Add the ixgbe driver code implementing ndo_ll_poll.
Adds ndo_ll_poll method and locking between it and the napi poll.
When receiving a packet we use skb_mark_ll to record the napi it came from.
Add each napi to the napi_hash right after netif_napi_add().
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NEliezer Tamir <eliezer.tamir@linux.intel.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adds low latency socket poll support for TCP.
In tcp_v[46]_rcv() add a call to sk_mark_ll() to copy the napi_id
from the skb to the sk.
In tcp_recvmsg(), when there is no data in the socket we busy-poll.
This is a good example of how to add busy-poll support to more protocols.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NEliezer Tamir <eliezer.tamir@linux.intel.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Tested-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add upport for busy-polling on UDP sockets.
In __udp[46]_lib_rcv add a call to sk_mark_ll() to copy the napi_id
from the skb into the sk.
This is done at the earliest possible moment, right after we identify
which socket this skb is for.
In __skb_recv_datagram When there is no data and the user
tries to read we busy poll.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NEliezer Tamir <eliezer.tamir@linux.intel.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Tested-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adds an ndo_ll_poll method and the code that supports it.
This method can be used by low latency applications to busy-poll
Ethernet device queues directly from the socket code.
sysctl_net_ll_poll controls how many microseconds to poll.
Default is zero (disabled).
Individual protocol support will be added by subsequent patches.
Signed-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NEliezer Tamir <eliezer.tamir@linux.intel.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Tested-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adds a napi_id and a hashing mechanism to lookup a napi by id.
This will be used by subsequent patches to implement low latency
Ethernet device polling.
Based on a code sample by Eric Dumazet.
Signed-off-by: NEliezer Tamir <eliezer.tamir@linux.intel.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Tested-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Newer Broadcom BCM63xx SoCs: 6328, 6362 and 6368 have an integrated switch
which needs to be driven slightly differently from the traditional
external switches. This patch introduces changes in arch/mips/bcm63xx in order
to:

- register a bcm63xx_enetsw driver instead of bcm63xx_enet driver
- update DMA channels configuration & state RAM base addresses
- add a new platform data configuration knob to define the number of
  ports per switch/device and force link on some ports
- define the required switch registers

On the driver side, the following changes are required:

- the switch ports need to be polled to ensure the link is up and
  running and RX/TX can properly work
- basic switch configuration needs to be performed for the switch to
  forward packets to the CPU
- update the MIB counters since the integrated
Signed-off-by: NMaxime Bizon <mbizon@freebox.fr>
Signed-off-by: NJonas Gorski <jogo@openwrt.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The current bcm63xx_enet driver always uses bcmenet_shared_base whenever
it needs to access DMA channel configuration space or access the DMA
channel state RAM. Split these register in 3 parts to be more accurate:

- global DMA configuration
- per DMA channel configuration space
- per DMA channel state RAM space

This is preliminary to support new chips where the global DMA
configuration remains the same, but there is a varying number of DMA
channels located at a different memory offset.
Signed-off-by: NMaxime Bizon <mbizon@freebox.fr>
Signed-off-by: NJonas Gorski <jogo@openwrt.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Implement the rset_nway ethtool callback which uses libphy generic
autonegotiation restart function.
Signed-off-by: NMaxime Bizon <mbizon@freebox.fr>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

To notify the userspace about our capability of multiqueue.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds TUNSETQUEUE ioctl to let userspace can temporarily disable or
enable a queue of macvtap. This is used to be compatible at API layer of tuntap
to simplify the userspace to manage the queues. This is done through introducing
a linked list to track all taps while using vlan->taps array to only track
active taps.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Linear search were used in both get_slot() and macvtap_get_queue(), this is
because:

- macvtap didn't reshuffle the array of taps when create or destroy a queue, so
  when adding a new queue, macvtap must do linear search to find a location for
  the new queue. This will also complicate the TUNSETQUEUE implementation for
  multiqueue API.
- the queue itself didn't track the queue index, so the we must do a linear
  search in the array to find the location of a existed queue.

The solution is straightforward: reshuffle the array and introduce a queue_index
to macvtap_queue.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Macvtap should be at least compatible with tap, so change the max number to 16.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Factor out the device holding logic to a macvtap_get_vlan(), this will be also
used by multiqueue API.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There's no need to add self to waitqueue if doing a nonblock read. This could
help to avoid the spinlock contention.
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Complier may generate codes that re-read the vlan->numvtaps during
macvtap_get_queue(). This may lead a race if vlan->numvtaps were changed in the
same time and which can lead unexpected result (e.g. very huge value).

We need prevent the compiler from generating such codes by adding an
ACCESS_ONCE() to make sure vlan->numvtaps were only read once.
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Don't cast a plain integer to a pointer.

drivers/net/ethernet/renesas/sh_eth.c: In function ‘sh_eth_chip_reset_giga’:
drivers/net/ethernet/renesas/sh_eth.c:482:22: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
drivers/net/ethernet/renesas/sh_eth.c:483:22: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
drivers/net/ethernet/renesas/sh_eth.c:492:22: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
drivers/net/ethernet/renesas/sh_eth.c:493:22: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since dependence on the certain SoCs is no  longer  necessary to compile the
driver, remove the dependency list from its Kconfig entry which is a popular
demand anyway...
Signed-off-by: NSergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Get the R-Car code/data in the driver out of #ifdef by adding "r8a777x-ether" to
the platfrom driver's  ID table; since it's the last #ifdef, we remove CARDNAME
from the  ID table and no longer check  the driver data before  assigning it to
'mdp->cd'...
Change the Ether platform device's name in the ARM platform code accordingly.
Signed-off-by: NSergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Get the SH7724 code/data in the driver out of #ifdef by adding "r8a7724-ether"
to the platform driver's ID table. Change the Ether platform device's name in
the SH platform code accordingly.
Signed-off-by: NSergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Get the SH7757 code/data in the driver out of #ifdef by adding "sh7757-ether"
and "sh7757-gether" to the platform driver's ID table.  Note that we can remove
SH_ETH_HAS_BOTH_MODULES and sh_eth_get_cpu_data().
Change the Ether/GEther platform devices' names in the SH platform code
accordingly.
Signed-off-by: NSergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Get the SH77{34|63} specific code/data in the driver out of #ifdef by adding
"sh7734-gether" and "sh7763-gether" to the platform driver's ID table.  Note
that we have to split the 'struct sh_eth_cpu_data' instance into two due to
#ifdef inside it; note that we can kill the duplicate sh_eth_set_rate_gether().
Change the GEther platform device's name in the SH platform code accordingly.
Signed-off-by: NSergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Get the R8A7740 code/data in the driver out of #ifdef by adding "r8a7740-gether"
to the platform driver's ID table.  Change the GEther platform device's name in
the ARM platform code accordingly.
Signed-off-by: NSergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Get  the SH7619 data in the driver out of #ifdef by adding "sh7619-ether" to the
platform driver's ID table. Change the Ether platform device's name  in  the SH
platform code accordingly.
Signed-off-by: NSergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Get the SH771[02] data in the driver out of #ifdef by adding "sh771x-ether" to
the platform driver's ID table. Change the Ether platform device's name in the
SH platform code accordingly.
Signed-off-by: NSergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We are trying to get away from the current driver's scheme of identifying a SoC
based on #ifdef's and the platform device ID table matching seems to be a good
replacement -- we can use the 'driver_data' field of 'struct platform_device_id'
as a pointer to a 'struct sh_eth_cpu_data'. Start by creating the initial table
with driver's name as the only entry without the driver data. Check  the driver
data in the probe() method and if it's not NULL override 'mdp->cd' from it.
Signed-off-by: NSergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch fixes icmp_ignore_bogus_error_responses default value to be 1 instead
of FALSE. It is initialized to 1 in icmp_sk_init().
Signed-off-by: NRami Rosen <ramirose@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I can hit ENOBUFS in the sendmsg() path with a large batch that is
composed of many netlink messages. Here that limit is 8 MBytes of
skbuff data area as kmalloc does not manage to get more than that.

While discussing atomic rule-set for nftables with Patrick McHardy,
we decided to put all rule-set updates that need to be applied
atomically in one single batch to simplify the existing approach.
However, as explained above, the existing netlink code limits us
to a maximum of ~20000 rules that fit in one single batch without
hitting ENOBUFS. iptables does not have such limitation as it is
using vmalloc.

This patch adds netlink_alloc_large_skb() which is only used in
the netlink_sendmsg() path. It uses alloc_skb if the memory
requested is <= one memory page, that should be the common case
for most subsystems, else vmalloc for higher memory allocations.
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently, if fail_over_mac is set to active, then attempts to
change the MAC of the bond itself silently fail.  However, if fail_over_mac
is set to follow, changes are permitted.

	Permitting the bond's MAC to change with fail_over_mac=follow
will disrupt the follow functionality, which normally controls the
assignment of MAC address to the bond and its slaves, and can cause
multiple ports to be assigned the same MAC address. which will interfere
with the functioning of the device (where the device here is a
virtualization-aware card for s390, qeth).
Signed-off-by: NJay Vosburgh <fubar@us.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch converts bonding to use the dev_uc/mc_sync and
dev_uc/mc_sync_multiple functions for updating the hardware addresses
of bonding slaves.

	The existing functions to add or remove addresses are removed,
and their functionality is replaced with calls to dev_mc_sync or
dev_mc_sync_multiple, depending upon the bonding mode.

	Calls to dev_uc_sync and dev_uc_sync_multiple are also added,
so that unicast addresses added to a bond will be properly synced with
its slaves.

	Various functions are renamed to better reflect the new
situation, and relevant comments are updated.
Signed-off-by: NJay Vosburgh <fubar@us.ibm.com>
Cc: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Passing pdev in fec_ptp_init() is enough, since we can get ndev locally.
Signed-off-by: NFabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Would be good to make things explicit and move those functions to
a new file called tcp_offload.c, thus make this similar to tcpv6_offload.c.
While moving all related functions into tcp_offload.c, we can also
make some of them static, since they are only used there. Also, add
an explicit registration function.
Suggested-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We have the minimal inline helper tcp_skb_mss to access
skb_shinfo(skb)->gso_size, so also use it here to get mss.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove the definition of HAVE_VLAN_PUT_TAG since it's not
used or exported anywhere.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch simplifies the tpacket_v3 example code a bit by getting rid
of unecessary macro wrappers, removing some debugging code so that it is
more to the point, and also adds a header comment. Now this example code
is the very minimum one needs to start from when dealing with tpacket_v3
and ~100 lines smaller than before.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Merge 'net' into 'net-next' to get the MSG_CMSG_COMPAT
regression fix.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Pull networking fix from David Miller:
 "This is a quick one commit pull request to cure the regression
  introduced by the MSG_CMSG_COMPAT change."

(Background: commit 1be374a0 completely broke 32-bit COMPAT handling
by not only disallowing MSG_CMSG_COMPAT from user APIs, but clearing it
in our own internal use too!)

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  net: Unbreak compat_sys_{send,recv}msg

Pull staging driver fixes from Greg Kroah-Hartman:
 "Here are some staging and IIO driver fixes for the 3.10-rc5 release.

  All of them are tiny, and fix a number of reported issues (build and
  runtime)"
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

* tag 'staging-3.10-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging:
  iio:inkern: Fix typo/bug in convert raw to processed.
  iio: frequency: ad4350: Fix bug / typo in mask
  inkern: iio_device_put after incorrect return/goto
  staging: alarm-dev: information leak in alarm_compat_ioctl()
  iio:callback buffer: free the scan_mask
  staging: alarm-dev: information leak in alarm_ioctl()
  drivers: staging: zcache: fix compile error
  staging: dwc2: fix value of dma_mask

Pull tty/serial driver fixes from Greg Kroah-Hartman:
 "Here are some small bugfixes, and one revert, of serial driver issues
  that have been reported"

* tag 'tty-3.10-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty:
  Revert "serial: 8250: Make SERIAL_8250_RUNTIME_UARTS work correctly"
  serial: samsung: enable clock before clearing pending interrupts during init
  serial/imx: disable hardware flow control at startup

Pull USB fixes from Greg Kroah-Hartman:
 "Here are a number of USB bugfixes and new device ids for the 3.10-rc5
  tree.

  Nothing major here, a number of new device ids (and movement from the
  option to the zte_ev driver of a number of ids that we had previously
  gotten wrong, some xhci bugfixes, some usb-serial driver fixes that
  were recently found, some host controller fixes / reverts, and a
  variety of smaller other things"

* tag 'usb-3.10-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb: (29 commits)
  USB: option,zte_ev: move most ZTE CDMA devices to zte_ev
  USB: option: blacklist network interface on Huawei E1820
  USB: whiteheat: fix broken port configuration
  USB: serial: fix TIOCMIWAIT return value
  USB: mos7720: fix hardware flow control
  USB: keyspan: remove unused endpoint-array access
  USB: keyspan: fix bogus array index
  USB: zte_ev: fix broken open
  USB: serial: Add Option GTM681W to qcserial device table.
  USB: Serial: cypress_M8: Enable FRWD Dongle hidcom device
  USB: EHCI: fix regression related to qh_refresh()
  usbfs: Increase arbitrary limit for USB 3 isopkt length
  USB: zte_ev: fix control-message timeouts
  USB: mos7720: fix message timeouts
  USB: iuu_phoenix: fix bulk-message timeout
  USB: ark3116: fix control-message timeout
  USB: mos7840: fix DMA to stack
  USB: mos7720: fix DMA to stack
  USB: visor: fix initialisation of Treo/Kyocera devices
  USB: serial: fix Treo/Kyocera interrrupt-in urb context
  ...