bnx2x driver already handles TSO for GRE, current code
is the same for IPIP.
Performance results : (Note we are now limited by receiver,
as it does not support GRO for IPIP yet)
Before patch :
lpq83:~# ./netperf -H 7.7.9.84 -Cc
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.9.84 () port 0 AF_INET
Recv Send Send Utilization Service Demand
Socket Socket Message Elapsed Send Recv Send Recv
Size Size Size Time Throughput local remote local remote
bytes bytes bytes secs. 10^6bits/s % S % S us/KB us/KB
87380 16384 16384 10.00 7710.19 4.52 6.62 1.152 1.687
After patch :
lpq83:~# ./netperf -H 7.7.9.84 -Cc
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.9.84 () port 0 AF_INET
Recv Send Send Utilization Service Demand
Socket Socket Message Elapsed Send Recv Send Recv
Size Size Size Time Throughput local remote local remote
bytes bytes bytes secs. 10^6bits/s % S % S us/KB us/KB
87380 16384 16384 10.00 8532.40 2.55 7.73 0.588 1.781
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now inet_gso_segment() is stackable, its relatively easy to
implement GSO/TSO support for IPIP
Performance results, when segmentation is done after tunnel
device (as no NIC is yet enabled for TSO IPIP support) :
Before patch :
lpq83:~# ./netperf -H 7.7.9.84 -Cc
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.9.84 () port 0 AF_INET
Recv Send Send Utilization Service Demand
Socket Socket Message Elapsed Send Recv Send Recv
Size Size Size Time Throughput local remote local remote
bytes bytes bytes secs. 10^6bits/s % S % S us/KB us/KB
87380 16384 16384 10.00 3357.88 5.09 3.70 2.983 2.167
After patch :
lpq83:~# ./netperf -H 7.7.9.84 -Cc
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.9.84 () port 0 AF_INET
Recv Send Send Utilization Service Demand
Socket Socket Message Elapsed Send Recv Send Recv
Size Size Size Time Throughput local remote local remote
bytes bytes bytes secs. 10^6bits/s % S % S us/KB us/KB
87380 16384 16384 10.00 7710.19 4.52 6.62 1.152 1.687
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to support GSO on IPIP, we need to make
inet_gso_segment() stackable.
It should not assume network header starts right after mac
header.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch makes gre_handle_offloads() more generic
and rename it to iptunnel_handle_offloads()
This will be used to add GSO/TSO support to IPIP tunnels.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While implementing GSO/TSO support for IPIP, I found skb_segment()
was assuming network header was immediately following mac header.
Its not really true in the case inet_gso_segment() is stacked :
By the time tcp_gso_segment() is called, network header points
to the inner IP header.
Let's instead assume nothing and pick the current offsets found in
original skb, we have skb_headers_offset_update() helper for that.
Also move the csum_start update inside skb_headers_offset_update()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ipv6_gso_send_check() and ipv6_gso_segment() are called by
skb_mac_gso_segment() under rcu lock, no need to use
rcu_read_lock() / rcu_read_unlock()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently we log a message whenever pcie_enable_error_reporting fails.
The message clutters up logs, especially when we don't support it for VFs.
Instead enable this only for PFs and log a message when the call succeeds.
Signed-off-by: Ajit Khaparde <ajit.khaparde@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are a mix of function prototypes with and without extern
in the kernel sources. Standardize on not using extern for
function prototypes.
Function prototypes don't need to be written with extern.
extern is assumed by the compiler. Its use is as unnecessary as
using auto to declare automatic/local variables in a block.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are a mix of function prototypes with and without extern
in the kernel sources. Standardize on not using extern for
function prototypes.
Function prototypes don't need to be written with extern.
extern is assumed by the compiler. Its use is as unnecessary as
using auto to declare automatic/local variables in a block.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are a mix of function prototypes with and without extern
in the kernel sources. Standardize on not using extern for
function prototypes.
Function prototypes don't need to be written with extern.
extern is assumed by the compiler. Its use is as unnecessary as
using auto to declare automatic/local variables in a block.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are a mix of function prototypes with and without extern
in the kernel sources. Standardize on not using extern for
function prototypes.
Function prototypes don't need to be written with extern.
extern is assumed by the compiler. Its use is as unnecessary as
using auto to declare automatic/local variables in a block.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
inet_gso_segment() and inet_gso_send_check() are called by
skb_mac_gso_segment() under rcu lock, no need to use
rcu_read_lock() / rcu_read_unlock()
Avoid calling ip_hdr() twice per function.
We can use ip_send_check() helper.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiri Pirko says:
====================
bonding: introduce bonding options Netlink support
This patchset basically allows "mode" and "active_slave" bonding options
to be propagated and set up via standart RT Netlink interface.
In future other options can be easily added as well.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
no longer needed since bond_option_active_slave_set() can be used
instead.
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
The backbone gw check has to be VLAN specific so that code
using it can specify VID where the check has to be done.
In the TT code, the check has been moved into the
tt_global_add() function so that it can be performed on a
per-entry basis instead of ignoring all the TT data received
from another backbone node. Only TT global entries belonging
to the VLAN where the backbone node is connected to are
skipped.
All the other spots where the TT code was checking whether a
node is a backbone have been removed.
Moreover, batadv_bla_is_backbone_gw_orig() now returns bool
since it used to return only 1 or 0.
Cc: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Instead of unconditionally removing all the TT entries
served by a given originator, make tt_global_orig_del()
remove only entries matching a given VLAN identifier
provided as argument.
If such argument is negative all the global entries
served by the originator are removed.
This change is used into the BLA code to purge entries
served by a newly discovered Backbone node, but limiting
the operation only to those connected to the VLAN where the
backbone has been discovered.
Cc: Simon Wunderlich <siwu@hrz.tu-chemnitz.de>
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
This change allows nodes to handle the TT table on a
per-VLAN basis. This is needed because nodes may have to
store only some of the global entries advertised by another
node.
In this scenario such nodes would re-create only a partial
global table and would not be able to compute a correct CRC
anymore.
This patch splits the logic and introduces one CRC per VLAN.
In this way a node fetching only some entries belonging to
some VLANs is still able to compute the needed CRCs and
still check the table correctness.
With this patch the shape of the TVLV-TT is changed too
because now a node needs to advertise all the CRCs of all
the VLANs that it is wired to.
The debug output of the local Translation Table now shows
the CRC along with each entry since there is not a common
value for the entire table anymore.
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
A TT response may be prepared and sent while the local or
global translation table is getting updated.
The worst case is when one of the tables is accessed after
its content has been recently updated but the metadata
(TTVN/CRC) has not yet. In this case the reader will get a
table content which does not match the TTVN/CRC.
This will lead to an inconsistent state and so to a TT
recovery.
To avoid entering this situation, put a lock around those TT
operations recomputing the metadata and around the TT
Response creation (the latter is the only reader that
accesses the metadata together with the table).
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
this comment refers to the old batmand codebase and does
not make sense anymore. Remove it
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
With this patch the functions batadv_send_skb_unicast() and
batadv_send_skb_unicast_4addr() are further refined into
batadv_send_skb_via_tt(), batadv_send_skb_via_tt_4addr() and
batadv_send_skb_via_gw(). This way we avoid any "guessing" about where to send
a packet in the unicast forwarding methods and let the callers decide.
This is going to be useful for the upcoming multicast related patches in
particular.
Further, the return values were polished a little to use the more
appropriate NET_XMIT_* defines.
Signed-off-by: Linus Lüssing <linus.luessing@web.de>
Acked-by: Antonio Quartulli <antonio@meshcoding.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
AP isolation has to be enabled on one VLAN interface only.
This patch moves the AP isolation attribute to the per-vlan
interface attribute set, enabling it to have a different
value depending on the selected vlan.
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Each VLAN can now have its own set of attributes which are
exported through a new subfolder in the sysfs tree.
Each VLAN created on top of a soft_iface will have its own
subfolder.
The subfolder is named "vlan%VID" and it is created inside
the "mesh" sysfs folder belonging to batman-adv.
Attributes corresponding to the untagged LAN are stored in
the root sysfs folder as before.
This patch also creates all the needed macros and data
structures to easily handle new VLAN spacific attributes.
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Since batman-adv is now fully VLAN-aware, a proper framework
able to handle per-vlan-interface attributes is needed.
Those attributes will affect the associated VLAN interface
only, rather than the real soft_iface (which would result
in every vlan interface having the same attribute
configuration).
To make the code simpler and easier to extend, attributes
associated to the standalone soft_iface are now treated
like belonging to yet another vlan having a special vid.
This vid is different from the others because it is made up
by all zeros and the VLAN_HAS_TAG bit is not set.
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
The same IP subnet can be used on different VLANs, therefore
DAT has to differentiate whether the IP to resolve belongs
to one or the other virtual LAN.
To accomplish this task DAT has to deal with the VLAN tag
and store it together with each ARP entry.
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
The gateway code is now adapted in order to correctly
interact with the Translation Table component by using the
vlan ID
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
now that each TT entry is characterised by a VLAN ID, the
latter has to be taken into consideration when computing the
local/global table CRC as it would be theoretically possible
to have the same client in two different VLANs
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
To make the translation table code VLAN-aware, each entry
must carry the VLAN ID which it belongs to. This patch adds
such attribute to the related TT structures.
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
My university will stop email service for alumni in january 2014, please
use my new e-mail address instead.
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Fix bogus merge conflict resolution by checking the return
values of the skb preparation routines.
Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
Randy found that if network namespace not enabled then
nd_net does not exist and would cause compilation failure.
This is handled correctly by using the dev_net() macro.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove the specialized code in __tcp_retransmit_skb() that tries to trim
any ACKed payload preceding a FIN before we retransmit (this was added
in 1999 in v2.2.3pre3). This trimming code was made unreachable by the
more general code added above it that uses tcp_trim_head() to trim any
ACKed payload, with or without a FIN (this was added in "[NET]: Add
segmentation offload support to TCP." in 2002 circa v2.5.33).
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Under certain low traffic conditions, the single core
devices with multiple Rx/Tx queues (MQ mode) may reach
soft lockup due to gfar_poll not returning in proper time.
The following exception was obtained using iperf on a 100Mbit
half-duplex link, for a p1010 single core device:
BUG: soft lockup - CPU#0 stuck for 23s! [iperf:2847]
Modules linked in:
CPU: 0 PID: 2847 Comm: iperf Not tainted 3.12.0-rc3 #16
task: e8bf8000 ti: eeb16000 task.ti: ee646000
NIP: c0255b6c LR: c0367ae8 CTR: c0461c18
REGS: eeb17e70 TRAP: 0901 Not tainted (3.12.0-rc3)
MSR: 00029000 <CE,EE,ME> CR: 44228428 XER: 20000000
GPR00: c0367ad4 eeb17f20 e8bf8000 ee01f4b4 00000008 ffffffff ffffffff
00000000
GPR08: 000000c0 00000008 000000ff ffffffc0 000193fe
NIP [c0255b6c] find_next_bit+0xb8/0xc4
LR [c0367ae8] gfar_poll+0xc8/0x1d8
Call Trace:
[eeb17f20] [c0367ad4] gfar_poll+0xb4/0x1d8 (unreliable)
[eeb17f70] [c0422100] net_rx_action+0xa4/0x158
[eeb17fa0] [c003ec6c] __do_softirq+0xcc/0x17c
[eeb17ff0] [c000c28c] call_do_softirq+0x24/0x3c
[ee647cc0] [c0004660] do_softirq+0x6c/0x94
[ee647ce0] [c003eb9c] local_bh_enable+0x9c/0xa0
[ee647cf0] [c0454fe8] tcp_prequeue_process+0xa4/0xdc
[ee647d10] [c0457e44] tcp_recvmsg+0x498/0x96c
[ee647d80] [c047b630] inet_recvmsg+0x40/0x64
[ee647da0] [c040ca8c] sock_recvmsg+0x90/0xc0
[ee647e30] [c040edb8] SyS_recvfrom+0x98/0xfc
To prevent this, the outer while() loop has been removed
allowing gfar_poll() to return faster even if there's
still budget left. Also, there's no need to recompute
the budget per Rx queue anymore.
Signed-off-by: Claudiu Manoil <claudiu.manoil@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The rtmsg_fib function doesn't modify this argument so mark
it const.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current test works fine in practice. The "amount" variable is
actually used as a boolean so negative values or any non-zero values
count as "true". However since we don't allow numbers greater than one,
let's not allow negative numbers either.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
fib_table_lookup has included the rcu lock protection.
Signed-off-by: baker.zhang <baker.kernel@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Steffen Klassert says:
====================
1) Don't use a wildcard SA if a more precise one is in acquire state,
from Fan Du.
2) Simplify the SA lookup when using wildcard source. We need to check
only the destination in this case, from Fan Du.
3) Add a receive path hook for IPsec virtual tunnel interfaces
to xfrm6_mode_tunnel.
4) Add support for IPsec virtual tunnel interfaces to ipv6.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Himanshu Madhani says:
====================
qlcnic: ethtool enhancements and code cleanup.
This patch series contains
o updates to ethtool for pause settings and enhance
register dump to display mask and ring indices.
o cleanup in DCB code and remove redundant eSwitch enablement command.
o fixed firmware dump collection logic to skip unknown entries.
Changes from v3 -> v4
o Dropped patch for Tx queue validation to be submitted in net.
Changes from v2 -> v3
o Updated patch to print informational messages as per Joe Perches's comment.
Changes from v1 -> v2
o Dropped patch to register device if adapter is in FAILED state for more rework.
o Updated patch to display ring indices via ethtool per Ben Hutchings's comment.
o Update patch for DCB cleanup per Stephen Hemminger's comment.
Please apply to net-next.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
o Driver aborts the minidump collection operation when it finds
an unknown entry opcode. This patch skips unknown entry type
and resumes the minidump collection operation.
o Removed a comparision of collected dump size with expected dump size.
Size may differ when driver decides to skip an entry.
Signed-off-by: Shahed Shaikh <shahed.shaikh@qlogic.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
o Move dcb specific function definitions to dcb files.
o Move dcb specific variables to qlcnic_dcb structure.
Signed-off-by: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
