aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/math-emu/poly_l2.c
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/x86/math-emu/poly_l2.c
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/x86/math-emu/poly_l2.c')
-rw-r--r--arch/x86/math-emu/poly_l2.c245
1 files changed, 245 insertions, 0 deletions
diff --git a/arch/x86/math-emu/poly_l2.c b/arch/x86/math-emu/poly_l2.c
new file mode 100644
index 000000000..98b6949bb
--- /dev/null
+++ b/arch/x86/math-emu/poly_l2.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0
+/*---------------------------------------------------------------------------+
+ | poly_l2.c |
+ | |
+ | Compute the base 2 log of a FPU_REG, using a polynomial approximation. |
+ | |
+ | Copyright (C) 1992,1993,1994,1997 |
+ | W. Metzenthen, 22 Parker St, Ormond, Vic 3163, Australia |
+ | E-mail billm@suburbia.net |
+ | |
+ | |
+ +---------------------------------------------------------------------------*/
+
+#include "exception.h"
+#include "reg_constant.h"
+#include "fpu_emu.h"
+#include "fpu_system.h"
+#include "control_w.h"
+#include "poly.h"
+
+static void log2_kernel(FPU_REG const *arg, u_char argsign,
+ Xsig * accum_result, long int *expon);
+
+/*--- poly_l2() -------------------------------------------------------------+
+ | Base 2 logarithm by a polynomial approximation. |
+ +---------------------------------------------------------------------------*/
+void poly_l2(FPU_REG *st0_ptr, FPU_REG *st1_ptr, u_char st1_sign)
+{
+ long int exponent, expon, expon_expon;
+ Xsig accumulator, expon_accum, yaccum;
+ u_char sign, argsign;
+ FPU_REG x;
+ int tag;
+
+ exponent = exponent16(st0_ptr);
+
+ /* From st0_ptr, make a number > sqrt(2)/2 and < sqrt(2) */
+ if (st0_ptr->sigh > (unsigned)0xb504f334) {
+ /* Treat as sqrt(2)/2 < st0_ptr < 1 */
+ significand(&x) = -significand(st0_ptr);
+ setexponent16(&x, -1);
+ exponent++;
+ argsign = SIGN_NEG;
+ } else {
+ /* Treat as 1 <= st0_ptr < sqrt(2) */
+ x.sigh = st0_ptr->sigh - 0x80000000;
+ x.sigl = st0_ptr->sigl;
+ setexponent16(&x, 0);
+ argsign = SIGN_POS;
+ }
+ tag = FPU_normalize_nuo(&x);
+
+ if (tag == TAG_Zero) {
+ expon = 0;
+ accumulator.msw = accumulator.midw = accumulator.lsw = 0;
+ } else {
+ log2_kernel(&x, argsign, &accumulator, &expon);
+ }
+
+ if (exponent < 0) {
+ sign = SIGN_NEG;
+ exponent = -exponent;
+ } else
+ sign = SIGN_POS;
+ expon_accum.msw = exponent;
+ expon_accum.midw = expon_accum.lsw = 0;
+ if (exponent) {
+ expon_expon = 31 + norm_Xsig(&expon_accum);
+ shr_Xsig(&accumulator, expon_expon - expon);
+
+ if (sign ^ argsign)
+ negate_Xsig(&accumulator);
+ add_Xsig_Xsig(&accumulator, &expon_accum);
+ } else {
+ expon_expon = expon;
+ sign = argsign;
+ }
+
+ yaccum.lsw = 0;
+ XSIG_LL(yaccum) = significand(st1_ptr);
+ mul_Xsig_Xsig(&accumulator, &yaccum);
+
+ expon_expon += round_Xsig(&accumulator);
+
+ if (accumulator.msw == 0) {
+ FPU_copy_to_reg1(&CONST_Z, TAG_Zero);
+ return;
+ }
+
+ significand(st1_ptr) = XSIG_LL(accumulator);
+ setexponent16(st1_ptr, expon_expon + exponent16(st1_ptr) + 1);
+
+ tag = FPU_round(st1_ptr, 1, 0, FULL_PRECISION, sign ^ st1_sign);
+ FPU_settagi(1, tag);
+
+ set_precision_flag_up(); /* 80486 appears to always do this */
+
+ return;
+
+}
+
+/*--- poly_l2p1() -----------------------------------------------------------+
+ | Base 2 logarithm by a polynomial approximation. |
+ | log2(x+1) |
+ +---------------------------------------------------------------------------*/
+int poly_l2p1(u_char sign0, u_char sign1,
+ FPU_REG * st0_ptr, FPU_REG * st1_ptr, FPU_REG * dest)
+{
+ u_char tag;
+ long int exponent;
+ Xsig accumulator, yaccum;
+
+ if (exponent16(st0_ptr) < 0) {
+ log2_kernel(st0_ptr, sign0, &accumulator, &exponent);
+
+ yaccum.lsw = 0;
+ XSIG_LL(yaccum) = significand(st1_ptr);
+ mul_Xsig_Xsig(&accumulator, &yaccum);
+
+ exponent += round_Xsig(&accumulator);
+
+ exponent += exponent16(st1_ptr) + 1;
+ if (exponent < EXP_WAY_UNDER)
+ exponent = EXP_WAY_UNDER;
+
+ significand(dest) = XSIG_LL(accumulator);
+ setexponent16(dest, exponent);
+
+ tag = FPU_round(dest, 1, 0, FULL_PRECISION, sign0 ^ sign1);
+ FPU_settagi(1, tag);
+
+ if (tag == TAG_Valid)
+ set_precision_flag_up(); /* 80486 appears to always do this */
+ } else {
+ /* The magnitude of st0_ptr is far too large. */
+
+ if (sign0 != SIGN_POS) {
+ /* Trying to get the log of a negative number. */
+#ifdef PECULIAR_486 /* Stupid 80486 doesn't worry about log(negative). */
+ changesign(st1_ptr);
+#else
+ if (arith_invalid(1) < 0)
+ return 1;
+#endif /* PECULIAR_486 */
+ }
+
+ /* 80486 appears to do this */
+ if (sign0 == SIGN_NEG)
+ set_precision_flag_down();
+ else
+ set_precision_flag_up();
+ }
+
+ if (exponent(dest) <= EXP_UNDER)
+ EXCEPTION(EX_Underflow);
+
+ return 0;
+
+}
+
+#undef HIPOWER
+#define HIPOWER 10
+static const unsigned long long logterms[HIPOWER] = {
+ 0x2a8eca5705fc2ef0LL,
+ 0xf6384ee1d01febceLL,
+ 0x093bb62877cdf642LL,
+ 0x006985d8a9ec439bLL,
+ 0x0005212c4f55a9c8LL,
+ 0x00004326a16927f0LL,
+ 0x0000038d1d80a0e7LL,
+ 0x0000003141cc80c6LL,
+ 0x00000002b1668c9fLL,
+ 0x000000002c7a46aaLL
+};
+
+static const unsigned long leadterm = 0xb8000000;
+
+/*--- log2_kernel() ---------------------------------------------------------+
+ | Base 2 logarithm by a polynomial approximation. |
+ | log2(x+1) |
+ +---------------------------------------------------------------------------*/
+static void log2_kernel(FPU_REG const *arg, u_char argsign, Xsig *accum_result,
+ long int *expon)
+{
+ long int exponent, adj;
+ unsigned long long Xsq;
+ Xsig accumulator, Numer, Denom, argSignif, arg_signif;
+
+ exponent = exponent16(arg);
+ Numer.lsw = Denom.lsw = 0;
+ XSIG_LL(Numer) = XSIG_LL(Denom) = significand(arg);
+ if (argsign == SIGN_POS) {
+ shr_Xsig(&Denom, 2 - (1 + exponent));
+ Denom.msw |= 0x80000000;
+ div_Xsig(&Numer, &Denom, &argSignif);
+ } else {
+ shr_Xsig(&Denom, 1 - (1 + exponent));
+ negate_Xsig(&Denom);
+ if (Denom.msw & 0x80000000) {
+ div_Xsig(&Numer, &Denom, &argSignif);
+ exponent++;
+ } else {
+ /* Denom must be 1.0 */
+ argSignif.lsw = Numer.lsw;
+ argSignif.midw = Numer.midw;
+ argSignif.msw = Numer.msw;
+ }
+ }
+
+#ifndef PECULIAR_486
+ /* Should check here that |local_arg| is within the valid range */
+ if (exponent >= -2) {
+ if ((exponent > -2) || (argSignif.msw > (unsigned)0xafb0ccc0)) {
+ /* The argument is too large */
+ }
+ }
+#endif /* PECULIAR_486 */
+
+ arg_signif.lsw = argSignif.lsw;
+ XSIG_LL(arg_signif) = XSIG_LL(argSignif);
+ adj = norm_Xsig(&argSignif);
+ accumulator.lsw = argSignif.lsw;
+ XSIG_LL(accumulator) = XSIG_LL(argSignif);
+ mul_Xsig_Xsig(&accumulator, &accumulator);
+ shr_Xsig(&accumulator, 2 * (-1 - (1 + exponent + adj)));
+ Xsq = XSIG_LL(accumulator);
+ if (accumulator.lsw & 0x80000000)
+ Xsq++;
+
+ accumulator.msw = accumulator.midw = accumulator.lsw = 0;
+ /* Do the basic fixed point polynomial evaluation */
+ polynomial_Xsig(&accumulator, &Xsq, logterms, HIPOWER - 1);
+
+ mul_Xsig_Xsig(&accumulator, &argSignif);
+ shr_Xsig(&accumulator, 6 - adj);
+
+ mul32_Xsig(&arg_signif, leadterm);
+ add_two_Xsig(&accumulator, &arg_signif, &exponent);
+
+ *expon = exponent + 1;
+ accum_result->lsw = accumulator.lsw;
+ accum_result->midw = accumulator.midw;
+ accum_result->msw = accumulator.msw;
+
+}