summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/coco/sev/Makefile3
-rw-r--r--arch/x86/hyperv/hv_init.c1
-rw-r--r--arch/x86/hyperv/irqdomain.c69
-rw-r--r--arch/x86/hyperv/ivm.c1
-rw-r--r--arch/x86/hyperv/nested.c1
-rw-r--r--arch/x86/include/asm/kvm_host.h7
-rw-r--r--arch/x86/include/asm/mshyperv.h22
-rw-r--r--arch/x86/include/asm/msr-index.h1
-rw-r--r--arch/x86/include/asm/shared/tdx.h1
-rw-r--r--arch/x86/include/uapi/asm/kvm.h8
-rw-r--r--arch/x86/kernel/cpu/amd.c10
-rw-r--r--arch/x86/kvm/hyperv.c5
-rw-r--r--arch/x86/kvm/svm/sev.c12
-rw-r--r--arch/x86/kvm/vmx/tdx.c35
-rw-r--r--arch/x86/kvm/x86.c8
-rw-r--r--arch/x86/kvm/xen.c15
17 files changed, 140 insertions, 61 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5b3362af7d65..8bed9030ad47 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -147,7 +147,7 @@ config X86
select ARCH_WANTS_DYNAMIC_TASK_STRUCT
select ARCH_WANTS_NO_INSTR
select ARCH_WANT_GENERAL_HUGETLB
- select ARCH_WANT_HUGE_PMD_SHARE
+ select ARCH_WANT_HUGE_PMD_SHARE if X86_64
select ARCH_WANT_LD_ORPHAN_WARN
select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP if X86_64
select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if X86_64
diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile
index db3255b979bd..342d79f0ab6a 100644
--- a/arch/x86/coco/sev/Makefile
+++ b/arch/x86/coco/sev/Makefile
@@ -5,5 +5,6 @@ obj-y += core.o sev-nmi.o vc-handle.o
# Clang 14 and older may fail to respect __no_sanitize_undefined when inlining
UBSAN_SANITIZE_sev-nmi.o := n
-# GCC may fail to respect __no_sanitize_address when inlining
+# GCC may fail to respect __no_sanitize_address or __no_kcsan when inlining
KASAN_SANITIZE_sev-nmi.o := n
+KCSAN_SANITIZE_sev-nmi.o := n
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 3d1d3547095a..afdbda2dd7b7 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -34,6 +34,7 @@
#include <linux/syscore_ops.h>
#include <clocksource/hyperv_timer.h>
#include <linux/highmem.h>
+#include <linux/export.h>
void *hv_hypercall_pg;
EXPORT_SYMBOL_GPL(hv_hypercall_pg);
diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
index 31f0d29cbc5e..090f5ac9f492 100644
--- a/arch/x86/hyperv/irqdomain.c
+++ b/arch/x86/hyperv/irqdomain.c
@@ -10,6 +10,7 @@
#include <linux/pci.h>
#include <linux/irq.h>
+#include <linux/export.h>
#include <asm/mshyperv.h>
static int hv_map_interrupt(union hv_device_id device_id, bool level,
@@ -46,7 +47,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
if (nr_bank < 0) {
local_irq_restore(flags);
pr_err("%s: unable to generate VP set\n", __func__);
- return EINVAL;
+ return -EINVAL;
}
intr_desc->target.flags = HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
@@ -66,7 +67,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
if (!hv_result_success(status))
hv_status_err(status, "\n");
- return hv_result(status);
+ return hv_result_to_errno(status);
}
static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry)
@@ -88,7 +89,10 @@ static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry)
status = hv_do_hypercall(HVCALL_UNMAP_DEVICE_INTERRUPT, input, NULL);
local_irq_restore(flags);
- return hv_result(status);
+ if (!hv_result_success(status))
+ hv_status_err(status, "\n");
+
+ return hv_result_to_errno(status);
}
#ifdef CONFIG_PCI_MSI
@@ -169,13 +173,34 @@ static union hv_device_id hv_build_pci_dev_id(struct pci_dev *dev)
return dev_id;
}
-static int hv_map_msi_interrupt(struct pci_dev *dev, int cpu, int vector,
- struct hv_interrupt_entry *entry)
+/**
+ * hv_map_msi_interrupt() - "Map" the MSI IRQ in the hypervisor.
+ * @data: Describes the IRQ
+ * @out_entry: Hypervisor (MSI) interrupt entry (can be NULL)
+ *
+ * Map the IRQ in the hypervisor by issuing a MAP_DEVICE_INTERRUPT hypercall.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_map_msi_interrupt(struct irq_data *data,
+ struct hv_interrupt_entry *out_entry)
{
- union hv_device_id device_id = hv_build_pci_dev_id(dev);
+ struct irq_cfg *cfg = irqd_cfg(data);
+ struct hv_interrupt_entry dummy;
+ union hv_device_id device_id;
+ struct msi_desc *msidesc;
+ struct pci_dev *dev;
+ int cpu;
- return hv_map_interrupt(device_id, false, cpu, vector, entry);
+ msidesc = irq_data_get_msi_desc(data);
+ dev = msi_desc_to_pci_dev(msidesc);
+ device_id = hv_build_pci_dev_id(dev);
+ cpu = cpumask_first(irq_data_get_effective_affinity_mask(data));
+
+ return hv_map_interrupt(device_id, false, cpu, cfg->vector,
+ out_entry ? out_entry : &dummy);
}
+EXPORT_SYMBOL_GPL(hv_map_msi_interrupt);
static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi_msg *msg)
{
@@ -188,13 +213,11 @@ static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi
static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry);
static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
{
+ struct hv_interrupt_entry *stored_entry;
+ struct irq_cfg *cfg = irqd_cfg(data);
struct msi_desc *msidesc;
struct pci_dev *dev;
- struct hv_interrupt_entry out_entry, *stored_entry;
- struct irq_cfg *cfg = irqd_cfg(data);
- const cpumask_t *affinity;
- int cpu;
- u64 status;
+ int ret;
msidesc = irq_data_get_msi_desc(data);
dev = msi_desc_to_pci_dev(msidesc);
@@ -204,9 +227,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
return;
}
- affinity = irq_data_get_effective_affinity_mask(data);
- cpu = cpumask_first_and(affinity, cpu_online_mask);
-
if (data->chip_data) {
/*
* This interrupt is already mapped. Let's unmap first.
@@ -219,14 +239,12 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
stored_entry = data->chip_data;
data->chip_data = NULL;
- status = hv_unmap_msi_interrupt(dev, stored_entry);
+ ret = hv_unmap_msi_interrupt(dev, stored_entry);
kfree(stored_entry);
- if (status != HV_STATUS_SUCCESS) {
- hv_status_debug(status, "failed to unmap\n");
+ if (ret)
return;
- }
}
stored_entry = kzalloc(sizeof(*stored_entry), GFP_ATOMIC);
@@ -235,15 +253,14 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
return;
}
- status = hv_map_msi_interrupt(dev, cpu, cfg->vector, &out_entry);
- if (status != HV_STATUS_SUCCESS) {
+ ret = hv_map_msi_interrupt(data, stored_entry);
+ if (ret) {
kfree(stored_entry);
return;
}
- *stored_entry = out_entry;
data->chip_data = stored_entry;
- entry_to_msi_msg(&out_entry, msg);
+ entry_to_msi_msg(data->chip_data, msg);
return;
}
@@ -257,7 +274,6 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
{
struct hv_interrupt_entry old_entry;
struct msi_msg msg;
- u64 status;
if (!irqd->chip_data) {
pr_debug("%s: no chip data\n!", __func__);
@@ -270,10 +286,7 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
kfree(irqd->chip_data);
irqd->chip_data = NULL;
- status = hv_unmap_msi_interrupt(dev, &old_entry);
-
- if (status != HV_STATUS_SUCCESS)
- hv_status_err(status, "\n");
+ (void)hv_unmap_msi_interrupt(dev, &old_entry);
}
static void hv_msi_free_irq(struct irq_domain *domain,
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index e93a2f488ff7..ade6c665c97e 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -10,6 +10,7 @@
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/cpu.h>
+#include <linux/export.h>
#include <asm/svm.h>
#include <asm/sev.h>
#include <asm/io.h>
diff --git a/arch/x86/hyperv/nested.c b/arch/x86/hyperv/nested.c
index 1083dc8646f9..8ccbb7c4fc27 100644
--- a/arch/x86/hyperv/nested.c
+++ b/arch/x86/hyperv/nested.c
@@ -11,6 +11,7 @@
#include <linux/types.h>
+#include <linux/export.h>
#include <hyperv/hvhdk.h>
#include <asm/mshyperv.h>
#include <asm/tlbflush.h>
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index fb01e456b624..f7af967aa16f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -700,8 +700,13 @@ struct kvm_vcpu_hv {
struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS];
- /* Preallocated buffer for handling hypercalls passing sparse vCPU set */
+ /*
+ * Preallocated buffers for handling hypercalls that pass sparse vCPU
+ * sets (for high vCPU counts, they're too large to comfortably fit on
+ * the stack).
+ */
u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS];
+ DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
struct hv_vp_assist_page vp_assist_page;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index e1752ba47e67..abc4659f5809 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -112,12 +112,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
return hv_status;
}
-/* Hypercall to the L0 hypervisor */
-static inline u64 hv_do_nested_hypercall(u64 control, void *input, void *output)
-{
- return hv_do_hypercall(control | HV_HYPERCALL_NESTED, input, output);
-}
-
/* Fast hypercall with 8 bytes of input and no output */
static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1)
{
@@ -165,13 +159,6 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
return _hv_do_fast_hypercall8(control, input1);
}
-static inline u64 hv_do_fast_nested_hypercall8(u16 code, u64 input1)
-{
- u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
-
- return _hv_do_fast_hypercall8(control, input1);
-}
-
/* Fast hypercall with 16 bytes of input */
static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
{
@@ -223,13 +210,6 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
return _hv_do_fast_hypercall16(control, input1, input2);
}
-static inline u64 hv_do_fast_nested_hypercall16(u16 code, u64 input1, u64 input2)
-{
- u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
-
- return _hv_do_fast_hypercall16(control, input1, input2);
-}
-
extern struct hv_vp_assist_page **hv_vp_assist_page;
static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
@@ -262,6 +242,8 @@ static inline void hv_apic_init(void) {}
struct irq_domain *hv_create_pci_msi_domain(void);
+int hv_map_msi_interrupt(struct irq_data *data,
+ struct hv_interrupt_entry *out_entry);
int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector,
struct hv_interrupt_entry *entry);
int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b7dded3c8113..5cfb5d74dd5f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -628,6 +628,7 @@
#define MSR_AMD64_OSVW_STATUS 0xc0010141
#define MSR_AMD_PPIN_CTL 0xc00102f0
#define MSR_AMD_PPIN 0xc00102f1
+#define MSR_AMD64_CPUID_FN_7 0xc0011002
#define MSR_AMD64_CPUID_FN_1 0xc0011004
#define MSR_AMD64_LS_CFG 0xc0011020
#define MSR_AMD64_DC_CFG 0xc0011022
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index d8525e6ef50a..8bc074c8d7c6 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -72,6 +72,7 @@
#define TDVMCALL_MAP_GPA 0x10001
#define TDVMCALL_GET_QUOTE 0x10002
#define TDVMCALL_REPORT_FATAL_ERROR 0x10003
+#define TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT 0x10004ULL
/*
* TDG.VP.VMCALL Status Codes (returned in R10)
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 6f3499507c5e..0f15d683817d 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -965,7 +965,13 @@ struct kvm_tdx_cmd {
struct kvm_tdx_capabilities {
__u64 supported_attrs;
__u64 supported_xfam;
- __u64 reserved[254];
+
+ __u64 kernel_tdvmcallinfo_1_r11;
+ __u64 user_tdvmcallinfo_1_r11;
+ __u64 kernel_tdvmcallinfo_1_r12;
+ __u64 user_tdvmcallinfo_1_r12;
+
+ __u64 reserved[250];
/* Configurable CPUID bits for userspace */
struct kvm_cpuid2 cpuid;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index b750ac008b78..329ee185d8cc 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -974,6 +974,16 @@ static void init_amd_zen2(struct cpuinfo_x86 *c)
init_spectral_chicken(c);
fix_erratum_1386(c);
zen2_zenbleed_check(c);
+
+ /* Disable RDSEED on AMD Cyan Skillfish because of an error. */
+ if (c->x86_model == 0x47 && c->x86_stepping == 0x0) {
+ clear_cpu_cap(c, X86_FEATURE_RDSEED);
+ msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18);
+ pr_emerg("RDSEED is not reliable on this platform; disabling.\n");
+ }
+
+ /* Correct misconfigured CPUID on some clients. */
+ clear_cpu_cap(c, X86_FEATURE_INVLPGB);
}
static void init_amd_zen3(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 24f0318c50d7..ee27064dd72f 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1979,6 +1979,9 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
goto out_flush_all;
+ if (is_noncanonical_invlpg_address(entries[i], vcpu))
+ continue;
+
/*
* Lower 12 bits of 'address' encode the number of additional
* pages to flush.
@@ -2001,11 +2004,11 @@ out_flush_all:
static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
{
struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ unsigned long *vcpu_mask = hv_vcpu->vcpu_mask;
u64 *sparse_banks = hv_vcpu->sparse_banks;
struct kvm *kvm = vcpu->kvm;
struct hv_tlb_flush_ex flush_ex;
struct hv_tlb_flush flush;
- DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
/*
* Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE'
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 459c3b791fd4..b201f77fcd49 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1971,6 +1971,10 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src)
struct kvm_vcpu *src_vcpu;
unsigned long i;
+ if (src->created_vcpus != atomic_read(&src->online_vcpus) ||
+ dst->created_vcpus != atomic_read(&dst->online_vcpus))
+ return -EBUSY;
+
if (!sev_es_guest(src))
return 0;
@@ -4445,8 +4449,12 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
* the VMSA will be NULL if this vCPU is the destination for intrahost
* migration, and will be copied later.
*/
- if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
- svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+ if (!svm->sev_es.snp_has_guest_vmsa) {
+ if (svm->sev_es.vmsa)
+ svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+ else
+ svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+ }
if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES))
svm->vmcb->control.allowed_sev_features = sev->vmsa_features |
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 1ad20c273f3b..ec79aacc446f 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -173,6 +173,8 @@ static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char i
tdx_clear_unsupported_cpuid(entry);
}
+#define TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT BIT(1)
+
static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
struct kvm_tdx_capabilities *caps)
{
@@ -188,6 +190,9 @@ static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
caps->cpuid.nent = td_conf->num_cpuid_config;
+ caps->user_tdvmcallinfo_1_r11 =
+ TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT;
+
for (i = 0; i < td_conf->num_cpuid_config; i++)
td_init_cpuid_entry2(&caps->cpuid.entries[i], i);
@@ -1530,6 +1535,27 @@ static int tdx_get_quote(struct kvm_vcpu *vcpu)
return 0;
}
+static int tdx_setup_event_notify_interrupt(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ u64 vector = tdx->vp_enter_args.r12;
+
+ if (vector < 32 || vector > 255) {
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
+ }
+
+ vcpu->run->exit_reason = KVM_EXIT_TDX;
+ vcpu->run->tdx.flags = 0;
+ vcpu->run->tdx.nr = TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT;
+ vcpu->run->tdx.setup_event_notify.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+ vcpu->run->tdx.setup_event_notify.vector = vector;
+
+ vcpu->arch.complete_userspace_io = tdx_complete_simple;
+
+ return 0;
+}
+
static int handle_tdvmcall(struct kvm_vcpu *vcpu)
{
switch (tdvmcall_leaf(vcpu)) {
@@ -1541,6 +1567,8 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu)
return tdx_get_td_vm_call_info(vcpu);
case TDVMCALL_GET_QUOTE:
return tdx_get_quote(vcpu);
+ case TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT:
+ return tdx_setup_event_notify_interrupt(vcpu);
default:
break;
}
@@ -2241,25 +2269,26 @@ static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd)
const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf;
struct kvm_tdx_capabilities __user *user_caps;
struct kvm_tdx_capabilities *caps = NULL;
+ u32 nr_user_entries;
int ret = 0;
/* flags is reserved for future use */
if (cmd->flags)
return -EINVAL;
- caps = kmalloc(sizeof(*caps) +
+ caps = kzalloc(sizeof(*caps) +
sizeof(struct kvm_cpuid_entry2) * td_conf->num_cpuid_config,
GFP_KERNEL);
if (!caps)
return -ENOMEM;
user_caps = u64_to_user_ptr(cmd->data);
- if (copy_from_user(caps, user_caps, sizeof(*caps))) {
+ if (get_user(nr_user_entries, &user_caps->cpuid.nent)) {
ret = -EFAULT;
goto out;
}
- if (caps->cpuid.nent < td_conf->num_cpuid_config) {
+ if (nr_user_entries < td_conf->num_cpuid_config) {
ret = -E2BIG;
goto out;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a9d992d5652f..93636f77c42d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3258,9 +3258,11 @@ int kvm_guest_time_update(struct kvm_vcpu *v)
/* With all the info we got, fill in the values */
- if (kvm_caps.has_tsc_control)
+ if (kvm_caps.has_tsc_control) {
tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz,
v->arch.l1_tsc_scaling_ratio);
+ tgt_tsc_khz = tgt_tsc_khz ? : 1;
+ }
if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
@@ -6186,6 +6188,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
u32 user_tsc_khz;
r = -EINVAL;
+
+ if (vcpu->arch.guest_tsc_protected)
+ goto out;
+
user_tsc_khz = (u32)arg;
if (kvm_caps.has_tsc_control &&
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 9b029bb29a16..5fa2cca43653 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1971,8 +1971,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm,
{
struct kvm_vcpu *vcpu;
- if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm))
- return -EINVAL;
+ /*
+ * Don't check for the port being within range of max_evtchn_port().
+ * Userspace can configure what ever targets it likes; events just won't
+ * be delivered if/while the target is invalid, just like userspace can
+ * configure MSIs which target non-existent APICs.
+ *
+ * This allow on Live Migration and Live Update, the IRQ routing table
+ * can be restored *independently* of other things like creating vCPUs,
+ * without imposing an ordering dependency on userspace. In this
+ * particular case, the problematic ordering would be with setting the
+ * Xen 'long mode' flag, which changes max_evtchn_port() to allow 4096
+ * instead of 1024 event channels.
+ */
/* We only support 2 level event channels for now */
if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
generated by cgit (git 2.34.1) at 2025-07-23 09:28:52 +0000