Key points of this patch are:
- In case new SACK information is advance only type, no skb
processing below previously discovered highest point is done
- Optimize cases below highest point too since there's no need
to always go up to highest point (which is very likely still
present in that SACK), this is not entirely true though
because I'm dropping the fastpath_skb_hint which could
previously optimize those cases even better. Whether that's
significant, I'm not too sure.
Currently it will provide skipping by walking. Combined with
RB-tree, all skipping would become fast too regardless of window
size (can be done incrementally later).
Previously a number of cases in TCP SACK processing fails to
take advantage of costly stored information in sack_recv_cache,
most importantly, expected events such as cumulative ACK and new
hole ACKs. Processing on such ACKs result in rather long walks
building up latencies (which easily gets nasty when window is
huge). Those latencies are often completely unnecessary
compared with the amount of _new_ information received, usually
for cumulative ACK there's no new information at all, yet TCP
walks whole queue unnecessary potentially taking a number of
costly cache misses on the way, etc.!
Since the inclusion of highest_sack, there's a lot information
that is very likely redundant (SACK fastpath hint stuff,
fackets_out, highest_sack), though there's no ultimate guarantee
that they'll remain the same whole the time (in all unearthly
scenarios). Take advantage of this knowledge here and drop
fastpath hint and use direct access to highest SACKed skb as
a replacement.
Effectively "special cased" fastpath is dropped. This change
adds some complexity to introduce better coveraged "fastpath",
though the added complexity should make TCP behave more cache
friendly.
The current ACK's SACK blocks are compared against each cached
block individially and only ranges that are new are then scanned
by the high constant walk. For other parts of write queue, even
when in previously known part of the SACK blocks, a faster skip
function is used (if necessary at all). In addition, whenever
possible, TCP fast-forwards to highest_sack skb that was made
available by an earlier patch. In typical case, no other things
but this fast-forward and mandatory markings after that occur
making the access pattern quite similar to the former fastpath
"special case".
DSACKs are special case that must always be walked.
The local to recv_sack_cache copying could be more intelligent
w.r.t DSACKs which are likely to be there only once but that
is left to a separate patch.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
It is going to replace the sack fastpath hint quite soon... :-)
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
The sock_valbool_flag() helper is used in setsockopt to
set or reset some flag on the sock. This helper is required
in the net/socket.c only, so move it there.
Besides, patch two places in sys_setsockopt() that repeat
this helper functionality manually.
Since this is not a bugfix, but a trivial cleanup, I
prepared this patch against net-2.6.25, but it also
applies (with a single offset) to the latest net-2.6.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Qdisc_class_ops are const, and Qdisc_ops are mostly read.
Using "const" and "__read_mostly" qualifiers helps to reduce false
sharing.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Policy table is implemented as an RCU linear list since we do not expect
large list nor frequent updates.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
After changeset:
[NETFILTER]: Introduce NF_INET_ hook values
It always evaluates to NF_INET_POST_ROUTING.
Signed-off-by: David S. Miller <davem@davemloft.net>
The IPv4 and IPv6 hook values are identical, yet some code tries to figure
out the "correct" value by looking at the address family. Introduce NF_INET_*
values for both IPv4 and IPv6. The old values are kept in a #ifndef __KERNEL__
section for userspace compatibility.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for async resumptions on input. To do so, the
transform would return -EINPROGRESS and subsequently invoke the
function xfrm_input_resume to resume processing.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The nhoff field isn't actually necessary in xfrm_input. For tunnel
mode transforms we now throw away the output IP header so it makes no
sense to fill in the nexthdr field. For transport mode we can now let
the function transport_finish do the setting and it knows where the
nexthdr field is.
The only other thing that needs the nexthdr field to be set is the
header extraction code. However, we can simply move the protocol
extraction out of the generic header extraction.
We want to minimise the amount of info we have to carry around between
transforms as this simplifies the resumption process for async crypto.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently x->lastused is u64 which means that it cannot be
read/written atomically on all architectures. David Miller observed
that the value stored in it is only an unsigned long which is always
atomic.
So based on his suggestion this patch changes the internal
representation from u64 to unsigned long while the user-interface
still refers to it as u64.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
As part of the work on asynchronous cryptographic operations, we need
to be able to resume from the spot where they occur. As such, it
helps if we isolate them to one spot.
This patch moves most of the remaining family-specific processing into
the common input code.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for async resumptions on output. To do so,
the transform would return -EINPROGRESS and subsequently invoke the
function xfrm_output_resume to resume processing.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
As part of the work on asynchrnous cryptographic operations, we need
to be able to resume from the spot where they occur. As such, it
helps if we isolate them to one spot.
This patch moves most of the remaining family-specific processing into
the common output code.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Most callers of the LOCAL_OUT chain will set the IP packet length
before doing so. They also share the same output function dst_output.
This patch creates a new function called ip6_local_out which does all
of that and converts the appropriate users over to it.
Apart from removing duplicate code, it will also help in merging the
IPsec output path.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Most callers of the LOCAL_OUT chain will set the IP packet length and
header checksum before doing so. They also share the same output
function dst_output.
This patch creates a new function called ip_local_out which does all
of that and converts the appropriate users over to it.
Apart from removing duplicate code, it will also help in merging the
IPsec output path once the same thing is done for IPv6.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
With inter-family transforms the inner mode differs from the outer
mode. Attempting to handle both sides from the same function means
that it needs to handle both IPv4 and IPv6 which creates duplication
and confusion.
This patch separates the two parts on the input path so that each
function deals with one family only.
In particular, the functions xfrm4_extract_inut/xfrm6_extract_inut
moves the pertinent fields from the IPv4/IPv6 IP headers into a
neutral format stored in skb->cb. This is then used by the inner mode
input functions to modify the inner IP header. In this way the input
function no longer has to know about the outer address family.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
With inter-family transforms the inner mode differs from the outer
mode. Attempting to handle both sides from the same function means
that it needs to handle both IPv4 and IPv6 which creates duplication
and confusion.
This patch separates the two parts on the output path so that each
function deals with one family only.
In particular, the functions xfrm4_extract_output/xfrm6_extract_output
moves the pertinent fields from the IPv4/IPv6 IP headers into a
neutral format stored in skb->cb. This is then used by the outer mode
output functions to write the outer IP header. In this way the output
function no longer has to know about the inner address family.
Since the extract functions are only called by tunnel modes (the only
modes that can support inter-family transforms), I've also moved the
xfrm*_tunnel_check_size calls into them. This allows the correct ICMP
message to be sent as opposed to now where you might call icmp_send
with an IPv6 packet and vice versa.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch changes the prototype of ipv4_copy_dscp and ipv6_copy_dscp so
that they directly take the outer DSCP rather than the outer IP header.
This will help us to unify the code for inter-family tunnels.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Half of the code in xfrm4_bundle_create and xfrm6_bundle_create are
common. This patch extracts that logic and puts it into
xfrm_bundle_create. The rest of it are then accessed through afinfo.
As a result this fixes the problem with inter-family transforms where
we treat every xfrm dst in the bundle as if it belongs to the top
family.
This patch also fixes a long-standing error-path bug where we may free
the xfrm states twice.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch moves the flow construction from the callers of
xfrm_dst_lookup into that function. It also changes xfrm_dst_lookup
so that it takes an xfrm state as its argument instead of explicit
addresses.
This removes any address-specific logic from the callers of
xfrm_dst_lookup which is needed to correctly support inter-family
transforms.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The functions local_addr and remote_addr are more than what they're
needed for. The same thing can be done easily with flags on the type
object. This patch does that and simplifies the wrapper functions in
xfrm6_policy accordingly.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The file net/netevent.h only refers to struct dst_entry * so it
doesn't need to include dst.h. I've replaced it with a forward
declaration.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
We have a number of copies of dst_discard scattered around the place
which all do the same thing, namely free a packet on the input or
output paths.
This patch deletes all of them except dst_discard and points all the
users to it.
The only non-trivial bit is decnet where it returns an error.
However, conceptually this is identical to the blackhole functions
used in IPv4 and IPv6 which do not return errors. So they should
either all return errors or all return zero. For now I've stuck with
the majority and picked zero as the return value.
It doesn't really matter in practice since few if any driver would
react differently depending on a zero return value or NET_RX_DROP.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The dst member nfheader_len is only used by IPv6. It's also currently
creating a rather ugly alignment hole in struct dst. Therefore this patch
moves it from there into struct rt6_info.
It also reorders the fields in rt6_info to minimize holes.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add raw drops counter for IPv4 in /proc/net/raw .
Signed-off-by: Wang Chen <wangchen@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow caller to pass in a release function, there might be
other resources that need releasing as well. Needed for
network receive.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
* git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6: (197 commits)
sh: add spi header and r2d platform data V3
sh: update r7780rp interrupt code
sh: remove consistent alloc stuff from the machine vector
sh: use declared coherent memory for dreamcast pci ethernet adapter
sh: declared coherent memory support V2
sh: Add support for SDK7780 board.
sh: constify function pointer tables
sh: Kill off -traditional for linker script.
cdrom: Add support for Sega Dreamcast GD-ROM.
sh: Kill off hs7751rvoip reference from arch/sh/Kconfig.
sh: Drop r7780rp_defconfig, use r7780mp_defconfig as kbuild default.
sh: Kill off dead HS771RVoIP board support.
sh: r7785rp: Fix up DECLARE_INTC_DESC() arg mismatch.
sh: r7785rp: Hook up the rest of the HL7785 FPGA IRQ vectors.
sh: r2d - enable sm501 usb host function
sh: remove voyagergx
sh: r2d - add lcd planel timings to sm501 platform data
sh: Add OHCI and UDC platform devices for SH7720.
sh: intc - remove default interrupt priority tables
sh: Correct pte size mismatch for X2 TLB.
...
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid: (24 commits)
HID: ADS/Tech Radio si470x needs blacklist entry
HID: Logitech Extreme 3D needs NOGET quirk
HID: Refactor MS Presenter 8K key mapping
HID: MS Presenter mapping for PID 0x0701
HID: Support Samsung IR remote
HID: fix compilation of hidbp drivers without usbhid
HID: Blacklist the Gretag-Macbeth Huey display colorimeter
HID: the `bit' in hidinput_mapping_quirks() is an out parameter
HID: remove redundant WARN_ON()s in order not to scare users
HID: force hiddev creation for SONY PS3 controller
HID: Use hid blacklist in usbmouse/usbkbd
HID: proper handling of MS 4k and 6k devices
HID: remove unused variable in quirk event handler
HID: hid-input quirk for BTC 8193
HID: separate hid-input event quirks from generic code
HID: refactor mapping to input subsystem for quirky devices
HID: Microsoft Wireless Optical Desktop 3.0 quirk
HID: Add support for Logitech Elite keyboards
HID: add full support for Genius KB-29E
HID: fix a potential bug in pointer casting
...
* 'sg' of git://git.kernel.dk/linux-2.6-block:
SG: work with the SCSI fixed maximum allocations.
SG: Convert SCSI to use scatterlist helpers for sg chaining
SG: Move functions to lib/scatterlist.c and add sg chaining allocator helpers
Samsung USB remotes (0419:0001) are rejected by kernel 2.6.23, because the
report descriptor from the remote contains a 48 bit HID report field. HID 1.11
states: Fields may span at most 4 bytes.
This patch, based on 2.6.23, fixes this by modifying the internal report
descriptor in hid-quirks.c. Additional user space support (e.g. LIRC) is
required to fetch the information from the hiddev interface.
The burden to reconstruct the data is moved into userspace (lirc through hiddev).
There is no need to set HID_QUIRK_HIDDEV quirk, as the device has also output
applications, which trigger the creation of hiddev device automatically.
Signed-off-by: Robert Schedel <r.schedel@yahoo.de>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Fix a panic, by changing
hidinput_mapping_quirks(,, unsigned long *bit,)
to
hidinput_mapping_quirks(,, unsigned long **bit,)
The `bit' in this function is an out parameter.
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
This removes ugly macros IS_* to distinguish devices that
need special handling in hid-input, and establish proper
quirks for them.
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
BTC 8193 keyboard handles its scrollwheel in very non-standard way.
It produces two non-standard usages for scrolling up and down, in
both cases with postive value equaling to 1. We handle this by temporary
mapping, which we then catch in quirk event handler, and remap to
negative HWHEEL even in order to introduce correct behavior.
Also the button requires special mapping, as it triggers standard-violating
usage code.
Reported in kernel.org bugzilla #9385
Reported-by: Kir Kolyshkin <kir@sacred.ru>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
This patch separates also the hid-input quirks that have to be
applied at the time the event occurs, so that the generic code
handling HUT-compliant devices is not messed up by them too much.
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Currently, the handling of mapping between hid and input for devices
that don't conform to HUT 1.12 specification is very messy -- no per-device
handling, no blacklists, conditions on idVendor and idProduct placed
all over the code.
This patch moves all the device-specific input mapping to a separate
file, and introduces a blacklist-style handling for non-standard
device-specific mappings.
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Genius KB-29E has broken report descriptor, which causes some of the
Consumer usages to appear incorrectly as Button usages. We fix it by
fixing the report descriptor before it is being parsed.
Also a few of the keys violate the HUT standard, so they need a special
handling. They currently fall into "Reserved" range as per HUT 1.12.
Reported-by: Szekeres Istvan <szekeres@iii.hu>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
This mouse distinguishes horizontal wheel from vertical by a special "pseudo
event" GenericDesktop.00b8, with values of 0 for vertical and 8 for horizontal
wheel. Because this event is supplied by the parser too late, we need to delay
a wheel event, wait for this one and send either REL_WHEEL or REL_HWHEEL to
input depending on the event value.
Signed-off-by: Pavel Troller <patrol@sinus.cz>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Preserve identifiers exposed in build and run time configuration though in
order not to break existing configurations.
This is in preparation for adding support for Apple aluminum USB keyboards.
Signed-off-by: Michel Daenzer <michel@tungstengraphics.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
* orion: (26 commits)
[ARM] Orion: implement power-off method for QNAP TS-109/209
[ARM] Orion: add support for QNAP TS-109/TS-209
[ARM] Orion: I2C support
[I2C] i2c-mv64xxx: Don't set i2c_adapter.retries
[I2C] Split mv643xx I2C platform support
[ARM] Orion: enable CONFIG_RTC_DRV_M41T80 for D-Link DNS-323
[ARM] Orion defconfig
[ARM] Orion: add support for Orion/MV88F5181 based D-Link DNS-323
[ARM] Orion: MV88F5181 support bits
[ARM] Orion: Buffalo/Revogear Kurobox Pro support
[ARM] OrionNAS RD board support
[ARM] Orion: support for Marvell Orion-2 (88F5281) Development Board
[ARM] Orion: common platform setup for Gigabit Ethernet port
[ARM] Orion: platform device registration for UART, USB and NAND
[ARM] Orion: system timer support
[ARM] Orion edge GPIO IRQ support
[ARM] Orion: IRQ support
[ARM] Orion: provide GPIO method for enabling hardware assisted blinking
[ARM] Orion: GPIO support
[ARM] Orion: programable address map support
...
Conflicts:
arch/arm/Kconfig
arch/arm/Makefile
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Add the reverse of s3c2410_gpio_getirq to convert
a IRQ number into a GPIO pin number.
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Remove warnings left in include/asm-arm/arch-s3c2410/debug-macro.S
whilst these where being experimented with.
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Add S3C2412_CLKDIVN_DVSEN and S3C2412_CLKDIVN_HALFHCLK definitions to
the S3C2412_CLKDIVN set.
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Add control constants for the S3C2412 SPI unit FIFO.
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
