From 06f6d1094aa0992432b1e2a0920b0ee86ccd83bf Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 15 Jul 2015 21:52:51 +0200 Subject: bonding: fix destruction of bond with devices different from arphrd_ether When the bonding is being unloaded and the netdevice notifier is unregistered it executes NETDEV_UNREGISTER for each device which should remove the bond's proc entry but if the device enslaved is not of ARPHRD_ETHER type and is in front of the bonding, it may execute bond_release_and_destroy() first which would release the last slave and destroy the bond device leaving the proc entry and thus we will get the following error (with dynamic debug on for bond_netdev_event to see the events order): [ 908.963051] eql: event: 9 [ 908.963052] eql: IFF_SLAVE [ 908.963054] eql: event: 2 [ 908.963056] eql: IFF_SLAVE [ 908.963058] eql: event: 6 [ 908.963059] eql: IFF_SLAVE [ 908.963110] bond0: Releasing active interface eql [ 908.976168] bond0: Destroying bond bond0 [ 908.976266] bond0 (unregistering): Released all slaves [ 908.984097] ------------[ cut here ]------------ [ 908.984107] WARNING: CPU: 0 PID: 1787 at fs/proc/generic.c:575 remove_proc_entry+0x112/0x160() [ 908.984110] remove_proc_entry: removing non-empty directory 'net/bonding', leaking at least 'bond0' [ 908.984111] Modules linked in: bonding(-) eql(O) 9p nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel ppdev qxl drm_kms_helper snd_hda_codec_generic aesni_intel ttm aes_x86_64 glue_helper pcspkr lrw gf128mul ablk_helper cryptd snd_hda_intel virtio_console snd_hda_codec psmouse serio_raw snd_hwdep snd_hda_core 9pnet_virtio 9pnet evdev joydev drm virtio_balloon snd_pcm snd_timer snd soundcore i2c_piix4 i2c_core pvpanic acpi_cpufreq parport_pc parport processor thermal_sys button autofs4 ext4 crc16 mbcache jbd2 hid_generic usbhid hid sg sr_mod cdrom ata_generic virtio_blk virtio_net floppy ata_piix e1000 libata ehci_pci virtio_pci scsi_mod uhci_hcd ehci_hcd virtio_ring virtio usbcore usb_common [last unloaded: bonding] [ 908.984168] CPU: 0 PID: 1787 Comm: rmmod Tainted: G W O 4.2.0-rc2+ #8 [ 908.984170] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 908.984172] 0000000000000000 ffffffff81732d41 ffffffff81525b34 ffff8800358dfda8 [ 908.984175] ffffffff8106c521 ffff88003595af78 ffff88003595af40 ffff88003e3a4280 [ 908.984178] ffffffffa058d040 0000000000000000 ffffffff8106c59a ffffffff8172ebd0 [ 908.984181] Call Trace: [ 908.984188] [] ? dump_stack+0x40/0x50 [ 908.984193] [] ? warn_slowpath_common+0x81/0xb0 [ 908.984196] [] ? warn_slowpath_fmt+0x4a/0x50 [ 908.984199] [] ? remove_proc_entry+0x112/0x160 [ 908.984205] [] ? bond_destroy_proc_dir+0x26/0x30 [bonding] [ 908.984208] [] ? bond_net_exit+0x8e/0xa0 [bonding] [ 908.984217] [] ? ops_exit_list.isra.4+0x37/0x70 [ 908.984225] [] ? unregister_pernet_operations+0x8d/0xd0 [ 908.984228] [] ? unregister_pernet_subsys+0x1d/0x30 [ 908.984232] [] ? bonding_exit+0x23/0xdba [bonding] [ 908.984236] [] ? SyS_delete_module+0x18a/0x250 [ 908.984241] [] ? task_work_run+0x89/0xc0 [ 908.984244] [] ? entry_SYSCALL_64_fastpath+0x16/0x75 [ 908.984247] ---[ end trace 7c006ed4abbef24b ]--- Thus remove the proc entry manually if bond_release_and_destroy() is used. Because of the checks in bond_remove_proc_entry() it's not a problem for a bond device to change namespaces (the bug fixed by the Fixes commit) but since commit f9399814927ad ("bonding: Don't allow bond devices to change network namespaces.") that can't happen anyway. Reported-by: Carol Soto Signed-off-by: Nikolay Aleksandrov Fixes: a64d49c3dd50 ("bonding: Manage /proc/net/bonding/ entries from the netdev events") Tested-by: Carol L Soto Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/bonding/bond_main.c') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 317a49480475..ec1404ec4d2f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1916,6 +1916,7 @@ static int bond_release_and_destroy(struct net_device *bond_dev, bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; netdev_info(bond_dev, "Destroying bond %s\n", bond_dev->name); + bond_remove_proc_entry(bond); unregister_netdevice(bond_dev); } return ret; -- cgit v1.2.3 From 7d5cd2ce5292b45e555de776cb9e72975a07460d Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 15 Jul 2015 22:57:01 +0200 Subject: bonding: correctly handle bonding type change on enslave failure If the bond is enslaving a device with different type it will be setup by it, but if after being setup the enslave fails the bond doesn't switch back its type and also keeps pointers to foreign structures that can be long gone. Thus revert back any type changes if the enslave failed and the bond had to change its type. Example: Before patch: $ echo lo > bond0/bonding/slaves -bash: echo: write error: Cannot assign requested address $ ip l sh bond0 20: bond0: mtu 1500 qdisc noop state DOWN mode DEFAULT group default link/loopback 16:54:78:34:bd:41 brd 00:00:00:00:00:00 $ echo +eth1 > bond0/bonding/slaves $ ip l sh bond0 20: bond0: mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000 link/ether 52:54:00:3f:47:69 brd ff:ff:ff:ff:ff:ff (notice the MASTER flag is gone) After patch: $ echo lo > bond0/bonding/slaves -bash: echo: write error: Cannot assign requested address $ ip l sh bond0 21: bond0: mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000 link/ether 6e:66:94:f6:07:fc brd ff:ff:ff:ff:ff:ff $ echo +eth1 > bond0/bonding/slaves $ ip l sh bond0 21: bond0: mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 1000 link/ether 52:54:00:3f:47:69 brd ff:ff:ff:ff:ff:ff Signed-off-by: Nikolay Aleksandrov Fixes: e36b9d16c6a6 ("bonding: clean muticast addresses when device changes type") Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'drivers/net/bonding/bond_main.c') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ec1404ec4d2f..1d26d6700c1d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1725,9 +1725,16 @@ err_free: err_undo_flags: /* Enslave of first slave has failed and we need to fix master's mac */ - if (!bond_has_slaves(bond) && - ether_addr_equal_64bits(bond_dev->dev_addr, slave_dev->dev_addr)) - eth_hw_addr_random(bond_dev); + if (!bond_has_slaves(bond)) { + if (ether_addr_equal_64bits(bond_dev->dev_addr, + slave_dev->dev_addr)) + eth_hw_addr_random(bond_dev); + if (bond_dev->type != ARPHRD_ETHER) { + ether_setup(bond_dev); + bond_dev->flags |= IFF_MASTER; + bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; + } + } return res; } -- cgit v1.2.3 From a951bc1e6ba58f11df5ed5ddc41311e10f5fd20b Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Thu, 16 Jul 2015 16:30:02 +0800 Subject: bonding: correct the MAC address for "follow" fail_over_mac policy The "follow" fail_over_mac policy is useful for multiport devices that either become confused or incur a performance penalty when multiple ports are programmed with the same MAC address, but the same MAC address still may happened by this steps for this policy: 1) echo +eth0 > /sys/class/net/bond0/bonding/slaves bond0 has the same mac address with eth0, it is MAC1. 2) echo +eth1 > /sys/class/net/bond0/bonding/slaves eth1 is backup, eth1 has MAC2. 3) ifconfig eth0 down eth1 became active slave, bond will swap MAC for eth0 and eth1, so eth1 has MAC1, and eth0 has MAC2. 4) ifconfig eth1 down there is no active slave, and eth1 still has MAC1, eth2 has MAC2. 5) ifconfig eth0 up the eth0 became active slave again, the bond set eth0 to MAC1. Something wrong here, then if you set eth1 up, the eth0 and eth1 will have the same MAC address, it will break this policy for ACTIVE_BACKUP mode. This patch will fix this problem by finding the old active slave and swap them MAC address before change active slave. Signed-off-by: Ding Tianhong Tested-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'drivers/net/bonding/bond_main.c') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1d26d6700c1d..e1ccefce9a9d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -625,6 +625,23 @@ static void bond_set_dev_addr(struct net_device *bond_dev, call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev); } +static struct slave *bond_get_old_active(struct bonding *bond, + struct slave *new_active) +{ + struct slave *slave; + struct list_head *iter; + + bond_for_each_slave(bond, slave, iter) { + if (slave == new_active) + continue; + + if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr)) + return slave; + } + + return NULL; +} + /* bond_do_fail_over_mac * * Perform special MAC address swapping for fail_over_mac settings @@ -652,6 +669,9 @@ static void bond_do_fail_over_mac(struct bonding *bond, if (!new_active) return; + if (!old_active) + old_active = bond_get_old_active(bond, new_active); + if (old_active) { ether_addr_copy(tmp_mac, new_active->dev->dev_addr); ether_addr_copy(saddr.sa_data, -- cgit v1.2.3