diff options
Diffstat (limited to 'arch')
80 files changed, 4250 insertions, 1528 deletions
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index 816db0b..d995821 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -185,6 +185,7 @@ #define HSR_COND (0xfU << HSR_COND_SHIFT) #define FSC_FAULT (0x04) +#define FSC_ACCESS (0x08) #define FSC_PERM (0x0c) /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 41008cd..d71607c 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -27,6 +27,8 @@ #include <asm/fpstate.h> #include <kvm/arm_arch_timer.h> +#define __KVM_HAVE_ARCH_INTC_INITIALIZED + #if defined(CONFIG_KVM_ARM_MAX_VCPUS) #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS #else @@ -165,19 +167,10 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); /* We do not have shadow page tables, hence the empty hooks */ -static inline int kvm_age_hva(struct kvm *kvm, unsigned long start, - unsigned long end) -{ - return 0; -} - -static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) -{ - return 0; -} - static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address) { diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h index 3f83db2..d8e90c8 100644 --- a/arch/arm/include/asm/kvm_mmio.h +++ b/arch/arm/include/asm/kvm_mmio.h @@ -28,28 +28,6 @@ struct kvm_decode { bool sign_extend; }; -/* - * The in-kernel MMIO emulation code wants to use a copy of run->mmio, - * which is an anonymous type. Use our own type instead. - */ -struct kvm_exit_mmio { - phys_addr_t phys_addr; - u8 data[8]; - u32 len; - bool is_write; - void *private; -}; - -static inline void kvm_prepare_mmio(struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - run->mmio.phys_addr = mmio->phys_addr; - run->mmio.len = mmio->len; - run->mmio.is_write = mmio->is_write; - memcpy(run->mmio.data, mmio->data, mmio->len); - run->exit_reason = KVM_EXIT_MMIO; -} - int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa); diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 0db25bc..2499867 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -198,6 +198,9 @@ struct kvm_arch_memory_slot { /* Highest supported SPI, from VGIC_NR_IRQS */ #define KVM_ARM_IRQ_GIC_MAX 127 +/* One single KVM irqchip, ie. the VGIC */ +#define KVM_NR_IRQCHIPS 1 + /* PSCI interface */ #define KVM_PSCI_FN_BASE 0x95c1ba5e #define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n)) diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 2d2d608..488eaac 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -190,7 +190,6 @@ int main(void) DEFINE(VCPU_HxFAR, offsetof(struct kvm_vcpu, arch.fault.hxfar)); DEFINE(VCPU_HPFAR, offsetof(struct kvm_vcpu, arch.fault.hpfar)); DEFINE(VCPU_HYP_PC, offsetof(struct kvm_vcpu, arch.fault.hyp_pc)); -#ifdef CONFIG_KVM_ARM_VGIC DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu)); DEFINE(VGIC_V2_CPU_HCR, offsetof(struct vgic_cpu, vgic_v2.vgic_hcr)); DEFINE(VGIC_V2_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr)); @@ -200,14 +199,11 @@ int main(void) DEFINE(VGIC_V2_CPU_APR, offsetof(struct vgic_cpu, vgic_v2.vgic_apr)); DEFINE(VGIC_V2_CPU_LR, offsetof(struct vgic_cpu, vgic_v2.vgic_lr)); DEFINE(VGIC_CPU_NR_LR, offsetof(struct vgic_cpu, nr_lr)); -#ifdef CONFIG_KVM_ARM_TIMER DEFINE(VCPU_TIMER_CNTV_CTL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl)); DEFINE(VCPU_TIMER_CNTV_CVAL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval)); DEFINE(KVM_TIMER_CNTVOFF, offsetof(struct kvm, arch.timer.cntvoff)); DEFINE(KVM_TIMER_ENABLED, offsetof(struct kvm, arch.timer.enabled)); -#endif DEFINE(KVM_VGIC_VCTRL, offsetof(struct kvm, arch.vgic.vctrl_base)); -#endif DEFINE(KVM_VTTBR, offsetof(struct kvm, arch.vttbr)); #endif return 0; diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index 338ace7..f1f79d1 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -18,6 +18,7 @@ if VIRTUALIZATION config KVM bool "Kernel-based Virtual Machine (KVM) support" + depends on MMU && OF select PREEMPT_NOTIFIERS select ANON_INODES select HAVE_KVM_CPU_RELAX_INTERCEPT @@ -26,10 +27,12 @@ config KVM select KVM_ARM_HOST select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU - depends on ARM_VIRT_EXT && ARM_LPAE + select MMU_NOTIFIER + select HAVE_KVM_EVENTFD + select HAVE_KVM_IRQFD + depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER ---help--- - Support hosting virtualized guest machines. You will also - need to select one or more of the processor modules below. + Support hosting virtualized guest machines. This module provides access to the hardware capabilities through a character device node named /dev/kvm. @@ -37,10 +40,7 @@ config KVM If unsure, say N. config KVM_ARM_HOST - bool "KVM host support for ARM cpus." - depends on KVM - depends on MMU - select MMU_NOTIFIER + bool ---help--- Provides host support for ARM processors. @@ -55,20 +55,4 @@ config KVM_ARM_MAX_VCPUS large, so only choose a reasonable number that you expect to actually use. -config KVM_ARM_VGIC - bool "KVM support for Virtual GIC" - depends on KVM_ARM_HOST && OF - select HAVE_KVM_IRQCHIP - default y - ---help--- - Adds support for a hardware assisted, in-kernel GIC emulation. - -config KVM_ARM_TIMER - bool "KVM support for Architected Timers" - depends on KVM_ARM_VGIC && ARM_ARCH_TIMER - select HAVE_KVM_IRQCHIP - default y - ---help--- - Adds support for the Architected Timers in virtual machines - endif # VIRTUALIZATION diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index 443b8be..139e46c 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -7,7 +7,7 @@ ifeq ($(plus_virt),+virt) plus_virt_def := -DREQUIRES_VIRT=1 endif -ccflags-y += -Ivirt/kvm -Iarch/arm/kvm +ccflags-y += -Iarch/arm/kvm CFLAGS_arm.o := -I. $(plus_virt_def) CFLAGS_mmu.o := -I. @@ -15,12 +15,12 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) KVM := ../../../virt/kvm -kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o +kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o obj-y += kvm-arm.o init.o interrupts.o obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o -obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o -obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o -obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o -obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o +obj-y += $(KVM)/arm/vgic.o +obj-y += $(KVM)/arm/vgic-v2.o +obj-y += $(KVM)/arm/vgic-v2-emul.o +obj-y += $(KVM)/arm/arch_timer.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 5560f74..6f53645 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -61,8 +61,6 @@ static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1); static u8 kvm_next_vmid; static DEFINE_SPINLOCK(kvm_vmid_lock); -static bool vgic_present; - static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) { BUG_ON(preemptible()); @@ -173,8 +171,8 @@ 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_IRQFD: + case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_USER_MEMORY: case KVM_CAP_SYNC_MMU: @@ -183,6 +181,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_PSCI: case KVM_CAP_ARM_PSCI_0_2: case KVM_CAP_READONLY_MEM: + case KVM_CAP_MP_STATE: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -268,7 +267,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - return 0; + return kvm_timer_should_fire(vcpu); } int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) @@ -313,13 +312,29 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - return -EINVAL; + if (vcpu->arch.pause) + 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) { - return -EINVAL; + switch (mp_state->mp_state) { + case KVM_MP_STATE_RUNNABLE: + vcpu->arch.pause = false; + break; + case KVM_MP_STATE_STOPPED: + vcpu->arch.pause = true; + break; + default: + return -EINVAL; + } + + return 0; } /** @@ -452,6 +467,11 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) return 0; } +bool kvm_arch_intc_initialized(struct kvm *kvm) +{ + return vgic_initialized(kvm); +} + static void vcpu_pause(struct kvm_vcpu *vcpu) { wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); @@ -831,8 +851,6 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, 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; @@ -847,10 +865,7 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { case KVM_CREATE_IRQCHIP: { - if (vgic_present) - return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); - else - return -ENXIO; + return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); } case KVM_ARM_SET_DEVICE_ADDR: { struct kvm_arm_device_addr dev_addr; @@ -1035,10 +1050,6 @@ static int init_hyp_mode(void) if (err) goto out_free_context; -#ifdef CONFIG_KVM_ARM_VGIC - vgic_present = true; -#endif - /* * Init HYP architected timer support */ diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 384bab6..d503fbb 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -109,22 +109,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) return -EINVAL; } -#ifndef CONFIG_KVM_ARM_TIMER - -#define NUM_TIMER_REGS 0 - -static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) -{ - return 0; -} - -static bool is_timer_reg(u64 index) -{ - return false; -} - -#else - #define NUM_TIMER_REGS 3 static bool is_timer_reg(u64 index) @@ -152,8 +136,6 @@ static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) return 0; } -#endif - static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(long)reg->addr; diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 14d4883..35e4a3a 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -402,7 +402,6 @@ vcpu .req r0 @ vcpu pointer always in r0 * Assumes vcpu pointer in vcpu reg */ .macro save_vgic_state -#ifdef CONFIG_KVM_ARM_VGIC /* Get VGIC VCTRL base into r2 */ ldr r2, [vcpu, #VCPU_KVM] ldr r2, [r2, #KVM_VGIC_VCTRL] @@ -460,7 +459,6 @@ ARM_BE8(rev r6, r6 ) subs r4, r4, #1 bne 1b 2: -#endif .endm /* @@ -469,7 +467,6 @@ ARM_BE8(rev r6, r6 ) * Assumes vcpu pointer in vcpu reg */ .macro restore_vgic_state -#ifdef CONFIG_KVM_ARM_VGIC /* Get VGIC VCTRL base into r2 */ ldr r2, [vcpu, #VCPU_KVM] ldr r2, [r2, #KVM_VGIC_VCTRL] @@ -501,7 +498,6 @@ ARM_BE8(rev r6, r6 ) subs r4, r4, #1 bne 1b 2: -#endif .endm #define CNTHCTL_PL1PCTEN (1 << 0) @@ -515,7 +511,6 @@ ARM_BE8(rev r6, r6 ) * Clobbers r2-r5 */ .macro save_timer_state -#ifdef CONFIG_KVM_ARM_TIMER ldr r4, [vcpu, #VCPU_KVM] ldr r2, [r4, #KVM_TIMER_ENABLED] cmp r2, #0 @@ -537,7 +532,6 @@ ARM_BE8(rev r6, r6 ) mcrr p15, 4, r2, r2, c14 @ CNTVOFF 1: -#endif @ Allow physical timer/counter access for the host mrc p15, 4, r2, c14, c1, 0 @ CNTHCTL orr r2, r2, #(CNTHCTL_PL1PCEN | CNTHCTL_PL1PCTEN) @@ -559,7 +553,6 @@ ARM_BE8(rev r6, r6 ) bic r2, r2, #CNTHCTL_PL1PCEN mcr p15, 4, r2, c14, c1, 0 @ CNTHCTL -#ifdef CONFIG_KVM_ARM_TIMER ldr r4, [vcpu, #VCPU_KVM] ldr r2, [r4, #KVM_TIMER_ENABLED] cmp r2, #0 @@ -579,7 +572,6 @@ ARM_BE8(rev r6, r6 ) and r2, r2, #3 mcr p15, 0, r2, c14, c3, 1 @ CNTV_CTL 1: -#endif .endm .equ vmentry, 0 diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 5d3bfc0..974b1c6 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -121,12 +121,11 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) return 0; } -static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, - struct kvm_exit_mmio *mmio) +static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len) { unsigned long rt; - int len; - bool is_write, sign_extend; + int access_size; + bool sign_extend; if (kvm_vcpu_dabt_isextabt(vcpu)) { /* cache operation on I/O addr, tell guest unsupported */ @@ -140,17 +139,15 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return 1; } - len = kvm_vcpu_dabt_get_as(vcpu); - if (unlikely(len < 0)) - return len; + access_size = kvm_vcpu_dabt_get_as(vcpu); + if (unlikely(access_size < 0)) + return access_size; - is_write = kvm_vcpu_dabt_iswrite(vcpu); + *is_write = kvm_vcpu_dabt_iswrite(vcpu); sign_extend = kvm_vcpu_dabt_issext(vcpu); rt = kvm_vcpu_dabt_get_rd(vcpu); - mmio->is_write = is_write; - mmio->phys_addr = fault_ipa; - mmio->len = len; + *len = access_size; vcpu->arch.mmio_decode.sign_extend = sign_extend; vcpu->arch.mmio_decode.rt = rt; @@ -165,20 +162,20 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa) { - struct kvm_exit_mmio mmio; unsigned long data; unsigned long rt; int ret; + bool is_write; + int len; + u8 data_buf[8]; /* - * Prepare MMIO operation. First stash it in a private - * structure that we can use for in-kernel emulation. If the - * kernel can't handle it, copy it into run->mmio and let user - * space do its magic. + * 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. */ - if (kvm_vcpu_dabt_isvalid(vcpu)) { - ret = decode_hsr(vcpu, fault_ipa, &mmio); + ret = decode_hsr(vcpu, &is_write, &len); if (ret) return ret; } else { @@ -188,21 +185,34 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, rt = vcpu->arch.mmio_decode.rt; - if (mmio.is_write) { - data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), - mmio.len); + if (is_write) { + data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len); + + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data); + mmio_write_buf(data_buf, len, data); - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, mmio.len, - fault_ipa, data); - mmio_write_buf(mmio.data, mmio.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, mmio.len, + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len, fault_ipa, 0); + + ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len, + data_buf); } - if (vgic_handle_mmio(vcpu, run, &mmio)) + /* 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; + memcpy(run->mmio.data, data_buf, len); + + if (!ret) { + /* We handled the access successfully in the kernel. */ + kvm_handle_mmio_return(vcpu, run); return 1; + } - kvm_prepare_mmio(run, &mmio); + run->exit_reason = KVM_EXIT_MMIO; return 0; } diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 5656d79..15b050d 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1330,10 +1330,51 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, 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. + */ +static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) +{ + pmd_t *pmd; + pte_t *pte; + pfn_t pfn; + bool pfn_valid = false; + + trace_kvm_access_fault(fault_ipa); + + spin_lock(&vcpu->kvm->mmu_lock); + + pmd = stage2_get_pmd(vcpu->kvm, NULL, fault_ipa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + goto out; + + if (kvm_pmd_huge(*pmd)) { /* THP, HugeTLB */ + *pmd = pmd_mkyoung(*pmd); + pfn = pmd_pfn(*pmd); + pfn_valid = true; + goto out; + } + + pte = pte_offset_kernel(pmd, fault_ipa); + if (pte_none(*pte)) /* Nothing there either */ + goto out; + + *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 @@ -1364,7 +1405,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Check the stage-2 fault is trans. fault or write fault */ fault_status = kvm_vcpu_trap_get_fault_type(vcpu); - if (fault_status != FSC_FAULT && fault_status != FSC_PERM) { + 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), @@ -1400,6 +1442,12 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Userspace should not be able to register out-of-bounds IPAs */ VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE); + 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; @@ -1408,15 +1456,16 @@ out_unlock: return ret; } -static void handle_hva_to_gpa(struct kvm *kvm, - unsigned long start, - unsigned long end, - void (*handler)(struct kvm *kvm, - gpa_t gpa, void *data), - void *data) +static int handle_hva_to_gpa(struct kvm *kvm, + unsigned long start, + unsigned long end, + int (*handler)(struct kvm *kvm, + gpa_t gpa, void *data), + void *data) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; + int ret = 0; slots = kvm_memslots(kvm); @@ -1440,14 +1489,17 @@ static void handle_hva_to_gpa(struct kvm *kvm, for (; gfn < gfn_end; ++gfn) { gpa_t gpa = gfn << PAGE_SHIFT; - handler(kvm, gpa, data); + ret |= handler(kvm, gpa, data); } } + + return ret; } -static void kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) { unmap_stage2_range(kvm, gpa, PAGE_SIZE); + return 0; } int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) @@ -1473,7 +1525,7 @@ int kvm_unmap_hva_range(struct kvm *kvm, return 0; } -static void kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data) +static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data) { pte_t *pte = (pte_t *)data; @@ -1485,6 +1537,7 @@ static void kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data) * through this calling path. */ stage2_set_pte(kvm, NULL, gpa, pte, 0); + return 0; } @@ -1501,6 +1554,67 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte); } +static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + pmd_t *pmd; + pte_t *pte; + + pmd = stage2_get_pmd(kvm, NULL, gpa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + return 0; + + if (kvm_pmd_huge(*pmd)) { /* THP, HugeTLB */ + if (pmd_young(*pmd)) { + *pmd = pmd_mkold(*pmd); + return 1; + } + + return 0; + } + + pte = pte_offset_kernel(pmd, gpa); + if (pte_none(*pte)) + return 0; + + if (pte_young(*pte)) { + *pte = pte_mkold(*pte); /* Just a page... */ + return 1; + } + + return 0; +} + +static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + pmd_t *pmd; + pte_t *pte; + + pmd = stage2_get_pmd(kvm, NULL, gpa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + return 0; + + if (kvm_pmd_huge(*pmd)) /* THP, HugeTLB */ + return pmd_young(*pmd); + + pte = pte_offset_kernel(pmd, gpa); + if (!pte_none(*pte)) /* Just a page... */ + return pte_young(*pte); + + return 0; +} + +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) +{ + 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) +{ + trace_kvm_test_age_hva(hva); + return handle_hva_to_gpa(kvm, hva, hva, 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); diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h index 6817664..0ec3539 100644 --- a/arch/arm/kvm/trace.h +++ b/arch/arm/kvm/trace.h @@ -68,6 +68,21 @@ TRACE_EVENT(kvm_guest_fault, __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), @@ -210,6 +225,39 @@ TRACE_EVENT(kvm_set_spte_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_hvc, TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), TP_ARGS(vcpu_pc, r0, imm), diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 92bbae3..7052245 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -90,6 +90,7 @@ #define ESR_ELx_FSC (0x3F) #define ESR_ELx_FSC_TYPE (0x3C) #define ESR_ELx_FSC_EXTABT (0x10) +#define ESR_ELx_FSC_ACCESS (0x08) #define ESR_ELx_FSC_FAULT (0x04) #define ESR_ELx_FSC_PERM (0x0C) #define ESR_ELx_CV (UL(1) << 24) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 54bb4ba..ac6fafb 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -188,6 +188,7 @@ /* For compatibility with fault code shared with 32-bit */ #define FSC_FAULT ESR_ELx_FSC_FAULT +#define FSC_ACCESS ESR_ELx_FSC_ACCESS #define FSC_PERM ESR_ELx_FSC_PERM /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 8ac3c70f..f0f58c9 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -28,6 +28,8 @@ #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> +#define __KVM_HAVE_ARCH_INTC_INITIALIZED + #if defined(CONFIG_KVM_ARM_MAX_VCPUS) #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS #else @@ -177,19 +179,10 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); /* We do not have shadow page tables, hence the empty hooks */ -static inline int kvm_age_hva(struct kvm *kvm, unsigned long start, - unsigned long end) -{ - return 0; -} - -static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) -{ - return 0; -} - static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address) { diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h index 9f52beb..889c908 100644 --- a/arch/arm64/include/asm/kvm_mmio.h +++ b/arch/arm64/include/asm/kvm_mmio.h @@ -31,28 +31,6 @@ struct kvm_decode { bool sign_extend; }; -/* - * The in-kernel MMIO emulation code wants to use a copy of run->mmio, - * which is an anonymous type. Use our own type instead. - */ -struct kvm_exit_mmio { - phys_addr_t phys_addr; - u8 data[8]; - u32 len; - bool is_write; - void *private; -}; - -static inline void kvm_prepare_mmio(struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - run->mmio.phys_addr = mmio->phys_addr; - run->mmio.len = mmio->len; - run->mmio.is_write = mmio->is_write; - memcpy(run->mmio.data, mmio->data, mmio->len); - run->exit_reason = KVM_EXIT_MMIO; -} - int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa); diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 3ef77a4..c154c0b7 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -191,6 +191,9 @@ struct kvm_arch_memory_slot { /* Highest supported SPI, from VGIC_NR_IRQS */ #define KVM_ARM_IRQ_GIC_MAX 127 +/* One single KVM irqchip, ie. the VGIC */ +#define KVM_NR_IRQCHIPS 1 + /* PSCI interface */ #define KVM_PSCI_FN_BASE 0x95c1ba5e #define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n)) diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index f5590c8..5105e29 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -18,6 +18,7 @@ if VIRTUALIZATION config KVM bool "Kernel-based Virtual Machine (KVM) support" + depends on OF select MMU_NOTIFIER select PREEMPT_NOTIFIERS select ANON_INODES @@ -25,10 +26,10 @@ config KVM select HAVE_KVM_ARCH_TLB_FLUSH_ALL select KVM_MMIO select KVM_ARM_HOST - select KVM_ARM_VGIC - select KVM_ARM_TIMER select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU + select HAVE_KVM_EVENTFD + select HAVE_KVM_IRQFD ---help--- Support hosting virtualized guest machines. @@ -50,17 +51,4 @@ config KVM_ARM_MAX_VCPUS large, so only choose a reasonable number that you expect to actually use. -config KVM_ARM_VGIC - bool - depends on KVM_ARM_HOST && OF - select HAVE_KVM_IRQCHIP - ---help--- - Adds support for a hardware assisted, in-kernel GIC emulation. - -config KVM_ARM_TIMER - bool - depends on KVM_ARM_VGIC - ---help--- - Adds support for the Architected Timers in virtual machines. - endif # VIRTUALIZATION diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 4e6e09e..d5904f8 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -2,7 +2,7 @@ # Makefile for Kernel-based Virtual Machine module # -ccflags-y += -Ivirt/kvm -Iarch/arm64/kvm +ccflags-y += -Iarch/arm64/kvm CFLAGS_arm.o := -I. CFLAGS_mmu.o := -I. @@ -11,7 +11,7 @@ ARM=../../../arch/arm/kvm obj-$(CONFIG_KVM_ARM_HOST) += kvm.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o @@ -19,11 +19,11 @@ kvm-$(CONFIG_KVM_ARM_HOST) += emulate.o inject_fault.o regmap.o kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o kvm-$(CONFIG_KVM_ARM_HOST) += guest.o reset.o sys_regs.o sys_regs_generic_v8.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o -kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v2-switch.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3-emul.o -kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v3-switch.o -kvm-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o +kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v2-switch.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o +kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v3-switch.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o diff --git a/arch/mips/include/asm/asmmacro-32.h b/arch/mips/include/asm/asmmacro-32.h index cdac7b3..8038647 100644 --- a/arch/mips/include/asm/asmmacro-32.h +++ b/arch/mips/include/asm/asmmacro-32.h @@ -16,38 +16,38 @@ .set push SET_HARDFLOAT cfc1 \tmp, fcr31 - swc1 $f0, THREAD_FPR0_LS64(\thread) - swc1 $f1, THREAD_FPR1_LS64(\thread) - swc1 $f2, THREAD_FPR2_LS64(\thread) - swc1 $f3, THREAD_FPR3_LS64(\thread) - swc1 $f4, THREAD_FPR4_LS64(\thread) - swc1 $f5, THREAD_FPR5_LS64(\thread) - swc1 $f6, THREAD_FPR6_LS64(\thread) - swc1 $f7, THREAD_FPR7_LS64(\thread) - swc1 $f8, THREAD_FPR8_LS64(\thread) - swc1 $f9, THREAD_FPR9_LS64(\thread) - swc1 $f10, THREAD_FPR10_LS64(\thread) - swc1 $f11, THREAD_FPR11_LS64(\thread) - swc1 $f12, THREAD_FPR12_LS64(\thread) - swc1 $f13, THREAD_FPR13_LS64(\thread) - swc1 $f14, THREAD_FPR14_LS64(\thread) - swc1 $f15, THREAD_FPR15_LS64(\thread) - swc1 $f16, THREAD_FPR16_LS64(\thread) - swc1 $f17, THREAD_FPR17_LS64(\thread) - swc1 $f18, THREAD_FPR18_LS64(\thread) - swc1 $f19, THREAD_FPR19_LS64(\thread) - swc1 $f20, THREAD_FPR20_LS64(\thread) - swc1 $f21, THREAD_FPR21_LS64(\thread) - swc1 $f22, THREAD_FPR22_LS64(\thread) - swc1 $f23, THREAD_FPR23_LS64(\thread) - swc1 $f24, THREAD_FPR24_LS64(\thread) - swc1 $f25, THREAD_FPR25_LS64(\thread) - swc1 $f26, THREAD_FPR26_LS64(\thread) - swc1 $f27, THREAD_FPR27_LS64(\thread) - swc1 $f28, THREAD_FPR28_LS64(\thread) - swc1 $f29, THREAD_FPR29_LS64(\thread) - swc1 $f30, THREAD_FPR30_LS64(\thread) - swc1 $f31, THREAD_FPR31_LS64(\thread) + swc1 $f0, THREAD_FPR0(\thread) + swc1 $f1, THREAD_FPR1(\thread) + swc1 $f2, THREAD_FPR2(\thread) + swc1 $f3, THREAD_FPR3(\thread) + swc1 $f4, THREAD_FPR4(\thread) + swc1 $f5, THREAD_FPR5(\thread) + swc1 $f6, THREAD_FPR6(\thread) + swc1 $f7, THREAD_FPR7(\thread) + swc1 $f8, THREAD_FPR8(\thread) + swc1 $f9, THREAD_FPR9(\thread) + swc1 $f10, THREAD_FPR10(\thread) + swc1 $f11, THREAD_FPR11(\thread) + swc1 $f12, THREAD_FPR12(\thread) + swc1 $f13, THREAD_FPR13(\thread) + swc1 $f14, THREAD_FPR14(\thread) + swc1 $f15, THREAD_FPR15(\thread) + swc1 $f16, THREAD_FPR16(\thread) + swc1 $f17, THREAD_FPR17(\thread) + swc1 $f18, THREAD_FPR18(\thread) + swc1 $f19, THREAD_FPR19(\thread) + swc1 $f20, THREAD_FPR20(\thread) + swc1 $f21, THREAD_FPR21(\thread) + swc1 $f22, THREAD_FPR22(\thread) + swc1 $f23, THREAD_FPR23(\thread) + swc1 $f24, THREAD_FPR24(\thread) + swc1 $f25, THREAD_FPR25(\thread) + swc1 $f26, THREAD_FPR26(\thread) + swc1 $f27, THREAD_FPR27(\thread) + swc1 $f28, THREAD_FPR28(\thread) + swc1 $f29, THREAD_FPR29(\thread) + swc1 $f30, THREAD_FPR30(\thread) + swc1 $f31, THREAD_FPR31(\thread) sw \tmp, THREAD_FCR31(\thread) .set pop .endm @@ -56,38 +56,38 @@ .set push SET_HARDFLOAT lw \tmp, THREAD_FCR31(\thread) - lwc1 $f0, THREAD_FPR0_LS64(\thread) - lwc1 $f1, THREAD_FPR1_LS64(\thread) - lwc1 $f2, THREAD_FPR2_LS64(\thread) - lwc1 $f3, THREAD_FPR3_LS64(\thread) - lwc1 $f4, THREAD_FPR4_LS64(\thread) - lwc1 $f5, THREAD_FPR5_LS64(\thread) - lwc1 $f6, THREAD_FPR6_LS64(\thread) - lwc1 $f7, THREAD_FPR7_LS64(\thread) - lwc1 $f8, THREAD_FPR8_LS64(\thread) - lwc1 $f9, THREAD_FPR9_LS64(\thread) - lwc1 $f10, THREAD_FPR10_LS64(\thread) - lwc1 $f11, THREAD_FPR11_LS64(\thread) - lwc1 $f12, THREAD_FPR12_LS64(\thread) - lwc1 $f13, THREAD_FPR13_LS64(\thread) - lwc1 $f14, THREAD_FPR14_LS64(\thread) - lwc1 $f15, THREAD_FPR15_LS64(\thread) - lwc1 $f16, THREAD_FPR16_LS64(\thread) - lwc1 $f17, THREAD_FPR17_LS64(\thread) - lwc1 $f18, THREAD_FPR18_LS64(\thread) - lwc1 $f19, THREAD_FPR19_LS64(\thread) - lwc1 $f20, THREAD_FPR20_LS64(\thread) - lwc1 $f21, THREAD_FPR21_LS64(\thread) - lwc1 $f22, THREAD_FPR22_LS64(\thread) - lwc1 $f23, THREAD_FPR23_LS64(\thread) - lwc1 $f24, THREAD_FPR24_LS64(\thread) - lwc1 $f25, THREAD_FPR25_LS64(\thread) - lwc1 $f26, THREAD_FPR26_LS64(\thread) - lwc1 $f27, THREAD_FPR27_LS64(\thread) - lwc1 $f28, THREAD_FPR28_LS64(\thread) - lwc1 $f29, THREAD_FPR29_LS64(\thread) - lwc1 $f30, THREAD_FPR30_LS64(\thread) - lwc1 $f31, THREAD_FPR31_LS64(\thread) + lwc1 $f0, THREAD_FPR0(\thread) + lwc1 $f1, THREAD_FPR1(\thread) + lwc1 $f2, THREAD_FPR2(\thread) + lwc1 $f3, THREAD_FPR3(\thread) + lwc1 $f4, THREAD_FPR4(\thread) + lwc1 $f5, THREAD_FPR5(\thread) + lwc1 $f6, THREAD_FPR6(\thread) + lwc1 $f7, THREAD_FPR7(\thread) + lwc1 $f8, THREAD_FPR8(\thread) + lwc1 $f9, THREAD_FPR9(\thread) + lwc1 $f10, THREAD_FPR10(\thread) + lwc1 $f11, THREAD_FPR11(\thread) + lwc1 $f12, THREAD_FPR12(\thread) + lwc1 $f13, THREAD_FPR13(\thread) + lwc1 $f14, THREAD_FPR14(\thread) + lwc1 $f15, THREAD_FPR15(\thread) + lwc1 $f16, THREAD_FPR16(\thread) + lwc1 $f17, THREAD_FPR17(\thread) + lwc1 $f18, THREAD_FPR18(\thread) + lwc1 $f19, THREAD_FPR19(\thread) + lwc1 $f20, THREAD_FPR20(\thread) + lwc1 $f21, THREAD_FPR21(\thread) + lwc1 $f22, THREAD_FPR22(\thread) + lwc1 $f23, THREAD_FPR23(\thread) + lwc1 $f24, THREAD_FPR24(\thread) + lwc1 $f25, THREAD_FPR25(\thread) + lwc1 $f26, THREAD_FPR26(\thread) + lwc1 $f27, THREAD_FPR27(\thread) + lwc1 $f28, THREAD_FPR28(\thread) + lwc1 $f29, THREAD_FPR29(\thread) + lwc1 $f30, THREAD_FPR30(\thread) + lwc1 $f31, THREAD_FPR31(\thread) ctc1 \tmp, fcr31 .set pop .endm diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h index 0cae459..6156ac8 100644 --- a/arch/mips/include/asm/asmmacro.h +++ b/arch/mips/include/asm/asmmacro.h @@ -60,22 +60,22 @@ .set push SET_HARDFLOAT cfc1 \tmp, fcr31 - sdc1 $f0, THREAD_FPR0_LS64(\thread) - sdc1 $f2, THREAD_FPR2_LS64(\thread) - sdc1 $f4, THREAD_FPR4_LS64(\thread) - sdc1 $f6, THREAD_FPR6_LS64(\thread) - sdc1 $f8, THREAD_FPR8_LS64(\thread) - sdc1 $f10, THREAD_FPR10_LS64(\thread) - sdc1 $f12, THREAD_FPR12_LS64(\thread) - sdc1 $f14, THREAD_FPR14_LS64(\thread) - sdc1 $f16, THREAD_FPR16_LS64(\thread) - sdc1 $f18, THREAD_FPR18_LS64(\thread) - sdc1 $f20, THREAD_FPR20_LS64(\thread) - sdc1 $f22, THREAD_FPR22_LS64(\thread) - sdc1 $f24, THREAD_FPR24_LS64(\thread) - sdc1 $f26, THREAD_FPR26_LS64(\thread) - sdc1 $f28, THREAD_FPR28_LS64(\thread) - sdc1 $f30, THREAD_FPR30_LS64(\thread) + sdc1 $f0, THREAD_FPR0(\thread) + sdc1 $f2, THREAD_FPR2(\thread) + sdc1 $f4, THREAD_FPR4(\thread) + sdc1 $f6, THREAD_FPR6(\thread) + sdc1 $f8, THREAD_FPR8(\thread) + sdc1 $f10, THREAD_FPR10(\thread) + sdc1 $f12, THREAD_FPR12(\thread) + sdc1 $f14, THREAD_FPR14(\thread) + sdc1 $f16, THREAD_FPR16(\thread) + sdc1 $f18, THREAD_FPR18(\thread) + sdc1 $f20, THREAD_FPR20(\thread) + sdc1 $f22, THREAD_FPR22(\thread) + sdc1 $f24, THREAD_FPR24(\thread) + sdc1 $f26, THREAD_FPR26(\thread) + sdc1 $f28, THREAD_FPR28(\thread) + sdc1 $f30, THREAD_FPR30(\thread) sw \tmp, THREAD_FCR31(\thread) .set pop .endm @@ -84,22 +84,22 @@ .set push .set mips64r2 SET_HARDFLOAT - sdc1 $f1, THREAD_FPR1_LS64(\thread) - sdc1 $f3, THREAD_FPR3_LS64(\thread) - sdc1 $f5, THREAD_FPR5_LS64(\thread) - sdc1 $f7, THREAD_FPR7_LS64(\thread) - sdc1 $f9, THREAD_FPR9_LS64(\thread) - sdc1 $f11, THREAD_FPR11_LS64(\thread) - sdc1 $f13, THREAD_FPR13_LS64(\thread) - sdc1 $f15, THREAD_FPR15_LS64(\thread) - sdc1 $f17, THREAD_FPR17_LS64(\thread) - sdc1 $f19, THREAD_FPR19_LS64(\thread) - sdc1 $f21, THREAD_FPR21_LS64(\thread) - sdc1 $f23, THREAD_FPR23_LS64(\thread) - sdc1 $f25, THREAD_FPR25_LS64(\thread) - sdc1 $f27, THREAD_FPR27_LS64(\thread) - sdc1 $f29, THREAD_FPR29_LS64(\thread) - sdc1 $f31, THREAD_FPR31_LS64(\thread) + sdc1 $f1, THREAD_FPR1(\thread) + sdc1 $f3, THREAD_FPR3(\thread) + sdc1 $f5, THREAD_FPR5(\thread) + sdc1 $f7, THREAD_FPR7(\thread) + sdc1 $f9, THREAD_FPR9(\thread) + sdc1 $f11, THREAD_FPR11(\thread) + sdc1 $f13, THREAD_FPR13(\thread) + sdc1 $f15, THREAD_FPR15(\thread) + sdc1 $f17, THREAD_FPR17(\thread) + sdc1 $f19, THREAD_FPR19(\thread) + sdc1 $f21, THREAD_FPR21(\thread) + sdc1 $f23, THREAD_FPR23(\thread) + sdc1 $f25, THREAD_FPR25(\thread) + sdc1 $f27, THREAD_FPR27(\thread) + sdc1 $f29, THREAD_FPR29(\thread) + sdc1 $f31, THREAD_FPR31(\thread) .set pop .endm @@ -118,22 +118,22 @@ .set push SET_HARDFLOAT lw \tmp, THREAD_FCR31(\thread) - ldc1 $f0, THREAD_FPR0_LS64(\thread) - ldc1 $f2, THREAD_FPR2_LS64(\thread) - ldc1 $f4, THREAD_FPR4_LS64(\thread) - ldc1 $f6, THREAD_FPR6_LS64(\thread) - ldc1 $f8, THREAD_FPR8_LS64(\thread) - ldc1 $f10, THREAD_FPR10_LS64(\thread) - ldc1 $f12, THREAD_FPR12_LS64(\thread) - ldc1 $f14, THREAD_FPR14_LS64(\thread) - ldc1 $f16, THREAD_FPR16_LS64(\thread) - ldc1 $f18, THREAD_FPR18_LS64(\thread) - ldc1 $f20, THREAD_FPR20_LS64(\thread) - ldc1 $f22, THREAD_FPR22_LS64(\thread) - ldc1 $f24, THREAD_FPR24_LS64(\thread) - ldc1 $f26, THREAD_FPR26_LS64(\thread) - ldc1 $f28, THREAD_FPR28_LS64(\thread) - ldc1 $f30, THREAD_FPR30_LS64(\thread) + ldc1 $f0, THREAD_FPR0(\thread) + ldc1 $f2, THREAD_FPR2(\thread) + ldc1 $f4, THREAD_FPR4(\thread) + ldc1 $f6, THREAD_FPR6(\thread) + ldc1 $f8, THREAD_FPR8(\thread) + ldc1 $f10, THREAD_FPR10(\thread) + ldc1 $f12, THREAD_FPR12(\thread) + ldc1 $f14, THREAD_FPR14(\thread) + ldc1 $f16, THREAD_FPR16(\thread) + ldc1 $f18, THREAD_FPR18(\thread) + ldc1 $f20, THREAD_FPR20(\thread) + ldc1 $f22, THREAD_FPR22(\thread) + ldc1 $f24, THREAD_FPR24(\thread) + ldc1 $f26, THREAD_FPR26(\thread) + ldc1 $f28, THREAD_FPR28(\thread) + ldc1 $f30, THREAD_FPR30(\thread) ctc1 \tmp, fcr31 .endm @@ -141,22 +141,22 @@ .set push .set mips64r2 SET_HARDFLOAT - ldc1 $f1, THREAD_FPR1_LS64(\thread) - ldc1 $f3, THREAD_FPR3_LS64(\thread) - ldc1 $f5, THREAD_FPR5_LS64(\thread) - ldc1 $f7, THREAD_FPR7_LS64(\thread) - ldc1 $f9, THREAD_FPR9_LS64(\thread) - ldc1 $f11, THREAD_FPR11_LS64(\thread) - ldc1 $f13, THREAD_FPR13_LS64(\thread) - ldc1 $f15, THREAD_FPR15_LS64(\thread) - ldc1 $f17, THREAD_FPR17_LS64(\thread) - ldc1 $f19, THREAD_FPR19_LS64(\thread) - ldc1 $f21, THREAD_FPR21_LS64(\thread) - ldc1 $f23, THREAD_FPR23_LS64(\thread) - ldc1 $f25, THREAD_FPR25_LS64(\thread) - ldc1 $f27, THREAD_FPR27_LS64(\thread) - ldc1 $f29, THREAD_FPR29_LS64(\thread) - ldc1 $f31, THREAD_FPR31_LS64(\thread) + ldc1 $f1, THREAD_FPR1(\thread) + ldc1 $f3, THREAD_FPR3(\thread) + ldc1 $f5, THREAD_FPR5(\thread) + ldc1 $f7, THREAD_FPR7(\thread) + ldc1 $f9, THREAD_FPR9(\thread) + ldc1 $f11, THREAD_FPR11(\thread) + ldc1 $f13, THREAD_FPR13(\thread) + ldc1 $f15, THREAD_FPR15(\thread) + ldc1 $f17, THREAD_FPR17(\thread) + ldc1 $f19, THREAD_FPR19(\thread) + ldc1 $f21, THREAD_FPR21(\thread) + ldc1 $f23, THREAD_FPR23(\thread) + ldc1 $f25, THREAD_FPR25(\thread) + ldc1 $f27, THREAD_FPR27(\thread) + ldc1 $f29, THREAD_FPR29(\thread) + ldc1 $f31, THREAD_FPR31(\thread) .set pop .endm @@ -211,6 +211,22 @@ .endm #ifdef TOOLCHAIN_SUPPORTS_MSA + .macro _cfcmsa rd, cs + .set push + .set mips32r2 + .set msa + cfcmsa \rd, $\cs + .set pop + .endm + + .macro _ctcmsa cd, rs + .set push + .set mips32r2 + .set msa + ctcmsa $\cd, \rs + .set pop + .endm + .macro ld_d wd, off, base .set push .set mips32r2 @@ -227,35 +243,35 @@ .set pop .endm - .macro copy_u_w rd, ws, n + .macro copy_u_w ws, n .set push .set mips32r2 .set msa - copy_u.w \rd, $w\ws[\n] + copy_u.w $1, $w\ws[\n] .set pop .endm - .macro copy_u_d rd, ws, n + .macro copy_u_d ws, n .set push .set mips64r2 .set msa - copy_u.d \rd, $w\ws[\n] + copy_u.d $1, $w\ws[\n] .set pop .endm - .macro insert_w wd, n, rs + .macro insert_w wd, n .set push .set mips32r2 .set msa - insert.w $w\wd[\n], \rs + insert.w $w\wd[\n], $1 .set pop .endm - .macro insert_d wd, n, rs + .macro insert_d wd, n .set push .set mips64r2 .set msa - insert.d $w\wd[\n], \rs + insert.d $w\wd[\n], $1 .set pop .endm #else @@ -283,7 +299,7 @@ /* * Temporary until all toolchains in use include MSA support. */ - .macro cfcmsa rd, cs + .macro _cfcmsa rd, cs .set push .set noat SET_HARDFLOAT @@ -293,7 +309,7 @@ .set pop .endm - .macro ctcmsa cd, rs + .macro _ctcmsa cd, rs .set push .set noat SET_HARDFLOAT @@ -320,44 +336,36 @@ .set pop .endm - .macro copy_u_w rd, ws, n + .macro copy_u_w ws, n .set push .set noat SET_HARDFLOAT .insn .word COPY_UW_MSA_INSN | (\n << 16) | (\ws << 11) - /* move triggers an assembler bug... */ - or \rd, $1, zero .set pop .endm - .macro copy_u_d rd, ws, n + .macro copy_u_d ws, n .set push .set noat SET_HARDFLOAT .insn .word COPY_UD_MSA_INSN | (\n << 16) | (\ws << 11) - /* move triggers an assembler bug... */ - or \rd, $1, zero .set pop .endm - .macro insert_w wd, n, rs + .macro insert_w wd, n .set push .set noat SET_HARDFLOAT - /* move triggers an assembler bug... */ - or $1, \rs, zero .word INSERT_W_MSA_INSN | (\n << 16) | (\wd << 6) .set pop .endm - .macro insert_d wd, n, rs + .macro insert_d wd, n .set push .set noat SET_HARDFLOAT - /* move triggers an assembler bug... */ - or $1, \rs, zero .word INSERT_D_MSA_INSN | (\n << 16) | (\wd << 6) .set pop .endm @@ -399,7 +407,7 @@ .set push .set noat SET_HARDFLOAT - cfcmsa $1, MSA_CSR + _cfcmsa $1, MSA_CSR sw $1, THREAD_MSA_CSR(\thread) .set pop .endm @@ -409,7 +417,7 @@ .set noat SET_HARDFLOAT lw $1, THREAD_MSA_CSR(\thread) - ctcmsa MSA_CSR, $1 + _ctcmsa MSA_CSR, $1 .set pop ld_d 0, THREAD_FPR0, \thread ld_d 1, THREAD_FPR1, \thread @@ -452,9 +460,6 @@ insert_w \wd, 2 insert_w \wd, 3 #endif - .if 31-\wd - msa_init_upper (\wd+1) - .endif .endm .macro msa_init_all_upper @@ -463,6 +468,37 @@ SET_HARDFLOAT not $1, zero msa_init_upper 0 + msa_init_upper 1 + msa_init_upper 2 + msa_init_upper 3 + msa_init_upper 4 + msa_init_upper 5 + msa_init_upper 6 + msa_init_upper 7 + msa_init_upper 8 + msa_init_upper 9 + msa_init_upper 10 + msa_init_upper 11 + msa_init_upper 12 + msa_init_upper 13 + msa_init_upper 14 + msa_init_upper 15 + msa_init_upper 16 + msa_init_upper 17 + msa_init_upper 18 + msa_init_upper 19 + msa_init_upper 20 + msa_init_upper 21 + msa_init_upper 22 + msa_init_upper 23 + msa_init_upper 24 + msa_init_upper 25 + msa_init_upper 26 + msa_init_upper 27 + msa_init_upper 28 + msa_init_upper 29 + msa_init_upper 30 + msa_init_upper 31 .set pop .endm diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index dd083e9..b104ad9 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -48,6 +48,12 @@ enum fpu_mode { #define FPU_FR_MASK 0x1 }; +#define __disable_fpu() \ +do { \ + clear_c0_status(ST0_CU1); \ + disable_fpu_hazard(); \ +} while (0) + static inline int __enable_fpu(enum fpu_mode mode) { int fr; @@ -86,7 +92,12 @@ fr_common: enable_fpu_hazard(); /* check FR has the desired value */ - return (!!(read_c0_status() & ST0_FR) == !!fr) ? 0 : SIGFPE; + if (!!(read_c0_status() & ST0_FR) == !!fr) + return 0; + + /* unsupported FR value */ + __disable_fpu(); + return SIGFPE; default: BUG(); @@ -95,12 +106,6 @@ fr_common: return SIGFPE; } -#define __disable_fpu() \ -do { \ - clear_c0_status(ST0_CU1); \ - disable_fpu_hazard(); \ -} while (0) - #define clear_fpu_owner() clear_thread_flag(TIF_USEDFPU) static inline int __is_fpu_owner(void) @@ -170,6 +175,7 @@ static inline void lose_fpu(int save) } disable_msa(); clear_thread_flag(TIF_USEDMSA); + __disable_fpu(); } else if (is_fpu_owner()) { if (save) _save_fp(current); diff --git a/arch/mips/include/asm/kdebug.h b/arch/mips/include/asm/kdebug.h index 6a9af5f..cba22ab 100644 --- a/arch/mips/include/asm/kdebug.h +++ b/arch/mips/include/asm/kdebug.h @@ -10,7 +10,8 @@ enum die_val { DIE_RI, DIE_PAGE_FAULT, DIE_BREAK, - DIE_SSTEPBP + DIE_SSTEPBP, + DIE_MSAFP }; #endif /* _ASM_MIPS_KDEBUG_H */ diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index ac4fc71..4c25823 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -21,10 +21,10 @@ /* MIPS KVM register ids */ #define MIPS_CP0_32(_R, _S) \ - (KVM_REG_MIPS | KVM_REG_SIZE_U32 | 0x10000 | (8 * (_R) + (_S))) + (KVM_REG_MIPS_CP0 | KVM_REG_SIZE_U32 | (8 * (_R) + (_S))) #define MIPS_CP0_64(_R, _S) \ - (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 0x10000 | (8 * (_R) + (_S))) + (KVM_REG_MIPS_CP0 | KVM_REG_SIZE_U64 | (8 * (_R) + (_S))) #define KVM_REG_MIPS_CP0_INDEX MIPS_CP0_32(0, 0) #define KVM_REG_MIPS_CP0_ENTRYLO0 MIPS_CP0_64(2, 0) @@ -42,11 +42,14 @@ #define KVM_REG_MIPS_CP0_STATUS MIPS_CP0_32(12, 0) #define KVM_REG_MIPS_CP0_CAUSE MIPS_CP0_32(13, 0) #define KVM_REG_MIPS_CP0_EPC MIPS_CP0_64(14, 0) +#define KVM_REG_MIPS_CP0_PRID MIPS_CP0_32(15, 0) #define KVM_REG_MIPS_CP0_EBASE MIPS_CP0_64(15, 1) #define KVM_REG_MIPS_CP0_CONFIG MIPS_CP0_32(16, 0) #define KVM_REG_MIPS_CP0_CONFIG1 MIPS_CP0_32(16, 1) #define KVM_REG_MIPS_CP0_CONFIG2 MIPS_CP0_32(16, 2) #define KVM_REG_MIPS_CP0_CONFIG3 MIPS_CP0_32(16, 3) +#define KVM_REG_MIPS_CP0_CONFIG4 MIPS_CP0_32(16, 4) +#define KVM_REG_MIPS_CP0_CONFIG5 MIPS_CP0_32(16, 5) #define KVM_REG_MIPS_CP0_CONFIG7 MIPS_CP0_32(16, 7) #define KVM_REG_MIPS_CP0_XCONTEXT MIPS_CP0_64(20, 0) #define KVM_REG_MIPS_CP0_ERROREPC MIPS_CP0_64(30, 0) @@ -119,6 +122,10 @@ struct kvm_vcpu_stat { u32 syscall_exits; u32 resvd_inst_exits; u32 break_inst_exits; + u32 trap_inst_exits; + u32 msa_fpe_exits; + u32 fpe_exits; + u32 msa_disabled_exits; u32 flush_dcache_exits; u32 halt_successful_poll; u32 halt_wakeup; @@ -138,6 +145,10 @@ enum kvm_mips_exit_types { SYSCALL_EXITS, RESVD_INST_EXITS, BREAK_INST_EXITS, + TRAP_INST_EXITS, + MSA_FPE_EXITS, + FPE_EXITS, + MSA_DISABLED_EXITS, FLUSH_DCACHE_EXITS, MAX_KVM_MIPS_EXIT_TYPES }; @@ -206,6 +217,8 @@ struct mips_coproc { #define MIPS_CP0_CONFIG1_SEL 1 #define MIPS_CP0_CONFIG2_SEL 2 #define MIPS_CP0_CONFIG3_SEL 3 +#define MIPS_CP0_CONFIG4_SEL 4 +#define MIPS_CP0_CONFIG5_SEL 5 /* Config0 register bits */ #define CP0C0_M 31 @@ -262,31 +275,6 @@ struct mips_coproc { #define CP0C3_SM 1 #define CP0C3_TL 0 -/* Have config1, Cacheable, noncoherent, write-back, write allocate*/ -#define MIPS_CONFIG0 \ - ((1 << CP0C0_M) | (0x3 << CP0C0_K0)) - -/* Have config2, no coprocessor2 attached, no MDMX support attached, - no performance counters, watch registers present, - no code compression, EJTAG present, no FPU, no watch registers */ -#define MIPS_CONFIG1 \ -((1 << CP0C1_M) | \ - (0 << CP0C1_C2) | (0 << CP0C1_MD) | (0 << CP0C1_PC) | \ - (0 << CP0C1_WR) | (0 << CP0C1_CA) | (1 << CP0C1_EP) | \ - (0 << CP0C1_FP)) - -/* Have config3, no tertiary/secondary caches implemented */ -#define MIPS_CONFIG2 \ -((1 << CP0C2_M)) - -/* No config4, no DSP ASE, no large physaddr (PABITS), - no external interrupt controller, no vectored interrupts, - no 1kb pages, no SmartMIPS ASE, no trace logic */ -#define MIPS_CONFIG3 \ -((0 << CP0C3_M) | (0 << CP0C3_DSPP) | (0 << CP0C3_LPA) | \ - (0 << CP0C3_VEIC) | (0 << CP0C3_VInt) | (0 << CP0C3_SP) | \ - (0 << CP0C3_SM) | (0 << CP0C3_TL)) - /* MMU types, the first four entries have the same layout as the CP0C0_MT field. */ enum mips_mmu_types { @@ -321,7 +309,9 @@ enum mips_mmu_types { */ #define T_TRAP 13 /* Trap instruction */ #define T_VCEI 14 /* Virtual coherency exception */ +#define T_MSAFPE 14 /* MSA floating point exception */ #define T_FPE 15 /* Floating point exception */ +#define T_MSADIS 21 /* MSA disabled exception */ #define T_WATCH 23 /* Watch address reference */ #define T_VCED 31 /* Virtual coherency data */ @@ -374,6 +364,9 @@ struct kvm_mips_tlb { long tlb_lo1; }; +#define KVM_MIPS_FPU_FPU 0x1 +#define KVM_MIPS_FPU_MSA 0x2 + #define KVM_MIPS_GUEST_TLB_SIZE 64 struct kvm_vcpu_arch { void *host_ebase, *guest_ebase; @@ -395,6 +388,8 @@ struct kvm_vcpu_arch { /* FPU State */ struct mips_fpu_struct fpu; + /* Which FPU state is loaded (KVM_MIPS_FPU_*) */ + unsigned int fpu_inuse; /* COP0 State */ struct mips_coproc *cop0; @@ -441,6 +436,9 @@ struct kvm_vcpu_arch { /* WAIT executed */ int wait; + + u8 fpu_enabled; + u8 msa_enabled; }; @@ -482,11 +480,15 @@ struct kvm_vcpu_arch { #define kvm_read_c0_guest_config1(cop0) (cop0->reg[MIPS_CP0_CONFIG][1]) #define kvm_read_c0_guest_config2(cop0) (cop0->reg[MIPS_CP0_CONFIG][2]) #define kvm_read_c0_guest_config3(cop0) (cop0->reg[MIPS_CP0_CONFIG][3]) +#define kvm_read_c0_guest_config4(cop0) (cop0->reg[MIPS_CP0_CONFIG][4]) +#define kvm_read_c0_guest_config5(cop0) (cop0->reg[MIPS_CP0_CONFIG][5]) #define kvm_read_c0_guest_config7(cop0) (cop0->reg[MIPS_CP0_CONFIG][7]) #define kvm_write_c0_guest_config(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][0] = (val)) #define kvm_write_c0_guest_config1(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][1] = (val)) #define kvm_write_c0_guest_config2(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][2] = (val)) #define kvm_write_c0_guest_config3(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][3] = (val)) +#define kvm_write_c0_guest_config4(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][4] = (val)) +#define kvm_write_c0_guest_config5(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][5] = (val)) #define kvm_write_c0_guest_config7(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][7] = (val)) #define kvm_read_c0_guest_errorepc(cop0) (cop0->reg[MIPS_CP0_ERROR_PC][0]) #define kvm_write_c0_guest_errorepc(cop0, val) (cop0->reg[MIPS_CP0_ERROR_PC][0] = (val)) @@ -567,6 +569,31 @@ static inline void _kvm_atomic_change_c0_guest_reg(unsigned long *reg, kvm_set_c0_guest_ebase(cop0, ((val) & (change))); \ } +/* Helpers */ + +static inline bool kvm_mips_guest_can_have_fpu(struct kvm_vcpu_arch *vcpu) +{ + return (!__builtin_constant_p(cpu_has_fpu) || cpu_has_fpu) && + vcpu->fpu_enabled; +} + +static inline bool kvm_mips_guest_has_fpu(struct kvm_vcpu_arch *vcpu) +{ + return kvm_mips_guest_can_have_fpu(vcpu) && + kvm_read_c0_guest_config1(vcpu->cop0) & MIPS_CONF1_FP; +} + +static inline bool kvm_mips_guest_can_have_msa(struct kvm_vcpu_arch *vcpu) +{ + return (!__builtin_constant_p(cpu_has_msa) || cpu_has_msa) && + vcpu->msa_enabled; +} + +static inline bool kvm_mips_guest_has_msa(struct kvm_vcpu_arch *vcpu) +{ + return kvm_mips_guest_can_have_msa(vcpu) && + kvm_read_c0_guest_config3(vcpu->cop0) & MIPS_CONF3_MSA; +} struct kvm_mips_callbacks { int (*handle_cop_unusable)(struct kvm_vcpu *vcpu); @@ -578,6 +605,10 @@ struct kvm_mips_callbacks { int (*handle_syscall)(struct kvm_vcpu *vcpu); int (*handle_res_inst)(struct kvm_vcpu *vcpu); int (*handle_break)(struct kvm_vcpu *vcpu); + int (*handle_trap)(struct kvm_vcpu *vcpu); + int (*handle_msa_fpe)(struct kvm_vcpu *vcpu); + int (*handle_fpe)(struct kvm_vcpu *vcpu); + int (*handle_msa_disabled)(struct kvm_vcpu *vcpu); int (*vm_init)(struct kvm *kvm); int (*vcpu_init)(struct kvm_vcpu *vcpu); int (*vcpu_setup)(struct kvm_vcpu *vcpu); @@ -596,6 +627,8 @@ struct kvm_mips_callbacks { const struct kvm_one_reg *reg, s64 *v); int (*set_one_reg)(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, s64 v); + int (*vcpu_get_regs)(struct kvm_vcpu *vcpu); + int (*vcpu_set_regs)(struct kvm_vcpu *vcpu); }; extern struct kvm_mips_callbacks *kvm_mips_callbacks; int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks); @@ -606,6 +639,19 @@ int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu); /* Trampoline ASM routine to start running in "Guest" context */ extern int __kvm_mips_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu); +/* FPU/MSA context management */ +void __kvm_save_fpu(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_fpu(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_fcsr(struct kvm_vcpu_arch *vcpu); +void __kvm_save_msa(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_msa(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_msa_upper(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_msacsr(struct kvm_vcpu_arch *vcpu); +void kvm_own_fpu(struct kvm_vcpu *vcpu); +void kvm_own_msa(struct kvm_vcpu *vcpu); +void kvm_drop_fpu(struct kvm_vcpu *vcpu); +void kvm_lose_fpu(struct kvm_vcpu *vcpu); + /* TLB handling */ uint32_t kvm_get_kernel_asid(struct kvm_vcpu *vcpu); @@ -711,6 +757,26 @@ extern enum emulation_result kvm_mips_emulate_bp_exc(unsigned long cause, struct kvm_run *run, struct kvm_vcpu *vcpu); +extern enum emulation_result kvm_mips_emulate_trap_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + +extern enum emulation_result kvm_mips_emulate_msafpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + +extern enum emulation_result kvm_mips_emulate_fpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + +extern enum emulation_result kvm_mips_emulate_msadis_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + extern enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run); @@ -749,6 +815,11 @@ enum emulation_result kvm_mips_emulate_load(uint32_t inst, struct kvm_run *run, struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config1_wrmask(struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config3_wrmask(struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config4_wrmask(struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config5_wrmask(struct kvm_vcpu *vcpu); + /* Dynamic binary translation */ extern int kvm_mips_trans_cache_index(uint32_t inst, uint32_t *opc, struct kvm_vcpu *vcpu); diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index b5dcbee..9b3b48e 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -105,7 +105,7 @@ union fpureg { #ifdef CONFIG_CPU_LITTLE_ENDIAN # define FPR_IDX(width, idx) (idx) #else -# define FPR_IDX(width, idx) ((FPU_REG_WIDTH / (width)) - 1 - (idx)) +# define FPR_IDX(width, idx) ((idx) ^ ((64 / (width)) - 1)) #endif #define BUILD_FPR_ACCESS(width) \ diff --git a/arch/mips/include/uapi/asm/kvm.h b/arch/mips/include/uapi/asm/kvm.h index 2c04b6d..6985eb5 100644 --- a/arch/mips/include/uapi/asm/kvm.h +++ b/arch/mips/include/uapi/asm/kvm.h @@ -36,77 +36,85 @@ struct kvm_regs { /* * for KVM_GET_FPU and KVM_SET_FPU - * - * If Status[FR] is zero (32-bit FPU), the upper 32-bits of the FPRs - * are zero filled. */ struct kvm_fpu { - __u64 fpr[32]; - __u32 fir; - __u32 fccr; - __u32 fexr; - __u32 fenr; - __u32 fcsr; - __u32 pad; }; /* - * For MIPS, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access CP0 + * For MIPS, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access various * registers. The id field is broken down as follows: * - * bits[2..0] - Register 'sel' index. - * bits[7..3] - Register 'rd' index. - * bits[15..8] - Must be zero. - * bits[31..16] - 1 -> CP0 registers. - * bits[51..32] - Must be zero. * bits[63..52] - As per linux/kvm.h + * bits[51..32] - Must be zero. + * bits[31..16] - Register set. + * + * Register set = 0: GP registers from kvm_regs (see definitions below). + * + * Register set = 1: CP0 registers. + * bits[15..8] - Must be zero. + * bits[7..3] - Register 'rd' index. + * bits[2..0] - Register 'sel' index. + * + * Register set = 2: KVM specific registers (see definitions below). + * + * Register set = 3: FPU / MSA registers (see definitions below). * * Other sets registers may be added in the future. Each set would * have its own identifier in bits[31..16]. - * - * The registers defined in struct kvm_regs are also accessible, the - * id values for these are below. */ -#define KVM_REG_MIPS_R0 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 0) -#define KVM_REG_MIPS_R1 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 1) -#define KVM_REG_MIPS_R2 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 2) -#define KVM_REG_MIPS_R3 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 3) -#define KVM_REG_MIPS_R4 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 4) -#define KVM_REG_MIPS_R5 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 5) -#define KVM_REG_MIPS_R6 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 6) -#define KVM_REG_MIPS_R7 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 7) -#define KVM_REG_MIPS_R8 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 8) -#define KVM_REG_MIPS_R9 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 9) -#define KVM_REG_MIPS_R10 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 10) -#define KVM_REG_MIPS_R11 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 11) -#define KVM_REG_MIPS_R12 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 12) -#define KVM_REG_MIPS_R13 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 13) -#define KVM_REG_MIPS_R14 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 14) -#define KVM_REG_MIPS_R15 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 15) -#define KVM_REG_MIPS_R16 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 16) -#define KVM_REG_MIPS_R17 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 17) -#define KVM_REG_MIPS_R18 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 18) -#define KVM_REG_MIPS_R19 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 19) -#define KVM_REG_MIPS_R20 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 20) -#define KVM_REG_MIPS_R21 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 21) -#define KVM_REG_MIPS_R22 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 22) -#define KVM_REG_MIPS_R23 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 23) -#define KVM_REG_MIPS_R24 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 24) -#define KVM_REG_MIPS_R25 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 25) -#define KVM_REG_MIPS_R26 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 26) -#define KVM_REG_MIPS_R27 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 27) -#define KVM_REG_MIPS_R28 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 28) -#define KVM_REG_MIPS_R29 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 29) -#define KVM_REG_MIPS_R30 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 30) -#define KVM_REG_MIPS_R31 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 31) - -#define KVM_REG_MIPS_HI (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 32) -#define KVM_REG_MIPS_LO (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 33) -#define KVM_REG_MIPS_PC (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 34) - -/* KVM specific control registers */ +#define KVM_REG_MIPS_GP (KVM_REG_MIPS | 0x0000000000000000ULL) +#define KVM_REG_MIPS_CP0 (KVM_REG_MIPS | 0x0000000000010000ULL) +#define KVM_REG_MIPS_KVM (KVM_REG_MIPS | 0x0000000000020000ULL) +#define KVM_REG_MIPS_FPU (KVM_REG_MIPS | 0x0000000000030000ULL) + + +/* + * KVM_REG_MIPS_GP - General purpose registers from kvm_regs. + */ + +#define KVM_REG_MIPS_R0 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 0) +#define KVM_REG_MIPS_R1 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 1) +#define KVM_REG_MIPS_R2 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 2) +#define KVM_REG_MIPS_R3 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 3) +#define KVM_REG_MIPS_R4 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 4) +#define KVM_REG_MIPS_R5 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 5) +#define KVM_REG_MIPS_R6 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 6) +#define KVM_REG_MIPS_R7 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 7) +#define KVM_REG_MIPS_R8 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 8) +#define KVM_REG_MIPS_R9 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 9) +#define KVM_REG_MIPS_R10 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 10) +#define KVM_REG_MIPS_R11 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 11) +#define KVM_REG_MIPS_R12 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 12) +#define KVM_REG_MIPS_R13 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 13) +#define KVM_REG_MIPS_R14 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 14) +#define KVM_REG_MIPS_R15 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 15) +#define KVM_REG_MIPS_R16 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 16) +#define KVM_REG_MIPS_R17 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 17) +#define KVM_REG_MIPS_R18 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 18) +#define KVM_REG_MIPS_R19 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 19) +#define KVM_REG_MIPS_R20 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 20) +#define KVM_REG_MIPS_R21 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 21) +#define KVM_REG_MIPS_R22 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 22) +#define KVM_REG_MIPS_R23 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 23) +#define KVM_REG_MIPS_R24 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 24) +#define KVM_REG_MIPS_R25 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 25) +#define KVM_REG_MIPS_R26 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 26) +#define KVM_REG_MIPS_R27 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 27) +#define KVM_REG_MIPS_R28 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 28) +#define KVM_REG_MIPS_R29 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 29) +#define KVM_REG_MIPS_R30 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 30) +#define KVM_REG_MIPS_R31 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 31) + +#define KVM_REG_MIPS_HI (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 32) +#define KVM_REG_MIPS_LO (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 33) +#define KVM_REG_MIPS_PC (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 34) + + +/* + * KVM_REG_MIPS_KVM - KVM specific control registers. + */ /* * CP0_Count control @@ -118,8 +126,7 @@ struct kvm_fpu { * safely without losing time or guest timer interrupts. * Other: Reserved, do not change. */ -#define KVM_REG_MIPS_COUNT_CTL (KVM_REG_MIPS | KVM_REG_SIZE_U64 | \ - 0x20000 | 0) +#define KVM_REG_MIPS_COUNT_CTL (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 0) #define KVM_REG_MIPS_COUNT_CTL_DC 0x00000001 /* @@ -131,15 +138,46 @@ struct kvm_fpu { * emulated. * Modifications to times in the future are rejected. */ -#define KVM_REG_MIPS_COUNT_RESUME (KVM_REG_MIPS | KVM_REG_SIZE_U64 | \ - 0x20000 | 1) +#define KVM_REG_MIPS_COUNT_RESUME (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 1) /* * CP0_Count rate in Hz * Specifies the rate of the CP0_Count timer in Hz. Modifications occur without * discontinuities in CP0_Count. */ -#define KVM_REG_MIPS_COUNT_HZ (KVM_REG_MIPS | KVM_REG_SIZE_U64 | \ - 0x20000 | 2) +#define KVM_REG_MIPS_COUNT_HZ (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 2) + + +/* + * KVM_REG_MIPS_FPU - Floating Point and MIPS SIMD Architecture (MSA) registers. + * + * bits[15..8] - Register subset (see definitions below). + * bits[7..5] - Must be zero. + * bits[4..0] - Register number within register subset. + */ + +#define KVM_REG_MIPS_FPR (KVM_REG_MIPS_FPU | 0x0000000000000000ULL) +#define KVM_REG_MIPS_FCR (KVM_REG_MIPS_FPU | 0x0000000000000100ULL) +#define KVM_REG_MIPS_MSACR (KVM_REG_MIPS_FPU | 0x0000000000000200ULL) + +/* + * KVM_REG_MIPS_FPR - Floating point / Vector registers. + */ +#define KVM_REG_MIPS_FPR_32(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U32 | (n)) +#define KVM_REG_MIPS_FPR_64(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U64 | (n)) +#define KVM_REG_MIPS_VEC_128(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U128 | (n)) + +/* + * KVM_REG_MIPS_FCR - Floating point control registers. + */ +#define KVM_REG_MIPS_FCR_IR (KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 | 0) +#define KVM_REG_MIPS_FCR_CSR (KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 | 31) + +/* + * KVM_REG_MIPS_MSACR - MIPS SIMD Architecture (MSA) control registers. + */ +#define KVM_REG_MIPS_MSA_IR (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 | 0) +#define KVM_REG_MIPS_MSA_CSR (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 | 1) + /* * KVM MIPS specific structures and definitions diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index 750d67a..e59fd7c 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -167,72 +167,6 @@ void output_thread_fpu_defines(void) OFFSET(THREAD_FPR30, task_struct, thread.fpu.fpr[30]); OFFSET(THREAD_FPR31, task_struct, thread.fpu.fpr[31]); - /* the least significant 64 bits of each FP register */ - OFFSET(THREAD_FPR0_LS64, task_struct, - thread.fpu.fpr[0].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR1_LS64, task_struct, - thread.fpu.fpr[1].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR2_LS64, task_struct, - thread.fpu.fpr[2].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR3_LS64, task_struct, - thread.fpu.fpr[3].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR4_LS64, task_struct, - thread.fpu.fpr[4].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR5_LS64, task_struct, - thread.fpu.fpr[5].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR6_LS64, task_struct, - thread.fpu.fpr[6].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR7_LS64, task_struct, - thread.fpu.fpr[7].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR8_LS64, task_struct, - thread.fpu.fpr[8].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR9_LS64, task_struct, - thread.fpu.fpr[9].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR10_LS64, task_struct, - thread.fpu.fpr[10].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR11_LS64, task_struct, - thread.fpu.fpr[11].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR12_LS64, task_struct, - thread.fpu.fpr[12].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR13_LS64, task_struct, - thread.fpu.fpr[13].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR14_LS64, task_struct, - thread.fpu.fpr[14].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR15_LS64, task_struct, - thread.fpu.fpr[15].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR16_LS64, task_struct, - thread.fpu.fpr[16].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR17_LS64, task_struct, - thread.fpu.fpr[17].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR18_LS64, task_struct, - thread.fpu.fpr[18].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR19_LS64, task_struct, - thread.fpu.fpr[19].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR20_LS64, task_struct, - thread.fpu.fpr[20].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR21_LS64, task_struct, - thread.fpu.fpr[21].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR22_LS64, task_struct, - thread.fpu.fpr[22].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR23_LS64, task_struct, - thread.fpu.fpr[23].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR24_LS64, task_struct, - thread.fpu.fpr[24].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR25_LS64, task_struct, - thread.fpu.fpr[25].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR26_LS64, task_struct, - thread.fpu.fpr[26].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR27_LS64, task_struct, - thread.fpu.fpr[27].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR28_LS64, task_struct, - thread.fpu.fpr[28].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR29_LS64, task_struct, - thread.fpu.fpr[29].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR30_LS64, task_struct, - thread.fpu.fpr[30].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR31_LS64, task_struct, - thread.fpu.fpr[31].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FCR31, task_struct, thread.fpu.fcr31); OFFSET(THREAD_MSA_CSR, task_struct, thread.fpu.msacsr); BLANK(); @@ -470,6 +404,45 @@ void output_kvm_defines(void) OFFSET(VCPU_LO, kvm_vcpu_arch, lo); OFFSET(VCPU_HI, kvm_vcpu_arch, hi); OFFSET(VCPU_PC, kvm_vcpu_arch, pc); + BLANK(); + + OFFSET(VCPU_FPR0, kvm_vcpu_arch, fpu.fpr[0]); + OFFSET(VCPU_FPR1, kvm_vcpu_arch, fpu.fpr[1]); + OFFSET(VCPU_FPR2, kvm_vcpu_arch, fpu.fpr[2]); + OFFSET(VCPU_FPR3, kvm_vcpu_arch, fpu.fpr[3]); + OFFSET(VCPU_FPR4, kvm_vcpu_arch, fpu.fpr[4]); + OFFSET(VCPU_FPR5, kvm_vcpu_arch, fpu.fpr[5]); + OFFSET(VCPU_FPR6, kvm_vcpu_arch, fpu.fpr[6]); + OFFSET(VCPU_FPR7, kvm_vcpu_arch, fpu.fpr[7]); + OFFSET(VCPU_FPR8, kvm_vcpu_arch, fpu.fpr[8]); + OFFSET(VCPU_FPR9, kvm_vcpu_arch, fpu.fpr[9]); + OFFSET(VCPU_FPR10, kvm_vcpu_arch, fpu.fpr[10]); + OFFSET(VCPU_FPR11, kvm_vcpu_arch, fpu.fpr[11]); + OFFSET(VCPU_FPR12, kvm_vcpu_arch, fpu.fpr[12]); + OFFSET(VCPU_FPR13, kvm_vcpu_arch, fpu.fpr[13]); + OFFSET(VCPU_FPR14, kvm_vcpu_arch, fpu.fpr[14]); + OFFSET(VCPU_FPR15, kvm_vcpu_arch, fpu.fpr[15]); + OFFSET(VCPU_FPR16, kvm_vcpu_arch, fpu.fpr[16]); + OFFSET(VCPU_FPR17, kvm_vcpu_arch, fpu.fpr[17]); + OFFSET(VCPU_FPR18, kvm_vcpu_arch, fpu.fpr[18]); + OFFSET(VCPU_FPR19, kvm_vcpu_arch, fpu.fpr[19]); + OFFSET(VCPU_FPR20, kvm_vcpu_arch, fpu.fpr[20]); + OFFSET(VCPU_FPR21, kvm_vcpu_arch, fpu.fpr[21]); + OFFSET(VCPU_FPR22, kvm_vcpu_arch, fpu.fpr[22]); + OFFSET(VCPU_FPR23, kvm_vcpu_arch, fpu.fpr[23]); + OFFSET(VCPU_FPR24, kvm_vcpu_arch, fpu.fpr[24]); + OFFSET(VCPU_FPR25, kvm_vcpu_arch, fpu.fpr[25]); + OFFSET(VCPU_FPR26, kvm_vcpu_arch, fpu.fpr[26]); + OFFSET(VCPU_FPR27, kvm_vcpu_arch, fpu.fpr[27]); + OFFSET(VCPU_FPR28, kvm_vcpu_arch, fpu.fpr[28]); + OFFSET(VCPU_FPR29, kvm_vcpu_arch, fpu.fpr[29]); + OFFSET(VCPU_FPR30, kvm_vcpu_arch, fpu.fpr[30]); + OFFSET(VCPU_FPR31, kvm_vcpu_arch, fpu.fpr[31]); + + OFFSET(VCPU_FCR31, kvm_vcpu_arch, fpu.fcr31); + OFFSET(VCPU_MSA_CSR, kvm_vcpu_arch, fpu.msacsr); + BLANK(); + OFFSET(VCPU_COP0, kvm_vcpu_arch, cop0); OFFSET(VCPU_GUEST_KERNEL_ASID, kvm_vcpu_arch, guest_kernel_asid); OFFSET(VCPU_GUEST_USER_ASID, kvm_vcpu_arch, guest_user_asid); diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index 2ebaabe..af42e70 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -360,12 +360,15 @@ NESTED(nmi_handler, PT_SIZE, sp) .set mips1 SET_HARDFLOAT cfc1 a1, fcr31 - li a2, ~(0x3f << 12) - and a2, a1 - ctc1 a2, fcr31 .set pop - TRACE_IRQS_ON - STI + CLI + TRACE_IRQS_OFF + .endm + + .macro __build_clear_msa_fpe + _cfcmsa a1, MSA_CSR + CLI + TRACE_IRQS_OFF .endm .macro __build_clear_ade @@ -426,7 +429,7 @@ NESTED(nmi_handler, PT_SIZE, sp) BUILD_HANDLER cpu cpu sti silent /* #11 */ BUILD_HANDLER ov ov sti silent /* #12 */ BUILD_HANDLER tr tr sti silent /* #13 */ - BUILD_HANDLER msa_fpe msa_fpe sti silent /* #14 */ + BUILD_HANDLER msa_fpe msa_fpe msa_fpe silent /* #14 */ BUILD_HANDLER fpe fpe fpe silent /* #15 */ BUILD_HANDLER ftlb ftlb none silent /* #16 */ BUILD_HANDLER msa msa sti silent /* #21 */ diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 5104528..7da6e32 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -46,6 +46,26 @@ #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> +static void init_fp_ctx(struct task_struct *target) +{ + /* If FP has been used then the target already has context */ + if (tsk_used_math(target)) + return; + + /* Begin with data registers set to all 1s... */ + memset(&target->thread.fpu.fpr, ~0, sizeof(target->thread.fpu.fpr)); + + /* ...and FCSR zeroed */ + target->thread.fpu.fcr31 = 0; + + /* + * Record that the target has "used" math, such that the context + * just initialised, and any modifications made by the caller, + * aren't discarded. + */ + set_stopped_child_used_math(target); +} + /* * Called by kernel/ptrace.c when detaching.. * @@ -142,6 +162,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data) if (!access_ok(VERIFY_READ, data, 33 * 8)) return -EIO; + init_fp_ctx(child); fregs = get_fpu_regs(child); for (i = 0; i < 32; i++) { @@ -439,6 +460,8 @@ static int fpr_set(struct task_struct *target, /* XXX fcr31 */ + init_fp_ctx(target); + if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t)) return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.fpu, @@ -660,12 +683,7 @@ long arch_ptrace(struct task_struct *child, long request, case FPR_BASE ... FPR_BASE + 31: { union fpureg *fregs = get_fpu_regs(child); - if (!tsk_used_math(child)) { - /* FP not yet used */ - memset(&child->thread.fpu, ~0, - sizeof(child->thread.fpu)); - child->thread.fpu.fcr31 = 0; - } + init_fp_ctx(child); #ifdef CONFIG_32BIT if (test_thread_flag(TIF_32BIT_FPREGS)) { /* diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S index 676c503..1d88af2 100644 --- a/arch/mips/kernel/r4k_fpu.S +++ b/arch/mips/kernel/r4k_fpu.S @@ -34,7 +34,6 @@ .endm .set noreorder - .set MIPS_ISA_ARCH_LEVEL_RAW LEAF(_save_fp_context) .set push @@ -103,6 +102,7 @@ LEAF(_save_fp_context) /* Save 32-bit process floating point context */ LEAF(_save_fp_context32) .set push + .set MIPS_ISA_ARCH_LEVEL_RAW SET_HARDFLOAT cfc1 t1, fcr31 diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 33984c0..5b4d711 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -701,6 +701,13 @@ asmlinkage void do_ov(struct pt_regs *regs) int process_fpemu_return(int sig, void __user *fault_addr) { + /* + * We can't allow the emulated instruction to leave any of the cause + * bits set in FCSR. If they were then the kernel would take an FP + * exception when restoring FP context. + */ + current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + if (sig == SIGSEGV || sig == SIGBUS) { struct siginfo si = {0}; si.si_addr = fault_addr; @@ -781,6 +788,11 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) if (notify_die(DIE_FP, "FP exception", regs, 0, regs_to_trapnr(regs), SIGFPE) == NOTIFY_STOP) goto out; + + /* Clear FCSR.Cause before enabling interrupts */ + write_32bit_cp1_register(CP1_STATUS, fcr31 & ~FPU_CSR_ALL_X); + local_irq_enable(); + die_if_kernel("FP exception in kernel code", regs); if (fcr31 & FPU_CSR_UNI_X) { @@ -804,18 +816,12 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1, &fault_addr); - /* - * We can't allow the emulated instruction to leave any of - * the cause bit set in $fcr31. - */ - current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + /* If something went wrong, signal */ + process_fpemu_return(sig, fault_addr); /* Restore the hardware register state */ own_fpu(1); /* Using the FPU again. */ - /* If something went wrong, signal */ - process_fpemu_return(sig, fault_addr); - goto out; } else if (fcr31 & FPU_CSR_INV_X) info.si_code = FPE_FLTINV; @@ -1392,13 +1398,22 @@ out: exception_exit(prev_state); } -asmlinkage void do_msa_fpe(struct pt_regs *regs) +asmlinkage void do_msa_fpe(struct pt_regs *regs, unsigned int msacsr) { enum ctx_state prev_state; prev_state = exception_enter(); + if (notify_die(DIE_MSAFP, "MSA FP exception", regs, 0, + regs_to_trapnr(regs), SIGFPE) == NOTIFY_STOP) + goto out; + + /* Clear MSACSR.Cause before enabling interrupts */ + write_msa_csr(msacsr & ~MSA_CSR_CAUSEF); + local_irq_enable(); + die_if_kernel("do_msa_fpe invoked from kernel context!", regs); force_sig(SIGFPE, current); +out: exception_exit(prev_state); } diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile index 401fe02..637ebbe 100644 --- a/arch/mips/kvm/Makefile +++ b/arch/mips/kvm/Makefile @@ -1,13 +1,15 @@ # Makefile for KVM support for MIPS # -common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) +common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) EXTRA_CFLAGS += -Ivirt/kvm -Iarch/mips/kvm -kvm-objs := $(common-objs) mips.o emulate.o locore.o \ +common-objs-$(CONFIG_CPU_HAS_MSA) += msa.o + +kvm-objs := $(common-objs-y) mips.o emulate.o locore.o \ interrupt.o stats.o commpage.o \ - dyntrans.o trap_emul.o + dyntrans.o trap_emul.o fpu.o obj-$(CONFIG_KVM) += kvm.o obj-y += callback.o tlb.o diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index fb3e8df..6230f37 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -884,6 +884,84 @@ enum emulation_result kvm_mips_emul_tlbp(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +/** + * kvm_mips_config1_wrmask() - Find mask of writable bits in guest Config1 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config1 CP0 + * register, by userland (currently read-only to the guest). + */ +unsigned int kvm_mips_config1_wrmask(struct kvm_vcpu *vcpu) +{ + unsigned int mask = 0; + + /* Permit FPU to be present if FPU is supported */ + if (kvm_mips_guest_can_have_fpu(&vcpu->arch)) + mask |= MIPS_CONF1_FP; + + return mask; +} + +/** + * kvm_mips_config3_wrmask() - Find mask of writable bits in guest Config3 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config3 CP0 + * register, by userland (currently read-only to the guest). + */ +unsigned int kvm_mips_config3_wrmask(struct kvm_vcpu *vcpu) +{ + /* Config4 is optional */ + unsigned int mask = MIPS_CONF_M; + + /* Permit MSA to be present if MSA is supported */ + if (kvm_mips_guest_can_have_msa(&vcpu->arch)) + mask |= MIPS_CONF3_MSA; + + return mask; +} + +/** + * kvm_mips_config4_wrmask() - Find mask of writable bits in guest Config4 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config4 CP0 + * register, by userland (currently read-only to the guest). + */ +unsigned int kvm_mips_config4_wrmask(struct kvm_vcpu *vcpu) +{ + /* Config5 is optional */ + return MIPS_CONF_M; +} + +/** + * kvm_mips_config5_wrmask() - Find mask of writable bits in guest Config5 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config5 CP0 + * register, by the guest itself. + */ +unsigned int kvm_mips_config5_wrmask(struct kvm_vcpu *vcpu) +{ + unsigned int mask = 0; + + /* Permit MSAEn changes if MSA supported and enabled */ + if (kvm_mips_guest_has_msa(&vcpu->arch)) + mask |= MIPS_CONF5_MSAEN; + + /* + * Permit guest FPU mode changes if FPU is enabled and the relevant + * feature exists according to FIR register. + */ + if (kvm_mips_guest_has_fpu(&vcpu->arch)) { + if (cpu_has_fre) + mask |= MIPS_CONF5_FRE; + /* We don't support UFR or UFE */ + } + + return mask; +} + enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause, struct kvm_run *run, struct kvm_vcpu *vcpu) @@ -1021,18 +1099,114 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, kvm_mips_write_compare(vcpu, vcpu->arch.gprs[rt]); } else if ((rd == MIPS_CP0_STATUS) && (sel == 0)) { - kvm_write_c0_guest_status(cop0, - vcpu->arch.gprs[rt]); + unsigned int old_val, val, change; + + old_val = kvm_read_c0_guest_status(cop0); + val = vcpu->arch.gprs[rt]; + change = val ^ old_val; + + /* Make sure that the NMI bit is never set */ + val &= ~ST0_NMI; + + /* + * Don't allow CU1 or FR to be set unless FPU + * capability enabled and exists in guest + * configuration. + */ + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + val &= ~(ST0_CU1 | ST0_FR); + + /* + * Also don't allow FR to be set if host doesn't + * support it. + */ + if (!(current_cpu_data.fpu_id & MIPS_FPIR_F64)) + val &= ~ST0_FR; + + + /* Handle changes in FPU mode */ + preempt_disable(); + + /* + * FPU and Vector register state is made + * UNPREDICTABLE by a change of FR, so don't + * even bother saving it. + */ + if (change & ST0_FR) + kvm_drop_fpu(vcpu); + + /* + * If MSA state is already live, it is undefined + * how it interacts with FR=0 FPU state, and we + * don't want to hit reserved instruction + * exceptions trying to save the MSA state later + * when CU=1 && FR=1, so play it safe and save + * it first. + */ + if (change & ST0_CU1 && !(val & ST0_FR) && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) + kvm_lose_fpu(vcpu); + /* - * Make sure that CU1 and NMI bits are - * never set + * Propagate CU1 (FPU enable) changes + * immediately if the FPU context is already + * loaded. When disabling we leave the context + * loaded so it can be quickly enabled again in + * the near future. */ - kvm_clear_c0_guest_status(cop0, - (ST0_CU1 | ST0_NMI)); + if (change & ST0_CU1 && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) + change_c0_status(ST0_CU1, val); + + preempt_enable(); + + kvm_write_c0_guest_status(cop0, val); #ifdef CONFIG_KVM_MIPS_DYN_TRANS - kvm_mips_trans_mtc0(inst, opc, vcpu); + /* + * If FPU present, we need CU1/FR bits to take + * effect fairly soon. + */ + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + kvm_mips_trans_mtc0(inst, opc, vcpu); #endif + } else if ((rd == MIPS_CP0_CONFIG) && (sel == 5)) { + unsigned int old_val, val, change, wrmask; + + old_val = kvm_read_c0_guest_config5(cop0); + val = vcpu->arch.gprs[rt]; + + /* Only a few bits are writable in Config5 */ + wrmask = kvm_mips_config5_wrmask(vcpu); + change = (val ^ old_val) & wrmask; + val = old_val ^ change; + + + /* Handle changes in FPU/MSA modes */ + preempt_disable(); + + /* + * Propagate FRE changes immediately if the FPU + * context is already loaded. + */ + if (change & MIPS_CONF5_FRE && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) + change_c0_config5(MIPS_CONF5_FRE, val); + + /* + * Propagate MSAEn changes immediately if the + * MSA context is already loaded. When disabling + * we leave the context loaded so it can be + * quickly enabled again in the near future. + */ + if (change & MIPS_CONF5_MSAEN && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) + change_c0_config5(MIPS_CONF5_MSAEN, + val); + + preempt_enable(); + + kvm_write_c0_guest_config5(cop0, val); } else if ((rd == MIPS_CP0_CAUSE) && (sel == 0)) { uint32_t old_cause, new_cause; @@ -1970,6 +2144,146 @@ enum emulation_result kvm_mips_emulate_bp_exc(unsigned long cause, return er; } +enum emulation_result kvm_mips_emulate_trap_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering TRAP @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_TRAP << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver TRAP when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + +enum emulation_result kvm_mips_emulate_msafpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering MSAFPE @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_MSAFPE << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver MSAFPE when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + +enum emulation_result kvm_mips_emulate_fpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering FPE @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_FPE << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver FPE when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + +enum emulation_result kvm_mips_emulate_msadis_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering MSADIS @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_MSADIS << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver MSADIS when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + /* ll/sc, rdhwr, sync emulation */ #define OPCODE 0xfc000000 @@ -2176,6 +2490,10 @@ enum emulation_result kvm_mips_check_privilege(unsigned long cause, case T_SYSCALL: case T_BREAK: case T_RES_INST: + case T_TRAP: + case T_MSAFPE: + case T_FPE: + case T_MSADIS: break; case T_COP_UNUSABLE: diff --git a/arch/mips/kvm/fpu.S b/arch/mips/kvm/fpu.S new file mode 100644 index 0000000..531fbf5 --- /dev/null +++ b/arch/mips/kvm/fpu.S @@ -0,0 +1,122 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * FPU context handling code for KVM. + * + * Copyright (C) 2015 Imagination Technologies Ltd. + */ + +#include <asm/asm.h> +#include <asm/asm-offsets.h> +#include <asm/fpregdef.h> +#include <asm/mipsregs.h> +#include <asm/regdef.h> + + .set noreorder + .set noat + +LEAF(__kvm_save_fpu) + .set push + .set mips64r2 + SET_HARDFLOAT + mfc0 t0, CP0_STATUS + sll t0, t0, 5 # is Status.FR set? + bgez t0, 1f # no: skip odd doubles + nop + sdc1 $f1, VCPU_FPR1(a0) + sdc1 $f3, VCPU_FPR3(a0) + sdc1 $f5, VCPU_FPR5(a0) + sdc1 $f7, VCPU_FPR7(a0) + sdc1 $f9, VCPU_FPR9(a0) + sdc1 $f11, VCPU_FPR11(a0) + sdc1 $f13, VCPU_FPR13(a0) + sdc1 $f15, VCPU_FPR15(a0) + sdc1 $f17, VCPU_FPR17(a0) + sdc1 $f19, VCPU_FPR19(a0) + sdc1 $f21, VCPU_FPR21(a0) + sdc1 $f23, VCPU_FPR23(a0) + sdc1 $f25, VCPU_FPR25(a0) + sdc1 $f27, VCPU_FPR27(a0) + sdc1 $f29, VCPU_FPR29(a0) + sdc1 $f31, VCPU_FPR31(a0) +1: sdc1 $f0, VCPU_FPR0(a0) + sdc1 $f2, VCPU_FPR2(a0) + sdc1 $f4, VCPU_FPR4(a0) + sdc1 $f6, VCPU_FPR6(a0) + sdc1 $f8, VCPU_FPR8(a0) + sdc1 $f10, VCPU_FPR10(a0) + sdc1 $f12, VCPU_FPR12(a0) + sdc1 $f14, VCPU_FPR14(a0) + sdc1 $f16, VCPU_FPR16(a0) + sdc1 $f18, VCPU_FPR18(a0) + sdc1 $f20, VCPU_FPR20(a0) + sdc1 $f22, VCPU_FPR22(a0) + sdc1 $f24, VCPU_FPR24(a0) + sdc1 $f26, VCPU_FPR26(a0) + sdc1 $f28, VCPU_FPR28(a0) + jr ra + sdc1 $f30, VCPU_FPR30(a0) + .set pop + END(__kvm_save_fpu) + +LEAF(__kvm_restore_fpu) + .set push + .set mips64r2 + SET_HARDFLOAT + mfc0 t0, CP0_STATUS + sll t0, t0, 5 # is Status.FR set? + bgez t0, 1f # no: skip odd doubles + nop + ldc1 $f1, VCPU_FPR1(a0) + ldc1 $f3, VCPU_FPR3(a0) + ldc1 $f5, VCPU_FPR5(a0) + ldc1 $f7, VCPU_FPR7(a0) + ldc1 $f9, VCPU_FPR9(a0) + ldc1 $f11, VCPU_FPR11(a0) + ldc1 $f13, VCPU_FPR13(a0) + ldc1 $f15, VCPU_FPR15(a0) + ldc1 $f17, VCPU_FPR17(a0) + ldc1 $f19, VCPU_FPR19(a0) + ldc1 $f21, VCPU_FPR21(a0) + ldc1 $f23, VCPU_FPR23(a0) + ldc1 $f25, VCPU_FPR25(a0) + ldc1 $f27, VCPU_FPR27(a0) + ldc1 $f29, VCPU_FPR29(a0) + ldc1 $f31, VCPU_FPR31(a0) +1: ldc1 $f0, VCPU_FPR0(a0) + ldc1 $f2, VCPU_FPR2(a0) + ldc1 $f4, VCPU_FPR4(a0) + ldc1 $f6, VCPU_FPR6(a0) + ldc1 $f8, VCPU_FPR8(a0) + ldc1 $f10, VCPU_FPR10(a0) + ldc1 $f12, VCPU_FPR12(a0) + ldc1 $f14, VCPU_FPR14(a0) + ldc1 $f16, VCPU_FPR16(a0) + ldc1 $f18, VCPU_FPR18(a0) + ldc1 $f20, VCPU_FPR20(a0) + ldc1 $f22, VCPU_FPR22(a0) + ldc1 $f24, VCPU_FPR24(a0) + ldc1 $f26, VCPU_FPR26(a0) + ldc1 $f28, VCPU_FPR28(a0) + jr ra + ldc1 $f30, VCPU_FPR30(a0) + .set pop + END(__kvm_restore_fpu) + +LEAF(__kvm_restore_fcsr) + .set push + SET_HARDFLOAT + lw t0, VCPU_FCR31(a0) + /* + * The ctc1 must stay at this offset in __kvm_restore_fcsr. + * See kvm_mips_csr_die_notify() which handles t0 containing a value + * which triggers an FP Exception, which must be stepped over and + * ignored since the set cause bits must remain there for the guest. + */ + ctc1 t0, fcr31 + jr ra + nop + .set pop + END(__kvm_restore_fcsr) diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S index 4a68b17..c567240 100644 --- a/arch/mips/kvm/locore.S +++ b/arch/mips/kvm/locore.S @@ -36,6 +36,8 @@ #define PT_HOST_USERLOCAL PT_EPC #define CP0_DDATA_LO $28,3 +#define CP0_CONFIG3 $16,3 +#define CP0_CONFIG5 $16,5 #define CP0_EBASE $15,1 #define CP0_INTCTL $12,1 @@ -353,6 +355,42 @@ NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra) LONG_L k0, VCPU_HOST_EBASE(k1) mtc0 k0,CP0_EBASE + /* + * If FPU is enabled, save FCR31 and clear it so that later ctc1's don't + * trigger FPE for pending exceptions. + */ + .set at + and v1, v0, ST0_CU1 + beqz v1, 1f + nop + .set push + SET_HARDFLOAT + cfc1 t0, fcr31 + sw t0, VCPU_FCR31(k1) + ctc1 zero,fcr31 + .set pop + .set noat +1: + +#ifdef CONFIG_CPU_HAS_MSA + /* + * If MSA is enabled, save MSACSR and clear it so that later + * instructions don't trigger MSAFPE for pending exceptions. + */ + mfc0 t0, CP0_CONFIG3 + ext t0, t0, 28, 1 /* MIPS_CONF3_MSAP */ + beqz t0, 1f + nop + mfc0 t0, CP0_CONFIG5 + ext t0, t0, 27, 1 /* MIPS_CONF5_MSAEN */ + beqz t0, 1f + nop + _cfcmsa t0, MSA_CSR + sw t0, VCPU_MSA_CSR(k1) + _ctcmsa MSA_CSR, zero +1: +#endif + /* Now that the new EBASE has been loaded, unset BEV and KSU_USER */ .set at and v0, v0, ~(ST0_EXL | KSU_USER | ST0_IE) diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index c9eccf5..bb68e8d 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -11,6 +11,7 @@ #include <linux/errno.h> #include <linux/err.h> +#include <linux/kdebug.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/fs.h> @@ -48,6 +49,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "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 }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll), KVM_STAT_VCPU }, { "halt_wakeup", VCPU_STAT(halt_wakeup), KVM_STAT_VCPU }, @@ -504,10 +509,13 @@ static u64 kvm_mips_get_one_regs[] = { KVM_REG_MIPS_CP0_STATUS, KVM_REG_MIPS_CP0_CAUSE, KVM_REG_MIPS_CP0_EPC, + KVM_REG_MIPS_CP0_PRID, KVM_REG_MIPS_CP0_CONFIG, KVM_REG_MIPS_CP0_CONFIG1, KVM_REG_MIPS_CP0_CONFIG2, KVM_REG_MIPS_CP0_CONFIG3, + KVM_REG_MIPS_CP0_CONFIG4, + KVM_REG_MIPS_CP0_CONFIG5, KVM_REG_MIPS_CP0_CONFIG7, KVM_REG_MIPS_CP0_ERROREPC, @@ -520,10 +528,14 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { struct mips_coproc *cop0 = vcpu->arch.cop0; + struct mips_fpu_struct *fpu = &vcpu->arch.fpu; int ret; s64 v; + s64 vs[2]; + unsigned int idx; switch (reg->id) { + /* General purpose registers */ case KVM_REG_MIPS_R0 ... KVM_REG_MIPS_R31: v = (long)vcpu->arch.gprs[reg->id - KVM_REG_MIPS_R0]; break; @@ -537,6 +549,67 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, v = (long)vcpu->arch.pc; break; + /* Floating point registers */ + case KVM_REG_MIPS_FPR_32(0) ... KVM_REG_MIPS_FPR_32(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_32(0); + /* Odd singles in top of even double when FR=0 */ + if (kvm_read_c0_guest_status(cop0) & ST0_FR) + v = get_fpr32(&fpu->fpr[idx], 0); + else + v = get_fpr32(&fpu->fpr[idx & ~1], idx & 1); + break; + case KVM_REG_MIPS_FPR_64(0) ... KVM_REG_MIPS_FPR_64(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_64(0); + /* Can't access odd doubles in FR=0 mode */ + if (idx & 1 && !(kvm_read_c0_guest_status(cop0) & ST0_FR)) + return -EINVAL; + v = get_fpr64(&fpu->fpr[idx], 0); + break; + case KVM_REG_MIPS_FCR_IR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + v = boot_cpu_data.fpu_id; + break; + case KVM_REG_MIPS_FCR_CSR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + v = fpu->fcr31; + break; + + /* MIPS SIMD Architecture (MSA) registers */ + case KVM_REG_MIPS_VEC_128(0) ... KVM_REG_MIPS_VEC_128(31): + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + /* Can't access MSA registers in FR=0 mode */ + if (!(kvm_read_c0_guest_status(cop0) & ST0_FR)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_VEC_128(0); +#ifdef CONFIG_CPU_LITTLE_ENDIAN + /* least significant byte first */ + vs[0] = get_fpr64(&fpu->fpr[idx], 0); + vs[1] = get_fpr64(&fpu->fpr[idx], 1); +#else + /* most significant byte first */ + vs[0] = get_fpr64(&fpu->fpr[idx], 1); + vs[1] = get_fpr64(&fpu->fpr[idx], 0); +#endif + break; + case KVM_REG_MIPS_MSA_IR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + v = boot_cpu_data.msa_id; + break; + case KVM_REG_MIPS_MSA_CSR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + v = fpu->msacsr; + break; + + /* Co-processor 0 registers */ case KVM_REG_MIPS_CP0_INDEX: v = (long)kvm_read_c0_guest_index(cop0); break; @@ -573,8 +646,8 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_EPC: v = (long)kvm_read_c0_guest_epc(cop0); break; - case KVM_REG_MIPS_CP0_ERROREPC: - v = (long)kvm_read_c0_guest_errorepc(cop0); + case KVM_REG_MIPS_CP0_PRID: + v = (long)kvm_read_c0_guest_prid(cop0); break; case KVM_REG_MIPS_CP0_CONFIG: v = (long)kvm_read_c0_guest_config(cop0); @@ -588,9 +661,18 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_CONFIG3: v = (long)kvm_read_c0_guest_config3(cop0); break; + case KVM_REG_MIPS_CP0_CONFIG4: + v = (long)kvm_read_c0_guest_config4(cop0); + break; + case KVM_REG_MIPS_CP0_CONFIG5: + v = (long)kvm_read_c0_guest_config5(cop0); + break; case KVM_REG_MIPS_CP0_CONFIG7: v = (long)kvm_read_c0_guest_config7(cop0); break; + case KVM_REG_MIPS_CP0_ERROREPC: + v = (long)kvm_read_c0_guest_errorepc(cop0); + break; /* registers to be handled specially */ case KVM_REG_MIPS_CP0_COUNT: case KVM_REG_MIPS_COUNT_CTL: @@ -612,6 +694,10 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, u32 v32 = (u32)v; return put_user(v32, uaddr32); + } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { + void __user *uaddr = (void __user *)(long)reg->addr; + + return copy_to_user(uaddr, vs, 16); } else { return -EINVAL; } @@ -621,7 +707,10 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { struct mips_coproc *cop0 = vcpu->arch.cop0; - u64 v; + struct mips_fpu_struct *fpu = &vcpu->arch.fpu; + s64 v; + s64 vs[2]; + unsigned int idx; if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U64) { u64 __user *uaddr64 = (u64 __user *)(long)reg->addr; @@ -635,11 +724,16 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, if (get_user(v32, uaddr32) != 0) return -EFAULT; v = (s64)v32; + } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { + void __user *uaddr = (void __user *)(long)reg->addr; + + return copy_from_user(vs, uaddr, 16); } else { return -EINVAL; } switch (reg->id) { + /* General purpose registers */ case KVM_REG_MIPS_R0: /* Silently ignore requests to set $0 */ break; @@ -656,6 +750,64 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, vcpu->arch.pc = v; break; + /* Floating point registers */ + case KVM_REG_MIPS_FPR_32(0) ... KVM_REG_MIPS_FPR_32(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_32(0); + /* Odd singles in top of even double when FR=0 */ + if (kvm_read_c0_guest_status(cop0) & ST0_FR) + set_fpr32(&fpu->fpr[idx], 0, v); + else + set_fpr32(&fpu->fpr[idx & ~1], idx & 1, v); + break; + case KVM_REG_MIPS_FPR_64(0) ... KVM_REG_MIPS_FPR_64(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_64(0); + /* Can't access odd doubles in FR=0 mode */ + if (idx & 1 && !(kvm_read_c0_guest_status(cop0) & ST0_FR)) + return -EINVAL; + set_fpr64(&fpu->fpr[idx], 0, v); + break; + case KVM_REG_MIPS_FCR_IR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + /* Read-only */ + break; + case KVM_REG_MIPS_FCR_CSR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + fpu->fcr31 = v; + break; + + /* MIPS SIMD Architecture (MSA) registers */ + case KVM_REG_MIPS_VEC_128(0) ... KVM_REG_MIPS_VEC_128(31): + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_VEC_128(0); +#ifdef CONFIG_CPU_LITTLE_ENDIAN + /* least significant byte first */ + set_fpr64(&fpu->fpr[idx], 0, vs[0]); + set_fpr64(&fpu->fpr[idx], 1, vs[1]); +#else + /* most significant byte first */ + set_fpr64(&fpu->fpr[idx], 1, vs[0]); + set_fpr64(&fpu->fpr[idx], 0, vs[1]); +#endif + break; + case KVM_REG_MIPS_MSA_IR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + /* Read-only */ + break; + case KVM_REG_MIPS_MSA_CSR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + fpu->msacsr = v; + break; + + /* Co-processor 0 registers */ case KVM_REG_MIPS_CP0_INDEX: kvm_write_c0_guest_index(cop0, v); break; @@ -686,6 +838,9 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_EPC: kvm_write_c0_guest_epc(cop0, v); break; + case KVM_REG_MIPS_CP0_PRID: + kvm_write_c0_guest_prid(cop0, v); + break; case KVM_REG_MIPS_CP0_ERROREPC: kvm_write_c0_guest_errorepc(cop0, v); break; @@ -693,6 +848,12 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_COUNT: case KVM_REG_MIPS_CP0_COMPARE: case KVM_REG_MIPS_CP0_CAUSE: + case KVM_REG_MIPS_CP0_CONFIG: + case KVM_REG_MIPS_CP0_CONFIG1: + case KVM_REG_MIPS_CP0_CONFIG2: + case KVM_REG_MIPS_CP0_CONFIG3: + case KVM_REG_MIPS_CP0_CONFIG4: + case KVM_REG_MIPS_CP0_CONFIG5: case KVM_REG_MIPS_COUNT_CTL: case KVM_REG_MIPS_COUNT_RESUME: case KVM_REG_MIPS_COUNT_HZ: @@ -703,6 +864,33 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, return 0; } +static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, + struct kvm_enable_cap *cap) +{ + int r = 0; + + if (!kvm_vm_ioctl_check_extension(vcpu->kvm, cap->cap)) + return -EINVAL; + if (cap->flags) + return -EINVAL; + if (cap->args[0]) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_MIPS_FPU: + vcpu->arch.fpu_enabled = true; + break; + case KVM_CAP_MIPS_MSA: + vcpu->arch.msa_enabled = true; + break; + default: + r = -EINVAL; + break; + } + + return r; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -760,6 +948,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); break; } + case KVM_ENABLE_CAP: { + struct kvm_enable_cap cap; + + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); + break; + } default: r = -ENOIOCTLCMD; } @@ -868,11 +1065,30 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) switch (ext) { case KVM_CAP_ONE_REG: + case KVM_CAP_ENABLE_CAP: r = 1; break; case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; + case KVM_CAP_MIPS_FPU: + r = !!cpu_has_fpu; + break; + case KVM_CAP_MIPS_MSA: + /* + * We don't support MSA vector partitioning yet: + * 1) It would require explicit support which can't be tested + * yet due to lack of support in current hardware. + * 2) It extends the state that would need to be saved/restored + * by e.g. QEMU for migration. + * + * When vector partitioning hardware becomes available, support + * could be added by requiring a flag when enabling + * KVM_CAP_MIPS_MSA capability to indicate that userland knows + * to save/restore the appropriate extra state. + */ + r = cpu_has_msa && !(boot_cpu_data.msa_id & MSA_IR_WRPF); + break; default: r = 0; break; @@ -1119,6 +1335,30 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) ret = kvm_mips_callbacks->handle_break(vcpu); break; + case T_TRAP: + ++vcpu->stat.trap_inst_exits; + trace_kvm_exit(vcpu, TRAP_INST_EXITS); + ret = kvm_mips_callbacks->handle_trap(vcpu); + break; + + case T_MSAFPE: + ++vcpu->stat.msa_fpe_exits; + trace_kvm_exit(vcpu, MSA_FPE_EXITS); + ret = kvm_mips_callbacks->handle_msa_fpe(vcpu); + break; + + case T_FPE: + ++vcpu->stat.fpe_exits; + trace_kvm_exit(vcpu, FPE_EXITS); + ret = kvm_mips_callbacks->handle_fpe(vcpu); + break; + + case T_MSADIS: + ++vcpu->stat.msa_disabled_exits; + trace_kvm_exit(vcpu, MSA_DISABLED_EXITS); + ret = kvm_mips_callbacks->handle_msa_disabled(vcpu); + break; + default: kvm_err("Exception Code: %d, not yet handled, @ PC: %p, inst: 0x%08x BadVaddr: %#lx Status: %#lx\n", exccode, opc, kvm_get_inst(opc, vcpu), badvaddr, @@ -1146,12 +1386,233 @@ skip_emul: } } + if (ret == RESUME_GUEST) { + /* + * If FPU / MSA are enabled (i.e. the guest's FPU / MSA context + * is live), restore FCR31 / MSACSR. + * + * This should be before returning to the guest exception + * vector, as it may well cause an [MSA] FP exception if there + * are pending exception bits unmasked. (see + * kvm_mips_csr_die_notifier() for how that is handled). + */ + if (kvm_mips_guest_has_fpu(&vcpu->arch) && + read_c0_status() & ST0_CU1) + __kvm_restore_fcsr(&vcpu->arch); + + if (kvm_mips_guest_has_msa(&vcpu->arch) && + read_c0_config5() & MIPS_CONF5_MSAEN) + __kvm_restore_msacsr(&vcpu->arch); + } + /* Disable HTW before returning to guest or host */ htw_stop(); return ret; } +/* Enable FPU for guest and restore context */ +void kvm_own_fpu(struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + unsigned int sr, cfg5; + + preempt_disable(); + + sr = kvm_read_c0_guest_status(cop0); + + /* + * If MSA state is already live, it is undefined how it interacts with + * FR=0 FPU state, and we don't want to hit reserved instruction + * exceptions trying to save the MSA state later when CU=1 && FR=1, so + * play it safe and save it first. + * + * In theory we shouldn't ever hit this case since kvm_lose_fpu() should + * get called when guest CU1 is set, however we can't trust the guest + * not to clobber the status register directly via the commpage. + */ + if (cpu_has_msa && sr & ST0_CU1 && !(sr & ST0_FR) && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) + kvm_lose_fpu(vcpu); + + /* + * Enable FPU for guest + * We set FR and FRE according to guest context + */ + change_c0_status(ST0_CU1 | ST0_FR, sr); + if (cpu_has_fre) { + cfg5 = kvm_read_c0_guest_config5(cop0); + change_c0_config5(MIPS_CONF5_FRE, cfg5); + } + enable_fpu_hazard(); + + /* If guest FPU state not active, restore it now */ + if (!(vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU)) { + __kvm_restore_fpu(&vcpu->arch); + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_FPU; + } + + preempt_enable(); +} + +#ifdef CONFIG_CPU_HAS_MSA +/* Enable MSA for guest and restore context */ +void kvm_own_msa(struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + unsigned int sr, cfg5; + + preempt_disable(); + + /* + * Enable FPU if enabled in guest, since we're restoring FPU context + * anyway. We set FR and FRE according to guest context. + */ + if (kvm_mips_guest_has_fpu(&vcpu->arch)) { + sr = kvm_read_c0_guest_status(cop0); + + /* + * If FR=0 FPU state is already live, it is undefined how it + * interacts with MSA state, so play it safe and save it first. + */ + if (!(sr & ST0_FR) && + (vcpu->arch.fpu_inuse & (KVM_MIPS_FPU_FPU | + KVM_MIPS_FPU_MSA)) == KVM_MIPS_FPU_FPU) + kvm_lose_fpu(vcpu); + + change_c0_status(ST0_CU1 | ST0_FR, sr); + if (sr & ST0_CU1 && cpu_has_fre) { + cfg5 = kvm_read_c0_guest_config5(cop0); + change_c0_config5(MIPS_CONF5_FRE, cfg5); + } + } + + /* Enable MSA for guest */ + set_c0_config5(MIPS_CONF5_MSAEN); + enable_fpu_hazard(); + + switch (vcpu->arch.fpu_inuse & (KVM_MIPS_FPU_FPU | KVM_MIPS_FPU_MSA)) { + case KVM_MIPS_FPU_FPU: + /* + * Guest FPU state already loaded, only restore upper MSA state + */ + __kvm_restore_msa_upper(&vcpu->arch); + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_MSA; + break; + case 0: + /* Neither FPU or MSA already active, restore full MSA state */ + __kvm_restore_msa(&vcpu->arch); + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_MSA; + if (kvm_mips_guest_has_fpu(&vcpu->arch)) + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_FPU; + break; + default: + break; + } + + preempt_enable(); +} +#endif + +/* Drop FPU & MSA without saving it */ +void kvm_drop_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + if (cpu_has_msa && vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) { + disable_msa(); + vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_MSA; + } + if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) { + clear_c0_status(ST0_CU1 | ST0_FR); + vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_FPU; + } + preempt_enable(); +} + +/* Save and disable FPU & MSA */ +void kvm_lose_fpu(struct kvm_vcpu *vcpu) +{ + /* + * FPU & MSA get disabled in root context (hardware) when it is disabled + * in guest context (software), but the register state in the hardware + * may still be in use. This is why we explicitly re-enable the hardware + * before saving. + */ + + preempt_disable(); + if (cpu_has_msa && vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) { + set_c0_config5(MIPS_CONF5_MSAEN); + enable_fpu_hazard(); + + __kvm_save_msa(&vcpu->arch); + + /* Disable MSA & FPU */ + disable_msa(); + if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) + clear_c0_status(ST0_CU1 | ST0_FR); + vcpu->arch.fpu_inuse &= ~(KVM_MIPS_FPU_FPU | KVM_MIPS_FPU_MSA); + } else if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) { + set_c0_status(ST0_CU1); + enable_fpu_hazard(); + + __kvm_save_fpu(&vcpu->arch); + vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_FPU; + + /* Disable FPU */ + clear_c0_status(ST0_CU1 | ST0_FR); + } + preempt_enable(); +} + +/* + * Step over a specific ctc1 to FCSR and a specific ctcmsa to MSACSR which are + * used to restore guest FCSR/MSACSR state and may trigger a "harmless" FP/MSAFP + * exception if cause bits are set in the value being written. + */ +static int kvm_mips_csr_die_notify(struct notifier_block *self, + unsigned long cmd, void *ptr) +{ + struct die_args *args = (struct die_args *)ptr; + struct pt_regs *regs = args->regs; + unsigned long pc; + + /* Only interested in FPE and MSAFPE */ + if (cmd != DIE_FP && cmd != DIE_MSAFP) + return NOTIFY_DONE; + + /* Return immediately if guest context isn't active */ + if (!(current->flags & PF_VCPU)) + return NOTIFY_DONE; + + /* Should never get here from user mode */ + BUG_ON(user_mode(regs)); + + pc = instruction_pointer(regs); + switch (cmd) { + case DIE_FP: + /* match 2nd instruction in __kvm_restore_fcsr */ + if (pc != (unsigned long)&__kvm_restore_fcsr + 4) + return NOTIFY_DONE; + break; + case DIE_MSAFP: + /* match 2nd/3rd instruction in __kvm_restore_msacsr */ + if (!cpu_has_msa || + pc < (unsigned long)&__kvm_restore_msacsr + 4 || + pc > (unsigned long)&__kvm_restore_msacsr + 8) + return NOTIFY_DONE; + break; + } + + /* Move PC forward a little and continue executing */ + instruction_pointer(regs) += 4; + + return NOTIFY_STOP; +} + +static struct notifier_block kvm_mips_csr_die_notifier = { + .notifier_call = kvm_mips_csr_die_notify, +}; + int __init kvm_mips_init(void) { int ret; @@ -1161,6 +1622,8 @@ int __init kvm_mips_init(void) if (ret) return ret; + register_die_notifier(&kvm_mips_csr_die_notifier); + /* * On MIPS, kernel modules are executed from "mapped space", which * requires TLBs. The TLB handling code is statically linked with @@ -1173,7 +1636,6 @@ int __init kvm_mips_init(void) kvm_mips_release_pfn_clean = kvm_release_pfn_clean; kvm_mips_is_error_pfn = is_error_pfn; - pr_info("KVM/MIPS Initialized\n"); return 0; } @@ -1185,7 +1647,7 @@ void __exit kvm_mips_exit(void) kvm_mips_release_pfn_clean = NULL; kvm_mips_is_error_pfn = NULL; - pr_info("KVM/MIPS unloaded\n"); + unregister_die_notifier(&kvm_mips_csr_die_notifier); } module_init(kvm_mips_init); diff --git a/arch/mips/kvm/msa.S b/arch/mips/kvm/msa.S new file mode 100644 index 0000000..d02f0c6 --- /dev/null +++ b/arch/mips/kvm/msa.S @@ -0,0 +1,161 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * MIPS SIMD Architecture (MSA) context handling code for KVM. + * + * Copyright (C) 2015 Imagination Technologies Ltd. + */ + +#include <asm/asm.h> +#include <asm/asm-offsets.h> +#include <asm/asmmacro.h> +#include <asm/regdef.h> + + .set noreorder + .set noat + +LEAF(__kvm_save_msa) + st_d 0, VCPU_FPR0, a0 + st_d 1, VCPU_FPR1, a0 + st_d 2, VCPU_FPR2, a0 + st_d 3, VCPU_FPR3, a0 + st_d 4, VCPU_FPR4, a0 + st_d 5, VCPU_FPR5, a0 + st_d 6, VCPU_FPR6, a0 + st_d 7, VCPU_FPR7, a0 + st_d 8, VCPU_FPR8, a0 + st_d 9, VCPU_FPR9, a0 + st_d 10, VCPU_FPR10, a0 + st_d 11, VCPU_FPR11, a0 + st_d 12, VCPU_FPR12, a0 + st_d 13, VCPU_FPR13, a0 + st_d 14, VCPU_FPR14, a0 + st_d 15, VCPU_FPR15, a0 + st_d 16, VCPU_FPR16, a0 + st_d 17, VCPU_FPR17, a0 + st_d 18, VCPU_FPR18, a0 + st_d 19, VCPU_FPR19, a0 + st_d 20, VCPU_FPR20, a0 + st_d 21, VCPU_FPR21, a0 + st_d 22, VCPU_FPR22, a0 + st_d 23, VCPU_FPR23, a0 + st_d 24, VCPU_FPR24, a0 + st_d 25, VCPU_FPR25, a0 + st_d 26, VCPU_FPR26, a0 + st_d 27, VCPU_FPR27, a0 + st_d 28, VCPU_FPR28, a0 + st_d 29, VCPU_FPR29, a0 + st_d 30, VCPU_FPR30, a0 + st_d 31, VCPU_FPR31, a0 + jr ra + nop + END(__kvm_save_msa) + +LEAF(__kvm_restore_msa) + ld_d 0, VCPU_FPR0, a0 + ld_d 1, VCPU_FPR1, a0 + ld_d 2, VCPU_FPR2, a0 + ld_d 3, VCPU_FPR3, a0 + ld_d 4, VCPU_FPR4, a0 + ld_d 5, VCPU_FPR5, a0 + ld_d 6, VCPU_FPR6, a0 + ld_d 7, VCPU_FPR7, a0 + ld_d 8, VCPU_FPR8, a0 + ld_d 9, VCPU_FPR9, a0 + ld_d 10, VCPU_FPR10, a0 + ld_d 11, VCPU_FPR11, a0 + ld_d 12, VCPU_FPR12, a0 + ld_d 13, VCPU_FPR13, a0 + ld_d 14, VCPU_FPR14, a0 + ld_d 15, VCPU_FPR15, a0 + ld_d 16, VCPU_FPR16, a0 + ld_d 17, VCPU_FPR17, a0 + ld_d 18, VCPU_FPR18, a0 + ld_d 19, VCPU_FPR19, a0 + ld_d 20, VCPU_FPR20, a0 + ld_d 21, VCPU_FPR21, a0 + ld_d 22, VCPU_FPR22, a0 + ld_d 23, VCPU_FPR23, a0 + ld_d 24, VCPU_FPR24, a0 + ld_d 25, VCPU_FPR25, a0 + ld_d 26, VCPU_FPR26, a0 + ld_d 27, VCPU_FPR27, a0 + ld_d 28, VCPU_FPR28, a0 + ld_d 29, VCPU_FPR29, a0 + ld_d 30, VCPU_FPR30, a0 + ld_d 31, VCPU_FPR31, a0 + jr ra + nop + END(__kvm_restore_msa) + + .macro kvm_restore_msa_upper wr, off, base + .set push + .set noat +#ifdef CONFIG_64BIT + ld $1, \off(\base) + insert_d \wr, 1 +#elif defined(CONFIG_CPU_LITTLE_ENDIAN) + lw $1, \off(\base) + insert_w \wr, 2 + lw $1, (\off+4)(\base) + insert_w \wr, 3 +#else /* CONFIG_CPU_BIG_ENDIAN */ + lw $1, (\off+4)(\base) + insert_w \wr, 2 + lw $1, \off(\base) + insert_w \wr, 3 +#endif + .set pop + .endm + +LEAF(__kvm_restore_msa_upper) + kvm_restore_msa_upper 0, VCPU_FPR0 +8, a0 + kvm_restore_msa_upper 1, VCPU_FPR1 +8, a0 + kvm_restore_msa_upper 2, VCPU_FPR2 +8, a0 + kvm_restore_msa_upper 3, VCPU_FPR3 +8, a0 + kvm_restore_msa_upper 4, VCPU_FPR4 +8, a0 + kvm_restore_msa_upper 5, VCPU_FPR5 +8, a0 + kvm_restore_msa_upper 6, VCPU_FPR6 +8, a0 + kvm_restore_msa_upper 7, VCPU_FPR7 +8, a0 + kvm_restore_msa_upper 8, VCPU_FPR8 +8, a0 + kvm_restore_msa_upper 9, VCPU_FPR9 +8, a0 + kvm_restore_msa_upper 10, VCPU_FPR10+8, a0 + kvm_restore_msa_upper 11, VCPU_FPR11+8, a0 + kvm_restore_msa_upper 12, VCPU_FPR12+8, a0 + kvm_restore_msa_upper 13, VCPU_FPR13+8, a0 + kvm_restore_msa_upper 14, VCPU_FPR14+8, a0 + kvm_restore_msa_upper 15, VCPU_FPR15+8, a0 + kvm_restore_msa_upper 16, VCPU_FPR16+8, a0 + kvm_restore_msa_upper 17, VCPU_FPR17+8, a0 + kvm_restore_msa_upper 18, VCPU_FPR18+8, a0 + kvm_restore_msa_upper 19, VCPU_FPR19+8, a0 + kvm_restore_msa_upper 20, VCPU_FPR20+8, a0 + kvm_restore_msa_upper 21, VCPU_FPR21+8, a0 + kvm_restore_msa_upper 22, VCPU_FPR22+8, a0 + kvm_restore_msa_upper 23, VCPU_FPR23+8, a0 + kvm_restore_msa_upper 24, VCPU_FPR24+8, a0 + kvm_restore_msa_upper 25, VCPU_FPR25+8, a0 + kvm_restore_msa_upper 26, VCPU_FPR26+8, a0 + kvm_restore_msa_upper 27, VCPU_FPR27+8, a0 + kvm_restore_msa_upper 28, VCPU_FPR28+8, a0 + kvm_restore_msa_upper 29, VCPU_FPR29+8, a0 + kvm_restore_msa_upper 30, VCPU_FPR30+8, a0 + kvm_restore_msa_upper 31, VCPU_FPR31+8, a0 + jr ra + nop + END(__kvm_restore_msa_upper) + +LEAF(__kvm_restore_msacsr) + lw t0, VCPU_MSA_CSR(a0) + /* + * The ctcmsa must stay at this offset in __kvm_restore_msacsr. + * See kvm_mips_csr_die_notify() which handles t0 containing a value + * which triggers an MSA FP Exception, which must be stepped over and + * ignored since the set cause bits must remain there for the guest. + */ + _ctcmsa MSA_CSR, t0 + jr ra + nop + END(__kvm_restore_msacsr) diff --git a/arch/mips/kvm/stats.c b/arch/mips/kvm/stats.c index a74d602..888bb67 100644 --- a/arch/mips/kvm/stats.c +++ b/arch/mips/kvm/stats.c @@ -25,6 +25,10 @@ char *kvm_mips_exit_types_str[MAX_KVM_MIPS_EXIT_TYPES] = { "System Call", "Reserved Inst", "Break Inst", + "Trap Inst", + "MSA FPE", + "FPE", + "MSA Disabled", "D-Cache Flushes", }; diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c index b6beb0e..aed0ac2 100644 --- a/arch/mips/kvm/tlb.c +++ b/arch/mips/kvm/tlb.c @@ -733,6 +733,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } } + /* restore guest state to registers */ + kvm_mips_callbacks->vcpu_set_regs(vcpu); + local_irq_restore(flags); } @@ -751,6 +754,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->arch.preempt_entryhi = read_c0_entryhi(); vcpu->arch.last_sched_cpu = cpu; + /* save guest state in registers */ + kvm_mips_callbacks->vcpu_get_regs(vcpu); + if (((cpu_context(cpu, current->mm) ^ asid_cache(cpu)) & ASID_VERSION_MASK)) { kvm_debug("%s: Dropping MMU Context: %#lx\n", __func__, diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c index fd7257b..d836ed5 100644 --- a/arch/mips/kvm/trap_emul.c +++ b/arch/mips/kvm/trap_emul.c @@ -39,16 +39,30 @@ static gpa_t kvm_trap_emul_gva_to_gpa_cb(gva_t gva) static int kvm_trap_emul_handle_cop_unusable(struct kvm_vcpu *vcpu) { + struct mips_coproc *cop0 = vcpu->arch.cop0; struct kvm_run *run = vcpu->run; uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc; unsigned long cause = vcpu->arch.host_cp0_cause; enum emulation_result er = EMULATE_DONE; int ret = RESUME_GUEST; - if (((cause & CAUSEF_CE) >> CAUSEB_CE) == 1) - er = kvm_mips_emulate_fpu_exc(cause, opc, run, vcpu); - else + if (((cause & CAUSEF_CE) >> CAUSEB_CE) == 1) { + /* FPU Unusable */ + if (!kvm_mips_guest_has_fpu(&vcpu->arch) || + (kvm_read_c0_guest_status(cop0) & ST0_CU1) == 0) { + /* + * Unusable/no FPU in guest: + * deliver guest COP1 Unusable Exception + */ + er = kvm_mips_emulate_fpu_exc(cause, opc, run, vcpu); + } else { + /* Restore FPU state */ + kvm_own_fpu(vcpu); + er = EMULATE_DONE; + } + } else { er = kvm_mips_emulate_inst(cause, opc, run, vcpu); + } switch (er) { case EMULATE_DONE: @@ -330,6 +344,107 @@ static int kvm_trap_emul_handle_break(struct kvm_vcpu *vcpu) return ret; } +static int kvm_trap_emul_handle_trap(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + er = kvm_mips_emulate_trap_exc(cause, opc, run, vcpu); + if (er == EMULATE_DONE) { + ret = RESUME_GUEST; + } else { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + } + return ret; +} + +static int kvm_trap_emul_handle_msa_fpe(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + er = kvm_mips_emulate_msafpe_exc(cause, opc, run, vcpu); + if (er == EMULATE_DONE) { + ret = RESUME_GUEST; + } else { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + } + return ret; +} + +static int kvm_trap_emul_handle_fpe(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + er = kvm_mips_emulate_fpe_exc(cause, opc, run, vcpu); + if (er == EMULATE_DONE) { + ret = RESUME_GUEST; + } else { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + } + return ret; +} + +/** + * kvm_trap_emul_handle_msa_disabled() - Guest used MSA while disabled in root. + * @vcpu: Virtual CPU context. + * + * Handle when the guest attempts to use MSA when it is disabled. + */ +static int kvm_trap_emul_handle_msa_disabled(struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + if (!kvm_mips_guest_has_msa(&vcpu->arch) || + (kvm_read_c0_guest_status(cop0) & (ST0_CU1 | ST0_FR)) == ST0_CU1) { + /* + * No MSA in guest, or FPU enabled and not in FR=1 mode, + * guest reserved instruction exception + */ + er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu); + } else if (!(kvm_read_c0_guest_config5(cop0) & MIPS_CONF5_MSAEN)) { + /* MSA disabled by guest, guest MSA disabled exception */ + er = kvm_mips_emulate_msadis_exc(cause, opc, run, vcpu); + } else { + /* Restore MSA/FPU state */ + kvm_own_msa(vcpu); + er = EMULATE_DONE; + } + + switch (er) { + case EMULATE_DONE: + ret = RESUME_GUEST; + break; + + case EMULATE_FAIL: + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + break; + + default: + BUG(); + } + return ret; +} + static int kvm_trap_emul_vm_init(struct kvm *kvm) { return 0; @@ -351,8 +466,9 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu) * guest will come up as expected, for now we simulate a MIPS 24kc */ kvm_write_c0_guest_prid(cop0, 0x00019300); - kvm_write_c0_guest_config(cop0, - MIPS_CONFIG0 | (0x1 << CP0C0_AR) | + /* Have config1, Cacheable, noncoherent, write-back, write allocate */ + kvm_write_c0_guest_config(cop0, MIPS_CONF_M | (0x3 << CP0C0_K0) | + (0x1 << CP0C0_AR) | (MMU_TYPE_R4000 << CP0C0_MT)); /* Read the cache characteristics from the host Config1 Register */ @@ -368,10 +484,18 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu) (1 << CP0C1_WR) | (1 << CP0C1_CA)); kvm_write_c0_guest_config1(cop0, config1); - kvm_write_c0_guest_config2(cop0, MIPS_CONFIG2); - /* MIPS_CONFIG2 | (read_c0_config2() & 0xfff) */ - kvm_write_c0_guest_config3(cop0, MIPS_CONFIG3 | (0 << CP0C3_VInt) | - (1 << CP0C3_ULRI)); + /* Have config3, no tertiary/secondary caches implemented */ + kvm_write_c0_guest_config2(cop0, MIPS_CONF_M); + /* MIPS_CONF_M | (read_c0_config2() & 0xfff) */ + + /* Have config4, UserLocal */ + kvm_write_c0_guest_config3(cop0, MIPS_CONF_M | MIPS_CONF3_ULRI); + + /* Have config5 */ + kvm_write_c0_guest_config4(cop0, MIPS_CONF_M); + + /* No config6 */ + kvm_write_c0_guest_config5(cop0, 0); /* Set Wait IE/IXMT Ignore in Config7, IAR, AR */ kvm_write_c0_guest_config7(cop0, (MIPS_CONF7_WII) | (1 << 10)); @@ -416,6 +540,7 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, { struct mips_coproc *cop0 = vcpu->arch.cop0; int ret = 0; + unsigned int cur, change; switch (reg->id) { case KVM_REG_MIPS_CP0_COUNT: @@ -444,6 +569,44 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, kvm_write_c0_guest_cause(cop0, v); } break; + case KVM_REG_MIPS_CP0_CONFIG: + /* read-only for now */ + break; + case KVM_REG_MIPS_CP0_CONFIG1: + cur = kvm_read_c0_guest_config1(cop0); + change = (cur ^ v) & kvm_mips_config1_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config1(cop0, v); + } + break; + case KVM_REG_MIPS_CP0_CONFIG2: + /* read-only for now */ + break; + case KVM_REG_MIPS_CP0_CONFIG3: + cur = kvm_read_c0_guest_config3(cop0); + change = (cur ^ v) & kvm_mips_config3_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config3(cop0, v); + } + break; + case KVM_REG_MIPS_CP0_CONFIG4: + cur = kvm_read_c0_guest_config4(cop0); + change = (cur ^ v) & kvm_mips_config4_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config4(cop0, v); + } + break; + case KVM_REG_MIPS_CP0_CONFIG5: + cur = kvm_read_c0_guest_config5(cop0); + change = (cur ^ v) & kvm_mips_config5_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config5(cop0, v); + } + break; case KVM_REG_MIPS_COUNT_CTL: ret = kvm_mips_set_count_ctl(vcpu, v); break; @@ -459,6 +622,18 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, return ret; } +static int kvm_trap_emul_vcpu_get_regs(struct kvm_vcpu *vcpu) +{ + kvm_lose_fpu(vcpu); + + return 0; +} + +static int kvm_trap_emul_vcpu_set_regs(struct kvm_vcpu *vcpu) +{ + return 0; +} + static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { /* exit handlers */ .handle_cop_unusable = kvm_trap_emul_handle_cop_unusable, @@ -470,6 +645,10 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { .handle_syscall = kvm_trap_emul_handle_syscall, .handle_res_inst = kvm_trap_emul_handle_res_inst, .handle_break = kvm_trap_emul_handle_break, + .handle_trap = kvm_trap_emul_handle_trap, + .handle_msa_fpe = kvm_trap_emul_handle_msa_fpe, + .handle_fpe = kvm_trap_emul_handle_fpe, + .handle_msa_disabled = kvm_trap_emul_handle_msa_disabled, .vm_init = kvm_trap_emul_vm_init, .vcpu_init = kvm_trap_emul_vcpu_init, @@ -483,6 +662,8 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { .irq_clear = kvm_mips_irq_clear_cb, .get_one_reg = kvm_trap_emul_get_one_reg, .set_one_reg = kvm_trap_emul_set_one_reg, + .vcpu_get_regs = kvm_trap_emul_vcpu_get_regs, + .vcpu_set_regs = kvm_trap_emul_vcpu_set_regs, }; int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks) diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c index 39b3a8f..6249cdc 100644 --- a/arch/powerpc/kvm/mpic.c +++ b/arch/powerpc/kvm/mpic.c @@ -34,7 +34,7 @@ #include <asm/kvm_para.h> #include <asm/kvm_host.h> #include <asm/kvm_ppc.h> -#include "iodev.h" +#include <kvm/iodev.h> #define MAX_CPU 32 #define MAX_SRC 256 @@ -289,11 +289,6 @@ static inline void IRQ_resetbit(struct irq_queue *q, int n_IRQ) clear_bit(n_IRQ, q->queue); } -static inline int IRQ_testbit(struct irq_queue *q, int n_IRQ) -{ - return test_bit(n_IRQ, q->queue); -} - static void IRQ_check(struct openpic *opp, struct irq_queue *q) { int irq = -1; @@ -1374,8 +1369,9 @@ static int kvm_mpic_write_internal(struct openpic *opp, gpa_t addr, u32 val) return -ENXIO; } -static int kvm_mpic_read(struct kvm_io_device *this, gpa_t addr, - int len, void *ptr) +static int kvm_mpic_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, void *ptr) { struct openpic *opp = container_of(this, struct openpic, mmio); int ret; @@ -1415,8 +1411,9 @@ static int kvm_mpic_read(struct kvm_io_device *this, gpa_t addr, return ret; } -static int kvm_mpic_write(struct kvm_io_device *this, gpa_t addr, - int len, const void *ptr) +static int kvm_mpic_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, const void *ptr) { struct openpic *opp = container_of(this, struct openpic, mmio); int ret; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 27c0fac..24bfe40 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -807,7 +807,7 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, idx = srcu_read_lock(&vcpu->kvm->srcu); - ret = kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr, + ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, run->mmio.phys_addr, bytes, &run->mmio.data); srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -880,7 +880,7 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, idx = srcu_read_lock(&vcpu->kvm->srcu); - ret = kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr, + ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, run->mmio.phys_addr, bytes, &run->mmio.data); srcu_read_unlock(&vcpu->kvm->srcu, idx); diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index f407bbf..d01fc58 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -172,7 +172,9 @@ struct kvm_s390_sie_block { __u32 fac; /* 0x01a0 */ __u8 reserved1a4[20]; /* 0x01a4 */ __u64 cbrlo; /* 0x01b8 */ - __u8 reserved1c0[30]; /* 0x01c0 */ + __u8 reserved1c0[8]; /* 0x01c0 */ + __u32 ecd; /* 0x01c8 */ + __u8 reserved1cc[18]; /* 0x01cc */ __u64 pp; /* 0x01de */ __u8 reserved1e6[2]; /* 0x01e6 */ __u64 itdba; /* 0x01e8 */ @@ -183,11 +185,17 @@ struct kvm_s390_itdb { __u8 data[256]; } __packed; +struct kvm_s390_vregs { + __vector128 vrs[32]; + __u8 reserved200[512]; /* for future vector expansion */ +} __packed; + struct sie_page { struct kvm_s390_sie_block sie_block; __u8 reserved200[1024]; /* 0x0200 */ struct kvm_s390_itdb itdb; /* 0x0600 */ - __u8 reserved700[2304]; /* 0x0700 */ + __u8 reserved700[1280]; /* 0x0700 */ + struct kvm_s390_vregs vregs; /* 0x0c00 */ } __packed; struct kvm_vcpu_stat { @@ -238,6 +246,7 @@ struct kvm_vcpu_stat { u32 instruction_sigp_stop; u32 instruction_sigp_stop_store_status; u32 instruction_sigp_store_status; + u32 instruction_sigp_store_adtl_status; u32 instruction_sigp_arch; u32 instruction_sigp_prefix; u32 instruction_sigp_restart; @@ -270,6 +279,7 @@ struct kvm_vcpu_stat { #define PGM_SPECIAL_OPERATION 0x13 #define PGM_OPERAND 0x15 #define PGM_TRACE_TABEL 0x16 +#define PGM_VECTOR_PROCESSING 0x1b #define PGM_SPACE_SWITCH 0x1c #define PGM_HFP_SQUARE_ROOT 0x1d #define PGM_PC_TRANSLATION_SPEC 0x1f @@ -334,6 +344,11 @@ enum irq_types { IRQ_PEND_COUNT }; +/* We have 2M for virtio device descriptor pages. Smallest amount of + * memory per page is 24 bytes (1 queue), so (2048*1024) / 24 = 87381 + */ +#define KVM_S390_MAX_VIRTIO_IRQS 87381 + /* * Repressible (non-floating) machine check interrupts * subclass bits in MCIC @@ -411,13 +426,32 @@ struct kvm_s390_local_interrupt { unsigned long pending_irqs; }; +#define FIRQ_LIST_IO_ISC_0 0 +#define FIRQ_LIST_IO_ISC_1 1 +#define FIRQ_LIST_IO_ISC_2 2 +#define FIRQ_LIST_IO_ISC_3 3 +#define FIRQ_LIST_IO_ISC_4 4 +#define FIRQ_LIST_IO_ISC_5 5 +#define FIRQ_LIST_IO_ISC_6 6 +#define FIRQ_LIST_IO_ISC_7 7 +#define FIRQ_LIST_PFAULT 8 +#define FIRQ_LIST_VIRTIO 9 +#define FIRQ_LIST_COUNT 10 +#define FIRQ_CNTR_IO 0 +#define FIRQ_CNTR_SERVICE 1 +#define FIRQ_CNTR_VIRTIO 2 +#define FIRQ_CNTR_PFAULT 3 +#define FIRQ_MAX_COUNT 4 + struct kvm_s390_float_interrupt { + unsigned long pending_irqs; spinlock_t lock; - struct list_head list; - atomic_t active; + struct list_head lists[FIRQ_LIST_COUNT]; + int counters[FIRQ_MAX_COUNT]; + struct kvm_s390_mchk_info mchk; + struct kvm_s390_ext_info srv_signal; int next_rr_cpu; unsigned long idle_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)]; - unsigned int irq_count; }; struct kvm_hw_wp_info_arch { @@ -465,6 +499,7 @@ struct kvm_vcpu_arch { s390_fp_regs host_fpregs; unsigned int host_acrs[NUM_ACRS]; s390_fp_regs guest_fpregs; + struct kvm_s390_vregs *host_vregs; struct kvm_s390_local_interrupt local_int; struct hrtimer ckc_timer; struct kvm_s390_pgm_info pgm; @@ -553,6 +588,7 @@ struct kvm_arch{ int use_cmma; int user_cpu_state_ctrl; int user_sigp; + int user_stsi; struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS]; wait_queue_head_t ipte_wq; int ipte_lock_count; diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index 9c77e60..ef1a5fc 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -150,6 +150,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_CRS (1UL << 3) #define KVM_SYNC_ARCH0 (1UL << 4) #define KVM_SYNC_PFAULT (1UL << 5) +#define KVM_SYNC_VRS (1UL << 6) /* definition of registers in kvm_run */ struct kvm_sync_regs { __u64 prefix; /* prefix register */ @@ -164,6 +165,9 @@ struct kvm_sync_regs { __u64 pft; /* pfault token [PFAULT] */ __u64 pfs; /* pfault select [PFAULT] */ __u64 pfc; /* pfault compare [PFAULT] */ + __u64 vrs[32][2]; /* vector registers */ + __u8 reserved[512]; /* for future vector expansion */ + __u32 fpc; /* only valid with vector registers */ }; #define KVM_REG_S390_TODPR (KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1) diff --git a/arch/s390/include/uapi/asm/sie.h b/arch/s390/include/uapi/asm/sie.h index d4096fd..ee69c08 100644 --- a/arch/s390/include/uapi/asm/sie.h +++ b/arch/s390/include/uapi/asm/sie.h @@ -230,7 +230,7 @@ * and returns a key, which can be used to find a mnemonic name * of the instruction in the icpt_insn_codes table. */ -#define icpt_insn_decoder(insn) \ +#define icpt_insn_decoder(insn) ( \ INSN_DECODE_IPA0(0x01, insn, 48, 0xff) \ INSN_DECODE_IPA0(0xaa, insn, 48, 0x0f) \ INSN_DECODE_IPA0(0xb2, insn, 48, 0xff) \ @@ -239,6 +239,6 @@ INSN_DECODE_IPA0(0xe5, insn, 48, 0xff) \ INSN_DECODE_IPA0(0xeb, insn, 16, 0xff) \ INSN_DECODE_IPA0(0xc8, insn, 48, 0x0f) \ - INSN_DECODE(insn) + INSN_DECODE(insn)) #endif /* _UAPI_ASM_S390_SIE_H */ diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index e07e916..8dc4db1 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -171,6 +171,7 @@ int main(void) #else /* CONFIG_32BIT */ DEFINE(__LC_DATA_EXC_CODE, offsetof(struct _lowcore, data_exc_code)); DEFINE(__LC_MCCK_FAIL_STOR_ADDR, offsetof(struct _lowcore, failing_storage_address)); + DEFINE(__LC_VX_SAVE_AREA_ADDR, offsetof(struct _lowcore, vector_save_area_addr)); DEFINE(__LC_EXT_PARAMS2, offsetof(struct _lowcore, ext_params2)); DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, floating_pt_save_area)); DEFINE(__LC_PASTE, offsetof(struct _lowcore, paste)); diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 9254aff..fc7ec95 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -77,7 +77,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) if (vcpu->run->s.regs.gprs[rx] & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], &parm, sizeof(parm)); + rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258) @@ -213,7 +213,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) * - gpr 3 contains the virtqueue index (passed as datamatch) * - gpr 4 contains the index on the bus (optionally) */ - ret = kvm_io_bus_write_cookie(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS, + ret = kvm_io_bus_write_cookie(vcpu, KVM_VIRTIO_CCW_NOTIFY_BUS, vcpu->run->s.regs.gprs[2] & 0xffffffff, 8, &vcpu->run->s.regs.gprs[3], vcpu->run->s.regs.gprs[4]); @@ -230,7 +230,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) { - int code = kvm_s390_get_base_disp_rs(vcpu) & 0xffff; + int code = kvm_s390_get_base_disp_rs(vcpu, NULL) & 0xffff; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 267523c..a7559f7 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -10,6 +10,7 @@ #include <asm/pgtable.h> #include "kvm-s390.h" #include "gaccess.h" +#include <asm/switch_to.h> union asce { unsigned long val; @@ -207,6 +208,54 @@ union raddress { unsigned long pfra : 52; /* Page-Frame Real Address */ }; +union alet { + u32 val; + struct { + u32 reserved : 7; + u32 p : 1; + u32 alesn : 8; + u32 alen : 16; + }; +}; + +union ald { + u32 val; + struct { + u32 : 1; + u32 alo : 24; + u32 all : 7; + }; +}; + +struct ale { + unsigned long i : 1; /* ALEN-Invalid Bit */ + unsigned long : 5; + unsigned long fo : 1; /* Fetch-Only Bit */ + unsigned long p : 1; /* Private Bit */ + unsigned long alesn : 8; /* Access-List-Entry Sequence Number */ + unsigned long aleax : 16; /* Access-List-Entry Authorization Index */ + unsigned long : 32; + unsigned long : 1; + unsigned long asteo : 25; /* ASN-Second-Table-Entry Origin */ + unsigned long : 6; + unsigned long astesn : 32; /* ASTE Sequence Number */ +} __packed; + +struct aste { + unsigned long i : 1; /* ASX-Invalid Bit */ + unsigned long ato : 29; /* Authority-Table Origin */ + unsigned long : 1; + unsigned long b : 1; /* Base-Space Bit */ + unsigned long ax : 16; /* Authorization Index */ + unsigned long atl : 12; /* Authority-Table Length */ + unsigned long : 2; + unsigned long ca : 1; /* Controlled-ASN Bit */ + unsigned long ra : 1; /* Reusable-ASN Bit */ + unsigned long asce : 64; /* Address-Space-Control Element */ + unsigned long ald : 32; + unsigned long astesn : 32; + /* .. more fields there */ +} __packed; int ipte_lock_held(struct kvm_vcpu *vcpu) { @@ -307,15 +356,157 @@ void ipte_unlock(struct kvm_vcpu *vcpu) ipte_unlock_simple(vcpu); } -static unsigned long get_vcpu_asce(struct kvm_vcpu *vcpu) +static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar, + int write) +{ + union alet alet; + struct ale ale; + struct aste aste; + unsigned long ald_addr, authority_table_addr; + union ald ald; + int eax, rc; + u8 authority_table; + + if (ar >= NUM_ACRS) + return -EINVAL; + + save_access_regs(vcpu->run->s.regs.acrs); + alet.val = vcpu->run->s.regs.acrs[ar]; + + if (ar == 0 || alet.val == 0) { + asce->val = vcpu->arch.sie_block->gcr[1]; + return 0; + } else if (alet.val == 1) { + asce->val = vcpu->arch.sie_block->gcr[7]; + return 0; + } + + if (alet.reserved) + return PGM_ALET_SPECIFICATION; + + if (alet.p) + ald_addr = vcpu->arch.sie_block->gcr[5]; + else + ald_addr = vcpu->arch.sie_block->gcr[2]; + ald_addr &= 0x7fffffc0; + + rc = read_guest_real(vcpu, ald_addr + 16, &ald.val, sizeof(union ald)); + if (rc) + return rc; + + if (alet.alen / 8 > ald.all) + return PGM_ALEN_TRANSLATION; + + if (0x7fffffff - ald.alo * 128 < alet.alen * 16) + return PGM_ADDRESSING; + + rc = read_guest_real(vcpu, ald.alo * 128 + alet.alen * 16, &ale, + sizeof(struct ale)); + if (rc) + return rc; + + if (ale.i == 1) + return PGM_ALEN_TRANSLATION; + if (ale.alesn != alet.alesn) + return PGM_ALE_SEQUENCE; + + rc = read_guest_real(vcpu, ale.asteo * 64, &aste, sizeof(struct aste)); + if (rc) + return rc; + + if (aste.i) + return PGM_ASTE_VALIDITY; + if (aste.astesn != ale.astesn) + return PGM_ASTE_SEQUENCE; + + if (ale.p == 1) { + eax = (vcpu->arch.sie_block->gcr[8] >> 16) & 0xffff; + if (ale.aleax != eax) { + if (eax / 16 > aste.atl) + return PGM_EXTENDED_AUTHORITY; + + authority_table_addr = aste.ato * 4 + eax / 4; + + rc = read_guest_real(vcpu, authority_table_addr, + &authority_table, + sizeof(u8)); + if (rc) + return rc; + + if ((authority_table & (0x40 >> ((eax & 3) * 2))) == 0) + return PGM_EXTENDED_AUTHORITY; + } + } + + if (ale.fo == 1 && write) + return PGM_PROTECTION; + + asce->val = aste.asce; + return 0; +} + +struct trans_exc_code_bits { + unsigned long addr : 52; /* Translation-exception Address */ + unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */ + unsigned long : 6; + unsigned long b60 : 1; + unsigned long b61 : 1; + unsigned long as : 2; /* ASCE Identifier */ +}; + +enum { + FSI_UNKNOWN = 0, /* Unknown wether fetch or store */ + FSI_STORE = 1, /* Exception was due to store operation */ + FSI_FETCH = 2 /* Exception was due to fetch operation */ +}; + +static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce, + ar_t ar, int write) { + int rc; + psw_t *psw = &vcpu->arch.sie_block->gpsw; + struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; + struct trans_exc_code_bits *tec_bits; + + memset(pgm, 0, sizeof(*pgm)); + tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; + tec_bits->fsi = write ? FSI_STORE : FSI_FETCH; + tec_bits->as = psw_bits(*psw).as; + + if (!psw_bits(*psw).t) { + asce->val = 0; + asce->r = 1; + return 0; + } + switch (psw_bits(vcpu->arch.sie_block->gpsw).as) { case PSW_AS_PRIMARY: - return vcpu->arch.sie_block->gcr[1]; + asce->val = vcpu->arch.sie_block->gcr[1]; + return 0; case PSW_AS_SECONDARY: - return vcpu->arch.sie_block->gcr[7]; + asce->val = vcpu->arch.sie_block->gcr[7]; + return 0; case PSW_AS_HOME: - return vcpu->arch.sie_block->gcr[13]; + asce->val = vcpu->arch.sie_block->gcr[13]; + return 0; + case PSW_AS_ACCREG: + rc = ar_translation(vcpu, asce, ar, write); + switch (rc) { + case PGM_ALEN_TRANSLATION: + case PGM_ALE_SEQUENCE: + case PGM_ASTE_VALIDITY: + case PGM_ASTE_SEQUENCE: + case PGM_EXTENDED_AUTHORITY: + vcpu->arch.pgm.exc_access_id = ar; + break; + case PGM_PROTECTION: + tec_bits->b60 = 1; + tec_bits->b61 = 1; + break; + } + if (rc > 0) + pgm->code = rc; + return rc; } return 0; } @@ -330,10 +521,11 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) * @vcpu: virtual cpu * @gva: guest virtual address * @gpa: points to where guest physical (absolute) address should be stored + * @asce: effective asce * @write: indicates if access is a write access * * Translate a guest virtual address into a guest absolute address by means - * of dynamic address translation as specified by the architecuture. + * of dynamic address translation as specified by the architecture. * If the resulting absolute address is not available in the configuration * an addressing exception is indicated and @gpa will not be changed. * @@ -345,7 +537,8 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) * by the architecture */ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, - unsigned long *gpa, int write) + unsigned long *gpa, const union asce asce, + int write) { union vaddress vaddr = {.addr = gva}; union raddress raddr = {.addr = gva}; @@ -354,12 +547,10 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, union ctlreg0 ctlreg0; unsigned long ptr; int edat1, edat2; - union asce asce; ctlreg0.val = vcpu->arch.sie_block->gcr[0]; edat1 = ctlreg0.edat && test_kvm_facility(vcpu->kvm, 8); edat2 = edat1 && test_kvm_facility(vcpu->kvm, 78); - asce.val = get_vcpu_asce(vcpu); if (asce.r) goto real_address; ptr = asce.origin * 4096; @@ -506,48 +697,30 @@ static inline int is_low_address(unsigned long ga) return (ga & ~0x11fful) == 0; } -static int low_address_protection_enabled(struct kvm_vcpu *vcpu) +static int low_address_protection_enabled(struct kvm_vcpu *vcpu, + const union asce asce) { union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]}; psw_t *psw = &vcpu->arch.sie_block->gpsw; - union asce asce; if (!ctlreg0.lap) return 0; - asce.val = get_vcpu_asce(vcpu); if (psw_bits(*psw).t && asce.p) return 0; return 1; } -struct trans_exc_code_bits { - unsigned long addr : 52; /* Translation-exception Address */ - unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */ - unsigned long : 7; - unsigned long b61 : 1; - unsigned long as : 2; /* ASCE Identifier */ -}; - -enum { - FSI_UNKNOWN = 0, /* Unknown wether fetch or store */ - FSI_STORE = 1, /* Exception was due to store operation */ - FSI_FETCH = 2 /* Exception was due to fetch operation */ -}; - static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, unsigned long *pages, unsigned long nr_pages, - int write) + const union asce asce, int write) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; psw_t *psw = &vcpu->arch.sie_block->gpsw; struct trans_exc_code_bits *tec_bits; int lap_enabled, rc; - memset(pgm, 0, sizeof(*pgm)); tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; - tec_bits->fsi = write ? FSI_STORE : FSI_FETCH; - tec_bits->as = psw_bits(*psw).as; - lap_enabled = low_address_protection_enabled(vcpu); + lap_enabled = low_address_protection_enabled(vcpu, asce); while (nr_pages) { ga = kvm_s390_logical_to_effective(vcpu, ga); tec_bits->addr = ga >> PAGE_SHIFT; @@ -557,7 +730,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, } ga &= PAGE_MASK; if (psw_bits(*psw).t) { - rc = guest_translate(vcpu, ga, pages, write); + rc = guest_translate(vcpu, ga, pages, asce, write); if (rc < 0) return rc; if (rc == PGM_PROTECTION) @@ -578,7 +751,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, return 0; } -int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len, int write) { psw_t *psw = &vcpu->arch.sie_block->gpsw; @@ -591,20 +764,19 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, if (!len) return 0; - /* Access register mode is not supported yet. */ - if (psw_bits(*psw).t && psw_bits(*psw).as == PSW_AS_ACCREG) - return -EOPNOTSUPP; + rc = get_vcpu_asce(vcpu, &asce, ar, write); + if (rc) + return rc; nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1; pages = pages_array; if (nr_pages > ARRAY_SIZE(pages_array)) pages = vmalloc(nr_pages * sizeof(unsigned long)); if (!pages) return -ENOMEM; - asce.val = get_vcpu_asce(vcpu); need_ipte_lock = psw_bits(*psw).t && !asce.r; if (need_ipte_lock) ipte_lock(vcpu); - rc = guest_page_range(vcpu, ga, pages, nr_pages, write); + rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, write); for (idx = 0; idx < nr_pages && !rc; idx++) { gpa = *(pages + idx) + (ga & ~PAGE_MASK); _len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len); @@ -652,7 +824,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * Note: The IPTE lock is not taken during this function, so the caller * has to take care of this. */ -int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, +int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, unsigned long *gpa, int write) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; @@ -661,26 +833,21 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, union asce asce; int rc; - /* Access register mode is not supported yet. */ - if (psw_bits(*psw).t && psw_bits(*psw).as == PSW_AS_ACCREG) - return -EOPNOTSUPP; - gva = kvm_s390_logical_to_effective(vcpu, gva); - memset(pgm, 0, sizeof(*pgm)); tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code; - tec->as = psw_bits(*psw).as; - tec->fsi = write ? FSI_STORE : FSI_FETCH; + rc = get_vcpu_asce(vcpu, &asce, ar, write); tec->addr = gva >> PAGE_SHIFT; - if (is_low_address(gva) && low_address_protection_enabled(vcpu)) { + if (rc) + return rc; + if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) { if (write) { rc = pgm->code = PGM_PROTECTION; return rc; } } - asce.val = get_vcpu_asce(vcpu); if (psw_bits(*psw).t && !asce.r) { /* Use DAT? */ - rc = guest_translate(vcpu, gva, gpa, write); + rc = guest_translate(vcpu, gva, gpa, asce, write); if (rc > 0) { if (rc == PGM_PROTECTION) tec->b61 = 1; @@ -697,28 +864,51 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, } /** - * kvm_s390_check_low_addr_protection - check for low-address protection - * @ga: Guest address + * check_gva_range - test a range of guest virtual addresses for accessibility + */ +int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, + unsigned long length, int is_write) +{ + unsigned long gpa; + unsigned long currlen; + int rc = 0; + + ipte_lock(vcpu); + while (length > 0 && !rc) { + currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE)); + rc = guest_translate_address(vcpu, gva, ar, &gpa, is_write); + gva += currlen; + length -= currlen; + } + ipte_unlock(vcpu); + + return rc; +} + +/** + * kvm_s390_check_low_addr_prot_real - check for low-address protection + * @gra: Guest real address * * Checks whether an address is subject to low-address protection and set * up vcpu->arch.pgm accordingly if necessary. * * Return: 0 if no protection exception, or PGM_PROTECTION if protected. */ -int kvm_s390_check_low_addr_protection(struct kvm_vcpu *vcpu, unsigned long ga) +int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; psw_t *psw = &vcpu->arch.sie_block->gpsw; struct trans_exc_code_bits *tec_bits; + union ctlreg0 ctlreg0 = {.val = vcpu->arch.sie_block->gcr[0]}; - if (!is_low_address(ga) || !low_address_protection_enabled(vcpu)) + if (!ctlreg0.lap || !is_low_address(gra)) return 0; memset(pgm, 0, sizeof(*pgm)); tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; tec_bits->fsi = FSI_STORE; tec_bits->as = psw_bits(*psw).as; - tec_bits->addr = ga >> PAGE_SHIFT; + tec_bits->addr = gra >> PAGE_SHIFT; pgm->code = PGM_PROTECTION; return pgm->code; diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 0149cf1..ef03726 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -156,9 +156,11 @@ int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data, } int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, - unsigned long *gpa, int write); + ar_t ar, unsigned long *gpa, int write); +int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, + unsigned long length, int is_write); -int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, +int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len, int write); int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, @@ -168,6 +170,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * write_guest - copy data from kernel space to guest space * @vcpu: virtual cpu * @ga: guest address + * @ar: access register * @data: source address in kernel space * @len: number of bytes to copy * @@ -176,8 +179,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * If DAT is off data will be copied to guest real or absolute memory. * If DAT is on data will be copied to the address space as specified by * the address space bits of the PSW: - * Primary, secondory or home space (access register mode is currently not - * implemented). + * Primary, secondary, home space or access register mode. * The addressing mode of the PSW is also inspected, so that address wrap * around is taken into account for 24-, 31- and 64-bit addressing mode, * if the to be copied data crosses page boundaries in guest address space. @@ -210,16 +212,17 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * if data has been changed in guest space in case of an exception. */ static inline __must_check -int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, +int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len) { - return access_guest(vcpu, ga, data, len, 1); + return access_guest(vcpu, ga, ar, data, len, 1); } /** * read_guest - copy data from guest space to kernel space * @vcpu: virtual cpu * @ga: guest address + * @ar: access register * @data: destination address in kernel space * @len: number of bytes to copy * @@ -229,10 +232,10 @@ int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, * data will be copied from guest space to kernel space. */ static inline __must_check -int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, void *data, +int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len) { - return access_guest(vcpu, ga, data, len, 0); + return access_guest(vcpu, ga, ar, data, len, 0); } /** @@ -330,6 +333,6 @@ int read_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, void ipte_lock(struct kvm_vcpu *vcpu); void ipte_unlock(struct kvm_vcpu *vcpu); int ipte_lock_held(struct kvm_vcpu *vcpu); -int kvm_s390_check_low_addr_protection(struct kvm_vcpu *vcpu, unsigned long ga); +int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra); #endif /* __KVM_S390_GACCESS_H */ diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index 3e8d409..e97b345 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -191,8 +191,8 @@ static int __import_wp_info(struct kvm_vcpu *vcpu, if (!wp_info->old_data) return -ENOMEM; /* try to backup the original value */ - ret = read_guest(vcpu, wp_info->phys_addr, wp_info->old_data, - wp_info->len); + ret = read_guest_abs(vcpu, wp_info->phys_addr, wp_info->old_data, + wp_info->len); if (ret) { kfree(wp_info->old_data); wp_info->old_data = NULL; @@ -362,8 +362,8 @@ static struct kvm_hw_wp_info_arch *any_wp_changed(struct kvm_vcpu *vcpu) continue; /* refetch the wp data and compare it to the old value */ - if (!read_guest(vcpu, wp_info->phys_addr, temp, - wp_info->len)) { + if (!read_guest_abs(vcpu, wp_info->phys_addr, temp, + wp_info->len)) { if (memcmp(temp, wp_info->old_data, wp_info->len)) { kfree(temp); return wp_info; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index bebd215..9e3779e 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -165,6 +165,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu, pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn; pgm_info->mon_code = vcpu->arch.sie_block->tecmc; break; + case PGM_VECTOR_PROCESSING: case PGM_DATA: pgm_info->data_exc_code = vcpu->arch.sie_block->dxc; break; @@ -319,7 +320,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) /* Make sure that the source is paged-in */ rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2], - &srcaddr, 0); + reg2, &srcaddr, 0); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0); @@ -328,7 +329,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) /* Make sure that the destination is paged-in */ rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1], - &dstaddr, 1); + reg1, &dstaddr, 1); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 073b5f3..9de4726 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1,7 +1,7 @@ /* * handling kvm guest interrupts * - * Copyright IBM Corp. 2008,2014 + * Copyright IBM Corp. 2008, 2015 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -17,9 +17,12 @@ #include <linux/signal.h> #include <linux/slab.h> #include <linux/bitmap.h> +#include <linux/vmalloc.h> #include <asm/asm-offsets.h> +#include <asm/dis.h> #include <asm/uaccess.h> #include <asm/sclp.h> +#include <asm/isc.h> #include "kvm-s390.h" #include "gaccess.h" #include "trace-s390.h" @@ -32,11 +35,6 @@ #define PFAULT_DONE 0x0680 #define VIRTIO_PARAM 0x0d00 -static int is_ioint(u64 type) -{ - return ((type & 0xfffe0000u) != 0xfffe0000u); -} - int psw_extint_disabled(struct kvm_vcpu *vcpu) { return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT); @@ -72,70 +70,45 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu) return 1; } -static u64 int_word_to_isc_bits(u32 int_word) +static int ckc_irq_pending(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.sie_block->ckc < + get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) + return 0; + return ckc_interrupts_enabled(vcpu); +} + +static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu) +{ + return !psw_extint_disabled(vcpu) && + (vcpu->arch.sie_block->gcr[0] & 0x400ul); +} + +static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.sie_block->cputm >> 63) && + cpu_timer_interrupts_enabled(vcpu); +} + +static inline int is_ioirq(unsigned long irq_type) { - u8 isc = (int_word & 0x38000000) >> 27; + return ((irq_type >= IRQ_PEND_IO_ISC_0) && + (irq_type <= IRQ_PEND_IO_ISC_7)); +} +static uint64_t isc_to_isc_bits(int isc) +{ return (0x80 >> isc) << 24; } -static int __must_check __interrupt_is_deliverable(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static inline u8 int_word_to_isc(u32 int_word) { - switch (inti->type) { - case KVM_S390_INT_EXTERNAL_CALL: - if (psw_extint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[0] & 0x2000ul) - return 1; - return 0; - case KVM_S390_INT_EMERGENCY: - if (psw_extint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[0] & 0x4000ul) - return 1; - return 0; - case KVM_S390_INT_CLOCK_COMP: - return ckc_interrupts_enabled(vcpu); - case KVM_S390_INT_CPU_TIMER: - if (psw_extint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[0] & 0x400ul) - return 1; - return 0; - case KVM_S390_INT_SERVICE: - case KVM_S390_INT_PFAULT_INIT: - case KVM_S390_INT_PFAULT_DONE: - case KVM_S390_INT_VIRTIO: - if (psw_extint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[0] & 0x200ul) - return 1; - return 0; - case KVM_S390_PROGRAM_INT: - case KVM_S390_SIGP_STOP: - case KVM_S390_SIGP_SET_PREFIX: - case KVM_S390_RESTART: - return 1; - case KVM_S390_MCHK: - if (psw_mchk_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[14] & inti->mchk.cr14) - return 1; - return 0; - case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - if (psw_ioint_disabled(vcpu)) - return 0; - if (vcpu->arch.sie_block->gcr[6] & - int_word_to_isc_bits(inti->io.io_int_word)) - return 1; - return 0; - default: - printk(KERN_WARNING "illegal interrupt type %llx\n", - inti->type); - BUG(); - } - return 0; + return (int_word & 0x38000000) >> 27; +} + +static inline unsigned long pending_floating_irqs(struct kvm_vcpu *vcpu) +{ + return vcpu->kvm->arch.float_int.pending_irqs; } static inline unsigned long pending_local_irqs(struct kvm_vcpu *vcpu) @@ -143,12 +116,31 @@ static inline unsigned long pending_local_irqs(struct kvm_vcpu *vcpu) return vcpu->arch.local_int.pending_irqs; } -static unsigned long deliverable_local_irqs(struct kvm_vcpu *vcpu) +static unsigned long disable_iscs(struct kvm_vcpu *vcpu, + unsigned long active_mask) +{ + int i; + + for (i = 0; i <= MAX_ISC; i++) + if (!(vcpu->arch.sie_block->gcr[6] & isc_to_isc_bits(i))) + active_mask &= ~(1UL << (IRQ_PEND_IO_ISC_0 + i)); + + return active_mask; +} + +static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) { - unsigned long active_mask = pending_local_irqs(vcpu); + unsigned long active_mask; + + active_mask = pending_local_irqs(vcpu); + active_mask |= pending_floating_irqs(vcpu); if (psw_extint_disabled(vcpu)) active_mask &= ~IRQ_PEND_EXT_MASK; + if (psw_ioint_disabled(vcpu)) + active_mask &= ~IRQ_PEND_IO_MASK; + else + active_mask = disable_iscs(vcpu, active_mask); if (!(vcpu->arch.sie_block->gcr[0] & 0x2000ul)) __clear_bit(IRQ_PEND_EXT_EXTERNAL, &active_mask); if (!(vcpu->arch.sie_block->gcr[0] & 0x4000ul)) @@ -157,8 +149,13 @@ static unsigned long deliverable_local_irqs(struct kvm_vcpu *vcpu) __clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask); if (!(vcpu->arch.sie_block->gcr[0] & 0x400ul)) __clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask); + if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul)) + __clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask); if (psw_mchk_disabled(vcpu)) active_mask &= ~IRQ_PEND_MCHK_MASK; + if (!(vcpu->arch.sie_block->gcr[14] & + vcpu->kvm->arch.float_int.mchk.cr14)) + __clear_bit(IRQ_PEND_MCHK_REP, &active_mask); /* * STOP irqs will never be actively delivered. They are triggered via @@ -200,6 +197,16 @@ static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag) atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags); } +static void set_intercept_indicators_io(struct kvm_vcpu *vcpu) +{ + if (!(pending_floating_irqs(vcpu) & IRQ_PEND_IO_MASK)) + return; + else if (psw_ioint_disabled(vcpu)) + __set_cpuflag(vcpu, CPUSTAT_IO_INT); + else + vcpu->arch.sie_block->lctl |= LCTL_CR6; +} + static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu) { if (!(pending_local_irqs(vcpu) & IRQ_PEND_EXT_MASK)) @@ -226,47 +233,17 @@ static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu) __set_cpuflag(vcpu, CPUSTAT_STOP_INT); } -/* Set interception request for non-deliverable local interrupts */ -static void set_intercept_indicators_local(struct kvm_vcpu *vcpu) +/* Set interception request for non-deliverable interrupts */ +static void set_intercept_indicators(struct kvm_vcpu *vcpu) { + set_intercept_indicators_io(vcpu); set_intercept_indicators_ext(vcpu); set_intercept_indicators_mchk(vcpu); set_intercept_indicators_stop(vcpu); } -static void __set_intercept_indicator(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) -{ - switch (inti->type) { - case KVM_S390_INT_SERVICE: - case KVM_S390_INT_PFAULT_DONE: - case KVM_S390_INT_VIRTIO: - if (psw_extint_disabled(vcpu)) - __set_cpuflag(vcpu, CPUSTAT_EXT_INT); - else - vcpu->arch.sie_block->lctl |= LCTL_CR0; - break; - case KVM_S390_MCHK: - if (psw_mchk_disabled(vcpu)) - vcpu->arch.sie_block->ictl |= ICTL_LPSW; - else - vcpu->arch.sie_block->lctl |= LCTL_CR14; - break; - case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - if (psw_ioint_disabled(vcpu)) - __set_cpuflag(vcpu, CPUSTAT_IO_INT); - else - vcpu->arch.sie_block->lctl |= LCTL_CR6; - break; - default: - BUG(); - } -} - static u16 get_ilc(struct kvm_vcpu *vcpu) { - const unsigned short table[] = { 2, 4, 4, 6 }; - switch (vcpu->arch.sie_block->icptcode) { case ICPT_INST: case ICPT_INSTPROGI: @@ -274,7 +251,7 @@ static u16 get_ilc(struct kvm_vcpu *vcpu) case ICPT_PARTEXEC: case ICPT_IOINST: /* last instruction only stored for these icptcodes */ - return table[vcpu->arch.sie_block->ipa >> 14]; + return insn_length(vcpu->arch.sie_block->ipa >> 8); case ICPT_PROGI: return vcpu->arch.sie_block->pgmilc; default: @@ -350,38 +327,72 @@ static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu) static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu) { + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - struct kvm_s390_mchk_info mchk; - int rc; + struct kvm_s390_mchk_info mchk = {}; + unsigned long adtl_status_addr; + int deliver = 0; + int rc = 0; + spin_lock(&fi->lock); spin_lock(&li->lock); - mchk = li->irq.mchk; + if (test_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs) || + test_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs)) { + /* + * If there was an exigent machine check pending, then any + * repressible machine checks that might have been pending + * are indicated along with it, so always clear bits for + * repressible and exigent interrupts + */ + mchk = li->irq.mchk; + clear_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs); + clear_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs); + memset(&li->irq.mchk, 0, sizeof(mchk)); + deliver = 1; + } /* - * If there was an exigent machine check pending, then any repressible - * machine checks that might have been pending are indicated along - * with it, so always clear both bits + * We indicate floating repressible conditions along with + * other pending conditions. Channel Report Pending and Channel + * Subsystem damage are the only two and and are indicated by + * bits in mcic and masked in cr14. */ - clear_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs); - clear_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs); - memset(&li->irq.mchk, 0, sizeof(mchk)); + if (test_and_clear_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) { + mchk.mcic |= fi->mchk.mcic; + mchk.cr14 |= fi->mchk.cr14; + memset(&fi->mchk, 0, sizeof(mchk)); + deliver = 1; + } spin_unlock(&li->lock); + spin_unlock(&fi->lock); - VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", - mchk.mcic); - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK, - mchk.cr14, mchk.mcic); - - rc = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED); - rc |= put_guest_lc(vcpu, mchk.mcic, - (u64 __user *) __LC_MCCK_CODE); - rc |= put_guest_lc(vcpu, mchk.failing_storage_address, - (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); - rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, - &mchk.fixed_logout, sizeof(mchk.fixed_logout)); - rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (deliver) { + VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", + mchk.mcic); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_MCHK, + mchk.cr14, mchk.mcic); + + rc = kvm_s390_vcpu_store_status(vcpu, + KVM_S390_STORE_STATUS_PREFIXED); + rc |= read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR, + &adtl_status_addr, + sizeof(unsigned long)); + rc |= kvm_s390_vcpu_store_adtl_status(vcpu, + adtl_status_addr); + rc |= put_guest_lc(vcpu, mchk.mcic, + (u64 __user *) __LC_MCCK_CODE); + rc |= put_guest_lc(vcpu, mchk.failing_storage_address, + (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); + rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, + &mchk.fixed_logout, + sizeof(mchk.fixed_logout)); + rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + } return rc ? -EFAULT : 0; } @@ -484,7 +495,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_pgm_info pgm_info; - int rc = 0; + int rc = 0, nullifying = false; u16 ilc = get_ilc(vcpu); spin_lock(&li->lock); @@ -509,6 +520,8 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) case PGM_LX_TRANSLATION: case PGM_PRIMARY_AUTHORITY: case PGM_SECONDARY_AUTHORITY: + nullifying = true; + /* fall through */ case PGM_SPACE_SWITCH: rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, (u64 *)__LC_TRANS_EXC_CODE); @@ -521,6 +534,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) case PGM_EXTENDED_AUTHORITY: rc = put_guest_lc(vcpu, pgm_info.exc_access_id, (u8 *)__LC_EXC_ACCESS_ID); + nullifying = true; break; case PGM_ASCE_TYPE: case PGM_PAGE_TRANSLATION: @@ -534,6 +548,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) (u8 *)__LC_EXC_ACCESS_ID); rc |= put_guest_lc(vcpu, pgm_info.op_access_id, (u8 *)__LC_OP_ACCESS_ID); + nullifying = true; break; case PGM_MONITOR: rc = put_guest_lc(vcpu, pgm_info.mon_class_nr, @@ -541,6 +556,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) rc |= put_guest_lc(vcpu, pgm_info.mon_code, (u64 *)__LC_MON_CODE); break; + case PGM_VECTOR_PROCESSING: case PGM_DATA: rc = put_guest_lc(vcpu, pgm_info.data_exc_code, (u32 *)__LC_DATA_EXC_CODE); @@ -551,6 +567,15 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) rc |= put_guest_lc(vcpu, pgm_info.exc_access_id, (u8 *)__LC_EXC_ACCESS_ID); break; + case PGM_STACK_FULL: + case PGM_STACK_EMPTY: + case PGM_STACK_SPECIFICATION: + case PGM_STACK_TYPE: + case PGM_STACK_OPERATION: + case PGM_TRACE_TABEL: + case PGM_CRYPTO_OPERATION: + nullifying = true; + break; } if (pgm_info.code & PGM_PER) { @@ -564,7 +589,12 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) (u8 *) __LC_PER_ACCESS_ID); } + if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST) + kvm_s390_rewind_psw(vcpu, ilc); + rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC); + rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea, + (u64 *) __LC_LAST_BREAK); rc |= put_guest_lc(vcpu, pgm_info.code, (u16 *)__LC_PGM_INT_CODE); rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW, @@ -574,16 +604,27 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } -static int __must_check __deliver_service(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static int __must_check __deliver_service(struct kvm_vcpu *vcpu) { - int rc; + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_ext_info ext; + int rc = 0; + + spin_lock(&fi->lock); + if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) { + spin_unlock(&fi->lock); + return 0; + } + ext = fi->srv_signal; + memset(&fi->srv_signal, 0, sizeof(ext)); + clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); + spin_unlock(&fi->lock); VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x", - inti->ext.ext_params); + ext.ext_params); vcpu->stat.deliver_service_signal++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->ext.ext_params, 0); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE, + ext.ext_params, 0); rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE); rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); @@ -591,106 +632,146 @@ static int __must_check __deliver_service(struct kvm_vcpu *vcpu, &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, inti->ext.ext_params, + rc |= put_guest_lc(vcpu, ext.ext_params, (u32 *)__LC_EXT_PARAMS); + return rc ? -EFAULT : 0; } -static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu) { - int rc; + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_interrupt_info *inti; + int rc = 0; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, - KVM_S390_INT_PFAULT_DONE, 0, - inti->ext.ext_params2); + spin_lock(&fi->lock); + inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_PFAULT], + struct kvm_s390_interrupt_info, + list); + if (inti) { + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_INT_PFAULT_DONE, 0, + inti->ext.ext_params2); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_PFAULT] -= 1; + } + if (list_empty(&fi->lists[FIRQ_LIST_PFAULT])) + clear_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs); + spin_unlock(&fi->lock); - rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, PFAULT_DONE, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, inti->ext.ext_params2, - (u64 *)__LC_EXT_PARAMS2); + if (inti) { + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, PFAULT_DONE, + (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params2, + (u64 *)__LC_EXT_PARAMS2); + kfree(inti); + } return rc ? -EFAULT : 0; } -static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu) { - int rc; + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_interrupt_info *inti; + int rc = 0; - VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx", - inti->ext.ext_params, inti->ext.ext_params2); - vcpu->stat.deliver_virtio_interrupt++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->ext.ext_params, - inti->ext.ext_params2); + spin_lock(&fi->lock); + inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_VIRTIO], + struct kvm_s390_interrupt_info, + list); + if (inti) { + VCPU_EVENT(vcpu, 4, + "interrupt: virtio parm:%x,parm64:%llx", + inti->ext.ext_params, inti->ext.ext_params2); + vcpu->stat.deliver_virtio_interrupt++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + inti->type, + inti->ext.ext_params, + inti->ext.ext_params2); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_VIRTIO] -= 1; + } + if (list_empty(&fi->lists[FIRQ_LIST_VIRTIO])) + clear_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs); + spin_unlock(&fi->lock); - rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, VIRTIO_PARAM, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, inti->ext.ext_params, - (u32 *)__LC_EXT_PARAMS); - rc |= put_guest_lc(vcpu, inti->ext.ext_params2, - (u64 *)__LC_EXT_PARAMS2); + if (inti) { + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, VIRTIO_PARAM, + (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params, + (u32 *)__LC_EXT_PARAMS); + rc |= put_guest_lc(vcpu, inti->ext.ext_params2, + (u64 *)__LC_EXT_PARAMS2); + kfree(inti); + } return rc ? -EFAULT : 0; } static int __must_check __deliver_io(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) + unsigned long irq_type) { - int rc; + struct list_head *isc_list; + struct kvm_s390_float_interrupt *fi; + struct kvm_s390_interrupt_info *inti = NULL; + int rc = 0; - VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type); - vcpu->stat.deliver_io_int++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - ((__u32)inti->io.subchannel_id << 16) | - inti->io.subchannel_nr, - ((__u64)inti->io.io_int_parm << 32) | - inti->io.io_int_word); - - rc = put_guest_lc(vcpu, inti->io.subchannel_id, - (u16 *)__LC_SUBCHANNEL_ID); - rc |= put_guest_lc(vcpu, inti->io.subchannel_nr, - (u16 *)__LC_SUBCHANNEL_NR); - rc |= put_guest_lc(vcpu, inti->io.io_int_parm, - (u32 *)__LC_IO_INT_PARM); - rc |= put_guest_lc(vcpu, inti->io.io_int_word, - (u32 *)__LC_IO_INT_WORD); - rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - return rc ? -EFAULT : 0; -} + fi = &vcpu->kvm->arch.float_int; -static int __must_check __deliver_mchk_floating(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) -{ - struct kvm_s390_mchk_info *mchk = &inti->mchk; - int rc; + spin_lock(&fi->lock); + isc_list = &fi->lists[irq_type - IRQ_PEND_IO_ISC_0]; + inti = list_first_entry_or_null(isc_list, + struct kvm_s390_interrupt_info, + list); + if (inti) { + VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type); + vcpu->stat.deliver_io_int++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + inti->type, + ((__u32)inti->io.subchannel_id << 16) | + inti->io.subchannel_nr, + ((__u64)inti->io.io_int_parm << 32) | + inti->io.io_int_word); + list_del(&inti->list); + fi->counters[FIRQ_CNTR_IO] -= 1; + } + if (list_empty(isc_list)) + clear_bit(irq_type, &fi->pending_irqs); + spin_unlock(&fi->lock); + + if (inti) { + rc = put_guest_lc(vcpu, inti->io.subchannel_id, + (u16 *)__LC_SUBCHANNEL_ID); + rc |= put_guest_lc(vcpu, inti->io.subchannel_nr, + (u16 *)__LC_SUBCHANNEL_NR); + rc |= put_guest_lc(vcpu, inti->io.io_int_parm, + (u32 *)__LC_IO_INT_PARM); + rc |= put_guest_lc(vcpu, inti->io.io_int_word, + (u32 *)__LC_IO_INT_WORD); + rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + kfree(inti); + } - VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", - mchk->mcic); - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK, - mchk->cr14, mchk->mcic); - - rc = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED); - rc |= put_guest_lc(vcpu, mchk->mcic, - (u64 __user *) __LC_MCCK_CODE); - rc |= put_guest_lc(vcpu, mchk->failing_storage_address, - (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); - rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, - &mchk->fixed_logout, sizeof(mchk->fixed_logout)); - rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); return rc ? -EFAULT : 0; } @@ -698,6 +779,7 @@ typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu); static const deliver_irq_t deliver_irq_funcs[] = { [IRQ_PEND_MCHK_EX] = __deliver_machine_check, + [IRQ_PEND_MCHK_REP] = __deliver_machine_check, [IRQ_PEND_PROG] = __deliver_prog, [IRQ_PEND_EXT_EMERGENCY] = __deliver_emergency_signal, [IRQ_PEND_EXT_EXTERNAL] = __deliver_external_call, @@ -706,36 +788,11 @@ static const deliver_irq_t deliver_irq_funcs[] = { [IRQ_PEND_RESTART] = __deliver_restart, [IRQ_PEND_SET_PREFIX] = __deliver_set_prefix, [IRQ_PEND_PFAULT_INIT] = __deliver_pfault_init, + [IRQ_PEND_EXT_SERVICE] = __deliver_service, + [IRQ_PEND_PFAULT_DONE] = __deliver_pfault_done, + [IRQ_PEND_VIRTIO] = __deliver_virtio, }; -static int __must_check __deliver_floating_interrupt(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) -{ - int rc; - - switch (inti->type) { - case KVM_S390_INT_SERVICE: - rc = __deliver_service(vcpu, inti); - break; - case KVM_S390_INT_PFAULT_DONE: - rc = __deliver_pfault_done(vcpu, inti); - break; - case KVM_S390_INT_VIRTIO: - rc = __deliver_virtio(vcpu, inti); - break; - case KVM_S390_MCHK: - rc = __deliver_mchk_floating(vcpu, inti); - break; - case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - rc = __deliver_io(vcpu, inti); - break; - default: - BUG(); - } - - return rc; -} - /* Check whether an external call is pending (deliverable or not) */ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu) { @@ -751,21 +808,9 @@ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu) int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop) { - struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int; - struct kvm_s390_interrupt_info *inti; int rc; - rc = !!deliverable_local_irqs(vcpu); - - if ((!rc) && atomic_read(&fi->active)) { - spin_lock(&fi->lock); - list_for_each_entry(inti, &fi->list, list) - if (__interrupt_is_deliverable(vcpu, inti)) { - rc = 1; - break; - } - spin_unlock(&fi->lock); - } + rc = !!deliverable_irqs(vcpu); if (!rc && kvm_cpu_has_pending_timer(vcpu)) rc = 1; @@ -784,12 +829,7 @@ int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop) int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - if (!(vcpu->arch.sie_block->ckc < - get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) - return 0; - if (!ckc_interrupts_enabled(vcpu)) - return 0; - return 1; + return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu); } int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) @@ -884,60 +924,45 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu) int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int; - struct kvm_s390_interrupt_info *n, *inti = NULL; deliver_irq_t func; - int deliver; int rc = 0; unsigned long irq_type; - unsigned long deliverable_irqs; + unsigned long irqs; __reset_intercept_indicators(vcpu); /* pending ckc conditions might have been invalidated */ clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); - if (kvm_cpu_has_pending_timer(vcpu)) + if (ckc_irq_pending(vcpu)) set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); + /* pending cpu timer conditions might have been invalidated */ + clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + if (cpu_timer_irq_pending(vcpu)) + set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + do { - deliverable_irqs = deliverable_local_irqs(vcpu); + irqs = deliverable_irqs(vcpu); /* bits are in the order of interrupt priority */ - irq_type = find_first_bit(&deliverable_irqs, IRQ_PEND_COUNT); + irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT); if (irq_type == IRQ_PEND_COUNT) break; - func = deliver_irq_funcs[irq_type]; - if (!func) { - WARN_ON_ONCE(func == NULL); - clear_bit(irq_type, &li->pending_irqs); - continue; + if (is_ioirq(irq_type)) { + rc = __deliver_io(vcpu, irq_type); + } else { + func = deliver_irq_funcs[irq_type]; + if (!func) { + WARN_ON_ONCE(func == NULL); + clear_bit(irq_type, &li->pending_irqs); + continue; + } + rc = func(vcpu); } - rc = func(vcpu); - } while (!rc && irq_type != IRQ_PEND_COUNT); + if (rc) + break; + } while (!rc); - set_intercept_indicators_local(vcpu); - - if (!rc && atomic_read(&fi->active)) { - do { - deliver = 0; - spin_lock(&fi->lock); - list_for_each_entry_safe(inti, n, &fi->list, list) { - if (__interrupt_is_deliverable(vcpu, inti)) { - list_del(&inti->list); - fi->irq_count--; - deliver = 1; - break; - } - __set_intercept_indicator(vcpu, inti); - } - if (list_empty(&fi->list)) - atomic_set(&fi->active, 0); - spin_unlock(&fi->lock); - if (deliver) { - rc = __deliver_floating_interrupt(vcpu, inti); - kfree(inti); - } - } while (!rc && deliver); - } + set_intercept_indicators(vcpu); return rc; } @@ -1172,80 +1197,182 @@ static int __inject_cpu_timer(struct kvm_vcpu *vcpu) return 0; } +static struct kvm_s390_interrupt_info *get_io_int(struct kvm *kvm, + int isc, u32 schid) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + struct list_head *isc_list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc]; + struct kvm_s390_interrupt_info *iter; + u16 id = (schid & 0xffff0000U) >> 16; + u16 nr = schid & 0x0000ffffU; + spin_lock(&fi->lock); + list_for_each_entry(iter, isc_list, list) { + if (schid && (id != iter->io.subchannel_id || + nr != iter->io.subchannel_nr)) + continue; + /* found an appropriate entry */ + list_del_init(&iter->list); + fi->counters[FIRQ_CNTR_IO] -= 1; + if (list_empty(isc_list)) + clear_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs); + spin_unlock(&fi->lock); + return iter; + } + spin_unlock(&fi->lock); + return NULL; +} + +/* + * Dequeue and return an I/O interrupt matching any of the interruption + * subclasses as designated by the isc mask in cr6 and the schid (if != 0). + */ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, - u64 cr6, u64 schid) + u64 isc_mask, u32 schid) +{ + struct kvm_s390_interrupt_info *inti = NULL; + int isc; + + for (isc = 0; isc <= MAX_ISC && !inti; isc++) { + if (isc_mask & isc_to_isc_bits(isc)) + inti = get_io_int(kvm, isc, schid); + } + return inti; +} + +#define SCCB_MASK 0xFFFFFFF8 +#define SCCB_EVENT_PENDING 0x3 + +static int __inject_service(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_EVENT_PENDING; + /* + * Early versions of the QEMU s390 bios will inject several + * service interrupts after another without handling a + * condition code indicating busy. + * We will silently ignore those superfluous sccb values. + * A future version of QEMU will take care of serialization + * of servc requests + */ + if (fi->srv_signal.ext_params & SCCB_MASK) + goto out; + fi->srv_signal.ext_params |= inti->ext.ext_params & SCCB_MASK; + set_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs); +out: + spin_unlock(&fi->lock); + kfree(inti); + return 0; +} + +static int __inject_virtio(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + if (fi->counters[FIRQ_CNTR_VIRTIO] >= KVM_S390_MAX_VIRTIO_IRQS) { + spin_unlock(&fi->lock); + return -EBUSY; + } + fi->counters[FIRQ_CNTR_VIRTIO] += 1; + list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_VIRTIO]); + set_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs); + spin_unlock(&fi->lock); + return 0; +} + +static int __inject_pfault_done(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + if (fi->counters[FIRQ_CNTR_PFAULT] >= + (ASYNC_PF_PER_VCPU * KVM_MAX_VCPUS)) { + spin_unlock(&fi->lock); + return -EBUSY; + } + fi->counters[FIRQ_CNTR_PFAULT] += 1; + list_add_tail(&inti->list, &fi->lists[FIRQ_LIST_PFAULT]); + set_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs); + spin_unlock(&fi->lock); + return 0; +} + +#define CR_PENDING_SUBCLASS 28 +static int __inject_float_mchk(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + + spin_lock(&fi->lock); + fi->mchk.cr14 |= inti->mchk.cr14 & (1UL << CR_PENDING_SUBCLASS); + fi->mchk.mcic |= inti->mchk.mcic; + set_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs); + spin_unlock(&fi->lock); + kfree(inti); + return 0; +} + +static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { struct kvm_s390_float_interrupt *fi; - struct kvm_s390_interrupt_info *inti, *iter; + struct list_head *list; + int isc; - if ((!schid && !cr6) || (schid && cr6)) - return NULL; fi = &kvm->arch.float_int; spin_lock(&fi->lock); - inti = NULL; - list_for_each_entry(iter, &fi->list, list) { - if (!is_ioint(iter->type)) - continue; - if (cr6 && - ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0)) - continue; - if (schid) { - if (((schid & 0x00000000ffff0000) >> 16) != - iter->io.subchannel_id) - continue; - if ((schid & 0x000000000000ffff) != - iter->io.subchannel_nr) - continue; - } - inti = iter; - break; - } - if (inti) { - list_del_init(&inti->list); - fi->irq_count--; + if (fi->counters[FIRQ_CNTR_IO] >= KVM_S390_MAX_FLOAT_IRQS) { + spin_unlock(&fi->lock); + return -EBUSY; } - if (list_empty(&fi->list)) - atomic_set(&fi->active, 0); + fi->counters[FIRQ_CNTR_IO] += 1; + + isc = int_word_to_isc(inti->io.io_int_word); + list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc]; + list_add_tail(&inti->list, list); + set_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs); spin_unlock(&fi->lock); - return inti; + return 0; } static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { struct kvm_s390_local_interrupt *li; struct kvm_s390_float_interrupt *fi; - struct kvm_s390_interrupt_info *iter; struct kvm_vcpu *dst_vcpu = NULL; int sigcpu; - int rc = 0; + u64 type = READ_ONCE(inti->type); + int rc; fi = &kvm->arch.float_int; - spin_lock(&fi->lock); - if (fi->irq_count >= KVM_S390_MAX_FLOAT_IRQS) { + + switch (type) { + case KVM_S390_MCHK: + rc = __inject_float_mchk(kvm, inti); + break; + case KVM_S390_INT_VIRTIO: + rc = __inject_virtio(kvm, inti); + break; + case KVM_S390_INT_SERVICE: + rc = __inject_service(kvm, inti); + break; + case KVM_S390_INT_PFAULT_DONE: + rc = __inject_pfault_done(kvm, inti); + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + rc = __inject_io(kvm, inti); + break; + default: rc = -EINVAL; - goto unlock_fi; } - fi->irq_count++; - if (!is_ioint(inti->type)) { - list_add_tail(&inti->list, &fi->list); - } else { - u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word); + if (rc) + return rc; - /* Keep I/O interrupts sorted in isc order. */ - list_for_each_entry(iter, &fi->list, list) { - if (!is_ioint(iter->type)) - continue; - if (int_word_to_isc_bits(iter->io.io_int_word) - <= isc_bits) - continue; - break; - } - list_add_tail(&inti->list, &iter->list); - } - atomic_set(&fi->active, 1); - if (atomic_read(&kvm->online_vcpus) == 0) - goto unlock_fi; sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS); if (sigcpu == KVM_MAX_VCPUS) { do { @@ -1257,7 +1384,7 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) dst_vcpu = kvm_get_vcpu(kvm, sigcpu); li = &dst_vcpu->arch.local_int; spin_lock(&li->lock); - switch (inti->type) { + switch (type) { case KVM_S390_MCHK: atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); break; @@ -1270,9 +1397,8 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) } spin_unlock(&li->lock); kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu)); -unlock_fi: - spin_unlock(&fi->lock); - return rc; + return 0; + } int kvm_s390_inject_vm(struct kvm *kvm, @@ -1332,10 +1458,10 @@ int kvm_s390_inject_vm(struct kvm *kvm, return rc; } -void kvm_s390_reinject_io_int(struct kvm *kvm, +int kvm_s390_reinject_io_int(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) { - __inject_vm(kvm, inti); + return __inject_vm(kvm, inti); } int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, @@ -1388,12 +1514,10 @@ void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu) spin_unlock(&li->lock); } -int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +static int do_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) { - struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; int rc; - spin_lock(&li->lock); switch (irq->type) { case KVM_S390_PROGRAM_INT: VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)", @@ -1433,83 +1557,130 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) default: rc = -EINVAL; } + + return rc; +} + +int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + + spin_lock(&li->lock); + rc = do_inject_vcpu(vcpu, irq); spin_unlock(&li->lock); if (!rc) kvm_s390_vcpu_wakeup(vcpu); return rc; } -void kvm_s390_clear_float_irqs(struct kvm *kvm) +static inline void clear_irq_list(struct list_head *_list) { - struct kvm_s390_float_interrupt *fi; - struct kvm_s390_interrupt_info *n, *inti = NULL; + struct kvm_s390_interrupt_info *inti, *n; - fi = &kvm->arch.float_int; - spin_lock(&fi->lock); - list_for_each_entry_safe(inti, n, &fi->list, list) { + list_for_each_entry_safe(inti, n, _list, list) { list_del(&inti->list); kfree(inti); } - fi->irq_count = 0; - atomic_set(&fi->active, 0); - spin_unlock(&fi->lock); } -static inline int copy_irq_to_user(struct kvm_s390_interrupt_info *inti, - u8 *addr) +static void inti_to_irq(struct kvm_s390_interrupt_info *inti, + struct kvm_s390_irq *irq) { - struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr; - struct kvm_s390_irq irq = {0}; - - irq.type = inti->type; + irq->type = inti->type; switch (inti->type) { case KVM_S390_INT_PFAULT_INIT: case KVM_S390_INT_PFAULT_DONE: case KVM_S390_INT_VIRTIO: - case KVM_S390_INT_SERVICE: - irq.u.ext = inti->ext; + irq->u.ext = inti->ext; break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - irq.u.io = inti->io; + irq->u.io = inti->io; break; - case KVM_S390_MCHK: - irq.u.mchk = inti->mchk; - break; - default: - return -EINVAL; } +} - if (copy_to_user(uptr, &irq, sizeof(irq))) - return -EFAULT; +void kvm_s390_clear_float_irqs(struct kvm *kvm) +{ + struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; + int i; - return 0; -} + spin_lock(&fi->lock); + for (i = 0; i < FIRQ_LIST_COUNT; i++) + clear_irq_list(&fi->lists[i]); + for (i = 0; i < FIRQ_MAX_COUNT; i++) + fi->counters[i] = 0; + spin_unlock(&fi->lock); +}; -static int get_all_floating_irqs(struct kvm *kvm, __u8 *buf, __u64 len) +static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) { struct kvm_s390_interrupt_info *inti; struct kvm_s390_float_interrupt *fi; + struct kvm_s390_irq *buf; + struct kvm_s390_irq *irq; + int max_irqs; int ret = 0; int n = 0; + int i; + + if (len > KVM_S390_FLIC_MAX_BUFFER || len == 0) + return -EINVAL; + + /* + * We are already using -ENOMEM to signal + * userspace it may retry with a bigger buffer, + * so we need to use something else for this case + */ + buf = vzalloc(len); + if (!buf) + return -ENOBUFS; + + max_irqs = len / sizeof(struct kvm_s390_irq); fi = &kvm->arch.float_int; spin_lock(&fi->lock); - - list_for_each_entry(inti, &fi->list, list) { - if (len < sizeof(struct kvm_s390_irq)) { + for (i = 0; i < FIRQ_LIST_COUNT; i++) { + list_for_each_entry(inti, &fi->lists[i], list) { + if (n == max_irqs) { + /* signal userspace to try again */ + ret = -ENOMEM; + goto out; + } + inti_to_irq(inti, &buf[n]); + n++; + } + } + if (test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs)) { + if (n == max_irqs) { /* signal userspace to try again */ ret = -ENOMEM; - break; + goto out; } - ret = copy_irq_to_user(inti, buf); - if (ret) - break; - buf += sizeof(struct kvm_s390_irq); - len -= sizeof(struct kvm_s390_irq); + irq = (struct kvm_s390_irq *) &buf[n]; + irq->type = KVM_S390_INT_SERVICE; + irq->u.ext = fi->srv_signal; n++; } + if (test_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) { + if (n == max_irqs) { + /* signal userspace to try again */ + ret = -ENOMEM; + goto out; + } + irq = (struct kvm_s390_irq *) &buf[n]; + irq->type = KVM_S390_MCHK; + irq->u.mchk = fi->mchk; + n++; +} +out: spin_unlock(&fi->lock); + if (!ret && n > 0) { + if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n)) + ret = -EFAULT; + } + vfree(buf); return ret < 0 ? ret : n; } @@ -1520,7 +1691,7 @@ static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) switch (attr->group) { case KVM_DEV_FLIC_GET_ALL_IRQS: - r = get_all_floating_irqs(dev->kvm, (u8 *) attr->addr, + r = get_all_floating_irqs(dev->kvm, (u8 __user *) attr->addr, attr->attr); break; default: @@ -1952,3 +2123,143 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, { return -EINVAL; } + +int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, void __user *irqstate, int len) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_irq *buf; + int r = 0; + int n; + + buf = vmalloc(len); + if (!buf) + return -ENOMEM; + + if (copy_from_user((void *) buf, irqstate, len)) { + r = -EFAULT; + goto out_free; + } + + /* + * Don't allow setting the interrupt state + * when there are already interrupts pending + */ + spin_lock(&li->lock); + if (li->pending_irqs) { + r = -EBUSY; + goto out_unlock; + } + + for (n = 0; n < len / sizeof(*buf); n++) { + r = do_inject_vcpu(vcpu, &buf[n]); + if (r) + break; + } + +out_unlock: + spin_unlock(&li->lock); +out_free: + vfree(buf); + + return r; +} + +static void store_local_irq(struct kvm_s390_local_interrupt *li, + struct kvm_s390_irq *irq, + unsigned long irq_type) +{ + switch (irq_type) { + case IRQ_PEND_MCHK_EX: + case IRQ_PEND_MCHK_REP: + irq->type = KVM_S390_MCHK; + irq->u.mchk = li->irq.mchk; + break; + case IRQ_PEND_PROG: + irq->type = KVM_S390_PROGRAM_INT; + irq->u.pgm = li->irq.pgm; + break; + case IRQ_PEND_PFAULT_INIT: + irq->type = KVM_S390_INT_PFAULT_INIT; + irq->u.ext = li->irq.ext; + break; + case IRQ_PEND_EXT_EXTERNAL: + irq->type = KVM_S390_INT_EXTERNAL_CALL; + irq->u.extcall = li->irq.extcall; + break; + case IRQ_PEND_EXT_CLOCK_COMP: + irq->type = KVM_S390_INT_CLOCK_COMP; + break; + case IRQ_PEND_EXT_CPU_TIMER: + irq->type = KVM_S390_INT_CPU_TIMER; + break; + case IRQ_PEND_SIGP_STOP: + irq->type = KVM_S390_SIGP_STOP; + irq->u.stop = li->irq.stop; + break; + case IRQ_PEND_RESTART: + irq->type = KVM_S390_RESTART; + break; + case IRQ_PEND_SET_PREFIX: + irq->type = KVM_S390_SIGP_SET_PREFIX; + irq->u.prefix = li->irq.prefix; + break; + } +} + +int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len) +{ + uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl; + unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + unsigned long pending_irqs; + struct kvm_s390_irq irq; + unsigned long irq_type; + int cpuaddr; + int n = 0; + + spin_lock(&li->lock); + pending_irqs = li->pending_irqs; + memcpy(&sigp_emerg_pending, &li->sigp_emerg_pending, + sizeof(sigp_emerg_pending)); + spin_unlock(&li->lock); + + for_each_set_bit(irq_type, &pending_irqs, IRQ_PEND_COUNT) { + memset(&irq, 0, sizeof(irq)); + if (irq_type == IRQ_PEND_EXT_EMERGENCY) + continue; + if (n + sizeof(irq) > len) + return -ENOBUFS; + store_local_irq(&vcpu->arch.local_int, &irq, irq_type); + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + + if (test_bit(IRQ_PEND_EXT_EMERGENCY, &pending_irqs)) { + for_each_set_bit(cpuaddr, sigp_emerg_pending, KVM_MAX_VCPUS) { + memset(&irq, 0, sizeof(irq)); + if (n + sizeof(irq) > len) + return -ENOBUFS; + irq.type = KVM_S390_INT_EMERGENCY; + irq.u.emerg.code = cpuaddr; + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + } + + if ((sigp_ctrl & SIGP_CTRL_C) && + (atomic_read(&vcpu->arch.sie_block->cpuflags) & + CPUSTAT_ECALL_PEND)) { + if (n + sizeof(irq) > len) + return -ENOBUFS; + memset(&irq, 0, sizeof(irq)); + irq.type = KVM_S390_INT_EXTERNAL_CALL; + irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK; + if (copy_to_user(&buf[n], &irq, sizeof(irq))) + return -EFAULT; + n += sizeof(irq); + } + + return n; +} diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 19e17bd..afa2bd7 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -25,11 +25,13 @@ #include <linux/random.h> #include <linux/slab.h> #include <linux/timer.h> +#include <linux/vmalloc.h> #include <asm/asm-offsets.h> #include <asm/lowcore.h> #include <asm/pgtable.h> #include <asm/nmi.h> #include <asm/switch_to.h> +#include <asm/isc.h> #include <asm/sclp.h> #include "kvm-s390.h" #include "gaccess.h" @@ -38,6 +40,11 @@ #include "trace.h" #include "trace-s390.h" +#define MEM_OP_MAX_SIZE 65536 /* Maximum transfer size for KVM_S390_MEM_OP */ +#define LOCAL_IRQS 32 +#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 struct kvm_stats_debugfs_item debugfs_entries[] = { @@ -87,6 +94,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "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) }, @@ -101,8 +109,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { /* upper facilities limit for kvm */ unsigned long kvm_s390_fac_list_mask[] = { - 0xff82fffbf4fc2000UL, - 0x005c000000000000UL, + 0xffe6fffbfcfdfc40UL, + 0x205c800000000000UL, }; unsigned long kvm_s390_fac_list_mask_size(void) @@ -171,9 +179,16 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_IRQCHIP: case KVM_CAP_VM_ATTRIBUTES: case KVM_CAP_MP_STATE: + case KVM_CAP_S390_INJECT_IRQ: case KVM_CAP_S390_USER_SIGP: + case KVM_CAP_S390_USER_STSI: + case KVM_CAP_S390_SKEYS: + case KVM_CAP_S390_IRQ_STATE: r = 1; break; + case KVM_CAP_S390_MEM_OP: + r = MEM_OP_MAX_SIZE; + break; case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; @@ -184,6 +199,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_COW: r = MACHINE_HAS_ESOP; break; + case KVM_CAP_S390_VECTOR_REGISTERS: + r = MACHINE_HAS_VX; + break; default: r = 0; } @@ -264,6 +282,18 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) kvm->arch.user_sigp = 1; r = 0; break; + case KVM_CAP_S390_VECTOR_REGISTERS: + if (MACHINE_HAS_VX) { + set_kvm_facility(kvm->arch.model.fac->mask, 129); + set_kvm_facility(kvm->arch.model.fac->list, 129); + r = 0; + } else + r = -EINVAL; + break; + case KVM_CAP_S390_USER_STSI: + kvm->arch.user_stsi = 1; + r = 0; + break; default: r = -EINVAL; break; @@ -708,6 +738,108 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) return ret; } +static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +{ + uint8_t *keys; + uint64_t hva; + unsigned long curkey; + int i, r = 0; + + if (args->flags != 0) + return -EINVAL; + + /* Is this guest using storage keys? */ + if (!mm_use_skey(current->mm)) + return KVM_S390_GET_SKEYS_NONE; + + /* Enforce sane limit on memory allocation */ + if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) + return -EINVAL; + + keys = kmalloc_array(args->count, sizeof(uint8_t), + GFP_KERNEL | __GFP_NOWARN); + if (!keys) + keys = vmalloc(sizeof(uint8_t) * args->count); + if (!keys) + return -ENOMEM; + + for (i = 0; i < args->count; i++) { + hva = gfn_to_hva(kvm, args->start_gfn + i); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + goto out; + } + + curkey = get_guest_storage_key(current->mm, hva); + if (IS_ERR_VALUE(curkey)) { + r = curkey; + goto out; + } + keys[i] = curkey; + } + + r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys, + sizeof(uint8_t) * args->count); + if (r) + r = -EFAULT; +out: + kvfree(keys); + return r; +} + +static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +{ + uint8_t *keys; + uint64_t hva; + int i, r = 0; + + if (args->flags != 0) + return -EINVAL; + + /* Enforce sane limit on memory allocation */ + if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX) + return -EINVAL; + + keys = kmalloc_array(args->count, sizeof(uint8_t), + GFP_KERNEL | __GFP_NOWARN); + if (!keys) + keys = vmalloc(sizeof(uint8_t) * args->count); + if (!keys) + return -ENOMEM; + + r = copy_from_user(keys, (uint8_t __user *)args->skeydata_addr, + sizeof(uint8_t) * args->count); + if (r) { + r = -EFAULT; + goto out; + } + + /* Enable storage key handling for the guest */ + s390_enable_skey(); + + for (i = 0; i < args->count; i++) { + hva = gfn_to_hva(kvm, args->start_gfn + i); + if (kvm_is_error_hva(hva)) { + r = -EFAULT; + goto out; + } + + /* Lowest order bit is reserved */ + if (keys[i] & 0x01) { + r = -EINVAL; + goto out; + } + + r = set_guest_storage_key(current->mm, hva, + (unsigned long)keys[i], 0); + if (r) + goto out; + } +out: + kvfree(keys); + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -767,6 +899,26 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_s390_vm_has_attr(kvm, &attr); break; } + case KVM_S390_GET_SKEYS: { + struct kvm_s390_skeys args; + + r = -EFAULT; + if (copy_from_user(&args, argp, + sizeof(struct kvm_s390_skeys))) + break; + r = kvm_s390_get_skeys(kvm, &args); + break; + } + case KVM_S390_SET_SKEYS: { + struct kvm_s390_skeys args; + + r = -EFAULT; + if (copy_from_user(&args, argp, + sizeof(struct kvm_s390_skeys))) + break; + r = kvm_s390_set_skeys(kvm, &args); + break; + } default: r = -ENOTTY; } @@ -887,7 +1039,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long)); if (!kvm->arch.dbf) - goto out_nodbf; + goto out_err; /* * The architectural maximum amount of facilities is 16 kbit. To store @@ -899,7 +1051,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.model.fac = (struct kvm_s390_fac *) get_zeroed_page(GFP_KERNEL | GFP_DMA); if (!kvm->arch.model.fac) - goto out_nofac; + goto out_err; /* Populate the facility mask initially. */ memcpy(kvm->arch.model.fac->mask, S390_lowcore.stfle_fac_list, @@ -919,10 +1071,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.model.ibc = sclp_get_ibc() & 0x0fff; if (kvm_s390_crypto_init(kvm) < 0) - goto out_crypto; + goto out_err; spin_lock_init(&kvm->arch.float_int.lock); - INIT_LIST_HEAD(&kvm->arch.float_int.list); + for (i = 0; i < FIRQ_LIST_COUNT; i++) + INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]); init_waitqueue_head(&kvm->arch.ipte_wq); mutex_init(&kvm->arch.ipte_mutex); @@ -934,7 +1087,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) } else { kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1); if (!kvm->arch.gmap) - goto out_nogmap; + goto out_err; kvm->arch.gmap->private = kvm; kvm->arch.gmap->pfault_enabled = 0; } @@ -946,15 +1099,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) spin_lock_init(&kvm->arch.start_stop_lock); return 0; -out_nogmap: +out_err: kfree(kvm->arch.crypto.crycb); -out_crypto: free_page((unsigned long)kvm->arch.model.fac); -out_nofac: debug_unregister(kvm->arch.dbf); -out_nodbf: free_page((unsigned long)(kvm->arch.sca)); -out_err: return rc; } @@ -1034,6 +1183,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) KVM_SYNC_CRS | KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT; + if (test_kvm_facility(vcpu->kvm, 129)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; if (kvm_is_ucontrol(vcpu->kvm)) return __kvm_ucontrol_vcpu_init(vcpu); @@ -1044,10 +1195,18 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { save_fp_ctl(&vcpu->arch.host_fpregs.fpc); - save_fp_regs(vcpu->arch.host_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) + save_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs); + else + save_fp_regs(vcpu->arch.host_fpregs.fprs); save_access_regs(vcpu->arch.host_acrs); - restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc); - restore_fp_regs(vcpu->arch.guest_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) { + restore_fp_ctl(&vcpu->run->s.regs.fpc); + restore_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + } else { + restore_fp_ctl(&vcpu->arch.guest_fpregs.fpc); + restore_fp_regs(vcpu->arch.guest_fpregs.fprs); + } restore_access_regs(vcpu->run->s.regs.acrs); gmap_enable(vcpu->arch.gmap); atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); @@ -1057,11 +1216,19 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); gmap_disable(vcpu->arch.gmap); - save_fp_ctl(&vcpu->arch.guest_fpregs.fpc); - save_fp_regs(vcpu->arch.guest_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) { + save_fp_ctl(&vcpu->run->s.regs.fpc); + save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + } else { + save_fp_ctl(&vcpu->arch.guest_fpregs.fpc); + save_fp_regs(vcpu->arch.guest_fpregs.fprs); + } save_access_regs(vcpu->run->s.regs.acrs); restore_fp_ctl(&vcpu->arch.host_fpregs.fpc); - restore_fp_regs(vcpu->arch.host_fpregs.fprs); + if (test_kvm_facility(vcpu->kvm, 129)) + restore_vx_regs((__vector128 *)&vcpu->arch.host_vregs->vrs); + else + restore_fp_regs(vcpu->arch.host_fpregs.fprs); restore_access_regs(vcpu->arch.host_acrs); } @@ -1129,6 +1296,15 @@ int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu) return 0; } +static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_cpu_model *model = &vcpu->kvm->arch.model; + + vcpu->arch.cpu_id = model->cpu_id; + vcpu->arch.sie_block->ibc = model->ibc; + vcpu->arch.sie_block->fac = (int) (long) model->fac->list; +} + int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { int rc = 0; @@ -1137,6 +1313,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) CPUSTAT_SM | CPUSTAT_STOPPED | CPUSTAT_GED); + kvm_s390_vcpu_setup_model(vcpu); + vcpu->arch.sie_block->ecb = 6; if (test_kvm_facility(vcpu->kvm, 50) && test_kvm_facility(vcpu->kvm, 73)) vcpu->arch.sie_block->ecb |= 0x10; @@ -1147,8 +1325,11 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->eca |= 1; if (sclp_has_sigpif()) vcpu->arch.sie_block->eca |= 0x10000000U; - vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE | - ICTL_TPROT; + if (test_kvm_facility(vcpu->kvm, 129)) { + vcpu->arch.sie_block->eca |= 0x00020000; + vcpu->arch.sie_block->ecd |= 0x20000000; + } + vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE; if (kvm_s390_cmma_enabled(vcpu->kvm)) { rc = kvm_s390_vcpu_setup_cmma(vcpu); @@ -1158,11 +1339,6 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup; - mutex_lock(&vcpu->kvm->lock); - vcpu->arch.cpu_id = vcpu->kvm->arch.model.cpu_id; - vcpu->arch.sie_block->ibc = vcpu->kvm->arch.model.ibc; - mutex_unlock(&vcpu->kvm->lock); - kvm_s390_vcpu_crypto_setup(vcpu); return rc; @@ -1190,6 +1366,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block = &sie_page->sie_block; vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb; + vcpu->arch.host_vregs = &sie_page->vregs; vcpu->arch.sie_block->icpua = id; if (!kvm_is_ucontrol(kvm)) { @@ -1205,7 +1382,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca; set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn); } - vcpu->arch.sie_block->fac = (int) (long) kvm->arch.model.fac->list; spin_lock_init(&vcpu->arch.local_int.lock); vcpu->arch.local_int.float_int = &kvm->arch.float_int; @@ -1725,6 +1901,31 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) return 0; } +static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu) +{ + psw_t *psw = &vcpu->arch.sie_block->gpsw; + u8 opcode; + int rc; + + VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction"); + trace_kvm_s390_sie_fault(vcpu); + + /* + * We want to inject an addressing exception, which is defined as a + * suppressing or terminating exception. However, since we came here + * by a DAT access exception, the PSW still points to the faulting + * instruction since DAT exceptions are nullifying. So we've got + * to look up the current opcode to get the length of the instruction + * to be able to forward the PSW. + */ + rc = read_guest(vcpu, psw->addr, 0, &opcode, 1); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + psw->addr = __rewind_psw(*psw, -insn_length(opcode)); + + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); +} + static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) { int rc = -1; @@ -1756,11 +1957,8 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) } } - if (rc == -1) { - VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction"); - trace_kvm_s390_sie_fault(vcpu); - rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - } + if (rc == -1) + rc = vcpu_post_run_fault_in_sie(vcpu); memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16); @@ -1976,6 +2174,35 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) return kvm_s390_store_status_unloaded(vcpu, addr); } +/* + * store additional status at address + */ +int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu, + unsigned long gpa) +{ + /* Only bits 0-53 are used for address formation */ + if (!(gpa & ~0x3ff)) + return 0; + + return write_guest_abs(vcpu, gpa & ~0x3ff, + (void *)&vcpu->run->s.regs.vrs, 512); +} + +int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr) +{ + if (!test_kvm_facility(vcpu->kvm, 129)) + return 0; + + /* + * The guest VXRS are in the host VXRs due to the lazy + * copying in vcpu load/put. Let's update our copies before we save + * it into the save area. + */ + save_vx_regs((__vector128 *)&vcpu->run->s.regs.vrs); + + return kvm_s390_store_adtl_status_unloaded(vcpu, addr); +} + static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) { kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu); @@ -2100,6 +2327,65 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return r; } +static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, + struct kvm_s390_mem_op *mop) +{ + void __user *uaddr = (void __user *)mop->buf; + void *tmpbuf = NULL; + int r, srcu_idx; + const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION + | KVM_S390_MEMOP_F_CHECK_ONLY; + + if (mop->flags & ~supported_flags) + return -EINVAL; + + if (mop->size > MEM_OP_MAX_SIZE) + return -E2BIG; + + if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) { + tmpbuf = vmalloc(mop->size); + if (!tmpbuf) + return -ENOMEM; + } + + srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + + switch (mop->op) { + case KVM_S390_MEMOP_LOGICAL_READ: + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, false); + break; + } + r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); + if (r == 0) { + if (copy_to_user(uaddr, tmpbuf, mop->size)) + r = -EFAULT; + } + break; + case KVM_S390_MEMOP_LOGICAL_WRITE: + if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { + r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, true); + break; + } + if (copy_from_user(tmpbuf, uaddr, mop->size)) { + r = -EFAULT; + break; + } + r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); + break; + default: + r = -EINVAL; + } + + srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); + + if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0) + kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); + + vfree(tmpbuf); + return r; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2109,6 +2395,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, long r; switch (ioctl) { + case KVM_S390_IRQ: { + struct kvm_s390_irq s390irq; + + r = -EFAULT; + if (copy_from_user(&s390irq, argp, sizeof(s390irq))) + break; + r = kvm_s390_inject_vcpu(vcpu, &s390irq); + break; + } case KVM_S390_INTERRUPT: { struct kvm_s390_interrupt s390int; struct kvm_s390_irq s390irq; @@ -2199,6 +2494,47 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); break; } + case KVM_S390_MEM_OP: { + struct kvm_s390_mem_op mem_op; + + if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0) + r = kvm_s390_guest_mem_op(vcpu, &mem_op); + else + r = -EFAULT; + break; + } + case KVM_S390_SET_IRQ_STATE: { + struct kvm_s390_irq_state irq_state; + + r = -EFAULT; + if (copy_from_user(&irq_state, argp, sizeof(irq_state))) + break; + if (irq_state.len > VCPU_IRQS_MAX_BUF || + irq_state.len == 0 || + irq_state.len % sizeof(struct kvm_s390_irq) > 0) { + r = -EINVAL; + break; + } + r = kvm_s390_set_irq_state(vcpu, + (void __user *) irq_state.buf, + irq_state.len); + break; + } + case KVM_S390_GET_IRQ_STATE: { + struct kvm_s390_irq_state irq_state; + + r = -EFAULT; + if (copy_from_user(&irq_state, argp, sizeof(irq_state))) + break; + if (irq_state.len == 0) { + r = -EINVAL; + break; + } + r = kvm_s390_get_irq_state(vcpu, + (__u8 __user *) irq_state.buf, + irq_state.len); + break; + } default: r = -ENOTTY; } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index c34109a..ca108b9 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -70,16 +70,22 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix) kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); } -static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu) +typedef u8 __bitwise ar_t; + +static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu, ar_t *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + if (ar) + *ar = base2; + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, - u64 *address1, u64 *address2) + u64 *address1, u64 *address2, + ar_t *ar_b1, ar_t *ar_b2) { u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28; u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16; @@ -88,6 +94,11 @@ static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu, *address1 = (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1; *address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; + + if (ar_b1) + *ar_b1 = base1; + if (ar_b2) + *ar_b2 = base2; } static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2) @@ -98,7 +109,7 @@ static inline void kvm_s390_get_regs_rre(struct kvm_vcpu *vcpu, int *r1, int *r2 *r2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16; } -static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu) +static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu, ar_t *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) + @@ -107,14 +118,20 @@ static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu) if (disp2 & 0x80000) disp2+=0xfff00000; + if (ar) + *ar = base2; + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2; } -static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu) +static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu, ar_t *ar) { u32 base2 = vcpu->arch.sie_block->ipb >> 28; u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16); + if (ar) + *ar = base2; + return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } @@ -125,13 +142,24 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc) vcpu->arch.sie_block->gpsw.mask |= cc << 44; } -/* test availability of facility in a kvm intance */ +/* test availability of facility in a kvm instance */ static inline int test_kvm_facility(struct kvm *kvm, unsigned long nr) { return __test_facility(nr, kvm->arch.model.fac->mask) && __test_facility(nr, kvm->arch.model.fac->list); } +static inline int set_kvm_facility(u64 *fac_list, unsigned long nr) +{ + unsigned char *ptr; + + if (nr >= MAX_FACILITY_BIT) + return -EINVAL; + ptr = (unsigned char *) fac_list + (nr >> 3); + *ptr |= (0x80UL >> (nr & 7)); + return 0; +} + /* are cpu states controlled by user space */ static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm) { @@ -150,9 +178,9 @@ int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq); int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code); struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, - u64 cr6, u64 schid); -void kvm_s390_reinject_io_int(struct kvm *kvm, - struct kvm_s390_interrupt_info *inti); + u64 isc_mask, u32 schid); +int kvm_s390_reinject_io_int(struct kvm *kvm, + struct kvm_s390_interrupt_info *inti); int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked); /* implemented in intercept.c */ @@ -177,7 +205,10 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu); /* implemented in kvm-s390.c */ long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); +int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu, + unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); +int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu); void s390_vcpu_block(struct kvm_vcpu *vcpu); @@ -241,6 +272,10 @@ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu); extern struct kvm_device_ops kvm_flic_ops; int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu); void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu); +int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, + void __user *buf, int len); +int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, + __u8 __user *buf, int len); /* implemented in guestdbg.c */ void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 3511169..d22d8ee 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -36,15 +36,16 @@ static int handle_set_clock(struct kvm_vcpu *vcpu) struct kvm_vcpu *cpup; s64 hostclk, val; int i, rc; + ar_t ar; u64 op2; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - op2 = kvm_s390_get_base_disp_s(vcpu); + op2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (op2 & 7) /* Operand must be on a doubleword boundary */ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, op2, &val, sizeof(val)); + rc = read_guest(vcpu, op2, ar, &val, sizeof(val)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -68,20 +69,21 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu) u64 operand2; u32 address; int rc; + ar_t ar; vcpu->stat.instruction_spx++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - operand2 = kvm_s390_get_base_disp_s(vcpu); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); /* must be word boundary */ if (operand2 & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); /* get the value */ - rc = read_guest(vcpu, operand2, &address, sizeof(address)); + rc = read_guest(vcpu, operand2, ar, &address, sizeof(address)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -107,13 +109,14 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu) u64 operand2; u32 address; int rc; + ar_t ar; vcpu->stat.instruction_stpx++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - operand2 = kvm_s390_get_base_disp_s(vcpu); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); /* must be word boundary */ if (operand2 & 3) @@ -122,7 +125,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu) address = kvm_s390_get_prefix(vcpu); /* get the value */ - rc = write_guest(vcpu, operand2, &address, sizeof(address)); + rc = write_guest(vcpu, operand2, ar, &address, sizeof(address)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -136,18 +139,19 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu) u16 vcpu_id = vcpu->vcpu_id; u64 ga; int rc; + ar_t ar; vcpu->stat.instruction_stap++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - ga = kvm_s390_get_base_disp_s(vcpu); + ga = kvm_s390_get_base_disp_s(vcpu, &ar); if (ga & 1) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = write_guest(vcpu, ga, &vcpu_id, sizeof(vcpu_id)); + rc = write_guest(vcpu, ga, ar, &vcpu_id, sizeof(vcpu_id)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -207,7 +211,7 @@ static int handle_test_block(struct kvm_vcpu *vcpu) kvm_s390_get_regs_rre(vcpu, NULL, ®2); addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; addr = kvm_s390_logical_to_effective(vcpu, addr); - if (kvm_s390_check_low_addr_protection(vcpu, addr)) + if (kvm_s390_check_low_addr_prot_real(vcpu, addr)) return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); addr = kvm_s390_real_to_abs(vcpu, addr); @@ -229,18 +233,20 @@ static int handle_tpi(struct kvm_vcpu *vcpu) struct kvm_s390_interrupt_info *inti; unsigned long len; u32 tpi_data[3]; - int cc, rc; + int rc; u64 addr; + ar_t ar; - rc = 0; - addr = kvm_s390_get_base_disp_s(vcpu); + addr = kvm_s390_get_base_disp_s(vcpu, &ar); if (addr & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - cc = 0; + inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->arch.sie_block->gcr[6], 0); - if (!inti) - goto no_interrupt; - cc = 1; + if (!inti) { + kvm_s390_set_psw_cc(vcpu, 0); + return 0; + } + tpi_data[0] = inti->io.subchannel_id << 16 | inti->io.subchannel_nr; tpi_data[1] = inti->io.io_int_parm; tpi_data[2] = inti->io.io_int_word; @@ -250,40 +256,51 @@ static int handle_tpi(struct kvm_vcpu *vcpu) * provided area. */ len = sizeof(tpi_data) - 4; - rc = write_guest(vcpu, addr, &tpi_data, len); - if (rc) - return kvm_s390_inject_prog_cond(vcpu, rc); + rc = write_guest(vcpu, addr, ar, &tpi_data, len); + if (rc) { + rc = kvm_s390_inject_prog_cond(vcpu, rc); + goto reinject_interrupt; + } } else { /* * Store the three-word I/O interruption code into * the appropriate lowcore area. */ len = sizeof(tpi_data); - if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) + if (write_guest_lc(vcpu, __LC_SUBCHANNEL_ID, &tpi_data, len)) { + /* failed writes to the low core are not recoverable */ rc = -EFAULT; + goto reinject_interrupt; + } } + + /* irq was successfully handed to the guest */ + kfree(inti); + kvm_s390_set_psw_cc(vcpu, 1); + return 0; +reinject_interrupt: /* * If we encounter a problem storing the interruption code, the * instruction is suppressed from the guest's view: reinject the * interrupt. */ - if (!rc) + if (kvm_s390_reinject_io_int(vcpu->kvm, inti)) { kfree(inti); - else - kvm_s390_reinject_io_int(vcpu->kvm, inti); -no_interrupt: - /* Set condition code and we're done. */ - if (!rc) - kvm_s390_set_psw_cc(vcpu, cc); + rc = -EFAULT; + } + /* don't set the cc, a pgm irq was injected or we drop to user space */ return rc ? -EFAULT : 0; } static int handle_tsch(struct kvm_vcpu *vcpu) { - struct kvm_s390_interrupt_info *inti; + struct kvm_s390_interrupt_info *inti = NULL; + const u64 isc_mask = 0xffUL << 24; /* all iscs set */ - inti = kvm_s390_get_io_int(vcpu->kvm, 0, - vcpu->run->s.regs.gprs[1]); + /* a valid schid has at least one bit set */ + if (vcpu->run->s.regs.gprs[1]) + inti = kvm_s390_get_io_int(vcpu->kvm, isc_mask, + vcpu->run->s.regs.gprs[1]); /* * Prepare exit to userspace. @@ -386,15 +403,16 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu) psw_compat_t new_psw; u64 addr; int rc; + ar_t ar; if (gpsw->mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - addr = kvm_s390_get_base_disp_s(vcpu); + addr = kvm_s390_get_base_disp_s(vcpu, &ar); if (addr & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw)); + rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); if (!(new_psw.mask & PSW32_MASK_BASE)) @@ -412,14 +430,15 @@ static int handle_lpswe(struct kvm_vcpu *vcpu) psw_t new_psw; u64 addr; int rc; + ar_t ar; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - addr = kvm_s390_get_base_disp_s(vcpu); + addr = kvm_s390_get_base_disp_s(vcpu, &ar); if (addr & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, addr, &new_psw, sizeof(new_psw)); + rc = read_guest(vcpu, addr, ar, &new_psw, sizeof(new_psw)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); vcpu->arch.sie_block->gpsw = new_psw; @@ -433,18 +452,19 @@ static int handle_stidp(struct kvm_vcpu *vcpu) u64 stidp_data = vcpu->arch.stidp_data; u64 operand2; int rc; + ar_t ar; vcpu->stat.instruction_stidp++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - operand2 = kvm_s390_get_base_disp_s(vcpu); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (operand2 & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = write_guest(vcpu, operand2, &stidp_data, sizeof(stidp_data)); + rc = write_guest(vcpu, operand2, ar, &stidp_data, sizeof(stidp_data)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); @@ -467,6 +487,7 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) for (n = mem->count - 1; n > 0 ; n--) memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0])); + memset(&mem->vm[0], 0, sizeof(mem->vm[0])); mem->vm[0].cpus_total = cpus; mem->vm[0].cpus_configured = cpus; mem->vm[0].cpus_standby = 0; @@ -478,6 +499,17 @@ static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem) ASCEBC(mem->vm[0].cpi, 16); } +static void insert_stsi_usr_data(struct kvm_vcpu *vcpu, u64 addr, ar_t ar, + u8 fc, u8 sel1, u16 sel2) +{ + vcpu->run->exit_reason = KVM_EXIT_S390_STSI; + vcpu->run->s390_stsi.addr = addr; + vcpu->run->s390_stsi.ar = ar; + vcpu->run->s390_stsi.fc = fc; + vcpu->run->s390_stsi.sel1 = sel1; + vcpu->run->s390_stsi.sel2 = sel2; +} + static int handle_stsi(struct kvm_vcpu *vcpu) { int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28; @@ -486,6 +518,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) unsigned long mem = 0; u64 operand2; int rc = 0; + ar_t ar; vcpu->stat.instruction_stsi++; VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2); @@ -508,7 +541,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) return 0; } - operand2 = kvm_s390_get_base_disp_s(vcpu); + operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (operand2 & 0xfff) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -532,16 +565,20 @@ static int handle_stsi(struct kvm_vcpu *vcpu) break; } - rc = write_guest(vcpu, operand2, (void *)mem, PAGE_SIZE); + rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); if (rc) { rc = kvm_s390_inject_prog_cond(vcpu, rc); goto out; } + if (vcpu->kvm->arch.user_stsi) { + insert_stsi_usr_data(vcpu, operand2, ar, fc, sel1, sel2); + rc = -EREMOTE; + } trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2); free_page(mem); kvm_s390_set_psw_cc(vcpu, 0); vcpu->run->s.regs.gprs[0] = 0; - return 0; + return rc; out_no_data: kvm_s390_set_psw_cc(vcpu, 3); out: @@ -670,7 +707,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) } if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) { - if (kvm_s390_check_low_addr_protection(vcpu, start)) + if (kvm_s390_check_low_addr_prot_real(vcpu, start)) return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); } @@ -776,13 +813,14 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u32 ctl_array[16]; u64 ga; + ar_t ar; vcpu->stat.instruction_lctl++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - ga = kvm_s390_get_base_disp_rs(vcpu); + ga = kvm_s390_get_base_disp_rs(vcpu, &ar); if (ga & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -791,7 +829,7 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga); nr_regs = ((reg3 - reg1) & 0xf) + 1; - rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32)); + rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); reg = reg1; @@ -814,13 +852,14 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u32 ctl_array[16]; u64 ga; + ar_t ar; vcpu->stat.instruction_stctl++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - ga = kvm_s390_get_base_disp_rs(vcpu); + ga = kvm_s390_get_base_disp_rs(vcpu, &ar); if (ga & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -836,7 +875,7 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu) break; reg = (reg + 1) % 16; } while (1); - rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32)); + rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u32)); return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; } @@ -847,13 +886,14 @@ static int handle_lctlg(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u64 ctl_array[16]; u64 ga; + ar_t ar; vcpu->stat.instruction_lctlg++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - ga = kvm_s390_get_base_disp_rsy(vcpu); + ga = kvm_s390_get_base_disp_rsy(vcpu, &ar); if (ga & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -862,7 +902,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu) trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga); nr_regs = ((reg3 - reg1) & 0xf) + 1; - rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64)); + rc = read_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); reg = reg1; @@ -884,13 +924,14 @@ static int handle_stctg(struct kvm_vcpu *vcpu) int reg, rc, nr_regs; u64 ctl_array[16]; u64 ga; + ar_t ar; vcpu->stat.instruction_stctg++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - ga = kvm_s390_get_base_disp_rsy(vcpu); + ga = kvm_s390_get_base_disp_rsy(vcpu, &ar); if (ga & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -906,7 +947,7 @@ static int handle_stctg(struct kvm_vcpu *vcpu) break; reg = (reg + 1) % 16; } while (1); - rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64)); + rc = write_guest(vcpu, ga, ar, ctl_array, nr_regs * sizeof(u64)); return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; } @@ -931,13 +972,14 @@ static int handle_tprot(struct kvm_vcpu *vcpu) unsigned long hva, gpa; int ret = 0, cc = 0; bool writable; + ar_t ar; vcpu->stat.instruction_tprot++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - kvm_s390_get_base_disp_sse(vcpu, &address1, &address2); + kvm_s390_get_base_disp_sse(vcpu, &address1, &address2, &ar, NULL); /* we only handle the Linux memory detection case: * access key == 0 @@ -946,11 +988,11 @@ static int handle_tprot(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) ipte_lock(vcpu); - ret = guest_translate_address(vcpu, address1, &gpa, 1); + ret = guest_translate_address(vcpu, address1, ar, &gpa, 1); if (ret == PGM_PROTECTION) { /* Write protected? Try again with read-only... */ cc = 1; - ret = guest_translate_address(vcpu, address1, &gpa, 0); + ret = guest_translate_address(vcpu, address1, ar, &gpa, 0); } if (ret) { if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) { diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 23b1e86..72e58bd 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -393,6 +393,9 @@ static int handle_sigp_order_in_user_space(struct kvm_vcpu *vcpu, u8 order_code) case SIGP_STORE_STATUS_AT_ADDRESS: vcpu->stat.instruction_sigp_store_status++; break; + case SIGP_STORE_ADDITIONAL_STATUS: + vcpu->stat.instruction_sigp_store_adtl_status++; + break; case SIGP_SET_PREFIX: vcpu->stat.instruction_sigp_prefix++; break; @@ -431,7 +434,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - order_code = kvm_s390_get_base_disp_rs(vcpu); + order_code = kvm_s390_get_base_disp_rs(vcpu, NULL); if (handle_sigp_order_in_user_space(vcpu, order_code)) return -EOPNOTSUPP; @@ -473,7 +476,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu) int r3 = vcpu->arch.sie_block->ipa & 0x000f; u16 cpu_addr = vcpu->run->s.regs.gprs[r3]; struct kvm_vcpu *dest_vcpu; - u8 order_code = kvm_s390_get_base_disp_rs(vcpu); + u8 order_code = kvm_s390_get_base_disp_rs(vcpu, NULL); trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a236e39..dea2e7e 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -81,11 +81,6 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); } -#define SELECTOR_TI_MASK (1 << 2) -#define SELECTOR_RPL_MASK 0x03 - -#define IOPL_SHIFT 12 - #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64 #define KVM_MMU_HASH_SHIFT 10 @@ -345,6 +340,7 @@ struct kvm_pmu { enum { KVM_DEBUGREG_BP_ENABLED = 1, KVM_DEBUGREG_WONT_EXIT = 2, + KVM_DEBUGREG_RELOAD = 4, }; struct kvm_vcpu_arch { @@ -431,6 +427,9 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES]; + + int maxphyaddr; + /* emulate context */ struct x86_emulate_ctxt emulate_ctxt; @@ -550,11 +549,20 @@ struct kvm_arch_memory_slot { struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; }; +/* + * We use as the mode the number of bits allocated in the LDR for the + * logical processor ID. It happens that these are all powers of two. + * This makes it is very easy to detect cases where the APICs are + * configured for multiple modes; in that case, we cannot use the map and + * hence cannot use kvm_irq_delivery_to_apic_fast either. + */ +#define KVM_APIC_MODE_XAPIC_CLUSTER 4 +#define KVM_APIC_MODE_XAPIC_FLAT 8 +#define KVM_APIC_MODE_X2APIC 16 + struct kvm_apic_map { struct rcu_head rcu; - u8 ldr_bits; - /* fields bellow are used to decode ldr values in different modes */ - u32 cid_shift, cid_mask, lid_mask, broadcast; + u8 mode; struct kvm_lapic *phys_map[256]; /* first index is cluster id second is cpu id in a cluster */ struct kvm_lapic *logical_map[16][16]; @@ -859,6 +867,8 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot); +void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, + struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot); void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, @@ -933,6 +943,7 @@ struct x86_emulate_ctxt; int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port); void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); +int kvm_vcpu_halt(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -1128,7 +1139,6 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); -int cpuid_maxphyaddr(struct kvm_vcpu *vcpu); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index e62cf89..c1adf33 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -115,7 +115,7 @@ static inline void kvm_spinlock_init(void) static inline bool kvm_para_available(void) { - return 0; + return false; } static inline unsigned int kvm_arch_para_features(void) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index d6b078e..25b1cc0 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -95,6 +95,7 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, struct pvclock_vsyscall_time_info { struct pvclock_vcpu_time_info pvti; + u32 migrate_count; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index c5f1a1d..1fe9218 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -67,6 +67,7 @@ #define EXIT_REASON_EPT_VIOLATION 48 #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_INVEPT 50 +#define EXIT_REASON_RDTSCP 51 #define EXIT_REASON_PREEMPTION_TIMER 52 #define EXIT_REASON_INVVPID 53 #define EXIT_REASON_WBINVD 54 diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d2..e5ecd20 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -141,7 +141,46 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } +static struct pvclock_vsyscall_time_info *pvclock_vdso_info; + +static struct pvclock_vsyscall_time_info * +pvclock_get_vsyscall_user_time_info(int cpu) +{ + if (!pvclock_vdso_info) { + BUG(); + return NULL; + } + + return &pvclock_vdso_info[cpu]; +} + +struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) +{ + return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; +} + #ifdef CONFIG_X86_64 +static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, + void *v) +{ + struct task_migration_notifier *mn = v; + struct pvclock_vsyscall_time_info *pvti; + + pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); + + /* this is NULL when pvclock vsyscall is not initialized */ + if (unlikely(pvti == NULL)) + return NOTIFY_DONE; + + pvti->migrate_count++; + + return NOTIFY_DONE; +} + +static struct notifier_block pvclock_migrate = { + .notifier_call = pvclock_task_migrate, +}; + /* * Initialize the generic pvclock vsyscall state. This will allocate * a/some page(s) for the per-vcpu pvclock information, set up a @@ -155,12 +194,17 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); + pvclock_vdso_info = i; + for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } + + register_task_migration_notifier(&pvclock_migrate); + return 0; } #endif diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 08f790d..16e8f96 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,5 +1,5 @@ -ccflags-y += -Ivirt/kvm -Iarch/x86/kvm +ccflags-y += -Iarch/x86/kvm CFLAGS_x86.o := -I. CFLAGS_svm.o := -I. diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 8a80737..59b69f6 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -104,6 +104,9 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) ((best->eax & 0xff00) >> 8) != 0) return -EINVAL; + /* Update physical-address width */ + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + kvm_pmu_cpuid_update(vcpu); return 0; } @@ -135,6 +138,21 @@ static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) } } +int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); + if (!best || best->eax < 0x80000008) + goto not_found; + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best) + return best->eax & 0xff; +not_found: + return 36; +} +EXPORT_SYMBOL_GPL(cpuid_query_maxphyaddr); + /* when an old userspace process fills a new kernel module */ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, @@ -757,21 +775,6 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); -int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - - best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); - if (!best || best->eax < 0x80000008) - goto not_found; - best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); - if (best) - return best->eax & 0xff; -not_found: - return 36; -} -EXPORT_SYMBOL_GPL(cpuid_maxphyaddr); - /* * If no match is found, check whether we exceed the vCPU's limit * and return the content of the highest valid _standard_ leaf instead. diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 4452eed..c3b1ad9 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -20,13 +20,19 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 __user *entries); void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); +int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); + +static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.maxphyaddr; +} static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; if (!static_cpu_has(X86_FEATURE_XSAVE)) - return 0; + return false; best = kvm_find_cpuid_entry(vcpu, 1, 0); return best && (best->ecx & bit(X86_FEATURE_XSAVE)); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 106c015..630bcb0 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -248,27 +248,7 @@ struct mode_dual { struct opcode mode64; }; -/* EFLAGS bit definitions. */ -#define EFLG_ID (1<<21) -#define EFLG_VIP (1<<20) -#define EFLG_VIF (1<<19) -#define EFLG_AC (1<<18) -#define EFLG_VM (1<<17) -#define EFLG_RF (1<<16) -#define EFLG_IOPL (3<<12) -#define EFLG_NT (1<<14) -#define EFLG_OF (1<<11) -#define EFLG_DF (1<<10) -#define EFLG_IF (1<<9) -#define EFLG_TF (1<<8) -#define EFLG_SF (1<<7) -#define EFLG_ZF (1<<6) -#define EFLG_AF (1<<4) -#define EFLG_PF (1<<2) -#define EFLG_CF (1<<0) - #define EFLG_RESERVED_ZEROS_MASK 0xffc0802a -#define EFLG_RESERVED_ONE_MASK 2 enum x86_transfer_type { X86_TRANSFER_NONE, @@ -317,7 +297,8 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) * These EFLAGS bits are restored from saved value during emulation, and * any changes are written back to the saved value after emulation. */ -#define EFLAGS_MASK (EFLG_OF|EFLG_SF|EFLG_ZF|EFLG_AF|EFLG_PF|EFLG_CF) +#define EFLAGS_MASK (X86_EFLAGS_OF|X86_EFLAGS_SF|X86_EFLAGS_ZF|X86_EFLAGS_AF|\ + X86_EFLAGS_PF|X86_EFLAGS_CF) #ifdef CONFIG_X86_64 #define ON64(x) x @@ -478,6 +459,25 @@ static void assign_masked(ulong *dest, ulong src, ulong mask) *dest = (*dest & ~mask) | (src & mask); } +static void assign_register(unsigned long *reg, u64 val, int bytes) +{ + /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ + switch (bytes) { + case 1: + *(u8 *)reg = (u8)val; + break; + case 2: + *(u16 *)reg = (u16)val; + break; + case 4: + *reg = (u32)val; + break; /* 64b: zero-extend */ + case 8: + *reg = val; + break; + } +} + static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt) { return (1UL << (ctxt->ad_bytes << 3)) - 1; @@ -943,6 +943,22 @@ FASTOP2(xadd); FASTOP2R(cmp, cmp_r); +static int em_bsf_c(struct x86_emulate_ctxt *ctxt) +{ + /* If src is zero, do not writeback, but update flags */ + if (ctxt->src.val == 0) + ctxt->dst.type = OP_NONE; + return fastop(ctxt, em_bsf); +} + +static int em_bsr_c(struct x86_emulate_ctxt *ctxt) +{ + /* If src is zero, do not writeback, but update flags */ + if (ctxt->src.val == 0) + ctxt->dst.type = OP_NONE; + return fastop(ctxt, em_bsr); +} + static u8 test_cc(unsigned int condition, unsigned long flags) { u8 rc; @@ -1399,7 +1415,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, unsigned int in_page, n; unsigned int count = ctxt->rep_prefix ? address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) : 1; - in_page = (ctxt->eflags & EFLG_DF) ? + in_page = (ctxt->eflags & X86_EFLAGS_DF) ? offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)) : PAGE_SIZE - offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)); n = min3(in_page, (unsigned int)sizeof(rc->data) / size, count); @@ -1412,7 +1428,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, } if (ctxt->rep_prefix && (ctxt->d & String) && - !(ctxt->eflags & EFLG_DF)) { + !(ctxt->eflags & X86_EFLAGS_DF)) { ctxt->dst.data = rc->data + rc->pos; ctxt->dst.type = OP_MEM_STR; ctxt->dst.count = (rc->end - rc->pos) / size; @@ -1691,21 +1707,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, static void write_register_operand(struct operand *op) { - /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ - switch (op->bytes) { - case 1: - *(u8 *)op->addr.reg = (u8)op->val; - break; - case 2: - *(u16 *)op->addr.reg = (u16)op->val; - break; - case 4: - *op->addr.reg = (u32)op->val; - break; /* 64b: zero-extend */ - case 8: - *op->addr.reg = op->val; - break; - } + return assign_register(op->addr.reg, op->val, op->bytes); } static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) @@ -1792,32 +1794,34 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, { int rc; unsigned long val, change_mask; - int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; + int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; int cpl = ctxt->ops->cpl(ctxt); rc = emulate_pop(ctxt, &val, len); if (rc != X86EMUL_CONTINUE) return rc; - change_mask = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF | EFLG_OF - | EFLG_TF | EFLG_DF | EFLG_NT | EFLG_AC | EFLG_ID; + change_mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | + X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF | + X86_EFLAGS_TF | X86_EFLAGS_DF | X86_EFLAGS_NT | + X86_EFLAGS_AC | X86_EFLAGS_ID; switch(ctxt->mode) { case X86EMUL_MODE_PROT64: case X86EMUL_MODE_PROT32: case X86EMUL_MODE_PROT16: if (cpl == 0) - change_mask |= EFLG_IOPL; + change_mask |= X86_EFLAGS_IOPL; if (cpl <= iopl) - change_mask |= EFLG_IF; + change_mask |= X86_EFLAGS_IF; break; case X86EMUL_MODE_VM86: if (iopl < 3) return emulate_gp(ctxt, 0); - change_mask |= EFLG_IF; + change_mask |= X86_EFLAGS_IF; break; default: /* real mode */ - change_mask |= (EFLG_IOPL | EFLG_IF); + change_mask |= (X86_EFLAGS_IOPL | X86_EFLAGS_IF); break; } @@ -1918,7 +1922,7 @@ static int em_pusha(struct x86_emulate_ctxt *ctxt) static int em_pushf(struct x86_emulate_ctxt *ctxt) { - ctxt->src.val = (unsigned long)ctxt->eflags & ~EFLG_VM; + ctxt->src.val = (unsigned long)ctxt->eflags & ~X86_EFLAGS_VM; return em_push(ctxt); } @@ -1926,6 +1930,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) { int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RDI; + u32 val; while (reg >= VCPU_REGS_RAX) { if (reg == VCPU_REGS_RSP) { @@ -1933,9 +1938,10 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) --reg; } - rc = emulate_pop(ctxt, reg_rmw(ctxt, reg), ctxt->op_bytes); + rc = emulate_pop(ctxt, &val, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) break; + assign_register(reg_rmw(ctxt, reg), val, ctxt->op_bytes); --reg; } return rc; @@ -1956,7 +1962,7 @@ static int __emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq) if (rc != X86EMUL_CONTINUE) return rc; - ctxt->eflags &= ~(EFLG_IF | EFLG_TF | EFLG_AC); + ctxt->eflags &= ~(X86_EFLAGS_IF | X86_EFLAGS_TF | X86_EFLAGS_AC); ctxt->src.val = get_segment_selector(ctxt, VCPU_SREG_CS); rc = em_push(ctxt); @@ -2022,10 +2028,14 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) unsigned long temp_eip = 0; unsigned long temp_eflags = 0; unsigned long cs = 0; - unsigned long mask = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF | EFLG_TF | - EFLG_IF | EFLG_DF | EFLG_OF | EFLG_IOPL | EFLG_NT | EFLG_RF | - EFLG_AC | EFLG_ID | (1 << 1); /* Last one is the reserved bit */ - unsigned long vm86_mask = EFLG_VM | EFLG_VIF | EFLG_VIP; + unsigned long mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | + X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_TF | + X86_EFLAGS_IF | X86_EFLAGS_DF | X86_EFLAGS_OF | + X86_EFLAGS_IOPL | X86_EFLAGS_NT | X86_EFLAGS_RF | + X86_EFLAGS_AC | X86_EFLAGS_ID | + X86_EFLAGS_FIXED; + unsigned long vm86_mask = X86_EFLAGS_VM | X86_EFLAGS_VIF | + X86_EFLAGS_VIP; /* TODO: Add stack limit check */ @@ -2054,7 +2064,6 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) ctxt->_eip = temp_eip; - if (ctxt->op_bytes == 4) ctxt->eflags = ((temp_eflags & mask) | (ctxt->eflags & vm86_mask)); else if (ctxt->op_bytes == 2) { @@ -2063,7 +2072,7 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) } ctxt->eflags &= ~EFLG_RESERVED_ZEROS_MASK; /* Clear reserved zeros */ - ctxt->eflags |= EFLG_RESERVED_ONE_MASK; + ctxt->eflags |= X86_EFLAGS_FIXED; ctxt->ops->set_nmi_mask(ctxt, false); return rc; @@ -2145,12 +2154,12 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) ((u32) (old >> 32) != (u32) reg_read(ctxt, VCPU_REGS_RDX))) { *reg_write(ctxt, VCPU_REGS_RAX) = (u32) (old >> 0); *reg_write(ctxt, VCPU_REGS_RDX) = (u32) (old >> 32); - ctxt->eflags &= ~EFLG_ZF; + ctxt->eflags &= ~X86_EFLAGS_ZF; } else { ctxt->dst.val64 = ((u64)reg_read(ctxt, VCPU_REGS_RCX) << 32) | (u32) reg_read(ctxt, VCPU_REGS_RBX); - ctxt->eflags |= EFLG_ZF; + ctxt->eflags |= X86_EFLAGS_ZF; } return X86EMUL_CONTINUE; } @@ -2222,7 +2231,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt) ctxt->src.val = ctxt->dst.orig_val; fastop(ctxt, em_cmp); - if (ctxt->eflags & EFLG_ZF) { + if (ctxt->eflags & X86_EFLAGS_ZF) { /* Success: write back to memory; no update of EAX */ ctxt->src.type = OP_NONE; ctxt->dst.val = ctxt->src.orig_val; @@ -2381,14 +2390,14 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt) ops->get_msr(ctxt, MSR_SYSCALL_MASK, &msr_data); ctxt->eflags &= ~msr_data; - ctxt->eflags |= EFLG_RESERVED_ONE_MASK; + ctxt->eflags |= X86_EFLAGS_FIXED; #endif } else { /* legacy mode */ ops->get_msr(ctxt, MSR_STAR, &msr_data); ctxt->_eip = (u32)msr_data; - ctxt->eflags &= ~(EFLG_VM | EFLG_IF); + ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); } return X86EMUL_CONTINUE; @@ -2425,8 +2434,8 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) if ((msr_data & 0xfffc) == 0x0) return emulate_gp(ctxt, 0); - ctxt->eflags &= ~(EFLG_VM | EFLG_IF); - cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK; + ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); + cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK; ss_sel = cs_sel + 8; if (efer & EFER_LMA) { cs.d = 0; @@ -2493,8 +2502,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) return emulate_gp(ctxt, 0); break; } - cs_sel |= SELECTOR_RPL_MASK; - ss_sel |= SELECTOR_RPL_MASK; + cs_sel |= SEGMENT_RPL_MASK; + ss_sel |= SEGMENT_RPL_MASK; ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); @@ -2512,7 +2521,7 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt) return false; if (ctxt->mode == X86EMUL_MODE_VM86) return true; - iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; + iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; return ctxt->ops->cpl(ctxt) > iopl; } @@ -2782,10 +2791,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, return ret; ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); - if (ret != X86EMUL_CONTINUE) - return ret; - return X86EMUL_CONTINUE; + return ret; } static int task_switch_32(struct x86_emulate_ctxt *ctxt, @@ -2954,7 +2961,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt, static void string_addr_inc(struct x86_emulate_ctxt *ctxt, int reg, struct operand *op) { - int df = (ctxt->eflags & EFLG_DF) ? -op->count : op->count; + int df = (ctxt->eflags & X86_EFLAGS_DF) ? -op->count : op->count; register_address_increment(ctxt, reg, df * op->bytes); op->addr.mem.ea = register_address(ctxt, reg); @@ -3323,7 +3330,7 @@ static int em_clts(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_vmcall(struct x86_emulate_ctxt *ctxt) +static int em_hypercall(struct x86_emulate_ctxt *ctxt) { int rc = ctxt->ops->fix_hypercall(ctxt); @@ -3395,17 +3402,6 @@ static int em_lgdt(struct x86_emulate_ctxt *ctxt) return em_lgdt_lidt(ctxt, true); } -static int em_vmmcall(struct x86_emulate_ctxt *ctxt) -{ - int rc; - - rc = ctxt->ops->fix_hypercall(ctxt); - - /* Disable writeback. */ - ctxt->dst.type = OP_NONE; - return rc; -} - static int em_lidt(struct x86_emulate_ctxt *ctxt) { return em_lgdt_lidt(ctxt, false); @@ -3504,7 +3500,8 @@ static int em_sahf(struct x86_emulate_ctxt *ctxt) { u32 flags; - flags = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF; + flags = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF | + X86_EFLAGS_SF; flags &= *reg_rmw(ctxt, VCPU_REGS_RAX) >> 8; ctxt->eflags &= ~0xffUL; @@ -3769,7 +3766,7 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) static const struct opcode group7_rm0[] = { N, - I(SrcNone | Priv | EmulateOnUD, em_vmcall), + I(SrcNone | Priv | EmulateOnUD, em_hypercall), N, N, N, N, N, N, }; @@ -3781,7 +3778,7 @@ static const struct opcode group7_rm1[] = { static const struct opcode group7_rm3[] = { DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa), - II(SrcNone | Prot | EmulateOnUD, em_vmmcall, vmmcall), + II(SrcNone | Prot | EmulateOnUD, em_hypercall, vmmcall), DIP(SrcNone | Prot | Priv, vmload, check_svme_pa), DIP(SrcNone | Prot | Priv, vmsave, check_svme_pa), DIP(SrcNone | Prot | Priv, stgi, check_svme), @@ -4192,7 +4189,8 @@ static const struct opcode twobyte_table[256] = { N, N, G(BitOp, group8), F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), - F(DstReg | SrcMem | ModRM, em_bsf), F(DstReg | SrcMem | ModRM, em_bsr), + I(DstReg | SrcMem | ModRM, em_bsf_c), + I(DstReg | SrcMem | ModRM, em_bsr_c), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xC7 */ F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd), @@ -4759,9 +4757,9 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) if (((ctxt->b == 0xa6) || (ctxt->b == 0xa7) || (ctxt->b == 0xae) || (ctxt->b == 0xaf)) && (((ctxt->rep_prefix == REPE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == 0)) + ((ctxt->eflags & X86_EFLAGS_ZF) == 0)) || ((ctxt->rep_prefix == REPNE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == EFLG_ZF)))) + ((ctxt->eflags & X86_EFLAGS_ZF) == X86_EFLAGS_ZF)))) return true; return false; @@ -4913,7 +4911,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) /* All REP prefixes have the same first termination condition */ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) { ctxt->eip = ctxt->_eip; - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; goto done; } } @@ -4963,9 +4961,9 @@ special_insn: } if (ctxt->rep_prefix && (ctxt->d & String)) - ctxt->eflags |= EFLG_RF; + ctxt->eflags |= X86_EFLAGS_RF; else - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; if (ctxt->execute) { if (ctxt->d & Fastop) { @@ -5014,7 +5012,7 @@ special_insn: rc = emulate_int(ctxt, ctxt->src.val); break; case 0xce: /* into */ - if (ctxt->eflags & EFLG_OF) + if (ctxt->eflags & X86_EFLAGS_OF) rc = emulate_int(ctxt, 4); break; case 0xe9: /* jmp rel */ @@ -5027,19 +5025,19 @@ special_insn: break; case 0xf5: /* cmc */ /* complement carry flag from eflags reg */ - ctxt->eflags ^= EFLG_CF; + ctxt->eflags ^= X86_EFLAGS_CF; break; case 0xf8: /* clc */ - ctxt->eflags &= ~EFLG_CF; + ctxt->eflags &= ~X86_EFLAGS_CF; break; case 0xf9: /* stc */ - ctxt->eflags |= EFLG_CF; + ctxt->eflags |= X86_EFLAGS_CF; break; case 0xfc: /* cld */ - ctxt->eflags &= ~EFLG_DF; + ctxt->eflags &= ~X86_EFLAGS_DF; break; case 0xfd: /* std */ - ctxt->eflags |= EFLG_DF; + ctxt->eflags |= X86_EFLAGS_DF; break; default: goto cannot_emulate; @@ -5100,7 +5098,7 @@ writeback: } goto done; /* skip rip writeback */ } - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; } ctxt->eip = ctxt->_eip; @@ -5137,8 +5135,7 @@ twobyte_insn: case 0x40 ... 0x4f: /* cmov */ if (test_cc(ctxt->b, ctxt->eflags)) ctxt->dst.val = ctxt->src.val; - else if (ctxt->mode != X86EMUL_MODE_PROT64 || - ctxt->op_bytes != 4) + else if (ctxt->op_bytes != 4) ctxt->dst.type = OP_NONE; /* no writeback */ break; case 0x80 ... 0x8f: /* jnz rel, etc*/ diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 298781d..4dce6f8 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -443,7 +443,8 @@ static inline int pit_in_range(gpa_t addr) (addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH)); } -static int pit_ioport_write(struct kvm_io_device *this, +static int pit_ioport_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, const void *data) { struct kvm_pit *pit = dev_to_pit(this); @@ -519,7 +520,8 @@ static int pit_ioport_write(struct kvm_io_device *this, return 0; } -static int pit_ioport_read(struct kvm_io_device *this, +static int pit_ioport_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, void *data) { struct kvm_pit *pit = dev_to_pit(this); @@ -589,7 +591,8 @@ static int pit_ioport_read(struct kvm_io_device *this, return 0; } -static int speaker_ioport_write(struct kvm_io_device *this, +static int speaker_ioport_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, const void *data) { struct kvm_pit *pit = speaker_to_pit(this); @@ -606,8 +609,9 @@ static int speaker_ioport_write(struct kvm_io_device *this, return 0; } -static int speaker_ioport_read(struct kvm_io_device *this, - gpa_t addr, int len, void *data) +static int speaker_ioport_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, void *data) { struct kvm_pit *pit = speaker_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index dd1b16b..c84990b 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -3,7 +3,7 @@ #include <linux/kthread.h> -#include "iodev.h" +#include <kvm/iodev.h> struct kvm_kpit_channel_state { u32 count; /* can be 65536 */ diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 9541ba3..fef922f 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -529,42 +529,42 @@ static int picdev_read(struct kvm_pic *s, return 0; } -static int picdev_master_write(struct kvm_io_device *dev, +static int picdev_master_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_master), addr, len, val); } -static int picdev_master_read(struct kvm_io_device *dev, +static int picdev_master_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_master), addr, len, val); } -static int picdev_slave_write(struct kvm_io_device *dev, +static int picdev_slave_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_slave), addr, len, val); } -static int picdev_slave_read(struct kvm_io_device *dev, +static int picdev_slave_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_slave), addr, len, val); } -static int picdev_eclr_write(struct kvm_io_device *dev, +static int picdev_eclr_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_eclr), addr, len, val); } -static int picdev_eclr_read(struct kvm_io_device *dev, +static int picdev_eclr_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_eclr), diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 46d4449..28146f0 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -206,6 +206,8 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, old_irr = ioapic->irr; ioapic->irr |= mask; + if (edge) + ioapic->irr_delivered &= ~mask; if ((edge && old_irr == ioapic->irr) || (!edge && entry.fields.remote_irr)) { ret = 0; @@ -349,7 +351,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) irqe.shorthand = 0; if (irqe.trig_mode == IOAPIC_EDGE_TRIG) - ioapic->irr &= ~(1 << irq); + ioapic->irr_delivered |= 1 << irq; if (irq == RTC_GSI && line_status) { /* @@ -473,13 +475,6 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, } } -bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) -{ - struct kvm_ioapic *ioapic = kvm->arch.vioapic; - smp_rmb(); - return test_bit(vector, ioapic->handled_vectors); -} - void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode) { struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; @@ -500,8 +495,8 @@ static inline int ioapic_in_range(struct kvm_ioapic *ioapic, gpa_t addr) (addr < ioapic->base_address + IOAPIC_MEM_LENGTH))); } -static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, - void *val) +static int ioapic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, + gpa_t addr, int len, void *val) { struct kvm_ioapic *ioapic = to_ioapic(this); u32 result; @@ -543,8 +538,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, return 0; } -static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, - const void *val) +static int ioapic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, + gpa_t addr, int len, const void *val) { struct kvm_ioapic *ioapic = to_ioapic(this); u32 data; @@ -599,6 +594,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic) ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS; ioapic->ioregsel = 0; ioapic->irr = 0; + ioapic->irr_delivered = 0; ioapic->id = 0; memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS); rtc_irq_eoi_tracking_reset(ioapic); @@ -656,6 +652,7 @@ int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) spin_lock(&ioapic->lock); memcpy(state, ioapic, sizeof(struct kvm_ioapic_state)); + state->irr &= ~ioapic->irr_delivered; spin_unlock(&ioapic->lock); return 0; } @@ -669,6 +666,7 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) spin_lock(&ioapic->lock); memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); ioapic->irr = 0; + ioapic->irr_delivered = 0; update_handled_vectors(ioapic); kvm_vcpu_request_scan_ioapic(kvm); kvm_ioapic_inject_all(ioapic, state->irr); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index c2e36d9..ca0b0b4 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -3,7 +3,7 @@ #include <linux/kvm_host.h> -#include "iodev.h" +#include <kvm/iodev.h> struct kvm; struct kvm_vcpu; @@ -77,6 +77,7 @@ struct kvm_ioapic { struct rtc_status rtc_status; struct delayed_work eoi_inject; u32 irq_eoi[IOAPIC_NUM_PINS]; + u32 irr_delivered; }; #ifdef DEBUG @@ -97,13 +98,19 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) return kvm->arch.vioapic; } +static inline bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) +{ + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + smp_rmb(); + return test_bit(vector, ioapic->handled_vectors); +} + void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode); int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode); -bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector); int kvm_ioapic_init(struct kvm *kvm); void kvm_ioapic_destroy(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 2d03568..ad68c73 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -27,7 +27,7 @@ #include <linux/kvm_host.h> #include <linux/spinlock.h> -#include "iodev.h" +#include <kvm/iodev.h> #include "ioapic.h" #include "lapic.h" diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4ee827d..d67206a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -133,6 +133,28 @@ static inline int kvm_apic_id(struct kvm_lapic *apic) return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; } +/* The logical map is definitely wrong if we have multiple + * modes at the same time. (Physical map is always right.) + */ +static inline bool kvm_apic_logical_map_valid(struct kvm_apic_map *map) +{ + return !(map->mode & (map->mode - 1)); +} + +static inline void +apic_logical_id(struct kvm_apic_map *map, u32 dest_id, u16 *cid, u16 *lid) +{ + unsigned lid_bits; + + BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_CLUSTER != 4); + BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_FLAT != 8); + BUILD_BUG_ON(KVM_APIC_MODE_X2APIC != 16); + lid_bits = map->mode; + + *cid = dest_id >> lid_bits; + *lid = dest_id & ((1 << lid_bits) - 1); +} + static void recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; @@ -146,48 +168,6 @@ static void recalculate_apic_map(struct kvm *kvm) if (!new) goto out; - new->ldr_bits = 8; - /* flat mode is default */ - new->cid_shift = 8; - new->cid_mask = 0; - new->lid_mask = 0xff; - new->broadcast = APIC_BROADCAST; - - kvm_for_each_vcpu(i, vcpu, kvm) { - struct kvm_lapic *apic = vcpu->arch.apic; - - if (!kvm_apic_present(vcpu)) - continue; - - if (apic_x2apic_mode(apic)) { - new->ldr_bits = 32; - new->cid_shift = 16; - new->cid_mask = new->lid_mask = 0xffff; - new->broadcast = X2APIC_BROADCAST; - } else if (kvm_apic_get_reg(apic, APIC_LDR)) { - if (kvm_apic_get_reg(apic, APIC_DFR) == - APIC_DFR_CLUSTER) { - new->cid_shift = 4; - new->cid_mask = 0xf; - new->lid_mask = 0xf; - } else { - new->cid_shift = 8; - new->cid_mask = 0; - new->lid_mask = 0xff; - } - } - - /* - * All APICs have to be configured in the same mode by an OS. - * We take advatage of this while building logical id loockup - * table. After reset APICs are in software disabled mode, so if - * we find apic with different setting we assume this is the mode - * OS wants all apics to be in; build lookup table accordingly. - */ - if (kvm_apic_sw_enabled(apic)) - break; - } - kvm_for_each_vcpu(i, vcpu, kvm) { struct kvm_lapic *apic = vcpu->arch.apic; u16 cid, lid; @@ -198,11 +178,25 @@ static void recalculate_apic_map(struct kvm *kvm) aid = kvm_apic_id(apic); ldr = kvm_apic_get_reg(apic, APIC_LDR); - cid = apic_cluster_id(new, ldr); - lid = apic_logical_id(new, ldr); if (aid < ARRAY_SIZE(new->phys_map)) new->phys_map[aid] = apic; + + if (apic_x2apic_mode(apic)) { + new->mode |= KVM_APIC_MODE_X2APIC; + } else if (ldr) { + ldr = GET_APIC_LOGICAL_ID(ldr); + if (kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) + new->mode |= KVM_APIC_MODE_XAPIC_FLAT; + else + new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER; + } + + if (!kvm_apic_logical_map_valid(new)) + continue; + + apic_logical_id(new, ldr, &cid, &lid); + if (lid && cid < ARRAY_SIZE(new->logical_map)) new->logical_map[cid][ffs(lid) - 1] = apic; } @@ -588,15 +582,23 @@ static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) apic_update_ppr(apic); } -static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 dest) +static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 mda) { - return dest == (apic_x2apic_mode(apic) ? - X2APIC_BROADCAST : APIC_BROADCAST); + if (apic_x2apic_mode(apic)) + return mda == X2APIC_BROADCAST; + + return GET_APIC_DEST_FIELD(mda) == APIC_BROADCAST; } -static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 dest) +static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 mda) { - return kvm_apic_id(apic) == dest || kvm_apic_broadcast(apic, dest); + if (kvm_apic_broadcast(apic, mda)) + return true; + + if (apic_x2apic_mode(apic)) + return mda == kvm_apic_id(apic); + + return mda == SET_APIC_DEST_FIELD(kvm_apic_id(apic)); } static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) @@ -613,6 +615,7 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) && (logical_id & mda & 0xffff) != 0; logical_id = GET_APIC_LOGICAL_ID(logical_id); + mda = GET_APIC_DEST_FIELD(mda); switch (kvm_apic_get_reg(apic, APIC_DFR)) { case APIC_DFR_FLAT: @@ -627,10 +630,27 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) } } +/* KVM APIC implementation has two quirks + * - dest always begins at 0 while xAPIC MDA has offset 24, + * - IOxAPIC messages have to be delivered (directly) to x2APIC. + */ +static u32 kvm_apic_mda(unsigned int dest_id, struct kvm_lapic *source, + struct kvm_lapic *target) +{ + bool ipi = source != NULL; + bool x2apic_mda = apic_x2apic_mode(ipi ? source : target); + + if (!ipi && dest_id == APIC_BROADCAST && x2apic_mda) + return X2APIC_BROADCAST; + + return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id); +} + bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode) { struct kvm_lapic *target = vcpu->arch.apic; + u32 mda = kvm_apic_mda(dest, source, target); apic_debug("target %p, source %p, dest 0x%x, " "dest_mode 0x%x, short_hand 0x%x\n", @@ -640,9 +660,9 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, switch (short_hand) { case APIC_DEST_NOSHORT: if (dest_mode == APIC_DEST_PHYSICAL) - return kvm_apic_match_physical_addr(target, dest); + return kvm_apic_match_physical_addr(target, mda); else - return kvm_apic_match_logical_addr(target, dest); + return kvm_apic_match_logical_addr(target, mda); case APIC_DEST_SELF: return target == source; case APIC_DEST_ALLINC: @@ -664,6 +684,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic **dst; int i; bool ret = false; + bool x2apic_ipi = src && apic_x2apic_mode(src); *r = -1; @@ -675,15 +696,15 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, if (irq->shorthand) return false; + if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST)) + return false; + rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); if (!map) goto out; - if (irq->dest_id == map->broadcast) - goto out; - ret = true; if (irq->dest_mode == APIC_DEST_PHYSICAL) { @@ -692,16 +713,20 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, dst = &map->phys_map[irq->dest_id]; } else { - u32 mda = irq->dest_id << (32 - map->ldr_bits); - u16 cid = apic_cluster_id(map, mda); + u16 cid; + + if (!kvm_apic_logical_map_valid(map)) { + ret = false; + goto out; + } + + apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap); if (cid >= ARRAY_SIZE(map->logical_map)) goto out; dst = map->logical_map[cid]; - bitmap = apic_logical_id(map, mda); - if (irq->delivery_mode == APIC_DM_LOWEST) { int l = -1; for_each_set_bit(i, &bitmap, 16) { @@ -1037,7 +1062,7 @@ static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr) addr < apic->base_address + LAPIC_MMIO_LENGTH; } -static int apic_mmio_read(struct kvm_io_device *this, +static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, void *data) { struct kvm_lapic *apic = to_lapic(this); @@ -1357,7 +1382,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) return ret; } -static int apic_mmio_write(struct kvm_io_device *this, +static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, const void *data) { struct kvm_lapic *apic = to_lapic(this); @@ -1497,8 +1522,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) return; } - if (!kvm_vcpu_is_bsp(apic->vcpu)) - value &= ~MSR_IA32_APICBASE_BSP; vcpu->arch.apic_base = value; /* update jump label if enable bit changes */ diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 0bc6c65..9d28383 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -1,7 +1,7 @@ #ifndef __KVM_X86_LAPIC_H #define __KVM_X86_LAPIC_H -#include "iodev.h" +#include <kvm/iodev.h> #include <linux/kvm_host.h> @@ -148,21 +148,6 @@ static inline bool kvm_apic_vid_enabled(struct kvm *kvm) return kvm_x86_ops->vm_has_apicv(kvm); } -static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr) -{ - u16 cid; - ldr >>= 32 - map->ldr_bits; - cid = (ldr >> map->cid_shift) & map->cid_mask; - - return cid; -} - -static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr) -{ - ldr >>= (32 - map->ldr_bits); - return ldr & map->lid_mask; -} - static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) { return vcpu->arch.apic->pending_events; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index cee7592..146f295 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4465,6 +4465,79 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, kvm_flush_remote_tlbs(kvm); } +static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, + unsigned long *rmapp) +{ + u64 *sptep; + struct rmap_iterator iter; + int need_tlb_flush = 0; + pfn_t pfn; + struct kvm_mmu_page *sp; + + for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { + BUG_ON(!(*sptep & PT_PRESENT_MASK)); + + sp = page_header(__pa(sptep)); + pfn = spte_to_pfn(*sptep); + + /* + * Only EPT supported for now; otherwise, one would need to + * find out efficiently whether the guest page tables are + * also using huge pages. + */ + if (sp->role.direct && + !kvm_is_reserved_pfn(pfn) && + PageTransCompound(pfn_to_page(pfn))) { + drop_spte(kvm, sptep); + sptep = rmap_get_first(*rmapp, &iter); + need_tlb_flush = 1; + } else + sptep = rmap_get_next(&iter); + } + + return need_tlb_flush; +} + +void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + bool flush = false; + unsigned long *rmapp; + unsigned long last_index, index; + gfn_t gfn_start, gfn_end; + + spin_lock(&kvm->mmu_lock); + + gfn_start = memslot->base_gfn; + gfn_end = memslot->base_gfn + memslot->npages - 1; + + if (gfn_start >= gfn_end) + goto out; + + rmapp = memslot->arch.rmap[0]; + last_index = gfn_to_index(gfn_end, memslot->base_gfn, + PT_PAGE_TABLE_LEVEL); + + for (index = 0; index <= last_index; ++index, ++rmapp) { + if (*rmapp) + flush |= kvm_mmu_zap_collapsible_spte(kvm, rmapp); + + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (flush) { + kvm_flush_remote_tlbs(kvm); + flush = false; + } + cond_resched_lock(&kvm->mmu_lock); + } + } + + if (flush) + kvm_flush_remote_tlbs(kvm); + +out: + spin_unlock(&kvm->mmu_lock); +} + void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 8e6b7d8..29fbf9d 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -38,7 +38,7 @@ static struct kvm_arch_event_perf_mapping { }; /* mapping between fixed pmc index and arch_events array */ -int fixed_pmc_events[] = {1, 0, 7}; +static int fixed_pmc_events[] = {1, 0, 7}; static bool pmc_is_gp(struct kvm_pmc *pmc) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index cc618c8..ce741b8 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1261,7 +1261,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_bsp(&svm->vcpu)) + if (kvm_vcpu_is_reset_bsp(&svm->vcpu)) svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; svm_init_osvw(&svm->vcpu); @@ -1929,14 +1929,12 @@ static int nop_on_interception(struct vcpu_svm *svm) static int halt_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 1; - skip_emulated_instruction(&svm->vcpu); return kvm_emulate_halt(&svm->vcpu); } static int vmmcall_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); kvm_emulate_hypercall(&svm->vcpu); return 1; } @@ -2757,11 +2755,11 @@ static int invlpga_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX], - vcpu->arch.regs[VCPU_REGS_RAX]); + trace_kvm_invlpga(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RCX), + kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ - kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]); + kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); @@ -2770,12 +2768,18 @@ static int invlpga_interception(struct vcpu_svm *svm) static int skinit_interception(struct vcpu_svm *svm) { - trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]); + trace_kvm_skinit(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } +static int wbinvd_interception(struct vcpu_svm *svm) +{ + kvm_emulate_wbinvd(&svm->vcpu); + return 1; +} + static int xsetbv_interception(struct vcpu_svm *svm) { u64 new_bv = kvm_read_edx_eax(&svm->vcpu); @@ -2902,7 +2906,8 @@ static int rdpmc_interception(struct vcpu_svm *svm) return 1; } -bool check_selective_cr0_intercepted(struct vcpu_svm *svm, unsigned long val) +static bool check_selective_cr0_intercepted(struct vcpu_svm *svm, + unsigned long val) { unsigned long cr0 = svm->vcpu.arch.cr0; bool ret = false; @@ -2940,7 +2945,10 @@ static int cr_interception(struct vcpu_svm *svm) return emulate_on_interception(svm); reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK; - cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0; + if (svm->vmcb->control.exit_code == SVM_EXIT_CR0_SEL_WRITE) + cr = SVM_EXIT_WRITE_CR0 - SVM_EXIT_READ_CR0; + else + cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0; err = 0; if (cr >= 16) { /* mov to cr */ @@ -3133,7 +3141,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) static int rdmsr_interception(struct vcpu_svm *svm) { - u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); u64 data; if (svm_get_msr(&svm->vcpu, ecx, &data)) { @@ -3142,8 +3150,8 @@ static int rdmsr_interception(struct vcpu_svm *svm) } else { trace_kvm_msr_read(ecx, data); - svm->vcpu.arch.regs[VCPU_REGS_RAX] = data & 0xffffffff; - svm->vcpu.arch.regs[VCPU_REGS_RDX] = data >> 32; + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, data & 0xffffffff); + kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, data >> 32); svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; skip_emulated_instruction(&svm->vcpu); } @@ -3246,9 +3254,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) static int wrmsr_interception(struct vcpu_svm *svm) { struct msr_data msr; - u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; - u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u) - | ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32); + u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); + u64 data = kvm_read_edx_eax(&svm->vcpu); msr.data = data; msr.index = ecx; @@ -3325,7 +3332,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR3] = cr_interception, [SVM_EXIT_READ_CR4] = cr_interception, [SVM_EXIT_READ_CR8] = cr_interception, - [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, + [SVM_EXIT_CR0_SEL_WRITE] = cr_interception, [SVM_EXIT_WRITE_CR0] = cr_interception, [SVM_EXIT_WRITE_CR3] = cr_interception, [SVM_EXIT_WRITE_CR4] = cr_interception, @@ -3376,7 +3383,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_STGI] = stgi_interception, [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = skinit_interception, - [SVM_EXIT_WBINVD] = emulate_on_interception, + [SVM_EXIT_WBINVD] = wbinvd_interception, [SVM_EXIT_MONITOR] = monitor_interception, [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, @@ -3555,7 +3562,7 @@ static int handle_exit(struct kvm_vcpu *vcpu) if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || !svm_exit_handlers[exit_code]) { - WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code); + WARN_ONCE(1, "svm: unexpected exit reason 0x%x\n", exit_code); kvm_queue_exception(vcpu, UD_VECTOR); return 1; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ae4f6d3..f5e8dce 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2470,6 +2470,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) vmx->nested.nested_vmx_secondary_ctls_low = 0; vmx->nested.nested_vmx_secondary_ctls_high &= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | @@ -3268,8 +3269,8 @@ static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, * default value. */ if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS) - save->selector &= ~SELECTOR_RPL_MASK; - save->dpl = save->selector & SELECTOR_RPL_MASK; + save->selector &= ~SEGMENT_RPL_MASK; + save->dpl = save->selector & SEGMENT_RPL_MASK; save->s = 1; } vmx_set_segment(vcpu, save, seg); @@ -3842,7 +3843,7 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu) unsigned int cs_rpl; vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); - cs_rpl = cs.selector & SELECTOR_RPL_MASK; + cs_rpl = cs.selector & SEGMENT_RPL_MASK; if (cs.unusable) return false; @@ -3870,7 +3871,7 @@ static bool stack_segment_valid(struct kvm_vcpu *vcpu) unsigned int ss_rpl; vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - ss_rpl = ss.selector & SELECTOR_RPL_MASK; + ss_rpl = ss.selector & SEGMENT_RPL_MASK; if (ss.unusable) return true; @@ -3892,7 +3893,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) unsigned int rpl; vmx_get_segment(vcpu, &var, seg); - rpl = var.selector & SELECTOR_RPL_MASK; + rpl = var.selector & SEGMENT_RPL_MASK; if (var.unusable) return true; @@ -3919,7 +3920,7 @@ static bool tr_valid(struct kvm_vcpu *vcpu) if (tr.unusable) return false; - if (tr.selector & SELECTOR_TI_MASK) /* TI = 1 */ + if (tr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */ return false; @@ -3937,7 +3938,7 @@ static bool ldtr_valid(struct kvm_vcpu *vcpu) if (ldtr.unusable) return true; - if (ldtr.selector & SELECTOR_TI_MASK) /* TI = 1 */ + if (ldtr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (ldtr.type != 2) return false; @@ -3954,8 +3955,8 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - return ((cs.selector & SELECTOR_RPL_MASK) == - (ss.selector & SELECTOR_RPL_MASK)); + return ((cs.selector & SEGMENT_RPL_MASK) == + (ss.selector & SEGMENT_RPL_MASK)); } /* @@ -4711,7 +4712,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(&vmx->vcpu, 0); apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_bsp(&vmx->vcpu)) + if (kvm_vcpu_is_reset_bsp(&vmx->vcpu)) apic_base_msr.data |= MSR_IA32_APICBASE_BSP; apic_base_msr.host_initiated = true; kvm_set_apic_base(&vmx->vcpu, &apic_base_msr); @@ -5006,7 +5007,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, if (emulate_instruction(vcpu, 0) == EMULATE_DONE) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_emulate_halt(vcpu); + return kvm_vcpu_halt(vcpu); } return 1; } @@ -5071,6 +5072,10 @@ static int handle_exception(struct kvm_vcpu *vcpu) } if (is_invalid_opcode(intr_info)) { + if (is_guest_mode(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(vcpu, UD_VECTOR); @@ -5090,9 +5095,10 @@ static int handle_exception(struct kvm_vcpu *vcpu) !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX; - vcpu->run->internal.ndata = 2; + vcpu->run->internal.ndata = 3; vcpu->run->internal.data[0] = vect_info; vcpu->run->internal.data[1] = intr_info; + vcpu->run->internal.data[2] = error_code; return 0; } @@ -5533,13 +5539,11 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) static int handle_halt(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); return kvm_emulate_halt(vcpu); } static int handle_vmcall(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); kvm_emulate_hypercall(vcpu); return 1; } @@ -5570,7 +5574,6 @@ static int handle_rdpmc(struct kvm_vcpu *vcpu) static int handle_wbinvd(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); kvm_emulate_wbinvd(vcpu); return 1; } @@ -5828,7 +5831,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { + if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { skip_emulated_instruction(vcpu); return 1; } @@ -5909,7 +5912,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - ret = kvm_emulate_halt(vcpu); + ret = kvm_vcpu_halt(vcpu); goto out; } @@ -7318,21 +7321,21 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, else if (port < 0x10000) bitmap = vmcs12->io_bitmap_b; else - return 1; + return true; bitmap += (port & 0x7fff) / 8; if (last_bitmap != bitmap) if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1)) - return 1; + return true; if (b & (1 << (port & 7))) - return 1; + return true; port++; size--; last_bitmap = bitmap; } - return 0; + return false; } /* @@ -7348,7 +7351,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, gpa_t bitmap; if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) - return 1; + return true; /* * The MSR_BITMAP page is divided into four 1024-byte bitmaps, @@ -7367,10 +7370,10 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, if (msr_index < 1024*8) { unsigned char b; if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1)) - return 1; + return true; return 1 & (b >> (msr_index & 7)); } else - return 1; /* let L1 handle the wrong parameter */ + return true; /* let L1 handle the wrong parameter */ } /* @@ -7392,7 +7395,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, case 0: if (vmcs12->cr0_guest_host_mask & (val ^ vmcs12->cr0_read_shadow)) - return 1; + return true; break; case 3: if ((vmcs12->cr3_target_count >= 1 && @@ -7403,37 +7406,37 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, vmcs12->cr3_target_value2 == val) || (vmcs12->cr3_target_count >= 4 && vmcs12->cr3_target_value3 == val)) - return 0; + return false; if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING)) - return 1; + return true; break; case 4: if (vmcs12->cr4_guest_host_mask & (vmcs12->cr4_read_shadow ^ val)) - return 1; + return true; break; case 8: if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING)) - return 1; + return true; break; } break; case 2: /* clts */ if ((vmcs12->cr0_guest_host_mask & X86_CR0_TS) && (vmcs12->cr0_read_shadow & X86_CR0_TS)) - return 1; + return true; break; case 1: /* mov from cr */ switch (cr) { case 3: if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_CR3_STORE_EXITING) - return 1; + return true; break; case 8: if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_CR8_STORE_EXITING) - return 1; + return true; break; } break; @@ -7444,14 +7447,14 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, */ if (vmcs12->cr0_guest_host_mask & 0xe & (val ^ vmcs12->cr0_read_shadow)) - return 1; + return true; if ((vmcs12->cr0_guest_host_mask & 0x1) && !(vmcs12->cr0_read_shadow & 0x1) && (val & 0x1)) - return 1; + return true; break; } - return 0; + return false; } /* @@ -7474,48 +7477,48 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) KVM_ISA_VMX); if (vmx->nested.nested_run_pending) - return 0; + return false; if (unlikely(vmx->fail)) { pr_info_ratelimited("%s failed vm entry %x\n", __func__, vmcs_read32(VM_INSTRUCTION_ERROR)); - return 1; + return true; } switch (exit_reason) { case EXIT_REASON_EXCEPTION_NMI: if (!is_exception(intr_info)) - return 0; + return false; else if (is_page_fault(intr_info)) return enable_ept; else if (is_no_device(intr_info) && !(vmcs12->guest_cr0 & X86_CR0_TS)) - return 0; + return false; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); case EXIT_REASON_EXTERNAL_INTERRUPT: - return 0; + return false; case EXIT_REASON_TRIPLE_FAULT: - return 1; + return true; case EXIT_REASON_PENDING_INTERRUPT: return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING); case EXIT_REASON_NMI_WINDOW: return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING); case EXIT_REASON_TASK_SWITCH: - return 1; + return true; case EXIT_REASON_CPUID: if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa) - return 0; - return 1; + return false; + return true; case EXIT_REASON_HLT: return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING); case EXIT_REASON_INVD: - return 1; + return true; case EXIT_REASON_INVLPG: return nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING); case EXIT_REASON_RDPMC: return nested_cpu_has(vmcs12, CPU_BASED_RDPMC_EXITING); - case EXIT_REASON_RDTSC: + case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP: return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING); case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR: case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD: @@ -7527,7 +7530,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * VMX instructions trap unconditionally. This allows L1 to * emulate them for its L2 guest, i.e., allows 3-level nesting! */ - return 1; + return true; case EXIT_REASON_CR_ACCESS: return nested_vmx_exit_handled_cr(vcpu, vmcs12); case EXIT_REASON_DR_ACCESS: @@ -7538,7 +7541,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_MSR_WRITE: return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason); case EXIT_REASON_INVALID_STATE: - return 1; + return true; case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); case EXIT_REASON_MONITOR_INSTRUCTION: @@ -7548,7 +7551,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) nested_cpu_has2(vmcs12, SECONDARY_EXEC_PAUSE_LOOP_EXITING); case EXIT_REASON_MCE_DURING_VMENTRY: - return 0; + return false; case EXIT_REASON_TPR_BELOW_THRESHOLD: return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW); case EXIT_REASON_APIC_ACCESS: @@ -7557,7 +7560,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_APIC_WRITE: case EXIT_REASON_EOI_INDUCED: /* apic_write and eoi_induced should exit unconditionally. */ - return 1; + return true; case EXIT_REASON_EPT_VIOLATION: /* * L0 always deals with the EPT violation. If nested EPT is @@ -7565,7 +7568,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * missing in the guest EPT table (EPT12), the EPT violation * will be injected with nested_ept_inject_page_fault() */ - return 0; + return false; case EXIT_REASON_EPT_MISCONFIG: /* * L2 never uses directly L1's EPT, but rather L0's own EPT @@ -7573,11 +7576,11 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * (EPT on EPT). So any problems with the structure of the * table is L0's fault. */ - return 0; + return false; case EXIT_REASON_WBINVD: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING); case EXIT_REASON_XSETBV: - return 1; + return true; case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS: /* * This should never happen, since it is not possible to @@ -7587,7 +7590,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) */ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); default: - return 1; + return true; } } @@ -8522,6 +8525,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) exec_control); } } + if (nested && !vmx->rdtscp_enabled) + vmx->nested.nested_vmx_secondary_ctls_high &= + ~SECONDARY_EXEC_RDTSCP; } /* Exposing INVPCID only when PCID is exposed */ @@ -8622,10 +8628,11 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); + int maxphyaddr = cpuid_maxphyaddr(vcpu); if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - /* TODO: Also verify bits beyond physical address width are 0 */ - if (!PAGE_ALIGNED(vmcs12->apic_access_addr)) + if (!PAGE_ALIGNED(vmcs12->apic_access_addr) || + vmcs12->apic_access_addr >> maxphyaddr) return false; /* @@ -8641,8 +8648,8 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, } if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { - /* TODO: Also verify bits beyond physical address width are 0 */ - if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr)) + if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr) || + vmcs12->virtual_apic_page_addr >> maxphyaddr) return false; if (vmx->nested.virtual_apic_page) /* shouldn't happen */ @@ -8665,7 +8672,8 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, } if (nested_cpu_has_posted_intr(vmcs12)) { - if (!IS_ALIGNED(vmcs12->posted_intr_desc_addr, 64)) + if (!IS_ALIGNED(vmcs12->posted_intr_desc_addr, 64) || + vmcs12->posted_intr_desc_addr >> maxphyaddr) return false; if (vmx->nested.pi_desc_page) { /* shouldn't happen */ @@ -8864,9 +8872,9 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, unsigned long count_field, - unsigned long addr_field, - int maxphyaddr) + unsigned long addr_field) { + int maxphyaddr; u64 count, addr; if (vmcs12_read_any(vcpu, count_field, &count) || @@ -8876,6 +8884,7 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, } if (count == 0) return 0; + maxphyaddr = cpuid_maxphyaddr(vcpu); if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr || (addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) { pr_warn_ratelimited( @@ -8889,19 +8898,16 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, static int nested_vmx_check_msr_switch_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - int maxphyaddr; - if (vmcs12->vm_exit_msr_load_count == 0 && vmcs12->vm_exit_msr_store_count == 0 && vmcs12->vm_entry_msr_load_count == 0) return 0; /* Fast path */ - maxphyaddr = cpuid_maxphyaddr(vcpu); if (nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_LOAD_COUNT, - VM_EXIT_MSR_LOAD_ADDR, maxphyaddr) || + VM_EXIT_MSR_LOAD_ADDR) || nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_STORE_COUNT, - VM_EXIT_MSR_STORE_ADDR, maxphyaddr) || + VM_EXIT_MSR_STORE_ADDR) || nested_vmx_check_msr_switch(vcpu, VM_ENTRY_MSR_LOAD_COUNT, - VM_ENTRY_MSR_LOAD_ADDR, maxphyaddr)) + VM_ENTRY_MSR_LOAD_ADDR)) return -EINVAL; return 0; } @@ -9151,8 +9157,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) exec_control &= ~SECONDARY_EXEC_RDTSCP; /* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_APIC_REGISTER_VIRT); + SECONDARY_EXEC_APIC_REGISTER_VIRT); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -9385,7 +9392,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) } if (!nested_get_vmcs12_pages(vcpu, vmcs12)) { - /*TODO: Also verify bits beyond physical address width are 0*/ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; } @@ -9524,7 +9530,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmcs12->launch_state = 1; if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) - return kvm_emulate_halt(vcpu); + return kvm_vcpu_halt(vcpu); vmx->nested.nested_run_pending = 1; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 32bf19e..2b2dd03 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -801,6 +801,17 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_cr8); +static void kvm_update_dr0123(struct kvm_vcpu *vcpu) +{ + int i; + + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + for (i = 0; i < KVM_NR_DB_REGS; i++) + vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; + } +} + static void kvm_update_dr6(struct kvm_vcpu *vcpu) { if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) @@ -3149,6 +3160,7 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, return -EINVAL; memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); + kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; kvm_update_dr6(vcpu); vcpu->arch.dr7 = dbgregs->dr7; @@ -4114,8 +4126,8 @@ static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, do { n = min(len, 8); if (!(vcpu->arch.apic && - !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, n, v)) - && kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + !kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v)) + && kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v)) break; handled += n; addr += n; @@ -4134,8 +4146,9 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) do { n = min(len, 8); if (!(vcpu->arch.apic && - !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, n, v)) - && kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + !kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev, + addr, n, v)) + && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v)) break; trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v); handled += n; @@ -4475,7 +4488,8 @@ mmio: return X86EMUL_CONTINUE; } -int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, +static int emulator_read_write(struct x86_emulate_ctxt *ctxt, + unsigned long addr, void *val, unsigned int bytes, struct x86_exception *exception, const struct read_write_emulator_ops *ops) @@ -4538,7 +4552,7 @@ static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, exception, &read_emultor); } -int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, +static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, const void *val, unsigned int bytes, @@ -4629,10 +4643,10 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) int r; if (vcpu->arch.pio.in) - r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, + r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, vcpu->arch.pio.size, pd); else - r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, + r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, vcpu->arch.pio.size, pd); return r; @@ -4705,7 +4719,7 @@ static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) kvm_mmu_invlpg(emul_to_vcpu(ctxt), address); } -int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) +int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) { if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; @@ -4722,19 +4736,29 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) wbinvd(); return X86EMUL_CONTINUE; } + +int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->skip_emulated_instruction(vcpu); + return kvm_emulate_wbinvd_noskip(vcpu); +} EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd); + + static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) { - kvm_emulate_wbinvd(emul_to_vcpu(ctxt)); + kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } -int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) +static int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long *dest) { return kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); } -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) +static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long value) { return __kvm_set_dr(emul_to_vcpu(ctxt), dr, value); @@ -5816,7 +5840,7 @@ void kvm_arch_exit(void) free_percpu(shared_msrs); } -int kvm_emulate_halt(struct kvm_vcpu *vcpu) +int kvm_vcpu_halt(struct kvm_vcpu *vcpu) { ++vcpu->stat.halt_exits; if (irqchip_in_kernel(vcpu->kvm)) { @@ -5827,6 +5851,13 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) return 0; } } +EXPORT_SYMBOL_GPL(kvm_vcpu_halt); + +int kvm_emulate_halt(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->skip_emulated_instruction(vcpu); + return kvm_vcpu_halt(vcpu); +} EXPORT_SYMBOL_GPL(kvm_emulate_halt); int kvm_hv_hypercall(struct kvm_vcpu *vcpu) @@ -5903,7 +5934,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) lapic_irq.dest_id = apicid; lapic_irq.delivery_mode = APIC_DM_REMRD; - kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL); + kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) @@ -5911,6 +5942,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) unsigned long nr, a0, a1, a2, a3, ret; int op_64_bit, r = 1; + kvm_x86_ops->skip_emulated_instruction(vcpu); + if (kvm_hv_hypercall_enabled(vcpu->kvm)) return kvm_hv_hypercall(vcpu); @@ -6164,7 +6197,7 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, } /* - * Returns 1 to let __vcpu_run() continue the guest execution loop without + * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the * userspace. */ @@ -6301,6 +6334,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); set_debugreg(vcpu->arch.dr6, 6); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } trace_kvm_entry(vcpu->vcpu_id); @@ -6382,42 +6416,47 @@ out: return r; } +static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) +{ + if (!kvm_arch_vcpu_runnable(vcpu)) { + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_block(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + if (!kvm_check_request(KVM_REQ_UNHALT, vcpu)) + return 1; + } + + kvm_apic_accept_events(vcpu); + switch(vcpu->arch.mp_state) { + case KVM_MP_STATE_HALTED: + vcpu->arch.pv.pv_unhalted = false; + vcpu->arch.mp_state = + KVM_MP_STATE_RUNNABLE; + case KVM_MP_STATE_RUNNABLE: + vcpu->arch.apf.halted = false; + break; + case KVM_MP_STATE_INIT_RECEIVED: + break; + default: + return -EINTR; + break; + } + return 1; +} -static int __vcpu_run(struct kvm_vcpu *vcpu) +static int vcpu_run(struct kvm_vcpu *vcpu) { int r; struct kvm *kvm = vcpu->kvm; vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - r = 1; - while (r > 0) { + for (;;) { if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted) r = vcpu_enter_guest(vcpu); - else { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) { - kvm_apic_accept_events(vcpu); - switch(vcpu->arch.mp_state) { - case KVM_MP_STATE_HALTED: - vcpu->arch.pv.pv_unhalted = false; - vcpu->arch.mp_state = - KVM_MP_STATE_RUNNABLE; - case KVM_MP_STATE_RUNNABLE: - vcpu->arch.apf.halted = false; - break; - case KVM_MP_STATE_INIT_RECEIVED: - break; - default: - r = -EINTR; - break; - } - } - } - + else + r = vcpu_block(kvm, vcpu); if (r <= 0) break; @@ -6429,6 +6468,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) r = -EINTR; vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.request_irq_exits; + break; } kvm_check_async_pf_completion(vcpu); @@ -6437,6 +6477,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) r = -EINTR; vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.signal_exits; + break; } if (need_resched()) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); @@ -6568,7 +6609,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } else WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed); - r = __vcpu_run(vcpu); + r = vcpu_run(vcpu); out: post_kvm_run_save(vcpu); @@ -7075,11 +7116,14 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu) kvm_clear_exception_queue(vcpu); memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); + kvm_update_dr0123(vcpu); vcpu->arch.dr6 = DR6_INIT; kvm_update_dr6(vcpu); vcpu->arch.dr7 = DR7_FIXED_1; kvm_update_dr7(vcpu); + vcpu->arch.cr2 = 0; + kvm_make_request(KVM_REQ_EVENT, vcpu); vcpu->arch.apf.msr_val = 0; vcpu->arch.st.msr_val = 0; @@ -7240,7 +7284,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.pv.pv_unhalted = false; vcpu->arch.emulate_ctxt.ops = &emulate_ops; - if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu)) + if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; @@ -7288,6 +7332,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = 0; vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); @@ -7428,7 +7474,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) { - kvm_kvfree(free->arch.rmap[i]); + kvfree(free->arch.rmap[i]); free->arch.rmap[i] = NULL; } if (i == 0) @@ -7436,7 +7482,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, if (!dont || free->arch.lpage_info[i - 1] != dont->arch.lpage_info[i - 1]) { - kvm_kvfree(free->arch.lpage_info[i - 1]); + kvfree(free->arch.lpage_info[i - 1]); free->arch.lpage_info[i - 1] = NULL; } } @@ -7490,12 +7536,12 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, out_free: for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - kvm_kvfree(slot->arch.rmap[i]); + kvfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; if (i == 0) continue; - kvm_kvfree(slot->arch.lpage_info[i - 1]); + kvfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } return -ENOMEM; @@ -7618,6 +7664,23 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, new = id_to_memslot(kvm->memslots, mem->slot); /* + * Dirty logging tracks sptes in 4k granularity, meaning that large + * sptes have to be split. If live migration is successful, the guest + * in the source machine will be destroyed and large sptes will be + * created in the destination. However, if the guest continues to run + * in the source machine (for example if live migration fails), small + * sptes will remain around and cause bad performance. + * + * Scan sptes if dirty logging has been stopped, dropping those + * which can be collapsed into a single large-page spte. Later + * page faults will create the large-page sptes. + */ + if ((change != KVM_MR_DELETE) && + (old->flags & KVM_MEM_LOG_DIRTY_PAGES) && + !(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) + kvm_mmu_zap_collapsible_sptes(kvm, new); + + /* * Set up write protection and/or dirty logging for the new slot. * * For KVM_MR_DELETE and KVM_MR_MOVE, the shadow pages of old slot have diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 9793322..40d2473 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -82,18 +82,15 @@ static notrace cycle_t vread_pvclock(int *mode) cycle_t ret; u64 last; u32 version; + u32 migrate_count; u8 flags; unsigned cpu, cpu1; /* - * Note: hypervisor must guarantee that: - * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. - * 2. that per-CPU pvclock time info is updated if the - * underlying CPU changes. - * 3. that version is increased whenever underlying CPU - * changes. - * + * When looping to get a consistent (time-info, tsc) pair, we + * also need to deal with the possibility we can switch vcpus, + * so make sure we always re-fetch time-info for the current vcpu. */ do { cpu = __getcpu() & VGETCPU_CPU_MASK; @@ -102,20 +99,27 @@ static notrace cycle_t vread_pvclock(int *mode) * __getcpu() calls (Gleb). */ - pvti = get_pvti(cpu); + /* Make sure migrate_count will change if we leave the VCPU. */ + do { + pvti = get_pvti(cpu); + migrate_count = pvti->migrate_count; + + cpu1 = cpu; + cpu = __getcpu() & VGETCPU_CPU_MASK; + } while (unlikely(cpu != cpu1)); version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); /* * Test we're still on the cpu as well as the version. - * We could have been migrated just after the first - * vgetcpu but before fetching the version, so we - * wouldn't notice a version change. + * - We must read TSC of pvti's VCPU. + * - KVM doesn't follow the versioning protocol, so data could + * change before version if we left the VCPU. */ - cpu1 = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1 || - (pvti->pvti.version & 1) || - pvti->pvti.version != version)); + smp_rmb(); + } while (unlikely((pvti->pvti.version & 1) || + pvti->pvti.version != version || + pvti->migrate_count != migrate_count)); if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) *mode = VCLOCK_NONE; |