summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu')
-rw-r--r--arch/x86/kernel/cpu/common.c8
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c91
-rw-r--r--arch/x86/kernel/cpu/resctrl/pseudo_lock.c41
3 files changed, 109 insertions, 31 deletions
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 6d75fab10161..382d4e6b848d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1280,11 +1280,11 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS),
VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO),
VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED),
VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED),
- VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED),
VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS),
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 0100468e72ca..e6bba12c759c 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -32,6 +32,7 @@
#include <asm/nmi.h>
#include <clocksource/hyperv_timer.h>
#include <asm/numa.h>
+#include <asm/svm.h>
/* Is Linux running as the root partition? */
bool hv_root_partition;
@@ -39,6 +40,10 @@ bool hv_root_partition;
bool hv_nested;
struct ms_hyperv_info ms_hyperv;
+/* Used in modules via hv_do_hypercall(): see arch/x86/include/asm/mshyperv.h */
+bool hyperv_paravisor_present __ro_after_init;
+EXPORT_SYMBOL_GPL(hyperv_paravisor_present);
+
#if IS_ENABLED(CONFIG_HYPERV)
static inline unsigned int hv_get_nested_reg(unsigned int reg)
{
@@ -65,8 +70,8 @@ u64 hv_get_non_nested_register(unsigned int reg)
{
u64 value;
- if (hv_is_synic_reg(reg) && hv_isolation_type_snp())
- hv_ghcb_msr_read(reg, &value);
+ if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present)
+ hv_ivm_msr_read(reg, &value);
else
rdmsrl(reg, value);
return value;
@@ -75,8 +80,8 @@ EXPORT_SYMBOL_GPL(hv_get_non_nested_register);
void hv_set_non_nested_register(unsigned int reg, u64 value)
{
- if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) {
- hv_ghcb_msr_write(reg, value);
+ if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present) {
+ hv_ivm_msr_write(reg, value);
/* Write proxy bit via wrmsl instruction */
if (hv_is_sint_reg(reg))
@@ -295,6 +300,15 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus)
native_smp_prepare_cpus(max_cpus);
+ /*
+ * Override wakeup_secondary_cpu_64 callback for SEV-SNP
+ * enlightened guest.
+ */
+ if (!ms_hyperv.paravisor_present && hv_isolation_type_snp()) {
+ apic->wakeup_secondary_cpu_64 = hv_snp_boot_ap;
+ return;
+ }
+
#ifdef CONFIG_X86_64
for_each_present_cpu(i) {
if (i == 0)
@@ -313,6 +327,26 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus)
}
#endif
+/*
+ * When a fully enlightened TDX VM runs on Hyper-V, the firmware sets the
+ * HW_REDUCED flag: refer to acpi_tb_create_local_fadt(). Consequently ttyS0
+ * interrupts can't work because request_irq() -> ... -> irq_to_desc() returns
+ * NULL for ttyS0. This happens because mp_config_acpi_legacy_irqs() sees a
+ * nr_legacy_irqs() of 0, so it doesn't initialize the array 'mp_irqs[]', and
+ * later setup_IO_APIC_irqs() -> find_irq_entry() fails to find the legacy irqs
+ * from the array and hence doesn't create the necessary irq description info.
+ *
+ * Clone arch/x86/kernel/acpi/boot.c: acpi_generic_reduced_hw_init() here,
+ * except don't change 'legacy_pic', which keeps its default value
+ * 'default_legacy_pic'. This way, mp_config_acpi_legacy_irqs() sees a non-zero
+ * nr_legacy_irqs() and eventually serial console interrupts works properly.
+ */
+static void __init reduced_hw_init(void)
+{
+ x86_init.timers.timer_init = x86_init_noop;
+ x86_init.irqs.pre_vector_init = x86_init_noop;
+}
+
static void __init ms_hyperv_init_platform(void)
{
int hv_max_functions_eax;
@@ -399,11 +433,33 @@ static void __init ms_hyperv_init_platform(void)
ms_hyperv.shared_gpa_boundary =
BIT_ULL(ms_hyperv.shared_gpa_boundary_bits);
+ hyperv_paravisor_present = !!ms_hyperv.paravisor_present;
+
pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n",
ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b);
- if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP)
+
+ if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) {
static_branch_enable(&isolation_type_snp);
+ } else if (hv_get_isolation_type() == HV_ISOLATION_TYPE_TDX) {
+ static_branch_enable(&isolation_type_tdx);
+
+ /* A TDX VM must use x2APIC and doesn't use lazy EOI. */
+ ms_hyperv.hints &= ~HV_X64_APIC_ACCESS_RECOMMENDED;
+
+ if (!ms_hyperv.paravisor_present) {
+ /* To be supported: more work is required. */
+ ms_hyperv.features &= ~HV_MSR_REFERENCE_TSC_AVAILABLE;
+
+ /* HV_REGISTER_CRASH_CTL is unsupported. */
+ ms_hyperv.misc_features &= ~HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
+
+ /* Don't trust Hyper-V's TLB-flushing hypercalls. */
+ ms_hyperv.hints &= ~HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED;
+
+ x86_init.acpi.reduced_hw_early_init = reduced_hw_init;
+ }
+ }
}
if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) {
@@ -473,7 +529,7 @@ static void __init ms_hyperv_init_platform(void)
#if IS_ENABLED(CONFIG_HYPERV)
if ((hv_get_isolation_type() == HV_ISOLATION_TYPE_VBS) ||
- (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP))
+ ms_hyperv.paravisor_present)
hv_vtom_init();
/*
* Setup the hook to get control post apic initialization.
@@ -497,7 +553,8 @@ static void __init ms_hyperv_init_platform(void)
# ifdef CONFIG_SMP
smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu;
- if (hv_root_partition)
+ if (hv_root_partition ||
+ (!ms_hyperv.paravisor_present && hv_isolation_type_snp()))
smp_ops.smp_prepare_cpus = hv_smp_prepare_cpus;
# endif
@@ -560,6 +617,22 @@ static bool __init ms_hyperv_msi_ext_dest_id(void)
return eax & HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE;
}
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+static void hv_sev_es_hcall_prepare(struct ghcb *ghcb, struct pt_regs *regs)
+{
+ /* RAX and CPL are already in the GHCB */
+ ghcb_set_rcx(ghcb, regs->cx);
+ ghcb_set_rdx(ghcb, regs->dx);
+ ghcb_set_r8(ghcb, regs->r8);
+}
+
+static bool hv_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs)
+{
+ /* No checking of the return state needed */
+ return true;
+}
+#endif
+
const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
.name = "Microsoft Hyper-V",
.detect = ms_hyperv_platform,
@@ -567,4 +640,8 @@ const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
.init.x2apic_available = ms_hyperv_x2apic_available,
.init.msi_ext_dest_id = ms_hyperv_msi_ext_dest_id,
.init.init_platform = ms_hyperv_init_platform,
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ .runtime.sev_es_hcall_prepare = hv_sev_es_hcall_prepare,
+ .runtime.sev_es_hcall_finish = hv_sev_es_hcall_finish,
+#endif
};
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 458cb7419502..8f559eeae08e 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -45,7 +45,21 @@ static u64 prefetch_disable_bits;
*/
static unsigned int pseudo_lock_major;
static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0);
-static struct class *pseudo_lock_class;
+
+static char *pseudo_lock_devnode(const struct device *dev, umode_t *mode)
+{
+ const struct rdtgroup *rdtgrp;
+
+ rdtgrp = dev_get_drvdata(dev);
+ if (mode)
+ *mode = 0600;
+ return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name);
+}
+
+static const struct class pseudo_lock_class = {
+ .name = "pseudo_lock",
+ .devnode = pseudo_lock_devnode,
+};
/**
* get_prefetch_disable_bits - prefetch disable bits of supported platforms
@@ -1353,7 +1367,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
&pseudo_measure_fops);
}
- dev = device_create(pseudo_lock_class, NULL,
+ dev = device_create(&pseudo_lock_class, NULL,
MKDEV(pseudo_lock_major, new_minor),
rdtgrp, "%s", rdtgrp->kn->name);
@@ -1383,7 +1397,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
goto out;
out_device:
- device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
+ device_destroy(&pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
out_debugfs:
debugfs_remove_recursive(plr->debugfs_dir);
pseudo_lock_minor_release(new_minor);
@@ -1424,7 +1438,7 @@ void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
pseudo_lock_cstates_relax(plr);
debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
- device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
+ device_destroy(&pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
pseudo_lock_minor_release(plr->minor);
free:
@@ -1560,16 +1574,6 @@ static const struct file_operations pseudo_lock_dev_fops = {
.mmap = pseudo_lock_dev_mmap,
};
-static char *pseudo_lock_devnode(const struct device *dev, umode_t *mode)
-{
- const struct rdtgroup *rdtgrp;
-
- rdtgrp = dev_get_drvdata(dev);
- if (mode)
- *mode = 0600;
- return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name);
-}
-
int rdt_pseudo_lock_init(void)
{
int ret;
@@ -1580,21 +1584,18 @@ int rdt_pseudo_lock_init(void)
pseudo_lock_major = ret;
- pseudo_lock_class = class_create("pseudo_lock");
- if (IS_ERR(pseudo_lock_class)) {
- ret = PTR_ERR(pseudo_lock_class);
+ ret = class_register(&pseudo_lock_class);
+ if (ret) {
unregister_chrdev(pseudo_lock_major, "pseudo_lock");
return ret;
}
- pseudo_lock_class->devnode = pseudo_lock_devnode;
return 0;
}
void rdt_pseudo_lock_release(void)
{
- class_destroy(pseudo_lock_class);
- pseudo_lock_class = NULL;
+ class_unregister(&pseudo_lock_class);
unregister_chrdev(pseudo_lock_major, "pseudo_lock");
pseudo_lock_major = 0;
}
generated by cgit v1.2.3 (git 2.25.1) at 2025-11-14 23:12:03 +0000