[RFC PATCH kvmtool v3 0/3] SPE support

[RFC PATCH kvmtool v3 0/3] SPE support

[Alexandru Elisei]

This series adds userspace support for creating a guest which can use SPE.
It requires KVM SPE support which is in the RFC phase, hence why this
series is also RFC. The kvmtool patches can also be found at [1], and the
KVM SPE patches can be found at [2].

To create a guest with SPE support the following steps must be executed:

1. Set the SPE virtual interrupt ID and then initialize the features on
every VCPU.

2. After the guest memory memslots have been created, kvmtool must mlock()
the VMAs backing the memslots.

3. After everything has been copied to the guest's memory, kvmtool must
execute the KVM_ARM_VM_SPE_CTRL(KVM_ARM_VM_SPE_FINALIZE) on the VM fd.

The first patch is a simple update to the Linux headers; the second patch
add a new init list that executes last which is necessary to make sure the
gest memory will not be touched after that; and the third patch contains
the actual SPE support.

[1] https://gitlab.arm.com/linux-arm/kvmtool-ae/-/tree/kvm-spe-v3
[2] https://gitlab.arm.com/linux-arm/linux-ae/-/tree/kvm-spe-v3

Alexandru Elisei (1):
  init: Add last_{init, exit} list macros

Sudeep Holla (2):
  update_headers: Sync kvm UAPI headers with linux 5.10-rc1
  arm64: Add SPE support

 Makefile                                  |   2 +-
 arm/aarch64/arm-cpu.c                     |   2 +
 arm/aarch64/include/asm/kvm.h             |  53 +++++++-
 arm/aarch64/include/kvm/kvm-config-arch.h |   2 +
 arm/aarch64/include/kvm/kvm-cpu-arch.h    |   3 +-
 arm/aarch64/kvm-cpu.c                     |   5 +
 arm/include/arm-common/kvm-config-arch.h  |   1 +
 arm/include/arm-common/spe.h              |   7 +
 arm/spe.c                                 | 154 ++++++++++++++++++++++
 include/kvm/util-init.h                   |   6 +-
 include/linux/kvm.h                       | 117 +++++++++++++++-
 powerpc/include/asm/kvm.h                 |   8 ++
 x86/include/asm/kvm.h                     |  42 +++++-
 13 files changed, 387 insertions(+), 15 deletions(-)
 create mode 100644 arm/include/arm-common/spe.h
 create mode 100644 arm/spe.c

-- 
2.29.1

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

[RFC PATCH kvmtool v3 1/3] update_headers: Sync kvm UAPI headers with linux 5.10-rc1

[Alexandru Elisei]

From: Sudeep Holla <sudeep.holla@arm.com>

The local copies of the kvm user API headers are getting stale.  In
preparation for some arch-specific updated, this patch reflects a re-run of
util/update_headers.sh to pull in upstream updates from linux v5.10-rc1.

[ Alexandru E: Updated headers to Linux tag v5.10-rc1 ]

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Alexandru Elisei <alexandru.elisei@arm.com>
---
 arm/aarch64/include/asm/kvm.h |  53 +++++++++++++--
 include/linux/kvm.h           | 117 ++++++++++++++++++++++++++++++++--
 powerpc/include/asm/kvm.h     |   8 +++
 x86/include/asm/kvm.h         |  42 +++++++++++-
 4 files changed, 209 insertions(+), 11 deletions(-)

diff --git a/arm/aarch64/include/asm/kvm.h b/arm/aarch64/include/asm/kvm.h
index 9a507716ae2f..8876e564ba56 100644
--- a/arm/aarch64/include/asm/kvm.h
+++ b/arm/aarch64/include/asm/kvm.h
@@ -106,6 +106,7 @@ struct kvm_regs {
 #define KVM_ARM_VCPU_SVE		4 /* enable SVE for this CPU */
 #define KVM_ARM_VCPU_PTRAUTH_ADDRESS	5 /* VCPU uses address authentication */
 #define KVM_ARM_VCPU_PTRAUTH_GENERIC	6 /* VCPU uses generic authentication */
+#define KVM_ARM_VCPU_SPE		7 /* Enable SPE for this CPU */
 
 struct kvm_vcpu_init {
 	__u32 target;
@@ -159,13 +160,29 @@ struct kvm_sync_regs {
 struct kvm_arch_memory_slot {
 };
 
+/*
+ * PMU filter structure. Describe a range of events with a particular
+ * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.
+ */
+struct kvm_pmu_event_filter {
+	__u16	base_event;
+	__u16	nevents;
+
+#define KVM_PMU_EVENT_ALLOW	0
+#define KVM_PMU_EVENT_DENY	1
+
+	__u8	action;
+	__u8	pad[3];
+};
+
 /* for KVM_GET/SET_VCPU_EVENTS */
 struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
+		__u8 ext_dabt_pending;
 		/* Align it to 8 bytes */
-		__u8 pad[6];
+		__u8 pad[5];
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];
@@ -219,10 +236,18 @@ struct kvm_vcpu_events {
 #define KVM_REG_ARM_PTIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 2, 2)
 #define KVM_REG_ARM_PTIMER_CNT		ARM64_SYS_REG(3, 3, 14, 0, 1)
 
-/* EL0 Virtual Timer Registers */
+/*
+ * EL0 Virtual Timer Registers
+ *
+ * WARNING:
+ *      KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT are not defined
+ *      with the appropriate register encodings.  Their values have been
+ *      accidentally swapped.  As this is set API, the definitions here
+ *      must be used, rather than ones derived from the encodings.
+ */
 #define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
-#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
+#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 
 /* KVM-as-firmware specific pseudo-registers */
 #define KVM_REG_ARM_FW			(0x0014 << KVM_REG_ARM_COPROC_SHIFT)
@@ -233,6 +258,15 @@ struct kvm_vcpu_events {
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL		0
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL		1
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED	2
+
+/*
+ * Only two states can be presented by the host kernel:
+ * - NOT_REQUIRED: the guest doesn't need to do anything
+ * - NOT_AVAIL: the guest isn't mitigated (it can still use SSBS if available)
+ *
+ * All the other values are deprecated. The host still accepts all
+ * values (they are ABI), but will narrow them to the above two.
+ */
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2	KVM_REG_ARM_FW_REG(2)
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL		0
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN		1
@@ -316,17 +350,28 @@ struct kvm_vcpu_events {
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
 #define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
+#define KVM_ARM_VM_SPE_CTRL		0
+#define   KVM_ARM_VM_SPE_FINALIZE	0
+
 /* Device Control API on vcpu fd */
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
 #define   KVM_ARM_VCPU_PMU_V3_IRQ	0
 #define   KVM_ARM_VCPU_PMU_V3_INIT	1
+#define   KVM_ARM_VCPU_PMU_V3_FILTER	2
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
+#define KVM_ARM_VCPU_PVTIME_CTRL	2
+#define   KVM_ARM_VCPU_PVTIME_IPA	0
+#define KVM_ARM_VCPU_SPE_CTRL		3
+#define   KVM_ARM_VCPU_SPE_IRQ		0
+#define   KVM_ARM_VCPU_SPE_INIT		1
 
 /* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_VCPU2_SHIFT		28
+#define KVM_ARM_IRQ_VCPU2_MASK		0xf
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
-#define KVM_ARM_IRQ_TYPE_MASK		0xff
+#define KVM_ARM_IRQ_TYPE_MASK		0xf
 #define KVM_ARM_IRQ_VCPU_SHIFT		16
 #define KVM_ARM_IRQ_VCPU_MASK		0xff
 #define KVM_ARM_IRQ_NUM_SHIFT		0
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 5e3f12d5359e..96228b823711 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -116,7 +116,7 @@ struct kvm_irq_level {
 	 * ACPI gsi notion of irq.
 	 * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47..
 	 * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23..
-	 * For ARM: See Documentation/virt/kvm/api.txt
+	 * For ARM: See Documentation/virt/kvm/api.rst
 	 */
 	union {
 		__u32 irq;
@@ -188,10 +188,13 @@ struct kvm_s390_cmma_log {
 struct kvm_hyperv_exit {
 #define KVM_EXIT_HYPERV_SYNIC          1
 #define KVM_EXIT_HYPERV_HCALL          2
+#define KVM_EXIT_HYPERV_SYNDBG         3
 	__u32 type;
+	__u32 pad1;
 	union {
 		struct {
 			__u32 msr;
+			__u32 pad2;
 			__u64 control;
 			__u64 evt_page;
 			__u64 msg_page;
@@ -201,6 +204,15 @@ struct kvm_hyperv_exit {
 			__u64 result;
 			__u64 params[2];
 		} hcall;
+		struct {
+			__u32 msr;
+			__u32 pad2;
+			__u64 control;
+			__u64 status;
+			__u64 send_page;
+			__u64 recv_page;
+			__u64 pending_page;
+		} syndbg;
 	} u;
 };
 
@@ -235,6 +247,9 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_S390_STSI        25
 #define KVM_EXIT_IOAPIC_EOI       26
 #define KVM_EXIT_HYPERV           27
+#define KVM_EXIT_ARM_NISV         28
+#define KVM_EXIT_X86_RDMSR        29
+#define KVM_EXIT_X86_WRMSR        30
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -243,6 +258,8 @@ struct kvm_hyperv_exit {
 #define KVM_INTERNAL_ERROR_SIMUL_EX	2
 /* Encounter unexpected vm-exit due to delivery event. */
 #define KVM_INTERNAL_ERROR_DELIVERY_EV	3
+/* Encounter unexpected vm-exit reason */
+#define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON	4
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
@@ -274,6 +291,7 @@ struct kvm_run {
 		/* KVM_EXIT_FAIL_ENTRY */
 		struct {
 			__u64 hardware_entry_failure_reason;
+			__u32 cpu;
 		} fail_entry;
 		/* KVM_EXIT_EXCEPTION */
 		struct {
@@ -392,6 +410,22 @@ struct kvm_run {
 		} eoi;
 		/* KVM_EXIT_HYPERV */
 		struct kvm_hyperv_exit hyperv;
+		/* KVM_EXIT_ARM_NISV */
+		struct {
+			__u64 esr_iss;
+			__u64 fault_ipa;
+		} arm_nisv;
+		/* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+		struct {
+			__u8 error; /* user -> kernel */
+			__u8 pad[7];
+#define KVM_MSR_EXIT_REASON_INVAL	(1 << 0)
+#define KVM_MSR_EXIT_REASON_UNKNOWN	(1 << 1)
+#define KVM_MSR_EXIT_REASON_FILTER	(1 << 2)
+			__u32 reason; /* kernel -> user */
+			__u32 index; /* kernel -> user */
+			__u64 data; /* kernel <-> user */
+		} msr;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -466,12 +500,17 @@ struct kvm_s390_mem_op {
 	__u32 size;		/* amount of bytes */
 	__u32 op;		/* type of operation */
 	__u64 buf;		/* buffer in userspace */
-	__u8 ar;		/* the access register number */
-	__u8 reserved[31];	/* should be set to 0 */
+	union {
+		__u8 ar;	/* the access register number */
+		__u32 sida_offset; /* offset into the sida */
+		__u8 reserved[32]; /* should be set to 0 */
+	};
 };
 /* types for kvm_s390_mem_op->op */
 #define KVM_S390_MEMOP_LOGICAL_READ	0
 #define KVM_S390_MEMOP_LOGICAL_WRITE	1
+#define KVM_S390_MEMOP_SIDA_READ	2
+#define KVM_S390_MEMOP_SIDA_WRITE	3
 /* flags for kvm_s390_mem_op->flags */
 #define KVM_S390_MEMOP_F_CHECK_ONLY		(1ULL << 0)
 #define KVM_S390_MEMOP_F_INJECT_EXCEPTION	(1ULL << 1)
@@ -764,9 +803,10 @@ struct kvm_ppc_resize_hpt {
 #define KVM_VM_PPC_HV 1
 #define KVM_VM_PPC_PR 2
 
-/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
-#define KVM_VM_MIPS_TE		0
+/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */
+#define KVM_VM_MIPS_AUTO	0
 #define KVM_VM_MIPS_VZ		1
+#define KVM_VM_MIPS_TE		2
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
@@ -996,6 +1036,24 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172
 #define KVM_CAP_PMU_EVENT_FILTER 173
+#define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
+#define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175
+#define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176
+#define KVM_CAP_ARM_NISV_TO_USER 177
+#define KVM_CAP_ARM_INJECT_EXT_DABT 178
+#define KVM_CAP_S390_VCPU_RESETS 179
+#define KVM_CAP_S390_PROTECTED 180
+#define KVM_CAP_PPC_SECURE_GUEST 181
+#define KVM_CAP_HALT_POLL 182
+#define KVM_CAP_ASYNC_PF_INT 183
+#define KVM_CAP_LAST_CPU 184
+#define KVM_CAP_SMALLER_MAXPHYADDR 185
+#define KVM_CAP_S390_DIAG318 186
+#define KVM_CAP_STEAL_TIME 187
+#define KVM_CAP_X86_USER_SPACE_MSR 188
+#define KVM_CAP_X86_MSR_FILTER 189
+#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
+#define KVM_CAP_ARM_SPE 191
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1086,7 +1144,7 @@ struct kvm_xen_hvm_config {
  *
  * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
  * the irqfd to operate in resampling mode for level triggered interrupt
- * emulation.  See Documentation/virt/kvm/api.txt.
+ * emulation.  See Documentation/virt/kvm/api.rst.
  */
 #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
 
@@ -1142,6 +1200,7 @@ struct kvm_dirty_tlb {
 #define KVM_REG_S390		0x5000000000000000ULL
 #define KVM_REG_ARM64		0x6000000000000000ULL
 #define KVM_REG_MIPS		0x7000000000000000ULL
+#define KVM_REG_RISCV		0x8000000000000000ULL
 
 #define KVM_REG_SIZE_SHIFT	52
 #define KVM_REG_SIZE_MASK	0x00f0000000000000ULL
@@ -1222,6 +1281,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_ARM_VGIC_ITS	KVM_DEV_TYPE_ARM_VGIC_ITS
 	KVM_DEV_TYPE_XIVE,
 #define KVM_DEV_TYPE_XIVE		KVM_DEV_TYPE_XIVE
+	KVM_DEV_TYPE_ARM_PV_TIME,
+#define KVM_DEV_TYPE_ARM_PV_TIME	KVM_DEV_TYPE_ARM_PV_TIME
 	KVM_DEV_TYPE_MAX,
 };
 
@@ -1332,6 +1393,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
 /* Available with KVM_CAP_PMU_EVENT_FILTER */
 #define KVM_SET_PMU_EVENT_FILTER  _IOW(KVMIO,  0xb2, struct kvm_pmu_event_filter)
+#define KVM_PPC_SVM_OFF		  _IO(KVMIO,  0xb3)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
@@ -1456,6 +1518,46 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_ARM_SVE */
 #define KVM_ARM_VCPU_FINALIZE	  _IOW(KVMIO,  0xc2, int)
 
+/* Available with  KVM_CAP_S390_VCPU_RESETS */
+#define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
+#define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
+
+struct kvm_s390_pv_sec_parm {
+	__u64 origin;
+	__u64 length;
+};
+
+struct kvm_s390_pv_unp {
+	__u64 addr;
+	__u64 size;
+	__u64 tweak;
+};
+
+enum pv_cmd_id {
+	KVM_PV_ENABLE,
+	KVM_PV_DISABLE,
+	KVM_PV_SET_SEC_PARMS,
+	KVM_PV_UNPACK,
+	KVM_PV_VERIFY,
+	KVM_PV_PREP_RESET,
+	KVM_PV_UNSHARE_ALL,
+};
+
+struct kvm_pv_cmd {
+	__u32 cmd;	/* Command to be executed */
+	__u16 rc;	/* Ultravisor return code */
+	__u16 rrc;	/* Ultravisor return reason code */
+	__u64 data;	/* Data or address */
+	__u32 flags;    /* flags for future extensions. Must be 0 for now */
+	__u32 reserved[3];
+};
+
+/* Available with KVM_CAP_S390_PROTECTED */
+#define KVM_S390_PV_COMMAND		_IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
+
+/* Available with KVM_CAP_X86_MSR_FILTER */
+#define KVM_X86_SET_MSR_FILTER	_IOW(KVMIO,  0xc6, struct kvm_msr_filter)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1606,4 +1708,7 @@ struct kvm_hyperv_eventfd {
 #define KVM_HYPERV_CONN_ID_MASK		0x00ffffff
 #define KVM_HYPERV_EVENTFD_DEASSIGN	(1 << 0)
 
+#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
+#define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
+
 #endif /* __LINUX_KVM_H */
diff --git a/powerpc/include/asm/kvm.h b/powerpc/include/asm/kvm.h
index b0f72dea8b11..c3af3f324c5a 100644
--- a/powerpc/include/asm/kvm.h
+++ b/powerpc/include/asm/kvm.h
@@ -640,6 +640,11 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_ONLINE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
 #define KVM_REG_PPC_PTCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0)
 
+/* POWER10 registers */
+#define KVM_REG_PPC_MMCR3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc1)
+#define KVM_REG_PPC_SIER2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc2)
+#define KVM_REG_PPC_SIER3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3)
+
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
  */
@@ -667,6 +672,8 @@ struct kvm_ppc_cpu_char {
 
 /* PPC64 eXternal Interrupt Controller Specification */
 #define KVM_DEV_XICS_GRP_SOURCES	1	/* 64-bit source attributes */
+#define KVM_DEV_XICS_GRP_CTRL		2
+#define   KVM_DEV_XICS_NR_SERVERS	1
 
 /* Layout of 64-bit source attribute values */
 #define  KVM_XICS_DESTINATION_SHIFT	0
@@ -683,6 +690,7 @@ struct kvm_ppc_cpu_char {
 #define KVM_DEV_XIVE_GRP_CTRL		1
 #define   KVM_DEV_XIVE_RESET		1
 #define   KVM_DEV_XIVE_EQ_SYNC		2
+#define   KVM_DEV_XIVE_NR_SERVERS	3
 #define KVM_DEV_XIVE_GRP_SOURCE		2	/* 64-bit source identifier */
 #define KVM_DEV_XIVE_GRP_SOURCE_CONFIG	3	/* 64-bit source identifier */
 #define KVM_DEV_XIVE_GRP_EQ_CONFIG	4	/* 64-bit EQ identifier */
diff --git a/x86/include/asm/kvm.h b/x86/include/asm/kvm.h
index 503d3f42da16..89e5f3d1bba8 100644
--- a/x86/include/asm/kvm.h
+++ b/x86/include/asm/kvm.h
@@ -192,6 +192,26 @@ struct kvm_msr_list {
 	__u32 indices[0];
 };
 
+/* Maximum size of any access bitmap in bytes */
+#define KVM_MSR_FILTER_MAX_BITMAP_SIZE 0x600
+
+/* for KVM_X86_SET_MSR_FILTER */
+struct kvm_msr_filter_range {
+#define KVM_MSR_FILTER_READ  (1 << 0)
+#define KVM_MSR_FILTER_WRITE (1 << 1)
+	__u32 flags;
+	__u32 nmsrs; /* number of msrs in bitmap */
+	__u32 base;  /* MSR index the bitmap starts at */
+	__u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
+};
+
+#define KVM_MSR_FILTER_MAX_RANGES 16
+struct kvm_msr_filter {
+#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#define KVM_MSR_FILTER_DEFAULT_DENY  (1 << 0)
+	__u32 flags;
+	struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
+};
 
 struct kvm_cpuid_entry {
 	__u32 function;
@@ -385,17 +405,23 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
-#define KVM_STATE_NESTED_FORMAT_SVM	1	/* unused */
+#define KVM_STATE_NESTED_FORMAT_SVM	1
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
 #define KVM_STATE_NESTED_EVMCS		0x00000004
+#define KVM_STATE_NESTED_MTF_PENDING	0x00000008
+#define KVM_STATE_NESTED_GIF_SET	0x00000100
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002
 
 #define KVM_STATE_NESTED_VMX_VMCS_SIZE	0x1000
 
+#define KVM_STATE_NESTED_SVM_VMCB_SIZE	0x1000
+
+#define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE	0x00000001
+
 struct kvm_vmx_nested_state_data {
 	__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
 	__u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
@@ -408,6 +434,18 @@ struct kvm_vmx_nested_state_hdr {
 	struct {
 		__u16 flags;
 	} smm;
+
+	__u32 flags;
+	__u64 preemption_timer_deadline;
+};
+
+struct kvm_svm_nested_state_data {
+	/* Save area only used if KVM_STATE_NESTED_RUN_PENDING.  */
+	__u8 vmcb12[KVM_STATE_NESTED_SVM_VMCB_SIZE];
+};
+
+struct kvm_svm_nested_state_hdr {
+	__u64 vmcb_pa;
 };
 
 /* for KVM_CAP_NESTED_STATE */
@@ -418,6 +456,7 @@ struct kvm_nested_state {
 
 	union {
 		struct kvm_vmx_nested_state_hdr vmx;
+		struct kvm_svm_nested_state_hdr svm;
 
 		/* Pad the header to 128 bytes.  */
 		__u8 pad[120];
@@ -430,6 +469,7 @@ struct kvm_nested_state {
 	 */
 	union {
 		struct kvm_vmx_nested_state_data vmx[0];
+		struct kvm_svm_nested_state_data svm[0];
 	} data;
 };
 
-- 
2.29.1

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

[RFC PATCH kvmtool v3 2/3] init: Add last_{init, exit} list macros

[Alexandru Elisei]

Add a last_init macro for constructor functions that will be executed last
in the initialization process. Add a symmetrical macro, last_exit, for
destructor functions that will be the last to be executed when kvmtool
exits.

The list priority for the late_{init, exit} macros has been bumped down a
spot, but their relative priority remains unchanged, to keep the same size
for the init_lists and exit_lists.

Signed-off-by: Alexandru Elisei <alexandru.elisei@arm.com>
---
 include/kvm/util-init.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/kvm/util-init.h b/include/kvm/util-init.h
index 13d4f04df678..e6a0e1696689 100644
--- a/include/kvm/util-init.h
+++ b/include/kvm/util-init.h
@@ -39,7 +39,8 @@ static void __attribute__ ((constructor)) __init__##cb(void)		\
 #define dev_init(cb) __init_list_add(cb, 5)
 #define virtio_dev_init(cb) __init_list_add(cb, 6)
 #define firmware_init(cb) __init_list_add(cb, 7)
-#define late_init(cb) __init_list_add(cb, 9)
+#define late_init(cb) __init_list_add(cb, 8)
+#define last_init(cb) __init_list_add(cb, 9)
 
 #define core_exit(cb) __exit_list_add(cb, 0)
 #define base_exit(cb) __exit_list_add(cb, 2)
@@ -47,5 +48,6 @@ static void __attribute__ ((constructor)) __init__##cb(void)		\
 #define dev_exit(cb) __exit_list_add(cb, 5)
 #define virtio_dev_exit(cb) __exit_list_add(cb, 6)
 #define firmware_exit(cb) __exit_list_add(cb, 7)
-#define late_exit(cb) __exit_list_add(cb, 9)
+#define late_exit(cb) __exit_list_add(cb, 8)
+#define last_exit(cb) __exit_list_add(cb, 9)
 #endif
-- 
2.29.1

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

[RFC PATCH kvmtool v3 3/3] arm64: Add SPE support

[Alexandru Elisei]

From: Sudeep Holla <sudeep.holla@arm.com>

Add a runtime configurable for kvmtool to enable SPE (Statistical
Profiling Extensions) for each vcpu and to create a corresponding DT node.
SPE is enabled at runtime with the --spe option.

[ Andrew M: Add SPE to init features ]
[ Alexandru E: Reworded commit, renamed spev1->spe to match kernel, added
	KVM_ARM_VM_SPE_FINALIZE, set VCPU feature only if requested by
	user ]

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Andrew Murray <andrew.murray@arm.com>
Signed-off-by: Alexandru Elisei <alexandru.elisei@arm.com>
---
 Makefile                                  |   2 +-
 arm/aarch64/arm-cpu.c                     |   2 +
 arm/aarch64/include/kvm/kvm-config-arch.h |   2 +
 arm/aarch64/include/kvm/kvm-cpu-arch.h    |   3 +-
 arm/aarch64/kvm-cpu.c                     |   5 +
 arm/include/arm-common/kvm-config-arch.h  |   1 +
 arm/include/arm-common/spe.h              |   7 +
 arm/spe.c                                 | 154 ++++++++++++++++++++++
 8 files changed, 174 insertions(+), 2 deletions(-)
 create mode 100644 arm/include/arm-common/spe.h
 create mode 100644 arm/spe.c

diff --git a/Makefile b/Makefile
index c465a491cf7e..9bfae78f0171 100644
--- a/Makefile
+++ b/Makefile
@@ -158,7 +158,7 @@ endif
 # ARM
 OBJS_ARM_COMMON		:= arm/fdt.o arm/gic.o arm/gicv2m.o arm/ioport.o \
 			   arm/kvm.o arm/kvm-cpu.o arm/pci.o arm/timer.o \
-			   arm/pmu.o
+			   arm/pmu.o arm/spe.o
 HDRS_ARM_COMMON		:= arm/include
 ifeq ($(ARCH), arm)
 	DEFINES		+= -DCONFIG_ARM
diff --git a/arm/aarch64/arm-cpu.c b/arm/aarch64/arm-cpu.c
index d7572b7790b1..6ccea033f361 100644
--- a/arm/aarch64/arm-cpu.c
+++ b/arm/aarch64/arm-cpu.c
@@ -6,6 +6,7 @@
 #include "arm-common/gic.h"
 #include "arm-common/timer.h"
 #include "arm-common/pmu.h"
+#include "arm-common/spe.h"
 
 #include <linux/byteorder.h>
 #include <linux/types.h>
@@ -17,6 +18,7 @@ static void generate_fdt_nodes(void *fdt, struct kvm *kvm)
 	gic__generate_fdt_nodes(fdt, kvm->cfg.arch.irqchip);
 	timer__generate_fdt_nodes(fdt, kvm, timer_interrupts);
 	pmu__generate_fdt_nodes(fdt, kvm);
+	spe__generate_fdt_nodes(fdt, kvm);
 }
 
 static int arm_cpu__vcpu_init(struct kvm_cpu *vcpu)
diff --git a/arm/aarch64/include/kvm/kvm-config-arch.h b/arm/aarch64/include/kvm/kvm-config-arch.h
index 04be43dfa9b2..9f618cd9d2c1 100644
--- a/arm/aarch64/include/kvm/kvm-config-arch.h
+++ b/arm/aarch64/include/kvm/kvm-config-arch.h
@@ -6,6 +6,8 @@
 			"Run AArch32 guest"),				\
 	OPT_BOOLEAN('\0', "pmu", &(cfg)->has_pmuv3,			\
 			"Create PMUv3 device"),				\
+	OPT_BOOLEAN('\0', "spe", &(cfg)->has_spe,			\
+			"Create SPE device"),				\
 	OPT_U64('\0', "kaslr-seed", &(cfg)->kaslr_seed,			\
 			"Specify random seed for Kernel Address Space "	\
 			"Layout Randomization (KASLR)"),
diff --git a/arm/aarch64/include/kvm/kvm-cpu-arch.h b/arm/aarch64/include/kvm/kvm-cpu-arch.h
index 8dfb82ecbc37..6868f2f66040 100644
--- a/arm/aarch64/include/kvm/kvm-cpu-arch.h
+++ b/arm/aarch64/include/kvm/kvm-cpu-arch.h
@@ -8,7 +8,8 @@
 #define ARM_VCPU_FEATURE_FLAGS(kvm, cpuid)	{				\
 	[0] = ((!!(cpuid) << KVM_ARM_VCPU_POWER_OFF) |				\
 	       (!!(kvm)->cfg.arch.aarch32_guest << KVM_ARM_VCPU_EL1_32BIT) |	\
-	       (!!(kvm)->cfg.arch.has_pmuv3 << KVM_ARM_VCPU_PMU_V3))		\
+	       (!!(kvm)->cfg.arch.has_pmuv3 << KVM_ARM_VCPU_PMU_V3) |		\
+	       (!!(kvm)->cfg.arch.has_spe << KVM_ARM_VCPU_SPE))			\
 }
 
 #define ARM_MPIDR_HWID_BITMASK	0xFF00FFFFFFUL
diff --git a/arm/aarch64/kvm-cpu.c b/arm/aarch64/kvm-cpu.c
index 9f3e8586880c..9b67c5f1d2e2 100644
--- a/arm/aarch64/kvm-cpu.c
+++ b/arm/aarch64/kvm-cpu.c
@@ -140,6 +140,11 @@ void kvm_cpu__select_features(struct kvm *kvm, struct kvm_vcpu_init *init)
 	/* Enable SVE if available */
 	if (kvm__supports_extension(kvm, KVM_CAP_ARM_SVE))
 		init->features[0] |= 1UL << KVM_ARM_VCPU_SVE;
+
+	/* Enable SPE if requested */
+	if (kvm->cfg.arch.has_spe &&
+	    kvm__supports_extension(kvm, KVM_CAP_ARM_SPE))
+		init->features[0] |= 1UL << KVM_ARM_VCPU_SPE;
 }
 
 int kvm_cpu__configure_features(struct kvm_cpu *vcpu)
diff --git a/arm/include/arm-common/kvm-config-arch.h b/arm/include/arm-common/kvm-config-arch.h
index 5734c46ab9e6..08d8bfd3f7e0 100644
--- a/arm/include/arm-common/kvm-config-arch.h
+++ b/arm/include/arm-common/kvm-config-arch.h
@@ -9,6 +9,7 @@ struct kvm_config_arch {
 	bool		virtio_trans_pci;
 	bool		aarch32_guest;
 	bool		has_pmuv3;
+	bool		has_spe;
 	u64		kaslr_seed;
 	enum irqchip_type irqchip;
 	u64		fw_addr;
diff --git a/arm/include/arm-common/spe.h b/arm/include/arm-common/spe.h
new file mode 100644
index 000000000000..75b12827cfbb
--- /dev/null
+++ b/arm/include/arm-common/spe.h
@@ -0,0 +1,7 @@
+#ifndef ARM_COMMON__SPE_H
+#define ARM_COMMON__SPE_H
+
+#define KVM_ARM_SPE_IRQ	21
+
+void spe__generate_fdt_nodes(void *fdt, struct kvm *kvm);
+#endif /* ARM_COMMON__SPE_H */
diff --git a/arm/spe.c b/arm/spe.c
new file mode 100644
index 000000000000..0e7e85e77311
--- /dev/null
+++ b/arm/spe.c
@@ -0,0 +1,154 @@
+#include <stdio.h>
+#include <errno.h>
+
+#include <sys/resource.h>
+
+#include "kvm/fdt.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/util.h"
+
+#include "arm-common/gic.h"
+#include "arm-common/spe.h"
+
+#ifdef CONFIG_ARM64
+static int set_spe_vcpu_attr(struct kvm *kvm, int vcpu_idx,
+			struct kvm_device_attr *attr)
+{
+	int ret, fd;
+
+	fd = kvm->cpus[vcpu_idx]->vcpu_fd;
+
+	ret = ioctl(fd, KVM_HAS_DEVICE_ATTR, attr);
+	if (ret) {
+		perror("SPE VCPU KVM_HAS_DEVICE_ATTR");
+		return ret;
+	}
+
+	ret = ioctl(fd, KVM_SET_DEVICE_ATTR, attr);
+	if (ret)
+		perror("SPE VCPU KVM_SET_DEVICE_ATTR");
+
+	return ret;
+}
+
+void spe__generate_fdt_nodes(void *fdt, struct kvm *kvm)
+{
+	const char compatible[] = "arm,statistical-profiling-extension-v1";
+	int irq = KVM_ARM_SPE_IRQ;
+	int i, ret;
+
+	u32 cpu_mask = (((1 << kvm->nrcpus) - 1) << GIC_FDT_IRQ_PPI_CPU_SHIFT) \
+		       & GIC_FDT_IRQ_PPI_CPU_MASK;
+	u32 irq_prop[] = {
+		cpu_to_fdt32(GIC_FDT_IRQ_TYPE_PPI),
+		cpu_to_fdt32(irq - 16),
+		cpu_to_fdt32(cpu_mask | IRQ_TYPE_LEVEL_HIGH),
+	};
+
+	if (!kvm->cfg.arch.has_spe)
+		return;
+
+	if (!kvm__supports_extension(kvm, KVM_CAP_ARM_SPE)) {
+		pr_info("SPE unsupported by KVM\n");
+		return;
+	}
+
+	for (i = 0; i < kvm->nrcpus; i++) {
+		struct kvm_device_attr spe_attr;
+
+		spe_attr = (struct kvm_device_attr){
+			.group	= KVM_ARM_VCPU_SPE_CTRL,
+			.addr	= (u64)(unsigned long)&irq,
+			.attr	= KVM_ARM_VCPU_SPE_IRQ,
+		};
+
+		ret = set_spe_vcpu_attr(kvm, i, &spe_attr);
+		if (ret)
+			return;
+
+		spe_attr = (struct kvm_device_attr){
+			.group	= KVM_ARM_VCPU_SPE_CTRL,
+			.attr	= KVM_ARM_VCPU_SPE_INIT,
+		};
+
+		ret = set_spe_vcpu_attr(kvm, i, &spe_attr);
+		if (ret)
+			return;
+	}
+
+	_FDT(fdt_begin_node(fdt, "spe"));
+	_FDT(fdt_property(fdt, "compatible", compatible, sizeof(compatible)));
+	_FDT(fdt_property(fdt, "interrupts", irq_prop, sizeof(irq_prop)));
+	_FDT(fdt_end_node(fdt));
+}
+
+static int set_spe_vm_attr(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	int ret;
+
+	ret = ioctl(kvm->vm_fd, KVM_HAS_DEVICE_ATTR, attr);
+	if (ret) {
+		perror("SPE VM KVM_HAS_DEVICE_ATTR");
+		return ret;
+	}
+
+	ret = ioctl(kvm->vm_fd, KVM_SET_DEVICE_ATTR, attr);
+	if (ret)
+		perror("SPE VM KVM_SET_DEVICE_ATTR");
+
+	return ret;
+}
+
+static void spe_try_increase_mlock_limit(struct kvm *kvm)
+{
+	u64 size = kvm->arch.ram_alloc_size;
+	struct rlimit mlock_limit, new_limit;
+
+	if (getrlimit(RLIMIT_MEMLOCK, &mlock_limit)) {
+		perror("getrlimit(RLIMIT_MEMLOCK)");
+		return;
+	}
+
+	if (mlock_limit.rlim_cur > size)
+		return;
+
+	new_limit.rlim_cur = size;
+	new_limit.rlim_max = max((rlim_t)size, mlock_limit.rlim_max);
+	/* Requires CAP_SYS_RESOURCE capability. */
+	setrlimit(RLIMIT_MEMLOCK, &new_limit);
+}
+
+static int spe__finalize(struct kvm *kvm)
+{
+	struct kvm_device_attr spe_attr = (struct kvm_device_attr) {
+		.group	= KVM_ARM_VM_SPE_CTRL,
+		.attr	= KVM_ARM_VM_SPE_FINALIZE,
+	};
+	int ret;
+
+	if (!kvm->cfg.arch.has_spe)
+		return 0;
+
+	if (!kvm__supports_extension(kvm, KVM_CAP_ARM_SPE))
+		return 0;
+
+	spe_try_increase_mlock_limit(kvm);
+
+	ret = mlock(kvm->arch.ram_alloc_start, kvm->arch.ram_alloc_size);
+	if (ret) {
+		perror("mlock");
+		return ret;
+	}
+
+	ret = set_spe_vm_attr(kvm, &spe_attr);
+	if (ret)
+		munlock(kvm->arch.ram_alloc_start, kvm->arch.ram_alloc_size);
+
+	return ret;
+}
+last_init(spe__finalize);
+
+#else
+void spe__generate_fdt_nodes(void *fdt, struct kvm *kvm) { }
+#endif
-- 
2.29.1

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm