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/sparc/include/asm/checksum_32.h | 210 +++++++++++++++++++++++++++++++++++ 1 file changed, 210 insertions(+) create mode 100644 arch/sparc/include/asm/checksum_32.h (limited to 'arch/sparc/include/asm/checksum_32.h') diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h new file mode 100644 index 000000000..ce11e0ad8 --- /dev/null +++ b/arch/sparc/include/asm/checksum_32.h @@ -0,0 +1,210 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SPARC_CHECKSUM_H +#define __SPARC_CHECKSUM_H + +/* checksum.h: IP/UDP/TCP checksum routines on the Sparc. + * + * Copyright(C) 1995 Linus Torvalds + * Copyright(C) 1995 Miguel de Icaza + * Copyright(C) 1996 David S. Miller + * Copyright(C) 1996 Eddie C. Dost + * Copyright(C) 1997 Jakub Jelinek + * + * derived from: + * Alpha checksum c-code + * ix86 inline assembly + * RFC1071 Computing the Internet Checksum + */ + +#include +#include + +/* computes the checksum of a memory block at buff, length len, + * and adds in "sum" (32-bit) + * + * returns a 32-bit number suitable for feeding into itself + * or csum_tcpudp_magic + * + * this function must be called with even lengths, except + * for the last fragment, which may be odd + * + * it's best to have buff aligned on a 32-bit boundary + */ +__wsum csum_partial(const void *buff, int len, __wsum sum); + +/* the same as csum_partial, but copies from fs:src while it + * checksums + * + * here even more important to align src and dst on a 32-bit (or even + * better 64-bit) boundary + */ + +unsigned int __csum_partial_copy_sparc_generic (const unsigned char *, unsigned char *); + +static inline __wsum +csum_partial_copy_nocheck(const void *src, void *dst, int len) +{ + register unsigned int ret asm("o0") = (unsigned int)src; + register char *d asm("o1") = dst; + register int l asm("g1") = len; + + __asm__ __volatile__ ( + "call __csum_partial_copy_sparc_generic\n\t" + " mov -1, %%g7\n" + : "=&r" (ret), "=&r" (d), "=&r" (l) + : "0" (ret), "1" (d), "2" (l) + : "o2", "o3", "o4", "o5", "o7", + "g2", "g3", "g4", "g5", "g7", + "memory", "cc"); + return (__force __wsum)ret; +} + +static inline __wsum +csum_and_copy_from_user(const void __user *src, void *dst, int len) +{ + if (unlikely(!access_ok(src, len))) + return 0; + return csum_partial_copy_nocheck((__force void *)src, dst, len); +} + +static inline __wsum +csum_and_copy_to_user(const void *src, void __user *dst, int len) +{ + if (!access_ok(dst, len)) + return 0; + return csum_partial_copy_nocheck(src, (__force void *)dst, len); +} + +/* ihl is always 5 or greater, almost always is 5, and iph is word aligned + * the majority of the time. + */ +static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) +{ + __sum16 sum; + + /* Note: We must read %2 before we touch %0 for the first time, + * because GCC can legitimately use the same register for + * both operands. + */ + __asm__ __volatile__("sub\t%2, 4, %%g4\n\t" + "ld\t[%1 + 0x00], %0\n\t" + "ld\t[%1 + 0x04], %%g2\n\t" + "ld\t[%1 + 0x08], %%g3\n\t" + "addcc\t%%g2, %0, %0\n\t" + "addxcc\t%%g3, %0, %0\n\t" + "ld\t[%1 + 0x0c], %%g2\n\t" + "ld\t[%1 + 0x10], %%g3\n\t" + "addxcc\t%%g2, %0, %0\n\t" + "addx\t%0, %%g0, %0\n" + "1:\taddcc\t%%g3, %0, %0\n\t" + "add\t%1, 4, %1\n\t" + "addxcc\t%0, %%g0, %0\n\t" + "subcc\t%%g4, 1, %%g4\n\t" + "be,a\t2f\n\t" + "sll\t%0, 16, %%g2\n\t" + "b\t1b\n\t" + "ld\t[%1 + 0x10], %%g3\n" + "2:\taddcc\t%0, %%g2, %%g2\n\t" + "srl\t%%g2, 16, %0\n\t" + "addx\t%0, %%g0, %0\n\t" + "xnor\t%%g0, %0, %0" + : "=r" (sum), "=&r" (iph) + : "r" (ihl), "1" (iph) + : "g2", "g3", "g4", "cc", "memory"); + return sum; +} + +/* Fold a partial checksum without adding pseudo headers. */ +static inline __sum16 csum_fold(__wsum sum) +{ + unsigned int tmp; + + __asm__ __volatile__("addcc\t%0, %1, %1\n\t" + "srl\t%1, 16, %1\n\t" + "addx\t%1, %%g0, %1\n\t" + "xnor\t%%g0, %1, %0" + : "=&r" (sum), "=r" (tmp) + : "0" (sum), "1" ((__force u32)sum<<16) + : "cc"); + return (__force __sum16)sum; +} + +static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, + __u32 len, __u8 proto, + __wsum sum) +{ + __asm__ __volatile__("addcc\t%1, %0, %0\n\t" + "addxcc\t%2, %0, %0\n\t" + "addxcc\t%3, %0, %0\n\t" + "addx\t%0, %%g0, %0\n\t" + : "=r" (sum), "=r" (saddr) + : "r" (daddr), "r" (proto + len), "0" (sum), + "1" (saddr) + : "cc"); + return sum; +} + +/* + * computes the checksum of the TCP/UDP pseudo-header + * returns a 16-bit checksum, already complemented + */ +static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, + __u32 len, __u8 proto, + __wsum sum) +{ + return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum)); +} + +#define _HAVE_ARCH_IPV6_CSUM + +static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum sum) +{ + __asm__ __volatile__ ( + "addcc %3, %4, %%g4\n\t" + "addxcc %5, %%g4, %%g4\n\t" + "ld [%2 + 0x0c], %%g2\n\t" + "ld [%2 + 0x08], %%g3\n\t" + "addxcc %%g2, %%g4, %%g4\n\t" + "ld [%2 + 0x04], %%g2\n\t" + "addxcc %%g3, %%g4, %%g4\n\t" + "ld [%2 + 0x00], %%g3\n\t" + "addxcc %%g2, %%g4, %%g4\n\t" + "ld [%1 + 0x0c], %%g2\n\t" + "addxcc %%g3, %%g4, %%g4\n\t" + "ld [%1 + 0x08], %%g3\n\t" + "addxcc %%g2, %%g4, %%g4\n\t" + "ld [%1 + 0x04], %%g2\n\t" + "addxcc %%g3, %%g4, %%g4\n\t" + "ld [%1 + 0x00], %%g3\n\t" + "addxcc %%g2, %%g4, %%g4\n\t" + "addxcc %%g3, %%g4, %0\n\t" + "addx 0, %0, %0\n" + : "=&r" (sum) + : "r" (saddr), "r" (daddr), + "r"(htonl(len)), "r"(htonl(proto)), "r"(sum) + : "g2", "g3", "g4", "cc"); + + return csum_fold(sum); +} + +/* this routine is used for miscellaneous IP-like checksums, mainly in icmp.c */ +static inline __sum16 ip_compute_csum(const void *buff, int len) +{ + return csum_fold(csum_partial(buff, len, 0)); +} + +#define HAVE_ARCH_CSUM_ADD +static inline __wsum csum_add(__wsum csum, __wsum addend) +{ + __asm__ __volatile__( + "addcc %0, %1, %0\n" + "addx %0, %%g0, %0" + : "=r" (csum) + : "r" (addend), "0" (csum)); + + return csum; +} + +#endif /* !(__SPARC_CHECKSUM_H) */ -- cgit v1.2.3