diff options
Diffstat (limited to 'arch/powerpc/kvm')
| -rw-r--r-- | arch/powerpc/kvm/Kconfig | 21 | ||||
| -rw-r--r-- | arch/powerpc/kvm/Makefile | 1 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_64_mmu_radix.c | 1 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_64_vio.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv.c | 28 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv.h | 10 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv_builtin.c | 25 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv_nested.c | 1 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv_p9_entry.c | 257 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv_p9_perf.c | 219 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_hv_rmhandlers.S | 24 | ||||
| -rw-r--r-- | arch/powerpc/kvm/book3s_xics.h | 1 | ||||
| -rw-r--r-- | arch/powerpc/kvm/powerpc.c | 1 | ||||
| -rw-r--r-- | arch/powerpc/kvm/trace_hv.h | 21 |
14 files changed, 322 insertions, 290 deletions
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index ddd88179110a..dcb398d5e009 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -128,9 +128,26 @@ config KVM_BOOK3S_64_PR and system calls on the host. config KVM_BOOK3S_HV_EXIT_TIMING - bool "Detailed timing for hypervisor real-mode code" + bool + +config KVM_BOOK3S_HV_P9_TIMING + bool "Detailed timing for the P9 entry point" + select KVM_BOOK3S_HV_EXIT_TIMING depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS help + Calculate time taken for each vcpu during vcpu entry and + exit, time spent inside the guest and time spent handling + hypercalls and page faults. The total, minimum and maximum + times in nanoseconds together with the number of executions + are reported in debugfs in kvm/vm#/vcpu#/timings. + + If unsure, say N. + +config KVM_BOOK3S_HV_P8_TIMING + bool "Detailed timing for hypervisor real-mode code (for POWER8)" + select KVM_BOOK3S_HV_EXIT_TIMING + depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS && !KVM_BOOK3S_HV_P9_TIMING + help Calculate time taken for each vcpu in the real-mode guest entry, exit, and interrupt handling code, plus time spent in the guest and in nap mode due to idle (cede) while other threads are still @@ -149,7 +166,7 @@ config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND Old nested HV capable Linux guests have a bug where they don't reflect the PMU in-use status of their L2 guest to the L0 host while the L2 PMU registers are live. This can result in loss - of L2 PMU register state, causing perf to not work correctly in + of L2 PMU register state, causing perf to not work correctly in L2 guests. Selecting this option for the L0 host implements a workaround for diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 0cd23ce07d68..5319d889b184 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -86,6 +86,7 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ book3s_hv_rm_mmu.o \ book3s_hv_ras.o \ book3s_hv_builtin.o \ + book3s_hv_p9_perf.o \ $(kvm-book3s_64-builtin-tm-objs-y) \ $(kvm-book3s_64-builtin-xics-objs-y) endif diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 42851c32ff3b..9d4b3feda3b6 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -22,6 +22,7 @@ #include <asm/ultravisor.h> #include <asm/kvm_book3s_uvmem.h> #include <asm/plpar_wrappers.h> +#include <asm/firmware.h> /* * Supported radix tree geometry. diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index d6589c4fe889..40864373ef87 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -307,7 +307,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, return ret; ret = -ENOMEM; - stt = kzalloc(struct_size(stt, pages, npages), GFP_KERNEL); + stt = kzalloc(struct_size(stt, pages, npages), GFP_KERNEL | __GFP_NOWARN); if (!stt) goto fail_acct; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 631062cde6b4..57d0835e56fd 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2660,11 +2660,21 @@ 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)) @@ -2783,8 +2793,9 @@ static const struct file_operations debugfs_timings_ops = { /* Create a debugfs directory for the vcpu */ static int kvmppc_arch_create_vcpu_debugfs_hv(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) { - debugfs_create_file("timings", 0444, debugfs_dentry, 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; } @@ -4005,8 +4016,10 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns 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; @@ -4694,6 +4707,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) 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; @@ -4759,6 +4774,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; do { + 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); @@ -4766,6 +4782,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) r = kvmppc_run_vcpu(vcpu); if (run->exit_reason == KVM_EXIT_PAPR_HCALL) { + accumulate_time(vcpu, &vcpu->arch.hcall); + if (WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_PR)) { /* * These should have been caught reflected @@ -4781,6 +4799,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *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(vcpu, vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); @@ -4792,12 +4811,15 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu) r = kvmppc_xics_rm_complete(vcpu, 0); } } while (is_kvmppc_resume_guest(r)); + 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; } @@ -5643,7 +5665,7 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) 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; /* diff --git a/arch/powerpc/kvm/book3s_hv.h b/arch/powerpc/kvm/book3s_hv.h index 6b7f07d9026b..2f2e59d7d433 100644 --- a/arch/powerpc/kvm/book3s_hv.h +++ b/arch/powerpc/kvm/book3s_hv.h @@ -40,3 +40,13 @@ void switch_pmu_to_guest(struct kvm_vcpu *vcpu, struct p9_host_os_sprs *host_os_sprs); void switch_pmu_to_host(struct kvm_vcpu *vcpu, struct p9_host_os_sprs *host_os_sprs); + +#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING +void accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next); +#define start_timing(vcpu, next) accumulate_time(vcpu, next) +#define end_timing(vcpu) accumulate_time(vcpu, NULL) +#else +#define accumulate_time(vcpu, next) do {} while (0) +#define start_timing(vcpu, next) do {} while (0) +#define end_timing(vcpu) do {} while (0) +#endif diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 88a8f6473c4e..da85f046377a 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -19,7 +19,7 @@ #include <asm/interrupt.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> -#include <asm/archrandom.h> +#include <asm/machdep.h> #include <asm/xics.h> #include <asm/xive.h> #include <asm/dbell.h> @@ -176,13 +176,14 @@ EXPORT_SYMBOL_GPL(kvmppc_hcall_impl_hv_realmode); int kvmppc_hwrng_present(void) { - return powernv_hwrng_present(); + return ppc_md.get_random_seed != NULL; } EXPORT_SYMBOL_GPL(kvmppc_hwrng_present); long kvmppc_rm_h_random(struct kvm_vcpu *vcpu) { - if (powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4])) + if (ppc_md.get_random_seed && + ppc_md.get_random_seed(&vcpu->arch.regs.gpr[4])) return H_SUCCESS; return H_HARDWARE; @@ -489,24 +490,6 @@ static long kvmppc_read_one_intr(bool *again) return kvmppc_check_passthru(xisr, xirr, again); } -void kvmppc_bad_interrupt(struct pt_regs *regs) -{ - /* - * 100 could happen at any time, 200 can happen due to invalid real - * address access for example (or any time due to a hardware problem). - */ - if (TRAP(regs) == 0x100) { - get_paca()->in_nmi++; - system_reset_exception(regs); - get_paca()->in_nmi--; - } else if (TRAP(regs) == 0x200) { - machine_check_exception(regs); - } else { - die("Bad interrupt in KVM entry/exit code", regs, SIGABRT); - } - panic("Bad KVM trap"); -} - static void kvmppc_end_cede(struct kvm_vcpu *vcpu) { vcpu->arch.ceded = 0; diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 0644732d1a25..be8249cc6107 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -20,6 +20,7 @@ #include <asm/pte-walk.h> #include <asm/reg.h> #include <asm/plpar_wrappers.h> +#include <asm/firmware.h> static struct patb_entry *pseries_partition_tb; diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c index 112a09b33328..34f1db212824 100644 --- a/arch/powerpc/kvm/book3s_hv_p9_entry.c +++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c @@ -3,231 +3,10 @@ #include <linux/kvm_host.h> #include <asm/asm-prototypes.h> #include <asm/dbell.h> -#include <asm/kvm_ppc.h> -#include <asm/pmc.h> #include <asm/ppc-opcode.h> #include "book3s_hv.h" -static void freeze_pmu(unsigned long mmcr0, unsigned long mmcra) -{ - if (!(mmcr0 & MMCR0_FC)) - goto do_freeze; - if (mmcra & MMCRA_SAMPLE_ENABLE) - goto do_freeze; - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - if (!(mmcr0 & MMCR0_PMCCEXT)) - goto do_freeze; - if (!(mmcra & MMCRA_BHRB_DISABLE)) - goto do_freeze; - } - return; - -do_freeze: - mmcr0 = MMCR0_FC; - mmcra = 0; - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - mmcr0 |= MMCR0_PMCCEXT; - mmcra = MMCRA_BHRB_DISABLE; - } - - mtspr(SPRN_MMCR0, mmcr0); - mtspr(SPRN_MMCRA, mmcra); - isync(); -} - -void switch_pmu_to_guest(struct kvm_vcpu *vcpu, - struct p9_host_os_sprs *host_os_sprs) -{ - struct lppaca *lp; - int load_pmu = 1; - - lp = vcpu->arch.vpa.pinned_addr; - if (lp) - load_pmu = lp->pmcregs_in_use; - - /* Save host */ - if (ppc_get_pmu_inuse()) { - /* - * It might be better to put PMU handling (at least for the - * host) in the perf subsystem because it knows more about what - * is being used. - */ - - /* POWER9, POWER10 do not implement HPMC or SPMC */ - - host_os_sprs->mmcr0 = mfspr(SPRN_MMCR0); - host_os_sprs->mmcra = mfspr(SPRN_MMCRA); - - freeze_pmu(host_os_sprs->mmcr0, host_os_sprs->mmcra); - - host_os_sprs->pmc1 = mfspr(SPRN_PMC1); - host_os_sprs->pmc2 = mfspr(SPRN_PMC2); - host_os_sprs->pmc3 = mfspr(SPRN_PMC3); - host_os_sprs->pmc4 = mfspr(SPRN_PMC4); - host_os_sprs->pmc5 = mfspr(SPRN_PMC5); - host_os_sprs->pmc6 = mfspr(SPRN_PMC6); - host_os_sprs->mmcr1 = mfspr(SPRN_MMCR1); - host_os_sprs->mmcr2 = mfspr(SPRN_MMCR2); - host_os_sprs->sdar = mfspr(SPRN_SDAR); - host_os_sprs->siar = mfspr(SPRN_SIAR); - host_os_sprs->sier1 = mfspr(SPRN_SIER); - - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - host_os_sprs->mmcr3 = mfspr(SPRN_MMCR3); - host_os_sprs->sier2 = mfspr(SPRN_SIER2); - host_os_sprs->sier3 = mfspr(SPRN_SIER3); - } - } - -#ifdef CONFIG_PPC_PSERIES - /* After saving PMU, before loading guest PMU, flip pmcregs_in_use */ - if (kvmhv_on_pseries()) { - barrier(); - get_lppaca()->pmcregs_in_use = load_pmu; - barrier(); - } -#endif - - /* - * Load guest. If the VPA said the PMCs are not in use but the guest - * tried to access them anyway, HFSCR[PM] will be set by the HFAC - * fault so we can make forward progress. - */ - if (load_pmu || (vcpu->arch.hfscr & HFSCR_PM)) { - mtspr(SPRN_PMC1, vcpu->arch.pmc[0]); - mtspr(SPRN_PMC2, vcpu->arch.pmc[1]); - mtspr(SPRN_PMC3, vcpu->arch.pmc[2]); - mtspr(SPRN_PMC4, vcpu->arch.pmc[3]); - mtspr(SPRN_PMC5, vcpu->arch.pmc[4]); - mtspr(SPRN_PMC6, vcpu->arch.pmc[5]); - mtspr(SPRN_MMCR1, vcpu->arch.mmcr[1]); - mtspr(SPRN_MMCR2, vcpu->arch.mmcr[2]); - mtspr(SPRN_SDAR, vcpu->arch.sdar); - mtspr(SPRN_SIAR, vcpu->arch.siar); - mtspr(SPRN_SIER, vcpu->arch.sier[0]); - - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - mtspr(SPRN_MMCR3, vcpu->arch.mmcr[3]); - mtspr(SPRN_SIER2, vcpu->arch.sier[1]); - mtspr(SPRN_SIER3, vcpu->arch.sier[2]); - } - - /* Set MMCRA then MMCR0 last */ - mtspr(SPRN_MMCRA, vcpu->arch.mmcra); - mtspr(SPRN_MMCR0, vcpu->arch.mmcr[0]); - /* No isync necessary because we're starting counters */ - - if (!vcpu->arch.nested && - (vcpu->arch.hfscr_permitted & HFSCR_PM)) - vcpu->arch.hfscr |= HFSCR_PM; - } -} -EXPORT_SYMBOL_GPL(switch_pmu_to_guest); - -void switch_pmu_to_host(struct kvm_vcpu *vcpu, - struct p9_host_os_sprs *host_os_sprs) -{ - struct lppaca *lp; - int save_pmu = 1; - - lp = vcpu->arch.vpa.pinned_addr; - if (lp) - save_pmu = lp->pmcregs_in_use; - if (IS_ENABLED(CONFIG_KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND)) { - /* - * Save pmu if this guest is capable of running nested guests. - * This is option is for old L1s that do not set their - * lppaca->pmcregs_in_use properly when entering their L2. - */ - save_pmu |= nesting_enabled(vcpu->kvm); - } - - if (save_pmu) { - vcpu->arch.mmcr[0] = mfspr(SPRN_MMCR0); - vcpu->arch.mmcra = mfspr(SPRN_MMCRA); - - freeze_pmu(vcpu->arch.mmcr[0], vcpu->arch.mmcra); - - vcpu->arch.pmc[0] = mfspr(SPRN_PMC1); - vcpu->arch.pmc[1] = mfspr(SPRN_PMC2); - vcpu->arch.pmc[2] = mfspr(SPRN_PMC3); - vcpu->arch.pmc[3] = mfspr(SPRN_PMC4); - vcpu->arch.pmc[4] = mfspr(SPRN_PMC5); - vcpu->arch.pmc[5] = mfspr(SPRN_PMC6); - vcpu->arch.mmcr[1] = mfspr(SPRN_MMCR1); - vcpu->arch.mmcr[2] = mfspr(SPRN_MMCR2); - vcpu->arch.sdar = mfspr(SPRN_SDAR); - vcpu->arch.siar = mfspr(SPRN_SIAR); - vcpu->arch.sier[0] = mfspr(SPRN_SIER); - - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - vcpu->arch.mmcr[3] = mfspr(SPRN_MMCR3); - vcpu->arch.sier[1] = mfspr(SPRN_SIER2); - vcpu->arch.sier[2] = mfspr(SPRN_SIER3); - } - - } else if (vcpu->arch.hfscr & HFSCR_PM) { - /* - * The guest accessed PMC SPRs without specifying they should - * be preserved, or it cleared pmcregs_in_use after the last - * access. Just ensure they are frozen. - */ - freeze_pmu(mfspr(SPRN_MMCR0), mfspr(SPRN_MMCRA)); - - /* - * Demand-fault PMU register access in the guest. - * - * This is used to grab the guest's VPA pmcregs_in_use value - * and reflect it into the host's VPA in the case of a nested - * hypervisor. - * - * It also avoids having to zero-out SPRs after each guest - * exit to avoid side-channels when. - * - * This is cleared here when we exit the guest, so later HFSCR - * interrupt handling can add it back to run the guest with - * PM enabled next time. - */ - if (!vcpu->arch.nested) - vcpu->arch.hfscr &= ~HFSCR_PM; - } /* otherwise the PMU should still be frozen */ - -#ifdef CONFIG_PPC_PSERIES - if (kvmhv_on_pseries()) { - barrier(); - get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse(); - barrier(); - } -#endif - - if (ppc_get_pmu_inuse()) { - mtspr(SPRN_PMC1, host_os_sprs->pmc1); - mtspr(SPRN_PMC2, host_os_sprs->pmc2); - mtspr(SPRN_PMC3, host_os_sprs->pmc3); - mtspr(SPRN_PMC4, host_os_sprs->pmc4); - mtspr(SPRN_PMC5, host_os_sprs->pmc5); - mtspr(SPRN_PMC6, host_os_sprs->pmc6); - mtspr(SPRN_MMCR1, host_os_sprs->mmcr1); - mtspr(SPRN_MMCR2, host_os_sprs->mmcr2); - mtspr(SPRN_SDAR, host_os_sprs->sdar); - mtspr(SPRN_SIAR, host_os_sprs->siar); - mtspr(SPRN_SIER, host_os_sprs->sier1); - - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - mtspr(SPRN_MMCR3, host_os_sprs->mmcr3); - mtspr(SPRN_SIER2, host_os_sprs->sier2); - mtspr(SPRN_SIER3, host_os_sprs->sier3); - } - - /* Set MMCRA then MMCR0 last */ - mtspr(SPRN_MMCRA, host_os_sprs->mmcra); - mtspr(SPRN_MMCR0, host_os_sprs->mmcr0); - isync(); - } -} -EXPORT_SYMBOL_GPL(switch_pmu_to_host); - static void load_spr_state(struct kvm_vcpu *vcpu, struct p9_host_os_sprs *host_os_sprs) { @@ -437,17 +216,8 @@ void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(restore_p9_host_os_sprs); -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING -static void __start_timing(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next) -{ - struct kvmppc_vcore *vc = vcpu->arch.vcore; - u64 tb = mftb() - vc->tb_offset_applied; - - vcpu->arch.cur_activity = next; - vcpu->arch.cur_tb_start = tb; -} - -static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next) +#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING +void accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next) { struct kvmppc_vcore *vc = vcpu->arch.vcore; struct kvmhv_tb_accumulator *curr; @@ -477,14 +247,7 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator smp_wmb(); curr->seqcount = seq + 2; } - -#define start_timing(vcpu, next) __start_timing(vcpu, next) -#define end_timing(vcpu) __start_timing(vcpu, NULL) -#define accumulate_time(vcpu, next) __accumulate_time(vcpu, next) -#else -#define start_timing(vcpu, next) do {} while (0) -#define end_timing(vcpu) do {} while (0) -#define accumulate_time(vcpu, next) do {} while (0) +EXPORT_SYMBOL_GPL(accumulate_time); #endif static inline u64 mfslbv(unsigned int idx) @@ -795,8 +558,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_HV); WARN_ON_ONCE(!(vcpu->arch.shregs.msr & MSR_ME)); - start_timing(vcpu, &vcpu->arch.rm_entry); - vcpu->arch.ceded = 0; /* Save MSR for restore, with EE clear. */ @@ -957,13 +718,13 @@ tm_return_to_guest: mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0); mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1); - accumulate_time(vcpu, &vcpu->arch.guest_time); - switch_pmu_to_guest(vcpu, &host_os_sprs); + accumulate_time(vcpu, &vcpu->arch.in_guest); + kvmppc_p9_enter_guest(vcpu); - switch_pmu_to_host(vcpu, &host_os_sprs); - accumulate_time(vcpu, &vcpu->arch.rm_intr); + accumulate_time(vcpu, &vcpu->arch.guest_exit); + switch_pmu_to_host(vcpu, &host_os_sprs); /* XXX: Could get these from r11/12 and paca exsave instead */ vcpu->arch.shregs.srr0 = mfspr(SPRN_SRR0); @@ -1058,8 +819,6 @@ tm_return_to_guest: #endif } - accumulate_time(vcpu, &vcpu->arch.rm_exit); - /* Advance host PURR/SPURR by the amount used by guest */ purr = mfspr(SPRN_PURR); spurr = mfspr(SPRN_SPURR); @@ -1166,8 +925,6 @@ tm_return_to_guest: asm volatile(PPC_CP_ABORT); out: - end_timing(vcpu); - return trap; } EXPORT_SYMBOL_GPL(kvmhv_vcpu_entry_p9); diff --git a/arch/powerpc/kvm/book3s_hv_p9_perf.c b/arch/powerpc/kvm/book3s_hv_p9_perf.c new file mode 100644 index 000000000000..44d24cca3df1 --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_p9_perf.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <asm/kvm_ppc.h> +#include <asm/pmc.h> + +#include "book3s_hv.h" + +static void freeze_pmu(unsigned long mmcr0, unsigned long mmcra) +{ + if (!(mmcr0 & MMCR0_FC)) + goto do_freeze; + if (mmcra & MMCRA_SAMPLE_ENABLE) + goto do_freeze; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + if (!(mmcr0 & MMCR0_PMCCEXT)) + goto do_freeze; + if (!(mmcra & MMCRA_BHRB_DISABLE)) + goto do_freeze; + } + return; + +do_freeze: + mmcr0 = MMCR0_FC; + mmcra = 0; + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mmcr0 |= MMCR0_PMCCEXT; + mmcra = MMCRA_BHRB_DISABLE; + } + + mtspr(SPRN_MMCR0, mmcr0); + mtspr(SPRN_MMCRA, mmcra); + isync(); +} + +void switch_pmu_to_guest(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + struct lppaca *lp; + int load_pmu = 1; + + lp = vcpu->arch.vpa.pinned_addr; + if (lp) + load_pmu = lp->pmcregs_in_use; + + /* Save host */ + if (ppc_get_pmu_inuse()) { + /* POWER9, POWER10 do not implement HPMC or SPMC */ + + host_os_sprs->mmcr0 = mfspr(SPRN_MMCR0); + host_os_sprs->mmcra = mfspr(SPRN_MMCRA); + + freeze_pmu(host_os_sprs->mmcr0, host_os_sprs->mmcra); + + host_os_sprs->pmc1 = mfspr(SPRN_PMC1); + host_os_sprs->pmc2 = mfspr(SPRN_PMC2); + host_os_sprs->pmc3 = mfspr(SPRN_PMC3); + host_os_sprs->pmc4 = mfspr(SPRN_PMC4); + host_os_sprs->pmc5 = mfspr(SPRN_PMC5); + host_os_sprs->pmc6 = mfspr(SPRN_PMC6); + host_os_sprs->mmcr1 = mfspr(SPRN_MMCR1); + host_os_sprs->mmcr2 = mfspr(SPRN_MMCR2); + host_os_sprs->sdar = mfspr(SPRN_SDAR); + host_os_sprs->siar = mfspr(SPRN_SIAR); + host_os_sprs->sier1 = mfspr(SPRN_SIER); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + host_os_sprs->mmcr3 = mfspr(SPRN_MMCR3); + host_os_sprs->sier2 = mfspr(SPRN_SIER2); + host_os_sprs->sier3 = mfspr(SPRN_SIER3); + } + } + +#ifdef CONFIG_PPC_PSERIES + /* After saving PMU, before loading guest PMU, flip pmcregs_in_use */ + if (kvmhv_on_pseries()) { + barrier(); + get_lppaca()->pmcregs_in_use = load_pmu; + barrier(); + } +#endif + + /* + * Load guest. If the VPA said the PMCs are not in use but the guest + * tried to access them anyway, HFSCR[PM] will be set by the HFAC + * fault so we can make forward progress. + */ + if (load_pmu || (vcpu->arch.hfscr & HFSCR_PM)) { + mtspr(SPRN_PMC1, vcpu->arch.pmc[0]); + mtspr(SPRN_PMC2, vcpu->arch.pmc[1]); + mtspr(SPRN_PMC3, vcpu->arch.pmc[2]); + mtspr(SPRN_PMC4, vcpu->arch.pmc[3]); + mtspr(SPRN_PMC5, vcpu->arch.pmc[4]); + mtspr(SPRN_PMC6, vcpu->arch.pmc[5]); + mtspr(SPRN_MMCR1, vcpu->arch.mmcr[1]); + mtspr(SPRN_MMCR2, vcpu->arch.mmcr[2]); + mtspr(SPRN_SDAR, vcpu->arch.sdar); + mtspr(SPRN_SIAR, vcpu->arch.siar); + mtspr(SPRN_SIER, vcpu->arch.sier[0]); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_MMCR3, vcpu->arch.mmcr[3]); + mtspr(SPRN_SIER2, vcpu->arch.sier[1]); + mtspr(SPRN_SIER3, vcpu->arch.sier[2]); + } + + /* Set MMCRA then MMCR0 last */ + mtspr(SPRN_MMCRA, vcpu->arch.mmcra); + mtspr(SPRN_MMCR0, vcpu->arch.mmcr[0]); + /* No isync necessary because we're starting counters */ + + if (!vcpu->arch.nested && + (vcpu->arch.hfscr_permitted & HFSCR_PM)) + vcpu->arch.hfscr |= HFSCR_PM; + } +} +EXPORT_SYMBOL_GPL(switch_pmu_to_guest); + +void switch_pmu_to_host(struct kvm_vcpu *vcpu, + struct p9_host_os_sprs *host_os_sprs) +{ + struct lppaca *lp; + int save_pmu = 1; + + lp = vcpu->arch.vpa.pinned_addr; + if (lp) + save_pmu = lp->pmcregs_in_use; + if (IS_ENABLED(CONFIG_KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND)) { + /* + * Save pmu if this guest is capable of running nested guests. + * This is option is for old L1s that do not set their + * lppaca->pmcregs_in_use properly when entering their L2. + */ + save_pmu |= nesting_enabled(vcpu->kvm); + } + + if (save_pmu) { + vcpu->arch.mmcr[0] = mfspr(SPRN_MMCR0); + vcpu->arch.mmcra = mfspr(SPRN_MMCRA); + + freeze_pmu(vcpu->arch.mmcr[0], vcpu->arch.mmcra); + + vcpu->arch.pmc[0] = mfspr(SPRN_PMC1); + vcpu->arch.pmc[1] = mfspr(SPRN_PMC2); + vcpu->arch.pmc[2] = mfspr(SPRN_PMC3); + vcpu->arch.pmc[3] = mfspr(SPRN_PMC4); + vcpu->arch.pmc[4] = mfspr(SPRN_PMC5); + vcpu->arch.pmc[5] = mfspr(SPRN_PMC6); + vcpu->arch.mmcr[1] = mfspr(SPRN_MMCR1); + vcpu->arch.mmcr[2] = mfspr(SPRN_MMCR2); + vcpu->arch.sdar = mfspr(SPRN_SDAR); + vcpu->arch.siar = mfspr(SPRN_SIAR); + vcpu->arch.sier[0] = mfspr(SPRN_SIER); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + vcpu->arch.mmcr[3] = mfspr(SPRN_MMCR3); + vcpu->arch.sier[1] = mfspr(SPRN_SIER2); + vcpu->arch.sier[2] = mfspr(SPRN_SIER3); + } + + } else if (vcpu->arch.hfscr & HFSCR_PM) { + /* + * The guest accessed PMC SPRs without specifying they should + * be preserved, or it cleared pmcregs_in_use after the last + * access. Just ensure they are frozen. + */ + freeze_pmu(mfspr(SPRN_MMCR0), mfspr(SPRN_MMCRA)); + + /* + * Demand-fault PMU register access in the guest. + * + * This is used to grab the guest's VPA pmcregs_in_use value + * and reflect it into the host's VPA in the case of a nested + * hypervisor. + * + * It also avoids having to zero-out SPRs after each guest + * exit to avoid side-channels when. + * + * This is cleared here when we exit the guest, so later HFSCR + * interrupt handling can add it back to run the guest with + * PM enabled next time. + */ + if (!vcpu->arch.nested) + vcpu->arch.hfscr &= ~HFSCR_PM; + } /* otherwise the PMU should still be frozen */ + +#ifdef CONFIG_PPC_PSERIES + if (kvmhv_on_pseries()) { + barrier(); + get_lppaca()->pmcregs_in_use = ppc_get_pmu_inuse(); + barrier(); + } +#endif + + if (ppc_get_pmu_inuse()) { + mtspr(SPRN_PMC1, host_os_sprs->pmc1); + mtspr(SPRN_PMC2, host_os_sprs->pmc2); + mtspr(SPRN_PMC3, host_os_sprs->pmc3); + mtspr(SPRN_PMC4, host_os_sprs->pmc4); + mtspr(SPRN_PMC5, host_os_sprs->pmc5); + mtspr(SPRN_PMC6, host_os_sprs->pmc6); + mtspr(SPRN_MMCR1, host_os_sprs->mmcr1); + mtspr(SPRN_MMCR2, host_os_sprs->mmcr2); + mtspr(SPRN_SDAR, host_os_sprs->sdar); + mtspr(SPRN_SIAR, host_os_sprs->siar); + mtspr(SPRN_SIER, host_os_sprs->sier1); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + mtspr(SPRN_MMCR3, host_os_sprs->mmcr3); + mtspr(SPRN_SIER2, host_os_sprs->sier2); + mtspr(SPRN_SIER3, host_os_sprs->sier3); + } + + /* Set MMCRA then MMCR0 last */ + mtspr(SPRN_MMCRA, host_os_sprs->mmcra); + mtspr(SPRN_MMCR0, host_os_sprs->mmcr0); + isync(); + } +} +EXPORT_SYMBOL_GPL(switch_pmu_to_host); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 0fc0e68d20d0..7ded202bf995 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -237,14 +237,14 @@ kvm_novcpu_wakeup: cmpdi r4, 0 beq kvmppc_primary_no_guest -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r4, VCPU_TB_RMENTRY bl kvmhv_start_timing #endif b kvmppc_got_guest kvm_novcpu_exit: -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING ld r4, HSTATE_KVM_VCPU(r13) cmpdi r4, 0 beq 13f @@ -523,7 +523,7 @@ kvmppc_hv_entry: li r6, KVM_GUEST_MODE_HOST_HV stb r6, HSTATE_IN_GUEST(r13) -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING /* Store initial timestamp */ cmpdi r4, 0 beq 1f @@ -894,7 +894,7 @@ fast_guest_return: li r9, KVM_GUEST_MODE_GUEST_HV stb r9, HSTATE_IN_GUEST(r13) -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING /* Accumulate timing */ addi r3, r4, VCPU_TB_GUEST bl kvmhv_accumulate_time @@ -945,7 +945,7 @@ secondary_too_late: cmpdi r4, 0 beq 11f stw r12, VCPU_TRAP(r4) -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r4, VCPU_TB_RMEXIT bl kvmhv_accumulate_time #endif @@ -959,7 +959,7 @@ hdec_soon: li r12, BOOK3S_INTERRUPT_HV_DECREMENTER 12: stw r12, VCPU_TRAP(r4) mr r9, r4 -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r4, VCPU_TB_RMEXIT bl kvmhv_accumulate_time #endif @@ -1056,7 +1056,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) li r0, MSR_RI mtmsrd r0, 1 -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r9, VCPU_TB_RMINTR mr r4, r9 bl kvmhv_accumulate_time @@ -1135,7 +1135,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r9, VCPU_TB_RMEXIT mr r4, r9 bl kvmhv_accumulate_time @@ -1495,7 +1495,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mtspr SPRN_LPCR,r8 isync -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING /* Finish timing, if we have a vcpu */ ld r4, HSTATE_KVM_VCPU(r13) cmpdi r4, 0 @@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM) ld r4, HSTATE_KVM_VCPU(r13) std r3, VCPU_DEC_EXPIRES(r4) -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING ld r4, HSTATE_KVM_VCPU(r13) addi r3, r4, VCPU_TB_CEDE bl kvmhv_accumulate_time @@ -2221,7 +2221,7 @@ kvm_end_cede: /* get vcpu pointer */ ld r4, HSTATE_KVM_VCPU(r13) -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING addi r3, r4, VCPU_TB_RMINTR bl kvmhv_accumulate_time #endif @@ -2961,7 +2961,7 @@ kvmppc_fix_pmao: isync blr -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING +#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING /* * Start timing an activity * r3 = pointer to time accumulation struct, r4 = vcpu diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h index 8e4c79e2fcd8..08fb0843faf5 100644 --- a/arch/powerpc/kvm/book3s_xics.h +++ b/arch/powerpc/kvm/book3s_xics.h @@ -143,6 +143,7 @@ static inline struct kvmppc_ics *kvmppc_xics_find_ics(struct kvmppc_xics *xics, } extern unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu); +extern unsigned long xics_rm_h_xirr_x(struct kvm_vcpu *vcpu); extern int xics_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, unsigned long mfrr); extern int xics_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 191992fcb2c2..fb1490761c87 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -33,6 +33,7 @@ #include <asm/plpar_wrappers.h> #endif #include <asm/ultravisor.h> +#include <asm/setup.h> #include "timing.h" #include "irq.h" diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h index 32e2cb5811cc..8d57c8428531 100644 --- a/arch/powerpc/kvm/trace_hv.h +++ b/arch/powerpc/kvm/trace_hv.h @@ -94,6 +94,7 @@ {H_GET_HCA_INFO, "H_GET_HCA_INFO"}, \ {H_GET_PERF_COUNT, "H_GET_PERF_COUNT"}, \ {H_MANAGE_TRACE, "H_MANAGE_TRACE"}, \ + {H_GET_CPU_CHARACTERISTICS, "H_GET_CPU_CHARACTERISTICS"}, \ {H_FREE_LOGICAL_LAN_BUFFER, "H_FREE_LOGICAL_LAN_BUFFER"}, \ {H_QUERY_INT_STATE, "H_QUERY_INT_STATE"}, \ {H_POLL_PENDING, "H_POLL_PENDING"}, \ @@ -125,7 +126,25 @@ {H_COP, "H_COP"}, \ {H_GET_MPP_X, "H_GET_MPP_X"}, \ {H_SET_MODE, "H_SET_MODE"}, \ - {H_RTAS, "H_RTAS"} + {H_REGISTER_PROC_TBL, "H_REGISTER_PROC_TBL"}, \ + {H_QUERY_VAS_CAPABILITIES, "H_QUERY_VAS_CAPABILITIES"}, \ + {H_INT_GET_SOURCE_INFO, "H_INT_GET_SOURCE_INFO"}, \ + {H_INT_SET_SOURCE_CONFIG, "H_INT_SET_SOURCE_CONFIG"}, \ + {H_INT_GET_QUEUE_INFO, "H_INT_GET_QUEUE_INFO"}, \ + {H_INT_SET_QUEUE_CONFIG, "H_INT_SET_QUEUE_CONFIG"}, \ + {H_INT_ESB, "H_INT_ESB"}, \ + {H_INT_RESET, "H_INT_RESET"}, \ + {H_RPT_INVALIDATE, "H_RPT_INVALIDATE"}, \ + {H_RTAS, "H_RTAS"}, \ + {H_LOGICAL_MEMOP, "H_LOGICAL_MEMOP"}, \ + {H_CAS, "H_CAS"}, \ + {H_UPDATE_DT, "H_UPDATE_DT"}, \ + {H_GET_PERF_COUNTER_INFO, "H_GET_PERF_COUNTER_INFO"}, \ + {H_SET_PARTITION_TABLE, "H_SET_PARTITION_TABLE"}, \ + {H_ENTER_NESTED, "H_ENTER_NESTED"}, \ + {H_TLB_INVALIDATE, "H_TLB_INVALIDATE"}, \ + {H_COPY_TOFROM_GUEST, "H_COPY_TOFROM_GUEST"} + #define kvm_trace_symbol_kvmret \ {RESUME_GUEST, "RESUME_GUEST"}, \ |