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/watchdog/sb_wdog.c | 363 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 363 insertions(+) create mode 100644 drivers/watchdog/sb_wdog.c (limited to 'drivers/watchdog/sb_wdog.c') diff --git a/drivers/watchdog/sb_wdog.c b/drivers/watchdog/sb_wdog.c new file mode 100644 index 000000000..504be461f --- /dev/null +++ b/drivers/watchdog/sb_wdog.c @@ -0,0 +1,363 @@ +/* + * Watchdog driver for SiByte SB1 SoCs + * + * Copyright (C) 2007 OnStor, Inc. * Andrew Sharp + * + * This driver is intended to make the second of two hardware watchdogs + * on the Sibyte 12XX and 11XX SoCs available to the user. There are two + * such devices available on the SoC, but it seems that there isn't an + * enumeration class for watchdogs in Linux like there is for RTCs. + * The second is used rather than the first because it uses IRQ 1, + * thereby avoiding all that IRQ 0 problematic nonsense. + * + * I have not tried this driver on a 1480 processor; it might work + * just well enough to really screw things up. + * + * It is a simple timer, and there is an interrupt that is raised the + * first time the timer expires. The second time it expires, the chip + * is reset and there is no way to redirect that NMI. Which could + * be problematic in some cases where this chip is sitting on the HT + * bus and has just taken responsibility for providing a cache block. + * Since the reset can't be redirected to the external reset pin, it is + * possible that other HT connected processors might hang and not reset. + * For Linux, a soft reset would probably be even worse than a hard reset. + * There you have it. + * + * The timer takes 23 bits of a 64 bit register (?) as a count value, + * and decrements the count every microsecond, for a max value of + * 0x7fffff usec or about 8.3ish seconds. + * + * This watchdog borrows some user semantics from the softdog driver, + * in that if you close the fd, it leaves the watchdog running, unless + * you previously wrote a 'V' to the fd, in which case it disables + * the watchdog when you close the fd like some other drivers. + * + * Based on various other watchdog drivers, which are probably all + * loosely based on something Alan Cox wrote years ago. + * + * (c) Copyright 1996 Alan Cox , + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 1 or 2 as published by the Free Software Foundation. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +static DEFINE_SPINLOCK(sbwd_lock); + +/* + * set the initial count value of a timer + * + * wdog is the iomem address of the cfg register + */ +static void sbwdog_set(char __iomem *wdog, unsigned long t) +{ + spin_lock(&sbwd_lock); + __raw_writeb(0, wdog); + __raw_writeq(t & 0x7fffffUL, wdog - 0x10); + spin_unlock(&sbwd_lock); +} + +/* + * cause the timer to [re]load it's initial count and start counting + * all over again + * + * wdog is the iomem address of the cfg register + */ +static void sbwdog_pet(char __iomem *wdog) +{ + spin_lock(&sbwd_lock); + __raw_writeb(__raw_readb(wdog) | 1, wdog); + spin_unlock(&sbwd_lock); +} + +static unsigned long sbwdog_gate; /* keeps it to one thread only */ +static char __iomem *kern_dog = (char __iomem *)(IO_BASE + (A_SCD_WDOG_CFG_0)); +static char __iomem *user_dog = (char __iomem *)(IO_BASE + (A_SCD_WDOG_CFG_1)); +static unsigned long timeout = 0x7fffffUL; /* useconds: 8.3ish secs. */ +static int expect_close; + +static const struct watchdog_info ident = { + .options = WDIOF_CARDRESET | WDIOF_SETTIMEOUT | + WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE, + .identity = "SiByte Watchdog", +}; + +/* + * Allow only a single thread to walk the dog + */ +static int sbwdog_open(struct inode *inode, struct file *file) +{ + stream_open(inode, file); + if (test_and_set_bit(0, &sbwdog_gate)) + return -EBUSY; + __module_get(THIS_MODULE); + + /* + * Activate the timer + */ + sbwdog_set(user_dog, timeout); + __raw_writeb(1, user_dog); + + return 0; +} + +/* + * Put the dog back in the kennel. + */ +static int sbwdog_release(struct inode *inode, struct file *file) +{ + if (expect_close == 42) { + __raw_writeb(0, user_dog); + module_put(THIS_MODULE); + } else { + pr_crit("%s: Unexpected close, not stopping watchdog!\n", + ident.identity); + sbwdog_pet(user_dog); + } + clear_bit(0, &sbwdog_gate); + expect_close = 0; + + return 0; +} + +/* + * 42 - the answer + */ +static ssize_t sbwdog_write(struct file *file, const char __user *data, + size_t len, loff_t *ppos) +{ + int i; + + if (len) { + /* + * restart the timer + */ + expect_close = 0; + + for (i = 0; i != len; i++) { + char c; + + if (get_user(c, data + i)) + return -EFAULT; + if (c == 'V') + expect_close = 42; + } + sbwdog_pet(user_dog); + } + + return len; +} + +static long sbwdog_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + int ret = -ENOTTY; + unsigned long time; + void __user *argp = (void __user *)arg; + int __user *p = argp; + + switch (cmd) { + case WDIOC_GETSUPPORT: + ret = copy_to_user(argp, &ident, sizeof(ident)) ? -EFAULT : 0; + break; + + case WDIOC_GETSTATUS: + case WDIOC_GETBOOTSTATUS: + ret = put_user(0, p); + break; + + case WDIOC_KEEPALIVE: + sbwdog_pet(user_dog); + ret = 0; + break; + + case WDIOC_SETTIMEOUT: + ret = get_user(time, p); + if (ret) + break; + + time *= 1000000; + if (time > 0x7fffffUL) { + ret = -EINVAL; + break; + } + timeout = time; + sbwdog_set(user_dog, timeout); + sbwdog_pet(user_dog); + fallthrough; + + case WDIOC_GETTIMEOUT: + /* + * get the remaining count from the ... count register + * which is 1*8 before the config register + */ + ret = put_user((u32)__raw_readq(user_dog - 8) / 1000000, p); + break; + } + return ret; +} + +/* + * Notifier for system down + */ +static int sbwdog_notify_sys(struct notifier_block *this, unsigned long code, + void *erf) +{ + if (code == SYS_DOWN || code == SYS_HALT) { + /* + * sit and sit + */ + __raw_writeb(0, user_dog); + __raw_writeb(0, kern_dog); + } + + return NOTIFY_DONE; +} + +static const struct file_operations sbwdog_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .write = sbwdog_write, + .unlocked_ioctl = sbwdog_ioctl, + .compat_ioctl = compat_ptr_ioctl, + .open = sbwdog_open, + .release = sbwdog_release, +}; + +static struct miscdevice sbwdog_miscdev = { + .minor = WATCHDOG_MINOR, + .name = "watchdog", + .fops = &sbwdog_fops, +}; + +static struct notifier_block sbwdog_notifier = { + .notifier_call = sbwdog_notify_sys, +}; + +/* + * interrupt handler + * + * doesn't do a whole lot for user, but oh so cleverly written so kernel + * code can use it to re-up the watchdog, thereby saving the kernel from + * having to create and maintain a timer, just to tickle another timer, + * which is just so wrong. + */ +irqreturn_t sbwdog_interrupt(int irq, void *addr) +{ + unsigned long wd_init; + char *wd_cfg_reg = (char *)addr; + u8 cfg; + + cfg = __raw_readb(wd_cfg_reg); + wd_init = __raw_readq(wd_cfg_reg - 8) & 0x7fffff; + + /* + * if it's the second watchdog timer, it's for those users + */ + if (wd_cfg_reg == user_dog) + pr_crit("%s in danger of initiating system reset " + "in %ld.%01ld seconds\n", + ident.identity, + wd_init / 1000000, (wd_init / 100000) % 10); + else + cfg |= 1; + + __raw_writeb(cfg, wd_cfg_reg); + + return IRQ_HANDLED; +} + +static int __init sbwdog_init(void) +{ + int ret; + + /* + * register a reboot notifier + */ + ret = register_reboot_notifier(&sbwdog_notifier); + if (ret) { + pr_err("%s: cannot register reboot notifier (err=%d)\n", + ident.identity, ret); + return ret; + } + + /* + * get the resources + */ + + ret = request_irq(1, sbwdog_interrupt, IRQF_SHARED, + ident.identity, (void *)user_dog); + if (ret) { + pr_err("%s: failed to request irq 1 - %d\n", + ident.identity, ret); + goto out; + } + + ret = misc_register(&sbwdog_miscdev); + if (ret == 0) { + pr_info("%s: timeout is %ld.%ld secs\n", + ident.identity, + timeout / 1000000, (timeout / 100000) % 10); + return 0; + } + free_irq(1, (void *)user_dog); +out: + unregister_reboot_notifier(&sbwdog_notifier); + + return ret; +} + +static void __exit sbwdog_exit(void) +{ + misc_deregister(&sbwdog_miscdev); + free_irq(1, (void *)user_dog); + unregister_reboot_notifier(&sbwdog_notifier); +} + +module_init(sbwdog_init); +module_exit(sbwdog_exit); + +MODULE_AUTHOR("Andrew Sharp "); +MODULE_DESCRIPTION("SiByte Watchdog"); + +module_param(timeout, ulong, 0); +MODULE_PARM_DESC(timeout, + "Watchdog timeout in microseconds (max/default 8388607 or 8.3ish secs)"); + +MODULE_LICENSE("GPL"); + +/* + * example code that can be put in a platform code area to utilize the + * first watchdog timer for the kernels own purpose. + +void platform_wd_setup(void) +{ + int ret; + + ret = request_irq(1, sbwdog_interrupt, IRQF_SHARED, + "Kernel Watchdog", IOADDR(A_SCD_WDOG_CFG_0)); + if (ret) { + pr_crit("Watchdog IRQ zero(0) failed to be requested - %d\n", ret); + } +} + + + */ -- cgit v1.2.3