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/alpha/include/asm/xor.h | 866 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 866 insertions(+) create mode 100644 arch/alpha/include/asm/xor.h (limited to 'arch/alpha/include/asm/xor.h') diff --git a/arch/alpha/include/asm/xor.h b/arch/alpha/include/asm/xor.h new file mode 100644 index 000000000..e0de0c233 --- /dev/null +++ b/arch/alpha/include/asm/xor.h @@ -0,0 +1,866 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * include/asm-alpha/xor.h + * + * Optimized RAID-5 checksumming functions for alpha EV5 and EV6 + */ + +extern void +xor_alpha_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2); +extern void +xor_alpha_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3); +extern void +xor_alpha_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4); +extern void +xor_alpha_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5); + +extern void +xor_alpha_prefetch_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2); +extern void +xor_alpha_prefetch_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3); +extern void +xor_alpha_prefetch_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4); +extern void +xor_alpha_prefetch_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5); + +asm(" \n\ + .text \n\ + .align 3 \n\ + .ent xor_alpha_2 \n\ +xor_alpha_2: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + .align 4 \n\ +2: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,8($17) \n\ + ldq $3,8($18) \n\ + \n\ + ldq $4,16($17) \n\ + ldq $5,16($18) \n\ + ldq $6,24($17) \n\ + ldq $7,24($18) \n\ + \n\ + ldq $19,32($17) \n\ + ldq $20,32($18) \n\ + ldq $21,40($17) \n\ + ldq $22,40($18) \n\ + \n\ + ldq $23,48($17) \n\ + ldq $24,48($18) \n\ + ldq $25,56($17) \n\ + xor $0,$1,$0 # 7 cycles from $1 load \n\ + \n\ + ldq $27,56($18) \n\ + xor $2,$3,$2 \n\ + stq $0,0($17) \n\ + xor $4,$5,$4 \n\ + \n\ + stq $2,8($17) \n\ + xor $6,$7,$6 \n\ + stq $4,16($17) \n\ + xor $19,$20,$19 \n\ + \n\ + stq $6,24($17) \n\ + xor $21,$22,$21 \n\ + stq $19,32($17) \n\ + xor $23,$24,$23 \n\ + \n\ + stq $21,40($17) \n\ + xor $25,$27,$25 \n\ + stq $23,48($17) \n\ + subq $16,1,$16 \n\ + \n\ + stq $25,56($17) \n\ + addq $17,64,$17 \n\ + addq $18,64,$18 \n\ + bgt $16,2b \n\ + \n\ + ret \n\ + .end xor_alpha_2 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_3 \n\ +xor_alpha_3: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + .align 4 \n\ +3: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,8($17) \n\ + \n\ + ldq $4,8($18) \n\ + ldq $6,16($17) \n\ + ldq $7,16($18) \n\ + ldq $21,24($17) \n\ + \n\ + ldq $22,24($18) \n\ + ldq $24,32($17) \n\ + ldq $25,32($18) \n\ + ldq $5,8($19) \n\ + \n\ + ldq $20,16($19) \n\ + ldq $23,24($19) \n\ + ldq $27,32($19) \n\ + nop \n\ + \n\ + xor $0,$1,$1 # 8 cycles from $0 load \n\ + xor $3,$4,$4 # 6 cycles from $4 load \n\ + xor $6,$7,$7 # 6 cycles from $7 load \n\ + xor $21,$22,$22 # 5 cycles from $22 load \n\ + \n\ + xor $1,$2,$2 # 9 cycles from $2 load \n\ + xor $24,$25,$25 # 5 cycles from $25 load \n\ + stq $2,0($17) \n\ + xor $4,$5,$5 # 6 cycles from $5 load \n\ + \n\ + stq $5,8($17) \n\ + xor $7,$20,$20 # 7 cycles from $20 load \n\ + stq $20,16($17) \n\ + xor $22,$23,$23 # 7 cycles from $23 load \n\ + \n\ + stq $23,24($17) \n\ + xor $25,$27,$27 # 7 cycles from $27 load \n\ + stq $27,32($17) \n\ + nop \n\ + \n\ + ldq $0,40($17) \n\ + ldq $1,40($18) \n\ + ldq $3,48($17) \n\ + ldq $4,48($18) \n\ + \n\ + ldq $6,56($17) \n\ + ldq $7,56($18) \n\ + ldq $2,40($19) \n\ + ldq $5,48($19) \n\ + \n\ + ldq $20,56($19) \n\ + xor $0,$1,$1 # 4 cycles from $1 load \n\ + xor $3,$4,$4 # 5 cycles from $4 load \n\ + xor $6,$7,$7 # 5 cycles from $7 load \n\ + \n\ + xor $1,$2,$2 # 4 cycles from $2 load \n\ + xor $4,$5,$5 # 5 cycles from $5 load \n\ + stq $2,40($17) \n\ + xor $7,$20,$20 # 4 cycles from $20 load \n\ + \n\ + stq $5,48($17) \n\ + subq $16,1,$16 \n\ + stq $20,56($17) \n\ + addq $19,64,$19 \n\ + \n\ + addq $18,64,$18 \n\ + addq $17,64,$17 \n\ + bgt $16,3b \n\ + ret \n\ + .end xor_alpha_3 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_4 \n\ +xor_alpha_4: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + .align 4 \n\ +4: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,0($20) \n\ + \n\ + ldq $4,8($17) \n\ + ldq $5,8($18) \n\ + ldq $6,8($19) \n\ + ldq $7,8($20) \n\ + \n\ + ldq $21,16($17) \n\ + ldq $22,16($18) \n\ + ldq $23,16($19) \n\ + ldq $24,16($20) \n\ + \n\ + ldq $25,24($17) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + ldq $27,24($18) \n\ + xor $2,$3,$3 # 6 cycles from $3 load \n\ + \n\ + ldq $0,24($19) \n\ + xor $1,$3,$3 \n\ + ldq $1,24($20) \n\ + xor $4,$5,$5 # 7 cycles from $5 load \n\ + \n\ + stq $3,0($17) \n\ + xor $6,$7,$7 \n\ + xor $21,$22,$22 # 7 cycles from $22 load \n\ + xor $5,$7,$7 \n\ + \n\ + stq $7,8($17) \n\ + xor $23,$24,$24 # 7 cycles from $24 load \n\ + ldq $2,32($17) \n\ + xor $22,$24,$24 \n\ + \n\ + ldq $3,32($18) \n\ + ldq $4,32($19) \n\ + ldq $5,32($20) \n\ + xor $25,$27,$27 # 8 cycles from $27 load \n\ + \n\ + ldq $6,40($17) \n\ + ldq $7,40($18) \n\ + ldq $21,40($19) \n\ + ldq $22,40($20) \n\ + \n\ + stq $24,16($17) \n\ + xor $0,$1,$1 # 9 cycles from $1 load \n\ + xor $2,$3,$3 # 5 cycles from $3 load \n\ + xor $27,$1,$1 \n\ + \n\ + stq $1,24($17) \n\ + xor $4,$5,$5 # 5 cycles from $5 load \n\ + ldq $23,48($17) \n\ + ldq $24,48($18) \n\ + \n\ + ldq $25,48($19) \n\ + xor $3,$5,$5 \n\ + ldq $27,48($20) \n\ + ldq $0,56($17) \n\ + \n\ + ldq $1,56($18) \n\ + ldq $2,56($19) \n\ + xor $6,$7,$7 # 8 cycles from $6 load \n\ + ldq $3,56($20) \n\ + \n\ + stq $5,32($17) \n\ + xor $21,$22,$22 # 8 cycles from $22 load \n\ + xor $7,$22,$22 \n\ + xor $23,$24,$24 # 5 cycles from $24 load \n\ + \n\ + stq $22,40($17) \n\ + xor $25,$27,$27 # 5 cycles from $27 load \n\ + xor $24,$27,$27 \n\ + xor $0,$1,$1 # 5 cycles from $1 load \n\ + \n\ + stq $27,48($17) \n\ + xor $2,$3,$3 # 4 cycles from $3 load \n\ + xor $1,$3,$3 \n\ + subq $16,1,$16 \n\ + \n\ + stq $3,56($17) \n\ + addq $20,64,$20 \n\ + addq $19,64,$19 \n\ + addq $18,64,$18 \n\ + \n\ + addq $17,64,$17 \n\ + bgt $16,4b \n\ + ret \n\ + .end xor_alpha_4 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_5 \n\ +xor_alpha_5: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + .align 4 \n\ +5: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,0($20) \n\ + \n\ + ldq $4,0($21) \n\ + ldq $5,8($17) \n\ + ldq $6,8($18) \n\ + ldq $7,8($19) \n\ + \n\ + ldq $22,8($20) \n\ + ldq $23,8($21) \n\ + ldq $24,16($17) \n\ + ldq $25,16($18) \n\ + \n\ + ldq $27,16($19) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + ldq $28,16($20) \n\ + xor $2,$3,$3 # 6 cycles from $3 load \n\ + \n\ + ldq $0,16($21) \n\ + xor $1,$3,$3 \n\ + ldq $1,24($17) \n\ + xor $3,$4,$4 # 7 cycles from $4 load \n\ + \n\ + stq $4,0($17) \n\ + xor $5,$6,$6 # 7 cycles from $6 load \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + xor $6,$23,$23 # 7 cycles from $23 load \n\ + \n\ + ldq $2,24($18) \n\ + xor $22,$23,$23 \n\ + ldq $3,24($19) \n\ + xor $24,$25,$25 # 8 cycles from $25 load \n\ + \n\ + stq $23,8($17) \n\ + xor $25,$27,$27 # 8 cycles from $27 load \n\ + ldq $4,24($20) \n\ + xor $28,$0,$0 # 7 cycles from $0 load \n\ + \n\ + ldq $5,24($21) \n\ + xor $27,$0,$0 \n\ + ldq $6,32($17) \n\ + ldq $7,32($18) \n\ + \n\ + stq $0,16($17) \n\ + xor $1,$2,$2 # 6 cycles from $2 load \n\ + ldq $22,32($19) \n\ + xor $3,$4,$4 # 4 cycles from $4 load \n\ + \n\ + ldq $23,32($20) \n\ + xor $2,$4,$4 \n\ + ldq $24,32($21) \n\ + ldq $25,40($17) \n\ + \n\ + ldq $27,40($18) \n\ + ldq $28,40($19) \n\ + ldq $0,40($20) \n\ + xor $4,$5,$5 # 7 cycles from $5 load \n\ + \n\ + stq $5,24($17) \n\ + xor $6,$7,$7 # 7 cycles from $7 load \n\ + ldq $1,40($21) \n\ + ldq $2,48($17) \n\ + \n\ + ldq $3,48($18) \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + ldq $4,48($19) \n\ + xor $23,$24,$24 # 6 cycles from $24 load \n\ + \n\ + ldq $5,48($20) \n\ + xor $22,$24,$24 \n\ + ldq $6,48($21) \n\ + xor $25,$27,$27 # 7 cycles from $27 load \n\ + \n\ + stq $24,32($17) \n\ + xor $27,$28,$28 # 8 cycles from $28 load \n\ + ldq $7,56($17) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + \n\ + ldq $22,56($18) \n\ + ldq $23,56($19) \n\ + ldq $24,56($20) \n\ + ldq $25,56($21) \n\ + \n\ + xor $28,$1,$1 \n\ + xor $2,$3,$3 # 9 cycles from $3 load \n\ + xor $3,$4,$4 # 9 cycles from $4 load \n\ + xor $5,$6,$6 # 8 cycles from $6 load \n\ + \n\ + stq $1,40($17) \n\ + xor $4,$6,$6 \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + xor $23,$24,$24 # 6 cycles from $24 load \n\ + \n\ + stq $6,48($17) \n\ + xor $22,$24,$24 \n\ + subq $16,1,$16 \n\ + xor $24,$25,$25 # 8 cycles from $25 load \n\ + \n\ + stq $25,56($17) \n\ + addq $21,64,$21 \n\ + addq $20,64,$20 \n\ + addq $19,64,$19 \n\ + \n\ + addq $18,64,$18 \n\ + addq $17,64,$17 \n\ + bgt $16,5b \n\ + ret \n\ + .end xor_alpha_5 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_prefetch_2 \n\ +xor_alpha_prefetch_2: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + \n\ + ldq $31, 0($17) \n\ + ldq $31, 0($18) \n\ + \n\ + ldq $31, 64($17) \n\ + ldq $31, 64($18) \n\ + \n\ + ldq $31, 128($17) \n\ + ldq $31, 128($18) \n\ + \n\ + ldq $31, 192($17) \n\ + ldq $31, 192($18) \n\ + .align 4 \n\ +2: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,8($17) \n\ + ldq $3,8($18) \n\ + \n\ + ldq $4,16($17) \n\ + ldq $5,16($18) \n\ + ldq $6,24($17) \n\ + ldq $7,24($18) \n\ + \n\ + ldq $19,32($17) \n\ + ldq $20,32($18) \n\ + ldq $21,40($17) \n\ + ldq $22,40($18) \n\ + \n\ + ldq $23,48($17) \n\ + ldq $24,48($18) \n\ + ldq $25,56($17) \n\ + ldq $27,56($18) \n\ + \n\ + ldq $31,256($17) \n\ + xor $0,$1,$0 # 8 cycles from $1 load \n\ + ldq $31,256($18) \n\ + xor $2,$3,$2 \n\ + \n\ + stq $0,0($17) \n\ + xor $4,$5,$4 \n\ + stq $2,8($17) \n\ + xor $6,$7,$6 \n\ + \n\ + stq $4,16($17) \n\ + xor $19,$20,$19 \n\ + stq $6,24($17) \n\ + xor $21,$22,$21 \n\ + \n\ + stq $19,32($17) \n\ + xor $23,$24,$23 \n\ + stq $21,40($17) \n\ + xor $25,$27,$25 \n\ + \n\ + stq $23,48($17) \n\ + subq $16,1,$16 \n\ + stq $25,56($17) \n\ + addq $17,64,$17 \n\ + \n\ + addq $18,64,$18 \n\ + bgt $16,2b \n\ + ret \n\ + .end xor_alpha_prefetch_2 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_prefetch_3 \n\ +xor_alpha_prefetch_3: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + \n\ + ldq $31, 0($17) \n\ + ldq $31, 0($18) \n\ + ldq $31, 0($19) \n\ + \n\ + ldq $31, 64($17) \n\ + ldq $31, 64($18) \n\ + ldq $31, 64($19) \n\ + \n\ + ldq $31, 128($17) \n\ + ldq $31, 128($18) \n\ + ldq $31, 128($19) \n\ + \n\ + ldq $31, 192($17) \n\ + ldq $31, 192($18) \n\ + ldq $31, 192($19) \n\ + .align 4 \n\ +3: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,8($17) \n\ + \n\ + ldq $4,8($18) \n\ + ldq $6,16($17) \n\ + ldq $7,16($18) \n\ + ldq $21,24($17) \n\ + \n\ + ldq $22,24($18) \n\ + ldq $24,32($17) \n\ + ldq $25,32($18) \n\ + ldq $5,8($19) \n\ + \n\ + ldq $20,16($19) \n\ + ldq $23,24($19) \n\ + ldq $27,32($19) \n\ + nop \n\ + \n\ + xor $0,$1,$1 # 8 cycles from $0 load \n\ + xor $3,$4,$4 # 7 cycles from $4 load \n\ + xor $6,$7,$7 # 6 cycles from $7 load \n\ + xor $21,$22,$22 # 5 cycles from $22 load \n\ + \n\ + xor $1,$2,$2 # 9 cycles from $2 load \n\ + xor $24,$25,$25 # 5 cycles from $25 load \n\ + stq $2,0($17) \n\ + xor $4,$5,$5 # 6 cycles from $5 load \n\ + \n\ + stq $5,8($17) \n\ + xor $7,$20,$20 # 7 cycles from $20 load \n\ + stq $20,16($17) \n\ + xor $22,$23,$23 # 7 cycles from $23 load \n\ + \n\ + stq $23,24($17) \n\ + xor $25,$27,$27 # 7 cycles from $27 load \n\ + stq $27,32($17) \n\ + nop \n\ + \n\ + ldq $0,40($17) \n\ + ldq $1,40($18) \n\ + ldq $3,48($17) \n\ + ldq $4,48($18) \n\ + \n\ + ldq $6,56($17) \n\ + ldq $7,56($18) \n\ + ldq $2,40($19) \n\ + ldq $5,48($19) \n\ + \n\ + ldq $20,56($19) \n\ + ldq $31,256($17) \n\ + ldq $31,256($18) \n\ + ldq $31,256($19) \n\ + \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + xor $3,$4,$4 # 5 cycles from $4 load \n\ + xor $6,$7,$7 # 5 cycles from $7 load \n\ + xor $1,$2,$2 # 4 cycles from $2 load \n\ + \n\ + xor $4,$5,$5 # 5 cycles from $5 load \n\ + xor $7,$20,$20 # 4 cycles from $20 load \n\ + stq $2,40($17) \n\ + subq $16,1,$16 \n\ + \n\ + stq $5,48($17) \n\ + addq $19,64,$19 \n\ + stq $20,56($17) \n\ + addq $18,64,$18 \n\ + \n\ + addq $17,64,$17 \n\ + bgt $16,3b \n\ + ret \n\ + .end xor_alpha_prefetch_3 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_prefetch_4 \n\ +xor_alpha_prefetch_4: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + \n\ + ldq $31, 0($17) \n\ + ldq $31, 0($18) \n\ + ldq $31, 0($19) \n\ + ldq $31, 0($20) \n\ + \n\ + ldq $31, 64($17) \n\ + ldq $31, 64($18) \n\ + ldq $31, 64($19) \n\ + ldq $31, 64($20) \n\ + \n\ + ldq $31, 128($17) \n\ + ldq $31, 128($18) \n\ + ldq $31, 128($19) \n\ + ldq $31, 128($20) \n\ + \n\ + ldq $31, 192($17) \n\ + ldq $31, 192($18) \n\ + ldq $31, 192($19) \n\ + ldq $31, 192($20) \n\ + .align 4 \n\ +4: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,0($20) \n\ + \n\ + ldq $4,8($17) \n\ + ldq $5,8($18) \n\ + ldq $6,8($19) \n\ + ldq $7,8($20) \n\ + \n\ + ldq $21,16($17) \n\ + ldq $22,16($18) \n\ + ldq $23,16($19) \n\ + ldq $24,16($20) \n\ + \n\ + ldq $25,24($17) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + ldq $27,24($18) \n\ + xor $2,$3,$3 # 6 cycles from $3 load \n\ + \n\ + ldq $0,24($19) \n\ + xor $1,$3,$3 \n\ + ldq $1,24($20) \n\ + xor $4,$5,$5 # 7 cycles from $5 load \n\ + \n\ + stq $3,0($17) \n\ + xor $6,$7,$7 \n\ + xor $21,$22,$22 # 7 cycles from $22 load \n\ + xor $5,$7,$7 \n\ + \n\ + stq $7,8($17) \n\ + xor $23,$24,$24 # 7 cycles from $24 load \n\ + ldq $2,32($17) \n\ + xor $22,$24,$24 \n\ + \n\ + ldq $3,32($18) \n\ + ldq $4,32($19) \n\ + ldq $5,32($20) \n\ + xor $25,$27,$27 # 8 cycles from $27 load \n\ + \n\ + ldq $6,40($17) \n\ + ldq $7,40($18) \n\ + ldq $21,40($19) \n\ + ldq $22,40($20) \n\ + \n\ + stq $24,16($17) \n\ + xor $0,$1,$1 # 9 cycles from $1 load \n\ + xor $2,$3,$3 # 5 cycles from $3 load \n\ + xor $27,$1,$1 \n\ + \n\ + stq $1,24($17) \n\ + xor $4,$5,$5 # 5 cycles from $5 load \n\ + ldq $23,48($17) \n\ + xor $3,$5,$5 \n\ + \n\ + ldq $24,48($18) \n\ + ldq $25,48($19) \n\ + ldq $27,48($20) \n\ + ldq $0,56($17) \n\ + \n\ + ldq $1,56($18) \n\ + ldq $2,56($19) \n\ + ldq $3,56($20) \n\ + xor $6,$7,$7 # 8 cycles from $6 load \n\ + \n\ + ldq $31,256($17) \n\ + xor $21,$22,$22 # 8 cycles from $22 load \n\ + ldq $31,256($18) \n\ + xor $7,$22,$22 \n\ + \n\ + ldq $31,256($19) \n\ + xor $23,$24,$24 # 6 cycles from $24 load \n\ + ldq $31,256($20) \n\ + xor $25,$27,$27 # 6 cycles from $27 load \n\ + \n\ + stq $5,32($17) \n\ + xor $24,$27,$27 \n\ + xor $0,$1,$1 # 7 cycles from $1 load \n\ + xor $2,$3,$3 # 6 cycles from $3 load \n\ + \n\ + stq $22,40($17) \n\ + xor $1,$3,$3 \n\ + stq $27,48($17) \n\ + subq $16,1,$16 \n\ + \n\ + stq $3,56($17) \n\ + addq $20,64,$20 \n\ + addq $19,64,$19 \n\ + addq $18,64,$18 \n\ + \n\ + addq $17,64,$17 \n\ + bgt $16,4b \n\ + ret \n\ + .end xor_alpha_prefetch_4 \n\ + \n\ + .align 3 \n\ + .ent xor_alpha_prefetch_5 \n\ +xor_alpha_prefetch_5: \n\ + .prologue 0 \n\ + srl $16, 6, $16 \n\ + \n\ + ldq $31, 0($17) \n\ + ldq $31, 0($18) \n\ + ldq $31, 0($19) \n\ + ldq $31, 0($20) \n\ + ldq $31, 0($21) \n\ + \n\ + ldq $31, 64($17) \n\ + ldq $31, 64($18) \n\ + ldq $31, 64($19) \n\ + ldq $31, 64($20) \n\ + ldq $31, 64($21) \n\ + \n\ + ldq $31, 128($17) \n\ + ldq $31, 128($18) \n\ + ldq $31, 128($19) \n\ + ldq $31, 128($20) \n\ + ldq $31, 128($21) \n\ + \n\ + ldq $31, 192($17) \n\ + ldq $31, 192($18) \n\ + ldq $31, 192($19) \n\ + ldq $31, 192($20) \n\ + ldq $31, 192($21) \n\ + .align 4 \n\ +5: \n\ + ldq $0,0($17) \n\ + ldq $1,0($18) \n\ + ldq $2,0($19) \n\ + ldq $3,0($20) \n\ + \n\ + ldq $4,0($21) \n\ + ldq $5,8($17) \n\ + ldq $6,8($18) \n\ + ldq $7,8($19) \n\ + \n\ + ldq $22,8($20) \n\ + ldq $23,8($21) \n\ + ldq $24,16($17) \n\ + ldq $25,16($18) \n\ + \n\ + ldq $27,16($19) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + ldq $28,16($20) \n\ + xor $2,$3,$3 # 6 cycles from $3 load \n\ + \n\ + ldq $0,16($21) \n\ + xor $1,$3,$3 \n\ + ldq $1,24($17) \n\ + xor $3,$4,$4 # 7 cycles from $4 load \n\ + \n\ + stq $4,0($17) \n\ + xor $5,$6,$6 # 7 cycles from $6 load \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + xor $6,$23,$23 # 7 cycles from $23 load \n\ + \n\ + ldq $2,24($18) \n\ + xor $22,$23,$23 \n\ + ldq $3,24($19) \n\ + xor $24,$25,$25 # 8 cycles from $25 load \n\ + \n\ + stq $23,8($17) \n\ + xor $25,$27,$27 # 8 cycles from $27 load \n\ + ldq $4,24($20) \n\ + xor $28,$0,$0 # 7 cycles from $0 load \n\ + \n\ + ldq $5,24($21) \n\ + xor $27,$0,$0 \n\ + ldq $6,32($17) \n\ + ldq $7,32($18) \n\ + \n\ + stq $0,16($17) \n\ + xor $1,$2,$2 # 6 cycles from $2 load \n\ + ldq $22,32($19) \n\ + xor $3,$4,$4 # 4 cycles from $4 load \n\ + \n\ + ldq $23,32($20) \n\ + xor $2,$4,$4 \n\ + ldq $24,32($21) \n\ + ldq $25,40($17) \n\ + \n\ + ldq $27,40($18) \n\ + ldq $28,40($19) \n\ + ldq $0,40($20) \n\ + xor $4,$5,$5 # 7 cycles from $5 load \n\ + \n\ + stq $5,24($17) \n\ + xor $6,$7,$7 # 7 cycles from $7 load \n\ + ldq $1,40($21) \n\ + ldq $2,48($17) \n\ + \n\ + ldq $3,48($18) \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + ldq $4,48($19) \n\ + xor $23,$24,$24 # 6 cycles from $24 load \n\ + \n\ + ldq $5,48($20) \n\ + xor $22,$24,$24 \n\ + ldq $6,48($21) \n\ + xor $25,$27,$27 # 7 cycles from $27 load \n\ + \n\ + stq $24,32($17) \n\ + xor $27,$28,$28 # 8 cycles from $28 load \n\ + ldq $7,56($17) \n\ + xor $0,$1,$1 # 6 cycles from $1 load \n\ + \n\ + ldq $22,56($18) \n\ + ldq $23,56($19) \n\ + ldq $24,56($20) \n\ + ldq $25,56($21) \n\ + \n\ + ldq $31,256($17) \n\ + xor $28,$1,$1 \n\ + ldq $31,256($18) \n\ + xor $2,$3,$3 # 9 cycles from $3 load \n\ + \n\ + ldq $31,256($19) \n\ + xor $3,$4,$4 # 9 cycles from $4 load \n\ + ldq $31,256($20) \n\ + xor $5,$6,$6 # 8 cycles from $6 load \n\ + \n\ + stq $1,40($17) \n\ + xor $4,$6,$6 \n\ + xor $7,$22,$22 # 7 cycles from $22 load \n\ + xor $23,$24,$24 # 6 cycles from $24 load \n\ + \n\ + stq $6,48($17) \n\ + xor $22,$24,$24 \n\ + ldq $31,256($21) \n\ + xor $24,$25,$25 # 8 cycles from $25 load \n\ + \n\ + stq $25,56($17) \n\ + subq $16,1,$16 \n\ + addq $21,64,$21 \n\ + addq $20,64,$20 \n\ + \n\ + addq $19,64,$19 \n\ + addq $18,64,$18 \n\ + addq $17,64,$17 \n\ + bgt $16,5b \n\ + \n\ + ret \n\ + .end xor_alpha_prefetch_5 \n\ +"); + +static struct xor_block_template xor_block_alpha = { + .name = "alpha", + .do_2 = xor_alpha_2, + .do_3 = xor_alpha_3, + .do_4 = xor_alpha_4, + .do_5 = xor_alpha_5, +}; + +static struct xor_block_template xor_block_alpha_prefetch = { + .name = "alpha prefetch", + .do_2 = xor_alpha_prefetch_2, + .do_3 = xor_alpha_prefetch_3, + .do_4 = xor_alpha_prefetch_4, + .do_5 = xor_alpha_prefetch_5, +}; + +/* For grins, also test the generic routines. */ +#include + +#undef XOR_TRY_TEMPLATES +#define XOR_TRY_TEMPLATES \ + do { \ + xor_speed(&xor_block_8regs); \ + xor_speed(&xor_block_32regs); \ + xor_speed(&xor_block_alpha); \ + xor_speed(&xor_block_alpha_prefetch); \ + } while (0) + +/* Force the use of alpha_prefetch if EV6, as it is significantly + faster in the cold cache case. */ +#define XOR_SELECT_TEMPLATE(FASTEST) \ + (implver() == IMPLVER_EV6 ? &xor_block_alpha_prefetch : FASTEST) -- cgit v1.2.3