From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- arch/ia64/lib/copy_page_mck.S | 188 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 188 insertions(+) create mode 100644 arch/ia64/lib/copy_page_mck.S (limited to 'arch/ia64/lib/copy_page_mck.S') diff --git a/arch/ia64/lib/copy_page_mck.S b/arch/ia64/lib/copy_page_mck.S new file mode 100644 index 000000000..d6fd56e4f --- /dev/null +++ b/arch/ia64/lib/copy_page_mck.S @@ -0,0 +1,188 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * McKinley-optimized version of copy_page(). + * + * Copyright (C) 2002 Hewlett-Packard Co + * David Mosberger + * + * Inputs: + * in0: address of target page + * in1: address of source page + * Output: + * no return value + * + * General idea: + * - use regular loads and stores to prefetch data to avoid consuming M-slot just for + * lfetches => good for in-cache performance + * - avoid l2 bank-conflicts by not storing into the same 16-byte bank within a single + * cycle + * + * Principle of operation: + * First, note that L1 has a line-size of 64 bytes and L2 a line-size of 128 bytes. + * To avoid secondary misses in L2, we prefetch both source and destination with a line-size + * of 128 bytes. When both of these lines are in the L2 and the first half of the + * source line is in L1, we start copying the remaining words. The second half of the + * source line is prefetched in an earlier iteration, so that by the time we start + * accessing it, it's also present in the L1. + * + * We use a software-pipelined loop to control the overall operation. The pipeline + * has 2*PREFETCH_DIST+K stages. The first PREFETCH_DIST stages are used for prefetching + * source cache-lines. The second PREFETCH_DIST stages are used for prefetching destination + * cache-lines, the last K stages are used to copy the cache-line words not copied by + * the prefetches. The four relevant points in the pipelined are called A, B, C, D: + * p[A] is TRUE if a source-line should be prefetched, p[B] is TRUE if a destination-line + * should be prefetched, p[C] is TRUE if the second half of an L2 line should be brought + * into L1D and p[D] is TRUE if a cacheline needs to be copied. + * + * This all sounds very complicated, but thanks to the modulo-scheduled loop support, + * the resulting code is very regular and quite easy to follow (once you get the idea). + * + * As a secondary optimization, the first 2*PREFETCH_DIST iterations are implemented + * as the separate .prefetch_loop. Logically, this loop performs exactly like the + * main-loop (.line_copy), but has all known-to-be-predicated-off instructions removed, + * so that each loop iteration is faster (again, good for cached case). + * + * When reading the code, it helps to keep the following picture in mind: + * + * word 0 word 1 + * +------+------+--- + * | v[x] | t1 | ^ + * | t2 | t3 | | + * | t4 | t5 | | + * | t6 | t7 | | 128 bytes + * | n[y] | t9 | | (L2 cache line) + * | t10 | t11 | | + * | t12 | t13 | | + * | t14 | t15 | v + * +------+------+--- + * + * Here, v[x] is copied by the (memory) prefetch. n[y] is loaded at p[C] + * to fetch the second-half of the L2 cache line into L1, and the tX words are copied in + * an order that avoids bank conflicts. + */ +#include +#include +#include + +#define PREFETCH_DIST 8 // McKinley sustains 16 outstanding L2 misses (8 ld, 8 st) + +#define src0 r2 +#define src1 r3 +#define dst0 r9 +#define dst1 r10 +#define src_pre_mem r11 +#define dst_pre_mem r14 +#define src_pre_l2 r15 +#define dst_pre_l2 r16 +#define t1 r17 +#define t2 r18 +#define t3 r19 +#define t4 r20 +#define t5 t1 // alias! +#define t6 t2 // alias! +#define t7 t3 // alias! +#define t9 t5 // alias! +#define t10 t4 // alias! +#define t11 t7 // alias! +#define t12 t6 // alias! +#define t14 t10 // alias! +#define t13 r21 +#define t15 r22 + +#define saved_lc r23 +#define saved_pr r24 + +#define A 0 +#define B (PREFETCH_DIST) +#define C (B + PREFETCH_DIST) +#define D (C + 3) +#define N (D + 1) +#define Nrot ((N + 7) & ~7) + +GLOBAL_ENTRY(copy_page) + .prologue + alloc r8 = ar.pfs, 2, Nrot-2, 0, Nrot + + .rotr v[2*PREFETCH_DIST], n[D-C+1] + .rotp p[N] + + .save ar.lc, saved_lc + mov saved_lc = ar.lc + .save pr, saved_pr + mov saved_pr = pr + .body + + mov src_pre_mem = in1 + mov pr.rot = 0x10000 + mov ar.ec = 1 // special unrolled loop + + mov dst_pre_mem = in0 + mov ar.lc = 2*PREFETCH_DIST - 1 + + add src_pre_l2 = 8*8, in1 + add dst_pre_l2 = 8*8, in0 + add src0 = 8, in1 // first t1 src + add src1 = 3*8, in1 // first t3 src + add dst0 = 8, in0 // first t1 dst + add dst1 = 3*8, in0 // first t3 dst + mov t1 = (PAGE_SIZE/128) - (2*PREFETCH_DIST) - 1 + nop.m 0 + nop.i 0 + ;; + // same as .line_copy loop, but with all predicated-off instructions removed: +.prefetch_loop: +(p[A]) ld8 v[A] = [src_pre_mem], 128 // M0 +(p[B]) st8 [dst_pre_mem] = v[B], 128 // M2 + br.ctop.sptk .prefetch_loop + ;; + cmp.eq p16, p0 = r0, r0 // reset p16 to 1 (br.ctop cleared it to zero) + mov ar.lc = t1 // with 64KB pages, t1 is too big to fit in 8 bits! + mov ar.ec = N // # of stages in pipeline + ;; +.line_copy: +(p[D]) ld8 t2 = [src0], 3*8 // M0 +(p[D]) ld8 t4 = [src1], 3*8 // M1 +(p[B]) st8 [dst_pre_mem] = v[B], 128 // M2 prefetch dst from memory +(p[D]) st8 [dst_pre_l2] = n[D-C], 128 // M3 prefetch dst from L2 + ;; +(p[A]) ld8 v[A] = [src_pre_mem], 128 // M0 prefetch src from memory +(p[C]) ld8 n[0] = [src_pre_l2], 128 // M1 prefetch src from L2 +(p[D]) st8 [dst0] = t1, 8 // M2 +(p[D]) st8 [dst1] = t3, 8 // M3 + ;; +(p[D]) ld8 t5 = [src0], 8 +(p[D]) ld8 t7 = [src1], 3*8 +(p[D]) st8 [dst0] = t2, 3*8 +(p[D]) st8 [dst1] = t4, 3*8 + ;; +(p[D]) ld8 t6 = [src0], 3*8 +(p[D]) ld8 t10 = [src1], 8 +(p[D]) st8 [dst0] = t5, 8 +(p[D]) st8 [dst1] = t7, 3*8 + ;; +(p[D]) ld8 t9 = [src0], 3*8 +(p[D]) ld8 t11 = [src1], 3*8 +(p[D]) st8 [dst0] = t6, 3*8 +(p[D]) st8 [dst1] = t10, 8 + ;; +(p[D]) ld8 t12 = [src0], 8 +(p[D]) ld8 t14 = [src1], 8 +(p[D]) st8 [dst0] = t9, 3*8 +(p[D]) st8 [dst1] = t11, 3*8 + ;; +(p[D]) ld8 t13 = [src0], 4*8 +(p[D]) ld8 t15 = [src1], 4*8 +(p[D]) st8 [dst0] = t12, 8 +(p[D]) st8 [dst1] = t14, 8 + ;; +(p[D-1])ld8 t1 = [src0], 8 +(p[D-1])ld8 t3 = [src1], 8 +(p[D]) st8 [dst0] = t13, 4*8 +(p[D]) st8 [dst1] = t15, 4*8 + br.ctop.sptk .line_copy + ;; + mov ar.lc = saved_lc + mov pr = saved_pr, -1 + br.ret.sptk.many rp +END(copy_page) +EXPORT_SYMBOL(copy_page) -- cgit v1.2.3