dev_queue_xmit enqueue's a skb and calls qdisc_run which
dequeue's the skb and xmits it. In most cases, the skb that
is enqueue'd is the same one that is dequeue'd (unless the
queue gets stopped or multiple cpu's write to the same queue
and ends in a race with qdisc_run). For default qdiscs, we
can remove the redundant enqueue/dequeue and simply xmit the
skb since the default qdisc is work-conserving.
The patch uses a new flag - TCQ_F_CAN_BYPASS to identify the
default fast queue. The controversial part of the patch is
incrementing qlen when a skb is requeued - this is to avoid
checks like the second line below:
+ } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
>> !q->gso_skb &&
+ !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) {
Results of a 2 hour testing for multiple netperf sessions (1,
2, 4, 8, 12 sessions on a 4 cpu system-X). The BW numbers are
aggregate Mb/s across iterations tested with this version on
System-X boxes with Chelsio 10gbps cards:
----------------------------------
Size | ORG BW NEW BW |
----------------------------------
128K | 156964 159381 |
256K | 158650 162042 |
----------------------------------
Changes from ver1:
1. Move sch_direct_xmit declaration from sch_generic.h to
pkt_sched.h
2. Update qdisc basic statistics for direct xmit path.
3. Set qlen to zero in qdisc_reset.
4. Changed some function names to more meaningful ones.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Elsewhere the sin_family field holds a value with a name of the form
AF_..., so it seems reasonable to do so here as well. Also the values of
PF_INET and AF_INET are the same.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
struct sockaddr_in sip;
@@
(
sip.sin_family ==
- PF_INET
+ AF_INET
|
sip.sin_family !=
- PF_INET
+ AF_INET
|
sip.sin_family =
- PF_INET
+ AF_INET
)
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
This sockopt goes in line with SO_TYPE and SO_PROTOCOL. It makes it
possible for userspace programs to pass around file descriptors — I
am referring to arguments-to-functions, but it may even work for the
fd passing over UNIX sockets — without needing to also pass the
auxiliary information (PF_INET6/IPPROTO_TCP).
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Similar to SO_TYPE returning the socket type, SO_PROTOCOL allows to
retrieve the protocol used with a given socket.
I am not quite sure why we have that-many copies of socket.h, and why
the values are not the same on all arches either, but for where hex
numbers dominate, I use 0x1029 for SO_PROTOCOL as that seems to be
the next free unused number across a bunch of operating systems, or
so Google results make me want to believe. SO_PROTOCOL for others
just uses the next free Linux number, 38.
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
String literals are constant, and usually, we can also tag the array
of pointers const too, moving it to the .rodata section.
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix build errors when SYSCTLs are not enabled:
(.init.text+0x5154): undefined reference to `net_ipv4_ctl_path'
(.init.text+0x5176): undefined reference to `register_net_sysctl_table'
xfrm4_policy.c:(.exit.text+0x573): undefined reference to `unregister_net_sysctl_table
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When an interface is configured in the AP mode, the mac80211
implementation doesn't inform the driver to receive PS Poll frames.
It leads to inability to communicate with power-saving stations
reliably.
The FIF_CONTROL flag isn't passed by mac80211 to
ieee80211_ops.configure_filter when an interface is in the AP mode.
And it's ok, because we don't want to receive ACK frames and other
control ones, but only PS Poll ones.
This patch introduces the FIF_PSPOLL filter flag in addition to
FIF_CONTROL, which means for the driver "pass PS Poll frames".
This flag is passed to the driver:
A) When an interface is configured in the AP mode.
B) In all cases, when the FIF_CONTROL flag was passed earlier (in
addition to it).
Signed-off-by: Igor Perminov <igor.perminov@inbox.ru>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
The SME state machine in cfg80211 uses the SSID stored
in struct wireless_dev internally, but fails to clear
it in multiple places (when giving up on a connection
attempt and when disconnecting). This doesn't matter to
the SME state machine, but does matter for IBSS. Thus,
in those cases, clear the SSID to avoid messing up the
IBSS state machine.
Reported-by: Joerg Albert <jal2@gmx.de>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Althoug GPS is a technology w/o transmitting radio
and thus not a primary candidate for rfkill switch,
rfkill gives unified interface point for devices with
wireless technology.
The input key is not supplied as it is too be deprecated.
Cc: johannes@sipsolutions.net
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Do a probe request every 30 seconds, and wait for probe response,
half a second This should lower the traffic that card sends, thus save
power Wainting longer for response makes probe more robust against
'slow' access points
Signed-off-by: Maxim Levitsky <maximlevitsky@gmail.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Tested-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Retry 5 times (chosen arbitary ), before assuming
that station is out of range.
Fixes frequent disassociations while connected to weak,
and sometimes even strong access points.
Signed-off-by: Maxim Levitky <maximlevitsky@gmail.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
The default of 500ms is pretty high, and leads
to the device being awake at least 50% of the
time under such light traffic conditions as a
simple 1 second interval ping. Reduce to just
100ms -- it should have a similar effect while
providing a better sleep time.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Kalle Valo <kalle.valo@iki.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Since the bss is always set now once we are connected, if the
bss has its own information element we refer to it and pass that
instead of relying on mac80211's parsing.
Now all cfg80211 drivers get country IE support, automatically and
we reduce the call overhead that we had on mac80211 which called this
upon every beacon and instead now call this only upon a successfull
connection by a STA on cfg80211.
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
We change regulatory code to be protected by its own regulatory
mutex and alleviate cfg80211_mutex to only be used to protect
cfg80211_rdev_list, the registered device list.
By doing this we will be able to work on regulatory core components
without having to have hog up the cfg80211_mutex. An example here is
we no longer need to use the cfg80211_mutex during driver specific
wiphy_apply_custom_regulatory(). We also no longer need it for the
the country IE regulatory hint; by doing so we end up curing this
new lockdep warning:
=======================================================
[ INFO: possible circular locking dependency detected ]
2.6.31-rc4-wl #12
-------------------------------------------------------
phy1/1709 is trying to acquire lock:
(cfg80211_mutex){+.+.+.}, at: [<ffffffffa00af852>] regulatory_hint_11d+0x32/0x3f0 [cfg80211]
but task is already holding lock:
(&ifmgd->mtx){+.+.+.}, at: [<ffffffffa0144228>] ieee80211_sta_work+0x108/0x10f0 [mac80211]
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #3 (&ifmgd->mtx){+.+.+.}:
[<ffffffff810857b6>] __lock_acquire+0xd76/0x12b0
[<ffffffff81085dd3>] lock_acquire+0xe3/0x120
[<ffffffff814eeae4>] mutex_lock_nested+0x44/0x350
[<ffffffffa0141bb8>] ieee80211_mgd_auth+0x108/0x1f0 [mac80211]
[<ffffffffa0148563>] ieee80211_auth+0x13/0x20 [mac80211]
[<ffffffffa00bc3a1>] __cfg80211_mlme_auth+0x1b1/0x2a0 [cfg80211]
[<ffffffffa00bc516>] cfg80211_mlme_auth+0x86/0xc0 [cfg80211]
[<ffffffffa00b368d>] nl80211_authenticate+0x21d/0x230 [cfg80211]
[<ffffffff81416ba6>] genl_rcv_msg+0x1b6/0x1f0
[<ffffffff81415c39>] netlink_rcv_skb+0x89/0xb0
[<ffffffff814169d9>] genl_rcv+0x29/0x40
[<ffffffff8141591d>] netlink_unicast+0x29d/0x2b0
[<ffffffff81416514>] netlink_sendmsg+0x214/0x300
[<ffffffff813e4407>] sock_sendmsg+0x107/0x130
[<ffffffff813e45b9>] sys_sendmsg+0x189/0x320
[<ffffffff81011f82>] system_call_fastpath+0x16/0x1b
[<ffffffffffffffff>] 0xffffffffffffffff
-> #2 (&wdev->mtx){+.+.+.}:
[<ffffffff810857b6>] __lock_acquire+0xd76/0x12b0
[<ffffffff81085dd3>] lock_acquire+0xe3/0x120
[<ffffffff814eeae4>] mutex_lock_nested+0x44/0x350
[<ffffffffa00ab304>] cfg80211_netdev_notifier_call+0x1a4/0x390 [cfg80211]
[<ffffffff814f3dff>] notifier_call_chain+0x3f/0x80
[<ffffffff81075a91>] raw_notifier_call_chain+0x11/0x20
[<ffffffff813f665a>] dev_open+0x10a/0x120
[<ffffffff813f59bd>] dev_change_flags+0x9d/0x1e0
[<ffffffff8144eb6e>] devinet_ioctl+0x6fe/0x760
[<ffffffff81450204>] inet_ioctl+0x94/0xc0
[<ffffffff813e25fa>] sock_ioctl+0x6a/0x290
[<ffffffff8111e911>] vfs_ioctl+0x31/0xa0
[<ffffffff8111ea9a>] do_vfs_ioctl+0x8a/0x5c0
[<ffffffff8111f069>] sys_ioctl+0x99/0xa0
[<ffffffff81011f82>] system_call_fastpath+0x16/0x1b
[<ffffffffffffffff>] 0xffffffffffffffff
-> #1 (&rdev->mtx){+.+.+.}:
[<ffffffff810857b6>] __lock_acquire+0xd76/0x12b0
[<ffffffff81085dd3>] lock_acquire+0xe3/0x120
[<ffffffff814eeae4>] mutex_lock_nested+0x44/0x350
[<ffffffffa00ac4d0>] cfg80211_get_dev_from_ifindex+0x60/0x90 [cfg80211]
[<ffffffffa00b21ff>] get_rdev_dev_by_info_ifindex+0x6f/0xa0 [cfg80211]
[<ffffffffa00b51eb>] nl80211_set_interface+0x3b/0x260 [cfg80211]
[<ffffffff81416ba6>] genl_rcv_msg+0x1b6/0x1f0
[<ffffffff81415c39>] netlink_rcv_skb+0x89/0xb0
[<ffffffff814169d9>] genl_rcv+0x29/0x40
[<ffffffff8141591d>] netlink_unicast+0x29d/0x2b0
[<ffffffff81416514>] netlink_sendmsg+0x214/0x300
[<ffffffff813e4407>] sock_sendmsg+0x107/0x130
[<ffffffff813e45b9>] sys_sendmsg+0x189/0x320
[<ffffffff81011f82>] system_call_fastpath+0x16/0x1b
[<ffffffffffffffff>] 0xffffffffffffffff
other info that might help us debug this:
3 locks held by phy1/1709:
#0: ((wiphy_name(local->hw.wiphy))){+.+.+.}, at: [<ffffffff8106b45d>] worker_thread+0x19d/0x340
#1: (&ifmgd->work){+.+.+.}, at: [<ffffffff8106b45d>] worker_thread+0x19d/0x340
#2: (&ifmgd->mtx){+.+.+.}, at: [<ffffffffa0144228>] ieee80211_sta_work+0x108/0x10f0 [mac80211]
Reported-by: Reinette Chatre <reinette.chatre@intel.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Simplify the country IE hint code by just bailing out if
a previous country IE has been issued. We currently just trust
the first AP we connect to on any card. The idea was to perform
conflict resolution within this routine but since we can no longer
iterate over the registered device list here we leave conflict
resolution to be dealt with at a later time on the workqueue.
This code has no functional changes other than saving us an
interation over the registered device list when a second card
is connected, or you unplug and connect the same one, and a
country IE is received. This would have been done upon every
beacon received.
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This has no functional changes.
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Some of the recent MLME rework I did broke powersave
because the ps_sdata isn't assigned at the right time,
and the work item wasn't removed from the list before
calling ieee80211_recalc_ps(). To be more specific,
this broke the case where you'd enabled PS before
associating, either automatically or with iwconfig.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
It's possible to get the NETDEV_UNREGISTER callback multiple
times (see net/core/dev.c:netdev_wait_allrefs) and this will
completely mess up our cleanup code. To avoid that, clean up
only when the interface is still on the wiphy interface list
from which it's removed on the first NETDEV_UNREGISTER call.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
The mac80211 workqueue exists to enable mac80211 and drivers
to queue their own work on a single threaded workqueue. mac80211
takes care to flush the workqueue during suspend but we never
really had requirements on drivers for how they should use
the workqueue in consideration for suspend.
We extend mac80211 to document how the mac80211 workqueue should
be used, how it should not be used and finally move raw access to
the workqueue to mac80211 only. Drivers and mac80211 use helpers
to queue work onto the mac80211 workqueue:
* ieee80211_queue_work()
* ieee80211_queue_delayed_work()
These helpers will now warn if mac80211 already completed its
suspend cycle and someone is trying to queue work. mac80211
flushes the mac80211 workqueue prior to suspend a few times,
but we haven't taken the care to ensure drivers won't add more
work after suspend. To help with this we add a warning when
someone tries to add work and mac80211 already completed the
suspend cycle.
Drivers should ensure they cancel any work or delayed work
in the mac80211 stop() callback.
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
sparse complains about a shadowed variable, which
we can just rename, and lots of stuff if the API
tracer is enabled, so kick out the tracer code in
a sparse run -- the macros just confuse it.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
When a userspace SME is active, we're currently not
keeping track of the BSS properly for reporting the
current link and for internal use. Additionally, it
looks like there is a possible BSS leak in that the
BSS never gets removed from auth_bsses[]. To fix it,
pass the BSS struct to __cfg80211_connect_result in
this case.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
When downing interfaces, it's a good idea to tell the driver to
stop sending beacons; that way the driver doesn't need special
code in ops->remove_interface() when it should already handle the
case in bss_info_changed().
This fixes a potential crash with at least ath5k since the vif
pointer will be nullified while beacon interrupts are still active.
Signed-off-by: Bob Copeland <me@bobcopeland.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Pavel Roskin reported a problem that seems to be due to
software retry of already transmitted frames. It turns
out that we've never done that correctly, but due to
some recent changes it now crashes in the TX code. I've
added a comment in the patch that explains the problem
better and also points to possible solutions -- which
I can't implement right now.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Current neigh_periodic_timer() function is fired by timer IRQ, and
scans one hash bucket each round (very litle work in fact)
As we are supposed to scan whole hash table in 15 seconds, this means
neigh_periodic_timer() can be fired very often. (depending on the number
of concurrent hash entries we stored in this table)
Converting this to a workqueue permits scanning whole table, minimizing
icache pollution, and firing this work every 15 seconds, independantly
of hash table size.
This 15 seconds delay is not a hard number, as work is a deferrable one.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since pr_err and friends are used instead of printk there is no point
in keeping IP_VS_ERR and friends. Furthermore make use of '__func__'
instead of hard coded function names.
Signed-off-by: Hannes Eder <heder@google.com>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This renames away a variable clash:
* ipv6_table[] is declared as a static global table;
* ipv6_sysctl_net_init() uses ipv6_table to refer/destroy dynamic memory;
* ipv6_sysctl_net_exit() also uses ipv6_table for the same purpose;
* both the two last functions call kfree() on ipv6_table.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Choose saner defaults for xfrm[4|6] gc_thresh values on init
Currently, the xfrm[4|6] code has hard-coded initial gc_thresh values
(set to 1024). Given that the ipv4 and ipv6 routing caches are sized
dynamically at boot time, the static selections can be non-sensical.
This patch dynamically selects an appropriate gc threshold based on
the corresponding main routing table size, using the assumption that
we should in the worst case be able to handle as many connections as
the routing table can.
For ipv4, the maximum route cache size is 16 * the number of hash
buckets in the route cache. Given that xfrm4 starts garbage
collection at the gc_thresh and prevents new allocations at 2 *
gc_thresh, we set gc_thresh to half the maximum route cache size.
For ipv6, its a bit trickier. there is no maximum route cache size,
but the ipv6 dst_ops gc_thresh is statically set to 1024. It seems
sane to select a simmilar gc_thresh for the xfrm6 code that is half
the number of hash buckets in the v6 route cache times 16 (like the v4
code does).
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If arp_format_neigh_entry() can be called with n->dev->addr_len == 0, then a
write to hbuffer[-1] occurs.
Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is no reason for the arbitrary restriction that device must be
up to create a vlan. This patch was added to Vyatta kernel to resolve startup
ordering issues where vlan's are created but real device was disabled.
Note: the vlan already correctly inherits the operstate from real device; so
if vlan is created and real device is marked down, the vlan is marked
down.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The test on map4 should be a test on map6.
The semantic match that finds this problem is as follows:
(http://www.emn.fr/x-info/coccinelle/)
// <smpl>
@@
expression *x;
identifier f;
constant char *C;
@@
x = \(kmalloc\|kcalloc\|kzalloc\)(...);
... when != x == NULL
when != x != NULL
when != (x || ...)
(
kfree(x)
|
f(...,C,...,x,...)
|
*f(...,x,...)
|
*x->f
)
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Acked-by: Paul Moore <paul.moore@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Finally! This is what you've all been waiting for!
This patch makes cfg80211 take care of wext emulation
_completely_ by itself, drivers that don't need things
cfg80211 doesn't do yet don't even need to be aware of
wireless extensions.
This means we can also clean up mac80211's and iwm's
Kconfig and make it possible to build them w/o wext
now!
RIP wext.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Since we now have handlers IWESSID for all modes, we can
combine them into one.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Since we now have IWAP handlers for all modes, we can
combine them into one.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Until now we implemented iwfreq for managed mode, we
needed to keep the implementations separate, but now
that we have all versions implemented we can combine
them and export just one handler.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
When enqueuing packets on the internal packet queue, we
need to ensure that we have a valid vif pointer since
that is required since the net namespace work. Add some
assertions to verify this, but also don't crash is for
some reason we don't end up with a vif pointer -- warn
and drop the packet in all these cases.
Since this code touches a number of hotpaths, it is
intended to be temporary, or maybe configurable in the
future, at least the bit that is in the path that gets
hit for every packet, ieee80211_tx_pending().
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
When trying to disassociate while not associated,
the kernel would crash rather than refusing the
operation, fix this;
Reported-by: Maxim Levitsky <maximlevitsky@gmail.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
