Signed-off-by: NMahesh Bandewar <maheshb@google.com>
Signed-off-by: NAndy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The Churn Detection machines detect the situation where a port is operable,
but the Actor and Partner have not attached the link to an Aggregator and
brought the link into operation within a bound time period. Under normal
operation of the LACP, agreement between Actor and Partner should be reached
very rapidly. Continued failure to reach agreement can be symptomatic of
device failure.

Actor-churn-detection state-machine
Reviewed-by: NNikolay Aleksandrov <nikolay@redhat.com>

===================================

BEGIN=True + PortEnable=False
           |
           v
 +------------------------+   ActorPort.Sync=True  +------------------+
 |   ACTOR_CHURN_MONITOR  | ---------------------> |  NO_ACTOR_CHURN  |
 |========================|                        |==================|
 |    ActorChurn=False    |  ActorPort.Sync=False  | ActorChurn=False |
 | ActorChurn.Timer=Start | <--------------------- |                  |
 +------------------------+                        +------------------+
           |                                                ^
           |                                                |
  ActorChurn.Timer=Expired                                  |
           |                                       ActorPort.Sync=True
           |                                                |
           |                +-----------------+             |
           |                |   ACTOR_CHURN   |             |
           |                |=================|             |
           +--------------> | ActorChurn=True | ------------+
                            |                 |
                            +-----------------+

Similar for the Partner-churn-detection.
Signed-off-by: NMahesh Bandewar <maheshb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The 802.1AX standard states:
"The DA in LACPDUs is the Slow_Protocols_Multicast address."

This patch enforces that and drops LACPDUs with destination MAC
addresses other than Slow_Protocols_Multicast address
Signed-off-by: NMahesh Bandewar <maheshb@google.com>
Reviewed-by: NNikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When a slave is added to a bond and it is not in full duplex mode,
AD_PORT_LACP_ENABLED flag is cleared, due to this LACP PDU is not sent
on slave. When the duplex is changed to full, the flag needs to be set
to send LACP PDU.

Cc: Andy Gospodarek <gospo@cumulusnetworks.com>
Reviewed-by: NNikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: NSatish Ashok <sashok@cumulusnetworks.com>
Signed-off-by: NJonathan Toppins <jtoppins@cumulusnetworks.com>
Signed-off-by: NJay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch attempts to fix the following problems when an actor or
partner's aggregator is not active:
    1. a slave's lacp port state is marked as AD_STATE_SYNCHRONIZATION
       even if it is attached to an inactive aggregator. LACP advertises
       this state to the partner, making the partner think he can move
       into COLLECTING_DISTRIBUTING state even though this link will not
       pass traffic on the local side

    2. a slave goes into COLLECTING_DISTRIBUTING state without checking
       if the aggregator is actually active

    3. when in COLLECTING_DISTRIBUTING state, the partner parameters may
       change, e.g. the partner_oper_port_state.SYNCHRONIZATION. The
       local mux machine is not reacting to the change and continue to
       keep the slave and bond up

    4. When bond slave leaves an inactive aggregator and joins an active
       aggregator, the actor oper port state need to update to SYNC state.

v2:
 * fix style issues in bond_3ad.c

Cc: Andy Gospodarek <gospo@cumulusnetworks.com>
Reviewed-by: NNikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: NWilson Kok <wkok@cumulusnetworks.com>
Signed-off-by: NJonathan Toppins <jtoppins@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds [2.5|20|40|56] Gbps enum definition, and fixes
aggregated bandwidth calculation based on above slave links.

CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: David S. Miller <davem@davemloft.net>
Signed-off-by: NJianhua Xie <jianhua.xie@freescale.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Port Key was determined as 16 bits according to the link speed,
duplex and user key (which is yet not supported).  In the old
speed field, 5 bits are for speed [1|10|100|1000|10000]Mbps as
below:
--------------------------------------------------------------
Port key :| User key        | Speed         |       Duplex|
--------------------------------------------------------------
    16                  6               1               0
This patch keeps the old layout, but changes AD_LINK_SPEED_BITMASK
from bit type to an enum type.  In this way, the speed field can
expand speed type from 5 to 32.

CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: David S. Miller <davem@davemloft.net>
Signed-off-by: NJianhua Xie <jianhua.xie@freescale.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This ways drivers like cxgb4 don't need to do ugly relative includes.
Reported-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Earlier change to use usable slave array for TLB mode had an additional
performance advantage. So extending the same logic to all other modes
that use xmit-hash for slave selection (viz 802.3AD, and XOR modes).
Also consolidating this with the earlier TLB change.

The main idea is to build the usable slaves array in the control path
and use that array for slave selection during xmit operation.

Measured performance in a setup with a bond of 4x1G NICs with 200
instances of netperf for the modes involved (3ad, xor, tlb)
cmd: netperf -t TCP_RR -H <TargetHost> -l 60 -s 5

Mode        TPS-Before   TPS-After

802.3ad   : 468,694      493,101
TLB (lb=0): 392,583      392,965
XOR       : 475,696      484,517
Signed-off-by: NMahesh Bandewar <maheshb@google.com>
Signed-off-by: NNikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

First adjust a couple of locking comments that were left inaccurate,
then adjust comments to use the netdev styling and remove extra new
lines where necessary and add a couple of new lines between declarations
and code. These are all trivial styling changes, no functional change.
Also removed a couple of outdated or obvious comments.
This patch is by no means a complete fix of all netdev style violations
but it gets the bonding closer.
Signed-off-by: NNikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that we have bond->mode_lock, we can remove the state_machine_lock
and use it in its place. There're no fast paths requiring the per-port
spinlocks so it should be okay to consolidate them into mode_lock.
Also move it inside the unbinding function as we don't want to expose
mode_lock outside of the specific modes.
Suggested-by: NJay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: NNikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

curr_slave_lock is now a misleading name, a much better name is
mode_lock as it'll be used for each mode's purposes and it's no longer
necessary to use a rwlock, a simple spinlock is enough.
Suggested-by: NJay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: NNikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove the read_lock in bond_3ad_lacpdu_recv() since when the slave is
being released its rx_handler is removed before 3ad unbind, so even if
packets arrive, they won't see the slave in an inconsistent state.
Signed-off-by: NNikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In 3ad mode the only syncing needed by bond->lock is for the wq
and the recv handler, so change them to use curr_slave_lock.
There're no locking dependencies here as 3ad doesn't use
curr_slave_lock at all.
Signed-off-by: NNikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To maintain the same message structure as netdev_* functions print.

CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Several functions left out cause we might not have at that time a valid
bond/slave/port.

Also, converted severa pr_ratelimited into net_ratelimited.

CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

They're verifying the same thing (except of IFF_UP, which is implied for
netif_running(), which is also a prerequisite).

CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Also, remove the IFF_UP verification cause we can't be netif_running() with
being also IFF_UP.

CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The struct ad_slave_info is very huge, and only be used for 802.3ad mode,
so alloc the structure dynamically could save 356 Bits for every slave in
non 802.3ad mode.

Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NDing Tianhong <dingtianhong@huawei.com>
Acked-by: NVeaceslav Falico <vfalico@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Modified the hash function to return just hash separating from the
modulo operation that can be performed by the caller. This is to
make way for the tlb mode to use the same hashing policies that
are used in the 802.3ad and Xor mode.

Change-Id: I276609e87e0ca213c4d1b17b79c5e0b0f3d0dd6f
Signed-off-by: NMahesh Bandewar <maheshb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Only ratelimit the ones that might spam, omiting the ones from
enslave/deslave.

CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Replace kfree_skb with dev_kfree_skb_any in functions that can
be called in hard irq and other contexts.
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Veaceslav has reported and fix this problem by commit f2ebd477
(bonding: restructure locking of bond_ab_arp_probe()). According Jay's
opinion, the current solution is not very well, because the notification
is to indicate that the interface has actually changed state in a meaningful
way, but these calls in the ab ARP monitor are internal settings of the flags
to allow the ARP monitor to search for a slave to become active when there are
no active slaves. The flag setting to active or backup is to permit the ARP
monitor's response logic to do the right thing when deciding if the test
slave (current_arp_slave) is up or not.

So the best way to fix the problem is that we should not send a notification
when the slave is in testing state, and check the state at the end of the
monitor, if the slave's state recover, avoid to send pointless notification
twice. And RTNL is really a big lock, hold it regardless the slave's state
changed or not when the current_active_slave is null will loss performance
(every 100ms), so we should hold it only when the slave's state changed and
need to notify.

I revert the old commit and add new modifications.

Cc: Jay Vosburgh <fubar@us.ibm.com>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NDing Tianhong <dingtianhong@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The problem was introduced by the commit 1d3ee88a
(bonding: add netlink attributes to slave link dev).
The bond_set_active_slave() and bond_set_backup_slave()
will use rtmsg_ifinfo to send slave's states, so these
two functions should be called in RTNL.

In 802.3ad mode, acquiring RTNL for the __enable_port and
__disable_port cases is difficult, as those calls generally
already hold the state machine lock, and cannot unconditionally
call rtnl_lock because either they already hold RTNL (for calls
via bond_3ad_unbind_slave) or due to the potential for deadlock
with bond_3ad_adapter_speed_changed, bond_3ad_adapter_duplex_changed,
bond_3ad_link_change, or bond_3ad_update_lacp_rate.  All four of
those are called with RTNL held, and acquire the state machine lock
second.  The calling contexts for __enable_port and __disable_port
already hold the state machine lock, and may or may not need RTNL.

According to the Jay's opinion, I don't think it is a problem that
the slave don't send notify message synchronously when the status
changed, normally the state machine is running every 100 ms, send
the notify message at the end of the state machine if the slave's
state changed should be better.

I fix the problem through these steps:

1). add a new function bond_set_slave_state() which could change
    the slave's state and call rtmsg_ifinfo() according to the input
    parameters called notify.

2). Add a new slave parameter which called should_notify, if the slave's state
    changed and don't notify yet, the parameter will be set to 1, and then if
    the slave's state changed again, the param will be set to 0, it indicate that
    the slave's state has been restored, no need to notify any one.

3). the __enable_port and __disable_port should not call rtmsg_ifinfo
    in the state machine lock, any change in the state of slave could
    set a flag in the slave, it will indicated that an rtmsg_ifinfo
    should be called at the end of the state machine.

Cc: Jay Vosburgh <fubar@us.ibm.com>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NDing Tianhong <dingtianhong@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Make the error case return early.
Make the normal return at the bottom of the function.
Reduces indent for readability.
Signed-off-by: NJoe Perches <joe@perches.com>
Reviewed-by: NDing Tianhong <dingtianhong@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It's smaller and faster for some architectures.
Signed-off-by: NJoe Perches <joe@perches.com>
Reviewed-by: NDing Tianhong <dingtianhong@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

aggregator_identifier is used to assign unique aggregator identifiers
to aggregators of a bond during device enslaving.

aggregator_identifier is currently a global variable that is zeroed in
bond_3ad_initialize().

This sequence will lead to duplicate aggregator identifiers for eth1 and eth3:

create bond0
change bond0 mode to 802.3ad
enslave eth0 to bond0 		//eth0 gets agg id 1
enslave eth1 to bond0 		//eth1 gets agg id 2
create bond1
change bond1 mode to 802.3ad
enslave eth2 to bond1		//aggregator_identifier is reset to 0
				//eth2 gets agg id 1
enslave eth3 to bond0 		//eth3 gets agg id 2

Fix this by making aggregator_identifier private to the bond.
Signed-off-by: NJiri Bohac <jbohac@suse.cz>
Acked-by: NVeaceslav Falico <vfalico@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ether_addr_copy is smaller and faster for some architectures.

This relies on a stack frame being at least __aligned(2)
for one use of an Ethernet address on the stack.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add missing terminating newlines.
Convert uses of pr_info to pr_cont in bond_check_params.
Standardize upper/lower case styles.
Typo fixes, remove unnecessary parentheses and periods.
Alignment neatening.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently, the implementation is meaningless - once again, we take the
slave structure and use it after we've exited RCU critical section.

Fix this by removing the rcu_read_lock() from __get_active_agg(), and
ensuring that all its callers are holding RCU.

Fixes: be79bd04 ("bonding: add RCU for bond_3ad_state_machine_handler()")
CC: dingtianhong@huawei.com
CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently, the RCU read lock usage is just wrong - it gets the slave struct
under RCU and continues to use it when RCU lock is released.

However, it's still safe to do this cause we didn't need the
rcu_read_lock() initially - all of the __get_first_agg() callers are either
holding RCU read lock or the RTNL lock, so that we can't sync while in it.

Fixes: be79bd04 ("bonding: add RCU for bond_3ad_state_machine_handler()")
CC: dingtianhong@huawei.com
CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently, its usage is just plainly wrong. It first gets a slave under
RCU, and, after releasing the RCU lock, continues to use it - whilst it can
be freed.

Fix this by ensuring that bond_3ad_set_carrier() holds RCU till it uses its
slave (or its agg).

Fixes: be79bd04 ("bonding: add RCU for bond_3ad_state_machine_handler()")
CC: dingtianhong@huawei.com
CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

That code has been around for ages without being used.

CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It's a huge mess currently, that is really hard to read. This cleanup
doesn't touch the logic at all, it only breaks easy-to-fix long lines and
updates comment styles.

CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I'm sure the operand slave and bond for the function will not
be NULL, so the check for the bond will not make any sense, so
remove the judgement, and the return value was useless here,
remove the unwanted return value.

The comments for the bond 3ad is too old, cleanup some errors
and warming.
Signed-off-by: NDing Tianhong <dingtianhong@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The bond_dev_queue_xmit() will always return 0, and as a fast path,
it is inappropriate to check the res value when xmit every package,
so remove the res check and avoid once judgement for xmit.
Signed-off-by: NDing Tianhong <dingtianhong@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use possibly more efficient ether_addr_equal_64bits
to instead of memcmp.

Modify the MAC_ADDR_COMPARE to MAC_ADDR_EQUAL, this looks more
appropriate.

The comments for the bond 3ad is too old, cleanup some errors
and warming.
Suggested-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDing Tianhong <dingtianhong@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The bond_3ad_handle_link_change is called with RTNL only,
and the function will modify the port's information with
no further locking, it will not mutex against bond state
machine and incoming LACPDU which do not hold RTNL, So I
add __get_state_machine_lock to protect the port.

But it is not a critical bug, it exist since day one, and till
now it has never been hit and reported, because changes to
speed is very rare, and will not occur critical problem.

The comments in the function is very old, cleanup it and
add a new pr_debug to debug the port message.
Signed-off-by: NDing Tianhong <dingtianhong@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jay Vosburgh said that the bond_3ad_adapter_duplex_changed is
called with RTNL only, and the function will modify the port's
information with no further locking, it will not mutex against
bond state machine and incoming LACPDU which do not hold RTNL,
So I add __get_state_machine_lock to protect the port.

But it is not a critical bug, it exist since day one, and till
now it has never been hit and reported, because changes to
speed is very rare, and will not occur critical problem.

The comments in the function is very old, cleanup it.
Suggested-by: NJay Vosburgh <fubar@us.ibm.com>
Signed-off-by: NDing Tianhong <dingtianhong@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>