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/powerpc/lib/memcpy_power7.S | 641 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 641 insertions(+) create mode 100644 arch/powerpc/lib/memcpy_power7.S (limited to 'arch/powerpc/lib/memcpy_power7.S') diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S new file mode 100644 index 000000000..54f226333 --- /dev/null +++ b/arch/powerpc/lib/memcpy_power7.S @@ -0,0 +1,641 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * + * Copyright (C) IBM Corporation, 2012 + * + * Author: Anton Blanchard + */ +#include + +#ifndef SELFTEST_CASE +/* 0 == don't use VMX, 1 == use VMX */ +#define SELFTEST_CASE 0 +#endif + +#ifdef __BIG_ENDIAN__ +#define LVS(VRT,RA,RB) lvsl VRT,RA,RB +#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRA,VRB,VRC +#else +#define LVS(VRT,RA,RB) lvsr VRT,RA,RB +#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRB,VRA,VRC +#endif + +_GLOBAL(memcpy_power7) + cmpldi r5,16 + cmpldi cr1,r5,4096 + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + blt .Lshort_copy + +#ifdef CONFIG_ALTIVEC +test_feature = SELFTEST_CASE +BEGIN_FTR_SECTION + bgt cr1, .Lvmx_copy +END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) +#endif + +.Lnonvmx_copy: + /* Get the source 8B aligned */ + neg r6,r4 + mtocrf 0x01,r6 + clrldi r6,r6,(64-3) + + bf cr7*4+3,1f + lbz r0,0(r4) + addi r4,r4,1 + stb r0,0(r3) + addi r3,r3,1 + +1: bf cr7*4+2,2f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +2: bf cr7*4+1,3f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +3: sub r5,r5,r6 + cmpldi r5,128 + blt 5f + + mflr r0 + stdu r1,-STACKFRAMESIZE(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) + std r17,STK_REG(R17)(r1) + std r18,STK_REG(R18)(r1) + std r19,STK_REG(R19)(r1) + std r20,STK_REG(R20)(r1) + std r21,STK_REG(R21)(r1) + std r22,STK_REG(R22)(r1) + std r0,STACKFRAMESIZE+16(r1) + + srdi r6,r5,7 + mtctr r6 + + /* Now do cacheline (128B) sized loads and stores. */ + .align 5 +4: + ld r0,0(r4) + ld r6,8(r4) + ld r7,16(r4) + ld r8,24(r4) + ld r9,32(r4) + ld r10,40(r4) + ld r11,48(r4) + ld r12,56(r4) + ld r14,64(r4) + ld r15,72(r4) + ld r16,80(r4) + ld r17,88(r4) + ld r18,96(r4) + ld r19,104(r4) + ld r20,112(r4) + ld r21,120(r4) + addi r4,r4,128 + std r0,0(r3) + std r6,8(r3) + std r7,16(r3) + std r8,24(r3) + std r9,32(r3) + std r10,40(r3) + std r11,48(r3) + std r12,56(r3) + std r14,64(r3) + std r15,72(r3) + std r16,80(r3) + std r17,88(r3) + std r18,96(r3) + std r19,104(r3) + std r20,112(r3) + std r21,120(r3) + addi r3,r3,128 + bdnz 4b + + clrldi r5,r5,(64-7) + + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + ld r17,STK_REG(R17)(r1) + ld r18,STK_REG(R18)(r1) + ld r19,STK_REG(R19)(r1) + ld r20,STK_REG(R20)(r1) + ld r21,STK_REG(R21)(r1) + ld r22,STK_REG(R22)(r1) + addi r1,r1,STACKFRAMESIZE + + /* Up to 127B to go */ +5: srdi r6,r5,4 + mtocrf 0x01,r6 + +6: bf cr7*4+1,7f + ld r0,0(r4) + ld r6,8(r4) + ld r7,16(r4) + ld r8,24(r4) + ld r9,32(r4) + ld r10,40(r4) + ld r11,48(r4) + ld r12,56(r4) + addi r4,r4,64 + std r0,0(r3) + std r6,8(r3) + std r7,16(r3) + std r8,24(r3) + std r9,32(r3) + std r10,40(r3) + std r11,48(r3) + std r12,56(r3) + addi r3,r3,64 + + /* Up to 63B to go */ +7: bf cr7*4+2,8f + ld r0,0(r4) + ld r6,8(r4) + ld r7,16(r4) + ld r8,24(r4) + addi r4,r4,32 + std r0,0(r3) + std r6,8(r3) + std r7,16(r3) + std r8,24(r3) + addi r3,r3,32 + + /* Up to 31B to go */ +8: bf cr7*4+3,9f + ld r0,0(r4) + ld r6,8(r4) + addi r4,r4,16 + std r0,0(r3) + std r6,8(r3) + addi r3,r3,16 + +9: clrldi r5,r5,(64-4) + + /* Up to 15B to go */ +.Lshort_copy: + mtocrf 0x01,r5 + bf cr7*4+0,12f + lwz r0,0(r4) /* Less chance of a reject with word ops */ + lwz r6,4(r4) + addi r4,r4,8 + stw r0,0(r3) + stw r6,4(r3) + addi r3,r3,8 + +12: bf cr7*4+1,13f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +13: bf cr7*4+2,14f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +14: bf cr7*4+3,15f + lbz r0,0(r4) + stb r0,0(r3) + +15: ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + blr + +.Lunwind_stack_nonvmx_copy: + addi r1,r1,STACKFRAMESIZE + b .Lnonvmx_copy + +.Lvmx_copy: +#ifdef CONFIG_ALTIVEC + mflr r0 + std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) + std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) + std r0,16(r1) + stdu r1,-STACKFRAMESIZE(r1) + bl enter_vmx_ops + cmpwi cr1,r3,0 + ld r0,STACKFRAMESIZE+16(r1) + ld r3,STK_REG(R31)(r1) + ld r4,STK_REG(R30)(r1) + ld r5,STK_REG(R29)(r1) + mtlr r0 + + /* + * We prefetch both the source and destination using enhanced touch + * instructions. We use a stream ID of 0 for the load side and + * 1 for the store side. + */ + clrrdi r6,r4,7 + clrrdi r9,r3,7 + ori r9,r9,1 /* stream=1 */ + + srdi r7,r5,7 /* length in cachelines, capped at 0x3FF */ + cmpldi r7,0x3FF + ble 1f + li r7,0x3FF +1: lis r0,0x0E00 /* depth=7 */ + sldi r7,r7,7 + or r7,r7,r0 + ori r10,r7,1 /* stream=1 */ + + lis r8,0x8000 /* GO=1 */ + clrldi r8,r8,32 + + dcbt 0,r6,0b01000 + dcbt 0,r7,0b01010 + dcbtst 0,r9,0b01000 + dcbtst 0,r10,0b01010 + eieio + dcbt 0,r8,0b01010 /* GO */ + + beq cr1,.Lunwind_stack_nonvmx_copy + + /* + * If source and destination are not relatively aligned we use a + * slower permute loop. + */ + xor r6,r4,r3 + rldicl. r6,r6,0,(64-4) + bne .Lvmx_unaligned_copy + + /* Get the destination 16B aligned */ + neg r6,r3 + mtocrf 0x01,r6 + clrldi r6,r6,(64-4) + + bf cr7*4+3,1f + lbz r0,0(r4) + addi r4,r4,1 + stb r0,0(r3) + addi r3,r3,1 + +1: bf cr7*4+2,2f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +2: bf cr7*4+1,3f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +3: bf cr7*4+0,4f + ld r0,0(r4) + addi r4,r4,8 + std r0,0(r3) + addi r3,r3,8 + +4: sub r5,r5,r6 + + /* Get the desination 128B aligned */ + neg r6,r3 + srdi r7,r6,4 + mtocrf 0x01,r7 + clrldi r6,r6,(64-7) + + li r9,16 + li r10,32 + li r11,48 + + bf cr7*4+3,5f + lvx v1,0,r4 + addi r4,r4,16 + stvx v1,0,r3 + addi r3,r3,16 + +5: bf cr7*4+2,6f + lvx v1,0,r4 + lvx v0,r4,r9 + addi r4,r4,32 + stvx v1,0,r3 + stvx v0,r3,r9 + addi r3,r3,32 + +6: bf cr7*4+1,7f + lvx v3,0,r4 + lvx v2,r4,r9 + lvx v1,r4,r10 + lvx v0,r4,r11 + addi r4,r4,64 + stvx v3,0,r3 + stvx v2,r3,r9 + stvx v1,r3,r10 + stvx v0,r3,r11 + addi r3,r3,64 + +7: sub r5,r5,r6 + srdi r6,r5,7 + + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) + + li r12,64 + li r14,80 + li r15,96 + li r16,112 + + mtctr r6 + + /* + * Now do cacheline sized loads and stores. By this stage the + * cacheline stores are also cacheline aligned. + */ + .align 5 +8: + lvx v7,0,r4 + lvx v6,r4,r9 + lvx v5,r4,r10 + lvx v4,r4,r11 + lvx v3,r4,r12 + lvx v2,r4,r14 + lvx v1,r4,r15 + lvx v0,r4,r16 + addi r4,r4,128 + stvx v7,0,r3 + stvx v6,r3,r9 + stvx v5,r3,r10 + stvx v4,r3,r11 + stvx v3,r3,r12 + stvx v2,r3,r14 + stvx v1,r3,r15 + stvx v0,r3,r16 + addi r3,r3,128 + bdnz 8b + + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + + /* Up to 127B to go */ + clrldi r5,r5,(64-7) + srdi r6,r5,4 + mtocrf 0x01,r6 + + bf cr7*4+1,9f + lvx v3,0,r4 + lvx v2,r4,r9 + lvx v1,r4,r10 + lvx v0,r4,r11 + addi r4,r4,64 + stvx v3,0,r3 + stvx v2,r3,r9 + stvx v1,r3,r10 + stvx v0,r3,r11 + addi r3,r3,64 + +9: bf cr7*4+2,10f + lvx v1,0,r4 + lvx v0,r4,r9 + addi r4,r4,32 + stvx v1,0,r3 + stvx v0,r3,r9 + addi r3,r3,32 + +10: bf cr7*4+3,11f + lvx v1,0,r4 + addi r4,r4,16 + stvx v1,0,r3 + addi r3,r3,16 + + /* Up to 15B to go */ +11: clrldi r5,r5,(64-4) + mtocrf 0x01,r5 + bf cr7*4+0,12f + ld r0,0(r4) + addi r4,r4,8 + std r0,0(r3) + addi r3,r3,8 + +12: bf cr7*4+1,13f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +13: bf cr7*4+2,14f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +14: bf cr7*4+3,15f + lbz r0,0(r4) + stb r0,0(r3) + +15: addi r1,r1,STACKFRAMESIZE + ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + b exit_vmx_ops /* tail call optimise */ + +.Lvmx_unaligned_copy: + /* Get the destination 16B aligned */ + neg r6,r3 + mtocrf 0x01,r6 + clrldi r6,r6,(64-4) + + bf cr7*4+3,1f + lbz r0,0(r4) + addi r4,r4,1 + stb r0,0(r3) + addi r3,r3,1 + +1: bf cr7*4+2,2f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +2: bf cr7*4+1,3f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +3: bf cr7*4+0,4f + lwz r0,0(r4) /* Less chance of a reject with word ops */ + lwz r7,4(r4) + addi r4,r4,8 + stw r0,0(r3) + stw r7,4(r3) + addi r3,r3,8 + +4: sub r5,r5,r6 + + /* Get the desination 128B aligned */ + neg r6,r3 + srdi r7,r6,4 + mtocrf 0x01,r7 + clrldi r6,r6,(64-7) + + li r9,16 + li r10,32 + li r11,48 + + LVS(v16,0,r4) /* Setup permute control vector */ + lvx v0,0,r4 + addi r4,r4,16 + + bf cr7*4+3,5f + lvx v1,0,r4 + VPERM(v8,v0,v1,v16) + addi r4,r4,16 + stvx v8,0,r3 + addi r3,r3,16 + vor v0,v1,v1 + +5: bf cr7*4+2,6f + lvx v1,0,r4 + VPERM(v8,v0,v1,v16) + lvx v0,r4,r9 + VPERM(v9,v1,v0,v16) + addi r4,r4,32 + stvx v8,0,r3 + stvx v9,r3,r9 + addi r3,r3,32 + +6: bf cr7*4+1,7f + lvx v3,0,r4 + VPERM(v8,v0,v3,v16) + lvx v2,r4,r9 + VPERM(v9,v3,v2,v16) + lvx v1,r4,r10 + VPERM(v10,v2,v1,v16) + lvx v0,r4,r11 + VPERM(v11,v1,v0,v16) + addi r4,r4,64 + stvx v8,0,r3 + stvx v9,r3,r9 + stvx v10,r3,r10 + stvx v11,r3,r11 + addi r3,r3,64 + +7: sub r5,r5,r6 + srdi r6,r5,7 + + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) + + li r12,64 + li r14,80 + li r15,96 + li r16,112 + + mtctr r6 + + /* + * Now do cacheline sized loads and stores. By this stage the + * cacheline stores are also cacheline aligned. + */ + .align 5 +8: + lvx v7,0,r4 + VPERM(v8,v0,v7,v16) + lvx v6,r4,r9 + VPERM(v9,v7,v6,v16) + lvx v5,r4,r10 + VPERM(v10,v6,v5,v16) + lvx v4,r4,r11 + VPERM(v11,v5,v4,v16) + lvx v3,r4,r12 + VPERM(v12,v4,v3,v16) + lvx v2,r4,r14 + VPERM(v13,v3,v2,v16) + lvx v1,r4,r15 + VPERM(v14,v2,v1,v16) + lvx v0,r4,r16 + VPERM(v15,v1,v0,v16) + addi r4,r4,128 + stvx v8,0,r3 + stvx v9,r3,r9 + stvx v10,r3,r10 + stvx v11,r3,r11 + stvx v12,r3,r12 + stvx v13,r3,r14 + stvx v14,r3,r15 + stvx v15,r3,r16 + addi r3,r3,128 + bdnz 8b + + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + + /* Up to 127B to go */ + clrldi r5,r5,(64-7) + srdi r6,r5,4 + mtocrf 0x01,r6 + + bf cr7*4+1,9f + lvx v3,0,r4 + VPERM(v8,v0,v3,v16) + lvx v2,r4,r9 + VPERM(v9,v3,v2,v16) + lvx v1,r4,r10 + VPERM(v10,v2,v1,v16) + lvx v0,r4,r11 + VPERM(v11,v1,v0,v16) + addi r4,r4,64 + stvx v8,0,r3 + stvx v9,r3,r9 + stvx v10,r3,r10 + stvx v11,r3,r11 + addi r3,r3,64 + +9: bf cr7*4+2,10f + lvx v1,0,r4 + VPERM(v8,v0,v1,v16) + lvx v0,r4,r9 + VPERM(v9,v1,v0,v16) + addi r4,r4,32 + stvx v8,0,r3 + stvx v9,r3,r9 + addi r3,r3,32 + +10: bf cr7*4+3,11f + lvx v1,0,r4 + VPERM(v8,v0,v1,v16) + addi r4,r4,16 + stvx v8,0,r3 + addi r3,r3,16 + + /* Up to 15B to go */ +11: clrldi r5,r5,(64-4) + addi r4,r4,-16 /* Unwind the +16 load offset */ + mtocrf 0x01,r5 + bf cr7*4+0,12f + lwz r0,0(r4) /* Less chance of a reject with word ops */ + lwz r6,4(r4) + addi r4,r4,8 + stw r0,0(r3) + stw r6,4(r3) + addi r3,r3,8 + +12: bf cr7*4+1,13f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +13: bf cr7*4+2,14f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +14: bf cr7*4+3,15f + lbz r0,0(r4) + stb r0,0(r3) + +15: addi r1,r1,STACKFRAMESIZE + ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + b exit_vmx_ops /* tail call optimise */ +#endif /* CONFIG_ALTIVEC */ -- cgit v1.2.3