Only build amd64

Documentation/virt/kvm/api.rst

@@ -6747,6 +6747,10 @@ the first `ndata` items (possibly zero) of the data array are valid.
    the guest issued a SYSTEM_RESET2 call according to v1.1 of the PSCI
    specification.
 
+ - for arm64, data[0] is set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2
+   if the guest issued a SYSTEM_OFF2 call according to v1.3 of the PSCI
+   specification.
+
  - for RISC-V, data[0] is set to the value of the second argument of the
    ``sbi_system_reset`` call.
 
@@ -6780,6 +6784,13 @@ either:
  - Deny the guest request to suspend the VM. See ARM DEN0022D.b 5.19.2
    "Caller responsibilities" for possible return values.
 
+Hibernation using the PSCI SYSTEM_OFF2 call is enabled when PSCI v1.3
+is enabled. If a guest invokes the PSCI SYSTEM_OFF2 function, KVM will
+exit to userspace with the KVM_SYSTEM_EVENT_SHUTDOWN event type and with
+data[0] set to KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2. The only
+supported hibernate type for the SYSTEM_OFF2 function is HIBERNATE_OFF
+0x0).
+
 ::
 
 		/* KVM_EXIT_IOAPIC_EOI */

MAINTAINERS

@@ -21611,6 +21611,7 @@ M:	Thierry Reding <[email protected]>
 R:	Krishna Reddy <[email protected]>
 L:	[email protected]
 S:	Supported
+F:	drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
 F:	drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
 F:	drivers/iommu/tegra*
 

Ubuntu.md

@@ -1,8 +1,8 @@
-Name:    linux
-Version: 6.1.0
+Name:    linux-aws
+Version: 6.2.0
 Series:  23.04 (lunar)
 Description:
     This is the source code for the Ubuntu linux kernel for the 23.04 series. This
-    source tree is used to produce the flavours: generic, generic-64k, generic-lpae.
+    source tree is used to produce the flavours: aws.
     This kernel is configured to support the widest range of desktop, laptop and
     server configurations.

arch/arm64/include/asm/pgtable.h

@@ -261,9 +261,14 @@ static inline pte_t pte_mkdevmap(pte_t pte)
 	return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL));
 }
 
-static inline void set_pte(pte_t *ptep, pte_t pte)
+static inline void __set_pte_nosync(pte_t *ptep, pte_t pte)
 {
 	WRITE_ONCE(*ptep, pte);
+}
+
+static inline void set_pte(pte_t *ptep, pte_t pte)
+{
+	__set_pte_nosync(ptep, pte);
 
 	/*
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance

arch/arm64/include/uapi/asm/kvm.h

@@ -481,6 +481,12 @@ enum {
  */
 #define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2	(1ULL << 0)
 
+/*
+ * Shutdown caused by a PSCI v1.3 SYSTEM_OFF2 call.
+ * Valid only when the system event has a type of KVM_SYSTEM_EVENT_SHUTDOWN.
+ */
+#define KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2	(1ULL << 0)
+
 /* run->fail_entry.hardware_entry_failure_reason codes. */
 #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED	(1ULL << 0)
 

arch/arm64/kernel/acpi.c

@@ -26,6 +26,7 @@
 #include <linux/libfdt.h>
 #include <linux/smp.h>
 #include <linux/serial_core.h>
+#include <linux/suspend.h>
 #include <linux/pgtable.h>
 
 #include <acpi/ghes.h>
@@ -227,6 +228,15 @@ void __init acpi_boot_table_init(void)
 		if (earlycon_acpi_spcr_enable)
 			early_init_dt_scan_chosen_stdout();
 	} else {
+#ifdef CONFIG_HIBERNATION
+		struct acpi_table_header *facs = NULL;
+		acpi_get_table(ACPI_SIG_FACS, 1, &facs);
+		if (facs) {
+			swsusp_hardware_signature =
+				((struct acpi_table_facs *)facs)->hardware_signature;
+			acpi_put_table(facs);
+		}
+#endif
 		acpi_parse_spcr(earlycon_acpi_spcr_enable, true);
 		if (IS_ENABLED(CONFIG_ACPI_BGRT))
 			acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);

arch/arm64/kvm/hyp/nvhe/psci-relay.c

@@ -265,6 +265,8 @@ static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_
 	case PSCI_1_0_FN_PSCI_FEATURES:
 	case PSCI_1_0_FN_SET_SUSPEND_MODE:
 	case PSCI_1_1_FN64_SYSTEM_RESET2:
+	case PSCI_1_3_FN_SYSTEM_OFF2:
+	case PSCI_1_3_FN64_SYSTEM_OFF2:
 		return psci_forward(host_ctxt);
 	case PSCI_1_0_FN64_SYSTEM_SUSPEND:
 		return psci_system_suspend(func_id, host_ctxt);

arch/arm64/kvm/hypercalls.c

@@ -575,6 +575,8 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		case KVM_ARM_PSCI_0_2:
 		case KVM_ARM_PSCI_1_0:
 		case KVM_ARM_PSCI_1_1:
+		case KVM_ARM_PSCI_1_2:
+		case KVM_ARM_PSCI_1_3:
 			if (!wants_02)
 				return -EINVAL;
 			vcpu->kvm->arch.psci_version = val;

arch/arm64/kvm/psci.c

@@ -194,6 +194,12 @@ static void kvm_psci_system_off(struct kvm_vcpu *vcpu)
 	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN, 0);
 }
 
+static void kvm_psci_system_off2(struct kvm_vcpu *vcpu)
+{
+	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN,
+				 KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2);
+}
+
 static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
 {
 	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET, 0);
@@ -322,7 +328,7 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 
 	switch(psci_fn) {
 	case PSCI_0_2_FN_PSCI_VERSION:
-		val = minor == 0 ? KVM_ARM_PSCI_1_0 : KVM_ARM_PSCI_1_1;
+		val = PSCI_VERSION(1, minor);
 		break;
 	case PSCI_1_0_FN_PSCI_FEATURES:
 		arg = smccc_get_arg1(vcpu);
@@ -358,6 +364,11 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 			if (minor >= 1)
 				val = 0;
 			break;
+		case PSCI_1_3_FN_SYSTEM_OFF2:
+		case PSCI_1_3_FN64_SYSTEM_OFF2:
+			if (minor >= 3)
+				val = BIT(PSCI_1_3_HIBERNATE_TYPE_OFF);
+			break;
 		}
 		break;
 	case PSCI_1_0_FN_SYSTEM_SUSPEND:
@@ -392,6 +403,32 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 			break;
 		}
 		break;
+	case PSCI_1_3_FN_SYSTEM_OFF2:
+		kvm_psci_narrow_to_32bit(vcpu);
+		fallthrough;
+	case PSCI_1_3_FN64_SYSTEM_OFF2:
+		if (minor < 3)
+			break;
+
+		arg = smccc_get_arg1(vcpu);
+		if (arg != PSCI_1_3_HIBERNATE_TYPE_OFF) {
+			val = PSCI_RET_INVALID_PARAMS;
+			break;
+		}
+		kvm_psci_system_off2(vcpu);
+		/*
+		 * We shouldn't be going back to guest VCPU after
+		 * receiving SYSTEM_OFF2 request.
+		 *
+		 * If user space accidentally/deliberately resumes
+		 * guest VCPU after SYSTEM_OFF2 request then guest
+		 * VCPU should see internal failure from PSCI return
+		 * value. To achieve this, we preload r0 (or x0) with
+		 * PSCI return value INTERNAL_FAILURE.
+		 */
+		val = PSCI_RET_INTERNAL_FAILURE;
+		ret = 0;
+		break;
 	default:
 		return kvm_psci_0_2_call(vcpu);
 	}
@@ -449,6 +486,10 @@ int kvm_psci_call(struct kvm_vcpu *vcpu)
 	}
 
 	switch (version) {
+	case KVM_ARM_PSCI_1_3:
+		return kvm_psci_1_x_call(vcpu, 3);
+	case KVM_ARM_PSCI_1_2:
+		return kvm_psci_1_x_call(vcpu, 2);
 	case KVM_ARM_PSCI_1_1:
 		return kvm_psci_1_x_call(vcpu, 1);
 	case KVM_ARM_PSCI_1_0:

arch/arm64/mm/mmu.c

@@ -166,16 +166,17 @@ bool pgattr_change_is_safe(u64 old, u64 new)
 	return ((old ^ new) & ~mask) == 0;
 }
 
-static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
+static void init_pte(pte_t *ptep, unsigned long addr, unsigned long end,
 		     phys_addr_t phys, pgprot_t prot)
 {
-	pte_t *ptep;
-
-	ptep = pte_set_fixmap_offset(pmdp, addr);
 	do {
 		pte_t old_pte = READ_ONCE(*ptep);
 
-		set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+		/*
+		 * Required barriers to make this visible to the table walker
+		 * are deferred to the end of alloc_init_cont_pte().
+		 */
+		__set_pte_nosync(ptep, pfn_pte(__phys_to_pfn(phys), prot));
 
 		/*
 		 * After the PTE entry has been populated once, we
@@ -186,8 +187,6 @@ static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
 
 		phys += PAGE_SIZE;
 	} while (ptep++, addr += PAGE_SIZE, addr != end);
-
-	pte_clear_fixmap();
 }
 
 static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
@@ -198,6 +197,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 {
 	unsigned long next;
 	pmd_t pmd = READ_ONCE(*pmdp);
+	pte_t *ptep;
 
 	BUG_ON(pmd_sect(pmd));
 	if (pmd_none(pmd)) {
@@ -213,6 +213,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 	}
 	BUG_ON(pmd_bad(pmd));
 
+	ptep = pte_set_fixmap_offset(pmdp, addr);
 	do {
 		pgprot_t __prot = prot;
 
@@ -223,20 +224,26 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pte(pmdp, addr, next, phys, __prot);
+		init_pte(ptep, addr, next, phys, __prot);
 
+		ptep += pte_index(next) - pte_index(addr);
 		phys += next - addr;
 	} while (addr = next, addr != end);
+
+	/*
+	 * Note: barriers and maintenance necessary to clear the fixmap slot
+	 * ensure that all previous pgtable writes are visible to the table
+	 * walker.
+	 */
+	pte_clear_fixmap();
 }
 
-static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
+static void init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
 		     phys_addr_t phys, pgprot_t prot,
 		     phys_addr_t (*pgtable_alloc)(int), int flags)
 {
 	unsigned long next;
-	pmd_t *pmdp;
 
-	pmdp = pmd_set_fixmap_offset(pudp, addr);
 	do {
 		pmd_t old_pmd = READ_ONCE(*pmdp);
 
@@ -262,8 +269,6 @@ static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 		}
 		phys += next - addr;
 	} while (pmdp++, addr = next, addr != end);
-
-	pmd_clear_fixmap();
 }
 
 static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
@@ -273,6 +278,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 {
 	unsigned long next;
 	pud_t pud = READ_ONCE(*pudp);
+	pmd_t *pmdp;
 
 	/*
 	 * Check for initial section mappings in the pgd/pud.
@@ -291,6 +297,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 	}
 	BUG_ON(pud_bad(pud));
 
+	pmdp = pmd_set_fixmap_offset(pudp, addr);
 	do {
 		pgprot_t __prot = prot;
 
@@ -301,10 +308,13 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags);
+		init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc, flags);
 
+		pmdp += pmd_index(next) - pmd_index(addr);
 		phys += next - addr;
 	} while (addr = next, addr != end);
+
+	pmd_clear_fixmap();
 }
 
 static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,

arch/x86/kernel/tsc.c

@@ -15,6 +15,7 @@
 #include <linux/timex.h>
 #include <linux/static_key.h>
 #include <linux/static_call.h>
+#include <linux/suspend.h>
 
 #include <asm/hpet.h>
 #include <asm/timer.h>
@@ -1650,3 +1651,31 @@ unsigned long calibrate_delay_is_known(void)
 	return 0;
 }
 #endif
+
+static int tsc_pm_notifier(struct notifier_block *notifier,
+                          unsigned long pm_event, void *unused)
+{
+	switch (pm_event) {
+	case PM_HIBERNATION_PREPARE:
+		clear_sched_clock_stable();
+		break;
+	case PM_POST_HIBERNATION:
+		/* Set back to the default */
+		if (!check_tsc_unstable())
+			set_sched_clock_stable();
+		break;
+	}
+
+	return 0;
+};
+
+static struct notifier_block tsc_pm_notifier_block = {
+       .notifier_call = tsc_pm_notifier,
+};
+
+static int tsc_setup_pm_notifier(void)
+{
+       return register_pm_notifier(&tsc_pm_notifier_block);
+}
+
+subsys_initcall(tsc_setup_pm_notifier);

arch/x86/xen/enlighten_hvm.c

@@ -36,6 +36,13 @@ static unsigned long shared_info_pfn;
 __ro_after_init bool xen_percpu_upcall;
 EXPORT_SYMBOL_GPL(xen_percpu_upcall);
 
+void xen_hvm_map_shared_info(void)
+{
+        xen_hvm_init_shared_info();
+        if(shared_info_pfn)
+                 HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn));
+}
+
 void xen_hvm_init_shared_info(void)
 {
 	struct xen_add_to_physmap xatp;
@@ -227,6 +234,7 @@ static void __init xen_hvm_guest_init(void)
 
 	xen_panic_handler_init();
 
+	xen_setup_syscore_ops();
 	xen_hvm_smp_init();
 	WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_hvm, xen_cpu_dead_hvm));
 	xen_unplug_emulated_devices();