Go to file
Alexander Lobakin 8aef998df3 net: core: allow fast GRO for skbs with Ethernet header in head
Commit 78d3fd0b7d ("gro: Only use skb_gro_header for completely
non-linear packets") back in May'09 (v2.6.31-rc1) has changed the
original condition '!skb_headlen(skb)' to
'skb->mac_header == skb->tail' in gro_reset_offset() saying: "Since
the drivers that need this optimisation all provide completely
non-linear packets" (note that this condition has become the current
'skb_mac_header(skb) == skb_tail_pointer(skb)' later with commmit
ced14f6804 ("net: Correct comparisons and calculations using
skb->tail and skb-transport_header") without any functional changes).

For now, we have the following rough statistics for v5.4-rc7:
1) napi_gro_frags: 14
2) napi_gro_receive with skb->head containing (most of) payload: 83
3) napi_gro_receive with skb->head containing all the headers: 20
4) napi_gro_receive with skb->head containing only Ethernet header: 2

With the current condition, fast GRO with the usage of
NAPI_GRO_CB(skb)->frag0 is available only in the [1] case.
Packets pushed by [2] and [3] go through the 'slow' path, but
it's not a problem for them as they already contain all the needed
headers in skb->head, so pskb_may_pull() only moves skb->data.

The layout of skbs in the fourth [4] case at the moment of
dev_gro_receive() is identical to skbs that have come through [1],
as napi_frags_skb() pulls Ethernet header to skb->head. The only
difference is that the mentioned condition is always false for them,
because skb_put() and friends irreversibly alter the tail pointer.
They also go through the 'slow' path, but now every single
pskb_may_pull() in every single .gro_receive() will call the *really*
slow __pskb_pull_tail() to pull headers to head. This significantly
decreases the overall performance for no visible reasons.

The only two users of method [4] is:
* drivers/staging/qlge
* drivers/net/wireless/iwlwifi (all three variants: dvm, mvm, mvm-mq)

Note that in case with wireless drivers we can't use [1]
(napi_gro_frags()) at least for now and mac80211 stack always
performs pushes and pulls anyways, so performance hit is inavoidable.

At the moment of v2.6.31 the mentioned change was necessary (that's
why I don't add the "Fixes:" tag), but it became obsolete since
skb_gro_mac_header() has gone in commit a50e233c50 ("net-gro:
restore frag0 optimization"), so we can simply revert the condition
in gro_reset_offset() to allow skbs from [4] go through the 'fast'
path just like in case [1].

This was tested on a 600 MHz MIPS CPU and a custom driver and this
patch gave boosts up to 40 Mbps to method [4] in both directions
comparing to net-next, which made overall performance relatively
close to [1] (without it, [4] is the slowest).

v2:
- Add more references and explanations to commit message
- Fix some typos ibid
- No functional changes

Signed-off-by: Alexander Lobakin <alobakin@dlink.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-16 12:59:50 -08:00
arch can: mcp251x: get rid of legacy platform data 2019-11-11 21:57:28 +01:00
block blkcg: make blkcg_print_stat() print stats only for online blkgs 2019-11-06 17:08:38 -07:00
certs PKCS#7: Refactor verify_pkcs7_signature() 2019-08-05 18:40:18 -04:00
crypto Merge branch 'next-lockdown' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security 2019-09-28 08:14:15 -07:00
Documentation mlx5-updates-2019-11-12 2019-11-14 18:01:45 -08:00
drivers bnx2x: Remove hw_reset_t function casts 2019-11-16 12:50:57 -08:00
fs for-linus-2019-11-08 2019-11-08 18:15:55 -08:00
include page_pool: do not release pool until inflight == 0. 2019-11-16 12:39:10 -08:00
init init: Support mounting root file systems over SMB 2019-10-02 12:15:15 -04:00
ipc ipc/sem.c: convert to use built-in RCU list checking 2019-09-25 17:51:41 -07:00
kernel Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net 2019-11-09 11:04:37 -08:00
lib Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net 2019-11-09 11:04:37 -08:00
LICENSES
mm Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net 2019-11-09 11:04:37 -08:00
net net: core: allow fast GRO for skbs with Ethernet header in head 2019-11-16 12:59:50 -08:00
samples samples/bpf: adjust Makefile and README.rst 2019-11-11 21:42:09 -08:00
scripts Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net 2019-11-09 11:04:37 -08:00
security Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net 2019-11-02 13:54:56 -07:00
sound ASoC: Fixes for v5.4 2019-11-07 13:52:17 +01:00
tools selftests: net: tcp_mmap should create detached threads 2019-11-15 12:46:08 -08:00
usr kbuild: update compile-test header list for v5.4-rc2 2019-10-05 15:29:49 +09:00
virt kvm: call kvm_arch_destroy_vm if vm creation fails 2019-10-31 12:13:16 +01:00
.clang-format clang-format: Update with the latest for_each macro list 2019-08-31 10:00:51 +02:00
.cocciconfig
.get_maintainer.ignore
.gitattributes
.gitignore Modules updates for v5.4 2019-09-22 10:34:46 -07:00
.mailmap A few MIPS fixes: 2019-10-26 19:43:12 -04:00
COPYING
CREDITS MAINTAINERS: Remove Simon as Renesas SoC Co-Maintainer 2019-10-10 08:12:51 -07:00
Kbuild kbuild: do not descend to ./Kbuild when cleaning 2019-08-21 21:03:58 +09:00
Kconfig
MAINTAINERS net: dsa: ocelot: add driver for Felix switch family 2019-11-15 12:32:16 -08:00
Makefile Linux 5.4-rc6 2019-11-03 14:07:26 -08:00
README

Linux kernel
============

There are several guides for kernel developers and users. These guides can
be rendered in a number of formats, like HTML and PDF. Please read
Documentation/admin-guide/README.rst first.

In order to build the documentation, use ``make htmldocs`` or
``make pdfdocs``.  The formatted documentation can also be read online at:

    https://www.kernel.org/doc/html/latest/

There are various text files in the Documentation/ subdirectory,
several of them using the Restructured Text markup notation.

Please read the Documentation/process/changes.rst file, as it contains the
requirements for building and running the kernel, and information about
the problems which may result by upgrading your kernel.