Ivo van Doorn [Tue, 25 Mar 2008 13:12:45 +0000 (14:12 +0100)]
rt2x00: Fix rate detection for invalid signals
It has been observed on rt2500pci hardware that some
frames received with signal 0x0C do not have the OFDM
flag set.
Signals can have 2 meanings:
1) The PLCP value
2) The bitrate * 10
For rt2500pci (1) is for frames received with a OFDM rate,
and (2) is for frames received with a CCK rate.
But 0x0C is a invalid bitrate value but is a valid PLCP
value for 54Mbs (obvious OFDM rate).
This means that it is possible that the hardware does not
set the OFDM bit correctly under all circumstances.
This results in rt2x00 failing to detect the rate and
mac80211 triggering a WARN_ON() and dropping the frame.
To bypass this, print a warning when such a frame is received,
and reset the rate to the lowest supported rate for the current band.
Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Assaf Krauss [Tue, 18 Mar 2008 21:57:50 +0000 (14:57 -0700)]
iwlwifi: Completing the parameter packaging
This patch completes the changes regarding the packaging of user
parameters.
Signed-off-by: Assaf Krauss <assaf.krauss@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Al Viro [Sun, 16 Mar 2008 22:26:44 +0000 (22:26 +0000)]
ipw2200 annotations and fixes
a) a bunch of printks in error-handling assums that ->status is
big-endian.
b) bitfields trouble
c) missing annotations
NB: a bunch of structs is declared packed for no good reason, AFAICS.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Ivo van Doorn [Sat, 15 Mar 2008 20:38:07 +0000 (21:38 +0100)]
rt2x00: Add dev_flags to rx descriptor
The rxdone_entry_desc structure contains 3 fields
which are always 1 or 0. We can safe 8 bytes by
replacing them with a single dev_flags fields which
contain the flags for those settings.
Additionally we can remove the OFDM flag since it
is no longer used since the introduction of the
SIGNAL_PLCP flag.
Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Vladimir Koutny [Tue, 18 Mar 2008 20:14:07 +0000 (21:14 +0100)]
mac80211: configure default wmm params correctly
Default WMM params have to be set according to beacon/probe response
information prior to authentication (or IBSS start/join); beacon queue
is configured only in IBSS. This does not affect the use of 'real' WMM
params as reported by AP.
Signed-off-by: Vladimir Koutny <vlado@ksp.sk> Acked-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Mohamed Abbas [Thu, 20 Mar 2008 15:14:29 +0000 (08:14 -0700)]
mac80211: prevent tuning during scanning
Postpone calling ieee80211_hw_config if hardware scanning is active.
This is similar to solution for software scanning where channel setting
is delayed until scan complete.
Signed-off-by: Mohamed Abbas <mohamed.abbas@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Acked-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Ron Rindjunsky [Tue, 18 Mar 2008 22:00:32 +0000 (15:00 -0700)]
mac80211: tear down of block ack sessions
This patch adds a clean tear down for all block ack sessions if interface
goes down or if a deauthentication is done.
Signed-off-by: Ron Rindjunsky <ron.rindjunsky@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Ron Rindjunsky [Tue, 18 Mar 2008 22:00:31 +0000 (15:00 -0700)]
mac80211: fixing debug prints for AddBA request
This patch also fixes the Rx timer's comments
Signed-off-by: Ron Rindjunsky <ron.rindjunsky@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Ron Rindjunsky [Tue, 18 Mar 2008 22:00:30 +0000 (15:00 -0700)]
mac80211: fixing delba debug print
This patch fixes a wrong debug print when receiving delba
Signed-off-by: Ron Rindjunsky <ron.rindjunsky@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Johannes Berg [Sun, 16 Mar 2008 17:42:44 +0000 (18:42 +0100)]
mac80211: filter scan results on unusable channels
When you have an AP on channel 13, it will currently often enough
be listed in scan results even when the regulatory domain restricts
to channels 1-11. This is due to channel overlap. To avoid getting
very strange failures, don't show such APs in the scan results. The
failure mode will now go from "I can see the AP but not associate"
to "I can't see the AP although I know it's there" which is easier
to debug.
This problem was first really noticed by Jes Sorensen.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Cc: Jes Sorensen <jes@trained-monkey.org> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Tomas Winkler [Fri, 21 Mar 2008 20:53:44 +0000 (13:53 -0700)]
iwlwifi: move host command sending functions to core module
1. Host command sending functions moved from iwl4965-base.c to iwl-hcmd.c
in iwlcore module
2. enqueue_hcmd function currently stays in iwl4965-base.c. It is invoked
through the new 'utils' field in priv's ops.
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Assaf Krauss <assaf.krauss@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Assaf Krauss [Fri, 21 Mar 2008 20:53:43 +0000 (13:53 -0700)]
iwlwifi: rename iwl4965_get_channel_info to iwl_get_channel_info
iwl4965_get_channel_info was moved to iwlcore module
4965 needs to be stripped off
Signed-off-by: Assaf Krauss <assaf.krauss@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Tomas Winkler [Fri, 21 Mar 2008 20:53:42 +0000 (13:53 -0700)]
iwlwifi: iwl3945 remove 4965 commands
This patch removes 4965 host commands from iwl-3945-commands.h
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
This patch add support for TKIP encryption (TX) in HW.
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
mac80211: allows driver to request a Phase 1 RX key
This patch makes mac80211 able to send a phase1 key for TKIP
decryption.
This is needed for drivers that don't do the rekeying by themselves
(i.e. iwlwifi). Upon IV16 wrap around, the packet is decrypted in SW,
if decryption is ok, mac80211 calls to update_tkip_key with a new
phase 1 RX key.
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
This patch makes mac80211 able to compute a TKIP key from an skb.
The requested key can be a phase 1 or a phase 2 key.
This is useful for drivers who need to provide tkip key to their
HW to enable HW encryption.
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
This patch adds translation for the RX status of an incoming packet.
The incoming status has to be translated to the old scheme in order to know
if the decryption has been done, MIC failure has occured, TTAK is valid etc...
This translation is mandatory for all RX packets when using 5300 and for
all HT packets using 4965.
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
This patch cleans up the set_key flow. Rxon with hw encryption bit set is
not sent upon each call to set_key. Separation is made between global key
(WEP) and dynamic key (TKIP + CCMP and WEP in some cases).
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Assaf Krauss [Fri, 14 Mar 2008 17:38:49 +0000 (10:38 -0700)]
iwlwifi: Probe Flow - Extracting hw and priv init
1. Extracting hw and priv initialization from probe function.
2. Moving some initialization functions to core module.
Signed-off-by: Assaf Krauss <assaf.krauss@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Assaf Krauss [Fri, 14 Mar 2008 17:38:48 +0000 (10:38 -0700)]
iwlwifi: Probe Flow - Performing allocation in a separate function
Performing allocation in a separate function (previously handled in
'probe')
Signed-off-by: Assaf Krauss <assaf.krauss@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Assaf Krauss [Fri, 14 Mar 2008 17:38:47 +0000 (10:38 -0700)]
iwlwifi: Packing all 4965 parameters
This patch defines a package struct for iwlwifi parameters, and uses a
single instance of this struct to group all iwl4965 module parameters
together.
Signed-off-by: Assaf Krauss <assaf.krauss@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Assaf Krauss [Fri, 14 Mar 2008 17:38:46 +0000 (10:38 -0700)]
iwlwifi: Re-ordering probe flow (4965)
This patch re-orders the iwl4965_pci_probe function.
Signed-off-by: Assaf Krauss <assaf.krauss@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Holger Schurig [Wed, 19 Mar 2008 16:08:32 +0000 (17:08 +0100)]
libertas: store rssi as an u32
Don't store an (hardware base) u8 value in bss_descriptor, but just an
unsigned int (RSSI is really unsigned). Compilers generate more efficent
code for ints than for bytes.
Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Acked-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Holger Schurig [Wed, 19 Mar 2008 13:25:58 +0000 (14:25 +0100)]
libertas: remove lots of unused stuff
This removes many unused function parameters as well as some not-implemented
functions, e.g. CMD_802_11_GET_STATS. The silly lbs_set_cmd_ctrl_node()
function is now also gone.
Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Acked-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Holger Schurig [Wed, 19 Mar 2008 13:25:18 +0000 (14:25 +0100)]
libertas: misc power saving adjusts
* firmware for the CF card supports power saving
* the driver currenly only accept "iwconfig ethX power on|off", so
I fixed what the range wext ioctl reports.
* initialize value/flags in lbs_get_power()
* get rid of unused parameter psmode in lbs_ps_confirm_sleep()
* some minor debug output tweaks
Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Acked-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Holger Schurig [Mon, 17 Mar 2008 11:45:58 +0000 (12:45 +0100)]
libertas: convert GET_LOG to a direct command
Now uses __lbs_cmd() to get the "log" (it's actually more a snapshot of
various counters, not a sequential log). Besides the "mechanical" convertion
the patch add the following logical changes:
* Removes the priv->logmsg variable, it was only used in one place anyway,
also don't blindly get the counters when associating. Getting the
counters then the user asks via WEXT for them is good enought.
* don't set wstats.discard.fragment with log.rxfrag, because the latter is
a counter for successfully received packets, not for fragmented packets.
Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Acked-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Holger Schurig [Tue, 18 Mar 2008 10:20:21 +0000 (11:20 +0100)]
libertas: fix scheduling while atomic bug in CMD_MAC_CONTROL
The old code incorrectly used lbs_cmd_with_response() and now uses
lbs_cmd_async().
While there I noticed that there is no real useful return values for
asynchronous command functions, so I made the function "void".
Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Acked-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Holger Schurig [Wed, 19 Mar 2008 09:11:00 +0000 (10:11 +0100)]
libertas: make a handy lbs_cmd_async() command
This uses a static lbs_cmd_async_callback function, which is a
noop. Just setting the callback argument to __lbs_cmd_async()
to NULL won't work, because then the cmdnode wouldn't be
released.
This also makes __lbs_cmd_async() a static method, which is
now only used by lbs_cmd() and lbs_cmd_async().
Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Acked-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Tomas Winkler [Wed, 12 Mar 2008 23:58:52 +0000 (16:58 -0700)]
iwlwifi: Add debugfs to iwl core
This patch adds debugfs support to iwl core
currently only iwl4965 is supported
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Tomas Winkler [Wed, 12 Mar 2008 23:58:51 +0000 (16:58 -0700)]
iwlwifi: Add TX/RX statistcs to driver
This patch supports collecting of TX and RX statistics in the driver.
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Tomas Winkler [Wed, 12 Mar 2008 23:58:50 +0000 (16:58 -0700)]
iwlwifi: rename struct iwl4965_priv to struct iwl_priv
This patch renames iwl4965_priv to iwl_priv. iwl_priv will
be shared by more hw.
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Tomas Winkler [Wed, 12 Mar 2008 23:58:49 +0000 (16:58 -0700)]
iwlwifi: rename iwl-4965-debug.h back to iwl-debug.h
This patch removes iwl-4965-debug.h to iwl-debug.h
It will be used by more NICs
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: Reinette Chatre <reinette.chatre@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Max Stepanov [Wed, 12 Mar 2008 23:58:48 +0000 (16:58 -0700)]
iwlwifi: Bug fix, CCMP with HW encryption with AGG
This patch fixes a bug in security. Enables CCMP HW encryption with
aggregations.
Signed-off-by: Max Stepanov <max.stepanov@intel.com> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Holger Schurig [Wed, 12 Mar 2008 16:06:09 +0000 (17:06 +0100)]
libertas: remove some unused commands
Neither CMD_802_11_PAIRWISE_TSC nor CMD_802_11_GROUP_TSC is used or
documented. It might have something to do with TKIP sequence counters,
but that's just an educated guess. Remove all occurences of them.
CMD_CODE_DNLD is also neither used nor documented.
Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Acked-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Holger Schurig [Wed, 12 Mar 2008 15:06:43 +0000 (16:06 +0100)]
libertas: rename packetfilter to mac_control
The CMD_MAC_CONTROL can be used for other things than just filtering
packets, e.g. to enable and disable WMM. This uses the same term mac_control
for the define, the function and the shadow value in struct lbs_private.
Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Acked-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Holger Schurig [Wed, 12 Mar 2008 15:05:40 +0000 (16:05 +0100)]
libertas: convert CMD_MAC_CONTROL to a direct command
convert CMD_MAC_CONTROL to a direct command
Signed-off-by: Holger Schurig <hs4233@mail.mn-solutions.de> Acked-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Florian Westphal [Mon, 24 Mar 2008 05:21:28 +0000 (22:21 -0700)]
[TCP]: Shrink syncookie_secret by 8 byte.
the first u32 copied from syncookie_secret is overwritten by the
minute-counter four lines below. After adjusting the destination
address, the size of syncookie_secret can be reduced accordingly.
AFAICS, the only other user of syncookie_secret[] is the ipv6
syncookie support. Because ipv6 syncookies only grab 44 bytes from
syncookie_secret[], this shouldn't affect them in any way.
With fixes from Glenn Griffin.
Signed-off-by: Florian Westphal <fw@strlen.de> Acked-by: Glenn Griffin <ggriffin.kernel@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Martin Devera [Mon, 24 Mar 2008 05:00:38 +0000 (22:00 -0700)]
sch_htb: fix "too many events" situation
HTB is event driven algorithm and part of its work is to apply
scheduled events at proper times. It tried to defend itself from
livelock by processing only limited number of events per dequeue.
Because of faster computers some users already hit this hardcoded
limit.
This patch limits processing up to 2 jiffies (why not 1 jiffie ?
because it might stop prematurely when only fraction of jiffie
remains).
Signed-off-by: Martin Devera <devik@cdi.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
Evgeniy Polyakov [Mon, 24 Mar 2008 04:51:12 +0000 (21:51 -0700)]
connector: convert to single-threaded workqueue
From: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
We don't need one cqueue thread for each CPU. cqueue is used for
receiving userspace datagrams, which are very rare and thus will
happily live with a single queue.
Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Sun, 23 Mar 2008 10:35:12 +0000 (03:35 -0700)]
[SUNGEM]: Fix NAPI assertion failure.
As reported by Johannes Berg:
I started getting this warning with recent kernels:
[ 773.908927] ------------[ cut here ]------------
[ 773.908954] Badness at net/core/dev.c:2204
...
If we loop more than once in gem_poll(), we'll
use more than the real budget in our gem_rx()
calls, thus eventually trigger the caller's
assertions in net_rx_action().
Subtract "work_done" from "budget" for the second
arg to gem_rx() to fix the bug.
Signed-off-by: David S. Miller <davem@davemloft.net>
Eliezer Tamir [Sun, 23 Mar 2008 10:07:45 +0000 (03:07 -0700)]
BNX2X: prevent ethtool from setting port type
On 10GBaseT boards setting the type to TP will cause the driver to try
to configure 1GBaseT.
Since there are currently no boards that support setting of the port
type, disable this for now.
Signed-off-by: Eliezer Tamir <eliezert@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
[IPV4] fib_trie: fix warning from rcu_assign_poinger
This gets rid of a warning caused by the test in rcu_assign_pointer.
I tried to fix rcu_assign_pointer, but that devolved into a long set
of discussions about doing it right that came to no real solution.
Since the test in rcu_assign_pointer for constant NULL would never
succeed in fib_trie, just open code instead.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Pavel Emelyanov [Sat, 22 Mar 2008 23:56:51 +0000 (16:56 -0700)]
[RAW]: Add raw_hashinfo member on struct proto.
Sorry for the patch sequence confusion :| but I found that the similar
thing can be done for raw sockets easily too late.
Expand the proto.h union with the raw_hashinfo member and use it in
raw_prot and rawv6_prot. This allows to drop the protocol specific
versions of hash and unhash callbacks.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Pavel Emelyanov [Sat, 22 Mar 2008 23:51:21 +0000 (16:51 -0700)]
[UDP]: Make full use of proto.h.udp_hash innovation.
After this we have only udp_lib_get_port to get the port and two
stubs for ipv4 and ipv6. No difference in udp and udplite except
for initialized h.udp_hash member.
I tried to find a graceful way to drop the only difference between
udp_v4_get_port and udp_v6_get_port (i.e. the rcv_saddr comparison
routine), but adding one more callback on the struct proto didn't
appear such :( Maybe later.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Pavel Emelyanov [Sat, 22 Mar 2008 23:50:58 +0000 (16:50 -0700)]
[SOCK]: Add udp_hash member to struct proto.
Inspired by the commit ab1e0a13 ([SOCK] proto: Add hashinfo member to
struct proto) from Arnaldo, I made similar thing for UDP/-Lite IPv4
and -v6 protocols.
The result is not that exciting, but it removes some levels of
indirection in udpxxx_get_port and saves some space in code and text.
The first step is to union existing hashinfo and new udp_hash on the
struct proto and give a name to this union, since future initialization
of tcpxxx_prot, dccp_vx_protinfo and udpxxx_protinfo will cause gcc
warning about inability to initialize anonymous member this way.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Denis V. Lunev [Sat, 22 Mar 2008 23:35:29 +0000 (16:35 -0700)]
[IPV4]: Remove unused ip_options->is_data.
ip_options->is_data is assigned only and never checked. The structure is
not a part of kernel interface to the userspace. So, it is safe to remove
this field.
Signed-off-by: Denis V. Lunev <den@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Herbert Xu [Sat, 22 Mar 2008 22:47:05 +0000 (15:47 -0700)]
[TCP]: Let skbs grow over a page on fast peers
While testing the virtio-net driver on KVM with TSO I noticed
that TSO performance with a 1500 MTU is significantly worse
compared to the performance of non-TSO with a 16436 MTU. The
packet dump shows that most of the packets sent are smaller
than a page.
Looking at the code this actually is quite obvious as it always
stop extending the packet if it's the first packet yet to be
sent and if it's larger than the MSS. Since each extension is
bound by the page size, this means that (given a 1500 MTU) we're
very unlikely to construct packets greater than a page, provided
that the receiver and the path is fast enough so that packets can
always be sent immediately.
The fix is also quite obvious. The push calls inside the loop
is just an optimisation so that we don't end up doing all the
sending at the end of the loop. Therefore there is no specific
reason why it has to do so at MSS boundaries. For TSO, the
most natural extension of this optimisation is to do the pushing
once the skb exceeds the TSO size goal.
This is what the patch does and testing with KVM shows that the
TSO performance with a 1500 MTU easily surpasses that of a 16436
MTU and indeed the packet sizes sent are generally larger than
16436.
I don't see any obvious downsides for slower peers or connections,
but it would be prudent to test this extensively to ensure that
those cases don't regress.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
Patrick McManus [Fri, 21 Mar 2008 23:33:01 +0000 (16:33 -0700)]
[TCP]: TCP_DEFER_ACCEPT updates - process as established
Change TCP_DEFER_ACCEPT implementation so that it transitions a
connection to ESTABLISHED after handshake is complete instead of
leaving it in SYN-RECV until some data arrvies. Place connection in
accept queue when first data packet arrives from slow path.
Benefits:
- established connection is now reset if it never makes it
to the accept queue
- diagnostic state of established matches with the packet traces
showing completed handshake
- TCP_DEFER_ACCEPT timeouts are expressed in seconds and can now be
enforced with reasonable accuracy instead of rounding up to next
exponential back-off of syn-ack retry.
Signed-off-by: Patrick McManus <mcmanus@ducksong.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Patrick McManus [Fri, 21 Mar 2008 23:29:22 +0000 (16:29 -0700)]
[TCP]: TCP_DEFER_ACCEPT updates - dont retxmt synack
a socket in LISTEN that had completed its 3 way handshake, but not notified
userspace because of SO_DEFER_ACCEPT, would retransmit the already
acked syn-ack during the time it was waiting for the first data byte
from the peer.
Signed-off-by: Patrick McManus <mcmanus@ducksong.com> Acked-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Patrick McManus [Fri, 21 Mar 2008 23:27:38 +0000 (16:27 -0700)]
[TCP]: TCP_DEFER_ACCEPT updates - defer timeout conflicts with max_thresh
timeout associated with SO_DEFER_ACCEPT wasn't being honored if it was
less than the timeout allowed by the maximum syn-recv queue size
algorithm. Fix by using the SO_DEFER_ACCEPT value if the ack has
arrived.
Signed-off-by: Patrick McManus <mcmanus@ducksong.com> Acked-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Pavel Emelyanov [Fri, 21 Mar 2008 22:52:00 +0000 (15:52 -0700)]
[NET]: NULL pointer dereference and other nasty things in /proc/net/(tcp|udp)[6]
Commits f40c81 ([NETNS][IPV4] tcp - make proc handle the network
namespaces) and a91275 ([NETNS][IPV6] udp - make proc handle the
network namespace) both introduced bad checks on sockets and tw
buckets to belong to proper net namespace.
I.e. when checking for socket to belong to given net and family the
do {
sk = sk_next(sk);
} while (sk && sk->sk_net != net && sk->sk_family != family);
constructions were used. This is wrong, since as soon as the
sk->sk_net fits the net the socket is immediately returned, even if it
belongs to other family.
As the result four /proc/net/(udp|tcp)[6] entries show wrong info.
The udp6 entry even oopses when dereferencing inet6_sk(sk) pointer:
dest = &np->daddr; /* will be NULL for AF_INET sockets */
...
seq_printf(...
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3],
...
Fix it by converting && to ||.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: Daniel Lezcano <dlezcano@fr.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Make socket filters work for netlink unicast and notifications.
This is useful for applications like Zebra that get overrun with
messages that are then ignored.
Note: netlink messages are in host byte order, but packet filter
state machine operations are done as network byte order.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
In file included from net/sctp/sm_statetable.c:50:
include/net/sctp/sctp.h: In function 'sctp_v6_pf_init':
include/net/sctp/sctp.h:392: warning: 'return' with a value, in function returning void
In file included from net/sctp/sm_statefuns.c:62:
include/net/sctp/sctp.h: In function 'sctp_v6_pf_init':
include/net/sctp/sctp.h:392: warning: 'return' with a value, in function returning void
...
Signed-off-by: David S. Miller <davem@davemloft.net>
Phil Oester [Fri, 21 Mar 2008 22:01:50 +0000 (15:01 -0700)]
[IPV4]: Fix null dereference in ip_defrag
Been seeing occasional panics in my testing of 2.6.25-rc in ip_defrag.
Offending line in ip_defrag is here:
net = skb->dev->nd_net
where dev is NULL. Bisected the problem down to commit ac18e7509e7df327e30d6e073a787d922eaf211d ([NETNS][FRAGS]: Make the
inet_frag_queue lookup work in namespaces).
Below patch (idea from Patrick McHardy) fixes the problem for me.
Signed-off-by: Phil Oester <kernel@linuxace.com> Acked-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
[NET]: Add per-connection option to set max TSO frame size
Update: My mailer ate one of Jarek's feedback mails... Fixed the
parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the
whitespace issue due to a patch import botch. Changed the types from
u32 to unsigned int to be more consistent with other variables in the
area. Also brought the patch up to the latest net-2.6.26 tree.
Update: Made gso_max_size container 32 bits, not 16. Moved the
location of gso_max_size within netdev to be less hotpath. Made more
consistent names between the sock and netdev layers, and added a
define for the max GSO size.
Update: Respun for net-2.6.26 tree.
Update: changed max_gso_frame_size and sk_gso_max_size from signed to
unsigned - thanks Stephen!
This patch adds the ability for device drivers to control the size of
the TSO frames being sent to them, per TCP connection. By setting the
netdevice's gso_max_size value, the socket layer will set the GSO
frame size based on that value. This will propogate into the TCP
layer, and send TSO's of that size to the hardware.
This can be desirable to help tune the bursty nature of TSO on a
per-adapter basis, where one may have 1 GbE and 10 GbE devices
coexisting in a system, one running multiqueue and the other not, etc.
This can also be desirable for devices that cannot support full 64 KB
TSO's, but still want to benefit from some level of segmentation
offloading.
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jarek Poplawski [Fri, 21 Mar 2008 00:05:13 +0000 (17:05 -0700)]
[NET] ifb: set separate lockdep classes for queue locks
[ 10.536424] =======================================================
[ 10.536424] [ INFO: possible circular locking dependency detected ]
[ 10.536424] 2.6.25-rc3-devel #3
[ 10.536424] -------------------------------------------------------
[ 10.536424] swapper/0 is trying to acquire lock:
[ 10.536424] (&dev->queue_lock){-+..}, at: [<c0299b4a>]
dev_queue_xmit+0x175/0x2f3
[ 10.536424]
[ 10.536424] but task is already holding lock:
[ 10.536424] (&p->tcfc_lock){-+..}, at: [<f8a67154>] tcf_mirred+0x20/0x178
[act_mirred]
[ 10.536424]
[ 10.536424] which lock already depends on the new lock.
lockdep warns of locking order while using ifb with sch_ingress and
act_mirred: ingress_lock, tcfc_lock, queue_lock (usually queue_lock
is at the beginning). This patch is only to tell lockdep that ifb is
a different device (e.g. from eth) and has its own pair of queue
locks. (This warning is a false-positive in common scenario of using
ifb; yet there are possible situations, when this order could be
dangerous; lockdep should warn in such a case.) (With suggestions by
David S. Miller)
Reported-and-tested-by: Denys Fedoryshchenko <denys@visp.net.lb> Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Acked-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
Patrick McHardy [Thu, 20 Mar 2008 23:11:27 +0000 (16:11 -0700)]
[TCP]: Fix shrinking windows with window scaling
When selecting a new window, tcp_select_window() tries not to shrink
the offered window by using the maximum of the remaining offered window
size and the newly calculated window size. The newly calculated window
size is always a multiple of the window scaling factor, the remaining
window size however might not be since it depends on rcv_wup/rcv_nxt.
This means we're effectively shrinking the window when scaling it down.
The dump below shows the problem (scaling factor 2^7):
- Window size of 557 (71296) is advertised, up to 3111907257:
IP 172.2.2.3.33000 > 172.2.2.2.33000: . ack 3111835961 win 557 <...>
- New window size of 514 (65792) is advertised, up to 3111907217, 40 bytes
below the last end:
If the sender uses up the entire window before it is shrunk, this can have
chaotic effects on the connection. When sending ACKs, tcp_acceptable_seq()
will notice that the window has been shrunk since tcp_wnd_end() is before
tp->snd_nxt, which makes it choose tcp_wnd_end() as sequence number.
This will fail the receivers checks in tcp_sequence() however since it
is before it's tp->rcv_wup, making it respond with a dupack.
If both sides are in this condition, this leads to a constant flood of
ACKs until the connection times out.
Make sure the window is never shrunk by aligning the remaining window to
the window scaling factor.
Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
zap_completion_queue() retrieves skbs from completion_queue where they have
zero skb->users counter. Before dev_kfree_skb_any() it should be non-zero
yet, so it's increased now.
Reported-and-tested-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Fabio Checconi [Thu, 20 Mar 2008 22:54:58 +0000 (15:54 -0700)]
bridge: use time_before() in br_fdb_cleanup()
In br_fdb_cleanup() next_timer and this_timer are in jiffies, so they
should be compared using the time_after() macro.
Signed-off-by: Fabio Checconi <fabio@gandalf.sssup.it> Signed-off-by: Stephen Hemminger <stephen.hemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Pavel Emelyanov [Thu, 20 Mar 2008 22:39:41 +0000 (15:39 -0700)]
audit: netlink socket can be auto-bound to pid other than current->pid (v2)
From: Pavel Emelyanov <xemul@openvz.org>
This patch is based on the one from Thomas.
The kauditd_thread() calls the netlink_unicast() and passes
the audit_pid to it. The audit_pid, in turn, is received from
the user space and the tool (I've checked the audit v1.6.9)
uses getpid() to pass one in the kernel. Besides, this tool
doesn't bind the netlink socket to this id, but simply creates
it allowing the kernel to auto-bind one.
That's the preamble.
The problem is that netlink_autobind() _does_not_ guarantees
that the socket will be auto-bound to the current pid. Instead
it uses the current pid as a hint to start looking for a free
id. So, in case of conflict, the audit messages can be sent
to a wrong socket. This can happen (it's unlikely, but can be)
in case some task opens more than one netlink sockets and then
the audit one starts - in this case the audit's pid can be busy
and its socket will be bound to another id.
The proposal is to introduce an audit_nlk_pid in audit subsys,
that will point to the netlink socket to send packets to. It
will most often be equal to audit_pid. The socket id can be
got from the skb's netlink CB right in the audit_receive_msg.
The audit_nlk_pid reset to 0 is not required, since all the
decisions are taken based on audit_pid value only.
Later, if the audit tools will bind the socket themselves, the
kernel will have to provide a way to setup the audit_nlk_pid
as well.
A good side effect of this patch is that audit_pid can later
be converted to struct pid, as it is not longer safe to use
pid_t-s in the presence of pid namespaces. But audit code still
uses the tgid from task_struct in the audit_signal_info and in
the audit_filter_syscall.
Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: Eric Paris <eparis@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
projects / linux-2.6 / log