summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/events/amd/core.c3
-rw-r--r--arch/x86/include/asm/intel-family.h2
-rw-r--r--arch/x86/include/asm/sev-common.h3
-rw-r--r--arch/x86/include/asm/svm.h12
-rw-r--r--arch/x86/include/asm/xen/cpuid.h22
-rw-r--r--arch/x86/kernel/acpi/boot.c9
-rw-r--r--arch/x86/kernel/cpu/mce/core.c1
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c12
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c7
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h1
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c25
-rw-r--r--arch/x86/kernel/fpu/xstate.c30
-rw-r--r--arch/x86/kernel/ftrace_64.S2
-rw-r--r--arch/x86/kernel/sev.c26
-rw-r--r--arch/x86/kvm/ioapic.c36
-rw-r--r--arch/x86/kvm/kvm_onhyperv.h5
-rw-r--r--arch/x86/kvm/svm/avic.c37
-rw-r--r--arch/x86/kvm/svm/svm.c37
-rw-r--r--arch/x86/kvm/svm/svm_onhyperv.h15
-rw-r--r--arch/x86/kvm/vmx/nested.c25
-rw-r--r--arch/x86/kvm/vmx/vmenter.S4
-rw-r--r--arch/x86/kvm/vmx/vmx.c12
-rw-r--r--arch/x86/kvm/x86.c14
-rw-r--r--arch/x86/mm/cpu_entry_area.c7
-rw-r--r--arch/x86/mm/mem_encrypt_identity.c3
-rw-r--r--arch/x86/xen/Makefile2
-rw-r--r--arch/x86/xen/enlighten_pv.c3
-rw-r--r--arch/x86/xen/enlighten_pvh.c13
-rw-r--r--arch/x86/xen/time.c7
-rw-r--r--arch/x86/xen/vga.c5
-rw-r--r--arch/x86/xen/xen-ops.h7
31 files changed, 286 insertions, 101 deletions
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 8c45b198b62f..bccea57dee81 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -923,6 +923,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
/* Event overflow */
handled++;
+ status &= ~mask;
perf_sample_data_init(&data, 0, hwc->last_period);
if (!x86_perf_event_set_period(event))
@@ -933,8 +934,6 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
if (perf_event_overflow(event, &data, regs))
x86_pmu_stop(event, 0);
-
- status &= ~mask;
}
/*
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index cbaf174d8efd..b3af2d45bbbb 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -125,6 +125,8 @@
#define INTEL_FAM6_LUNARLAKE_M 0xBD
+#define INTEL_FAM6_ARROWLAKE 0xC6
+
/* "Small Core" Processors (Atom/E-Core) */
#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index b8357d6ecd47..b63be696b776 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -128,8 +128,9 @@ struct snp_psc_desc {
struct psc_entry entries[VMGEXIT_PSC_MAX_ENTRY];
} __packed;
-/* Guest message request error code */
+/* Guest message request error codes */
#define SNP_GUEST_REQ_INVALID_LEN BIT_ULL(32)
+#define SNP_GUEST_REQ_ERR_BUSY BIT_ULL(33)
#define GHCB_MSR_TERM_REQ 0x100
#define GHCB_MSR_TERM_REASON_SET_POS 12
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index cb1ee53ad3b1..770dcf75eaa9 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -261,20 +261,22 @@ enum avic_ipi_failure_cause {
AVIC_IPI_FAILURE_INVALID_BACKING_PAGE,
};
-#define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(9, 0)
+#define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(8, 0)
/*
- * For AVIC, the max index allowed for physical APIC ID
- * table is 0xff (255).
+ * For AVIC, the max index allowed for physical APIC ID table is 0xfe (254), as
+ * 0xff is a broadcast to all CPUs, i.e. can't be targeted individually.
*/
#define AVIC_MAX_PHYSICAL_ID 0XFEULL
/*
- * For x2AVIC, the max index allowed for physical APIC ID
- * table is 0x1ff (511).
+ * For x2AVIC, the max index allowed for physical APIC ID table is 0x1ff (511).
*/
#define X2AVIC_MAX_PHYSICAL_ID 0x1FFUL
+static_assert((AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == AVIC_MAX_PHYSICAL_ID);
+static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_MAX_PHYSICAL_ID);
+
#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF)
#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL
diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h
index 6daa9b0c8d11..a3c29b1496c8 100644
--- a/arch/x86/include/asm/xen/cpuid.h
+++ b/arch/x86/include/asm/xen/cpuid.h
@@ -89,11 +89,21 @@
* Sub-leaf 2: EAX: host tsc frequency in kHz
*/
+#define XEN_CPUID_TSC_EMULATED (1u << 0)
+#define XEN_CPUID_HOST_TSC_RELIABLE (1u << 1)
+#define XEN_CPUID_RDTSCP_INSTR_AVAIL (1u << 2)
+
+#define XEN_CPUID_TSC_MODE_DEFAULT (0)
+#define XEN_CPUID_TSC_MODE_ALWAYS_EMULATE (1u)
+#define XEN_CPUID_TSC_MODE_NEVER_EMULATE (2u)
+#define XEN_CPUID_TSC_MODE_PVRDTSCP (3u)
+
/*
* Leaf 5 (0x40000x04)
* HVM-specific features
* Sub-leaf 0: EAX: Features
* Sub-leaf 0: EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag)
+ * Sub-leaf 0: ECX: domain id (iff EAX has XEN_HVM_CPUID_DOMID_PRESENT flag)
*/
#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0) /* Virtualized APIC registers */
#define XEN_HVM_CPUID_X2APIC_VIRT (1u << 1) /* Virtualized x2APIC accesses */
@@ -102,12 +112,16 @@
#define XEN_HVM_CPUID_VCPU_ID_PRESENT (1u << 3) /* vcpu id is present in EBX */
#define XEN_HVM_CPUID_DOMID_PRESENT (1u << 4) /* domid is present in ECX */
/*
- * Bits 55:49 from the IO-APIC RTE and bits 11:5 from the MSI address can be
- * used to store high bits for the Destination ID. This expands the Destination
- * ID field from 8 to 15 bits, allowing to target APIC IDs up 32768.
+ * With interrupt format set to 0 (non-remappable) bits 55:49 from the
+ * IO-APIC RTE and bits 11:5 from the MSI address can be used to store
+ * high bits for the Destination ID. This expands the Destination ID
+ * field from 8 to 15 bits, allowing to target APIC IDs up 32768.
*/
#define XEN_HVM_CPUID_EXT_DEST_ID (1u << 5)
-/* Per-vCPU event channel upcalls */
+/*
+ * Per-vCPU event channel upcalls work correctly with physical IRQs
+ * bound to event channels.
+ */
#define XEN_HVM_CPUID_UPCALL_VECTOR (1u << 6)
/*
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 1c38174b5f01..0dac4ab5b55b 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -146,7 +146,11 @@ static int __init acpi_parse_madt(struct acpi_table_header *table)
pr_debug("Local APIC address 0x%08x\n", madt->address);
}
- if (madt->header.revision >= 5)
+
+ /* ACPI 6.3 and newer support the online capable bit. */
+ if (acpi_gbl_FADT.header.revision > 6 ||
+ (acpi_gbl_FADT.header.revision == 6 &&
+ acpi_gbl_FADT.minor_revision >= 3))
acpi_support_online_capable = true;
default_acpi_madt_oem_check(madt->header.oem_id,
@@ -193,7 +197,8 @@ static bool __init acpi_is_processor_usable(u32 lapic_flags)
if (lapic_flags & ACPI_MADT_ENABLED)
return true;
- if (acpi_support_online_capable && (lapic_flags & ACPI_MADT_ONLINE_CAPABLE))
+ if (!acpi_support_online_capable ||
+ (lapic_flags & ACPI_MADT_ONLINE_CAPABLE))
return true;
return false;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 7832a69d170e..2eec60f50057 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -2355,6 +2355,7 @@ static void mce_restart(void)
{
mce_timer_delete_all();
on_each_cpu(mce_cpu_restart, NULL, 1);
+ mce_schedule_work();
}
/* Toggle features for corrected errors */
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index f36dc2f796c5..f1197366a97d 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -358,12 +358,16 @@ static void __init ms_hyperv_init_platform(void)
* To mirror what Windows does we should extract CPU management
* features and use the ReservedIdentityBit to detect if Linux is the
* root partition. But that requires negotiating CPU management
- * interface (a process to be finalized).
+ * interface (a process to be finalized). For now, use the privilege
+ * flag as the indicator for running as root.
*
- * For now, use the privilege flag as the indicator for running as
- * root.
+ * Hyper-V should never specify running as root and as a Confidential
+ * VM. But to protect against a compromised/malicious Hyper-V trying
+ * to exploit root behavior to expose Confidential VM memory, ignore
+ * the root partition setting if also a Confidential VM.
*/
- if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_CPU_MANAGEMENT) {
+ if ((ms_hyperv.priv_high & HV_CPU_MANAGEMENT) &&
+ !(ms_hyperv.priv_high & HV_ISOLATION)) {
hv_root_partition = true;
pr_info("Hyper-V: running as root partition\n");
}
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index eb07d4435391..b44c487727d4 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -368,7 +368,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
{
struct resctrl_schema *s;
struct rdtgroup *rdtgrp;
- struct rdt_domain *dom;
struct rdt_resource *r;
char *tok, *resname;
int ret = 0;
@@ -397,10 +396,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
goto out;
}
- list_for_each_entry(s, &resctrl_schema_all, list) {
- list_for_each_entry(dom, &s->res->domains, list)
- memset(dom->staged_config, 0, sizeof(dom->staged_config));
- }
+ rdt_staged_configs_clear();
while ((tok = strsep(&buf, "\n")) != NULL) {
resname = strim(strsep(&tok, ":"));
@@ -445,6 +441,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
}
out:
+ rdt_staged_configs_clear();
rdtgroup_kn_unlock(of->kn);
cpus_read_unlock();
return ret ?: nbytes;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 8edecc5763d8..85ceaf9a31ac 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -555,5 +555,6 @@ void __check_limbo(struct rdt_domain *d, bool force_free);
void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
void __init thread_throttle_mode_init(void);
void __init mbm_config_rftype_init(const char *config);
+void rdt_staged_configs_clear(void);
#endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 884b6e9a7e31..6ad33f355861 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -78,6 +78,19 @@ void rdt_last_cmd_printf(const char *fmt, ...)
va_end(ap);
}
+void rdt_staged_configs_clear(void)
+{
+ struct rdt_resource *r;
+ struct rdt_domain *dom;
+
+ lockdep_assert_held(&rdtgroup_mutex);
+
+ for_each_alloc_capable_rdt_resource(r) {
+ list_for_each_entry(dom, &r->domains, list)
+ memset(dom->staged_config, 0, sizeof(dom->staged_config));
+ }
+}
+
/*
* Trivial allocator for CLOSIDs. Since h/w only supports a small number,
* we can keep a bitmap of free CLOSIDs in a single integer.
@@ -3107,7 +3120,9 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
{
struct resctrl_schema *s;
struct rdt_resource *r;
- int ret;
+ int ret = 0;
+
+ rdt_staged_configs_clear();
list_for_each_entry(s, &resctrl_schema_all, list) {
r = s->res;
@@ -3119,20 +3134,22 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
} else {
ret = rdtgroup_init_cat(s, rdtgrp->closid);
if (ret < 0)
- return ret;
+ goto out;
}
ret = resctrl_arch_update_domains(r, rdtgrp->closid);
if (ret < 0) {
rdt_last_cmd_puts("Failed to initialize allocations\n");
- return ret;
+ goto out;
}
}
rdtgrp->mode = RDT_MODE_SHAREABLE;
- return 0;
+out:
+ rdt_staged_configs_clear();
+ return ret;
}
static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 714166cc25f2..0bab497c9436 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1118,21 +1118,20 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
zerofrom = offsetof(struct xregs_state, extended_state_area);
/*
- * The ptrace buffer is in non-compacted XSAVE format. In
- * non-compacted format disabled features still occupy state space,
- * but there is no state to copy from in the compacted
- * init_fpstate. The gap tracking will zero these states.
- */
- mask = fpstate->user_xfeatures;
-
- /*
- * Dynamic features are not present in init_fpstate. When they are
- * in an all zeros init state, remove those from 'mask' to zero
- * those features in the user buffer instead of retrieving them
- * from init_fpstate.
+ * This 'mask' indicates which states to copy from fpstate.
+ * Those extended states that are not present in fpstate are
+ * either disabled or initialized:
+ *
+ * In non-compacted format, disabled features still occupy
+ * state space but there is no state to copy from in the
+ * compacted init_fpstate. The gap tracking will zero these
+ * states.
+ *
+ * The extended features have an all zeroes init state. Thus,
+ * remove them from 'mask' to zero those features in the user
+ * buffer instead of retrieving them from init_fpstate.
*/
- if (fpu_state_size_dynamic())
- mask &= (header.xfeatures | xinit->header.xcomp_bv);
+ mask = header.xfeatures;
for_each_extended_xfeature(i, mask) {
/*
@@ -1151,9 +1150,8 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
pkru.pkru = pkru_val;
membuf_write(&to, &pkru, sizeof(pkru));
} else {
- copy_feature(header.xfeatures & BIT_ULL(i), &to,
+ membuf_write(&to,
__raw_xsave_addr(xsave, i),
- __raw_xsave_addr(xinit, i),
xstate_sizes[i]);
}
/*
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 1265ad519249..fb4f1e01b64a 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -136,10 +136,12 @@ SYM_TYPED_FUNC_START(ftrace_stub)
RET
SYM_FUNC_END(ftrace_stub)
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
SYM_TYPED_FUNC_START(ftrace_stub_graph)
CALL_DEPTH_ACCOUNT
RET
SYM_FUNC_END(ftrace_stub_graph)
+#endif
#ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 679026a640ef..3f664ab277c4 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -2183,9 +2183,6 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned
struct ghcb *ghcb;
int ret;
- if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
- return -ENODEV;
-
if (!fw_err)
return -EINVAL;
@@ -2212,15 +2209,26 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned
if (ret)
goto e_put;
- if (ghcb->save.sw_exit_info_2) {
- /* Number of expected pages are returned in RBX */
- if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST &&
- ghcb->save.sw_exit_info_2 == SNP_GUEST_REQ_INVALID_LEN)
- input->data_npages = ghcb_get_rbx(ghcb);
+ *fw_err = ghcb->save.sw_exit_info_2;
+ switch (*fw_err) {
+ case 0:
+ break;
- *fw_err = ghcb->save.sw_exit_info_2;
+ case SNP_GUEST_REQ_ERR_BUSY:
+ ret = -EAGAIN;
+ break;
+ case SNP_GUEST_REQ_INVALID_LEN:
+ /* Number of expected pages are returned in RBX */
+ if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST) {
+ input->data_npages = ghcb_get_rbx(ghcb);
+ ret = -ENOSPC;
+ break;
+ }
+ fallthrough;
+ default:
ret = -EIO;
+ break;
}
e_put:
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 042dee556125..995eb5054360 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -368,9 +368,39 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
mask_after = e->fields.mask;
if (mask_before != mask_after)
kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
- if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
- && ioapic->irr & (1 << index))
- ioapic_service(ioapic, index, false);
+ if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG &&
+ ioapic->irr & (1 << index) && !e->fields.mask && !e->fields.remote_irr) {
+ /*
+ * Pending status in irr may be outdated: the IRQ line may have
+ * already been deasserted by a device while the IRQ was masked.
+ * This occurs, for instance, if the interrupt is handled in a
+ * Linux guest as a oneshot interrupt (IRQF_ONESHOT). In this
+ * case the guest acknowledges the interrupt to the device in
+ * its threaded irq handler, i.e. after the EOI but before
+ * unmasking, so at the time of unmasking the IRQ line is
+ * already down but our pending irr bit is still set. In such
+ * cases, injecting this pending interrupt to the guest is
+ * buggy: the guest will receive an extra unwanted interrupt.
+ *
+ * So we need to check here if the IRQ is actually still pending.
+ * As we are generally not able to probe the IRQ line status
+ * directly, we do it through irqfd resampler. Namely, we clear
+ * the pending status and notify the resampler that this interrupt
+ * is done, without actually injecting it into the guest. If the
+ * IRQ line is actually already deasserted, we are done. If it is
+ * still asserted, a new interrupt will be shortly triggered
+ * through irqfd and injected into the guest.
+ *
+ * If, however, it's not possible to resample (no irqfd resampler
+ * registered for this irq), then unconditionally inject this
+ * pending interrupt into the guest, so the guest will not miss
+ * an interrupt, although may get an extra unwanted interrupt.
+ */
+ if (kvm_notify_irqfd_resampler(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index))
+ ioapic->irr &= ~(1 << index);
+ else
+ ioapic_service(ioapic, index, false);
+ }
if (e->fields.delivery_mode == APIC_DM_FIXED) {
struct kvm_lapic_irq irq;
diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h
index 287e98ef9df3..6272dabec02d 100644
--- a/arch/x86/kvm/kvm_onhyperv.h
+++ b/arch/x86/kvm/kvm_onhyperv.h
@@ -12,6 +12,11 @@ int hv_remote_flush_tlb_with_range(struct kvm *kvm,
int hv_remote_flush_tlb(struct kvm *kvm);
void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp);
#else /* !CONFIG_HYPERV */
+static inline int hv_remote_flush_tlb(struct kvm *kvm)
+{
+ return -EOPNOTSUPP;
+}
+
static inline void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp)
{
}
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index ca684979e90d..cfc8ab773025 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -27,19 +27,38 @@
#include "irq.h"
#include "svm.h"
-/* AVIC GATAG is encoded using VM and VCPU IDs */
-#define AVIC_VCPU_ID_BITS 8
-#define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1)
+/*
+ * Encode the arbitrary VM ID and the vCPU's default APIC ID, i.e the vCPU ID,
+ * into the GATag so that KVM can retrieve the correct vCPU from a GALog entry
+ * if an interrupt can't be delivered, e.g. because the vCPU isn't running.
+ *
+ * For the vCPU ID, use however many bits are currently allowed for the max
+ * guest physical APIC ID (limited by the size of the physical ID table), and
+ * use whatever bits remain to assign arbitrary AVIC IDs to VMs. Note, the
+ * size of the GATag is defined by hardware (32 bits), but is an opaque value
+ * as far as hardware is concerned.
+ */
+#define AVIC_VCPU_ID_MASK AVIC_PHYSICAL_MAX_INDEX_MASK
-#define AVIC_VM_ID_BITS 24
-#define AVIC_VM_ID_NR (1 << AVIC_VM_ID_BITS)
-#define AVIC_VM_ID_MASK ((1 << AVIC_VM_ID_BITS) - 1)
+#define AVIC_VM_ID_SHIFT HWEIGHT32(AVIC_PHYSICAL_MAX_INDEX_MASK)
+#define AVIC_VM_ID_MASK (GENMASK(31, AVIC_VM_ID_SHIFT) >> AVIC_VM_ID_SHIFT)
-#define AVIC_GATAG(x, y) (((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \
- (y & AVIC_VCPU_ID_MASK))
-#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK)
+#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VM_ID_SHIFT) & AVIC_VM_ID_MASK)
#define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK)
+#define __AVIC_GATAG(vm_id, vcpu_id) ((((vm_id) & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \
+ ((vcpu_id) & AVIC_VCPU_ID_MASK))
+#define AVIC_GATAG(vm_id, vcpu_id) \
+({ \
+ u32 ga_tag = __AVIC_GATAG(vm_id, vcpu_id); \
+ \
+ WARN_ON_ONCE(AVIC_GATAG_TO_VCPUID(ga_tag) != (vcpu_id)); \
+ WARN_ON_ONCE(AVIC_GATAG_TO_VMID(ga_tag) != (vm_id)); \
+ ga_tag; \
+})
+
+static_assert(__AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_ID_MASK) == -1u);
+
static bool force_avic;
module_param_unsafe(force_avic, bool, 0444);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 252e7f37e4e2..f25bc3cbb250 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3729,7 +3729,7 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu)
svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
}
-static void svm_flush_tlb_current(struct kvm_vcpu *vcpu)
+static void svm_flush_tlb_asid(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -3753,6 +3753,37 @@ static void svm_flush_tlb_current(struct kvm_vcpu *vcpu)
svm->current_vmcb->asid_generation--;
}
+static void svm_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+ hpa_t root_tdp = vcpu->arch.mmu->root.hpa;
+
+ /*
+ * When running on Hyper-V with EnlightenedNptTlb enabled, explicitly
+ * flush the NPT mappings via hypercall as flushing the ASID only
+ * affects virtual to physical mappings, it does not invalidate guest
+ * physical to host physical mappings.
+ */
+ if (svm_hv_is_enlightened_tlb_enabled(vcpu) && VALID_PAGE(root_tdp))
+ hyperv_flush_guest_mapping(root_tdp);
+
+ svm_flush_tlb_asid(vcpu);
+}
+
+static void svm_flush_tlb_all(struct kvm_vcpu *vcpu)
+{
+ /*
+ * When running on Hyper-V with EnlightenedNptTlb enabled, remote TLB
+ * flushes should be routed to hv_remote_flush_tlb() without requesting
+ * a "regular" remote flush. Reaching this point means either there's
+ * a KVM bug or a prior hv_remote_flush_tlb() call failed, both of
+ * which might be fatal to the guest. Yell, but try to recover.
+ */
+ if (WARN_ON_ONCE(svm_hv_is_enlightened_tlb_enabled(vcpu)))
+ hv_remote_flush_tlb(vcpu->kvm);
+
+ svm_flush_tlb_asid(vcpu);
+}
+
static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -4745,10 +4776,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.set_rflags = svm_set_rflags,
.get_if_flag = svm_get_if_flag,
- .flush_tlb_all = svm_flush_tlb_current,
+ .flush_tlb_all = svm_flush_tlb_all,
.flush_tlb_current = svm_flush_tlb_current,
.flush_tlb_gva = svm_flush_tlb_gva,
- .flush_tlb_guest = svm_flush_tlb_current,
+ .flush_tlb_guest = svm_flush_tlb_asid,
.vcpu_pre_run = svm_vcpu_pre_run,
.vcpu_run = svm_vcpu_run,
diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h
index cff838f15db5..786d46d73a8e 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.h
+++ b/arch/x86/kvm/svm/svm_onhyperv.h
@@ -6,6 +6,8 @@
#ifndef __ARCH_X86_KVM_SVM_ONHYPERV_H__
#define __ARCH_X86_KVM_SVM_ONHYPERV_H__
+#include <asm/mshyperv.h>
+
#if IS_ENABLED(CONFIG_HYPERV)
#include "kvm_onhyperv.h"
@@ -15,6 +17,14 @@ static struct kvm_x86_ops svm_x86_ops;
int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu);
+static inline bool svm_hv_is_enlightened_tlb_enabled(struct kvm_vcpu *vcpu)
+{
+ struct hv_vmcb_enlightenments *hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments;
+
+ return ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB &&
+ !!hve->hv_enlightenments_control.enlightened_npt_tlb;
+}
+
static inline void svm_hv_init_vmcb(struct vmcb *vmcb)
{
struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments;
@@ -80,6 +90,11 @@ static inline void svm_hv_update_vp_id(struct vmcb *vmcb, struct kvm_vcpu *vcpu)
}
#else
+static inline bool svm_hv_is_enlightened_tlb_enabled(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
static inline void svm_hv_init_vmcb(struct vmcb *vmcb)
{
}
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7c4f5ca405c7..768487611db7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2903,7 +2903,7 @@ static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
- bool ia32e;
+ bool ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) ||
CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) ||
@@ -2923,12 +2923,6 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
vmcs12->host_ia32_perf_global_ctrl)))
return -EINVAL;
-#ifdef CONFIG_X86_64
- ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
-#else
- ia32e = false;
-#endif
-
if (ia32e) {
if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
return -EINVAL;
@@ -3022,7 +3016,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12,
enum vm_entry_failure_code *entry_failure_code)
{
- bool ia32e;
+ bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE);
*entry_failure_code = ENTRY_FAIL_DEFAULT;
@@ -3048,6 +3042,13 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
vmcs12->guest_ia32_perf_global_ctrl)))
return -EINVAL;
+ if (CC((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG))
+ return -EINVAL;
+
+ if (CC(ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) ||
+ CC(ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG)))
+ return -EINVAL;
+
/*
* If the load IA32_EFER VM-entry control is 1, the following checks
* are performed on the field for the IA32_EFER MSR:
@@ -3059,7 +3060,6 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
*/
if (to_vmx(vcpu)->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) {
- ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0;
if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) ||
CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) ||
CC(((vmcs12->guest_cr0 & X86_CR0_PG) &&
@@ -3868,7 +3868,12 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu)
exit_qual = 0;
}
- if (ex->has_error_code) {
+ /*
+ * Unlike AMD's Paged Real Mode, which reports an error code on #PF
+ * VM-Exits even if the CPU is in Real Mode, Intel VMX never sets the
+ * "has error code" flags on VM-Exit if the CPU is in Real Mode.
+ */
+ if (ex->has_error_code && is_protmode(vcpu)) {
/*
* Intel CPUs do not generate error codes with bits 31:16 set,
* and more importantly VMX disallows setting bits 31:16 in the
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index f550540ed54e..631fd7da2bc3 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -262,7 +262,7 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
* eIBRS has its own protection against poisoned RSB, so it doesn't
* need the RSB filling sequence. But it does need to be enabled, and a
* single call to retire, before the first unbalanced RET.
- */
+ */
FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\
X86_FEATURE_RSB_VMEXIT_LITE
@@ -311,7 +311,7 @@ SYM_FUNC_END(vmx_do_nmi_irqoff)
* vmread_error_trampoline - Trampoline from inline asm to vmread_error()
* @field: VMCS field encoding that failed
* @fault: %true if the VMREAD faulted, %false if it failed
-
+ *
* Save and restore volatile registers across a call to vmread_error(). Note,
* all parameters are passed on the stack.
*/
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index bcac3efcde41..d2d6e1b6c788 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -874,7 +874,7 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu)
*/
if (is_guest_mode(vcpu))
eb |= get_vmcs12(vcpu)->exception_bitmap;
- else {
+ else {
int mask = 0, match = 0;
if (enable_ept && (eb & (1u << PF_VECTOR))) {
@@ -1282,7 +1282,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
}
}
- if (vmx->nested.need_vmcs12_to_shadow_sync)
+ if (vmx->nested.need_vmcs12_to_shadow_sync)
nested_sync_vmcs12_to_shadow(vcpu);
if (vmx->guest_state_loaded)
@@ -5049,10 +5049,10 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
if (to_vmx(vcpu)->nested.nested_run_pending)
return -EBUSY;
- /*
- * An IRQ must not be injected into L2 if it's supposed to VM-Exit,
- * e.g. if the IRQ arrived asynchronously after checking nested events.
- */
+ /*
+ * An IRQ must not be injected into L2 if it's supposed to VM-Exit,
+ * e.g. if the IRQ arrived asynchronously after checking nested events.
+ */
if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
return -EBUSY;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7713420abab0..3d852ce84920 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4432,6 +4432,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_VAPIC:
case KVM_CAP_ENABLE_CAP:
case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
+ case KVM_CAP_IRQFD_RESAMPLE:
r = 1;
break;
case KVM_CAP_EXIT_HYPERCALL:
@@ -8903,6 +8904,8 @@ restart:
}
if (ctxt->have_exception) {
+ WARN_ON_ONCE(vcpu->mmio_needed && !vcpu->mmio_is_write);
+ vcpu->mmio_needed = false;
r = 1;
inject_emulated_exception(vcpu);
} else if (vcpu->arch.pio.count) {
@@ -9906,13 +9909,20 @@ int kvm_check_nested_events(struct kvm_vcpu *vcpu)
static void kvm_inject_exception(struct kvm_vcpu *vcpu)
{
+ /*
+ * Suppress the error code if the vCPU is in Real Mode, as Real Mode
+ * exceptions don't report error codes. The presence of an error code
+ * is carried with the exception and only stripped when the exception
+ * is injected as intercepted #PF VM-Exits for AMD's Paged Real Mode do
+ * report an error code despite the CPU being in Real Mode.
+ */
+ vcpu->arch.exception.has_error_code &= is_protmode(vcpu);
+
trace_kvm_inj_exception(vcpu->arch.exception.vector,
vcpu->arch.exception.has_error_code,
vcpu->arch.exception.error_code,
vcpu->arch.exception.injected);
- if (vcpu->arch.exception.error_code && !is_protmode(vcpu))
- vcpu->arch.exception.error_code = false;
static_call(kvm_x86_inject_exception)(vcpu);
}
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index 7316a8224259..e91500a80963 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -10,6 +10,7 @@
#include <asm/fixmap.h>
#include <asm/desc.h>
#include <asm/kasan.h>
+#include <asm/setup.h>
static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);
@@ -29,6 +30,12 @@ static __init void init_cea_offsets(void)
unsigned int max_cea;
unsigned int i, j;
+ if (!kaslr_enabled()) {
+ for_each_possible_cpu(i)
+ per_cpu(_cea_offset, i) = i;
+ return;
+ }
+
max_cea = (CPU_ENTRY_AREA_MAP_SIZE - PAGE_SIZE) / CPU_ENTRY_AREA_SIZE;
/* O(sodding terrible) */
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 88cccd65029d..c6efcf559d88 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -600,7 +600,8 @@ void __init sme_enable(struct boot_params *bp)
cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr |
((u64)bp->ext_cmd_line_ptr << 32));
- cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer));
+ if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0)
+ return;
if (!strncmp(buffer, cmdline_on, sizeof(buffer)))
sme_me_mask = me_mask;
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 3c5b52fbe4a7..a9ec8c9f5c5d 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -45,6 +45,6 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o
-obj-$(CONFIG_XEN_PV_DOM0) += vga.o
+obj-$(CONFIG_XEN_DOM0) += vga.o
obj-$(CONFIG_XEN_EFI) += efi.o
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index bb59cc6ddb2d..093b78c8bbec 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1390,7 +1390,8 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si)
x86_platform.set_legacy_features =
xen_dom0_set_legacy_features;
- xen_init_vga(info, xen_start_info->console.dom0.info_size);
+ xen_init_vga(info, xen_start_info->console.dom0.info_size,
+ &boot_params.screen_info);
xen_start_info->console.domU.mfn = 0;
xen_start_info->console.domU.evtchn = 0;
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index bcae606bbc5c..ada3868c02c2 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -43,6 +43,19 @@ void __init xen_pvh_init(struct boot_params *boot_params)
x86_init.oem.banner = xen_banner;
xen_efi_init(boot_params);
+
+ if (xen_initial_domain()) {
+ struct xen_platform_op op = {
+ .cmd = XENPF_get_dom0_console,
+ };
+ int ret = HYPERVISOR_platform_op(&op);
+
+ if (ret > 0)
+ xen_init_vga(&op.u.dom0_console,
+ min(ret * sizeof(char),
+ sizeof(op.u.dom0_console)),
+ &boot_params->screen_info);
+ }
}
void __init mem_map_via_hcall(struct boot_params *boot_params_p)
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 1d597364b49d..b74ac2562cfb 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -20,6 +20,7 @@
#include <asm/pvclock.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
+#include <asm/xen/cpuid.h>
#include <xen/events.h>
#include <xen/features.h>
@@ -503,11 +504,7 @@ static int __init xen_tsc_safe_clocksource(void)
/* Leaf 4, sub-leaf 0 (0x40000x03) */
cpuid_count(xen_cpuid_base() + 3, 0, &eax, &ebx, &ecx, &edx);
- /* tsc_mode = no_emulate (2) */
- if (ebx != 2)
- return 0;
-
- return 1;
+ return ebx == XEN_CPUID_TSC_MODE_NEVER_EMULATE;
}
static void __init xen_time_init(void)
diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c
index 14ea32e734d5..d97adab8420f 100644
--- a/arch/x86/xen/vga.c
+++ b/arch/x86/xen/vga.c
@@ -9,10 +9,9 @@
#include "xen-ops.h"
-void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size)
+void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size,
+ struct screen_info *screen_info)
{
- struct screen_info *screen_info = &boot_params.screen_info;
-
/* This is drawn from a dump from vgacon:startup in
* standard Linux. */
screen_info->orig_video_mode = 3;
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 9a8bb972193d..a10903785a33 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -108,11 +108,12 @@ static inline void xen_uninit_lock_cpu(int cpu)
struct dom0_vga_console_info;
-#ifdef CONFIG_XEN_PV_DOM0
-void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
+#ifdef CONFIG_XEN_DOM0
+void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size,
+ struct screen_info *);
#else
static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
- size_t size)
+ size_t size, struct screen_info *si)
{
}
#endif