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/m68k/fpsp040/scale.S | 370 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 370 insertions(+) create mode 100644 arch/m68k/fpsp040/scale.S (limited to 'arch/m68k/fpsp040/scale.S') diff --git a/arch/m68k/fpsp040/scale.S b/arch/m68k/fpsp040/scale.S new file mode 100644 index 000000000..04829dd4f --- /dev/null +++ b/arch/m68k/fpsp040/scale.S @@ -0,0 +1,370 @@ +| +| scale.sa 3.3 7/30/91 +| +| The entry point sSCALE computes the destination operand +| scaled by the source operand. If the absolute value of +| the source operand is (>= 2^14) an overflow or underflow +| is returned. +| +| The entry point sscale is called from do_func to emulate +| the fscale unimplemented instruction. +| +| Input: Double-extended destination operand in FPTEMP, +| double-extended source operand in ETEMP. +| +| Output: The function returns scale(X,Y) to fp0. +| +| Modifies: fp0. +| +| Algorithm: +| +| Copyright (C) Motorola, Inc. 1990 +| All Rights Reserved +| +| For details on the license for this file, please see the +| file, README, in this same directory. + +|SCALE idnt 2,1 | Motorola 040 Floating Point Software Package + + |section 8 + +#include "fpsp.h" + + |xref t_ovfl2 + |xref t_unfl + |xref round + |xref t_resdnrm + +SRC_BNDS: .short 0x3fff,0x400c + +| +| This entry point is used by the unimplemented instruction exception +| handler. +| +| +| +| FSCALE +| + .global sscale +sscale: + fmovel #0,%fpcr |clr user enabled exc + clrl %d1 + movew FPTEMP(%a6),%d1 |get dest exponent + smi L_SCR1(%a6) |use L_SCR1 to hold sign + andil #0x7fff,%d1 |strip sign + movew ETEMP(%a6),%d0 |check src bounds + andiw #0x7fff,%d0 |clr sign bit + cmp2w SRC_BNDS,%d0 + bccs src_in + cmpiw #0x400c,%d0 |test for too large + bge src_out +| +| The source input is below 1, so we check for denormalized numbers +| and set unfl. +| +src_small: + moveb DTAG(%a6),%d0 + andib #0xe0,%d0 + tstb %d0 + beqs no_denorm + st STORE_FLG(%a6) |dest already contains result + orl #unfl_mask,USER_FPSR(%a6) |set UNFL +den_done: + leal FPTEMP(%a6),%a0 + bra t_resdnrm +no_denorm: + fmovel USER_FPCR(%a6),%FPCR + fmovex FPTEMP(%a6),%fp0 |simply return dest + rts + + +| +| Source is within 2^14 range. To perform the int operation, +| move it to d0. +| +src_in: + fmovex ETEMP(%a6),%fp0 |move in src for int + fmovel #rz_mode,%fpcr |force rz for src conversion + fmovel %fp0,%d0 |int src to d0 + fmovel #0,%FPSR |clr status from above + tstw ETEMP(%a6) |check src sign + blt src_neg +| +| Source is positive. Add the src to the dest exponent. +| The result can be denormalized, if src = 0, or overflow, +| if the result of the add sets a bit in the upper word. +| +src_pos: + tstw %d1 |check for denorm + beq dst_dnrm + addl %d0,%d1 |add src to dest exp + beqs denorm |if zero, result is denorm + cmpil #0x7fff,%d1 |test for overflow + bges ovfl + tstb L_SCR1(%a6) + beqs spos_pos + orw #0x8000,%d1 +spos_pos: + movew %d1,FPTEMP(%a6) |result in FPTEMP + fmovel USER_FPCR(%a6),%FPCR + fmovex FPTEMP(%a6),%fp0 |write result to fp0 + rts +ovfl: + tstb L_SCR1(%a6) + beqs sovl_pos + orw #0x8000,%d1 +sovl_pos: + movew FPTEMP(%a6),ETEMP(%a6) |result in ETEMP + movel FPTEMP_HI(%a6),ETEMP_HI(%a6) + movel FPTEMP_LO(%a6),ETEMP_LO(%a6) + bra t_ovfl2 + +denorm: + tstb L_SCR1(%a6) + beqs den_pos + orw #0x8000,%d1 +den_pos: + tstl FPTEMP_HI(%a6) |check j bit + blts nden_exit |if set, not denorm + movew %d1,ETEMP(%a6) |input expected in ETEMP + movel FPTEMP_HI(%a6),ETEMP_HI(%a6) + movel FPTEMP_LO(%a6),ETEMP_LO(%a6) + orl #unfl_bit,USER_FPSR(%a6) |set unfl + leal ETEMP(%a6),%a0 + bra t_resdnrm +nden_exit: + movew %d1,FPTEMP(%a6) |result in FPTEMP + fmovel USER_FPCR(%a6),%FPCR + fmovex FPTEMP(%a6),%fp0 |write result to fp0 + rts + +| +| Source is negative. Add the src to the dest exponent. +| (The result exponent will be reduced). The result can be +| denormalized. +| +src_neg: + addl %d0,%d1 |add src to dest + beqs denorm |if zero, result is denorm + blts fix_dnrm |if negative, result is +| ;needing denormalization + tstb L_SCR1(%a6) + beqs sneg_pos + orw #0x8000,%d1 +sneg_pos: + movew %d1,FPTEMP(%a6) |result in FPTEMP + fmovel USER_FPCR(%a6),%FPCR + fmovex FPTEMP(%a6),%fp0 |write result to fp0 + rts + + +| +| The result exponent is below denorm value. Test for catastrophic +| underflow and force zero if true. If not, try to shift the +| mantissa right until a zero exponent exists. +| +fix_dnrm: + cmpiw #0xffc0,%d1 |lower bound for normalization + blt fix_unfl |if lower, catastrophic unfl + movew %d1,%d0 |use d0 for exp + movel %d2,-(%a7) |free d2 for norm + movel FPTEMP_HI(%a6),%d1 + movel FPTEMP_LO(%a6),%d2 + clrl L_SCR2(%a6) +fix_loop: + addw #1,%d0 |drive d0 to 0 + lsrl #1,%d1 |while shifting the + roxrl #1,%d2 |mantissa to the right + bccs no_carry + st L_SCR2(%a6) |use L_SCR2 to capture inex +no_carry: + tstw %d0 |it is finished when + blts fix_loop |d0 is zero or the mantissa + tstb L_SCR2(%a6) + beqs tst_zero + orl #unfl_inx_mask,USER_FPSR(%a6) +| ;set unfl, aunfl, ainex +| +| Test for zero. If zero, simply use fmove to return +/- zero +| to the fpu. +| +tst_zero: + clrw FPTEMP_EX(%a6) + tstb L_SCR1(%a6) |test for sign + beqs tst_con + orw #0x8000,FPTEMP_EX(%a6) |set sign bit +tst_con: + movel %d1,FPTEMP_HI(%a6) + movel %d2,FPTEMP_LO(%a6) + movel (%a7)+,%d2 + tstl %d1 + bnes not_zero + tstl FPTEMP_LO(%a6) + bnes not_zero +| +| Result is zero. Check for rounding mode to set lsb. If the +| mode is rp, and the zero is positive, return smallest denorm. +| If the mode is rm, and the zero is negative, return smallest +| negative denorm. +| + btstb #5,FPCR_MODE(%a6) |test if rm or rp + beqs no_dir + btstb #4,FPCR_MODE(%a6) |check which one + beqs zer_rm +zer_rp: + tstb L_SCR1(%a6) |check sign + bnes no_dir |if set, neg op, no inc + movel #1,FPTEMP_LO(%a6) |set lsb + bras sm_dnrm +zer_rm: + tstb L_SCR1(%a6) |check sign + beqs no_dir |if clr, neg op, no inc + movel #1,FPTEMP_LO(%a6) |set lsb + orl #neg_mask,USER_FPSR(%a6) |set N + bras sm_dnrm +no_dir: + fmovel USER_FPCR(%a6),%FPCR + fmovex FPTEMP(%a6),%fp0 |use fmove to set cc's + rts + +| +| The rounding mode changed the zero to a smallest denorm. Call +| t_resdnrm with exceptional operand in ETEMP. +| +sm_dnrm: + movel FPTEMP_EX(%a6),ETEMP_EX(%a6) + movel FPTEMP_HI(%a6),ETEMP_HI(%a6) + movel FPTEMP_LO(%a6),ETEMP_LO(%a6) + leal ETEMP(%a6),%a0 + bra t_resdnrm + +| +| Result is still denormalized. +| +not_zero: + orl #unfl_mask,USER_FPSR(%a6) |set unfl + tstb L_SCR1(%a6) |check for sign + beqs fix_exit + orl #neg_mask,USER_FPSR(%a6) |set N +fix_exit: + bras sm_dnrm + + +| +| The result has underflowed to zero. Return zero and set +| unfl, aunfl, and ainex. +| +fix_unfl: + orl #unfl_inx_mask,USER_FPSR(%a6) + btstb #5,FPCR_MODE(%a6) |test if rm or rp + beqs no_dir2 + btstb #4,FPCR_MODE(%a6) |check which one + beqs zer_rm2 +zer_rp2: + tstb L_SCR1(%a6) |check sign + bnes no_dir2 |if set, neg op, no inc + clrl FPTEMP_EX(%a6) + clrl FPTEMP_HI(%a6) + movel #1,FPTEMP_LO(%a6) |set lsb + bras sm_dnrm |return smallest denorm +zer_rm2: + tstb L_SCR1(%a6) |check sign + beqs no_dir2 |if clr, neg op, no inc + movew #0x8000,FPTEMP_EX(%a6) + clrl FPTEMP_HI(%a6) + movel #1,FPTEMP_LO(%a6) |set lsb + orl #neg_mask,USER_FPSR(%a6) |set N + bra sm_dnrm |return smallest denorm + +no_dir2: + tstb L_SCR1(%a6) + bges pos_zero +neg_zero: + clrl FP_SCR1(%a6) |clear the exceptional operand + clrl FP_SCR1+4(%a6) |for gen_except. + clrl FP_SCR1+8(%a6) + fmoves #0x80000000,%fp0 + rts +pos_zero: + clrl FP_SCR1(%a6) |clear the exceptional operand + clrl FP_SCR1+4(%a6) |for gen_except. + clrl FP_SCR1+8(%a6) + fmoves #0x00000000,%fp0 + rts + +| +| The destination is a denormalized number. It must be handled +| by first shifting the bits in the mantissa until it is normalized, +| then adding the remainder of the source to the exponent. +| +dst_dnrm: + moveml %d2/%d3,-(%a7) + movew FPTEMP_EX(%a6),%d1 + movel FPTEMP_HI(%a6),%d2 + movel FPTEMP_LO(%a6),%d3 +dst_loop: + tstl %d2 |test for normalized result + blts dst_norm |exit loop if so + tstl %d0 |otherwise, test shift count + beqs dst_fin |if zero, shifting is done + subil #1,%d0 |dec src + lsll #1,%d3 + roxll #1,%d2 + bras dst_loop +| +| Destination became normalized. Simply add the remaining +| portion of the src to the exponent. +| +dst_norm: + addw %d0,%d1 |dst is normalized; add src + tstb L_SCR1(%a6) + beqs dnrm_pos + orl #0x8000,%d1 +dnrm_pos: + movemw %d1,FPTEMP_EX(%a6) + moveml %d2,FPTEMP_HI(%a6) + moveml %d3,FPTEMP_LO(%a6) + fmovel USER_FPCR(%a6),%FPCR + fmovex FPTEMP(%a6),%fp0 + moveml (%a7)+,%d2/%d3 + rts + +| +| Destination remained denormalized. Call t_excdnrm with +| exceptional operand in ETEMP. +| +dst_fin: + tstb L_SCR1(%a6) |check for sign + beqs dst_exit + orl #neg_mask,USER_FPSR(%a6) |set N + orl #0x8000,%d1 +dst_exit: + movemw %d1,ETEMP_EX(%a6) + moveml %d2,ETEMP_HI(%a6) + moveml %d3,ETEMP_LO(%a6) + orl #unfl_mask,USER_FPSR(%a6) |set unfl + moveml (%a7)+,%d2/%d3 + leal ETEMP(%a6),%a0 + bra t_resdnrm + +| +| Source is outside of 2^14 range. Test the sign and branch +| to the appropriate exception handler. +| +src_out: + tstb L_SCR1(%a6) + beqs scro_pos + orl #0x8000,%d1 +scro_pos: + movel FPTEMP_HI(%a6),ETEMP_HI(%a6) + movel FPTEMP_LO(%a6),ETEMP_LO(%a6) + tstw ETEMP(%a6) + blts res_neg +res_pos: + movew %d1,ETEMP(%a6) |result in ETEMP + bra t_ovfl2 +res_neg: + movew %d1,ETEMP(%a6) |result in ETEMP + leal ETEMP(%a6),%a0 + bra t_unfl + |end -- cgit v1.2.3