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/sparc/lib/NG4memcpy.S | 386 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 386 insertions(+) create mode 100644 arch/sparc/lib/NG4memcpy.S (limited to 'arch/sparc/lib/NG4memcpy.S') diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S new file mode 100644 index 000000000..7ad58ebe0 --- /dev/null +++ b/arch/sparc/lib/NG4memcpy.S @@ -0,0 +1,386 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* NG4memcpy.S: Niagara-4 optimized memcpy. + * + * Copyright (C) 2012 David S. Miller (davem@davemloft.net) + */ + +#ifdef __KERNEL__ +#include +#include +#include +#define GLOBAL_SPARE %g7 +#else +#define ASI_BLK_INIT_QUAD_LDD_P 0xe2 +#define FPRS_FEF 0x04 + +/* On T4 it is very expensive to access ASRs like %fprs and + * %asi, avoiding a read or a write can save ~50 cycles. + */ +#define FPU_ENTER \ + rd %fprs, %o5; \ + andcc %o5, FPRS_FEF, %g0; \ + be,a,pn %icc, 999f; \ + wr %g0, FPRS_FEF, %fprs; \ + 999: + +#ifdef MEMCPY_DEBUG +#define VISEntryHalf FPU_ENTER; \ + clr %g1; clr %g2; clr %g3; clr %g5; subcc %g0, %g0, %g0; +#define VISExitHalf and %o5, FPRS_FEF, %o5; wr %o5, 0x0, %fprs +#else +#define VISEntryHalf FPU_ENTER +#define VISExitHalf and %o5, FPRS_FEF, %o5; wr %o5, 0x0, %fprs +#endif + +#define GLOBAL_SPARE %g5 +#endif + +#ifndef STORE_ASI +#ifndef SIMULATE_NIAGARA_ON_NON_NIAGARA +#define STORE_ASI ASI_BLK_INIT_QUAD_LDD_P +#else +#define STORE_ASI 0x80 /* ASI_P */ +#endif +#endif + +#if !defined(EX_LD) && !defined(EX_ST) +#define NON_USER_COPY +#endif + +#ifndef EX_LD +#define EX_LD(x,y) x +#endif +#ifndef EX_LD_FP +#define EX_LD_FP(x,y) x +#endif + +#ifndef EX_ST +#define EX_ST(x,y) x +#endif +#ifndef EX_ST_FP +#define EX_ST_FP(x,y) x +#endif + + +#ifndef LOAD +#define LOAD(type,addr,dest) type [addr], dest +#endif + +#ifndef STORE +#ifndef MEMCPY_DEBUG +#define STORE(type,src,addr) type src, [addr] +#else +#define STORE(type,src,addr) type##a src, [addr] %asi +#endif +#endif + +#ifndef STORE_INIT +#define STORE_INIT(src,addr) stxa src, [addr] STORE_ASI +#endif + +#ifndef FUNC_NAME +#define FUNC_NAME NG4memcpy +#endif +#ifndef PREAMBLE +#define PREAMBLE +#endif + +#ifndef XCC +#define XCC xcc +#endif + + .register %g2,#scratch + .register %g3,#scratch + + .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +#endif + .align 64 + + .globl FUNC_NAME + .type FUNC_NAME,#function +FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ +#ifdef MEMCPY_DEBUG + wr %g0, 0x80, %asi +#endif + srlx %o2, 31, %g2 + cmp %g2, 0 + tne %XCC, 5 + PREAMBLE + mov %o0, %o3 + brz,pn %o2, .Lexit + cmp %o2, 3 + ble,pn %icc, .Ltiny + cmp %o2, 19 + ble,pn %icc, .Lsmall + or %o0, %o1, %g2 + cmp %o2, 128 + bl,pn %icc, .Lmedium + nop + +.Llarge:/* len >= 0x80 */ + /* First get dest 8 byte aligned. */ + sub %g0, %o0, %g1 + and %g1, 0x7, %g1 + brz,pt %g1, 51f + sub %o2, %g1, %o2 + + +1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), memcpy_retl_o2_plus_g1) + add %o1, 1, %o1 + subcc %g1, 1, %g1 + add %o0, 1, %o0 + bne,pt %icc, 1b + EX_ST(STORE(stb, %g2, %o0 - 0x01), memcpy_retl_o2_plus_g1_plus_1) + +51: LOAD(prefetch, %o1 + 0x040, #n_reads_strong) + LOAD(prefetch, %o1 + 0x080, #n_reads_strong) + LOAD(prefetch, %o1 + 0x0c0, #n_reads_strong) + LOAD(prefetch, %o1 + 0x100, #n_reads_strong) + LOAD(prefetch, %o1 + 0x140, #n_reads_strong) + LOAD(prefetch, %o1 + 0x180, #n_reads_strong) + LOAD(prefetch, %o1 + 0x1c0, #n_reads_strong) + LOAD(prefetch, %o1 + 0x200, #n_reads_strong) + + /* Check if we can use the straight fully aligned + * loop, or we require the alignaddr/faligndata variant. + */ + andcc %o1, 0x7, %o5 + bne,pn %icc, .Llarge_src_unaligned + sub %g0, %o0, %g1 + + /* Legitimize the use of initializing stores by getting dest + * to be 64-byte aligned. + */ + and %g1, 0x3f, %g1 + brz,pt %g1, .Llarge_aligned + sub %o2, %g1, %o2 + +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g2), memcpy_retl_o2_plus_g1) + add %o1, 8, %o1 + subcc %g1, 8, %g1 + add %o0, 8, %o0 + bne,pt %icc, 1b + EX_ST(STORE(stx, %g2, %o0 - 0x08), memcpy_retl_o2_plus_g1_plus_8) + +.Llarge_aligned: + /* len >= 0x80 && src 8-byte aligned && dest 8-byte aligned */ + andn %o2, 0x3f, %o4 + sub %o2, %o4, %o2 + +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), memcpy_retl_o2_plus_o4) + add %o1, 0x40, %o1 + EX_LD(LOAD(ldx, %o1 - 0x38, %g2), memcpy_retl_o2_plus_o4) + subcc %o4, 0x40, %o4 + EX_LD(LOAD(ldx, %o1 - 0x30, %g3), memcpy_retl_o2_plus_o4_plus_64) + EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE), memcpy_retl_o2_plus_o4_plus_64) + EX_LD(LOAD(ldx, %o1 - 0x20, %o5), memcpy_retl_o2_plus_o4_plus_64) + EX_ST(STORE_INIT(%g1, %o0), memcpy_retl_o2_plus_o4_plus_64) + add %o0, 0x08, %o0 + EX_ST(STORE_INIT(%g2, %o0), memcpy_retl_o2_plus_o4_plus_56) + add %o0, 0x08, %o0 + EX_LD(LOAD(ldx, %o1 - 0x18, %g2), memcpy_retl_o2_plus_o4_plus_48) + EX_ST(STORE_INIT(%g3, %o0), memcpy_retl_o2_plus_o4_plus_48) + add %o0, 0x08, %o0 + EX_LD(LOAD(ldx, %o1 - 0x10, %g3), memcpy_retl_o2_plus_o4_plus_40) + EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), memcpy_retl_o2_plus_o4_plus_40) + add %o0, 0x08, %o0 + EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE), memcpy_retl_o2_plus_o4_plus_32) + EX_ST(STORE_INIT(%o5, %o0), memcpy_retl_o2_plus_o4_plus_32) + add %o0, 0x08, %o0 + EX_ST(STORE_INIT(%g2, %o0), memcpy_retl_o2_plus_o4_plus_24) + add %o0, 0x08, %o0 + EX_ST(STORE_INIT(%g3, %o0), memcpy_retl_o2_plus_o4_plus_16) + add %o0, 0x08, %o0 + EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), memcpy_retl_o2_plus_o4_plus_8) + add %o0, 0x08, %o0 + bne,pt %icc, 1b + LOAD(prefetch, %o1 + 0x200, #n_reads_strong) + + membar #StoreLoad | #StoreStore + + brz,pn %o2, .Lexit + cmp %o2, 19 + ble,pn %icc, .Lsmall_unaligned + nop + ba,a,pt %icc, .Lmedium_noprefetch + +.Lexit: retl + mov EX_RETVAL(%o3), %o0 + +.Llarge_src_unaligned: +#ifdef NON_USER_COPY + VISEntryHalfFast(.Lmedium_vis_entry_fail) +#else + VISEntryHalf +#endif + andn %o2, 0x3f, %o4 + sub %o2, %o4, %o2 + alignaddr %o1, %g0, %g1 + add %o1, %o4, %o1 + EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0), memcpy_retl_o2_plus_o4) +1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2), memcpy_retl_o2_plus_o4) + subcc %o4, 0x40, %o4 + EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4), memcpy_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6), memcpy_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8), memcpy_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10), memcpy_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12), memcpy_retl_o2_plus_o4_plus_64) + EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14), memcpy_retl_o2_plus_o4_plus_64) + faligndata %f0, %f2, %f16 + EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0), memcpy_retl_o2_plus_o4_plus_64) + faligndata %f2, %f4, %f18 + add %g1, 0x40, %g1 + faligndata %f4, %f6, %f20 + faligndata %f6, %f8, %f22 + faligndata %f8, %f10, %f24 + faligndata %f10, %f12, %f26 + faligndata %f12, %f14, %f28 + faligndata %f14, %f0, %f30 + EX_ST_FP(STORE(std, %f16, %o0 + 0x00), memcpy_retl_o2_plus_o4_plus_64) + EX_ST_FP(STORE(std, %f18, %o0 + 0x08), memcpy_retl_o2_plus_o4_plus_56) + EX_ST_FP(STORE(std, %f20, %o0 + 0x10), memcpy_retl_o2_plus_o4_plus_48) + EX_ST_FP(STORE(std, %f22, %o0 + 0x18), memcpy_retl_o2_plus_o4_plus_40) + EX_ST_FP(STORE(std, %f24, %o0 + 0x20), memcpy_retl_o2_plus_o4_plus_32) + EX_ST_FP(STORE(std, %f26, %o0 + 0x28), memcpy_retl_o2_plus_o4_plus_24) + EX_ST_FP(STORE(std, %f28, %o0 + 0x30), memcpy_retl_o2_plus_o4_plus_16) + EX_ST_FP(STORE(std, %f30, %o0 + 0x38), memcpy_retl_o2_plus_o4_plus_8) + add %o0, 0x40, %o0 + bne,pt %icc, 1b + LOAD(prefetch, %g1 + 0x200, #n_reads_strong) +#ifdef NON_USER_COPY + VISExitHalfFast +#else + VISExitHalf +#endif + brz,pn %o2, .Lexit + cmp %o2, 19 + ble,pn %icc, .Lsmall_unaligned + nop + ba,a,pt %icc, .Lmedium_unaligned + +#ifdef NON_USER_COPY +.Lmedium_vis_entry_fail: + or %o0, %o1, %g2 +#endif +.Lmedium: + LOAD(prefetch, %o1 + 0x40, #n_reads_strong) + andcc %g2, 0x7, %g0 + bne,pn %icc, .Lmedium_unaligned + nop +.Lmedium_noprefetch: + andncc %o2, 0x20 - 1, %o5 + be,pn %icc, 2f + sub %o2, %o5, %o2 +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), memcpy_retl_o2_plus_o5) + EX_LD(LOAD(ldx, %o1 + 0x08, %g2), memcpy_retl_o2_plus_o5) + EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE), memcpy_retl_o2_plus_o5) + EX_LD(LOAD(ldx, %o1 + 0x18, %o4), memcpy_retl_o2_plus_o5) + add %o1, 0x20, %o1 + subcc %o5, 0x20, %o5 + EX_ST(STORE(stx, %g1, %o0 + 0x00), memcpy_retl_o2_plus_o5_plus_32) + EX_ST(STORE(stx, %g2, %o0 + 0x08), memcpy_retl_o2_plus_o5_plus_24) + EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10), memcpy_retl_o2_plus_o5_plus_24) + EX_ST(STORE(stx, %o4, %o0 + 0x18), memcpy_retl_o2_plus_o5_plus_8) + bne,pt %icc, 1b + add %o0, 0x20, %o0 +2: andcc %o2, 0x18, %o5 + be,pt %icc, 3f + sub %o2, %o5, %o2 + +1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), memcpy_retl_o2_plus_o5) + add %o1, 0x08, %o1 + add %o0, 0x08, %o0 + subcc %o5, 0x08, %o5 + bne,pt %icc, 1b + EX_ST(STORE(stx, %g1, %o0 - 0x08), memcpy_retl_o2_plus_o5_plus_8) +3: brz,pt %o2, .Lexit + cmp %o2, 0x04 + bl,pn %icc, .Ltiny + nop + EX_LD(LOAD(lduw, %o1 + 0x00, %g1), memcpy_retl_o2) + add %o1, 0x04, %o1 + add %o0, 0x04, %o0 + subcc %o2, 0x04, %o2 + bne,pn %icc, .Ltiny + EX_ST(STORE(stw, %g1, %o0 - 0x04), memcpy_retl_o2_plus_4) + ba,a,pt %icc, .Lexit +.Lmedium_unaligned: + /* First get dest 8 byte aligned. */ + sub %g0, %o0, %g1 + and %g1, 0x7, %g1 + brz,pt %g1, 2f + sub %o2, %g1, %o2 + +1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), memcpy_retl_o2_plus_g1) + add %o1, 1, %o1 + subcc %g1, 1, %g1 + add %o0, 1, %o0 + bne,pt %icc, 1b + EX_ST(STORE(stb, %g2, %o0 - 0x01), memcpy_retl_o2_plus_g1_plus_1) +2: + and %o1, 0x7, %g1 + brz,pn %g1, .Lmedium_noprefetch + sll %g1, 3, %g1 + mov 64, %g2 + sub %g2, %g1, %g2 + andn %o1, 0x7, %o1 + EX_LD(LOAD(ldx, %o1 + 0x00, %o4), memcpy_retl_o2) + sllx %o4, %g1, %o4 + andn %o2, 0x08 - 1, %o5 + sub %o2, %o5, %o2 +1: EX_LD(LOAD(ldx, %o1 + 0x08, %g3), memcpy_retl_o2_plus_o5) + add %o1, 0x08, %o1 + subcc %o5, 0x08, %o5 + srlx %g3, %g2, GLOBAL_SPARE + or GLOBAL_SPARE, %o4, GLOBAL_SPARE + EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00), memcpy_retl_o2_plus_o5_plus_8) + add %o0, 0x08, %o0 + bne,pt %icc, 1b + sllx %g3, %g1, %o4 + srl %g1, 3, %g1 + add %o1, %g1, %o1 + brz,pn %o2, .Lexit + nop + ba,pt %icc, .Lsmall_unaligned + +.Ltiny: + EX_LD(LOAD(ldub, %o1 + 0x00, %g1), memcpy_retl_o2) + subcc %o2, 1, %o2 + be,pn %icc, .Lexit + EX_ST(STORE(stb, %g1, %o0 + 0x00), memcpy_retl_o2_plus_1) + EX_LD(LOAD(ldub, %o1 + 0x01, %g1), memcpy_retl_o2) + subcc %o2, 1, %o2 + be,pn %icc, .Lexit + EX_ST(STORE(stb, %g1, %o0 + 0x01), memcpy_retl_o2_plus_1) + EX_LD(LOAD(ldub, %o1 + 0x02, %g1), memcpy_retl_o2) + ba,pt %icc, .Lexit + EX_ST(STORE(stb, %g1, %o0 + 0x02), memcpy_retl_o2) + +.Lsmall: + andcc %g2, 0x3, %g0 + bne,pn %icc, .Lsmall_unaligned + andn %o2, 0x4 - 1, %o5 + sub %o2, %o5, %o2 +1: + EX_LD(LOAD(lduw, %o1 + 0x00, %g1), memcpy_retl_o2_plus_o5) + add %o1, 0x04, %o1 + subcc %o5, 0x04, %o5 + add %o0, 0x04, %o0 + bne,pt %icc, 1b + EX_ST(STORE(stw, %g1, %o0 - 0x04), memcpy_retl_o2_plus_o5_plus_4) + brz,pt %o2, .Lexit + nop + ba,a,pt %icc, .Ltiny + +.Lsmall_unaligned: +1: EX_LD(LOAD(ldub, %o1 + 0x00, %g1), memcpy_retl_o2) + add %o1, 1, %o1 + add %o0, 1, %o0 + subcc %o2, 1, %o2 + bne,pt %icc, 1b + EX_ST(STORE(stb, %g1, %o0 - 0x01), memcpy_retl_o2_plus_1) + ba,a,pt %icc, .Lexit + nop + .size FUNC_NAME, .-FUNC_NAME -- cgit v1.2.3