diff options
| author |   Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-03 15:13:47 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-03 15:13:47 -0700 |
| commit | 039aeb9deb9291f3b19c375a8bc6fa7f768996cc (patch) | |
| tree | d98d5ddf276843995aa214157b587bb88270c530 /arch | |
| parent | Merge tag 'hyperv-next-signed' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux (diff) | |
| parent | KVM: selftests: fix rdtsc() for vmx_tsc_adjust_test (diff) | |
| download | linux-dev-039aeb9deb9291f3b19c375a8bc6fa7f768996cc.tar.xz linux-dev-039aeb9deb9291f3b19c375a8bc6fa7f768996cc.zip | |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"ARM:
- Move the arch-specific code into arch/arm64/kvm
- Start the post-32bit cleanup
- Cherry-pick a few non-invasive pre-NV patches
x86:
- Rework of TLB flushing
- Rework of event injection, especially with respect to nested
virtualization
- Nested AMD event injection facelift, building on the rework of
generic code and fixing a lot of corner cases
- Nested AMD live migration support
- Optimization for TSC deadline MSR writes and IPIs
- Various cleanups
- Asynchronous page fault cleanups (from tglx, common topic branch
with tip tree)
- Interrupt-based delivery of asynchronous "page ready" events (host
side)
- Hyper-V MSRs and hypercalls for guest debugging
- VMX preemption timer fixes
s390:
- Cleanups
Generic:
- switch vCPU thread wakeup from swait to rcuwait
The other architectures, and the guest side of the asynchronous page
fault work, will come next week"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (256 commits)
KVM: selftests: fix rdtsc() for vmx_tsc_adjust_test
KVM: check userspace_addr for all memslots
KVM: selftests: update hyperv_cpuid with SynDBG tests
x86/kvm/hyper-v: Add support for synthetic debugger via hypercalls
x86/kvm/hyper-v: enable hypercalls regardless of hypercall page
x86/kvm/hyper-v: Add support for synthetic debugger interface
x86/hyper-v: Add synthetic debugger definitions
KVM: selftests: VMX preemption timer migration test
KVM: nVMX: Fix VMX preemption timer migration
x86/kvm/hyper-v: Explicitly align hcall param for kvm_hyperv_exit
KVM: x86/pmu: Support full width counting
KVM: x86/pmu: Tweak kvm_pmu_get_msr to pass 'struct msr_data' in
KVM: x86: announce KVM_FEATURE_ASYNC_PF_INT
KVM: x86: acknowledgment mechanism for async pf page ready notifications
KVM: x86: interrupt based APF 'page ready' event delivery
KVM: introduce kvm_read_guest_offset_cached()
KVM: rename kvm_arch_can_inject_async_page_present() to kvm_arch_can_dequeue_async_page_present()
KVM: x86: extend struct kvm_vcpu_pv_apf_data with token info
Revert "KVM: async_pf: Fix #DF due to inject "Page not Present" and "Page Ready" exceptions simultaneously"
KVM: VMX: Replace zero-length array with flexible-array
...
Diffstat (limited to 'arch')
115 files changed, 23253 insertions, 2456 deletions
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 7c7eeeaab9fa..0c9b5fc4ba0a 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -64,12 +64,14 @@ extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); extern void __kvm_tlb_flush_vmid(struct kvm *kvm); extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu); -extern void __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high); +extern void __kvm_timer_set_cntvoff(u64 cntvoff); extern int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu); extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu); +extern void __kvm_enable_ssbs(void); + extern u64 __vgic_v3_get_ich_vtr_el2(void); extern u64 __vgic_v3_read_vmcr(void); extern void __vgic_v3_write_vmcr(u32 vmcr); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 57c0afcf9dcf..abbdf9703e20 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -46,6 +46,9 @@ #define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) #define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4) +#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ + KVM_DIRTY_LOG_INITIALLY_SET) + DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); extern unsigned int kvm_sve_max_vl; @@ -112,12 +115,8 @@ struct kvm_vcpu_fault_info { u64 disr_el1; /* Deferred [SError] Status Register */ }; -/* - * 0 is reserved as an invalid value. - * Order should be kept in sync with the save/restore code. - */ enum vcpu_sysreg { - __INVALID_SYSREG__, + __INVALID_SYSREG__, /* 0 is reserved as an invalid value */ MPIDR_EL1, /* MultiProcessor Affinity Register */ CSSELR_EL1, /* Cache Size Selection Register */ SCTLR_EL1, /* System Control Register */ @@ -415,6 +414,8 @@ struct kvm_vm_stat { struct kvm_vcpu_stat { u64 halt_successful_poll; u64 halt_attempted_poll; + u64 halt_poll_success_ns; + u64 halt_poll_fail_ns; u64 halt_poll_invalid; u64 halt_wakeup; u64 hvc_exit_stat; @@ -530,39 +531,6 @@ static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) cpu_ctxt->sys_regs[MPIDR_EL1] = read_cpuid_mpidr(); } -void __kvm_enable_ssbs(void); - -static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, - unsigned long hyp_stack_ptr, - unsigned long vector_ptr) -{ - /* - * Calculate the raw per-cpu offset without a translation from the - * kernel's mapping to the linear mapping, and store it in tpidr_el2 - * so that we can use adr_l to access per-cpu variables in EL2. - */ - u64 tpidr_el2 = ((u64)this_cpu_ptr(&kvm_host_data) - - (u64)kvm_ksym_ref(kvm_host_data)); - - /* - * Call initialization code, and switch to the full blown HYP code. - * If the cpucaps haven't been finalized yet, something has gone very - * wrong, and hyp will crash and burn when it uses any - * cpus_have_const_cap() wrapper. - */ - BUG_ON(!system_capabilities_finalized()); - __kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2); - - /* - * Disabling SSBD on a non-VHE system requires us to enable SSBS - * at EL2. - */ - if (!has_vhe() && this_cpu_has_cap(ARM64_SSBS) && - arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) { - kvm_call_hyp(__kvm_enable_ssbs); - } -} - static inline bool kvm_arch_requires_vhe(void) { /* @@ -594,8 +562,6 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); -static inline void __cpu_init_stage2(void) {} - /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 015883671ec3..ce3080834bfa 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -55,12 +55,12 @@ int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu); -void __vgic_v3_save_state(struct kvm_vcpu *vcpu); -void __vgic_v3_restore_state(struct kvm_vcpu *vcpu); -void __vgic_v3_activate_traps(struct kvm_vcpu *vcpu); -void __vgic_v3_deactivate_traps(struct kvm_vcpu *vcpu); -void __vgic_v3_save_aprs(struct kvm_vcpu *vcpu); -void __vgic_v3_restore_aprs(struct kvm_vcpu *vcpu); +void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if); +void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if); +void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if); +void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if); +void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if); +void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if); int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu); void __timer_enable_traps(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 85da6befe76e..324c8483d2b9 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -363,8 +363,6 @@ static inline void __kvm_flush_dcache_pud(pud_t pud) } } -#define kvm_virt_to_phys(x) __pa_symbol(x) - void kvm_set_way_flush(struct kvm_vcpu *vcpu); void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled); @@ -473,7 +471,7 @@ static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, extern void *__kvm_bp_vect_base; extern int __kvm_harden_el2_vector_slot; -/* This is only called on a VHE system */ +/* This is called on both VHE and !VHE systems */ static inline void *kvm_get_hyp_vector(void) { struct bp_hardening_data *data = arm64_get_bp_hardening_data(); diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 2172ec7594ba..953b6a1ce549 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -35,7 +35,7 @@ #define GIC_PRIO_PSR_I_SET (1 << 4) /* Additional SPSR bits not exposed in the UABI */ - +#define PSR_MODE_THREAD_BIT (1 << 0) #define PSR_IL_BIT (1 << 20) /* AArch32-specific ptrace requests */ diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 61fd26752adc..5051b388c654 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -85,7 +85,7 @@ static inline bool is_kernel_in_hyp_mode(void) static __always_inline bool has_vhe(void) { - if (cpus_have_const_cap(ARM64_HAS_VIRT_HOST_EXTN)) + if (cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN)) return true; return false; diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 3539d7092612..0577e2142284 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -97,7 +97,7 @@ int main(void) DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack)); DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task)); BLANK(); -#ifdef CONFIG_KVM_ARM_HOST +#ifdef CONFIG_KVM DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt)); DEFINE(VCPU_FAULT_DISR, offsetof(struct kvm_vcpu, arch.fault.disr_el1)); DEFINE(VCPU_WORKAROUND_FLAGS, offsetof(struct kvm_vcpu, arch.workaround_flags)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index b0ce6bf14f6a..ad06d6802d2e 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -234,7 +234,7 @@ static int detect_harden_bp_fw(void) smccc_end = NULL; break; -#if IS_ENABLED(CONFIG_KVM_ARM_HOST) +#if IS_ENABLED(CONFIG_KVM) case SMCCC_CONDUIT_SMC: cb = call_smc_arch_workaround_1; smccc_start = __smccc_workaround_1_smc; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 04b1ca0d7aba..4b6f4999d06a 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -422,7 +422,7 @@ static void __init hyp_mode_check(void) "CPU: CPUs started in inconsistent modes"); else pr_info("CPU: All CPU(s) started at EL1\n"); - if (IS_ENABLED(CONFIG_KVM_ARM_HOST)) + if (IS_ENABLED(CONFIG_KVM)) kvm_compute_layout(); } diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 449386d76441..f1c1f981482c 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -3,7 +3,6 @@ # KVM configuration # -source "virt/kvm/Kconfig" source "virt/lib/Kconfig" menuconfig VIRTUALIZATION @@ -18,7 +17,7 @@ menuconfig VIRTUALIZATION if VIRTUALIZATION -config KVM +menuconfig KVM bool "Kernel-based Virtual Machine (KVM) support" depends on OF # for TASKSTATS/TASK_DELAY_ACCT: @@ -28,13 +27,11 @@ config KVM select HAVE_KVM_CPU_RELAX_INTERCEPT select HAVE_KVM_ARCH_TLB_FLUSH_ALL select KVM_MMIO - select KVM_ARM_HOST select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU select KVM_VFIO select HAVE_KVM_EVENTFD select HAVE_KVM_IRQFD - select KVM_ARM_PMU if HW_PERF_EVENTS select HAVE_KVM_MSI select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQ_ROUTING @@ -45,23 +42,24 @@ config KVM select TASK_DELAY_ACCT ---help--- Support hosting virtualized guest machines. - We don't support KVM with 16K page tables yet, due to the multiple - levels of fake page tables. If unsure, say N. -config KVM_ARM_HOST - bool - ---help--- - Provides host support for ARM processors. +if KVM + +source "virt/kvm/Kconfig" config KVM_ARM_PMU - bool + bool "Virtual Performance Monitoring Unit (PMU) support" + depends on HW_PERF_EVENTS + default y ---help--- Adds support for a virtual Performance Monitoring Unit (PMU) in virtual machines. config KVM_INDIRECT_VECTORS - def_bool KVM && (HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS) + def_bool HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS + +endif # KVM endif # VIRTUALIZATION diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 5ffbdc39e780..8d3d9513cbfe 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -3,37 +3,25 @@ # Makefile for Kernel-based Virtual Machine module # -ccflags-y += -I $(srctree)/$(src) -I $(srctree)/virt/kvm/arm/vgic +ccflags-y += -I $(srctree)/$(src) KVM=../../../virt/kvm -obj-$(CONFIG_KVM_ARM_HOST) += kvm.o -obj-$(CONFIG_KVM_ARM_HOST) += hyp/ +obj-$(CONFIG_KVM) += kvm.o +obj-$(CONFIG_KVM) += hyp/ -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hypercalls.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/pvtime.o +kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ + $(KVM)/vfio.o $(KVM)/irqchip.o \ + arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ + inject_fault.o regmap.o va_layout.o hyp.o hyp-init.o handle_exit.o \ + guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o \ + vgic-sys-reg-v3.o fpsimd.o pmu.o \ + aarch32.o arch_timer.o \ + vgic/vgic.o vgic/vgic-init.o \ + vgic/vgic-irqfd.o vgic/vgic-v2.o \ + vgic/vgic-v3.o vgic/vgic-v4.o \ + vgic/vgic-mmio.o vgic/vgic-mmio-v2.o \ + vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \ + vgic/vgic-its.o vgic/vgic-debug.o -kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o va_layout.o -kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o -kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o -kvm-$(CONFIG_KVM_ARM_HOST) += vgic-sys-reg-v3.o fpsimd.o pmu.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/aarch32.o - -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-init.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-irqfd.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v2.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v3.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-v4.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v2.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v3.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-kvm-device.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-its.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-debug.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/irqchip.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o -kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o +kvm-$(CONFIG_KVM_ARM_PMU) += pmu-emul.o diff --git a/arch/arm64/kvm/aarch32.c b/arch/arm64/kvm/aarch32.c new file mode 100644 index 000000000000..0a356aa91aa1 --- /dev/null +++ b/arch/arm64/kvm/aarch32.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * (not much of an) Emulation layer for 32bit guests. + * + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * based on arch/arm/kvm/emulate.c + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + */ + +#include <linux/bits.h> +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> + +#define DFSR_FSC_EXTABT_LPAE 0x10 +#define DFSR_FSC_EXTABT_nLPAE 0x08 +#define DFSR_LPAE BIT(9) + +/* + * Table taken from ARMv8 ARM DDI0487B-B, table G1-10. + */ +static const u8 return_offsets[8][2] = { + [0] = { 0, 0 }, /* Reset, unused */ + [1] = { 4, 2 }, /* Undefined */ + [2] = { 0, 0 }, /* SVC, unused */ + [3] = { 4, 4 }, /* Prefetch abort */ + [4] = { 8, 8 }, /* Data abort */ + [5] = { 0, 0 }, /* HVC, unused */ + [6] = { 4, 4 }, /* IRQ, unused */ + [7] = { 4, 4 }, /* FIQ, unused */ +}; + +/* + * When an exception is taken, most CPSR fields are left unchanged in the + * handler. However, some are explicitly overridden (e.g. M[4:0]). + * + * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with + * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was + * obsoleted by the ARMv7 virtualization extensions and is RES0. + * + * For the SPSR layout seen from AArch32, see: + * - ARM DDI 0406C.d, page B1-1148 + * - ARM DDI 0487E.a, page G8-6264 + * + * For the SPSR_ELx layout for AArch32 seen from AArch64, see: + * - ARM DDI 0487E.a, page C5-426 + * + * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from + * MSB to LSB. + */ +static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode) +{ + u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR); + unsigned long old, new; + + old = *vcpu_cpsr(vcpu); + new = 0; + + new |= (old & PSR_AA32_N_BIT); + new |= (old & PSR_AA32_Z_BIT); + new |= (old & PSR_AA32_C_BIT); + new |= (old & PSR_AA32_V_BIT); + new |= (old & PSR_AA32_Q_BIT); + + // CPSR.IT[7:0] are set to zero upon any exception + // See ARM DDI 0487E.a, section G1.12.3 + // See ARM DDI 0406C.d, section B1.8.3 + + new |= (old & PSR_AA32_DIT_BIT); + + // CPSR.SSBS is set to SCTLR.DSSBS upon any exception + // See ARM DDI 0487E.a, page G8-6244 + if (sctlr & BIT(31)) + new |= PSR_AA32_SSBS_BIT; + + // CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0 + // SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented + // See ARM DDI 0487E.a, page G8-6246 + new |= (old & PSR_AA32_PAN_BIT); + if (!(sctlr & BIT(23))) + new |= PSR_AA32_PAN_BIT; + + // SS does not exist in AArch32, so ignore + + // CPSR.IL is set to zero upon any exception + // See ARM DDI 0487E.a, page G1-5527 + + new |= (old & PSR_AA32_GE_MASK); + + // CPSR.IT[7:0] are set to zero upon any exception + // See prior comment above + + // CPSR.E is set to SCTLR.EE upon any exception + // See ARM DDI 0487E.a, page G8-6245 + // See ARM DDI 0406C.d, page B4-1701 + if (sctlr & BIT(25)) + new |= PSR_AA32_E_BIT; + + // CPSR.A is unchanged upon an exception to Undefined, Supervisor + // CPSR.A is set upon an exception to other modes + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= (old & PSR_AA32_A_BIT); + if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC) + new |= PSR_AA32_A_BIT; + + // CPSR.I is set upon any exception + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= PSR_AA32_I_BIT; + + // CPSR.F is set upon an exception to FIQ + // CPSR.F is unchanged upon an exception to other modes + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= (old & PSR_AA32_F_BIT); + if (mode == PSR_AA32_MODE_FIQ) + new |= PSR_AA32_F_BIT; + + // CPSR.T is set to SCTLR.TE upon any exception + // See ARM DDI 0487E.a, page G8-5514 + // See ARM DDI 0406C.d, page B1-1181 + if (sctlr & BIT(30)) + new |= PSR_AA32_T_BIT; + + new |= mode; + + return new; +} + +static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) +{ + unsigned long spsr = *vcpu_cpsr(vcpu); + bool is_thumb = (spsr & PSR_AA32_T_BIT); + u32 return_offset = return_offsets[vect_offset >> 2][is_thumb]; + u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR); + + *vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode); + + /* Note: These now point to the banked copies */ + vcpu_write_spsr(vcpu, host_spsr_to_spsr32(spsr)); + *vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; + + /* Branch to exception vector */ + if (sctlr & (1 << 13)) + vect_offset += 0xffff0000; + else /* always have security exceptions */ + vect_offset += vcpu_cp15(vcpu, c12_VBAR); + + *vcpu_pc(vcpu) = vect_offset; +} + +void kvm_inject_undef32(struct kvm_vcpu *vcpu) +{ + prepare_fault32(vcpu, PSR_AA32_MODE_UND, 4); +} + +/* + * Modelled after TakeDataAbortException() and TakePrefetchAbortException + * pseudocode. + */ +static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, + unsigned long addr) +{ + u32 vect_offset; + u32 *far, *fsr; + bool is_lpae; + + if (is_pabt) { + vect_offset = 12; + far = &vcpu_cp15(vcpu, c6_IFAR); + fsr = &vcpu_cp15(vcpu, c5_IFSR); + } else { /* !iabt */ + vect_offset = 16; + far = &vcpu_cp15(vcpu, c6_DFAR); + fsr = &vcpu_cp15(vcpu, c5_DFSR); + } + + prepare_fault32(vcpu, PSR_AA32_MODE_ABT, vect_offset); + + *far = addr; + + /* Give the guest an IMPLEMENTATION DEFINED exception */ + is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31); + if (is_lpae) { + *fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE; + } else { + /* no need to shuffle FS[4] into DFSR[10] as its 0 */ + *fsr = DFSR_FSC_EXTABT_nLPAE; + } +} + +void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr) +{ + inject_abt32(vcpu, false, addr); +} + +void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr) +{ + inject_abt32(vcpu, true, addr); +} diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c new file mode 100644 index 000000000000..a1fe0ea3254e --- /dev/null +++ b/arch/arm64/kvm/arch_timer.c @@ -0,0 +1,1171 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 ARM Ltd. + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <linux/cpu.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/uaccess.h> + +#include <clocksource/arm_arch_timer.h> +#include <asm/arch_timer.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> + +#include <kvm/arm_vgic.h> +#include <kvm/arm_arch_timer.h> + +#include "trace.h" + +static struct timecounter *timecounter; +static unsigned int host_vtimer_irq; +static unsigned int host_ptimer_irq; +static u32 host_vtimer_irq_flags; +static u32 host_ptimer_irq_flags; + +static DEFINE_STATIC_KEY_FALSE(has_gic_active_state); + +static const struct kvm_irq_level default_ptimer_irq = { + .irq = 30, + .level = 1, +}; + +static const struct kvm_irq_level default_vtimer_irq = { + .irq = 27, + .level = 1, +}; + +static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx); +static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, + struct arch_timer_context *timer_ctx); +static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx); +static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, + struct arch_timer_context *timer, + enum kvm_arch_timer_regs treg, + u64 val); +static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, + struct arch_timer_context *timer, + enum kvm_arch_timer_regs treg); + +u64 kvm_phys_timer_read(void) +{ + return timecounter->cc->read(timecounter->cc); +} + +static void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map) +{ + if (has_vhe()) { + map->direct_vtimer = vcpu_vtimer(vcpu); + map->direct_ptimer = vcpu_ptimer(vcpu); + map->emul_ptimer = NULL; + } else { + map->direct_vtimer = vcpu_vtimer(vcpu); + map->direct_ptimer = NULL; + map->emul_ptimer = vcpu_ptimer(vcpu); + } + + trace_kvm_get_timer_map(vcpu->vcpu_id, map); +} + +static inline bool userspace_irqchip(struct kvm *kvm) +{ + return static_branch_unlikely(&userspace_irqchip_in_use) && + unlikely(!irqchip_in_kernel(kvm)); +} + +static void soft_timer_start(struct hrtimer *hrt, u64 ns) +{ + hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns), + HRTIMER_MODE_ABS_HARD); +} + +static void soft_timer_cancel(struct hrtimer *hrt) +{ + hrtimer_cancel(hrt); +} + +static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) +{ + struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; + struct arch_timer_context *ctx; + struct timer_map map; + + /* + * We may see a timer interrupt after vcpu_put() has been called which + * sets the CPU's vcpu pointer to NULL, because even though the timer + * has been disabled in timer_save_state(), the hardware interrupt + * signal may not have been retired from the interrupt controller yet. + */ + if (!vcpu) + return IRQ_HANDLED; + + get_timer_map(vcpu, &map); + + if (irq == host_vtimer_irq) + ctx = map.direct_vtimer; + else + ctx = map.direct_ptimer; + + if (kvm_timer_should_fire(ctx)) + kvm_timer_update_irq(vcpu, true, ctx); + + if (userspace_irqchip(vcpu->kvm) && + !static_branch_unlikely(&has_gic_active_state)) + disable_percpu_irq(host_vtimer_irq); + + return IRQ_HANDLED; +} + +static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx) +{ + u64 cval, now; + + cval = timer_ctx->cnt_cval; + now = kvm_phys_timer_read() - timer_ctx->cntvoff; + + if (now < cval) { + u64 ns; + + ns = cyclecounter_cyc2ns(timecounter->cc, + cval - now, + timecounter->mask, + &timecounter->frac); + return ns; + } + + return 0; +} + +static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx) +{ + WARN_ON(timer_ctx && timer_ctx->loaded); + return timer_ctx && + !(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_IT_MASK) && + (timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_ENABLE); +} + +/* + * Returns the earliest expiration time in ns among guest timers. + * Note that it will return 0 if none of timers can fire. + */ +static u64 kvm_timer_earliest_exp(struct kvm_vcpu *vcpu) +{ + u64 min_delta = ULLONG_MAX; + int i; + + for (i = 0; i < NR_KVM_TIMERS; i++) { + struct arch_timer_context *ctx = &vcpu->arch.timer_cpu.timers[i]; + + WARN(ctx->loaded, "timer %d loaded\n", i); + if (kvm_timer_irq_can_fire(ctx)) + min_delta = min(min_delta, kvm_timer_compute_delta(ctx)); + } + + /* If none of timers can fire, then return 0 */ + if (min_delta == ULLONG_MAX) + return 0; + + return min_delta; +} + +static enum hrtimer_restart kvm_bg_timer_expire(struct hrtimer *hrt) +{ + struct arch_timer_cpu *timer; + struct kvm_vcpu *vcpu; + u64 ns; + + timer = container_of(hrt, struct arch_timer_cpu, bg_timer); + vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu); + + /* + * Check that the timer has really expired from the guest's + * PoV (NTP on the host may have forced it to expire + * early). If we should have slept longer, restart it. + */ + ns = kvm_timer_earliest_exp(vcpu); + if (unlikely(ns)) { + hrtimer_forward_now(hrt, ns_to_ktime(ns)); + return HRTIMER_RESTART; + } + + kvm_vcpu_wake_up(vcpu); + return HRTIMER_NORESTART; +} + +static enum hrtimer_restart kvm_hrtimer_expire(struct hrtimer *hrt) +{ + struct arch_timer_context *ctx; + struct kvm_vcpu *vcpu; + u64 ns; + + ctx = container_of(hrt, struct arch_timer_context, hrtimer); + vcpu = ctx->vcpu; + + trace_kvm_timer_hrtimer_expire(ctx); + + /* + * Check that the timer has really expired from the guest's + * PoV (NTP on the host may have forced it to expire + * early). If not ready, schedule for a later time. + */ + ns = kvm_timer_compute_delta(ctx); + if (unlikely(ns)) { + hrtimer_forward_now(hrt, ns_to_ktime(ns)); + return HRTIMER_RESTART; + } + + kvm_timer_update_irq(vcpu, true, ctx); + return HRTIMER_NORESTART; +} + +static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) +{ + enum kvm_arch_timers index; + u64 cval, now; + + if (!timer_ctx) + return false; + + index = arch_timer_ctx_index(timer_ctx); + + if (timer_ctx->loaded) { + u32 cnt_ctl = 0; + + switch (index) { + case TIMER_VTIMER: + cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL); + break; + case TIMER_PTIMER: + cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL); + break; + case NR_KVM_TIMERS: + /* GCC is braindead */ + cnt_ctl = 0; + break; + } + + return (cnt_ctl & ARCH_TIMER_CTRL_ENABLE) && + (cnt_ctl & ARCH_TIMER_CTRL_IT_STAT) && + !(cnt_ctl & ARCH_TIMER_CTRL_IT_MASK); + } + + if (!kvm_timer_irq_can_fire(timer_ctx)) + return false; + + cval = timer_ctx->cnt_cval; + now = kvm_phys_timer_read() - timer_ctx->cntvoff; + + return cval <= now; +} + +bool kvm_timer_is_pending(struct kvm_vcpu *vcpu) +{ + struct timer_map map; + + get_timer_map(vcpu, &map); + + return kvm_timer_should_fire(map.direct_vtimer) || + kvm_timer_should_fire(map.direct_ptimer) || + kvm_timer_should_fire(map.emul_ptimer); +} + +/* + * Reflect the timer output level into the kvm_run structure + */ +void kvm_timer_update_run(struct kvm_vcpu *vcpu) +{ + struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); + struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + struct kvm_sync_regs *regs = &vcpu->run->s.regs; + + /* Populate the device bitmap with the timer states */ + regs->device_irq_level &= ~(KVM_ARM_DEV_EL1_VTIMER | + KVM_ARM_DEV_EL1_PTIMER); + if (kvm_timer_should_fire(vtimer)) + regs->device_irq_level |= KVM_ARM_DEV_EL1_VTIMER; + if (kvm_timer_should_fire(ptimer)) + regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER; +} + +static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, + struct arch_timer_context *timer_ctx) +{ + int ret; + + timer_ctx->irq.level = new_level; + trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq, + timer_ctx->irq.level); + + if (!userspace_irqchip(vcpu->kvm)) { + ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, + timer_ctx->irq.irq, + timer_ctx->irq.level, + timer_ctx); + WARN_ON(ret); + } +} + +/* Only called for a fully emulated timer */ +static void timer_emulate(struct arch_timer_context *ctx) +{ + bool should_fire = kvm_timer_should_fire(ctx); + + trace_kvm_timer_emulate(ctx, should_fire); + + if (should_fire != ctx->irq.level) { + kvm_timer_update_irq(ctx->vcpu, should_fire, ctx); + return; + } + + /* + * If the timer can fire now, we don't need to have a soft timer + * scheduled for the future. If the timer cannot fire at all, + * then we also don't need a soft timer. + */ + if (!kvm_timer_irq_can_fire(ctx)) { + soft_timer_cancel(&ctx->hrtimer); + return; + } + + soft_timer_start(&ctx->hrtimer, kvm_timer_compute_delta(ctx)); +} + +static void timer_save_state(struct arch_timer_context *ctx) +{ + struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu); + enum kvm_arch_timers index = arch_timer_ctx_index(ctx); + unsigned long flags; + + if (!timer->enabled) + return; + + local_irq_save(flags); + + if (!ctx->loaded) + goto out; + + switch (index) { + case TIMER_VTIMER: + ctx->cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL); + ctx->cnt_cval = read_sysreg_el0(SYS_CNTV_CVAL); + + /* Disable the timer */ + write_sysreg_el0(0, SYS_CNTV_CTL); + isb(); + + break; + case TIMER_PTIMER: + ctx->cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL); + ctx->cnt_cval = read_sysreg_el0(SYS_CNTP_CVAL); + + /* Disable the timer */ + write_sysreg_el0(0, SYS_CNTP_CTL); + isb(); + + break; + case NR_KVM_TIMERS: + BUG(); + } + + trace_kvm_timer_save_state(ctx); + + ctx->loaded = false; +out: + local_irq_restore(flags); +} + +/* + * Schedule the background timer before calling kvm_vcpu_block, so that this + * thread is removed from its waitqueue and made runnable when there's a timer + * interrupt to handle. + */ +static void kvm_timer_blocking(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + struct timer_map map; + + get_timer_map(vcpu, &map); + + /* + * If no timers are capable of raising interrupts (disabled or + * masked), then there's no more work for us to do. + */ + if (!kvm_timer_irq_can_fire(map.direct_vtimer) && + !kvm_timer_irq_can_fire(map.direct_ptimer) && + !kvm_timer_irq_can_fire(map.emul_ptimer)) + return; + + /* + * At least one guest time will expire. Schedule a background timer. + * Set the earliest expiration time among the guest timers. + */ + soft_timer_start(&timer->bg_timer, kvm_timer_earliest_exp(vcpu)); +} + +static void kvm_timer_unblocking(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + + soft_timer_cancel(&timer->bg_timer); +} + +static void timer_restore_state(struct arch_timer_context *ctx) +{ + struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu); + enum kvm_arch_timers index = arch_timer_ctx_index(ctx); + unsigned long flags; + + if (!timer->enabled) + return; + + local_irq_save(flags); + + if (ctx->loaded) + goto out; + + switch (index) { + case TIMER_VTIMER: + write_sysreg_el0(ctx->cnt_cval, SYS_CNTV_CVAL); + isb(); + write_sysreg_el0(ctx->cnt_ctl, SYS_CNTV_CTL); + break; + case TIMER_PTIMER: + write_sysreg_el0(ctx->cnt_cval, SYS_CNTP_CVAL); + isb(); + write_sysreg_el0(ctx->cnt_ctl, SYS_CNTP_CTL); + break; + case NR_KVM_TIMERS: + BUG(); + } + + trace_kvm_timer_restore_state(ctx); + + ctx->loaded = true; +out: + local_irq_restore(flags); +} + +static void set_cntvoff(u64 cntvoff) +{ + kvm_call_hyp(__kvm_timer_set_cntvoff, cntvoff); +} + +static inline void set_timer_irq_phys_active(struct arch_timer_context *ctx, bool active) +{ + int r; + r = irq_set_irqchip_state(ctx->host_timer_irq, IRQCHIP_STATE_ACTIVE, active); + WARN_ON(r); +} + +static void kvm_timer_vcpu_load_gic(struct arch_timer_context *ctx) +{ + struct kvm_vcpu *vcpu = ctx->vcpu; + bool phys_active = false; + + /* + * Update the timer output so that it is likely to match the + * state we're about to restore. If the timer expires between + * this point and the register restoration, we'll take the + * interrupt anyway. + */ + kvm_timer_update_irq(ctx->vcpu, kvm_timer_should_fire(ctx), ctx); + + if (irqchip_in_kernel(vcpu->kvm)) + phys_active = kvm_vgic_map_is_active(vcpu, ctx->irq.irq); + + phys_active |= ctx->irq.level; + + set_timer_irq_phys_active(ctx, phys_active); +} + +static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu) +{ + struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); + + /* + * Update the timer output so that it is likely to match the + * state we're about to restore. If the timer expires between + * this point and the register restoration, we'll take the + * interrupt anyway. + */ + kvm_timer_update_irq(vcpu, kvm_timer_should_fire(vtimer), vtimer); + + /* + * When using a userspace irqchip with the architected timers and a + * host interrupt controller that doesn't support an active state, we + * must still prevent continuously exiting from the guest, and + * therefore mask the physical interrupt by disabling it on the host + * interrupt controller when the virtual level is high, such that the + * guest can make forward progress. Once we detect the output level + * being de-asserted, we unmask the interrupt again so that we exit + * from the guest when the timer fires. + */ + if (vtimer->irq.level) + disable_percpu_irq(host_vtimer_irq); + else + enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); +} + +void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + struct timer_map map; + + if (unlikely(!timer->enabled)) + return; + + get_timer_map(vcpu, &map); + + if (static_branch_likely(&has_gic_active_state)) { + kvm_timer_vcpu_load_gic(map.direct_vtimer); + if (map.direct_ptimer) + kvm_timer_vcpu_load_gic(map.direct_ptimer); + } else { + kvm_timer_vcpu_load_nogic(vcpu); + } + + set_cntvoff(map.direct_vtimer->cntvoff); + + kvm_timer_unblocking(vcpu); + + timer_restore_state(map.direct_vtimer); + if (map.direct_ptimer) + timer_restore_state(map.direct_ptimer); + + if (map.emul_ptimer) + timer_emulate(map.emul_ptimer); +} + +bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu) +{ + struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); + struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + struct kvm_sync_regs *sregs = &vcpu->run->s.regs; + bool vlevel, plevel; + + if (likely(irqchip_in_kernel(vcpu->kvm))) + return false; + + vlevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_VTIMER; + plevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_PTIMER; + + return kvm_timer_should_fire(vtimer) != vlevel || + kvm_timer_should_fire(ptimer) != plevel; +} + +void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + struct timer_map map; + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); + + if (unlikely(!timer->enabled)) + return; + + get_timer_map(vcpu, &map); + + timer_save_state(map.direct_vtimer); + if (map.direct_ptimer) + timer_save_state(map.direct_ptimer); + + /* + * Cancel soft timer emulation, because the only case where we + * need it after a vcpu_put is in the context of a sleeping VCPU, and + * in that case we already factor in the deadline for the physical + * timer when scheduling the bg_timer. + * + * In any case, we re-schedule the hrtimer for the physical timer when + * coming back to the VCPU thread in kvm_timer_vcpu_load(). + */ + if (map.emul_ptimer) + soft_timer_cancel(&map.emul_ptimer->hrtimer); + + if (rcuwait_active(wait)) + kvm_timer_blocking(vcpu); + + /* + * The kernel may decide to run userspace after calling vcpu_put, so + * we reset cntvoff to 0 to ensure a consistent read between user + * accesses to the virtual counter and kernel access to the physical + * counter of non-VHE case. For VHE, the virtual counter uses a fixed + * virtual offset of zero, so no need to zero CNTVOFF_EL2 register. + */ + set_cntvoff(0); +} + +/* + * With a userspace irqchip we have to check if the guest de-asserted the + * timer and if so, unmask the timer irq signal on the host interrupt + * controller to ensure that we see future timer signals. + */ +static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu) +{ + struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); + + if (!kvm_timer_should_fire(vtimer)) { + kvm_timer_update_irq(vcpu, false, vtimer); + if (static_branch_likely(&has_gic_active_state)) + set_timer_irq_phys_active(vtimer, false); + else + enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); + } +} + +void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + + if (unlikely(!timer->enabled)) + return; + + if (unlikely(!irqchip_in_kernel(vcpu->kvm))) + unmask_vtimer_irq_user(vcpu); +} + +int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + struct timer_map map; + + get_timer_map(vcpu, &map); + + /* + * The bits in CNTV_CTL are architecturally reset to UNKNOWN for ARMv8 + * and to 0 for ARMv7. We provide an implementation that always + * resets the timer to be disabled and unmasked and is compliant with + * the ARMv7 architecture. + */ + vcpu_vtimer(vcpu)->cnt_ctl = 0; + vcpu_ptimer(vcpu)->cnt_ctl = 0; + + if (timer->enabled) { + kvm_timer_update_irq(vcpu, false, vcpu_vtimer(vcpu)); + kvm_timer_update_irq(vcpu, false, vcpu_ptimer(vcpu)); + + if (irqchip_in_kernel(vcpu->kvm)) { + kvm_vgic_reset_mapped_irq(vcpu, map.direct_vtimer->irq.irq); + if (map.direct_ptimer) + kvm_vgic_reset_mapped_irq(vcpu, map.direct_ptimer->irq.irq); + } + } + + if (map.emul_ptimer) + soft_timer_cancel(&map.emul_ptimer->hrtimer); + + return 0; +} + +/* Make the updates of cntvoff for all vtimer contexts atomic */ +static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff) +{ + int i; + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu *tmp; + + mutex_lock(&kvm->lock); + kvm_for_each_vcpu(i, tmp, kvm) + vcpu_vtimer(tmp)->cntvoff = cntvoff; + + /* + * When called from the vcpu create path, the CPU being created is not + * included in the loop above, so we just set it here as well. + */ + vcpu_vtimer(vcpu)->cntvoff = cntvoff; + mutex_unlock(&kvm->lock); +} + +void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); + struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + + /* Synchronize cntvoff across all vtimers of a VM. */ + update_vtimer_cntvoff(vcpu, kvm_phys_timer_read()); + ptimer->cntvoff = 0; + + hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + timer->bg_timer.function = kvm_bg_timer_expire; + + hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + vtimer->hrtimer.function = kvm_hrtimer_expire; + ptimer->hrtimer.function = kvm_hrtimer_expire; + + vtimer->irq.irq = default_vtimer_irq.irq; + ptimer->irq.irq = default_ptimer_irq.irq; + + vtimer->host_timer_irq = host_vtimer_irq; + ptimer->host_timer_irq = host_ptimer_irq; + + vtimer->host_timer_irq_flags = host_vtimer_irq_flags; + ptimer->host_timer_irq_flags = host_ptimer_irq_flags; + + vtimer->vcpu = vcpu; + ptimer->vcpu = vcpu; +} + +static void kvm_timer_init_interrupt(void *info) +{ + enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); + enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags); +} + +int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) +{ + struct arch_timer_context *timer; + + switch (regid) { + case KVM_REG_ARM_TIMER_CTL: + timer = vcpu_vtimer(vcpu); + kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); + break; + case KVM_REG_ARM_TIMER_CNT: + timer = vcpu_vtimer(vcpu); + update_vtimer_cntvoff(vcpu, kvm_phys_timer_read() - value); + break; + case KVM_REG_ARM_TIMER_CVAL: + timer = vcpu_vtimer(vcpu); + kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value); + break; + case KVM_REG_ARM_PTIMER_CTL: + timer = vcpu_ptimer(vcpu); + kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); + break; + case KVM_REG_ARM_PTIMER_CVAL: + timer = vcpu_ptimer(vcpu); + kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value); + break; + + default: + return -1; + } + + return 0; +} + +static u64 read_timer_ctl(struct arch_timer_context *timer) +{ + /* + * Set ISTATUS bit if it's expired. + * Note that according to ARMv8 ARM Issue A.k, ISTATUS bit is + * UNKNOWN when ENABLE bit is 0, so we chose to set ISTATUS bit + * regardless of ENABLE bit for our implementation convenience. + */ + if (!kvm_timer_compute_delta(timer)) + return timer->cnt_ctl | ARCH_TIMER_CTRL_IT_STAT; + else + return timer->cnt_ctl; +} + +u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid) +{ + switch (regid) { + case KVM_REG_ARM_TIMER_CTL: + return kvm_arm_timer_read(vcpu, + vcpu_vtimer(vcpu), TIMER_REG_CTL); + case KVM_REG_ARM_TIMER_CNT: + return kvm_arm_timer_read(vcpu, + vcpu_vtimer(vcpu), TIMER_REG_CNT); + case KVM_REG_ARM_TIMER_CVAL: + return kvm_arm_timer_read(vcpu, + vcpu_vtimer(vcpu), TIMER_REG_CVAL); + case KVM_REG_ARM_PTIMER_CTL: + return kvm_arm_timer_read(vcpu, + vcpu_ptimer(vcpu), TIMER_REG_CTL); + case KVM_REG_ARM_PTIMER_CNT: + return kvm_arm_timer_read(vcpu, + vcpu_ptimer(vcpu), TIMER_REG_CNT); + case KVM_REG_ARM_PTIMER_CVAL: + return kvm_arm_timer_read(vcpu, + vcpu_ptimer(vcpu), TIMER_REG_CVAL); + } + return (u64)-1; +} + +static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, + struct arch_timer_context *timer, + enum kvm_arch_timer_regs treg) +{ + u64 val; + + switch (treg) { + case TIMER_REG_TVAL: + val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff; + val &= lower_32_bits(val); + break; + + case TIMER_REG_CTL: + val = read_timer_ctl(timer); + break; + + case TIMER_REG_CVAL: + val = timer->cnt_cval; + break; + + case TIMER_REG_CNT: + val = kvm_phys_timer_read() - timer->cntvoff; + break; + + default: + BUG(); + } + + return val; +} + +u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, + enum kvm_arch_timers tmr, + enum kvm_arch_timer_regs treg) +{ + u64 val; + + preempt_disable(); + kvm_timer_vcpu_put(vcpu); + + val = kvm_arm_timer_read(vcpu, vcpu_get_timer(vcpu, tmr), treg); + + kvm_timer_vcpu_load(vcpu); + preempt_enable(); + + return val; +} + +static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, + struct arch_timer_context *timer, + enum kvm_arch_timer_regs treg, + u64 val) +{ + switch (treg) { + case TIMER_REG_TVAL: + timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + (s32)val; + break; + + case TIMER_REG_CTL: + timer->cnt_ctl = val & ~ARCH_TIMER_CTRL_IT_STAT; + break; + + case TIMER_REG_CVAL: + timer->cnt_cval = val; + break; + + default: + BUG(); + } +} + +void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, + enum kvm_arch_timers tmr, + enum kvm_arch_timer_regs treg, + u64 val) +{ + preempt_disable(); + kvm_timer_vcpu_put(vcpu); + + kvm_arm_timer_write(vcpu, vcpu_get_timer(vcpu, tmr), treg, val); + + kvm_timer_vcpu_load(vcpu); + preempt_enable(); +} + +static int kvm_timer_starting_cpu(unsigned int cpu) +{ + kvm_timer_init_interrupt(NULL); + return 0; +} + +static int kvm_timer_dying_cpu(unsigned int cpu) +{ + disable_percpu_irq(host_vtimer_irq); + return 0; +} + +int kvm_timer_hyp_init(bool has_gic) +{ + struct arch_timer_kvm_info *info; + int err; + + info = arch_timer_get_kvm_info(); + timecounter = &info->timecounter; + + if (!timecounter->cc) { + kvm_err("kvm_arch_timer: uninitialized timecounter\n"); + return -ENODEV; + } + + /* First, do the virtual EL1 timer irq */ + + if (info->virtual_irq <= 0) { + kvm_err("kvm_arch_timer: invalid virtual timer IRQ: %d\n", + info->virtual_irq); + return -ENODEV; + } + host_vtimer_irq = info->virtual_irq; + + host_vtimer_irq_flags = irq_get_trigger_type(host_vtimer_irq); + if (host_vtimer_irq_flags != IRQF_TRIGGER_HIGH && + host_vtimer_irq_flags != IRQF_TRIGGER_LOW) { + kvm_err("Invalid trigger for vtimer IRQ%d, assuming level low\n", + host_vtimer_irq); + host_vtimer_irq_flags = IRQF_TRIGGER_LOW; + } + + err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler, + "kvm guest vtimer", kvm_get_running_vcpus()); + if (err) { + kvm_err("kvm_arch_timer: can't request vtimer interrupt %d (%d)\n", + host_vtimer_irq, err); + return err; + } + + if (has_gic) { + err = irq_set_vcpu_affinity(host_vtimer_irq, + kvm_get_running_vcpus()); + if (err) { + kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); + goto out_free_irq; + } + + static_branch_enable(&has_gic_active_state); + } + + kvm_debug("virtual timer IRQ%d\n", host_vtimer_irq); + + /* Now let's do the physical EL1 timer irq */ + + if (info->physical_irq > 0) { + host_ptimer_irq = info->physical_irq; + host_ptimer_irq_flags = irq_get_trigger_type(host_ptimer_irq); + if (host_ptimer_irq_flags != IRQF_TRIGGER_HIGH && + host_ptimer_irq_flags != IRQF_TRIGGER_LOW) { + kvm_err("Invalid trigger for ptimer IRQ%d, assuming level low\n", + host_ptimer_irq); + host_ptimer_irq_flags = IRQF_TRIGGER_LOW; + } + + err = request_percpu_irq(host_ptimer_irq, kvm_arch_timer_handler, + "kvm guest ptimer", kvm_get_running_vcpus()); + if (err) { + kvm_err("kvm_arch_timer: can't request ptimer interrupt %d (%d)\n", + host_ptimer_irq, err); + return err; + } + + if (has_gic) { + err = irq_set_vcpu_affinity(host_ptimer_irq, + kvm_get_running_vcpus()); + if (err) { + kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); + goto out_free_irq; + } + } + + kvm_debug("physical timer IRQ%d\n", host_ptimer_irq); + } else if (has_vhe()) { + kvm_err("kvm_arch_timer: invalid physical timer IRQ: %d\n", + info->physical_irq); + err = -ENODEV; + goto out_free_irq; + } + + cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING, + "kvm/arm/timer:starting", kvm_timer_starting_cpu, + kvm_timer_dying_cpu); + return 0; +out_free_irq: + free_percpu_irq(host_vtimer_irq, kvm_get_running_vcpus()); + return err; +} + +void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + + soft_timer_cancel(&timer->bg_timer); +} + +static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) +{ + int vtimer_irq, ptimer_irq; + int i, ret; + + vtimer_irq = vcpu_vtimer(vcpu)->irq.irq; + ret = kvm_vgic_set_owner(vcpu, vtimer_irq, vcpu_vtimer(vcpu)); + if (ret) + return false; + + ptimer_irq = vcpu_ptimer(vcpu)->irq.irq; + ret = kvm_vgic_set_owner(vcpu, ptimer_irq, vcpu_ptimer(vcpu)); + if (ret) + return false; + + kvm_for_each_vcpu(i, vcpu, vcpu->kvm) { + if (vcpu_vtimer(vcpu)->irq.irq != vtimer_irq || + vcpu_ptimer(vcpu)->irq.irq != ptimer_irq) + return false; + } + + return true; +} + +bool kvm_arch_timer_get_input_level(int vintid) +{ + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + struct arch_timer_context *timer; + + if (vintid == vcpu_vtimer(vcpu)->irq.irq) + timer = vcpu_vtimer(vcpu); + else if (vintid == vcpu_ptimer(vcpu)->irq.irq) + timer = vcpu_ptimer(vcpu); + else + BUG(); + + return kvm_timer_should_fire(timer); +} + +int kvm_timer_enable(struct kvm_vcpu *vcpu) +{ + struct arch_timer_cpu *timer = vcpu_timer(vcpu); + struct timer_map map; + int ret; + + if (timer->enabled) + return 0; + + /* Without a VGIC we do not map virtual IRQs to physical IRQs */ + if (!irqchip_in_kernel(vcpu->kvm)) + goto no_vgic; + + if (!vgic_initialized(vcpu->kvm)) + return -ENODEV; + + if (!timer_irqs_are_valid(vcpu)) { + kvm_debug("incorrectly configured timer irqs\n"); + return -EINVAL; + } + + get_timer_map(vcpu, &map); + + ret = kvm_vgic_map_phys_irq(vcpu, + map.direct_vtimer->host_timer_irq, + map.direct_vtimer->irq.irq, + kvm_arch_timer_get_input_level); + if (ret) + return ret; + + if (map.direct_ptimer) { + ret = kvm_vgic_map_phys_irq(vcpu, + map.direct_ptimer->host_timer_irq, + map.direct_ptimer->irq.irq, + kvm_arch_timer_get_input_level); + } + + if (ret) + return ret; + +no_vgic: + timer->enabled = 1; + return 0; +} + +/* + * On VHE system, we only need to configure the EL2 timer trap register once, + * not for every world switch. + * The host kernel runs at EL2 with HCR_EL2.TGE == 1, + * and this makes those bits have no effect for the host kernel execution. + */ +void kvm_timer_init_vhe(void) +{ + /* When HCR_EL2.E2H ==1, EL1PCEN and EL1PCTEN are shifted by 10 */ + u32 cnthctl_shift = 10; + u64 val; + + /* + * VHE systems allow the guest direct access to the EL1 physical + * timer/counter. + */ + val = read_sysreg(cnthctl_el2); + val |= (CNTHCTL_EL1PCEN << cnthctl_shift); + val |= (CNTHCTL_EL1PCTEN << cnthctl_shift); + write_sysreg(val, cnthctl_el2); +} + +static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq) +{ + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + vcpu_vtimer(vcpu)->irq.irq = vtimer_irq; + vcpu_ptimer(vcpu)->irq.irq = ptimer_irq; + } +} + +int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) +{ + int __user *uaddr = (int __user *)(long)attr->addr; + struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); + struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + int irq; + + if (!irqchip_in_kernel(vcpu->kvm)) + return -EINVAL; + + if (get_user(irq, uaddr)) + return -EFAULT; + + if (!(irq_is_ppi(irq))) + return -EINVAL; + + if (vcpu->arch.timer_cpu.enabled) + return -EBUSY; + + switch (attr->attr) { + case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: + set_timer_irqs(vcpu->kvm, irq, ptimer->irq.irq); + break; + case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: + set_timer_irqs(vcpu->kvm, vtimer->irq.irq, irq); + break; + default: + return -ENXIO; + } + + return 0; +} + +int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) +{ + int __user *uaddr = (int __user *)(long)attr->addr; + struct arch_timer_context *timer; + int irq; + + switch (attr->attr) { + case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: + timer = vcpu_vtimer(vcpu); + break; + case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: + timer = vcpu_ptimer(vcpu); + break; + default: + return -ENXIO; + } + + irq = timer->irq.irq; + return put_user(irq, uaddr); +} + +int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) +{ + switch (attr->attr) { + case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: + case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: + return 0; + } + + return -ENXIO; +} diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c new file mode 100644 index 000000000000..7a57381c05e8 --- /dev/null +++ b/arch/arm64/kvm/arm.c @@ -0,0 +1,1710 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + */ + +#include <linux/bug.h> +#include <linux/cpu_pm.h> +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/kvm_host.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/vmalloc.h> +#include <linux/fs.h> +#include <linux/mman.h> +#include <linux/sched.h> +#include <linux/kvm.h> +#include <linux/kvm_irqfd.h> +#include <linux/irqbypass.h> +#include <linux/sched/stat.h> +#include <trace/events/kvm.h> + +#define CREATE_TRACE_POINTS +#include "trace_arm.h" + +#include <linux/uaccess.h> +#include <asm/ptrace.h> +#include <asm/mman.h> +#include <asm/tlbflush.h> +#include <asm/cacheflush.h> +#include <asm/cpufeature.h> +#include <asm/virt.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_coproc.h> +#include <asm/sections.h> + +#include <kvm/arm_hypercalls.h> +#include <kvm/arm_pmu.h> +#include <kvm/arm_psci.h> + +#ifdef REQUIRES_VIRT +__asm__(".arch_extension virt"); +#endif + +DEFINE_PER_CPU(kvm_host_data_t, kvm_host_data); +static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); + +/* The VMID used in the VTTBR */ +static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1); +static u32 kvm_next_vmid; +static DEFINE_SPINLOCK(kvm_vmid_lock); + +static bool vgic_present; + +static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled); +DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use); + +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; +} + +int kvm_arch_hardware_setup(void *opaque) +{ + return 0; +} + +int kvm_arch_check_processor_compat(void *opaque) +{ + return 0; +} + +int kvm_vm_ioctl_enable_cap(struct kvm *kvm, + struct kvm_enable_cap *cap) +{ + int r; + + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_ARM_NISV_TO_USER: + r = 0; + kvm->arch.return_nisv_io_abort_to_user = true; + break; + default: + r = -EINVAL; + break; + } + + return r; +} + +static int kvm_arm_default_max_vcpus(void) +{ + return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS; +} + +/** + * kvm_arch_init_vm - initializes a VM data structure + * @kvm: pointer to the KVM struct + */ +int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) +{ + int ret, cpu; + + ret = kvm_arm_setup_stage2(kvm, type); + if (ret) + return ret; + + kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran)); + if (!kvm->arch.last_vcpu_ran) + return -ENOMEM; + + for_each_possible_cpu(cpu) + *per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1; + + ret = kvm_alloc_stage2_pgd(kvm); + if (ret) + goto out_fail_alloc; + + ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP); + if (ret) + goto out_free_stage2_pgd; + + kvm_vgic_early_init(kvm); + + /* Mark the initial VMID generation invalid */ + kvm->arch.vmid.vmid_gen = 0; + + /* The maximum number of VCPUs is limited by the host's GIC model */ + kvm->arch.max_vcpus = kvm_arm_default_max_vcpus(); + + return ret; +out_free_stage2_pgd: + kvm_free_stage2_pgd(kvm); +out_fail_alloc: + free_percpu(kvm->arch.last_vcpu_ran); + kvm->arch.last_vcpu_ran = NULL; + return ret; +} + +int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu) +{ + return 0; +} + +vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) +{ + return VM_FAULT_SIGBUS; +} + + +/** + * kvm_arch_destroy_vm - destroy the VM data structure + * @kvm: pointer to the KVM struct + */ +void kvm_arch_destroy_vm(struct kvm *kvm) +{ + int i; + + kvm_vgic_destroy(kvm); + + free_percpu(kvm->arch.last_vcpu_ran); + kvm->arch.last_vcpu_ran = NULL; + + for (i = 0; i < KVM_MAX_VCPUS; ++i) { + if (kvm->vcpus[i]) { + kvm_vcpu_destroy(kvm->vcpus[i]); + kvm->vcpus[i] = NULL; + } + } + atomic_set(&kvm->online_vcpus, 0); +} + +int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) +{ + int r; + switch (ext) { + case KVM_CAP_IRQCHIP: + r = vgic_present; + break; + case KVM_CAP_IOEVENTFD: + case KVM_CAP_DEVICE_CTRL: + case KVM_CAP_USER_MEMORY: + case KVM_CAP_SYNC_MMU: + case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: + case KVM_CAP_ONE_REG: + case KVM_CAP_ARM_PSCI: + case KVM_CAP_ARM_PSCI_0_2: + case KVM_CAP_READONLY_MEM: + case KVM_CAP_MP_STATE: + case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_VCPU_EVENTS: + case KVM_CAP_ARM_IRQ_LINE_LAYOUT_2: + case KVM_CAP_ARM_NISV_TO_USER: + case KVM_CAP_ARM_INJECT_EXT_DABT: + r = 1; + break; + case KVM_CAP_ARM_SET_DEVICE_ADDR: + r = 1; + break; + case KVM_CAP_NR_VCPUS: + r = num_online_cpus(); + break; + case KVM_CAP_MAX_VCPUS: + case KVM_CAP_MAX_VCPU_ID: + if (kvm) + r = kvm->arch.max_vcpus; + else + r = kvm_arm_default_max_vcpus(); + break; + case KVM_CAP_MSI_DEVID: + if (!kvm) + r = -EINVAL; + else + r = kvm->arch.vgic.msis_require_devid; + break; + case KVM_CAP_ARM_USER_IRQ: + /* + * 1: EL1_VTIMER, EL1_PTIMER, and PMU. + * (bump this number if adding more devices) + */ + r = 1; + break; + default: + r = kvm_arch_vm_ioctl_check_extension(kvm, ext); + break; + } + return r; +} + +long kvm_arch_dev_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + return -EINVAL; +} + +struct kvm *kvm_arch_alloc_vm(void) +{ + if (!has_vhe()) + return kzalloc(sizeof(struct kvm), GFP_KERNEL); + + return vzalloc(sizeof(struct kvm)); +} + +void kvm_arch_free_vm(struct kvm *kvm) +{ + if (!has_vhe()) + kfree(kvm); + else + vfree(kvm); +} + +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) +{ + if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) + return -EBUSY; + + if (id >= kvm->arch.max_vcpus) + return -EINVAL; + + return 0; +} + +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) +{ + int err; + + /* Force users to call KVM_ARM_VCPU_INIT */ + vcpu->arch.target = -1; + bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); + + /* Set up the timer */ + kvm_timer_vcpu_init(vcpu); + + kvm_pmu_vcpu_init(vcpu); + + kvm_arm_reset_debug_ptr(vcpu); + + kvm_arm_pvtime_vcpu_init(&vcpu->arch); + + err = kvm_vgic_vcpu_init(vcpu); + if (err) + return err; + + return create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP); +} + +void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) +{ +} + +void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm))) + static_branch_dec(&userspace_irqchip_in_use); + + kvm_mmu_free_memory_caches(vcpu); + kvm_timer_vcpu_terminate(vcpu); + kvm_pmu_vcpu_destroy(vcpu); + + kvm_arm_vcpu_destroy(vcpu); +} + +int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) +{ + return kvm_timer_is_pending(vcpu); +} + +void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) +{ + /* + * If we're about to block (most likely because we've just hit a + * WFI), we need to sync back the state of the GIC CPU interface + * so that we have the latest PMR and group enables. This ensures + * that kvm_arch_vcpu_runnable has up-to-date data to decide + * whether we have pending interrupts. + * + * For the same reason, we want to tell GICv4 that we need + * doorbells to be signalled, should an interrupt become pending. + */ + preempt_disable(); + kvm_vgic_vmcr_sync(vcpu); + vgic_v4_put(vcpu, true); + preempt_enable(); +} + +void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + vgic_v4_load(vcpu); + preempt_enable(); +} + +void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + int *last_ran; + kvm_host_data_t *cpu_data; + + last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran); + cpu_data = this_cpu_ptr(&kvm_host_data); + + /* + * We might get preempted before the vCPU actually runs, but + * over-invalidation doesn't affect correctness. + */ + if (*last_ran != vcpu->vcpu_id) { + kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu); + *last_ran = vcpu->vcpu_id; + } + + vcpu->cpu = cpu; + vcpu->arch.host_cpu_context = &cpu_data->host_ctxt; + + kvm_vgic_load(vcpu); + kvm_timer_vcpu_load(vcpu); + kvm_vcpu_load_sysregs(vcpu); + kvm_arch_vcpu_load_fp(vcpu); + kvm_vcpu_pmu_restore_guest(vcpu); + if (kvm_arm_is_pvtime_enabled(&vcpu->arch)) + kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu); + + if (single_task_running()) + vcpu_clear_wfx_traps(vcpu); + else + vcpu_set_wfx_traps(vcpu); + + vcpu_ptrauth_setup_lazy(vcpu); +} + +void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) +{ + kvm_arch_vcpu_put_fp(vcpu); + kvm_vcpu_put_sysregs(vcpu); + kvm_timer_vcpu_put(vcpu); + kvm_vgic_put(vcpu); + kvm_vcpu_pmu_restore_host(vcpu); + + vcpu->cpu = -1; +} + +static void vcpu_power_off(struct kvm_vcpu *vcpu) +{ + vcpu->arch.power_off = true; + kvm_make_request(KVM_REQ_SLEEP, vcpu); + kvm_vcpu_kick(vcpu); +} + +int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + if (vcpu->arch.power_off) + mp_state->mp_state = KVM_MP_STATE_STOPPED; + else + mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + + return 0; +} + +int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + int ret = 0; + + switch (mp_state->mp_state) { + case KVM_MP_STATE_RUNNABLE: + vcpu->arch.power_off = false; + break; + case KVM_MP_STATE_STOPPED: + vcpu_power_off(vcpu); + break; + default: + ret = -EINVAL; + } + + return ret; +} + +/** + * kvm_arch_vcpu_runnable - determine if the vcpu can be scheduled + * @v: The VCPU pointer + * + * If the guest CPU is not waiting for interrupts or an interrupt line is + * asserted, the CPU is by definition runnable. + */ +int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) +{ + bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF); + return ((irq_lines || kvm_vgic_vcpu_pending_irq(v)) + && !v->arch.power_off && !v->arch.pause); +} + +bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) +{ + return vcpu_mode_priv(vcpu); +} + +/* Just ensure a guest exit from a particular CPU */ +static void exit_vm_noop(void *info) +{ +} + +void force_vm_exit(const cpumask_t *mask) +{ + preempt_disable(); + smp_call_function_many(mask, exit_vm_noop, NULL, true); + preempt_enable(); +} + +/** + * need_new_vmid_gen - check that the VMID is still valid + * @vmid: The VMID to check + * + * return true if there is a new generation of VMIDs being used + * + * The hardware supports a limited set of values with the value zero reserved + * for the host, so we check if an assigned value belongs to a previous + * generation, which requires us to assign a new value. If we're the first to + * use a VMID for the new generation, we must flush necessary caches and TLBs + * on all CPUs. + */ +static bool need_new_vmid_gen(struct kvm_vmid *vmid) +{ + u64 current_vmid_gen = atomic64_read(&kvm_vmid_gen); + smp_rmb(); /* Orders read of kvm_vmid_gen and kvm->arch.vmid */ + return unlikely(READ_ONCE(vmid->vmid_gen) != current_vmid_gen); +} + +/** + * update_vmid - Update the vmid with a valid VMID for the current generation + * @kvm: The guest that struct vmid belongs to + * @vmid: The stage-2 VMID information struct + */ +static void update_vmid(struct kvm_vmid *vmid) +{ + if (!need_new_vmid_gen(vmid)) + return; + + spin_lock(&kvm_vmid_lock); + + /* + * We need to re-check the vmid_gen here to ensure that if another vcpu + * already allocated a valid vmid for this vm, then this vcpu should + * use the same vmid. + */ + if (!need_new_vmid_gen(vmid)) { + spin_unlock(&kvm_vmid_lock); + return; + } + + /* First user of a new VMID generation? */ + if (unlikely(kvm_next_vmid == 0)) { + atomic64_inc(&kvm_vmid_gen); + kvm_next_vmid = 1; + + /* + * On SMP we know no other CPUs can use this CPU's or each + * other's VMID after force_vm_exit returns since the + * kvm_vmid_lock blocks them from reentry to the guest. + */ + force_vm_exit(cpu_all_mask); + /* + * Now broadcast TLB + ICACHE invalidation over the inner + * shareable domain to make sure all data structures are + * clean. + */ + kvm_call_hyp(__kvm_flush_vm_context); + } + + vmid->vmid = kvm_next_vmid; + kvm_next_vmid++; + kvm_next_vmid &= (1 << kvm_get_vmid_bits()) - 1; + + smp_wmb(); + WRITE_ONCE(vmid->vmid_gen, atomic64_read(&kvm_vmid_gen)); + + spin_unlock(&kvm_vmid_lock); +} + +static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + int ret = 0; + + 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))) { + /* + * Map the VGIC hardware resources before running a vcpu the + * first time on this VM. + */ + if (unlikely(!vgic_ready(kvm))) { + ret = kvm_vgic_map_resources(kvm); + if (ret) + return ret; + } + } else { + /* + * Tell the rest of the code that there are userspace irqchip + * VMs in the wild. + */ + static_branch_inc(&userspace_irqchip_in_use); + } + + ret = kvm_timer_enable(vcpu); + if (ret) + return ret; + + ret = kvm_arm_pmu_v3_enable(vcpu); + + return ret; +} + +bool kvm_arch_intc_initialized(struct kvm *kvm) +{ + return vgic_initialized(kvm); +} + +void kvm_arm_halt_guest(struct kvm *kvm) +{ + int i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) + vcpu->arch.pause = true; + kvm_make_all_cpus_request(kvm, KVM_REQ_SLEEP); +} + +void kvm_arm_resume_guest(struct kvm *kvm) +{ + int i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + vcpu->arch.pause = false; + rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); + } +} + +static void vcpu_req_sleep(struct kvm_vcpu *vcpu) +{ + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); + + rcuwait_wait_event(wait, + (!vcpu->arch.power_off) &&(!vcpu->arch.pause), + TASK_INTERRUPTIBLE); + + if (vcpu->arch.power_off || vcpu->arch.pause) { + /* Awaken to handle a signal, request we sleep again later. */ + kvm_make_request(KVM_REQ_SLEEP, vcpu); + } + + /* + * Make sure we will observe a potential reset request if we've + * observed a change to the power state. Pairs with the smp_wmb() in + * kvm_psci_vcpu_on(). + */ + smp_rmb(); +} + +static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.target >= 0; +} + +static void check_vcpu_requests(struct kvm_vcpu *vcpu) +{ + if (kvm_request_pending(vcpu)) { + if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) + vcpu_req_sleep(vcpu); + + if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) + kvm_reset_vcpu(vcpu); + + /* + * Clear IRQ_PENDING requests that were made to guarantee + * that a VCPU sees new virtual interrupts. + */ + kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu); + + if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu)) + kvm_update_stolen_time(vcpu); + + if (kvm_check_request(KVM_REQ_RELOAD_GICv4, vcpu)) { + /* The distributor enable bits were changed */ + preempt_disable(); + vgic_v4_put(vcpu, false); + vgic_v4_load(vcpu); + preempt_enable(); + } + } +} + +/** + * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code + * @vcpu: The VCPU pointer + * + * This function is called through the VCPU_RUN ioctl called from user space. It + * will execute VM code in a loop until the time slice for the process is used + * or some emulation is needed from user space in which case the function will + * return with return value 0 and with the kvm_run structure filled in with the + * required data for the requested emulation. + */ +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + int ret; + + if (unlikely(!kvm_vcpu_initialized(vcpu))) + return -ENOEXEC; + + ret = kvm_vcpu_first_run_init(vcpu); + if (ret) + return ret; + + if (run->exit_reason == KVM_EXIT_MMIO) { + ret = kvm_handle_mmio_return(vcpu, run); + if (ret) + return ret; + } + + if (run->immediate_exit) + return -EINTR; + + vcpu_load(vcpu); + + kvm_sigset_activate(vcpu); + + ret = 1; + run->exit_reason = KVM_EXIT_UNKNOWN; + while (ret > 0) { + /* + * Check conditions before entering the guest + */ + cond_resched(); + + update_vmid(&vcpu->kvm->arch.vmid); + + check_vcpu_requests(vcpu); + + /* + * Preparing the interrupts to be injected also + * involves poking the GIC, which must be done in a + * non-preemptible context. + */ + preempt_disable(); + + kvm_pmu_flush_hwstate(vcpu); + + local_irq_disable(); + + kvm_vgic_flush_hwstate(vcpu); + + /* + * Exit if we have a signal pending so that we can deliver the + * signal to user space. + */ + if (signal_pending(current)) { + ret = -EINTR; + run->exit_reason = KVM_EXIT_INTR; + } + + /* + * If we're using a userspace irqchip, then check if we need + * to tell a userspace irqchip about timer or PMU level + * changes and if so, exit to userspace (the actual level + * state gets updated in kvm_timer_update_run and + * kvm_pmu_update_run below). + */ + if (static_branch_unlikely(&userspace_irqchip_in_use)) { + if (kvm_timer_should_notify_user(vcpu) || + kvm_pmu_should_notify_user(vcpu)) { + ret = -EINTR; + run->exit_reason = KVM_EXIT_INTR; + } + } + + /* + * Ensure we set mode to IN_GUEST_MODE after we disable + * interrupts and before the final VCPU requests check. + * See the comment in kvm_vcpu_exiting_guest_mode() and + * Documentation/virt/kvm/vcpu-requests.rst + */ + smp_store_mb(vcpu->mode, IN_GUEST_MODE); + + if (ret <= 0 || need_new_vmid_gen(&vcpu->kvm->arch.vmid) || + kvm_request_pending(vcpu)) { + vcpu->mode = OUTSIDE_GUEST_MODE; + isb(); /* Ensure work in x_flush_hwstate is committed */ + kvm_pmu_sync_hwstate(vcpu); + if (static_branch_unlikely(&userspace_irqchip_in_use)) + kvm_timer_sync_hwstate(vcpu); + kvm_vgic_sync_hwstate(vcpu); + local_irq_enable(); + preempt_enable(); + continue; + } + + kvm_arm_setup_debug(vcpu); + + /************************************************************** + * Enter the guest + */ + trace_kvm_entry(*vcpu_pc(vcpu)); + guest_enter_irqoff(); + + if (has_vhe()) { + ret = kvm_vcpu_run_vhe(vcpu); + } else { + ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu); + } + + vcpu->mode = OUTSIDE_GUEST_MODE; + vcpu->stat.exits++; + /* + * Back from guest + *************************************************************/ + + kvm_arm_clear_debug(vcpu); + + /* + * We must sync the PMU state before the vgic state so + * that the vgic can properly sample the updated state of the + * interrupt line. + */ + kvm_pmu_sync_hwstate(vcpu); + + /* + * Sync the vgic state before syncing the timer state because + * the timer code needs to know if the virtual timer + * interrupts are active. + */ + kvm_vgic_sync_hwstate(vcpu); + + /* + * Sync the timer hardware state before enabling interrupts as + * we don't want vtimer interrupts to race with syncing the + * timer virtual interrupt state. + */ + if (static_branch_unlikely(&userspace_irqchip_in_use)) + kvm_timer_sync_hwstate(vcpu); + + kvm_arch_vcpu_ctxsync_fp(vcpu); + + /* + * We may have taken a host interrupt in HYP mode (ie + * while executing the guest). This interrupt is still + * pending, as we haven't serviced it yet! + * + * We're now back in SVC mode, with interrupts + * disabled. Enabling the interrupts now will have + * the effect of taking the interrupt again, in SVC + * mode this time. + */ + local_irq_enable(); + + /* + * We do local_irq_enable() before calling guest_exit() so + * that if a timer interrupt hits while running the guest we + * account that tick as being spent in the guest. We enable + * preemption after calling guest_exit() so that if we get + * preempted we make sure ticks after that is not counted as + * guest time. + */ + guest_exit(); + trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); + + /* Exit types that need handling before we can be preempted */ + handle_exit_early(vcpu, run, ret); + + preempt_enable(); + + ret = handle_exit(vcpu, run, ret); + } + + /* Tell userspace about in-kernel device output levels */ + if (unlikely(!irqchip_in_kernel(vcpu->kvm))) { + kvm_timer_update_run(vcpu); + kvm_pmu_update_run(vcpu); + } + + kvm_sigset_deactivate(vcpu); + + vcpu_put(vcpu); + return ret; +} + +static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level) +{ + int bit_index; + bool set; + unsigned long *hcr; + + if (number == KVM_ARM_IRQ_CPU_IRQ) + bit_index = __ffs(HCR_VI); + else /* KVM_ARM_IRQ_CPU_FIQ */ + bit_index = __ffs(HCR_VF); + + hcr = vcpu_hcr(vcpu); + if (level) + set = test_and_set_bit(bit_index, hcr); + else + set = test_and_clear_bit(bit_index, hcr); + + /* + * If we didn't change anything, no need to wake up or kick other CPUs + */ + if (set == level) + return 0; + + /* + * The vcpu irq_lines field was updated, wake up sleeping VCPUs and + * trigger a world-switch round on the running physical CPU to set the + * virtual IRQ/FIQ fields in the HCR appropriately. + */ + kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); + kvm_vcpu_kick(vcpu); + + return 0; +} + +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, + bool line_status) +{ + u32 irq = irq_level->irq; + unsigned int irq_type, vcpu_idx, irq_num; + int nrcpus = atomic_read(&kvm->online_vcpus); + struct kvm_vcpu *vcpu = NULL; + bool level = irq_level->level; + + irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK; + vcpu_idx = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK; + vcpu_idx += ((irq >> KVM_ARM_IRQ_VCPU2_SHIFT) & KVM_ARM_IRQ_VCPU2_MASK) * (KVM_ARM_IRQ_VCPU_MASK + 1); + irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK; + + trace_kvm_irq_line(irq_type, vcpu_idx, irq_num, irq_level->level); + + switch (irq_type) { + case KVM_ARM_IRQ_TYPE_CPU: + if (irqchip_in_kernel(kvm)) + return -ENXIO; + + if (vcpu_idx >= nrcpus) + return -EINVAL; + + vcpu = kvm_get_vcpu(kvm, vcpu_idx); + if (!vcpu) + return -EINVAL; + + if (irq_num > KVM_ARM_IRQ_CPU_FIQ) + return -EINVAL; + + return vcpu_interrupt_line(vcpu, irq_num, level); + case KVM_ARM_IRQ_TYPE_PPI: + if (!irqchip_in_kernel(kvm)) + return -ENXIO; + + if (vcpu_idx >= nrcpus) + return -EINVAL; + + vcpu = kvm_get_vcpu(kvm, vcpu_idx); + if (!vcpu) + return -EINVAL; + + if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS) + return -EINVAL; + + return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level, NULL); + case KVM_ARM_IRQ_TYPE_SPI: + if (!irqchip_in_kernel(kvm)) + return -ENXIO; + + if (irq_num < VGIC_NR_PRIVATE_IRQS) + return -EINVAL; + + return kvm_vgic_inject_irq(kvm, 0, irq_num, level, NULL); + } + + return -EINVAL; +} + +static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, + const struct kvm_vcpu_init *init) +{ + unsigned int i, ret; + int phys_target = kvm_target_cpu(); + + if (init->target != phys_target) + return -EINVAL; + + /* + * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must + * use the same target. + */ + if (vcpu->arch.target != -1 && vcpu->arch.target != init->target) + return -EINVAL; + + /* -ENOENT for unknown features, -EINVAL for invalid combinations. */ + for (i = 0; i < sizeof(init->features) * 8; i++) { + bool set = (init->features[i / 32] & (1 << (i % 32))); + + if (set && i >= KVM_VCPU_MAX_FEATURES) + return -ENOENT; + + /* + * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must + * use the same feature set. + */ + if (vcpu->arch.target != -1 && i < KVM_VCPU_MAX_FEATURES && + test_bit(i, vcpu->arch.features) != set) + return -EINVAL; + + if (set) + set_bit(i, vcpu->arch.features); + } + + vcpu->arch.target = phys_target; + + /* Now we know what it is, we can reset it. */ + ret = kvm_reset_vcpu(vcpu); + if (ret) { + vcpu->arch.target = -1; + bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); + } + + return ret; +} + +static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, + struct kvm_vcpu_init *init) +{ + int ret; + + ret = kvm_vcpu_set_target(vcpu, init); + if (ret) + return ret; + + /* + * Ensure a rebooted VM will fault in RAM pages and detect if the + * guest MMU is turned off and flush the caches as needed. + * + * S2FWB enforces all memory accesses to RAM being cacheable, we + * ensure that the cache is always coherent. + */ + if (vcpu->arch.has_run_once && !cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) + stage2_unmap_vm(vcpu->kvm); + + vcpu_reset_hcr(vcpu); + + /* + * Handle the "start in power-off" case. + */ + if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) + vcpu_power_off(vcpu); + else + vcpu->arch.power_off = false; + + return 0; +} + +static int kvm_arm_vcpu_set_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + int ret = -ENXIO; + + switch (attr->group) { + default: + ret = kvm_arm_vcpu_arch_set_attr(vcpu, attr); + break; + } + + return ret; +} + +static int kvm_arm_vcpu_get_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + int ret = -ENXIO; + + switch (attr->group) { + default: + ret = kvm_arm_vcpu_arch_get_attr(vcpu, attr); + break; + } + + return ret; +} + +static int kvm_arm_vcpu_has_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + int ret = -ENXIO; + + switch (attr->group) { + default: + ret = kvm_arm_vcpu_arch_has_attr(vcpu, attr); + break; + } + + return ret; +} + +static int kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + memset(events, 0, sizeof(*events)); + + return __kvm_arm_vcpu_get_events(vcpu, events); +} + +static int kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + int i; + + /* check whether the reserved field is zero */ + for (i = 0; i < ARRAY_SIZE(events->reserved); i++) + if (events->reserved[i]) + return -EINVAL; + + /* check whether the pad field is zero */ + for (i = 0; i < ARRAY_SIZE(events->exception.pad); i++) + if (events->exception.pad[i]) + return -EINVAL; + + return __kvm_arm_vcpu_set_events(vcpu, events); +} + +long kvm_arch_vcpu_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + struct kvm_device_attr attr; + long r; + + switch (ioctl) { + case KVM_ARM_VCPU_INIT: { + struct kvm_vcpu_init init; + + r = -EFAULT; + if (copy_from_user(&init, argp, sizeof(init))) + break; + + r = kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init); + break; + } + case KVM_SET_ONE_REG: + case KVM_GET_ONE_REG: { + struct kvm_one_reg reg; + + r = -ENOEXEC; + if (unlikely(!kvm_vcpu_initialized(vcpu))) + break; + + r = -EFAULT; + if (copy_from_user(®, argp, sizeof(reg))) + break; + + if (ioctl == KVM_SET_ONE_REG) + r = kvm_arm_set_reg(vcpu, ®); + else + r = kvm_arm_get_reg(vcpu, ®); + break; + } + case KVM_GET_REG_LIST: { + struct kvm_reg_list __user *user_list = argp; + struct kvm_reg_list reg_list; + unsigned n; + + r = -ENOEXEC; + 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; + n = reg_list.n; + reg_list.n = kvm_arm_num_regs(vcpu); + if (copy_to_user(user_list, ®_list, sizeof(reg_list))) + break; + r = -E2BIG; + if (n < reg_list.n) + break; + r = kvm_arm_copy_reg_indices(vcpu, user_list->reg); + break; + } + case KVM_SET_DEVICE_ATTR: { + r = -EFAULT; + if (copy_from_user(&attr, argp, sizeof(attr))) + break; + r = kvm_arm_vcpu_set_attr(vcpu, &attr); + break; + } + case KVM_GET_DEVICE_ATTR: { + r = -EFAULT; + if (copy_from_user(&attr, argp, sizeof(attr))) + break; + r = kvm_arm_vcpu_get_attr(vcpu, &attr); + break; + } + case KVM_HAS_DEVICE_ATTR: { + r = -EFAULT; + if (copy_from_user(&attr, argp, sizeof(attr))) + break; + r = kvm_arm_vcpu_has_attr(vcpu, &attr); + break; + } + case KVM_GET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + if (kvm_arm_vcpu_get_events(vcpu, &events)) + return -EINVAL; + + if (copy_to_user(argp, &events, sizeof(events))) + return -EFAULT; + + return 0; + } + case KVM_SET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + if (copy_from_user(&events, argp, sizeof(events))) + return -EFAULT; + + 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; + } + + return r; +} + +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) +{ + +} + +void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + kvm_flush_remote_tlbs(kvm); +} + +static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, + struct kvm_arm_device_addr *dev_addr) +{ + unsigned long dev_id, type; + + dev_id = (dev_addr->id & KVM_ARM_DEVICE_ID_MASK) >> + KVM_ARM_DEVICE_ID_SHIFT; + type = (dev_addr->id & KVM_ARM_DEVICE_TYPE_MASK) >> + KVM_ARM_DEVICE_TYPE_SHIFT; + + switch (dev_id) { + case KVM_ARM_DEVICE_VGIC_V2: + if (!vgic_present) + return -ENXIO; + return kvm_vgic_addr(kvm, type, &dev_addr->addr, true); + default: + return -ENODEV; + } +} + +long kvm_arch_vm_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm *kvm = filp->private_data; + void __user *argp = (void __user *)arg; + + switch (ioctl) { + case KVM_CREATE_IRQCHIP: { + int ret; + if (!vgic_present) + return -ENXIO; + mutex_lock(&kvm->lock); + ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + mutex_unlock(&kvm->lock); + return ret; + } + case KVM_ARM_SET_DEVICE_ADDR: { + struct kvm_arm_device_addr dev_addr; + + if (copy_from_user(&dev_addr, argp, sizeof(dev_addr))) + return -EFAULT; + return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr); + } + case KVM_ARM_PREFERRED_TARGET: { + int err; + struct kvm_vcpu_init init; + + err = kvm_vcpu_preferred_target(&init); + if (err) + return err; + + if (copy_to_user(argp, &init, sizeof(init))) + return -EFAULT; + + return 0; + } + default: + return -EINVAL; + } +} + +static void cpu_init_hyp_mode(void) +{ + phys_addr_t pgd_ptr; + unsigned long hyp_stack_ptr; + unsigned long vector_ptr; + unsigned long tpidr_el2; + + /* Switch from the HYP stub to our own HYP init vector */ + __hyp_set_vectors(kvm_get_idmap_vector()); + + /* + * Calculate the raw per-cpu offset without a translation from the + * kernel's mapping to the linear mapping, and store it in tpidr_el2 + * so that we can use adr_l to access per-cpu variables in EL2. + */ + tpidr_el2 = ((unsigned long)this_cpu_ptr(&kvm_host_data) - + (unsigned long)kvm_ksym_ref(kvm_host_data)); + + pgd_ptr = kvm_mmu_get_httbr(); + hyp_stack_ptr = __this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE; + vector_ptr = (unsigned long)kvm_get_hyp_vector(); + + /* + * Call initialization code, and switch to the full blown HYP code. + * If the cpucaps haven't been finalized yet, something has gone very + * wrong, and hyp will crash and burn when it uses any + * cpus_have_const_cap() wrapper. + */ + BUG_ON(!system_capabilities_finalized()); + __kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2); + + /* + * Disabling SSBD on a non-VHE system requires us to enable SSBS + * at EL2. + */ + if (this_cpu_has_cap(ARM64_SSBS) && + arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) { + kvm_call_hyp(__kvm_enable_ssbs); + } +} + +static void cpu_hyp_reset(void) +{ + if (!is_kernel_in_hyp_mode()) + __hyp_reset_vectors(); +} + +static void cpu_hyp_reinit(void) +{ + kvm_init_host_cpu_context(&this_cpu_ptr(&kvm_host_data)->host_ctxt); + + cpu_hyp_reset(); + + if (is_kernel_in_hyp_mode()) + kvm_timer_init_vhe(); + else + cpu_init_hyp_mode(); + + kvm_arm_init_debug(); + + if (vgic_present) + kvm_vgic_init_cpu_hardware(); +} + +static void _kvm_arch_hardware_enable(void *discard) +{ + if (!__this_cpu_read(kvm_arm_hardware_enabled)) { + cpu_hyp_reinit(); + __this_cpu_write(kvm_arm_hardware_enabled, 1); + } +} + +int kvm_arch_hardware_enable(void) +{ + _kvm_arch_hardware_enable(NULL); + return 0; +} + +static void _kvm_arch_hardware_disable(void *discard) +{ + if (__this_cpu_read(kvm_arm_hardware_enabled)) { + cpu_hyp_reset(); + __this_cpu_write(kvm_arm_hardware_enabled, 0); + } +} + +void kvm_arch_hardware_disable(void) +{ + _kvm_arch_hardware_disable(NULL); +} + +#ifdef CONFIG_CPU_PM +static int hyp_init_cpu_pm_notifier(struct notifier_block *self, + unsigned long cmd, + void *v) +{ + /* + * kvm_arm_hardware_enabled is left with its old value over + * PM_ENTER->PM_EXIT. It is used to indicate PM_EXIT should + * re-enable hyp. + */ + switch (cmd) { + case CPU_PM_ENTER: + if (__this_cpu_read(kvm_arm_hardware_enabled)) + /* + * don't update kvm_arm_hardware_enabled here + * so that the hardware will be re-enabled + * when we resume. See below. + */ + cpu_hyp_reset(); + + return NOTIFY_OK; + case CPU_PM_ENTER_FAILED: + case CPU_PM_EXIT: + if (__this_cpu_read(kvm_arm_hardware_enabled)) + /* The hardware was enabled before suspend. */ + cpu_hyp_reinit(); + + return NOTIFY_OK; + + default: + return NOTIFY_DONE; + } +} + +static struct notifier_block hyp_init_cpu_pm_nb = { + .notifier_call = hyp_init_cpu_pm_notifier, +}; + +static void __init hyp_cpu_pm_init(void) +{ + cpu_pm_register_notifier(&hyp_init_cpu_pm_nb); +} +static void __init hyp_cpu_pm_exit(void) +{ + cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb); +} +#else +static inline void hyp_cpu_pm_init(void) +{ +} +static inline void hyp_cpu_pm_exit(void) +{ +} +#endif + +static int init_common_resources(void) +{ + return kvm_set_ipa_limit(); +} + +static int init_subsystems(void) +{ + int err = 0; + + /* + * Enable hardware so that subsystem initialisation can access EL2. + */ + on_each_cpu(_kvm_arch_hardware_enable, NULL, 1); + + /* + * Register CPU lower-power notifier + */ + hyp_cpu_pm_init(); + + /* + * Init HYP view of VGIC + */ + err = kvm_vgic_hyp_init(); + switch (err) { + case 0: + vgic_present = true; + break; + case -ENODEV: + case -ENXIO: + vgic_present = false; + err = 0; + break; + default: + goto out; + } + + /* + * Init HYP architected timer support + */ + err = kvm_timer_hyp_init(vgic_present); + if (err) + goto out; + + kvm_perf_init(); + kvm_coproc_table_init(); + +out: + on_each_cpu(_kvm_arch_hardware_disable, NULL, 1); + + return err; +} + +static void teardown_hyp_mode(void) +{ + int cpu; + + free_hyp_pgds(); + for_each_possible_cpu(cpu) + free_page(per_cpu(kvm_arm_hyp_stack_page, cpu)); +} + +/** + * Inits Hyp-mode on all online CPUs + */ +static int init_hyp_mode(void) +{ + int cpu; + int err = 0; + + /* + * Allocate Hyp PGD and setup Hyp identity mapping + */ + err = kvm_mmu_init(); + if (err) + goto out_err; + + /* + * Allocate stack pages for Hypervisor-mode + */ + for_each_possible_cpu(cpu) { + unsigned long stack_page; + + stack_page = __get_free_page(GFP_KERNEL); + if (!stack_page) { + err = -ENOMEM; + goto out_err; + } + + per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page; + } + + /* + * Map the Hyp-code called directly from the host + */ + err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start), + kvm_ksym_ref(__hyp_text_end), PAGE_HYP_EXEC); + if (err) { + kvm_err("Cannot map world-switch code\n"); + goto out_err; + } + + err = create_hyp_mappings(kvm_ksym_ref(__start_rodata), + kvm_ksym_ref(__end_rodata), PAGE_HYP_RO); + if (err) { + kvm_err("Cannot map rodata section\n"); + goto out_err; + } + + err = create_hyp_mappings(kvm_ksym_ref(__bss_start), + kvm_ksym_ref(__bss_stop), PAGE_HYP_RO); + if (err) { + kvm_err("Cannot map bss section\n"); + goto out_err; + } + + err = kvm_map_vectors(); + if (err) { + kvm_err("Cannot map vectors\n"); + goto out_err; + } + + /* + * Map the Hyp stack pages + */ + for_each_possible_cpu(cpu) { + char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu); + err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE, + PAGE_HYP); + + if (err) { + kvm_err("Cannot map hyp stack\n"); + goto out_err; + } + } + + for_each_possible_cpu(cpu) { + kvm_host_data_t *cpu_data; + + cpu_data = per_cpu_ptr(&kvm_host_data, cpu); + err = create_hyp_mappings(cpu_data, cpu_data + 1, PAGE_HYP); + + if (err) { + kvm_err("Cannot map host CPU state: %d\n", err); + goto out_err; + } + } + + err = hyp_map_aux_data(); + if (err) + kvm_err("Cannot map host auxiliary data: %d\n", err); + + return 0; + +out_err: + teardown_hyp_mode(); + kvm_err("error initializing Hyp mode: %d\n", err); + return err; +} + +static void check_kvm_target_cpu(void *ret) +{ + *(int *)ret = kvm_target_cpu(); +} + +struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) +{ + struct kvm_vcpu *vcpu; + int i; + + mpidr &= MPIDR_HWID_BITMASK; + kvm_for_each_vcpu(i, vcpu, kvm) { + if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu)) + return vcpu; + } + return NULL; +} + +bool kvm_arch_has_irq_bypass(void) +{ + return true; +} + +int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + return kvm_vgic_v4_set_forwarding(irqfd->kvm, prod->irq, + &irqfd->irq_entry); +} +void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq, + &irqfd->irq_entry); +} + +void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *cons) +{ + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + kvm_arm_halt_guest(irqfd->kvm); +} + +void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons) +{ + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + kvm_arm_resume_guest(irqfd->kvm); +} + +/** + * Initialize Hyp-mode and memory mappings on all CPUs. + */ +int kvm_arch_init(void *opaque) +{ + int err; + int ret, cpu; + bool in_hyp_mode; + + if (!is_hyp_mode_available()) { + kvm_info("HYP mode not available\n"); + return -ENODEV; + } + + in_hyp_mode = is_kernel_in_hyp_mode(); + + if (!in_hyp_mode && kvm_arch_requires_vhe()) { + kvm_pr_unimpl("CPU unsupported in non-VHE mode, not initializing\n"); + return -ENODEV; + } + + for_each_online_cpu(cpu) { + smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1); + if (ret < 0) { + kvm_err("Error, CPU %d not supported!\n", cpu); + return -ENODEV; + } + } + + err = init_common_resources(); + if (err) + return err; + + err = kvm_arm_init_sve(); + if (err) + return err; + + if (!in_hyp_mode) { + err = init_hyp_mode(); + if (err) + goto out_err; + } + + err = init_subsystems(); + if (err) + goto out_hyp; + + if (in_hyp_mode) + kvm_info("VHE mode initialized successfully\n"); + else + kvm_info("Hyp mode initialized successfully\n"); + + return 0; + +out_hyp: + hyp_cpu_pm_exit(); + if (!in_hyp_mode) + teardown_hyp_mode(); +out_err: + return err; +} + +/* NOP: Compiling as a module not supported */ +void kvm_arch_exit(void) +{ + kvm_perf_teardown(); +} + +static int arm_init(void) +{ + int rc = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + return rc; +} + +module_init(arm_init); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 50a279d3ddd7..aea43ec60f37 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -29,20 +29,19 @@ #include "trace.h" -#define VM_STAT(x) { #x, offsetof(struct kvm, stat.x), KVM_STAT_VM } -#define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU } - struct kvm_stats_debugfs_item debugfs_entries[] = { - VCPU_STAT(halt_successful_poll), - VCPU_STAT(halt_attempted_poll), - VCPU_STAT(halt_poll_invalid), - VCPU_STAT(halt_wakeup), - VCPU_STAT(hvc_exit_stat), - VCPU_STAT(wfe_exit_stat), - VCPU_STAT(wfi_exit_stat), - VCPU_STAT(mmio_exit_user), - VCPU_STAT(mmio_exit_kernel), - VCPU_STAT(exits), + VCPU_STAT("halt_successful_poll", halt_successful_poll), + VCPU_STAT("halt_attempted_poll", halt_attempted_poll), + VCPU_STAT("halt_poll_invalid", halt_poll_invalid), + VCPU_STAT("halt_wakeup", halt_wakeup), + VCPU_STAT("hvc_exit_stat", hvc_exit_stat), + VCPU_STAT("wfe_exit_stat", wfe_exit_stat), + VCPU_STAT("wfi_exit_stat", wfi_exit_stat), + VCPU_STAT("mmio_exit_user", mmio_exit_user), + VCPU_STAT("mmio_exit_kernel", mmio_exit_kernel), + VCPU_STAT("exits", exits), + VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), + VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), { NULL } }; @@ -267,7 +266,7 @@ static int set_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) /* * Vector lengths supported by the host can't currently be * hidden from the guest individually: instead we can only set a - * maxmium via ZCR_EL2.LEN. So, make sure the available vector + * maximum via ZCR_EL2.LEN. So, make sure the available vector * lengths match the set requested exactly up to the requested * maximum: */ @@ -337,7 +336,7 @@ static int sve_reg_to_region(struct sve_state_reg_region *region, unsigned int reg_num; unsigned int reqoffset, reqlen; /* User-requested offset and length */ - unsigned int maxlen; /* Maxmimum permitted length */ + unsigned int maxlen; /* Maximum permitted length */ size_t sve_state_size; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index aacfc55de44c..eb194696ef62 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -23,7 +23,7 @@ #include <kvm/arm_hypercalls.h> #define CREATE_TRACE_POINTS -#include "trace.h" +#include "trace_handle_exit.h" typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *); diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index ea710f674cb6..8c9880783839 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/arch/arm64/kvm/hyp/Makefile @@ -6,20 +6,10 @@ ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \ $(DISABLE_STACKLEAK_PLUGIN) -KVM=../../../../virt/kvm +obj-$(CONFIG_KVM) += hyp.o -obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o -obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o -obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/aarch32.o - -obj-$(CONFIG_KVM_ARM_HOST) += vgic-v2-cpuif-proxy.o -obj-$(CONFIG_KVM_ARM_HOST) += sysreg-sr.o -obj-$(CONFIG_KVM_ARM_HOST) += debug-sr.o -obj-$(CONFIG_KVM_ARM_HOST) += entry.o -obj-$(CONFIG_KVM_ARM_HOST) += switch.o -obj-$(CONFIG_KVM_ARM_HOST) += fpsimd.o -obj-$(CONFIG_KVM_ARM_HOST) += tlb.o -obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o +hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \ + debug-sr.o entry.o switch.o fpsimd.o tlb.o hyp-entry.o # KVM code is run at a different exception code with a different map, so # compiler instrumentation that inserts callbacks or checks into the code may diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c new file mode 100644 index 000000000000..25c0e47d57cb --- /dev/null +++ b/arch/arm64/kvm/hyp/aarch32.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hyp portion of the (not much of an) Emulation layer for 32bit guests. + * + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * based on arch/arm/kvm/emulate.c + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + */ + +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> + +/* + * stolen from arch/arm/kernel/opcodes.c + * + * condition code lookup table + * index into the table is test code: EQ, NE, ... LT, GT, AL, NV + * + * bit position in short is condition code: NZCV + */ +static const unsigned short cc_map[16] = { + 0xF0F0, /* EQ == Z set */ + 0x0F0F, /* NE */ + 0xCCCC, /* CS == C set */ + 0x3333, /* CC */ + 0xFF00, /* MI == N set */ + 0x00FF, /* PL */ + 0xAAAA, /* VS == V set */ + 0x5555, /* VC */ + 0x0C0C, /* HI == C set && Z clear */ + 0xF3F3, /* LS == C clear || Z set */ + 0xAA55, /* GE == (N==V) */ + 0x55AA, /* LT == (N!=V) */ + 0x0A05, /* GT == (!Z && (N==V)) */ + 0xF5FA, /* LE == (Z || (N!=V)) */ + 0xFFFF, /* AL always */ + 0 /* NV */ +}; + +/* + * Check if a trapped instruction should have been executed or not. + */ +bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu) +{ + unsigned long cpsr; + u32 cpsr_cond; + int cond; + + /* Top two bits non-zero? Unconditional. */ + if (kvm_vcpu_get_hsr(vcpu) >> 30) + return true; + + /* Is condition field valid? */ + cond = kvm_vcpu_get_condition(vcpu); + if (cond == 0xE) + return true; + + cpsr = *vcpu_cpsr(vcpu); + + if (cond < 0) { + /* This can happen in Thumb mode: examine IT state. */ + unsigned long it; + + it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3); + + /* it == 0 => unconditional. */ + if (it == 0) + return true; + + /* The cond for this insn works out as the top 4 bits. */ + cond = (it >> 4); + } + + cpsr_cond = cpsr >> 28; + + if (!((cc_map[cond] >> cpsr_cond) & 1)) + return false; + + return true; +} + +/** + * adjust_itstate - adjust ITSTATE when emulating instructions in IT-block + * @vcpu: The VCPU pointer + * + * When exceptions occur while instructions are executed in Thumb IF-THEN + * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have + * to do this little bit of work manually. The fields map like this: + * + * IT[7:0] -> CPSR[26:25],CPSR[15:10] + */ +static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu) +{ + unsigned long itbits, cond; + unsigned long cpsr = *vcpu_cpsr(vcpu); + bool is_arm = !(cpsr & PSR_AA32_T_BIT); + + if (is_arm || !(cpsr & PSR_AA32_IT_MASK)) + return; + + cond = (cpsr & 0xe000) >> 13; + itbits = (cpsr & 0x1c00) >> (10 - 2); + itbits |= (cpsr & (0x3 << 25)) >> 25; + + /* Perform ITAdvance (see page A2-52 in ARM DDI 0406C) */ + if ((itbits & 0x7) == 0) + itbits = cond = 0; + else + itbits = (itbits << 1) & 0x1f; + + cpsr &= ~PSR_AA32_IT_MASK; + cpsr |= cond << 13; + cpsr |= (itbits & 0x1c) << (10 - 2); + cpsr |= (itbits & 0x3) << 25; + *vcpu_cpsr(vcpu) = cpsr; +} + +/** + * kvm_skip_instr - skip a trapped instruction and proceed to the next + * @vcpu: The vcpu pointer + */ +void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) +{ + u32 pc = *vcpu_pc(vcpu); + bool is_thumb; + + is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT); + if (is_thumb && !is_wide_instr) + pc += 2; + else + pc += 4; + + *vcpu_pc(vcpu) = pc; + + kvm_adjust_itstate(vcpu); +} diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 1336e6f0acdf..676b6585e5ae 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -270,8 +270,8 @@ static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu) static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu) { if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { - __vgic_v3_save_state(vcpu); - __vgic_v3_deactivate_traps(vcpu); + __vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3); + __vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3); } } @@ -279,8 +279,8 @@ static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu) static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu) { if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { - __vgic_v3_activate_traps(vcpu); - __vgic_v3_restore_state(vcpu); + __vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3); + __vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3); } } diff --git a/arch/arm64/kvm/hyp/timer-sr.c b/arch/arm64/kvm/hyp/timer-sr.c new file mode 100644 index 000000000000..fb5c0be33223 --- /dev/null +++ b/arch/arm64/kvm/hyp/timer-sr.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <clocksource/arm_arch_timer.h> +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_hyp.h> + +void __hyp_text __kvm_timer_set_cntvoff(u64 cntvoff) +{ + write_sysreg(cntvoff, cntvoff_el2); +} + +/* + * Should only be called on non-VHE systems. + * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe(). + */ +void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu) +{ + u64 val; + + /* Allow physical timer/counter access for the host */ + val = read_sysreg(cnthctl_el2); + val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN; + write_sysreg(val, cnthctl_el2); +} + +/* + * Should only be called on non-VHE systems. + * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe(). + */ +void __hyp_text __timer_enable_traps(struct kvm_vcpu *vcpu) +{ + u64 val; + + /* + * Disallow physical timer access for the guest + * Physical counter access is allowed + */ + val = read_sysreg(cnthctl_el2); + val &= ~CNTHCTL_EL1PCEN; + val |= CNTHCTL_EL1PCTEN; + write_sysreg(val, cnthctl_el2); +} diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c new file mode 100644 index 000000000000..10ed539835c1 --- /dev/null +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -0,0 +1,1113 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <linux/compiler.h> +#include <linux/irqchip/arm-gic-v3.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> + +#define vtr_to_max_lr_idx(v) ((v) & 0xf) +#define vtr_to_nr_pre_bits(v) ((((u32)(v) >> 26) & 7) + 1) +#define vtr_to_nr_apr_regs(v) (1 << (vtr_to_nr_pre_bits(v) - 5)) + +static u64 __hyp_text __gic_v3_get_lr(unsigned int lr) +{ + switch (lr & 0xf) { + case 0: + return read_gicreg(ICH_LR0_EL2); + case 1: + return read_gicreg(ICH_LR1_EL2); + case 2: + return read_gicreg(ICH_LR2_EL2); + case 3: + return read_gicreg(ICH_LR3_EL2); + case 4: + return read_gicreg(ICH_LR4_EL2); + case 5: + return read_gicreg(ICH_LR5_EL2); + case 6: + return read_gicreg(ICH_LR6_EL2); + case 7: + return read_gicreg(ICH_LR7_EL2); + case 8: + return read_gicreg(ICH_LR8_EL2); + case 9: + return read_gicreg(ICH_LR9_EL2); + case 10: + return read_gicreg(ICH_LR10_EL2); + case 11: + return read_gicreg(ICH_LR11_EL2); + case 12: + return read_gicreg(ICH_LR12_EL2); + case 13: + return read_gicreg(ICH_LR13_EL2); + case 14: + return read_gicreg(ICH_LR14_EL2); + case 15: + return read_gicreg(ICH_LR15_EL2); + } + + unreachable(); +} + +static void __hyp_text __gic_v3_set_lr(u64 val, int lr) +{ + switch (lr & 0xf) { + case 0: + write_gicreg(val, ICH_LR0_EL2); + break; + case 1: + write_gicreg(val, ICH_LR1_EL2); + break; + case 2: + write_gicreg(val, ICH_LR2_EL2); + break; + case 3: + write_gicreg(val, ICH_LR3_EL2); + break; + case 4: + write_gicreg(val, ICH_LR4_EL2); + break; + case 5: + write_gicreg(val, ICH_LR5_EL2); + break; + case 6: + write_gicreg(val, ICH_LR6_EL2); + break; + case 7: + write_gicreg(val, ICH_LR7_EL2); + break; + case 8: + write_gicreg(val, ICH_LR8_EL2); + break; + case 9: + write_gicreg(val, ICH_LR9_EL2); + break; + case 10: + write_gicreg(val, ICH_LR10_EL2); + break; + case 11: + write_gicreg(val, ICH_LR11_EL2); + break; + case 12: + write_gicreg(val, ICH_LR12_EL2); + break; + case 13: + write_gicreg(val, ICH_LR13_EL2); + break; + case 14: + write_gicreg(val, ICH_LR14_EL2); + break; + case 15: + write_gicreg(val, ICH_LR15_EL2); + break; + } +} + +static void __hyp_text __vgic_v3_write_ap0rn(u32 val, int n) +{ + switch (n) { + case 0: + write_gicreg(val, ICH_AP0R0_EL2); + break; + case 1: + write_gicreg(val, ICH_AP0R1_EL2); + break; + case 2: + write_gicreg(val, ICH_AP0R2_EL2); + break; + case 3: + write_gicreg(val, ICH_AP0R3_EL2); + break; + } +} + +static void __hyp_text __vgic_v3_write_ap1rn(u32 val, int n) +{ + switch (n) { + case 0: + write_gicreg(val, ICH_AP1R0_EL2); + break; + case 1: + write_gicreg(val, ICH_AP1R1_EL2); + break; + case 2: + write_gicreg(val, ICH_AP1R2_EL2); + break; + case 3: + write_gicreg(val, ICH_AP1R3_EL2); + break; + } +} + +static u32 __hyp_text __vgic_v3_read_ap0rn(int n) +{ + u32 val; + + switch (n) { + case 0: + val = read_gicreg(ICH_AP0R0_EL2); + break; + case 1: + val = read_gicreg(ICH_AP0R1_EL2); + break; + case 2: + val = read_gicreg(ICH_AP0R2_EL2); + break; + case 3: + val = read_gicreg(ICH_AP0R3_EL2); + break; + default: + unreachable(); + } + + return val; +} + +static u32 __hyp_text __vgic_v3_read_ap1rn(int n) +{ + u32 val; + + switch (n) { + case 0: + val = read_gicreg(ICH_AP1R0_EL2); + break; + case 1: + val = read_gicreg(ICH_AP1R1_EL2); + break; + case 2: + val = read_gicreg(ICH_AP1R2_EL2); + break; + case 3: + val = read_gicreg(ICH_AP1R3_EL2); + break; + default: + unreachable(); + } + + return val; +} + +void __hyp_text __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if) +{ + u64 used_lrs = cpu_if->used_lrs; + + /* + * Make sure stores to the GIC via the memory mapped interface + * are now visible to the system register interface when reading the + * LRs, and when reading back the VMCR on non-VHE systems. + */ + if (used_lrs || !has_vhe()) { + if (!cpu_if->vgic_sre) { + dsb(sy); + isb(); + } + } + + if (used_lrs || cpu_if->its_vpe.its_vm) { + int i; + u32 elrsr; + + elrsr = read_gicreg(ICH_ELRSR_EL2); + + write_gicreg(cpu_if->vgic_hcr & ~ICH_HCR_EN, ICH_HCR_EL2); + + for (i = 0; i < used_lrs; i++) { + if (elrsr & (1 << i)) + cpu_if->vgic_lr[i] &= ~ICH_LR_STATE; + else + cpu_if->vgic_lr[i] = __gic_v3_get_lr(i); + + __gic_v3_set_lr(0, i); + } + } +} + +void __hyp_text __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if) +{ + u64 used_lrs = cpu_if->used_lrs; + int i; + + if (used_lrs || cpu_if->its_vpe.its_vm) { + write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2); + + for (i = 0; i < used_lrs; i++) + __gic_v3_set_lr(cpu_if->vgic_lr[i], i); + } + + /* + * Ensure that writes to the LRs, and on non-VHE systems ensure that + * the write to the VMCR in __vgic_v3_activate_traps(), will have + * reached the (re)distributors. This ensure the guest will read the + * correct values from the memory-mapped interface. + */ + if (used_lrs || !has_vhe()) { + if (!cpu_if->vgic_sre) { + isb(); + dsb(sy); + } + } +} + +void __hyp_text __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if) +{ + /* + * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a + * Group0 interrupt (as generated in GICv2 mode) to be + * delivered as a FIQ to the guest, with potentially fatal + * consequences. So we must make sure that ICC_SRE_EL1 has + * been actually programmed with the value we want before + * starting to mess with the rest of the GIC, and VMCR_EL2 in + * particular. This logic must be called before + * __vgic_v3_restore_state(). + */ + if (!cpu_if->vgic_sre) { + write_gicreg(0, ICC_SRE_EL1); + isb(); + write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2); + + + if (has_vhe()) { + /* + * Ensure that the write to the VMCR will have reached + * the (re)distributors. This ensure the guest will + * read the correct values from the memory-mapped + * interface. + */ + isb(); + dsb(sy); + } + } + + /* + * Prevent the guest from touching the GIC system registers if + * SRE isn't enabled for GICv3 emulation. + */ + write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE, + ICC_SRE_EL2); + + /* + * If we need to trap system registers, we must write + * ICH_HCR_EL2 anyway, even if no interrupts are being + * injected, + */ + if (static_branch_unlikely(&vgic_v3_cpuif_trap) || + cpu_if->its_vpe.its_vm) + write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2); +} + +void __hyp_text __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if) +{ + u64 val; + + if (!cpu_if->vgic_sre) { + cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2); + } + + val = read_gicreg(ICC_SRE_EL2); + write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2); + + if (!cpu_if->vgic_sre) { + /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */ + isb(); + write_gicreg(1, ICC_SRE_EL1); + } + + /* + * If we were trapping system registers, we enabled the VGIC even if + * no interrupts were being injected, and we disable it again here. + */ + if (static_branch_unlikely(&vgic_v3_cpuif_trap) || + cpu_if->its_vpe.its_vm) + write_gicreg(0, ICH_HCR_EL2); +} + +void __hyp_text __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if) +{ + u64 val; + u32 nr_pre_bits; + + val = read_gicreg(ICH_VTR_EL2); + nr_pre_bits = vtr_to_nr_pre_bits(val); + + switch (nr_pre_bits) { + case 7: + cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3); + cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2); + /* Fall through */ + case 6: + cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1); + /* Fall through */ + default: + cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0); + } + + switch (nr_pre_bits) { + case 7: + cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3); + cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2); + /* Fall through */ + case 6: + cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1); + /* Fall through */ + default: + cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0); + } +} + +void __hyp_text __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if) +{ + u64 val; + u32 nr_pre_bits; + + val = read_gicreg(ICH_VTR_EL2); + nr_pre_bits = vtr_to_nr_pre_bits(val); + + switch (nr_pre_bits) { + case 7: + __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3); + __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2); + /* Fall through */ + case 6: + __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1); + /* Fall through */ + default: + __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0); + } + + switch (nr_pre_bits) { + case 7: + __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3); + __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2); + /* Fall through */ + case 6: + __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1); + /* Fall through */ + default: + __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0); + } +} + +void __hyp_text __vgic_v3_init_lrs(void) +{ + int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2)); + int i; + + for (i = 0; i <= max_lr_idx; i++) + __gic_v3_set_lr(0, i); +} + +u64 __hyp_text __vgic_v3_get_ich_vtr_el2(void) +{ + return read_gicreg(ICH_VTR_EL2); +} + +u64 __hyp_text __vgic_v3_read_vmcr(void) +{ + return read_gicreg(ICH_VMCR_EL2); +} + +void __hyp_text __vgic_v3_write_vmcr(u32 vmcr) +{ + write_gicreg(vmcr, ICH_VMCR_EL2); +} + +static int __hyp_text __vgic_v3_bpr_min(void) +{ + /* See Pseudocode for VPriorityGroup */ + return 8 - vtr_to_nr_pre_bits(read_gicreg(ICH_VTR_EL2)); +} + +static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu) +{ + u32 esr = kvm_vcpu_get_hsr(vcpu); + u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT; + + return crm != 8; +} + +#define GICv3_IDLE_PRIORITY 0xff + +static int __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, + u32 vmcr, + u64 *lr_val) +{ + unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; + u8 priority = GICv3_IDLE_PRIORITY; + int i, lr = -1; + + for (i = 0; i < used_lrs; i++) { + u64 val = __gic_v3_get_lr(i); + u8 lr_prio = (val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; + + /* Not pending in the state? */ + if ((val & ICH_LR_STATE) != ICH_LR_PENDING_BIT) + continue; + + /* Group-0 interrupt, but Group-0 disabled? */ + if (!(val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_ENG0_MASK)) + continue; + + /* Group-1 interrupt, but Group-1 disabled? */ + if ((val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_ENG1_MASK)) + continue; + + /* Not the highest priority? */ + if (lr_prio >= priority) + continue; + + /* This is a candidate */ + priority = lr_prio; + *lr_val = val; + lr = i; + } + + if (lr == -1) + *lr_val = ICC_IAR1_EL1_SPURIOUS; + + return lr; +} + +static int __hyp_text __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, + int intid, u64 *lr_val) +{ + unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; + int i; + + for (i = 0; i < used_lrs; i++) { + u64 val = __gic_v3_get_lr(i); + + if ((val & ICH_LR_VIRTUAL_ID_MASK) == intid && + (val & ICH_LR_ACTIVE_BIT)) { + *lr_val = val; + return i; + } + } + + *lr_val = ICC_IAR1_EL1_SPURIOUS; + return -1; +} + +static int __hyp_text __vgic_v3_get_highest_active_priority(void) +{ + u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2)); + u32 hap = 0; + int i; + + for (i = 0; i < nr_apr_regs; i++) { + u32 val; + + /* + * The ICH_AP0Rn_EL2 and ICH_AP1Rn_EL2 registers + * contain the active priority levels for this VCPU + * for the maximum number of supported priority + * levels, and we return the full priority level only + * if the BPR is programmed to its minimum, otherwise + * we return a combination of the priority level and + * subpriority, as determined by the setting of the + * BPR, but without the full subpriority. + */ + val = __vgic_v3_read_ap0rn(i); + val |= __vgic_v3_read_ap1rn(i); + if (!val) { + hap += 32; + continue; + } + + return (hap + __ffs(val)) << __vgic_v3_bpr_min(); + } + + return GICv3_IDLE_PRIORITY; +} + +static unsigned int __hyp_text __vgic_v3_get_bpr0(u32 vmcr) +{ + return (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT; +} + +static unsigned int __hyp_text __vgic_v3_get_bpr1(u32 vmcr) +{ + unsigned int bpr; + + if (vmcr & ICH_VMCR_CBPR_MASK) { + bpr = __vgic_v3_get_bpr0(vmcr); + if (bpr < 7) + bpr++; + } else { + bpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT; + } + + return bpr; +} + +/* + * Convert a priority to a preemption level, taking the relevant BPR + * into account by zeroing the sub-priority bits. + */ +static u8 __hyp_text __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp) +{ + unsigned int bpr; + + if (!grp) + bpr = __vgic_v3_get_bpr0(vmcr) + 1; + else + bpr = __vgic_v3_get_bpr1(vmcr); + + return pri & (GENMASK(7, 0) << bpr); +} + +/* + * The priority value is independent of any of the BPR values, so we + * normalize it using the minimal BPR value. This guarantees that no + * matter what the guest does with its BPR, we can always set/get the + * same value of a priority. + */ +static void __hyp_text __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp) +{ + u8 pre, ap; + u32 val; + int apr; + + pre = __vgic_v3_pri_to_pre(pri, vmcr, grp); + ap = pre >> __vgic_v3_bpr_min(); + apr = ap / 32; + + if (!grp) { + val = __vgic_v3_read_ap0rn(apr); + __vgic_v3_write_ap0rn(val | BIT(ap % 32), apr); + } else { + val = __vgic_v3_read_ap1rn(apr); + __vgic_v3_write_ap1rn(val | BIT(ap % 32), apr); + } +} + +static int __hyp_text __vgic_v3_clear_highest_active_priority(void) +{ + u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2)); + u32 hap = 0; + int i; + + for (i = 0; i < nr_apr_regs; i++) { + u32 ap0, ap1; + int c0, c1; + + ap0 = __vgic_v3_read_ap0rn(i); + ap1 = __vgic_v3_read_ap1rn(i); + if (!ap0 && !ap1) { + hap += 32; + continue; + } + + c0 = ap0 ? __ffs(ap0) : 32; + c1 = ap1 ? __ffs(ap1) : 32; + + /* Always clear the LSB, which is the highest priority */ + if (c0 < c1) { + ap0 &= ~BIT(c0); + __vgic_v3_write_ap0rn(ap0, i); + hap += c0; + } else { + ap1 &= ~BIT(c1); + __vgic_v3_write_ap1rn(ap1, i); + hap += c1; + } + + /* Rescale to 8 bits of priority */ + return hap << __vgic_v3_bpr_min(); + } + + return GICv3_IDLE_PRIORITY; +} + +static void __hyp_text __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u64 lr_val; + u8 lr_prio, pmr; + int lr, grp; + + grp = __vgic_v3_get_group(vcpu); + + lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val); + if (lr < 0) + goto spurious; + + if (grp != !!(lr_val & ICH_LR_GROUP)) + goto spurious; + + pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT; + lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; + if (pmr <= lr_prio) + goto spurious; + + if (__vgic_v3_get_highest_active_priority() <= __vgic_v3_pri_to_pre(lr_prio, vmcr, grp)) + goto spurious; + + lr_val &= ~ICH_LR_STATE; + /* No active state for LPIs */ + if ((lr_val & ICH_LR_VIRTUAL_ID_MASK) <= VGIC_MAX_SPI) + lr_val |= ICH_LR_ACTIVE_BIT; + __gic_v3_set_lr(lr_val, lr); + __vgic_v3_set_active_priority(lr_prio, vmcr, grp); + vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK); + return; + +spurious: + vcpu_set_reg(vcpu, rt, ICC_IAR1_EL1_SPURIOUS); +} + +static void __hyp_text __vgic_v3_clear_active_lr(int lr, u64 lr_val) +{ + lr_val &= ~ICH_LR_ACTIVE_BIT; + if (lr_val & ICH_LR_HW) { + u32 pid; + + pid = (lr_val & ICH_LR_PHYS_ID_MASK) >> ICH_LR_PHYS_ID_SHIFT; + gic_write_dir(pid); + } + + __gic_v3_set_lr(lr_val, lr); +} + +static void __hyp_text __vgic_v3_bump_eoicount(void) +{ + u32 hcr; + + hcr = read_gicreg(ICH_HCR_EL2); + hcr += 1 << ICH_HCR_EOIcount_SHIFT; + write_gicreg(hcr, ICH_HCR_EL2); +} + +static void __hyp_text __vgic_v3_write_dir(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + u32 vid = vcpu_get_reg(vcpu, rt); + u64 lr_val; + int lr; + + /* EOImode == 0, nothing to be done here */ + if (!(vmcr & ICH_VMCR_EOIM_MASK)) + return; + + /* No deactivate to be performed on an LPI */ + if (vid >= VGIC_MIN_LPI) + return; + + lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val); + if (lr == -1) { + __vgic_v3_bump_eoicount(); + return; + } + + __vgic_v3_clear_active_lr(lr, lr_val); +} + +static void __hyp_text __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u32 vid = vcpu_get_reg(vcpu, rt); + u64 lr_val; + u8 lr_prio, act_prio; + int lr, grp; + + grp = __vgic_v3_get_group(vcpu); + + /* Drop priority in any case */ + act_prio = __vgic_v3_clear_highest_active_priority(); + + /* If EOIing an LPI, no deactivate to be performed */ + if (vid >= VGIC_MIN_LPI) + return; + + /* EOImode == 1, nothing to be done here */ + if (vmcr & ICH_VMCR_EOIM_MASK) + return; + + lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val); + if (lr == -1) { + __vgic_v3_bump_eoicount(); + return; + } + + lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; + + /* If priorities or group do not match, the guest has fscked-up. */ + if (grp != !!(lr_val & ICH_LR_GROUP) || + __vgic_v3_pri_to_pre(lr_prio, vmcr, grp) != act_prio) + return; + + /* Let's now perform the deactivation */ + __vgic_v3_clear_active_lr(lr, lr_val); +} + +static void __hyp_text __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG0_MASK)); +} + +static void __hyp_text __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG1_MASK)); +} + +static void __hyp_text __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u64 val = vcpu_get_reg(vcpu, rt); + + if (val & 1) + vmcr |= ICH_VMCR_ENG0_MASK; + else + vmcr &= ~ICH_VMCR_ENG0_MASK; + + __vgic_v3_write_vmcr(vmcr); +} + +static void __hyp_text __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u64 val = vcpu_get_reg(vcpu, rt); + + if (val & 1) + vmcr |= ICH_VMCR_ENG1_MASK; + else + vmcr &= ~ICH_VMCR_ENG1_MASK; + + __vgic_v3_write_vmcr(vmcr); +} + +static void __hyp_text __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr0(vmcr)); +} + +static void __hyp_text __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr1(vmcr)); +} + +static void __hyp_text __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u64 val = vcpu_get_reg(vcpu, rt); + u8 bpr_min = __vgic_v3_bpr_min() - 1; + + /* Enforce BPR limiting */ + if (val < bpr_min) + val = bpr_min; + + val <<= ICH_VMCR_BPR0_SHIFT; + val &= ICH_VMCR_BPR0_MASK; + vmcr &= ~ICH_VMCR_BPR0_MASK; + vmcr |= val; + + __vgic_v3_write_vmcr(vmcr); +} + +static void __hyp_text __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u64 val = vcpu_get_reg(vcpu, rt); + u8 bpr_min = __vgic_v3_bpr_min(); + + if (vmcr & ICH_VMCR_CBPR_MASK) + return; + + /* Enforce BPR limiting */ + if (val < bpr_min) + val = bpr_min; + + val <<= ICH_VMCR_BPR1_SHIFT; + val &= ICH_VMCR_BPR1_MASK; + vmcr &= ~ICH_VMCR_BPR1_MASK; + vmcr |= val; + + __vgic_v3_write_vmcr(vmcr); +} + +static void __hyp_text __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n) +{ + u32 val; + + if (!__vgic_v3_get_group(vcpu)) + val = __vgic_v3_read_ap0rn(n); + else + val = __vgic_v3_read_ap1rn(n); + + vcpu_set_reg(vcpu, rt, val); +} + +static void __hyp_text __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n) +{ + u32 val = vcpu_get_reg(vcpu, rt); + + if (!__vgic_v3_get_group(vcpu)) + __vgic_v3_write_ap0rn(val, n); + else + __vgic_v3_write_ap1rn(val, n); +} + +static void __hyp_text __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + __vgic_v3_read_apxrn(vcpu, rt, 0); +} + +static void __hyp_text __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + __vgic_v3_read_apxrn(vcpu, rt, 1); +} + +static void __hyp_text __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + __vgic_v3_read_apxrn(vcpu, rt, 2); +} + +static void __hyp_text __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + __vgic_v3_read_apxrn(vcpu, rt, 3); +} + +static void __hyp_text __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + __vgic_v3_write_apxrn(vcpu, rt, 0); +} + +static void __hyp_text __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + __vgic_v3_write_apxrn(vcpu, rt, 1); +} + +static void __hyp_text __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + __vgic_v3_write_apxrn(vcpu, rt, 2); +} + +static void __hyp_text __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + __vgic_v3_write_apxrn(vcpu, rt, 3); +} + +static void __hyp_text __vgic_v3_read_hppir(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + u64 lr_val; + int lr, lr_grp, grp; + + grp = __vgic_v3_get_group(vcpu); + + lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val); + if (lr == -1) + goto spurious; + + lr_grp = !!(lr_val & ICH_LR_GROUP); + if (lr_grp != grp) + lr_val = ICC_IAR1_EL1_SPURIOUS; + +spurious: + vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK); +} + +static void __hyp_text __vgic_v3_read_pmr(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + vmcr &= ICH_VMCR_PMR_MASK; + vmcr >>= ICH_VMCR_PMR_SHIFT; + vcpu_set_reg(vcpu, rt, vmcr); +} + +static void __hyp_text __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + u32 val = vcpu_get_reg(vcpu, rt); + + val <<= ICH_VMCR_PMR_SHIFT; + val &= ICH_VMCR_PMR_MASK; + vmcr &= ~ICH_VMCR_PMR_MASK; + vmcr |= val; + + write_gicreg(vmcr, ICH_VMCR_EL2); +} + +static void __hyp_text __vgic_v3_read_rpr(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + u32 val = __vgic_v3_get_highest_active_priority(); + vcpu_set_reg(vcpu, rt, val); +} + +static void __hyp_text __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + u32 vtr, val; + + vtr = read_gicreg(ICH_VTR_EL2); + /* PRIbits */ + val = ((vtr >> 29) & 7) << ICC_CTLR_EL1_PRI_BITS_SHIFT; + /* IDbits */ + val |= ((vtr >> 23) & 7) << ICC_CTLR_EL1_ID_BITS_SHIFT; + /* SEIS */ + val |= ((vtr >> 22) & 1) << ICC_CTLR_EL1_SEIS_SHIFT; + /* A3V */ + val |= ((vtr >> 21) & 1) << ICC_CTLR_EL1_A3V_SHIFT; + /* EOImode */ + val |= ((vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT) << ICC_CTLR_EL1_EOImode_SHIFT; + /* CBPR */ + val |= (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT; + + vcpu_set_reg(vcpu, rt, val); +} + +static void __hyp_text __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + u32 val = vcpu_get_reg(vcpu, rt); + + if (val & ICC_CTLR_EL1_CBPR_MASK) + vmcr |= ICH_VMCR_CBPR_MASK; + else + vmcr &= ~ICH_VMCR_CBPR_MASK; + + if (val & ICC_CTLR_EL1_EOImode_MASK) + vmcr |= ICH_VMCR_EOIM_MASK; + else + vmcr &= ~ICH_VMCR_EOIM_MASK; + + write_gicreg(vmcr, ICH_VMCR_EL2); +} + +int __hyp_text __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu) +{ + int rt; + u32 esr; + u32 vmcr; + void (*fn)(struct kvm_vcpu *, u32, int); + bool is_read; + u32 sysreg; + + esr = kvm_vcpu_get_hsr(vcpu); + if (vcpu_mode_is_32bit(vcpu)) { + if (!kvm_condition_valid(vcpu)) { + __kvm_skip_instr(vcpu); + return 1; + } + + sysreg = esr_cp15_to_sysreg(esr); + } else { + sysreg = esr_sys64_to_sysreg(esr); + } + + is_read = (esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ; + + switch (sysreg) { + case SYS_ICC_IAR0_EL1: + case SYS_ICC_IAR1_EL1: + if (unlikely(!is_read)) + return 0; + fn = __vgic_v3_read_iar; + break; + case SYS_ICC_EOIR0_EL1: + case SYS_ICC_EOIR1_EL1: + if (unlikely(is_read)) + return 0; + fn = __vgic_v3_write_eoir; + break; + case SYS_ICC_IGRPEN1_EL1: + if (is_read) + fn = __vgic_v3_read_igrpen1; + else + fn = __vgic_v3_write_igrpen1; + break; + case SYS_ICC_BPR1_EL1: + if (is_read) + fn = __vgic_v3_read_bpr1; + else + fn = __vgic_v3_write_bpr1; + break; + case SYS_ICC_AP0Rn_EL1(0): + case SYS_ICC_AP1Rn_EL1(0): + if (is_read) + fn = __vgic_v3_read_apxr0; + else + fn = __vgic_v3_write_apxr0; + break; + case SYS_ICC_AP0Rn_EL1(1): + case SYS_ICC_AP1Rn_EL1(1): + if (is_read) + fn = __vgic_v3_read_apxr1; + else + fn = __vgic_v3_write_apxr1; + break; + case SYS_ICC_AP0Rn_EL1(2): + case SYS_ICC_AP1Rn_EL1(2): + if (is_read) + fn = __vgic_v3_read_apxr2; + else + fn = __vgic_v3_write_apxr2; + break; + case SYS_ICC_AP0Rn_EL1(3): + case SYS_ICC_AP1Rn_EL1(3): + if (is_read) + fn = __vgic_v3_read_apxr3; + else + fn = __vgic_v3_write_apxr3; + break; + case SYS_ICC_HPPIR0_EL1: + case SYS_ICC_HPPIR1_EL1: + if (unlikely(!is_read)) + return 0; + fn = __vgic_v3_read_hppir; + break; + case SYS_ICC_IGRPEN0_EL1: + if (is_read) + fn = __vgic_v3_read_igrpen0; + else + fn = __vgic_v3_write_igrpen0; + break; + case SYS_ICC_BPR0_EL1: + if (is_read) + fn = __vgic_v3_read_bpr0; + else + fn = __vgic_v3_write_bpr0; + break; + case SYS_ICC_DIR_EL1: + if (unlikely(is_read)) + return 0; + fn = __vgic_v3_write_dir; + break; + case SYS_ICC_RPR_EL1: + if (unlikely(!is_read)) + return 0; + fn = __vgic_v3_read_rpr; + break; + case SYS_ICC_CTLR_EL1: + if (is_read) + fn = __vgic_v3_read_ctlr; + else + fn = __vgic_v3_write_ctlr; + break; + case SYS_ICC_PMR_EL1: + if (is_read) + fn = __vgic_v3_read_pmr; + else + fn = __vgic_v3_write_pmr; + break; + default: + return 0; + } + + vmcr = __vgic_v3_read_vmcr(); + rt = kvm_vcpu_sys_get_rt(vcpu); + fn(vcpu, vmcr, rt); + + __kvm_skip_instr(vcpu); + + return 1; +} diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c new file mode 100644 index 000000000000..550dfa3e53cd --- /dev/null +++ b/arch/arm64/kvm/hypercalls.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 Arm Ltd. + +#include <linux/arm-smccc.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_emulate.h> + +#include <kvm/arm_hypercalls.h> +#include <kvm/arm_psci.h> + +int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) +{ + u32 func_id = smccc_get_function(vcpu); + long val = SMCCC_RET_NOT_SUPPORTED; + u32 feature; + gpa_t gpa; + + switch (func_id) { + case ARM_SMCCC_VERSION_FUNC_ID: + val = ARM_SMCCC_VERSION_1_1; + break; + case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: + feature = smccc_get_arg1(vcpu); + switch (feature) { + case ARM_SMCCC_ARCH_WORKAROUND_1: + switch (kvm_arm_harden_branch_predictor()) { + case KVM_BP_HARDEN_UNKNOWN: + break; + case KVM_BP_HARDEN_WA_NEEDED: + val = SMCCC_RET_SUCCESS; + break; + case KVM_BP_HARDEN_NOT_REQUIRED: + val = SMCCC_RET_NOT_REQUIRED; + break; + } + break; + case ARM_SMCCC_ARCH_WORKAROUND_2: + switch (kvm_arm_have_ssbd()) { + case KVM_SSBD_FORCE_DISABLE: + case KVM_SSBD_UNKNOWN: + break; + case KVM_SSBD_KERNEL: + val = SMCCC_RET_SUCCESS; + break; + case KVM_SSBD_FORCE_ENABLE: + case KVM_SSBD_MITIGATED: + val = SMCCC_RET_NOT_REQUIRED; + break; + } + break; + case ARM_SMCCC_HV_PV_TIME_FEATURES: + val = SMCCC_RET_SUCCESS; + break; + } + break; + case ARM_SMCCC_HV_PV_TIME_FEATURES: + val = kvm_hypercall_pv_features(vcpu); + break; + case ARM_SMCCC_HV_PV_TIME_ST: + gpa = kvm_init_stolen_time(vcpu); + if (gpa != GPA_INVALID) + val = gpa; + break; + default: + return kvm_psci_call(vcpu); + } + + smccc_set_retval(vcpu, val, 0, 0, 0); + return 1; +} diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 6aafc2825c1c..e21fdd93027a 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -26,28 +26,12 @@ enum exception_type { except_type_serror = 0x180, }; -static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type) -{ - u64 exc_offset; - - switch (*vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT)) { - case PSR_MODE_EL1t: - exc_offset = CURRENT_EL_SP_EL0_VECTOR; - break; - case PSR_MODE_EL1h: - exc_offset = CURRENT_EL_SP_ELx_VECTOR; - break; - case PSR_MODE_EL0t: - exc_offset = LOWER_EL_AArch64_VECTOR; - break; - default: - exc_offset = LOWER_EL_AArch32_VECTOR; - } - - return vcpu_read_sys_reg(vcpu, VBAR_EL1) + exc_offset + type; -} - /* + * This performs the exception entry at a given EL (@target_mode), stashing PC + * and PSTATE into ELR and SPSR respectively, and compute the new PC/PSTATE. + * The EL passed to this function *must* be a non-secure, privileged mode with + * bit 0 being set (PSTATE.SP == 1). + * * When an exception is taken, most PSTATE fields are left unchanged in the * handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all * of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx @@ -59,10 +43,35 @@ static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type) * Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from * MSB to LSB. */ -static unsigned long get_except64_pstate(struct kvm_vcpu *vcpu) +static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, + enum exception_type type) { - unsigned long sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1); - unsigned long old, new; + unsigned long sctlr, vbar, old, new, mode; + u64 exc_offset; + + mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); + + if (mode == target_mode) + exc_offset = CURRENT_EL_SP_ELx_VECTOR; + else if ((mode | PSR_MODE_THREAD_BIT) == target_mode) + exc_offset = CURRENT_EL_SP_EL0_VECTOR; + else if (!(mode & PSR_MODE32_BIT)) + exc_offset = LOWER_EL_AArch64_VECTOR; + else + exc_offset = LOWER_EL_AArch32_VECTOR; + + switch (target_mode) { + case PSR_MODE_EL1h: + vbar = vcpu_read_sys_reg(vcpu, VBAR_EL1); + sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1); + vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu)); + break; + default: + /* Don't do that */ + BUG(); + } + + *vcpu_pc(vcpu) = vbar + exc_offset + type; old = *vcpu_cpsr(vcpu); new = 0; @@ -105,9 +114,10 @@ static unsigned long get_except64_pstate(struct kvm_vcpu *vcpu) new |= PSR_I_BIT; new |= PSR_F_BIT; - new |= PSR_MODE_EL1h; + new |= target_mode; - return new; + *vcpu_cpsr(vcpu) = new; + vcpu_write_spsr(vcpu, old); } static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr) @@ -116,11 +126,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr bool is_aarch32 = vcpu_mode_is_32bit(vcpu); u32 esr = 0; - vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu)); - *vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync); - - *vcpu_cpsr(vcpu) = get_except64_pstate(vcpu); - vcpu_write_spsr(vcpu, cpsr); + enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync); vcpu_write_sys_reg(vcpu, addr, FAR_EL1); @@ -148,14 +154,9 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr static void inject_undef64(struct kvm_vcpu *vcpu) { - unsigned long cpsr = *vcpu_cpsr(vcpu); u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); - vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu)); - *vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync); - - *vcpu_cpsr(vcpu) = get_except64_pstate(vcpu); - vcpu_write_spsr(vcpu, cpsr); + enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync); /* * Build an unknown exception, depending on the instruction diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c new file mode 100644 index 000000000000..4e0366759726 --- /dev/null +++ b/arch/arm64/kvm/mmio.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + */ + +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> +#include <trace/events/kvm.h> + +#include "trace.h" + +void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data) +{ + void *datap = NULL; + union { + u8 byte; + u16 hword; + u32 word; + u64 dword; + } tmp; + + switch (len) { + case 1: + tmp.byte = data; + datap = &tmp.byte; + break; + case 2: + tmp.hword = data; + datap = &tmp.hword; + break; + case 4: + tmp.word = data; + datap = &tmp.word; + break; + case 8: + tmp.dword = data; + datap = &tmp.dword; + break; + } + + memcpy(buf, datap, len); +} + +unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len) +{ + unsigned long data = 0; + union { + u16 hword; + u32 word; + u64 dword; + } tmp; + + switch (len) { + case 1: + data = *(u8 *)buf; + break; + case 2: + memcpy(&tmp.hword, buf, len); + data = tmp.hword; + break; + case 4: + memcpy(&tmp.word, buf, len); + data = tmp.word; + break; + case 8: + memcpy(&tmp.dword, buf, len); + data = tmp.dword; + break; + } + + return data; +} + +/** + * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation + * or in-kernel IO emulation + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the mmio data + */ +int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + unsigned long data; + unsigned int len; + int mask; + + /* Detect an already handled MMIO return */ + if (unlikely(!vcpu->mmio_needed)) + return 0; + + vcpu->mmio_needed = 0; + + if (!kvm_vcpu_dabt_iswrite(vcpu)) { + len = kvm_vcpu_dabt_get_as(vcpu); + data = kvm_mmio_read_buf(run->mmio.data, len); + + if (kvm_vcpu_dabt_issext(vcpu) && + len < sizeof(unsigned long)) { + mask = 1U << ((len * 8) - 1); + data = (data ^ mask) - mask; + } + + if (!kvm_vcpu_dabt_issf(vcpu)) + data = data & 0xffffffff; + + trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, + &data); + data = vcpu_data_host_to_guest(vcpu, data, len); + vcpu_set_reg(vcpu, kvm_vcpu_dabt_get_rd(vcpu), data); + } + + /* + * The MMIO instruction is emulated and should not be re-executed + * in the guest. + */ + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + + return 0; +} + +int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, + phys_addr_t fault_ipa) +{ + unsigned long data; + unsigned long rt; + int ret; + bool is_write; + int len; + u8 data_buf[8]; + + /* + * No valid syndrome? Ask userspace for help if it has + * volunteered to do so, and bail out otherwise. + */ + if (!kvm_vcpu_dabt_isvalid(vcpu)) { + if (vcpu->kvm->arch.return_nisv_io_abort_to_user) { + run->exit_reason = KVM_EXIT_ARM_NISV; + run->arm_nisv.esr_iss = kvm_vcpu_dabt_iss_nisv_sanitized(vcpu); + run->arm_nisv.fault_ipa = fault_ipa; + return 0; + } + + kvm_pr_unimpl("Data abort outside memslots with no valid syndrome info\n"); + return -ENOSYS; + } + + /* Page table accesses IO mem: tell guest to fix its TTBR */ + if (kvm_vcpu_dabt_iss1tw(vcpu)) { + kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + return 1; + } + + /* + * Prepare MMIO operation. First decode the syndrome data we get + * from the CPU. Then try if some in-kernel emulation feels + * responsible, otherwise let user space do its magic. + */ + is_write = kvm_vcpu_dabt_iswrite(vcpu); + len = kvm_vcpu_dabt_get_as(vcpu); + rt = kvm_vcpu_dabt_get_rd(vcpu); + + if (is_write) { + data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt), + len); + + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, &data); + kvm_mmio_write_buf(data_buf, len, data); + + ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len, + data_buf); + } else { + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len, + fault_ipa, NULL); + + ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len, + data_buf); + } + + /* Now prepare kvm_run for the potential return to userland. */ + run->mmio.is_write = is_write; + run->mmio.phys_addr = fault_ipa; + run->mmio.len = len; + vcpu->mmio_needed = 1; + + if (!ret) { + /* We handled the access successfully in the kernel. */ + if (!is_write) + memcpy(run->mmio.data, data_buf, len); + vcpu->stat.mmio_exit_kernel++; + kvm_handle_mmio_return(vcpu, run); + return 1; + } + + if (is_write) + memcpy(run->mmio.data, data_buf, len); + vcpu->stat.mmio_exit_user++; + run->exit_reason = KVM_EXIT_MMIO; + return 0; +} diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c new file mode 100644 index 000000000000..a1f6bc70c4e4 --- /dev/null +++ b/arch/arm64/kvm/mmu.c @@ -0,0 +1,2467 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + */ + +#include <linux/mman.h> +#include <linux/kvm_host.h> +#include <linux/io.h> +#include <linux/hugetlb.h> +#include <linux/sched/signal.h> +#include <trace/events/kvm.h> +#include <asm/pgalloc.h> +#include <asm/cacheflush.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_ras.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/virt.h> + +#include "trace.h" + +static pgd_t *boot_hyp_pgd; +static pgd_t *hyp_pgd; +static pgd_t *merged_hyp_pgd; +static DEFINE_MUTEX(kvm_hyp_pgd_mutex); + +static unsigned long hyp_idmap_start; +static unsigned long hyp_idmap_end; +static phys_addr_t hyp_idmap_vector; + +static unsigned long io_map_base; + +#define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t)) + +#define KVM_S2PTE_FLAG_IS_IOMAP (1UL << 0) +#define KVM_S2_FLAG_LOGGING_ACTIVE (1UL << 1) + +static bool is_iomap(unsigned long flags) +{ + return flags & KVM_S2PTE_FLAG_IS_IOMAP; +} + +static bool memslot_is_logging(struct kvm_memory_slot *memslot) +{ + return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY); +} + +/** + * kvm_flush_remote_tlbs() - flush all VM TLB entries for v7/8 + * @kvm: pointer to kvm structure. + * + * Interface to HYP function to flush all VM TLB entries + */ +void kvm_flush_remote_tlbs(struct kvm *kvm) +{ + kvm_call_hyp(__kvm_tlb_flush_vmid, kvm); +} + +static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) +{ + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa); +} + +/* + * D-Cache management functions. They take the page table entries by + * value, as they are flushing the cache using the kernel mapping (or + * kmap on 32bit). + */ +static void kvm_flush_dcache_pte(pte_t pte) +{ + __kvm_flush_dcache_pte(pte); +} + +static void kvm_flush_dcache_pmd(pmd_t pmd) +{ + __kvm_flush_dcache_pmd(pmd); +} + +static void kvm_flush_dcache_pud(pud_t pud) +{ + __kvm_flush_dcache_pud(pud); +} + +static bool kvm_is_device_pfn(unsigned long pfn) +{ + return !pfn_valid(pfn); +} + +/** + * stage2_dissolve_pmd() - clear and flush huge PMD entry + * @kvm: pointer to kvm structure. + * @addr: IPA + * @pmd: pmd pointer for IPA + * + * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs. + */ +static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd) +{ + if (!pmd_thp_or_huge(*pmd)) + return; + + pmd_clear(pmd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + put_page(virt_to_page(pmd)); +} + +/** + * stage2_dissolve_pud() - clear and flush huge PUD entry + * @kvm: pointer to kvm structure. + * @addr: IPA + * @pud: pud pointer for IPA + * + * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs. + */ +static void stage2_dissolve_pud(struct kvm *kvm, phys_addr_t addr, pud_t *pudp) +{ + if (!stage2_pud_huge(kvm, *pudp)) + return; + + stage2_pud_clear(kvm, pudp); + kvm_tlb_flush_vmid_ipa(kvm, addr); + put_page(virt_to_page(pudp)); +} + +static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, + int min, int max) +{ + void *page; + + BUG_ON(max > KVM_NR_MEM_OBJS); + if (cache->nobjs >= min) + return 0; + while (cache->nobjs < max) { + page = (void *)__get_free_page(GFP_PGTABLE_USER); + if (!page) + return -ENOMEM; + cache->objects[cache->nobjs++] = page; + } + return 0; +} + +static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) +{ + while (mc->nobjs) + free_page((unsigned long)mc->objects[--mc->nobjs]); +} + +static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) +{ + void *p; + + BUG_ON(!mc || !mc->nobjs); + p = mc->objects[--mc->nobjs]; + return p; +} + +static void clear_stage2_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr) +{ + pud_t *pud_table __maybe_unused = stage2_pud_offset(kvm, pgd, 0UL); + stage2_pgd_clear(kvm, pgd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + stage2_pud_free(kvm, pud_table); + put_page(virt_to_page(pgd)); +} + +static void clear_stage2_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr) +{ + pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(kvm, pud, 0); + VM_BUG_ON(stage2_pud_huge(kvm, *pud)); + stage2_pud_clear(kvm, pud); + kvm_tlb_flush_vmid_ipa(kvm, addr); + stage2_pmd_free(kvm, pmd_table); + put_page(virt_to_page(pud)); +} + +static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr) +{ + pte_t *pte_table = pte_offset_kernel(pmd, 0); + VM_BUG_ON(pmd_thp_or_huge(*pmd)); + pmd_clear(pmd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + free_page((unsigned long)pte_table); + put_page(virt_to_page(pmd)); +} + +static inline void kvm_set_pte(pte_t *ptep, pte_t new_pte) +{ + WRITE_ONCE(*ptep, new_pte); + dsb(ishst); +} + +static inline void kvm_set_pmd(pmd_t *pmdp, pmd_t new_pmd) +{ + WRITE_ONCE(*pmdp, new_pmd); + dsb(ishst); +} + +static inline void kvm_pmd_populate(pmd_t *pmdp, pte_t *ptep) +{ + kvm_set_pmd(pmdp, kvm_mk_pmd(ptep)); +} + +static inline void kvm_pud_populate(pud_t *pudp, pmd_t *pmdp) +{ + WRITE_ONCE(*pudp, kvm_mk_pud(pmdp)); + dsb(ishst); +} + +static inline void kvm_pgd_populate(pgd_t *pgdp, pud_t *pudp) +{ + WRITE_ONCE(*pgdp, kvm_mk_pgd(pudp)); + dsb(ishst); +} + +/* + * Unmapping vs dcache management: + * + * If a guest maps certain memory pages as uncached, all writes will + * bypass the data cache and go directly to RAM. However, the CPUs + * can still speculate reads (not writes) and fill cache lines with + * data. + * + * Those cache lines will be *clean* cache lines though, so a + * clean+invalidate operation is equivalent to an invalidate + * operation, because no cache lines are marked dirty. + * + * Those clean cache lines could be filled prior to an uncached write + * by the guest, and the cache coherent IO subsystem would therefore + * end up writing old data to disk. + * + * This is why right after unmapping a page/section and invalidating + * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure + * the IO subsystem will never hit in the cache. + * + * This is all avoided on systems that have ARM64_HAS_STAGE2_FWB, as + * we then fully enforce cacheability of RAM, no matter what the guest + * does. + */ +static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd, + phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t start_addr = addr; + pte_t *pte, *start_pte; + + start_pte = pte = pte_offset_kernel(pmd, addr); + do { + if (!pte_none(*pte)) { + pte_t old_pte = *pte; + + kvm_set_pte(pte, __pte(0)); + kvm_tlb_flush_vmid_ipa(kvm, addr); + + /* No need to invalidate the cache for device mappings */ + if (!kvm_is_device_pfn(pte_pfn(old_pte))) + kvm_flush_dcache_pte(old_pte); + + put_page(virt_to_page(pte)); + } + } while (pte++, addr += PAGE_SIZE, addr != end); + + if (stage2_pte_table_empty(kvm, start_pte)) + clear_stage2_pmd_entry(kvm, pmd, start_addr); +} + +static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud, + phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t next, start_addr = addr; + pmd_t *pmd, *start_pmd; + + start_pmd = pmd = stage2_pmd_offset(kvm, pud, addr); + do { + next = stage2_pmd_addr_end(kvm, addr, end); + if (!pmd_none(*pmd)) { + if (pmd_thp_or_huge(*pmd)) { + pmd_t old_pmd = *pmd; + + pmd_clear(pmd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + + kvm_flush_dcache_pmd(old_pmd); + + put_page(virt_to_page(pmd)); + } else { + unmap_stage2_ptes(kvm, pmd, addr, next); + } + } + } while (pmd++, addr = next, addr != end); + + if (stage2_pmd_table_empty(kvm, start_pmd)) + clear_stage2_pud_entry(kvm, pud, start_addr); +} + +static void unmap_stage2_puds(struct kvm *kvm, pgd_t *pgd, + phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t next, start_addr = addr; + pud_t *pud, *start_pud; + + start_pud = pud = stage2_pud_offset(kvm, pgd, addr); + do { + next = stage2_pud_addr_end(kvm, addr, end); + if (!stage2_pud_none(kvm, *pud)) { + if (stage2_pud_huge(kvm, *pud)) { + pud_t old_pud = *pud; + + stage2_pud_clear(kvm, pud); + kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_flush_dcache_pud(old_pud); + put_page(virt_to_page(pud)); + } else { + unmap_stage2_pmds(kvm, pud, addr, next); + } + } + } while (pud++, addr = next, addr != end); + + if (stage2_pud_table_empty(kvm, start_pud)) + clear_stage2_pgd_entry(kvm, pgd, start_addr); +} + +/** + * unmap_stage2_range -- Clear stage2 page table entries to unmap a range + * @kvm: The VM pointer + * @start: The intermediate physical base address of the range to unmap + * @size: The size of the area to unmap + * + * Clear a range of stage-2 mappings, lowering the various ref-counts. Must + * be called while holding mmu_lock (unless for freeing the stage2 pgd before + * destroying the VM), otherwise another faulting VCPU may come in and mess + * with things behind our backs. + */ +static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) +{ + pgd_t *pgd; + phys_addr_t addr = start, end = start + size; + phys_addr_t next; + + assert_spin_locked(&kvm->mmu_lock); + WARN_ON(size & ~PAGE_MASK); + + pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr); + do { + /* + * Make sure the page table is still active, as another thread + * could have possibly freed the page table, while we released + * the lock. + */ + if (!READ_ONCE(kvm->arch.pgd)) + break; + next = stage2_pgd_addr_end(kvm, addr, end); + if (!stage2_pgd_none(kvm, *pgd)) + unmap_stage2_puds(kvm, pgd, addr, next); + /* + * If the range is too large, release the kvm->mmu_lock + * to prevent starvation and lockup detector warnings. + */ + if (next != end) + cond_resched_lock(&kvm->mmu_lock); + } while (pgd++, addr = next, addr != end); +} + +static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, + phys_addr_t addr, phys_addr_t end) +{ + pte_t *pte; + + pte = pte_offset_kernel(pmd, addr); + do { + if (!pte_none(*pte) && !kvm_is_device_pfn(pte_pfn(*pte))) + kvm_flush_dcache_pte(*pte); + } while (pte++, addr += PAGE_SIZE, addr != end); +} + +static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud, + phys_addr_t addr, phys_addr_t end) +{ + pmd_t *pmd; + phys_addr_t next; + + pmd = stage2_pmd_offset(kvm, pud, addr); + do { + next = stage2_pmd_addr_end(kvm, addr, end); + if (!pmd_none(*pmd)) { + if (pmd_thp_or_huge(*pmd)) + kvm_flush_dcache_pmd(*pmd); + else + stage2_flush_ptes(kvm, pmd, addr, next); + } + } while (pmd++, addr = next, addr != end); +} + +static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd, + phys_addr_t addr, phys_addr_t end) +{ + pud_t *pud; + phys_addr_t next; + + pud = stage2_pud_offset(kvm, pgd, addr); + do { + next = stage2_pud_addr_end(kvm, addr, end); + if (!stage2_pud_none(kvm, *pud)) { + if (stage2_pud_huge(kvm, *pud)) + kvm_flush_dcache_pud(*pud); + else + stage2_flush_pmds(kvm, pud, addr, next); + } + } while (pud++, addr = next, addr != end); +} + +static void stage2_flush_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t end = addr + PAGE_SIZE * memslot->npages; + phys_addr_t next; + pgd_t *pgd; + + pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr); + do { + next = stage2_pgd_addr_end(kvm, addr, end); + if (!stage2_pgd_none(kvm, *pgd)) + stage2_flush_puds(kvm, pgd, addr, next); + + if (next != end) + cond_resched_lock(&kvm->mmu_lock); + } while (pgd++, addr = next, addr != end); +} + +/** + * stage2_flush_vm - Invalidate cache for pages mapped in stage 2 + * @kvm: The struct kvm pointer + * + * Go through the stage 2 page tables and invalidate any cache lines + * backing memory already mapped to the VM. + */ +static void stage2_flush_vm(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) + stage2_flush_memslot(kvm, memslot); + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); +} + +static void clear_hyp_pgd_entry(pgd_t *pgd) +{ + pud_t *pud_table __maybe_unused = pud_offset(pgd, 0UL); + pgd_clear(pgd); + pud_free(NULL, pud_table); + put_page(virt_to_page(pgd)); +} + +static void clear_hyp_pud_entry(pud_t *pud) +{ + pmd_t *pmd_table __maybe_unused = pmd_offset(pud, 0); + VM_BUG_ON(pud_huge(*pud)); + pud_clear(pud); + pmd_free(NULL, pmd_table); + put_page(virt_to_page(pud)); +} + +static void clear_hyp_pmd_entry(pmd_t *pmd) +{ + pte_t *pte_table = pte_offset_kernel(pmd, 0); + VM_BUG_ON(pmd_thp_or_huge(*pmd)); + pmd_clear(pmd); + pte_free_kernel(NULL, pte_table); + put_page(virt_to_page(pmd)); +} + +static void unmap_hyp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end) +{ + pte_t *pte, *start_pte; + + start_pte = pte = pte_offset_kernel(pmd, addr); + do { + if (!pte_none(*pte)) { + kvm_set_pte(pte, __pte(0)); + put_page(virt_to_page(pte)); + } + } while (pte++, addr += PAGE_SIZE, addr != end); + + if (hyp_pte_table_empty(start_pte)) + clear_hyp_pmd_entry(pmd); +} + +static void unmap_hyp_pmds(pud_t *pud, phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t next; + pmd_t *pmd, *start_pmd; + + start_pmd = pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + /* Hyp doesn't use huge pmds */ + if (!pmd_none(*pmd)) + unmap_hyp_ptes(pmd, addr, next); + } while (pmd++, addr = next, addr != end); + + if (hyp_pmd_table_empty(start_pmd)) + clear_hyp_pud_entry(pud); +} + +static void unmap_hyp_puds(pgd_t *pgd, phys_addr_t addr, phys_addr_t end) +{ + phys_addr_t next; + pud_t *pud, *start_pud; + + start_pud = pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); + /* Hyp doesn't use huge puds */ + if (!pud_none(*pud)) + unmap_hyp_pmds(pud, addr, next); + } while (pud++, addr = next, addr != end); + + if (hyp_pud_table_empty(start_pud)) + clear_hyp_pgd_entry(pgd); +} + +static unsigned int kvm_pgd_index(unsigned long addr, unsigned int ptrs_per_pgd) +{ + return (addr >> PGDIR_SHIFT) & (ptrs_per_pgd - 1); +} + +static void __unmap_hyp_range(pgd_t *pgdp, unsigned long ptrs_per_pgd, + phys_addr_t start, u64 size) +{ + pgd_t *pgd; + phys_addr_t addr = start, end = start + size; + phys_addr_t next; + + /* + * We don't unmap anything from HYP, except at the hyp tear down. + * Hence, we don't have to invalidate the TLBs here. + */ + pgd = pgdp + kvm_pgd_index(addr, ptrs_per_pgd); + do { + next = pgd_addr_end(addr, end); + if (!pgd_none(*pgd)) + unmap_hyp_puds(pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + +static void unmap_hyp_range(pgd_t *pgdp, phys_addr_t start, u64 size) +{ + __unmap_hyp_range(pgdp, PTRS_PER_PGD, start, size); +} + +static void unmap_hyp_idmap_range(pgd_t *pgdp, phys_addr_t start, u64 size) +{ + __unmap_hyp_range(pgdp, __kvm_idmap_ptrs_per_pgd(), start, size); +} + +/** + * free_hyp_pgds - free Hyp-mode page tables + * + * Assumes hyp_pgd is a page table used strictly in Hyp-mode and + * therefore contains either mappings in the kernel memory area (above + * PAGE_OFFSET), or device mappings in the idmap range. + * + * boot_hyp_pgd should only map the idmap range, and is only used in + * the extended idmap case. + */ +void free_hyp_pgds(void) +{ + pgd_t *id_pgd; + + mutex_lock(&kvm_hyp_pgd_mutex); + + id_pgd = boot_hyp_pgd ? boot_hyp_pgd : hyp_pgd; + + if (id_pgd) { + /* In case we never called hyp_mmu_init() */ + if (!io_map_base) + io_map_base = hyp_idmap_start; + unmap_hyp_idmap_range(id_pgd, io_map_base, + hyp_idmap_start + PAGE_SIZE - io_map_base); + } + + if (boot_hyp_pgd) { + free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order); + boot_hyp_pgd = NULL; + } + + if (hyp_pgd) { + unmap_hyp_range(hyp_pgd, kern_hyp_va(PAGE_OFFSET), + (uintptr_t)high_memory - PAGE_OFFSET); + + free_pages((unsigned long)hyp_pgd, hyp_pgd_order); + hyp_pgd = NULL; + } + if (merged_hyp_pgd) { + clear_page(merged_hyp_pgd); + free_page((unsigned long)merged_hyp_pgd); + merged_hyp_pgd = NULL; + } + + mutex_unlock(&kvm_hyp_pgd_mutex); +} + +static void create_hyp_pte_mappings(pmd_t *pmd, unsigned long start, + unsigned long end, unsigned long pfn, + pgprot_t prot) +{ + pte_t *pte; + unsigned long addr; + + addr = start; + do { + pte = pte_offset_kernel(pmd, addr); + kvm_set_pte(pte, kvm_pfn_pte(pfn, prot)); + get_page(virt_to_page(pte)); + pfn++; + } while (addr += PAGE_SIZE, addr != end); +} + +static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start, + unsigned long end, unsigned long pfn, + pgprot_t prot) +{ + pmd_t *pmd; + pte_t *pte; + unsigned long addr, next; + + addr = start; + do { + pmd = pmd_offset(pud, addr); + + BUG_ON(pmd_sect(*pmd)); + + if (pmd_none(*pmd)) { + pte = pte_alloc_one_kernel(NULL); + if (!pte) { + kvm_err("Cannot allocate Hyp pte\n"); + return -ENOMEM; + } + kvm_pmd_populate(pmd, pte); + get_page(virt_to_page(pmd)); + } + + next = pmd_addr_end(addr, end); + + create_hyp_pte_mappings(pmd, addr, next, pfn, prot); + pfn += (next - addr) >> PAGE_SHIFT; + } while (addr = next, addr != end); + + return 0; +} + +static int create_hyp_pud_mappings(pgd_t *pgd, unsigned long start, + unsigned long end, unsigned long pfn, + pgprot_t prot) +{ + pud_t *pud; + pmd_t *pmd; + unsigned long addr, next; + int ret; + + addr = start; + do { + pud = pud_offset(pgd, addr); + + if (pud_none_or_clear_bad(pud)) { + pmd = pmd_alloc_one(NULL, addr); + if (!pmd) { + kvm_err("Cannot allocate Hyp pmd\n"); + return -ENOMEM; + } + kvm_pud_populate(pud, pmd); + get_page(virt_to_page(pud)); + } + + next = pud_addr_end(addr, end); + ret = create_hyp_pmd_mappings(pud, addr, next, pfn, prot); + if (ret) + return ret; + pfn += (next - addr) >> PAGE_SHIFT; + } while (addr = next, addr != end); + + return 0; +} + +static int __create_hyp_mappings(pgd_t *pgdp, unsigned long ptrs_per_pgd, + unsigned long start, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + pgd_t *pgd; + pud_t *pud; + unsigned long addr, next; + int err = 0; + + mutex_lock(&kvm_hyp_pgd_mutex); + addr = start & PAGE_MASK; + end = PAGE_ALIGN(end); + do { + pgd = pgdp + kvm_pgd_index(addr, ptrs_per_pgd); + + if (pgd_none(*pgd)) { + pud = pud_alloc_one(NULL, addr); + if (!pud) { + kvm_err("Cannot allocate Hyp pud\n"); + err = -ENOMEM; + goto out; + } + kvm_pgd_populate(pgd, pud); + get_page(virt_to_page(pgd)); + } + + next = pgd_addr_end(addr, end); + err = create_hyp_pud_mappings(pgd, addr, next, pfn, prot); + if (err) + goto out; + pfn += (next - addr) >> PAGE_SHIFT; + } while (addr = next, addr != end); +out: + mutex_unlock(&kvm_hyp_pgd_mutex); + return err; +} + +static phys_addr_t kvm_kaddr_to_phys(void *kaddr) +{ + if (!is_vmalloc_addr(kaddr)) { + BUG_ON(!virt_addr_valid(kaddr)); + return __pa(kaddr); + } else { + return page_to_phys(vmalloc_to_page(kaddr)) + + offset_in_page(kaddr); + } +} + +/** + * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode + * @from: The virtual kernel start address of the range + * @to: The virtual kernel end address of the range (exclusive) + * @prot: The protection to be applied to this range + * + * The same virtual address as the kernel virtual address is also used + * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying + * physical pages. + */ +int create_hyp_mappings(void *from, void *to, pgprot_t prot) +{ + phys_addr_t phys_addr; + unsigned long virt_addr; + unsigned long start = kern_hyp_va((unsigned long)from); + unsigned long end = kern_hyp_va((unsigned long)to); + + if (is_kernel_in_hyp_mode()) + return 0; + + start = start & PAGE_MASK; + end = PAGE_ALIGN(end); + + for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) { + int err; + + phys_addr = kvm_kaddr_to_phys(from + virt_addr - start); + err = __create_hyp_mappings(hyp_pgd, PTRS_PER_PGD, + virt_addr, virt_addr + PAGE_SIZE, + __phys_to_pfn(phys_addr), + prot); + if (err) + return err; + } + + return 0; +} + +static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, + unsigned long *haddr, pgprot_t prot) +{ + pgd_t *pgd = hyp_pgd; + unsigned long base; + int ret = 0; + + mutex_lock(&kvm_hyp_pgd_mutex); + + /* + * This assumes that we have enough space below the idmap + * page to allocate our VAs. If not, the check below will + * kick. A potential alternative would be to detect that + * overflow and switch to an allocation above the idmap. + * + * The allocated size is always a multiple of PAGE_SIZE. + */ + size = PAGE_ALIGN(size + offset_in_page(phys_addr)); + base = io_map_base - size; + + /* + * Verify that BIT(VA_BITS - 1) hasn't been flipped by + * allocating the new area, as it would indicate we've + * overflowed the idmap/IO address range. + */ + if ((base ^ io_map_base) & BIT(VA_BITS - 1)) + ret = -ENOMEM; + else + io_map_base = base; + + mutex_unlock(&kvm_hyp_pgd_mutex); + + if (ret) + goto out; + + if (__kvm_cpu_uses_extended_idmap()) + pgd = boot_hyp_pgd; + + ret = __create_hyp_mappings(pgd, __kvm_idmap_ptrs_per_pgd(), + base, base + size, + __phys_to_pfn(phys_addr), prot); + if (ret) + goto out; + + *haddr = base + offset_in_page(phys_addr); + +out: + return ret; +} + +/** + * create_hyp_io_mappings - Map IO into both kernel and HYP + * @phys_addr: The physical start address which gets mapped + * @size: Size of the region being mapped + * @kaddr: Kernel VA for this mapping + * @haddr: HYP VA for this mapping + */ +int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, + void __iomem **kaddr, + void __iomem **haddr) +{ + unsigned long addr; + int ret; + + *kaddr = ioremap(phys_addr, size); + if (!*kaddr) + return -ENOMEM; + + if (is_kernel_in_hyp_mode()) { + *haddr = *kaddr; + return 0; + } + + ret = __create_hyp_private_mapping(phys_addr, size, + &addr, PAGE_HYP_DEVICE); + if (ret) { + iounmap(*kaddr); + *kaddr = NULL; + *haddr = NULL; + return ret; + } + + *haddr = (void __iomem *)addr; + return 0; +} + +/** + * create_hyp_exec_mappings - Map an executable range into HYP + * @phys_addr: The physical start address which gets mapped + * @size: Size of the region being mapped + * @haddr: HYP VA for this mapping + */ +int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, + void **haddr) +{ + unsigned long addr; + int ret; + + BUG_ON(is_kernel_in_hyp_mode()); + + ret = __create_hyp_private_mapping(phys_addr, size, + &addr, PAGE_HYP_EXEC); + if (ret) { + *haddr = NULL; + return ret; + } + + *haddr = (void *)addr; + return 0; +} + +/** + * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation. + * @kvm: The KVM struct pointer for the VM. + * + * Allocates only the stage-2 HW PGD level table(s) of size defined by + * stage2_pgd_size(kvm). + * + * Note we don't need locking here as this is only called when the VM is + * created, which can only be done once. + */ +int kvm_alloc_stage2_pgd(struct kvm *kvm) +{ + phys_addr_t pgd_phys; + pgd_t *pgd; + + if (kvm->arch.pgd != NULL) { + kvm_err("kvm_arch already initialized?\n"); + return -EINVAL; + } + + /* Allocate the HW PGD, making sure that each page gets its own refcount */ + pgd = alloc_pages_exact(stage2_pgd_size(kvm), GFP_KERNEL | __GFP_ZERO); + if (!pgd) + return -ENOMEM; + + pgd_phys = virt_to_phys(pgd); + if (WARN_ON(pgd_phys & ~kvm_vttbr_baddr_mask(kvm))) + return -EINVAL; + + kvm->arch.pgd = pgd; + kvm->arch.pgd_phys = pgd_phys; + return 0; +} + +static void stage2_unmap_memslot(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + hva_t hva = memslot->userspace_addr; + phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t size = PAGE_SIZE * memslot->npages; + hva_t reg_end = hva + size; + + /* + * A memory region could potentially cover multiple VMAs, and any holes + * between them, so iterate over all of them to find out if we should + * unmap any of them. + * + * +--------------------------------------------+ + * +---------------+----------------+ +----------------+ + * | : VMA 1 | VMA 2 | | VMA 3 : | + * +---------------+----------------+ +----------------+ + * | memory region | + * +--------------------------------------------+ + */ + do { + struct vm_area_struct *vma = find_vma(current->mm, hva); + hva_t vm_start, vm_end; + + if (!vma || vma->vm_start >= reg_end) + break; + + /* + * Take the intersection of this VMA with the memory region + */ + vm_start = max(hva, vma->vm_start); + vm_end = min(reg_end, vma->vm_end); + + if (!(vma->vm_flags & VM_PFNMAP)) { + gpa_t gpa = addr + (vm_start - memslot->userspace_addr); + unmap_stage2_range(kvm, gpa, vm_end - vm_start); + } + hva = vm_end; + } while (hva < reg_end); +} + +/** + * stage2_unmap_vm - Unmap Stage-2 RAM mappings + * @kvm: The struct kvm pointer + * + * Go through the memregions and unmap any regular RAM + * backing memory already mapped to the VM. + */ +void stage2_unmap_vm(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int idx; + + idx = srcu_read_lock(&kvm->srcu); + down_read(¤t->mm->mmap_sem); + spin_lock(&kvm->mmu_lock); + + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) + stage2_unmap_memslot(kvm, memslot); + + spin_unlock(&kvm->mmu_lock); + up_read(¤t->mm->mmap_sem); + srcu_read_unlock(&kvm->srcu, idx); +} + +/** + * kvm_free_stage2_pgd - free all stage-2 tables + * @kvm: The KVM struct pointer for the VM. + * + * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all + * underlying level-2 and level-3 tables before freeing the actual level-1 table + * and setting the struct pointer to NULL. + */ +void kvm_free_stage2_pgd(struct kvm *kvm) +{ + void *pgd = NULL; + + spin_lock(&kvm->mmu_lock); + if (kvm->arch.pgd) { + unmap_stage2_range(kvm, 0, kvm_phys_size(kvm)); + pgd = READ_ONCE(kvm->arch.pgd); + kvm->arch.pgd = NULL; + kvm->arch.pgd_phys = 0; + } + spin_unlock(&kvm->mmu_lock); + + /* Free the HW pgd, one page at a time */ + if (pgd) + free_pages_exact(pgd, stage2_pgd_size(kvm)); +} + +static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, + phys_addr_t addr) +{ + pgd_t *pgd; + pud_t *pud; + + pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr); + if (stage2_pgd_none(kvm, *pgd)) { + if (!cache) + return NULL; + pud = mmu_memory_cache_alloc(cache); + stage2_pgd_populate(kvm, pgd, pud); + get_page(virt_to_page(pgd)); + } + + return stage2_pud_offset(kvm, pgd, addr); +} + +static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, + phys_addr_t addr) +{ + pud_t *pud; + pmd_t *pmd; + + pud = stage2_get_pud(kvm, cache, addr); + if (!pud || stage2_pud_huge(kvm, *pud)) + return NULL; + + if (stage2_pud_none(kvm, *pud)) { + if (!cache) + return NULL; + pmd = mmu_memory_cache_alloc(cache); + stage2_pud_populate(kvm, pud, pmd); + get_page(virt_to_page(pud)); + } + + return stage2_pmd_offset(kvm, pud, addr); +} + +static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache + *cache, phys_addr_t addr, const pmd_t *new_pmd) +{ + pmd_t *pmd, old_pmd; + +retry: + pmd = stage2_get_pmd(kvm, cache, addr); + VM_BUG_ON(!pmd); + + old_pmd = *pmd; + /* + * Multiple vcpus faulting on the same PMD entry, can + * lead to them sequentially updating the PMD with the + * same value. Following the break-before-make + * (pmd_clear() followed by tlb_flush()) process can + * hinder forward progress due to refaults generated + * on missing translations. + * + * Skip updating the page table if the entry is + * unchanged. + */ + if (pmd_val(old_pmd) == pmd_val(*new_pmd)) + return 0; + + if (pmd_present(old_pmd)) { + /* + * If we already have PTE level mapping for this block, + * we must unmap it to avoid inconsistent TLB state and + * leaking the table page. We could end up in this situation + * if the memory slot was marked for dirty logging and was + * reverted, leaving PTE level mappings for the pages accessed + * during the period. So, unmap the PTE level mapping for this + * block and retry, as we could have released the upper level + * table in the process. + * + * Normal THP split/merge follows mmu_notifier callbacks and do + * get handled accordingly. + */ + if (!pmd_thp_or_huge(old_pmd)) { + unmap_stage2_range(kvm, addr & S2_PMD_MASK, S2_PMD_SIZE); + goto retry; + } + /* + * Mapping in huge pages should only happen through a + * fault. If a page is merged into a transparent huge + * page, the individual subpages of that huge page + * should be unmapped through MMU notifiers before we + * get here. + * + * Merging of CompoundPages is not supported; they + * should become splitting first, unmapped, merged, + * and mapped back in on-demand. + */ + WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd)); + pmd_clear(pmd); + kvm_tlb_flush_vmid_ipa(kvm, addr); + } else { + get_page(virt_to_page(pmd)); + } + + kvm_set_pmd(pmd, *new_pmd); + return 0; +} + +static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, + phys_addr_t addr, const pud_t *new_pudp) +{ + pud_t *pudp, old_pud; + +retry: + pudp = stage2_get_pud(kvm, cache, addr); + VM_BUG_ON(!pudp); + + old_pud = *pudp; + + /* + * A large number of vcpus faulting on the same stage 2 entry, + * can lead to a refault due to the stage2_pud_clear()/tlb_flush(). + * Skip updating the page tables if there is no change. + */ + if (pud_val(old_pud) == pud_val(*new_pudp)) + return 0; + + if (stage2_pud_present(kvm, old_pud)) { + /* + * If we already have table level mapping for this block, unmap + * the range for this block and retry. + */ + if (!stage2_pud_huge(kvm, old_pud)) { + unmap_stage2_range(kvm, addr & S2_PUD_MASK, S2_PUD_SIZE); + goto retry; + } + + WARN_ON_ONCE(kvm_pud_pfn(old_pud) != kvm_pud_pfn(*new_pudp)); + stage2_pud_clear(kvm, pudp); + kvm_tlb_flush_vmid_ipa(kvm, addr); + } else { + get_page(virt_to_page(pudp)); + } + + kvm_set_pud(pudp, *new_pudp); + return 0; +} + +/* + * stage2_get_leaf_entry - walk the stage2 VM page tables and return + * true if a valid and present leaf-entry is found. A pointer to the + * leaf-entry is returned in the appropriate level variable - pudpp, + * pmdpp, ptepp. + */ +static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr, + pud_t **pudpp, pmd_t **pmdpp, pte_t **ptepp) +{ + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; + + *pudpp = NULL; + *pmdpp = NULL; + *ptepp = NULL; + + pudp = stage2_get_pud(kvm, NULL, addr); + if (!pudp || stage2_pud_none(kvm, *pudp) || !stage2_pud_present(kvm, *pudp)) + return false; + + if (stage2_pud_huge(kvm, *pudp)) { + *pudpp = pudp; + return true; + } + + pmdp = stage2_pmd_offset(kvm, pudp, addr); + if (!pmdp || pmd_none(*pmdp) || !pmd_present(*pmdp)) + return false; + + if (pmd_thp_or_huge(*pmdp)) { + *pmdpp = pmdp; + return true; + } + + ptep = pte_offset_kernel(pmdp, addr); + if (!ptep || pte_none(*ptep) || !pte_present(*ptep)) + return false; + + *ptepp = ptep; + return true; +} + +static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr) +{ + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; + bool found; + + found = stage2_get_leaf_entry(kvm, addr, &pudp, &pmdp, &ptep); + if (!found) + return false; + + if (pudp) + return kvm_s2pud_exec(pudp); + else if (pmdp) + return kvm_s2pmd_exec(pmdp); + else + return kvm_s2pte_exec(ptep); +} + +static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, + phys_addr_t addr, const pte_t *new_pte, + unsigned long flags) +{ + pud_t *pud; + pmd_t *pmd; + pte_t *pte, old_pte; + bool iomap = flags & KVM_S2PTE_FLAG_IS_IOMAP; + bool logging_active = flags & KVM_S2_FLAG_LOGGING_ACTIVE; + + VM_BUG_ON(logging_active && !cache); + + /* Create stage-2 page table mapping - Levels 0 and 1 */ + pud = stage2_get_pud(kvm, cache, addr); + if (!pud) { + /* + * Ignore calls from kvm_set_spte_hva for unallocated + * address ranges. + */ + return 0; + } + + /* + * While dirty page logging - dissolve huge PUD, then continue + * on to allocate page. + */ + if (logging_active) + stage2_dissolve_pud(kvm, addr, pud); + + if (stage2_pud_none(kvm, *pud)) { + if (!cache) + return 0; /* ignore calls from kvm_set_spte_hva */ + pmd = mmu_memory_cache_alloc(cache); + stage2_pud_populate(kvm, pud, pmd); + get_page(virt_to_page(pud)); + } + + pmd = stage2_pmd_offset(kvm, pud, addr); + if (!pmd) { + /* + * Ignore calls from kvm_set_spte_hva for unallocated + * address ranges. + */ + return 0; + } + + /* + * While dirty page logging - dissolve huge PMD, then continue on to + * allocate page. + */ + if (logging_active) + stage2_dissolve_pmd(kvm, addr, pmd); + + /* Create stage-2 page mappings - Level 2 */ + if (pmd_none(*pmd)) { + if (!cache) + return 0; /* ignore calls from kvm_set_spte_hva */ + pte = mmu_memory_cache_alloc(cache); + kvm_pmd_populate(pmd, pte); + get_page(virt_to_page(pmd)); + } + + pte = pte_offset_kernel(pmd, addr); + + if (iomap && pte_present(*pte)) + return -EFAULT; + + /* Create 2nd stage page table mapping - Level 3 */ + old_pte = *pte; + if (pte_present(old_pte)) { + /* Skip page table update if there is no change */ + if (pte_val(old_pte) == pte_val(*new_pte)) + return 0; + + kvm_set_pte(pte, __pte(0)); + kvm_tlb_flush_vmid_ipa(kvm, addr); + } else { + get_page(virt_to_page(pte)); + } + + kvm_set_pte(pte, *new_pte); + return 0; +} + +#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +static int stage2_ptep_test_and_clear_young(pte_t *pte) +{ + if (pte_young(*pte)) { + *pte = pte_mkold(*pte); + return 1; + } + return 0; +} +#else +static int stage2_ptep_test_and_clear_young(pte_t *pte) +{ + return __ptep_test_and_clear_young(pte); +} +#endif + +static int stage2_pmdp_test_and_clear_young(pmd_t *pmd) +{ + return stage2_ptep_test_and_clear_young((pte_t *)pmd); +} + +static int stage2_pudp_test_and_clear_young(pud_t *pud) +{ + return stage2_ptep_test_and_clear_young((pte_t *)pud); +} + +/** + * kvm_phys_addr_ioremap - map a device range to guest IPA + * + * @kvm: The KVM pointer + * @guest_ipa: The IPA at which to insert the mapping + * @pa: The physical address of the device + * @size: The size of the mapping + */ +int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, + phys_addr_t pa, unsigned long size, bool writable) +{ + phys_addr_t addr, end; + int ret = 0; + unsigned long pfn; + struct kvm_mmu_memory_cache cache = { 0, }; + + end = (guest_ipa + size + PAGE_SIZE - 1) & PAGE_MASK; + pfn = __phys_to_pfn(pa); + + for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) { + pte_t pte = kvm_pfn_pte(pfn, PAGE_S2_DEVICE); + + if (writable) + pte = kvm_s2pte_mkwrite(pte); + + ret = mmu_topup_memory_cache(&cache, + kvm_mmu_cache_min_pages(kvm), + KVM_NR_MEM_OBJS); + if (ret) + goto out; + spin_lock(&kvm->mmu_lock); + ret = stage2_set_pte(kvm, &cache, addr, &pte, + KVM_S2PTE_FLAG_IS_IOMAP); + spin_unlock(&kvm->mmu_lock); + if (ret) + goto out; + + pfn++; + } + +out: + mmu_free_memory_cache(&cache); + return ret; +} + +/** + * stage2_wp_ptes - write protect PMD range + * @pmd: pointer to pmd entry + * @addr: range start address + * @end: range end address + */ +static void stage2_wp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end) +{ + pte_t *pte; + + pte = pte_offset_kernel(pmd, addr); + do { + if (!pte_none(*pte)) { + if (!kvm_s2pte_readonly(pte)) + kvm_set_s2pte_readonly(pte); + } + } while (pte++, addr += PAGE_SIZE, addr != end); +} + +/** + * stage2_wp_pmds - write protect PUD range + * kvm: kvm instance for the VM + * @pud: pointer to pud entry + * @addr: range start address + * @end: range end address + */ +static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud, + phys_addr_t addr, phys_addr_t end) +{ + pmd_t *pmd; + phys_addr_t next; + + pmd = stage2_pmd_offset(kvm, pud, addr); + + do { + next = stage2_pmd_addr_end(kvm, addr, end); + if (!pmd_none(*pmd)) { + if (pmd_thp_or_huge(*pmd)) { + if (!kvm_s2pmd_readonly(pmd)) + kvm_set_s2pmd_readonly(pmd); + } else { + stage2_wp_ptes(pmd, addr, next); + } + } + } while (pmd++, addr = next, addr != end); +} + +/** + * stage2_wp_puds - write protect PGD range + * @pgd: pointer to pgd entry + * @addr: range start address + * @end: range end address + */ +static void stage2_wp_puds(struct kvm *kvm, pgd_t *pgd, + phys_addr_t addr, phys_addr_t end) +{ + pud_t *pud; + phys_addr_t next; + + pud = stage2_pud_offset(kvm, pgd, addr); + do { + next = stage2_pud_addr_end(kvm, addr, end); + if (!stage2_pud_none(kvm, *pud)) { + if (stage2_pud_huge(kvm, *pud)) { + if (!kvm_s2pud_readonly(pud)) + kvm_set_s2pud_readonly(pud); + } else { + stage2_wp_pmds(kvm, pud, addr, next); + } + } + } while (pud++, addr = next, addr != end); +} + +/** + * stage2_wp_range() - write protect stage2 memory region range + * @kvm: The KVM pointer + * @addr: Start address of range + * @end: End address of range + */ +static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) +{ + pgd_t *pgd; + phys_addr_t next; + + pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr); + do { + /* + * Release kvm_mmu_lock periodically if the memory region is + * large. Otherwise, we may see kernel panics with + * CONFIG_DETECT_HUNG_TASK, CONFIG_LOCKUP_DETECTOR, + * CONFIG_LOCKDEP. Additionally, holding the lock too long + * will also starve other vCPUs. We have to also make sure + * that the page tables are not freed while we released + * the lock. + */ + cond_resched_lock(&kvm->mmu_lock); + if (!READ_ONCE(kvm->arch.pgd)) + break; + next = stage2_pgd_addr_end(kvm, addr, end); + if (stage2_pgd_present(kvm, *pgd)) + stage2_wp_puds(kvm, pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + +/** + * kvm_mmu_wp_memory_region() - write protect stage 2 entries for memory slot + * @kvm: The KVM pointer + * @slot: The memory slot to write protect + * + * Called to start logging dirty pages after memory region + * KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns + * all present PUD, PMD and PTEs are write protected in the memory region. + * Afterwards read of dirty page log can be called. + * + * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired, + * serializing operations for VM memory regions. + */ +void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot) +{ + struct kvm_memslots *slots = kvm_memslots(kvm); + struct kvm_memory_slot *memslot = id_to_memslot(slots, slot); + phys_addr_t start, end; + + if (WARN_ON_ONCE(!memslot)) + return; + + start = memslot->base_gfn << PAGE_SHIFT; + end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; + + spin_lock(&kvm->mmu_lock); + stage2_wp_range(kvm, start, end); + spin_unlock(&kvm->mmu_lock); + kvm_flush_remote_tlbs(kvm); +} + +/** + * kvm_mmu_write_protect_pt_masked() - write protect dirty pages + * @kvm: The KVM pointer + * @slot: The memory slot associated with mask + * @gfn_offset: The gfn offset in memory slot + * @mask: The mask of dirty pages at offset 'gfn_offset' in this memory + * slot to be write protected + * + * Walks bits set in mask write protects the associated pte's. Caller must + * acquire kvm_mmu_lock. + */ +static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn_offset, unsigned long mask) +{ + phys_addr_t base_gfn = slot->base_gfn + gfn_offset; + phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT; + phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT; + + stage2_wp_range(kvm, start, end); +} + +/* + * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected + * dirty pages. + * + * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to + * enable dirty logging for them. + */ +void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn_offset, unsigned long mask) +{ + kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); +} + +static void clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size) +{ + __clean_dcache_guest_page(pfn, size); +} + +static void invalidate_icache_guest_page(kvm_pfn_t pfn, unsigned long size) +{ + __invalidate_icache_guest_page(pfn, size); +} + +static void kvm_send_hwpoison_signal(unsigned long address, short lsb) +{ + send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current); +} + +static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot, + unsigned long hva, + unsigned long map_size) +{ + gpa_t gpa_start; + hva_t uaddr_start, uaddr_end; + size_t size; + + /* The memslot and the VMA are guaranteed to be aligned to PAGE_SIZE */ + if (map_size == PAGE_SIZE) + return true; + + size = memslot->npages * PAGE_SIZE; + + gpa_start = memslot->base_gfn << PAGE_SHIFT; + + uaddr_start = memslot->userspace_addr; + uaddr_end = uaddr_start + size; + + /* + * Pages belonging to memslots that don't have the same alignment + * within a PMD/PUD for userspace and IPA cannot be mapped with stage-2 + * PMD/PUD entries, because we'll end up mapping the wrong pages. + * + * Consider a layout like the following: + * + * memslot->userspace_addr: + * +-----+--------------------+--------------------+---+ + * |abcde|fgh Stage-1 block | Stage-1 block tv|xyz| + * +-----+--------------------+--------------------+---+ + * + * memslot->base_gfn << PAGE_SHIFT: + * +---+--------------------+--------------------+-----+ + * |abc|def Stage-2 block | Stage-2 block |tvxyz| + * +---+--------------------+--------------------+-----+ + * + * If we create those stage-2 blocks, we'll end up with this incorrect + * mapping: + * d -> f + * e -> g + * f -> h + */ + if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1))) + return false; + + /* + * Next, let's make sure we're not trying to map anything not covered + * by the memslot. This means we have to prohibit block size mappings + * for the beginning and end of a non-block aligned and non-block sized + * memory slot (illustrated by the head and tail parts of the + * userspace view above containing pages 'abcde' and 'xyz', + * respectively). + * + * Note that it doesn't matter if we do the check using the + * userspace_addr or the base_gfn, as both are equally aligned (per + * the check above) and equally sized. + */ + return (hva & ~(map_size - 1)) >= uaddr_start && + (hva & ~(map_size - 1)) + map_size <= uaddr_end; +} + +/* + * Check if the given hva is backed by a transparent huge page (THP) and + * whether it can be mapped using block mapping in stage2. If so, adjust + * the stage2 PFN and IPA accordingly. Only PMD_SIZE THPs are currently + * supported. This will need to be updated to support other THP sizes. + * + * Returns the size of the mapping. + */ +static unsigned long +transparent_hugepage_adjust(struct kvm_memory_slot *memslot, + unsigned long hva, kvm_pfn_t *pfnp, + phys_addr_t *ipap) +{ + kvm_pfn_t pfn = *pfnp; + + /* + * Make sure the adjustment is done only for THP pages. Also make + * sure that the HVA and IPA are sufficiently aligned and that the + * block map is contained within the memslot. + */ + if (kvm_is_transparent_hugepage(pfn) && + fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) { + /* + * The address we faulted on is backed by a transparent huge + * page. However, because we map the compound huge page and + * not the individual tail page, we need to transfer the + * refcount to the head page. We have to be careful that the + * THP doesn't start to split while we are adjusting the + * refcounts. + * + * We are sure this doesn't happen, because mmu_notifier_retry + * was successful and we are holding the mmu_lock, so if this + * THP is trying to split, it will be blocked in the mmu + * notifier before touching any of the pages, specifically + * before being able to call __split_huge_page_refcount(). + * + * We can therefore safely transfer the refcount from PG_tail + * to PG_head and switch the pfn from a tail page to the head + * page accordingly. + */ + *ipap &= PMD_MASK; + kvm_release_pfn_clean(pfn); + pfn &= ~(PTRS_PER_PMD - 1); + kvm_get_pfn(pfn); + *pfnp = pfn; + + return PMD_SIZE; + } + + /* Use page mapping if we cannot use block mapping. */ + return PAGE_SIZE; +} + +static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, + struct kvm_memory_slot *memslot, unsigned long hva, + unsigned long fault_status) +{ + int ret; + bool write_fault, writable, force_pte = false; + bool exec_fault, needs_exec; + unsigned long mmu_seq; + gfn_t gfn = fault_ipa >> PAGE_SHIFT; + struct kvm *kvm = vcpu->kvm; + struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; + struct vm_area_struct *vma; + short vma_shift; + kvm_pfn_t pfn; + pgprot_t mem_type = PAGE_S2; + bool logging_active = memslot_is_logging(memslot); + unsigned long vma_pagesize, flags = 0; + + write_fault = kvm_is_write_fault(vcpu); + exec_fault = kvm_vcpu_trap_is_iabt(vcpu); + VM_BUG_ON(write_fault && exec_fault); + + if (fault_status == FSC_PERM && !write_fault && !exec_fault) { + kvm_err("Unexpected L2 read permission error\n"); + return -EFAULT; + } + + /* Let's check if we will get back a huge page backed by hugetlbfs */ + down_read(¤t->mm->mmap_sem); + vma = find_vma_intersection(current->mm, hva, hva + 1); + if (unlikely(!vma)) { + kvm_err("Failed to find VMA for hva 0x%lx\n", hva); + up_read(¤t->mm->mmap_sem); + return -EFAULT; + } + + if (is_vm_hugetlb_page(vma)) + vma_shift = huge_page_shift(hstate_vma(vma)); + else + vma_shift = PAGE_SHIFT; + + vma_pagesize = 1ULL << vma_shift; + if (logging_active || + (vma->vm_flags & VM_PFNMAP) || + !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) { + force_pte = true; + vma_pagesize = PAGE_SIZE; + } + + /* + * The stage2 has a minimum of 2 level table (For arm64 see + * kvm_arm_setup_stage2()). Hence, we are guaranteed that we can + * use PMD_SIZE huge mappings (even when the PMD is folded into PGD). + * As for PUD huge maps, we must make sure that we have at least + * 3 levels, i.e, PMD is not folded. + */ + if (vma_pagesize == PMD_SIZE || + (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm))) + gfn = (fault_ipa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT; + up_read(¤t->mm->mmap_sem); + + /* We need minimum second+third level pages */ + ret = mmu_topup_memory_cache(memcache, kvm_mmu_cache_min_pages(kvm), + KVM_NR_MEM_OBJS); + if (ret) + return ret; + + mmu_seq = vcpu->kvm->mmu_notifier_seq; + /* + * Ensure the read of mmu_notifier_seq happens before we call + * gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk + * the page we just got a reference to gets unmapped before we have a + * chance to grab the mmu_lock, which ensure that if the page gets + * unmapped afterwards, the call to kvm_unmap_hva will take it away + * from us again properly. This smp_rmb() interacts with the smp_wmb() + * in kvm_mmu_notifier_invalidate_<page|range_end>. + */ + smp_rmb(); + + pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable); + if (pfn == KVM_PFN_ERR_HWPOISON) { + kvm_send_hwpoison_signal(hva, vma_shift); + return 0; + } + if (is_error_noslot_pfn(pfn)) + return -EFAULT; + + if (kvm_is_device_pfn(pfn)) { + mem_type = PAGE_S2_DEVICE; + flags |= KVM_S2PTE_FLAG_IS_IOMAP; + } else if (logging_active) { + /* + * Faults on pages in a memslot with logging enabled + * should not be mapped with huge pages (it introduces churn + * and performance degradation), so force a pte mapping. + */ + flags |= KVM_S2_FLAG_LOGGING_ACTIVE; + + /* + * Only actually map the page as writable if this was a write + * fault. + */ + if (!write_fault) + writable = false; + } + + if (exec_fault && is_iomap(flags)) + return -ENOEXEC; + + spin_lock(&kvm->mmu_lock); + if (mmu_notifier_retry(kvm, mmu_seq)) + goto out_unlock; + + /* + * If we are not forced to use page mapping, check if we are + * backed by a THP and thus use block mapping if possible. + */ + if (vma_pagesize == PAGE_SIZE && !force_pte) + vma_pagesize = transparent_hugepage_adjust(memslot, hva, + &pfn, &fault_ipa); + if (writable) + kvm_set_pfn_dirty(pfn); + + if (fault_status != FSC_PERM && !is_iomap(flags)) + clean_dcache_guest_page(pfn, vma_pagesize); + + if (exec_fault) + invalidate_icache_guest_page(pfn, vma_pagesize); + + /* + * If we took an execution fault we have made the + * icache/dcache coherent above and should now let the s2 + * mapping be executable. + * + * Write faults (!exec_fault && FSC_PERM) are orthogonal to + * execute permissions, and we preserve whatever we have. + */ + needs_exec = exec_fault || + (fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa)); + + if (vma_pagesize == PUD_SIZE) { + pud_t new_pud = kvm_pfn_pud(pfn, mem_type); + + new_pud = kvm_pud_mkhuge(new_pud); + if (writable) + new_pud = kvm_s2pud_mkwrite(new_pud); + + if (needs_exec) + new_pud = kvm_s2pud_mkexec(new_pud); + + ret = stage2_set_pud_huge(kvm, memcache, fault_ipa, &new_pud); + } else if (vma_pagesize == PMD_SIZE) { + pmd_t new_pmd = kvm_pfn_pmd(pfn, mem_type); + + new_pmd = kvm_pmd_mkhuge(new_pmd); + + if (writable) + new_pmd = kvm_s2pmd_mkwrite(new_pmd); + + if (needs_exec) + new_pmd = kvm_s2pmd_mkexec(new_pmd); + + ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); + } else { + pte_t new_pte = kvm_pfn_pte(pfn, mem_type); + + if (writable) { + new_pte = kvm_s2pte_mkwrite(new_pte); + mark_page_dirty(kvm, gfn); + } + + if (needs_exec) + new_pte = kvm_s2pte_mkexec(new_pte); + + ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags); + } + +out_unlock: + spin_unlock(&kvm->mmu_lock); + kvm_set_pfn_accessed(pfn); + kvm_release_pfn_clean(pfn); + return ret; +} + +/* + * Resolve the access fault by making the page young again. + * Note that because the faulting entry is guaranteed not to be + * cached in the TLB, we don't need to invalidate anything. + * Only the HW Access Flag updates are supported for Stage 2 (no DBM), + * so there is no need for atomic (pte|pmd)_mkyoung operations. + */ +static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) +{ + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + kvm_pfn_t pfn; + bool pfn_valid = false; + + trace_kvm_access_fault(fault_ipa); + + spin_lock(&vcpu->kvm->mmu_lock); + + if (!stage2_get_leaf_entry(vcpu->kvm, fault_ipa, &pud, &pmd, &pte)) + goto out; + + if (pud) { /* HugeTLB */ + *pud = kvm_s2pud_mkyoung(*pud); + pfn = kvm_pud_pfn(*pud); + pfn_valid = true; + } else if (pmd) { /* THP, HugeTLB */ + *pmd = pmd_mkyoung(*pmd); + pfn = pmd_pfn(*pmd); + pfn_valid = true; + } else { + *pte = pte_mkyoung(*pte); /* Just a page... */ + pfn = pte_pfn(*pte); + pfn_valid = true; + } + +out: + spin_unlock(&vcpu->kvm->mmu_lock); + if (pfn_valid) + kvm_set_pfn_accessed(pfn); +} + +/** + * kvm_handle_guest_abort - handles all 2nd stage aborts + * @vcpu: the VCPU pointer + * @run: the kvm_run structure + * + * Any abort that gets to the host is almost guaranteed to be caused by a + * missing second stage translation table entry, which can mean that either the + * guest simply needs more memory and we must allocate an appropriate page or it + * can mean that the guest tried to access I/O memory, which is emulated by user + * space. The distinction is based on the IPA causing the fault and whether this + * memory region has been registered as standard RAM by user space. + */ +int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + unsigned long fault_status; + phys_addr_t fault_ipa; + struct kvm_memory_slot *memslot; + unsigned long hva; + bool is_iabt, write_fault, writable; + gfn_t gfn; + int ret, idx; + + fault_status = kvm_vcpu_trap_get_fault_type(vcpu); + + fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); + is_iabt = kvm_vcpu_trap_is_iabt(vcpu); + + /* Synchronous External Abort? */ + if (kvm_vcpu_dabt_isextabt(vcpu)) { + /* + * For RAS the host kernel may handle this abort. + * There is no need to pass the error into the guest. + */ + if (!kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_hsr(vcpu))) + return 1; + + if (unlikely(!is_iabt)) { + kvm_inject_vabt(vcpu); + return 1; + } + } + + trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu), + kvm_vcpu_get_hfar(vcpu), fault_ipa); + + /* Check the stage-2 fault is trans. fault or write fault */ + if (fault_status != FSC_FAULT && fault_status != FSC_PERM && + fault_status != FSC_ACCESS) { + kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", + kvm_vcpu_trap_get_class(vcpu), + (unsigned long)kvm_vcpu_trap_get_fault(vcpu), + (unsigned long)kvm_vcpu_get_hsr(vcpu)); + return -EFAULT; + } + + idx = srcu_read_lock(&vcpu->kvm->srcu); + + gfn = fault_ipa >> PAGE_SHIFT; + memslot = gfn_to_memslot(vcpu->kvm, gfn); + hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable); + write_fault = kvm_is_write_fault(vcpu); + if (kvm_is_error_hva(hva) || (write_fault && !writable)) { + if (is_iabt) { + /* Prefetch Abort on I/O address */ + ret = -ENOEXEC; + goto out; + } + + /* + * Check for a cache maintenance operation. Since we + * ended-up here, we know it is outside of any memory + * slot. But we can't find out if that is for a device, + * or if the guest is just being stupid. The only thing + * we know for sure is that this range cannot be cached. + * + * So let's assume that the guest is just being + * cautious, and skip the instruction. + */ + if (kvm_vcpu_dabt_is_cm(vcpu)) { + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + ret = 1; + goto out_unlock; + } + + /* + * The IPA is reported as [MAX:12], so we need to + * complement it with the bottom 12 bits from the + * faulting VA. This is always 12 bits, irrespective + * of the page size. + */ + fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1); + ret = io_mem_abort(vcpu, run, fault_ipa); + goto out_unlock; + } + + /* Userspace should not be able to register out-of-bounds IPAs */ + VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm)); + + if (fault_status == FSC_ACCESS) { + handle_access_fault(vcpu, fault_ipa); + ret = 1; + goto out_unlock; + } + + ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status); + if (ret == 0) + ret = 1; +out: + if (ret == -ENOEXEC) { + kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + ret = 1; + } +out_unlock: + srcu_read_unlock(&vcpu->kvm->srcu, idx); + return ret; +} + +static int handle_hva_to_gpa(struct kvm *kvm, + unsigned long start, + unsigned long end, + int (*handler)(struct kvm *kvm, + gpa_t gpa, u64 size, + void *data), + void *data) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int ret = 0; + + slots = kvm_memslots(kvm); + + /* we only care about the pages that the guest sees */ + kvm_for_each_memslot(memslot, slots) { + unsigned long hva_start, hva_end; + gfn_t gpa; + + hva_start = max(start, memslot->userspace_addr); + hva_end = min(end, memslot->userspace_addr + + (memslot->npages << PAGE_SHIFT)); + if (hva_start >= hva_end) + continue; + + gpa = hva_to_gfn_memslot(hva_start, memslot) << PAGE_SHIFT; + ret |= handler(kvm, gpa, (u64)(hva_end - hva_start), data); + } + + return ret; +} + +static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data) +{ + unmap_stage2_range(kvm, gpa, size); + return 0; +} + +int kvm_unmap_hva_range(struct kvm *kvm, + unsigned long start, unsigned long end) +{ + if (!kvm->arch.pgd) + return 0; + + trace_kvm_unmap_hva_range(start, end); + handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); + return 0; +} + +static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data) +{ + pte_t *pte = (pte_t *)data; + + WARN_ON(size != PAGE_SIZE); + /* + * We can always call stage2_set_pte with KVM_S2PTE_FLAG_LOGGING_ACTIVE + * flag clear because MMU notifiers will have unmapped a huge PMD before + * calling ->change_pte() (which in turn calls kvm_set_spte_hva()) and + * therefore stage2_set_pte() never needs to clear out a huge PMD + * through this calling path. + */ + stage2_set_pte(kvm, NULL, gpa, pte, 0); + return 0; +} + + +int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) +{ + unsigned long end = hva + PAGE_SIZE; + kvm_pfn_t pfn = pte_pfn(pte); + pte_t stage2_pte; + + if (!kvm->arch.pgd) + return 0; + + trace_kvm_set_spte_hva(hva); + + /* + * We've moved a page around, probably through CoW, so let's treat it + * just like a translation fault and clean the cache to the PoC. + */ + clean_dcache_guest_page(pfn, PAGE_SIZE); + stage2_pte = kvm_pfn_pte(pfn, PAGE_S2); + handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte); + + return 0; +} + +static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data) +{ + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); + if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte)) + return 0; + + if (pud) + return stage2_pudp_test_and_clear_young(pud); + else if (pmd) + return stage2_pmdp_test_and_clear_young(pmd); + else + return stage2_ptep_test_and_clear_young(pte); +} + +static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data) +{ + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); + if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte)) + return 0; + + if (pud) + return kvm_s2pud_young(*pud); + else if (pmd) + return pmd_young(*pmd); + else + return pte_young(*pte); +} + +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) +{ + if (!kvm->arch.pgd) + return 0; + trace_kvm_age_hva(start, end); + return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL); +} + +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +{ + if (!kvm->arch.pgd) + return 0; + trace_kvm_test_age_hva(hva); + return handle_hva_to_gpa(kvm, hva, hva + PAGE_SIZE, + kvm_test_age_hva_handler, NULL); +} + +void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu) +{ + mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); +} + +phys_addr_t kvm_mmu_get_httbr(void) +{ + if (__kvm_cpu_uses_extended_idmap()) + return virt_to_phys(merged_hyp_pgd); + else + return virt_to_phys(hyp_pgd); +} + +phys_addr_t kvm_get_idmap_vector(void) +{ + return hyp_idmap_vector; +} + +static int kvm_map_idmap_text(pgd_t *pgd) +{ + int err; + + /* Create the idmap in the boot page tables */ + err = __create_hyp_mappings(pgd, __kvm_idmap_ptrs_per_pgd(), + hyp_idmap_start, hyp_idmap_end, + __phys_to_pfn(hyp_idmap_start), + PAGE_HYP_EXEC); + if (err) + kvm_err("Failed to idmap %lx-%lx\n", + hyp_idmap_start, hyp_idmap_end); + + return err; +} + +int kvm_mmu_init(void) +{ + int err; + + hyp_idmap_start = __pa_symbol(__hyp_idmap_text_start); + hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE); + hyp_idmap_end = __pa_symbol(__hyp_idmap_text_end); + hyp_idmap_end = ALIGN(hyp_idmap_end, PAGE_SIZE); + hyp_idmap_vector = __pa_symbol(__kvm_hyp_init); + + /* + * We rely on the linker script to ensure at build time that the HYP + * init code does not cross a page boundary. + */ + BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK); + + kvm_debug("IDMAP page: %lx\n", hyp_idmap_start); + kvm_debug("HYP VA range: %lx:%lx\n", + kern_hyp_va(PAGE_OFFSET), + kern_hyp_va((unsigned long)high_memory - 1)); + + if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) && + hyp_idmap_start < kern_hyp_va((unsigned long)high_memory - 1) && + hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) { + /* + * The idmap page is intersecting with the VA space, + * it is not safe to continue further. + */ + kvm_err("IDMAP intersecting with HYP VA, unable to continue\n"); + err = -EINVAL; + goto out; + } + + hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order); + if (!hyp_pgd) { + kvm_err("Hyp mode PGD not allocated\n"); + err = -ENOMEM; + goto out; + } + + if (__kvm_cpu_uses_extended_idmap()) { + boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + hyp_pgd_order); + if (!boot_hyp_pgd) { + kvm_err("Hyp boot PGD not allocated\n"); + err = -ENOMEM; + goto out; + } + + err = kvm_map_idmap_text(boot_hyp_pgd); + if (err) + goto out; + + merged_hyp_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!merged_hyp_pgd) { + kvm_err("Failed to allocate extra HYP pgd\n"); + goto out; + } + __kvm_extend_hypmap(boot_hyp_pgd, hyp_pgd, merged_hyp_pgd, + hyp_idmap_start); + } else { + err = kvm_map_idmap_text(hyp_pgd); + if (err) + goto out; + } + + io_map_base = hyp_idmap_start; + return 0; +out: + free_hyp_pgds(); + return err; +} + +void kvm_arch_commit_memory_region(struct kvm *kvm, + const struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + enum kvm_mr_change change) +{ + /* + * At this point memslot has been committed and there is an + * allocated dirty_bitmap[], dirty pages will be tracked while the + * memory slot is write protected. + */ + if (change != KVM_MR_DELETE && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) { + /* + * If we're with initial-all-set, we don't need to write + * protect any pages because they're all reported as dirty. + * Huge pages and normal pages will be write protect gradually. + */ + if (!kvm_dirty_log_manual_protect_and_init_set(kvm)) { + kvm_mmu_wp_memory_region(kvm, mem->slot); + } + } +} + +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, + const struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change) +{ + hva_t hva = mem->userspace_addr; + hva_t reg_end = hva + mem->memory_size; + bool writable = !(mem->flags & KVM_MEM_READONLY); + int ret = 0; + + if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && + change != KVM_MR_FLAGS_ONLY) + return 0; + + /* + * Prevent userspace from creating a memory region outside of the IPA + * space addressable by the KVM guest IPA space. + */ + if (memslot->base_gfn + memslot->npages >= + (kvm_phys_size(kvm) >> PAGE_SHIFT)) + return -EFAULT; + + down_read(¤t->mm->mmap_sem); + /* + * A memory region could potentially cover multiple VMAs, and any holes + * between them, so iterate over all of them to find out if we can map + * any of them right now. + * + * +--------------------------------------------+ + * +---------------+----------------+ +----------------+ + * | : VMA 1 | VMA 2 | | VMA 3 : | + * +---------------+----------------+ +----------------+ + * | memory region | + * +--------------------------------------------+ + */ + do { + struct vm_area_struct *vma = find_vma(current->mm, hva); + hva_t vm_start, vm_end; + + if (!vma || vma->vm_start >= reg_end) + break; + + /* + * Take the intersection of this VMA with the memory region + */ + vm_start = max(hva, vma->vm_start); + vm_end = min(reg_end, vma->vm_end); + + if (vma->vm_flags & VM_PFNMAP) { + gpa_t gpa = mem->guest_phys_addr + + (vm_start - mem->userspace_addr); + phys_addr_t pa; + + pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; + pa += vm_start - vma->vm_start; + + /* IO region dirty page logging not allowed */ + if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + ret = -EINVAL; + goto out; + } + + ret = kvm_phys_addr_ioremap(kvm, gpa, pa, + vm_end - vm_start, + writable); + if (ret) + break; + } + hva = vm_end; + } while (hva < reg_end); + + if (change == KVM_MR_FLAGS_ONLY) + goto out; + + spin_lock(&kvm->mmu_lock); + if (ret) + unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size); + else + stage2_flush_memslot(kvm, memslot); + spin_unlock(&kvm->mmu_lock); +out: + up_read(¤t->mm->mmap_sem); + return ret; +} + +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) +{ +} + +void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) +{ +} + +void kvm_arch_flush_shadow_all(struct kvm *kvm) +{ + kvm_free_stage2_pgd(kvm); +} + +void kvm_arch_flush_shadow_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + gpa_t gpa = slot->base_gfn << PAGE_SHIFT; + phys_addr_t size = slot->npages << PAGE_SHIFT; + + spin_lock(&kvm->mmu_lock); + unmap_stage2_range(kvm, gpa, size); + spin_unlock(&kvm->mmu_lock); +} + +/* + * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). + * + * Main problems: + * - S/W ops are local to a CPU (not broadcast) + * - We have line migration behind our back (speculation) + * - System caches don't support S/W at all (damn!) + * + * In the face of the above, the best we can do is to try and convert + * S/W ops to VA ops. Because the guest is not allowed to infer the + * S/W to PA mapping, it can only use S/W to nuke the whole cache, + * which is a rather good thing for us. + * + * Also, it is only used when turning caches on/off ("The expected + * usage of the cache maintenance instructions that operate by set/way + * is associated with the cache maintenance instructions associated + * with the powerdown and powerup of caches, if this is required by + * the implementation."). + * + * We use the following policy: + * + * - If we trap a S/W operation, we enable VM trapping to detect + * caches being turned on/off, and do a full clean. + * + * - We flush the caches on both caches being turned on and off. + * + * - Once the caches are enabled, we stop trapping VM ops. + */ +void kvm_set_way_flush(struct kvm_vcpu *vcpu) +{ + unsigned long hcr = *vcpu_hcr(vcpu); + + /* + * If this is the first time we do a S/W operation + * (i.e. HCR_TVM not set) flush the whole memory, and set the + * VM trapping. + * + * Otherwise, rely on the VM trapping to wait for the MMU + + * Caches to be turned off. At that point, we'll be able to + * clean the caches again. + */ + if (!(hcr & HCR_TVM)) { + trace_kvm_set_way_flush(*vcpu_pc(vcpu), + vcpu_has_cache_enabled(vcpu)); + stage2_flush_vm(vcpu->kvm); + *vcpu_hcr(vcpu) = hcr | HCR_TVM; + } +} + +void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled) +{ + bool now_enabled = vcpu_has_cache_enabled(vcpu); + + /* + * If switching the MMU+caches on, need to invalidate the caches. + * If switching it off, need to clean the caches. + * Clean + invalidate does the trick always. + */ + if (now_enabled != was_enabled) + stage2_flush_vm(vcpu->kvm); + + /* Caches are now on, stop trapping VM ops (until a S/W op) */ + if (now_enabled) + *vcpu_hcr(vcpu) &= ~HCR_TVM; + + trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled); +} diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c new file mode 100644 index 000000000000..d45b8b9a4415 --- /dev/null +++ b/arch/arm64/kvm/perf.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Based on the x86 implementation. + * + * Copyright (C) 2012 ARM Ltd. + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <linux/perf_event.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_emulate.h> + +static int kvm_is_in_guest(void) +{ + return kvm_get_running_vcpu() != NULL; +} + +static int kvm_is_user_mode(void) +{ + struct kvm_vcpu *vcpu; + + vcpu = kvm_get_running_vcpu(); + + if (vcpu) + return !vcpu_mode_priv(vcpu); + + return 0; +} + +static unsigned long kvm_get_guest_ip(void) +{ + struct kvm_vcpu *vcpu; + + vcpu = kvm_get_running_vcpu(); + + if (vcpu) + return *vcpu_pc(vcpu); + + return 0; +} + +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, +}; + +int kvm_perf_init(void) +{ + return perf_register_guest_info_callbacks(&kvm_guest_cbs); +} + +int kvm_perf_teardown(void) +{ + return perf_unregister_guest_info_callbacks(&kvm_guest_cbs); +} diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c new file mode 100644 index 000000000000..f0d0312c0a55 --- /dev/null +++ b/arch/arm64/kvm/pmu-emul.c @@ -0,0 +1,869 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 Linaro Ltd. + * Author: Shannon Zhao <shannon.zhao@linaro.org> + */ + +#include <linux/cpu.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/perf_event.h> +#include <linux/perf/arm_pmu.h> +#include <linux/uaccess.h> +#include <asm/kvm_emulate.h> +#include <kvm/arm_pmu.h> +#include <kvm/arm_vgic.h> + +static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx); +static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx); +static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc); + +#define PERF_ATTR_CFG1_KVM_PMU_CHAINED 0x1 + +/** + * kvm_pmu_idx_is_64bit - determine if select_idx is a 64bit counter + * @vcpu: The vcpu pointer + * @select_idx: The counter index + */ +static bool kvm_pmu_idx_is_64bit(struct kvm_vcpu *vcpu, u64 select_idx) +{ + return (select_idx == ARMV8_PMU_CYCLE_IDX && + __vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_LC); +} + +static struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu; + struct kvm_vcpu_arch *vcpu_arch; + + pmc -= pmc->idx; + pmu = container_of(pmc, struct kvm_pmu, pmc[0]); + vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu); + return container_of(vcpu_arch, struct kvm_vcpu, arch); +} + +/** + * kvm_pmu_pmc_is_chained - determine if the pmc is chained + * @pmc: The PMU counter pointer + */ +static bool kvm_pmu_pmc_is_chained(struct kvm_pmc *pmc) +{ + struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); + + return test_bit(pmc->idx >> 1, vcpu->arch.pmu.chained); +} + +/** + * kvm_pmu_idx_is_high_counter - determine if select_idx is a high/low counter + * @select_idx: The counter index + */ +static bool kvm_pmu_idx_is_high_counter(u64 select_idx) +{ + return select_idx & 0x1; +} + +/** + * kvm_pmu_get_canonical_pmc - obtain the canonical pmc + * @pmc: The PMU counter pointer + * + * When a pair of PMCs are chained together we use the low counter (canonical) + * to hold the underlying perf event. + */ +static struct kvm_pmc *kvm_pmu_get_canonical_pmc(struct kvm_pmc *pmc) +{ + if (kvm_pmu_pmc_is_chained(pmc) && + kvm_pmu_idx_is_high_counter(pmc->idx)) + return pmc - 1; + + return pmc; +} +static struct kvm_pmc *kvm_pmu_get_alternate_pmc(struct kvm_pmc *pmc) +{ + if (kvm_pmu_idx_is_high_counter(pmc->idx)) + return pmc - 1; + else + return pmc + 1; +} + +/** + * kvm_pmu_idx_has_chain_evtype - determine if the event type is chain + * @vcpu: The vcpu pointer + * @select_idx: The counter index + */ +static bool kvm_pmu_idx_has_chain_evtype(struct kvm_vcpu *vcpu, u64 select_idx) +{ + u64 eventsel, reg; + + select_idx |= 0x1; + + if (select_idx == ARMV8_PMU_CYCLE_IDX) + return false; + + reg = PMEVTYPER0_EL0 + select_idx; + eventsel = __vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_EVENT; + + return eventsel == ARMV8_PMUV3_PERFCTR_CHAIN; +} + +/** + * kvm_pmu_get_pair_counter_value - get PMU counter value + * @vcpu: The vcpu pointer + * @pmc: The PMU counter pointer + */ +static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu, + struct kvm_pmc *pmc) +{ + u64 counter, counter_high, reg, enabled, running; + + if (kvm_pmu_pmc_is_chained(pmc)) { + pmc = kvm_pmu_get_canonical_pmc(pmc); + reg = PMEVCNTR0_EL0 + pmc->idx; + + counter = __vcpu_sys_reg(vcpu, reg); + counter_high = __vcpu_sys_reg(vcpu, reg + 1); + + counter = lower_32_bits(counter) | (counter_high << 32); + } else { + reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX) + ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx; + counter = __vcpu_sys_reg(vcpu, reg); + } + + /* + * The real counter value is equal to the value of counter register plus + * the value perf event counts. + */ + if (pmc->perf_event) + counter += perf_event_read_value(pmc->perf_event, &enabled, + &running); + + return counter; +} + +/** + * kvm_pmu_get_counter_value - get PMU counter value + * @vcpu: The vcpu pointer + * @select_idx: The counter index + */ +u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) +{ + u64 counter; + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmc *pmc = &pmu->pmc[select_idx]; + + counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); + + if (kvm_pmu_pmc_is_chained(pmc) && + kvm_pmu_idx_is_high_counter(select_idx)) + counter = upper_32_bits(counter); + else if (select_idx != ARMV8_PMU_CYCLE_IDX) + counter = lower_32_bits(counter); + + return counter; +} + +/** + * kvm_pmu_set_counter_value - set PMU counter value + * @vcpu: The vcpu pointer + * @select_idx: The counter index + * @val: The counter value + */ +void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) +{ + u64 reg; + + reg = (select_idx == ARMV8_PMU_CYCLE_IDX) + ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx; + __vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx); + + /* Recreate the perf event to reflect the updated sample_period */ + kvm_pmu_create_perf_event(vcpu, select_idx); +} + +/** + * kvm_pmu_release_perf_event - remove the perf event + * @pmc: The PMU counter pointer + */ +static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) +{ + pmc = kvm_pmu_get_canonical_pmc(pmc); + if (pmc->perf_event) { + perf_event_disable(pmc->perf_event); + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + } +} + +/** + * kvm_pmu_stop_counter - stop PMU counter + * @pmc: The PMU counter pointer + * + * If this counter has been configured to monitor some event, release it here. + */ +static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc) +{ + u64 counter, reg, val; + + pmc = kvm_pmu_get_canonical_pmc(pmc); + if (!pmc->perf_event) + return; + + counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); + + if (pmc->idx == ARMV8_PMU_CYCLE_IDX) { + reg = PMCCNTR_EL0; + val = counter; + } else { + reg = PMEVCNTR0_EL0 + pmc->idx; + val = lower_32_bits(counter); + } + + __vcpu_sys_reg(vcpu, reg) = val; + + if (kvm_pmu_pmc_is_chained(pmc)) + __vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter); + + kvm_pmu_release_perf_event(pmc); +} + +/** + * kvm_pmu_vcpu_init - assign pmu counter idx for cpu + * @vcpu: The vcpu pointer + * + */ +void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_pmu *pmu = &vcpu->arch.pmu; + + for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) + pmu->pmc[i].idx = i; +} + +/** + * kvm_pmu_vcpu_reset - reset pmu state for cpu + * @vcpu: The vcpu pointer + * + */ +void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) +{ + unsigned long mask = kvm_pmu_valid_counter_mask(vcpu); + struct kvm_pmu *pmu = &vcpu->arch.pmu; + int i; + + for_each_set_bit(i, &mask, 32) + kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]); + + bitmap_zero(vcpu->arch.pmu.chained, ARMV8_PMU_MAX_COUNTER_PAIRS); +} + +/** + * kvm_pmu_vcpu_destroy - free perf event of PMU for cpu + * @vcpu: The vcpu pointer + * + */ +void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_pmu *pmu = &vcpu->arch.pmu; + + for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) + kvm_pmu_release_perf_event(&pmu->pmc[i]); +} + +u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu) +{ + u64 val = __vcpu_sys_reg(vcpu, PMCR_EL0) >> ARMV8_PMU_PMCR_N_SHIFT; + + val &= ARMV8_PMU_PMCR_N_MASK; + if (val == 0) + return BIT(ARMV8_PMU_CYCLE_IDX); + else + return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX); +} + +/** + * kvm_pmu_enable_counter_mask - enable selected PMU counters + * @vcpu: The vcpu pointer + * @val: the value guest writes to PMCNTENSET register + * + * Call perf_event_enable to start counting the perf event + */ +void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) +{ + int i; + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmc *pmc; + + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val) + return; + + for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { + if (!(val & BIT(i))) + continue; + + pmc = &pmu->pmc[i]; + + /* A change in the enable state may affect the chain state */ + kvm_pmu_update_pmc_chained(vcpu, i); + kvm_pmu_create_perf_event(vcpu, i); + + /* At this point, pmc must be the canonical */ + if (pmc->perf_event) { + perf_event_enable(pmc->perf_event); + if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) + kvm_debug("fail to enable perf event\n"); + } + } +} + +/** + * kvm_pmu_disable_counter_mask - disable selected PMU counters + * @vcpu: The vcpu pointer + * @val: the value guest writes to PMCNTENCLR register + * + * Call perf_event_disable to stop counting the perf event + */ +void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) +{ + int i; + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmc *pmc; + + if (!val) + return; + + for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { + if (!(val & BIT(i))) + continue; + + pmc = &pmu->pmc[i]; + + /* A change in the enable state may affect the chain state */ + kvm_pmu_update_pmc_chained(vcpu, i); + kvm_pmu_create_perf_event(vcpu, i); + + /* At this point, pmc must be the canonical */ + if (pmc->perf_event) + perf_event_disable(pmc->perf_event); + } +} + +static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu) +{ + u64 reg = 0; + + if ((__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) { + reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0); + reg &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); + reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1); + reg &= kvm_pmu_valid_counter_mask(vcpu); + } + + return reg; +} + +static void kvm_pmu_update_state(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + bool overflow; + + if (!kvm_arm_pmu_v3_ready(vcpu)) + return; + + overflow = !!kvm_pmu_overflow_status(vcpu); + if (pmu->irq_level == overflow) + return; + + pmu->irq_level = overflow; + + if (likely(irqchip_in_kernel(vcpu->kvm))) { + int ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, + pmu->irq_num, overflow, pmu); + WARN_ON(ret); + } +} + +bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_sync_regs *sregs = &vcpu->run->s.regs; + bool run_level = sregs->device_irq_level & KVM_ARM_DEV_PMU; + + if (likely(irqchip_in_kernel(vcpu->kvm))) + return false; + + return pmu->irq_level != run_level; +} + +/* + * Reflect the PMU overflow interrupt output level into the kvm_run structure + */ +void kvm_pmu_update_run(struct kvm_vcpu *vcpu) +{ + struct kvm_sync_regs *regs = &vcpu->run->s.regs; + + /* Populate the timer bitmap for user space */ + regs->device_irq_level &= ~KVM_ARM_DEV_PMU; + if (vcpu->arch.pmu.irq_level) + regs->device_irq_level |= KVM_ARM_DEV_PMU; +} + +/** + * kvm_pmu_flush_hwstate - flush pmu state to cpu + * @vcpu: The vcpu pointer + * + * Check if the PMU has overflowed while we were running in the host, and inject + * an interrupt if that was the case. + */ +void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) +{ + kvm_pmu_update_state(vcpu); +} + +/** + * kvm_pmu_sync_hwstate - sync pmu state from cpu + * @vcpu: The vcpu pointer + * + * Check if the PMU has overflowed while we were running in the guest, and + * inject an interrupt if that was the case. + */ +void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) +{ + kvm_pmu_update_state(vcpu); +} + +/** + * When the perf event overflows, set the overflow status and inform the vcpu. + */ +static void kvm_pmu_perf_overflow(struct perf_event *perf_event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct kvm_pmc *pmc = perf_event->overflow_handler_context; + struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu); + struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); + int idx = pmc->idx; + u64 period; + + cpu_pmu->pmu.stop(perf_event, PERF_EF_UPDATE); + + /* + * Reset the sample period to the architectural limit, + * i.e. the point where the counter overflows. + */ + period = -(local64_read(&perf_event->count)); + + if (!kvm_pmu_idx_is_64bit(vcpu, pmc->idx)) + period &= GENMASK(31, 0); + + local64_set(&perf_event->hw.period_left, 0); + perf_event->attr.sample_period = period; + perf_event->hw.sample_period = period; + + __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx); + + if (kvm_pmu_overflow_status(vcpu)) { + kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); + kvm_vcpu_kick(vcpu); + } + + cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD); +} + +/** + * kvm_pmu_software_increment - do software increment + * @vcpu: The vcpu pointer + * @val: the value guest writes to PMSWINC register + */ +void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + int i; + + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) + return; + + /* Weed out disabled counters */ + val &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); + + for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++) { + u64 type, reg; + + if (!(val & BIT(i))) + continue; + + /* PMSWINC only applies to ... SW_INC! */ + type = __vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i); + type &= ARMV8_PMU_EVTYPE_EVENT; + if (type != ARMV8_PMUV3_PERFCTR_SW_INCR) + continue; + + /* increment this even SW_INC counter */ + reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1; + reg = lower_32_bits(reg); + __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg; + + if (reg) /* no overflow on the low part */ + continue; + + if (kvm_pmu_pmc_is_chained(&pmu->pmc[i])) { + /* increment the high counter */ + reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i + 1) + 1; + reg = lower_32_bits(reg); + __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i + 1) = reg; + if (!reg) /* mark overflow on the high counter */ + __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i + 1); + } else { + /* mark overflow on low counter */ + __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i); + } + } +} + +/** + * kvm_pmu_handle_pmcr - handle PMCR register + * @vcpu: The vcpu pointer + * @val: the value guest writes to PMCR register + */ +void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) +{ + unsigned long mask = kvm_pmu_valid_counter_mask(vcpu); + int i; + + if (val & ARMV8_PMU_PMCR_E) { + kvm_pmu_enable_counter_mask(vcpu, + __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask); + } else { + kvm_pmu_disable_counter_mask(vcpu, mask); + } + + if (val & ARMV8_PMU_PMCR_C) + kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); + + if (val & ARMV8_PMU_PMCR_P) { + for_each_set_bit(i, &mask, 32) + kvm_pmu_set_counter_value(vcpu, i, 0); + } +} + +static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx) +{ + return (__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) && + (__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(select_idx)); +} + +/** + * kvm_pmu_create_perf_event - create a perf event for a counter + * @vcpu: The vcpu pointer + * @select_idx: The number of selected counter + */ +static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmc *pmc; + struct perf_event *event; + struct perf_event_attr attr; + u64 eventsel, counter, reg, data; + + /* + * For chained counters the event type and filtering attributes are + * obtained from the low/even counter. We also use this counter to + * determine if the event is enabled/disabled. + */ + pmc = kvm_pmu_get_canonical_pmc(&pmu->pmc[select_idx]); + + reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX) + ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + pmc->idx; + data = __vcpu_sys_reg(vcpu, reg); + + kvm_pmu_stop_counter(vcpu, pmc); + eventsel = data & ARMV8_PMU_EVTYPE_EVENT; + + /* Software increment event does't need to be backed by a perf event */ + if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR && + pmc->idx != ARMV8_PMU_CYCLE_IDX) + return; + + memset(&attr, 0, sizeof(struct perf_event_attr)); + attr.type = PERF_TYPE_RAW; + attr.size = sizeof(attr); + attr.pinned = 1; + attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, pmc->idx); + attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0; + attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0; + attr.exclude_hv = 1; /* Don't count EL2 events */ + attr.exclude_host = 1; /* Don't count host events */ + attr.config = (pmc->idx == ARMV8_PMU_CYCLE_IDX) ? + ARMV8_PMUV3_PERFCTR_CPU_CYCLES : eventsel; + + counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); + + if (kvm_pmu_pmc_is_chained(pmc)) { + /** + * The initial sample period (overflow count) of an event. For + * chained counters we only support overflow interrupts on the + * high counter. + */ + attr.sample_period = (-counter) & GENMASK(63, 0); + attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED; + + event = perf_event_create_kernel_counter(&attr, -1, current, + kvm_pmu_perf_overflow, + pmc + 1); + } else { + /* The initial sample period (overflow count) of an event. */ + if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx)) + attr.sample_period = (-counter) & GENMASK(63, 0); + else + attr.sample_period = (-counter) & GENMASK(31, 0); + + event = perf_event_create_kernel_counter(&attr, -1, current, + kvm_pmu_perf_overflow, pmc); + } + + if (IS_ERR(event)) { + pr_err_once("kvm: pmu event creation failed %ld\n", + PTR_ERR(event)); + return; + } + + pmc->perf_event = event; +} + +/** + * kvm_pmu_update_pmc_chained - update chained bitmap + * @vcpu: The vcpu pointer + * @select_idx: The number of selected counter + * + * Update the chained bitmap based on the event type written in the + * typer register and the enable state of the odd register. + */ +static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmc *pmc = &pmu->pmc[select_idx], *canonical_pmc; + bool new_state, old_state; + + old_state = kvm_pmu_pmc_is_chained(pmc); + new_state = kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx) && + kvm_pmu_counter_is_enabled(vcpu, pmc->idx | 0x1); + + if (old_state == new_state) + return; + + canonical_pmc = kvm_pmu_get_canonical_pmc(pmc); + kvm_pmu_stop_counter(vcpu, canonical_pmc); + if (new_state) { + /* + * During promotion from !chained to chained we must ensure + * the adjacent counter is stopped and its event destroyed + */ + kvm_pmu_stop_counter(vcpu, kvm_pmu_get_alternate_pmc(pmc)); + set_bit(pmc->idx >> 1, vcpu->arch.pmu.chained); + return; + } + clear_bit(pmc->idx >> 1, vcpu->arch.pmu.chained); +} + +/** + * kvm_pmu_set_counter_event_type - set selected counter to monitor some event + * @vcpu: The vcpu pointer + * @data: The data guest writes to PMXEVTYPER_EL0 + * @select_idx: The number of selected counter + * + * When OS accesses PMXEVTYPER_EL0, that means it wants to set a PMC to count an + * event with given hardware event number. Here we call perf_event API to + * emulate this action and create a kernel perf event for it. + */ +void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, + u64 select_idx) +{ + u64 reg, event_type = data & ARMV8_PMU_EVTYPE_MASK; + + reg = (select_idx == ARMV8_PMU_CYCLE_IDX) + ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx; + + __vcpu_sys_reg(vcpu, reg) = event_type; + + kvm_pmu_update_pmc_chained(vcpu, select_idx); + kvm_pmu_create_perf_event(vcpu, select_idx); +} + +bool kvm_arm_support_pmu_v3(void) +{ + /* + * Check if HW_PERF_EVENTS are supported by checking the number of + * hardware performance counters. This could ensure the presence of + * a physical PMU and CONFIG_PERF_EVENT is selected. + */ + return (perf_num_counters() > 0); +} + +int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) +{ + if (!vcpu->arch.pmu.created) + return 0; + + /* + * A valid interrupt configuration for the PMU is either to have a + * properly configured interrupt number and using an in-kernel + * irqchip, or to not have an in-kernel GIC and not set an IRQ. + */ + if (irqchip_in_kernel(vcpu->kvm)) { + int irq = vcpu->arch.pmu.irq_num; + if (!kvm_arm_pmu_irq_initialized(vcpu)) + return -EINVAL; + + /* + * If we are using an in-kernel vgic, at this point we know + * the vgic will be initialized, so we can check the PMU irq + * number against the dimensions of the vgic and make sure + * it's valid. + */ + if (!irq_is_ppi(irq) && !vgic_valid_spi(vcpu->kvm, irq)) + return -EINVAL; + } else if (kvm_arm_pmu_irq_initialized(vcpu)) { + return -EINVAL; + } + + kvm_pmu_vcpu_reset(vcpu); + vcpu->arch.pmu.ready = true; + + return 0; +} + +static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu) +{ + if (!kvm_arm_support_pmu_v3()) + return -ENODEV; + + if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features)) + return -ENXIO; + + if (vcpu->arch.pmu.created) + return -EBUSY; + + if (irqchip_in_kernel(vcpu->kvm)) { + int ret; + + /* + * If using the PMU with an in-kernel virtual GIC + * implementation, we require the GIC to be already + * initialized when initializing the PMU. + */ + if (!vgic_initialized(vcpu->kvm)) + return -ENODEV; + + if (!kvm_arm_pmu_irq_initialized(vcpu)) + return -ENXIO; + + ret = kvm_vgic_set_owner(vcpu, vcpu->arch.pmu.irq_num, + &vcpu->arch.pmu); + if (ret) + return ret; + } + + vcpu->arch.pmu.created = true; + return 0; +} + +/* + * For one VM the interrupt type must be same for each vcpu. + * As a PPI, the interrupt number is the same for all vcpus, + * while as an SPI it must be a separate number per vcpu. + */ +static bool pmu_irq_is_valid(struct kvm *kvm, int irq) +{ + int i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!kvm_arm_pmu_irq_initialized(vcpu)) + continue; + + if (irq_is_ppi(irq)) { + if (vcpu->arch.pmu.irq_num != irq) + return false; + } else { + if (vcpu->arch.pmu.irq_num == irq) + return false; + } + } + + return true; +} + +int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) +{ + switch (attr->attr) { + case KVM_ARM_VCPU_PMU_V3_IRQ: { + int __user *uaddr = (int __user *)(long)attr->addr; + int irq; + + if (!irqchip_in_kernel(vcpu->kvm)) + return -EINVAL; + + if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features)) + return -ENODEV; + + if (get_user(irq, uaddr)) + return -EFAULT; + + /* The PMU overflow interrupt can be a PPI or a valid SPI. */ + if (!(irq_is_ppi(irq) || irq_is_spi(irq))) + return -EINVAL; + + if (!pmu_irq_is_valid(vcpu->kvm, irq)) + return -EINVAL; + + if (kvm_arm_pmu_irq_initialized(vcpu)) + return -EBUSY; + + kvm_debug("Set kvm ARM PMU irq: %d\n", irq); + vcpu->arch.pmu.irq_num = irq; + return 0; + } + case KVM_ARM_VCPU_PMU_V3_INIT: + return kvm_arm_pmu_v3_init(vcpu); + } + + return -ENXIO; +} + +int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) +{ + switch (attr->attr) { + case KVM_ARM_VCPU_PMU_V3_IRQ: { + int __user *uaddr = (int __user *)(long)attr->addr; + int irq; + + if (!irqchip_in_kernel(vcpu->kvm)) + return -EINVAL; + + if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features)) + return -ENODEV; + + if (!kvm_arm_pmu_irq_initialized(vcpu)) + return -ENXIO; + + irq = vcpu->arch.pmu.irq_num; + return put_user(irq, uaddr); + } + } + + return -ENXIO; +} + +int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) +{ + switch (attr->attr) { + case KVM_ARM_VCPU_PMU_V3_IRQ: + case KVM_ARM_VCPU_PMU_V3_INIT: + if (kvm_arm_support_pmu_v3() && + test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features)) + return 0; + } + + return -ENXIO; +} diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c new file mode 100644 index 000000000000..83415e96b589 --- /dev/null +++ b/arch/arm64/kvm/psci.c @@ -0,0 +1,564 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <linux/arm-smccc.h> +#include <linux/preempt.h> +#include <linux/kvm_host.h> +#include <linux/uaccess.h> +#include <linux/wait.h> + +#include <asm/cputype.h> +#include <asm/kvm_emulate.h> + +#include <kvm/arm_psci.h> +#include <kvm/arm_hypercalls.h> + +/* + * This is an implementation of the Power State Coordination Interface + * as described in ARM document number ARM DEN 0022A. + */ + +#define AFFINITY_MASK(level) ~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1) + +static unsigned long psci_affinity_mask(unsigned long affinity_level) +{ + if (affinity_level <= 3) + return MPIDR_HWID_BITMASK & AFFINITY_MASK(affinity_level); + + return 0; +} + +static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu) +{ + /* + * NOTE: For simplicity, we make VCPU suspend emulation to be + * same-as WFI (Wait-for-interrupt) emulation. + * + * This means for KVM the wakeup events are interrupts and + * this is consistent with intended use of StateID as described + * in section 5.4.1 of PSCI v0.2 specification (ARM DEN 0022A). + * + * Further, we also treat power-down request to be same as + * stand-by request as-per section 5.4.2 clause 3 of PSCI v0.2 + * specification (ARM DEN 0022A). This means all suspend states + * for KVM will preserve the register state. + */ + kvm_vcpu_block(vcpu); + kvm_clear_request(KVM_REQ_UNHALT, vcpu); + + return PSCI_RET_SUCCESS; +} + +static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu) +{ + vcpu->arch.power_off = true; + kvm_make_request(KVM_REQ_SLEEP, vcpu); + kvm_vcpu_kick(vcpu); +} + +static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) +{ + struct vcpu_reset_state *reset_state; + struct kvm *kvm = source_vcpu->kvm; + struct kvm_vcpu *vcpu = NULL; + unsigned long cpu_id; + + cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK; + if (vcpu_mode_is_32bit(source_vcpu)) + cpu_id &= ~((u32) 0); + + vcpu = kvm_mpidr_to_vcpu(kvm, cpu_id); + + /* + * Make sure the caller requested a valid CPU and that the CPU is + * turned off. + */ + if (!vcpu) + return PSCI_RET_INVALID_PARAMS; + if (!vcpu->arch.power_off) { + if (kvm_psci_version(source_vcpu, kvm) != KVM_ARM_PSCI_0_1) + return PSCI_RET_ALREADY_ON; + else + return PSCI_RET_INVALID_PARAMS; + } + + reset_state = &vcpu->arch.reset_state; + + reset_state->pc = smccc_get_arg2(source_vcpu); + + /* Propagate caller endianness */ + reset_state->be = kvm_vcpu_is_be(source_vcpu); + + /* + * NOTE: We always update r0 (or x0) because for PSCI v0.1 + * the general purpose registers are undefined upon CPU_ON. + */ + reset_state->r0 = smccc_get_arg3(source_vcpu); + + WRITE_ONCE(reset_state->reset, true); + kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); + + /* + * Make sure the reset request is observed if the change to + * power_state is observed. + */ + smp_wmb(); + + vcpu->arch.power_off = false; + kvm_vcpu_wake_up(vcpu); + + return PSCI_RET_SUCCESS; +} + +static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) +{ + int i, matching_cpus = 0; + unsigned long mpidr; + unsigned long target_affinity; + unsigned long target_affinity_mask; + unsigned long lowest_affinity_level; + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu *tmp; + + target_affinity = smccc_get_arg1(vcpu); + lowest_affinity_level = smccc_get_arg2(vcpu); + + /* Determine target affinity mask */ + target_affinity_mask = psci_affinity_mask(lowest_affinity_level); + if (!target_affinity_mask) + return PSCI_RET_INVALID_PARAMS; + + /* Ignore other bits of target affinity */ + target_affinity &= target_affinity_mask; + + /* + * If one or more VCPU matching target affinity are running + * then ON else OFF + */ + kvm_for_each_vcpu(i, tmp, kvm) { + mpidr = kvm_vcpu_get_mpidr_aff(tmp); + if ((mpidr & target_affinity_mask) == target_affinity) { + matching_cpus++; + if (!tmp->arch.power_off) + return PSCI_0_2_AFFINITY_LEVEL_ON; + } + } + + if (!matching_cpus) + return PSCI_RET_INVALID_PARAMS; + + return PSCI_0_2_AFFINITY_LEVEL_OFF; +} + +static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type) +{ + int i; + struct kvm_vcpu *tmp; + + /* + * The KVM ABI specifies that a system event exit may call KVM_RUN + * again and may perform shutdown/reboot at a later time that when the + * actual request is made. Since we are implementing PSCI and a + * caller of PSCI reboot and shutdown expects that the system shuts + * down or reboots immediately, let's make sure that VCPUs are not run + * after this call is handled and before the VCPUs have been + * re-initialized. + */ + kvm_for_each_vcpu(i, tmp, vcpu->kvm) + tmp->arch.power_off = true; + kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); + + memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); + vcpu->run->system_event.type = type; + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; +} + +static void kvm_psci_system_off(struct kvm_vcpu *vcpu) +{ + kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN); +} + +static void kvm_psci_system_reset(struct kvm_vcpu *vcpu) +{ + kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET); +} + +static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) +{ + int i; + + /* + * Zero the input registers' upper 32 bits. They will be fully + * zeroed on exit, so we're fine changing them in place. + */ + for (i = 1; i < 4; i++) + vcpu_set_reg(vcpu, i, lower_32_bits(vcpu_get_reg(vcpu, i))); +} + +static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn) +{ + switch(fn) { + case PSCI_0_2_FN64_CPU_SUSPEND: + case PSCI_0_2_FN64_CPU_ON: + case PSCI_0_2_FN64_AFFINITY_INFO: + /* Disallow these functions for 32bit guests */ + if (vcpu_mode_is_32bit(vcpu)) + return PSCI_RET_NOT_SUPPORTED; + break; + } + + return 0; +} + +static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + u32 psci_fn = smccc_get_function(vcpu); + unsigned long val; + int ret = 1; + + val = kvm_psci_check_allowed_function(vcpu, psci_fn); + if (val) + goto out; + + switch (psci_fn) { + case PSCI_0_2_FN_PSCI_VERSION: + /* + * Bits[31:16] = Major Version = 0 + * Bits[15:0] = Minor Version = 2 + */ + val = KVM_ARM_PSCI_0_2; + break; + case PSCI_0_2_FN_CPU_SUSPEND: + case PSCI_0_2_FN64_CPU_SUSPEND: + val = kvm_psci_vcpu_suspend(vcpu); + break; + case PSCI_0_2_FN_CPU_OFF: + kvm_psci_vcpu_off(vcpu); + val = PSCI_RET_SUCCESS; + break; + case PSCI_0_2_FN_CPU_ON: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; + case PSCI_0_2_FN64_CPU_ON: + mutex_lock(&kvm->lock); + val = kvm_psci_vcpu_on(vcpu); + mutex_unlock(&kvm->lock); + break; + case PSCI_0_2_FN_AFFINITY_INFO: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; + case PSCI_0_2_FN64_AFFINITY_INFO: + val = kvm_psci_vcpu_affinity_info(vcpu); + break; + case PSCI_0_2_FN_MIGRATE_INFO_TYPE: + /* + * Trusted OS is MP hence does not require migration + * or + * Trusted OS is not present + */ + val = PSCI_0_2_TOS_MP; + break; + case PSCI_0_2_FN_SYSTEM_OFF: + kvm_psci_system_off(vcpu); + /* + * We shouldn't be going back to guest VCPU after + * receiving SYSTEM_OFF request. + * + * If user space accidentally/deliberately resumes + * guest VCPU after SYSTEM_OFF request then guest + * VCPU should see internal failure from PSCI return + * value. To achieve this, we preload r0 (or x0) with + * PSCI return value INTERNAL_FAILURE. + */ + val = PSCI_RET_INTERNAL_FAILURE; + ret = 0; + break; + case PSCI_0_2_FN_SYSTEM_RESET: + kvm_psci_system_reset(vcpu); + /* + * Same reason as SYSTEM_OFF for preloading r0 (or x0) + * with PSCI return value INTERNAL_FAILURE. + */ + val = PSCI_RET_INTERNAL_FAILURE; + ret = 0; + break; + default: + val = PSCI_RET_NOT_SUPPORTED; + break; + } + +out: + smccc_set_retval(vcpu, val, 0, 0, 0); + return ret; +} + +static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu) +{ + u32 psci_fn = smccc_get_function(vcpu); + u32 feature; + unsigned long val; + int ret = 1; + + switch(psci_fn) { + case PSCI_0_2_FN_PSCI_VERSION: + val = KVM_ARM_PSCI_1_0; + break; + case PSCI_1_0_FN_PSCI_FEATURES: + feature = smccc_get_arg1(vcpu); + val = kvm_psci_check_allowed_function(vcpu, feature); + if (val) + break; + + switch(feature) { + case PSCI_0_2_FN_PSCI_VERSION: + case PSCI_0_2_FN_CPU_SUSPEND: + case PSCI_0_2_FN64_CPU_SUSPEND: + case PSCI_0_2_FN_CPU_OFF: + case PSCI_0_2_FN_CPU_ON: + case PSCI_0_2_FN64_CPU_ON: + case PSCI_0_2_FN_AFFINITY_INFO: + case PSCI_0_2_FN64_AFFINITY_INFO: + case PSCI_0_2_FN_MIGRATE_INFO_TYPE: + case PSCI_0_2_FN_SYSTEM_OFF: + case PSCI_0_2_FN_SYSTEM_RESET: + case PSCI_1_0_FN_PSCI_FEATURES: + case ARM_SMCCC_VERSION_FUNC_ID: + val = 0; + break; + default: + val = PSCI_RET_NOT_SUPPORTED; + break; + } + break; + default: + return kvm_psci_0_2_call(vcpu); + } + + smccc_set_retval(vcpu, val, 0, 0, 0); + return ret; +} + +static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + u32 psci_fn = smccc_get_function(vcpu); + unsigned long val; + + switch (psci_fn) { + case KVM_PSCI_FN_CPU_OFF: + kvm_psci_vcpu_off(vcpu); + val = PSCI_RET_SUCCESS; + break; + case KVM_PSCI_FN_CPU_ON: + mutex_lock(&kvm->lock); + val = kvm_psci_vcpu_on(vcpu); + mutex_unlock(&kvm->lock); + break; + default: + val = PSCI_RET_NOT_SUPPORTED; + break; + } + + smccc_set_retval(vcpu, val, 0, 0, 0); + return 1; +} + +/** + * kvm_psci_call - handle PSCI call if r0 value is in range + * @vcpu: Pointer to the VCPU struct + * + * Handle PSCI calls from guests through traps from HVC instructions. + * The calling convention is similar to SMC calls to the secure world + * where the function number is placed in r0. + * + * This function returns: > 0 (success), 0 (success but exit to user + * space), and < 0 (errors) + * + * Errors: + * -EINVAL: Unrecognized PSCI function + */ +int kvm_psci_call(struct kvm_vcpu *vcpu) +{ + switch (kvm_psci_version(vcpu, vcpu->kvm)) { + case KVM_ARM_PSCI_1_0: + return kvm_psci_1_0_call(vcpu); + case KVM_ARM_PSCI_0_2: + return kvm_psci_0_2_call(vcpu); + case KVM_ARM_PSCI_0_1: + return kvm_psci_0_1_call(vcpu); + default: + return -EINVAL; + }; +} + +int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) +{ + return 3; /* PSCI version and two workaround registers */ +} + +int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) +{ + if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices++)) + return -EFAULT; + + if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, uindices++)) + return -EFAULT; + + if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, uindices++)) + return -EFAULT; + + return 0; +} + +#define KVM_REG_FEATURE_LEVEL_WIDTH 4 +#define KVM_REG_FEATURE_LEVEL_MASK (BIT(KVM_REG_FEATURE_LEVEL_WIDTH) - 1) + +/* + * Convert the workaround level into an easy-to-compare number, where higher + * values mean better protection. + */ +static int get_kernel_wa_level(u64 regid) +{ + switch (regid) { + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + switch (kvm_arm_harden_branch_predictor()) { + case KVM_BP_HARDEN_UNKNOWN: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; + case KVM_BP_HARDEN_WA_NEEDED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL; + case KVM_BP_HARDEN_NOT_REQUIRED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED; + } + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + switch (kvm_arm_have_ssbd()) { + case KVM_SSBD_FORCE_DISABLE: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; + case KVM_SSBD_KERNEL: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL; + case KVM_SSBD_FORCE_ENABLE: + case KVM_SSBD_MITIGATED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; + case KVM_SSBD_UNKNOWN: + default: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN; + } + } + + return -EINVAL; +} + +int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + void __user *uaddr = (void __user *)(long)reg->addr; + u64 val; + + switch (reg->id) { + case KVM_REG_ARM_PSCI_VERSION: + val = kvm_psci_version(vcpu, vcpu->kvm); + break; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK; + break; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK; + + if (val == KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL && + kvm_arm_get_vcpu_workaround_2_flag(vcpu)) + val |= KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED; + break; + default: + return -ENOENT; + } + + if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + void __user *uaddr = (void __user *)(long)reg->addr; + u64 val; + int wa_level; + + if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + switch (reg->id) { + case KVM_REG_ARM_PSCI_VERSION: + { + bool wants_02; + + wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features); + + switch (val) { + case KVM_ARM_PSCI_0_1: + if (wants_02) + return -EINVAL; + vcpu->kvm->arch.psci_version = val; + return 0; + case KVM_ARM_PSCI_0_2: + case KVM_ARM_PSCI_1_0: + if (!wants_02) + return -EINVAL; + vcpu->kvm->arch.psci_version = val; + return 0; + } + break; + } + + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + if (val & ~KVM_REG_FEATURE_LEVEL_MASK) + return -EINVAL; + + if (get_kernel_wa_level(reg->id) < val) + return -EINVAL; + + return 0; + + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + if (val & ~(KVM_REG_FEATURE_LEVEL_MASK | + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED)) + return -EINVAL; + + wa_level = val & KVM_REG_FEATURE_LEVEL_MASK; + + if (get_kernel_wa_level(reg->id) < wa_level) + return -EINVAL; + + /* The enabled bit must not be set unless the level is AVAIL. */ + if (wa_level != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL && + wa_level != val) + return -EINVAL; + + /* Are we finished or do we need to check the enable bit ? */ + if (kvm_arm_have_ssbd() != KVM_SSBD_KERNEL) + return 0; + + /* + * If this kernel supports the workaround to be switched on + * or off, make sure it matches the requested setting. + */ + switch (wa_level) { + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: + kvm_arm_set_vcpu_workaround_2_flag(vcpu, + val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED); + break; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: + kvm_arm_set_vcpu_workaround_2_flag(vcpu, true); + break; + } + + return 0; + default: + return -ENOENT; + } + + return -EINVAL; +} diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c new file mode 100644 index 000000000000..1e0f4c284888 --- /dev/null +++ b/arch/arm64/kvm/pvtime.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 Arm Ltd. + +#include <linux/arm-smccc.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_mmu.h> +#include <asm/pvclock-abi.h> + +#include <kvm/arm_hypercalls.h> + +void kvm_update_stolen_time(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + u64 steal; + __le64 steal_le; + u64 offset; + int idx; + u64 base = vcpu->arch.steal.base; + + if (base == GPA_INVALID) + return; + + /* Let's do the local bookkeeping */ + steal = vcpu->arch.steal.steal; + steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal; + vcpu->arch.steal.last_steal = current->sched_info.run_delay; + vcpu->arch.steal.steal = steal; + + steal_le = cpu_to_le64(steal); + idx = srcu_read_lock(&kvm->srcu); + offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time); + kvm_put_guest(kvm, base + offset, steal_le, u64); + srcu_read_unlock(&kvm->srcu, idx); +} + +long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) +{ + u32 feature = smccc_get_arg1(vcpu); + long val = SMCCC_RET_NOT_SUPPORTED; + + switch (feature) { + case ARM_SMCCC_HV_PV_TIME_FEATURES: + case ARM_SMCCC_HV_PV_TIME_ST: + val = SMCCC_RET_SUCCESS; + break; + } + + return val; +} + +gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) +{ + struct pvclock_vcpu_stolen_time init_values = {}; + struct kvm *kvm = vcpu->kvm; + u64 base = vcpu->arch.steal.base; + int idx; + + if (base == GPA_INVALID) + return base; + + /* + * Start counting stolen time from the time the guest requests + * the feature enabled. + */ + vcpu->arch.steal.steal = 0; + vcpu->arch.steal.last_steal = current->sched_info.run_delay; + + idx = srcu_read_lock(&kvm->srcu); + kvm_write_guest(kvm, base, &init_values, sizeof(init_values)); + srcu_read_unlock(&kvm->srcu, idx); + + return base; +} + +int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + u64 __user *user = (u64 __user *)attr->addr; + struct kvm *kvm = vcpu->kvm; + u64 ipa; + int ret = 0; + int idx; + + if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA) + return -ENXIO; + + if (get_user(ipa, user)) + return -EFAULT; + if (!IS_ALIGNED(ipa, 64)) + return -EINVAL; + if (vcpu->arch.steal.base != GPA_INVALID) + return -EEXIST; + + /* Check the address is in a valid memslot */ + idx = srcu_read_lock(&kvm->srcu); + if (kvm_is_error_hva(gfn_to_hva(kvm, ipa >> PAGE_SHIFT))) + ret = -EINVAL; + srcu_read_unlock(&kvm->srcu, idx); + + if (!ret) + vcpu->arch.steal.base = ipa; + + return ret; +} + +int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + u64 __user *user = (u64 __user *)attr->addr; + u64 ipa; + + if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA) + return -ENXIO; + + ipa = vcpu->arch.steal.base; + + if (put_user(ipa, user)) + return -EFAULT; + return 0; +} + +int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, + struct kvm_device_attr *attr) +{ + switch (attr->attr) { + case KVM_ARM_VCPU_PVTIME_IPA: + return 0; + } + return -ENXIO; +} diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 70cd7bcca433..d3b209023727 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -36,15 +36,11 @@ static u32 kvm_ipa_limit; /* * ARMv8 Reset Values */ -static const struct kvm_regs default_regs_reset = { - .regs.pstate = (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | - PSR_F_BIT | PSR_D_BIT), -}; +#define VCPU_RESET_PSTATE_EL1 (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \ + PSR_F_BIT | PSR_D_BIT) -static const struct kvm_regs default_regs_reset32 = { - .regs.pstate = (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | - PSR_AA32_I_BIT | PSR_AA32_F_BIT), -}; +#define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \ + PSR_AA32_I_BIT | PSR_AA32_F_BIT) /** * kvm_arch_vm_ioctl_check_extension @@ -155,7 +151,7 @@ static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu) vl = vcpu->arch.sve_max_vl; /* - * Resposibility for these properties is shared between + * Responsibility for these properties is shared between * kvm_arm_init_arch_resources(), kvm_vcpu_enable_sve() and * set_sve_vls(). Double-check here just to be sure: */ @@ -241,7 +237,7 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) * ioctl or as part of handling a request issued by another VCPU in the PSCI * handling code. In the first case, the VCPU will not be loaded, and in the * second case the VCPU will be loaded. Because this function operates purely - * on the memory-backed valus of system registers, we want to do a full put if + * on the memory-backed values of system registers, we want to do a full put if * we were loaded (handling a request) and load the values back at the end of * the function. Otherwise we leave the state alone. In both cases, we * disable preemption around the vcpu reset as we would otherwise race with @@ -249,9 +245,9 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) */ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) { - const struct kvm_regs *cpu_reset; int ret = -EINVAL; bool loaded; + u32 pstate; /* Reset PMU outside of the non-preemptible section */ kvm_pmu_vcpu_reset(vcpu); @@ -282,16 +278,17 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) goto out; - cpu_reset = &default_regs_reset32; + pstate = VCPU_RESET_PSTATE_SVC; } else { - cpu_reset = &default_regs_reset; + pstate = VCPU_RESET_PSTATE_EL1; } break; } /* Reset core registers */ - memcpy(vcpu_gp_regs(vcpu), cpu_reset, sizeof(*cpu_reset)); + memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu))); + vcpu_gp_regs(vcpu)->regs.pstate = pstate; /* Reset system registers */ kvm_reset_sys_regs(vcpu); @@ -388,7 +385,7 @@ int kvm_set_ipa_limit(void) * * So clamp the ipa limit further down to limit the number of levels. * Since we can concatenate upto 16 tables at entry level, we could - * go upto 4bits above the maximum VA addressible with the current + * go upto 4bits above the maximum VA addressable with the current * number of levels. */ va_max = PGDIR_SHIFT + PAGE_SHIFT - 3; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 7d7a39b01135..80985439bfb2 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -34,7 +34,7 @@ #include "trace.h" /* - * All of this file is extremly similar to the ARM coproc.c, but the + * All of this file is extremely similar to the ARM coproc.c, but the * types are different. My gut feeling is that it should be pretty * easy to merge, but that would be an ABI breakage -- again. VFP * would also need to be abstracted. @@ -64,11 +64,8 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu, return false; } -u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) +static bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val) { - if (!vcpu->arch.sysregs_loaded_on_cpu) - goto immediate_read; - /* * System registers listed in the switch are not saved on every * exit from the guest but are only saved on vcpu_put. @@ -79,75 +76,92 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) * thread when emulating cross-VCPU communication. */ switch (reg) { - case CSSELR_EL1: return read_sysreg_s(SYS_CSSELR_EL1); - case SCTLR_EL1: return read_sysreg_s(SYS_SCTLR_EL12); - case ACTLR_EL1: return read_sysreg_s(SYS_ACTLR_EL1); - case CPACR_EL1: return read_sysreg_s(SYS_CPACR_EL12); - case TTBR0_EL1: return read_sysreg_s(SYS_TTBR0_EL12); - case TTBR1_EL1: return read_sysreg_s(SYS_TTBR1_EL12); - case TCR_EL1: return read_sysreg_s(SYS_TCR_EL12); - case ESR_EL1: return read_sysreg_s(SYS_ESR_EL12); - case AFSR0_EL1: return read_sysreg_s(SYS_AFSR0_EL12); - case AFSR1_EL1: return read_sysreg_s(SYS_AFSR1_EL12); - case FAR_EL1: return read_sysreg_s(SYS_FAR_EL12); - case MAIR_EL1: return read_sysreg_s(SYS_MAIR_EL12); - case VBAR_EL1: return read_sysreg_s(SYS_VBAR_EL12); - case CONTEXTIDR_EL1: return read_sysreg_s(SYS_CONTEXTIDR_EL12); - case TPIDR_EL0: return read_sysreg_s(SYS_TPIDR_EL0); - case TPIDRRO_EL0: return read_sysreg_s(SYS_TPIDRRO_EL0); - case TPIDR_EL1: return read_sysreg_s(SYS_TPIDR_EL1); - case AMAIR_EL1: return read_sysreg_s(SYS_AMAIR_EL12); - case CNTKCTL_EL1: return read_sysreg_s(SYS_CNTKCTL_EL12); - case PAR_EL1: return read_sysreg_s(SYS_PAR_EL1); - case DACR32_EL2: return read_sysreg_s(SYS_DACR32_EL2); - case IFSR32_EL2: return read_sysreg_s(SYS_IFSR32_EL2); - case DBGVCR32_EL2: return read_sysreg_s(SYS_DBGVCR32_EL2); + case CSSELR_EL1: *val = read_sysreg_s(SYS_CSSELR_EL1); break; + case SCTLR_EL1: *val = read_sysreg_s(SYS_SCTLR_EL12); break; + case ACTLR_EL1: *val = read_sysreg_s(SYS_ACTLR_EL1); break; + case CPACR_EL1: *val = read_sysreg_s(SYS_CPACR_EL12); break; + case TTBR0_EL1: *val = read_sysreg_s(SYS_TTBR0_EL12); break; + case TTBR1_EL1: *val = read_sysreg_s(SYS_TTBR1_EL12); break; + case TCR_EL1: *val = read_sysreg_s(SYS_TCR_EL12); break; + case ESR_EL1: *val = read_sysreg_s(SYS_ESR_EL12); break; + case AFSR0_EL1: *val = read_sysreg_s(SYS_AFSR0_EL12); break; + case AFSR1_EL1: *val = read_sysreg_s(SYS_AFSR1_EL12); break; + case FAR_EL1: *val = read_sysreg_s(SYS_FAR_EL12); break; + case MAIR_EL1: *val = read_sysreg_s(SYS_MAIR_EL12); break; + case VBAR_EL1: *val = read_sysreg_s(SYS_VBAR_EL12); break; + case CONTEXTIDR_EL1: *val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break; + case TPIDR_EL0: *val = read_sysreg_s(SYS_TPIDR_EL0); break; + case TPIDRRO_EL0: *val = read_sysreg_s(SYS_TPIDRRO_EL0); break; + case TPIDR_EL1: *val = read_sysreg_s(SYS_TPIDR_EL1); break; + case AMAIR_EL1: *val = read_sysreg_s(SYS_AMAIR_EL12); break; + case CNTKCTL_EL1: *val = read_sysreg_s(SYS_CNTKCTL_EL12); break; + case PAR_EL1: *val = read_sysreg_s(SYS_PAR_EL1); break; + case DACR32_EL2: *val = read_sysreg_s(SYS_DACR32_EL2); break; + case IFSR32_EL2: *val = read_sysreg_s(SYS_IFSR32_EL2); break; + case DBGVCR32_EL2: *val = read_sysreg_s(SYS_DBGVCR32_EL2); break; + default: return false; } -immediate_read: - return __vcpu_sys_reg(vcpu, reg); + return true; } -void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) +static bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg) { - if (!vcpu->arch.sysregs_loaded_on_cpu) - goto immediate_write; - /* * System registers listed in the switch are not restored on every * entry to the guest but are only restored on vcpu_load. * * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but - * should never be listed below, because the the MPIDR should only be - * set once, before running the VCPU, and never changed later. + * should never be listed below, because the MPIDR should only be set + * once, before running the VCPU, and never changed later. */ switch (reg) { - case CSSELR_EL1: write_sysreg_s(val, SYS_CSSELR_EL1); return; - case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); return; - case ACTLR_EL1: write_sysreg_s(val, SYS_ACTLR_EL1); return; - case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); return; - case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); return; - case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); return; - case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); return; - case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); return; - case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); return; - case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); return; - case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); return; - case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); return; - case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); return; - case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12); return; - case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); return; - case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); return; - case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); return; - case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); return; - case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); return; - case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); return; - case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); return; - case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); return; - case DBGVCR32_EL2: write_sysreg_s(val, SYS_DBGVCR32_EL2); return; + case CSSELR_EL1: write_sysreg_s(val, SYS_CSSELR_EL1); break; + case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); break; + case ACTLR_EL1: write_sysreg_s(val, SYS_ACTLR_EL1); break; + case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); break; + case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); break; + case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); break; + case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); break; + case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); break; + case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); break; + case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); break; + case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); break; + case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); break; + case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); break; + case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break; + case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); break; + case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); break; + case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); break; + case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); break; + case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); break; + case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); break; + case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); break; + case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); break; + case DBGVCR32_EL2: write_sysreg_s(val, SYS_DBGVCR32_EL2); break; + default: return false; } -immediate_write: + return true; +} + +u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) +{ + u64 val = 0x8badf00d8badf00d; + + if (vcpu->arch.sysregs_loaded_on_cpu && + __vcpu_read_sys_reg_from_cpu(reg, &val)) + return val; + + return __vcpu_sys_reg(vcpu, reg); +} + +void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) +{ + if (vcpu->arch.sysregs_loaded_on_cpu && + __vcpu_write_sys_reg_to_cpu(val, reg)) + return; + __vcpu_sys_reg(vcpu, reg) = val; } @@ -1532,7 +1546,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 }, { SYS_DESC(SYS_PMINTENSET_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 }, - { SYS_DESC(SYS_PMINTENCLR_EL1), access_pminten, NULL, PMINTENSET_EL1 }, + { SYS_DESC(SYS_PMINTENCLR_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 }, { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, @@ -1571,8 +1585,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 }, { SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, - { SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, NULL, PMCNTENSET_EL0 }, - { SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, NULL, PMOVSSET_EL0 }, + { SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, + { SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 }, { SYS_DESC(SYS_PMSWINC_EL0), access_pmswinc, reset_unknown, PMSWINC_EL0 }, { SYS_DESC(SYS_PMSELR_EL0), access_pmselr, reset_unknown, PMSELR_EL0 }, { SYS_DESC(SYS_PMCEID0_EL0), access_pmceid }, @@ -2073,12 +2087,37 @@ static const struct sys_reg_desc cp15_64_regs[] = { { SYS_DESC(SYS_AARCH32_CNTP_CVAL), access_arch_timer }, }; +static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n, + bool is_32) +{ + unsigned int i; + + for (i = 0; i < n; i++) { + if (!is_32 && table[i].reg && !table[i].reset) { + kvm_err("sys_reg table %p entry %d has lacks reset\n", + table, i); + return 1; + } + + if (i && cmp_sys_reg(&table[i-1], &table[i]) >= 0) { + kvm_err("sys_reg table %p out of order (%d)\n", table, i - 1); + return 1; + } + } + + return 0; +} + /* Target specific emulation tables */ static struct kvm_sys_reg_target_table *target_tables[KVM_ARM_NUM_TARGETS]; void kvm_register_target_sys_reg_table(unsigned int target, struct kvm_sys_reg_target_table *table) { + if (check_sysreg_table(table->table64.table, table->table64.num, false) || + check_sysreg_table(table->table32.table, table->table32.num, true)) + return; + target_tables[target] = table; } @@ -2364,19 +2403,13 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, } static void reset_sys_reg_descs(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *table, size_t num, - unsigned long *bmap) + const struct sys_reg_desc *table, size_t num) { unsigned long i; for (i = 0; i < num; i++) - if (table[i].reset) { - int reg = table[i].reg; - + if (table[i].reset) table[i].reset(vcpu, &table[i]); - if (reg > 0 && reg < NR_SYS_REGS) - set_bit(reg, bmap); - } } /** @@ -2832,32 +2865,18 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) return write_demux_regids(uindices); } -static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n) -{ - unsigned int i; - - for (i = 1; i < n; i++) { - if (cmp_sys_reg(&table[i-1], &table[i]) >= 0) { - kvm_err("sys_reg table %p out of order (%d)\n", table, i - 1); - return 1; - } - } - - return 0; -} - void kvm_sys_reg_table_init(void) { unsigned int i; struct sys_reg_desc clidr; /* Make sure tables are unique and in order. */ - BUG_ON(check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs))); - BUG_ON(check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs))); - BUG_ON(check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs))); - BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs))); - BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs))); - BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs))); + BUG_ON(check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs), false)); + BUG_ON(check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs), true)); + BUG_ON(check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs), true)); + BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs), true)); + BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs), true)); + BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs), false)); /* We abuse the reset function to overwrite the table itself. */ for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) @@ -2893,17 +2912,10 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) { size_t num; const struct sys_reg_desc *table; - DECLARE_BITMAP(bmap, NR_SYS_REGS) = { 0, }; /* Generic chip reset first (so target could override). */ - reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs), bmap); + reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); table = get_target_table(vcpu->arch.target, true, &num); - reset_sys_reg_descs(vcpu, table, num, bmap); - - for (num = 1; num < NR_SYS_REGS; num++) { - if (WARN(!test_bit(num, bmap), - "Didn't reset __vcpu_sys_reg(%zi)\n", num)) - break; - } + reset_sys_reg_descs(vcpu, table, num); } diff --git a/arch/arm64/kvm/trace.h b/arch/arm64/kvm/trace.h index eab91ad0effb..86f9ea47be29 100644 --- a/arch/arm64/kvm/trace.h +++ b/arch/arm64/kvm/trace.h @@ -1,216 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#if !defined(_TRACE_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ) +#ifndef _TRACE_ARM64_KVM_H #define _TRACE_ARM64_KVM_H -#include <linux/tracepoint.h> -#include "sys_regs.h" +#include "trace_arm.h" +#include "trace_handle_exit.h" -#undef TRACE_SYSTEM -#define TRACE_SYSTEM kvm - -TRACE_EVENT(kvm_wfx_arm64, - TP_PROTO(unsigned long vcpu_pc, bool is_wfe), - TP_ARGS(vcpu_pc, is_wfe), - - TP_STRUCT__entry( - __field(unsigned long, vcpu_pc) - __field(bool, is_wfe) - ), - - TP_fast_assign( - __entry->vcpu_pc = vcpu_pc; - __entry->is_wfe = is_wfe; - ), - - TP_printk("guest executed wf%c at: 0x%08lx", - __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc) -); - -TRACE_EVENT(kvm_hvc_arm64, - TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), - TP_ARGS(vcpu_pc, r0, imm), - - TP_STRUCT__entry( - __field(unsigned long, vcpu_pc) - __field(unsigned long, r0) - __field(unsigned long, imm) - ), - - TP_fast_assign( - __entry->vcpu_pc = vcpu_pc; - __entry->r0 = r0; - __entry->imm = imm; - ), - - TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)", - __entry->vcpu_pc, __entry->r0, __entry->imm) -); - -TRACE_EVENT(kvm_arm_setup_debug, - TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug), - TP_ARGS(vcpu, guest_debug), - - TP_STRUCT__entry( - __field(struct kvm_vcpu *, vcpu) - __field(__u32, guest_debug) - ), - - TP_fast_assign( - __entry->vcpu = vcpu; - __entry->guest_debug = guest_debug; - ), - - TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug) -); - -TRACE_EVENT(kvm_arm_clear_debug, - TP_PROTO(__u32 guest_debug), - TP_ARGS(guest_debug), - - TP_STRUCT__entry( - __field(__u32, guest_debug) - ), - - TP_fast_assign( - __entry->guest_debug = guest_debug; - ), - - TP_printk("flags: 0x%08x", __entry->guest_debug) -); - -TRACE_EVENT(kvm_arm_set_dreg32, - TP_PROTO(const char *name, __u32 value), - TP_ARGS(name, value), - - TP_STRUCT__entry( - __field(const char *, name) - __field(__u32, value) - ), - - TP_fast_assign( - __entry->name = name; - __entry->value = value; - ), - - TP_printk("%s: 0x%08x", __entry->name, __entry->value) -); - -TRACE_DEFINE_SIZEOF(__u64); - -TRACE_EVENT(kvm_arm_set_regset, - TP_PROTO(const char *type, int len, __u64 *control, __u64 *value), - TP_ARGS(type, len, control, value), - TP_STRUCT__entry( - __field(const char *, name) - __field(int, len) - __array(u64, ctrls, 16) - __array(u64, values, 16) - ), - TP_fast_assign( - __entry->name = type; - __entry->len = len; - memcpy(__entry->ctrls, control, len << 3); - memcpy(__entry->values, value, len << 3); - ), - TP_printk("%d %s CTRL:%s VALUE:%s", __entry->len, __entry->name, - __print_array(__entry->ctrls, __entry->len, sizeof(__u64)), - __print_array(__entry->values, __entry->len, sizeof(__u64))) -); - -TRACE_EVENT(trap_reg, - TP_PROTO(const char *fn, int reg, bool is_write, u64 write_value), - TP_ARGS(fn, reg, is_write, write_value), - - TP_STRUCT__entry( - __field(const char *, fn) - __field(int, reg) - __field(bool, is_write) - __field(u64, write_value) - ), - - TP_fast_assign( - __entry->fn = fn; - __entry->reg = reg; - __entry->is_write = is_write; - __entry->write_value = write_value; - ), - - TP_printk("%s %s reg %d (0x%08llx)", __entry->fn, __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value) -); - -TRACE_EVENT(kvm_handle_sys_reg, - TP_PROTO(unsigned long hsr), - TP_ARGS(hsr), - - TP_STRUCT__entry( - __field(unsigned long, hsr) - ), - - TP_fast_assign( - __entry->hsr = hsr; - ), - - TP_printk("HSR 0x%08lx", __entry->hsr) -); - -TRACE_EVENT(kvm_sys_access, - TP_PROTO(unsigned long vcpu_pc, struct sys_reg_params *params, const struct sys_reg_desc *reg), - TP_ARGS(vcpu_pc, params, reg), - - TP_STRUCT__entry( - __field(unsigned long, vcpu_pc) - __field(bool, is_write) - __field(const char *, name) - __field(u8, Op0) - __field(u8, Op1) - __field(u8, CRn) - __field(u8, CRm) - __field(u8, Op2) - ), - - TP_fast_assign( - __entry->vcpu_pc = vcpu_pc; - __entry->is_write = params->is_write; - __entry->name = reg->name; - __entry->Op0 = reg->Op0; - __entry->Op0 = reg->Op0; - __entry->Op1 = reg->Op1; - __entry->CRn = reg->CRn; - __entry->CRm = reg->CRm; - __entry->Op2 = reg->Op2; - ), - - TP_printk("PC: %lx %s (%d,%d,%d,%d,%d) %s", - __entry->vcpu_pc, __entry->name ?: "UNKN", - __entry->Op0, __entry->Op1, __entry->CRn, - __entry->CRm, __entry->Op2, - __entry->is_write ? "write" : "read") -); - -TRACE_EVENT(kvm_set_guest_debug, - TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug), - TP_ARGS(vcpu, guest_debug), - - TP_STRUCT__entry( - __field(struct kvm_vcpu *, vcpu) - __field(__u32, guest_debug) - ), - - TP_fast_assign( - __entry->vcpu = vcpu; - __entry->guest_debug = guest_debug; - ), - - TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug) -); - - -#endif /* _TRACE_ARM64_KVM_H */ - -#undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH . -#undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_FILE trace - -/* This part must be outside protection */ -#include <trace/define_trace.h> +#endif /* _TRACE_ARM64_KVM_H */ diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h new file mode 100644 index 000000000000..4c71270cc097 --- /dev/null +++ b/arch/arm64/kvm/trace_arm.h @@ -0,0 +1,378 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if !defined(_TRACE_ARM_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_ARM_ARM64_KVM_H + +#include <kvm/arm_arch_timer.h> +#include <linux/tracepoint.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm + +/* + * Tracepoints for entry/exit to guest + */ +TRACE_EVENT(kvm_entry, + TP_PROTO(unsigned long vcpu_pc), + TP_ARGS(vcpu_pc), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + ), + + TP_printk("PC: 0x%08lx", __entry->vcpu_pc) +); + +TRACE_EVENT(kvm_exit, + TP_PROTO(int ret, unsigned int esr_ec, unsigned long vcpu_pc), + TP_ARGS(ret, esr_ec, vcpu_pc), + + TP_STRUCT__entry( + __field( int, ret ) + __field( unsigned int, esr_ec ) + __field( unsigned long, vcpu_pc ) + ), + + TP_fast_assign( + __entry->ret = ARM_EXCEPTION_CODE(ret); + __entry->esr_ec = ARM_EXCEPTION_IS_TRAP(ret) ? esr_ec : 0; + __entry->vcpu_pc = vcpu_pc; + ), + + TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx", + __print_symbolic(__entry->ret, kvm_arm_exception_type), + __entry->esr_ec, + __print_symbolic(__entry->esr_ec, kvm_arm_exception_class), + __entry->vcpu_pc) +); + +TRACE_EVENT(kvm_guest_fault, + TP_PROTO(unsigned long vcpu_pc, unsigned long hsr, + unsigned long hxfar, + unsigned long long ipa), + TP_ARGS(vcpu_pc, hsr, hxfar, ipa), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( unsigned long, hsr ) + __field( unsigned long, hxfar ) + __field( unsigned long long, ipa ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->hsr = hsr; + __entry->hxfar = hxfar; + __entry->ipa = ipa; + ), + + TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx", + __entry->ipa, __entry->hsr, + __entry->hxfar, __entry->vcpu_pc) +); + +TRACE_EVENT(kvm_access_fault, + TP_PROTO(unsigned long ipa), + TP_ARGS(ipa), + + TP_STRUCT__entry( + __field( unsigned long, ipa ) + ), + + TP_fast_assign( + __entry->ipa = ipa; + ), + + TP_printk("IPA: %lx", __entry->ipa) +); + +TRACE_EVENT(kvm_irq_line, + TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level), + TP_ARGS(type, vcpu_idx, irq_num, level), + + TP_STRUCT__entry( + __field( unsigned int, type ) + __field( int, vcpu_idx ) + __field( int, irq_num ) + __field( int, level ) + ), + + TP_fast_assign( + __entry->type = type; + __entry->vcpu_idx = vcpu_idx; + __entry->irq_num = irq_num; + __entry->level = level; + ), + + TP_printk("Inject %s interrupt (%d), vcpu->idx: %d, num: %d, level: %d", + (__entry->type == KVM_ARM_IRQ_TYPE_CPU) ? "CPU" : + (__entry->type == KVM_ARM_IRQ_TYPE_PPI) ? "VGIC PPI" : + (__entry->type == KVM_ARM_IRQ_TYPE_SPI) ? "VGIC SPI" : "UNKNOWN", + __entry->type, __entry->vcpu_idx, __entry->irq_num, __entry->level) +); + +TRACE_EVENT(kvm_mmio_emulate, + TP_PROTO(unsigned long vcpu_pc, unsigned long instr, + unsigned long cpsr), + TP_ARGS(vcpu_pc, instr, cpsr), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( unsigned long, instr ) + __field( unsigned long, cpsr ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->instr = instr; + __entry->cpsr = cpsr; + ), + + TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)", + __entry->vcpu_pc, __entry->instr, __entry->cpsr) +); + +TRACE_EVENT(kvm_unmap_hva_range, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end), + + TP_STRUCT__entry( + __field( unsigned long, start ) + __field( unsigned long, end ) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + ), + + TP_printk("mmu notifier unmap range: %#08lx -- %#08lx", + __entry->start, __entry->end) +); + +TRACE_EVENT(kvm_set_spte_hva, + TP_PROTO(unsigned long hva), + TP_ARGS(hva), + + TP_STRUCT__entry( + __field( unsigned long, hva ) + ), + + TP_fast_assign( + __entry->hva = hva; + ), + + TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva) +); + +TRACE_EVENT(kvm_age_hva, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end), + + TP_STRUCT__entry( + __field( unsigned long, start ) + __field( unsigned long, end ) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + ), + + TP_printk("mmu notifier age hva: %#08lx -- %#08lx", + __entry->start, __entry->end) +); + +TRACE_EVENT(kvm_test_age_hva, + TP_PROTO(unsigned long hva), + TP_ARGS(hva), + + TP_STRUCT__entry( + __field( unsigned long, hva ) + ), + + TP_fast_assign( + __entry->hva = hva; + ), + + TP_printk("mmu notifier test age hva: %#08lx", __entry->hva) +); + +TRACE_EVENT(kvm_set_way_flush, + TP_PROTO(unsigned long vcpu_pc, bool cache), + TP_ARGS(vcpu_pc, cache), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( bool, cache ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->cache = cache; + ), + + TP_printk("S/W flush at 0x%016lx (cache %s)", + __entry->vcpu_pc, __entry->cache ? "on" : "off") +); + +TRACE_EVENT(kvm_toggle_cache, + TP_PROTO(unsigned long vcpu_pc, bool was, bool now), + TP_ARGS(vcpu_pc, was, now), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( bool, was ) + __field( bool, now ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->was = was; + __entry->now = now; + ), + + TP_printk("VM op at 0x%016lx (cache was %s, now %s)", + __entry->vcpu_pc, __entry->was ? "on" : "off", + __entry->now ? "on" : "off") +); + +/* + * Tracepoints for arch_timer + */ +TRACE_EVENT(kvm_timer_update_irq, + TP_PROTO(unsigned long vcpu_id, __u32 irq, int level), + TP_ARGS(vcpu_id, irq, level), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_id ) + __field( __u32, irq ) + __field( int, level ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->irq = irq; + __entry->level = level; + ), + + TP_printk("VCPU: %ld, IRQ %d, level %d", + __entry->vcpu_id, __entry->irq, __entry->level) +); + +TRACE_EVENT(kvm_get_timer_map, + TP_PROTO(unsigned long vcpu_id, struct timer_map *map), + TP_ARGS(vcpu_id, map), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_id ) + __field( int, direct_vtimer ) + __field( int, direct_ptimer ) + __field( int, emul_ptimer ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->direct_vtimer = arch_timer_ctx_index(map->direct_vtimer); + __entry->direct_ptimer = + (map->direct_ptimer) ? arch_timer_ctx_index(map->direct_ptimer) : -1; + __entry->emul_ptimer = + (map->emul_ptimer) ? arch_timer_ctx_index(map->emul_ptimer) : -1; + ), + + TP_printk("VCPU: %ld, dv: %d, dp: %d, ep: %d", + __entry->vcpu_id, + __entry->direct_vtimer, + __entry->direct_ptimer, + __entry->emul_ptimer) +); + +TRACE_EVENT(kvm_timer_save_state, + TP_PROTO(struct arch_timer_context *ctx), + TP_ARGS(ctx), + + TP_STRUCT__entry( + __field( unsigned long, ctl ) + __field( unsigned long long, cval ) + __field( int, timer_idx ) + ), + + TP_fast_assign( + __entry->ctl = ctx->cnt_ctl; + __entry->cval = ctx->cnt_cval; + __entry->timer_idx = arch_timer_ctx_index(ctx); + ), + + TP_printk(" CTL: %#08lx CVAL: %#16llx arch_timer_ctx_index: %d", + __entry->ctl, + __entry->cval, + __entry->timer_idx) +); + +TRACE_EVENT(kvm_timer_restore_state, + TP_PROTO(struct arch_timer_context *ctx), + TP_ARGS(ctx), + + TP_STRUCT__entry( + __field( unsigned long, ctl ) + __field( unsigned long long, cval ) + __field( int, timer_idx ) + ), + + TP_fast_assign( + __entry->ctl = ctx->cnt_ctl; + __entry->cval = ctx->cnt_cval; + __entry->timer_idx = arch_timer_ctx_index(ctx); + ), + + TP_printk("CTL: %#08lx CVAL: %#16llx arch_timer_ctx_index: %d", + __entry->ctl, + __entry->cval, + __entry->timer_idx) +); + +TRACE_EVENT(kvm_timer_hrtimer_expire, + TP_PROTO(struct arch_timer_context *ctx), + TP_ARGS(ctx), + + TP_STRUCT__entry( + __field( int, timer_idx ) + ), + + TP_fast_assign( + __entry->timer_idx = arch_timer_ctx_index(ctx); + ), + + TP_printk("arch_timer_ctx_index: %d", __entry->timer_idx) +); + +TRACE_EVENT(kvm_timer_emulate, + TP_PROTO(struct arch_timer_context *ctx, bool should_fire), + TP_ARGS(ctx, should_fire), + + TP_STRUCT__entry( + __field( int, timer_idx ) + __field( bool, should_fire ) + ), + + TP_fast_assign( + __entry->timer_idx = arch_timer_ctx_index(ctx); + __entry->should_fire = should_fire; + ), + + TP_printk("arch_timer_ctx_index: %d (should_fire: %d)", + __entry->timer_idx, __entry->should_fire) +); + +#endif /* _TRACE_ARM_ARM64_KVM_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace_arm + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/arm64/kvm/trace_handle_exit.h b/arch/arm64/kvm/trace_handle_exit.h new file mode 100644 index 000000000000..2c56d1e0f5bd --- /dev/null +++ b/arch/arm64/kvm/trace_handle_exit.h @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if !defined(_TRACE_HANDLE_EXIT_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_HANDLE_EXIT_ARM64_KVM_H + +#include <linux/tracepoint.h> +#include "sys_regs.h" + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm + +TRACE_EVENT(kvm_wfx_arm64, + TP_PROTO(unsigned long vcpu_pc, bool is_wfe), + TP_ARGS(vcpu_pc, is_wfe), + + TP_STRUCT__entry( + __field(unsigned long, vcpu_pc) + __field(bool, is_wfe) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->is_wfe = is_wfe; + ), + + TP_printk("guest executed wf%c at: 0x%08lx", + __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc) +); + +TRACE_EVENT(kvm_hvc_arm64, + TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), + TP_ARGS(vcpu_pc, r0, imm), + + TP_STRUCT__entry( + __field(unsigned long, vcpu_pc) + __field(unsigned long, r0) + __field(unsigned long, imm) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->r0 = r0; + __entry->imm = imm; + ), + + TP_printk("HVC at 0x%08lx (r0: 0x%08lx, imm: 0x%lx)", + __entry->vcpu_pc, __entry->r0, __entry->imm) +); + +TRACE_EVENT(kvm_arm_setup_debug, + TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug), + TP_ARGS(vcpu, guest_debug), + + TP_STRUCT__entry( + __field(struct kvm_vcpu *, vcpu) + __field(__u32, guest_debug) + ), + + TP_fast_assign( + __entry->vcpu = vcpu; + __entry->guest_debug = guest_debug; + ), + + TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug) +); + +TRACE_EVENT(kvm_arm_clear_debug, + TP_PROTO(__u32 guest_debug), + TP_ARGS(guest_debug), + + TP_STRUCT__entry( + __field(__u32, guest_debug) + ), + + TP_fast_assign( + __entry->guest_debug = guest_debug; + ), + + TP_printk("flags: 0x%08x", __entry->guest_debug) +); + +TRACE_EVENT(kvm_arm_set_dreg32, + TP_PROTO(const char *name, __u32 value), + TP_ARGS(name, value), + + TP_STRUCT__entry( + __field(const char *, name) + __field(__u32, value) + ), + + TP_fast_assign( + __entry->name = name; + __entry->value = value; + ), + + TP_printk("%s: 0x%08x", __entry->name, __entry->value) +); + +TRACE_DEFINE_SIZEOF(__u64); + +TRACE_EVENT(kvm_arm_set_regset, + TP_PROTO(const char *type, int len, __u64 *control, __u64 *value), + TP_ARGS(type, len, control, value), + TP_STRUCT__entry( + __field(const char *, name) + __field(int, len) + __array(u64, ctrls, 16) + __array(u64, values, 16) + ), + TP_fast_assign( + __entry->name = type; + __entry->len = len; + memcpy(__entry->ctrls, control, len << 3); + memcpy(__entry->values, value, len << 3); + ), + TP_printk("%d %s CTRL:%s VALUE:%s", __entry->len, __entry->name, + __print_array(__entry->ctrls, __entry->len, sizeof(__u64)), + __print_array(__entry->values, __entry->len, sizeof(__u64))) +); + +TRACE_EVENT(trap_reg, + TP_PROTO(const char *fn, int reg, bool is_write, u64 write_value), + TP_ARGS(fn, reg, is_write, write_value), + + TP_STRUCT__entry( + __field(const char *, fn) + __field(int, reg) + __field(bool, is_write) + __field(u64, write_value) + ), + + TP_fast_assign( + __entry->fn = fn; + __entry->reg = reg; + __entry->is_write = is_write; + __entry->write_value = write_value; + ), + + TP_printk("%s %s reg %d (0x%08llx)", __entry->fn, __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value) +); + +TRACE_EVENT(kvm_handle_sys_reg, + TP_PROTO(unsigned long hsr), + TP_ARGS(hsr), + + TP_STRUCT__entry( + __field(unsigned long, hsr) + ), + + TP_fast_assign( + __entry->hsr = hsr; + ), + + TP_printk("HSR 0x%08lx", __entry->hsr) +); + +TRACE_EVENT(kvm_sys_access, + TP_PROTO(unsigned long vcpu_pc, struct sys_reg_params *params, const struct sys_reg_desc *reg), + TP_ARGS(vcpu_pc, params, reg), + + TP_STRUCT__entry( + __field(unsigned long, vcpu_pc) + __field(bool, is_write) + __field(const char *, name) + __field(u8, Op0) + __field(u8, Op1) + __field(u8, CRn) + __field(u8, CRm) + __field(u8, Op2) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->is_write = params->is_write; + __entry->name = reg->name; + __entry->Op0 = reg->Op0; + __entry->Op0 = reg->Op0; + __entry->Op1 = reg->Op1; + __entry->CRn = reg->CRn; + __entry->CRm = reg->CRm; + __entry->Op2 = reg->Op2; + ), + + TP_printk("PC: %lx %s (%d,%d,%d,%d,%d) %s", + __entry->vcpu_pc, __entry->name ?: "UNKN", + __entry->Op0, __entry->Op1, __entry->CRn, + __entry->CRm, __entry->Op2, + __entry->is_write ? "write" : "read") +); + +TRACE_EVENT(kvm_set_guest_debug, + TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug), + TP_ARGS(vcpu, guest_debug), + + TP_STRUCT__entry( + __field(struct kvm_vcpu *, vcpu) + __field(__u32, guest_debug) + ), + + TP_fast_assign( + __entry->vcpu = vcpu; + __entry->guest_debug = guest_debug; + ), + + TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug) +); + +#endif /* _TRACE_HANDLE_EXIT_ARM64_KVM_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace_handle_exit + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c index e7d1ea92095d..2f92bdcb1188 100644 --- a/arch/arm64/kvm/vgic-sys-reg-v3.c +++ b/arch/arm64/kvm/vgic-sys-reg-v3.c @@ -7,7 +7,7 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> -#include "vgic.h" +#include "vgic/vgic.h" #include "sys_regs.h" static bool access_gic_ctlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, diff --git a/arch/arm64/kvm/vgic/trace.h b/arch/arm64/kvm/vgic/trace.h new file mode 100644 index 000000000000..83c64401a7fc --- /dev/null +++ b/arch/arm64/kvm/vgic/trace.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if !defined(_TRACE_VGIC_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_VGIC_H + +#include <linux/tracepoint.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm + +TRACE_EVENT(vgic_update_irq_pending, + TP_PROTO(unsigned long vcpu_id, __u32 irq, bool level), + TP_ARGS(vcpu_id, irq, level), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_id ) + __field( __u32, irq ) + __field( bool, level ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->irq = irq; + __entry->level = level; + ), + + TP_printk("VCPU: %ld, IRQ %d, level: %d", + __entry->vcpu_id, __entry->irq, __entry->level) +); + +#endif /* _TRACE_VGIC_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ../../arch/arm64/kvm/vgic +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c new file mode 100644 index 000000000000..b13a9e3f99dd --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -0,0 +1,300 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2016 Linaro + * Author: Christoffer Dall <christoffer.dall@linaro.org> + */ + +#include <linux/cpu.h> +#include <linux/debugfs.h> +#include <linux/interrupt.h> +#include <linux/kvm_host.h> +#include <linux/seq_file.h> +#include <kvm/arm_vgic.h> +#include <asm/kvm_mmu.h> +#include "vgic.h" + +/* + * Structure to control looping through the entire vgic state. We start at + * zero for each field and move upwards. So, if dist_id is 0 we print the + * distributor info. When dist_id is 1, we have already printed it and move + * on. + * + * When vcpu_id < nr_cpus we print the vcpu info until vcpu_id == nr_cpus and + * so on. + */ +struct vgic_state_iter { + int nr_cpus; + int nr_spis; + int nr_lpis; + int dist_id; + int vcpu_id; + int intid; + int lpi_idx; + u32 *lpi_array; +}; + +static void iter_next(struct vgic_state_iter *iter) +{ + if (iter->dist_id == 0) { + iter->dist_id++; + return; + } + + iter->intid++; + if (iter->intid == VGIC_NR_PRIVATE_IRQS && + ++iter->vcpu_id < iter->nr_cpus) + iter->intid = 0; + + if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS)) { + if (iter->lpi_idx < iter->nr_lpis) + iter->intid = iter->lpi_array[iter->lpi_idx]; + iter->lpi_idx++; + } +} + +static void iter_init(struct kvm *kvm, struct vgic_state_iter *iter, + loff_t pos) +{ + int nr_cpus = atomic_read(&kvm->online_vcpus); + + memset(iter, 0, sizeof(*iter)); + + iter->nr_cpus = nr_cpus; + iter->nr_spis = kvm->arch.vgic.nr_spis; + if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + iter->nr_lpis = vgic_copy_lpi_list(kvm, NULL, &iter->lpi_array); + if (iter->nr_lpis < 0) + iter->nr_lpis = 0; + } + + /* Fast forward to the right position if needed */ + while (pos--) + iter_next(iter); +} + +static bool end_of_vgic(struct vgic_state_iter *iter) +{ + return iter->dist_id > 0 && + iter->vcpu_id == iter->nr_cpus && + iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS) && + iter->lpi_idx > iter->nr_lpis; +} + +static void *vgic_debug_start(struct seq_file *s, loff_t *pos) +{ + struct kvm *kvm = (struct kvm *)s->private; + struct vgic_state_iter *iter; + + mutex_lock(&kvm->lock); + iter = kvm->arch.vgic.iter; + if (iter) { + iter = ERR_PTR(-EBUSY); + goto out; + } + + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) { + iter = ERR_PTR(-ENOMEM); + goto out; + } + + iter_init(kvm, iter, *pos); + kvm->arch.vgic.iter = iter; + + if (end_of_vgic(iter)) + iter = NULL; +out: + mutex_unlock(&kvm->lock); + return iter; +} + +static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos) +{ + struct kvm *kvm = (struct kvm *)s->private; + struct vgic_state_iter *iter = kvm->arch.vgic.iter; + + ++*pos; + iter_next(iter); + if (end_of_vgic(iter)) + iter = NULL; + return iter; +} + +static void vgic_debug_stop(struct seq_file *s, void *v) +{ + struct kvm *kvm = (struct kvm *)s->private; + struct vgic_state_iter *iter; + + /* + * If the seq file wasn't properly opened, there's nothing to clearn + * up. + */ + if (IS_ERR(v)) + return; + + mutex_lock(&kvm->lock); + iter = kvm->arch.vgic.iter; + kfree(iter->lpi_array); + kfree(iter); + kvm->arch.vgic.iter = NULL; + mutex_unlock(&kvm->lock); +} + +static void print_dist_state(struct seq_file *s, struct vgic_dist *dist) +{ + bool v3 = dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3; + + seq_printf(s, "Distributor\n"); + seq_printf(s, "===========\n"); + seq_printf(s, "vgic_model:\t%s\n", v3 ? "GICv3" : "GICv2"); + seq_printf(s, "nr_spis:\t%d\n", dist->nr_spis); + if (v3) + seq_printf(s, "nr_lpis:\t%d\n", dist->lpi_list_count); + seq_printf(s, "enabled:\t%d\n", dist->enabled); + seq_printf(s, "\n"); + + seq_printf(s, "P=pending_latch, L=line_level, A=active\n"); + seq_printf(s, "E=enabled, H=hw, C=config (level=1, edge=0)\n"); + seq_printf(s, "G=group\n"); +} + +static void print_header(struct seq_file *s, struct vgic_irq *irq, + struct kvm_vcpu *vcpu) +{ + int id = 0; + char *hdr = "SPI "; + + if (vcpu) { + hdr = "VCPU"; + id = vcpu->vcpu_id; + } + + seq_printf(s, "\n"); + seq_printf(s, "%s%2d TYP ID TGT_ID PLAEHCG HWID TARGET SRC PRI VCPU_ID\n", hdr, id); + seq_printf(s, "----------------------------------------------------------------\n"); +} + +static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, + struct kvm_vcpu *vcpu) +{ + char *type; + bool pending; + + if (irq->intid < VGIC_NR_SGIS) + type = "SGI"; + else if (irq->intid < VGIC_NR_PRIVATE_IRQS) + type = "PPI"; + else if (irq->intid < VGIC_MAX_SPI) + type = "SPI"; + else + type = "LPI"; + + if (irq->intid ==0 || irq->intid == VGIC_NR_PRIVATE_IRQS) + print_header(s, irq, vcpu); + + pending = irq->pending_latch; + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + int err; + + err = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &pending); + WARN_ON_ONCE(err); + } + + seq_printf(s, " %s %4d " + " %2d " + "%d%d%d%d%d%d%d " + "%8d " + "%8x " + " %2x " + "%3d " + " %2d " + "\n", + type, irq->intid, + (irq->target_vcpu) ? irq->target_vcpu->vcpu_id : -1, + pending, + irq->line_level, + irq->active, + irq->enabled, + irq->hw, + irq->config == VGIC_CONFIG_LEVEL, + irq->group, + irq->hwintid, + irq->mpidr, + irq->source, + irq->priority, + (irq->vcpu) ? irq->vcpu->vcpu_id : -1); +} + +static int vgic_debug_show(struct seq_file *s, void *v) +{ + struct kvm *kvm = (struct kvm *)s->private; + struct vgic_state_iter *iter = (struct vgic_state_iter *)v; + struct vgic_irq *irq; + struct kvm_vcpu *vcpu = NULL; + unsigned long flags; + + if (iter->dist_id == 0) { + print_dist_state(s, &kvm->arch.vgic); + return 0; + } + + if (!kvm->arch.vgic.initialized) + return 0; + + if (iter->vcpu_id < iter->nr_cpus) + vcpu = kvm_get_vcpu(kvm, iter->vcpu_id); + + irq = vgic_get_irq(kvm, vcpu, iter->intid); + if (!irq) { + seq_printf(s, " LPI %4d freed\n", iter->intid); + return 0; + } + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + print_irq_state(s, irq, vcpu); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(kvm, irq); + return 0; +} + +static const struct seq_operations vgic_debug_seq_ops = { + .start = vgic_debug_start, + .next = vgic_debug_next, + .stop = vgic_debug_stop, + .show = vgic_debug_show +}; + +static int debug_open(struct inode *inode, struct file *file) +{ + int ret; + ret = seq_open(file, &vgic_debug_seq_ops); + if (!ret) { + struct seq_file *seq; + /* seq_open will have modified file->private_data */ + seq = file->private_data; + seq->private = inode->i_private; + } + + return ret; +}; + +static const struct file_operations vgic_debug_fops = { + .owner = THIS_MODULE, + .open = debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release +}; + +void vgic_debug_init(struct kvm *kvm) +{ + debugfs_create_file("vgic-state", 0444, kvm->debugfs_dentry, kvm, + &vgic_debug_fops); +} + +void vgic_debug_destroy(struct kvm *kvm) +{ +} diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c new file mode 100644 index 000000000000..32e32d67a127 --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -0,0 +1,556 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015, 2016 ARM Ltd. + */ + +#include <linux/uaccess.h> +#include <linux/interrupt.h> +#include <linux/cpu.h> +#include <linux/kvm_host.h> +#include <kvm/arm_vgic.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_mmu.h> +#include "vgic.h" + +/* + * Initialization rules: there are multiple stages to the vgic + * initialization, both for the distributor and the CPU interfaces. The basic + * idea is that even though the VGIC is not functional or not requested from + * user space, the critical path of the run loop can still call VGIC functions + * that just won't do anything, without them having to check additional + * initialization flags to ensure they don't look at uninitialized data + * structures. + * + * Distributor: + * + * - kvm_vgic_early_init(): initialization of static data that doesn't + * depend on any sizing information or emulation type. No allocation + * is allowed there. + * + * - vgic_init(): allocation and initialization of the generic data + * structures that depend on sizing information (number of CPUs, + * number of interrupts). Also initializes the vcpu specific data + * structures. Can be executed lazily for GICv2. + * + * CPU Interface: + * + * - kvm_vgic_vcpu_init(): initialization of static data that + * doesn't depend on any sizing information or emulation type. No + * allocation is allowed there. + */ + +/* EARLY INIT */ + +/** + * kvm_vgic_early_init() - Initialize static VGIC VCPU data structures + * @kvm: The VM whose VGIC districutor should be initialized + * + * Only do initialization of static structures that don't require any + * allocation or sizing information from userspace. vgic_init() called + * kvm_vgic_dist_init() which takes care of the rest. + */ +void kvm_vgic_early_init(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + + INIT_LIST_HEAD(&dist->lpi_list_head); + INIT_LIST_HEAD(&dist->lpi_translation_cache); + raw_spin_lock_init(&dist->lpi_list_lock); +} + +/* CREATION */ + +/** + * kvm_vgic_create: triggered by the instantiation of the VGIC device by + * user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only) + * or through the generic KVM_CREATE_DEVICE API ioctl. + * irqchip_in_kernel() tells you if this function succeeded or not. + * @kvm: kvm struct pointer + * @type: KVM_DEV_TYPE_ARM_VGIC_V[23] + */ +int kvm_vgic_create(struct kvm *kvm, u32 type) +{ + int i, ret; + struct kvm_vcpu *vcpu; + + if (irqchip_in_kernel(kvm)) + return -EEXIST; + + /* + * This function is also called by the KVM_CREATE_IRQCHIP handler, + * which had no chance yet to check the availability of the GICv2 + * emulation. So check this here again. KVM_CREATE_DEVICE does + * the proper checks already. + */ + if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && + !kvm_vgic_global_state.can_emulate_gicv2) + return -ENODEV; + + ret = -EBUSY; + if (!lock_all_vcpus(kvm)) + return ret; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->arch.has_run_once) + goto out_unlock; + } + ret = 0; + + if (type == KVM_DEV_TYPE_ARM_VGIC_V2) + kvm->arch.max_vcpus = VGIC_V2_MAX_CPUS; + else + kvm->arch.max_vcpus = VGIC_V3_MAX_CPUS; + + if (atomic_read(&kvm->online_vcpus) > kvm->arch.max_vcpus) { + ret = -E2BIG; + goto out_unlock; + } + + kvm->arch.vgic.in_kernel = true; + kvm->arch.vgic.vgic_model = type; + + kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; + + if (type == KVM_DEV_TYPE_ARM_VGIC_V2) + kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; + else + INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); + +out_unlock: + unlock_all_vcpus(kvm); + return ret; +} + +/* INIT/DESTROY */ + +/** + * kvm_vgic_dist_init: initialize the dist data structures + * @kvm: kvm struct pointer + * @nr_spis: number of spis, frozen by caller + */ +static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0); + int i; + + dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL); + if (!dist->spis) + return -ENOMEM; + + /* + * In the following code we do not take the irq struct lock since + * no other action on irq structs can happen while the VGIC is + * not initialized yet: + * If someone wants to inject an interrupt or does a MMIO access, we + * require prior initialization in case of a virtual GICv3 or trigger + * initialization when using a virtual GICv2. + */ + for (i = 0; i < nr_spis; i++) { + struct vgic_irq *irq = &dist->spis[i]; + + irq->intid = i + VGIC_NR_PRIVATE_IRQS; + INIT_LIST_HEAD(&irq->ap_list); + raw_spin_lock_init(&irq->irq_lock); + irq->vcpu = NULL; + irq->target_vcpu = vcpu0; + kref_init(&irq->refcount); + switch (dist->vgic_model) { + case KVM_DEV_TYPE_ARM_VGIC_V2: + irq->targets = 0; + irq->group = 0; + break; + case KVM_DEV_TYPE_ARM_VGIC_V3: + irq->mpidr = 0; + irq->group = 1; + break; + default: + kfree(dist->spis); + dist->spis = NULL; + return -EINVAL; + } + } + return 0; +} + +/** + * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data + * structures and register VCPU-specific KVM iodevs + * + * @vcpu: pointer to the VCPU being created and initialized + * + * Only do initialization, but do not actually enable the + * VGIC CPU interface + */ +int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + int ret = 0; + int i; + + vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; + + INIT_LIST_HEAD(&vgic_cpu->ap_list_head); + raw_spin_lock_init(&vgic_cpu->ap_list_lock); + atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0); + + /* + * Enable and configure all SGIs to be edge-triggered and + * configure all PPIs as level-triggered. + */ + for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { + struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; + + INIT_LIST_HEAD(&irq->ap_list); + raw_spin_lock_init(&irq->irq_lock); + irq->intid = i; + irq->vcpu = NULL; + irq->target_vcpu = vcpu; + kref_init(&irq->refcount); + if (vgic_irq_is_sgi(i)) { + /* SGIs */ + irq->enabled = 1; + irq->config = VGIC_CONFIG_EDGE; + } else { + /* PPIs */ + irq->config = VGIC_CONFIG_LEVEL; + } + } + + if (!irqchip_in_kernel(vcpu->kvm)) + return 0; + + /* + * If we are creating a VCPU with a GICv3 we must also register the + * KVM io device for the redistributor that belongs to this VCPU. + */ + if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + mutex_lock(&vcpu->kvm->lock); + ret = vgic_register_redist_iodev(vcpu); + mutex_unlock(&vcpu->kvm->lock); + } + return ret; +} + +static void kvm_vgic_vcpu_enable(struct kvm_vcpu *vcpu) +{ + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_enable(vcpu); + else + vgic_v3_enable(vcpu); +} + +/* + * vgic_init: allocates and initializes dist and vcpu data structures + * depending on two dimensioning parameters: + * - the number of spis + * - the number of vcpus + * The function is generally called when nr_spis has been explicitly set + * by the guest through the KVM DEVICE API. If not nr_spis is set to 256. + * vgic_initialized() returns true when this function has succeeded. + * Must be called with kvm->lock held! + */ +int vgic_init(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int ret = 0, i, idx; + + if (vgic_initialized(kvm)) + return 0; + + /* Are we also in the middle of creating a VCPU? */ + if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus)) + return -EBUSY; + + /* freeze the number of spis */ + if (!dist->nr_spis) + dist->nr_spis = VGIC_NR_IRQS_LEGACY - VGIC_NR_PRIVATE_IRQS; + + ret = kvm_vgic_dist_init(kvm, dist->nr_spis); + if (ret) + goto out; + + /* Initialize groups on CPUs created before the VGIC type was known */ + kvm_for_each_vcpu(idx, vcpu, kvm) { + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + + for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { + struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; + switch (dist->vgic_model) { + case KVM_DEV_TYPE_ARM_VGIC_V3: + irq->group = 1; + irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + break; + case KVM_DEV_TYPE_ARM_VGIC_V2: + irq->group = 0; + irq->targets = 1U << idx; + break; + default: + ret = -EINVAL; + goto out; + } + } + } + + if (vgic_has_its(kvm)) + vgic_lpi_translation_cache_init(kvm); + + /* + * If we have GICv4.1 enabled, unconditionnaly request enable the + * v4 support so that we get HW-accelerated vSGIs. Otherwise, only + * enable it if we present a virtual ITS to the guest. + */ + if (vgic_supports_direct_msis(kvm)) { + ret = vgic_v4_init(kvm); + if (ret) + goto out; + } + + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vgic_vcpu_enable(vcpu); + + ret = kvm_vgic_setup_default_irq_routing(kvm); + if (ret) + goto out; + + vgic_debug_init(kvm); + + dist->implementation_rev = 2; + dist->initialized = true; + +out: + return ret; +} + +static void kvm_vgic_dist_destroy(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_redist_region *rdreg, *next; + + dist->ready = false; + dist->initialized = false; + + kfree(dist->spis); + dist->spis = NULL; + dist->nr_spis = 0; + + if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) { + list_del(&rdreg->list); + kfree(rdreg); + } + INIT_LIST_HEAD(&dist->rd_regions); + } + + if (vgic_has_its(kvm)) + vgic_lpi_translation_cache_destroy(kvm); + + if (vgic_supports_direct_msis(kvm)) + vgic_v4_teardown(kvm); +} + +void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + + /* + * Retire all pending LPIs on this vcpu anyway as we're + * going to destroy it. + */ + vgic_flush_pending_lpis(vcpu); + + INIT_LIST_HEAD(&vgic_cpu->ap_list_head); +} + +/* To be called with kvm->lock held */ +static void __kvm_vgic_destroy(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i; + + vgic_debug_destroy(kvm); + + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_vgic_vcpu_destroy(vcpu); + + kvm_vgic_dist_destroy(kvm); +} + +void kvm_vgic_destroy(struct kvm *kvm) +{ + mutex_lock(&kvm->lock); + __kvm_vgic_destroy(kvm); + mutex_unlock(&kvm->lock); +} + +/** + * vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest + * is a GICv2. A GICv3 must be explicitly initialized by the guest using the + * KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEVICE group. + * @kvm: kvm struct pointer + */ +int vgic_lazy_init(struct kvm *kvm) +{ + int ret = 0; + + if (unlikely(!vgic_initialized(kvm))) { + /* + * We only provide the automatic initialization of the VGIC + * for the legacy case of a GICv2. Any other type must + * be explicitly initialized once setup with the respective + * KVM device call. + */ + if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2) + return -EBUSY; + + mutex_lock(&kvm->lock); + ret = vgic_init(kvm); + mutex_unlock(&kvm->lock); + } + + return ret; +} + +/* RESOURCE MAPPING */ + +/** + * Map the MMIO regions depending on the VGIC model exposed to the guest + * called on the first VCPU run. + * Also map the virtual CPU interface into the VM. + * v2/v3 derivatives call vgic_init if not already done. + * vgic_ready() returns true if this function has succeeded. + * @kvm: kvm struct pointer + */ +int kvm_vgic_map_resources(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + int ret = 0; + + mutex_lock(&kvm->lock); + if (!irqchip_in_kernel(kvm)) + goto out; + + if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) + ret = vgic_v2_map_resources(kvm); + else + ret = vgic_v3_map_resources(kvm); + + if (ret) + __kvm_vgic_destroy(kvm); + +out: + mutex_unlock(&kvm->lock); + return ret; +} + +/* GENERIC PROBE */ + +static int vgic_init_cpu_starting(unsigned int cpu) +{ + enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0); + return 0; +} + + +static int vgic_init_cpu_dying(unsigned int cpu) +{ + disable_percpu_irq(kvm_vgic_global_state.maint_irq); + return 0; +} + +static irqreturn_t vgic_maintenance_handler(int irq, void *data) +{ + /* + * We cannot rely on the vgic maintenance interrupt to be + * delivered synchronously. This means we can only use it to + * exit the VM, and we perform the handling of EOIed + * interrupts on the exit path (see vgic_fold_lr_state). + */ + return IRQ_HANDLED; +} + +/** + * kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware + * + * For a specific CPU, initialize the GIC VE hardware. + */ +void kvm_vgic_init_cpu_hardware(void) +{ + BUG_ON(preemptible()); + + /* + * We want to make sure the list registers start out clear so that we + * only have the program the used registers. + */ + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_init_lrs(); + else + kvm_call_hyp(__vgic_v3_init_lrs); +} + +/** + * kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable + * according to the host GIC model. Accordingly calls either + * vgic_v2/v3_probe which registers the KVM_DEVICE that can be + * instantiated by a guest later on . + */ +int kvm_vgic_hyp_init(void) +{ + const struct gic_kvm_info *gic_kvm_info; + int ret; + + gic_kvm_info = gic_get_kvm_info(); + if (!gic_kvm_info) + return -ENODEV; + + if (!gic_kvm_info->maint_irq) { + kvm_err("No vgic maintenance irq\n"); + return -ENXIO; + } + + switch (gic_kvm_info->type) { + case GIC_V2: + ret = vgic_v2_probe(gic_kvm_info); + break; + case GIC_V3: + ret = vgic_v3_probe(gic_kvm_info); + if (!ret) { + static_branch_enable(&kvm_vgic_global_state.gicv3_cpuif); + kvm_info("GIC system register CPU interface enabled\n"); + } + break; + default: + ret = -ENODEV; + } + + if (ret) + return ret; + + kvm_vgic_global_state.maint_irq = gic_kvm_info->maint_irq; + ret = request_percpu_irq(kvm_vgic_global_state.maint_irq, + vgic_maintenance_handler, + "vgic", kvm_get_running_vcpus()); + if (ret) { + kvm_err("Cannot register interrupt %d\n", + kvm_vgic_global_state.maint_irq); + return ret; + } + + ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, + "kvm/arm/vgic:starting", + vgic_init_cpu_starting, vgic_init_cpu_dying); + if (ret) { + kvm_err("Cannot register vgic CPU notifier\n"); + goto out_free_irq; + } + + kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq); + return 0; + +out_free_irq: + free_percpu_irq(kvm_vgic_global_state.maint_irq, + kvm_get_running_vcpus()); + return ret; +} diff --git a/arch/arm64/kvm/vgic/vgic-irqfd.c b/arch/arm64/kvm/vgic/vgic-irqfd.c new file mode 100644 index 000000000000..d8cdfea5cc96 --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-irqfd.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015, 2016 ARM Ltd. + */ + +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <trace/events/kvm.h> +#include <kvm/arm_vgic.h> +#include "vgic.h" + +/** + * vgic_irqfd_set_irq: inject the IRQ corresponding to the + * irqchip routing entry + * + * This is the entry point for irqfd IRQ injection + */ +static int vgic_irqfd_set_irq(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, + int level, bool line_status) +{ + unsigned int spi_id = e->irqchip.pin + VGIC_NR_PRIVATE_IRQS; + + if (!vgic_valid_spi(kvm, spi_id)) + return -EINVAL; + return kvm_vgic_inject_irq(kvm, 0, spi_id, level, NULL); +} + +/** + * kvm_set_routing_entry: populate a kvm routing entry + * from a user routing entry + * + * @kvm: the VM this entry is applied to + * @e: kvm kernel routing entry handle + * @ue: user api routing entry handle + * return 0 on success, -EINVAL on errors. + */ +int kvm_set_routing_entry(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) +{ + int r = -EINVAL; + + switch (ue->type) { + case KVM_IRQ_ROUTING_IRQCHIP: + e->set = vgic_irqfd_set_irq; + e->irqchip.irqchip = ue->u.irqchip.irqchip; + e->irqchip.pin = ue->u.irqchip.pin; + if ((e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS) || + (e->irqchip.irqchip >= KVM_NR_IRQCHIPS)) + goto out; + break; + case KVM_IRQ_ROUTING_MSI: + e->set = kvm_set_msi; + e->msi.address_lo = ue->u.msi.address_lo; + e->msi.address_hi = ue->u.msi.address_hi; + e->msi.data = ue->u.msi.data; + e->msi.flags = ue->flags; + e->msi.devid = ue->u.msi.devid; + break; + default: + goto out; + } + r = 0; +out: + return r; +} + +static void kvm_populate_msi(struct kvm_kernel_irq_routing_entry *e, + struct kvm_msi *msi) +{ + msi->address_lo = e->msi.address_lo; + msi->address_hi = e->msi.address_hi; + msi->data = e->msi.data; + msi->flags = e->msi.flags; + msi->devid = e->msi.devid; +} +/** + * kvm_set_msi: inject the MSI corresponding to the + * MSI routing entry + * + * This is the entry point for irqfd MSI injection + * and userspace MSI injection. + */ +int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, + int level, bool line_status) +{ + struct kvm_msi msi; + + if (!vgic_has_its(kvm)) + return -ENODEV; + + if (!level) + return -1; + + kvm_populate_msi(e, &msi); + return vgic_its_inject_msi(kvm, &msi); +} + +/** + * kvm_arch_set_irq_inatomic: fast-path for irqfd injection + * + * Currently only direct MSI injection is supported. + */ +int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, + bool line_status) +{ + if (e->type == KVM_IRQ_ROUTING_MSI && vgic_has_its(kvm) && level) { + struct kvm_msi msi; + + kvm_populate_msi(e, &msi); + if (!vgic_its_inject_cached_translation(kvm, &msi)) + return 0; + } + + return -EWOULDBLOCK; +} + +int kvm_vgic_setup_default_irq_routing(struct kvm *kvm) +{ + struct kvm_irq_routing_entry *entries; + struct vgic_dist *dist = &kvm->arch.vgic; + u32 nr = dist->nr_spis; + int i, ret; + + entries = kcalloc(nr, sizeof(*entries), GFP_KERNEL); + if (!entries) + return -ENOMEM; + + for (i = 0; i < nr; i++) { + entries[i].gsi = i; + entries[i].type = KVM_IRQ_ROUTING_IRQCHIP; + entries[i].u.irqchip.irqchip = 0; + entries[i].u.irqchip.pin = i; + } + ret = kvm_set_irq_routing(kvm, entries, nr, 0); + kfree(entries); + return ret; +} diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c new file mode 100644 index 000000000000..c012a52b19f5 --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -0,0 +1,2783 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * GICv3 ITS emulation + * + * Copyright (C) 2015,2016 ARM Ltd. + * Author: Andre Przywara <andre.przywara@arm.com> + */ + +#include <linux/cpu.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/interrupt.h> +#include <linux/list.h> +#include <linux/uaccess.h> +#include <linux/list_sort.h> + +#include <linux/irqchip/arm-gic-v3.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_mmu.h> + +#include "vgic.h" +#include "vgic-mmio.h" + +static int vgic_its_save_tables_v0(struct vgic_its *its); +static int vgic_its_restore_tables_v0(struct vgic_its *its); +static int vgic_its_commit_v0(struct vgic_its *its); +static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, + struct kvm_vcpu *filter_vcpu, bool needs_inv); + +/* + * Creates a new (reference to a) struct vgic_irq for a given LPI. + * If this LPI is already mapped on another ITS, we increase its refcount + * and return a pointer to the existing structure. + * If this is a "new" LPI, we allocate and initialize a new struct vgic_irq. + * This function returns a pointer to the _unlocked_ structure. + */ +static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, + struct kvm_vcpu *vcpu) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq; + unsigned long flags; + int ret; + + /* In this case there is no put, since we keep the reference. */ + if (irq) + return irq; + + irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL); + if (!irq) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&irq->lpi_list); + INIT_LIST_HEAD(&irq->ap_list); + raw_spin_lock_init(&irq->irq_lock); + + irq->config = VGIC_CONFIG_EDGE; + kref_init(&irq->refcount); + irq->intid = intid; + irq->target_vcpu = vcpu; + irq->group = 1; + + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); + + /* + * There could be a race with another vgic_add_lpi(), so we need to + * check that we don't add a second list entry with the same LPI. + */ + list_for_each_entry(oldirq, &dist->lpi_list_head, lpi_list) { + if (oldirq->intid != intid) + continue; + + /* Someone was faster with adding this LPI, lets use that. */ + kfree(irq); + irq = oldirq; + + /* + * This increases the refcount, the caller is expected to + * call vgic_put_irq() on the returned pointer once it's + * finished with the IRQ. + */ + vgic_get_irq_kref(irq); + + goto out_unlock; + } + + list_add_tail(&irq->lpi_list, &dist->lpi_list_head); + dist->lpi_list_count++; + +out_unlock: + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + + /* + * We "cache" the configuration table entries in our struct vgic_irq's. + * However we only have those structs for mapped IRQs, so we read in + * the respective config data from memory here upon mapping the LPI. + * + * Should any of these fail, behave as if we couldn't create the LPI + * by dropping the refcount and returning the error. + */ + ret = update_lpi_config(kvm, irq, NULL, false); + if (ret) { + vgic_put_irq(kvm, irq); + return ERR_PTR(ret); + } + + ret = vgic_v3_lpi_sync_pending_status(kvm, irq); + if (ret) { + vgic_put_irq(kvm, irq); + return ERR_PTR(ret); + } + + return irq; +} + +struct its_device { + struct list_head dev_list; + + /* the head for the list of ITTEs */ + struct list_head itt_head; + u32 num_eventid_bits; + gpa_t itt_addr; + u32 device_id; +}; + +#define COLLECTION_NOT_MAPPED ((u32)~0) + +struct its_collection { + struct list_head coll_list; + + u32 collection_id; + u32 target_addr; +}; + +#define its_is_collection_mapped(coll) ((coll) && \ + ((coll)->target_addr != COLLECTION_NOT_MAPPED)) + +struct its_ite { + struct list_head ite_list; + + struct vgic_irq *irq; + struct its_collection *collection; + u32 event_id; +}; + +struct vgic_translation_cache_entry { + struct list_head entry; + phys_addr_t db; + u32 devid; + u32 eventid; + struct vgic_irq *irq; +}; + +/** + * struct vgic_its_abi - ITS abi ops and settings + * @cte_esz: collection table entry size + * @dte_esz: device table entry size + * @ite_esz: interrupt translation table entry size + * @save tables: save the ITS tables into guest RAM + * @restore_tables: restore the ITS internal structs from tables + * stored in guest RAM + * @commit: initialize the registers which expose the ABI settings, + * especially the entry sizes + */ +struct vgic_its_abi { + int cte_esz; + int dte_esz; + int ite_esz; + int (*save_tables)(struct vgic_its *its); + int (*restore_tables)(struct vgic_its *its); + int (*commit)(struct vgic_its *its); +}; + +#define ABI_0_ESZ 8 +#define ESZ_MAX ABI_0_ESZ + +static const struct vgic_its_abi its_table_abi_versions[] = { + [0] = { + .cte_esz = ABI_0_ESZ, + .dte_esz = ABI_0_ESZ, + .ite_esz = ABI_0_ESZ, + .save_tables = vgic_its_save_tables_v0, + .restore_tables = vgic_its_restore_tables_v0, + .commit = vgic_its_commit_v0, + }, +}; + +#define NR_ITS_ABIS ARRAY_SIZE(its_table_abi_versions) + +inline const struct vgic_its_abi *vgic_its_get_abi(struct vgic_its *its) +{ + return &its_table_abi_versions[its->abi_rev]; +} + +static int vgic_its_set_abi(struct vgic_its *its, u32 rev) +{ + const struct vgic_its_abi *abi; + + its->abi_rev = rev; + abi = vgic_its_get_abi(its); + return abi->commit(its); +} + +/* + * Find and returns a device in the device table for an ITS. + * Must be called with the its_lock mutex held. + */ +static struct its_device *find_its_device(struct vgic_its *its, u32 device_id) +{ + struct its_device *device; + + list_for_each_entry(device, &its->device_list, dev_list) + if (device_id == device->device_id) + return device; + + return NULL; +} + +/* + * Find and returns an interrupt translation table entry (ITTE) for a given + * Device ID/Event ID pair on an ITS. + * Must be called with the its_lock mutex held. + */ +static struct its_ite *find_ite(struct vgic_its *its, u32 device_id, + u32 event_id) +{ + struct its_device *device; + struct its_ite *ite; + + device = find_its_device(its, device_id); + if (device == NULL) + return NULL; + + list_for_each_entry(ite, &device->itt_head, ite_list) + if (ite->event_id == event_id) + return ite; + + return NULL; +} + +/* To be used as an iterator this macro misses the enclosing parentheses */ +#define for_each_lpi_its(dev, ite, its) \ + list_for_each_entry(dev, &(its)->device_list, dev_list) \ + list_for_each_entry(ite, &(dev)->itt_head, ite_list) + +#define GIC_LPI_OFFSET 8192 + +#define VITS_TYPER_IDBITS 16 +#define VITS_TYPER_DEVBITS 16 +#define VITS_DTE_MAX_DEVID_OFFSET (BIT(14) - 1) +#define VITS_ITE_MAX_EVENTID_OFFSET (BIT(16) - 1) + +/* + * Finds and returns a collection in the ITS collection table. + * Must be called with the its_lock mutex held. + */ +static struct its_collection *find_collection(struct vgic_its *its, int coll_id) +{ + struct its_collection *collection; + + list_for_each_entry(collection, &its->collection_list, coll_list) { + if (coll_id == collection->collection_id) + return collection; + } + + return NULL; +} + +#define LPI_PROP_ENABLE_BIT(p) ((p) & LPI_PROP_ENABLED) +#define LPI_PROP_PRIORITY(p) ((p) & 0xfc) + +/* + * Reads the configuration data for a given LPI from guest memory and + * updates the fields in struct vgic_irq. + * If filter_vcpu is not NULL, applies only if the IRQ is targeting this + * VCPU. Unconditionally applies if filter_vcpu is NULL. + */ +static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, + struct kvm_vcpu *filter_vcpu, bool needs_inv) +{ + u64 propbase = GICR_PROPBASER_ADDRESS(kvm->arch.vgic.propbaser); + u8 prop; + int ret; + unsigned long flags; + + ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET, + &prop, 1); + + if (ret) + return ret; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (!filter_vcpu || filter_vcpu == irq->target_vcpu) { + irq->priority = LPI_PROP_PRIORITY(prop); + irq->enabled = LPI_PROP_ENABLE_BIT(prop); + + if (!irq->hw) { + vgic_queue_irq_unlock(kvm, irq, flags); + return 0; + } + } + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + if (irq->hw) + return its_prop_update_vlpi(irq->host_irq, prop, needs_inv); + + return 0; +} + +/* + * Create a snapshot of the current LPIs targeting @vcpu, so that we can + * enumerate those LPIs without holding any lock. + * Returns their number and puts the kmalloc'ed array into intid_ptr. + */ +int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_irq *irq; + unsigned long flags; + u32 *intids; + int irq_count, i = 0; + + /* + * There is an obvious race between allocating the array and LPIs + * being mapped/unmapped. If we ended up here as a result of a + * command, we're safe (locks are held, preventing another + * command). If coming from another path (such as enabling LPIs), + * we must be careful not to overrun the array. + */ + irq_count = READ_ONCE(dist->lpi_list_count); + intids = kmalloc_array(irq_count, sizeof(intids[0]), GFP_KERNEL); + if (!intids) + return -ENOMEM; + + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); + list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { + if (i == irq_count) + break; + /* We don't need to "get" the IRQ, as we hold the list lock. */ + if (vcpu && irq->target_vcpu != vcpu) + continue; + intids[i++] = irq->intid; + } + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + + *intid_ptr = intids; + return i; +} + +static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) +{ + int ret = 0; + unsigned long flags; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->target_vcpu = vcpu; + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + if (irq->hw) { + struct its_vlpi_map map; + + ret = its_get_vlpi(irq->host_irq, &map); + if (ret) + return ret; + + if (map.vpe) + atomic_dec(&map.vpe->vlpi_count); + map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + atomic_inc(&map.vpe->vlpi_count); + + ret = its_map_vlpi(irq->host_irq, &map); + } + + return ret; +} + +/* + * Promotes the ITS view of affinity of an ITTE (which redistributor this LPI + * is targeting) to the VGIC's view, which deals with target VCPUs. + * Needs to be called whenever either the collection for a LPIs has + * changed or the collection itself got retargeted. + */ +static void update_affinity_ite(struct kvm *kvm, struct its_ite *ite) +{ + struct kvm_vcpu *vcpu; + + if (!its_is_collection_mapped(ite->collection)) + return; + + vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr); + update_affinity(ite->irq, vcpu); +} + +/* + * Updates the target VCPU for every LPI targeting this collection. + * Must be called with the its_lock mutex held. + */ +static void update_affinity_collection(struct kvm *kvm, struct vgic_its *its, + struct its_collection *coll) +{ + struct its_device *device; + struct its_ite *ite; + + for_each_lpi_its(device, ite, its) { + if (!ite->collection || coll != ite->collection) + continue; + + update_affinity_ite(kvm, ite); + } +} + +static u32 max_lpis_propbaser(u64 propbaser) +{ + int nr_idbits = (propbaser & 0x1f) + 1; + + return 1U << min(nr_idbits, INTERRUPT_ID_BITS_ITS); +} + +/* + * Sync the pending table pending bit of LPIs targeting @vcpu + * with our own data structures. This relies on the LPI being + * mapped before. + */ +static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) +{ + gpa_t pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); + struct vgic_irq *irq; + int last_byte_offset = -1; + int ret = 0; + u32 *intids; + int nr_irqs, i; + unsigned long flags; + u8 pendmask; + + nr_irqs = vgic_copy_lpi_list(vcpu->kvm, vcpu, &intids); + if (nr_irqs < 0) + return nr_irqs; + + for (i = 0; i < nr_irqs; i++) { + int byte_offset, bit_nr; + + byte_offset = intids[i] / BITS_PER_BYTE; + bit_nr = intids[i] % BITS_PER_BYTE; + + /* + * For contiguously allocated LPIs chances are we just read + * this very same byte in the last iteration. Reuse that. + */ + if (byte_offset != last_byte_offset) { + ret = kvm_read_guest_lock(vcpu->kvm, + pendbase + byte_offset, + &pendmask, 1); + if (ret) { + kfree(intids); + return ret; + } + last_byte_offset = byte_offset; + } + + irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->pending_latch = pendmask & (1U << bit_nr); + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + vgic_put_irq(vcpu->kvm, irq); + } + + kfree(intids); + + return ret; +} + +static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm, + struct vgic_its *its, + gpa_t addr, unsigned int len) +{ + const struct vgic_its_abi *abi = vgic_its_get_abi(its); + u64 reg = GITS_TYPER_PLPIS; + + /* + * We use linear CPU numbers for redistributor addressing, + * so GITS_TYPER.PTA is 0. + * Also we force all PROPBASER registers to be the same, so + * CommonLPIAff is 0 as well. + * To avoid memory waste in the guest, we keep the number of IDBits and + * DevBits low - as least for the time being. + */ + reg |= GIC_ENCODE_SZ(VITS_TYPER_DEVBITS, 5) << GITS_TYPER_DEVBITS_SHIFT; + reg |= GIC_ENCODE_SZ(VITS_TYPER_IDBITS, 5) << GITS_TYPER_IDBITS_SHIFT; + reg |= GIC_ENCODE_SZ(abi->ite_esz, 4) << GITS_TYPER_ITT_ENTRY_SIZE_SHIFT; + + return extract_bytes(reg, addr & 7, len); +} + +static unsigned long vgic_mmio_read_its_iidr(struct kvm *kvm, + struct vgic_its *its, + gpa_t addr, unsigned int len) +{ + u32 val; + + val = (its->abi_rev << GITS_IIDR_REV_SHIFT) & GITS_IIDR_REV_MASK; + val |= (PRODUCT_ID_KVM << GITS_IIDR_PRODUCTID_SHIFT) | IMPLEMENTER_ARM; + return val; +} + +static int vgic_mmio_uaccess_write_its_iidr(struct kvm *kvm, + struct vgic_its *its, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 rev = GITS_IIDR_REV(val); + + if (rev >= NR_ITS_ABIS) + return -EINVAL; + return vgic_its_set_abi(its, rev); +} + +static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm, + struct vgic_its *its, + gpa_t addr, unsigned int len) +{ + switch (addr & 0xffff) { + case GITS_PIDR0: + return 0x92; /* part number, bits[7:0] */ + case GITS_PIDR1: + return 0xb4; /* part number, bits[11:8] */ + case GITS_PIDR2: + return GIC_PIDR2_ARCH_GICv3 | 0x0b; + case GITS_PIDR4: + return 0x40; /* This is a 64K software visible page */ + /* The following are the ID registers for (any) GIC. */ + case GITS_CIDR0: + return 0x0d; + case GITS_CIDR1: + return 0xf0; + case GITS_CIDR2: + return 0x05; + case GITS_CIDR3: + return 0xb1; + } + + return 0; +} + +static struct vgic_irq *__vgic_its_check_cache(struct vgic_dist *dist, + phys_addr_t db, + u32 devid, u32 eventid) +{ + struct vgic_translation_cache_entry *cte; + + list_for_each_entry(cte, &dist->lpi_translation_cache, entry) { + /* + * If we hit a NULL entry, there is nothing after this + * point. + */ + if (!cte->irq) + break; + + if (cte->db != db || cte->devid != devid || + cte->eventid != eventid) + continue; + + /* + * Move this entry to the head, as it is the most + * recently used. + */ + if (!list_is_first(&cte->entry, &dist->lpi_translation_cache)) + list_move(&cte->entry, &dist->lpi_translation_cache); + + return cte->irq; + } + + return NULL; +} + +static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db, + u32 devid, u32 eventid) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_irq *irq; + unsigned long flags; + + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); + irq = __vgic_its_check_cache(dist, db, devid, eventid); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + + return irq; +} + +static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its, + u32 devid, u32 eventid, + struct vgic_irq *irq) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_translation_cache_entry *cte; + unsigned long flags; + phys_addr_t db; + + /* Do not cache a directly injected interrupt */ + if (irq->hw) + return; + + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); + + if (unlikely(list_empty(&dist->lpi_translation_cache))) + goto out; + + /* + * We could have raced with another CPU caching the same + * translation behind our back, so let's check it is not in + * already + */ + db = its->vgic_its_base + GITS_TRANSLATER; + if (__vgic_its_check_cache(dist, db, devid, eventid)) + goto out; + + /* Always reuse the last entry (LRU policy) */ + cte = list_last_entry(&dist->lpi_translation_cache, + typeof(*cte), entry); + + /* + * Caching the translation implies having an extra reference + * to the interrupt, so drop the potential reference on what + * was in the cache, and increment it on the new interrupt. + */ + if (cte->irq) + __vgic_put_lpi_locked(kvm, cte->irq); + + vgic_get_irq_kref(irq); + + cte->db = db; + cte->devid = devid; + cte->eventid = eventid; + cte->irq = irq; + + /* Move the new translation to the head of the list */ + list_move(&cte->entry, &dist->lpi_translation_cache); + +out: + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); +} + +void vgic_its_invalidate_cache(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_translation_cache_entry *cte; + unsigned long flags; + + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); + + list_for_each_entry(cte, &dist->lpi_translation_cache, entry) { + /* + * If we hit a NULL entry, there is nothing after this + * point. + */ + if (!cte->irq) + break; + + __vgic_put_lpi_locked(kvm, cte->irq); + cte->irq = NULL; + } + + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); +} + +int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, + u32 devid, u32 eventid, struct vgic_irq **irq) +{ + struct kvm_vcpu *vcpu; + struct its_ite *ite; + + if (!its->enabled) + return -EBUSY; + + ite = find_ite(its, devid, eventid); + if (!ite || !its_is_collection_mapped(ite->collection)) + return E_ITS_INT_UNMAPPED_INTERRUPT; + + vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr); + if (!vcpu) + return E_ITS_INT_UNMAPPED_INTERRUPT; + + if (!vcpu->arch.vgic_cpu.lpis_enabled) + return -EBUSY; + + vgic_its_cache_translation(kvm, its, devid, eventid, ite->irq); + + *irq = ite->irq; + return 0; +} + +struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi) +{ + u64 address; + struct kvm_io_device *kvm_io_dev; + struct vgic_io_device *iodev; + + if (!vgic_has_its(kvm)) + return ERR_PTR(-ENODEV); + + if (!(msi->flags & KVM_MSI_VALID_DEVID)) + return ERR_PTR(-EINVAL); + + address = (u64)msi->address_hi << 32 | msi->address_lo; + + kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, address); + if (!kvm_io_dev) + return ERR_PTR(-EINVAL); + + if (kvm_io_dev->ops != &kvm_io_gic_ops) + return ERR_PTR(-EINVAL); + + iodev = container_of(kvm_io_dev, struct vgic_io_device, dev); + if (iodev->iodev_type != IODEV_ITS) + return ERR_PTR(-EINVAL); + + return iodev->its; +} + +/* + * Find the target VCPU and the LPI number for a given devid/eventid pair + * and make this IRQ pending, possibly injecting it. + * Must be called with the its_lock mutex held. + * Returns 0 on success, a positive error value for any ITS mapping + * related errors and negative error values for generic errors. + */ +static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, + u32 devid, u32 eventid) +{ + struct vgic_irq *irq = NULL; + unsigned long flags; + int err; + + err = vgic_its_resolve_lpi(kvm, its, devid, eventid, &irq); + if (err) + return err; + + if (irq->hw) + return irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, true); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->pending_latch = true; + vgic_queue_irq_unlock(kvm, irq, flags); + + return 0; +} + +int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi) +{ + struct vgic_irq *irq; + unsigned long flags; + phys_addr_t db; + + db = (u64)msi->address_hi << 32 | msi->address_lo; + irq = vgic_its_check_cache(kvm, db, msi->devid, msi->data); + + if (!irq) + return -1; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->pending_latch = true; + vgic_queue_irq_unlock(kvm, irq, flags); + + return 0; +} + +/* + * Queries the KVM IO bus framework to get the ITS pointer from the given + * doorbell address. + * We then call vgic_its_trigger_msi() with the decoded data. + * According to the KVM_SIGNAL_MSI API description returns 1 on success. + */ +int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) +{ + struct vgic_its *its; + int ret; + + if (!vgic_its_inject_cached_translation(kvm, msi)) + return 1; + + its = vgic_msi_to_its(kvm, msi); + if (IS_ERR(its)) + return PTR_ERR(its); + + mutex_lock(&its->its_lock); + ret = vgic_its_trigger_msi(kvm, its, msi->devid, msi->data); + mutex_unlock(&its->its_lock); + + if (ret < 0) + return ret; + + /* + * KVM_SIGNAL_MSI demands a return value > 0 for success and 0 + * if the guest has blocked the MSI. So we map any LPI mapping + * related error to that. + */ + if (ret) + return 0; + else + return 1; +} + +/* Requires the its_lock to be held. */ +static void its_free_ite(struct kvm *kvm, struct its_ite *ite) +{ + list_del(&ite->ite_list); + + /* This put matches the get in vgic_add_lpi. */ + if (ite->irq) { + if (ite->irq->hw) + WARN_ON(its_unmap_vlpi(ite->irq->host_irq)); + + vgic_put_irq(kvm, ite->irq); + } + + kfree(ite); +} + +static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size) +{ + return (le64_to_cpu(its_cmd[word]) >> shift) & (BIT_ULL(size) - 1); +} + +#define its_cmd_get_command(cmd) its_cmd_mask_field(cmd, 0, 0, 8) +#define its_cmd_get_deviceid(cmd) its_cmd_mask_field(cmd, 0, 32, 32) +#define its_cmd_get_size(cmd) (its_cmd_mask_field(cmd, 1, 0, 5) + 1) +#define its_cmd_get_id(cmd) its_cmd_mask_field(cmd, 1, 0, 32) +#define its_cmd_get_physical_id(cmd) its_cmd_mask_field(cmd, 1, 32, 32) +#define its_cmd_get_collection(cmd) its_cmd_mask_field(cmd, 2, 0, 16) +#define its_cmd_get_ittaddr(cmd) (its_cmd_mask_field(cmd, 2, 8, 44) << 8) +#define its_cmd_get_target_addr(cmd) its_cmd_mask_field(cmd, 2, 16, 32) +#define its_cmd_get_validbit(cmd) its_cmd_mask_field(cmd, 2, 63, 1) + +/* + * The DISCARD command frees an Interrupt Translation Table Entry (ITTE). + * Must be called with the its_lock mutex held. + */ +static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its, + u64 *its_cmd) +{ + u32 device_id = its_cmd_get_deviceid(its_cmd); + u32 event_id = its_cmd_get_id(its_cmd); + struct its_ite *ite; + + ite = find_ite(its, device_id, event_id); + if (ite && its_is_collection_mapped(ite->collection)) { + /* + * Though the spec talks about removing the pending state, we + * don't bother here since we clear the ITTE anyway and the + * pending state is a property of the ITTE struct. + */ + vgic_its_invalidate_cache(kvm); + + its_free_ite(kvm, ite); + return 0; + } + + return E_ITS_DISCARD_UNMAPPED_INTERRUPT; +} + +/* + * The MOVI command moves an ITTE to a different collection. + * Must be called with the its_lock mutex held. + */ +static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its, + u64 *its_cmd) +{ + u32 device_id = its_cmd_get_deviceid(its_cmd); + u32 event_id = its_cmd_get_id(its_cmd); + u32 coll_id = its_cmd_get_collection(its_cmd); + struct kvm_vcpu *vcpu; + struct its_ite *ite; + struct its_collection *collection; + + ite = find_ite(its, device_id, event_id); + if (!ite) + return E_ITS_MOVI_UNMAPPED_INTERRUPT; + + if (!its_is_collection_mapped(ite->collection)) + return E_ITS_MOVI_UNMAPPED_COLLECTION; + + collection = find_collection(its, coll_id); + if (!its_is_collection_mapped(collection)) + return E_ITS_MOVI_UNMAPPED_COLLECTION; + + ite->collection = collection; + vcpu = kvm_get_vcpu(kvm, collection->target_addr); + + vgic_its_invalidate_cache(kvm); + + return update_affinity(ite->irq, vcpu); +} + +/* + * Check whether an ID can be stored into the corresponding guest table. + * For a direct table this is pretty easy, but gets a bit nasty for + * indirect tables. We check whether the resulting guest physical address + * is actually valid (covered by a memslot and guest accessible). + * For this we have to read the respective first level entry. + */ +static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, + gpa_t *eaddr) +{ + int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; + u64 indirect_ptr, type = GITS_BASER_TYPE(baser); + phys_addr_t base = GITS_BASER_ADDR_48_to_52(baser); + int esz = GITS_BASER_ENTRY_SIZE(baser); + int index, idx; + gfn_t gfn; + bool ret; + + switch (type) { + case GITS_BASER_TYPE_DEVICE: + if (id >= BIT_ULL(VITS_TYPER_DEVBITS)) + return false; + break; + case GITS_BASER_TYPE_COLLECTION: + /* as GITS_TYPER.CIL == 0, ITS supports 16-bit collection ID */ + if (id >= BIT_ULL(16)) + return false; + break; + default: + return false; + } + + if (!(baser & GITS_BASER_INDIRECT)) { + phys_addr_t addr; + + if (id >= (l1_tbl_size / esz)) + return false; + + addr = base + id * esz; + gfn = addr >> PAGE_SHIFT; + + if (eaddr) + *eaddr = addr; + + goto out; + } + + /* calculate and check the index into the 1st level */ + index = id / (SZ_64K / esz); + if (index >= (l1_tbl_size / sizeof(u64))) + return false; + + /* Each 1st level entry is represented by a 64-bit value. */ + if (kvm_read_guest_lock(its->dev->kvm, + base + index * sizeof(indirect_ptr), + &indirect_ptr, sizeof(indirect_ptr))) + return false; + + indirect_ptr = le64_to_cpu(indirect_ptr); + + /* check the valid bit of the first level entry */ + if (!(indirect_ptr & BIT_ULL(63))) + return false; + + /* Mask the guest physical address and calculate the frame number. */ + indirect_ptr &= GENMASK_ULL(51, 16); + + /* Find the address of the actual entry */ + index = id % (SZ_64K / esz); + indirect_ptr += index * esz; + gfn = indirect_ptr >> PAGE_SHIFT; + + if (eaddr) + *eaddr = indirect_ptr; + +out: + idx = srcu_read_lock(&its->dev->kvm->srcu); + ret = kvm_is_visible_gfn(its->dev->kvm, gfn); + srcu_read_unlock(&its->dev->kvm->srcu, idx); + return ret; +} + +static int vgic_its_alloc_collection(struct vgic_its *its, + struct its_collection **colp, + u32 coll_id) +{ + struct its_collection *collection; + + if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) + return E_ITS_MAPC_COLLECTION_OOR; + + collection = kzalloc(sizeof(*collection), GFP_KERNEL); + if (!collection) + return -ENOMEM; + + collection->collection_id = coll_id; + collection->target_addr = COLLECTION_NOT_MAPPED; + + list_add_tail(&collection->coll_list, &its->collection_list); + *colp = collection; + + return 0; +} + +static void vgic_its_free_collection(struct vgic_its *its, u32 coll_id) +{ + struct its_collection *collection; + struct its_device *device; + struct its_ite *ite; + + /* + * Clearing the mapping for that collection ID removes the + * entry from the list. If there wasn't any before, we can + * go home early. + */ + collection = find_collection(its, coll_id); + if (!collection) + return; + + for_each_lpi_its(device, ite, its) + if (ite->collection && + ite->collection->collection_id == coll_id) + ite->collection = NULL; + + list_del(&collection->coll_list); + kfree(collection); +} + +/* Must be called with its_lock mutex held */ +static struct its_ite *vgic_its_alloc_ite(struct its_device *device, + struct its_collection *collection, + u32 event_id) +{ + struct its_ite *ite; + + ite = kzalloc(sizeof(*ite), GFP_KERNEL); + if (!ite) + return ERR_PTR(-ENOMEM); + + ite->event_id = event_id; + ite->collection = collection; + + list_add_tail(&ite->ite_list, &device->itt_head); + return ite; +} + +/* + * The MAPTI and MAPI commands map LPIs to ITTEs. + * Must be called with its_lock mutex held. + */ +static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, + u64 *its_cmd) +{ + u32 device_id = its_cmd_get_deviceid(its_cmd); + u32 event_id = its_cmd_get_id(its_cmd); + u32 coll_id = its_cmd_get_collection(its_cmd); + struct its_ite *ite; + struct kvm_vcpu *vcpu = NULL; + struct its_device *device; + struct its_collection *collection, *new_coll = NULL; + struct vgic_irq *irq; + int lpi_nr; + + device = find_its_device(its, device_id); + if (!device) + return E_ITS_MAPTI_UNMAPPED_DEVICE; + + if (event_id >= BIT_ULL(device->num_eventid_bits)) + return E_ITS_MAPTI_ID_OOR; + + if (its_cmd_get_command(its_cmd) == GITS_CMD_MAPTI) + lpi_nr = its_cmd_get_physical_id(its_cmd); + else + lpi_nr = event_id; + if (lpi_nr < GIC_LPI_OFFSET || + lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser)) + return E_ITS_MAPTI_PHYSICALID_OOR; + + /* If there is an existing mapping, behavior is UNPREDICTABLE. */ + if (find_ite(its, device_id, event_id)) + return 0; + + collection = find_collection(its, coll_id); + if (!collection) { + int ret = vgic_its_alloc_collection(its, &collection, coll_id); + if (ret) + return ret; + new_coll = collection; + } + + ite = vgic_its_alloc_ite(device, collection, event_id); + if (IS_ERR(ite)) { + if (new_coll) + vgic_its_free_collection(its, coll_id); + return PTR_ERR(ite); + } + + if (its_is_collection_mapped(collection)) + vcpu = kvm_get_vcpu(kvm, collection->target_addr); + + irq = vgic_add_lpi(kvm, lpi_nr, vcpu); + if (IS_ERR(irq)) { + if (new_coll) + vgic_its_free_collection(its, coll_id); + its_free_ite(kvm, ite); + return PTR_ERR(irq); + } + ite->irq = irq; + + return 0; +} + +/* Requires the its_lock to be held. */ +static void vgic_its_free_device(struct kvm *kvm, struct its_device *device) +{ + struct its_ite *ite, *temp; + + /* + * The spec says that unmapping a device with still valid + * ITTEs associated is UNPREDICTABLE. We remove all ITTEs, + * since we cannot leave the memory unreferenced. + */ + list_for_each_entry_safe(ite, temp, &device->itt_head, ite_list) + its_free_ite(kvm, ite); + + vgic_its_invalidate_cache(kvm); + + list_del(&device->dev_list); + kfree(device); +} + +/* its lock must be held */ +static void vgic_its_free_device_list(struct kvm *kvm, struct vgic_its *its) +{ + struct its_device *cur, *temp; + + list_for_each_entry_safe(cur, temp, &its->device_list, dev_list) + vgic_its_free_device(kvm, cur); +} + +/* its lock must be held */ +static void vgic_its_free_collection_list(struct kvm *kvm, struct vgic_its *its) +{ + struct its_collection *cur, *temp; + + list_for_each_entry_safe(cur, temp, &its->collection_list, coll_list) + vgic_its_free_collection(its, cur->collection_id); +} + +/* Must be called with its_lock mutex held */ +static struct its_device *vgic_its_alloc_device(struct vgic_its *its, + u32 device_id, gpa_t itt_addr, + u8 num_eventid_bits) +{ + struct its_device *device; + + device = kzalloc(sizeof(*device), GFP_KERNEL); + if (!device) + return ERR_PTR(-ENOMEM); + + device->device_id = device_id; + device->itt_addr = itt_addr; + device->num_eventid_bits = num_eventid_bits; + INIT_LIST_HEAD(&device->itt_head); + + list_add_tail(&device->dev_list, &its->device_list); + return device; +} + +/* + * MAPD maps or unmaps a device ID to Interrupt Translation Tables (ITTs). + * Must be called with the its_lock mutex held. + */ +static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its, + u64 *its_cmd) +{ + u32 device_id = its_cmd_get_deviceid(its_cmd); + bool valid = its_cmd_get_validbit(its_cmd); + u8 num_eventid_bits = its_cmd_get_size(its_cmd); + gpa_t itt_addr = its_cmd_get_ittaddr(its_cmd); + struct its_device *device; + + if (!vgic_its_check_id(its, its->baser_device_table, device_id, NULL)) + return E_ITS_MAPD_DEVICE_OOR; + + if (valid && num_eventid_bits > VITS_TYPER_IDBITS) + return E_ITS_MAPD_ITTSIZE_OOR; + + device = find_its_device(its, device_id); + + /* + * The spec says that calling MAPD on an already mapped device + * invalidates all cached data for this device. We implement this + * by removing the mapping and re-establishing it. + */ + if (device) + vgic_its_free_device(kvm, device); + + /* + * The spec does not say whether unmapping a not-mapped device + * is an error, so we are done in any case. + */ + if (!valid) + return 0; + + device = vgic_its_alloc_device(its, device_id, itt_addr, + num_eventid_bits); + + return PTR_ERR_OR_ZERO(device); +} + +/* + * The MAPC command maps collection IDs to redistributors. + * Must be called with the its_lock mutex held. + */ +static int vgic_its_cmd_handle_mapc(struct kvm *kvm, struct vgic_its *its, + u64 *its_cmd) +{ + u16 coll_id; + u32 target_addr; + struct its_collection *collection; + bool valid; + + valid = its_cmd_get_validbit(its_cmd); + coll_id = its_cmd_get_collection(its_cmd); + target_addr = its_cmd_get_target_addr(its_cmd); + + if (target_addr >= atomic_read(&kvm->online_vcpus)) + return E_ITS_MAPC_PROCNUM_OOR; + + if (!valid) { + vgic_its_free_collection(its, coll_id); + vgic_its_invalidate_cache(kvm); + } else { + collection = find_collection(its, coll_id); + + if (!collection) { + int ret; + + ret = vgic_its_alloc_collection(its, &collection, + coll_id); + if (ret) + return ret; + collection->target_addr = target_addr; + } else { + collection->target_addr = target_addr; + update_affinity_collection(kvm, its, collection); + } + } + + return 0; +} + +/* + * The CLEAR command removes the pending state for a particular LPI. + * Must be called with the its_lock mutex held. + */ +static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its, + u64 *its_cmd) +{ + u32 device_id = its_cmd_get_deviceid(its_cmd); + u32 event_id = its_cmd_get_id(its_cmd); + struct its_ite *ite; + + + ite = find_ite(its, device_id, event_id); + if (!ite) + return E_ITS_CLEAR_UNMAPPED_INTERRUPT; + + ite->irq->pending_latch = false; + + if (ite->irq->hw) + return irq_set_irqchip_state(ite->irq->host_irq, + IRQCHIP_STATE_PENDING, false); + + return 0; +} + +/* + * The INV command syncs the configuration bits from the memory table. + * Must be called with the its_lock mutex held. + */ +static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its, + u64 *its_cmd) +{ + u32 device_id = its_cmd_get_deviceid(its_cmd); + u32 event_id = its_cmd_get_id(its_cmd); + struct its_ite *ite; + + + ite = find_ite(its, device_id, event_id); + if (!ite) + return E_ITS_INV_UNMAPPED_INTERRUPT; + + return update_lpi_config(kvm, ite->irq, NULL, true); +} + +/* + * The INVALL command requests flushing of all IRQ data in this collection. + * Find the VCPU mapped to that collection, then iterate over the VM's list + * of mapped LPIs and update the configuration for each IRQ which targets + * the specified vcpu. The configuration will be read from the in-memory + * configuration table. + * Must be called with the its_lock mutex held. + */ +static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its, + u64 *its_cmd) +{ + u32 coll_id = its_cmd_get_collection(its_cmd); + struct its_collection *collection; + struct kvm_vcpu *vcpu; + struct vgic_irq *irq; + u32 *intids; + int irq_count, i; + + collection = find_collection(its, coll_id); + if (!its_is_collection_mapped(collection)) + return E_ITS_INVALL_UNMAPPED_COLLECTION; + + vcpu = kvm_get_vcpu(kvm, collection->target_addr); + + irq_count = vgic_copy_lpi_list(kvm, vcpu, &intids); + if (irq_count < 0) + return irq_count; + + for (i = 0; i < irq_count; i++) { + irq = vgic_get_irq(kvm, NULL, intids[i]); + if (!irq) + continue; + update_lpi_config(kvm, irq, vcpu, false); + vgic_put_irq(kvm, irq); + } + + kfree(intids); + + if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm) + its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe); + + return 0; +} + +/* + * The MOVALL command moves the pending state of all IRQs targeting one + * redistributor to another. We don't hold the pending state in the VCPUs, + * but in the IRQs instead, so there is really not much to do for us here. + * However the spec says that no IRQ must target the old redistributor + * afterwards, so we make sure that no LPI is using the associated target_vcpu. + * This command affects all LPIs in the system that target that redistributor. + */ +static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, + u64 *its_cmd) +{ + u32 target1_addr = its_cmd_get_target_addr(its_cmd); + u32 target2_addr = its_cmd_mask_field(its_cmd, 3, 16, 32); + struct kvm_vcpu *vcpu1, *vcpu2; + struct vgic_irq *irq; + u32 *intids; + int irq_count, i; + + if (target1_addr >= atomic_read(&kvm->online_vcpus) || + target2_addr >= atomic_read(&kvm->online_vcpus)) + return E_ITS_MOVALL_PROCNUM_OOR; + + if (target1_addr == target2_addr) + return 0; + + vcpu1 = kvm_get_vcpu(kvm, target1_addr); + vcpu2 = kvm_get_vcpu(kvm, target2_addr); + + irq_count = vgic_copy_lpi_list(kvm, vcpu1, &intids); + if (irq_count < 0) + return irq_count; + + for (i = 0; i < irq_count; i++) { + irq = vgic_get_irq(kvm, NULL, intids[i]); + + update_affinity(irq, vcpu2); + + vgic_put_irq(kvm, irq); + } + + vgic_its_invalidate_cache(kvm); + + kfree(intids); + return 0; +} + +/* + * The INT command injects the LPI associated with that DevID/EvID pair. + * Must be called with the its_lock mutex held. + */ +static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its, + u64 *its_cmd) +{ + u32 msi_data = its_cmd_get_id(its_cmd); + u64 msi_devid = its_cmd_get_deviceid(its_cmd); + + return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); +} + +/* + * This function is called with the its_cmd lock held, but the ITS data + * structure lock dropped. + */ +static int vgic_its_handle_command(struct kvm *kvm, struct vgic_its *its, + u64 *its_cmd) +{ + int ret = -ENODEV; + + mutex_lock(&its->its_lock); + switch (its_cmd_get_command(its_cmd)) { + case GITS_CMD_MAPD: + ret = vgic_its_cmd_handle_mapd(kvm, its, its_cmd); + break; + case GITS_CMD_MAPC: + ret = vgic_its_cmd_handle_mapc(kvm, its, its_cmd); + break; + case GITS_CMD_MAPI: + ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd); + break; + case GITS_CMD_MAPTI: + ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd); + break; + case GITS_CMD_MOVI: + ret = vgic_its_cmd_handle_movi(kvm, its, its_cmd); + break; + case GITS_CMD_DISCARD: + ret = vgic_its_cmd_handle_discard(kvm, its, its_cmd); + break; + case GITS_CMD_CLEAR: + ret = vgic_its_cmd_handle_clear(kvm, its, its_cmd); + break; + case GITS_CMD_MOVALL: + ret = vgic_its_cmd_handle_movall(kvm, its, its_cmd); + break; + case GITS_CMD_INT: + ret = vgic_its_cmd_handle_int(kvm, its, its_cmd); + break; + case GITS_CMD_INV: + ret = vgic_its_cmd_handle_inv(kvm, its, its_cmd); + break; + case GITS_CMD_INVALL: + ret = vgic_its_cmd_handle_invall(kvm, its, its_cmd); + break; + case GITS_CMD_SYNC: + /* we ignore this command: we are in sync all of the time */ + ret = 0; + break; + } + mutex_unlock(&its->its_lock); + + return ret; +} + +static u64 vgic_sanitise_its_baser(u64 reg) +{ + reg = vgic_sanitise_field(reg, GITS_BASER_SHAREABILITY_MASK, + GITS_BASER_SHAREABILITY_SHIFT, + vgic_sanitise_shareability); + reg = vgic_sanitise_field(reg, GITS_BASER_INNER_CACHEABILITY_MASK, + GITS_BASER_INNER_CACHEABILITY_SHIFT, + vgic_sanitise_inner_cacheability); + reg = vgic_sanitise_field(reg, GITS_BASER_OUTER_CACHEABILITY_MASK, + GITS_BASER_OUTER_CACHEABILITY_SHIFT, + vgic_sanitise_outer_cacheability); + + /* We support only one (ITS) page size: 64K */ + reg = (reg & ~GITS_BASER_PAGE_SIZE_MASK) | GITS_BASER_PAGE_SIZE_64K; + + return reg; +} + +static u64 vgic_sanitise_its_cbaser(u64 reg) +{ + reg = vgic_sanitise_field(reg, GITS_CBASER_SHAREABILITY_MASK, + GITS_CBASER_SHAREABILITY_SHIFT, + vgic_sanitise_shareability); + reg = vgic_sanitise_field(reg, GITS_CBASER_INNER_CACHEABILITY_MASK, + GITS_CBASER_INNER_CACHEABILITY_SHIFT, + vgic_sanitise_inner_cacheability); + reg = vgic_sanitise_field(reg, GITS_CBASER_OUTER_CACHEABILITY_MASK, + GITS_CBASER_OUTER_CACHEABILITY_SHIFT, + vgic_sanitise_outer_cacheability); + + /* Sanitise the physical address to be 64k aligned. */ + reg &= ~GENMASK_ULL(15, 12); + + return reg; +} + +static unsigned long vgic_mmio_read_its_cbaser(struct kvm *kvm, + struct vgic_its *its, + gpa_t addr, unsigned int len) +{ + return extract_bytes(its->cbaser, addr & 7, len); +} + +static void vgic_mmio_write_its_cbaser(struct kvm *kvm, struct vgic_its *its, + gpa_t addr, unsigned int len, + unsigned long val) +{ + /* When GITS_CTLR.Enable is 1, this register is RO. */ + if (its->enabled) + return; + + mutex_lock(&its->cmd_lock); + its->cbaser = update_64bit_reg(its->cbaser, addr & 7, len, val); + its->cbaser = vgic_sanitise_its_cbaser(its->cbaser); + its->creadr = 0; + /* + * CWRITER is architecturally UNKNOWN on reset, but we need to reset + * it to CREADR to make sure we start with an empty command buffer. + */ + its->cwriter = its->creadr; + mutex_unlock(&its->cmd_lock); +} + +#define ITS_CMD_BUFFER_SIZE(baser) ((((baser) & 0xff) + 1) << 12) +#define ITS_CMD_SIZE 32 +#define ITS_CMD_OFFSET(reg) ((reg) & GENMASK(19, 5)) + +/* Must be called with the cmd_lock held. */ +static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its) +{ + gpa_t cbaser; + u64 cmd_buf[4]; + + /* Commands are only processed when the ITS is enabled. */ + if (!its->enabled) + return; + + cbaser = GITS_CBASER_ADDRESS(its->cbaser); + + while (its->cwriter != its->creadr) { + int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr, + cmd_buf, ITS_CMD_SIZE); + /* + * If kvm_read_guest() fails, this could be due to the guest + * programming a bogus value in CBASER or something else going + * wrong from which we cannot easily recover. + * According to section 6.3.2 in the GICv3 spec we can just + * ignore that command then. + */ + if (!ret) + vgic_its_handle_command(kvm, its, cmd_buf); + + its->creadr += ITS_CMD_SIZE; + if (its->creadr == ITS_CMD_BUFFER_SIZE(its->cbaser)) + its->creadr = 0; + } +} + +/* + * By writing to CWRITER the guest announces new commands to be processed. + * To avoid any races in the first place, we take the its_cmd lock, which + * protects our ring buffer variables, so that there is only one user + * per ITS handling commands at a given time. + */ +static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u64 reg; + + if (!its) + return; + + mutex_lock(&its->cmd_lock); + + reg = update_64bit_reg(its->cwriter, addr & 7, len, val); + reg = ITS_CMD_OFFSET(reg); + if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { + mutex_unlock(&its->cmd_lock); + return; + } + its->cwriter = reg; + + vgic_its_process_commands(kvm, its); + + mutex_unlock(&its->cmd_lock); +} + +static unsigned long vgic_mmio_read_its_cwriter(struct kvm *kvm, + struct vgic_its *its, + gpa_t addr, unsigned int len) +{ + return extract_bytes(its->cwriter, addr & 0x7, len); +} + +static unsigned long vgic_mmio_read_its_creadr(struct kvm *kvm, + struct vgic_its *its, + gpa_t addr, unsigned int len) +{ + return extract_bytes(its->creadr, addr & 0x7, len); +} + +static int vgic_mmio_uaccess_write_its_creadr(struct kvm *kvm, + struct vgic_its *its, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 cmd_offset; + int ret = 0; + + mutex_lock(&its->cmd_lock); + + if (its->enabled) { + ret = -EBUSY; + goto out; + } + + cmd_offset = ITS_CMD_OFFSET(val); + if (cmd_offset >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { + ret = -EINVAL; + goto out; + } + + its->creadr = cmd_offset; +out: + mutex_unlock(&its->cmd_lock); + return ret; +} + +#define BASER_INDEX(addr) (((addr) / sizeof(u64)) & 0x7) +static unsigned long vgic_mmio_read_its_baser(struct kvm *kvm, + struct vgic_its *its, + gpa_t addr, unsigned int len) +{ + u64 reg; + + switch (BASER_INDEX(addr)) { + case 0: + reg = its->baser_device_table; + break; + case 1: + reg = its->baser_coll_table; + break; + default: + reg = 0; + break; + } + + return extract_bytes(reg, addr & 7, len); +} + +#define GITS_BASER_RO_MASK (GENMASK_ULL(52, 48) | GENMASK_ULL(58, 56)) +static void vgic_mmio_write_its_baser(struct kvm *kvm, + struct vgic_its *its, + gpa_t addr, unsigned int len, + unsigned long val) +{ + const struct vgic_its_abi *abi = vgic_its_get_abi(its); + u64 entry_size, table_type; + u64 reg, *regptr, clearbits = 0; + + /* When GITS_CTLR.Enable is 1, we ignore write accesses. */ + if (its->enabled) + return; + + switch (BASER_INDEX(addr)) { + case 0: + regptr = &its->baser_device_table; + entry_size = abi->dte_esz; + table_type = GITS_BASER_TYPE_DEVICE; + break; + case 1: + regptr = &its->baser_coll_table; + entry_size = abi->cte_esz; + table_type = GITS_BASER_TYPE_COLLECTION; + clearbits = GITS_BASER_INDIRECT; + break; + default: + return; + } + + reg = update_64bit_reg(*regptr, addr & 7, len, val); + reg &= ~GITS_BASER_RO_MASK; + reg &= ~clearbits; + + reg |= (entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT; + reg |= table_type << GITS_BASER_TYPE_SHIFT; + reg = vgic_sanitise_its_baser(reg); + + *regptr = reg; + + if (!(reg & GITS_BASER_VALID)) { + /* Take the its_lock to prevent a race with a save/restore */ + mutex_lock(&its->its_lock); + switch (table_type) { + case GITS_BASER_TYPE_DEVICE: + vgic_its_free_device_list(kvm, its); + break; + case GITS_BASER_TYPE_COLLECTION: + vgic_its_free_collection_list(kvm, its); + break; + } + mutex_unlock(&its->its_lock); + } +} + +static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu, + struct vgic_its *its, + gpa_t addr, unsigned int len) +{ + u32 reg = 0; + + mutex_lock(&its->cmd_lock); + if (its->creadr == its->cwriter) + reg |= GITS_CTLR_QUIESCENT; + if (its->enabled) + reg |= GITS_CTLR_ENABLE; + mutex_unlock(&its->cmd_lock); + + return reg; +} + +static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its, + gpa_t addr, unsigned int len, + unsigned long val) +{ + mutex_lock(&its->cmd_lock); + + /* + * It is UNPREDICTABLE to enable the ITS if any of the CBASER or + * device/collection BASER are invalid + */ + if (!its->enabled && (val & GITS_CTLR_ENABLE) && + (!(its->baser_device_table & GITS_BASER_VALID) || + !(its->baser_coll_table & GITS_BASER_VALID) || + !(its->cbaser & GITS_CBASER_VALID))) + goto out; + + its->enabled = !!(val & GITS_CTLR_ENABLE); + if (!its->enabled) + vgic_its_invalidate_cache(kvm); + + /* + * Try to process any pending commands. This function bails out early + * if the ITS is disabled or no commands have been queued. + */ + vgic_its_process_commands(kvm, its); + +out: + mutex_unlock(&its->cmd_lock); +} + +#define REGISTER_ITS_DESC(off, rd, wr, length, acc) \ +{ \ + .reg_offset = off, \ + .len = length, \ + .access_flags = acc, \ + .its_read = rd, \ + .its_write = wr, \ +} + +#define REGISTER_ITS_DESC_UACCESS(off, rd, wr, uwr, length, acc)\ +{ \ + .reg_offset = off, \ + .len = length, \ + .access_flags = acc, \ + .its_read = rd, \ + .its_write = wr, \ + .uaccess_its_write = uwr, \ +} + +static void its_mmio_write_wi(struct kvm *kvm, struct vgic_its *its, + gpa_t addr, unsigned int len, unsigned long val) +{ + /* Ignore */ +} + +static struct vgic_register_region its_registers[] = { + REGISTER_ITS_DESC(GITS_CTLR, + vgic_mmio_read_its_ctlr, vgic_mmio_write_its_ctlr, 4, + VGIC_ACCESS_32bit), + REGISTER_ITS_DESC_UACCESS(GITS_IIDR, + vgic_mmio_read_its_iidr, its_mmio_write_wi, + vgic_mmio_uaccess_write_its_iidr, 4, + VGIC_ACCESS_32bit), + REGISTER_ITS_DESC(GITS_TYPER, + vgic_mmio_read_its_typer, its_mmio_write_wi, 8, + VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_ITS_DESC(GITS_CBASER, + vgic_mmio_read_its_cbaser, vgic_mmio_write_its_cbaser, 8, + VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_ITS_DESC(GITS_CWRITER, + vgic_mmio_read_its_cwriter, vgic_mmio_write_its_cwriter, 8, + VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_ITS_DESC_UACCESS(GITS_CREADR, + vgic_mmio_read_its_creadr, its_mmio_write_wi, + vgic_mmio_uaccess_write_its_creadr, 8, + VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_ITS_DESC(GITS_BASER, + vgic_mmio_read_its_baser, vgic_mmio_write_its_baser, 0x40, + VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_ITS_DESC(GITS_IDREGS_BASE, + vgic_mmio_read_its_idregs, its_mmio_write_wi, 0x30, + VGIC_ACCESS_32bit), +}; + +/* This is called on setting the LPI enable bit in the redistributor. */ +void vgic_enable_lpis(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.vgic_cpu.pendbaser & GICR_PENDBASER_PTZ)) + its_sync_lpi_pending_table(vcpu); +} + +static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its, + u64 addr) +{ + struct vgic_io_device *iodev = &its->iodev; + int ret; + + mutex_lock(&kvm->slots_lock); + if (!IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { + ret = -EBUSY; + goto out; + } + + its->vgic_its_base = addr; + iodev->regions = its_registers; + iodev->nr_regions = ARRAY_SIZE(its_registers); + kvm_iodevice_init(&iodev->dev, &kvm_io_gic_ops); + + iodev->base_addr = its->vgic_its_base; + iodev->iodev_type = IODEV_ITS; + iodev->its = its; + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, iodev->base_addr, + KVM_VGIC_V3_ITS_SIZE, &iodev->dev); +out: + mutex_unlock(&kvm->slots_lock); + + return ret; +} + +/* Default is 16 cached LPIs per vcpu */ +#define LPI_DEFAULT_PCPU_CACHE_SIZE 16 + +void vgic_lpi_translation_cache_init(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + unsigned int sz; + int i; + + if (!list_empty(&dist->lpi_translation_cache)) + return; + + sz = atomic_read(&kvm->online_vcpus) * LPI_DEFAULT_PCPU_CACHE_SIZE; + + for (i = 0; i < sz; i++) { + struct vgic_translation_cache_entry *cte; + + /* An allocation failure is not fatal */ + cte = kzalloc(sizeof(*cte), GFP_KERNEL); + if (WARN_ON(!cte)) + break; + + INIT_LIST_HEAD(&cte->entry); + list_add(&cte->entry, &dist->lpi_translation_cache); + } +} + +void vgic_lpi_translation_cache_destroy(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_translation_cache_entry *cte, *tmp; + + vgic_its_invalidate_cache(kvm); + + list_for_each_entry_safe(cte, tmp, + &dist->lpi_translation_cache, entry) { + list_del(&cte->entry); + kfree(cte); + } +} + +#define INITIAL_BASER_VALUE \ + (GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb) | \ + GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner) | \ + GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) | \ + GITS_BASER_PAGE_SIZE_64K) + +#define INITIAL_PROPBASER_VALUE \ + (GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWb) | \ + GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, SameAsInner) | \ + GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable)) + +static int vgic_its_create(struct kvm_device *dev, u32 type) +{ + struct vgic_its *its; + + if (type != KVM_DEV_TYPE_ARM_VGIC_ITS) + return -ENODEV; + + its = kzalloc(sizeof(struct vgic_its), GFP_KERNEL); + if (!its) + return -ENOMEM; + + if (vgic_initialized(dev->kvm)) { + int ret = vgic_v4_init(dev->kvm); + if (ret < 0) { + kfree(its); + return ret; + } + + vgic_lpi_translation_cache_init(dev->kvm); + } + + mutex_init(&its->its_lock); + mutex_init(&its->cmd_lock); + + its->vgic_its_base = VGIC_ADDR_UNDEF; + + INIT_LIST_HEAD(&its->device_list); + INIT_LIST_HEAD(&its->collection_list); + + dev->kvm->arch.vgic.msis_require_devid = true; + dev->kvm->arch.vgic.has_its = true; + its->enabled = false; + its->dev = dev; + + its->baser_device_table = INITIAL_BASER_VALUE | + ((u64)GITS_BASER_TYPE_DEVICE << GITS_BASER_TYPE_SHIFT); + its->baser_coll_table = INITIAL_BASER_VALUE | + ((u64)GITS_BASER_TYPE_COLLECTION << GITS_BASER_TYPE_SHIFT); + dev->kvm->arch.vgic.propbaser = INITIAL_PROPBASER_VALUE; + + dev->private = its; + + return vgic_its_set_abi(its, NR_ITS_ABIS - 1); +} + +static void vgic_its_destroy(struct kvm_device *kvm_dev) +{ + struct kvm *kvm = kvm_dev->kvm; + struct vgic_its *its = kvm_dev->private; + + mutex_lock(&its->its_lock); + + vgic_its_free_device_list(kvm, its); + vgic_its_free_collection_list(kvm, its); + + mutex_unlock(&its->its_lock); + kfree(its); + kfree(kvm_dev);/* alloc by kvm_ioctl_create_device, free by .destroy */ +} + +static int vgic_its_has_attr_regs(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + const struct vgic_register_region *region; + gpa_t offset = attr->attr; + int align; + + align = (offset < GITS_TYPER) || (offset >= GITS_PIDR4) ? 0x3 : 0x7; + + if (offset & align) + return -EINVAL; + + region = vgic_find_mmio_region(its_registers, + ARRAY_SIZE(its_registers), + offset); + if (!region) + return -ENXIO; + + return 0; +} + +static int vgic_its_attr_regs_access(struct kvm_device *dev, + struct kvm_device_attr *attr, + u64 *reg, bool is_write) +{ + const struct vgic_register_region *region; + struct vgic_its *its; + gpa_t addr, offset; + unsigned int len; + int align, ret = 0; + + its = dev->private; + offset = attr->attr; + + /* + * Although the spec supports upper/lower 32-bit accesses to + * 64-bit ITS registers, the userspace ABI requires 64-bit + * accesses to all 64-bit wide registers. We therefore only + * support 32-bit accesses to GITS_CTLR, GITS_IIDR and GITS ID + * registers + */ + if ((offset < GITS_TYPER) || (offset >= GITS_PIDR4)) + align = 0x3; + else + align = 0x7; + + if (offset & align) + return -EINVAL; + + mutex_lock(&dev->kvm->lock); + + if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { + ret = -ENXIO; + goto out; + } + + region = vgic_find_mmio_region(its_registers, + ARRAY_SIZE(its_registers), + offset); + if (!region) { + ret = -ENXIO; + goto out; + } + + if (!lock_all_vcpus(dev->kvm)) { + ret = -EBUSY; + goto out; + } + + addr = its->vgic_its_base + offset; + + len = region->access_flags & VGIC_ACCESS_64bit ? 8 : 4; + + if (is_write) { + if (region->uaccess_its_write) + ret = region->uaccess_its_write(dev->kvm, its, addr, + len, *reg); + else + region->its_write(dev->kvm, its, addr, len, *reg); + } else { + *reg = region->its_read(dev->kvm, its, addr, len); + } + unlock_all_vcpus(dev->kvm); +out: + mutex_unlock(&dev->kvm->lock); + return ret; +} + +static u32 compute_next_devid_offset(struct list_head *h, + struct its_device *dev) +{ + struct its_device *next; + u32 next_offset; + + if (list_is_last(&dev->dev_list, h)) + return 0; + next = list_next_entry(dev, dev_list); + next_offset = next->device_id - dev->device_id; + + return min_t(u32, next_offset, VITS_DTE_MAX_DEVID_OFFSET); +} + +static u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite) +{ + struct its_ite *next; + u32 next_offset; + + if (list_is_last(&ite->ite_list, h)) + return 0; + next = list_next_entry(ite, ite_list); + next_offset = next->event_id - ite->event_id; + + return min_t(u32, next_offset, VITS_ITE_MAX_EVENTID_OFFSET); +} + +/** + * entry_fn_t - Callback called on a table entry restore path + * @its: its handle + * @id: id of the entry + * @entry: pointer to the entry + * @opaque: pointer to an opaque data + * + * Return: < 0 on error, 0 if last element was identified, id offset to next + * element otherwise + */ +typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry, + void *opaque); + +/** + * scan_its_table - Scan a contiguous table in guest RAM and applies a function + * to each entry + * + * @its: its handle + * @base: base gpa of the table + * @size: size of the table in bytes + * @esz: entry size in bytes + * @start_id: the ID of the first entry in the table + * (non zero for 2d level tables) + * @fn: function to apply on each entry + * + * Return: < 0 on error, 0 if last element was identified, 1 otherwise + * (the last element may not be found on second level tables) + */ +static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, + int start_id, entry_fn_t fn, void *opaque) +{ + struct kvm *kvm = its->dev->kvm; + unsigned long len = size; + int id = start_id; + gpa_t gpa = base; + char entry[ESZ_MAX]; + int ret; + + memset(entry, 0, esz); + + while (len > 0) { + int next_offset; + size_t byte_offset; + + ret = kvm_read_guest_lock(kvm, gpa, entry, esz); + if (ret) + return ret; + + next_offset = fn(its, id, entry, opaque); + if (next_offset <= 0) + return next_offset; + + byte_offset = next_offset * esz; + id += next_offset; + gpa += byte_offset; + len -= byte_offset; + } + return 1; +} + +/** + * vgic_its_save_ite - Save an interrupt translation entry at @gpa + */ +static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, + struct its_ite *ite, gpa_t gpa, int ite_esz) +{ + struct kvm *kvm = its->dev->kvm; + u32 next_offset; + u64 val; + + next_offset = compute_next_eventid_offset(&dev->itt_head, ite); + val = ((u64)next_offset << KVM_ITS_ITE_NEXT_SHIFT) | + ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) | + ite->collection->collection_id; + val = cpu_to_le64(val); + return kvm_write_guest_lock(kvm, gpa, &val, ite_esz); +} + +/** + * vgic_its_restore_ite - restore an interrupt translation entry + * @event_id: id used for indexing + * @ptr: pointer to the ITE entry + * @opaque: pointer to the its_device + */ +static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id, + void *ptr, void *opaque) +{ + struct its_device *dev = (struct its_device *)opaque; + struct its_collection *collection; + struct kvm *kvm = its->dev->kvm; + struct kvm_vcpu *vcpu = NULL; + u64 val; + u64 *p = (u64 *)ptr; + struct vgic_irq *irq; + u32 coll_id, lpi_id; + struct its_ite *ite; + u32 offset; + + val = *p; + + val = le64_to_cpu(val); + + coll_id = val & KVM_ITS_ITE_ICID_MASK; + lpi_id = (val & KVM_ITS_ITE_PINTID_MASK) >> KVM_ITS_ITE_PINTID_SHIFT; + + if (!lpi_id) + return 1; /* invalid entry, no choice but to scan next entry */ + + if (lpi_id < VGIC_MIN_LPI) + return -EINVAL; + + offset = val >> KVM_ITS_ITE_NEXT_SHIFT; + if (event_id + offset >= BIT_ULL(dev->num_eventid_bits)) + return -EINVAL; + + collection = find_collection(its, coll_id); + if (!collection) + return -EINVAL; + + ite = vgic_its_alloc_ite(dev, collection, event_id); + if (IS_ERR(ite)) + return PTR_ERR(ite); + + if (its_is_collection_mapped(collection)) + vcpu = kvm_get_vcpu(kvm, collection->target_addr); + + irq = vgic_add_lpi(kvm, lpi_id, vcpu); + if (IS_ERR(irq)) + return PTR_ERR(irq); + ite->irq = irq; + + return offset; +} + +static int vgic_its_ite_cmp(void *priv, struct list_head *a, + struct list_head *b) +{ + struct its_ite *itea = container_of(a, struct its_ite, ite_list); + struct its_ite *iteb = container_of(b, struct its_ite, ite_list); + + if (itea->event_id < iteb->event_id) + return -1; + else + return 1; +} + +static int vgic_its_save_itt(struct vgic_its *its, struct its_device *device) +{ + const struct vgic_its_abi *abi = vgic_its_get_abi(its); + gpa_t base = device->itt_addr; + struct its_ite *ite; + int ret; + int ite_esz = abi->ite_esz; + + list_sort(NULL, &device->itt_head, vgic_its_ite_cmp); + + list_for_each_entry(ite, &device->itt_head, ite_list) { + gpa_t gpa = base + ite->event_id * ite_esz; + + /* + * If an LPI carries the HW bit, this means that this + * interrupt is controlled by GICv4, and we do not + * have direct access to that state. Let's simply fail + * the save operation... + */ + if (ite->irq->hw) + return -EACCES; + + ret = vgic_its_save_ite(its, device, ite, gpa, ite_esz); + if (ret) + return ret; + } + return 0; +} + +/** + * vgic_its_restore_itt - restore the ITT of a device + * + * @its: its handle + * @dev: device handle + * + * Return 0 on success, < 0 on error + */ +static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev) +{ + const struct vgic_its_abi *abi = vgic_its_get_abi(its); + gpa_t base = dev->itt_addr; + int ret; + int ite_esz = abi->ite_esz; + size_t max_size = BIT_ULL(dev->num_eventid_bits) * ite_esz; + + ret = scan_its_table(its, base, max_size, ite_esz, 0, + vgic_its_restore_ite, dev); + + /* scan_its_table returns +1 if all ITEs are invalid */ + if (ret > 0) + ret = 0; + + return ret; +} + +/** + * vgic_its_save_dte - Save a device table entry at a given GPA + * + * @its: ITS handle + * @dev: ITS device + * @ptr: GPA + */ +static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, + gpa_t ptr, int dte_esz) +{ + struct kvm *kvm = its->dev->kvm; + u64 val, itt_addr_field; + u32 next_offset; + + itt_addr_field = dev->itt_addr >> 8; + next_offset = compute_next_devid_offset(&its->device_list, dev); + val = (1ULL << KVM_ITS_DTE_VALID_SHIFT | + ((u64)next_offset << KVM_ITS_DTE_NEXT_SHIFT) | + (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) | + (dev->num_eventid_bits - 1)); + val = cpu_to_le64(val); + return kvm_write_guest_lock(kvm, ptr, &val, dte_esz); +} + +/** + * vgic_its_restore_dte - restore a device table entry + * + * @its: its handle + * @id: device id the DTE corresponds to + * @ptr: kernel VA where the 8 byte DTE is located + * @opaque: unused + * + * Return: < 0 on error, 0 if the dte is the last one, id offset to the + * next dte otherwise + */ +static int vgic_its_restore_dte(struct vgic_its *its, u32 id, + void *ptr, void *opaque) +{ + struct its_device *dev; + gpa_t itt_addr; + u8 num_eventid_bits; + u64 entry = *(u64 *)ptr; + bool valid; + u32 offset; + int ret; + + entry = le64_to_cpu(entry); + + valid = entry >> KVM_ITS_DTE_VALID_SHIFT; + num_eventid_bits = (entry & KVM_ITS_DTE_SIZE_MASK) + 1; + itt_addr = ((entry & KVM_ITS_DTE_ITTADDR_MASK) + >> KVM_ITS_DTE_ITTADDR_SHIFT) << 8; + + if (!valid) + return 1; + + /* dte entry is valid */ + offset = (entry & KVM_ITS_DTE_NEXT_MASK) >> KVM_ITS_DTE_NEXT_SHIFT; + + dev = vgic_its_alloc_device(its, id, itt_addr, num_eventid_bits); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + ret = vgic_its_restore_itt(its, dev); + if (ret) { + vgic_its_free_device(its->dev->kvm, dev); + return ret; + } + + return offset; +} + +static int vgic_its_device_cmp(void *priv, struct list_head *a, + struct list_head *b) +{ + struct its_device *deva = container_of(a, struct its_device, dev_list); + struct its_device *devb = container_of(b, struct its_device, dev_list); + + if (deva->device_id < devb->device_id) + return -1; + else + return 1; +} + +/** + * vgic_its_save_device_tables - Save the device table and all ITT + * into guest RAM + * + * L1/L2 handling is hidden by vgic_its_check_id() helper which directly + * returns the GPA of the device entry + */ +static int vgic_its_save_device_tables(struct vgic_its *its) +{ + const struct vgic_its_abi *abi = vgic_its_get_abi(its); + u64 baser = its->baser_device_table; + struct its_device *dev; + int dte_esz = abi->dte_esz; + + if (!(baser & GITS_BASER_VALID)) + return 0; + + list_sort(NULL, &its->device_list, vgic_its_device_cmp); + + list_for_each_entry(dev, &its->device_list, dev_list) { + int ret; + gpa_t eaddr; + + if (!vgic_its_check_id(its, baser, + dev->device_id, &eaddr)) + return -EINVAL; + + ret = vgic_its_save_itt(its, dev); + if (ret) + return ret; + + ret = vgic_its_save_dte(its, dev, eaddr, dte_esz); + if (ret) + return ret; + } + return 0; +} + +/** + * handle_l1_dte - callback used for L1 device table entries (2 stage case) + * + * @its: its handle + * @id: index of the entry in the L1 table + * @addr: kernel VA + * @opaque: unused + * + * L1 table entries are scanned by steps of 1 entry + * Return < 0 if error, 0 if last dte was found when scanning the L2 + * table, +1 otherwise (meaning next L1 entry must be scanned) + */ +static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr, + void *opaque) +{ + const struct vgic_its_abi *abi = vgic_its_get_abi(its); + int l2_start_id = id * (SZ_64K / abi->dte_esz); + u64 entry = *(u64 *)addr; + int dte_esz = abi->dte_esz; + gpa_t gpa; + int ret; + + entry = le64_to_cpu(entry); + + if (!(entry & KVM_ITS_L1E_VALID_MASK)) + return 1; + + gpa = entry & KVM_ITS_L1E_ADDR_MASK; + + ret = scan_its_table(its, gpa, SZ_64K, dte_esz, + l2_start_id, vgic_its_restore_dte, NULL); + + return ret; +} + +/** + * vgic_its_restore_device_tables - Restore the device table and all ITT + * from guest RAM to internal data structs + */ +static int vgic_its_restore_device_tables(struct vgic_its *its) +{ + const struct vgic_its_abi *abi = vgic_its_get_abi(its); + u64 baser = its->baser_device_table; + int l1_esz, ret; + int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; + gpa_t l1_gpa; + + if (!(baser & GITS_BASER_VALID)) + return 0; + + l1_gpa = GITS_BASER_ADDR_48_to_52(baser); + + if (baser & GITS_BASER_INDIRECT) { + l1_esz = GITS_LVL1_ENTRY_SIZE; + ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0, + handle_l1_dte, NULL); + } else { + l1_esz = abi->dte_esz; + ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0, + vgic_its_restore_dte, NULL); + } + + /* scan_its_table returns +1 if all entries are invalid */ + if (ret > 0) + ret = 0; + + return ret; +} + +static int vgic_its_save_cte(struct vgic_its *its, + struct its_collection *collection, + gpa_t gpa, int esz) +{ + u64 val; + + val = (1ULL << KVM_ITS_CTE_VALID_SHIFT | + ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) | + collection->collection_id); + val = cpu_to_le64(val); + return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz); +} + +static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) +{ + struct its_collection *collection; + struct kvm *kvm = its->dev->kvm; + u32 target_addr, coll_id; + u64 val; + int ret; + + BUG_ON(esz > sizeof(val)); + ret = kvm_read_guest_lock(kvm, gpa, &val, esz); + if (ret) + return ret; + val = le64_to_cpu(val); + if (!(val & KVM_ITS_CTE_VALID_MASK)) + return 0; + + target_addr = (u32)(val >> KVM_ITS_CTE_RDBASE_SHIFT); + coll_id = val & KVM_ITS_CTE_ICID_MASK; + + if (target_addr != COLLECTION_NOT_MAPPED && + target_addr >= atomic_read(&kvm->online_vcpus)) + return -EINVAL; + + collection = find_collection(its, coll_id); + if (collection) + return -EEXIST; + ret = vgic_its_alloc_collection(its, &collection, coll_id); + if (ret) + return ret; + collection->target_addr = target_addr; + return 1; +} + +/** + * vgic_its_save_collection_table - Save the collection table into + * guest RAM + */ +static int vgic_its_save_collection_table(struct vgic_its *its) +{ + const struct vgic_its_abi *abi = vgic_its_get_abi(its); + u64 baser = its->baser_coll_table; + gpa_t gpa = GITS_BASER_ADDR_48_to_52(baser); + struct its_collection *collection; + u64 val; + size_t max_size, filled = 0; + int ret, cte_esz = abi->cte_esz; + + if (!(baser & GITS_BASER_VALID)) + return 0; + + max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; + + list_for_each_entry(collection, &its->collection_list, coll_list) { + ret = vgic_its_save_cte(its, collection, gpa, cte_esz); + if (ret) + return ret; + gpa += cte_esz; + filled += cte_esz; + } + + if (filled == max_size) + return 0; + + /* + * table is not fully filled, add a last dummy element + * with valid bit unset + */ + val = 0; + BUG_ON(cte_esz > sizeof(val)); + ret = kvm_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); + return ret; +} + +/** + * vgic_its_restore_collection_table - reads the collection table + * in guest memory and restores the ITS internal state. Requires the + * BASER registers to be restored before. + */ +static int vgic_its_restore_collection_table(struct vgic_its *its) +{ + const struct vgic_its_abi *abi = vgic_its_get_abi(its); + u64 baser = its->baser_coll_table; + int cte_esz = abi->cte_esz; + size_t max_size, read = 0; + gpa_t gpa; + int ret; + + if (!(baser & GITS_BASER_VALID)) + return 0; + + gpa = GITS_BASER_ADDR_48_to_52(baser); + + max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; + + while (read < max_size) { + ret = vgic_its_restore_cte(its, gpa, cte_esz); + if (ret <= 0) + break; + gpa += cte_esz; + read += cte_esz; + } + + if (ret > 0) + return 0; + + return ret; +} + +/** + * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM + * according to v0 ABI + */ +static int vgic_its_save_tables_v0(struct vgic_its *its) +{ + int ret; + + ret = vgic_its_save_device_tables(its); + if (ret) + return ret; + + return vgic_its_save_collection_table(its); +} + +/** + * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM + * to internal data structs according to V0 ABI + * + */ +static int vgic_its_restore_tables_v0(struct vgic_its *its) +{ + int ret; + + ret = vgic_its_restore_collection_table(its); + if (ret) + return ret; + + return vgic_its_restore_device_tables(its); +} + +static int vgic_its_commit_v0(struct vgic_its *its) +{ + const struct vgic_its_abi *abi; + + abi = vgic_its_get_abi(its); + its->baser_coll_table &= ~GITS_BASER_ENTRY_SIZE_MASK; + its->baser_device_table &= ~GITS_BASER_ENTRY_SIZE_MASK; + + its->baser_coll_table |= (GIC_ENCODE_SZ(abi->cte_esz, 5) + << GITS_BASER_ENTRY_SIZE_SHIFT); + + its->baser_device_table |= (GIC_ENCODE_SZ(abi->dte_esz, 5) + << GITS_BASER_ENTRY_SIZE_SHIFT); + return 0; +} + +static void vgic_its_reset(struct kvm *kvm, struct vgic_its *its) +{ + /* We need to keep the ABI specific field values */ + its->baser_coll_table &= ~GITS_BASER_VALID; + its->baser_device_table &= ~GITS_BASER_VALID; + its->cbaser = 0; + its->creadr = 0; + its->cwriter = 0; + its->enabled = 0; + vgic_its_free_device_list(kvm, its); + vgic_its_free_collection_list(kvm, its); +} + +static int vgic_its_has_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: + switch (attr->attr) { + case KVM_VGIC_ITS_ADDR_TYPE: + return 0; + } + break; + case KVM_DEV_ARM_VGIC_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_ARM_VGIC_CTRL_INIT: + return 0; + case KVM_DEV_ARM_ITS_CTRL_RESET: + return 0; + case KVM_DEV_ARM_ITS_SAVE_TABLES: + return 0; + case KVM_DEV_ARM_ITS_RESTORE_TABLES: + return 0; + } + break; + case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: + return vgic_its_has_attr_regs(dev, attr); + } + return -ENXIO; +} + +static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) +{ + const struct vgic_its_abi *abi = vgic_its_get_abi(its); + int ret = 0; + + if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */ + return 0; + + mutex_lock(&kvm->lock); + mutex_lock(&its->its_lock); + + if (!lock_all_vcpus(kvm)) { + mutex_unlock(&its->its_lock); + mutex_unlock(&kvm->lock); + return -EBUSY; + } + + switch (attr) { + case KVM_DEV_ARM_ITS_CTRL_RESET: + vgic_its_reset(kvm, its); + break; + case KVM_DEV_ARM_ITS_SAVE_TABLES: + ret = abi->save_tables(its); + break; + case KVM_DEV_ARM_ITS_RESTORE_TABLES: + ret = abi->restore_tables(its); + break; + } + + unlock_all_vcpus(kvm); + mutex_unlock(&its->its_lock); + mutex_unlock(&kvm->lock); + return ret; +} + +static int vgic_its_set_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + struct vgic_its *its = dev->private; + int ret; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: { + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + unsigned long type = (unsigned long)attr->attr; + u64 addr; + + if (type != KVM_VGIC_ITS_ADDR_TYPE) + return -ENODEV; + + if (copy_from_user(&addr, uaddr, sizeof(addr))) + return -EFAULT; + + ret = vgic_check_ioaddr(dev->kvm, &its->vgic_its_base, + addr, SZ_64K); + if (ret) + return ret; + + return vgic_register_its_iodev(dev->kvm, its, addr); + } + case KVM_DEV_ARM_VGIC_GRP_CTRL: + return vgic_its_ctrl(dev->kvm, its, attr->attr); + case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: { + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + u64 reg; + + if (get_user(reg, uaddr)) + return -EFAULT; + + return vgic_its_attr_regs_access(dev, attr, ®, true); + } + } + return -ENXIO; +} + +static int vgic_its_get_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: { + struct vgic_its *its = dev->private; + u64 addr = its->vgic_its_base; + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + unsigned long type = (unsigned long)attr->attr; + + if (type != KVM_VGIC_ITS_ADDR_TYPE) + return -ENODEV; + + if (copy_to_user(uaddr, &addr, sizeof(addr))) + return -EFAULT; + break; + } + case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: { + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + u64 reg; + int ret; + + ret = vgic_its_attr_regs_access(dev, attr, ®, false); + if (ret) + return ret; + return put_user(reg, uaddr); + } + default: + return -ENXIO; + } + + return 0; +} + +static struct kvm_device_ops kvm_arm_vgic_its_ops = { + .name = "kvm-arm-vgic-its", + .create = vgic_its_create, + .destroy = vgic_its_destroy, + .set_attr = vgic_its_set_attr, + .get_attr = vgic_its_get_attr, + .has_attr = vgic_its_has_attr, +}; + +int kvm_vgic_register_its_device(void) +{ + return kvm_register_device_ops(&kvm_arm_vgic_its_ops, + KVM_DEV_TYPE_ARM_VGIC_ITS); +} diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c new file mode 100644 index 000000000000..44419679f91a --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -0,0 +1,741 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VGIC: KVM DEVICE API + * + * Copyright (C) 2015 ARM Ltd. + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ +#include <linux/kvm_host.h> +#include <kvm/arm_vgic.h> +#include <linux/uaccess.h> +#include <asm/kvm_mmu.h> +#include <asm/cputype.h> +#include "vgic.h" + +/* common helpers */ + +int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr, + phys_addr_t addr, phys_addr_t alignment) +{ + if (addr & ~kvm_phys_mask(kvm)) + return -E2BIG; + + if (!IS_ALIGNED(addr, alignment)) + return -EINVAL; + + if (!IS_VGIC_ADDR_UNDEF(*ioaddr)) + return -EEXIST; + + return 0; +} + +static int vgic_check_type(struct kvm *kvm, int type_needed) +{ + if (kvm->arch.vgic.vgic_model != type_needed) + return -ENODEV; + else + return 0; +} + +/** + * kvm_vgic_addr - set or get vgic VM base addresses + * @kvm: pointer to the vm struct + * @type: the VGIC addr type, one of KVM_VGIC_V[23]_ADDR_TYPE_XXX + * @addr: pointer to address value + * @write: if true set the address in the VM address space, if false read the + * address + * + * Set or get the vgic base addresses for the distributor and the virtual CPU + * interface in the VM physical address space. These addresses are properties + * of the emulated core/SoC and therefore user space initially knows this + * information. + * Check them for sanity (alignment, double assignment). We can't check for + * overlapping regions in case of a virtual GICv3 here, since we don't know + * the number of VCPUs yet, so we defer this check to map_resources(). + */ +int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) +{ + int r = 0; + struct vgic_dist *vgic = &kvm->arch.vgic; + phys_addr_t *addr_ptr, alignment; + u64 undef_value = VGIC_ADDR_UNDEF; + + mutex_lock(&kvm->lock); + switch (type) { + case KVM_VGIC_V2_ADDR_TYPE_DIST: + r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + addr_ptr = &vgic->vgic_dist_base; + alignment = SZ_4K; + break; + case KVM_VGIC_V2_ADDR_TYPE_CPU: + r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + addr_ptr = &vgic->vgic_cpu_base; + alignment = SZ_4K; + break; + case KVM_VGIC_V3_ADDR_TYPE_DIST: + r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); + addr_ptr = &vgic->vgic_dist_base; + alignment = SZ_64K; + break; + case KVM_VGIC_V3_ADDR_TYPE_REDIST: { + struct vgic_redist_region *rdreg; + + r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); + if (r) + break; + if (write) { + r = vgic_v3_set_redist_base(kvm, 0, *addr, 0); + goto out; + } + rdreg = list_first_entry(&vgic->rd_regions, + struct vgic_redist_region, list); + if (!rdreg) + addr_ptr = &undef_value; + else + addr_ptr = &rdreg->base; + break; + } + case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: + { + struct vgic_redist_region *rdreg; + u8 index; + + r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); + if (r) + break; + + index = *addr & KVM_VGIC_V3_RDIST_INDEX_MASK; + + if (write) { + gpa_t base = *addr & KVM_VGIC_V3_RDIST_BASE_MASK; + u32 count = (*addr & KVM_VGIC_V3_RDIST_COUNT_MASK) + >> KVM_VGIC_V3_RDIST_COUNT_SHIFT; + u8 flags = (*addr & KVM_VGIC_V3_RDIST_FLAGS_MASK) + >> KVM_VGIC_V3_RDIST_FLAGS_SHIFT; + + if (!count || flags) + r = -EINVAL; + else + r = vgic_v3_set_redist_base(kvm, index, + base, count); + goto out; + } + + rdreg = vgic_v3_rdist_region_from_index(kvm, index); + if (!rdreg) { + r = -ENOENT; + goto out; + } + + *addr = index; + *addr |= rdreg->base; + *addr |= (u64)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT; + goto out; + } + default: + r = -ENODEV; + } + + if (r) + goto out; + + if (write) { + r = vgic_check_ioaddr(kvm, addr_ptr, *addr, alignment); + if (!r) + *addr_ptr = *addr; + } else { + *addr = *addr_ptr; + } + +out: + mutex_unlock(&kvm->lock); + return r; +} + +static int vgic_set_common_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + int r; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: { + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + u64 addr; + unsigned long type = (unsigned long)attr->attr; + + if (copy_from_user(&addr, uaddr, sizeof(addr))) + return -EFAULT; + + r = kvm_vgic_addr(dev->kvm, type, &addr, true); + return (r == -ENODEV) ? -ENXIO : r; + } + case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + u32 val; + int ret = 0; + + if (get_user(val, uaddr)) + return -EFAULT; + + /* + * We require: + * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs + * - at most 1024 interrupts + * - a multiple of 32 interrupts + */ + if (val < (VGIC_NR_PRIVATE_IRQS + 32) || + val > VGIC_MAX_RESERVED || + (val & 31)) + return -EINVAL; + + mutex_lock(&dev->kvm->lock); + + if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis) + ret = -EBUSY; + else + dev->kvm->arch.vgic.nr_spis = + val - VGIC_NR_PRIVATE_IRQS; + + mutex_unlock(&dev->kvm->lock); + + return ret; + } + case KVM_DEV_ARM_VGIC_GRP_CTRL: { + switch (attr->attr) { + case KVM_DEV_ARM_VGIC_CTRL_INIT: + mutex_lock(&dev->kvm->lock); + r = vgic_init(dev->kvm); + mutex_unlock(&dev->kvm->lock); + return r; + } + break; + } + } + + return -ENXIO; +} + +static int vgic_get_common_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + int r = -ENXIO; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: { + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + u64 addr; + unsigned long type = (unsigned long)attr->attr; + + r = kvm_vgic_addr(dev->kvm, type, &addr, false); + if (r) + return (r == -ENODEV) ? -ENXIO : r; + + if (copy_to_user(uaddr, &addr, sizeof(addr))) + return -EFAULT; + break; + } + case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + + r = put_user(dev->kvm->arch.vgic.nr_spis + + VGIC_NR_PRIVATE_IRQS, uaddr); + break; + } + } + + return r; +} + +static int vgic_create(struct kvm_device *dev, u32 type) +{ + return kvm_vgic_create(dev->kvm, type); +} + +static void vgic_destroy(struct kvm_device *dev) +{ + kfree(dev); +} + +int kvm_register_vgic_device(unsigned long type) +{ + int ret = -ENODEV; + + switch (type) { + case KVM_DEV_TYPE_ARM_VGIC_V2: + ret = kvm_register_device_ops(&kvm_arm_vgic_v2_ops, + KVM_DEV_TYPE_ARM_VGIC_V2); + break; + case KVM_DEV_TYPE_ARM_VGIC_V3: + ret = kvm_register_device_ops(&kvm_arm_vgic_v3_ops, + KVM_DEV_TYPE_ARM_VGIC_V3); + + if (ret) + break; + ret = kvm_vgic_register_its_device(); + break; + } + + return ret; +} + +int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, + struct vgic_reg_attr *reg_attr) +{ + int cpuid; + + cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >> + KVM_DEV_ARM_VGIC_CPUID_SHIFT; + + if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) + return -EINVAL; + + reg_attr->vcpu = kvm_get_vcpu(dev->kvm, cpuid); + reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; + + return 0; +} + +/* unlocks vcpus from @vcpu_lock_idx and smaller */ +static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx) +{ + struct kvm_vcpu *tmp_vcpu; + + for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { + tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); + mutex_unlock(&tmp_vcpu->mutex); + } +} + +void unlock_all_vcpus(struct kvm *kvm) +{ + unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1); +} + +/* Returns true if all vcpus were locked, false otherwise */ +bool lock_all_vcpus(struct kvm *kvm) +{ + struct kvm_vcpu *tmp_vcpu; + int c; + + /* + * Any time a vcpu is run, vcpu_load is called which tries to grab the + * vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure + * that no other VCPUs are run and fiddle with the vgic state while we + * access it. + */ + kvm_for_each_vcpu(c, tmp_vcpu, kvm) { + if (!mutex_trylock(&tmp_vcpu->mutex)) { + unlock_vcpus(kvm, c - 1); + return false; + } + } + + return true; +} + +/** + * vgic_v2_attr_regs_access - allows user space to access VGIC v2 state + * + * @dev: kvm device handle + * @attr: kvm device attribute + * @reg: address the value is read or written + * @is_write: true if userspace is writing a register + */ +static int vgic_v2_attr_regs_access(struct kvm_device *dev, + struct kvm_device_attr *attr, + u32 *reg, bool is_write) +{ + struct vgic_reg_attr reg_attr; + gpa_t addr; + struct kvm_vcpu *vcpu; + int ret; + + ret = vgic_v2_parse_attr(dev, attr, ®_attr); + if (ret) + return ret; + + vcpu = reg_attr.vcpu; + addr = reg_attr.addr; + + mutex_lock(&dev->kvm->lock); + + ret = vgic_init(dev->kvm); + if (ret) + goto out; + + if (!lock_all_vcpus(dev->kvm)) { + ret = -EBUSY; + goto out; + } + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: + ret = vgic_v2_cpuif_uaccess(vcpu, is_write, addr, reg); + break; + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + ret = vgic_v2_dist_uaccess(vcpu, is_write, addr, reg); + break; + default: + ret = -EINVAL; + break; + } + + unlock_all_vcpus(dev->kvm); +out: + mutex_unlock(&dev->kvm->lock); + return ret; +} + +static int vgic_v2_set_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + int ret; + + ret = vgic_set_common_attr(dev, attr); + if (ret != -ENXIO) + return ret; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + u32 reg; + + if (get_user(reg, uaddr)) + return -EFAULT; + + return vgic_v2_attr_regs_access(dev, attr, ®, true); + } + } + + return -ENXIO; +} + +static int vgic_v2_get_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + int ret; + + ret = vgic_get_common_attr(dev, attr); + if (ret != -ENXIO) + return ret; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + u32 reg = 0; + + ret = vgic_v2_attr_regs_access(dev, attr, ®, false); + if (ret) + return ret; + return put_user(reg, uaddr); + } + } + + return -ENXIO; +} + +static int vgic_v2_has_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: + switch (attr->attr) { + case KVM_VGIC_V2_ADDR_TYPE_DIST: + case KVM_VGIC_V2_ADDR_TYPE_CPU: + return 0; + } + break; + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: + return vgic_v2_has_attr_regs(dev, attr); + case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: + return 0; + case KVM_DEV_ARM_VGIC_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_ARM_VGIC_CTRL_INIT: + return 0; + } + } + return -ENXIO; +} + +struct kvm_device_ops kvm_arm_vgic_v2_ops = { + .name = "kvm-arm-vgic-v2", + .create = vgic_create, + .destroy = vgic_destroy, + .set_attr = vgic_v2_set_attr, + .get_attr = vgic_v2_get_attr, + .has_attr = vgic_v2_has_attr, +}; + +int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, + struct vgic_reg_attr *reg_attr) +{ + unsigned long vgic_mpidr, mpidr_reg; + + /* + * For KVM_DEV_ARM_VGIC_GRP_DIST_REGS group, + * attr might not hold MPIDR. Hence assume vcpu0. + */ + if (attr->group != KVM_DEV_ARM_VGIC_GRP_DIST_REGS) { + vgic_mpidr = (attr->attr & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) >> + KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT; + + mpidr_reg = VGIC_TO_MPIDR(vgic_mpidr); + reg_attr->vcpu = kvm_mpidr_to_vcpu(dev->kvm, mpidr_reg); + } else { + reg_attr->vcpu = kvm_get_vcpu(dev->kvm, 0); + } + + if (!reg_attr->vcpu) + return -EINVAL; + + reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; + + return 0; +} + +/* + * vgic_v3_attr_regs_access - allows user space to access VGIC v3 state + * + * @dev: kvm device handle + * @attr: kvm device attribute + * @reg: address the value is read or written + * @is_write: true if userspace is writing a register + */ +static int vgic_v3_attr_regs_access(struct kvm_device *dev, + struct kvm_device_attr *attr, + u64 *reg, bool is_write) +{ + struct vgic_reg_attr reg_attr; + gpa_t addr; + struct kvm_vcpu *vcpu; + int ret; + u32 tmp32; + + ret = vgic_v3_parse_attr(dev, attr, ®_attr); + if (ret) + return ret; + + vcpu = reg_attr.vcpu; + addr = reg_attr.addr; + + mutex_lock(&dev->kvm->lock); + + if (unlikely(!vgic_initialized(dev->kvm))) { + ret = -EBUSY; + goto out; + } + + if (!lock_all_vcpus(dev->kvm)) { + ret = -EBUSY; + goto out; + } + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + if (is_write) + tmp32 = *reg; + + ret = vgic_v3_dist_uaccess(vcpu, is_write, addr, &tmp32); + if (!is_write) + *reg = tmp32; + break; + case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: + if (is_write) + tmp32 = *reg; + + ret = vgic_v3_redist_uaccess(vcpu, is_write, addr, &tmp32); + if (!is_write) + *reg = tmp32; + break; + case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: { + u64 regid; + + regid = (attr->attr & KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK); + ret = vgic_v3_cpu_sysregs_uaccess(vcpu, is_write, + regid, reg); + break; + } + case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { + unsigned int info, intid; + + info = (attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> + KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT; + if (info == VGIC_LEVEL_INFO_LINE_LEVEL) { + intid = attr->attr & + KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK; + ret = vgic_v3_line_level_info_uaccess(vcpu, is_write, + intid, reg); + } else { + ret = -EINVAL; + } + break; + } + default: + ret = -EINVAL; + break; + } + + unlock_all_vcpus(dev->kvm); +out: + mutex_unlock(&dev->kvm->lock); + return ret; +} + +static int vgic_v3_set_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + int ret; + + ret = vgic_set_common_attr(dev, attr); + if (ret != -ENXIO) + return ret; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + u32 tmp32; + u64 reg; + + if (get_user(tmp32, uaddr)) + return -EFAULT; + + reg = tmp32; + return vgic_v3_attr_regs_access(dev, attr, ®, true); + } + case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: { + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + u64 reg; + + if (get_user(reg, uaddr)) + return -EFAULT; + + return vgic_v3_attr_regs_access(dev, attr, ®, true); + } + case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + u64 reg; + u32 tmp32; + + if (get_user(tmp32, uaddr)) + return -EFAULT; + + reg = tmp32; + return vgic_v3_attr_regs_access(dev, attr, ®, true); + } + case KVM_DEV_ARM_VGIC_GRP_CTRL: { + int ret; + + switch (attr->attr) { + case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: + mutex_lock(&dev->kvm->lock); + + if (!lock_all_vcpus(dev->kvm)) { + mutex_unlock(&dev->kvm->lock); + return -EBUSY; + } + ret = vgic_v3_save_pending_tables(dev->kvm); + unlock_all_vcpus(dev->kvm); + mutex_unlock(&dev->kvm->lock); + return ret; + } + break; + } + } + return -ENXIO; +} + +static int vgic_v3_get_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + int ret; + + ret = vgic_get_common_attr(dev, attr); + if (ret != -ENXIO) + return ret; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + u64 reg; + u32 tmp32; + + ret = vgic_v3_attr_regs_access(dev, attr, ®, false); + if (ret) + return ret; + tmp32 = reg; + return put_user(tmp32, uaddr); + } + case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: { + u64 __user *uaddr = (u64 __user *)(long)attr->addr; + u64 reg; + + ret = vgic_v3_attr_regs_access(dev, attr, ®, false); + if (ret) + return ret; + return put_user(reg, uaddr); + } + case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { + u32 __user *uaddr = (u32 __user *)(long)attr->addr; + u64 reg; + u32 tmp32; + + ret = vgic_v3_attr_regs_access(dev, attr, ®, false); + if (ret) + return ret; + tmp32 = reg; + return put_user(tmp32, uaddr); + } + } + return -ENXIO; +} + +static int vgic_v3_has_attr(struct kvm_device *dev, + struct kvm_device_attr *attr) +{ + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_ADDR: + switch (attr->attr) { + case KVM_VGIC_V3_ADDR_TYPE_DIST: + case KVM_VGIC_V3_ADDR_TYPE_REDIST: + case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: + return 0; + } + break; + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: + case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: + return vgic_v3_has_attr_regs(dev, attr); + case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: + return 0; + case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { + if (((attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> + KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) == + VGIC_LEVEL_INFO_LINE_LEVEL) + return 0; + break; + } + case KVM_DEV_ARM_VGIC_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_ARM_VGIC_CTRL_INIT: + return 0; + case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: + return 0; + } + } + return -ENXIO; +} + +struct kvm_device_ops kvm_arm_vgic_v3_ops = { + .name = "kvm-arm-vgic-v3", + .create = vgic_create, + .destroy = vgic_destroy, + .set_attr = vgic_v3_set_attr, + .get_attr = vgic_v3_get_attr, + .has_attr = vgic_v3_has_attr, +}; diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c new file mode 100644 index 000000000000..a016f07adc28 --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c @@ -0,0 +1,550 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VGICv2 MMIO handling functions + */ + +#include <linux/irqchip/arm-gic.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/nospec.h> + +#include <kvm/iodev.h> +#include <kvm/arm_vgic.h> + +#include "vgic.h" +#include "vgic-mmio.h" + +/* + * The Revision field in the IIDR have the following meanings: + * + * Revision 1: Report GICv2 interrupts as group 0 instead of group 1 + * Revision 2: Interrupt groups are guest-configurable and signaled using + * their configured groups. + */ + +static unsigned long vgic_mmio_read_v2_misc(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + struct vgic_dist *vgic = &vcpu->kvm->arch.vgic; + u32 value; + + switch (addr & 0x0c) { + case GIC_DIST_CTRL: + value = vgic->enabled ? GICD_ENABLE : 0; + break; + case GIC_DIST_CTR: + value = vgic->nr_spis + VGIC_NR_PRIVATE_IRQS; + value = (value >> 5) - 1; + value |= (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5; + break; + case GIC_DIST_IIDR: + value = (PRODUCT_ID_KVM << GICD_IIDR_PRODUCT_ID_SHIFT) | + (vgic->implementation_rev << GICD_IIDR_REVISION_SHIFT) | + (IMPLEMENTER_ARM << GICD_IIDR_IMPLEMENTER_SHIFT); + break; + default: + return 0; + } + + return value; +} + +static void vgic_mmio_write_v2_misc(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + bool was_enabled = dist->enabled; + + switch (addr & 0x0c) { + case GIC_DIST_CTRL: + dist->enabled = val & GICD_ENABLE; + if (!was_enabled && dist->enabled) + vgic_kick_vcpus(vcpu->kvm); + break; + case GIC_DIST_CTR: + case GIC_DIST_IIDR: + /* Nothing to do */ + return; + } +} + +static int vgic_mmio_uaccess_write_v2_misc(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + switch (addr & 0x0c) { + case GIC_DIST_IIDR: + if (val != vgic_mmio_read_v2_misc(vcpu, addr, len)) + return -EINVAL; + + /* + * If we observe a write to GICD_IIDR we know that userspace + * has been updated and has had a chance to cope with older + * kernels (VGICv2 IIDR.Revision == 0) incorrectly reporting + * interrupts as group 1, and therefore we now allow groups to + * be user writable. Doing this by default would break + * migration from old kernels to new kernels with legacy + * userspace. + */ + vcpu->kvm->arch.vgic.v2_groups_user_writable = true; + return 0; + } + + vgic_mmio_write_v2_misc(vcpu, addr, len, val); + return 0; +} + +static int vgic_mmio_uaccess_write_v2_group(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + if (vcpu->kvm->arch.vgic.v2_groups_user_writable) + vgic_mmio_write_group(vcpu, addr, len, val); + + return 0; +} + +static void vgic_mmio_write_sgir(struct kvm_vcpu *source_vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + int nr_vcpus = atomic_read(&source_vcpu->kvm->online_vcpus); + int intid = val & 0xf; + int targets = (val >> 16) & 0xff; + int mode = (val >> 24) & 0x03; + int c; + struct kvm_vcpu *vcpu; + unsigned long flags; + + switch (mode) { + case 0x0: /* as specified by targets */ + break; + case 0x1: + targets = (1U << nr_vcpus) - 1; /* all, ... */ + targets &= ~(1U << source_vcpu->vcpu_id); /* but self */ + break; + case 0x2: /* this very vCPU only */ + targets = (1U << source_vcpu->vcpu_id); + break; + case 0x3: /* reserved */ + return; + } + + kvm_for_each_vcpu(c, vcpu, source_vcpu->kvm) { + struct vgic_irq *irq; + + if (!(targets & (1U << c))) + continue; + + irq = vgic_get_irq(source_vcpu->kvm, vcpu, intid); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->pending_latch = true; + irq->source |= 1U << source_vcpu->vcpu_id; + + vgic_queue_irq_unlock(source_vcpu->kvm, irq, flags); + vgic_put_irq(source_vcpu->kvm, irq); + } +} + +static unsigned long vgic_mmio_read_target(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 8); + int i; + u64 val = 0; + + for (i = 0; i < len; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + val |= (u64)irq->targets << (i * 8); + + vgic_put_irq(vcpu->kvm, irq); + } + + return val; +} + +static void vgic_mmio_write_target(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 8); + u8 cpu_mask = GENMASK(atomic_read(&vcpu->kvm->online_vcpus) - 1, 0); + int i; + unsigned long flags; + + /* GICD_ITARGETSR[0-7] are read-only */ + if (intid < VGIC_NR_PRIVATE_IRQS) + return; + + for (i = 0; i < len; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid + i); + int target; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + irq->targets = (val >> (i * 8)) & cpu_mask; + target = irq->targets ? __ffs(irq->targets) : 0; + irq->target_vcpu = kvm_get_vcpu(vcpu->kvm, target); + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +static unsigned long vgic_mmio_read_sgipend(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = addr & 0x0f; + int i; + u64 val = 0; + + for (i = 0; i < len; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + val |= (u64)irq->source << (i * 8); + + vgic_put_irq(vcpu->kvm, irq); + } + return val; +} + +static void vgic_mmio_write_sgipendc(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = addr & 0x0f; + int i; + unsigned long flags; + + for (i = 0; i < len; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + irq->source &= ~((val >> (i * 8)) & 0xff); + if (!irq->source) + irq->pending_latch = false; + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +static void vgic_mmio_write_sgipends(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = addr & 0x0f; + int i; + unsigned long flags; + + for (i = 0; i < len; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + irq->source |= (val >> (i * 8)) & 0xff; + + if (irq->source) { + irq->pending_latch = true; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + } else { + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + } + vgic_put_irq(vcpu->kvm, irq); + } +} + +#define GICC_ARCH_VERSION_V2 0x2 + +/* These are for userland accesses only, there is no guest-facing emulation. */ +static unsigned long vgic_mmio_read_vcpuif(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + struct vgic_vmcr vmcr; + u32 val; + + vgic_get_vmcr(vcpu, &vmcr); + + switch (addr & 0xff) { + case GIC_CPU_CTRL: + val = vmcr.grpen0 << GIC_CPU_CTRL_EnableGrp0_SHIFT; + val |= vmcr.grpen1 << GIC_CPU_CTRL_EnableGrp1_SHIFT; + val |= vmcr.ackctl << GIC_CPU_CTRL_AckCtl_SHIFT; + val |= vmcr.fiqen << GIC_CPU_CTRL_FIQEn_SHIFT; + val |= vmcr.cbpr << GIC_CPU_CTRL_CBPR_SHIFT; + val |= vmcr.eoim << GIC_CPU_CTRL_EOImodeNS_SHIFT; + + break; + case GIC_CPU_PRIMASK: + /* + * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the + * the PMR field as GICH_VMCR.VMPriMask rather than + * GICC_PMR.Priority, so we expose the upper five bits of + * priority mask to userspace using the lower bits in the + * unsigned long. + */ + val = (vmcr.pmr & GICV_PMR_PRIORITY_MASK) >> + GICV_PMR_PRIORITY_SHIFT; + break; + case GIC_CPU_BINPOINT: + val = vmcr.bpr; + break; + case GIC_CPU_ALIAS_BINPOINT: + val = vmcr.abpr; + break; + case GIC_CPU_IDENT: + val = ((PRODUCT_ID_KVM << 20) | + (GICC_ARCH_VERSION_V2 << 16) | + IMPLEMENTER_ARM); + break; + default: + return 0; + } + + return val; +} + +static void vgic_mmio_write_vcpuif(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + struct vgic_vmcr vmcr; + + vgic_get_vmcr(vcpu, &vmcr); + + switch (addr & 0xff) { + case GIC_CPU_CTRL: + vmcr.grpen0 = !!(val & GIC_CPU_CTRL_EnableGrp0); + vmcr.grpen1 = !!(val & GIC_CPU_CTRL_EnableGrp1); + vmcr.ackctl = !!(val & GIC_CPU_CTRL_AckCtl); + vmcr.fiqen = !!(val & GIC_CPU_CTRL_FIQEn); + vmcr.cbpr = !!(val & GIC_CPU_CTRL_CBPR); + vmcr.eoim = !!(val & GIC_CPU_CTRL_EOImodeNS); + + break; + case GIC_CPU_PRIMASK: + /* + * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the + * the PMR field as GICH_VMCR.VMPriMask rather than + * GICC_PMR.Priority, so we expose the upper five bits of + * priority mask to userspace using the lower bits in the + * unsigned long. + */ + vmcr.pmr = (val << GICV_PMR_PRIORITY_SHIFT) & + GICV_PMR_PRIORITY_MASK; + break; + case GIC_CPU_BINPOINT: + vmcr.bpr = val; + break; + case GIC_CPU_ALIAS_BINPOINT: + vmcr.abpr = val; + break; + } + + vgic_set_vmcr(vcpu, &vmcr); +} + +static unsigned long vgic_mmio_read_apr(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + int n; /* which APRn is this */ + + n = (addr >> 2) & 0x3; + + if (kvm_vgic_global_state.type == VGIC_V2) { + /* GICv2 hardware systems support max. 32 groups */ + if (n != 0) + return 0; + return vcpu->arch.vgic_cpu.vgic_v2.vgic_apr; + } else { + struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; + + if (n > vgic_v3_max_apr_idx(vcpu)) + return 0; + + n = array_index_nospec(n, 4); + + /* GICv3 only uses ICH_AP1Rn for memory mapped (GICv2) guests */ + return vgicv3->vgic_ap1r[n]; + } +} + +static void vgic_mmio_write_apr(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + int n; /* which APRn is this */ + + n = (addr >> 2) & 0x3; + + if (kvm_vgic_global_state.type == VGIC_V2) { + /* GICv2 hardware systems support max. 32 groups */ + if (n != 0) + return; + vcpu->arch.vgic_cpu.vgic_v2.vgic_apr = val; + } else { + struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; + + if (n > vgic_v3_max_apr_idx(vcpu)) + return; + + n = array_index_nospec(n, 4); + + /* GICv3 only uses ICH_AP1Rn for memory mapped (GICv2) guests */ + vgicv3->vgic_ap1r[n] = val; + } +} + +static const struct vgic_register_region vgic_v2_dist_registers[] = { + REGISTER_DESC_WITH_LENGTH_UACCESS(GIC_DIST_CTRL, + vgic_mmio_read_v2_misc, vgic_mmio_write_v2_misc, + NULL, vgic_mmio_uaccess_write_v2_misc, + 12, VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_IGROUP, + vgic_mmio_read_group, vgic_mmio_write_group, + NULL, vgic_mmio_uaccess_write_v2_group, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_SET, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_CLEAR, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET, + vgic_mmio_read_pending, vgic_mmio_write_spending, + NULL, vgic_uaccess_write_spending, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR, + vgic_mmio_read_pending, vgic_mmio_write_cpending, + NULL, vgic_uaccess_write_cpending, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET, + vgic_mmio_read_active, vgic_mmio_write_sactive, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_CLEAR, + vgic_mmio_read_active, vgic_mmio_write_cactive, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PRI, + vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, + 8, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), + REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_TARGET, + vgic_mmio_read_target, vgic_mmio_write_target, NULL, NULL, 8, + VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), + REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_CONFIG, + vgic_mmio_read_config, vgic_mmio_write_config, NULL, NULL, 2, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GIC_DIST_SOFTINT, + vgic_mmio_read_raz, vgic_mmio_write_sgir, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GIC_DIST_SGI_PENDING_CLEAR, + vgic_mmio_read_sgipend, vgic_mmio_write_sgipendc, 16, + VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), + REGISTER_DESC_WITH_LENGTH(GIC_DIST_SGI_PENDING_SET, + vgic_mmio_read_sgipend, vgic_mmio_write_sgipends, 16, + VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), +}; + +static const struct vgic_register_region vgic_v2_cpu_registers[] = { + REGISTER_DESC_WITH_LENGTH(GIC_CPU_CTRL, + vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GIC_CPU_PRIMASK, + vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GIC_CPU_BINPOINT, + vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GIC_CPU_ALIAS_BINPOINT, + vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GIC_CPU_ACTIVEPRIO, + vgic_mmio_read_apr, vgic_mmio_write_apr, 16, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GIC_CPU_IDENT, + vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4, + VGIC_ACCESS_32bit), +}; + +unsigned int vgic_v2_init_dist_iodev(struct vgic_io_device *dev) +{ + dev->regions = vgic_v2_dist_registers; + dev->nr_regions = ARRAY_SIZE(vgic_v2_dist_registers); + + kvm_iodevice_init(&dev->dev, &kvm_io_gic_ops); + + return SZ_4K; +} + +int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + const struct vgic_register_region *region; + struct vgic_io_device iodev; + struct vgic_reg_attr reg_attr; + struct kvm_vcpu *vcpu; + gpa_t addr; + int ret; + + ret = vgic_v2_parse_attr(dev, attr, ®_attr); + if (ret) + return ret; + + vcpu = reg_attr.vcpu; + addr = reg_attr.addr; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + iodev.regions = vgic_v2_dist_registers; + iodev.nr_regions = ARRAY_SIZE(vgic_v2_dist_registers); + iodev.base_addr = 0; + break; + case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: + iodev.regions = vgic_v2_cpu_registers; + iodev.nr_regions = ARRAY_SIZE(vgic_v2_cpu_registers); + iodev.base_addr = 0; + break; + default: + return -ENXIO; + } + + /* We only support aligned 32-bit accesses. */ + if (addr & 3) + return -ENXIO; + + region = vgic_get_mmio_region(vcpu, &iodev, addr, sizeof(u32)); + if (!region) + return -ENXIO; + + return 0; +} + +int vgic_v2_cpuif_uaccess(struct kvm_vcpu *vcpu, bool is_write, + int offset, u32 *val) +{ + struct vgic_io_device dev = { + .regions = vgic_v2_cpu_registers, + .nr_regions = ARRAY_SIZE(vgic_v2_cpu_registers), + .iodev_type = IODEV_CPUIF, + }; + + return vgic_uaccess(vcpu, &dev, is_write, offset, val); +} + +int vgic_v2_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, + int offset, u32 *val) +{ + struct vgic_io_device dev = { + .regions = vgic_v2_dist_registers, + .nr_regions = ARRAY_SIZE(vgic_v2_dist_registers), + .iodev_type = IODEV_DIST, + }; + + return vgic_uaccess(vcpu, &dev, is_write, offset, val); +} diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c new file mode 100644 index 000000000000..d2339a2b9fb9 --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -0,0 +1,1063 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VGICv3 MMIO handling functions + */ + +#include <linux/bitfield.h> +#include <linux/irqchip/arm-gic-v3.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/interrupt.h> +#include <kvm/iodev.h> +#include <kvm/arm_vgic.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_mmu.h> + +#include "vgic.h" +#include "vgic-mmio.h" + +/* extract @num bytes at @offset bytes offset in data */ +unsigned long extract_bytes(u64 data, unsigned int offset, + unsigned int num) +{ + return (data >> (offset * 8)) & GENMASK_ULL(num * 8 - 1, 0); +} + +/* allows updates of any half of a 64-bit register (or the whole thing) */ +u64 update_64bit_reg(u64 reg, unsigned int offset, unsigned int len, + unsigned long val) +{ + int lower = (offset & 4) * 8; + int upper = lower + 8 * len - 1; + + reg &= ~GENMASK_ULL(upper, lower); + val &= GENMASK_ULL(len * 8 - 1, 0); + + return reg | ((u64)val << lower); +} + +bool vgic_has_its(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + + if (dist->vgic_model != KVM_DEV_TYPE_ARM_VGIC_V3) + return false; + + return dist->has_its; +} + +bool vgic_supports_direct_msis(struct kvm *kvm) +{ + return (kvm_vgic_global_state.has_gicv4_1 || + (kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm))); +} + +/* + * The Revision field in the IIDR have the following meanings: + * + * Revision 2: Interrupt groups are guest-configurable and signaled using + * their configured groups. + */ + +static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + struct vgic_dist *vgic = &vcpu->kvm->arch.vgic; + u32 value = 0; + + switch (addr & 0x0c) { + case GICD_CTLR: + if (vgic->enabled) + value |= GICD_CTLR_ENABLE_SS_G1; + value |= GICD_CTLR_ARE_NS | GICD_CTLR_DS; + if (vgic->nassgireq) + value |= GICD_CTLR_nASSGIreq; + break; + case GICD_TYPER: + value = vgic->nr_spis + VGIC_NR_PRIVATE_IRQS; + value = (value >> 5) - 1; + if (vgic_has_its(vcpu->kvm)) { + value |= (INTERRUPT_ID_BITS_ITS - 1) << 19; + value |= GICD_TYPER_LPIS; + } else { + value |= (INTERRUPT_ID_BITS_SPIS - 1) << 19; + } + break; + case GICD_TYPER2: + if (kvm_vgic_global_state.has_gicv4_1) + value = GICD_TYPER2_nASSGIcap; + break; + case GICD_IIDR: + value = (PRODUCT_ID_KVM << GICD_IIDR_PRODUCT_ID_SHIFT) | + (vgic->implementation_rev << GICD_IIDR_REVISION_SHIFT) | + (IMPLEMENTER_ARM << GICD_IIDR_IMPLEMENTER_SHIFT); + break; + default: + return 0; + } + + return value; +} + +static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + switch (addr & 0x0c) { + case GICD_CTLR: { + bool was_enabled, is_hwsgi; + + mutex_lock(&vcpu->kvm->lock); + + was_enabled = dist->enabled; + is_hwsgi = dist->nassgireq; + + dist->enabled = val & GICD_CTLR_ENABLE_SS_G1; + + /* Not a GICv4.1? No HW SGIs */ + if (!kvm_vgic_global_state.has_gicv4_1) + val &= ~GICD_CTLR_nASSGIreq; + + /* Dist stays enabled? nASSGIreq is RO */ + if (was_enabled && dist->enabled) { + val &= ~GICD_CTLR_nASSGIreq; + val |= FIELD_PREP(GICD_CTLR_nASSGIreq, is_hwsgi); + } + + /* Switching HW SGIs? */ + dist->nassgireq = val & GICD_CTLR_nASSGIreq; + if (is_hwsgi != dist->nassgireq) + vgic_v4_configure_vsgis(vcpu->kvm); + + if (kvm_vgic_global_state.has_gicv4_1 && + was_enabled != dist->enabled) + kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_RELOAD_GICv4); + else if (!was_enabled && dist->enabled) + vgic_kick_vcpus(vcpu->kvm); + + mutex_unlock(&vcpu->kvm->lock); + break; + } + case GICD_TYPER: + case GICD_TYPER2: + case GICD_IIDR: + /* This is at best for documentation purposes... */ + return; + } +} + +static int vgic_mmio_uaccess_write_v3_misc(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + switch (addr & 0x0c) { + case GICD_TYPER2: + case GICD_IIDR: + if (val != vgic_mmio_read_v3_misc(vcpu, addr, len)) + return -EINVAL; + return 0; + case GICD_CTLR: + /* Not a GICv4.1? No HW SGIs */ + if (!kvm_vgic_global_state.has_gicv4_1) + val &= ~GICD_CTLR_nASSGIreq; + + dist->enabled = val & GICD_CTLR_ENABLE_SS_G1; + dist->nassgireq = val & GICD_CTLR_nASSGIreq; + return 0; + } + + vgic_mmio_write_v3_misc(vcpu, addr, len, val); + return 0; +} + +static unsigned long vgic_mmio_read_irouter(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + int intid = VGIC_ADDR_TO_INTID(addr, 64); + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid); + unsigned long ret = 0; + + if (!irq) + return 0; + + /* The upper word is RAZ for us. */ + if (!(addr & 4)) + ret = extract_bytes(READ_ONCE(irq->mpidr), addr & 7, len); + + vgic_put_irq(vcpu->kvm, irq); + return ret; +} + +static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + int intid = VGIC_ADDR_TO_INTID(addr, 64); + struct vgic_irq *irq; + unsigned long flags; + + /* The upper word is WI for us since we don't implement Aff3. */ + if (addr & 4) + return; + + irq = vgic_get_irq(vcpu->kvm, NULL, intid); + + if (!irq) + return; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + /* We only care about and preserve Aff0, Aff1 and Aff2. */ + irq->mpidr = val & GENMASK(23, 0); + irq->target_vcpu = kvm_mpidr_to_vcpu(vcpu->kvm, irq->mpidr); + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); +} + +static unsigned long vgic_mmio_read_v3r_ctlr(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + + return vgic_cpu->lpis_enabled ? GICR_CTLR_ENABLE_LPIS : 0; +} + + +static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + bool was_enabled = vgic_cpu->lpis_enabled; + + if (!vgic_has_its(vcpu->kvm)) + return; + + vgic_cpu->lpis_enabled = val & GICR_CTLR_ENABLE_LPIS; + + if (was_enabled && !vgic_cpu->lpis_enabled) { + vgic_flush_pending_lpis(vcpu); + vgic_its_invalidate_cache(vcpu->kvm); + } + + if (!was_enabled && vgic_cpu->lpis_enabled) + vgic_enable_lpis(vcpu); +} + +static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_redist_region *rdreg = vgic_cpu->rdreg; + int target_vcpu_id = vcpu->vcpu_id; + gpa_t last_rdist_typer = rdreg->base + GICR_TYPER + + (rdreg->free_index - 1) * KVM_VGIC_V3_REDIST_SIZE; + u64 value; + + value = (u64)(mpidr & GENMASK(23, 0)) << 32; + value |= ((target_vcpu_id & 0xffff) << 8); + + if (addr == last_rdist_typer) + value |= GICR_TYPER_LAST; + if (vgic_has_its(vcpu->kvm)) + value |= GICR_TYPER_PLPIS; + + return extract_bytes(value, addr & 7, len); +} + +static unsigned long vgic_mmio_read_v3r_iidr(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0); +} + +static unsigned long vgic_mmio_read_v3_idregs(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + switch (addr & 0xffff) { + case GICD_PIDR2: + /* report a GICv3 compliant implementation */ + return 0x3b; + } + + return 0; +} + +static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + u32 value = 0; + int i; + + /* + * pending state of interrupt is latched in pending_latch variable. + * Userspace will save and restore pending state and line_level + * separately. + * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst + * for handling of ISPENDR and ICPENDR. + */ + for (i = 0; i < len * 8; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + bool state = irq->pending_latch; + + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + int err; + + err = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &state); + WARN_ON(err); + } + + if (state) + value |= (1U << i); + + vgic_put_irq(vcpu->kvm, irq); + } + + return value; +} + +static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for (i = 0; i < len * 8; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (test_bit(i, &val)) { + /* + * pending_latch is set irrespective of irq type + * (level or edge) to avoid dependency that VM should + * restore irq config before pending info. + */ + irq->pending_latch = true; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + } else { + irq->pending_latch = false; + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + } + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +/* We want to avoid outer shareable. */ +u64 vgic_sanitise_shareability(u64 field) +{ + switch (field) { + case GIC_BASER_OuterShareable: + return GIC_BASER_InnerShareable; + default: + return field; + } +} + +/* Avoid any inner non-cacheable mapping. */ +u64 vgic_sanitise_inner_cacheability(u64 field) +{ + switch (field) { + case GIC_BASER_CACHE_nCnB: + case GIC_BASER_CACHE_nC: + return GIC_BASER_CACHE_RaWb; + default: + return field; + } +} + +/* Non-cacheable or same-as-inner are OK. */ +u64 vgic_sanitise_outer_cacheability(u64 field) +{ + switch (field) { + case GIC_BASER_CACHE_SameAsInner: + case GIC_BASER_CACHE_nC: + return field; + default: + return GIC_BASER_CACHE_nC; + } +} + +u64 vgic_sanitise_field(u64 reg, u64 field_mask, int field_shift, + u64 (*sanitise_fn)(u64)) +{ + u64 field = (reg & field_mask) >> field_shift; + + field = sanitise_fn(field) << field_shift; + return (reg & ~field_mask) | field; +} + +#define PROPBASER_RES0_MASK \ + (GENMASK_ULL(63, 59) | GENMASK_ULL(55, 52) | GENMASK_ULL(6, 5)) +#define PENDBASER_RES0_MASK \ + (BIT_ULL(63) | GENMASK_ULL(61, 59) | GENMASK_ULL(55, 52) | \ + GENMASK_ULL(15, 12) | GENMASK_ULL(6, 0)) + +static u64 vgic_sanitise_pendbaser(u64 reg) +{ + reg = vgic_sanitise_field(reg, GICR_PENDBASER_SHAREABILITY_MASK, + GICR_PENDBASER_SHAREABILITY_SHIFT, + vgic_sanitise_shareability); + reg = vgic_sanitise_field(reg, GICR_PENDBASER_INNER_CACHEABILITY_MASK, + GICR_PENDBASER_INNER_CACHEABILITY_SHIFT, + vgic_sanitise_inner_cacheability); + reg = vgic_sanitise_field(reg, GICR_PENDBASER_OUTER_CACHEABILITY_MASK, + GICR_PENDBASER_OUTER_CACHEABILITY_SHIFT, + vgic_sanitise_outer_cacheability); + + reg &= ~PENDBASER_RES0_MASK; + + return reg; +} + +static u64 vgic_sanitise_propbaser(u64 reg) +{ + reg = vgic_sanitise_field(reg, GICR_PROPBASER_SHAREABILITY_MASK, + GICR_PROPBASER_SHAREABILITY_SHIFT, + vgic_sanitise_shareability); + reg = vgic_sanitise_field(reg, GICR_PROPBASER_INNER_CACHEABILITY_MASK, + GICR_PROPBASER_INNER_CACHEABILITY_SHIFT, + vgic_sanitise_inner_cacheability); + reg = vgic_sanitise_field(reg, GICR_PROPBASER_OUTER_CACHEABILITY_MASK, + GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT, + vgic_sanitise_outer_cacheability); + + reg &= ~PROPBASER_RES0_MASK; + return reg; +} + +static unsigned long vgic_mmio_read_propbase(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + return extract_bytes(dist->propbaser, addr & 7, len); +} + +static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + u64 old_propbaser, propbaser; + + /* Storing a value with LPIs already enabled is undefined */ + if (vgic_cpu->lpis_enabled) + return; + + do { + old_propbaser = READ_ONCE(dist->propbaser); + propbaser = old_propbaser; + propbaser = update_64bit_reg(propbaser, addr & 4, len, val); + propbaser = vgic_sanitise_propbaser(propbaser); + } while (cmpxchg64(&dist->propbaser, old_propbaser, + propbaser) != old_propbaser); +} + +static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + u64 value = vgic_cpu->pendbaser; + + value &= ~GICR_PENDBASER_PTZ; + + return extract_bytes(value, addr & 7, len); +} + +static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + u64 old_pendbaser, pendbaser; + + /* Storing a value with LPIs already enabled is undefined */ + if (vgic_cpu->lpis_enabled) + return; + + do { + old_pendbaser = READ_ONCE(vgic_cpu->pendbaser); + pendbaser = old_pendbaser; + pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val); + pendbaser = vgic_sanitise_pendbaser(pendbaser); + } while (cmpxchg64(&vgic_cpu->pendbaser, old_pendbaser, + pendbaser) != old_pendbaser); +} + +/* + * The GICv3 per-IRQ registers are split to control PPIs and SGIs in the + * redistributors, while SPIs are covered by registers in the distributor + * block. Trying to set private IRQs in this block gets ignored. + * We take some special care here to fix the calculation of the register + * offset. + */ +#define REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(off, rd, wr, ur, uw, bpi, acc) \ + { \ + .reg_offset = off, \ + .bits_per_irq = bpi, \ + .len = (bpi * VGIC_NR_PRIVATE_IRQS) / 8, \ + .access_flags = acc, \ + .read = vgic_mmio_read_raz, \ + .write = vgic_mmio_write_wi, \ + }, { \ + .reg_offset = off + (bpi * VGIC_NR_PRIVATE_IRQS) / 8, \ + .bits_per_irq = bpi, \ + .len = (bpi * (1024 - VGIC_NR_PRIVATE_IRQS)) / 8, \ + .access_flags = acc, \ + .read = rd, \ + .write = wr, \ + .uaccess_read = ur, \ + .uaccess_write = uw, \ + } + +static const struct vgic_register_region vgic_v3_dist_registers[] = { + REGISTER_DESC_WITH_LENGTH_UACCESS(GICD_CTLR, + vgic_mmio_read_v3_misc, vgic_mmio_write_v3_misc, + NULL, vgic_mmio_uaccess_write_v3_misc, + 16, VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICD_STATUSR, + vgic_mmio_read_rao, vgic_mmio_write_wi, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IGROUPR, + vgic_mmio_read_group, vgic_mmio_write_group, NULL, NULL, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISENABLER, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICENABLER, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR, + vgic_mmio_read_pending, vgic_mmio_write_spending, + vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICPENDR, + vgic_mmio_read_pending, vgic_mmio_write_cpending, + vgic_mmio_read_raz, vgic_mmio_uaccess_write_wi, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER, + vgic_mmio_read_active, vgic_mmio_write_sactive, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER, + vgic_mmio_read_active, vgic_mmio_write_cactive, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, + 1, VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR, + vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, + 8, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ITARGETSR, + vgic_mmio_read_raz, vgic_mmio_write_wi, NULL, NULL, 8, + VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICFGR, + vgic_mmio_read_config, vgic_mmio_write_config, NULL, NULL, 2, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IGRPMODR, + vgic_mmio_read_raz, vgic_mmio_write_wi, NULL, NULL, 1, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IROUTER, + vgic_mmio_read_irouter, vgic_mmio_write_irouter, NULL, NULL, 64, + VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICD_IDREGS, + vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48, + VGIC_ACCESS_32bit), +}; + +static const struct vgic_register_region vgic_v3_rd_registers[] = { + /* RD_base registers */ + REGISTER_DESC_WITH_LENGTH(GICR_CTLR, + vgic_mmio_read_v3r_ctlr, vgic_mmio_write_v3r_ctlr, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICR_STATUSR, + vgic_mmio_read_raz, vgic_mmio_write_wi, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICR_IIDR, + vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICR_TYPER, + vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, 8, + VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICR_WAKER, + vgic_mmio_read_raz, vgic_mmio_write_wi, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICR_PROPBASER, + vgic_mmio_read_propbase, vgic_mmio_write_propbase, 8, + VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICR_PENDBASER, + vgic_mmio_read_pendbase, vgic_mmio_write_pendbase, 8, + VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICR_IDREGS, + vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48, + VGIC_ACCESS_32bit), + /* SGI_base registers */ + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGROUPR0, + vgic_mmio_read_group, vgic_mmio_write_group, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISENABLER0, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICENABLER0, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0, + vgic_mmio_read_pending, vgic_mmio_write_spending, + vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICPENDR0, + vgic_mmio_read_pending, vgic_mmio_write_cpending, + vgic_mmio_read_raz, vgic_mmio_uaccess_write_wi, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISACTIVER0, + vgic_mmio_read_active, vgic_mmio_write_sactive, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICACTIVER0, + vgic_mmio_read_active, vgic_mmio_write_cactive, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IPRIORITYR0, + vgic_mmio_read_priority, vgic_mmio_write_priority, 32, + VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ICFGR0, + vgic_mmio_read_config, vgic_mmio_write_config, 8, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGRPMODR0, + vgic_mmio_read_raz, vgic_mmio_write_wi, 4, + VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_NSACR, + vgic_mmio_read_raz, vgic_mmio_write_wi, 4, + VGIC_ACCESS_32bit), +}; + +unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev) +{ + dev->regions = vgic_v3_dist_registers; + dev->nr_regions = ARRAY_SIZE(vgic_v3_dist_registers); + + kvm_iodevice_init(&dev->dev, &kvm_io_gic_ops); + + return SZ_64K; +} + +/** + * vgic_register_redist_iodev - register a single redist iodev + * @vcpu: The VCPU to which the redistributor belongs + * + * Register a KVM iodev for this VCPU's redistributor using the address + * provided. + * + * Return 0 on success, -ERRNO otherwise. + */ +int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + struct vgic_dist *vgic = &kvm->arch.vgic; + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; + struct vgic_redist_region *rdreg; + gpa_t rd_base; + int ret; + + if (!IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) + return 0; + + /* + * We may be creating VCPUs before having set the base address for the + * redistributor region, in which case we will come back to this + * function for all VCPUs when the base address is set. Just return + * without doing any work for now. + */ + rdreg = vgic_v3_rdist_free_slot(&vgic->rd_regions); + if (!rdreg) + return 0; + + if (!vgic_v3_check_base(kvm)) + return -EINVAL; + + vgic_cpu->rdreg = rdreg; + + rd_base = rdreg->base + rdreg->free_index * KVM_VGIC_V3_REDIST_SIZE; + + kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops); + rd_dev->base_addr = rd_base; + rd_dev->iodev_type = IODEV_REDIST; + rd_dev->regions = vgic_v3_rd_registers; + rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rd_registers); + rd_dev->redist_vcpu = vcpu; + + mutex_lock(&kvm->slots_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base, + 2 * SZ_64K, &rd_dev->dev); + mutex_unlock(&kvm->slots_lock); + + if (ret) + return ret; + + rdreg->free_index++; + return 0; +} + +static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) +{ + struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; + + kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &rd_dev->dev); +} + +static int vgic_register_all_redist_iodevs(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int c, ret = 0; + + kvm_for_each_vcpu(c, vcpu, kvm) { + ret = vgic_register_redist_iodev(vcpu); + if (ret) + break; + } + + if (ret) { + /* The current c failed, so we start with the previous one. */ + mutex_lock(&kvm->slots_lock); + for (c--; c >= 0; c--) { + vcpu = kvm_get_vcpu(kvm, c); + vgic_unregister_redist_iodev(vcpu); + } + mutex_unlock(&kvm->slots_lock); + } + + return ret; +} + +/** + * vgic_v3_insert_redist_region - Insert a new redistributor region + * + * Performs various checks before inserting the rdist region in the list. + * Those tests depend on whether the size of the rdist region is known + * (ie. count != 0). The list is sorted by rdist region index. + * + * @kvm: kvm handle + * @index: redist region index + * @base: base of the new rdist region + * @count: number of redistributors the region is made of (0 in the old style + * single region, whose size is induced from the number of vcpus) + * + * Return 0 on success, < 0 otherwise + */ +static int vgic_v3_insert_redist_region(struct kvm *kvm, uint32_t index, + gpa_t base, uint32_t count) +{ + struct vgic_dist *d = &kvm->arch.vgic; + struct vgic_redist_region *rdreg; + struct list_head *rd_regions = &d->rd_regions; + size_t size = count * KVM_VGIC_V3_REDIST_SIZE; + int ret; + + /* single rdist region already set ?*/ + if (!count && !list_empty(rd_regions)) + return -EINVAL; + + /* cross the end of memory ? */ + if (base + size < base) + return -EINVAL; + + if (list_empty(rd_regions)) { + if (index != 0) + return -EINVAL; + } else { + rdreg = list_last_entry(rd_regions, + struct vgic_redist_region, list); + if (index != rdreg->index + 1) + return -EINVAL; + + /* Cannot add an explicitly sized regions after legacy region */ + if (!rdreg->count) + return -EINVAL; + } + + /* + * For legacy single-region redistributor regions (!count), + * check that the redistributor region does not overlap with the + * distributor's address space. + */ + if (!count && !IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && + vgic_dist_overlap(kvm, base, size)) + return -EINVAL; + + /* collision with any other rdist region? */ + if (vgic_v3_rdist_overlap(kvm, base, size)) + return -EINVAL; + + rdreg = kzalloc(sizeof(*rdreg), GFP_KERNEL); + if (!rdreg) + return -ENOMEM; + + rdreg->base = VGIC_ADDR_UNDEF; + + ret = vgic_check_ioaddr(kvm, &rdreg->base, base, SZ_64K); + if (ret) + goto free; + + rdreg->base = base; + rdreg->count = count; + rdreg->free_index = 0; + rdreg->index = index; + + list_add_tail(&rdreg->list, rd_regions); + return 0; +free: + kfree(rdreg); + return ret; +} + +int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) +{ + int ret; + + ret = vgic_v3_insert_redist_region(kvm, index, addr, count); + if (ret) + return ret; + + /* + * Register iodevs for each existing VCPU. Adding more VCPUs + * afterwards will register the iodevs when needed. + */ + ret = vgic_register_all_redist_iodevs(kvm); + if (ret) + return ret; + + return 0; +} + +int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + const struct vgic_register_region *region; + struct vgic_io_device iodev; + struct vgic_reg_attr reg_attr; + struct kvm_vcpu *vcpu; + gpa_t addr; + int ret; + + ret = vgic_v3_parse_attr(dev, attr, ®_attr); + if (ret) + return ret; + + vcpu = reg_attr.vcpu; + addr = reg_attr.addr; + + switch (attr->group) { + case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: + iodev.regions = vgic_v3_dist_registers; + iodev.nr_regions = ARRAY_SIZE(vgic_v3_dist_registers); + iodev.base_addr = 0; + break; + case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:{ + iodev.regions = vgic_v3_rd_registers; + iodev.nr_regions = ARRAY_SIZE(vgic_v3_rd_registers); + iodev.base_addr = 0; + break; + } + case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: { + u64 reg, id; + + id = (attr->attr & KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK); + return vgic_v3_has_cpu_sysregs_attr(vcpu, 0, id, ®); + } + default: + return -ENXIO; + } + + /* We only support aligned 32-bit accesses. */ + if (addr & 3) + return -ENXIO; + + region = vgic_get_mmio_region(vcpu, &iodev, addr, sizeof(u32)); + if (!region) + return -ENXIO; + + return 0; +} +/* + * Compare a given affinity (level 1-3 and a level 0 mask, from the SGI + * generation register ICC_SGI1R_EL1) with a given VCPU. + * If the VCPU's MPIDR matches, return the level0 affinity, otherwise + * return -1. + */ +static int match_mpidr(u64 sgi_aff, u16 sgi_cpu_mask, struct kvm_vcpu *vcpu) +{ + unsigned long affinity; + int level0; + + /* + * Split the current VCPU's MPIDR into affinity level 0 and the + * rest as this is what we have to compare against. + */ + affinity = kvm_vcpu_get_mpidr_aff(vcpu); + level0 = MPIDR_AFFINITY_LEVEL(affinity, 0); + affinity &= ~MPIDR_LEVEL_MASK; + + /* bail out if the upper three levels don't match */ + if (sgi_aff != affinity) + return -1; + + /* Is this VCPU's bit set in the mask ? */ + if (!(sgi_cpu_mask & BIT(level0))) + return -1; + + return level0; +} + +/* + * The ICC_SGI* registers encode the affinity differently from the MPIDR, + * so provide a wrapper to use the existing defines to isolate a certain + * affinity level. + */ +#define SGI_AFFINITY_LEVEL(reg, level) \ + ((((reg) & ICC_SGI1R_AFFINITY_## level ##_MASK) \ + >> ICC_SGI1R_AFFINITY_## level ##_SHIFT) << MPIDR_LEVEL_SHIFT(level)) + +/** + * vgic_v3_dispatch_sgi - handle SGI requests from VCPUs + * @vcpu: The VCPU requesting a SGI + * @reg: The value written into ICC_{ASGI1,SGI0,SGI1}R by that VCPU + * @allow_group1: Does the sysreg access allow generation of G1 SGIs + * + * With GICv3 (and ARE=1) CPUs trigger SGIs by writing to a system register. + * This will trap in sys_regs.c and call this function. + * This ICC_SGI1R_EL1 register contains the upper three affinity levels of the + * target processors as well as a bitmask of 16 Aff0 CPUs. + * If the interrupt routing mode bit is not set, we iterate over all VCPUs to + * check for matching ones. If this bit is set, we signal all, but not the + * calling VCPU. + */ +void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu *c_vcpu; + u16 target_cpus; + u64 mpidr; + int sgi, c; + int vcpu_id = vcpu->vcpu_id; + bool broadcast; + unsigned long flags; + + sgi = (reg & ICC_SGI1R_SGI_ID_MASK) >> ICC_SGI1R_SGI_ID_SHIFT; + broadcast = reg & BIT_ULL(ICC_SGI1R_IRQ_ROUTING_MODE_BIT); + target_cpus = (reg & ICC_SGI1R_TARGET_LIST_MASK) >> ICC_SGI1R_TARGET_LIST_SHIFT; + mpidr = SGI_AFFINITY_LEVEL(reg, 3); + mpidr |= SGI_AFFINITY_LEVEL(reg, 2); + mpidr |= SGI_AFFINITY_LEVEL(reg, 1); + + /* + * We iterate over all VCPUs to find the MPIDRs matching the request. + * If we have handled one CPU, we clear its bit to detect early + * if we are already finished. This avoids iterating through all + * VCPUs when most of the times we just signal a single VCPU. + */ + kvm_for_each_vcpu(c, c_vcpu, kvm) { + struct vgic_irq *irq; + + /* Exit early if we have dealt with all requested CPUs */ + if (!broadcast && target_cpus == 0) + break; + + /* Don't signal the calling VCPU */ + if (broadcast && c == vcpu_id) + continue; + + if (!broadcast) { + int level0; + + level0 = match_mpidr(mpidr, target_cpus, c_vcpu); + if (level0 == -1) + continue; + + /* remove this matching VCPU from the mask */ + target_cpus &= ~BIT(level0); + } + + irq = vgic_get_irq(vcpu->kvm, c_vcpu, sgi); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + /* + * An access targetting Group0 SGIs can only generate + * those, while an access targetting Group1 SGIs can + * generate interrupts of either group. + */ + if (!irq->group || allow_group1) { + if (!irq->hw) { + irq->pending_latch = true; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + } else { + /* HW SGI? Ask the GIC to inject it */ + int err; + err = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + true); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + } + } else { + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + } + + vgic_put_irq(vcpu->kvm, irq); + } +} + +int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, + int offset, u32 *val) +{ + struct vgic_io_device dev = { + .regions = vgic_v3_dist_registers, + .nr_regions = ARRAY_SIZE(vgic_v3_dist_registers), + }; + + return vgic_uaccess(vcpu, &dev, is_write, offset, val); +} + +int vgic_v3_redist_uaccess(struct kvm_vcpu *vcpu, bool is_write, + int offset, u32 *val) +{ + struct vgic_io_device rd_dev = { + .regions = vgic_v3_rd_registers, + .nr_regions = ARRAY_SIZE(vgic_v3_rd_registers), + }; + + return vgic_uaccess(vcpu, &rd_dev, is_write, offset, val); +} + +int vgic_v3_line_level_info_uaccess(struct kvm_vcpu *vcpu, bool is_write, + u32 intid, u64 *val) +{ + if (intid % 32) + return -EINVAL; + + if (is_write) + vgic_write_irq_line_level_info(vcpu, intid, *val); + else + *val = vgic_read_irq_line_level_info(vcpu, intid); + + return 0; +} diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c new file mode 100644 index 000000000000..b2d73fc0d1ef --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -0,0 +1,1088 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * VGIC MMIO handling functions + */ + +#include <linux/bitops.h> +#include <linux/bsearch.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <kvm/iodev.h> +#include <kvm/arm_arch_timer.h> +#include <kvm/arm_vgic.h> + +#include "vgic.h" +#include "vgic-mmio.h" + +unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return 0; +} + +unsigned long vgic_mmio_read_rao(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return -1UL; +} + +void vgic_mmio_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, + unsigned int len, unsigned long val) +{ + /* Ignore */ +} + +int vgic_mmio_uaccess_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, + unsigned int len, unsigned long val) +{ + /* Ignore */ + return 0; +} + +unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + u32 value = 0; + int i; + + /* Loop over all IRQs affected by this read */ + for (i = 0; i < len * 8; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + if (irq->group) + value |= BIT(i); + + vgic_put_irq(vcpu->kvm, irq); + } + + return value; +} + +static void vgic_update_vsgi(struct vgic_irq *irq) +{ + WARN_ON(its_prop_update_vsgi(irq->host_irq, irq->priority, irq->group)); +} + +void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, + unsigned int len, unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for (i = 0; i < len * 8; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->group = !!(val & BIT(i)); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + vgic_update_vsgi(irq); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + } else { + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + } + + vgic_put_irq(vcpu->kvm, irq); + } +} + +/* + * Read accesses to both GICD_ICENABLER and GICD_ISENABLER return the value + * of the enabled bit, so there is only one function for both here. + */ +unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + u32 value = 0; + int i; + + /* Loop over all IRQs affected by this read */ + for (i = 0; i < len * 8; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + if (irq->enabled) + value |= (1U << i); + + vgic_put_irq(vcpu->kvm, irq); + } + + return value; +} + +void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + if (!irq->enabled) { + struct irq_data *data; + + irq->enabled = true; + data = &irq_to_desc(irq->host_irq)->irq_data; + while (irqd_irq_disabled(data)) + enable_irq(irq->host_irq); + } + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + continue; + } else if (vgic_irq_is_mapped_level(irq)) { + bool was_high = irq->line_level; + + /* + * We need to update the state of the interrupt because + * the guest might have changed the state of the device + * while the interrupt was disabled at the VGIC level. + */ + irq->line_level = vgic_get_phys_line_level(irq); + /* + * Deactivate the physical interrupt so the GIC will let + * us know when it is asserted again. + */ + if (!irq->active && was_high && !irq->line_level) + vgic_irq_set_phys_active(irq, false); + } + irq->enabled = true; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } +} + +void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->hw && vgic_irq_is_sgi(irq->intid) && irq->enabled) + disable_irq_nosync(irq->host_irq); + + irq->enabled = false; + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->enabled = true; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->enabled = false; + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + u32 value = 0; + int i; + + /* Loop over all IRQs affected by this read */ + for (i = 0; i < len * 8; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + unsigned long flags; + bool val; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + int err; + + val = false; + err = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &val); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + } else { + val = irq_is_pending(irq); + } + + value |= ((u32)val << i); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return value; +} + +static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq) +{ + return (vgic_irq_is_sgi(irq->intid) && + vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2); +} + +void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + /* GICD_ISPENDR0 SGI bits are WI */ + if (is_vgic_v2_sgi(vcpu, irq)) { + vgic_put_irq(vcpu->kvm, irq); + continue; + } + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + /* HW SGI? Ask the GIC to inject it */ + int err; + err = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + true); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + continue; + } + + irq->pending_latch = true; + if (irq->hw) + vgic_irq_set_phys_active(irq, true); + + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->pending_latch = true; + + /* + * GICv2 SGIs are terribly broken. We can't restore + * the source of the interrupt, so just pick the vcpu + * itself as the source... + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source |= BIT(vcpu->vcpu_id); + + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq) +{ + irq->pending_latch = false; + + /* + * We don't want the guest to effectively mask the physical + * interrupt by doing a write to SPENDR followed by a write to + * CPENDR for HW interrupts, so we clear the active state on + * the physical side if the virtual interrupt is not active. + * This may lead to taking an additional interrupt on the + * host, but that should not be a problem as the worst that + * can happen is an additional vgic injection. We also clear + * the pending state to maintain proper semantics for edge HW + * interrupts. + */ + vgic_irq_set_phys_pending(irq, false); + if (!irq->active) + vgic_irq_set_phys_active(irq, false); +} + +void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + /* GICD_ICPENDR0 SGI bits are WI */ + if (is_vgic_v2_sgi(vcpu, irq)) { + vgic_put_irq(vcpu->kvm, irq); + continue; + } + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + /* HW SGI? Ask the GIC to clear its pending bit */ + int err; + err = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + false); + WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + continue; + } + + if (irq->hw) + vgic_hw_irq_cpending(vcpu, irq); + else + irq->pending_latch = false; + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + /* + * More fun with GICv2 SGIs! If we're clearing one of them + * from userspace, which source vcpu to clear? Let's not + * even think of it, and blow the whole set. + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source = 0; + + irq->pending_latch = false; + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +/* + * If we are fiddling with an IRQ's active state, we have to make sure the IRQ + * is not queued on some running VCPU's LRs, because then the change to the + * active state can be overwritten when the VCPU's state is synced coming back + * from the guest. + * + * For shared interrupts as well as GICv3 private interrupts, we have to + * stop all the VCPUs because interrupts can be migrated while we don't hold + * the IRQ locks and we don't want to be chasing moving targets. + * + * For GICv2 private interrupts we don't have to do anything because + * userspace accesses to the VGIC state already require all VCPUs to be + * stopped, and only the VCPU itself can modify its private interrupts + * active state, which guarantees that the VCPU is not running. + */ +static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_halt_guest(vcpu->kvm); +} + +/* See vgic_access_active_prepare */ +static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_resume_guest(vcpu->kvm); +} + +static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + u32 value = 0; + int i; + + /* Loop over all IRQs affected by this read */ + for (i = 0; i < len * 8; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + /* + * Even for HW interrupts, don't evaluate the HW state as + * all the guest is interested in is the virtual state. + */ + if (irq->active) + value |= (1U << i); + + vgic_put_irq(vcpu->kvm, irq); + } + + return value; +} + +unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + u32 val; + + mutex_lock(&vcpu->kvm->lock); + vgic_access_active_prepare(vcpu, intid); + + val = __vgic_mmio_read_active(vcpu, addr, len); + + vgic_access_active_finish(vcpu, intid); + mutex_unlock(&vcpu->kvm->lock); + + return val; +} + +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return __vgic_mmio_read_active(vcpu, addr, len); +} + +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, + bool active, bool is_uaccess) +{ + if (is_uaccess) + return; + + irq->active = active; + vgic_irq_set_phys_active(irq, active); +} + +static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, + bool active) +{ + unsigned long flags; + struct kvm_vcpu *requester_vcpu = kvm_get_running_vcpu(); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (irq->hw && !vgic_irq_is_sgi(irq->intid)) { + vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); + } else if (irq->hw && vgic_irq_is_sgi(irq->intid)) { + /* + * GICv4.1 VSGI feature doesn't track an active state, + * so let's not kid ourselves, there is nothing we can + * do here. + */ + irq->active = false; + } else { + u32 model = vcpu->kvm->arch.vgic.vgic_model; + u8 active_source; + + irq->active = active; + + /* + * The GICv2 architecture indicates that the source CPUID for + * an SGI should be provided during an EOI which implies that + * the active state is stored somewhere, but at the same time + * this state is not architecturally exposed anywhere and we + * have no way of knowing the right source. + * + * This may lead to a VCPU not being able to receive + * additional instances of a particular SGI after migration + * for a GICv2 VM on some GIC implementations. Oh well. + */ + active_source = (requester_vcpu) ? requester_vcpu->vcpu_id : 0; + + if (model == KVM_DEV_TYPE_ARM_VGIC_V2 && + active && vgic_irq_is_sgi(irq->intid)) + irq->active_source = active_source; + } + + if (irq->active) + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + else + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); +} + +static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + vgic_mmio_change_active(vcpu, irq, false); + vgic_put_irq(vcpu->kvm, irq); + } +} + +void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + + mutex_lock(&vcpu->kvm->lock); + vgic_access_active_prepare(vcpu, intid); + + __vgic_mmio_write_cactive(vcpu, addr, len, val); + + vgic_access_active_finish(vcpu, intid); + mutex_unlock(&vcpu->kvm->lock); +} + +int vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + __vgic_mmio_write_cactive(vcpu, addr, len, val); + return 0; +} + +static void __vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + vgic_mmio_change_active(vcpu, irq, true); + vgic_put_irq(vcpu->kvm, irq); + } +} + +void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + + mutex_lock(&vcpu->kvm->lock); + vgic_access_active_prepare(vcpu, intid); + + __vgic_mmio_write_sactive(vcpu, addr, len, val); + + vgic_access_active_finish(vcpu, intid); + mutex_unlock(&vcpu->kvm->lock); +} + +int vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + __vgic_mmio_write_sactive(vcpu, addr, len, val); + return 0; +} + +unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 8); + int i; + u64 val = 0; + + for (i = 0; i < len; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + val |= (u64)irq->priority << (i * 8); + + vgic_put_irq(vcpu->kvm, irq); + } + + return val; +} + +/* + * We currently don't handle changing the priority of an interrupt that + * is already pending on a VCPU. If there is a need for this, we would + * need to make this VCPU exit and re-evaluate the priorities, potentially + * leading to this interrupt getting presented now to the guest (if it has + * been masked by the priority mask before). + */ +void vgic_mmio_write_priority(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 8); + int i; + unsigned long flags; + + for (i = 0; i < len; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + /* Narrow the priority range to what we actually support */ + irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS); + if (irq->hw && vgic_irq_is_sgi(irq->intid)) + vgic_update_vsgi(irq); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } +} + +unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 2); + u32 value = 0; + int i; + + for (i = 0; i < len * 4; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + if (irq->config == VGIC_CONFIG_EDGE) + value |= (2U << (i * 2)); + + vgic_put_irq(vcpu->kvm, irq); + } + + return value; +} + +void vgic_mmio_write_config(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 2); + int i; + unsigned long flags; + + for (i = 0; i < len * 4; i++) { + struct vgic_irq *irq; + + /* + * The configuration cannot be changed for SGIs in general, + * for PPIs this is IMPLEMENTATION DEFINED. The arch timer + * code relies on PPIs being level triggered, so we also + * make them read-only here. + */ + if (intid + i < VGIC_NR_PRIVATE_IRQS) + continue; + + irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (test_bit(i * 2 + 1, &val)) + irq->config = VGIC_CONFIG_EDGE; + else + irq->config = VGIC_CONFIG_LEVEL; + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +u64 vgic_read_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid) +{ + int i; + u64 val = 0; + int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; + + for (i = 0; i < 32; i++) { + struct vgic_irq *irq; + + if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs) + continue; + + irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + if (irq->config == VGIC_CONFIG_LEVEL && irq->line_level) + val |= (1U << i); + + vgic_put_irq(vcpu->kvm, irq); + } + + return val; +} + +void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid, + const u64 val) +{ + int i; + int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; + unsigned long flags; + + for (i = 0; i < 32; i++) { + struct vgic_irq *irq; + bool new_level; + + if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs) + continue; + + irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + /* + * Line level is set irrespective of irq type + * (level or edge) to avoid dependency that VM should + * restore irq config before line level. + */ + new_level = !!(val & (1U << i)); + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->line_level = new_level; + if (new_level) + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + else + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } +} + +static int match_region(const void *key, const void *elt) +{ + const unsigned int offset = (unsigned long)key; + const struct vgic_register_region *region = elt; + + if (offset < region->reg_offset) + return -1; + + if (offset >= region->reg_offset + region->len) + return 1; + + return 0; +} + +const struct vgic_register_region * +vgic_find_mmio_region(const struct vgic_register_region *regions, + int nr_regions, unsigned int offset) +{ + return bsearch((void *)(uintptr_t)offset, regions, nr_regions, + sizeof(regions[0]), match_region); +} + +void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) +{ + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_set_vmcr(vcpu, vmcr); + else + vgic_v3_set_vmcr(vcpu, vmcr); +} + +void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) +{ + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_get_vmcr(vcpu, vmcr); + else + vgic_v3_get_vmcr(vcpu, vmcr); +} + +/* + * kvm_mmio_read_buf() returns a value in a format where it can be converted + * to a byte array and be directly observed as the guest wanted it to appear + * in memory if it had done the store itself, which is LE for the GIC, as the + * guest knows the GIC is always LE. + * + * We convert this value to the CPUs native format to deal with it as a data + * value. + */ +unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len) +{ + unsigned long data = kvm_mmio_read_buf(val, len); + + switch (len) { + case 1: + return data; + case 2: + return le16_to_cpu(data); + case 4: + return le32_to_cpu(data); + default: + return le64_to_cpu(data); + } +} + +/* + * kvm_mmio_write_buf() expects a value in a format such that if converted to + * a byte array it is observed as the guest would see it if it could perform + * the load directly. Since the GIC is LE, and the guest knows this, the + * guest expects a value in little endian format. + * + * We convert the data value from the CPUs native format to LE so that the + * value is returned in the proper format. + */ +void vgic_data_host_to_mmio_bus(void *buf, unsigned int len, + unsigned long data) +{ + switch (len) { + case 1: + break; + case 2: + data = cpu_to_le16(data); + break; + case 4: + data = cpu_to_le32(data); + break; + default: + data = cpu_to_le64(data); + } + + kvm_mmio_write_buf(buf, len, data); +} + +static +struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev) +{ + return container_of(dev, struct vgic_io_device, dev); +} + +static bool check_region(const struct kvm *kvm, + const struct vgic_register_region *region, + gpa_t addr, int len) +{ + int flags, nr_irqs = kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; + + switch (len) { + case sizeof(u8): + flags = VGIC_ACCESS_8bit; + break; + case sizeof(u32): + flags = VGIC_ACCESS_32bit; + break; + case sizeof(u64): + flags = VGIC_ACCESS_64bit; + break; + default: + return false; + } + + if ((region->access_flags & flags) && IS_ALIGNED(addr, len)) { + if (!region->bits_per_irq) + return true; + + /* Do we access a non-allocated IRQ? */ + return VGIC_ADDR_TO_INTID(addr, region->bits_per_irq) < nr_irqs; + } + + return false; +} + +const struct vgic_register_region * +vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, + gpa_t addr, int len) +{ + const struct vgic_register_region *region; + + region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions, + addr - iodev->base_addr); + if (!region || !check_region(vcpu->kvm, region, addr, len)) + return NULL; + + return region; +} + +static int vgic_uaccess_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, + gpa_t addr, u32 *val) +{ + struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); + const struct vgic_register_region *region; + struct kvm_vcpu *r_vcpu; + + region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32)); + if (!region) { + *val = 0; + return 0; + } + + r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu; + if (region->uaccess_read) + *val = region->uaccess_read(r_vcpu, addr, sizeof(u32)); + else + *val = region->read(r_vcpu, addr, sizeof(u32)); + + return 0; +} + +static int vgic_uaccess_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, + gpa_t addr, const u32 *val) +{ + struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); + const struct vgic_register_region *region; + struct kvm_vcpu *r_vcpu; + + region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32)); + if (!region) + return 0; + + r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu; + if (region->uaccess_write) + return region->uaccess_write(r_vcpu, addr, sizeof(u32), *val); + + region->write(r_vcpu, addr, sizeof(u32), *val); + return 0; +} + +/* + * Userland access to VGIC registers. + */ +int vgic_uaccess(struct kvm_vcpu *vcpu, struct vgic_io_device *dev, + bool is_write, int offset, u32 *val) +{ + if (is_write) + return vgic_uaccess_write(vcpu, &dev->dev, offset, val); + else + return vgic_uaccess_read(vcpu, &dev->dev, offset, val); +} + +static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); + const struct vgic_register_region *region; + unsigned long data = 0; + + region = vgic_get_mmio_region(vcpu, iodev, addr, len); + if (!region) { + memset(val, 0, len); + return 0; + } + + switch (iodev->iodev_type) { + case IODEV_CPUIF: + data = region->read(vcpu, addr, len); + break; + case IODEV_DIST: + data = region->read(vcpu, addr, len); + break; + case IODEV_REDIST: + data = region->read(iodev->redist_vcpu, addr, len); + break; + case IODEV_ITS: + data = region->its_read(vcpu->kvm, iodev->its, addr, len); + break; + } + + vgic_data_host_to_mmio_bus(val, len, data); + return 0; +} + +static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); + const struct vgic_register_region *region; + unsigned long data = vgic_data_mmio_bus_to_host(val, len); + + region = vgic_get_mmio_region(vcpu, iodev, addr, len); + if (!region) + return 0; + + switch (iodev->iodev_type) { + case IODEV_CPUIF: + region->write(vcpu, addr, len, data); + break; + case IODEV_DIST: + region->write(vcpu, addr, len, data); + break; + case IODEV_REDIST: + region->write(iodev->redist_vcpu, addr, len, data); + break; + case IODEV_ITS: + region->its_write(vcpu->kvm, iodev->its, addr, len, data); + break; + } + + return 0; +} + +struct kvm_io_device_ops kvm_io_gic_ops = { + .read = dispatch_mmio_read, + .write = dispatch_mmio_write, +}; + +int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, + enum vgic_type type) +{ + struct vgic_io_device *io_device = &kvm->arch.vgic.dist_iodev; + int ret = 0; + unsigned int len; + + switch (type) { + case VGIC_V2: + len = vgic_v2_init_dist_iodev(io_device); + break; + case VGIC_V3: + len = vgic_v3_init_dist_iodev(io_device); + break; + default: + BUG_ON(1); + } + + io_device->base_addr = dist_base_address; + io_device->iodev_type = IODEV_DIST; + io_device->redist_vcpu = NULL; + + mutex_lock(&kvm->slots_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address, + len, &io_device->dev); + mutex_unlock(&kvm->slots_lock); + + return ret; +} diff --git a/arch/arm64/kvm/vgic/vgic-mmio.h b/arch/arm64/kvm/vgic/vgic-mmio.h new file mode 100644 index 000000000000..fefcca2b14dc --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-mmio.h @@ -0,0 +1,227 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015, 2016 ARM Ltd. + */ +#ifndef __KVM_ARM_VGIC_MMIO_H__ +#define __KVM_ARM_VGIC_MMIO_H__ + +struct vgic_register_region { + unsigned int reg_offset; + unsigned int len; + unsigned int bits_per_irq; + unsigned int access_flags; + union { + unsigned long (*read)(struct kvm_vcpu *vcpu, gpa_t addr, + unsigned int len); + unsigned long (*its_read)(struct kvm *kvm, struct vgic_its *its, + gpa_t addr, unsigned int len); + }; + union { + void (*write)(struct kvm_vcpu *vcpu, gpa_t addr, + unsigned int len, unsigned long val); + void (*its_write)(struct kvm *kvm, struct vgic_its *its, + gpa_t addr, unsigned int len, + unsigned long val); + }; + unsigned long (*uaccess_read)(struct kvm_vcpu *vcpu, gpa_t addr, + unsigned int len); + union { + int (*uaccess_write)(struct kvm_vcpu *vcpu, gpa_t addr, + unsigned int len, unsigned long val); + int (*uaccess_its_write)(struct kvm *kvm, struct vgic_its *its, + gpa_t addr, unsigned int len, + unsigned long val); + }; +}; + +extern struct kvm_io_device_ops kvm_io_gic_ops; + +#define VGIC_ACCESS_8bit 1 +#define VGIC_ACCESS_32bit 2 +#define VGIC_ACCESS_64bit 4 + +/* + * Generate a mask that covers the number of bytes required to address + * up to 1024 interrupts, each represented by <bits> bits. This assumes + * that <bits> is a power of two. + */ +#define VGIC_ADDR_IRQ_MASK(bits) (((bits) * 1024 / 8) - 1) + +/* + * (addr & mask) gives us the _byte_ offset for the INT ID. + * We multiply this by 8 the get the _bit_ offset, then divide this by + * the number of bits to learn the actual INT ID. + * But instead of a division (which requires a "long long div" implementation), + * we shift by the binary logarithm of <bits>. + * This assumes that <bits> is a power of two. + */ +#define VGIC_ADDR_TO_INTID(addr, bits) (((addr) & VGIC_ADDR_IRQ_MASK(bits)) * \ + 8 >> ilog2(bits)) + +/* + * Some VGIC registers store per-IRQ information, with a different number + * of bits per IRQ. For those registers this macro is used. + * The _WITH_LENGTH version instantiates registers with a fixed length + * and is mutually exclusive with the _PER_IRQ version. + */ +#define REGISTER_DESC_WITH_BITS_PER_IRQ(off, rd, wr, ur, uw, bpi, acc) \ + { \ + .reg_offset = off, \ + .bits_per_irq = bpi, \ + .len = bpi * 1024 / 8, \ + .access_flags = acc, \ + .read = rd, \ + .write = wr, \ + .uaccess_read = ur, \ + .uaccess_write = uw, \ + } + +#define REGISTER_DESC_WITH_LENGTH(off, rd, wr, length, acc) \ + { \ + .reg_offset = off, \ + .bits_per_irq = 0, \ + .len = length, \ + .access_flags = acc, \ + .read = rd, \ + .write = wr, \ + } + +#define REGISTER_DESC_WITH_LENGTH_UACCESS(off, rd, wr, urd, uwr, length, acc) \ + { \ + .reg_offset = off, \ + .bits_per_irq = 0, \ + .len = length, \ + .access_flags = acc, \ + .read = rd, \ + .write = wr, \ + .uaccess_read = urd, \ + .uaccess_write = uwr, \ + } + +unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len); + +void vgic_data_host_to_mmio_bus(void *buf, unsigned int len, + unsigned long data); + +unsigned long extract_bytes(u64 data, unsigned int offset, + unsigned int num); + +u64 update_64bit_reg(u64 reg, unsigned int offset, unsigned int len, + unsigned long val); + +unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + +unsigned long vgic_mmio_read_rao(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + +void vgic_mmio_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, + unsigned int len, unsigned long val); + +int vgic_mmio_uaccess_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, + unsigned int len, unsigned long val); + +unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu, gpa_t addr, + unsigned int len); + +void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, + unsigned int len, unsigned long val); + +unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + +void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + +void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + +void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + +void vgic_mmio_write_priority(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + +void vgic_mmio_write_config(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess(struct kvm_vcpu *vcpu, struct vgic_io_device *dev, + bool is_write, int offset, u32 *val); + +u64 vgic_read_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid); + +void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid, + const u64 val); + +unsigned int vgic_v2_init_dist_iodev(struct vgic_io_device *dev); + +unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev); + +u64 vgic_sanitise_outer_cacheability(u64 reg); +u64 vgic_sanitise_inner_cacheability(u64 reg); +u64 vgic_sanitise_shareability(u64 reg); +u64 vgic_sanitise_field(u64 reg, u64 field_mask, int field_shift, + u64 (*sanitise_fn)(u64)); + +/* Find the proper register handler entry given a certain address offset */ +const struct vgic_register_region * +vgic_find_mmio_region(const struct vgic_register_region *regions, + int nr_regions, unsigned int offset); + +#endif diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c new file mode 100644 index 000000000000..ebf53a4e1296 --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-v2.c @@ -0,0 +1,504 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015, 2016 ARM Ltd. + */ + +#include <linux/irqchip/arm-gic.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <kvm/arm_vgic.h> +#include <asm/kvm_mmu.h> + +#include "vgic.h" + +static inline void vgic_v2_write_lr(int lr, u32 val) +{ + void __iomem *base = kvm_vgic_global_state.vctrl_base; + + writel_relaxed(val, base + GICH_LR0 + (lr * 4)); +} + +void vgic_v2_init_lrs(void) +{ + int i; + + for (i = 0; i < kvm_vgic_global_state.nr_lr; i++) + vgic_v2_write_lr(i, 0); +} + +void vgic_v2_set_underflow(struct kvm_vcpu *vcpu) +{ + struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2; + + cpuif->vgic_hcr |= GICH_HCR_UIE; +} + +static bool lr_signals_eoi_mi(u32 lr_val) +{ + return !(lr_val & GICH_LR_STATE) && (lr_val & GICH_LR_EOI) && + !(lr_val & GICH_LR_HW); +} + +/* + * transfer the content of the LRs back into the corresponding ap_list: + * - active bit is transferred as is + * - pending bit is + * - transferred as is in case of edge sensitive IRQs + * - set to the line-level (resample time) for level sensitive IRQs + */ +void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_v2_cpu_if *cpuif = &vgic_cpu->vgic_v2; + int lr; + + DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); + + cpuif->vgic_hcr &= ~GICH_HCR_UIE; + + for (lr = 0; lr < vgic_cpu->vgic_v2.used_lrs; lr++) { + u32 val = cpuif->vgic_lr[lr]; + u32 cpuid, intid = val & GICH_LR_VIRTUALID; + struct vgic_irq *irq; + + /* Extract the source vCPU id from the LR */ + cpuid = val & GICH_LR_PHYSID_CPUID; + cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT; + cpuid &= 7; + + /* Notify fds when the guest EOI'ed a level-triggered SPI */ + if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid)) + kvm_notify_acked_irq(vcpu->kvm, 0, + intid - VGIC_NR_PRIVATE_IRQS); + + irq = vgic_get_irq(vcpu->kvm, vcpu, intid); + + raw_spin_lock(&irq->irq_lock); + + /* Always preserve the active bit */ + irq->active = !!(val & GICH_LR_ACTIVE_BIT); + + if (irq->active && vgic_irq_is_sgi(intid)) + irq->active_source = cpuid; + + /* Edge is the only case where we preserve the pending bit */ + if (irq->config == VGIC_CONFIG_EDGE && + (val & GICH_LR_PENDING_BIT)) { + irq->pending_latch = true; + + if (vgic_irq_is_sgi(intid)) + irq->source |= (1 << cpuid); + } + + /* + * Clear soft pending state when level irqs have been acked. + */ + if (irq->config == VGIC_CONFIG_LEVEL && !(val & GICH_LR_STATE)) + irq->pending_latch = false; + + /* + * Level-triggered mapped IRQs are special because we only + * observe rising edges as input to the VGIC. + * + * If the guest never acked the interrupt we have to sample + * the physical line and set the line level, because the + * device state could have changed or we simply need to + * process the still pending interrupt later. + * + * If this causes us to lower the level, we have to also clear + * the physical active state, since we will otherwise never be + * told when the interrupt becomes asserted again. + */ + if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) { + irq->line_level = vgic_get_phys_line_level(irq); + + if (!irq->line_level) + vgic_irq_set_phys_active(irq, false); + } + + raw_spin_unlock(&irq->irq_lock); + vgic_put_irq(vcpu->kvm, irq); + } + + cpuif->used_lrs = 0; +} + +/* + * Populates the particular LR with the state of a given IRQ: + * - for an edge sensitive IRQ the pending state is cleared in struct vgic_irq + * - for a level sensitive IRQ the pending state value is unchanged; + * it is dictated directly by the input level + * + * If @irq describes an SGI with multiple sources, we choose the + * lowest-numbered source VCPU and clear that bit in the source bitmap. + * + * The irq_lock must be held by the caller. + */ +void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) +{ + u32 val = irq->intid; + bool allow_pending = true; + + if (irq->active) { + val |= GICH_LR_ACTIVE_BIT; + if (vgic_irq_is_sgi(irq->intid)) + val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT; + if (vgic_irq_is_multi_sgi(irq)) { + allow_pending = false; + val |= GICH_LR_EOI; + } + } + + if (irq->group) + val |= GICH_LR_GROUP1; + + if (irq->hw) { + val |= GICH_LR_HW; + val |= irq->hwintid << GICH_LR_PHYSID_CPUID_SHIFT; + /* + * Never set pending+active on a HW interrupt, as the + * pending state is kept at the physical distributor + * level. + */ + if (irq->active) + allow_pending = false; + } else { + if (irq->config == VGIC_CONFIG_LEVEL) { + val |= GICH_LR_EOI; + + /* + * Software resampling doesn't work very well + * if we allow P+A, so let's not do that. + */ + if (irq->active) + allow_pending = false; + } + } + + if (allow_pending && irq_is_pending(irq)) { + val |= GICH_LR_PENDING_BIT; + + if (irq->config == VGIC_CONFIG_EDGE) + irq->pending_latch = false; + + if (vgic_irq_is_sgi(irq->intid)) { + u32 src = ffs(irq->source); + + if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n", + irq->intid)) + return; + + val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT; + irq->source &= ~(1 << (src - 1)); + if (irq->source) { + irq->pending_latch = true; + val |= GICH_LR_EOI; + } + } + } + + /* + * Level-triggered mapped IRQs are special because we only observe + * rising edges as input to the VGIC. We therefore lower the line + * level here, so that we can take new virtual IRQs. See + * vgic_v2_fold_lr_state for more info. + */ + if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) + irq->line_level = false; + + /* The GICv2 LR only holds five bits of priority. */ + val |= (irq->priority >> 3) << GICH_LR_PRIORITY_SHIFT; + + vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = val; +} + +void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr) +{ + vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = 0; +} + +void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) +{ + struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; + u32 vmcr; + + vmcr = (vmcrp->grpen0 << GICH_VMCR_ENABLE_GRP0_SHIFT) & + GICH_VMCR_ENABLE_GRP0_MASK; + vmcr |= (vmcrp->grpen1 << GICH_VMCR_ENABLE_GRP1_SHIFT) & + GICH_VMCR_ENABLE_GRP1_MASK; + vmcr |= (vmcrp->ackctl << GICH_VMCR_ACK_CTL_SHIFT) & + GICH_VMCR_ACK_CTL_MASK; + vmcr |= (vmcrp->fiqen << GICH_VMCR_FIQ_EN_SHIFT) & + GICH_VMCR_FIQ_EN_MASK; + vmcr |= (vmcrp->cbpr << GICH_VMCR_CBPR_SHIFT) & + GICH_VMCR_CBPR_MASK; + vmcr |= (vmcrp->eoim << GICH_VMCR_EOI_MODE_SHIFT) & + GICH_VMCR_EOI_MODE_MASK; + vmcr |= (vmcrp->abpr << GICH_VMCR_ALIAS_BINPOINT_SHIFT) & + GICH_VMCR_ALIAS_BINPOINT_MASK; + vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) & + GICH_VMCR_BINPOINT_MASK; + vmcr |= ((vmcrp->pmr >> GICV_PMR_PRIORITY_SHIFT) << + GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK; + + cpu_if->vgic_vmcr = vmcr; +} + +void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) +{ + struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; + u32 vmcr; + + vmcr = cpu_if->vgic_vmcr; + + vmcrp->grpen0 = (vmcr & GICH_VMCR_ENABLE_GRP0_MASK) >> + GICH_VMCR_ENABLE_GRP0_SHIFT; + vmcrp->grpen1 = (vmcr & GICH_VMCR_ENABLE_GRP1_MASK) >> + GICH_VMCR_ENABLE_GRP1_SHIFT; + vmcrp->ackctl = (vmcr & GICH_VMCR_ACK_CTL_MASK) >> + GICH_VMCR_ACK_CTL_SHIFT; + vmcrp->fiqen = (vmcr & GICH_VMCR_FIQ_EN_MASK) >> + GICH_VMCR_FIQ_EN_SHIFT; + vmcrp->cbpr = (vmcr & GICH_VMCR_CBPR_MASK) >> + GICH_VMCR_CBPR_SHIFT; + vmcrp->eoim = (vmcr & GICH_VMCR_EOI_MODE_MASK) >> + GICH_VMCR_EOI_MODE_SHIFT; + + vmcrp->abpr = (vmcr & GICH_VMCR_ALIAS_BINPOINT_MASK) >> + GICH_VMCR_ALIAS_BINPOINT_SHIFT; + vmcrp->bpr = (vmcr & GICH_VMCR_BINPOINT_MASK) >> + GICH_VMCR_BINPOINT_SHIFT; + vmcrp->pmr = ((vmcr & GICH_VMCR_PRIMASK_MASK) >> + GICH_VMCR_PRIMASK_SHIFT) << GICV_PMR_PRIORITY_SHIFT; +} + +void vgic_v2_enable(struct kvm_vcpu *vcpu) +{ + /* + * By forcing VMCR to zero, the GIC will restore the binary + * points to their reset values. Anything else resets to zero + * anyway. + */ + vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = 0; + + /* Get the show on the road... */ + vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr = GICH_HCR_EN; +} + +/* check for overlapping regions and for regions crossing the end of memory */ +static bool vgic_v2_check_base(gpa_t dist_base, gpa_t cpu_base) +{ + if (dist_base + KVM_VGIC_V2_DIST_SIZE < dist_base) + return false; + if (cpu_base + KVM_VGIC_V2_CPU_SIZE < cpu_base) + return false; + + if (dist_base + KVM_VGIC_V2_DIST_SIZE <= cpu_base) + return true; + if (cpu_base + KVM_VGIC_V2_CPU_SIZE <= dist_base) + return true; + + return false; +} + +int vgic_v2_map_resources(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + int ret = 0; + + if (vgic_ready(kvm)) + goto out; + + if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) || + IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) { + kvm_err("Need to set vgic cpu and dist addresses first\n"); + ret = -ENXIO; + goto out; + } + + if (!vgic_v2_check_base(dist->vgic_dist_base, dist->vgic_cpu_base)) { + kvm_err("VGIC CPU and dist frames overlap\n"); + ret = -EINVAL; + goto out; + } + + /* + * Initialize the vgic if this hasn't already been done on demand by + * accessing the vgic state from userspace. + */ + ret = vgic_init(kvm); + if (ret) { + kvm_err("Unable to initialize VGIC dynamic data structures\n"); + goto out; + } + + ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V2); + if (ret) { + kvm_err("Unable to register VGIC MMIO regions\n"); + goto out; + } + + if (!static_branch_unlikely(&vgic_v2_cpuif_trap)) { + ret = kvm_phys_addr_ioremap(kvm, dist->vgic_cpu_base, + kvm_vgic_global_state.vcpu_base, + KVM_VGIC_V2_CPU_SIZE, true); + if (ret) { + kvm_err("Unable to remap VGIC CPU to VCPU\n"); + goto out; + } + } + + dist->ready = true; + +out: + return ret; +} + +DEFINE_STATIC_KEY_FALSE(vgic_v2_cpuif_trap); + +/** + * vgic_v2_probe - probe for a VGICv2 compatible interrupt controller + * @info: pointer to the GIC description + * + * Returns 0 if the VGICv2 has been probed successfully, returns an error code + * otherwise + */ +int vgic_v2_probe(const struct gic_kvm_info *info) +{ + int ret; + u32 vtr; + + if (!info->vctrl.start) { + kvm_err("GICH not present in the firmware table\n"); + return -ENXIO; + } + + if (!PAGE_ALIGNED(info->vcpu.start) || + !PAGE_ALIGNED(resource_size(&info->vcpu))) { + kvm_info("GICV region size/alignment is unsafe, using trapping (reduced performance)\n"); + + ret = create_hyp_io_mappings(info->vcpu.start, + resource_size(&info->vcpu), + &kvm_vgic_global_state.vcpu_base_va, + &kvm_vgic_global_state.vcpu_hyp_va); + if (ret) { + kvm_err("Cannot map GICV into hyp\n"); + goto out; + } + + static_branch_enable(&vgic_v2_cpuif_trap); + } + + ret = create_hyp_io_mappings(info->vctrl.start, + resource_size(&info->vctrl), + &kvm_vgic_global_state.vctrl_base, + &kvm_vgic_global_state.vctrl_hyp); + if (ret) { + kvm_err("Cannot map VCTRL into hyp\n"); + goto out; + } + + vtr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_VTR); + kvm_vgic_global_state.nr_lr = (vtr & 0x3f) + 1; + + ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2); + if (ret) { + kvm_err("Cannot register GICv2 KVM device\n"); + goto out; + } + + kvm_vgic_global_state.can_emulate_gicv2 = true; + kvm_vgic_global_state.vcpu_base = info->vcpu.start; + kvm_vgic_global_state.type = VGIC_V2; + kvm_vgic_global_state.max_gic_vcpus = VGIC_V2_MAX_CPUS; + + kvm_debug("vgic-v2@%llx\n", info->vctrl.start); + + return 0; +out: + if (kvm_vgic_global_state.vctrl_base) + iounmap(kvm_vgic_global_state.vctrl_base); + if (kvm_vgic_global_state.vcpu_base_va) + iounmap(kvm_vgic_global_state.vcpu_base_va); + + return ret; +} + +static void save_lrs(struct kvm_vcpu *vcpu, void __iomem *base) +{ + struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; + u64 used_lrs = cpu_if->used_lrs; + u64 elrsr; + int i; + + elrsr = readl_relaxed(base + GICH_ELRSR0); + if (unlikely(used_lrs > 32)) + elrsr |= ((u64)readl_relaxed(base + GICH_ELRSR1)) << 32; + + for (i = 0; i < used_lrs; i++) { + if (elrsr & (1UL << i)) + cpu_if->vgic_lr[i] &= ~GICH_LR_STATE; + else + cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4)); + + writel_relaxed(0, base + GICH_LR0 + (i * 4)); + } +} + +void vgic_v2_save_state(struct kvm_vcpu *vcpu) +{ + void __iomem *base = kvm_vgic_global_state.vctrl_base; + u64 used_lrs = vcpu->arch.vgic_cpu.vgic_v2.used_lrs; + + if (!base) + return; + + if (used_lrs) { + save_lrs(vcpu, base); + writel_relaxed(0, base + GICH_HCR); + } +} + +void vgic_v2_restore_state(struct kvm_vcpu *vcpu) +{ + struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; + void __iomem *base = kvm_vgic_global_state.vctrl_base; + u64 used_lrs = cpu_if->used_lrs; + int i; + + if (!base) + return; + + if (used_lrs) { + writel_relaxed(cpu_if->vgic_hcr, base + GICH_HCR); + for (i = 0; i < used_lrs; i++) { + writel_relaxed(cpu_if->vgic_lr[i], + base + GICH_LR0 + (i * 4)); + } + } +} + +void vgic_v2_load(struct kvm_vcpu *vcpu) +{ + struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; + + writel_relaxed(cpu_if->vgic_vmcr, + kvm_vgic_global_state.vctrl_base + GICH_VMCR); + writel_relaxed(cpu_if->vgic_apr, + kvm_vgic_global_state.vctrl_base + GICH_APR); +} + +void vgic_v2_vmcr_sync(struct kvm_vcpu *vcpu) +{ + struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; + + cpu_if->vgic_vmcr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_VMCR); +} + +void vgic_v2_put(struct kvm_vcpu *vcpu) +{ + struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; + + vgic_v2_vmcr_sync(vcpu); + cpu_if->vgic_apr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_APR); +} diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c new file mode 100644 index 000000000000..76e2d85789ed --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -0,0 +1,693 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/irqchip/arm-gic-v3.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <kvm/arm_vgic.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_asm.h> + +#include "vgic.h" + +static bool group0_trap; +static bool group1_trap; +static bool common_trap; +static bool gicv4_enable; + +void vgic_v3_set_underflow(struct kvm_vcpu *vcpu) +{ + struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3; + + cpuif->vgic_hcr |= ICH_HCR_UIE; +} + +static bool lr_signals_eoi_mi(u64 lr_val) +{ + return !(lr_val & ICH_LR_STATE) && (lr_val & ICH_LR_EOI) && + !(lr_val & ICH_LR_HW); +} + +void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3; + u32 model = vcpu->kvm->arch.vgic.vgic_model; + int lr; + + DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); + + cpuif->vgic_hcr &= ~ICH_HCR_UIE; + + for (lr = 0; lr < cpuif->used_lrs; lr++) { + u64 val = cpuif->vgic_lr[lr]; + u32 intid, cpuid; + struct vgic_irq *irq; + bool is_v2_sgi = false; + + cpuid = val & GICH_LR_PHYSID_CPUID; + cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT; + + if (model == KVM_DEV_TYPE_ARM_VGIC_V3) { + intid = val & ICH_LR_VIRTUAL_ID_MASK; + } else { + intid = val & GICH_LR_VIRTUALID; + is_v2_sgi = vgic_irq_is_sgi(intid); + } + + /* Notify fds when the guest EOI'ed a level-triggered IRQ */ + if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid)) + kvm_notify_acked_irq(vcpu->kvm, 0, + intid - VGIC_NR_PRIVATE_IRQS); + + irq = vgic_get_irq(vcpu->kvm, vcpu, intid); + if (!irq) /* An LPI could have been unmapped. */ + continue; + + raw_spin_lock(&irq->irq_lock); + + /* Always preserve the active bit */ + irq->active = !!(val & ICH_LR_ACTIVE_BIT); + + if (irq->active && is_v2_sgi) + irq->active_source = cpuid; + + /* Edge is the only case where we preserve the pending bit */ + if (irq->config == VGIC_CONFIG_EDGE && + (val & ICH_LR_PENDING_BIT)) { + irq->pending_latch = true; + + if (is_v2_sgi) + irq->source |= (1 << cpuid); + } + + /* + * Clear soft pending state when level irqs have been acked. + */ + if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE)) + irq->pending_latch = false; + + /* + * Level-triggered mapped IRQs are special because we only + * observe rising edges as input to the VGIC. + * + * If the guest never acked the interrupt we have to sample + * the physical line and set the line level, because the + * device state could have changed or we simply need to + * process the still pending interrupt later. + * + * If this causes us to lower the level, we have to also clear + * the physical active state, since we will otherwise never be + * told when the interrupt becomes asserted again. + */ + if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) { + irq->line_level = vgic_get_phys_line_level(irq); + + if (!irq->line_level) + vgic_irq_set_phys_active(irq, false); + } + + raw_spin_unlock(&irq->irq_lock); + vgic_put_irq(vcpu->kvm, irq); + } + + cpuif->used_lrs = 0; +} + +/* Requires the irq to be locked already */ +void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) +{ + u32 model = vcpu->kvm->arch.vgic.vgic_model; + u64 val = irq->intid; + bool allow_pending = true, is_v2_sgi; + + is_v2_sgi = (vgic_irq_is_sgi(irq->intid) && + model == KVM_DEV_TYPE_ARM_VGIC_V2); + + if (irq->active) { + val |= ICH_LR_ACTIVE_BIT; + if (is_v2_sgi) + val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT; + if (vgic_irq_is_multi_sgi(irq)) { + allow_pending = false; + val |= ICH_LR_EOI; + } + } + + if (irq->hw) { + val |= ICH_LR_HW; + val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT; + /* + * Never set pending+active on a HW interrupt, as the + * pending state is kept at the physical distributor + * level. + */ + if (irq->active) + allow_pending = false; + } else { + if (irq->config == VGIC_CONFIG_LEVEL) { + val |= ICH_LR_EOI; + + /* + * Software resampling doesn't work very well + * if we allow P+A, so let's not do that. + */ + if (irq->active) + allow_pending = false; + } + } + + if (allow_pending && irq_is_pending(irq)) { + val |= ICH_LR_PENDING_BIT; + + if (irq->config == VGIC_CONFIG_EDGE) + irq->pending_latch = false; + + if (vgic_irq_is_sgi(irq->intid) && + model == KVM_DEV_TYPE_ARM_VGIC_V2) { + u32 src = ffs(irq->source); + + if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n", + irq->intid)) + return; + + val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT; + irq->source &= ~(1 << (src - 1)); + if (irq->source) { + irq->pending_latch = true; + val |= ICH_LR_EOI; + } + } + } + + /* + * Level-triggered mapped IRQs are special because we only observe + * rising edges as input to the VGIC. We therefore lower the line + * level here, so that we can take new virtual IRQs. See + * vgic_v3_fold_lr_state for more info. + */ + if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) + irq->line_level = false; + + if (irq->group) + val |= ICH_LR_GROUP; + + val |= (u64)irq->priority << ICH_LR_PRIORITY_SHIFT; + + vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = val; +} + +void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr) +{ + vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = 0; +} + +void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) +{ + struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; + u32 model = vcpu->kvm->arch.vgic.vgic_model; + u32 vmcr; + + if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { + vmcr = (vmcrp->ackctl << ICH_VMCR_ACK_CTL_SHIFT) & + ICH_VMCR_ACK_CTL_MASK; + vmcr |= (vmcrp->fiqen << ICH_VMCR_FIQ_EN_SHIFT) & + ICH_VMCR_FIQ_EN_MASK; + } else { + /* + * When emulating GICv3 on GICv3 with SRE=1 on the + * VFIQEn bit is RES1 and the VAckCtl bit is RES0. + */ + vmcr = ICH_VMCR_FIQ_EN_MASK; + } + + vmcr |= (vmcrp->cbpr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK; + vmcr |= (vmcrp->eoim << ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK; + vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK; + vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK; + vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK; + vmcr |= (vmcrp->grpen0 << ICH_VMCR_ENG0_SHIFT) & ICH_VMCR_ENG0_MASK; + vmcr |= (vmcrp->grpen1 << ICH_VMCR_ENG1_SHIFT) & ICH_VMCR_ENG1_MASK; + + cpu_if->vgic_vmcr = vmcr; +} + +void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) +{ + struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; + u32 model = vcpu->kvm->arch.vgic.vgic_model; + u32 vmcr; + + vmcr = cpu_if->vgic_vmcr; + + if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { + vmcrp->ackctl = (vmcr & ICH_VMCR_ACK_CTL_MASK) >> + ICH_VMCR_ACK_CTL_SHIFT; + vmcrp->fiqen = (vmcr & ICH_VMCR_FIQ_EN_MASK) >> + ICH_VMCR_FIQ_EN_SHIFT; + } else { + /* + * When emulating GICv3 on GICv3 with SRE=1 on the + * VFIQEn bit is RES1 and the VAckCtl bit is RES0. + */ + vmcrp->fiqen = 1; + vmcrp->ackctl = 0; + } + + vmcrp->cbpr = (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT; + vmcrp->eoim = (vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT; + vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT; + vmcrp->bpr = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT; + vmcrp->pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT; + vmcrp->grpen0 = (vmcr & ICH_VMCR_ENG0_MASK) >> ICH_VMCR_ENG0_SHIFT; + vmcrp->grpen1 = (vmcr & ICH_VMCR_ENG1_MASK) >> ICH_VMCR_ENG1_SHIFT; +} + +#define INITIAL_PENDBASER_VALUE \ + (GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWb) | \ + GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, SameAsInner) | \ + GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable)) + +void vgic_v3_enable(struct kvm_vcpu *vcpu) +{ + struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3; + + /* + * By forcing VMCR to zero, the GIC will restore the binary + * points to their reset values. Anything else resets to zero + * anyway. + */ + vgic_v3->vgic_vmcr = 0; + + /* + * If we are emulating a GICv3, we do it in an non-GICv2-compatible + * way, so we force SRE to 1 to demonstrate this to the guest. + * Also, we don't support any form of IRQ/FIQ bypass. + * This goes with the spec allowing the value to be RAO/WI. + */ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB | + ICC_SRE_EL1_DFB | + ICC_SRE_EL1_SRE); + vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE; + } else { + vgic_v3->vgic_sre = 0; + } + + vcpu->arch.vgic_cpu.num_id_bits = (kvm_vgic_global_state.ich_vtr_el2 & + ICH_VTR_ID_BITS_MASK) >> + ICH_VTR_ID_BITS_SHIFT; + vcpu->arch.vgic_cpu.num_pri_bits = ((kvm_vgic_global_state.ich_vtr_el2 & + ICH_VTR_PRI_BITS_MASK) >> + ICH_VTR_PRI_BITS_SHIFT) + 1; + + /* Get the show on the road... */ + vgic_v3->vgic_hcr = ICH_HCR_EN; + if (group0_trap) + vgic_v3->vgic_hcr |= ICH_HCR_TALL0; + if (group1_trap) + vgic_v3->vgic_hcr |= ICH_HCR_TALL1; + if (common_trap) + vgic_v3->vgic_hcr |= ICH_HCR_TC; +} + +int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq) +{ + struct kvm_vcpu *vcpu; + int byte_offset, bit_nr; + gpa_t pendbase, ptr; + bool status; + u8 val; + int ret; + unsigned long flags; + +retry: + vcpu = irq->target_vcpu; + if (!vcpu) + return 0; + + pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); + + byte_offset = irq->intid / BITS_PER_BYTE; + bit_nr = irq->intid % BITS_PER_BYTE; + ptr = pendbase + byte_offset; + + ret = kvm_read_guest_lock(kvm, ptr, &val, 1); + if (ret) + return ret; + + status = val & (1 << bit_nr); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->target_vcpu != vcpu) { + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + goto retry; + } + irq->pending_latch = status; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + if (status) { + /* clear consumed data */ + val &= ~(1 << bit_nr); + ret = kvm_write_guest_lock(kvm, ptr, &val, 1); + if (ret) + return ret; + } + return 0; +} + +/** + * vgic_v3_save_pending_tables - Save the pending tables into guest RAM + * kvm lock and all vcpu lock must be held + */ +int vgic_v3_save_pending_tables(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_irq *irq; + gpa_t last_ptr = ~(gpa_t)0; + int ret; + u8 val; + + list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { + int byte_offset, bit_nr; + struct kvm_vcpu *vcpu; + gpa_t pendbase, ptr; + bool stored; + + vcpu = irq->target_vcpu; + if (!vcpu) + continue; + + pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); + + byte_offset = irq->intid / BITS_PER_BYTE; + bit_nr = irq->intid % BITS_PER_BYTE; + ptr = pendbase + byte_offset; + + if (ptr != last_ptr) { + ret = kvm_read_guest_lock(kvm, ptr, &val, 1); + if (ret) + return ret; + last_ptr = ptr; + } + + stored = val & (1U << bit_nr); + if (stored == irq->pending_latch) + continue; + + if (irq->pending_latch) + val |= 1 << bit_nr; + else + val &= ~(1 << bit_nr); + + ret = kvm_write_guest_lock(kvm, ptr, &val, 1); + if (ret) + return ret; + } + return 0; +} + +/** + * vgic_v3_rdist_overlap - check if a region overlaps with any + * existing redistributor region + * + * @kvm: kvm handle + * @base: base of the region + * @size: size of region + * + * Return: true if there is an overlap + */ +bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size) +{ + struct vgic_dist *d = &kvm->arch.vgic; + struct vgic_redist_region *rdreg; + + list_for_each_entry(rdreg, &d->rd_regions, list) { + if ((base + size > rdreg->base) && + (base < rdreg->base + vgic_v3_rd_region_size(kvm, rdreg))) + return true; + } + return false; +} + +/* + * Check for overlapping regions and for regions crossing the end of memory + * for base addresses which have already been set. + */ +bool vgic_v3_check_base(struct kvm *kvm) +{ + struct vgic_dist *d = &kvm->arch.vgic; + struct vgic_redist_region *rdreg; + + if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && + d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base) + return false; + + list_for_each_entry(rdreg, &d->rd_regions, list) { + if (rdreg->base + vgic_v3_rd_region_size(kvm, rdreg) < + rdreg->base) + return false; + } + + if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base)) + return true; + + return !vgic_v3_rdist_overlap(kvm, d->vgic_dist_base, + KVM_VGIC_V3_DIST_SIZE); +} + +/** + * vgic_v3_rdist_free_slot - Look up registered rdist regions and identify one + * which has free space to put a new rdist region. + * + * @rd_regions: redistributor region list head + * + * A redistributor regions maps n redistributors, n = region size / (2 x 64kB). + * Stride between redistributors is 0 and regions are filled in the index order. + * + * Return: the redist region handle, if any, that has space to map a new rdist + * region. + */ +struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions) +{ + struct vgic_redist_region *rdreg; + + list_for_each_entry(rdreg, rd_regions, list) { + if (!vgic_v3_redist_region_full(rdreg)) + return rdreg; + } + return NULL; +} + +struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, + u32 index) +{ + struct list_head *rd_regions = &kvm->arch.vgic.rd_regions; + struct vgic_redist_region *rdreg; + + list_for_each_entry(rdreg, rd_regions, list) { + if (rdreg->index == index) + return rdreg; + } + return NULL; +} + + +int vgic_v3_map_resources(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int ret = 0; + int c; + + if (vgic_ready(kvm)) + goto out; + + kvm_for_each_vcpu(c, vcpu, kvm) { + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + + if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { + kvm_debug("vcpu %d redistributor base not set\n", c); + ret = -ENXIO; + goto out; + } + } + + if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) { + kvm_err("Need to set vgic distributor addresses first\n"); + ret = -ENXIO; + goto out; + } + + if (!vgic_v3_check_base(kvm)) { + kvm_err("VGIC redist and dist frames overlap\n"); + ret = -EINVAL; + goto out; + } + + /* + * For a VGICv3 we require the userland to explicitly initialize + * the VGIC before we need to use it. + */ + if (!vgic_initialized(kvm)) { + ret = -EBUSY; + goto out; + } + + ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V3); + if (ret) { + kvm_err("Unable to register VGICv3 dist MMIO regions\n"); + goto out; + } + + if (kvm_vgic_global_state.has_gicv4_1) + vgic_v4_configure_vsgis(kvm); + dist->ready = true; + +out: + return ret; +} + +DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap); + +static int __init early_group0_trap_cfg(char *buf) +{ + return strtobool(buf, &group0_trap); +} +early_param("kvm-arm.vgic_v3_group0_trap", early_group0_trap_cfg); + +static int __init early_group1_trap_cfg(char *buf) +{ + return strtobool(buf, &group1_trap); +} +early_param("kvm-arm.vgic_v3_group1_trap", early_group1_trap_cfg); + +static int __init early_common_trap_cfg(char *buf) +{ + return strtobool(buf, &common_trap); +} +early_param("kvm-arm.vgic_v3_common_trap", early_common_trap_cfg); + +static int __init early_gicv4_enable(char *buf) +{ + return strtobool(buf, &gicv4_enable); +} +early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); + +/** + * vgic_v3_probe - probe for a VGICv3 compatible interrupt controller + * @info: pointer to the GIC description + * + * Returns 0 if the VGICv3 has been probed successfully, returns an error code + * otherwise + */ +int vgic_v3_probe(const struct gic_kvm_info *info) +{ + u32 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_ich_vtr_el2); + int ret; + + /* + * The ListRegs field is 5 bits, but there is an architectural + * maximum of 16 list registers. Just ignore bit 4... + */ + kvm_vgic_global_state.nr_lr = (ich_vtr_el2 & 0xf) + 1; + kvm_vgic_global_state.can_emulate_gicv2 = false; + kvm_vgic_global_state.ich_vtr_el2 = ich_vtr_el2; + + /* GICv4 support? */ + if (info->has_v4) { + kvm_vgic_global_state.has_gicv4 = gicv4_enable; + kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable; + kvm_info("GICv4%s support %sabled\n", + kvm_vgic_global_state.has_gicv4_1 ? ".1" : "", + gicv4_enable ? "en" : "dis"); + } + + if (!info->vcpu.start) { + kvm_info("GICv3: no GICV resource entry\n"); + kvm_vgic_global_state.vcpu_base = 0; + } else if (!PAGE_ALIGNED(info->vcpu.start)) { + pr_warn("GICV physical address 0x%llx not page aligned\n", + (unsigned long long)info->vcpu.start); + kvm_vgic_global_state.vcpu_base = 0; + } else { + kvm_vgic_global_state.vcpu_base = info->vcpu.start; + kvm_vgic_global_state.can_emulate_gicv2 = true; + ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2); + if (ret) { + kvm_err("Cannot register GICv2 KVM device.\n"); + return ret; + } + kvm_info("vgic-v2@%llx\n", info->vcpu.start); + } + ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V3); + if (ret) { + kvm_err("Cannot register GICv3 KVM device.\n"); + kvm_unregister_device_ops(KVM_DEV_TYPE_ARM_VGIC_V2); + return ret; + } + + if (kvm_vgic_global_state.vcpu_base == 0) + kvm_info("disabling GICv2 emulation\n"); + + if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_30115)) { + group0_trap = true; + group1_trap = true; + } + + if (group0_trap || group1_trap || common_trap) { + kvm_info("GICv3 sysreg trapping enabled ([%s%s%s], reduced performance)\n", + group0_trap ? "G0" : "", + group1_trap ? "G1" : "", + common_trap ? "C" : ""); + static_branch_enable(&vgic_v3_cpuif_trap); + } + + kvm_vgic_global_state.vctrl_base = NULL; + kvm_vgic_global_state.type = VGIC_V3; + kvm_vgic_global_state.max_gic_vcpus = VGIC_V3_MAX_CPUS; + + return 0; +} + +void vgic_v3_load(struct kvm_vcpu *vcpu) +{ + struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; + + /* + * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen + * is dependent on ICC_SRE_EL1.SRE, and we have to perform the + * VMCR_EL2 save/restore in the world switch. + */ + if (likely(cpu_if->vgic_sre)) + kvm_call_hyp(__vgic_v3_write_vmcr, cpu_if->vgic_vmcr); + + kvm_call_hyp(__vgic_v3_restore_aprs, kern_hyp_va(cpu_if)); + + if (has_vhe()) + __vgic_v3_activate_traps(cpu_if); + + WARN_ON(vgic_v4_load(vcpu)); +} + +void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu) +{ + struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; + + if (likely(cpu_if->vgic_sre)) + cpu_if->vgic_vmcr = kvm_call_hyp_ret(__vgic_v3_read_vmcr); +} + +void vgic_v3_put(struct kvm_vcpu *vcpu) +{ + struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; + + WARN_ON(vgic_v4_put(vcpu, false)); + + vgic_v3_vmcr_sync(vcpu); + + kvm_call_hyp(__vgic_v3_save_aprs, kern_hyp_va(cpu_if)); + + if (has_vhe()) + __vgic_v3_deactivate_traps(cpu_if); +} diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c new file mode 100644 index 000000000000..27ac833e5ec7 --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -0,0 +1,453 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2017 ARM Ltd. + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/kvm_host.h> +#include <linux/irqchip/arm-gic-v3.h> + +#include "vgic.h" + +/* + * How KVM uses GICv4 (insert rude comments here): + * + * The vgic-v4 layer acts as a bridge between several entities: + * - The GICv4 ITS representation offered by the ITS driver + * - VFIO, which is in charge of the PCI endpoint + * - The virtual ITS, which is the only thing the guest sees + * + * The configuration of VLPIs is triggered by a callback from VFIO, + * instructing KVM that a PCI device has been configured to deliver + * MSIs to a vITS. + * + * kvm_vgic_v4_set_forwarding() is thus called with the routing entry, + * and this is used to find the corresponding vITS data structures + * (ITS instance, device, event and irq) using a process that is + * extremely similar to the injection of an MSI. + * + * At this stage, we can link the guest's view of an LPI (uniquely + * identified by the routing entry) and the host irq, using the GICv4 + * driver mapping operation. Should the mapping succeed, we've then + * successfully upgraded the guest's LPI to a VLPI. We can then start + * with updating GICv4's view of the property table and generating an + * INValidation in order to kickstart the delivery of this VLPI to the + * guest directly, without software intervention. Well, almost. + * + * When the PCI endpoint is deconfigured, this operation is reversed + * with VFIO calling kvm_vgic_v4_unset_forwarding(). + * + * Once the VLPI has been mapped, it needs to follow any change the + * guest performs on its LPI through the vITS. For that, a number of + * command handlers have hooks to communicate these changes to the HW: + * - Any invalidation triggers a call to its_prop_update_vlpi() + * - The INT command results in a irq_set_irqchip_state(), which + * generates an INT on the corresponding VLPI. + * - The CLEAR command results in a irq_set_irqchip_state(), which + * generates an CLEAR on the corresponding VLPI. + * - DISCARD translates into an unmap, similar to a call to + * kvm_vgic_v4_unset_forwarding(). + * - MOVI is translated by an update of the existing mapping, changing + * the target vcpu, resulting in a VMOVI being generated. + * - MOVALL is translated by a string of mapping updates (similar to + * the handling of MOVI). MOVALL is horrible. + * + * Note that a DISCARD/MAPTI sequence emitted from the guest without + * reprogramming the PCI endpoint after MAPTI does not result in a + * VLPI being mapped, as there is no callback from VFIO (the guest + * will get the interrupt via the normal SW injection). Fixing this is + * not trivial, and requires some horrible messing with the VFIO + * internals. Not fun. Don't do that. + * + * Then there is the scheduling. Each time a vcpu is about to run on a + * physical CPU, KVM must tell the corresponding redistributor about + * it. And if we've migrated our vcpu from one CPU to another, we must + * tell the ITS (so that the messages reach the right redistributor). + * This is done in two steps: first issue a irq_set_affinity() on the + * irq corresponding to the vcpu, then call its_make_vpe_resident(). + * You must be in a non-preemptible context. On exit, a call to + * its_make_vpe_non_resident() tells the redistributor that we're done + * with the vcpu. + * + * Finally, the doorbell handling: Each vcpu is allocated an interrupt + * which will fire each time a VLPI is made pending whilst the vcpu is + * not running. Each time the vcpu gets blocked, the doorbell + * interrupt gets enabled. When the vcpu is unblocked (for whatever + * reason), the doorbell interrupt is disabled. + */ + +#define DB_IRQ_FLAGS (IRQ_NOAUTOEN | IRQ_DISABLE_UNLAZY | IRQ_NO_BALANCING) + +static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info) +{ + struct kvm_vcpu *vcpu = info; + + /* We got the message, no need to fire again */ + if (!kvm_vgic_global_state.has_gicv4_1 && + !irqd_irq_disabled(&irq_to_desc(irq)->irq_data)) + disable_irq_nosync(irq); + + vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true; + kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); + kvm_vcpu_kick(vcpu); + + return IRQ_HANDLED; +} + +static void vgic_v4_sync_sgi_config(struct its_vpe *vpe, struct vgic_irq *irq) +{ + vpe->sgi_config[irq->intid].enabled = irq->enabled; + vpe->sgi_config[irq->intid].group = irq->group; + vpe->sgi_config[irq->intid].priority = irq->priority; +} + +static void vgic_v4_enable_vsgis(struct kvm_vcpu *vcpu) +{ + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + int i; + + /* + * With GICv4.1, every virtual SGI can be directly injected. So + * let's pretend that they are HW interrupts, tied to a host + * IRQ. The SGI code will do its magic. + */ + for (i = 0; i < VGIC_NR_SGIS; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, i); + struct irq_desc *desc; + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (irq->hw) + goto unlock; + + irq->hw = true; + irq->host_irq = irq_find_mapping(vpe->sgi_domain, i); + + /* Transfer the full irq state to the vPE */ + vgic_v4_sync_sgi_config(vpe, irq); + desc = irq_to_desc(irq->host_irq); + ret = irq_domain_activate_irq(irq_desc_get_irq_data(desc), + false); + if (!WARN_ON(ret)) { + /* Transfer pending state */ + ret = irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + irq->pending_latch); + WARN_ON(ret); + irq->pending_latch = false; + } + unlock: + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +static void vgic_v4_disable_vsgis(struct kvm_vcpu *vcpu) +{ + int i; + + for (i = 0; i < VGIC_NR_SGIS; i++) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, i); + struct irq_desc *desc; + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (!irq->hw) + goto unlock; + + irq->hw = false; + ret = irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &irq->pending_latch); + WARN_ON(ret); + + desc = irq_to_desc(irq->host_irq); + irq_domain_deactivate_irq(irq_desc_get_irq_data(desc)); + unlock: + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + } +} + +/* Must be called with the kvm lock held */ +void vgic_v4_configure_vsgis(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int i; + + kvm_arm_halt_guest(kvm); + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (dist->nassgireq) + vgic_v4_enable_vsgis(vcpu); + else + vgic_v4_disable_vsgis(vcpu); + } + + kvm_arm_resume_guest(kvm); +} + +/** + * vgic_v4_init - Initialize the GICv4 data structures + * @kvm: Pointer to the VM being initialized + * + * We may be called each time a vITS is created, or when the + * vgic is initialized. This relies on kvm->lock to be + * held. In both cases, the number of vcpus should now be + * fixed. + */ +int vgic_v4_init(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int i, nr_vcpus, ret; + + if (!kvm_vgic_global_state.has_gicv4) + return 0; /* Nothing to see here... move along. */ + + if (dist->its_vm.vpes) + return 0; + + nr_vcpus = atomic_read(&kvm->online_vcpus); + + dist->its_vm.vpes = kcalloc(nr_vcpus, sizeof(*dist->its_vm.vpes), + GFP_KERNEL); + if (!dist->its_vm.vpes) + return -ENOMEM; + + dist->its_vm.nr_vpes = nr_vcpus; + + kvm_for_each_vcpu(i, vcpu, kvm) + dist->its_vm.vpes[i] = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + + ret = its_alloc_vcpu_irqs(&dist->its_vm); + if (ret < 0) { + kvm_err("VPE IRQ allocation failure\n"); + kfree(dist->its_vm.vpes); + dist->its_vm.nr_vpes = 0; + dist->its_vm.vpes = NULL; + return ret; + } + + kvm_for_each_vcpu(i, vcpu, kvm) { + int irq = dist->its_vm.vpes[i]->irq; + unsigned long irq_flags = DB_IRQ_FLAGS; + + /* + * Don't automatically enable the doorbell, as we're + * flipping it back and forth when the vcpu gets + * blocked. Also disable the lazy disabling, as the + * doorbell could kick us out of the guest too + * early... + * + * On GICv4.1, the doorbell is managed in HW and must + * be left enabled. + */ + if (kvm_vgic_global_state.has_gicv4_1) + irq_flags &= ~IRQ_NOAUTOEN; + irq_set_status_flags(irq, irq_flags); + + ret = request_irq(irq, vgic_v4_doorbell_handler, + 0, "vcpu", vcpu); + if (ret) { + kvm_err("failed to allocate vcpu IRQ%d\n", irq); + /* + * Trick: adjust the number of vpes so we know + * how many to nuke on teardown... + */ + dist->its_vm.nr_vpes = i; + break; + } + } + + if (ret) + vgic_v4_teardown(kvm); + + return ret; +} + +/** + * vgic_v4_teardown - Free the GICv4 data structures + * @kvm: Pointer to the VM being destroyed + * + * Relies on kvm->lock to be held. + */ +void vgic_v4_teardown(struct kvm *kvm) +{ + struct its_vm *its_vm = &kvm->arch.vgic.its_vm; + int i; + + if (!its_vm->vpes) + return; + + for (i = 0; i < its_vm->nr_vpes; i++) { + struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, i); + int irq = its_vm->vpes[i]->irq; + + irq_clear_status_flags(irq, DB_IRQ_FLAGS); + free_irq(irq, vcpu); + } + + its_free_vcpu_irqs(its_vm); + kfree(its_vm->vpes); + its_vm->nr_vpes = 0; + its_vm->vpes = NULL; +} + +int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db) +{ + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + + if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident) + return 0; + + return its_make_vpe_non_resident(vpe, need_db); +} + +int vgic_v4_load(struct kvm_vcpu *vcpu) +{ + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + int err; + + if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident) + return 0; + + /* + * Before making the VPE resident, make sure the redistributor + * corresponding to our current CPU expects us here. See the + * doc in drivers/irqchip/irq-gic-v4.c to understand how this + * turns into a VMOVP command at the ITS level. + */ + err = irq_set_affinity(vpe->irq, cpumask_of(smp_processor_id())); + if (err) + return err; + + err = its_make_vpe_resident(vpe, false, vcpu->kvm->arch.vgic.enabled); + if (err) + return err; + + /* + * Now that the VPE is resident, let's get rid of a potential + * doorbell interrupt that would still be pending. This is a + * GICv4.0 only "feature"... + */ + if (!kvm_vgic_global_state.has_gicv4_1) + err = irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false); + + return err; +} + +static struct vgic_its *vgic_get_its(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *irq_entry) +{ + struct kvm_msi msi = (struct kvm_msi) { + .address_lo = irq_entry->msi.address_lo, + .address_hi = irq_entry->msi.address_hi, + .data = irq_entry->msi.data, + .flags = irq_entry->msi.flags, + .devid = irq_entry->msi.devid, + }; + + return vgic_msi_to_its(kvm, &msi); +} + +int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, + struct kvm_kernel_irq_routing_entry *irq_entry) +{ + struct vgic_its *its; + struct vgic_irq *irq; + struct its_vlpi_map map; + int ret; + + if (!vgic_supports_direct_msis(kvm)) + return 0; + + /* + * Get the ITS, and escape early on error (not a valid + * doorbell for any of our vITSs). + */ + its = vgic_get_its(kvm, irq_entry); + if (IS_ERR(its)) + return 0; + + mutex_lock(&its->its_lock); + + /* Perform the actual DevID/EventID -> LPI translation. */ + ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, + irq_entry->msi.data, &irq); + if (ret) + goto out; + + /* + * Emit the mapping request. If it fails, the ITS probably + * isn't v4 compatible, so let's silently bail out. Holding + * the ITS lock should ensure that nothing can modify the + * target vcpu. + */ + map = (struct its_vlpi_map) { + .vm = &kvm->arch.vgic.its_vm, + .vpe = &irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe, + .vintid = irq->intid, + .properties = ((irq->priority & 0xfc) | + (irq->enabled ? LPI_PROP_ENABLED : 0) | + LPI_PROP_GROUP1), + .db_enabled = true, + }; + + ret = its_map_vlpi(virq, &map); + if (ret) + goto out; + + irq->hw = true; + irq->host_irq = virq; + atomic_inc(&map.vpe->vlpi_count); + +out: + mutex_unlock(&its->its_lock); + return ret; +} + +int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq, + struct kvm_kernel_irq_routing_entry *irq_entry) +{ + struct vgic_its *its; + struct vgic_irq *irq; + int ret; + + if (!vgic_supports_direct_msis(kvm)) + return 0; + + /* + * Get the ITS, and escape early on error (not a valid + * doorbell for any of our vITSs). + */ + its = vgic_get_its(kvm, irq_entry); + if (IS_ERR(its)) + return 0; + + mutex_lock(&its->its_lock); + + ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, + irq_entry->msi.data, &irq); + if (ret) + goto out; + + WARN_ON(!(irq->hw && irq->host_irq == virq)); + if (irq->hw) { + atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count); + irq->hw = false; + ret = its_unmap_vlpi(virq); + } + +out: + mutex_unlock(&its->its_lock); + return ret; +} diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c new file mode 100644 index 000000000000..c3643b7f101b --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic.c @@ -0,0 +1,1020 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015, 2016 ARM Ltd. + */ + +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/list_sort.h> +#include <linux/nospec.h> + +#include <asm/kvm_hyp.h> + +#include "vgic.h" + +#define CREATE_TRACE_POINTS +#include "trace.h" + +struct vgic_global kvm_vgic_global_state __ro_after_init = { + .gicv3_cpuif = STATIC_KEY_FALSE_INIT, +}; + +/* + * Locking order is always: + * kvm->lock (mutex) + * its->cmd_lock (mutex) + * its->its_lock (mutex) + * vgic_cpu->ap_list_lock must be taken with IRQs disabled + * kvm->lpi_list_lock must be taken with IRQs disabled + * vgic_irq->irq_lock must be taken with IRQs disabled + * + * As the ap_list_lock might be taken from the timer interrupt handler, + * we have to disable IRQs before taking this lock and everything lower + * than it. + * + * If you need to take multiple locks, always take the upper lock first, + * then the lower ones, e.g. first take the its_lock, then the irq_lock. + * If you are already holding a lock and need to take a higher one, you + * have to drop the lower ranking lock first and re-aquire it after having + * taken the upper one. + * + * When taking more than one ap_list_lock at the same time, always take the + * lowest numbered VCPU's ap_list_lock first, so: + * vcpuX->vcpu_id < vcpuY->vcpu_id: + * raw_spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock); + * raw_spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock); + * + * Since the VGIC must support injecting virtual interrupts from ISRs, we have + * to use the raw_spin_lock_irqsave/raw_spin_unlock_irqrestore versions of outer + * spinlocks for any lock that may be taken while injecting an interrupt. + */ + +/* + * Iterate over the VM's list of mapped LPIs to find the one with a + * matching interrupt ID and return a reference to the IRQ structure. + */ +static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_irq *irq = NULL; + unsigned long flags; + + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); + + list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { + if (irq->intid != intid) + continue; + + /* + * This increases the refcount, the caller is expected to + * call vgic_put_irq() later once it's finished with the IRQ. + */ + vgic_get_irq_kref(irq); + goto out_unlock; + } + irq = NULL; + +out_unlock: + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + + return irq; +} + +/* + * This looks up the virtual interrupt ID to get the corresponding + * struct vgic_irq. It also increases the refcount, so any caller is expected + * to call vgic_put_irq() once it's finished with this IRQ. + */ +struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, + u32 intid) +{ + /* SGIs and PPIs */ + if (intid <= VGIC_MAX_PRIVATE) { + intid = array_index_nospec(intid, VGIC_MAX_PRIVATE + 1); + return &vcpu->arch.vgic_cpu.private_irqs[intid]; + } + + /* SPIs */ + if (intid < (kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) { + intid = array_index_nospec(intid, kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS); + return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS]; + } + + /* LPIs */ + if (intid >= VGIC_MIN_LPI) + return vgic_get_lpi(kvm, intid); + + WARN(1, "Looking up struct vgic_irq for reserved INTID"); + return NULL; +} + +/* + * We can't do anything in here, because we lack the kvm pointer to + * lock and remove the item from the lpi_list. So we keep this function + * empty and use the return value of kref_put() to trigger the freeing. + */ +static void vgic_irq_release(struct kref *ref) +{ +} + +/* + * Drop the refcount on the LPI. Must be called with lpi_list_lock held. + */ +void __vgic_put_lpi_locked(struct kvm *kvm, struct vgic_irq *irq) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + + if (!kref_put(&irq->refcount, vgic_irq_release)) + return; + + list_del(&irq->lpi_list); + dist->lpi_list_count--; + + kfree(irq); +} + +void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long flags; + + if (irq->intid < VGIC_MIN_LPI) + return; + + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); + __vgic_put_lpi_locked(kvm, irq); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); +} + +void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_irq *irq, *tmp; + unsigned long flags; + + raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); + + list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { + if (irq->intid >= VGIC_MIN_LPI) { + raw_spin_lock(&irq->irq_lock); + list_del(&irq->ap_list); + irq->vcpu = NULL; + raw_spin_unlock(&irq->irq_lock); + vgic_put_irq(vcpu->kvm, irq); + } + } + + raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); +} + +void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending) +{ + WARN_ON(irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + pending)); +} + +bool vgic_get_phys_line_level(struct vgic_irq *irq) +{ + bool line_level; + + BUG_ON(!irq->hw); + + if (irq->get_input_level) + return irq->get_input_level(irq->intid); + + WARN_ON(irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &line_level)); + return line_level; +} + +/* Set/Clear the physical active state */ +void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active) +{ + + BUG_ON(!irq->hw); + WARN_ON(irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_ACTIVE, + active)); +} + +/** + * kvm_vgic_target_oracle - compute the target vcpu for an irq + * + * @irq: The irq to route. Must be already locked. + * + * Based on the current state of the interrupt (enabled, pending, + * active, vcpu and target_vcpu), compute the next vcpu this should be + * given to. Return NULL if this shouldn't be injected at all. + * + * Requires the IRQ lock to be held. + */ +static struct kvm_vcpu *vgic_target_oracle(struct vgic_irq *irq) +{ + lockdep_assert_held(&irq->irq_lock); + + /* If the interrupt is active, it must stay on the current vcpu */ + if (irq->active) + return irq->vcpu ? : irq->target_vcpu; + + /* + * If the IRQ is not active but enabled and pending, we should direct + * it to its configured target VCPU. + * If the distributor is disabled, pending interrupts shouldn't be + * forwarded. + */ + if (irq->enabled && irq_is_pending(irq)) { + if (unlikely(irq->target_vcpu && + !irq->target_vcpu->kvm->arch.vgic.enabled)) + return NULL; + + return irq->target_vcpu; + } + + /* If neither active nor pending and enabled, then this IRQ should not + * be queued to any VCPU. + */ + return NULL; +} + +/* + * The order of items in the ap_lists defines how we'll pack things in LRs as + * well, the first items in the list being the first things populated in the + * LRs. + * + * A hard rule is that active interrupts can never be pushed out of the LRs + * (and therefore take priority) since we cannot reliably trap on deactivation + * of IRQs and therefore they have to be present in the LRs. + * + * Otherwise things should be sorted by the priority field and the GIC + * hardware support will take care of preemption of priority groups etc. + * + * Return negative if "a" sorts before "b", 0 to preserve order, and positive + * to sort "b" before "a". + */ +static int vgic_irq_cmp(void *priv, struct list_head *a, struct list_head *b) +{ + struct vgic_irq *irqa = container_of(a, struct vgic_irq, ap_list); + struct vgic_irq *irqb = container_of(b, struct vgic_irq, ap_list); + bool penda, pendb; + int ret; + + /* + * list_sort may call this function with the same element when + * the list is fairly long. + */ + if (unlikely(irqa == irqb)) + return 0; + + raw_spin_lock(&irqa->irq_lock); + raw_spin_lock_nested(&irqb->irq_lock, SINGLE_DEPTH_NESTING); + + if (irqa->active || irqb->active) { + ret = (int)irqb->active - (int)irqa->active; + goto out; + } + + penda = irqa->enabled && irq_is_pending(irqa); + pendb = irqb->enabled && irq_is_pending(irqb); + + if (!penda || !pendb) { + ret = (int)pendb - (int)penda; + goto out; + } + + /* Both pending and enabled, sort by priority */ + ret = irqa->priority - irqb->priority; +out: + raw_spin_unlock(&irqb->irq_lock); + raw_spin_unlock(&irqa->irq_lock); + return ret; +} + +/* Must be called with the ap_list_lock held */ +static void vgic_sort_ap_list(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + + lockdep_assert_held(&vgic_cpu->ap_list_lock); + + list_sort(NULL, &vgic_cpu->ap_list_head, vgic_irq_cmp); +} + +/* + * Only valid injection if changing level for level-triggered IRQs or for a + * rising edge, and in-kernel connected IRQ lines can only be controlled by + * their owner. + */ +static bool vgic_validate_injection(struct vgic_irq *irq, bool level, void *owner) +{ + if (irq->owner != owner) + return false; + + switch (irq->config) { + case VGIC_CONFIG_LEVEL: + return irq->line_level != level; + case VGIC_CONFIG_EDGE: + return level; + } + + return false; +} + +/* + * Check whether an IRQ needs to (and can) be queued to a VCPU's ap list. + * Do the queuing if necessary, taking the right locks in the right order. + * Returns true when the IRQ was queued, false otherwise. + * + * Needs to be entered with the IRQ lock already held, but will return + * with all locks dropped. + */ +bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, + unsigned long flags) +{ + struct kvm_vcpu *vcpu; + + lockdep_assert_held(&irq->irq_lock); + +retry: + vcpu = vgic_target_oracle(irq); + if (irq->vcpu || !vcpu) { + /* + * If this IRQ is already on a VCPU's ap_list, then it + * cannot be moved or modified and there is no more work for + * us to do. + * + * Otherwise, if the irq is not pending and enabled, it does + * not need to be inserted into an ap_list and there is also + * no more work for us to do. + */ + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + /* + * We have to kick the VCPU here, because we could be + * queueing an edge-triggered interrupt for which we + * get no EOI maintenance interrupt. In that case, + * while the IRQ is already on the VCPU's AP list, the + * VCPU could have EOI'ed the original interrupt and + * won't see this one until it exits for some other + * reason. + */ + if (vcpu) { + kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); + kvm_vcpu_kick(vcpu); + } + return false; + } + + /* + * We must unlock the irq lock to take the ap_list_lock where + * we are going to insert this new pending interrupt. + */ + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + /* someone can do stuff here, which we re-check below */ + + raw_spin_lock_irqsave(&vcpu->arch.vgic_cpu.ap_list_lock, flags); + raw_spin_lock(&irq->irq_lock); + + /* + * Did something change behind our backs? + * + * There are two cases: + * 1) The irq lost its pending state or was disabled behind our + * backs and/or it was queued to another VCPU's ap_list. + * 2) Someone changed the affinity on this irq behind our + * backs and we are now holding the wrong ap_list_lock. + * + * In both cases, drop the locks and retry. + */ + + if (unlikely(irq->vcpu || vcpu != vgic_target_oracle(irq))) { + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, + flags); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + goto retry; + } + + /* + * Grab a reference to the irq to reflect the fact that it is + * now in the ap_list. + */ + vgic_get_irq_kref(irq); + list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head); + irq->vcpu = vcpu; + + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags); + + kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); + kvm_vcpu_kick(vcpu); + + return true; +} + +/** + * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic + * @kvm: The VM structure pointer + * @cpuid: The CPU for PPIs + * @intid: The INTID to inject a new state to. + * @level: Edge-triggered: true: to trigger the interrupt + * false: to ignore the call + * Level-sensitive true: raise the input signal + * false: lower the input signal + * @owner: The opaque pointer to the owner of the IRQ being raised to verify + * that the caller is allowed to inject this IRQ. Userspace + * injections will have owner == NULL. + * + * The VGIC is not concerned with devices being active-LOW or active-HIGH for + * level-sensitive interrupts. You can think of the level parameter as 1 + * being HIGH and 0 being LOW and all devices being active-HIGH. + */ +int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid, + bool level, void *owner) +{ + struct kvm_vcpu *vcpu; + struct vgic_irq *irq; + unsigned long flags; + int ret; + + trace_vgic_update_irq_pending(cpuid, intid, level); + + ret = vgic_lazy_init(kvm); + if (ret) + return ret; + + vcpu = kvm_get_vcpu(kvm, cpuid); + if (!vcpu && intid < VGIC_NR_PRIVATE_IRQS) + return -EINVAL; + + irq = vgic_get_irq(kvm, vcpu, intid); + if (!irq) + return -EINVAL; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + + if (!vgic_validate_injection(irq, level, owner)) { + /* Nothing to see here, move along... */ + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(kvm, irq); + return 0; + } + + if (irq->config == VGIC_CONFIG_LEVEL) + irq->line_level = level; + else + irq->pending_latch = true; + + vgic_queue_irq_unlock(kvm, irq, flags); + vgic_put_irq(kvm, irq); + + return 0; +} + +/* @irq->irq_lock must be held */ +static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq, + unsigned int host_irq, + bool (*get_input_level)(int vindid)) +{ + struct irq_desc *desc; + struct irq_data *data; + + /* + * Find the physical IRQ number corresponding to @host_irq + */ + desc = irq_to_desc(host_irq); + if (!desc) { + kvm_err("%s: no interrupt descriptor\n", __func__); + return -EINVAL; + } + data = irq_desc_get_irq_data(desc); + while (data->parent_data) + data = data->parent_data; + + irq->hw = true; + irq->host_irq = host_irq; + irq->hwintid = data->hwirq; + irq->get_input_level = get_input_level; + return 0; +} + +/* @irq->irq_lock must be held */ +static inline void kvm_vgic_unmap_irq(struct vgic_irq *irq) +{ + irq->hw = false; + irq->hwintid = 0; + irq->get_input_level = NULL; +} + +int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, + u32 vintid, bool (*get_input_level)(int vindid)) +{ + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); + unsigned long flags; + int ret; + + BUG_ON(!irq); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + ret = kvm_vgic_map_irq(vcpu, irq, host_irq, get_input_level); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + return ret; +} + +/** + * kvm_vgic_reset_mapped_irq - Reset a mapped IRQ + * @vcpu: The VCPU pointer + * @vintid: The INTID of the interrupt + * + * Reset the active and pending states of a mapped interrupt. Kernel + * subsystems injecting mapped interrupts should reset their interrupt lines + * when we are doing a reset of the VM. + */ +void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid) +{ + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); + unsigned long flags; + + if (!irq->hw) + goto out; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->active = false; + irq->pending_latch = false; + irq->line_level = false; + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); +out: + vgic_put_irq(vcpu->kvm, irq); +} + +int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid) +{ + struct vgic_irq *irq; + unsigned long flags; + + if (!vgic_initialized(vcpu->kvm)) + return -EAGAIN; + + irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); + BUG_ON(!irq); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + kvm_vgic_unmap_irq(irq); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + return 0; +} + +/** + * kvm_vgic_set_owner - Set the owner of an interrupt for a VM + * + * @vcpu: Pointer to the VCPU (used for PPIs) + * @intid: The virtual INTID identifying the interrupt (PPI or SPI) + * @owner: Opaque pointer to the owner + * + * Returns 0 if intid is not already used by another in-kernel device and the + * owner is set, otherwise returns an error code. + */ +int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner) +{ + struct vgic_irq *irq; + unsigned long flags; + int ret = 0; + + if (!vgic_initialized(vcpu->kvm)) + return -EAGAIN; + + /* SGIs and LPIs cannot be wired up to any device */ + if (!irq_is_ppi(intid) && !vgic_valid_spi(vcpu->kvm, intid)) + return -EINVAL; + + irq = vgic_get_irq(vcpu->kvm, vcpu, intid); + raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->owner && irq->owner != owner) + ret = -EEXIST; + else + irq->owner = owner; + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + return ret; +} + +/** + * vgic_prune_ap_list - Remove non-relevant interrupts from the list + * + * @vcpu: The VCPU pointer + * + * Go over the list of "interesting" interrupts, and prune those that we + * won't have to consider in the near future. + */ +static void vgic_prune_ap_list(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_irq *irq, *tmp; + + DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); + +retry: + raw_spin_lock(&vgic_cpu->ap_list_lock); + + list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { + struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB; + bool target_vcpu_needs_kick = false; + + raw_spin_lock(&irq->irq_lock); + + BUG_ON(vcpu != irq->vcpu); + + target_vcpu = vgic_target_oracle(irq); + + if (!target_vcpu) { + /* + * We don't need to process this interrupt any + * further, move it off the list. + */ + list_del(&irq->ap_list); + irq->vcpu = NULL; + raw_spin_unlock(&irq->irq_lock); + + /* + * This vgic_put_irq call matches the + * vgic_get_irq_kref in vgic_queue_irq_unlock, + * where we added the LPI to the ap_list. As + * we remove the irq from the list, we drop + * also drop the refcount. + */ + vgic_put_irq(vcpu->kvm, irq); + continue; + } + + if (target_vcpu == vcpu) { + /* We're on the right CPU */ + raw_spin_unlock(&irq->irq_lock); + continue; + } + + /* This interrupt looks like it has to be migrated. */ + + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock(&vgic_cpu->ap_list_lock); + + /* + * Ensure locking order by always locking the smallest + * ID first. + */ + if (vcpu->vcpu_id < target_vcpu->vcpu_id) { + vcpuA = vcpu; + vcpuB = target_vcpu; + } else { + vcpuA = target_vcpu; + vcpuB = vcpu; + } + + raw_spin_lock(&vcpuA->arch.vgic_cpu.ap_list_lock); + raw_spin_lock_nested(&vcpuB->arch.vgic_cpu.ap_list_lock, + SINGLE_DEPTH_NESTING); + raw_spin_lock(&irq->irq_lock); + + /* + * If the affinity has been preserved, move the + * interrupt around. Otherwise, it means things have + * changed while the interrupt was unlocked, and we + * need to replay this. + * + * In all cases, we cannot trust the list not to have + * changed, so we restart from the beginning. + */ + if (target_vcpu == vgic_target_oracle(irq)) { + struct vgic_cpu *new_cpu = &target_vcpu->arch.vgic_cpu; + + list_del(&irq->ap_list); + irq->vcpu = target_vcpu; + list_add_tail(&irq->ap_list, &new_cpu->ap_list_head); + target_vcpu_needs_kick = true; + } + + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock); + raw_spin_unlock(&vcpuA->arch.vgic_cpu.ap_list_lock); + + if (target_vcpu_needs_kick) { + kvm_make_request(KVM_REQ_IRQ_PENDING, target_vcpu); + kvm_vcpu_kick(target_vcpu); + } + + goto retry; + } + + raw_spin_unlock(&vgic_cpu->ap_list_lock); +} + +static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu) +{ + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_fold_lr_state(vcpu); + else + vgic_v3_fold_lr_state(vcpu); +} + +/* Requires the irq_lock to be held. */ +static inline void vgic_populate_lr(struct kvm_vcpu *vcpu, + struct vgic_irq *irq, int lr) +{ + lockdep_assert_held(&irq->irq_lock); + + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_populate_lr(vcpu, irq, lr); + else + vgic_v3_populate_lr(vcpu, irq, lr); +} + +static inline void vgic_clear_lr(struct kvm_vcpu *vcpu, int lr) +{ + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_clear_lr(vcpu, lr); + else + vgic_v3_clear_lr(vcpu, lr); +} + +static inline void vgic_set_underflow(struct kvm_vcpu *vcpu) +{ + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_set_underflow(vcpu); + else + vgic_v3_set_underflow(vcpu); +} + +/* Requires the ap_list_lock to be held. */ +static int compute_ap_list_depth(struct kvm_vcpu *vcpu, + bool *multi_sgi) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_irq *irq; + int count = 0; + + *multi_sgi = false; + + lockdep_assert_held(&vgic_cpu->ap_list_lock); + + list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { + int w; + + raw_spin_lock(&irq->irq_lock); + /* GICv2 SGIs can count for more than one... */ + w = vgic_irq_get_lr_count(irq); + raw_spin_unlock(&irq->irq_lock); + + count += w; + *multi_sgi |= (w > 1); + } + return count; +} + +/* Requires the VCPU's ap_list_lock to be held. */ +static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_irq *irq; + int count; + bool multi_sgi; + u8 prio = 0xff; + int i = 0; + + lockdep_assert_held(&vgic_cpu->ap_list_lock); + + count = compute_ap_list_depth(vcpu, &multi_sgi); + if (count > kvm_vgic_global_state.nr_lr || multi_sgi) + vgic_sort_ap_list(vcpu); + + count = 0; + + list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { + raw_spin_lock(&irq->irq_lock); + + /* + * If we have multi-SGIs in the pipeline, we need to + * guarantee that they are all seen before any IRQ of + * lower priority. In that case, we need to filter out + * these interrupts by exiting early. This is easy as + * the AP list has been sorted already. + */ + if (multi_sgi && irq->priority > prio) { + _raw_spin_unlock(&irq->irq_lock); + break; + } + + if (likely(vgic_target_oracle(irq) == vcpu)) { + vgic_populate_lr(vcpu, irq, count++); + + if (irq->source) + prio = irq->priority; + } + + raw_spin_unlock(&irq->irq_lock); + + if (count == kvm_vgic_global_state.nr_lr) { + if (!list_is_last(&irq->ap_list, + &vgic_cpu->ap_list_head)) + vgic_set_underflow(vcpu); + break; + } + } + + /* Nuke remaining LRs */ + for (i = count ; i < kvm_vgic_global_state.nr_lr; i++) + vgic_clear_lr(vcpu, i); + + if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + vcpu->arch.vgic_cpu.vgic_v2.used_lrs = count; + else + vcpu->arch.vgic_cpu.vgic_v3.used_lrs = count; +} + +static inline bool can_access_vgic_from_kernel(void) +{ + /* + * GICv2 can always be accessed from the kernel because it is + * memory-mapped, and VHE systems can access GICv3 EL2 system + * registers. + */ + return !static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) || has_vhe(); +} + +static inline void vgic_save_state(struct kvm_vcpu *vcpu) +{ + if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + vgic_v2_save_state(vcpu); + else + __vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3); +} + +/* Sync back the hardware VGIC state into our emulation after a guest's run. */ +void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) +{ + int used_lrs; + + /* An empty ap_list_head implies used_lrs == 0 */ + if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) + return; + + if (can_access_vgic_from_kernel()) + vgic_save_state(vcpu); + + if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + used_lrs = vcpu->arch.vgic_cpu.vgic_v2.used_lrs; + else + used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; + + if (used_lrs) + vgic_fold_lr_state(vcpu); + vgic_prune_ap_list(vcpu); +} + +static inline void vgic_restore_state(struct kvm_vcpu *vcpu) +{ + if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) + vgic_v2_restore_state(vcpu); + else + __vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3); +} + +/* Flush our emulation state into the GIC hardware before entering the guest. */ +void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) +{ + /* + * If there are no virtual interrupts active or pending for this + * VCPU, then there is no work to do and we can bail out without + * taking any lock. There is a potential race with someone injecting + * interrupts to the VCPU, but it is a benign race as the VCPU will + * either observe the new interrupt before or after doing this check, + * and introducing additional synchronization mechanism doesn't change + * this. + * + * Note that we still need to go through the whole thing if anything + * can be directly injected (GICv4). + */ + if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head) && + !vgic_supports_direct_msis(vcpu->kvm)) + return; + + DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); + + if (!list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) { + raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock); + vgic_flush_lr_state(vcpu); + raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock); + } + + if (can_access_vgic_from_kernel()) + vgic_restore_state(vcpu); +} + +void kvm_vgic_load(struct kvm_vcpu *vcpu) +{ + if (unlikely(!vgic_initialized(vcpu->kvm))) + return; + + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_load(vcpu); + else + vgic_v3_load(vcpu); +} + +void kvm_vgic_put(struct kvm_vcpu *vcpu) +{ + if (unlikely(!vgic_initialized(vcpu->kvm))) + return; + + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_put(vcpu); + else + vgic_v3_put(vcpu); +} + +void kvm_vgic_vmcr_sync(struct kvm_vcpu *vcpu) +{ + if (unlikely(!irqchip_in_kernel(vcpu->kvm))) + return; + + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_vmcr_sync(vcpu); + else + vgic_v3_vmcr_sync(vcpu); +} + +int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_irq *irq; + bool pending = false; + unsigned long flags; + struct vgic_vmcr vmcr; + + if (!vcpu->kvm->arch.vgic.enabled) + return false; + + if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last) + return true; + + vgic_get_vmcr(vcpu, &vmcr); + + raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); + + list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { + raw_spin_lock(&irq->irq_lock); + pending = irq_is_pending(irq) && irq->enabled && + !irq->active && + irq->priority < vmcr.pmr; + raw_spin_unlock(&irq->irq_lock); + + if (pending) + break; + } + + raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); + + return pending; +} + +void vgic_kick_vcpus(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int c; + + /* + * We've injected an interrupt, time to find out who deserves + * a good kick... + */ + kvm_for_each_vcpu(c, vcpu, kvm) { + if (kvm_vgic_vcpu_pending_irq(vcpu)) { + kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); + kvm_vcpu_kick(vcpu); + } + } +} + +bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid) +{ + struct vgic_irq *irq; + bool map_is_active; + unsigned long flags; + + if (!vgic_initialized(vcpu->kvm)) + return false; + + irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); + raw_spin_lock_irqsave(&irq->irq_lock, flags); + map_is_active = irq->hw && irq->active; + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + vgic_put_irq(vcpu->kvm, irq); + + return map_is_active; +} diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h new file mode 100644 index 000000000000..64fcd7511110 --- /dev/null +++ b/arch/arm64/kvm/vgic/vgic.h @@ -0,0 +1,321 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015, 2016 ARM Ltd. + */ +#ifndef __KVM_ARM_VGIC_NEW_H__ +#define __KVM_ARM_VGIC_NEW_H__ + +#include <linux/irqchip/arm-gic-common.h> + +#define PRODUCT_ID_KVM 0x4b /* ASCII code K */ +#define IMPLEMENTER_ARM 0x43b + +#define VGIC_ADDR_UNDEF (-1) +#define IS_VGIC_ADDR_UNDEF(_x) ((_x) == VGIC_ADDR_UNDEF) + +#define INTERRUPT_ID_BITS_SPIS 10 +#define INTERRUPT_ID_BITS_ITS 16 +#define VGIC_PRI_BITS 5 + +#define vgic_irq_is_sgi(intid) ((intid) < VGIC_NR_SGIS) + +#define VGIC_AFFINITY_0_SHIFT 0 +#define VGIC_AFFINITY_0_MASK (0xffUL << VGIC_AFFINITY_0_SHIFT) +#define VGIC_AFFINITY_1_SHIFT 8 +#define VGIC_AFFINITY_1_MASK (0xffUL << VGIC_AFFINITY_1_SHIFT) +#define VGIC_AFFINITY_2_SHIFT 16 +#define VGIC_AFFINITY_2_MASK (0xffUL << VGIC_AFFINITY_2_SHIFT) +#define VGIC_AFFINITY_3_SHIFT 24 +#define VGIC_AFFINITY_3_MASK (0xffUL << VGIC_AFFINITY_3_SHIFT) + +#define VGIC_AFFINITY_LEVEL(reg, level) \ + ((((reg) & VGIC_AFFINITY_## level ##_MASK) \ + >> VGIC_AFFINITY_## level ##_SHIFT) << MPIDR_LEVEL_SHIFT(level)) + +/* + * The Userspace encodes the affinity differently from the MPIDR, + * Below macro converts vgic userspace format to MPIDR reg format. + */ +#define VGIC_TO_MPIDR(val) (VGIC_AFFINITY_LEVEL(val, 0) | \ + VGIC_AFFINITY_LEVEL(val, 1) | \ + VGIC_AFFINITY_LEVEL(val, 2) | \ + VGIC_AFFINITY_LEVEL(val, 3)) + +/* + * As per Documentation/virt/kvm/devices/arm-vgic-v3.rst, + * below macros are defined for CPUREG encoding. + */ +#define KVM_REG_ARM_VGIC_SYSREG_OP0_MASK 0x000000000000c000 +#define KVM_REG_ARM_VGIC_SYSREG_OP0_SHIFT 14 +#define KVM_REG_ARM_VGIC_SYSREG_OP1_MASK 0x0000000000003800 +#define KVM_REG_ARM_VGIC_SYSREG_OP1_SHIFT 11 +#define KVM_REG_ARM_VGIC_SYSREG_CRN_MASK 0x0000000000000780 +#define KVM_REG_ARM_VGIC_SYSREG_CRN_SHIFT 7 +#define KVM_REG_ARM_VGIC_SYSREG_CRM_MASK 0x0000000000000078 +#define KVM_REG_ARM_VGIC_SYSREG_CRM_SHIFT 3 +#define KVM_REG_ARM_VGIC_SYSREG_OP2_MASK 0x0000000000000007 +#define KVM_REG_ARM_VGIC_SYSREG_OP2_SHIFT 0 + +#define KVM_DEV_ARM_VGIC_SYSREG_MASK (KVM_REG_ARM_VGIC_SYSREG_OP0_MASK | \ + KVM_REG_ARM_VGIC_SYSREG_OP1_MASK | \ + KVM_REG_ARM_VGIC_SYSREG_CRN_MASK | \ + KVM_REG_ARM_VGIC_SYSREG_CRM_MASK | \ + KVM_REG_ARM_VGIC_SYSREG_OP2_MASK) + +/* + * As per Documentation/virt/kvm/devices/arm-vgic-its.rst, + * below macros are defined for ITS table entry encoding. + */ +#define KVM_ITS_CTE_VALID_SHIFT 63 +#define KVM_ITS_CTE_VALID_MASK BIT_ULL(63) +#define KVM_ITS_CTE_RDBASE_SHIFT 16 +#define KVM_ITS_CTE_ICID_MASK GENMASK_ULL(15, 0) +#define KVM_ITS_ITE_NEXT_SHIFT 48 +#define KVM_ITS_ITE_PINTID_SHIFT 16 +#define KVM_ITS_ITE_PINTID_MASK GENMASK_ULL(47, 16) +#define KVM_ITS_ITE_ICID_MASK GENMASK_ULL(15, 0) +#define KVM_ITS_DTE_VALID_SHIFT 63 +#define KVM_ITS_DTE_VALID_MASK BIT_ULL(63) +#define KVM_ITS_DTE_NEXT_SHIFT 49 +#define KVM_ITS_DTE_NEXT_MASK GENMASK_ULL(62, 49) +#define KVM_ITS_DTE_ITTADDR_SHIFT 5 +#define KVM_ITS_DTE_ITTADDR_MASK GENMASK_ULL(48, 5) +#define KVM_ITS_DTE_SIZE_MASK GENMASK_ULL(4, 0) +#define KVM_ITS_L1E_VALID_MASK BIT_ULL(63) +/* we only support 64 kB translation table page size */ +#define KVM_ITS_L1E_ADDR_MASK GENMASK_ULL(51, 16) + +#define KVM_VGIC_V3_RDIST_INDEX_MASK GENMASK_ULL(11, 0) +#define KVM_VGIC_V3_RDIST_FLAGS_MASK GENMASK_ULL(15, 12) +#define KVM_VGIC_V3_RDIST_FLAGS_SHIFT 12 +#define KVM_VGIC_V3_RDIST_BASE_MASK GENMASK_ULL(51, 16) +#define KVM_VGIC_V3_RDIST_COUNT_MASK GENMASK_ULL(63, 52) +#define KVM_VGIC_V3_RDIST_COUNT_SHIFT 52 + +#ifdef CONFIG_DEBUG_SPINLOCK +#define DEBUG_SPINLOCK_BUG_ON(p) BUG_ON(p) +#else +#define DEBUG_SPINLOCK_BUG_ON(p) +#endif + +/* Requires the irq_lock to be held by the caller. */ +static inline bool irq_is_pending(struct vgic_irq *irq) +{ + if (irq->config == VGIC_CONFIG_EDGE) + return irq->pending_latch; + else + return irq->pending_latch || irq->line_level; +} + +static inline bool vgic_irq_is_mapped_level(struct vgic_irq *irq) +{ + return irq->config == VGIC_CONFIG_LEVEL && irq->hw; +} + +static inline int vgic_irq_get_lr_count(struct vgic_irq *irq) +{ + /* Account for the active state as an interrupt */ + if (vgic_irq_is_sgi(irq->intid) && irq->source) + return hweight8(irq->source) + irq->active; + + return irq_is_pending(irq) || irq->active; +} + +static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq) +{ + return vgic_irq_get_lr_count(irq) > 1; +} + +/* + * This struct provides an intermediate representation of the fields contained + * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC + * state to userspace can generate either GICv2 or GICv3 CPU interface + * registers regardless of the hardware backed GIC used. + */ +struct vgic_vmcr { + u32 grpen0; + u32 grpen1; + + u32 ackctl; + u32 fiqen; + u32 cbpr; + u32 eoim; + + u32 abpr; + u32 bpr; + u32 pmr; /* Priority mask field in the GICC_PMR and + * ICC_PMR_EL1 priority field format */ +}; + +struct vgic_reg_attr { + struct kvm_vcpu *vcpu; + gpa_t addr; +}; + +int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, + struct vgic_reg_attr *reg_attr); +int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, + struct vgic_reg_attr *reg_attr); +const struct vgic_register_region * +vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, + gpa_t addr, int len); +struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, + u32 intid); +void __vgic_put_lpi_locked(struct kvm *kvm, struct vgic_irq *irq); +void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq); +bool vgic_get_phys_line_level(struct vgic_irq *irq); +void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending); +void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active); +bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, + unsigned long flags); +void vgic_kick_vcpus(struct kvm *kvm); + +int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr, + phys_addr_t addr, phys_addr_t alignment); + +void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu); +void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr); +void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr); +void vgic_v2_set_underflow(struct kvm_vcpu *vcpu); +void vgic_v2_set_npie(struct kvm_vcpu *vcpu); +int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr); +int vgic_v2_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, + int offset, u32 *val); +int vgic_v2_cpuif_uaccess(struct kvm_vcpu *vcpu, bool is_write, + int offset, u32 *val); +void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); +void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); +void vgic_v2_enable(struct kvm_vcpu *vcpu); +int vgic_v2_probe(const struct gic_kvm_info *info); +int vgic_v2_map_resources(struct kvm *kvm); +int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, + enum vgic_type); + +void vgic_v2_init_lrs(void); +void vgic_v2_load(struct kvm_vcpu *vcpu); +void vgic_v2_put(struct kvm_vcpu *vcpu); +void vgic_v2_vmcr_sync(struct kvm_vcpu *vcpu); + +void vgic_v2_save_state(struct kvm_vcpu *vcpu); +void vgic_v2_restore_state(struct kvm_vcpu *vcpu); + +static inline void vgic_get_irq_kref(struct vgic_irq *irq) +{ + if (irq->intid < VGIC_MIN_LPI) + return; + + kref_get(&irq->refcount); +} + +void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu); +void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr); +void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr); +void vgic_v3_set_underflow(struct kvm_vcpu *vcpu); +void vgic_v3_set_npie(struct kvm_vcpu *vcpu); +void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); +void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); +void vgic_v3_enable(struct kvm_vcpu *vcpu); +int vgic_v3_probe(const struct gic_kvm_info *info); +int vgic_v3_map_resources(struct kvm *kvm); +int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq); +int vgic_v3_save_pending_tables(struct kvm *kvm); +int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count); +int vgic_register_redist_iodev(struct kvm_vcpu *vcpu); +bool vgic_v3_check_base(struct kvm *kvm); + +void vgic_v3_load(struct kvm_vcpu *vcpu); +void vgic_v3_put(struct kvm_vcpu *vcpu); +void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu); + +bool vgic_has_its(struct kvm *kvm); +int kvm_vgic_register_its_device(void); +void vgic_enable_lpis(struct kvm_vcpu *vcpu); +void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu); +int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi); +int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr); +int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, + int offset, u32 *val); +int vgic_v3_redist_uaccess(struct kvm_vcpu *vcpu, bool is_write, + int offset, u32 *val); +int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, bool is_write, + u64 id, u64 *val); +int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, bool is_write, u64 id, + u64 *reg); +int vgic_v3_line_level_info_uaccess(struct kvm_vcpu *vcpu, bool is_write, + u32 intid, u64 *val); +int kvm_register_vgic_device(unsigned long type); +void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); +void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); +int vgic_lazy_init(struct kvm *kvm); +int vgic_init(struct kvm *kvm); + +void vgic_debug_init(struct kvm *kvm); +void vgic_debug_destroy(struct kvm *kvm); + +bool lock_all_vcpus(struct kvm *kvm); +void unlock_all_vcpus(struct kvm *kvm); + +static inline int vgic_v3_max_apr_idx(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *cpu_if = &vcpu->arch.vgic_cpu; + + /* + * num_pri_bits are initialized with HW supported values. + * We can rely safely on num_pri_bits even if VM has not + * restored ICC_CTLR_EL1 before restoring APnR registers. + */ + switch (cpu_if->num_pri_bits) { + case 7: return 3; + case 6: return 1; + default: return 0; + } +} + +static inline bool +vgic_v3_redist_region_full(struct vgic_redist_region *region) +{ + if (!region->count) + return false; + + return (region->free_index >= region->count); +} + +struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rdregs); + +static inline size_t +vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) +{ + if (!rdreg->count) + return atomic_read(&kvm->online_vcpus) * KVM_VGIC_V3_REDIST_SIZE; + else + return rdreg->count * KVM_VGIC_V3_REDIST_SIZE; +} + +struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, + u32 index); + +bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); + +static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size) +{ + struct vgic_dist *d = &kvm->arch.vgic; + + return (base + size > d->vgic_dist_base) && + (base < d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE); +} + +int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr); +int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, + u32 devid, u32 eventid, struct vgic_irq **irq); +struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi); +int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi); +void vgic_lpi_translation_cache_init(struct kvm *kvm); +void vgic_lpi_translation_cache_destroy(struct kvm *kvm); +void vgic_its_invalidate_cache(struct kvm *kvm); + +bool vgic_supports_direct_msis(struct kvm *kvm); +int vgic_v4_init(struct kvm *kvm); +void vgic_v4_teardown(struct kvm *kvm); +void vgic_v4_configure_vsgis(struct kvm *kvm); + +#endif diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 2c343c346b79..e28b5a946e26 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -174,6 +174,8 @@ struct kvm_vcpu_stat { #endif u64 halt_successful_poll; u64 halt_attempted_poll; + u64 halt_poll_success_ns; + u64 halt_poll_fail_ns; u64 halt_poll_invalid; u64 halt_wakeup; }; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 2261c63174c5..3b0148c99c0d 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -39,40 +39,41 @@ #define VECTORSPACING 0x100 /* for EI/VI mode */ #endif -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x) struct kvm_stats_debugfs_item debugfs_entries[] = { - { "wait", VCPU_STAT(wait_exits), KVM_STAT_VCPU }, - { "cache", VCPU_STAT(cache_exits), KVM_STAT_VCPU }, - { "signal", VCPU_STAT(signal_exits), KVM_STAT_VCPU }, - { "interrupt", VCPU_STAT(int_exits), KVM_STAT_VCPU }, - { "cop_unusable", VCPU_STAT(cop_unusable_exits), KVM_STAT_VCPU }, - { "tlbmod", VCPU_STAT(tlbmod_exits), KVM_STAT_VCPU }, - { "tlbmiss_ld", VCPU_STAT(tlbmiss_ld_exits), KVM_STAT_VCPU }, - { "tlbmiss_st", VCPU_STAT(tlbmiss_st_exits), KVM_STAT_VCPU }, - { "addrerr_st", VCPU_STAT(addrerr_st_exits), KVM_STAT_VCPU }, - { "addrerr_ld", VCPU_STAT(addrerr_ld_exits), KVM_STAT_VCPU }, - { "syscall", VCPU_STAT(syscall_exits), KVM_STAT_VCPU }, - { "resvd_inst", VCPU_STAT(resvd_inst_exits), KVM_STAT_VCPU }, - { "break_inst", VCPU_STAT(break_inst_exits), KVM_STAT_VCPU }, - { "trap_inst", VCPU_STAT(trap_inst_exits), KVM_STAT_VCPU }, - { "msa_fpe", VCPU_STAT(msa_fpe_exits), KVM_STAT_VCPU }, - { "fpe", VCPU_STAT(fpe_exits), KVM_STAT_VCPU }, - { "msa_disabled", VCPU_STAT(msa_disabled_exits), KVM_STAT_VCPU }, - { "flush_dcache", VCPU_STAT(flush_dcache_exits), KVM_STAT_VCPU }, + VCPU_STAT("wait", wait_exits), + VCPU_STAT("cache", cache_exits), + VCPU_STAT("signal", signal_exits), + VCPU_STAT("interrupt", int_exits), + VCPU_STAT("cop_unusable", cop_unusable_exits), + VCPU_STAT("tlbmod", tlbmod_exits), + VCPU_STAT("tlbmiss_ld", tlbmiss_ld_exits), + VCPU_STAT("tlbmiss_st", tlbmiss_st_exits), + VCPU_STAT("addrerr_st", addrerr_st_exits), + VCPU_STAT("addrerr_ld", addrerr_ld_exits), + VCPU_STAT("syscall", syscall_exits), + VCPU_STAT("resvd_inst", resvd_inst_exits), + VCPU_STAT("break_inst", break_inst_exits), + VCPU_STAT("trap_inst", trap_inst_exits), + VCPU_STAT("msa_fpe", msa_fpe_exits), + VCPU_STAT("fpe", fpe_exits), + VCPU_STAT("msa_disabled", msa_disabled_exits), + VCPU_STAT("flush_dcache", flush_dcache_exits), #ifdef CONFIG_KVM_MIPS_VZ - { "vz_gpsi", VCPU_STAT(vz_gpsi_exits), KVM_STAT_VCPU }, - { "vz_gsfc", VCPU_STAT(vz_gsfc_exits), KVM_STAT_VCPU }, - { "vz_hc", VCPU_STAT(vz_hc_exits), KVM_STAT_VCPU }, - { "vz_grr", VCPU_STAT(vz_grr_exits), KVM_STAT_VCPU }, - { "vz_gva", VCPU_STAT(vz_gva_exits), KVM_STAT_VCPU }, - { "vz_ghfc", VCPU_STAT(vz_ghfc_exits), KVM_STAT_VCPU }, - { "vz_gpa", VCPU_STAT(vz_gpa_exits), KVM_STAT_VCPU }, - { "vz_resvd", VCPU_STAT(vz_resvd_exits), KVM_STAT_VCPU }, + VCPU_STAT("vz_gpsi", vz_gpsi_exits), + VCPU_STAT("vz_gsfc", vz_gsfc_exits), + VCPU_STAT("vz_hc", vz_hc_exits), + VCPU_STAT("vz_grr", vz_grr_exits), + VCPU_STAT("vz_gva", vz_gva_exits), + VCPU_STAT("vz_ghfc", vz_ghfc_exits), + VCPU_STAT("vz_gpa", vz_gpa_exits), + VCPU_STAT("vz_resvd", vz_resvd_exits), #endif - { "halt_successful_poll", VCPU_STAT(halt_successful_poll), KVM_STAT_VCPU }, - { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll), KVM_STAT_VCPU }, - { "halt_poll_invalid", VCPU_STAT(halt_poll_invalid), KVM_STAT_VCPU }, - { "halt_wakeup", VCPU_STAT(halt_wakeup), KVM_STAT_VCPU }, + VCPU_STAT("halt_successful_poll", halt_successful_poll), + VCPU_STAT("halt_attempted_poll", halt_attempted_poll), + VCPU_STAT("halt_poll_invalid", halt_poll_invalid), + VCPU_STAT("halt_wakeup", halt_wakeup), + VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), + VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), {NULL} }; @@ -284,8 +285,7 @@ static enum hrtimer_restart kvm_mips_comparecount_wakeup(struct hrtimer *timer) kvm_mips_callbacks->queue_timer_int(vcpu); vcpu->arch.wait = 0; - if (swq_has_sleeper(&vcpu->wq)) - swake_up_one(&vcpu->wq); + rcuwait_wake_up(&vcpu->wait); return kvm_mips_count_timeout(vcpu); } @@ -439,8 +439,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, return -ENOIOCTLCMD; } -int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { + struct kvm_run *run = vcpu->run; int r = -EINTR; vcpu_load(vcpu); @@ -511,8 +512,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, dvcpu->arch.wait = 0; - if (swq_has_sleeper(&dvcpu->wq)) - swake_up_one(&dvcpu->wq); + rcuwait_wake_up(&dvcpu->wait); return 0; } diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 506e4df2d730..6e5d85ba588d 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -78,7 +78,7 @@ struct kvmppc_vcore { struct kvm_vcpu *runnable_threads[MAX_SMT_THREADS]; struct list_head preempt_list; spinlock_t lock; - struct swait_queue_head wq; + struct rcuwait wait; spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ u64 stolen_tb; u64 preempt_tb; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 1dc63101ffe1..337047ba4a56 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -751,7 +751,7 @@ struct kvm_vcpu_arch { u8 irq_pending; /* Used by XIVE to signal pending guest irqs */ u32 last_inst; - struct swait_queue_head *wqp; + struct rcuwait *waitp; struct kvmppc_vcore *vcore; int ret; int trap; diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 5690a1f9b976..37508a356f28 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -36,41 +36,38 @@ #include "book3s.h" #include "trace.h" -#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ -#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ - /* #define EXIT_DEBUG */ struct kvm_stats_debugfs_item debugfs_entries[] = { - { "exits", VCPU_STAT(sum_exits) }, - { "mmio", VCPU_STAT(mmio_exits) }, - { "sig", VCPU_STAT(signal_exits) }, - { "sysc", VCPU_STAT(syscall_exits) }, - { "inst_emu", VCPU_STAT(emulated_inst_exits) }, - { "dec", VCPU_STAT(dec_exits) }, - { "ext_intr", VCPU_STAT(ext_intr_exits) }, - { "queue_intr", VCPU_STAT(queue_intr) }, - { "halt_poll_success_ns", VCPU_STAT(halt_poll_success_ns) }, - { "halt_poll_fail_ns", VCPU_STAT(halt_poll_fail_ns) }, - { "halt_wait_ns", VCPU_STAT(halt_wait_ns) }, - { "halt_successful_poll", VCPU_STAT(halt_successful_poll), }, - { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll), }, - { "halt_successful_wait", VCPU_STAT(halt_successful_wait) }, - { "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) }, - { "halt_wakeup", VCPU_STAT(halt_wakeup) }, - { "pf_storage", VCPU_STAT(pf_storage) }, - { "sp_storage", VCPU_STAT(sp_storage) }, - { "pf_instruc", VCPU_STAT(pf_instruc) }, - { "sp_instruc", VCPU_STAT(sp_instruc) }, - { "ld", VCPU_STAT(ld) }, - { "ld_slow", VCPU_STAT(ld_slow) }, - { "st", VCPU_STAT(st) }, - { "st_slow", VCPU_STAT(st_slow) }, - { "pthru_all", VCPU_STAT(pthru_all) }, - { "pthru_host", VCPU_STAT(pthru_host) }, - { "pthru_bad_aff", VCPU_STAT(pthru_bad_aff) }, - { "largepages_2M", VM_STAT(num_2M_pages, .mode = 0444) }, - { "largepages_1G", VM_STAT(num_1G_pages, .mode = 0444) }, + VCPU_STAT("exits", sum_exits), + VCPU_STAT("mmio", mmio_exits), + VCPU_STAT("sig", signal_exits), + VCPU_STAT("sysc", syscall_exits), + VCPU_STAT("inst_emu", emulated_inst_exits), + VCPU_STAT("dec", dec_exits), + VCPU_STAT("ext_intr", ext_intr_exits), + VCPU_STAT("queue_intr", queue_intr), + VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), + VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), + VCPU_STAT("halt_wait_ns", halt_wait_ns), + VCPU_STAT("halt_successful_poll", halt_successful_poll), + VCPU_STAT("halt_attempted_poll", halt_attempted_poll), + VCPU_STAT("halt_successful_wait", halt_successful_wait), + VCPU_STAT("halt_poll_invalid", halt_poll_invalid), + VCPU_STAT("halt_wakeup", halt_wakeup), + VCPU_STAT("pf_storage", pf_storage), + VCPU_STAT("sp_storage", sp_storage), + VCPU_STAT("pf_instruc", pf_instruc), + VCPU_STAT("sp_instruc", sp_instruc), + VCPU_STAT("ld", ld), + VCPU_STAT("ld_slow", ld_slow), + VCPU_STAT("st", st), + VCPU_STAT("st_slow", st_slow), + VCPU_STAT("pthru_all", pthru_all), + VCPU_STAT("pthru_host", pthru_host), + VCPU_STAT("pthru_bad_aff", pthru_bad_aff), + VM_STAT("largepages_2M", num_2M_pages, .mode = 0444), + VM_STAT("largepages_1G", num_1G_pages, .mode = 0444), { NULL } }; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 93493f0cbfe8..7f59c47a5b9d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -230,13 +230,11 @@ static bool kvmppc_ipi_thread(int cpu) static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) { int cpu; - struct swait_queue_head *wqp; + struct rcuwait *waitp; - wqp = kvm_arch_vcpu_wq(vcpu); - if (swq_has_sleeper(wqp)) { - swake_up_one(wqp); + waitp = kvm_arch_vcpu_get_wait(vcpu); + if (rcuwait_wake_up(waitp)) ++vcpu->stat.halt_wakeup; - } cpu = READ_ONCE(vcpu->arch.thread_cpu); if (cpu >= 0 && kvmppc_ipi_thread(cpu)) @@ -2125,7 +2123,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int id) spin_lock_init(&vcore->lock); spin_lock_init(&vcore->stoltb_lock); - init_swait_queue_head(&vcore->wq); + rcuwait_init(&vcore->wait); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; vcore->first_vcpuid = id; @@ -3784,7 +3782,6 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) ktime_t cur, start_poll, start_wait; int do_sleep = 1; u64 block_ns; - DECLARE_SWAITQUEUE(wait); /* Poll for pending exceptions and ceded state */ cur = start_poll = ktime_get(); @@ -3812,10 +3809,10 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) } } - prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE); - + prepare_to_rcuwait(&vc->wait); + set_current_state(TASK_INTERRUPTIBLE); if (kvmppc_vcore_check_block(vc)) { - finish_swait(&vc->wq, &wait); + finish_rcuwait(&vc->wait); do_sleep = 0; /* If we polled, count this as a successful poll */ if (vc->halt_poll_ns) @@ -3829,7 +3826,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) trace_kvmppc_vcore_blocked(vc, 0); spin_unlock(&vc->lock); schedule(); - finish_swait(&vc->wq, &wait); + finish_rcuwait(&vc->wait); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; trace_kvmppc_vcore_blocked(vc, 1); @@ -3940,7 +3937,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { - swake_up_one(&vc->wq); + rcuwait_wake_up(&vc->wait); } } @@ -4279,7 +4276,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) } user_vrsave = mfspr(SPRN_VRSAVE); - vcpu->arch.wqp = &vcpu->arch.vcore->wq; + vcpu->arch.waitp = &vcpu->arch.vcore->wait; vcpu->arch.pgdir = kvm->mm->pgd; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 6c18ea88fd25..888afe8d35cc 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -35,29 +35,28 @@ unsigned long kvmppc_booke_handlers; -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU - struct kvm_stats_debugfs_item debugfs_entries[] = { - { "mmio", VCPU_STAT(mmio_exits) }, - { "sig", VCPU_STAT(signal_exits) }, - { "itlb_r", VCPU_STAT(itlb_real_miss_exits) }, - { "itlb_v", VCPU_STAT(itlb_virt_miss_exits) }, - { "dtlb_r", VCPU_STAT(dtlb_real_miss_exits) }, - { "dtlb_v", VCPU_STAT(dtlb_virt_miss_exits) }, - { "sysc", VCPU_STAT(syscall_exits) }, - { "isi", VCPU_STAT(isi_exits) }, - { "dsi", VCPU_STAT(dsi_exits) }, - { "inst_emu", VCPU_STAT(emulated_inst_exits) }, - { "dec", VCPU_STAT(dec_exits) }, - { "ext_intr", VCPU_STAT(ext_intr_exits) }, - { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, - { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, - { "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) }, - { "halt_wakeup", VCPU_STAT(halt_wakeup) }, - { "doorbell", VCPU_STAT(dbell_exits) }, - { "guest doorbell", VCPU_STAT(gdbell_exits) }, - { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, + VCPU_STAT("mmio", mmio_exits), + VCPU_STAT("sig", signal_exits), + VCPU_STAT("itlb_r", itlb_real_miss_exits), + VCPU_STAT("itlb_v", itlb_virt_miss_exits), + VCPU_STAT("dtlb_r", dtlb_real_miss_exits), + VCPU_STAT("dtlb_v", dtlb_virt_miss_exits), + VCPU_STAT("sysc", syscall_exits), + VCPU_STAT("isi", isi_exits), + VCPU_STAT("dsi", dsi_exits), + VCPU_STAT("inst_emu", emulated_inst_exits), + VCPU_STAT("dec", dec_exits), + VCPU_STAT("ext_intr", ext_intr_exits), + VCPU_STAT("halt_successful_poll", halt_successful_poll), + VCPU_STAT("halt_attempted_poll", halt_attempted_poll), + VCPU_STAT("halt_poll_invalid", halt_poll_invalid), + VCPU_STAT("halt_wakeup", halt_wakeup), + VCPU_STAT("doorbell", dbell_exits), + VCPU_STAT("guest doorbell", gdbell_exits), + VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), + VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), + VM_STAT("remote_tlb_flush", remote_tlb_flush), { NULL } }; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index ad2f172c26a6..27ccff612903 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -752,7 +752,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (err) goto out_vcpu_uninit; - vcpu->arch.wqp = &vcpu->wq; + vcpu->arch.waitp = &vcpu->wait; kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id); return 0; @@ -1765,8 +1765,9 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) return r; } -int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { + struct kvm_run *run = vcpu->run; int r; vcpu_load(vcpu); diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index d6bcd34f3ec3..3d554887794e 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -375,6 +375,8 @@ struct kvm_vcpu_stat { u64 halt_poll_invalid; u64 halt_no_poll_steal; u64 halt_wakeup; + u64 halt_poll_success_ns; + u64 halt_poll_fail_ns; u64 instruction_lctl; u64 instruction_lctlg; u64 instruction_stctl; @@ -971,7 +973,7 @@ struct kvm_arch_async_pf { unsigned long pfault_token; }; -bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu); +bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu); void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); @@ -982,6 +984,8 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); +static inline void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu) {} + void kvm_arch_crypto_clear_masks(struct kvm *kvm); void kvm_arch_crypto_set_masks(struct kvm *kvm, unsigned long *apm, unsigned long *aqm, unsigned long *adm); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index bfb481134994..a4d4ca2769bd 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3082,7 +3082,7 @@ static enum hrtimer_restart gisa_vcpu_kicker(struct hrtimer *timer) __airqs_kick_single_vcpu(kvm, pending_mask); hrtimer_forward_now(timer, ns_to_ktime(gi->expires)); return HRTIMER_RESTART; - }; + } return HRTIMER_NORESTART; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d05bb040fd42..06bde4bad205 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -57,110 +57,109 @@ #define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \ (KVM_MAX_VCPUS + LOCAL_IRQS)) -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM - struct kvm_stats_debugfs_item debugfs_entries[] = { - { "userspace_handled", VCPU_STAT(exit_userspace) }, - { "exit_null", VCPU_STAT(exit_null) }, - { "exit_validity", VCPU_STAT(exit_validity) }, - { "exit_stop_request", VCPU_STAT(exit_stop_request) }, - { "exit_external_request", VCPU_STAT(exit_external_request) }, - { "exit_io_request", VCPU_STAT(exit_io_request) }, - { "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) }, - { "exit_instruction", VCPU_STAT(exit_instruction) }, - { "exit_pei", VCPU_STAT(exit_pei) }, - { "exit_program_interruption", VCPU_STAT(exit_program_interruption) }, - { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) }, - { "exit_operation_exception", VCPU_STAT(exit_operation_exception) }, - { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, - { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, - { "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) }, - { "halt_no_poll_steal", VCPU_STAT(halt_no_poll_steal) }, - { "halt_wakeup", VCPU_STAT(halt_wakeup) }, - { "instruction_lctlg", VCPU_STAT(instruction_lctlg) }, - { "instruction_lctl", VCPU_STAT(instruction_lctl) }, - { "instruction_stctl", VCPU_STAT(instruction_stctl) }, - { "instruction_stctg", VCPU_STAT(instruction_stctg) }, - { "deliver_ckc", VCPU_STAT(deliver_ckc) }, - { "deliver_cputm", VCPU_STAT(deliver_cputm) }, - { "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) }, - { "deliver_external_call", VCPU_STAT(deliver_external_call) }, - { "deliver_service_signal", VCPU_STAT(deliver_service_signal) }, - { "deliver_virtio", VCPU_STAT(deliver_virtio) }, - { "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) }, - { "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) }, - { "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) }, - { "deliver_program", VCPU_STAT(deliver_program) }, - { "deliver_io", VCPU_STAT(deliver_io) }, - { "deliver_machine_check", VCPU_STAT(deliver_machine_check) }, - { "exit_wait_state", VCPU_STAT(exit_wait_state) }, - { "inject_ckc", VCPU_STAT(inject_ckc) }, - { "inject_cputm", VCPU_STAT(inject_cputm) }, - { "inject_external_call", VCPU_STAT(inject_external_call) }, - { "inject_float_mchk", VM_STAT(inject_float_mchk) }, - { "inject_emergency_signal", VCPU_STAT(inject_emergency_signal) }, - { "inject_io", VM_STAT(inject_io) }, - { "inject_mchk", VCPU_STAT(inject_mchk) }, - { "inject_pfault_done", VM_STAT(inject_pfault_done) }, - { "inject_program", VCPU_STAT(inject_program) }, - { "inject_restart", VCPU_STAT(inject_restart) }, - { "inject_service_signal", VM_STAT(inject_service_signal) }, - { "inject_set_prefix", VCPU_STAT(inject_set_prefix) }, - { "inject_stop_signal", VCPU_STAT(inject_stop_signal) }, - { "inject_pfault_init", VCPU_STAT(inject_pfault_init) }, - { "inject_virtio", VM_STAT(inject_virtio) }, - { "instruction_epsw", VCPU_STAT(instruction_epsw) }, - { "instruction_gs", VCPU_STAT(instruction_gs) }, - { "instruction_io_other", VCPU_STAT(instruction_io_other) }, - { "instruction_lpsw", VCPU_STAT(instruction_lpsw) }, - { "instruction_lpswe", VCPU_STAT(instruction_lpswe) }, - { "instruction_pfmf", VCPU_STAT(instruction_pfmf) }, - { "instruction_ptff", VCPU_STAT(instruction_ptff) }, - { "instruction_stidp", VCPU_STAT(instruction_stidp) }, - { "instruction_sck", VCPU_STAT(instruction_sck) }, - { "instruction_sckpf", VCPU_STAT(instruction_sckpf) }, - { "instruction_spx", VCPU_STAT(instruction_spx) }, - { "instruction_stpx", VCPU_STAT(instruction_stpx) }, - { "instruction_stap", VCPU_STAT(instruction_stap) }, - { "instruction_iske", VCPU_STAT(instruction_iske) }, - { "instruction_ri", VCPU_STAT(instruction_ri) }, - { "instruction_rrbe", VCPU_STAT(instruction_rrbe) }, - { "instruction_sske", VCPU_STAT(instruction_sske) }, - { "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) }, - { "instruction_essa", VCPU_STAT(instruction_essa) }, - { "instruction_stsi", VCPU_STAT(instruction_stsi) }, - { "instruction_stfl", VCPU_STAT(instruction_stfl) }, - { "instruction_tb", VCPU_STAT(instruction_tb) }, - { "instruction_tpi", VCPU_STAT(instruction_tpi) }, - { "instruction_tprot", VCPU_STAT(instruction_tprot) }, - { "instruction_tsch", VCPU_STAT(instruction_tsch) }, - { "instruction_sthyi", VCPU_STAT(instruction_sthyi) }, - { "instruction_sie", VCPU_STAT(instruction_sie) }, - { "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) }, - { "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) }, - { "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) }, - { "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) }, - { "instruction_sigp_cond_emergency", VCPU_STAT(instruction_sigp_cond_emergency) }, - { "instruction_sigp_start", VCPU_STAT(instruction_sigp_start) }, - { "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) }, - { "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) }, - { "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) }, - { "instruction_sigp_store_adtl_status", VCPU_STAT(instruction_sigp_store_adtl_status) }, - { "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) }, - { "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) }, - { "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) }, - { "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) }, - { "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) }, - { "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) }, - { "instruction_diag_10", VCPU_STAT(diagnose_10) }, - { "instruction_diag_44", VCPU_STAT(diagnose_44) }, - { "instruction_diag_9c", VCPU_STAT(diagnose_9c) }, - { "diag_9c_ignored", VCPU_STAT(diagnose_9c_ignored) }, - { "instruction_diag_258", VCPU_STAT(diagnose_258) }, - { "instruction_diag_308", VCPU_STAT(diagnose_308) }, - { "instruction_diag_500", VCPU_STAT(diagnose_500) }, - { "instruction_diag_other", VCPU_STAT(diagnose_other) }, + VCPU_STAT("userspace_handled", exit_userspace), + VCPU_STAT("exit_null", exit_null), + VCPU_STAT("exit_validity", exit_validity), + VCPU_STAT("exit_stop_request", exit_stop_request), + VCPU_STAT("exit_external_request", exit_external_request), + VCPU_STAT("exit_io_request", exit_io_request), + VCPU_STAT("exit_external_interrupt", exit_external_interrupt), + VCPU_STAT("exit_instruction", exit_instruction), + VCPU_STAT("exit_pei", exit_pei), + VCPU_STAT("exit_program_interruption", exit_program_interruption), + VCPU_STAT("exit_instr_and_program_int", exit_instr_and_program), + VCPU_STAT("exit_operation_exception", exit_operation_exception), + VCPU_STAT("halt_successful_poll", halt_successful_poll), + VCPU_STAT("halt_attempted_poll", halt_attempted_poll), + VCPU_STAT("halt_poll_invalid", halt_poll_invalid), + VCPU_STAT("halt_no_poll_steal", halt_no_poll_steal), + VCPU_STAT("halt_wakeup", halt_wakeup), + VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), + VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), + VCPU_STAT("instruction_lctlg", instruction_lctlg), + VCPU_STAT("instruction_lctl", instruction_lctl), + VCPU_STAT("instruction_stctl", instruction_stctl), + VCPU_STAT("instruction_stctg", instruction_stctg), + VCPU_STAT("deliver_ckc", deliver_ckc), + VCPU_STAT("deliver_cputm", deliver_cputm), + VCPU_STAT("deliver_emergency_signal", deliver_emergency_signal), + VCPU_STAT("deliver_external_call", deliver_external_call), + VCPU_STAT("deliver_service_signal", deliver_service_signal), + VCPU_STAT("deliver_virtio", deliver_virtio), + VCPU_STAT("deliver_stop_signal", deliver_stop_signal), + VCPU_STAT("deliver_prefix_signal", deliver_prefix_signal), + VCPU_STAT("deliver_restart_signal", deliver_restart_signal), + VCPU_STAT("deliver_program", deliver_program), + VCPU_STAT("deliver_io", deliver_io), + VCPU_STAT("deliver_machine_check", deliver_machine_check), + VCPU_STAT("exit_wait_state", exit_wait_state), + VCPU_STAT("inject_ckc", inject_ckc), + VCPU_STAT("inject_cputm", inject_cputm), + VCPU_STAT("inject_external_call", inject_external_call), + VM_STAT("inject_float_mchk", inject_float_mchk), + VCPU_STAT("inject_emergency_signal", inject_emergency_signal), + VM_STAT("inject_io", inject_io), + VCPU_STAT("inject_mchk", inject_mchk), + VM_STAT("inject_pfault_done", inject_pfault_done), + VCPU_STAT("inject_program", inject_program), + VCPU_STAT("inject_restart", inject_restart), + VM_STAT("inject_service_signal", inject_service_signal), + VCPU_STAT("inject_set_prefix", inject_set_prefix), + VCPU_STAT("inject_stop_signal", inject_stop_signal), + VCPU_STAT("inject_pfault_init", inject_pfault_init), + VM_STAT("inject_virtio", inject_virtio), + VCPU_STAT("instruction_epsw", instruction_epsw), + VCPU_STAT("instruction_gs", instruction_gs), + VCPU_STAT("instruction_io_other", instruction_io_other), + VCPU_STAT("instruction_lpsw", instruction_lpsw), + VCPU_STAT("instruction_lpswe", instruction_lpswe), + VCPU_STAT("instruction_pfmf", instruction_pfmf), + VCPU_STAT("instruction_ptff", instruction_ptff), + VCPU_STAT("instruction_stidp", instruction_stidp), + VCPU_STAT("instruction_sck", instruction_sck), + VCPU_STAT("instruction_sckpf", instruction_sckpf), + VCPU_STAT("instruction_spx", instruction_spx), + VCPU_STAT("instruction_stpx", instruction_stpx), + VCPU_STAT("instruction_stap", instruction_stap), + VCPU_STAT("instruction_iske", instruction_iske), + VCPU_STAT("instruction_ri", instruction_ri), + VCPU_STAT("instruction_rrbe", instruction_rrbe), + VCPU_STAT("instruction_sske", instruction_sske), + VCPU_STAT("instruction_ipte_interlock", instruction_ipte_interlock), + VCPU_STAT("instruction_essa", instruction_essa), + VCPU_STAT("instruction_stsi", instruction_stsi), + VCPU_STAT("instruction_stfl", instruction_stfl), + VCPU_STAT("instruction_tb", instruction_tb), + VCPU_STAT("instruction_tpi", instruction_tpi), + VCPU_STAT("instruction_tprot", instruction_tprot), + VCPU_STAT("instruction_tsch", instruction_tsch), + VCPU_STAT("instruction_sthyi", instruction_sthyi), + VCPU_STAT("instruction_sie", instruction_sie), + VCPU_STAT("instruction_sigp_sense", instruction_sigp_sense), + VCPU_STAT("instruction_sigp_sense_running", instruction_sigp_sense_running), + VCPU_STAT("instruction_sigp_external_call", instruction_sigp_external_call), + VCPU_STAT("instruction_sigp_emergency", instruction_sigp_emergency), + VCPU_STAT("instruction_sigp_cond_emergency", instruction_sigp_cond_emergency), + VCPU_STAT("instruction_sigp_start", instruction_sigp_start), + VCPU_STAT("instruction_sigp_stop", instruction_sigp_stop), + VCPU_STAT("instruction_sigp_stop_store_status", instruction_sigp_stop_store_status), + VCPU_STAT("instruction_sigp_store_status", instruction_sigp_store_status), + VCPU_STAT("instruction_sigp_store_adtl_status", instruction_sigp_store_adtl_status), + VCPU_STAT("instruction_sigp_set_arch", instruction_sigp_arch), + VCPU_STAT("instruction_sigp_set_prefix", instruction_sigp_prefix), + VCPU_STAT("instruction_sigp_restart", instruction_sigp_restart), + VCPU_STAT("instruction_sigp_cpu_reset", instruction_sigp_cpu_reset), + VCPU_STAT("instruction_sigp_init_cpu_reset", instruction_sigp_init_cpu_reset), + VCPU_STAT("instruction_sigp_unknown", instruction_sigp_unknown), + VCPU_STAT("instruction_diag_10", diagnose_10), + VCPU_STAT("instruction_diag_44", diagnose_44), + VCPU_STAT("instruction_diag_9c", diagnose_9c), + VCPU_STAT("diag_9c_ignored", diagnose_9c_ignored), + VCPU_STAT("instruction_diag_258", diagnose_258), + VCPU_STAT("instruction_diag_308", diagnose_308), + VCPU_STAT("instruction_diag_500", diagnose_500), + VCPU_STAT("instruction_diag_other", diagnose_other), { NULL } }; @@ -3944,7 +3943,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, /* s390 will always inject the page directly */ } -bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) +bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) { /* * s390 will always inject the page directly, @@ -4337,8 +4336,9 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) store_regs_fmt2(vcpu, kvm_run); } -int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { + struct kvm_run *kvm_run = vcpu->run; int rc; if (kvm_run->immediate_exit) diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 4f6c22d72072..ef05b4e167fb 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -1000,8 +1000,6 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) handle_last_fault(vcpu, vsie_page); - if (need_resched()) - schedule(); if (test_cpu_flag(CIF_MCCK_PENDING)) s390_handle_mcck(); @@ -1185,6 +1183,7 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) kvm_s390_vcpu_has_irq(vcpu, 0) || kvm_s390_vcpu_sie_inhibited(vcpu)) break; + cond_resched(); } if (rc == -EFAULT) { diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 1a95d8809cc3..4b6903fbba4a 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -788,19 +788,19 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level) { const int asce_type = gmap->asce & _ASCE_TYPE_MASK; - unsigned long *table; + unsigned long *table = gmap->table; - if ((gmap->asce & _ASCE_TYPE_MASK) + 4 < (level * 4)) - return NULL; if (gmap_is_shadow(gmap) && gmap->removed) return NULL; + if (WARN_ON_ONCE(level > (asce_type >> 2) + 1)) + return NULL; + if (asce_type != _ASCE_TYPE_REGION1 && gaddr & (-1UL << (31 + (asce_type >> 2) * 11))) return NULL; - table = gmap->table; - switch (gmap->asce & _ASCE_TYPE_MASK) { + switch (asce_type) { case _ASCE_TYPE_REGION1: table += (gaddr & _REGION1_INDEX) >> _REGION1_SHIFT; if (level == 4) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index ac232f456396..a5eed844e948 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1691,14 +1691,6 @@ SYM_CODE_START(general_protection) jmp common_exception SYM_CODE_END(general_protection) -#ifdef CONFIG_KVM_GUEST -SYM_CODE_START(async_page_fault) - ASM_CLAC - pushl $do_async_page_fault - jmp common_exception_read_cr2 -SYM_CODE_END(async_page_fault) -#endif - SYM_CODE_START(rewind_stack_do_exit) /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 64fe3d82157e..eead1e2bebd5 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1202,10 +1202,6 @@ idtentry xendebug do_debug has_error_code=0 idtentry general_protection do_general_protection has_error_code=1 idtentry page_fault do_page_fault has_error_code=1 read_cr2=1 -#ifdef CONFIG_KVM_GUEST -idtentry async_page_fault do_async_page_fault has_error_code=1 read_cr2=1 -#endif - #ifdef CONFIG_X86_MCE idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 4e91f6118d5d..7a4d2062385c 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -83,6 +83,8 @@ #define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) /* Crash MSR available */ #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) +/* Support for debug MSRs available */ +#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) /* stimer Direct Mode is available */ #define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1c0b62d26962..1da5858501ca 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -83,6 +83,10 @@ #define KVM_REQ_GET_VMCS12_PAGES KVM_ARCH_REQ(24) #define KVM_REQ_APICV_UPDATE \ KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26) +#define KVM_REQ_HV_TLB_FLUSH \ + KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_APF_READY KVM_ARCH_REQ(28) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ @@ -107,15 +111,8 @@ #define UNMAPPED_GVA (~(gpa_t)0) /* KVM Hugepage definitions for x86 */ -enum { - PT_PAGE_TABLE_LEVEL = 1, - PT_DIRECTORY_LEVEL = 2, - PT_PDPE_LEVEL = 3, - /* set max level to the biggest one */ - PT_MAX_HUGEPAGE_LEVEL = PT_PDPE_LEVEL, -}; -#define KVM_NR_PAGE_SIZES (PT_MAX_HUGEPAGE_LEVEL - \ - PT_PAGE_TABLE_LEVEL + 1) +#define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G +#define KVM_NR_PAGE_SIZES (KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1) #define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9) #define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x)) #define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) @@ -124,7 +121,7 @@ enum { static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) { - /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */ + /* KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K) must be 0. */ return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); } @@ -164,9 +161,13 @@ enum kvm_reg { NR_VCPU_REGS, VCPU_EXREG_PDPTR = NR_VCPU_REGS, + VCPU_EXREG_CR0, VCPU_EXREG_CR3, + VCPU_EXREG_CR4, VCPU_EXREG_RFLAGS, VCPU_EXREG_SEGMENTS, + VCPU_EXREG_EXIT_INFO_1, + VCPU_EXREG_EXIT_INFO_2, }; enum { @@ -182,8 +183,10 @@ enum { enum exit_fastpath_completion { EXIT_FASTPATH_NONE, - EXIT_FASTPATH_SKIP_EMUL_INS, + EXIT_FASTPATH_REENTER_GUEST, + EXIT_FASTPATH_EXIT_HANDLED, }; +typedef enum exit_fastpath_completion fastpath_t; struct x86_emulate_ctxt; struct x86_exception; @@ -372,12 +375,12 @@ struct rsvd_bits_validate { }; struct kvm_mmu_root_info { - gpa_t cr3; + gpa_t pgd; hpa_t hpa; }; #define KVM_MMU_ROOT_INFO_INVALID \ - ((struct kvm_mmu_root_info) { .cr3 = INVALID_PAGE, .hpa = INVALID_PAGE }) + ((struct kvm_mmu_root_info) { .pgd = INVALID_PAGE, .hpa = INVALID_PAGE }) #define KVM_MMU_NUM_PREV_ROOTS 3 @@ -403,7 +406,7 @@ struct kvm_mmu { void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, const void *pte); hpa_t root_hpa; - gpa_t root_cr3; + gpa_t root_pgd; union kvm_mmu_role mmu_role; u8 root_level; u8 shadow_root_level; @@ -598,6 +601,7 @@ struct kvm_vcpu_arch { u64 ia32_xss; u64 microcode_version; u64 arch_capabilities; + u64 perf_capabilities; /* * Paging state of the vcpu @@ -650,7 +654,6 @@ struct kvm_vcpu_arch { u64 xcr0; u64 guest_supported_xcr0; - u32 guest_xstate_size; struct kvm_pio_request pio; void *pio_data; @@ -680,6 +683,7 @@ struct kvm_vcpu_arch { struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES]; int maxphyaddr; + int tdp_level; /* emulate context */ @@ -703,6 +707,7 @@ struct kvm_vcpu_arch { struct gfn_to_pfn_cache cache; } st; + u64 l1_tsc_offset; u64 tsc_offset; u64 last_guest_tsc; u64 last_host_tsc; @@ -762,14 +767,17 @@ struct kvm_vcpu_arch { struct { bool halted; - gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)]; + gfn_t gfns[ASYNC_PF_PER_VCPU]; struct gfn_to_hva_cache data; - u64 msr_val; + u64 msr_en_val; /* MSR_KVM_ASYNC_PF_EN */ + u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */ + u16 vec; u32 id; bool send_user_only; - u32 host_apf_reason; + u32 host_apf_flags; unsigned long nested_apf_token; bool delivery_as_pf_vmexit; + bool pageready_pending; } apf; /* OSVW MSRs (AMD only) */ @@ -855,6 +863,18 @@ struct kvm_apic_map { struct kvm_lapic *phys_map[]; }; +/* Hyper-V synthetic debugger (SynDbg)*/ +struct kvm_hv_syndbg { + struct { + u64 control; + u64 status; + u64 send_page; + u64 recv_page; + u64 pending_page; + } control; + u64 options; +}; + /* Hyper-V emulation context */ struct kvm_hv { struct mutex hv_lock; @@ -878,6 +898,7 @@ struct kvm_hv { atomic_t num_mismatched_vp_indexes; struct hv_partition_assist_pg *hv_pa_pg; + struct kvm_hv_syndbg hv_syndbg; }; enum kvm_irqchip_mode { @@ -1028,6 +1049,8 @@ struct kvm_vcpu_stat { u64 irq_injections; u64 nmi_injections; u64 req_event; + u64 halt_poll_success_ns; + u64 halt_poll_fail_ns; }; struct x86_instruction_info; @@ -1059,7 +1082,7 @@ struct kvm_x86_ops { void (*hardware_disable)(void); void (*hardware_unsetup)(void); bool (*cpu_has_accelerated_tpr)(void); - bool (*has_emulated_msr)(int index); + bool (*has_emulated_msr)(u32 index); void (*cpuid_update)(struct kvm_vcpu *vcpu); unsigned int vm_size; @@ -1085,8 +1108,6 @@ struct kvm_x86_ops { void (*set_segment)(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l); - void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu); - void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu); void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); int (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); @@ -1100,7 +1121,8 @@ struct kvm_x86_ops { unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); - void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa); + void (*tlb_flush_all)(struct kvm_vcpu *vcpu); + void (*tlb_flush_current)(struct kvm_vcpu *vcpu); int (*tlb_remote_flush)(struct kvm *kvm); int (*tlb_remote_flush_with_range)(struct kvm *kvm, struct kvm_tlb_range *range); @@ -1113,7 +1135,13 @@ struct kvm_x86_ops { */ void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr); - void (*run)(struct kvm_vcpu *vcpu); + /* + * Flush any TLB entries created by the guest. Like tlb_flush_gva(), + * does not need to flush GPA->HPA mappings. + */ + void (*tlb_flush_guest)(struct kvm_vcpu *vcpu); + + enum exit_fastpath_completion (*run)(struct kvm_vcpu *vcpu); int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); @@ -1126,8 +1154,8 @@ struct kvm_x86_ops { void (*set_nmi)(struct kvm_vcpu *vcpu); void (*queue_exception)(struct kvm_vcpu *vcpu); void (*cancel_injection)(struct kvm_vcpu *vcpu); - int (*interrupt_allowed)(struct kvm_vcpu *vcpu); - int (*nmi_allowed)(struct kvm_vcpu *vcpu); + int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection); + int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); bool (*get_nmi_mask)(struct kvm_vcpu *vcpu); void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked); void (*enable_nmi_window)(struct kvm_vcpu *vcpu); @@ -1141,7 +1169,7 @@ struct kvm_x86_ops { bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); - void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); + void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu); int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); @@ -1153,7 +1181,6 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); - u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu); /* Returns actual tsc_offset set in active VMCS */ u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); @@ -1163,10 +1190,8 @@ struct kvm_x86_ops { struct x86_instruction_info *info, enum x86_intercept_stage stage, struct x86_exception *exception); - void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu, - enum exit_fastpath_completion *exit_fastpath); + void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu); - int (*check_nested_events)(struct kvm_vcpu *vcpu); void (*request_immediate_exit)(struct kvm_vcpu *vcpu); void (*sched_in)(struct kvm_vcpu *kvm, int cpu); @@ -1199,6 +1224,7 @@ struct kvm_x86_ops { /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; + const struct kvm_x86_nested_ops *nested_ops; /* * Architecture specific hooks for vCPU blocking due to @@ -1226,18 +1252,10 @@ struct kvm_x86_ops { void (*setup_mce)(struct kvm_vcpu *vcpu); - int (*get_nested_state)(struct kvm_vcpu *vcpu, - struct kvm_nested_state __user *user_kvm_nested_state, - unsigned user_data_size); - int (*set_nested_state)(struct kvm_vcpu *vcpu, - struct kvm_nested_state __user *user_kvm_nested_state, - struct kvm_nested_state *kvm_state); - bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu); - - int (*smi_allowed)(struct kvm_vcpu *vcpu); + int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate); - int (*enable_smi_window)(struct kvm_vcpu *vcpu); + void (*enable_smi_window)(struct kvm_vcpu *vcpu); int (*mem_enc_op)(struct kvm *kvm, void __user *argp); int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); @@ -1245,14 +1263,28 @@ struct kvm_x86_ops { int (*get_msr_feature)(struct kvm_msr_entry *entry); - int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu, - uint16_t *vmcs_version); - uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu); - bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu); bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu); + + void (*migrate_timers)(struct kvm_vcpu *vcpu); +}; + +struct kvm_x86_nested_ops { + int (*check_events)(struct kvm_vcpu *vcpu); + bool (*hv_timer_pending)(struct kvm_vcpu *vcpu); + int (*get_state)(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + unsigned user_data_size); + int (*set_state)(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + struct kvm_nested_state *kvm_state); + bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu); + + int (*enable_evmcs)(struct kvm_vcpu *vcpu, + uint16_t *vmcs_version); + uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu); }; struct kvm_x86_init_ops { @@ -1451,6 +1483,8 @@ void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long pay void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); +bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, + struct x86_exception *fault); int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, gfn_t gfn, void *data, int offset, int len, u32 access); @@ -1478,6 +1512,8 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); void kvm_inject_nmi(struct kvm_vcpu *vcpu); +void kvm_update_dr7(struct kvm_vcpu *vcpu); + int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); @@ -1508,8 +1544,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); +void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gva_t gva, hpa_t root_hpa); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); -void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush); +void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush, + bool skip_mmu_sync); void kvm_configure_mmu(bool enable_tdp, int tdp_page_level); @@ -1573,8 +1612,6 @@ enum { }; #define HF_GIF_MASK (1 << 0) -#define HF_HIF_MASK (1 << 1) -#define HF_VINTR_MASK (1 << 2) #define HF_NMI_MASK (1 << 3) #define HF_IRET_MASK (1 << 4) #define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ @@ -1640,7 +1677,8 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); -bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu); +void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu); +bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu); extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 9b4df6eaa11a..57fd1966c4ea 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -88,11 +88,21 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, bool kvm_para_available(void); unsigned int kvm_arch_para_features(void); unsigned int kvm_arch_para_hints(void); -void kvm_async_pf_task_wait(u32 token, int interrupt_kernel); +void kvm_async_pf_task_wait_schedule(u32 token); void kvm_async_pf_task_wake(u32 token); -u32 kvm_read_and_reset_pf_reason(void); -extern void kvm_disable_steal_time(void); -void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address); +u32 kvm_read_and_reset_apf_flags(void); +void kvm_disable_steal_time(void); +bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token); + +DECLARE_STATIC_KEY_FALSE(kvm_async_pf_enabled); + +static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token) +{ + if (static_branch_unlikely(&kvm_async_pf_enabled)) + return __kvm_handle_async_pf(regs, token); + else + return false; +} #ifdef CONFIG_PARAVIRT_SPINLOCKS void __init kvm_spinlock_init(void); @@ -103,7 +113,7 @@ static inline void kvm_spinlock_init(void) #endif /* CONFIG_PARAVIRT_SPINLOCKS */ #else /* CONFIG_KVM_GUEST */ -#define kvm_async_pf_task_wait(T, I) do {} while(0) +#define kvm_async_pf_task_wait_schedule(T) do {} while(0) #define kvm_async_pf_task_wake(T) do {} while(0) static inline bool kvm_para_available(void) @@ -121,7 +131,7 @@ static inline unsigned int kvm_arch_para_hints(void) return 0; } -static inline u32 kvm_read_and_reset_pf_reason(void) +static inline u32 kvm_read_and_reset_apf_flags(void) { return 0; } @@ -130,6 +140,11 @@ static inline void kvm_disable_steal_time(void) { return; } + +static inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token) +{ + return false; +} #endif #endif /* _ASM_X86_KVM_PARA_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 6ece8561ba66..8a1f5382a4ea 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -96,7 +96,6 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u8 reserved_6[8]; /* Offset 0xe8 */ u64 avic_logical_id; /* Offset 0xf0 */ u64 avic_physical_id; /* Offset 0xf8 */ - u8 reserved_7[768]; }; @@ -203,8 +202,16 @@ struct __attribute__ ((__packed__)) vmcb_save_area { u64 last_excp_to; }; + +static inline void __unused_size_checks(void) +{ + BUILD_BUG_ON(sizeof(struct vmcb_save_area) != 0x298); + BUILD_BUG_ON(sizeof(struct vmcb_control_area) != 256); +} + struct __attribute__ ((__packed__)) vmcb { struct vmcb_control_area control; + u8 reserved_control[1024 - sizeof(struct vmcb_control_area)]; struct vmcb_save_area save; }; diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 5e090d1f03f8..cd7de4b401fe 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -527,10 +527,12 @@ struct vmx_msr_entry { /* * Exit Qualifications for entry failure during or after loading guest state */ -#define ENTRY_FAIL_DEFAULT 0 -#define ENTRY_FAIL_PDPTE 2 -#define ENTRY_FAIL_NMI 3 -#define ENTRY_FAIL_VMCS_LINK_PTR 4 +enum vm_entry_failure_code { + ENTRY_FAIL_DEFAULT = 0, + ENTRY_FAIL_PDPTE = 2, + ENTRY_FAIL_NMI = 3, + ENTRY_FAIL_VMCS_LINK_PTR = 4, +}; /* * Exit Qualifications for EPT Violations diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 96d9cd208610..6807153c0410 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -50,14 +50,12 @@ struct x86_init_resources { * @pre_vector_init: init code to run before interrupt vectors * are set up. * @intr_init: interrupt init code - * @trap_init: platform specific trap setup * @intr_mode_select: interrupt delivery mode selection * @intr_mode_init: interrupt delivery mode setup */ struct x86_init_irqs { void (*pre_vector_init)(void); void (*intr_init)(void); - void (*trap_init)(void); void (*intr_mode_select)(void); void (*intr_mode_init)(void); }; diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 3f3f780c8c65..17c5a038f42d 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -385,32 +385,48 @@ 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]; }; struct kvm_vmx_nested_state_hdr { + __u32 flags; __u64 vmxon_pa; __u64 vmcs12_pa; + __u64 preemption_timer_deadline; struct { __u16 flags; } smm; }; +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 */ struct kvm_nested_state { __u16 flags; @@ -419,6 +435,7 @@ 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]; @@ -431,6 +448,7 @@ struct kvm_nested_state { */ union { struct kvm_vmx_nested_state_data vmx[0]; + struct kvm_svm_nested_state_data svm[0]; } data; }; diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 2a8e0b6b9805..812e9b4c1114 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -31,6 +31,7 @@ #define KVM_FEATURE_PV_SEND_IPI 11 #define KVM_FEATURE_POLL_CONTROL 12 #define KVM_FEATURE_PV_SCHED_YIELD 13 +#define KVM_FEATURE_ASYNC_PF_INT 14 #define KVM_HINTS_REALTIME 0 @@ -50,6 +51,8 @@ #define MSR_KVM_STEAL_TIME 0x4b564d03 #define MSR_KVM_PV_EOI_EN 0x4b564d04 #define MSR_KVM_POLL_CONTROL 0x4b564d05 +#define MSR_KVM_ASYNC_PF_INT 0x4b564d06 +#define MSR_KVM_ASYNC_PF_ACK 0x4b564d07 struct kvm_steal_time { __u64 steal; @@ -81,6 +84,11 @@ struct kvm_clock_pairing { #define KVM_ASYNC_PF_ENABLED (1 << 0) #define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1) #define KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT (1 << 2) +#define KVM_ASYNC_PF_DELIVERY_AS_INT (1 << 3) + +/* MSR_KVM_ASYNC_PF_INT */ +#define KVM_ASYNC_PF_VEC_MASK GENMASK(7, 0) + /* Operations for KVM_HC_MMU_OP */ #define KVM_MMU_OP_WRITE_PTE 1 @@ -112,8 +120,13 @@ struct kvm_mmu_op_release_pt { #define KVM_PV_REASON_PAGE_READY 2 struct kvm_vcpu_pv_apf_data { - __u32 reason; - __u8 pad[60]; + /* Used for 'page not present' events delivered via #PF */ + __u32 flags; + + /* Used for 'page ready' events delivered via interrupt notification */ + __u32 token; + + __u8 pad[56]; __u32 enabled; }; diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index e95b72ec19bc..b8ff9e8ac0d5 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -150,6 +150,9 @@ { EXIT_REASON_UMWAIT, "UMWAIT" }, \ { EXIT_REASON_TPAUSE, "TPAUSE" } +#define VMX_EXIT_REASON_FLAGS \ + { VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" } + #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 6efe0410fb72..d6f22a3a1f7d 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -35,6 +35,8 @@ #include <asm/tlb.h> #include <asm/cpuidle_haltpoll.h> +DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled); + static int kvmapf = 1; static int __init parse_no_kvmapf(char *arg) @@ -73,7 +75,6 @@ struct kvm_task_sleep_node { struct swait_queue_head wq; u32 token; int cpu; - bool halted; }; static struct kvm_task_sleep_head { @@ -96,77 +97,64 @@ static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b, return NULL; } -/* - * @interrupt_kernel: Is this called from a routine which interrupts the kernel - * (other than user space)? - */ -void kvm_async_pf_task_wait(u32 token, int interrupt_kernel) +static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n) { u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; - struct kvm_task_sleep_node n, *e; - DECLARE_SWAITQUEUE(wait); - - rcu_irq_enter(); + struct kvm_task_sleep_node *e; raw_spin_lock(&b->lock); e = _find_apf_task(b, token); if (e) { /* dummy entry exist -> wake up was delivered ahead of PF */ hlist_del(&e->link); - kfree(e); raw_spin_unlock(&b->lock); - - rcu_irq_exit(); - return; + kfree(e); + return false; } - n.token = token; - n.cpu = smp_processor_id(); - n.halted = is_idle_task(current) || - (IS_ENABLED(CONFIG_PREEMPT_COUNT) - ? preempt_count() > 1 || rcu_preempt_depth() - : interrupt_kernel); - init_swait_queue_head(&n.wq); - hlist_add_head(&n.link, &b->list); + n->token = token; + n->cpu = smp_processor_id(); + init_swait_queue_head(&n->wq); + hlist_add_head(&n->link, &b->list); raw_spin_unlock(&b->lock); + return true; +} + +/* + * kvm_async_pf_task_wait_schedule - Wait for pagefault to be handled + * @token: Token to identify the sleep node entry + * + * Invoked from the async pagefault handling code or from the VM exit page + * fault handler. In both cases RCU is watching. + */ +void kvm_async_pf_task_wait_schedule(u32 token) +{ + struct kvm_task_sleep_node n; + DECLARE_SWAITQUEUE(wait); + + lockdep_assert_irqs_disabled(); + + if (!kvm_async_pf_queue_task(token, &n)) + return; for (;;) { - if (!n.halted) - prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE); if (hlist_unhashed(&n.link)) break; - rcu_irq_exit(); - - if (!n.halted) { - local_irq_enable(); - schedule(); - local_irq_disable(); - } else { - /* - * We cannot reschedule. So halt. - */ - native_safe_halt(); - local_irq_disable(); - } - - rcu_irq_enter(); + local_irq_enable(); + schedule(); + local_irq_disable(); } - if (!n.halted) - finish_swait(&n.wq, &wait); - - rcu_irq_exit(); - return; + finish_swait(&n.wq, &wait); } -EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait); +EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait_schedule); static void apf_task_wake_one(struct kvm_task_sleep_node *n) { hlist_del_init(&n->link); - if (n->halted) - smp_send_reschedule(n->cpu); - else if (swq_has_sleeper(&n->wq)) + if (swq_has_sleeper(&n->wq)) swake_up_one(&n->wq); } @@ -175,12 +163,13 @@ static void apf_task_wake_all(void) int i; for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) { - struct hlist_node *p, *next; struct kvm_task_sleep_head *b = &async_pf_sleepers[i]; + struct kvm_task_sleep_node *n; + struct hlist_node *p, *next; + raw_spin_lock(&b->lock); hlist_for_each_safe(p, next, &b->list) { - struct kvm_task_sleep_node *n = - hlist_entry(p, typeof(*n), link); + n = hlist_entry(p, typeof(*n), link); if (n->cpu == smp_processor_id()) apf_task_wake_one(n); } @@ -221,46 +210,61 @@ again: n->cpu = smp_processor_id(); init_swait_queue_head(&n->wq); hlist_add_head(&n->link, &b->list); - } else + } else { apf_task_wake_one(n); + } raw_spin_unlock(&b->lock); return; } EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake); -u32 kvm_read_and_reset_pf_reason(void) +u32 kvm_read_and_reset_apf_flags(void) { - u32 reason = 0; + u32 flags = 0; if (__this_cpu_read(apf_reason.enabled)) { - reason = __this_cpu_read(apf_reason.reason); - __this_cpu_write(apf_reason.reason, 0); + flags = __this_cpu_read(apf_reason.flags); + __this_cpu_write(apf_reason.flags, 0); } - return reason; + return flags; } -EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason); -NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason); +EXPORT_SYMBOL_GPL(kvm_read_and_reset_apf_flags); +NOKPROBE_SYMBOL(kvm_read_and_reset_apf_flags); -dotraplinkage void -do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) +bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token) { - switch (kvm_read_and_reset_pf_reason()) { - default: - do_page_fault(regs, error_code, address); - break; + u32 reason = kvm_read_and_reset_apf_flags(); + + switch (reason) { case KVM_PV_REASON_PAGE_NOT_PRESENT: - /* page is swapped out by the host. */ - kvm_async_pf_task_wait((u32)address, !user_mode(regs)); - break; case KVM_PV_REASON_PAGE_READY: + break; + default: + return false; + } + + /* + * If the host managed to inject an async #PF into an interrupt + * disabled region, then die hard as this is not going to end well + * and the host side is seriously broken. + */ + if (unlikely(!(regs->flags & X86_EFLAGS_IF))) + panic("Host injected async #PF in interrupt disabled region\n"); + + if (reason == KVM_PV_REASON_PAGE_NOT_PRESENT) { + if (unlikely(!(user_mode(regs)))) + panic("Host injected async #PF in kernel mode\n"); + /* Page is swapped out by the host. */ + kvm_async_pf_task_wait_schedule(token); + } else { rcu_irq_enter(); - kvm_async_pf_task_wake((u32)address); + kvm_async_pf_task_wake(token); rcu_irq_exit(); - break; } + return true; } -NOKPROBE_SYMBOL(do_async_page_fault); +NOKPROBE_SYMBOL(__kvm_handle_async_pf); static void __init paravirt_ops_setup(void) { @@ -306,11 +310,11 @@ static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val) static void kvm_guest_cpu_init(void) { if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) { - u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason)); + u64 pa; -#ifdef CONFIG_PREEMPTION - pa |= KVM_ASYNC_PF_SEND_ALWAYS; -#endif + WARN_ON_ONCE(!static_branch_likely(&kvm_async_pf_enabled)); + + pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason)); pa |= KVM_ASYNC_PF_ENABLED; if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT)) @@ -318,12 +322,12 @@ static void kvm_guest_cpu_init(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); - printk(KERN_INFO"KVM setup async PF for cpu %d\n", - smp_processor_id()); + pr_info("KVM setup async PF for cpu %d\n", smp_processor_id()); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) { unsigned long pa; + /* Size alignment is implied but just to make it explicit. */ BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4); __this_cpu_write(kvm_apic_eoi, 0); @@ -344,8 +348,7 @@ static void kvm_pv_disable_apf(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, 0); __this_cpu_write(apf_reason.enabled, 0); - printk(KERN_INFO"Unregister pv shared memory for cpu %d\n", - smp_processor_id()); + pr_info("Unregister pv shared memory for cpu %d\n", smp_processor_id()); } static void kvm_pv_guest_cpu_reboot(void *unused) @@ -592,12 +595,6 @@ static int kvm_cpu_down_prepare(unsigned int cpu) } #endif -static void __init kvm_apf_trap_init(void) -{ - update_intr_gate(X86_TRAP_PF, async_page_fault); -} - - static void kvm_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info) { @@ -632,8 +629,6 @@ static void __init kvm_guest_init(void) register_reboot_notifier(&kvm_pv_reboot_nb); for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) raw_spin_lock_init(&async_pf_sleepers[i].lock); - if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF)) - x86_init.irqs.trap_init = kvm_apf_trap_init; if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { has_steal_clock = 1; @@ -649,6 +644,9 @@ static void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) apic_set_eoi_write(kvm_guest_apic_eoi_write); + if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) + static_branch_enable(&kvm_async_pf_enabled); + #ifdef CONFIG_SMP smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus; smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 428186d9de46..4cc541051994 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -903,7 +903,5 @@ void __init trap_init(void) idt_setup_ist_traps(); - x86_init.irqs.trap_init(); - idt_setup_debugidt_traps(); } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 85f1a90c55cd..123f1c1f1788 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -79,7 +79,6 @@ struct x86_init_ops x86_init __initdata = { .irqs = { .pre_vector_init = init_ISA_irqs, .intr_init = native_init_IRQ, - .trap_init = x86_init_noop, .intr_mode_select = apic_intr_mode_select, .intr_mode_init = apic_intr_mode_init }, diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 901cd1fdecd9..253b8e875ccd 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -86,12 +86,10 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) best = kvm_find_cpuid_entry(vcpu, 0xD, 0); if (!best) { vcpu->arch.guest_supported_xcr0 = 0; - vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; } else { vcpu->arch.guest_supported_xcr0 = (best->eax | ((u64)best->edx << 32)) & supported_xcr0; - vcpu->arch.guest_xstate_size = best->ebx = - xstate_required_size(vcpu->arch.xcr0, false); + best->ebx = xstate_required_size(vcpu->arch.xcr0, false); } best = kvm_find_cpuid_entry(vcpu, 0xD, 1); @@ -124,8 +122,9 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) MSR_IA32_MISC_ENABLE_MWAIT); } - /* Update physical-address width */ + /* Note, maxphyaddr must be updated before tdp_level. */ vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + vcpu->arch.tdp_level = kvm_x86_ops.get_tdp_level(vcpu); kvm_mmu_reset_context(vcpu); kvm_pmu_refresh(vcpu); @@ -297,7 +296,7 @@ void kvm_set_cpu_caps(void) F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | 0 /* DS-CPL, VMX, SMX, EST */ | 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | - F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ | + F(FMA) | F(CX16) | 0 /* xTPR Update */ | F(PDCM) | F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) | F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | @@ -712,7 +711,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) (1 << KVM_FEATURE_ASYNC_PF_VMEXIT) | (1 << KVM_FEATURE_PV_SEND_IPI) | (1 << KVM_FEATURE_POLL_CONTROL) | - (1 << KVM_FEATURE_PV_SCHED_YIELD); + (1 << KVM_FEATURE_PV_SCHED_YIELD) | + (1 << KVM_FEATURE_ASYNC_PF_INT); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); @@ -728,6 +728,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) cpuid_entry_override(entry, CPUID_8000_0001_EDX); cpuid_entry_override(entry, CPUID_8000_0001_ECX); break; + case 0x80000006: + /* L2 cache and TLB: pass through host info. */ + break; case 0x80000007: /* Advanced power management */ /* invariant TSC is CPUID.80000007H:EDX[8] */ entry->edx &= (1 << 8); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 63a70f6a3df3..05434cd9342f 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -303,4 +303,9 @@ static __always_inline void kvm_cpu_cap_check_and_set(unsigned int x86_feature) kvm_cpu_cap_set(x86_feature); } +static inline bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa) +{ + return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu)); +} + #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index bddaba9c68dd..de5476f8683e 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5798,6 +5798,8 @@ writeback: } ctxt->eip = ctxt->_eip; + if (ctxt->mode != X86EMUL_MODE_PROT64) + ctxt->eip = (u32)ctxt->_eip; done: if (rc == X86EMUL_PROPAGATE_FAULT) { diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 6bc6d7613f76..238b78e069fe 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -21,6 +21,7 @@ #include "x86.h" #include "lapic.h" #include "ioapic.h" +#include "cpuid.h" #include "hyperv.h" #include <linux/cpu.h> @@ -266,6 +267,123 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, return ret; } +static bool kvm_hv_is_syndbg_enabled(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *entry; + + entry = kvm_find_cpuid_entry(vcpu, + HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, + 0); + if (!entry) + return false; + + return entry->eax & HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; +} + +static int kvm_hv_syndbg_complete_userspace(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_hv *hv = &kvm->arch.hyperv; + + if (vcpu->run->hyperv.u.syndbg.msr == HV_X64_MSR_SYNDBG_CONTROL) + hv->hv_syndbg.control.status = + vcpu->run->hyperv.u.syndbg.status; + return 1; +} + +static void syndbg_exit(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu); + struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv; + + hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNDBG; + hv_vcpu->exit.u.syndbg.msr = msr; + hv_vcpu->exit.u.syndbg.control = syndbg->control.control; + hv_vcpu->exit.u.syndbg.send_page = syndbg->control.send_page; + hv_vcpu->exit.u.syndbg.recv_page = syndbg->control.recv_page; + hv_vcpu->exit.u.syndbg.pending_page = syndbg->control.pending_page; + vcpu->arch.complete_userspace_io = + kvm_hv_syndbg_complete_userspace; + + kvm_make_request(KVM_REQ_HV_EXIT, vcpu); +} + +static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) +{ + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu); + + if (!kvm_hv_is_syndbg_enabled(vcpu) && !host) + return 1; + + trace_kvm_hv_syndbg_set_msr(vcpu->vcpu_id, + vcpu_to_hv_vcpu(vcpu)->vp_index, msr, data); + switch (msr) { + case HV_X64_MSR_SYNDBG_CONTROL: + syndbg->control.control = data; + if (!host) + syndbg_exit(vcpu, msr); + break; + case HV_X64_MSR_SYNDBG_STATUS: + syndbg->control.status = data; + break; + case HV_X64_MSR_SYNDBG_SEND_BUFFER: + syndbg->control.send_page = data; + break; + case HV_X64_MSR_SYNDBG_RECV_BUFFER: + syndbg->control.recv_page = data; + break; + case HV_X64_MSR_SYNDBG_PENDING_BUFFER: + syndbg->control.pending_page = data; + if (!host) + syndbg_exit(vcpu, msr); + break; + case HV_X64_MSR_SYNDBG_OPTIONS: + syndbg->options = data; + break; + default: + break; + } + + return 0; +} + +static int syndbg_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) +{ + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu); + + if (!kvm_hv_is_syndbg_enabled(vcpu) && !host) + return 1; + + switch (msr) { + case HV_X64_MSR_SYNDBG_CONTROL: + *pdata = syndbg->control.control; + break; + case HV_X64_MSR_SYNDBG_STATUS: + *pdata = syndbg->control.status; + break; + case HV_X64_MSR_SYNDBG_SEND_BUFFER: + *pdata = syndbg->control.send_page; + break; + case HV_X64_MSR_SYNDBG_RECV_BUFFER: + *pdata = syndbg->control.recv_page; + break; + case HV_X64_MSR_SYNDBG_PENDING_BUFFER: + *pdata = syndbg->control.pending_page; + break; + case HV_X64_MSR_SYNDBG_OPTIONS: + *pdata = syndbg->options; + break; + default: + break; + } + + trace_kvm_hv_syndbg_get_msr(vcpu->vcpu_id, + vcpu_to_hv_vcpu(vcpu)->vp_index, msr, + *pdata); + + return 0; +} + static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata, bool host) { @@ -800,6 +918,8 @@ static bool kvm_hv_msr_partition_wide(u32 msr) case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_SYNDBG_OPTIONS: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: r = true; break; } @@ -1061,6 +1181,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, if (!host) return 1; break; + case HV_X64_MSR_SYNDBG_OPTIONS: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: + return syndbg_set_msr(vcpu, msr, data, host); default: vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", msr, data); @@ -1190,7 +1313,8 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 0; } -static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, + bool host) { u64 data = 0; struct kvm *kvm = vcpu->kvm; @@ -1227,6 +1351,9 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case HV_X64_MSR_TSC_EMULATION_STATUS: data = hv->hv_tsc_emulation_status; break; + case HV_X64_MSR_SYNDBG_OPTIONS: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: + return syndbg_get_msr(vcpu, msr, pdata, host); default: vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; @@ -1316,7 +1443,7 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host) int r; mutex_lock(&vcpu->kvm->arch.hyperv.hv_lock); - r = kvm_hv_get_msr_pw(vcpu, msr, pdata); + r = kvm_hv_get_msr_pw(vcpu, msr, pdata, host); mutex_unlock(&vcpu->kvm->arch.hyperv.hv_lock); return r; } else @@ -1425,8 +1552,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa, * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't * analyze it here, flush TLB regardless of the specified address space. */ - kvm_make_vcpus_request_mask(kvm, - KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP, + kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, NULL, vcpu_mask, &hv_vcpu->tlb_flush); ret_success: @@ -1530,7 +1656,7 @@ ret_success: bool kvm_hv_hypercall_enabled(struct kvm *kvm) { - return READ_ONCE(kvm->arch.hyperv.hv_hypercall) & HV_X64_MSR_HYPERCALL_ENABLE; + return READ_ONCE(kvm->arch.hyperv.hv_guest_os_id) != 0; } static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) @@ -1709,6 +1835,34 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) } ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, true, false); break; + case HVCALL_POST_DEBUG_DATA: + case HVCALL_RETRIEVE_DEBUG_DATA: + if (unlikely(fast)) { + ret = HV_STATUS_INVALID_PARAMETER; + break; + } + fallthrough; + case HVCALL_RESET_DEBUG_SESSION: { + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu); + + if (!kvm_hv_is_syndbg_enabled(vcpu)) { + ret = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + } + + if (!(syndbg->options & HV_X64_SYNDBG_OPTION_USE_HCALLS)) { + ret = HV_STATUS_OPERATION_DENIED; + break; + } + vcpu->run->exit_reason = KVM_EXIT_HYPERV; + vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; + vcpu->run->hyperv.u.hcall.input = param; + vcpu->run->hyperv.u.hcall.params[0] = ingpa; + vcpu->run->hyperv.u.hcall.params[1] = outgpa; + vcpu->arch.complete_userspace_io = + kvm_hv_hypercall_complete_userspace; + return 0; + } default: ret = HV_STATUS_INVALID_HYPERCALL_CODE; break; @@ -1796,12 +1950,15 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, { .function = HYPERV_CPUID_FEATURES }, { .function = HYPERV_CPUID_ENLIGHTMENT_INFO }, { .function = HYPERV_CPUID_IMPLEMENT_LIMITS }, + { .function = HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS }, + { .function = HYPERV_CPUID_SYNDBG_INTERFACE }, + { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES }, { .function = HYPERV_CPUID_NESTED_FEATURES }, }; int i, nent = ARRAY_SIZE(cpuid_entries); - if (kvm_x86_ops.nested_get_evmcs_version) - evmcs_ver = kvm_x86_ops.nested_get_evmcs_version(vcpu); + if (kvm_x86_ops.nested_ops->get_evmcs_version) + evmcs_ver = kvm_x86_ops.nested_ops->get_evmcs_version(vcpu); /* Skip NESTED_FEATURES if eVMCS is not supported */ if (!evmcs_ver) @@ -1821,7 +1978,7 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, case HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS: memcpy(signature, "Linux KVM Hv", 12); - ent->eax = HYPERV_CPUID_NESTED_FEATURES; + ent->eax = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES; ent->ebx = signature[0]; ent->ecx = signature[1]; ent->edx = signature[2]; @@ -1860,6 +2017,10 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + ent->ebx |= HV_DEBUGGING; + ent->edx |= HV_X64_GUEST_DEBUGGING_AVAILABLE; + ent->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; + /* * Direct Synthetic timers only make sense with in-kernel * LAPIC @@ -1903,6 +2064,24 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, break; + case HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS: + memcpy(signature, "Linux KVM Hv", 12); + + ent->eax = 0; + ent->ebx = signature[0]; + ent->ecx = signature[1]; + ent->edx = signature[2]; + break; + + case HYPERV_CPUID_SYNDBG_INTERFACE: + memcpy(signature, "VS#1\0\0\0\0\0\0\0\0", 12); + ent->eax = signature[0]; + break; + + case HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES: + ent->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + break; + default: break; } diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 757cb578101c..e68c6c2e9649 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -23,6 +23,33 @@ #include <linux/kvm_host.h> +/* + * The #defines related to the synthetic debugger are required by KDNet, but + * they are not documented in the Hyper-V TLFS because the synthetic debugger + * functionality has been deprecated and is subject to removal in future + * versions of Windows. + */ +#define HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS 0x40000080 +#define HYPERV_CPUID_SYNDBG_INTERFACE 0x40000081 +#define HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES 0x40000082 + +/* + * Hyper-V synthetic debugger platform capabilities + * These are HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX bits. + */ +#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING BIT(1) + +/* Hyper-V Synthetic debug options MSR */ +#define HV_X64_MSR_SYNDBG_CONTROL 0x400000F1 +#define HV_X64_MSR_SYNDBG_STATUS 0x400000F2 +#define HV_X64_MSR_SYNDBG_SEND_BUFFER 0x400000F3 +#define HV_X64_MSR_SYNDBG_RECV_BUFFER 0x400000F4 +#define HV_X64_MSR_SYNDBG_PENDING_BUFFER 0x400000F5 +#define HV_X64_MSR_SYNDBG_OPTIONS 0x400000FF + +/* Hyper-V HV_X64_MSR_SYNDBG_OPTIONS bits */ +#define HV_X64_SYNDBG_OPTION_USE_HCALLS BIT(2) + static inline struct kvm_vcpu_hv *vcpu_to_hv_vcpu(struct kvm_vcpu *vcpu) { return &vcpu->arch.hyperv; @@ -46,6 +73,11 @@ static inline struct kvm_vcpu *synic_to_vcpu(struct kvm_vcpu_hv_synic *synic) return hv_vcpu_to_vcpu(container_of(synic, struct kvm_vcpu_hv, synic)); } +static inline struct kvm_hv_syndbg *vcpu_to_hv_syndbg(struct kvm_vcpu *vcpu) +{ + return &vcpu->kvm->arch.hyperv.hv_syndbg; +} + int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 2fb2e3c80724..660401700075 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -3,8 +3,8 @@ #define __KVM_IO_APIC_H #include <linux/kvm_host.h> - #include <kvm/iodev.h> +#include "irq.h" struct kvm; struct kvm_vcpu; @@ -108,11 +108,7 @@ do { \ static inline int ioapic_in_kernel(struct kvm *kvm) { - int mode = kvm->arch.irqchip_mode; - - /* Matches smp_wmb() when setting irqchip_mode */ - smp_rmb(); - return mode == KVM_IRQCHIP_KERNEL; + return irqchip_kernel(kvm); } void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index e330e7d125f7..99d118ffc67d 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -83,6 +83,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ } +EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr); /* * check if there is pending interrupt without @@ -159,6 +160,8 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu) { __kvm_migrate_apic_timer(vcpu); __kvm_migrate_pit_timer(vcpu); + if (kvm_x86_ops.migrate_timers) + kvm_x86_ops.migrate_timers(vcpu); } bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args) diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index f173ab6b407e..9b64abf9b3f1 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -16,7 +16,6 @@ #include <linux/spinlock.h> #include <kvm/iodev.h> -#include "ioapic.h" #include "lapic.h" #define PIC_NUM_PINS 16 @@ -66,15 +65,6 @@ void kvm_pic_destroy(struct kvm *kvm); int kvm_pic_read_irq(struct kvm *kvm); void kvm_pic_update_irq(struct kvm_pic *s); -static inline int pic_in_kernel(struct kvm *kvm) -{ - int mode = kvm->arch.irqchip_mode; - - /* Matches smp_wmb() when setting irqchip_mode */ - smp_rmb(); - return mode == KVM_IRQCHIP_KERNEL; -} - static inline int irqchip_split(struct kvm *kvm) { int mode = kvm->arch.irqchip_mode; @@ -93,6 +83,11 @@ static inline int irqchip_kernel(struct kvm *kvm) return mode == KVM_IRQCHIP_KERNEL; } +static inline int pic_in_kernel(struct kvm *kvm) +{ + return irqchip_kernel(kvm); +} + static inline int irqchip_in_kernel(struct kvm *kvm) { int mode = kvm->arch.irqchip_mode; diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 62558b9bdda7..ff2d0e9ca3bc 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -116,8 +116,9 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS; - if (tmask & vcpu->arch.cr0_guest_owned_bits) - kvm_x86_ops.decache_cr0_guest_bits(vcpu); + if ((tmask & vcpu->arch.cr0_guest_owned_bits) && + !kvm_register_is_available(vcpu, VCPU_EXREG_CR0)) + kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_CR0); return vcpu->arch.cr0 & mask; } @@ -129,8 +130,9 @@ static inline ulong kvm_read_cr0(struct kvm_vcpu *vcpu) static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR4_GUEST_BITS; - if (tmask & vcpu->arch.cr4_guest_owned_bits) - kvm_x86_ops.decache_cr4_guest_bits(vcpu); + if ((tmask & vcpu->arch.cr4_guest_owned_bits) && + !kvm_register_is_available(vcpu, VCPU_EXREG_CR4)) + kvm_x86_ops.cache_reg(vcpu, VCPU_EXREG_CR4); return vcpu->arch.cr4 & mask; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 9af25c97612a..34a7e0533dad 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -36,6 +36,7 @@ #include <linux/jump_label.h> #include "kvm_cache_regs.h" #include "irq.h" +#include "ioapic.h" #include "trace.h" #include "x86.h" #include "cpuid.h" @@ -110,11 +111,18 @@ static inline u32 kvm_x2apic_id(struct kvm_lapic *apic) return apic->vcpu->vcpu_id; } -bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu) +static bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu) { return pi_inject_timer && kvm_vcpu_apicv_active(vcpu); } -EXPORT_SYMBOL_GPL(kvm_can_post_timer_interrupt); + +bool kvm_can_use_hv_timer(struct kvm_vcpu *vcpu) +{ + return kvm_x86_ops.set_hv_timer + && !(kvm_mwait_in_guest(vcpu->kvm) || + kvm_can_post_timer_interrupt(vcpu)); +} +EXPORT_SYMBOL_GPL(kvm_can_use_hv_timer); static bool kvm_use_posted_timer_interrupt(struct kvm_vcpu *vcpu) { @@ -1593,7 +1601,7 @@ static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic) } } -static void apic_timer_expired(struct kvm_lapic *apic) +static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn) { struct kvm_vcpu *vcpu = apic->vcpu; struct kvm_timer *ktimer = &apic->lapic_timer; @@ -1604,6 +1612,12 @@ static void apic_timer_expired(struct kvm_lapic *apic) if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use) ktimer->expired_tscdeadline = ktimer->tscdeadline; + if (!from_timer_fn && vcpu->arch.apicv_active) { + WARN_ON(kvm_get_running_vcpu() != vcpu); + kvm_apic_inject_pending_timer_irqs(apic); + return; + } + if (kvm_use_posted_timer_interrupt(apic->vcpu)) { if (apic->lapic_timer.timer_advance_ns) __kvm_wait_lapic_expire(vcpu); @@ -1643,18 +1657,23 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) expire = ktime_sub_ns(expire, ktimer->timer_advance_ns); hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_HARD); } else - apic_timer_expired(apic); + apic_timer_expired(apic, false); local_irq_restore(flags); } +static inline u64 tmict_to_ns(struct kvm_lapic *apic, u32 tmict) +{ + return (u64)tmict * APIC_BUS_CYCLE_NS * (u64)apic->divide_count; +} + static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_divisor) { ktime_t now, remaining; u64 ns_remaining_old, ns_remaining_new; - apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT) - * APIC_BUS_CYCLE_NS * apic->divide_count; + apic->lapic_timer.period = + tmict_to_ns(apic, kvm_lapic_get_reg(apic, APIC_TMICT)); limit_periodic_timer_frequency(apic); now = ktime_get(); @@ -1672,14 +1691,15 @@ static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_diviso apic->lapic_timer.target_expiration = ktime_add_ns(now, ns_remaining_new); } -static bool set_target_expiration(struct kvm_lapic *apic) +static bool set_target_expiration(struct kvm_lapic *apic, u32 count_reg) { ktime_t now; u64 tscl = rdtsc(); + s64 deadline; now = ktime_get(); - apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT) - * APIC_BUS_CYCLE_NS * apic->divide_count; + apic->lapic_timer.period = + tmict_to_ns(apic, kvm_lapic_get_reg(apic, APIC_TMICT)); if (!apic->lapic_timer.period) { apic->lapic_timer.tscdeadline = 0; @@ -1687,10 +1707,32 @@ static bool set_target_expiration(struct kvm_lapic *apic) } limit_periodic_timer_frequency(apic); + deadline = apic->lapic_timer.period; + + if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) { + if (unlikely(count_reg != APIC_TMICT)) { + deadline = tmict_to_ns(apic, + kvm_lapic_get_reg(apic, count_reg)); + if (unlikely(deadline <= 0)) + deadline = apic->lapic_timer.period; + else if (unlikely(deadline > apic->lapic_timer.period)) { + pr_info_ratelimited( + "kvm: vcpu %i: requested lapic timer restore with " + "starting count register %#x=%u (%lld ns) > initial count (%lld ns). " + "Using initial count to start timer.\n", + apic->vcpu->vcpu_id, + count_reg, + kvm_lapic_get_reg(apic, count_reg), + deadline, apic->lapic_timer.period); + kvm_lapic_set_reg(apic, count_reg, 0); + deadline = apic->lapic_timer.period; + } + } + } apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) + - nsec_to_cycles(apic->vcpu, apic->lapic_timer.period); - apic->lapic_timer.target_expiration = ktime_add_ns(now, apic->lapic_timer.period); + nsec_to_cycles(apic->vcpu, deadline); + apic->lapic_timer.target_expiration = ktime_add_ns(now, deadline); return true; } @@ -1723,7 +1765,7 @@ static void start_sw_period(struct kvm_lapic *apic) if (ktime_after(ktime_get(), apic->lapic_timer.target_expiration)) { - apic_timer_expired(apic); + apic_timer_expired(apic, false); if (apic_lvtt_oneshot(apic)) return; @@ -1760,7 +1802,7 @@ static bool start_hv_timer(struct kvm_lapic *apic) bool expired; WARN_ON(preemptible()); - if (!kvm_x86_ops.set_hv_timer) + if (!kvm_can_use_hv_timer(vcpu)) return false; if (!ktimer->tscdeadline) @@ -1785,7 +1827,7 @@ static bool start_hv_timer(struct kvm_lapic *apic) if (atomic_read(&ktimer->pending)) { cancel_hv_timer(apic); } else if (expired) { - apic_timer_expired(apic); + apic_timer_expired(apic, false); cancel_hv_timer(apic); } } @@ -1833,9 +1875,9 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) /* If the preempt notifier has already run, it also called apic_timer_expired */ if (!apic->lapic_timer.hv_timer_in_use) goto out; - WARN_ON(swait_active(&vcpu->wq)); + WARN_ON(rcuwait_active(&vcpu->wait)); cancel_hv_timer(apic); - apic_timer_expired(apic); + apic_timer_expired(apic, false); if (apic_lvtt_period(apic) && apic->lapic_timer.period) { advance_periodic_target_expiration(apic); @@ -1872,17 +1914,22 @@ void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu) restart_apic_timer(apic); } -static void start_apic_timer(struct kvm_lapic *apic) +static void __start_apic_timer(struct kvm_lapic *apic, u32 count_reg) { atomic_set(&apic->lapic_timer.pending, 0); if ((apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) - && !set_target_expiration(apic)) + && !set_target_expiration(apic, count_reg)) return; restart_apic_timer(apic); } +static void start_apic_timer(struct kvm_lapic *apic) +{ + __start_apic_timer(apic, APIC_TMICT); +} + static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) { bool lvt0_in_nmi_mode = apic_lvt_nmi_mode(lvt0_val); @@ -2336,7 +2383,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer); - apic_timer_expired(apic); + apic_timer_expired(apic, true); if (lapic_is_periodic(apic)) { advance_periodic_target_expiration(apic); @@ -2493,6 +2540,14 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { memcpy(s->regs, vcpu->arch.apic->regs, sizeof(*s)); + + /* + * Get calculated timer current count for remaining timer period (if + * any) and store it in the returned register set. + */ + __kvm_lapic_set_reg(s->regs, APIC_TMCCT, + __apic_read(vcpu->arch.apic, APIC_TMCCT)); + return kvm_apic_state_fixup(vcpu, s, false); } @@ -2520,7 +2575,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) apic_update_lvtt(apic); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); update_divide_count(apic); - start_apic_timer(apic); + __start_apic_timer(apic, APIC_TMCCT); kvm_apic_update_apicv(vcpu); apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index a0ffb4331418..754f29beb83e 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -161,9 +161,14 @@ static inline u32 kvm_lapic_get_reg(struct kvm_lapic *apic, int reg_off) return *((u32 *) (apic->regs + reg_off)); } +static inline void __kvm_lapic_set_reg(char *regs, int reg_off, u32 val) +{ + *((u32 *) (regs + reg_off)) = val; +} + static inline void kvm_lapic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val) { - *((u32 *) (apic->regs + reg_off)) = val; + __kvm_lapic_set_reg(apic->regs, reg_off, val); } extern struct static_key kvm_no_apic_vcpu; @@ -245,7 +250,7 @@ void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu); void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu); bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu); void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu); -bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu); +bool kvm_can_use_hv_timer(struct kvm_vcpu *vcpu); static inline enum lapic_mode kvm_apic_mode(u64 apic_base) { diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 8a3b1bce722a..0ad06bfe2c2c 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -51,13 +51,13 @@ static inline u64 rsvd_bits(int s, int e) return ((1ULL << (e - s + 1)) - 1) << s; } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask); +void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask); void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots); -void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); +void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool accessed_dirty, gpa_t new_eptp); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index fd59fee84631..fdd05c233308 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -16,6 +16,7 @@ */ #include "irq.h" +#include "ioapic.h" #include "mmu.h" #include "x86.h" #include "kvm_cache_regs.h" @@ -78,6 +79,9 @@ module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops, &nx_huge_pages_recovery_ratio, 0644); __MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); +static bool __read_mostly force_flush_and_sync_on_reuse; +module_param_named(flush_on_reuse, force_flush_and_sync_on_reuse, bool, 0644); + /* * When setting this variable to true it enables Two-Dimensional-Paging * where the hardware walks 2 page tables: @@ -244,7 +248,6 @@ static u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */ static u64 __read_mostly shadow_user_mask; static u64 __read_mostly shadow_accessed_mask; static u64 __read_mostly shadow_dirty_mask; -static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_mmio_value; static u64 __read_mostly shadow_mmio_access_mask; static u64 __read_mostly shadow_present_mask; @@ -331,19 +334,19 @@ static void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, kvm_flush_remote_tlbs_with_range(kvm, &range); } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask) +void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask) { BUG_ON((u64)(unsigned)access_mask != access_mask); - BUG_ON((mmio_mask & mmio_value) != mmio_value); + WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len)); + WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask); shadow_mmio_value = mmio_value | SPTE_MMIO_MASK; - shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; shadow_mmio_access_mask = access_mask; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); static bool is_mmio_spte(u64 spte) { - return (spte & shadow_mmio_mask) == shadow_mmio_value; + return (spte & SPTE_SPECIAL_MASK) == SPTE_MMIO_MASK; } static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) @@ -566,7 +569,6 @@ static void kvm_mmu_reset_all_pte_masks(void) shadow_dirty_mask = 0; shadow_nx_mask = 0; shadow_x_mask = 0; - shadow_mmio_mask = 0; shadow_present_mask = 0; shadow_acc_track_mask = 0; @@ -583,16 +585,15 @@ static void kvm_mmu_reset_all_pte_masks(void) * the most significant bits of legal physical address space. */ shadow_nonpresent_or_rsvd_mask = 0; - low_phys_bits = boot_cpu_data.x86_cache_bits; - if (boot_cpu_data.x86_cache_bits < - 52 - shadow_nonpresent_or_rsvd_mask_len) { + low_phys_bits = boot_cpu_data.x86_phys_bits; + if (boot_cpu_has_bug(X86_BUG_L1TF) && + !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >= + 52 - shadow_nonpresent_or_rsvd_mask_len)) { + low_phys_bits = boot_cpu_data.x86_cache_bits + - shadow_nonpresent_or_rsvd_mask_len; shadow_nonpresent_or_rsvd_mask = - rsvd_bits(boot_cpu_data.x86_cache_bits - - shadow_nonpresent_or_rsvd_mask_len, - boot_cpu_data.x86_cache_bits - 1); - low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len; - } else - WARN_ON_ONCE(boot_cpu_has_bug(X86_BUG_L1TF)); + rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1); + } shadow_nonpresent_or_rsvd_lower_gfn_mask = GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT); @@ -620,7 +621,7 @@ static int is_large_pte(u64 pte) static int is_last_spte(u64 pte, int level) { - if (level == PT_PAGE_TABLE_LEVEL) + if (level == PG_LEVEL_4K) return 1; if (is_large_pte(pte)) return 1; @@ -1196,7 +1197,7 @@ static void update_gfn_disallow_lpage_count(struct kvm_memory_slot *slot, struct kvm_lpage_info *linfo; int i; - for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { + for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); linfo->disallow_lpage += count; WARN_ON(linfo->disallow_lpage < 0); @@ -1225,7 +1226,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) slot = __gfn_to_memslot(slots, gfn); /* the non-leaf shadow pages are keeping readonly. */ - if (sp->role.level > PT_PAGE_TABLE_LEVEL) + if (sp->role.level > PG_LEVEL_4K) return kvm_slot_page_track_add_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE); @@ -1253,7 +1254,7 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) gfn = sp->gfn; slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); - if (sp->role.level > PT_PAGE_TABLE_LEVEL) + if (sp->role.level > PG_LEVEL_4K) return kvm_slot_page_track_remove_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE); @@ -1398,7 +1399,7 @@ static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level, unsigned long idx; idx = gfn_to_index(gfn, slot->base_gfn, level); - return &slot->arch.rmap[level - PT_PAGE_TABLE_LEVEL][idx]; + return &slot->arch.rmap[level - PG_LEVEL_4K][idx]; } static struct kvm_rmap_head *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, @@ -1529,8 +1530,7 @@ static void drop_spte(struct kvm *kvm, u64 *sptep) static bool __drop_large_spte(struct kvm *kvm, u64 *sptep) { if (is_large_pte(*sptep)) { - WARN_ON(page_header(__pa(sptep))->role.level == - PT_PAGE_TABLE_LEVEL); + WARN_ON(page_header(__pa(sptep))->role.level == PG_LEVEL_4K); drop_spte(kvm, sptep); --kvm->stat.lpages; return true; @@ -1682,7 +1682,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, while (mask) { rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), - PT_PAGE_TABLE_LEVEL, slot); + PG_LEVEL_4K, slot); __rmap_write_protect(kvm, rmap_head, false); /* clear the first set bit */ @@ -1708,7 +1708,7 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, while (mask) { rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), - PT_PAGE_TABLE_LEVEL, slot); + PG_LEVEL_4K, slot); __rmap_clear_dirty(kvm, rmap_head); /* clear the first set bit */ @@ -1760,7 +1760,7 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, int i; bool write_protected = false; - for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { + for (i = PG_LEVEL_4K; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { rmap_head = __gfn_to_rmap(gfn, i, slot); write_protected |= __rmap_write_protect(kvm, rmap_head, true); } @@ -1948,8 +1948,8 @@ static int kvm_handle_hva_range(struct kvm *kvm, gfn_start = hva_to_gfn_memslot(hva_start, memslot); gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); - for_each_slot_rmap_range(memslot, PT_PAGE_TABLE_LEVEL, - PT_MAX_HUGEPAGE_LEVEL, + for_each_slot_rmap_range(memslot, PG_LEVEL_4K, + KVM_MAX_HUGEPAGE_LEVEL, gfn_start, gfn_end - 1, &iterator) ret |= handler(kvm, iterator.rmap, memslot, @@ -2153,10 +2153,6 @@ static int nonpaging_sync_page(struct kvm_vcpu *vcpu, return 0; } -static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root) -{ -} - static void nonpaging_update_pte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, const void *pte) @@ -2313,7 +2309,7 @@ static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu, return; if (local_flush) - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } #ifdef CONFIG_KVM_MMU_AUDIT @@ -2347,7 +2343,7 @@ static bool kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, if (!s->unsync) continue; - WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL); + WARN_ON(s->role.level != PG_LEVEL_4K); ret |= kvm_sync_page(vcpu, s, invalid_list); } @@ -2376,7 +2372,7 @@ static int mmu_pages_next(struct kvm_mmu_pages *pvec, int level = sp->role.level; parents->idx[level-1] = idx; - if (level == PT_PAGE_TABLE_LEVEL) + if (level == PG_LEVEL_4K) break; parents->parent[level-2] = sp; @@ -2398,7 +2394,7 @@ static int mmu_pages_first(struct kvm_mmu_pages *pvec, sp = pvec->page[0].sp; level = sp->role.level; - WARN_ON(level == PT_PAGE_TABLE_LEVEL); + WARN_ON(level == PG_LEVEL_4K); parents->parent[level-2] = sp; @@ -2520,11 +2516,11 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, break; WARN_ON(!list_empty(&invalid_list)); - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } if (sp->unsync_children) - kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); __clear_sp_write_flooding_count(sp); trace_kvm_mmu_get_page(sp, false); @@ -2546,11 +2542,10 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, * be inconsistent with guest page table. */ account_shadowed(vcpu->kvm, sp); - if (level == PT_PAGE_TABLE_LEVEL && - rmap_write_protect(vcpu, gfn)) + if (level == PG_LEVEL_4K && rmap_write_protect(vcpu, gfn)) kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn, 1); - if (level > PT_PAGE_TABLE_LEVEL && need_sync) + if (level > PG_LEVEL_4K && need_sync) flush |= kvm_sync_pages(vcpu, gfn, &invalid_list); } clear_page(sp->spt); @@ -2601,7 +2596,7 @@ static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator, static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator) { - if (iterator->level < PT_PAGE_TABLE_LEVEL) + if (iterator->level < PG_LEVEL_4K) return false; iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level); @@ -2722,7 +2717,7 @@ static int mmu_zap_unsync_children(struct kvm *kvm, struct mmu_page_path parents; struct kvm_mmu_pages pages; - if (parent->role.level == PT_PAGE_TABLE_LEVEL) + if (parent->role.level == PG_LEVEL_4K) return 0; while (mmu_unsync_walk(parent, &pages)) { @@ -2921,7 +2916,7 @@ static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, if (sp->unsync) continue; - WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL); + WARN_ON(sp->role.level != PG_LEVEL_4K); kvm_unsync_page(vcpu, sp); } @@ -3020,7 +3015,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (!speculative) spte |= spte_shadow_accessed_mask(spte); - if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) && + if (level > PG_LEVEL_4K && (pte_access & ACC_EXEC_MASK) && is_nx_huge_page_enabled()) { pte_access &= ~ACC_EXEC_MASK; } @@ -3033,7 +3028,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (pte_access & ACC_USER_MASK) spte |= shadow_user_mask; - if (level > PT_PAGE_TABLE_LEVEL) + if (level > PG_LEVEL_4K) spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) spte |= kvm_x86_ops.get_mt_mask(vcpu, gfn, @@ -3103,8 +3098,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, * If we overwrite a PTE page pointer with a 2MB PMD, unlink * the parent of the now unreachable PTE. */ - if (level > PT_PAGE_TABLE_LEVEL && - !is_large_pte(*sptep)) { + if (level > PG_LEVEL_4K && !is_large_pte(*sptep)) { struct kvm_mmu_page *child; u64 pte = *sptep; @@ -3125,7 +3119,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (set_spte_ret & SET_SPTE_WRITE_PROTECTED_PT) { if (write_fault) ret = RET_PF_EMULATE; - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } if (set_spte_ret & SET_SPTE_NEED_REMOTE_TLB_FLUSH || flush) @@ -3228,7 +3222,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) if (sp_ad_disabled(sp)) return; - if (sp->role.level > PT_PAGE_TABLE_LEVEL) + if (sp->role.level > PG_LEVEL_4K) return; __direct_pte_prefetch(vcpu, sp, sptep); @@ -3241,12 +3235,8 @@ static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn, pte_t *pte; int level; - BUILD_BUG_ON(PT_PAGE_TABLE_LEVEL != (int)PG_LEVEL_4K || - PT_DIRECTORY_LEVEL != (int)PG_LEVEL_2M || - PT_PDPE_LEVEL != (int)PG_LEVEL_1G); - if (!PageCompound(pfn_to_page(pfn)) && !kvm_is_zone_device_pfn(pfn)) - return PT_PAGE_TABLE_LEVEL; + return PG_LEVEL_4K; /* * Note, using the already-retrieved memslot and __gfn_to_hva_memslot() @@ -3260,7 +3250,7 @@ static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn, pte = lookup_address_in_mm(vcpu->kvm->mm, hva, &level); if (unlikely(!pte)) - return PT_PAGE_TABLE_LEVEL; + return PG_LEVEL_4K; return level; } @@ -3274,28 +3264,28 @@ static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t mask; int level; - if (unlikely(max_level == PT_PAGE_TABLE_LEVEL)) - return PT_PAGE_TABLE_LEVEL; + if (unlikely(max_level == PG_LEVEL_4K)) + return PG_LEVEL_4K; if (is_error_noslot_pfn(pfn) || kvm_is_reserved_pfn(pfn)) - return PT_PAGE_TABLE_LEVEL; + return PG_LEVEL_4K; slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, true); if (!slot) - return PT_PAGE_TABLE_LEVEL; + return PG_LEVEL_4K; max_level = min(max_level, max_page_level); - for ( ; max_level > PT_PAGE_TABLE_LEVEL; max_level--) { + for ( ; max_level > PG_LEVEL_4K; max_level--) { linfo = lpage_info_slot(gfn, slot, max_level); if (!linfo->disallow_lpage) break; } - if (max_level == PT_PAGE_TABLE_LEVEL) - return PT_PAGE_TABLE_LEVEL; + if (max_level == PG_LEVEL_4K) + return PG_LEVEL_4K; level = host_pfn_mapping_level(vcpu, gfn, pfn, slot); - if (level == PT_PAGE_TABLE_LEVEL) + if (level == PG_LEVEL_4K) return level; level = min(level, max_level); @@ -3317,7 +3307,7 @@ static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it, int level = *levelp; u64 spte = *it.sptep; - if (it.level == level && level > PT_PAGE_TABLE_LEVEL && + if (it.level == level && level > PG_LEVEL_4K && is_nx_huge_page_enabled() && is_shadow_present_pte(spte) && !is_large_pte(spte)) { @@ -3574,7 +3564,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * * See the comments in kvm_arch_commit_memory_region(). */ - if (sp->role.level > PT_PAGE_TABLE_LEVEL) + if (sp->role.level > PG_LEVEL_4K) break; } @@ -3666,7 +3656,7 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, &invalid_list); mmu->root_hpa = INVALID_PAGE; } - mmu->root_cr3 = 0; + mmu->root_pgd = 0; } kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); @@ -3686,58 +3676,64 @@ static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn) return ret; } -static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) +static hpa_t mmu_alloc_root(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gva, + u8 level, bool direct) { struct kvm_mmu_page *sp; + + spin_lock(&vcpu->kvm->mmu_lock); + + if (make_mmu_pages_available(vcpu)) { + spin_unlock(&vcpu->kvm->mmu_lock); + return INVALID_PAGE; + } + sp = kvm_mmu_get_page(vcpu, gfn, gva, level, direct, ACC_ALL); + ++sp->root_count; + + spin_unlock(&vcpu->kvm->mmu_lock); + return __pa(sp->spt); +} + +static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) +{ + u8 shadow_root_level = vcpu->arch.mmu->shadow_root_level; + hpa_t root; unsigned i; - if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) { - spin_lock(&vcpu->kvm->mmu_lock); - if(make_mmu_pages_available(vcpu) < 0) { - spin_unlock(&vcpu->kvm->mmu_lock); + if (shadow_root_level >= PT64_ROOT_4LEVEL) { + root = mmu_alloc_root(vcpu, 0, 0, shadow_root_level, true); + if (!VALID_PAGE(root)) return -ENOSPC; - } - sp = kvm_mmu_get_page(vcpu, 0, 0, - vcpu->arch.mmu->shadow_root_level, 1, ACC_ALL); - ++sp->root_count; - spin_unlock(&vcpu->kvm->mmu_lock); - vcpu->arch.mmu->root_hpa = __pa(sp->spt); - } else if (vcpu->arch.mmu->shadow_root_level == PT32E_ROOT_LEVEL) { + vcpu->arch.mmu->root_hpa = root; + } else if (shadow_root_level == PT32E_ROOT_LEVEL) { for (i = 0; i < 4; ++i) { - hpa_t root = vcpu->arch.mmu->pae_root[i]; + MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu->pae_root[i])); - MMU_WARN_ON(VALID_PAGE(root)); - spin_lock(&vcpu->kvm->mmu_lock); - if (make_mmu_pages_available(vcpu) < 0) { - spin_unlock(&vcpu->kvm->mmu_lock); + root = mmu_alloc_root(vcpu, i << (30 - PAGE_SHIFT), + i << 30, PT32_ROOT_LEVEL, true); + if (!VALID_PAGE(root)) return -ENOSPC; - } - sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT), - i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL); - root = __pa(sp->spt); - ++sp->root_count; - spin_unlock(&vcpu->kvm->mmu_lock); vcpu->arch.mmu->pae_root[i] = root | PT_PRESENT_MASK; } vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root); } else BUG(); - /* root_cr3 is ignored for direct MMUs. */ - vcpu->arch.mmu->root_cr3 = 0; + /* root_pgd is ignored for direct MMUs. */ + vcpu->arch.mmu->root_pgd = 0; return 0; } static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) { - struct kvm_mmu_page *sp; u64 pdptr, pm_mask; - gfn_t root_gfn, root_cr3; + gfn_t root_gfn, root_pgd; + hpa_t root; int i; - root_cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); - root_gfn = root_cr3 >> PAGE_SHIFT; + root_pgd = vcpu->arch.mmu->get_guest_pgd(vcpu); + root_gfn = root_pgd >> PAGE_SHIFT; if (mmu_check_root(vcpu, root_gfn)) return 1; @@ -3747,22 +3743,14 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) * write-protect the guests page table root. */ if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) { - hpa_t root = vcpu->arch.mmu->root_hpa; - - MMU_WARN_ON(VALID_PAGE(root)); + MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu->root_hpa)); - spin_lock(&vcpu->kvm->mmu_lock); - if (make_mmu_pages_available(vcpu) < 0) { - spin_unlock(&vcpu->kvm->mmu_lock); + root = mmu_alloc_root(vcpu, root_gfn, 0, + vcpu->arch.mmu->shadow_root_level, false); + if (!VALID_PAGE(root)) return -ENOSPC; - } - sp = kvm_mmu_get_page(vcpu, root_gfn, 0, - vcpu->arch.mmu->shadow_root_level, 0, ACC_ALL); - root = __pa(sp->spt); - ++sp->root_count; - spin_unlock(&vcpu->kvm->mmu_lock); vcpu->arch.mmu->root_hpa = root; - goto set_root_cr3; + goto set_root_pgd; } /* @@ -3775,9 +3763,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK; for (i = 0; i < 4; ++i) { - hpa_t root = vcpu->arch.mmu->pae_root[i]; - - MMU_WARN_ON(VALID_PAGE(root)); + MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu->pae_root[i])); if (vcpu->arch.mmu->root_level == PT32E_ROOT_LEVEL) { pdptr = vcpu->arch.mmu->get_pdptr(vcpu, i); if (!(pdptr & PT_PRESENT_MASK)) { @@ -3788,17 +3774,11 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) if (mmu_check_root(vcpu, root_gfn)) return 1; } - spin_lock(&vcpu->kvm->mmu_lock); - if (make_mmu_pages_available(vcpu) < 0) { - spin_unlock(&vcpu->kvm->mmu_lock); - return -ENOSPC; - } - sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL, - 0, ACC_ALL); - root = __pa(sp->spt); - ++sp->root_count; - spin_unlock(&vcpu->kvm->mmu_lock); + root = mmu_alloc_root(vcpu, root_gfn, i << 30, + PT32_ROOT_LEVEL, false); + if (!VALID_PAGE(root)) + return -ENOSPC; vcpu->arch.mmu->pae_root[i] = root | pm_mask; } vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root); @@ -3828,8 +3808,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->lm_root); } -set_root_cr3: - vcpu->arch.mmu->root_cr3 = root_cr3; +set_root_pgd: + vcpu->arch.mmu->root_pgd = root_pgd; return 0; } @@ -4083,18 +4063,16 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, bool *writable) { - struct kvm_memory_slot *slot; + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); bool async; - /* - * Don't expose private memslots to L2. - */ - if (is_guest_mode(vcpu) && !kvm_is_visible_gfn(vcpu->kvm, gfn)) { + /* Don't expose private memslots to L2. */ + if (is_guest_mode(vcpu) && !kvm_is_visible_memslot(slot)) { *pfn = KVM_PFN_NOSLOT; + *writable = false; return false; } - slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); async = false; *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable); if (!async) @@ -4135,7 +4113,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, return r; if (lpage_disallowed) - max_level = PT_PAGE_TABLE_LEVEL; + max_level = PG_LEVEL_4K; if (fast_page_fault(vcpu, gpa, error_code)) return RET_PF_RETRY; @@ -4171,7 +4149,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, /* This path builds a PAE pagetable, we can map 2mb pages at maximum. */ return direct_page_fault(vcpu, gpa & PAGE_MASK, error_code, prefault, - PT_DIRECTORY_LEVEL, false); + PG_LEVEL_2M, false); } int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, @@ -4186,7 +4164,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, #endif vcpu->arch.l1tf_flush_l1d = true; - switch (vcpu->arch.apf.host_apf_reason) { + switch (vcpu->arch.apf.host_apf_flags) { default: trace_kvm_page_fault(fault_address, error_code); @@ -4196,13 +4174,13 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, insn_len); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: - vcpu->arch.apf.host_apf_reason = 0; + vcpu->arch.apf.host_apf_flags = 0; local_irq_disable(); - kvm_async_pf_task_wait(fault_address, 0); + kvm_async_pf_task_wait_schedule(fault_address); local_irq_enable(); break; case KVM_PV_REASON_PAGE_READY: - vcpu->arch.apf.host_apf_reason = 0; + vcpu->arch.apf.host_apf_flags = 0; local_irq_disable(); kvm_async_pf_task_wake(fault_address); local_irq_enable(); @@ -4217,8 +4195,8 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, { int max_level; - for (max_level = PT_MAX_HUGEPAGE_LEVEL; - max_level > PT_PAGE_TABLE_LEVEL; + for (max_level = KVM_MAX_HUGEPAGE_LEVEL; + max_level > PG_LEVEL_4K; max_level--) { int page_num = KVM_PAGES_PER_HPAGE(max_level); gfn_t base = (gpa >> PAGE_SHIFT) & ~(page_num - 1); @@ -4237,7 +4215,7 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu, context->page_fault = nonpaging_page_fault; context->gva_to_gpa = nonpaging_gva_to_gpa; context->sync_page = nonpaging_sync_page; - context->invlpg = nonpaging_invlpg; + context->invlpg = NULL; context->update_pte = nonpaging_update_pte; context->root_level = 0; context->shadow_root_level = PT32E_ROOT_LEVEL; @@ -4245,51 +4223,50 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu, context->nx = false; } -static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t cr3, +static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd, union kvm_mmu_page_role role) { - return (role.direct || cr3 == root->cr3) && + return (role.direct || pgd == root->pgd) && VALID_PAGE(root->hpa) && page_header(root->hpa) && role.word == page_header(root->hpa)->role.word; } /* - * Find out if a previously cached root matching the new CR3/role is available. + * Find out if a previously cached root matching the new pgd/role is available. * The current root is also inserted into the cache. * If a matching root was found, it is assigned to kvm_mmu->root_hpa and true is * returned. * Otherwise, the LRU root from the cache is assigned to kvm_mmu->root_hpa and * false is returned. This root should now be freed by the caller. */ -static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3, +static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_pgd, union kvm_mmu_page_role new_role) { uint i; struct kvm_mmu_root_info root; struct kvm_mmu *mmu = vcpu->arch.mmu; - root.cr3 = mmu->root_cr3; + root.pgd = mmu->root_pgd; root.hpa = mmu->root_hpa; - if (is_root_usable(&root, new_cr3, new_role)) + if (is_root_usable(&root, new_pgd, new_role)) return true; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { swap(root, mmu->prev_roots[i]); - if (is_root_usable(&root, new_cr3, new_role)) + if (is_root_usable(&root, new_pgd, new_role)) break; } mmu->root_hpa = root.hpa; - mmu->root_cr3 = root.cr3; + mmu->root_pgd = root.pgd; return i < KVM_MMU_NUM_PREV_ROOTS; } -static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3, - union kvm_mmu_page_role new_role, - bool skip_tlb_flush) +static bool fast_pgd_switch(struct kvm_vcpu *vcpu, gpa_t new_pgd, + union kvm_mmu_page_role new_role) { struct kvm_mmu *mmu = vcpu->arch.mmu; @@ -4299,70 +4276,59 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3, * later if necessary. */ if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL && - mmu->root_level >= PT64_ROOT_4LEVEL) { - if (mmu_check_root(vcpu, new_cr3 >> PAGE_SHIFT)) - return false; - - if (cached_root_available(vcpu, new_cr3, new_role)) { - /* - * It is possible that the cached previous root page is - * obsolete because of a change in the MMU generation - * number. However, changing the generation number is - * accompanied by KVM_REQ_MMU_RELOAD, which will free - * the root set here and allocate a new one. - */ - kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); - if (!skip_tlb_flush) { - kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - } - - /* - * The last MMIO access's GVA and GPA are cached in the - * VCPU. When switching to a new CR3, that GVA->GPA - * mapping may no longer be valid. So clear any cached - * MMIO info even when we don't need to sync the shadow - * page tables. - */ - vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); - - __clear_sp_write_flooding_count( - page_header(mmu->root_hpa)); - - return true; - } - } + mmu->root_level >= PT64_ROOT_4LEVEL) + return !mmu_check_root(vcpu, new_pgd >> PAGE_SHIFT) && + cached_root_available(vcpu, new_pgd, new_role); return false; } -static void __kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, +static void __kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, union kvm_mmu_page_role new_role, - bool skip_tlb_flush) + bool skip_tlb_flush, bool skip_mmu_sync) { - if (!fast_cr3_switch(vcpu, new_cr3, new_role, skip_tlb_flush)) - kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, - KVM_MMU_ROOT_CURRENT); + if (!fast_pgd_switch(vcpu, new_pgd, new_role)) { + kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, KVM_MMU_ROOT_CURRENT); + return; + } + + /* + * It's possible that the cached previous root page is obsolete because + * of a change in the MMU generation number. However, changing the + * generation number is accompanied by KVM_REQ_MMU_RELOAD, which will + * free the root set here and allocate a new one. + */ + kvm_make_request(KVM_REQ_LOAD_MMU_PGD, vcpu); + + if (!skip_mmu_sync || force_flush_and_sync_on_reuse) + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + if (!skip_tlb_flush || force_flush_and_sync_on_reuse) + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + + /* + * The last MMIO access's GVA and GPA are cached in the VCPU. When + * switching to a new CR3, that GVA->GPA mapping may no longer be + * valid. So clear any cached MMIO info even when we don't need to sync + * the shadow page tables. + */ + vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); + + __clear_sp_write_flooding_count(page_header(vcpu->arch.mmu->root_hpa)); } -void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush) +void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush, + bool skip_mmu_sync) { - __kvm_mmu_new_cr3(vcpu, new_cr3, kvm_mmu_calc_root_page_role(vcpu), - skip_tlb_flush); + __kvm_mmu_new_pgd(vcpu, new_pgd, kvm_mmu_calc_root_page_role(vcpu), + skip_tlb_flush, skip_mmu_sync); } -EXPORT_SYMBOL_GPL(kvm_mmu_new_cr3); +EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); static unsigned long get_cr3(struct kvm_vcpu *vcpu) { return kvm_read_cr3(vcpu); } -static void inject_page_fault(struct kvm_vcpu *vcpu, - struct x86_exception *fault) -{ - vcpu->arch.mmu->inject_page_fault(vcpu, fault); -} - static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned int access, int *nr_present) { @@ -4391,11 +4357,11 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, gpte &= level - mmu->last_nonleaf_level; /* - * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set - * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means - * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then. + * PG_LEVEL_4K always terminates. The RHS has bit 7 set + * iff level <= PG_LEVEL_4K, which for our purpose means + * level == PG_LEVEL_4K; set PT_PAGE_SIZE_MASK in gpte then. */ - gpte |= level - PT_PAGE_TABLE_LEVEL - 1; + gpte |= level - PG_LEVEL_4K - 1; return gpte & PT_PAGE_SIZE_MASK; } @@ -4909,7 +4875,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only); role.base.ad_disabled = (shadow_accessed_mask == 0); - role.base.level = kvm_x86_ops.get_tdp_level(vcpu); + role.base.level = vcpu->arch.tdp_level; role.base.direct = true; role.base.gpte_is_8_bytes = true; @@ -4928,9 +4894,9 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->mmu_role.as_u64 = new_role.as_u64; context->page_fault = kvm_tdp_page_fault; context->sync_page = nonpaging_sync_page; - context->invlpg = nonpaging_invlpg; + context->invlpg = NULL; context->update_pte = nonpaging_update_pte; - context->shadow_root_level = kvm_x86_ops.get_tdp_level(vcpu); + context->shadow_root_level = vcpu->arch.tdp_level; context->direct_map = true; context->get_guest_pgd = get_cr3; context->get_pdptr = kvm_pdptr_read; @@ -4986,7 +4952,7 @@ kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) return role; } -void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) +void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer) { struct kvm_mmu *context = vcpu->arch.mmu; union kvm_mmu_role new_role = @@ -4995,11 +4961,11 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) if (new_role.as_u64 == context->mmu_role.as_u64) return; - if (!is_paging(vcpu)) + if (!(cr0 & X86_CR0_PG)) nonpaging_init_context(vcpu, context); - else if (is_long_mode(vcpu)) + else if (efer & EFER_LMA) paging64_init_context(vcpu, context); - else if (is_pae(vcpu)) + else if (cr4 & X86_CR4_PAE) paging32E_init_context(vcpu, context); else paging32_init_context(vcpu, context); @@ -5047,7 +5013,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty, execonly, level); - __kvm_mmu_new_cr3(vcpu, new_eptp, new_role.base, false); + __kvm_mmu_new_pgd(vcpu, new_eptp, new_role.base, true, true); if (new_role.as_u64 == context->mmu_role.as_u64) return; @@ -5077,7 +5043,11 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu) { struct kvm_mmu *context = vcpu->arch.mmu; - kvm_init_shadow_mmu(vcpu); + kvm_init_shadow_mmu(vcpu, + kvm_read_cr0_bits(vcpu, X86_CR0_PG), + kvm_read_cr4_bits(vcpu, X86_CR4_PAE), + vcpu->arch.efer); + context->get_guest_pgd = get_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; @@ -5097,6 +5067,12 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) g_context->inject_page_fault = kvm_inject_page_fault; /* + * L2 page tables are never shadowed, so there is no need to sync + * SPTEs. + */ + g_context->invlpg = NULL; + + /* * Note that arch.mmu->gva_to_gpa translates l2_gpa to l1_gpa using * L1's nested page tables (e.g. EPT12). The nested translation * of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using @@ -5183,7 +5159,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) if (r) goto out; kvm_mmu_load_pgd(vcpu); - kvm_x86_ops.tlb_flush(vcpu, true); + kvm_x86_ops.tlb_flush_current(vcpu); out: return r; } @@ -5202,7 +5178,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, const void *new) { - if (sp->role.level != PT_PAGE_TABLE_LEVEL) { + if (sp->role.level != PG_LEVEL_4K) { ++vcpu->kvm->stat.mmu_pde_zapped; return; } @@ -5260,7 +5236,7 @@ static bool detect_write_flooding(struct kvm_mmu_page *sp) * Skip write-flooding detected for the sp whose level is 1, because * it can become unsync, then the guest page is not write-protected. */ - if (sp->role.level == PT_PAGE_TABLE_LEVEL) + if (sp->role.level == PG_LEVEL_4K) return false; atomic_inc(&sp->write_flooding_count); @@ -5497,37 +5473,54 @@ emulate: } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); -void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) +void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + gva_t gva, hpa_t root_hpa) { - struct kvm_mmu *mmu = vcpu->arch.mmu; int i; - /* INVLPG on a * non-canonical address is a NOP according to the SDM. */ - if (is_noncanonical_address(gva, vcpu)) + /* It's actually a GPA for vcpu->arch.guest_mmu. */ + if (mmu != &vcpu->arch.guest_mmu) { + /* INVLPG on a non-canonical address is a NOP according to the SDM. */ + if (is_noncanonical_address(gva, vcpu)) + return; + + kvm_x86_ops.tlb_flush_gva(vcpu, gva); + } + + if (!mmu->invlpg) return; - mmu->invlpg(vcpu, gva, mmu->root_hpa); + if (root_hpa == INVALID_PAGE) { + mmu->invlpg(vcpu, gva, mmu->root_hpa); - /* - * INVLPG is required to invalidate any global mappings for the VA, - * irrespective of PCID. Since it would take us roughly similar amount - * of work to determine whether any of the prev_root mappings of the VA - * is marked global, or to just sync it blindly, so we might as well - * just always sync it. - * - * Mappings not reachable via the current cr3 or the prev_roots will be - * synced when switching to that cr3, so nothing needs to be done here - * for them. - */ - for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) - if (VALID_PAGE(mmu->prev_roots[i].hpa)) - mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); + /* + * INVLPG is required to invalidate any global mappings for the VA, + * irrespective of PCID. Since it would take us roughly similar amount + * of work to determine whether any of the prev_root mappings of the VA + * is marked global, or to just sync it blindly, so we might as well + * just always sync it. + * + * Mappings not reachable via the current cr3 or the prev_roots will be + * synced when switching to that cr3, so nothing needs to be done here + * for them. + */ + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) + if (VALID_PAGE(mmu->prev_roots[i].hpa)) + mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); + } else { + mmu->invlpg(vcpu, gva, root_hpa); + } +} +EXPORT_SYMBOL_GPL(kvm_mmu_invalidate_gva); - kvm_x86_ops.tlb_flush_gva(vcpu, gva); +void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) +{ + kvm_mmu_invalidate_gva(vcpu, vcpu->arch.mmu, gva, INVALID_PAGE); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); + void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) { struct kvm_mmu *mmu = vcpu->arch.mmu; @@ -5541,7 +5534,7 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { if (VALID_PAGE(mmu->prev_roots[i].hpa) && - pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].cr3)) { + pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd)) { mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); tlb_flush = true; } @@ -5574,9 +5567,9 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_page_level) if (tdp_enabled) max_page_level = tdp_page_level; else if (boot_cpu_has(X86_FEATURE_GBPAGES)) - max_page_level = PT_PDPE_LEVEL; + max_page_level = PG_LEVEL_1G; else - max_page_level = PT_DIRECTORY_LEVEL; + max_page_level = PG_LEVEL_2M; } EXPORT_SYMBOL_GPL(kvm_configure_mmu); @@ -5632,24 +5625,24 @@ static __always_inline bool slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { - return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, - PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); + return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K, + KVM_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } static __always_inline bool slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { - return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1, - PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); + return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K + 1, + KVM_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); } static __always_inline bool slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { - return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, - PT_PAGE_TABLE_LEVEL, lock_flush_tlb); + return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K, + PG_LEVEL_4K, lock_flush_tlb); } static void free_mmu_pages(struct kvm_mmu *mmu) @@ -5672,7 +5665,7 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) * SVM's 32-bit NPT support, TDP paging doesn't use PAE paging and can * skip allocating the PDP table. */ - if (tdp_enabled && kvm_x86_ops.get_tdp_level(vcpu) > PT32E_ROOT_LEVEL) + if (tdp_enabled && vcpu->arch.tdp_level > PT32E_ROOT_LEVEL) return 0; page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_DMA32); @@ -5695,13 +5688,13 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; vcpu->arch.root_mmu.root_hpa = INVALID_PAGE; - vcpu->arch.root_mmu.root_cr3 = 0; + vcpu->arch.root_mmu.root_pgd = 0; vcpu->arch.root_mmu.translate_gpa = translate_gpa; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) vcpu->arch.root_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; vcpu->arch.guest_mmu.root_hpa = INVALID_PAGE; - vcpu->arch.guest_mmu.root_cr3 = 0; + vcpu->arch.guest_mmu.root_pgd = 0; vcpu->arch.guest_mmu.translate_gpa = translate_gpa; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; @@ -5859,7 +5852,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) continue; slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, - PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL, + PG_LEVEL_4K, + KVM_MAX_HUGEPAGE_LEVEL, start, end - 1, true); } } @@ -5881,7 +5875,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, spin_lock(&kvm->mmu_lock); flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, - start_level, PT_MAX_HUGEPAGE_LEVEL, false); + start_level, KVM_MAX_HUGEPAGE_LEVEL, false); spin_unlock(&kvm->mmu_lock); /* @@ -6142,27 +6136,18 @@ static void kvm_set_mmio_spte_mask(void) u64 mask; /* - * Set the reserved bits and the present bit of an paging-structure - * entry to generate page fault with PFER.RSV = 1. + * Set a reserved PA bit in MMIO SPTEs to generate page faults with + * PFEC.RSVD=1 on MMIO accesses. 64-bit PTEs (PAE, x86-64, and EPT + * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports + * 52-bit physical addresses then there are no reserved PA bits in the + * PTEs and so the reserved PA approach must be disabled. */ + if (shadow_phys_bits < 52) + mask = BIT_ULL(51) | PT_PRESENT_MASK; + else + mask = 0; - /* - * Mask the uppermost physical address bit, which would be reserved as - * long as the supported physical address width is less than 52. - */ - mask = 1ull << 51; - - /* Set the present bit. */ - mask |= 1ull; - - /* - * If reserved bit is not supported, clear the present bit to disable - * mmio page fault. - */ - if (shadow_phys_bits == 52) - mask &= ~1ull; - - kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK); + kvm_mmu_set_mmio_spte_mask(mask, ACC_WRITE_MASK | ACC_USER_MASK); } static bool get_nx_auto_mode(void) diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index ddc1ec3bdacd..a7bcde34d1f2 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -61,7 +61,7 @@ static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn, { int index, val; - index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL); + index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); val = slot->arch.gfn_track[mode][index]; @@ -151,7 +151,7 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn, if (!slot) return false; - index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL); + index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); return !!READ_ONCE(slot->arch.gfn_track[mode][index]); } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 9bdf9b7d9a96..38c576495048 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -75,7 +75,7 @@ #define PT_GUEST_ACCESSED_MASK (1 << PT_GUEST_ACCESSED_SHIFT) #define gpte_to_gfn_lvl FNAME(gpte_to_gfn_lvl) -#define gpte_to_gfn(pte) gpte_to_gfn_lvl((pte), PT_PAGE_TABLE_LEVEL) +#define gpte_to_gfn(pte) gpte_to_gfn_lvl((pte), PG_LEVEL_4K) /* * The guest_walker structure emulates the behavior of the hardware page @@ -198,7 +198,7 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, !(gpte & PT_GUEST_ACCESSED_MASK)) goto no_present; - if (FNAME(is_rsvd_bits_set)(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) + if (FNAME(is_rsvd_bits_set)(vcpu->arch.mmu, gpte, PG_LEVEL_4K)) goto no_present; return false; @@ -436,7 +436,7 @@ retry_walk: gfn = gpte_to_gfn_lvl(pte, walker->level); gfn += (addr & PT_LVL_OFFSET_MASK(walker->level)) >> PAGE_SHIFT; - if (PTTYPE == 32 && walker->level == PT_DIRECTORY_LEVEL && is_cpuid_PSE36()) + if (PTTYPE == 32 && walker->level > PG_LEVEL_4K && is_cpuid_PSE36()) gfn += pse36_gfn_delta(pte); real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault); @@ -552,7 +552,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * we call mmu_set_spte() with host_writable = true because * pte_prefetch_gfn_to_pfn always gets a writable pfn. */ - mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn, + mmu_set_spte(vcpu, spte, pte_access, 0, PG_LEVEL_4K, gfn, pfn, true, true); kvm_release_pfn_clean(pfn); @@ -575,7 +575,7 @@ static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu, u64 mask; int r, index; - if (level == PT_PAGE_TABLE_LEVEL) { + if (level == PG_LEVEL_4K) { mask = PTE_PREFETCH_NUM * sizeof(pt_element_t) - 1; base_gpa = pte_gpa & ~mask; index = (pte_gpa - base_gpa) / sizeof(pt_element_t); @@ -600,7 +600,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, sp = page_header(__pa(sptep)); - if (sp->role.level > PT_PAGE_TABLE_LEVEL) + if (sp->role.level > PG_LEVEL_4K) return; if (sp->role.direct) @@ -812,7 +812,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, if (!r) { pgprintk("%s: guest page fault\n", __func__); if (!prefault) - inject_page_fault(vcpu, &walker.fault); + kvm_inject_emulated_page_fault(vcpu, &walker.fault); return RET_PF_RETRY; } @@ -828,7 +828,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code, &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable); if (lpage_disallowed || is_self_change_mapping) - max_level = PT_PAGE_TABLE_LEVEL; + max_level = PG_LEVEL_4K; else max_level = walker.level; @@ -884,7 +884,7 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) { int offset = 0; - WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL); + WARN_ON(sp->role.level != PG_LEVEL_4K); if (PTTYPE == 32) offset = sp->role.quadrant << PT64_LEVEL_BITS; @@ -1070,7 +1070,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) host_writable = sp->spt[i] & SPTE_HOST_WRITEABLE; set_spte_ret |= set_spte(vcpu, &sp->spt[i], - pte_access, PT_PAGE_TABLE_LEVEL, + pte_access, PG_LEVEL_4K, gfn, spte_to_pfn(sp->spt[i]), true, false, host_writable); } diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index ca39f62aabc6..9d2844f87f6d 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -100,7 +100,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) sp = page_header(__pa(sptep)); if (sp->unsync) { - if (level != PT_PAGE_TABLE_LEVEL) { + if (level != PG_LEVEL_4K) { audit_printk(vcpu->kvm, "unsync sp: %p " "level = %d\n", sp, level); return; @@ -176,7 +176,7 @@ static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp) { int i; - if (sp->role.level != PT_PAGE_TABLE_LEVEL) + if (sp->role.level != PG_LEVEL_4K) return; for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { @@ -200,7 +200,7 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, sp->gfn); - rmap_head = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot); + rmap_head = __gfn_to_rmap(sp->gfn, PG_LEVEL_4K, slot); for_each_rmap_spte(rmap_head, &iter, sptep) { if (is_writable_pte(*sptep)) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index a5078841bdac..b86346903f2e 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -397,9 +397,9 @@ static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr) __set_bit(pmc->idx, pmu->pmc_in_use); } -int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - return kvm_x86_ops.pmu_ops->get_msr(vcpu, msr, data); + return kvm_x86_ops.pmu_ops->get_msr(vcpu, msr_info); } int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index a6c78a797cb1..ab85eed8a6cc 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -32,7 +32,7 @@ struct kvm_pmu_ops { struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr); int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); - int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data); + int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); void (*refresh)(struct kvm_vcpu *vcpu); void (*init)(struct kvm_vcpu *vcpu); @@ -147,7 +147,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); -int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); +int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); void kvm_pmu_refresh(struct kvm_vcpu *vcpu); void kvm_pmu_reset(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 9a2a62e5afeb..8a6db11dcb43 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -25,6 +25,8 @@ #include "trace.h" #include "mmu.h" #include "x86.h" +#include "cpuid.h" +#include "lapic.h" #include "svm.h" static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, @@ -59,7 +61,7 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) { struct vcpu_svm *svm = to_svm(vcpu); - u64 cr3 = svm->nested.nested_cr3; + u64 cr3 = svm->nested.ctl.nested_cr3; u64 pdpte; int ret; @@ -74,19 +76,22 @@ static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - return svm->nested.nested_cr3; + return svm->nested.ctl.nested_cr3; } static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *hsave = svm->nested.hsave; + WARN_ON(mmu_is_nested(vcpu)); vcpu->arch.mmu = &vcpu->arch.guest_mmu; - kvm_init_shadow_mmu(vcpu); + kvm_init_shadow_mmu(vcpu, X86_CR0_PG, hsave->save.cr4, hsave->save.efer); vcpu->arch.mmu->get_guest_pgd = nested_svm_get_tdp_cr3; vcpu->arch.mmu->get_pdptr = nested_svm_get_tdp_pdptr; vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit; - vcpu->arch.mmu->shadow_root_level = kvm_x86_ops.get_tdp_level(vcpu); + vcpu->arch.mmu->shadow_root_level = vcpu->arch.tdp_level; reset_shadow_zero_bits_mask(vcpu, vcpu->arch.mmu); vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; } @@ -99,8 +104,7 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) void recalc_intercepts(struct vcpu_svm *svm) { - struct vmcb_control_area *c, *h; - struct nested_state *g; + struct vmcb_control_area *c, *h, *g; mark_dirty(svm->vmcb, VMCB_INTERCEPTS); @@ -109,14 +113,16 @@ void recalc_intercepts(struct vcpu_svm *svm) c = &svm->vmcb->control; h = &svm->nested.hsave->control; - g = &svm->nested; + g = &svm->nested.ctl; + + svm->nested.host_intercept_exceptions = h->intercept_exceptions; c->intercept_cr = h->intercept_cr; c->intercept_dr = h->intercept_dr; c->intercept_exceptions = h->intercept_exceptions; c->intercept = h->intercept; - if (svm->vcpu.arch.hflags & HF_VINTR_MASK) { + if (g->int_ctl & V_INTR_MASKING_MASK) { /* We only want the cr8 intercept bits of L1 */ c->intercept_cr &= ~(1U << INTERCEPT_CR8_READ); c->intercept_cr &= ~(1U << INTERCEPT_CR8_WRITE); @@ -138,11 +144,9 @@ void recalc_intercepts(struct vcpu_svm *svm) c->intercept |= g->intercept; } -static void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *from_vmcb) +static void copy_vmcb_control_area(struct vmcb_control_area *dst, + struct vmcb_control_area *from) { - struct vmcb_control_area *dst = &dst_vmcb->control; - struct vmcb_control_area *from = &from_vmcb->control; - dst->intercept_cr = from->intercept_cr; dst->intercept_dr = from->intercept_dr; dst->intercept_exceptions = from->intercept_exceptions; @@ -150,7 +154,7 @@ static void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *from_vmcb dst->iopm_base_pa = from->iopm_base_pa; dst->msrpm_base_pa = from->msrpm_base_pa; dst->tsc_offset = from->tsc_offset; - dst->asid = from->asid; + /* asid not copied, it is handled manually for svm->vmcb. */ dst->tlb_ctl = from->tlb_ctl; dst->int_ctl = from->int_ctl; dst->int_vector = from->int_vector; @@ -179,7 +183,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) */ int i; - if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) + if (!(svm->nested.ctl.intercept & (1ULL << INTERCEPT_MSR_PROT))) return true; for (i = 0; i < MSRPM_OFFSETS; i++) { @@ -190,7 +194,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) break; p = msrpm_offsets[i]; - offset = svm->nested.vmcb_msrpm + (p * 4); + offset = svm->nested.ctl.msrpm_base_pa + (p * 4); if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4)) return false; @@ -203,41 +207,111 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) return true; } -static bool nested_vmcb_checks(struct vmcb *vmcb) +static bool nested_vmcb_check_controls(struct vmcb_control_area *control) { - if ((vmcb->save.efer & EFER_SVME) == 0) + if ((control->intercept & (1ULL << INTERCEPT_VMRUN)) == 0) return false; - if ((vmcb->control.intercept & (1ULL << INTERCEPT_VMRUN)) == 0) + if (control->asid == 0) return false; - if (vmcb->control.asid == 0) - return false; - - if ((vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) && + if ((control->nested_ctl & SVM_NESTED_CTL_NP_ENABLE) && !npt_enabled) return false; return true; } -void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, - struct vmcb *nested_vmcb, struct kvm_host_map *map) +static bool nested_vmcb_checks(struct vmcb *vmcb) { - bool evaluate_pending_interrupts = - is_intercept(svm, INTERCEPT_VINTR) || - is_intercept(svm, INTERCEPT_IRET); + if ((vmcb->save.efer & EFER_SVME) == 0) + return false; - if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF) - svm->vcpu.arch.hflags |= HF_HIF_MASK; - else - svm->vcpu.arch.hflags &= ~HF_HIF_MASK; + if (((vmcb->save.cr0 & X86_CR0_CD) == 0) && + (vmcb->save.cr0 & X86_CR0_NW)) + return false; - if (nested_vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) { - svm->nested.nested_cr3 = nested_vmcb->control.nested_cr3; - nested_svm_init_mmu_context(&svm->vcpu); + return nested_vmcb_check_controls(&vmcb->control); +} + +static void load_nested_vmcb_control(struct vcpu_svm *svm, + struct vmcb_control_area *control) +{ + copy_vmcb_control_area(&svm->nested.ctl, control); + + /* Copy it here because nested_svm_check_controls will check it. */ + svm->nested.ctl.asid = control->asid; + svm->nested.ctl.msrpm_base_pa &= ~0x0fffULL; + svm->nested.ctl.iopm_base_pa &= ~0x0fffULL; +} + +/* + * Synchronize fields that are written by the processor, so that + * they can be copied back into the nested_vmcb. + */ +void sync_nested_vmcb_control(struct vcpu_svm *svm) +{ + u32 mask; + svm->nested.ctl.event_inj = svm->vmcb->control.event_inj; + svm->nested.ctl.event_inj_err = svm->vmcb->control.event_inj_err; + + /* Only a few fields of int_ctl are written by the processor. */ + mask = V_IRQ_MASK | V_TPR_MASK; + if (!(svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) && + is_intercept(svm, SVM_EXIT_VINTR)) { + /* + * In order to request an interrupt window, L0 is usurping + * svm->vmcb->control.int_ctl and possibly setting V_IRQ + * even if it was clear in L1's VMCB. Restoring it would be + * wrong. However, in this case V_IRQ will remain true until + * interrupt_window_interception calls svm_clear_vintr and + * restores int_ctl. We can just leave it aside. + */ + mask &= ~V_IRQ_MASK; } + svm->nested.ctl.int_ctl &= ~mask; + svm->nested.ctl.int_ctl |= svm->vmcb->control.int_ctl & mask; +} + +/* + * Transfer any event that L0 or L1 wanted to inject into L2 to + * EXIT_INT_INFO. + */ +static void nested_vmcb_save_pending_event(struct vcpu_svm *svm, + struct vmcb *nested_vmcb) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + u32 exit_int_info = 0; + unsigned int nr; + + if (vcpu->arch.exception.injected) { + nr = vcpu->arch.exception.nr; + exit_int_info = nr | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT; + + if (vcpu->arch.exception.has_error_code) { + exit_int_info |= SVM_EVTINJ_VALID_ERR; + nested_vmcb->control.exit_int_info_err = + vcpu->arch.exception.error_code; + } + + } else if (vcpu->arch.nmi_injected) { + exit_int_info = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI; + } else if (vcpu->arch.interrupt.injected) { + nr = vcpu->arch.interrupt.nr; + exit_int_info = nr | SVM_EVTINJ_VALID; + + if (vcpu->arch.interrupt.soft) + exit_int_info |= SVM_EVTINJ_TYPE_SOFT; + else + exit_int_info |= SVM_EVTINJ_TYPE_INTR; + } + + nested_vmcb->control.exit_int_info = exit_int_info; +} + +static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *nested_vmcb) +{ /* Load the nested guest state */ svm->vmcb->save.es = nested_vmcb->save.es; svm->vmcb->save.cs = nested_vmcb->save.cs; @@ -249,14 +323,7 @@ void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, svm_set_efer(&svm->vcpu, nested_vmcb->save.efer); svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0); svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4); - if (npt_enabled) { - svm->vmcb->save.cr3 = nested_vmcb->save.cr3; - svm->vcpu.arch.cr3 = nested_vmcb->save.cr3; - } else - (void)kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); - - /* Guest paging mode is active - reset mmu */ - kvm_mmu_reset_context(&svm->vcpu); + (void)kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2; kvm_rax_write(&svm->vcpu, nested_vmcb->save.rax); @@ -270,38 +337,34 @@ void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, svm->vmcb->save.dr7 = nested_vmcb->save.dr7; svm->vcpu.arch.dr6 = nested_vmcb->save.dr6; svm->vmcb->save.cpl = nested_vmcb->save.cpl; +} - svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL; - svm->nested.vmcb_iopm = nested_vmcb->control.iopm_base_pa & ~0x0fffULL; +static void nested_prepare_vmcb_control(struct vcpu_svm *svm) +{ + const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK; + if (svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) + nested_svm_init_mmu_context(&svm->vcpu); - /* cache intercepts */ - svm->nested.intercept_cr = nested_vmcb->control.intercept_cr; - svm->nested.intercept_dr = nested_vmcb->control.intercept_dr; - svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions; - svm->nested.intercept = nested_vmcb->control.intercept; + /* Guest paging mode is active - reset mmu */ + kvm_mmu_reset_context(&svm->vcpu); - svm_flush_tlb(&svm->vcpu, true); - svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; - if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) - svm->vcpu.arch.hflags |= HF_VINTR_MASK; - else - svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; + svm_flush_tlb(&svm->vcpu); - svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset; - svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset; + svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset = + svm->vcpu.arch.l1_tsc_offset + svm->nested.ctl.tsc_offset; - svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext; - svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; - svm->vmcb->control.int_state = nested_vmcb->control.int_state; - svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; - svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; + svm->vmcb->control.int_ctl = + (svm->nested.ctl.int_ctl & ~mask) | + (svm->nested.hsave->control.int_ctl & mask); - svm->vmcb->control.pause_filter_count = - nested_vmcb->control.pause_filter_count; - svm->vmcb->control.pause_filter_thresh = - nested_vmcb->control.pause_filter_thresh; + svm->vmcb->control.virt_ext = svm->nested.ctl.virt_ext; + svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; + svm->vmcb->control.int_state = svm->nested.ctl.int_state; + svm->vmcb->control.event_inj = svm->nested.ctl.event_inj; + svm->vmcb->control.event_inj_err = svm->nested.ctl.event_inj_err; - kvm_vcpu_unmap(&svm->vcpu, map, true); + svm->vmcb->control.pause_filter_count = svm->nested.ctl.pause_filter_count; + svm->vmcb->control.pause_filter_thresh = svm->nested.ctl.pause_filter_thresh; /* Enter Guest-Mode */ enter_guest_mode(&svm->vcpu); @@ -312,25 +375,18 @@ void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, */ recalc_intercepts(svm); - svm->nested.vmcb = vmcb_gpa; + mark_all_dirty(svm->vmcb); +} - /* - * If L1 had a pending IRQ/NMI before executing VMRUN, - * which wasn't delivered because it was disallowed (e.g. - * interrupts disabled), L0 needs to evaluate if this pending - * event should cause an exit from L2 to L1 or be delivered - * directly to L2. - * - * Usually this would be handled by the processor noticing an - * IRQ/NMI window request. However, VMRUN can unblock interrupts - * by implicitly setting GIF, so force L0 to perform pending event - * evaluation by requesting a KVM_REQ_EVENT. - */ - enable_gif(svm); - if (unlikely(evaluate_pending_interrupts)) - kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); +void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, + struct vmcb *nested_vmcb) +{ + svm->nested.vmcb = vmcb_gpa; + load_nested_vmcb_control(svm, &nested_vmcb->control); + nested_prepare_vmcb_save(svm, nested_vmcb); + nested_prepare_vmcb_control(svm); - mark_all_dirty(svm->vmcb); + svm_set_gif(svm, true); } int nested_svm_vmrun(struct vcpu_svm *svm) @@ -342,8 +398,12 @@ int nested_svm_vmrun(struct vcpu_svm *svm) struct kvm_host_map map; u64 vmcb_gpa; - vmcb_gpa = svm->vmcb->save.rax; + if (is_smm(&svm->vcpu)) { + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; + } + vmcb_gpa = svm->vmcb->save.rax; ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map); if (ret == -EINVAL) { kvm_inject_gp(&svm->vcpu, 0); @@ -361,10 +421,7 @@ int nested_svm_vmrun(struct vcpu_svm *svm) nested_vmcb->control.exit_code_hi = 0; nested_vmcb->control.exit_info_1 = 0; nested_vmcb->control.exit_info_2 = 0; - - kvm_vcpu_unmap(&svm->vcpu, &map, true); - - return ret; + goto out; } trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa, @@ -404,9 +461,10 @@ int nested_svm_vmrun(struct vcpu_svm *svm) else hsave->save.cr3 = kvm_read_cr3(&svm->vcpu); - copy_vmcb_control_area(hsave, vmcb); + copy_vmcb_control_area(&hsave->control, &vmcb->control); - enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, &map); + svm->nested.nested_run_pending = 1; + enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb); if (!nested_svm_vmrun_msrpm(svm)) { svm->vmcb->control.exit_code = SVM_EXIT_ERR; @@ -417,6 +475,9 @@ int nested_svm_vmrun(struct vcpu_svm *svm) nested_svm_vmexit(svm); } +out: + kvm_vcpu_unmap(&svm->vcpu, &map, true); + return ret; } @@ -444,13 +505,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm) struct vmcb *vmcb = svm->vmcb; struct kvm_host_map map; - trace_kvm_nested_vmexit_inject(vmcb->control.exit_code, - vmcb->control.exit_info_1, - vmcb->control.exit_info_2, - vmcb->control.exit_int_info, - vmcb->control.exit_int_info_err, - KVM_ISA_SVM); - rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->nested.vmcb), &map); if (rc) { if (rc == -EINVAL) @@ -463,9 +517,13 @@ int nested_svm_vmexit(struct vcpu_svm *svm) /* Exit Guest-Mode */ leave_guest_mode(&svm->vcpu); svm->nested.vmcb = 0; + WARN_ON_ONCE(svm->nested.nested_run_pending); + + /* in case we halted in L2 */ + svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE; /* Give the current vmcb to the guest */ - disable_gif(svm); + svm_set_gif(svm, false); nested_vmcb->save.es = vmcb->save.es; nested_vmcb->save.cs = vmcb->save.cs; @@ -479,62 +537,42 @@ int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->save.cr2 = vmcb->save.cr2; nested_vmcb->save.cr4 = svm->vcpu.arch.cr4; nested_vmcb->save.rflags = kvm_get_rflags(&svm->vcpu); - nested_vmcb->save.rip = vmcb->save.rip; - nested_vmcb->save.rsp = vmcb->save.rsp; - nested_vmcb->save.rax = vmcb->save.rax; + nested_vmcb->save.rip = kvm_rip_read(&svm->vcpu); + nested_vmcb->save.rsp = kvm_rsp_read(&svm->vcpu); + nested_vmcb->save.rax = kvm_rax_read(&svm->vcpu); nested_vmcb->save.dr7 = vmcb->save.dr7; nested_vmcb->save.dr6 = svm->vcpu.arch.dr6; nested_vmcb->save.cpl = vmcb->save.cpl; - nested_vmcb->control.int_ctl = vmcb->control.int_ctl; - nested_vmcb->control.int_vector = vmcb->control.int_vector; nested_vmcb->control.int_state = vmcb->control.int_state; nested_vmcb->control.exit_code = vmcb->control.exit_code; nested_vmcb->control.exit_code_hi = vmcb->control.exit_code_hi; nested_vmcb->control.exit_info_1 = vmcb->control.exit_info_1; nested_vmcb->control.exit_info_2 = vmcb->control.exit_info_2; - nested_vmcb->control.exit_int_info = vmcb->control.exit_int_info; - nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err; + + if (nested_vmcb->control.exit_code != SVM_EXIT_ERR) + nested_vmcb_save_pending_event(svm, nested_vmcb); if (svm->nrips_enabled) nested_vmcb->control.next_rip = vmcb->control.next_rip; - /* - * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have - * to make sure that we do not lose injected events. So check event_inj - * here and copy it to exit_int_info if it is valid. - * Exit_int_info and event_inj can't be both valid because the case - * below only happens on a VMRUN instruction intercept which has - * no valid exit_int_info set. - */ - if (vmcb->control.event_inj & SVM_EVTINJ_VALID) { - struct vmcb_control_area *nc = &nested_vmcb->control; - - nc->exit_int_info = vmcb->control.event_inj; - nc->exit_int_info_err = vmcb->control.event_inj_err; - } - - nested_vmcb->control.tlb_ctl = 0; - nested_vmcb->control.event_inj = 0; - nested_vmcb->control.event_inj_err = 0; + nested_vmcb->control.int_ctl = svm->nested.ctl.int_ctl; + nested_vmcb->control.tlb_ctl = svm->nested.ctl.tlb_ctl; + nested_vmcb->control.event_inj = svm->nested.ctl.event_inj; + nested_vmcb->control.event_inj_err = svm->nested.ctl.event_inj_err; nested_vmcb->control.pause_filter_count = svm->vmcb->control.pause_filter_count; nested_vmcb->control.pause_filter_thresh = svm->vmcb->control.pause_filter_thresh; - /* We always set V_INTR_MASKING and remember the old value in hflags */ - if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) - nested_vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; - /* Restore the original control entries */ - copy_vmcb_control_area(vmcb, hsave); + copy_vmcb_control_area(&vmcb->control, &hsave->control); - svm->vcpu.arch.tsc_offset = svm->vmcb->control.tsc_offset; - kvm_clear_exception_queue(&svm->vcpu); - kvm_clear_interrupt_queue(&svm->vcpu); + svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset = + svm->vcpu.arch.l1_tsc_offset; - svm->nested.nested_cr3 = 0; + svm->nested.ctl.nested_cr3 = 0; /* Restore selected save entries */ svm->vmcb->save.es = hsave->save.es; @@ -562,6 +600,13 @@ int nested_svm_vmexit(struct vcpu_svm *svm) mark_all_dirty(svm->vmcb); + trace_kvm_nested_vmexit_inject(nested_vmcb->control.exit_code, + nested_vmcb->control.exit_info_1, + nested_vmcb->control.exit_info_2, + nested_vmcb->control.exit_int_info, + nested_vmcb->control.exit_int_info_err, + KVM_ISA_SVM); + kvm_vcpu_unmap(&svm->vcpu, &map, true); nested_svm_uninit_mmu_context(&svm->vcpu); @@ -579,12 +624,28 @@ int nested_svm_vmexit(struct vcpu_svm *svm) return 0; } +/* + * Forcibly leave nested mode in order to be able to reset the VCPU later on. + */ +void svm_leave_nested(struct vcpu_svm *svm) +{ + if (is_guest_mode(&svm->vcpu)) { + struct vmcb *hsave = svm->nested.hsave; + struct vmcb *vmcb = svm->vmcb; + + svm->nested.nested_run_pending = 0; + leave_guest_mode(&svm->vcpu); + copy_vmcb_control_area(&vmcb->control, &hsave->control); + nested_svm_uninit_mmu_context(&svm->vcpu); + } +} + static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) { u32 offset, msr, value; int write, mask; - if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT))) + if (!(svm->nested.ctl.intercept & (1ULL << INTERCEPT_MSR_PROT))) return NESTED_EXIT_HOST; msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; @@ -598,56 +659,12 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) /* Offset is in 32 bit units but need in 8 bit units */ offset *= 4; - if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.vmcb_msrpm + offset, &value, 4)) + if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.ctl.msrpm_base_pa + offset, &value, 4)) return NESTED_EXIT_DONE; return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; } -/* DB exceptions for our internal use must not cause vmexit */ -static int nested_svm_intercept_db(struct vcpu_svm *svm) -{ - unsigned long dr6 = svm->vmcb->save.dr6; - - /* Always catch it and pass it to userspace if debugging. */ - if (svm->vcpu.guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - return NESTED_EXIT_HOST; - - /* if we're not singlestepping, it's not ours */ - if (!svm->nmi_singlestep) - goto reflected_db; - - /* if it's not a singlestep exception, it's not ours */ - if (!(dr6 & DR6_BS)) - goto reflected_db; - - /* if the guest is singlestepping, it should get the vmexit */ - if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) { - disable_nmi_singlestep(svm); - goto reflected_db; - } - - /* it's ours, the nested hypervisor must not see this one */ - return NESTED_EXIT_HOST; - -reflected_db: - /* - * Synchronize guest DR6 here just like in kvm_deliver_exception_payload; - * it will be moved into the nested VMCB by nested_svm_vmexit. Once - * exceptions will be moved to svm_check_nested_events, all this stuff - * will just go away and we could just return NESTED_EXIT_HOST - * unconditionally. db_interception will queue the exception, which - * will be processed by svm_check_nested_events if a nested vmexit is - * required, and we will just use kvm_deliver_exception_payload to copy - * the payload to DR6 before vmexit. - */ - WARN_ON(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT); - svm->vcpu.arch.dr6 &= ~(DR_TRAP_BITS | DR6_RTM); - svm->vcpu.arch.dr6 |= dr6 & ~DR6_FIXED_1; - return NESTED_EXIT_DONE; -} - static int nested_svm_intercept_ioio(struct vcpu_svm *svm) { unsigned port, size, iopm_len; @@ -655,13 +672,13 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm) u8 start_bit; u64 gpa; - if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT))) + if (!(svm->nested.ctl.intercept & (1ULL << INTERCEPT_IOIO_PROT))) return NESTED_EXIT_HOST; port = svm->vmcb->control.exit_info_1 >> 16; size = (svm->vmcb->control.exit_info_1 & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; - gpa = svm->nested.vmcb_iopm + (port / 8); + gpa = svm->nested.ctl.iopm_base_pa + (port / 8); start_bit = port % 8; iopm_len = (start_bit + size > 8) ? 2 : 1; mask = (0xf >> (4 - size)) << start_bit; @@ -687,31 +704,23 @@ static int nested_svm_intercept(struct vcpu_svm *svm) break; case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: { u32 bit = 1U << (exit_code - SVM_EXIT_READ_CR0); - if (svm->nested.intercept_cr & bit) + if (svm->nested.ctl.intercept_cr & bit) vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: { u32 bit = 1U << (exit_code - SVM_EXIT_READ_DR0); - if (svm->nested.intercept_dr & bit) + if (svm->nested.ctl.intercept_dr & bit) vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { - u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); - if (svm->nested.intercept_exceptions & excp_bits) { - if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR) - vmexit = nested_svm_intercept_db(svm); - else if (exit_code == SVM_EXIT_EXCP_BASE + BP_VECTOR && - svm->vcpu.guest_debug & KVM_GUESTDBG_USE_SW_BP) - vmexit = NESTED_EXIT_HOST; - else - vmexit = NESTED_EXIT_DONE; - } - /* async page fault always cause vmexit */ - else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) && - svm->vcpu.arch.exception.nested_apf != 0) - vmexit = NESTED_EXIT_DONE; + /* + * Host-intercepted exceptions have been checked already in + * nested_svm_exit_special. There is nothing to do here, + * the vmexit is injected by svm_check_nested_events. + */ + vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_ERR: { @@ -720,7 +729,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm) } default: { u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); - if (svm->nested.intercept & exit_bits) + if (svm->nested.ctl.intercept & exit_bits) vmexit = NESTED_EXIT_DONE; } } @@ -756,62 +765,140 @@ int nested_svm_check_permissions(struct vcpu_svm *svm) return 0; } -int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, - bool has_error_code, u32 error_code) +static bool nested_exit_on_exception(struct vcpu_svm *svm) { - int vmexit; + unsigned int nr = svm->vcpu.arch.exception.nr; - if (!is_guest_mode(&svm->vcpu)) - return 0; + return (svm->nested.ctl.intercept_exceptions & (1 << nr)); +} - vmexit = nested_svm_intercept(svm); - if (vmexit != NESTED_EXIT_DONE) - return 0; +static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm) +{ + unsigned int nr = svm->vcpu.arch.exception.nr; svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; svm->vmcb->control.exit_code_hi = 0; - svm->vmcb->control.exit_info_1 = error_code; + + if (svm->vcpu.arch.exception.has_error_code) + svm->vmcb->control.exit_info_1 = svm->vcpu.arch.exception.error_code; /* * EXITINFO2 is undefined for all exception intercepts other * than #PF. */ - if (svm->vcpu.arch.exception.nested_apf) - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; - else if (svm->vcpu.arch.exception.has_payload) - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload; - else - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; + if (nr == PF_VECTOR) { + if (svm->vcpu.arch.exception.nested_apf) + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; + else if (svm->vcpu.arch.exception.has_payload) + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload; + else + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; + } else if (nr == DB_VECTOR) { + /* See inject_pending_event. */ + kvm_deliver_exception_payload(&svm->vcpu); + if (svm->vcpu.arch.dr7 & DR7_GD) { + svm->vcpu.arch.dr7 &= ~DR7_GD; + kvm_update_dr7(&svm->vcpu); + } + } else + WARN_ON(svm->vcpu.arch.exception.has_payload); - svm->nested.exit_required = true; - return vmexit; + nested_svm_vmexit(svm); +} + +static void nested_svm_smi(struct vcpu_svm *svm) +{ + svm->vmcb->control.exit_code = SVM_EXIT_SMI; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + + nested_svm_vmexit(svm); +} + +static void nested_svm_nmi(struct vcpu_svm *svm) +{ + svm->vmcb->control.exit_code = SVM_EXIT_NMI; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + + nested_svm_vmexit(svm); } static void nested_svm_intr(struct vcpu_svm *svm) { + trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); + svm->vmcb->control.exit_code = SVM_EXIT_INTR; svm->vmcb->control.exit_info_1 = 0; svm->vmcb->control.exit_info_2 = 0; - /* nested_svm_vmexit this gets called afterwards from handle_exit */ - svm->nested.exit_required = true; - trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); + nested_svm_vmexit(svm); } -static bool nested_exit_on_intr(struct vcpu_svm *svm) +static inline bool nested_exit_on_init(struct vcpu_svm *svm) { - return (svm->nested.intercept & 1ULL); + return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_INIT)); +} + +static void nested_svm_init(struct vcpu_svm *svm) +{ + svm->vmcb->control.exit_code = SVM_EXIT_INIT; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + + nested_svm_vmexit(svm); } -int svm_check_nested_events(struct kvm_vcpu *vcpu) + +static int svm_check_nested_events(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); bool block_nested_events = - kvm_event_needs_reinjection(vcpu) || svm->nested.exit_required; + kvm_event_needs_reinjection(vcpu) || svm->nested.nested_run_pending; + struct kvm_lapic *apic = vcpu->arch.apic; + + if (lapic_in_kernel(vcpu) && + test_bit(KVM_APIC_INIT, &apic->pending_events)) { + if (block_nested_events) + return -EBUSY; + if (!nested_exit_on_init(svm)) + return 0; + nested_svm_init(svm); + return 0; + } + + if (vcpu->arch.exception.pending) { + if (block_nested_events) + return -EBUSY; + if (!nested_exit_on_exception(svm)) + return 0; + nested_svm_inject_exception_vmexit(svm); + return 0; + } + + if (vcpu->arch.smi_pending && !svm_smi_blocked(vcpu)) { + if (block_nested_events) + return -EBUSY; + if (!nested_exit_on_smi(svm)) + return 0; + nested_svm_smi(svm); + return 0; + } + + if (vcpu->arch.nmi_pending && !svm_nmi_blocked(vcpu)) { + if (block_nested_events) + return -EBUSY; + if (!nested_exit_on_nmi(svm)) + return 0; + nested_svm_nmi(svm); + return 0; + } - if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(svm)) { + if (kvm_cpu_has_interrupt(vcpu) && !svm_interrupt_blocked(vcpu)) { if (block_nested_events) return -EBUSY; + if (!nested_exit_on_intr(svm)) + return 0; nested_svm_intr(svm); return 0; } @@ -826,21 +913,170 @@ int nested_svm_exit_special(struct vcpu_svm *svm) switch (exit_code) { case SVM_EXIT_INTR: case SVM_EXIT_NMI: - case SVM_EXIT_EXCP_BASE + MC_VECTOR: - return NESTED_EXIT_HOST; case SVM_EXIT_NPF: - /* For now we are always handling NPFs when using them */ - if (npt_enabled) + return NESTED_EXIT_HOST; + case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { + u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); + + if (get_host_vmcb(svm)->control.intercept_exceptions & excp_bits) return NESTED_EXIT_HOST; - break; - case SVM_EXIT_EXCP_BASE + PF_VECTOR: - /* When we're shadowing, trap PFs, but not async PF */ - if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0) + else if (exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR && + svm->vcpu.arch.apf.host_apf_flags) + /* Trap async PF even if not shadowing */ return NESTED_EXIT_HOST; break; + } default: break; } return NESTED_EXIT_CONTINUE; } + +static int svm_get_nested_state(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + u32 user_data_size) +{ + struct vcpu_svm *svm; + struct kvm_nested_state kvm_state = { + .flags = 0, + .format = KVM_STATE_NESTED_FORMAT_SVM, + .size = sizeof(kvm_state), + }; + struct vmcb __user *user_vmcb = (struct vmcb __user *) + &user_kvm_nested_state->data.svm[0]; + + if (!vcpu) + return kvm_state.size + KVM_STATE_NESTED_SVM_VMCB_SIZE; + + svm = to_svm(vcpu); + + if (user_data_size < kvm_state.size) + goto out; + + /* First fill in the header and copy it out. */ + if (is_guest_mode(vcpu)) { + kvm_state.hdr.svm.vmcb_pa = svm->nested.vmcb; + kvm_state.size += KVM_STATE_NESTED_SVM_VMCB_SIZE; + kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE; + + if (svm->nested.nested_run_pending) + kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING; + } + + if (gif_set(svm)) + kvm_state.flags |= KVM_STATE_NESTED_GIF_SET; + + if (copy_to_user(user_kvm_nested_state, &kvm_state, sizeof(kvm_state))) + return -EFAULT; + + if (!is_guest_mode(vcpu)) + goto out; + + /* + * Copy over the full size of the VMCB rather than just the size + * of the structs. + */ + if (clear_user(user_vmcb, KVM_STATE_NESTED_SVM_VMCB_SIZE)) + return -EFAULT; + if (copy_to_user(&user_vmcb->control, &svm->nested.ctl, + sizeof(user_vmcb->control))) + return -EFAULT; + if (copy_to_user(&user_vmcb->save, &svm->nested.hsave->save, + sizeof(user_vmcb->save))) + return -EFAULT; + +out: + return kvm_state.size; +} + +static int svm_set_nested_state(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + struct kvm_nested_state *kvm_state) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *hsave = svm->nested.hsave; + struct vmcb __user *user_vmcb = (struct vmcb __user *) + &user_kvm_nested_state->data.svm[0]; + struct vmcb_control_area ctl; + struct vmcb_save_area save; + u32 cr0; + + if (kvm_state->format != KVM_STATE_NESTED_FORMAT_SVM) + return -EINVAL; + + if (kvm_state->flags & ~(KVM_STATE_NESTED_GUEST_MODE | + KVM_STATE_NESTED_RUN_PENDING | + KVM_STATE_NESTED_GIF_SET)) + return -EINVAL; + + /* + * If in guest mode, vcpu->arch.efer actually refers to the L2 guest's + * EFER.SVME, but EFER.SVME still has to be 1 for VMRUN to succeed. + */ + if (!(vcpu->arch.efer & EFER_SVME)) { + /* GIF=1 and no guest mode are required if SVME=0. */ + if (kvm_state->flags != KVM_STATE_NESTED_GIF_SET) + return -EINVAL; + } + + /* SMM temporarily disables SVM, so we cannot be in guest mode. */ + if (is_smm(vcpu) && (kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) + return -EINVAL; + + if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) { + svm_leave_nested(svm); + goto out_set_gif; + } + + if (!page_address_valid(vcpu, kvm_state->hdr.svm.vmcb_pa)) + return -EINVAL; + if (kvm_state->size < sizeof(*kvm_state) + KVM_STATE_NESTED_SVM_VMCB_SIZE) + return -EINVAL; + if (copy_from_user(&ctl, &user_vmcb->control, sizeof(ctl))) + return -EFAULT; + if (copy_from_user(&save, &user_vmcb->save, sizeof(save))) + return -EFAULT; + + if (!nested_vmcb_check_controls(&ctl)) + return -EINVAL; + + /* + * Processor state contains L2 state. Check that it is + * valid for guest mode (see nested_vmcb_checks). + */ + cr0 = kvm_read_cr0(vcpu); + if (((cr0 & X86_CR0_CD) == 0) && (cr0 & X86_CR0_NW)) + return -EINVAL; + + /* + * Validate host state saved from before VMRUN (see + * nested_svm_check_permissions). + * TODO: validate reserved bits for all saved state. + */ + if (!(save.cr0 & X86_CR0_PG)) + return -EINVAL; + + /* + * All checks done, we can enter guest mode. L1 control fields + * come from the nested save state. Guest state is already + * in the registers, the save area of the nested state instead + * contains saved L1 state. + */ + copy_vmcb_control_area(&hsave->control, &svm->vmcb->control); + hsave->save = save; + + svm->nested.vmcb = kvm_state->hdr.svm.vmcb_pa; + load_nested_vmcb_control(svm, &ctl); + nested_prepare_vmcb_control(svm); + +out_set_gif: + svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); + return 0; +} + +struct kvm_x86_nested_ops svm_nested_ops = { + .check_events = svm_check_nested_events, + .get_state = svm_get_nested_state, + .set_state = svm_set_nested_state, +}; diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index ce0b10fe5e2b..035da07500e8 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -215,21 +215,22 @@ static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) return pmc; } -static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *pmc; + u32 msr = msr_info->index; /* MSR_PERFCTRn */ pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { - *data = pmc_read_counter(pmc); + msr_info->data = pmc_read_counter(pmc); return 0; } /* MSR_EVNTSELn */ pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL); if (pmc) { - *data = pmc->eventsel; + msr_info->data = pmc->eventsel; return 0; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index a862c768fd54..9e333b91ff78 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -33,6 +33,7 @@ #include <asm/debugreg.h> #include <asm/kvm_para.h> #include <asm/irq_remapping.h> +#include <asm/mce.h> #include <asm/spec-ctrl.h> #include <asm/cpu_device_id.h> @@ -264,6 +265,7 @@ static int get_npt_level(struct kvm_vcpu *vcpu) void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { + struct vcpu_svm *svm = to_svm(vcpu); vcpu->arch.efer = efer; if (!npt_enabled) { @@ -274,8 +276,13 @@ void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) efer &= ~EFER_LME; } - to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; - mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); + if (!(efer & EFER_SVME)) { + svm_leave_nested(svm); + svm_set_gif(svm, true); + } + + svm->vmcb->save.efer = efer | EFER_SVME; + mark_dirty(svm->vmcb, VMCB_CR); } static int is_external_interrupt(u32 info) @@ -318,9 +325,6 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) return 0; } else { - if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE) - pr_err("%s: ip 0x%lx next 0x%llx\n", - __func__, kvm_rip_read(vcpu), svm->next_rip); kvm_rip_write(vcpu, svm->next_rip); } svm_set_interrupt_shadow(vcpu, 0); @@ -333,17 +337,8 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); unsigned nr = vcpu->arch.exception.nr; bool has_error_code = vcpu->arch.exception.has_error_code; - bool reinject = vcpu->arch.exception.injected; u32 error_code = vcpu->arch.exception.error_code; - /* - * If we are within a nested VM we'd better #VMEXIT and let the guest - * handle the exception - */ - if (!reinject && - nested_svm_check_exception(svm, nr, has_error_code, error_code)) - return; - kvm_deliver_exception_payload(&svm->vcpu); if (nr == BP_VECTOR && !nrips) { @@ -780,7 +775,7 @@ static __init void svm_adjust_mmio_mask(void) */ mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0; - kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); + kvm_mmu_set_mmio_spte_mask(mask, PT_WRITABLE_MASK | PT_USER_MASK); } static void svm_hardware_teardown(void) @@ -890,7 +885,7 @@ static __init int svm_hardware_setup(void) if (npt_enabled && !npt) npt_enabled = false; - kvm_configure_mmu(npt_enabled, PT_PDPE_LEVEL); + kvm_configure_mmu(npt_enabled, PG_LEVEL_1G); pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); if (nrips) { @@ -953,16 +948,6 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } -static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - if (is_guest_mode(vcpu)) - return svm->nested.hsave->control.tsc_offset; - - return vcpu->arch.tsc_offset; -} - static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1208,6 +1193,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm->avic_is_running = true; svm->nested.hsave = page_address(hsave_page); + clear_page(svm->nested.hsave); svm->msrpm = page_address(msrpm_pages); svm_vcpu_init_msrpm(svm->msrpm); @@ -1364,12 +1350,13 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } -static inline void svm_enable_vintr(struct vcpu_svm *svm) +static void svm_set_vintr(struct vcpu_svm *svm) { struct vmcb_control_area *control; /* The following fields are ignored when AVIC is enabled */ WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu)); + set_intercept(svm, INTERCEPT_VINTR); /* * This is just a dummy VINTR to actually cause a vmexit to happen. @@ -1383,18 +1370,19 @@ static inline void svm_enable_vintr(struct vcpu_svm *svm) mark_dirty(svm->vmcb, VMCB_INTR); } -static void svm_set_vintr(struct vcpu_svm *svm) -{ - set_intercept(svm, INTERCEPT_VINTR); - if (is_intercept(svm, INTERCEPT_VINTR)) - svm_enable_vintr(svm); -} - static void svm_clear_vintr(struct vcpu_svm *svm) { + const u32 mask = V_TPR_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK | V_INTR_MASKING_MASK; clr_intercept(svm, INTERCEPT_VINTR); - svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; + /* Drop int_ctl fields related to VINTR injection. */ + svm->vmcb->control.int_ctl &= mask; + if (is_guest_mode(&svm->vcpu)) { + WARN_ON((svm->vmcb->control.int_ctl & V_TPR_MASK) != + (svm->nested.ctl.int_ctl & V_TPR_MASK)); + svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & ~mask; + } + mark_dirty(svm->vmcb, VMCB_INTR); } @@ -1533,14 +1521,6 @@ static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) mark_dirty(svm->vmcb, VMCB_DT); } -static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) -{ -} - -static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) -{ -} - static void update_cr0_intercept(struct vcpu_svm *svm) { ulong gcr0 = svm->vcpu.arch.cr0; @@ -1603,7 +1583,7 @@ int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE)) - svm_flush_tlb(vcpu, true); + svm_flush_tlb(vcpu); vcpu->arch.cr4 = cr4; if (!npt_enabled) @@ -1842,6 +1822,25 @@ static bool is_erratum_383(void) return true; } +/* + * Trigger machine check on the host. We assume all the MSRs are already set up + * by the CPU and that we still run on the same CPU as the MCE occurred on. + * We pass a fake environment to the machine check handler because we want + * the guest to be always treated like user space, no matter what context + * it used internally. + */ +static void kvm_machine_check(void) +{ +#if defined(CONFIG_X86_MCE) + struct pt_regs regs = { + .cs = 3, /* Fake ring 3 no matter what the guest ran on */ + .flags = X86_EFLAGS_IF, + }; + + do_machine_check(®s, 0); +#endif +} + static void svm_handle_mce(struct vcpu_svm *svm) { if (is_erratum_383()) { @@ -1860,11 +1859,7 @@ static void svm_handle_mce(struct vcpu_svm *svm) * On an #MC intercept the MCE handler is not called automatically in * the host. So do it by hand here. */ - asm volatile ( - "int $0x12\n"); - /* not sure if we ever come back to this point */ - - return; + kvm_machine_check(); } static int mc_interception(struct vcpu_svm *svm) @@ -1993,6 +1988,38 @@ static int vmrun_interception(struct vcpu_svm *svm) return nested_svm_vmrun(svm); } +void svm_set_gif(struct vcpu_svm *svm, bool value) +{ + if (value) { + /* + * If VGIF is enabled, the STGI intercept is only added to + * detect the opening of the SMI/NMI window; remove it now. + * Likewise, clear the VINTR intercept, we will set it + * again while processing KVM_REQ_EVENT if needed. + */ + if (vgif_enabled(svm)) + clr_intercept(svm, INTERCEPT_STGI); + if (is_intercept(svm, SVM_EXIT_VINTR)) + svm_clear_vintr(svm); + + enable_gif(svm); + if (svm->vcpu.arch.smi_pending || + svm->vcpu.arch.nmi_pending || + kvm_cpu_has_injectable_intr(&svm->vcpu)) + kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); + } else { + disable_gif(svm); + + /* + * After a CLGI no interrupts should come. But if vGIF is + * in use, we still rely on the VINTR intercept (rather than + * STGI) to detect an open interrupt window. + */ + if (!vgif_enabled(svm)) + svm_clear_vintr(svm); + } +} + static int stgi_interception(struct vcpu_svm *svm) { int ret; @@ -2000,18 +2027,8 @@ static int stgi_interception(struct vcpu_svm *svm) if (nested_svm_check_permissions(svm)) return 1; - /* - * If VGIF is enabled, the STGI intercept is only added to - * detect the opening of the SMI/NMI window; remove it now. - */ - if (vgif_enabled(svm)) - clr_intercept(svm, INTERCEPT_STGI); - ret = kvm_skip_emulated_instruction(&svm->vcpu); - kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); - - enable_gif(svm); - + svm_set_gif(svm, true); return ret; } @@ -2023,13 +2040,7 @@ static int clgi_interception(struct vcpu_svm *svm) return 1; ret = kvm_skip_emulated_instruction(&svm->vcpu); - - disable_gif(svm); - - /* After a CLGI no interrupts should come */ - if (!kvm_vcpu_apicv_active(&svm->vcpu)) - svm_clear_vintr(svm); - + svm_set_gif(svm, false); return ret; } @@ -2193,7 +2204,7 @@ static bool check_selective_cr0_intercepted(struct vcpu_svm *svm, bool ret = false; u64 intercept; - intercept = svm->nested.intercept; + intercept = svm->nested.ctl.intercept; if (!is_guest_mode(&svm->vcpu) || (!(intercept & (1ULL << INTERCEPT_SELECTIVE_CR0)))) @@ -2671,8 +2682,6 @@ static int interrupt_window_interception(struct vcpu_svm *svm) */ svm_toggle_avic_for_irq_window(&svm->vcpu, true); - svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; - mark_dirty(svm->vmcb, VMCB_INTR); ++svm->vcpu.stat.irq_window_exits; return 1; } @@ -2898,8 +2907,7 @@ static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) *info2 = control->exit_info_2; } -static int handle_exit(struct kvm_vcpu *vcpu, - enum exit_fastpath_completion exit_fastpath) +static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_run *kvm_run = vcpu->run; @@ -2912,12 +2920,7 @@ static int handle_exit(struct kvm_vcpu *vcpu, if (npt_enabled) vcpu->arch.cr3 = svm->vmcb->save.cr3; - if (unlikely(svm->nested.exit_required)) { - nested_svm_vmexit(svm); - svm->nested.exit_required = false; - - return 1; - } + svm_complete_interrupts(svm); if (is_guest_mode(vcpu)) { int vmexit; @@ -2938,8 +2941,6 @@ static int handle_exit(struct kvm_vcpu *vcpu, return 1; } - svm_complete_interrupts(svm); - if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) { kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; kvm_run->fail_entry.hardware_entry_failure_reason @@ -2957,10 +2958,10 @@ static int handle_exit(struct kvm_vcpu *vcpu, __func__, svm->vmcb->control.exit_int_info, exit_code); - if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) { - kvm_skip_emulated_instruction(vcpu); + if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; - } else if (exit_code >= ARRAY_SIZE(svm_exit_handlers) + + if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || !svm_exit_handlers[exit_code]) { vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code); dump_vmcb(vcpu); @@ -3049,18 +3050,37 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) set_cr_intercept(svm, INTERCEPT_CR8_WRITE); } -static int svm_nmi_allowed(struct kvm_vcpu *vcpu) +bool svm_nmi_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - int ret; - ret = !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && - !(svm->vcpu.arch.hflags & HF_NMI_MASK); - ret = ret && gif_set(svm) && nested_svm_nmi(svm); + bool ret; + + if (!gif_set(svm)) + return true; + + if (is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) + return false; + + ret = (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || + (svm->vcpu.arch.hflags & HF_NMI_MASK); return ret; } +static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +{ + struct vcpu_svm *svm = to_svm(vcpu); + if (svm->nested.nested_run_pending) + return -EBUSY; + + /* An NMI must not be injected into L2 if it's supposed to VM-Exit. */ + if (for_injection && is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) + return -EBUSY; + + return !svm_nmi_blocked(vcpu); +} + static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3081,19 +3101,46 @@ static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) } } -static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) +bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - if (!gif_set(svm) || - (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)) - return 0; + if (!gif_set(svm)) + return true; - if (is_guest_mode(vcpu) && (svm->vcpu.arch.hflags & HF_VINTR_MASK)) - return !!(svm->vcpu.arch.hflags & HF_HIF_MASK); - else - return !!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF); + if (is_guest_mode(vcpu)) { + /* As long as interrupts are being delivered... */ + if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) + ? !(svm->nested.hsave->save.rflags & X86_EFLAGS_IF) + : !(kvm_get_rflags(vcpu) & X86_EFLAGS_IF)) + return true; + + /* ... vmexits aren't blocked by the interrupt shadow */ + if (nested_exit_on_intr(svm)) + return false; + } else { + if (!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF)) + return true; + } + + return (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK); +} + +static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) +{ + struct vcpu_svm *svm = to_svm(vcpu); + if (svm->nested.nested_run_pending) + return -EBUSY; + + /* + * An IRQ must not be injected into L2 if it's supposed to VM-Exit, + * e.g. if the IRQ arrived asynchronously after checking nested events. + */ + if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(svm)) + return -EBUSY; + + return !svm_interrupt_blocked(vcpu); } static void enable_irq_window(struct kvm_vcpu *vcpu) @@ -3134,9 +3181,6 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) return; /* STGI will cause a vm exit */ } - if (svm->nested.exit_required) - return; /* we're not going to run the guest yet */ - /* * Something prevents NMI from been injected. Single step over possible * problem (IRET or exception injection or interrupt shadow) @@ -3156,10 +3200,17 @@ static int svm_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) return 0; } -void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) +void svm_flush_tlb(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + /* + * Flush only the current ASID even if the TLB flush was invoked via + * kvm_flush_remote_tlbs(). Although flushing remote TLBs requires all + * ASIDs to be flushed, KVM uses a single ASID for L1 and L2, and + * unconditionally does a TLB flush on both nested VM-Enter and nested + * VM-Exit (via kvm_mmu_reset_context()). + */ if (static_cpu_has(X86_FEATURE_FLUSHBYASID)) svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; else @@ -3279,10 +3330,21 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu) svm_complete_interrupts(svm); } +static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) +{ + if (!is_guest_mode(vcpu) && + to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && + to_svm(vcpu)->vmcb->control.exit_info_1) + return handle_fastpath_set_msr_irqoff(vcpu); + + return EXIT_FASTPATH_NONE; +} + void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); -static void svm_vcpu_run(struct kvm_vcpu *vcpu) +static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) { + fastpath_t exit_fastpath; struct vcpu_svm *svm = to_svm(vcpu); svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; @@ -3290,13 +3352,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; /* - * A vmexit emulation is required before the vcpu can be executed - * again. - */ - if (unlikely(svm->nested.exit_required)) - return; - - /* * Disable singlestep if we're injecting an interrupt/exception. * We don't want our modified rflags to be pushed on the stack where * we might not be able to easily reset them if we disabled NMI @@ -3387,6 +3442,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) stgi(); /* Any pending NMI will happen here */ + exit_fastpath = svm_exit_handlers_fastpath(vcpu); if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_after_interrupt(&svm->vcpu); @@ -3394,12 +3450,17 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) sync_cr8_to_lapic(vcpu); svm->next_rip = 0; + if (is_guest_mode(&svm->vcpu)) { + sync_nested_vmcb_control(svm); + svm->nested.nested_run_pending = 0; + } svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING; /* if exit due to PF check for async PF */ if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) - svm->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); + svm->vcpu.arch.apf.host_apf_flags = + kvm_read_and_reset_apf_flags(); if (npt_enabled) { vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); @@ -3415,12 +3476,12 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm_handle_mce(svm); mark_all_clean(svm->vmcb); + return exit_fastpath; } static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); - bool update_guest_cr3 = true; unsigned long cr3; cr3 = __sme_set(root); @@ -3429,18 +3490,13 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root) mark_dirty(svm->vmcb, VMCB_NPT); /* Loading L2's CR3 is handled by enter_svm_guest_mode. */ - if (is_guest_mode(vcpu)) - update_guest_cr3 = false; - else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - cr3 = vcpu->arch.cr3; - else /* CR3 is already up-to-date. */ - update_guest_cr3 = false; + if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + return; + cr3 = vcpu->arch.cr3; } - if (update_guest_cr3) { - svm->vmcb->save.cr3 = cr3; - mark_dirty(svm->vmcb, VMCB_CR); - } + svm->vmcb->save.cr3 = cr3; + mark_dirty(svm->vmcb, VMCB_CR); } static int is_disabled(void) @@ -3475,7 +3531,7 @@ static bool svm_cpu_has_accelerated_tpr(void) return false; } -static bool svm_has_emulated_msr(int index) +static bool svm_has_emulated_msr(u32 index) { switch (index) { case MSR_IA32_MCG_EXT_CTL: @@ -3628,7 +3684,7 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, info->intercept == x86_intercept_clts) break; - intercept = svm->nested.intercept; + intercept = svm->nested.ctl.intercept; if (!(intercept & (1ULL << INTERCEPT_SELECTIVE_CR0))) break; @@ -3716,13 +3772,8 @@ out: return ret; } -static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu, - enum exit_fastpath_completion *exit_fastpath) +static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) { - if (!is_guest_mode(vcpu) && - to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && - to_svm(vcpu)->vmcb->control.exit_info_1) - *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) @@ -3737,23 +3788,28 @@ static void svm_setup_mce(struct kvm_vcpu *vcpu) vcpu->arch.mcg_cap &= 0x1ff; } -static int svm_smi_allowed(struct kvm_vcpu *vcpu) +bool svm_smi_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); /* Per APM Vol.2 15.22.2 "Response to SMI" */ if (!gif_set(svm)) - return 0; + return true; - if (is_guest_mode(&svm->vcpu) && - svm->nested.intercept & (1ULL << INTERCEPT_SMI)) { - /* TODO: Might need to set exit_info_1 and exit_info_2 here */ - svm->vmcb->control.exit_code = SVM_EXIT_SMI; - svm->nested.exit_required = true; - return 0; - } + return is_smm(vcpu); +} - return 1; +static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +{ + struct vcpu_svm *svm = to_svm(vcpu); + if (svm->nested.nested_run_pending) + return -EBUSY; + + /* An SMI must not be injected into L2 if it's supposed to VM-Exit. */ + if (for_injection && is_guest_mode(vcpu) && nested_exit_on_smi(svm)) + return -EBUSY; + + return !svm_smi_blocked(vcpu); } static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) @@ -3793,12 +3849,13 @@ static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) if (kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb), &map) == -EINVAL) return 1; nested_vmcb = map.hva; - enter_svm_guest_mode(svm, vmcb, nested_vmcb, &map); + enter_svm_guest_mode(svm, vmcb, nested_vmcb); + kvm_vcpu_unmap(&svm->vcpu, &map, true); } return 0; } -static int enable_smi_window(struct kvm_vcpu *vcpu) +static void enable_smi_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3806,9 +3863,9 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) if (vgif_enabled(svm)) set_intercept(svm, INTERCEPT_STGI); /* STGI will cause a vm exit */ - return 1; + } else { + /* We must be in SMM; RSM will cause a vmexit anyway. */ } - return 0; } static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) @@ -3819,6 +3876,13 @@ static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) bool is_user = svm_get_cpl(vcpu) == 3; /* + * If RIP is invalid, go ahead with emulation which will cause an + * internal error exit. + */ + if (!kvm_vcpu_gfn_to_memslot(vcpu, kvm_rip_read(vcpu) >> PAGE_SHIFT)) + return true; + + /* * Detect and workaround Errata 1096 Fam_17h_00_0Fh. * * Errata: @@ -3876,9 +3940,9 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) /* * TODO: Last condition latch INIT signals on vCPU when * vCPU is in guest-mode and vmcb12 defines intercept on INIT. - * To properly emulate the INIT intercept, SVM should implement - * kvm_x86_ops.check_nested_events() and call nested_svm_vmexit() - * there if an INIT signal is pending. + * To properly emulate the INIT intercept, + * svm_check_nested_events() should call nested_svm_vmexit() + * if an INIT signal is pending. */ return !gif_set(svm) || (svm->vmcb->control.intercept & (1ULL << INTERCEPT_INIT)); @@ -3932,8 +3996,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .set_segment = svm_set_segment, .get_cpl = svm_get_cpl, .get_cs_db_l_bits = kvm_get_cs_db_l_bits, - .decache_cr0_guest_bits = svm_decache_cr0_guest_bits, - .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, .set_cr0 = svm_set_cr0, .set_cr4 = svm_set_cr4, .set_efer = svm_set_efer, @@ -3947,8 +4009,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, - .tlb_flush = svm_flush_tlb, + .tlb_flush_all = svm_flush_tlb, + .tlb_flush_current = svm_flush_tlb, .tlb_flush_gva = svm_flush_tlb_gva, + .tlb_flush_guest = svm_flush_tlb, .run = svm_vcpu_run, .handle_exit = handle_exit, @@ -3989,7 +4053,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .has_wbinvd_exit = svm_has_wbinvd_exit, - .read_l1_tsc_offset = svm_read_l1_tsc_offset, .write_l1_tsc_offset = svm_write_l1_tsc_offset, .load_mmu_pgd = svm_load_mmu_pgd, @@ -4002,6 +4065,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .sched_in = svm_sched_in, .pmu_ops = &amd_pmu_ops, + .nested_ops = &svm_nested_ops, + .deliver_posted_interrupt = svm_deliver_avic_intr, .dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt, .update_pi_irte = svm_update_pi_irte, @@ -4016,14 +4081,9 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .mem_enc_reg_region = svm_register_enc_region, .mem_enc_unreg_region = svm_unregister_enc_region, - .nested_enable_evmcs = NULL, - .nested_get_evmcs_version = NULL, - .need_emulation_on_page_fault = svm_need_emulation_on_page_fault, .apic_init_signal_blocked = svm_apic_init_signal_blocked, - - .check_nested_events = svm_check_nested_events, }; static struct kvm_x86_init_ops svm_init_ops __initdata = { diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index df3474f4fb02..6ac4c00a5d82 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -86,25 +86,17 @@ struct nested_state { u64 hsave_msr; u64 vm_cr_msr; u64 vmcb; + u32 host_intercept_exceptions; /* These are the merged vectors */ u32 *msrpm; - /* gpa pointers to the real vectors */ - u64 vmcb_msrpm; - u64 vmcb_iopm; + /* A VMRUN has started but has not yet been performed, so + * we cannot inject a nested vmexit yet. */ + bool nested_run_pending; - /* A VMEXIT is required but not yet emulated */ - bool exit_required; - - /* cache for intercepts of the guest */ - u32 intercept_cr; - u32 intercept_dr; - u32 intercept_exceptions; - u64 intercept; - - /* Nested Paging related state */ - u64 nested_cr3; + /* cache for control fields of the guest */ + struct vmcb_control_area ctl; }; struct vcpu_svm { @@ -360,8 +352,12 @@ u32 svm_msrpm_offset(u32 msr); void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer); void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); -void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); +void svm_flush_tlb(struct kvm_vcpu *vcpu); void disable_nmi_singlestep(struct vcpu_svm *svm); +bool svm_smi_blocked(struct kvm_vcpu *vcpu); +bool svm_nmi_blocked(struct kvm_vcpu *vcpu); +bool svm_interrupt_blocked(struct kvm_vcpu *vcpu); +void svm_set_gif(struct vcpu_svm *svm, bool value); /* nested.c */ @@ -369,28 +365,31 @@ void disable_nmi_singlestep(struct vcpu_svm *svm); #define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ #define NESTED_EXIT_CONTINUE 2 /* Further checks needed */ -/* This function returns true if it is save to enable the nmi window */ -static inline bool nested_svm_nmi(struct vcpu_svm *svm) +static inline bool svm_nested_virtualize_tpr(struct kvm_vcpu *vcpu) { - if (!is_guest_mode(&svm->vcpu)) - return true; + struct vcpu_svm *svm = to_svm(vcpu); - if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI))) - return true; + return is_guest_mode(vcpu) && (svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK); +} - svm->vmcb->control.exit_code = SVM_EXIT_NMI; - svm->nested.exit_required = true; +static inline bool nested_exit_on_smi(struct vcpu_svm *svm) +{ + return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_SMI)); +} - return false; +static inline bool nested_exit_on_intr(struct vcpu_svm *svm) +{ + return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_INTR)); } -static inline bool svm_nested_virtualize_tpr(struct kvm_vcpu *vcpu) +static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) { - return is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK); + return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_NMI)); } void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, - struct vmcb *nested_vmcb, struct kvm_host_map *map); + struct vmcb *nested_vmcb); +void svm_leave_nested(struct vcpu_svm *svm); int nested_svm_vmrun(struct vcpu_svm *svm); void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb); int nested_svm_vmexit(struct vcpu_svm *svm); @@ -398,8 +397,10 @@ int nested_svm_exit_handled(struct vcpu_svm *svm); int nested_svm_check_permissions(struct vcpu_svm *svm); int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); -int svm_check_nested_events(struct kvm_vcpu *vcpu); int nested_svm_exit_special(struct vcpu_svm *svm); +void sync_nested_vmcb_control(struct vcpu_svm *svm); + +extern struct kvm_x86_nested_ops svm_nested_ops; /* avic.c */ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 249062f24b94..b66432b015d2 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -225,6 +225,14 @@ TRACE_EVENT(kvm_apic, #define KVM_ISA_VMX 1 #define KVM_ISA_SVM 2 +#define kvm_print_exit_reason(exit_reason, isa) \ + (isa == KVM_ISA_VMX) ? \ + __print_symbolic(exit_reason & 0xffff, VMX_EXIT_REASONS) : \ + __print_symbolic(exit_reason, SVM_EXIT_REASONS), \ + (isa == KVM_ISA_VMX && exit_reason & ~0xffff) ? " " : "", \ + (isa == KVM_ISA_VMX) ? \ + __print_flags(exit_reason & ~0xffff, " ", VMX_EXIT_REASON_FLAGS) : "" + /* * Tracepoint for kvm guest exit: */ @@ -250,12 +258,10 @@ TRACE_EVENT(kvm_exit, &__entry->info2); ), - TP_printk("vcpu %u reason %s rip 0x%lx info %llx %llx", + TP_printk("vcpu %u reason %s%s%s rip 0x%lx info %llx %llx", __entry->vcpu_id, - (__entry->isa == KVM_ISA_VMX) ? - __print_symbolic(__entry->exit_reason, VMX_EXIT_REASONS) : - __print_symbolic(__entry->exit_reason, SVM_EXIT_REASONS), - __entry->guest_rip, __entry->info1, __entry->info2) + kvm_print_exit_reason(__entry->exit_reason, __entry->isa), + __entry->guest_rip, __entry->info1, __entry->info2) ); /* @@ -588,12 +594,10 @@ TRACE_EVENT(kvm_nested_vmexit, __entry->exit_int_info_err = exit_int_info_err; __entry->isa = isa; ), - TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx " + TP_printk("rip: 0x%016llx reason: %s%s%s ext_inf1: 0x%016llx " "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", __entry->rip, - (__entry->isa == KVM_ISA_VMX) ? - __print_symbolic(__entry->exit_code, VMX_EXIT_REASONS) : - __print_symbolic(__entry->exit_code, SVM_EXIT_REASONS), + kvm_print_exit_reason(__entry->exit_code, __entry->isa), __entry->exit_info1, __entry->exit_info2, __entry->exit_int_info, __entry->exit_int_info_err) ); @@ -626,13 +630,11 @@ TRACE_EVENT(kvm_nested_vmexit_inject, __entry->isa = isa; ), - TP_printk("reason: %s ext_inf1: 0x%016llx " + TP_printk("reason: %s%s%s ext_inf1: 0x%016llx " "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", - (__entry->isa == KVM_ISA_VMX) ? - __print_symbolic(__entry->exit_code, VMX_EXIT_REASONS) : - __print_symbolic(__entry->exit_code, SVM_EXIT_REASONS), - __entry->exit_info1, __entry->exit_info2, - __entry->exit_int_info, __entry->exit_int_info_err) + kvm_print_exit_reason(__entry->exit_code, __entry->isa), + __entry->exit_info1, __entry->exit_info2, + __entry->exit_int_info, __entry->exit_int_info_err) ); /* @@ -1539,6 +1541,57 @@ TRACE_EVENT(kvm_nested_vmenter_failed, __print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS)) ); +/* + * Tracepoint for syndbg_set_msr. + */ +TRACE_EVENT(kvm_hv_syndbg_set_msr, + TP_PROTO(int vcpu_id, u32 vp_index, u32 msr, u64 data), + TP_ARGS(vcpu_id, vp_index, msr, data), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, vp_index) + __field(u32, msr) + __field(u64, data) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->vp_index = vp_index; + __entry->msr = msr; + __entry->data = data; + ), + + TP_printk("vcpu_id %d vp_index %u msr 0x%x data 0x%llx", + __entry->vcpu_id, __entry->vp_index, __entry->msr, + __entry->data) +); + +/* + * Tracepoint for syndbg_get_msr. + */ +TRACE_EVENT(kvm_hv_syndbg_get_msr, + TP_PROTO(int vcpu_id, u32 vp_index, u32 msr, u64 data), + TP_ARGS(vcpu_id, vp_index, msr, data), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, vp_index) + __field(u32, msr) + __field(u64, data) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->vp_index = vp_index; + __entry->msr = msr; + __entry->data = data; + ), + + TP_printk("vcpu_id %d vp_index %u msr 0x%x data 0x%llx", + __entry->vcpu_id, __entry->vp_index, __entry->msr, + __entry->data) +); #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 8903475f751e..4bbd8b448d22 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -18,6 +18,8 @@ extern int __read_mostly pt_mode; #define PT_MODE_SYSTEM 0 #define PT_MODE_HOST_GUEST 1 +#define PMU_CAP_FW_WRITES (1ULL << 13) + struct nested_vmx_msrs { /* * We only store the "true" versions of the VMX capability MSRs. We @@ -367,4 +369,13 @@ static inline bool vmx_pt_mode_is_host_guest(void) return pt_mode == PT_MODE_HOST_GUEST; } +static inline u64 vmx_get_perf_capabilities(void) +{ + /* + * Since counters are virtualized, KVM would support full + * width counting unconditionally, even if the host lacks it. + */ + return PMU_CAP_FW_WRITES; +} + #endif /* __KVM_X86_VMX_CAPS_H */ diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 303813423c3e..e5325bd0f304 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -4,6 +4,7 @@ #include <linux/smp.h> #include "../hyperv.h" +#include "../cpuid.h" #include "evmcs.h" #include "vmcs.h" #include "vmx.h" @@ -160,14 +161,6 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr, HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(CR3_TARGET_VALUE0, cr3_target_value0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(CR3_TARGET_VALUE1, cr3_target_value1, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(CR3_TARGET_VALUE2, cr3_target_value2, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(CR3_TARGET_VALUE3, cr3_target_value3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), /* 32 bit rw */ EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold, @@ -334,17 +327,18 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa) uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * vmcs_version represents the range of supported Enlightened VMCS - * versions: lower 8 bits is the minimal version, higher 8 bits is the - * maximum supported version. KVM supports versions from 1 to - * KVM_EVMCS_VERSION. - */ - if (vmx->nested.enlightened_vmcs_enabled) - return (KVM_EVMCS_VERSION << 8) | 1; - - return 0; + struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * vmcs_version represents the range of supported Enlightened VMCS + * versions: lower 8 bits is the minimal version, higher 8 bits is the + * maximum supported version. KVM supports versions from 1 to + * KVM_EVMCS_VERSION. + */ + if (kvm_cpu_cap_get(X86_FEATURE_VMX) && + vmx->nested.enlightened_vmcs_enabled) + return (KVM_EVMCS_VERSION << 8) | 1; + + return 0; } void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index e44f33c82332..9c74a732b08d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -303,11 +303,11 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) cpu = get_cpu(); prev = vmx->loaded_vmcs; vmx->loaded_vmcs = vmcs; - vmx_vcpu_load_vmcs(vcpu, cpu); + vmx_vcpu_load_vmcs(vcpu, cpu, prev); vmx_sync_vmcs_host_state(vmx, prev); put_cpu(); - vmx_segment_cache_clear(vmx); + vmx_register_cache_reset(vcpu); } /* @@ -328,19 +328,19 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exit_reason; + u32 vm_exit_reason; unsigned long exit_qualification = vcpu->arch.exit_qualification; if (vmx->nested.pml_full) { - exit_reason = EXIT_REASON_PML_FULL; + vm_exit_reason = EXIT_REASON_PML_FULL; vmx->nested.pml_full = false; exit_qualification &= INTR_INFO_UNBLOCK_NMI; } else if (fault->error_code & PFERR_RSVD_MASK) - exit_reason = EXIT_REASON_EPT_MISCONFIG; + vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; else - exit_reason = EXIT_REASON_EPT_VIOLATION; + vm_exit_reason = EXIT_REASON_EPT_VIOLATION; - nested_vmx_vmexit(vcpu, exit_reason, 0, exit_qualification); + nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification); vmcs12->guest_physical_address = fault->address; } @@ -437,11 +437,6 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, } } -static bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa) -{ - return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu)); -} - static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -698,11 +693,6 @@ static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu) VM_EXIT_ACK_INTR_ON_EXIT; } -static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu) -{ - return nested_cpu_has_nmi_exiting(get_vmcs12(vcpu)); -} - static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -927,6 +917,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) } return 0; fail: + /* Note, max_msr_list_size is at most 4096, i.e. this can't wrap. */ return i + 1; } @@ -1074,34 +1065,81 @@ static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val) } /* + * Returns true if the MMU needs to be sync'd on nested VM-Enter/VM-Exit. + * tl;dr: the MMU needs a sync if L0 is using shadow paging and L1 didn't + * enable VPID for L2 (implying it expects a TLB flush on VMX transitions). + * Here's why. + * + * If EPT is enabled by L0 a sync is never needed: + * - if it is disabled by L1, then L0 is not shadowing L1 or L2 PTEs, there + * cannot be unsync'd SPTEs for either L1 or L2. + * + * - if it is also enabled by L1, then L0 doesn't need to sync on VM-Enter + * VM-Enter as VM-Enter isn't required to invalidate guest-physical mappings + * (irrespective of VPID), i.e. L1 can't rely on the (virtual) CPU to flush + * stale guest-physical mappings for L2 from the TLB. And as above, L0 isn't + * shadowing L1 PTEs so there are no unsync'd SPTEs to sync on VM-Exit. + * + * If EPT is disabled by L0: + * - if VPID is enabled by L1 (for L2), the situation is similar to when L1 + * enables EPT: L0 doesn't need to sync as VM-Enter and VM-Exit aren't + * required to invalidate linear mappings (EPT is disabled so there are + * no combined or guest-physical mappings), i.e. L1 can't rely on the + * (virtual) CPU to flush stale linear mappings for either L2 or itself (L1). + * + * - however if VPID is disabled by L1, then a sync is needed as L1 expects all + * linear mappings (EPT is disabled so there are no combined or guest-physical + * mappings) to be invalidated on both VM-Enter and VM-Exit. + * + * Note, this logic is subtly different than nested_has_guest_tlb_tag(), which + * additionally checks that L2 has been assigned a VPID (when EPT is disabled). + * Whether or not L2 has been assigned a VPID by L0 is irrelevant with respect + * to L1's expectations, e.g. L0 needs to invalidate hardware TLB entries if L2 + * doesn't have a unique VPID to prevent reusing L1's entries (assuming L1 has + * been assigned a VPID), but L0 doesn't need to do a MMU sync because L1 + * doesn't expect stale (virtual) TLB entries to be flushed, i.e. L1 doesn't + * know that L0 will flush the TLB and so L1 will do INVVPID as needed to flush + * stale TLB entries, at which point L0 will sync L2's MMU. + */ +static bool nested_vmx_transition_mmu_sync(struct kvm_vcpu *vcpu) +{ + return !enable_ept && !nested_cpu_has_vpid(get_vmcs12(vcpu)); +} + +/* * Load guest's/host's cr3 at nested entry/exit. @nested_ept is true if we are * emulating VM-Entry into a guest with EPT enabled. On failure, the expected * Exit Qualification (for a VM-Entry consistency check VM-Exit) is assigned to * @entry_failure_code. */ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, - u32 *entry_failure_code) + enum vm_entry_failure_code *entry_failure_code) { - if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) { - if (CC(!nested_cr3_valid(vcpu, cr3))) { - *entry_failure_code = ENTRY_FAIL_DEFAULT; - return -EINVAL; - } + if (CC(!nested_cr3_valid(vcpu, cr3))) { + *entry_failure_code = ENTRY_FAIL_DEFAULT; + return -EINVAL; + } - /* - * If PAE paging and EPT are both on, CR3 is not used by the CPU and - * must not be dereferenced. - */ - if (is_pae_paging(vcpu) && !nested_ept) { - if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { - *entry_failure_code = ENTRY_FAIL_PDPTE; - return -EINVAL; - } + /* + * If PAE paging and EPT are both on, CR3 is not used by the CPU and + * must not be dereferenced. + */ + if (!nested_ept && is_pae_paging(vcpu) && + (cr3 != kvm_read_cr3(vcpu) || pdptrs_changed(vcpu))) { + if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) { + *entry_failure_code = ENTRY_FAIL_PDPTE; + return -EINVAL; } } + /* + * Unconditionally skip the TLB flush on fast CR3 switch, all TLB + * flushes are handled by nested_vmx_transition_tlb_flush(). See + * nested_vmx_transition_mmu_sync for details on skipping the MMU sync. + */ if (!nested_ept) - kvm_mmu_new_cr3(vcpu, cr3, false); + kvm_mmu_new_pgd(vcpu, cr3, true, + !nested_vmx_transition_mmu_sync(vcpu)); vcpu->arch.cr3 = cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); @@ -1132,11 +1170,48 @@ static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu) (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02); } -static u16 nested_get_vpid02(struct kvm_vcpu *vcpu) +static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12, + bool is_vmenter) { struct vcpu_vmx *vmx = to_vmx(vcpu); - return vmx->nested.vpid02 ? vmx->nested.vpid02 : vmx->vpid; + /* + * If VPID is disabled, linear and combined mappings are flushed on + * VM-Enter/VM-Exit, and guest-physical mappings are valid only for + * their associated EPTP. + */ + if (!enable_vpid) + return; + + /* + * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings + * for *all* contexts to be flushed on VM-Enter/VM-Exit. + * + * If VPID is enabled and used by vmc12, but L2 does not have a unique + * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate + * a VPID for L2, flush the current context as the effective ASID is + * common to both L1 and L2. + * + * Defer the flush so that it runs after vmcs02.EPTP has been set by + * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid + * redundant flushes further down the nested pipeline. + * + * If a TLB flush isn't required due to any of the above, and vpid12 is + * changing then the new "virtual" VPID (vpid12) will reuse the same + * "real" VPID (vpid02), and so needs to be sync'd. There is no direct + * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for + * all nested vCPUs. + */ + if (!nested_cpu_has_vpid(vmcs12)) { + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + } else if (!nested_has_guest_tlb_tag(vcpu)) { + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + } else if (is_vmenter && + vmcs12->virtual_processor_id != vmx->nested.last_vpid) { + vmx->nested.last_vpid = vmcs12->virtual_processor_id; + vpid_sync_context(nested_get_vpid02(vcpu)); + } } static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) @@ -1700,10 +1775,6 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) * vmcs12->vm_exit_msr_store_addr = evmcs->vm_exit_msr_store_addr; * vmcs12->vm_exit_msr_load_addr = evmcs->vm_exit_msr_load_addr; * vmcs12->vm_entry_msr_load_addr = evmcs->vm_entry_msr_load_addr; - * vmcs12->cr3_target_value0 = evmcs->cr3_target_value0; - * vmcs12->cr3_target_value1 = evmcs->cr3_target_value1; - * vmcs12->cr3_target_value2 = evmcs->cr3_target_value2; - * vmcs12->cr3_target_value3 = evmcs->cr3_target_value3; * vmcs12->page_fault_error_code_mask = * evmcs->page_fault_error_code_mask; * vmcs12->page_fault_error_code_match = @@ -1777,10 +1848,6 @@ static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) * evmcs->vm_exit_msr_store_addr = vmcs12->vm_exit_msr_store_addr; * evmcs->vm_exit_msr_load_addr = vmcs12->vm_exit_msr_load_addr; * evmcs->vm_entry_msr_load_addr = vmcs12->vm_entry_msr_load_addr; - * evmcs->cr3_target_value0 = vmcs12->cr3_target_value0; - * evmcs->cr3_target_value1 = vmcs12->cr3_target_value1; - * evmcs->cr3_target_value2 = vmcs12->cr3_target_value2; - * evmcs->cr3_target_value3 = vmcs12->cr3_target_value3; * evmcs->tpr_threshold = vmcs12->tpr_threshold; * evmcs->virtual_processor_id = vmcs12->virtual_processor_id; * evmcs->exception_bitmap = vmcs12->exception_bitmap; @@ -2020,9 +2087,25 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer) return HRTIMER_NORESTART; } -static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) +static u64 vmx_calc_preemption_timer_value(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + u64 l1_scaled_tsc = kvm_read_l1_tsc(vcpu, rdtsc()) >> + VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE; + + if (!vmx->nested.has_preemption_timer_deadline) { + vmx->nested.preemption_timer_deadline = + vmcs12->vmx_preemption_timer_value + l1_scaled_tsc; + vmx->nested.has_preemption_timer_deadline = true; + } + return vmx->nested.preemption_timer_deadline - l1_scaled_tsc; +} + +static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu, + u64 preemption_timeout) { - u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value; struct vcpu_vmx *vmx = to_vmx(vcpu); /* @@ -2041,7 +2124,8 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) preemption_timeout *= 1000000; do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz); hrtimer_start(&vmx->nested.preemption_timer, - ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL); + ktime_add_ns(ktime_get(), preemption_timeout), + HRTIMER_MODE_ABS_PINNED); } static u64 nested_vmx_calc_efer(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) @@ -2398,7 +2482,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * is assigned to entry_failure_code on failure. */ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - u32 *entry_failure_code) + enum vm_entry_failure_code *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs; @@ -2447,32 +2531,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); - if (enable_vpid) { - /* - * There is no direct mapping between vpid02 and vpid12, the - * vpid02 is per-vCPU for L0 and reused while the value of - * vpid12 is changed w/ one invvpid during nested vmentry. - * The vpid12 is allocated by L1 for L2, so it will not - * influence global bitmap(for vpid01 and vpid02 allocation) - * even if spawn a lot of nested vCPUs. - */ - if (nested_cpu_has_vpid(vmcs12) && nested_has_guest_tlb_tag(vcpu)) { - if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) { - vmx->nested.last_vpid = vmcs12->virtual_processor_id; - __vmx_flush_tlb(vcpu, nested_get_vpid02(vcpu), false); - } - } else { - /* - * If L1 use EPT, then L0 needs to execute INVEPT on - * EPTP02 instead of EPTP01. Therefore, delay TLB - * flush until vmcs02->eptp is fully updated by - * KVM_REQ_LOAD_MMU_PGD. Note that this assumes - * KVM_REQ_TLB_FLUSH is evaluated after - * KVM_REQ_LOAD_MMU_PGD in vcpu_enter_guest(). - */ - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - } - } + nested_vmx_transition_tlb_flush(vcpu, vmcs12, true); if (nested_cpu_has_ept(vmcs12)) nested_ept_init_mmu_context(vcpu); @@ -2883,11 +2942,11 @@ static int nested_check_guest_non_reg_state(struct vmcs12 *vmcs12) static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - u32 *exit_qual) + enum vm_entry_failure_code *entry_failure_code) { bool ia32e; - *exit_qual = ENTRY_FAIL_DEFAULT; + *entry_failure_code = ENTRY_FAIL_DEFAULT; if (CC(!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0)) || CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4))) @@ -2902,7 +2961,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, return -EINVAL; if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) { - *exit_qual = ENTRY_FAIL_VMCS_LINK_PTR; + *entry_failure_code = ENTRY_FAIL_VMCS_LINK_PTR; return -EINVAL; } @@ -3194,9 +3253,12 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + enum vm_entry_failure_code entry_failure_code; bool evaluate_pending_interrupts; - u32 exit_reason = EXIT_REASON_INVALID_STATE; - u32 exit_qual; + u32 exit_reason, failed_index; + + if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) + kvm_vcpu_flush_tlb_current(vcpu); evaluate_pending_interrupts = exec_controls_get(vmx) & (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); @@ -3241,24 +3303,33 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, return NVMX_VMENTRY_VMFAIL; } - if (nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual)) + if (nested_vmx_check_guest_state(vcpu, vmcs12, + &entry_failure_code)) { + exit_reason = EXIT_REASON_INVALID_STATE; + vmcs12->exit_qualification = entry_failure_code; goto vmentry_fail_vmexit; + } } enter_guest_mode(vcpu); if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) vcpu->arch.tsc_offset += vmcs12->tsc_offset; - if (prepare_vmcs02(vcpu, vmcs12, &exit_qual)) + if (prepare_vmcs02(vcpu, vmcs12, &entry_failure_code)) { + exit_reason = EXIT_REASON_INVALID_STATE; + vmcs12->exit_qualification = entry_failure_code; goto vmentry_fail_vmexit_guest_mode; + } if (from_vmentry) { - exit_reason = EXIT_REASON_MSR_LOAD_FAIL; - exit_qual = nested_vmx_load_msr(vcpu, - vmcs12->vm_entry_msr_load_addr, - vmcs12->vm_entry_msr_load_count); - if (exit_qual) + failed_index = nested_vmx_load_msr(vcpu, + vmcs12->vm_entry_msr_load_addr, + vmcs12->vm_entry_msr_load_count); + if (failed_index) { + exit_reason = EXIT_REASON_MSR_LOAD_FAIL; + vmcs12->exit_qualification = failed_index; goto vmentry_fail_vmexit_guest_mode; + } } else { /* * The MMU is not initialized to point at the right entities yet and @@ -3293,8 +3364,10 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, * the timer. */ vmx->nested.preemption_timer_expired = false; - if (nested_cpu_has_preemption_timer(vmcs12)) - vmx_start_preemption_timer(vcpu); + if (nested_cpu_has_preemption_timer(vmcs12)) { + u64 timer_value = vmx_calc_preemption_timer_value(vcpu); + vmx_start_preemption_timer(vcpu, timer_value); + } /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point @@ -3322,7 +3395,6 @@ vmentry_fail_vmexit: load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY; - vmcs12->exit_qualification = exit_qual; if (enable_shadow_vmcs || vmx->nested.hv_evmcs) vmx->nested.need_vmcs12_to_shadow_sync = true; return NVMX_VMENTRY_VMEXIT; @@ -3403,6 +3475,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * the nested entry. */ vmx->nested.nested_run_pending = 1; + vmx->nested.has_preemption_timer_deadline = false; status = nested_vmx_enter_non_root_mode(vcpu, true); if (unlikely(status != NVMX_VMENTRY_SUCCESS)) goto vmentry_failed; @@ -3632,6 +3705,12 @@ static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu) vcpu->arch.exception.payload); } +static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) +{ + return nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) && + to_vmx(vcpu)->nested.preemption_timer_expired; +} + static int vmx_check_nested_events(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3661,11 +3740,11 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) /* * Process any exceptions that are not debug traps before MTF. */ - if (vcpu->arch.exception.pending && - !vmx_pending_dbg_trap(vcpu) && - nested_vmx_check_exception(vcpu, &exit_qual)) { + if (vcpu->arch.exception.pending && !vmx_pending_dbg_trap(vcpu)) { if (block_nested_events) return -EBUSY; + if (!nested_vmx_check_exception(vcpu, &exit_qual)) + goto no_vmexit; nested_vmx_inject_exception_vmexit(vcpu, exit_qual); return 0; } @@ -3678,25 +3757,34 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) return 0; } - if (vcpu->arch.exception.pending && - nested_vmx_check_exception(vcpu, &exit_qual)) { + if (vcpu->arch.exception.pending) { if (block_nested_events) return -EBUSY; + if (!nested_vmx_check_exception(vcpu, &exit_qual)) + goto no_vmexit; nested_vmx_inject_exception_vmexit(vcpu, exit_qual); return 0; } - if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) && - vmx->nested.preemption_timer_expired) { + if (nested_vmx_preemption_timer_pending(vcpu)) { if (block_nested_events) return -EBUSY; nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0); return 0; } - if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) { + if (vcpu->arch.smi_pending && !is_smm(vcpu)) { + if (block_nested_events) + return -EBUSY; + goto no_vmexit; + } + + if (vcpu->arch.nmi_pending && !vmx_nmi_blocked(vcpu)) { if (block_nested_events) return -EBUSY; + if (!nested_exit_on_nmi(vcpu)) + goto no_vmexit; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, NMI_VECTOR | INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK, 0); @@ -3709,13 +3797,16 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) return 0; } - if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) { + if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) { if (block_nested_events) return -EBUSY; + if (!nested_exit_on_intr(vcpu)) + goto no_vmexit; nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); return 0; } +no_vmexit: vmx_complete_nested_posted_interrupt(vcpu); return 0; } @@ -3842,12 +3933,12 @@ static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu, cpu = get_cpu(); vmx->loaded_vmcs = &vmx->nested.vmcs02; - vmx_vcpu_load(&vmx->vcpu, cpu); + vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->vmcs01); sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); vmx->loaded_vmcs = &vmx->vmcs01; - vmx_vcpu_load(&vmx->vcpu, cpu); + vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->nested.vmcs02); put_cpu(); } @@ -3876,10 +3967,6 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_cs_ar_bytes = vmcs_read32(GUEST_CS_AR_BYTES); vmcs12->guest_ss_ar_bytes = vmcs_read32(GUEST_SS_AR_BYTES); - vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS); - vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP); - vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP); - vmcs12->guest_interruptibility_info = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); @@ -3889,9 +3976,10 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE; if (nested_cpu_has_preemption_timer(vmcs12) && - vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) - vmcs12->vmx_preemption_timer_value = - vmx_get_preemption_timer_value(vcpu); + vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER && + !vmx->nested.nested_run_pending) + vmcs12->vmx_preemption_timer_value = + vmx_get_preemption_timer_value(vcpu); /* * In some cases (usually, nested EPT), L2 is allowed to change its @@ -3939,11 +4027,11 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) * which already writes to vmcs12 directly. */ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - u32 exit_reason, u32 exit_intr_info, + u32 vm_exit_reason, u32 exit_intr_info, unsigned long exit_qualification) { /* update exit information fields: */ - vmcs12->vm_exit_reason = exit_reason; + vmcs12->vm_exit_reason = vm_exit_reason; vmcs12->exit_qualification = exit_qualification; vmcs12->vm_exit_intr_info = exit_intr_info; @@ -3998,8 +4086,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { + enum vm_entry_failure_code ignored; struct kvm_segment seg; - u32 entry_failure_code; if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->host_ia32_efer; @@ -4034,30 +4122,13 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * Only PDPTE load can fail as the value of cr3 was checked on entry and * couldn't have changed. */ - if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code)) + if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &ignored)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); if (!enable_ept) vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; - /* - * If vmcs01 doesn't use VPID, CPU flushes TLB on every - * VMEntry/VMExit. Thus, no need to flush TLB. - * - * If vmcs12 doesn't use VPID, L1 expects TLB to be - * flushed on every VMEntry/VMExit. - * - * Otherwise, we can preserve TLB entries as long as we are - * able to tag L1 TLB entries differently than L2 TLB entries. - * - * If vmcs12 uses EPT, we need to execute this flush on EPTP01 - * and therefore we request the TLB flush to happen only after VMCS EPTP - * has been set by KVM_REQ_LOAD_MMU_PGD. - */ - if (enable_vpid && - (!nested_cpu_has_vpid(vmcs12) || !nested_has_guest_tlb_tag(vcpu))) { - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - } + nested_vmx_transition_tlb_flush(vcpu, vmcs12, false); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs); vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp); @@ -4204,7 +4275,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) * VMFail, like everything else we just need to ensure our * software model is up-to-date. */ - if (enable_ept) + if (enable_ept && is_pae_paging(vcpu)) ept_save_pdptrs(vcpu); kvm_mmu_reset_context(vcpu); @@ -4272,7 +4343,7 @@ vmabort: * and modify vmcs12 to make it see what it would expect to see there if * L2 was its real guest. Must only be called when in L2 (is_guest_mode()) */ -void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, +void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, u32 exit_intr_info, unsigned long exit_qualification) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4281,6 +4352,10 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); + /* Service the TLB flush request for L2 before switching to L1. */ + if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) + kvm_vcpu_flush_tlb_current(vcpu); + leave_guest_mode(vcpu); if (nested_cpu_has_preemption_timer(vmcs12)) @@ -4292,9 +4367,9 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, if (likely(!vmx->fail)) { sync_vmcs02_to_vmcs12(vcpu, vmcs12); - if (exit_reason != -1) - prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, - exit_qualification); + if (vm_exit_reason != -1) + prepare_vmcs12(vcpu, vmcs12, vm_exit_reason, + exit_intr_info, exit_qualification); /* * Must happen outside of sync_vmcs02_to_vmcs12() as it will @@ -4344,20 +4419,20 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true); vmx->nested.pi_desc = NULL; - /* - * We are now running in L2, mmu_notifier will force to reload the - * page's hpa for L2 vmcs. Need to reload it for L1 before entering L1. - */ - kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); + if (vmx->nested.reload_vmcs01_apic_access_page) { + vmx->nested.reload_vmcs01_apic_access_page = false; + kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); + } - if ((exit_reason != -1) && (enable_shadow_vmcs || vmx->nested.hv_evmcs)) + if ((vm_exit_reason != -1) && + (enable_shadow_vmcs || vmx->nested.hv_evmcs)) vmx->nested.need_vmcs12_to_shadow_sync = true; /* in case we halted in L2 */ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (likely(!vmx->fail)) { - if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && + if ((u16)vm_exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && nested_exit_intr_ack_set(vcpu)) { int irq = kvm_cpu_get_interrupt(vcpu); WARN_ON(irq < 0); @@ -4365,7 +4440,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR; } - if (exit_reason != -1) + if (vm_exit_reason != -1) trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, vmcs12->exit_qualification, vmcs12->idt_vectoring_info_field, @@ -4554,13 +4629,13 @@ static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer) gva_t gva; struct x86_exception e; - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu), vmcs_read32(VMX_INSTRUCTION_INFO), false, sizeof(*vmpointer), &gva)) return 1; if (kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e)) { - kvm_inject_page_fault(vcpu, &e); + kvm_inject_emulated_page_fault(vcpu, &e); return 1; } @@ -4614,7 +4689,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) goto out_shadow_vmcs; hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL_PINNED); + HRTIMER_MODE_ABS_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; vmx->nested.vpid02 = allocate_vpid(); @@ -4819,7 +4894,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) : get_vmcs12(vcpu); - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + unsigned long exit_qualification = vmx_get_exit_qual(vcpu); u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); struct vcpu_vmx *vmx = to_vmx(vcpu); struct x86_exception e; @@ -4869,7 +4944,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) return 1; /* _system ok, nested_vmx_check_permission has verified cpl=0 */ if (kvm_write_guest_virt_system(vcpu, gva, &value, len, &e)) { - kvm_inject_page_fault(vcpu, &e); + kvm_inject_emulated_page_fault(vcpu, &e); return 1; } } @@ -4905,7 +4980,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) : get_vmcs12(vcpu); - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + unsigned long exit_qualification = vmx_get_exit_qual(vcpu); u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); struct vcpu_vmx *vmx = to_vmx(vcpu); struct x86_exception e; @@ -4943,7 +5018,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) instr_info, false, len, &gva)) return 1; if (kvm_read_guest_virt(vcpu, gva, &value, len, &e)) { - kvm_inject_page_fault(vcpu, &e); + kvm_inject_emulated_page_fault(vcpu, &e); return 1; } } @@ -5090,7 +5165,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) /* Emulate the VMPTRST instruction */ static int handle_vmptrst(struct kvm_vcpu *vcpu) { - unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION); + unsigned long exit_qual = vmx_get_exit_qual(vcpu); u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr; struct x86_exception e; @@ -5108,23 +5183,33 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) /* *_system ok, nested_vmx_check_permission has verified cpl=0 */ if (kvm_write_guest_virt_system(vcpu, gva, (void *)¤t_vmptr, sizeof(gpa_t), &e)) { - kvm_inject_page_fault(vcpu, &e); + kvm_inject_emulated_page_fault(vcpu, &e); return 1; } return nested_vmx_succeed(vcpu); } +#define EPTP_PA_MASK GENMASK_ULL(51, 12) + +static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) +{ + return VALID_PAGE(root_hpa) && + ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); +} + /* Emulate the INVEPT instruction */ static int handle_invept(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 vmx_instruction_info, types; - unsigned long type; + unsigned long type, roots_to_free; + struct kvm_mmu *mmu; gva_t gva; struct x86_exception e; struct { u64 eptp, gpa; } operand; + int i; if (!(vmx->nested.msrs.secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) || @@ -5148,27 +5233,49 @@ static int handle_invept(struct kvm_vcpu *vcpu) /* According to the Intel VMX instruction reference, the memory * operand is read even if it isn't needed (e.g., for type==global) */ - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu), vmx_instruction_info, false, sizeof(operand), &gva)) return 1; if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) { - kvm_inject_page_fault(vcpu, &e); + kvm_inject_emulated_page_fault(vcpu, &e); return 1; } - switch (type) { - case VMX_EPT_EXTENT_GLOBAL: - case VMX_EPT_EXTENT_CONTEXT: /* - * TODO: Sync the necessary shadow EPT roots here, rather than - * at the next emulated VM-entry. + * Nested EPT roots are always held through guest_mmu, + * not root_mmu. */ + mmu = &vcpu->arch.guest_mmu; + + switch (type) { + case VMX_EPT_EXTENT_CONTEXT: + if (!nested_vmx_check_eptp(vcpu, operand.eptp)) + return nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + + roots_to_free = 0; + if (nested_ept_root_matches(mmu->root_hpa, mmu->root_pgd, + operand.eptp)) + roots_to_free |= KVM_MMU_ROOT_CURRENT; + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + if (nested_ept_root_matches(mmu->prev_roots[i].hpa, + mmu->prev_roots[i].pgd, + operand.eptp)) + roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); + } + break; + case VMX_EPT_EXTENT_GLOBAL: + roots_to_free = KVM_MMU_ROOTS_ALL; break; default: BUG(); break; } + if (roots_to_free) + kvm_mmu_free_roots(vcpu, mmu, roots_to_free); + return nested_vmx_succeed(vcpu); } @@ -5208,11 +5315,11 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) /* according to the intel vmx instruction reference, the memory * operand is read even if it isn't needed (e.g., for type==global) */ - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu), vmx_instruction_info, false, sizeof(operand), &gva)) return 1; if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) { - kvm_inject_page_fault(vcpu, &e); + kvm_inject_emulated_page_fault(vcpu, &e); return 1; } if (operand.vpid >> 16) @@ -5226,27 +5333,37 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) is_noncanonical_address(operand.gla, vcpu)) return nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); - if (cpu_has_vmx_invvpid_individual_addr()) { - __invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR, - vpid02, operand.gla); - } else - __vmx_flush_tlb(vcpu, vpid02, false); + vpid_sync_vcpu_addr(vpid02, operand.gla); break; case VMX_VPID_EXTENT_SINGLE_CONTEXT: case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL: if (!operand.vpid) return nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); - __vmx_flush_tlb(vcpu, vpid02, false); + vpid_sync_context(vpid02); break; case VMX_VPID_EXTENT_ALL_CONTEXT: - __vmx_flush_tlb(vcpu, vpid02, false); + vpid_sync_context(vpid02); break; default: WARN_ON_ONCE(1); return kvm_skip_emulated_instruction(vcpu); } + /* + * Sync the shadow page tables if EPT is disabled, L1 is invalidating + * linear mappings for L2 (tagged with L2's VPID). Free all roots as + * VPIDs are not tracked in the MMU role. + * + * Note, this operates on root_mmu, not guest_mmu, as L1 and L2 share + * an MMU when EPT is disabled. + * + * TODO: sync only the affected SPTEs for INVDIVIDUAL_ADDR. + */ + if (!enable_ept) + kvm_mmu_free_roots(vcpu, &vcpu->arch.root_mmu, + KVM_MMU_ROOTS_ALL); + return nested_vmx_succeed(vcpu); } @@ -5327,8 +5444,8 @@ static int handle_vmfunc(struct kvm_vcpu *vcpu) fail: nested_vmx_vmexit(vcpu, vmx->exit_reason, - vmcs_read32(VM_EXIT_INTR_INFO), - vmcs_readl(EXIT_QUALIFICATION)); + vmx_get_intr_info(vcpu), + vmx_get_exit_qual(vcpu)); return 1; } @@ -5379,7 +5496,7 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + exit_qualification = vmx_get_exit_qual(vcpu); port = exit_qualification >> 16; size = (exit_qualification & 7) + 1; @@ -5433,7 +5550,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + unsigned long exit_qualification = vmx_get_exit_qual(vcpu); int cr = exit_qualification & 15; int reg; unsigned long val; @@ -5449,15 +5566,6 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, return true; break; case 3: - if ((vmcs12->cr3_target_count >= 1 && - vmcs12->cr3_target_value0 == val) || - (vmcs12->cr3_target_count >= 2 && - vmcs12->cr3_target_value1 == val) || - (vmcs12->cr3_target_count >= 3 && - vmcs12->cr3_target_value2 == val) || - (vmcs12->cr3_target_count >= 4 && - vmcs12->cr3_target_value3 == val)) - return false; if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING)) return true; break; @@ -5551,49 +5659,85 @@ static bool nested_vmx_exit_handled_mtf(struct vmcs12 *vmcs12) } /* - * Return true if we should exit from L2 to L1 to handle an exit, or false if we - * should handle it ourselves in L0 (and then continue L2). Only call this - * when in is_guest_mode (L2). + * Return true if L0 wants to handle an exit from L2 regardless of whether or not + * L1 wants the exit. Only call this when in is_guest_mode (L2). */ -bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) +static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) { - u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - - WARN_ON_ONCE(vmx->nested.nested_run_pending); - - if (unlikely(vmx->fail)) { - trace_kvm_nested_vmenter_failed( - "hardware VM-instruction error: ", - vmcs_read32(VM_INSTRUCTION_ERROR)); - return true; - } - - trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason, - vmcs_readl(EXIT_QUALIFICATION), - vmx->idt_vectoring_info, - intr_info, - vmcs_read32(VM_EXIT_INTR_ERROR_CODE), - KVM_ISA_VMX); + u32 intr_info; switch (exit_reason) { case EXIT_REASON_EXCEPTION_NMI: + intr_info = vmx_get_intr_info(vcpu); if (is_nmi(intr_info)) - return false; + return true; else if (is_page_fault(intr_info)) - return !vmx->vcpu.arch.apf.host_apf_reason && enable_ept; + return vcpu->arch.apf.host_apf_flags || !enable_ept; else if (is_debug(intr_info) && vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - return false; + return true; else if (is_breakpoint(intr_info) && vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) - return false; + return true; + return false; + case EXIT_REASON_EXTERNAL_INTERRUPT: + return true; + case EXIT_REASON_MCE_DURING_VMENTRY: + return true; + case EXIT_REASON_EPT_VIOLATION: + /* + * L0 always deals with the EPT violation. If nested EPT is + * used, and the nested mmu code discovers that the address is + * missing in the guest EPT table (EPT12), the EPT violation + * will be injected with nested_ept_inject_page_fault() + */ + return true; + case EXIT_REASON_EPT_MISCONFIG: + /* + * L2 never uses directly L1's EPT, but rather L0's own EPT + * table (shadow on EPT) or a merged EPT table that L0 built + * (EPT on EPT). So any problems with the structure of the + * table is L0's fault. + */ + return true; + case EXIT_REASON_PREEMPTION_TIMER: + return true; + case EXIT_REASON_PML_FULL: + /* We emulate PML support to L1. */ + return true; + case EXIT_REASON_VMFUNC: + /* VM functions are emulated through L2->L0 vmexits. */ + return true; + case EXIT_REASON_ENCLS: + /* SGX is never exposed to L1 */ + return true; + default: + break; + } + return false; +} + +/* + * Return 1 if L1 wants to intercept an exit from L2. Only call this when in + * is_guest_mode (L2). + */ +static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu, u32 exit_reason) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + u32 intr_info; + + switch (exit_reason) { + case EXIT_REASON_EXCEPTION_NMI: + intr_info = vmx_get_intr_info(vcpu); + if (is_nmi(intr_info)) + return true; + else if (is_page_fault(intr_info)) + return true; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); case EXIT_REASON_EXTERNAL_INTERRUPT: - return false; + return nested_exit_on_intr(vcpu); case EXIT_REASON_TRIPLE_FAULT: return true; case EXIT_REASON_INTERRUPT_WINDOW: @@ -5658,7 +5802,7 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) nested_cpu_has2(vmcs12, SECONDARY_EXEC_PAUSE_LOOP_EXITING); case EXIT_REASON_MCE_DURING_VMENTRY: - return false; + return true; case EXIT_REASON_TPR_BELOW_THRESHOLD: return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW); case EXIT_REASON_APIC_ACCESS: @@ -5670,22 +5814,6 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) * delivery" only come from vmcs12. */ return true; - case EXIT_REASON_EPT_VIOLATION: - /* - * L0 always deals with the EPT violation. If nested EPT is - * used, and the nested mmu code discovers that the address is - * missing in the guest EPT table (EPT12), the EPT violation - * will be injected with nested_ept_inject_page_fault() - */ - return false; - case EXIT_REASON_EPT_MISCONFIG: - /* - * L2 never uses directly L1's EPT, but rather L0's own EPT - * table (shadow on EPT) or a merged EPT table that L0 built - * (EPT on EPT). So any problems with the structure of the - * table is L0's fault. - */ - return false; case EXIT_REASON_INVPCID: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_INVPCID) && @@ -5702,17 +5830,6 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) * the XSS exit bitmap in vmcs12. */ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); - case EXIT_REASON_PREEMPTION_TIMER: - return false; - case EXIT_REASON_PML_FULL: - /* We emulate PML support to L1. */ - return false; - case EXIT_REASON_VMFUNC: - /* VM functions are emulated through L2->L0 vmexits. */ - return false; - case EXIT_REASON_ENCLS: - /* SGX is never exposed to L1 */ - return false; case EXIT_REASON_UMWAIT: case EXIT_REASON_TPAUSE: return nested_cpu_has2(vmcs12, @@ -5722,6 +5839,67 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) } } +/* + * Conditionally reflect a VM-Exit into L1. Returns %true if the VM-Exit was + * reflected into L1. + */ +bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 exit_reason = vmx->exit_reason; + unsigned long exit_qual; + u32 exit_intr_info; + + WARN_ON_ONCE(vmx->nested.nested_run_pending); + + /* + * Late nested VM-Fail shares the same flow as nested VM-Exit since KVM + * has already loaded L2's state. + */ + if (unlikely(vmx->fail)) { + trace_kvm_nested_vmenter_failed( + "hardware VM-instruction error: ", + vmcs_read32(VM_INSTRUCTION_ERROR)); + exit_intr_info = 0; + exit_qual = 0; + goto reflect_vmexit; + } + + exit_intr_info = vmx_get_intr_info(vcpu); + exit_qual = vmx_get_exit_qual(vcpu); + + trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason, exit_qual, + vmx->idt_vectoring_info, exit_intr_info, + vmcs_read32(VM_EXIT_INTR_ERROR_CODE), + KVM_ISA_VMX); + + /* If L0 (KVM) wants the exit, it trumps L1's desires. */ + if (nested_vmx_l0_wants_exit(vcpu, exit_reason)) + return false; + + /* If L1 doesn't want the exit, handle it in L0. */ + if (!nested_vmx_l1_wants_exit(vcpu, exit_reason)) + return false; + + /* + * vmcs.VM_EXIT_INTR_INFO is only valid for EXCEPTION_NMI exits. For + * EXTERNAL_INTERRUPT, the value for vmcs12->vm_exit_intr_info would + * need to be synthesized by querying the in-kernel LAPIC, but external + * interrupts are never reflected to L1 so it's a non-issue. + */ + if ((exit_intr_info & + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) == + (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + + vmcs12->vm_exit_intr_error_code = + vmcs_read32(VM_EXIT_INTR_ERROR_CODE); + } + +reflect_vmexit: + nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info, exit_qual); + return true; +} static int vmx_get_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, @@ -5733,8 +5911,10 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, .flags = 0, .format = KVM_STATE_NESTED_FORMAT_VMX, .size = sizeof(kvm_state), + .hdr.vmx.flags = 0, .hdr.vmx.vmxon_pa = -1ull, .hdr.vmx.vmcs12_pa = -1ull, + .hdr.vmx.preemption_timer_deadline = 0, }; struct kvm_vmx_nested_state_data __user *user_vmx_nested_state = &user_kvm_nested_state->data.vmx[0]; @@ -5776,6 +5956,14 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (vmx->nested.mtf_pending) kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING; + + if (nested_cpu_has_preemption_timer(vmcs12) && + vmx->nested.has_preemption_timer_deadline) { + kvm_state.hdr.vmx.flags |= + KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE; + kvm_state.hdr.vmx.preemption_timer_deadline = + vmx->nested.preemption_timer_deadline; + } } } @@ -5821,7 +6009,6 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, get_shadow_vmcs12(vcpu), VMCS12_SIZE)) return -EFAULT; } - out: return kvm_state.size; } @@ -5844,7 +6031,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12; - u32 exit_qual; + enum vm_entry_failure_code ignored; struct kvm_vmx_nested_state_data __user *user_vmx_nested_state = &user_kvm_nested_state->data.vmx[0]; int ret; @@ -5983,9 +6170,15 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, goto error_guest_mode; } + if (kvm_state->hdr.vmx.flags & KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) { + vmx->nested.has_preemption_timer_deadline = true; + vmx->nested.preemption_timer_deadline = + kvm_state->hdr.vmx.preemption_timer_deadline; + } + if (nested_vmx_check_controls(vcpu, vmcs12) || nested_vmx_check_host_state(vcpu, vmcs12) || - nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual)) + nested_vmx_check_guest_state(vcpu, vmcs12, &ignored)) goto error_guest_mode; vmx->nested.dirty_vmcs12 = true; @@ -6031,7 +6224,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) * reason is that if one of these bits is necessary, it will appear * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control * fields of vmcs01 and vmcs02, will turn these bits off - and - * nested_vmx_exit_reflected() will not pass related exits to L1. + * nested_vmx_l1_wants_exit() will not pass related exits to L1. * These rules have exceptions below. */ @@ -6259,8 +6452,7 @@ void nested_vmx_hardware_unsetup(void) } } -__init int nested_vmx_hardware_setup(struct kvm_x86_ops *ops, - int (*exit_handlers[])(struct kvm_vcpu *)) +__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) { int i; @@ -6296,12 +6488,15 @@ __init int nested_vmx_hardware_setup(struct kvm_x86_ops *ops, exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid; exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc; - ops->check_nested_events = vmx_check_nested_events; - ops->get_nested_state = vmx_get_nested_state; - ops->set_nested_state = vmx_set_nested_state; - ops->get_vmcs12_pages = nested_get_vmcs12_pages; - ops->nested_enable_evmcs = nested_enable_evmcs; - ops->nested_get_evmcs_version = nested_get_evmcs_version; - return 0; } + +struct kvm_x86_nested_ops vmx_nested_ops = { + .check_events = vmx_check_nested_events, + .hv_timer_pending = nested_vmx_preemption_timer_pending, + .get_state = vmx_get_nested_state, + .set_state = vmx_set_nested_state, + .get_vmcs12_pages = nested_get_vmcs12_pages, + .enable_evmcs = nested_enable_evmcs, + .get_evmcs_version = nested_get_evmcs_version, +}; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index ac56aefa49e3..758bccc26cf9 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -19,14 +19,13 @@ enum nvmx_vmentry_status { void vmx_leave_nested(struct kvm_vcpu *vcpu); void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps); void nested_vmx_hardware_unsetup(void); -__init int nested_vmx_hardware_setup(struct kvm_x86_ops *ops, - int (*exit_handlers[])(struct kvm_vcpu *)); +__init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry); -bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason); -void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, +bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu); +void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, u32 exit_intr_info, unsigned long exit_qualification); void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu); int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); @@ -62,6 +61,13 @@ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu) vmx->nested.hv_evmcs; } +static inline u16 nested_get_vpid02(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + return vmx->nested.vpid02 ? vmx->nested.vpid02 : vmx->vpid; +} + static inline unsigned long nested_ept_get_eptp(struct kvm_vcpu *vcpu) { /* return the page table to be shadowed - in our case, EPT12 */ @@ -74,34 +80,6 @@ static inline bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu) } /* - * Reflect a VM Exit into L1. - */ -static inline int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu, - u32 exit_reason) -{ - u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - - /* - * At this point, the exit interruption info in exit_intr_info - * is only valid for EXCEPTION_NMI exits. For EXTERNAL_INTERRUPT - * we need to query the in-kernel LAPIC. - */ - WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT); - if ((exit_intr_info & - (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) == - (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - - vmcs12->vm_exit_intr_error_code = - vmcs_read32(VM_EXIT_INTR_ERROR_CODE); - } - - nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info, - vmcs_readl(EXIT_QUALIFICATION)); - return 1; -} - -/* * Return the cr0 value that a nested guest would read. This is a combination * of the real cr0 used to run the guest (guest_cr0), and the bits shadowed by * its hypervisor (cr0_read_shadow). @@ -246,6 +224,11 @@ static inline bool nested_cpu_has_save_preemption_timer(struct vmcs12 *vmcs12) VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; } +static inline bool nested_exit_on_nmi(struct kvm_vcpu *vcpu) +{ + return nested_cpu_has_nmi_exiting(get_vmcs12(vcpu)); +} + /* * In nested virtualization, check if L1 asked to exit on external interrupts. * For most existing hypervisors, this will always return true. @@ -299,4 +282,6 @@ static inline bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val) #define nested_guest_cr4_valid nested_cr4_valid #define nested_host_cr4_valid nested_cr4_valid +extern struct kvm_x86_nested_ops vmx_nested_ops; + #endif /* __KVM_X86_VMX_NESTED_H */ diff --git a/arch/x86/kvm/vmx/ops.h b/arch/x86/kvm/vmx/ops.h index 19717d0a1100..5f1ac002b4b6 100644 --- a/arch/x86/kvm/vmx/ops.h +++ b/arch/x86/kvm/vmx/ops.h @@ -268,42 +268,38 @@ static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa) vmx_asm2(invept, "r"(ext), "m"(operand), ext, eptp, gpa); } -static inline bool vpid_sync_vcpu_addr(int vpid, gva_t addr) -{ - if (vpid == 0) - return true; - - if (cpu_has_vmx_invvpid_individual_addr()) { - __invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR, vpid, addr); - return true; - } - - return false; -} - static inline void vpid_sync_vcpu_single(int vpid) { if (vpid == 0) return; - if (cpu_has_vmx_invvpid_single()) - __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vpid, 0); + __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vpid, 0); } static inline void vpid_sync_vcpu_global(void) { - if (cpu_has_vmx_invvpid_global()) - __invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0); + __invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0); } static inline void vpid_sync_context(int vpid) { if (cpu_has_vmx_invvpid_single()) vpid_sync_vcpu_single(vpid); - else + else if (vpid != 0) vpid_sync_vcpu_global(); } +static inline void vpid_sync_vcpu_addr(int vpid, gva_t addr) +{ + if (vpid == 0) + return; + + if (cpu_has_vmx_invvpid_individual_addr()) + __invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR, vpid, addr); + else + vpid_sync_context(vpid); +} + static inline void ept_sync_global(void) { __invept(VMX_EPT_EXTENT_GLOBAL, 0, 0); diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 7c857737b438..d33d890b605f 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -18,6 +18,8 @@ #include "nested.h" #include "pmu.h" +#define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0) + static struct kvm_event_hw_type_mapping intel_arch_events[] = { /* Index must match CPUID 0x0A.EBX bit vector */ [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, @@ -150,6 +152,22 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, return &counters[array_index_nospec(idx, num_counters)]; } +static inline bool fw_writes_is_enabled(struct kvm_vcpu *vcpu) +{ + if (!guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) + return false; + + return vcpu->arch.perf_capabilities & PMU_CAP_FW_WRITES; +} + +static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr) +{ + if (!fw_writes_is_enabled(pmu_to_vcpu(pmu))) + return NULL; + + return get_gp_pmc(pmu, msr, MSR_IA32_PMC0); +} + static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -162,10 +180,13 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) case MSR_CORE_PERF_GLOBAL_OVF_CTRL: ret = pmu->version > 1; break; + case MSR_IA32_PERF_CAPABILITIES: + ret = guest_cpuid_has(vcpu, X86_FEATURE_PDCM); + break; default: ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) || get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) || - get_fixed_pmc(pmu, msr); + get_fixed_pmc(pmu, msr) || get_fw_gp_pmc(pmu, msr); break; } @@ -184,35 +205,45 @@ static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) return pmc; } -static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *pmc; + u32 msr = msr_info->index; switch (msr) { case MSR_CORE_PERF_FIXED_CTR_CTRL: - *data = pmu->fixed_ctr_ctrl; + msr_info->data = pmu->fixed_ctr_ctrl; return 0; case MSR_CORE_PERF_GLOBAL_STATUS: - *data = pmu->global_status; + msr_info->data = pmu->global_status; return 0; case MSR_CORE_PERF_GLOBAL_CTRL: - *data = pmu->global_ctrl; + msr_info->data = pmu->global_ctrl; return 0; case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - *data = pmu->global_ovf_ctrl; + msr_info->data = pmu->global_ovf_ctrl; + return 0; + case MSR_IA32_PERF_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) + return 1; + msr_info->data = vcpu->arch.perf_capabilities; return 0; default: - if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) { + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || + (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) { u64 val = pmc_read_counter(pmc); - *data = val & pmu->counter_bitmask[KVM_PMC_GP]; + msr_info->data = + val & pmu->counter_bitmask[KVM_PMC_GP]; return 0; } else if ((pmc = get_fixed_pmc(pmu, msr))) { u64 val = pmc_read_counter(pmc); - *data = val & pmu->counter_bitmask[KVM_PMC_FIXED]; + msr_info->data = + val & pmu->counter_bitmask[KVM_PMC_FIXED]; return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { - *data = pmc->eventsel; + msr_info->data = pmc->eventsel; return 0; } } @@ -258,9 +289,22 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } break; + case MSR_IA32_PERF_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM) ? + (data & ~vmx_get_perf_capabilities()) : data) + return 1; + vcpu->arch.perf_capabilities = data; + return 0; default: - if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) { - if (!msr_info->host_initiated) + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || + (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) { + if ((msr & MSR_PMC_FULL_WIDTH_BIT) && + (data & ~pmu->counter_bitmask[KVM_PMC_GP])) + return 1; + if (!msr_info->host_initiated && + !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; pmc->counter += data - pmc_read_counter(pmc); if (pmc->perf_event) @@ -300,6 +344,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->counter_bitmask[KVM_PMC_FIXED] = 0; pmu->version = 0; pmu->reserved_bits = 0xffffffff00200000ull; + vcpu->arch.perf_capabilities = 0; entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); if (!entry) @@ -312,6 +357,8 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) return; perf_get_x86_pmu_capability(&x86_pmu); + if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) + vcpu->arch.perf_capabilities = vmx_get_perf_capabilities(); pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, x86_pmu.num_counters_gp); diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 481ad879197b..5c0ff80b85c0 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -19,7 +19,7 @@ struct vmcs_hdr { struct vmcs { struct vmcs_hdr hdr; u32 abort; - char data[0]; + char data[]; }; DECLARE_PER_CPU(struct vmcs *, current_vmcs); diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c index 53dfb401316d..c8e51c004f78 100644 --- a/arch/x86/kvm/vmx/vmcs12.c +++ b/arch/x86/kvm/vmx/vmcs12.c @@ -115,10 +115,6 @@ const unsigned short vmcs_field_to_offset_table[] = { FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask), FIELD(CR0_READ_SHADOW, cr0_read_shadow), FIELD(CR4_READ_SHADOW, cr4_read_shadow), - FIELD(CR3_TARGET_VALUE0, cr3_target_value0), - FIELD(CR3_TARGET_VALUE1, cr3_target_value1), - FIELD(CR3_TARGET_VALUE2, cr3_target_value2), - FIELD(CR3_TARGET_VALUE3, cr3_target_value3), FIELD(EXIT_QUALIFICATION, exit_qualification), FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address), FIELD(GUEST_CR0, guest_cr0), diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index d0c6df373f67..80232daf00ff 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -80,10 +80,7 @@ struct __packed vmcs12 { natural_width cr4_guest_host_mask; natural_width cr0_read_shadow; natural_width cr4_read_shadow; - natural_width cr3_target_value0; - natural_width cr3_target_value1; - natural_width cr3_target_value2; - natural_width cr3_target_value3; + natural_width dead_space[4]; /* Last remnants of cr3_target_value[0-3]. */ natural_width exit_qualification; natural_width guest_linear_address; natural_width guest_cr0; @@ -263,10 +260,7 @@ static inline void vmx_check_vmcs12_offsets(void) CHECK_OFFSET(cr4_guest_host_mask, 352); CHECK_OFFSET(cr0_read_shadow, 360); CHECK_OFFSET(cr4_read_shadow, 368); - CHECK_OFFSET(cr3_target_value0, 376); - CHECK_OFFSET(cr3_target_value1, 384); - CHECK_OFFSET(cr3_target_value2, 392); - CHECK_OFFSET(cr3_target_value3, 400); + CHECK_OFFSET(dead_space, 376); CHECK_OFFSET(exit_qualification, 408); CHECK_OFFSET(guest_linear_address, 416); CHECK_OFFSET(guest_cr0, 424); diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 51d1a82742fd..e0a182cb3cdd 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -166,13 +166,13 @@ SYM_FUNC_START(__vmx_vcpu_run) mov WORD_SIZE(%_ASM_SP), %_ASM_AX /* Save all guest registers, including RAX from the stack */ - __ASM_SIZE(pop) VCPU_RAX(%_ASM_AX) - mov %_ASM_CX, VCPU_RCX(%_ASM_AX) - mov %_ASM_DX, VCPU_RDX(%_ASM_AX) - mov %_ASM_BX, VCPU_RBX(%_ASM_AX) - mov %_ASM_BP, VCPU_RBP(%_ASM_AX) - mov %_ASM_SI, VCPU_RSI(%_ASM_AX) - mov %_ASM_DI, VCPU_RDI(%_ASM_AX) + pop VCPU_RAX(%_ASM_AX) + mov %_ASM_CX, VCPU_RCX(%_ASM_AX) + mov %_ASM_DX, VCPU_RDX(%_ASM_AX) + mov %_ASM_BX, VCPU_RBX(%_ASM_AX) + mov %_ASM_BP, VCPU_RBP(%_ASM_AX) + mov %_ASM_SI, VCPU_RSI(%_ASM_AX) + mov %_ASM_DI, VCPU_RDI(%_ASM_AX) #ifdef CONFIG_X86_64 mov %r8, VCPU_R8 (%_ASM_AX) mov %r9, VCPU_R9 (%_ASM_AX) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 89c766fad889..170cc76a581f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -437,6 +437,11 @@ static const struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; +static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) +{ + vmx->segment_cache.bitmask = 0; +} + static unsigned long host_idt_base; /* @@ -1306,10 +1311,12 @@ after_clear_sn: pi_set_on(pi_desc); } -void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) +void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, + struct loaded_vmcs *buddy) { struct vcpu_vmx *vmx = to_vmx(vcpu); bool already_loaded = vmx->loaded_vmcs->cpu == cpu; + struct vmcs *prev; if (!already_loaded) { loaded_vmcs_clear(vmx->loaded_vmcs); @@ -1328,16 +1335,28 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) local_irq_enable(); } - if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { + prev = per_cpu(current_vmcs, cpu); + if (prev != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); - indirect_branch_prediction_barrier(); + + /* + * No indirect branch prediction barrier needed when switching + * the active VMCS within a guest, e.g. on nested VM-Enter. + * The L1 VMM can protect itself with retpolines, IBPB or IBRS. + */ + if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)) + indirect_branch_prediction_barrier(); } if (!already_loaded) { void *gdt = get_current_gdt_ro(); unsigned long sysenter_esp; + /* + * Flush all EPTP/VPID contexts, the new pCPU may have stale + * TLB entries from its previous association with the vCPU. + */ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); /* @@ -1364,11 +1383,11 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu) * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. */ -void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - vmx_vcpu_load_vmcs(vcpu, cpu); + vmx_vcpu_load_vmcs(vcpu, cpu, NULL); vmx_vcpu_pi_load(vcpu, cpu); @@ -1546,7 +1565,7 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { - unsigned long rip; + unsigned long rip, orig_rip; /* * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on @@ -1558,8 +1577,17 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) */ if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) { - rip = kvm_rip_read(vcpu); - rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); + orig_rip = kvm_rip_read(vcpu); + rip = orig_rip + vmcs_read32(VM_EXIT_INSTRUCTION_LEN); +#ifdef CONFIG_X86_64 + /* + * We need to mask out the high 32 bits of RIP if not in 64-bit + * mode, but just finding out that we are in 64-bit mode is + * quite expensive. Only do it if there was a carry. + */ + if (unlikely(((rip ^ orig_rip) >> 31) == 3) && !is_64_bit_mode(vcpu)) + rip = (u32)rip; +#endif kvm_rip_write(vcpu, rip); } else { if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) @@ -1712,17 +1740,6 @@ static void setup_msrs(struct vcpu_vmx *vmx) vmx_update_msr_bitmap(&vmx->vcpu); } -static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu) -{ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - - if (is_guest_mode(vcpu) && - (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)) - return vcpu->arch.tsc_offset - vmcs12->tsc_offset; - - return vcpu->arch.tsc_offset; -} - static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -1771,6 +1788,9 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) if (!nested) return 1; return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); + case MSR_IA32_PERF_CAPABILITIES: + msr->data = vmx_get_perf_capabilities(); + return 0; default: return 1; } @@ -1926,6 +1946,16 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } +static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, + u64 data) +{ +#ifdef CONFIG_X86_64 + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return (u32)data; +#endif + return (unsigned long)data; +} + /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -1963,13 +1993,17 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmcs_write32(GUEST_SYSENTER_CS, data); break; case MSR_IA32_SYSENTER_EIP: - if (is_guest_mode(vcpu)) + if (is_guest_mode(vcpu)) { + data = nested_vmx_truncate_sysenter_addr(vcpu, data); get_vmcs12(vcpu)->guest_sysenter_eip = data; + } vmcs_writel(GUEST_SYSENTER_EIP, data); break; case MSR_IA32_SYSENTER_ESP: - if (is_guest_mode(vcpu)) + if (is_guest_mode(vcpu)) { + data = nested_vmx_truncate_sysenter_addr(vcpu, data); get_vmcs12(vcpu)->guest_sysenter_esp = data; + } vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_DEBUGCTLMSR: @@ -2187,6 +2221,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { + unsigned long guest_owned_bits; + kvm_register_mark_available(vcpu, reg); switch (reg) { @@ -2200,10 +2236,22 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) if (enable_ept) ept_save_pdptrs(vcpu); break; + case VCPU_EXREG_CR0: + guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; + + vcpu->arch.cr0 &= ~guest_owned_bits; + vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & guest_owned_bits; + break; case VCPU_EXREG_CR3: if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu))) vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); break; + case VCPU_EXREG_CR4: + guest_owned_bits = vcpu->arch.cr4_guest_owned_bits; + + vcpu->arch.cr4 &= ~guest_owned_bits; + vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & guest_owned_bits; + break; default: WARN_ON_ONCE(1); break; @@ -2837,34 +2885,64 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) +static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu) { - int vpid = to_vmx(vcpu)->vpid; - - if (!vpid_sync_vcpu_addr(vpid, addr)) - vpid_sync_context(vpid); + struct vcpu_vmx *vmx = to_vmx(vcpu); /* - * If VPIDs are not supported or enabled, then the above is a no-op. - * But we don't really need a TLB flush in that case anyway, because - * each VM entry/exit includes an implicit flush when VPID is 0. + * INVEPT must be issued when EPT is enabled, irrespective of VPID, as + * the CPU is not required to invalidate guest-physical mappings on + * VM-Entry, even if VPID is disabled. Guest-physical mappings are + * associated with the root EPT structure and not any particular VPID + * (INVVPID also isn't required to invalidate guest-physical mappings). */ + if (enable_ept) { + ept_sync_global(); + } else if (enable_vpid) { + if (cpu_has_vmx_invvpid_global()) { + vpid_sync_vcpu_global(); + } else { + vpid_sync_vcpu_single(vmx->vpid); + vpid_sync_vcpu_single(vmx->nested.vpid02); + } + } } -static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) +static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu) { - ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; + u64 root_hpa = vcpu->arch.mmu->root_hpa; - vcpu->arch.cr0 &= ~cr0_guest_owned_bits; - vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits; + /* No flush required if the current context is invalid. */ + if (!VALID_PAGE(root_hpa)) + return; + + if (enable_ept) + ept_sync_context(construct_eptp(vcpu, root_hpa)); + else if (!is_guest_mode(vcpu)) + vpid_sync_context(to_vmx(vcpu)->vpid); + else + vpid_sync_context(nested_get_vpid02(vcpu)); } -static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) +static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr) { - ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits; + /* + * vpid_sync_vcpu_addr() is a nop if vmx->vpid==0, see the comment in + * vmx_flush_tlb_guest() for an explanation of why this is ok. + */ + vpid_sync_vcpu_addr(to_vmx(vcpu)->vpid, addr); +} - vcpu->arch.cr4 &= ~cr4_guest_owned_bits; - vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & cr4_guest_owned_bits; +static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) +{ + /* + * vpid_sync_context() is a nop if vmx->vpid==0, e.g. if enable_vpid==0 + * or a vpid couldn't be allocated for this vCPU. VM-Enter and VM-Exit + * are required to flush GVA->{G,H}PA mappings from the TLB if vpid is + * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed), + * i.e. no explicit INVVPID is necessary. + */ + vpid_sync_context(to_vmx(vcpu)->vpid); } static void ept_load_pdptrs(struct kvm_vcpu *vcpu) @@ -2886,12 +2964,13 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - if (is_pae_paging(vcpu)) { - mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0); - mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1); - mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); - mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); - } + if (WARN_ON_ONCE(!is_pae_paging(vcpu))) + return; + + mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0); + mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1); + mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2); + mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3); kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR); } @@ -2955,20 +3034,27 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, hw_cr0); vcpu->arch.cr0 = cr0; + kvm_register_mark_available(vcpu, VCPU_EXREG_CR0); /* depends on vcpu->arch.cr0 to be set to a new value */ vmx->emulation_required = emulation_required(vcpu); } -static int get_ept_level(struct kvm_vcpu *vcpu) +static int vmx_get_tdp_level(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu))) - return vmx_eptp_page_walk_level(nested_ept_get_eptp(vcpu)); if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48)) return 5; return 4; } +static int get_ept_level(struct kvm_vcpu *vcpu) +{ + if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu))) + return vmx_eptp_page_walk_level(nested_ept_get_eptp(vcpu)); + + return vmx_get_tdp_level(vcpu); +} + u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) { u64 eptp = VMX_EPTP_MT_WB; @@ -2983,16 +3069,15 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) return eptp; } -void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long cr3) +void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd) { struct kvm *kvm = vcpu->kvm; bool update_guest_cr3 = true; unsigned long guest_cr3; u64 eptp; - guest_cr3 = cr3; if (enable_ept) { - eptp = construct_eptp(vcpu, cr3); + eptp = construct_eptp(vcpu, pgd); vmcs_write64(EPT_POINTER, eptp); if (kvm_x86_ops.tlb_remote_flush) { @@ -3003,16 +3088,15 @@ void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long cr3) spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock); } - /* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */ - if (is_guest_mode(vcpu)) - update_guest_cr3 = false; - else if (!enable_unrestricted_guest && !is_paging(vcpu)) + if (!enable_unrestricted_guest && !is_paging(vcpu)) guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr; else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) guest_cr3 = vcpu->arch.cr3; else /* vmcs01.GUEST_CR3 is already up-to-date. */ update_guest_cr3 = false; ept_load_pdptrs(vcpu); + } else { + guest_cr3 = pgd; } if (update_guest_cr3) @@ -3063,6 +3147,7 @@ int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; vcpu->arch.cr4 = cr4; + kvm_register_mark_available(vcpu, VCPU_EXREG_CR4); if (!enable_unrestricted_guest) { if (enable_ept) { @@ -3851,7 +3936,8 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (pi_test_and_set_on(&vmx->pi_desc)) return 0; - if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) + if (vcpu != kvm_get_running_vcpu() && + !kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); return 0; @@ -4147,8 +4233,7 @@ static void ept_set_mmio_spte_mask(void) * EPT Misconfigurations can be generated if the value of bits 2:0 * of an EPT paging-structure entry is 110b (write/execute). */ - kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK, - VMX_EPT_MISCONFIG_WX_VALUE, 0); + kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE, 0); } #define VMX_XSS_EXIT_BITMAP 0 @@ -4453,31 +4538,54 @@ void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) } } -static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) +bool vmx_nmi_blocked(struct kvm_vcpu *vcpu) { - if (to_vmx(vcpu)->nested.nested_run_pending) - return 0; + if (is_guest_mode(vcpu) && nested_exit_on_nmi(vcpu)) + return false; - if (!enable_vnmi && - to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked) - return 0; + if (!enable_vnmi && to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked) + return true; - return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI - | GUEST_INTR_STATE_NMI)); + return (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI | + GUEST_INTR_STATE_NMI)); } -static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) +static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { if (to_vmx(vcpu)->nested.nested_run_pending) - return false; + return -EBUSY; + + /* An NMI must not be injected into L2 if it's supposed to VM-Exit. */ + if (for_injection && is_guest_mode(vcpu) && nested_exit_on_nmi(vcpu)) + return -EBUSY; + + return !vmx_nmi_blocked(vcpu); +} +bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu) +{ if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) - return true; + return false; - return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && - !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); + return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); +} + +static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) +{ + if (to_vmx(vcpu)->nested.nested_run_pending) + return -EBUSY; + + /* + * An IRQ must not be injected into L2 if it's supposed to VM-Exit, + * e.g. if the IRQ arrived asynchronously after checking nested events. + */ + if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) + return -EBUSY; + + return !vmx_interrupt_blocked(vcpu); } static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) @@ -4518,10 +4626,8 @@ static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) return false; /* fall through */ case DB_VECTOR: - if (vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - return false; - /* fall through */ + return !(vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)); case DE_VECTOR: case OF_VECTOR: case BR_VECTOR: @@ -4616,7 +4722,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) u32 vect_info; vect_info = vmx->idt_vectoring_info; - intr_info = vmx->exit_intr_info; + intr_info = vmx_get_intr_info(vcpu); if (is_machine_check(intr_info) || is_nmi(intr_info)) return 1; /* handled by handle_exception_nmi_irqoff() */ @@ -4660,9 +4766,9 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) } if (is_page_fault(intr_info)) { - cr2 = vmcs_readl(EXIT_QUALIFICATION); + cr2 = vmx_get_exit_qual(vcpu); /* EPT won't cause page fault directly */ - WARN_ON_ONCE(!vcpu->arch.apf.host_apf_reason && enable_ept); + WARN_ON_ONCE(!vcpu->arch.apf.host_apf_flags && enable_ept); return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0); } @@ -4673,7 +4779,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) switch (ex_no) { case DB_VECTOR: - dr6 = vmcs_readl(EXIT_QUALIFICATION); + dr6 = vmx_get_exit_qual(vcpu); if (!(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { if (is_icebp(intr_info)) @@ -4740,7 +4846,7 @@ static int handle_io(struct kvm_vcpu *vcpu) int size, in, string; unsigned port; - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + exit_qualification = vmx_get_exit_qual(vcpu); string = (exit_qualification & 16) != 0; ++vcpu->stat.io_exits; @@ -4831,7 +4937,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) int err; int ret; - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + exit_qualification = vmx_get_exit_qual(vcpu); cr = exit_qualification & 15; reg = (exit_qualification >> 8) & 15; switch ((exit_qualification >> 4) & 3) { @@ -4908,7 +5014,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) unsigned long exit_qualification; int dr, dr7, reg; - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + exit_qualification = vmx_get_exit_qual(vcpu); dr = exit_qualification & DEBUG_REG_ACCESS_NUM; /* First, if DR does not exist, trigger UD */ @@ -5010,7 +5116,7 @@ static int handle_invd(struct kvm_vcpu *vcpu) static int handle_invlpg(struct kvm_vcpu *vcpu) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + unsigned long exit_qualification = vmx_get_exit_qual(vcpu); kvm_mmu_invlpg(vcpu, exit_qualification); return kvm_skip_emulated_instruction(vcpu); @@ -5042,7 +5148,7 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu) static int handle_apic_access(struct kvm_vcpu *vcpu) { if (likely(fasteoi)) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + unsigned long exit_qualification = vmx_get_exit_qual(vcpu); int access_type, offset; access_type = exit_qualification & APIC_ACCESS_TYPE; @@ -5063,7 +5169,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu) static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + unsigned long exit_qualification = vmx_get_exit_qual(vcpu); int vector = exit_qualification & 0xff; /* EOI-induced VM exit is trap-like and thus no need to adjust IP */ @@ -5073,7 +5179,7 @@ static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) static int handle_apic_write(struct kvm_vcpu *vcpu) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + unsigned long exit_qualification = vmx_get_exit_qual(vcpu); u32 offset = exit_qualification & 0xfff; /* APIC-write VM exit is trap-like and thus no need to adjust IP */ @@ -5094,7 +5200,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) idt_index = (vmx->idt_vectoring_info & VECTORING_INFO_VECTOR_MASK); type = (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK); - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + exit_qualification = vmx_get_exit_qual(vcpu); reason = (u32)exit_qualification >> 30; if (reason == TASK_SWITCH_GATE && idt_v) { @@ -5144,7 +5250,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) gpa_t gpa; u64 error_code; - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + exit_qualification = vmx_get_exit_qual(vcpu); /* * EPT violation happened while executing iret from NMI, @@ -5216,18 +5322,11 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) bool intr_window_requested; unsigned count = 130; - /* - * We should never reach the point where we are emulating L2 - * due to invalid guest state as that means we incorrectly - * allowed a nested VMEntry with an invalid vmcs12. - */ - WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending); - intr_window_requested = exec_controls_get(vmx) & CPU_BASED_INTR_WINDOW_EXITING; while (vmx->emulation_required && count-- != 0) { - if (intr_window_requested && vmx_interrupt_allowed(vcpu)) + if (intr_window_requested && !vmx_interrupt_blocked(vcpu)) return handle_interrupt_window(&vmx->vcpu); if (kvm_test_request(KVM_REQ_EVENT, vcpu)) @@ -5404,13 +5503,13 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) /* According to the Intel instruction reference, the memory operand * is read even if it isn't needed (e.g., for type==all) */ - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu), vmx_instruction_info, false, sizeof(operand), &gva)) return 1; if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) { - kvm_inject_page_fault(vcpu, &e); + kvm_inject_emulated_page_fault(vcpu, &e); return 1; } @@ -5439,11 +5538,11 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) if (kvm_get_active_pcid(vcpu) == operand.pcid) { kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) - if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].cr3) + if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].pgd) == operand.pcid) roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i); @@ -5480,7 +5579,7 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) trace_kvm_pml_full(vcpu->vcpu_id); - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + exit_qualification = vmx_get_exit_qual(vcpu); /* * PML buffer FULL happened while executing iret from NMI, @@ -5499,14 +5598,22 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) return 1; } -static int handle_preemption_timer(struct kvm_vcpu *vcpu) +static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); if (!vmx->req_immediate_exit && - !unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) + !unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) { kvm_lapic_expired_hv_timer(vcpu); + return EXIT_FASTPATH_REENTER_GUEST; + } + + return EXIT_FASTPATH_NONE; +} +static int handle_preemption_timer(struct kvm_vcpu *vcpu) +{ + handle_fastpath_preemption_timer(vcpu); return 1; } @@ -5594,8 +5701,8 @@ static const int kvm_vmx_max_exit_handlers = static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) { - *info1 = vmcs_readl(EXIT_QUALIFICATION); - *info2 = vmcs_read32(VM_EXIT_INTR_INFO); + *info1 = vmx_get_exit_qual(vcpu); + *info2 = vmx_get_intr_info(vcpu); } static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) @@ -5677,7 +5784,6 @@ void dump_vmcs(void) u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control; unsigned long cr4; u64 efer; - int i, n; if (!dump_invalid_vmcs) { pr_warn_ratelimited("set kvm_intel.dump_invalid_vmcs=1 to dump internal KVM state.\n"); @@ -5814,14 +5920,6 @@ void dump_vmcs(void) pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV)); if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT)) pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(EPT_POINTER)); - n = vmcs_read32(CR3_TARGET_COUNT); - for (i = 0; i + 1 < n; i += 4) - pr_err("CR3 target%u=%016lx target%u=%016lx\n", - i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2), - i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2)); - if (i < n) - pr_err("CR3 target%u=%016lx\n", - i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2)); if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING) pr_err("PLE Gap=%08x Window=%08x\n", vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW)); @@ -5834,15 +5932,12 @@ void dump_vmcs(void) * The guest has exited. See if we can fix it or if we need userspace * assistance. */ -static int vmx_handle_exit(struct kvm_vcpu *vcpu, - enum exit_fastpath_completion exit_fastpath) +static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; - trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); - /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before @@ -5853,6 +5948,14 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, if (enable_pml) vmx_flush_pml_buffer(vcpu); + /* + * We should never reach this point with a pending nested VM-Enter, and + * more specifically emulation of L2 due to invalid guest state (see + * below) should never happen as that means we incorrectly allowed a + * nested VM-Enter with an invalid vmcs12. + */ + WARN_ON_ONCE(vmx->nested.nested_run_pending); + /* If guest state is invalid, start emulating */ if (vmx->emulation_required) return handle_invalid_guest_state(vcpu); @@ -5871,8 +5974,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, */ nested_mark_vmcs12_pages_dirty(vcpu); - if (nested_vmx_exit_reflected(vcpu, exit_reason)) - return nested_vmx_reflect_vmexit(vcpu, exit_reason); + if (nested_vmx_reflect_vmexit(vcpu)) + return 1; } if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { @@ -5919,7 +6022,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, if (unlikely(!enable_vnmi && vmx->loaded_vmcs->soft_vnmi_blocked)) { - if (vmx_interrupt_allowed(vcpu)) { + if (!vmx_interrupt_blocked(vcpu)) { vmx->loaded_vmcs->soft_vnmi_blocked = 0; } else if (vmx->loaded_vmcs->vnmi_blocked_time > 1000000000LL && vcpu->arch.nmi_pending) { @@ -5936,10 +6039,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, } } - if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) { - kvm_skip_emulated_instruction(vcpu); + if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; - } if (exit_reason >= kvm_vmx_max_exit_handlers) goto unexpected_vmexit; @@ -6093,7 +6194,15 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) if (flexpriority_enabled) { sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - vmx_flush_tlb(vcpu, true); + kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); + + /* + * Flush the TLB, reloading the APIC access page will + * only do so if its physical address has changed, but + * the guest may have inserted a non-APIC mapping into + * the TLB while the APIC access page was disabled. + */ + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } break; case LAPIC_MODE_X2APIC: @@ -6107,12 +6216,32 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) vmx_update_msr_bitmap(vcpu); } -static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) +static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) { - if (!is_guest_mode(vcpu)) { - vmcs_write64(APIC_ACCESS_ADDR, hpa); - vmx_flush_tlb(vcpu, true); + struct page *page; + + /* Defer reload until vmcs01 is the current VMCS. */ + if (is_guest_mode(vcpu)) { + to_vmx(vcpu)->nested.reload_vmcs01_apic_access_page = true; + return; } + + if (!(secondary_exec_controls_get(to_vmx(vcpu)) & + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) + return; + + page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); + if (is_error_page(page)) + return; + + vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(page)); + vmx_flush_tlb_current(vcpu); + + /* + * Do not pin apic access page in memory, the MMU notifier + * will call us again if it is migrated or swapped out. + */ + put_page(page); } static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) @@ -6230,16 +6359,16 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) { - vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + u32 intr_info = vmx_get_intr_info(&vmx->vcpu); /* if exit due to PF check for async PF */ - if (is_page_fault(vmx->exit_intr_info)) { - vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); + if (is_page_fault(intr_info)) { + vmx->vcpu.arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); /* Handle machine checks before interrupts are enabled */ - } else if (is_machine_check(vmx->exit_intr_info)) { + } else if (is_machine_check(intr_info)) { kvm_machine_check(); /* We need to handle NMIs before interrupts are enabled */ - } else if (is_nmi(vmx->exit_intr_info)) { + } else if (is_nmi(intr_info)) { kvm_before_interrupt(&vmx->vcpu); asm("int $2"); kvm_after_interrupt(&vmx->vcpu); @@ -6254,9 +6383,8 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) unsigned long tmp; #endif gate_desc *desc; - u32 intr_info; + u32 intr_info = vmx_get_intr_info(vcpu); - intr_info = vmcs_read32(VM_EXIT_INTR_INFO); if (WARN_ONCE(!is_external_intr(intr_info), "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; @@ -6269,13 +6397,13 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) asm volatile( #ifdef CONFIG_X86_64 - "mov %%" _ASM_SP ", %[sp]\n\t" - "and $0xfffffffffffffff0, %%" _ASM_SP "\n\t" - "push $%c[ss]\n\t" + "mov %%rsp, %[sp]\n\t" + "and $-16, %%rsp\n\t" + "push %[ss]\n\t" "push %[sp]\n\t" #endif "pushf\n\t" - __ASM_SIZE(push) " $%c[cs]\n\t" + "push %[cs]\n\t" CALL_NOSPEC : #ifdef CONFIG_X86_64 @@ -6284,7 +6412,9 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) ASM_CALL_CONSTRAINT : [thunk_target]"r"(entry), +#ifdef CONFIG_X86_64 [ss]"i"(__KERNEL_DS), +#endif [cs]"i"(__KERNEL_CS) ); @@ -6292,8 +6422,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) } STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff); -static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu, - enum exit_fastpath_completion *exit_fastpath) +static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6301,12 +6430,9 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu, handle_external_interrupt_irqoff(vcpu); else if (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI) handle_exception_nmi_irqoff(vmx); - else if (!is_guest_mode(vcpu) && - vmx->exit_reason == EXIT_REASON_MSR_WRITE) - *exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu); } -static bool vmx_has_emulated_msr(int index) +static bool vmx_has_emulated_msr(u32 index) { switch (index) { case MSR_IA32_SMBASE: @@ -6337,11 +6463,8 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) if (enable_vnmi) { if (vmx->loaded_vmcs->nmi_known_unmasked) return; - /* - * Can't use vmx->exit_intr_info since we're not sure what - * the exit reason is. - */ - exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + + exit_intr_info = vmx_get_intr_info(&vmx->vcpu); unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0; vector = exit_intr_info & INTR_INFO_VECTOR_MASK; /* @@ -6508,13 +6631,27 @@ void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) } } +static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) +{ + switch (to_vmx(vcpu)->exit_reason) { + case EXIT_REASON_MSR_WRITE: + return handle_fastpath_set_msr_irqoff(vcpu); + case EXIT_REASON_PREEMPTION_TIMER: + return handle_fastpath_preemption_timer(vcpu); + default: + return EXIT_FASTPATH_NONE; + } +} + bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched); -static void vmx_vcpu_run(struct kvm_vcpu *vcpu) +static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) { + fastpath_t exit_fastpath; struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; +reenter_guest: /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && vmx->loaded_vmcs->soft_vnmi_blocked)) @@ -6523,7 +6660,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) /* Don't enter VMX if guest state is invalid, let the exit handler start emulation until we arrive back to a valid state */ if (vmx->emulation_required) - return; + return EXIT_FASTPATH_NONE; if (vmx->ple_window_dirty) { vmx->ple_window_dirty = false; @@ -6643,12 +6780,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) loadsegment(es, __USER_DS); #endif - vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) - | (1 << VCPU_EXREG_RFLAGS) - | (1 << VCPU_EXREG_PDPTR) - | (1 << VCPU_EXREG_SEGMENTS) - | (1 << VCPU_EXREG_CR3)); - vcpu->arch.regs_dirty = 0; + vmx_register_cache_reset(vcpu); pt_guest_exit(vmx); @@ -6657,18 +6789,45 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->nested.nested_run_pending = 0; vmx->idt_vectoring_info = 0; - vmx->exit_reason = vmx->fail ? 0xdead : vmcs_read32(VM_EXIT_REASON); - if ((u16)vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY) + if (unlikely(vmx->fail)) { + vmx->exit_reason = 0xdead; + return EXIT_FASTPATH_NONE; + } + + vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); + if (unlikely((u16)vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY)) kvm_machine_check(); - if (vmx->fail || (vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) - return; + trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); + + if (unlikely(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) + return EXIT_FASTPATH_NONE; vmx->loaded_vmcs->launched = 1; vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); + + if (is_guest_mode(vcpu)) + return EXIT_FASTPATH_NONE; + + exit_fastpath = vmx_exit_handlers_fastpath(vcpu); + if (exit_fastpath == EXIT_FASTPATH_REENTER_GUEST) { + if (!kvm_vcpu_exit_request(vcpu)) { + /* + * FIXME: this goto should be a loop in vcpu_enter_guest, + * but it would incur the cost of a retpoline for now. + * Revisit once static calls are available. + */ + if (vcpu->arch.apicv_active) + vmx_sync_pir_to_irr(vcpu); + goto reenter_guest; + } + exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; + } + + return exit_fastpath; } static void vmx_free_vcpu(struct kvm_vcpu *vcpu) @@ -7138,6 +7297,9 @@ static __init void vmx_set_cpu_caps(void) /* CPUID 0x80000001 */ if (!cpu_has_vmx_rdtscp()) kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); + + if (vmx_waitpkg_supported()) + kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); } static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) @@ -7253,10 +7415,6 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer; - if (kvm_mwait_in_guest(vcpu->kvm) || - kvm_can_post_timer_interrupt(vcpu)) - return -EOPNOTSUPP; - vmx = to_vmx(vcpu); tscl = rdtsc(); guest_tscl = kvm_read_l1_tsc(vcpu, tscl); @@ -7599,12 +7757,12 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) ~FEAT_CTL_LMCE_ENABLED; } -static int vmx_smi_allowed(struct kvm_vcpu *vcpu) +static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { /* we need a nested vmexit to enter SMM, postpone if run is pending */ if (to_vmx(vcpu)->nested.nested_run_pending) - return 0; - return 1; + return -EBUSY; + return !is_smm(vcpu); } static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) @@ -7641,9 +7799,9 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) return 0; } -static int enable_smi_window(struct kvm_vcpu *vcpu) +static void enable_smi_window(struct kvm_vcpu *vcpu) { - return 0; + /* RSM will cause a vmexit anyway. */ } static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) @@ -7656,6 +7814,16 @@ static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) return to_vmx(vcpu)->nested.vmxon; } +static void vmx_migrate_timers(struct kvm_vcpu *vcpu) +{ + if (is_guest_mode(vcpu)) { + struct hrtimer *timer = &to_vmx(vcpu)->nested.preemption_timer; + + if (hrtimer_try_to_cancel(timer) == 1) + hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED); + } +} + static void hardware_unsetup(void) { if (nested) @@ -7700,8 +7868,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_segment = vmx_set_segment, .get_cpl = vmx_get_cpl, .get_cs_db_l_bits = vmx_get_cs_db_l_bits, - .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits, - .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, .set_cr0 = vmx_set_cr0, .set_cr4 = vmx_set_cr4, .set_efer = vmx_set_efer, @@ -7715,8 +7881,10 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, - .tlb_flush = vmx_flush_tlb, + .tlb_flush_all = vmx_flush_tlb_all, + .tlb_flush_current = vmx_flush_tlb_current, .tlb_flush_gva = vmx_flush_tlb_gva, + .tlb_flush_guest = vmx_flush_tlb_guest, .run = vmx_vcpu_run, .handle_exit = vmx_handle_exit, @@ -7751,7 +7919,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_tss_addr = vmx_set_tss_addr, .set_identity_map_addr = vmx_set_identity_map_addr, - .get_tdp_level = get_ept_level, + .get_tdp_level = vmx_get_tdp_level, .get_mt_mask = vmx_get_mt_mask, .get_exit_info = vmx_get_exit_info, @@ -7760,7 +7928,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - .read_l1_tsc_offset = vmx_read_l1_tsc_offset, .write_l1_tsc_offset = vmx_write_l1_tsc_offset, .load_mmu_pgd = vmx_load_mmu_pgd, @@ -7782,6 +7949,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .post_block = vmx_post_block, .pmu_ops = &intel_pmu_ops, + .nested_ops = &vmx_nested_ops, .update_pi_irte = vmx_update_pi_irte, @@ -7797,14 +7965,9 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .pre_leave_smm = vmx_pre_leave_smm, .enable_smi_window = enable_smi_window, - .check_nested_events = NULL, - .get_nested_state = NULL, - .set_nested_state = NULL, - .get_vmcs12_pages = NULL, - .nested_enable_evmcs = NULL, - .nested_get_evmcs_version = NULL, .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, .apic_init_signal_blocked = vmx_apic_init_signal_blocked, + .migrate_timers = vmx_migrate_timers, }; static __init int hardware_setup(void) @@ -7903,11 +8066,11 @@ static __init int hardware_setup(void) if (!enable_ept) ept_lpage_level = 0; else if (cpu_has_vmx_ept_1g_page()) - ept_lpage_level = PT_PDPE_LEVEL; + ept_lpage_level = PG_LEVEL_1G; else if (cpu_has_vmx_ept_2m_page()) - ept_lpage_level = PT_DIRECTORY_LEVEL; + ept_lpage_level = PG_LEVEL_2M; else - ept_lpage_level = PT_PAGE_TABLE_LEVEL; + ept_lpage_level = PG_LEVEL_4K; kvm_configure_mmu(enable_ept, ept_lpage_level); /* @@ -7967,8 +8130,7 @@ static __init int hardware_setup(void) nested_vmx_setup_ctls_msrs(&vmcs_config.nested, vmx_capability.ept); - r = nested_vmx_hardware_setup(&vmx_x86_ops, - kvm_vmx_exit_handlers); + r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) return r; } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index aab9df55336e..672c28f17e49 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -8,6 +8,7 @@ #include <asm/intel_pt.h> #include "capabilities.h" +#include "kvm_cache_regs.h" #include "ops.h" #include "vmcs.h" @@ -136,6 +137,7 @@ struct nested_vmx { bool vmcs02_initialized; bool change_vmcs01_virtual_apic_mode; + bool reload_vmcs01_apic_access_page; /* * Enlightened VMCS has been enabled. It does not mean that L1 has to @@ -167,6 +169,8 @@ struct nested_vmx { u16 posted_intr_nv; struct hrtimer preemption_timer; + u64 preemption_timer_deadline; + bool has_preemption_timer_deadline; bool preemption_timer_expired; /* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */ @@ -208,6 +212,7 @@ struct vcpu_vmx { */ bool guest_state_loaded; + unsigned long exit_qualification; u32 exit_intr_info; u32 idt_vectoring_info; ulong rflags; @@ -317,8 +322,8 @@ struct kvm_vmx { }; bool nested_vmx_allowed(struct kvm_vcpu *vcpu); -void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu); -void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu); +void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, + struct loaded_vmcs *buddy); int allocate_vpid(void); void free_vpid(int vpid); void vmx_set_constant_host_state(struct vcpu_vmx *vmx); @@ -341,6 +346,8 @@ void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa); void update_exception_bitmap(struct kvm_vcpu *vcpu); void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); +bool vmx_nmi_blocked(struct kvm_vcpu *vcpu); +bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu); bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); @@ -441,9 +448,18 @@ BUILD_CONTROLS_SHADOW(pin, PIN_BASED_VM_EXEC_CONTROL) BUILD_CONTROLS_SHADOW(exec, CPU_BASED_VM_EXEC_CONTROL) BUILD_CONTROLS_SHADOW(secondary_exec, SECONDARY_VM_EXEC_CONTROL) -static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) +static inline void vmx_register_cache_reset(struct kvm_vcpu *vcpu) { - vmx->segment_cache.bitmask = 0; + vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) + | (1 << VCPU_EXREG_RFLAGS) + | (1 << VCPU_EXREG_PDPTR) + | (1 << VCPU_EXREG_SEGMENTS) + | (1 << VCPU_EXREG_CR0) + | (1 << VCPU_EXREG_CR3) + | (1 << VCPU_EXREG_CR4) + | (1 << VCPU_EXREG_EXIT_INFO_1) + | (1 << VCPU_EXREG_EXIT_INFO_2)); + vcpu->arch.regs_dirty = 0; } static inline u32 vmx_vmentry_ctrl(void) @@ -486,6 +502,28 @@ static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) return &(to_vmx(vcpu)->pi_desc); } +static inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!kvm_register_is_available(vcpu, VCPU_EXREG_EXIT_INFO_1)) { + kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); + vmx->exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + } + return vmx->exit_qualification; +} + +static inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!kvm_register_is_available(vcpu, VCPU_EXREG_EXIT_INFO_2)) { + kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2); + vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + } + return vmx->exit_intr_info; +} + struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags); void free_vmcs(struct vmcs *vmcs); int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs); @@ -500,24 +538,6 @@ static inline struct vmcs *alloc_vmcs(bool shadow) u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa); -static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid, - bool invalidate_gpa) -{ - if (enable_ept && (invalidate_gpa || !enable_vpid)) { - if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) - return; - ept_sync_context(construct_eptp(vcpu, - vcpu->arch.mmu->root_hpa)); - } else { - vpid_sync_context(vpid); - } -} - -static inline void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) -{ - __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa); -} - static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx) { vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c17e6eb9ad43..9e41b5135340 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -18,6 +18,7 @@ #include <linux/kvm_host.h> #include "irq.h" +#include "ioapic.h" #include "mmu.h" #include "i8254.h" #include "tss.h" @@ -97,9 +98,6 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; -#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ -#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ - #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -194,45 +192,46 @@ u64 __read_mostly supported_xss; EXPORT_SYMBOL_GPL(supported_xss); struct kvm_stats_debugfs_item debugfs_entries[] = { - { "pf_fixed", VCPU_STAT(pf_fixed) }, - { "pf_guest", VCPU_STAT(pf_guest) }, - { "tlb_flush", VCPU_STAT(tlb_flush) }, - { "invlpg", VCPU_STAT(invlpg) }, - { "exits", VCPU_STAT(exits) }, - { "io_exits", VCPU_STAT(io_exits) }, - { "mmio_exits", VCPU_STAT(mmio_exits) }, - { "signal_exits", VCPU_STAT(signal_exits) }, - { "irq_window", VCPU_STAT(irq_window_exits) }, - { "nmi_window", VCPU_STAT(nmi_window_exits) }, - { "halt_exits", VCPU_STAT(halt_exits) }, - { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, - { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, - { "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) }, - { "halt_wakeup", VCPU_STAT(halt_wakeup) }, - { "hypercalls", VCPU_STAT(hypercalls) }, - { "request_irq", VCPU_STAT(request_irq_exits) }, - { "irq_exits", VCPU_STAT(irq_exits) }, - { "host_state_reload", VCPU_STAT(host_state_reload) }, - { "fpu_reload", VCPU_STAT(fpu_reload) }, - { "insn_emulation", VCPU_STAT(insn_emulation) }, - { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) }, - { "irq_injections", VCPU_STAT(irq_injections) }, - { "nmi_injections", VCPU_STAT(nmi_injections) }, - { "req_event", VCPU_STAT(req_event) }, - { "l1d_flush", VCPU_STAT(l1d_flush) }, - { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, - { "mmu_pte_write", VM_STAT(mmu_pte_write) }, - { "mmu_pte_updated", VM_STAT(mmu_pte_updated) }, - { "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) }, - { "mmu_flooded", VM_STAT(mmu_flooded) }, - { "mmu_recycled", VM_STAT(mmu_recycled) }, - { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, - { "mmu_unsync", VM_STAT(mmu_unsync) }, - { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, - { "largepages", VM_STAT(lpages, .mode = 0444) }, - { "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) }, - { "max_mmu_page_hash_collisions", - VM_STAT(max_mmu_page_hash_collisions) }, + VCPU_STAT("pf_fixed", pf_fixed), + VCPU_STAT("pf_guest", pf_guest), + VCPU_STAT("tlb_flush", tlb_flush), + VCPU_STAT("invlpg", invlpg), + VCPU_STAT("exits", exits), + VCPU_STAT("io_exits", io_exits), + VCPU_STAT("mmio_exits", mmio_exits), + VCPU_STAT("signal_exits", signal_exits), + VCPU_STAT("irq_window", irq_window_exits), + VCPU_STAT("nmi_window", nmi_window_exits), + VCPU_STAT("halt_exits", halt_exits), + VCPU_STAT("halt_successful_poll", halt_successful_poll), + VCPU_STAT("halt_attempted_poll", halt_attempted_poll), + VCPU_STAT("halt_poll_invalid", halt_poll_invalid), + VCPU_STAT("halt_wakeup", halt_wakeup), + VCPU_STAT("hypercalls", hypercalls), + VCPU_STAT("request_irq", request_irq_exits), + VCPU_STAT("irq_exits", irq_exits), + VCPU_STAT("host_state_reload", host_state_reload), + VCPU_STAT("fpu_reload", fpu_reload), + VCPU_STAT("insn_emulation", insn_emulation), + VCPU_STAT("insn_emulation_fail", insn_emulation_fail), + VCPU_STAT("irq_injections", irq_injections), + VCPU_STAT("nmi_injections", nmi_injections), + VCPU_STAT("req_event", req_event), + VCPU_STAT("l1d_flush", l1d_flush), + VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), + VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), + VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped), + VM_STAT("mmu_pte_write", mmu_pte_write), + VM_STAT("mmu_pte_updated", mmu_pte_updated), + VM_STAT("mmu_pde_zapped", mmu_pde_zapped), + VM_STAT("mmu_flooded", mmu_flooded), + VM_STAT("mmu_recycled", mmu_recycled), + VM_STAT("mmu_cache_miss", mmu_cache_miss), + VM_STAT("mmu_unsync", mmu_unsync), + VM_STAT("remote_tlb_flush", remote_tlb_flush), + VM_STAT("largepages", lpages, .mode = 0444), + VM_STAT("nx_largepages_splitted", nx_lpage_splits, .mode = 0444), + VM_STAT("max_mmu_page_hash_collisions", max_mmu_page_hash_collisions), { NULL } }; @@ -261,7 +260,7 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt); static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu) { int i; - for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU); i++) + for (i = 0; i < ASYNC_PF_PER_VCPU; i++) vcpu->arch.apf.gfns[i] = ~0; } @@ -612,15 +611,28 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) } EXPORT_SYMBOL_GPL(kvm_inject_page_fault); -static bool kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) +bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, + struct x86_exception *fault) { - if (mmu_is_nested(vcpu) && !fault->nested_page_fault) - vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault); - else - vcpu->arch.mmu->inject_page_fault(vcpu, fault); + struct kvm_mmu *fault_mmu; + WARN_ON_ONCE(fault->vector != PF_VECTOR); + + fault_mmu = fault->nested_page_fault ? vcpu->arch.mmu : + vcpu->arch.walk_mmu; + + /* + * Invalidate the TLB entry for the faulting address, if it exists, + * else the access will fault indefinitely (and to emulate hardware). + */ + if ((fault->error_code & PFERR_PRESENT_MASK) && + !(fault->error_code & PFERR_RSVD_MASK)) + kvm_mmu_invalidate_gva(vcpu, fault_mmu, fault->address, + fault_mmu->root_hpa); + fault_mmu->inject_page_fault(vcpu, fault); return fault->nested_page_fault; } +EXPORT_SYMBOL_GPL(kvm_inject_emulated_page_fault); void kvm_inject_nmi(struct kvm_vcpu *vcpu) { @@ -1008,7 +1020,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) { if (!skip_tlb_flush) { kvm_mmu_sync_roots(vcpu); - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } return 0; } @@ -1020,7 +1032,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) return 1; - kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush); + kvm_mmu_new_pgd(vcpu, cr3, skip_tlb_flush, skip_tlb_flush); vcpu->arch.cr3 = cr3; kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); @@ -1060,7 +1072,7 @@ static void kvm_update_dr0123(struct kvm_vcpu *vcpu) } } -static void kvm_update_dr7(struct kvm_vcpu *vcpu) +void kvm_update_dr7(struct kvm_vcpu *vcpu) { unsigned long dr7; @@ -1073,6 +1085,7 @@ static void kvm_update_dr7(struct kvm_vcpu *vcpu) if (dr7 & DR7_BP_EN_MASK) vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED; } +EXPORT_SYMBOL_GPL(kvm_update_dr7); static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) { @@ -1233,13 +1246,18 @@ static const u32 emulated_msrs_all[] = { HV_X64_MSR_VP_ASSIST_PAGE, HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, HV_X64_MSR_TSC_EMULATION_STATUS, + HV_X64_MSR_SYNDBG_OPTIONS, + HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, + HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, + HV_X64_MSR_SYNDBG_PENDING_BUFFER, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, - MSR_KVM_PV_EOI_EN, + MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, MSR_IA32_TSC_ADJUST, MSR_IA32_TSCDEADLINE, MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_PERF_CAPABILITIES, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, @@ -1306,6 +1324,7 @@ static const u32 msr_based_features_all[] = { MSR_F10H_DECFG, MSR_IA32_UCODE_REV, MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_PERF_CAPABILITIES, }; static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)]; @@ -1564,6 +1583,13 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr); +bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu) +{ + return vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || + need_resched() || signal_pending(current); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_exit_request); + /* * The fast path for frequent and performance sensitive wrmsr emulation, * i.e. the sending of IPI, sending IPI early in the VM-Exit flow reduces @@ -1592,27 +1618,44 @@ static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data return 1; } -enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) +static int handle_fastpath_set_tscdeadline(struct kvm_vcpu *vcpu, u64 data) +{ + if (!kvm_can_use_hv_timer(vcpu)) + return 1; + + kvm_set_lapic_tscdeadline_msr(vcpu, data); + return 0; +} + +fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) { u32 msr = kvm_rcx_read(vcpu); u64 data; - int ret = 0; + fastpath_t ret = EXIT_FASTPATH_NONE; switch (msr) { case APIC_BASE_MSR + (APIC_ICR >> 4): data = kvm_read_edx_eax(vcpu); - ret = handle_fastpath_set_x2apic_icr_irqoff(vcpu, data); + if (!handle_fastpath_set_x2apic_icr_irqoff(vcpu, data)) { + kvm_skip_emulated_instruction(vcpu); + ret = EXIT_FASTPATH_EXIT_HANDLED; + } + break; + case MSR_IA32_TSCDEADLINE: + data = kvm_read_edx_eax(vcpu); + if (!handle_fastpath_set_tscdeadline(vcpu, data)) { + kvm_skip_emulated_instruction(vcpu); + ret = EXIT_FASTPATH_REENTER_GUEST; + } break; default: - return EXIT_FASTPATH_NONE; + break; } - if (!ret) { + if (ret != EXIT_FASTPATH_NONE) trace_kvm_msr_write(msr, data); - return EXIT_FASTPATH_SKIP_EMUL_INS; - } - return EXIT_FASTPATH_NONE; + return ret; } EXPORT_SYMBOL_GPL(handle_fastpath_set_msr_irqoff); @@ -1901,7 +1944,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) { - u64 curr_offset = kvm_x86_ops.read_l1_tsc_offset(vcpu); + u64 curr_offset = vcpu->arch.l1_tsc_offset; vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; } @@ -1943,14 +1986,13 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { - u64 tsc_offset = kvm_x86_ops.read_l1_tsc_offset(vcpu); - - return tsc_offset + kvm_scale_tsc(vcpu, host_tsc); + return vcpu->arch.l1_tsc_offset + kvm_scale_tsc(vcpu, host_tsc); } EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { + vcpu->arch.l1_tsc_offset = offset; vcpu->arch.tsc_offset = kvm_x86_ops.write_l1_tsc_offset(vcpu, offset); } @@ -2075,7 +2117,7 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc); static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { - u64 tsc_offset = kvm_x86_ops.read_l1_tsc_offset(vcpu); + u64 tsc_offset = vcpu->arch.l1_tsc_offset; kvm_vcpu_write_tsc_offset(vcpu, tsc_offset + adjustment); } @@ -2637,29 +2679,54 @@ out: return r; } +static inline bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) +{ + u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; + + return (vcpu->arch.apf.msr_en_val & mask) == mask; +} + static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; - /* Bits 3:5 are reserved, Should be zero */ - if (data & 0x38) + /* Bits 4:5 are reserved, Should be zero */ + if (data & 0x30) return 1; - vcpu->arch.apf.msr_val = data; + vcpu->arch.apf.msr_en_val = data; - if (!(data & KVM_ASYNC_PF_ENABLED)) { + if (!kvm_pv_async_pf_enabled(vcpu)) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); return 0; } if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, - sizeof(u32))) + sizeof(u64))) return 1; vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS); vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT; + kvm_async_pf_wakeup_all(vcpu); + + return 0; +} + +static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data) +{ + /* Bits 8-63 are reserved */ + if (data >> 8) + return 1; + + if (!lapic_in_kernel(vcpu)) + return 1; + + vcpu->arch.apf.msr_int_val = data; + + vcpu->arch.apf.vec = data & KVM_ASYNC_PF_VEC_MASK; + return 0; } @@ -2669,10 +2736,16 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu) vcpu->arch.time = 0; } -static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) +static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.tlb_flush; + kvm_x86_ops.tlb_flush_all(vcpu); +} + +static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - kvm_x86_ops.tlb_flush(vcpu, invalidate_gpa); + kvm_x86_ops.tlb_flush_guest(vcpu); } static void record_steal_time(struct kvm_vcpu *vcpu) @@ -2698,7 +2771,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu) trace_kvm_pv_tlb_flush(vcpu->vcpu_id, st->preempted & KVM_VCPU_FLUSH_TLB); if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB) - kvm_vcpu_flush_tlb(vcpu, false); + kvm_vcpu_flush_tlb_guest(vcpu); vcpu->arch.st.preempted = 0; @@ -2875,6 +2948,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (kvm_pv_enable_async_pf(vcpu, data)) return 1; break; + case MSR_KVM_ASYNC_PF_INT: + if (kvm_pv_enable_async_pf_int(vcpu, data)) + return 1; + break; + case MSR_KVM_ASYNC_PF_ACK: + if (data & 0x1) { + vcpu->arch.apf.pageready_pending = false; + kvm_check_async_pf_completion(vcpu); + } + break; case MSR_KVM_STEAL_TIME: if (unlikely(!sched_info_on())) @@ -2932,6 +3015,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: + case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: @@ -3071,7 +3156,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) - return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); + return kvm_pmu_get_msr(vcpu, msr_info); msr_info->data = 0; break; case MSR_IA32_UCODE_REV: @@ -3149,7 +3234,13 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.time; break; case MSR_KVM_ASYNC_PF_EN: - msr_info->data = vcpu->arch.apf.msr_val; + msr_info->data = vcpu->arch.apf.msr_en_val; + break; + case MSR_KVM_ASYNC_PF_INT: + msr_info->data = vcpu->arch.apf.msr_int_val; + break; + case MSR_KVM_ASYNC_PF_ACK: + msr_info->data = 0; break; case MSR_KVM_STEAL_TIME: msr_info->data = vcpu->arch.st.msr_val; @@ -3187,6 +3278,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x20000000; break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: + case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: @@ -3233,7 +3326,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; default: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) - return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); + return kvm_pmu_get_msr(vcpu, msr_info); if (!ignore_msrs) { vcpu_debug_ratelimited(vcpu, "unhandled rdmsr: 0x%x\n", msr_info->index); @@ -3363,6 +3456,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_X86_ROBUST_SINGLESTEP: case KVM_CAP_XSAVE: case KVM_CAP_ASYNC_PF: + case KVM_CAP_ASYNC_PF_INT: case KVM_CAP_GET_TSC_KHZ: case KVM_CAP_KVMCLOCK_CTRL: case KVM_CAP_READONLY_MEM: @@ -3431,14 +3525,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_X2APIC_API_VALID_FLAGS; break; case KVM_CAP_NESTED_STATE: - r = kvm_x86_ops.get_nested_state ? - kvm_x86_ops.get_nested_state(NULL, NULL, 0) : 0; + r = kvm_x86_ops.nested_ops->get_state ? + kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0; break; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: r = kvm_x86_ops.enable_direct_tlbflush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - r = kvm_x86_ops.nested_enable_evmcs != NULL; + r = kvm_x86_ops.nested_ops->enable_evmcs != NULL; break; default: break; @@ -4226,9 +4320,9 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return kvm_hv_activate_synic(vcpu, cap->cap == KVM_CAP_HYPERV_SYNIC2); case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - if (!kvm_x86_ops.nested_enable_evmcs) + if (!kvm_x86_ops.nested_ops->enable_evmcs) return -ENOTTY; - r = kvm_x86_ops.nested_enable_evmcs(vcpu, &vmcs_version); + r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); if (!r) { user_ptr = (void __user *)(uintptr_t)cap->args[0]; if (copy_to_user(user_ptr, &vmcs_version, @@ -4543,7 +4637,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, u32 user_data_size; r = -EINVAL; - if (!kvm_x86_ops.get_nested_state) + if (!kvm_x86_ops.nested_ops->get_state) break; BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size)); @@ -4551,8 +4645,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (get_user(user_data_size, &user_kvm_nested_state->size)) break; - r = kvm_x86_ops.get_nested_state(vcpu, user_kvm_nested_state, - user_data_size); + r = kvm_x86_ops.nested_ops->get_state(vcpu, user_kvm_nested_state, + user_data_size); if (r < 0) break; @@ -4573,7 +4667,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, int idx; r = -EINVAL; - if (!kvm_x86_ops.set_nested_state) + if (!kvm_x86_ops.nested_ops->set_state) break; r = -EFAULT; @@ -4586,7 +4680,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (kvm_state.flags & ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE - | KVM_STATE_NESTED_EVMCS)) + | KVM_STATE_NESTED_EVMCS | KVM_STATE_NESTED_MTF_PENDING + | KVM_STATE_NESTED_GIF_SET)) break; /* nested_run_pending implies guest_mode. */ @@ -4595,7 +4690,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvm_x86_ops.set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); + r = kvm_x86_ops.nested_ops->set_state(vcpu, user_kvm_nested_state, &kvm_state); srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } @@ -5242,6 +5337,10 @@ static void kvm_init_msr_list(void) if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) continue; break; + case MSR_IA32_UMWAIT_CONTROL: + if (!kvm_cpu_cap_has(X86_FEATURE_WAITPKG)) + continue; + break; case MSR_IA32_RTIT_CTL: case MSR_IA32_RTIT_STATUS: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) @@ -5259,7 +5358,7 @@ static void kvm_init_msr_list(void) !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) continue; break; - case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: { + case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >= intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) @@ -5274,7 +5373,7 @@ static void kvm_init_msr_list(void) if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) continue; - } + break; default: break; } @@ -6403,7 +6502,7 @@ static bool inject_emulated_exception(struct kvm_vcpu *vcpu) { struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; if (ctxt->exception.vector == PF_VECTOR) - return kvm_propagate_fault(vcpu, &ctxt->exception); + return kvm_inject_emulated_page_fault(vcpu, &ctxt->exception); if (ctxt->exception.error_code_valid) kvm_queue_exception_e(vcpu, ctxt->exception.vector, @@ -7669,14 +7768,17 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) kvm_x86_ops.update_cr8_intercept(vcpu, tpr, max_irr); } -static int inject_pending_event(struct kvm_vcpu *vcpu) +static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) { int r; + bool can_inject = true; /* try to reinject previous events if any */ - if (vcpu->arch.exception.injected) + if (vcpu->arch.exception.injected) { kvm_x86_ops.queue_exception(vcpu); + can_inject = false; + } /* * Do not inject an NMI or interrupt if there is a pending * exception. Exceptions and interrupts are recognized at @@ -7692,22 +7794,28 @@ static int inject_pending_event(struct kvm_vcpu *vcpu) * fully complete the previous instruction. */ else if (!vcpu->arch.exception.pending) { - if (vcpu->arch.nmi_injected) + if (vcpu->arch.nmi_injected) { kvm_x86_ops.set_nmi(vcpu); - else if (vcpu->arch.interrupt.injected) + can_inject = false; + } else if (vcpu->arch.interrupt.injected) { kvm_x86_ops.set_irq(vcpu); + can_inject = false; + } } + WARN_ON_ONCE(vcpu->arch.exception.injected && + vcpu->arch.exception.pending); + /* * Call check_nested_events() even if we reinjected a previous event * in order for caller to determine if it should require immediate-exit * from L2 to L1 due to pending L1 events which require exit * from L2 to L1. */ - if (is_guest_mode(vcpu) && kvm_x86_ops.check_nested_events) { - r = kvm_x86_ops.check_nested_events(vcpu); - if (r != 0) - return r; + if (is_guest_mode(vcpu)) { + r = kvm_x86_ops.nested_ops->check_events(vcpu); + if (r < 0) + goto busy; } /* try to inject new event if pending */ @@ -7716,7 +7824,6 @@ static int inject_pending_event(struct kvm_vcpu *vcpu) vcpu->arch.exception.has_error_code, vcpu->arch.exception.error_code); - WARN_ON_ONCE(vcpu->arch.exception.injected); vcpu->arch.exception.pending = false; vcpu->arch.exception.injected = true; @@ -7725,16 +7832,6 @@ static int inject_pending_event(struct kvm_vcpu *vcpu) X86_EFLAGS_RF); if (vcpu->arch.exception.nr == DB_VECTOR) { - /* - * This code assumes that nSVM doesn't use - * check_nested_events(). If it does, the - * DR6/DR7 changes should happen before L1 - * gets a #VMEXIT for an intercepted #DB in - * L2. (Under VMX, on the other hand, the - * DR6/DR7 changes should not happen in the - * event of a VM-exit to L1 for an intercepted - * #DB in L2.) - */ kvm_deliver_exception_payload(vcpu); if (vcpu->arch.dr7 & DR7_GD) { vcpu->arch.dr7 &= ~DR7_GD; @@ -7743,42 +7840,72 @@ static int inject_pending_event(struct kvm_vcpu *vcpu) } kvm_x86_ops.queue_exception(vcpu); + can_inject = false; } - /* Don't consider new event if we re-injected an event */ - if (kvm_event_needs_reinjection(vcpu)) - return 0; + /* + * Finally, inject interrupt events. If an event cannot be injected + * due to architectural conditions (e.g. IF=0) a window-open exit + * will re-request KVM_REQ_EVENT. Sometimes however an event is pending + * and can architecturally be injected, but we cannot do it right now: + * an interrupt could have arrived just now and we have to inject it + * as a vmexit, or there could already an event in the queue, which is + * indicated by can_inject. In that case we request an immediate exit + * in order to make progress and get back here for another iteration. + * The kvm_x86_ops hooks communicate this by returning -EBUSY. + */ + if (vcpu->arch.smi_pending) { + r = can_inject ? kvm_x86_ops.smi_allowed(vcpu, true) : -EBUSY; + if (r < 0) + goto busy; + if (r) { + vcpu->arch.smi_pending = false; + ++vcpu->arch.smi_count; + enter_smm(vcpu); + can_inject = false; + } else + kvm_x86_ops.enable_smi_window(vcpu); + } - if (vcpu->arch.smi_pending && !is_smm(vcpu) && - kvm_x86_ops.smi_allowed(vcpu)) { - vcpu->arch.smi_pending = false; - ++vcpu->arch.smi_count; - enter_smm(vcpu); - } else if (vcpu->arch.nmi_pending && kvm_x86_ops.nmi_allowed(vcpu)) { - --vcpu->arch.nmi_pending; - vcpu->arch.nmi_injected = true; - kvm_x86_ops.set_nmi(vcpu); - } else if (kvm_cpu_has_injectable_intr(vcpu)) { - /* - * Because interrupts can be injected asynchronously, we are - * calling check_nested_events again here to avoid a race condition. - * See https://lkml.org/lkml/2014/7/2/60 for discussion about this - * proposal and current concerns. Perhaps we should be setting - * KVM_REQ_EVENT only on certain events and not unconditionally? - */ - if (is_guest_mode(vcpu) && kvm_x86_ops.check_nested_events) { - r = kvm_x86_ops.check_nested_events(vcpu); - if (r != 0) - return r; + if (vcpu->arch.nmi_pending) { + r = can_inject ? kvm_x86_ops.nmi_allowed(vcpu, true) : -EBUSY; + if (r < 0) + goto busy; + if (r) { + --vcpu->arch.nmi_pending; + vcpu->arch.nmi_injected = true; + kvm_x86_ops.set_nmi(vcpu); + can_inject = false; + WARN_ON(kvm_x86_ops.nmi_allowed(vcpu, true) < 0); } - if (kvm_x86_ops.interrupt_allowed(vcpu)) { - kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), - false); + if (vcpu->arch.nmi_pending) + kvm_x86_ops.enable_nmi_window(vcpu); + } + + if (kvm_cpu_has_injectable_intr(vcpu)) { + r = can_inject ? kvm_x86_ops.interrupt_allowed(vcpu, true) : -EBUSY; + if (r < 0) + goto busy; + if (r) { + kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); kvm_x86_ops.set_irq(vcpu); + WARN_ON(kvm_x86_ops.interrupt_allowed(vcpu, true) < 0); } + if (kvm_cpu_has_injectable_intr(vcpu)) + kvm_x86_ops.enable_irq_window(vcpu); } - return 0; + if (is_guest_mode(vcpu) && + kvm_x86_ops.nested_ops->hv_timer_pending && + kvm_x86_ops.nested_ops->hv_timer_pending(vcpu)) + *req_immediate_exit = true; + + WARN_ON(vcpu->arch.exception.pending); + return; + +busy: + *req_immediate_exit = true; + return; } static void process_nmi(struct kvm_vcpu *vcpu) @@ -8169,24 +8296,13 @@ int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { - struct page *page = NULL; - if (!lapic_in_kernel(vcpu)) return; if (!kvm_x86_ops.set_apic_access_page_addr) return; - page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (is_error_page(page)) - return; - kvm_x86_ops.set_apic_access_page_addr(vcpu, page_to_phys(page)); - - /* - * Do not pin apic access page in memory, the MMU notifier - * will call us again if it is migrated or swapped out. - */ - put_page(page); + kvm_x86_ops.set_apic_access_page_addr(vcpu); } void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) @@ -8206,13 +8322,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_int_win = dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); - enum exit_fastpath_completion exit_fastpath = EXIT_FASTPATH_NONE; + fastpath_t exit_fastpath; bool req_immediate_exit = false; if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) { - if (unlikely(!kvm_x86_ops.get_vmcs12_pages(vcpu))) { + if (unlikely(!kvm_x86_ops.nested_ops->get_vmcs12_pages(vcpu))) { r = 0; goto out; } @@ -8234,8 +8350,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_mmu_sync_roots(vcpu); if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu)) kvm_mmu_load_pgd(vcpu); - if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) - kvm_vcpu_flush_tlb(vcpu, true); + if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) { + kvm_vcpu_flush_tlb_all(vcpu); + + /* Flushing all ASIDs flushes the current ASID... */ + kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + } + if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) + kvm_vcpu_flush_tlb_current(vcpu); + if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu)) + kvm_vcpu_flush_tlb_guest(vcpu); + if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; @@ -8308,6 +8433,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_hv_process_stimers(vcpu); if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) kvm_vcpu_update_apicv(vcpu); + if (kvm_check_request(KVM_REQ_APF_READY, vcpu)) + kvm_check_async_pf_completion(vcpu); } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { @@ -8318,32 +8445,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } - if (inject_pending_event(vcpu) != 0) - req_immediate_exit = true; - else { - /* Enable SMI/NMI/IRQ window open exits if needed. - * - * SMIs have three cases: - * 1) They can be nested, and then there is nothing to - * do here because RSM will cause a vmexit anyway. - * 2) There is an ISA-specific reason why SMI cannot be - * injected, and the moment when this changes can be - * intercepted. - * 3) Or the SMI can be pending because - * inject_pending_event has completed the injection - * of an IRQ or NMI from the previous vmexit, and - * then we request an immediate exit to inject the - * SMI. - */ - if (vcpu->arch.smi_pending && !is_smm(vcpu)) - if (!kvm_x86_ops.enable_smi_window(vcpu)) - req_immediate_exit = true; - if (vcpu->arch.nmi_pending) - kvm_x86_ops.enable_nmi_window(vcpu); - if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) - kvm_x86_ops.enable_irq_window(vcpu); - WARN_ON(vcpu->arch.exception.pending); - } + inject_pending_event(vcpu, &req_immediate_exit); + if (req_int_win) + kvm_x86_ops.enable_irq_window(vcpu); if (kvm_lapic_enabled(vcpu)) { update_cr8_intercept(vcpu); @@ -8391,8 +8495,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) kvm_x86_ops.sync_pir_to_irr(vcpu); - if (vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) - || need_resched() || signal_pending(current)) { + if (kvm_vcpu_exit_request(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); local_irq_enable(); @@ -8424,7 +8527,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } - kvm_x86_ops.run(vcpu); + exit_fastpath = kvm_x86_ops.run(vcpu); /* * Do this here before restoring debug registers on the host. And @@ -8455,7 +8558,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_x86_ops.handle_exit_irqoff(vcpu, &exit_fastpath); + kvm_x86_ops.handle_exit_irqoff(vcpu); /* * Consume any pending interrupts, including the possible source of @@ -8502,6 +8605,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) return r; cancel_injection: + if (req_immediate_exit) + kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_x86_ops.cancel_injection(vcpu); if (unlikely(vcpu->arch.apic_attention)) kvm_lapic_sync_from_vapic(vcpu); @@ -8544,8 +8649,8 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu) && kvm_x86_ops.check_nested_events) - kvm_x86_ops.check_nested_events(vcpu); + if (is_guest_mode(vcpu)) + kvm_x86_ops.nested_ops->check_events(vcpu); return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); @@ -8581,8 +8686,6 @@ static int vcpu_run(struct kvm_vcpu *vcpu) break; } - kvm_check_async_pf_completion(vcpu); - if (signal_pending(current)) { r = -EINTR; vcpu->run->exit_reason = KVM_EXIT_INTR; @@ -8727,8 +8830,9 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) trace_kvm_fpu(0); } -int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { + struct kvm_run *kvm_run = vcpu->run; int r; vcpu_load(vcpu); @@ -8746,18 +8850,18 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) r = -EAGAIN; if (signal_pending(current)) { r = -EINTR; - vcpu->run->exit_reason = KVM_EXIT_INTR; + kvm_run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.signal_exits; } goto out; } - if (vcpu->run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) { + if (kvm_run->kvm_valid_regs & ~KVM_SYNC_X86_VALID_FIELDS) { r = -EINVAL; goto out; } - if (vcpu->run->kvm_dirty_regs) { + if (kvm_run->kvm_dirty_regs) { r = sync_regs(vcpu); if (r != 0) goto out; @@ -8787,7 +8891,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) out: kvm_put_guest_fpu(vcpu); - if (vcpu->run->kvm_valid_regs) + if (kvm_run->kvm_valid_regs) store_regs(vcpu); post_kvm_run_save(vcpu); kvm_sigset_deactivate(vcpu); @@ -9379,9 +9483,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) } fx_init(vcpu); - vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; - vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + vcpu->arch.tdp_level = kvm_x86_ops.get_tdp_level(vcpu); vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; @@ -9502,7 +9605,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.cr2 = 0; kvm_make_request(KVM_REQ_EVENT, vcpu); - vcpu->arch.apf.msr_val = 0; + vcpu->arch.apf.msr_en_val = 0; + vcpu->arch.apf.msr_int_val = 0; vcpu->arch.st.msr_val = 0; kvmclock_reset(vcpu); @@ -10040,7 +10144,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, { /* Still write protect RO slot */ if (new->flags & KVM_MEM_READONLY) { - kvm_mmu_slot_remove_write_access(kvm, new, PT_PAGE_TABLE_LEVEL); + kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_4K); return; } @@ -10080,7 +10184,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, } else { int level = kvm_dirty_log_manual_protect_and_init_set(kvm) ? - PT_DIRECTORY_LEVEL : PT_PAGE_TABLE_LEVEL; + PG_LEVEL_2M : PG_LEVEL_4K; /* * If we're with initial-all-set, we don't need @@ -10182,11 +10286,12 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_NMI, vcpu) || (vcpu->arch.nmi_pending && - kvm_x86_ops.nmi_allowed(vcpu))) + kvm_x86_ops.nmi_allowed(vcpu, false))) return true; if (kvm_test_request(KVM_REQ_SMI, vcpu) || - (vcpu->arch.smi_pending && !is_smm(vcpu))) + (vcpu->arch.smi_pending && + kvm_x86_ops.smi_allowed(vcpu, false))) return true; if (kvm_arch_interrupt_allowed(vcpu) && @@ -10197,6 +10302,11 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (kvm_hv_has_stimer_pending(vcpu)) return true; + if (is_guest_mode(vcpu) && + kvm_x86_ops.nested_ops->hv_timer_pending && + kvm_x86_ops.nested_ops->hv_timer_pending(vcpu)) + return true; + return false; } @@ -10233,7 +10343,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) { - return kvm_x86_ops.interrupt_allowed(vcpu); + return kvm_x86_ops.interrupt_allowed(vcpu, false); } unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu) @@ -10298,12 +10408,14 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) static inline u32 kvm_async_pf_hash_fn(gfn_t gfn) { + BUILD_BUG_ON(!is_power_of_2(ASYNC_PF_PER_VCPU)); + return hash_32(gfn & 0xffffffff, order_base_2(ASYNC_PF_PER_VCPU)); } static inline u32 kvm_async_pf_next_probe(u32 key) { - return (key + 1) & (roundup_pow_of_two(ASYNC_PF_PER_VCPU) - 1); + return (key + 1) & (ASYNC_PF_PER_VCPU - 1); } static void kvm_add_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) @@ -10321,7 +10433,7 @@ static u32 kvm_async_pf_gfn_slot(struct kvm_vcpu *vcpu, gfn_t gfn) int i; u32 key = kvm_async_pf_hash_fn(gfn); - for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU) && + for (i = 0; i < ASYNC_PF_PER_VCPU && (vcpu->arch.apf.gfns[key] != gfn && vcpu->arch.apf.gfns[key] != ~0); i++) key = kvm_async_pf_next_probe(key); @@ -10339,6 +10451,10 @@ static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) u32 i, j, k; i = j = kvm_async_pf_gfn_slot(vcpu, gfn); + + if (WARN_ON_ONCE(vcpu->arch.apf.gfns[i] != gfn)) + return; + while (true) { vcpu->arch.apf.gfns[i] = ~0; do { @@ -10357,18 +10473,32 @@ static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) } } -static int apf_put_user(struct kvm_vcpu *vcpu, u32 val) +static inline int apf_put_user_notpresent(struct kvm_vcpu *vcpu) { + u32 reason = KVM_PV_REASON_PAGE_NOT_PRESENT; - return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val, - sizeof(val)); + return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &reason, + sizeof(reason)); } -static int apf_get_user(struct kvm_vcpu *vcpu, u32 *val) +static inline int apf_put_user_ready(struct kvm_vcpu *vcpu, u32 token) { + unsigned int offset = offsetof(struct kvm_vcpu_pv_apf_data, token); - return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, val, - sizeof(u32)); + return kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.apf.data, + &token, offset, sizeof(token)); +} + +static inline bool apf_pageready_slot_free(struct kvm_vcpu *vcpu) +{ + unsigned int offset = offsetof(struct kvm_vcpu_pv_apf_data, token); + u32 val; + + if (kvm_read_guest_offset_cached(vcpu->kvm, &vcpu->arch.apf.data, + &val, offset, sizeof(val))) + return false; + + return !val; } static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) @@ -10376,9 +10506,8 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu)) return false; - if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) || - (vcpu->arch.apf.send_user_only && - kvm_x86_ops.get_cpl(vcpu) == 0)) + if (!kvm_pv_async_pf_enabled(vcpu) || + (vcpu->arch.apf.send_user_only && kvm_x86_ops.get_cpl(vcpu) == 0)) return false; return true; @@ -10398,7 +10527,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) * If interrupts are off we cannot even use an artificial * halt state. */ - return kvm_x86_ops.interrupt_allowed(vcpu); + return kvm_arch_interrupt_allowed(vcpu); } void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, @@ -10410,7 +10539,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, kvm_add_async_pf_gfn(vcpu, work->arch.gfn); if (kvm_can_deliver_async_pf(vcpu) && - !apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) { + !apf_put_user_notpresent(vcpu)) { fault.vector = PF_VECTOR; fault.error_code_valid = true; fault.error_code = 0; @@ -10434,8 +10563,10 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { - struct x86_exception fault; - u32 val; + struct kvm_lapic_irq irq = { + .delivery_mode = APIC_DM_FIXED, + .vector = vcpu->arch.apf.vec + }; if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ @@ -10443,39 +10574,29 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, kvm_del_async_pf_gfn(vcpu, work->arch.gfn); trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa); - if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED && - !apf_get_user(vcpu, &val)) { - if (val == KVM_PV_REASON_PAGE_NOT_PRESENT && - vcpu->arch.exception.pending && - vcpu->arch.exception.nr == PF_VECTOR && - !apf_put_user(vcpu, 0)) { - vcpu->arch.exception.injected = false; - vcpu->arch.exception.pending = false; - vcpu->arch.exception.nr = 0; - vcpu->arch.exception.has_error_code = false; - vcpu->arch.exception.error_code = 0; - vcpu->arch.exception.has_payload = false; - vcpu->arch.exception.payload = 0; - } else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { - fault.vector = PF_VECTOR; - fault.error_code_valid = true; - fault.error_code = 0; - fault.nested_page_fault = false; - fault.address = work->arch.token; - fault.async_page_fault = true; - kvm_inject_page_fault(vcpu, &fault); - } + if (kvm_pv_async_pf_enabled(vcpu) && + !apf_put_user_ready(vcpu, work->arch.token)) { + vcpu->arch.apf.pageready_pending = true; + kvm_apic_set_irq(vcpu, &irq, NULL); } + vcpu->arch.apf.halted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } -bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) +void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu) +{ + kvm_make_request(KVM_REQ_APF_READY, vcpu); + if (!vcpu->arch.apf.pageready_pending) + kvm_vcpu_kick(vcpu); +} + +bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu) { - if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED)) + if (!kvm_pv_async_pf_enabled(vcpu)) return true; else - return kvm_can_do_async_pf(vcpu); + return apf_pageready_slot_free(vcpu); } void kvm_arch_start_assignment(struct kvm *kvm) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index b968acc0516f..6eb62e97e59f 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -125,6 +125,12 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu; } +static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.tlb_flush; + kvm_x86_ops.tlb_flush_current(vcpu); +} + static inline int is_pae(struct kvm_vcpu *vcpu) { return kvm_read_cr4_bits(vcpu, X86_CR4_PAE); @@ -268,7 +274,7 @@ bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, bool kvm_vector_hashing_enabled(void); int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); -enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); +fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); extern u64 host_xcr0; extern u64 supported_xcr0; @@ -358,5 +364,6 @@ static inline bool kvm_dr7_valid(u64 data) void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu); void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu); u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu); +bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu); #endif diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index dffe8e4d3140..c5437f2964ee 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -30,6 +30,7 @@ #include <asm/desc.h> /* store_idt(), ... */ #include <asm/cpu_entry_area.h> /* exception stack */ #include <asm/pgtable_areas.h> /* VMALLOC_START, ... */ +#include <asm/kvm_para.h> /* kvm_handle_async_pf */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -1359,6 +1360,24 @@ do_page_fault(struct pt_regs *regs, unsigned long hw_error_code, unsigned long address) { prefetchw(¤t->mm->mmap_sem); + /* + * KVM has two types of events that are, logically, interrupts, but + * are unfortunately delivered using the #PF vector. These events are + * "you just accessed valid memory, but the host doesn't have it right + * now, so I'll put you to sleep if you continue" and "that memory + * you tried to access earlier is available now." + * + * We are relying on the interrupted context being sane (valid RSP, + * relevant locks not held, etc.), which is fine as long as the + * interrupted context had IF=1. We are also relying on the KVM + * async pf type field and CR2 being read consistently instead of + * getting values from real and async page faults mixed up. + * + * Fingers crossed. + */ + if (kvm_handle_async_pf(regs, (u32)address)) + return; + trace_page_fault_entries(regs, hw_error_code, address); if (unlikely(kmmio_fault(regs, address))) |