Currently NAT (and others) that want to modify cloned skbs copy them,
even if in the vast majority of cases its not necessary because the
skb is a clone made by TCP and the portion NAT wants to modify is
actually writable because TCP release the header reference before
cloning.
The problem is that there is no clean way for NAT to find out how
long the writable header area is, so this patch introduces skb->hdr_len
to hold this length. When a headerless skb is cloned skb->hdr_len
is set to the current headroom, for regular clones it is copied from
the original. A new function skb_clone_writable(skb, len) returns
whether the skb is writable up to len bytes from skb->data. To avoid
enlarging the skb the mac_len field is reduced to 16 bit and the
new hdr_len field is put in the remaining 16 bit.
I've done a few rough benchmarks of NAT (not with this exact patch,
but a very similar one). As expected it saves huge amounts of system
time in case of sendfile, bringing it down to basically the same
amount as without NAT, with sendmsg it only helps on loopback,
probably because of the large MTU.
Transmit a 1GB file using sendfile/sendmsg over eth0/lo with and
without NAT:
- sendfile eth0, no NAT: sys 0m0.388s
- sendfile eth0, NAT: sys 0m1.835s
- sendfile eth0: NAT + path: sys 0m0.370s (~ -80%)
- sendfile lo, no NAT: sys 0m0.258s
- sendfile lo, NAT: sys 0m2.609s
- sendfile lo, NAT + patch: sys 0m0.260s (~ -90%)
- sendmsg eth0, no NAT: sys 0m2.508s
- sendmsg eth0, NAT: sys 0m2.539s
- sendmsg eth0, NAT + patch: sys 0m2.445s (no change)
- sendmsg lo, no NAT: sys 0m2.151s
- sendmsg lo, NAT: sys 0m3.557s
- sendmsg lo, NAT + patch: sys 0m2.159s (~ -40%)
I expect other users can see a similar performance improvement,
packet mangling iptables targets, ipip and ip_gre come to mind ..
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Changes :
- netif_queue_stopped need not be called inside qdisc_restart as
it has been called already in qdisc_run() before the first skb
is sent, and in __qdisc_run() after each intermediate skb is
sent (note : we are the only sender, so the queue cannot get
stopped while the tx lock was got in the ~LLTX case).
- BUG_ON((int) q->q.qlen < 0) was a relic from old times when -1
meant more packets are available, and __qdisc_run used to loop
when qdisc_restart() returned -1. During those days, it was
necessary to make sure that qlen is never less than zero, since
__qdisc_run would get into an infinite loop if no packets are on
the queue and this bug in qdisc was there (and worse - no more
skbs could ever get queue'd as we hold the queue lock too). With
Herbert's recent change to return values, this check is not
required. Hopefully Herbert can validate this change. If at all
this is required, it should be added to skb_dequeue (in failure
case), and not to qdisc_qlen.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
New changes :
- Incorporated Peter Waskiewicz's comments.
- Re-added back one warning message (on driver returning wrong value).
Previous changes :
- Converted to use switch/case code which looks neater.
- "if (ret == NETDEV_TX_LOCKED && lockless)" is buggy, and the lockless
check should be removed, since driver will return NETDEV_TX_LOCKED only
if lockless is true and driver has to do the locking. In the original
code as well as the latest code, this code can result in a bug where
if LLTX is not set for a driver (lockless == 0) but the driver is written
wrongly to do a trylock (despite LLTX being set), the driver returns
LOCKED. But since lockless is zero, the packet is requeue'd instead of
calling collision code which will issue warning and free up the skb.
Instead this skb will be retried with this driver next time, and the same
result will ensue. Removing this check will catch these driver bugs instead
of hiding the problem. I am keeping this change to readability section
since :
a. it is confusing to check two things as it is; and
b. it is difficult to keep this check in the changed 'switch' code.
- Changed some names, like try_get_tx_pkt to dev_dequeue_skb (as that is
the work being done and easier to understand) and do_dev_requeue to
dev_requeue_skb, merged handle_dev_cpu_collision and tx_islocked to
dev_handle_collision (handle_dev_cpu_collision is a small routine with only
one caller, so there is no need to have two separate routines which also
results in getting rid of two macros, etc.
- Removed an XXX comment as it should never fail (I suspect this was related
to batch skb WIP, Jamal ?). Converted some functions to original coding
style of having the return values and the function name on same line, eg
prio2list.
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ccid3_hc_tx_send_packet currently returns 0 when the time difference between
current time and t_nom is less than 1000 microseconds.
In this case the packet is sent immediately; but, unlike other packets that can
be emitted on first attempt, it will not have its window counter updated and
its options set as required. This is a bug.
Fix: Require the time difference to be at least 1000 microseconds. The
algorithm then converges: time differences > 1000 microseconds trigger the
timer in dccp_write_xmit; after timer expiry this function is tried again; when
the time difference is less than 1000, the packet will have its options added
and window counter updated as required.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
This updates the computation of t_nom and t_last_win_count to use the newer
gettimeofday interface.
Committer note: used ktime_to_timeval to set the 'now' variable to t_ld in
ccid3hctx_no_feedback_timer
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
This provides a reusable time difference function which returns the difference in
microseconds, as often used in the DCCP code.
Commiter note: renamed ktime_delta to ktime_us_delta and put it in ktime.h.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
It had just a slab cache, so, for the sake of simplicity just make
dccp_trfc_lib module init routine create the slab cache, no need for users of
the lib to create a private loss_interval object.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Now ccid3_hc_rx_update_li is ready to be moved to
net/dccp/ccids/lib/loss_interval, it uses the same interface as the other
functions there.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This is a preparatory patch for moving these loss interval functions from
net/dccp/ccids/ccid3.c to net/dccp/ccids/lib/loss_interval.c.
Based on a patch by Ian McDonald.
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
When compiling with EXTRA_CFLAGS=-W noticed that tstamp is not initialised
correctly in dccp_li_calc_first_li.
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
When compiling with EXTRA_CFLAGS=-W notice that we have signed/unsigned issue
in dccp.h.
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
Keep track of the number of configured ingress/egress QoS mappings to
avoid iteration while calculating the netlink attribute size.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb->priority has only 32 bits and even VLAN uses 32 bit values in its API.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The returned device is unused, return proper error codes instead and avoid
having the ioctl handler guess the error.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move device registration and configuration of the underlying device to a
seperate function.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move the checks of the underlying device to a seperate function.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move group allocation to a seperate function to clean up the code a bit
and allocate groups before registering the device. Device registration
is globally visible and causes netlink events, so we shouldn't fail
afterwards.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move some device initialization code to new dev->init callback to make
it shareable with netlink. Additionally this fixes a minor bug, dev->iflink
is set after registration, which causes an incorrect value in the initial
netlink message.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move the device lookup and checks to the ioctl handler under the RTNL and
change all name-based interfaces to take a struct net_device * instead.
This allows to use them from a netlink interface, which identifies devices
based on ifindex not name. It also avoids races between the ioctl interface
and the (upcoming) netlink interface since now all changes happen under the
RTNL.
As a nice side effect this greatly simplifies error handling in the helper
functions and fixes a number of incorrect error codes like -EINVAL for
device not found.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use a list instead of an array to allow creating new devices.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use a list instead of an array to allow creating new devices.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add rtnetlink API for creating, changing and deleting software devices.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Split up rtnl_setlink into a function performing validation and a function
performing the actual changes. This allows to share the modifcation logic
with rtnl_newlink, which is introduced by the next patch.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
At present, transmission rate information for mac80211 is available only
if verbose debugging is turned on, and then only in the logs. This patch
implements the SIOCGIWRATE ioctl, which adds the current transmission rate to
the output of iwconfig.
Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It hasn't "summed" anything in over 7 years, and it's
just a straight mempcy ala skb_copy_to_linear_data()
so just get rid of it.
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently the code for /proc/net/tcp disable BH while iterating
over the entire established hash table. Even though we call
cond_resched_softirq for each entry, we still won't process
softirq's as regularly as we would otherwise do which results
in poor performance when the system is loaded near capacity.
This anomaly comes from the 2.4 code where this was all in a
single function and the local_bh_disable might have made sense
as a small optimisation.
The cost of each local_bh_disable is so small when compared
against the increased latency in keeping it disabled over a
large but mostly empty TCP established hash table that we
should just move it to the individual read_lock/read_unlock
calls as we do in inet_diag.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Over the years this code has gotten hairier. Resulting in many long
discussions over long summer days and patches that get it wrong.
This patch helps tame that code so normal people will understand it.
Thanks to Thomas Graf, Peter J. waskiewicz Jr, and Patrick McHardy
for their valuable reviews.
Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch enhances TIPC's stream socket send routine so that
it avoids transmitting data in chunks that require fragmentation
and reassembly, thereby improving performance at both the
sending and receiving ends of the connection.
The "maximum packet size" hint that records MTU info allows
the socket to decide how big a chunk it should send; in the
event that the hint has become stale, fragmentation may still
occur, but the data will be passed correctly and the hint will
be updated in time for the following send. Note: The 66060 byte
pseudo-MTU used for intra-node connections requires the send
routine to perform an additional check to ensure it does not
exceed TIPC"s limit of 66000 bytes of user data per chunk.
Signed-off-by: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Jon Paul Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch modifies TIPC's socket API to utilize existing
generic routines to indicate unsupported operations, rather
than adding similar TIPC-specific routines.
Signed-off-by: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Jon Paul Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch simplifies TIPC's Ethernet receive routine to take
advantage of information already present in each incoming sk_buff
indicating whether the packet was explicitly sent to the interface,
has been broadcast to all interfaces, or was picked up because the
interface is in promiscous mode.
This new approach also fixes the problem of TIPC accepting unwanted
traffic through UML's multicast-based Ethernet interfaces (which
deliver traffic in a promiscuous manner even if the interface is
not configured to be promiscuous).
Signed-off-by: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Jon Paul Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the termios2 structure ready for enabling on most platforms. One or
two like Sparc are plain weird so have been left alone. Most can use the
same structure as ktermios for termios2 (ie the newer ioctl uses the
structure matching the current kernel structure)
Signed-off-by: Alan Cox <alan@redhat.com>
Cc: Bryan Wu <bryan.wu@analog.com>
Cc: Ian Molton <spyro@f2s.com>
Cc: Haavard Skinnemoen <hskinnemoen@atmel.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Mikael Starvik <starvik@axis.com>
Cc: David Howells <dhowells@redhat.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Hirokazu Takata <takata@linux-m32r.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Roman Zippel <zippel@linux-m68k.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Matthew Wilcox <willy@debian.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp>
Cc: Richard Curnow <rc@rc0.org.uk>
Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp>
Cc: Chris Zankel <chris@zankel.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Many places in kernel use seq_file API to iterate over a regular list_head.
The code for such iteration is identical in all the places, so it's worth
introducing a common helpers.
This makes code about 300 lines smaller:
The first version of this patch made the helper functions static inline
in the seq_file.h header. This patch moves them to the fs/seq_file.c as
Andrew proposed. The vmlinux .text section sizes are as follows:
2.6.22-rc1-mm1: 0x001794d5
with the previous version: 0x00179505
with this patch: 0x00179135
The config file used was make allnoconfig with the "y" inclusion of all
the possible options to make the files modified by the patch compile plus
drivers I have on the test node.
This patch:
Many places in kernel use seq_file API to iterate over a regular list_head.
The code for such iteration is identical in all the places, so it's worth
introducing a common helpers.
Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is a hybrid version of the patch to add the LZO1X compression
algorithm to the kernel. Nitin and myself have merged the best parts of
the various patches to form this version which we're both happy with (and
are jointly signing off).
The performance of this version is equivalent to the original minilzo code
it was based on. Bytecode comparisons have also been made on ARM, i386 and
x86_64 with favourable results.
There are several users of LZO lined up including jffs2, crypto and reiser4
since its much faster than zlib.
Signed-off-by: Nitin Gupta <nitingupta910@gmail.com>
Signed-off-by: Richard Purdie <rpurdie@openedhand.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/drzeus/mmc:
mmc: at91_mci: fix hanging and rework to match flowcharts
mmc: at91_mci typo
sdhci: Fix "Unexpected interrupt" handling
mmc: fix silly copy-and-paste error
mmc: move layer init and workqueue to core file
mmc: refactor host class handling
mmc: refactor bus operations
sdhci: add ene controller id
mmc: bounce requests for simple hosts
* 'upstream-linus' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6: (40 commits)
bonding/bond_main.c: make 2 functions static
ps3: gigabit ethernet driver for PS3, take3
[netdrvr] Fix dependencies for ax88796 ne2k clone driver
eHEA: Capability flag for DLPAR support
Remove sk98lin ethernet driver.
sunhme.c:quattro_pci_find() must be __devinit
bonding / ipv6: no addrconf for slaves separately from master
atl1: remove write-only var in tx handler
macmace: use "unsigned long flags;"
Cleanup usbnet_probe() return value handling
netxen: deinline and sparse fix
eeprom_93cx6: shorten pulse timing to match spec (bis)
phylib: Add Marvell 88E1112 phy id
phylib: cleanup marvell.c a bit
AX88796 network driver
IOC3: Switch to pci refcounting safe APIs
e100: Fix Tyan motherboard e100 not receiving IPMI commands
QE Ethernet driver writes to wrong register to mask interrupts
rrunner.c:rr_init() must be __devinit
tokenring/3c359.c:xl_init() must be __devinit
...
* 'upstream-linus' of master.kernel.org:/pub/scm/linux/kernel/git/jgarzik/libata-dev: (32 commits)
[libata] sata_mv: print out additional chip info during probe
[libata] Use ATA_UDMAx standard masks when filling driver's udma_mask info
[libata] AHCI: Add support for Marvell AHCI-like chips (initially 6145)
[libata] Clean up driver udma_mask initializers
libata: Support chips with 64K PRD quirk
Add a PCI ID for santa rosa's PATA controller.
sata_sil24: sil24_interrupt() micro-optimisation
Add irq_flags to struct pata_platform_info
sata_promise: cleanups
[libata] pata_ixp4xx: kill unused var
ata_piix: fix pio/mwdma programming
[libata] ahci: minor internal cleanups
[ATA] Add named constant for ATAPI command DEVICE RESET
[libata] sata_sx4, sata_via: minor documentation updates
[libata] ahci: minor internal cleanups
[libata] ahci: Factor out SATA port init into a separate function
[libata] pata_sil680: minor cleanups from benh
[libata] sata_sx4: named constant cleanup
[libata] pata_ixp4xx: convert to new EH
[libata] pdc_adma: Reorder initializers with a couple structs
...
