Commit 8c48eea3ad ("page_pool: allow caching from safely localized
NAPI") allowed direct recycling of skb pages to their PP for some cases,
but unfortunately missed a couple of other majors.
For example, %XDP_DROP in skb mode. The netstack just calls kfree_skb(),
which unconditionally passes `false` as @napi_safe. Thus, all pages go
through ptr_ring and locks, although most of time we're actually inside
the NAPI polling this PP is linked with, so that it would be perfectly
safe to recycle pages directly.
Let's address such. If @napi_safe is true, we're fine, don't change
anything for this path. But if it's false, check whether we are in the
softirq context. It will most likely be so and then if ->list_owner
is our current CPU, we're good to use direct recycling, even though
@napi_safe is false -- concurrent access is excluded. in_softirq()
protection is needed mostly due to we can hit this place in the
process context (not the hardirq though).
For the mentioned xdp-drop-skb-mode case, the improvement I got is
3-4% in Mpps. As for page_pool stats, recycle_ring is now 0 and
alloc_slow counter doesn't change most of time, which means the
MM layer is not even called to allocate any new pages.
Suggested-by: Jakub Kicinski <kuba@kernel.org> # in_softirq()
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-7-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Page pool use in hardirq is prohibited, add debug checks
to catch misuses. IIRC we previously discussed using
DEBUG_NET_WARN_ON_ONCE() for this, but there were concerns
that people will have DEBUG_NET enabled in perf testing.
I don't think anyone enables lockdep in perf testing,
so use lockdep to avoid pushback and arguing :)
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-6-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently, pp->p.napi is always read, but the actual variable it gets
assigned to is read-only when @napi_safe is true. For the !napi_safe
cases, which yet is still a pack, it's an unneeded operation.
Moreover, it can lead to premature or even redundant page_pool
cacheline access. For example, when page_pool_is_last_frag() returns
false (with the recent frag improvements).
Thus, read it only when @napi_safe is true. This also allows moving
@napi inside the condition block itself. Constify it while we are
here, because why not.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-5-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
On x86_64, frag_* fields of struct page_pool are scattered across two
cachelines despite the summary size of 24 bytes. All three fields are
used in pretty much the same places, but the last field, ::frag_users,
is pushed out to the next CL, provoking unwanted false-sharing on
hotpath (frags allocation code).
There are some holes and cold members to move around. Move frag_* one
block up, placing them right after &page_pool_params perfectly at the
beginning of CL2. This doesn't do any meaningful to the second block, as
those are some destroy-path cold structures, and doesn't do anything to
::alloc_stats, which still starts at 200-byte offset, 8 bytes after CL3
(still fitting into 1 cacheline).
On my setup, this yields 1-2% of Mpps when using PP frags actively.
When it comes to 32-bit architectures with 32-byte CL: &page_pool_params
plus ::pad is 44 bytes, the block taken care of is 16 bytes within one
CL, so there should be at least no regressions from the actual change.
::pages_state_hold_cnt is not related directly to that triple, but is
paired currently with ::frags_offset and decoupling them would mean
either two 4-byte holes or more invasive layout changes.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-4-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently, touching <net/page_pool/types.h> triggers a rebuild of more
than half of the kernel. That's because it's included in
<linux/skbuff.h>. And each new include to page_pool/types.h adds more
[useless] data for the toolchain to process per each source file from
that pile.
In commit 6a5bcd84e8 ("page_pool: Allow drivers to hint on SKB
recycling"), Matteo included it to be able to call a couple of functions
defined there. Then, in commit 57f05bc2ab ("page_pool: keep pp info as
long as page pool owns the page") one of the calls was removed, so only
one was left. It's the call to page_pool_return_skb_page() in
napi_frag_unref(). The function is external and doesn't have any
dependencies. Having very niche page_pool_types.h included only for that
looks like an overkill.
As %PP_SIGNATURE is not local to page_pool.c (was only in the
early submissions), nothing holds this function there. Teleport
page_pool_return_skb_page() to skbuff.c, just next to the main consumer,
skb_pp_recycle(), and rename it to napi_pp_put_page(), as it doesn't
work with skbs at all and the former name tells nothing. The #if guards
here are only to not compile and have it in the vmlinux when not needed
-- both call sites are already guarded.
Now, touching page_pool_types.h only triggers rebuilding of the drivers
using it and a couple of core networking files.
Suggested-by: Jakub Kicinski <kuba@kernel.org> # make skbuff.h less heavy
Suggested-by: Alexander Duyck <alexanderduyck@fb.com> # move to skbuff.c
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-3-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Split types and pure function declarations from page_pool.h
and add them in page_page/types.h, so that C sources can
include page_pool.h and headers should generally only include
page_pool/types.h as suggested by jakub.
Rename page_pool.h to page_pool/helpers.h to have both in
one place.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-2-aleksander.lobakin@intel.com
[Jakub: change microsoft/mana, fix kdoc paths in Documentation]
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----
iQFHBAABCgAxFiEEDs2BvajyNKlf9TJQvlAcSiqKBOgFAmTQn1YTHG1rbEBwZW5n
dXRyb25peC5kZQAKCRC+UBxKKooE6Eh3CACQmSMV6FLXhFsOUzQS9ZyiKwQaAMG7
1giCbXRJS6CiyHIbkye/h7AIC4WYcr9bTXxFTLypWBMqo9uFEm/jiFRPMyJcPsZa
g8ySbQqkYeaGb0RkrHFbChsJaSnZhH1niatrAw+Vk2jeh/3Dait+LPFtdDWbLFsw
6mPoZMv18tVy1r/0kiqPCive1Gie3eKzmVwBk9AK6XVUPS88bX7OKRppoRXv3f9x
DpNKfJjhyWtBCoK8wsR3vVc1jRNL3eeLN7t8E7zYhfKRQsts1rVnyrWdihEjZ9ik
e97oMG5Zeu8yStYiAkbGjNlhs1Uujlzc3yJoN0tuIFvniD2xC4bxeZ+X
=X3r+
-----END PGP SIGNATURE-----
Merge tag 'linux-can-next-for-6.6-20230807' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next
Marc Kleine-Budde says:
====================
pull-request: can-next 2023-08-07
The patch is from me and reverts the addition of the CAN controller
nodes in the allwinner d1 SoC.
* tag 'linux-can-next-for-6.6-20230807' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next:
Revert "riscv: dts: allwinner: d1: Add CAN controller nodes"
====================
Link: https://lore.kernel.org/r/20230807074222.1576119-1-mkl@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
As the i.MX8MP supports reading MAC propagation delay and correcting the
Hardware timestamp counter for additional delays [1], enable the feature
for this SoC.
This reduces phase error of the PPS output from the PTP Hardware Clock
from approx 150ns to 100ns.
[1] i.MX8MP Reference Manual, rev.1 Section 11.7.2.5.3 "Timestamp
correction"
Signed-off-by: Johannes Zink <j.zink@pengutronix.de>
Link: https://lore.kernel.org/r/20230719-stmmac_correct_mac_delay-v3-2-61e63427735e@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The IEEE1588 Standard specifies that the timestamps of Packets must be
captured when the PTP message timestamp point (leading edge of first
octet after the start of frame delimiter) crosses the boundary between
the node and the network. As the MAC latches the timestamp at an
internal point, the captured timestamp must be corrected for the
additional data transmission latency, as described in the publicly
available datasheet [1].
This patch only corrects for the MAC-Internal delay, which can be read
out from the MAC_Ingress_Timestamp_Latency register on DWMAC version 5,
since the Phy framework currently does not support querying the Phy
ingress and egress latency. The Closs Domain Crossing Circuits errors as
indicated in [1] are already being accounted in the
stmmac_get_tx_hwtstamp() function and are not corrected here.
As the Latency varies for different link speeds and MII
modes of operation, the correction value needs to be updated on each
link state change.
As the delay also causes a phase shift in the timestamp counter compared
to the rest of the network, this correction will also reduce phase error
when generating PPS outputs from the timestamp counter.
Since the correction registers may be unavailable on some hardware and
no feature bits are documented for dynamically detection of the MAC
propagation delay readout, introduce a feature bit to explicitely enable
MAC delay Correction in the gluecode driver.
[1] i.MX8MP Reference Manual, rev.1 Section 11.7.2.5.3 "Timestamp
correction"
Signed-off-by: Johannes Zink <j.zink@pengutronix.de>
Link: https://lore.kernel.org/r/20230719-stmmac_correct_mac_delay-v2-1-3366f38ee9a6@pengutronix.de
Link: https://lore.kernel.org/r/20230719-stmmac_correct_mac_delay-v3-1-61e63427735e@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit 6ba5a3c52d ("[UDP]: Make full use of proto.h.udp_hash innovation.")
removed these implementations but leave declarations.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit ce0aa27ff3 ("sfp: add sfp-bus to bridge between network devices and sfp cages")
declared but never implemented it.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit f8572d8f2a ("sysctl net: Remove unused binary sysctl code")
left behind this declaration.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit acb674428c ("net: sched: introduce per-block callbacks")
implemented these but never used it.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
pneigh_for_each() is never implemented since the beginning of git history.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 3c4d755915 ("tls: kernel TLS support") declared but never implemented
these functions.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Setting dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS is only legal
for drivers which were converted to ndo_hwtstamp_get() and
ndo_hwtstamp_set(), and it is only there that we call ndo_hwtstamp_set()
for a request that otherwise goes to phylib (for stuff like packet traps,
which need to be undone if phylib failed, hence the old_cfg logic).
The problem is that we end up calling ndo_hwtstamp_get() when we don't
need to (even if the SIOCSHWTSTAMP wasn't intended for phylib, or if it
was, but the driver didn't set IFF_SEE_ALL_HWTSTAMP_REQUESTS). For those
unnecessary conditions, we share a code path with virtual drivers (vlan,
macvlan, bonding) where ndo_hwtstamp_get() is implemented as
generic_hwtstamp_get_lower(), and may be resolved through
generic_hwtstamp_ioctl_lower() if the lower device is unconverted.
I.e. this situation:
$ ip link add link eno0 name eno0.100 type vlan id 100
$ hwstamp_ctl -i eno0.100 -t 1
We are unprepared to deal with this, because if ndo_hwtstamp_get() is
resolved through a legacy ndo_eth_ioctl(SIOCGHWTSTAMP) lower_dev
implementation, that needs a non-NULL old_cfg.ifr pointer, and we don't
have it.
But we don't even need to deal with it either. In the general case,
drivers may not even implement SIOCGHWTSTAMP handling, only SIOCSHWTSTAMP,
so it makes sense to completely avoid a SIOCGHWTSTAMP call if we can.
The solution is to split the single "if" condition into 3 smaller ones,
thus separating the decision to call ndo_hwtstamp_get() from the
decision to call ndo_hwtstamp_set(). The third "if" condition is
identical to the first one, and both are subsets of the second one.
Thus, the "cfg" argument of kernel_hwtstamp_config_changed() is always
valid.
Reported-by: Eric Dumazet <edumazet@google.com>
Closes: https://lore.kernel.org/netdev/CANn89iLOspJsvjPj+y8jikg7erXDomWe8sqHMdfL_2LQSFrPAg@mail.gmail.com/
Fixes: fd770e856e ("net: remove phy_has_hwtstamp() -> phy_mii_ioctl() decision from converted drivers")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use eth_broadcast_addr() to assign broadcast address instead
of memset().
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
gcc with W=1 reports
drivers/net/ethernet/ibm/ibmvnic.c:194:13: warning: variable 'rc' set but not used [-Wunused-but-set-variable]
^
This variable is not used so remove it.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308040609.zQsSXWXI-lkp@intel.com/
Signed-off-by: Yu Liao <liaoyu15@huawei.com>
Reviewed-by: Nick Child <nnac123@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add page pool for RX buffers for faster buffer cycle and reduce CPU
usage.
The standard page pool API is used.
With iperf and 128 threads test, this patch improved the throughput
by 12-15%, and decreased the IRQ associated CPU's usage from 99-100% to
10-50%.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rushil Gupta says:
====================
gve: Add QPL mode for DQO descriptor format
GVE supports QPL ("queue-page-list") mode where
all data is communicated through a set of pre-registered
pages. Adding this mode to DQO.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a note about QPL and RDA mode
Signed-off-by: Rushil Gupta <rushilg@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Bailey Forrest <bcf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The RX path allocates the QPL page pool at queue creation, and
tries to reuse these pages through page recycling. This patch
ensures that on refill no non-QPL pages are posted to the device.
When the driver is running low on free buffers, an ondemand
allocation step kicks in that allocates a non-qpl page for
SKB business to free up the QPL page in use.
gve_try_recycle_buf was moved to gve_rx_append_frags so that driver does
not attempt to mark buffer as used if a non-qpl page was allocated
ondemand.
Signed-off-by: Rushil Gupta <rushilg@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Bailey Forrest <bcf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Each QPL page is divided into GVE_TX_BUFS_PER_PAGE_DQO buffers.
When a packet needs to be transmitted, we break the packet into max
GVE_TX_BUF_SIZE_DQO sized chunks and transmit each chunk using a TX
descriptor.
We allocate the TX buffers from the free list in dqo_tx.
We store these TX buffer indices in an array in the pending_packet
structure.
The TX buffers are returned to the free list in dqo_compl after
receiving packet completion or when removing packets from miss
completions list.
Signed-off-by: Rushil Gupta <rushilg@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Bailey Forrest <bcf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
GVE supports QPL ("queue-page-list") mode where
all data is communicated through a set of pre-registered
pages. Adding this mode to DQO descriptor format.
Add checks, abi-changes and device options to support
QPL mode for DQO in addition to GQI. Also, use
pages-per-qpl supplied by device-option to control the
size of the "queue-page-list".
Signed-off-by: Rushil Gupta <rushilg@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Bailey Forrest <bcf@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet says:
====================
tcp: set few options locklessly
This series is avoiding the socket lock for six TCP options.
They are not heavily used, but this exercise can give
ideas for other parts of TCP/IP stack :)
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
rskq_defer_accept field can be read/written without
the need of holding the socket lock.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tp->linger2 can be set locklessly as long as readers
use READ_ONCE().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tp->keepalive_probes can be set locklessly, readers
are already taking care of this field being potentially
set by other threads.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tp->keepalive_intvl can be set locklessly, readers
are already taking care of this field being potentially
set by other threads.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
icsk->icsk_user_timeout can be set locklessly,
if all read sides use READ_ONCE().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
icsk->icsk_syn_retries can safely be set without locking the socket.
We have to add READ_ONCE() annotations in tcp_fastopen_synack_timer()
and tcp_write_timeout().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The first pull request for v6.6 and only driver patches this time.
Nothing special really standing out, it has been quiet most likely due
to vacations.
Major changes:
rtl8xxxu
* enable AP mode for: RTL8192FU, RTL8710BU (RTL8188GU), RTL8192EU and RTL8723BU
mwifiex
* allow moving to a different namespace
mt76
* preparation for mt7925 support
* mt7981 support
ath12k
* Extremely High Throughput (EHT) PHY support for Wi-Fi 7
-----BEGIN PGP SIGNATURE-----
iQFFBAABCgAvFiEEiBjanGPFTz4PRfLobhckVSbrbZsFAmTM6gkRHGt2YWxvQGtl
cm5lbC5vcmcACgkQbhckVSbrbZuuAggAjRQi7Vjsfr+GlZ+g/y/vf+ircw8YjKgy
wJqnQ0fnJ4rpyxqVFjMr+ocuOrdBufTSs/W4fqOBbbg9oimsgg+vxIQA8GmQIUVQ
ZQVWQHVqPLQ6NVp/YZJnt9seeCewGHW6UZxG9k0MqR1RJn+KinmSjWKRo1D56niL
rJQAK0FWrVqkj5nt9lKRJLMGxX0k/ftrdZgHanUOVCNYi9Ukx0jXSbqSMftTk7xz
r3jtuY5zAV+2GXoMIbW4ogBks4Yx06XzVycByzj+dYt5E3VBdDFX+mXlsw9vnjbv
whVzsuMnYBu6CCFlKDPdGsmrzZA0GrLCRZE9uw7yhwZZ+qKkQZ8kNw==
=5r3T
-----END PGP SIGNATURE-----
Merge tag 'wireless-next-2023-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next
Kalle Valo says:
====================
wireless-next patches for v6.6
The first pull request for v6.6 and only driver patches this time.
Nothing special really standing out, it has been quiet most likely due
to vacations.
Major changes:
rtl8xxxu
- enable AP mode for: RTL8192FU, RTL8710BU (RTL8188GU),
RTL8192EU and RTL8723BU
mwifiex
- allow moving to a different namespace
mt76
- preparation for mt7925 support
- mt7981 support
ath12k
- Extremely High Throughput (EHT) PHY support for Wi-Fi 7
* tag 'wireless-next-2023-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next: (172 commits)
wifi: rtw89: return failure if needed firmware elements are not recognized
wifi: rtw89: add to parse firmware elements of BB and RF tables
wifi: rtw89: introduce infrastructure of firmware elements
wifi: rtw89: add firmware suit for BB MCU 0/1
wifi: rtw89: add firmware parser for v1 format
wifi: rtw89: introduce v1 format of firmware header
wifi: rtw89: support firmware log with formatted text
wifi: rtw89: recognize log format from firmware file
wifi: ath12k: avoid deadlock by change ieee80211_queue_work for regd_update_work
wifi: ath12k: add handler for scan event WMI_SCAN_EVENT_DEQUEUED
wifi: ath12k: relax list iteration in ath12k_mac_vif_unref()
wifi: ath12k: configure puncturing bitmap
wifi: ath12k: parse WMI service ready ext2 event
wifi: ath12k: add MLO header in peer association
wifi: ath12k: peer assoc for 320 MHz
wifi: ath12k: add WMI support for EHT peer
wifi: ath12k: prepare EHT peer assoc parameters
wifi: ath12k: add EHT PHY modes
wifi: ath12k: propagate EHT capabilities to userspace
wifi: ath12k: WMI support to process EHT capabilities
...
====================
Link: https://lore.kernel.org/r/87msz7j942.fsf@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Kuniyuki Iwashima says:
====================
tcp: Disable header prediction for MD5.
The 1st patch disable header prediction for MD5 flow and the 2nd
patch updates the stale comment in tcp_parse_options().
====================
Link: https://lore.kernel.org/r/20230803224552.69398-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Since commit 9ea88a1530 ("tcp: md5: check md5 signature without socket
lock"), the MD5 option is checked in tcp_v[46]_rcv().
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230803224552.69398-3-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
TCP socket saves the minimum required header length in tcp_header_len
of struct tcp_sock, and later the value is used in __tcp_fast_path_on()
to generate a part of TCP header in tcp_sock(sk)->pred_flags.
In tcp_rcv_established(), if the incoming packet has the same pattern
with pred_flags, we enter the fast path and skip full option parsing.
The MD5 option is parsed in tcp_v[46]_rcv(), so we need not parse it
again later in tcp_rcv_established() unless other options exist. We
add TCPOLEN_MD5SIG_ALIGNED to tcp_header_len in two paths to avoid the
slow path.
For passive open connections with MD5, we add TCPOLEN_MD5SIG_ALIGNED
to tcp_header_len in tcp_create_openreq_child() after 3WHS.
On the other hand, we do it in tcp_connect_init() for active open
connections. However, the value is overwritten while processing
SYN+ACK or crossed SYN in tcp_rcv_synsent_state_process().
These two cases will have the wrong value in pred_flags and never go
into the fast path.
We could update tcp_header_len in tcp_rcv_synsent_state_process(), but
a test with slightly modified netperf which uses MD5 for each flow shows
that the slow path is actually a bit faster than the fast path.
On c5.4xlarge EC2 instance (16 vCPU, 32 GiB mem)
$ for i in {1..10}; do
./super_netperf $(nproc) -H localhost -l 10 -- -m 256 -M 256;
done
Avg of 10
* 36e68eadd3 : 10.376 Gbps
* all fast path : 10.374 Gbps (patch v2, See Link)
* all slow path : 10.394 Gbps
The header prediction is not worth adding complexity for MD5, so let's
disable it for MD5.
Link: https://lore.kernel.org/netdev/20230803042214.38309-1-kuniyu@amazon.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230803224552.69398-2-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Move marking the PHY as being on a SFP module into the SFP code between
getting the PHY device (and thus initialising the phy_device structure)
and registering the discovered device.
This means that PHY drivers can use phy_on_sfp() in their match and
get_features methods.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1qRaga-001vKt-8X@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit c3d2ed93b1 ("mlxsw: Remove old parsing depth infrastructure")
left behind mlxsw_sp_nve_inc_parsing_depth_get()/mlxsw_sp_nve_inc_parsing_depth_put().
And commit 532b49e41e ("mlxsw: spectrum_span: Derive SBIB from maximum port speed & MTU")
remove mlxsw_sp_span_port_mtu_update()/mlxsw_sp_span_speed_update_work() but leave the
declarations.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://lore.kernel.org/r/20230803142047.42660-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
ixgbe_napi_add_all()/ixgbe_napi_del_all() are declared but never implemented in
commit 92915f7120 ("ixgbevf: Driver main and ethool interface module and main header")
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230803141904.15316-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit d021c34405 ("VSOCK: Introduce VM Sockets") declared but never implemented
vsock_release_pending(). Also vsock_init_tap() never implemented since introduction
in commit 531b374834 ("VSOCK: Add vsockmon tap functions").
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://lore.kernel.org/r/20230803134507.22660-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit d8d9ba8dc9 ("net: 802: remove dead leftover after ipx driver removal")
remove these implementations but leave the declarations.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230803135424.41664-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
After commit 098a697b49 ("tcp_metrics: Use a single hash table
for all network namespaces.") we can avoid calling tcp_net_metrics_init()
for each new netns.
Instead, rename tcp_net_metrics_init() to tcp_metrics_hash_alloc(),
and move it to __init section.
Also move tcpmhash_entries to __initdata section.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230803135417.2716879-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
llc_conn_ac_send_i_rsp_as_ack() and llc_conn_ev_sendack_tmr_exp()
are never implemented since beginning of git history.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230803134747.41512-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Jiri Pirko says:
====================
devlink: use spec to generate split ops
This is an outcome of the discussion in the following thread:
https://lore.kernel.org/netdev/20230720121829.566974-1-jiri@resnulli.us/
It serves as a dependency on the linked selector patchset.
There is an existing spec for devlink used for userspace part
generation. There are two commands supported there.
This patchset extends the spec so kernel split ops code could
be generated from it.
====================
Link: https://lore.kernel.org/r/20230803111340.1074067-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Do the switch and use generated split ops for get and info_get commands.
Remove those from small ops array.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-13-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Put the newly added generated header to the include list. Remove the
duplicated temporary function prototypes.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-12-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Improve the existing devlink spec in order to serve as a source for
generation of valid devlink split ops for the existing commands.
Add the generated sources.
Node that the policies are narrowed down only to the attributes that
are actually parsed. The dont-validate-strict parsing policy makes sure
that other possibly passed garbage attributes from userspace are
ignored during validation.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-11-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add missing dump op for info-get command and re-generate related
devlink-user.[ch] code.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20230803111340.1074067-10-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
