linux/net/bridge/br_netlink.c

1622 lines
45 KiB
C
Raw Normal View History

/*
* Bridge netlink control interface
*
* Authors:
* Stephen Hemminger <shemminger@osdl.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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/etherdevice.h>
#include <net/rtnetlink.h>
[NET]: Make the device list and device lookups per namespace. This patch makes most of the generic device layer network namespace safe. This patch makes dev_base_head a network namespace variable, and then it picks up a few associated variables. The functions: dev_getbyhwaddr dev_getfirsthwbytype dev_get_by_flags dev_get_by_name __dev_get_by_name dev_get_by_index __dev_get_by_index dev_ioctl dev_ethtool dev_load wireless_process_ioctl were modified to take a network namespace argument, and deal with it. vlan_ioctl_set and brioctl_set were modified so their hooks will receive a network namespace argument. So basically anthing in the core of the network stack that was affected to by the change of dev_base was modified to handle multiple network namespaces. The rest of the network stack was simply modified to explicitly use &init_net the initial network namespace. This can be fixed when those components of the network stack are modified to handle multiple network namespaces. For now the ifindex generator is left global. Fundametally ifindex numbers are per namespace, or else we will have corner case problems with migration when we get that far. At the same time there are assumptions in the network stack that the ifindex of a network device won't change. Making the ifindex number global seems a good compromise until the network stack can cope with ifindex changes when you change namespaces, and the like. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-09-18 02:56:21 +08:00
#include <net/net_namespace.h>
#include <net/sock.h>
#include <uapi/linux/if_bridge.h>
#include "br_private.h"
#include "br_private_stp.h"
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
#include "br_private_tunnel.h"
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>
2015-09-26 01:00:11 +08:00
static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg,
u32 filter_mask)
{
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>
2015-09-26 01:00:11 +08:00
struct net_bridge_vlan *v;
u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0;
u16 flags, pvid;
int num_vlans = 0;
if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED))
return 0;
pvid = br_get_pvid(vg);
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>
2015-09-26 01:00:11 +08:00
/* Count number of vlan infos */
list_for_each_entry_rcu(v, &vg->vlan_list, vlist) {
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>
2015-09-26 01:00:11 +08:00
/* only a context, bridge vlan not activated */
if (!br_vlan_should_use(v))
continue;
if (v->vid == pvid)
flags |= BRIDGE_VLAN_INFO_PVID;
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>
2015-09-26 01:00:11 +08:00
if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)
flags |= BRIDGE_VLAN_INFO_UNTAGGED;
if (vid_range_start == 0) {
goto initvars;
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>
2015-09-26 01:00:11 +08:00
} else if ((v->vid - vid_range_end) == 1 &&
flags == vid_range_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>
2015-09-26 01:00:11 +08:00
vid_range_end = v->vid;
continue;
} else {
if ((vid_range_end - vid_range_start) > 0)
num_vlans += 2;
else
num_vlans += 1;
}
initvars:
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>
2015-09-26 01:00:11 +08:00
vid_range_start = v->vid;
vid_range_end = v->vid;
vid_range_flags = flags;
}
if (vid_range_start != 0) {
if ((vid_range_end - vid_range_start) > 0)
num_vlans += 2;
else
num_vlans += 1;
}
return num_vlans;
}
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>
2015-09-26 01:00:11 +08:00
static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg,
u32 filter_mask)
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>
2015-09-26 01:00:11 +08:00
{
int num_vlans;
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>
2015-09-26 01:00:11 +08:00
if (!vg)
return 0;
if (filter_mask & RTEXT_FILTER_BRVLAN)
return vg->num_vlans;
rcu_read_lock();
num_vlans = __get_num_vlan_infos(vg, filter_mask);
rcu_read_unlock();
return num_vlans;
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>
2015-09-26 01:00:11 +08:00
}
static size_t br_get_link_af_size_filtered(const struct net_device *dev,
u32 filter_mask)
{
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>
2015-09-26 01:00:11 +08:00
struct net_bridge_vlan_group *vg = NULL;
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
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>
2015-09-26 01:00:11 +08:00
struct net_bridge *br;
int num_vlan_infos;
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
size_t vinfo_sz = 0;
rcu_read_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>
2015-09-26 01:00:11 +08:00
if (br_port_exists(dev)) {
p = br_port_get_rcu(dev);
vg = nbp_vlan_group_rcu(p);
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>
2015-09-26 01:00:11 +08:00
} else if (dev->priv_flags & IFF_EBRIDGE) {
br = netdev_priv(dev);
vg = br_vlan_group_rcu(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>
2015-09-26 01:00:11 +08:00
}
num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask);
rcu_read_unlock();
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
if (p && (p->flags & BR_VLAN_TUNNEL))
vinfo_sz += br_get_vlan_tunnel_info_size(vg);
/* Each VLAN is returned in bridge_vlan_info along with flags */
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info));
return vinfo_sz;
}
static inline size_t br_port_info_size(void)
{
return nla_total_size(1) /* IFLA_BRPORT_STATE */
+ nla_total_size(2) /* IFLA_BRPORT_PRIORITY */
+ nla_total_size(4) /* IFLA_BRPORT_COST */
+ nla_total_size(1) /* IFLA_BRPORT_MODE */
+ nla_total_size(1) /* IFLA_BRPORT_GUARD */
+ nla_total_size(1) /* IFLA_BRPORT_PROTECT */
+ nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */
+ nla_total_size(1) /* IFLA_BRPORT_MCAST_TO_UCAST */
+ nla_total_size(1) /* IFLA_BRPORT_LEARNING */
+ nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */
+ nla_total_size(1) /* IFLA_BRPORT_MCAST_FLOOD */
+ nla_total_size(1) /* IFLA_BRPORT_BCAST_FLOOD */
+ nla_total_size(1) /* IFLA_BRPORT_PROXYARP */
+ nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
+ nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */
+ nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */
+ nla_total_size(1) /* IFLA_BRPORT_ISOLATED */
+ nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */
+ nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */
+ nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */
+ nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */
+ nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */
+ nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */
+ nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */
+ nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */
+ nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */
+ nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */
+ nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */
#endif
+ nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */
+ 0;
}
static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask)
{
return NLMSG_ALIGN(sizeof(struct ifinfomsg))
+ nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
+ nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */
+ nla_total_size(4) /* IFLA_MASTER */
+ nla_total_size(4) /* IFLA_MTU */
+ nla_total_size(4) /* IFLA_LINK */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */
+ nla_total_size(br_get_link_af_size_filtered(dev,
filter_mask)); /* IFLA_AF_SPEC */
}
static int br_port_fill_attrs(struct sk_buff *skb,
const struct net_bridge_port *p)
{
u8 mode = !!(p->flags & BR_HAIRPIN_MODE);
u64 timerval;
if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) ||
nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) ||
nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) ||
nla_put_u8(skb, IFLA_BRPORT_MODE, mode) ||
nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) ||
nla_put_u8(skb, IFLA_BRPORT_PROTECT,
!!(p->flags & BR_ROOT_BLOCK)) ||
nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE,
!!(p->flags & BR_MULTICAST_FAST_LEAVE)) ||
nla_put_u8(skb, IFLA_BRPORT_MCAST_TO_UCAST,
!!(p->flags & BR_MULTICAST_TO_UNICAST)) ||
nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) ||
nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD,
!!(p->flags & BR_FLOOD)) ||
nla_put_u8(skb, IFLA_BRPORT_MCAST_FLOOD,
!!(p->flags & BR_MCAST_FLOOD)) ||
nla_put_u8(skb, IFLA_BRPORT_BCAST_FLOOD,
!!(p->flags & BR_BCAST_FLOOD)) ||
nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) ||
nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI,
!!(p->flags & BR_PROXYARP_WIFI)) ||
nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id),
&p->designated_root) ||
nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id),
&p->designated_bridge) ||
nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) ||
nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost) ||
nla_put_u16(skb, IFLA_BRPORT_ID, p->port_id) ||
nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no) ||
nla_put_u8(skb, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK,
p->topology_change_ack) ||
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) ||
nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags &
BR_VLAN_TUNNEL)) ||
nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) ||
nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS,
!!(p->flags & BR_NEIGH_SUPPRESS)) ||
nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED)))
return -EMSGSIZE;
timerval = br_timer_value(&p->message_age_timer);
if (nla_put_u64_64bit(skb, IFLA_BRPORT_MESSAGE_AGE_TIMER, timerval,
IFLA_BRPORT_PAD))
return -EMSGSIZE;
timerval = br_timer_value(&p->forward_delay_timer);
if (nla_put_u64_64bit(skb, IFLA_BRPORT_FORWARD_DELAY_TIMER, timerval,
IFLA_BRPORT_PAD))
return -EMSGSIZE;
timerval = br_timer_value(&p->hold_timer);
if (nla_put_u64_64bit(skb, IFLA_BRPORT_HOLD_TIMER, timerval,
IFLA_BRPORT_PAD))
return -EMSGSIZE;
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER,
p->multicast_router))
return -EMSGSIZE;
#endif
return 0;
}
static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start,
u16 vid_end, u16 flags)
{
struct bridge_vlan_info vinfo;
if ((vid_end - vid_start) > 0) {
/* add range to skb */
vinfo.vid = vid_start;
vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_BEGIN;
if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO,
sizeof(vinfo), &vinfo))
goto nla_put_failure;
vinfo.vid = vid_end;
vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END;
if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO,
sizeof(vinfo), &vinfo))
goto nla_put_failure;
} else {
vinfo.vid = vid_start;
vinfo.flags = flags;
if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO,
sizeof(vinfo), &vinfo))
goto nla_put_failure;
}
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb,
struct net_bridge_vlan_group *vg)
{
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>
2015-09-26 01:00:11 +08:00
struct net_bridge_vlan *v;
u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0;
u16 flags, pvid;
int err = 0;
/* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan
* and mark vlan info with begin and end flags
* if vlaninfo represents a range
*/
pvid = br_get_pvid(vg);
list_for_each_entry_rcu(v, &vg->vlan_list, vlist) {
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>
2015-09-26 01:00:11 +08:00
if (!br_vlan_should_use(v))
continue;
if (v->vid == pvid)
flags |= BRIDGE_VLAN_INFO_PVID;
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>
2015-09-26 01:00:11 +08:00
if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)
flags |= BRIDGE_VLAN_INFO_UNTAGGED;
if (vid_range_start == 0) {
goto initvars;
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>
2015-09-26 01:00:11 +08:00
} else if ((v->vid - vid_range_end) == 1 &&
flags == vid_range_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>
2015-09-26 01:00:11 +08:00
vid_range_end = v->vid;
continue;
} else {
err = br_fill_ifvlaninfo_range(skb, vid_range_start,
vid_range_end,
vid_range_flags);
if (err)
return err;
}
initvars:
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>
2015-09-26 01:00:11 +08:00
vid_range_start = v->vid;
vid_range_end = v->vid;
vid_range_flags = flags;
}
if (vid_range_start != 0) {
/* Call it once more to send any left over vlans */
err = br_fill_ifvlaninfo_range(skb, vid_range_start,
vid_range_end,
vid_range_flags);
if (err)
return err;
}
return 0;
}
static int br_fill_ifvlaninfo(struct sk_buff *skb,
struct net_bridge_vlan_group *vg)
{
struct bridge_vlan_info vinfo;
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>
2015-09-26 01:00:11 +08:00
struct net_bridge_vlan *v;
u16 pvid;
pvid = br_get_pvid(vg);
list_for_each_entry_rcu(v, &vg->vlan_list, vlist) {
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>
2015-09-26 01:00:11 +08:00
if (!br_vlan_should_use(v))
continue;
vinfo.vid = v->vid;
vinfo.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>
2015-09-26 01:00:11 +08:00
if (v->vid == pvid)
vinfo.flags |= BRIDGE_VLAN_INFO_PVID;
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>
2015-09-26 01:00:11 +08:00
if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)
vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED;
if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO,
sizeof(vinfo), &vinfo))
goto nla_put_failure;
}
return 0;
nla_put_failure:
return -EMSGSIZE;
}
/*
* Create one netlink message for one interface
* Contains port and master info as well as carrier and bridge state.
*/
static int br_fill_ifinfo(struct sk_buff *skb,
const struct net_bridge_port *port,
u32 pid, u32 seq, int event, unsigned int flags,
u32 filter_mask, const struct net_device *dev)
{
u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
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>
2015-09-26 01:00:11 +08:00
struct net_bridge *br;
struct ifinfomsg *hdr;
struct nlmsghdr *nlh;
if (port)
br = port->br;
else
br = netdev_priv(dev);
br_debug(br, "br_fill_info event %d port %s master %s\n",
event, dev->name, br->dev->name);
nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags);
if (nlh == NULL)
return -EMSGSIZE;
hdr = nlmsg_data(nlh);
hdr->ifi_family = AF_BRIDGE;
hdr->__ifi_pad = 0;
hdr->ifi_type = dev->type;
hdr->ifi_index = dev->ifindex;
hdr->ifi_flags = dev_get_flags(dev);
hdr->ifi_change = 0;
if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
nla_put_u32(skb, IFLA_MASTER, br->dev->ifindex) ||
nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
nla_put_u8(skb, IFLA_OPERSTATE, operstate) ||
(dev->addr_len &&
nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) ||
(dev->ifindex != dev_get_iflink(dev) &&
nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))))
goto nla_put_failure;
if (event == RTM_NEWLINK && port) {
struct nlattr *nest
= nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED);
if (nest == NULL || br_port_fill_attrs(skb, port) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
}
/* Check if the VID information is requested */
if ((filter_mask & RTEXT_FILTER_BRVLAN) ||
(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) {
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>
2015-09-26 01:00:11 +08:00
struct net_bridge_vlan_group *vg;
struct nlattr *af;
int err;
/* RCU needed because of the VLAN locking rules (rcu || rtnl) */
rcu_read_lock();
if (port)
vg = nbp_vlan_group_rcu(port);
else
vg = br_vlan_group_rcu(br);
if (!vg || !vg->num_vlans) {
rcu_read_unlock();
goto done;
}
af = nla_nest_start(skb, IFLA_AF_SPEC);
if (!af) {
rcu_read_unlock();
goto nla_put_failure;
}
if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)
err = br_fill_ifvlaninfo_compressed(skb, vg);
else
err = br_fill_ifvlaninfo(skb, vg);
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
if (port && (port->flags & BR_VLAN_TUNNEL))
err = br_fill_vlan_tunnel_info(skb, vg);
rcu_read_unlock();
if (err)
goto nla_put_failure;
nla_nest_end(skb, af);
}
done:
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>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
/* Notify listeners of a change in bridge or port information */
void br_ifinfo_notify(int event, const struct net_bridge *br,
const struct net_bridge_port *port)
{
u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
struct net_device *dev;
struct sk_buff *skb;
int err = -ENOBUFS;
struct net *net;
u16 port_no = 0;
if (WARN_ON(!port && !br))
return;
if (port) {
dev = port->dev;
br = port->br;
port_no = port->port_no;
} else {
dev = br->dev;
}
net = dev_net(dev);
br_debug(br, "port %u(%s) event %d\n", port_no, dev->name, event);
skb = nlmsg_new(br_nlmsg_size(dev, filter), GFP_ATOMIC);
if (skb == NULL)
goto errout;
err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev);
if (err < 0) {
/* -EMSGSIZE implies BUG in br_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
2009-02-25 15:18:28 +08:00
rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
return;
errout:
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
}
/*
* Dump information about all ports, in response to GETLINK
*/
int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
struct net_device *dev, u32 filter_mask, int nlflags)
{
struct net_bridge_port *port = br_port_get_rtnl(dev);
if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) &&
!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED))
return 0;
return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags,
filter_mask, dev);
}
static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
int cmd, struct bridge_vlan_info *vinfo, bool *changed)
{
bool curr_change;
int err = 0;
switch (cmd) {
case RTM_SETLINK:
if (p) {
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>
2015-09-26 01:00:11 +08:00
/* if the MASTER flag is set this will act on the global
* per-VLAN entry as well
*/
err = nbp_vlan_add(p, vinfo->vid, vinfo->flags,
&curr_change);
} else {
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>
2015-09-26 01:00:11 +08:00
vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY;
err = br_vlan_add(br, vinfo->vid, vinfo->flags,
&curr_change);
}
if (curr_change)
*changed = true;
break;
case RTM_DELLINK:
if (p) {
if (!nbp_vlan_delete(p, vinfo->vid))
*changed = true;
if ((vinfo->flags & BRIDGE_VLAN_INFO_MASTER) &&
!br_vlan_delete(p->br, vinfo->vid))
*changed = true;
} else if (!br_vlan_delete(br, vinfo->vid)) {
*changed = true;
}
break;
}
return err;
}
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
static int br_process_vlan_info(struct net_bridge *br,
struct net_bridge_port *p, int cmd,
struct bridge_vlan_info *vinfo_curr,
struct bridge_vlan_info **vinfo_last,
bool *changed)
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
{
if (!vinfo_curr->vid || vinfo_curr->vid >= VLAN_VID_MASK)
return -EINVAL;
if (vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
/* check if we are already processing a range */
if (*vinfo_last)
return -EINVAL;
*vinfo_last = vinfo_curr;
/* don't allow range of pvids */
if ((*vinfo_last)->flags & BRIDGE_VLAN_INFO_PVID)
return -EINVAL;
return 0;
}
if (*vinfo_last) {
struct bridge_vlan_info tmp_vinfo;
int v, err;
if (!(vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_END))
return -EINVAL;
if (vinfo_curr->vid <= (*vinfo_last)->vid)
return -EINVAL;
memcpy(&tmp_vinfo, *vinfo_last,
sizeof(struct bridge_vlan_info));
for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) {
tmp_vinfo.vid = v;
err = br_vlan_info(br, p, cmd, &tmp_vinfo, changed);
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
if (err)
break;
}
*vinfo_last = NULL;
return err;
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
}
return br_vlan_info(br, p, cmd, vinfo_curr, changed);
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
}
static int br_afspec(struct net_bridge *br,
struct net_bridge_port *p,
struct nlattr *af_spec,
int cmd, bool *changed)
{
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
struct bridge_vlan_info *vinfo_curr = NULL;
struct bridge_vlan_info *vinfo_last = NULL;
struct nlattr *attr;
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
struct vtunnel_info tinfo_last = {};
struct vtunnel_info tinfo_curr = {};
int err = 0, rem;
nla_for_each_nested(attr, af_spec, rem) {
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
err = 0;
switch (nla_type(attr)) {
case IFLA_BRIDGE_VLAN_TUNNEL_INFO:
if (!p || !(p->flags & BR_VLAN_TUNNEL))
return -EINVAL;
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
err = br_parse_vlan_tunnel_info(attr, &tinfo_curr);
if (err)
return err;
err = br_process_vlan_tunnel_info(br, p, cmd,
&tinfo_curr,
&tinfo_last,
changed);
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
if (err)
return err;
break;
case IFLA_BRIDGE_VLAN_INFO:
if (nla_len(attr) != sizeof(struct bridge_vlan_info))
return -EINVAL;
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
vinfo_curr = nla_data(attr);
err = br_process_vlan_info(br, p, cmd, vinfo_curr,
&vinfo_last, changed);
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
if (err)
return err;
break;
}
}
return err;
}
static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
[IFLA_BRPORT_STATE] = { .type = NLA_U8 },
[IFLA_BRPORT_COST] = { .type = NLA_U32 },
[IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 },
[IFLA_BRPORT_MODE] = { .type = NLA_U8 },
[IFLA_BRPORT_GUARD] = { .type = NLA_U8 },
[IFLA_BRPORT_PROTECT] = { .type = NLA_U8 },
[IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 },
[IFLA_BRPORT_LEARNING] = { .type = NLA_U8 },
[IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 },
[IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 },
[IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 },
[IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 },
[IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 },
[IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 },
[IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 },
[IFLA_BRPORT_VLAN_TUNNEL] = { .type = NLA_U8 },
[IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 },
[IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 },
[IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 },
};
/* Change the state of the port and notify spanning tree */
static int br_set_port_state(struct net_bridge_port *p, u8 state)
{
if (state > BR_STATE_BLOCKING)
return -EINVAL;
/* if kernel STP is running, don't allow changes */
if (p->br->stp_enabled == BR_KERNEL_STP)
return -EBUSY;
/* if device is not up, change is not allowed
* if link is not present, only allowable state is disabled
*/
if (!netif_running(p->dev) ||
(!netif_oper_up(p->dev) && state != BR_STATE_DISABLED))
return -ENETDOWN;
br_set_state(p, state);
br_port_state_selection(p->br);
return 0;
}
/* Set/clear or port flags based on attribute */
static int br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[],
int attrtype, unsigned long mask)
{
unsigned long flags;
int err;
if (!tb[attrtype])
return 0;
if (nla_get_u8(tb[attrtype]))
flags = p->flags | mask;
else
flags = p->flags & ~mask;
err = br_switchdev_set_port_flag(p, flags, mask);
if (err)
return err;
p->flags = flags;
return 0;
}
/* Process bridge protocol info on port */
static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
{
unsigned long old_flags = p->flags;
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
bool br_vlan_tunnel_old = false;
int err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
if (err)
return err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD);
if (err)
return err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE);
if (err)
return err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK);
if (err)
return err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING);
if (err)
return err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD);
if (err)
return err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD);
if (err)
return err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST);
if (err)
return err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD);
if (err)
return err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP);
if (err)
return err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI);
if (err)
return err;
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
br_vlan_tunnel_old = (p->flags & BR_VLAN_TUNNEL) ? true : false;
err = br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL);
if (err)
return err;
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
if (br_vlan_tunnel_old && !(p->flags & BR_VLAN_TUNNEL))
nbp_vlan_tunnel_info_flush(p);
if (tb[IFLA_BRPORT_COST]) {
err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST]));
if (err)
return err;
}
if (tb[IFLA_BRPORT_PRIORITY]) {
err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY]));
if (err)
return err;
}
if (tb[IFLA_BRPORT_STATE]) {
err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE]));
if (err)
return err;
}
if (tb[IFLA_BRPORT_FLUSH])
br_fdb_delete_by_port(p->br, p, 0, 0);
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
if (tb[IFLA_BRPORT_MULTICAST_ROUTER]) {
u8 mcast_router = nla_get_u8(tb[IFLA_BRPORT_MULTICAST_ROUTER]);
err = br_multicast_set_port_router(p, mcast_router);
if (err)
return err;
}
#endif
if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) {
u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]);
if (fwd_mask & BR_GROUPFWD_MACPAUSE)
return -EINVAL;
p->group_fwd_mask = fwd_mask;
}
err = br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS,
BR_NEIGH_SUPPRESS);
if (err)
return err;
err = br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED);
if (err)
return err;
br_port_flags_change(p, old_flags ^ p->flags);
return 0;
}
/* Change state and parameters on port. */
int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
{
struct net_bridge *br = (struct net_bridge *)netdev_priv(dev);
struct nlattr *tb[IFLA_BRPORT_MAX + 1];
struct net_bridge_port *p;
struct nlattr *protinfo;
struct nlattr *afspec;
bool changed = false;
int err = 0;
protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO);
afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
if (!protinfo && !afspec)
return 0;
p = br_port_get_rtnl(dev);
/* We want to accept dev as bridge itself if the AF_SPEC
* is set to see if someone is setting vlan info on the bridge
*/
if (!p && !afspec)
return -EINVAL;
if (p && protinfo) {
if (protinfo->nla_type & NLA_F_NESTED) {
err = nla_parse_nested(tb, IFLA_BRPORT_MAX, protinfo,
br_port_policy, NULL);
if (err)
return err;
spin_lock_bh(&p->br->lock);
err = br_setport(p, tb);
spin_unlock_bh(&p->br->lock);
} else {
/* Binary compatibility with old RSTP */
if (nla_len(protinfo) < sizeof(u8))
return -EINVAL;
spin_lock_bh(&p->br->lock);
err = br_set_port_state(p, nla_get_u8(protinfo));
spin_unlock_bh(&p->br->lock);
}
if (err)
goto out;
changed = true;
}
if (afspec)
err = br_afspec(br, p, afspec, RTM_SETLINK, &changed);
if (changed)
br_ifinfo_notify(RTM_NEWLINK, br, p);
out:
return err;
}
/* Delete port information */
int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
{
struct net_bridge *br = (struct net_bridge *)netdev_priv(dev);
struct net_bridge_port *p;
struct nlattr *afspec;
bool changed = false;
int err = 0;
afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
if (!afspec)
return 0;
p = br_port_get_rtnl(dev);
/* We want to accept dev as bridge itself as well */
if (!p && !(dev->priv_flags & IFF_EBRIDGE))
return -EINVAL;
err = br_afspec(br, p, afspec, RTM_DELLINK, &changed);
if (changed)
bridge: fix setlink/dellink notifications problems with bridge getlink/setlink notifications today: - bridge setlink generates two notifications to userspace - one from the bridge driver - one from rtnetlink.c (rtnl_bridge_notify) - dellink generates one notification from rtnetlink.c. Which means bridge setlink and dellink notifications are not consistent - Looking at the code it appears, If both BRIDGE_FLAGS_MASTER and BRIDGE_FLAGS_SELF were set, the size calculation in rtnl_bridge_notify can be wrong. Example: if you set both BRIDGE_FLAGS_MASTER and BRIDGE_FLAGS_SELF in a setlink request to rocker dev, rtnl_bridge_notify will allocate skb for one set of bridge attributes, but, both the bridge driver and rocker dev will try to add attributes resulting in twice the number of attributes being added to the skb. (rocker dev calls ndo_dflt_bridge_getlink) There are multiple options: 1) Generate one notification including all attributes from master and self: But, I don't think it will work, because both master and self may use the same attributes/policy. Cannot pack the same set of attributes in a single notification from both master and slave (duplicate attributes). 2) Generate one notification from master and the other notification from self (This seems to be ideal): For master: the master driver will send notification (bridge in this example) For self: the self driver will send notification (rocker in the above example. It can use helpers from rtnetlink.c to do so. Like the ndo_dflt_bridge_getlink api). This patch implements 2) (leaving the 'rtnl_bridge_notify' around to be used with 'self'). v1->v2 : - rtnl_bridge_notify is now called only for self, so, remove 'BRIDGE_FLAGS_SELF' check and cleanup a few things - rtnl_bridge_dellink used to always send a RTM_NEWLINK msg earlier. So, I have changed the notification from br_dellink to go as RTM_NEWLINK Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-15 12:02:25 +08:00
/* Send RTM_NEWLINK because userspace
* expects RTM_NEWLINK for vlan dels
*/
br_ifinfo_notify(RTM_NEWLINK, br, p);
return err;
}
static int br_validate(struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
if (tb[IFLA_ADDRESS]) {
if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
return -EINVAL;
if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
return -EADDRNOTAVAIL;
}
if (!data)
return 0;
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
if (data[IFLA_BR_VLAN_PROTOCOL]) {
switch (nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL])) {
case htons(ETH_P_8021Q):
case htons(ETH_P_8021AD):
break;
default:
return -EPROTONOSUPPORT;
}
}
if (data[IFLA_BR_VLAN_DEFAULT_PVID]) {
__u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]);
if (defpvid >= VLAN_VID_MASK)
return -EINVAL;
}
#endif
return 0;
}
static int br_port_slave_changelink(struct net_device *brdev,
struct net_device *dev,
struct nlattr *tb[],
struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct net_bridge *br = netdev_priv(brdev);
int ret;
if (!data)
return 0;
spin_lock_bh(&br->lock);
ret = br_setport(br_port_get_rtnl(dev), data);
spin_unlock_bh(&br->lock);
return ret;
}
static int br_port_fill_slave_info(struct sk_buff *skb,
const struct net_device *brdev,
const struct net_device *dev)
{
return br_port_fill_attrs(skb, br_port_get_rtnl(dev));
}
static size_t br_port_get_slave_size(const struct net_device *brdev,
const struct net_device *dev)
{
return br_port_info_size();
}
static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
[IFLA_BR_FORWARD_DELAY] = { .type = NLA_U32 },
[IFLA_BR_HELLO_TIME] = { .type = NLA_U32 },
[IFLA_BR_MAX_AGE] = { .type = NLA_U32 },
[IFLA_BR_AGEING_TIME] = { .type = NLA_U32 },
[IFLA_BR_STP_STATE] = { .type = NLA_U32 },
[IFLA_BR_PRIORITY] = { .type = NLA_U16 },
[IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 },
[IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 },
[IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 },
[IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY,
.len = ETH_ALEN },
[IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 },
[IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 },
[IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 },
[IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 },
[IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 },
[IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 },
[IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 },
[IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 },
[IFLA_BR_MCAST_LAST_MEMBER_INTVL] = { .type = NLA_U64 },
[IFLA_BR_MCAST_MEMBERSHIP_INTVL] = { .type = NLA_U64 },
[IFLA_BR_MCAST_QUERIER_INTVL] = { .type = NLA_U64 },
[IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 },
[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 },
[IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 },
[IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 },
[IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 },
[IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 },
[IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 },
[IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 },
[IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 },
[IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 },
[IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 },
};
static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct net_bridge *br = netdev_priv(brdev);
int err;
if (!data)
return 0;
if (data[IFLA_BR_FORWARD_DELAY]) {
err = br_set_forward_delay(br, nla_get_u32(data[IFLA_BR_FORWARD_DELAY]));
if (err)
return err;
}
if (data[IFLA_BR_HELLO_TIME]) {
err = br_set_hello_time(br, nla_get_u32(data[IFLA_BR_HELLO_TIME]));
if (err)
return err;
}
if (data[IFLA_BR_MAX_AGE]) {
err = br_set_max_age(br, nla_get_u32(data[IFLA_BR_MAX_AGE]));
if (err)
return err;
}
if (data[IFLA_BR_AGEING_TIME]) {
err = br_set_ageing_time(br, nla_get_u32(data[IFLA_BR_AGEING_TIME]));
if (err)
return err;
}
if (data[IFLA_BR_STP_STATE]) {
u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]);
br_stp_set_enabled(br, stp_enabled);
}
if (data[IFLA_BR_PRIORITY]) {
u32 priority = nla_get_u16(data[IFLA_BR_PRIORITY]);
br_stp_set_bridge_priority(br, priority);
}
if (data[IFLA_BR_VLAN_FILTERING]) {
u8 vlan_filter = nla_get_u8(data[IFLA_BR_VLAN_FILTERING]);
err = __br_vlan_filter_toggle(br, vlan_filter);
if (err)
return err;
}
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
if (data[IFLA_BR_VLAN_PROTOCOL]) {
__be16 vlan_proto = nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]);
err = __br_vlan_set_proto(br, vlan_proto);
if (err)
return err;
}
if (data[IFLA_BR_VLAN_DEFAULT_PVID]) {
__u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]);
err = __br_vlan_set_default_pvid(br, defpvid);
if (err)
return err;
}
if (data[IFLA_BR_VLAN_STATS_ENABLED]) {
__u8 vlan_stats = nla_get_u8(data[IFLA_BR_VLAN_STATS_ENABLED]);
err = br_vlan_set_stats(br, vlan_stats);
if (err)
return err;
}
#endif
if (data[IFLA_BR_GROUP_FWD_MASK]) {
u16 fwd_mask = nla_get_u16(data[IFLA_BR_GROUP_FWD_MASK]);
if (fwd_mask & BR_GROUPFWD_RESTRICTED)
return -EINVAL;
br->group_fwd_mask = fwd_mask;
}
if (data[IFLA_BR_GROUP_ADDR]) {
u8 new_addr[ETH_ALEN];
if (nla_len(data[IFLA_BR_GROUP_ADDR]) != ETH_ALEN)
return -EINVAL;
memcpy(new_addr, nla_data(data[IFLA_BR_GROUP_ADDR]), ETH_ALEN);
if (!is_link_local_ether_addr(new_addr))
return -EINVAL;
if (new_addr[5] == 1 || /* 802.3x Pause address */
new_addr[5] == 2 || /* 802.3ad Slow protocols */
new_addr[5] == 3) /* 802.1X PAE address */
return -EINVAL;
spin_lock_bh(&br->lock);
memcpy(br->group_addr, new_addr, sizeof(br->group_addr));
spin_unlock_bh(&br->lock);
br->group_addr_set = true;
br_recalculate_fwd_mask(br);
}
if (data[IFLA_BR_FDB_FLUSH])
br_fdb_flush(br);
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
if (data[IFLA_BR_MCAST_ROUTER]) {
u8 multicast_router = nla_get_u8(data[IFLA_BR_MCAST_ROUTER]);
err = br_multicast_set_router(br, multicast_router);
if (err)
return err;
}
if (data[IFLA_BR_MCAST_SNOOPING]) {
u8 mcast_snooping = nla_get_u8(data[IFLA_BR_MCAST_SNOOPING]);
err = br_multicast_toggle(br, mcast_snooping);
if (err)
return err;
}
if (data[IFLA_BR_MCAST_QUERY_USE_IFADDR]) {
u8 val;
val = nla_get_u8(data[IFLA_BR_MCAST_QUERY_USE_IFADDR]);
br->multicast_query_use_ifaddr = !!val;
}
if (data[IFLA_BR_MCAST_QUERIER]) {
u8 mcast_querier = nla_get_u8(data[IFLA_BR_MCAST_QUERIER]);
err = br_multicast_set_querier(br, mcast_querier);
if (err)
return err;
}
if (data[IFLA_BR_MCAST_HASH_ELASTICITY]) {
u32 val = nla_get_u32(data[IFLA_BR_MCAST_HASH_ELASTICITY]);
br->hash_elasticity = val;
}
if (data[IFLA_BR_MCAST_HASH_MAX]) {
u32 hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]);
err = br_multicast_set_hash_max(br, hash_max);
if (err)
return err;
}
if (data[IFLA_BR_MCAST_LAST_MEMBER_CNT]) {
u32 val = nla_get_u32(data[IFLA_BR_MCAST_LAST_MEMBER_CNT]);
br->multicast_last_member_count = val;
}
if (data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]) {
u32 val = nla_get_u32(data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]);
br->multicast_startup_query_count = val;
}
if (data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]) {
u64 val = nla_get_u64(data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]);
br->multicast_last_member_interval = clock_t_to_jiffies(val);
}
if (data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]) {
u64 val = nla_get_u64(data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]);
br->multicast_membership_interval = clock_t_to_jiffies(val);
}
if (data[IFLA_BR_MCAST_QUERIER_INTVL]) {
u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERIER_INTVL]);
br->multicast_querier_interval = clock_t_to_jiffies(val);
}
if (data[IFLA_BR_MCAST_QUERY_INTVL]) {
u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]);
br->multicast_query_interval = clock_t_to_jiffies(val);
}
if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) {
u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]);
br->multicast_query_response_interval = clock_t_to_jiffies(val);
}
if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) {
u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]);
br->multicast_startup_query_interval = clock_t_to_jiffies(val);
}
if (data[IFLA_BR_MCAST_STATS_ENABLED]) {
__u8 mcast_stats;
mcast_stats = nla_get_u8(data[IFLA_BR_MCAST_STATS_ENABLED]);
br->multicast_stats_enabled = !!mcast_stats;
}
if (data[IFLA_BR_MCAST_IGMP_VERSION]) {
__u8 igmp_version;
igmp_version = nla_get_u8(data[IFLA_BR_MCAST_IGMP_VERSION]);
err = br_multicast_set_igmp_version(br, igmp_version);
if (err)
return err;
}
#if IS_ENABLED(CONFIG_IPV6)
if (data[IFLA_BR_MCAST_MLD_VERSION]) {
__u8 mld_version;
mld_version = nla_get_u8(data[IFLA_BR_MCAST_MLD_VERSION]);
err = br_multicast_set_mld_version(br, mld_version);
if (err)
return err;
}
#endif
#endif
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
if (data[IFLA_BR_NF_CALL_IPTABLES]) {
u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IPTABLES]);
br->nf_call_iptables = val ? true : false;
}
if (data[IFLA_BR_NF_CALL_IP6TABLES]) {
u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IP6TABLES]);
br->nf_call_ip6tables = val ? true : false;
}
if (data[IFLA_BR_NF_CALL_ARPTABLES]) {
u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_ARPTABLES]);
br->nf_call_arptables = val ? true : false;
}
#endif
return 0;
}
static int br_dev_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct net_bridge *br = netdev_priv(dev);
int err;
net: bridge: fix early call to br_stp_change_bridge_id and plug newlink leaks The early call to br_stp_change_bridge_id in bridge's newlink can cause a memory leak if an error occurs during the newlink because the fdb entries are not cleaned up if a different lladdr was specified, also another minor issue is that it generates fdb notifications with ifindex = 0. Another unrelated memory leak is the bridge sysfs entries which get added on NETDEV_REGISTER event, but are not cleaned up in the newlink error path. To remove this special case the call to br_stp_change_bridge_id is done after netdev register and we cleanup the bridge on changelink error via br_dev_delete to plug all leaks. This patch makes netlink bridge destruction on newlink error the same as dellink and ioctl del which is necessary since at that point we have a fully initialized bridge device. To reproduce the issue: $ ip l add br0 address 00:11:22:33:44:55 type bridge group_fwd_mask 1 RTNETLINK answers: Invalid argument $ rmmod bridge [ 1822.142525] ============================================================================= [ 1822.143640] BUG bridge_fdb_cache (Tainted: G O ): Objects remaining in bridge_fdb_cache on __kmem_cache_shutdown() [ 1822.144821] ----------------------------------------------------------------------------- [ 1822.145990] Disabling lock debugging due to kernel taint [ 1822.146732] INFO: Slab 0x0000000092a844b2 objects=32 used=2 fp=0x00000000fef011b0 flags=0x1ffff8000000100 [ 1822.147700] CPU: 2 PID: 13584 Comm: rmmod Tainted: G B O 4.15.0-rc2+ #87 [ 1822.148578] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 [ 1822.150008] Call Trace: [ 1822.150510] dump_stack+0x78/0xa9 [ 1822.151156] slab_err+0xb1/0xd3 [ 1822.151834] ? __kmalloc+0x1bb/0x1ce [ 1822.152546] __kmem_cache_shutdown+0x151/0x28b [ 1822.153395] shutdown_cache+0x13/0x144 [ 1822.154126] kmem_cache_destroy+0x1c0/0x1fb [ 1822.154669] SyS_delete_module+0x194/0x244 [ 1822.155199] ? trace_hardirqs_on_thunk+0x1a/0x1c [ 1822.155773] entry_SYSCALL_64_fastpath+0x23/0x9a [ 1822.156343] RIP: 0033:0x7f929bd38b17 [ 1822.156859] RSP: 002b:00007ffd160e9a98 EFLAGS: 00000202 ORIG_RAX: 00000000000000b0 [ 1822.157728] RAX: ffffffffffffffda RBX: 00005578316ba090 RCX: 00007f929bd38b17 [ 1822.158422] RDX: 00007f929bd9ec60 RSI: 0000000000000800 RDI: 00005578316ba0f0 [ 1822.159114] RBP: 0000000000000003 R08: 00007f929bff5f20 R09: 00007ffd160e8a11 [ 1822.159808] R10: 00007ffd160e9860 R11: 0000000000000202 R12: 00007ffd160e8a80 [ 1822.160513] R13: 0000000000000000 R14: 0000000000000000 R15: 00005578316ba090 [ 1822.161278] INFO: Object 0x000000007645de29 @offset=0 [ 1822.161666] INFO: Object 0x00000000d5df2ab5 @offset=128 Fixes: 30313a3d5794 ("bridge: Handle IFLA_ADDRESS correctly when creating bridge device") Fixes: 5b8d5429daa0 ("bridge: netlink: register netdevice before executing changelink") Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-18 23:35:09 +08:00
err = register_netdevice(dev);
if (err)
return err;
if (tb[IFLA_ADDRESS]) {
spin_lock_bh(&br->lock);
br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
spin_unlock_bh(&br->lock);
}
err = br_changelink(dev, tb, data, extack);
bridge: netlink: register netdevice before executing changelink Peter reported a kernel oops when executing the following command: $ ip link add name test type bridge vlan_default_pvid 1 [13634.939408] BUG: unable to handle kernel NULL pointer dereference at 0000000000000190 [13634.939436] IP: __vlan_add+0x73/0x5f0 [...] [13634.939783] Call Trace: [13634.939791] ? pcpu_next_unpop+0x3b/0x50 [13634.939801] ? pcpu_alloc+0x3d2/0x680 [13634.939810] ? br_vlan_add+0x135/0x1b0 [13634.939820] ? __br_vlan_set_default_pvid.part.28+0x204/0x2b0 [13634.939834] ? br_changelink+0x120/0x4e0 [13634.939844] ? br_dev_newlink+0x50/0x70 [13634.939854] ? rtnl_newlink+0x5f5/0x8a0 [13634.939864] ? rtnl_newlink+0x176/0x8a0 [13634.939874] ? mem_cgroup_commit_charge+0x7c/0x4e0 [13634.939886] ? rtnetlink_rcv_msg+0xe1/0x220 [13634.939896] ? lookup_fast+0x52/0x370 [13634.939905] ? rtnl_newlink+0x8a0/0x8a0 [13634.939915] ? netlink_rcv_skb+0xa1/0xc0 [13634.939925] ? rtnetlink_rcv+0x24/0x30 [13634.939934] ? netlink_unicast+0x177/0x220 [13634.939944] ? netlink_sendmsg+0x2fe/0x3b0 [13634.939954] ? _copy_from_user+0x39/0x40 [13634.939964] ? sock_sendmsg+0x30/0x40 [13634.940159] ? ___sys_sendmsg+0x29d/0x2b0 [13634.940326] ? __alloc_pages_nodemask+0xdf/0x230 [13634.940478] ? mem_cgroup_commit_charge+0x7c/0x4e0 [13634.940592] ? mem_cgroup_try_charge+0x76/0x1a0 [13634.940701] ? __handle_mm_fault+0xdb9/0x10b0 [13634.940809] ? __sys_sendmsg+0x51/0x90 [13634.940917] ? entry_SYSCALL_64_fastpath+0x1e/0xad The problem is that the bridge's VLAN group is created after setting the default PVID, when registering the netdevice and executing its ndo_init(). Fix this by changing the order of both operations, so that br_changelink() is only processed after the netdevice is registered, when the VLAN group is already initialized. Fixes: b6677449dff6 ("bridge: netlink: call br_changelink() during br_dev_newlink()") Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Ido Schimmel <idosch@mellanox.com> Reported-by: Peter V. Saveliev <peter@svinota.eu> Tested-by: Peter V. Saveliev <peter@svinota.eu> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-10 19:59:28 +08:00
if (err)
net: bridge: fix early call to br_stp_change_bridge_id and plug newlink leaks The early call to br_stp_change_bridge_id in bridge's newlink can cause a memory leak if an error occurs during the newlink because the fdb entries are not cleaned up if a different lladdr was specified, also another minor issue is that it generates fdb notifications with ifindex = 0. Another unrelated memory leak is the bridge sysfs entries which get added on NETDEV_REGISTER event, but are not cleaned up in the newlink error path. To remove this special case the call to br_stp_change_bridge_id is done after netdev register and we cleanup the bridge on changelink error via br_dev_delete to plug all leaks. This patch makes netlink bridge destruction on newlink error the same as dellink and ioctl del which is necessary since at that point we have a fully initialized bridge device. To reproduce the issue: $ ip l add br0 address 00:11:22:33:44:55 type bridge group_fwd_mask 1 RTNETLINK answers: Invalid argument $ rmmod bridge [ 1822.142525] ============================================================================= [ 1822.143640] BUG bridge_fdb_cache (Tainted: G O ): Objects remaining in bridge_fdb_cache on __kmem_cache_shutdown() [ 1822.144821] ----------------------------------------------------------------------------- [ 1822.145990] Disabling lock debugging due to kernel taint [ 1822.146732] INFO: Slab 0x0000000092a844b2 objects=32 used=2 fp=0x00000000fef011b0 flags=0x1ffff8000000100 [ 1822.147700] CPU: 2 PID: 13584 Comm: rmmod Tainted: G B O 4.15.0-rc2+ #87 [ 1822.148578] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 [ 1822.150008] Call Trace: [ 1822.150510] dump_stack+0x78/0xa9 [ 1822.151156] slab_err+0xb1/0xd3 [ 1822.151834] ? __kmalloc+0x1bb/0x1ce [ 1822.152546] __kmem_cache_shutdown+0x151/0x28b [ 1822.153395] shutdown_cache+0x13/0x144 [ 1822.154126] kmem_cache_destroy+0x1c0/0x1fb [ 1822.154669] SyS_delete_module+0x194/0x244 [ 1822.155199] ? trace_hardirqs_on_thunk+0x1a/0x1c [ 1822.155773] entry_SYSCALL_64_fastpath+0x23/0x9a [ 1822.156343] RIP: 0033:0x7f929bd38b17 [ 1822.156859] RSP: 002b:00007ffd160e9a98 EFLAGS: 00000202 ORIG_RAX: 00000000000000b0 [ 1822.157728] RAX: ffffffffffffffda RBX: 00005578316ba090 RCX: 00007f929bd38b17 [ 1822.158422] RDX: 00007f929bd9ec60 RSI: 0000000000000800 RDI: 00005578316ba0f0 [ 1822.159114] RBP: 0000000000000003 R08: 00007f929bff5f20 R09: 00007ffd160e8a11 [ 1822.159808] R10: 00007ffd160e9860 R11: 0000000000000202 R12: 00007ffd160e8a80 [ 1822.160513] R13: 0000000000000000 R14: 0000000000000000 R15: 00005578316ba090 [ 1822.161278] INFO: Object 0x000000007645de29 @offset=0 [ 1822.161666] INFO: Object 0x00000000d5df2ab5 @offset=128 Fixes: 30313a3d5794 ("bridge: Handle IFLA_ADDRESS correctly when creating bridge device") Fixes: 5b8d5429daa0 ("bridge: netlink: register netdevice before executing changelink") Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-18 23:35:09 +08:00
br_dev_delete(dev, NULL);
bridge: netlink: register netdevice before executing changelink Peter reported a kernel oops when executing the following command: $ ip link add name test type bridge vlan_default_pvid 1 [13634.939408] BUG: unable to handle kernel NULL pointer dereference at 0000000000000190 [13634.939436] IP: __vlan_add+0x73/0x5f0 [...] [13634.939783] Call Trace: [13634.939791] ? pcpu_next_unpop+0x3b/0x50 [13634.939801] ? pcpu_alloc+0x3d2/0x680 [13634.939810] ? br_vlan_add+0x135/0x1b0 [13634.939820] ? __br_vlan_set_default_pvid.part.28+0x204/0x2b0 [13634.939834] ? br_changelink+0x120/0x4e0 [13634.939844] ? br_dev_newlink+0x50/0x70 [13634.939854] ? rtnl_newlink+0x5f5/0x8a0 [13634.939864] ? rtnl_newlink+0x176/0x8a0 [13634.939874] ? mem_cgroup_commit_charge+0x7c/0x4e0 [13634.939886] ? rtnetlink_rcv_msg+0xe1/0x220 [13634.939896] ? lookup_fast+0x52/0x370 [13634.939905] ? rtnl_newlink+0x8a0/0x8a0 [13634.939915] ? netlink_rcv_skb+0xa1/0xc0 [13634.939925] ? rtnetlink_rcv+0x24/0x30 [13634.939934] ? netlink_unicast+0x177/0x220 [13634.939944] ? netlink_sendmsg+0x2fe/0x3b0 [13634.939954] ? _copy_from_user+0x39/0x40 [13634.939964] ? sock_sendmsg+0x30/0x40 [13634.940159] ? ___sys_sendmsg+0x29d/0x2b0 [13634.940326] ? __alloc_pages_nodemask+0xdf/0x230 [13634.940478] ? mem_cgroup_commit_charge+0x7c/0x4e0 [13634.940592] ? mem_cgroup_try_charge+0x76/0x1a0 [13634.940701] ? __handle_mm_fault+0xdb9/0x10b0 [13634.940809] ? __sys_sendmsg+0x51/0x90 [13634.940917] ? entry_SYSCALL_64_fastpath+0x1e/0xad The problem is that the bridge's VLAN group is created after setting the default PVID, when registering the netdevice and executing its ndo_init(). Fix this by changing the order of both operations, so that br_changelink() is only processed after the netdevice is registered, when the VLAN group is already initialized. Fixes: b6677449dff6 ("bridge: netlink: call br_changelink() during br_dev_newlink()") Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Ido Schimmel <idosch@mellanox.com> Reported-by: Peter V. Saveliev <peter@svinota.eu> Tested-by: Peter V. Saveliev <peter@svinota.eu> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-10 19:59:28 +08:00
return err;
}
static size_t br_get_size(const struct net_device *brdev)
{
return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */
nla_total_size(sizeof(u32)) + /* IFLA_BR_HELLO_TIME */
nla_total_size(sizeof(u32)) + /* IFLA_BR_MAX_AGE */
nla_total_size(sizeof(u32)) + /* IFLA_BR_AGEING_TIME */
nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_STATE */
nla_total_size(sizeof(u16)) + /* IFLA_BR_PRIORITY */
nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_FILTERING */
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */
nla_total_size(sizeof(u16)) + /* IFLA_BR_VLAN_DEFAULT_PVID */
nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_STATS_ENABLED */
#endif
nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */
nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */
nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */
nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */
nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */
nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */
nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_HELLO_TIMER */
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_GC_TIMER */
nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_STATS_ENABLED */
nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */
nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */
nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */
nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_STARTUP_QUERY_CNT */
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_LAST_MEMBER_INTVL */
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_MEMBERSHIP_INTVL */
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERIER_INTVL */
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */
nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_IGMP_VERSION */
nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_MLD_VERSION */
#endif
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */
nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IP6TABLES */
nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_ARPTABLES */
#endif
0;
}
static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
{
struct net_bridge *br = netdev_priv(brdev);
u32 forward_delay = jiffies_to_clock_t(br->forward_delay);
u32 hello_time = jiffies_to_clock_t(br->hello_time);
u32 age_time = jiffies_to_clock_t(br->max_age);
u32 ageing_time = jiffies_to_clock_t(br->ageing_time);
u32 stp_enabled = br->stp_enabled;
u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1];
u8 vlan_enabled = br_vlan_enabled(br->dev);
u64 clockval;
clockval = br_timer_value(&br->hello_timer);
if (nla_put_u64_64bit(skb, IFLA_BR_HELLO_TIMER, clockval, IFLA_BR_PAD))
return -EMSGSIZE;
clockval = br_timer_value(&br->tcn_timer);
if (nla_put_u64_64bit(skb, IFLA_BR_TCN_TIMER, clockval, IFLA_BR_PAD))
return -EMSGSIZE;
clockval = br_timer_value(&br->topology_change_timer);
if (nla_put_u64_64bit(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, clockval,
IFLA_BR_PAD))
return -EMSGSIZE;
clockval = br_timer_value(&br->gc_work.timer);
if (nla_put_u64_64bit(skb, IFLA_BR_GC_TIMER, clockval, IFLA_BR_PAD))
return -EMSGSIZE;
if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) ||
nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) ||
nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) ||
nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) ||
nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) ||
nla_put_u16(skb, IFLA_BR_PRIORITY, priority) ||
nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) ||
nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, br->group_fwd_mask) ||
nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(struct ifla_bridge_id),
&br->bridge_id) ||
nla_put(skb, IFLA_BR_ROOT_ID, sizeof(struct ifla_bridge_id),
&br->designated_root) ||
nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port) ||
nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost) ||
nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) ||
nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED,
br->topology_change_detected) ||
nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr))
return -EMSGSIZE;
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto) ||
nla_put_u16(skb, IFLA_BR_VLAN_DEFAULT_PVID, br->default_pvid) ||
nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED, br->vlan_stats_enabled))
return -EMSGSIZE;
#endif
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router) ||
nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled) ||
nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR,
br->multicast_query_use_ifaddr) ||
nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier) ||
nla_put_u8(skb, IFLA_BR_MCAST_STATS_ENABLED,
br->multicast_stats_enabled) ||
nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY,
br->hash_elasticity) ||
nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) ||
nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT,
br->multicast_last_member_count) ||
nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT,
br->multicast_startup_query_count) ||
nla_put_u8(skb, IFLA_BR_MCAST_IGMP_VERSION,
br->multicast_igmp_version))
return -EMSGSIZE;
#if IS_ENABLED(CONFIG_IPV6)
if (nla_put_u8(skb, IFLA_BR_MCAST_MLD_VERSION,
br->multicast_mld_version))
return -EMSGSIZE;
#endif
clockval = jiffies_to_clock_t(br->multicast_last_member_interval);
if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval,
IFLA_BR_PAD))
return -EMSGSIZE;
clockval = jiffies_to_clock_t(br->multicast_membership_interval);
if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_MEMBERSHIP_INTVL, clockval,
IFLA_BR_PAD))
return -EMSGSIZE;
clockval = jiffies_to_clock_t(br->multicast_querier_interval);
if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERIER_INTVL, clockval,
IFLA_BR_PAD))
return -EMSGSIZE;
clockval = jiffies_to_clock_t(br->multicast_query_interval);
if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_INTVL, clockval,
IFLA_BR_PAD))
return -EMSGSIZE;
clockval = jiffies_to_clock_t(br->multicast_query_response_interval);
if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, clockval,
IFLA_BR_PAD))
return -EMSGSIZE;
clockval = jiffies_to_clock_t(br->multicast_startup_query_interval);
if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval,
IFLA_BR_PAD))
return -EMSGSIZE;
#endif
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
if (nla_put_u8(skb, IFLA_BR_NF_CALL_IPTABLES,
br->nf_call_iptables ? 1 : 0) ||
nla_put_u8(skb, IFLA_BR_NF_CALL_IP6TABLES,
br->nf_call_ip6tables ? 1 : 0) ||
nla_put_u8(skb, IFLA_BR_NF_CALL_ARPTABLES,
br->nf_call_arptables ? 1 : 0))
return -EMSGSIZE;
#endif
return 0;
}
static size_t br_get_linkxstats_size(const struct net_device *dev, int attr)
{
struct net_bridge_port *p = NULL;
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *v;
struct net_bridge *br;
int numvls = 0;
switch (attr) {
case IFLA_STATS_LINK_XSTATS:
br = netdev_priv(dev);
vg = br_vlan_group(br);
break;
case IFLA_STATS_LINK_XSTATS_SLAVE:
p = br_port_get_rtnl(dev);
if (!p)
return 0;
br = p->br;
vg = nbp_vlan_group(p);
break;
default:
return 0;
}
if (vg) {
/* we need to count all, even placeholder entries */
list_for_each_entry(v, &vg->vlan_list, vlist)
numvls++;
}
return numvls * nla_total_size(sizeof(struct bridge_vlan_xstats)) +
nla_total_size(sizeof(struct br_mcast_stats)) +
nla_total_size(0);
}
static int br_fill_linkxstats(struct sk_buff *skb,
const struct net_device *dev,
int *prividx, int attr)
{
struct nlattr *nla __maybe_unused;
struct net_bridge_port *p = NULL;
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *v;
struct net_bridge *br;
struct nlattr *nest;
int vl_idx = 0;
switch (attr) {
case IFLA_STATS_LINK_XSTATS:
br = netdev_priv(dev);
vg = br_vlan_group(br);
break;
case IFLA_STATS_LINK_XSTATS_SLAVE:
p = br_port_get_rtnl(dev);
if (!p)
return 0;
br = p->br;
vg = nbp_vlan_group(p);
break;
default:
return -EINVAL;
}
nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BRIDGE);
if (!nest)
return -EMSGSIZE;
if (vg) {
u16 pvid;
pvid = br_get_pvid(vg);
list_for_each_entry(v, &vg->vlan_list, vlist) {
struct bridge_vlan_xstats vxi;
struct br_vlan_stats stats;
if (++vl_idx < *prividx)
continue;
memset(&vxi, 0, sizeof(vxi));
vxi.vid = v->vid;
vxi.flags = v->flags;
if (v->vid == pvid)
vxi.flags |= BRIDGE_VLAN_INFO_PVID;
br_vlan_get_stats(v, &stats);
vxi.rx_bytes = stats.rx_bytes;
vxi.rx_packets = stats.rx_packets;
vxi.tx_bytes = stats.tx_bytes;
vxi.tx_packets = stats.tx_packets;
if (nla_put(skb, BRIDGE_XSTATS_VLAN, sizeof(vxi), &vxi))
goto nla_put_failure;
}
}
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
if (++vl_idx >= *prividx) {
nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST,
sizeof(struct br_mcast_stats),
BRIDGE_XSTATS_PAD);
if (!nla)
goto nla_put_failure;
br_multicast_get_stats(br, p, nla_data(nla));
}
#endif
nla_nest_end(skb, nest);
*prividx = 0;
return 0;
nla_put_failure:
nla_nest_end(skb, nest);
*prividx = vl_idx;
return -EMSGSIZE;
}
static struct rtnl_af_ops br_af_ops __read_mostly = {
.family = AF_BRIDGE,
.get_link_af_size = br_get_link_af_size_filtered,
};
struct rtnl_link_ops br_link_ops __read_mostly = {
.kind = "bridge",
.priv_size = sizeof(struct net_bridge),
.setup = br_dev_setup,
.maxtype = IFLA_BR_MAX,
.policy = br_policy,
.validate = br_validate,
.newlink = br_dev_newlink,
.changelink = br_changelink,
.dellink = br_dev_delete,
.get_size = br_get_size,
.fill_info = br_fill_info,
.fill_linkxstats = br_fill_linkxstats,
.get_linkxstats_size = br_get_linkxstats_size,
.slave_maxtype = IFLA_BRPORT_MAX,
.slave_policy = br_port_policy,
.slave_changelink = br_port_slave_changelink,
.get_slave_size = br_port_get_slave_size,
.fill_slave_info = br_port_fill_slave_info,
};
int __init br_netlink_init(void)
{
int err;
br_mdb_init();
rtnl_af_register(&br_af_ops);
err = rtnl_link_register(&br_link_ops);
if (err)
goto out_af;
return 0;
out_af:
rtnl_af_unregister(&br_af_ops);
br_mdb_uninit();
return err;
}
void br_netlink_fini(void)
{
br_mdb_uninit();
rtnl_af_unregister(&br_af_ops);
rtnl_link_unregister(&br_link_ops);
}