linux/net/bridge/br_fdb.c

1146 lines
27 KiB
C
Raw Normal View History

/*
* Forwarding database
* Linux ethernet bridge
*
* Authors:
* Lennert Buytenhek <buytenh@gnu.org>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/rculist.h>
#include <linux/spinlock.h>
#include <linux/times.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/jhash.h>
#include <linux/random.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/atomic.h>
#include <asm/unaligned.h>
#include <linux/if_vlan.h>
#include <net/switchdev.h>
#include "br_private.h"
static struct kmem_cache *br_fdb_cache __read_mostly;
static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr, u16 vid);
static void fdb_notify(struct net_bridge *br,
const struct net_bridge_fdb_entry *, int);
static u32 fdb_salt __read_mostly;
int __init br_fdb_init(void)
{
br_fdb_cache = kmem_cache_create("bridge_fdb_cache",
sizeof(struct net_bridge_fdb_entry),
0,
SLAB_HWCACHE_ALIGN, NULL);
if (!br_fdb_cache)
return -ENOMEM;
get_random_bytes(&fdb_salt, sizeof(fdb_salt));
return 0;
}
void br_fdb_fini(void)
{
kmem_cache_destroy(br_fdb_cache);
}
/* if topology_changing then use forward_delay (default 15 sec)
* otherwise keep longer (default 5 minutes)
*/
static inline unsigned long hold_time(const struct net_bridge *br)
{
return br->topology_change ? br->forward_delay : br->ageing_time;
}
static inline int has_expired(const struct net_bridge *br,
const struct net_bridge_fdb_entry *fdb)
{
return !fdb->is_static && !fdb->added_by_external_learn &&
time_before_eq(fdb->updated + hold_time(br), jiffies);
}
static inline int br_mac_hash(const unsigned char *mac, __u16 vid)
{
/* use 1 byte of OUI and 3 bytes of NIC */
u32 key = get_unaligned((u32 *)(mac + 2));
return jhash_2words(key, vid, fdb_salt) & (BR_HASH_SIZE - 1);
}
static void fdb_rcu_free(struct rcu_head *head)
{
struct net_bridge_fdb_entry *ent
= container_of(head, struct net_bridge_fdb_entry, rcu);
kmem_cache_free(br_fdb_cache, ent);
}
static struct net_bridge_fdb_entry *fdb_find_rcu(struct hlist_head *head,
const unsigned char *addr,
__u16 vid)
{
struct net_bridge_fdb_entry *f;
WARN_ON_ONCE(!rcu_read_lock_held());
hlist_for_each_entry_rcu(f, head, hlist)
if (ether_addr_equal(f->addr.addr, addr) && f->vlan_id == vid)
break;
return f;
}
/* requires bridge hash_lock */
static struct net_bridge_fdb_entry *br_fdb_find(struct net_bridge *br,
const unsigned char *addr,
__u16 vid)
{
struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
struct net_bridge_fdb_entry *fdb;
lockdep_assert_held_once(&br->hash_lock);
rcu_read_lock();
fdb = fdb_find_rcu(head, addr, vid);
rcu_read_unlock();
return fdb;
}
struct net_bridge_fdb_entry *br_fdb_find_rcu(struct net_bridge *br,
const unsigned char *addr,
__u16 vid)
{
struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
return fdb_find_rcu(head, addr, vid);
}
/* When a static FDB entry is added, the mac address from the entry is
* added to the bridge private HW address list and all required ports
* are then updated with the new information.
* Called under RTNL.
*/
static void fdb_add_hw_addr(struct net_bridge *br, const unsigned char *addr)
{
int err;
struct net_bridge_port *p;
ASSERT_RTNL();
list_for_each_entry(p, &br->port_list, list) {
if (!br_promisc_port(p)) {
err = dev_uc_add(p->dev, addr);
if (err)
goto undo;
}
}
return;
undo:
list_for_each_entry_continue_reverse(p, &br->port_list, list) {
if (!br_promisc_port(p))
dev_uc_del(p->dev, addr);
}
}
/* When a static FDB entry is deleted, the HW address from that entry is
* also removed from the bridge private HW address list and updates all
* the ports with needed information.
* Called under RTNL.
*/
static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr)
{
struct net_bridge_port *p;
ASSERT_RTNL();
list_for_each_entry(p, &br->port_list, list) {
if (!br_promisc_port(p))
dev_uc_del(p->dev, addr);
}
}
static void fdb_del_external_learn(struct net_bridge_fdb_entry *f)
{
struct switchdev_obj_port_fdb fdb = {
.obj = {
.orig_dev = f->dst->dev,
.id = SWITCHDEV_OBJ_ID_PORT_FDB,
.flags = SWITCHDEV_F_DEFER,
},
.vid = f->vlan_id,
};
ether_addr_copy(fdb.addr, f->addr.addr);
switchdev_port_obj_del(f->dst->dev, &fdb.obj);
}
static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f)
{
if (f->is_static)
fdb_del_hw_addr(br, f->addr.addr);
if (f->added_by_external_learn)
fdb_del_external_learn(f);
hlist_del_init_rcu(&f->hlist);
fdb_notify(br, f, RTM_DELNEIGH);
call_rcu(&f->rcu, fdb_rcu_free);
}
/* Delete a local entry if no other port had the same address. */
static void fdb_delete_local(struct net_bridge *br,
const struct net_bridge_port *p,
struct net_bridge_fdb_entry *f)
{
const unsigned char *addr = f->addr.addr;
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan_group *vg;
const struct net_bridge_vlan *v;
struct net_bridge_port *op;
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
u16 vid = f->vlan_id;
/* Maybe another port has same hw addr? */
list_for_each_entry(op, &br->port_list, list) {
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
vg = nbp_vlan_group(op);
if (op != p && ether_addr_equal(op->dev->dev_addr, addr) &&
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
(!vid || br_vlan_find(vg, vid))) {
f->dst = op;
f->added_by_user = 0;
return;
}
}
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
vg = br_vlan_group(br);
v = br_vlan_find(vg, vid);
/* Maybe bridge device has same hw addr? */
if (p && ether_addr_equal(br->dev->dev_addr, addr) &&
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
(!vid || (v && br_vlan_should_use(v)))) {
f->dst = NULL;
f->added_by_user = 0;
return;
}
fdb_delete(br, f);
}
void br_fdb_find_delete_local(struct net_bridge *br,
const struct net_bridge_port *p,
const unsigned char *addr, u16 vid)
{
struct net_bridge_fdb_entry *f;
spin_lock_bh(&br->hash_lock);
f = br_fdb_find(br, addr, vid);
if (f && f->is_local && !f->added_by_user && f->dst == p)
fdb_delete_local(br, p, f);
spin_unlock_bh(&br->hash_lock);
}
void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
{
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan_group *vg;
struct net_bridge *br = p->br;
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan *v;
int i;
spin_lock_bh(&br->hash_lock);
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
vg = nbp_vlan_group(p);
/* Search all chains since old address/hash is unknown */
for (i = 0; i < BR_HASH_SIZE; i++) {
struct hlist_node *h;
hlist_for_each(h, &br->hash[i]) {
struct net_bridge_fdb_entry *f;
f = hlist_entry(h, struct net_bridge_fdb_entry, hlist);
if (f->dst == p && f->is_local && !f->added_by_user) {
/* delete old one */
fdb_delete_local(br, p, f);
/* if this port has no vlan information
* configured, we can safely be done at
* this point.
*/
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
if (!vg || !vg->num_vlans)
goto insert;
}
}
}
insert:
/* insert new address, may fail if invalid address or dup. */
fdb_insert(br, p, newaddr, 0);
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
if (!vg || !vg->num_vlans)
goto done;
/* Now add entries for every VLAN configured on the port.
* This function runs under RTNL so the bitmap will not change
* from under us.
*/
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
list_for_each_entry(v, &vg->vlan_list, vlist)
fdb_insert(br, p, newaddr, v->vid);
done:
spin_unlock_bh(&br->hash_lock);
}
void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
{
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan_group *vg;
struct net_bridge_fdb_entry *f;
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan *v;
spin_lock_bh(&br->hash_lock);
/* If old entry was unassociated with any port, then delete it. */
f = br_fdb_find(br, br->dev->dev_addr, 0);
if (f && f->is_local && !f->dst && !f->added_by_user)
fdb_delete_local(br, NULL, f);
fdb_insert(br, NULL, newaddr, 0);
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
vg = br_vlan_group(br);
if (!vg || !vg->num_vlans)
goto out;
/* Now remove and add entries for every VLAN configured on the
* bridge. This function runs under RTNL so the bitmap will not
* change from under us.
*/
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
list_for_each_entry(v, &vg->vlan_list, vlist) {
if (!br_vlan_should_use(v))
continue;
f = br_fdb_find(br, br->dev->dev_addr, v->vid);
if (f && f->is_local && !f->dst && !f->added_by_user)
fdb_delete_local(br, NULL, f);
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
fdb_insert(br, NULL, newaddr, v->vid);
}
out:
spin_unlock_bh(&br->hash_lock);
}
void br_fdb_cleanup(struct work_struct *work)
{
struct net_bridge *br = container_of(work, struct net_bridge,
gc_work.work);
unsigned long delay = hold_time(br);
unsigned long work_delay = delay;
unsigned long now = jiffies;
int i;
for (i = 0; i < BR_HASH_SIZE; i++) {
struct net_bridge_fdb_entry *f;
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
struct hlist_node *n;
if (!br->hash[i].first)
continue;
spin_lock_bh(&br->hash_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_safe(f, n, &br->hash[i], hlist) {
unsigned long this_timer;
if (f->is_static)
continue;
if (f->added_by_external_learn)
continue;
this_timer = f->updated + delay;
if (time_after(this_timer, now))
work_delay = min(work_delay, this_timer - now);
else
fdb_delete(br, f);
}
spin_unlock_bh(&br->hash_lock);
cond_resched();
}
/* Cleanup minimum 10 milliseconds apart */
work_delay = max_t(unsigned long, work_delay, msecs_to_jiffies(10));
mod_delayed_work(system_long_wq, &br->gc_work, work_delay);
}
/* Completely flush all dynamic entries in forwarding database.*/
void br_fdb_flush(struct net_bridge *br)
{
int i;
spin_lock_bh(&br->hash_lock);
for (i = 0; i < BR_HASH_SIZE; i++) {
struct net_bridge_fdb_entry *f;
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
struct hlist_node *n;
hlist_for_each_entry_safe(f, n, &br->hash[i], hlist) {
if (!f->is_static)
fdb_delete(br, f);
}
}
spin_unlock_bh(&br->hash_lock);
}
/* Flush all entries referring to a specific port.
* if do_all is set also flush static entries
* if vid is set delete all entries that match the vlan_id
*/
void br_fdb_delete_by_port(struct net_bridge *br,
const struct net_bridge_port *p,
u16 vid,
int do_all)
{
int i;
spin_lock_bh(&br->hash_lock);
for (i = 0; i < BR_HASH_SIZE; i++) {
struct hlist_node *h, *g;
hlist_for_each_safe(h, g, &br->hash[i]) {
struct net_bridge_fdb_entry *f
= hlist_entry(h, struct net_bridge_fdb_entry, hlist);
if (f->dst != p)
continue;
if (!do_all)
if (f->is_static || (vid && f->vlan_id != vid))
continue;
if (f->is_local)
fdb_delete_local(br, p, f);
else
fdb_delete(br, f);
}
}
spin_unlock_bh(&br->hash_lock);
}
#if IS_ENABLED(CONFIG_ATM_LANE)
/* Interface used by ATM LANE hook to test
* if an addr is on some other bridge port */
int br_fdb_test_addr(struct net_device *dev, unsigned char *addr)
{
struct net_bridge_fdb_entry *fdb;
struct net_bridge_port *port;
int ret;
rcu_read_lock();
port = br_port_get_rcu(dev);
if (!port)
ret = 0;
else {
fdb = br_fdb_find_rcu(port->br, addr, 0);
ret = fdb && fdb->dst && fdb->dst->dev != dev &&
fdb->dst->state == BR_STATE_FORWARDING;
}
rcu_read_unlock();
return ret;
}
#endif /* CONFIG_ATM_LANE */
/*
* Fill buffer with forwarding table records in
* the API format.
*/
int br_fdb_fillbuf(struct net_bridge *br, void *buf,
unsigned long maxnum, unsigned long skip)
{
struct __fdb_entry *fe = buf;
int i, num = 0;
struct net_bridge_fdb_entry *f;
memset(buf, 0, maxnum*sizeof(struct __fdb_entry));
rcu_read_lock();
for (i = 0; i < BR_HASH_SIZE; i++) {
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(f, &br->hash[i], hlist) {
if (num >= maxnum)
goto out;
if (has_expired(br, f))
continue;
/* ignore pseudo entry for local MAC address */
if (!f->dst)
continue;
if (skip) {
--skip;
continue;
}
/* convert from internal format to API */
memcpy(fe->mac_addr, f->addr.addr, ETH_ALEN);
/* due to ABI compat need to split into hi/lo */
fe->port_no = f->dst->port_no;
fe->port_hi = f->dst->port_no >> 8;
fe->is_local = f->is_local;
if (!f->is_static)
fe->ageing_timer_value = jiffies_delta_to_clock_t(jiffies - f->updated);
++fe;
++num;
}
}
out:
rcu_read_unlock();
return num;
}
static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head,
struct net_bridge_port *source,
const unsigned char *addr,
bridge: set is_local and is_static before fdb entry is added to the fdb hashtable Problem Description: We can add fdbs pointing to the bridge with NULL ->dst but that has a few race conditions because br_fdb_insert() is used which first creates the fdb and then, after the fdb has been published/linked, sets "is_local" to 1 and in that time frame if a packet arrives for that fdb it may see it as non-local and either do a NULL ptr dereference in br_forward() or attach the fdb to the port where it arrived, and later br_fdb_insert() will make it local thus getting a wrong fdb entry. Call chain br_handle_frame_finish() -> br_forward(): But in br_handle_frame_finish() in order to call br_forward() the dst should not be local i.e. skb != NULL, whenever the dst is found to be local skb is set to NULL so we can't forward it, and here comes the problem since it's running only with RCU when forwarding packets it can see the entry before "is_local" is set to 1 and actually try to dereference NULL. The main issue is that if someone sends a packet to the switch while it's adding the entry which points to the bridge device, it may dereference NULL ptr. This is needed now after we can add fdbs pointing to the bridge. This poses a problem for br_fdb_update() as well, while someone's adding a bridge fdb, but before it has is_local == 1, it might get moved to a port if it comes as a source mac and then it may get its "is_local" set to 1 This patch changes fdb_create to take is_local and is_static as arguments to set these values in the fdb entry before it is added to the hash. Also adds null check for port in br_forward. Fixes: 3741873b4f73 ("bridge: allow adding of fdb entries pointing to the bridge device") Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-27 14:52:56 +00:00
__u16 vid,
unsigned char is_local,
unsigned char is_static)
{
struct net_bridge_fdb_entry *fdb;
fdb = kmem_cache_alloc(br_fdb_cache, GFP_ATOMIC);
if (fdb) {
memcpy(fdb->addr.addr, addr, ETH_ALEN);
fdb->dst = source;
fdb->vlan_id = vid;
bridge: set is_local and is_static before fdb entry is added to the fdb hashtable Problem Description: We can add fdbs pointing to the bridge with NULL ->dst but that has a few race conditions because br_fdb_insert() is used which first creates the fdb and then, after the fdb has been published/linked, sets "is_local" to 1 and in that time frame if a packet arrives for that fdb it may see it as non-local and either do a NULL ptr dereference in br_forward() or attach the fdb to the port where it arrived, and later br_fdb_insert() will make it local thus getting a wrong fdb entry. Call chain br_handle_frame_finish() -> br_forward(): But in br_handle_frame_finish() in order to call br_forward() the dst should not be local i.e. skb != NULL, whenever the dst is found to be local skb is set to NULL so we can't forward it, and here comes the problem since it's running only with RCU when forwarding packets it can see the entry before "is_local" is set to 1 and actually try to dereference NULL. The main issue is that if someone sends a packet to the switch while it's adding the entry which points to the bridge device, it may dereference NULL ptr. This is needed now after we can add fdbs pointing to the bridge. This poses a problem for br_fdb_update() as well, while someone's adding a bridge fdb, but before it has is_local == 1, it might get moved to a port if it comes as a source mac and then it may get its "is_local" set to 1 This patch changes fdb_create to take is_local and is_static as arguments to set these values in the fdb entry before it is added to the hash. Also adds null check for port in br_forward. Fixes: 3741873b4f73 ("bridge: allow adding of fdb entries pointing to the bridge device") Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-27 14:52:56 +00:00
fdb->is_local = is_local;
fdb->is_static = is_static;
fdb->added_by_user = 0;
fdb->added_by_external_learn = 0;
fdb->offloaded = 0;
fdb->updated = fdb->used = jiffies;
hlist_add_head_rcu(&fdb->hlist, head);
}
return fdb;
}
static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr, u16 vid)
{
struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
struct net_bridge_fdb_entry *fdb;
if (!is_valid_ether_addr(addr))
return -EINVAL;
fdb = br_fdb_find(br, addr, vid);
if (fdb) {
/* it is okay to have multiple ports with same
* address, just use the first one.
*/
if (fdb->is_local)
return 0;
br_warn(br, "adding interface %s with same address as a received packet (addr:%pM, vlan:%u)\n",
source ? source->dev->name : br->dev->name, addr, vid);
fdb_delete(br, fdb);
}
bridge: set is_local and is_static before fdb entry is added to the fdb hashtable Problem Description: We can add fdbs pointing to the bridge with NULL ->dst but that has a few race conditions because br_fdb_insert() is used which first creates the fdb and then, after the fdb has been published/linked, sets "is_local" to 1 and in that time frame if a packet arrives for that fdb it may see it as non-local and either do a NULL ptr dereference in br_forward() or attach the fdb to the port where it arrived, and later br_fdb_insert() will make it local thus getting a wrong fdb entry. Call chain br_handle_frame_finish() -> br_forward(): But in br_handle_frame_finish() in order to call br_forward() the dst should not be local i.e. skb != NULL, whenever the dst is found to be local skb is set to NULL so we can't forward it, and here comes the problem since it's running only with RCU when forwarding packets it can see the entry before "is_local" is set to 1 and actually try to dereference NULL. The main issue is that if someone sends a packet to the switch while it's adding the entry which points to the bridge device, it may dereference NULL ptr. This is needed now after we can add fdbs pointing to the bridge. This poses a problem for br_fdb_update() as well, while someone's adding a bridge fdb, but before it has is_local == 1, it might get moved to a port if it comes as a source mac and then it may get its "is_local" set to 1 This patch changes fdb_create to take is_local and is_static as arguments to set these values in the fdb entry before it is added to the hash. Also adds null check for port in br_forward. Fixes: 3741873b4f73 ("bridge: allow adding of fdb entries pointing to the bridge device") Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-27 14:52:56 +00:00
fdb = fdb_create(head, source, addr, vid, 1, 1);
if (!fdb)
return -ENOMEM;
fdb_add_hw_addr(br, addr);
fdb_notify(br, fdb, RTM_NEWNEIGH);
return 0;
}
/* Add entry for local address of interface */
int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr, u16 vid)
{
int ret;
spin_lock_bh(&br->hash_lock);
ret = fdb_insert(br, source, addr, vid);
spin_unlock_bh(&br->hash_lock);
return ret;
}
void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
const unsigned char *addr, u16 vid, bool added_by_user)
{
struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
struct net_bridge_fdb_entry *fdb;
bool fdb_modified = false;
/* some users want to always flood. */
if (hold_time(br) == 0)
return;
/* ignore packets unless we are using this port */
if (!(source->state == BR_STATE_LEARNING ||
source->state == BR_STATE_FORWARDING))
return;
fdb = fdb_find_rcu(head, addr, vid);
if (likely(fdb)) {
/* attempt to update an entry for a local interface */
if (unlikely(fdb->is_local)) {
if (net_ratelimit())
br_warn(br, "received packet on %s with own address as source address (addr:%pM, vlan:%u)\n",
source->dev->name, addr, vid);
} else {
unsigned long now = jiffies;
/* fastpath: update of existing entry */
if (unlikely(source != fdb->dst)) {
fdb->dst = source;
fdb_modified = true;
/* Take over HW learned entry */
if (unlikely(fdb->added_by_external_learn))
fdb->added_by_external_learn = 0;
}
if (now != fdb->updated)
fdb->updated = now;
if (unlikely(added_by_user))
fdb->added_by_user = 1;
if (unlikely(fdb_modified))
fdb_notify(br, fdb, RTM_NEWNEIGH);
}
} else {
spin_lock(&br->hash_lock);
if (likely(!fdb_find_rcu(head, addr, vid))) {
bridge: set is_local and is_static before fdb entry is added to the fdb hashtable Problem Description: We can add fdbs pointing to the bridge with NULL ->dst but that has a few race conditions because br_fdb_insert() is used which first creates the fdb and then, after the fdb has been published/linked, sets "is_local" to 1 and in that time frame if a packet arrives for that fdb it may see it as non-local and either do a NULL ptr dereference in br_forward() or attach the fdb to the port where it arrived, and later br_fdb_insert() will make it local thus getting a wrong fdb entry. Call chain br_handle_frame_finish() -> br_forward(): But in br_handle_frame_finish() in order to call br_forward() the dst should not be local i.e. skb != NULL, whenever the dst is found to be local skb is set to NULL so we can't forward it, and here comes the problem since it's running only with RCU when forwarding packets it can see the entry before "is_local" is set to 1 and actually try to dereference NULL. The main issue is that if someone sends a packet to the switch while it's adding the entry which points to the bridge device, it may dereference NULL ptr. This is needed now after we can add fdbs pointing to the bridge. This poses a problem for br_fdb_update() as well, while someone's adding a bridge fdb, but before it has is_local == 1, it might get moved to a port if it comes as a source mac and then it may get its "is_local" set to 1 This patch changes fdb_create to take is_local and is_static as arguments to set these values in the fdb entry before it is added to the hash. Also adds null check for port in br_forward. Fixes: 3741873b4f73 ("bridge: allow adding of fdb entries pointing to the bridge device") Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-27 14:52:56 +00:00
fdb = fdb_create(head, source, addr, vid, 0, 0);
if (fdb) {
if (unlikely(added_by_user))
fdb->added_by_user = 1;
fdb_notify(br, fdb, RTM_NEWNEIGH);
}
}
/* else we lose race and someone else inserts
* it first, don't bother updating
*/
spin_unlock(&br->hash_lock);
}
}
static int fdb_to_nud(const struct net_bridge *br,
const struct net_bridge_fdb_entry *fdb)
{
if (fdb->is_local)
return NUD_PERMANENT;
else if (fdb->is_static)
return NUD_NOARP;
else if (has_expired(br, fdb))
return NUD_STALE;
else
return NUD_REACHABLE;
}
static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
const struct net_bridge_fdb_entry *fdb,
u32 portid, u32 seq, int type, unsigned int flags)
{
unsigned long now = jiffies;
struct nda_cacheinfo ci;
struct nlmsghdr *nlh;
struct ndmsg *ndm;
nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
if (nlh == NULL)
return -EMSGSIZE;
ndm = nlmsg_data(nlh);
ndm->ndm_family = AF_BRIDGE;
ndm->ndm_pad1 = 0;
ndm->ndm_pad2 = 0;
ndm->ndm_flags = 0;
ndm->ndm_type = 0;
ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex;
ndm->ndm_state = fdb_to_nud(br, fdb);
if (fdb->offloaded)
ndm->ndm_flags |= NTF_OFFLOADED;
if (fdb->added_by_external_learn)
ndm->ndm_flags |= NTF_EXT_LEARNED;
if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr))
goto nla_put_failure;
if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex))
goto nla_put_failure;
ci.ndm_used = jiffies_to_clock_t(now - fdb->used);
ci.ndm_confirmed = 0;
ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated);
ci.ndm_refcnt = 0;
if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
goto nla_put_failure;
if (fdb->vlan_id && nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->vlan_id))
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 inline size_t fdb_nlmsg_size(void)
{
return NLMSG_ALIGN(sizeof(struct ndmsg))
+ nla_total_size(ETH_ALEN) /* NDA_LLADDR */
+ nla_total_size(sizeof(u32)) /* NDA_MASTER */
+ nla_total_size(sizeof(u16)) /* NDA_VLAN */
+ nla_total_size(sizeof(struct nda_cacheinfo));
}
static void fdb_notify(struct net_bridge *br,
const struct net_bridge_fdb_entry *fdb, int type)
{
struct net *net = dev_net(br->dev);
struct sk_buff *skb;
int err = -ENOBUFS;
br_switchdev_fdb_notify(fdb, type);
skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC);
if (skb == NULL)
goto errout;
err = fdb_fill_info(skb, br, fdb, 0, 0, type, 0);
if (err < 0) {
/* -EMSGSIZE implies BUG in fdb_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
return;
errout:
rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
}
/* Dump information about entries, in response to GETNEIGH */
net: add generic PF_BRIDGE:RTM_ FDB hooks This adds two new flags NTF_MASTER and NTF_SELF that can now be used to specify where PF_BRIDGE netlink commands should be sent. NTF_MASTER sends the commands to the 'dev->master' device for parsing. Typically this will be the linux net/bridge, or open-vswitch devices. Also without any flags set the command will be handled by the master device as well so that current user space tools continue to work as expected. The NTF_SELF flag will push the PF_BRIDGE commands to the device. In the basic example below the commands are then parsed and programmed in the embedded bridge. Note if both NTF_SELF and NTF_MASTER bits are set then the command will be sent to both 'dev->master' and 'dev' this allows user space to easily keep the embedded bridge and software bridge in sync. There is a slight complication in the case with both flags set when an error occurs. To resolve this the rtnl handler clears the NTF_ flag in the netlink ack to indicate which sets completed successfully. The add/del handlers will abort as soon as any error occurs. To support this new net device ops were added to call into the device and the existing bridging code was refactored to use these. There should be no required changes in user space to support the current bridge behavior. A basic setup with a SR-IOV enabled NIC looks like this, veth0 veth2 | | ------------ | bridge0 | <---- software bridging ------------ / / ethx.y ethx VF PF \ \ <---- propagate FDB entries to HW \ \ -------------------- | Embedded Bridge | <---- hardware offloaded switching -------------------- In this case the embedded bridge must be managed to allow 'veth0' to communicate with 'ethx.y' correctly. At present drivers managing the embedded bridge either send frames onto the network which then get dropped by the switch OR the embedded bridge will flood these frames. With this patch we have a mechanism to manage the embedded bridge correctly from user space. This example is specific to SR-IOV but replacing the VF with another PF or dropping this into the DSA framework generates similar management issues. Examples session using the 'br'[1] tool to add, dump and then delete a mac address with a new "embedded" option and enabled ixgbe driver: # br fdb add 22:35:19:ac:60:59 dev eth3 # br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static #br fdb add 22:35:19:ac:60:59 embedded dev eth3 #br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static eth3 22:35:19:ac:60:59 local embedded #br fdb del 22:35:19:ac:60:59 embedded dev eth3 I added a couple lines to 'br' to set the flags correctly is all. It is my opinion that the merit of this patch is now embedded and SW bridges can both be modeled correctly in user space using very nearly the same message passing. [1] 'br' tool was published as an RFC here and will be renamed 'bridge' http://patchwork.ozlabs.org/patch/117664/ Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for valuable feedback, suggestions, and review. v2: fixed api descriptions and error case with both NTF_SELF and NTF_MASTER set plus updated patch description. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-15 06:43:56 +00:00
int br_fdb_dump(struct sk_buff *skb,
struct netlink_callback *cb,
struct net_device *dev,
struct net_device *filter_dev,
rtnetlink: fdb dump: optimize by saving last interface markers fdb dumps spanning multiple skb's currently restart from the first interface again for every skb. This results in unnecessary iterations on the already visited interfaces and their fdb entries. In large scale setups, we have seen this to slow down fdb dumps considerably. On a system with 30k macs we see fdb dumps spanning across more than 300 skbs. To fix the problem, this patch replaces the existing single fdb marker with three markers: netdev hash entries, netdevs and fdb index to continue where we left off instead of restarting from the first netdev. This is consistent with link dumps. In the process of fixing the performance issue, this patch also re-implements fix done by commit 472681d57a5d ("net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump") (with an internal fix from Wilson Kok) in the following ways: - change ndo_fdb_dump handlers to return error code instead of the last fdb index - use cb->args strictly for dump frag markers and not error codes. This is consistent with other dump functions. Below results were taken on a system with 1000 netdevs and 35085 fdb entries: before patch: $time bridge fdb show | wc -l 15065 real 1m11.791s user 0m0.070s sys 1m8.395s (existing code does not return all macs) after patch: $time bridge fdb show | wc -l 35085 real 0m2.017s user 0m0.113s sys 0m1.942s Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 04:56:45 +00:00
int *idx)
{
net: add generic PF_BRIDGE:RTM_ FDB hooks This adds two new flags NTF_MASTER and NTF_SELF that can now be used to specify where PF_BRIDGE netlink commands should be sent. NTF_MASTER sends the commands to the 'dev->master' device for parsing. Typically this will be the linux net/bridge, or open-vswitch devices. Also without any flags set the command will be handled by the master device as well so that current user space tools continue to work as expected. The NTF_SELF flag will push the PF_BRIDGE commands to the device. In the basic example below the commands are then parsed and programmed in the embedded bridge. Note if both NTF_SELF and NTF_MASTER bits are set then the command will be sent to both 'dev->master' and 'dev' this allows user space to easily keep the embedded bridge and software bridge in sync. There is a slight complication in the case with both flags set when an error occurs. To resolve this the rtnl handler clears the NTF_ flag in the netlink ack to indicate which sets completed successfully. The add/del handlers will abort as soon as any error occurs. To support this new net device ops were added to call into the device and the existing bridging code was refactored to use these. There should be no required changes in user space to support the current bridge behavior. A basic setup with a SR-IOV enabled NIC looks like this, veth0 veth2 | | ------------ | bridge0 | <---- software bridging ------------ / / ethx.y ethx VF PF \ \ <---- propagate FDB entries to HW \ \ -------------------- | Embedded Bridge | <---- hardware offloaded switching -------------------- In this case the embedded bridge must be managed to allow 'veth0' to communicate with 'ethx.y' correctly. At present drivers managing the embedded bridge either send frames onto the network which then get dropped by the switch OR the embedded bridge will flood these frames. With this patch we have a mechanism to manage the embedded bridge correctly from user space. This example is specific to SR-IOV but replacing the VF with another PF or dropping this into the DSA framework generates similar management issues. Examples session using the 'br'[1] tool to add, dump and then delete a mac address with a new "embedded" option and enabled ixgbe driver: # br fdb add 22:35:19:ac:60:59 dev eth3 # br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static #br fdb add 22:35:19:ac:60:59 embedded dev eth3 #br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static eth3 22:35:19:ac:60:59 local embedded #br fdb del 22:35:19:ac:60:59 embedded dev eth3 I added a couple lines to 'br' to set the flags correctly is all. It is my opinion that the merit of this patch is now embedded and SW bridges can both be modeled correctly in user space using very nearly the same message passing. [1] 'br' tool was published as an RFC here and will be renamed 'bridge' http://patchwork.ozlabs.org/patch/117664/ Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for valuable feedback, suggestions, and review. v2: fixed api descriptions and error case with both NTF_SELF and NTF_MASTER set plus updated patch description. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-15 06:43:56 +00:00
struct net_bridge *br = netdev_priv(dev);
rtnetlink: fdb dump: optimize by saving last interface markers fdb dumps spanning multiple skb's currently restart from the first interface again for every skb. This results in unnecessary iterations on the already visited interfaces and their fdb entries. In large scale setups, we have seen this to slow down fdb dumps considerably. On a system with 30k macs we see fdb dumps spanning across more than 300 skbs. To fix the problem, this patch replaces the existing single fdb marker with three markers: netdev hash entries, netdevs and fdb index to continue where we left off instead of restarting from the first netdev. This is consistent with link dumps. In the process of fixing the performance issue, this patch also re-implements fix done by commit 472681d57a5d ("net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump") (with an internal fix from Wilson Kok) in the following ways: - change ndo_fdb_dump handlers to return error code instead of the last fdb index - use cb->args strictly for dump frag markers and not error codes. This is consistent with other dump functions. Below results were taken on a system with 1000 netdevs and 35085 fdb entries: before patch: $time bridge fdb show | wc -l 15065 real 1m11.791s user 0m0.070s sys 1m8.395s (existing code does not return all macs) after patch: $time bridge fdb show | wc -l 35085 real 0m2.017s user 0m0.113s sys 0m1.942s Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 04:56:45 +00:00
int err = 0;
net: add generic PF_BRIDGE:RTM_ FDB hooks This adds two new flags NTF_MASTER and NTF_SELF that can now be used to specify where PF_BRIDGE netlink commands should be sent. NTF_MASTER sends the commands to the 'dev->master' device for parsing. Typically this will be the linux net/bridge, or open-vswitch devices. Also without any flags set the command will be handled by the master device as well so that current user space tools continue to work as expected. The NTF_SELF flag will push the PF_BRIDGE commands to the device. In the basic example below the commands are then parsed and programmed in the embedded bridge. Note if both NTF_SELF and NTF_MASTER bits are set then the command will be sent to both 'dev->master' and 'dev' this allows user space to easily keep the embedded bridge and software bridge in sync. There is a slight complication in the case with both flags set when an error occurs. To resolve this the rtnl handler clears the NTF_ flag in the netlink ack to indicate which sets completed successfully. The add/del handlers will abort as soon as any error occurs. To support this new net device ops were added to call into the device and the existing bridging code was refactored to use these. There should be no required changes in user space to support the current bridge behavior. A basic setup with a SR-IOV enabled NIC looks like this, veth0 veth2 | | ------------ | bridge0 | <---- software bridging ------------ / / ethx.y ethx VF PF \ \ <---- propagate FDB entries to HW \ \ -------------------- | Embedded Bridge | <---- hardware offloaded switching -------------------- In this case the embedded bridge must be managed to allow 'veth0' to communicate with 'ethx.y' correctly. At present drivers managing the embedded bridge either send frames onto the network which then get dropped by the switch OR the embedded bridge will flood these frames. With this patch we have a mechanism to manage the embedded bridge correctly from user space. This example is specific to SR-IOV but replacing the VF with another PF or dropping this into the DSA framework generates similar management issues. Examples session using the 'br'[1] tool to add, dump and then delete a mac address with a new "embedded" option and enabled ixgbe driver: # br fdb add 22:35:19:ac:60:59 dev eth3 # br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static #br fdb add 22:35:19:ac:60:59 embedded dev eth3 #br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static eth3 22:35:19:ac:60:59 local embedded #br fdb del 22:35:19:ac:60:59 embedded dev eth3 I added a couple lines to 'br' to set the flags correctly is all. It is my opinion that the merit of this patch is now embedded and SW bridges can both be modeled correctly in user space using very nearly the same message passing. [1] 'br' tool was published as an RFC here and will be renamed 'bridge' http://patchwork.ozlabs.org/patch/117664/ Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for valuable feedback, suggestions, and review. v2: fixed api descriptions and error case with both NTF_SELF and NTF_MASTER set plus updated patch description. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-15 06:43:56 +00:00
int i;
net: add generic PF_BRIDGE:RTM_ FDB hooks This adds two new flags NTF_MASTER and NTF_SELF that can now be used to specify where PF_BRIDGE netlink commands should be sent. NTF_MASTER sends the commands to the 'dev->master' device for parsing. Typically this will be the linux net/bridge, or open-vswitch devices. Also without any flags set the command will be handled by the master device as well so that current user space tools continue to work as expected. The NTF_SELF flag will push the PF_BRIDGE commands to the device. In the basic example below the commands are then parsed and programmed in the embedded bridge. Note if both NTF_SELF and NTF_MASTER bits are set then the command will be sent to both 'dev->master' and 'dev' this allows user space to easily keep the embedded bridge and software bridge in sync. There is a slight complication in the case with both flags set when an error occurs. To resolve this the rtnl handler clears the NTF_ flag in the netlink ack to indicate which sets completed successfully. The add/del handlers will abort as soon as any error occurs. To support this new net device ops were added to call into the device and the existing bridging code was refactored to use these. There should be no required changes in user space to support the current bridge behavior. A basic setup with a SR-IOV enabled NIC looks like this, veth0 veth2 | | ------------ | bridge0 | <---- software bridging ------------ / / ethx.y ethx VF PF \ \ <---- propagate FDB entries to HW \ \ -------------------- | Embedded Bridge | <---- hardware offloaded switching -------------------- In this case the embedded bridge must be managed to allow 'veth0' to communicate with 'ethx.y' correctly. At present drivers managing the embedded bridge either send frames onto the network which then get dropped by the switch OR the embedded bridge will flood these frames. With this patch we have a mechanism to manage the embedded bridge correctly from user space. This example is specific to SR-IOV but replacing the VF with another PF or dropping this into the DSA framework generates similar management issues. Examples session using the 'br'[1] tool to add, dump and then delete a mac address with a new "embedded" option and enabled ixgbe driver: # br fdb add 22:35:19:ac:60:59 dev eth3 # br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static #br fdb add 22:35:19:ac:60:59 embedded dev eth3 #br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static eth3 22:35:19:ac:60:59 local embedded #br fdb del 22:35:19:ac:60:59 embedded dev eth3 I added a couple lines to 'br' to set the flags correctly is all. It is my opinion that the merit of this patch is now embedded and SW bridges can both be modeled correctly in user space using very nearly the same message passing. [1] 'br' tool was published as an RFC here and will be renamed 'bridge' http://patchwork.ozlabs.org/patch/117664/ Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for valuable feedback, suggestions, and review. v2: fixed api descriptions and error case with both NTF_SELF and NTF_MASTER set plus updated patch description. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-15 06:43:56 +00:00
if (!(dev->priv_flags & IFF_EBRIDGE))
goto out;
rtnetlink: fdb dump: optimize by saving last interface markers fdb dumps spanning multiple skb's currently restart from the first interface again for every skb. This results in unnecessary iterations on the already visited interfaces and their fdb entries. In large scale setups, we have seen this to slow down fdb dumps considerably. On a system with 30k macs we see fdb dumps spanning across more than 300 skbs. To fix the problem, this patch replaces the existing single fdb marker with three markers: netdev hash entries, netdevs and fdb index to continue where we left off instead of restarting from the first netdev. This is consistent with link dumps. In the process of fixing the performance issue, this patch also re-implements fix done by commit 472681d57a5d ("net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump") (with an internal fix from Wilson Kok) in the following ways: - change ndo_fdb_dump handlers to return error code instead of the last fdb index - use cb->args strictly for dump frag markers and not error codes. This is consistent with other dump functions. Below results were taken on a system with 1000 netdevs and 35085 fdb entries: before patch: $time bridge fdb show | wc -l 15065 real 1m11.791s user 0m0.070s sys 1m8.395s (existing code does not return all macs) after patch: $time bridge fdb show | wc -l 35085 real 0m2.017s user 0m0.113s sys 0m1.942s Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 04:56:45 +00:00
if (!filter_dev) {
err = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx);
if (err < 0)
goto out;
}
net: Do not call ndo_dflt_fdb_dump if ndo_fdb_dump is defined Add checking whether the call to ndo_dflt_fdb_dump is needed. It is not expected to call ndo_dflt_fdb_dump unconditionally by some drivers (i.e. qlcnic or macvlan) that defines own ndo_fdb_dump. Other drivers define own ndo_fdb_dump and don't want ndo_dflt_fdb_dump to be called at all. At the same time it is desirable to call the default dump function on a bridge device. Fix attributes that are passed to dev->netdev_ops->ndo_fdb_dump. Add extra checking in br_fdb_dump to avoid duplicate entries as now filter_dev can be NULL. Following tests for filtering have been performed before the change and after the patch was applied to make sure they are the same and it doesn't break the filtering algorithm. [root@localhost ~]# cd /root/iproute2-3.18.0/bridge [root@localhost bridge]# modprobe dummy [root@localhost bridge]# ./bridge fdb add f1:f2:f3:f4:f5:f6 dev dummy0 [root@localhost bridge]# brctl addbr br0 [root@localhost bridge]# brctl addif br0 dummy0 [root@localhost bridge]# ip link set dev br0 address 02:00:00:12:01:04 [root@localhost bridge]# # show all [root@localhost bridge]# ./bridge fdb show 33:33:00:00:00:01 dev p2p1 self permanent 01:00:5e:00:00:01 dev p2p1 self permanent 33:33:ff:ac:ce:32 dev p2p1 self permanent 33:33:00:00:02:02 dev p2p1 self permanent 01:00:5e:00:00:fb dev p2p1 self permanent 33:33:00:00:00:01 dev p7p1 self permanent 01:00:5e:00:00:01 dev p7p1 self permanent 33:33:ff:79:50:53 dev p7p1 self permanent 33:33:00:00:02:02 dev p7p1 self permanent 01:00:5e:00:00:fb dev p7p1 self permanent f2:46:50:85:6d:d9 dev dummy0 master br0 permanent f2:46:50:85:6d:d9 dev dummy0 vlan 1 master br0 permanent 33:33:00:00:00:01 dev dummy0 self permanent f1:f2:f3:f4:f5:f6 dev dummy0 self permanent 33:33:00:00:00:01 dev br0 self permanent 02:00:00:12:01:04 dev br0 vlan 1 master br0 permanent 02:00:00:12:01:04 dev br0 master br0 permanent [root@localhost bridge]# # filter by bridge [root@localhost bridge]# ./bridge fdb show br br0 f2:46:50:85:6d:d9 dev dummy0 master br0 permanent f2:46:50:85:6d:d9 dev dummy0 vlan 1 master br0 permanent 33:33:00:00:00:01 dev dummy0 self permanent f1:f2:f3:f4:f5:f6 dev dummy0 self permanent 33:33:00:00:00:01 dev br0 self permanent 02:00:00:12:01:04 dev br0 vlan 1 master br0 permanent 02:00:00:12:01:04 dev br0 master br0 permanent [root@localhost bridge]# # filter by port [root@localhost bridge]# ./bridge fdb show brport dummy0 f2:46:50:85:6d:d9 master br0 permanent f2:46:50:85:6d:d9 vlan 1 master br0 permanent 33:33:00:00:00:01 self permanent f1:f2:f3:f4:f5:f6 self permanent [root@localhost bridge]# # filter by port + bridge [root@localhost bridge]# ./bridge fdb show br br0 brport dummy0 f2:46:50:85:6d:d9 master br0 permanent f2:46:50:85:6d:d9 vlan 1 master br0 permanent 33:33:00:00:00:01 self permanent f1:f2:f3:f4:f5:f6 self permanent [root@localhost bridge]# Signed-off-by: Hubert Sokolowski <hubert.sokolowski@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-05 17:29:21 +00:00
net: add generic PF_BRIDGE:RTM_ FDB hooks This adds two new flags NTF_MASTER and NTF_SELF that can now be used to specify where PF_BRIDGE netlink commands should be sent. NTF_MASTER sends the commands to the 'dev->master' device for parsing. Typically this will be the linux net/bridge, or open-vswitch devices. Also without any flags set the command will be handled by the master device as well so that current user space tools continue to work as expected. The NTF_SELF flag will push the PF_BRIDGE commands to the device. In the basic example below the commands are then parsed and programmed in the embedded bridge. Note if both NTF_SELF and NTF_MASTER bits are set then the command will be sent to both 'dev->master' and 'dev' this allows user space to easily keep the embedded bridge and software bridge in sync. There is a slight complication in the case with both flags set when an error occurs. To resolve this the rtnl handler clears the NTF_ flag in the netlink ack to indicate which sets completed successfully. The add/del handlers will abort as soon as any error occurs. To support this new net device ops were added to call into the device and the existing bridging code was refactored to use these. There should be no required changes in user space to support the current bridge behavior. A basic setup with a SR-IOV enabled NIC looks like this, veth0 veth2 | | ------------ | bridge0 | <---- software bridging ------------ / / ethx.y ethx VF PF \ \ <---- propagate FDB entries to HW \ \ -------------------- | Embedded Bridge | <---- hardware offloaded switching -------------------- In this case the embedded bridge must be managed to allow 'veth0' to communicate with 'ethx.y' correctly. At present drivers managing the embedded bridge either send frames onto the network which then get dropped by the switch OR the embedded bridge will flood these frames. With this patch we have a mechanism to manage the embedded bridge correctly from user space. This example is specific to SR-IOV but replacing the VF with another PF or dropping this into the DSA framework generates similar management issues. Examples session using the 'br'[1] tool to add, dump and then delete a mac address with a new "embedded" option and enabled ixgbe driver: # br fdb add 22:35:19:ac:60:59 dev eth3 # br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static #br fdb add 22:35:19:ac:60:59 embedded dev eth3 #br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static eth3 22:35:19:ac:60:59 local embedded #br fdb del 22:35:19:ac:60:59 embedded dev eth3 I added a couple lines to 'br' to set the flags correctly is all. It is my opinion that the merit of this patch is now embedded and SW bridges can both be modeled correctly in user space using very nearly the same message passing. [1] 'br' tool was published as an RFC here and will be renamed 'bridge' http://patchwork.ozlabs.org/patch/117664/ Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for valuable feedback, suggestions, and review. v2: fixed api descriptions and error case with both NTF_SELF and NTF_MASTER set plus updated patch description. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-15 06:43:56 +00:00
for (i = 0; i < BR_HASH_SIZE; i++) {
struct net_bridge_fdb_entry *f;
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(f, &br->hash[i], hlist) {
rtnetlink: fdb dump: optimize by saving last interface markers fdb dumps spanning multiple skb's currently restart from the first interface again for every skb. This results in unnecessary iterations on the already visited interfaces and their fdb entries. In large scale setups, we have seen this to slow down fdb dumps considerably. On a system with 30k macs we see fdb dumps spanning across more than 300 skbs. To fix the problem, this patch replaces the existing single fdb marker with three markers: netdev hash entries, netdevs and fdb index to continue where we left off instead of restarting from the first netdev. This is consistent with link dumps. In the process of fixing the performance issue, this patch also re-implements fix done by commit 472681d57a5d ("net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump") (with an internal fix from Wilson Kok) in the following ways: - change ndo_fdb_dump handlers to return error code instead of the last fdb index - use cb->args strictly for dump frag markers and not error codes. This is consistent with other dump functions. Below results were taken on a system with 1000 netdevs and 35085 fdb entries: before patch: $time bridge fdb show | wc -l 15065 real 1m11.791s user 0m0.070s sys 1m8.395s (existing code does not return all macs) after patch: $time bridge fdb show | wc -l 35085 real 0m2.017s user 0m0.113s sys 0m1.942s Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 04:56:45 +00:00
if (*idx < cb->args[2])
net: add generic PF_BRIDGE:RTM_ FDB hooks This adds two new flags NTF_MASTER and NTF_SELF that can now be used to specify where PF_BRIDGE netlink commands should be sent. NTF_MASTER sends the commands to the 'dev->master' device for parsing. Typically this will be the linux net/bridge, or open-vswitch devices. Also without any flags set the command will be handled by the master device as well so that current user space tools continue to work as expected. The NTF_SELF flag will push the PF_BRIDGE commands to the device. In the basic example below the commands are then parsed and programmed in the embedded bridge. Note if both NTF_SELF and NTF_MASTER bits are set then the command will be sent to both 'dev->master' and 'dev' this allows user space to easily keep the embedded bridge and software bridge in sync. There is a slight complication in the case with both flags set when an error occurs. To resolve this the rtnl handler clears the NTF_ flag in the netlink ack to indicate which sets completed successfully. The add/del handlers will abort as soon as any error occurs. To support this new net device ops were added to call into the device and the existing bridging code was refactored to use these. There should be no required changes in user space to support the current bridge behavior. A basic setup with a SR-IOV enabled NIC looks like this, veth0 veth2 | | ------------ | bridge0 | <---- software bridging ------------ / / ethx.y ethx VF PF \ \ <---- propagate FDB entries to HW \ \ -------------------- | Embedded Bridge | <---- hardware offloaded switching -------------------- In this case the embedded bridge must be managed to allow 'veth0' to communicate with 'ethx.y' correctly. At present drivers managing the embedded bridge either send frames onto the network which then get dropped by the switch OR the embedded bridge will flood these frames. With this patch we have a mechanism to manage the embedded bridge correctly from user space. This example is specific to SR-IOV but replacing the VF with another PF or dropping this into the DSA framework generates similar management issues. Examples session using the 'br'[1] tool to add, dump and then delete a mac address with a new "embedded" option and enabled ixgbe driver: # br fdb add 22:35:19:ac:60:59 dev eth3 # br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static #br fdb add 22:35:19:ac:60:59 embedded dev eth3 #br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static eth3 22:35:19:ac:60:59 local embedded #br fdb del 22:35:19:ac:60:59 embedded dev eth3 I added a couple lines to 'br' to set the flags correctly is all. It is my opinion that the merit of this patch is now embedded and SW bridges can both be modeled correctly in user space using very nearly the same message passing. [1] 'br' tool was published as an RFC here and will be renamed 'bridge' http://patchwork.ozlabs.org/patch/117664/ Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for valuable feedback, suggestions, and review. v2: fixed api descriptions and error case with both NTF_SELF and NTF_MASTER set plus updated patch description. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-15 06:43:56 +00:00
goto skip;
bridge: netlink dump interface at par with brctl Actually better than brctl showmacs because we can filter by bridge port in the kernel. The current bridge netlink interface doesnt scale when you have many bridges each with large fdbs or even bridges with many bridge ports And now for the science non-fiction novel you have all been waiting for.. //lets see what bridge ports we have root@moja-1:/configs/may30-iprt/bridge# ./bridge link show 8: eth1 state DOWN : <BROADCAST,MULTICAST> mtu 1500 master br0 state disabled priority 32 cost 19 17: sw1-p1 state DOWN : <BROADCAST,NOARP> mtu 1500 master br0 state disabled priority 32 cost 100 // show all.. root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show 33:33:00:00:00:01 dev bond0 self permanent 33:33:00:00:00:01 dev dummy0 self permanent 33:33:00:00:00:01 dev ifb0 self permanent 33:33:00:00:00:01 dev ifb1 self permanent 33:33:00:00:00:01 dev eth0 self permanent 01:00:5e:00:00:01 dev eth0 self permanent 33:33:ff:22:01:01 dev eth0 self permanent 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent 33:33:00:00:00:01 dev gretap0 self permanent da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent //filter by bridge root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br br0 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent // bridge sw1 has no ports attached.. root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br sw1 //filter by port root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show brport eth1 02:00:00:12:01:02 vlan 0 master br0 permanent 00:17:42:8a:b4:05 vlan 0 master br0 permanent 00:17:42:8a:b4:07 self permanent 33:33:00:00:00:01 self permanent // filter by port + bridge root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br br0 brport sw1-p1 da:ac:46:27:d9:53 vlan 0 master br0 permanent 33:33:00:00:00:01 self permanent // for shits and giggles (as they say in New Brunswick), lets // change the mac that br0 uses // Note: a magical fdb entry with no brport is added ... root@moja-1:/configs/may30-iprt/bridge# ip link set dev br0 address 02:00:00:12:01:04 // lets see if we can see the unicorn .. root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show 33:33:00:00:00:01 dev bond0 self permanent 33:33:00:00:00:01 dev dummy0 self permanent 33:33:00:00:00:01 dev ifb0 self permanent 33:33:00:00:00:01 dev ifb1 self permanent 33:33:00:00:00:01 dev eth0 self permanent 01:00:5e:00:00:01 dev eth0 self permanent 33:33:ff:22:01:01 dev eth0 self permanent 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent 33:33:00:00:00:01 dev gretap0 self permanent 02:00:00:12:01:04 dev br0 vlan 0 master br0 permanent <=== there it is da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent //can we see it if we filter by bridge? root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br br0 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent 02:00:00:12:01:04 dev br0 vlan 0 master br0 permanent <=== there it is da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-10 11:01:59 +00:00
if (filter_dev &&
(!f->dst || f->dst->dev != filter_dev)) {
if (filter_dev != dev)
goto skip;
net: Do not call ndo_dflt_fdb_dump if ndo_fdb_dump is defined Add checking whether the call to ndo_dflt_fdb_dump is needed. It is not expected to call ndo_dflt_fdb_dump unconditionally by some drivers (i.e. qlcnic or macvlan) that defines own ndo_fdb_dump. Other drivers define own ndo_fdb_dump and don't want ndo_dflt_fdb_dump to be called at all. At the same time it is desirable to call the default dump function on a bridge device. Fix attributes that are passed to dev->netdev_ops->ndo_fdb_dump. Add extra checking in br_fdb_dump to avoid duplicate entries as now filter_dev can be NULL. Following tests for filtering have been performed before the change and after the patch was applied to make sure they are the same and it doesn't break the filtering algorithm. [root@localhost ~]# cd /root/iproute2-3.18.0/bridge [root@localhost bridge]# modprobe dummy [root@localhost bridge]# ./bridge fdb add f1:f2:f3:f4:f5:f6 dev dummy0 [root@localhost bridge]# brctl addbr br0 [root@localhost bridge]# brctl addif br0 dummy0 [root@localhost bridge]# ip link set dev br0 address 02:00:00:12:01:04 [root@localhost bridge]# # show all [root@localhost bridge]# ./bridge fdb show 33:33:00:00:00:01 dev p2p1 self permanent 01:00:5e:00:00:01 dev p2p1 self permanent 33:33:ff:ac:ce:32 dev p2p1 self permanent 33:33:00:00:02:02 dev p2p1 self permanent 01:00:5e:00:00:fb dev p2p1 self permanent 33:33:00:00:00:01 dev p7p1 self permanent 01:00:5e:00:00:01 dev p7p1 self permanent 33:33:ff:79:50:53 dev p7p1 self permanent 33:33:00:00:02:02 dev p7p1 self permanent 01:00:5e:00:00:fb dev p7p1 self permanent f2:46:50:85:6d:d9 dev dummy0 master br0 permanent f2:46:50:85:6d:d9 dev dummy0 vlan 1 master br0 permanent 33:33:00:00:00:01 dev dummy0 self permanent f1:f2:f3:f4:f5:f6 dev dummy0 self permanent 33:33:00:00:00:01 dev br0 self permanent 02:00:00:12:01:04 dev br0 vlan 1 master br0 permanent 02:00:00:12:01:04 dev br0 master br0 permanent [root@localhost bridge]# # filter by bridge [root@localhost bridge]# ./bridge fdb show br br0 f2:46:50:85:6d:d9 dev dummy0 master br0 permanent f2:46:50:85:6d:d9 dev dummy0 vlan 1 master br0 permanent 33:33:00:00:00:01 dev dummy0 self permanent f1:f2:f3:f4:f5:f6 dev dummy0 self permanent 33:33:00:00:00:01 dev br0 self permanent 02:00:00:12:01:04 dev br0 vlan 1 master br0 permanent 02:00:00:12:01:04 dev br0 master br0 permanent [root@localhost bridge]# # filter by port [root@localhost bridge]# ./bridge fdb show brport dummy0 f2:46:50:85:6d:d9 master br0 permanent f2:46:50:85:6d:d9 vlan 1 master br0 permanent 33:33:00:00:00:01 self permanent f1:f2:f3:f4:f5:f6 self permanent [root@localhost bridge]# # filter by port + bridge [root@localhost bridge]# ./bridge fdb show br br0 brport dummy0 f2:46:50:85:6d:d9 master br0 permanent f2:46:50:85:6d:d9 vlan 1 master br0 permanent 33:33:00:00:00:01 self permanent f1:f2:f3:f4:f5:f6 self permanent [root@localhost bridge]# Signed-off-by: Hubert Sokolowski <hubert.sokolowski@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-05 17:29:21 +00:00
/* !f->dst is a special case for bridge
bridge: netlink dump interface at par with brctl Actually better than brctl showmacs because we can filter by bridge port in the kernel. The current bridge netlink interface doesnt scale when you have many bridges each with large fdbs or even bridges with many bridge ports And now for the science non-fiction novel you have all been waiting for.. //lets see what bridge ports we have root@moja-1:/configs/may30-iprt/bridge# ./bridge link show 8: eth1 state DOWN : <BROADCAST,MULTICAST> mtu 1500 master br0 state disabled priority 32 cost 19 17: sw1-p1 state DOWN : <BROADCAST,NOARP> mtu 1500 master br0 state disabled priority 32 cost 100 // show all.. root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show 33:33:00:00:00:01 dev bond0 self permanent 33:33:00:00:00:01 dev dummy0 self permanent 33:33:00:00:00:01 dev ifb0 self permanent 33:33:00:00:00:01 dev ifb1 self permanent 33:33:00:00:00:01 dev eth0 self permanent 01:00:5e:00:00:01 dev eth0 self permanent 33:33:ff:22:01:01 dev eth0 self permanent 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent 33:33:00:00:00:01 dev gretap0 self permanent da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent //filter by bridge root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br br0 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent // bridge sw1 has no ports attached.. root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br sw1 //filter by port root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show brport eth1 02:00:00:12:01:02 vlan 0 master br0 permanent 00:17:42:8a:b4:05 vlan 0 master br0 permanent 00:17:42:8a:b4:07 self permanent 33:33:00:00:00:01 self permanent // filter by port + bridge root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br br0 brport sw1-p1 da:ac:46:27:d9:53 vlan 0 master br0 permanent 33:33:00:00:00:01 self permanent // for shits and giggles (as they say in New Brunswick), lets // change the mac that br0 uses // Note: a magical fdb entry with no brport is added ... root@moja-1:/configs/may30-iprt/bridge# ip link set dev br0 address 02:00:00:12:01:04 // lets see if we can see the unicorn .. root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show 33:33:00:00:00:01 dev bond0 self permanent 33:33:00:00:00:01 dev dummy0 self permanent 33:33:00:00:00:01 dev ifb0 self permanent 33:33:00:00:00:01 dev ifb1 self permanent 33:33:00:00:00:01 dev eth0 self permanent 01:00:5e:00:00:01 dev eth0 self permanent 33:33:ff:22:01:01 dev eth0 self permanent 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent 33:33:00:00:00:01 dev gretap0 self permanent 02:00:00:12:01:04 dev br0 vlan 0 master br0 permanent <=== there it is da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent //can we see it if we filter by bridge? root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br br0 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent 02:00:00:12:01:04 dev br0 vlan 0 master br0 permanent <=== there it is da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-10 11:01:59 +00:00
* It means the MAC belongs to the bridge
* Therefore need a little more filtering
* we only want to dump the !f->dst case
*/
if (f->dst)
goto skip;
}
net: Do not call ndo_dflt_fdb_dump if ndo_fdb_dump is defined Add checking whether the call to ndo_dflt_fdb_dump is needed. It is not expected to call ndo_dflt_fdb_dump unconditionally by some drivers (i.e. qlcnic or macvlan) that defines own ndo_fdb_dump. Other drivers define own ndo_fdb_dump and don't want ndo_dflt_fdb_dump to be called at all. At the same time it is desirable to call the default dump function on a bridge device. Fix attributes that are passed to dev->netdev_ops->ndo_fdb_dump. Add extra checking in br_fdb_dump to avoid duplicate entries as now filter_dev can be NULL. Following tests for filtering have been performed before the change and after the patch was applied to make sure they are the same and it doesn't break the filtering algorithm. [root@localhost ~]# cd /root/iproute2-3.18.0/bridge [root@localhost bridge]# modprobe dummy [root@localhost bridge]# ./bridge fdb add f1:f2:f3:f4:f5:f6 dev dummy0 [root@localhost bridge]# brctl addbr br0 [root@localhost bridge]# brctl addif br0 dummy0 [root@localhost bridge]# ip link set dev br0 address 02:00:00:12:01:04 [root@localhost bridge]# # show all [root@localhost bridge]# ./bridge fdb show 33:33:00:00:00:01 dev p2p1 self permanent 01:00:5e:00:00:01 dev p2p1 self permanent 33:33:ff:ac:ce:32 dev p2p1 self permanent 33:33:00:00:02:02 dev p2p1 self permanent 01:00:5e:00:00:fb dev p2p1 self permanent 33:33:00:00:00:01 dev p7p1 self permanent 01:00:5e:00:00:01 dev p7p1 self permanent 33:33:ff:79:50:53 dev p7p1 self permanent 33:33:00:00:02:02 dev p7p1 self permanent 01:00:5e:00:00:fb dev p7p1 self permanent f2:46:50:85:6d:d9 dev dummy0 master br0 permanent f2:46:50:85:6d:d9 dev dummy0 vlan 1 master br0 permanent 33:33:00:00:00:01 dev dummy0 self permanent f1:f2:f3:f4:f5:f6 dev dummy0 self permanent 33:33:00:00:00:01 dev br0 self permanent 02:00:00:12:01:04 dev br0 vlan 1 master br0 permanent 02:00:00:12:01:04 dev br0 master br0 permanent [root@localhost bridge]# # filter by bridge [root@localhost bridge]# ./bridge fdb show br br0 f2:46:50:85:6d:d9 dev dummy0 master br0 permanent f2:46:50:85:6d:d9 dev dummy0 vlan 1 master br0 permanent 33:33:00:00:00:01 dev dummy0 self permanent f1:f2:f3:f4:f5:f6 dev dummy0 self permanent 33:33:00:00:00:01 dev br0 self permanent 02:00:00:12:01:04 dev br0 vlan 1 master br0 permanent 02:00:00:12:01:04 dev br0 master br0 permanent [root@localhost bridge]# # filter by port [root@localhost bridge]# ./bridge fdb show brport dummy0 f2:46:50:85:6d:d9 master br0 permanent f2:46:50:85:6d:d9 vlan 1 master br0 permanent 33:33:00:00:00:01 self permanent f1:f2:f3:f4:f5:f6 self permanent [root@localhost bridge]# # filter by port + bridge [root@localhost bridge]# ./bridge fdb show br br0 brport dummy0 f2:46:50:85:6d:d9 master br0 permanent f2:46:50:85:6d:d9 vlan 1 master br0 permanent 33:33:00:00:00:01 self permanent f1:f2:f3:f4:f5:f6 self permanent [root@localhost bridge]# Signed-off-by: Hubert Sokolowski <hubert.sokolowski@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-05 17:29:21 +00:00
if (!filter_dev && f->dst)
goto skip;
err = fdb_fill_info(skb, br, f,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
RTM_NEWNEIGH,
NLM_F_MULTI);
rtnetlink: fdb dump: optimize by saving last interface markers fdb dumps spanning multiple skb's currently restart from the first interface again for every skb. This results in unnecessary iterations on the already visited interfaces and their fdb entries. In large scale setups, we have seen this to slow down fdb dumps considerably. On a system with 30k macs we see fdb dumps spanning across more than 300 skbs. To fix the problem, this patch replaces the existing single fdb marker with three markers: netdev hash entries, netdevs and fdb index to continue where we left off instead of restarting from the first netdev. This is consistent with link dumps. In the process of fixing the performance issue, this patch also re-implements fix done by commit 472681d57a5d ("net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump") (with an internal fix from Wilson Kok) in the following ways: - change ndo_fdb_dump handlers to return error code instead of the last fdb index - use cb->args strictly for dump frag markers and not error codes. This is consistent with other dump functions. Below results were taken on a system with 1000 netdevs and 35085 fdb entries: before patch: $time bridge fdb show | wc -l 15065 real 1m11.791s user 0m0.070s sys 1m8.395s (existing code does not return all macs) after patch: $time bridge fdb show | wc -l 35085 real 0m2.017s user 0m0.113s sys 0m1.942s Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 04:56:45 +00:00
if (err < 0)
goto out;
skip:
rtnetlink: fdb dump: optimize by saving last interface markers fdb dumps spanning multiple skb's currently restart from the first interface again for every skb. This results in unnecessary iterations on the already visited interfaces and their fdb entries. In large scale setups, we have seen this to slow down fdb dumps considerably. On a system with 30k macs we see fdb dumps spanning across more than 300 skbs. To fix the problem, this patch replaces the existing single fdb marker with three markers: netdev hash entries, netdevs and fdb index to continue where we left off instead of restarting from the first netdev. This is consistent with link dumps. In the process of fixing the performance issue, this patch also re-implements fix done by commit 472681d57a5d ("net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump") (with an internal fix from Wilson Kok) in the following ways: - change ndo_fdb_dump handlers to return error code instead of the last fdb index - use cb->args strictly for dump frag markers and not error codes. This is consistent with other dump functions. Below results were taken on a system with 1000 netdevs and 35085 fdb entries: before patch: $time bridge fdb show | wc -l 15065 real 1m11.791s user 0m0.070s sys 1m8.395s (existing code does not return all macs) after patch: $time bridge fdb show | wc -l 35085 real 0m2.017s user 0m0.113s sys 0m1.942s Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 04:56:45 +00:00
*idx += 1;
}
}
net: add generic PF_BRIDGE:RTM_ FDB hooks This adds two new flags NTF_MASTER and NTF_SELF that can now be used to specify where PF_BRIDGE netlink commands should be sent. NTF_MASTER sends the commands to the 'dev->master' device for parsing. Typically this will be the linux net/bridge, or open-vswitch devices. Also without any flags set the command will be handled by the master device as well so that current user space tools continue to work as expected. The NTF_SELF flag will push the PF_BRIDGE commands to the device. In the basic example below the commands are then parsed and programmed in the embedded bridge. Note if both NTF_SELF and NTF_MASTER bits are set then the command will be sent to both 'dev->master' and 'dev' this allows user space to easily keep the embedded bridge and software bridge in sync. There is a slight complication in the case with both flags set when an error occurs. To resolve this the rtnl handler clears the NTF_ flag in the netlink ack to indicate which sets completed successfully. The add/del handlers will abort as soon as any error occurs. To support this new net device ops were added to call into the device and the existing bridging code was refactored to use these. There should be no required changes in user space to support the current bridge behavior. A basic setup with a SR-IOV enabled NIC looks like this, veth0 veth2 | | ------------ | bridge0 | <---- software bridging ------------ / / ethx.y ethx VF PF \ \ <---- propagate FDB entries to HW \ \ -------------------- | Embedded Bridge | <---- hardware offloaded switching -------------------- In this case the embedded bridge must be managed to allow 'veth0' to communicate with 'ethx.y' correctly. At present drivers managing the embedded bridge either send frames onto the network which then get dropped by the switch OR the embedded bridge will flood these frames. With this patch we have a mechanism to manage the embedded bridge correctly from user space. This example is specific to SR-IOV but replacing the VF with another PF or dropping this into the DSA framework generates similar management issues. Examples session using the 'br'[1] tool to add, dump and then delete a mac address with a new "embedded" option and enabled ixgbe driver: # br fdb add 22:35:19:ac:60:59 dev eth3 # br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static #br fdb add 22:35:19:ac:60:59 embedded dev eth3 #br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static eth3 22:35:19:ac:60:59 local embedded #br fdb del 22:35:19:ac:60:59 embedded dev eth3 I added a couple lines to 'br' to set the flags correctly is all. It is my opinion that the merit of this patch is now embedded and SW bridges can both be modeled correctly in user space using very nearly the same message passing. [1] 'br' tool was published as an RFC here and will be renamed 'bridge' http://patchwork.ozlabs.org/patch/117664/ Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for valuable feedback, suggestions, and review. v2: fixed api descriptions and error case with both NTF_SELF and NTF_MASTER set plus updated patch description. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-15 06:43:56 +00:00
out:
rtnetlink: fdb dump: optimize by saving last interface markers fdb dumps spanning multiple skb's currently restart from the first interface again for every skb. This results in unnecessary iterations on the already visited interfaces and their fdb entries. In large scale setups, we have seen this to slow down fdb dumps considerably. On a system with 30k macs we see fdb dumps spanning across more than 300 skbs. To fix the problem, this patch replaces the existing single fdb marker with three markers: netdev hash entries, netdevs and fdb index to continue where we left off instead of restarting from the first netdev. This is consistent with link dumps. In the process of fixing the performance issue, this patch also re-implements fix done by commit 472681d57a5d ("net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump") (with an internal fix from Wilson Kok) in the following ways: - change ndo_fdb_dump handlers to return error code instead of the last fdb index - use cb->args strictly for dump frag markers and not error codes. This is consistent with other dump functions. Below results were taken on a system with 1000 netdevs and 35085 fdb entries: before patch: $time bridge fdb show | wc -l 15065 real 1m11.791s user 0m0.070s sys 1m8.395s (existing code does not return all macs) after patch: $time bridge fdb show | wc -l 35085 real 0m2.017s user 0m0.113s sys 0m1.942s Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 04:56:45 +00:00
return err;
}
/* Update (create or replace) forwarding database entry */
static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
const __u8 *addr, __u16 state, __u16 flags, __u16 vid)
{
struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
struct net_bridge_fdb_entry *fdb;
bool modified = false;
/* If the port cannot learn allow only local and static entries */
if (source && !(state & NUD_PERMANENT) && !(state & NUD_NOARP) &&
!(source->state == BR_STATE_LEARNING ||
source->state == BR_STATE_FORWARDING))
return -EPERM;
if (!source && !(state & NUD_PERMANENT)) {
pr_info("bridge: RTM_NEWNEIGH %s without NUD_PERMANENT\n",
br->dev->name);
return -EINVAL;
}
fdb = br_fdb_find(br, addr, vid);
if (fdb == NULL) {
if (!(flags & NLM_F_CREATE))
return -ENOENT;
bridge: set is_local and is_static before fdb entry is added to the fdb hashtable Problem Description: We can add fdbs pointing to the bridge with NULL ->dst but that has a few race conditions because br_fdb_insert() is used which first creates the fdb and then, after the fdb has been published/linked, sets "is_local" to 1 and in that time frame if a packet arrives for that fdb it may see it as non-local and either do a NULL ptr dereference in br_forward() or attach the fdb to the port where it arrived, and later br_fdb_insert() will make it local thus getting a wrong fdb entry. Call chain br_handle_frame_finish() -> br_forward(): But in br_handle_frame_finish() in order to call br_forward() the dst should not be local i.e. skb != NULL, whenever the dst is found to be local skb is set to NULL so we can't forward it, and here comes the problem since it's running only with RCU when forwarding packets it can see the entry before "is_local" is set to 1 and actually try to dereference NULL. The main issue is that if someone sends a packet to the switch while it's adding the entry which points to the bridge device, it may dereference NULL ptr. This is needed now after we can add fdbs pointing to the bridge. This poses a problem for br_fdb_update() as well, while someone's adding a bridge fdb, but before it has is_local == 1, it might get moved to a port if it comes as a source mac and then it may get its "is_local" set to 1 This patch changes fdb_create to take is_local and is_static as arguments to set these values in the fdb entry before it is added to the hash. Also adds null check for port in br_forward. Fixes: 3741873b4f73 ("bridge: allow adding of fdb entries pointing to the bridge device") Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-27 14:52:56 +00:00
fdb = fdb_create(head, source, addr, vid, 0, 0);
if (!fdb)
return -ENOMEM;
modified = true;
} else {
if (flags & NLM_F_EXCL)
return -EEXIST;
if (fdb->dst != source) {
fdb->dst = source;
modified = true;
}
}
if (fdb_to_nud(br, fdb) != state) {
if (state & NUD_PERMANENT) {
fdb->is_local = 1;
if (!fdb->is_static) {
fdb->is_static = 1;
fdb_add_hw_addr(br, addr);
}
} else if (state & NUD_NOARP) {
fdb->is_local = 0;
if (!fdb->is_static) {
fdb->is_static = 1;
fdb_add_hw_addr(br, addr);
}
} else {
fdb->is_local = 0;
if (fdb->is_static) {
fdb->is_static = 0;
fdb_del_hw_addr(br, addr);
}
}
modified = true;
}
fdb->added_by_user = 1;
fdb->used = jiffies;
if (modified) {
fdb->updated = jiffies;
fdb_notify(br, fdb, RTM_NEWNEIGH);
}
return 0;
}
static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br,
struct net_bridge_port *p, const unsigned char *addr,
u16 nlh_flags, u16 vid)
{
int err = 0;
if (ndm->ndm_flags & NTF_USE) {
if (!p) {
pr_info("bridge: RTM_NEWNEIGH %s with NTF_USE is not supported\n",
br->dev->name);
return -EINVAL;
}
local_bh_disable();
rcu_read_lock();
br_fdb_update(br, p, addr, vid, true);
rcu_read_unlock();
local_bh_enable();
} else if (ndm->ndm_flags & NTF_EXT_LEARNED) {
err = br_fdb_external_learn_add(br, p, addr, vid);
} else {
spin_lock_bh(&br->hash_lock);
err = fdb_add_entry(br, p, addr, ndm->ndm_state,
nlh_flags, vid);
spin_unlock_bh(&br->hash_lock);
}
return err;
}
/* Add new permanent fdb entry with RTM_NEWNEIGH */
int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid, u16 nlh_flags)
{
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan_group *vg;
struct net_bridge_port *p = NULL;
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan *v;
struct net_bridge *br = NULL;
net: add generic PF_BRIDGE:RTM_ FDB hooks This adds two new flags NTF_MASTER and NTF_SELF that can now be used to specify where PF_BRIDGE netlink commands should be sent. NTF_MASTER sends the commands to the 'dev->master' device for parsing. Typically this will be the linux net/bridge, or open-vswitch devices. Also without any flags set the command will be handled by the master device as well so that current user space tools continue to work as expected. The NTF_SELF flag will push the PF_BRIDGE commands to the device. In the basic example below the commands are then parsed and programmed in the embedded bridge. Note if both NTF_SELF and NTF_MASTER bits are set then the command will be sent to both 'dev->master' and 'dev' this allows user space to easily keep the embedded bridge and software bridge in sync. There is a slight complication in the case with both flags set when an error occurs. To resolve this the rtnl handler clears the NTF_ flag in the netlink ack to indicate which sets completed successfully. The add/del handlers will abort as soon as any error occurs. To support this new net device ops were added to call into the device and the existing bridging code was refactored to use these. There should be no required changes in user space to support the current bridge behavior. A basic setup with a SR-IOV enabled NIC looks like this, veth0 veth2 | | ------------ | bridge0 | <---- software bridging ------------ / / ethx.y ethx VF PF \ \ <---- propagate FDB entries to HW \ \ -------------------- | Embedded Bridge | <---- hardware offloaded switching -------------------- In this case the embedded bridge must be managed to allow 'veth0' to communicate with 'ethx.y' correctly. At present drivers managing the embedded bridge either send frames onto the network which then get dropped by the switch OR the embedded bridge will flood these frames. With this patch we have a mechanism to manage the embedded bridge correctly from user space. This example is specific to SR-IOV but replacing the VF with another PF or dropping this into the DSA framework generates similar management issues. Examples session using the 'br'[1] tool to add, dump and then delete a mac address with a new "embedded" option and enabled ixgbe driver: # br fdb add 22:35:19:ac:60:59 dev eth3 # br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static #br fdb add 22:35:19:ac:60:59 embedded dev eth3 #br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static eth3 22:35:19:ac:60:59 local embedded #br fdb del 22:35:19:ac:60:59 embedded dev eth3 I added a couple lines to 'br' to set the flags correctly is all. It is my opinion that the merit of this patch is now embedded and SW bridges can both be modeled correctly in user space using very nearly the same message passing. [1] 'br' tool was published as an RFC here and will be renamed 'bridge' http://patchwork.ozlabs.org/patch/117664/ Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for valuable feedback, suggestions, and review. v2: fixed api descriptions and error case with both NTF_SELF and NTF_MASTER set plus updated patch description. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-15 06:43:56 +00:00
int err = 0;
if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) {
pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state);
return -EINVAL;
}
if (is_zero_ether_addr(addr)) {
pr_info("bridge: RTM_NEWNEIGH with invalid ether address\n");
return -EINVAL;
}
if (dev->priv_flags & IFF_EBRIDGE) {
br = netdev_priv(dev);
vg = br_vlan_group(br);
} else {
p = br_port_get_rtnl(dev);
if (!p) {
pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n",
dev->name);
return -EINVAL;
}
br = p->br;
vg = nbp_vlan_group(p);
}
if (vid) {
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
v = br_vlan_find(vg, vid);
if (!v || !br_vlan_should_use(v)) {
pr_info("bridge: RTM_NEWNEIGH with unconfigured vlan %d on %s\n", vid, dev->name);
return -EINVAL;
}
/* VID was specified, so use it. */
err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid);
} else {
err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0);
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
if (err || !vg || !vg->num_vlans)
goto out;
/* We have vlans configured on this port and user didn't
* specify a VLAN. To be nice, add/update entry for every
* vlan on this port.
*/
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
list_for_each_entry(v, &vg->vlan_list, vlist) {
if (!br_vlan_should_use(v))
continue;
err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid);
if (err)
goto out;
}
}
out:
return err;
}
static int fdb_delete_by_addr_and_port(struct net_bridge *br,
const struct net_bridge_port *p,
const u8 *addr, u16 vlan)
{
struct net_bridge_fdb_entry *fdb;
fdb = br_fdb_find(br, addr, vlan);
if (!fdb || fdb->dst != p)
return -ENOENT;
fdb_delete(br, fdb);
return 0;
}
static int __br_fdb_delete(struct net_bridge *br,
const struct net_bridge_port *p,
const unsigned char *addr, u16 vid)
{
int err;
spin_lock_bh(&br->hash_lock);
err = fdb_delete_by_addr_and_port(br, p, addr, vid);
spin_unlock_bh(&br->hash_lock);
return err;
}
/* Remove neighbor entry with RTM_DELNEIGH */
int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid)
{
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan_group *vg;
struct net_bridge_port *p = NULL;
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
struct net_bridge_vlan *v;
struct net_bridge *br;
int err;
if (dev->priv_flags & IFF_EBRIDGE) {
br = netdev_priv(dev);
vg = br_vlan_group(br);
} else {
p = br_port_get_rtnl(dev);
if (!p) {
pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n",
dev->name);
return -EINVAL;
}
vg = nbp_vlan_group(p);
br = p->br;
}
if (vid) {
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
v = br_vlan_find(vg, vid);
if (!v) {
pr_info("bridge: RTM_DELNEIGH with unconfigured vlan %d on %s\n", vid, dev->name);
return -EINVAL;
}
err = __br_fdb_delete(br, p, addr, vid);
} else {
err = -ENOENT;
err &= __br_fdb_delete(br, p, addr, 0);
bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 17:00:11 +00:00
if (!vg || !vg->num_vlans)
return err;
list_for_each_entry(v, &vg->vlan_list, vlist) {
if (!br_vlan_should_use(v))
continue;
err &= __br_fdb_delete(br, p, addr, v->vid);
}
}
return err;
}
int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p)
{
struct net_bridge_fdb_entry *fdb, *tmp;
int i;
int err;
ASSERT_RTNL();
for (i = 0; i < BR_HASH_SIZE; i++) {
hlist_for_each_entry(fdb, &br->hash[i], hlist) {
/* We only care for static entries */
if (!fdb->is_static)
continue;
err = dev_uc_add(p->dev, fdb->addr.addr);
if (err)
goto rollback;
}
}
return 0;
rollback:
for (i = 0; i < BR_HASH_SIZE; i++) {
hlist_for_each_entry(tmp, &br->hash[i], hlist) {
/* If we reached the fdb that failed, we can stop */
if (tmp == fdb)
break;
/* We only care for static entries */
if (!tmp->is_static)
continue;
dev_uc_del(p->dev, tmp->addr.addr);
}
}
return err;
}
void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p)
{
struct net_bridge_fdb_entry *fdb;
int i;
ASSERT_RTNL();
for (i = 0; i < BR_HASH_SIZE; i++) {
hlist_for_each_entry_rcu(fdb, &br->hash[i], hlist) {
/* We only care for static entries */
if (!fdb->is_static)
continue;
dev_uc_del(p->dev, fdb->addr.addr);
}
}
}
int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
const unsigned char *addr, u16 vid)
{
struct hlist_head *head;
struct net_bridge_fdb_entry *fdb;
int err = 0;
spin_lock_bh(&br->hash_lock);
head = &br->hash[br_mac_hash(addr, vid)];
fdb = br_fdb_find(br, addr, vid);
if (!fdb) {
bridge: set is_local and is_static before fdb entry is added to the fdb hashtable Problem Description: We can add fdbs pointing to the bridge with NULL ->dst but that has a few race conditions because br_fdb_insert() is used which first creates the fdb and then, after the fdb has been published/linked, sets "is_local" to 1 and in that time frame if a packet arrives for that fdb it may see it as non-local and either do a NULL ptr dereference in br_forward() or attach the fdb to the port where it arrived, and later br_fdb_insert() will make it local thus getting a wrong fdb entry. Call chain br_handle_frame_finish() -> br_forward(): But in br_handle_frame_finish() in order to call br_forward() the dst should not be local i.e. skb != NULL, whenever the dst is found to be local skb is set to NULL so we can't forward it, and here comes the problem since it's running only with RCU when forwarding packets it can see the entry before "is_local" is set to 1 and actually try to dereference NULL. The main issue is that if someone sends a packet to the switch while it's adding the entry which points to the bridge device, it may dereference NULL ptr. This is needed now after we can add fdbs pointing to the bridge. This poses a problem for br_fdb_update() as well, while someone's adding a bridge fdb, but before it has is_local == 1, it might get moved to a port if it comes as a source mac and then it may get its "is_local" set to 1 This patch changes fdb_create to take is_local and is_static as arguments to set these values in the fdb entry before it is added to the hash. Also adds null check for port in br_forward. Fixes: 3741873b4f73 ("bridge: allow adding of fdb entries pointing to the bridge device") Reported-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-27 14:52:56 +00:00
fdb = fdb_create(head, p, addr, vid, 0, 0);
if (!fdb) {
err = -ENOMEM;
goto err_unlock;
}
fdb->added_by_external_learn = 1;
fdb_notify(br, fdb, RTM_NEWNEIGH);
} else if (fdb->added_by_external_learn) {
/* Refresh entry */
fdb->updated = fdb->used = jiffies;
} else if (!fdb->added_by_user) {
/* Take over SW learned entry */
fdb->added_by_external_learn = 1;
fdb->updated = jiffies;
fdb_notify(br, fdb, RTM_NEWNEIGH);
}
err_unlock:
spin_unlock_bh(&br->hash_lock);
return err;
}
int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
const unsigned char *addr, u16 vid)
{
struct net_bridge_fdb_entry *fdb;
int err = 0;
spin_lock_bh(&br->hash_lock);
fdb = br_fdb_find(br, addr, vid);
if (fdb && fdb->added_by_external_learn)
fdb_delete(br, fdb);
else
err = -ENOENT;
spin_unlock_bh(&br->hash_lock);
return err;
}
void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p,
const unsigned char *addr, u16 vid)
{
struct net_bridge_fdb_entry *fdb;
spin_lock_bh(&br->hash_lock);
fdb = br_fdb_find(br, addr, vid);
if (fdb)
fdb->offloaded = 1;
spin_unlock_bh(&br->hash_lock);
}