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/powerpc/kernel/vecemu.c | 351 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 351 insertions(+) create mode 100644 arch/powerpc/kernel/vecemu.c (limited to 'arch/powerpc/kernel/vecemu.c') diff --git a/arch/powerpc/kernel/vecemu.c b/arch/powerpc/kernel/vecemu.c new file mode 100644 index 000000000..fd9432875 --- /dev/null +++ b/arch/powerpc/kernel/vecemu.c @@ -0,0 +1,351 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Routines to emulate some Altivec/VMX instructions, specifically + * those that can trap when given denormalized operands in Java mode. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +/* Functions in vector.S */ +extern void vaddfp(vector128 *dst, vector128 *a, vector128 *b); +extern void vsubfp(vector128 *dst, vector128 *a, vector128 *b); +extern void vmaddfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c); +extern void vnmsubfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c); +extern void vrefp(vector128 *dst, vector128 *src); +extern void vrsqrtefp(vector128 *dst, vector128 *src); +extern void vexptep(vector128 *dst, vector128 *src); + +static unsigned int exp2s[8] = { + 0x800000, + 0x8b95c2, + 0x9837f0, + 0xa5fed7, + 0xb504f3, + 0xc5672a, + 0xd744fd, + 0xeac0c7 +}; + +/* + * Computes an estimate of 2^x. The `s' argument is the 32-bit + * single-precision floating-point representation of x. + */ +static unsigned int eexp2(unsigned int s) +{ + int exp, pwr; + unsigned int mant, frac; + + /* extract exponent field from input */ + exp = ((s >> 23) & 0xff) - 127; + if (exp > 7) { + /* check for NaN input */ + if (exp == 128 && (s & 0x7fffff) != 0) + return s | 0x400000; /* return QNaN */ + /* 2^-big = 0, 2^+big = +Inf */ + return (s & 0x80000000)? 0: 0x7f800000; /* 0 or +Inf */ + } + if (exp < -23) + return 0x3f800000; /* 1.0 */ + + /* convert to fixed point integer in 9.23 representation */ + pwr = (s & 0x7fffff) | 0x800000; + if (exp > 0) + pwr <<= exp; + else + pwr >>= -exp; + if (s & 0x80000000) + pwr = -pwr; + + /* extract integer part, which becomes exponent part of result */ + exp = (pwr >> 23) + 126; + if (exp >= 254) + return 0x7f800000; + if (exp < -23) + return 0; + + /* table lookup on top 3 bits of fraction to get mantissa */ + mant = exp2s[(pwr >> 20) & 7]; + + /* linear interpolation using remaining 20 bits of fraction */ + asm("mulhwu %0,%1,%2" : "=r" (frac) + : "r" (pwr << 12), "r" (0x172b83ff)); + asm("mulhwu %0,%1,%2" : "=r" (frac) : "r" (frac), "r" (mant)); + mant += frac; + + if (exp >= 0) + return mant + (exp << 23); + + /* denormalized result */ + exp = -exp; + mant += 1 << (exp - 1); + return mant >> exp; +} + +/* + * Computes an estimate of log_2(x). The `s' argument is the 32-bit + * single-precision floating-point representation of x. + */ +static unsigned int elog2(unsigned int s) +{ + int exp, mant, lz, frac; + + exp = s & 0x7f800000; + mant = s & 0x7fffff; + if (exp == 0x7f800000) { /* Inf or NaN */ + if (mant != 0) + s |= 0x400000; /* turn NaN into QNaN */ + return s; + } + if ((exp | mant) == 0) /* +0 or -0 */ + return 0xff800000; /* return -Inf */ + + if (exp == 0) { + /* denormalized */ + asm("cntlzw %0,%1" : "=r" (lz) : "r" (mant)); + mant <<= lz - 8; + exp = (-118 - lz) << 23; + } else { + mant |= 0x800000; + exp -= 127 << 23; + } + + if (mant >= 0xb504f3) { /* 2^0.5 * 2^23 */ + exp |= 0x400000; /* 0.5 * 2^23 */ + asm("mulhwu %0,%1,%2" : "=r" (mant) + : "r" (mant), "r" (0xb504f334)); /* 2^-0.5 * 2^32 */ + } + if (mant >= 0x9837f0) { /* 2^0.25 * 2^23 */ + exp |= 0x200000; /* 0.25 * 2^23 */ + asm("mulhwu %0,%1,%2" : "=r" (mant) + : "r" (mant), "r" (0xd744fccb)); /* 2^-0.25 * 2^32 */ + } + if (mant >= 0x8b95c2) { /* 2^0.125 * 2^23 */ + exp |= 0x100000; /* 0.125 * 2^23 */ + asm("mulhwu %0,%1,%2" : "=r" (mant) + : "r" (mant), "r" (0xeac0c6e8)); /* 2^-0.125 * 2^32 */ + } + if (mant > 0x800000) { /* 1.0 * 2^23 */ + /* calculate (mant - 1) * 1.381097463 */ + /* 1.381097463 == 0.125 / (2^0.125 - 1) */ + asm("mulhwu %0,%1,%2" : "=r" (frac) + : "r" ((mant - 0x800000) << 1), "r" (0xb0c7cd3a)); + exp += frac; + } + s = exp & 0x80000000; + if (exp != 0) { + if (s) + exp = -exp; + asm("cntlzw %0,%1" : "=r" (lz) : "r" (exp)); + lz = 8 - lz; + if (lz > 0) + exp >>= lz; + else if (lz < 0) + exp <<= -lz; + s += ((lz + 126) << 23) + exp; + } + return s; +} + +#define VSCR_SAT 1 + +static int ctsxs(unsigned int x, int scale, unsigned int *vscrp) +{ + int exp, mant; + + exp = (x >> 23) & 0xff; + mant = x & 0x7fffff; + if (exp == 255 && mant != 0) + return 0; /* NaN -> 0 */ + exp = exp - 127 + scale; + if (exp < 0) + return 0; /* round towards zero */ + if (exp >= 31) { + /* saturate, unless the result would be -2^31 */ + if (x + (scale << 23) != 0xcf000000) + *vscrp |= VSCR_SAT; + return (x & 0x80000000)? 0x80000000: 0x7fffffff; + } + mant |= 0x800000; + mant = (mant << 7) >> (30 - exp); + return (x & 0x80000000)? -mant: mant; +} + +static unsigned int ctuxs(unsigned int x, int scale, unsigned int *vscrp) +{ + int exp; + unsigned int mant; + + exp = (x >> 23) & 0xff; + mant = x & 0x7fffff; + if (exp == 255 && mant != 0) + return 0; /* NaN -> 0 */ + exp = exp - 127 + scale; + if (exp < 0) + return 0; /* round towards zero */ + if (x & 0x80000000) { + /* negative => saturate to 0 */ + *vscrp |= VSCR_SAT; + return 0; + } + if (exp >= 32) { + /* saturate */ + *vscrp |= VSCR_SAT; + return 0xffffffff; + } + mant |= 0x800000; + mant = (mant << 8) >> (31 - exp); + return mant; +} + +/* Round to floating integer, towards 0 */ +static unsigned int rfiz(unsigned int x) +{ + int exp; + + exp = ((x >> 23) & 0xff) - 127; + if (exp == 128 && (x & 0x7fffff) != 0) + return x | 0x400000; /* NaN -> make it a QNaN */ + if (exp >= 23) + return x; /* it's an integer already (or Inf) */ + if (exp < 0) + return x & 0x80000000; /* |x| < 1.0 rounds to 0 */ + return x & ~(0x7fffff >> exp); +} + +/* Round to floating integer, towards +/- Inf */ +static unsigned int rfii(unsigned int x) +{ + int exp, mask; + + exp = ((x >> 23) & 0xff) - 127; + if (exp == 128 && (x & 0x7fffff) != 0) + return x | 0x400000; /* NaN -> make it a QNaN */ + if (exp >= 23) + return x; /* it's an integer already (or Inf) */ + if ((x & 0x7fffffff) == 0) + return x; /* +/-0 -> +/-0 */ + if (exp < 0) + /* 0 < |x| < 1.0 rounds to +/- 1.0 */ + return (x & 0x80000000) | 0x3f800000; + mask = 0x7fffff >> exp; + /* mantissa overflows into exponent - that's OK, + it can't overflow into the sign bit */ + return (x + mask) & ~mask; +} + +/* Round to floating integer, to nearest */ +static unsigned int rfin(unsigned int x) +{ + int exp, half; + + exp = ((x >> 23) & 0xff) - 127; + if (exp == 128 && (x & 0x7fffff) != 0) + return x | 0x400000; /* NaN -> make it a QNaN */ + if (exp >= 23) + return x; /* it's an integer already (or Inf) */ + if (exp < -1) + return x & 0x80000000; /* |x| < 0.5 -> +/-0 */ + if (exp == -1) + /* 0.5 <= |x| < 1.0 rounds to +/- 1.0 */ + return (x & 0x80000000) | 0x3f800000; + half = 0x400000 >> exp; + /* add 0.5 to the magnitude and chop off the fraction bits */ + return (x + half) & ~(0x7fffff >> exp); +} + +int emulate_altivec(struct pt_regs *regs) +{ + ppc_inst_t instr; + unsigned int i, word; + unsigned int va, vb, vc, vd; + vector128 *vrs; + + if (get_user_instr(instr, (void __user *)regs->nip)) + return -EFAULT; + + word = ppc_inst_val(instr); + if (ppc_inst_primary_opcode(instr) != 4) + return -EINVAL; /* not an altivec instruction */ + vd = (word >> 21) & 0x1f; + va = (word >> 16) & 0x1f; + vb = (word >> 11) & 0x1f; + vc = (word >> 6) & 0x1f; + + vrs = current->thread.vr_state.vr; + switch (word & 0x3f) { + case 10: + switch (vc) { + case 0: /* vaddfp */ + vaddfp(&vrs[vd], &vrs[va], &vrs[vb]); + break; + case 1: /* vsubfp */ + vsubfp(&vrs[vd], &vrs[va], &vrs[vb]); + break; + case 4: /* vrefp */ + vrefp(&vrs[vd], &vrs[vb]); + break; + case 5: /* vrsqrtefp */ + vrsqrtefp(&vrs[vd], &vrs[vb]); + break; + case 6: /* vexptefp */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = eexp2(vrs[vb].u[i]); + break; + case 7: /* vlogefp */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = elog2(vrs[vb].u[i]); + break; + case 8: /* vrfin */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = rfin(vrs[vb].u[i]); + break; + case 9: /* vrfiz */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = rfiz(vrs[vb].u[i]); + break; + case 10: /* vrfip */ + for (i = 0; i < 4; ++i) { + u32 x = vrs[vb].u[i]; + x = (x & 0x80000000)? rfiz(x): rfii(x); + vrs[vd].u[i] = x; + } + break; + case 11: /* vrfim */ + for (i = 0; i < 4; ++i) { + u32 x = vrs[vb].u[i]; + x = (x & 0x80000000)? rfii(x): rfiz(x); + vrs[vd].u[i] = x; + } + break; + case 14: /* vctuxs */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = ctuxs(vrs[vb].u[i], va, + ¤t->thread.vr_state.vscr.u[3]); + break; + case 15: /* vctsxs */ + for (i = 0; i < 4; ++i) + vrs[vd].u[i] = ctsxs(vrs[vb].u[i], va, + ¤t->thread.vr_state.vscr.u[3]); + break; + default: + return -EINVAL; + } + break; + case 46: /* vmaddfp */ + vmaddfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]); + break; + case 47: /* vnmsubfp */ + vnmsubfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]); + break; + default: + return -EINVAL; + } + + return 0; +} -- cgit v1.2.3