Tests showed that when whole bandwidth is consumed, the latency for
various kind of traffic can reach high values. With saturated
link (e.g. with iperf from target to host) simple ping could take
significant amount of time. BQL proved to improve this situation
when implemented in mvneta driver. Measurements of ping latency
for 3 link speeds:
Speed | Latency w/o BQL | Latency with BQL
10    |      7-14 ms    |     3.5 ms
100   |      2-12 ms    |     0.6 ms
1000  |   often timeout |   up to 2ms

Decreasing latency as above result in sligt performance cost - 4kpps
(-1.4%) when pushing 64B packets via two bridged interfaces of Armada 38x.
For 1500B packets in the same setup, the mpstat tool showed +8% of
CPU occupation (default affinity, second CPU idle). Even though this
cost seems reasonable to take, considering other improvements.

This commit adds byte queue limit mechanism for the mvneta driver.
Signed-off-by: NMarcin Wojtas <mw@semihalf.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Basing on xmit_more flag of the skb, TX descriptors can be concatenated
before flushing. This commit delay Tx descriptor flush if the queue is
running and if there is more skb's to send.

A maximum allowed number of descriptors for flushing at once due to
MVNETA_TXQ_UPDATE_REG(q) reqisters limitation, is 255. Because of that
a new macro was added (MVNETA_TXQ_DEC_SENT_MASK) in order to ensure that
concatenated amount of descriptor does not exceed that value.
Signed-off-by: NSimon Guinot <simon.guinot@sequanux.org>
Signed-off-by: NMarcin Wojtas <mw@semihalf.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>

ktime_set(S,N) was required for the timespec storage type and is still
useful for situations where a Seconds and Nanoseconds part of a time value
needs to be converted. For anything where the Seconds argument is 0, this
is pointless and can be replaced with a simple assignment.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>

Since commit 71ce391d ("net: mvpp2: enable proper per-CPU TX
buffers unmapping"), we are not correctly DMA unmapping TX buffers for
fragments.

Indeed, the mvpp2_txq_inc_put() function only stores in the
txq_cpu->tx_buffs[] array the physical address of the buffer to be
DMA-unmapped when skb != NULL. In addition, when DMA-unmapping, we use
skb_headlen(skb) to get the size to be unmapped. Both of this works fine
for TX descriptors that are associated directly to a SKB, but not the
ones that are used for fragments, with a NULL pointer as skb:

 - We have a NULL physical address when calling DMA unmap
 - skb_headlen(skb) crashes because skb is NULL

This causes random crashes when fragments are used.

To solve this problem, we need to:

 - Store the physical address of the buffer to be unmapped
   unconditionally, regardless of whether it is tied to a SKB or not.

 - Store the length of the buffer to be unmapped, which requires a new
   field.

Instead of adding a third array to store the length of the buffer to be
unmapped, and as suggested by David Miller, this commit refactors the
tx_buffs[] and tx_skb[] arrays of 'struct mvpp2_txq_pcpu' into a
separate structure 'mvpp2_txq_pcpu_buf', to which a 'size' field is
added. Therefore, instead of having three arrays to allocate/free, we
have a single one, which also improve data locality, reducing the
impact on the CPU cache.

Fixes: 71ce391d ("net: mvpp2: enable proper per-CPU TX buffers unmapping")
Reported-by: NRaphael G <raphael.glon@corp.ovh.com>
Cc: Raphael G <raphael.glon@corp.ovh.com>
Cc: stable@vger.kernel.org
Signed-off-by: NThomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The build of sparc allmodconfig fails with the error:
"of_irq_to_resource" [drivers/net/ethernet/marvell/mv643xx_eth.ko]
	undefined!

of_irq_to_resource() is defined when CONFIG_OF_IRQ is defined. And also
CONFIG_OF_IRQ can only be defined if CONFIG_IRQ is defined. So we can
safely use #if defined(CONFIG_OF_IRQ) in the code.
Signed-off-by: NSudip Mukherjee <sudip.mukherjee@codethink.co.uk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We previously relied on GENERIC_ALLOCATOR to be selected by CONFIG_ARM,
but now we can compile-test the driver on other architectures that
don't select it:

drivers/net/built-in.o: In function `mvneta_bm_remove':
mvneta_bm.c:(.text+0x4ee35): undefined reference to `gen_pool_free'

This adds an explicit select for the part of the driver that has
the dependency.

Fixes: a0627f77 ("net: marvell: Allow drivers to be built with COMPILE_TEST")
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

These two statements were not indented correctly so it's sort of
confusing.
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Armada 3700 is a new ARMv8 SoC from Marvell using same network controller
as older Armada 370/38x/XP. There are however some differences that
needed taking into account when adding support for it:

* open default MBUS window to 4GB of DRAM - Armada 3700 SoC's Mbus
  configuration for network controller has to be done on two levels:
  global and per-port. The first one is inherited from the
  bootloader. The latter can be opened in a default way, leaving
  arbitration to the bus controller.  Hence filled mbus_dram_target_info
  structure is not needed

* make per-CPU operation optional - Recent patches adding RSS and XPS
  support for Armada 38x/XP enabled per-CPU operation of the controller
  by default. Contrary to older SoC's Armada 3700 SoC's network
  controller is not capable of per-CPU processing due to interrupt lines'
  connectivity.  This patch restores non-per-CPU operation, which is now
  optional and depends on neta_armada3700 flag value in mvneta_port
  structure. In order not to complicate the code, separate interrupt
  subroutine is implemented.

For now, on the Armada 3700, RSS is disabled as the current
implementation depend on the per cpu interrupts.

[gregory.clement@free-electrons.com: extract from a larger patch, replace
some ifdef and port to net-next for v4.10]
Signed-off-by: NMarcin Wojtas <mw@semihalf.com>
Signed-off-by: NGregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: NMarcin Wojtas <mw@semihalf.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Actually only the mvneta_bm support is not 64-bits compatible.
The mvneta code itself can run on 64-bits architecture.
Signed-off-by: NGregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: NMarcin Wojtas <mw@semihalf.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Prepare the mvneta driver in order to be usable on the 64 bits platform
such as the Armada 3700.

[gregory.clement@free-electrons.com]: this patch was extract from a larger
one to ease review and maintenance.
Signed-off-by: NMarcin Wojtas <mw@semihalf.com>
Signed-off-by: NGregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: NMarcin Wojtas <mw@semihalf.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Until now the virtual address of the received buffer were stored in the
cookie field of the rx descriptor. However, this field is 32-bits only
which prevents to use the driver on a 64-bits architecture.

With this patch the virtual address is stored in an array not shared with
the hardware (no more need to use the DMA API). Thanks to this, it is
possible to use cache contrary to the access of the rx descriptor member.

The change is done in the swbm path only because the hwbm uses the cookie
field, this also means that currently the hwbm is not usable in 64-bits.
Signed-off-by: NGregory CLEMENT <gregory.clement@free-electrons.com>
Reviewed-by: NJisheng Zhang <jszhang@marvell.com>
Tested-by: NMarcin Wojtas <mw@semihalf.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For HWBM all buffers are allocated in mvneta_bm_construct() and in runtime
they are put into descriptors by hardware. There is no need to fill them
at this point.
Suggested-by: NMarcin Wojtas <mw@semihalf.com>
Signed-off-by: NGregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: NMarcin Wojtas <mw@semihalf.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

For small frame reuse the phys_addr variable instead of accessing the
uncacheable value in the rx descriptor.
Signed-off-by: NGregory CLEMENT <gregory.clement@free-electrons.com>
Tested-by: NMarcin Wojtas <mw@semihalf.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Make sure to deregister and free any fixed-link PHY registered using
of_phy_register_fixed_link() on probe errors and on driver unbind.

Fixes: 83895bed ("net: mvneta: add support for fixed links")
Signed-off-by: NJohan Hovold <johan@kernel.org>
Reviewed-by: NThomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

gcc-7 detects a short memset in mvpp2, introduced in the original
merge of the driver:

drivers/net/ethernet/marvell/mvpp2.c: In function 'mvpp2_cls_init':
drivers/net/ethernet/marvell/mvpp2.c:3296:2: error: 'memset' used with length equal to number of elements without multiplication by element size [-Werror=memset-elt-size]

The result seems to be that we write uninitialized data into the
flow table registers, although we did not get any warning about
that uninitialized data usage.

Using sizeof() lets us initialize then entire array instead.

Fixes: 3f518509 ("ethernet: Add new driver for Marvell Armada 375 network unit")
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The mvneta driver advertises it supports IFF_UNICAST_FLT. However, it
actually does not. The hardware probably does support it, but there is
no code to configure the filter. As a quick and simple fix, remove the
flag. This will cause the core to fall back to promiscuous mode.
Signed-off-by: NAndrew Lunn <andrew@lunn.ch>
Fixes: b50b72de ("net: mvneta: enable features before registering the driver")
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Both of these drivers won't work on 64-bit architectures unless they
are redesigned, since they store a virtual address pointer in a 32-bit
field of the descriptors:

drivers/net/ethernet/marvell/mvneta_bm.c: In function 'mvneta_bm_construct':
drivers/net/ethernet/marvell/mvneta_bm.c:103:16: error: cast from pointer to integer of different size [-Werror=pointer-to-int-cast]
drivers/net/ethernet/marvell/mvpp2.c: In function 'mvpp2_prs_vlan_init':
drivers/net/ethernet/marvell/mvpp2.c:2563:32: error: large integer implicitly truncated to unsigned type [-Werror=overflow]

This limits the COMPILE_TEST option for the two drivers again to
only build them on 32-bit. This seems nicer than shutting up the
warnings, in case we ever actually want to use them on 64-bit,
as the warnings indicate which parts of the driver are currently
broken there.

Fixes: a0627f77 ("net: marvell: Allow drivers to be built with COMPILE_TEST")
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

All Marvell Ethernet drivers actually build fine with COMPILE_TEST with
a few warnings. We need to add a few HAS_DMA dependencies to fix linking
failures on problematic architectures like m32r.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The sky2 frequently crashes during machine shutdown with:

sky2_get_stats+0x60/0x3d8 [sky2]
dev_get_stats+0x68/0xd8
rtnl_fill_stats+0x54/0x140
rtnl_fill_ifinfo+0x46c/0xc68
rtmsg_ifinfo_build_skb+0x7c/0xf0
rtmsg_ifinfo.part.22+0x3c/0x70
rtmsg_ifinfo+0x50/0x5c
netdev_state_change+0x4c/0x58
linkwatch_do_dev+0x50/0x88
__linkwatch_run_queue+0x104/0x1a4
linkwatch_event+0x30/0x3c
process_one_work+0x140/0x3e0
worker_thread+0x60/0x44c
kthread+0xdc/0xf0
ret_from_fork+0x10/0x50

This is caused by the sky2 being called after it has been shutdown.
A previous thread about this can be found here:

https://lkml.org/lkml/2016/4/12/410

An alternative fix is to assure that IFF_UP gets cleared by
calling dev_close() during shutdown. This is similar to what the
bnx2/tg3/xgene and maybe others are doing to assure that the driver
isn't being called following _shutdown().
Signed-off-by: NJeremy Linton <jeremy.linton@arm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Implement ethtool::nway_reset using phy_ethtool_nway_reset. We are
already using dev->phydev all over the place so this comes for free.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Implement ethtool::nway_reset using phy_ethtool_nway_reset. We are
already using dev->phydev all over the place so this comes for free.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Implement ethtool::nway_reset using phy_ethtool_nway_reset. We are
already using dev->phydev all over the place so this comes for free.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Reviewed-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The coalesce settings behave badly when changing just one value:

... # ethtool -c eth0
rx-usecs: 249
... # ethtool -C eth0 tx-usecs 250
... # ethtool -c eth0
rx-usecs: 248

This occurs due to rounding errors when calculating the microseconds
value - the divisons round down.  This causes (eg) the rx-usecs to
decrease by one every time the tx-usecs value is set as per the above.

Fix this by making the divison round-to-nearest.
Signed-off-by: NRussell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The second SET_NETDEV_DEV() in the hunk should be
removed.
Reported-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

One merge conflict block wasn't resolved.
Reported-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The MAC is capable of RGMII mode and that is probably a more typical
connection type than GMII today (eg it is used by Marvell Reference
designs for several SOCs). Let DT users specify the standard

   phy-connection-type = "rgmii-id";

On a phy node.
Signed-off-by: NJason Gunthorpe <jgunthorpe@obsidianresearch.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Somehow, I missed a healthy number of ethernet drivers in the last pass.
Most of these drivers either were in need of an updated max_mtu to make
jumbo frames possible to enable again. In a few cases, also setting a
different min_mtu to match previous lower bounds. There are also a few
drivers that had no upper bounds checking, so they're getting a brand new
ETH_MAX_MTU that is identical to IP_MAX_MTU, but accessible by includes
all ethernet and ethernet-like drivers all have already.

acenic:
- min_mtu = 0, max_mtu = 9000

amazon/ena:
- min_mtu = 128, max_mtu = adapter->max_mtu

amd/xgbe:
- min_mtu = 0, max_mtu = 9000

sb1250:
- min_mtu = 0, max_mtu = 1518

cxgb3:
- min_mtu = 81, max_mtu = 65535

cxgb4:
- min_mtu = 81, max_mtu = 9600

cxgb4vf:
- min_mtu = 81, max_mtu = 65535

benet:
- min_mtu = 256, max_mtu = 9000

ibmveth:
- min_mtu = 68, max_mtu = 65535

ibmvnic:
- min_mtu = adapter->min_mtu, max_mtu = adapter->max_mtu
- remove now redundant ibmvnic_change_mtu

jme:
- min_mtu = 1280, max_mtu = 9202

mv643xx_eth:
- min_mtu = 64, max_mtu = 9500

mlxsw:
- min_mtu = 0, max_mtu = 65535
- Basically bypassing the core checks, and instead relying on dynamic
  checks in the respective switch drivers' ndo_change_mtu functions

ns83820:
- min_mtu = 0
- remove redundant ns83820_change_mtu, only checked for mtu > 1500

netxen:
- min_mtu = 0, max_mtu = 8000 (P2), max_mtu = 9600 (P3)

qlge:
- min_mtu = 1500, max_mtu = 9000
- driver only supports setting mtu to 1500 or 9000, so the core check only
  rules out < 1500 and > 9000, qlge_change_mtu still needs to check that
  the value is 1500 or 9000

qualcomm/emac:
- min_mtu = 46, max_mtu = 9194

xilinx_axienet:
- min_mtu = 64, max_mtu = 9000

Fixes: 61e84623 ("net: centralize net_device min/max MTU checking")
CC: netdev@vger.kernel.org
CC: Jes Sorensen <jes@trained-monkey.org>
CC: Netanel Belgazal <netanel@annapurnalabs.com>
CC: Tom Lendacky <thomas.lendacky@amd.com>
CC: Santosh Raspatur <santosh@chelsio.com>
CC: Hariprasad S <hariprasad@chelsio.com>
CC: Sathya Perla <sathya.perla@broadcom.com>
CC: Ajit Khaparde <ajit.khaparde@broadcom.com>
CC: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
CC: Somnath Kotur <somnath.kotur@broadcom.com>
CC: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
CC: John Allen <jallen@linux.vnet.ibm.com>
CC: Guo-Fu Tseng <cooldavid@cooldavid.org>
CC: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
CC: Jiri Pirko <jiri@mellanox.com>
CC: Ido Schimmel <idosch@mellanox.com>
CC: Manish Chopra <manish.chopra@qlogic.com>
CC: Sony Chacko <sony.chacko@qlogic.com>
CC: Rajesh Borundia <rajesh.borundia@qlogic.com>
CC: Timur Tabi <timur@codeaurora.org>
CC: Anirudha Sarangi <anirudh@xilinx.com>
CC: John Linn <John.Linn@xilinx.com>
Signed-off-by: NJarod Wilson <jarod@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adding led support for phy causes namespace conflicts for some
phy drivers.

The marvel skge driver declared an enum for representing the states of
Link LED Register. The enum contained constant LED_OFF which conflicted
with declartation found in linux/leds.h.
LED_OFF changed to LED_REG_OFF
Also changed LED_ON to LED_REG_ON to avoid possible future conflict and
for consistency.
Signed-off-by: NZach Brown <zach.brown@ni.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

mvneta: min_mtu 68, max_mtu 9676
- mtu validation routine mostly did range check, merge back into
  mvneta_change_mtu for simplicity

mvpp2: min_mtu 68, max_mtu 9676
- mtu validation routine mostly did range check, merge back into
  mvpp2_change_mtu for simplicity

pxa168_eth: min_mtu 68, max_mtu 9500

skge: min_mtu 60, max_mtu 9000

sky2: min_mtu 68, max_mtu 1500 or 9000, depending on hw

CC: netdev@vger.kernel.org
CC: Mirko Lindner <mlindner@marvell.com>
CC: Stephen Hemminger <stephen@networkplumber.org>
CC: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: NJarod Wilson <jarod@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ethtool api {get|set}_settings is deprecated.
We move this driver to new api {get|set}_link_ksettings.
Signed-off-by: NPhilippe Reynes <tremyfr@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The private structure contain a pointer to phydev, but the structure
net_device already contain such pointer. So we can remove the pointer
phydev in the private structure, and update the driver to use the
one contained in struct net_device.
Signed-off-by: NPhilippe Reynes <tremyfr@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is no need to clk_disable_unprepare(dev->clk)
before it was initialized.

Found by Linux Driver Verification project (linuxtesting.org).
Signed-off-by: NAlexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We get 2 warnings when building kernel with W=1:
drivers/net/ethernet/marvell/mvneta.c:639:27: warning: no previous prototype for 'mvneta_get_stats64' [-Wmissing-prototypes]
drivers/net/ethernet/marvell/mvneta.c:3529:5: warning: no previous prototype for 'mvneta_ethtool_set_link_ksettings' [-Wmissing-prototypes]

In fact, these two functions are only used in the file in which they are
declared and don't need a declaration, but can be made static.
so this patch marks these functions with 'static'.
Signed-off-by: NBaoyou Xie <baoyou.xie@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either
built-in or as a module, use that macro instead of open coding the same.

Using the macro makes the code more readable by helping abstract away some
of the Kconfig built-in and module enable details.
Signed-off-by: NJavier Martinez Canillas <javier@osg.samsung.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Install the callbacks via the state machine and let the core invoke
the callbacks on the already online CPUs.
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: netdev@vger.kernel.org
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20160818125731.27256-9-bigeasy@linutronix.deSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

Update the sky2 driver to pass number of packets done to NAPI.
The driver was never updated when napi_complete_done was added.
Signed-off-by: NStephen Hemminger <stephen@networkplumber.org>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ethtool api {get|set}_settings is deprecated.
We move the mvneta driver to new api {get|set}_link_ksettings.

We use the generic function phy_ethtool_get_link_ksettings,
and update old mvneta_ethtool_set_settings to the new api.
Signed-off-by: NPhilippe Reynes <tremyfr@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The private structure contain a pointer to phydev, but the structure
net_device already contain such pointer. So we can remove the pointer
phy_dev in the private structure, and update the driver to use the
one contained in struct net_device.
Signed-off-by: NPhilippe Reynes <tremyfr@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>