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/x86/kernel/nmi.c | 555 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 555 insertions(+) create mode 100644 arch/x86/kernel/nmi.c (limited to 'arch/x86/kernel/nmi.c') diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c new file mode 100644 index 000000000..cec0bfa3b --- /dev/null +++ b/arch/x86/kernel/nmi.c @@ -0,0 +1,555 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + * Copyright (C) 2011 Don Zickus Red Hat, Inc. + * + * Pentium III FXSR, SSE support + * Gareth Hughes , May 2000 + */ + +/* + * Handle hardware traps and faults. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +struct nmi_desc { + raw_spinlock_t lock; + struct list_head head; +}; + +static struct nmi_desc nmi_desc[NMI_MAX] = +{ + { + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock), + .head = LIST_HEAD_INIT(nmi_desc[0].head), + }, + { + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock), + .head = LIST_HEAD_INIT(nmi_desc[1].head), + }, + { + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[2].lock), + .head = LIST_HEAD_INIT(nmi_desc[2].head), + }, + { + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[3].lock), + .head = LIST_HEAD_INIT(nmi_desc[3].head), + }, + +}; + +struct nmi_stats { + unsigned int normal; + unsigned int unknown; + unsigned int external; + unsigned int swallow; +}; + +static DEFINE_PER_CPU(struct nmi_stats, nmi_stats); + +static int ignore_nmis __read_mostly; + +int unknown_nmi_panic; +/* + * Prevent NMI reason port (0x61) being accessed simultaneously, can + * only be used in NMI handler. + */ +static DEFINE_RAW_SPINLOCK(nmi_reason_lock); + +static int __init setup_unknown_nmi_panic(char *str) +{ + unknown_nmi_panic = 1; + return 1; +} +__setup("unknown_nmi_panic", setup_unknown_nmi_panic); + +#define nmi_to_desc(type) (&nmi_desc[type]) + +static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC; + +static int __init nmi_warning_debugfs(void) +{ + debugfs_create_u64("nmi_longest_ns", 0644, + arch_debugfs_dir, &nmi_longest_ns); + return 0; +} +fs_initcall(nmi_warning_debugfs); + +static void nmi_check_duration(struct nmiaction *action, u64 duration) +{ + int remainder_ns, decimal_msecs; + + if (duration < nmi_longest_ns || duration < action->max_duration) + return; + + action->max_duration = duration; + + remainder_ns = do_div(duration, (1000 * 1000)); + decimal_msecs = remainder_ns / 1000; + + printk_ratelimited(KERN_INFO + "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", + action->handler, duration, decimal_msecs); +} + +static int nmi_handle(unsigned int type, struct pt_regs *regs) +{ + struct nmi_desc *desc = nmi_to_desc(type); + struct nmiaction *a; + int handled=0; + + rcu_read_lock(); + + /* + * NMIs are edge-triggered, which means if you have enough + * of them concurrently, you can lose some because only one + * can be latched at any given time. Walk the whole list + * to handle those situations. + */ + list_for_each_entry_rcu(a, &desc->head, list) { + int thishandled; + u64 delta; + + delta = sched_clock(); + thishandled = a->handler(type, regs); + handled += thishandled; + delta = sched_clock() - delta; + trace_nmi_handler(a->handler, (int)delta, thishandled); + + nmi_check_duration(a, delta); + } + + rcu_read_unlock(); + + /* return total number of NMI events handled */ + return handled; +} +NOKPROBE_SYMBOL(nmi_handle); + +int __register_nmi_handler(unsigned int type, struct nmiaction *action) +{ + struct nmi_desc *desc = nmi_to_desc(type); + unsigned long flags; + + if (WARN_ON_ONCE(!action->handler || !list_empty(&action->list))) + return -EINVAL; + + raw_spin_lock_irqsave(&desc->lock, flags); + + /* + * Indicate if there are multiple registrations on the + * internal NMI handler call chains (SERR and IO_CHECK). + */ + WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head)); + WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head)); + + /* + * some handlers need to be executed first otherwise a fake + * event confuses some handlers (kdump uses this flag) + */ + if (action->flags & NMI_FLAG_FIRST) + list_add_rcu(&action->list, &desc->head); + else + list_add_tail_rcu(&action->list, &desc->head); + + raw_spin_unlock_irqrestore(&desc->lock, flags); + return 0; +} +EXPORT_SYMBOL(__register_nmi_handler); + +void unregister_nmi_handler(unsigned int type, const char *name) +{ + struct nmi_desc *desc = nmi_to_desc(type); + struct nmiaction *n, *found = NULL; + unsigned long flags; + + raw_spin_lock_irqsave(&desc->lock, flags); + + list_for_each_entry_rcu(n, &desc->head, list) { + /* + * the name passed in to describe the nmi handler + * is used as the lookup key + */ + if (!strcmp(n->name, name)) { + WARN(in_nmi(), + "Trying to free NMI (%s) from NMI context!\n", n->name); + list_del_rcu(&n->list); + found = n; + break; + } + } + + raw_spin_unlock_irqrestore(&desc->lock, flags); + if (found) { + synchronize_rcu(); + INIT_LIST_HEAD(&found->list); + } +} +EXPORT_SYMBOL_GPL(unregister_nmi_handler); + +static void +pci_serr_error(unsigned char reason, struct pt_regs *regs) +{ + /* check to see if anyone registered against these types of errors */ + if (nmi_handle(NMI_SERR, regs)) + return; + + pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n", + reason, smp_processor_id()); + + if (panic_on_unrecovered_nmi) + nmi_panic(regs, "NMI: Not continuing"); + + pr_emerg("Dazed and confused, but trying to continue\n"); + + /* Clear and disable the PCI SERR error line. */ + reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR; + outb(reason, NMI_REASON_PORT); +} +NOKPROBE_SYMBOL(pci_serr_error); + +static void +io_check_error(unsigned char reason, struct pt_regs *regs) +{ + unsigned long i; + + /* check to see if anyone registered against these types of errors */ + if (nmi_handle(NMI_IO_CHECK, regs)) + return; + + pr_emerg( + "NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n", + reason, smp_processor_id()); + show_regs(regs); + + if (panic_on_io_nmi) { + nmi_panic(regs, "NMI IOCK error: Not continuing"); + + /* + * If we end up here, it means we have received an NMI while + * processing panic(). Simply return without delaying and + * re-enabling NMIs. + */ + return; + } + + /* Re-enable the IOCK line, wait for a few seconds */ + reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK; + outb(reason, NMI_REASON_PORT); + + i = 20000; + while (--i) { + touch_nmi_watchdog(); + udelay(100); + } + + reason &= ~NMI_REASON_CLEAR_IOCHK; + outb(reason, NMI_REASON_PORT); +} +NOKPROBE_SYMBOL(io_check_error); + +static void +unknown_nmi_error(unsigned char reason, struct pt_regs *regs) +{ + int handled; + + /* + * Use 'false' as back-to-back NMIs are dealt with one level up. + * Of course this makes having multiple 'unknown' handlers useless + * as only the first one is ever run (unless it can actually determine + * if it caused the NMI) + */ + handled = nmi_handle(NMI_UNKNOWN, regs); + if (handled) { + __this_cpu_add(nmi_stats.unknown, handled); + return; + } + + __this_cpu_add(nmi_stats.unknown, 1); + + pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", + reason, smp_processor_id()); + + if (unknown_nmi_panic || panic_on_unrecovered_nmi) + nmi_panic(regs, "NMI: Not continuing"); + + pr_emerg("Dazed and confused, but trying to continue\n"); +} +NOKPROBE_SYMBOL(unknown_nmi_error); + +static DEFINE_PER_CPU(bool, swallow_nmi); +static DEFINE_PER_CPU(unsigned long, last_nmi_rip); + +static noinstr void default_do_nmi(struct pt_regs *regs) +{ + unsigned char reason = 0; + int handled; + bool b2b = false; + + /* + * CPU-specific NMI must be processed before non-CPU-specific + * NMI, otherwise we may lose it, because the CPU-specific + * NMI can not be detected/processed on other CPUs. + */ + + /* + * Back-to-back NMIs are interesting because they can either + * be two NMI or more than two NMIs (any thing over two is dropped + * due to NMI being edge-triggered). If this is the second half + * of the back-to-back NMI, assume we dropped things and process + * more handlers. Otherwise reset the 'swallow' NMI behaviour + */ + if (regs->ip == __this_cpu_read(last_nmi_rip)) + b2b = true; + else + __this_cpu_write(swallow_nmi, false); + + __this_cpu_write(last_nmi_rip, regs->ip); + + instrumentation_begin(); + + handled = nmi_handle(NMI_LOCAL, regs); + __this_cpu_add(nmi_stats.normal, handled); + if (handled) { + /* + * There are cases when a NMI handler handles multiple + * events in the current NMI. One of these events may + * be queued for in the next NMI. Because the event is + * already handled, the next NMI will result in an unknown + * NMI. Instead lets flag this for a potential NMI to + * swallow. + */ + if (handled > 1) + __this_cpu_write(swallow_nmi, true); + goto out; + } + + /* + * Non-CPU-specific NMI: NMI sources can be processed on any CPU. + * + * Another CPU may be processing panic routines while holding + * nmi_reason_lock. Check if the CPU issued the IPI for crash dumping, + * and if so, call its callback directly. If there is no CPU preparing + * crash dump, we simply loop here. + */ + while (!raw_spin_trylock(&nmi_reason_lock)) { + run_crash_ipi_callback(regs); + cpu_relax(); + } + + reason = x86_platform.get_nmi_reason(); + + if (reason & NMI_REASON_MASK) { + if (reason & NMI_REASON_SERR) + pci_serr_error(reason, regs); + else if (reason & NMI_REASON_IOCHK) + io_check_error(reason, regs); +#ifdef CONFIG_X86_32 + /* + * Reassert NMI in case it became active + * meanwhile as it's edge-triggered: + */ + reassert_nmi(); +#endif + __this_cpu_add(nmi_stats.external, 1); + raw_spin_unlock(&nmi_reason_lock); + goto out; + } + raw_spin_unlock(&nmi_reason_lock); + + /* + * Only one NMI can be latched at a time. To handle + * this we may process multiple nmi handlers at once to + * cover the case where an NMI is dropped. The downside + * to this approach is we may process an NMI prematurely, + * while its real NMI is sitting latched. This will cause + * an unknown NMI on the next run of the NMI processing. + * + * We tried to flag that condition above, by setting the + * swallow_nmi flag when we process more than one event. + * This condition is also only present on the second half + * of a back-to-back NMI, so we flag that condition too. + * + * If both are true, we assume we already processed this + * NMI previously and we swallow it. Otherwise we reset + * the logic. + * + * There are scenarios where we may accidentally swallow + * a 'real' unknown NMI. For example, while processing + * a perf NMI another perf NMI comes in along with a + * 'real' unknown NMI. These two NMIs get combined into + * one (as described above). When the next NMI gets + * processed, it will be flagged by perf as handled, but + * no one will know that there was a 'real' unknown NMI sent + * also. As a result it gets swallowed. Or if the first + * perf NMI returns two events handled then the second + * NMI will get eaten by the logic below, again losing a + * 'real' unknown NMI. But this is the best we can do + * for now. + */ + if (b2b && __this_cpu_read(swallow_nmi)) + __this_cpu_add(nmi_stats.swallow, 1); + else + unknown_nmi_error(reason, regs); + +out: + instrumentation_end(); +} + +/* + * NMIs can page fault or hit breakpoints which will cause it to lose + * its NMI context with the CPU when the breakpoint or page fault does an IRET. + * + * As a result, NMIs can nest if NMIs get unmasked due an IRET during + * NMI processing. On x86_64, the asm glue protects us from nested NMIs + * if the outer NMI came from kernel mode, but we can still nest if the + * outer NMI came from user mode. + * + * To handle these nested NMIs, we have three states: + * + * 1) not running + * 2) executing + * 3) latched + * + * When no NMI is in progress, it is in the "not running" state. + * When an NMI comes in, it goes into the "executing" state. + * Normally, if another NMI is triggered, it does not interrupt + * the running NMI and the HW will simply latch it so that when + * the first NMI finishes, it will restart the second NMI. + * (Note, the latch is binary, thus multiple NMIs triggering, + * when one is running, are ignored. Only one NMI is restarted.) + * + * If an NMI executes an iret, another NMI can preempt it. We do not + * want to allow this new NMI to run, but we want to execute it when the + * first one finishes. We set the state to "latched", and the exit of + * the first NMI will perform a dec_return, if the result is zero + * (NOT_RUNNING), then it will simply exit the NMI handler. If not, the + * dec_return would have set the state to NMI_EXECUTING (what we want it + * to be when we are running). In this case, we simply jump back to + * rerun the NMI handler again, and restart the 'latched' NMI. + * + * No trap (breakpoint or page fault) should be hit before nmi_restart, + * thus there is no race between the first check of state for NOT_RUNNING + * and setting it to NMI_EXECUTING. The HW will prevent nested NMIs + * at this point. + * + * In case the NMI takes a page fault, we need to save off the CR2 + * because the NMI could have preempted another page fault and corrupt + * the CR2 that is about to be read. As nested NMIs must be restarted + * and they can not take breakpoints or page faults, the update of the + * CR2 must be done before converting the nmi state back to NOT_RUNNING. + * Otherwise, there would be a race of another nested NMI coming in + * after setting state to NOT_RUNNING but before updating the nmi_cr2. + */ +enum nmi_states { + NMI_NOT_RUNNING = 0, + NMI_EXECUTING, + NMI_LATCHED, +}; +static DEFINE_PER_CPU(enum nmi_states, nmi_state); +static DEFINE_PER_CPU(unsigned long, nmi_cr2); +static DEFINE_PER_CPU(unsigned long, nmi_dr7); + +DEFINE_IDTENTRY_RAW(exc_nmi) +{ + irqentry_state_t irq_state; + + /* + * Re-enable NMIs right here when running as an SEV-ES guest. This might + * cause nested NMIs, but those can be handled safely. + */ + sev_es_nmi_complete(); + + if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) + return; + + if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { + this_cpu_write(nmi_state, NMI_LATCHED); + return; + } + this_cpu_write(nmi_state, NMI_EXECUTING); + this_cpu_write(nmi_cr2, read_cr2()); +nmi_restart: + + /* + * Needs to happen before DR7 is accessed, because the hypervisor can + * intercept DR7 reads/writes, turning those into #VC exceptions. + */ + sev_es_ist_enter(regs); + + this_cpu_write(nmi_dr7, local_db_save()); + + irq_state = irqentry_nmi_enter(regs); + + inc_irq_stat(__nmi_count); + + if (!ignore_nmis) + default_do_nmi(regs); + + irqentry_nmi_exit(regs, irq_state); + + local_db_restore(this_cpu_read(nmi_dr7)); + + sev_es_ist_exit(); + + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) + write_cr2(this_cpu_read(nmi_cr2)); + if (this_cpu_dec_return(nmi_state)) + goto nmi_restart; + + if (user_mode(regs)) + mds_user_clear_cpu_buffers(); +} + +#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) +DEFINE_IDTENTRY_RAW(exc_nmi_noist) +{ + exc_nmi(regs); +} +#endif +#if IS_MODULE(CONFIG_KVM_INTEL) +EXPORT_SYMBOL_GPL(asm_exc_nmi_noist); +#endif + +void stop_nmi(void) +{ + ignore_nmis++; +} + +void restart_nmi(void) +{ + ignore_nmis--; +} + +/* reset the back-to-back NMI logic */ +void local_touch_nmi(void) +{ + __this_cpu_write(last_nmi_rip, 0); +} +EXPORT_SYMBOL_GPL(local_touch_nmi); -- cgit v1.2.3