aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/cpuid.c13
-rw-r--r--arch/x86/kvm/cpuid.h2
-rw-r--r--arch/x86/kvm/debugfs.c23
-rw-r--r--arch/x86/kvm/emulate.c4
-rw-r--r--arch/x86/kvm/hyperv.c5
-rw-r--r--arch/x86/kvm/hyperv.h5
-rw-r--r--arch/x86/kvm/irq.c21
-rw-r--r--arch/x86/kvm/irq.h15
-rw-r--r--arch/x86/kvm/irq_comm.c13
-rw-r--r--arch/x86/kvm/lapic.c6
-rw-r--r--arch/x86/kvm/mmu.c21
-rw-r--r--arch/x86/kvm/mmu_audit.c5
-rw-r--r--arch/x86/kvm/mtrr.c4
-rw-r--r--arch/x86/kvm/page_track.c4
-rw-r--r--arch/x86/kvm/paging_tmpl.h5
-rw-r--r--arch/x86/kvm/pmu.c19
-rw-r--r--arch/x86/kvm/pmu.h3
-rw-r--r--arch/x86/kvm/pmu_amd.c8
-rw-r--r--arch/x86/kvm/svm.c20
-rw-r--r--arch/x86/kvm/vmx/nested.c150
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c31
-rw-r--r--arch/x86/kvm/vmx/vmcs12.h5
-rw-r--r--arch/x86/kvm/vmx/vmx.c31
-rw-r--r--arch/x86/kvm/vmx/vmx.h1
-rw-r--r--arch/x86/kvm/x86.c31
25 files changed, 227 insertions, 218 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 80a642a0143d..4992e7c99588 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Kernel-based Virtual Machine driver for Linux
* cpuid support routines
@@ -6,10 +7,6 @@
*
* Copyright 2011 Red Hat, Inc. and/or its affiliates.
* Copyright IBM Corporation, 2008
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#include <linux/kvm_host.h>
@@ -456,8 +453,9 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
}
break;
}
- /* function 4 has additional index. */
- case 4: {
+ /* functions 4 and 0x8000001d have additional index. */
+ case 4:
+ case 0x8000001d: {
int i, cache_type;
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
@@ -701,8 +699,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
entry->ecx = entry->edx = 0;
break;
case 0x8000001a:
- break;
- case 0x8000001d:
+ case 0x8000001e:
break;
/*Add support for Centaur's CPUID instruction*/
case 0xC0000000:
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 9a327d5b6d1f..d78a61408243 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -47,8 +47,6 @@ static const struct cpuid_reg reverse_cpuid[] = {
[CPUID_8000_0001_ECX] = {0x80000001, 0, CPUID_ECX},
[CPUID_7_0_EBX] = { 7, 0, CPUID_EBX},
[CPUID_D_1_EAX] = { 0xd, 1, CPUID_EAX},
- [CPUID_F_0_EDX] = { 0xf, 0, CPUID_EDX},
- [CPUID_F_1_EDX] = { 0xf, 1, CPUID_EDX},
[CPUID_8000_0008_EBX] = {0x80000008, 0, CPUID_EBX},
[CPUID_6_EAX] = { 6, 0, CPUID_EAX},
[CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX},
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index c19c7ede9bd6..329361b69d5e 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -1,20 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Kernel-based Virtual Machine driver for Linux
*
* Copyright 2016 Red Hat, Inc. and/or its affiliates.
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#include <linux/kvm_host.h>
#include <linux/debugfs.h>
+#include "lapic.h"
bool kvm_arch_has_vcpu_debugfs(void)
{
return true;
}
+static int vcpu_get_timer_advance_ns(void *data, u64 *val)
+{
+ struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
+ *val = vcpu->arch.apic->lapic_timer.timer_advance_ns;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_timer_advance_ns_fops, vcpu_get_timer_advance_ns, NULL, "%llu\n");
+
static int vcpu_get_tsc_offset(void *data, u64 *val)
{
struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
@@ -51,6 +58,14 @@ int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
if (!ret)
return -ENOMEM;
+ if (lapic_in_kernel(vcpu)) {
+ ret = debugfs_create_file("lapic_timer_advance_ns", 0444,
+ vcpu->debugfs_dentry,
+ vcpu, &vcpu_timer_advance_ns_fops);
+ if (!ret)
+ return -ENOMEM;
+ }
+
if (kvm_has_tsc_control) {
ret = debugfs_create_file("tsc-scaling-ratio", 0444,
vcpu->debugfs_dentry,
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index d0d5dd44b4f4..4a387a235424 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/******************************************************************************
* emulate.c
*
@@ -14,9 +15,6 @@
* Avi Kivity <avi@qumranet.com>
* Yaniv Kamay <yaniv@qumranet.com>
*
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
* From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4
*/
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 8ca4b39918e0..a39e38f13029 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* KVM Microsoft Hyper-V emulation
*
@@ -15,10 +16,6 @@
* Amit Shah <amit.shah@qumranet.com>
* Ben-Ami Yassour <benami@il.ibm.com>
* Andrey Smetanin <asmetanin@virtuozzo.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#include "x86.h"
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index fd7cf13a2144..757cb578101c 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* KVM Microsoft Hyper-V emulation
*
@@ -15,10 +16,6 @@
* Amit Shah <amit.shah@qumranet.com>
* Ben-Ami Yassour <benami@il.ibm.com>
* Andrey Smetanin <asmetanin@virtuozzo.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#ifndef __ARCH_X86_KVM_HYPERV_H__
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index faa264822cee..e330e7d125f7 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -1,23 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* irq.c: API for in kernel interrupt controller
* Copyright (c) 2007, Intel Corporation.
* Copyright 2009 Red Hat, Inc. and/or its affiliates.
*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
* Authors:
* Yaozu (Eddie) Dong <Eddie.dong@intel.com>
- *
*/
#include <linux/export.h>
@@ -172,3 +160,10 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
__kvm_migrate_apic_timer(vcpu);
__kvm_migrate_pit_timer(vcpu);
}
+
+bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)
+{
+ bool resample = args->flags & KVM_IRQFD_FLAG_RESAMPLE;
+
+ return resample ? irqchip_kernel(kvm) : irqchip_in_kernel(kvm);
+}
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index d5005cc26521..d6519a3aa959 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* irq.h: in kernel interrupt controller related definitions
* Copyright (c) 2007, Intel Corporation.
*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
* Authors:
* Yaozu (Eddie) Dong <Eddie.dong@intel.com>
- *
*/
#ifndef __IRQ_H
@@ -114,6 +102,7 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
return mode != KVM_IRQCHIP_NONE;
}
+bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 3cc3b2d130a0..924b3bd5a7b7 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* irq_comm.c: Common API for in kernel interrupt controller
* Copyright (c) 2007, Intel Corporation.
*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
* Authors:
* Yaozu (Eddie) Dong <Eddie.dong@intel.com>
*
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4924f83ed4f3..4dabc318adb8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Local APIC virtualization
@@ -13,9 +14,6 @@
* Yaozu (Eddie) Dong <eddie.dong@intel.com>
*
* Based on Xen 3.1 code, Copyright (c) 2004, Intel Corporation.
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
*/
#include <linux/kvm_host.h>
@@ -2341,7 +2339,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
struct kvm_lapic *apic = vcpu->arch.apic;
u32 ppr;
- if (!apic_enabled(apic))
+ if (!kvm_apic_hw_enabled(apic))
return -1;
__apic_update_ppr(apic, &ppr);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 1e9ba81accba..98f6e4f88b04 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Kernel-based Virtual Machine driver for Linux
*
@@ -12,10 +13,6 @@
* Authors:
* Yaniv Kamay <yaniv@qumranet.com>
* Avi Kivity <avi@qumranet.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#include "irq.h"
@@ -5602,14 +5599,18 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
struct page *page;
int i;
- if (tdp_enabled)
- return 0;
-
/*
- * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64.
- * Therefore we need to allocate shadow page tables in the first
- * 4GB of memory, which happens to fit the DMA32 zone.
+ * When using PAE paging, the four PDPTEs are treated as 'root' pages,
+ * while the PDP table is a per-vCPU construct that's allocated at MMU
+ * creation. When emulating 32-bit mode, cr3 is only 32 bits even on
+ * x86_64. Therefore we need to allocate the PDP table in the first
+ * 4GB of memory, which happens to fit the DMA32 zone. Except for
+ * SVM's 32-bit NPT support, TDP paging doesn't use PAE paging and can
+ * skip allocating the PDP table.
*/
+ if (tdp_enabled && kvm_x86_ops->get_tdp_level(vcpu) > PT32E_ROOT_LEVEL)
+ return 0;
+
page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_DMA32);
if (!page)
return -ENOMEM;
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index abac7e208853..ca39f62aabc6 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* mmu_audit.c:
*
@@ -11,10 +12,6 @@
* Avi Kivity <avi@qumranet.com>
* Marcelo Tosatti <mtosatti@redhat.com>
* Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#include <linux/ratelimit.h>
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 9f72cc427158..25ce3edd1872 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* vMTRR implementation
*
@@ -11,9 +12,6 @@
* Marcelo Tosatti <mtosatti@redhat.com>
* Paolo Bonzini <pbonzini@redhat.com>
* Xiao Guangrong <guangrong.xiao@linux.intel.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
*/
#include <linux/kvm_host.h>
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index fd04d462fdae..3521e2d176f2 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Support KVM gust page tracking
*
@@ -8,9 +9,6 @@
*
* Author:
* Xiao Guangrong <guangrong.xiao@linux.intel.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
*/
#include <linux/kvm_host.h>
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 367a47df4ba0..d583bcd119fc 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Kernel-based Virtual Machine driver for Linux
*
@@ -12,10 +13,6 @@
* Authors:
* Yaniv Kamay <yaniv@qumranet.com>
* Avi Kivity <avi@qumranet.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
/*
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index e39741997893..ab73a9a639ae 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Kernel-based Virtual Machine -- Performance Monitoring Unit support
*
@@ -7,10 +8,6 @@
* Avi Kivity <avi@redhat.com>
* Gleb Natapov <gleb@redhat.com>
* Wei Huang <wei@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#include <linux/types.h>
@@ -264,10 +261,10 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
ctr_val = rdtsc();
break;
case VMWARE_BACKDOOR_PMC_REAL_TIME:
- ctr_val = ktime_get_boot_ns();
+ ctr_val = ktime_get_boottime_ns();
break;
case VMWARE_BACKDOOR_PMC_APPARENT_TIME:
- ctr_val = ktime_get_boot_ns() +
+ ctr_val = ktime_get_boottime_ns() +
vcpu->kvm->arch.kvmclock_offset;
break;
default:
@@ -283,7 +280,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
bool fast_mode = idx & (1u << 31);
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct kvm_pmc *pmc;
- u64 ctr_val;
+ u64 mask = fast_mode ? ~0u : ~0ull;
if (!pmu->version)
return 1;
@@ -291,15 +288,11 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
if (is_vmware_backdoor_pmc(idx))
return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
- pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx);
+ pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask);
if (!pmc)
return 1;
- ctr_val = pmc_read_counter(pmc);
- if (fast_mode)
- ctr_val = (u32)ctr_val;
-
- *data = ctr_val;
+ *data = pmc_read_counter(pmc) & mask;
return 0;
}
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index ba8898e1a854..22dff661145a 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -25,7 +25,8 @@ struct kvm_pmu_ops {
unsigned (*find_fixed_event)(int idx);
bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
- struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx);
+ struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx,
+ u64 *mask);
int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx);
bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index 1495a735b38e..c8388389a3b0 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/arch/x86/kvm/pmu_amd.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* KVM PMU support for AMD
*
@@ -6,9 +7,6 @@
* Author:
* Wei Huang <wei@redhat.com>
*
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
* Implementation is based on pmu_intel.c file
*/
#include <linux/types.h>
@@ -186,7 +184,7 @@ static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
}
/* idx is the ECX register of RDPMC instruction */
-static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx)
+static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *mask)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct kvm_pmc *counters;
@@ -269,10 +267,10 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
pmu->reserved_bits = 0xffffffff00200000ull;
+ pmu->version = 1;
/* not applicable to AMD; but clean them to prevent any fall out */
pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
pmu->nr_arch_fixed_counters = 0;
- pmu->version = 0;
pmu->global_status = 0;
}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a849dcb7fbc5..48c865a4e5dd 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Kernel-based Virtual Machine driver for Linux
*
@@ -9,10 +10,6 @@
* Authors:
* Yaniv Kamay <yaniv@qumranet.com>
* Avi Kivity <avi@qumranet.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#define pr_fmt(fmt) "SVM: " fmt
@@ -379,6 +376,9 @@ module_param(vgif, int, 0444);
static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT);
module_param(sev, int, 0444);
+static bool __read_mostly dump_invalid_vmcb = 0;
+module_param(dump_invalid_vmcb, bool, 0644);
+
static u8 rsm_ins_bytes[] = "\x0f\xaa";
static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
@@ -2024,7 +2024,11 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (!kvm_vcpu_apicv_active(vcpu))
return;
- if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT))
+ /*
+ * Since the host physical APIC id is 8 bits,
+ * we can support host APIC ID upto 255.
+ */
+ if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
return;
entry = READ_ONCE(*(svm->avic_physical_id_cache));
@@ -4824,6 +4828,11 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
struct vmcb_control_area *control = &svm->vmcb->control;
struct vmcb_save_area *save = &svm->vmcb->save;
+ if (!dump_invalid_vmcb) {
+ pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
+ return;
+ }
+
pr_err("VMCB Control Area:\n");
pr_err("%-20s%04x\n", "cr_read:", control->intercept_cr & 0xffff);
pr_err("%-20s%04x\n", "cr_write:", control->intercept_cr >> 16);
@@ -4982,7 +4991,6 @@ static int handle_exit(struct kvm_vcpu *vcpu)
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
kvm_run->fail_entry.hardware_entry_failure_reason
= svm->vmcb->control.exit_code;
- pr_err("KVM: FAILED VMRUN WITH VMCB:\n");
dump_vmcb(vcpu);
return 0;
}
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index f1a69117ac0f..46af3a5e9209 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1397,7 +1397,7 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
}
if (unlikely(!(evmcs->hv_clean_fields &
- HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) {
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN))) {
vmcs12->exception_bitmap = evmcs->exception_bitmap;
}
@@ -1437,7 +1437,7 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
}
if (unlikely(!(evmcs->hv_clean_fields &
- HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) {
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1))) {
vmcs12->pin_based_vm_exec_control =
evmcs->pin_based_vm_exec_control;
vmcs12->vm_exit_controls = evmcs->vm_exit_controls;
@@ -2784,14 +2784,13 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
: "cc", "memory"
);
- preempt_enable();
-
if (vmx->msr_autoload.host.nr)
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
if (vmx->msr_autoload.guest.nr)
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
if (vm_fail) {
+ preempt_enable();
WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
VMXERR_ENTRY_INVALID_CONTROL_FIELD);
return 1;
@@ -2803,6 +2802,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
local_irq_enable();
if (hw_breakpoint_active())
set_debugreg(__this_cpu_read(cpu_dr7), 7);
+ preempt_enable();
/*
* A non-failing VMEntry means we somehow entered guest mode with
@@ -5226,40 +5226,42 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12;
struct kvm_nested_state kvm_state = {
.flags = 0,
- .format = 0,
+ .format = KVM_STATE_NESTED_FORMAT_VMX,
.size = sizeof(kvm_state),
- .vmx.vmxon_pa = -1ull,
- .vmx.vmcs_pa = -1ull,
+ .hdr.vmx.vmxon_pa = -1ull,
+ .hdr.vmx.vmcs12_pa = -1ull,
};
+ struct kvm_vmx_nested_state_data __user *user_vmx_nested_state =
+ &user_kvm_nested_state->data.vmx[0];
if (!vcpu)
- return kvm_state.size + 2 * VMCS12_SIZE;
+ return kvm_state.size + sizeof(*user_vmx_nested_state);
vmx = to_vmx(vcpu);
vmcs12 = get_vmcs12(vcpu);
- if (nested_vmx_allowed(vcpu) && vmx->nested.enlightened_vmcs_enabled)
- kvm_state.flags |= KVM_STATE_NESTED_EVMCS;
-
if (nested_vmx_allowed(vcpu) &&
(vmx->nested.vmxon || vmx->nested.smm.vmxon)) {
- kvm_state.vmx.vmxon_pa = vmx->nested.vmxon_ptr;
- kvm_state.vmx.vmcs_pa = vmx->nested.current_vmptr;
+ kvm_state.hdr.vmx.vmxon_pa = vmx->nested.vmxon_ptr;
+ kvm_state.hdr.vmx.vmcs12_pa = vmx->nested.current_vmptr;
if (vmx_has_valid_vmcs12(vcpu)) {
- kvm_state.size += VMCS12_SIZE;
+ kvm_state.size += sizeof(user_vmx_nested_state->vmcs12);
+
+ if (vmx->nested.hv_evmcs)
+ kvm_state.flags |= KVM_STATE_NESTED_EVMCS;
if (is_guest_mode(vcpu) &&
nested_cpu_has_shadow_vmcs(vmcs12) &&
vmcs12->vmcs_link_pointer != -1ull)
- kvm_state.size += VMCS12_SIZE;
+ kvm_state.size += sizeof(user_vmx_nested_state->shadow_vmcs12);
}
if (vmx->nested.smm.vmxon)
- kvm_state.vmx.smm.flags |= KVM_STATE_NESTED_SMM_VMXON;
+ kvm_state.hdr.vmx.smm.flags |= KVM_STATE_NESTED_SMM_VMXON;
if (vmx->nested.smm.guest_mode)
- kvm_state.vmx.smm.flags |= KVM_STATE_NESTED_SMM_GUEST_MODE;
+ kvm_state.hdr.vmx.smm.flags |= KVM_STATE_NESTED_SMM_GUEST_MODE;
if (is_guest_mode(vcpu)) {
kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE;
@@ -5294,16 +5296,19 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
copy_shadow_to_vmcs12(vmx);
}
+ BUILD_BUG_ON(sizeof(user_vmx_nested_state->vmcs12) < VMCS12_SIZE);
+ BUILD_BUG_ON(sizeof(user_vmx_nested_state->shadow_vmcs12) < VMCS12_SIZE);
+
/*
* Copy over the full allocated size of vmcs12 rather than just the size
* of the struct.
*/
- if (copy_to_user(user_kvm_nested_state->data, vmcs12, VMCS12_SIZE))
+ if (copy_to_user(user_vmx_nested_state->vmcs12, vmcs12, VMCS12_SIZE))
return -EFAULT;
if (nested_cpu_has_shadow_vmcs(vmcs12) &&
vmcs12->vmcs_link_pointer != -1ull) {
- if (copy_to_user(user_kvm_nested_state->data + VMCS12_SIZE,
+ if (copy_to_user(user_vmx_nested_state->shadow_vmcs12,
get_shadow_vmcs12(vcpu), VMCS12_SIZE))
return -EFAULT;
}
@@ -5331,33 +5336,44 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12;
u32 exit_qual;
+ struct kvm_vmx_nested_state_data __user *user_vmx_nested_state =
+ &user_kvm_nested_state->data.vmx[0];
int ret;
- if (kvm_state->format != 0)
+ if (kvm_state->format != KVM_STATE_NESTED_FORMAT_VMX)
return -EINVAL;
- if (!nested_vmx_allowed(vcpu))
- return kvm_state->vmx.vmxon_pa == -1ull ? 0 : -EINVAL;
+ if (kvm_state->hdr.vmx.vmxon_pa == -1ull) {
+ if (kvm_state->hdr.vmx.smm.flags)
+ return -EINVAL;
- if (kvm_state->vmx.vmxon_pa == -1ull) {
- if (kvm_state->vmx.smm.flags)
+ if (kvm_state->hdr.vmx.vmcs12_pa != -1ull)
return -EINVAL;
- if (kvm_state->vmx.vmcs_pa != -1ull)
+ /*
+ * KVM_STATE_NESTED_EVMCS used to signal that KVM should
+ * enable eVMCS capability on vCPU. However, since then
+ * code was changed such that flag signals vmcs12 should
+ * be copied into eVMCS in guest memory.
+ *
+ * To preserve backwards compatability, allow user
+ * to set this flag even when there is no VMXON region.
+ */
+ if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS)
+ return -EINVAL;
+ } else {
+ if (!nested_vmx_allowed(vcpu))
return -EINVAL;
- vmx_leave_nested(vcpu);
- return 0;
+ if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa))
+ return -EINVAL;
}
- if (!page_address_valid(vcpu, kvm_state->vmx.vmxon_pa))
- return -EINVAL;
-
- if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
+ if ((kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
return -EINVAL;
- if (kvm_state->vmx.smm.flags &
+ if (kvm_state->hdr.vmx.smm.flags &
~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON))
return -EINVAL;
@@ -5366,21 +5382,26 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
* nor can VMLAUNCH/VMRESUME be pending. Outside SMM, SMM flags
* must be zero.
*/
- if (is_smm(vcpu) ? kvm_state->flags : kvm_state->vmx.smm.flags)
+ if (is_smm(vcpu) ?
+ (kvm_state->flags &
+ (KVM_STATE_NESTED_GUEST_MODE | KVM_STATE_NESTED_RUN_PENDING))
+ : kvm_state->hdr.vmx.smm.flags)
return -EINVAL;
- if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
- !(kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON))
+ if ((kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
+ !(kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON))
return -EINVAL;
+ if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) &&
+ (!nested_vmx_allowed(vcpu) || !vmx->nested.enlightened_vmcs_enabled))
+ return -EINVAL;
+
vmx_leave_nested(vcpu);
- if (kvm_state->vmx.vmxon_pa == -1ull)
- return 0;
- if (kvm_state->flags & KVM_STATE_NESTED_EVMCS)
- nested_enable_evmcs(vcpu, NULL);
+ if (kvm_state->hdr.vmx.vmxon_pa == -1ull)
+ return 0;
- vmx->nested.vmxon_ptr = kvm_state->vmx.vmxon_pa;
+ vmx->nested.vmxon_ptr = kvm_state->hdr.vmx.vmxon_pa;
ret = enter_vmx_operation(vcpu);
if (ret)
return ret;
@@ -5389,12 +5410,12 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12))
return 0;
- if (kvm_state->vmx.vmcs_pa != -1ull) {
- if (kvm_state->vmx.vmcs_pa == kvm_state->vmx.vmxon_pa ||
- !page_address_valid(vcpu, kvm_state->vmx.vmcs_pa))
+ if (kvm_state->hdr.vmx.vmcs12_pa != -1ull) {
+ if (kvm_state->hdr.vmx.vmcs12_pa == kvm_state->hdr.vmx.vmxon_pa ||
+ !page_address_valid(vcpu, kvm_state->hdr.vmx.vmcs12_pa))
return -EINVAL;
- set_current_vmptr(vmx, kvm_state->vmx.vmcs_pa);
+ set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa);
} else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) {
/*
* Sync eVMCS upon entry as we may not have
@@ -5405,16 +5426,16 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
return -EINVAL;
}
- if (kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON) {
+ if (kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON) {
vmx->nested.smm.vmxon = true;
vmx->nested.vmxon = false;
- if (kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE)
+ if (kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE)
vmx->nested.smm.guest_mode = true;
}
vmcs12 = get_vmcs12(vcpu);
- if (copy_from_user(vmcs12, user_kvm_nested_state->data, sizeof(*vmcs12)))
+ if (copy_from_user(vmcs12, user_vmx_nested_state->vmcs12, sizeof(*vmcs12)))
return -EFAULT;
if (vmcs12->hdr.revision_id != VMCS12_REVISION)
@@ -5423,39 +5444,46 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
return 0;
+ vmx->nested.nested_run_pending =
+ !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
+
+ ret = -EINVAL;
if (nested_cpu_has_shadow_vmcs(vmcs12) &&
vmcs12->vmcs_link_pointer != -1ull) {
struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
- if (kvm_state->size < sizeof(*kvm_state) + 2 * sizeof(*vmcs12))
- return -EINVAL;
+ if (kvm_state->size <
+ sizeof(*kvm_state) +
+ sizeof(user_vmx_nested_state->vmcs12) + sizeof(*shadow_vmcs12))
+ goto error_guest_mode;
if (copy_from_user(shadow_vmcs12,
- user_kvm_nested_state->data + VMCS12_SIZE,
- sizeof(*vmcs12)))
- return -EFAULT;
+ user_vmx_nested_state->shadow_vmcs12,
+ sizeof(*shadow_vmcs12))) {
+ ret = -EFAULT;
+ goto error_guest_mode;
+ }
if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION ||
!shadow_vmcs12->hdr.shadow_vmcs)
- return -EINVAL;
+ goto error_guest_mode;
}
if (nested_vmx_check_controls(vcpu, vmcs12) ||
nested_vmx_check_host_state(vcpu, vmcs12) ||
nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual))
- return -EINVAL;
+ goto error_guest_mode;
vmx->nested.dirty_vmcs12 = true;
- vmx->nested.nested_run_pending =
- !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
-
ret = nested_vmx_enter_non_root_mode(vcpu, false);
- if (ret) {
- vmx->nested.nested_run_pending = 0;
- return -EINVAL;
- }
+ if (ret)
+ goto error_guest_mode;
return 0;
+
+error_guest_mode:
+ vmx->nested.nested_run_pending = 0;
+ return ret;
}
void nested_vmx_vcpu_setup(void)
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index f8502c376b37..68d231d49c7a 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* KVM PMU support for Intel CPUs
*
@@ -6,10 +7,6 @@
* Authors:
* Avi Kivity <avi@redhat.com>
* Gleb Natapov <gleb@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#include <linux/types.h>
#include <linux/kvm_host.h>
@@ -126,7 +123,7 @@ static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
}
static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu,
- unsigned idx)
+ unsigned idx, u64 *mask)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
bool fixed = idx & (1u << 30);
@@ -138,6 +135,7 @@ static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu,
if (fixed && idx >= pmu->nr_arch_fixed_counters)
return NULL;
counters = fixed ? pmu->fixed_counters : pmu->gp_counters;
+ *mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP];
return &counters[idx];
}
@@ -183,9 +181,13 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
*data = pmu->global_ovf_ctrl;
return 0;
default:
- if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
- (pmc = get_fixed_pmc(pmu, msr))) {
- *data = pmc_read_counter(pmc);
+ if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) {
+ u64 val = pmc_read_counter(pmc);
+ *data = val & pmu->counter_bitmask[KVM_PMC_GP];
+ return 0;
+ } else if ((pmc = get_fixed_pmc(pmu, msr))) {
+ u64 val = pmc_read_counter(pmc);
+ *data = val & pmu->counter_bitmask[KVM_PMC_FIXED];
return 0;
} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
*data = pmc->eventsel;
@@ -235,11 +237,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
}
break;
default:
- if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
- (pmc = get_fixed_pmc(pmu, msr))) {
- if (!msr_info->host_initiated)
- data = (s64)(s32)data;
- pmc->counter += data - pmc_read_counter(pmc);
+ if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) {
+ if (msr_info->host_initiated)
+ pmc->counter = data;
+ else
+ pmc->counter = (s32)data;
+ return 0;
+ } else if ((pmc = get_fixed_pmc(pmu, msr))) {
+ pmc->counter = data;
return 0;
} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
if (data == pmc->eventsel)
diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
index 3a742428ad17..337718fc8a36 100644
--- a/arch/x86/kvm/vmx/vmcs12.h
+++ b/arch/x86/kvm/vmx/vmcs12.h
@@ -201,9 +201,10 @@ struct __packed vmcs12 {
/*
* VMCS12_SIZE is the number of bytes L1 should allocate for the VMXON region
* and any VMCS region. Although only sizeof(struct vmcs12) are used by the
- * current implementation, 4K are reserved to avoid future complications.
+ * current implementation, 4K are reserved to avoid future complications and
+ * to preserve userspace ABI.
*/
-#define VMCS12_SIZE 0x1000
+#define VMCS12_SIZE KVM_STATE_NESTED_VMX_VMCS_SIZE
/*
* VMCS12_MAX_FIELD_INDEX is the highest index value used in any
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 1ac167614032..d98eac371c0a 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Kernel-based Virtual Machine driver for Linux
*
@@ -10,10 +11,6 @@
* Authors:
* Avi Kivity <avi@qumranet.com>
* Yaniv Kamay <yaniv@qumranet.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#include <linux/frame.h>
@@ -114,6 +111,9 @@ static u64 __read_mostly host_xss;
bool __read_mostly enable_pml = 1;
module_param_named(pml, enable_pml, bool, S_IRUGO);
+static bool __read_mostly dump_invalid_vmcs = 0;
+module_param(dump_invalid_vmcs, bool, 0644);
+
#define MSR_BITMAP_MODE_X2APIC 1
#define MSR_BITMAP_MODE_X2APIC_APICV 2
@@ -5607,15 +5607,24 @@ static void vmx_dump_dtsel(char *name, uint32_t limit)
void dump_vmcs(void)
{
- u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
- u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
- u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
- u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
- u32 secondary_exec_control = 0;
- unsigned long cr4 = vmcs_readl(GUEST_CR4);
- u64 efer = vmcs_read64(GUEST_IA32_EFER);
+ u32 vmentry_ctl, vmexit_ctl;
+ u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control;
+ unsigned long cr4;
+ u64 efer;
int i, n;
+ if (!dump_invalid_vmcs) {
+ pr_warn_ratelimited("set kvm_intel.dump_invalid_vmcs=1 to dump internal KVM state.\n");
+ return;
+ }
+
+ vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
+ vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
+ cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+ pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
+ cr4 = vmcs_readl(GUEST_CR4);
+ efer = vmcs_read64(GUEST_IA32_EFER);
+ secondary_exec_control = 0;
if (cpu_has_secondary_exec_ctrls())
secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 63d37ccce3dc..61128b48c503 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -319,6 +319,7 @@ void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr);
void pt_update_intercept_for_msr(struct vcpu_vmx *vmx);
+void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
#define POSTED_INTR_ON 0
#define POSTED_INTR_SN 1
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 536b78c4af6e..63bb1ee8258e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Kernel-based Virtual Machine driver for Linux
*
@@ -13,10 +14,6 @@
* Yaniv Kamay <yaniv@qumranet.com>
* Amit Shah <amit.shah@qumranet.com>
* Ben-Ami Yassour <benami@il.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#include <linux/kvm_host.h>
@@ -70,6 +67,7 @@
#include <asm/mshyperv.h>
#include <asm/hypervisor.h>
#include <asm/intel_pt.h>
+#include <clocksource/hyperv_timer.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
@@ -143,7 +141,7 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
* tuning, i.e. allows priveleged userspace to set an exact advancement time.
*/
static int __read_mostly lapic_timer_advance_ns = -1;
-module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
+module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR);
static bool __read_mostly vector_hashing = true;
module_param(vector_hashing, bool, S_IRUGO);
@@ -1298,7 +1296,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
u64 efer = msr_info->data;
if (efer & efer_reserved_bits)
- return false;
+ return 1;
if (!msr_info->host_initiated) {
if (!__kvm_valid_efer(vcpu, efer))
@@ -1557,7 +1555,7 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
vcpu->arch.tsc_always_catchup = 1;
return 0;
} else {
- WARN(1, "user requested TSC rate below hardware speed\n");
+ pr_warn_ratelimited("user requested TSC rate below hardware speed\n");
return -1;
}
}
@@ -1567,8 +1565,8 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
user_tsc_khz, tsc_khz);
if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) {
- WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
- user_tsc_khz);
+ pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
+ user_tsc_khz);
return -1;
}
@@ -1731,7 +1729,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
offset = kvm_compute_tsc_offset(vcpu, data);
- ns = ktime_get_boot_ns();
+ ns = ktime_get_boottime_ns();
elapsed = ns - kvm->arch.last_tsc_nsec;
if (vcpu->arch.virtual_tsc_khz) {
@@ -2073,7 +2071,7 @@ u64 get_kvmclock_ns(struct kvm *kvm)
spin_lock(&ka->pvclock_gtod_sync_lock);
if (!ka->use_master_clock) {
spin_unlock(&ka->pvclock_gtod_sync_lock);
- return ktime_get_boot_ns() + ka->kvmclock_offset;
+ return ktime_get_boottime_ns() + ka->kvmclock_offset;
}
hv_clock.tsc_timestamp = ka->master_cycle_now;
@@ -2089,7 +2087,7 @@ u64 get_kvmclock_ns(struct kvm *kvm)
&hv_clock.tsc_to_system_mul);
ret = __pvclock_read_cycles(&hv_clock, rdtsc());
} else
- ret = ktime_get_boot_ns() + ka->kvmclock_offset;
+ ret = ktime_get_boottime_ns() + ka->kvmclock_offset;
put_cpu();
@@ -2188,7 +2186,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
}
if (!use_master_clock) {
host_tsc = rdtsc();
- kernel_ns = ktime_get_boot_ns();
+ kernel_ns = ktime_get_boottime_ns();
}
tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
@@ -3122,6 +3120,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
break;
+ case KVM_CAP_MAX_VCPU_ID:
+ r = KVM_MAX_VCPU_ID;
+ break;
case KVM_CAP_PV_MMU: /* obsolete */
r = 0;
break;
@@ -9015,7 +9016,7 @@ int kvm_arch_hardware_enable(void)
* before any KVM threads can be running. Unfortunately, we can't
* bring the TSCs fully up to date with real time, as we aren't yet far
* enough into CPU bringup that we know how much real time has actually
- * elapsed; our helper function, ktime_get_boot_ns() will be using boot
+ * elapsed; our helper function, ktime_get_boottime_ns() will be using boot
* variables that haven't been updated yet.
*
* So we simply find the maximum observed TSC above, then record the
@@ -9243,7 +9244,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
mutex_init(&kvm->arch.apic_map_lock);
spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
- kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
+ kvm->arch.kvmclock_offset = -ktime_get_boottime_ns();
pvclock_update_vm_gtod_copy(kvm);
kvm->arch.guest_can_read_msr_platform_info = true;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.