Merge tag 'hyperv-next-signed-20230902' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - Support for SEV-SNP guests on Hyper-V (Tianyu Lan)

 - Support for TDX guests on Hyper-V (Dexuan Cui)

 - Use SBRM API in Hyper-V balloon driver (Mitchell Levy)

 - Avoid dereferencing ACPI root object handle in VMBus driver (Maciej
   Szmigiero)

 - A few misecllaneous fixes (Jiapeng Chong, Nathan Chancellor, Saurabh
   Sengar)

* tag 'hyperv-next-signed-20230902' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux: (24 commits)
  x86/hyperv: Remove duplicate include
  x86/hyperv: Move the code in ivm.c around to avoid unnecessary ifdef's
  x86/hyperv: Remove hv_isolation_type_en_snp
  x86/hyperv: Use TDX GHCI to access some MSRs in a TDX VM with the paravisor
  Drivers: hv: vmbus: Bring the post_msg_page back for TDX VMs with the paravisor
  x86/hyperv: Introduce a global variable hyperv_paravisor_present
  Drivers: hv: vmbus: Support >64 VPs for a fully enlightened TDX/SNP VM
  x86/hyperv: Fix serial console interrupts for fully enlightened TDX guests
  Drivers: hv: vmbus: Support fully enlightened TDX guests
  x86/hyperv: Support hypercalls for fully enlightened TDX guests
  x86/hyperv: Add hv_isolation_type_tdx() to detect TDX guests
  x86/hyperv: Fix undefined reference to isolation_type_en_snp without CONFIG_HYPERV
  x86/hyperv: Add missing 'inline' to hv_snp_boot_ap() stub
  hv: hyperv.h: Replace one-element array with flexible-array member
  Drivers: hv: vmbus: Don't dereference ACPI root object handle
  x86/hyperv: Add hyperv-specific handling for VMMCALL under SEV-ES
  x86/hyperv: Add smp support for SEV-SNP guest
  clocksource: hyper-v: Mark hyperv tsc page unencrypted in sev-snp enlightened guest
  x86/hyperv: Use vmmcall to implement Hyper-V hypercall in sev-snp enlightened guest
  drivers: hv: Mark percpu hvcall input arg page unencrypted in SEV-SNP enlightened guest
  ...

1 files changed, 84 insertions, 7 deletions

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
 };