- 03 Mar, 2022 18 commits
-
-
David S. Miller authored
Joe Damato says: ==================== page_pool: Add stats counters Greetings: Welcome to v9. This revisions adds a commit which updates the page_pool documentation to describe the stats API, structures, and fields. Additionally, this revision contains a minor cosmetic change suggested by Saeed in page_pool_recycle_in_ring in commit 2: "page_pool: Add recycle stats", which removes an unnecessary #ifdef. There are no functional changes in this revision. Benchmark output from the v7 cover [1] is pasted below, as it is still relevant since no functional changes have been made in this revision: Benchmarks have been re-run. As always, results between runs are highly variable; you'll find results showing that stats disabled are both faster and slower than stats enabled in back to back benchmark runs. Raw benchmark output with stats off [2] and stats on [3] are available for examination. Test system: - 2x Intel(R) Xeon(R) Gold 6140 CPU @ 2.30GHz - 2 NUMA zones, with 18 cores per zone and 2 threads per core bench_page_pool_simple results, loops=200000000 test name stats enabled stats disabled cycles nanosec cycles nanosec for_loop 0 0.335 0 0.336 atomic_inc 14 6.106 13 6.022 lock 30 13.365 32 13.968 no-softirq-page_pool01 75 32.884 74 32.308 no-softirq-page_pool02 79 34.696 74 32.302 no-softirq-page_pool03 110 48.005 105 46.073 tasklet_page_pool01_fast_path 14 6.156 14 6.211 tasklet_page_pool02_ptr_ring 41 18.028 39 17.391 tasklet_page_pool03_slow 107 46.646 105 46.123 bench_page_pool_cross_cpu results, loops=20000000 returning_cpus=4: test name stats enabled stats disabled cycles nanosec cycles nanosec page_pool_cross_cpu CPU(0) 3973 1731.596 4015 1750.015 page_pool_cross_cpu CPU(1) 3976 1733.217 4022 1752.864 page_pool_cross_cpu CPU(2) 3973 1731.615 4016 1750.433 page_pool_cross_cpu CPU(3) 3976 1733.218 4021 1752.806 page_pool_cross_cpu CPU(4) 994 433.305 1005 438.217 page_pool_cross_cpu average 3378 - 3415 - bench_page_pool_cross_cpu results, loops=20000000 returning_cpus=8: test name stats enabled stats disabled cycles nanosec cycles nanosec page_pool_cross_cpu CPU(0) 6969 3037.488 6909 3011.463 page_pool_cross_cpu CPU(1) 6974 3039.469 6913 3012.961 page_pool_cross_cpu CPU(2) 6969 3037.575 6910 3011.585 page_pool_cross_cpu CPU(3) 6974 3039.415 6913 3012.961 page_pool_cross_cpu CPU(4) 6969 3037.288 6909 3011.368 page_pool_cross_cpu CPU(5) 6972 3038.732 6913 3012.920 page_pool_cross_cpu CPU(6) 6969 3037.350 6909 3011.386 page_pool_cross_cpu CPU(7) 6973 3039.356 6913 3012.921 page_pool_cross_cpu CPU(8) 871 379.934 864 376.620 page_pool_cross_cpu average 6293 - 6239 - Thanks. [1]: https://lore.kernel.org/all/1645810914-35485-1-git-send-email-jdamato@fastly.com/ [2]: https://gist.githubusercontent.com/jdamato-fsly/d7c34b9fa7be1ce132a266b0f2b92aea/raw/327dcd71d11ece10238fbf19e0472afbcbf22fd4/v7_stats_disabled [3]: https://gist.githubusercontent.com/jdamato-fsly/d7c34b9fa7be1ce132a266b0f2b92aea/raw/327dcd71d11ece10238fbf19e0472afbcbf22fd4/v7_stats_enabled v8 -> v9: - Add documentation about the page_pool_get_stats API, stats structures, and fields to Documentation/networking/page_pool.rst. - Remove unnecessary #ifdef in page_pool_recycle_in_ring. v7 -> v8: - Rename mlx5 ethtool stats so that users have a better idea of their meaning. v6 -> v7: - stats split out into two structs one single per-page pool struct for allocation path stats and one per-cpu pointer for recycle path stats. - page_pool_get_stats updated to use a wrapper struct to gather stats for allocation and recycle stats with a single argument. - placement of structs adjusted - mlx5 driver modified to use page_pool_get_stats API v5 -> v6: - Per cpu page_pool_stats struct pointer is now marked as ____cacheline_aligned_in_smp. Placement of the field in the struct is unchanged; it is the last field. v4 -> v5: - Fixed the description of the kernel option in Kconfig. - Squashed commits 1-10 from v4 into a single commit for easier review. - Changed the comment style of the comment for the this_cpu_inc_alloc_stat macro. - Changed the return type of page_pool_get_stats from struct page_pool_stat * to bool. v3 -> v4: - Restructured stats to be per-cpu per-pool. - Global stats and proc file were removed. - Exposed an API (page_pool_get_stats) for batching the pool stats. v2 -> v3: - patch 8/10 ("Add stat tracking cache refill") fixed placement of counter increment. - patch 10/10 ("net-procfs: Show page pool stats in proc") updated: - fix unused label warning from kernel test robot, - fixed page_pool_seq_show to only display the refill stat once, - added a remove_proc_entry for page_pool_stat to dev_proc_net_exit. v1 -> v2: - A new kernel config option has been added, which defaults to N, preventing this code from being compiled in by default - The stats structure has been converted to a per-cpu structure - The stats are now exported via proc (/proc/net/page_pool_stat) ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Joe Damato authored
This change adds support for the page_pool_get_stats API to mlx5. If the user has enabled CONFIG_PAGE_POOL_STATS in their kernel, ethtool will output page pool stats. Signed-off-by:
Joe Damato <jdamato@fastly.com> Acked-by:
Saeed Mahameed <saeed@kernel.org> Signed-off-by:
-
Joe Damato authored
Add the new stats API, kernel config parameter, and stats structure information to the page_pool documentation. Signed-off-by:
-
Joe Damato authored
Adds a function page_pool_get_stats which can be used by drivers to obtain stats for a specified page_pool. Signed-off-by:
Jesper Dangaard Brouer <brouer@redhat.com> Reviewed-by:
Ilias Apalodimas <ilias.apalodimas@linaro.org> Signed-off-by:
-
Joe Damato authored
Add per-cpu stats tracking page pool recycling events: - cached: recycling placed page in the page pool cache - cache_full: page pool cache was full - ring: page placed into the ptr ring - ring_full: page released from page pool because the ptr ring was full - released_refcnt: page released (and not recycled) because refcnt > 1 Signed-off-by:
-
Joe Damato authored
Add per-pool statistics counters for the allocation path of a page pool. These stats are incremented in softirq context, so no locking or per-cpu variables are needed. This code is disabled by default and a kernel config option is provided for users who wish to enable them. The statistics added are: - fast: successful fast path allocations - slow: slow path order-0 allocations - slow_high_order: slow path high order allocations - empty: ptr ring is empty, so a slow path allocation was forced. - refill: an allocation which triggered a refill of the cache - waive: pages obtained from the ptr ring that cannot be added to the cache due to a NUMA mismatch. Signed-off-by:
-
Tao Chen authored
Last tcp_write_queue_head() use was removed in commit 114f39fe ("tcp: restore autocorking"), so remove it. Signed-off-by:
Tao Chen <chentao3@hotmail.com> Link: https://lore.kernel.org/r/SYZP282MB33317DEE1253B37C0F57231E86029@SYZP282MB3331.AUSP282.PROD.OUTLOOK.COMSigned-off-by:
Jakub Kicinski <kuba@kernel.org>
-
Kurt Kanzenbach authored
Network drivers such as igb or igc call eth_get_headlen() to determine the header length for their to be constructed skbs in receive path. When running HSR on top of these drivers, it results in triggering BUG_ON() in skb_pull(). The reason is the skb headlen is not sufficient for HSR to work correctly. skb_pull() notices that. For instance, eth_get_headlen() returns 14 bytes for TCP traffic over HSR which is not correct. The problem is, the flow dissection code does not take HSR into account. Therefore, add support for it. Reported-by:
Anthony Harivel <anthony.harivel@linutronix.de> Signed-off-by:
Kurt Kanzenbach <kurt@linutronix.de> Link: https://lore.kernel.org/r/20220228195856.88187-1-kurt@linutronix.deSigned-off-by:
-
Baruch Siach authored
Add support for direct RMII MAC mode. This allows hardware with CPU port connected in direct 100M fixed link to work properly. Signed-off-by:
Baruch Siach <baruch.siach@siklu.com> Link: https://lore.kernel.org/r/a962d1ccbeec42daa10dd8aff0e66e31f0faf1eb.1646050203.git.baruch@tkos.co.ilSigned-off-by:
-
Baruch Siach authored
When the given cmode has no serdes, mv88e6xxx_serdes_get_lane() returns -NODEV. Earlier in the same function the code skips serdes handing in this case. Do the same after cmode set. Signed-off-by:
-
Yang Li authored
Eliminate the following coccicheck warning: ./net/openvswitch/flow.c:379:2-3: Unneeded semicolon Reported-by:
Abaci Robot <abaci@linux.alibaba.com> Signed-off-by:
Yang Li <yang.lee@linux.alibaba.com> Link: https://lore.kernel.org/r/20220227132208.24658-1-yang.lee@linux.alibaba.comSigned-off-by:
-
Baowen Zheng authored
Add extack message to return exact message to user when adding invalid filter with conflict flags for TC action. In previous implement we just return EINVAL which is confusing for user. Signed-off-by:
Baowen Zheng <baowen.zheng@corigine.com> Reviewed-by:
Roi Dayan <roid@nvidia.com> Link: https://lore.kernel.org/r/1646191769-17761-1-git-send-email-baowen.zheng@corigine.comSigned-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queueJakub Kicinski authored
Tony Nguyen says: ==================== 40GbE Intel Wired LAN Driver Updates 2022-03-01 This series contains updates to iavf driver only. Mateusz adds support for interrupt moderation for 50G and 100G speeds as well as support for the driver to specify a request as its primary MAC address. He also refactors VLAN V2 capability exchange into more generic extended capabilities to ease the addition of future capabilities. Finally, he corrects the incorrect return of iavf_status values and removes non-inclusive language. Minghao Chi removes unneeded variables, instead returning values directly. * '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue: iavf: Remove non-inclusive language iavf: Fix incorrect use of assigning iavf_status to int iavf: stop leaking iavf_status as "errno" values iavf: remove redundant ret variable iavf: Add usage of new virtchnl format to set default MAC iavf: refactor processing of VLAN V2 capability message iavf: Add support for 50G/100G in AIM algorithm ==================== Link: https://lore.kernel.org/r/20220301185939.3005116-1-anthony.l.nguyen@intel.comSigned-off-by:
-
Christophe JAILLET authored
Use ida_alloc_xxx()/ida_free() instead to ida_simple_get()/ida_simple_remove(). The latter is deprecated and more verbose. Signed-off-by:
Christophe JAILLET <christophe.jaillet@wanadoo.fr> Signed-off-by:
Simon Horman <simon.horman@corigine.com> Link: https://lore.kernel.org/r/20220301131212.26348-1-simon.horman@corigine.comSigned-off-by:
-
Russell King (Oracle) authored
Convert sfp to use %pe for printing error codes, which can print them as errno symbols rather than numbers. Signed-off-by:
Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Reviewed-by:
Andrew Lunn <andrew@lunn.ch> Link: https://lore.kernel.org/r/E1nOyEN-00BuuE-OB@rmk-PC.armlinux.org.ukSigned-off-by:
-
Russell King (Oracle) authored
Convert phylink to use %pe for printing error codes, which can print them as errno symbols rather than numbers. Signed-off-by:
-
Harold Huang authored
In patch [1], tun_msg_ctl was added to allow pass batched xdp buffers to tun_sendmsg. Although we donot use msg_controllen in this path, we should check msg_controllen to make sure the caller pass a valid msg_ctl. [1]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=fe8dd45bb7556246c6b76277b1ba4296c91c2505Reported-by:
Eric Dumazet <eric.dumazet@gmail.com> Suggested-by:
Jason Wang <jasowang@redhat.com> Signed-off-by:
Harold Huang <baymaxhuang@gmail.com> Acked-by:
-
git://git.open-mesh.org/linux-mergeJakub Kicinski authored
Simon Wunderlich says: ==================== This cleanup patchset includes the following patches: - bump version strings, by Simon Wunderlich - Remove redundant 'flush_workqueue()' calls, by Christophe JAILLET - Migrate to linux/container_of.h, by Sven Eckelmann - Demote batadv-on-batadv skip error message, by Sven Eckelmann * tag 'batadv-next-pullrequest-20220302' of git://git.open-mesh.org/linux-merge: batman-adv: Demote batadv-on-batadv skip error message batman-adv: Migrate to linux/container_of.h batman-adv: Remove redundant 'flush_workqueue()' calls batman-adv: Start new development cycle ==================== Link: https://lore.kernel.org/r/20220302163522.102842-1-sw@simonwunderlich.deSigned-off-by:
-
- 02 Mar, 2022 13 commits
-
-
Wang Qing authored
add missing ")" which caused by previous commit. Fixes: 61c4fb9c ("net: hamradio: use time_is_after_jiffies() instead of open coding it") Link: https://lore.kernel.org/all/1646018012-61129-1-git-send-email-wangqing@vivo.com/Signed-off-by:
Wang Qing <wangqing@vivo.com> Link: https://lore.kernel.org/r/1646203277-83159-1-git-send-email-wangqing@vivo.comSigned-off-by:
-
Sven Eckelmann authored
The error message "Cannot find parent device" was shown for users of macvtap (on batadv devices) whenever the macvtap was moved to a different netns. This happens because macvtap doesn't provide an implementation for rtnl_link_ops->get_link_net. The situation for which this message is printed is actually not an error but just a warning that the optional sanity check was skipped. So demote the message from error to warning and adjust the text to better explain what happened. Reported-by:
Leonardo Mörlein <freifunk@irrelefant.net> Signed-off-by:
Sven Eckelmann <sven@narfation.org> Signed-off-by:
Simon Wunderlich <sw@simonwunderlich.de>
-
Sven Eckelmann authored
The commit d2a8ebbf ("kernel.h: split out container_of() and typeof_member() macros") introduced a new header for the container_of related macros from (previously) linux/kernel.h. Signed-off-by:
-
Jakub Kicinski authored
Daniel Braunwarth says: ==================== if_ether.h: add industrial fieldbus Ethertypes This set of patches adds the Ethertypes for PROFINET and EtherCAT. The defines should be used by iproute2 to extend the list of available link layer protocols. ==================== Link: https://lore.kernel.org/r/20220228133029.100913-1-daniel@braunwarth.devSigned-off-by:
-
Daniel Braunwarth authored
Add the Ethertype for EtherCAT protocol. Signed-off-by:
Daniel Braunwarth <daniel@braunwarth.dev> Signed-off-by:
-
Daniel Braunwarth authored
Add the Ethertype for PROFINET protocol. Signed-off-by:
-
Sven Eckelmann authored
Assign rtnl_link_ops->get_link_net() callback so that IFLA_LINK_NETNSID is added to rtnetlink messages. This fixes iproute2 which otherwise resolved the link interface to an interface in the wrong namespace. Test commands: ip netns add nst ip link add dummy0 type dummy ip link add link macvtap0 link dummy0 type macvtap ip link set macvtap0 netns nst ip -netns nst link show macvtap0 Before: 10: macvtap0@gre0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 500 link/ether 5e:8f:ae:1d:60:50 brd ff:ff:ff:ff:ff:ff After: 10: macvtap0@if2: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode DEFAULT group default qlen 500 link/ether 5e:8f:ae:1d:60:50 brd ff:ff:ff:ff:ff:ff link-netnsid 0 Reported-by: -
Wan Jiabing authored
Fix the following coccicheck warning: ./drivers/net/ethernet/netronome/nfp/flower/qos_conf.c:750:7-55: WARNING avoid newline at end of message in NL_SET_ERR_MSG_MOD Signed-off-by:
Wan Jiabing <wanjiabing@vivo.com> Reviewed-by:
-
Harold Huang authored
In tun, NAPI is supported and we can also use NAPI in the path of batched XDP buffs to accelerate packet processing. What is more, after we use NAPI, GRO is also supported. The iperf shows that the throughput of single stream could be improved from 4.5Gbps to 9.2Gbps. Additionally, 9.2 Gbps nearly reachs the line speed of the phy nic and there is still about 15% idle cpu core remaining on the vhost thread. Test topology: [iperf server]<--->tap<--->dpdk testpmd<--->phy nic<--->[iperf client] Iperf stream: iperf3 -c 10.0.0.2 -i 1 -t 10 Before: ... [ 5] 5.00-6.00 sec 558 MBytes 4.68 Gbits/sec 0 1.50 MBytes [ 5] 6.00-7.00 sec 556 MBytes 4.67 Gbits/sec 1 1.35 MBytes [ 5] 7.00-8.00 sec 556 MBytes 4.67 Gbits/sec 2 1.18 MBytes [ 5] 8.00-9.00 sec 559 MBytes 4.69 Gbits/sec 0 1.48 MBytes [ 5] 9.00-10.00 sec 556 MBytes 4.67 Gbits/sec 1 1.33 MBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate Retr [ 5] 0.00-10.00 sec 5.39 GBytes 4.63 Gbits/sec 72 sender [ 5] 0.00-10.04 sec 5.39 GBytes 4.61 Gbits/sec receiver After: ... [ 5] 5.00-6.00 sec 1.07 GBytes 9.19 Gbits/sec 0 1.55 MBytes [ 5] 6.00-7.00 sec 1.08 GBytes 9.30 Gbits/sec 0 1.63 MBytes [ 5] 7.00-8.00 sec 1.08 GBytes 9.25 Gbits/sec 0 1.72 MBytes [ 5] 8.00-9.00 sec 1.08 GBytes 9.25 Gbits/sec 77 1.31 MBytes [ 5] 9.00-10.00 sec 1.08 GBytes 9.24 Gbits/sec 0 1.48 MBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bitrate Retr [ 5] 0.00-10.00 sec 10.8 GBytes 9.28 Gbits/sec 166 sender [ 5] 0.00-10.04 sec 10.8 GBytes 9.24 Gbits/sec receiver Reported-at: https://lore.kernel.org/all/CACGkMEvTLG0Ayg+TtbN4q4pPW-ycgCCs3sC3-TF8cuRTf7Pp1A@mail.gmail.comSigned-off-by:
-
Jakub Kicinski authored
Íñigo Huguet says: ==================== sfc: optimize RXQs count and affinities In sfc driver one RX queue per physical core was allocated by default. Later on, IRQ affinities were set spreading the IRQs in all NUMA local CPUs. However, with that default configuration it result in a non very optimal configuration in many modern systems. Specifically, in systems with hyper threading and 2 NUMA nodes, affinities are set in a way that IRQs are handled by all logical cores of one same NUMA node. Handling IRQs from both hyper threading siblings has no benefit, and setting affinities to one queue per physical core is neither a very good idea because there is a performance penalty for moving data across nodes (I was able to check it with some XDP tests using pktgen). This patches reduce the default number of channels to one per physical core in the local NUMA node. Then, they set IRQ affinities to CPUs in the local NUMA node only. This way we save hardware resources since channels are limited resources. We also leave more room for XDP_TX channels without hitting driver's limit of 32 channels per interface. Running performance tests using iperf with a SFC9140 device showed no performance penalty for reducing the number of channels. RX XDP tests showed that performance can go down to less than half if the IRQ is handled by a CPU in a different NUMA node, which doesn't happen with the new defaults from this patches. ==================== Link: https://lore.kernel.org/r/20220228132254.25787-1-ihuguet@redhat.comSigned-off-by:
-
Íñigo Huguet authored
Affinity hints were being set to CPUs in local NUMA node first, and then in other CPUs. This was creating 2 unintended issues: 1. Channels created to be assigned each to a different physical core were assigned to hyperthreading siblings because of being in same NUMA node. Since the patch previous to this one, this did not longer happen with default rss_cpus modparam because less channels are created. 2. XDP channels could be assigned to CPUs in different NUMA nodes, decreasing performance too much (to less than half in some of my tests). This patch sets the affinity hints spreading the channels only in local NUMA node's CPUs. A fallback for the case that no CPU in local NUMA node is online has been added too. Example of CPUs being assigned in a non optimal way before this and the previous patch (note: in this system, xdp-8 to xdp-15 are created because num_possible_cpus == 64, but num_present_cpus == 32 so they're never used): $ lscpu | grep -i numa NUMA node(s): 2 NUMA node0 CPU(s): 0-7,16-23 NUMA node1 CPU(s): 8-15,24-31 $ grep -H . /proc/irq/*/0000:07:00.0*/../smp_affinity_list /proc/irq/141/0000:07:00.0-0/../smp_affinity_list:0 /proc/irq/142/0000:07:00.0-1/../smp_affinity_list:1 /proc/irq/143/0000:07:00.0-2/../smp_affinity_list:2 /proc/irq/144/0000:07:00.0-3/../smp_affinity_list:3 /proc/irq/145/0000:07:00.0-4/../smp_affinity_list:4 /proc/irq/146/0000:07:00.0-5/../smp_affinity_list:5 /proc/irq/147/0000:07:00.0-6/../smp_affinity_list:6 /proc/irq/148/0000:07:00.0-7/../smp_affinity_list:7 /proc/irq/149/0000:07:00.0-8/../smp_affinity_list:16 /proc/irq/150/0000:07:00.0-9/../smp_affinity_list:17 /proc/irq/151/0000:07:00.0-10/../smp_affinity_list:18 /proc/irq/152/0000:07:00.0-11/../smp_affinity_list:19 /proc/irq/153/0000:07:00.0-12/../smp_affinity_list:20 /proc/irq/154/0000:07:00.0-13/../smp_affinity_list:21 /proc/irq/155/0000:07:00.0-14/../smp_affinity_list:22 /proc/irq/156/0000:07:00.0-15/../smp_affinity_list:23 /proc/irq/157/0000:07:00.0-xdp-0/../smp_affinity_list:8 /proc/irq/158/0000:07:00.0-xdp-1/../smp_affinity_list:9 /proc/irq/159/0000:07:00.0-xdp-2/../smp_affinity_list:10 /proc/irq/160/0000:07:00.0-xdp-3/../smp_affinity_list:11 /proc/irq/161/0000:07:00.0-xdp-4/../smp_affinity_list:12 /proc/irq/162/0000:07:00.0-xdp-5/../smp_affinity_list:13 /proc/irq/163/0000:07:00.0-xdp-6/../smp_affinity_list:14 /proc/irq/164/0000:07:00.0-xdp-7/../smp_affinity_list:15 /proc/irq/165/0000:07:00.0-xdp-8/../smp_affinity_list:24 /proc/irq/166/0000:07:00.0-xdp-9/../smp_affinity_list:25 /proc/irq/167/0000:07:00.0-xdp-10/../smp_affinity_list:26 /proc/irq/168/0000:07:00.0-xdp-11/../smp_affinity_list:27 /proc/irq/169/0000:07:00.0-xdp-12/../smp_affinity_list:28 /proc/irq/170/0000:07:00.0-xdp-13/../smp_affinity_list:29 /proc/irq/171/0000:07:00.0-xdp-14/../smp_affinity_list:30 /proc/irq/172/0000:07:00.0-xdp-15/../smp_affinity_list:31 CPUs assignments after this and previous patch, so normal channels created only one per core in NUMA node and affinities set only to local NUMA node: $ grep -H . /proc/irq/*/0000:07:00.0*/../smp_affinity_list /proc/irq/116/0000:07:00.0-0/../smp_affinity_list:0 /proc/irq/117/0000:07:00.0-1/../smp_affinity_list:1 /proc/irq/118/0000:07:00.0-2/../smp_affinity_list:2 /proc/irq/119/0000:07:00.0-3/../smp_affinity_list:3 /proc/irq/120/0000:07:00.0-4/../smp_affinity_list:4 /proc/irq/121/0000:07:00.0-5/../smp_affinity_list:5 /proc/irq/122/0000:07:00.0-6/../smp_affinity_list:6 /proc/irq/123/0000:07:00.0-7/../smp_affinity_list:7 /proc/irq/124/0000:07:00.0-xdp-0/../smp_affinity_list:16 /proc/irq/125/0000:07:00.0-xdp-1/../smp_affinity_list:17 /proc/irq/126/0000:07:00.0-xdp-2/../smp_affinity_list:18 /proc/irq/127/0000:07:00.0-xdp-3/../smp_affinity_list:19 /proc/irq/128/0000:07:00.0-xdp-4/../smp_affinity_list:20 /proc/irq/129/0000:07:00.0-xdp-5/../smp_affinity_list:21 /proc/irq/130/0000:07:00.0-xdp-6/../smp_affinity_list:22 /proc/irq/131/0000:07:00.0-xdp-7/../smp_affinity_list:23 /proc/irq/132/0000:07:00.0-xdp-8/../smp_affinity_list:0 /proc/irq/133/0000:07:00.0-xdp-9/../smp_affinity_list:1 /proc/irq/134/0000:07:00.0-xdp-10/../smp_affinity_list:2 /proc/irq/135/0000:07:00.0-xdp-11/../smp_affinity_list:3 /proc/irq/136/0000:07:00.0-xdp-12/../smp_affinity_list:4 /proc/irq/137/0000:07:00.0-xdp-13/../smp_affinity_list:5 /proc/irq/138/0000:07:00.0-xdp-14/../smp_affinity_list:6 /proc/irq/139/0000:07:00.0-xdp-15/../smp_affinity_list:7 Signed-off-by:
Íñigo Huguet <ihuguet@redhat.com> Acked-by:
Martin Habets <habetsm.xilinx@gmail.com> Signed-off-by:
-
Íñigo Huguet authored
Handling channels from CPUs in different NUMA node can penalize performance, so better configure only one channel per core in the same NUMA node than the NIC, and not per each core in the system. Fallback to all other online cores if there are not online CPUs in local NUMA node. Signed-off-by:
-
Jakub Kicinski authored
Fix build: include/linux/minmax.h:45:25: note: in expansion of macro ‘__careful_cmp’ 45 | #define min(x, y) __careful_cmp(x, y, <) | ^~~~~~~~~~~~~ net/smc/smc_tx.c:150:24: note: in expansion of macro ‘min’ 150 | corking_size = min(sock_net(&smc->sk)->smc.sysctl_autocorking_size, | ^~~ Fixes: 12bbb0d1 ("net/smc: add sysctl for autocorking") Link: https://lore.kernel.org/r/20220301222446.1271127-1-kuba@kernel.orgSigned-off-by:
-
- 01 Mar, 2022 9 commits
-
-
Mateusz Palczewski authored
Remove non-inclusive language from the iavf driver. Signed-off-by:
Aleksandr Loktionov <aleksandr.loktionov@intel.com> Signed-off-by:
Mateusz Palczewski <mateusz.palczewski@intel.com> Signed-off-by:
Tony Nguyen <anthony.l.nguyen@intel.com>
-
Mateusz Palczewski authored
Currently there are functions in iavf_virtchnl.c for polling specific virtchnl receive events. These are all assigning iavf_status values to int values. Fix this and explicitly assign int values if iavf_status is not IAVF_SUCCESS. Also, refactor a small amount of duplicated code that can be reused by all of the previously mentioned functions. Finally, fix some spacing errors for variable assignment and get rid of all the goto statements in the refactored functions for clarity. Signed-off-by:
Brett Creeley <brett.creeley@intel.com> Signed-off-by:
Konrad Jankowski <konrad0.jankowski@intel.com> Signed-off-by:
-
Mateusz Palczewski authored
Several functions in the iAVF core files take status values of the enum iavf_status and convert them into integer values. This leads to confusion as functions return both Linux errno values and status codes intermixed. Reporting status codes as if they were "errno" values can lead to confusion when reviewing error logs. Additionally, it can lead to unexpected behavior if a return value is not interpreted properly. Fix this by introducing iavf_status_to_errno, a switch that explicitly converts from the status codes into an appropriate error value. Also introduce a virtchnl_status_to_errno function for the one case where we were returning both virtchnl status codes and iavf_status codes in the same function. Signed-off-by:
Jacob Keller <jacob.e.keller@intel.com> Signed-off-by:
-
Minghao Chi authored
Return value directly instead of taking this in another redundant variable. Reported-by:
Zeal Robot <zealci@zte.com.cn> Signed-off-by:
Minghao Chi <chi.minghao@zte.com.cn> Signed-off-by:
CGEL ZTE <cgel.zte@gmail.com> Tested-by:
-
Mateusz Palczewski authored
Use new type field of VIRTCHNL_OP_ADD_ETH_ADDR and VIRTCHNL_OP_DEL_ETH_ADDR requests to indicate that VF wants to change its default MAC address. Signed-off-by:
Sylwester Dziedziuch <sylwesterx.dziedziuch@intel.com> Signed-off-by:
Jedrzej Jagielski <jedrzej.jagielski@intel.com> Signed-off-by:
-
Mateusz Palczewski authored
In order to handle the capability exchange necessary for VIRTCHNL_VF_OFFLOAD_VLAN_V2, the driver must send a VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS message. This must occur prior to __IAVF_CONFIG_ADAPTER, and the driver must wait for the response from the PF. To handle this, the __IAVF_INIT_GET_OFFLOAD_VLAN_V2_CAPS state was introduced. This state is intended to process the response from the VLAN V2 caps message. This works ok, but is difficult to extend to adding more extended capability exchange. Existing (and future) AVF features are relying more and more on these sort of extended ops for processing additional capabilities. Just like VLAN V2, this exchange must happen prior to __IAVF_CONFIG_ADPATER. Since we only send one outstanding AQ message at a time during init, it is not clear where to place this state. Adding more capability specific states becomes a mess. Instead of having the "previous" state send a message and then transition into a capability-specific state, introduce __IAVF_EXTENDED_CAPS state. This state will use a list of extended_caps that determines what messages to send and receive. As long as there are extended_caps bits still set, the driver will remain in this state performing one send or one receive per state machine loop. Refactor the VLAN V2 negotiation to use this new state, and remove the capability-specific state. This makes it significantly easier to add a new similar capability exchange going forward. Extended capabilities are processed by having an associated SEND and RECV extended capability bit. During __IAVF_EXTENDED_CAPS, the driver checks these bits in order by feature, first the send bit for a feature, then the recv bit for a feature. Each send flag will call a function that sends the necessary response, while each receive flag will wait for the response from the PF. If a given feature can't be negotiated with the PF, the associated flags will be cleared in order to skip processing of that feature. Signed-off-by:
-
Mateusz Palczewski authored
Advanced link speed support was added long back, but adding AIM support was missed. This patch adds AIM support for advanced link speed support, which allows the algorithm to take into account 50G/100G link speeds. Also, other previous speeds are taken into consideration when advanced link speeds are supported. Signed-off-by:
Alexander Lobakin <alexandr.lobakin@intel.com> Tested-by:
-
David S. Miller authored
Dust Li says: ==================== net/smc: some datapath performance optimizations This series tries to improve the performance of SMC in datapath. - patch #1, add sysctl interface to support tuning the behaviour of SMC in container environment. - patch #2/#3, add autocorking support which is very efficient for small messages without trade-off for latency. - patch #4, send directly on setting TCP_NODELAY, without wake up the TX worker, this make it consistent with clearing TCP_CORK. - patch #5, this correct the setting of RMB window update limit, so we don't send CDC messages to update peer's RMB window too frequently in some cases. - patch #6, implemented something like NAPI in SMC, decrease the number of hardirq when busy. - patch #7, this moves TX work doing in the BH to the user context when sock_lock is hold by user. With this patchset applied, we can get a good performance gain: - qperf tcp_bw test has shown a great improvement. Other benchmarks like 'netperf TCP_STREAM' or 'sockperf throughput' has similar result. - In my testing environment, running qperf tcp_bw and tcp_lat, SMC behaves better then TCP in most all message size. Here are some test results with the following testing command: client: smc_run taskset -c 1 qperf smc-server -oo msg_size:1:64K:*2 \ -t 30 -vu tcp_{bw|lat} server: smc_run taskset -c 1 qperf ==== Bandwidth ==== MsgSize Origin SMC TCP SMC with patches 1 0.578 MB/s 2.392 MB/s(313.57%) 2.561 MB/s(342.83%) 2 1.159 MB/s 4.780 MB/s(312.53%) 5.162 MB/s(345.46%) 4 2.283 MB/s 10.266 MB/s(349.77%) 10.122 MB/s(343.46%) 8 4.668 MB/s 19.040 MB/s(307.86%) 20.521 MB/s(339.59%) 16 9.147 MB/s 38.904 MB/s(325.31%) 40.823 MB/s(346.29%) 32 18.369 MB/s 79.587 MB/s(333.25%) 80.535 MB/s(338.42%) 64 36.562 MB/s 148.668 MB/s(306.61%) 158.170 MB/s(332.60%) 128 72.961 MB/s 274.913 MB/s(276.80%) 316.217 MB/s(333.41%) 256 144.705 MB/s 512.059 MB/s(253.86%) 626.019 MB/s(332.62%) 512 288.873 MB/s 884.977 MB/s(206.35%) 1221.596 MB/s(322.88%) 1024 574.180 MB/s 1337.736 MB/s(132.98%) 2203.156 MB/s(283.70%) 2048 1095.192 MB/s 1865.952 MB/s( 70.38%) 3036.448 MB/s(177.25%) 4096 2066.157 MB/s 2380.337 MB/s( 15.21%) 3834.271 MB/s( 85.58%) 8192 3717.198 MB/s 2733.073 MB/s(-26.47%) 4904.910 MB/s( 31.95%) 16384 4742.221 MB/s 2958.693 MB/s(-37.61%) 5220.272 MB/s( 10.08%) 32768 5349.550 MB/s 3061.285 MB/s(-42.77%) 5321.865 MB/s( -0.52%) 65536 5162.919 MB/s 3731.408 MB/s(-27.73%) 5245.021 MB/s( 1.59%) ==== Latency ==== MsgSize Origin SMC TCP SMC with patches 1 10.540 us 11.938 us( 13.26%) 10.356 us( -1.75%) 2 10.996 us 11.992 us( 9.06%) 10.073 us( -8.39%) 4 10.229 us 11.687 us( 14.25%) 9.996 us( -2.28%) 8 10.203 us 11.653 us( 14.21%) 10.063 us( -1.37%) 16 10.530 us 11.313 us( 7.44%) 10.013 us( -4.91%) 32 10.241 us 11.586 us( 13.13%) 10.081 us( -1.56%) 64 10.693 us 11.652 us( 8.97%) 9.986 us( -6.61%) 128 10.597 us 11.579 us( 9.27%) 10.262 us( -3.16%) 256 10.409 us 11.957 us( 14.87%) 10.148 us( -2.51%) 512 11.088 us 12.505 us( 12.78%) 10.206 us( -7.95%) 1024 11.240 us 12.255 us( 9.03%) 10.631 us( -5.42%) 2048 11.485 us 16.970 us( 47.76%) 10.981 us( -4.39%) 4096 12.077 us 13.948 us( 15.49%) 11.847 us( -1.90%) 8192 13.683 us 16.693 us( 22.00%) 13.336 us( -2.54%) 16384 16.470 us 23.615 us( 43.38%) 16.519 us( 0.30%) 32768 22.540 us 40.966 us( 81.75%) 22.452 us( -0.39%) 65536 34.192 us 73.003 us(113.51%) 33.916 us( -0.81%) ------------ Test environment notes: 1. Testing is run on 2 VMs within the same physical host 2. The NIC is ConnectX-4Lx, using SRIOV, and passing through 2 VFs to the 2 VMs respectively. 3. To decrease jitter, VM's vCPU are binded to each physical CPU, and those physical CPUs are all isolated using boot parameter `isolcpus=xxx` 4. The queue number are set to 1, and interrupt from the queue is binded to CPU0 in the guest ==================== Signed-off-by: -
Dust Li authored
Send data all the way down to the RDMA device is a time consuming operation(get a new slot, maybe do RDMA Write and send a CDC, etc). Moving those operations from BH to user context is good for performance. If the sock_lock is hold by user, we don't try to send data out in the BH context, but just mark we should send. Since the user will release the sock_lock soon, we can do the sending there. Add smc_release_cb() which will be called in release_sock() and try send in the callback if needed. This patch moves the sending part out from BH if sock lock is hold by user. In my testing environment, this saves about 20% softirq in the qperf 4K tcp_bw test in the sender side with no noticeable throughput drop. Signed-off-by:
Dust Li <dust.li@linux.alibaba.com> Signed-off-by:
-
