMBOL(inet_select_addr);
static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst,
__be32 local, int scope)
{
int same = 0;
__be32 addr = 0;
for_ifa(in_dev) {
if (!addr &&
(local == ifa->ifa_local || !local) &&
ifa->ifa_scope <= scope) {
addr = ifa->ifa_local;
if (same)
break;
}
if (!same) {
same = (!local || inet_ifa_match(local, ifa)) &&
(!dst || inet_ifa_match(dst, ifa));
if (same && addr) {
if (local || !dst)
break;
/* Is the selected addr into dst subnet? */
if (inet_ifa_match(addr, ifa))
break;
/* No, then can we use new local src? */
if (ifa->ifa_scope <= scope) {
addr = ifa->ifa_local;
break;
}
/* search for large dst subnet for addr */
same = 0;
}
}
} endfor_ifa(in_dev);
return same ? addr : 0;
}
/*
* Confirm that local IP address exists using wildcards:
* - net: netns to check, cannot be NULL
* - in_dev: only on this interface, NULL=any interface
* - dst: only in the same subnet as dst, 0=any dst
* - local: address, 0=autoselect the local address
* - scope: maximum allowed scope value for the local address
*/
__be32 inet_confirm_addr(struct net *net, struct in_device *in_dev,
__be32 dst, __be32 local, int scope)
{
__be32 addr = 0;
struct net_device *dev;
if (in_dev)
return confirm_addr_indev(in_dev, dst, local, scope);
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
in_dev = __in_dev_get_rcu(dev);
if (in_dev) {
addr = confirm_addr_indev(in_dev, dst, local, scope);
if (addr)
break;
}
}
rcu_read_unlock();
return addr;
}
bonding: remove entries for master_ip and vlan_ip and query devices instead The following patch aimed to resolve an issue where secondary, tertiary, etc. addresses added to bond interfaces could overwrite the bond->master_ip and vlan_ip values. commit 917fbdb32f37e9a93b00bb12ee83532982982df3 Author: Henrik Saavedra Persson <henrik.e.persson@ericsson.com> Date: Wed Nov 23 23:37:15 2011 +0000 bonding: only use primary address for ARP That patch was good because it prevented bonds using ARP monitoring from sending frames with an invalid source IP address. Unfortunately, it didn't always work as expected. When using an ioctl (like ifconfig does) to set the IP address and netmask, 2 separate ioctls are actually called to set the IP and netmask if the mask chosen doesn't match the standard mask for that class of address. The first ioctl did not have a mask that matched the one in the primary address and would still cause the device address to be overwritten. The second ioctl that was called to set the mask would then detect as secondary and ignored, but the damage was already done. This was not an issue when using an application that used netlink sockets as the setting of IP and netmask came down at once. The inconsistent behavior between those two interfaces was something that needed to be resolved. While I was thinking about how I wanted to resolve this, Ralf Zeidler came with a patch that resolved this on a RHEL kernel by keeping a full shadow of the entries in dev->ifa_list for the bonding device and vlan devices in the bonding driver. I didn't like the duplication of the list as I want to see the 'bonding' struct and code shrink rather than grow, but liked the general idea. As the Subject indicates this patch drops the master_ip and vlan_ip elements from the 'bonding' and 'vlan_entry' structs, respectively. This can be done because a device's address-list is now traversed to determine the optimal source IP address for ARP requests and for checks to see if the bonding device has a particular IP address. This code could have all be contained inside the bonding driver, but it made more sense to me to EXPORT and call inet_confirm_addr since it did exactly what was needed. I tested this and a backported patch and everything works as expected. Ralf also helped with verification of the backported patch. Thanks to Ralf for all his help on this. v2: Whitespace and organizational changes based on suggestions from Jay Vosburgh and Dave Miller. v3: Fixup incorrect usage of rcu_read_unlock based on Dave Miller's suggestion. Signed-off-by: Andy Gospodarek <andy@greyhouse.net> CC: Ralf Zeidler <ralf.zeidler@nsn.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-22 16:14:29 +00:00
EXPORT_SYMBOL(inet_confirm_addr);
/*
* Device notifier
*/
int register_inetaddr_notifier(struct notifier_block *nb)
{
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 09:16:30 +00:00
return blocking_notifier_chain_register(&inetaddr_chain, nb);
}
EXPORT_SYMBOL(register_inetaddr_notifier);
int unregister_inetaddr_notifier(struct notifier_block *nb)
{
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 09:16:30 +00:00
return blocking_notifier_chain_unregister(&inetaddr_chain, nb);
}
EXPORT_SYMBOL(unregister_inetaddr_notifier);
/* Rename ifa_labels for a device name change. Make some effort to preserve
* existing alias numbering and to create unique labels if possible.
*/
static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
{
struct in_ifaddr *ifa;
int named = 0;
for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
char old[IFNAMSIZ], *dot;
memcpy(old, ifa->ifa_label, IFNAMSIZ);
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
if (named++ == 0)
goto skip;
dot = strchr(old, ':');
if (!dot) {
sprintf(old, ":%d", named);
dot = old;
}
if (strlen(dot) + strlen(dev->name) < IFNAMSIZ)
strcat(ifa->ifa_label, dot);
else
strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot);
skip:
rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
}
}
static bool inetdev_valid_mtu(unsigned int mtu)
{
return mtu >= 68;
}
static void inetdev_send_gratuitous_arp(struct net_device *dev,
struct in_device *in_dev)
{
struct in_ifaddr *ifa;
for (ifa = in_dev->ifa_list; ifa;
ifa = ifa->ifa_next) {
arp_send(ARPOP_REQUEST, ETH_P_ARP,
ifa->ifa_local, dev,
ifa->ifa_local, NULL,
dev->dev_addr, NULL);
}
}
/* Called only under RTNL semaphore */
static int inetdev_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct in_device *in_dev = __in_dev_get_rtnl(dev);
ASSERT_RTNL();
if (!in_dev) {
if (event == NETDEV_REGISTER) {
in_dev = inetdev_init(dev);
if (IS_ERR(in_dev))
return notifier_from_errno(PTR_ERR(in_dev));
if (dev->flags & IFF_LOOPBACK) {
IN_DEV_CONF_SET(in_dev, NOXFRM, 1);
IN_DEV_CONF_SET(in_dev, NOPOLICY, 1);
}
} else if (event == NETDEV_CHANGEMTU) {
/* Re-enabling IP */
if (inetdev_valid_mtu(dev->mtu))
in_dev = inetdev_init(dev);
}
goto out;
}
switch (event) {
case NETDEV_REGISTER:
pr_debug("%s: bug\n", __func__);
RCU_INIT_POINTER(dev->ip_ptr, NULL);
break;
case NETDEV_UP:
if (!inetdev_valid_mtu(dev->mtu))
break;
if (dev->flags & IFF_LOOPBACK) {
struct in_ifaddr *ifa = inet_alloc_ifa();
if (ifa) {
INIT_HLIST_NODE(&ifa->hash);
ifa->ifa_local =
ifa->ifa_address = htonl(INADDR_LOOPBACK);
ifa->ifa_prefixlen = 8;
ifa->ifa_mask = inet_make_mask(8);
in_dev_hold(in_dev);
ifa->ifa_dev = in_dev;
ifa->ifa_scope = RT_SCOPE_HOST;
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
set_ifa_lifetime(ifa, INFINITY_LIFE_TIME,
INFINITY_LIFE_TIME);
ipv4_devconf_setall(in_dev);
neigh_parms_data_state_setall(in_dev->arp_parms);
inet_insert_ifa(ifa);
}
}
ip_mc_up(in_dev);
/* fall through */
case NETDEV_CHANGEADDR:
if (!IN_DEV_ARP_NOTIFY(in_dev))
break;
/* fall through */
case NETDEV_NOTIFY_PEERS:
/* Send gratuitous ARP to notify of link change */
inetdev_send_gratuitous_arp(dev, in_dev);
break;
case NETDEV_DOWN:
ip_mc_down(in_dev);
break;
case NETDEV_PRE_TYPE_CHANGE:
ip_mc_unmap(in_dev);
break;
case NETDEV_POST_TYPE_CHANGE:
ip_mc_remap(in_dev);
break;
case NETDEV_CHANGEMTU:
if (inetdev_valid_mtu(dev->mtu))
break;
/* disable IP when MTU is not enough */
case NETDEV_UNREGISTER:
inetdev_destroy(in_dev);
break;
case NETDEV_CHANGENAME:
/* Do not notify about label change, this event is
* not interesting to applications using netlink.
*/
inetdev_changename(dev, in_dev);
devinet_sysctl_unregister(in_dev);
devinet_sysctl_register(in_dev);
break;
}
out:
return NOTIFY_DONE;
}
static struct notifier_block ip_netdev_notifier = {
.notifier_call = inetdev_event,
};
static size_t inet_nlmsg_size(void)
{
return NLMSG_ALIGN(sizeof(struct ifaddrmsg))
+ nla_total_size(4) /* IFA_ADDRESS */
+ nla_total_size(4) /* IFA_LOCAL */
+ nla_total_size(4) /* IFA_BROADCAST */
+ nla_total_size(IFNAMSIZ) /* IFA_LABEL */
ipv4: Fix runtime WARNING in rtmsg_ifa() On m68k/ARAnyM: WARNING: CPU: 0 PID: 407 at net/ipv4/devinet.c:1599 0x316a99() Modules linked in: CPU: 0 PID: 407 Comm: ifconfig Not tainted 3.13.0-atari-09263-g0c71d68014d1 #1378 Stack from 10c4fdf0: 10c4fdf0 002ffabb 000243e8 00000000 008ced6c 00024416 00316a99 0000063f 00316a99 00000009 00000000 002501b4 00316a99 0000063f c0a86117 00000080 c0a86117 00ad0c90 00250a5a 00000014 00ad0c90 00000000 00000000 00000001 00b02dd0 00356594 00000000 00356594 c0a86117 eff6c9e4 008ced6c 00000002 008ced60 0024f9b4 00250b52 00ad0c90 00000000 00000000 00252390 00ad0c90 eff6c9e4 0000004f 00000000 00000000 eff6c9e4 8000e25c eff6c9e4 80001020 Call Trace: [<000243e8>] warn_slowpath_common+0x52/0x6c [<00024416>] warn_slowpath_null+0x14/0x1a [<002501b4>] rtmsg_ifa+0xdc/0xf0 [<00250a5a>] __inet_insert_ifa+0xd6/0x1c2 [<0024f9b4>] inet_abc_len+0x0/0x42 [<00250b52>] inet_insert_ifa+0xc/0x12 [<00252390>] devinet_ioctl+0x2ae/0x5d6 Adding some debugging code reveals that net_fill_ifaddr() fails in put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp, preferred, valid)) nla_put complains: lib/nlattr.c:454: skb_tailroom(skb) = 12, nla_total_size(attrlen) = 20 Apparently commit 5c766d642bcaffd0c2a5b354db2068515b3846cf ("ipv4: introduce address lifetime") forgot to take into account the addition of struct ifa_cacheinfo in inet_nlmsg_size(). Hence add it, like is already done for ipv6. Suggested-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-05 07:38:25 +00:00
+ nla_total_size(4) /* IFA_FLAGS */
+ nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */
}
static inline u32 cstamp_delta(unsigned long cstamp)
{
return (cstamp - INITIAL_JIFFIES) * 100UL / HZ;
}
static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp,
unsigned long tstamp, u32 preferred, u32 valid)
{
struct ifa_cacheinfo ci;
ci.cstamp = cstamp_delta(cstamp);
ci.tstamp = cstamp_delta(tstamp);
ci.ifa_prefered = preferred;
ci.ifa_valid = valid;
return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci);
}
static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
u32 portid, u32 seq, int event, unsigned int flags)
{
struct ifaddrmsg *ifm;
struct nlmsghdr *nlh;
u32 preferred, valid;
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags);
if (!nlh)
return -EMSGSIZE;
ifm = nlmsg_data(nlh);
ifm->ifa_family = AF_INET;
ifm->ifa_prefixlen = ifa->ifa_prefixlen;
ifm->ifa_flags = ifa->ifa_flags;
ifm->ifa_scope = ifa->ifa_scope;
ifm->ifa_index = ifa->ifa_dev->dev->ifindex;
if (!(ifm->ifa_flags & IFA_F_PERMANENT)) {
preferred = ifa->ifa_preferred_lft;
valid = ifa->ifa_valid_lft;
if (preferred != INFINITY_LIFE_TIME) {
long tval = (jiffies - ifa->ifa_tstamp) / HZ;
if (preferred > tval)
preferred -= tval;
else
preferred = 0;
if (valid != INFINITY_LIFE_TIME) {
if (valid > tval)
valid -= tval;
else
valid = 0;
}
}
} else {
preferred = INFINITY_LIFE_TIME;
valid = INFINITY_LIFE_TIME;
}
if ((ifa->ifa_address &&
nla_put_in_addr(skb, IFA_ADDRESS, ifa->ifa_address)) ||
(ifa->ifa_local &&
nla_put_in_addr(skb, IFA_LOCAL, ifa->ifa_local)) ||
(ifa->ifa_broadcast &&
nla_put_in_addr(skb, IFA_BROADCAST, ifa->ifa_broadcast)) ||
(ifa->ifa_label[0] &&
nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) ||
nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) ||
put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp,
preferred, valid))
goto nla_put_failure;
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-16 21:09:00 +00:00
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
int h, s_h;
int idx, s_idx;
int ip_idx, s_ip_idx;
struct net_device *dev;
struct in_device *in_dev;
struct in_ifaddr *ifa;
struct hlist_head *head;
s_h = cb->args[0];
s_idx = idx = cb->args[1];
s_ip_idx = ip_idx = cb->args[2];
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &net->dev_index_head[h];
rcu_read_lock();
cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
net->dev_base_seq;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_rcu(dev, head, index_hlist) {
if (idx < s_idx)
goto cont;
if (h > s_h || idx > s_idx)
s_ip_idx = 0;
in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
goto cont;
for (ifa = in_dev->ifa_list, ip_idx = 0; ifa;
ifa = ifa->ifa_next, ip_idx++) {
if (ip_idx < s_ip_idx)
continue;
if (inet_fill_ifaddr(skb, ifa,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-16 21:09:00 +00:00
RTM_NEWADDR, NLM_F_MULTI) < 0) {
rcu_read_unlock();
goto done;
}
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
}
cont:
idx++;
}
rcu_read_unlock();
}
done:
cb->args[0] = h;
cb->args[1] = idx;
cb->args[2] = ip_idx;
return skb->len;
}
static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh,
u32 portid)
{
struct sk_buff *skb;
u32 seq = nlh ? nlh->nlmsg_seq : 0;
int err = -ENOBUFS;
struct net *net;
net = dev_net(ifa->ifa_dev->dev);
skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL);
if (!skb)
goto errout;
err = inet_fill_ifaddr(skb, ifa, portid, seq, event, 0);
if (err < 0) {
/* -EMSGSIZE implies BUG in inet_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL);
2009-02-25 07:18:28 +00:00
return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err);
}
static size_t inet_get_link_af_size(const struct net_device *dev,
u32 ext_filter_mask)
{
struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr);
if (!in_dev)
return 0;
return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */
}
static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev,
u32 ext_filter_mask)
{
struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr);
struct nlattr *nla;
int i;
if (!in_dev)
return -ENODATA;
nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4);
if (!nla)
return -EMSGSIZE;
for (i = 0; i < IPV4_DEVCONF_MAX; i++)
((u32 *) nla_data(nla))[i] = in_dev->cnf.data[i];
return 0;
}
static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = {
[IFLA_INET_CONF] = { .type = NLA_NESTED },
};
static int inet_validate_link_af(const struct net_device *dev,
const struct nlattr *nla)
{
struct nlattr *a, *tb[IFLA_INET_MAX+1];
int err, rem;
if (dev && !__in_dev_get_rtnl(dev))
return -EAFNOSUPPORT;
err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy);
if (err < 0)
return err;
if (tb[IFLA_INET_CONF]) {
nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) {
int cfgid = nla_type(a);
if (nla_len(a) < 4)
return -EINVAL;
if (cfgid <= 0 || cfgid > IPV4_DEVCONF_MAX)
return -EINVAL;
}
}
return 0;
}
static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla)
{
struct in_device *in_dev = __in_dev_get_rtnl(dev);
struct nlattr *a, *tb[IFLA_INET_MAX+1];
int rem;
if (!in_dev)
return -EAFNOSUPPORT;
if (nla_parse_nested(tb, IFLA_INET_MAX, nla, NULL) < 0)
BUG();
if (tb[IFLA_INET_CONF]) {
nla_for_each_nested(a, tb[IFLA_INET_CONF], rem)
ipv4_devconf_set(in_dev, nla_type(a), nla_get_u32(a));
}
return 0;
}
static int inet_netconf_msgsize_devconf(int type)
{
int size = NLMSG_ALIGN(sizeof(struct netconfmsg))
+ nla_total_size(4); /* NETCONFA_IFINDEX */
bool all = false;
if (type == NETCONFA_ALL)
all = true;
if (all || type == NETCONFA_FORWARDING)
size += nla_total_size(4);
if (all || type == NETCONFA_RP_FILTER)
size += nla_total_size(4);
if (all || type == NETCONFA_MC_FORWARDING)
size += nla_total_size(4);
if (all || type == NETCONFA_PROXY_NEIGH)
size += nla_total_size(4);
if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN)
size += nla_total_size(4);
return size;
}
static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
struct ipv4_devconf *devconf, u32 portid,
u32 seq, int event, unsigned int flags,
int type)
{
struct nlmsghdr *nlh;
struct netconfmsg *ncm;
bool all = false;
nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg),
flags);
if (!nlh)
return -EMSGSIZE;
if (type == NETCONFA_ALL)
all = true;
ncm = nlmsg_data(nlh);
ncm->ncm_family = AF_INET;
if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0)
goto nla_put_failure;
if ((all || type == NETCONFA_FORWARDING) &&
nla_put_s32(skb, NETCONFA_FORWARDING,
IPV4_DEVCONF(*devconf, FORWARDING)) < 0)
goto nla_put_failure;
if ((all || type == NETCONFA_RP_FILTER) &&
nla_put_s32(skb, NETCONFA_RP_FILTER,
IPV4_DEVCONF(*devconf, RP_FILTER)) < 0)
goto nla_put_failure;
if ((all || type == NETCONFA_MC_FORWARDING) &&
nla_put_s32(skb, NETCONFA_MC_FORWARDING,
IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0)
goto nla_put_failure;
if ((all || type == NETCONFA_PROXY_NEIGH) &&
nla_put_s32(skb, NETCONFA_PROXY_NEIGH,
IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0)
goto nla_put_failure;
if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) &&
nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0)
goto nla_put_failure;
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-16 21:09:00 +00:00
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
void inet_netconf_notify_devconf(struct net *net, int type, int ifindex,
struct ipv4_devconf *devconf)
{
struct sk_buff *skb;
int err = -ENOBUFS;
skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_ATOMIC);
if (!skb)
goto errout;
err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0,
RTM_NEWNETCONF, 0, type);
if (err < 0) {
/* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_ATOMIC);
return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err);
}
static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
[NETCONFA_IFINDEX] = { .len = sizeof(int) },
[NETCONFA_FORWARDING] = { .len = sizeof(int) },
[NETCONFA_RP_FILTER] = { .len = sizeof(int) },
[NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) },
[NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) },
};
static int inet_netconf_get_devconf(struct sk_buff *in_skb,
struct nlmsghdr *nlh)
{
struct net *net = sock_net(in_skb->sk);
struct nlattr *tb[NETCONFA_MAX+1];
struct netconfmsg *ncm;
struct sk_buff *skb;
struct ipv4_devconf *devconf;
struct in_device *in_dev;
struct net_device *dev;
int ifindex;
int err;
err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX,
devconf_ipv4_policy);
if (err < 0)
goto errout;
err = -EINVAL;
if (!tb[NETCONFA_IFINDEX])
goto errout;
ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]);
switch (ifindex) {
case NETCONFA_IFINDEX_ALL:
devconf = net->ipv4.devconf_all;
break;
case NETCONFA_IFINDEX_DEFAULT:
devconf = net->ipv4.devconf_dflt;
break;
default:
dev = __dev_get_by_index(net, ifindex);
if (!dev)
goto errout;
in_dev = __in_dev_get_rtnl(dev);
if (!in_dev)
goto errout;
devconf = &in_dev->cnf;
break;
}
err = -ENOBUFS;
skb = nlmsg_new(inet_netconf_msgsize_devconf(NETCONFA_ALL), GFP_ATOMIC);
if (!skb)
goto errout;
err = inet_netconf_fill_devconf(skb, ifindex, devconf,
NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, RTM_NEWNETCONF, 0,
NETCONFA_ALL);
if (err < 0) {
/* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
errout:
return err;
}
static int inet_netconf_dump_devconf(struct sk_buff *skb,
struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
int h, s_h;
int idx, s_idx;
struct net_device *dev;
struct in_device *in_dev;
struct hlist_head *head;
s_h = cb->args[0];
s_idx = idx = cb->args[1];
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &net->dev_index_head[h];
rcu_read_lock();
cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^
net->dev_base_seq;
hlist_for_each_entry_rcu(dev, head, index_hlist) {
if (idx < s_idx)
goto cont;
in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
goto cont;
if (inet_netconf_fill_devconf(skb, dev->ifindex,
&in_dev->cnf,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
RTM_NEWNETCONF,
NLM_F_MULTI,
NETCONFA_ALL) < 0) {
rcu_read_unlock();
goto done;
}
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
idx++;
}
rcu_read_unlock();
}
if (h == NETDEV_HASHENTRIES) {
if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL,
net->ipv4.devconf_all,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
RTM_NEWNETCONF, NLM_F_MULTI,
NETCONFA_ALL) < 0)
goto done;
else
h++;
}
if (h == NETDEV_HASHENTRIES + 1) {
if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT,
net->ipv4.devconf_dflt,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
RTM_NEWNETCONF, NLM_F_MULTI,
NETCONFA_ALL) < 0)
goto done;
else
h++;
}
done:
cb->args[0] = h;
cb->args[1] = idx;
return skb->len;
}
#ifdef CONFIG_SYSCTL
static void devinet_copy_dflt_conf(struct net *net, int i)
{
struct net_device *dev;
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
struct in_device *in_dev;
in_dev = __in_dev_get_rcu(dev);
if (in_dev && !test_bit(i, in_dev->cnf.state))
in_dev->cnf.data[i] = net->ipv4.devconf_dflt->data[i];
}
rcu_read_unlock();
}
/* called with RTNL locked */
static void inet_forward_change(struct net *net)
{
struct net_device *dev;
int on = IPV4_DEVCONF_ALL(net, FORWARDING);
IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on;
IPV4_DEVCONF_DFLT(net, FORWARDING) = on;
inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
NETCONFA_IFINDEX_ALL,
net->ipv4.devconf_all);
inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
NETCONFA_IFINDEX_DEFAULT,
net->ipv4.devconf_dflt);
for_each_netdev(net, dev) {
struct in_device *in_dev;
if (on)
dev_disable_lro(dev);
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
if (in_dev) {
IN_DEV_CONF_SET(in_dev, FORWARDING, on);
inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
dev->ifindex, &in_dev->cnf);
}
rcu_read_unlock();
}
}
static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf)
{
if (cnf == net->ipv4.devconf_dflt)
return NETCONFA_IFINDEX_DEFAULT;
else if (cnf == net->ipv4.devconf_all)
return NETCONFA_IFINDEX_ALL;
else {
struct in_device *idev
= container_of(cnf, struct in_device, cnf);
return idev->dev->ifindex;
}
}
static int devinet_conf_proc(struct ctl_table *ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
int old_value = *(int *)ctl->data;
int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
int new_value = *(int *)ctl->data;
if (write) {
struct ipv4_devconf *cnf = ctl->extra1;
struct net *net = ctl->extra2;
int i = (int *)ctl->data - cnf->data;
int ifindex;
set_bit(i, cnf->state);
if (cnf == net->ipv4.devconf_dflt)
devinet_copy_dflt_conf(net, i);
if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 ||
i == IPV4_DEVCONF_ROUTE_LOCALNET - 1)
if ((new_value == 0) && (old_value != 0))
rt_cache_flush(net);
if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
new_value != old_value) {
ifindex = devinet_conf_ifindex(net, cnf);
inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER,
ifindex, cnf);
}
if (i == IPV4_DEVCONF_PROXY_ARP - 1 &&
new_value != old_value) {
ifindex = devinet_conf_ifindex(net, cnf);
inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
ifindex, cnf);
}
if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 &&
new_value != old_value) {
ifindex = devinet_conf_ifindex(net, cnf);
inet_netconf_notify_devconf(net, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
ifindex, cnf);
}
}
return ret;
}
static int devinet_sysctl_forward(struct ctl_table *ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
int *valp = ctl->data;
int val = *valp;
loff_t pos = *ppos;
int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
if (write && *valp != val) {
struct net *net = ctl->extra2;
if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) {
if (!rtnl_trylock()) {
/* Restore the original values before restarting */
*valp = val;
*ppos = pos;
return restart_syscall();
}
if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) {
inet_forward_change(net);
} else {
struct ipv4_devconf *cnf = ctl->extra1;
struct in_device *idev =
container_of(cnf, struct in_device, cnf);
if (*valp)
dev_disable_lro(idev->dev);
inet_netconf_notify_devconf(net,
NETCONFA_FORWARDING,
idev->dev->ifindex,
cnf);
}
rtnl_unlock();
rt_cache_flush(net);
} else
inet_netconf_notify_devconf(net, NETCONFA_FORWARDING,
NETCONFA_IFINDEX_DEFAULT,
net->ipv4.devconf_dflt);
}
return ret;
}
static int ipv4_doint_and_flush(struct ctl_table *ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
int *valp = ctl->data;
int val = *valp;
int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
struct net *net = ctl->extra2;
if (write && *valp != val)
rt_cache_flush(net);
return ret;
}
#define DEVINET_SYSCTL_ENTRY(attr, name, mval, proc) \
{ \
.procname = name, \
.data = ipv4_devconf.data + \
IPV4_DEVCONF_ ## attr - 1, \
.maxlen = sizeof(int), \
.mode = mval, \
.proc_handler = proc, \
.extra1 = &ipv4_devconf, \
}
#define DEVINET_SYSCTL_RW_ENTRY(attr, name) \
DEVINET_SYSCTL_ENTRY(attr, name, 0644, devinet_conf_proc)
#define DEVINET_SYSCTL_RO_ENTRY(attr, name) \
DEVINET_SYSCTL_ENTRY(attr, name, 0444, devinet_conf_proc)
#define DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, proc) \
DEVINET_SYSCTL_ENTRY(attr, name, 0644, proc)
#define DEVINET_SYSCTL_FLUSHING_ENTRY(attr, name) \
DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, ipv4_doint_and_flush)
static struct devinet_sysctl_table {
struct ctl_table_header *sysctl_header;
struct ctl_table devinet_vars[__IPV4_DEVCONF_MAX];
} devinet_sysctl = {
.devinet_vars = {
DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding",
devinet_sysctl_forward),
DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"),
DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"),
DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"),
DEVINET_SYSCTL_RW_ENTRY(SHARED_MEDIA, "shared_media"),
DEVINET_SYSCTL_RW_ENTRY(RP_FILTER, "rp_filter"),
DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"),
DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE,
"accept_source_route"),
DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"),
DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"),
DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"),
DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"),
DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"),
DEVINET_SYSCTL_RW_ENTRY(LOG_MARTIANS, "log_martians"),
DEVINET_SYSCTL_RW_ENTRY(TAG, "tag"),
DEVINET_SYSCTL_RW_ENTRY(ARPFILTER, "arp_filter"),
DEVINET_SYSCTL_RW_ENTRY(ARP_ANNOUNCE, "arp_announce"),
DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"),
DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"),
DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"),
DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"),
DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION,
"force_igmp_version"),
net: igmp: Allow user-space configuration of igmp unsolicited report interval Adds the new procfs knobs: /proc/sys/net/ipv4/conf/*/igmpv2_unsolicited_report_interval /proc/sys/net/ipv4/conf/*/igmpv3_unsolicited_report_interval Which will allow userspace configuration of the IGMP unsolicited report interval (see below) in milliseconds. The defaults are 10000ms for IGMPv2 and 1000ms for IGMPv3 in accordance with RFC2236 and RFC3376. Background: If an IGMP join packet is lost you will not receive data sent to the multicast group so if no data arrives from that multicast group in a period of time after the IGMP join a second IGMP join will be sent. The delay between joins is the "IGMP Unsolicited Report Interval". Prior to this patch this value was hard coded in the kernel to 10s for IGMPv2 and 1s for IGMPv3. 10s is unsuitable for some use-cases, such as IPTV as it can cause channel change to be slow in the presence of packet loss. This patch allows the value to be overridden from userspace for both IGMPv2 and IGMPv3 such that it can be tuned accoding to the network. Tested with Wireshark and a simple program to join a (non-existent) multicast group. The distribution of timings for the second join differ based upon setting the procfs knobs. igmpvX_unsolicited_report_interval is intended to follow the pattern established by force_igmp_version, and while a procfs entry has been added a corresponding sysctl knob has not as it is my understanding that sysctl is deprecated[1]. [1]: http://lwn.net/Articles/247243/ Signed-off-by: William Manley <william.manley@youview.com> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Benjamin LaHaise <bcrl@kvack.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-06 18:03:15 +00:00
DEVINET_SYSCTL_RW_ENTRY(IGMPV2_UNSOLICITED_REPORT_INTERVAL,
"igmpv2_unsolicited_report_interval"),
DEVINET_SYSCTL_RW_ENTRY(IGMPV3_UNSOLICITED_REPORT_INTERVAL,
"igmpv3_unsolicited_report_interval"),
net: ipv4 sysctl option to ignore routes when nexthop link is down This feature is only enabled with the new per-interface or ipv4 global sysctls called 'ignore_routes_with_linkdown'. net.ipv4.conf.all.ignore_routes_with_linkdown = 0 net.ipv4.conf.default.ignore_routes_with_linkdown = 0 net.ipv4.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, will report to userspace that a route is dead and will no longer resolve to this nexthop when performing a fib lookup. This will signal to userspace that the route will not be selected. The signalling of a RTNH_F_DEAD is only passed to userspace if the sysctl is enabled and link is down. This was done as without it the netlink listeners would have no idea whether or not a nexthop would be selected. The kernel only sets RTNH_F_DEAD internally if the interface has IFF_UP cleared. With the new sysctl set, the following behavior can be observed (interface p8p1 is link-down): default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 dead linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 dead linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 90.0.0.1 via 70.0.0.2 dev p7p1 src 70.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 via 10.0.5.2 dev p9p1 src 10.0.5.15 cache While the route does remain in the table (so it can be modified if needed rather than being wiped away as it would be if IFF_UP was cleared), the proper next-hop is chosen automatically when the link is down. Now interface p8p1 is linked-up: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 192.168.56.0/24 dev p2p1 proto kernel scope link src 192.168.56.2 90.0.0.1 via 80.0.0.2 dev p8p1 src 80.0.0.1 cache local 80.0.0.1 dev lo src 80.0.0.1 cache <local> 80.0.0.2 dev p8p1 src 80.0.0.1 cache and the output changes to what one would expect. If the sysctl is not set, the following output would be expected when p8p1 is down: default via 10.0.5.2 dev p9p1 10.0.5.0/24 dev p9p1 proto kernel scope link src 10.0.5.15 70.0.0.0/24 dev p7p1 proto kernel scope link src 70.0.0.1 80.0.0.0/24 dev p8p1 proto kernel scope link src 80.0.0.1 linkdown 90.0.0.0/24 via 80.0.0.2 dev p8p1 metric 1 linkdown 90.0.0.0/24 via 70.0.0.2 dev p7p1 metric 2 Since the dead flag does not appear, there should be no expectation that the kernel would skip using this route due to link being down. v2: Split kernel changes into 2 patches, this actually makes a behavioral change if the sysctl is set. Also took suggestion from Alex to simplify code by only checking sysctl during fib lookup and suggestion from Scott to add a per-interface sysctl. v3: Code clean-ups to make it more readable and efficient as well as a reverse path check fix. v4: Drop binary sysctl v5: Whitespace fixups from Dave v6: Style changes from Dave and checkpatch suggestions v7: One more checkpatch fixup Signed-off-by: Andy Gospodarek <gospo@cumulusnetworks.com> Signed-off-by: Dinesh Dutt <ddutt@cumulusnetworks.com> Acked-by: Scott Feldman <sfeldma@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-23 17:45:37 +00:00
DEVINET_SYSCTL_RW_ENTRY(IGNORE_ROUTES_WITH_LINKDOWN,
"ignore_routes_with_linkdown"),
DEVINET_SYSCTL_RW_ENTRY(DROP_GRATUITOUS_ARP,
"drop_gratuitous_arp"),
DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"),
DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"),
DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES,
"promote_secondaries"),
DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET,
"route_localnet"),
DEVINET_SYSCTL_FLUSHING_ENTRY(DROP_UNICAST_IN_L2_MULTICAST,
"drop_unicast_in_l2_multicast"),
},
};
static int __devinet_sysctl_register(struct net *net, char *dev_name,
struct ipv4_devconf *p)
{
int i;
struct devinet_sysctl_table *t;
char path[sizeof("net/ipv4/conf/") + IFNAMSIZ];
t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL);
if (!t)
goto out;
for (i = 0; i < ARRAY_SIZE(t->devinet_vars) - 1; i++) {
t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf;
t->devinet_vars[i].extra1 = p;
t->devinet_vars[i].extra2 = net;
}
snprintf(path, sizeof(path), "net/ipv4/conf/%s", dev_name);
t->sysctl_header = register_net_sysctl(net, path, t->devinet_vars);
if (!t->sysctl_header)
goto free;
p->sysctl = t;
return 0;
free:
kfree(t);
out:
return -ENOBUFS;
}
static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf)
{
struct devinet_sysctl_table *t = cnf->sysctl;
if (!t)
return;
cnf->sysctl = NULL;
unregister_net_sysctl_table(t->sysctl_header);
kfree(t);
}
static int devinet_sysctl_register(struct in_device *idev)
{
int err;
if (!sysctl_dev_name_is_allowed(idev->dev->name))
return -EINVAL;
err = neigh_sysctl_register(idev->dev, idev->arp_parms, NULL);
if (err)
return err;
err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name,
&idev->cnf);
if (err)
neigh_sysctl_unregister(idev->arp_parms);
return err;
}
static void devinet_sysctl_unregister(struct in_device *idev)
{
__devinet_sysctl_unregister(&idev->cnf);
neigh_sysctl_unregister(idev->arp_parms);
}
static struct ctl_table ctl_forward_entry[] = {
{
.procname = "ip_forward",
.data = &ipv4_devconf.data[
IPV4_DEVCONF_FORWARDING - 1],
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = devinet_sysctl_forward,
.extra1 = &ipv4_devconf,
.extra2 = &init_net,
},
{ },
};
#endif
static __net_init int devinet_init_net(struct net *net)
{
int err;
struct ipv4_devconf *all, *dflt;
#ifdef CONFIG_SYSCTL
struct ctl_table *tbl = ctl_forward_entry;
struct ctl_table_header *forw_hdr;
#endif
err = -ENOMEM;
all = &ipv4_devconf;
dflt = &ipv4_devconf_dflt;
if (!net_eq(net, &init_net)) {
all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL);
if (!all)
goto err_alloc_all;
dflt = kmemdup(dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL);
if (!dflt)
goto err_alloc_dflt;
#ifdef CONFIG_SYSCTL
tbl = kmemdup(tbl, sizeof(ctl_forward_entry), GFP_KERNEL);
if (!tbl)
goto err_alloc_ctl;
tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1];
tbl[0].extra1 = all;
tbl[0].extra2 = net;
#endif
}
#ifdef CONFIG_SYSCTL
err = __devinet_sysctl_register(net, "all", all);
if (err < 0)
goto err_reg_all;
err = __devinet_sysctl_register(net, "default", dflt);
if (err < 0)
goto err_reg_dflt;
err = -ENOMEM;
forw_hdr = register_net_sysctl(net, "net/ipv4", tbl);
if (!forw_hdr)
goto err_reg_ctl;
net->ipv4.forw_hdr = forw_hdr;
#endif
net->ipv4.devconf_all = all;
net->ipv4.devconf_dflt = dflt;
return 0;
#ifdef CONFIG_SYSCTL
err_reg_ctl:
__devinet_sysctl_unregister(dflt);
err_reg_dflt:
__devinet_sysctl_unregister(all);
err_reg_all:
if (tbl != ctl_forward_entry)
kfree(tbl);
err_alloc_ctl:
#endif
if (dflt != &ipv4_devconf_dflt)
kfree(dflt);
err_alloc_dflt:
if (all != &ipv4_devconf)
kfree(all);
err_alloc_all:
return err;
}
static __net_exit void devinet_exit_net(struct net *net)
{
#ifdef CONFIG_SYSCTL
struct ctl_table *tbl;
tbl = net->ipv4.forw_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv4.forw_hdr);
__devinet_sysctl_unregister(net->ipv4.devconf_dflt);
__devinet_sysctl_unregister(net->ipv4.devconf_all);
kfree(tbl);
#endif
kfree(net->ipv4.devconf_dflt);
kfree(net->ipv4.devconf_all);
}
static __net_initdata struct pernet_operations devinet_ops = {
.init = devinet_init_net,
.exit = devinet_exit_net,
};
static struct rtnl_af_ops inet_af_ops __read_mostly = {
.family = AF_INET,
.fill_link_af = inet_fill_link_af,
.get_link_af_size = inet_get_link_af_size,
.validate_link_af = inet_validate_link_af,
.set_link_af = inet_set_link_af,
};
void __init devinet_init(void)
{
int i;
for (i = 0; i < IN4_ADDR_HSIZE; i++)
INIT_HLIST_HEAD(&inet_addr_lst[i]);
register_pernet_subsys(&devinet_ops);
register_gifconf(PF_INET, inet_gifconf);
register_netdevice_notifier(&ip_netdev_notifier);
queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0);
rtnl_af_register(&inet_af_ops);
rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL);
rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL);
rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL);
rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf,
inet_netconf_dump_devconf, NULL);
}