diff options
Diffstat (limited to 'arch/powerpc/kvm/book3s_hv.c')
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv.c | 2662 |
1 files changed, 1737 insertions, 925 deletions
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index dc53578193ee..52427fc2a33f 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -42,6 +42,8 @@ #include <linux/module.h> #include <linux/compiler.h> #include <linux/of.h> +#include <linux/irqdomain.h> +#include <linux/smp.h> #include <asm/ftrace.h> #include <asm/reg.h> @@ -53,11 +55,13 @@ #include <asm/cputable.h> #include <asm/cacheflush.h> #include <linux/uaccess.h> +#include <asm/interrupt.h> #include <asm/io.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> #include <asm/mmu_context.h> #include <asm/lppaca.h> +#include <asm/pmc.h> #include <asm/processor.h> #include <asm/cputhreads.h> #include <asm/page.h> @@ -72,11 +76,15 @@ #include <asm/xics.h> #include <asm/xive.h> #include <asm/hw_breakpoint.h> -#include <asm/kvm_host.h> #include <asm/kvm_book3s_uvmem.h> #include <asm/ultravisor.h> +#include <asm/dtl.h> +#include <asm/plpar_wrappers.h> + +#include <trace/events/ipi.h> #include "book3s.h" +#include "book3s_hv.h" #define CREATE_TRACE_POINTS #include "trace_hv.h" @@ -102,16 +110,12 @@ static int target_smt_mode; module_param(target_smt_mode, int, 0644); MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)"); -static bool indep_threads_mode = true; -module_param(indep_threads_mode, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(indep_threads_mode, "Independent-threads mode (only on POWER9)"); - static bool one_vm_per_core; module_param(one_vm_per_core, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(one_vm_per_core, "Only run vCPUs from the same VM on a core (requires indep_threads_mode=N)"); +MODULE_PARM_DESC(one_vm_per_core, "Only run vCPUs from the same VM on a core (requires POWER8 or older)"); #ifdef CONFIG_KVM_XICS -static struct kernel_param_ops module_param_ops = { +static const struct kernel_param_ops module_param_ops = { .set = param_set_int, .get = param_get_int, }; @@ -128,14 +132,6 @@ static bool nested = true; module_param(nested, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(nested, "Enable nested virtualization (only on POWER9)"); -static inline bool nesting_enabled(struct kvm *kvm) -{ - return kvm->arch.nested_enable && kvm_is_radix(kvm); -} - -/* If set, the threads on each CPU core have to be in the same MMU mode */ -static bool no_mixing_hpt_and_radix; - static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); /* @@ -231,13 +227,18 @@ static bool kvmppc_ipi_thread(int cpu) static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) { int cpu; - struct swait_queue_head *wqp; + struct rcuwait *waitp; - wqp = kvm_arch_vcpu_wq(vcpu); - if (swq_has_sleeper(wqp)) { - swake_up_one(wqp); - ++vcpu->stat.halt_wakeup; - } + /* + * rcuwait_wake_up contains smp_mb() which orders prior stores that + * create pending work vs below loads of cpu fields. The other side + * is the barrier in vcpu run that orders setting the cpu fields vs + * testing for pending work. + */ + + waitp = kvm_arch_vcpu_get_wait(vcpu); + if (rcuwait_wake_up(waitp)) + ++vcpu->stat.generic.halt_wakeup; cpu = READ_ONCE(vcpu->arch.thread_cpu); if (cpu >= 0 && kvmppc_ipi_thread(cpu)) @@ -251,6 +252,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) /* * We use the vcpu_load/put functions to measure stolen time. + * * Stolen time is counted as time when either the vcpu is able to * run as part of a virtual core, but the task running the vcore * is preempted or sleeping, or when the vcpu needs something done @@ -280,24 +282,34 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) * lock. The stolen times are measured in units of timebase ticks. * (Note that the != TB_NIL checks below are purely defensive; * they should never fail.) + * + * The POWER9 path is simpler, one vcpu per virtual core so the + * former case does not exist. If a vcpu is preempted when it is + * BUSY_IN_HOST and not ceded or otherwise blocked, then accumulate + * the stolen cycles in busy_stolen. RUNNING is not a preemptible + * state in the P9 path. */ -static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc) +static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc, u64 tb) { unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); - vc->preempt_tb = mftb(); + vc->preempt_tb = tb; spin_unlock_irqrestore(&vc->stoltb_lock, flags); } -static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc) +static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc, u64 tb) { unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); if (vc->preempt_tb != TB_NIL) { - vc->stolen_tb += mftb() - vc->preempt_tb; + vc->stolen_tb += tb - vc->preempt_tb; vc->preempt_tb = TB_NIL; } spin_unlock_irqrestore(&vc->stoltb_lock, flags); @@ -307,6 +319,18 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; unsigned long flags; + u64 now; + + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (vcpu->arch.busy_preempt != TB_NIL) { + WARN_ON_ONCE(vcpu->arch.state != KVMPPC_VCPU_BUSY_IN_HOST); + vc->stolen_tb += mftb() - vcpu->arch.busy_preempt; + vcpu->arch.busy_preempt = TB_NIL; + } + return; + } + + now = mftb(); /* * We can test vc->runner without taking the vcore lock, @@ -315,12 +339,12 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) * ever sets it to NULL. */ if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING) - kvmppc_core_end_stolen(vc); + kvmppc_core_end_stolen(vc, now); spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST && vcpu->arch.busy_preempt != TB_NIL) { - vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt; + vcpu->arch.busy_stolen += now - vcpu->arch.busy_preempt; vcpu->arch.busy_preempt = TB_NIL; } spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); @@ -330,13 +354,32 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; unsigned long flags; + u64 now; + + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + /* + * In the P9 path, RUNNABLE is not preemptible + * (nor takes host interrupts) + */ + WARN_ON_ONCE(vcpu->arch.state == KVMPPC_VCPU_RUNNABLE); + /* + * Account stolen time when preempted while the vcpu task is + * running in the kernel (but not in qemu, which is INACTIVE). + */ + if (task_is_running(current) && + vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST) + vcpu->arch.busy_preempt = mftb(); + return; + } + + now = mftb(); if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING) - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, now); spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST) - vcpu->arch.busy_preempt = mftb(); + vcpu->arch.busy_preempt = now; spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); } @@ -346,15 +389,17 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr) } /* Dummy value used in computing PCR value below */ -#define PCR_ARCH_300 (PCR_ARCH_207 << 1) +#define PCR_ARCH_31 (PCR_ARCH_300 << 1) static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) { - unsigned long host_pcr_bit = 0, guest_pcr_bit = 0; + unsigned long host_pcr_bit = 0, guest_pcr_bit = 0, cap = 0; struct kvmppc_vcore *vc = vcpu->arch.vcore; /* We can (emulate) our own architecture version and anything older */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) + if (cpu_has_feature(CPU_FTR_ARCH_31)) + host_pcr_bit = PCR_ARCH_31; + else if (cpu_has_feature(CPU_FTR_ARCH_300)) host_pcr_bit = PCR_ARCH_300; else if (cpu_has_feature(CPU_FTR_ARCH_207S)) host_pcr_bit = PCR_ARCH_207; @@ -379,6 +424,11 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) break; case PVR_ARCH_300: guest_pcr_bit = PCR_ARCH_300; + cap = H_GUEST_CAP_POWER9; + break; + case PVR_ARCH_31: + guest_pcr_bit = PCR_ARCH_31; + cap = H_GUEST_CAP_POWER10; break; default: return -EINVAL; @@ -389,8 +439,14 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) if (guest_pcr_bit > host_pcr_bit) return -EINVAL; + if (kvmhv_on_pseries() && kvmhv_is_nestedv2()) { + if (!(cap & nested_capabilities)) + return -EINVAL; + } + spin_lock(&vc->lock); vc->arch_compat = arch_compat; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LOGICAL_PVR); /* * Set all PCR bits for which guest_pcr_bit <= bit < host_pcr_bit * Also set all reserved PCR bits @@ -429,7 +485,7 @@ static void kvmppc_dump_regs(struct kvm_vcpu *vcpu) for (r = 0; r < vcpu->arch.slb_max; ++r) pr_err(" ESID = %.16llx VSID = %.16llx\n", vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv); - pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n", + pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.16lx\n", vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1, vcpu->arch.last_inst); } @@ -594,7 +650,8 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu, return err; } -static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap) +static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap, + struct kvmppc_vpa *old_vpap) { struct kvm *kvm = vcpu->kvm; void *va; @@ -634,9 +691,8 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap) kvmppc_unpin_guest_page(kvm, va, gpa, false); va = NULL; } - if (vpap->pinned_addr) - kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa, - vpap->dirty); + *old_vpap = *vpap; + vpap->gpa = gpa; vpap->pinned_addr = va; vpap->dirty = false; @@ -646,6 +702,9 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap) static void kvmppc_update_vpas(struct kvm_vcpu *vcpu) { + struct kvm *kvm = vcpu->kvm; + struct kvmppc_vpa old_vpa = { 0 }; + if (!(vcpu->arch.vpa.update_pending || vcpu->arch.slb_shadow.update_pending || vcpu->arch.dtl.update_pending)) @@ -653,17 +712,34 @@ static void kvmppc_update_vpas(struct kvm_vcpu *vcpu) spin_lock(&vcpu->arch.vpa_update_lock); if (vcpu->arch.vpa.update_pending) { - kvmppc_update_vpa(vcpu, &vcpu->arch.vpa); - if (vcpu->arch.vpa.pinned_addr) + kvmppc_update_vpa(vcpu, &vcpu->arch.vpa, &old_vpa); + if (old_vpa.pinned_addr) { + if (kvmhv_is_nestedv2()) + kvmhv_nestedv2_set_vpa(vcpu, ~0ull); + kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa, + old_vpa.dirty); + } + if (vcpu->arch.vpa.pinned_addr) { init_vpa(vcpu, vcpu->arch.vpa.pinned_addr); + if (kvmhv_is_nestedv2()) + kvmhv_nestedv2_set_vpa(vcpu, __pa(vcpu->arch.vpa.pinned_addr)); + } } if (vcpu->arch.dtl.update_pending) { - kvmppc_update_vpa(vcpu, &vcpu->arch.dtl); + kvmppc_update_vpa(vcpu, &vcpu->arch.dtl, &old_vpa); + if (old_vpa.pinned_addr) + kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa, + old_vpa.dirty); vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr; vcpu->arch.dtl_index = 0; } - if (vcpu->arch.slb_shadow.update_pending) - kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow); + if (vcpu->arch.slb_shadow.update_pending) { + kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow, &old_vpa); + if (old_vpa.pinned_addr) + kvmppc_unpin_guest_page(kvm, old_vpa.pinned_addr, old_vpa.gpa, + old_vpa.dirty); + } + spin_unlock(&vcpu->arch.vpa_update_lock); } @@ -676,6 +752,8 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now) u64 p; unsigned long flags; + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + spin_lock_irqsave(&vc->stoltb_lock, flags); p = vc->stolen_tb; if (vc->vcore_state != VCORE_INACTIVE && @@ -685,19 +763,55 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now) return p; } -static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, - struct kvmppc_vcore *vc) +static void __kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, + struct lppaca *vpa, + unsigned int pcpu, u64 now, + unsigned long stolen) { struct dtl_entry *dt; + + dt = vcpu->arch.dtl_ptr; + + if (!dt) + return; + + dt->dispatch_reason = 7; + dt->preempt_reason = 0; + dt->processor_id = cpu_to_be16(pcpu + vcpu->arch.ptid); + dt->enqueue_to_dispatch_time = cpu_to_be32(stolen); + dt->ready_to_enqueue_time = 0; + dt->waiting_to_ready_time = 0; + dt->timebase = cpu_to_be64(now); + dt->fault_addr = 0; + dt->srr0 = cpu_to_be64(kvmppc_get_pc(vcpu)); + dt->srr1 = cpu_to_be64(vcpu->arch.shregs.msr); + + ++dt; + if (dt == vcpu->arch.dtl.pinned_end) + dt = vcpu->arch.dtl.pinned_addr; + vcpu->arch.dtl_ptr = dt; + /* order writing *dt vs. writing vpa->dtl_idx */ + smp_wmb(); + vpa->dtl_idx = cpu_to_be64(++vcpu->arch.dtl_index); + + /* vcpu->arch.dtl.dirty is set by the caller */ +} + +static void kvmppc_update_vpa_dispatch(struct kvm_vcpu *vcpu, + struct kvmppc_vcore *vc) +{ struct lppaca *vpa; unsigned long stolen; unsigned long core_stolen; u64 now; unsigned long flags; - dt = vcpu->arch.dtl_ptr; vpa = vcpu->arch.vpa.pinned_addr; + if (!vpa) + return; + now = mftb(); + core_stolen = vcore_stolen_time(vc, now); stolen = core_stolen - vcpu->arch.stolen_logged; vcpu->arch.stolen_logged = core_stolen; @@ -705,23 +819,35 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu, stolen += vcpu->arch.busy_stolen; vcpu->arch.busy_stolen = 0; spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); - if (!dt || !vpa) + + vpa->enqueue_dispatch_tb = cpu_to_be64(be64_to_cpu(vpa->enqueue_dispatch_tb) + stolen); + + __kvmppc_create_dtl_entry(vcpu, vpa, vc->pcpu, now + kvmppc_get_tb_offset(vcpu), stolen); + + vcpu->arch.vpa.dirty = true; +} + +static void kvmppc_update_vpa_dispatch_p9(struct kvm_vcpu *vcpu, + struct kvmppc_vcore *vc, + u64 now) +{ + struct lppaca *vpa; + unsigned long stolen; + unsigned long stolen_delta; + + vpa = vcpu->arch.vpa.pinned_addr; + if (!vpa) return; - memset(dt, 0, sizeof(struct dtl_entry)); - dt->dispatch_reason = 7; - dt->processor_id = cpu_to_be16(vc->pcpu + vcpu->arch.ptid); - dt->timebase = cpu_to_be64(now + vc->tb_offset); - dt->enqueue_to_dispatch_time = cpu_to_be32(stolen); - dt->srr0 = cpu_to_be64(kvmppc_get_pc(vcpu)); - dt->srr1 = cpu_to_be64(vcpu->arch.shregs.msr); - ++dt; - if (dt == vcpu->arch.dtl.pinned_end) - dt = vcpu->arch.dtl.pinned_addr; - vcpu->arch.dtl_ptr = dt; - /* order writing *dt vs. writing vpa->dtl_idx */ - smp_wmb(); - vpa->dtl_idx = cpu_to_be64(++vcpu->arch.dtl_index); - vcpu->arch.dtl.dirty = true; + + stolen = vc->stolen_tb; + stolen_delta = stolen - vcpu->arch.stolen_logged; + vcpu->arch.stolen_logged = stolen; + + vpa->enqueue_dispatch_tb = cpu_to_be64(stolen); + + __kvmppc_create_dtl_entry(vcpu, vpa, vc->pcpu, now, stolen_delta); + + vcpu->arch.vpa.dirty = true; } /* See if there is a doorbell interrupt pending for a vcpu */ @@ -732,6 +858,8 @@ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu) if (vcpu->arch.doorbell_request) return true; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return false; /* * Ensure that the read of vcore->dpdes comes after the read * of vcpu->doorbell_request. This barrier matches the @@ -745,9 +873,9 @@ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu) static bool kvmppc_power8_compatible(struct kvm_vcpu *vcpu) { - if (vcpu->arch.vcore->arch_compat >= PVR_ARCH_207) + if (kvmppc_get_arch_compat(vcpu) >= PVR_ARCH_207) return true; - if ((!vcpu->arch.vcore->arch_compat) && + if ((!kvmppc_get_arch_compat(vcpu)) && cpu_has_feature(CPU_FTR_ARCH_207S)) return true; return false; @@ -768,9 +896,9 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, /* Guests can't breakpoint the hypervisor */ if ((value1 & CIABR_PRIV) == CIABR_PRIV_HYPER) return H_P3; - vcpu->arch.ciabr = value1; + kvmppc_set_ciabr_hv(vcpu, value1); return H_SUCCESS; - case H_SET_MODE_RESOURCE_SET_DAWR: + case H_SET_MODE_RESOURCE_SET_DAWR0: if (!kvmppc_power8_compatible(vcpu)) return H_P2; if (!ppc_breakpoint_available()) @@ -779,12 +907,32 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, return H_UNSUPPORTED_FLAG_START; if (value2 & DABRX_HYP) return H_P4; - vcpu->arch.dawr = value1; - vcpu->arch.dawrx = value2; + kvmppc_set_dawr0_hv(vcpu, value1); + kvmppc_set_dawrx0_hv(vcpu, value2); + return H_SUCCESS; + case H_SET_MODE_RESOURCE_SET_DAWR1: + if (!kvmppc_power8_compatible(vcpu)) + return H_P2; + if (!ppc_breakpoint_available()) + return H_P2; + if (!cpu_has_feature(CPU_FTR_DAWR1)) + return H_P2; + if (!vcpu->kvm->arch.dawr1_enabled) + return H_FUNCTION; + if (mflags) + return H_UNSUPPORTED_FLAG_START; + if (value2 & DABRX_HYP) + return H_P4; + kvmppc_set_dawr1_hv(vcpu, value1); + kvmppc_set_dawrx1_hv(vcpu, value2); return H_SUCCESS; case H_SET_MODE_RESOURCE_ADDR_TRANS_MODE: - /* KVM does not support mflags=2 (AIL=2) */ - if (mflags != 0 && mflags != 3) + /* + * KVM does not support mflags=2 (AIL=2) and AIL=1 is reserved. + * Keep this in synch with kvmppc_filter_guest_lpcr_hv. + */ + if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG) && + kvmhv_vcpu_is_radix(vcpu) && mflags == 3) return H_UNSUPPORTED_FLAG_START; return H_TOO_HARD; default: @@ -876,14 +1024,19 @@ static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target) * H_SUCCESS if the source vcore wasn't idle (e.g. if it may * have useful work to do and should not confer) so we don't * recheck that here. + * + * In the case of the P9 single vcpu per vcore case, the real + * mode handler is not called but no other threads are in the + * source vcore. */ - - spin_lock(&vcore->lock); - if (target->arch.state == KVMPPC_VCPU_RUNNABLE && - vcore->vcore_state != VCORE_INACTIVE && - vcore->runner) - target = vcore->runner; - spin_unlock(&vcore->lock); + if (!cpu_has_feature(CPU_FTR_ARCH_300)) { + spin_lock(&vcore->lock); + if (target->arch.state == KVMPPC_VCPU_RUNNABLE && + vcore->vcore_state != VCORE_INACTIVE && + vcore->runner) + target = vcore->runner; + spin_unlock(&vcore->lock); + } return kvm_vcpu_yield_to(target); } @@ -901,8 +1054,71 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu) return yield_count; } +/* + * H_RPT_INVALIDATE hcall handler for nested guests. + * + * Handles only nested process-scoped invalidation requests in L0. + */ +static int kvmppc_nested_h_rpt_invalidate(struct kvm_vcpu *vcpu) +{ + unsigned long type = kvmppc_get_gpr(vcpu, 6); + unsigned long pid, pg_sizes, start, end; + + /* + * The partition-scoped invalidations aren't handled here in L0. + */ + if (type & H_RPTI_TYPE_NESTED) + return RESUME_HOST; + + pid = kvmppc_get_gpr(vcpu, 4); + pg_sizes = kvmppc_get_gpr(vcpu, 7); + start = kvmppc_get_gpr(vcpu, 8); + end = kvmppc_get_gpr(vcpu, 9); + + do_h_rpt_invalidate_prt(pid, vcpu->arch.nested->shadow_lpid, + type, pg_sizes, start, end); + + kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + return RESUME_GUEST; +} + +static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu, + unsigned long id, unsigned long target, + unsigned long type, unsigned long pg_sizes, + unsigned long start, unsigned long end) +{ + if (!kvm_is_radix(vcpu->kvm)) + return H_UNSUPPORTED; + + if (end < start) + return H_P5; + + /* + * Partition-scoped invalidation for nested guests. + */ + if (type & H_RPTI_TYPE_NESTED) { + if (!nesting_enabled(vcpu->kvm)) + return H_FUNCTION; + + /* Support only cores as target */ + if (target != H_RPTI_TARGET_CMMU) + return H_P2; + + return do_h_rpt_invalidate_pat(vcpu, id, type, pg_sizes, + start, end); + } + + /* + * Process-scoped invalidation for L1 guests. + */ + do_h_rpt_invalidate_prt(id, vcpu->kvm->arch.lpid, + type, pg_sizes, start, end); + return H_SUCCESS; +} + int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) { + struct kvm *kvm = vcpu->kvm; unsigned long req = kvmppc_get_gpr(vcpu, 3); unsigned long target, ret = H_SUCCESS; int yield_count; @@ -914,17 +1130,63 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) return RESUME_HOST; switch (req) { + case H_REMOVE: + ret = kvmppc_h_remove(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_ENTER: + ret = kvmppc_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6), + kvmppc_get_gpr(vcpu, 7)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_READ: + ret = kvmppc_h_read(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_CLEAR_MOD: + ret = kvmppc_h_clear_mod(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_CLEAR_REF: + ret = kvmppc_h_clear_ref(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_PROTECT: + ret = kvmppc_h_protect(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_BULK_REMOVE: + ret = kvmppc_h_bulk_remove(vcpu); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_CEDE: break; case H_PROD: target = kvmppc_get_gpr(vcpu, 4); - tvcpu = kvmppc_find_vcpu(vcpu->kvm, target); + tvcpu = kvmppc_find_vcpu(kvm, target); if (!tvcpu) { ret = H_PARAMETER; break; } tvcpu->arch.prodded = 1; - smp_mb(); + smp_mb(); /* This orders prodded store vs ceded load */ if (tvcpu->arch.ceded) kvmppc_fast_vcpu_kick_hv(tvcpu); break; @@ -932,7 +1194,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) target = kvmppc_get_gpr(vcpu, 4); if (target == -1) break; - tvcpu = kvmppc_find_vcpu(vcpu->kvm, target); + tvcpu = kvmppc_find_vcpu(kvm, target); if (!tvcpu) { ret = H_PARAMETER; break; @@ -948,12 +1210,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) kvmppc_get_gpr(vcpu, 6)); break; case H_RTAS: - if (list_empty(&vcpu->kvm->arch.rtas_tokens)) + if (list_empty(&kvm->arch.rtas_tokens)) return RESUME_HOST; - idx = srcu_read_lock(&vcpu->kvm->srcu); + idx = srcu_read_lock(&kvm->srcu); rc = kvmppc_rtas_hcall(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); + srcu_read_unlock(&kvm->srcu, idx); if (rc == -ENOENT) return RESUME_HOST; @@ -1033,19 +1295,31 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) return RESUME_HOST; break; #endif - case H_RANDOM: - if (!powernv_get_random_long(&vcpu->arch.regs.gpr[4])) + case H_RANDOM: { + unsigned long rand; + + if (!arch_get_random_seed_longs(&rand, 1)) ret = H_HARDWARE; + kvmppc_set_gpr(vcpu, 4, rand); + break; + } + case H_RPT_INVALIDATE: + ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6), + kvmppc_get_gpr(vcpu, 7), + kvmppc_get_gpr(vcpu, 8), + kvmppc_get_gpr(vcpu, 9)); break; case H_SET_PARTITION_TABLE: ret = H_FUNCTION; - if (nesting_enabled(vcpu->kvm)) + if (nesting_enabled(kvm)) ret = kvmhv_set_partition_table(vcpu); break; case H_ENTER_NESTED: ret = H_FUNCTION; - if (!nesting_enabled(vcpu->kvm)) + if (!nesting_enabled(kvm)) break; ret = kvmhv_enter_nested_guest(vcpu); if (ret == H_INTERRUPT) { @@ -1060,12 +1334,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) break; case H_TLB_INVALIDATE: ret = H_FUNCTION; - if (nesting_enabled(vcpu->kvm)) + if (nesting_enabled(kvm)) ret = kvmhv_do_nested_tlbie(vcpu); break; case H_COPY_TOFROM_GUEST: ret = H_FUNCTION; - if (nesting_enabled(vcpu->kvm)) + if (nesting_enabled(kvm)) ret = kvmhv_copy_tofrom_guest_nested(vcpu); break; case H_PAGE_INIT: @@ -1074,41 +1348,61 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) kvmppc_get_gpr(vcpu, 6)); break; case H_SVM_PAGE_IN: - ret = kvmppc_h_svm_page_in(vcpu->kvm, - kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5), - kvmppc_get_gpr(vcpu, 6)); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_page_in(kvm, + kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); break; case H_SVM_PAGE_OUT: - ret = kvmppc_h_svm_page_out(vcpu->kvm, - kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5), - kvmppc_get_gpr(vcpu, 6)); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_page_out(kvm, + kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); break; case H_SVM_INIT_START: - ret = kvmppc_h_svm_init_start(vcpu->kvm); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_init_start(kvm); break; case H_SVM_INIT_DONE: - ret = kvmppc_h_svm_init_done(vcpu->kvm); + ret = H_UNSUPPORTED; + if (kvmppc_get_srr1(vcpu) & MSR_S) + ret = kvmppc_h_svm_init_done(kvm); + break; + case H_SVM_INIT_ABORT: + /* + * Even if that call is made by the Ultravisor, the SSR1 value + * is the guest context one, with the secure bit clear as it has + * not yet been secured. So we can't check it here. + * Instead the kvm->arch.secure_guest flag is checked inside + * kvmppc_h_svm_init_abort(). + */ + ret = kvmppc_h_svm_init_abort(kvm); break; default: return RESUME_HOST; } + WARN_ON_ONCE(ret == H_TOO_HARD); kvmppc_set_gpr(vcpu, 3, ret); vcpu->arch.hcall_needed = 0; return RESUME_GUEST; } /* - * Handle H_CEDE in the nested virtualization case where we haven't - * called the real-mode hcall handlers in book3s_hv_rmhandlers.S. + * Handle H_CEDE in the P9 path where we don't call the real-mode hcall + * handlers in book3s_hv_rmhandlers.S. + * * This has to be done early, not in kvmppc_pseries_do_hcall(), so * that the cede logic in kvmppc_run_single_vcpu() works properly. */ -static void kvmppc_nested_cede(struct kvm_vcpu *vcpu) +static void kvmppc_cede(struct kvm_vcpu *vcpu) { - vcpu->arch.shregs.msr |= MSR_EE; + __kvmppc_set_msr_hv(vcpu, __kvmppc_get_msr_hv(vcpu) | MSR_EE); vcpu->arch.ceded = 1; smp_mb(); if (vcpu->arch.prodded) { @@ -1126,6 +1420,12 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd) case H_CONFER: case H_REGISTER_VPA: case H_SET_MODE: +#ifdef CONFIG_SPAPR_TCE_IOMMU + case H_GET_TCE: + case H_PUT_TCE: + case H_PUT_TCE_INDIRECT: + case H_STUFF_TCE: +#endif case H_LOGICAL_CI_LOAD: case H_LOGICAL_CI_STORE: #ifdef CONFIG_KVM_XICS @@ -1137,6 +1437,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd) case H_XIRR_X: #endif case H_PAGE_INIT: + case H_RPT_INVALIDATE: return 1; } @@ -1144,10 +1445,9 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd) return kvmppc_hcall_impl_hv_realmode(cmd); } -static int kvmppc_emulate_debug_inst(struct kvm_run *run, - struct kvm_vcpu *vcpu) +static int kvmppc_emulate_debug_inst(struct kvm_vcpu *vcpu) { - u32 last_inst; + ppc_inst_t last_inst; if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst) != EMULATE_DONE) { @@ -1158,12 +1458,13 @@ static int kvmppc_emulate_debug_inst(struct kvm_run *run, return RESUME_GUEST; } - if (last_inst == KVMPPC_INST_SW_BREAKPOINT) { - run->exit_reason = KVM_EXIT_DEBUG; - run->debug.arch.address = kvmppc_get_pc(vcpu); + if (ppc_inst_val(last_inst) == KVMPPC_INST_SW_BREAKPOINT) { + vcpu->run->exit_reason = KVM_EXIT_DEBUG; + vcpu->run->debug.arch.address = kvmppc_get_pc(vcpu); return RESUME_HOST; } else { - kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED)); return RESUME_GUEST; } } @@ -1211,9 +1512,11 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu) unsigned long arg; struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tvcpu; + ppc_inst_t pinst; - if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst) != EMULATE_DONE) + if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst) != EMULATE_DONE) return RESUME_GUEST; + inst = ppc_inst_val(pinst); if (get_op(inst) != 31) return EMULATE_FAIL; rb = get_rb(inst); @@ -1221,9 +1524,9 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu) switch (get_xop(inst)) { case OP_31_XOP_MSGSNDP: arg = kvmppc_get_gpr(vcpu, rb); - if (((arg >> 27) & 0xf) != PPC_DBELL_SERVER) + if (((arg >> 27) & 0x1f) != PPC_DBELL_SERVER) break; - arg &= 0x3f; + arg &= 0x7f; if (arg >= kvm->arch.emul_smt_mode) break; tvcpu = kvmppc_find_vcpu(kvm, vcpu->vcpu_id - thr + arg); @@ -1236,7 +1539,7 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu) break; case OP_31_XOP_MSGCLRP: arg = kvmppc_get_gpr(vcpu, rb); - if (((arg >> 27) & 0xf) != PPC_DBELL_SERVER) + if (((arg >> 27) & 0x1f) != PPC_DBELL_SERVER) break; vcpu->arch.vcore->dpdes = 0; vcpu->arch.doorbell_request = 0; @@ -1261,9 +1564,47 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu) return RESUME_GUEST; } -static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, +/* + * If the lppaca had pmcregs_in_use clear when we exited the guest, then + * HFSCR_PM is cleared for next entry. If the guest then tries to access + * the PMU SPRs, we get this facility unavailable interrupt. Putting HFSCR_PM + * back in the guest HFSCR will cause the next entry to load the PMU SPRs and + * allow the guest access to continue. + */ +static int kvmppc_pmu_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_PM)) + return EMULATE_FAIL; + + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_PM); + + return RESUME_GUEST; +} + +static int kvmppc_ebb_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_EBB)) + return EMULATE_FAIL; + + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_EBB); + + return RESUME_GUEST; +} + +static int kvmppc_tm_unavailable(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hfscr_permitted & HFSCR_TM)) + return EMULATE_FAIL; + + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_TM); + + return RESUME_GUEST; +} + +static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, struct task_struct *tsk) { + struct kvm_run *run = vcpu->run; int r = RESUME_HOST; vcpu->stat.sum_exits++; @@ -1276,7 +1617,7 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, * That can happen due to a bug, or due to a machine check * occurring at just the wrong time. */ - if (vcpu->arch.shregs.msr & MSR_HV) { + if (!kvmhv_is_nestedv2() && (__kvmppc_get_msr_hv(vcpu) & MSR_HV)) { printk(KERN_EMERG "KVM trap in HV mode!\n"); printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n", vcpu->arch.trap, kvmppc_get_pc(vcpu), @@ -1290,6 +1631,10 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, run->ready_for_interrupt_injection = 1; switch (vcpu->arch.trap) { /* We're good on these - the host merely wanted to get our attention */ + case BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER: + WARN_ON_ONCE(1); /* Should never happen */ + vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; + fallthrough; case BOOK3S_INTERRUPT_HV_DECREMENTER: vcpu->stat.dec_exits++; r = RESUME_GUEST; @@ -1306,9 +1651,15 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, case BOOK3S_INTERRUPT_SYSTEM_RESET: r = RESUME_GUEST; break; - case BOOK3S_INTERRUPT_MACHINE_CHECK: - /* Print the MCE event to host console. */ - machine_check_print_event_info(&vcpu->arch.mce_evt, false, true); + case BOOK3S_INTERRUPT_MACHINE_CHECK: { + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + /* + * Print the MCE event to host console. Ratelimit so the guest + * can't flood the host log. + */ + if (__ratelimit(&rs)) + machine_check_print_event_info(&vcpu->arch.mce_evt,false, true); /* * If the guest can do FWNMI, exit to userspace so it can @@ -1317,7 +1668,8 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, * so that it knows that the machine check occurred. */ if (!vcpu->kvm->arch.fwnmi_enabled) { - ulong flags = vcpu->arch.shregs.msr & 0x083c0000; + ulong flags = (__kvmppc_get_msr_hv(vcpu) & 0x083c0000) | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED); kvmppc_core_queue_machine_check(vcpu, flags); r = RESUME_GUEST; break; @@ -1336,6 +1688,7 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, r = RESUME_HOST; break; + } case BOOK3S_INTERRUPT_PROGRAM: { ulong flags; @@ -1345,20 +1698,47 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, * as a result of a hypervisor emulation interrupt * (e40) getting turned into a 700 by BML RTAS. */ - flags = vcpu->arch.shregs.msr & 0x1f0000ull; + flags = (__kvmppc_get_msr_hv(vcpu) & 0x1f0000ull) | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED); kvmppc_core_queue_program(vcpu, flags); r = RESUME_GUEST; break; } case BOOK3S_INTERRUPT_SYSCALL: { - /* hcall - punt to userspace */ int i; - /* hypercall with MSR_PR has already been handled in rmode, - * and never reaches here. - */ + if (!kvmhv_is_nestedv2() && unlikely(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) { + /* + * Guest userspace executed sc 1. This can only be + * reached by the P9 path because the old path + * handles this case in realmode hcall handlers. + */ + if (!kvmhv_vcpu_is_radix(vcpu)) { + /* + * A guest could be running PR KVM, so this + * may be a PR KVM hcall. It must be reflected + * to the guest kernel as a sc interrupt. + */ + kvmppc_core_queue_syscall(vcpu); + } else { + /* + * Radix guests can not run PR KVM or nested HV + * hash guests which might run PR KVM, so this + * is always a privilege fault. Send a program + * check to guest kernel. + */ + kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV); + } + r = RESUME_GUEST; + break; + } + /* + * hcall - gather args and set exit_reason. This will next be + * handled by kvmppc_pseries_do_hcall which may be able to deal + * with it and resume guest, or may punt to userspace. + */ run->papr_hcall.nr = kvmppc_get_gpr(vcpu, 3); for (i = 0; i < 9; ++i) run->papr_hcall.args[i] = kvmppc_get_gpr(vcpu, 4 + i); @@ -1371,20 +1751,107 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, * We get these next two if the guest accesses a page which it thinks * it has mapped but which is not actually present, either because * it is for an emulated I/O device or because the corresonding - * host page has been paged out. Any other HDSI/HISI interrupts - * have been handled already. + * host page has been paged out. + * + * Any other HDSI/HISI interrupts have been handled already for P7/8 + * guests. For POWER9 hash guests not using rmhandlers, basic hash + * fault handling is done here. */ - case BOOK3S_INTERRUPT_H_DATA_STORAGE: - r = RESUME_PAGE_FAULT; + case BOOK3S_INTERRUPT_H_DATA_STORAGE: { + unsigned long vsid; + long err; + + if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG) && + unlikely(vcpu->arch.fault_dsisr == HDSISR_CANARY)) { + r = RESUME_GUEST; /* Just retry if it's the canary */ + break; + } + + if (kvm_is_radix(vcpu->kvm) || !cpu_has_feature(CPU_FTR_ARCH_300)) { + /* + * Radix doesn't require anything, and pre-ISAv3.0 hash + * already attempted to handle this in rmhandlers. The + * hash fault handling below is v3 only (it uses ASDR + * via fault_gpa). + */ + r = RESUME_PAGE_FAULT; + break; + } + + if (!(vcpu->arch.fault_dsisr & (DSISR_NOHPTE | DSISR_PROTFAULT))) { + kvmppc_core_queue_data_storage(vcpu, + kvmppc_get_msr(vcpu) & SRR1_PREFIXED, + vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); + r = RESUME_GUEST; + break; + } + + if (!(__kvmppc_get_msr_hv(vcpu) & MSR_DR)) + vsid = vcpu->kvm->arch.vrma_slb_v; + else + vsid = vcpu->arch.fault_gpa; + + err = kvmppc_hpte_hv_fault(vcpu, vcpu->arch.fault_dar, + vsid, vcpu->arch.fault_dsisr, true); + if (err == 0) { + r = RESUME_GUEST; + } else if (err == -1 || err == -2) { + r = RESUME_PAGE_FAULT; + } else { + kvmppc_core_queue_data_storage(vcpu, + kvmppc_get_msr(vcpu) & SRR1_PREFIXED, + vcpu->arch.fault_dar, err); + r = RESUME_GUEST; + } break; - case BOOK3S_INTERRUPT_H_INST_STORAGE: + } + case BOOK3S_INTERRUPT_H_INST_STORAGE: { + unsigned long vsid; + long err; + vcpu->arch.fault_dar = kvmppc_get_pc(vcpu); - vcpu->arch.fault_dsisr = vcpu->arch.shregs.msr & + vcpu->arch.fault_dsisr = __kvmppc_get_msr_hv(vcpu) & DSISR_SRR1_MATCH_64S; - if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE) - vcpu->arch.fault_dsisr |= DSISR_ISSTORE; - r = RESUME_PAGE_FAULT; + if (kvm_is_radix(vcpu->kvm) || !cpu_has_feature(CPU_FTR_ARCH_300)) { + /* + * Radix doesn't require anything, and pre-ISAv3.0 hash + * already attempted to handle this in rmhandlers. The + * hash fault handling below is v3 only (it uses ASDR + * via fault_gpa). + */ + if (__kvmppc_get_msr_hv(vcpu) & HSRR1_HISI_WRITE) + vcpu->arch.fault_dsisr |= DSISR_ISSTORE; + r = RESUME_PAGE_FAULT; + break; + } + + if (!(vcpu->arch.fault_dsisr & SRR1_ISI_NOPT)) { + kvmppc_core_queue_inst_storage(vcpu, + vcpu->arch.fault_dsisr | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED)); + r = RESUME_GUEST; + break; + } + + if (!(__kvmppc_get_msr_hv(vcpu) & MSR_IR)) + vsid = vcpu->kvm->arch.vrma_slb_v; + else + vsid = vcpu->arch.fault_gpa; + + err = kvmppc_hpte_hv_fault(vcpu, vcpu->arch.fault_dar, + vsid, vcpu->arch.fault_dsisr, false); + if (err == 0) { + r = RESUME_GUEST; + } else if (err == -1) { + r = RESUME_PAGE_FAULT; + } else { + kvmppc_core_queue_inst_storage(vcpu, + err | (kvmppc_get_msr(vcpu) & SRR1_PREFIXED)); + r = RESUME_GUEST; + } break; + } + /* * This occurs if the guest executes an illegal instruction. * If the guest debug is disabled, generate a program interrupt @@ -1398,12 +1865,28 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, swab32(vcpu->arch.emul_inst) : vcpu->arch.emul_inst; if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) { - r = kvmppc_emulate_debug_inst(run, vcpu); + r = kvmppc_emulate_debug_inst(vcpu); } else { - kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED)); r = RESUME_GUEST; } break; + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + case BOOK3S_INTERRUPT_HV_SOFTPATCH: + /* + * This occurs for various TM-related instructions that + * we need to emulate on POWER9 DD2.2. We have already + * handled the cases where the guest was in real-suspend + * mode and was transitioning to transactional state. + */ + r = kvmhv_p9_tm_emulation(vcpu); + if (r != -1) + break; + fallthrough; /* go to facility unavailable handler */ +#endif + /* * This occurs if the guest (kernel or userspace), does something that * is prohibited by HFSCR. @@ -1411,28 +1894,27 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, * to emulate. * Otherwise, we just generate a program interrupt to the guest. */ - case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: + case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: { + u64 cause = kvmppc_get_hfscr_hv(vcpu) >> 56; + r = EMULATE_FAIL; - if (((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) && - cpu_has_feature(CPU_FTR_ARCH_300)) - r = kvmppc_emulate_doorbell_instr(vcpu); + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (cause == FSCR_MSGP_LG) + r = kvmppc_emulate_doorbell_instr(vcpu); + if (cause == FSCR_PM_LG) + r = kvmppc_pmu_unavailable(vcpu); + if (cause == FSCR_EBB_LG) + r = kvmppc_ebb_unavailable(vcpu); + if (cause == FSCR_TM_LG) + r = kvmppc_tm_unavailable(vcpu); + } if (r == EMULATE_FAIL) { - kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED)); r = RESUME_GUEST; } break; - -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - case BOOK3S_INTERRUPT_HV_SOFTPATCH: - /* - * This occurs for various TM-related instructions that - * we need to emulate on POWER9 DD2.2. We have already - * handled the cases where the guest was in real-suspend - * mode and was transitioning to transactional state. - */ - r = kvmhv_p9_tm_emulation(vcpu); - break; -#endif + } case BOOK3S_INTERRUPT_HV_RM_HARD: r = RESUME_PASSTHROUGH; @@ -1441,7 +1923,7 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, kvmppc_dump_regs(vcpu); printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n", vcpu->arch.trap, kvmppc_get_pc(vcpu), - vcpu->arch.shregs.msr); + __kvmppc_get_msr_hv(vcpu)); run->hw.hardware_exit_reason = vcpu->arch.trap; r = RESUME_HOST; break; @@ -1450,7 +1932,7 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, return r; } -static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) +static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) { int r; int srcu_idx; @@ -1465,11 +1947,11 @@ static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) * That can happen due to a bug, or due to a machine check * occurring at just the wrong time. */ - if (vcpu->arch.shregs.msr & MSR_HV) { + if (__kvmppc_get_msr_hv(vcpu) & MSR_HV) { pr_emerg("KVM trap in HV mode while nested!\n"); pr_emerg("trap=0x%x | pc=0x%lx | msr=0x%llx\n", vcpu->arch.trap, kvmppc_get_pc(vcpu), - vcpu->arch.shregs.msr); + __kvmppc_get_msr_hv(vcpu)); kvmppc_dump_regs(vcpu); return RESUME_HOST; } @@ -1488,6 +1970,12 @@ static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) vcpu->stat.ext_intr_exits++; r = RESUME_GUEST; break; + /* These need to go to the nested HV */ + case BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER: + vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER; + vcpu->stat.dec_exits++; + r = RESUME_HOST; + break; /* SR/HMI/PMI are HV interrupts that host has handled. Resume guest.*/ case BOOK3S_INTERRUPT_HMI: case BOOK3S_INTERRUPT_PERFMON: @@ -1495,11 +1983,16 @@ static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) r = RESUME_GUEST; break; case BOOK3S_INTERRUPT_MACHINE_CHECK: + { + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); /* Pass the machine check to the L1 guest */ r = RESUME_HOST; /* Print the MCE event to host console. */ - machine_check_print_event_info(&vcpu->arch.mce_evt, false, true); + if (__ratelimit(&rs)) + machine_check_print_event_info(&vcpu->arch.mce_evt, false, true); break; + } /* * We get these next two if the guest accesses a page which it thinks * it has mapped but which is not actually present, either because @@ -1508,17 +2001,17 @@ static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) */ case BOOK3S_INTERRUPT_H_DATA_STORAGE: srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvmhv_nested_page_fault(run, vcpu); + r = kvmhv_nested_page_fault(vcpu); srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); break; case BOOK3S_INTERRUPT_H_INST_STORAGE: vcpu->arch.fault_dar = kvmppc_get_pc(vcpu); vcpu->arch.fault_dsisr = kvmppc_get_msr(vcpu) & DSISR_SRR1_MATCH_64S; - if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE) + if (__kvmppc_get_msr_hv(vcpu) & HSRR1_HISI_WRITE) vcpu->arch.fault_dsisr |= DSISR_ISSTORE; srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvmhv_nested_page_fault(run, vcpu); + r = kvmhv_nested_page_fault(vcpu); srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); break; @@ -1531,15 +2024,65 @@ static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) * mode and was transitioning to transactional state. */ r = kvmhv_p9_tm_emulation(vcpu); - break; + if (r != -1) + break; + fallthrough; /* go to facility unavailable handler */ #endif + case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: { + u64 cause = vcpu->arch.hfscr >> 56; + + /* + * Only pass HFU interrupts to the L1 if the facility is + * permitted but disabled by the L1's HFSCR, otherwise + * the interrupt does not make sense to the L1 so turn + * it into a HEAI. + */ + if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) || + (vcpu->arch.nested_hfscr & (1UL << cause))) { + ppc_inst_t pinst; + vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST; + + /* + * If the fetch failed, return to guest and + * try executing it again. + */ + r = kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst); + vcpu->arch.emul_inst = ppc_inst_val(pinst); + if (r != EMULATE_DONE) + r = RESUME_GUEST; + else + r = RESUME_HOST; + } else { + r = RESUME_HOST; + } + + break; + } + case BOOK3S_INTERRUPT_HV_RM_HARD: vcpu->arch.trap = 0; r = RESUME_GUEST; if (!xics_on_xive()) kvmppc_xics_rm_complete(vcpu, 0); break; + case BOOK3S_INTERRUPT_SYSCALL: + { + unsigned long req = kvmppc_get_gpr(vcpu, 3); + + /* + * The H_RPT_INVALIDATE hcalls issued by nested + * guests for process-scoped invalidations when + * GTSE=0, are handled here in L0. + */ + if (req == H_RPT_INVALIDATE) { + r = kvmppc_nested_h_rpt_invalidate(vcpu); + break; + } + + r = RESUME_HOST; + break; + } default: r = RESUME_HOST; break; @@ -1585,6 +2128,49 @@ static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu, return 0; } +/* + * Enforce limits on guest LPCR values based on hardware availability, + * guest configuration, and possibly hypervisor support and security + * concerns. + */ +unsigned long kvmppc_filter_lpcr_hv(struct kvm *kvm, unsigned long lpcr) +{ + /* LPCR_TC only applies to HPT guests */ + if (kvm_is_radix(kvm)) + lpcr &= ~LPCR_TC; + + /* On POWER8 and above, userspace can modify AIL */ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + lpcr &= ~LPCR_AIL; + if ((lpcr & LPCR_AIL) != LPCR_AIL_3) + lpcr &= ~LPCR_AIL; /* LPCR[AIL]=1/2 is disallowed */ + /* + * On some POWER9s we force AIL off for radix guests to prevent + * executing in MSR[HV]=1 mode with the MMU enabled and PIDR set to + * guest, which can result in Q0 translations with LPID=0 PID=PIDR to + * be cached, which the host TLB management does not expect. + */ + if (kvm_is_radix(kvm) && cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) + lpcr &= ~LPCR_AIL; + + /* + * On POWER9, allow userspace to enable large decrementer for the + * guest, whether or not the host has it enabled. + */ + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + lpcr &= ~LPCR_LD; + + return lpcr; +} + +static void verify_lpcr(struct kvm *kvm, unsigned long lpcr) +{ + if (lpcr != kvmppc_filter_lpcr_hv(kvm, lpcr)) { + WARN_ONCE(1, "lpcr 0x%lx differs from filtered 0x%lx\n", + lpcr, kvmppc_filter_lpcr_hv(kvm, lpcr)); + } +} + static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, bool preserve_top32) { @@ -1593,13 +2179,30 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, u64 mask; spin_lock(&vc->lock); + + /* + * Userspace can only modify + * DPFD (default prefetch depth), ILE (interrupt little-endian), + * TC (translation control), AIL (alternate interrupt location), + * LD (large decrementer). + * These are subject to restrictions from kvmppc_filter_lcpr_hv(). + */ + mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD; + + /* Broken 32-bit version of LPCR must not clear top bits */ + if (preserve_top32) + mask &= 0xFFFFFFFF; + + new_lpcr = kvmppc_filter_lpcr_hv(kvm, + (vc->lpcr & ~mask) | (new_lpcr & mask)); + /* * If ILE (interrupt little-endian) has changed, update the * MSR_LE bit in the intr_msr for each vcpu in this vcore. */ if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.vcore != vc) @@ -1611,25 +2214,9 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, } } - /* - * Userspace can only modify DPFD (default prefetch depth), - * ILE (interrupt little-endian) and TC (translation control). - * On POWER8 and POWER9 userspace can also modify AIL (alt. interrupt loc.). - */ - mask = LPCR_DPFD | LPCR_ILE | LPCR_TC; - if (cpu_has_feature(CPU_FTR_ARCH_207S)) - mask |= LPCR_AIL; - /* - * On POWER9, allow userspace to enable large decrementer for the - * guest, whether or not the host has it enabled. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) - mask |= LPCR_LD; + vc->lpcr = new_lpcr; + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LPCR); - /* Broken 32-bit version of LPCR must not clear top bits */ - if (preserve_top32) - mask &= 0xFFFFFFFF; - vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask); spin_unlock(&vc->lock); } @@ -1653,46 +2240,64 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.dabrx); break; case KVM_REG_PPC_DSCR: - *val = get_reg_val(id, vcpu->arch.dscr); + *val = get_reg_val(id, kvmppc_get_dscr_hv(vcpu)); break; case KVM_REG_PPC_PURR: - *val = get_reg_val(id, vcpu->arch.purr); + *val = get_reg_val(id, kvmppc_get_purr_hv(vcpu)); break; case KVM_REG_PPC_SPURR: - *val = get_reg_val(id, vcpu->arch.spurr); + *val = get_reg_val(id, kvmppc_get_spurr_hv(vcpu)); break; case KVM_REG_PPC_AMR: - *val = get_reg_val(id, vcpu->arch.amr); + *val = get_reg_val(id, kvmppc_get_amr_hv(vcpu)); break; case KVM_REG_PPC_UAMOR: - *val = get_reg_val(id, vcpu->arch.uamor); + *val = get_reg_val(id, kvmppc_get_uamor_hv(vcpu)); break; - case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS: + case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1: i = id - KVM_REG_PPC_MMCR0; - *val = get_reg_val(id, vcpu->arch.mmcr[i]); + *val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, i)); + break; + case KVM_REG_PPC_MMCR2: + *val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, 2)); + break; + case KVM_REG_PPC_MMCRA: + *val = get_reg_val(id, kvmppc_get_mmcra_hv(vcpu)); + break; + case KVM_REG_PPC_MMCRS: + *val = get_reg_val(id, vcpu->arch.mmcrs); + break; + case KVM_REG_PPC_MMCR3: + *val = get_reg_val(id, kvmppc_get_mmcr_hv(vcpu, 3)); break; case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8: i = id - KVM_REG_PPC_PMC1; - *val = get_reg_val(id, vcpu->arch.pmc[i]); + *val = get_reg_val(id, kvmppc_get_pmc_hv(vcpu, i)); break; case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2: i = id - KVM_REG_PPC_SPMC1; *val = get_reg_val(id, vcpu->arch.spmc[i]); break; case KVM_REG_PPC_SIAR: - *val = get_reg_val(id, vcpu->arch.siar); + *val = get_reg_val(id, kvmppc_get_siar_hv(vcpu)); break; case KVM_REG_PPC_SDAR: - *val = get_reg_val(id, vcpu->arch.sdar); + *val = get_reg_val(id, kvmppc_get_siar_hv(vcpu)); break; case KVM_REG_PPC_SIER: - *val = get_reg_val(id, vcpu->arch.sier); + *val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 0)); + break; + case KVM_REG_PPC_SIER2: + *val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 1)); + break; + case KVM_REG_PPC_SIER3: + *val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 2)); break; case KVM_REG_PPC_IAMR: - *val = get_reg_val(id, vcpu->arch.iamr); + *val = get_reg_val(id, kvmppc_get_iamr_hv(vcpu)); break; case KVM_REG_PPC_PSPB: - *val = get_reg_val(id, vcpu->arch.pspb); + *val = get_reg_val(id, kvmppc_get_pspb_hv(vcpu)); break; case KVM_REG_PPC_DPDES: /* @@ -1701,20 +2306,28 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, * either vcore->dpdes or doorbell_request. * On POWER8, doorbell_request is 0. */ - *val = get_reg_val(id, vcpu->arch.vcore->dpdes | - vcpu->arch.doorbell_request); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + *val = get_reg_val(id, vcpu->arch.doorbell_request); + else + *val = get_reg_val(id, vcpu->arch.vcore->dpdes); break; case KVM_REG_PPC_VTB: - *val = get_reg_val(id, vcpu->arch.vcore->vtb); + *val = get_reg_val(id, kvmppc_get_vtb(vcpu)); break; case KVM_REG_PPC_DAWR: - *val = get_reg_val(id, vcpu->arch.dawr); + *val = get_reg_val(id, kvmppc_get_dawr0_hv(vcpu)); break; case KVM_REG_PPC_DAWRX: - *val = get_reg_val(id, vcpu->arch.dawrx); + *val = get_reg_val(id, kvmppc_get_dawrx0_hv(vcpu)); + break; + case KVM_REG_PPC_DAWR1: + *val = get_reg_val(id, kvmppc_get_dawr1_hv(vcpu)); + break; + case KVM_REG_PPC_DAWRX1: + *val = get_reg_val(id, kvmppc_get_dawrx1_hv(vcpu)); break; case KVM_REG_PPC_CIABR: - *val = get_reg_val(id, vcpu->arch.ciabr); + *val = get_reg_val(id, kvmppc_get_ciabr_hv(vcpu)); break; case KVM_REG_PPC_CSIGR: *val = get_reg_val(id, vcpu->arch.csigr); @@ -1726,13 +2339,13 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.tcscr); break; case KVM_REG_PPC_PID: - *val = get_reg_val(id, vcpu->arch.pid); + *val = get_reg_val(id, kvmppc_get_pid(vcpu)); break; case KVM_REG_PPC_ACOP: *val = get_reg_val(id, vcpu->arch.acop); break; case KVM_REG_PPC_WORT: - *val = get_reg_val(id, vcpu->arch.wort); + *val = get_reg_val(id, kvmppc_get_wort_hv(vcpu)); break; case KVM_REG_PPC_TIDR: *val = get_reg_val(id, vcpu->arch.tid); @@ -1758,14 +2371,14 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, spin_unlock(&vcpu->arch.vpa_update_lock); break; case KVM_REG_PPC_TB_OFFSET: - *val = get_reg_val(id, vcpu->arch.vcore->tb_offset); + *val = get_reg_val(id, kvmppc_get_tb_offset(vcpu)); break; case KVM_REG_PPC_LPCR: case KVM_REG_PPC_LPCR_64: - *val = get_reg_val(id, vcpu->arch.vcore->lpcr); + *val = get_reg_val(id, kvmppc_get_lpcr(vcpu)); break; case KVM_REG_PPC_PPR: - *val = get_reg_val(id, vcpu->arch.ppr); + *val = get_reg_val(id, kvmppc_get_ppr_hv(vcpu)); break; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM case KVM_REG_PPC_TFHAR: @@ -1834,11 +2447,10 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, break; #endif case KVM_REG_PPC_ARCH_COMPAT: - *val = get_reg_val(id, vcpu->arch.vcore->arch_compat); + *val = get_reg_val(id, kvmppc_get_arch_compat(vcpu)); break; case KVM_REG_PPC_DEC_EXPIRY: - *val = get_reg_val(id, vcpu->arch.dec_expires + - vcpu->arch.vcore->tb_offset); + *val = get_reg_val(id, kvmppc_get_dec_expires(vcpu)); break; case KVM_REG_PPC_ONLINE: *val = get_reg_val(id, vcpu->arch.online); @@ -1846,6 +2458,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_PTCR: *val = get_reg_val(id, vcpu->kvm->arch.l1_ptcr); break; + case KVM_REG_PPC_FSCR: + *val = get_reg_val(id, kvmppc_get_fscr_hv(vcpu)); + break; default: r = -EINVAL; break; @@ -1874,64 +2489,91 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP; break; case KVM_REG_PPC_DSCR: - vcpu->arch.dscr = set_reg_val(id, *val); + kvmppc_set_dscr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_PURR: - vcpu->arch.purr = set_reg_val(id, *val); + kvmppc_set_purr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_SPURR: - vcpu->arch.spurr = set_reg_val(id, *val); + kvmppc_set_spurr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_AMR: - vcpu->arch.amr = set_reg_val(id, *val); + kvmppc_set_amr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_UAMOR: - vcpu->arch.uamor = set_reg_val(id, *val); + kvmppc_set_uamor_hv(vcpu, set_reg_val(id, *val)); break; - case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS: + case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1: i = id - KVM_REG_PPC_MMCR0; - vcpu->arch.mmcr[i] = set_reg_val(id, *val); + kvmppc_set_mmcr_hv(vcpu, i, set_reg_val(id, *val)); + break; + case KVM_REG_PPC_MMCR2: + kvmppc_set_mmcr_hv(vcpu, 2, set_reg_val(id, *val)); + break; + case KVM_REG_PPC_MMCRA: + kvmppc_set_mmcra_hv(vcpu, set_reg_val(id, *val)); + break; + case KVM_REG_PPC_MMCRS: + vcpu->arch.mmcrs = set_reg_val(id, *val); + break; + case KVM_REG_PPC_MMCR3: + *val = get_reg_val(id, vcpu->arch.mmcr[3]); break; case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8: i = id - KVM_REG_PPC_PMC1; - vcpu->arch.pmc[i] = set_reg_val(id, *val); + kvmppc_set_pmc_hv(vcpu, i, set_reg_val(id, *val)); break; case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2: i = id - KVM_REG_PPC_SPMC1; vcpu->arch.spmc[i] = set_reg_val(id, *val); break; case KVM_REG_PPC_SIAR: - vcpu->arch.siar = set_reg_val(id, *val); + kvmppc_set_siar_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_SDAR: - vcpu->arch.sdar = set_reg_val(id, *val); + kvmppc_set_sdar_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_SIER: - vcpu->arch.sier = set_reg_val(id, *val); + kvmppc_set_sier_hv(vcpu, 0, set_reg_val(id, *val)); + break; + case KVM_REG_PPC_SIER2: + kvmppc_set_sier_hv(vcpu, 1, set_reg_val(id, *val)); + break; + case KVM_REG_PPC_SIER3: + kvmppc_set_sier_hv(vcpu, 2, set_reg_val(id, *val)); break; case KVM_REG_PPC_IAMR: - vcpu->arch.iamr = set_reg_val(id, *val); + kvmppc_set_iamr_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_PSPB: - vcpu->arch.pspb = set_reg_val(id, *val); + kvmppc_set_pspb_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DPDES: - vcpu->arch.vcore->dpdes = set_reg_val(id, *val); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + vcpu->arch.doorbell_request = set_reg_val(id, *val) & 1; + else + vcpu->arch.vcore->dpdes = set_reg_val(id, *val); break; case KVM_REG_PPC_VTB: - vcpu->arch.vcore->vtb = set_reg_val(id, *val); + kvmppc_set_vtb(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DAWR: - vcpu->arch.dawr = set_reg_val(id, *val); + kvmppc_set_dawr0_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DAWRX: - vcpu->arch.dawrx = set_reg_val(id, *val) & ~DAWRX_HYP; + kvmppc_set_dawrx0_hv(vcpu, set_reg_val(id, *val) & ~DAWRX_HYP); + break; + case KVM_REG_PPC_DAWR1: + kvmppc_set_dawr1_hv(vcpu, set_reg_val(id, *val)); + break; + case KVM_REG_PPC_DAWRX1: + kvmppc_set_dawrx1_hv(vcpu, set_reg_val(id, *val) & ~DAWRX_HYP); break; case KVM_REG_PPC_CIABR: - vcpu->arch.ciabr = set_reg_val(id, *val); + kvmppc_set_ciabr_hv(vcpu, set_reg_val(id, *val)); /* Don't allow setting breakpoints in hypervisor code */ - if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER) - vcpu->arch.ciabr &= ~CIABR_PRIV; /* disable */ + if ((kvmppc_get_ciabr_hv(vcpu) & CIABR_PRIV) == CIABR_PRIV_HYPER) + kvmppc_set_ciabr_hv(vcpu, kvmppc_get_ciabr_hv(vcpu) & ~CIABR_PRIV); break; case KVM_REG_PPC_CSIGR: vcpu->arch.csigr = set_reg_val(id, *val); @@ -1943,13 +2585,13 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.tcscr = set_reg_val(id, *val); break; case KVM_REG_PPC_PID: - vcpu->arch.pid = set_reg_val(id, *val); + kvmppc_set_pid(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_ACOP: vcpu->arch.acop = set_reg_val(id, *val); break; case KVM_REG_PPC_WORT: - vcpu->arch.wort = set_reg_val(id, *val); + kvmppc_set_wort_hv(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_TIDR: vcpu->arch.tid = set_reg_val(id, *val); @@ -1984,10 +2626,25 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len); break; case KVM_REG_PPC_TB_OFFSET: + { /* round up to multiple of 2^24 */ - vcpu->arch.vcore->tb_offset = - ALIGN(set_reg_val(id, *val), 1UL << 24); + u64 tb_offset = ALIGN(set_reg_val(id, *val), 1UL << 24); + + /* + * Now that we know the timebase offset, update the + * decrementer expiry with a guest timebase value. If + * the userspace does not set DEC_EXPIRY, this ensures + * a migrated vcpu at least starts with an expired + * decrementer, which is better than a large one that + * causes a hang. + */ + kvmppc_set_tb_offset(vcpu, tb_offset); + if (!kvmppc_get_dec_expires(vcpu) && tb_offset) + kvmppc_set_dec_expires(vcpu, get_tb() + tb_offset); + + kvmppc_set_tb_offset(vcpu, tb_offset); break; + } case KVM_REG_PPC_LPCR: kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), true); break; @@ -1995,7 +2652,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), false); break; case KVM_REG_PPC_PPR: - vcpu->arch.ppr = set_reg_val(id, *val); + kvmppc_set_ppr_hv(vcpu, set_reg_val(id, *val)); break; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM case KVM_REG_PPC_TFHAR: @@ -2066,8 +2723,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_DEC_EXPIRY: - vcpu->arch.dec_expires = set_reg_val(id, *val) - - vcpu->arch.vcore->tb_offset; + kvmppc_set_dec_expires(vcpu, set_reg_val(id, *val)); break; case KVM_REG_PPC_ONLINE: i = set_reg_val(id, *val); @@ -2080,6 +2736,9 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_PTCR: vcpu->kvm->arch.l1_ptcr = set_reg_val(id, *val); break; + case KVM_REG_PPC_FSCR: + kvmppc_set_fscr_hv(vcpu, set_reg_val(id, *val)); + break; default: r = -EINVAL; break; @@ -2097,7 +2756,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, */ static int threads_per_vcore(struct kvm *kvm) { - if (kvm->arch.threads_indep) + if (cpu_has_feature(CPU_FTR_ARCH_300)) return 1; return threads_per_subcore; } @@ -2113,7 +2772,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int id) spin_lock_init(&vcore->lock); spin_lock_init(&vcore->stoltb_lock); - init_swait_queue_head(&vcore->wq); + rcuwait_init(&vcore->wait); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; vcore->first_vcpuid = id; @@ -2128,11 +2787,21 @@ static struct debugfs_timings_element { const char *name; size_t offset; } timings[] = { +#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING + {"vcpu_entry", offsetof(struct kvm_vcpu, arch.vcpu_entry)}, + {"guest_entry", offsetof(struct kvm_vcpu, arch.guest_entry)}, + {"in_guest", offsetof(struct kvm_vcpu, arch.in_guest)}, + {"guest_exit", offsetof(struct kvm_vcpu, arch.guest_exit)}, + {"vcpu_exit", offsetof(struct kvm_vcpu, arch.vcpu_exit)}, + {"hypercall", offsetof(struct kvm_vcpu, arch.hcall)}, + {"page_fault", offsetof(struct kvm_vcpu, arch.pg_fault)}, +#else {"rm_entry", offsetof(struct kvm_vcpu, arch.rm_entry)}, {"rm_intr", offsetof(struct kvm_vcpu, arch.rm_intr)}, {"rm_exit", offsetof(struct kvm_vcpu, arch.rm_exit)}, {"guest", offsetof(struct kvm_vcpu, arch.guest_time)}, {"cede", offsetof(struct kvm_vcpu, arch.cede_time)}, +#endif }; #define N_TIMINGS (ARRAY_SIZE(timings)) @@ -2249,44 +2918,31 @@ static const struct file_operations debugfs_timings_ops = { }; /* Create a debugfs directory for the vcpu */ -static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id) +static int kvmppc_arch_create_vcpu_debugfs_hv(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) { - char buf[16]; - struct kvm *kvm = vcpu->kvm; - - snprintf(buf, sizeof(buf), "vcpu%u", id); - if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir)) - return; - vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir); - if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir)) - return; - vcpu->arch.debugfs_timings = - debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir, - vcpu, &debugfs_timings_ops); + if (cpu_has_feature(CPU_FTR_ARCH_300) == IS_ENABLED(CONFIG_KVM_BOOK3S_HV_P9_TIMING)) + debugfs_create_file("timings", 0444, debugfs_dentry, vcpu, + &debugfs_timings_ops); + return 0; } #else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */ -static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id) +static int kvmppc_arch_create_vcpu_debugfs_hv(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) { + return 0; } #endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */ -static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, - unsigned int id) +static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu; int err; int core; struct kvmppc_vcore *vcore; + struct kvm *kvm; + unsigned int id; - err = -ENOMEM; - vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); - if (!vcpu) - goto out; - - err = kvm_vcpu_init(vcpu, kvm, id); - if (err) - goto free_vcpu; + kvm = vcpu->kvm; + id = vcpu->vcpu_id; vcpu->arch.shared = &vcpu->arch.shregs; #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE @@ -2300,32 +2956,60 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, vcpu->arch.shared_big_endian = false; #endif #endif - vcpu->arch.mmcr[0] = MMCR0_FC; - vcpu->arch.ctrl = CTRL_RUNLATCH; + + if (kvmhv_is_nestedv2()) { + err = kvmhv_nestedv2_vcpu_create(vcpu, &vcpu->arch.nestedv2_io); + if (err < 0) + return err; + } + + kvmppc_set_mmcr_hv(vcpu, 0, MMCR0_FC); + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + kvmppc_set_mmcr_hv(vcpu, 0, kvmppc_get_mmcr_hv(vcpu, 0) | MMCR0_PMCCEXT); + kvmppc_set_mmcra_hv(vcpu, MMCRA_BHRB_DISABLE); + } + + kvmppc_set_ctrl_hv(vcpu, CTRL_RUNLATCH); /* default to host PVR, since we can't spoof it */ kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR)); spin_lock_init(&vcpu->arch.vpa_update_lock); spin_lock_init(&vcpu->arch.tbacct_lock); vcpu->arch.busy_preempt = TB_NIL; + __kvmppc_set_msr_hv(vcpu, MSR_ME); vcpu->arch.intr_msr = MSR_SF | MSR_ME; /* * Set the default HFSCR for the guest from the host value. - * This value is only used on POWER9. - * On POWER9, we want to virtualize the doorbell facility, so we + * This value is only used on POWER9 and later. + * On >= POWER9, we want to virtualize the doorbell facility, so we * don't set the HFSCR_MSGP bit, and that causes those instructions * to trap and then we emulate them. */ - vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB | - HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP; + kvmppc_set_hfscr_hv(vcpu, HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB | + HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP); + + /* On POWER10 and later, allow prefixed instructions */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_PREFIX); + if (cpu_has_feature(CPU_FTR_HVMODE)) { - vcpu->arch.hfscr &= mfspr(SPRN_HFSCR); + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) & mfspr(SPRN_HFSCR)); + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) - vcpu->arch.hfscr |= HFSCR_TM; + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) | HFSCR_TM); +#endif } if (cpu_has_feature(CPU_FTR_TM_COMP)) vcpu->arch.hfscr |= HFSCR_TM; + vcpu->arch.hfscr_permitted = kvmppc_get_hfscr_hv(vcpu); + + /* + * PM, EBB, TM are demand-faulted so start with it clear. + */ + kvmppc_set_hfscr_hv(vcpu, kvmppc_get_hfscr_hv(vcpu) & ~(HFSCR_PM | HFSCR_EBB | HFSCR_TM)); + kvmppc_mmu_book3s_hv_init(vcpu); vcpu->arch.state = KVMPPC_VCPU_NOTREADY; @@ -2368,7 +3052,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, mutex_unlock(&kvm->lock); if (!vcore) - goto free_vcpu; + return err; spin_lock(&vcore->lock); ++vcore->num_threads; @@ -2381,14 +3065,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, vcpu->arch.cpu_type = KVM_CPU_3S_64; kvmppc_sanity_check(vcpu); - debugfs_vcpu_init(vcpu, id); - - return vcpu; - -free_vcpu: - kmem_cache_free(kvm_vcpu_cache, vcpu); -out: - return ERR_PTR(err); + return 0; } static int kvmhv_set_smt_mode(struct kvm *kvm, unsigned long smt_mode, @@ -2442,8 +3119,8 @@ static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu) unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow); unpin_vpa(vcpu->kvm, &vcpu->arch.vpa); spin_unlock(&vcpu->arch.vpa_update_lock); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(kvm_vcpu_cache, vcpu); + if (kvmhv_is_nestedv2()) + kvmhv_nestedv2_vcpu_free(vcpu, &vcpu->arch.nestedv2_io); } static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu) @@ -2457,13 +3134,13 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu) unsigned long dec_nsec, now; now = get_tb(); - if (now > vcpu->arch.dec_expires) { + if (now > kvmppc_dec_expires_host_tb(vcpu)) { /* decrementer has already gone negative */ kvmppc_core_queue_dec(vcpu); kvmppc_core_prepare_to_enter(vcpu); return; } - dec_nsec = tb_to_ns(vcpu->arch.dec_expires - now); + dec_nsec = tb_to_ns(kvmppc_dec_expires_host_tb(vcpu) - now); hrtimer_start(&vcpu->arch.dec_timer, dec_nsec, HRTIMER_MODE_REL); vcpu->arch.timer_running = 1; } @@ -2471,14 +3148,14 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu) extern int __kvmppc_vcore_entry(void); static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, - struct kvm_vcpu *vcpu) + struct kvm_vcpu *vcpu, u64 tb) { u64 now; if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE) return; spin_lock_irq(&vcpu->arch.tbacct_lock); - now = mftb(); + now = tb; vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) - vcpu->arch.stolen_logged; vcpu->arch.busy_preempt = now; @@ -2533,29 +3210,59 @@ static void kvmppc_release_hwthread(int cpu) tpaca->kvm_hstate.kvm_split_mode = NULL; } +static DEFINE_PER_CPU(struct kvm *, cpu_in_guest); + static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) { struct kvm_nested_guest *nested = vcpu->arch.nested; - cpumask_t *cpu_in_guest; + cpumask_t *need_tlb_flush; int i; - cpu = cpu_first_thread_sibling(cpu); - if (nested) { - cpumask_set_cpu(cpu, &nested->need_tlb_flush); - cpu_in_guest = &nested->cpu_in_guest; - } else { - cpumask_set_cpu(cpu, &kvm->arch.need_tlb_flush); - cpu_in_guest = &kvm->arch.cpu_in_guest; - } + if (nested) + need_tlb_flush = &nested->need_tlb_flush; + else + need_tlb_flush = &kvm->arch.need_tlb_flush; + + cpu = cpu_first_tlb_thread_sibling(cpu); + for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu); + i += cpu_tlb_thread_sibling_step()) + cpumask_set_cpu(i, need_tlb_flush); + /* - * Make sure setting of bit in need_tlb_flush precedes - * testing of cpu_in_guest bits. The matching barrier on - * the other side is the first smp_mb() in kvmppc_run_core(). + * Make sure setting of bit in need_tlb_flush precedes testing of + * cpu_in_guest. The matching barrier on the other side is hwsync + * when switching to guest MMU mode, which happens between + * cpu_in_guest being set to the guest kvm, and need_tlb_flush bit + * being tested. */ smp_mb(); - for (i = 0; i < threads_per_core; ++i) - if (cpumask_test_cpu(cpu + i, cpu_in_guest)) - smp_call_function_single(cpu + i, do_nothing, NULL, 1); + + for (i = cpu; i <= cpu_last_tlb_thread_sibling(cpu); + i += cpu_tlb_thread_sibling_step()) { + struct kvm *running = *per_cpu_ptr(&cpu_in_guest, i); + + if (running == kvm) + smp_call_function_single(i, do_nothing, NULL, 1); + } +} + +static void do_migrate_away_vcpu(void *arg) +{ + struct kvm_vcpu *vcpu = arg; + struct kvm *kvm = vcpu->kvm; + + /* + * If the guest has GTSE, it may execute tlbie, so do a eieio; tlbsync; + * ptesync sequence on the old CPU before migrating to a new one, in + * case we interrupted the guest between a tlbie ; eieio ; + * tlbsync; ptesync sequence. + * + * Otherwise, ptesync is sufficient for ordering tlbiel sequences. + */ + if (kvm->arch.lpcr & LPCR_GTSE) + asm volatile("eieio; tlbsync; ptesync"); + else + asm volatile("ptesync"); } static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) @@ -2581,14 +3288,17 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu) * can move around between pcpus. To cope with this, when * a vcpu moves from one pcpu to another, we need to tell * any vcpus running on the same core as this vcpu previously - * ran to flush the TLB. The TLB is shared between threads, - * so we use a single bit in .need_tlb_flush for all 4 threads. + * ran to flush the TLB. */ if (prev_cpu != pcpu) { - if (prev_cpu >= 0 && - cpu_first_thread_sibling(prev_cpu) != - cpu_first_thread_sibling(pcpu)) - radix_flush_cpu(kvm, prev_cpu, vcpu); + if (prev_cpu >= 0) { + if (cpu_first_tlb_thread_sibling(prev_cpu) != + cpu_first_tlb_thread_sibling(pcpu)) + radix_flush_cpu(kvm, prev_cpu, vcpu); + + smp_call_function_single(prev_cpu, + do_migrate_away_vcpu, vcpu, 1); + } if (nested) nested->prev_cpu[vcpu->arch.nested_vcpu_id] = pcpu; else @@ -2600,7 +3310,6 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) { int cpu; struct paca_struct *tpaca; - struct kvm *kvm = vc->kvm; cpu = vc->pcpu; if (vcpu) { @@ -2611,7 +3320,6 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) cpu += vcpu->arch.ptid; vcpu->cpu = vc->pcpu; vcpu->arch.thread_cpu = cpu; - cpumask_set_cpu(cpu, &kvm->arch.cpu_in_guest); } tpaca = paca_ptrs[cpu]; tpaca->kvm_hstate.kvm_vcpu = vcpu; @@ -2712,6 +3420,8 @@ static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc) { struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores); + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + vc->vcore_state = VCORE_PREEMPT; vc->pcpu = smp_processor_id(); if (vc->num_threads < threads_per_vcore(vc->kvm)) { @@ -2721,14 +3431,16 @@ static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc) } /* Start accumulating stolen time */ - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, mftb()); } static void kvmppc_vcore_end_preempt(struct kvmppc_vcore *vc) { struct preempted_vcore_list *lp; - kvmppc_core_end_stolen(vc); + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); + + kvmppc_core_end_stolen(vc, mftb()); if (!list_empty(&vc->preempt_list)) { lp = &per_cpu(preempted_vcores, vc->pcpu); spin_lock(&lp->lock); @@ -2811,11 +3523,6 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip) if (one_vm_per_core && vc->kvm != cip->vc[0]->kvm) return false; - /* Some POWER9 chips require all threads to be in the same MMU mode */ - if (no_mixing_hpt_and_radix && - kvm_is_radix(vc->kvm) != kvm_is_radix(cip->vc[0]->kvm)) - return false; - if (n_threads < cip->max_subcore_threads) n_threads = cip->max_subcore_threads; if (!subcore_config_ok(cip->n_subcores + 1, n_threads)) @@ -2860,7 +3567,7 @@ static void prepare_threads(struct kvmppc_vcore *vc) vcpu->arch.ret = RESUME_GUEST; else continue; - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } } @@ -2879,7 +3586,7 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) list_del_init(&pvc->preempt_list); if (pvc->runner == NULL) { pvc->vcore_state = VCORE_INACTIVE; - kvmppc_core_end_stolen(pvc); + kvmppc_core_end_stolen(pvc, mftb()); } spin_unlock(&pvc->lock); continue; @@ -2888,7 +3595,7 @@ static void collect_piggybacks(struct core_info *cip, int target_threads) spin_unlock(&pvc->lock); continue; } - kvmppc_core_end_stolen(pvc); + kvmppc_core_end_stolen(pvc, mftb()); pvc->vcore_state = VCORE_PIGGYBACK; if (cip->total_threads >= target_threads) break; @@ -2932,7 +3639,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) */ spin_unlock(&vc->lock); /* cancel pending dec exception if dec is positive */ - if (now < vcpu->arch.dec_expires && + if (now < kvmppc_dec_expires_host_tb(vcpu) && kvmppc_core_pending_dec(vcpu)) kvmppc_core_dequeue_dec(vcpu); @@ -2940,7 +3647,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) ret = RESUME_GUEST; if (vcpu->arch.trap) - ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu, + ret = kvmppc_handle_exit_hv(vcpu, vcpu->arch.run_task); vcpu->arch.ret = ret; @@ -2955,7 +3662,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) else ++still_running; } else { - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } } @@ -2964,7 +3671,7 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) kvmppc_vcore_preempt(vc); } else if (vc->runner) { vc->vcore_state = VCORE_PREEMPT; - kvmppc_core_start_stolen(vc); + kvmppc_core_start_stolen(vc, mftb()); } else { vc->vcore_state = VCORE_INACTIVE; } @@ -3059,7 +3766,9 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) int controlled_threads; int trap; bool is_power8; - bool hpt_on_radix; + + if (WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300))) + return; /* * Remove from the list any threads that have a signal pending @@ -3088,18 +3797,12 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) * Make sure we are running on primary threads, and that secondary * threads are offline. Also check if the number of threads in this * guest are greater than the current system threads per guest. - * On POWER9, we need to be not in independent-threads mode if - * this is a HPT guest on a radix host machine where the - * CPU threads may not be in different MMU modes. */ - hpt_on_radix = no_mixing_hpt_and_radix && radix_enabled() && - !kvm_is_radix(vc->kvm); - if (((controlled_threads > 1) && - ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) || - (hpt_on_radix && vc->kvm->arch.threads_indep)) { + if ((controlled_threads > 1) && + ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) { for_each_runnable_thread(i, vcpu, vc) { vcpu->arch.ret = -EBUSY; - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); wake_up(&vcpu->arch.cpu_run); } goto out; @@ -3118,18 +3821,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) collect_piggybacks(&core_info, target_threads); /* - * On radix, arrange for TLB flushing if necessary. - * This has to be done before disabling interrupts since - * it uses smp_call_function(). - */ - pcpu = smp_processor_id(); - if (kvm_is_radix(vc->kvm)) { - for (sub = 0; sub < core_info.n_subcores; ++sub) - for_each_runnable_thread(i, vcpu, core_info.vc[sub]) - kvmppc_prepare_radix_vcpu(vcpu, pcpu); - } - - /* * Hard-disable interrupts, and check resched flag and signals. * If we need to reschedule or deliver a signal, clean up * and return without going into the guest(s). @@ -3161,10 +3852,9 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) cmd_bit = stat_bit = 0; split = core_info.n_subcores; sip = NULL; - is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S) - && !cpu_has_feature(CPU_FTR_ARCH_300); + is_power8 = cpu_has_feature(CPU_FTR_ARCH_207S); - if (split > 1 || hpt_on_radix) { + if (split > 1) { sip = &split_info; memset(&split_info, 0, sizeof(split_info)); for (sub = 0; sub < core_info.n_subcores; ++sub) @@ -3186,13 +3876,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) split_info.subcore_size = subcore_size; } else { split_info.subcore_size = 1; - if (hpt_on_radix) { - /* Use the split_info for LPCR/LPIDR changes */ - split_info.lpcr_req = vc->lpcr; - split_info.lpidr_req = vc->kvm->arch.lpid; - split_info.host_lpcr = vc->kvm->arch.host_lpcr; - split_info.do_set = 1; - } } /* order writes to split_info before kvm_split_mode pointer */ @@ -3202,7 +3885,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) for (thr = 0; thr < controlled_threads; ++thr) { struct paca_struct *paca = paca_ptrs[pcpu + thr]; - paca->kvm_hstate.tid = thr; paca->kvm_hstate.napping = 0; paca->kvm_hstate.kvm_split_mode = sip; } @@ -3251,8 +3933,16 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) pvc = core_info.vc[sub]; pvc->pcpu = pcpu + thr; for_each_runnable_thread(i, vcpu, pvc) { + /* + * XXX: is kvmppc_start_thread called too late here? + * It updates vcpu->cpu and vcpu->arch.thread_cpu + * which are used by kvmppc_fast_vcpu_kick_hv(), but + * kick is called after new exceptions become available + * and exceptions are checked earlier than here, by + * kvmppc_core_prepare_to_enter. + */ kvmppc_start_thread(vcpu, pvc); - kvmppc_create_dtl_entry(vcpu, pvc); + kvmppc_update_vpa_dispatch(vcpu, pvc); trace_kvm_guest_enter(vcpu); if (!vcpu->arch.ptid) thr0_done = true; @@ -3276,10 +3966,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) * When doing micro-threading, poke the inactive threads as well. * This gets them to the nap instruction after kvm_do_nap, * which reduces the time taken to unsplit later. - * For POWER9 HPT guest on radix host, we need all the secondary - * threads woken up so they can do the LPCR/LPIDR change. */ - if (cmd_bit || hpt_on_radix) { + if (cmd_bit) { split_info.do_nap = 1; /* ask secondaries to nap when done */ for (thr = 1; thr < threads_per_subcore; ++thr) if (!(active & (1 << thr))) @@ -3294,23 +3982,17 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) for (sub = 0; sub < core_info.n_subcores; ++sub) spin_unlock(&core_info.vc[sub]->lock); - guest_enter_irqoff(); + guest_timing_enter_irqoff(); srcu_idx = srcu_read_lock(&vc->kvm->srcu); + guest_state_enter_irqoff(); this_cpu_disable_ftrace(); - /* - * Interrupts will be enabled once we get into the guest, - * so tell lockdep that we're about to enable interrupts. - */ - trace_hardirqs_on(); - trap = __kvmppc_vcore_entry(); - trace_hardirqs_off(); - this_cpu_enable_ftrace(); + guest_state_exit_irqoff(); srcu_read_unlock(&vc->kvm->srcu, srcu_idx); @@ -3340,31 +4022,32 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) cpu_relax(); ++loops; } - } else if (hpt_on_radix) { - /* Wait for all threads to have seen final sync */ - for (thr = 1; thr < controlled_threads; ++thr) { - struct paca_struct *paca = paca_ptrs[pcpu + thr]; - - while (paca->kvm_hstate.kvm_split_mode) { - HMT_low(); - barrier(); - } - HMT_medium(); - } + split_info.do_nap = 0; } - split_info.do_nap = 0; kvmppc_set_host_core(pcpu); + if (!vtime_accounting_enabled_this_cpu()) { + local_irq_enable(); + /* + * Service IRQs here before guest_timing_exit_irqoff() so any + * ticks that occurred while running the guest are accounted to + * the guest. If vtime accounting is enabled, accounting uses + * TB rather than ticks, so it can be done without enabling + * interrupts here, which has the problem that it accounts + * interrupt processing overhead to the host. + */ + local_irq_disable(); + } + guest_timing_exit_irqoff(); + local_irq_enable(); - guest_exit(); /* Let secondaries go back to the offline loop */ for (i = 0; i < controlled_threads; ++i) { kvmppc_release_hwthread(pcpu + i); if (sip && sip->napped[i]) kvmppc_ipi_thread(pcpu + i); - cpumask_clear_cpu(pcpu + i, &vc->kvm->arch.cpu_in_guest); } spin_unlock(&vc->lock); @@ -3386,319 +4069,268 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) trace_kvmppc_run_core(vc, 1); } -/* - * Load up hypervisor-mode registers on P9. - */ -static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit, - unsigned long lpcr) +static inline bool hcall_is_xics(unsigned long req) { - struct kvmppc_vcore *vc = vcpu->arch.vcore; - s64 hdec; - u64 tb, purr, spurr; - int trap; - unsigned long host_hfscr = mfspr(SPRN_HFSCR); - unsigned long host_ciabr = mfspr(SPRN_CIABR); - unsigned long host_dawr = mfspr(SPRN_DAWR); - unsigned long host_dawrx = mfspr(SPRN_DAWRX); - unsigned long host_psscr = mfspr(SPRN_PSSCR); - unsigned long host_pidr = mfspr(SPRN_PID); - - hdec = time_limit - mftb(); - if (hdec < 0) - return BOOK3S_INTERRUPT_HV_DECREMENTER; - mtspr(SPRN_HDEC, hdec); + return req == H_EOI || req == H_CPPR || req == H_IPI || + req == H_IPOLL || req == H_XIRR || req == H_XIRR_X; +} - if (vc->tb_offset) { - u64 new_tb = mftb() + vc->tb_offset; - mtspr(SPRN_TBU40, new_tb); - tb = mftb(); - if ((tb & 0xffffff) < (new_tb & 0xffffff)) - mtspr(SPRN_TBU40, new_tb + 0x1000000); - vc->tb_offset_applied = vc->tb_offset; +static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu) +{ + struct lppaca *lp = vcpu->arch.vpa.pinned_addr; + if (lp) { + u32 yield_count = be32_to_cpu(lp->yield_count) + 1; + lp->yield_count = cpu_to_be32(yield_count); + vcpu->arch.vpa.dirty = 1; } +} - if (vc->pcr) - mtspr(SPRN_PCR, vc->pcr | PCR_MASK); - mtspr(SPRN_DPDES, vc->dpdes); - mtspr(SPRN_VTB, vc->vtb); +static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit, + unsigned long lpcr, u64 *tb) +{ + struct kvmhv_nestedv2_io *io; + unsigned long msr, i; + int trap; + long rc; + + io = &vcpu->arch.nestedv2_io; + + msr = mfmsr(); + kvmppc_msr_hard_disable_set_facilities(vcpu, msr); + if (lazy_irq_pending()) + return 0; + + rc = kvmhv_nestedv2_flush_vcpu(vcpu, time_limit); + if (rc < 0) + return -EINVAL; - local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR); - local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR); - mtspr(SPRN_PURR, vcpu->arch.purr); - mtspr(SPRN_SPURR, vcpu->arch.spurr); + kvmppc_gse_put_u64(io->vcpu_run_input, KVMPPC_GSID_LPCR, lpcr); - if (dawr_enabled()) { - mtspr(SPRN_DAWR, vcpu->arch.dawr); - mtspr(SPRN_DAWRX, vcpu->arch.dawrx); + accumulate_time(vcpu, &vcpu->arch.in_guest); + rc = plpar_guest_run_vcpu(0, vcpu->kvm->arch.lpid, vcpu->vcpu_id, + &trap, &i); + + if (rc != H_SUCCESS) { + pr_err("KVM Guest Run VCPU hcall failed\n"); + if (rc == H_INVALID_ELEMENT_ID) + pr_err("KVM: Guest Run VCPU invalid element id at %ld\n", i); + else if (rc == H_INVALID_ELEMENT_SIZE) + pr_err("KVM: Guest Run VCPU invalid element size at %ld\n", i); + else if (rc == H_INVALID_ELEMENT_VALUE) + pr_err("KVM: Guest Run VCPU invalid element value at %ld\n", i); + return -EINVAL; } - mtspr(SPRN_CIABR, vcpu->arch.ciabr); - mtspr(SPRN_IC, vcpu->arch.ic); - mtspr(SPRN_PID, vcpu->arch.pid); + accumulate_time(vcpu, &vcpu->arch.guest_exit); - mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC | - (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); + *tb = mftb(); + kvmppc_gsm_reset(io->vcpu_message); + kvmppc_gsm_reset(io->vcore_message); + kvmppc_gsbm_zero(&io->valids); - mtspr(SPRN_HFSCR, vcpu->arch.hfscr); + rc = kvmhv_nestedv2_parse_output(vcpu); + if (rc < 0) + return -EINVAL; - mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0); - mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1); - mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2); - mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3); + timer_rearm_host_dec(*tb); - mtspr(SPRN_AMOR, ~0UL); + return trap; +} - mtspr(SPRN_LPCR, lpcr); - isync(); +/* call our hypervisor to load up HV regs and go */ +static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb) +{ + unsigned long host_psscr; + unsigned long msr; + struct hv_guest_state hvregs; + struct p9_host_os_sprs host_os_sprs; + s64 dec; + int trap; - kvmppc_xive_push_vcpu(vcpu); + msr = mfmsr(); - mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0); - mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1); + save_p9_host_os_sprs(&host_os_sprs); - trap = __kvmhv_vcpu_entry_p9(vcpu); + /* + * We need to save and restore the guest visible part of the + * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor + * doesn't do this for us. Note only required if pseries since + * this is done in kvmhv_vcpu_entry_p9() below otherwise. + */ + host_psscr = mfspr(SPRN_PSSCR_PR); - /* Advance host PURR/SPURR by the amount used by guest */ - purr = mfspr(SPRN_PURR); - spurr = mfspr(SPRN_SPURR); - mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr + - purr - vcpu->arch.purr); - mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr + - spurr - vcpu->arch.spurr); - vcpu->arch.purr = purr; - vcpu->arch.spurr = spurr; + kvmppc_msr_hard_disable_set_facilities(vcpu, msr); + if (lazy_irq_pending()) + return 0; - vcpu->arch.ic = mfspr(SPRN_IC); - vcpu->arch.pid = mfspr(SPRN_PID); - vcpu->arch.psscr = mfspr(SPRN_PSSCR) & PSSCR_GUEST_VIS; + if (unlikely(load_vcpu_state(vcpu, &host_os_sprs))) + msr = mfmsr(); /* TM restore can update msr */ - vcpu->arch.shregs.sprg0 = mfspr(SPRN_SPRG0); - vcpu->arch.shregs.sprg1 = mfspr(SPRN_SPRG1); - vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2); - vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3); + if (vcpu->arch.psscr != host_psscr) + mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); - /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ - mtspr(SPRN_PSSCR, host_psscr | - (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); - mtspr(SPRN_HFSCR, host_hfscr); - mtspr(SPRN_CIABR, host_ciabr); - mtspr(SPRN_DAWR, host_dawr); - mtspr(SPRN_DAWRX, host_dawrx); - mtspr(SPRN_PID, host_pidr); + kvmhv_save_hv_regs(vcpu, &hvregs); + hvregs.lpcr = lpcr; + hvregs.amor = ~0; + vcpu->arch.regs.msr = vcpu->arch.shregs.msr; + hvregs.version = HV_GUEST_STATE_VERSION; + if (vcpu->arch.nested) { + hvregs.lpid = vcpu->arch.nested->shadow_lpid; + hvregs.vcpu_token = vcpu->arch.nested_vcpu_id; + } else { + hvregs.lpid = vcpu->kvm->arch.lpid; + hvregs.vcpu_token = vcpu->vcpu_id; + } + hvregs.hdec_expiry = time_limit; /* - * Since this is radix, do a eieio; tlbsync; ptesync sequence in - * case we interrupted the guest between a tlbie and a ptesync. + * When setting DEC, we must always deal with irq_work_raise + * via NMI vs setting DEC. The problem occurs right as we + * switch into guest mode if a NMI hits and sets pending work + * and sets DEC, then that will apply to the guest and not + * bring us back to the host. + * + * irq_work_raise could check a flag (or possibly LPCR[HDICE] + * for example) and set HDEC to 1? That wouldn't solve the + * nested hv case which needs to abort the hcall or zero the + * time limit. + * + * XXX: Another day's problem. */ - asm volatile("eieio; tlbsync; ptesync"); + mtspr(SPRN_DEC, kvmppc_dec_expires_host_tb(vcpu) - *tb); - mtspr(SPRN_LPID, vcpu->kvm->arch.host_lpid); /* restore host LPID */ - isync(); + mtspr(SPRN_DAR, vcpu->arch.shregs.dar); + mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); + switch_pmu_to_guest(vcpu, &host_os_sprs); + accumulate_time(vcpu, &vcpu->arch.in_guest); + trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), + __pa(&vcpu->arch.regs)); + accumulate_time(vcpu, &vcpu->arch.guest_exit); + kvmhv_restore_hv_return_state(vcpu, &hvregs); + switch_pmu_to_host(vcpu, &host_os_sprs); + vcpu->arch.shregs.msr = vcpu->arch.regs.msr; + vcpu->arch.shregs.dar = mfspr(SPRN_DAR); + vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); + vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); + + store_vcpu_state(vcpu); - vc->dpdes = mfspr(SPRN_DPDES); - vc->vtb = mfspr(SPRN_VTB); - mtspr(SPRN_DPDES, 0); - if (vc->pcr) - mtspr(SPRN_PCR, PCR_MASK); + dec = mfspr(SPRN_DEC); + if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ + dec = (s32) dec; + *tb = mftb(); + vcpu->arch.dec_expires = dec + (*tb + kvmppc_get_tb_offset(vcpu)); - if (vc->tb_offset_applied) { - u64 new_tb = mftb() - vc->tb_offset_applied; - mtspr(SPRN_TBU40, new_tb); - tb = mftb(); - if ((tb & 0xffffff) < (new_tb & 0xffffff)) - mtspr(SPRN_TBU40, new_tb + 0x1000000); - vc->tb_offset_applied = 0; - } + timer_rearm_host_dec(*tb); - mtspr(SPRN_HDEC, 0x7fffffff); - mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr); + restore_p9_host_os_sprs(vcpu, &host_os_sprs); + if (vcpu->arch.psscr != host_psscr) + mtspr(SPRN_PSSCR_PR, host_psscr); return trap; } /* - * Virtual-mode guest entry for POWER9 and later when the host and - * guest are both using the radix MMU. The LPIDR has already been set. + * Guest entry for POWER9 and later CPUs. */ -int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, - unsigned long lpcr) +static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, + unsigned long lpcr, u64 *tb) { - struct kvmppc_vcore *vc = vcpu->arch.vcore; - unsigned long host_dscr = mfspr(SPRN_DSCR); - unsigned long host_tidr = mfspr(SPRN_TIDR); - unsigned long host_iamr = mfspr(SPRN_IAMR); - unsigned long host_amr = mfspr(SPRN_AMR); - s64 dec; - u64 tb; - int trap, save_pmu; + struct kvm *kvm = vcpu->kvm; + struct kvm_nested_guest *nested = vcpu->arch.nested; + u64 next_timer; + int trap; - dec = mfspr(SPRN_DEC); - tb = mftb(); - if (dec < 512) + next_timer = timer_get_next_tb(); + if (*tb >= next_timer) return BOOK3S_INTERRUPT_HV_DECREMENTER; - local_paca->kvm_hstate.dec_expires = dec + tb; - if (local_paca->kvm_hstate.dec_expires < time_limit) - time_limit = local_paca->kvm_hstate.dec_expires; + if (next_timer < time_limit) + time_limit = next_timer; + else if (*tb >= time_limit) /* nested time limit */ + return BOOK3S_INTERRUPT_NESTED_HV_DECREMENTER; vcpu->arch.ceded = 0; - kvmhv_save_host_pmu(); /* saves it to PACA kvm_hstate */ - - kvmppc_subcore_enter_guest(); - - vc->entry_exit_map = 1; - vc->in_guest = 1; - - if (vcpu->arch.vpa.pinned_addr) { - struct lppaca *lp = vcpu->arch.vpa.pinned_addr; - u32 yield_count = be32_to_cpu(lp->yield_count) + 1; - lp->yield_count = cpu_to_be32(yield_count); - vcpu->arch.vpa.dirty = 1; - } - - if (cpu_has_feature(CPU_FTR_TM) || - cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) - kvmppc_restore_tm_hv(vcpu, vcpu->arch.shregs.msr, true); - - kvmhv_load_guest_pmu(vcpu); - - msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX); - load_fp_state(&vcpu->arch.fp); -#ifdef CONFIG_ALTIVEC - load_vr_state(&vcpu->arch.vr); -#endif - mtspr(SPRN_VRSAVE, vcpu->arch.vrsave); - - mtspr(SPRN_DSCR, vcpu->arch.dscr); - mtspr(SPRN_IAMR, vcpu->arch.iamr); - mtspr(SPRN_PSPB, vcpu->arch.pspb); - mtspr(SPRN_FSCR, vcpu->arch.fscr); - mtspr(SPRN_TAR, vcpu->arch.tar); - mtspr(SPRN_EBBHR, vcpu->arch.ebbhr); - mtspr(SPRN_EBBRR, vcpu->arch.ebbrr); - mtspr(SPRN_BESCR, vcpu->arch.bescr); - mtspr(SPRN_WORT, vcpu->arch.wort); - mtspr(SPRN_TIDR, vcpu->arch.tid); - mtspr(SPRN_DAR, vcpu->arch.shregs.dar); - mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr); - mtspr(SPRN_AMR, vcpu->arch.amr); - mtspr(SPRN_UAMOR, vcpu->arch.uamor); - - if (!(vcpu->arch.ctrl & 1)) - mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1); - - mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb()); + vcpu_vpa_increment_dispatch(vcpu); if (kvmhv_on_pseries()) { - /* - * We need to save and restore the guest visible part of the - * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor - * doesn't do this for us. Note only required if pseries since - * this is done in kvmhv_load_hv_regs_and_go() below otherwise. - */ - unsigned long host_psscr; - /* call our hypervisor to load up HV regs and go */ - struct hv_guest_state hvregs; - - host_psscr = mfspr(SPRN_PSSCR_PR); - mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr); - kvmhv_save_hv_regs(vcpu, &hvregs); - hvregs.lpcr = lpcr; - vcpu->arch.regs.msr = vcpu->arch.shregs.msr; - hvregs.version = HV_GUEST_STATE_VERSION; - if (vcpu->arch.nested) { - hvregs.lpid = vcpu->arch.nested->shadow_lpid; - hvregs.vcpu_token = vcpu->arch.nested_vcpu_id; - } else { - hvregs.lpid = vcpu->kvm->arch.lpid; - hvregs.vcpu_token = vcpu->vcpu_id; - } - hvregs.hdec_expiry = time_limit; - trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs), - __pa(&vcpu->arch.regs)); - kvmhv_restore_hv_return_state(vcpu, &hvregs); - vcpu->arch.shregs.msr = vcpu->arch.regs.msr; - vcpu->arch.shregs.dar = mfspr(SPRN_DAR); - vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR); - vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR); - mtspr(SPRN_PSSCR_PR, host_psscr); + if (kvmhv_is_nestedv1()) + trap = kvmhv_vcpu_entry_p9_nested(vcpu, time_limit, lpcr, tb); + else + trap = kvmhv_vcpu_entry_nestedv2(vcpu, time_limit, lpcr, tb); /* H_CEDE has to be handled now, not later */ - if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested && + if (trap == BOOK3S_INTERRUPT_SYSCALL && !nested && kvmppc_get_gpr(vcpu, 3) == H_CEDE) { - kvmppc_nested_cede(vcpu); + kvmppc_cede(vcpu); + kvmppc_set_gpr(vcpu, 3, 0); trap = 0; } - } else { - trap = kvmhv_load_hv_regs_and_go(vcpu, time_limit, lpcr); - } - vcpu->arch.slb_max = 0; - dec = mfspr(SPRN_DEC); - if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */ - dec = (s32) dec; - tb = mftb(); - vcpu->arch.dec_expires = dec + tb; - vcpu->cpu = -1; - vcpu->arch.thread_cpu = -1; - vcpu->arch.ctrl = mfspr(SPRN_CTRLF); - - vcpu->arch.iamr = mfspr(SPRN_IAMR); - vcpu->arch.pspb = mfspr(SPRN_PSPB); - vcpu->arch.fscr = mfspr(SPRN_FSCR); - vcpu->arch.tar = mfspr(SPRN_TAR); - vcpu->arch.ebbhr = mfspr(SPRN_EBBHR); - vcpu->arch.ebbrr = mfspr(SPRN_EBBRR); - vcpu->arch.bescr = mfspr(SPRN_BESCR); - vcpu->arch.wort = mfspr(SPRN_WORT); - vcpu->arch.tid = mfspr(SPRN_TIDR); - vcpu->arch.amr = mfspr(SPRN_AMR); - vcpu->arch.uamor = mfspr(SPRN_UAMOR); - vcpu->arch.dscr = mfspr(SPRN_DSCR); - - mtspr(SPRN_PSPB, 0); - mtspr(SPRN_WORT, 0); - mtspr(SPRN_UAMOR, 0); - mtspr(SPRN_DSCR, host_dscr); - mtspr(SPRN_TIDR, host_tidr); - mtspr(SPRN_IAMR, host_iamr); - mtspr(SPRN_PSPB, 0); - - if (host_amr != vcpu->arch.amr) - mtspr(SPRN_AMR, host_amr); - - msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX); - store_fp_state(&vcpu->arch.fp); -#ifdef CONFIG_ALTIVEC - store_vr_state(&vcpu->arch.vr); -#endif - vcpu->arch.vrsave = mfspr(SPRN_VRSAVE); + } else if (nested) { + __this_cpu_write(cpu_in_guest, kvm); + trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr, tb); + __this_cpu_write(cpu_in_guest, NULL); - if (cpu_has_feature(CPU_FTR_TM) || - cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) - kvmppc_save_tm_hv(vcpu, vcpu->arch.shregs.msr, true); + } else { + kvmppc_xive_push_vcpu(vcpu); - save_pmu = 1; - if (vcpu->arch.vpa.pinned_addr) { - struct lppaca *lp = vcpu->arch.vpa.pinned_addr; - u32 yield_count = be32_to_cpu(lp->yield_count) + 1; - lp->yield_count = cpu_to_be32(yield_count); - vcpu->arch.vpa.dirty = 1; - save_pmu = lp->pmcregs_in_use; - } - /* Must save pmu if this guest is capable of running nested guests */ - save_pmu |= nesting_enabled(vcpu->kvm); + __this_cpu_write(cpu_in_guest, kvm); + trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr, tb); + __this_cpu_write(cpu_in_guest, NULL); - kvmhv_save_guest_pmu(vcpu, save_pmu); + if (trap == BOOK3S_INTERRUPT_SYSCALL && + !(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) { + unsigned long req = kvmppc_get_gpr(vcpu, 3); - vc->entry_exit_map = 0x101; - vc->in_guest = 0; + /* + * XIVE rearm and XICS hcalls must be handled + * before xive context is pulled (is this + * true?) + */ + if (req == H_CEDE) { + /* H_CEDE has to be handled now */ + kvmppc_cede(vcpu); + if (!kvmppc_xive_rearm_escalation(vcpu)) { + /* + * Pending escalation so abort + * the cede. + */ + vcpu->arch.ceded = 0; + } + kvmppc_set_gpr(vcpu, 3, 0); + trap = 0; + + } else if (req == H_ENTER_NESTED) { + /* + * L2 should not run with the L1 + * context so rearm and pull it. + */ + if (!kvmppc_xive_rearm_escalation(vcpu)) { + /* + * Pending escalation so abort + * H_ENTER_NESTED. + */ + kvmppc_set_gpr(vcpu, 3, 0); + trap = 0; + } + + } else if (hcall_is_xics(req)) { + int ret; - mtspr(SPRN_DEC, local_paca->kvm_hstate.dec_expires - mftb()); - mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso); + ret = kvmppc_xive_xics_hcall(vcpu, req); + if (ret != H_TOO_HARD) { + kvmppc_set_gpr(vcpu, 3, ret); + trap = 0; + } + } + } + kvmppc_xive_pull_vcpu(vcpu); - kvmhv_load_host_pmu(); + if (kvm_is_radix(kvm)) + vcpu->arch.slb_max = 0; + } - kvmppc_subcore_exit_guest(); + vcpu_vpa_increment_dispatch(vcpu); return trap; } @@ -3763,6 +4395,13 @@ static bool kvmppc_vcpu_woken(struct kvm_vcpu *vcpu) return false; } +static bool kvmppc_vcpu_check_block(struct kvm_vcpu *vcpu) +{ + if (!vcpu->arch.ceded || kvmppc_vcpu_woken(vcpu)) + return true; + return false; +} + /* * Check to see if any of the runnable vcpus on the vcore have pending * exceptions or are no longer ceded @@ -3773,7 +4412,7 @@ static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc) int i; for_each_runnable_thread(i, vcpu, vc) { - if (!vcpu->arch.ceded || kvmppc_vcpu_woken(vcpu)) + if (kvmppc_vcpu_check_block(vcpu)) return 1; } @@ -3789,13 +4428,14 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) ktime_t cur, start_poll, start_wait; int do_sleep = 1; u64 block_ns; - DECLARE_SWAITQUEUE(wait); + + WARN_ON_ONCE(cpu_has_feature(CPU_FTR_ARCH_300)); /* Poll for pending exceptions and ceded state */ cur = start_poll = ktime_get(); if (vc->halt_poll_ns) { ktime_t stop = ktime_add_ns(start_poll, vc->halt_poll_ns); - ++vc->runner->stat.halt_attempted_poll; + ++vc->runner->stat.generic.halt_attempted_poll; vc->vcore_state = VCORE_POLLING; spin_unlock(&vc->lock); @@ -3806,38 +4446,38 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) break; } cur = ktime_get(); - } while (single_task_running() && ktime_before(cur, stop)); + } while (kvm_vcpu_can_poll(cur, stop)); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; if (!do_sleep) { - ++vc->runner->stat.halt_successful_poll; + ++vc->runner->stat.generic.halt_successful_poll; goto out; } } - prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE); - + prepare_to_rcuwait(&vc->wait); + set_current_state(TASK_INTERRUPTIBLE); if (kvmppc_vcore_check_block(vc)) { - finish_swait(&vc->wq, &wait); + finish_rcuwait(&vc->wait); do_sleep = 0; /* If we polled, count this as a successful poll */ if (vc->halt_poll_ns) - ++vc->runner->stat.halt_successful_poll; + ++vc->runner->stat.generic.halt_successful_poll; goto out; } start_wait = ktime_get(); vc->vcore_state = VCORE_SLEEPING; - trace_kvmppc_vcore_blocked(vc, 0); + trace_kvmppc_vcore_blocked(vc->runner, 0); spin_unlock(&vc->lock); schedule(); - finish_swait(&vc->wq, &wait); + finish_rcuwait(&vc->wait); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; - trace_kvmppc_vcore_blocked(vc, 1); + trace_kvmppc_vcore_blocked(vc->runner, 1); ++vc->runner->stat.halt_successful_wait; cur = ktime_get(); @@ -3847,19 +4487,31 @@ out: /* Attribute wait time */ if (do_sleep) { - vc->runner->stat.halt_wait_ns += + vc->runner->stat.generic.halt_wait_ns += ktime_to_ns(cur) - ktime_to_ns(start_wait); + KVM_STATS_LOG_HIST_UPDATE( + vc->runner->stat.generic.halt_wait_hist, + ktime_to_ns(cur) - ktime_to_ns(start_wait)); /* Attribute failed poll time */ - if (vc->halt_poll_ns) - vc->runner->stat.halt_poll_fail_ns += + if (vc->halt_poll_ns) { + vc->runner->stat.generic.halt_poll_fail_ns += ktime_to_ns(start_wait) - ktime_to_ns(start_poll); + KVM_STATS_LOG_HIST_UPDATE( + vc->runner->stat.generic.halt_poll_fail_hist, + ktime_to_ns(start_wait) - + ktime_to_ns(start_poll)); + } } else { /* Attribute successful poll time */ - if (vc->halt_poll_ns) - vc->runner->stat.halt_poll_success_ns += + if (vc->halt_poll_ns) { + vc->runner->stat.generic.halt_poll_success_ns += ktime_to_ns(cur) - ktime_to_ns(start_poll); + KVM_STATS_LOG_HIST_UPDATE( + vc->runner->stat.generic.halt_poll_success_hist, + ktime_to_ns(cur) - ktime_to_ns(start_poll)); + } } /* Adjust poll time */ @@ -3884,7 +4536,6 @@ out: /* * This never fails for a radix guest, as none of the operations it does * for a radix guest can fail or have a way to report failure. - * kvmhv_run_single_vcpu() relies on this fact. */ static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu) { @@ -3905,15 +4556,16 @@ static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu) return r; } -static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu) { + struct kvm_run *run = vcpu->run; int n_ceded, i, r; struct kvmppc_vcore *vc; struct kvm_vcpu *v; trace_kvmppc_run_vcpu_enter(vcpu); - kvm_run->exit_reason = 0; + run->exit_reason = 0; vcpu->arch.ret = RESUME_GUEST; vcpu->arch.trap = 0; kvmppc_update_vpas(vcpu); @@ -3925,7 +4577,6 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) spin_lock(&vc->lock); vcpu->arch.ceded = 0; vcpu->arch.run_task = current; - vcpu->arch.kvm_run = kvm_run; vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb()); vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; vcpu->arch.busy_preempt = TB_NIL; @@ -3941,11 +4592,11 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) if ((vc->vcore_state == VCORE_PIGGYBACK || vc->vcore_state == VCORE_RUNNING) && !VCORE_IS_EXITING(vc)) { - kvmppc_create_dtl_entry(vcpu, vc); + kvmppc_update_vpa_dispatch(vcpu, vc); kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { - swake_up_one(&vc->wq); + rcuwait_wake_up(&vc->wait); } } @@ -3958,8 +4609,8 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) r = kvmhv_setup_mmu(vcpu); spin_lock(&vc->lock); if (r) { - kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; - kvm_run->fail_entry. + run->exit_reason = KVM_EXIT_FAIL_ENTRY; + run->fail_entry. hardware_entry_failure_reason = 0; vcpu->arch.ret = r; break; @@ -3976,9 +4627,9 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) for_each_runnable_thread(i, v, vc) { kvmppc_core_prepare_to_enter(v); if (signal_pending(v->arch.run_task)) { - kvmppc_remove_runnable(vc, v); + kvmppc_remove_runnable(vc, v, mftb()); v->stat.signal_exits++; - v->arch.kvm_run->exit_reason = KVM_EXIT_INTR; + v->run->exit_reason = KVM_EXIT_INTR; v->arch.ret = -EINTR; wake_up(&v->arch.cpu_run); } @@ -4017,9 +4668,9 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_vcore_end_preempt(vc); if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) { - kvmppc_remove_runnable(vc, vcpu); + kvmppc_remove_runnable(vc, vcpu, mftb()); vcpu->stat.signal_exits++; - kvm_run->exit_reason = KVM_EXIT_INTR; + run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; } @@ -4030,73 +4681,97 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) wake_up(&v->arch.cpu_run); } - trace_kvmppc_run_vcpu_exit(vcpu, kvm_run); + trace_kvmppc_run_vcpu_exit(vcpu); spin_unlock(&vc->lock); return vcpu->arch.ret; } -int kvmhv_run_single_vcpu(struct kvm_run *kvm_run, - struct kvm_vcpu *vcpu, u64 time_limit, +int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr) { + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); + struct kvm_run *run = vcpu->run; int trap, r, pcpu; - int srcu_idx, lpid; + int srcu_idx; struct kvmppc_vcore *vc; struct kvm *kvm = vcpu->kvm; struct kvm_nested_guest *nested = vcpu->arch.nested; + unsigned long flags; + u64 tb; trace_kvmppc_run_vcpu_enter(vcpu); - kvm_run->exit_reason = 0; + run->exit_reason = 0; vcpu->arch.ret = RESUME_GUEST; vcpu->arch.trap = 0; vc = vcpu->arch.vcore; vcpu->arch.ceded = 0; vcpu->arch.run_task = current; - vcpu->arch.kvm_run = kvm_run; - vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb()); - vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; - vcpu->arch.busy_preempt = TB_NIL; vcpu->arch.last_inst = KVM_INST_FETCH_FAILED; - vc->runnable_threads[0] = vcpu; - vc->n_runnable = 1; - vc->runner = vcpu; /* See if the MMU is ready to go */ - if (!kvm->arch.mmu_ready) - kvmhv_setup_mmu(vcpu); + if (unlikely(!kvm->arch.mmu_ready)) { + r = kvmhv_setup_mmu(vcpu); + if (r) { + run->exit_reason = KVM_EXIT_FAIL_ENTRY; + run->fail_entry.hardware_entry_failure_reason = 0; + vcpu->arch.ret = r; + return r; + } + } if (need_resched()) cond_resched(); kvmppc_update_vpas(vcpu); - init_vcore_to_run(vc); - vc->preempt_tb = TB_NIL; - preempt_disable(); pcpu = smp_processor_id(); - vc->pcpu = pcpu; - kvmppc_prepare_radix_vcpu(vcpu, pcpu); + if (kvm_is_radix(kvm)) + kvmppc_prepare_radix_vcpu(vcpu, pcpu); + + /* flags save not required, but irq_pmu has no disable/enable API */ + powerpc_local_irq_pmu_save(flags); + + vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; - local_irq_disable(); - hard_irq_disable(); if (signal_pending(current)) goto sigpend; - if (lazy_irq_pending() || need_resched() || !kvm->arch.mmu_ready) + if (need_resched() || !kvm->arch.mmu_ready) goto out; + vcpu->cpu = pcpu; + vcpu->arch.thread_cpu = pcpu; + vc->pcpu = pcpu; + local_paca->kvm_hstate.kvm_vcpu = vcpu; + local_paca->kvm_hstate.ptid = 0; + local_paca->kvm_hstate.fake_suspend = 0; + + /* + * Orders set cpu/thread_cpu vs testing for pending interrupts and + * doorbells below. The other side is when these fields are set vs + * kvmppc_fast_vcpu_kick_hv reading the cpu/thread_cpu fields to + * kick a vCPU to notice the pending interrupt. + */ + smp_mb(); + if (!nested) { kvmppc_core_prepare_to_enter(vcpu); - if (vcpu->arch.doorbell_request) { - vc->dpdes = 1; - smp_wmb(); - vcpu->arch.doorbell_request = 0; - } if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, - &vcpu->arch.pending_exceptions)) - lpcr |= LPCR_MER; + &vcpu->arch.pending_exceptions) || + xive_interrupt_pending(vcpu)) { + /* + * For nested HV, don't synthesize but always pass MER, + * the L0 will be able to optimise that more + * effectively than manipulating registers directly. + */ + if (!kvmhv_on_pseries() && (__kvmppc_get_msr_hv(vcpu) & MSR_EE)) + kvmppc_inject_interrupt_hv(vcpu, + BOOK3S_INTERRUPT_EXTERNAL, 0); + else + lpcr |= LPCR_MER; + } } else if (vcpu->arch.pending_exceptions || vcpu->arch.doorbell_request || xive_interrupt_pending(vcpu)) { @@ -4104,56 +4779,53 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run, goto out; } - kvmppc_clear_host_core(pcpu); + if (vcpu->arch.timer_running) { + hrtimer_try_to_cancel(&vcpu->arch.dec_timer); + vcpu->arch.timer_running = 0; + } - local_paca->kvm_hstate.tid = 0; - local_paca->kvm_hstate.napping = 0; - local_paca->kvm_hstate.kvm_split_mode = NULL; - kvmppc_start_thread(vcpu, vc); - kvmppc_create_dtl_entry(vcpu, vc); - trace_kvm_guest_enter(vcpu); + tb = mftb(); - vc->vcore_state = VCORE_RUNNING; - trace_kvmppc_run_core(vc, 0); + kvmppc_update_vpa_dispatch_p9(vcpu, vc, tb + kvmppc_get_tb_offset(vcpu)); - if (cpu_has_feature(CPU_FTR_HVMODE)) { - lpid = nested ? nested->shadow_lpid : kvm->arch.lpid; - mtspr(SPRN_LPID, lpid); - isync(); - kvmppc_check_need_tlb_flush(kvm, pcpu, nested); - } + trace_kvm_guest_enter(vcpu); - guest_enter_irqoff(); + guest_timing_enter_irqoff(); srcu_idx = srcu_read_lock(&kvm->srcu); + guest_state_enter_irqoff(); this_cpu_disable_ftrace(); - /* Tell lockdep that we're about to enable interrupts */ - trace_hardirqs_on(); - - trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr); + trap = kvmhv_p9_guest_entry(vcpu, time_limit, lpcr, &tb); vcpu->arch.trap = trap; - trace_hardirqs_off(); - this_cpu_enable_ftrace(); + guest_state_exit_irqoff(); srcu_read_unlock(&kvm->srcu, srcu_idx); - if (cpu_has_feature(CPU_FTR_HVMODE)) { - mtspr(SPRN_LPID, kvm->arch.host_lpid); - isync(); - } - set_irq_happened(trap); - kvmppc_set_host_core(pcpu); + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; + vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; - local_irq_enable(); - guest_exit(); + if (!vtime_accounting_enabled_this_cpu()) { + powerpc_local_irq_pmu_restore(flags); + /* + * Service IRQs here before guest_timing_exit_irqoff() so any + * ticks that occurred while running the guest are accounted to + * the guest. If vtime accounting is enabled, accounting uses + * TB rather than ticks, so it can be done without enabling + * interrupts here, which has the problem that it accounts + * interrupt processing overhead to the host. + */ + powerpc_local_irq_pmu_save(flags); + } + guest_timing_exit_irqoff(); - cpumask_clear_cpu(pcpu, &kvm->arch.cpu_in_guest); + powerpc_local_irq_pmu_restore(flags); preempt_enable(); @@ -4162,8 +4834,8 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run, * entering a nested guest in which case the decrementer is now owned * by L2 and the L1 decrementer is provided in hdec_expires */ - if (kvmppc_core_pending_dec(vcpu) && - ((get_tb() < vcpu->arch.dec_expires) || + if (!kvmhv_is_nestedv2() && kvmppc_core_pending_dec(vcpu) && + ((tb < kvmppc_dec_expires_host_tb(vcpu)) || (trap == BOOK3S_INTERRUPT_SYSCALL && kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED))) kvmppc_core_dequeue_dec(vcpu); @@ -4172,69 +4844,80 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run, r = RESUME_GUEST; if (trap) { if (!nested) - r = kvmppc_handle_exit_hv(kvm_run, vcpu, current); + r = kvmppc_handle_exit_hv(vcpu, current); else - r = kvmppc_handle_nested_exit(kvm_run, vcpu); + r = kvmppc_handle_nested_exit(vcpu); } vcpu->arch.ret = r; - if (is_kvmppc_resume_guest(r) && vcpu->arch.ceded && - !kvmppc_vcpu_woken(vcpu)) { + if (is_kvmppc_resume_guest(r) && !kvmppc_vcpu_check_block(vcpu)) { kvmppc_set_timer(vcpu); - while (vcpu->arch.ceded && !kvmppc_vcpu_woken(vcpu)) { + + prepare_to_rcuwait(wait); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); if (signal_pending(current)) { vcpu->stat.signal_exits++; - kvm_run->exit_reason = KVM_EXIT_INTR; + run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; break; } - spin_lock(&vc->lock); - kvmppc_vcore_blocked(vc); - spin_unlock(&vc->lock); + + if (kvmppc_vcpu_check_block(vcpu)) + break; + + trace_kvmppc_vcore_blocked(vcpu, 0); + schedule(); + trace_kvmppc_vcore_blocked(vcpu, 1); } + finish_rcuwait(wait); } vcpu->arch.ceded = 0; - vc->vcore_state = VCORE_INACTIVE; - trace_kvmppc_run_core(vc, 1); - done: - kvmppc_remove_runnable(vc, vcpu); - trace_kvmppc_run_vcpu_exit(vcpu, kvm_run); + trace_kvmppc_run_vcpu_exit(vcpu); return vcpu->arch.ret; sigpend: vcpu->stat.signal_exits++; - kvm_run->exit_reason = KVM_EXIT_INTR; + run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; out: - local_irq_enable(); + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; + vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; + powerpc_local_irq_pmu_restore(flags); preempt_enable(); goto done; } -static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) +static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) { + struct kvm_run *run = vcpu->run; int r; int srcu_idx; - unsigned long ebb_regs[3] = {}; /* shut up GCC */ - unsigned long user_tar = 0; - unsigned int user_vrsave; struct kvm *kvm; + unsigned long msr; + + start_timing(vcpu, &vcpu->arch.vcpu_entry); if (!vcpu->arch.sane) { run->exit_reason = KVM_EXIT_INTERNAL_ERROR; return -EINVAL; } + /* No need to go into the guest when all we'll do is come back out */ + if (signal_pending(current)) { + run->exit_reason = KVM_EXIT_INTR; + return -EINTR; + } + +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM /* * Don't allow entry with a suspended transaction, because * the guest entry/exit code will lose it. - * If the guest has TM enabled, save away their TM-related SPRs - * (they will get restored by the TM unavailable interrupt). */ -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs && (current->thread.regs->msr & MSR_TM)) { if (MSR_TM_ACTIVE(current->thread.regs->msr)) { @@ -4242,12 +4925,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) run->fail_entry.hardware_entry_failure_reason = 0; return -EINVAL; } - /* Enable TM so we can read the TM SPRs */ - mtmsr(mfmsr() | MSR_TM); - current->thread.tm_tfhar = mfspr(SPRN_TFHAR); - current->thread.tm_tfiar = mfspr(SPRN_TFIAR); - current->thread.tm_texasr = mfspr(SPRN_TEXASR); - current->thread.regs->msr &= ~MSR_TM; } #endif @@ -4262,57 +4939,62 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) kvmppc_core_prepare_to_enter(vcpu); - /* No need to go into the guest when all we'll do is come back out */ - if (signal_pending(current)) { - run->exit_reason = KVM_EXIT_INTR; - return -EINTR; - } - kvm = vcpu->kvm; atomic_inc(&kvm->arch.vcpus_running); /* Order vcpus_running vs. mmu_ready, see kvmppc_alloc_reset_hpt */ smp_mb(); - flush_all_to_thread(current); + msr = 0; + if (IS_ENABLED(CONFIG_PPC_FPU)) + msr |= MSR_FP; + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + msr |= MSR_VEC; + if (cpu_has_feature(CPU_FTR_VSX)) + msr |= MSR_VSX; + if ((cpu_has_feature(CPU_FTR_TM) || + cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) && + (kvmppc_get_hfscr_hv(vcpu) & HFSCR_TM)) + msr |= MSR_TM; + msr = msr_check_and_set(msr); - /* Save userspace EBB and other register values */ - if (cpu_has_feature(CPU_FTR_ARCH_207S)) { - ebb_regs[0] = mfspr(SPRN_EBBHR); - ebb_regs[1] = mfspr(SPRN_EBBRR); - ebb_regs[2] = mfspr(SPRN_BESCR); - user_tar = mfspr(SPRN_TAR); - } - user_vrsave = mfspr(SPRN_VRSAVE); + kvmppc_save_user_regs(); + + kvmppc_save_current_sprs(); - vcpu->arch.wqp = &vcpu->arch.vcore->wq; - vcpu->arch.pgdir = current->mm->pgd; + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + vcpu->arch.waitp = &vcpu->arch.vcore->wait; + vcpu->arch.pgdir = kvm->mm->pgd; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; do { - /* - * The early POWER9 chips that can't mix radix and HPT threads - * on the same core also need the workaround for the problem - * where the TLB would prefetch entries in the guest exit path - * for radix guests using the guest PIDR value and LPID 0. - * The workaround is in the old path (kvmppc_run_vcpu()) - * but not the new path (kvmhv_run_single_vcpu()). - */ - if (kvm->arch.threads_indep && kvm_is_radix(kvm) && - !no_mixing_hpt_and_radix) - r = kvmhv_run_single_vcpu(run, vcpu, ~(u64)0, + accumulate_time(vcpu, &vcpu->arch.guest_entry); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + r = kvmhv_run_single_vcpu(vcpu, ~(u64)0, vcpu->arch.vcore->lpcr); else - r = kvmppc_run_vcpu(run, vcpu); - - if (run->exit_reason == KVM_EXIT_PAPR_HCALL && - !(vcpu->arch.shregs.msr & MSR_PR)) { + r = kvmppc_run_vcpu(vcpu); + + if (run->exit_reason == KVM_EXIT_PAPR_HCALL) { + accumulate_time(vcpu, &vcpu->arch.hcall); + + if (!kvmhv_is_nestedv2() && WARN_ON_ONCE(__kvmppc_get_msr_hv(vcpu) & MSR_PR)) { + /* + * These should have been caught reflected + * into the guest by now. Final sanity check: + * don't allow userspace to execute hcalls in + * the hypervisor. + */ + r = RESUME_GUEST; + continue; + } trace_kvm_hcall_enter(vcpu); r = kvmppc_pseries_do_hcall(vcpu); trace_kvm_hcall_exit(vcpu, r); kvmppc_core_prepare_to_enter(vcpu); } else if (r == RESUME_PAGE_FAULT) { + accumulate_time(vcpu, &vcpu->arch.pg_fault); srcu_idx = srcu_read_lock(&kvm->srcu); - r = kvmppc_book3s_hv_page_fault(run, vcpu, + r = kvmppc_book3s_hv_page_fault(vcpu, vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); srcu_read_unlock(&kvm->srcu, srcu_idx); } else if (r == RESUME_PASSTHROUGH) { @@ -4322,19 +5004,15 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) r = kvmppc_xics_rm_complete(vcpu, 0); } } while (is_kvmppc_resume_guest(r)); - - /* Restore userspace EBB and other register values */ - if (cpu_has_feature(CPU_FTR_ARCH_207S)) { - mtspr(SPRN_EBBHR, ebb_regs[0]); - mtspr(SPRN_EBBRR, ebb_regs[1]); - mtspr(SPRN_BESCR, ebb_regs[2]); - mtspr(SPRN_TAR, user_tar); - mtspr(SPRN_FSCR, current->thread.fscr); - } - mtspr(SPRN_VRSAVE, user_vrsave); + accumulate_time(vcpu, &vcpu->arch.vcpu_exit); vcpu->arch.state = KVMPPC_VCPU_NOTREADY; atomic_dec(&kvm->arch.vcpus_running); + + srr_regs_clobbered(); + + end_timing(vcpu); + return r; } @@ -4396,8 +5074,8 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int i, r; - unsigned long n; + int r; + unsigned long n, i; unsigned long *buf, *p; struct kvm_vcpu *vcpu; @@ -4410,7 +5088,7 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, slots = kvm_memslots(kvm); memslot = id_to_memslot(slots, log->slot); r = -ENOENT; - if (!memslot->dirty_bitmap) + if (!memslot || !memslot->dirty_bitmap) goto out; /* @@ -4457,47 +5135,45 @@ out: return r; } -static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) +static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *slot) { - if (!dont || free->arch.rmap != dont->arch.rmap) { - vfree(free->arch.rmap); - free->arch.rmap = NULL; - } + vfree(slot->arch.rmap); + slot->arch.rmap = NULL; } -static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot, - unsigned long npages) +static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { - slot->arch.rmap = vzalloc(array_size(npages, sizeof(*slot->arch.rmap))); - if (!slot->arch.rmap) - return -ENOMEM; + if (change == KVM_MR_CREATE) { + unsigned long size = array_size(new->npages, sizeof(*new->arch.rmap)); - return 0; -} + if ((size >> PAGE_SHIFT) > totalram_pages()) + return -ENOMEM; + + new->arch.rmap = vzalloc(size); + if (!new->arch.rmap) + return -ENOMEM; + } else if (change != KVM_MR_DELETE) { + new->arch.rmap = old->arch.rmap; + } -static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem) -{ return 0; } static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - unsigned long npages = mem->memory_size >> PAGE_SHIFT; - /* - * If we are making a new memslot, it might make + * If we are creating or modifying a memslot, it might make * some address that was previously cached as emulated * MMIO be no longer emulated MMIO, so invalidate * all the caches of emulated MMIO translations. */ - if (npages) + if (change != KVM_MR_DELETE) atomic64_inc(&kvm->arch.mmio_update); /* @@ -4524,16 +5200,14 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, switch (change) { case KVM_MR_CREATE: - if (kvmppc_uvmem_slot_init(kvm, new)) - return; - uv_register_mem_slot(kvm->arch.lpid, - new->base_gfn << PAGE_SHIFT, - new->npages * PAGE_SIZE, - 0, new->id); + /* + * @TODO kvmppc_uvmem_memslot_create() can fail and + * return error. Fix this. + */ + kvmppc_uvmem_memslot_create(kvm, new); break; case KVM_MR_DELETE: - uv_unregister_mem_slot(kvm->arch.lpid, old->id); - kvmppc_uvmem_slot_free(kvm, old); + kvmppc_uvmem_memslot_delete(kvm, old); break; default: /* TODO: Handle KVM_MR_MOVE */ @@ -4560,17 +5234,22 @@ void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask) struct kvmppc_vcore *vc = kvm->arch.vcores[i]; if (!vc) continue; + spin_lock(&vc->lock); vc->lpcr = (vc->lpcr & ~mask) | lpcr; + verify_lpcr(kvm, vc->lpcr); spin_unlock(&vc->lock); if (++cores_done >= kvm->arch.online_vcores) break; } -} -static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu) -{ - return; + if (kvmhv_is_nestedv2()) { + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + kvmhv_nestedv2_mark_dirty(vcpu, KVMPPC_GSID_LPCR); + } + } } void kvmppc_setup_partition_table(struct kvm *kvm) @@ -4640,14 +5319,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) /* Look up the VMA for the start of this memory slot */ hva = memslot->userspace_addr; - down_read(¤t->mm->mmap_sem); - vma = find_vma(current->mm, hva); - if (!vma || vma->vm_start > hva || (vma->vm_flags & VM_IO)) + mmap_read_lock(kvm->mm); + vma = vma_lookup(kvm->mm, hva); + if (!vma || (vma->vm_flags & VM_IO)) goto up_out; psize = vma_kernel_pagesize(vma); - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(kvm->mm); /* We can handle 4k, 64k or 16M pages in the VRMA */ if (psize >= 0x1000000) @@ -4680,7 +5359,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) return err; up_out: - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(kvm->mm); goto out_srcu; } @@ -4690,17 +5369,24 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) */ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) { + unsigned long lpcr, lpcr_mask; + if (nesting_enabled(kvm)) kvmhv_release_all_nested(kvm); kvmppc_rmap_reset(kvm); kvm->arch.process_table = 0; - /* Mutual exclusion with kvm_unmap_hva_range etc. */ + /* Mutual exclusion with kvm_unmap_gfn_range etc. */ spin_lock(&kvm->mmu_lock); kvm->arch.radix = 0; spin_unlock(&kvm->mmu_lock); kvmppc_free_radix(kvm); - kvmppc_update_lpcr(kvm, LPCR_VPM1, - LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR); + + lpcr = LPCR_VPM1; + lpcr_mask = LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_ARCH_31)) + lpcr_mask |= LPCR_HAIL; + kvmppc_update_lpcr(kvm, lpcr, lpcr_mask); + return 0; } @@ -4710,19 +5396,29 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) */ int kvmppc_switch_mmu_to_radix(struct kvm *kvm) { + unsigned long lpcr, lpcr_mask; int err; err = kvmppc_init_vm_radix(kvm); if (err) return err; kvmppc_rmap_reset(kvm); - /* Mutual exclusion with kvm_unmap_hva_range etc. */ + /* Mutual exclusion with kvm_unmap_gfn_range etc. */ spin_lock(&kvm->mmu_lock); kvm->arch.radix = 1; spin_unlock(&kvm->mmu_lock); kvmppc_free_hpt(&kvm->arch.hpt); - kvmppc_update_lpcr(kvm, LPCR_UPRT | LPCR_GTSE | LPCR_HR, - LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR); + + lpcr = LPCR_UPRT | LPCR_GTSE | LPCR_HR; + lpcr_mask = LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + lpcr_mask |= LPCR_HAIL; + if (cpu_has_feature(CPU_FTR_HVMODE) && + (kvm->arch.host_lpcr & LPCR_HAIL)) + lpcr |= LPCR_HAIL; + } + kvmppc_update_lpcr(kvm, lpcr, lpcr_mask); + return 0; } @@ -4744,6 +5440,9 @@ void kvmppc_alloc_host_rm_ops(void) int cpu, core; int size; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + return; + /* Not the first time here ? */ if (kvmppc_host_rm_ops_hv != NULL) return; @@ -4809,7 +5508,6 @@ void kvmppc_free_host_rm_ops(void) static int kvmppc_core_init_vm_hv(struct kvm *kvm) { unsigned long lpcr, lpid; - char buf[32]; int ret; mutex_init(&kvm->arch.uvmem_lock); @@ -4818,15 +5516,43 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) /* Allocate the guest's logical partition ID */ - lpid = kvmppc_alloc_lpid(); - if ((long)lpid < 0) - return -ENOMEM; - kvm->arch.lpid = lpid; + if (!kvmhv_is_nestedv2()) { + lpid = kvmppc_alloc_lpid(); + if ((long)lpid < 0) + return -ENOMEM; + kvm->arch.lpid = lpid; + } kvmppc_alloc_host_rm_ops(); kvmhv_vm_nested_init(kvm); + if (kvmhv_is_nestedv2()) { + long rc; + unsigned long guest_id; + + rc = plpar_guest_create(0, &guest_id); + + if (rc != H_SUCCESS) + pr_err("KVM: Create Guest hcall failed, rc=%ld\n", rc); + + switch (rc) { + case H_PARAMETER: + case H_FUNCTION: + case H_STATE: + return -EINVAL; + case H_NOT_ENOUGH_RESOURCES: + case H_ABORTED: + return -ENOMEM; + case H_AUTHORITY: + return -EPERM; + case H_NOT_AVAILABLE: + return -EBUSY; + } + kvm->arch.lpid = guest_id; + } + + /* * Since we don't flush the TLB when tearing down a VM, * and this lpid might have previously been used, @@ -4850,6 +5576,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR); lpcr &= LPCR_PECE | LPCR_LPES; } else { + /* + * The L2 LPES mode will be set by the L0 according to whether + * or not it needs to take external interrupts in HV mode. + */ lpcr = 0; } lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE | @@ -4886,14 +5616,22 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) kvm->arch.mmu_ready = 1; lpcr &= ~LPCR_VPM1; lpcr |= LPCR_UPRT | LPCR_GTSE | LPCR_HR; + if (cpu_has_feature(CPU_FTR_HVMODE) && + cpu_has_feature(CPU_FTR_ARCH_31) && + (kvm->arch.host_lpcr & LPCR_HAIL)) + lpcr |= LPCR_HAIL; ret = kvmppc_init_vm_radix(kvm); if (ret) { - kvmppc_free_lpid(kvm->arch.lpid); + if (kvmhv_is_nestedv2()) + plpar_guest_delete(0, kvm->arch.lpid); + else + kvmppc_free_lpid(kvm->arch.lpid); return ret; } kvmppc_setup_partition_table(kvm); } + verify_lpcr(kvm, lpcr); kvm->arch.lpcr = lpcr; /* Initialization for future HPT resizes */ @@ -4903,7 +5641,12 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) * Work out how many sets the TLB has, for the use of * the TLB invalidation loop in book3s_hv_rmhandlers.S. */ - if (radix_enabled()) + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + /* + * P10 will flush all the congruence class with a single tlbiel + */ + kvm->arch.tlb_sets = 1; + } else if (radix_enabled()) kvm->arch.tlb_sets = POWER9_TLB_SETS_RADIX; /* 128 */ else if (cpu_has_feature(CPU_FTR_ARCH_300)) kvm->arch.tlb_sets = POWER9_TLB_SETS_HASH; /* 256 */ @@ -4915,18 +5658,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) /* * Track that we now have a HV mode VM active. This blocks secondary * CPU threads from coming online. - * On POWER9, we only need to do this if the "indep_threads_mode" - * module parameter has been set to N. */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) { - if (!indep_threads_mode && !cpu_has_feature(CPU_FTR_HVMODE)) { - pr_warn("KVM: Ignoring indep_threads_mode=N in nested hypervisor\n"); - kvm->arch.threads_indep = true; - } else { - kvm->arch.threads_indep = indep_threads_mode; - } - } - if (!kvm->arch.threads_indep) + if (!cpu_has_feature(CPU_FTR_ARCH_300)) kvm_hv_vm_activated(); /* @@ -4942,15 +5675,14 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) kvm->arch.smt_mode = 1; kvm->arch.emul_smt_mode = 1; - /* - * Create a debugfs directory for the VM - */ - snprintf(buf, sizeof(buf), "vm%d", current->pid); - kvm->arch.debugfs_dir = debugfs_create_dir(buf, kvm_debugfs_dir); + return 0; +} + +static int kvmppc_arch_create_vm_debugfs_hv(struct kvm *kvm) +{ kvmppc_mmu_debugfs_init(kvm); if (radix_enabled()) kvmhv_radix_debugfs_init(kvm); - return 0; } @@ -4965,9 +5697,7 @@ static void kvmppc_free_vcores(struct kvm *kvm) static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) { - debugfs_remove_recursive(kvm->arch.debugfs_dir); - - if (!kvm->arch.threads_indep) + if (!cpu_has_feature(CPU_FTR_ARCH_300)) kvm_hv_vm_deactivated(); kvmppc_free_vcores(kvm); @@ -4983,17 +5713,24 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) if (nesting_enabled(kvm)) kvmhv_release_all_nested(kvm); kvm->arch.process_table = 0; - uv_svm_terminate(kvm->arch.lpid); - kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0); + if (kvm->arch.secure_guest) + uv_svm_terminate(kvm->arch.lpid); + if (!kvmhv_is_nestedv2()) + kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0); } - kvmppc_free_lpid(kvm->arch.lpid); + if (kvmhv_is_nestedv2()) { + kvmhv_flush_lpid(kvm->arch.lpid); + plpar_guest_delete(0, kvm->arch.lpid); + } else { + kvmppc_free_lpid(kvm->arch.lpid); + } kvmppc_free_pimap(kvm); } /* We don't need to emulate any privileged instructions or dcbz */ -static int kvmppc_core_emulate_op_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, +static int kvmppc_core_emulate_op_hv(struct kvm_vcpu *vcpu, unsigned int inst, int *advance) { return EMULATE_FAIL; @@ -5043,6 +5780,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) struct kvmppc_passthru_irqmap *pimap; struct irq_chip *chip; int i, rc = 0; + struct irq_data *host_data; if (!kvm_irq_bypass) return 1; @@ -5070,7 +5808,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) * what our real-mode EOI code does, or a XIVE interrupt */ chip = irq_data_get_irq_chip(&desc->irq_data); - if (!chip || !(is_pnv_opal_msi(chip) || is_xive_irq(chip))) { + if (!chip || !is_pnv_opal_msi(chip)) { pr_warn("kvmppc_set_passthru_irq_hv: Could not assign IRQ map for (%d,%d)\n", host_irq, guest_gsi); mutex_unlock(&kvm->lock); @@ -5107,15 +5845,22 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) * the KVM real mode handler. */ smp_wmb(); - irq_map->r_hwirq = desc->irq_data.hwirq; + + /* + * The 'host_irq' number is mapped in the PCI-MSI domain but + * the underlying calls, which will EOI the interrupt in real + * mode, need an HW IRQ number mapped in the XICS IRQ domain. + */ + host_data = irq_domain_get_irq_data(irq_get_default_host(), host_irq); + irq_map->r_hwirq = (unsigned int)irqd_to_hwirq(host_data); if (i == pimap->n_mapped) pimap->n_mapped++; if (xics_on_xive()) - rc = kvmppc_xive_set_mapped(kvm, guest_gsi, desc); + rc = kvmppc_xive_set_mapped(kvm, guest_gsi, host_irq); else - kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq); + kvmppc_xics_set_mapped(kvm, guest_gsi, irq_map->r_hwirq); if (rc) irq_map->r_hwirq = 0; @@ -5154,11 +5899,11 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) } if (xics_on_xive()) - rc = kvmppc_xive_clr_mapped(kvm, guest_gsi, pimap->mapped[i].desc); + rc = kvmppc_xive_clr_mapped(kvm, guest_gsi, host_irq); else kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq); - /* invalidate the entry (what do do on error from the above ?) */ + /* invalidate the entry (what to do on error from the above ?) */ pimap->mapped[i].r_hwirq = 0; /* @@ -5208,18 +5953,24 @@ static void kvmppc_irq_bypass_del_producer_hv(struct irq_bypass_consumer *cons, } #endif -static long kvm_arch_vm_ioctl_hv(struct file *filp, - unsigned int ioctl, unsigned long arg) +static int kvm_arch_vm_ioctl_hv(struct file *filp, + unsigned int ioctl, unsigned long arg) { struct kvm *kvm __maybe_unused = filp->private_data; void __user *argp = (void __user *)arg; - long r; + int r; switch (ioctl) { case KVM_PPC_ALLOCATE_HTAB: { u32 htab_order; + /* If we're a nested hypervisor, we currently only support radix */ + if (kvmhv_on_pseries()) { + r = -EOPNOTSUPP; + break; + } + r = -EFAULT; if (get_user(htab_order, (u32 __user *)argp)) break; @@ -5281,8 +6032,10 @@ static unsigned int default_hcall_list[] = { H_READ, H_PROTECT, H_BULK_REMOVE, +#ifdef CONFIG_SPAPR_TCE_IOMMU H_GET_TCE, H_PUT_TCE, +#endif H_SET_DABR, H_SET_XDABR, H_CEDE, @@ -5379,7 +6132,11 @@ static int kvmhv_enable_nested(struct kvm *kvm) { if (!nested) return -EPERM; - if (!cpu_has_feature(CPU_FTR_ARCH_300) || no_mixing_hpt_and_radix) + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return -ENODEV; + if (!radix_enabled()) + return -ENODEV; + if (kvmhv_is_nestedv2()) return -ENODEV; /* kvm == NULL means the caller is testing if the capability exists */ @@ -5436,6 +6193,21 @@ static void unpin_vpa_reset(struct kvm *kvm, struct kvmppc_vpa *vpa) } /* + * Enable a guest to become a secure VM, or test whether + * that could be enabled. + * Called when the KVM_CAP_PPC_SECURE_GUEST capability is + * tested (kvm == NULL) or enabled (kvm != NULL). + */ +static int kvmhv_enable_svm(struct kvm *kvm) +{ + if (!kvmppc_uvmem_available()) + return -EINVAL; + if (kvm) + kvm->arch.svm_enabled = 1; + return 0; +} + +/* * IOCTL handler to turn off secure mode of guest * * - Release all device pages @@ -5449,7 +6221,7 @@ static int kvmhv_svm_off(struct kvm *kvm) int mmu_was_ready; int srcu_idx; int ret = 0; - int i; + unsigned long i; if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) return ret; @@ -5468,15 +6240,16 @@ static int kvmhv_svm_off(struct kvm *kvm) } srcu_idx = srcu_read_lock(&kvm->srcu); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { struct kvm_memory_slot *memslot; struct kvm_memslots *slots = __kvm_memslots(kvm, i); + int bkt; if (!slots) continue; - kvm_for_each_memslot(memslot, slots) { - kvmppc_uvmem_drop_pages(memslot, kvm); + kvm_for_each_memslot(memslot, bkt, slots) { + kvmppc_uvmem_drop_pages(memslot, kvm, true); uv_unregister_mem_slot(kvm->arch.lpid, memslot->id); } } @@ -5514,6 +6287,40 @@ out: return ret; } +static int kvmhv_enable_dawr1(struct kvm *kvm) +{ + if (!cpu_has_feature(CPU_FTR_DAWR1)) + return -ENODEV; + + /* kvm == NULL means the caller is testing if the capability exists */ + if (kvm) + kvm->arch.dawr1_enabled = true; + return 0; +} + +static bool kvmppc_hash_v3_possible(void) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return false; + + if (!cpu_has_feature(CPU_FTR_HVMODE)) + return false; + + /* + * POWER9 chips before version 2.02 can't have some threads in + * HPT mode and some in radix mode on the same core. + */ + if (radix_enabled()) { + unsigned int pvr = mfspr(SPRN_PVR); + if ((pvr >> 16) == PVR_POWER9 && + (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) || + ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101))) + return false; + } + + return true; +} + static struct kvmppc_ops kvm_ops_hv = { .get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv, .set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv, @@ -5531,13 +6338,11 @@ static struct kvmppc_ops kvm_ops_hv = { .flush_memslot = kvmppc_core_flush_memslot_hv, .prepare_memory_region = kvmppc_core_prepare_memory_region_hv, .commit_memory_region = kvmppc_core_commit_memory_region_hv, - .unmap_hva_range = kvm_unmap_hva_range_hv, - .age_hva = kvm_age_hva_hv, - .test_age_hva = kvm_test_age_hva_hv, - .set_spte_hva = kvm_set_spte_hva_hv, - .mmu_destroy = kvmppc_mmu_destroy_hv, + .unmap_gfn_range = kvm_unmap_gfn_range_hv, + .age_gfn = kvm_age_gfn_hv, + .test_age_gfn = kvm_test_age_gfn_hv, + .set_spte_gfn = kvm_set_spte_gfn_hv, .free_memslot = kvmppc_core_free_memslot_hv, - .create_memslot = kvmppc_core_create_memslot_hv, .init_vm = kvmppc_core_init_vm_hv, .destroy_vm = kvmppc_core_destroy_vm_hv, .get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv, @@ -5557,7 +6362,12 @@ static struct kvmppc_ops kvm_ops_hv = { .enable_nested = kvmhv_enable_nested, .load_from_eaddr = kvmhv_load_from_eaddr, .store_to_eaddr = kvmhv_store_to_eaddr, + .enable_svm = kvmhv_enable_svm, .svm_off = kvmhv_svm_off, + .enable_dawr1 = kvmhv_enable_dawr1, + .hash_v3_possible = kvmppc_hash_v3_possible, + .create_vcpu_debugfs = kvmppc_arch_create_vcpu_debugfs_hv, + .create_vm_debugfs = kvmppc_arch_create_vm_debugfs_hv, }; static int kvm_init_subcore_bitmap(void) @@ -5616,9 +6426,11 @@ static int kvmppc_book3s_init_hv(void) if (r) return r; - r = kvm_init_subcore_bitmap(); - if (r) - return r; + if (!cpu_has_feature(CPU_FTR_ARCH_300)) { + r = kvm_init_subcore_bitmap(); + if (r) + goto err; + } /* * We need a way of accessing the XICS interrupt controller, @@ -5633,42 +6445,42 @@ static int kvmppc_book3s_init_hv(void) np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc"); if (!np) { pr_err("KVM-HV: Cannot determine method for accessing XICS\n"); - return -ENODEV; + r = -ENODEV; + goto err; } /* presence of intc confirmed - node can be dropped again */ of_node_put(np); } #endif - kvm_ops_hv.owner = THIS_MODULE; - kvmppc_hv_ops = &kvm_ops_hv; - init_default_hcalls(); init_vcore_lists(); r = kvmppc_mmu_hv_init(); if (r) - return r; + goto err; - if (kvmppc_radix_possible()) + if (kvmppc_radix_possible()) { r = kvmppc_radix_init(); - - /* - * POWER9 chips before version 2.02 can't have some threads in - * HPT mode and some in radix mode on the same core. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) { - unsigned int pvr = mfspr(SPRN_PVR); - if ((pvr >> 16) == PVR_POWER9 && - (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) || - ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101))) - no_mixing_hpt_and_radix = true; + if (r) + goto err; } r = kvmppc_uvmem_init(); - if (r < 0) + if (r < 0) { pr_err("KVM-HV: kvmppc_uvmem_init failed %d\n", r); + return r; + } + + kvm_ops_hv.owner = THIS_MODULE; + kvmppc_hv_ops = &kvm_ops_hv; + + return 0; + +err: + kvmhv_nested_exit(); + kvmppc_radix_exit(); return r; } |