From 22098763a10d9c1340827fcf6edab66f153b27f0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2026 12:27:00 -0700 Subject: Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Don't destroy user event fields when removal fails User event fields are destroyed before the event is removed from visibility. But that can fail leaving the still visible event with no fields. Move the destroying of the fields to after the event is successfully removed from visibility. - Initialize function graph state is fork before calling copy_exec_state() For non-CLONE_VM forks, copy_exec_state() allocates a new task_exec_state. If that allocation fails, ftrace_graph_exit_task() will free the tasks ret_stack pointer. Since that pointer is still using the parent's ret_stack, it mistakenly frees the parent's pointer too. Call ftrace_graph_init() on the task first which will NULL out the new tasks's ret_stack and if the copy fails, it will not free anything. - Remove FGRAPH_MAX_INDEX The macro FGRAPH_MAX_INDEX was added but never used. Remove it. - Save ent_size in function graph printing of nested functions The function graph tracer needs to look at the next event to see if the next event is the return of the current function entry. If it is, it prints a single line: ktime_get(); Otherwise it prints it like a nested function: tick_nohz_irq_exit() { ktime_get(); kcpustat_irq_exit(); } In order to look at the next event, it must save the current event so that it has the information to print from it. It saves the event in the iterator descriptor called "ent". What it doesn't save is the ent_size of the event which is now used to know if the function graph arguments are to be printed. The peek doesn't save the size so the size used happens to be that of the size of the last event that was seen. Save the entry event size in the iterator descriptor so that the correct size is used. - Fix several errors with freeing data in the histogram code The histogram code had a lot of leaked or or incorrect accounting when failures happen. Correct them. - Fix histogram regression of .percent and .graph modifiers Up until 6.3 histogram values could have "percent" or "graph" modifiers that changed how they were printed. But a change that added restricting histograms values from being strings, stack traces and other modifiers inadvertently prevented them from using the percent and graph modifiers, which were legal use cases for values. Put back the percent and graph modifiers. - Fix various typos in the comments - Set the trace_clock before initializing a histogram with clock argument The histogram API allows the user to specific which trace clock to use via a "clock=" string. The histogram is set up first before the clock is checked. If the passed in clock is not valid, it exits without fully fixing up the histogram leaving it on the list and a use-after-free can trigger. Update the clock argument first and if it fails then exit gracefully before the histogram trigger is placed on any lists. - Restore :mod: trailer after parsing in ftrace_set_clr_event The function ftrace_set_clr_event() modifies the parse string and needs to put it back to what was passed in. It searches for ":mod:" via a strsep() but fails to put back the first ':' in the string. Add back the ':' in the passed in string. - Take trace_array reference when opening a tracer options file The options files are dynamically created and some tracers add their own options. When a tracer adds their own list of options, the trace_array holding them has an array to hold the list of options for each tracer. This array increases in size via a krealloc(), and the new entry gets a newly allocated array to hold the options of the new tracer being added. The element in each entry of the tracer's option array holds a pointer back to the trace_array, a pointer to the tracer it is associated to, a pointer to the flags of the option. The issue is that these arrays are freed when the trace_array is freed when its instance it represents is removed from the instances directory. There's a race that an open of one of these options files can happen when the instance is being removed. Add a new helper function to be called by the open function of the options file to iterate all existing trace_arrays under a lock and find the one that has the given option element in one of it's tracer arrays. If found, then update the associated trace_array's reference counter to keep it from being freed. If not found, have the open call return -ENODEV. - Disable interrupts when acquiring the lock in rb_wake_up_waiters() The function rb_wake_up_waiters() assumes it will be called in interrupt context and does not disable irqs when taking cpu_buffer->reader_lock, which can be called in hard interrupt context. The issue is in PREEMPT_RT, this function is called in thread context leaving this lock open to a deadlock. Take the lock with interrupts disabled. - Use rcu_assign_pointer() for tmp_ops filter hash The tmp_ops used in update_ftrace_direct_mod() assigns its filter_hash field directly, but that field is annotated as __rcu and sparse complains. Assign it with rcu_assign_pointer() - Fix use-after-free in enable_trigger_private_data_free() The trace_event_call is accessed through the event_trigger_data's trace_event_file pointer to put the trace_event_call on freeing. The issue is that the trace_event_file data may have been freed already causing a use-after-free. Add a field to the event_trigger_data that points directly to the trace_event_call so that it can decrement its reference directly without needing to go through the trace_event_file. - Fix accounting of buffer data remote headers trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount the number of pages is needed for the asked for size as it doesn't take into account the meta data on each page. Add a helper function to do the calculation properly and use that in these functions. - Catch nr_page_va overflow in ring_buffer_desc sizing The number of pages per remote ring buffer is capped by ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to overflow that field would silently allocate a descriptor smaller than what was asked for. - Do not resize the subbuf order if any per_cpu buffer is disabled The mmapping of ring buffers disables resizing the subbuffers, but it is done per-cpu whereas the subbuf size change is done for all the per_cpu buffers under the buffer->mutex. It could change the size of some while the mapping is happening on others. Have the resize of the subbuf order check all the per_cpu buffers under the lock to see if any of them is disabled before starting and causing an inconsistency between buffers that are being mapped. * tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits) ring-buffer: Check resize_disabled before publishing the new subbuf order tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing tracing/remotes: Account for ring buffer page header in size calculation tracing: Don't dereference trace_event_file in deferred trigger free ftrace: Use rcu_assign_pointer() for tmp_ops filter hash ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters() tracing: Take trace_array reference when opening a tracer options file tracing: Fix ring_buffer_read_page_size() kernel-doc tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event() tracing: Fix memory corruption from a "STACKTRACE" histogram key tracing: Fix memory corruption from the histogram stacktrace modifier tracing: Undo the registration when enabling the histogram trigger fails tracing: Take the reference before publishing the named histogram trigger tracing: Set the trace clock before registering the histogram trigger tracing: Fix typo "preceeded" in comment tracing: Fix typo "availabe" in comment tracing: Let histogram values keep the percent and graph modifiers tracing: Keep the entry count when the histogram stats allocation fails tracing: Free histogram the field rejected for a bad modifier tracing: Free histogram the var ref when its initialization fails ... --- drivers/clocksource/hyperv_timer.c | 558 +++++++++++++++++++++++++++++++++++++ 1 file changed, 558 insertions(+) create mode 100644 drivers/clocksource/hyperv_timer.c (limited to 'drivers/clocksource/hyperv_timer.c') diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c new file mode 100644 index 000000000..dddfff458 --- /dev/null +++ b/drivers/clocksource/hyperv_timer.c @@ -0,0 +1,558 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Clocksource driver for the synthetic counter and timers + * provided by the Hyper-V hypervisor to guest VMs, as described + * in the Hyper-V Top Level Functional Spec (TLFS). This driver + * is instruction set architecture independent. + * + * Copyright (C) 2019, Microsoft, Inc. + * + * Author: Michael Kelley + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct clock_event_device __percpu *hv_clock_event; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; + +static int stimer0_irq = -1; +static __maybe_unused DEFINE_PER_CPU(long, stimer0_evt); + +static void hv_stimer0_isr(void) +{ + struct clock_event_device *ce; + + ce = this_cpu_ptr(hv_clock_event); + ce->event_handler(ce); +} + +/* + * stimer0 interrupt handler for architectures that support + * per-cpu interrupts + */ +static irqreturn_t __maybe_unused hv_stimer0_percpu_isr(int irq, void *dev_id) +{ + hv_stimer0_isr(); + return IRQ_HANDLED; +} + +static int hv_ce_set_next_event(unsigned long delta, + struct clock_event_device *evt) +{ + u64 current_tick; + + current_tick = hv_read_reference_counter(); + current_tick += delta; + hv_set_msr(HV_MSR_STIMER0_COUNT, current_tick); + return 0; +} + +static int hv_ce_shutdown(struct clock_event_device *evt) +{ + hv_set_msr(HV_MSR_STIMER0_COUNT, 0); + hv_set_msr(HV_MSR_STIMER0_CONFIG, 0); + if (stimer0_irq >= 0) + disable_percpu_irq(stimer0_irq); + + return 0; +} + +static int hv_ce_set_oneshot(struct clock_event_device *evt) +{ + union hv_stimer_config timer_cfg; + + timer_cfg.as_uint64 = 0; + timer_cfg.enable = 1; + timer_cfg.auto_enable = 1; + + /* + * When it expires, the timer will directly interrupt + * on the specified hardware vector/IRQ. + */ + timer_cfg.direct_mode = 1; + timer_cfg.apic_vector = HYPERV_STIMER0_VECTOR; + if (stimer0_irq >= 0) + enable_percpu_irq(stimer0_irq, IRQ_TYPE_NONE); + + hv_set_msr(HV_MSR_STIMER0_CONFIG, timer_cfg.as_uint64); + return 0; +} + +/* + * hv_stimer_init - Per-cpu initialization of the clockevent + */ +static int hv_stimer_init(unsigned int cpu) +{ + struct clock_event_device *ce; + + if (!hv_clock_event) + return 0; + + ce = per_cpu_ptr(hv_clock_event, cpu); + ce->name = "Hyper-V clockevent"; + ce->features = CLOCK_EVT_FEAT_ONESHOT; + ce->cpumask = cpumask_of(cpu); + + /* + * Lower the rating of the Hyper-V timer in a TDX VM without paravisor, + * so the local APIC timer (lapic_clockevent) is the default timer in + * such a VM. The Hyper-V timer is not preferred in such a VM because + * it depends on the slow VM Reference Counter MSR (the Hyper-V TSC + * page is not enbled in such a VM because the VM uses Invariant TSC + * as a better clocksource and it's challenging to mark the Hyper-V + * TSC page shared in very early boot). + */ + if (!ms_hyperv.paravisor_present && hv_isolation_type_tdx()) + ce->rating = 90; + else + ce->rating = 1000; + + ce->set_state_shutdown = hv_ce_shutdown; + ce->set_state_oneshot = hv_ce_set_oneshot; + ce->set_next_event = hv_ce_set_next_event; + + clockevents_config_and_register(ce, + HV_CLOCK_HZ, + HV_MIN_DELTA_TICKS, + HV_MAX_MAX_DELTA_TICKS); + return 0; +} + +/* + * hv_stimer_cleanup - Per-cpu cleanup of the clockevent + */ +int hv_stimer_cleanup(unsigned int cpu) +{ + struct clock_event_device *ce; + + if (!hv_clock_event) + return 0; + + ce = per_cpu_ptr(hv_clock_event, cpu); + hv_ce_shutdown(ce); + + return 0; +} +EXPORT_SYMBOL_GPL(hv_stimer_cleanup); + +/* + * These placeholders are overridden by arch specific code on + * architectures that need special setup of the stimer0 IRQ because + * they don't support per-cpu IRQs (such as x86/x64). + */ +void __weak hv_setup_stimer0_handler(void (*handler)(void)) +{ +}; + +void __weak hv_remove_stimer0_handler(void) +{ +}; + +#ifdef CONFIG_ACPI +/* Called only on architectures with per-cpu IRQs (i.e., not x86/x64) */ +static int hv_setup_stimer0_irq(void) +{ + int ret; + + ret = acpi_register_gsi(NULL, HYPERV_STIMER0_VECTOR, + ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_HIGH); + if (ret < 0) { + pr_err("Can't register Hyper-V stimer0 GSI. Error %d", ret); + return ret; + } + stimer0_irq = ret; + + ret = request_percpu_irq(stimer0_irq, hv_stimer0_percpu_isr, + "Hyper-V stimer0", &stimer0_evt); + if (ret) { + pr_err("Can't request Hyper-V stimer0 IRQ %d. Error %d", + stimer0_irq, ret); + acpi_unregister_gsi(stimer0_irq); + stimer0_irq = -1; + } + return ret; +} + +static void hv_remove_stimer0_irq(void) +{ + if (stimer0_irq == -1) { + hv_remove_stimer0_handler(); + } else { + free_percpu_irq(stimer0_irq, &stimer0_evt); + acpi_unregister_gsi(stimer0_irq); + stimer0_irq = -1; + } +} +#else +static int hv_setup_stimer0_irq(void) +{ + return 0; +} + +static void hv_remove_stimer0_irq(void) +{ +} +#endif + +/* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */ +int hv_stimer_alloc(bool have_percpu_irqs) +{ + int ret; + + /* + * Synthetic timers are always available except on old versions of + * Hyper-V on x86. In that case, return as error as Linux will use a + * clockevent based on emulated LAPIC timer hardware. + */ + if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) || + !(ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE)) + return -EINVAL; + + hv_clock_event = alloc_percpu(struct clock_event_device); + if (!hv_clock_event) + return -ENOMEM; + + if (have_percpu_irqs) { + ret = hv_setup_stimer0_irq(); + if (ret) + goto free_clock_event; + } else { + hv_setup_stimer0_handler(hv_stimer0_isr); + } + + ret = cpuhp_setup_state(CPUHP_AP_HYPERV_TIMER_STARTING, + "clockevents/hyperv/stimer:starting", + hv_stimer_init, hv_stimer_cleanup); + if (ret < 0) { + hv_remove_stimer0_irq(); + goto free_clock_event; + } + return ret; + +free_clock_event: + free_percpu(hv_clock_event); + hv_clock_event = NULL; + return ret; +} +EXPORT_SYMBOL_GPL(hv_stimer_alloc); + +/* + * Do a global cleanup of clockevents for the cases of kexec and + * vmbus exit + */ +void hv_stimer_global_cleanup(void) +{ + if (!hv_clock_event) + return; + + cpuhp_remove_state(CPUHP_AP_HYPERV_TIMER_STARTING); + hv_remove_stimer0_irq(); + stimer0_irq = -1; + + free_percpu(hv_clock_event); + hv_clock_event = NULL; + +} +EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup); + +static __always_inline u64 read_hv_clock_msr(void) +{ + /* + * Read the partition counter to get the current tick count. This count + * is set to 0 when the partition is created and is incremented in 100 + * nanosecond units. + * + * Use hv_raw_get_msr() because this function is used from + * noinstr. Notable; while HV_MSR_TIME_REF_COUNT is a synthetic + * register it doesn't need the GHCB path. + */ + return hv_raw_get_msr(HV_MSR_TIME_REF_COUNT); +} + +/* + * Code and definitions for the Hyper-V clocksources. Two + * clocksources are defined: one that reads the Hyper-V defined MSR, and + * the other that uses the TSC reference page feature as defined in the + * TLFS. The MSR version is for compatibility with old versions of + * Hyper-V and 32-bit x86. The TSC reference page version is preferred. + */ + +static union { + struct ms_hyperv_tsc_page page; + u8 reserved[PAGE_SIZE]; +} tsc_pg __bss_decrypted __aligned(PAGE_SIZE); + +static struct ms_hyperv_tsc_page *tsc_page = &tsc_pg.page; +static unsigned long tsc_pfn; + +unsigned long hv_get_tsc_pfn(void) +{ + return tsc_pfn; +} +EXPORT_SYMBOL_GPL(hv_get_tsc_pfn); + +struct ms_hyperv_tsc_page *hv_get_tsc_page(void) +{ + return tsc_page; +} +EXPORT_SYMBOL_GPL(hv_get_tsc_page); + +static __always_inline u64 read_hv_clock_tsc(void) +{ + u64 cur_tsc, time; + + /* + * The Hyper-V Top-Level Function Spec (TLFS), section Timers, + * subsection Refererence Counter, guarantees that the TSC and MSR + * times are in sync and monotonic. Therefore we can fall back + * to the MSR in case the TSC page indicates unavailability. + */ + if (!hv_read_tsc_page_tsc(tsc_page, &cur_tsc, &time)) + time = read_hv_clock_msr(); + + return time; +} + +static u64 notrace read_hv_clock_tsc_cs(struct clocksource *arg) +{ + return read_hv_clock_tsc(); +} + +static u64 notrace read_hv_clock_tsc_cs_snapshot(struct clocksource *arg, + struct clocksource_hw_snapshot *chs) +{ + u64 time; + + if (hv_read_tsc_page_tsc(tsc_page, &chs->hw_cycles, &time)) { + chs->hw_csid = CSID_X86_TSC; + } else { + chs->hw_cycles = 0; + chs->hw_csid = CSID_GENERIC; + time = read_hv_clock_msr(); + } + + return time; +} + +static u64 noinstr read_hv_sched_clock_tsc(void) +{ + return (read_hv_clock_tsc() - hv_sched_clock_offset) * + (NSEC_PER_SEC / HV_CLOCK_HZ); +} + +static void suspend_hv_clock_tsc(struct clocksource *arg) +{ + union hv_reference_tsc_msr tsc_msr; + + /* Disable the TSC page */ + tsc_msr.as_uint64 = hv_get_msr(HV_MSR_REFERENCE_TSC); + tsc_msr.enable = 0; + hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); +} + + +static void resume_hv_clock_tsc(struct clocksource *arg) +{ + union hv_reference_tsc_msr tsc_msr; + + /* Re-enable the TSC page */ + tsc_msr.as_uint64 = hv_get_msr(HV_MSR_REFERENCE_TSC); + tsc_msr.enable = 1; + tsc_msr.pfn = tsc_pfn; + hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); +} + +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + +#ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK +static int hv_cs_enable(struct clocksource *cs) +{ + vclocks_set_used(VDSO_CLOCKMODE_HVCLOCK); + return 0; +} +#endif + +static struct clocksource hyperv_cs_tsc = { + .name = "hyperv_clocksource_tsc_page", + .rating = 500, + .read = read_hv_clock_tsc_cs, + .read_snapshot = read_hv_clock_tsc_cs_snapshot, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .suspend = suspend_hv_clock_tsc, + .resume = resume_hv_clock_tsc, +#ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK + .enable = hv_cs_enable, + .vdso_clock_mode = VDSO_CLOCKMODE_HVCLOCK, +#else + .vdso_clock_mode = VDSO_CLOCKMODE_NONE, +#endif +}; + +static u64 notrace read_hv_clock_msr_cs(struct clocksource *arg) +{ + return read_hv_clock_msr(); +} + +static struct clocksource hyperv_cs_msr = { + .name = "hyperv_clocksource_msr", + .rating = 495, + .read = read_hv_clock_msr_cs, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +/* + * Reference to pv_ops must be inline so objtool + * detection of noinstr violations can work correctly. + */ +#ifdef CONFIG_GENERIC_SCHED_CLOCK +static __always_inline void hv_setup_sched_clock(void *sched_clock) +{ + /* + * We're on an architecture with generic sched clock (not x86/x64). + * The Hyper-V sched clock read function returns nanoseconds, not + * the normal 100ns units of the Hyper-V synthetic clock. + */ + sched_clock_register(sched_clock, 64, NSEC_PER_SEC); +} +#elif defined CONFIG_PARAVIRT +#include + +static __always_inline void hv_setup_sched_clock(void *sched_clock) +{ + /* We're on x86/x64 *and* using PV ops */ + paravirt_set_sched_clock(sched_clock); +} +#else /* !CONFIG_GENERIC_SCHED_CLOCK && !CONFIG_PARAVIRT */ +static __always_inline void hv_setup_sched_clock(void *sched_clock) {} +#endif /* CONFIG_GENERIC_SCHED_CLOCK */ + +static void __init hv_init_tsc_clocksource(void) +{ + union hv_reference_tsc_msr tsc_msr; + + /* + * When running as a guest partition: + * + * If Hyper-V offers TSC_INVARIANT, then the virtualized TSC correctly + * handles frequency and offset changes due to live migration, + * pause/resume, and other VM management operations. So lower the + * Hyper-V Reference TSC rating, causing the generic TSC to be used. + * TSC_INVARIANT is not offered on ARM64, so the Hyper-V Reference + * TSC will be preferred over the virtualized ARM64 arch counter. + * + * When running as the root partition: + * + * There is no HV_ACCESS_TSC_INVARIANT feature. Always lower the rating + * of the Hyper-V Reference TSC. + */ + if ((ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) || + hv_root_partition()) { + hyperv_cs_tsc.rating = 250; + hyperv_cs_msr.rating = 245; + } + + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + hv_read_reference_counter = read_hv_clock_tsc; + + /* + * TSC page mapping works differently in root compared to guest. + * - In guest partition the guest PFN has to be passed to the + * hypervisor. + * - In root partition it's other way around: it has to map the PFN + * provided by the hypervisor. + * But it can't be mapped right here as it's too early and MMU isn't + * ready yet. So, we only set the enable bit here and will remap the + * page later in hv_remap_tsc_clocksource(). + * + * It worth mentioning, that TSC clocksource read function + * (read_hv_clock_tsc) has a MSR-based fallback mechanism, used when + * TSC page is zeroed (which is the case until the PFN is remapped) and + * thus TSC clocksource will work even without the real TSC page + * mapped. + */ + tsc_msr.as_uint64 = hv_get_msr(HV_MSR_REFERENCE_TSC); + if (hv_root_partition()) + tsc_pfn = tsc_msr.pfn; + else + tsc_pfn = HVPFN_DOWN(virt_to_phys(tsc_page)); + tsc_msr.enable = 1; + tsc_msr.pfn = tsc_pfn; + hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); + + clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100); + + /* + * If TSC is invariant, then let it stay as the sched clock since it + * will be faster than reading the TSC page. But if not invariant, use + * the TSC page so that live migrations across hosts with different + * frequencies is handled correctly. + */ + if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT)) { + hv_sched_clock_offset = hv_read_reference_counter(); + hv_setup_sched_clock(read_hv_sched_clock_tsc); + } +} + +void __init hv_init_clocksource(void) +{ + /* + * Try to set up the TSC page clocksource, then the MSR clocksource. + * At least one of these will always be available except on very old + * versions of Hyper-V on x86. In that case we won't have a Hyper-V + * clocksource, but Linux will still run with a clocksource based + * on the emulated PIT or LAPIC timer. + * + * Never use the MSR clocksource as sched clock. It's too slow. + * Better to use the native sched clock as the fallback. + */ + hv_init_tsc_clocksource(); + + if (ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE) + clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100); +} + +void __init hv_remap_tsc_clocksource(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + if (!hv_root_partition()) { + WARN(1, "%s: attempt to remap TSC page in guest partition\n", + __func__); + return; + } + + tsc_page = memremap(tsc_pfn << HV_HYP_PAGE_SHIFT, sizeof(tsc_pg), + MEMREMAP_WB); + if (!tsc_page) + pr_err("Failed to remap Hyper-V TSC page.\n"); +} -- cgit v1.3.1