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/include/asm/exception-64e.h | 172 +++++++++++++++++++++++++++++++ 1 file changed, 172 insertions(+) create mode 100644 arch/powerpc/include/asm/exception-64e.h (limited to 'arch/powerpc/include/asm/exception-64e.h') diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h new file mode 100644 index 000000000..b1ef1e92c --- /dev/null +++ b/arch/powerpc/include/asm/exception-64e.h @@ -0,0 +1,172 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Definitions for use by exception code on Book3-E + * + * Copyright (C) 2008 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp. + */ +#ifndef _ASM_POWERPC_EXCEPTION_64E_H +#define _ASM_POWERPC_EXCEPTION_64E_H + +/* + * SPRGs usage an other considerations... + * + * Since TLB miss and other standard exceptions can be interrupted by + * critical exceptions which can themselves be interrupted by machine + * checks, and since the two later can themselves cause a TLB miss when + * hitting the linear mapping for the kernel stacks, we need to be a bit + * creative on how we use SPRGs. + * + * The base idea is that we have one SRPG reserved for critical and one + * for machine check interrupts. Those are used to save a GPR that can + * then be used to get the PACA, and store as much context as we need + * to save in there. That includes saving the SPRGs used by the TLB miss + * handler for linear mapping misses and the associated SRR0/1 due to + * the above re-entrancy issue. + * + * So here's the current usage pattern. It's done regardless of which + * SPRGs are user-readable though, thus we might have to change some of + * this later. In order to do that more easily, we use special constants + * for naming them + * + * WARNING: Some of these SPRGs are user readable. We need to do something + * about it as some point by making sure they can't be used to leak kernel + * critical data + */ + +#define PACA_EXGDBELL PACA_EXGEN + +/* We are out of SPRGs so we save some things in the PACA. The normal + * exception frame is smaller than the CRIT or MC one though + */ +#define EX_R1 (0 * 8) +#define EX_CR (1 * 8) +#define EX_R10 (2 * 8) +#define EX_R11 (3 * 8) +#define EX_R14 (4 * 8) +#define EX_R15 (5 * 8) + +/* + * The TLB miss exception uses different slots. + * + * The bolted variant uses only the first six fields, + * which in combination with pgd and kernel_pgd fits in + * one 64-byte cache line. + */ + +#define EX_TLB_R10 ( 0 * 8) +#define EX_TLB_R11 ( 1 * 8) +#define EX_TLB_R14 ( 2 * 8) +#define EX_TLB_R15 ( 3 * 8) +#define EX_TLB_R16 ( 4 * 8) +#define EX_TLB_CR ( 5 * 8) +#define EX_TLB_R12 ( 6 * 8) +#define EX_TLB_R13 ( 7 * 8) +#define EX_TLB_DEAR ( 8 * 8) /* Level 0 and 2 only */ +#define EX_TLB_ESR ( 9 * 8) /* Level 0 and 2 only */ +#define EX_TLB_SRR0 (10 * 8) +#define EX_TLB_SRR1 (11 * 8) +#define EX_TLB_R7 (12 * 8) +#define EX_TLB_SIZE (13 * 8) + +#define START_EXCEPTION(label) \ + .globl exc_##label##_book3e; \ +exc_##label##_book3e: + +/* TLB miss exception prolog + * + * This prolog handles re-entrancy (up to 3 levels supported in the PACA + * though we currently don't test for overflow). It provides you with a + * re-entrancy safe working space of r10...r16 and CR with r12 being used + * as the exception area pointer in the PACA for that level of re-entrancy + * and r13 containing the PACA pointer. + * + * SRR0 and SRR1 are saved, but DEAR and ESR are not, since they don't apply + * as-is for instruction exceptions. It's up to the actual exception code + * to save them as well if required. + */ +#define TLB_MISS_PROLOG \ + mtspr SPRN_SPRG_TLB_SCRATCH,r12; \ + mfspr r12,SPRN_SPRG_TLB_EXFRAME; \ + std r10,EX_TLB_R10(r12); \ + mfcr r10; \ + std r11,EX_TLB_R11(r12); \ + mfspr r11,SPRN_SPRG_TLB_SCRATCH; \ + std r13,EX_TLB_R13(r12); \ + mfspr r13,SPRN_SPRG_PACA; \ + std r14,EX_TLB_R14(r12); \ + addi r14,r12,EX_TLB_SIZE; \ + std r15,EX_TLB_R15(r12); \ + mfspr r15,SPRN_SRR1; \ + std r16,EX_TLB_R16(r12); \ + mfspr r16,SPRN_SRR0; \ + std r10,EX_TLB_CR(r12); \ + std r11,EX_TLB_R12(r12); \ + mtspr SPRN_SPRG_TLB_EXFRAME,r14; \ + std r15,EX_TLB_SRR1(r12); \ + std r16,EX_TLB_SRR0(r12); + +/* And these are the matching epilogs that restores things + * + * There are 3 epilogs: + * + * - SUCCESS : Unwinds one level + * - ERROR : restore from level 0 and reset + * - ERROR_SPECIAL : restore from current level and reset + * + * Normal errors use ERROR, that is, they restore the initial fault context + * and trigger a fault. However, there is a special case for linear mapping + * errors. Those should basically never happen, but if they do happen, we + * want the error to point out the context that did that linear mapping + * fault, not the initial level 0 (basically, we got a bogus PGF or something + * like that). For userland errors on the linear mapping, there is no + * difference since those are always level 0 anyway + */ + +#define TLB_MISS_RESTORE(freg) \ + ld r14,EX_TLB_CR(r12); \ + ld r10,EX_TLB_R10(r12); \ + ld r15,EX_TLB_SRR0(r12); \ + ld r16,EX_TLB_SRR1(r12); \ + mtspr SPRN_SPRG_TLB_EXFRAME,freg; \ + ld r11,EX_TLB_R11(r12); \ + mtcr r14; \ + ld r13,EX_TLB_R13(r12); \ + ld r14,EX_TLB_R14(r12); \ + mtspr SPRN_SRR0,r15; \ + ld r15,EX_TLB_R15(r12); \ + mtspr SPRN_SRR1,r16; \ + ld r16,EX_TLB_R16(r12); \ + ld r12,EX_TLB_R12(r12); \ + +#define TLB_MISS_EPILOG_SUCCESS \ + TLB_MISS_RESTORE(r12) + +#define TLB_MISS_EPILOG_ERROR \ + addi r12,r13,PACA_EXTLB; \ + TLB_MISS_RESTORE(r12) + +#define TLB_MISS_EPILOG_ERROR_SPECIAL \ + addi r11,r13,PACA_EXTLB; \ + TLB_MISS_RESTORE(r11) + +#ifndef __ASSEMBLY__ +extern unsigned int interrupt_base_book3e; +#endif + +#define SET_IVOR(vector_number, vector_offset) \ + LOAD_REG_ADDR(r3,interrupt_base_book3e);\ + ori r3,r3,vector_offset@l; \ + mtspr SPRN_IVOR##vector_number,r3; +/* + * powerpc relies on return from interrupt/syscall being context synchronising + * (which rfi is) to support ARCH_HAS_MEMBARRIER_SYNC_CORE without additional + * synchronisation instructions. + */ +#define RFI_TO_KERNEL \ + rfi + +#define RFI_TO_USER \ + rfi + +#endif /* _ASM_POWERPC_EXCEPTION_64E_H */ + -- cgit v1.2.3