This patch adds tracepoints to the i40e and i40evf drivers to which
BPF programs can be attached for feature testing and verification.
It's expected that an attached BPF program will identify and count or
log some interesting subset of traffic. The bcc-tools package is
helpful there for containing all the BPF arcana in a handy Python
wrapper. Though you can make these tracepoints log trace messages, the
messages themselves probably won't be very useful (other to verify the
tracepoint is being called while you're debugging your BPF program).

The idea here is that tracepoints have such low performance cost when
disabled that we can leave these in the upstream drivers. This may
eventually enable the instrumentation of unmodified customer systems
should the need arise to verify a NIC feature is working as expected.
In general this enables one set of feature verification tools to be
used on these drivers whether they're built with the kernel or
separately.

Users are advised against using these tracepoints for anything other
than a diagnostic tool. They have a performance impact when enabled,
and their exact placement and form may change as we see how well they
work in practice for the purposes above.

Change-ID: Id6014a7322c0e6d08068114dd20bd156f2f6435e
Signed-off-by: NScott Peterson <scott.d.peterson@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch fixes an issue I introduced when I converted the code over to
using the length field to determine if a descriptor was done or not. It
turns out that we are also processing programming descriptors in the Rx
path and need to have these processed even though the length field will be
0 on these packets.  What will happen with a programming descriptor is that
we will receive a descriptor that has the SPH bit set, and the header
length and packet length fields cleared.

To account for this we should be checking for the bit for split header
being set even though we aren't actually using header split. This bit is
set in the length field to indicate if a programming descriptor response is
contained in the descriptor. Since we don't support header split we don't
need to perform the extra checks of using a fixed value for the entire
length field.

In addition I am moving the function for checking if a filter is a
programming status filter into the i40e_txrx.c file since there is no
longer support for FCoE it doesn't make sense to keep this file in i40e.h.

Change-ID: I12c359c3dc70adb9d6b92b27324bb2c7f04c1a06
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Rx checksum offload for tunneled packets was never being negotiated or
requested by VF. This capability was assumed by default and enabled in
current hardware for VF. Going forward, this feature needs to be disabled
or advanced ptypes should be negotiated with PF in the future.

Change-ID: I9e54cfa8a90e03ab6956db4412f1e337ccd2c2e0
Signed-off-by: NPreethi Banala <preethi.banala@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch is meant to improve the performance of the Rx path.
Specifically by using build_skb we have several distinct advantages.

In the case of small frames we were previously using a copy-break approach.
This means that we were allocating a page fragment to use for skb->head,
and were having to copy the packet into that region.  Both of those calls
are now avoided since we just build the skb around the data.

In the case of large frames the gains are much more significant.
Specifically we were having to allocate skb->head, and copy the headers as
before.  However in addition we were having to parse the header using
eth_get_headlen which could be quite expensive.  All of this is avoided by
building the frame around the data.  I have seen gains as high as 30% when
using VXLAN for instance due to just header pulling overhead.

Finally with all this in place it also sets us up to start looking at
enabling XDP.  Specifically we now have a path in which the data is in the
page and the frame is built around it.  So if we parse it with XDP before
we call build_skb we can take care of any necessary processing there.

Change-ID: Id4bdd618e94473d41f892417e5d8019639e421e3
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch adds padding to the start of frames to make room for headroom
for us to eventually start using build_skb.  Right now we guarantee at
least NET_SKB_PAD + NET_IP_ALIGN, however we allocate more space if more is
available.  For example on x86 the headroom should be 192 bytes.

On systems that have too large of a cache line size to support storing 1.5K
padding and shared info we default to using 3K buffers and reserve
everything that isn't used for skb_shared_info or the data buffer for
headroom.

Change-ID: I33c641c9a1ea10cf7cc484c2d20985368d2d709a
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

There are situations where adding padding to the front and back of an Rx
buffer will require that we add additional padding.  Specifically if
NET_IP_ALIGN is non-zero, or the MTU size is larger than 7.5K we would need
to use 2K buffers which leaves us with no room for the padding.

To preemptively address these cases I am adding support for 3K buffers to
the Rx path so that we can provide the additional padding needed in the
event of NET_IP_ALIGN being non-zero or a cache line being greater than 64.

Change-ID: I938bc1ba611285428df39a613cd66f98e60b55c7
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch is meant to clean up the code in preparation for us adding
support for build_skb.  Specifically we deconstruct i40e_fetch_buffer into
several functions so that those functions can later be reused when we add a
path for build_skb.

Specifically with this change we split out the code for adding a page to an
exiting skb.

Change-ID: Iab1efbab6b8b97cb60ab9fdd0be1d37a056a154d
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch pulls out the code responsible for handling buffer recycling and
page counting and distributes it through several functions.  This allows us
to commonize the bits that handle either freeing or recycling the buffers.

As far as the page count tracking one change to the logic is that
pagecnt_bias is decremented as soon as we call i40e_get_rx_buffer.  It is
then the responsibility of the function that pulls the data to either
increment the pagecnt_bias if the buffer can be recycled as-is, or to
update page_offset so that we are pointing at the correct location for
placement of the next buffer.

Change-ID: Ibac576360cb7f0b1627f2a993d13c1a8a2bf60af
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch pulls the code responsible for fetching the Rx buffer and
synchronizing DMA into a function, specifically called i40e_get_rx_buffer.

The general idea is to allow for better code reuse by pulling this out of
i40e_fetch_rx_buffer.  We dropped a couple of prefetches since the time
between the prefetch being called and the data being accessed was too small
to be useful.

Change-ID: I4885fce4b2637dbedc8e16431169d23d3d7e79b9
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change makes it so that we use the length of the packet instead of the
DD status bit to determine if a new descriptor is ready to be processed.
The obvious advantage is that it cuts down on reads as we don't really even
need the DD bit if going from a 0 to a non-zero value on size is enough to
inform us that the packet has been completed.

Change-ID: Iebdf9cdb36c454ef092df27199b92ad09c374231
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The current driver mode is to use a write-back mechanism for the head
register which indicates transmit completions. The VF driver needs to be
able to work on hardware that exclusively uses descriptor write-back, so
change the default driver mode of operation to descriptor write-back for
VF. In our analysis, performance wasn't significantly different with
either write-back method.

Change-ID: Ia92e4ec77c2df8dc4515c71d53746d57d77759af
Signed-off-by: NPreethi Banala <preethi.banala@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This is a minor clean-up to make the i40e/i40evf process_skb_fields
function look a little more like what we have in igb.  The Rx checksum
function called out a need for skb->protocol but I can't see where it
actually needs it.  I am assuming this is something that was likely
refactored out some time ago as the Rx checksum code has gone through a few
rewrites.

Change-ID: I0b4668a34d90b61b66ded7c7c26e19a3e2d06251
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

We need to reset skb back to NULL when we have freed it in the Rx cleanup
path.  I found one spot where this wasn't occurring so this patch fixes it.

Change-ID: Iaca68934200732cd4a63eb0bd83b539c95f8c4dd
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Update the driver code so that we do bulk updates of the page reference
count instead of just incrementing it by one reference at a time.  The
advantage to doing this is that we cut down on atomic operations and
this in turn should give us a slight improvement in cycles per packet.
In addition if we eventually move this over to using build_skb the gains
will be more noticeable.

I also found and fixed a store forwarding stall from where we were
assigning "*new_buff = *old_buff".  By breaking it up into individual
copies we can avoid this and as a result the performance is slightly
improved.

Change-ID: I1d3880dece4133eca3c32423b04a5467321ccc52
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch adds support for DMA_ATTR_SKIP_CPU_SYNC and
DMA_ATTR_WEAK_ORDERING. By enabling both of these for the Rx path we
are able to see performance improvements on architectures that implement
either one due to the fact that page mapping and unmapping only has to
sync what is actually being used instead of the entire buffer. In addition
by enabling the weak ordering attribute enables a performance improvement
for architectures that can associate a memory ordering with a DMA buffer
such as Sparc.

Change-ID: If176824e8231c5b24b8a5d55b339a6026738fc75
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Fix, or rather, avoid a sparse warning caused by the fact that
csum_replace_by_diff expects to receive a __wsum value. Since the
calculation appears to work, simply typecast the passed paylen value to
__wsum to avoid the warning.

This seems pretty fishy since __wsum was obviously annotated as
a separate type on purpose, so this throws the entire calculation into
question. Since it currently appears to behave as expected, the typecast
is probably safe.

Change-ID: I4fdc5cddd589abc16098176e8a61127e761488f4
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch fixes a bug introduced with the addition of the per queue
ITR feature support in ethtool.  With that addition, there were
functions added which converted the ITR settings to binary values.
The IS_ENABLED macros that run on those values check whether a bit
is set or not and with the value being binary, the bit check always
returned ITR disabled which prevents any updating of the ITR rate.
This patch fixes the problem by changing the functions to return the
current ITR value instead and renaming it to better reflect
its function.  These functions now provide a value which will be
accurately asessed and update the ITR as intended.

Change-ID: I14f1d088d052e27f652aaa3113e186415ddea1fc
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Reorganize the i40e_pull_tail() logic, doing it in i40e_add_rx_frag()
where it's cheaper.  The igb driver does this the same way.

Also renames i40e_page_is_reserved() to reflect what it actually
tests.

Change-ID: Icd9cc507aae1fcdc02308b3a09034111b4c24071
Signed-off-by: NScott Peterson <scott.d.peterson@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch reduces the size of struct i40e_rx_buffer by one pointer,
and makes the i40e driver a little more consistent with the igb driver
in terms of packets that span buffers.

We do this by moving the skb field from struct i40e_rx_buffer to
struct i40e_ring. We pass the skb we already have (or NULL if we
don't) to i40e_fetch_rx_buffer(), which skips the skb allocation if we
already have one for this packet.

Change-ID: I4ad48a531844494ba0c5d8e1a62209a057f661b0
Signed-off-by: NScott Peterson <scott.d.peterson@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

On packet RX, we perform a DMA sync for CPU before passing the
packet up.  Here we limit that sync to the actual length of the
incoming packet, rather than always syncing the entire buffer.

Change-ID: I626aaf6c37275a8ce9e81efcaa773f327b331487
Signed-off-by: NScott Peterson <scott.d.peterson@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch does some quick work to pull some of the data off of the stack
and hopefully start storing it in the Tx buffer info section of the Tx
ring.  Ideally we should be moving away from having to store much of
anything on the stack and can just maintain it all in the descriptor rings.

Change-ID: I4b4715ea1920e122502482b3f9e56a9a6cb1e9fe
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Currently the function i40e_napi-poll() returns 0 when it clean completely
the Rx rings, but this foul budget accounting in core code.

Fix this by returning the actual work done, capped to budget - 1, since
the core doesn't allow to return the full budget when the driver modifies
the NAPI status

This is based on a similar change that was made for the ixgbe driver by
Paolo Abeni.

Change-ID: Ic3d93ad2fa2fc8ce3164bc461e69367da0f9173b
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch reorders the logic at the end of i40e_tx_map to address the
fact that the logic was rather convoluted and much larger than it needed
to be.

In order to try and coalesce the code paths I have updated some of the
comments and repurposed some of the variables in order to reduce
unnecessary overhead.

This patch does the following:
1.  Quit tracking skb->xmit_more with a flag, just max out packet_stride
2.  Drop tail_bump and do_rs and instead just use desc_count and td_cmd
3.  Pull comments from ixgbe that make need for wmb() more explicit.

Change-ID: Ic7da85ec75043c634e87fef958109789bcc6317c
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch cleans up several pieces of redundant code in the Rx clean-up
paths.

The first bit is that hdr_addr and the status_err_len portions of the Rx
descriptor represent the same value.  As such there is no point in setting
them to 0 before setting them to 0.  I'm dropping the second spot where we
are updating the value to 0 so that we only have 1 write for this value
instead of 2.

The second piece is the checking for the DD bit in the packet.  We only
need to check for a non-zero value for the status_err_len because if the
device is done with the descriptor it will have written something back and
the DD is just one piece of it.  In addition I have moved the reading of
the Rx descriptor bits related to rx_ptype down so that they are actually
below the dma_rmb() call so that we are guaranteed that we don't have any
funky 64b on 32b calls causing any ordering issues.

Change-ID: I256e44a025d3c64a7224aaaec37c852bfcb1871b
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

There exists a bug in which a 'perfect storm' can occur and cause
interrupts to fail to be correctly affinitized. This causes unexpected
behavior and has a substantial impact on performance when it happens.

The bug occurs if there is heavy traffic, any number of CPUs that have
an i40e interrupt are pegged at 100%, and the interrupt afffinity for
those CPUs is changed.  Instead of moving to the new CPU, the interrupt
continues to be polled while there is heavy traffic.

The bug is most readily realized as the driver is first brought up and
all interrupts start on CPU0. If there is heavy traffic and the
interrupt starts polling before the interrupt is affinitized, the
interrupt will be stuck on CPU0 until traffic stops. The bug, however,
can also be wrought out more simply by affinitizing all the interrupts
to a single CPU and then attempting to move any of those interrupts off
while there is heavy traffic.

This patch fixes the bug by registering for update notifications from
the kernel when the interrupt affinity changes. When that fires, we
cache the intended affinity mask. Then, while polling, if the cpu is
pegged at 100% and we failed to clean the rings, we check to make sure
we have the correct affinity and stop polling if we're firing on the
wrong CPU.  When the kernel successfully moves the interrupt, it will
start polling on the correct CPU. The performance impact is minimal
since the only time this section gets executed is when performance is
already compromised by the CPU.

Change-ID: I4410a880159b9dba1f8297aa72bef36dca34e830
Signed-off-by: NAlan Brady <alan.brady@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

In commit a75e8005 ("i40e: queue-specific settings for interrupt
moderation") the i40e driver gained support for setting interrupt
moderation values per queue. This patch adds support for this feature
to the i40evf driver as well. In addition, a few changes are made to
the i40e implementation to add function header documentation comments,
as well.

This behaves in a similar fashion to the implementation in i40e. Thus,
requesting the moderation value when no queue is provided will report
queue 0 value, while setting the value without a queue will set all
queues at once.

Change-ID: I1f310a57c8e6c84a8524c178d44d1b7a6d3a848e
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch adds a txring_txq function which allows us to convert a
i40e_ring/i40evf_ring to a netdev_tx_queue structure.  This way we
can avoid having to make a multi-line function call for all the spots
that need access to this.

Change-ID: Ic063b71d8b92ea406d2c32e798c8e2b02809d65b
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The Tx cleanup flow was incorrectly assuming it could check for the flow
director bits after it had unmapped the buffer.  However in this case it
results in us trying to free a raw_buf as though it is an sk_buff.

To fix this I am moving up the flag test for the FD_SB bit so that when
find a non-NULL skb or raw_buf value we then check the flag and use the
appropriate call to free the buffer.

Change-ID: I6284034ba1ea87c9922e56f6eb3181f7f09bddde
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The i40e driver was incorrectly assuming that we would always be pulling
no more than 1 descriptor from each fragment.  It is in fact possible for
us to end up with the case where 2 descriptors worth of data may be pulled
when a frame is larger than one of the pieces generated when aligning the
payload to either 4K or pieces smaller than 16K.

To adjust for this we just need to make certain to test all the way to the
end of the fragments as it is possible for us to span 2 descriptors in the
block before us so we need to guarantee that even the last 6 descriptors
have enough data to fill a full frame.

Change-ID: Ic2ecb4d6b745f447d334e66c14002152f50e2f99
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch refactors tail bump check.

Change-ID: Ide0e19171d67d90cb2b06b8dcd4fa791ae120160
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This initializer isn't needed because the variable is assigned right
away.

Change-ID: I6ce3edb3f4e0364db248a7a0bcc62ca95c01d941
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

There are a couple of issues I found in i40e_rx_checksum while doing some
recent testing.  As a result I have found the Rx checksum logic is pretty
much broken and returning that the checksum is valid for tunnels in cases
where it is not.

First the inner types are not the correct values to use to test for if a
tunnel is present or not.  In addition the inner protocol types are not a
bitmask as such performing an OR of the values doesn't make sense.  I have
instead changed the code so that the inner protocol types are used to
determine if we report CHECKSUM_UNNECESSARY or not.  For anything that does
not end in UDP, TCP, or SCTP it doesn't make much sense to report a
checksum offload since it won't contain a checksum anyway.

This leaves us with the need to set the csum_level based on some value.
For that purpose I am using the tunnel_type field.  If the tunnel type is
GRENAT or greater then this means we have a GRE or UDP tunnel with an inner
header.  In the case of GRE or UDP we will have a possible checksum present
so for this reason it should be safe to set the csum_level to 1 to indicate
that we are reporting the state of the inner header.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch adds support for offloading IPXIP6 type packets that represent
either IPv4 or IPv6 encapsulated inside of an IPv6 outer IP header.  In
addition with this change we should also be able to support FOU
encapsulated traffic with outer IPv6 headers.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch defines two new GSO definitions SKB_GSO_IPXIP4 and
SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and
NETIF_F_GSO_IPXIP6. These are used to described IP in IP
tunnel and what the outer protocol is. The inner protocol
can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and
SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT
are removed (these are both instances of SKB_GSO_IPXIP4).
SKB_GSO_IPXIP6 will be used when support for GSO with IP
encapsulation over IPv6 is added.
Signed-off-by: NTom Herbert <tom@herbertland.com>
Acked-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is part 2 of the Rx refactor series, just including
changes to i40evf.

This refactor aligns the receive routine with the one in
ixgbe which was highly optimized.  This reduces the code
we have to maintain and allows for (hopefully) more readable
and maintainable RX hot path.

In order to do this:
- consolidate the receive path into a single function that doesn't
  use packet split but *does* use pages for Rx buffers.
- remove the old _1buf routine
- consolidate several routines into helper functions
- remove VF ethtool control over packet split
- remove priv_flags interface since it is unused
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

As part of preparation for the rx-refactor, remove the
packet split receive routine and ancillary code.

Some of the split related context set up code stays in
i40e_virtchnl_pf.c in case an older VF driver tries to load
and still wants to use packet split.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Refactor the interpretation of a tunnel.  This removes
some code and lets us start using the hardware's parsing.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch makes it so that i40e and i40evf can use GSO_PARTIAL to support
segmentation for frames with checksums enabled in outer headers.  As a
result we can now send data over these types of tunnels at over 20Gb/s
versus the 12Gb/s that was previously possible on my system.

The advantage with the i40e parts is that this offload is mostly
transparent as the hardware still deals with the inner and/or outer IPv4
headers so the IP ID is still incrementing for both when this offload is
performed.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The driver was offloading the VLAN tag into the skb
any time there was a VLAN tag and the hardware stripping was
enabled.  Just check to make sure it's enabled before put_tag.

Change-Id: Ife95290c06edd9a616393b38679923938b382241
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Looking over the documentation it turns out enabling IPIP and SIT offloads
for i40e is pretty straightforward.  As such I decided to enable them with
this patch.  In my testing I am seeing an improvement of 8 to 10 Gb/s
for IPIP and SIT tunnels with this offload enabled.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>