Under rare circumstances there might be a situation where a requirement
of having XDP Tx queue per CPU could not be fulfilled and some of the Tx
resources have to be shared between CPUs. This yields a need for placing
accesses to xdp_ring inside a critical section protected by spinlock.
These accesses happen to be in the hot path, so let's introduce the
static branch that will be triggered from the control plane when driver
could not provide Tx queue dedicated for XDP on each CPU.

Currently, the design that has been picked is to allow any number of XDP
Tx queues that is at least half of a count of CPUs that platform has.
For lower number driver will bail out with a response to user that there
were not enough Tx resources that would allow configuring XDP. The
sharing of rings is signalled via static branch enablement which in turn
indicates that lock for xdp_ring accesses needs to be taken in hot path.

Approach based on static branch has no impact on performance of a
non-fallback path. One thing that is needed to be mentioned is a fact
that the static branch will act as a global driver switch, meaning that
if one PF got out of Tx resources, then other PFs that ice driver is
servicing will suffer. However, given the fact that HW that ice driver
is handling has 1024 Tx queues per each PF, this is currently an
unlikely scenario.
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NGeorge Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Optimize Tx descriptor cleaning for XDP. Current approach doesn't
really scale and chokes when multiple flows are handled.

Introduce two ring fields, @next_dd and @next_rs that will keep track of
descriptor that should be looked at when the need for cleaning arise and
the descriptor that should have the RS bit set, respectively.

Note that at this point the threshold is a constant (32), but it is
something that we could make configurable.

First thing is to get away from setting RS bit on each descriptor. Let's
do this only once NTU is higher than the currently @next_rs value. In
such case, grab the tx_desc[next_rs], set the RS bit in descriptor and
advance the @next_rs by a 32.

Second thing is to clean the Tx ring only when there are less than 32
free entries. For that case, look up the tx_desc[next_dd] for a DD bit.
This bit is written back by HW to let the driver know that xmit was
successful. It will happen only for those descriptors that had RS bit
set. Clean only 32 descriptors and advance the DD bit.

Actual cleaning routine is moved from ice_napi_poll() down to the
ice_xmit_xdp_ring(). It is safe to do so as XDP ring will not get any
SKBs in there that would rely on interrupts for the cleaning. Nice side
effect is that for rare case of Tx fallback path (that next patch is
going to introduce) we don't have to trigger the SW irq to clean the
ring.

With those two concepts, ring is kept at being almost full, but it is
guaranteed that driver will be able to produce Tx descriptors.

This approach seems to work out well even though the Tx descriptors are
produced in one-by-one manner. Test was conducted with the ice HW
bombarded with packets from HW generator, configured to generate 30
flows.

Xdp2 sample yields the following results:
<snip>
proto 17:   79973066 pkt/s
proto 17:   80018911 pkt/s
proto 17:   80004654 pkt/s
proto 17:   79992395 pkt/s
proto 17:   79975162 pkt/s
proto 17:   79955054 pkt/s
proto 17:   79869168 pkt/s
proto 17:   79823947 pkt/s
proto 17:   79636971 pkt/s
</snip>

As that sample reports the Rx'ed frames, let's look at sar output.
It says that what we Rx'ed we do actually Tx, no noticeable drops.
Average:        IFACE   rxpck/s   txpck/s    rxkB/s    txkB/s   rxcmp/s txcmp/s  rxmcst/s   %ifutil
Average:       ens4f1 79842324.00 79842310.40 4678261.17 4678260.38 0.00      0.00      0.00     38.32

with tx_busy staying calm.

When compared to a state before:
Average:        IFACE   rxpck/s   txpck/s    rxkB/s    txkB/s   rxcmp/s txcmp/s  rxmcst/s   %ifutil
Average:       ens4f1 90919711.60 42233822.60 5327326.85 2474638.04 0.00      0.00      0.00     43.64

it can be observed that the amount of txpck/s is almost doubled, meaning
that the performance is improved by around 90%. All of this due to the
drops in the driver, previously the tx_busy stat was bumped at a 7mpps
rate.
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NGeorge Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

With rings being split, it is now convenient to introduce a pointer to
XDP ring within the Rx ring. For XDP_TX workloads this means that
xdp_rings array access will be skipped, which was executed per each
processed frame.

Also, read the XDP prog once per NAPI and if prog is present, set up the
local xdp_ring pointer. Reading prog a single time was discussed in [1]
with some concern raised by Toke around dispatcher handling and having
the need for going through the RCU grace period in the ndo_bpf driver
callback, but ice currently is torning down NAPI instances regardless of
the prog presence on VSI.

Although the pointer to XDP ring introduced to Rx ring makes things a
lot slimmer/simpler, I still feel that single prog read per NAPI
lifetime is beneficial.

Further patch that will introduce the fallback path will also get a
profit from that as xdp_ring pointer will be set during the XDP rings
setup.

[1]: https://lore.kernel.org/bpf/87k0oseo6e.fsf@toke.dk/Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NGeorge Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

While it was convenient to have a generic ring structure that served
both Tx and Rx sides, next commits are going to introduce several
Tx-specific fields, so in order to avoid hurting the Rx side, let's
pull out the Tx ring onto new ice_tx_ring and ice_rx_ring structs.

Rx ring could be handled by the old ice_ring which would reduce the code
churn within this patch, but this would make things asymmetric.

Make the union out of the ring container within ice_q_vector so that it
is possible to iterate over newly introduced ice_tx_ring.

Remove the @size as it's only accessed from control path and it can be
calculated pretty easily.

Change definitions of ice_update_ring_stats and
ice_fetch_u64_stats_per_ring so that they are ring agnostic and can be
used for both Rx and Tx rings.

Sizes of Rx and Tx ring structs are 256 and 192 bytes, respectively. In
Rx ring xdp_rxq_info occupies its own cacheline, so it's the major
difference now.
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NGurucharan G <gurucharanx.g@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Currently ice_container_type is scoped only for ice_ethtool.c. Next
commit that will split the ice_ring struct onto Rx/Tx specific ring
structs is going to also modify the type of linked list of rings that is
within ice_ring_container. Therefore, the functions that are taking the
ice_ring_container as an input argument will need to be aware of a ring
type that will be looked up.

Embed ice_container_type within ice_ring_container and initialize it
properly when allocating the q_vectors.
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NGurucharan G <gurucharanx.g@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

This field is dead and driver is not making any use of it. Simply remove
it.
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NGurucharan G <gurucharanx.g@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Implement code to handle submission of APP TLV's
containing DSCP to TC mapping.

The first such mapping received on an interface
will cause that PF to switch to L3 DSCP QoS mode,
apply the default config for that mode, and apply
the received mapping.

Only one such mapping will be allowed per DSCP value,
and when the last DSCP mapping is deleted, the PF
will switch back into L2 VLAN QoS mode, applying the
appropriate default QoS settings.

L3 DSCP QoS mode will only be allowed in SW DCBx
mode, in other words, when the FW LLDP engine is
disabled.  Commands that break this mutual exclusivity
will be blocked.
Co-developed-by: NAnirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Signed-off-by: NAnirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Signed-off-by: NDave Ertman <david.m.ertman@intel.com>
Tested-by: NGurucharan G <gurucharanx.g@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

In order to use the new xsk batched buffer allocation interface, a
pointer to an array of struct xsk_buff pointers need to be provided so
that the function can put the result of the allocation there. In the
ice driver, we already have a ring that stores pointers to
xdp_buffs. This is only used for the xsk zero-copy driver and is a
union with the structure that is used for the regular non zero-copy
path. Unfortunately, that structure is larger than the xdp_buffs
pointers which mean that there will be a stride (of 20 bytes) between
each xdp_buff pointer. And feeding this into the xsk_buff_alloc_batch
interface will not work since it assumes a regular array of xdp_buff
pointers (each 8 bytes with 0 bytes in-between them on a 64-bit
system).

To fix this, remove the xdp_buff pointer from the rx_buf union and
move it one step higher to the union above which only has pointers to
arrays in it. This solves the problem and we can directly feed the SW
ring of xdp_buff pointers straight into the allocation function in the
next patch when that interface is used. This will improve performance.
Signed-off-by: NMagnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-4-magnus.karlsson@gmail.com

Add support for enabling Tx timestamp requests for outgoing packets on
E810 devices.

The ice hardware can support multiple outstanding Tx timestamp requests.
When sending a descriptor to hardware, a Tx timestamp request is made by
setting a request bit, and assigning an index that represents which Tx
timestamp index to store the timestamp in.

Hardware makes no effort to synchronize the index use, so it is up to
software to ensure that Tx timestamp indexes are not re-used before the
timestamp is reported back.

To do this, introduce a Tx timestamp tracker which will keep track of
currently in-use indexes.

In the hot path, if a packet has a timestamp request, an index will be
requested from the tracker. Unfortunately, this does require a lock as
the indexes are shared across all queues on a PHY. There are not enough
indexes to reliably assign only 1 to each queue.

For the E810 devices, the timestamp indexes are not shared across PHYs,
so each port can have its own tracking.

Once hardware captures a timestamp, an interrupt is fired. In this
interrupt, trigger a new work item that will figure out which timestamp
was completed, and report the timestamp back to the stack.

This function loops through the Tx timestamp indexes and checks whether
there is now a valid timestamp. If so, it clears the PHY timestamp
indication in the PHY memory, locks and removes the SKB and bit in the
tracker, then reports the timestamp to the stack.

It is possible in some cases that a timestamp request will be initiated
but never completed. This might occur if the packet is dropped by
software or hardware before it reaches the PHY.

Add a task to the periodic work function that will check whether
a timestamp request is more than a few seconds old. If so, the timestamp
index is cleared in the PHY, and the SKB is released.

Just as with Rx timestamps, the Tx timestamps are only 40 bits wide, and
use the same overall logic for extending to 64 bits of nanoseconds.

With this change, E810 devices should be able to perform basic PTP
functionality.

Future changes will extend the support to cover the E822-based devices.
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Add SIOCGHWTSTAMP and SIOCSHWTSTAMP ioctl handlers to respond to
requests to enable timestamping support. If the request is for enabling
Rx timestamps, set a bit in the Rx descriptors to indicate that receive
timestamps should be reported.

Hardware captures receive timestamps in the PHY which only captures part
of the timer, and reports only 40 bits into the Rx descriptor. The upper
32 bits represent the contents of GLTSYN_TIME_L at the point of packet
reception, while the lower 8 bits represent the upper 8 bits of
GLTSYN_TIME_0.

The networking and PTP stack expect 64 bit timestamps in nanoseconds. To
support this, implement some logic to extend the timestamps by using the
full PHC time.

If the Rx timestamp was captured prior to the PHC time, then the real
timestamp is

  PHC - (lower_32_bits(PHC) - timestamp)

If the Rx timestamp was captured after the PHC time, then the real
timestamp is

  PHC + (timestamp - lower_32_bits(PHC))

These calculations are correct as long as neither the PHC timestamp nor
the Rx timestamps are more than 2^32-1 nanseconds old. Further, we can
detect when the Rx timestamp is before or after the PHC as long as the
PHC timestamp is no more than 2^31-1 nanoseconds old.

In that case, we calculate the delta between the lower 32 bits of the
PHC and the Rx timestamp. If it's larger than 2^31-1 then the Rx
timestamp must have been captured in the past. If it's smaller, then the
Rx timestamp must have been captured after PHC time.

Add an ice_ptp_extend_32b_ts function that relies on a cached copy of
the PHC time and implements this algorithm to calculate the proper upper
32bits of the Rx timestamps.

Cache the PHC time periodically in all of the Rx rings. This enables
each Rx ring to simply call the extension function with a recent copy of
the PHC time. By ensuring that the PHC time is kept up to date
periodically, we ensure this algorithm doesn't use stale data and
produce incorrect results.

To cache the time, introduce a kworker and a kwork item to periodically
store the Rx time. It might seem like we should use the .do_aux_work
interface of the PTP clock. This doesn't work because all PFs must cache
this time, but only one PF owns the PTP clock device.

Thus, the ice driver will manage its own kthread instead of relying on
the PTP do_aux_work handler.

With this change, the driver can now report Rx timestamps on all
incoming packets.
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Use a dedicated bitfield in order to both increase
the amount of checking around the length of ITR writes
as well as simplify the checks of dynamic mode.

Basically unpack the "high bit means dynamic" logic
into bitfields.

Also, remove some unused ITR defines.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

The ice driver has support for adaptive interrupt moderation, an
algorithm for tuning the interrupt rate dynamically. This algorithm
is based on various assumptions about ring size, socket buffer size,
link speed, SKB overhead, ethernet frame overhead and more.

The Linux kernel has support for a dynamic interrupt moderation
algorithm known as "dimlib". Replace the custom driver-specific
implementation of dynamic interrupt moderation with the kernel's
algorithm.

The Intel hardware has a different hardware implementation than the
originators of the dimlib code had to work with, which requires the
driver to use a slightly different set of inputs for the actual
moderation values, while getting all the advice from dimlib of
better/worse, shift left or right.

The change made for this implementation is to use a pair of values
for each of the 5 "slots" that the dimlib moderation expects, and
the driver will program those pairs when dimlib recommends a slot to
use. The currently implementation uses two tables, one for receive
and one for transmit, and the pairs of values in each slot set the
maximum delay of an interrupt and a maximum number of interrupts per
second (both expressed in microseconds).

There are two separate kinds of bugs fixed by using DIMLIB, one is
UDP single stream send was too slow, and the other is that 8K
ping-pong was going to the most aggressive moderation and has much
too high latency.

The overall result of using DIMLIB is that we meet or exceed our
performance expectations set based on the old algorithm.
Co-developed-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Tracking of the rx_gro_dropped statistic was removed in
commit f73fc403 ("ice: drop dead code in ice_receive_skb()").
Remove the associated variables and its reporting to ethtool stats.
Signed-off-by: NAnirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

There is an issue when the Tx or Rx ring size increases using
'ethtool -L ...' where the new rings don't get the correct ITR
values because when we rebuild the VSI we don't know that some
of the rings may be new.

Fix this by looking at the original number of rings and
determining if the rings in ice_vsi_rebuild_set_coalesce()
were not present in the original rings received in
ice_vsi_rebuild_get_coalesce().

Also change the code to return an error if we can't allocate
memory for the coalesce data in ice_vsi_rebuild().
Signed-off-by: NPaul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Enable and configure XPS. The driver code implemented sets up the Transmit
Packet Steering Map, which in turn will be used by the kernel in queue
selection during Tx.
Signed-off-by: NBenita Bose <benita.bose@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Output of ice_rx_offset() is based on ethtool's priv flag setting, which
when changed, causes PF reset (disables napi, frees irqs, loads
different Rx mem model, etc.). This means that within napi its result is
constant and there is no reason to call it per each processed frame.

Add new 'rx_offset' field to ice_ring that is meant to hold the
ice_rx_offset() result and use it within ice_clean_rx_irq().
Furthermore, use it within ice_alloc_mapped_page().
Reviewed-by: NBjörn Töpel <bjorn.topel@intel.com>
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Similar thing has been done in i40e, as there is no real need for having
the sk_buff pointer in each rx_buf. Non-eop frames can be simply handled
on that pointer moved upwards to rx_ring.
Reviewed-by: NBjörn Töpel <bjorn.topel@intel.com>
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

The writeback enable logic was incorrectly implemented (due to
misunderstanding what the side effects of the implementation would be
during polling).

Fix this logic issue, while implementing a new feature allowing the user
to control the writeback frequency using the knobs for controlling
interrupt throttling that we already have.  Basically if you leave
adaptive interrupts enabled, the writeback frequency will be varied even
if busy_polling or if napi-poll is in use.  If the interrupt rates are
set to a fixed value by ethtool -C and adaptive is off, the driver will
allow the user-set interrupt rate to guide how frequently the hardware
will complete descriptors to the driver.

Effectively the user will get a control over the hardware efficiency,
allowing the choice between immediate interrupts or delayed up to a
maximum of the interrupt rate, even when interrupts are disabled
during polling.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Co-developed-by: NBrett Creeley <brett.creeley@intel.com>
Signed-off-by: NBrett Creeley <brett.creeley@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

This takes care of all of the trivial W=1 fixes in the Intel
Ethernet drivers, which allows developers and maintainers to
build more of the networking tree with more complete warning
checks.

There are three classes of kdoc warnings fixed:
 - cannot understand function prototype: 'x'
 - Excess function parameter 'x' description in 'y'
 - Function parameter or member 'x' not described in 'y'

All of the changes were trivial comment updates on
function headers.

Inspired by Lee Jones' series of wireless work to do the same.
Compile tested only, and passes simple test of
$ git ls-files *.[ch] | egrep drivers/net/ethernet/intel | \
  xargs scripts/kernel-doc -none
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Replace the explicit umem reference passed to the driver in AF_XDP
zero-copy mode with the buffer pool instead. This in preparation for
extending the functionality of the zero-copy mode so that umems can be
shared between queues on the same netdev and also between netdevs. In
this commit, only an umem reference has been added to the buffer pool
struct. But later commits will add other entities to it. These are
going to be entities that are different between different queue ids
and netdevs even though the umem is shared between them.
Signed-off-by: NMagnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NBjörn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-2-git-send-email-magnus.karlsson@intel.com

Display and count some useful hot-path statistics. The usefulness is as
follows:

- tx_restart: use to determine if the transmit ring size is too small or
  if the transmit interrupt rate is too low.
- rx_gro_dropped: use to count drops from GRO layer, which previously were
  completely uncounted when occurring.
- tx_busy: use to determine when the driver is miscounting number of
  descriptors needed for an skb.
- tx_timeout: as our other drivers, count the number of times we've reset
  due to timeout because the kernel only prints a warning once per netdev.

Several of these were already counted but not displayed.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

The page reuse statistic wasn't even being displayed to the user, even
though the driver counted it. Don't waste the struct space and hot-path
cycles since the driver doesn't display it.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Fix the remaining signed vs unsigned issues, which appear
when compiling with -Werror=sign-compare.

Many of these are because there is an external interface that is passing
an int to us (which we can't change) but that we (rightfully) store
and compare against as an unsigned in our data structures.
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NBruce Allan <bruce.w.allan@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Support the addition and deletion of IPv4 filters.

Supported fields are: src-ip, dst-ip, src-port, and dst-port
Supported flow-types are: tcp4, udp4, sctp4, ip4

Example usage:

ethtool -N eth0 flow-type tcp4 src-ip 192.168.0.55 dst-ip 172.16.0.55 \
src-port 16 dst-port 12 action 32
Signed-off-by: NHenry Tieman <henry.w.tieman@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Flow Director allows for redirection based on ntuple rules. Rules are
programmed using the ethtool set-ntuple interface. Supported actions are
redirect to queue and drop.

Setup the initial framework to process Flow Director filters. Create and
allocate resources to manage and program filters to the hardware. Filters
are processed via a sideband interface; a control VSI is created to manage
communication and process requests through the sideband. Upon allocation of
resources, update the hardware tables to accept perfect filters.
Signed-off-by: NHenry Tieman <henry.w.tieman@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Create a boost TCAM entry for each tunnel port in order to get a tunnel
PTYPE. Update netdev feature flags and implement the appropriate logic to
get and set values for hardware offloads.
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NHenry Tieman <henry.w.tieman@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Remove MEM_TYPE_ZERO_COPY in favor of the new MEM_TYPE_XSK_BUFF_POOL
APIs.

v4->v5: Fixed "warning: Excess function parameter 'alloc' description
        in 'ice_alloc_rx_bufs_zc'" and "warning: Excess function
        parameter 'xdp' description in
        'ice_construct_skb_zc'". (Jakub)
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: NBjörn Töpel <bjorn.topel@intel.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Cc: intel-wired-lan@lists.osuosl.org
Link: https://lore.kernel.org/bpf/20200520192103.355233-10-bjorn.topel@gmail.com

Currently if a user sets an odd [tx|rx]-usecs value through ethtool,
the request is denied because the hardware is set to have an ITR
granularity of 2us. This caused poor customer experience. Fix this by
aligning to a register allowed value, which results in rounding down.
Also, print a once per ring container type message to be clear about
our intentions.

Also, change the ITR_TO_REG define to be the bitwise and of the ITR
setting and the ICE_ITR_MASK. This makes the purpose of ITR_TO_REG more
obvious.
Signed-off-by: NBrett Creeley <brett.creeley@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This is a collection of trivial fixes including fixing whitespace, typos,
function headers, reverse Christmas tree, etc.
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

After each rebuild driver deallocates q_vectors, so the interrupt
throttle rate (ITR) settings get lost.

Create a function to save and restore ITR for each queue. If a user
increases the number of queues, restore all the previous queue
settings for each existing queue, and the additional queues will
get the default setting.
Signed-off-by: NMichal Swiatkowski <michal.swiatkowski@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Take into account the underlying architecture specific settings and
based on that calculate the possible padding that can be supplied.
Typically, for x86 and standard MTU size we will end up with 192 bytes
of headroom. This is the same behavior as our other drivers have and we
can dedicate it for XDP purposes.

Furthermore, introduce the Rx ring flag for indicating whether build_skb
is used on particular. Based on that invoke the routines for padding
calculation.
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Add an ethtool "legacy-rx" priv flag for toggling the Rx path. This
control knob will be mainly used for build_skb usage as well as buffer
size/MTU manipulation.

In preparation for adding build_skb support in a way that it takes
care of how we set the values of max_frame and rx_buf_len fields of
struct ice_vsi. Specifically, in this patch mentioned fields are set to
values that will allow us to provide headroom and tailroom in-place.

This can be mostly broken down onto following:
- for legacy-rx "on" ethtool control knob, old behaviour is kept;
- for standard 1500 MTU size configure the buffer of size 1536, as
  network stack is expecting the NET_SKB_PAD to be provided and
  NET_IP_ALIGN can have a non-zero value (these can be typically equal
  to 32 and 2, respectively);
- for larger MTUs go with max_frame set to 9k and configure the 3k
  buffer in case when PAGE_SIZE of underlying arch is less than 8k; 3k
  buffer is implying the need for order 1 page, so that our page
  recycling scheme can still be applied;

With that said, substitute the hardcoded ICE_RXBUF_2048 and PAGE_SIZE
values in DMA API that we're making use of with rx_ring->rx_buf_len and
ice_rx_pg_size(rx_ring). The latter is an introduced helper for
determining the page size based on its order (which was figured out via
ice_rx_pg_order). Last but not least, take care of truesize calculation.

In the followup patch the headroom/tailroom computation logic will be
introduced.

This change aligns the buffer and frame configuration with other Intel
drivers, most importantly with iavf.
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Add zero copy AF_XDP support.  This patch adds zero copy support for
Tx and Rx; code for zero copy is added to ice_xsk.h and ice_xsk.c.

For Tx, implement ndo_xsk_wakeup. As with other drivers, reuse
existing XDP Tx queues for this task, since XDP_REDIRECT guarantees
mutual exclusion between different NAPI contexts based on CPU ID. In
turn, a netdev can XDP_REDIRECT to another netdev with a different
NAPI context, since the operation is bound to a specific core and each
core has its own hardware ring.

For Rx, allocate frames as MEM_TYPE_ZERO_COPY on queues that AF_XDP is
enabled.
Signed-off-by: NKrzysztof Kazimierczak <krzysztof.kazimierczak@intel.com>
Co-developed-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

In preparation of AF XDP, move functions that will be used both by skb and
zero-copy paths to a new file called ice_txrx_lib.c.  This allows us to
avoid using ifdefs to control the staticness of said functions.

Move other functions (ice_rx_csum, ice_rx_hash and ice_ptype_to_htype)
called only by the moved ones to the new file as well.
Signed-off-by: NKrzysztof Kazimierczak <krzysztof.kazimierczak@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Add support for XDP. Implement ndo_bpf and ndo_xdp_xmit.  Upon load of
an XDP program, allocate additional Tx rings for dedicated XDP use.
The following actions are supported: XDP_TX, XDP_DROP, XDP_REDIRECT,
XDP_PASS, and XDP_ABORTED.
Signed-off-by: NMaciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Remove a few uses of kernel configuration flags from ice_lib.c by
introducing a new source file ice_base.c. Also move corresponding
function prototypes from ice_lib.h to ice_base.h and include ice_base.h
where required.
Signed-off-by: NAnirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Currently when busy polling is enabled we aren't setting/enabling
WB_ON_ITR in the driver. This doesn't break the driver, but it does
cause issues. If we don't enable WB_ON_ITR mode we will still get
write-backs from hardware during polling when a cache line has been
filled, but if a cache line is not filled we will not get the
write-back because WB_ON_ITR is not set. Fix this by enabling
WB_ON_ITR in the driver when interrupts are disabled.
Signed-off-by: NBrett Creeley <brett.creeley@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

We can use bit fields to store boolean values and when the
bit fields are next to each other, the compiler will combine them
(as long as the size holds enough).
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NAnirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Use more efficient structure ordering by using the pahole tool
and a lot of code inspection to get hot cache lines to have
packed data (no holes if possible) and adjacent warm data.

ice_ring prior to this change:
  /* size: 192, cachelines: 3, members: 23 */
  /* sum members: 158, holes: 4, sum holes: 12 */
  /* padding: 22 */

ice_ring after this change:
  /* size: 192, cachelines: 3, members: 25 */
  /* sum members: 162, holes: 1, sum holes: 1 */
  /* padding: 29 */

ice_tx_buf prior to this change:
  /* size: 48, cachelines: 1, members: 7 */
  /* sum members: 38, holes: 2, sum holes: 6 */
  /* padding: 4 */
  /* last cacheline: 48 bytes */

ice_tx_buf after this change:
  /* size: 40, cachelines: 1, members: 7 */
  /* sum members: 38, holes: 1, sum holes: 2 */
  /* last cacheline: 40 bytes */
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NAnirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Currently the driver allows rx-usecs-high values to be set,
but when querying the device for rx-usecs-high the value
does not stick. This is because it was not yet implemented.
Add code to allow the user to change rx-usecs-high and
use this to set the q_vector's intrl value.
Signed-off-by: NBrett Creeley <brett.creeley@intel.com>
Signed-off-by: NAnirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>