Adds functions to allocate and free vswitches and vports; vadaptors
are automatically allocated and freed when TX/RX queues are
initialised and finalised.  This vswitching structure is only created
if the firmware supports it, so a check that full-featured firmware
is running is performed first.

If the MC resets, the vswitching infrastructure will need to be
recreated, so mark the "must_probe_vswitching" flag when an MC reboot
is detected.

Don't try to create a vswitch if vf-count=0

This allocation of vswitches and vports does not currently support
configuring VLAN tags, but that can be added in a future change.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The default port ID of EVB_PORT_ID_ASSIGNED is a "magic" number
for the MCFW to select the physical port of the PF.  If other
vswitches and vports are created on top of the default firmware
configuration, the ID of the newly created vport is then required
when passed to MCDI commands.  Currently, this doesn't happen so
the vport_id is never changed, but a subsequent patch will change
this behaviour so that other vswitches and vports are created.

The vport_id recorded in nic_data is only relevant for PFs.
VFs will have their vports created by their parent PF, and in
that case the parent PF will record the vport ID of each VF.
For a VF, nic_data->vport_id is expected to remain at the default
value.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The (future) code to add/remove vswitches and vports will be
dependent on the firmware variant.
To simplify the checking of the firmware variant, record
values for rx_dpcpu_fw_id and tx_dpcpu_fw_id in EF10 nic_data.

There was only one place where this was previously used:
efx_mcdi_print_fwver() in ethtool.c.
The MC_CMD_GET_CAPABILITIES can be replaced and the values from
nic_data used instead.

Note that the printing of "?" if the MC command fails or if the
outlength is incorrect no longer apply, because errors are returned
in efx_ef10_init_datapath_caps() in both of these cases.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The TX_DOMAIN field is currently reserved but its safer to set
it to 0 for future compatibility.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds support for the use of sriov_configure on EF10
to enable Virtual Functions while the driver is loaded.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

sfc: Own header for nic-specific sriov functions, single instance of netdev_ops and sriov removed from Falcon code

By putting all the efx_{siena,ef10}_sriov_* declarations in
{siena,ef10}_sriov.h, ensure they cannot be called from nic-generic code.
Also fixes up an instance of this, where mcdi.c was calling
efx_siena_sriov_flr.

The single instance of netdev_ops should call general high level
functions that can then call something adapter specific in efx_nic_type.
We should only do adapter specialisation via efx_nic_type.

Removal of sriov functionality from the Falcon code means that tests
are needed for the presence of some callbacks.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This reverts commits:

d92916f7 ("sfc: Own header for nic-specific sriov functions,")
25672dba ("sfc: Enable VF's via a write to the sysfs file
 sriov_numvfs")

As they break the build with SRIOV disabled and there is no
easy way to fix it the way things are arranged.
Reported-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds support for the use of sriov_configure on EF10
to enable Virtual Functions while the driver is loaded.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

sfc: Own header for nic-specific sriov functions, single instance of netdev_ops and sriov removed from Falcon code

By putting all the efx_{siena,ef10}_sriov_* declarations in
{siena,ef10}_sriov.h, ensure they cannot be called from nic-generic code.
Also fixes up an instance of this, where mcdi.c was calling
efx_siena_sriov_flr.

The single instance of netdev_ops should call general high level
functions that can then call something adapter specific in efx_nic_type.
We should only do adapter specialisation via efx_nic_type.

Removal of sriov functionality from the Falcon code means that tests
are needed for the presence of some callbacks.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Also add dummy functions where required to avoid NULL pointer dereference.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

efx_ef10_probe() was BUGging out if the BAR2 size was 0.  This is
 unnecessarily violent; instead we should just fail to probe the device.
Kept a WARN_ON as this problem indicates a broken or misconfigured NIC.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Added a counter rx_noskb_drop for failure to allocate an skb.
Summed the per-channel rx_nodesc_trunc counters earlier so that they can
 be included in rx_dropped.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When an MCDI command times out (whether or not we find it
completed when we poll), call efx_mcdi_abandon(), which tells
all subsequent MCDI calls to fail-fast, and queues up an FLR.

Because an FLR doesn't lead to receiving any reboot even from
the MC (unlike most other types of reset), we have to call
efx_ef10_reset_mc_allocations.
In efx_start_all(), if a reset (of any kind) is pending, we
bail out.
Without this, attempts to reconfigure (e.g. change mtu) can
cause driver/mc state inconsistency if the first MCDI call
triggers an FLR.

For similar reasons, on EF10, in
efx_reset_down(method=RESET_TYPE_MCDI_TIMEOUT), set the number
of active queues to zero before calling efx_stop_all().
And, on farch, in efx_reset_up(method=RESET_TYPE_MCDI_TIMEOUT),
set active_queues and flushes pending & outstanding to zero.

efx_mcdi_mode_{poll,event}() should not take us out of fail-fast
 mode. Instead, this is done by efx_mcdi_reset() after the FLR
completes.

The new FLR reset_type RESET_TYPE_MCDI_TIMEOUT doesn't really
fit into the hierarchy of reset 'scopes' whereby efx_reset()
decides some resets subsume others.  Thus, it uses separate logic.

Also, fixed up some inconsistency around RESET_TYPE_MC_BIST,
which was in the wrong place in that hierarchy.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When using the "separate_tx_channels=1" module parameter, the TX queues are
initially numbered starting from the first TX-only channel number (after all the
RX-only channels).  efx_set_channels() renumbers the queues so that they are
indexed from zero.

On EF10, the TX queues need to be relabelled in this way before calling the
dimension_resources NIC type operation, otherwise the TX queue PIO buffers can be
linked to the wrong VIs when using "separate_tx_channels=1".

Added comments to explain UC/WC mappings for PIO buffers
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Processing any incoming packets with a with a napi budget of 0
is incorrect driver behavior.

This matters as netpoll will shortly call drivers with a budget of 0
to avoid receive packet processing happening in hard irq context.
Signed-off-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Faster than memcpy/memset on some architectures.
Signed-off-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

EF10 implements option descriptors to switch TX checksum offload
on and off between packets.  We could therefore use a single
hardware TX queue per kernel TX queue, although we don't yet.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

PORT_RESET MC command was NOP in the ef10 firmware hence we are using
ENTITY_RESET to make sure all resource allocations are reset.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When we insert an filter, the firmware checks that the given RX queue
index is in range even if it will not be used.  In case we're
inserting a drop filter, pass the value 0.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The original names are unnecessarily alarming.  Head-of-line blocking
is not an emergency.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The operation can now fail, so change its return type to int.

Remove the inline wrapper while we're changing the signature.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Currently a higher priority client can remove a lower priority
client's filter with equal match-expression.  This might happen if (a)
the higher priority client has a double-free bug, or (b) another
client with sufficient priority replaced and then removed an equal
filter, allowing the low priority client to insert an equal filter.

In neither case does it actually make sense to carry out the removal;
we should say the filter doesn't exist, as the filter currently
present is not the one that the high-priority client is referring to.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Change all the 'stack' naming to 'auto' (or other meaningful term);
the device address list is based on more than just what the network
stack wants, and the no-match filters aren't really what the stack
wants at all.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

MAC filters inserted automatically by the driver, based on the device
address list (EF10) or no-match filters (Siena), should be overridable
at MANUAL or REQUIRED priority.  Currently they themselves have
REQUIRED priority and this requires some odd special-casing.

We also can't reliably tell whether such a MAC filter has or has
not been overridden.  We just remember that it is wanted by the
stack (RX_STACK flag).

Add another priority level, AUTO, between HINT and MANUAL, and
use this for the automatic filters while they have not been
overridden.  Remove the RX_STACK flag.  Add an RX_OVER_AUTO
flag which is set only when an AUTO filter has been overridden
(or was requested to be inserted while a higher-priority filter
existed).
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The EF10 implementation already does this, and it makes more logical
sense to group the RSS hash key and indirection table together.
Rename the operation to rx_push_rss_config.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

In case of certain hardware and firmware errors it can be useful to
have more context than just the file and line number.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The SFC9100 family has only one clock per controller, shared by all
functions.  Therefore only create a clock device under the primary
function, and make all other functions refer to the primary's clock
device.

Since PTP functionality is limited to port 0 and PF 0 on the earlier
SFN[56]322F boards, and we also set the primary flag for that
function, we can make the creation of a clock device conditional only
on this flag.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The EF10 firmware can optionally insert RX timestamps in the packet
prefix.  These only include the clock minor value.  We must also
enable periodic time sync events on each event queue which provide
the high bits of the clock value.

[bwh: Combined and rebased several changes.
 Added the above description and some sanity checks for inline vs
 separate timestamps.
 Changed efx_rx_skb_attach_timestamp() to read the packet prefix
 from the skb head area.]
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The MC firmware will return error MC_CMD_ERR_ENOSPC if filter
insertion fails due to lack of resources.  The net driver's filter
implementation for Falcon-architecture returns EBUSY.  They should
behave consistently, so for EF10 change ENOSPC to EBUSY.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Split each of efx_mcdi_rpc, efx_mcdi_rpc_finish, and efx_mcdi_rpc_async into
a normal and a _quiet version; made the former log MCDI errors with
netif_err (and include the raw MCDI error code), and the latter never log
them at all.  Changed various callers; any where some errors are expected
(but others are not) call the _quiet version and then if necessary log the
MCDI error themselves.  Said logging is done by new efx_mcdi_display_error.

Callers of efx_mcdi_rpc*_quiet functions which may want to log the error
need to ensure that their outbuf is big enough to hold an MCDI error; to
this end, they now use MCDI_DECLARE_BUF_OUT_OR_ERR, which always allocates
at least 8 bytes.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

We don't directly control RX ingress on Siena or any later
controllers, and so we cannot prevent packets from entering the RX
datapath while the RX queues are not set up.  This results in
the hardware incrementing RX_NODESC_DROP_CNT, but it's not an
error and we should not include it in error stats.

When bringing an interface up or down, pull (or wait for) stats and
count the number of packets that were dropped while the interface was
down.  Subtract this from the reported RX dropped count.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

The addition of RX event merging support means we don't reliably
detect dropped RX events now.  Currently we will only detect them if
the previous event for the RX queue had the CONT bit set.

Only accept RX completion events as merged if the
GET_CAPABILITIES_OUT_RX_BATCHING bit is set in datapath_caps (which it
won't be for the low-latency datapath) and the CONT bit is not set on
the event.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

To run BISTs the MC goes down in to a special mode where it will only
respond to MCDI from the testing PF, and TX, RX and event queues are
torn down. Other PFs get a message as it goes down to tell them it's
going down.

When the other PFs get this message, they check the soft status
register to tell when the MC has rebooted after BIST mode and they can
start recovery.

[bwh: Convert the test result to 1 or -1 as for earlier NICs]
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Recognise the new Packet Memory and RX Data Path counters.

The following counters are added:
rx_pm_{trunc,discard}_bb_overflow - burst buffer overflowed.  This should not
 occur if BB correctly configured.
rx_pm_{trunc,discard}_vfifo_full - not enough space in packet memory.  May
 indicate RX performance problems.
rx_pm_{trunc,discard}_qbb - dropped by 802.1Qbb early discard mechanism.
 Since Qbb is not supported at present, this should not occur.
rx_pm_discard_mapping - 802.1p priority configured to be dropped.  This should
 not occur in normal operation.
rx_dp_q_disabled_packets - packet was to be delivered to a queue but queue is
 disabled.  May indicate misconfiguration by the driver.
rx_dp_di_dropped_packets - parser-dispatcher indicated that a packet should be
 dropped.
rx_dp_streaming_packets - packet was sent to the RXDP streaming bus, ie. a
 filter directed the packet to the MCPU.
rx_dp_emerg_{fetch,wait} - RX datapath had to wait for descriptors to be
 loaded.  Indicates performance problems but not drops.

These are only provided if the MC firmware has the
PM_AND_RXDP_COUNTERS capability.  Otherwise, mask them out.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Previously, efx_ef10_stat_mask returned a static const unsigned long[], which
meant that each possible mask had to be declared statically with
STAT_MASK_BITMAP.  Since adding a condition would double the size of the
decision tree, we now create the bitmask dynamically.

To do this, we have two functions efx_ef10_raw_stat_mask, which returns a u64,
and efx_ef10_get_stat_mask, which fills in an unsigned long * argument.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Try to allocate a segment of PIO buffer to each TX channel.  If
allocation fails, log an error but continue.

PIO buffers must be mapped separately from the NIC registers, with
write-combining enabled.  Where the host page size is 4K, we could
potentially map each VI's registers and PIO buffer separately.
However, this would add significant complexity, and we also need to
support architectures such as POWER which have a greater page size.
So make a single contiguous write-combining mapping after the
uncacheable mapping, aligned to the host page size, and link PIO
buffers there.  Where necessary, allocate additional VIs within
the write-combining mapping purely for access to PIO buffers.

Link all TX buffers to TX queues and the additional VIs in
efx_ef10_dimension_resources() and in efx_ef10_init_nic() after
an MC reboot.
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>

Signed-off-by: NFengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NBen Hutchings <bhutchings@solarflare.com>