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/sh/math-emu/Makefile | 2 + arch/sh/math-emu/math.c | 506 ++++++++++++++++++++++++++++++++++++++++++++ arch/sh/math-emu/sfp-util.h | 73 +++++++ 3 files changed, 581 insertions(+) create mode 100644 arch/sh/math-emu/Makefile create mode 100644 arch/sh/math-emu/math.c create mode 100644 arch/sh/math-emu/sfp-util.h (limited to 'arch/sh/math-emu') diff --git a/arch/sh/math-emu/Makefile b/arch/sh/math-emu/Makefile new file mode 100644 index 000000000..ba06e42c4 --- /dev/null +++ b/arch/sh/math-emu/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-y := math.o diff --git a/arch/sh/math-emu/math.c b/arch/sh/math-emu/math.c new file mode 100644 index 000000000..cdaef6501 --- /dev/null +++ b/arch/sh/math-emu/math.c @@ -0,0 +1,506 @@ +/* + * arch/sh/math-emu/math.c + * + * Copyright (C) 2006 Takashi YOSHII + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include "sfp-util.h" +#include +#include +#include + +#define FPUL (fregs->fpul) +#define FPSCR (fregs->fpscr) +#define FPSCR_RM (FPSCR&3) +#define FPSCR_DN ((FPSCR>>18)&1) +#define FPSCR_PR ((FPSCR>>19)&1) +#define FPSCR_SZ ((FPSCR>>20)&1) +#define FPSCR_FR ((FPSCR>>21)&1) +#define FPSCR_MASK 0x003fffffUL + +#define BANK(n) (n^(FPSCR_FR?16:0)) +#define FR ((unsigned long*)(fregs->fp_regs)) +#define FR0 (FR[BANK(0)]) +#define FRn (FR[BANK(n)]) +#define FRm (FR[BANK(m)]) +#define DR ((unsigned long long*)(fregs->fp_regs)) +#define DRn (DR[BANK(n)/2]) +#define DRm (DR[BANK(m)/2]) + +#define XREG(n) (n^16) +#define XFn (FR[BANK(XREG(n))]) +#define XFm (FR[BANK(XREG(m))]) +#define XDn (DR[BANK(XREG(n))/2]) +#define XDm (DR[BANK(XREG(m))/2]) + +#define R0 (regs->regs[0]) +#define Rn (regs->regs[n]) +#define Rm (regs->regs[m]) + +#define MWRITE(d,a) ({if(put_user(d, (typeof (d) __user *)a)) return -EFAULT;}) +#define MREAD(d,a) ({if(get_user(d, (typeof (d) __user *)a)) return -EFAULT;}) + +#define PACK_S(r,f) FP_PACK_SP(&r,f) +#define UNPACK_S(f,r) FP_UNPACK_SP(f,&r) +#define PACK_D(r,f) \ + {u32 t[2]; FP_PACK_DP(t,f); ((u32*)&r)[0]=t[1]; ((u32*)&r)[1]=t[0];} +#define UNPACK_D(f,r) \ + {u32 t[2]; t[0]=((u32*)&r)[1]; t[1]=((u32*)&r)[0]; FP_UNPACK_DP(f,t);} + +// 2 args instructions. +#define BOTH_PRmn(op,x) \ + FP_DECL_EX; if(FPSCR_PR) op(D,x,DRm,DRn); else op(S,x,FRm,FRn); + +#define CMP_X(SZ,R,M,N) do{ \ + FP_DECL_##SZ(Fm); FP_DECL_##SZ(Fn); \ + UNPACK_##SZ(Fm, M); UNPACK_##SZ(Fn, N); \ + FP_CMP_##SZ(R, Fn, Fm, 2); }while(0) +#define EQ_X(SZ,R,M,N) do{ \ + FP_DECL_##SZ(Fm); FP_DECL_##SZ(Fn); \ + UNPACK_##SZ(Fm, M); UNPACK_##SZ(Fn, N); \ + FP_CMP_EQ_##SZ(R, Fn, Fm); }while(0) +#define CMP(OP) ({ int r; BOTH_PRmn(OP##_X,r); r; }) + +static int +fcmp_gt(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, int n) +{ + if (CMP(CMP) > 0) + regs->sr |= 1; + else + regs->sr &= ~1; + + return 0; +} + +static int +fcmp_eq(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, int n) +{ + if (CMP(CMP /*EQ*/) == 0) + regs->sr |= 1; + else + regs->sr &= ~1; + return 0; +} + +#define ARITH_X(SZ,OP,M,N) do{ \ + FP_DECL_##SZ(Fm); FP_DECL_##SZ(Fn); FP_DECL_##SZ(Fr); \ + UNPACK_##SZ(Fm, M); UNPACK_##SZ(Fn, N); \ + FP_##OP##_##SZ(Fr, Fn, Fm); \ + PACK_##SZ(N, Fr); }while(0) + +static int +fadd(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, int n) +{ + BOTH_PRmn(ARITH_X, ADD); + return 0; +} + +static int +fsub(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, int n) +{ + BOTH_PRmn(ARITH_X, SUB); + return 0; +} + +static int +fmul(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, int n) +{ + BOTH_PRmn(ARITH_X, MUL); + return 0; +} + +static int +fdiv(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, int n) +{ + BOTH_PRmn(ARITH_X, DIV); + return 0; +} + +static int +fmac(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, int n) +{ + FP_DECL_EX; + FP_DECL_S(Fr); + FP_DECL_S(Ft); + FP_DECL_S(F0); + FP_DECL_S(Fm); + FP_DECL_S(Fn); + UNPACK_S(F0, FR0); + UNPACK_S(Fm, FRm); + UNPACK_S(Fn, FRn); + FP_MUL_S(Ft, Fm, F0); + FP_ADD_S(Fr, Fn, Ft); + PACK_S(FRn, Fr); + return 0; +} + +// to process fmov's extension (odd n for DR access XD). +#define FMOV_EXT(x) if(x&1) x+=16-1 + +static int +fmov_idx_reg(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, + int n) +{ + if (FPSCR_SZ) { + FMOV_EXT(n); + MREAD(FRn, Rm + R0 + 4); + n++; + MREAD(FRn, Rm + R0); + } else { + MREAD(FRn, Rm + R0); + } + + return 0; +} + +static int +fmov_mem_reg(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, + int n) +{ + if (FPSCR_SZ) { + FMOV_EXT(n); + MREAD(FRn, Rm + 4); + n++; + MREAD(FRn, Rm); + } else { + MREAD(FRn, Rm); + } + + return 0; +} + +static int +fmov_inc_reg(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, + int n) +{ + if (FPSCR_SZ) { + FMOV_EXT(n); + MREAD(FRn, Rm + 4); + n++; + MREAD(FRn, Rm); + Rm += 8; + } else { + MREAD(FRn, Rm); + Rm += 4; + } + + return 0; +} + +static int +fmov_reg_idx(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, + int n) +{ + if (FPSCR_SZ) { + FMOV_EXT(m); + MWRITE(FRm, Rn + R0 + 4); + m++; + MWRITE(FRm, Rn + R0); + } else { + MWRITE(FRm, Rn + R0); + } + + return 0; +} + +static int +fmov_reg_mem(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, + int n) +{ + if (FPSCR_SZ) { + FMOV_EXT(m); + MWRITE(FRm, Rn + 4); + m++; + MWRITE(FRm, Rn); + } else { + MWRITE(FRm, Rn); + } + + return 0; +} + +static int +fmov_reg_dec(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, + int n) +{ + if (FPSCR_SZ) { + FMOV_EXT(m); + Rn -= 8; + MWRITE(FRm, Rn + 4); + m++; + MWRITE(FRm, Rn); + } else { + Rn -= 4; + MWRITE(FRm, Rn); + } + + return 0; +} + +static int +fmov_reg_reg(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, + int n) +{ + if (FPSCR_SZ) { + FMOV_EXT(m); + FMOV_EXT(n); + DRn = DRm; + } else { + FRn = FRm; + } + + return 0; +} + +static int +fnop_mn(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m, int n) +{ + return -EINVAL; +} + +// 1 arg instructions. +#define NOTYETn(i) static int i(struct sh_fpu_soft_struct *fregs, int n) \ + { printk( #i " not yet done.\n"); return 0; } + +NOTYETn(ftrv) +NOTYETn(fsqrt) +NOTYETn(fipr) +NOTYETn(fsca) +NOTYETn(fsrra) + +#define EMU_FLOAT_X(SZ,N) do { \ + FP_DECL_##SZ(Fn); \ + FP_FROM_INT_##SZ(Fn, FPUL, 32, int); \ + PACK_##SZ(N, Fn); }while(0) +static int ffloat(struct sh_fpu_soft_struct *fregs, int n) +{ + FP_DECL_EX; + + if (FPSCR_PR) + EMU_FLOAT_X(D, DRn); + else + EMU_FLOAT_X(S, FRn); + + return 0; +} + +#define EMU_FTRC_X(SZ,N) do { \ + FP_DECL_##SZ(Fn); \ + UNPACK_##SZ(Fn, N); \ + FP_TO_INT_##SZ(FPUL, Fn, 32, 1); }while(0) +static int ftrc(struct sh_fpu_soft_struct *fregs, int n) +{ + FP_DECL_EX; + + if (FPSCR_PR) + EMU_FTRC_X(D, DRn); + else + EMU_FTRC_X(S, FRn); + + return 0; +} + +static int fcnvsd(struct sh_fpu_soft_struct *fregs, int n) +{ + FP_DECL_EX; + FP_DECL_S(Fn); + FP_DECL_D(Fr); + UNPACK_S(Fn, FPUL); + FP_CONV(D, S, 2, 1, Fr, Fn); + PACK_D(DRn, Fr); + return 0; +} + +static int fcnvds(struct sh_fpu_soft_struct *fregs, int n) +{ + FP_DECL_EX; + FP_DECL_D(Fn); + FP_DECL_S(Fr); + UNPACK_D(Fn, DRn); + FP_CONV(S, D, 1, 2, Fr, Fn); + PACK_S(FPUL, Fr); + return 0; +} + +static int fxchg(struct sh_fpu_soft_struct *fregs, int flag) +{ + FPSCR ^= flag; + return 0; +} + +static int fsts(struct sh_fpu_soft_struct *fregs, int n) +{ + FRn = FPUL; + return 0; +} + +static int flds(struct sh_fpu_soft_struct *fregs, int n) +{ + FPUL = FRn; + return 0; +} + +static int fneg(struct sh_fpu_soft_struct *fregs, int n) +{ + FRn ^= (1 << (_FP_W_TYPE_SIZE - 1)); + return 0; +} + +static int fabs(struct sh_fpu_soft_struct *fregs, int n) +{ + FRn &= ~(1 << (_FP_W_TYPE_SIZE - 1)); + return 0; +} + +static int fld0(struct sh_fpu_soft_struct *fregs, int n) +{ + FRn = 0; + return 0; +} + +static int fld1(struct sh_fpu_soft_struct *fregs, int n) +{ + FRn = (_FP_EXPBIAS_S << (_FP_FRACBITS_S - 1)); + return 0; +} + +static int fnop_n(struct sh_fpu_soft_struct *fregs, int n) +{ + return -EINVAL; +} + +/// Instruction decoders. + +static int id_fxfd(struct sh_fpu_soft_struct *, int); +static int id_fnxd(struct sh_fpu_soft_struct *, struct pt_regs *, int, int); + +static int (*fnxd[])(struct sh_fpu_soft_struct *, int) = { + fsts, flds, ffloat, ftrc, fneg, fabs, fsqrt, fsrra, + fld0, fld1, fcnvsd, fcnvds, fnop_n, fnop_n, fipr, id_fxfd +}; + +static int (*fnmx[])(struct sh_fpu_soft_struct *, struct pt_regs *, int, int) = { + fadd, fsub, fmul, fdiv, fcmp_eq, fcmp_gt, fmov_idx_reg, fmov_reg_idx, + fmov_mem_reg, fmov_inc_reg, fmov_reg_mem, fmov_reg_dec, + fmov_reg_reg, id_fnxd, fmac, fnop_mn}; + +static int id_fxfd(struct sh_fpu_soft_struct *fregs, int x) +{ + const int flag[] = { FPSCR_SZ, FPSCR_PR, FPSCR_FR, 0 }; + switch (x & 3) { + case 3: + fxchg(fregs, flag[x >> 2]); + break; + case 1: + ftrv(fregs, x - 1); + break; + default: + fsca(fregs, x); + } + return 0; +} + +static int +id_fnxd(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int x, int n) +{ + return (fnxd[x])(fregs, n); +} + +static int +id_fnmx(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, u16 code) +{ + int n = (code >> 8) & 0xf, m = (code >> 4) & 0xf, x = code & 0xf; + return (fnmx[x])(fregs, regs, m, n); +} + +static int +id_sys(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, u16 code) +{ + int n = ((code >> 8) & 0xf); + unsigned long *reg = (code & 0x0010) ? &FPUL : &FPSCR; + + switch (code & 0xf0ff) { + case 0x005a: + case 0x006a: + Rn = *reg; + break; + case 0x405a: + case 0x406a: + *reg = Rn; + break; + case 0x4052: + case 0x4062: + Rn -= 4; + MWRITE(*reg, Rn); + break; + case 0x4056: + case 0x4066: + MREAD(*reg, Rn); + Rn += 4; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int fpu_emulate(u16 code, struct sh_fpu_soft_struct *fregs, struct pt_regs *regs) +{ + if ((code & 0xf000) == 0xf000) + return id_fnmx(fregs, regs, code); + else + return id_sys(fregs, regs, code); +} + +/** + * fpu_init - Initialize FPU registers + * @fpu: Pointer to software emulated FPU registers. + */ +static void fpu_init(struct sh_fpu_soft_struct *fpu) +{ + int i; + + fpu->fpscr = FPSCR_INIT; + fpu->fpul = 0; + + for (i = 0; i < 16; i++) { + fpu->fp_regs[i] = 0; + fpu->xfp_regs[i]= 0; + } +} + +/** + * do_fpu_inst - Handle reserved instructions for FPU emulation + * @inst: instruction code. + * @regs: registers on stack. + */ +int do_fpu_inst(unsigned short inst, struct pt_regs *regs) +{ + struct task_struct *tsk = current; + struct sh_fpu_soft_struct *fpu = &(tsk->thread.xstate->softfpu); + + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0); + + if (!(task_thread_info(tsk)->status & TS_USEDFPU)) { + /* initialize once. */ + fpu_init(fpu); + task_thread_info(tsk)->status |= TS_USEDFPU; + } + + return fpu_emulate(inst, fpu, regs); +} diff --git a/arch/sh/math-emu/sfp-util.h b/arch/sh/math-emu/sfp-util.h new file mode 100644 index 000000000..784f54134 --- /dev/null +++ b/arch/sh/math-emu/sfp-util.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * These are copied from glibc/stdlib/longlong.h + */ + +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ + do { \ + UWtype __x; \ + __x = (al) + (bl); \ + (sh) = (ah) + (bh) + (__x < (al)); \ + (sl) = __x; \ + } while (0) + +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ + do { \ + UWtype __x; \ + __x = (al) - (bl); \ + (sh) = (ah) - (bh) - (__x > (al)); \ + (sl) = __x; \ + } while (0) + +#define umul_ppmm(w1, w0, u, v) \ + __asm__ ("dmulu.l %2,%3\n\tsts macl,%1\n\tsts mach,%0" \ + : "=r" ((u32)(w1)), "=r" ((u32)(w0)) \ + : "r" ((u32)(u)), "r" ((u32)(v)) \ + : "macl", "mach") + +#define __ll_B ((UWtype) 1 << (W_TYPE_SIZE / 2)) +#define __ll_lowpart(t) ((UWtype) (t) & (__ll_B - 1)) +#define __ll_highpart(t) ((UWtype) (t) >> (W_TYPE_SIZE / 2)) + +#define udiv_qrnnd(q, r, n1, n0, d) \ + do { \ + UWtype __d1, __d0, __q1, __q0; \ + UWtype __r1, __r0, __m; \ + __d1 = __ll_highpart (d); \ + __d0 = __ll_lowpart (d); \ + \ + __r1 = (n1) % __d1; \ + __q1 = (n1) / __d1; \ + __m = (UWtype) __q1 * __d0; \ + __r1 = __r1 * __ll_B | __ll_highpart (n0); \ + if (__r1 < __m) \ + { \ + __q1--, __r1 += (d); \ + if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */\ + if (__r1 < __m) \ + __q1--, __r1 += (d); \ + } \ + __r1 -= __m; \ + \ + __r0 = __r1 % __d1; \ + __q0 = __r1 / __d1; \ + __m = (UWtype) __q0 * __d0; \ + __r0 = __r0 * __ll_B | __ll_lowpart (n0); \ + if (__r0 < __m) \ + { \ + __q0--, __r0 += (d); \ + if (__r0 >= (d)) \ + if (__r0 < __m) \ + __q0--, __r0 += (d); \ + } \ + __r0 -= __m; \ + \ + (q) = (UWtype) __q1 * __ll_B | __q0; \ + (r) = __r0; \ + } while (0) + +#define abort() return 0 + +#define __BYTE_ORDER __LITTLE_ENDIAN + + -- cgit v1.2.3