Revision tags: v6.12-rc4 |
|
#
be602cde |
| 17-Oct-2024 |
Ingo Molnar <mingo@kernel.org> |
Merge branch 'linus' into sched/urgent, to resolve conflict
Conflicts: kernel/sched/ext.c
There's a context conflict between this upstream commit:
3fdb9ebcec10 sched_ext: Start schedulers with
Merge branch 'linus' into sched/urgent, to resolve conflict
Conflicts: kernel/sched/ext.c
There's a context conflict between this upstream commit:
3fdb9ebcec10 sched_ext: Start schedulers with consistent p->scx.slice values
... and this fix in sched/urgent:
98442f0ccd82 sched: Fix delayed_dequeue vs switched_from_fair()
Resolve it.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
show more ...
|
Revision tags: v6.12-rc3 |
|
#
1d227fcc |
| 10-Oct-2024 |
Linus Torvalds <torvalds@linux-foundation.org> |
Merge tag 'net-6.12-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski: "Including fixes from bluetooth and netfilter.
Current release - r
Merge tag 'net-6.12-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski: "Including fixes from bluetooth and netfilter.
Current release - regressions:
- dsa: sja1105: fix reception from VLAN-unaware bridges
- Revert "net: stmmac: set PP_FLAG_DMA_SYNC_DEV only if XDP is enabled"
- eth: fec: don't save PTP state if PTP is unsupported
Current release - new code bugs:
- smc: fix lack of icsk_syn_mss with IPPROTO_SMC, prevent null-deref
- eth: airoha: update Tx CPU DMA ring idx at the end of xmit loop
- phy: aquantia: AQR115c fix up PMA capabilities
Previous releases - regressions:
- tcp: 3 fixes for retrans_stamp and undo logic
Previous releases - always broken:
- net: do not delay dst_entries_add() in dst_release()
- netfilter: restrict xtables extensions to families that are safe, syzbot found a way to combine ebtables with extensions that are never used by userspace tools
- sctp: ensure sk_state is set to CLOSED if hashing fails in sctp_listen_start
- mptcp: handle consistently DSS corruption, and prevent corruption due to large pmtu xmit"
* tag 'net-6.12-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (87 commits) MAINTAINERS: Add headers and mailing list to UDP section MAINTAINERS: consistently exclude wireless files from NETWORKING [GENERAL] slip: make slhc_remember() more robust against malicious packets net/smc: fix lacks of icsk_syn_mss with IPPROTO_SMC ppp: fix ppp_async_encode() illegal access docs: netdev: document guidance on cleanup patches phonet: Handle error of rtnl_register_module(). mpls: Handle error of rtnl_register_module(). mctp: Handle error of rtnl_register_module(). bridge: Handle error of rtnl_register_module(). vxlan: Handle error of rtnl_register_module(). rtnetlink: Add bulk registration helpers for rtnetlink message handlers. net: do not delay dst_entries_add() in dst_release() mptcp: pm: do not remove closing subflows mptcp: fallback when MPTCP opts are dropped after 1st data tcp: fix mptcp DSS corruption due to large pmtu xmit mptcp: handle consistently DSS corruption net: netconsole: fix wrong warning net: dsa: refuse cross-chip mirroring operations net: fec: don't save PTP state if PTP is unsupported ...
show more ...
|
Revision tags: v6.12-rc2 |
|
#
096c0fa4 |
| 04-Oct-2024 |
Jakub Kicinski <kuba@kernel.org> |
Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue
Tony Nguyen says:
==================== Intel Wired LAN Driver Updates 2024-09-30 (ice, idpf)
This series cont
Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue
Tony Nguyen says:
==================== Intel Wired LAN Driver Updates 2024-09-30 (ice, idpf)
This series contains updates to ice and idpf drivers:
For ice:
Michal corrects setting of dst VSI on LAN filters and adds clearing of port VLAN configuration during reset.
Gui-Dong Han corrects failures to decrement refcount in some error paths.
Przemek resolves a memory leak in ice_init_tx_topology().
Arkadiusz prevents setting of DPLL_PIN_STATE_SELECTABLE to an improper value.
Dave stops clearing of VLAN tracking bit to allow for VLANs to be properly restored after reset.
For idpf:
Ahmed sets uninitialized dyn_ctl_intrvl_s value.
Josh corrects use and reporting of mailbox size.
Larysa corrects order of function calls during de-initialization.
* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue: idpf: deinit virtchnl transaction manager after vport and vectors idpf: use actual mbx receive payload length idpf: fix VF dynamic interrupt ctl register initialization ice: fix VLAN replay after reset ice: disallow DPLL_PIN_STATE_SELECTABLE for dpll output pins ice: fix memleak in ice_init_tx_topology() ice: clear port vlan config during reset ice: Fix improper handling of refcount in ice_sriov_set_msix_vec_count() ice: Fix improper handling of refcount in ice_dpll_init_rclk_pins() ice: set correct dst VSI in only LAN filters ====================
Link: https://patch.msgid.link/20240930223601.3137464-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
show more ...
|
Revision tags: v6.12-rc1, v6.11, v6.11-rc7 |
|
#
09d0fb5c |
| 04-Sep-2024 |
Larysa Zaremba <larysa.zaremba@intel.com> |
idpf: deinit virtchnl transaction manager after vport and vectors
When the device is removed, idpf is supposed to make certain virtchnl requests e.g. VIRTCHNL2_OP_DEALLOC_VECTORS and VIRTCHNL2_OP_DE
idpf: deinit virtchnl transaction manager after vport and vectors
When the device is removed, idpf is supposed to make certain virtchnl requests e.g. VIRTCHNL2_OP_DEALLOC_VECTORS and VIRTCHNL2_OP_DESTROY_VPORT.
However, this does not happen due to the referenced commit introducing virtchnl transaction manager and placing its deinitialization before those messages are sent. Then the sending is impossible due to no transactions being available.
Lack of cleanup can lead to the FW becoming unresponsive from e.g. unloading-loading the driver and creating-destroying VFs afterwards.
Move transaction manager deinitialization to after other virtchnl-related cleanup is done.
Fixes: 34c21fa894a1 ("idpf: implement virtchnl transaction manager") Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com> Tested-by: Krishneil Singh <krishneil.k.singh@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
show more ...
|
#
640f7006 |
| 03-Sep-2024 |
Joshua Hay <joshua.a.hay@intel.com> |
idpf: use actual mbx receive payload length
When a mailbox message is received, the driver is checking for a non 0 datalen in the controlq descriptor. If it is valid, the payload is attached to the
idpf: use actual mbx receive payload length
When a mailbox message is received, the driver is checking for a non 0 datalen in the controlq descriptor. If it is valid, the payload is attached to the ctlq message to give to the upper layer. However, the payload response size given to the upper layer was taken from the buffer metadata which is _always_ the max buffer size. This meant the API was returning 4K as the payload size for all messages. This went unnoticed since the virtchnl exchange response logic was checking for a response size less than 0 (error), not less than exact size, or not greater than or equal to the max mailbox buffer size (4K). All of these checks will pass in the success case since the size provided is always 4K. However, this breaks anyone that wants to validate the exact response size.
Fetch the actual payload length from the value provided in the descriptor data_len field (instead of the buffer metadata).
Unfortunately, this means we lose some extra error parsing for variable sized virtchnl responses such as create vport and get ptypes. However, the original checks weren't really helping anyways since the size was _always_ 4K.
Fixes: 34c21fa894a1 ("idpf: implement virtchnl transaction manager") Cc: stable@vger.kernel.org # 6.9+ Signed-off-by: Joshua Hay <joshua.a.hay@intel.com> Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Tested-by: Krishneil Singh <krishneil.k.singh@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
show more ...
|
#
36ec807b |
| 20-Sep-2024 |
Dmitry Torokhov <dmitry.torokhov@gmail.com> |
Merge branch 'next' into for-linus
Prepare input updates for 6.12 merge window.
|
#
f057b572 |
| 06-Sep-2024 |
Dmitry Torokhov <dmitry.torokhov@gmail.com> |
Merge branch 'ib/6.11-rc6-matrix-keypad-spitz' into next
Bring in changes removing support for platform data from matrix-keypad driver.
|
Revision tags: v6.11-rc6, v6.11-rc5, v6.11-rc4, v6.11-rc3, v6.11-rc2 |
|
#
66e72a01 |
| 29-Jul-2024 |
Jerome Brunet <jbrunet@baylibre.com> |
Merge tag 'v6.11-rc1' into clk-meson-next
Linux 6.11-rc1
|
#
ee057c8c |
| 14-Aug-2024 |
Steven Rostedt <rostedt@goodmis.org> |
Merge tag 'v6.11-rc3' into trace/ring-buffer/core
The "reserve_mem" kernel command line parameter has been pulled into v6.11. Merge the latest -rc3 to allow the persistent ring buffer memory to be a
Merge tag 'v6.11-rc3' into trace/ring-buffer/core
The "reserve_mem" kernel command line parameter has been pulled into v6.11. Merge the latest -rc3 to allow the persistent ring buffer memory to be able to be mapped at the address specified by the "reserve_mem" command line parameter.
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
show more ...
|
#
c8faf11c |
| 30-Jul-2024 |
Tejun Heo <tj@kernel.org> |
Merge tag 'v6.11-rc1' into for-6.12
Linux 6.11-rc1
|
#
ed7171ff |
| 16-Aug-2024 |
Lucas De Marchi <lucas.demarchi@intel.com> |
Merge drm/drm-next into drm-xe-next
Get drm-xe-next on v6.11-rc2 and synchronized with drm-intel-next for the display side. This resolves the current conflict for the enable_display module parameter
Merge drm/drm-next into drm-xe-next
Get drm-xe-next on v6.11-rc2 and synchronized with drm-intel-next for the display side. This resolves the current conflict for the enable_display module parameter and allows further pending refactors.
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
show more ...
|
#
5c61f598 |
| 12-Aug-2024 |
Thomas Zimmermann <tzimmermann@suse.de> |
Merge drm/drm-next into drm-misc-next
Get drm-misc-next to the state of v6.11-rc2.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
|
#
3663e2c4 |
| 01-Aug-2024 |
Jani Nikula <jani.nikula@intel.com> |
Merge drm/drm-next into drm-intel-next
Sync with v6.11-rc1 in general, and specifically get the new BACKLIGHT_POWER_ constants for power states.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
|
#
4436e6da |
| 02-Aug-2024 |
Thomas Gleixner <tglx@linutronix.de> |
Merge branch 'linus' into x86/mm
Bring x86 and selftests up to date
|
#
a1ff5a7d |
| 30-Jul-2024 |
Maxime Ripard <mripard@kernel.org> |
Merge drm/drm-fixes into drm-misc-fixes
Let's start the new drm-misc-fixes cycle by bringing in 6.11-rc1.
Signed-off-by: Maxime Ripard <mripard@kernel.org>
|
Revision tags: v6.11-rc1 |
|
#
a23e1966 |
| 15-Jul-2024 |
Dmitry Torokhov <dmitry.torokhov@gmail.com> |
Merge branch 'next' into for-linus
Prepare input updates for 6.11 merge window.
|
Revision tags: v6.10, v6.10-rc7, v6.10-rc6, v6.10-rc5, v6.10-rc4, v6.10-rc3, v6.10-rc2 |
|
#
6f47c7ae |
| 28-May-2024 |
Dmitry Torokhov <dmitry.torokhov@gmail.com> |
Merge tag 'v6.9' into next
Sync up with the mainline to bring in the new cleanup API.
|
Revision tags: v6.10-rc1 |
|
#
60a2f25d |
| 16-May-2024 |
Tvrtko Ursulin <tursulin@ursulin.net> |
Merge drm/drm-next into drm-intel-gt-next
Some display refactoring patches are needed in order to allow conflict- less merging.
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
|
#
51835949 |
| 17-Jul-2024 |
Linus Torvalds <torvalds@linux-foundation.org> |
Merge tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Not much excitement - a handful of large patchsets (devmem a
Merge tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Not much excitement - a handful of large patchsets (devmem among them) did not make it in time.
Core & protocols:
- Use local_lock in addition to local_bh_disable() to protect per-CPU resources in networking, a step closer for local_bh_disable() not to act as a big lock on PREEMPT_RT
- Use flex array for netdevice priv area, ensure its cache alignment
- Add a sysctl knob to allow user to specify a default rto_min at socket init time. Bit of a big hammer but multiple companies were independently carrying such patch downstream so clearly it's useful
- Support scheduling transmission of packets based on CLOCK_TAI
- Un-pin TCP TIMEWAIT timer to avoid it firing on CPUs later cordoned off using cpusets
- Support multiple L2TPv3 UDP tunnels using the same 5-tuple address
- Allow configuration of multipath hash seed, to both allow synchronizing hashing of two routers, and preventing partial accidental sync
- Improve TCP compliance with RFC 9293 for simultaneous connect()
- Support sending NAT keepalives in IPsec ESP in UDP states. Userspace IKE daemon had to do this before, but the kernel can better keep track of it
- Support sending supervision HSR frames with MAC addresses stored in ProxyNodeTable when RedBox (i.e. HSR-SAN) is enabled
- Introduce IPPROTO_SMC for selecting SMC when socket is created
- Allow UDP GSO transmit from devices with no checksum offload
- openvswitch: add packet sampling via psample, separating the sampled traffic from "upcall" packets sent to user space for forwarding
- nf_tables: shrink memory consumption for transaction objects
Things we sprinkled into general kernel code:
- Power Sequencing subsystem (used by Qualcomm Bluetooth driver for QCA6390) [ Already merged separately - Linus ]
- Add IRQ information in sysfs for auxiliary bus
- Introduce guard definition for local_lock
- Add aligned flavor of __cacheline_group_{begin, end}() markings for grouping fields in structures
BPF:
- Notify user space (via epoll) when a struct_ops object is getting detached/unregistered
- Add new kfuncs for a generic, open-coded bits iterator
- Enable BPF programs to declare arrays of kptr, bpf_rb_root, and bpf_list_head
- Support resilient split BTF which cuts down on duplication and makes BTF as compact as possible WRT BTF from modules
- Add support for dumping kfunc prototypes from BTF which enables both detecting as well as dumping compilable prototypes for kfuncs
- riscv64 BPF JIT improvements in particular to add 12-argument support for BPF trampolines and to utilize bpf_prog_pack for the latter
- Add the capability to offload the netfilter flowtable in XDP layer through kfuncs
Driver API:
- Allow users to configure IRQ tresholds between which automatic IRQ moderation can choose
- Expand Power Sourcing (PoE) status with power, class and failure reason. Support setting power limits
- Track additional RSS contexts in the core, make sure configuration changes don't break them
- Support IPsec crypto offload for IPv6 ESP and IPv4 UDP-encapsulated ESP data paths
- Support updating firmware on SFP modules
Tests and tooling:
- mptcp: use net/lib.sh to manage netns
- TCP-AO and TCP-MD5: replace debug prints used by tests with tracepoints
- openvswitch: make test self-contained (don't depend on OvS CLI tools)
Drivers:
- Ethernet high-speed NICs: - Broadcom (bnxt): - increase the max total outstanding PTP TX packets to 4 - add timestamping statistics support - implement netdev_queue_mgmt_ops - support new RSS context API - Intel (100G, ice, idpf): - implement FEC statistics and dumping signal quality indicators - support E825C products (with 56Gbps PHYs) - nVidia/Mellanox: - support HW-GRO - mlx4/mlx5: support per-queue statistics via netlink - obey the max number of EQs setting in sub-functions - AMD/Solarflare: - support new RSS context API - AMD/Pensando: - ionic: rework fix for doorbell miss to lower overhead and skip it on new HW - Wangxun: - txgbe: support Flow Director perfect filters
- Ethernet NICs consumer, embedded and virtual: - Add driver for Tehuti Networks TN40xx chips - Add driver for Meta's internal NIC chips - Add driver for Ethernet MAC on Airoha EN7581 SoCs - Add driver for Renesas Ethernet-TSN devices - Google cloud vNIC: - flow steering support - Microsoft vNIC: - support page sizes other than 4KB on ARM64 - vmware vNIC: - support latency measurement (update to version 9) - VirtIO net: - support for Byte Queue Limits - support configuring thresholds for automatic IRQ moderation - support for AF_XDP Rx zero-copy - Synopsys (stmmac): - support for STM32MP13 SoC - let platforms select the right PCS implementation - TI: - icssg-prueth: add multicast filtering support - icssg-prueth: enable PTP timestamping and PPS - Renesas: - ravb: improve Rx performance 30-400% by using page pool, theaded NAPI and timer-based IRQ coalescing - ravb: add MII support for R-Car V4M - Cadence (macb): - macb: add ARP support to Wake-On-LAN - Cortina: - use phylib for RX and TX pause configuration
- Ethernet switches: - nVidia/Mellanox: - support configuration of multipath hash seed - report more accurate max MTU - use page_pool to improve Rx performance - MediaTek: - mt7530: add support for bridge port isolation - Qualcomm: - qca8k: add support for bridge port isolation - Microchip: - lan9371/2: add 100BaseTX PHY support - NXP: - vsc73xx: implement VLAN operations
- Ethernet PHYs: - aquantia: enable support for aqr115c - aquantia: add support for PHY LEDs - realtek: add support for rtl8224 2.5Gbps PHY - xpcs: add memory-mapped device support - add BroadR-Reach link mode and support in Broadcom's PHY driver
- CAN: - add document for ISO 15765-2 protocol support - mcp251xfd: workaround for erratum DS80000789E, use timestamps to catch when device returns incorrect FIFO status
- WiFi: - mac80211/cfg80211: - parse Transmit Power Envelope (TPE) data in mac80211 instead of in drivers - improvements for 6 GHz regulatory flexibility - multi-link improvements - support multiple radios per wiphy - remove DEAUTH_NEED_MGD_TX_PREP flag - Intel (iwlwifi): - bump FW API to 91 for BZ/SC devices - report 64-bit radiotap timestamp - enable P2P low latency by default - handle Transmit Power Envelope (TPE) advertised by AP - remove support for older FW for new devices - fast resume (keeping the device configured) - mvm: re-enable Multi-Link Operation (MLO) - aggregation (A-MSDU) optimizations - MediaTek (mt76): - mt7925 Multi-Link Operation (MLO) support - Qualcomm (ath10k): - LED support for various chipsets - Qualcomm (ath12k): - remove unsupported Tx monitor handling - support channel 2 in 6 GHz band - support Spatial Multiplexing Power Save (SMPS) in 6 GHz band - supprt multiple BSSID (MBSSID) and Enhanced Multi-BSSID Advertisements (EMA) - support dynamic VLAN - add panic handler for resetting the firmware state - DebugFS support for datapath statistics - WCN7850: support for Wake on WLAN - Microchip (wilc1000): - read MAC address during probe to make it visible to user space - suspend/resume improvements - TI (wl18xx): - support newer firmware versions - RealTek (rtw89): - preparation for RTL8852BE-VT support - Wake on WLAN support for WiFi 6 chips - 36-bit PCI DMA support - RealTek (rtlwifi): - RTL8192DU support - Broadcom (brcmfmac): - Management Frame Protection support (to enable WPA3)
- Bluetooth: - qualcomm: use the power sequencer for QCA6390 - btusb: mediatek: add ISO data transmission functions - hci_bcm4377: add BCM4388 support - btintel: add support for BlazarU core - btintel: add support for Whale Peak2 - btnxpuart: add support for AW693 A1 chipset - btnxpuart: add support for IW615 chipset - btusb: add Realtek RTL8852BE support ID 0x13d3:0x3591"
* tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1589 commits) eth: fbnic: Fix spelling mistake "tiggerring" -> "triggering" tcp: Replace strncpy() with strscpy() wifi: ath12k: fix build vs old compiler tcp: Don't access uninit tcp_rsk(req)->ao_keyid in tcp_create_openreq_child(). eth: fbnic: Write the TCAM tables used for RSS control and Rx to host eth: fbnic: Add L2 address programming eth: fbnic: Add basic Rx handling eth: fbnic: Add basic Tx handling eth: fbnic: Add link detection eth: fbnic: Add initial messaging to notify FW of our presence eth: fbnic: Implement Rx queue alloc/start/stop/free eth: fbnic: Implement Tx queue alloc/start/stop/free eth: fbnic: Allocate a netdevice and napi vectors with queues eth: fbnic: Add FW communication mechanism eth: fbnic: Add message parsing for FW messages eth: fbnic: Add register init to set PCIe/Ethernet device config eth: fbnic: Allocate core device specific structures and devlink interface eth: fbnic: Add scaffolding for Meta's NIC driver PCI: Add Meta Platforms vendor ID net/sched: cls_flower: propagate tca[TCA_OPTIONS] to NL_REQ_ATTR_CHECK ...
show more ...
|
#
69cf8730 |
| 13-Jul-2024 |
Jakub Kicinski <kuba@kernel.org> |
Merge branch '200GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue
Tony Nguyen says:
==================== idpf: XDP chapter I: convert Rx to libeth
Alexander Lobakin says:
XD
Merge branch '200GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue
Tony Nguyen says:
==================== idpf: XDP chapter I: convert Rx to libeth
Alexander Lobakin says:
XDP for idpf is currently 5 chapters: * convert Rx to libeth (this); * convert Tx and stats to libeth; * generic XDP and XSk code changes, libeth_xdp; * actual XDP for idpf via libeth_xdp; * XSk for idpf (^).
Part I does the following: * splits &idpf_queue into 4 (RQ, SQ, FQ, CQ) and puts them on a diet; * ensures optimal cacheline placement, strictly asserts CL sizes; * moves currently unused/dead singleq mode out of line; * reuses libeth's Rx ptype definitions and helpers; * uses libeth's Rx buffer management for both header and payload; * eliminates memcpy()s and coherent DMA uses on hotpath, uses napi_build_skb() instead of in-place short skb allocation.
Most idpf patches, except for the queue split, removes more lines than adds.
Expect far better memory utilization and +5-8% on Rx depending on the case (+17% on skb XDP_DROP :>).
* '200GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue: idpf: use libeth Rx buffer management for payload buffer idpf: convert header split mode to libeth + napi_build_skb() libeth: support different types of buffers for Rx idpf: remove legacy Page Pool Ethtool stats idpf: reuse libeth's definitions of parsed ptype structures idpf: compile singleq code only under default-n CONFIG_IDPF_SINGLEQ idpf: merge singleq and splitq &net_device_ops idpf: strictly assert cachelines of queue and queue vector structures idpf: avoid bloating &idpf_q_vector with big %NR_CPUS idpf: split &idpf_queue into 4 strictly-typed queue structures idpf: stop using macros for accessing queue descriptors libeth: add cacheline / struct layout assertion helpers page_pool: use __cacheline_group_{begin, end}_aligned() cache: add __cacheline_group_{begin, end}_aligned() (+ couple more) ====================
Link: https://patch.msgid.link/20240710203031.188081-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
show more ...
|
#
74d1412a |
| 20-Jun-2024 |
Alexander Lobakin <aleksander.lobakin@intel.com> |
idpf: use libeth Rx buffer management for payload buffer
idpf uses Page Pool for data buffers with hardcoded buffer lengths of 4k for "classic" buffers and 2k for "short" ones. This is not flexible
idpf: use libeth Rx buffer management for payload buffer
idpf uses Page Pool for data buffers with hardcoded buffer lengths of 4k for "classic" buffers and 2k for "short" ones. This is not flexible and does not ensure optimal memory usage. Why would you need 4k buffers when the MTU is 1500? Use libeth for the data buffers and don't hardcode any buffer sizes. Let them be calculated from the MTU for "classics" and then divide the truesize by 2 for "short" ones. The memory usage is now greatly reduced and 2 buffer queues starts make sense: on frames <= 1024, you'll recycle (and resync) a page only after 4 HW writes rather than two.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
show more ...
|
#
90912f9f |
| 20-Jun-2024 |
Alexander Lobakin <aleksander.lobakin@intel.com> |
idpf: convert header split mode to libeth + napi_build_skb()
Currently, idpf uses the following model for the header buffers:
* buffers are allocated via dma_alloc_coherent(); * when receiving, nap
idpf: convert header split mode to libeth + napi_build_skb()
Currently, idpf uses the following model for the header buffers:
* buffers are allocated via dma_alloc_coherent(); * when receiving, napi_alloc_skb() is called and then the header is copied to the newly allocated linear part.
This is far from optimal as DMA coherent zone is slow on many systems and memcpy() neutralizes the idea and benefits of the header split. Not speaking of that XDP can't be run on DMA coherent buffers, but at the same time the idea of allocating an skb to run XDP program is ill. Instead, use libeth to create page_pools for the header buffers, allocate them dynamically and then build an skb via napi_build_skb() around them with no memory copy. With one exception...
When you enable header split, you expect you'll always have a separate header buffer, so that you could reserve headroom and tailroom only there and then use full buffers for the data. For example, this is how TCP zerocopy works -- you have to have the payload aligned to PAGE_SIZE. The current hardware running idpf does *not* guarantee that you'll always have headers placed separately. For example, on my setup, even ICMP packets are written as one piece to the data buffers. You can't build a valid skb around a data buffer in this case. To not complicate things and not lose TCP zerocopy etc., when such thing happens, use the empty header buffer and pull either full frame (if it's short) or the Ethernet header there and build an skb around it. GRO layer will pull more from the data buffer later. This W/A will hopefully be removed one day.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
show more ...
|
#
1b1b2620 |
| 20-Jun-2024 |
Alexander Lobakin <aleksander.lobakin@intel.com> |
idpf: reuse libeth's definitions of parsed ptype structures
idpf's in-kernel parsed ptype structure is almost identical to the one used in the previous Intel drivers, which means it can be converted
idpf: reuse libeth's definitions of parsed ptype structures
idpf's in-kernel parsed ptype structure is almost identical to the one used in the previous Intel drivers, which means it can be converted to use libeth's definitions and even helpers. The only difference is that it doesn't use a constant table (libie), rather than one obtained from the device. Remove the driver counterpart and use libeth's helpers for hashes and checksums. This slightly optimizes skb fields processing due to faster checks. Also don't define big static array of ptypes in &idpf_vport -- allocate them dynamically. The pointer to it is anyway cached in &idpf_rx_queue.
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Reviewed-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
show more ...
|
#
f771314d |
| 20-Jun-2024 |
Alexander Lobakin <aleksander.lobakin@intel.com> |
idpf: compile singleq code only under default-n CONFIG_IDPF_SINGLEQ
Currently, all HW supporting idpf supports the singleq model, but none of it advertises it by default, as splitq is supported and
idpf: compile singleq code only under default-n CONFIG_IDPF_SINGLEQ
Currently, all HW supporting idpf supports the singleq model, but none of it advertises it by default, as splitq is supported and preferred for multiple reasons. Still, this almost dead code often times adds hotpath branches and redundant cacheline accesses. While it can't currently be removed, add CONFIG_IDPF_SINGLEQ and build the singleq code only when it's enabled manually. This corresponds to -10 Kb of object code size and a good bunch of hotpath checks. idpf_is_queue_model_split() works as a gate and compiles out to `true` when the config option is disabled.
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
show more ...
|
#
e4891e46 |
| 20-Jun-2024 |
Alexander Lobakin <aleksander.lobakin@intel.com> |
idpf: split &idpf_queue into 4 strictly-typed queue structures
Currently, sizeof(struct idpf_queue) is 32 Kb. This is due to the 12-bit hashtable declaration at the end of the queue. This HT is need
idpf: split &idpf_queue into 4 strictly-typed queue structures
Currently, sizeof(struct idpf_queue) is 32 Kb. This is due to the 12-bit hashtable declaration at the end of the queue. This HT is needed only for Tx queues when the flow scheduling mode is enabled. But &idpf_queue is unified for all of the queue types, provoking excessive memory usage. The unified structure in general makes the code less effective via suboptimal fields placement. You can't avoid that unless you make unions each 2 fields. Even then, different field alignment etc., doesn't allow you to optimize things to the limit. Split &idpf_queue into 4 structures corresponding to the queue types: RQ (Rx queue), SQ (Tx queue), FQ (buffer queue), and CQ (completion queue). Place only needed fields there and shortcuts handy for hotpath. Allocate the abovementioned hashtable dynamically and only when needed, keeping &idpf_tx_queue relatively short (192 bytes, same as Rx). This HT is used only for OOO completions, which aren't really hotpath anyway. Note that this change must be done atomically, otherwise it's really easy to get lost and miss something.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
show more ...
|