mirror of
https://github.com/torvalds/linux.git
synced 2024-12-12 14:12:51 +00:00
1268ed0c47
The IPI hypercalls depend on being able to map the Linux notion of CPU ID
to the hypervisor's notion of the CPU ID. The array hv_vp_index[] provides
this mapping. Code for populating this array depends on the IPI functionality.
Break this circular dependency.
[ tglx: Use a proper define instead of '-1' with a u32 variable as pointed
out by Vitaly ]
Fixes: 68bb7bfb79
("X86/Hyper-V: Enable IPI enlightenments")
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Michael Kelley <mikelley@microsoft.com>
Cc: gregkh@linuxfoundation.org
Cc: devel@linuxdriverproject.org
Cc: olaf@aepfle.de
Cc: apw@canonical.com
Cc: jasowang@redhat.com
Cc: hpa@zytor.com
Cc: sthemmin@microsoft.com
Cc: Michael.H.Kelley@microsoft.com
Cc: vkuznets@redhat.com
Link: https://lkml.kernel.org/r/20180703230155.15160-1-kys@linuxonhyperv.com
450 lines
11 KiB
C
450 lines
11 KiB
C
/*
|
|
* X86 specific Hyper-V initialization code.
|
|
*
|
|
* Copyright (C) 2016, Microsoft, Inc.
|
|
*
|
|
* Author : K. Y. Srinivasan <kys@microsoft.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms of the GNU General Public License version 2 as published
|
|
* by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
|
|
* NON INFRINGEMENT. See the GNU General Public License for more
|
|
* details.
|
|
*
|
|
*/
|
|
|
|
#include <linux/types.h>
|
|
#include <asm/apic.h>
|
|
#include <asm/desc.h>
|
|
#include <asm/hypervisor.h>
|
|
#include <asm/hyperv-tlfs.h>
|
|
#include <asm/mshyperv.h>
|
|
#include <linux/version.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/clockchips.h>
|
|
#include <linux/hyperv.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/cpuhotplug.h>
|
|
|
|
#ifdef CONFIG_HYPERV_TSCPAGE
|
|
|
|
static struct ms_hyperv_tsc_page *tsc_pg;
|
|
|
|
struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
|
|
{
|
|
return tsc_pg;
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_get_tsc_page);
|
|
|
|
static u64 read_hv_clock_tsc(struct clocksource *arg)
|
|
{
|
|
u64 current_tick = hv_read_tsc_page(tsc_pg);
|
|
|
|
if (current_tick == U64_MAX)
|
|
rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
|
|
|
|
return current_tick;
|
|
}
|
|
|
|
static struct clocksource hyperv_cs_tsc = {
|
|
.name = "hyperv_clocksource_tsc_page",
|
|
.rating = 400,
|
|
.read = read_hv_clock_tsc,
|
|
.mask = CLOCKSOURCE_MASK(64),
|
|
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
|
|
};
|
|
#endif
|
|
|
|
static u64 read_hv_clock_msr(struct clocksource *arg)
|
|
{
|
|
u64 current_tick;
|
|
/*
|
|
* 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.
|
|
*/
|
|
rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
|
|
return current_tick;
|
|
}
|
|
|
|
static struct clocksource hyperv_cs_msr = {
|
|
.name = "hyperv_clocksource_msr",
|
|
.rating = 400,
|
|
.read = read_hv_clock_msr,
|
|
.mask = CLOCKSOURCE_MASK(64),
|
|
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
|
|
};
|
|
|
|
void *hv_hypercall_pg;
|
|
EXPORT_SYMBOL_GPL(hv_hypercall_pg);
|
|
struct clocksource *hyperv_cs;
|
|
EXPORT_SYMBOL_GPL(hyperv_cs);
|
|
|
|
u32 *hv_vp_index;
|
|
EXPORT_SYMBOL_GPL(hv_vp_index);
|
|
|
|
struct hv_vp_assist_page **hv_vp_assist_page;
|
|
EXPORT_SYMBOL_GPL(hv_vp_assist_page);
|
|
|
|
void __percpu **hyperv_pcpu_input_arg;
|
|
EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
|
|
|
|
u32 hv_max_vp_index;
|
|
|
|
static int hv_cpu_init(unsigned int cpu)
|
|
{
|
|
u64 msr_vp_index;
|
|
struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
|
|
void **input_arg;
|
|
|
|
input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
|
|
*input_arg = page_address(alloc_page(GFP_KERNEL));
|
|
|
|
hv_get_vp_index(msr_vp_index);
|
|
|
|
hv_vp_index[smp_processor_id()] = msr_vp_index;
|
|
|
|
if (msr_vp_index > hv_max_vp_index)
|
|
hv_max_vp_index = msr_vp_index;
|
|
|
|
if (!hv_vp_assist_page)
|
|
return 0;
|
|
|
|
if (!*hvp)
|
|
*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
|
|
|
|
if (*hvp) {
|
|
u64 val;
|
|
|
|
val = vmalloc_to_pfn(*hvp);
|
|
val = (val << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) |
|
|
HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
|
|
|
|
wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, val);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void (*hv_reenlightenment_cb)(void);
|
|
|
|
static void hv_reenlightenment_notify(struct work_struct *dummy)
|
|
{
|
|
struct hv_tsc_emulation_status emu_status;
|
|
|
|
rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
|
|
|
|
/* Don't issue the callback if TSC accesses are not emulated */
|
|
if (hv_reenlightenment_cb && emu_status.inprogress)
|
|
hv_reenlightenment_cb();
|
|
}
|
|
static DECLARE_DELAYED_WORK(hv_reenlightenment_work, hv_reenlightenment_notify);
|
|
|
|
void hyperv_stop_tsc_emulation(void)
|
|
{
|
|
u64 freq;
|
|
struct hv_tsc_emulation_status emu_status;
|
|
|
|
rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
|
|
emu_status.inprogress = 0;
|
|
wrmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
|
|
|
|
rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
|
|
tsc_khz = div64_u64(freq, 1000);
|
|
}
|
|
EXPORT_SYMBOL_GPL(hyperv_stop_tsc_emulation);
|
|
|
|
static inline bool hv_reenlightenment_available(void)
|
|
{
|
|
/*
|
|
* Check for required features and priviliges to make TSC frequency
|
|
* change notifications work.
|
|
*/
|
|
return ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
|
|
ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE &&
|
|
ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT;
|
|
}
|
|
|
|
__visible void __irq_entry hyperv_reenlightenment_intr(struct pt_regs *regs)
|
|
{
|
|
entering_ack_irq();
|
|
|
|
inc_irq_stat(irq_hv_reenlightenment_count);
|
|
|
|
schedule_delayed_work(&hv_reenlightenment_work, HZ/10);
|
|
|
|
exiting_irq();
|
|
}
|
|
|
|
void set_hv_tscchange_cb(void (*cb)(void))
|
|
{
|
|
struct hv_reenlightenment_control re_ctrl = {
|
|
.vector = HYPERV_REENLIGHTENMENT_VECTOR,
|
|
.enabled = 1,
|
|
.target_vp = hv_vp_index[smp_processor_id()]
|
|
};
|
|
struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1};
|
|
|
|
if (!hv_reenlightenment_available()) {
|
|
pr_warn("Hyper-V: reenlightenment support is unavailable\n");
|
|
return;
|
|
}
|
|
|
|
hv_reenlightenment_cb = cb;
|
|
|
|
/* Make sure callback is registered before we write to MSRs */
|
|
wmb();
|
|
|
|
wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
|
|
wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
|
|
}
|
|
EXPORT_SYMBOL_GPL(set_hv_tscchange_cb);
|
|
|
|
void clear_hv_tscchange_cb(void)
|
|
{
|
|
struct hv_reenlightenment_control re_ctrl;
|
|
|
|
if (!hv_reenlightenment_available())
|
|
return;
|
|
|
|
rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
|
|
re_ctrl.enabled = 0;
|
|
wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
|
|
|
|
hv_reenlightenment_cb = NULL;
|
|
}
|
|
EXPORT_SYMBOL_GPL(clear_hv_tscchange_cb);
|
|
|
|
static int hv_cpu_die(unsigned int cpu)
|
|
{
|
|
struct hv_reenlightenment_control re_ctrl;
|
|
unsigned int new_cpu;
|
|
unsigned long flags;
|
|
void **input_arg;
|
|
void *input_pg = NULL;
|
|
|
|
local_irq_save(flags);
|
|
input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
|
|
input_pg = *input_arg;
|
|
*input_arg = NULL;
|
|
local_irq_restore(flags);
|
|
free_page((unsigned long)input_pg);
|
|
|
|
if (hv_vp_assist_page && hv_vp_assist_page[cpu])
|
|
wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0);
|
|
|
|
if (hv_reenlightenment_cb == NULL)
|
|
return 0;
|
|
|
|
rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
|
|
if (re_ctrl.target_vp == hv_vp_index[cpu]) {
|
|
/* Reassign to some other online CPU */
|
|
new_cpu = cpumask_any_but(cpu_online_mask, cpu);
|
|
|
|
re_ctrl.target_vp = hv_vp_index[new_cpu];
|
|
wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* This function is to be invoked early in the boot sequence after the
|
|
* hypervisor has been detected.
|
|
*
|
|
* 1. Setup the hypercall page.
|
|
* 2. Register Hyper-V specific clocksource.
|
|
* 3. Setup Hyper-V specific APIC entry points.
|
|
*/
|
|
void __init hyperv_init(void)
|
|
{
|
|
u64 guest_id, required_msrs;
|
|
union hv_x64_msr_hypercall_contents hypercall_msr;
|
|
int cpuhp, i;
|
|
|
|
if (x86_hyper_type != X86_HYPER_MS_HYPERV)
|
|
return;
|
|
|
|
/* Absolutely required MSRs */
|
|
required_msrs = HV_X64_MSR_HYPERCALL_AVAILABLE |
|
|
HV_X64_MSR_VP_INDEX_AVAILABLE;
|
|
|
|
if ((ms_hyperv.features & required_msrs) != required_msrs)
|
|
return;
|
|
|
|
/*
|
|
* Allocate the per-CPU state for the hypercall input arg.
|
|
* If this allocation fails, we will not be able to setup
|
|
* (per-CPU) hypercall input page and thus this failure is
|
|
* fatal on Hyper-V.
|
|
*/
|
|
hyperv_pcpu_input_arg = alloc_percpu(void *);
|
|
|
|
BUG_ON(hyperv_pcpu_input_arg == NULL);
|
|
|
|
/* Allocate percpu VP index */
|
|
hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index),
|
|
GFP_KERNEL);
|
|
if (!hv_vp_index)
|
|
return;
|
|
|
|
for (i = 0; i < num_possible_cpus(); i++)
|
|
hv_vp_index[i] = VP_INVAL;
|
|
|
|
hv_vp_assist_page = kcalloc(num_possible_cpus(),
|
|
sizeof(*hv_vp_assist_page), GFP_KERNEL);
|
|
if (!hv_vp_assist_page) {
|
|
ms_hyperv.hints &= ~HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
|
|
goto free_vp_index;
|
|
}
|
|
|
|
cpuhp = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
|
|
hv_cpu_init, hv_cpu_die);
|
|
if (cpuhp < 0)
|
|
goto free_vp_assist_page;
|
|
|
|
/*
|
|
* Setup the hypercall page and enable hypercalls.
|
|
* 1. Register the guest ID
|
|
* 2. Enable the hypercall and register the hypercall page
|
|
*/
|
|
guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0);
|
|
wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
|
|
|
|
hv_hypercall_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX);
|
|
if (hv_hypercall_pg == NULL) {
|
|
wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
|
|
goto remove_cpuhp_state;
|
|
}
|
|
|
|
rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
|
|
hypercall_msr.enable = 1;
|
|
hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
|
|
wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
|
|
|
|
hv_apic_init();
|
|
|
|
/*
|
|
* Register Hyper-V specific clocksource.
|
|
*/
|
|
#ifdef CONFIG_HYPERV_TSCPAGE
|
|
if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
|
|
union hv_x64_msr_hypercall_contents tsc_msr;
|
|
|
|
tsc_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
|
|
if (!tsc_pg)
|
|
goto register_msr_cs;
|
|
|
|
hyperv_cs = &hyperv_cs_tsc;
|
|
|
|
rdmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
|
|
|
|
tsc_msr.enable = 1;
|
|
tsc_msr.guest_physical_address = vmalloc_to_pfn(tsc_pg);
|
|
|
|
wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
|
|
|
|
hyperv_cs_tsc.archdata.vclock_mode = VCLOCK_HVCLOCK;
|
|
|
|
clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
|
|
return;
|
|
}
|
|
register_msr_cs:
|
|
#endif
|
|
/*
|
|
* For 32 bit guests just use the MSR based mechanism for reading
|
|
* the partition counter.
|
|
*/
|
|
|
|
hyperv_cs = &hyperv_cs_msr;
|
|
if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
|
|
clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
|
|
|
|
return;
|
|
|
|
remove_cpuhp_state:
|
|
cpuhp_remove_state(cpuhp);
|
|
free_vp_assist_page:
|
|
kfree(hv_vp_assist_page);
|
|
hv_vp_assist_page = NULL;
|
|
free_vp_index:
|
|
kfree(hv_vp_index);
|
|
hv_vp_index = NULL;
|
|
}
|
|
|
|
/*
|
|
* This routine is called before kexec/kdump, it does the required cleanup.
|
|
*/
|
|
void hyperv_cleanup(void)
|
|
{
|
|
union hv_x64_msr_hypercall_contents hypercall_msr;
|
|
|
|
/* Reset our OS id */
|
|
wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
|
|
|
|
/* Reset the hypercall page */
|
|
hypercall_msr.as_uint64 = 0;
|
|
wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
|
|
|
|
/* Reset the TSC page */
|
|
hypercall_msr.as_uint64 = 0;
|
|
wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
|
|
}
|
|
EXPORT_SYMBOL_GPL(hyperv_cleanup);
|
|
|
|
void hyperv_report_panic(struct pt_regs *regs, long err)
|
|
{
|
|
static bool panic_reported;
|
|
u64 guest_id;
|
|
|
|
/*
|
|
* We prefer to report panic on 'die' chain as we have proper
|
|
* registers to report, but if we miss it (e.g. on BUG()) we need
|
|
* to report it on 'panic'.
|
|
*/
|
|
if (panic_reported)
|
|
return;
|
|
panic_reported = true;
|
|
|
|
rdmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
|
|
|
|
wrmsrl(HV_X64_MSR_CRASH_P0, err);
|
|
wrmsrl(HV_X64_MSR_CRASH_P1, guest_id);
|
|
wrmsrl(HV_X64_MSR_CRASH_P2, regs->ip);
|
|
wrmsrl(HV_X64_MSR_CRASH_P3, regs->ax);
|
|
wrmsrl(HV_X64_MSR_CRASH_P4, regs->sp);
|
|
|
|
/*
|
|
* Let Hyper-V know there is crash data available
|
|
*/
|
|
wrmsrl(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
|
|
}
|
|
EXPORT_SYMBOL_GPL(hyperv_report_panic);
|
|
|
|
bool hv_is_hyperv_initialized(void)
|
|
{
|
|
union hv_x64_msr_hypercall_contents hypercall_msr;
|
|
|
|
/*
|
|
* Ensure that we're really on Hyper-V, and not a KVM or Xen
|
|
* emulation of Hyper-V
|
|
*/
|
|
if (x86_hyper_type != X86_HYPER_MS_HYPERV)
|
|
return false;
|
|
|
|
/*
|
|
* Verify that earlier initialization succeeded by checking
|
|
* that the hypercall page is setup
|
|
*/
|
|
hypercall_msr.as_uint64 = 0;
|
|
rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
|
|
|
|
return hypercall_msr.enable;
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
|