The IRQ code already has support for lockdep class for the lock mutex
in an interrupt descriptor. Extend this to add a second class for the
request mutex in the descriptor. Not having a class is resulting in
false positive splats in some code paths.
Signed-off-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: linus.walleij@linaro.org
Cc: grygorii.strashko@ti.com
Cc: f.fainelli@gmail.com
Link: https://lkml.kernel.org/r/1512234664-21555-1-git-send-email-andrew@lunn.ch

If the thermal subsystem returne -EPROBE_DEFER or any other error
when hwmon calls devm_thermal_zone_of_sensor_register(), this is
silently ignored.

I ran into this with an incorrectly defined thermal zone, making
it non-existing and thus this call failed with -EPROBE_DEFER
assuming it would appear later. The sensor was still added
which is incorrect: sensors must strictly be added after the
thermal zones, so deferred probe must be respected.

Fixes: d560168b ("hwmon: (core) New hwmon registration API")
Signed-off-by: NLinus Walleij <linus.walleij@linaro.org>
Signed-off-by: NGuenter Roeck <linux@roeck-us.net>

Following commit 9427ecbe ("gpio: Rework of_gpiochip_set_names()
to use device property accessors"), "gpio-line-names" DT property is
not retrieved anymore when chip->parent is not set by the driver.
This is due to OF based property reads having been replaced by device
based property reads.

This patch fixes that by making use of
fwnode_property_read_string_array() instead of
device_property_read_string_array() and handing over either
of_fwnode_handle(chip->of_node) or dev_fwnode(chip->parent)
to that function.

Fixes: 9427ecbe ("gpio: Rework of_gpiochip_set_names() to use device property accessors")
Cc: stable@vger.kernel.org
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Acked-by: NMika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: NLinus Walleij <linus.walleij@linaro.org>

Revert changes introduced by commit f0fbe7bc ("gpio: Move irqdomain
into struct gpio_irq_chip") as they are not aplicable to this driver.
Reported-by: NRussell King - ARM Linux <linux@armlinux.org.uk>
Fixes: f0fbe7bc ("gpio: Move irqdomain into struct gpio_irq_chip")
Signed-off-by: NGrygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: NLinus Walleij <linus.walleij@linaro.org>

The vk cts test:
dEQP-VK.api.external.semaphore.opaque_fd.export_multiple_times_temporary

triggers a lot of
VFS: Close: file count is 0

Dave pointed out that clearing the syncobj->file from
drm_syncobj_file_release() was sufficient to silence the test, but that
opens a can of worm since we assumed that the syncobj->file was never
unset. Stop trying to reuse the same struct file for every fd pointing
to the drm_syncobj, and allocate one file for each fd instead.

v2: Fixup return handling of drm_syncobj_fd_to_handle
v2.1: [airlied: fix possible syncobj ref race]
Reported-by: NDave Airlie <airlied@redhat.com>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Tested-by: NDave Airlie <airlied@redhat.com>
Reviewed-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Due to a spec misinterpretation, the Linux implementation of the BTT log
area had different padding scheme from other implementations, such as
UEFI and NVML.

This fixes the padding scheme, and defaults to it for new BTT layouts.
We attempt to detect the padding scheme in use when probing for an
existing BTT. If we detect the older/incompatible scheme, we continue
using it.
Reported-by: NJuston Li <juston.li@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: <stable@vger.kernel.org>
Fixes: 5212e11f ("nd_btt: atomic sector updates")
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Recent updates to btt.h neglected to add corresponding kernel-doc lines
for new structure members. Add them.
Signed-off-by: NVishal Verma <vishal.l.verma@intel.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

Patch bd36d3ba fixed a deadlock in the
failure path of drm_lease_create. This made the partially initialized
lease object visible for a short window of time.

To avoid having the lessee state appear transiently, I've rearranged
the code so that the lessor fields are not filled in until the
parameters are all validated and the function will succeed.
Signed-off-by: NKeith Packard <keithp@keithp.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20171221065424.1304-1-keithp@keithp.com

Commit 966a9671 randomly added alignment to this structure, but
it's actually detrimental to performance of null_blk. Test case:

Running on both the home and remote node shows a ~5% degradation
in performance.

While in there, move blk_status_t to the hole after the integer tag
in the nullb_cmd structure. After this patch, we shrink the size
from 192 to 152 bytes.

Fixes: 966a9671 ("smp: Avoid using two cache lines for struct call_single_data")
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Make sure to check both return code fields before processing the
response. Otherwise we risk operating on invalid data.

Fixes: c9475369 ("s390/qeth: rework RX/TX checksum offload")
Signed-off-by: NJulian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit f5775e0b ("x86/xen: discard RAM regions above the maximum
reservation") left host memory not assigned to dom0 as available for
memory hotplug.

Unfortunately this also meant that those regions could be used by
others. Specifically, commit fa564ad9 ("x86/PCI: Enable a 64bit BAR
on AMD Family 15h (Models 00-1f, 30-3f, 60-7f)") may try to map those
addresses as MMIO.

To prevent this mark unallocated host memory as E820_TYPE_UNUSABLE (thus
effectively reverting f5775e0b) and keep track of that region as
a hostmem resource that can be used for the hotplug.
Signed-off-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: NJuergen Gross <jgross@suse.com>

After TC offloads were converted to callbacks we have no choice
but keep track of the offloaded filter in the driver.

The check for nn->dp.bpf_offload_xdp was a stop gap solution
to make sure failed TC offload won't disable XDP, it's no longer
necessary.  nfp_net_bpf_offload() will return -EBUSY on
TC vs XDP conflicts.

Fixes: 3f7889c4 ("net: sched: cls_bpf: call block callbacks for offload")
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

cls_bpf used to take care of tracking what offload state a filter
is in, i.e. it would track if offload request succeeded or not.
This information would then be used to issue correct requests to
the driver, e.g. requests for statistics only on offloaded filters,
removing only filters which were offloaded, using add instead of
replace if previous filter was not added etc.

This tracking of offload state no longer functions with the new
callback infrastructure.  There could be multiple entities trying
to offload the same filter.

Throw out all the tracking and corresponding commands and simply
pass to the drivers both old and new bpf program.  Drivers will
have to deal with offload state tracking by themselves.

Fixes: 3f7889c4 ("net: sched: cls_bpf: call block callbacks for offload")
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There are few reasons in mvneta_rx_swbm() function when received packet
is dropped. mvneta_rx_error() should be called only if error bit [16]
is set in rx descriptor.

[gregory.clement@free-electrons.com: add fixes tag]
Cc: stable@vger.kernel.org
Fixes: dc35a10f ("net: mvneta: bm: add support for hardware buffer management")
Signed-off-by: NYelena Krivosheev <yelena@marvell.com>
Tested-by: NDmitri Epshtein <dima@marvell.com>
Signed-off-by: NGregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When adding the RX queue association with each CPU, a typo was made in
the mvneta_cleanup_rxqs() function. This patch fixes it.

[gregory.clement@free-electrons.com: add commit log and fixes tag]
Cc: stable@vger.kernel.org
Fixes: 2dcf75e2 ("net: mvneta: Associate RX queues with each CPU")
Signed-off-by: NYelena Krivosheev <yelena@marvell.com>
Tested-by: NDmitri Epshtein <dima@marvell.com>
Signed-off-by: NGregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When port connect to PHY in polling mode (with poll interval 1 sec),
port and phy link status must be synchronize in order don't loss link
change event.

[gregory.clement@free-electrons.com: add fixes tag]
Cc: <stable@vger.kernel.org>
Fixes: c5aff182 ("net: mvneta: driver for Marvell Armada 370/XP network unit")
Signed-off-by: NYelena Krivosheev <yelena@marvell.com>
Tested-by: NDmitri Epshtein <dima@marvell.com>
Signed-off-by: NGregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

lock_all_ctx in setplane_internal may return -EINTR, and
__setplane_internal could return -EDEADLK. Making more
special cases for fb would make the code even harder to
read, so the easiest solution is not taking over the fb
refcount, and making callers responsible for dropping
the ref.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102707
Fixes: 13736ba3 ("drm/legacy: Convert setplane ioctl locking to interruptible.")
Testcase: kms_atomic_interruptible
Signed-off-by: NMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171220093545.613-2-maarten.lankhorst@linux.intel.comReviewed-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

When attached to the connector, the mode_valid callback will only filter
the modes provided by the connector itself as part of its probe.

However, it will not be doing it when the mode is provided by the
userspace, which still might result in a broken configuration.

In order to enforce these constraints, move our mode_valid callback to the
encoder which doesn't have this behaviour.
Acked-by: NDaniel Vetter <daniel@ffwll.ch>
Signed-off-by: NHans Verkuil <hans.verkuil@cisco.com>
[maxime: Wrote the commit log in order to update the patch from the merged
	 v3 to the v4 that was correct.]
Signed-off-by: NMaxime Ripard <maxime.ripard@free-electrons.com>
Link: https://patchwork.freedesktop.org/patch/msgid/0fa230a8-d01d-561a-f74f-6b4fd421255b@xs4all.nl

The following namespace configuration attempt:

    # ndctl create-namespace -e namespace0.0 -m devdax -a 1G -f
    libndctl: ndctl_dax_enable: dax0.1: failed to enable
      Error: namespace0.0: failed to enable

    failed to reconfigure namespace: No such device or address

...fails when the backing memory range is not physically aligned to 1G:

    # cat /proc/iomem | grep Persistent
    210000000-30fffffff : Persistent Memory (legacy)

In the above example the 4G persistent memory range starts and ends on a
256MB boundary.

We handle this case correctly when needing to handle cases that violate
section alignment (128MB) collisions against "System RAM", and we simply
need to extend that padding/truncation for the 1GB alignment use case.

Cc: <stable@vger.kernel.org>
Fixes: 315c5625 ("libnvdimm, pfn: add 'align' attribute...")
Reported-and-tested-by: NJane Chu <jane.chu@oracle.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

The alignment checks at pfn driver startup fail to properly account for
the 'start_pad' in the case where the namespace is misaligned relative
to its internal alignment. This is typically triggered in 1G aligned
namespace, but could theoretically trigger with small namespace
alignments. When this triggers the kernel reports messages of the form:

    dax2.1: bad offset: 0x3c000000 dax disabled align: 0x40000000

Cc: <stable@vger.kernel.org>
Fixes: 1ee6667c ("libnvdimm, pfn, dax: fix initialization vs autodetect...")
Reported-by: NJane Chu <jane.chu@oracle.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

fdo#104340.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

During unload, on mlx5_stop_eqs we move command interface from events
mode to polling mode, but if command interface EQ destroy fail we move
back to events mode.
That's wrong since even if we fail to destroy command interface EQ, we
do release its irq, so no interrupts will be received.

Fixes: e126ba97 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: NMoshe Shemesh <moshe@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

When mlx5_stop_eqs fails to destroy any of the eqs it returns with an error.
In such failure flow the function will return without
releasing all EQs irqs and then pci_free_irq_vectors will fail.
Fix by only warn on destroy EQ failure and continue to release other
EQs and their irqs.

It fixes the following kernel trace:
kernel: kernel BUG at drivers/pci/msi.c:352!
...
...
kernel: Call Trace:
kernel: pci_disable_msix+0xd3/0x100
kernel: pci_free_irq_vectors+0xe/0x20
kernel: mlx5_load_one.isra.17+0x9f5/0xec0 [mlx5_core]

Fixes: e126ba97 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: NMoshe Shemesh <moshe@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Flow steering priority and namespace are software only objects that
didn't have the proper destructors and were not freed during steering
cleanup.

Fix it by adding destructor functions for these objects.

Fixes: bd71b08e ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

When calling add/remove VXLAN port, a lock must be held in order to
prevent race scenarios when more than one add/remove happens at the
same time.
Fix by holding our state_lock (mutex) as done by all other parts of the
driver.
Note that the spinlock protecting the radix-tree is still needed in
order to synchronize radix-tree access from softirq context.

Fixes: b3f63c3d ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: NGal Pressman <galp@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

A refcount mechanism must be implemented in order to prevent unwanted
scenarios such as:
- Open an IPv4 VXLAN interface
- Open an IPv6 VXLAN interface (different socket)
- Remove one of the interfaces

With current implementation, the UDP port will be removed from our VXLAN
database and turn off the offloads for the other interface, which is
still active.
The reference count mechanism will only allow UDP port removals once all
consumers are gone.

Fixes: b3f63c3d ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: NGal Pressman <galp@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

mlx5e_vxlan_lookup_port is called both from mlx5e_add_vxlan_port (user
context) and mlx5e_features_check (softirq), but the lock acquired does
not disable bottom half and might result in deadlock. Fix it by simply
replacing spin_lock() with spin_lock_bh().
While at it, replace all unnecessary spin_lock_irq() to spin_lock_bh().

lockdep's WARNING: inconsistent lock state
[  654.028136] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
[  654.028229] swapper/5/0 [HC0[0]:SC1[9]:HE1:SE0] takes:
[  654.028321]  (&(&vxlan_db->lock)->rlock){+.?.}, at: [<ffffffffa06e7f0e>] mlx5e_vxlan_lookup_port+0x1e/0x50 [mlx5_core]
[  654.028528] {SOFTIRQ-ON-W} state was registered at:
[  654.028607]   _raw_spin_lock+0x3c/0x70
[  654.028689]   mlx5e_vxlan_lookup_port+0x1e/0x50 [mlx5_core]
[  654.028794]   mlx5e_vxlan_add_port+0x2e/0x120 [mlx5_core]
[  654.028878]   process_one_work+0x1e9/0x640
[  654.028942]   worker_thread+0x4a/0x3f0
[  654.029002]   kthread+0x141/0x180
[  654.029056]   ret_from_fork+0x24/0x30
[  654.029114] irq event stamp: 579088
[  654.029174] hardirqs last  enabled at (579088): [<ffffffff818f475a>] ip6_finish_output2+0x49a/0x8c0
[  654.029309] hardirqs last disabled at (579087): [<ffffffff818f470e>] ip6_finish_output2+0x44e/0x8c0
[  654.029446] softirqs last  enabled at (579030): [<ffffffff810b3b3d>] irq_enter+0x6d/0x80
[  654.029567] softirqs last disabled at (579031): [<ffffffff810b3c05>] irq_exit+0xb5/0xc0
[  654.029684] other info that might help us debug this:
[  654.029781]  Possible unsafe locking scenario:

[  654.029868]        CPU0
[  654.029908]        ----
[  654.029947]   lock(&(&vxlan_db->lock)->rlock);
[  654.030045]   <Interrupt>
[  654.030090]     lock(&(&vxlan_db->lock)->rlock);
[  654.030162]
 *** DEADLOCK ***

Fixes: b3f63c3d ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: NGal Pressman <galp@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

In error flow, when DESTROY_QP command should be executed, the wrong
mailbox was set with data, not the one that is written to hardware,
Fix that.

Fixes: 09a7d9ec '{net,IB}/mlx5: QP/XRCD commands via mlx5 ifc'
Signed-off-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Fix misspelling in word syndrome.

Fixes: e126ba97 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Fixes the bug when turning on/off CQE compression mechanism
resets the RX rings size to default value when it is not
needed.

Fixes: 2fc4bfb7 ("net/mlx5e: Dynamic RQ type infrastructure")
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

The assumption that the next header field contains the transport
protocol is wrong for IPv6 packets with extension headers.
Instead, we should look the inner-most next header field in the buffer.
This will fix TSO offload for tunnels over IPv6 with extension headers.

Performance testing: 19.25x improvement, cool!
Measuring bandwidth of 16 threads TCP traffic over IPv6 GRE tap.
CPU: Intel(R) Xeon(R) CPU E5-2660 v2 @ 2.20GHz
NIC: Mellanox Technologies MT28800 Family [ConnectX-5 Ex]
TSO: Enabled
Before: 4,926.24  Mbps
Now   : 94,827.91 Mbps

Fixes: b3f63c3d ("net/mlx5e: Add netdev support for VXLAN tunneling")
Signed-off-by: NGal Pressman <galp@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Fix bug that allows ets bw sum to be 0% when ets tc type exists.

Fixes: 08fb1dac ('net/mlx5e: Support DCBNL IEEE ETS')
Signed-off-by: NMoshe Shemesh <moshe@mellanox.com>
Reviewed-by: NHuy Nguyen <huyn@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

In mlx5_ifc, struct size was not complete, and thus driver was sending
garbage after the last defined field. Fixed it by adding reserved field
to complete the struct size.

In addition, rename all set_rate_limit to set_pp_rate_limit to be
compliant with the Firmware <-> Driver definition.

Fixes: 7486216b ("{net,IB}/mlx5: mlx5_ifc updates")
Fixes: 1466cc5b ("net/mlx5: Rate limit tables support")
Signed-off-by: NEran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Before the offending commit, mlx5 core did the IRQ affinity itself,
and it seems that the new generic code have some drawbacks and one
of them is the lack for user ability to modify irq affinity after
the initial affinity values got assigned.

The issue is still being discussed and a solution in the new generic code
is required, until then we need to revert this patch.

This fixes the following issue:
echo <new affinity> > /proc/irq/<x>/smp_affinity
fails with  -EIO

This reverts commit a435393a.
Note: kept mlx5_get_vector_affinity in include/linux/mlx5/driver.h since
it is used in mlx5_ib driver.

Fixes: a435393a ("mlx5: move affinity hints assignments to generic code")
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jes Sorensen <jsorensen@fb.com>
Reported-by: NJes Sorensen <jsorensen@fb.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Currently, if a size of zero is passed to
mlx5_fpga_mem_{read|write}_i2c()
the "err" return value will not be initialized, which triggers gcc
warnings:

[..]/mlx5/core/fpga/sdk.c:87 mlx5_fpga_mem_read_i2c() error:
uninitialized symbol 'err'.
[..]/mlx5/core/fpga/sdk.c:115 mlx5_fpga_mem_write_i2c() error:
uninitialized symbol 'err'.

fix that.

Fixes: a9956d35 ('net/mlx5: FPGA, Add SBU infrastructure')
Signed-off-by: NKamal Heib <kamalh@mellanox.com>
Reviewed-by: NYevgeny Kliteynik <kliteyn@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

Our MMC host driver now issues a reset, instead of just deasserting
the reset control, since commit c34eda69 ("mmc: sunxi: Reset the
device at probe time"). The sun9i-mmc clock driver does not support
this, and will fail, which results in MMC not probing.

This patch implements the reset callback by asserting the reset control,
then deasserting it after a small delay.

Fixes: 7a6fca87 ("clk: sunxi: Add driver for A80 MMC config clocks/resets")
Cc: <stable@vger.kernel.org> # 4.14.x
Signed-off-by: NChen-Yu Tsai <wens@csie.org>
Acked-by: NPhilipp Zabel <p.zabel@pengutronix.de>
Acked-by: NMaxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: NMichael Turquette <mturquette@baylibre.com>
Link: lkml.kernel.org/r/20171218035751.20661-1-wens@csie.org

As noted in dwmac4_wrback_get_rx_timestamp_status the timestamp is found
in the context descriptor following the current descriptor. However the
current code looks for the context descriptor in the current
descriptor, which will always fail.
Signed-off-by: NFredrik Hallenberg <megahallon@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When using GMAC4 the value written in PTP_SSIR should be shifted however
the shifted value is also used in subsequent calculations which results
in a bad timestamp value.
Signed-off-by: NFredrik Hallenberg <megahallon@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Unlike ip tunnels, now vxlan doesn't do any pmtu update for
upper dst pmtu, even if it doesn't match the lower dst pmtu
any more.

The problem can be reproduced when reducing the vxlan lower
dev's pmtu when running netperf. In jianlin's testing, the
performance went to 1/7 of the previous.

This patch is to update the upper dst pmtu to match the lower
dst pmtu on tx path so that packets can be sent out even when
lower dev's pmtu has been changed.

It also works for metadata dst.

Note that this patch doesn't process any pmtu icmp packet.
But even in the future, the support for pmtu icmp packets
process of udp tunnels will also needs this.

The same thing will be done for geneve in another patch.
Signed-off-by: NXin Long <lucien.xin@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Under certain conditions EMAC stop reception of incoming packets and
continuously increment R_MISS register instead of saving data into
provided buffer. The commit implement workaround for such situation.
Then the stall detected EMAC will be restarted.

On device the stall looks like the device lost it's dynamic IP address.
ifconfig shows that interface error counter rapidly increments.
At the same time on the DHCP server we can see continues DHCP-requests
from device.

In real network stalls happen really rarely. To make them frequent the
broadcast storm[1] should be simulated. For simulation it is necessary
to make following connections:
    1. connect radxarock to 1st port of switch
    2. connect some PC to 2nd port of switch
    3. connect two other free ports together using standard ethernet cable,
       in order to make a switching loop.

After that, is necessary to make a broadcast storm. For example, running on
PC 'ping' to some IP address triggers ARP-request storm. After some
time (~10sec), EMAC on rk3188 will stall.

Observed and tested on rk3188 radxarock.

[1] https://en.wikipedia.org/wiki/Broadcast_radiationSigned-off-by: NAlexander Kochetkov <al.kochet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>