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>

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>

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>

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>

Bump i40e to 0.4.3 and i40evf to 0.9.27.

Change-ID: I4141e9f8615bdcfa3b1b5ecbc2ac62603a03b7ad
Signed-off-by: NCatherine Sullivan <catherine.sullivan@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Use an extra state variable to keep track of when the IRQs are fully
set up.  This keeps us from trying to unhook IRQs that already were
left unhooked in a failed reset recovery, e.g. when firmware is broken.

Change-ID: I073eb081e4ef8aedcbdf1ee0717c0ed64fa172f2
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

If a reset recovery failed (e.g. firmware is broken), the HMC space won't
get set up.  We don't need to try to delete it if it didn't get set up.
This stops some needless error messages when we already know we need to
just tear things down.

Change-ID: Iac600481765e20b136052b43a544e55d7870268b
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The i40e driver should print link messages like all the
other Intel Ethernet drivers.

Change-ID: Ia88bdb96794e17a3962fcea94db176de01f921f7
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Add the missing unicast, multicast, and broadcast stats for the port.

Change-ID: Ifc366d7b7745f70eaac9d00eeb0694eb9ec076a9
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Add VSI HW stats for unicast, multicast, and broadcast for Rx and Tx.
Stop printing the netdev multicast value because it doesn't include Tx
and would be confusing.

Change-ID: I08278b6657e7c838fd29a4a1f305f78fe1b150be
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The wait time was originally too optimistic and the resets were failing
after EMPR.  This increases the loop count to wait considerably longer.
This won't delay the actual wait longer than really needed, just allows
us to poll more times as needed.

Change-ID: If7b96f55cc25b8d06cbbe8665259d250188c53d7
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Add a function which indicates our intention to enable or disable a particular
Tx queue. Also add a function to notify the device's Tx unit that we're about
to enable or disable a Tx queue.

Change-ID: I6adf3cbb5bb3e3c984d1ec969e06577c19ef296d
Signed-off-by: NMatt Jared <matthew.a.jared@intel.com>
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Tested-by: NJim Young <jamesx.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>