Fixed a bug that shows up with recv window sizes that exceed the size of
the RCV_BUFSIZ field in opt0 (>= 1024K).  If the recv window exceeds
this, then we specify the max possible in opt0, add add the rest in via
a RX_DATA_ACK credits.
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Select the appropriate hw mtu index and initial sequence number to optimize
hw memory performance.

Add new cxgb4_best_aligned_mtu() which allows callers to provide enough
information to be used to [possibly] select an MTU which will result in the
TCP Data Segment Size (AKA Maximum Segment Size) to be an aligned value.

If an RTR message exhange is required, then align the ISS to 8B - 1 + 4, so
that after the SYN the send seqno will align on a 4B boundary. The RTR
message exchange will leave the send seqno aligned on an 8B boundary.
If an RTR is not required, then align the ISS to 8B - 1.  The goal is
to have the send seqno be 8B aligned when we send the first FPDU.

Based on original work by Casey Leedom <leeedom@chelsio.com> and
Steve Wise <swise@opengridcomputing.com>
Signed-off-by: NCasey Leedom <leedom@chelsio.com>
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently indirect interrupts for RDMA CQs funnel through the LLD's RDMA
RXQs, which also handle direct interrupts for offload CPLs during RDMA
connection setup/teardown.  The intended T4 usage model, however, is to
have indirect interrupts flow through dedicated IQs. IE not to mix
indirect interrupts with CPL messages in an IQ.  This patch adds the
concept of RDMA concentrator IQs, or CIQs, setup and maintained by the
LLD and exported to iw_cxgb4 for use when creating CQs. RDMA CPLs will
flow through the LLD's RDMA RXQs, and CQ interrupts flow through the
CIQs.

Design:

cxgb4 creates and exports an array of CIQs for the RDMA ULD.  These IQs
are sized according to the max available CQs available at adapter init.
In addition, these IQs don't need FL buffers since they only service
indirect interrupts.  One CIQ is setup per RX channel similar to the
RDMA RXQs.

iw_cxgb4 will utilize these CIQs based on the vector value passed into
create_cq().  The num_comp_vectors advertised by iw_cxgb4 will be the
number of CIQs configured, and thus the vector value will be the index
into the array of CIQs.

Based on original work by Steve Wise <swise@opengridcomputing.com>
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NHariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is no need to require forcing device down on a Ethernet GRE (gretap)
tunnel to change the MAC address.
Signed-off-by: NStephen Hemminger <stephen@networkplumber.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

tcp_fragment can be called from process context (from tso_fragment).
Add a new gfp parameter to allow it to preserve atomic memory if
possible.
Signed-off-by: NOctavian Purdila <octavian.purdila@intel.com>
Reviewed-by: NChristoph Paasch <christoph.paasch@uclouvain.be>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2014-06-09

This series contains more updates to i40e and i40evf.

Shannon adds checks for error status bits on the admin event queue and
provides notification if seen.  Cleans up unused variable and memory
allocation which was used earlier in driver development and is no longer
needed.  Also fixes the driver to not complain about removing
non-existent MAC addresses.  Bumps the driver versions for both i40e
and i40evf.

Catherine fixes a function header comment to make sure the comment correctly
reflects the function name.

Mitch adds code to allow for additional VSIs since the number of VSIs that
the firmware reports to us is a guaranteed minimum, not an absolute
maximum.  The hardware actually supports for more than the reported value,
which we often need.  Implements anti-spoofing for VFs for both MAC
addresses and VLANs, as well as enable this feature by default for all VFs.

Anjali changes the interrupt distribution policy to change the way
resources for special features are handled.  Fixes the driver to not fall
back to one queue if the only feature enabled is ATR, since FD_SB
and FD_ATR need to be checked independently in order to decide if we
will support multiple queue or not.  Allows the RSS table entry range
and GPS to be any number, not necessarily a power of 2 because hardware
does not restrict us to use a power of 2 GPS in the case of RSS as long as
we are not sharing the RSS table with another VSI (VMDq).

Frank modifies the driver to keep SR-IOV enabled in the case that RSS,
VMFq, FD_SB and DCB are disabled so that SR-IOV does not get turned off
unnecessarily.

Jesse fixes a bug in receive checksum where the driver was not marking
packets with bad checksums correctly, especially IPv6 packets with a bad
checksum.  To do this correctly, we need a define that may be set by
hardware in rare cases.

Greg fixes the driver to delete all the old and stale MAC filters for the
VF VSI when the host administrator changes the VF MAC address from under
its feet.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Bumpity and Fred Worm say it's time to change the numbers again.
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Change-ID: I658731d022ea23cedede4be2bfecd8b4cc68d270
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

We tell the HW upper boundary of power of 2 in VSI config,
but the HW does not restrict us to use just power of 2 GPS in
case of RSS as long as we are not sharing the RSS table with
another VSI (VMDq). We at present are not doing RSS in VMDq
VSI.
If we were to enable that and if the system had CPU count which
was not power 2, the VMDq VSIs will see a little skewed distribution.

Change-ID: I3ea797ce9065a3ca4fc4d04251bf195463410473
Signed-off-by: NAnjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Delete all the old and stale MAC filters for the VF VSI when the host
administrator changes the VF MAC address from under its feet.  Also don't
bother to add a filter for the VSI when its going to go away anyway.
Just record the new address and punch the VF reset.

Change-ID: Ic0d12055926f41989d1965ccf500053729c063ad
Signed-off-by: NGreg Rose <gregory.v.rose@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

FD_SB and FD_ATR needs to be checked independently in order to decide if
we will support multiple queues or not.

Change-ID: I9d3274f5924c79e29efdbcf66a2fcca1fee2107f
Signed-off-by: NAnjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The driver was not marking packets with bad checksums
correctly, especially IPv6 packets with a bad checksum.
To do this correctly we need a define that may be set by
hardware in rare cases.

Change-ID: I1a997b72b491ded27a78ac3bce1197b2d2611130
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Modify the logic in i40e_determine_queue_usage() so that
SR-IOV doesn't get turned off unnecessarily.

Change-ID: I86ca304fa9f742a50e9ea831b887f358a6a9d53d
Signed-off-by: NFrank Zhang <frank_1.zhang@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch changes the way resources are distributed to special features.

Change-ID: I847e49d714a1d70e97f3f994cb39bfb5e02ab016
Signed-off-by: NAnjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Our hardware supports VF antispoofing for both MAC addresses and VLANs.
Enable this feature by default for all VFs and implement the netdev op
to control it from the command line.

Change-ID: Ifb941da22785848aa3aba6b2231be135b8ea8f31
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

We don't need to complain in the log about mac addresses that
can't be deleted because they don't exist.

Change-ID: I4e6370df175bf72726f06d2206c03bcbfded8387
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This was a vestige of early driver development that no longer
has any actual use.

Change-ID: I95b5b19c4bbfaff8759197af671ebaf716cb6ab5
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The number of VSIs that the firmware reports to us is a guaranteed
minimum, not an absolute maximum. The hardware actually supports far
more  than the reported value, which we often need.

To allow for this, we allocate space for a larger number of VSIs than is
guaranteed by the firmware, with the knowledge that we may fail to get
them all in the future.

Note that we are just allocating pointers here, the actual (much larger)
VSI structures are allocated on demand.

Change-ID: I6f4e535ce39d3bf417aef78306e04fbc7505140e
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Fix function header comment to have the correct function name.
Signed-off-by: NCatherine Sullivan <catherine.sullivan@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Check for error status bits on the AdminQ event queue and announce them
if seen.  If the Firmware sets these bits, it will trigger an AdminQ
interrupt to get the driver's attention to process the ARQ, which will
likely be enough to clear the actual issue.
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Change-ID: I009e0ebc8be764e40e193b29aed2863f43eb5cb0
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

John W. Linville says:

====================
pull request: wireless-next 2014-06-06

Please accept this batch of fixes intended for the 3.16 stream.

For the bluetooth bits, Gustavo says:

"Here some more patches for 3.16. We know that Linus already opened the merge
window, but this is fix only pull request, and most of the patches here are
also tagged for stable."

Along with that, Andrea Merello provides a fix for the broken scanning
in the venerable at76c50x driver...
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2014-06-08

This series contains updates to i40e and i40evf.

Jesse fixes an issue reported by Eric Dumazet where the driver was not
masking the right bits in the receive descriptor before checking them.
Also fixes TSO accounting since the kernel now can send as much as 32kB
in a single skb->frag[.] entry, even on a system with 4kB pages.

Anjali cleans up registers which are no longer supported.

Akeem cleans up code comments and removes num_msix_entries from the
interrupt setup routine since it was not being used.  Fixes an issue where
FD SB/ATR and NTUPLE configuration status were reported erroneously, so
now the driver reports FDir without further information.  Fixes a coding
error where during the registration for NAPI, the driver was requesting
256 budget.  The max recommended value for this NAPI_POLL_WEIGHT or 64.
Lastly, removed deprecated device IDs because they will not be shipped.

Mitch removes log messages which were redundant so therefore unnecessary.
Also removes a bogus code comment since VF drivers require MSI-X or they
won't get interrupts at all and cleans up the formatting of several log
messages.  Mitch also fixes the possibility of null pointers in VSI, since
not all VSIs have transmit rings.

Shannon ensures to clear the PXE mode bit on each reset after the AdminQ
has been rebuilt.

Catherine bumps the driver versions for i40e and i40evf.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Bump i40e to 0.4.5 and i40evf to 0.9.29.

Change-ID: I9faca5544446518c5425612e733499cf16ef20a1
Signed-off-by: NCatherine Sullivan <catherine.sullivan@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Remove two device IDs 1582 and 1573, because they will not be shipped.

Change-ID: Ica2e550b5b21a69e3f353eba2fe5e1c532a548c4
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Fix a coding error where during the registration for NAPI
the driver requested 256 budget.  The max recommended
value for this is NAPI_POLL_WEIGHT or 64.

Change-ID: I03ea1e2934a84ff1b5d572988b18315d6d91c5c6
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The TSO logic in the transmit path had some assumptions that
have been broken now that the kernel can send as much as 32kB
in a single skb->frag[.] entry, even on a system with 4kB pages.

This fixes the assumptions and allows the kernel to operate
as efficiently as possible with both SENDFILE and SEND.

In addition, the hardware limit of data contained in a descriptor is
changed to the next power of two below where it currently is in
order to align to a power of two value, preventing a single byte
of data in a descriptor.

Change-ID: I6af1f0b87c1458e10644dbd47541591075a52651
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Both the PF side and the VF side of the VF reset process are too noisy.
We already warn the user that a reset is happening, and that is
sufficient.

Because some of these message are inside if statements, we have to
rejigger the brackets at the same time to keep our coding style
consistent.

Change-ID: Id175562fb0ec7c396d9de156b4890e136f52d5f4
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Once more, with feeling: not all VSIs have rings. To assume so is to
invite null pointers to your party.

Change-ID: I576858824468d9712d119fa1015a1f28c27712c4
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Be sure to clear PXE mode bit on each reset after AdminQ has been rebuilt.

Change-ID: I992d8c79594f8ca0660c50844ace675ecb9c9bf2
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch fixes an issue where FD SB/ATR and NTUPLE configurations status are
reported erroneously. Without this patch, driver reports FDir without further
information.

Change-ID: I5bdd2871b7f2db1e5f5e76c741ae6a0dc603b453
Signed-off-by: NAkeem G Abodunrin <akeem.g.abodunrin@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The correct format is %pM, not %pMAC.

Change-ID: Idb335723a966fe56db3a72b9c07c08ca66f9db3c
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NSibai Li <sibai.li@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Clean up inconsistent log messages, mostly related to punctuation. Based
on the dogma that "kernel messages are not sentences", remove all
trailing periods. Reword a few of the messages to make them less
sentence-like.

Change-ID: Ibd849aa7623a77549b0709988c66ab05d1311472
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NSibai Li <sibai.li@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This comment is just plain false. VF drivers require MSI-X or they won't
get interrupts at all.

Change-ID: Iaea5e30b6926948aa834a3c506d9a9223d9e3e29
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NSibai Li <sibai.li@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

We don't need to print log messages when we encounter an out-of-memory
condition, as the allocator will do this for us. Also, remove a Tx hang
message that duplicates the one emitted by the netdev layer, and a
duplicate message in the watchdog.

Change-ID: If2056e6135fe248f66ea939778f9895660f4d189
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NSibai Li <sibai.li@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

1. There is no ixgbe_watchdog_task function in the driver, so change
   the comment to the correct function name, i40e_watchdog_subtask.
2. Remove num_msix_entries from interrupt set_up routine
   because it is never used.
3. Remove some TBD comments that are not needed.

Change-ID: I37697a04007074b797f85fd83d626672e4df1ad1
Signed-off-by: NAkeem G Abodunrin <akeem.g.abodunrin@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Remove use of registers no longer supported.

Change-ID: I9d27399091cea78a926489d94f958edd762f5a20
Signed-off-by: NAnjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

As reported by Eric Dumazet, the driver is not masking the right
bits in the receive descriptor before it starts checking them.

This patch extends the mask to allow for the right bits to be
checked, and fixes the issue permanently via a define.

CC: Eric Dumazet <eric.dumazet@gmail.com>
Change-ID: I3274f7619057a950f468143e6d7e11b129f54655
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

During key removal, the key object is freed, but not taken out of the
llsec key list properly. Fix that.
Signed-off-by: NPhoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NJiri Pirko <jiri@resnulli.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NJiri Pirko <jiri@resnulli.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The include of asm/cputype.h breaks the powerpc build. This
include was accidentally left in from driver debugging and
can be removed.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>,
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>