DSA stacks an Ethernet device on top of an Ethernet device. This can
cause false positive lockdep splats for the transmit queue:
Acked-by: Florian Fainelli <f.fainelli@gmail.com>

=============================================
[ INFO: possible recursive locking detected ]
4.0.0-rc7-01838-g70621a215fc7 #386 Not tainted
---------------------------------------------
kworker/0:0/4 is trying to acquire lock:
 (_xmit_ETHER#2){+.-...}, at: [<c040e95c>] sch_direct_xmit+0xa8/0x1fc

but task is already holding lock:
 (_xmit_ETHER#2){+.-...}, at: [<c03f4208>] __dev_queue_xmit+0x4d4/0x56c

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(_xmit_ETHER#2);
  lock(_xmit_ETHER#2);

To avoid this, walk the tq queues of the dsa slaves and set a lockdep
class.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

DSA can have nested MDIO busses, where the Ethernet MDIO bus is used
to access an MDIO bus within the switch which has the PHYs connected
to it. This nesting causes lockdep to give false positives. Use
mutex_lock_nested() to avoid this.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

The SMI bus is the bottleneck in all switch operations, not the
granularity of locks. Replace the stats mutex by the SMI mutex to make
the locking concept simpler.

The REG_READ/REG_WRITE macros cannot be used while holding the SMI
mutex, since they try to acquire it. Replace with calls to the
appropriate function which does not try to get the mutex.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

The SMI bus is the bottleneck in all switch operations, not the
granularity of locks. Replace the PHY mutex by the SMI mutex to make
the locking concept simpler.

The REG_READ/REG_WRITE macros cannot be used while holding the SMI
mutex, since they try to acquire it. Replace with calls to the
appropriate function which does not try to get the mutex.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

The mv88e6185 is part of the family that the mv88e6131 driver
supports. Add it to the probe function, and set the number of ports.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

The 6171 is one member of the family 6171/6175/6350/6351. Add the
other family members to the driver.

Not tested on these new devices.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

The mv88e6172 is part of the mv88e6352 family of devices. Move support
for it out of the mv88e6171 driver into the mv88e6352, which results
in some simplifications to the code.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

Use defines for registers, shifts and bits in the remaining register
accesses in the individual drivers, in order to aid readability.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

Now that setting up a port is identical for all switches, centralisers
the code looping over all the ports to set them up.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

The port setup code in the individual drivers is identical for 6123,
6171, and 6352, and very similar in 6131. Move it all into mv88e6xxx,
using the chip families to differentiate on features.

Similarly, the global setup is also very similar. Move the majority
into mv8e6xxx.

The chips themselves fall into families. Add helpers which uses the
device IDs to determine if a device is a member of a family or not.
Add some additional device IDs to the existing list, to make these
helper functions more complete. However these IDs are not yet added to
the probe functions.
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

VXLAN must provide the skb mark and specifiy IPPROTO_UDP when doing
the FIB lookup for the remote ip. Otherwise an invalid route might
be returned.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch remove kernel-doc warnings.
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Synchronize names with other drivers.
Signed-off-by: Srikanth Thokala <sthokal@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Use of_property_* calls
Signed-off-by: Srikanth Thokala <sthokal@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

use devm_* calls
Signed-off-by: Srikanth Thokala <sthokal@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Synchronize names with other drivers
Signed-off-by: Srikanth Thokala <sthokal@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

There is rule for network drivers with comments blocks
which is newly checked by checkpatch.pl script.
Let's fix it.
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Removed checkpatch.pl errors and warnings.
Signed-off-by: Srikanth Thokala <sthokal@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds proper checks to handle the PHY-less case.
Signed-off-by: Srikanth Thokala <sthokal@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In the current implementation, jumbo frames are supported only
for the frame sizes > 16K. This patch corrects this logic to
handle jumbo frames for lesser frame sizes (< 16K) ensuring jumbo frame
MTU is within the limit of max frame size configured in the h/w
design.
Signed-off-by: Srikanth Thokala <sthokal@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The packet completion interrupts for TX and RX should be serviced before
the packets are consumed. This ensures against the degenerate case when a
new completion interrupt is raised after the handler has exited but before
the interrupts are cleared. In this case its possible for the ISR to clear
an unhandled interrupt (leading to potential deadlock).
Signed-off-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Tested-by: Jason Wu <huanyu@xilinx.com>
Acked-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The AXI-DMA rx-delay interrupt can sometimes be triggered
when there are 0 outstanding packets received. This is due
to the fact that the receive function will greedily consume
as many packets as possible on interrupt. So if two packets
(with a very particular timing) arrive in succession they
will each cause the rx-delay interrupt, but the first interrupt
will consume both packets.
This means the second interrupt is a 0 packet receive.

This is mostly OK, except that the tail pointer register is
updated unconditionally on receive. Currently the tail pointer
is always set to the current bd-ring descriptor under
the assumption that the hardware has moved onto the next
descriptor. What this means for length 0 recv is the current
descriptor that the hardware is potentially yet to use will
be marked as the tail. This causes the hardware to think
its run out of descriptors deadlocking the whole rx path.

Fixed by updating the tail pointer to the most recent
successfully consumed descriptor.
Reported-by: Wendy Liang <wendy.liang@xilinx.com>
Signed-off-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Tested-by: Jason Wu <huanyu@xilinx.com>
Acked-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds support for the RGMII. The h/w configuration
parameter C_PHY_TYPE, which represents the interface configured in
the design, is used to differentiate various interfaces supported
by AXI Ethernet.
Signed-off-by: Srikanth Thokala <sthokal@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Hariprasad Shenai says:

====================
Trivial fixes and changes for SGE

This patch series adds the following.
Discard packet if length is greater than MTU, move sge monitor code to a
new routine, add device node to ULD info, add congestion notification from
SGE for ingress queue and freelists and for T5, setting up the Congestion
Manager values of the new RX Ethernet Queue is done by firmware now.

This patch series has been created against net-next tree and includes
patches on cxgb4 driver.

We have included all the maintainers of respective drivers. Kindly review
the change and let us know in case of any review comments.

Thanks

V2: Align parenthesis for PATCH 2/6 and PATCH 5/6
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

pktgen sends raw udp packets and bypasses most of the
linux networking stack. User can specify different packet sizes.
Hence we need to discard the packet if the length is greater than mtu
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Adds device node to ULD info. Use the node info to alloc_ring() for ctrl
TX queues
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Passes a Congestion Channel Map to t4_sge_alloc_rxq()
for the Ethernet RX Queues based on the MPS Buffer Group Map
of the TX Channel rather than just the TX Channel Map.
Also, in t4_sge_alloc_rxq() for T5, setting up the
Congestion Manager values of the new RX Ethernet Queue is
done by firmware now.
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Also changed the name of t4_hw.c:get_mps_bg_map() to t4_get_mps_bg_map()
and make it an exported routine with a definition in cxgb4.h.
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

We need to make sure that the Free List Size, in pointers, is at
least 2 Egress Queue Units (8 pointers/each) larger than the SGE's Egress
Congestion Threshold (in pointers).
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

A 64bit division went in unnoticed. Use do_div() to accomodate
non 64bit architectures.

Reported-by: kbuild test robot
Fixes: 1aa661f5 ("rhashtable-test: Measure time to insert, remove & traverse entries")
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>

Remove useless obj variable and goto logic.
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

Mahesh Bandewar says:

====================
Multicast processing in IPvlan

Dan Willems pointed out that autoconf in IPvlan is broken because of the
way broadcast bit gets set. Since broadcast processing is a real performance
drain, the broadcast bit in multicast filter was only set when the interface
was configured with IPv4 address. In autoconf scenario, when there are
no addresses configured; this logic did not work and it wouldn't allow
DHCPv4 to work. The only way was to add protocol specific hacks to avoid
processing unnecessary broadcast burdon.

This jugglery could be avoided if these multicast / broadcast packets are taken
out of fast-path and are processed in a work-queue. This will enable us to add
broadcast bit in all multicast filters without any impact on performance of
the virtual device. This patch series just does that.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Earlier tricks of setting broadcast bit only when IPv4 address is added
onto interface are not good enough especially when autoconf comes in play.
Setting them on always is performance drag but now that multicast /
broadcast is not processed in fast-path; enabling broadcast will let
autoconf work correctly without affecting performance characteristics of
the device.
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Processing multicast / broadcast in fast path is performance draining
and having more links means more cloning and bringing performance
down further.

Broadcast; in particular, need to be given to all the virtual links.
Earlier tricks of enabling broadcast bit for IPv4 only interfaces are not
really working since it fails autoconf. Which means enabling broadcast
for all the links if protocol specific hacks do not have to be added into
the driver.

This patch defers all (incoming as well as outgoing) multicast traffic to
a work-queue leaving only the unicast traffic in the fast-path. Now if we
need to apply any additional tricks to further reduce the impact of this
(multicast / broadcast) type of traffic, it can be implemented while
processing this work without affecting the fast-path.
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Alexander Duyck says:

====================
Add eth_proto_is_802_3 to provide improved means of checking Ethertype

This patch series implements and makes use of eth_proto_is_802_3().  The
idea behind the function is to provide an optimized means of testing to
determine if a given Ethertype value is a length or 802.3 protocol number.
The standard path for this was to use ntohs(proto) and then perform a
comparison.  This adds a slight cost as it usually requires either a 16b
rotate or byte swap which can cost 1 cycle or more depending on the
processor.

I had previously addressed this for eth_type_trans, however in doing so I had
overlooked checking with sparse and had introduced a couple sparse warnings.
The first patch in this series fixes those sparse warnings as well as does
some additional optimization for big endian systems.  In addition it pushes
the code out into a separate function which can then be used in the other
patches to reduce the instruction count/processing time in those functions
as well.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Replace "ntohs(proto) >= ETH_P_802_3_MIN" w/ eth_proto_is_802_3(proto).
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Replace "ntohs(proto) >= ETH_P_802_3_MIN" w/ eth_proto_is_802_3(proto).
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Replace "ntohs(proto) >= ETH_P_802_3_MIN" w/ eth_proto_is_802_3(proto).
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Replace "ntohs(proto) >= ETH_P_802_3_MIN" w/ eth_proto_is_802_3(proto).
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>