During SACK processing, most of the benefits of TSO are eaten by
the SACK blocks that one-by-one fragment SKBs to MSS sized chunks.
Then we're in problems when cleanup work for them has to be done
when a large cumulative ACK comes. Try to return back to pre-split
state already while more and more SACK info gets discovered by
combining newly discovered SACK areas with the previous skb if
that's SACKed as well.
This approach has a number of benefits:
1) The processing overhead is spread more equally over the RTT
2) Write queue has less skbs to process (affect everything
which has to walk in the queue past the sacked areas)
3) Write queue is consistent whole the time, so no other parts
of TCP has to be aware of this (this was not the case with
some other approach that was, well, quite intrusive all
around).
4) Clean_rtx_queue can release most of the pages using single
put_page instead of previous PAGE_SIZE/mss+1 calls
In case a hole is fully filled by the new SACK block, we attempt
to combine the next skb too which allows construction of skbs
that are even larger than what tso split them to and it handles
hole per on every nth patterns that often occur during slow start
overshoot pretty nicely. Though this to be really useful also
a retransmission would have to get lost since cumulative ACKs
advance one hole at a time in the most typical case.
TODO: handle upwards only merging. That should be rather easy
when segment is fully sacked but I'm leaving that as future
work item (it won't make very large difference anyway since
this current approach already covers quite a lot of normal
cases).
I was earlier thinking of some sophisticated way of tracking
timestamps of the first and the last segment but later on
realized that it won't be that necessary at all to store the
timestamp of the last segment. The cases that can occur are
basically either:
1) ambiguous => no sensible measurement can be taken anyway
2) non-ambiguous is due to reordering => having the timestamp
of the last segment there is just skewing things more off
than does some good since the ack got triggered by one of
the holes (besides some substle issues that would make
determining right hole/skb even harder problem). Anyway,
it has nothing to do with this change then.
I choose to route some abnormal looking cases with goto noop,
some could be handled differently (eg., by stopping the
walking at that skb but again). In general, they either
shouldn't happen at all or are rare enough to make no difference
in practice.
In theory this change (as whole) could cause some macroscale
regression (global) because of cache misses that are taken over
the round-trip time but it gets very likely better because of much
less (local) cache misses per other write queue walkers and the
big recovery clearing cumulative ack.
Worth to note that these benefits would be very easy to get also
without TSO/GSO being on as long as the data is in pages so that
we can merge them. Currently I won't let that happen because
DSACK splitting at fragment that would mess up pcounts due to
sk_can_gso in tcp_set_skb_tso_segs. Once DSACKs fragments gets
avoided, we have some conditions that can be made less strict.
TODO: I will probably have to convert the excessive pointer
passing to struct sacktag_state... :-)
My testing revealed that considerable amount of skbs couldn't
be shifted because they were cloned (most likely still awaiting
tx reclaim)...
[The rest is considering future work instead since I got
repeatably EFAULT to tcpdump's recvfrom when I added
pskb_expand_head to deal with clones, so I separated that
into another, later patch]
...To counter that, I gave up on the fifth advantage:
5) When growing previous SACK block, less allocs for new skbs
are done, basically a new alloc is needed only when new hole
is detected and when the previous skb runs out of frags space
...which now only happens of if reclaim is fast enough to dispose
the clone before the SACK block comes in (the window is RTT long),
otherwise we'll have to alloc some.
With clones being handled I got these numbers (will be somewhat
worse without that), taken with fine-grained mibs:
TCPSackShifted 398
TCPSackMerged 877
TCPSackShiftFallback 320
TCPSACKCOLLAPSEFALLBACKGSO 0
TCPSACKCOLLAPSEFALLBACKSKBBITS 0
TCPSACKCOLLAPSEFALLBACKSKBDATA 0
TCPSACKCOLLAPSEFALLBACKBELOW 0
TCPSACKCOLLAPSEFALLBACKFIRST 1
TCPSACKCOLLAPSEFALLBACKPREVBITS 318
TCPSACKCOLLAPSEFALLBACKMSS 1
TCPSACKCOLLAPSEFALLBACKNOHEAD 0
TCPSACKCOLLAPSEFALLBACKSHIFT 0
TCPSACKCOLLAPSENOOPSEQ 0
TCPSACKCOLLAPSENOOPSMALLPCOUNT 0
TCPSACKCOLLAPSENOOPSMALLLEN 0
TCPSACKCOLLAPSEHOLE 12
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can reduce pressure on dst entry refcount that slowdown UDP transmit
path on SMP machines. This pressure is visible on RTP servers when
delivering content to mediagateways, especially big ones, handling
thousand of streams. Several cpus send UDP frames to the same
destination, hence use the same dst entry.
This patch makes ip_append_data() eventually steal the refcount its
callers had to take on the dst entry.
This doesnt avoid all refcounting, but still gives speedups on SMP,
on UDP/RAW transmit path
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is the last step to be able to perform full RCU lookups
in __inet_lookup() : After established/timewait tables, we
add RCU lookups to listening hash table.
The only trick here is that a socket of a given type (TCP ipv4,
TCP ipv6, ...) can now flight between two different tables
(established and listening) during a RCU grace period, so we
must use different 'nulls' end-of-chain values for two tables.
We define a large value :
#define LISTENING_NULLS_BASE (1U << 29)
So that slots in listening table are guaranteed to have different
end-of-chain values than slots in established table. A reader can
still detect it finished its lookup in the right chain.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can avoid some useless instructions if !CONFIG_NET_NS
Because of RCU, we use INET_MATCH or INET_TW_MATCH twice for the found
socket, so thats six instructions less per incoming TCP packet.
Yet another tbench speedup :)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds #include <linux/timer.h> in lib80211.h to avoid
these compilation erros.
> In file included from /work/src/wireless-testing/net/wireless/lib80211.c:24:
> /work/src/wireless-testing/include/net/lib80211.h:113: error: field
> 'crypt_deinit_timer' has incomplete type
> /work/src/wireless-testing/net/wireless/lib80211.c: In function
> 'lib80211_crypt_info_init':
> /work/src/wireless-testing/net/wireless/lib80211.c:83: error: implicit
> declaration of function 'setup_timer'
> /work/src/wireless-testing/net/wireless/lib80211.c: In function
> 'lib80211_crypt_info_free':
> /work/src/wireless-testing/net/wireless/lib80211.c:95: error: implicit
> declaration of function 'del_timer_sync'
> /work/src/wireless-testing/net/wireless/lib80211.c: In function
> 'lib80211_crypt_deinit_handler':
> /work/src/wireless-testing/net/wireless/lib80211.c:157: error:
> implicit declaration of function 'add_timer'
> /work/src/wireless-testing/net/wireless/lib80211.c: In function
> 'lib80211_crypt_delayed_deinit':
> /work/src/wireless-testing/net/wireless/lib80211.c:182: error:
> implicit declaration of function 'timer_pending'
> make[3]: *** [net/wireless/lib80211.o] Error 1
> make[2]: *** [net/wireless] Error 2
> make[1]: *** [net] Error 2
> make: *** [sub-make] Error 2
Signed-off-by: Rami Rosen <ramirose@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Otherwise, the BUILD_BUG_ON calls in ieee80211_tx_info_clear_status can
fail on some architectures.
Signed-off-by: John W. Linville <linville@tuxdriver.com>
These bits are shared already between ipw2x00 and hostap, and could
probably be shared both more cleanly and with other drivers. This
commit simply relocates the code to lib80211 and adjusts the drivers
appropriately.
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Delete kernel-doc struct descriptions for fields that don't exist:
Warning(include/net/mac80211.h:1263): Excess struct/union/enum/typedef member 'conf_ht' description in 'ieee80211_ops'
Warning(net/mac80211/sta_info.h:309): Excess struct/union/enum/typedef member 'addr' description in 'sta_info'
Warning(net/mac80211/sta_info.h:309): Excess struct/union/enum/typedef member 'aid' description in 'sta_info'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
cc: Johannes Berg <johannes@sipsolutions.net>
cc: John W. Linville <linville@tuxdriver.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
On ARM alignment is done slightly different from other architectures.
struct ieee80211_tx_rate is aligned to word size, even though it only has 3
single-byte members, which triggers the BUILD_BUG_ON in
ieee80211_tx_info_clear_status
This patch marks the struct ieee80211_tx_rate as packed, so that ARM
behaves like the other architectures.
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Adds an interface to configure the Backward Congestion Notification
(BCN) feature. In a BCN capabale network, congestion notifications
from congested points out in the network can cause the end station
limit the rate of a given traffic flow.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Adds a netlink interface for Data Center Bridging (DCB) to get and set
the enable state of the Priority Flow Control (PFC) feature.
Primarily, this is a way to turn off PFC in the driver while DCB
remains enabled.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Adds interface for Data Center Bridging (DCB) to query (and set if
supported) the number of traffic classes currently supported by the
device for the two (DCB) features: priority groups (PG) and priority
flow control (PFC).
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Adds to the netlink interface for Data Center Bridging (DCB), allowing
the DCB capabilities supported by a device to be queried.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds support for Data Center Bridging (DCB) features in the ixgbe
driver and adds an rtnetlink interface for configuring DCB to the
kernel. The DCB feature support included are Priority Grouping (PG) -
which allows bandwidth guarantees to be allocated to groups to traffic
based on the 802.1q priority, and Priority Based Flow Control (PFC) -
which introduces a new MAC control PAUSE frame which works at
granularity of the 802.1p priority instead of the link (IEEE 802.3x).
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now TCP & DCCP use RCU lookups, we can convert ehash rwlocks to spinlocks.
/proc/net/tcp and other seq_file 'readers' can safely be converted to 'writers'.
This should speedup writers, since spin_lock()/spin_unlock()
only use one atomic operation instead of two for write_lock()/write_unlock()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch prepares RCU migration of listening_hash table for
TCP/DCCP protocols.
listening_hash table being small (32 slots per protocol), we add
a spinlock for each slot, instead of a single rwlock for whole table.
This should reduce hold time of readers, and writers concurrency.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The first argument to csum_partial is const void *
casts to char/u8 * are not necessary
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Before ieee80211_notify_mac() was added, it was presented with the
use case of using it to tell mac80211 that the association may
have been lost because the firmware crashed/reset.
Since then, it has also been used by iwlwifi to (slightly) speed
up re-association after resume, a workaround around the fact that
mac80211 has no suspend/resume handling yet. It is also not used
by any other drivers, so clearly it cannot be necessary for "good
enough" suspend/resume.
Unfortunately, the callback suffers from a severe problem: It only
works for station mode. If suspend/resume happens while in IBSS or
any other mode (but station), then the callback is pointless.
Recently, it has created a number of locking issues, first because
it required rtnl locking rather than RCU due to calling sleeping
functions within the critical section, and now because it's called
by iwlwifi from the mac80211 workqueue that may not use the rtnl
because it is flushed under rtnl.
(cf. http://bugzilla.kernel.org/show_bug.cgi?id=12046)
I think, therefore, that we should take a step back, remove it
entirely for now and add the small feature it provided properly.
For suspend and resume we will need to introduce new hooks, and for
the case where the firmware was reset the driver will probably
simply just pretend it has done a suspend/resume cycle to get
mac80211 to reprogram the hardware completely, not just try to
connect to the current AP again in station mode. When doing so, we
will need to take into account locking issues and possibly defer
to schedule_work from within mac80211 for the resume operation,
while the suspend operation must be done directly.
Proper suspend/resume should also not necessarily try to reconnect
to the current AP, the time spent in suspend may have been short
enough to not be disconnected from the AP, mac80211 will detect
that the AP went out of range quickly if it did, and if the
association is lost then the AP will disassoc as soon as a data
frame is sent. We might also take into account WWOL then, and
have mac80211 program the hardware into such a mode where it is
available and requested.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Simply delete ops from list and let list debugging do the job.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As found in the past (commit f1dd9c379c
[NET]: Fix tbench regression in 2.6.25-rc1), it is really
important that struct dst_entry refcount is aligned on a cache line.
We cannot use __atribute((aligned)), so manually pad the structure
for 32 and 64 bit arches.
for 32bit : offsetof(truct dst_entry, __refcnt) is 0x80
for 64bit : offsetof(truct dst_entry, __refcnt) is 0xc0
As it is not possible to guess at compile time cache line size,
we use a generic value of 64 bytes, that satisfies many current arches.
(Using 128 bytes alignment on 64bit arches would waste 64 bytes)
Add a BUILD_BUG_ON to catch future updates to "struct dst_entry" dont
break this alignment.
"tbench 8" is 4.4 % faster on a dual quad core (HP BL460c G1), Intel E5450 @3.00GHz
(2350 MB/s instead of 2250 MB/s)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RCU was added to UDP lookups, using a fast infrastructure :
- sockets kmem_cache use SLAB_DESTROY_BY_RCU and dont pay the
price of call_rcu() at freeing time.
- hlist_nulls permits to use few memory barriers.
This patch uses same infrastructure for TCP/DCCP established
and timewait sockets.
Thanks to SLAB_DESTROY_BY_RCU, no slowdown for applications
using short lived TCP connections. A followup patch, converting
rwlocks to spinlocks will even speedup this case.
__inet_lookup_established() is pretty fast now we dont have to
dirty a contended cache line (read_lock/read_unlock)
Only established and timewait hashtable are converted to RCU
(bind table and listen table are still using traditional locking)
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is a straightforward patch, using hlist_nulls infrastructure.
RCUification already done on UDP two weeks ago.
Using hlist_nulls permits us to avoid some memory barriers, both
at lookup time and delete time.
Patch is large because it adds new macros to include/net/sock.h.
These macros will be used by TCP & DCCP in next patch.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
fix this warning:
net/bluetooth/af_bluetooth.c:60: warning: ‘bt_key_strings’ defined but not used
net/bluetooth/af_bluetooth.c:71: warning: ‘bt_slock_key_strings’ defined but not used
this is a lockdep macro problem in the !LOCKDEP case.
We cannot convert it to an inline because the macro works on multiple types,
but we can mark the parameter used.
[ also clean up a misaligned tab in sock_lock_init_class_and_name() ]
[ also remove #ifdefs from around af_family_clock_key strings - which
were certainly added to get rid of the ugly build warnings. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: David S. Miller <davem@davemloft.net>
After implementing qdisc->ops->peek() and changing sch_netem into
classless qdisc there are no more qdisc->ops->requeue() users. This
patch removes this method with its wrappers (qdisc_requeue()), and
also unused qdisc->requeue structure. There are a few minor fixes of
warnings (htb_enqueue()) and comments btw.
The idea to kill ->requeue() and a similar patch were first developed
by David S. Miller.
Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The urg_ptr field is not used anywhere and is merely confusing.
Signed-off-by: Petr Tesarik <ptesarik@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Every user is under CONFIG_NET_DMA already, so ifdef field as well.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Using read_pnet() and write_pnet() in neighbour code ease the reading
of code.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can shrink size of "struct inet_bind_bucket" by 50%, using
read_pnet() and write_pnet()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces two helpers that deal with reading and writing
struct net pointers in various network structures.
Their implementation depends on CONFIG_NET_NS
For symmetry, both functions work with "struct net **pnet".
Their usage should reduce the number of #ifdef CONFIG_NET_NS,
without adding many helpers for each network structure
that hold a "struct net *pointer"
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
->pde isn't actually needed, since name is stashed in ->id.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ensure regulatory converstion macros safely accept
multiple arguments and make REG_RULE() use them.
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Add a new attribute, NL80211_ATTR_WIPHY_TXQ_PARAMS, that can be used with
NL80211_CMD_SET_WIPHY for userspace (e.g., hostapd) to set TX queue
parameters (txop, cwmin, cwmax, aifs).
Signed-off-by: Jouni Malinen <jouni.malinen@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Add a new attribute, NL80211_ATTR_BSS_BASIC_RATES, that can be used with
NL80211_CMD_SET_BSS for userspace (e.g., hostapd) to set which rates are
in the basic rate set.
Signed-off-by: Jouni Malinen <jouni.malinen@atheros.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This adds a helper function that, given a bitmap of basic
rates and a bitrate returns the response rate for this rate.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Send a notification to the driver on succesful
reception of an ADDBA response, add IEEE80211_AMPDU_TX_RESUME
for this purpose.
Signed-off-by: Sujith <Sujith.Manoharan@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Remove the SSID from the driver API since now there is no
driver that requires knowing the SSID and I think it's
unlikely that any hardware design that does require the
SSID will play well with mac80211.
This also removes support for setting the SSID in master
mode which will require a patch to hostapd to not try.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Previously I assumed that the receive queues of candidates don't
change during the GC. This is only half true, nothing can be received
from the queues (see comment in unix_gc()), but buffers could be added
through the other half of the socket pair, which may still have file
descriptors referring to it.
This can result in inc_inflight_move_tail() erronously increasing the
"inflight" counter for a unix socket for which dec_inflight() wasn't
previously called. This in turn can trigger the "BUG_ON(total_refs <
inflight_refs)" in a later garbage collection run.
Fix this by only manipulating the "inflight" counter for sockets which
are candidates themselves. Duplicating the file references in
unix_attach_fds() is also needed to prevent a socket becoming a
candidate for GC while the skb that contains it is not yet queued.
Reported-by: Andrea Bittau <a.bittau@cs.ucl.ac.uk>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
CC: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
__scm_destroy() walks the list of file descriptors in the scm_fp_list
pointed to by the scm_cookie argument.
Those, in turn, can close sockets and invoke __scm_destroy() again.
There is nothing which limits how deeply this can occur.
The idea for how to fix this is from Linus. Basically, we do all of
the fput()s at the top level by collecting all of the scm_fp_list
objects hit by an fput(). Inside of the initial __scm_destroy() we
keep running the list until it is empty.
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
