diff mbox series

[1/2,n,aws] UBUNTU: SAUCE: KVM: arm64: Add PSCI SYSTEM_OFF2 function for hibernation

Message ID 20240419173307.83813-3-philip.cox@canonical.com
State New
Headers show
Series [1/2,n,aws] UBUNTU: SAUCE: KVM: arm64: Add PSCI SYSTEM_OFF2 function for hibernation | expand

Commit Message

Philip Cox April 19, 2024, 5:33 p.m. UTC
From: David Woodhouse <dwmw@amazon.co.uk>

BugLink: https://bugs.launchpad.net/bugs/2060992

The PSCI v1.3 specification (alpha) adds support for a SYSTEM_OFF2 function
which is analogous to ACPI S4 state. This will allow hosting environments
to determine that a guest is hibernated rather than just powered off, and
ensure that they preserve the virtual environment appropriately to allow
the guest to resume safely (or bump the hardware_signature in the FACS to
trigger a clean reboot instead).

The beta version will be changed to say that PSCI_FEATURES returns a bit
mask of the supported hibernate types, which is implemented here.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
(cherry-picked from https://lore.kernel.org/lkml/20240312135958.727765-1-dwmw2@infradead.org)
Signed-off-by: Philip Cox <philip.cox@canonical.com>
---
 Documentation/virt/kvm/api.rst       | 11 +++++++++
 arch/arm64/include/asm/kvm_host.h    |  2 ++
 arch/arm64/include/uapi/asm/kvm.h    |  6 +++++
 arch/arm64/kvm/arm.c                 |  5 ++++
 arch/arm64/kvm/hyp/nvhe/psci-relay.c |  2 ++
 arch/arm64/kvm/psci.c                | 37 ++++++++++++++++++++++++++++
 include/uapi/linux/kvm.h             |  1 +
 include/uapi/linux/psci.h            |  5 ++++
 8 files changed, 69 insertions(+)
diff mbox series

Patch

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 09c7e585ff58..541abd67ae85 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6732,6 +6732,10 @@  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.
 
@@ -6765,6 +6769,13 @@  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 with the
+KVM_CAP_ARM_SYSTEM_OFF2 VM capability. 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 */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 21c57b812569..d6da0eb1c236 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -274,6 +274,8 @@  struct kvm_arch {
 #define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE		6
 	/* Initial ID reg values loaded */
 #define KVM_ARCH_FLAG_ID_REGS_INITIALIZED		7
+	/* PSCI SYSTEM_OFF2 (hibernate) enabled for the guest */
+#define KVM_ARCH_FLAG_SYSTEM_OFF2_ENABLED		8
 	unsigned long flags;
 
 	/* VM-wide vCPU feature set */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 89d2fc872d9f..2f15aed54c56 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/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)
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index a25265aca432..1c58762272eb 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -98,6 +98,10 @@  int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		r = 0;
 		set_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags);
 		break;
+	case KVM_CAP_ARM_SYSTEM_OFF2:
+		r = 0;
+		set_bit(KVM_ARCH_FLAG_SYSTEM_OFF2_ENABLED, &kvm->arch.flags);
+		break;
 	case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE:
 		new_cap = cap->args[0];
 
@@ -238,6 +242,7 @@  int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_VCPU_ATTRIBUTES:
 	case KVM_CAP_PTP_KVM:
 	case KVM_CAP_ARM_SYSTEM_SUSPEND:
+	case KVM_CAP_ARM_SYSTEM_OFF2:
 	case KVM_CAP_IRQFD_RESAMPLE:
 	case KVM_CAP_COUNTER_OFFSET:
 		r = 1;
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index d57bcb6ab94d..0d4bea0b9ca2 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -264,6 +264,8 @@  static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_
 	switch (func_id) {
 	case PSCI_1_0_FN_PSCI_FEATURES:
 	case PSCI_1_0_FN_SET_SUSPEND_MODE:
+	case PSCI_1_3_FN_SYSTEM_OFF2:
+	case PSCI_1_3_FN64_SYSTEM_OFF2:
 	case PSCI_1_1_FN64_SYSTEM_RESET2:
 		return psci_forward(host_ctxt);
 	case PSCI_1_0_FN64_SYSTEM_SUSPEND:
diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index 1f69b667332b..59570eea8aa7 100644
--- a/arch/arm64/kvm/psci.c
+++ b/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);
@@ -353,6 +359,11 @@  static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 			if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags))
 				val = 0;
 			break;
+		case PSCI_1_3_FN_SYSTEM_OFF2:
+		case PSCI_1_3_FN64_SYSTEM_OFF2:
+			if (test_bit(KVM_ARCH_FLAG_SYSTEM_OFF2_ENABLED, &kvm->arch.flags))
+				val = 1UL << PSCI_1_3_HIBERNATE_TYPE_OFF;
+			break;
 		case PSCI_1_1_FN_SYSTEM_RESET2:
 		case PSCI_1_1_FN64_SYSTEM_RESET2:
 			if (minor >= 1)
@@ -374,6 +385,32 @@  static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor)
 			return 0;
 		}
 		break;
+	case PSCI_1_3_FN_SYSTEM_OFF2:
+		kvm_psci_narrow_to_32bit(vcpu);
+		fallthrough;
+	case PSCI_1_3_FN64_SYSTEM_OFF2:
+		if (!test_bit(KVM_ARCH_FLAG_SYSTEM_OFF2_ENABLED, &kvm->arch.flags))
+			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_OFF 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;
 	case PSCI_1_1_FN_SYSTEM_RESET2:
 		kvm_psci_narrow_to_32bit(vcpu);
 		fallthrough;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index c3308536482b..f3f97be6ed46 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1155,6 +1155,7 @@  struct kvm_ppc_resize_hpt {
 #define KVM_CAP_MEMORY_ATTRIBUTES 233
 #define KVM_CAP_GUEST_MEMFD 234
 #define KVM_CAP_VM_TYPES 235
+#define KVM_CAP_ARM_SYSTEM_OFF2 236
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h
index 42a40ad3fb62..f9a015ebe221 100644
--- a/include/uapi/linux/psci.h
+++ b/include/uapi/linux/psci.h
@@ -59,6 +59,7 @@ 
 #define PSCI_1_1_FN_SYSTEM_RESET2		PSCI_0_2_FN(18)
 #define PSCI_1_1_FN_MEM_PROTECT			PSCI_0_2_FN(19)
 #define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE	PSCI_0_2_FN(20)
+#define PSCI_1_3_FN_SYSTEM_OFF2			PSCI_0_2_FN(21)
 
 #define PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND	PSCI_0_2_FN64(12)
 #define PSCI_1_0_FN64_NODE_HW_STATE		PSCI_0_2_FN64(13)
@@ -68,6 +69,7 @@ 
 
 #define PSCI_1_1_FN64_SYSTEM_RESET2		PSCI_0_2_FN64(18)
 #define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE	PSCI_0_2_FN64(20)
+#define PSCI_1_3_FN64_SYSTEM_OFF2		PSCI_0_2_FN64(21)
 
 /* PSCI v0.2 power state encoding for CPU_SUSPEND function */
 #define PSCI_0_2_POWER_STATE_ID_MASK		0xffff
@@ -100,6 +102,9 @@ 
 #define PSCI_1_1_RESET_TYPE_SYSTEM_WARM_RESET	0
 #define PSCI_1_1_RESET_TYPE_VENDOR_START	0x80000000U
 
+/* PSCI v1.3 hibernate type for SYSTEM_OFF2 */
+#define PSCI_1_3_HIBERNATE_TYPE_OFF		0
+
 /* PSCI version decoding (independent of PSCI version) */
 #define PSCI_VERSION_MAJOR_SHIFT		16
 #define PSCI_VERSION_MINOR_MASK			\