linux_dsm_epyc7002/include/linux/rtnetlink.h

130 lines
4.1 KiB
C
Raw Normal View History

#ifndef __LINUX_RTNETLINK_H
#define __LINUX_RTNETLINK_H
#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/wait.h>
#include <uapi/linux/rtnetlink.h>
extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo);
extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid);
2009-02-25 14:18:28 +07:00
extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid,
u32 group, struct nlmsghdr *nlh, gfp_t flags);
extern void rtnl_set_sk_err(struct net *net, u32 group, int error);
extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics);
extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst,
u32 id, long expires, u32 error);
net: fix rtnl notification in atomic context commit 991fb3f74c "dev: always advertise rx_flags changes via netlink" introduced rtnl notification from __dev_set_promiscuity(), which can be called in atomic context. Steps to reproduce: ip tuntap add dev tap1 mode tap ifconfig tap1 up tcpdump -nei tap1 & ip tuntap del dev tap1 mode tap [ 271.627994] device tap1 left promiscuous mode [ 271.639897] BUG: sleeping function called from invalid context at mm/slub.c:940 [ 271.664491] in_atomic(): 1, irqs_disabled(): 0, pid: 3394, name: ip [ 271.677525] INFO: lockdep is turned off. [ 271.690503] CPU: 0 PID: 3394 Comm: ip Tainted: G W 3.12.0-rc3+ #73 [ 271.703996] Hardware name: System manufacturer System Product Name/P8Z77 WS, BIOS 3007 07/26/2012 [ 271.731254] ffffffff81a58506 ffff8807f0d57a58 ffffffff817544e5 ffff88082fa0f428 [ 271.760261] ffff8808071f5f40 ffff8807f0d57a88 ffffffff8108bad1 ffffffff81110ff8 [ 271.790683] 0000000000000010 00000000000000d0 00000000000000d0 ffff8807f0d57af8 [ 271.822332] Call Trace: [ 271.838234] [<ffffffff817544e5>] dump_stack+0x55/0x76 [ 271.854446] [<ffffffff8108bad1>] __might_sleep+0x181/0x240 [ 271.870836] [<ffffffff81110ff8>] ? rcu_irq_exit+0x68/0xb0 [ 271.887076] [<ffffffff811a80be>] kmem_cache_alloc_node+0x4e/0x2a0 [ 271.903368] [<ffffffff810b4ddc>] ? vprintk_emit+0x1dc/0x5a0 [ 271.919716] [<ffffffff81614d67>] ? __alloc_skb+0x57/0x2a0 [ 271.936088] [<ffffffff810b4de0>] ? vprintk_emit+0x1e0/0x5a0 [ 271.952504] [<ffffffff81614d67>] __alloc_skb+0x57/0x2a0 [ 271.968902] [<ffffffff8163a0b2>] rtmsg_ifinfo+0x52/0x100 [ 271.985302] [<ffffffff8162ac6d>] __dev_notify_flags+0xad/0xc0 [ 272.001642] [<ffffffff8162ad0c>] __dev_set_promiscuity+0x8c/0x1c0 [ 272.017917] [<ffffffff81731ea5>] ? packet_notifier+0x5/0x380 [ 272.033961] [<ffffffff8162b109>] dev_set_promiscuity+0x29/0x50 [ 272.049855] [<ffffffff8172e937>] packet_dev_mc+0x87/0xc0 [ 272.065494] [<ffffffff81732052>] packet_notifier+0x1b2/0x380 [ 272.080915] [<ffffffff81731ea5>] ? packet_notifier+0x5/0x380 [ 272.096009] [<ffffffff81761c66>] notifier_call_chain+0x66/0x150 [ 272.110803] [<ffffffff8108503e>] __raw_notifier_call_chain+0xe/0x10 [ 272.125468] [<ffffffff81085056>] raw_notifier_call_chain+0x16/0x20 [ 272.139984] [<ffffffff81620190>] call_netdevice_notifiers_info+0x40/0x70 [ 272.154523] [<ffffffff816201d6>] call_netdevice_notifiers+0x16/0x20 [ 272.168552] [<ffffffff816224c5>] rollback_registered_many+0x145/0x240 [ 272.182263] [<ffffffff81622641>] rollback_registered+0x31/0x40 [ 272.195369] [<ffffffff816229c8>] unregister_netdevice_queue+0x58/0x90 [ 272.208230] [<ffffffff81547ca0>] __tun_detach+0x140/0x340 [ 272.220686] [<ffffffff81547ed6>] tun_chr_close+0x36/0x60 Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-24 06:02:42 +07:00
void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags);
rtnetlink: delay RTM_DELLINK notification until after ndo_uninit() The commit 56bfa7ee7c ("unregister_netdevice : move RTM_DELLINK to until after ndo_uninit") tried to do this ealier but while doing so it created a problem. Unfortunately the delayed rtmsg_ifinfo() also delayed call to fill_info(). So this translated into asking driver to remove private state and then query it's private state. This could have catastropic consequences. This change breaks the rtmsg_ifinfo() into two parts - one takes the precise snapshot of the device by called fill_info() before calling the ndo_uninit() and the second part sends the notification using collected snapshot. It was brought to notice when last link is deleted from an ipvlan device when it has free-ed the port and the subsequent .fill_info() call is trying to get the info from the port. kernel: [ 255.139429] ------------[ cut here ]------------ kernel: [ 255.139439] WARNING: CPU: 12 PID: 11173 at net/core/rtnetlink.c:2238 rtmsg_ifinfo+0x100/0x110() kernel: [ 255.139493] Modules linked in: ipvlan bonding w1_therm ds2482 wire cdc_acm ehci_pci ehci_hcd i2c_dev i2c_i801 i2c_core msr cpuid bnx2x ptp pps_core mdio libcrc32c kernel: [ 255.139513] CPU: 12 PID: 11173 Comm: ip Not tainted 3.18.0-smp-DEV #167 kernel: [ 255.139514] Hardware name: Intel RML,PCH/Ibis_QC_18, BIOS 1.0.10 05/15/2012 kernel: [ 255.139515] 0000000000000009 ffff880851b6b828 ffffffff815d87f4 00000000000000e0 kernel: [ 255.139516] 0000000000000000 ffff880851b6b868 ffffffff8109c29c 0000000000000000 kernel: [ 255.139518] 00000000ffffffa6 00000000000000d0 ffffffff81aaf580 0000000000000011 kernel: [ 255.139520] Call Trace: kernel: [ 255.139527] [<ffffffff815d87f4>] dump_stack+0x46/0x58 kernel: [ 255.139531] [<ffffffff8109c29c>] warn_slowpath_common+0x8c/0xc0 kernel: [ 255.139540] [<ffffffff8109c2ea>] warn_slowpath_null+0x1a/0x20 kernel: [ 255.139544] [<ffffffff8150d570>] rtmsg_ifinfo+0x100/0x110 kernel: [ 255.139547] [<ffffffff814f78b5>] rollback_registered_many+0x1d5/0x2d0 kernel: [ 255.139549] [<ffffffff814f79cf>] unregister_netdevice_many+0x1f/0xb0 kernel: [ 255.139551] [<ffffffff8150acab>] rtnl_dellink+0xbb/0x110 kernel: [ 255.139553] [<ffffffff8150da90>] rtnetlink_rcv_msg+0xa0/0x240 kernel: [ 255.139557] [<ffffffff81329283>] ? rhashtable_lookup_compare+0x43/0x80 kernel: [ 255.139558] [<ffffffff8150d9f0>] ? __rtnl_unlock+0x20/0x20 kernel: [ 255.139562] [<ffffffff8152cb11>] netlink_rcv_skb+0xb1/0xc0 kernel: [ 255.139563] [<ffffffff8150a495>] rtnetlink_rcv+0x25/0x40 kernel: [ 255.139565] [<ffffffff8152c398>] netlink_unicast+0x178/0x230 kernel: [ 255.139567] [<ffffffff8152c75f>] netlink_sendmsg+0x30f/0x420 kernel: [ 255.139571] [<ffffffff814e0b0c>] sock_sendmsg+0x9c/0xd0 kernel: [ 255.139575] [<ffffffff811d1d7f>] ? rw_copy_check_uvector+0x6f/0x130 kernel: [ 255.139577] [<ffffffff814e11c9>] ? copy_msghdr_from_user+0x139/0x1b0 kernel: [ 255.139578] [<ffffffff814e1774>] ___sys_sendmsg+0x304/0x310 kernel: [ 255.139581] [<ffffffff81198723>] ? handle_mm_fault+0xca3/0xde0 kernel: [ 255.139585] [<ffffffff811ebc4c>] ? destroy_inode+0x3c/0x70 kernel: [ 255.139589] [<ffffffff8108e6ec>] ? __do_page_fault+0x20c/0x500 kernel: [ 255.139597] [<ffffffff811e8336>] ? dput+0xb6/0x190 kernel: [ 255.139606] [<ffffffff811f05f6>] ? mntput+0x26/0x40 kernel: [ 255.139611] [<ffffffff811d2b94>] ? __fput+0x174/0x1e0 kernel: [ 255.139613] [<ffffffff814e2129>] __sys_sendmsg+0x49/0x90 kernel: [ 255.139615] [<ffffffff814e2182>] SyS_sendmsg+0x12/0x20 kernel: [ 255.139617] [<ffffffff815df092>] system_call_fastpath+0x12/0x17 kernel: [ 255.139619] ---[ end trace 5e6703e87d984f6b ]--- Signed-off-by: Mahesh Bandewar <maheshb@google.com> Reported-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Cc: Eric Dumazet <edumazet@google.com> Cc: Roopa Prabhu <roopa@cumulusnetworks.com> Cc: David S. Miller <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-04 04:46:24 +07:00
struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
unsigned change, u32 event,
gfp_t flags);
rtnetlink: delay RTM_DELLINK notification until after ndo_uninit() The commit 56bfa7ee7c ("unregister_netdevice : move RTM_DELLINK to until after ndo_uninit") tried to do this ealier but while doing so it created a problem. Unfortunately the delayed rtmsg_ifinfo() also delayed call to fill_info(). So this translated into asking driver to remove private state and then query it's private state. This could have catastropic consequences. This change breaks the rtmsg_ifinfo() into two parts - one takes the precise snapshot of the device by called fill_info() before calling the ndo_uninit() and the second part sends the notification using collected snapshot. It was brought to notice when last link is deleted from an ipvlan device when it has free-ed the port and the subsequent .fill_info() call is trying to get the info from the port. kernel: [ 255.139429] ------------[ cut here ]------------ kernel: [ 255.139439] WARNING: CPU: 12 PID: 11173 at net/core/rtnetlink.c:2238 rtmsg_ifinfo+0x100/0x110() kernel: [ 255.139493] Modules linked in: ipvlan bonding w1_therm ds2482 wire cdc_acm ehci_pci ehci_hcd i2c_dev i2c_i801 i2c_core msr cpuid bnx2x ptp pps_core mdio libcrc32c kernel: [ 255.139513] CPU: 12 PID: 11173 Comm: ip Not tainted 3.18.0-smp-DEV #167 kernel: [ 255.139514] Hardware name: Intel RML,PCH/Ibis_QC_18, BIOS 1.0.10 05/15/2012 kernel: [ 255.139515] 0000000000000009 ffff880851b6b828 ffffffff815d87f4 00000000000000e0 kernel: [ 255.139516] 0000000000000000 ffff880851b6b868 ffffffff8109c29c 0000000000000000 kernel: [ 255.139518] 00000000ffffffa6 00000000000000d0 ffffffff81aaf580 0000000000000011 kernel: [ 255.139520] Call Trace: kernel: [ 255.139527] [<ffffffff815d87f4>] dump_stack+0x46/0x58 kernel: [ 255.139531] [<ffffffff8109c29c>] warn_slowpath_common+0x8c/0xc0 kernel: [ 255.139540] [<ffffffff8109c2ea>] warn_slowpath_null+0x1a/0x20 kernel: [ 255.139544] [<ffffffff8150d570>] rtmsg_ifinfo+0x100/0x110 kernel: [ 255.139547] [<ffffffff814f78b5>] rollback_registered_many+0x1d5/0x2d0 kernel: [ 255.139549] [<ffffffff814f79cf>] unregister_netdevice_many+0x1f/0xb0 kernel: [ 255.139551] [<ffffffff8150acab>] rtnl_dellink+0xbb/0x110 kernel: [ 255.139553] [<ffffffff8150da90>] rtnetlink_rcv_msg+0xa0/0x240 kernel: [ 255.139557] [<ffffffff81329283>] ? rhashtable_lookup_compare+0x43/0x80 kernel: [ 255.139558] [<ffffffff8150d9f0>] ? __rtnl_unlock+0x20/0x20 kernel: [ 255.139562] [<ffffffff8152cb11>] netlink_rcv_skb+0xb1/0xc0 kernel: [ 255.139563] [<ffffffff8150a495>] rtnetlink_rcv+0x25/0x40 kernel: [ 255.139565] [<ffffffff8152c398>] netlink_unicast+0x178/0x230 kernel: [ 255.139567] [<ffffffff8152c75f>] netlink_sendmsg+0x30f/0x420 kernel: [ 255.139571] [<ffffffff814e0b0c>] sock_sendmsg+0x9c/0xd0 kernel: [ 255.139575] [<ffffffff811d1d7f>] ? rw_copy_check_uvector+0x6f/0x130 kernel: [ 255.139577] [<ffffffff814e11c9>] ? copy_msghdr_from_user+0x139/0x1b0 kernel: [ 255.139578] [<ffffffff814e1774>] ___sys_sendmsg+0x304/0x310 kernel: [ 255.139581] [<ffffffff81198723>] ? handle_mm_fault+0xca3/0xde0 kernel: [ 255.139585] [<ffffffff811ebc4c>] ? destroy_inode+0x3c/0x70 kernel: [ 255.139589] [<ffffffff8108e6ec>] ? __do_page_fault+0x20c/0x500 kernel: [ 255.139597] [<ffffffff811e8336>] ? dput+0xb6/0x190 kernel: [ 255.139606] [<ffffffff811f05f6>] ? mntput+0x26/0x40 kernel: [ 255.139611] [<ffffffff811d2b94>] ? __fput+0x174/0x1e0 kernel: [ 255.139613] [<ffffffff814e2129>] __sys_sendmsg+0x49/0x90 kernel: [ 255.139615] [<ffffffff814e2182>] SyS_sendmsg+0x12/0x20 kernel: [ 255.139617] [<ffffffff815df092>] system_call_fastpath+0x12/0x17 kernel: [ 255.139619] ---[ end trace 5e6703e87d984f6b ]--- Signed-off-by: Mahesh Bandewar <maheshb@google.com> Reported-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Cc: Eric Dumazet <edumazet@google.com> Cc: Roopa Prabhu <roopa@cumulusnetworks.com> Cc: David S. Miller <davem@davemloft.net> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-04 04:46:24 +07:00
void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev,
gfp_t flags);
/* RTNL is used as a global lock for all changes to network configuration */
extern void rtnl_lock(void);
extern void rtnl_unlock(void);
extern int rtnl_trylock(void);
extern int rtnl_is_locked(void);
extern wait_queue_head_t netdev_unregistering_wq;
extern struct mutex net_mutex;
#ifdef CONFIG_PROVE_LOCKING
extern bool lockdep_rtnl_is_held(void);
#else
static inline bool lockdep_rtnl_is_held(void)
{
return true;
}
#endif /* #ifdef CONFIG_PROVE_LOCKING */
/**
* rcu_dereference_rtnl - rcu_dereference with debug checking
* @p: The pointer to read, prior to dereferencing
*
* Do an rcu_dereference(p), but check caller either holds rcu_read_lock()
* or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference()
*/
#define rcu_dereference_rtnl(p) \
rcu_dereference_check(p, lockdep_rtnl_is_held())
/**
* rcu_dereference_bh_rtnl - rcu_dereference_bh with debug checking
* @p: The pointer to read, prior to dereference
*
* Do an rcu_dereference_bh(p), but check caller either holds rcu_read_lock_bh()
* or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference_bh()
*/
#define rcu_dereference_bh_rtnl(p) \
rcu_dereference_bh_check(p, lockdep_rtnl_is_held())
/**
* rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL
* @p: The pointer to read, prior to dereferencing
*
* Return the value of the specified RCU-protected pointer, but omit
* both the smp_read_barrier_depends() and the ACCESS_ONCE(), because
* caller holds RTNL.
*/
#define rtnl_dereference(p) \
rcu_dereference_protected(p, lockdep_rtnl_is_held())
static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev)
{
return rtnl_dereference(dev->ingress_queue);
}
struct netdev_queue *dev_ingress_queue_create(struct net_device *dev);
#ifdef CONFIG_NET_INGRESS
void net_inc_ingress_queue(void);
void net_dec_ingress_queue(void);
#endif
net, sched: add clsact qdisc This work adds a generalization of the ingress qdisc as a qdisc holding only classifiers. The clsact qdisc works on ingress, but also on egress. In both cases, it's execution happens without taking the qdisc lock, and the main difference for the egress part compared to prior version of [1] is that this can be applied with _any_ underlying real egress qdisc (also classless ones). Besides solving the use-case of [1], that is, allowing for more programmability on assigning skb->priority for the mqprio case that is supported by most popular 10G+ NICs, it also opens up a lot more flexibility for other tc applications. The main work on classification can already be done at clsact egress time if the use-case allows and state stored for later retrieval f.e. again in skb->priority with major/minors (which is checked by most classful qdiscs before consulting tc_classify()) and/or in other skb fields like skb->tc_index for some light-weight post-processing to get to the eventual classid in case of a classful qdisc. Another use case is that the clsact egress part allows to have a central egress counterpart to the ingress classifiers, so that classifiers can easily share state (e.g. in cls_bpf via eBPF maps) for ingress and egress. Currently, default setups like mq + pfifo_fast would require for this to use, for example, prio qdisc instead (to get a tc_classify() run) and to duplicate the egress classifier for each queue. With clsact, it allows for leaving the setup as is, it can additionally assign skb->priority to put the skb in one of pfifo_fast's bands and it can share state with maps. Moreover, we can access the skb's dst entry (f.e. to retrieve tclassid) w/o the need to perform a skb_dst_force() to hold on to it any longer. In lwt case, we can also use this facility to setup dst metadata via cls_bpf (bpf_skb_set_tunnel_key()) without needing a real egress qdisc just for that (case of IFF_NO_QUEUE devices, for example). The realization can be done without any changes to the scheduler core framework. All it takes is that we have two a-priori defined minors/child classes, where we can mux between ingress and egress classifier list (dev->ingress_cl_list and dev->egress_cl_list, latter stored close to dev->_tx to avoid extra cacheline miss for moderate loads). The egress part is a bit similar modelled to handle_ing() and patched to a noop in case the functionality is not used. Both handlers are now called sch_handle_ingress() and sch_handle_egress(), code sharing among the two doesn't seem practical as there are various minor differences in both paths, so that making them conditional in a single handler would rather slow things down. Full compatibility to ingress qdisc is provided as well. Since both piggyback on TC_H_CLSACT, only one of them (ingress/clsact) can exist per netdevice, and thus ingress qdisc specific behaviour can be retained for user space. This means, either a user does 'tc qdisc add dev foo ingress' and configures ingress qdisc as usual, or the 'tc qdisc add dev foo clsact' alternative, where both, ingress and egress classifier can be configured as in the below example. ingress qdisc supports attaching classifier to any minor number whereas clsact has two fixed minors for muxing between the lists, therefore to not break user space setups, they are better done as two separate qdiscs. I decided to extend the sch_ingress module with clsact functionality so that commonly used code can be reused, the module is being aliased with sch_clsact so that it can be auto-loaded properly. Alternative would have been to add a flag when initializing ingress to alter its behaviour plus aliasing to a different name (as it's more than just ingress). However, the first would end up, based on the flag, choosing the new/old behaviour by calling different function implementations to handle each anyway, the latter would require to register ingress qdisc once again under different alias. So, this really begs to provide a minimal, cleaner approach to have Qdisc_ops and Qdisc_class_ops by its own that share callbacks used by both. Example, adding qdisc: # tc qdisc add dev foo clsact # tc qdisc show dev foo qdisc mq 0: root qdisc pfifo_fast 0: parent :1 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :2 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :3 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :4 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc clsact ffff: parent ffff:fff1 Adding filters (deleting, etc works analogous by specifying ingress/egress): # tc filter add dev foo ingress bpf da obj bar.o sec ingress # tc filter add dev foo egress bpf da obj bar.o sec egress # tc filter show dev foo ingress filter protocol all pref 49152 bpf filter protocol all pref 49152 bpf handle 0x1 bar.o:[ingress] direct-action # tc filter show dev foo egress filter protocol all pref 49152 bpf filter protocol all pref 49152 bpf handle 0x1 bar.o:[egress] direct-action A 'tc filter show dev foo' or 'tc filter show dev foo parent ffff:' will show an empty list for clsact. Either using the parent names (ingress/egress) or specifying the full major/minor will then show the related filter lists. Prior work on a mqprio prequeue() facility [1] was done mainly by John Fastabend. [1] http://patchwork.ozlabs.org/patch/512949/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-08 04:29:47 +07:00
#ifdef CONFIG_NET_EGRESS
void net_inc_egress_queue(void);
void net_dec_egress_queue(void);
#endif
void rtnetlink_init(void);
void __rtnl_unlock(void);
void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail);
#define ASSERT_RTNL() do { \
if (unlikely(!rtnl_is_locked())) { \
printk(KERN_ERR "RTNL: assertion failed at %s (%d)\n", \
__FILE__, __LINE__); \
dump_stack(); \
} \
} while(0)
net: add generic PF_BRIDGE:RTM_ FDB hooks This adds two new flags NTF_MASTER and NTF_SELF that can now be used to specify where PF_BRIDGE netlink commands should be sent. NTF_MASTER sends the commands to the 'dev->master' device for parsing. Typically this will be the linux net/bridge, or open-vswitch devices. Also without any flags set the command will be handled by the master device as well so that current user space tools continue to work as expected. The NTF_SELF flag will push the PF_BRIDGE commands to the device. In the basic example below the commands are then parsed and programmed in the embedded bridge. Note if both NTF_SELF and NTF_MASTER bits are set then the command will be sent to both 'dev->master' and 'dev' this allows user space to easily keep the embedded bridge and software bridge in sync. There is a slight complication in the case with both flags set when an error occurs. To resolve this the rtnl handler clears the NTF_ flag in the netlink ack to indicate which sets completed successfully. The add/del handlers will abort as soon as any error occurs. To support this new net device ops were added to call into the device and the existing bridging code was refactored to use these. There should be no required changes in user space to support the current bridge behavior. A basic setup with a SR-IOV enabled NIC looks like this, veth0 veth2 | | ------------ | bridge0 | <---- software bridging ------------ / / ethx.y ethx VF PF \ \ <---- propagate FDB entries to HW \ \ -------------------- | Embedded Bridge | <---- hardware offloaded switching -------------------- In this case the embedded bridge must be managed to allow 'veth0' to communicate with 'ethx.y' correctly. At present drivers managing the embedded bridge either send frames onto the network which then get dropped by the switch OR the embedded bridge will flood these frames. With this patch we have a mechanism to manage the embedded bridge correctly from user space. This example is specific to SR-IOV but replacing the VF with another PF or dropping this into the DSA framework generates similar management issues. Examples session using the 'br'[1] tool to add, dump and then delete a mac address with a new "embedded" option and enabled ixgbe driver: # br fdb add 22:35:19:ac:60:59 dev eth3 # br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static #br fdb add 22:35:19:ac:60:59 embedded dev eth3 #br fdb port mac addr flags veth0 22:35:19:ac:60:58 static veth0 9a:5f:81:f7:f6:ec local eth3 00:1b:21:55:23:59 local eth3 22:35:19:ac:60:59 static veth0 22:35:19:ac:60:57 static eth3 22:35:19:ac:60:59 local embedded #br fdb del 22:35:19:ac:60:59 embedded dev eth3 I added a couple lines to 'br' to set the flags correctly is all. It is my opinion that the merit of this patch is now embedded and SW bridges can both be modeled correctly in user space using very nearly the same message passing. [1] 'br' tool was published as an RFC here and will be renamed 'bridge' http://patchwork.ozlabs.org/patch/117664/ Thanks to Jamal Hadi Salim, Stephen Hemminger and Ben Hutchings for valuable feedback, suggestions, and review. v2: fixed api descriptions and error case with both NTF_SELF and NTF_MASTER set plus updated patch description. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-15 13:43:56 +07:00
extern int ndo_dflt_fdb_dump(struct sk_buff *skb,
struct netlink_callback *cb,
struct net_device *dev,
struct net_device *filter_dev,
rtnetlink: fdb dump: optimize by saving last interface markers fdb dumps spanning multiple skb's currently restart from the first interface again for every skb. This results in unnecessary iterations on the already visited interfaces and their fdb entries. In large scale setups, we have seen this to slow down fdb dumps considerably. On a system with 30k macs we see fdb dumps spanning across more than 300 skbs. To fix the problem, this patch replaces the existing single fdb marker with three markers: netdev hash entries, netdevs and fdb index to continue where we left off instead of restarting from the first netdev. This is consistent with link dumps. In the process of fixing the performance issue, this patch also re-implements fix done by commit 472681d57a5d ("net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump") (with an internal fix from Wilson Kok) in the following ways: - change ndo_fdb_dump handlers to return error code instead of the last fdb index - use cb->args strictly for dump frag markers and not error codes. This is consistent with other dump functions. Below results were taken on a system with 1000 netdevs and 35085 fdb entries: before patch: $time bridge fdb show | wc -l 15065 real 1m11.791s user 0m0.070s sys 1m8.395s (existing code does not return all macs) after patch: $time bridge fdb show | wc -l 35085 real 0m2.017s user 0m0.113s sys 0m1.942s Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: Wilson Kok <wkok@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-31 11:56:45 +07:00
int *idx);
extern int ndo_dflt_fdb_add(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
u16 vid,
u16 flags);
extern int ndo_dflt_fdb_del(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr,
u16 vid);
extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
struct net_device *dev, u16 mode,
u32 flags, u32 mask, int nlflags,
u32 filter_mask,
int (*vlan_fill)(struct sk_buff *skb,
struct net_device *dev,
u32 filter_mask));
#endif /* __LINUX_RTNETLINK_H */