Commit Graph

475607 Commits

Author SHA1 Message Date
Chen Gang
28b5533a6f drivers/net/dsa/Kconfig: Let NET_DSA_BCM_SF2 depend on HAS_IOMEM
NET_DSA_BCM_SF2 need HAS_IOMEM, so depend on it, the related error (with
allmodconfig under um):

    CC [M]  drivers/net/dsa/bcm_sf2.o
  drivers/net/dsa/bcm_sf2.c: In function ‘bcm_sf2_sw_setup’:
  drivers/net/dsa/bcm_sf2.c:487:3: error: implicit declaration of function ‘iounmap’ [-Werror=implicit-function-declaration]
     iounmap(*base);
     ^

Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:52:04 -07:00
Chen Gang
9dc8be2816 drivers/net/can/Kconfig: Let CAN_AT91 depend on HAS_IOMEM
CAN_AT91 needs HAS_IOMEM, so depends on it. The related error (with
allmodconfig under um):

    CC [M]  drivers/net/can/at91_can.o
  drivers/net/can/at91_can.c: In function ‘at91_can_probe’:
  drivers/net/can/at91_can.c:1329:2: error: implicit declaration of function ‘ioremap_nocache’ [-Werror=implicit-function-declaration]
  addr = ioremap_nocache(res->start, resource_size(res));
    ^
  drivers/net/can/at91_can.c:1329:7: warning: assignment makes pointer from integer without a cast [enabled by default]
    addr = ioremap_nocache(res->start, resource_size(res));
         ^
  drivers/net/can/at91_can.c:1384:2: error: implicit declaration of function ‘iounmap’ [-Werror=implicit-function-declaration]
    iounmap(addr);
    ^

Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:52:03 -07:00
David S. Miller
579899a9ea Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next
Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2014-10-02

This series contains updates to fm10k, igb, ixgbe and i40e.

Alex provides two updates to the fm10k driver.  First reduces the buffer
size to 2k for all page sizes, since most frames only have a 1500 MTU
so supporting a buffer size larger than this is somewhat wasteful.
Second fixes an issue where the number of transmit queues was not being
updated, so added the lines necessary to update the number of transmit
queues.

Rick Jones provides two patches to convert ixgbe, igb and i40e to use
dev_consume_skb_any().

Emil provides two patches for ixgbe, first cleans up a couple of wait
loops on auto-negotiation that were not needed.  Second fixes an issue
reported by Fujitsu/Red Hat, which consolidates the logic behind the
dynamically setting of TXDCTL.WTHRESH depending on interrupt throttle
rate (ITR) setting regardless of BQL.

Ethan Zhao provides a cleanup patch for ixgbe where he noticed a
duplicate define.

Bernhard Kaindl provides a patch for igb to remove a source of latency
spikes by not calling code that uses mdelay() for feeding a PHY stat
while being called with a spinlock held.

Todd bumps the igb version based on the recent changes.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:43:50 -07:00
David S. Miller
48fea861c9 Merge branch 'mlx5-next'
Eli Cohen says:

====================
mlx5 update for 3.18

This series integrates a new mechanism for populating and extracting field values
used in the driver/firmware interaction around command mailboxes.

Changes from V1:
 - Remove unused definition of memcpy_cpu_to_be32()
 - Remove definitions of non_existent_*() and use BUILD_BUG_ON() instead.
 - Added a patch one line patch to add support for ConnectX-4 devices.

Changes from V0:
 - trimmed the auto-generated file to a minimum, as required by the reviewers.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:42:37 -07:00
Eli Cohen
f832dc820f net/mlx5_core: Add ConnectX-4 to list of supported devices
Add the upcoming ConnectX-4 device to the list of supported devices by then
mlx5 driver.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:42:32 -07:00
Eli Cohen
5903325a64 net/mlx5_core: Identify resources by their type
This patch puts a common part as the first field of mlx5_core_qp. This field is
used to identify which resource generated an event. This is required since upcoming
new resource types such as DC targets are allocated for the same numerical space
as regular QPs and may generate the same events. By searching the resource in the
same table we can then look at the common field to identify the resource.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:42:32 -07:00
Eli Cohen
b775516b04 net/mlx5_core: use set/get macros in device caps
Transform device capabilities related commands to use set/get macros to
manipulate command mailboxes.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:42:32 -07:00
Eli Cohen
d29b796ada net/mlx5_core: Use hardware registers description header file
Add an auto generated header file that describes hardware registers along with
set of macros that set/get values. The macros do static checks to avoid
overflow, handle endianess, and overall provide a clean way to code commands.
Currently the header file is small and we will add structs as we make use of
the macros.
A few commands were removed from the commands enum since they are not supported
currently and will be added when support is available.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:42:31 -07:00
Eli Cohen
c7a08ac7ee net/mlx5_core: Update device capabilities handling
Rearrange struct mlx5_caps so it has a "gen" field to represent the current
capabilities configured for the device. Max capabilities can also be queried
from the device. Also update capabilities struct to contain more fields as per
the latest revision if firmware specification.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:42:31 -07:00
hayeswang
ea6a7112d8 r8152: autoresume before setting MAC address
Resume the device before setting the MAC address.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:40:28 -07:00
Michel Stam
3cc81d85ee asix: Don't reset PHY on if_up for ASIX 88772
I've noticed every time the interface is set to 'up,', the kernel
reports that the link speed is set to 100 Mbps/Full Duplex, even
when ethtool is used to set autonegotiation to 'off', half
duplex, 10 Mbps.
It can be tested by:
 ifconfig eth0 down
 ethtool -s eth0 autoneg off speed 10 duplex half
 ifconfig eth0 up

Then checking 'dmesg' for the link speed.

Signed-off-by: Michel Stam <m.stam@fugro.nl>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:38:49 -07:00
Eric Dumazet
55a93b3ea7 qdisc: validate skb without holding lock
Validation of skb can be pretty expensive :

GSO segmentation and/or checksum computations.

We can do this without holding qdisc lock, so that other cpus
can queue additional packets.

Trick is that requeued packets were already validated, so we carry
a boolean so that sch_direct_xmit() can validate a fresh skb list,
or directly use an old one.

Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads
host.

Turning TSO on or off had no effect on throughput, only few more cpu
cycles. Lock contention on qdisc lock disappeared.

Same if disabling TX checksum offload.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:36:11 -07:00
Tobias Klauser
6a05880a8b net: ethernet: Remove superfluous ether_setup after alloc_etherdev
There is no need to call ether_setup after alloc_ethdev since it was
already called there.

Follow commits c706471b26 ("net: axienet: remove unnecessary
ether_setup after alloc_etherdev") and 3c87dcbfb3 ("net: ll_temac:
Remove unnecessary ether_setup after alloc_etherdev") and fix the
pattern in all remaining ethernet drivers.

Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 15:31:40 -07:00
Joe Perches
906d201530 dynamic_debug: change __dynamic_<foo>_dbg return types to void
The return value is not used by callers of these functions
so change the functions to return void.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-03 14:55:48 -07:00
Yasuaki Ishimatsu
33ead538f6 driver/base/node: remove unnecessary kfree of node struct from unregister_one_node
Commit 92d585ef06 ("numa: fix NULL pointer access and memory
leak in unregister_one_node()") added kfree() of node struct in
unregister_one_node(). But node struct is freed by node_device_release()
which is called in  unregister_node(). So by adding the kfree(),
node struct is freed two times.

While hot removing memory, the commit leads the following BUG_ON():

  kernel BUG at mm/slub.c:3346!
  invalid opcode: 0000 [#1] SMP
  [...]
  Call Trace:
   [...] unregister_one_node
   [...] try_offline_node
   [...] remove_memory
   [...] acpi_memory_device_remove
   [...] acpi_bus_trim
   [...] acpi_bus_trim
   [...] acpi_device_hotplug
   [...] acpi_hotplug_work_fn
   [...] process_one_work
   [...] worker_thread
   [...] ? rescuer_thread
   [...] kthread
   [...] ? kthread_create_on_node
   [...] ret_from_fork
   [...] ? kthread_create_on_node

This patch removes unnecessary kfree() from unregister_one_node().

Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Xishi Qiu <qiuxishi@huawei.com>
Cc: stable@vger.kernel.org # v3.16+
Fixes: 92d585ef06 "numa: fix NULL pointer access and memory leak in unregister_one_node()"
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-03 14:55:48 -07:00
Paul Bolle
4ed9a3d455 USB: host: st: fix typo 'CONFIG_USB_EHCI_HCD_ST'
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Fixes: 905e300e10 ("USB: host: st: fix ehci/ohci driver selection")
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-03 14:50:10 -07:00
Hans de Goede
2d75b9cbb1 uas: Reduce number of function arguments for uas_alloc_foo functions
The stream_id and pipe are already present in uas_cmd_info resp uas_dev_info,
so there is no need to pass a copy along.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-03 14:46:22 -07:00
Andrew Bresticker
29e409f0f7 xhci: Allow xHCI drivers to be built as separate modules
Instead of building all of the xHCI code into a single module, separate
it out into the core (xhci-hcd), PCI (xhci-pci, now selected by the new
config option CONFIG_USB_XHCI_PCI), and platform (xhci-plat) drivers.
Also update the PCI/platform drivers with module descriptions/licenses
and have them register their respective drivers in their initcalls.

Signed-off-by: Andrew Bresticker <abrestic@chromium.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-03 14:44:45 -07:00
Andrew Bresticker
436e8c7d45 xhci: Export symbols used by host-controller drivers
In preparation for allowing the xHCI host controller drivers to be built
as separate modules, export symbols from the xHCI core that may be used
by the host controller drivers.

Signed-off-by: Andrew Bresticker <abrestic@chromium.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-03 14:44:45 -07:00
Andrew Bresticker
e1cd972741 xhci: Check for XHCI_COMP_MODE_QUIRK when disabling D3cold
Instead of calling xhci_compliance_mode_recovery_timer_quirk_check() again
in the PCI suspend path, just check for XHCI_COMP_MODE_QUIRK which will
have been set based on xhci_compliance_mode_recovery_timer_quirk_check()
in xhci_init().

Signed-off-by: Andrew Bresticker <abrestic@chromium.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-03 14:44:45 -07:00
Andrew Bresticker
1885d9a337 xhci: Introduce xhci_init_driver()
Since the struct hc_driver is mostly the same across the xhci-pci,
xhci-plat, and the upcoming xhci-tegra driver, introduce the function
xhci_init_driver() which will populate the hc_driver with the default
xHCI operations.  The caller must supply a setup function which will
be used as the hc_driver's reset callback.

Note that xhci-plat also overrides the default ->start() callback so
that it can do rcar-specific initialization.

Signed-off-by: Andrew Bresticker <abrestic@chromium.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-03 14:44:45 -07:00
Linus Torvalds
126d4576cb Merge branch 'i2c/for-current' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux
Pull i2c fixes from Wolfram Sang:
 "Two i2c driver bugfixes"

* 'i2c/for-current' of git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux:
  i2c: qup: Fix order of runtime pm initialization
  i2c: rk3x: fix 0 length write transfers
2014-10-03 14:20:44 -07:00
Mark Einon
e603984823 staging: et131x: Remove et131x driver from drivers/staging
The current version of the et131x driver has been accepted into the
main tree at /drivers/net/ethernet, so it can now be removed from
staging.

The MAINTAINERS entry has not been touched here, as the patch to
add the driver to drivers/net modifies it correctly.

Signed-off-by: Mark Einon <mark.einon@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-10-03 13:55:14 -07:00
Linus Torvalds
039001972a While testing some new changes for 3.18, I kept hitting a bug every so
often in the ring buffer. At first I thought it had to do with some
 of the changes I was working on, but then testing something else I
 realized that the bug was in 3.17 itself. I ran several bisects as the
 bug was not very reproducible, and finally came up with the commit
 that I could reproduce easily within a few minutes, and without the change
 I could run the tests over an hour without issue. The change fit the
 bug and I figured out a fix. That bad commit was:
 
 Commit 651e22f270 "ring-buffer: Always reset iterator to reader page"
 
 This commit fixed a bug, but in the process created another one. It used
 the wrong value as the cached value that is used to see if things changed
 while an iterator was in use. This made it look like a change always
 happened, and could cause the iterator to go into an infinite loop.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJULvrkAAoJEKQekfcNnQGuD+sH/iHPE2qb2ojCP9+hqOpszdd1
 d8rN8BNZsDlJxfWQELw2vGVXTmeW7txW5DFWQ3I8qSSjwYa6l27M4mHsw2QLagtw
 kIrcazis3IAcYCH8OE4ruD5nAGYLFqRIt0MOa/NAJD0r00xM7nvOhII2+6uAXF+A
 1JbQDRq8eleCKMUMV0XchqWx6pYTXL8cLh1YEXZ0BTUFKIz+y22HjWnMf+odDhLB
 okQic67/+i7mJDAAW4U+pyevd0QBZdDOohjQtbj+irv2pb7WtWqylKcYhAYSpgsy
 MtPzzYyPDs/aHLNcnIJVdVtbKfNXsaHuCgEvKKgLXnKMMcS5UxSIxj+Q1IxSIOM=
 =B7HS
 -----END PGP SIGNATURE-----

Merge tag 'trace-fixes-v3.17-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull trace ring buffer iterator fix from Steven Rostedt:
 "While testing some new changes for 3.18, I kept hitting a bug every so
  often in the ring buffer.  At first I thought it had to do with some
  of the changes I was working on, but then testing something else I
  realized that the bug was in 3.17 itself.  I ran several bisects as
  the bug was not very reproducible, and finally came up with the commit
  that I could reproduce easily within a few minutes, and without the
  change I could run the tests over an hour without issue.  The change
  fit the bug and I figured out a fix.  That bad commit was:

    Commit 651e22f270 "ring-buffer: Always reset iterator to reader page"

  This commit fixed a bug, but in the process created another one.  It
  used the wrong value as the cached value that is used to see if things
  changed while an iterator was in use.  This made it look like a change
  always happened, and could cause the iterator to go into an infinite
  loop"

* tag 'trace-fixes-v3.17-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
  ring-buffer: Fix infinite spin in reading buffer
2014-10-03 13:31:57 -07:00
Linus Torvalds
7d1419f30c Merge branch 'for-linus' of git://git.samba.org/sfrench/cifs-2.6
Pull cifs/smb3 fixes from Steve French:
 "Fix for CIFS/SMB3 oops on reconnect during readpages (3.17 regression)
  and for incorrectly closing file handle in symlink error cases"

* 'for-linus' of git://git.samba.org/sfrench/cifs-2.6:
  CIFS: Fix readpages retrying on reconnects
  Fix problem recognizing symlinks
2014-10-03 13:09:57 -07:00
David S. Miller
fba7516303 Merge branch 'rds-net'
Herton R. Krzesinski says:

====================
Small fixes/changes for RDS

I got a report of one issue within RDS (after investigation it was a double
free), and I'm sending the fix (patch 3/3) which reporter said it works (no more
WARNING triggered on a specially instrumented kernel). The report/test was done
on a very old kernel (RHEL 5, 2.6.18 based with backports), but the problem the
patch handles still exists and should not change. Besides that, while
reviewing some of the code but being unable to reproduce with rds_tcp, I
noticed two small improvements/fixes which are in patches 1 and 2.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 12:52:19 -07:00
Herton R. Krzesinski
593cbb3ec6 net/rds: fix possible double free on sock tear down
I got a report of a double free happening at RDS slab cache. One
suspicion was that may be somewhere we were doing a sock_hold/sock_put
on an already freed sock. Thus after providing a kernel with the
following change:

 static inline void sock_hold(struct sock *sk)
 {
-       atomic_inc(&sk->sk_refcnt);
+       if (!atomic_inc_not_zero(&sk->sk_refcnt))
+               WARN(1, "Trying to hold sock already gone: %p (family: %hd)\n",
+                       sk, sk->sk_family);
 }

The warning successfuly triggered:

Trying to hold sock already gone: ffff81f6dda61280 (family: 21)
WARNING: at include/net/sock.h:350 sock_hold()
Call Trace:
<IRQ>  [<ffffffff8adac135>] :rds:rds_send_remove_from_sock+0xf0/0x21b
[<ffffffff8adad35c>] :rds:rds_send_drop_acked+0xbf/0xcf
[<ffffffff8addf546>] :rds_rdma:rds_ib_recv_tasklet_fn+0x256/0x2dc
[<ffffffff8009899a>] tasklet_action+0x8f/0x12b
[<ffffffff800125a2>] __do_softirq+0x89/0x133
[<ffffffff8005f30c>] call_softirq+0x1c/0x28
[<ffffffff8006e644>] do_softirq+0x2c/0x7d
[<ffffffff8006e4d4>] do_IRQ+0xee/0xf7
[<ffffffff8005e625>] ret_from_intr+0x0/0xa
<EOI>

Looking at the call chain above, the only way I think this would be
possible is if somewhere we already released the same socket->sock which
is assigned to the rds_message at rds_send_remove_from_sock. Which seems
only possible to happen after the tear down done on rds_release.

rds_release properly calls rds_send_drop_to to drop the socket from any
rds_message, and some proper synchronization is in place to avoid race
with rds_send_drop_acked/rds_send_remove_from_sock. However, I still see
a very narrow window where it may be possible we touch a sock already
released: when rds_release races with rds_send_drop_acked, we check
RDS_MSG_ON_CONN to avoid cleanup on the same rds_message, but in this
specific case we don't clear rm->m_rs. In this case, it seems we could
then go on at rds_send_drop_to and after it returns, the sock is freed
by last sock_put on rds_release, with concurrently we being at
rds_send_remove_from_sock; then at some point in the loop at
rds_send_remove_from_sock we process an rds_message which didn't have
rm->m_rs unset for a freed sock, and a possible sock_hold on an sock
already gone at rds_release happens.

This hopefully address the described condition above and avoids a double
free on "second last" sock_put. In addition, I removed the comment about
socket destruction on top of rds_send_drop_acked: we call rds_send_drop_to
in rds_release and we should have things properly serialized there, thus
I can't see the comment being accurate there.

Signed-off-by: Herton R. Krzesinski <herton@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 12:52:00 -07:00
Herton R. Krzesinski
eb74cc97b8 net/rds: do proper house keeping if connection fails in rds_tcp_conn_connect
I see two problems if we consider the sock->ops->connect attempt to fail in
rds_tcp_conn_connect. The first issue is that for example we don't remove the
previously added rds_tcp_connection item to rds_tcp_tc_list at
rds_tcp_set_callbacks, which means that on a next reconnect attempt for the
same rds_connection, when rds_tcp_conn_connect is called we can again call
rds_tcp_set_callbacks, resulting in duplicated items on rds_tcp_tc_list,
leading to list corruption: to avoid this just make sure we call
properly rds_tcp_restore_callbacks before we exit. The second issue
is that we should also release the sock properly, by setting sock = NULL
only if we are returning without error.

Signed-off-by: Herton R. Krzesinski <herton@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 12:51:59 -07:00
Herton R. Krzesinski
310886dd5f net/rds: call rds_conn_drop instead of open code it at rds_connect_complete
Signed-off-by: Herton R. Krzesinski <herton@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 12:51:59 -07:00
David S. Miller
c2bf5ec204 Merge branch 'qdisc_bulk_dequeue'
Jesper Dangaard Brouer says:

====================
qdisc: bulk dequeue support

This patchset uses DaveM's recent API changes to dev_hard_start_xmit(),
from the qdisc layer, to implement dequeue bulking.

Patch01: "qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"
 - Implement basic qdisc dequeue bulking
 - This time, 100% relying on BQL limits, no magic safe-guard constants

Patch02: "qdisc: dequeue bulking also pickup GSO/TSO packets"
 - Extend bulking to bulk several GSO/TSO packets
 - Seperate patch, as it introduce a small regression, see test section.

We do have a patch03, which exports a userspace tunable as a BQL
tunable, that can byte-cap or disable the bulking/bursting.  But we
could not agree on it internally, thus not sending it now.  We
basically strive to avoid adding any new userspace tunable.

Testing patch01:
================
 Demonstrating the performance improvement of qdisc dequeue bulking, is
tricky because the effect only "kicks-in" once the qdisc system have a
backlog. Thus, for a backlog to form, we need either 1) to exceed wirespeed
of the link or 2) exceed the capability of the device driver.

For practical use-cases, the measureable effect of this will be a
reduction in CPU usage

01-TCP_STREAM:
--------------
Testing effect for TCP involves disabling TSO and GSO, because TCP
already benefit from bulking, via TSO and especially for GSO segmented
packets.  This patch view TSO/GSO as a seperate kind of bulking, and
avoid further bulking of these packet types.

The measured perf diff benefit (at 10Gbit/s) for a single netperf
TCP_STREAM were 9.24% less CPU used on calls to _raw_spin_lock()
(mostly from sch_direct_xmit).

If my E5-2695v2(ES) CPU is tuned according to:
 http://netoptimizer.blogspot.dk/2014/04/basic-tuning-for-network-overload.html
Then it is possible that a single netperf TCP_STREAM, with GSO and TSO
disabled, can utilize all bandwidth on a 10Gbit/s link.  This will
then cause a standing backlog queue at the qdisc layer.

Trying to pressure the system some more CPU util wise, I'm starting
24x TCP_STREAMs and monitoring the overall CPU utilization.  This
confirms bulking saves CPU cycles when it "kicks-in".

Tool mpstat, while stressing the system with netperf 24x TCP_STREAM, shows:
 * Disabled bulking: sys:2.58%  soft:8.50%  idle:88.78%
 * Enabled  bulking: sys:2.43%  soft:7.66%  idle:89.79%

02-UDP_STREAM
-------------
The measured perf diff benefit for UDP_STREAM were 6.41% less CPU used
on calls to _raw_spin_lock().  24x UDP_STREAM with packet size -m 1472 (to
avoid sending UDP/IP fragments).

03-trafgen driver test
----------------------
The performance of the 10Gbit/s ixgbe driver is limited due to
updating the HW ring-queue tail-pointer on every packet.  As
previously demonstrated with pktgen.

Using trafgen to send RAW frames from userspace (via AF_PACKET), and
forcing it through qdisc path (with option --qdisc-path and -t0),
sending with 12 CPUs.

I can demonstrate this driver layer limitation:
 * 12.8 Mpps with no qdisc bulking
 * 14.8 Mpps with qdisc bulking (full 10G-wirespeed)

Testing patch02:
================
Testing Bulking several GSO/TSO packets:

Measuring HoL (Head-of-Line) blocking for TSO and GSO, with
netperf-wrapper. Bulking several TSO show no performance regressions
(requeues were in the area 32 requeues/sec for 10G while transmitting
approx 813Kpps).

Bulking several GSOs does show small regression or very small
improvement (requeues were in the area 8000 requeues/sec, for 10G
while transmitting approx 813Kpps).

 Using ixgbe 10Gbit/s with GSO bulking, we can measure some additional
latency. Base-case, which is "normal" GSO bulking, sees varying
high-prio queue delay between 0.38ms to 0.47ms.  Bulking several GSOs
together, result in a stable high-prio queue delay of 0.50ms.

Corrosponding to:
 (10000*10^6)*((0.50-0.47)/10^3)/8 = 37500 bytes
 (10000*10^6)*((0.50-0.38)/10^3)/8 = 150000 bytes
 37500/1500  = 25 pkts
 150000/1500 = 100 pkts

 Using igb at 100Mbit/s with GSO bulking, shows an improvement.
Base-case sees varying high-prio queue delay between 2.23ms to 2.35ms
diff of 0.12ms corrosponding to 1500 bytes at 100Mbit/s. Bulking
several GSOs together, result in a stable high-prio queue delay of
2.23ms.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 12:37:23 -07:00
Jesper Dangaard Brouer
808e7ac0bd qdisc: dequeue bulking also pickup GSO/TSO packets
The TSO and GSO segmented packets already benefit from bulking
on their own.

The TSO packets have always taken advantage of the only updating
the tailptr once for a large packet.

The GSO segmented packets have recently taken advantage of
bulking xmit_more API, via merge commit 53fda7f7f9 ("Merge
branch 'xmit_list'"), specifically via commit 7f2e870f2a ("net:
Move main gso loop out of dev_hard_start_xmit() into helper.")
allowing qdisc requeue of remaining list.  And via commit
ce93718fb7 ("net: Don't keep around original SKB when we
software segment GSO frames.").

This patch allow further bulking of TSO/GSO packets together,
when dequeueing from the qdisc.

Testing:
 Measuring HoL (Head-of-Line) blocking for TSO and GSO, with
netperf-wrapper. Bulking several TSO show no performance regressions
(requeues were in the area 32 requeues/sec).

Bulking several GSOs does show small regression or very small
improvement (requeues were in the area 8000 requeues/sec).

 Using ixgbe 10Gbit/s with GSO bulking, we can measure some additional
latency. Base-case, which is "normal" GSO bulking, sees varying
high-prio queue delay between 0.38ms to 0.47ms.  Bulking several GSOs
together, result in a stable high-prio queue delay of 0.50ms.

 Using igb at 100Mbit/s with GSO bulking, shows an improvement.
Base-case sees varying high-prio queue delay between 2.23ms to 2.35ms

Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 12:37:06 -07:00
Jesper Dangaard Brouer
5772e9a346 qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE
Based on DaveM's recent API work on dev_hard_start_xmit(), that allows
sending/processing an entire skb list.

This patch implements qdisc bulk dequeue, by allowing multiple packets
to be dequeued in dequeue_skb().

The optimization principle for this is two fold, (1) to amortize
locking cost and (2) avoid expensive tailptr update for notifying HW.
 (1) Several packets are dequeued while holding the qdisc root_lock,
amortizing locking cost over several packet.  The dequeued SKB list is
processed under the TXQ lock in dev_hard_start_xmit(), thus also
amortizing the cost of the TXQ lock.
 (2) Further more, dev_hard_start_xmit() will utilize the skb->xmit_more
API to delay HW tailptr update, which also reduces the cost per
packet.

One restriction of the new API is that every SKB must belong to the
same TXQ.  This patch takes the easy way out, by restricting bulk
dequeue to qdisc's with the TCQ_F_ONETXQUEUE flag, that specifies the
qdisc only have attached a single TXQ.

Some detail about the flow; dev_hard_start_xmit() will process the skb
list, and transmit packets individually towards the driver (see
xmit_one()).  In case the driver stops midway in the list, the
remaining skb list is returned by dev_hard_start_xmit().  In
sch_direct_xmit() this returned list is requeued by dev_requeue_skb().

To avoid overshooting the HW limits, which results in requeuing, the
patch limits the amount of bytes dequeued, based on the drivers BQL
limits.  In-effect bulking will only happen for BQL enabled drivers.

Small amounts for extra HoL blocking (2x MTU/0.24ms) were
measured at 100Mbit/s, with bulking 8 packets, but the
oscillating nature of the measurement indicate something, like
sched latency might be causing this effect. More comparisons
show, that this oscillation goes away occationally. Thus, we
disregard this artifact completely and remove any "magic" bulking
limit.

For now, as a conservative approach, stop bulking when seeing TSO and
segmented GSO packets.  They already benefit from bulking on their own.
A followup patch add this, to allow easier bisect-ability for finding
regressions.

Jointed work with Hannes, Daniel and Florian.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 12:37:06 -07:00
Mark Einon
38df6492eb et131x: Add PCIe gigabit ethernet driver et131x to drivers/net
This adds the ethernet driver for Agere et131x devices to
drivers/net/ethernet.

The driver being added has been in the staging tree for some time, and will be
removed from there in a seperate patch. This one merely disables the staging
version to prevent two instances being built.

Signed-off-by: Mark Einon <mark.einon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-03 12:22:19 -07:00
Dmitry Torokhov
447a8b858e Merge branch 'next' into for-linus
Prepare first round of input updates for 3.18.
2014-10-03 11:24:46 -07:00
Linus Torvalds
ee042ec880 One fix for raid5 discard issue.
-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIVAwUAVC40bznsnt1WYoG5AQJs0w//T8Z3vBhXwC3SjREbH42x8pWxFXgzhUdW
 WGKwYYwHFQfL05rP3eg+X+Sh+X3s3E3/+lFzDVE/JGjBdSG/A5X+j5jRH6ENl16u
 32wQjZwKliYxSiUPWbbPzl0BDi3nyhpR1CMsgTWpU6qkMuGy2npNZFK/cQIy4/Je
 ygXLwncKPfAVszaMrx9oBeghpwTnJR3Se1RAYhxc4qQLm+jXfUTQ9Ool3J2InZo3
 st7weyuvPrtr+Em65ta0j/VIOzTP5dIallq+LSL5e0lhn5Pc99XBaM60lEzH9mwP
 t8ZDuV6HL8rXktCOwNtkmEQeW/7uOpmwKG0yt6nPFKghsclJvbyrtxOWKnOrPAd8
 0rvUAX7EXX/OQyEjguhJQ1ZK9E4HxglGay7trVyXeLdK3kOUaVjAlG/5y8FrEusU
 K/uOnHwIiCDxTZ86imTcRcXxOG5eWVscsWwVFIHf2IN4J1NKJ7rQB6LP4WEKzHGE
 y3CgSy/c7yyuksMlYZE9q1GRc5i8pI5tGg3tV2S2uvgjuNIw6dkAF1UjW5Mpgy3x
 OFue/SxsYWuBeSqMANuJQDeCOLttwSZV/Ho3Kac+nA7l0LTXkVIYFj0bSGIIUxjI
 scF+r04u35/jib0QALdeTw9FB46V5GYZ7d0bd/lEMxe24dsPreCKiI/xDvpr5NQn
 8flYcaBK+PI=
 =Qyea
 -----END PGP SIGNATURE-----

Merge tag 'md/3.17-final-fix' of git://neil.brown.name/md

Pull raid5 discard fix from Neil Brown:
 "One fix for raid5 discard issue"

* tag 'md/3.17-final-fix' of git://neil.brown.name/md:
  md/raid5: disable 'DISCARD' by default due to safety concerns.
2014-10-03 08:40:37 -07:00
Mark Brown
a2285b8c75 Merge remote-tracking branch 'spi/topic/xilinx' into spi-next 2014-10-03 16:33:44 +01:00
Mark Brown
bab4d751f7 Merge remote-tracking branches 'spi/topic/pl022', 'spi/topic/pxa2xx', 'spi/topic/rspi', 'spi/topic/sh-msiof' and 'spi/topic/sirf' into spi-next 2014-10-03 16:33:42 +01:00
Mark Brown
899d81b974 Merge remote-tracking branches 'spi/topic/fsl-dspi', 'spi/topic/imx', 'spi/topic/mxs', 'spi/topic/omap-100k' and 'spi/topic/orion' into spi-next 2014-10-03 16:33:41 +01:00
Mark Brown
7020d76971 Merge remote-tracking branches 'spi/topic/davinci', 'spi/topic/doc', 'spi/topic/dw' and 'spi/topic/fsl' into spi-next 2014-10-03 16:33:39 +01:00
Mark Brown
1fc8450313 Merge remote-tracking branches 'spi/topic/bcm53xx', 'spi/topic/cadence', 'spi/topic/checkpatch' and 'spi/topic/clps711x' into spi-next 2014-10-03 16:33:37 +01:00
Mark Brown
613c44798f Merge remote-tracking branch 'spi/topic/dma-dep' into spi-next 2014-10-03 16:33:37 +01:00
Mark Brown
ad71f40a83 Merge remote-tracking branch 'spi/topic/core' into spi-next 2014-10-03 16:33:37 +01:00
Mark Brown
62d02e41ea Merge remote-tracking branch 'spi/fix/rockchip' into spi-linus 2014-10-03 16:33:35 +01:00
Linus Torvalds
80ad99da8b Merge branch 'drm-fixes' of git://people.freedesktop.org/~airlied/linux
Pull drm fixes from Dave Airlie:
 "Nothing too major or scary.

  One i915 regression fix, nouveau has a tmds regression fix, along with
  a regression fix for the runtime pm code for optimus laptops not
  restoring the display hw correctly"

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
  drm/nouveau: make sure display hardware is reinitialised on runtime resume
  drm/nouveau: punt fbcon resume out to a workqueue
  drm/nouveau: fix regression on original nv50 board
  drm/nv50/disp: fix dpms regression on certain boards
  drm/i915: Flush the PTEs after updating them before suspend
2014-10-03 08:31:14 -07:00
Geoff Levand
0a6479b0ff arm64: Remove unneeded extern keyword
Function prototypes are never definitions, so remove any 'extern' keyword
from the funcion prototypes in cpu_ops.h. Fixes warnings emited by
checkpatch.

Signed-off-by: Geoff Levand <geoff@infradead.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-10-03 14:51:02 +01:00
Michael Opdenacker
0415447aa3 Documentation: fix broken v4l-utils URL
This replaces http://git.linuxtv.org/v4l-utils/ (broken link)
by http://git.linuxtv.org/cgit.cgi/v4l-utils.git/

Signed-off-by: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2014-10-03 15:49:57 +02:00
Uwe Kleine-König
c8fdd497a4 ARM64: make of_device_ids const
of_device_ids (i.e. compatible strings and the respective data) are not
supposed to change at runtime. All functions working with of_device_ids
provided by <linux/of.h> work with const of_device_ids. So mark the
only non-const struct in arch/arm64 as const, too.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-10-03 14:49:28 +01:00
Peter Foley
7b345771ba Documentation: update include path for mpssd
sysfs.c includes mpssd.h which includes virtio_ids.h.
sysfs.c doesn't have the proper include flags set to use the latest
headers, so this causes a build error if the system headers are too old.

Signed-off-by: Peter Foley <pefoley2@pefoley.com>
Cc: rdunlap@infradead.org
Cc: linux-doc@vger.kernel.org
Cc: sudeep.dutt@intel.com
Cc: nikhil.rao@intel.com
Cc: ashutosh.dixit@intel.com
Cc: akpm@linux-foundation.org
Cc: gregkh@linuxfoundation.org
Cc: harshavardhan.r.kharche@intel.com
Cc: caz.yokoyama@intel.com
Cc: dasaratharaman.chandramouli@intel.com
Cc: jkosina@suse.cz
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2014-10-03 15:48:20 +02:00
Arturo Borrero
8da4cc1b10 netfilter: nft_masq: register/unregister notifiers on module init/exit
We have to register the notifiers in the masquerade expression from
the the module _init and _exit path.

This fixes crashes when removing the masquerade rule with no
ipt_MASQUERADE support in place (which was masking the problem).

Fixes: 9ba1f72 ("netfilter: nf_tables: add new nft_masq expression")
Signed-off-by: Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2014-10-03 14:24:35 +02:00
Michael Heimpold
a44619c31c spi: spi-mxs: fix a tiny typo in a comment
Signed-off-by: Michael Heimpold <mhei@heimpold.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
2014-10-03 10:33:57 +01:00