summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/configs/exynos_defconfig2
-rw-r--r--arch/arm/configs/multi_v7_defconfig2
-rw-r--r--arch/arm/configs/pxa_defconfig2
-rw-r--r--arch/arm/mm/flush.c4
-rw-r--r--arch/arm64/Kconfig.platforms2
-rw-r--r--arch/arm64/configs/defconfig2
-rw-r--r--arch/arm64/hyperv/mshyperv.c53
-rw-r--r--arch/arm64/include/asm/kvm_host.h3
-rw-r--r--arch/arm64/include/asm/sysreg.h1
-rw-r--r--arch/arm64/kvm/arch_timer.c4
-rw-r--r--arch/arm64/kvm/arm.c69
-rw-r--r--arch/arm64/kvm/hypercalls.c10
-rw-r--r--arch/arm64/kvm/nested.c6
-rw-r--r--arch/arm64/kvm/vgic/vgic-debug.c5
-rw-r--r--arch/arm64/kvm/vgic/vgic-init.c31
-rw-r--r--arch/arm64/kvm/vgic/vgic-its.c56
-rw-r--r--arch/arm64/kvm/vgic/vgic-kvm-device.c12
-rw-r--r--arch/arm64/kvm/vgic/vgic-v4.c92
-rw-r--r--arch/m68k/coldfire/gpio.c8
-rw-r--r--arch/m68k/kernel/setup_no.c3
-rw-r--r--arch/m68k/kernel/uboot.c2
-rw-r--r--arch/m68k/mm/motorola.c3
-rw-r--r--arch/riscv/kvm/aia_device.c34
-rw-r--r--arch/riscv/mm/cacheflush.c2
-rw-r--r--arch/s390/include/asm/gmap.h2
-rw-r--r--arch/s390/include/asm/gmap_helpers.h15
-rw-r--r--arch/s390/include/asm/tlb.h1
-rw-r--r--arch/s390/include/asm/uv.h1
-rw-r--r--arch/s390/kernel/uv.c97
-rw-r--r--arch/s390/kvm/Makefile2
-rw-r--r--arch/s390/kvm/diag.c30
-rw-r--r--arch/s390/kvm/gaccess.c3
-rw-r--r--arch/s390/kvm/gmap-vsie.c1
-rw-r--r--arch/s390/kvm/gmap.c121
-rw-r--r--arch/s390/kvm/gmap.h39
-rw-r--r--arch/s390/kvm/intercept.c9
-rw-r--r--arch/s390/kvm/kvm-s390.c10
-rw-r--r--arch/s390/kvm/kvm-s390.h42
-rw-r--r--arch/s390/kvm/priv.c6
-rw-r--r--arch/s390/kvm/pv.c61
-rw-r--r--arch/s390/kvm/vsie.c19
-rw-r--r--arch/s390/lib/crypto/Makefile3
-rw-r--r--arch/s390/mm/Makefile2
-rw-r--r--arch/s390/mm/fault.c1
-rw-r--r--arch/s390/mm/gmap.c185
-rw-r--r--arch/s390/mm/gmap_helpers.c221
-rw-r--r--arch/s390/mm/init.c1
-rw-r--r--arch/s390/mm/pgalloc.c2
-rw-r--r--arch/s390/mm/pgtable.c1
-rw-r--r--arch/x86/coco/sev/core.c13
-rw-r--r--arch/x86/hyperv/hv_init.c67
-rw-r--r--arch/x86/hyperv/hv_vtl.c61
-rw-r--r--arch/x86/hyperv/ivm.c11
-rw-r--r--arch/x86/include/asm/apic.h8
-rw-r--r--arch/x86/include/asm/cpufeatures.h4
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h9
-rw-r--r--arch/x86/include/asm/mshyperv.h7
-rw-r--r--arch/x86/include/asm/msr.h4
-rw-r--r--arch/x86/include/asm/posted_intr.h78
-rw-r--r--arch/x86/include/asm/svm.h10
-rw-r--r--arch/x86/include/uapi/asm/kvm.h1
-rw-r--r--arch/x86/include/uapi/asm/svm.h2
-rw-r--r--arch/x86/kernel/acpi/madt_wakeup.c2
-rw-r--r--arch/x86/kernel/apic/apic_noop.c8
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c2
-rw-r--r--arch/x86/kernel/irq.c63
-rw-r--r--arch/x86/kernel/smpboot.c10
-rw-r--r--arch/x86/kvm/cpuid.c8
-rw-r--r--arch/x86/kvm/ioapic.c7
-rw-r--r--arch/x86/kvm/ioapic.h2
-rw-r--r--arch/x86/kvm/irq_comm.c37
-rw-r--r--arch/x86/kvm/lapic.c28
-rw-r--r--arch/x86/kvm/lapic.h4
-rw-r--r--arch/x86/kvm/mmu/mmu.c5
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c19
-rw-r--r--arch/x86/kvm/svm/nested.c36
-rw-r--r--arch/x86/kvm/svm/sev.c185
-rw-r--r--arch/x86/kvm/svm/svm.c162
-rw-r--r--arch/x86/kvm/svm/svm.h14
-rw-r--r--arch/x86/kvm/vmx/common.h4
-rw-r--r--arch/x86/kvm/vmx/main.c208
-rw-r--r--arch/x86/kvm/vmx/nested.c48
-rw-r--r--arch/x86/kvm/vmx/posted_intr.c17
-rw-r--r--arch/x86/kvm/vmx/posted_intr.h5
-rw-r--r--arch/x86/kvm/vmx/vmenter.S3
-rw-r--r--arch/x86/kvm/vmx/vmx.c23
-rw-r--r--arch/x86/kvm/vmx/vmx.h3
-rw-r--r--arch/x86/kvm/vmx/x86_ops.h66
-rw-r--r--arch/x86/kvm/x86.c44
-rw-r--r--arch/x86/kvm/x86.h18
-rw-r--r--arch/x86/pci/Makefile6
-rw-r--r--arch/x86/pci/intel_mid.c (renamed from arch/x86/pci/intel_mid_pci.c)0
-rw-r--r--arch/xtensa/Kbuild2
-rw-r--r--arch/xtensa/Kconfig3
-rw-r--r--arch/xtensa/boot/dts/Makefile2
-rw-r--r--arch/xtensa/configs/audio_kc705_defconfig2
-rw-r--r--arch/xtensa/configs/cadence_csp_defconfig2
-rw-r--r--arch/xtensa/configs/common_defconfig1
-rw-r--r--arch/xtensa/configs/generic_kc705_defconfig2
-rw-r--r--arch/xtensa/configs/nommu_kc705_defconfig2
-rw-r--r--arch/xtensa/configs/smp_lx200_defconfig2
-rw-r--r--arch/xtensa/configs/virt_defconfig2
-rw-r--r--arch/xtensa/configs/xip_kc705_defconfig2
-rw-r--r--arch/xtensa/include/asm/ptrace.h5
106 files changed, 1471 insertions, 1155 deletions
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index e81964cce516..f71af368674c 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -167,7 +167,7 @@ CONFIG_MFD_MAX77686=y
CONFIG_MFD_MAX77693=y
CONFIG_MFD_MAX8997=y
CONFIG_MFD_MAX8998=y
-CONFIG_MFD_SEC_CORE=y
+CONFIG_MFD_SEC_I2C=y
CONFIG_MFD_STMPE=y
CONFIG_STMPE_I2C=y
CONFIG_MFD_TPS65090=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index aca01ad6aafc..50c170b4619f 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -612,7 +612,7 @@ CONFIG_MFD_QCOM_RPM=y
CONFIG_MFD_SPMI_PMIC=y
CONFIG_MFD_RK8XX_I2C=y
CONFIG_MFD_RN5T618=y
-CONFIG_MFD_SEC_CORE=y
+CONFIG_MFD_SEC_I2C=y
CONFIG_MFD_STMPE=y
CONFIG_MFD_PALMAS=y
CONFIG_MFD_TPS65090=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index ded4b9a5accf..ff29c5b0e9c9 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -335,7 +335,7 @@ CONFIG_MFD_MAX77693=y
CONFIG_MFD_MAX8907=m
CONFIG_EZX_PCAP=y
CONFIG_UCB1400_CORE=m
-CONFIG_MFD_SEC_CORE=y
+CONFIG_MFD_SEC_I2C=y
CONFIG_MFD_PALMAS=y
CONFIG_MFD_TPS65090=y
CONFIG_MFD_TPS6586X=y
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 0749cf8a6637..5219158d54cf 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -227,9 +227,9 @@ void __flush_dcache_folio(struct address_space *mapping, struct folio *folio)
}
/*
- * If this is a page cache page, and we have an aliasing VIPT cache,
+ * If this is a page cache folio, and we have an aliasing VIPT cache,
* we only need to do one flush - which would be at the relevant
- * userspace colour, which is congruent with page->index.
+ * userspace colour, which is congruent with folio->index.
*/
if (mapping && cache_is_vipt_aliasing())
flush_pfn_alias(folio_pfn(folio), folio_pos(folio));
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index 8b76821f190f..a541bb029aa4 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -269,7 +269,7 @@ config ARCH_QCOM
bool "Qualcomm Platforms"
select GPIOLIB
select PINCTRL
- select HAVE_PWRCTL if PCI
+ select HAVE_PWRCTRL if PCI
help
This enables support for the ARMv8 based Qualcomm chipsets.
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 1e99db100607..897fc686e6a9 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -774,7 +774,7 @@ CONFIG_MFD_MT6397=y
CONFIG_MFD_SPMI_PMIC=y
CONFIG_MFD_RK8XX_I2C=y
CONFIG_MFD_RK8XX_SPI=y
-CONFIG_MFD_SEC_CORE=y
+CONFIG_MFD_SEC_I2C=y
CONFIG_MFD_SL28CPLD=y
CONFIG_RZ_MTU3=y
CONFIG_MFD_TI_AM335X_TSCADC=m
diff --git a/arch/arm64/hyperv/mshyperv.c b/arch/arm64/hyperv/mshyperv.c
index 4e27cc29c79e..4fdc26ade1d7 100644
--- a/arch/arm64/hyperv/mshyperv.c
+++ b/arch/arm64/hyperv/mshyperv.c
@@ -28,6 +28,48 @@ int hv_get_hypervisor_version(union hv_hypervisor_version_info *info)
}
EXPORT_SYMBOL_GPL(hv_get_hypervisor_version);
+#ifdef CONFIG_ACPI
+
+static bool __init hyperv_detect_via_acpi(void)
+{
+ if (acpi_disabled)
+ return false;
+ /*
+ * Hypervisor ID is only available in ACPI v6+, and the
+ * structure layout was extended in v6 to accommodate that
+ * new field.
+ *
+ * At the very minimum, this check makes sure not to read
+ * past the FADT structure.
+ *
+ * It is also needed to catch running in some unknown
+ * non-Hyper-V environment that has ACPI 5.x or less.
+ * In such a case, it can't be Hyper-V.
+ */
+ if (acpi_gbl_FADT.header.revision < 6)
+ return false;
+ return strncmp((char *)&acpi_gbl_FADT.hypervisor_id, "MsHyperV", 8) == 0;
+}
+
+#else
+
+static bool __init hyperv_detect_via_acpi(void)
+{
+ return false;
+}
+
+#endif
+
+static bool __init hyperv_detect_via_smccc(void)
+{
+ uuid_t hyperv_uuid = UUID_INIT(
+ 0x58ba324d, 0x6447, 0x24cd,
+ 0x75, 0x6c, 0xef, 0x8e,
+ 0x24, 0x70, 0x59, 0x16);
+
+ return arm_smccc_hypervisor_has_uuid(&hyperv_uuid);
+}
+
static int __init hyperv_init(void)
{
struct hv_get_vp_registers_output result;
@@ -36,13 +78,11 @@ static int __init hyperv_init(void)
/*
* Allow for a kernel built with CONFIG_HYPERV to be running in
- * a non-Hyper-V environment, including on DT instead of ACPI.
+ * a non-Hyper-V environment.
+ *
* In such cases, do nothing and return success.
*/
- if (acpi_disabled)
- return 0;
-
- if (strncmp((char *)&acpi_gbl_FADT.hypervisor_id, "MsHyperV", 8))
+ if (!hyperv_detect_via_acpi() && !hyperv_detect_via_smccc())
return 0;
/* Setup the guest ID */
@@ -77,6 +117,9 @@ static int __init hyperv_init(void)
if (ms_hyperv.priv_high & HV_ACCESS_PARTITION_ID)
hv_get_partition_id();
+ ms_hyperv.vtl = get_vtl();
+ if (ms_hyperv.vtl > 0) /* non default VTL */
+ pr_info("Linux runs in Hyper-V Virtual Trust Level %d\n", ms_hyperv.vtl);
ms_hyperv_late_init();
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d941abc6b5ee..6ce2c5173482 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1320,9 +1320,6 @@ int __init populate_sysreg_config(const struct sys_reg_desc *sr,
unsigned int idx);
int __init populate_nv_trap_config(void);
-bool lock_all_vcpus(struct kvm *kvm);
-void unlock_all_vcpus(struct kvm *kvm);
-
void kvm_calculate_traps(struct kvm_vcpu *vcpu);
/* MMIO helpers */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index cd853801a8f7..f1bb0d10c39a 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -12,6 +12,7 @@
#include <linux/bits.h>
#include <linux/stringify.h>
#include <linux/kasan-tags.h>
+#include <linux/kconfig.h>
#include <asm/gpr-num.h>
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 5133dcbfe9f7..fdbc8beec930 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -1766,7 +1766,7 @@ int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm,
mutex_lock(&kvm->lock);
- if (lock_all_vcpus(kvm)) {
+ if (!kvm_trylock_all_vcpus(kvm)) {
set_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &kvm->arch.flags);
/*
@@ -1778,7 +1778,7 @@ int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm,
kvm->arch.timer_data.voffset = offset->counter_offset;
kvm->arch.timer_data.poffset = offset->counter_offset;
- unlock_all_vcpus(kvm);
+ kvm_unlock_all_vcpus(kvm);
} else {
ret = -EBUSY;
}
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 36cfcffb40d8..de2b4e9c9f9f 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1924,49 +1924,6 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
}
}
-/* unlocks vcpus from @vcpu_lock_idx and smaller */
-static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx)
-{
- struct kvm_vcpu *tmp_vcpu;
-
- for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
- tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
- mutex_unlock(&tmp_vcpu->mutex);
- }
-}
-
-void unlock_all_vcpus(struct kvm *kvm)
-{
- lockdep_assert_held(&kvm->lock);
-
- unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1);
-}
-
-/* Returns true if all vcpus were locked, false otherwise */
-bool lock_all_vcpus(struct kvm *kvm)
-{
- struct kvm_vcpu *tmp_vcpu;
- unsigned long c;
-
- lockdep_assert_held(&kvm->lock);
-
- /*
- * Any time a vcpu is in an ioctl (including running), the
- * core KVM code tries to grab the vcpu->mutex.
- *
- * By grabbing the vcpu->mutex of all VCPUs we ensure that no
- * other VCPUs can fiddle with the state while we access it.
- */
- kvm_for_each_vcpu(c, tmp_vcpu, kvm) {
- if (!mutex_trylock(&tmp_vcpu->mutex)) {
- unlock_vcpus(kvm, c - 1);
- return false;
- }
- }
-
- return true;
-}
-
static unsigned long nvhe_percpu_size(void)
{
return (unsigned long)CHOOSE_NVHE_SYM(__per_cpu_end) -
@@ -2790,6 +2747,7 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
return kvm_vgic_v4_set_forwarding(irqfd->kvm, prod->irq,
&irqfd->irq_entry);
}
+
void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
@@ -2800,8 +2758,29 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
if (irq_entry->type != KVM_IRQ_ROUTING_MSI)
return;
- kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq,
- &irqfd->irq_entry);
+ kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq);
+}
+
+bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
+ struct kvm_kernel_irq_routing_entry *new)
+{
+ if (new->type != KVM_IRQ_ROUTING_MSI)
+ return true;
+
+ return memcmp(&old->msi, &new->msi, sizeof(new->msi));
+}
+
+int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
+ uint32_t guest_irq, bool set)
+{
+ /*
+ * Remapping the vLPI requires taking the its_lock mutex to resolve
+ * the new translation. We're in spinlock land at this point, so no
+ * chance of resolving the translation.
+ *
+ * Unmap the vLPI and fall back to software LPI injection.
+ */
+ return kvm_vgic_v4_unset_forwarding(kvm, host_irq);
}
void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *cons)
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 569941eeb3fe..58c5fe7d7572 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -270,6 +270,7 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
u32 feature;
u8 action;
gpa_t gpa;
+ uuid_t uuid;
action = kvm_smccc_get_action(vcpu, func_id);
switch (action) {
@@ -355,10 +356,11 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
val[0] = gpa;
break;
case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID:
- val[0] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0;
- val[1] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1;
- val[2] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2;
- val[3] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3;
+ uuid = ARM_SMCCC_VENDOR_HYP_UID_KVM;
+ val[0] = smccc_uuid_to_reg(&uuid, 0);
+ val[1] = smccc_uuid_to_reg(&uuid, 1);
+ val[2] = smccc_uuid_to_reg(&uuid, 2);
+ val[3] = smccc_uuid_to_reg(&uuid, 3);
break;
case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID:
val[0] = smccc_feat->vendor_hyp_bmap;
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 291dbe38eb5c..4a53e4147fb0 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -918,6 +918,8 @@ static void invalidate_vncr_va(struct kvm *kvm,
}
}
+#define tlbi_va_s1_to_va(v) (u64)sign_extend64((v) << 12, 48)
+
static void compute_s1_tlbi_range(struct kvm_vcpu *vcpu, u32 inst, u64 val,
struct s1e2_tlbi_scope *scope)
{
@@ -964,7 +966,7 @@ static void compute_s1_tlbi_range(struct kvm_vcpu *vcpu, u32 inst, u64 val,
scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val));
if (!scope->size)
scope->size = SZ_1G;
- scope->va = (val << 12) & ~(scope->size - 1);
+ scope->va = tlbi_va_s1_to_va(val) & ~(scope->size - 1);
scope->asid = FIELD_GET(TLBIR_ASID_MASK, val);
break;
case OP_TLBI_ASIDE1:
@@ -992,7 +994,7 @@ static void compute_s1_tlbi_range(struct kvm_vcpu *vcpu, u32 inst, u64 val,
scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val));
if (!scope->size)
scope->size = SZ_1G;
- scope->va = (val << 12) & ~(scope->size - 1);
+ scope->va = tlbi_va_s1_to_va(val) & ~(scope->size - 1);
break;
case OP_TLBI_RVAE2:
case OP_TLBI_RVAE2IS:
diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c
index f8425f381de9..2684f273d9e1 100644
--- a/arch/arm64/kvm/vgic/vgic-debug.c
+++ b/arch/arm64/kvm/vgic/vgic-debug.c
@@ -490,6 +490,9 @@ static int vgic_its_debug_show(struct seq_file *s, void *v)
struct its_device *dev = iter->dev;
struct its_ite *ite = iter->ite;
+ if (!ite)
+ return 0;
+
if (list_is_first(&ite->ite_list, &dev->itt_head)) {
seq_printf(s, "\n");
seq_printf(s, "Device ID: 0x%x, Event ID Range: [0 - %llu]\n",
@@ -498,7 +501,7 @@ static int vgic_its_debug_show(struct seq_file *s, void *v)
seq_printf(s, "-----------------------------------------------\n");
}
- if (ite && ite->irq && ite->collection) {
+ if (ite->irq && ite->collection) {
seq_printf(s, "%8u %8u %8u %8u %8u %2d\n",
ite->event_id, ite->irq->intid, ite->irq->hwintid,
ite->collection->target_addr,
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 1f33e71c2a73..eb1205654ac8 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -84,15 +84,40 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
!kvm_vgic_global_state.can_emulate_gicv2)
return -ENODEV;
- /* Must be held to avoid race with vCPU creation */
+ /*
+ * Ensure mutual exclusion with vCPU creation and any vCPU ioctls by:
+ *
+ * - Holding kvm->lock to prevent KVM_CREATE_VCPU from reaching
+ * kvm_arch_vcpu_precreate() and ensuring created_vcpus is stable.
+ * This alone is insufficient, as kvm_vm_ioctl_create_vcpu() drops
+ * the kvm->lock before completing the vCPU creation.
+ */
lockdep_assert_held(&kvm->lock);
+ /*
+ * - Acquiring the vCPU mutex for every *online* vCPU to prevent
+ * concurrent vCPU ioctls for vCPUs already visible to userspace.
+ */
ret = -EBUSY;
- if (!lock_all_vcpus(kvm))
+ if (kvm_trylock_all_vcpus(kvm))
return ret;
+ /*
+ * - Taking the config_lock which protects VGIC data structures such
+ * as the per-vCPU arrays of private IRQs (SGIs, PPIs).
+ */
mutex_lock(&kvm->arch.config_lock);
+ /*
+ * - Bailing on the entire thing if a vCPU is in the middle of creation,
+ * dropped the kvm->lock, but hasn't reached kvm_arch_vcpu_create().
+ *
+ * The whole combination of this guarantees that no vCPU can get into
+ * KVM with a VGIC configuration inconsistent with the VM's VGIC.
+ */
+ if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus))
+ goto out_unlock;
+
if (irqchip_in_kernel(kvm)) {
ret = -EEXIST;
goto out_unlock;
@@ -142,7 +167,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
out_unlock:
mutex_unlock(&kvm->arch.config_lock);
- unlock_all_vcpus(kvm);
+ kvm_unlock_all_vcpus(kvm);
return ret;
}
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 569f9da9049f..534049c7c94b 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -306,39 +306,34 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
}
}
- raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
-
if (irq->hw)
- return its_prop_update_vlpi(irq->host_irq, prop, needs_inv);
+ ret = its_prop_update_vlpi(irq->host_irq, prop, needs_inv);
- return 0;
+ raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+ return ret;
}
static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu)
{
- int ret = 0;
- unsigned long flags;
+ struct its_vlpi_map map;
+ int ret;
- raw_spin_lock_irqsave(&irq->irq_lock, flags);
+ guard(raw_spinlock_irqsave)(&irq->irq_lock);
irq->target_vcpu = vcpu;
- raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
- if (irq->hw) {
- struct its_vlpi_map map;
-
- ret = its_get_vlpi(irq->host_irq, &map);
- if (ret)
- return ret;
+ if (!irq->hw)
+ return 0;
- if (map.vpe)
- atomic_dec(&map.vpe->vlpi_count);
- map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
- atomic_inc(&map.vpe->vlpi_count);
+ ret = its_get_vlpi(irq->host_irq, &map);
+ if (ret)
+ return ret;
- ret = its_map_vlpi(irq->host_irq, &map);
- }
+ if (map.vpe)
+ atomic_dec(&map.vpe->vlpi_count);
- return ret;
+ map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
+ atomic_inc(&map.vpe->vlpi_count);
+ return its_map_vlpi(irq->host_irq, &map);
}
static struct kvm_vcpu *collection_to_vcpu(struct kvm *kvm,
@@ -756,12 +751,17 @@ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi)
/* Requires the its_lock to be held. */
static void its_free_ite(struct kvm *kvm, struct its_ite *ite)
{
+ struct vgic_irq *irq = ite->irq;
list_del(&ite->ite_list);
/* This put matches the get in vgic_add_lpi. */
- if (ite->irq) {
- if (ite->irq->hw)
- WARN_ON(its_unmap_vlpi(ite->irq->host_irq));
+ if (irq) {
+ scoped_guard(raw_spinlock_irqsave, &irq->irq_lock) {
+ if (irq->hw)
+ WARN_ON(its_unmap_vlpi(ite->irq->host_irq));
+
+ irq->hw = false;
+ }
vgic_put_irq(kvm, ite->irq);
}
@@ -1971,7 +1971,7 @@ static int vgic_its_attr_regs_access(struct kvm_device *dev,
mutex_lock(&dev->kvm->lock);
- if (!lock_all_vcpus(dev->kvm)) {
+ if (kvm_trylock_all_vcpus(dev->kvm)) {
mutex_unlock(&dev->kvm->lock);
return -EBUSY;
}
@@ -2006,7 +2006,7 @@ static int vgic_its_attr_regs_access(struct kvm_device *dev,
}
out:
mutex_unlock(&dev->kvm->arch.config_lock);
- unlock_all_vcpus(dev->kvm);
+ kvm_unlock_all_vcpus(dev->kvm);
mutex_unlock(&dev->kvm->lock);
return ret;
}
@@ -2676,7 +2676,7 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
mutex_lock(&kvm->lock);
- if (!lock_all_vcpus(kvm)) {
+ if (kvm_trylock_all_vcpus(kvm)) {
mutex_unlock(&kvm->lock);
return -EBUSY;
}
@@ -2698,7 +2698,7 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
mutex_unlock(&its->its_lock);
mutex_unlock(&kvm->arch.config_lock);
- unlock_all_vcpus(kvm);
+ kvm_unlock_all_vcpus(kvm);
mutex_unlock(&kvm->lock);
return ret;
}
diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index 359094f68c23..f9ae790163fb 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -268,7 +268,7 @@ static int vgic_set_common_attr(struct kvm_device *dev,
return -ENXIO;
mutex_lock(&dev->kvm->lock);
- if (!lock_all_vcpus(dev->kvm)) {
+ if (kvm_trylock_all_vcpus(dev->kvm)) {
mutex_unlock(&dev->kvm->lock);
return -EBUSY;
}
@@ -276,7 +276,7 @@ static int vgic_set_common_attr(struct kvm_device *dev,
mutex_lock(&dev->kvm->arch.config_lock);
r = vgic_v3_save_pending_tables(dev->kvm);
mutex_unlock(&dev->kvm->arch.config_lock);
- unlock_all_vcpus(dev->kvm);
+ kvm_unlock_all_vcpus(dev->kvm);
mutex_unlock(&dev->kvm->lock);
return r;
}
@@ -390,7 +390,7 @@ static int vgic_v2_attr_regs_access(struct kvm_device *dev,
mutex_lock(&dev->kvm->lock);
- if (!lock_all_vcpus(dev->kvm)) {
+ if (kvm_trylock_all_vcpus(dev->kvm)) {
mutex_unlock(&dev->kvm->lock);
return -EBUSY;
}
@@ -415,7 +415,7 @@ static int vgic_v2_attr_regs_access(struct kvm_device *dev,
out:
mutex_unlock(&dev->kvm->arch.config_lock);
- unlock_all_vcpus(dev->kvm);
+ kvm_unlock_all_vcpus(dev->kvm);
mutex_unlock(&dev->kvm->lock);
if (!ret && !is_write)
@@ -554,7 +554,7 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
mutex_lock(&dev->kvm->lock);
- if (!lock_all_vcpus(dev->kvm)) {
+ if (kvm_trylock_all_vcpus(dev->kvm)) {
mutex_unlock(&dev->kvm->lock);
return -EBUSY;
}
@@ -611,7 +611,7 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
out:
mutex_unlock(&dev->kvm->arch.config_lock);
- unlock_all_vcpus(dev->kvm);
+ kvm_unlock_all_vcpus(dev->kvm);
mutex_unlock(&dev->kvm->lock);
if (!ret && uaccess && !is_write) {
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index c7de6154627c..193946108192 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -444,7 +444,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
if (IS_ERR(its))
return 0;
- mutex_lock(&its->its_lock);
+ guard(mutex)(&its->its_lock);
/*
* Perform the actual DevID/EventID -> LPI translation.
@@ -455,11 +455,13 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
*/
if (vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid,
irq_entry->msi.data, &irq))
- goto out;
+ return 0;
+
+ raw_spin_lock_irqsave(&irq->irq_lock, flags);
/* Silently exit if the vLPI is already mapped */
if (irq->hw)
- goto out;
+ goto out_unlock_irq;
/*
* Emit the mapping request. If it fails, the ITS probably
@@ -479,68 +481,74 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq,
ret = its_map_vlpi(virq, &map);
if (ret)
- goto out;
+ goto out_unlock_irq;
irq->hw = true;
irq->host_irq = virq;
atomic_inc(&map.vpe->vlpi_count);
/* Transfer pending state */
- raw_spin_lock_irqsave(&irq->irq_lock, flags);
- if (irq->pending_latch) {
- ret = irq_set_irqchip_state(irq->host_irq,
- IRQCHIP_STATE_PENDING,
- irq->pending_latch);
- WARN_RATELIMIT(ret, "IRQ %d", irq->host_irq);
+ if (!irq->pending_latch)
+ goto out_unlock_irq;
- /*
- * Clear pending_latch and communicate this state
- * change via vgic_queue_irq_unlock.
- */
- irq->pending_latch = false;
- vgic_queue_irq_unlock(kvm, irq, flags);
- } else {
- raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
- }
+ ret = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING,
+ irq->pending_latch);
+ WARN_RATELIMIT(ret, "IRQ %d", irq->host_irq);
-out:
- mutex_unlock(&its->its_lock);
+ /*
+ * Clear pending_latch and communicate this state
+ * change via vgic_queue_irq_unlock.
+ */
+ irq->pending_latch = false;
+ vgic_queue_irq_unlock(kvm, irq, flags);
+ return ret;
+
+out_unlock_irq:
+ raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
return ret;
}
-int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq,
- struct kvm_kernel_irq_routing_entry *irq_entry)
+static struct vgic_irq *__vgic_host_irq_get_vlpi(struct kvm *kvm, int host_irq)
{
- struct vgic_its *its;
struct vgic_irq *irq;
- int ret;
+ unsigned long idx;
+
+ guard(rcu)();
+ xa_for_each(&kvm->arch.vgic.lpi_xa, idx, irq) {
+ if (!irq->hw || irq->host_irq != host_irq)
+ continue;
+
+ if (!vgic_try_get_irq_kref(irq))
+ return NULL;
+
+ return irq;
+ }
+
+ return NULL;
+}
+
+int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int host_irq)
+{
+ struct vgic_irq *irq;
+ unsigned long flags;
+ int ret = 0;
if (!vgic_supports_direct_msis(kvm))
return 0;
- /*
- * Get the ITS, and escape early on error (not a valid
- * doorbell for any of our vITSs).
- */
- its = vgic_get_its(kvm, irq_entry);
- if (IS_ERR(its))
+ irq = __vgic_host_irq_get_vlpi(kvm, host_irq);
+ if (!irq)
return 0;
- mutex_lock(&its->its_lock);
-
- ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid,
- irq_entry->msi.data, &irq);
- if (ret)
- goto out;
-
- WARN_ON(irq->hw && irq->host_irq != virq);
+ raw_spin_lock_irqsave(&irq->irq_lock, flags);
+ WARN_ON(irq->hw && irq->host_irq != host_irq);
if (irq->hw) {
atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count);
irq->hw = false;
- ret = its_unmap_vlpi(virq);
+ ret = its_unmap_vlpi(host_irq);
}
-out:
- mutex_unlock(&its->its_lock);
+ raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
+ vgic_put_irq(kvm, irq);
return ret;
}
diff --git a/arch/m68k/coldfire/gpio.c b/arch/m68k/coldfire/gpio.c
index ca26de257871..30e5a4ed799d 100644
--- a/arch/m68k/coldfire/gpio.c
+++ b/arch/m68k/coldfire/gpio.c
@@ -123,10 +123,12 @@ static int mcfgpio_direction_output(struct gpio_chip *chip, unsigned offset,
return __mcfgpio_direction_output(offset, value);
}
-static void mcfgpio_set_value(struct gpio_chip *chip, unsigned offset,
- int value)
+static int mcfgpio_set_value(struct gpio_chip *chip, unsigned int offset,
+ int value)
{
__mcfgpio_set_value(offset, value);
+
+ return 0;
}
static int mcfgpio_request(struct gpio_chip *chip, unsigned offset)
@@ -158,7 +160,7 @@ static struct gpio_chip mcfgpio_chip = {
.direction_input = mcfgpio_direction_input,
.direction_output = mcfgpio_direction_output,
.get = mcfgpio_get_value,
- .set = mcfgpio_set_value,
+ .set_rv = mcfgpio_set_value,
.to_irq = mcfgpio_to_irq,
.base = 0,
.ngpio = MCFGPIO_PIN_MAX,
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index f9872098f5ca..f724875b15cc 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -145,8 +145,7 @@ void __init setup_arch(char **cmdline_p)
/* Keep a copy of command line */
*cmdline_p = &command_line[0];
- memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
- boot_command_line[COMMAND_LINE_SIZE-1] = 0;
+ strscpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
/*
* Give all the memory to the bootmap allocator, tell it to put the
diff --git a/arch/m68k/kernel/uboot.c b/arch/m68k/kernel/uboot.c
index 5e52ea150d5c..fa7c279ead5d 100644
--- a/arch/m68k/kernel/uboot.c
+++ b/arch/m68k/kernel/uboot.c
@@ -73,7 +73,7 @@ static void __init parse_uboot_commandline(char *commandp, int size)
uboot_cmd_end = sp[5];
if (uboot_cmd_start && uboot_cmd_end)
- strncpy(commandp, (const char *)uboot_cmd_start, size);
+ strscpy(commandp, (const char *)uboot_cmd_start, size);
#if defined(CONFIG_BLK_DEV_INITRD)
uboot_initrd_start = sp[2];
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index 6ab3ef39ba7a..745bd575dcfa 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -105,7 +105,8 @@ static struct list_head ptable_list[3] = {
#define PD_PTABLE(page) ((ptable_desc *)&(virt_to_page((void *)(page))->lru))
#define PD_PAGE(ptable) (list_entry(ptable, struct page, lru))
-#define PD_MARKBITS(dp) (*(unsigned int *)&PD_PAGE(dp)->index)
+#define PD_PTDESC(ptable) (list_entry(ptable, struct ptdesc, pt_list))
+#define PD_MARKBITS(dp) (*(unsigned int *)&PD_PTDESC(dp)->pt_index)
static const int ptable_shift[3] = {
7+2, /* PGD */
diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c
index 43e472ff3e1a..806c41931cde 100644
--- a/arch/riscv/kvm/aia_device.c
+++ b/arch/riscv/kvm/aia_device.c
@@ -12,36 +12,6 @@
#include <linux/kvm_host.h>
#include <linux/uaccess.h>
-static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx)
-{
- struct kvm_vcpu *tmp_vcpu;
-
- for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
- tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
- mutex_unlock(&tmp_vcpu->mutex);
- }
-}
-
-static void unlock_all_vcpus(struct kvm *kvm)
-{
- unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1);
-}
-
-static bool lock_all_vcpus(struct kvm *kvm)
-{
- struct kvm_vcpu *tmp_vcpu;
- unsigned long c;
-
- kvm_for_each_vcpu(c, tmp_vcpu, kvm) {
- if (!mutex_trylock(&tmp_vcpu->mutex)) {
- unlock_vcpus(kvm, c - 1);
- return false;
- }
- }
-
- return true;
-}
-
static int aia_create(struct kvm_device *dev, u32 type)
{
int ret;
@@ -53,7 +23,7 @@ static int aia_create(struct kvm_device *dev, u32 type)
return -EEXIST;
ret = -EBUSY;
- if (!lock_all_vcpus(kvm))
+ if (kvm_trylock_all_vcpus(kvm))
return ret;
kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -65,7 +35,7 @@ static int aia_create(struct kvm_device *dev, u32 type)
kvm->arch.aia.in_kernel = true;
out_unlock:
- unlock_all_vcpus(kvm);
+ kvm_unlock_all_vcpus(kvm);
return ret;
}
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index b81672729887..b8e96dfff19d 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -172,7 +172,7 @@ static void set_icache_stale_mask(void)
stale_cpu = cpumask_test_cpu(cpu, mask);
cpumask_setall(mask);
- cpumask_assign_cpu(cpu, mask, stale_cpu);
+ __assign_cpu(cpu, mask, stale_cpu);
put_cpu();
}
#endif
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 9f2814d0e1e9..66c5808fd011 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -110,7 +110,6 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
unsigned long __gmap_translate(struct gmap *, unsigned long gaddr);
int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr);
-void gmap_discard(struct gmap *, unsigned long from, unsigned long to);
void __gmap_zap(struct gmap *, unsigned long gaddr);
void gmap_unlink(struct mm_struct *, unsigned long *table, unsigned long vmaddr);
@@ -134,7 +133,6 @@ int gmap_protect_one(struct gmap *gmap, unsigned long gaddr, int prot, unsigned
void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
unsigned long gaddr, unsigned long vmaddr);
-int s390_disable_cow_sharing(void);
int s390_replace_asce(struct gmap *gmap);
void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns);
int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start,
diff --git a/arch/s390/include/asm/gmap_helpers.h b/arch/s390/include/asm/gmap_helpers.h
new file mode 100644
index 000000000000..5356446a61c4
--- /dev/null
+++ b/arch/s390/include/asm/gmap_helpers.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Helper functions for KVM guest address space mapping code
+ *
+ * Copyright IBM Corp. 2025
+ */
+
+#ifndef _ASM_S390_GMAP_HELPERS_H
+#define _ASM_S390_GMAP_HELPERS_H
+
+void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_helper_discard(struct mm_struct *mm, unsigned long vmaddr, unsigned long end);
+int gmap_helper_disable_cow_sharing(void);
+
+#endif /* _ASM_S390_GMAP_HELPERS_H */
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index e5103e8e697d..1e50f6f1ad9d 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -36,6 +36,7 @@ static inline bool __tlb_remove_folio_pages(struct mmu_gather *tlb,
#include <asm/tlbflush.h>
#include <asm-generic/tlb.h>
+#include <asm/gmap.h>
/*
* Release the page cache reference for a pte removed by
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index b008402ec9aa..8018549a1ad2 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -16,7 +16,6 @@
#include <linux/bug.h>
#include <linux/sched.h>
#include <asm/page.h>
-#include <asm/gmap.h>
#include <asm/asm.h>
#define UVC_CC_OK 0
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 4ab0b6b4866e..b99478e84da4 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -15,6 +15,7 @@
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/pagewalk.h>
+#include <linux/backing-dev.h>
#include <asm/facility.h>
#include <asm/sections.h>
#include <asm/uv.h>
@@ -135,7 +136,7 @@ int uv_destroy_folio(struct folio *folio)
{
int rc;
- /* See gmap_make_secure(): large folios cannot be secure */
+ /* Large folios cannot be secure */
if (unlikely(folio_test_large(folio)))
return 0;
@@ -184,7 +185,7 @@ int uv_convert_from_secure_folio(struct folio *folio)
{
int rc;
- /* See gmap_make_secure(): large folios cannot be secure */
+ /* Large folios cannot be secure */
if (unlikely(folio_test_large(folio)))
return 0;
@@ -324,32 +325,87 @@ static int make_folio_secure(struct mm_struct *mm, struct folio *folio, struct u
}
/**
- * s390_wiggle_split_folio() - try to drain extra references to a folio and optionally split.
+ * s390_wiggle_split_folio() - try to drain extra references to a folio and
+ * split the folio if it is large.
* @mm: the mm containing the folio to work on
* @folio: the folio
- * @split: whether to split a large folio
*
* Context: Must be called while holding an extra reference to the folio;
* the mm lock should not be held.
- * Return: 0 if the folio was split successfully;
- * -EAGAIN if the folio was not split successfully but another attempt
- * can be made, or if @split was set to false;
- * -EINVAL in case of other errors. See split_folio().
+ * Return: 0 if the operation was successful;
+ * -EAGAIN if splitting the large folio was not successful,
+ * but another attempt can be made;
+ * -EINVAL in case of other folio splitting errors. See split_folio().
*/
-static int s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split)
+static int s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio)
{
- int rc;
+ int rc, tried_splits;
lockdep_assert_not_held(&mm->mmap_lock);
folio_wait_writeback(folio);
lru_add_drain_all();
- if (split) {
+
+ if (!folio_test_large(folio))
+ return 0;
+
+ for (tried_splits = 0; tried_splits < 2; tried_splits++) {
+ struct address_space *mapping;
+ loff_t lstart, lend;
+ struct inode *inode;
+
folio_lock(folio);
rc = split_folio(folio);
+ if (rc != -EBUSY) {
+ folio_unlock(folio);
+ return rc;
+ }
+
+ /*
+ * Splitting with -EBUSY can fail for various reasons, but we
+ * have to handle one case explicitly for now: some mappings
+ * don't allow for splitting dirty folios; writeback will
+ * mark them clean again, including marking all page table
+ * entries mapping the folio read-only, to catch future write
+ * attempts.
+ *
+ * While the system should be writing back dirty folios in the
+ * background, we obtained this folio by looking up a writable
+ * page table entry. On these problematic mappings, writable
+ * page table entries imply dirty folios, preventing the
+ * split in the first place.
+ *
+ * To prevent a livelock when trigger writeback manually and
+ * letting the caller look up the folio again in the page
+ * table (turning it dirty), immediately try to split again.
+ *
+ * This is only a problem for some mappings (e.g., XFS);
+ * mappings that do not support writeback (e.g., shmem) do not
+ * apply.
+ */
+ if (!folio_test_dirty(folio) || folio_test_anon(folio) ||
+ !folio->mapping || !mapping_can_writeback(folio->mapping)) {
+ folio_unlock(folio);
+ break;
+ }
+
+ /*
+ * Ideally, we'd only trigger writeback on this exact folio. But
+ * there is no easy way to do that, so we'll stabilize the
+ * mapping while we still hold the folio lock, so we can drop
+ * the folio lock to trigger writeback on the range currently
+ * covered by the folio instead.
+ */
+ mapping = folio->mapping;
+ lstart = folio_pos(folio);
+ lend = lstart + folio_size(folio) - 1;
+ inode = igrab(mapping->host);
folio_unlock(folio);
- if (rc != -EBUSY)
- return rc;
+ if (unlikely(!inode))
+ break;
+
+ filemap_write_and_wait_range(mapping, lstart, lend);
+ iput(mapping->host);
}
return -EAGAIN;
}
@@ -393,8 +449,11 @@ int make_hva_secure(struct mm_struct *mm, unsigned long hva, struct uv_cb_header
folio_walk_end(&fw, vma);
mmap_read_unlock(mm);
- if (rc == -E2BIG || rc == -EBUSY)
- rc = s390_wiggle_split_folio(mm, folio, rc == -E2BIG);
+ if (rc == -E2BIG || rc == -EBUSY) {
+ rc = s390_wiggle_split_folio(mm, folio);
+ if (!rc)
+ rc = -EAGAIN;
+ }
folio_put(folio);
return rc;
@@ -403,15 +462,15 @@ EXPORT_SYMBOL_GPL(make_hva_secure);
/*
* To be called with the folio locked or with an extra reference! This will
- * prevent gmap_make_secure from touching the folio concurrently. Having 2
- * parallel arch_make_folio_accessible is fine, as the UV calls will become a
- * no-op if the folio is already exported.
+ * prevent kvm_s390_pv_make_secure() from touching the folio concurrently.
+ * Having 2 parallel arch_make_folio_accessible is fine, as the UV calls will
+ * become a no-op if the folio is already exported.
*/
int arch_make_folio_accessible(struct folio *folio)
{
int rc = 0;
- /* See gmap_make_secure(): large folios cannot be secure */
+ /* Large folios cannot be secure */
if (unlikely(folio_test_large(folio)))
return 0;
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index f0ffe874adc2..9a723c48b05a 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -8,7 +8,7 @@ include $(srctree)/virt/kvm/Makefile.kvm
ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o
-kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o gmap.o gmap-vsie.o
+kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o gmap-vsie.o
kvm-$(CONFIG_VFIO_PCI_ZDEV_KVM) += pci.o
obj-$(CONFIG_KVM) += kvm.o
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 74f73141f9b9..53233dec8cad 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -11,12 +11,30 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <asm/gmap.h>
+#include <asm/gmap_helpers.h>
#include <asm/virtio-ccw.h>
#include "kvm-s390.h"
#include "trace.h"
#include "trace-s390.h"
#include "gaccess.h"
+static void do_discard_gfn_range(struct kvm_vcpu *vcpu, gfn_t gfn_start, gfn_t gfn_end)
+{
+ struct kvm_memslot_iter iter;
+ struct kvm_memory_slot *slot;
+ struct kvm_memslots *slots;
+ unsigned long start, end;
+
+ slots = kvm_vcpu_memslots(vcpu);
+
+ kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) {
+ slot = iter.slot;
+ start = __gfn_to_hva_memslot(slot, max(gfn_start, slot->base_gfn));
+ end = __gfn_to_hva_memslot(slot, min(gfn_end, slot->base_gfn + slot->npages));
+ gmap_helper_discard(vcpu->kvm->mm, start, end);
+ }
+}
+
static int diag_release_pages(struct kvm_vcpu *vcpu)
{
unsigned long start, end;
@@ -32,12 +50,13 @@ static int diag_release_pages(struct kvm_vcpu *vcpu)
VCPU_EVENT(vcpu, 5, "diag release pages %lX %lX", start, end);
+ mmap_read_lock(vcpu->kvm->mm);
/*
* We checked for start >= end above, so lets check for the
* fast path (no prefix swap page involved)
*/
if (end <= prefix || start >= prefix + 2 * PAGE_SIZE) {
- gmap_discard(vcpu->arch.gmap, start, end);
+ do_discard_gfn_range(vcpu, gpa_to_gfn(start), gpa_to_gfn(end));
} else {
/*
* This is slow path. gmap_discard will check for start
@@ -45,13 +64,14 @@ static int diag_release_pages(struct kvm_vcpu *vcpu)
* prefix and let gmap_discard make some of these calls
* NOPs.
*/
- gmap_discard(vcpu->arch.gmap, start, prefix);
+ do_discard_gfn_range(vcpu, gpa_to_gfn(start), gpa_to_gfn(prefix));
if (start <= prefix)
- gmap_discard(vcpu->arch.gmap, 0, PAGE_SIZE);
+ do_discard_gfn_range(vcpu, 0, 1);
if (end > prefix + PAGE_SIZE)
- gmap_discard(vcpu->arch.gmap, PAGE_SIZE, 2 * PAGE_SIZE);
- gmap_discard(vcpu->arch.gmap, prefix + 2 * PAGE_SIZE, end);
+ do_discard_gfn_range(vcpu, 1, 2);
+ do_discard_gfn_range(vcpu, gpa_to_gfn(prefix) + 2, gpa_to_gfn(end));
}
+ mmap_read_unlock(vcpu->kvm->mm);
return 0;
}
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index f6fded15633a..e23670e1949c 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -16,9 +16,10 @@
#include <asm/gmap.h>
#include <asm/dat-bits.h>
#include "kvm-s390.h"
-#include "gmap.h"
#include "gaccess.h"
+#define GMAP_SHADOW_FAKE_TABLE 1ULL
+
/*
* vaddress union in order to easily decode a virtual address into its
* region first index, region second index etc. parts.
diff --git a/arch/s390/kvm/gmap-vsie.c b/arch/s390/kvm/gmap-vsie.c
index a6d1dbb04c97..56ef153eb8fe 100644
--- a/arch/s390/kvm/gmap-vsie.c
+++ b/arch/s390/kvm/gmap-vsie.c
@@ -22,7 +22,6 @@
#include <asm/uv.h>
#include "kvm-s390.h"
-#include "gmap.h"
/**
* gmap_find_shadow - find a specific asce in the list of shadow tables
diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c
deleted file mode 100644
index 6d8944d1b4a0..000000000000
--- a/arch/s390/kvm/gmap.c
+++ /dev/null
@@ -1,121 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Guest memory management for KVM/s390
- *
- * Copyright IBM Corp. 2008, 2020, 2024
- *
- * Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com>
- * Martin Schwidefsky <schwidefsky@de.ibm.com>
- * David Hildenbrand <david@redhat.com>
- * Janosch Frank <frankja@linux.vnet.ibm.com>
- */
-
-#include <linux/compiler.h>
-#include <linux/kvm.h>
-#include <linux/kvm_host.h>
-#include <linux/pgtable.h>
-#include <linux/pagemap.h>
-
-#include <asm/lowcore.h>
-#include <asm/gmap.h>
-#include <asm/uv.h>
-
-#include "gmap.h"
-
-/**
- * gmap_make_secure() - make one guest page secure
- * @gmap: the guest gmap
- * @gaddr: the guest address that needs to be made secure
- * @uvcb: the UVCB specifying which operation needs to be performed
- *
- * Context: needs to be called with kvm->srcu held.
- * Return: 0 on success, < 0 in case of error.
- */
-int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
-{
- struct kvm *kvm = gmap->private;
- unsigned long vmaddr;
-
- lockdep_assert_held(&kvm->srcu);
-
- vmaddr = gfn_to_hva(kvm, gpa_to_gfn(gaddr));
- if (kvm_is_error_hva(vmaddr))
- return -EFAULT;
- return make_hva_secure(gmap->mm, vmaddr, uvcb);
-}
-
-int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
-{
- struct uv_cb_cts uvcb = {
- .header.cmd = UVC_CMD_CONV_TO_SEC_STOR,
- .header.len = sizeof(uvcb),
- .guest_handle = gmap->guest_handle,
- .gaddr = gaddr,
- };
-
- return gmap_make_secure(gmap, gaddr, &uvcb);
-}
-
-/**
- * __gmap_destroy_page() - Destroy a guest page.
- * @gmap: the gmap of the guest
- * @page: the page to destroy
- *
- * An attempt will be made to destroy the given guest page. If the attempt
- * fails, an attempt is made to export the page. If both attempts fail, an
- * appropriate error is returned.
- *
- * Context: must be called holding the mm lock for gmap->mm
- */
-static int __gmap_destroy_page(struct gmap *gmap, struct page *page)
-{
- struct folio *folio = page_folio(page);
- int rc;
-
- /*
- * See gmap_make_secure(): large folios cannot be secure. Small
- * folio implies FW_LEVEL_PTE.
- */
- if (folio_test_large(folio))
- return -EFAULT;
-
- rc = uv_destroy_folio(folio);
- /*
- * Fault handlers can race; it is possible that two CPUs will fault
- * on the same secure page. One CPU can destroy the page, reboot,
- * re-enter secure mode and import it, while the second CPU was
- * stuck at the beginning of the handler. At some point the second
- * CPU will be able to progress, and it will not be able to destroy
- * the page. In that case we do not want to terminate the process,
- * we instead try to export the page.
- */
- if (rc)
- rc = uv_convert_from_secure_folio(folio);
-
- return rc;
-}
-
-/**
- * gmap_destroy_page() - Destroy a guest page.
- * @gmap: the gmap of the guest
- * @gaddr: the guest address to destroy
- *
- * An attempt will be made to destroy the given guest page. If the attempt
- * fails, an attempt is made to export the page. If both attempts fail, an
- * appropriate error is returned.
- *
- * Context: may sleep.
- */
-int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr)
-{
- struct page *page;
- int rc = 0;
-
- mmap_read_lock(gmap->mm);
- page = gfn_to_page(gmap->private, gpa_to_gfn(gaddr));
- if (page)
- rc = __gmap_destroy_page(gmap, page);
- kvm_release_page_clean(page);
- mmap_read_unlock(gmap->mm);
- return rc;
-}
diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h
deleted file mode 100644
index c8f031c9ea5f..000000000000
--- a/arch/s390/kvm/gmap.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * KVM guest address space mapping code
- *
- * Copyright IBM Corp. 2007, 2016, 2025
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- * Claudio Imbrenda <imbrenda@linux.ibm.com>
- */
-
-#ifndef ARCH_KVM_S390_GMAP_H
-#define ARCH_KVM_S390_GMAP_H
-
-#define GMAP_SHADOW_FAKE_TABLE 1ULL
-
-int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
-int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
-int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr);
-struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level);
-
-/**
- * gmap_shadow_valid - check if a shadow guest address space matches the
- * given properties and is still valid
- * @sg: pointer to the shadow guest address space structure
- * @asce: ASCE for which the shadow table is requested
- * @edat_level: edat level to be used for the shadow translation
- *
- * Returns 1 if the gmap shadow is still valid and matches the given
- * properties, the caller can continue using it. Returns 0 otherwise, the
- * caller has to request a new shadow gmap in this case.
- *
- */
-static inline int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level)
-{
- if (sg->removed)
- return 0;
- return sg->orig_asce == asce && sg->edat_level == edat_level;
-}
-
-#endif
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index a06a000f196c..c7908950c1f4 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -21,7 +21,6 @@
#include "gaccess.h"
#include "trace.h"
#include "trace-s390.h"
-#include "gmap.h"
u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
{
@@ -545,7 +544,7 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu)
guest_uvcb->header.cmd);
return 0;
}
- rc = gmap_make_secure(vcpu->arch.gmap, uvcb.gaddr, &uvcb);
+ rc = kvm_s390_pv_make_secure(vcpu->kvm, uvcb.gaddr, &uvcb);
/*
* If the unpin did not succeed, the guest will exit again for the UVC
* and we will retry the unpin.
@@ -653,10 +652,8 @@ int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
break;
case ICPT_PV_PREF:
rc = 0;
- gmap_convert_to_secure(vcpu->arch.gmap,
- kvm_s390_get_prefix(vcpu));
- gmap_convert_to_secure(vcpu->arch.gmap,
- kvm_s390_get_prefix(vcpu) + PAGE_SIZE);
+ kvm_s390_pv_convert_to_secure(vcpu->kvm, kvm_s390_get_prefix(vcpu));
+ kvm_s390_pv_convert_to_secure(vcpu->kvm, kvm_s390_get_prefix(vcpu) + PAGE_SIZE);
break;
default:
return -EOPNOTSUPP;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 3f3175193fd7..d5ad10791c25 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -40,6 +40,7 @@
#include <asm/machine.h>
#include <asm/stp.h>
#include <asm/gmap.h>
+#include <asm/gmap_helpers.h>
#include <asm/nmi.h>
#include <asm/isc.h>
#include <asm/sclp.h>
@@ -52,7 +53,6 @@
#include "kvm-s390.h"
#include "gaccess.h"
#include "pci.h"
-#include "gmap.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
@@ -2674,7 +2674,9 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
if (r)
break;
- r = s390_disable_cow_sharing();
+ mmap_write_lock(kvm->mm);
+ r = gmap_helper_disable_cow_sharing();
+ mmap_write_unlock(kvm->mm);
if (r)
break;
@@ -4973,7 +4975,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
* previous protected guest. The old pages need to be destroyed
* so the new guest can use them.
*/
- if (gmap_destroy_page(vcpu->arch.gmap, gaddr)) {
+ if (kvm_s390_pv_destroy_page(vcpu->kvm, gaddr)) {
/*
* Either KVM messed up the secure guest mapping or the
* same page is mapped into multiple secure guests.
@@ -4995,7 +4997,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
* guest has not been imported yet. Try to import the page into
* the protected guest.
*/
- rc = gmap_convert_to_secure(vcpu->arch.gmap, gaddr);
+ rc = kvm_s390_pv_convert_to_secure(vcpu->kvm, gaddr);
if (rc == -EINVAL)
send_sig(SIGSEGV, current, 0);
if (rc != -ENXIO)
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 8d3bbb2dd8d2..c44fe0c3a097 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -308,6 +308,9 @@ int kvm_s390_pv_dump_stor_state(struct kvm *kvm, void __user *buff_user,
u64 *gaddr, u64 buff_user_len, u16 *rc, u16 *rrc);
int kvm_s390_pv_dump_complete(struct kvm *kvm, void __user *buff_user,
u16 *rc, u16 *rrc);
+int kvm_s390_pv_destroy_page(struct kvm *kvm, unsigned long gaddr);
+int kvm_s390_pv_convert_to_secure(struct kvm *kvm, unsigned long gaddr);
+int kvm_s390_pv_make_secure(struct kvm *kvm, unsigned long gaddr, void *uvcb);
static inline u64 kvm_s390_pv_get_handle(struct kvm *kvm)
{
@@ -319,6 +322,41 @@ static inline u64 kvm_s390_pv_cpu_get_handle(struct kvm_vcpu *vcpu)
return vcpu->arch.pv.handle;
}
+/**
+ * __kvm_s390_pv_destroy_page() - Destroy a guest page.
+ * @page: the page to destroy
+ *
+ * An attempt will be made to destroy the given guest page. If the attempt
+ * fails, an attempt is made to export the page. If both attempts fail, an
+ * appropriate error is returned.
+ *
+ * Context: must be called holding the mm lock for gmap->mm
+ */
+static inline int __kvm_s390_pv_destroy_page(struct page *page)
+{
+ struct folio *folio = page_folio(page);
+ int rc;
+
+ /* Large folios cannot be secure. Small folio implies FW_LEVEL_PTE. */
+ if (folio_test_large(folio))
+ return -EFAULT;
+
+ rc = uv_destroy_folio(folio);
+ /*
+ * Fault handlers can race; it is possible that two CPUs will fault
+ * on the same secure page. One CPU can destroy the page, reboot,
+ * re-enter secure mode and import it, while the second CPU was
+ * stuck at the beginning of the handler. At some point the second
+ * CPU will be able to progress, and it will not be able to destroy
+ * the page. In that case we do not want to terminate the process,
+ * we instead try to export the page.
+ */
+ if (rc)
+ rc = uv_convert_from_secure_folio(folio);
+
+ return rc;
+}
+
/* implemented in interrupt.c */
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu);
@@ -398,6 +436,10 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
unsigned long end);
void kvm_s390_vsie_init(struct kvm *kvm);
void kvm_s390_vsie_destroy(struct kvm *kvm);
+int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level);
+
+/* implemented in gmap-vsie.c */
+struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level);
/* implemented in sigp.c */
int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 1a49b89706f8..9253c70897a8 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -1248,6 +1248,8 @@ static inline int __do_essa(struct kvm_vcpu *vcpu, const int orc)
static int handle_essa(struct kvm_vcpu *vcpu)
{
+ lockdep_assert_held(&vcpu->kvm->srcu);
+
/* entries expected to be 1FF */
int entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3;
unsigned long *cbrlo;
@@ -1297,12 +1299,8 @@ static int handle_essa(struct kvm_vcpu *vcpu)
/* Retry the ESSA instruction */
kvm_s390_retry_instr(vcpu);
} else {
- int srcu_idx;
-
mmap_read_lock(vcpu->kvm->mm);
- srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
i = __do_essa(vcpu, orc);
- srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
mmap_read_unlock(vcpu->kvm->mm);
if (i < 0)
return i;
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 22c012aa5206..14c330ec8ceb 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -17,7 +17,6 @@
#include <linux/sched/mm.h>
#include <linux/mmu_notifier.h>
#include "kvm-s390.h"
-#include "gmap.h"
bool kvm_s390_pv_is_protected(struct kvm *kvm)
{
@@ -34,6 +33,64 @@ bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu)
EXPORT_SYMBOL_GPL(kvm_s390_pv_cpu_is_protected);
/**
+ * kvm_s390_pv_make_secure() - make one guest page secure
+ * @kvm: the guest
+ * @gaddr: the guest address that needs to be made secure
+ * @uvcb: the UVCB specifying which operation needs to be performed
+ *
+ * Context: needs to be called with kvm->srcu held.
+ * Return: 0 on success, < 0 in case of error.
+ */
+int kvm_s390_pv_make_secure(struct kvm *kvm, unsigned long gaddr, void *uvcb)
+{
+ unsigned long vmaddr;
+
+ lockdep_assert_held(&kvm->srcu);
+
+ vmaddr = gfn_to_hva(kvm, gpa_to_gfn(gaddr));
+ if (kvm_is_error_hva(vmaddr))
+ return -EFAULT;
+ return make_hva_secure(kvm->mm, vmaddr, uvcb);
+}
+
+int kvm_s390_pv_convert_to_secure(struct kvm *kvm, unsigned long gaddr)
+{
+ struct uv_cb_cts uvcb = {
+ .header.cmd = UVC_CMD_CONV_TO_SEC_STOR,
+ .header.len = sizeof(uvcb),
+ .guest_handle = kvm_s390_pv_get_handle(kvm),
+ .gaddr = gaddr,
+ };
+
+ return kvm_s390_pv_make_secure(kvm, gaddr, &uvcb);
+}
+
+/**
+ * kvm_s390_pv_destroy_page() - Destroy a guest page.
+ * @kvm: the guest
+ * @gaddr: the guest address to destroy
+ *
+ * An attempt will be made to destroy the given guest page. If the attempt
+ * fails, an attempt is made to export the page. If both attempts fail, an
+ * appropriate error is returned.
+ *
+ * Context: may sleep.
+ */
+int kvm_s390_pv_destroy_page(struct kvm *kvm, unsigned long gaddr)
+{
+ struct page *page;
+ int rc = 0;
+
+ mmap_read_lock(kvm->mm);
+ page = gfn_to_page(kvm, gpa_to_gfn(gaddr));
+ if (page)
+ rc = __kvm_s390_pv_destroy_page(page);
+ kvm_release_page_clean(page);
+ mmap_read_unlock(kvm->mm);
+ return rc;
+}
+
+/**
* struct pv_vm_to_be_destroyed - Represents a protected VM that needs to
* be destroyed
*
@@ -638,7 +695,7 @@ static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak,
.tweak[0] = tweak,
.tweak[1] = offset,
};
- int ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb);
+ int ret = kvm_s390_pv_make_secure(kvm, addr, &uvcb);
unsigned long vmaddr;
bool unlocked;
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index a78df3a4f353..13a9661d2b28 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -23,7 +23,6 @@
#include <asm/facility.h>
#include "kvm-s390.h"
#include "gaccess.h"
-#include "gmap.h"
enum vsie_page_flags {
VSIE_PAGE_IN_USE = 0,
@@ -68,6 +67,24 @@ struct vsie_page {
__u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE]; /* 0x0800 */
};
+/**
+ * gmap_shadow_valid() - check if a shadow guest address space matches the
+ * given properties and is still valid
+ * @sg: pointer to the shadow guest address space structure
+ * @asce: ASCE for which the shadow table is requested
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * Returns 1 if the gmap shadow is still valid and matches the given
+ * properties, the caller can continue using it. Returns 0 otherwise; the
+ * caller has to request a new shadow gmap in this case.
+ */
+int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level)
+{
+ if (sg->removed)
+ return 0;
+ return sg->orig_asce == asce && sg->edat_level == edat_level;
+}
+
/* trigger a validity icpt for the given scb */
static int set_validity_icpt(struct kvm_s390_sie_block *scb,
__u16 reason_code)
diff --git a/arch/s390/lib/crypto/Makefile b/arch/s390/lib/crypto/Makefile
index 920197967f46..5df30f1e7930 100644
--- a/arch/s390/lib/crypto/Makefile
+++ b/arch/s390/lib/crypto/Makefile
@@ -3,4 +3,5 @@
obj-$(CONFIG_CRYPTO_CHACHA_S390) += chacha_s390.o
chacha_s390-y := chacha-glue.o chacha-s390.o
-obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256.o
+obj-$(CONFIG_CRYPTO_SHA256_S390) += sha256-s390.o
+sha256-s390-y := sha256.o
diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile
index 9726b91fe7e4..bd0401cc7ca5 100644
--- a/arch/s390/mm/Makefile
+++ b/arch/s390/mm/Makefile
@@ -12,3 +12,5 @@ obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_PTDUMP) += dump_pagetables.o
obj-$(CONFIG_PGSTE) += gmap.o
obj-$(CONFIG_PFAULT) += pfault.o
+
+obj-$(subst m,y,$(CONFIG_KVM)) += gmap_helpers.o
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index da84ff6770de..3829521450dd 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -40,7 +40,6 @@
#include <asm/ptrace.h>
#include <asm/fault.h>
#include <asm/diag.h>
-#include <asm/gmap.h>
#include <asm/irq.h>
#include <asm/facility.h>
#include <asm/uv.h>
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index a94bd4870c65..012a4366a2ad 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -22,9 +22,9 @@
#include <asm/page-states.h>
#include <asm/pgalloc.h>
#include <asm/machine.h>
+#include <asm/gmap_helpers.h>
#include <asm/gmap.h>
#include <asm/page.h>
-#include <asm/tlb.h>
/*
* The address is saved in a radix tree directly; NULL would be ambiguous,
@@ -620,63 +620,20 @@ EXPORT_SYMBOL(__gmap_link);
*/
void __gmap_zap(struct gmap *gmap, unsigned long gaddr)
{
- struct vm_area_struct *vma;
unsigned long vmaddr;
- spinlock_t *ptl;
- pte_t *ptep;
+
+ mmap_assert_locked(gmap->mm);
/* Find the vm address for the guest address */
vmaddr = (unsigned long) radix_tree_lookup(&gmap->guest_to_host,
gaddr >> PMD_SHIFT);
if (vmaddr) {
vmaddr |= gaddr & ~PMD_MASK;
-
- vma = vma_lookup(gmap->mm, vmaddr);
- if (!vma || is_vm_hugetlb_page(vma))
- return;
-
- /* Get pointer to the page table entry */
- ptep = get_locked_pte(gmap->mm, vmaddr, &ptl);
- if (likely(ptep)) {
- ptep_zap_unused(gmap->mm, vmaddr, ptep, 0);
- pte_unmap_unlock(ptep, ptl);
- }
+ gmap_helper_zap_one_page(gmap->mm, vmaddr);
}
}
EXPORT_SYMBOL_GPL(__gmap_zap);
-void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
-{
- unsigned long gaddr, vmaddr, size;
- struct vm_area_struct *vma;
-
- mmap_read_lock(gmap->mm);
- for (gaddr = from; gaddr < to;
- gaddr = (gaddr + PMD_SIZE) & PMD_MASK) {
- /* Find the vm address for the guest address */
- vmaddr = (unsigned long)
- radix_tree_lookup(&gmap->guest_to_host,
- gaddr >> PMD_SHIFT);
- if (!vmaddr)
- continue;
- vmaddr |= gaddr & ~PMD_MASK;
- /* Find vma in the parent mm */
- vma = find_vma(gmap->mm, vmaddr);
- if (!vma)
- continue;
- /*
- * We do not discard pages that are backed by
- * hugetlbfs, so we don't have to refault them.
- */
- if (is_vm_hugetlb_page(vma))
- continue;
- size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
- zap_page_range_single(vma, vmaddr, size, NULL);
- }
- mmap_read_unlock(gmap->mm);
-}
-EXPORT_SYMBOL_GPL(gmap_discard);
-
static LIST_HEAD(gmap_notifier_list);
static DEFINE_SPINLOCK(gmap_notifier_lock);
@@ -2269,138 +2226,6 @@ int s390_enable_sie(void)
}
EXPORT_SYMBOL_GPL(s390_enable_sie);
-static int find_zeropage_pte_entry(pte_t *pte, unsigned long addr,
- unsigned long end, struct mm_walk *walk)
-{
- unsigned long *found_addr = walk->private;
-
- /* Return 1 of the page is a zeropage. */
- if (is_zero_pfn(pte_pfn(*pte))) {
- /*
- * Shared zeropage in e.g., a FS DAX mapping? We cannot do the
- * right thing and likely don't care: FAULT_FLAG_UNSHARE
- * currently only works in COW mappings, which is also where
- * mm_forbids_zeropage() is checked.
- */
- if (!is_cow_mapping(walk->vma->vm_flags))
- return -EFAULT;
-
- *found_addr = addr;
- return 1;
- }
- return 0;
-}
-
-static const struct mm_walk_ops find_zeropage_ops = {
- .pte_entry = find_zeropage_pte_entry,
- .walk_lock = PGWALK_WRLOCK,
-};
-
-/*
- * Unshare all shared zeropages, replacing them by anonymous pages. Note that
- * we cannot simply zap all shared zeropages, because this could later
- * trigger unexpected userfaultfd missing events.
- *
- * This must be called after mm->context.allow_cow_sharing was
- * set to 0, to avoid future mappings of shared zeropages.
- *
- * mm contracts with s390, that even if mm were to remove a page table,
- * and racing with walk_page_range_vma() calling pte_offset_map_lock()
- * would fail, it will never insert a page table containing empty zero
- * pages once mm_forbids_zeropage(mm) i.e.
- * mm->context.allow_cow_sharing is set to 0.
- */
-static int __s390_unshare_zeropages(struct mm_struct *mm)
-{
- struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, mm, 0);
- unsigned long addr;
- vm_fault_t fault;
- int rc;
-
- for_each_vma(vmi, vma) {
- /*
- * We could only look at COW mappings, but it's more future
- * proof to catch unexpected zeropages in other mappings and
- * fail.
- */
- if ((vma->vm_flags & VM_PFNMAP) || is_vm_hugetlb_page(vma))
- continue;
- addr = vma->vm_start;
-
-retry:
- rc = walk_page_range_vma(vma, addr, vma->vm_end,
- &find_zeropage_ops, &addr);
- if (rc < 0)
- return rc;
- else if (!rc)
- continue;
-
- /* addr was updated by find_zeropage_pte_entry() */
- fault = handle_mm_fault(vma, addr,
- FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE,
- NULL);
- if (fault & VM_FAULT_OOM)
- return -ENOMEM;
- /*
- * See break_ksm(): even after handle_mm_fault() returned 0, we
- * must start the lookup from the current address, because
- * handle_mm_fault() may back out if there's any difficulty.
- *
- * VM_FAULT_SIGBUS and VM_FAULT_SIGSEGV are unexpected but
- * maybe they could trigger in the future on concurrent
- * truncation. In that case, the shared zeropage would be gone
- * and we can simply retry and make progress.
- */
- cond_resched();
- goto retry;
- }
-
- return 0;
-}
-
-static int __s390_disable_cow_sharing(struct mm_struct *mm)
-{
- int rc;
-
- if (!mm->context.allow_cow_sharing)
- return 0;
-
- mm->context.allow_cow_sharing = 0;
-
- /* Replace all shared zeropages by anonymous pages. */
- rc = __s390_unshare_zeropages(mm);
- /*
- * Make sure to disable KSM (if enabled for the whole process or
- * individual VMAs). Note that nothing currently hinders user space
- * from re-enabling it.
- */
- if (!rc)
- rc = ksm_disable(mm);
- if (rc)
- mm->context.allow_cow_sharing = 1;
- return rc;
-}
-
-/*
- * Disable most COW-sharing of memory pages for the whole process:
- * (1) Disable KSM and unmerge/unshare any KSM pages.
- * (2) Disallow shared zeropages and unshare any zerpages that are mapped.
- *
- * Not that we currently don't bother with COW-shared pages that are shared
- * with parent/child processes due to fork().
- */
-int s390_disable_cow_sharing(void)
-{
- int rc;
-
- mmap_write_lock(current->mm);
- rc = __s390_disable_cow_sharing(current->mm);
- mmap_write_unlock(current->mm);
- return rc;
-}
-EXPORT_SYMBOL_GPL(s390_disable_cow_sharing);
-
/*
* Enable storage key handling from now on and initialize the storage
* keys with the default key.
@@ -2468,7 +2293,7 @@ int s390_enable_skey(void)
goto out_up;
mm->context.uses_skeys = 1;
- rc = __s390_disable_cow_sharing(mm);
+ rc = gmap_helper_disable_cow_sharing();
if (rc) {
mm->context.uses_skeys = 0;
goto out_up;
diff --git a/arch/s390/mm/gmap_helpers.c b/arch/s390/mm/gmap_helpers.c
new file mode 100644
index 000000000000..a45d417ad951
--- /dev/null
+++ b/arch/s390/mm/gmap_helpers.c
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Helper functions for KVM guest address space mapping code
+ *
+ * Copyright IBM Corp. 2007, 2025
+ */
+#include <linux/mm_types.h>
+#include <linux/mmap_lock.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/pagewalk.h>
+#include <linux/ksm.h>
+#include <asm/gmap_helpers.h>
+
+/**
+ * ptep_zap_swap_entry() - discard a swap entry.
+ * @mm: the mm
+ * @entry: the swap entry that needs to be zapped
+ *
+ * Discards the given swap entry. If the swap entry was an actual swap
+ * entry (and not a migration entry, for example), the actual swapped
+ * page is also discarded from swap.
+ */
+static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry)
+{
+ if (!non_swap_entry(entry))
+ dec_mm_counter(mm, MM_SWAPENTS);
+ else if (is_migration_entry(entry))
+ dec_mm_counter(mm, mm_counter(pfn_swap_entry_folio(entry)));
+ free_swap_and_cache(entry);
+}
+
+/**
+ * gmap_helper_zap_one_page() - discard a page if it was swapped.
+ * @mm: the mm
+ * @vmaddr: the userspace virtual address that needs to be discarded
+ *
+ * If the given address maps to a swap entry, discard it.
+ *
+ * Context: needs to be called while holding the mmap lock.
+ */
+void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr)
+{
+ struct vm_area_struct *vma;
+ spinlock_t *ptl;
+ pte_t *ptep;
+
+ mmap_assert_locked(mm);
+
+ /* Find the vm address for the guest address */
+ vma = vma_lookup(mm, vmaddr);
+ if (!vma || is_vm_hugetlb_page(vma))
+ return;
+
+ /* Get pointer to the page table entry */
+ ptep = get_locked_pte(mm, vmaddr, &ptl);
+ if (unlikely(!ptep))
+ return;
+ if (pte_swap(*ptep))
+ ptep_zap_swap_entry(mm, pte_to_swp_entry(*ptep));
+ pte_unmap_unlock(ptep, ptl);
+}
+EXPORT_SYMBOL_GPL(gmap_helper_zap_one_page);
+
+/**
+ * gmap_helper_discard() - discard user pages in the given range
+ * @mm: the mm
+ * @vmaddr: starting userspace address
+ * @end: end address (first address outside the range)
+ *
+ * All userpace pages in the range [@vamddr, @end) are discarded and unmapped.
+ *
+ * Context: needs to be called while holding the mmap lock.
+ */
+void gmap_helper_discard(struct mm_struct *mm, unsigned long vmaddr, unsigned long end)
+{
+ struct vm_area_struct *vma;
+
+ mmap_assert_locked(mm);
+
+ while (vmaddr < end) {
+ vma = find_vma_intersection(mm, vmaddr, end);
+ if (!vma)
+ return;
+ if (!is_vm_hugetlb_page(vma))
+ zap_page_range_single(vma, vmaddr, min(end, vma->vm_end) - vmaddr, NULL);
+ vmaddr = vma->vm_end;
+ }
+}
+EXPORT_SYMBOL_GPL(gmap_helper_discard);
+
+static int find_zeropage_pte_entry(pte_t *pte, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+{
+ unsigned long *found_addr = walk->private;
+
+ /* Return 1 of the page is a zeropage. */
+ if (is_zero_pfn(pte_pfn(*pte))) {
+ /*
+ * Shared zeropage in e.g., a FS DAX mapping? We cannot do the
+ * right thing and likely don't care: FAULT_FLAG_UNSHARE
+ * currently only works in COW mappings, which is also where
+ * mm_forbids_zeropage() is checked.
+ */
+ if (!is_cow_mapping(walk->vma->vm_flags))
+ return -EFAULT;
+
+ *found_addr = addr;
+ return 1;
+ }
+ return 0;
+}
+
+static const struct mm_walk_ops find_zeropage_ops = {
+ .pte_entry = find_zeropage_pte_entry,
+ .walk_lock = PGWALK_WRLOCK,
+};
+
+/** __gmap_helper_unshare_zeropages() - unshare all shared zeropages
+ * @mm: the mm whose zero pages are to be unshared
+ *
+ * Unshare all shared zeropages, replacing them by anonymous pages. Note that
+ * we cannot simply zap all shared zeropages, because this could later
+ * trigger unexpected userfaultfd missing events.
+ *
+ * This must be called after mm->context.allow_cow_sharing was
+ * set to 0, to avoid future mappings of shared zeropages.
+ *
+ * mm contracts with s390, that even if mm were to remove a page table,
+ * and racing with walk_page_range_vma() calling pte_offset_map_lock()
+ * would fail, it will never insert a page table containing empty zero
+ * pages once mm_forbids_zeropage(mm) i.e.
+ * mm->context.allow_cow_sharing is set to 0.
+ */
+static int __gmap_helper_unshare_zeropages(struct mm_struct *mm)
+{
+ struct vm_area_struct *vma;
+ VMA_ITERATOR(vmi, mm, 0);
+ unsigned long addr;
+ vm_fault_t fault;
+ int rc;
+
+ for_each_vma(vmi, vma) {
+ /*
+ * We could only look at COW mappings, but it's more future
+ * proof to catch unexpected zeropages in other mappings and
+ * fail.
+ */
+ if ((vma->vm_flags & VM_PFNMAP) || is_vm_hugetlb_page(vma))
+ continue;
+ addr = vma->vm_start;
+
+retry:
+ rc = walk_page_range_vma(vma, addr, vma->vm_end,
+ &find_zeropage_ops, &addr);
+ if (rc < 0)
+ return rc;
+ else if (!rc)
+ continue;
+
+ /* addr was updated by find_zeropage_pte_entry() */
+ fault = handle_mm_fault(vma, addr,
+ FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE,
+ NULL);
+ if (fault & VM_FAULT_OOM)
+ return -ENOMEM;
+ /*
+ * See break_ksm(): even after handle_mm_fault() returned 0, we
+ * must start the lookup from the current address, because
+ * handle_mm_fault() may back out if there's any difficulty.
+ *
+ * VM_FAULT_SIGBUS and VM_FAULT_SIGSEGV are unexpected but
+ * maybe they could trigger in the future on concurrent
+ * truncation. In that case, the shared zeropage would be gone
+ * and we can simply retry and make progress.
+ */
+ cond_resched();
+ goto retry;
+ }
+
+ return 0;
+}
+
+/**
+ * gmap_helper_disable_cow_sharing() - disable all COW sharing
+ *
+ * Disable most COW-sharing of memory pages for the whole process:
+ * (1) Disable KSM and unmerge/unshare any KSM pages.
+ * (2) Disallow shared zeropages and unshare any zerpages that are mapped.
+ *
+ * Not that we currently don't bother with COW-shared pages that are shared
+ * with parent/child processes due to fork().
+ */
+int gmap_helper_disable_cow_sharing(void)
+{
+ struct mm_struct *mm = current->mm;
+ int rc;
+
+ mmap_assert_write_locked(mm);
+
+ if (!mm->context.allow_cow_sharing)
+ return 0;
+
+ mm->context.allow_cow_sharing = 0;
+
+ /* Replace all shared zeropages by anonymous pages. */
+ rc = __gmap_helper_unshare_zeropages(mm);
+ /*
+ * Make sure to disable KSM (if enabled for the whole process or
+ * individual VMAs). Note that nothing currently hinders user space
+ * from re-enabling it.
+ */
+ if (!rc)
+ rc = ksm_disable(mm);
+ if (rc)
+ mm->context.allow_cow_sharing = 1;
+ return rc;
+}
+EXPORT_SYMBOL_GPL(gmap_helper_disable_cow_sharing);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index afa085e8186c..074bf4fb4ce2 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -40,7 +40,6 @@
#include <asm/kfence.h>
#include <asm/dma.h>
#include <asm/abs_lowcore.h>
-#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/sclp.h>
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index abe1e58e8b45..b449fd2605b0 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -12,8 +12,6 @@
#include <asm/mmu_context.h>
#include <asm/page-states.h>
#include <asm/pgalloc.h>
-#include <asm/gmap.h>
-#include <asm/tlb.h>
#include <asm/tlbflush.h>
unsigned long *crst_table_alloc(struct mm_struct *mm)
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 9901934284ec..7df70cd8f739 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -20,7 +20,6 @@
#include <linux/ksm.h>
#include <linux/mman.h>
-#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/page-states.h>
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index fbc1215d2746..b6db4e0b936b 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -869,12 +869,12 @@ static void *snp_alloc_vmsa_page(int cpu)
return page_address(p + 1);
}
-static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
+static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip, unsigned int cpu)
{
struct sev_es_save_area *cur_vmsa, *vmsa;
struct svsm_ca *caa;
u8 sipi_vector;
- int cpu, ret;
+ int ret;
u64 cr4;
/*
@@ -895,15 +895,6 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
/* Override start_ip with known protected guest start IP */
start_ip = real_mode_header->sev_es_trampoline_start;
-
- /* Find the logical CPU for the APIC ID */
- for_each_present_cpu(cpu) {
- if (arch_match_cpu_phys_id(cpu, apic_id))
- break;
- }
- if (cpu >= nr_cpu_ids)
- return -EINVAL;
-
cur_vmsa = per_cpu(sev_vmsa, cpu);
/*
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 5d27194a2efa..3d1d3547095a 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -391,40 +391,6 @@ static void __init hv_stimer_setup_percpu_clockev(void)
old_setup_percpu_clockev();
}
-#if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
-static u8 __init get_vtl(void)
-{
- u64 control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_REGISTERS;
- struct hv_input_get_vp_registers *input;
- struct hv_output_get_vp_registers *output;
- unsigned long flags;
- u64 ret;
-
- local_irq_save(flags);
- input = *this_cpu_ptr(hyperv_pcpu_input_arg);
- output = *this_cpu_ptr(hyperv_pcpu_output_arg);
-
- memset(input, 0, struct_size(input, names, 1));
- input->partition_id = HV_PARTITION_ID_SELF;
- input->vp_index = HV_VP_INDEX_SELF;
- input->input_vtl.as_uint8 = 0;
- input->names[0] = HV_REGISTER_VSM_VP_STATUS;
-
- ret = hv_do_hypercall(control, input, output);
- if (hv_result_success(ret)) {
- ret = output->values[0].reg8 & HV_X64_VTL_MASK;
- } else {
- pr_err("Failed to get VTL(error: %lld) exiting...\n", ret);
- BUG();
- }
-
- local_irq_restore(flags);
- return ret;
-}
-#else
-static inline u8 get_vtl(void) { return 0; }
-#endif
-
/*
* This function is to be invoked early in the boot sequence after the
* hypervisor has been detected.
@@ -707,3 +673,36 @@ bool hv_is_hyperv_initialized(void)
return hypercall_msr.enable;
}
EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
+
+int hv_apicid_to_vp_index(u32 apic_id)
+{
+ u64 control;
+ u64 status;
+ unsigned long irq_flags;
+ struct hv_get_vp_from_apic_id_in *input;
+ u32 *output, ret;
+
+ local_irq_save(irq_flags);
+
+ input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+ memset(input, 0, sizeof(*input));
+ input->partition_id = HV_PARTITION_ID_SELF;
+ input->apic_ids[0] = apic_id;
+
+ output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+ control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_INDEX_FROM_APIC_ID;
+ status = hv_do_hypercall(control, input, output);
+ ret = output[0];
+
+ local_irq_restore(irq_flags);
+
+ if (!hv_result_success(status)) {
+ pr_err("failed to get vp index from apic id %d, status %#llx\n",
+ apic_id, status);
+ return -EINVAL;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(hv_apicid_to_vp_index);
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 4580936dcb03..042e8712d8de 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -56,7 +56,12 @@ static void __noreturn hv_vtl_restart(char __maybe_unused *cmd)
void __init hv_vtl_init_platform(void)
{
- pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
+ /*
+ * This function is a no-op if the VTL mode is not enabled.
+ * If it is, this function runs if and only the kernel boots in
+ * VTL2 which the x86 hv initialization path makes sure of.
+ */
+ pr_info("Linux runs in Hyper-V Virtual Trust Level %d\n", ms_hyperv.vtl);
x86_platform.realmode_reserve = x86_init_noop;
x86_platform.realmode_init = x86_init_noop;
@@ -207,63 +212,23 @@ free_lock:
return ret;
}
-static int hv_vtl_apicid_to_vp_id(u32 apic_id)
-{
- u64 control;
- u64 status;
- unsigned long irq_flags;
- struct hv_get_vp_from_apic_id_in *input;
- u32 *output, ret;
-
- local_irq_save(irq_flags);
-
- input = *this_cpu_ptr(hyperv_pcpu_input_arg);
- memset(input, 0, sizeof(*input));
- input->partition_id = HV_PARTITION_ID_SELF;
- input->apic_ids[0] = apic_id;
-
- output = *this_cpu_ptr(hyperv_pcpu_output_arg);
-
- control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID;
- status = hv_do_hypercall(control, input, output);
- ret = output[0];
-
- local_irq_restore(irq_flags);
-
- if (!hv_result_success(status)) {
- pr_err("failed to get vp id from apic id %d, status %#llx\n",
- apic_id, status);
- return -EINVAL;
- }
-
- return ret;
-}
-
-static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip)
+static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip, unsigned int cpu)
{
- int vp_id, cpu;
-
- /* Find the logical CPU for the APIC ID */
- for_each_present_cpu(cpu) {
- if (arch_match_cpu_phys_id(cpu, apicid))
- break;
- }
- if (cpu >= nr_cpu_ids)
- return -EINVAL;
+ int vp_index;
pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid);
- vp_id = hv_vtl_apicid_to_vp_id(apicid);
+ vp_index = hv_apicid_to_vp_index(apicid);
- if (vp_id < 0) {
+ if (vp_index < 0) {
pr_err("Couldn't find CPU with APIC ID %d\n", apicid);
return -EINVAL;
}
- if (vp_id > ms_hyperv.max_vp_index) {
- pr_err("Invalid CPU id %d for APIC ID %d\n", vp_id, apicid);
+ if (vp_index > ms_hyperv.max_vp_index) {
+ pr_err("Invalid CPU id %d for APIC ID %d\n", vp_index, apicid);
return -EINVAL;
}
- return hv_vtl_bringup_vcpu(vp_id, cpu, start_eip);
+ return hv_vtl_bringup_vcpu(vp_index, cpu, start_eip);
}
int __init hv_vtl_early_init(void)
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 09a165a3c41e..e93a2f488ff7 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -9,6 +9,7 @@
#include <linux/bitfield.h>
#include <linux/types.h>
#include <linux/slab.h>
+#include <linux/cpu.h>
#include <asm/svm.h>
#include <asm/sev.h>
#include <asm/io.h>
@@ -289,7 +290,7 @@ static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa)
free_page((unsigned long)vmsa);
}
-int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
+int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip, unsigned int cpu)
{
struct sev_es_save_area *vmsa = (struct sev_es_save_area *)
__get_free_page(GFP_KERNEL | __GFP_ZERO);
@@ -298,10 +299,16 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
u64 ret, retry = 5;
struct hv_enable_vp_vtl *start_vp_input;
unsigned long flags;
+ int vp_index;
if (!vmsa)
return -ENOMEM;
+ /* Find the Hyper-V VP index which might be not the same as APIC ID */
+ vp_index = hv_apicid_to_vp_index(apic_id);
+ if (vp_index < 0 || vp_index > ms_hyperv.max_vp_index)
+ return -EINVAL;
+
native_store_gdt(&gdtr);
vmsa->gdtr.base = gdtr.address;
@@ -349,7 +356,7 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
start_vp_input = (struct hv_enable_vp_vtl *)ap_start_input_arg;
memset(start_vp_input, 0, sizeof(*start_vp_input));
start_vp_input->partition_id = -1;
- start_vp_input->vp_index = cpu;
+ start_vp_input->vp_index = vp_index;
start_vp_input->target_vtl.target_vtl = ms_hyperv.vtl;
*(u64 *)&start_vp_input->vp_context = __pa(vmsa) | 1;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 68e10e30fe9b..23d86c9750b9 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -313,9 +313,9 @@ struct apic {
u32 (*get_apic_id)(u32 id);
/* wakeup_secondary_cpu */
- int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip, unsigned int cpu);
/* wakeup secondary CPU using 64-bit wakeup point */
- int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip, unsigned int cpu);
char *name;
};
@@ -333,8 +333,8 @@ struct apic_override {
void (*send_IPI_self)(int vector);
u64 (*icr_read)(void);
void (*icr_write)(u32 low, u32 high);
- int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
- int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip, unsigned int cpu);
+ int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip, unsigned int cpu);
};
/*
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 5b50e0e35129..ee176236c2be 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -336,6 +336,7 @@
#define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */
#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */
#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */
+#define X86_FEATURE_AMD_IBRS_SAME_MODE (13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/
#define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */
#define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */
#define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */
@@ -378,6 +379,7 @@
#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */
#define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */
#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */
+#define X86_FEATURE_BUS_LOCK_THRESHOLD (15*32+29) /* Bus lock threshold */
#define X86_FEATURE_IDLE_HLT (15*32+30) /* IDLE HLT intercept */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
@@ -446,6 +448,7 @@
#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */
#define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */
#define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */
+#define X86_FEATURE_ALLOWED_SEV_FEATURES (19*32+27) /* Allowed SEV Features */
#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */
#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */
@@ -457,6 +460,7 @@
#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */
#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */
+#define X86_FEATURE_PREFETCHI (20*32+20) /* Prefetch Data/Instruction to Cache Level */
#define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */
#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
#define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 79406bf07a1c..8d50e3e0a19b 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -127,7 +127,7 @@ KVM_X86_OP(leave_smm)
KVM_X86_OP(enable_smi_window)
#endif
KVM_X86_OP_OPTIONAL(dev_get_attr)
-KVM_X86_OP(mem_enc_ioctl)
+KVM_X86_OP_OPTIONAL(mem_enc_ioctl)
KVM_X86_OP_OPTIONAL(vcpu_mem_enc_ioctl)
KVM_X86_OP_OPTIONAL(mem_enc_register_region)
KVM_X86_OP_OPTIONAL(mem_enc_unregister_region)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 67b464651c8d..b4a391929cdb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -126,7 +126,8 @@
KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_HV_TLB_FLUSH \
KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE KVM_ARCH_REQ(34)
+#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE \
+ KVM_ARCH_REQ_FLAGS(34, KVM_REQUEST_WAIT)
#define CR0_RESERVED_BITS \
(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -412,7 +413,6 @@ struct kvm_rmap_head {
};
struct kvm_pio_request {
- unsigned long linear_rip;
unsigned long count;
int in;
int port;
@@ -918,6 +918,7 @@ struct kvm_vcpu_arch {
bool emulate_regs_need_sync_to_vcpu;
bool emulate_regs_need_sync_from_vcpu;
int (*complete_userspace_io)(struct kvm_vcpu *vcpu);
+ unsigned long cui_linear_rip;
gpa_t time;
s8 pvclock_tsc_shift;
@@ -1035,6 +1036,7 @@ struct kvm_vcpu_arch {
int pending_ioapic_eoi;
int pending_external_vector;
+ int highest_stale_pending_ioapic_eoi;
/* be preempted when it's in kernel-mode(cpl=0) */
bool preempted_in_kernel;
@@ -1942,6 +1944,7 @@ struct kvm_arch_async_pf {
extern u32 __read_mostly kvm_nr_uret_msrs;
extern bool __read_mostly allow_smaller_maxphyaddr;
extern bool __read_mostly enable_apicv;
+extern bool __read_mostly enable_device_posted_irqs;
extern struct kvm_x86_ops kvm_x86_ops;
#define kvm_x86_call(func) static_call(kvm_x86_##func)
@@ -2445,7 +2448,7 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
static inline bool kvm_arch_has_irq_bypass(void)
{
- return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
+ return enable_device_posted_irqs;
}
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 778444310cfb..e1752ba47e67 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -269,11 +269,12 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
#ifdef CONFIG_AMD_MEM_ENCRYPT
bool hv_ghcb_negotiate_protocol(void);
void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason);
-int hv_snp_boot_ap(u32 cpu, unsigned long start_ip);
+int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip, unsigned int cpu);
#else
static inline bool hv_ghcb_negotiate_protocol(void) { return false; }
static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {}
-static inline int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) { return 0; }
+static inline int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip,
+ unsigned int cpu) { return 0; }
#endif
#if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST)
@@ -307,6 +308,7 @@ static __always_inline u64 hv_raw_get_msr(unsigned int reg)
{
return native_rdmsrq(reg);
}
+int hv_apicid_to_vp_index(u32 apic_id);
#else /* CONFIG_HYPERV */
static inline void hyperv_init(void) {}
@@ -328,6 +330,7 @@ static inline void hv_set_msr(unsigned int reg, u64 value) { }
static inline u64 hv_get_msr(unsigned int reg) { return 0; }
static inline void hv_set_non_nested_msr(unsigned int reg, u64 value) { }
static inline u64 hv_get_non_nested_msr(unsigned int reg) { return 0; }
+static inline int hv_apicid_to_vp_index(u32 apic_id) { return -EINVAL; }
#endif /* CONFIG_HYPERV */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 4096b8af4ba7..9c2ea29e12a9 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -228,7 +228,7 @@ static __always_inline u64 rdpmc(int counter)
#endif /* !CONFIG_PARAVIRT_XXL */
/* Instruction opcode for WRMSRNS supported in binutils >= 2.40 */
-#define WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6)
+#define ASM_WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6)
/* Non-serializing WRMSR, when available. Falls back to a serializing WRMSR. */
static __always_inline void wrmsrns(u32 msr, u64 val)
@@ -237,7 +237,7 @@ static __always_inline void wrmsrns(u32 msr, u64 val)
* WRMSR is 2 bytes. WRMSRNS is 3 bytes. Pad WRMSR with a redundant
* DS prefix to avoid a trailing NOP.
*/
- asm volatile("1: " ALTERNATIVE("ds wrmsr", WRMSRNS, X86_FEATURE_WRMSRNS)
+ asm volatile("1: " ALTERNATIVE("ds wrmsr", ASM_WRMSRNS, X86_FEATURE_WRMSRNS)
"2: " _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR)
: : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)));
}
diff --git a/arch/x86/include/asm/posted_intr.h b/arch/x86/include/asm/posted_intr.h
index bb107ebbe713..a5f761fbf45b 100644
--- a/arch/x86/include/asm/posted_intr.h
+++ b/arch/x86/include/asm/posted_intr.h
@@ -1,19 +1,24 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _X86_POSTED_INTR_H
#define _X86_POSTED_INTR_H
+
+#include <asm/cmpxchg.h>
+#include <asm/rwonce.h>
#include <asm/irq_vectors.h>
+#include <linux/bitmap.h>
+
#define POSTED_INTR_ON 0
#define POSTED_INTR_SN 1
#define PID_TABLE_ENTRY_VALID 1
+#define NR_PIR_VECTORS 256
+#define NR_PIR_WORDS (NR_PIR_VECTORS / BITS_PER_LONG)
+
/* Posted-Interrupt Descriptor */
struct pi_desc {
- union {
- u32 pir[8]; /* Posted interrupt requested */
- u64 pir64[4];
- };
+ unsigned long pir[NR_PIR_WORDS]; /* Posted interrupt requested */
union {
struct {
u16 notifications; /* Suppress and outstanding bits */
@@ -26,6 +31,65 @@ struct pi_desc {
u32 rsvd[6];
} __aligned(64);
+/*
+ * De-multiplexing posted interrupts is on the performance path, the code
+ * below is written to optimize the cache performance based on the following
+ * considerations:
+ * 1.Posted interrupt descriptor (PID) fits in a cache line that is frequently
+ * accessed by both CPU and IOMMU.
+ * 2.During software processing of posted interrupts, the CPU needs to do
+ * natural width read and xchg for checking and clearing posted interrupt
+ * request (PIR), a 256 bit field within the PID.
+ * 3.On the other side, the IOMMU does atomic swaps of the entire PID cache
+ * line when posting interrupts and setting control bits.
+ * 4.The CPU can access the cache line a magnitude faster than the IOMMU.
+ * 5.Each time the IOMMU does interrupt posting to the PIR will evict the PID
+ * cache line. The cache line states after each operation are as follows,
+ * assuming a 64-bit kernel:
+ * CPU IOMMU PID Cache line state
+ * ---------------------------------------------------------------
+ *...read64 exclusive
+ *...lock xchg64 modified
+ *... post/atomic swap invalid
+ *...-------------------------------------------------------------
+ *
+ * To reduce L1 data cache miss, it is important to avoid contention with
+ * IOMMU's interrupt posting/atomic swap. Therefore, a copy of PIR is used
+ * when processing posted interrupts in software, e.g. to dispatch interrupt
+ * handlers for posted MSIs, or to move interrupts from the PIR to the vIRR
+ * in KVM.
+ *
+ * In addition, the code is trying to keep the cache line state consistent
+ * as much as possible. e.g. when making a copy and clearing the PIR
+ * (assuming non-zero PIR bits are present in the entire PIR), it does:
+ * read, read, read, read, xchg, xchg, xchg, xchg
+ * instead of:
+ * read, xchg, read, xchg, read, xchg, read, xchg
+ */
+static __always_inline bool pi_harvest_pir(unsigned long *pir,
+ unsigned long *pir_vals)
+{
+ unsigned long pending = 0;
+ int i;
+
+ for (i = 0; i < NR_PIR_WORDS; i++) {
+ pir_vals[i] = READ_ONCE(pir[i]);
+ pending |= pir_vals[i];
+ }
+
+ if (!pending)
+ return false;
+
+ for (i = 0; i < NR_PIR_WORDS; i++) {
+ if (!pir_vals[i])
+ continue;
+
+ pir_vals[i] = arch_xchg(&pir[i], 0);
+ }
+
+ return true;
+}
+
static inline bool pi_test_and_set_on(struct pi_desc *pi_desc)
{
return test_and_set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
@@ -43,12 +107,12 @@ static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc)
static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
{
- return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
+ return test_and_set_bit(vector, pi_desc->pir);
}
static inline bool pi_is_pir_empty(struct pi_desc *pi_desc)
{
- return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS);
+ return bitmap_empty(pi_desc->pir, NR_VECTORS);
}
static inline void pi_set_sn(struct pi_desc *pi_desc)
@@ -110,7 +174,7 @@ static inline bool pi_pending_this_cpu(unsigned int vector)
if (WARN_ON_ONCE(vector > NR_VECTORS || vector < FIRST_EXTERNAL_VECTOR))
return false;
- return test_bit(vector, (unsigned long *)pid->pir);
+ return test_bit(vector, pid->pir);
}
extern void intel_posted_msi_init(void);
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 9b7fa99ae951..ad954a1a6656 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -116,6 +116,7 @@ enum {
INTERCEPT_INVPCID,
INTERCEPT_MCOMMIT,
INTERCEPT_TLBSYNC,
+ INTERCEPT_BUSLOCK,
INTERCEPT_IDLE_HLT = 166,
};
@@ -159,7 +160,12 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
u64 avic_physical_id; /* Offset 0xf8 */
u8 reserved_7[8];
u64 vmsa_pa; /* Used for an SEV-ES guest */
- u8 reserved_8[720];
+ u8 reserved_8[16];
+ u16 bus_lock_counter; /* Offset 0x120 */
+ u8 reserved_9[22];
+ u64 allowed_sev_features; /* Offset 0x138 */
+ u64 guest_sev_features; /* Offset 0x140 */
+ u8 reserved_10[664];
/*
* Offset 0x3e0, 32 bytes reserved
* for use by hypervisor/software.
@@ -291,6 +297,8 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_
#define SVM_SEV_FEAT_ALTERNATE_INJECTION BIT(4)
#define SVM_SEV_FEAT_DEBUG_SWAP BIT(5)
+#define VMCB_ALLOWED_SEV_FEATURES_VALID BIT_ULL(63)
+
struct vmcb_seg {
u16 selector;
u16 attrib;
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 225a12e0d5d6..6f3499507c5e 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -845,6 +845,7 @@ struct kvm_sev_snp_launch_start {
};
/* Kept in sync with firmware values for simplicity. */
+#define KVM_SEV_PAGE_TYPE_INVALID 0x0
#define KVM_SEV_SNP_PAGE_TYPE_NORMAL 0x1
#define KVM_SEV_SNP_PAGE_TYPE_ZERO 0x3
#define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED 0x4
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index ec1321248dac..9c640a521a67 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -95,6 +95,7 @@
#define SVM_EXIT_CR14_WRITE_TRAP 0x09e
#define SVM_EXIT_CR15_WRITE_TRAP 0x09f
#define SVM_EXIT_INVPCID 0x0a2
+#define SVM_EXIT_BUS_LOCK 0x0a5
#define SVM_EXIT_IDLE_HLT 0x0a6
#define SVM_EXIT_NPF 0x400
#define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401
@@ -225,6 +226,7 @@
{ SVM_EXIT_CR4_WRITE_TRAP, "write_cr4_trap" }, \
{ SVM_EXIT_CR8_WRITE_TRAP, "write_cr8_trap" }, \
{ SVM_EXIT_INVPCID, "invpcid" }, \
+ { SVM_EXIT_BUS_LOCK, "buslock" }, \
{ SVM_EXIT_IDLE_HLT, "idle-halt" }, \
{ SVM_EXIT_NPF, "npf" }, \
{ SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \
diff --git a/arch/x86/kernel/acpi/madt_wakeup.c b/arch/x86/kernel/acpi/madt_wakeup.c
index f36f28405dcc..6d7603511f52 100644
--- a/arch/x86/kernel/acpi/madt_wakeup.c
+++ b/arch/x86/kernel/acpi/madt_wakeup.c
@@ -126,7 +126,7 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
return 0;
}
-static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip)
+static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip, unsigned int cpu)
{
if (!acpi_mp_wake_mailbox_paddr) {
pr_warn_once("No MADT mailbox: cannot bringup secondary CPUs. Booting with kexec?\n");
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index b5bb7a2e8340..58abb941c45b 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -27,7 +27,13 @@ static void noop_send_IPI_allbutself(int vector) { }
static void noop_send_IPI_all(int vector) { }
static void noop_send_IPI_self(int vector) { }
static void noop_apic_icr_write(u32 low, u32 id) { }
-static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { return -1; }
+
+static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip,
+ unsigned int cpu)
+{
+ return -1;
+}
+
static u64 noop_apic_icr_read(void) { return 0; }
static u32 noop_get_apic_id(u32 apicid) { return 0; }
static void noop_apic_eoi(void) { }
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index e272bc7fdc8e..5c5be2d58242 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -57,7 +57,7 @@ static void numachip2_apic_icr_write(int apicid, unsigned int val)
numachip2_write32_lcsr(NUMACHIP2_APIC_ICR, (apicid << 12) | val);
}
-static int numachip_wakeup_secondary(u32 phys_apicid, unsigned long start_rip)
+static int numachip_wakeup_secondary(u32 phys_apicid, unsigned long start_rip, unsigned int cpu)
{
numachip_apic_icr_write(phys_apicid, APIC_DM_INIT);
numachip_apic_icr_write(phys_apicid, APIC_DM_STARTUP |
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 7fef504ca508..15209f220e1f 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -667,7 +667,7 @@ static __init void build_uv_gr_table(void)
}
}
-static int uv_wakeup_secondary(u32 phys_apicid, unsigned long start_rip)
+static int uv_wakeup_secondary(u32 phys_apicid, unsigned long start_rip, unsigned int cpu)
{
unsigned long val;
int pnode;
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 81f9b78e0f7b..9ed29ff10e59 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -380,61 +380,18 @@ void intel_posted_msi_init(void)
this_cpu_write(posted_msi_pi_desc.ndst, destination);
}
-/*
- * De-multiplexing posted interrupts is on the performance path, the code
- * below is written to optimize the cache performance based on the following
- * considerations:
- * 1.Posted interrupt descriptor (PID) fits in a cache line that is frequently
- * accessed by both CPU and IOMMU.
- * 2.During posted MSI processing, the CPU needs to do 64-bit read and xchg
- * for checking and clearing posted interrupt request (PIR), a 256 bit field
- * within the PID.
- * 3.On the other side, the IOMMU does atomic swaps of the entire PID cache
- * line when posting interrupts and setting control bits.
- * 4.The CPU can access the cache line a magnitude faster than the IOMMU.
- * 5.Each time the IOMMU does interrupt posting to the PIR will evict the PID
- * cache line. The cache line states after each operation are as follows:
- * CPU IOMMU PID Cache line state
- * ---------------------------------------------------------------
- *...read64 exclusive
- *...lock xchg64 modified
- *... post/atomic swap invalid
- *...-------------------------------------------------------------
- *
- * To reduce L1 data cache miss, it is important to avoid contention with
- * IOMMU's interrupt posting/atomic swap. Therefore, a copy of PIR is used
- * to dispatch interrupt handlers.
- *
- * In addition, the code is trying to keep the cache line state consistent
- * as much as possible. e.g. when making a copy and clearing the PIR
- * (assuming non-zero PIR bits are present in the entire PIR), it does:
- * read, read, read, read, xchg, xchg, xchg, xchg
- * instead of:
- * read, xchg, read, xchg, read, xchg, read, xchg
- */
-static __always_inline bool handle_pending_pir(u64 *pir, struct pt_regs *regs)
+static __always_inline bool handle_pending_pir(unsigned long *pir, struct pt_regs *regs)
{
- int i, vec = FIRST_EXTERNAL_VECTOR;
- unsigned long pir_copy[4];
- bool handled = false;
+ unsigned long pir_copy[NR_PIR_WORDS];
+ int vec = FIRST_EXTERNAL_VECTOR;
- for (i = 0; i < 4; i++)
- pir_copy[i] = pir[i];
-
- for (i = 0; i < 4; i++) {
- if (!pir_copy[i])
- continue;
+ if (!pi_harvest_pir(pir, pir_copy))
+ return false;
- pir_copy[i] = arch_xchg(&pir[i], 0);
- handled = true;
- }
-
- if (handled) {
- for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR)
- call_irq_handler(vec, regs);
- }
+ for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR)
+ call_irq_handler(vec, regs);
- return handled;
+ return true;
}
/*
@@ -464,7 +421,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification)
* MAX_POSTED_MSI_COALESCING_LOOP - 1 loops are executed here.
*/
while (++i < MAX_POSTED_MSI_COALESCING_LOOP) {
- if (!handle_pending_pir(pid->pir64, regs))
+ if (!handle_pending_pir(pid->pir, regs))
break;
}
@@ -479,7 +436,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification)
* process PIR bits one last time such that handling the new interrupts
* are not delayed until the next IRQ.
*/
- handle_pending_pir(pid->pir64, regs);
+ handle_pending_pir(pid->pir, regs);
apic_eoi();
irq_exit();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 1ba92ac9441d..fc78c2325fd2 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -695,7 +695,7 @@ static void send_init_sequence(u32 phys_apicid)
/*
* Wake up AP by INIT, INIT, STARTUP sequence.
*/
-static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip)
+static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip, unsigned int cpu)
{
unsigned long send_status = 0, accept_status = 0;
int num_starts, j, maxlvt;
@@ -842,7 +842,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
* Returns zero if startup was successfully sent, else error code from
* ->wakeup_secondary_cpu.
*/
-static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle)
+static int do_boot_cpu(u32 apicid, unsigned int cpu, struct task_struct *idle)
{
unsigned long start_ip = real_mode_header->trampoline_start;
int ret;
@@ -896,11 +896,11 @@ static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle)
* - Use an INIT boot APIC message
*/
if (apic->wakeup_secondary_cpu_64)
- ret = apic->wakeup_secondary_cpu_64(apicid, start_ip);
+ ret = apic->wakeup_secondary_cpu_64(apicid, start_ip, cpu);
else if (apic->wakeup_secondary_cpu)
- ret = apic->wakeup_secondary_cpu(apicid, start_ip);
+ ret = apic->wakeup_secondary_cpu(apicid, start_ip, cpu);
else
- ret = wakeup_secondary_cpu_via_init(apicid, start_ip);
+ ret = wakeup_secondary_cpu_via_init(apicid, start_ip, cpu);
/* If the wakeup mechanism failed, cleanup the warm reset vector */
if (ret)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 6569b453546b..b2d006756e02 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -978,6 +978,7 @@ void kvm_set_cpu_caps(void)
F(FZRM),
F(FSRS),
F(FSRC),
+ F(WRMSRNS),
F(AMX_FP16),
F(AVX_IFMA),
F(LAM),
@@ -1093,6 +1094,7 @@ void kvm_set_cpu_caps(void)
F(AMD_SSB_NO),
F(AMD_STIBP),
F(AMD_STIBP_ALWAYS_ON),
+ F(AMD_IBRS_SAME_MODE),
F(AMD_PSFD),
F(AMD_IBPB_RET),
);
@@ -1150,6 +1152,7 @@ void kvm_set_cpu_caps(void)
kvm_cpu_cap_init(CPUID_8000_0021_EAX,
F(NO_NESTED_DATA_BP),
+ F(WRMSR_XX_BASE_NS),
/*
* Synthesize "LFENCE is serializing" into the AMD-defined entry
* in KVM's supported CPUID, i.e. if the feature is reported as
@@ -1163,10 +1166,13 @@ void kvm_set_cpu_caps(void)
SYNTHESIZED_F(LFENCE_RDTSC),
/* SmmPgCfgLock */
F(NULL_SEL_CLR_BASE),
+ /* UpperAddressIgnore */
F(AUTOIBRS),
+ F(PREFETCHI),
EMULATED_F(NO_SMM_CTL_MSR),
/* PrefetchCtlMsr */
- F(WRMSR_XX_BASE_NS),
+ /* GpOnUserCpuid */
+ /* EPSF */
SYNTHESIZED_F(SBPB),
SYNTHESIZED_F(IBPB_BRTYPE),
SYNTHESIZED_F(SRSO_NO),
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 995eb5054360..45dae2d5d2f1 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -296,11 +296,8 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors)
index == RTC_GSI) {
u16 dm = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode);
- if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
- e->fields.dest_id, dm) ||
- kvm_apic_pending_eoi(vcpu, e->fields.vector))
- __set_bit(e->fields.vector,
- ioapic_handled_vectors);
+ kvm_scan_ioapic_irq(vcpu, e->fields.dest_id, dm,
+ e->fields.vector, ioapic_handled_vectors);
}
}
spin_unlock(&ioapic->lock);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index 539333ac4b38..aa8cb4ac0479 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -120,4 +120,6 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu,
ulong *ioapic_handled_vectors);
void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
ulong *ioapic_handled_vectors);
+void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode,
+ u8 vector, unsigned long *ioapic_handled_vectors);
#endif
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 8136695f7b96..d6d792b5d1bd 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -402,6 +402,33 @@ void kvm_arch_post_irq_routing_update(struct kvm *kvm)
kvm_make_scan_ioapic_request(kvm);
}
+void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode,
+ u8 vector, unsigned long *ioapic_handled_vectors)
+{
+ /*
+ * Intercept EOI if the vCPU is the target of the new IRQ routing, or
+ * the vCPU has a pending IRQ from the old routing, i.e. if the vCPU
+ * may receive a level-triggered IRQ in the future, or already received
+ * level-triggered IRQ. The EOI needs to be intercepted and forwarded
+ * to I/O APIC emulation so that the IRQ can be de-asserted.
+ */
+ if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, dest_id, dest_mode)) {
+ __set_bit(vector, ioapic_handled_vectors);
+ } else if (kvm_apic_pending_eoi(vcpu, vector)) {
+ __set_bit(vector, ioapic_handled_vectors);
+
+ /*
+ * Track the highest pending EOI for which the vCPU is NOT the
+ * target in the new routing. Only the EOI for the IRQ that is
+ * in-flight (for the old routing) needs to be intercepted, any
+ * future IRQs that arrive on this vCPU will be coincidental to
+ * the level-triggered routing and don't need to be intercepted.
+ */
+ if ((int)vector > vcpu->arch.highest_stale_pending_ioapic_eoi)
+ vcpu->arch.highest_stale_pending_ioapic_eoi = vector;
+ }
+}
+
void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
ulong *ioapic_handled_vectors)
{
@@ -424,11 +451,11 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
kvm_set_msi_irq(vcpu->kvm, entry, &irq);
- if (irq.trig_mode &&
- (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
- irq.dest_id, irq.dest_mode) ||
- kvm_apic_pending_eoi(vcpu, irq.vector)))
- __set_bit(irq.vector, ioapic_handled_vectors);
+ if (!irq.trig_mode)
+ continue;
+
+ kvm_scan_ioapic_irq(vcpu, irq.dest_id, irq.dest_mode,
+ irq.vector, ioapic_handled_vectors);
}
}
srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c9de81cc27e1..73418dc0ebb2 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -655,27 +655,29 @@ static u8 count_vectors(void *bitmap)
return count;
}
-bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr)
+bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr)
{
+ unsigned long pir_vals[NR_PIR_WORDS];
+ u32 *__pir = (void *)pir_vals;
u32 i, vec;
- u32 pir_val, irr_val, prev_irr_val;
+ u32 irr_val, prev_irr_val;
int max_updated_irr;
max_updated_irr = -1;
*max_irr = -1;
+ if (!pi_harvest_pir(pir, pir_vals))
+ return false;
+
for (i = vec = 0; i <= 7; i++, vec += 32) {
u32 *p_irr = (u32 *)(regs + APIC_IRR + i * 0x10);
- irr_val = *p_irr;
- pir_val = READ_ONCE(pir[i]);
-
- if (pir_val) {
- pir_val = xchg(&pir[i], 0);
+ irr_val = READ_ONCE(*p_irr);
+ if (__pir[i]) {
prev_irr_val = irr_val;
do {
- irr_val = prev_irr_val | pir_val;
+ irr_val = prev_irr_val | __pir[i];
} while (prev_irr_val != irr_val &&
!try_cmpxchg(p_irr, &prev_irr_val, irr_val));
@@ -691,7 +693,7 @@ bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr)
}
EXPORT_SYMBOL_GPL(__kvm_apic_update_irr);
-bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr)
+bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, unsigned long *pir, int *max_irr)
{
struct kvm_lapic *apic = vcpu->arch.apic;
bool irr_updated = __kvm_apic_update_irr(pir, apic->regs, max_irr);
@@ -1459,6 +1461,14 @@ static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
if (!kvm_ioapic_handles_vector(apic, vector))
return;
+ /*
+ * If the intercepted EOI is for an IRQ that was pending from previous
+ * routing, then re-scan the I/O APIC routes as EOIs for the IRQ likely
+ * no longer need to be intercepted.
+ */
+ if (apic->vcpu->arch.highest_stale_pending_ioapic_eoi == vector)
+ kvm_make_request(KVM_REQ_SCAN_IOAPIC, apic->vcpu);
+
/* Request a KVM exit to inform the userspace IOAPIC. */
if (irqchip_split(apic->vcpu->kvm)) {
apic->vcpu->arch.pending_ioapic_eoi = vector;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index e33c969439f7..4ce30db65828 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -103,8 +103,8 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int shorthand, unsigned int dest, int dest_mode);
int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec);
-bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr);
-bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr);
+bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr);
+bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, unsigned long *pir, int *max_irr);
void kvm_apic_update_ppr(struct kvm_vcpu *vcpu);
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
struct dest_map *dest_map);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 7b3f1783ab3c..cbc84c6abc2e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3020,7 +3020,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
}
if (is_shadow_present_pte(*sptep)) {
- if (prefetch)
+ if (prefetch && is_last_spte(*sptep, level) &&
+ pfn == spte_to_pfn(*sptep))
return RET_PF_SPURIOUS;
/*
@@ -3034,7 +3035,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
child = spte_to_child_sp(pte);
drop_parent_pte(vcpu->kvm, child, sptep);
flush = true;
- } else if (pfn != spte_to_pfn(*sptep)) {
+ } else if (WARN_ON_ONCE(pfn != spte_to_pfn(*sptep))) {
drop_spte(vcpu->kvm, sptep);
flush = true;
} else
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 405874f4d088..7f3d7229b2c1 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -378,7 +378,7 @@ static void remove_external_spte(struct kvm *kvm, gfn_t gfn, u64 old_spte,
/* Zapping leaf spte is allowed only when write lock is held. */
lockdep_assert_held_write(&kvm->mmu_lock);
/* Because write lock is held, operation should success. */
- ret = static_call(kvm_x86_remove_external_spte)(kvm, gfn, level, old_pfn);
+ ret = kvm_x86_call(remove_external_spte)(kvm, gfn, level, old_pfn);
KVM_BUG_ON(ret, kvm);
}
@@ -485,8 +485,8 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared)
}
if (is_mirror_sp(sp) &&
- WARN_ON(static_call(kvm_x86_free_external_spt)(kvm, base_gfn, sp->role.level,
- sp->external_spt))) {
+ WARN_ON(kvm_x86_call(free_external_spt)(kvm, base_gfn, sp->role.level,
+ sp->external_spt))) {
/*
* Failed to free page table page in mirror page table and
* there is nothing to do further.
@@ -538,12 +538,12 @@ static int __must_check set_external_spte_present(struct kvm *kvm, tdp_ptep_t sp
* external page table, or leaf.
*/
if (is_leaf) {
- ret = static_call(kvm_x86_set_external_spte)(kvm, gfn, level, new_pfn);
+ ret = kvm_x86_call(set_external_spte)(kvm, gfn, level, new_pfn);
} else {
void *external_spt = get_external_spt(gfn, new_spte, level);
KVM_BUG_ON(!external_spt, kvm);
- ret = static_call(kvm_x86_link_external_spt)(kvm, gfn, level, external_spt);
+ ret = kvm_x86_call(link_external_spt)(kvm, gfn, level, external_spt);
}
if (ret)
__kvm_tdp_mmu_write_spte(sptep, old_spte);
@@ -1153,13 +1153,12 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
if (WARN_ON_ONCE(sp->role.level != fault->goal_level))
return RET_PF_RETRY;
- if (fault->prefetch && is_shadow_present_pte(iter->old_spte))
- return RET_PF_SPURIOUS;
-
if (is_shadow_present_pte(iter->old_spte) &&
- is_access_allowed(fault, iter->old_spte) &&
- is_last_spte(iter->old_spte, iter->level))
+ (fault->prefetch || is_access_allowed(fault, iter->old_spte)) &&
+ is_last_spte(iter->old_spte, iter->level)) {
+ WARN_ON_ONCE(fault->pfn != spte_to_pfn(iter->old_spte));
return RET_PF_SPURIOUS;
+ }
if (unlikely(!fault->slot))
new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 834b67672d50..8427a48b8b7a 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -678,6 +678,33 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
vmcb02->control.iopm_base_pa = vmcb01->control.iopm_base_pa;
vmcb02->control.msrpm_base_pa = vmcb01->control.msrpm_base_pa;
+ /*
+ * Stash vmcb02's counter if the guest hasn't moved past the guilty
+ * instruction; otherwise, reset the counter to '0'.
+ *
+ * In order to detect if L2 has made forward progress or not, track the
+ * RIP at which a bus lock has occurred on a per-vmcb12 basis. If RIP
+ * is changed, guest has clearly made forward progress, bus_lock_counter
+ * still remained '1', so reset bus_lock_counter to '0'. Eg. In the
+ * scenario, where a buslock happened in L1 before VMRUN, the bus lock
+ * firmly happened on an instruction in the past. Even if vmcb01's
+ * counter is still '1', (because the guilty instruction got patched),
+ * the vCPU has clearly made forward progress and so KVM should reset
+ * vmcb02's counter to '0'.
+ *
+ * If the RIP hasn't changed, stash the bus lock counter at nested VMRUN
+ * to prevent the same guilty instruction from triggering a VM-Exit. Eg.
+ * if userspace rate-limits the vCPU, then it's entirely possible that
+ * L1's tick interrupt is pending by the time userspace re-runs the
+ * vCPU. If KVM unconditionally clears the counter on VMRUN, then when
+ * L1 re-enters L2, the same instruction will trigger a VM-Exit and the
+ * entire cycle start over.
+ */
+ if (vmcb02->save.rip && (svm->nested.ctl.bus_lock_rip == vmcb02->save.rip))
+ vmcb02->control.bus_lock_counter = 1;
+ else
+ vmcb02->control.bus_lock_counter = 0;
+
/* Done at vmrun: asid. */
/* Also overwritten later if necessary. */
@@ -1039,8 +1066,17 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
}
+ /*
+ * Invalidate bus_lock_rip unless KVM is still waiting for the guest
+ * to make forward progress before re-enabling bus lock detection.
+ */
+ if (!vmcb02->control.bus_lock_counter)
+ svm->nested.ctl.bus_lock_rip = INVALID_GPA;
+
nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr);
+ kvm_nested_vmexit_handle_ibrs(vcpu);
+
svm_switch_vmcb(svm, &svm->vmcb01);
/*
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 1aa0f07d3a63..5a69b657dae9 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -561,6 +561,8 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
+ sev->policy = params.policy;
+
memset(&start, 0, sizeof(start));
dh_blob = NULL;
@@ -1593,11 +1595,11 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
/* allocate memory for header and transport buffer */
ret = -ENOMEM;
- hdr = kzalloc(params.hdr_len, GFP_KERNEL_ACCOUNT);
+ hdr = kzalloc(params.hdr_len, GFP_KERNEL);
if (!hdr)
goto e_unpin;
- trans_data = kzalloc(params.trans_len, GFP_KERNEL_ACCOUNT);
+ trans_data = kzalloc(params.trans_len, GFP_KERNEL);
if (!trans_data)
goto e_free_hdr;
@@ -1883,70 +1885,6 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
atomic_set_release(&src_sev->migration_in_progress, 0);
}
-/* vCPU mutex subclasses. */
-enum sev_migration_role {
- SEV_MIGRATION_SOURCE = 0,
- SEV_MIGRATION_TARGET,
- SEV_NR_MIGRATION_ROLES,
-};
-
-static int sev_lock_vcpus_for_migration(struct kvm *kvm,
- enum sev_migration_role role)
-{
- struct kvm_vcpu *vcpu;
- unsigned long i, j;
-
- kvm_for_each_vcpu(i, vcpu, kvm) {
- if (mutex_lock_killable_nested(&vcpu->mutex, role))
- goto out_unlock;
-
-#ifdef CONFIG_PROVE_LOCKING
- if (!i)
- /*
- * Reset the role to one that avoids colliding with
- * the role used for the first vcpu mutex.
- */
- role = SEV_NR_MIGRATION_ROLES;
- else
- mutex_release(&vcpu->mutex.dep_map, _THIS_IP_);
-#endif
- }
-
- return 0;
-
-out_unlock:
-
- kvm_for_each_vcpu(j, vcpu, kvm) {
- if (i == j)
- break;
-
-#ifdef CONFIG_PROVE_LOCKING
- if (j)
- mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_);
-#endif
-
- mutex_unlock(&vcpu->mutex);
- }
- return -EINTR;
-}
-
-static void sev_unlock_vcpus_for_migration(struct kvm *kvm)
-{
- struct kvm_vcpu *vcpu;
- unsigned long i;
- bool first = true;
-
- kvm_for_each_vcpu(i, vcpu, kvm) {
- if (first)
- first = false;
- else
- mutex_acquire(&vcpu->mutex.dep_map,
- SEV_NR_MIGRATION_ROLES, 0, _THIS_IP_);
-
- mutex_unlock(&vcpu->mutex);
- }
-}
-
static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
{
struct kvm_sev_info *dst = to_kvm_sev_info(dst_kvm);
@@ -2084,10 +2022,10 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
charged = true;
}
- ret = sev_lock_vcpus_for_migration(kvm, SEV_MIGRATION_SOURCE);
+ ret = kvm_lock_all_vcpus(kvm);
if (ret)
goto out_dst_cgroup;
- ret = sev_lock_vcpus_for_migration(source_kvm, SEV_MIGRATION_TARGET);
+ ret = kvm_lock_all_vcpus(source_kvm);
if (ret)
goto out_dst_vcpu;
@@ -2101,9 +2039,9 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
ret = 0;
out_source_vcpu:
- sev_unlock_vcpus_for_migration(source_kvm);
+ kvm_unlock_all_vcpus(source_kvm);
out_dst_vcpu:
- sev_unlock_vcpus_for_migration(kvm);
+ kvm_unlock_all_vcpus(kvm);
out_dst_cgroup:
/* Operates on the source on success, on the destination on failure. */
if (charged)
@@ -2200,6 +2138,8 @@ static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (params.policy & SNP_POLICY_MASK_SINGLE_SOCKET)
return -EINVAL;
+ sev->policy = params.policy;
+
sev->snp_context = snp_context_create(kvm, argp);
if (!sev->snp_context)
return -ENOTTY;
@@ -4007,10 +3947,8 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm)
* Unless Creation is deferred until INIT, signal the vCPU to update
* its state.
*/
- if (request != SVM_VMGEXIT_AP_CREATE_ON_INIT) {
- kvm_make_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
- kvm_vcpu_kick(target_vcpu);
- }
+ if (request != SVM_VMGEXIT_AP_CREATE_ON_INIT)
+ kvm_make_request_and_kick(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
return 0;
}
@@ -4468,6 +4406,7 @@ void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
static void sev_es_init_vmcb(struct vcpu_svm *svm)
{
+ struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm);
struct vmcb *vmcb = svm->vmcb01.ptr;
struct kvm_vcpu *vcpu = &svm->vcpu;
@@ -4483,6 +4422,10 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+ if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES))
+ svm->vmcb->control.allowed_sev_features = sev->vmsa_features |
+ VMCB_ALLOWED_SEV_FEATURES_VALID;
+
/* Can't intercept CR register access, HV can't modify CR registers */
svm_clr_intercept(svm, INTERCEPT_CR0_READ);
svm_clr_intercept(svm, INTERCEPT_CR4_READ);
@@ -4943,3 +4886,97 @@ int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
return level;
}
+
+struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ struct vmcb_save_area *vmsa;
+ struct kvm_sev_info *sev;
+ int error = 0;
+ int ret;
+
+ if (!sev_es_guest(vcpu->kvm))
+ return NULL;
+
+ /*
+ * If the VMSA has not yet been encrypted, return a pointer to the
+ * current un-encrypted VMSA.
+ */
+ if (!vcpu->arch.guest_state_protected)
+ return (struct vmcb_save_area *)svm->sev_es.vmsa;
+
+ sev = to_kvm_sev_info(vcpu->kvm);
+
+ /* Check if the SEV policy allows debugging */
+ if (sev_snp_guest(vcpu->kvm)) {
+ if (!(sev->policy & SNP_POLICY_DEBUG))
+ return NULL;
+ } else {
+ if (sev->policy & SEV_POLICY_NODBG)
+ return NULL;
+ }
+
+ if (sev_snp_guest(vcpu->kvm)) {
+ struct sev_data_snp_dbg dbg = {0};
+
+ vmsa = snp_alloc_firmware_page(__GFP_ZERO);
+ if (!vmsa)
+ return NULL;
+
+ dbg.gctx_paddr = __psp_pa(sev->snp_context);
+ dbg.src_addr = svm->vmcb->control.vmsa_pa;
+ dbg.dst_addr = __psp_pa(vmsa);
+
+ ret = sev_do_cmd(SEV_CMD_SNP_DBG_DECRYPT, &dbg, &error);
+
+ /*
+ * Return the target page to a hypervisor page no matter what.
+ * If this fails, the page can't be used, so leak it and don't
+ * try to use it.
+ */
+ if (snp_page_reclaim(vcpu->kvm, PHYS_PFN(__pa(vmsa))))
+ return NULL;
+
+ if (ret) {
+ pr_err("SEV: SNP_DBG_DECRYPT failed ret=%d, fw_error=%d (%#x)\n",
+ ret, error, error);
+ free_page((unsigned long)vmsa);
+
+ return NULL;
+ }
+ } else {
+ struct sev_data_dbg dbg = {0};
+ struct page *vmsa_page;
+
+ vmsa_page = alloc_page(GFP_KERNEL);
+ if (!vmsa_page)
+ return NULL;
+
+ vmsa = page_address(vmsa_page);
+
+ dbg.handle = sev->handle;
+ dbg.src_addr = svm->vmcb->control.vmsa_pa;
+ dbg.dst_addr = __psp_pa(vmsa);
+ dbg.len = PAGE_SIZE;
+
+ ret = sev_do_cmd(SEV_CMD_DBG_DECRYPT, &dbg, &error);
+ if (ret) {
+ pr_err("SEV: SEV_CMD_DBG_DECRYPT failed ret=%d, fw_error=%d (0x%x)\n",
+ ret, error, error);
+ __free_page(vmsa_page);
+
+ return NULL;
+ }
+ }
+
+ return vmsa;
+}
+
+void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa)
+{
+ /* If the VMSA has not yet been encrypted, nothing was allocated */
+ if (!vcpu->arch.guest_state_protected || !vmsa)
+ return;
+
+ free_page((unsigned long)vmsa);
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index ffb34dadff1c..ab9b947dbf4f 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -29,6 +29,7 @@
#include <linux/cc_platform.h>
#include <linux/smp.h>
#include <linux/string_choices.h>
+#include <linux/mutex.h>
#include <asm/apic.h>
#include <asm/msr.h>
@@ -232,6 +233,8 @@ module_param(tsc_scaling, int, 0444);
static bool avic;
module_param(avic, bool, 0444);
+module_param(enable_device_posted_irqs, bool, 0444);
+
bool __read_mostly dump_invalid_vmcb;
module_param(dump_invalid_vmcb, bool, 0644);
@@ -250,6 +253,8 @@ static unsigned long iopm_base;
DEFINE_PER_CPU(struct svm_cpu_data, svm_data);
+static DEFINE_MUTEX(vmcb_dump_mutex);
+
/*
* Only MSR_TSC_AUX is switched via the user return hook. EFER is switched via
* the VMCB, and the SYSCALL/SYSENTER MSRs are handled by VMLOAD/VMSAVE.
@@ -1369,6 +1374,9 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK;
}
+ if (vcpu->kvm->arch.bus_lock_detection_enabled)
+ svm_set_intercept(svm, INTERCEPT_BUSLOCK);
+
if (sev_guest(vcpu->kvm))
sev_init_vmcb(svm);
@@ -1478,25 +1486,10 @@ out:
return err;
}
-static void svm_clear_current_vmcb(struct vmcb *vmcb)
-{
- int i;
-
- for_each_online_cpu(i)
- cmpxchg(per_cpu_ptr(&svm_data.current_vmcb, i), vmcb, NULL);
-}
-
static void svm_vcpu_free(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- /*
- * The vmcb page can be recycled, causing a false negative in
- * svm_vcpu_load(). So, ensure that no logical CPU has this
- * vmcb page recorded as its current vmcb.
- */
- svm_clear_current_vmcb(svm->vmcb);
-
svm_leave_nested(vcpu);
svm_free_nested(svm);
@@ -1610,19 +1603,9 @@ static void svm_prepare_host_switch(struct kvm_vcpu *vcpu)
static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
- struct vcpu_svm *svm = to_svm(vcpu);
- struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
-
if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
shrink_ple_window(vcpu);
- if (sd->current_vmcb != svm->vmcb) {
- sd->current_vmcb = svm->vmcb;
-
- if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT) &&
- static_branch_likely(&switch_vcpu_ibpb))
- indirect_branch_prediction_barrier();
- }
if (kvm_vcpu_apicv_active(vcpu))
avic_vcpu_load(vcpu, cpu);
}
@@ -3221,17 +3204,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
}
/*
- * AMD changed the architectural behavior of bits 5:2. On CPUs
- * without BusLockTrap, bits 5:2 control "external pins", but
- * on CPUs that support BusLockDetect, bit 2 enables BusLockTrap
- * and bits 5:3 are reserved-to-zero. Sadly, old KVM allowed
- * the guest to set bits 5:2 despite not actually virtualizing
- * Performance-Monitoring/Breakpoint external pins. Drop bits
- * 5:2 for backwards compatibility.
- */
- data &= ~GENMASK(5, 2);
-
- /*
* Suppress BTF as KVM doesn't virtualize BTF, but there's no
* way to communicate lack of support to the guest.
*/
@@ -3361,6 +3333,37 @@ static int invpcid_interception(struct kvm_vcpu *vcpu)
return kvm_handle_invpcid(vcpu, type, gva);
}
+static inline int complete_userspace_buslock(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ /*
+ * If userspace has NOT changed RIP, then KVM's ABI is to let the guest
+ * execute the bus-locking instruction. Set the bus lock counter to '1'
+ * to effectively step past the bus lock.
+ */
+ if (kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))
+ svm->vmcb->control.bus_lock_counter = 1;
+
+ return 1;
+}
+
+static int bus_lock_exit(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
+ vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK;
+
+ vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu);
+ vcpu->arch.complete_userspace_io = complete_userspace_buslock;
+
+ if (is_guest_mode(vcpu))
+ svm->nested.ctl.bus_lock_rip = vcpu->arch.cui_linear_rip;
+
+ return 0;
+}
+
static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[SVM_EXIT_READ_CR0] = cr_interception,
[SVM_EXIT_READ_CR3] = cr_interception,
@@ -3430,6 +3433,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[SVM_EXIT_INVPCID] = invpcid_interception,
[SVM_EXIT_IDLE_HLT] = kvm_emulate_halt,
[SVM_EXIT_NPF] = npf_interception,
+ [SVM_EXIT_BUS_LOCK] = bus_lock_exit,
[SVM_EXIT_RSM] = rsm_interception,
[SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception,
[SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception,
@@ -3444,14 +3448,21 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
struct vmcb_control_area *control = &svm->vmcb->control;
struct vmcb_save_area *save = &svm->vmcb->save;
struct vmcb_save_area *save01 = &svm->vmcb01.ptr->save;
+ char *vm_type;
if (!dump_invalid_vmcb) {
pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
return;
}
- pr_err("VMCB %p, last attempted VMRUN on CPU %d\n",
- svm->current_vmcb->ptr, vcpu->arch.last_vmentry_cpu);
+ guard(mutex)(&vmcb_dump_mutex);
+
+ vm_type = sev_snp_guest(vcpu->kvm) ? "SEV-SNP" :
+ sev_es_guest(vcpu->kvm) ? "SEV-ES" :
+ sev_guest(vcpu->kvm) ? "SEV" : "SVM";
+
+ pr_err("%s vCPU%u VMCB %p, last attempted VMRUN on CPU %d\n",
+ vm_type, vcpu->vcpu_id, svm->current_vmcb->ptr, vcpu->arch.last_vmentry_cpu);
pr_err("VMCB Control Area:\n");
pr_err("%-20s%04x\n", "cr_read:", control->intercepts[INTERCEPT_CR] & 0xffff);
pr_err("%-20s%04x\n", "cr_write:", control->intercepts[INTERCEPT_CR] >> 16);
@@ -3489,6 +3500,17 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id);
pr_err("%-20s%016llx\n", "avic_physical_id:", control->avic_physical_id);
pr_err("%-20s%016llx\n", "vmsa_pa:", control->vmsa_pa);
+ pr_err("%-20s%016llx\n", "allowed_sev_features:", control->allowed_sev_features);
+ pr_err("%-20s%016llx\n", "guest_sev_features:", control->guest_sev_features);
+
+ if (sev_es_guest(vcpu->kvm)) {
+ save = sev_decrypt_vmsa(vcpu);
+ if (!save)
+ goto no_vmsa;
+
+ save01 = save;
+ }
+
pr_err("VMCB State Save Area:\n");
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"es:",
@@ -3559,6 +3581,63 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
pr_err("%-15s %016llx %-13s %016llx\n",
"excp_from:", save->last_excp_from,
"excp_to:", save->last_excp_to);
+
+ if (sev_es_guest(vcpu->kvm)) {
+ struct sev_es_save_area *vmsa = (struct sev_es_save_area *)save;
+
+ pr_err("%-15s %016llx\n",
+ "sev_features", vmsa->sev_features);
+
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "rax:", vmsa->rax, "rbx:", vmsa->rbx);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "rcx:", vmsa->rcx, "rdx:", vmsa->rdx);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "rsi:", vmsa->rsi, "rdi:", vmsa->rdi);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "rbp:", vmsa->rbp, "rsp:", vmsa->rsp);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "r8:", vmsa->r8, "r9:", vmsa->r9);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "r10:", vmsa->r10, "r11:", vmsa->r11);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "r12:", vmsa->r12, "r13:", vmsa->r13);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "r14:", vmsa->r14, "r15:", vmsa->r15);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "xcr0:", vmsa->xcr0, "xss:", vmsa->xss);
+ } else {
+ pr_err("%-15s %016llx %-13s %016lx\n",
+ "rax:", save->rax, "rbx:",
+ vcpu->arch.regs[VCPU_REGS_RBX]);
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "rcx:", vcpu->arch.regs[VCPU_REGS_RCX],
+ "rdx:", vcpu->arch.regs[VCPU_REGS_RDX]);
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "rsi:", vcpu->arch.regs[VCPU_REGS_RSI],
+ "rdi:", vcpu->arch.regs[VCPU_REGS_RDI]);
+ pr_err("%-15s %016lx %-13s %016llx\n",
+ "rbp:", vcpu->arch.regs[VCPU_REGS_RBP],
+ "rsp:", save->rsp);
+#ifdef CONFIG_X86_64
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "r8:", vcpu->arch.regs[VCPU_REGS_R8],
+ "r9:", vcpu->arch.regs[VCPU_REGS_R9]);
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "r10:", vcpu->arch.regs[VCPU_REGS_R10],
+ "r11:", vcpu->arch.regs[VCPU_REGS_R11]);
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "r12:", vcpu->arch.regs[VCPU_REGS_R12],
+ "r13:", vcpu->arch.regs[VCPU_REGS_R13]);
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "r14:", vcpu->arch.regs[VCPU_REGS_R14],
+ "r15:", vcpu->arch.regs[VCPU_REGS_R15]);
+#endif
+ }
+
+no_vmsa:
+ if (sev_es_guest(vcpu->kvm))
+ sev_free_decrypted_vmsa(vcpu, save);
}
static bool svm_check_exit_valid(u64 exit_code)
@@ -3595,6 +3674,10 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
return kvm_emulate_halt(vcpu);
else if (exit_code == SVM_EXIT_NPF)
return npf_interception(vcpu);
+#ifdef CONFIG_KVM_AMD_SEV
+ else if (exit_code == SVM_EXIT_VMGEXIT)
+ return sev_handle_vmgexit(vcpu);
+#endif
#endif
return svm_exit_handlers[exit_code](vcpu);
}
@@ -5356,6 +5439,9 @@ static __init void svm_set_cpu_caps(void)
kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
}
+ if (cpu_feature_enabled(X86_FEATURE_BUS_LOCK_THRESHOLD))
+ kvm_caps.has_bus_lock_exit = true;
+
/* CPUID 0x80000008 */
if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
boot_cpu_has(X86_FEATURE_AMD_SSBD))
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f16b068c4228..e6f3c6a153a0 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -98,6 +98,7 @@ struct kvm_sev_info {
unsigned int asid; /* ASID used for this guest */
unsigned int handle; /* SEV firmware handle */
int fd; /* SEV device fd */
+ unsigned long policy;
unsigned long pages_locked; /* Number of pages locked */
struct list_head regions_list; /* List of registered regions */
u64 ap_jump_table; /* SEV-ES AP Jump Table address */
@@ -114,6 +115,9 @@ struct kvm_sev_info {
struct mutex guest_req_mutex; /* Must acquire before using bounce buffers */
};
+#define SEV_POLICY_NODBG BIT_ULL(0)
+#define SNP_POLICY_DEBUG BIT_ULL(19)
+
struct kvm_svm {
struct kvm kvm;
@@ -169,6 +173,7 @@ struct vmcb_ctrl_area_cached {
u64 nested_cr3;
u64 virt_ext;
u32 clean;
+ u64 bus_lock_rip;
union {
#if IS_ENABLED(CONFIG_HYPERV) || IS_ENABLED(CONFIG_KVM_HYPERV)
struct hv_vmcb_enlightenments hv_enlightenments;
@@ -340,8 +345,6 @@ struct svm_cpu_data {
struct vmcb *save_area;
unsigned long save_area_pa;
- struct vmcb *current_vmcb;
-
/* index = sev_asid, value = vmcb pointer */
struct vmcb **sev_vmcbs;
};
@@ -785,6 +788,8 @@ void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
+struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu);
+void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa);
#else
static inline struct page *snp_safe_alloc_page_node(int node, gfp_t gfp)
{
@@ -816,6 +821,11 @@ static inline int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
return 0;
}
+static inline struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu)
+{
+ return NULL;
+}
+static inline void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa) {}
#endif
/* vmenter.S */
diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h
index 8f46a06e2c44..a0c5e8781c33 100644
--- a/arch/x86/kvm/vmx/common.h
+++ b/arch/x86/kvm/vmx/common.h
@@ -71,8 +71,8 @@ static __always_inline bool is_td_vcpu(struct kvm_vcpu *vcpu)
#else
-static inline bool is_td(struct kvm *kvm) { return false; }
-static inline bool is_td_vcpu(struct kvm_vcpu *vcpu) { return false; }
+static __always_inline bool is_td(struct kvm *kvm) { return false; }
+static __always_inline bool is_td_vcpu(struct kvm_vcpu *vcpu) { return false; }
#endif
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 94d5d907d37b..d1e02e567b57 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -12,7 +12,6 @@
#ifdef CONFIG_KVM_INTEL_TDX
static_assert(offsetof(struct vcpu_vmx, vt) == offsetof(struct vcpu_tdx, vt));
-#endif
static void vt_disable_virtualization_cpu(void)
{
@@ -240,7 +239,7 @@ static int vt_complete_emulated_msr(struct kvm_vcpu *vcpu, int err)
if (is_td_vcpu(vcpu))
return tdx_complete_emulated_msr(vcpu, err);
- return kvm_complete_insn_gp(vcpu, err);
+ return vmx_complete_emulated_msr(vcpu, err);
}
#ifdef CONFIG_KVM_SMM
@@ -315,14 +314,6 @@ static void vt_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
return vmx_set_virtual_apic_mode(vcpu);
}
-static void vt_apicv_pre_state_restore(struct kvm_vcpu *vcpu)
-{
- struct pi_desc *pi = vcpu_to_pi_desc(vcpu);
-
- pi_clear_on(pi);
- memset(pi->pir, 0, sizeof(pi->pir));
-}
-
static void vt_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
{
if (is_td_vcpu(vcpu))
@@ -888,6 +879,13 @@ static int vt_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
return 0;
}
+#define vt_op(name) vt_##name
+#define vt_op_tdx_only(name) vt_##name
+#else /* CONFIG_KVM_INTEL_TDX */
+#define vt_op(name) vmx_##name
+#define vt_op_tdx_only(name) NULL
+#endif /* CONFIG_KVM_INTEL_TDX */
+
#define VMX_REQUIRED_APICV_INHIBITS \
(BIT(APICV_INHIBIT_REASON_DISABLED) | \
BIT(APICV_INHIBIT_REASON_ABSENT) | \
@@ -905,113 +903,113 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.hardware_unsetup = vmx_hardware_unsetup,
.enable_virtualization_cpu = vmx_enable_virtualization_cpu,
- .disable_virtualization_cpu = vt_disable_virtualization_cpu,
+ .disable_virtualization_cpu = vt_op(disable_virtualization_cpu),
.emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu,
- .has_emulated_msr = vt_has_emulated_msr,
+ .has_emulated_msr = vt_op(has_emulated_msr),
.vm_size = sizeof(struct kvm_vmx),
- .vm_init = vt_vm_init,
- .vm_pre_destroy = vt_vm_pre_destroy,
- .vm_destroy = vt_vm_destroy,
+ .vm_init = vt_op(vm_init),
+ .vm_destroy = vt_op(vm_destroy),
+ .vm_pre_destroy = vt_op_tdx_only(vm_pre_destroy),
- .vcpu_precreate = vt_vcpu_precreate,
- .vcpu_create = vt_vcpu_create,
- .vcpu_free = vt_vcpu_free,
- .vcpu_reset = vt_vcpu_reset,
+ .vcpu_precreate = vt_op(vcpu_precreate),
+ .vcpu_create = vt_op(vcpu_create),
+ .vcpu_free = vt_op(vcpu_free),
+ .vcpu_reset = vt_op(vcpu_reset),
- .prepare_switch_to_guest = vt_prepare_switch_to_guest,
- .vcpu_load = vt_vcpu_load,
- .vcpu_put = vt_vcpu_put,
+ .prepare_switch_to_guest = vt_op(prepare_switch_to_guest),
+ .vcpu_load = vt_op(vcpu_load),
+ .vcpu_put = vt_op(vcpu_put),
- .update_exception_bitmap = vt_update_exception_bitmap,
+ .update_exception_bitmap = vt_op(update_exception_bitmap),
.get_feature_msr = vmx_get_feature_msr,
- .get_msr = vt_get_msr,
- .set_msr = vt_set_msr,
-
- .get_segment_base = vt_get_segment_base,
- .get_segment = vt_get_segment,
- .set_segment = vt_set_segment,
- .get_cpl = vt_get_cpl,
- .get_cpl_no_cache = vt_get_cpl_no_cache,
- .get_cs_db_l_bits = vt_get_cs_db_l_bits,
- .is_valid_cr0 = vt_is_valid_cr0,
- .set_cr0 = vt_set_cr0,
- .is_valid_cr4 = vt_is_valid_cr4,
- .set_cr4 = vt_set_cr4,
- .set_efer = vt_set_efer,
- .get_idt = vt_get_idt,
- .set_idt = vt_set_idt,
- .get_gdt = vt_get_gdt,
- .set_gdt = vt_set_gdt,
- .set_dr6 = vt_set_dr6,
- .set_dr7 = vt_set_dr7,
- .sync_dirty_debug_regs = vt_sync_dirty_debug_regs,
- .cache_reg = vt_cache_reg,
- .get_rflags = vt_get_rflags,
- .set_rflags = vt_set_rflags,
- .get_if_flag = vt_get_if_flag,
-
- .flush_tlb_all = vt_flush_tlb_all,
- .flush_tlb_current = vt_flush_tlb_current,
- .flush_tlb_gva = vt_flush_tlb_gva,
- .flush_tlb_guest = vt_flush_tlb_guest,
-
- .vcpu_pre_run = vt_vcpu_pre_run,
- .vcpu_run = vt_vcpu_run,
- .handle_exit = vt_handle_exit,
+ .get_msr = vt_op(get_msr),
+ .set_msr = vt_op(set_msr),
+
+ .get_segment_base = vt_op(get_segment_base),
+ .get_segment = vt_op(get_segment),
+ .set_segment = vt_op(set_segment),
+ .get_cpl = vt_op(get_cpl),
+ .get_cpl_no_cache = vt_op(get_cpl_no_cache),
+ .get_cs_db_l_bits = vt_op(get_cs_db_l_bits),
+ .is_valid_cr0 = vt_op(is_valid_cr0),
+ .set_cr0 = vt_op(set_cr0),
+ .is_valid_cr4 = vt_op(is_valid_cr4),
+ .set_cr4 = vt_op(set_cr4),
+ .set_efer = vt_op(set_efer),
+ .get_idt = vt_op(get_idt),
+ .set_idt = vt_op(set_idt),
+ .get_gdt = vt_op(get_gdt),
+ .set_gdt = vt_op(set_gdt),
+ .set_dr6 = vt_op(set_dr6),
+ .set_dr7 = vt_op(set_dr7),
+ .sync_dirty_debug_regs = vt_op(sync_dirty_debug_regs),
+ .cache_reg = vt_op(cache_reg),
+ .get_rflags = vt_op(get_rflags),
+ .set_rflags = vt_op(set_rflags),
+ .get_if_flag = vt_op(get_if_flag),
+
+ .flush_tlb_all = vt_op(flush_tlb_all),
+ .flush_tlb_current = vt_op(flush_tlb_current),
+ .flush_tlb_gva = vt_op(flush_tlb_gva),
+ .flush_tlb_guest = vt_op(flush_tlb_guest),
+
+ .vcpu_pre_run = vt_op(vcpu_pre_run),
+ .vcpu_run = vt_op(vcpu_run),
+ .handle_exit = vt_op(handle_exit),
.skip_emulated_instruction = vmx_skip_emulated_instruction,
.update_emulated_instruction = vmx_update_emulated_instruction,
- .set_interrupt_shadow = vt_set_interrupt_shadow,
- .get_interrupt_shadow = vt_get_interrupt_shadow,
- .patch_hypercall = vt_patch_hypercall,
- .inject_irq = vt_inject_irq,
- .inject_nmi = vt_inject_nmi,
- .inject_exception = vt_inject_exception,
- .cancel_injection = vt_cancel_injection,
- .interrupt_allowed = vt_interrupt_allowed,
- .nmi_allowed = vt_nmi_allowed,
- .get_nmi_mask = vt_get_nmi_mask,
- .set_nmi_mask = vt_set_nmi_mask,
- .enable_nmi_window = vt_enable_nmi_window,
- .enable_irq_window = vt_enable_irq_window,
- .update_cr8_intercept = vt_update_cr8_intercept,
+ .set_interrupt_shadow = vt_op(set_interrupt_shadow),
+ .get_interrupt_shadow = vt_op(get_interrupt_shadow),
+ .patch_hypercall = vt_op(patch_hypercall),
+ .inject_irq = vt_op(inject_irq),
+ .inject_nmi = vt_op(inject_nmi),
+ .inject_exception = vt_op(inject_exception),
+ .cancel_injection = vt_op(cancel_injection),
+ .interrupt_allowed = vt_op(interrupt_allowed),
+ .nmi_allowed = vt_op(nmi_allowed),
+ .get_nmi_mask = vt_op(get_nmi_mask),
+ .set_nmi_mask = vt_op(set_nmi_mask),
+ .enable_nmi_window = vt_op(enable_nmi_window),
+ .enable_irq_window = vt_op(enable_irq_window),
+ .update_cr8_intercept = vt_op(update_cr8_intercept),
.x2apic_icr_is_split = false,
- .set_virtual_apic_mode = vt_set_virtual_apic_mode,
- .set_apic_access_page_addr = vt_set_apic_access_page_addr,
- .refresh_apicv_exec_ctrl = vt_refresh_apicv_exec_ctrl,
- .load_eoi_exitmap = vt_load_eoi_exitmap,
- .apicv_pre_state_restore = vt_apicv_pre_state_restore,
+ .set_virtual_apic_mode = vt_op(set_virtual_apic_mode),
+ .set_apic_access_page_addr = vt_op(set_apic_access_page_addr),
+ .refresh_apicv_exec_ctrl = vt_op(refresh_apicv_exec_ctrl),
+ .load_eoi_exitmap = vt_op(load_eoi_exitmap),
+ .apicv_pre_state_restore = pi_apicv_pre_state_restore,
.required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS,
- .hwapic_isr_update = vt_hwapic_isr_update,
- .sync_pir_to_irr = vt_sync_pir_to_irr,
- .deliver_interrupt = vt_deliver_interrupt,
+ .hwapic_isr_update = vt_op(hwapic_isr_update),
+ .sync_pir_to_irr = vt_op(sync_pir_to_irr),
+ .deliver_interrupt = vt_op(deliver_interrupt),
.dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
- .set_tss_addr = vt_set_tss_addr,
- .set_identity_map_addr = vt_set_identity_map_addr,
+ .set_tss_addr = vt_op(set_tss_addr),
+ .set_identity_map_addr = vt_op(set_identity_map_addr),
.get_mt_mask = vmx_get_mt_mask,
- .get_exit_info = vt_get_exit_info,
- .get_entry_info = vt_get_entry_info,
+ .get_exit_info = vt_op(get_exit_info),
+ .get_entry_info = vt_op(get_entry_info),
- .vcpu_after_set_cpuid = vt_vcpu_after_set_cpuid,
+ .vcpu_after_set_cpuid = vt_op(vcpu_after_set_cpuid),
.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
- .get_l2_tsc_offset = vt_get_l2_tsc_offset,
- .get_l2_tsc_multiplier = vt_get_l2_tsc_multiplier,
- .write_tsc_offset = vt_write_tsc_offset,
- .write_tsc_multiplier = vt_write_tsc_multiplier,
+ .get_l2_tsc_offset = vt_op(get_l2_tsc_offset),
+ .get_l2_tsc_multiplier = vt_op(get_l2_tsc_multiplier),
+ .write_tsc_offset = vt_op(write_tsc_offset),
+ .write_tsc_multiplier = vt_op(write_tsc_multiplier),
- .load_mmu_pgd = vt_load_mmu_pgd,
+ .load_mmu_pgd = vt_op(load_mmu_pgd),
.check_intercept = vmx_check_intercept,
.handle_exit_irqoff = vmx_handle_exit_irqoff,
- .update_cpu_dirty_logging = vt_update_cpu_dirty_logging,
+ .update_cpu_dirty_logging = vt_op(update_cpu_dirty_logging),
.nested_ops = &vmx_nested_ops,
@@ -1019,38 +1017,38 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.pi_start_assignment = vmx_pi_start_assignment,
#ifdef CONFIG_X86_64
- .set_hv_timer = vt_set_hv_timer,
- .cancel_hv_timer = vt_cancel_hv_timer,
+ .set_hv_timer = vt_op(set_hv_timer),
+ .cancel_hv_timer = vt_op(cancel_hv_timer),
#endif
- .setup_mce = vt_setup_mce,
+ .setup_mce = vt_op(setup_mce),
#ifdef CONFIG_KVM_SMM
- .smi_allowed = vt_smi_allowed,
- .enter_smm = vt_enter_smm,
- .leave_smm = vt_leave_smm,
- .enable_smi_window = vt_enable_smi_window,
+ .smi_allowed = vt_op(smi_allowed),
+ .enter_smm = vt_op(enter_smm),
+ .leave_smm = vt_op(leave_smm),
+ .enable_smi_window = vt_op(enable_smi_window),
#endif
- .check_emulate_instruction = vt_check_emulate_instruction,
- .apic_init_signal_blocked = vt_apic_init_signal_blocked,
+ .check_emulate_instruction = vt_op(check_emulate_instruction),
+ .apic_init_signal_blocked = vt_op(apic_init_signal_blocked),
.migrate_timers = vmx_migrate_timers,
- .msr_filter_changed = vt_msr_filter_changed,
- .complete_emulated_msr = vt_complete_emulated_msr,
+ .msr_filter_changed = vt_op(msr_filter_changed),
+ .complete_emulated_msr = vt_op(complete_emulated_msr),
.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
.get_untagged_addr = vmx_get_untagged_addr,
- .mem_enc_ioctl = vt_mem_enc_ioctl,
- .vcpu_mem_enc_ioctl = vt_vcpu_mem_enc_ioctl,
+ .mem_enc_ioctl = vt_op_tdx_only(mem_enc_ioctl),
+ .vcpu_mem_enc_ioctl = vt_op_tdx_only(vcpu_mem_enc_ioctl),
- .private_max_mapping_level = vt_gmem_private_max_mapping_level
+ .private_max_mapping_level = vt_op_tdx_only(gmem_private_max_mapping_level)
};
struct kvm_x86_init_ops vt_init_ops __initdata = {
- .hardware_setup = vt_hardware_setup,
+ .hardware_setup = vt_op(hardware_setup),
.handle_intel_pt_intr = NULL,
.runtime_ops = &vt_x86_ops,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 71701e2414a4..7211c71d4241 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -302,7 +302,7 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
cpu = get_cpu();
prev = vmx->loaded_vmcs;
vmx->loaded_vmcs = vmcs;
- vmx_vcpu_load_vmcs(vcpu, cpu, prev);
+ vmx_vcpu_load_vmcs(vcpu, cpu);
vmx_sync_vmcs_host_state(vmx, prev);
put_cpu();
@@ -825,12 +825,30 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
return 0;
}
+static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
+ vmx->nested.msrs.misc_high);
+
+ return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER;
+}
+
static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
u32 count, u64 addr)
{
if (count == 0)
return 0;
+ /*
+ * Exceeding the limit results in architecturally _undefined_ behavior,
+ * i.e. KVM is allowed to do literally anything in response to a bad
+ * limit. Immediately generate a consistency check so that code that
+ * consumes the count doesn't need to worry about extreme edge cases.
+ */
+ if (count > nested_vmx_max_atomic_switch_msrs(vcpu))
+ return -EINVAL;
+
if (!kvm_vcpu_is_legal_aligned_gpa(vcpu, addr, 16) ||
!kvm_vcpu_is_legal_gpa(vcpu, (addr + count * sizeof(struct vmx_msr_entry) - 1)))
return -EINVAL;
@@ -941,15 +959,6 @@ static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
return 0;
}
-static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
- vmx->nested.msrs.misc_high);
-
- return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER;
-}
-
/*
* Load guest's/host's msr at nested entry/exit.
* return 0 for success, entry index for failure.
@@ -966,7 +975,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
for (i = 0; i < count; i++) {
- if (unlikely(i >= max_msr_list_size))
+ if (WARN_ON_ONCE(i >= max_msr_list_size))
goto fail;
if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
@@ -1054,7 +1063,7 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
for (i = 0; i < count; i++) {
- if (unlikely(i >= max_msr_list_size))
+ if (WARN_ON_ONCE(i >= max_msr_list_size))
return -EINVAL;
if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
@@ -4521,12 +4530,12 @@ static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu,
cpu = get_cpu();
vmx->loaded_vmcs = &vmx->nested.vmcs02;
- vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->vmcs01);
+ vmx_vcpu_load_vmcs(vcpu, cpu);
sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
vmx->loaded_vmcs = &vmx->vmcs01;
- vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->nested.vmcs02);
+ vmx_vcpu_load_vmcs(vcpu, cpu);
put_cpu();
}
@@ -5021,16 +5030,7 @@ void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- /*
- * If IBRS is advertised to the vCPU, KVM must flush the indirect
- * branch predictors when transitioning from L2 to L1, as L1 expects
- * hardware (KVM in this case) to provide separate predictor modes.
- * Bare metal isolates VMX root (host) from VMX non-root (guest), but
- * doesn't isolate different VMCSs, i.e. in this case, doesn't provide
- * separate modes for L2 vs L1.
- */
- if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL))
- indirect_branch_prediction_barrier();
+ kvm_nested_vmexit_handle_ibrs(vcpu);
/* Update any VMCS fields that might have changed while L2 ran */
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 99d1d599ff8c..5c615e5845bf 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -34,7 +34,7 @@ static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock);
#define PI_LOCK_SCHED_OUT SINGLE_DEPTH_NESTING
-struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
+static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
{
return &(to_vt(vcpu)->pi_desc);
}
@@ -148,9 +148,8 @@ after_clear_sn:
static bool vmx_can_use_vtd_pi(struct kvm *kvm)
{
- return irqchip_in_kernel(kvm) && enable_apicv &&
- kvm_arch_has_assigned_device(kvm) &&
- irq_remapping_cap(IRQ_POSTING_CAP);
+ return irqchip_in_kernel(kvm) && kvm_arch_has_irq_bypass() &&
+ kvm_arch_has_assigned_device(kvm);
}
/*
@@ -264,6 +263,14 @@ void __init pi_init_cpu(int cpu)
raw_spin_lock_init(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
}
+void pi_apicv_pre_state_restore(struct kvm_vcpu *vcpu)
+{
+ struct pi_desc *pi = vcpu_to_pi_desc(vcpu);
+
+ pi_clear_on(pi);
+ memset(pi->pir, 0, sizeof(pi->pir));
+}
+
bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
{
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -281,7 +288,7 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
*/
void vmx_pi_start_assignment(struct kvm *kvm)
{
- if (!irq_remapping_cap(IRQ_POSTING_CAP))
+ if (!kvm_arch_has_irq_bypass())
return;
kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK);
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 68605ca7ef68..80499ea0e674 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -5,12 +5,11 @@
#include <linux/bitmap.h>
#include <asm/posted_intr.h>
-struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu);
-
void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu);
void pi_wakeup_handler(void);
void __init pi_init_cpu(int cpu);
+void pi_apicv_pre_state_restore(struct kvm_vcpu *vcpu);
bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu);
int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
uint32_t guest_irq, bool set);
@@ -20,7 +19,7 @@ static inline int pi_find_highest_vector(struct pi_desc *pi_desc)
{
int vec;
- vec = find_last_bit((unsigned long *)pi_desc->pir, 256);
+ vec = find_last_bit(pi_desc->pir, 256);
return vec < 256 ? vec : -1;
}
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index f6986dee6f8c..0a6cf5bff2aa 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -59,8 +59,7 @@
* without the explicit restore, thinks the stack is getting walloped.
* Using an unwind hint is problematic due to x86-64's dynamic alignment.
*/
- mov %_ASM_BP, %_ASM_SP
- pop %_ASM_BP
+ leave
RET
.endm
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b12414108cbf..4953846cb30d 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -117,6 +117,8 @@ module_param(enable_apicv, bool, 0444);
bool __read_mostly enable_ipiv = true;
module_param(enable_ipiv, bool, 0444);
+module_param(enable_device_posted_irqs, bool, 0444);
+
/*
* If nested=1, nested virtualization is supported, i.e., guests may use
* VMX and be a hypervisor for its own guests. If nested=0, guests may not
@@ -772,8 +774,11 @@ void vmx_emergency_disable_virtualization_cpu(void)
return;
list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
- loaded_vmcss_on_cpu_link)
+ loaded_vmcss_on_cpu_link) {
vmcs_clear(v->vmcs);
+ if (v->shadow_vmcs)
+ vmcs_clear(v->shadow_vmcs);
+ }
kvm_cpu_vmxoff();
}
@@ -1445,8 +1450,7 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
}
}
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
- struct loaded_vmcs *buddy)
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
bool already_loaded = vmx->loaded_vmcs->cpu == cpu;
@@ -1473,17 +1477,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
if (prev != vmx->loaded_vmcs->vmcs) {
per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
vmcs_load(vmx->loaded_vmcs->vmcs);
-
- /*
- * No indirect branch prediction barrier needed when switching
- * the active VMCS within a vCPU, unless IBRS is advertised to
- * the vCPU. To minimize the number of IBPBs executed, KVM
- * performs IBPB on nested VM-Exit (a single nested transition
- * may switch the active VMCS multiple times).
- */
- if (static_branch_likely(&switch_vcpu_ibpb) &&
- (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)))
- indirect_branch_prediction_barrier();
}
if (!already_loaded) {
@@ -1522,7 +1515,7 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
shrink_ple_window(vcpu);
- vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
+ vmx_vcpu_load_vmcs(vcpu, cpu);
vmx_vcpu_pi_load(vcpu, cpu);
}
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 6d1e40ecc024..b5758c33c60f 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -354,8 +354,7 @@ static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu)
return vt->exit_intr_info;
}
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
- struct loaded_vmcs *buddy);
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu);
int allocate_vpid(void);
void free_vpid(int vpid);
void vmx_set_constant_host_state(struct vcpu_vmx *vmx);
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 6bf8be570b2e..b4596f651232 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -57,6 +57,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu);
int vmx_get_feature_msr(u32 msr, u64 *data);
int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
+#define vmx_complete_emulated_msr kvm_complete_insn_gp
u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg);
void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
@@ -163,71 +164,6 @@ void tdx_flush_tlb_current(struct kvm_vcpu *vcpu);
void tdx_flush_tlb_all(struct kvm_vcpu *vcpu);
void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
-#else
-static inline void tdx_disable_virtualization_cpu(void) {}
-static inline int tdx_vm_init(struct kvm *kvm) { return -EOPNOTSUPP; }
-static inline void tdx_mmu_release_hkid(struct kvm *kvm) {}
-static inline void tdx_vm_destroy(struct kvm *kvm) {}
-static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; }
-
-static inline int tdx_vcpu_create(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; }
-static inline void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) {}
-static inline void tdx_vcpu_free(struct kvm_vcpu *vcpu) {}
-static inline void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) {}
-static inline int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; }
-static inline fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
-{
- return EXIT_FASTPATH_NONE;
-}
-static inline void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) {}
-static inline void tdx_vcpu_put(struct kvm_vcpu *vcpu) {}
-static inline bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu) { return false; }
-static inline int tdx_handle_exit(struct kvm_vcpu *vcpu,
- enum exit_fastpath_completion fastpath) { return 0; }
-
-static inline void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
- int trig_mode, int vector) {}
-static inline void tdx_inject_nmi(struct kvm_vcpu *vcpu) {}
-static inline void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1,
- u64 *info2, u32 *intr_info, u32 *error_code) {}
-static inline bool tdx_has_emulated_msr(u32 index) { return false; }
-static inline int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; }
-static inline int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; }
-
-static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }
-
-static inline int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn,
- enum pg_level level,
- void *private_spt)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn,
- enum pg_level level,
- void *private_spt)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
- enum pg_level level,
- kvm_pfn_t pfn)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
- enum pg_level level,
- kvm_pfn_t pfn)
-{
- return -EOPNOTSUPP;
-}
-
-static inline void tdx_flush_tlb_current(struct kvm_vcpu *vcpu) {}
-static inline void tdx_flush_tlb_all(struct kvm_vcpu *vcpu) {}
-static inline void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) {}
-static inline int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn) { return 0; }
#endif
#endif /* __KVM_X86_VMX_X86_OPS_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 570e7f8cbf64..b58a74c1722d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -226,6 +226,9 @@ EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
bool __read_mostly enable_apicv = true;
EXPORT_SYMBOL_GPL(enable_apicv);
+bool __read_mostly enable_device_posted_irqs = true;
+EXPORT_SYMBOL_GPL(enable_device_posted_irqs);
+
const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
KVM_GENERIC_VM_STATS(),
STATS_DESC_COUNTER(VM, mmu_shadow_zapped),
@@ -4990,6 +4993,8 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
return kvm_arch_has_noncoherent_dma(vcpu->kvm);
}
+static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu);
+
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -5012,6 +5017,19 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
kvm_x86_call(vcpu_load)(vcpu, cpu);
+ if (vcpu != per_cpu(last_vcpu, cpu)) {
+ /*
+ * Flush the branch predictor when switching vCPUs on the same
+ * physical CPU, as each vCPU needs its own branch prediction
+ * domain. No IBPB is needed when switching between L1 and L2
+ * on the same vCPU unless IBRS is advertised to the vCPU; that
+ * is handled on the nested VM-Exit path.
+ */
+ if (static_branch_likely(&switch_vcpu_ibpb))
+ indirect_branch_prediction_barrier();
+ per_cpu(last_vcpu, cpu) = vcpu;
+ }
+
/* Save host pkru register if supported */
vcpu->arch.host_pkru = read_pkru();
@@ -7326,10 +7344,13 @@ set_pit2_out:
r = READ_ONCE(kvm->arch.default_tsc_khz);
goto out;
}
- case KVM_MEMORY_ENCRYPT_OP: {
+ case KVM_MEMORY_ENCRYPT_OP:
+ r = -ENOTTY;
+ if (!kvm_x86_ops.mem_enc_ioctl)
+ goto out;
+
r = kvm_x86_call(mem_enc_ioctl)(kvm, argp);
break;
- }
case KVM_MEMORY_ENCRYPT_REG_REGION: {
struct kvm_enc_region region;
@@ -8023,7 +8044,7 @@ static int emulator_read_write(struct x86_emulate_ctxt *ctxt,
return rc;
if (!vcpu->mmio_nr_fragments)
- return rc;
+ return X86EMUL_CONTINUE;
gpa = vcpu->mmio_fragments[0].gpa;
@@ -9361,7 +9382,7 @@ static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
{
vcpu->arch.pio.count = 0;
- if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip)))
+ if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip)))
return 1;
return kvm_skip_emulated_instruction(vcpu);
@@ -9386,7 +9407,7 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
complete_fast_pio_out_port_0x7e;
kvm_skip_emulated_instruction(vcpu);
} else {
- vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
+ vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu);
vcpu->arch.complete_userspace_io = complete_fast_pio_out;
}
return 0;
@@ -9399,7 +9420,7 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
/* We should only ever be called with arch.pio.count equal to 1 */
BUG_ON(vcpu->arch.pio.count != 1);
- if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) {
+ if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))) {
vcpu->arch.pio.count = 0;
return 1;
}
@@ -9428,7 +9449,7 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size,
return ret;
}
- vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
+ vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu);
vcpu->arch.complete_userspace_io = complete_fast_pio_in;
return 0;
@@ -9811,6 +9832,9 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
if (r != 0)
goto out_mmu_exit;
+ enable_device_posted_irqs &= enable_apicv &&
+ irq_remapping_cap(IRQ_POSTING_CAP);
+
kvm_ops_update(ops);
for_each_online_cpu(cpu) {
@@ -10694,6 +10718,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
return;
bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256);
+ vcpu->arch.highest_stale_pending_ioapic_eoi = -1;
kvm_x86_call(sync_pir_to_irr)(vcpu);
@@ -12419,13 +12444,16 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
- int idx;
+ int idx, cpu;
kvm_clear_async_pf_completion_queue(vcpu);
kvm_mmu_unload(vcpu);
kvmclock_reset(vcpu);
+ for_each_possible_cpu(cpu)
+ cmpxchg(per_cpu_ptr(&last_vcpu, cpu), vcpu, NULL);
+
kvm_x86_call(vcpu_free)(vcpu);
kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 88a9475899c8..832f0faf4779 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -121,6 +121,24 @@ static inline void kvm_leave_nested(struct kvm_vcpu *vcpu)
kvm_x86_ops.nested_ops->leave_nested(vcpu);
}
+/*
+ * If IBRS is advertised to the vCPU, KVM must flush the indirect branch
+ * predictors when transitioning from L2 to L1, as L1 expects hardware (KVM in
+ * this case) to provide separate predictor modes. Bare metal isolates the host
+ * from the guest, but doesn't isolate different guests from one another (in
+ * this case L1 and L2). The exception is if bare metal supports same mode IBRS,
+ * which offers protection within the same mode, and hence protects L1 from L2.
+ */
+static inline void kvm_nested_vmexit_handle_ibrs(struct kvm_vcpu *vcpu)
+{
+ if (cpu_feature_enabled(X86_FEATURE_AMD_IBRS_SAME_MODE))
+ return;
+
+ if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) ||
+ guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBRS))
+ indirect_branch_prediction_barrier();
+}
+
static inline bool kvm_vcpu_has_run(struct kvm_vcpu *vcpu)
{
return vcpu->arch.last_vmentry_cpu != -1;
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 4933fb337983..c1efd5b0d198 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -8,13 +8,13 @@ obj-$(CONFIG_PCI_OLPC) += olpc.o
obj-$(CONFIG_PCI_XEN) += xen.o
obj-y += fixup.o
-obj-$(CONFIG_X86_INTEL_CE) += ce4100.o
obj-$(CONFIG_ACPI) += acpi.o
obj-y += legacy.o irq.o
-obj-$(CONFIG_X86_NUMACHIP) += numachip.o
+obj-$(CONFIG_X86_INTEL_CE) += ce4100.o
+obj-$(CONFIG_X86_INTEL_MID) += intel_mid.o
-obj-$(CONFIG_X86_INTEL_MID) += intel_mid_pci.o
+obj-$(CONFIG_X86_NUMACHIP) += numachip.o
obj-y += common.o early.o
obj-y += bus_numa.o
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid.c
index b433b1753016..b433b1753016 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid.c
diff --git a/arch/xtensa/Kbuild b/arch/xtensa/Kbuild
index fd12f61745ba..015baeb765b9 100644
--- a/arch/xtensa/Kbuild
+++ b/arch/xtensa/Kbuild
@@ -1,2 +1,2 @@
# SPDX-License-Identifier: GPL-2.0-only
-obj-y += kernel/ mm/ platforms/ boot/dts/
+obj-y += kernel/ mm/ platforms/
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index d3db28f2f811..f2f9cd9cde50 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -20,6 +20,7 @@ config XTENSA
select ARCH_USE_QUEUED_SPINLOCKS
select ARCH_WANT_IPC_PARSE_VERSION
select BUILDTIME_TABLE_SORT
+ select GENERIC_BUILTIN_DTB
select CLONE_BACKWARDS
select COMMON_CLK
select DMA_NONCOHERENT_MMAP if MMU
@@ -462,7 +463,7 @@ config USE_OF
help
Include support for flattened device tree machine descriptions.
-config BUILTIN_DTB_SOURCE
+config BUILTIN_DTB_NAME
string "DTB to build into the kernel image"
depends on OF
diff --git a/arch/xtensa/boot/dts/Makefile b/arch/xtensa/boot/dts/Makefile
index d6408c16d74e..7271294ce523 100644
--- a/arch/xtensa/boot/dts/Makefile
+++ b/arch/xtensa/boot/dts/Makefile
@@ -7,7 +7,7 @@
#
#
-obj-$(CONFIG_OF) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_SOURCE))
+dtb-$(CONFIG_OF) += $(addsuffix .dtb, $(CONFIG_BUILTIN_DTB_NAME))
# for CONFIG_OF_ALL_DTBS test
dtb- := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts))
diff --git a/arch/xtensa/configs/audio_kc705_defconfig b/arch/xtensa/configs/audio_kc705_defconfig
index 436b7cac9694..f2af1a32c9c7 100644
--- a/arch/xtensa/configs/audio_kc705_defconfig
+++ b/arch/xtensa/configs/audio_kc705_defconfig
@@ -30,7 +30,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0"
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="kc705"
+CONFIG_BUILTIN_DTB_NAME="kc705"
# CONFIG_COMPACTION is not set
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_PM=y
diff --git a/arch/xtensa/configs/cadence_csp_defconfig b/arch/xtensa/configs/cadence_csp_defconfig
index 49f50d1bd724..88ed5284e21c 100644
--- a/arch/xtensa/configs/cadence_csp_defconfig
+++ b/arch/xtensa/configs/cadence_csp_defconfig
@@ -34,7 +34,7 @@ CONFIG_HIGHMEM=y
# CONFIG_PCI is not set
CONFIG_XTENSA_PLATFORM_XTFPGA=y
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="csp"
+CONFIG_BUILTIN_DTB_NAME="csp"
# CONFIG_COMPACTION is not set
CONFIG_XTFPGA_LCD=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
diff --git a/arch/xtensa/configs/common_defconfig b/arch/xtensa/configs/common_defconfig
index fa9389869154..09e4a1d9d1f3 100644
--- a/arch/xtensa/configs/common_defconfig
+++ b/arch/xtensa/configs/common_defconfig
@@ -32,7 +32,6 @@ CONFIG_NET_SCH_TEQL=m
CONFIG_NET_SCH_TBF=m
CONFIG_NET_SCH_GRED=m
CONFIG_NET_SCH_DSMARK=m
-CONFIG_NET_CLS_TCINDEX=m
CONFIG_NET_CLS_ROUTE4=m
CONFIG_NET_CLS_FW=m
CONFIG_NET_CLS_U32=m
diff --git a/arch/xtensa/configs/generic_kc705_defconfig b/arch/xtensa/configs/generic_kc705_defconfig
index e376238bc5ca..4427907becca 100644
--- a/arch/xtensa/configs/generic_kc705_defconfig
+++ b/arch/xtensa/configs/generic_kc705_defconfig
@@ -29,7 +29,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0"
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="kc705"
+CONFIG_BUILTIN_DTB_NAME="kc705"
# CONFIG_COMPACTION is not set
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_NET=y
diff --git a/arch/xtensa/configs/nommu_kc705_defconfig b/arch/xtensa/configs/nommu_kc705_defconfig
index c2ab4306ee20..5828228522ba 100644
--- a/arch/xtensa/configs/nommu_kc705_defconfig
+++ b/arch/xtensa/configs/nommu_kc705_defconfig
@@ -36,7 +36,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0x9d050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=256M@0x60000000"
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="kc705_nommu"
+CONFIG_BUILTIN_DTB_NAME="kc705_nommu"
CONFIG_BINFMT_FLAT=y
CONFIG_NET=y
CONFIG_PACKET=y
diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig
index 63b56ce79f83..326966ca7831 100644
--- a/arch/xtensa/configs/smp_lx200_defconfig
+++ b/arch/xtensa/configs/smp_lx200_defconfig
@@ -33,7 +33,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=96M@0"
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="lx200mx"
+CONFIG_BUILTIN_DTB_NAME="lx200mx"
# CONFIG_COMPACTION is not set
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_NET=y
diff --git a/arch/xtensa/configs/virt_defconfig b/arch/xtensa/configs/virt_defconfig
index 98acb7191cb7..e37048985b47 100644
--- a/arch/xtensa/configs/virt_defconfig
+++ b/arch/xtensa/configs/virt_defconfig
@@ -24,7 +24,7 @@ CONFIG_HIGHMEM=y
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x80000000@0"
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="virt"
+CONFIG_BUILTIN_DTB_NAME="virt"
# CONFIG_PARSE_BOOTPARAM is not set
CONFIG_JUMP_LABEL=y
CONFIG_MODULES=y
diff --git a/arch/xtensa/configs/xip_kc705_defconfig b/arch/xtensa/configs/xip_kc705_defconfig
index 165652c45b85..ee47438f9b51 100644
--- a/arch/xtensa/configs/xip_kc705_defconfig
+++ b/arch/xtensa/configs/xip_kc705_defconfig
@@ -29,7 +29,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0"
CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB_SOURCE="kc705"
+CONFIG_BUILTIN_DTB_NAME="kc705"
# CONFIG_PARSE_BOOTPARAM is not set
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
# CONFIG_COMPACTION is not set
diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h
index 86c70117371b..4871e5a4d6fb 100644
--- a/arch/xtensa/include/asm/ptrace.h
+++ b/arch/xtensa/include/asm/ptrace.h
@@ -72,13 +72,10 @@ struct pt_regs {
/* Additional configurable registers that are used by the compiler. */
xtregs_opt_t xtregs_opt;
- /* Make sure the areg field is 16 bytes aligned. */
- int align[0] __attribute__ ((aligned(16)));
-
/* current register frame.
* Note: The ESF for kernel exceptions ends after 16 registers!
*/
- unsigned long areg[XCHAL_NUM_AREGS];
+ unsigned long areg[XCHAL_NUM_AREGS] __aligned(16);
};
# define arch_has_single_step() (1)