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/x86/math-emu/div_Xsig.S | 367 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 367 insertions(+) create mode 100644 arch/x86/math-emu/div_Xsig.S (limited to 'arch/x86/math-emu/div_Xsig.S') diff --git a/arch/x86/math-emu/div_Xsig.S b/arch/x86/math-emu/div_Xsig.S new file mode 100644 index 000000000..8c270ab41 --- /dev/null +++ b/arch/x86/math-emu/div_Xsig.S @@ -0,0 +1,367 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + .file "div_Xsig.S" +/*---------------------------------------------------------------------------+ + | div_Xsig.S | + | | + | Division subroutine for 96 bit quantities | + | | + | Copyright (C) 1994,1995 | + | W. Metzenthen, 22 Parker St, Ormond, Vic 3163, | + | Australia. E-mail billm@jacobi.maths.monash.edu.au | + | | + | | + +---------------------------------------------------------------------------*/ + +/*---------------------------------------------------------------------------+ + | Divide the 96 bit quantity pointed to by a, by that pointed to by b, and | + | put the 96 bit result at the location d. | + | | + | The result may not be accurate to 96 bits. It is intended for use where | + | a result better than 64 bits is required. The result should usually be | + | good to at least 94 bits. | + | The returned result is actually divided by one half. This is done to | + | prevent overflow. | + | | + | .aaaaaaaaaaaaaa / .bbbbbbbbbbbbb -> .dddddddddddd | + | | + | void div_Xsig(Xsig *a, Xsig *b, Xsig *dest) | + | | + +---------------------------------------------------------------------------*/ + +#include "exception.h" +#include "fpu_emu.h" + + +#define XsigLL(x) (x) +#define XsigL(x) 4(x) +#define XsigH(x) 8(x) + + +#ifndef NON_REENTRANT_FPU +/* + Local storage on the stack: + Accumulator: FPU_accum_3:FPU_accum_2:FPU_accum_1:FPU_accum_0 + */ +#define FPU_accum_3 -4(%ebp) +#define FPU_accum_2 -8(%ebp) +#define FPU_accum_1 -12(%ebp) +#define FPU_accum_0 -16(%ebp) +#define FPU_result_3 -20(%ebp) +#define FPU_result_2 -24(%ebp) +#define FPU_result_1 -28(%ebp) + +#else +.data +/* + Local storage in a static area: + Accumulator: FPU_accum_3:FPU_accum_2:FPU_accum_1:FPU_accum_0 + */ + .align 4,0 +FPU_accum_3: + .long 0 +FPU_accum_2: + .long 0 +FPU_accum_1: + .long 0 +FPU_accum_0: + .long 0 +FPU_result_3: + .long 0 +FPU_result_2: + .long 0 +FPU_result_1: + .long 0 +#endif /* NON_REENTRANT_FPU */ + + +.text +SYM_FUNC_START(div_Xsig) + pushl %ebp + movl %esp,%ebp +#ifndef NON_REENTRANT_FPU + subl $28,%esp +#endif /* NON_REENTRANT_FPU */ + + pushl %esi + pushl %edi + pushl %ebx + + movl PARAM1,%esi /* pointer to num */ + movl PARAM2,%ebx /* pointer to denom */ + +#ifdef PARANOID + testl $0x80000000, XsigH(%ebx) /* Divisor */ + je L_bugged +#endif /* PARANOID */ + + +/*---------------------------------------------------------------------------+ + | Divide: Return arg1/arg2 to arg3. | + | | + | The maximum returned value is (ignoring exponents) | + | .ffffffff ffffffff | + | ------------------ = 1.ffffffff fffffffe | + | .80000000 00000000 | + | and the minimum is | + | .80000000 00000000 | + | ------------------ = .80000000 00000001 (rounded) | + | .ffffffff ffffffff | + | | + +---------------------------------------------------------------------------*/ + + /* Save extended dividend in local register */ + + /* Divide by 2 to prevent overflow */ + clc + movl XsigH(%esi),%eax + rcrl %eax + movl %eax,FPU_accum_3 + movl XsigL(%esi),%eax + rcrl %eax + movl %eax,FPU_accum_2 + movl XsigLL(%esi),%eax + rcrl %eax + movl %eax,FPU_accum_1 + movl $0,%eax + rcrl %eax + movl %eax,FPU_accum_0 + + movl FPU_accum_2,%eax /* Get the current num */ + movl FPU_accum_3,%edx + +/*----------------------------------------------------------------------*/ +/* Initialization done. + Do the first 32 bits. */ + + /* We will divide by a number which is too large */ + movl XsigH(%ebx),%ecx + addl $1,%ecx + jnc LFirst_div_not_1 + + /* here we need to divide by 100000000h, + i.e., no division at all.. */ + mov %edx,%eax + jmp LFirst_div_done + +LFirst_div_not_1: + divl %ecx /* Divide the numerator by the augmented + denom ms dw */ + +LFirst_div_done: + movl %eax,FPU_result_3 /* Put the result in the answer */ + + mull XsigH(%ebx) /* mul by the ms dw of the denom */ + + subl %eax,FPU_accum_2 /* Subtract from the num local reg */ + sbbl %edx,FPU_accum_3 + + movl FPU_result_3,%eax /* Get the result back */ + mull XsigL(%ebx) /* now mul the ls dw of the denom */ + + subl %eax,FPU_accum_1 /* Subtract from the num local reg */ + sbbl %edx,FPU_accum_2 + sbbl $0,FPU_accum_3 + je LDo_2nd_32_bits /* Must check for non-zero result here */ + +#ifdef PARANOID + jb L_bugged_1 +#endif /* PARANOID */ + + /* need to subtract another once of the denom */ + incl FPU_result_3 /* Correct the answer */ + + movl XsigL(%ebx),%eax + movl XsigH(%ebx),%edx + subl %eax,FPU_accum_1 /* Subtract from the num local reg */ + sbbl %edx,FPU_accum_2 + +#ifdef PARANOID + sbbl $0,FPU_accum_3 + jne L_bugged_1 /* Must check for non-zero result here */ +#endif /* PARANOID */ + +/*----------------------------------------------------------------------*/ +/* Half of the main problem is done, there is just a reduced numerator + to handle now. + Work with the second 32 bits, FPU_accum_0 not used from now on */ +LDo_2nd_32_bits: + movl FPU_accum_2,%edx /* get the reduced num */ + movl FPU_accum_1,%eax + + /* need to check for possible subsequent overflow */ + cmpl XsigH(%ebx),%edx + jb LDo_2nd_div + ja LPrevent_2nd_overflow + + cmpl XsigL(%ebx),%eax + jb LDo_2nd_div + +LPrevent_2nd_overflow: +/* The numerator is greater or equal, would cause overflow */ + /* prevent overflow */ + subl XsigL(%ebx),%eax + sbbl XsigH(%ebx),%edx + movl %edx,FPU_accum_2 + movl %eax,FPU_accum_1 + + incl FPU_result_3 /* Reflect the subtraction in the answer */ + +#ifdef PARANOID + je L_bugged_2 /* Can't bump the result to 1.0 */ +#endif /* PARANOID */ + +LDo_2nd_div: + cmpl $0,%ecx /* augmented denom msw */ + jnz LSecond_div_not_1 + + /* %ecx == 0, we are dividing by 1.0 */ + mov %edx,%eax + jmp LSecond_div_done + +LSecond_div_not_1: + divl %ecx /* Divide the numerator by the denom ms dw */ + +LSecond_div_done: + movl %eax,FPU_result_2 /* Put the result in the answer */ + + mull XsigH(%ebx) /* mul by the ms dw of the denom */ + + subl %eax,FPU_accum_1 /* Subtract from the num local reg */ + sbbl %edx,FPU_accum_2 + +#ifdef PARANOID + jc L_bugged_2 +#endif /* PARANOID */ + + movl FPU_result_2,%eax /* Get the result back */ + mull XsigL(%ebx) /* now mul the ls dw of the denom */ + + subl %eax,FPU_accum_0 /* Subtract from the num local reg */ + sbbl %edx,FPU_accum_1 /* Subtract from the num local reg */ + sbbl $0,FPU_accum_2 + +#ifdef PARANOID + jc L_bugged_2 +#endif /* PARANOID */ + + jz LDo_3rd_32_bits + +#ifdef PARANOID + cmpl $1,FPU_accum_2 + jne L_bugged_2 +#endif /* PARANOID */ + + /* need to subtract another once of the denom */ + movl XsigL(%ebx),%eax + movl XsigH(%ebx),%edx + subl %eax,FPU_accum_0 /* Subtract from the num local reg */ + sbbl %edx,FPU_accum_1 + sbbl $0,FPU_accum_2 + +#ifdef PARANOID + jc L_bugged_2 + jne L_bugged_2 +#endif /* PARANOID */ + + addl $1,FPU_result_2 /* Correct the answer */ + adcl $0,FPU_result_3 + +#ifdef PARANOID + jc L_bugged_2 /* Must check for non-zero result here */ +#endif /* PARANOID */ + +/*----------------------------------------------------------------------*/ +/* The division is essentially finished here, we just need to perform + tidying operations. + Deal with the 3rd 32 bits */ +LDo_3rd_32_bits: + /* We use an approximation for the third 32 bits. + To take account of the 3rd 32 bits of the divisor + (call them del), we subtract del * (a/b) */ + + movl FPU_result_3,%eax /* a/b */ + mull XsigLL(%ebx) /* del */ + + subl %edx,FPU_accum_1 + + /* A borrow indicates that the result is negative */ + jnb LTest_over + + movl XsigH(%ebx),%edx + addl %edx,FPU_accum_1 + + subl $1,FPU_result_2 /* Adjust the answer */ + sbbl $0,FPU_result_3 + + /* The above addition might not have been enough, check again. */ + movl FPU_accum_1,%edx /* get the reduced num */ + cmpl XsigH(%ebx),%edx /* denom */ + jb LDo_3rd_div + + movl XsigH(%ebx),%edx + addl %edx,FPU_accum_1 + + subl $1,FPU_result_2 /* Adjust the answer */ + sbbl $0,FPU_result_3 + jmp LDo_3rd_div + +LTest_over: + movl FPU_accum_1,%edx /* get the reduced num */ + + /* need to check for possible subsequent overflow */ + cmpl XsigH(%ebx),%edx /* denom */ + jb LDo_3rd_div + + /* prevent overflow */ + subl XsigH(%ebx),%edx + movl %edx,FPU_accum_1 + + addl $1,FPU_result_2 /* Reflect the subtraction in the answer */ + adcl $0,FPU_result_3 + +LDo_3rd_div: + movl FPU_accum_0,%eax + movl FPU_accum_1,%edx + divl XsigH(%ebx) + + movl %eax,FPU_result_1 /* Rough estimate of third word */ + + movl PARAM3,%esi /* pointer to answer */ + + movl FPU_result_1,%eax + movl %eax,XsigLL(%esi) + movl FPU_result_2,%eax + movl %eax,XsigL(%esi) + movl FPU_result_3,%eax + movl %eax,XsigH(%esi) + +L_exit: + popl %ebx + popl %edi + popl %esi + + leave + RET + + +#ifdef PARANOID +/* The logic is wrong if we got here */ +L_bugged: + pushl EX_INTERNAL|0x240 + call EXCEPTION + pop %ebx + jmp L_exit + +L_bugged_1: + pushl EX_INTERNAL|0x241 + call EXCEPTION + pop %ebx + jmp L_exit + +L_bugged_2: + pushl EX_INTERNAL|0x242 + call EXCEPTION + pop %ebx + jmp L_exit +#endif /* PARANOID */ +SYM_FUNC_END(div_Xsig) -- cgit v1.2.3