aboutsummaryrefslogtreecommitdiff
path: root/arch/sparc/lib/memcpy.S
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /arch/sparc/lib/memcpy.S
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
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(). ...
Diffstat (limited to 'arch/sparc/lib/memcpy.S')
-rw-r--r--arch/sparc/lib/memcpy.S462
1 files changed, 462 insertions, 0 deletions
diff --git a/arch/sparc/lib/memcpy.S b/arch/sparc/lib/memcpy.S
new file mode 100644
index 000000000..ee823d8c9
--- /dev/null
+++ b/arch/sparc/lib/memcpy.S
@@ -0,0 +1,462 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* memcpy.S: Sparc optimized memcpy and memmove code
+ * Hand optimized from GNU libc's memcpy and memmove
+ * Copyright (C) 1991,1996 Free Software Foundation
+ * Copyright (C) 1995 Linus Torvalds (Linus.Torvalds@helsinki.fi)
+ * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
+ * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
+ * Copyright (C) 1996 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ */
+
+#include <asm/export.h>
+#define FUNC(x) \
+ .globl x; \
+ .type x,@function; \
+ .align 4; \
+x:
+
+/* Both these macros have to start with exactly the same insn */
+#define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
+ ldd [%src + (offset) + 0x00], %t0; \
+ ldd [%src + (offset) + 0x08], %t2; \
+ ldd [%src + (offset) + 0x10], %t4; \
+ ldd [%src + (offset) + 0x18], %t6; \
+ st %t0, [%dst + (offset) + 0x00]; \
+ st %t1, [%dst + (offset) + 0x04]; \
+ st %t2, [%dst + (offset) + 0x08]; \
+ st %t3, [%dst + (offset) + 0x0c]; \
+ st %t4, [%dst + (offset) + 0x10]; \
+ st %t5, [%dst + (offset) + 0x14]; \
+ st %t6, [%dst + (offset) + 0x18]; \
+ st %t7, [%dst + (offset) + 0x1c];
+
+#define MOVE_BIGALIGNCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
+ ldd [%src + (offset) + 0x00], %t0; \
+ ldd [%src + (offset) + 0x08], %t2; \
+ ldd [%src + (offset) + 0x10], %t4; \
+ ldd [%src + (offset) + 0x18], %t6; \
+ std %t0, [%dst + (offset) + 0x00]; \
+ std %t2, [%dst + (offset) + 0x08]; \
+ std %t4, [%dst + (offset) + 0x10]; \
+ std %t6, [%dst + (offset) + 0x18];
+
+#define MOVE_LASTCHUNK(src, dst, offset, t0, t1, t2, t3) \
+ ldd [%src - (offset) - 0x10], %t0; \
+ ldd [%src - (offset) - 0x08], %t2; \
+ st %t0, [%dst - (offset) - 0x10]; \
+ st %t1, [%dst - (offset) - 0x0c]; \
+ st %t2, [%dst - (offset) - 0x08]; \
+ st %t3, [%dst - (offset) - 0x04];
+
+#define MOVE_LASTALIGNCHUNK(src, dst, offset, t0, t1, t2, t3) \
+ ldd [%src - (offset) - 0x10], %t0; \
+ ldd [%src - (offset) - 0x08], %t2; \
+ std %t0, [%dst - (offset) - 0x10]; \
+ std %t2, [%dst - (offset) - 0x08];
+
+#define MOVE_SHORTCHUNK(src, dst, offset, t0, t1) \
+ ldub [%src - (offset) - 0x02], %t0; \
+ ldub [%src - (offset) - 0x01], %t1; \
+ stb %t0, [%dst - (offset) - 0x02]; \
+ stb %t1, [%dst - (offset) - 0x01];
+
+ .text
+ .align 4
+
+FUNC(memmove)
+EXPORT_SYMBOL(memmove)
+ cmp %o0, %o1
+ mov %o0, %g7
+ bleu 9f
+ sub %o0, %o1, %o4
+
+ add %o1, %o2, %o3
+ cmp %o3, %o0
+ bleu 0f
+ andcc %o4, 3, %o5
+
+ add %o1, %o2, %o1
+ add %o0, %o2, %o0
+ sub %o1, 1, %o1
+ sub %o0, 1, %o0
+
+1: /* reverse_bytes */
+
+ ldub [%o1], %o4
+ subcc %o2, 1, %o2
+ stb %o4, [%o0]
+ sub %o1, 1, %o1
+ bne 1b
+ sub %o0, 1, %o0
+
+ retl
+ mov %g7, %o0
+
+/* NOTE: This code is executed just for the cases,
+ where %src (=%o1) & 3 is != 0.
+ We need to align it to 4. So, for (%src & 3)
+ 1 we need to do ldub,lduh
+ 2 lduh
+ 3 just ldub
+ so even if it looks weird, the branches
+ are correct here. -jj
+ */
+78: /* dword_align */
+
+ andcc %o1, 1, %g0
+ be 4f
+ andcc %o1, 2, %g0
+
+ ldub [%o1], %g2
+ add %o1, 1, %o1
+ stb %g2, [%o0]
+ sub %o2, 1, %o2
+ bne 3f
+ add %o0, 1, %o0
+4:
+ lduh [%o1], %g2
+ add %o1, 2, %o1
+ sth %g2, [%o0]
+ sub %o2, 2, %o2
+ b 3f
+ add %o0, 2, %o0
+
+FUNC(memcpy) /* %o0=dst %o1=src %o2=len */
+EXPORT_SYMBOL(memcpy)
+
+ sub %o0, %o1, %o4
+ mov %o0, %g7
+9:
+ andcc %o4, 3, %o5
+0:
+ bne 86f
+ cmp %o2, 15
+
+ bleu 90f
+ andcc %o1, 3, %g0
+
+ bne 78b
+3:
+ andcc %o1, 4, %g0
+
+ be 2f
+ mov %o2, %g1
+
+ ld [%o1], %o4
+ sub %g1, 4, %g1
+ st %o4, [%o0]
+ add %o1, 4, %o1
+ add %o0, 4, %o0
+2:
+ andcc %g1, 0xffffff80, %g0
+ be 3f
+ andcc %o0, 4, %g0
+
+ be 82f + 4
+5:
+ MOVE_BIGCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5)
+ MOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
+ MOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
+ MOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
+ sub %g1, 128, %g1
+ add %o1, 128, %o1
+ cmp %g1, 128
+ bge 5b
+ add %o0, 128, %o0
+3:
+ andcc %g1, 0x70, %g4
+ be 80f
+ andcc %g1, 8, %g0
+
+ sethi %hi(80f), %o5
+ srl %g4, 1, %o4
+ add %g4, %o4, %o4
+ add %o1, %g4, %o1
+ sub %o5, %o4, %o5
+ jmpl %o5 + %lo(80f), %g0
+ add %o0, %g4, %o0
+
+79: /* memcpy_table */
+
+ MOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g4, g5)
+ MOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g4, g5)
+ MOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g4, g5)
+ MOVE_LASTCHUNK(o1, o0, 0x30, g2, g3, g4, g5)
+ MOVE_LASTCHUNK(o1, o0, 0x20, g2, g3, g4, g5)
+ MOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g4, g5)
+ MOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
+
+80: /* memcpy_table_end */
+ be 81f
+ andcc %g1, 4, %g0
+
+ ldd [%o1], %g2
+ add %o0, 8, %o0
+ st %g2, [%o0 - 0x08]
+ add %o1, 8, %o1
+ st %g3, [%o0 - 0x04]
+
+81: /* memcpy_last7 */
+
+ be 1f
+ andcc %g1, 2, %g0
+
+ ld [%o1], %g2
+ add %o1, 4, %o1
+ st %g2, [%o0]
+ add %o0, 4, %o0
+1:
+ be 1f
+ andcc %g1, 1, %g0
+
+ lduh [%o1], %g2
+ add %o1, 2, %o1
+ sth %g2, [%o0]
+ add %o0, 2, %o0
+1:
+ be 1f
+ nop
+
+ ldub [%o1], %g2
+ stb %g2, [%o0]
+1:
+ retl
+ mov %g7, %o0
+
+82: /* ldd_std */
+ MOVE_BIGALIGNCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5)
+ MOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
+ MOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
+ MOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
+ subcc %g1, 128, %g1
+ add %o1, 128, %o1
+ cmp %g1, 128
+ bge 82b
+ add %o0, 128, %o0
+
+ andcc %g1, 0x70, %g4
+ be 84f
+ andcc %g1, 8, %g0
+
+ sethi %hi(84f), %o5
+ add %o1, %g4, %o1
+ sub %o5, %g4, %o5
+ jmpl %o5 + %lo(84f), %g0
+ add %o0, %g4, %o0
+
+83: /* amemcpy_table */
+
+ MOVE_LASTALIGNCHUNK(o1, o0, 0x60, g2, g3, g4, g5)
+ MOVE_LASTALIGNCHUNK(o1, o0, 0x50, g2, g3, g4, g5)
+ MOVE_LASTALIGNCHUNK(o1, o0, 0x40, g2, g3, g4, g5)
+ MOVE_LASTALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5)
+ MOVE_LASTALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5)
+ MOVE_LASTALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5)
+ MOVE_LASTALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
+
+84: /* amemcpy_table_end */
+ be 85f
+ andcc %g1, 4, %g0
+
+ ldd [%o1], %g2
+ add %o0, 8, %o0
+ std %g2, [%o0 - 0x08]
+ add %o1, 8, %o1
+85: /* amemcpy_last7 */
+ be 1f
+ andcc %g1, 2, %g0
+
+ ld [%o1], %g2
+ add %o1, 4, %o1
+ st %g2, [%o0]
+ add %o0, 4, %o0
+1:
+ be 1f
+ andcc %g1, 1, %g0
+
+ lduh [%o1], %g2
+ add %o1, 2, %o1
+ sth %g2, [%o0]
+ add %o0, 2, %o0
+1:
+ be 1f
+ nop
+
+ ldub [%o1], %g2
+ stb %g2, [%o0]
+1:
+ retl
+ mov %g7, %o0
+
+86: /* non_aligned */
+ cmp %o2, 6
+ bleu 88f
+ nop
+
+ save %sp, -96, %sp
+ andcc %i0, 3, %g0
+ be 61f
+ andcc %i0, 1, %g0
+ be 60f
+ andcc %i0, 2, %g0
+
+ ldub [%i1], %g5
+ add %i1, 1, %i1
+ stb %g5, [%i0]
+ sub %i2, 1, %i2
+ bne 61f
+ add %i0, 1, %i0
+60:
+ ldub [%i1], %g3
+ add %i1, 2, %i1
+ stb %g3, [%i0]
+ sub %i2, 2, %i2
+ ldub [%i1 - 1], %g3
+ add %i0, 2, %i0
+ stb %g3, [%i0 - 1]
+61:
+ and %i1, 3, %g2
+ and %i2, 0xc, %g3
+ and %i1, -4, %i1
+ cmp %g3, 4
+ sll %g2, 3, %g4
+ mov 32, %g2
+ be 4f
+ sub %g2, %g4, %l0
+
+ blu 3f
+ cmp %g3, 0x8
+
+ be 2f
+ srl %i2, 2, %g3
+
+ ld [%i1], %i3
+ add %i0, -8, %i0
+ ld [%i1 + 4], %i4
+ b 8f
+ add %g3, 1, %g3
+2:
+ ld [%i1], %i4
+ add %i0, -12, %i0
+ ld [%i1 + 4], %i5
+ add %g3, 2, %g3
+ b 9f
+ add %i1, -4, %i1
+3:
+ ld [%i1], %g1
+ add %i0, -4, %i0
+ ld [%i1 + 4], %i3
+ srl %i2, 2, %g3
+ b 7f
+ add %i1, 4, %i1
+4:
+ ld [%i1], %i5
+ cmp %i2, 7
+ ld [%i1 + 4], %g1
+ srl %i2, 2, %g3
+ bleu 10f
+ add %i1, 8, %i1
+
+ ld [%i1], %i3
+ add %g3, -1, %g3
+5:
+ sll %i5, %g4, %g2
+ srl %g1, %l0, %g5
+ or %g2, %g5, %g2
+ st %g2, [%i0]
+7:
+ ld [%i1 + 4], %i4
+ sll %g1, %g4, %g2
+ srl %i3, %l0, %g5
+ or %g2, %g5, %g2
+ st %g2, [%i0 + 4]
+8:
+ ld [%i1 + 8], %i5
+ sll %i3, %g4, %g2
+ srl %i4, %l0, %g5
+ or %g2, %g5, %g2
+ st %g2, [%i0 + 8]
+9:
+ ld [%i1 + 12], %g1
+ sll %i4, %g4, %g2
+ srl %i5, %l0, %g5
+ addcc %g3, -4, %g3
+ or %g2, %g5, %g2
+ add %i1, 16, %i1
+ st %g2, [%i0 + 12]
+ add %i0, 16, %i0
+ bne,a 5b
+ ld [%i1], %i3
+10:
+ sll %i5, %g4, %g2
+ srl %g1, %l0, %g5
+ srl %l0, 3, %g3
+ or %g2, %g5, %g2
+ sub %i1, %g3, %i1
+ andcc %i2, 2, %g0
+ st %g2, [%i0]
+ be 1f
+ andcc %i2, 1, %g0
+
+ ldub [%i1], %g2
+ add %i1, 2, %i1
+ stb %g2, [%i0 + 4]
+ add %i0, 2, %i0
+ ldub [%i1 - 1], %g2
+ stb %g2, [%i0 + 3]
+1:
+ be 1f
+ nop
+ ldub [%i1], %g2
+ stb %g2, [%i0 + 4]
+1:
+ ret
+ restore %g7, %g0, %o0
+
+88: /* short_end */
+
+ and %o2, 0xe, %o3
+20:
+ sethi %hi(89f), %o5
+ sll %o3, 3, %o4
+ add %o0, %o3, %o0
+ sub %o5, %o4, %o5
+ add %o1, %o3, %o1
+ jmpl %o5 + %lo(89f), %g0
+ andcc %o2, 1, %g0
+
+ MOVE_SHORTCHUNK(o1, o0, 0x0c, g2, g3)
+ MOVE_SHORTCHUNK(o1, o0, 0x0a, g2, g3)
+ MOVE_SHORTCHUNK(o1, o0, 0x08, g2, g3)
+ MOVE_SHORTCHUNK(o1, o0, 0x06, g2, g3)
+ MOVE_SHORTCHUNK(o1, o0, 0x04, g2, g3)
+ MOVE_SHORTCHUNK(o1, o0, 0x02, g2, g3)
+ MOVE_SHORTCHUNK(o1, o0, 0x00, g2, g3)
+
+89: /* short_table_end */
+
+ be 1f
+ nop
+
+ ldub [%o1], %g2
+ stb %g2, [%o0]
+1:
+ retl
+ mov %g7, %o0
+
+90: /* short_aligned_end */
+ bne 88b
+ andcc %o2, 8, %g0
+
+ be 1f
+ andcc %o2, 4, %g0
+
+ ld [%o1 + 0x00], %g2
+ ld [%o1 + 0x04], %g3
+ add %o1, 8, %o1
+ st %g2, [%o0 + 0x00]
+ st %g3, [%o0 + 0x04]
+ add %o0, 8, %o0
+1:
+ b 81b
+ mov %o2, %g1