Return error code if autosuspend_en, eee_get, or eee_set don't exist.
Signed-off-by: NHayes Wang <hayeswang@realtek.com>
Signed-off-by: NJakub Kicinski <kuba@kernel.org>

U1/U2 shoued be enabled for USB 3.0 or later. The USB 2.0 doesn't
support it.
Signed-off-by: NHayes Wang <hayeswang@realtek.com>
Signed-off-by: NJakub Kicinski <kuba@kernel.org>

Add support for being able to set the learning attribute on port, and
make sure that the standalone ports start up with learning disabled.

We can remove the code in bcm_sf2 that configured the ports learning
attribute because we want the standalone ports to have learning disabled
by default and port 7 cannot be bridged, so its learning attribute will
not change past its initial configuration.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NJakub Kicinski <kuba@kernel.org>

Because bcm_sf2 implements its own dsa_switch_ops we need to export the
b53_br_flags_pre(), b53_br_flags() and b53_set_mrouter so we can wire-up
them up like they used to be with the former b53_br_egress_floods().

Fixes: a8b659e7 ("net: dsa: act as passthrough for bridge port flags")
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Reviewed-by: NVladimir Oltean <olteanv@gmail.com>
Signed-off-by: NJakub Kicinski <kuba@kernel.org>

sky2.c driver uses netdev_warn() before the net device is initialized.
Fix it by using dev_warn() instead.
Signed-off-by: NKrzysztof Halasa <khalasa@piap.pl>

Link: https://lore.kernel.org/r/m3a6s1r1ul.fsf@t19.piap.plSigned-off-by: NJakub Kicinski <kuba@kernel.org>

In ndo_stop functions, netdev_completed_queue() is called during forced
tx reclaim, after netdev_reset_queue(). This may trigger kernel panic if
there is any tx skb left.

This patch moves netdev_reset_queue() to after tx reclaim, so BQL can
complete successfully then reset.
Signed-off-by: NSieng Piaw Liew <liew.s.piaw@gmail.com>
Fixes: 4c59b0f5 ("bcm63xx_enet: add BQL support")
Acked-by: NFlorian Fainelli <f.fainelli@gmail.com>
Link: https://lore.kernel.org/r/20210222013530.1356-1-liew.s.piaw@gmail.comSigned-off-by: NJakub Kicinski <kuba@kernel.org>

The icmp{,v6}_send functions make all sorts of use of skb->cb, casting
it with IPCB or IP6CB, assuming the skb to have come directly from the
inet layer. But when the packet comes from the ndo layer, especially
when forwarded, there's no telling what might be in skb->cb at that
point. As a result, the icmp sending code risks reading bogus memory
contents, which can result in nasty stack overflows such as this one
reported by a user:

    panic+0x108/0x2ea
    __stack_chk_fail+0x14/0x20
    __icmp_send+0x5bd/0x5c0
    icmp_ndo_send+0x148/0x160

In icmp_send, skb->cb is cast with IPCB and an ip_options struct is read
from it. The optlen parameter there is of particular note, as it can
induce writes beyond bounds. There are quite a few ways that can happen
in __ip_options_echo. For example:

    // sptr/skb are attacker-controlled skb bytes
    sptr = skb_network_header(skb);
    // dptr/dopt points to stack memory allocated by __icmp_send
    dptr = dopt->__data;
    // sopt is the corrupt skb->cb in question
    if (sopt->rr) {
        optlen  = sptr[sopt->rr+1]; // corrupt skb->cb + skb->data
        soffset = sptr[sopt->rr+2]; // corrupt skb->cb + skb->data
	// this now writes potentially attacker-controlled data, over
	// flowing the stack:
        memcpy(dptr, sptr+sopt->rr, optlen);
    }

In the icmpv6_send case, the story is similar, but not as dire, as only
IP6CB(skb)->iif and IP6CB(skb)->dsthao are used. The dsthao case is
worse than the iif case, but it is passed to ipv6_find_tlv, which does
a bit of bounds checking on the value.

This is easy to simulate by doing a `memset(skb->cb, 0x41,
sizeof(skb->cb));` before calling icmp{,v6}_ndo_send, and it's only by
good fortune and the rarity of icmp sending from that context that we've
avoided reports like this until now. For example, in KASAN:

    BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0xa0e/0x12b0
    Write of size 38 at addr ffff888006f1f80e by task ping/89
    CPU: 2 PID: 89 Comm: ping Not tainted 5.10.0-rc7-debug+ #5
    Call Trace:
     dump_stack+0x9a/0xcc
     print_address_description.constprop.0+0x1a/0x160
     __kasan_report.cold+0x20/0x38
     kasan_report+0x32/0x40
     check_memory_region+0x145/0x1a0
     memcpy+0x39/0x60
     __ip_options_echo+0xa0e/0x12b0
     __icmp_send+0x744/0x1700

Actually, out of the 4 drivers that do this, only gtp zeroed the cb for
the v4 case, while the rest did not. So this commit actually removes the
gtp-specific zeroing, while putting the code where it belongs in the
shared infrastructure of icmp{,v6}_ndo_send.

This commit fixes the issue by passing an empty IPCB or IP6CB along to
the functions that actually do the work. For the icmp_send, this was
already trivial, thanks to __icmp_send providing the plumbing function.
For icmpv6_send, this required a tiny bit of refactoring to make it
behave like the v4 case, after which it was straight forward.

Fixes: a2b78e9b ("sunvnet: generate ICMP PTMUD messages for smaller port MTUs")
Reported-by: NSinYu <liuxyon@gmail.com>
Reviewed-by: NWillem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/netdev/CAF=yD-LOF116aHub6RMe8vB8ZpnrrnoTdqhobEx+bvoA8AsP0w@mail.gmail.com/T/Signed-off-by: NJason A. Donenfeld <Jason@zx2c4.com>
Link: https://lore.kernel.org/r/20210223131858.72082-1-Jason@zx2c4.comSigned-off-by: NJakub Kicinski <kuba@kernel.org>

mlx4_do_mirror_rule() forgets to call mlx4_free_cmd_mailbox() to
free the memory region allocated by mlx4_alloc_cmd_mailbox() before
an exit.
Add the missed call to fix it.

Fixes: 78efed27 ("net/mlx4_core: Support mirroring VF DMFS rules on both ports")
Signed-off-by: NChuhong Yuan <hslester96@gmail.com>
Reviewed-by: NTariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20210221143559.390277-1-hslester96@gmail.comSigned-off-by: NJakub Kicinski <kuba@kernel.org>

When link speed is not 100 Mbps, port transmit rate and speed divider
are set to 8 and 1000000 respectively. These values are incorrect for
CBS idleslope and sendslope HW values calculation if the link speed is
not 1 Gbps.

This patch adds switch statement to set the values of port transmit rate
and speed divider for 10 Gbps, 5 Gbps, 2.5 Gbps, 1 Gbps, and 100 Mbps.
Note that CBS is not supported at 10 Mbps.

Fixes: bc41a668 ("net: stmmac: tc: Remove the speed dependency")
Fixes: 1f705bc6 ("net: stmmac: Add support for CBS QDISC")
Signed-off-by: NSong, Yoong Siang <yoong.siang.song@intel.com>
Link: https://lore.kernel.org/r/1613655653-11755-1-git-send-email-yoong.siang.song@intel.comSigned-off-by: NJakub Kicinski <kuba@kernel.org>

The comments to phy_select_page() say that "phy_restore_page() must
always be called after this, irrespective of success or failure of this
call."  If we don't call phy_restore_page() then we are still holding
the phy_lock_mdio_bus() so it eventually leads to a dead lock.

Fixes: 32ab60e5 ("net: phy: icplus: add MDI/MDIX support for IP101A/G")
Fixes: f9bc51e6 ("net: phy: icplus: fix paged register access")
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: NMichael Walle <michael@walle.cc>
Reviewed-by: NRussell King <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/YC+OpFGsDPXPnXM5@mwandaSigned-off-by: NJakub Kicinski <kuba@kernel.org>

PPv2 loopback port doesn't support RSS, so we should
skip RSS configurations for this port.
Signed-off-by: NStefan Chulski <stefanc@marvell.com>
Reviewed-by: NMarcin Wojtas <mw@semihalf.com>
Link: https://lore.kernel.org/r/1613652123-19021-1-git-send-email-stefanc@marvell.comSigned-off-by: NJakub Kicinski <kuba@kernel.org>

The current use of container_of is flawed and unnecessary. Obtain
the dpaa_napi_portal reference from the private percpu data instead.

Fixes: a1e031ff ("dpaa_eth: add XDP_REDIRECT support")
Reported-by: NSascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: NCamelia Groza <camelia.groza@nxp.com>
Acked-by: NMadalin Bucur <madalin.bucur@oss.nxp.com>
Acked-by: NJesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/r/20210218182106.22613-1-camelia.groza@nxp.comSigned-off-by: NJakub Kicinski <kuba@kernel.org>

2 bytes of the MTU are reserved for Atheros DSA tag, but DSA core
has already handled that since commit dc0fe7d4.
Remove the unnecessary reservation.

Fixes: d51b6ce4 ("net: ethernet: add ag71xx driver")
Signed-off-by: NDENG Qingfang <dqfext@gmail.com>
Reviewed-by: NOleksij Rempel <o.rempel@pengutronix.de>
Link: https://lore.kernel.org/r/20210218034514.3421-1-dqfext@gmail.comSigned-off-by: NJakub Kicinski <kuba@kernel.org>

This code does not allocate enough memory for the NUL terminator so it
ends up putting it one character beyond the end of the buffer.

Fixes: 8756828a ("octeontx2-af: Add NPA aura and pool contexts to debugfs")
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fixes the following sparse warnings:
i40e_main.c:5953:32: warning: cast from restricted __le16
i40e_main.c:8008:29: warning: incorrect type in assignment (different base types)
i40e_main.c:8008:29:    expected unsigned int [assigned] [usertype] ipa
i40e_main.c:8008:29:    got restricted __le32 [usertype]
i40e_main.c:8008:29: warning: incorrect type in assignment (different base types)
i40e_main.c:8008:29:    expected unsigned int [assigned] [usertype] ipa
i40e_main.c:8008:29:    got restricted __le32 [usertype]
i40e_txrx.c:1950:59: warning: incorrect type in initializer (different base types)
i40e_txrx.c:1950:59:    expected unsigned short [usertype] vlan_tag
i40e_txrx.c:1950:59:    got restricted __le16 [usertype] l2tag1
i40e_txrx.c:1953:40: warning: cast to restricted __le16
i40e_xsk.c:448:38: warning: invalid assignment: |=
i40e_xsk.c:448:38:    left side has type restricted __le64
i40e_xsk.c:448:38:    right side has type int

Fixes: 2f4b411a ("i40e: Enable cloud filters via tc-flower")
Fixes: 2a508c64 ("i40e: fix VLAN.TCI == 0 RX HW offload")
Fixes: 3106c580 ("i40e: Use batched xsk Tx interfaces to increase performance")
Fixes: 8f88b303 ("i40e: Add infrastructure for queue channel support")
Signed-off-by: NNorbert Ciosek <norbertx.ciosek@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Fix insufficient distinction between IPv4 and IPv6 addresses
when creating a filter.
IPv4 and IPv6 are kept in the same memory area. If IPv6 is added,
then it's caught by IPv4 check, which leads to err -95.

Fixes: 2f4b411a ("i40e: Enable cloud filters via tc-flower")
Signed-off-by: NGrzegorz Szczurek <grzegorzx.szczurek@intel.com>
Signed-off-by: NMateusz Palczewski <mateusz.palczewski@intel.com>
Reviewed-by: NJaroslaw Gawin <jaroslawx.gawin@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

When creating VFs they were sometimes not getting resources.
It was caused by not executing i40e_reset_all_vfs due to
flag __I40E_VF_DISABLE being set on PF. Because of this
IAVF was never able to finish setup sequence never
getting reset indication from PF.
Changed test_and_set_bit __I40E_VF_DISABLE in
i40e_sync_filters_subtask to test_bit and removed clear_bit.
This function should not set this bit it should only check
if it hasn't been already set.

Fixes: a7542b87 ("i40e: check __I40E_VF_DISABLE bit in i40e_sync_filters_subtask")
Signed-off-by: NSylwester Dziedziuch <sylwesterx.dziedziuch@intel.com>
Tested-by: NKonrad Jankowski <konrad0.jankowski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Fix addition of VLAN filter for PF after enabling FW LLDP agent.
Changing LLDP Agent causes FW to re-initialize per NVM settings.
Remove default PF filter and move "Enable/Disable" to currently used
reset flag.
Without this patch PF would try to add MAC VLAN filter with default
switch filter present. This causes AQ error and sets promiscuous mode
on.

Fixes: c65e78f8 ("i40e: Further implementation of LLDP")
Signed-off-by: NPrzemyslaw Patynowski <przemyslawx.patynowski@intel.com>
Signed-off-by: NMateusz Palczewski <mateusz.palczewski@intel.com>
Reviewed-by: NSylwester Dziedziuch <sylwesterx.dziedziuch@intel.com>
Reviewed-by: NAleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

During driver loading flow control settings were written to FW
using a variable which was always zero, since it was being set
only by ethtool. This behavior has been corrected and driver
no longer overwrites the default FW/NVM settings.

Fixes: 373149fc ("i40e: Decrease the scope of rtnl lock")
Signed-off-by: NDawid Lukwinski <dawid.lukwinski@intel.com>
Signed-off-by: NMateusz Palczewski <mateusz.palczewski@intel.com>
Reviewed-by: NAleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Zero-initialize AQ command data structures to comply with
API specifications.

Fixes: 2f4b411a ("i40e: Enable cloud filters via tc-flower")
Fixes: f4492db1 ("i40e: Add NPAR BW get and set functions")
Signed-off-by: NAndrzej Sawuła <andrzej.sawula@intel.com>
Signed-off-by: NMateusz Palczewski <mateusz.palczewski@intel.com>
Reviewed-by: NArkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Reviewed-by: NAleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Struct i40e_veb is allocated in function i40e_setup_pf_switch, and
stored to an array field veb inside struct i40e_pf. However when
i40e_setup_misc_vector fails, this memory leaks.

Fix this by calling exit and teardown functions.
Signed-off-by: NKeita Suzuki <keitasuzuki.park@sslab.ics.keio.ac.jp>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

When a packet contains an IPv6 header with next header which is
an extension header and not a protocol one, the kernel function
skb_transport_header called with such sk_buff will return a
pointer to the extension header and not to the TCP one.

The above explained call caused a problem with packet processing
for skb with encapsulation for tunnel with I40E_TX_CTX_EXT_IP_IPV6.
The extension header was not skipped at all.

The ipv6_skip_exthdr function does check if next header of the IPV6
header is an extension header and doesn't modify the l4_proto pointer
if it points to a protocol header value so its safe to omit the
comparison of exthdr and l4.hdr pointers. The ipv6_skip_exthdr can
return value -1. This means that the skipping process failed
and there is something wrong with the packet so it will be dropped.

Fixes: a3fd9d88 ("i40e/i40evf: Handle IPv6 extension headers in checksum offload")
Signed-off-by: NSlawomir Laba <slawomirx.laba@intel.com>
Signed-off-by: NPrzemyslaw Patynowski <przemyslawx.patynowski@intel.com>
Reviewed-by: NAleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: NTony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: NTony Nguyen <anthony.l.nguyen@intel.com>

Static checkers complained about an off by one read overflow in
otx2_get_fecparam() and we applied two conflicting fixes for it.

Correct: b0aae0bd ("octeontx2: Fix condition.")
  Wrong: 93efb0c6 ("octeontx2-pf: Fix out-of-bounds read in otx2_get_fecparam()")

Revert the incorrect fix.

Fixes: 93efb0c6 ("octeontx2-pf: Fix out-of-bounds read in otx2_get_fecparam()")
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

These defines are used with set_bit() and test_bit() which take a bit
number.  In other words, the code is doing:

	if (BIT(BIT(1)) & pf->hw.cap_flag) {

This was done consistently so it did not cause a problem at runtime but
it's still worth fixing.

Fixes: facede82 ("octeontx2-pf: cn10k: Add mbox support for CN10K")
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch populates the PCI bus info in the ethtool driver query data.

Users will be able to view PCI bus info using 'ethtool -i <interface>'.
Signed-off-by: NWong Vee Khee <vee.khee.wong@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The Ethernet MAC and PHY are usually major consumers of power on boards
which may not be able to fully power off (those with no PMIC). Powering
down the MAC and internal PHY saves power while these boards are "off".
Reviewed-by: NChen-Yu Tsai <wens@csie.org>
Signed-off-by: NSamuel Holland <samuel@sholland.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adjust the spacing and use an explicit "return 0" in the success path
to make the function easier to parse.
Reviewed-by: NChen-Yu Tsai <wens@csie.org>
Signed-off-by: NSamuel Holland <samuel@sholland.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use the appropriate function instead of reimplementing it,
and update the error message to match the code.
Reviewed-by: NChen-Yu Tsai <wens@csie.org>
Signed-off-by: NSamuel Holland <samuel@sholland.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

sun8i_dwmac_unpower_internal_phy already checks if the PHY is powered,
so there is no need to do it again here.
Reviewed-by: NChen-Yu Tsai <wens@csie.org>
Signed-off-by: NSamuel Holland <samuel@sholland.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is a deinitialization function that always returned zero, and that
return value was always ignored. Have it return void instead.
Reviewed-by: NChen-Yu Tsai <wens@csie.org>
Signed-off-by: NSamuel Holland <samuel@sholland.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use macro pm_ptr(), this helps to avoid some ifdeffery.
Signed-off-by: NHeiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We have no in-tree users, also update the sfp-phylink.rst documentation
to indicate that phy_attach_direct() is used instead of of_phy_attach().
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>

Ocelot now uses include/linux/dsa/ocelot.h which makes use of
CONFIG_PACKING to pack/unpack bits into the Injection/Extraction Frame
Headers. So it needs to explicitly select it, otherwise there might be
build errors due to the missing dependency.

Fixes: 40d3f295 ("net: mscc: ocelot: use common tag parsing code with DSA")
Reported-by: NNaresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NJakub Kicinski <kuba@kernel.org>

bcm54xx_config_init was modifying the PHY LED configuration to enable link
and activity indications. However, some SFP modules (such as Bel-Fuse
SFP-1GBT-06) have no LEDs but use the LED outputs to control the SFP LOS
signal, and modifying the LED settings will cause the LOS output to
malfunction. Skip this configuration for PHYs which are bound to an SFP
bus.
Signed-off-by: NRobert Hancock <robert.hancock@calian.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add a flag and helper function to indicate that a PHY device is part of
an SFP module, which is set on attach. This can be used by PHY drivers
to handle SFP-specific quirks or behavior.
Signed-off-by: NRobert Hancock <robert.hancock@calian.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The default configuration for the BCM54616S PHY may not match the desired
mode when using 1000BaseX or SGMII interface modes, such as when it is on
an SFP module. Add code to explicitly set the correct mode using
programming sequences provided by Bel-Fuse:

https://www.belfuse.com/resources/datasheets/powersolutions/ds-bps-sfp-1gbt-05-series.pdf
https://www.belfuse.com/resources/datasheets/powersolutions/ds-bps-sfp-1gbt-06-series.pdfSigned-off-by: NRobert Hancock <robert.hancock@calian.com>
Acked-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On cpu architectures w/o dma cache snooping, dma_unmap() is a
is a very expensive operation, because its resulting sync
needs to invalidate cpu caches.

Increase efficiency/performance by syncing only those sections
of the lan743x's rx ring buffers that are actually in use.
Signed-off-by: NSven Van Asbroeck <thesven73@gmail.com>
Reviewed-by: NBryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The buffers in the lan743x driver's receive ring are always 9K,
even when the largest packet that can be received (the mtu) is
much smaller. This performs particularly badly on cpu archs
without dma cache snooping (such as ARM): each received packet
results in a 9K dma_{map|unmap} operation, which is very expensive
because cpu caches need to be invalidated.

Careful measurement of the driver rx path on armv7 reveals that
the cpu spends the majority of its time waiting for cache
invalidation.

Optimize by keeping the rx ring buffer size as close as possible
to the mtu. This limits the amount of cache that requires
invalidation.

This optimization would normally force us to re-allocate all
ring buffers when the mtu is changed - a disruptive event,
because it can only happen when the network interface is down.

Remove the need to re-allocate all ring buffers by adding support
for multi-buffer frames. Now any combination of mtu and ring
buffer size will work. When the mtu changes from mtu1 to mtu2,
consumed buffers of size mtu1 are lazily replaced by newly
allocated buffers of size mtu2.

These optimizations double the rx performance on armv7.
Third parties report 3x rx speedup on armv8.

Tested with iperf3 on a freescale imx6qp + lan7430, both sides
set to mtu 1500 bytes, measure rx performance:

Before:
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-20.00  sec   550 MBytes   231 Mbits/sec    0
After:
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-20.00  sec  1.33 GBytes   570 Mbits/sec    0
Signed-off-by: NSven Van Asbroeck <thesven73@gmail.com>
Reviewed-by: NBryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The following call path suggests that calling unregister_netdev on an
interface that is up will first bring it down.

enetc_pf_remove
-> unregister_netdev
   -> unregister_netdevice_queue
      -> unregister_netdevice_many
         -> dev_close_many
            -> __dev_close_many
               -> enetc_close
                  -> enetc_stop
                     -> phylink_stop

However, enetc first destroys the phylink instance, then calls
unregister_netdev. This is already dissimilar to the setup (and error
path teardown path) from enetc_pf_probe, but more than that, it is buggy
because it is invalid to call phylink_stop after phylink_destroy.

So let's first unregister the netdev (and let the .ndo_stop events
consume themselves), then destroy the phylink instance, then free the
netdev.

Fixes: 71b77a7a ("enetc: Migrate to PHYLINK and PCS_LYNX")
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>