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/U3memcpy.S | 520 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 520 insertions(+) create mode 100644 arch/sparc/lib/U3memcpy.S (limited to 'arch/sparc/lib/U3memcpy.S') diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S new file mode 100644 index 000000000..9248d59c7 --- /dev/null +++ b/arch/sparc/lib/U3memcpy.S @@ -0,0 +1,520 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* U3memcpy.S: UltraSparc-III optimized memcpy. + * + * Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com) + */ + +#ifdef __KERNEL__ +#include +#include +#include +#define GLOBAL_SPARE %g7 +#else +#define ASI_BLK_P 0xf0 +#define FPRS_FEF 0x04 +#ifdef MEMCPY_DEBUG +#define VISEntryHalf rd %fprs, %o5; wr %g0, FPRS_FEF, %fprs; \ + clr %g1; clr %g2; clr %g3; subcc %g0, %g0, %g0; +#define VISExitHalf and %o5, FPRS_FEF, %o5; wr %o5, 0x0, %fprs +#else +#define VISEntryHalf rd %fprs, %o5; wr %g0, FPRS_FEF, %fprs +#define VISExitHalf and %o5, FPRS_FEF, %o5; wr %o5, 0x0, %fprs +#endif +#define GLOBAL_SPARE %g5 +#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 +#define STORE(type,src,addr) type src, [addr] +#endif + +#ifndef STORE_BLK +#define STORE_BLK(src,addr) stda src, [addr] ASI_BLK_P +#endif + +#ifndef FUNC_NAME +#define FUNC_NAME U3memcpy +#endif + +#ifndef PREAMBLE +#define PREAMBLE +#endif + +#ifndef XCC +#define XCC xcc +#endif + + .register %g2,#scratch + .register %g3,#scratch + + /* Special/non-trivial issues of this code: + * + * 1) %o5 is preserved from VISEntryHalf to VISExitHalf + * 2) Only low 32 FPU registers are used so that only the + * lower half of the FPU register set is dirtied by this + * code. This is especially important in the kernel. + * 3) This code never prefetches cachelines past the end + * of the source buffer. + */ + + .text +#ifndef EX_RETVAL +#define EX_RETVAL(x) x +__restore_fp: + VISExitHalf + retl + nop +ENTRY(U3_retl_o2_plus_g2_plus_g1_plus_1_fp) + add %g1, 1, %g1 + add %g2, %g1, %g2 + ba,pt %xcc, __restore_fp + add %o2, %g2, %o0 +ENDPROC(U3_retl_o2_plus_g2_plus_g1_plus_1_fp) +ENTRY(U3_retl_o2_plus_g2_fp) + ba,pt %xcc, __restore_fp + add %o2, %g2, %o0 +ENDPROC(U3_retl_o2_plus_g2_fp) +ENTRY(U3_retl_o2_plus_g2_plus_8_fp) + add %g2, 8, %g2 + ba,pt %xcc, __restore_fp + add %o2, %g2, %o0 +ENDPROC(U3_retl_o2_plus_g2_plus_8_fp) +ENTRY(U3_retl_o2) + retl + mov %o2, %o0 +ENDPROC(U3_retl_o2) +ENTRY(U3_retl_o2_plus_1) + retl + add %o2, 1, %o0 +ENDPROC(U3_retl_o2_plus_1) +ENTRY(U3_retl_o2_plus_4) + retl + add %o2, 4, %o0 +ENDPROC(U3_retl_o2_plus_4) +ENTRY(U3_retl_o2_plus_8) + retl + add %o2, 8, %o0 +ENDPROC(U3_retl_o2_plus_8) +ENTRY(U3_retl_o2_plus_g1_plus_1) + add %g1, 1, %g1 + retl + add %o2, %g1, %o0 +ENDPROC(U3_retl_o2_plus_g1_plus_1) +ENTRY(U3_retl_o2_fp) + ba,pt %xcc, __restore_fp + mov %o2, %o0 +ENDPROC(U3_retl_o2_fp) +ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp) + sll %o3, 6, %o3 + add %o3, 0x80, %o3 + ba,pt %xcc, __restore_fp + add %o2, %o3, %o0 +ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp) +ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp) + sll %o3, 6, %o3 + add %o3, 0x40, %o3 + ba,pt %xcc, __restore_fp + add %o2, %o3, %o0 +ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp) +ENTRY(U3_retl_o2_plus_GS_plus_0x10) + add GLOBAL_SPARE, 0x10, GLOBAL_SPARE + retl + add %o2, GLOBAL_SPARE, %o0 +ENDPROC(U3_retl_o2_plus_GS_plus_0x10) +ENTRY(U3_retl_o2_plus_GS_plus_0x08) + add GLOBAL_SPARE, 0x08, GLOBAL_SPARE + retl + add %o2, GLOBAL_SPARE, %o0 +ENDPROC(U3_retl_o2_plus_GS_plus_0x08) +ENTRY(U3_retl_o2_and_7_plus_GS) + and %o2, 7, %o2 + retl + add %o2, GLOBAL_SPARE, %o0 +ENDPROC(U3_retl_o2_and_7_plus_GS) +ENTRY(U3_retl_o2_and_7_plus_GS_plus_8) + add GLOBAL_SPARE, 8, GLOBAL_SPARE + and %o2, 7, %o2 + retl + add %o2, GLOBAL_SPARE, %o0 +ENDPROC(U3_retl_o2_and_7_plus_GS_plus_8) +#endif + + .align 64 + + /* The cheetah's flexible spine, oversized liver, enlarged heart, + * slender muscular body, and claws make it the swiftest hunter + * in Africa and the fastest animal on land. Can reach speeds + * of up to 2.4GB per second. + */ + + .globl FUNC_NAME + .type FUNC_NAME,#function +FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ + srlx %o2, 31, %g2 + cmp %g2, 0 + + /* software trap 5 "Range Check" if dst >= 0x80000000 */ + tne %xcc, 5 + PREAMBLE + mov %o0, %o4 + + /* if len == 0 */ + cmp %o2, 0 + be,pn %XCC, end_return + or %o0, %o1, %o3 + + /* if len < 16 */ + cmp %o2, 16 + blu,a,pn %XCC, less_than_16 + or %o3, %o2, %o3 + + /* if len < 192 */ + cmp %o2, (3 * 64) + blu,pt %XCC, less_than_192 + andcc %o3, 0x7, %g0 + + /* Clobbers o5/g1/g2/g3/g7/icc/xcc. We must preserve + * o5 from here until we hit VISExitHalf. + */ + VISEntryHalf + + /* Is 'dst' already aligned on an 64-byte boundary? */ + andcc %o0, 0x3f, %g2 + be,pt %XCC, 2f + + /* Compute abs((dst & 0x3f) - 0x40) into %g2. This is the number + * of bytes to copy to make 'dst' 64-byte aligned. We pre- + * subtract this from 'len'. + */ + sub %o0, %o1, GLOBAL_SPARE + sub %g2, 0x40, %g2 + sub %g0, %g2, %g2 + sub %o2, %g2, %o2 + andcc %g2, 0x7, %g1 + be,pt %icc, 2f + and %g2, 0x38, %g2 + +1: subcc %g1, 0x1, %g1 + EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U3_retl_o2_plus_g2_plus_g1_plus_1) + EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE), U3_retl_o2_plus_g2_plus_g1_plus_1) + bgu,pt %XCC, 1b + add %o1, 0x1, %o1 + + add %o1, GLOBAL_SPARE, %o0 + +2: cmp %g2, 0x0 + and %o1, 0x7, %g1 + be,pt %icc, 3f + alignaddr %o1, %g0, %o1 + + EX_LD_FP(LOAD(ldd, %o1, %f4), U3_retl_o2_plus_g2) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U3_retl_o2_plus_g2) + add %o1, 0x8, %o1 + subcc %g2, 0x8, %g2 + faligndata %f4, %f6, %f0 + EX_ST_FP(STORE(std, %f0, %o0), U3_retl_o2_plus_g2_plus_8) + be,pn %icc, 3f + add %o0, 0x8, %o0 + + EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U3_retl_o2_plus_g2) + add %o1, 0x8, %o1 + subcc %g2, 0x8, %g2 + faligndata %f6, %f4, %f2 + EX_ST_FP(STORE(std, %f2, %o0), U3_retl_o2_plus_g2_plus_8) + bne,pt %icc, 1b + add %o0, 0x8, %o0 + +3: LOAD(prefetch, %o1 + 0x000, #one_read) + LOAD(prefetch, %o1 + 0x040, #one_read) + andn %o2, (0x40 - 1), GLOBAL_SPARE + LOAD(prefetch, %o1 + 0x080, #one_read) + LOAD(prefetch, %o1 + 0x0c0, #one_read) + LOAD(prefetch, %o1 + 0x100, #one_read) + EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0), U3_retl_o2) + LOAD(prefetch, %o1 + 0x140, #one_read) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2) + LOAD(prefetch, %o1 + 0x180, #one_read) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2) + LOAD(prefetch, %o1 + 0x1c0, #one_read) + faligndata %f0, %f2, %f16 + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2) + faligndata %f2, %f4, %f18 + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2) + faligndata %f4, %f6, %f20 + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2) + faligndata %f6, %f8, %f22 + + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2) + faligndata %f8, %f10, %f24 + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2) + faligndata %f10, %f12, %f26 + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2) + + subcc GLOBAL_SPARE, 0x80, GLOBAL_SPARE + add %o1, 0x40, %o1 + bgu,pt %XCC, 1f + srl GLOBAL_SPARE, 6, %o3 + ba,pt %xcc, 2f + nop + + .align 64 +1: + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80) + faligndata %f12, %f14, %f28 + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80) + faligndata %f14, %f0, %f30 + EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40) + faligndata %f0, %f2, %f16 + add %o0, 0x40, %o0 + + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40) + faligndata %f2, %f4, %f18 + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40) + faligndata %f4, %f6, %f20 + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40) + subcc %o3, 0x01, %o3 + faligndata %f6, %f8, %f22 + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x80) + + faligndata %f8, %f10, %f24 + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x80) + LOAD(prefetch, %o1 + 0x1c0, #one_read) + faligndata %f10, %f12, %f26 + bg,pt %XCC, 1b + add %o1, 0x40, %o1 + + /* Finally we copy the last full 64-byte block. */ +2: + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80) + faligndata %f12, %f14, %f28 + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80) + faligndata %f14, %f0, %f30 + EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40) + faligndata %f0, %f2, %f16 + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40) + faligndata %f2, %f4, %f18 + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40) + faligndata %f4, %f6, %f20 + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40) + faligndata %f6, %f8, %f22 + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x40) + faligndata %f8, %f10, %f24 + cmp %g1, 0 + be,pt %XCC, 1f + add %o0, 0x40, %o0 + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x40) +1: faligndata %f10, %f12, %f26 + faligndata %f12, %f14, %f28 + faligndata %f14, %f0, %f30 + EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x40) + add %o0, 0x40, %o0 + add %o1, 0x40, %o1 + membar #Sync + + /* Now we copy the (len modulo 64) bytes at the end. + * Note how we borrow the %f0 loaded above. + * + * Also notice how this code is careful not to perform a + * load past the end of the src buffer. + */ + and %o2, 0x3f, %o2 + andcc %o2, 0x38, %g2 + be,pn %XCC, 2f + subcc %g2, 0x8, %g2 + be,pn %XCC, 2f + cmp %g1, 0 + + sub %o2, %g2, %o2 + be,a,pt %XCC, 1f + EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0), U3_retl_o2_plus_g2) + +1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2), U3_retl_o2_plus_g2) + add %o1, 0x8, %o1 + subcc %g2, 0x8, %g2 + faligndata %f0, %f2, %f8 + EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8) + be,pn %XCC, 2f + add %o0, 0x8, %o0 + EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0), U3_retl_o2_plus_g2) + add %o1, 0x8, %o1 + subcc %g2, 0x8, %g2 + faligndata %f2, %f0, %f8 + EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8) + bne,pn %XCC, 1b + add %o0, 0x8, %o0 + + /* If anything is left, we copy it one byte at a time. + * Note that %g1 is (src & 0x3) saved above before the + * alignaddr was performed. + */ +2: + cmp %o2, 0 + add %o1, %g1, %o1 + VISExitHalf + be,pn %XCC, end_return + sub %o0, %o1, %o3 + + andcc %g1, 0x7, %g0 + bne,pn %icc, 90f + andcc %o2, 0x8, %g0 + be,pt %icc, 1f + nop + EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2) + EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2) + add %o1, 0x8, %o1 + sub %o2, 8, %o2 + +1: andcc %o2, 0x4, %g0 + be,pt %icc, 1f + nop + EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2) + EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2) + add %o1, 0x4, %o1 + sub %o2, 4, %o2 + +1: andcc %o2, 0x2, %g0 + be,pt %icc, 1f + nop + EX_LD(LOAD(lduh, %o1, %o5), U3_retl_o2) + EX_ST(STORE(sth, %o5, %o1 + %o3), U3_retl_o2) + add %o1, 0x2, %o1 + sub %o2, 2, %o2 + +1: andcc %o2, 0x1, %g0 + be,pt %icc, end_return + nop + EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2) + ba,pt %xcc, end_return + EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2) + + .align 64 + /* 16 <= len < 192 */ +less_than_192: + bne,pn %XCC, 75f + sub %o0, %o1, %o3 + +72: + andn %o2, 0xf, GLOBAL_SPARE + and %o2, 0xf, %o2 +1: subcc GLOBAL_SPARE, 0x10, GLOBAL_SPARE + EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U3_retl_o2_plus_GS_plus_0x10) + EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U3_retl_o2_plus_GS_plus_0x10) + EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x10) + add %o1, 0x8, %o1 + EX_ST(STORE(stx, %g1, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x08) + bgu,pt %XCC, 1b + add %o1, 0x8, %o1 +73: andcc %o2, 0x8, %g0 + be,pt %XCC, 1f + nop + sub %o2, 0x8, %o2 + EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2_plus_8) + EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_8) + add %o1, 0x8, %o1 +1: andcc %o2, 0x4, %g0 + be,pt %XCC, 1f + nop + sub %o2, 0x4, %o2 + EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2_plus_4) + EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2_plus_4) + add %o1, 0x4, %o1 +1: cmp %o2, 0 + be,pt %XCC, end_return + nop + ba,pt %xcc, 90f + nop + +75: + andcc %o0, 0x7, %g1 + sub %g1, 0x8, %g1 + be,pn %icc, 2f + sub %g0, %g1, %g1 + sub %o2, %g1, %o2 + +1: subcc %g1, 1, %g1 + EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2_plus_g1_plus_1) + EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2_plus_g1_plus_1) + bgu,pt %icc, 1b + add %o1, 1, %o1 + +2: add %o1, %o3, %o0 + andcc %o1, 0x7, %g1 + bne,pt %icc, 8f + sll %g1, 3, %g1 + + cmp %o2, 16 + bgeu,pt %icc, 72b + nop + ba,a,pt %xcc, 73b + +8: mov 64, %o3 + andn %o1, 0x7, %o1 + EX_LD(LOAD(ldx, %o1, %g2), U3_retl_o2) + sub %o3, %g1, %o3 + andn %o2, 0x7, GLOBAL_SPARE + sllx %g2, %g1, %g2 +1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U3_retl_o2_and_7_plus_GS) + subcc GLOBAL_SPARE, 0x8, GLOBAL_SPARE + add %o1, 0x8, %o1 + srlx %g3, %o3, %o5 + or %o5, %g2, %o5 + EX_ST(STORE(stx, %o5, %o0), U3_retl_o2_and_7_plus_GS_plus_8) + add %o0, 0x8, %o0 + bgu,pt %icc, 1b + sllx %g3, %g1, %g2 + + srl %g1, 3, %g1 + andcc %o2, 0x7, %o2 + be,pn %icc, end_return + add %o1, %g1, %o1 + ba,pt %xcc, 90f + sub %o0, %o1, %o3 + + .align 64 + /* 0 < len < 16 */ +less_than_16: + andcc %o3, 0x3, %g0 + bne,pn %XCC, 90f + sub %o0, %o1, %o3 + +1: + subcc %o2, 4, %o2 + EX_LD(LOAD(lduw, %o1, %g1), U3_retl_o2_plus_4) + EX_ST(STORE(stw, %g1, %o1 + %o3), U3_retl_o2_plus_4) + bgu,pt %XCC, 1b + add %o1, 4, %o1 + +end_return: + retl + mov EX_RETVAL(%o4), %o0 + + .align 32 +90: + subcc %o2, 1, %o2 + EX_LD(LOAD(ldub, %o1, %g1), U3_retl_o2_plus_1) + EX_ST(STORE(stb, %g1, %o1 + %o3), U3_retl_o2_plus_1) + bgu,pt %XCC, 90b + add %o1, 1, %o1 + retl + mov EX_RETVAL(%o4), %o0 + + .size FUNC_NAME, .-FUNC_NAME -- cgit v1.2.3