Since there are potential drawbacks to the new Rx allocation approach I
thought it best to add a "chicken bit" so that we can turn the feature off
if in the event that a problem is found.

It also provides a means of validating the legacy Rx path in the event that
we are forced to fall back.  At some point in the future when we are
convinced we don't need it anymore we might be able to drop the legacy-rx
flag.
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 providing a buffer with headroom and tailroom
to allow for shared info, NET_SKB_PAD, and NET_IP_ALIGN.  With this
combined with the DMA changes we can start using build_skb to build frames
around an incoming Rx buffer instead of having to memcpy the headers.
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 are going to be expanding the number of Rx paths in the driver.  Instead
of duplicating all that code I am pulling it apart into separate functions
so that we don't have so much code duplication.
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.
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>

In order to support build_skb with jumbo frames it will be necessary to use
3K buffers for the Rx path with 8K pages backing them.  This is needed on
architectures that implement 4K pages because we can't support 2K buffers
plus padding in a 4K page.

In the case of systems that support page sizes larger than 4K the 3K
attribute will only be applied to FCoE as we can fall back to using just 2K
buffers and adding the padding.
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>

Batch the page count updates instead of doing them one at a time.  By doing
this we can improve the overall performance as the atomic increment
operations can be expensive due to the fact that on x86 they are locked
operations which can cause stalls.  By doing bulk updates we can
consolidate the stall which should help to improve the overall receive
performance.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Acked-by: NJohn Fastabend <john.r.fastabend@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.
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>

On some platforms, syncing a buffer for DMA is expensive. Rather than
sync the whole 2K receive buffer, only synchronise the length of the
frame, which will typically be the MTU, or a much smaller TCP ACK.
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 consolidates the code for the ixgbe driver so that it is more
inline with what is already in igb.  The general idea is to just
consolidate functions that represent logical steps in the Rx process so we
can later update them more easily.
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 version to reflect the new devices that it
supports.
Signed-off-by: NMark Rustad <mark.d.rustad@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Since dcbnl_ops is global, it should be prefixed by ixgbe_
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Though not advertised through ethtool, if the link partner advertises a
2.5Gb or 5Gb connection, and the adapter supports it, allow the speed to be
used.
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: NKrishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

In linux-4.5, busy polling was implemented in core
NAPI stack, meaning that all custom implementation can
be removed from drivers.

Not only we remove lot's of code, we also remove one lock
operation in fast path, and allow GRO to do its job.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Acked-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The network stack no longer uses the last_rx member of struct net_device
since the bonding driver switched to use its own private last_rx in
commit 9f242738 ("bonding: use last_arp_rx in slave_last_rx()").

However, some drivers still (ab)use the field for their own purposes and
some driver just update it without actually using it.

Previously, there was an accompanying comment for the last_rx member
added in commit 4dc89133 ("net: add a comment on netdev->last_rx")
which asked drivers not to update is, unless really needed. However,
this commend was removed in commit f8ff080d ("bonding: remove
useless updating of slave->dev->last_rx"), so some drivers added later
on still did update last_rx.

Remove all usage of last_rx and switch three drivers (sky2, atp and
smc91c92_cs) which actually read and write it to use their own private
copy in netdev_priv.

Compile-tested with allyesconfig and allmodconfig on x86 and arm.

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Mirko Lindner <mlindner@marvell.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: NTobias Klauser <tklauser@distanz.ch>
Acked-by: NEric Dumazet <edumazet@google.com>
Reviewed-by: NJay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Relax ordering(RO) is one feature of 82599 NIC, to enable this feature can
enhance the performance for some cpu architecure, such as SPARC and so on.
Currently it only supports one special cpu architecture(SPARC) in 82599
driver to enable RO feature, this is not very common for other cpu architecture
which really needs RO feature.
This patch add one common config CONFIG_ARCH_WANT_RELAX_ORDER to set RO feature,
and should define CONFIG_ARCH_WANT_RELAX_ORDER in sparc Kconfig firstly.
Signed-off-by: NMao Wenan <maowenan@huawei.com>
Reviewed-by: NAlexander Duyck <alexander.duyck@gmail.com>
Reviewed-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The network device operation for reading statistics is only called
in one place, and it ignores the return value. Having a structure
return value is potentially confusing because some future driver could
incorrectly assume that the return value was used.

Fix all drivers with ndo_get_stats64 to have a void function.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch extends the xcast mailbox message to include support for
unicast promiscuous mode.  To allow a VF to enter this mode the PF
must be in promiscuous mode.

A later patch will add the support needed in the VF driver (ixgbevf)
Signed-off-by: NDon Skidmore <donald.c.skidmore@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Implement support for devices that have firmware-controlled PHYs.
Signed-off-by: NMark Rustad <mark.d.rustad@intel.com>
Tested-by: NKrishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Implement new interface for firmware commands to access some PHYs.
Signed-off-by: NMark Rustad <mark.d.rustad@intel.com>
Tested-by: NKrishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The firmware version method and functions are not used anywhere, so
remove them all.
Signed-off-by: NMark Rustad <mark.d.rustad@intel.com>
Tested-by: NKrishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

There are two problems with EEPROM access. One is that it needs to
hold the semaphore until the entire response is read or else the
response can be corrupted by other firmware accesses. The second
problem is that acquiring and releasing the semaphore is slow, so
it should be taken and released once when multiple EEPROM accesses
will be done.

Both of these issues can be solved by adding a new function,
ixgbe_hic_unlocked, to issue firmware commands that will assume
that the caller has acquired the needed semaphore.
Signed-off-by: NMark Rustad <mark.d.rustad@intel.com>
Tested-by: NKrishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch ensures that the advertised link speeds are configured
for X553 KR/KX backplane.  Without this patch the link remains at
1G when resuming from low power after being downshifted by LPLU.
Signed-off-by: NDon Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Rx timestamp does not work on 82599 and X540 because bitwise operation
of RX_HWTSTAMP flags is incorrect and ixgbe_ptp_rx_hwtstamp() is never
called. This patch fixes it to enable Rx timestamp on 82599 and X540.

Without this fix:
ptp4l[278.730]: selected /dev/ptp8 as PTP clock
ptp4l[278.733]: port 1: INITIALIZING to LISTENING on INITIALIZE
ptp4l[278.733]: port 0: INITIALIZING to LISTENING on INITIALIZE
ptp4l[278.834]: port 1: received SYNC without timestamp
ptp4l[278.835]: port 1: new foreign master 1c3947.fffe.60f9cc-1
ptp4l[279.834]: port 1: received SYNC without timestamp
ptp4l[280.834]: port 1: received SYNC without timestamp
ptp4l[281.834]: port 1: received SYNC without timestamp
ptp4l[282.834]: port 1: received SYNC without timestamp
ptp4l[282.835]: selected best master clock 1c3947.fffe.60f9cc
ptp4l[282.835]: port 1: LISTENING to UNCALIBRATED on RS_SLAVE
ptp4l[283.834]: port 1: received SYNC without timestamp

With this fix:
ptp4l[239.154]: selected /dev/ptp8 as PTP clock
ptp4l[239.157]: port 1: INITIALIZING to LISTENING on INITIALIZE
ptp4l[239.157]: port 0: INITIALIZING to LISTENING on INITIALIZE
ptp4l[240.989]: port 1: new foreign master 1c3947.fffe.60f9cc-1
ptp4l[244.989]: selected best master clock 1c3947.fffe.60f9cc
ptp4l[244.989]: port 1: LISTENING to UNCALIBRATED on RS_SLAVE
ptp4l[246.977]: master offset -899583339542096 s0 freq      +0 path delay     16222
ptp4l[247.977]: master offset -899583339617265 s1 freq  -75169 path delay     16177
ptp4l[248.977]: master offset       -130 s2 freq  -75299 path delay     16177
ptp4l[248.977]: port 1: UNCALIBRATED to SLAVE on MASTER_CLOCK_SELECTED
ptp4l[249.977]: master offset         -9 s2 freq  -75217 path delay     16177
ptp4l[250.977]: master offset         88 s2 freq  -75123 path delay     16132

Fixes: a9763f3c ("ixgbe: Update PTP to support X550EM_x devices")
Signed-off-by: NYusuke Suzuki <yus-suzuki@uf.jp.nec.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Make sure that we free the IRQs in ixgbe_io_error_detected() when
responding to an PCIe AER error and also restore them when the
interface recovers from it.

Previously it was possible to trigger BUG_ON() check in free_msix_irqs()
in the case where we call ixgbe_remove() after a failed recovery from
AER error because the interrupts were not freed.
Signed-off-by: NEmil Tantilov <emil.s.tantilov@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

There are two methods for setting mac addresses in a Macvlan, that
differentiate themselves in the function macvlan_set_mac_Address.
If the macvlan mode is passthru, then we use the dev_set_mac_address
method, otherwise we use the dev_uc api via macvlan_sync_addresses.
The latter method (which would stem from using any non-passthru mode,
like bridge, or vepa), calls down into the driver in a path that terminates
in ixgbevf_set_uc_addr_vf, which sends a IXGBE_VF_SET_MACVLAN message,
which causes the pf to spawn the noted error message.  This occurs because
it appears that the guest is trying to delete the mac address of the macvlan
before adding another.

The other path in macvlan_set_mac_address uses dev_set_mac_address, which
calls into ixgbevf_set_mac which uses the IXGBE_VF_SET_MAC_ADDR to the
pf to set the macvlan mac address.

The discrepancy here is in the handlers.  The handler function for
IXGBE_VF_SET_MAC_ADDR (ixgbe_set_vf_mac_addr) has a check for
the vfinfo[].trusted bit to allow the operation if the vf is trusted.
In comparison, the IXGBE_VF_SET_MACVLAN message handler
(ixgbe_set_vf_macvlan_msg) has no such check of the trusted bit.
Signed-off-by: NKen Cox <jkc@redhat.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

When an interface is part of a namespace it is possible that
ixgbe_close() may be called while __ixgbe_shutdown() is running
which ends up in a double free WARN and/or a BUG in free_msi_irqs().

To handle this situation we extend the rtnl_lock() to protect the
call to netif_device_detach() and ixgbe_clear_interrupt_scheme()
in __ixgbe_shutdown() and check for netif_device_present()
to avoid clearing the interrupts second time in ixgbe_close();

Also extend the rtnl lock in ixgbe_resume() to netif_device_attach().
Signed-off-by: NEmil Tantilov <emil.s.tantilov@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

BaseT adapters that are capable of supporting 100Mb are not reporting this
capability.  This patch corrects the reporting so that 100Mb is shown as
supported on those adapters.
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>

A retry count of 10 is likely to run into problems on X550 devices that
have to detect and reset unresponsive CS4227 devices. So, reduce the I2C
retry count to 3 for X550 and above. This should avoid any possible
regressions in existing devices.
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>

This is an extension of commit 003287e0 ("ixgbevf: Correct parameter
sent to LED function"); add bounds checking to x540 functions to ensure the
index is valid.
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>

The indirection table was reported incorrectly for X550 and newer
where we can support up to 64 RSS queues.

Reported-by Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: NEmil Tantilov <emil.s.tantilov@intel.com>
Tested-by: NAndrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The generic PHY reset check we had previously is not sufficient for the
ixgbe_phy_x550em_ext_t PHY type.  Check 1.CC02.0 instead - same as
ixgbe_init_ext_t_x550().
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>

Some x550 devices require the driver version reported to its firmware; this
patch sends the driver version string to the firmware through the host
interface command for x550 devices.
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>

FEC is configured by the NVM and the driver should not be
overriding it.
Signed-off-by: NEmil Tantilov <emil.s.tantilov@intel.com>
Tested-by: NKrishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

There is no point in having an extra type for extra confusion. u64 is
unambiguous.

Conversion was done with the following coccinelle script:

@rem@
@@
-typedef u64 cycle_t;

@fix@
typedef cycle_t;
@@
-cycle_t
+u64
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: John Stultz <john.stultz@linaro.org>

In the case of IPIP and SIT tunnel frames the outer transport header
offset is actually set to the same offset as the inner transport header.
This results in the lco_csum call not doing any checksum computation over
the inner IPv4/v6 header data.

In order to account for that I am updating the code so that we determine
the location to start the checksum ourselves based on the location of the
IPv4 header and the length.

Fixes: b83e3010 ("ixgbe/ixgbevf: Add support for GSO partial")
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For some Tx paths (e.g., tpacket_snd()), ixgbe_atr may be
passed down an sk_buff that has the network and transport
header in the paged data, so it needs to make sure these
headers are available in the headlen bytes to calculate the
l4_proto.

This patch expect that network and transport headers are
already available in the non-paged header dat.  The assumption
is that the caller has set this up if l4_proto based Tx
steering is desired.
Signed-off-by: NSowmini Varadhan <sowmini.varadhan@oracle.com>
Reviewed-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NKrishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Commit 9f12df90 ("ixgbe: Store VXLAN port number in network order")
incorrectly checks for hdr.ipv4->protocol != IPPROTO_UDP
in ixgbe_atr(). This check should be for "==" instead.
Signed-off-by: NSowmini Varadhan <sowmini.varadhan@oracle.com>
Reviewed-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Tested-by: NKrishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

We were using an old Alpha version of the X550 phy ID.  This was leading
to unnecessary queries of the PHY.  I removed the old ID (which shouldn't
be on any HW) and add the two that are.
Signed-off-by: NDon Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch add X553 FW ALEF support for B0.  ALEF is the new unified
FW.  This contains updated register defines for ALEF speed
configuration.  Likewise it also removes the AN_CNTL_8 usage from
the native SFI flow as it is no longer supported by FW.
Signed-off-by: NDon Skidmore <donald.c.skidmore@intel.com>
Tested-by: NKrishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Fix an issue where set_phy_power was NULL for X550 copper devices
because get_invariants was called before hw->device_id was set.
Signed-off-by: NEmil Tantilov <emil.s.tantilov@intel.com>
Tested-by: NKrishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>