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(). ... --- drivers/clocksource/timer-clint.c | 244 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 244 insertions(+) create mode 100644 drivers/clocksource/timer-clint.c (limited to 'drivers/clocksource/timer-clint.c') diff --git a/drivers/clocksource/timer-clint.c b/drivers/clocksource/timer-clint.c new file mode 100644 index 000000000..6cfe2ab73 --- /dev/null +++ b/drivers/clocksource/timer-clint.c @@ -0,0 +1,244 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * + * Most of the M-mode (i.e. NoMMU) RISC-V systems usually have a + * CLINT MMIO timer device. + */ + +#define pr_fmt(fmt) "clint: " fmt +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifndef CONFIG_RISCV_M_MODE +#include +#endif + +#define CLINT_IPI_OFF 0 +#define CLINT_TIMER_CMP_OFF 0x4000 +#define CLINT_TIMER_VAL_OFF 0xbff8 + +/* CLINT manages IPI and Timer for RISC-V M-mode */ +static u32 __iomem *clint_ipi_base; +static u64 __iomem *clint_timer_cmp; +static u64 __iomem *clint_timer_val; +static unsigned long clint_timer_freq; +static unsigned int clint_timer_irq; + +#ifdef CONFIG_RISCV_M_MODE +u64 __iomem *clint_time_val; +EXPORT_SYMBOL(clint_time_val); +#endif + +static void clint_send_ipi(const struct cpumask *target) +{ + unsigned int cpu; + + for_each_cpu(cpu, target) + writel(1, clint_ipi_base + cpuid_to_hartid_map(cpu)); +} + +static void clint_clear_ipi(void) +{ + writel(0, clint_ipi_base + cpuid_to_hartid_map(smp_processor_id())); +} + +static struct riscv_ipi_ops clint_ipi_ops = { + .ipi_inject = clint_send_ipi, + .ipi_clear = clint_clear_ipi, +}; + +#ifdef CONFIG_64BIT +#define clint_get_cycles() readq_relaxed(clint_timer_val) +#else +#define clint_get_cycles() readl_relaxed(clint_timer_val) +#define clint_get_cycles_hi() readl_relaxed(((u32 *)clint_timer_val) + 1) +#endif + +#ifdef CONFIG_64BIT +static u64 notrace clint_get_cycles64(void) +{ + return clint_get_cycles(); +} +#else /* CONFIG_64BIT */ +static u64 notrace clint_get_cycles64(void) +{ + u32 hi, lo; + + do { + hi = clint_get_cycles_hi(); + lo = clint_get_cycles(); + } while (hi != clint_get_cycles_hi()); + + return ((u64)hi << 32) | lo; +} +#endif /* CONFIG_64BIT */ + +static u64 clint_rdtime(struct clocksource *cs) +{ + return clint_get_cycles64(); +} + +static struct clocksource clint_clocksource = { + .name = "clint_clocksource", + .rating = 300, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .read = clint_rdtime, +}; + +static int clint_clock_next_event(unsigned long delta, + struct clock_event_device *ce) +{ + void __iomem *r = clint_timer_cmp + + cpuid_to_hartid_map(smp_processor_id()); + + csr_set(CSR_IE, IE_TIE); + writeq_relaxed(clint_get_cycles64() + delta, r); + return 0; +} + +static DEFINE_PER_CPU(struct clock_event_device, clint_clock_event) = { + .name = "clint_clockevent", + .features = CLOCK_EVT_FEAT_ONESHOT, + .rating = 100, + .set_next_event = clint_clock_next_event, +}; + +static int clint_timer_starting_cpu(unsigned int cpu) +{ + struct clock_event_device *ce = per_cpu_ptr(&clint_clock_event, cpu); + + ce->cpumask = cpumask_of(cpu); + clockevents_config_and_register(ce, clint_timer_freq, 100, 0x7fffffff); + + enable_percpu_irq(clint_timer_irq, + irq_get_trigger_type(clint_timer_irq)); + return 0; +} + +static int clint_timer_dying_cpu(unsigned int cpu) +{ + disable_percpu_irq(clint_timer_irq); + return 0; +} + +static irqreturn_t clint_timer_interrupt(int irq, void *dev_id) +{ + struct clock_event_device *evdev = this_cpu_ptr(&clint_clock_event); + + csr_clear(CSR_IE, IE_TIE); + evdev->event_handler(evdev); + + return IRQ_HANDLED; +} + +static int __init clint_timer_init_dt(struct device_node *np) +{ + int rc; + u32 i, nr_irqs; + void __iomem *base; + struct of_phandle_args oirq; + + /* + * Ensure that CLINT device interrupts are either RV_IRQ_TIMER or + * RV_IRQ_SOFT. If it's anything else then we ignore the device. + */ + nr_irqs = of_irq_count(np); + for (i = 0; i < nr_irqs; i++) { + if (of_irq_parse_one(np, i, &oirq)) { + pr_err("%pOFP: failed to parse irq %d.\n", np, i); + continue; + } + + if ((oirq.args_count != 1) || + (oirq.args[0] != RV_IRQ_TIMER && + oirq.args[0] != RV_IRQ_SOFT)) { + pr_err("%pOFP: invalid irq %d (hwirq %d)\n", + np, i, oirq.args[0]); + return -ENODEV; + } + + /* Find parent irq domain and map timer irq */ + if (!clint_timer_irq && + oirq.args[0] == RV_IRQ_TIMER && + irq_find_host(oirq.np)) + clint_timer_irq = irq_of_parse_and_map(np, i); + } + + /* If CLINT timer irq not found then fail */ + if (!clint_timer_irq) { + pr_err("%pOFP: timer irq not found\n", np); + return -ENODEV; + } + + base = of_iomap(np, 0); + if (!base) { + pr_err("%pOFP: could not map registers\n", np); + return -ENODEV; + } + + clint_ipi_base = base + CLINT_IPI_OFF; + clint_timer_cmp = base + CLINT_TIMER_CMP_OFF; + clint_timer_val = base + CLINT_TIMER_VAL_OFF; + clint_timer_freq = riscv_timebase; + +#ifdef CONFIG_RISCV_M_MODE + /* + * Yes, that's an odd naming scheme. time_val is public, but hopefully + * will die in favor of something cleaner. + */ + clint_time_val = clint_timer_val; +#endif + + pr_info("%pOFP: timer running at %ld Hz\n", np, clint_timer_freq); + + rc = clocksource_register_hz(&clint_clocksource, clint_timer_freq); + if (rc) { + pr_err("%pOFP: clocksource register failed [%d]\n", np, rc); + goto fail_iounmap; + } + + sched_clock_register(clint_get_cycles64, 64, clint_timer_freq); + + rc = request_percpu_irq(clint_timer_irq, clint_timer_interrupt, + "clint-timer", &clint_clock_event); + if (rc) { + pr_err("registering percpu irq failed [%d]\n", rc); + goto fail_iounmap; + } + + rc = cpuhp_setup_state(CPUHP_AP_CLINT_TIMER_STARTING, + "clockevents/clint/timer:starting", + clint_timer_starting_cpu, + clint_timer_dying_cpu); + if (rc) { + pr_err("%pOFP: cpuhp setup state failed [%d]\n", np, rc); + goto fail_free_irq; + } + + riscv_set_ipi_ops(&clint_ipi_ops); + clint_clear_ipi(); + + return 0; + +fail_free_irq: + free_irq(clint_timer_irq, &clint_clock_event); +fail_iounmap: + iounmap(base); + return rc; +} + +TIMER_OF_DECLARE(clint_timer, "riscv,clint0", clint_timer_init_dt); +TIMER_OF_DECLARE(clint_timer1, "sifive,clint0", clint_timer_init_dt); -- cgit v1.2.3