We would like to automatically provide busy polling support
to all NAPI drivers, without them having to implement anything.

skb_mark_napi_id() can be called from napi_gro_receive() and
napi_get_frags().

Few drivers are still calling skb_mark_napi_id() because
they use netif_receive_skb(). They should eventually call
napi_gro_receive() instead. I will leave this to drivers
maintainers.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Busy polling can now be handled in generic NAPI poll infrastructure.
This removes complexity and fast path overhead :

mlx4 used two spin_lock()/spin_unlock() pair per napi->poll() call
in mlx4_en_cq_lock_napi()/mlx4_en_cq_unlock_napi()

Tested:

Without busy polling :

lpaa23:~# echo 0 >/proc/sys/net/core/busy_read
lpaa24:~# echo 0 >/proc/sys/net/core/busy_read
lpaa23:~# ./netperf -H lpaa24 -t TCP_RR
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to lpaa24.prod.google.com () port 0 AF_INET : first burst 0
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate
bytes  Bytes  bytes    bytes   secs.    per sec

16384  87380  1        1       10.00    47330.78

With busy polling :

lpaa23:~# echo 70 >/proc/sys/net/core/busy_read
lpaa24:~# echo 70 >/proc/sys/net/core/busy_read
lpaa23:~# ./netperf -H lpaa24 -t TCP_RR
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to lpaa24.prod.google.com () port 0 AF_INET : first burst 0
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate
bytes  Bytes  bytes    bytes   secs.    per sec

16384  87380  1        1       10.00    97643.55
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Switch to native NAPI polling, as this reduces overhead and complexity.

Normal path is faster, since one cmpxchg() is not anymore requested,
and busy polling with the NAPI polling has same performance.

Tested:
lpk50:~# cat /proc/sys/net/core/busy_read
70
lpk50:~# nstat >/dev/null;./netperf -H lpk55 -t TCP_RR;nstat
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to lpk55.prod.google.com () port 0 AF_INET : first burst 0
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate
bytes  Bytes  bytes    bytes   secs.    per sec

16384  87380  1        1       10.00    40095.07
16384  87380
IpInReceives                    401062             0.0
IpInDelivers                    401062             0.0
IpOutRequests                   401079             0.0
TcpActiveOpens                  7                  0.0
TcpPassiveOpens                 3                  0.0
TcpAttemptFails                 3                  0.0
TcpEstabResets                  5                  0.0
TcpInSegs                       401036             0.0
TcpOutSegs                      401052             0.0
TcpOutRsts                      38                 0.0
UdpInDatagrams                  26                 0.0
UdpOutDatagrams                 27                 0.0
Ip6OutNoRoutes                  1                  0.0
TcpExtDelayedACKs               1                  0.0
TcpExtTCPPrequeued              98                 0.0
TcpExtTCPDirectCopyFromPrequeue 98                 0.0
TcpExtTCPHPHits                 4                  0.0
TcpExtTCPHPHitsToUser           98                 0.0
TcpExtTCPPureAcks               5                  0.0
TcpExtTCPHPAcks                 101                0.0
TcpExtTCPAbortOnData            6                  0.0
TcpExtBusyPollRxPackets         400832             0.0
TcpExtTCPOrigDataSent           400983             0.0
IpExtInOctets                   21273867           0.0
IpExtOutOctets                  21261254           0.0
IpExtInNoECTPkts                401064             0.0
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A NAPI poll handler should return number of RX packets processed,
instead of 0 / budget.

This allows proper busy poll accounting through LINUX_MIB_BUSYPOLLRXPACKETS
SNMP counter.

napi_complete_done() allows /sys/class/net/ethX/gro_flush_timeout
to be used for finer GRO aggregation control.

Tested:

Enabled busy polling, and checked TcpExtBusyPollRxPackets counter is increasing.

echo 70 >/proc/sys/net/core/busy_read
nstat >/dev/null
netperf -H target -t TCP_RR >/dev/null
nstat | grep TcpExtBusyPollRxPackets
TcpExtBusyPollRxPackets         490958             0.0
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Eli Cohen <eli@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is now easy to add busy polling support to a NAPI driver,
with very little impact on normal input path.

This patch serves as a reference implementation.

Note:

A followup patch will add proper napi_complete_done() in mlx5,
so that LINUX_MIB_BUSYPOLLRXPACKETS snmp counter is properly handled.

Tested:

Normal TCP_RR results without busy polling :

lpk51:~# echo 0 >/proc/sys/net/core/busy_read
lpk52:~# echo 0 >/proc/sys/net/core/busy_read

lpk51:~# ./netperf -H 192.168.4.52 -t TCP_RR -l 10
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.4.52 () port 0 AF_INET : first burst 0
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate
bytes  Bytes  bytes    bytes   secs.    per sec

16384  87380  1        1       10.00    53509.49
16384  87380

Now enable busy polling :

lpk51:~# echo 70 >/proc/sys/net/core/busy_read
lpk52:~# echo 70 >/proc/sys/net/core/busy_read

lpk51:~# ./netperf -H 192.168.4.52 -t TCP_RR -l 10
MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.4.52 () port 0 AF_INET : first burst 0
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate
bytes  Bytes  bytes    bytes   secs.    per sec

16384  87380  1        1       10.00    97530.92
16384  87380
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

mlx4_en_low_latency_recv() is called with BH disabled,
as other ndo_busy_poll() methods.

No need for spin_lock_bh()/spin_unlock_bh()
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The lancer_cmd_get_file_len() uses lancer_cmd_read_object() to get
the current size of registers for ethtool registers dump. Returned status
value is stored but not checked. The check itself is not necessary as
the data_read output variable is initialized to 0 and status variable
can be removed.
Signed-off-by: NIvan Vecera <ivecera@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The NOLINK state will poll the phy once a second to see if the link
has come up. If the phy has an interrupt line, this polling can be
skipped, since the phy should interrupt when the link returns.
Signed-off-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The 88E1540 can be found embedded in the Marvell 88E6352 switch.  It
is compatible with the 88E1510, so add support for it, using the
88E1510 specific functions.
Signed-off-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Reset pskb in macvlan_handle_frame in case skb_share_check returned a
clone.

Fixes: 8a4eb573 ("net: introduce rx_handler results and logic around that")
Signed-off-by: NSabrina Dubroca <sd@queasysnail.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

ipvlan_handle_frame is a rx_handler, and when it returns a value other
than RX_HANDLER_CONSUMED (here, NET_RX_DROP aka RX_HANDLER_ANOTHER),
__netif_receive_skb_core expects that the skb still exists and will
process it further, but we just freed it.

Fixes: 2ad7bf36 ("ipvlan: Initial check-in of the IPVLAN driver.")
Signed-off-by: NSabrina Dubroca <sd@queasysnail.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Pass a **skb to ipvlan_rcv_frame so that if skb_share_check returns a
new skb, we actually use it during further processing.

It's safe to ignore the new skb in the ipvlan_xmit_* functions, because
they call ipvlan_rcv_frame with local == true, so that dev_forward_skb
is called and always takes ownership of the skb.

Fixes: 2ad7bf36 ("ipvlan: Initial check-in of the IPVLAN driver.")
Signed-off-by: NSabrina Dubroca <sd@queasysnail.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

By default the driver allowed incorrect frames to be received. What is
worse the code does not handle very short frames correctly. The FCS
length is unconditionally subtracted, and the underflow can cause
skb_put to be called with large number after implicit cast to unsigned.
And indeed, an skb_over_panic() was observed with via-velocity.

This removes the module parameter as it does not work in it's
current state, and should be implemented via NETIF_F_RXALL if needed.
Suggested-by: NFrancois Romieu <romieu@fr.zoreil.com>
Signed-off-by: NTimo Teräs <timo.teras@iki.fi>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that IP1000A chips are supported by dl2k driver, the buggy ipg
driver can be removed.
Signed-off-by: NOndrej Zary <linux@rainbow-software.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add support for IP1000A chips to dl2k driver.
IP1000A chip looks like a TC9020 with integrated PHY.

This allows IP1000A chips to work reliably because the ipg driver is
buggy - it loses packets under load and then completely stops
transmitting data.

Tested with Asus NX1101 v2.0 at 10, 100 and 1000Mbps:
vendor=0x13f0 device=0x1023 (rev 0x41)
subsystem vendor=0x1043 device=0x8180

MAC address registers access needed to be changed from 8-bit to 16-bit
because 8-bit does not work on IP1000A. 8-bit access is not even
allowed in the TC9020 datasheet (although it worked). 16-bit access
works on both.

Tested that it does not break D-Link DGE-550T (DL-2000 chip, probably
a rebranded TC9020):
vendor=0x1186 device=0x4000 (rev 0x0c)
subsystem vendor=0x1186 device=0x4000
Signed-off-by: NOndrej Zary <linux@rainbow-software.org>
Reviewed-by: NAndy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In some cases the crash is caused by nicvf_remove() being called from
outside. For example, if we try to feed the device to vfio after the
probe has failed for some reason. So, move the check to better place.
Signed-off-by: NPavel Fedin <p.fedin@samsung.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 05cc5a39 "bnx2x: add vlan filtering offload" introduced
a regression in regard for vlans for 57710, 57711 adapters -
Loading 8021q module on a machine with such an adapter would cause
a null pointer dereference, as the driver mistakenly publishes it
has capabilities for vlan CTAG filtering.
Reported-by: NOtto Sabart <osabart@redhat.com>
Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This driver does not handle the AVB-DMAC Receive FIFO Warning interrupt
now, so the interrupt should not be enabled.
Signed-off-by: NMasaru Nagai <masaru.nagai.vx@renesas.com>
Signed-off-by: NYoshihiro Kaneko <ykaneko0929@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This pci_error_handlers structure is never modified, like all the other
pci_error_handlers structures, so declare it as const.

Done with the help of Coccinelle.
Signed-off-by: NJulia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This pci_error_handlers structure is never modified, like all the other
pci_error_handlers structures, so declare it as const.

Done with the help of Coccinelle.
Signed-off-by: NJulia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NShrikrishna Khare <skhare@vmware.com>
Reported-by: NMasao Uebayashi <uebayasi@gmail.com>
Signed-off-by: NBhavesh Davda <bhavesh@vmware.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since Dell DW5580 is a 3G modem, this patch adds the device as a
mobile broadband adapter
Signed-off-by: NDaniele Palmas <dnlplm@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NIvan Vecera <ivecera@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove rsstable array and its initialization from be_set_rss_hash_opts().
The array became unused after "e2557877 be2net: Support for configurable
RSS hash key". The initial RSS table is now filled and stored for later
usage during Rx queue creation.
Signed-off-by: NIvan Vecera <ivecera@redhat.com>
Acked-by: NSathya Perla <sathya.perla@avagotech.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When RX/TX interrupt for Network Control queue and Best Effort queue
is issued at the same time, the interrupt mask of Network Control
queue will be reset when the mask of Best Effort queue is set.
This patch fixes this problem.
Signed-off-by: NMasaru Nagai <masaru.nagai.vx@renesas.com>
Signed-off-by: NYoshihiro Kaneko <ykaneko0929@gmail.com>
Acked-by: NGeert Uytterhoeven <geert+renesas@glider.be>
Acked-by: NSimon Horman <horms+renesas@verge.net.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On certain hardware after software reboot the chip may get stuck and fail
to reinitialize during reset. This can be fixed by ensuring that PHY is
reset too.

Old PHY resetting method required operational MDIO interface, therefore
the chip should have been already set up. In order to be able to function
during probe, it is changed to use PMT_CTRL register.

The problem could be observed on SMDK5410 board.
Signed-off-by: NPavel Fedin <p.fedin@samsung.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This adds support for the Vitesse VSC8601 PHY. Generic functions are
used for everything except interrupt handling.
Signed-off-by: NMans Rullgard <mans@mansr.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 77a99394 "phy/at8031: enable at8031 to work on interrupt mode"
added interrupt support for the 8031 PHY but left out the other two
chips supported by this driver.

This patch sets the .ack_interrupt and .config_intr functions for the
8030 and 8035 drivers as well.
Signed-off-by: NMans Rullgard <mans@mansr.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To align with the mv88e6xxx code, use the register defines to
access all the register addresses and bit fields.
Acked-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NNeil Armstrong <narmstrong@baylibre.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To align with the mv88e6xxx code, add a similar header file
with all the register defines.
The file is based on the mv88e6xxx header for coherency.
Acked-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NNeil Armstrong <narmstrong@baylibre.com>
Acked-by: NVivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

According to the mv88e6060 datasheet, the first mac byte must
be at position 9 instead of 8 since the bit 8 is used to select
if the mac address must differ for each port for Pause frames.
Use the correct shift and set the same mac address for all port.
Acked-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NNeil Armstrong <narmstrong@baylibre.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

According to the mv88e6060 datasheet, the MaxFrameSize bit position
is 10 instead of 11 which is reserved.
Use the bit correctly to setup max frame size to 1536.
Acked-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NNeil Armstrong <narmstrong@baylibre.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

According to the mv88e6060 datasheet, the InitReady bit position
is 11 and the polarity is inverted.
Use the bit correctly to detect the end of initialization.
Acked-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NNeil Armstrong <narmstrong@baylibre.com>
Acked-by: NVivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As of mv88e6xxx remove the poll_link callback since the link
state change polling is now handled by the phylib.

Tested on a mv88e6060 B0 device with a TI DM816X SoC.
Suggested-by: NAndrew Lunn <andrew@lunn.ch>
Acked-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NNeil Armstrong <narmstrong@baylibre.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The err variable wasn't set with the correct error value in some cases.

Fixes: 47605df9 ('mlx4: Modify proxy/tunnel QP mechanism [..]')
Signed-off-by: NNoa Osherovich <noaos@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When cleaning slave's counter resources, we hold a spinlock that
protects the slave's counters list. As part of the clean, we call
__mlx4_clear_if_stat which calls mlx4_alloc_cmd_mailbox which is a
sleepable function.

In order to fix this issue, hold the spinlock, and copy all counter
indices into a temporary array, and release the spinlock. Afterwards,
iterate over this array and free every counter. Repeat this scenario
until the original list is empty (a new counter might have been added
while releasing the counters from the temporary array).

Fixes: b72ca7e9 ("net/mlx4_core: Reset counters data when freed")
Reported-by: NMoni Shoua <monis@mellanox.com>
Tested-by: NMoni Shoua <monis@mellanox.com>
Signed-off-by: NJack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: NEran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On xmit path we use skb_frag_dma_map() which is using dma_map_page(),
while upon completion we dma-unmap the skb fragments using
dma_unmap_single() rather than dma_unmap_page().

To fix this, we now save the dma map type on xmit path and use this
info to call the right dma unmap method upon TX completion.
Signed-off-by: NAchiad Shochat <achiad@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

On change mtu the driver compares between hardware queried mtu and
software requested mtu. We need to compare between software
representation of the queried mtu and the requested mtu.

Fixes: facc9699 ('net/mlx5e: Fix HW MTU settings')
Signed-off-by: NDoron Tsur <doront@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Prevent outgoing multicast frames from looping back to the RX queue.

By introducing new HW capability self_lb_en_modifiable, which indicates
the support to modify self_lb_en bit in modify_tir command.

When this capability is set we can prevent TIRs from sending back
loopback multicast traffic to their own RQs, by "refreshing TIRs" with
modify_tir command, on every time new channels (SQs/RQs) are created at
device open.
This is needed since TIRs are static and only allocated once on driver
load, and the loopback decision is under their responsibility.

Fixes issues of the kind:
"IPv6: eth2: IPv6 duplicate address fe80::e61d:2dff:fe5c:f2e9 detected!"
The issue is seen since the IPv6 solicitations multicast messages are
loopedback and the network stack thinks they are coming from another host.

Fixes: 5c50368f ("net/mlx5e: Light-weight netdev open/stop")
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

mlx5e_get_inline_hdr_size didn't take into account the vlan insertion
into the inline WQE segment.
This could lead to max inline violation in cases where
skb_headlen(skb) + VLAN_HLEN >= sq->max_inline.

Fixes: 3ea4891d ("net/mlx5e: Fix LSO vlan insertion")
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>
Signed-off-by: NAchiad Shochat <achiad@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>