The value we read from the header is in network byte order, whereas
 EFX_POPULATE_QWORD_* takes values in host byte order (which it then
 converts to little-endian, as MCDI is little-endian).

Fixes: e9117e50 ("sfc: Firmware-Assisted TSO version 2")
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It confuses sparse, which thinks the size isn't constant.  Let's achieve
 the same thing with a BUILD_BUG_ON, since we know which one should be
 bigger and don't expect them ever to change.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

efx_start_all can return without initialising queues as a reset is pending.
 This means that when netif_device_attach is called, the kernel can start
 sending traffic without having an initialised TX queue to send to.
This patch avoids this by not calling netif_device_attach if there is a
 pending reset.

Fixes: e283546c ("sfc:On MCDI timeout, issue an FLR (and mark MCDI to fail-fast)")
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If the hw doesn't think they exist, we should defer to its authority.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On EF10, hardware filter IDs are 13 bits, but in some places we store
 32-bit "full filter IDs" in which higher order bits encode the filter
 match-priority.  This could cause a filter to have a full filter ID of
 0xffff, which is also the value EFX_EF10_FILTER_ID_INVALID which we use
 in 16-bit "short" filter IDs (without match-priority bits).  This would
 occur if the hardware filter ID was 0x1fff and the match-priority was 7.
Unfortunately, some code that checks for EFX_EF10_FILTER_ID_INVALID can
 be called on full filter IDs, and will WARN_ON if this ever happens.
So, since we have plenty of spare bits in the full filter ID, this patch
 shifts the priority bits left one bit when constructing the full filter
 IDs, ensuring that the 0x2000 bit of a full filter ID will always be 0
 and thus no full filter ID can ever equal EFX_EF10_FILTER_ID_INVALID.

This patch also replaces open-coded full<->short filter ID conversions
 with calls to functions, thus keeping the definition of the full filter
 ID format in one place.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add min_interrupt_mode specification per NIC type.
It is a bit confusing because of "highest interrupt mode is less capable".
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fixes: a0ee3541 ("sfc: process RX event inner checksum flags")
Reported-by: NColin Ian King <colin.king@canonical.com>
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Implement ndo_udp_tunnel_{add,del} to update the NIC's list of VXLAN and
 GENEVE UDP ports.  Also reset the port list to empty on driver load and
 on driver unload, with appropriate flag set on the unload case.
These port numbers are used for RX inner checksum offload, and in future
 will also be used for TX inner checksum offload and encapsulated TSO.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Set the csum_level for encapsulated packets where the encapsulation
 type, l3 class and l4 class are sets that need it.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add support for RX checksum offload of encapsulated packets. This
 essentially just means paying attention to the inner checksum flags
 in the RX event, and if *either* checksum flag indicates a fail then
 don't tell the kernel that checksum offload was successful.
Also, count these checksum errors and export the counts to ethtool -S.

Test the most common "good" case of RX events with a single bitmask
 instead of a series of ifs.  Move the more specific error checking
 in to a separate function for clarity, and don't use unlikely() there
 since we know at least one of the bits is bad.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This bug is harmless because it's just a sanity check and we always
pass valid values for "encap_type" but the test is off by one.

Fixes: 9b410801 ("sfc: insert catch-all filters for encapsulated traffic")
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Acked-by: NBert Kenward <bkenward@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

encap_type should be checked to see if it is greater or equal to
the size of array map to fix an off-by-one array size check. This
fixes an array overrun read as detected by static analysis by
CoverityScan, CID#1398883 ("Out-of-bounds-read")

Fixes: 9b410801 ("sfc: insert catch-all filters for encapsulated traffic")
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Acked-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

8000 series adapters support filtering VXLAN, NVGRE and GENEVE traffic
 based on inner fields, and when the NIC recognises such traffic, it
 does not match unencapsulated traffic filters any more.  So add catch-
 all filters for encapsulated traffic on supporting platforms.
Although recognition of VXLAN and GENEVE is based on UDP ports, and thus
 will not occur until the driver (on the primary PF) notifies the
 firmware of UDP ports to use, NVGRE will always be recognised, hence
 without this patch 8000 series adapters will drop all NVGRE traffic.

Partly based on patches by Jon Cooper <jcooper@solarflare.com>.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Rationalise several debug-or-warnings printks using netif_cond_dbg
 to make output more consistent.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If the NIC is switched from full-featured to low-latency, encapsulated
 filters are no longer available, and this causes errors. This patch
 removes those filters from the filter table on restore.
Also, if filters which are removed by the above, or which we fail to
 insert when restoring filters, were UC, MC or broadcast default
 filters, invalidate the corresponding vlan->default_filters entry.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

PIO buffer allocation can fail for two valid reasons:
 - we've run out of them (results in -ENOSPC)
 - the NIC configuration doesn't support them (results in -EPERM)
Since both these failures are expected netif_err is excessive.
Signed-off-by: NBert Kenward <bkenward@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Ensures that we report the key and indirection table the NIC is using,
 rather than (if setting them failed earlier) what we wanted it to use.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The 8000 series SFC NICs have 4K PIO buffers, rather than the 2K of
 the 7000 series.  Rather than having a hard-coded PIO buffer size
 (ER_DZ_TX_PIOBUF_SIZE), read it from the GET_CAPABILITIES_V2 MCDI
 response.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If an option descriptor has been sent on a queue but not followed by a
 packet, there will have been no completion event, so the read and write
 counts won't match and we'll think we can't do PIO.  This combines with
 the fact that we have two TX queues (for en/disable checksum offload),
 and that both must be empty for PIO to happen.
This patch adds a separate "packet_write_count" that tracks the most
 recent write_count we expect to see a completion event for; this excludes
 option descriptors but _includes_ PIO descriptors (even though they look
 like option descriptors).  This is then used, rather than write_count,
 in efx_nic_tx_is_empty().
We only bother to maintain packet_write_count on EF10, since on Siena
 (a) there are no option descriptors and it always equals write_count, and
 (b) there's no PIO, so we don't need it anyway.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Setting dev_port changes the device names allocated by systemd. Any devices
with a dev_port >0 will (in default distro configurations) have a suffix of
"d<port-number>" appended.

This is not something done by other drivers, and causes confusion for users.

Fixes: 8be41320 ("sfc: Add code to export port_num in netdev->dev_port")
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There's no good reason why this should be an SRIOV-only thing.
Thus, also move it out of SRIOV-specific files.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If we failed to set up RSS on EF10 (e.g. because firmware declared
 RX_RSS_LIMITED), ethtool --show-nfc $dev rx-flow-hash ... should report
 no fields, rather than confusingly reporting what fields we _would_ be
 hashing on if RSS was working.

Fixes: dcb4123c ("sfc: disable RSS when unsupported")
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Logically, EFX_BUG_ON_PARANOID can never be correct.  For, BUG_ON should
 only be used if it is not possible to continue without potential harm;
 and since the non-DEBUG driver will continue regardless (as the BUG_ON is
 compiled out), clearly the BUG_ON cannot be needed in the DEBUG driver.
So, replace every EFX_BUG_ON_PARANOID with either an EFX_WARN_ON_PARANOID
 or the newly defined EFX_WARN_ON_ONCE_PARANOID.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It gives no advantage over GSO now that xmit_more exists.  If we find
 ourselves unable to handle a TSO skb (because our TXQ doesn't have a
 TSOv2 context and the NIC doesn't support TSOv1), hand it back to GSO.
 Also do that if the TSO handler fails with EINVAL for any other reason.
As Falcon-architecture NICs don't support any firmware-assisted TSO,
 they no longer advertise TSO feature flags at all.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If we fail to init the TXQ because of insufficient TSOv2 contexts,
try again with TSOv2 disabled.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add support for FATSOv2 to the driver. FATSOv2 offloads far more of the task
 of TCP segmentation to the firmware, such that we now just pass a single
 super-packet to the NIC. This means TSO has a great deal in common with a
 normal DMA transmit, apart from adding a couple of option descriptors.
 NIC-specific checks have been moved off the fast path and in to
 initialisation where possible.

This also moves FATSOv1/SWTSO to a new file (tx_tso.c).  The end of transmit
 and some error handling is now outside TSO, since it is common with other
 code.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This improves UDP spreading, and also slightly improves GRO performance
of encapsulated TCP on 7000 series NICs.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

MC_CMD_TRIGGER_INTERRUPT does not work on the SFC9140, as used in the
sfn7x42q and sfn7x24f.
Check for this using the MCDI workaround mechanism.
The command is only used during self test.  If it's not supported, skip
the interrupt test.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

nic_data was already initialised to the right thing, no need to assign
it again.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TX size bins were not supported on the 7000's 40G MAC, but the 8000 series
does support them and the MCPU advertises that via a new capability bit.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On 32-bit systems, mask is only an array of 3 longs, not 4, so don't try
to write to mask[3].
Also include build-time checks in case the size of the bitmask changes.

Fixes: 3c36a2ad ("sfc: display vadaptor statistics for all interfaces")
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The division is already being done properly in efx_ef10_get_timer_config
which returns zero-on-success, unlike the old efx_ef10_get_sysclk_freq.

Fixes: d95e329a ("sfc: get timer configuration from adapter")
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On SFN8000 series adapters the MC provides a method to get the timer
quantum and the maximum timer setting. We revert to the old values if the
new call is unavailable.
Signed-off-by: NBert Kenward <bkenward@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

SFN8000-series NICs require a new method of setting interrupt moderation,
via MCDI. This is indicated by a workaround flag. This new MCDI command
takes an explicit time value rather than a number of ticks. It therefore
makes sense to also store the moderation values in terms of time, since
that is what the ethtool interface is interested in.
Signed-off-by: NBert Kenward <bkenward@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Rather than explicitly specifying flags we can now specify a desired
performance target to the firmware, ie higher throughput or lower latency.
For now we use the default "auto" configuration.
Signed-off-by: NBert Kenward <bkenward@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NBert Kenward <bkenward@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If vPort has VLAN_RESTRICT flag, VLAN tagged traffic will not be
delivered without corresponding Rx filters which may be proxied to and
moderated by hypervisor.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If it is not supported we simply disable the feature.

For the feature to work we need firmware filter support for
OUTER_VID + LOC_MAC and for OUTER_VID + LOC_MAC_IG.
The low-latency firmware can match on OUTER_VID + LOC_MAC but not on
OUTER_VID + LOC_MAC_IG.
For the capture packet firmware it is the other way around.
Only the full-feature variant can match on both combinations.

Incorporates a fix by Andrew Rybchenko <Andrew.Rybchenko@oktetlabs.ru>
in the net_dev->[hw_]features handling.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>