Eric Dumazet [Mon, 22 Oct 2012 21:42:47 +0000 (21:42 +0000)]
ipv4: tcp: clean up tcp_v4_early_demux()
Use same header helpers than tcp_v6_early_demux() because they
are a bit faster, and as they make IPv4/IPv6 versions look
the same.
Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Neal Cardwell [Mon, 22 Oct 2012 21:41:48 +0000 (21:41 +0000)]
ipv6: tcp: clean up tcp_v6_early_demux() icsk variable
Remove an icsk variable, which by convention should refer to an
inet_connection_sock rather than an inet_sock. In the process, make
the tcp_v6_early_demux() code and formatting a bit more like
tcp_v4_early_demux(), to ease comparisons and maintenance.
Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 23 Oct 2012 06:51:00 +0000 (02:51 -0400)]
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next
Jeff Kirsher says:
====================
This series contains updates to ixgbe only. Only change to this series
is I dropped the "ixgbe: Add support for pipeline reset" due to
change requested by Martin Josefsson.
Alexander Duyck (7):
ixgbe: Add support for IPv6 and UDP to ixgbe_get_headlen
ixgbe: Add support for tracking the default user priority to SR-IOV
ixgbe: Add support for GET_QUEUES message to get DCB configuration
ixgbe: Enable support for VF API version 1.1 in the PF.
ixgbevf: Add VF DCB + SR-IOV support
ixgbe: Drop unnecessary addition from ixgbe_set_rx_buffer_len
ixgbe: Fix possible memory leak in ixgbe_set_ringparam
Don Skidmore (1):
ixgbe: Add function ixgbe_reset_pipeline_82599
Emil Tantilov (1):
ixgbe: add WOL support for new subdevice id
Jacob Keller (1):
ixgbe: (PTP) refactor init, cyclecounter and reset
Tushar Dave (1):
ixgbe: Correcting small packet padding
Wei Yongjun (1):
ixgbe: using is_zero_ether_addr() to simplify the code
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Bjørn Mork [Mon, 22 Oct 2012 10:56:40 +0000 (10:56 +0000)]
net: cdc_mbim: Device Service Stream support
MBIM devices can support up to 256 generic streams called
Device Service Streams (DSS). The MBIM spec says
The format of the Device Service Stream payload depends
on the device service (as identified by the corresponding
UUID) that is used when opening the data stream.
Example use cases are serial AT command interfaces and NMEA
data streams. We cannot make any assumptions about these
device services.
Adding support for Device Service Stream by extending
the MBIM session to VLAN mapping scheme, allocating
VLAN IDs 256 to 511 for DSS, using the DSS SessionID
as the lower 8bit of the VLAN ID.
Using a netdev for DSS keeps the device framing intact and
allows userspace to do whatever it want with the streams.
For example, exporting an AT command interface using DSS
session #0 to a PTY for use with a terminal application like
minicom:
vconfig add wwan0 256
ip link set dev wwan0 up
ip link set dev wwan0.256 up
socat INTERFACE:wwan0.256,type=2 PTY:,echo=0,link=/tmp/modem
Device configuration must be done using MBIM control commands
over the /dev/cdc-wdmx device. The userspace management
application should coordinate host VLAN configuration and the
device MBIM configuration using the device capabilities to
find out if it needs to set up PTY mappings etc.
Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: David S. Miller <davem@davemloft.net>
Bjørn Mork [Mon, 22 Oct 2012 10:56:39 +0000 (10:56 +0000)]
net: cdc_ncm: map MBIM IPS SessionID to VLAN ID
MBIM devices can support up to 256 independent IP Streams.
The main network device will only handle SessionID 0. Mapping
SessionIDs 1 to 255 to VLANs using the SessionID as VLAN ID
allow userspace to use these streams with traditional tools
like vconfig.
Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: David S. Miller <davem@davemloft.net>
Bjørn Mork [Mon, 22 Oct 2012 10:56:38 +0000 (10:56 +0000)]
net: cdc_ncm: do not bind to NCM compatible MBIM devices
The MBIM specification allows a MBIM device to disguise
itself as NCM for backwards compatibility, using additional
altsettings with different subclass (control) or protocol
(data):
Greg Suarez [Mon, 22 Oct 2012 10:56:36 +0000 (10:56 +0000)]
net: cdc_mbim: adding MBIM driver
The CDC Mobile Broadband Interface Model (MBIM) specification
extends CDC NCM by
- removing the redundant ethernet header from the point-to-point
USB channel
- adding support for multiple IP (v4 and/or v6) sessions multiplexed
on the same USB channel
- adding a MBIM control channel encapsulated in CDC
- adding Device Service Streams (DSS), which are non IP generic data
streams multiplexed on the same USB channel as the IP sessions
MBIM devices are managed using the dedicated control channel, and no
data will flow on the data channel until a control session has been
established. This driver has no knowledge of MBIM control messages.
It just exports the control channel to a /dev/cdc-wdmX character
device for userspace management applications. Such an application is
therefore required to use this driver.
This patch implements basic MBIM support, reusing the NCM and WDM driver
APIs, currently limited to IP sessions with SessionID 0. DSS and
multiplexed IP sessions are not yet supported.
Signed-off-by: Greg Suarez <gsuarez@smithmicro.com> Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: David S. Miller <davem@davemloft.net>
Bjørn Mork [Mon, 22 Oct 2012 10:56:34 +0000 (10:56 +0000)]
net: cdc_ncm: refactoring for tx multiplexing
Adding multiplexed NDP support to cdc_ncm_fill_tx_frame, allowing
transmissions of multiple independent sessions within the same NTB.
Refactoring the code quite a bit to avoid having to store copies
of multiple NDPs being prepared for tx. The old code would still
reserve enough room for a maximum sized NDP in the skb so we might
as well keep them in the skb while they are being prepared.
Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: David S. Miller <davem@davemloft.net>
Bjørn Mork [Mon, 22 Oct 2012 10:56:33 +0000 (10:56 +0000)]
net: cdc_ncm: splitting rx_fixup for code reuse
Verifying and handling received MBIM and NCM frames will need
to be different in three areas:
- verifying the NDP signature
- checking valid datagram length
- datagram header manipulation
This makes it inconvenient to share rx_fixup in whole. But
some verification parts are common. Split these out in separate
functions.
Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: David S. Miller <davem@davemloft.net>
Bjørn Mork [Mon, 22 Oct 2012 10:56:32 +0000 (10:56 +0000)]
net: cdc_ncm: process chained NDPs
The NCM 1.0 spefication makes provisions for linking more than
one NDP into a single NTB. This is important for MBIM support,
where these NDPs might be of different types.
Following the chain of NDPs is also correct for NCM, and will
not change anything in the common case where there is only
one NDP
Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: David S. Miller <davem@davemloft.net>
Greg Suarez [Mon, 22 Oct 2012 10:56:30 +0000 (10:56 +0000)]
net: cdc_ncm: adding MBIM support to ncm_setup
MBIM and NCM are very similar, so we can reuse most of the
setup and bind logic in cdc_ncm for CDC MBIM devices. Handle
a few minor differences in ncm_setup.
Signed-off-by: Greg Suarez <gsuarez@smithmicro.com> Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: David S. Miller <davem@davemloft.net>
Greg Suarez [Mon, 22 Oct 2012 10:56:29 +0000 (10:56 +0000)]
USB: cdc: add MBIM constants and structures
Based on revision 1.0 of "Universal Serial Bus Communications
Class Subclass Specification for Mobile Broadband Interface
Model" available from www.usb.org
Signed-off-by: Greg Suarez <gsuarez@smithmicro.com>
[bmork: added DSS defines] Signed-off-by: Bjørn Mork <bjorn@mork.no> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Some devices do not support the 8 byte variants of the NTB input
size control messages despite announcing such support in their
NCM or MBIM functional descriptor.
According to the NCM specification, all devices must support the
4 byte variant regardless of whether or not the flag is set:
If bit D5 is set in the bmNetworkCapabilities field of
function’s NCM Functional Descriptor, the host may
set wLength either to 4 or to 8. If wLength is 4, the
function shall assume that wNtbInMaxDatagrams is to be
set to zero. If wLength is 8, then the function shall
use the provided value as the limit. The function shall
return an error response (a STALL PID) if wLength is set
to any other value.
We do not set wNtbInMaxDatagrams in any case, so we can just as
well unconditionally use the 4 byte variant without losing any
functionality. This works around the known firmware bug, and
simplifies the code considerably.
Signed-off-by: Bjørn Mork <bjorn@mork.no> Signed-off-by: David S. Miller <davem@davemloft.net>
Joachim Eastwood [Mon, 22 Oct 2012 08:45:31 +0000 (08:45 +0000)]
net/macb: fix truncate warnings
When building macb on x86_64 the following warnings show up:
drivers/net/ethernet/cadence/macb.c: In function macb_interrupt:
drivers/net/ethernet/cadence/macb.c:556:4: warning: large integer implicitly truncated to unsigned type [-Woverflow]
drivers/net/ethernet/cadence/macb.c: In function macb_reset_hw:
drivers/net/ethernet/cadence/macb.c:792:2: warning: large integer implicitly truncated to unsigned type [-Woverflow]
drivers/net/ethernet/cadence/macb.c:793:2: warning: large integer implicitly truncated to unsigned type [-Woverflow]
drivers/net/ethernet/cadence/macb.c:796:2: warning: large integer implicitly truncated to unsigned type [-Woverflow]
Use -1 insted of ~0UL, as done in other places in the driver,
to silence these warnings.
Signed-off-by: Joachim Eastwood <manabian@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Nicolas Dichtel [Mon, 22 Oct 2012 03:42:09 +0000 (03:42 +0000)]
ipv6: add support of equal cost multipath (ECMP)
Each nexthop is added like a single route in the routing table. All routes
that have the same metric/weight and destination but not the same gateway
are considering as ECMP routes. They are linked together, through a list called
rt6i_siblings.
ECMP routes can be added in one shot, with RTA_MULTIPATH attribute or one after
the other (in both case, the flag NLM_F_EXCL should not be set).
The patch is based on a previous work from
Luc Saillard <luc.saillard@6wind.com>.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Wed, 12 Sep 2012 07:09:51 +0000 (07:09 +0000)]
ixgbe: Fix possible memory leak in ixgbe_set_ringparam
We were not correctly freeing the temporary rings on error in
ixgbe_set_ring_param. In order to correct this I am unwinding a number of
changes that were made in order to get things back to the original working
form with modification for the current ring layouts.
This approach has multiple advantages including a smaller memory footprint,
and the fact that the interface is stopped while we are allocating the rings
meaning that there is less potential for some sort of memory corruption on the
ring.
The only disadvantage I see with this approach is that on a Rx allocation
failure we will report an error and only update the Tx rings. However the
adapter should be fully functional in this state and the likelihood of such
an error is very low. In addition it is not unreasonable to expect the
user to need to recheck the ring configuration should they experience an
error setting the ring sizes.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Don Skidmore [Tue, 11 Sep 2012 06:58:19 +0000 (06:58 +0000)]
ixgbe: Add function ixgbe_reset_pipeline_82599
This patch adds a function that forces a full pipeline reset. This
function will be used in following patches to completely reset the PHY
during resets.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Sat, 8 Sep 2012 03:17:01 +0000 (03:17 +0000)]
ixgbe: Drop unnecessary addition from ixgbe_set_rx_buffer_len
We still had some code floating around from the old single buffer receive
path. As a result we were adding VLAN_HLEN to max_frame although the
resultant value was never used. Since that is the case we can drop this from
the function.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Tushar Dave [Fri, 14 Sep 2012 04:24:49 +0000 (04:24 +0000)]
ixgbe: Correcting small packet padding
Driver pad skb up to 17 bytes because of the HW requirement. However, that code
implementation mess up the skb tail pointer after padding. This patch sets
skb->tail correctly.
Signed-off-by: Tushar Dave <tushar.n.dave@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Jacob Keller [Sat, 25 Aug 2012 03:54:19 +0000 (03:54 +0000)]
ixgbe: (PTP) refactor init, cyclecounter and reset
This patch modifies when and where PTP registers and data are set. Previously
a work-around was used inside cyclecounter_start in order to reset some of the
time registers. This patch creates a new ixgbe_ptp_reset specifically for this
purpose. The cyclecounter configuration has trimmed down to only modify what
is necessary. Due to hardware conditions after probe and before open, PTP init
has now moved into the ixgbe_open call. This allows the ptp device name in the
sysfs to be the ethernet device name instead of the MAC address.
The cyclecounter check flag is renamed to PTP_ENABLED and is used to prevent
PTP init from happening when PTP has not been enabled.
CC: Richard Cochran <richardcochran@gmail.com> Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Emil Tantilov [Thu, 16 Aug 2012 08:13:07 +0000 (08:13 +0000)]
ixgbe: add WOL support for new subdevice id
This patch adds a subdevice id for new 82599 device. The define is needed
to allow enabling WOL support.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Fri, 20 Jul 2012 08:10:03 +0000 (08:10 +0000)]
ixgbevf: Add VF DCB + SR-IOV support
This change adds support for DCB and SR-IOV from the VF. With this change
in place the VF will correctly use a traffic class other than 0 in the case
that the PF is configured with the default user priority belonging to a
traffic class other than 0.
Cc: Greg Rose <gregory.v.rose@intel.com> Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Sibai Li <sibai.li@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Fri, 20 Jul 2012 08:09:37 +0000 (08:09 +0000)]
ixgbe: Enable support for VF API version 1.1 in the PF.
This change switches on the last few bits for us enabling version 1.1 VF
support in the PF.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Tested-by: Robert Garrett <RobertX.Garrett@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Fri, 20 Jul 2012 08:09:32 +0000 (08:09 +0000)]
ixgbe: Add support for GET_QUEUES message to get DCB configuration
This patch addresses several issues in regards to the combination of DCB
and SR-IOV. Specifically it allows us to send information to the VF on
which queues it should be using.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 2 Oct 2012 00:17:03 +0000 (00:17 +0000)]
ixgbe: Add support for tracking the default user priority to SR-IOV
It is necessary to track the default user priority in the PF so that we can
force it upon the VFs. The motivation behind this is to keep the VFs from
getting access to user priorities meant for things like storage.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Thu, 24 May 2012 08:26:29 +0000 (08:26 +0000)]
ixgbe: Add support for IPv6 and UDP to ixgbe_get_headlen
This change adds support for IPv6 and UDP to ixgbe_get_headlen. The
advantage to this is that we can now handle ipv4/UDP, ipv6/TCP, and
ipv6/UDP with a single memcpy instead of having to do them in multiple
pskb_may_pull calls.
A quick bit of testing shows that we increase throughput for a single
session of netperf from 8800Mpbs to about 9300Mpbs in the case of ipv6/TCP.
As such overall ipv6 performance should improve with this change.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Eric Dumazet [Sun, 21 Oct 2012 20:12:09 +0000 (20:12 +0000)]
ipv4: 16 slots in initial fib_info hash table
A small host typically needs ~10 fib_info structures, so create initial
hash table with 16 slots instead of only one. This removes potential
false sharing and reallocs/rehashes (1->2->4->8->16)
Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Sun, 21 Oct 2012 19:57:11 +0000 (19:57 +0000)]
tcp: RFC 5961 5.2 Blind Data Injection Attack Mitigation
RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation]
All TCP stacks MAY implement the following mitigation. TCP stacks
that implement this mitigation MUST add an additional input check to
any incoming segment. The ACK value is considered acceptable only if
it is in the range of ((SND.UNA - MAX.SND.WND) <= SEG.ACK <=
SND.NXT). All incoming segments whose ACK value doesn't satisfy the
above condition MUST be discarded and an ACK sent back.
Move tcp_send_challenge_ack() before tcp_ack() to avoid a forward
declaration.
Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Jerry Chu <hkchu@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
FW flash layout on Skyhawk-R is different from BE3-R.
Hence the code needs to be fixed to flash FW on Skyhawk-R.
Also cleaning up code in BE3-R flashing function.
Signed-off-by: Vasundhara Volam <vasundhara.volam@emulex.com> Signed-off-by: Padmanabh Ratnakar <padmanabh.ratnakar@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
be2net: Enabling Wake-on-LAN is not supported in S5 state
be_shutdown is enabling wake-on-lan by calling be_setup_wol.
Emulex adapter do not support wake-on-lan in S5 state.
Signed-off-by: Vasundhara Volam <vasundhara.volam@emulex.com> Signed-off-by: Padmanabh Ratnakar <padmanabh.ratnakar@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
be2net: Fix issues in error recovery due to wrong queue state
During recovery from a FW error, destroy queue operation may fail.
Queue should be marked as destroyed so that recovery code can recreate
the queue. Also fix queue created state not getting checked at one instance.
Signed-off-by: Padmanabh Ratnakar <padmanabh.ratnakar@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
be2net: Fix error messages while driver load for VFs
VF does not have privileges to execute many commands. When VFs try
to execute those commands there are unnecessary error messages.
Fix this by executing only those commands for which VF has privilege.
Signed-off-by: Padmanabh Ratnakar <padmanabh.ratnakar@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
be2net: Fix change MAC operation for VF for Lancer
For changing MAC of VF from PF, delete MAC operation needs to be done before
assigning new MAC. Also in ndo_set_mac_address operation avoid delete MAC if
it has been already deleted by PF.
Signed-off-by: Padmanabh Ratnakar <padmanabh.ratnakar@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
be2net: Fix driver load failure for different FW configs in Lancer
Driver assumes FW resource counts and capabilities while creating queues and
using functionality like RSS. This causes driver load to fail in FW configs
where resources and capabilities are reduced. Fix this by querying FW
configuration during probe and using resources and capabilities accordingly.
Signed-off-by: Padmanabh Ratnakar <padmanabh.ratnakar@emulex.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Rami Rosen [Fri, 19 Oct 2012 01:09:30 +0000 (01:09 +0000)]
net:dev: remove double indentical assignment in dev_change_net_namespace().
This patch removes double assignment of err to -EINVAL in dev_change_net_namespace().
Signed-off-by: Rami Rosen <ramirose@gmail.com> Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Pavel Emelyanov [Thu, 18 Oct 2012 23:55:56 +0000 (23:55 +0000)]
sockopt: Make SO_BINDTODEVICE readable
The SO_BINDTODEVICE option is the only SOL_SOCKET one that can be set, but
cannot be get via sockopt API. The only way we can find the device id a
socket is bound to is via sock-diag interface. But the diag works only on
hashed sockets, while the opt in question can be set for yet unhashed one.
That said, in order to know what device a socket is bound to (we do want
to know this in checkpoint-restore project) I propose to make this option
getsockopt-able and report the respective device index.
Another solution to the problem might be to teach the sock-diag reporting
info on unhashed sockets. Should I go this way instead?
Signed-off-by: Pavel Emelyanov <xemul@parallels.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Haiyang Zhang [Thu, 18 Oct 2012 11:00:52 +0000 (11:00 +0000)]
hyperv: Remove unnecessary comments in rndis_filter_receive_data()
Checked with Windows networking team, there is only one RNDIS message
in each netvsc packet.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Sat, 20 Oct 2012 02:19:23 +0000 (22:19 -0400)]
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next
Jeff Kirsher says:
====================
This series contains updates to ixgbe and igb.
Alexander Duyck (13):
ixgbe: Initialize q_vector cpu and affinity masks correctly
ixgbe: Enable jumbo frames support w/ SR-IOV
ixgbe: Move message handling routines into their own functions
ixgbe: Add mailbox API version negotiation support to ixgbe PF
igb: Split Rx timestamping into two separate functions
igb: Do not use header split, instead receive all frames into a
single buffer
igb: Combine post-processing of skb into a single function
igb: Map entire page and sync half instead of mapping and unmapping
half pages
igb: Move rx_buffer related code in Rx cleanup path into separate
function
igb: Lock buffer size at 2K even on systems with larger pages
igb: Combine q_vector and ring allocation into a single function
igb: Move the calls to set the Tx and Rx queues into igb_open
igb: Split igb_update_dca into separate Tx and Rx functions
Tushar Dave (1):
igb: Correcting and improving small packet check and padding
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 19 Oct 2012 17:47:00 +0000 (13:47 -0400)]
Merge branch 'at91'
Joachim Eastwood says;
====================
This patch series prepares the old at91_ether driver for code sharing
with the macb driver. The hardware is similar except for DMA TX/RX, so
its not quite clear if it is practical to support both in one
driver. But stuff like MDIO and statistics should be possible to
share.
Patch 1 adds some register defines and bits that is only found on
RM9200.
Patch 2-4 uses the register defines and access functions from the macb
header. These can be squashed if it cause too much churn.
Patch 5 merges the private at91_ether struct with the private macb
struct. This makes it easier to later share code with the macb. The
private macb struct becomes quite large, but most at91_ether specific
members are removed in later patches.
Patch 8 make macb compile when we select at91_ether. Is this approach
okey?
Patch 9 makes use of MDIO code from macb. This rips out the private
phy handling code in at91_ether. One thing that is lost is the
interrupt support for phy. But this should easy to add to macb which
will then benefit both drivers.
Patch 10 makes use of the macb_set_rx_mode from macb.
Patch 11-12 makes at91_ether share the rx dma struct members from
macb. Patch also moves the rx buffer allocation into netdev open and
dealloc into netdev close.
Last patch remove the now unused rm9200 emac header from include/mach.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Tue, 25 Sep 2012 00:31:27 +0000 (00:31 +0000)]
igb: Split igb_update_dca into separate Tx and Rx functions
This change makes it so that igb_update_dca is broken into two halves, one
for Rx and one for Tx. The advantage to this is primarily readability.
In addition I am enabling relaxed ordering for reads from hardware since
this is supported on all of the igb parts.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 25 Sep 2012 00:31:22 +0000 (00:31 +0000)]
igb: Move the calls to set the Tx and Rx queues into igb_open
This change helps to address locking issues seen with
netif_set_real_num_tx_queues and netif_set_real_num_rx_queues when used in
the igb_set_interrupt_capability function. To resolve these locking issues
I have moved the two function calls into __igb_open so that they can be
called while the RTNL lock is held.
An added advantage to this is that the number of queues is not updated
until the last possible moment so if there are any issues in allocating
MSI-X interrupts or resources for the rings we have time to change the
values prior to updating the netdev.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 25 Sep 2012 00:31:17 +0000 (00:31 +0000)]
igb: Combine q_vector and ring allocation into a single function
This change combines the the allocation of q_vectors and rings into a single
function. The advantage of this is that we are guaranteed we will avoid
overlap in the L1 cache sets.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 25 Sep 2012 00:31:12 +0000 (00:31 +0000)]
igb: Lock buffer size at 2K even on systems with larger pages
This change locks us in at 2K buffers even on a system that supports larger
frames. The reason for this change is to make better use of pages and to
reduce the overall truesize of frames generated by igb.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 25 Sep 2012 00:31:07 +0000 (00:31 +0000)]
igb: Move rx_buffer related code in Rx cleanup path into separate function
In order to try and isolate things a bit further I am moving the code
related to retrieving data from the rx_buffer_info structure into a
separate function.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 25 Sep 2012 00:31:02 +0000 (00:31 +0000)]
igb: Map entire page and sync half instead of mapping and unmapping half pages
This change makes it so that we map the entire page and just sync half of
it for the device at a time. The advantage to this approach is that we can
avoid the locking on map/unmap seen in many IOMMU implementations.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 25 Sep 2012 00:30:57 +0000 (00:30 +0000)]
igb: Combine post-processing of skb into a single function
This change is meant to just clean-up a number of function calls that were
made at the end of the Rx clean-up path by combining them into a single
function call.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 25 Sep 2012 00:30:52 +0000 (00:30 +0000)]
igb: Do not use header split, instead receive all frames into a single buffer
This change makes it so that we no longer use header split. The idea is to
reduce partial cache line writes by hardware when handling frames larger
then header size. We can compensate for the extra overhead of having to
memcpy the header buffer by avoiding the cache misses seen by leaving an
full skb allocated and sitting on the ring.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Tue, 25 Sep 2012 05:14:55 +0000 (05:14 +0000)]
igb: Split Rx timestamping into two separate functions
In order to support page based receive we will need to split up the two
different types of timestamping into two separate functions. The first one
will handle legacy timestamps with the value in the register, and the new
one will handle timestamps in the Rx buffer itself.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Acked-by: Matthew Vick <matthew.vick@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Tushar Dave [Fri, 14 Sep 2012 03:43:43 +0000 (03:43 +0000)]
igb: Correcting and improving small packet check and padding
Current implementation mess up the tail pointer. This patch sets skb->tail
correctly.
Also, the small packet check and padding is optimized by using unlikely and
calling skb_pad directly.
Signed-off-by: Tushar Dave <tushar.n.dave@intel.com> Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Fri, 20 Jul 2012 08:09:22 +0000 (08:09 +0000)]
ixgbe: Add mailbox API version negotiation support to ixgbe PF
This change allows us to add a mailbox versioning API. This will allow us
to determine the features supported by the VFs from the PF. For example we
will be implementing a version 1.1 API for the VF that will indicate that
it can support us enabling Jumbo frames as the VF will support buffer
chaining.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Tested-by: Robert Garrett <RobertX.Garrett@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Fri, 20 Jul 2012 08:09:17 +0000 (08:09 +0000)]
ixgbe: Move message handling routines into their own functions
Instead of trying to maintain one large monolithic function that handles
most of the different messages from the VF it makes sense to break the
message handling function up so that we can just go through one switch
statement and call the correct routine for a given message.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Wed, 15 Aug 2012 02:10:43 +0000 (02:10 +0000)]
ixgbe: Enable jumbo frames support w/ SR-IOV
This change makes it so that we can have limited support for jumbo frames
when SR-IOV is enabled. In order to accomplish this it is necessary to
disable all VFs when the PF has jumbo frames enabled. If the VFs then
request the same maximum frame size as the PF they will be re-enabled. A
follow on patch will add a means of identifying when a VF can support
spanning buffers and does not need to be worried about the actual supported
max frame size.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Tested-by: Robert Garrett <robertx.e.garrett@intel.com> Tested-by: Sibai Li <Sibai.li@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Alexander Duyck [Fri, 27 Jul 2012 23:49:30 +0000 (23:49 +0000)]
ixgbe: Initialize q_vector cpu and affinity masks correctly
When enabling DCB the rings belonging to a q_vector on CPU 0 were not
reinitializing their DCA registers. Upon closer inspection the issue was
that the q_vector CPU variable was left at 0 resulting in the driver not
updating the DCA registers.
In order to guarantee the DCA registers will be updated I am adding a
couple line change so that we initialize the CPU variable to -1 which will
force a DCA update the first time an interrupt fires on that q_vector.
In addition we were setting the CPU affinity hint to all CPUs when we were
not specifying a CPU. Instead we should leave it as all zeros to avoid any
possible confusion about the fact that we shouldn't be giving a hint.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
David S. Miller [Thu, 18 Oct 2012 19:36:59 +0000 (15:36 -0400)]
Merge tag 'batman-adv-fix-for-davem' of git://git.open-mesh.org/linux-merge
Included fixes:
- Fix broadcast packet CRC calculation which can lead to ~80% broadcast packet
loss
- Fix a race condition in duplicate broadcast packet check
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Thu, 18 Oct 2012 09:14:12 +0000 (09:14 +0000)]
tcp: fix FIONREAD/SIOCINQ
tcp_ioctl() tries to take into account if tcp socket received a FIN
to report correct number bytes in receive queue.
But its flaky because if the application ate the last skb,
we return 1 instead of 0.
Correct way to detect that FIN was received is to test SOCK_DONE.
Reported-by: Elliot Hughes <enh@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Thu, 18 Oct 2012 03:21:55 +0000 (03:21 +0000)]
netlink: use kfree_rcu() in netlink_release()
On some suspend/resume operations involving wimax device, we have
noticed some intermittent memory corruptions in netlink code.
Stéphane Marchesin tracked this corruption in netlink_update_listeners()
and suggested a patch.
It appears netlink_release() should use kfree_rcu() instead of kfree()
for the listeners structure as it may be used by other cpus using RCU
protection.
netlink_release() must set to NULL the listeners pointer when
it is about to be freed.
Also have to protect netlink_update_listeners() and
netlink_has_listeners() if listeners is NULL.
Add a nl_deref_protected() lockdep helper to properly document which
locks protects us.
Reported-by: Jonathan Kliegman <kliegs@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Stéphane Marchesin <marcheu@google.com> Cc: Sam Leffler <sleffler@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Steffen Klassert [Wed, 17 Oct 2012 21:17:44 +0000 (21:17 +0000)]
ipv4: Fix flushing of cached routing informations
Currently we can not flush cached pmtu/redirect informations via
the ipv4_sysctl_rtcache_flush sysctl. We need to check the rt_genid
of the old route and reset the nh exeption if the old route is
expired when we bind a new route to a nh exeption.
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jay Purohit [Sun, 14 Oct 2012 07:07:21 +0000 (07:07 +0000)]
usb/ipheth: Add iPhone 5 support
I noticed that the iPhone ethernet driver did not support
iPhone 5. I quickly added support to it in my kernel, here's
a patch.
Signed-off-by: Jay Purohit <jspurohit@velocitylimitless.com> Acked-by: Valdis Kletnieks <valdis.kletnieks@vt.edu> Signed-off-by: Jan Ceuleers <jan.ceuleers@computer.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Threads in the bottom half of batadv_bla_check_bcast_duplist() might
otherwise for instance overwrite variables which other threads might
be using/reading at the same time in the top half, potentially
leading to messing up the bcast_duplist, possibly resulting in false
bridge loop avoidance duplicate check decisions.
Signed-off-by: Linus Lüssing <linus.luessing@web.de> Acked-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de> Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Linus Lüssing [Wed, 17 Oct 2012 12:53:04 +0000 (14:53 +0200)]
batman-adv: Fix broadcast packet CRC calculation
So far the crc16 checksum for a batman-adv broadcast data packet, received
on a batman-adv hard interface, was calculated over zero bytes of its
content leading to many incoming broadcast data packets wrongly being
dropped (60-80% packet loss).
This patch fixes this issue by calculating the crc16 over the actual,
complete broadcast payload.
The issue is a regression introduced by
("batman-adv: add broadcast duplicate check").
Signed-off-by: Linus Lüssing <linus.luessing@web.de> Acked-by: Simon Wunderlich <siwu@hrz.tu-chemnitz.de> Signed-off-by: Marek Lindner <lindner_marek@yahoo.de>
Linus Torvalds [Wed, 17 Oct 2012 20:40:22 +0000 (13:40 -0700)]
Merge tag 'uapi-fixes-20121017' of git://git.infradead.org/users/dhowells/linux-headers
Pull misc UAPI fixes from David Howells:
"They do a number of things:
(1) Import a patch from Catalin Marinas to extend the generic-y in
Kbuild facility to uapi directories.
(2) Make arch/tile's ucontext.h file use (1) and remove the header-y
line from the kernel internal side of things.
(3) Remove some now-empty conditional bits from include/linux/Kbuild.
The contents got moved to the UAPI side of things along with new
conditionals.
(4) Deal with now-empty files:
(a) Empty Kbuild files under include/ get removed.
(b) Empty Kbuild files under arch/ get comments to hold them as
they are likely to end up with generic-y or genhdr-y lines.
Deleting them appears to work if we want to go that route.
(c) Put a comment into uapi/asm-generic/kvm_para.h to prevent the
patch program from deleting that, and made the arches with
empty kvm_para.h uapi files use that instead of having their
own files.
(d) Put comments into four other empty uapi/ headers to prevent the
patch program from deleting them.
A question: Is this the right way to deal with the now-empty Kbuild
files?
The ones under include/ are unlikely to be used - even for generated
files, I think - so getting rid of them is probably okay. Once all
the bits are in, we can probably remove all the Kbuild files under
include/ that aren't also under include/uapi/.
The ones under arch/ are more of an issue because of the potential for
generic-y and genhdr-y."
* tag 'uapi-fixes-20121017' of git://git.infradead.org/users/dhowells/linux-headers:
UAPI: Make arch/sparc/include/uapi/asm/sigcontext.h non-empty
UAPI: Make arch/sh/include/uapi/asm/hw_breakpoint.h non-empty
UAPI: Make arch/mn10300/include/uapi/asm/setup.h non-empty
UAPI: Put a comment into uapi/asm-generic/kvm_para.h and use it from arches
UAPI: The tile arch uses the generic ucontext.h file
UAPI: Place comments in empty arch Kbuilds to make them non-empty
UAPI: Remove empty non-UAPI Kbuild files
UAPI: Remove empty conditionals from include/linux/Kbuild
UAPI: Make uapi/linux/irqnr.h non-empty
uapi: Allow automatic generation of uapi/asm/ header files
projects / ~andy / linux / log