Add ethtool statistics for case where send chimmeny buffer is
exhausted and driver has to fall back to doing scatter/gather
send. Also, add statistic for case where ring buffer is full and
receive completions are delayed.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Control the size of the buffer areas via ethtool ring settings.
They aren't really traditional hardware rings, but host API breaks
receive and send buffer into chunks. The final size of the chunks are
controlled by the host.

The default value of send and receive buffer area for host DMA
is much larger than it needs to be. Experimentation shows that
4M receive and 1M send is sufficient.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When VF device is discovered, delay bring it automatically up in
order to allow userspace to some simple changes (like renaming).
Reported-by: NVitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Go back to switching datapath directly in the notifier callback.
Otherwise datapath might not get switched on unregister.

No need for calling the NOTIFY_PEERS notifier since that is only for
a gratitious ARP/ND packet; but that is not required with Hyper-V
because both VF and synthetic NIC have the same MAC address.
Reported-by: NVitaly Kuznetsov <vkuznets@redhat.com>
Fixes: 0c195567 ("netvsc: transparent VF management")
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The existing sub channel code did not wait for all the sub-channels
to completely initialize. This could lead to race causing crash
in napi_netif_del() from bad list. The existing code would send
an init message, then wait only for the initial response that
the init message was received. It thought it was waiting for
sub channels but really the init response did the wakeup.

The new code keeps track of the number of open channels and
waits until that many are open.

Other issues here were:
  * host might return less sub-channels than was requested.
  * the new init status is not valid until after init was completed.

Fixes: b3e6b82a ("hv_netvsc: Wait for sub-channels to be processed during probe")
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch implements transparent fail over from synthetic NIC to
SR-IOV virtual function NIC in Hyper-V environment. It is a better
alternative to using bonding as is done now. Instead, the receive and
transmit fail over is done internally inside the driver.

Using bonding driver has lots of issues because it depends on the
script being run early enough in the boot process and with sufficient
information to make the association. This patch moves all that
functionality into the kernel.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Optimize how receive completion ring are managed.
   * Allocate only as many slots as needed for all buffers from host
   * Allocate before setting up sub channel for better error detection
   * Don't need to keep copy of initial receive section message
   * Precompute the watermark for when receive flushing is needed
   * Replace division with conditional test
   * Replace atomic per-device variable with per-channel check.
   * Handle corner case where receive completion send
     fails if ring buffer to host is full.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The internal API was passing struct hv_page_buffer **
when only simple struct hv_page_buffer * was necessary
for passing an array.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This includes a bunch of fixups for issues reported by
lockdep.
   * ethtool routines can assume RTNL
   * send is done with RCU lock (and BH disable)
   * avoid refetching internal device struct (netvsc)
     instead pass it as a parameter.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This value has been calculated in rndis_device_attach since 4.11.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The rndis functions are used when changing device state.
Therefore the references from network device to internal state
are protected by RTNL mutex.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Keep back pointer in the per-channel data structure to
avoid any possible RCU related issues when napi poll is
called but netvsc_device is in RCU limbo.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The netvsc_device structure should be accessed by rcu_dereference
in the send path.  Change arguments to netvsc_send() to make
this easier to do correctly.

Remove no longer needed hv_device_to_netvsc_device.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The rndis_filter_device_add function is called both in
probe context and RTNL context,and creates the netvsc_device
inner structure. It is easier to get the RTNL lock annotation
correct if it returns the object directly, rather than implicitly
by updating network device private data.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use device detach/attach to ensure that no packets are handed
to device during state changes. Call rndis_filter_open/close
directly as part of later VF related changes.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When the VF NIC is opened, the synthetic NIC's carrier state is set to
off. This tells the host to transitions data path to the VF device. But
if startup script or user manipulates the admin state of the netvsc
device directly for example:
        # ifconfig eth0 down
	# ifconfig eth0 up
Then the carrier state of the synthetic NIC would be on, even though the
data path was still over the VF NIC. This patch sets the carrier state
of synthetic NIC with consideration of the related VF state.
Signed-off-by: NHaiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We simply use rndis_device->link_state in the netdev_dbg. The variable,
link_state from struct netvsc_device_info, is not used anywhere else.
Signed-off-by: NHaiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The element netvsc_device:extension is always a pointer to RNDIS
information.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The work queue and handling of network filter parameters should
be in rndis_device. This gets rid of warning from RCU checks,
eliminates a race and cleans up code.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

My change (introduced in 4.11) to use find_first_clear_bit
incorrectly assumed that the size argument was words, not bits.
The effect was only a small limited number of the available send
sections were being actually used. This can cause performance loss
with some workloads.

Since map_words is now used only during initialization, it can
be on stack instead of in per-device data.

Fixes: b58a1858 ("netvsc: simplify get next send section")
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If the outgoing skb has a RX queue mapping available, we use the queue
number directly, other than put it through Send Indirection Table.
Signed-off-by: NHaiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Rather than a lock and variable, use a refcount_t to keep track
of the number of sub channels.  Don't need to wait for subchannels
on device removal since wait was already done in device_add.

Also fix the error handling; don't wait forever in case of
an error on request to create sub channels.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is cleaner to use RCU protected pointer (nvdev_ctx->nvdev)
to indicate device is in removed state, rather than having a separate
boolean flag. By using the pointer the context can be checked
by static checkers and dynamic lockdep.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The netvsc driver has an internal structure (netvsc_device) which
is created when device is opened and released when device is closed.
And also opened/released when MTU or number of channels change.

Since this is referenced in the receive and transmit path, it is
safer to use RCU to protect/prevent use after free problems.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When using NAPI, the single stream performance declined signifcantly
because the poll routine was updating host after every burst
of packets. This excess signalling caused host throttling.

This fix restores the old behavior. Host is only signalled
after the ring has been emptied.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Not used anywhere.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Move the send indirection table from the inner device (netvsc)
to the network device context.

It is possible that netvsc_device is not present (remove in progress).
This solves potential use after free issues when packet is being
created during MTU change, shutdown, or queue count changes.

Fixes: d8e18ee0 ("netvsc: enhance transmit select_queue")
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use NAPI (softirq), to handle receive packets and send completions.
Previously this was handled by tasklet.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Report packets and bytes transferred through a vmbus channel via ethtool.
This supersedes need for per-cpu statistics.

Example:
$ ethtool -S eth0
NIC statistics:
...
     tx_queue_0_packets: 3523179
     tx_queue_0_bytes: 505370920
     rx_queue_0_packets: 41430490
     rx_queue_0_bytes: 62714661254
     tx_queue_1_packets: 0
     tx_queue_1_bytes: 0
     rx_queue_1_packets: 0
     rx_queue_1_bytes: 0
...
Reviewed-by: NLong Li <longli@microsoft.com>
Reviewed-by: NK. Y. Srinivasan <kys@microsoft.com>
Reviewed-by: NHaiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: NSimon Xiao <sixiao@microsoft.com>
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Most drivers do not increment transmit statistics until after the
transmit is completed. This will also be necessary for BQL support.

Slight additional complexity because the netvsc driver aggregates
multiple packets into one transmit.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since now keep track of per-queue outstanding sends, we can avoid
one atomic update by removing no longer needed per-device atomic.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

All caller's already have pointer to netvsc_device so pass it.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

All the caller's/callee's know that the format of the device_add
parameter is a netvsc_device_info struct.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Do manual optimizations of receive path:
  - remove checks for impossible conditions (but keep checks
    for bad data from host)
  - pass argument down, rather than having callee recompute what
    is already known
  - remove indirection about receive buffer datalength
  - remove dependence on VLAN_TAG_PRESENCE
  - use _hot/_cold and likely/unlikely
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Put all the per-channel state together in one data struct.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Allow setting receive indirection table. Also uses the system standard
for initialization.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This allows for number of channels to be managed in a manner similar
to existing hardware drivers. It also removes the restriction of
maximum 8 channels and allows as many as the host will allow.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For some cases it is useful to be able to change RSS key value.
For example, replacing RSS key with a symmetric hash.
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Redo how Hyper-V network driver negotiates offload features. Query the
host to determine offload settings, and use the result.

Also:
  * disable IPv4 header checksum offload (not used by Linux)
  * enable TSO only if host supports
  * enable UDP checksum offload if supported
  * don't advertise support for checksumming of non-IP protocols
  * adjust GSO maximum segment size
  * enable HIGHDMA
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ring buffer mapping now handles the wraparound case
inside get_next_pkt_raw. Therefore it is not necessary to have an
additional special receive staging buffer.

See commit 1562edaed8c164ca5199 ("Drivers: hv: ring_buffer: count on
wrap around mappings")
Signed-off-by: NStephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>