Add AMD SEV guest live migration support

---
 .../virt/kvm/amd-memory-encryption.rst        |  27 ++++
 arch/x86/kvm/svm/sev.c                        | 125 ++++++++++++++++++
 include/linux/psp-sev.h                       |   8 +-
 include/uapi/linux/kvm.h                      |  12 ++
 4 files changed, 168 insertions(+), 4 deletions(-)

Documentation/virt/kvm/amd-memory-encryption.rst +27 -0

index 09a8f2a34e39..9f9896b72d36 100644
@@ -263,6 +263,33 @@ Returns: 0 on success, -negative on error
                 __u32 trans_len;
         };
 
+10. KVM_SEV_SEND_START
+----------------------
+
+The KVM_SEV_SEND_START command can be used by the hypervisor to create an
+outgoing guest encryption context.
+
+Parameters (in): struct kvm_sev_send_start
+
+Returns: 0 on success, -negative on error
+
+::
+        struct kvm_sev_send_start {
+                __u32 policy;                 /* guest policy */
+
+                __u64 pdh_cert_uaddr;         /* platform Diffie-Hellman certificate */
+                __u32 pdh_cert_len;
+
+                __u64 plat_certs_uaddr;        /* platform certificate chain */
+                __u32 plat_certs_len;
+
+                __u64 amd_certs_uaddr;        /* AMD certificate */
+                __u32 amd_certs_len;
+
+                __u64 session_uaddr;          /* Guest session information */
+                __u32 session_len;
+        };
+
 References
 ==========

arch/x86/kvm/svm/sev.c +125 -0

137 lines not on this page · raw message

include/linux/psp-sev.h +4 -4

index 49d155cd2dfe..454f35904d47 100644
@@ -325,11 +325,11 @@ struct sev_data_send_start {
 	u64 pdh_cert_address;			/* In */
 	u32 pdh_cert_len;			/* In */
 	u32 reserved1;
-	u64 plat_cert_address;			/* In */
-	u32 plat_cert_len;			/* In */
+	u64 plat_certs_address;			/* In */
+	u32 plat_certs_len;			/* In */
 	u32 reserved2;
-	u64 amd_cert_address;			/* In */
-	u32 amd_cert_len;			/* In */
+	u64 amd_certs_address;			/* In */
+	u32 amd_certs_len;			/* In */
 	u32 reserved3;
 	u64 session_address;			/* In */
 	u32 session_len;			/* In/Out */

include/uapi/linux/kvm.h +12 -0

index 886802b8ffba..f91aca926e89 100644
@@ -1643,6 +1643,18 @@ struct kvm_sev_dbg {
 	__u32 len;
 };
 
+struct kvm_sev_send_start {
+	__u32 policy;
+	__u64 pdh_cert_uaddr;
+	__u32 pdh_cert_len;
+	__u64 plat_certs_uaddr;
+	__u32 plat_certs_len;
+	__u64 amd_certs_uaddr;
+	__u32 amd_certs_len;
+	__u64 session_uaddr;
+	__u32 session_len;
+};
+
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
 #define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:06 UTC #3 lore raw

PATCH v9 3/18 KVM: SVM: Add KVM_SEV_SEND_FINISH command

From: Brijesh Singh <[email protected]>

The command is used to finailize the encryption context created with KVM_SEV_SEND_START command.

Cc Thomas Gleixner <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Paolo Bonzini <[email protected]>

Cc "Radim Krčmář" <[email protected]>

Cc Joerg Roedel <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Tom Lendacky <[email protected]>

---
 .../virt/kvm/amd-memory-encryption.rst        |  8 +++++++
 arch/x86/kvm/svm/sev.c                        | 23 +++++++++++++++++++
 2 files changed, 31 insertions(+)

Documentation/virt/kvm/amd-memory-encryption.rst +8 -0

index 8bed1d801558..0da0c199efa8 100644
@@ -314,6 +314,14 @@ Returns: 0 on success, -negative on error
                 __u32 trans_len;
         };
 
+12. KVM_SEV_SEND_FINISH
+------------------------
+
+After completion of the migration flow, the KVM_SEV_SEND_FINISH command can be
+issued by the hypervisor to delete the encryption context.
+
+Returns: 0 on success, -negative on error
+
 References
 ==========

arch/x86/kvm/svm/sev.c +23 -0

index adfe2e53abf3..877780222378 100644
@@ -1167,6 +1167,26 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return ret;
 }
 
+static int sev_send_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_data_send_finish *data;
+	int ret;
+
+	if (!sev_guest(kvm))
+		return -ENOTTY;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->handle = sev->handle;
+	ret = sev_issue_cmd(kvm, SEV_CMD_SEND_FINISH, data, &argp->error);
+
+	kfree(data);
+	return ret;
+}
+
 int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;

@@ -1217,6 +1237,9 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 	case KVM_SEV_SEND_UPDATE_DATA:
 		r = sev_send_update_data(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_SEND_FINISH:
+		r = sev_send_finish(kvm, &sev_cmd);
+		break;
 	default:
 		r = -EINVAL;
 		goto out;

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:06 UTC #2 lore raw

PATCH v9 2/18 KVM: SVM: Add KVM_SEND_UPDATE_DATA command

From: Brijesh Singh <[email protected]>

The command is used for encrypting the guest memory region using the encryption context created with KVM_SEV_SEND_START.

Cc Thomas Gleixner <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Paolo Bonzini <[email protected]>

Cc "Radim Krčmář" <[email protected]>

Cc Joerg Roedel <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Tom Lendacky <[email protected]>

---
 .../virt/kvm/amd-memory-encryption.rst        |  24 ++++
 arch/x86/kvm/svm/sev.c                        | 124 ++++++++++++++++++
 include/uapi/linux/kvm.h                      |   9 ++
 3 files changed, 157 insertions(+)

Documentation/virt/kvm/amd-memory-encryption.rst +24 -0

index 9f9896b72d36..8bed1d801558 100644
@@ -290,6 +290,30 @@ Returns: 0 on success, -negative on error
                 __u32 session_len;
         };
 
+11. KVM_SEV_SEND_UPDATE_DATA
+----------------------------
+
+The KVM_SEV_SEND_UPDATE_DATA command can be used by the hypervisor to encrypt the
+outgoing guest memory region with the encryption context creating using
+KVM_SEV_SEND_START.
+
+Parameters (in): struct kvm_sev_send_update_data
+
+Returns: 0 on success, -negative on error
+
+::
+
+        struct kvm_sev_launch_send_update_data {
+                __u64 hdr_uaddr;        /* userspace address containing the packet header */
+                __u32 hdr_len;
+
+                __u64 guest_uaddr;      /* the source memory region to be encrypted */
+                __u32 guest_len;
+
+                __u64 trans_uaddr;      /* the destition memory region  */
+                __u32 trans_len;
+        };
+
 References
 ==========

arch/x86/kvm/svm/sev.c +124 -0

154 lines not on this page · raw message

include/uapi/linux/kvm.h +9 -0

index f91aca926e89..c6f9d58b5a81 100644
@@ -1655,6 +1655,15 @@ struct kvm_sev_send_start {
 	__u32 session_len;
 };
 
+struct kvm_sev_send_update_data {
+	__u64 hdr_uaddr;
+	__u32 hdr_len;
+	__u64 guest_uaddr;
+	__u32 guest_len;
+	__u64 trans_uaddr;
+	__u32 trans_len;
+};
+
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
 #define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:06 UTC #4 lore raw

PATCH v9 4/18 KVM: SVM: Add support for KVM_SEV_RECEIVE_START command

From: Brijesh Singh <[email protected]>

The command is used to create the encryption context for an incoming SEV guest. The encryption context can be later used by the hypervisor to import the incoming data into the SEV guest memory space.

Cc Thomas Gleixner <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Paolo Bonzini <[email protected]>

Cc "Radim Krčmář" <[email protected]>

Cc Joerg Roedel <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Tom Lendacky <[email protected]>

---
 .../virt/kvm/amd-memory-encryption.rst        | 29 +++++++
 arch/x86/kvm/svm/sev.c                        | 81 +++++++++++++++++++
 include/uapi/linux/kvm.h                      |  9 +++
 3 files changed, 119 insertions(+)

Documentation/virt/kvm/amd-memory-encryption.rst +29 -0

index 0da0c199efa8..079ac5ac2459 100644
@@ -322,6 +322,35 @@ issued by the hypervisor to delete the encryption context.
 
 Returns: 0 on success, -negative on error
 
+13. KVM_SEV_RECEIVE_START
+------------------------
+
+The KVM_SEV_RECEIVE_START command is used for creating the memory encryption
+context for an incoming SEV guest. To create the encryption context, the user must
+provide a guest policy, the platform public Diffie-Hellman (PDH) key and session
+information.
+
+Parameters: struct  kvm_sev_receive_start (in/out)
+
+Returns: 0 on success, -negative on error
+
+::
+
+        struct kvm_sev_receive_start {
+                __u32 handle;           /* if zero then firmware creates a new handle */
+                __u32 policy;           /* guest's policy */
+
+                __u64 pdh_uaddr;        /* userspace address pointing to the PDH key */
+                __u32 pdh_len;
+
+                __u64 session_uaddr;    /* userspace address which points to the guest session information */
+                __u32 session_len;
+        };
+
+On success, the 'handle' field contains a new handle and on error, a negative value.
+
+For more details, see SEV spec Section 6.12.
+
 References
 ==========

arch/x86/kvm/svm/sev.c +81 -0

93 lines not on this page · raw message

include/uapi/linux/kvm.h +9 -0

index c6f9d58b5a81..a9e6ffcfe7e2 100644
@@ -1664,6 +1664,15 @@ struct kvm_sev_send_update_data {
 	__u32 trans_len;
 };
 
+struct kvm_sev_receive_start {
+	__u32 handle;
+	__u32 policy;
+	__u64 pdh_uaddr;
+	__u32 pdh_len;
+	__u64 session_uaddr;
+	__u32 session_len;
+};
+
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
 #define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:06 UTC #6 lore raw

PATCH v9 6/18 KVM: SVM: Add KVM_SEV_RECEIVE_FINISH command

From: Brijesh Singh <[email protected]>

The command finalize the guest receiving process and make the SEV guest ready for the execution.

Cc Thomas Gleixner <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Paolo Bonzini <[email protected]>

Cc "Radim Krčmář" <[email protected]>

Cc Joerg Roedel <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Tom Lendacky <[email protected]>

---
 .../virt/kvm/amd-memory-encryption.rst        |  8 +++++++
 arch/x86/kvm/svm/sev.c                        | 23 +++++++++++++++++++
 2 files changed, 31 insertions(+)

Documentation/virt/kvm/amd-memory-encryption.rst +8 -0

index da40be3d8bc2..1f7bbda1f971 100644
@@ -375,6 +375,14 @@ Returns: 0 on success, -negative on error
                 __u32 trans_len;
         };
 
+15. KVM_SEV_RECEIVE_FINISH
+------------------------
+
+After completion of the migration flow, the KVM_SEV_RECEIVE_FINISH command can be
+issued by the hypervisor to make the guest ready for execution.
+
+Returns: 0 on success, -negative on error
+
 References
 ==========

arch/x86/kvm/svm/sev.c +23 -0

index 34240c022042..edd98a8de2f8 100644
@@ -1341,6 +1341,26 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return ret;
 }
 
+static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_data_receive_finish *data;
+	int ret;
+
+	if (!sev_guest(kvm))
+		return -ENOTTY;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->handle = sev->handle;
+	ret = sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, data, &argp->error);
+
+	kfree(data);
+	return ret;
+}
+
 int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;

@@ -1400,6 +1420,9 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 	case KVM_SEV_RECEIVE_UPDATE_DATA:
 		r = sev_receive_update_data(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_RECEIVE_FINISH:
+		r = sev_receive_finish(kvm, &sev_cmd);
+		break;
 	default:
 		r = -EINVAL;
 		goto out;

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:07 UTC #5 lore raw

PATCH v9 5/18 KVM: SVM: Add KVM_SEV_RECEIVE_UPDATE_DATA command

From: Brijesh Singh <[email protected]>

The command is used for copying the incoming buffer into the SEV guest memory space.

Cc Thomas Gleixner <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Paolo Bonzini <[email protected]>

Cc "Radim Krčmář" <[email protected]>

Cc Joerg Roedel <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Tom Lendacky <[email protected]>

---
 .../virt/kvm/amd-memory-encryption.rst        | 24 ++++++
 arch/x86/kvm/svm/sev.c                        | 79 +++++++++++++++++++
 include/uapi/linux/kvm.h                      |  9 +++
 3 files changed, 112 insertions(+)

Documentation/virt/kvm/amd-memory-encryption.rst +24 -0

index 079ac5ac2459..da40be3d8bc2 100644
@@ -351,6 +351,30 @@ On success, the 'handle' field contains a new handle and on error, a negative va
 
 For more details, see SEV spec Section 6.12.
 
+14. KVM_SEV_RECEIVE_UPDATE_DATA
+----------------------------
+
+The KVM_SEV_RECEIVE_UPDATE_DATA command can be used by the hypervisor to copy
+the incoming buffers into the guest memory region with encryption context
+created during the KVM_SEV_RECEIVE_START.
+
+Parameters (in): struct kvm_sev_receive_update_data
+
+Returns: 0 on success, -negative on error
+
+::
+
+        struct kvm_sev_launch_receive_update_data {
+                __u64 hdr_uaddr;        /* userspace address containing the packet header */
+                __u32 hdr_len;
+
+                __u64 guest_uaddr;      /* the destination guest memory region */
+                __u32 guest_len;
+
+                __u64 trans_uaddr;      /* the incoming buffer memory region  */
+                __u32 trans_len;
+        };
+
 References
 ==========

arch/x86/kvm/svm/sev.c +79 -0

91 lines not on this page · raw message

include/uapi/linux/kvm.h +9 -0

index a9e6ffcfe7e2..fc0a48c37aac 100644
@@ -1673,6 +1673,15 @@ struct kvm_sev_receive_start {
 	__u32 session_len;
 };
 
+struct kvm_sev_receive_update_data {
+	__u64 hdr_uaddr;
+	__u32 hdr_len;
+	__u64 guest_uaddr;
+	__u32 guest_len;
+	__u64 trans_uaddr;
+	__u32 trans_len;
+};
+
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
 #define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:07 UTC #7 lore raw

PATCH v9 7/18 KVM: x86: Add AMD SEV specific Hypercall3

From: Brijesh Singh <[email protected]>

KVM hypercall framework relies on alternative framework to patch the VMCALL -> VMMCALL on AMD platform. If a hypercall is made before apply_alternative() is called then it defaults to VMCALL. The approach works fine on non SEV guest. A VMCALL would causes #UD, and hypervisor will be able to decode the instruction and do the right things. But when SEV is active, guest memory is encrypted with guest key and hypervisor will not be able to decode the instruction bytes.

Add SEV specific hypercall3, it unconditionally uses VMMCALL. The hypercall will be used by the SEV guest to notify encrypted pages to the hypervisor.

Cc Thomas Gleixner <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Paolo Bonzini <[email protected]>

Cc "Radim Krčmář" <[email protected]>

Cc Joerg Roedel <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Tom Lendacky <[email protected]>

---
 arch/x86/include/asm/kvm_para.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

arch/x86/include/asm/kvm_para.h +12 -0

index 338119852512..bc1b11d057fc 100644
@@ -85,6 +85,18 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 	return ret;
 }
 
+static inline long kvm_sev_hypercall3(unsigned int nr, unsigned long p1,
+				      unsigned long p2, unsigned long p3)
+{
+	long ret;
+
+	asm volatile("vmmcall"
+		     : "=a"(ret)
+		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3)
+		     : "memory");
+	return ret;
+}
+
 #ifdef CONFIG_KVM_GUEST
 bool kvm_para_available(void);
 unsigned int kvm_arch_para_features(void);

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:07 UTC #8 lore raw

PATCH v9 8/18 KVM: X86: Introduce KVM_HC_PAGE_ENC_STATUS hypercall

From: Brijesh Singh <[email protected]>

This hypercall is used by the SEV guest to notify a change in the page encryption status to the hypervisor. The hypercall should be invoked only when the encryption attribute is changed from encrypted -> decrypted and vice versa. By default all guest pages are considered encrypted.

Cc Thomas Gleixner <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Paolo Bonzini <[email protected]>

Cc "Radim Krčmář" <[email protected]>

Cc Joerg Roedel <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Tom Lendacky <[email protected]>

---
 Documentation/virt/kvm/hypercalls.rst | 15 +++++
 arch/x86/include/asm/kvm_host.h       |  2 +
 arch/x86/kvm/svm/sev.c                | 90 +++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c                |  2 +
 arch/x86/kvm/svm/svm.h                |  4 ++
 arch/x86/kvm/vmx/vmx.c                |  1 +
 arch/x86/kvm/x86.c                    |  6 ++
 include/uapi/linux/kvm_para.h         |  1 +
 8 files changed, 121 insertions(+)

Documentation/virt/kvm/hypercalls.rst +15 -0

index ed4fddd364ea..7aff0cebab7c 100644
@@ -169,3 +169,18 @@ a0: destination APIC ID
 
 :Usage example: When sending a call-function IPI-many to vCPUs, yield if
 	        any of the IPI target vCPUs was preempted.
+
+
+8. KVM_HC_PAGE_ENC_STATUS
+-------------------------
+:Architecture: x86
+:Status: active
+:Purpose: Notify the encryption status changes in guest page table (SEV guest)
+
+a0: the guest physical address of the start page
+a1: the number of pages
+a2: encryption attribute
+
+   Where:
+	* 1: Encryption attribute is set
+	* 0: Encryption attribute is cleared

arch/x86/include/asm/kvm_host.h +2 -0

index f002cdb13a0b..d035dc983a7a 100644
@@ -1282,6 +1282,8 @@ struct kvm_x86_ops {
 
 	void (*migrate_timers)(struct kvm_vcpu *vcpu);
 	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
+	int (*page_enc_status_hc)(struct kvm *kvm, unsigned long gpa,
+				  unsigned long sz, unsigned long mode);
 };
 
 struct kvm_x86_nested_ops {

arch/x86/kvm/svm/sev.c +90 -0

102 lines not on this page · raw message

arch/x86/kvm/svm/svm.c +2 -0

index 6dc337b9c231..7122ea5f7c47 100644
@@ -4312,6 +4312,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.apic_init_signal_blocked = svm_apic_init_signal_blocked,
 
 	.msr_filter_changed = svm_msr_filter_changed,
+
+	.page_enc_status_hc = svm_page_enc_status_hc,
 };
 
 static struct kvm_x86_init_ops svm_init_ops __initdata = {

arch/x86/kvm/svm/svm.h +4 -0

index fdff76eb6ceb..0103a23ca174 100644
@@ -66,6 +66,8 @@ struct kvm_sev_info {
 	int fd;			/* SEV device fd */
 	unsigned long pages_locked; /* Number of pages locked */
 	struct list_head regions_list;  /* List of registered regions */
+	unsigned long *page_enc_bmap;
+	unsigned long page_enc_bmap_size;
 };
 
 struct kvm_svm {

@@ -409,6 +411,8 @@ int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 			       bool has_error_code, u32 error_code);
 int nested_svm_exit_special(struct vcpu_svm *svm);
 void sync_nested_vmcb_control(struct vcpu_svm *svm);
+int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
+                           unsigned long npages, unsigned long enc);
 
 extern struct kvm_x86_nested_ops svm_nested_ops;

arch/x86/kvm/vmx/vmx.c +1 -0

index c3441e7e5a87..f0a00e69f892 100644
@@ -7719,6 +7719,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.can_emulate_instruction = vmx_can_emulate_instruction,
 	.apic_init_signal_blocked = vmx_apic_init_signal_blocked,
 	.migrate_timers = vmx_migrate_timers,
+	.page_enc_status_hc = NULL,
 
 	.msr_filter_changed = vmx_msr_filter_changed,
 	.cpu_dirty_log_size = vmx_cpu_dirty_log_size,

arch/x86/kvm/x86.c +6 -0

index a3fdc16cfd6f..3afc78f18f69 100644
@@ -8125,6 +8125,12 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		kvm_sched_yield(vcpu->kvm, a0);
 		ret = 0;
 		break;
+	case KVM_HC_PAGE_ENC_STATUS:
+		ret = -KVM_ENOSYS;
+		if (kvm_x86_ops.page_enc_status_hc)
+			ret = kvm_x86_ops.page_enc_status_hc(vcpu->kvm,
+					a0, a1, a2);
+		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;

include/uapi/linux/kvm_para.h +1 -0

index 8b86609849b9..847b83b75dc8 100644
@@ -29,6 +29,7 @@
 #define KVM_HC_CLOCK_PAIRING		9
 #define KVM_HC_SEND_IPI		10
 #define KVM_HC_SCHED_YIELD		11
+#define KVM_HC_PAGE_ENC_STATUS		12
 
 /*
  * hypercalls use architecture specific

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:07 UTC #9 lore raw

PATCH v9 9/18 KVM: x86: Introduce KVM_GET_PAGE_ENC_BITMAP ioctl

From: Brijesh Singh <[email protected]>

The ioctl can be used to retrieve page encryption bitmap for a given gfn range.

Return the correct bitmap as per the number of pages being requested by the user. Ensure that we only copy bmap->num_pages bits in the userspace buffer, if bmap->num_pages is not byte aligned we read the trailing bits from the userspace and copy those bits as is.

Cc Thomas Gleixner <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Paolo Bonzini <[email protected]>

Cc "Radim Krčmář" <[email protected]>

Cc Joerg Roedel <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Tom Lendacky <[email protected]>

---
 Documentation/virt/kvm/api.rst  | 27 +++++++++++++
 arch/x86/include/asm/kvm_host.h |  2 +
 arch/x86/kvm/svm/sev.c          | 70 +++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c          |  1 +
 arch/x86/kvm/svm/svm.h          |  1 +
 arch/x86/kvm/x86.c              | 12 ++++++
 include/uapi/linux/kvm.h        | 12 ++++++
 7 files changed, 125 insertions(+)

Documentation/virt/kvm/api.rst +27 -0

index 70254eaa5229..ae410f4332ab 100644
@@ -4671,6 +4671,33 @@ This ioctl resets VCPU registers and control structures according to
 the clear cpu reset definition in the POP. However, the cpu is not put
 into ESA mode. This reset is a superset of the initial reset.
 
+4.125 KVM_GET_PAGE_ENC_BITMAP (vm ioctl)
+---------------------------------------
+
+:Capability: basic
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_page_enc_bitmap (in/out)
+:Returns: 0 on success, -1 on error
+
+/* for KVM_GET_PAGE_ENC_BITMAP */
+struct kvm_page_enc_bitmap {
+	__u64 start_gfn;
+	__u64 num_pages;
+	union {
+		void __user *enc_bitmap; /* one bit per page */
+		__u64 padding2;
+	};
+};
+
+The encrypted VMs have the concept of private and shared pages. The private
+pages are encrypted with the guest-specific key, while the shared pages may
+be encrypted with the hypervisor key. The KVM_GET_PAGE_ENC_BITMAP can
+be used to get the bitmap indicating whether the guest page is private
+or shared. The bitmap can be used during the guest migration. If the page
+is private then the userspace need to use SEV migration commands to transmit
+the page.
+
 
 4.125 KVM_S390_PV_COMMAND
 -------------------------

arch/x86/include/asm/kvm_host.h +2 -0

index d035dc983a7a..8c2e40199ecb 100644
@@ -1284,6 +1284,8 @@ struct kvm_x86_ops {
 	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
 	int (*page_enc_status_hc)(struct kvm *kvm, unsigned long gpa,
 				  unsigned long sz, unsigned long mode);
+	int (*get_page_enc_bitmap)(struct kvm *kvm,
+				struct kvm_page_enc_bitmap *bmap);
 };
 
 struct kvm_x86_nested_ops {

arch/x86/kvm/svm/sev.c +70 -0

76 lines not on this page · raw message

arch/x86/kvm/svm/svm.c +1 -0

index 7122ea5f7c47..bff89cab3ed0 100644
@@ -4314,6 +4314,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.msr_filter_changed = svm_msr_filter_changed,
 
 	.page_enc_status_hc = svm_page_enc_status_hc,
+	.get_page_enc_bitmap = svm_get_page_enc_bitmap,
 };
 
 static struct kvm_x86_init_ops svm_init_ops __initdata = {

arch/x86/kvm/svm/svm.h +1 -0

index 0103a23ca174..4ce73f1034b9 100644
@@ -413,6 +413,7 @@ int nested_svm_exit_special(struct vcpu_svm *svm);
 void sync_nested_vmcb_control(struct vcpu_svm *svm);
 int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
                            unsigned long npages, unsigned long enc);
+int svm_get_page_enc_bitmap(struct kvm *kvm, struct kvm_page_enc_bitmap *bmap);
 
 extern struct kvm_x86_nested_ops svm_nested_ops;

arch/x86/kvm/x86.c +12 -0

index 3afc78f18f69..d3cb95a4dd55 100644
@@ -5695,6 +5695,18 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	case KVM_X86_SET_MSR_FILTER:
 		r = kvm_vm_ioctl_set_msr_filter(kvm, argp);
 		break;
+	case KVM_GET_PAGE_ENC_BITMAP: {
+		struct kvm_page_enc_bitmap bitmap;
+
+		r = -EFAULT;
+		if (copy_from_user(&bitmap, argp, sizeof(bitmap)))
+			goto out;
+
+		r = -ENOTTY;
+		if (kvm_x86_ops.get_page_enc_bitmap)
+			r = kvm_x86_ops.get_page_enc_bitmap(kvm, &bitmap);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}

include/uapi/linux/kvm.h +12 -0

index fc0a48c37aac..67cdb301ec4d 100644
@@ -532,6 +532,16 @@ struct kvm_dirty_log {
 	};
 };
 
+/* for KVM_GET_PAGE_ENC_BITMAP */
+struct kvm_page_enc_bitmap {
+	__u64 start_gfn;
+	__u64 num_pages;
+	union {
+		void __user *enc_bitmap; /* one bit per page */
+		__u64 padding2;
+	};
+};
+
 /* for KVM_CLEAR_DIRTY_LOG */
 struct kvm_clear_dirty_log {
 	__u32 slot;

@@ -1563,6 +1573,8 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_DIRTY_LOG_RING */
 #define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
 
+#define KVM_GET_PAGE_ENC_BITMAP	_IOW(KVMIO, 0xc8, struct kvm_page_enc_bitmap)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:08 UTC #10 lore raw

PATCH v9 10/18 mm: x86: Invoke hypercall when page encryption status is changed

From: Brijesh Singh <[email protected]>

Invoke a hypercall when a memory region is changed from encrypted -> decrypted and vice versa. Hypervisor needs to know the page encryption status during the guest migration.

Cc Thomas Gleixner <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Paolo Bonzini <[email protected]>

Cc "Radim Krčmář" <[email protected]>

Cc Joerg Roedel <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Tom Lendacky <[email protected]>

---
 arch/x86/include/asm/paravirt.h       | 10 +++++
 arch/x86/include/asm/paravirt_types.h |  2 +
 arch/x86/kernel/paravirt.c            |  1 +
 arch/x86/mm/mem_encrypt.c             | 57 ++++++++++++++++++++++++++-
 arch/x86/mm/pat/set_memory.c          |  7 ++++
 5 files changed, 76 insertions(+), 1 deletion(-)

arch/x86/include/asm/paravirt.h +10 -0

index d25cc6830e89..7aeb7c508c53 100644
@@ -84,6 +84,12 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 	PVOP_VCALL1(mmu.exit_mmap, mm);
 }
 
+static inline void page_encryption_changed(unsigned long vaddr, int npages,
+						bool enc)
+{
+	PVOP_VCALL3(mmu.page_encryption_changed, vaddr, npages, enc);
+}
+
 #ifdef CONFIG_PARAVIRT_XXL
 static inline void load_sp0(unsigned long sp0)
 {

@@ -840,6 +846,10 @@ static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
 static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 {
 }
+
+static inline void page_encryption_changed(unsigned long vaddr, int npages, bool enc)
+{
+}
 #endif
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PARAVIRT_H */

arch/x86/include/asm/paravirt_types.h +2 -0

index 0fad9f61c76a..d7787ec4d19f 100644
@@ -209,6 +209,8 @@ struct pv_mmu_ops {
 
 	/* Hook for intercepting the destruction of an mm_struct. */
 	void (*exit_mmap)(struct mm_struct *mm);
+	void (*page_encryption_changed)(unsigned long vaddr, int npages,
+					bool enc);
 
 #ifdef CONFIG_PARAVIRT_XXL
 	struct paravirt_callee_save read_cr2;

arch/x86/kernel/paravirt.c +1 -0

index 6c3407ba6ee9..52913356b6fa 100644
@@ -340,6 +340,7 @@ struct paravirt_patch_template pv_ops = {
 			(void (*)(struct mmu_gather *, void *))tlb_remove_page,
 
 	.mmu.exit_mmap		= paravirt_nop,
+	.mmu.page_encryption_changed	= paravirt_nop,
 
 #ifdef CONFIG_PARAVIRT_XXL
 	.mmu.read_cr2		= __PV_IS_CALLEE_SAVE(native_read_cr2),

arch/x86/mm/mem_encrypt.c +56 -1

98 lines not on this page · raw message

arch/x86/mm/pat/set_memory.c +7 -0

index 40baa90e74f4..dcd4557bb7fa 100644
@@ -27,6 +27,7 @@
 #include <asm/proto.h>
 #include <asm/memtype.h>
 #include <asm/set_memory.h>
+#include <asm/paravirt.h>
 
 #include "../mm_internal.h"

@@ -2012,6 +2013,12 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 	 */
 	cpa_flush(&cpa, 0);
 
+	/* Notify hypervisor that a given memory range is mapped encrypted
+	 * or decrypted. The hypervisor will use this information during the
+	 * VM migration.
+	 */
+	page_encryption_changed(addr, numpages, enc);
+
 	return ret;
 }

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:08 UTC #12 lore raw

PATCH v9 12/18 KVM: SVM: Add support for static allocation of unified Page Encryption Bitmap.

From: Ashish Kalra <[email protected]>

Add support for static allocation of the unified Page encryption bitmap by extending kvm_arch_commit_memory_region() callack to add svm specific x86_ops which can read the userspace provided memory region/memslots and calculate the amount of guest RAM managed by the KVM and grow the bitmap based on that information, i.e. the highest guest PA that is mapped by a memslot.

Earlier we used to dynamic resizing of the page encryption bitmap based on the guest hypercall, but potentially a malicious guest can make a hypercall which can trigger a really large memory allocation on the host side and may eventually cause denial of service.

Hence now we don't do dynamic resizing of the page encryption bitmap as per the hypercall and allocate it statically based on guest memory allocation by walking through memslots and computing it's size.

---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/svm/sev.c          | 35 +++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c          |  1 +
 arch/x86/kvm/svm/svm.h          |  1 +
 arch/x86/kvm/x86.c              |  5 +++++
 5 files changed, 43 insertions(+)

arch/x86/include/asm/kvm_host.h +1 -0

index 352ebc576036..91fc22d793e8 100644
@@ -1282,6 +1282,7 @@ struct kvm_x86_ops {
 
 	void (*migrate_timers)(struct kvm_vcpu *vcpu);
 	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
+	void (*commit_memory_region)(struct kvm *kvm, enum kvm_mr_change change);
 	int (*page_enc_status_hc)(struct kvm *kvm, unsigned long gpa,
 				  unsigned long sz, unsigned long mode);
 	int (*get_page_enc_bitmap)(struct kvm *kvm,

arch/x86/kvm/svm/sev.c +35 -0

index 6f34d0214440..b87b6225d2da 100644
@@ -1391,6 +1391,41 @@ static int sev_resize_page_enc_bitmap(struct kvm *kvm, unsigned long new_size)
 	return 0;
 }
 
+void svm_commit_memory_region(struct kvm *kvm, enum kvm_mr_change change)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	gfn_t start, end = 0;
+
+	spin_lock(&kvm->mmu_lock);
+	if (change == KVM_MR_CREATE) {
+		slots = kvm_memslots(kvm);
+		kvm_for_each_memslot(memslot, slots) {
+			start = memslot->base_gfn;
+			end = memslot->base_gfn + memslot->npages;
+			/*
+			 * KVM memslots is a sorted list, starting with
+			 * the highest mapped guest PA, so pick the topmost
+			 * valid guest PA.
+			 */
+			if (memslot->npages)
+				break;
+		}
+	}
+	spin_unlock(&kvm->mmu_lock);
+
+	if (end) {
+		/*
+		 * NORE: This callback is invoked in vm ioctl
+		 * set_user_memory_region, hence we can use a
+		 * mutex here.
+		 */
+		mutex_lock(&kvm->lock);
+		sev_resize_page_enc_bitmap(kvm, end);
+		mutex_unlock(&kvm->lock);
+	}
+}
+
 int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
 				  unsigned long npages, unsigned long enc)
 {

arch/x86/kvm/svm/svm.c +1 -0

index 6ebdf20773ea..7aa7858c8209 100644
@@ -4313,6 +4313,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.msr_filter_changed = svm_msr_filter_changed,
 
+	.commit_memory_region = svm_commit_memory_region,
 	.page_enc_status_hc = svm_page_enc_status_hc,
 	.get_page_enc_bitmap = svm_get_page_enc_bitmap,
 	.set_page_enc_bitmap = svm_set_page_enc_bitmap,

arch/x86/kvm/svm/svm.h +1 -0

index 2268c0ab650b..5a4656bad681 100644
@@ -415,6 +415,7 @@ int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
                            unsigned long npages, unsigned long enc);
 int svm_get_page_enc_bitmap(struct kvm *kvm, struct kvm_page_enc_bitmap *bmap);
 int svm_set_page_enc_bitmap(struct kvm *kvm, struct kvm_page_enc_bitmap *bmap);
+void svm_commit_memory_region(struct kvm *kvm, enum kvm_mr_change change);
 
 extern struct kvm_x86_nested_ops svm_nested_ops;

arch/x86/kvm/x86.c +5 -0

index 3cf64a94004f..c1acbd397b50 100644
@@ -10717,6 +10717,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	/* Free the arrays associated with the old memslot. */
 	if (change == KVM_MR_MOVE)
 		kvm_arch_free_memslot(kvm, old);
+
+	if (change == KVM_MR_CREATE || change == KVM_MR_DELETE) {
+		if (kvm_x86_ops.commit_memory_region)
+			kvm_x86_ops.commit_memory_region(kvm, change);
+	}
 }
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:09 UTC #11 lore raw

PATCH v9 11/18 KVM: x86: Introduce KVM_SET_PAGE_ENC_BITMAP ioctl

From: Brijesh Singh <[email protected]>

The ioctl can be used to set page encryption bitmap for an incoming guest.

Cc Thomas Gleixner <[email protected]>

Cc Ingo Molnar <[email protected]>

Cc "H. Peter Anvin" <[email protected]>

Cc Paolo Bonzini <[email protected]>

Cc "Radim Krčmář" <[email protected]>

Cc Joerg Roedel <[email protected]>

Cc Borislav Petkov <[email protected]>

Cc Tom Lendacky <[email protected]>

---
 Documentation/virt/kvm/api.rst  | 44 +++++++++++++++++++++++++++++
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/svm/sev.c          | 50 +++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c          |  1 +
 arch/x86/kvm/svm/svm.h          |  1 +
 arch/x86/kvm/x86.c              | 12 ++++++++
 include/uapi/linux/kvm.h        |  1 +
 7 files changed, 111 insertions(+)

Documentation/virt/kvm/api.rst +44 -0

index ae410f4332ab..1a3336cbbfe8 100644
@@ -4698,6 +4698,28 @@ or shared. The bitmap can be used during the guest migration. If the page
 is private then the userspace need to use SEV migration commands to transmit
 the page.
 
+4.126 KVM_SET_PAGE_ENC_BITMAP (vm ioctl)
+---------------------------------------
+
+:Capability: basic
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_page_enc_bitmap (in/out)
+:Returns: 0 on success, -1 on error
+
+/* for KVM_SET_PAGE_ENC_BITMAP */
+struct kvm_page_enc_bitmap {
+	__u64 start_gfn;
+	__u64 num_pages;
+	union {
+		void __user *enc_bitmap; /* one bit per page */
+		__u64 padding2;
+	};
+};
+
+During the guest live migration the outgoing guest exports its page encryption
+bitmap, the KVM_SET_PAGE_ENC_BITMAP can be used to build the page encryption
+bitmap for an incoming guest.
 
 4.125 KVM_S390_PV_COMMAND
 -------------------------

@@ -4852,6 +4874,28 @@ into user space.
 If a vCPU is in running state while this ioctl is invoked, the vCPU may
 experience inconsistent filtering behavior on MSR accesses.
 
+4.126 KVM_SET_PAGE_ENC_BITMAP (vm ioctl)
+---------------------------------------
+
+:Capability: basic
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_page_enc_bitmap (in/out)
+:Returns: 0 on success, -1 on error
+
+/* for KVM_SET_PAGE_ENC_BITMAP */
+struct kvm_page_enc_bitmap {
+	__u64 start_gfn;
+	__u64 num_pages;
+	union {
+		void __user *enc_bitmap; /* one bit per page */
+		__u64 padding2;
+	};
+};
+
+During the guest live migration the outgoing guest exports its page encryption
+bitmap, the KVM_SET_PAGE_ENC_BITMAP can be used to build the page encryption
+bitmap for an incoming guest.
 
 5. The kvm_run structure
 ========================

arch/x86/include/asm/kvm_host.h +2 -0

index 8c2e40199ecb..352ebc576036 100644
@@ -1286,6 +1286,8 @@ struct kvm_x86_ops {
 				  unsigned long sz, unsigned long mode);
 	int (*get_page_enc_bitmap)(struct kvm *kvm,
 				struct kvm_page_enc_bitmap *bmap);
+	int (*set_page_enc_bitmap)(struct kvm *kvm,
+				struct kvm_page_enc_bitmap *bmap);
 };
 
 struct kvm_x86_nested_ops {

arch/x86/kvm/svm/sev.c +50 -0

56 lines not on this page · raw message

arch/x86/kvm/svm/svm.c +1 -0

index bff89cab3ed0..6ebdf20773ea 100644
@@ -4315,6 +4315,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.page_enc_status_hc = svm_page_enc_status_hc,
 	.get_page_enc_bitmap = svm_get_page_enc_bitmap,
+	.set_page_enc_bitmap = svm_set_page_enc_bitmap,
 };
 
 static struct kvm_x86_init_ops svm_init_ops __initdata = {

arch/x86/kvm/svm/svm.h +1 -0

index 4ce73f1034b9..2268c0ab650b 100644
@@ -414,6 +414,7 @@ void sync_nested_vmcb_control(struct vcpu_svm *svm);
 int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
                            unsigned long npages, unsigned long enc);
 int svm_get_page_enc_bitmap(struct kvm *kvm, struct kvm_page_enc_bitmap *bmap);
+int svm_set_page_enc_bitmap(struct kvm *kvm, struct kvm_page_enc_bitmap *bmap);
 
 extern struct kvm_x86_nested_ops svm_nested_ops;

arch/x86/kvm/x86.c +12 -0

index d3cb95a4dd55..3cf64a94004f 100644
@@ -5707,6 +5707,18 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = kvm_x86_ops.get_page_enc_bitmap(kvm, &bitmap);
 		break;
 	}
+	case KVM_SET_PAGE_ENC_BITMAP: {
+		struct kvm_page_enc_bitmap bitmap;
+
+		r = -EFAULT;
+		if (copy_from_user(&bitmap, argp, sizeof(bitmap)))
+			goto out;
+
+		r = -ENOTTY;
+		if (kvm_x86_ops.set_page_enc_bitmap)
+			r = kvm_x86_ops.set_page_enc_bitmap(kvm, &bitmap);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}

include/uapi/linux/kvm.h +1 -0

index 67cdb301ec4d..79cd28b17b33 100644
@@ -1574,6 +1574,7 @@ struct kvm_pv_cmd {
 #define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
 
 #define KVM_GET_PAGE_ENC_BITMAP	_IOW(KVMIO, 0xc8, struct kvm_page_enc_bitmap)
+#define KVM_SET_PAGE_ENC_BITMAP	_IOW(KVMIO, 0xc9, struct kvm_page_enc_bitmap)
 
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:09 UTC #14 lore raw

PATCH v9 14/18 EFI: Introduce the new AMD Memory Encryption GUID.

From: Ashish Kalra <[email protected]>

Introduce a new AMD Memory Encryption GUID which is currently used for defining a new UEFI enviroment variable which indicates UEFI/OVMF support for the SEV live migration feature. This variable is setup when UEFI/OVMF detects host/hypervisor support for SEV live migration and later this variable is read by the kernel using EFI runtime services to verify if OVMF supports the live migration feature.

---
 include/linux/efi.h | 1 +
 1 file changed, 1 insertion(+)

include/linux/efi.h +1 -0

index d7c0e73af2b9..47d5b70ec058 100644
@@ -362,6 +362,7 @@ void efi_native_runtime_setup(void);
 
 /* OEM GUIDs */
 #define DELLEMC_EFI_RCI2_TABLE_GUID		EFI_GUID(0x2d9f28a2, 0xa886, 0x456a,  0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55)
+#define MEM_ENCRYPT_GUID			EFI_GUID(0x0cf29b71, 0x9e51, 0x433a,  0xa3, 0xb7, 0x81, 0xf3, 0xab, 0x16, 0xb8, 0x75)
 
 typedef struct {
 	efi_guid_t guid;

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:09 UTC #13 lore raw

PATCH v9 13/18 KVM: x86: Introduce new KVM_FEATURE_SEV_LIVE_MIGRATION feature & Custom MSR.

From: Ashish Kalra <[email protected]>

Add new KVM_FEATURE_SEV_LIVE_MIGRATION feature for guest to check for host-side support for SEV live migration. Also add a new custom MSR_KVM_SEV_LIVE_MIG_EN for guest to enable the SEV live migration feature.

---
 Documentation/virt/kvm/cpuid.rst     |  5 +++++
 Documentation/virt/kvm/msr.rst       | 16 ++++++++++++++++
 arch/x86/include/uapi/asm/kvm_para.h |  5 +++++
 arch/x86/kvm/svm/sev.c               | 14 ++++++++++++++
 arch/x86/kvm/svm/svm.c               | 16 ++++++++++++++++
 arch/x86/kvm/svm/svm.h               |  2 ++
 6 files changed, 58 insertions(+)

Documentation/virt/kvm/cpuid.rst +5 -0

index cf62162d4be2..0bdb6cdb12d3 100644
@@ -96,6 +96,11 @@ KVM_FEATURE_MSI_EXT_DEST_ID        15          guest checks this feature bit
                                                before using extended destination
                                                ID bits in MSI address bits 11-5.
 
+KVM_FEATURE_SEV_LIVE_MIGRATION     16          guest checks this feature bit before
+                                               using the page encryption state
+                                               hypercall to notify the page state
+                                               change
+
 KVM_FEATURE_CLOCKSOURCE_STABLE_BIT 24          host will warn if no guest-side
                                                per-cpu warps are expected in
                                                kvmclock

Documentation/virt/kvm/msr.rst +16 -0

index e37a14c323d2..ffac027aba5b 100644
@@ -376,3 +376,19 @@ data:
 	write '1' to bit 0 of the MSR, this causes the host to re-scan its queue
 	and check if there are more notifications pending. The MSR is available
 	if KVM_FEATURE_ASYNC_PF_INT is present in CPUID.
+
+MSR_KVM_SEV_LIVE_MIG_EN:
+        0x4b564d08
+
+	Control SEV Live Migration features.
+
+data:
+        Bit 0 enables (1) or disables (0) host-side SEV Live Migration feature,
+        in other words, this is guest->host communication that it's properly
+        handling the encryption bitmap.
+
+        Bit 1 enables (1) or disables (0) support for SEV Live Migration extensions,
+        any future extensions related to this live migration support, such as
+        extensions/support for accelerated migration, etc.
+
+        All other bits are reserved.

arch/x86/include/uapi/asm/kvm_para.h +5 -0

index 950afebfba88..0e8e59115ce2 100644
@@ -33,6 +33,7 @@
 #define KVM_FEATURE_PV_SCHED_YIELD	13
 #define KVM_FEATURE_ASYNC_PF_INT	14
 #define KVM_FEATURE_MSI_EXT_DEST_ID	15
+#define KVM_FEATURE_SEV_LIVE_MIGRATION	16
 
 #define KVM_HINTS_REALTIME      0

@@ -54,6 +55,7 @@
 #define MSR_KVM_POLL_CONTROL	0x4b564d05
 #define MSR_KVM_ASYNC_PF_INT	0x4b564d06
 #define MSR_KVM_ASYNC_PF_ACK	0x4b564d07
+#define MSR_KVM_SEV_LIVE_MIG_EN	0x4b564d08
 
 struct kvm_steal_time {
 	__u64 steal;

@@ -136,4 +138,7 @@ struct kvm_vcpu_pv_apf_data {
 #define KVM_PV_EOI_ENABLED KVM_PV_EOI_MASK
 #define KVM_PV_EOI_DISABLED 0x0
 
+#define KVM_SEV_LIVE_MIGRATION_ENABLED			(1 << 0)
+#define KVM_SEV_LIVE_MIGRATION_EXTENSIONS_SUPPORTED	(1 << 1)
+
 #endif /* _UAPI_ASM_X86_KVM_PARA_H */

arch/x86/kvm/svm/sev.c +14 -0

index b87b6225d2da..83565e35fa09 100644
@@ -1483,6 +1483,17 @@ int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
 	return 0;
 }
 
+void sev_update_migration_flags(struct kvm *kvm, u64 data)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+
+	if (!sev_guest(kvm))
+		return;
+
+	if (data & KVM_SEV_LIVE_MIGRATION_ENABLED)
+		sev->live_migration_enabled = true;
+}
+
 int svm_get_page_enc_bitmap(struct kvm *kvm,
 				   struct kvm_page_enc_bitmap *bmap)
 {

@@ -1495,6 +1506,9 @@ int svm_get_page_enc_bitmap(struct kvm *kvm,
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 
+	if (!sev->live_migration_enabled)
+		return -EINVAL;
+
 	gfn_start = bmap->start_gfn;
 	gfn_end = gfn_start + bmap->num_pages;

arch/x86/kvm/svm/svm.c +16 -0

index 7aa7858c8209..6f47db7b8805 100644
@@ -2765,6 +2765,9 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		svm->msr_decfg = data;
 		break;
 	}
+	case MSR_KVM_SEV_LIVE_MIG_EN:
+		sev_update_migration_flags(vcpu->kvm, data);
+		break;
 	case MSR_IA32_APICBASE:
 		if (kvm_vcpu_apicv_active(vcpu))
 			avic_update_vapic_bar(to_svm(vcpu), data);

@@ -3769,6 +3772,19 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 			vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f));
 	}
 
+        /*
+         * If SEV guest then enable the Live migration feature.
+         */
+        if (sev_guest(vcpu->kvm)) {
+              struct kvm_cpuid_entry2 *best;
+
+              best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
+              if (!best)
+                      return;
+
+              best->eax |= (1 << KVM_FEATURE_SEV_LIVE_MIGRATION);
+        }
+
 	if (!kvm_vcpu_apicv_active(vcpu))
 		return;

arch/x86/kvm/svm/svm.h +2 -0

index 5a4656bad681..d1f503dc2584 100644
@@ -66,6 +66,7 @@ struct kvm_sev_info {
 	int fd;			/* SEV device fd */
 	unsigned long pages_locked; /* Number of pages locked */
 	struct list_head regions_list;  /* List of registered regions */
+	bool live_migration_enabled;
 	unsigned long *page_enc_bmap;
 	unsigned long page_enc_bmap_size;
 };

@@ -505,5 +506,6 @@ int svm_unregister_enc_region(struct kvm *kvm,
 void pre_sev_run(struct vcpu_svm *svm, int cpu);
 int __init sev_hardware_setup(void);
 void sev_hardware_teardown(void);
+void sev_update_migration_flags(struct kvm *kvm, u64 data);
 
 #endif

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:09 UTC #15 lore raw

PATCH v9 15/18 KVM: x86: Add guest support for detecting and enabling SEV Live Migration feature.

From: Ashish Kalra <[email protected]>

The guest support for detecting and enabling SEV Live migration feature uses the following logic :

- kvm_init_plaform() checks if its booted under the EFI

- If not EFI,

i) check for the KVM_FEATURE_CPUID

ii) if CPUID reports that migration is support then issue wrmsrl
to enable the SEV migration support

- If EFI,

i) Check the KVM_FEATURE_CPUID.

ii) If CPUID reports that migration is supported, then reads the UEFI enviroment variable which
indicates OVMF support for live migration.

iii) If variable is set then wrmsr to enable the SEV migration support.

The EFI live migration check is done using a late_initcall() callback.

---
 arch/x86/include/asm/mem_encrypt.h | 11 ++++++
 arch/x86/kernel/kvm.c              | 62 ++++++++++++++++++++++++++++++
 arch/x86/mm/mem_encrypt.c          | 11 ++++++
 3 files changed, 84 insertions(+)

arch/x86/include/asm/mem_encrypt.h +11 -0

index 2f62bbdd9d12..83012af1660c 100644
@@ -21,6 +21,7 @@
 extern u64 sme_me_mask;
 extern u64 sev_status;
 extern bool sev_enabled;
+extern bool sev_live_mig_enabled;
 
 void sme_encrypt_execute(unsigned long encrypted_kernel_vaddr,
 			 unsigned long decrypted_kernel_vaddr,

@@ -43,6 +44,8 @@ void __init sme_enable(struct boot_params *bp);
 
 int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size);
 int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
+void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages,
+					    bool enc);
 
 void __init mem_encrypt_free_decrypted_mem(void);

@@ -59,6 +62,7 @@ bool sev_es_active(void);
 #else	/* !CONFIG_AMD_MEM_ENCRYPT */
 
 #define sme_me_mask	0ULL
+#define sev_live_mig_enabled	false
 
 static inline void __init sme_early_encrypt(resource_size_t paddr,
 					    unsigned long size) { }

@@ -82,6 +86,8 @@ static inline int __init
 early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; }
 static inline int __init
 early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; }
+static inline void __init
+early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) {}
 
 static inline void mem_encrypt_free_decrypted_mem(void) { }

@@ -110,6 +116,11 @@ static inline u64 sme_get_me_mask(void)
 	return sme_me_mask;
 }
 
+static inline bool sev_live_migration_enabled(void)
+{
+	return sev_live_mig_enabled;
+}
+
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __X86_MEM_ENCRYPT_H__ */

arch/x86/kernel/kvm.c +62 -0

80 lines not on this page · raw message

arch/x86/mm/mem_encrypt.c +11 -0

index 9d1ac65050d0..cc1a4c762149 100644
@@ -48,6 +48,8 @@ EXPORT_SYMBOL_GPL(sev_enable_key);
 
 bool sev_enabled __section(".data");
 
+bool sev_live_mig_enabled __section(".data");
+
 /* Buffer used for early in-place encryption by BSP, no locking needed */
 static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE);

@@ -206,6 +208,9 @@ static void set_memory_enc_dec_hypercall(unsigned long vaddr, int npages,
 	unsigned long sz = npages << PAGE_SHIFT;
 	unsigned long vaddr_end, vaddr_next;
 
+	if (!sev_live_migration_enabled())
+		return;
+
 	vaddr_end = vaddr + sz;
 
 	for (; vaddr < vaddr_end; vaddr = vaddr_next) {

@@ -376,6 +381,12 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size)
 	return early_set_memory_enc_dec(vaddr, size, true);
 }
 
+void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages,
+					bool enc)
+{
+	set_memory_enc_dec_hypercall(vaddr, npages, enc);
+}
+
 /*
  * SME and SEV are very similar but they are not the same, so there are
  * times that the kernel will need to distinguish between SME and SEV. The

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:10 UTC #16 lore raw

PATCH v9 16/18 KVM: x86: Mark _bss_decrypted section variables as decrypted in page encryption bitmap.

From: Ashish Kalra <[email protected]>

Ensure that _bss_decrypted section variables such as hv_clock_boot and wall_clock are marked as decrypted in the page encryption bitmap if sev live migration is supported.

---
 arch/x86/kernel/kvmclock.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

arch/x86/kernel/kvmclock.c +12 -0

index aa593743acf6..f80cc637ff2c 100644
@@ -333,6 +333,18 @@ void __init kvmclock_init(void)
 	pr_info("kvm-clock: Using msrs %x and %x",
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
+	if (sev_live_migration_enabled()) {
+		unsigned long nr_pages;
+		/*
+		 * sizeof(hv_clock_boot) is already PAGE_SIZE aligned
+		 */
+		early_set_mem_enc_dec_hypercall((unsigned long)hv_clock_boot,
+						1, 0);
+		nr_pages = DIV_ROUND_UP(sizeof(wall_clock), PAGE_SIZE);
+		early_set_mem_enc_dec_hypercall((unsigned long)&wall_clock,
+						nr_pages, 0);
+	}
+
 	this_cpu_write(hv_clock_per_cpu, &hv_clock_boot[0]);
 	kvm_register_clock("primary cpu clock");
 	pvclock_set_pvti_cpu0_va(hv_clock_boot);

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:10 UTC #18 lore raw

PATCH v9 18/18 KVM: SVM: Bypass DBG_DECRYPT API calls for unecrypted guest memory.

From: Ashish Kalra <[email protected]>

For all explicitly unecrypted guest memory regions such as S/W IOTLB bounce buffers, dma_decrypted() allocated regions and for guest regions marked as "__bss_decrypted", ensure that DBG_DECRYPT API calls are bypassed for such regions. The guest memory regions encryption status is referenced using the page encryption bitmap.

Uses the two added infrastructure functions hva_to_memslot() and hva_to_gfn().

---
 arch/x86/kvm/svm/sev.c | 76 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 76 insertions(+)

arch/x86/kvm/svm/sev.c +76 -0

index 83565e35fa09..da002945a5ae 100644
@@ -764,6 +764,37 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr,
 	return ret;
 }
 
+static struct kvm_memory_slot *hva_to_memslot(struct kvm *kvm,
+					      unsigned long hva)
+{
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *memslot;
+
+	kvm_for_each_memslot(memslot, slots) {
+		if (hva >= memslot->userspace_addr &&
+		    hva < memslot->userspace_addr +
+			      (memslot->npages << PAGE_SHIFT))
+			return memslot;
+	}
+
+	return NULL;
+}
+
+static bool hva_to_gfn(struct kvm *kvm, unsigned long hva, gfn_t *gfn)
+{
+	struct kvm_memory_slot *memslot;
+	gpa_t gpa_offset;
+
+	memslot = hva_to_memslot(kvm, hva);
+	if (!memslot)
+		return false;
+
+	gpa_offset = hva - memslot->userspace_addr;
+	*gfn = ((memslot->base_gfn << PAGE_SHIFT) + gpa_offset) >> PAGE_SHIFT;
+
+	return true;
+}
+
 static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
 {
 	unsigned long vaddr, vaddr_end, next_vaddr;

@@ -793,6 +824,50 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
 	for (; vaddr < vaddr_end; vaddr = next_vaddr) {
 		int len, s_off, d_off;
 
+		if (dec) {
+			struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+			struct page *src_tpage = NULL;
+			gfn_t gfn_start;
+			int srcu_idx;
+
+			/* ensure hva_to_gfn translations remain valid */
+			srcu_idx = srcu_read_lock(&kvm->srcu);
+			if (!hva_to_gfn(kvm, vaddr, &gfn_start)) {
+				srcu_read_unlock(&kvm->srcu, srcu_idx);
+				return -EINVAL;
+			}
+			if (sev->page_enc_bmap) {
+				if (!test_bit(gfn_start, sev->page_enc_bmap)) {
+					src_tpage = alloc_page(GFP_KERNEL);
+					if (!src_tpage) {
+						srcu_read_unlock(&kvm->srcu, srcu_idx);
+						return -ENOMEM;
+					}
+					/*
+					 * Since user buffer may not be page aligned, calculate the
+					 * offset within the page.
+					*/
+					s_off = vaddr & ~PAGE_MASK;
+					d_off = dst_vaddr & ~PAGE_MASK;
+					len = min_t(size_t, (PAGE_SIZE - s_off), size);
+
+					if (copy_from_user(page_address(src_tpage),
+							   (void __user *)(uintptr_t)vaddr, len)) {
+						__free_page(src_tpage);
+						srcu_read_unlock(&kvm->srcu, srcu_idx);
+						return -EFAULT;
+					}
+					if (copy_to_user((void __user *)(uintptr_t)dst_vaddr,
+							 page_address(src_tpage), len)) {
+						ret = -EFAULT;
+					}
+					__free_page(src_tpage);
+					srcu_read_unlock(&kvm->srcu, srcu_idx);
+					goto already_decrypted;
+				}
+			}
+		}
+
 		/* lock userspace source and destination page */
 		src_p = sev_pin_memory(kvm, vaddr & PAGE_MASK, PAGE_SIZE, &n, 0);
 		if (IS_ERR(src_p))

@@ -837,6 +912,7 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
 		sev_unpin_memory(kvm, src_p, n);
 		sev_unpin_memory(kvm, dst_p, n);
 
+already_decrypted:
 		if (ret)
 			goto err;

Signature · 1 line

2.17.1

Ashish Kalra

author

2020-12-08 22:10 UTC #17 lore raw

PATCH v9 17/18 KVM: x86: Add kexec support for SEV Live Migration.

From: Ashish Kalra <[email protected]>

Reset the host's page encryption bitmap related to kernel specific page encryption status settings before we load a new kernel by kexec. We cannot reset the complete page encryption bitmap here as we need to retain the UEFI/OVMF firmware specific settings.

The host's page encryption bitmap is maintained for the guest to keep the encrypted/decrypted state of the guest pages, therefore we need to explicitly mark all shared pages as encrypted again before rebooting into the new guest kernel.

---
 arch/x86/kernel/kvm.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

arch/x86/kernel/kvm.c +28 -0

index 7da8b6b3528c..3245ec003401 100644
@@ -39,6 +39,7 @@
 #include <asm/cpuidle_haltpoll.h>
 #include <asm/ptrace.h>
 #include <asm/svm.h>
+#include <asm/e820/api.h>
 
 DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);

@@ -384,6 +385,33 @@ static void kvm_pv_guest_cpu_reboot(void *unused)
 	 */
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
 		wrmsrl(MSR_KVM_PV_EOI_EN, 0);
+	/*
+	 * Reset the host's page encryption bitmap related to kernel
+	 * specific page encryption status settings before we load a
+	 * new kernel by kexec. NOTE: We cannot reset the complete
+	 * page encryption bitmap here as we need to retain the
+	 * UEFI/OVMF firmware specific settings.
+	 */
+	if (sev_live_migration_enabled() & (smp_processor_id() == 0)) {
+		int i;
+		unsigned long nr_pages;
+
+		for (i = 0; i < e820_table->nr_entries; i++) {
+			struct e820_entry *entry = &e820_table->entries[i];
+			unsigned long start_pfn;
+			unsigned long end_pfn;
+
+			if (entry->type != E820_TYPE_RAM)
+				continue;
+
+			start_pfn = entry->addr >> PAGE_SHIFT;
+			end_pfn = (entry->addr + entry->size) >> PAGE_SHIFT;
+			nr_pages = DIV_ROUND_UP(entry->size, PAGE_SIZE);
+
+			kvm_sev_hypercall3(KVM_HC_PAGE_ENC_STATUS,
+					   entry->addr, nr_pages, 1);
+		}
+	}
 	kvm_pv_disable_apf();
 	kvm_disable_steal_time();
 }

Signature · 1 line

2.17.1

Steve Rutherford

2021-01-15 00:33 UTC #19 lore raw