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-davinci.c | 366 ++++++++++++++++++++++++++++++++++++ 1 file changed, 366 insertions(+) create mode 100644 drivers/clocksource/timer-davinci.c (limited to 'drivers/clocksource/timer-davinci.c') diff --git a/drivers/clocksource/timer-davinci.c b/drivers/clocksource/timer-davinci.c new file mode 100644 index 000000000..9996c0542 --- /dev/null +++ b/drivers/clocksource/timer-davinci.c @@ -0,0 +1,366 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * TI DaVinci clocksource driver + * + * Copyright (C) 2019 Texas Instruments + * Author: Bartosz Golaszewski + * (with tiny parts adopted from code by Kevin Hilman ) + */ + +#define pr_fmt(fmt) "%s: " fmt, __func__ + +#include +#include +#include +#include +#include +#include +#include + +#include + +#define DAVINCI_TIMER_REG_TIM12 0x10 +#define DAVINCI_TIMER_REG_TIM34 0x14 +#define DAVINCI_TIMER_REG_PRD12 0x18 +#define DAVINCI_TIMER_REG_PRD34 0x1c +#define DAVINCI_TIMER_REG_TCR 0x20 +#define DAVINCI_TIMER_REG_TGCR 0x24 + +#define DAVINCI_TIMER_TIMMODE_MASK GENMASK(3, 2) +#define DAVINCI_TIMER_RESET_MASK GENMASK(1, 0) +#define DAVINCI_TIMER_TIMMODE_32BIT_UNCHAINED BIT(2) +#define DAVINCI_TIMER_UNRESET GENMASK(1, 0) + +#define DAVINCI_TIMER_ENAMODE_MASK GENMASK(1, 0) +#define DAVINCI_TIMER_ENAMODE_DISABLED 0x00 +#define DAVINCI_TIMER_ENAMODE_ONESHOT BIT(0) +#define DAVINCI_TIMER_ENAMODE_PERIODIC BIT(1) + +#define DAVINCI_TIMER_ENAMODE_SHIFT_TIM12 6 +#define DAVINCI_TIMER_ENAMODE_SHIFT_TIM34 22 + +#define DAVINCI_TIMER_MIN_DELTA 0x01 +#define DAVINCI_TIMER_MAX_DELTA 0xfffffffe + +#define DAVINCI_TIMER_CLKSRC_BITS 32 + +#define DAVINCI_TIMER_TGCR_DEFAULT \ + (DAVINCI_TIMER_TIMMODE_32BIT_UNCHAINED | DAVINCI_TIMER_UNRESET) + +struct davinci_clockevent { + struct clock_event_device dev; + void __iomem *base; + unsigned int cmp_off; +}; + +/* + * This must be globally accessible by davinci_timer_read_sched_clock(), so + * let's keep it here. + */ +static struct { + struct clocksource dev; + void __iomem *base; + unsigned int tim_off; +} davinci_clocksource; + +static struct davinci_clockevent * +to_davinci_clockevent(struct clock_event_device *clockevent) +{ + return container_of(clockevent, struct davinci_clockevent, dev); +} + +static unsigned int +davinci_clockevent_read(struct davinci_clockevent *clockevent, + unsigned int reg) +{ + return readl_relaxed(clockevent->base + reg); +} + +static void davinci_clockevent_write(struct davinci_clockevent *clockevent, + unsigned int reg, unsigned int val) +{ + writel_relaxed(val, clockevent->base + reg); +} + +static void davinci_tim12_shutdown(void __iomem *base) +{ + unsigned int tcr; + + tcr = DAVINCI_TIMER_ENAMODE_DISABLED << + DAVINCI_TIMER_ENAMODE_SHIFT_TIM12; + /* + * This function is only ever called if we're using both timer + * halves. In this case TIM34 runs in periodic mode and we must + * not modify it. + */ + tcr |= DAVINCI_TIMER_ENAMODE_PERIODIC << + DAVINCI_TIMER_ENAMODE_SHIFT_TIM34; + + writel_relaxed(tcr, base + DAVINCI_TIMER_REG_TCR); +} + +static void davinci_tim12_set_oneshot(void __iomem *base) +{ + unsigned int tcr; + + tcr = DAVINCI_TIMER_ENAMODE_ONESHOT << + DAVINCI_TIMER_ENAMODE_SHIFT_TIM12; + /* Same as above. */ + tcr |= DAVINCI_TIMER_ENAMODE_PERIODIC << + DAVINCI_TIMER_ENAMODE_SHIFT_TIM34; + + writel_relaxed(tcr, base + DAVINCI_TIMER_REG_TCR); +} + +static int davinci_clockevent_shutdown(struct clock_event_device *dev) +{ + struct davinci_clockevent *clockevent; + + clockevent = to_davinci_clockevent(dev); + + davinci_tim12_shutdown(clockevent->base); + + return 0; +} + +static int davinci_clockevent_set_oneshot(struct clock_event_device *dev) +{ + struct davinci_clockevent *clockevent = to_davinci_clockevent(dev); + + davinci_clockevent_write(clockevent, DAVINCI_TIMER_REG_TIM12, 0x0); + + davinci_tim12_set_oneshot(clockevent->base); + + return 0; +} + +static int +davinci_clockevent_set_next_event_std(unsigned long cycles, + struct clock_event_device *dev) +{ + struct davinci_clockevent *clockevent = to_davinci_clockevent(dev); + + davinci_clockevent_shutdown(dev); + + davinci_clockevent_write(clockevent, DAVINCI_TIMER_REG_TIM12, 0x0); + davinci_clockevent_write(clockevent, DAVINCI_TIMER_REG_PRD12, cycles); + + davinci_clockevent_set_oneshot(dev); + + return 0; +} + +static int +davinci_clockevent_set_next_event_cmp(unsigned long cycles, + struct clock_event_device *dev) +{ + struct davinci_clockevent *clockevent = to_davinci_clockevent(dev); + unsigned int curr_time; + + curr_time = davinci_clockevent_read(clockevent, + DAVINCI_TIMER_REG_TIM12); + davinci_clockevent_write(clockevent, + clockevent->cmp_off, curr_time + cycles); + + return 0; +} + +static irqreturn_t davinci_timer_irq_timer(int irq, void *data) +{ + struct davinci_clockevent *clockevent = data; + + if (!clockevent_state_oneshot(&clockevent->dev)) + davinci_tim12_shutdown(clockevent->base); + + clockevent->dev.event_handler(&clockevent->dev); + + return IRQ_HANDLED; +} + +static u64 notrace davinci_timer_read_sched_clock(void) +{ + return readl_relaxed(davinci_clocksource.base + + davinci_clocksource.tim_off); +} + +static u64 davinci_clocksource_read(struct clocksource *dev) +{ + return davinci_timer_read_sched_clock(); +} + +/* + * Standard use-case: we're using tim12 for clockevent and tim34 for + * clocksource. The default is making the former run in oneshot mode + * and the latter in periodic mode. + */ +static void davinci_clocksource_init_tim34(void __iomem *base) +{ + int tcr; + + tcr = DAVINCI_TIMER_ENAMODE_PERIODIC << + DAVINCI_TIMER_ENAMODE_SHIFT_TIM34; + tcr |= DAVINCI_TIMER_ENAMODE_ONESHOT << + DAVINCI_TIMER_ENAMODE_SHIFT_TIM12; + + writel_relaxed(0x0, base + DAVINCI_TIMER_REG_TIM34); + writel_relaxed(UINT_MAX, base + DAVINCI_TIMER_REG_PRD34); + writel_relaxed(tcr, base + DAVINCI_TIMER_REG_TCR); +} + +/* + * Special use-case on da830: the DSP may use tim34. We're using tim12 for + * both clocksource and clockevent. We set tim12 to periodic and don't touch + * tim34. + */ +static void davinci_clocksource_init_tim12(void __iomem *base) +{ + unsigned int tcr; + + tcr = DAVINCI_TIMER_ENAMODE_PERIODIC << + DAVINCI_TIMER_ENAMODE_SHIFT_TIM12; + + writel_relaxed(0x0, base + DAVINCI_TIMER_REG_TIM12); + writel_relaxed(UINT_MAX, base + DAVINCI_TIMER_REG_PRD12); + writel_relaxed(tcr, base + DAVINCI_TIMER_REG_TCR); +} + +static void davinci_timer_init(void __iomem *base) +{ + /* Set clock to internal mode and disable it. */ + writel_relaxed(0x0, base + DAVINCI_TIMER_REG_TCR); + /* + * Reset both 32-bit timers, set no prescaler for timer 34, set the + * timer to dual 32-bit unchained mode, unreset both 32-bit timers. + */ + writel_relaxed(DAVINCI_TIMER_TGCR_DEFAULT, + base + DAVINCI_TIMER_REG_TGCR); + /* Init both counters to zero. */ + writel_relaxed(0x0, base + DAVINCI_TIMER_REG_TIM12); + writel_relaxed(0x0, base + DAVINCI_TIMER_REG_TIM34); +} + +int __init davinci_timer_register(struct clk *clk, + const struct davinci_timer_cfg *timer_cfg) +{ + struct davinci_clockevent *clockevent; + unsigned int tick_rate; + void __iomem *base; + int rv; + + rv = clk_prepare_enable(clk); + if (rv) { + pr_err("Unable to prepare and enable the timer clock\n"); + return rv; + } + + if (!request_mem_region(timer_cfg->reg.start, + resource_size(&timer_cfg->reg), + "davinci-timer")) { + pr_err("Unable to request memory region\n"); + return -EBUSY; + } + + base = ioremap(timer_cfg->reg.start, resource_size(&timer_cfg->reg)); + if (!base) { + pr_err("Unable to map the register range\n"); + return -ENOMEM; + } + + davinci_timer_init(base); + tick_rate = clk_get_rate(clk); + + clockevent = kzalloc(sizeof(*clockevent), GFP_KERNEL); + if (!clockevent) + return -ENOMEM; + + clockevent->dev.name = "tim12"; + clockevent->dev.features = CLOCK_EVT_FEAT_ONESHOT; + clockevent->dev.cpumask = cpumask_of(0); + clockevent->base = base; + + if (timer_cfg->cmp_off) { + clockevent->cmp_off = timer_cfg->cmp_off; + clockevent->dev.set_next_event = + davinci_clockevent_set_next_event_cmp; + } else { + clockevent->dev.set_next_event = + davinci_clockevent_set_next_event_std; + clockevent->dev.set_state_oneshot = + davinci_clockevent_set_oneshot; + clockevent->dev.set_state_shutdown = + davinci_clockevent_shutdown; + } + + rv = request_irq(timer_cfg->irq[DAVINCI_TIMER_CLOCKEVENT_IRQ].start, + davinci_timer_irq_timer, IRQF_TIMER, + "clockevent/tim12", clockevent); + if (rv) { + pr_err("Unable to request the clockevent interrupt\n"); + return rv; + } + + davinci_clocksource.dev.rating = 300; + davinci_clocksource.dev.read = davinci_clocksource_read; + davinci_clocksource.dev.mask = + CLOCKSOURCE_MASK(DAVINCI_TIMER_CLKSRC_BITS); + davinci_clocksource.dev.flags = CLOCK_SOURCE_IS_CONTINUOUS; + davinci_clocksource.base = base; + + if (timer_cfg->cmp_off) { + davinci_clocksource.dev.name = "tim12"; + davinci_clocksource.tim_off = DAVINCI_TIMER_REG_TIM12; + davinci_clocksource_init_tim12(base); + } else { + davinci_clocksource.dev.name = "tim34"; + davinci_clocksource.tim_off = DAVINCI_TIMER_REG_TIM34; + davinci_clocksource_init_tim34(base); + } + + clockevents_config_and_register(&clockevent->dev, tick_rate, + DAVINCI_TIMER_MIN_DELTA, + DAVINCI_TIMER_MAX_DELTA); + + rv = clocksource_register_hz(&davinci_clocksource.dev, tick_rate); + if (rv) { + pr_err("Unable to register clocksource\n"); + return rv; + } + + sched_clock_register(davinci_timer_read_sched_clock, + DAVINCI_TIMER_CLKSRC_BITS, tick_rate); + + return 0; +} + +static int __init of_davinci_timer_register(struct device_node *np) +{ + struct davinci_timer_cfg timer_cfg = { }; + struct clk *clk; + int rv; + + rv = of_address_to_resource(np, 0, &timer_cfg.reg); + if (rv) { + pr_err("Unable to get the register range for timer\n"); + return rv; + } + + rv = of_irq_to_resource_table(np, timer_cfg.irq, + DAVINCI_TIMER_NUM_IRQS); + if (rv != DAVINCI_TIMER_NUM_IRQS) { + pr_err("Unable to get the interrupts for timer\n"); + return rv; + } + + clk = of_clk_get(np, 0); + if (IS_ERR(clk)) { + pr_err("Unable to get the timer clock\n"); + return PTR_ERR(clk); + } + + rv = davinci_timer_register(clk, &timer_cfg); + if (rv) + clk_put(clk); + + return rv; +} +TIMER_OF_DECLARE(davinci_timer, "ti,da830-timer", of_davinci_timer_register); -- cgit v1.2.3