As Michael point out, We used to limit the max pending DMAs to get better cache
utilization. But it was not done correctly since it was one done when there's no
new buffers submitted from guest. Guest can easily exceeds the limitation by
keeping sending packets.

So this patch moves the check into main loop. Tests shows about 5%-10%
improvement on per cpu throughput for guest tx.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We used to poll vhost queue before making DMA is done, this is racy if vhost
thread were waked up before marking DMA is done which can result the signal to
be missed. Fix this by always polling the vhost thread before DMA is done.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently, even if the packet length is smaller than VHOST_GOODCOPY_LEN, if
upend_idx != done_idx we still set zcopy_used to true and rollback this choice
later. This could be avoided by determining zerocopy once by checking all
conditions at one time before.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Let vhost_add_used() to use vhost_add_used_n() to reduce the code
duplication. To avoid the overhead brought by __copy_to_user(). We will use
put_user() when one used need to be added.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We tend to batch the used adding and signaling in vhost_zerocopy_callback()
which may result more than 100 used buffers to be updated in
vhost_zerocopy_signal_used() in some cases. So switch to use
vhost_add_used_and_signal_n() to avoid multiple calls to
vhost_add_used_and_signal(). Which means much less times of used index
updating and memory barriers.

2% performance improvement were seen on netperf TCP_RR test.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

None of its caller use its return value, so let it return void.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use the wrapper functions for getting and setting the driver data
using pci_dev instead of using dev_{get,set}_drvdata() with
&pdev->dev, so we can directly pass a struct pci_dev. This is
a purely cosmetic change.
Signed-off-by: NJingoo Han <jg1.han@samsung.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use the wrapper functions for getting and setting the driver data
using pci_dev instead of using dev_{get,set}_drvdata() with
&pdev->dev, so we can directly pass a struct pci_dev. This is
a purely cosmetic change.
Signed-off-by: NJingoo Han <jg1.han@samsung.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use the wrapper functions for getting and setting the driver data
using platform_device instead of using dev_{get,set}_drvdata()
with &pdev->dev, so we can directly pass a struct platform_device.
This is a purely cosmetic change.
Signed-off-by: NJingoo Han <jg1.han@samsung.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use the wrapper functions for getting and setting the driver data
using platform_device instead of using dev_{get,set}_drvdata()
with &pdev->dev, so we can directly pass a struct platform_device.
This is a purely cosmetic change.
Signed-off-by: NJingoo Han <jg1.han@samsung.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use the wrapper functions for getting and setting the driver data
using platform_device instead of using dev_{get,set}_drvdata()
with &pdev->dev, so we can directly pass a struct platform_device.
This is a purely cosmetic change.
Signed-off-by: NJingoo Han <jg1.han@samsung.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This function is being removed, so remove the reference to it.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This function is being removed, rename the reference.
Signed-off-by: NJoe Perches <joe@perches.com>
Acked-by: NAntonio Quartulli <ordex@autistici.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Convert the llc_<foo> static inlines to the
equivalents from etherdevice.h and remove
the llc_<foo> static inline functions.

llc_mac_null -> is_zero_ether_addr
llc_mac_multicast -> is_multicast_ether_addr
llc_mac_match -> ether_addr_equal
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use the new bool function ether_addr_equal to add
some clarity and reduce the likelihood for misuse
of compare_ether_addr for sorting.

Done via cocci script: (and a little typing)

$ cat compare_ether_addr.cocci
@@
expression a,b;
@@
-	!compare_ether_addr(a, b)
+	ether_addr_equal(a, b)

@@
expression a,b;
@@
-	compare_ether_addr(a, b)
+	!ether_addr_equal(a, b)

@@
expression a,b;
@@
-	!ether_addr_equal(a, b) == 0
+	ether_addr_equal(a, b)

@@
expression a,b;
@@
-	!ether_addr_equal(a, b) != 0
+	!ether_addr_equal(a, b)

@@
expression a,b;
@@
-	ether_addr_equal(a, b) == 0
+	!ether_addr_equal(a, b)

@@
expression a,b;
@@
-	ether_addr_equal(a, b) != 0
+	ether_addr_equal(a, b)

@@
expression a,b;
@@
-	!!ether_addr_equal(a, b)
+	ether_addr_equal(a, b)
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NLiu Junliang <liujunliang_ljl@163.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

SkyHawk-R can support VEB or VEPA mode.
This patch will allow the user to set/query this switch setting.
Signed-off-by: NAjit Khaparde <ajit.khaparde@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The name of the function in the comment is __skb_alloc_page() while we
are actually commenting __skb_alloc_pages(). Fix this typo and make it
a valid kernel doc comment.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix the amount of sent bytes reported to BQL by reporting the
number of bytes on wire in the xmit routine, and recording that
value for each skb in order to be correctly confirmed on Tx
confirmation cleanup.

Reporting skb->len to BQL just before exiting xmit is not correct
due to possible insertions of TOE block and alignment bytes in the
skb->data, which are being stripped off by the controller before
transmission on wire.  This led to mismatch of (incorrectly)
reported bytes to BQL b/w xmit and Tx confirmation, resulting in
Tx timeout firing, for the h/w tx timestamping acceleration case.

There's no easy way to obtain the number of bytes on wire in the Tx
confirmation routine, so skb->cb is used to convey that information
from xmit to Tx confirmation, for now (as proposed by Eric). Revived
the currently unused GFAR_CB() construct for that purpose.
Signed-off-by: NClaudiu Manoil <claudiu.manoil@freescale.com>

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When my 'ifup eth' script was fired multiple times and ran concurrent on
my laptop, for some obscure /etc scripting reason, it was revealed
that the store_enabled() function in netconsole doesn't handle it nicely,
as recorded by the Oops below (a syslog paste, but not mangled too much
to prevent from discerning the traceback).

On Linux 3.10.4, this patch seeks to remedy the problem, and it has been
running stable on my laptop for a few days.

[52608.609325] BUG: unable to handle kernel NULL pointer dereference at 00000000000003e0
[52608.609331] IP: [<ffffffff81532a17>] __netpoll_cleanup+0x27/0xe0
[52608.609339] PGD 15e51a067 PUD 15433e067 PMD 0
[52608.609343] Oops: 0000 [#1] SMP re firewire_ohci firewire_core crc_itu_t [last unloaded: kvm_intel]
[52608.609347] Modules linked in: kvm_intel tun vfat fat ppdev parport_pc parport fuse ipt_MASQUERADE usb_storage nf_conntrack_netbios_ns nf_conn [..garbled..]
[52608.609433] RAX: 0000000000000000 RBX: ffff880210bbcc68 RCX: 0000000000000000
[52608.609435] RDX: 0000000000000000 RSI: ffff8801ba447da0 RDI: ffff880210bbcc68
[52608.609437] RBP: ffff8801ba447e18 R08: 0000000000000000 R09: 0000000000000001
[52608.609439] R10: 000000000000000a R11: f000000000000000 R12: ffff880210bbcc68
[52608.609441] R13: ffff88020bc41000 R14: 0000000000000002 R15: 000000000000000200000000000
[52608.609443] FS:  00007f38d7bff740(0000) GS:ffff88021dc40000(0000) knlGS:0000000000000000
[52608.609446] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003300000000001427e0
[52608.609448] CR2: 00000000000003e0 CR3: 0000000154103000 CR4: 00000000001427e0
[52608.609450] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[52608.609452] netpoll: netconsole: local port 6665ess 10.0.0.27
[52608.609454] netpoll: netconsole: local IPv4 address 10.0.0.27
[52608.609456] netpoll: netconsole: interface 'em1'
[52608.609457] netpoll: netconsole: remote port 514ress 10.0.0.15
[52608.609459] netpoll: netconsole: remote IPv4 address 10.0.0.15:65:a8:9a:c7
[52608.609461] netpoll: netconsole: remote ethernet address 1c:6f:65:a8:9a:c7
[52608.609463] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[52608.609464] Stack:801ba447e08 ffff880210bbcc68 ffffffffffffffea ffff88020bc41000
[52608.609466]  ffff8801ba447e08 ffff880210bbcc68 ffffffffffffffea ffff88020bc41000
[52608.609471]  0000000000000002 0000000000000002 ffff8801ba447e38 ffffffff81532af4
[52608.609475]  0000000000000000 ffff880210bbcc00 ffff8801ba447e78 ffffffff81420e7c
[52608.609479] Call Trace:
[52608.609484]  [<ffffffff81532af4>] netpoll_cleanup+0x24/0x50
[52608.609489]  [<ffffffff81420e7c>] store_enabled+0x5c/0xe0
[52608.609492]  [<ffffffff81420abe>] netconsole_target_attr_store+0x2e/0x40
[52608.609498]  [<ffffffff811ff2a2>] configfs_write_file+0xd2/0x130
[52608.609503]  [<ffffffff81188f95>] vfs_write+0xc5/0x1f0
[52608.609506]  [<ffffffff81189482>] SyS_write+0x52/0xa0/0x10
[52608.609511]  [<ffffffff81628c2e>] ? do_page_fault+0xe/0x10
[52608.609516]  [<ffffffff8162d402>] system_call_fastpath+0x16/0x1b
[52608.609517] Code: 1f 44 00 00 0f 1f 44 00 00 55 48 89 e5 48 83 ec 30 4c 89 65 e0 48 89 5d d8 49 89 fc 4c 89 6d e8 4c 89 75 f0 4c 89 7d f8 48 8 [..garbled..]
[52608.609559] RIP  [<ffffffff81532a17>] __netpoll_cleanup+0x27/0xe0
[52608.609563]  RSP <ffff8801ba447de8>
[52608.609564] CR2: 00000000000003e0
[52608.609567] ---[ end trace d25ec343349b61d2 ]---
Signed-off-by: NDan Aloni <alonid@postram.com>
Signed-off-by: NNeil Horman <nhorman@tuxdriver.com>
CC: David S. Miller <davem@davemloft.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This corrects an oversight when r8a7790 support was added to sh_eth.
Signed-off-by: NKouei Abe <kouei.abe.cp@renesas.com>
Signed-off-by: NSimon Horman <horms+renesas@verge.net.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NKouei Abe <kouei.abe.cp@renesas.com>
Signed-off-by: NSimon Horman <horms+renesas@verge.net.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Store VID in ->vlan_id (if any), and remove the useless ->tag.

CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We're using it currently to verify if we have vlans before getting the tag
from the skb we're about to send. It's useless because the vlan_get_tag()
verifies if the skb has the tag (and returns an error if not), and we can
receive tagged skbs only if we *already* have vlans.

Plus, the current RCUed implementation is kind of useless anyway - the we
can remove the last vlan in the moment we return from the function.

So remove the only usage of it and the whole function.

CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: NVeaceslav Falico <vfalico@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Marc Kleine-Budde says:

====================
this is a pull request for net-next. There are two patches from Gerhard
Sittig, which improves the clock handling on mpc5121. Oliver Hartkopp
provides a patch that adds a per rule limitation of frame hops.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

John W. Linville says:

====================
Please accept this batch of updates intended for the 3.12 stream.

For the mac80211 bits, Johannes says this:

"This time I have various improvements all over the place: IBSS, mesh,
testmode, AP client powersave handling, one of the rare rfkill patches
and some code cleanup."

Also for mac80211:

"And I also have some more changes for -next, just a few small fixes and
improvements, nothing really stands out."

And for iwlwifi:

"This time I have some powersave work (notably uAPSD support), CQM
offloads, support for a new firmware API and various code cleanups."

Regarding the Bluetooth bits, Gustavo says:

"Patches to 3.12, here we have:

* implementation of a proper tty_port for RFCOMM devices, this fixes some
issues people were seeing lately in the kernel.
* Add voice_setting option for SCO, it is used for SCO Codec selection
* bugfixes, small improvements and clean ups"

For the NFC bits, Samuel says:

"With this one we have:

- A few pn533 improvements and minor fixes. Testing our pn533 driver
  against Google's NCI stack triggered a few issues that we fixed now.
  We also added Tx fragmentation support to this driver.

- More NFC secure element handling. We added a GET_SE netlink command
  for getting all the discovered secure elements, and we defined 2
  additional secure element netlink event (transaction and connectivity).
  We also fixed a couple of typos and copy-paste bugs from the secure
  element handling code.

- Firmware download support for the pn544 driver. This chipset can enter a
  special mode where it's waiting for firmware blobs to replace the
  already flashed one. We now support that mode."

With repect to the ath tree, Kalle says:

"New features in ath10k are rx/tx checsumming in hw and survey scan
implemented by Michal. Also he made fixes to different areas of the
driver, most notable being fixing the case when using two streams and
reducing the number of interface combinations to avoid firmware crashes.
Bartosz did a clean related to how we handle SoC power save in PCI
layer.

For ath6kl Mohammed and Vasanth sent each a patch to fix two infrequent
crashes."

I also pulled the wireless tree into wireless-next to support a
request from Johannes.  On top of all that, there are the usual
sort of driver updates.  The mwifiex, brcmfmac, brcmsmac, ath9k,
and rt2x00 drivers all get some attention, as does the bcma bus and
a few other random bits here and there.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is a follow-up commit for commit b1dcdc68 ("net: tcp_probe:
allow more advanced ingress filtering by mark") that allows for
advanced SCTP probe module filtering based on skb mark (for a more
detailed description and advantages using mark, refer to b1dcdc68).
The current option to filter by a given port is still being preserved.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Acked-by: NNeil Horman <nhorman@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This config option is superfluous in that it only guards a call
to neigh_app_ns(). Enabling CONFIG_ARPD by default has no
change in behavior. There will now be call to __neigh_notify()
for each ARP resolution, which has no impact unless there is a
user space daemon waiting to receive the notification, i.e.,
the case for which CONFIG_ARPD was designed anyways.
Suggested-by: NEric W. Biederman <ebiederm@xmission.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: James Morris <jmorris@namei.org>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Patrick McHardy <kaber@trash.net>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Gao feng <gaofeng@cn.fujitsu.com>
Cc: Joe Perches <joe@perches.com>
Cc: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: NTim Gardner <tim.gardner@canonical.com>
Reviewed-by: N"Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If the VIRTIO_NET_F_GUEST_CSUM virtio feature is available, the guest
does not have to calculate the checksums on all received packets. This
is pretty much the same feature as RX checksum offloading on real
network cards, so the virtio-net driver should report this by setting
the NETIF_F_RXCSUM flag. When the user now runs "ethtool -k", he or she
can see whether the virtio-net interface has to calculate RX checksums
or not.
Signed-off-by: NThomas Huth <thuth@linux.vnet.ibm.com>
Acked-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Bjørn Mork says:

====================
net: set addr_assign_type when inheriting a dev_addr

Copying the dev_addr from a parent device is an operation
common to a number of drivers. The addr_assign_type should
be updated accordingly, either by reusing the value from
the source device or explicitly indicating that the address
is stolen by setting addr_assign_type to NET_ADDR_STOLEN.

This patch set adds a helper copying both the dev_addr and
the addr_assign_type, and use this helper in drivers which
don't currently set the addr_assign_type. Using NET_ADDR_STOLEN
might be more appropriate in some of these cases.  Please
let me know, and I'll update the patch accordingly.

Changes in v2:
 - assuming addr_len == ETH_ALEN to allow optimized memcpy
 - dropped the vt6656 patch due to addr_len being unset in that driver
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A device inheriting a random or set address should reflect this in
its addr_assign_type.

Cc: Forest Bond <forest@alittletooquiet.net>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Acked-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A device inheriting a random or set address should reflect this in
its addr_assign_type.
Acked-by: NJohn W. Linville <linville@tuxdriver.com>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A device inheriting a random or set address should reflect this in
its addr_assign_type.

Cc: Jouni Malinen <j@w1.fi>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A device inheriting a random or set address should reflect this in
its addr_assign_type.
Acked-by: NJohn W. Linville <linville@tuxdriver.com>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A device inheriting a random or set address should reflect this in
its addr_assign_type.

Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A device inheriting a random or set address should reflect this in
its addr_assign_type.

Cc: Patrick McHardy <kaber@trash.net>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A device inheriting a random or set address should reflect this in
its addr_assign_type.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A device inheriting a random or set address should reflect this in
its addr_assign_type.

Cc: Patrick McHardy <kaber@trash.net>
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some etherdevices inherit their address from a parent or
master device. The addr_assign_type should be updated along
with the address in these cases.  Adding a helper function
to simplify this.
Signed-off-by: NBjørn Mork <bjorn@mork.no>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fengguang reported:

   net/built-in.o: In function `in6_dev_finish_destroy':
   (.text+0x4ca7d): undefined reference to `snmp_mib_free'

this is due to snmp_mib_free() is defined when CONFIG_INET is enabled,
but in6_dev_finish_destroy() is now moved to core kernel.

I think snmp_mib_free() is small enough to be inlined, so just make it
static inline.
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NCong Wang <amwang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>