OpenCloudOS-Kernel/arch/x86/hyperv/hv_init.c

610 lines
16 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* X86 specific Hyper-V initialization code.
*
* Copyright (C) 2016, Microsoft, Inc.
*
* Author : K. Y. Srinivasan <kys@microsoft.com>
*/
#include <linux/efi.h>
#include <linux/types.h>
#include <linux/bitfield.h>
#include <linux/io.h>
x86/hyperv: Reenlightenment notifications support Hyper-V supports Live Migration notification. This is supposed to be used in conjunction with TSC emulation: when a VM is migrated to a host with different TSC frequency for some short period the host emulates the accesses to TSC and sends an interrupt to notify about the event. When the guest is done updating everything it can disable TSC emulation and everything will start working fast again. These notifications weren't required until now as Hyper-V guests are not supposed to use TSC as a clocksource: in Linux the TSC is even marked as unstable on boot. Guests normally use 'tsc page' clocksource and host updates its values on migrations automatically. Things change when with nested virtualization: even when the PV clocksources (kvm-clock or tsc page) are passed through to the nested guests the TSC frequency and frequency changes need to be know.. Hyper-V Top Level Functional Specification (as of v5.0b) wrongly specifies EAX:BIT(12) of CPUID:0x40000009 as the feature identification bit. The right one to check is EAX:BIT(13) of CPUID:0x40000003. I was assured that the fix in on the way. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: kvm@vger.kernel.org Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com> Cc: Roman Kagan <rkagan@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: devel@linuxdriverproject.org Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Cathy Avery <cavery@redhat.com> Cc: Mohammed Gamal <mmorsy@redhat.com> Link: https://lkml.kernel.org/r/20180124132337.30138-4-vkuznets@redhat.com
2018-01-24 21:23:33 +08:00
#include <asm/apic.h>
#include <asm/desc.h>
#include <asm/hypervisor.h>
#include <asm/hyperv-tlfs.h>
#include <asm/mshyperv.h>
#include <asm/idtentry.h>
#include <linux/kexec.h>
#include <linux/version.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/hyperv.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/cpuhotplug.h>
#include <linux/syscore_ops.h>
clocksource/drivers: Continue making Hyper-V clocksource ISA agnostic Continue consolidating Hyper-V clock and timer code into an ISA independent Hyper-V clocksource driver. Move the existing clocksource code under drivers/hv and arch/x86 to the new clocksource driver while separating out the ISA dependencies. Update Hyper-V initialization to call initialization and cleanup routines since the Hyper-V synthetic clock is not independently enumerated in ACPI. Update Hyper-V clocksource users in KVM and VDSO to get definitions from the new include file. No behavior is changed and no new functionality is added. Suggested-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: "bp@alien8.de" <bp@alien8.de> Cc: "will.deacon@arm.com" <will.deacon@arm.com> Cc: "catalin.marinas@arm.com" <catalin.marinas@arm.com> Cc: "mark.rutland@arm.com" <mark.rutland@arm.com> Cc: "linux-arm-kernel@lists.infradead.org" <linux-arm-kernel@lists.infradead.org> Cc: "gregkh@linuxfoundation.org" <gregkh@linuxfoundation.org> Cc: "linux-hyperv@vger.kernel.org" <linux-hyperv@vger.kernel.org> Cc: "olaf@aepfle.de" <olaf@aepfle.de> Cc: "apw@canonical.com" <apw@canonical.com> Cc: "jasowang@redhat.com" <jasowang@redhat.com> Cc: "marcelo.cerri@canonical.com" <marcelo.cerri@canonical.com> Cc: Sunil Muthuswamy <sunilmut@microsoft.com> Cc: KY Srinivasan <kys@microsoft.com> Cc: "sashal@kernel.org" <sashal@kernel.org> Cc: "vincenzo.frascino@arm.com" <vincenzo.frascino@arm.com> Cc: "linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org> Cc: "linux-mips@vger.kernel.org" <linux-mips@vger.kernel.org> Cc: "linux-kselftest@vger.kernel.org" <linux-kselftest@vger.kernel.org> Cc: "arnd@arndb.de" <arnd@arndb.de> Cc: "linux@armlinux.org.uk" <linux@armlinux.org.uk> Cc: "ralf@linux-mips.org" <ralf@linux-mips.org> Cc: "paul.burton@mips.com" <paul.burton@mips.com> Cc: "daniel.lezcano@linaro.org" <daniel.lezcano@linaro.org> Cc: "salyzyn@android.com" <salyzyn@android.com> Cc: "pcc@google.com" <pcc@google.com> Cc: "shuah@kernel.org" <shuah@kernel.org> Cc: "0x7f454c46@gmail.com" <0x7f454c46@gmail.com> Cc: "linux@rasmusvillemoes.dk" <linux@rasmusvillemoes.dk> Cc: "huw@codeweavers.com" <huw@codeweavers.com> Cc: "sfr@canb.auug.org.au" <sfr@canb.auug.org.au> Cc: "pbonzini@redhat.com" <pbonzini@redhat.com> Cc: "rkrcmar@redhat.com" <rkrcmar@redhat.com> Cc: "kvm@vger.kernel.org" <kvm@vger.kernel.org> Link: https://lkml.kernel.org/r/1561955054-1838-3-git-send-email-mikelley@microsoft.com
2019-07-01 12:26:06 +08:00
#include <clocksource/hyperv_timer.h>
#include <linux/highmem.h>
#include <linux/swiotlb.h>
int hyperv_init_cpuhp;
u64 hv_current_partition_id = ~0ull;
EXPORT_SYMBOL_GPL(hv_current_partition_id);
void *hv_hypercall_pg;
EXPORT_SYMBOL_GPL(hv_hypercall_pg);
union hv_ghcb __percpu **hv_ghcb_pg;
/* Storage to save the hypercall page temporarily for hibernation */
static void *hv_hypercall_pg_saved;
struct hv_vp_assist_page **hv_vp_assist_page;
EXPORT_SYMBOL_GPL(hv_vp_assist_page);
static int hyperv_init_ghcb(void)
{
u64 ghcb_gpa;
void *ghcb_va;
void **ghcb_base;
if (!hv_isolation_type_snp())
return 0;
if (!hv_ghcb_pg)
return -EINVAL;
/*
* GHCB page is allocated by paravisor. The address
* returned by MSR_AMD64_SEV_ES_GHCB is above shared
* memory boundary and map it here.
*/
rdmsrl(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);
ghcb_va = memremap(ghcb_gpa, HV_HYP_PAGE_SIZE, MEMREMAP_WB);
if (!ghcb_va)
return -ENOMEM;
ghcb_base = (void **)this_cpu_ptr(hv_ghcb_pg);
*ghcb_base = ghcb_va;
return 0;
}
static int hv_cpu_init(unsigned int cpu)
{
x86/hyperv: fix root partition faults when writing to VP assist page MSR For root partition the VP assist pages are pre-determined by the hypervisor. The root kernel is not allowed to change them to different locations. And thus, we are getting below stack as in current implementation root is trying to perform write to specific MSR. [ 2.778197] unchecked MSR access error: WRMSR to 0x40000073 (tried to write 0x0000000145ac5001) at rIP: 0xffffffff810c1084 (native_write_msr+0x4/0x30) [ 2.784867] Call Trace: [ 2.791507] hv_cpu_init+0xf1/0x1c0 [ 2.798144] ? hyperv_report_panic+0xd0/0xd0 [ 2.804806] cpuhp_invoke_callback+0x11a/0x440 [ 2.811465] ? hv_resume+0x90/0x90 [ 2.818137] cpuhp_issue_call+0x126/0x130 [ 2.824782] __cpuhp_setup_state_cpuslocked+0x102/0x2b0 [ 2.831427] ? hyperv_report_panic+0xd0/0xd0 [ 2.838075] ? hyperv_report_panic+0xd0/0xd0 [ 2.844723] ? hv_resume+0x90/0x90 [ 2.851375] __cpuhp_setup_state+0x3d/0x90 [ 2.858030] hyperv_init+0x14e/0x410 [ 2.864689] ? enable_IR_x2apic+0x190/0x1a0 [ 2.871349] apic_intr_mode_init+0x8b/0x100 [ 2.878017] x86_late_time_init+0x20/0x30 [ 2.884675] start_kernel+0x459/0x4fb [ 2.891329] secondary_startup_64_no_verify+0xb0/0xbb Since the hypervisor already provides the VP assist pages for root partition, we need to memremap the memory from hypervisor for root kernel to use. The mapping is done in hv_cpu_init during bringup and is unmapped in hv_cpu_die during teardown. Signed-off-by: Praveen Kumar <kumarpraveen@linux.microsoft.com> Reviewed-by: Sunil Muthuswamy <sunilmut@microsoft.com> Link: https://lore.kernel.org/r/20210731120519.17154-1-kumarpraveen@linux.microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2021-07-31 20:05:19 +08:00
union hv_vp_assist_msr_contents msr = { 0 };
struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
int ret;
ret = hv_common_cpu_init(cpu);
if (ret)
return ret;
if (!hv_vp_assist_page)
return 0;
x86/hyper-v: Zero out the VP ASSIST PAGE on allocation The VP ASSIST PAGE is an "overlay" page (see Hyper-V TLFS's Section 5.2.1 "GPA Overlay Pages" for the details) and here is an excerpt: "The hypervisor defines several special pages that "overlay" the guest's Guest Physical Addresses (GPA) space. Overlays are addressed GPA but are not included in the normal GPA map maintained internally by the hypervisor. Conceptually, they exist in a separate map that overlays the GPA map. If a page within the GPA space is overlaid, any SPA page mapped to the GPA page is effectively "obscured" and generally unreachable by the virtual processor through processor memory accesses. If an overlay page is disabled, the underlying GPA page is "uncovered", and an existing mapping becomes accessible to the guest." SPA = System Physical Address = the final real physical address. When a CPU (e.g. CPU1) is onlined, hv_cpu_init() allocates the VP ASSIST PAGE and enables the EOI optimization for this CPU by writing the MSR HV_X64_MSR_VP_ASSIST_PAGE. From now on, hvp->apic_assist belongs to the special SPA page, and this CPU *always* uses hvp->apic_assist (which is shared with the hypervisor) to decide if it needs to write the EOI MSR. When a CPU is offlined then on the outgoing CPU: 1. hv_cpu_die() disables the EOI optimizaton for this CPU, and from now on hvp->apic_assist belongs to the original "normal" SPA page; 2. the remaining work of stopping this CPU is done 3. this CPU is completely stopped. Between 1 and 3, this CPU can still receive interrupts (e.g. reschedule IPIs from CPU0, and Local APIC timer interrupts), and this CPU *must* write the EOI MSR for every interrupt received, otherwise the hypervisor may not deliver further interrupts, which may be needed to completely stop the CPU. So, after the EOI optimization is disabled in hv_cpu_die(), it's required that the hvp->apic_assist's bit0 is zero, which is not guaranteed by the current allocation mode because it lacks __GFP_ZERO. As a consequence the bit might be set and interrupt handling would not write the EOI MSR causing interrupt delivery to become stuck. Add the missing __GFP_ZERO to the allocation. Note 1: after the "normal" SPA page is allocted and zeroed out, neither the hypervisor nor the guest writes into the page, so the page remains with zeros. Note 2: see Section 10.3.5 "EOI Assist" for the details of the EOI optimization. When the optimization is enabled, the guest can still write the EOI MSR register irrespective of the "No EOI required" value, but that's slower than the optimized assist based variant. Fixes: ba696429d290 ("x86/hyper-v: Implement EOI assist") Signed-off-by: Dexuan Cui <decui@microsoft.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/ <PU1P153MB0169B716A637FABF07433C04BFCB0@PU1P153MB0169.APCP153.PROD.OUTLOOK.COM
2019-07-19 11:22:35 +08:00
if (!*hvp) {
x86/hyperv: fix root partition faults when writing to VP assist page MSR For root partition the VP assist pages are pre-determined by the hypervisor. The root kernel is not allowed to change them to different locations. And thus, we are getting below stack as in current implementation root is trying to perform write to specific MSR. [ 2.778197] unchecked MSR access error: WRMSR to 0x40000073 (tried to write 0x0000000145ac5001) at rIP: 0xffffffff810c1084 (native_write_msr+0x4/0x30) [ 2.784867] Call Trace: [ 2.791507] hv_cpu_init+0xf1/0x1c0 [ 2.798144] ? hyperv_report_panic+0xd0/0xd0 [ 2.804806] cpuhp_invoke_callback+0x11a/0x440 [ 2.811465] ? hv_resume+0x90/0x90 [ 2.818137] cpuhp_issue_call+0x126/0x130 [ 2.824782] __cpuhp_setup_state_cpuslocked+0x102/0x2b0 [ 2.831427] ? hyperv_report_panic+0xd0/0xd0 [ 2.838075] ? hyperv_report_panic+0xd0/0xd0 [ 2.844723] ? hv_resume+0x90/0x90 [ 2.851375] __cpuhp_setup_state+0x3d/0x90 [ 2.858030] hyperv_init+0x14e/0x410 [ 2.864689] ? enable_IR_x2apic+0x190/0x1a0 [ 2.871349] apic_intr_mode_init+0x8b/0x100 [ 2.878017] x86_late_time_init+0x20/0x30 [ 2.884675] start_kernel+0x459/0x4fb [ 2.891329] secondary_startup_64_no_verify+0xb0/0xbb Since the hypervisor already provides the VP assist pages for root partition, we need to memremap the memory from hypervisor for root kernel to use. The mapping is done in hv_cpu_init during bringup and is unmapped in hv_cpu_die during teardown. Signed-off-by: Praveen Kumar <kumarpraveen@linux.microsoft.com> Reviewed-by: Sunil Muthuswamy <sunilmut@microsoft.com> Link: https://lore.kernel.org/r/20210731120519.17154-1-kumarpraveen@linux.microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2021-07-31 20:05:19 +08:00
if (hv_root_partition) {
/*
* For root partition we get the hypervisor provided VP assist
* page, instead of allocating a new page.
*/
rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
*hvp = memremap(msr.pfn <<
HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT,
PAGE_SIZE, MEMREMAP_WB);
} else {
/*
* The VP assist page is an "overlay" page (see Hyper-V TLFS's
* Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed
* out to make sure we always write the EOI MSR in
* hv_apic_eoi_write() *after* the EOI optimization is disabled
* in hv_cpu_die(), otherwise a CPU may not be stopped in the
* case of CPU offlining and the VM will hang.
*/
*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
if (*hvp)
msr.pfn = vmalloc_to_pfn(*hvp);
}
WARN_ON(!(*hvp));
if (*hvp) {
msr.enable = 1;
wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
}
}
return hyperv_init_ghcb();
}
x86/hyperv: Reenlightenment notifications support Hyper-V supports Live Migration notification. This is supposed to be used in conjunction with TSC emulation: when a VM is migrated to a host with different TSC frequency for some short period the host emulates the accesses to TSC and sends an interrupt to notify about the event. When the guest is done updating everything it can disable TSC emulation and everything will start working fast again. These notifications weren't required until now as Hyper-V guests are not supposed to use TSC as a clocksource: in Linux the TSC is even marked as unstable on boot. Guests normally use 'tsc page' clocksource and host updates its values on migrations automatically. Things change when with nested virtualization: even when the PV clocksources (kvm-clock or tsc page) are passed through to the nested guests the TSC frequency and frequency changes need to be know.. Hyper-V Top Level Functional Specification (as of v5.0b) wrongly specifies EAX:BIT(12) of CPUID:0x40000009 as the feature identification bit. The right one to check is EAX:BIT(13) of CPUID:0x40000003. I was assured that the fix in on the way. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: kvm@vger.kernel.org Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com> Cc: Roman Kagan <rkagan@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: devel@linuxdriverproject.org Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Cathy Avery <cavery@redhat.com> Cc: Mohammed Gamal <mmorsy@redhat.com> Link: https://lkml.kernel.org/r/20180124132337.30138-4-vkuznets@redhat.com
2018-01-24 21:23:33 +08:00
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 privileges to make TSC frequency
x86/hyperv: Reenlightenment notifications support Hyper-V supports Live Migration notification. This is supposed to be used in conjunction with TSC emulation: when a VM is migrated to a host with different TSC frequency for some short period the host emulates the accesses to TSC and sends an interrupt to notify about the event. When the guest is done updating everything it can disable TSC emulation and everything will start working fast again. These notifications weren't required until now as Hyper-V guests are not supposed to use TSC as a clocksource: in Linux the TSC is even marked as unstable on boot. Guests normally use 'tsc page' clocksource and host updates its values on migrations automatically. Things change when with nested virtualization: even when the PV clocksources (kvm-clock or tsc page) are passed through to the nested guests the TSC frequency and frequency changes need to be know.. Hyper-V Top Level Functional Specification (as of v5.0b) wrongly specifies EAX:BIT(12) of CPUID:0x40000009 as the feature identification bit. The right one to check is EAX:BIT(13) of CPUID:0x40000003. I was assured that the fix in on the way. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: kvm@vger.kernel.org Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com> Cc: Roman Kagan <rkagan@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: devel@linuxdriverproject.org Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Cathy Avery <cavery@redhat.com> Cc: Mohammed Gamal <mmorsy@redhat.com> Link: https://lkml.kernel.org/r/20180124132337.30138-4-vkuznets@redhat.com
2018-01-24 21:23:33 +08:00
* change notifications work.
*/
return ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
x86/hyperv: Reenlightenment notifications support Hyper-V supports Live Migration notification. This is supposed to be used in conjunction with TSC emulation: when a VM is migrated to a host with different TSC frequency for some short period the host emulates the accesses to TSC and sends an interrupt to notify about the event. When the guest is done updating everything it can disable TSC emulation and everything will start working fast again. These notifications weren't required until now as Hyper-V guests are not supposed to use TSC as a clocksource: in Linux the TSC is even marked as unstable on boot. Guests normally use 'tsc page' clocksource and host updates its values on migrations automatically. Things change when with nested virtualization: even when the PV clocksources (kvm-clock or tsc page) are passed through to the nested guests the TSC frequency and frequency changes need to be know.. Hyper-V Top Level Functional Specification (as of v5.0b) wrongly specifies EAX:BIT(12) of CPUID:0x40000009 as the feature identification bit. The right one to check is EAX:BIT(13) of CPUID:0x40000003. I was assured that the fix in on the way. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: kvm@vger.kernel.org Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com> Cc: Roman Kagan <rkagan@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: devel@linuxdriverproject.org Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Cathy Avery <cavery@redhat.com> Cc: Mohammed Gamal <mmorsy@redhat.com> Link: https://lkml.kernel.org/r/20180124132337.30138-4-vkuznets@redhat.com
2018-01-24 21:23:33 +08:00
ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE &&
ms_hyperv.features & HV_ACCESS_REENLIGHTENMENT;
x86/hyperv: Reenlightenment notifications support Hyper-V supports Live Migration notification. This is supposed to be used in conjunction with TSC emulation: when a VM is migrated to a host with different TSC frequency for some short period the host emulates the accesses to TSC and sends an interrupt to notify about the event. When the guest is done updating everything it can disable TSC emulation and everything will start working fast again. These notifications weren't required until now as Hyper-V guests are not supposed to use TSC as a clocksource: in Linux the TSC is even marked as unstable on boot. Guests normally use 'tsc page' clocksource and host updates its values on migrations automatically. Things change when with nested virtualization: even when the PV clocksources (kvm-clock or tsc page) are passed through to the nested guests the TSC frequency and frequency changes need to be know.. Hyper-V Top Level Functional Specification (as of v5.0b) wrongly specifies EAX:BIT(12) of CPUID:0x40000009 as the feature identification bit. The right one to check is EAX:BIT(13) of CPUID:0x40000003. I was assured that the fix in on the way. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: kvm@vger.kernel.org Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com> Cc: Roman Kagan <rkagan@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: devel@linuxdriverproject.org Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Cathy Avery <cavery@redhat.com> Cc: Mohammed Gamal <mmorsy@redhat.com> Link: https://lkml.kernel.org/r/20180124132337.30138-4-vkuznets@redhat.com
2018-01-24 21:23:33 +08:00
}
DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_reenlightenment)
x86/hyperv: Reenlightenment notifications support Hyper-V supports Live Migration notification. This is supposed to be used in conjunction with TSC emulation: when a VM is migrated to a host with different TSC frequency for some short period the host emulates the accesses to TSC and sends an interrupt to notify about the event. When the guest is done updating everything it can disable TSC emulation and everything will start working fast again. These notifications weren't required until now as Hyper-V guests are not supposed to use TSC as a clocksource: in Linux the TSC is even marked as unstable on boot. Guests normally use 'tsc page' clocksource and host updates its values on migrations automatically. Things change when with nested virtualization: even when the PV clocksources (kvm-clock or tsc page) are passed through to the nested guests the TSC frequency and frequency changes need to be know.. Hyper-V Top Level Functional Specification (as of v5.0b) wrongly specifies EAX:BIT(12) of CPUID:0x40000009 as the feature identification bit. The right one to check is EAX:BIT(13) of CPUID:0x40000003. I was assured that the fix in on the way. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: kvm@vger.kernel.org Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com> Cc: Roman Kagan <rkagan@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: devel@linuxdriverproject.org Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Cathy Avery <cavery@redhat.com> Cc: Mohammed Gamal <mmorsy@redhat.com> Link: https://lkml.kernel.org/r/20180124132337.30138-4-vkuznets@redhat.com
2018-01-24 21:23:33 +08:00
{
ack_APIC_irq();
inc_irq_stat(irq_hv_reenlightenment_count);
x86/hyperv: Reenlightenment notifications support Hyper-V supports Live Migration notification. This is supposed to be used in conjunction with TSC emulation: when a VM is migrated to a host with different TSC frequency for some short period the host emulates the accesses to TSC and sends an interrupt to notify about the event. When the guest is done updating everything it can disable TSC emulation and everything will start working fast again. These notifications weren't required until now as Hyper-V guests are not supposed to use TSC as a clocksource: in Linux the TSC is even marked as unstable on boot. Guests normally use 'tsc page' clocksource and host updates its values on migrations automatically. Things change when with nested virtualization: even when the PV clocksources (kvm-clock or tsc page) are passed through to the nested guests the TSC frequency and frequency changes need to be know.. Hyper-V Top Level Functional Specification (as of v5.0b) wrongly specifies EAX:BIT(12) of CPUID:0x40000009 as the feature identification bit. The right one to check is EAX:BIT(13) of CPUID:0x40000003. I was assured that the fix in on the way. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: kvm@vger.kernel.org Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com> Cc: Roman Kagan <rkagan@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: devel@linuxdriverproject.org Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Cathy Avery <cavery@redhat.com> Cc: Mohammed Gamal <mmorsy@redhat.com> Link: https://lkml.kernel.org/r/20180124132337.30138-4-vkuznets@redhat.com
2018-01-24 21:23:33 +08:00
schedule_delayed_work(&hv_reenlightenment_work, HZ/10);
}
void set_hv_tscchange_cb(void (*cb)(void))
{
struct hv_reenlightenment_control re_ctrl = {
.vector = HYPERV_REENLIGHTENMENT_VECTOR,
.enabled = 1,
};
struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1};
if (!hv_reenlightenment_available()) {
pr_warn("Hyper-V: reenlightenment support is unavailable\n");
return;
}
if (!hv_vp_index)
return;
x86/hyperv: Reenlightenment notifications support Hyper-V supports Live Migration notification. This is supposed to be used in conjunction with TSC emulation: when a VM is migrated to a host with different TSC frequency for some short period the host emulates the accesses to TSC and sends an interrupt to notify about the event. When the guest is done updating everything it can disable TSC emulation and everything will start working fast again. These notifications weren't required until now as Hyper-V guests are not supposed to use TSC as a clocksource: in Linux the TSC is even marked as unstable on boot. Guests normally use 'tsc page' clocksource and host updates its values on migrations automatically. Things change when with nested virtualization: even when the PV clocksources (kvm-clock or tsc page) are passed through to the nested guests the TSC frequency and frequency changes need to be know.. Hyper-V Top Level Functional Specification (as of v5.0b) wrongly specifies EAX:BIT(12) of CPUID:0x40000009 as the feature identification bit. The right one to check is EAX:BIT(13) of CPUID:0x40000003. I was assured that the fix in on the way. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: kvm@vger.kernel.org Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com> Cc: Roman Kagan <rkagan@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: devel@linuxdriverproject.org Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Cathy Avery <cavery@redhat.com> Cc: Mohammed Gamal <mmorsy@redhat.com> Link: https://lkml.kernel.org/r/20180124132337.30138-4-vkuznets@redhat.com
2018-01-24 21:23:33 +08:00
hv_reenlightenment_cb = cb;
/* Make sure callback is registered before we write to MSRs */
wmb();
2021-10-12 23:50:05 +08:00
re_ctrl.target_vp = hv_vp_index[get_cpu()];
x86/hyperv: Reenlightenment notifications support Hyper-V supports Live Migration notification. This is supposed to be used in conjunction with TSC emulation: when a VM is migrated to a host with different TSC frequency for some short period the host emulates the accesses to TSC and sends an interrupt to notify about the event. When the guest is done updating everything it can disable TSC emulation and everything will start working fast again. These notifications weren't required until now as Hyper-V guests are not supposed to use TSC as a clocksource: in Linux the TSC is even marked as unstable on boot. Guests normally use 'tsc page' clocksource and host updates its values on migrations automatically. Things change when with nested virtualization: even when the PV clocksources (kvm-clock or tsc page) are passed through to the nested guests the TSC frequency and frequency changes need to be know.. Hyper-V Top Level Functional Specification (as of v5.0b) wrongly specifies EAX:BIT(12) of CPUID:0x40000009 as the feature identification bit. The right one to check is EAX:BIT(13) of CPUID:0x40000003. I was assured that the fix in on the way. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: kvm@vger.kernel.org Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com> Cc: Roman Kagan <rkagan@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: devel@linuxdriverproject.org Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Cathy Avery <cavery@redhat.com> Cc: Mohammed Gamal <mmorsy@redhat.com> Link: https://lkml.kernel.org/r/20180124132337.30138-4-vkuznets@redhat.com
2018-01-24 21:23:33 +08:00
wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
2021-10-12 23:50:05 +08:00
put_cpu();
x86/hyperv: Reenlightenment notifications support Hyper-V supports Live Migration notification. This is supposed to be used in conjunction with TSC emulation: when a VM is migrated to a host with different TSC frequency for some short period the host emulates the accesses to TSC and sends an interrupt to notify about the event. When the guest is done updating everything it can disable TSC emulation and everything will start working fast again. These notifications weren't required until now as Hyper-V guests are not supposed to use TSC as a clocksource: in Linux the TSC is even marked as unstable on boot. Guests normally use 'tsc page' clocksource and host updates its values on migrations automatically. Things change when with nested virtualization: even when the PV clocksources (kvm-clock or tsc page) are passed through to the nested guests the TSC frequency and frequency changes need to be know.. Hyper-V Top Level Functional Specification (as of v5.0b) wrongly specifies EAX:BIT(12) of CPUID:0x40000009 as the feature identification bit. The right one to check is EAX:BIT(13) of CPUID:0x40000003. I was assured that the fix in on the way. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: kvm@vger.kernel.org Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com> Cc: Roman Kagan <rkagan@virtuozzo.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: devel@linuxdriverproject.org Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Cathy Avery <cavery@redhat.com> Cc: Mohammed Gamal <mmorsy@redhat.com> Link: https://lkml.kernel.org/r/20180124132337.30138-4-vkuznets@redhat.com
2018-01-24 21:23:33 +08:00
}
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;
void **ghcb_va;
if (hv_ghcb_pg) {
ghcb_va = (void **)this_cpu_ptr(hv_ghcb_pg);
if (*ghcb_va)
memunmap(*ghcb_va);
*ghcb_va = NULL;
}
hv_common_cpu_die(cpu);
x86/hyperv: fix root partition faults when writing to VP assist page MSR For root partition the VP assist pages are pre-determined by the hypervisor. The root kernel is not allowed to change them to different locations. And thus, we are getting below stack as in current implementation root is trying to perform write to specific MSR. [ 2.778197] unchecked MSR access error: WRMSR to 0x40000073 (tried to write 0x0000000145ac5001) at rIP: 0xffffffff810c1084 (native_write_msr+0x4/0x30) [ 2.784867] Call Trace: [ 2.791507] hv_cpu_init+0xf1/0x1c0 [ 2.798144] ? hyperv_report_panic+0xd0/0xd0 [ 2.804806] cpuhp_invoke_callback+0x11a/0x440 [ 2.811465] ? hv_resume+0x90/0x90 [ 2.818137] cpuhp_issue_call+0x126/0x130 [ 2.824782] __cpuhp_setup_state_cpuslocked+0x102/0x2b0 [ 2.831427] ? hyperv_report_panic+0xd0/0xd0 [ 2.838075] ? hyperv_report_panic+0xd0/0xd0 [ 2.844723] ? hv_resume+0x90/0x90 [ 2.851375] __cpuhp_setup_state+0x3d/0x90 [ 2.858030] hyperv_init+0x14e/0x410 [ 2.864689] ? enable_IR_x2apic+0x190/0x1a0 [ 2.871349] apic_intr_mode_init+0x8b/0x100 [ 2.878017] x86_late_time_init+0x20/0x30 [ 2.884675] start_kernel+0x459/0x4fb [ 2.891329] secondary_startup_64_no_verify+0xb0/0xbb Since the hypervisor already provides the VP assist pages for root partition, we need to memremap the memory from hypervisor for root kernel to use. The mapping is done in hv_cpu_init during bringup and is unmapped in hv_cpu_die during teardown. Signed-off-by: Praveen Kumar <kumarpraveen@linux.microsoft.com> Reviewed-by: Sunil Muthuswamy <sunilmut@microsoft.com> Link: https://lore.kernel.org/r/20210731120519.17154-1-kumarpraveen@linux.microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2021-07-31 20:05:19 +08:00
if (hv_vp_assist_page && hv_vp_assist_page[cpu]) {
union hv_vp_assist_msr_contents msr = { 0 };
if (hv_root_partition) {
/*
* For root partition the VP assist page is mapped to
* hypervisor provided page, and thus we unmap the
* page here and nullify it, so that in future we have
* correct page address mapped in hv_cpu_init.
*/
memunmap(hv_vp_assist_page[cpu]);
hv_vp_assist_page[cpu] = NULL;
rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
msr.enable = 0;
}
wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
}
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 reenlightenment notifications to some other online
* CPU or just disable the feature if there are no online CPUs
* left (happens on hibernation).
*/
new_cpu = cpumask_any_but(cpu_online_mask, cpu);
if (new_cpu < nr_cpu_ids)
re_ctrl.target_vp = hv_vp_index[new_cpu];
else
re_ctrl.enabled = 0;
wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
}
return 0;
}
static int __init hv_pci_init(void)
{
int gen2vm = efi_enabled(EFI_BOOT);
/*
* For Generation-2 VM, we exit from pci_arch_init() by returning 0.
* The purpose is to suppress the harmless warning:
* "PCI: Fatal: No config space access function found"
*/
if (gen2vm)
return 0;
/* For Generation-1 VM, we'll proceed in pci_arch_init(). */
return 1;
}
static int hv_suspend(void)
{
union hv_x64_msr_hypercall_contents hypercall_msr;
x86/hyperv: Suspend/resume the VP assist page for hibernation Unlike the other CPUs, CPU0 is never offlined during hibernation, so in the resume path, the "new" kernel's VP assist page is not suspended (i.e. not disabled), and later when we jump to the "old" kernel, the page is not properly re-enabled for CPU0 with the allocated page from the old kernel. So far, the VP assist page is used by hv_apic_eoi_write(), and is also used in the case of nested virtualization (running KVM atop Hyper-V). For hv_apic_eoi_write(), when the page is not properly re-enabled, hvp->apic_assist is always 0, so the HV_X64_MSR_EOI MSR is always written. This is not ideal with respect to performance, but Hyper-V can still correctly handle this according to the Hyper-V spec; nevertheless, Linux still must update the Hyper-V hypervisor with the correct VP assist page to prevent Hyper-V from writing to the stale page, which causes guest memory corruption and consequently may have caused the hangs and triple faults seen during non-boot CPUs resume. Fix the issue by calling hv_cpu_die()/hv_cpu_init() in the syscore ops. Without the fix, hibernation can fail at a rate of 1/300 ~ 1/500. With the fix, hibernation can pass a long-haul test of 2000 runs. In the case of nested virtualization, disabling/reenabling the assist page upon hibernation may be unsafe if there are active L2 guests. It looks KVM should be enhanced to abort the hibernation request if there is any active L2 guest. Fixes: 05bd330a7fd8 ("x86/hyperv: Suspend/resume the hypercall page for hibernation") Cc: stable@vger.kernel.org Signed-off-by: Dexuan Cui <decui@microsoft.com> Link: https://lore.kernel.org/r/1587437171-2472-1-git-send-email-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-21 10:46:11 +08:00
int ret;
if (hv_root_partition)
return -EPERM;
/*
* Reset the hypercall page as it is going to be invalidated
* across hibernation. Setting hv_hypercall_pg to NULL ensures
* that any subsequent hypercall operation fails safely instead of
* crashing due to an access of an invalid page. The hypercall page
* pointer is restored on resume.
*/
hv_hypercall_pg_saved = hv_hypercall_pg;
hv_hypercall_pg = NULL;
/* Disable the hypercall page in the hypervisor */
rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hypercall_msr.enable = 0;
wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
x86/hyperv: Suspend/resume the VP assist page for hibernation Unlike the other CPUs, CPU0 is never offlined during hibernation, so in the resume path, the "new" kernel's VP assist page is not suspended (i.e. not disabled), and later when we jump to the "old" kernel, the page is not properly re-enabled for CPU0 with the allocated page from the old kernel. So far, the VP assist page is used by hv_apic_eoi_write(), and is also used in the case of nested virtualization (running KVM atop Hyper-V). For hv_apic_eoi_write(), when the page is not properly re-enabled, hvp->apic_assist is always 0, so the HV_X64_MSR_EOI MSR is always written. This is not ideal with respect to performance, but Hyper-V can still correctly handle this according to the Hyper-V spec; nevertheless, Linux still must update the Hyper-V hypervisor with the correct VP assist page to prevent Hyper-V from writing to the stale page, which causes guest memory corruption and consequently may have caused the hangs and triple faults seen during non-boot CPUs resume. Fix the issue by calling hv_cpu_die()/hv_cpu_init() in the syscore ops. Without the fix, hibernation can fail at a rate of 1/300 ~ 1/500. With the fix, hibernation can pass a long-haul test of 2000 runs. In the case of nested virtualization, disabling/reenabling the assist page upon hibernation may be unsafe if there are active L2 guests. It looks KVM should be enhanced to abort the hibernation request if there is any active L2 guest. Fixes: 05bd330a7fd8 ("x86/hyperv: Suspend/resume the hypercall page for hibernation") Cc: stable@vger.kernel.org Signed-off-by: Dexuan Cui <decui@microsoft.com> Link: https://lore.kernel.org/r/1587437171-2472-1-git-send-email-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-21 10:46:11 +08:00
ret = hv_cpu_die(0);
return ret;
}
static void hv_resume(void)
{
union hv_x64_msr_hypercall_contents hypercall_msr;
x86/hyperv: Suspend/resume the VP assist page for hibernation Unlike the other CPUs, CPU0 is never offlined during hibernation, so in the resume path, the "new" kernel's VP assist page is not suspended (i.e. not disabled), and later when we jump to the "old" kernel, the page is not properly re-enabled for CPU0 with the allocated page from the old kernel. So far, the VP assist page is used by hv_apic_eoi_write(), and is also used in the case of nested virtualization (running KVM atop Hyper-V). For hv_apic_eoi_write(), when the page is not properly re-enabled, hvp->apic_assist is always 0, so the HV_X64_MSR_EOI MSR is always written. This is not ideal with respect to performance, but Hyper-V can still correctly handle this according to the Hyper-V spec; nevertheless, Linux still must update the Hyper-V hypervisor with the correct VP assist page to prevent Hyper-V from writing to the stale page, which causes guest memory corruption and consequently may have caused the hangs and triple faults seen during non-boot CPUs resume. Fix the issue by calling hv_cpu_die()/hv_cpu_init() in the syscore ops. Without the fix, hibernation can fail at a rate of 1/300 ~ 1/500. With the fix, hibernation can pass a long-haul test of 2000 runs. In the case of nested virtualization, disabling/reenabling the assist page upon hibernation may be unsafe if there are active L2 guests. It looks KVM should be enhanced to abort the hibernation request if there is any active L2 guest. Fixes: 05bd330a7fd8 ("x86/hyperv: Suspend/resume the hypercall page for hibernation") Cc: stable@vger.kernel.org Signed-off-by: Dexuan Cui <decui@microsoft.com> Link: https://lore.kernel.org/r/1587437171-2472-1-git-send-email-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-21 10:46:11 +08:00
int ret;
ret = hv_cpu_init(0);
WARN_ON(ret);
/* Re-enable the hypercall page */
rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hypercall_msr.enable = 1;
hypercall_msr.guest_physical_address =
vmalloc_to_pfn(hv_hypercall_pg_saved);
wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hv_hypercall_pg = hv_hypercall_pg_saved;
hv_hypercall_pg_saved = NULL;
/*
* Reenlightenment notifications are disabled by hv_cpu_die(0),
* reenable them here if hv_reenlightenment_cb was previously set.
*/
if (hv_reenlightenment_cb)
set_hv_tscchange_cb(hv_reenlightenment_cb);
}
x86/hyperv: Suspend/resume the VP assist page for hibernation Unlike the other CPUs, CPU0 is never offlined during hibernation, so in the resume path, the "new" kernel's VP assist page is not suspended (i.e. not disabled), and later when we jump to the "old" kernel, the page is not properly re-enabled for CPU0 with the allocated page from the old kernel. So far, the VP assist page is used by hv_apic_eoi_write(), and is also used in the case of nested virtualization (running KVM atop Hyper-V). For hv_apic_eoi_write(), when the page is not properly re-enabled, hvp->apic_assist is always 0, so the HV_X64_MSR_EOI MSR is always written. This is not ideal with respect to performance, but Hyper-V can still correctly handle this according to the Hyper-V spec; nevertheless, Linux still must update the Hyper-V hypervisor with the correct VP assist page to prevent Hyper-V from writing to the stale page, which causes guest memory corruption and consequently may have caused the hangs and triple faults seen during non-boot CPUs resume. Fix the issue by calling hv_cpu_die()/hv_cpu_init() in the syscore ops. Without the fix, hibernation can fail at a rate of 1/300 ~ 1/500. With the fix, hibernation can pass a long-haul test of 2000 runs. In the case of nested virtualization, disabling/reenabling the assist page upon hibernation may be unsafe if there are active L2 guests. It looks KVM should be enhanced to abort the hibernation request if there is any active L2 guest. Fixes: 05bd330a7fd8 ("x86/hyperv: Suspend/resume the hypercall page for hibernation") Cc: stable@vger.kernel.org Signed-off-by: Dexuan Cui <decui@microsoft.com> Link: https://lore.kernel.org/r/1587437171-2472-1-git-send-email-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2020-04-21 10:46:11 +08:00
/* Note: when the ops are called, only CPU0 is online and IRQs are disabled. */
static struct syscore_ops hv_syscore_ops = {
.suspend = hv_suspend,
.resume = hv_resume,
};
x86/hyperv: Initialize clockevents after LAPIC is initialized With commit 4df4cb9e99f8, the Hyper-V direct-mode STIMER is actually initialized before LAPIC is initialized: see apic_intr_mode_init() x86_platform.apic_post_init() hyperv_init() hv_stimer_alloc() apic_bsp_setup() setup_local_APIC() setup_local_APIC() temporarily disables LAPIC, initializes it and re-eanble it. The direct-mode STIMER depends on LAPIC, and when it's registered, it can be programmed immediately and the timer can fire very soon: hv_stimer_init clockevents_config_and_register clockevents_register_device tick_check_new_device tick_setup_device tick_setup_periodic(), tick_setup_oneshot() clockevents_program_event When the timer fires in the hypervisor, if the LAPIC is in the disabled state, new versions of Hyper-V ignore the event and don't inject the timer interrupt into the VM, and hence the VM hangs when it boots. Note: when the VM starts/reboots, the LAPIC is pre-enabled by the firmware, so the window of LAPIC being temporarily disabled is pretty small, and the issue can only happen once out of 100~200 reboots for a 40-vCPU VM on one dev host, and on another host the issue doesn't reproduce after 2000 reboots. The issue is more noticeable for kdump/kexec, because the LAPIC is disabled by the first kernel, and stays disabled until the kdump/kexec kernel enables it. This is especially an issue to a Generation-2 VM (for which Hyper-V doesn't emulate the PIT timer) when CONFIG_HZ=1000 (rather than CONFIG_HZ=250) is used. Fix the issue by moving hv_stimer_alloc() to a later place where the LAPIC timer is initialized. Fixes: 4df4cb9e99f8 ("x86/hyperv: Initialize clockevents earlier in CPU onlining") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20210116223136.13892-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2021-01-17 06:31:36 +08:00
static void (* __initdata old_setup_percpu_clockev)(void);
static void __init hv_stimer_setup_percpu_clockev(void)
{
/*
* Ignore any errors in setting up stimer clockevents
* as we can run with the LAPIC timer as a fallback.
*/
(void)hv_stimer_alloc(false);
x86/hyperv: Initialize clockevents after LAPIC is initialized With commit 4df4cb9e99f8, the Hyper-V direct-mode STIMER is actually initialized before LAPIC is initialized: see apic_intr_mode_init() x86_platform.apic_post_init() hyperv_init() hv_stimer_alloc() apic_bsp_setup() setup_local_APIC() setup_local_APIC() temporarily disables LAPIC, initializes it and re-eanble it. The direct-mode STIMER depends on LAPIC, and when it's registered, it can be programmed immediately and the timer can fire very soon: hv_stimer_init clockevents_config_and_register clockevents_register_device tick_check_new_device tick_setup_device tick_setup_periodic(), tick_setup_oneshot() clockevents_program_event When the timer fires in the hypervisor, if the LAPIC is in the disabled state, new versions of Hyper-V ignore the event and don't inject the timer interrupt into the VM, and hence the VM hangs when it boots. Note: when the VM starts/reboots, the LAPIC is pre-enabled by the firmware, so the window of LAPIC being temporarily disabled is pretty small, and the issue can only happen once out of 100~200 reboots for a 40-vCPU VM on one dev host, and on another host the issue doesn't reproduce after 2000 reboots. The issue is more noticeable for kdump/kexec, because the LAPIC is disabled by the first kernel, and stays disabled until the kdump/kexec kernel enables it. This is especially an issue to a Generation-2 VM (for which Hyper-V doesn't emulate the PIT timer) when CONFIG_HZ=1000 (rather than CONFIG_HZ=250) is used. Fix the issue by moving hv_stimer_alloc() to a later place where the LAPIC timer is initialized. Fixes: 4df4cb9e99f8 ("x86/hyperv: Initialize clockevents earlier in CPU onlining") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20210116223136.13892-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2021-01-17 06:31:36 +08:00
/*
* Still register the LAPIC timer, because the direct-mode STIMER is
* not supported by old versions of Hyper-V. This also allows users
* to switch to LAPIC timer via /sys, if they want to.
*/
if (old_setup_percpu_clockev)
old_setup_percpu_clockev();
}
static void __init hv_get_partition_id(void)
{
struct hv_get_partition_id *output_page;
u64 status;
unsigned long flags;
local_irq_save(flags);
output_page = *this_cpu_ptr(hyperv_pcpu_output_arg);
status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output_page);
if (!hv_result_success(status)) {
/* No point in proceeding if this failed */
pr_err("Failed to get partition ID: %lld\n", status);
BUG();
}
hv_current_partition_id = output_page->partition_id;
local_irq_restore(flags);
}
/*
* 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;
union hv_x64_msr_hypercall_contents hypercall_msr;
int cpuhp;
if (x86_hyper_type != X86_HYPER_MS_HYPERV)
return;
if (hv_common_init())
return;
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 common_free;
}
if (hv_isolation_type_snp()) {
hv_ghcb_pg = alloc_percpu(union hv_ghcb *);
if (!hv_ghcb_pg)
goto free_vp_assist_page;
}
cpuhp = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
hv_cpu_init, hv_cpu_die);
if (cpuhp < 0)
goto free_ghcb_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);
/* Hyper-V requires to write guest os id via ghcb in SNP IVM. */
hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id);
x86/hyperv: allocate the hypercall page with only read and execute bits Patch series "fix a hyperv W^X violation and remove vmalloc_exec" Dexuan reported a W^X violation due to the fact that the hyper hypercall page due switching it to be allocated using vmalloc_exec. The problem is that PAGE_KERNEL_EXEC as used by vmalloc_exec actually sets writable permissions in the pte. This series fixes the issue by switching to the low-level __vmalloc_node_range interface that allows specifing more detailed permissions instead. It then also open codes the other two callers and removes the somewhat confusing vmalloc_exec interface. Peter noted that the hyper hypercall page allocation also has another long standing issue in that it shouldn't use the full vmalloc but just the module space. This issue is so far theoretical as the allocation is done early in the boot process. I plan to fix it with another bigger series for 5.9. This patch (of 3): Avoid a W^X violation cause by the fact that PAGE_KERNEL_EXEC includes the writable bit. For this resurrect the removed PAGE_KERNEL_RX definition, but as PAGE_KERNEL_ROX to match arm64 and powerpc. Link: http://lkml.kernel.org/r/20200618064307.32739-2-hch@lst.de Fixes: 78bb17f76edc ("x86/hyperv: use vmalloc_exec for the hypercall page") Signed-off-by: Christoph Hellwig <hch@lst.de> Reported-by: Dexuan Cui <decui@microsoft.com> Tested-by: Vitaly Kuznetsov <vkuznets@redhat.com> Acked-by: Wei Liu <wei.liu@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: David Hildenbrand <david@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-26 11:30:40 +08:00
hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START,
VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX,
VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
__builtin_return_address(0));
if (hv_hypercall_pg == NULL)
goto clean_guest_os_id;
rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hypercall_msr.enable = 1;
if (hv_root_partition) {
struct page *pg;
void *src, *dst;
/*
* For the root partition, the hypervisor will set up its
* hypercall page. The hypervisor guarantees it will not show
* up in the root's address space. The root can't change the
* location of the hypercall page.
*
* Order is important here. We must enable the hypercall page
* so it is populated with code, then copy the code to an
* executable page.
*/
wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
pg = vmalloc_to_page(hv_hypercall_pg);
dst = kmap(pg);
src = memremap(hypercall_msr.guest_physical_address << PAGE_SHIFT, PAGE_SIZE,
MEMREMAP_WB);
BUG_ON(!(src && dst));
memcpy(dst, src, HV_HYP_PAGE_SIZE);
memunmap(src);
kunmap(pg);
} else {
hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
}
x86/hyperv: Initialize clockevents earlier in CPU onlining Hyper-V has historically initialized stimer-based clockevents late in the process of onlining a CPU because clockevents depend on stimer interrupts. In the original Hyper-V design, stimer interrupts generate a VMbus message, so the VMbus machinery must be running first, and VMbus can't be initialized until relatively late. On x86/64, LAPIC timer based clockevents are used during early initialization before VMbus and stimer-based clockevents are ready, and again during CPU offlining after the stimer clockevents have been shut down. Unfortunately, this design creates problems when offlining CPUs for hibernation or other purposes. stimer-based clockevents are shut down relatively early in the offlining process, so clockevents_unbind_device() must be used to fallback to the LAPIC-based clockevents for the remainder of the offlining process. Furthermore, the late initialization and early shutdown of stimer-based clockevents doesn't work well on ARM64 since there is no other timer like the LAPIC to fallback to. So CPU onlining and offlining doesn't work properly. Fix this by recognizing that stimer Direct Mode is the normal path for newer versions of Hyper-V on x86/64, and the only path on other architectures. With stimer Direct Mode, stimer interrupts don't require any VMbus machinery. stimer clockevents can be initialized and shut down consistent with how it is done for other clockevent devices. While the old VMbus-based stimer interrupts must still be supported for backward compatibility on x86, that mode of operation can be treated as legacy. So add a new Hyper-V stimer entry in the CPU hotplug state list, and use that new state when in Direct Mode. Update the Hyper-V clocksource driver to allocate and initialize stimer clockevents earlier during boot. Update Hyper-V initialization and the VMbus driver to use this new design. As a result, the LAPIC timer is no longer used during boot or CPU onlining/offlining and clockevents_unbind_device() is not called. But retain the old design as a legacy implementation for older versions of Hyper-V that don't support Direct Mode. Signed-off-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Dexuan Cui <decui@microsoft.com> Link: https://lkml.kernel.org/r/1573607467-9456-1-git-send-email-mikelley@microsoft.com
2019-11-13 09:11:49 +08:00
/*
x86/hyperv: Initialize clockevents after LAPIC is initialized With commit 4df4cb9e99f8, the Hyper-V direct-mode STIMER is actually initialized before LAPIC is initialized: see apic_intr_mode_init() x86_platform.apic_post_init() hyperv_init() hv_stimer_alloc() apic_bsp_setup() setup_local_APIC() setup_local_APIC() temporarily disables LAPIC, initializes it and re-eanble it. The direct-mode STIMER depends on LAPIC, and when it's registered, it can be programmed immediately and the timer can fire very soon: hv_stimer_init clockevents_config_and_register clockevents_register_device tick_check_new_device tick_setup_device tick_setup_periodic(), tick_setup_oneshot() clockevents_program_event When the timer fires in the hypervisor, if the LAPIC is in the disabled state, new versions of Hyper-V ignore the event and don't inject the timer interrupt into the VM, and hence the VM hangs when it boots. Note: when the VM starts/reboots, the LAPIC is pre-enabled by the firmware, so the window of LAPIC being temporarily disabled is pretty small, and the issue can only happen once out of 100~200 reboots for a 40-vCPU VM on one dev host, and on another host the issue doesn't reproduce after 2000 reboots. The issue is more noticeable for kdump/kexec, because the LAPIC is disabled by the first kernel, and stays disabled until the kdump/kexec kernel enables it. This is especially an issue to a Generation-2 VM (for which Hyper-V doesn't emulate the PIT timer) when CONFIG_HZ=1000 (rather than CONFIG_HZ=250) is used. Fix the issue by moving hv_stimer_alloc() to a later place where the LAPIC timer is initialized. Fixes: 4df4cb9e99f8 ("x86/hyperv: Initialize clockevents earlier in CPU onlining") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20210116223136.13892-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2021-01-17 06:31:36 +08:00
* hyperv_init() is called before LAPIC is initialized: see
* apic_intr_mode_init() -> x86_platform.apic_post_init() and
* apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER
* depends on LAPIC, so hv_stimer_alloc() should be called from
* x86_init.timers.setup_percpu_clockev.
x86/hyperv: Initialize clockevents earlier in CPU onlining Hyper-V has historically initialized stimer-based clockevents late in the process of onlining a CPU because clockevents depend on stimer interrupts. In the original Hyper-V design, stimer interrupts generate a VMbus message, so the VMbus machinery must be running first, and VMbus can't be initialized until relatively late. On x86/64, LAPIC timer based clockevents are used during early initialization before VMbus and stimer-based clockevents are ready, and again during CPU offlining after the stimer clockevents have been shut down. Unfortunately, this design creates problems when offlining CPUs for hibernation or other purposes. stimer-based clockevents are shut down relatively early in the offlining process, so clockevents_unbind_device() must be used to fallback to the LAPIC-based clockevents for the remainder of the offlining process. Furthermore, the late initialization and early shutdown of stimer-based clockevents doesn't work well on ARM64 since there is no other timer like the LAPIC to fallback to. So CPU onlining and offlining doesn't work properly. Fix this by recognizing that stimer Direct Mode is the normal path for newer versions of Hyper-V on x86/64, and the only path on other architectures. With stimer Direct Mode, stimer interrupts don't require any VMbus machinery. stimer clockevents can be initialized and shut down consistent with how it is done for other clockevent devices. While the old VMbus-based stimer interrupts must still be supported for backward compatibility on x86, that mode of operation can be treated as legacy. So add a new Hyper-V stimer entry in the CPU hotplug state list, and use that new state when in Direct Mode. Update the Hyper-V clocksource driver to allocate and initialize stimer clockevents earlier during boot. Update Hyper-V initialization and the VMbus driver to use this new design. As a result, the LAPIC timer is no longer used during boot or CPU onlining/offlining and clockevents_unbind_device() is not called. But retain the old design as a legacy implementation for older versions of Hyper-V that don't support Direct Mode. Signed-off-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Dexuan Cui <decui@microsoft.com> Link: https://lkml.kernel.org/r/1573607467-9456-1-git-send-email-mikelley@microsoft.com
2019-11-13 09:11:49 +08:00
*/
x86/hyperv: Initialize clockevents after LAPIC is initialized With commit 4df4cb9e99f8, the Hyper-V direct-mode STIMER is actually initialized before LAPIC is initialized: see apic_intr_mode_init() x86_platform.apic_post_init() hyperv_init() hv_stimer_alloc() apic_bsp_setup() setup_local_APIC() setup_local_APIC() temporarily disables LAPIC, initializes it and re-eanble it. The direct-mode STIMER depends on LAPIC, and when it's registered, it can be programmed immediately and the timer can fire very soon: hv_stimer_init clockevents_config_and_register clockevents_register_device tick_check_new_device tick_setup_device tick_setup_periodic(), tick_setup_oneshot() clockevents_program_event When the timer fires in the hypervisor, if the LAPIC is in the disabled state, new versions of Hyper-V ignore the event and don't inject the timer interrupt into the VM, and hence the VM hangs when it boots. Note: when the VM starts/reboots, the LAPIC is pre-enabled by the firmware, so the window of LAPIC being temporarily disabled is pretty small, and the issue can only happen once out of 100~200 reboots for a 40-vCPU VM on one dev host, and on another host the issue doesn't reproduce after 2000 reboots. The issue is more noticeable for kdump/kexec, because the LAPIC is disabled by the first kernel, and stays disabled until the kdump/kexec kernel enables it. This is especially an issue to a Generation-2 VM (for which Hyper-V doesn't emulate the PIT timer) when CONFIG_HZ=1000 (rather than CONFIG_HZ=250) is used. Fix the issue by moving hv_stimer_alloc() to a later place where the LAPIC timer is initialized. Fixes: 4df4cb9e99f8 ("x86/hyperv: Initialize clockevents earlier in CPU onlining") Signed-off-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20210116223136.13892-1-decui@microsoft.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
2021-01-17 06:31:36 +08:00
old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev;
x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev;
x86/hyperv: Initialize clockevents earlier in CPU onlining Hyper-V has historically initialized stimer-based clockevents late in the process of onlining a CPU because clockevents depend on stimer interrupts. In the original Hyper-V design, stimer interrupts generate a VMbus message, so the VMbus machinery must be running first, and VMbus can't be initialized until relatively late. On x86/64, LAPIC timer based clockevents are used during early initialization before VMbus and stimer-based clockevents are ready, and again during CPU offlining after the stimer clockevents have been shut down. Unfortunately, this design creates problems when offlining CPUs for hibernation or other purposes. stimer-based clockevents are shut down relatively early in the offlining process, so clockevents_unbind_device() must be used to fallback to the LAPIC-based clockevents for the remainder of the offlining process. Furthermore, the late initialization and early shutdown of stimer-based clockevents doesn't work well on ARM64 since there is no other timer like the LAPIC to fallback to. So CPU onlining and offlining doesn't work properly. Fix this by recognizing that stimer Direct Mode is the normal path for newer versions of Hyper-V on x86/64, and the only path on other architectures. With stimer Direct Mode, stimer interrupts don't require any VMbus machinery. stimer clockevents can be initialized and shut down consistent with how it is done for other clockevent devices. While the old VMbus-based stimer interrupts must still be supported for backward compatibility on x86, that mode of operation can be treated as legacy. So add a new Hyper-V stimer entry in the CPU hotplug state list, and use that new state when in Direct Mode. Update the Hyper-V clocksource driver to allocate and initialize stimer clockevents earlier during boot. Update Hyper-V initialization and the VMbus driver to use this new design. As a result, the LAPIC timer is no longer used during boot or CPU onlining/offlining and clockevents_unbind_device() is not called. But retain the old design as a legacy implementation for older versions of Hyper-V that don't support Direct Mode. Signed-off-by: Michael Kelley <mikelley@microsoft.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Dexuan Cui <decui@microsoft.com> Reviewed-by: Dexuan Cui <decui@microsoft.com> Link: https://lkml.kernel.org/r/1573607467-9456-1-git-send-email-mikelley@microsoft.com
2019-11-13 09:11:49 +08:00
hv_apic_init();
x86_init.pci.arch_init = hv_pci_init;
register_syscore_ops(&hv_syscore_ops);
hyperv_init_cpuhp = cpuhp;
if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID)
hv_get_partition_id();
BUG_ON(hv_root_partition && hv_current_partition_id == ~0ull);
#ifdef CONFIG_PCI_MSI
/*
* If we're running as root, we want to create our own PCI MSI domain.
* We can't set this in hv_pci_init because that would be too late.
*/
if (hv_root_partition)
x86_init.irqs.create_pci_msi_domain = hv_create_pci_msi_domain;
#endif
/* Query the VMs extended capability once, so that it can be cached. */
hv_query_ext_cap(0);
#ifdef CONFIG_SWIOTLB
/*
* Swiotlb bounce buffer needs to be mapped in extra address
* space. Map function doesn't work in the early place and so
* call swiotlb_update_mem_attributes() here.
*/
if (hv_is_isolation_supported())
swiotlb_update_mem_attributes();
#endif
return;
clean_guest_os_id:
wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
cpuhp_remove_state(cpuhp);
free_ghcb_page:
free_percpu(hv_ghcb_pg);
free_vp_assist_page:
kfree(hv_vp_assist_page);
hv_vp_assist_page = NULL;
common_free:
hv_common_free();
}
/*
* This routine is called before kexec/kdump, it does the required cleanup.
*/
void hyperv_cleanup(void)
{
union hv_x64_msr_hypercall_contents hypercall_msr;
unregister_syscore_ops(&hv_syscore_ops);
/* Reset our OS id */
wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
x86/hyperv: Fix kernel panic when kexec on HyperV After commit 68bb7bfb7985 ("X86/Hyper-V: Enable IPI enlightenments"), kexec fails with a kernel panic: kexec_core: Starting new kernel BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v3.0 03/02/2018 RIP: 0010:0xffffc9000001d000 Call Trace: ? __send_ipi_mask+0x1c6/0x2d0 ? hv_send_ipi_mask_allbutself+0x6d/0xb0 ? mp_save_irq+0x70/0x70 ? __ioapic_read_entry+0x32/0x50 ? ioapic_read_entry+0x39/0x50 ? clear_IO_APIC_pin+0xb8/0x110 ? native_stop_other_cpus+0x6e/0x170 ? native_machine_shutdown+0x22/0x40 ? kernel_kexec+0x136/0x156 That happens if hypercall based IPIs are used because the hypercall page is reset very early upon kexec reboot, but kexec sends IPIs to stop CPUs, which invokes the hypercall and dereferences the unusable page. To fix his, reset hv_hypercall_pg to NULL before the page is reset to avoid any misuse, IPI sending will fall back to the non hypercall based method. This only happens on kexec / kdump so just setting the pointer to NULL is good enough. Fixes: 68bb7bfb7985 ("X86/Hyper-V: Enable IPI enlightenments") Signed-off-by: Kairui Song <kasong@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Sasha Levin <sashal@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Dave Young <dyoung@redhat.com> Cc: devel@linuxdriverproject.org Link: https://lkml.kernel.org/r/20190306111827.14131-1-kasong@redhat.com
2019-03-06 19:18:27 +08:00
/*
* Reset hypercall page reference before reset the page,
* let hypercall operations fail safely rather than
* panic the kernel for using invalid hypercall page
*/
hv_hypercall_pg = NULL;
/* 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);
}
void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
{
static bool panic_reported;
u64 guest_id;
if (in_die && !panic_on_oops)
return;
/*
* 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);