From 2b953ea348128ef4d70b0e21f01c1bdee48ee4dc Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Fri, 28 Sep 2018 14:39:18 +0100 Subject: KVM: Allow 2048-bit register access via ioctl interface The Arm SVE architecture defines registers that are up to 2048 bits in size (with some possibility of further future expansion). In order to avoid the need for an excessively large number of ioctls when saving and restoring a vcpu's registers, this patch adds a #define to make support for individual 2048-bit registers through the KVM_{GET,SET}_ONE_REG ioctl interface official. This will allow each SVE register to be accessed in a single call. There are sufficient spare bits in the register id size field for this change, so there is no ABI impact, providing that KVM_GET_REG_LIST does not enumerate any 2048-bit register unless userspace explicitly opts in to the relevant architecture-specific features. Signed-off-by: Dave Martin Reviewed-by: Alex Bennée Tested-by: zhang.lei Signed-off-by: Marc Zyngier --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 6d4ea4b6c922..dc77a5a3648d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1145,6 +1145,7 @@ struct kvm_dirty_tlb { #define KVM_REG_SIZE_U256 0x0050000000000000ULL #define KVM_REG_SIZE_U512 0x0060000000000000ULL #define KVM_REG_SIZE_U1024 0x0070000000000000ULL +#define KVM_REG_SIZE_U2048 0x0080000000000000ULL struct kvm_reg_list { __u64 n; /* number of regs */ -- cgit v1.2.3 From 7dd32a0d0103a5941efbb971f85a3e930cc5665e Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Wed, 19 Dec 2018 14:27:01 +0000 Subject: KVM: arm/arm64: Add KVM_ARM_VCPU_FINALIZE ioctl Some aspects of vcpu configuration may be too complex to be completed inside KVM_ARM_VCPU_INIT. Thus, there may be a requirement for userspace to do some additional configuration before various other ioctls will work in a consistent way. In particular this will be the case for SVE, where userspace will need to negotiate the set of vector lengths to be made available to the guest before the vcpu becomes fully usable. In order to provide an explicit way for userspace to confirm that it has finished setting up a particular vcpu feature, this patch adds a new ioctl KVM_ARM_VCPU_FINALIZE. When userspace has opted into a feature that requires finalization, typically by means of a feature flag passed to KVM_ARM_VCPU_INIT, a matching call to KVM_ARM_VCPU_FINALIZE is now required before KVM_RUN or KVM_GET_REG_LIST is allowed. Individual features may impose additional restrictions where appropriate. No existing vcpu features are affected by this, so current userspace implementations will continue to work exactly as before, with no need to issue KVM_ARM_VCPU_FINALIZE. As implemented in this patch, KVM_ARM_VCPU_FINALIZE is currently a placeholder: no finalizable features exist yet, so ioctl is not required and will always yield EINVAL. Subsequent patches will add the finalization logic to make use of this ioctl for SVE. No functional change for existing userspace. Signed-off-by: Dave Martin Reviewed-by: Julien Thierry Tested-by: zhang.lei Signed-off-by: Marc Zyngier --- arch/arm/include/asm/kvm_host.h | 4 ++++ arch/arm64/include/asm/kvm_host.h | 4 ++++ include/uapi/linux/kvm.h | 3 +++ virt/kvm/arm/arm.c | 18 ++++++++++++++++++ 4 files changed, 29 insertions(+) (limited to 'include') diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index a49ee01242ff..e80cfc18412b 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -19,6 +19,7 @@ #ifndef __ARM_KVM_HOST_H__ #define __ARM_KVM_HOST_H__ +#include #include #include #include @@ -411,4 +412,7 @@ static inline int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type) return 0; } +#define kvm_arm_vcpu_finalize(vcpu, what) (-EINVAL) +#define kvm_arm_vcpu_is_finalized(vcpu) true + #endif /* __ARM_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 3e8950942591..98658f7dad68 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -23,6 +23,7 @@ #define __ARM64_KVM_HOST_H__ #include +#include #include #include #include @@ -625,4 +626,7 @@ void kvm_arch_free_vm(struct kvm *kvm); int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type); +#define kvm_arm_vcpu_finalize(vcpu, what) (-EINVAL) +#define kvm_arm_vcpu_is_finalized(vcpu) true + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index dc77a5a3648d..c3b8e7a31315 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1441,6 +1441,9 @@ struct kvm_enc_region { /* Available with KVM_CAP_HYPERV_CPUID */ #define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2) +/* Available with KVM_CAP_ARM_SVE */ +#define KVM_ARM_VCPU_FINALIZE _IOW(KVMIO, 0xc2, int) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index c69e1370a5dc..9edbf0f676e7 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -545,6 +545,9 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) if (likely(vcpu->arch.has_run_once)) return 0; + if (!kvm_arm_vcpu_is_finalized(vcpu)) + return -EPERM; + vcpu->arch.has_run_once = true; if (likely(irqchip_in_kernel(kvm))) { @@ -1116,6 +1119,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (unlikely(!kvm_vcpu_initialized(vcpu))) break; + r = -EPERM; + if (!kvm_arm_vcpu_is_finalized(vcpu)) + break; + r = -EFAULT; if (copy_from_user(®_list, user_list, sizeof(reg_list))) break; @@ -1169,6 +1176,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp, return kvm_arm_vcpu_set_events(vcpu, &events); } + case KVM_ARM_VCPU_FINALIZE: { + int what; + + if (!kvm_vcpu_initialized(vcpu)) + return -ENOEXEC; + + if (get_user(what, (const int __user *)argp)) + return -EFAULT; + + return kvm_arm_vcpu_finalize(vcpu, what); + } default: r = -EINVAL; } -- cgit v1.2.3 From 555f3d03e7fb43a539050aee91337978da14a25e Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Tue, 15 Jan 2019 12:21:22 +0000 Subject: KVM: arm64: Add a capability to advertise SVE support To provide a uniform way to check for KVM SVE support amongst other features, this patch adds a suitable capability KVM_CAP_ARM_SVE, and reports it as present when SVE is available. Signed-off-by: Dave Martin Reviewed-by: Julien Thierry Tested-by: zhang.lei Signed-off-by: Marc Zyngier --- arch/arm64/kvm/reset.c | 3 +++ include/uapi/linux/kvm.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 32c5ac0a3872..f13378d0a0ad 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -98,6 +98,9 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_VM_IPA_SIZE: r = kvm_ipa_limit; break; + case KVM_CAP_ARM_SVE: + r = system_supports_sve(); + break; default: r = 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index c3b8e7a31315..1d564445b515 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -988,6 +988,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_VM_IPA_SIZE 165 #define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 #define KVM_CAP_HYPERV_CPUID 167 +#define KVM_CAP_ARM_SVE 168 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From a243c16d18be130b17cf1064e9115de73bfdff5a Mon Sep 17 00:00:00 2001 From: Amit Daniel Kachhap Date: Tue, 23 Apr 2019 10:12:37 +0530 Subject: KVM: arm64: Add capability to advertise ptrauth for guest This patch advertises the capability of two cpu feature called address pointer authentication and generic pointer authentication. These capabilities depend upon system support for pointer authentication and VHE mode. The current arm64 KVM partially implements pointer authentication and support of address/generic authentication are tied together. However, separate ABI requirements for both of them is added so that any future isolated implementation will not require any ABI changes. Signed-off-by: Amit Daniel Kachhap Cc: Mark Rutland Cc: Marc Zyngier Cc: Christoffer Dall Cc: kvmarm@lists.cs.columbia.edu Signed-off-by: Marc Zyngier --- Documentation/virtual/kvm/api.txt | 14 ++++++++++---- arch/arm64/kvm/reset.c | 5 +++++ include/uapi/linux/kvm.h | 2 ++ 3 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 32afe7f5c35a..fac1887f25b5 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -2763,13 +2763,19 @@ Possible features: - KVM_ARM_VCPU_PTRAUTH_ADDRESS: Enables Address Pointer authentication for arm64 only. - Both KVM_ARM_VCPU_PTRAUTH_ADDRESS and KVM_ARM_VCPU_PTRAUTH_GENERIC - must be requested or neither must be requested. + Depends on KVM_CAP_ARM_PTRAUTH_ADDRESS. + If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are + both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and + KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be + requested. - KVM_ARM_VCPU_PTRAUTH_GENERIC: Enables Generic Pointer authentication for arm64 only. - Both KVM_ARM_VCPU_PTRAUTH_ADDRESS and KVM_ARM_VCPU_PTRAUTH_GENERIC - must be requested or neither must be requested. + Depends on KVM_CAP_ARM_PTRAUTH_GENERIC. + If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are + both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and + KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be + requested. - KVM_ARM_VCPU_SVE: Enables SVE for the CPU (arm64 only). Depends on KVM_CAP_ARM_SVE. diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 028d0c604652..f0faf54f5857 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -101,6 +101,11 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_SVE: r = system_supports_sve(); break; + case KVM_CAP_ARM_PTRAUTH_ADDRESS: + case KVM_CAP_ARM_PTRAUTH_GENERIC: + r = has_vhe() && system_supports_address_auth() && + system_supports_generic_auth(); + break; default: r = 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 1d564445b515..4dc34f8e29f6 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -989,6 +989,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 #define KVM_CAP_HYPERV_CPUID 167 #define KVM_CAP_ARM_SVE 168 +#define KVM_CAP_ARM_PTRAUTH_ADDRESS 169 +#define KVM_CAP_ARM_PTRAUTH_GENERIC 170 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From cdd6ad3ac63d2fa320baefcf92a02a918375c30f Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 5 Mar 2019 05:30:01 -0500 Subject: KVM: polling: add architecture backend to disable polling There are cases where halt polling is unwanted. For example when running KVM on an over committed LPAR we rather want to give back the CPU to neighbour LPARs instead of polling. Let us provide a callback that allows architectures to disable polling. Signed-off-by: Christian Borntraeger Acked-by: Paolo Bonzini Reviewed-by: Cornelia Huck Signed-off-by: Christian Borntraeger --- include/linux/kvm_host.h | 10 ++++++++++ virt/kvm/Kconfig | 3 +++ virt/kvm/kvm_main.c | 2 +- 3 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9d55c63db09b..b3aff1a3f633 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1305,6 +1305,16 @@ static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) } #endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */ +#ifdef CONFIG_HAVE_KVM_NO_POLL +/* Callback that tells if we must not poll */ +bool kvm_arch_no_poll(struct kvm_vcpu *vcpu); +#else +static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) +{ + return false; +} +#endif /* CONFIG_HAVE_KVM_NO_POLL */ + #ifdef CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index ea434ddc8499..aad9284c043a 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -57,3 +57,6 @@ config HAVE_KVM_VCPU_ASYNC_IOCTL config HAVE_KVM_VCPU_RUN_PID_CHANGE bool + +config HAVE_KVM_NO_POLL + bool diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 55fe8e20d8fd..23aec2f4ba71 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2253,7 +2253,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) u64 block_ns; start = cur = ktime_get(); - if (vcpu->halt_poll_ns) { + if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) { ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns); ++vcpu->stat.halt_attempted_poll; -- cgit v1.2.3 From 90c73795afa24890bd2ae4f3b359de04b4147d37 Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Thu, 18 Apr 2019 12:39:27 +0200 Subject: KVM: PPC: Book3S HV: Add a new KVM device for the XIVE native exploitation mode This is the basic framework for the new KVM device supporting the XIVE native exploitation mode. The user interface exposes a new KVM device to be created by QEMU, only available when running on a L0 hypervisor. Support for nested guests is not available yet. The XIVE device reuses the device structure of the XICS-on-XIVE device as they have a lot in common. That could possibly change in the future if the need arise. Signed-off-by: Cédric Le Goater Reviewed-by: David Gibson Signed-off-by: Paul Mackerras --- Documentation/virtual/kvm/devices/xive.txt | 19 +++ arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/include/asm/kvm_ppc.h | 8 ++ arch/powerpc/include/uapi/asm/kvm.h | 3 + arch/powerpc/kvm/Makefile | 2 +- arch/powerpc/kvm/book3s.c | 7 +- arch/powerpc/kvm/book3s_xive_native.c | 179 +++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 2 + 8 files changed, 219 insertions(+), 2 deletions(-) create mode 100644 Documentation/virtual/kvm/devices/xive.txt create mode 100644 arch/powerpc/kvm/book3s_xive_native.c (limited to 'include') diff --git a/Documentation/virtual/kvm/devices/xive.txt b/Documentation/virtual/kvm/devices/xive.txt new file mode 100644 index 000000000000..fdbd2ff92a88 --- /dev/null +++ b/Documentation/virtual/kvm/devices/xive.txt @@ -0,0 +1,19 @@ +POWER9 eXternal Interrupt Virtualization Engine (XIVE Gen1) +========================================================== + +Device types supported: + KVM_DEV_TYPE_XIVE POWER9 XIVE Interrupt Controller generation 1 + +This device acts as a VM interrupt controller. It provides the KVM +interface to configure the interrupt sources of a VM in the underlying +POWER9 XIVE interrupt controller. + +Only one XIVE instance may be instantiated. A guest XIVE device +requires a POWER9 host and the guest OS should have support for the +XIVE native exploitation interrupt mode. If not, it should run using +the legacy interrupt mode, referred as XICS (POWER7/8). + +* Groups: + + 1. KVM_DEV_XIVE_GRP_CTRL + Provides global controls on the device diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 07cefa53222e..9074f1d7613c 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -225,6 +225,7 @@ extern struct kvm_device_ops kvm_xics_ops; struct kvmppc_xive; struct kvmppc_xive_vcpu; extern struct kvm_device_ops kvm_xive_ops; +extern struct kvm_device_ops kvm_xive_native_ops; struct kvmppc_passthru_irqmap; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 0e99a6f8066f..f746d85f36c7 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -593,6 +593,10 @@ extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval); extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu); + +extern void kvmppc_xive_native_init_module(void); +extern void kvmppc_xive_native_exit_module(void); + #else static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server, u32 priority) { return -1; } @@ -616,6 +620,10 @@ static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { retur static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status) { return -ENODEV; } static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { } + +static inline void kvmppc_xive_native_init_module(void) { } +static inline void kvmppc_xive_native_exit_module(void) { } + #endif /* CONFIG_KVM_XIVE */ #if defined(CONFIG_PPC_POWERNV) && defined(CONFIG_KVM_BOOK3S_64_HANDLER) diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 26ca425f4c2c..be0ce1f17625 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -677,4 +677,7 @@ struct kvm_ppc_cpu_char { #define KVM_XICS_PRESENTED (1ULL << 43) #define KVM_XICS_QUEUED (1ULL << 44) +/* POWER9 XIVE Native Interrupt Controller */ +#define KVM_DEV_XIVE_GRP_CTRL 1 + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 3223aec88b2c..4c67cc79de7c 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -94,7 +94,7 @@ endif kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \ book3s_xics.o -kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o +kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o book3s_xive_native.o kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o kvm-book3s_64-module-objs := \ diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 10c5579d20ce..7c3348fa27e1 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -1050,6 +1050,9 @@ static int kvmppc_book3s_init(void) if (xics_on_xive()) { kvmppc_xive_init_module(); kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS); + kvmppc_xive_native_init_module(); + kvm_register_device_ops(&kvm_xive_native_ops, + KVM_DEV_TYPE_XIVE); } else #endif kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS); @@ -1060,8 +1063,10 @@ static int kvmppc_book3s_init(void) static void kvmppc_book3s_exit(void) { #ifdef CONFIG_KVM_XICS - if (xics_on_xive()) + if (xics_on_xive()) { kvmppc_xive_exit_module(); + kvmppc_xive_native_exit_module(); + } #endif #ifdef CONFIG_KVM_BOOK3S_32_HANDLER kvmppc_book3s_exit_pr(); diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c new file mode 100644 index 000000000000..751259394150 --- /dev/null +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2017-2019, IBM Corporation. + */ + +#define pr_fmt(fmt) "xive-kvm: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "book3s_xive.h" + +static int kvmppc_xive_native_set_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_XIVE_GRP_CTRL: + break; + } + return -ENXIO; +} + +static int kvmppc_xive_native_get_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + return -ENXIO; +} + +static int kvmppc_xive_native_has_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_XIVE_GRP_CTRL: + break; + } + return -ENXIO; +} + +static void kvmppc_xive_native_free(struct kvm_device *dev) +{ + struct kvmppc_xive *xive = dev->private; + struct kvm *kvm = xive->kvm; + + debugfs_remove(xive->dentry); + + pr_devel("Destroying xive native device\n"); + + if (kvm) + kvm->arch.xive = NULL; + + if (xive->vp_base != XIVE_INVALID_VP) + xive_native_free_vp_block(xive->vp_base); + + kfree(xive); + kfree(dev); +} + +static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type) +{ + struct kvmppc_xive *xive; + struct kvm *kvm = dev->kvm; + int ret = 0; + + pr_devel("Creating xive native device\n"); + + if (kvm->arch.xive) + return -EEXIST; + + xive = kzalloc(sizeof(*xive), GFP_KERNEL); + if (!xive) + return -ENOMEM; + + dev->private = xive; + xive->dev = dev; + xive->kvm = kvm; + kvm->arch.xive = xive; + + /* + * Allocate a bunch of VPs. KVM_MAX_VCPUS is a large value for + * a default. Getting the max number of CPUs the VM was + * configured with would improve our usage of the XIVE VP space. + */ + xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS); + pr_devel("VP_Base=%x\n", xive->vp_base); + + if (xive->vp_base == XIVE_INVALID_VP) + ret = -ENXIO; + + xive->single_escalation = xive_native_has_single_escalation(); + + if (ret) + kfree(xive); + + return ret; +} + +static int xive_native_debug_show(struct seq_file *m, void *private) +{ + struct kvmppc_xive *xive = m->private; + struct kvm *kvm = xive->kvm; + + if (!kvm) + return 0; + + return 0; +} + +static int xive_native_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, xive_native_debug_show, inode->i_private); +} + +static const struct file_operations xive_native_debug_fops = { + .open = xive_native_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void xive_native_debugfs_init(struct kvmppc_xive *xive) +{ + char *name; + + name = kasprintf(GFP_KERNEL, "kvm-xive-%p", xive); + if (!name) { + pr_err("%s: no memory for name\n", __func__); + return; + } + + xive->dentry = debugfs_create_file(name, 0444, powerpc_debugfs_root, + xive, &xive_native_debug_fops); + + pr_debug("%s: created %s\n", __func__, name); + kfree(name); +} + +static void kvmppc_xive_native_init(struct kvm_device *dev) +{ + struct kvmppc_xive *xive = (struct kvmppc_xive *)dev->private; + + /* Register some debug interfaces */ + xive_native_debugfs_init(xive); +} + +struct kvm_device_ops kvm_xive_native_ops = { + .name = "kvm-xive-native", + .create = kvmppc_xive_native_create, + .init = kvmppc_xive_native_init, + .destroy = kvmppc_xive_native_free, + .set_attr = kvmppc_xive_native_set_attr, + .get_attr = kvmppc_xive_native_get_attr, + .has_attr = kvmppc_xive_native_has_attr, +}; + +void kvmppc_xive_native_init_module(void) +{ + ; +} + +void kvmppc_xive_native_exit_module(void) +{ + ; +} diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 6d4ea4b6c922..e6368163d3a0 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1211,6 +1211,8 @@ enum kvm_device_type { #define KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_ITS, #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_MAX, }; -- cgit v1.2.3 From eacc56bb9de3e6830ddc169553772cd6de59ee4c Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Thu, 18 Apr 2019 12:39:28 +0200 Subject: KVM: PPC: Book3S HV: XIVE: Introduce a new capability KVM_CAP_PPC_IRQ_XIVE The user interface exposes a new capability KVM_CAP_PPC_IRQ_XIVE to let QEMU connect the vCPU presenters to the XIVE KVM device if required. The capability is not advertised for now as the full support for the XIVE native exploitation mode is not yet available. When this is case, the capability will be advertised on PowerNV Hypervisors only. Nested guests (pseries KVM Hypervisor) are not supported. Internally, the interface to the new KVM device is protected with a new interrupt mode: KVMPPC_IRQ_XIVE. Signed-off-by: Cédric Le Goater Reviewed-by: David Gibson Signed-off-by: Paul Mackerras --- Documentation/virtual/kvm/api.txt | 9 ++ arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/include/asm/kvm_ppc.h | 13 +++ arch/powerpc/kvm/book3s_xive.c | 88 ++++++++++---------- arch/powerpc/kvm/book3s_xive.h | 11 +++ arch/powerpc/kvm/book3s_xive_native.c | 150 ++++++++++++++++++++++++++++++++++ arch/powerpc/kvm/powerpc.c | 36 ++++++++ include/uapi/linux/kvm.h | 1 + 8 files changed, 268 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 67068c47c591..e38eb17b7be6 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -4504,6 +4504,15 @@ struct kvm_sync_regs { struct kvm_vcpu_events events; }; +6.75 KVM_CAP_PPC_IRQ_XIVE + +Architectures: ppc +Target: vcpu +Parameters: args[0] is the XIVE device fd + args[1] is the XIVE CPU number (server ID) for this vcpu + +This capability connects the vcpu to an in-kernel XIVE device. + 7. Capabilities that can be enabled on VMs ------------------------------------------ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 9074f1d7613c..eac25fd7e631 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -453,6 +453,7 @@ struct kvmppc_passthru_irqmap { #define KVMPPC_IRQ_DEFAULT 0 #define KVMPPC_IRQ_MPIC 1 #define KVMPPC_IRQ_XICS 2 /* Includes a XIVE option */ +#define KVMPPC_IRQ_XIVE 3 /* XIVE native exploitation mode */ #define MMIO_HPTE_CACHE_SIZE 4 diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index f746d85f36c7..9fc2753e516e 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -594,6 +594,14 @@ extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu); +static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.irq_type == KVMPPC_IRQ_XIVE; +} + +extern int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, + struct kvm_vcpu *vcpu, u32 cpu); +extern void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu); extern void kvmppc_xive_native_init_module(void); extern void kvmppc_xive_native_exit_module(void); @@ -621,6 +629,11 @@ static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 ir int level, bool line_status) { return -ENODEV; } static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { } +static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu) + { return 0; } +static inline int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, + struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; } +static inline void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { } static inline void kvmppc_xive_native_init_module(void) { } static inline void kvmppc_xive_native_exit_module(void) { } diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index f78d002f0fe0..e7f1ada1c3de 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -380,11 +380,6 @@ static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio) return -EBUSY; } -static u32 xive_vp(struct kvmppc_xive *xive, u32 server) -{ - return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server); -} - static u8 xive_lock_and_mask(struct kvmppc_xive *xive, struct kvmppc_xive_src_block *sb, struct kvmppc_xive_irq_state *state) @@ -430,8 +425,8 @@ static u8 xive_lock_and_mask(struct kvmppc_xive *xive, */ if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) { xive_native_configure_irq(hw_num, - xive_vp(xive, state->act_server), - MASKED, state->number); + kvmppc_xive_vp(xive, state->act_server), + MASKED, state->number); /* set old_p so we can track if an H_EOI was done */ state->old_p = true; state->old_q = false; @@ -486,8 +481,8 @@ static void xive_finish_unmask(struct kvmppc_xive *xive, */ if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) { xive_native_configure_irq(hw_num, - xive_vp(xive, state->act_server), - state->act_priority, state->number); + kvmppc_xive_vp(xive, state->act_server), + state->act_priority, state->number); /* If an EOI is needed, do it here */ if (!state->old_p) xive_vm_source_eoi(hw_num, xd); @@ -563,7 +558,7 @@ static int xive_target_interrupt(struct kvm *kvm, kvmppc_xive_select_irq(state, &hw_num, NULL); return xive_native_configure_irq(hw_num, - xive_vp(xive, server), + kvmppc_xive_vp(xive, server), prio, state->number); } @@ -951,7 +946,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq, * which is fine for a never started interrupt. */ xive_native_configure_irq(hw_irq, - xive_vp(xive, state->act_server), + kvmppc_xive_vp(xive, state->act_server), state->act_priority, state->number); /* @@ -1027,7 +1022,7 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq, /* Reconfigure the IPI */ xive_native_configure_irq(state->ipi_number, - xive_vp(xive, state->act_server), + kvmppc_xive_vp(xive, state->act_server), state->act_priority, state->number); /* @@ -1049,7 +1044,7 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq, } EXPORT_SYMBOL_GPL(kvmppc_xive_clr_mapped); -static void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu) +void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; struct kvm *kvm = vcpu->kvm; @@ -1166,7 +1161,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, xc->xive = xive; xc->vcpu = vcpu; xc->server_num = cpu; - xc->vp_id = xive_vp(xive, cpu); + xc->vp_id = kvmppc_xive_vp(xive, cpu); xc->mfrr = 0xff; xc->valid = true; @@ -1883,6 +1878,43 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) return 0; } +int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu) +{ + struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; + unsigned int i; + + for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) { + struct xive_q *q = &xc->queues[i]; + u32 i0, i1, idx; + + if (!q->qpage && !xc->esc_virq[i]) + continue; + + seq_printf(m, " [q%d]: ", i); + + if (q->qpage) { + idx = q->idx; + i0 = be32_to_cpup(q->qpage + idx); + idx = (idx + 1) & q->msk; + i1 = be32_to_cpup(q->qpage + idx); + seq_printf(m, "T=%d %08x %08x...\n", q->toggle, + i0, i1); + } + if (xc->esc_virq[i]) { + struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]); + struct xive_irq_data *xd = + irq_data_get_irq_handler_data(d); + u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET); + + seq_printf(m, "E:%c%c I(%d:%llx:%llx)", + (pq & XIVE_ESB_VAL_P) ? 'P' : 'p', + (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q', + xc->esc_virq[i], pq, xd->eoi_page); + seq_puts(m, "\n"); + } + } + return 0; +} static int xive_debug_show(struct seq_file *m, void *private) { @@ -1908,7 +1940,6 @@ static int xive_debug_show(struct seq_file *m, void *private) kvm_for_each_vcpu(i, vcpu, kvm) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; - unsigned int i; if (!xc) continue; @@ -1918,33 +1949,8 @@ static int xive_debug_show(struct seq_file *m, void *private) xc->server_num, xc->cppr, xc->hw_cppr, xc->mfrr, xc->pending, xc->stat_rm_h_xirr, xc->stat_vm_h_xirr); - for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) { - struct xive_q *q = &xc->queues[i]; - u32 i0, i1, idx; - if (!q->qpage && !xc->esc_virq[i]) - continue; - - seq_printf(m, " [q%d]: ", i); - - if (q->qpage) { - idx = q->idx; - i0 = be32_to_cpup(q->qpage + idx); - idx = (idx + 1) & q->msk; - i1 = be32_to_cpup(q->qpage + idx); - seq_printf(m, "T=%d %08x %08x... \n", q->toggle, i0, i1); - } - if (xc->esc_virq[i]) { - struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]); - struct xive_irq_data *xd = irq_data_get_irq_handler_data(d); - u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET); - seq_printf(m, "E:%c%c I(%d:%llx:%llx)", - (pq & XIVE_ESB_VAL_P) ? 'P' : 'p', - (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q', - xc->esc_virq[i], pq, xd->eoi_page); - seq_printf(m, "\n"); - } - } + kvmppc_xive_debug_show_queues(m, vcpu); t_rm_h_xirr += xc->stat_rm_h_xirr; t_rm_h_ipoll += xc->stat_rm_h_ipoll; diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index a08ae6fd4c51..d366df69b9cb 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -198,6 +198,11 @@ static inline struct kvmppc_xive_src_block *kvmppc_xive_find_source(struct kvmpp return xive->src_blocks[bid]; } +static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server) +{ + return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server); +} + /* * Mapping between guest priorities and host priorities * is as follow. @@ -248,5 +253,11 @@ extern int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server, extern int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr); extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr); +/* + * Common Xive routines for XICS-over-XIVE and XIVE native + */ +void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu); +int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu); + #endif /* CONFIG_KVM_XICS */ #endif /* _KVM_PPC_BOOK3S_XICS_H */ diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 751259394150..6fa73cfd9d9c 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -26,6 +26,134 @@ #include "book3s_xive.h" +static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio) +{ + struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; + struct xive_q *q = &xc->queues[prio]; + + xive_native_disable_queue(xc->vp_id, q, prio); + if (q->qpage) { + put_page(virt_to_page(q->qpage)); + q->qpage = NULL; + } +} + +void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) +{ + struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; + int i; + + if (!kvmppc_xive_enabled(vcpu)) + return; + + if (!xc) + return; + + pr_devel("native_cleanup_vcpu(cpu=%d)\n", xc->server_num); + + /* Ensure no interrupt is still routed to that VP */ + xc->valid = false; + kvmppc_xive_disable_vcpu_interrupts(vcpu); + + /* Disable the VP */ + xive_native_disable_vp(xc->vp_id); + + /* Free the queues & associated interrupts */ + for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) { + /* Free the escalation irq */ + if (xc->esc_virq[i]) { + free_irq(xc->esc_virq[i], vcpu); + irq_dispose_mapping(xc->esc_virq[i]); + kfree(xc->esc_virq_names[i]); + xc->esc_virq[i] = 0; + } + + /* Free the queue */ + kvmppc_xive_native_cleanup_queue(vcpu, i); + } + + /* Free the VP */ + kfree(xc); + + /* Cleanup the vcpu */ + vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT; + vcpu->arch.xive_vcpu = NULL; +} + +int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, + struct kvm_vcpu *vcpu, u32 server_num) +{ + struct kvmppc_xive *xive = dev->private; + struct kvmppc_xive_vcpu *xc = NULL; + int rc; + + pr_devel("native_connect_vcpu(server=%d)\n", server_num); + + if (dev->ops != &kvm_xive_native_ops) { + pr_devel("Wrong ops !\n"); + return -EPERM; + } + if (xive->kvm != vcpu->kvm) + return -EPERM; + if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT) + return -EBUSY; + if (server_num >= KVM_MAX_VCPUS) { + pr_devel("Out of bounds !\n"); + return -EINVAL; + } + + mutex_lock(&vcpu->kvm->lock); + + if (kvmppc_xive_find_server(vcpu->kvm, server_num)) { + pr_devel("Duplicate !\n"); + rc = -EEXIST; + goto bail; + } + + xc = kzalloc(sizeof(*xc), GFP_KERNEL); + if (!xc) { + rc = -ENOMEM; + goto bail; + } + + vcpu->arch.xive_vcpu = xc; + xc->xive = xive; + xc->vcpu = vcpu; + xc->server_num = server_num; + + xc->vp_id = kvmppc_xive_vp(xive, server_num); + xc->valid = true; + vcpu->arch.irq_type = KVMPPC_IRQ_XIVE; + + rc = xive_native_get_vp_info(xc->vp_id, &xc->vp_cam, &xc->vp_chip_id); + if (rc) { + pr_err("Failed to get VP info from OPAL: %d\n", rc); + goto bail; + } + + /* + * Enable the VP first as the single escalation mode will + * affect escalation interrupts numbering + */ + rc = xive_native_enable_vp(xc->vp_id, xive->single_escalation); + if (rc) { + pr_err("Failed to enable VP in OPAL: %d\n", rc); + goto bail; + } + + /* Configure VCPU fields for use by assembly push/pull */ + vcpu->arch.xive_saved_state.w01 = cpu_to_be64(0xff000000); + vcpu->arch.xive_cam_word = cpu_to_be32(xc->vp_cam | TM_QW1W2_VO); + + /* TODO: reset all queues to a clean state ? */ +bail: + mutex_unlock(&vcpu->kvm->lock); + if (rc) + kvmppc_xive_native_cleanup_vcpu(vcpu); + + return rc; +} + static int kvmppc_xive_native_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { @@ -114,10 +242,32 @@ static int xive_native_debug_show(struct seq_file *m, void *private) { struct kvmppc_xive *xive = m->private; struct kvm *kvm = xive->kvm; + struct kvm_vcpu *vcpu; + unsigned int i; if (!kvm) return 0; + seq_puts(m, "=========\nVCPU state\n=========\n"); + + kvm_for_each_vcpu(i, vcpu, kvm) { + struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; + + if (!xc) + continue; + + seq_printf(m, "cpu server %#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n", + xc->server_num, + vcpu->arch.xive_saved_state.nsr, + vcpu->arch.xive_saved_state.cppr, + vcpu->arch.xive_saved_state.ipb, + vcpu->arch.xive_saved_state.pipr, + vcpu->arch.xive_saved_state.w01, + (u32) vcpu->arch.xive_cam_word); + + kvmppc_xive_debug_show_queues(m, vcpu); + } + return 0; } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 8885377ec3e0..b0858ee61460 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -570,6 +570,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PPC_GET_CPU_CHAR: r = 1; break; +#ifdef CONFIG_KVM_XIVE + case KVM_CAP_PPC_IRQ_XIVE: + /* + * Return false until all the XIVE infrastructure is + * in place including support for migration. + */ + r = 0; + break; +#endif case KVM_CAP_PPC_ALLOC_HTAB: r = hv_enabled; @@ -753,6 +762,9 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) else kvmppc_xics_free_icp(vcpu); break; + case KVMPPC_IRQ_XIVE: + kvmppc_xive_native_cleanup_vcpu(vcpu); + break; } kvmppc_core_vcpu_free(vcpu); @@ -1941,6 +1953,30 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, break; } #endif /* CONFIG_KVM_XICS */ +#ifdef CONFIG_KVM_XIVE + case KVM_CAP_PPC_IRQ_XIVE: { + struct fd f; + struct kvm_device *dev; + + r = -EBADF; + f = fdget(cap->args[0]); + if (!f.file) + break; + + r = -ENXIO; + if (!xive_enabled()) + break; + + r = -EPERM; + dev = kvm_device_from_filp(f.file); + if (dev) + r = kvmppc_xive_native_connect_vcpu(dev, vcpu, + cap->args[1]); + + fdput(f); + break; + } +#endif /* CONFIG_KVM_XIVE */ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE case KVM_CAP_PPC_FWNMI: r = -EINVAL; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e6368163d3a0..52bf74a1616e 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -988,6 +988,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_VM_IPA_SIZE 165 #define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 #define KVM_CAP_HYPERV_CPUID 167 +#define KVM_CAP_PPC_IRQ_XIVE 168 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From a1cd3f0883f435e5f9ae6530d7e62b361c87a91a Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Thu, 18 Apr 2019 12:39:36 +0200 Subject: KVM: Introduce a 'mmap' method for KVM devices Some KVM devices will want to handle special mappings related to the underlying HW. For instance, the XIVE interrupt controller of the POWER9 processor has MMIO pages for thread interrupt management and for interrupt source control that need to be exposed to the guest when the OS has the required support. Cc: Paolo Bonzini Signed-off-by: Cédric Le Goater Reviewed-by: David Gibson Signed-off-by: Paul Mackerras --- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 11 +++++++++++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9d55c63db09b..831d963451d8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1245,6 +1245,7 @@ struct kvm_device_ops { int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); long (*ioctl)(struct kvm_device *dev, unsigned int ioctl, unsigned long arg); + int (*mmap)(struct kvm_device *dev, struct vm_area_struct *vma); }; void kvm_device_get(struct kvm_device *dev); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 55fe8e20d8fd..ea2018ae1cd7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2884,6 +2884,16 @@ out: } #endif +static int kvm_device_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct kvm_device *dev = filp->private_data; + + if (dev->ops->mmap) + return dev->ops->mmap(dev, vma); + + return -ENODEV; +} + static int kvm_device_ioctl_attr(struct kvm_device *dev, int (*accessor)(struct kvm_device *dev, struct kvm_device_attr *attr), @@ -2936,6 +2946,7 @@ static const struct file_operations kvm_device_fops = { .unlocked_ioctl = kvm_device_ioctl, .release = kvm_device_release, KVM_COMPAT(kvm_device_ioctl), + .mmap = kvm_device_mmap, }; struct kvm_device *kvm_device_from_filp(struct file *filp) -- cgit v1.2.3 From 2bde9b3ec8bdf60788e9e2ce8c07a2f8d6003dbd Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Thu, 18 Apr 2019 12:39:41 +0200 Subject: KVM: Introduce a 'release' method for KVM devices When a P9 sPAPR VM boots, the CAS negotiation process determines which interrupt mode to use (XICS legacy or XIVE native) and invokes a machine reset to activate the chosen mode. To be able to switch from one interrupt mode to another, we introduce the capability to release a KVM device without destroying the VM. The KVM device interface is extended with a new 'release' method which is called when the file descriptor of the device is closed. Once 'release' is called, the 'destroy' method will not be called anymore as the device is removed from the device list of the VM. Cc: Paolo Bonzini Signed-off-by: Cédric Le Goater Reviewed-by: David Gibson Signed-off-by: Paul Mackerras --- include/linux/kvm_host.h | 9 +++++++++ virt/kvm/kvm_main.c | 13 +++++++++++++ 2 files changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 831d963451d8..722692e2f745 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1240,6 +1240,15 @@ struct kvm_device_ops { */ void (*destroy)(struct kvm_device *dev); + /* + * Release is an alternative method to free the device. It is + * called when the device file descriptor is closed. Once + * release is called, the destroy method will not be called + * anymore as the device is removed from the device list of + * the VM. kvm->lock is held. + */ + void (*release)(struct kvm_device *dev); + int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index ea2018ae1cd7..ea2619d5ca98 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2938,6 +2938,19 @@ static int kvm_device_release(struct inode *inode, struct file *filp) struct kvm_device *dev = filp->private_data; struct kvm *kvm = dev->kvm; + if (!dev) + return -ENODEV; + + if (dev->kvm != kvm) + return -EPERM; + + if (dev->ops->release) { + mutex_lock(&kvm->lock); + list_del(&dev->vm_node); + dev->ops->release(dev); + mutex_unlock(&kvm->lock); + } + kvm_put_kvm(kvm); return 0; } -- cgit v1.2.3 From 8479e04e7d6b1974629a0f657afa8ec5f17d2e90 Mon Sep 17 00:00:00 2001 From: Luwei Kang Date: Mon, 18 Feb 2019 19:26:07 -0500 Subject: KVM: x86: Inject PMI for KVM guest Inject a PMI for KVM guest when Intel PT working in Host-Guest mode and Guest ToPA entry memory buffer was completely filled. Signed-off-by: Luwei Kang Signed-off-by: Paolo Bonzini --- arch/x86/events/intel/core.c | 6 +++++- arch/x86/include/asm/msr-index.h | 4 ++++ arch/x86/kvm/x86.c | 10 ++++++++++ include/linux/perf_event.h | 1 + 4 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 8baa441d8000..386151b2c62f 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2307,7 +2307,11 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) */ if (__test_and_clear_bit(55, (unsigned long *)&status)) { handled++; - intel_pt_interrupt(); + if (unlikely(perf_guest_cbs && perf_guest_cbs->is_in_guest() && + perf_guest_cbs->handle_intel_pt_intr)) + perf_guest_cbs->handle_intel_pt_intr(); + else + intel_pt_interrupt(); } /* diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ca5bc0eacb95..be40c094bc49 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -781,6 +781,10 @@ #define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f #define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390 +/* PERF_GLOBAL_OVF_CTL bits */ +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT 55 +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI (1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT) + /* Geode defined MSRs */ #define MSR_GEODE_BUSCONT_CONF0 0x00001900 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6c27d224f744..cedd396e3003 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6839,10 +6839,20 @@ static unsigned long kvm_get_guest_ip(void) return ip; } +static void kvm_handle_intel_pt_intr(void) +{ + struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu); + + kvm_make_request(KVM_REQ_PMI, vcpu); + __set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT, + (unsigned long *)&vcpu->arch.pmu.global_status); +} + static struct perf_guest_info_callbacks kvm_guest_cbs = { .is_in_guest = kvm_is_in_guest, .is_user_mode = kvm_is_user_mode, .get_guest_ip = kvm_get_guest_ip, + .handle_intel_pt_intr = kvm_handle_intel_pt_intr, }; static void kvm_set_mmio_spte_mask(void) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e47ef764f613..820c4ff31bc5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -30,6 +30,7 @@ struct perf_guest_info_callbacks { int (*is_in_guest)(void); int (*is_user_mode)(void); unsigned long (*get_guest_ip)(void); + void (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT -- cgit v1.2.3 From e45adf665a53df0db37f784ed87c6b57ddd81885 Mon Sep 17 00:00:00 2001 From: KarimAllah Ahmed Date: Thu, 31 Jan 2019 21:24:34 +0100 Subject: KVM: Introduce a new guest mapping API In KVM, specially for nested guests, there is a dominant pattern of: => map guest memory -> do_something -> unmap guest memory In addition to all this unnecessarily noise in the code due to boiler plate code, most of the time the mapping function does not properly handle memory that is not backed by "struct page". This new guest mapping API encapsulate most of this boiler plate code and also handles guest memory that is not backed by "struct page". The current implementation of this API is using memremap for memory that is not backed by a "struct page" which would lead to a huge slow-down if it was used for high-frequency mapping operations. The API does not have any effect on current setups where guest memory is backed by a "struct page". Further patches are going to also introduce a pfn-cache which would significantly improve the performance of the memremap case. Signed-off-by: KarimAllah Ahmed Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 28 +++++++++++++++++++++ virt/kvm/kvm_main.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 92 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 43f87ad83ff4..6f665c16e31d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -227,6 +227,32 @@ enum { READING_SHADOW_PAGE_TABLES, }; +#define KVM_UNMAPPED_PAGE ((void *) 0x500 + POISON_POINTER_DELTA) + +struct kvm_host_map { + /* + * Only valid if the 'pfn' is managed by the host kernel (i.e. There is + * a 'struct page' for it. When using mem= kernel parameter some memory + * can be used as guest memory but they are not managed by host + * kernel). + * If 'pfn' is not managed by the host kernel, this field is + * initialized to KVM_UNMAPPED_PAGE. + */ + struct page *page; + void *hva; + kvm_pfn_t pfn; + kvm_pfn_t gfn; +}; + +/* + * Used to check if the mapping is valid or not. Never use 'kvm_host_map' + * directly to check for that. + */ +static inline bool kvm_vcpu_mapped(struct kvm_host_map *map) +{ + return !!map->hva; +} + /* * Sometimes a large or cross-page mmio needs to be broken up into separate * exits for userspace servicing. @@ -733,7 +759,9 @@ struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); +int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); +void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3194aa3d0b43..53de2f946f9e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1742,6 +1742,70 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_page); +static int __kvm_map_gfn(struct kvm_memory_slot *slot, gfn_t gfn, + struct kvm_host_map *map) +{ + kvm_pfn_t pfn; + void *hva = NULL; + struct page *page = KVM_UNMAPPED_PAGE; + + if (!map) + return -EINVAL; + + pfn = gfn_to_pfn_memslot(slot, gfn); + if (is_error_noslot_pfn(pfn)) + return -EINVAL; + + if (pfn_valid(pfn)) { + page = pfn_to_page(pfn); + hva = kmap(page); + } else { + hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); + } + + if (!hva) + return -EFAULT; + + map->page = page; + map->hva = hva; + map->pfn = pfn; + map->gfn = gfn; + + return 0; +} + +int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map) +{ + return __kvm_map_gfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, map); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_map); + +void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, + bool dirty) +{ + if (!map) + return; + + if (!map->hva) + return; + + if (map->page) + kunmap(map->page); + else + memunmap(map->hva); + + if (dirty) { + kvm_vcpu_mark_page_dirty(vcpu, map->gfn); + kvm_release_pfn_dirty(map->pfn); + } else { + kvm_release_pfn_clean(map->pfn); + } + + map->hva = NULL; + map->page = NULL; +} +EXPORT_SYMBOL_GPL(kvm_vcpu_unmap); + struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn) { kvm_pfn_t pfn; -- cgit v1.2.3 From d7547c55cbe7471255ca51f14bcd4699f5eaabe5 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 8 May 2019 17:15:47 +0800 Subject: KVM: Introduce KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 The previous KVM_CAP_MANUAL_DIRTY_LOG_PROTECT has some problem which blocks the correct usage from userspace. Obsolete the old one and introduce a new capability bit for it. Suggested-by: Paolo Bonzini Signed-off-by: Peter Xu Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 15 ++++++++++----- include/uapi/linux/kvm.h | 5 +++-- tools/testing/selftests/kvm/dirty_log_test.c | 4 ++-- virt/kvm/kvm_main.c | 4 ++-- 4 files changed, 17 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 675cb0bea903..47a5eb00bc53 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -330,7 +330,7 @@ They must be less than the value that KVM_CHECK_EXTENSION returns for the KVM_CAP_MULTI_ADDRESS_SPACE capability. The bits in the dirty bitmap are cleared before the ioctl returns, unless -KVM_CAP_MANUAL_DIRTY_LOG_PROTECT is enabled. For more information, +KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled. For more information, see the description of the capability. 4.9 KVM_SET_MEMORY_ALIAS @@ -3791,7 +3791,7 @@ to I/O ports. 4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl) -Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT +Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 Architectures: x86 Type: vm ioctl Parameters: struct kvm_dirty_log (in) @@ -3824,10 +3824,10 @@ the address space for which you want to return the dirty bitmap. They must be less than the value that KVM_CHECK_EXTENSION returns for the KVM_CAP_MULTI_ADDRESS_SPACE capability. -This ioctl is mostly useful when KVM_CAP_MANUAL_DIRTY_LOG_PROTECT +This ioctl is mostly useful when KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled; for more information, see the description of the capability. However, it can always be used as long as KVM_CHECK_EXTENSION confirms -that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT is present. +that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present. 4.118 KVM_GET_SUPPORTED_HV_CPUID @@ -4780,7 +4780,7 @@ and injected exceptions. * For the new DR6 bits, note that bit 16 is set iff the #DB exception will clear DR6.RTM. -7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT +7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 Architectures: all Parameters: args[0] whether feature should be enabled or not @@ -4803,6 +4803,11 @@ while userspace can see false reports of dirty pages. Manual reprotection helps reducing this time, improving guest performance and reducing the number of dirty log false positives. +KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 was previously available under the name +KVM_CAP_MANUAL_DIRTY_LOG_PROTECT, but the implementation had bugs that make +it hard or impossible to use it correctly. The availability of +KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 signals that those bugs are fixed. +Userspace should not try to use KVM_CAP_MANUAL_DIRTY_LOG_PROTECT. 8. Other capabilities. ---------------------- diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 6d4ea4b6c922..d673734c46cb 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -986,8 +986,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163 #define KVM_CAP_EXCEPTION_PAYLOAD 164 #define KVM_CAP_ARM_VM_IPA_SIZE 165 -#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 +#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 /* Obsolete */ #define KVM_CAP_HYPERV_CPUID 167 +#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 168 #ifdef KVM_CAP_IRQ_ROUTING @@ -1434,7 +1435,7 @@ struct kvm_enc_region { #define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state) #define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state) -/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT */ +/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */ #define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log) /* Available with KVM_CAP_HYPERV_CPUID */ diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 052fb5856df4..a29d1119ccb3 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -311,7 +311,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, #ifdef USE_CLEAR_DIRTY_LOG struct kvm_enable_cap cap = {}; - cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT; + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; cap.args[0] = 1; vm_enable_cap(vm, &cap); #endif @@ -427,7 +427,7 @@ int main(int argc, char *argv[]) int opt, i; #ifdef USE_CLEAR_DIRTY_LOG - if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT)) { + if (!kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2)) { fprintf(stderr, "KVM_CLEAR_DIRTY_LOG not available, skipping tests\n"); exit(KSFT_SKIP); } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 7883e0ad07fe..f4e02cd8fa43 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3110,7 +3110,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_CHECK_EXTENSION_VM: case KVM_CAP_ENABLE_CAP_VM: #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT - case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT: + case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: #endif return 1; #ifdef CONFIG_KVM_MMIO @@ -3148,7 +3148,7 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, { switch (cap->cap) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT - case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT: + case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: if (cap->flags || (cap->args[0] & ~1)) return -EINVAL; kvm->manual_dirty_log_protect = cap->args[0]; -- cgit v1.2.3