diff options
Diffstat (limited to 'arch/powerpc/kvm')
27 files changed, 399 insertions, 152 deletions
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index dbfdc126bf14..9a0d1c1aca6c 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -20,7 +20,6 @@ if VIRTUALIZATION config KVM bool select KVM_COMMON - select HAVE_KVM_VCPU_ASYNC_IOCTL select KVM_VFIO select HAVE_KVM_IRQ_BYPASS @@ -39,7 +38,6 @@ config KVM_BOOK3S_64_HANDLER config KVM_BOOK3S_PR_POSSIBLE bool select KVM_MMIO - select KVM_GENERIC_MMU_NOTIFIER config KVM_BOOK3S_HV_POSSIBLE bool @@ -82,7 +80,7 @@ config KVM_BOOK3S_64_HV tristate "KVM for POWER7 and later using hypervisor mode in host" depends on KVM_BOOK3S_64 && PPC_POWERNV select KVM_BOOK3S_HV_POSSIBLE - select KVM_GENERIC_MMU_NOTIFIER + select KVM_BOOK3S_HV_PMU select CMA help Support running unmodified book3s_64 guest kernels in @@ -171,6 +169,18 @@ config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND those buggy L1s which saves the L2 state, at the cost of performance in all nested-capable guest entry/exit. +config KVM_BOOK3S_HV_PMU + tristate "Hypervisor Perf events for KVM Book3s-HV" + depends on KVM_BOOK3S_64_HV + help + Enable Book3s-HV Hypervisor Perf events PMU named 'kvm-hv'. These + Perf events give an overview of hypervisor performance overall + instead of a specific guests. Currently the PMU reports + L0-Hypervisor stats on a kvm-hv enabled PSeries LPAR like: + * Total/Used Guest-Heap + * Total/Used Guest Page-table Memory + * Total amount of Guest Page-table Memory reclaimed + config KVM_BOOKE_HV bool @@ -191,7 +201,6 @@ config KVM_E500V2 depends on !CONTEXT_TRACKING_USER select KVM select KVM_MMIO - select KVM_GENERIC_MMU_NOTIFIER help Support running unmodified E500 guest kernels in virtual machines on E500v2 host processors. @@ -208,7 +217,6 @@ config KVM_E500MC select KVM select KVM_MMIO select KVM_BOOKE_HV - select KVM_GENERIC_MMU_NOTIFIER help Support running unmodified E500MC/E5500/E6500 guest kernels in virtual machines on E500MC/E5500/E6500 host processors. diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index d79c5d1098c0..2efbe05caed7 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -38,7 +38,7 @@ /* #define EXIT_DEBUG */ -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_ICOUNTER(VM, num_2M_pages), STATS_DESC_ICOUNTER(VM, num_1G_pages) @@ -53,7 +53,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, sum_exits), STATS_DESC_COUNTER(VCPU, mmio_exits), diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c index 5b7212edbb13..c7e4b62642ea 100644 --- a/arch/powerpc/kvm/book3s_32_mmu_host.c +++ b/arch/powerpc/kvm/book3s_32_mmu_host.c @@ -125,8 +125,6 @@ static u32 *kvmppc_mmu_get_pteg(struct kvm_vcpu *vcpu, u32 vsid, u32 eaddr, return (u32*)pteg; } -extern char etext[]; - int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte, bool iswrite) { diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index f305395cf26e..2ccb3d138f46 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -1494,7 +1494,7 @@ int kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, /* start new resize */ - resize = kzalloc(sizeof(*resize), GFP_KERNEL); + resize = kzalloc_obj(*resize); if (!resize) { ret = -ENOMEM; goto out; @@ -1943,7 +1943,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf) /* reject flags we don't recognize */ if (ghf->flags & ~(KVM_GET_HTAB_BOLTED_ONLY | KVM_GET_HTAB_WRITE)) return -EINVAL; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + ctx = kzalloc_obj(*ctx); if (!ctx) return -ENOMEM; kvm_get_kvm(kvm); @@ -1985,7 +1985,7 @@ static int debugfs_htab_open(struct inode *inode, struct file *file) struct kvm *kvm = inode->i_private; struct debugfs_htab_state *p; - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kzalloc_obj(*p); if (!p) return -ENOMEM; diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index b3e6e73d6a08..933fc7cb9afc 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -1256,7 +1256,7 @@ static int debugfs_radix_open(struct inode *inode, struct file *file) struct kvm *kvm = inode->i_private; struct debugfs_radix_state *p; - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kzalloc_obj(*p); if (!p) return -ENOMEM; diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 742aa58a7c7e..c5f3f5b29d89 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -178,7 +178,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, } rcu_read_unlock(); - stit = kzalloc(sizeof(*stit), GFP_KERNEL); + stit = kzalloc_obj(*stit); if (!stit) { iommu_tce_table_put(tbl); return -ENOMEM; @@ -305,7 +305,7 @@ int kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, return ret; ret = -ENOMEM; - stt = kzalloc(struct_size(stt, pages, npages), GFP_KERNEL | __GFP_NOWARN); + stt = kzalloc_flex(*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 86bff159c51e..61dbeea317f3 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -36,7 +36,6 @@ #include <linux/gfp.h> #include <linux/vmalloc.h> #include <linux/highmem.h> -#include <linux/hugetlb.h> #include <linux/kvm_irqfd.h> #include <linux/irqbypass.h> #include <linux/module.h> @@ -2790,7 +2789,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int id) { struct kvmppc_vcore *vcore; - vcore = kzalloc(sizeof(struct kvmppc_vcore), GFP_KERNEL); + vcore = kzalloc_obj(struct kvmppc_vcore); if (vcore == NULL) return NULL; @@ -2842,7 +2841,7 @@ static int debugfs_timings_open(struct inode *inode, struct file *file) struct kvm_vcpu *vcpu = inode->i_private; struct debugfs_timings_state *p; - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kzalloc_obj(*p); if (!p) return -ENOMEM; @@ -5637,7 +5636,7 @@ void kvmppc_alloc_host_rm_ops(void) if (kvmppc_host_rm_ops_hv != NULL) return; - ops = kzalloc(sizeof(struct kvmppc_host_rm_ops), GFP_KERNEL); + ops = kzalloc_obj(struct kvmppc_host_rm_ops); if (!ops) return; @@ -5960,7 +5959,7 @@ void kvmppc_free_pimap(struct kvm *kvm) static struct kvmppc_passthru_irqmap *kvmppc_alloc_pimap(void) { - return kzalloc(sizeof(struct kvmppc_passthru_irqmap), GFP_KERNEL); + return kzalloc_obj(struct kvmppc_passthru_irqmap); } static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) @@ -6041,7 +6040,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) * 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); + host_data = irq_domain_get_irq_data(irq_get_default_domain(), host_irq); irq_map->r_hwirq = (unsigned int)irqd_to_hwirq(host_data); if (i == pimap->n_mapped) @@ -6541,10 +6540,6 @@ static struct kvmppc_ops kvm_ops_hv = { .fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv, .arch_vm_ioctl = kvm_arch_vm_ioctl_hv, .hcall_implemented = kvmppc_hcall_impl_hv, -#ifdef CONFIG_KVM_XICS - .irq_bypass_add_producer = kvmppc_irq_bypass_add_producer_hv, - .irq_bypass_del_producer = kvmppc_irq_bypass_del_producer_hv, -#endif .configure_mmu = kvmhv_configure_mmu, .get_rmmu_info = kvmhv_get_rmmu_info, .set_smt_mode = kvmhv_set_smt_mode, @@ -6662,6 +6657,22 @@ static int kvmppc_book3s_init_hv(void) return r; } +#if defined(CONFIG_KVM_XICS) + /* + * IRQ bypass is supported only for interrupts whose EOI operations are + * handled via OPAL calls. Therefore, register IRQ bypass handlers + * exclusively for PowerNV KVM when booted with 'xive=off', indicating + * the use of the emulated XICS interrupt controller. + */ + if (!kvmhv_on_pseries()) { + pr_info("KVM-HV: Enabling IRQ bypass\n"); + kvm_ops_hv.irq_bypass_add_producer = + kvmppc_irq_bypass_add_producer_hv; + kvm_ops_hv.irq_bypass_del_producer = + kvmppc_irq_bypass_del_producer_hv; + } +#endif + kvm_ops_hv.owner = THIS_MODULE; kvmppc_hv_ops = &kvm_ops_hv; diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 5f8c2321cfb5..22e616662255 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -726,7 +726,7 @@ static struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int struct kvm_nested_guest *gp; long shadow_lpid; - gp = kzalloc(sizeof(*gp), GFP_KERNEL); + gp = kzalloc_obj(*gp); if (!gp) return NULL; gp->l1_host = kvm; @@ -1671,7 +1671,7 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu, /* 4. Insert the pte into our shadow_pgtable */ - n_rmap = kzalloc(sizeof(*n_rmap), GFP_KERNEL); + n_rmap = kzalloc_obj(*n_rmap); if (!n_rmap) return RESUME_GUEST; /* Let the guest try again */ n_rmap->rmap = (n_gpa & RMAP_NESTED_GPA_MASK) | diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c index e5c7ce1fb761..87691cf86cae 100644 --- a/arch/powerpc/kvm/book3s_hv_nestedv2.c +++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c @@ -123,6 +123,12 @@ static size_t gs_msg_ops_vcpu_get_size(struct kvmppc_gs_msg *gsm) case KVMPPC_GSID_PROCESS_TABLE: case KVMPPC_GSID_RUN_INPUT: case KVMPPC_GSID_RUN_OUTPUT: + /* Host wide counters */ + case KVMPPC_GSID_L0_GUEST_HEAP: + case KVMPPC_GSID_L0_GUEST_HEAP_MAX: + case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE: + case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX: + case KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM: break; default: size += kvmppc_gse_total_size(kvmppc_gsid_size(iden)); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index ea7ad200b330..83f7504349d2 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1524,14 +1524,12 @@ kvm_flush_link_stack: /* Flush the link stack. On Power8 it's up to 32 entries in size. */ .rept 32 - ANNOTATE_INTRA_FUNCTION_CALL bl .+4 .endr /* And on Power9 it's up to 64. */ BEGIN_FTR_SECTION .rept 32 - ANNOTATE_INTRA_FUNCTION_CALL bl .+4 .endr END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 3a6592a31a10..5fbb95d90e99 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -249,7 +249,7 @@ int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) { struct kvmppc_uvmem_slot *p; - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kzalloc_obj(*p); if (!p) return -ENOMEM; p->pfns = vcalloc(slot->npages, sizeof(*p->pfns)); @@ -393,7 +393,7 @@ static int kvmppc_memslot_page_merge(struct kvm *kvm, { unsigned long gfn = memslot->base_gfn; unsigned long end, start = gfn_to_hva(kvm, gfn); - unsigned long vm_flags; + vm_flags_t vm_flags; int ret = 0; struct vm_area_struct *vma; int merge_flag = (merge) ? MADV_MERGEABLE : MADV_UNMERGEABLE; @@ -711,7 +711,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) bitmap_set(kvmppc_uvmem_bitmap, bit, 1); spin_unlock(&kvmppc_uvmem_bitmap_lock); - pvt = kzalloc(sizeof(*pvt), GFP_KERNEL); + pvt = kzalloc_obj(*pvt); if (!pvt) goto out_clear; @@ -723,7 +723,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) dpage = pfn_to_page(uvmem_pfn); dpage->zone_device_data = pvt; - zone_device_page_init(dpage); + zone_device_page_init(dpage, &kvmppc_uvmem_pgmap, 0); return dpage; out_clear: spin_lock(&kvmppc_uvmem_bitmap_lock); @@ -1014,8 +1014,9 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf) * to a normal PFN during H_SVM_PAGE_OUT. * Gets called with kvm->arch.uvmem_lock held. */ -static void kvmppc_uvmem_page_free(struct page *page) +static void kvmppc_uvmem_folio_free(struct folio *folio) { + struct page *page = &folio->page; unsigned long pfn = page_to_pfn(page) - (kvmppc_uvmem_pgmap.range.start >> PAGE_SHIFT); struct kvmppc_uvmem_page_pvt *pvt; @@ -1034,7 +1035,7 @@ static void kvmppc_uvmem_page_free(struct page *page) } static const struct dev_pagemap_ops kvmppc_uvmem_ops = { - .page_free = kvmppc_uvmem_page_free, + .folio_free = kvmppc_uvmem_folio_free, .migrate_to_ram = kvmppc_uvmem_migrate_to_ram, }; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 83bcdc80ce51..2ba2dd26a7ea 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1738,8 +1738,7 @@ static int kvmppc_core_vcpu_create_pr(struct kvm_vcpu *vcpu) vcpu->arch.book3s = vcpu_book3s; #ifdef CONFIG_KVM_BOOK3S_32_HANDLER - vcpu->arch.shadow_vcpu = - kzalloc(sizeof(*vcpu->arch.shadow_vcpu), GFP_KERNEL); + vcpu->arch.shadow_vcpu = kzalloc_obj(*vcpu->arch.shadow_vcpu); if (!vcpu->arch.shadow_vcpu) goto free_vcpu3s; #endif diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index 6808bda0dbc1..0507715d0fdd 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -183,7 +183,7 @@ static int rtas_token_define(struct kvm *kvm, char *name, u64 token) if (!found) return -ENOENT; - d = kzalloc(sizeof(*d), GFP_KERNEL); + d = kzalloc_obj(*d); if (!d) return -ENOMEM; diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index 589a8f257120..74a44fa702b0 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -1037,7 +1037,7 @@ static struct kvmppc_ics *kvmppc_xics_create_ics(struct kvm *kvm, goto out; /* Create the ICS */ - ics = kzalloc(sizeof(struct kvmppc_ics), GFP_KERNEL); + ics = kzalloc_obj(struct kvmppc_ics); if (!ics) goto out; @@ -1069,7 +1069,7 @@ static int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server_nu if (kvmppc_xics_find_server(vcpu->kvm, server_num)) return -EEXIST; - icp = kzalloc(sizeof(struct kvmppc_icp), GFP_KERNEL); + icp = kzalloc_obj(struct kvmppc_icp); if (!icp) return -ENOMEM; @@ -1388,7 +1388,7 @@ static struct kvmppc_xics *kvmppc_xics_get_device(struct kvm *kvm) struct kvmppc_xics *xics = *kvm_xics_device; if (!xics) { - xics = kzalloc(sizeof(*xics), GFP_KERNEL); + xics = kzalloc_obj(*xics); *kvm_xics_device = xics; } else { memset(xics, 0, sizeof(*xics)); diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 1362c672387e..1d67237783b7 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -916,8 +916,7 @@ int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio, * it fires once. */ if (single_escalation) { - struct irq_data *d = irq_get_irq_data(xc->esc_virq[prio]); - struct xive_irq_data *xd = irq_data_get_irq_handler_data(d); + struct xive_irq_data *xd = irq_get_chip_data(xc->esc_virq[prio]); xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01); vcpu->arch.xive_esc_raddr = xd->eoi_page; @@ -1555,7 +1554,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq, struct kvmppc_xive_src_block *sb; struct kvmppc_xive_irq_state *state; struct irq_data *host_data = - irq_domain_get_irq_data(irq_get_default_host(), host_irq); + irq_domain_get_irq_data(irq_get_default_domain(), host_irq); unsigned int hw_irq = (unsigned int)irqd_to_hwirq(host_data); u16 idx; u8 prio; @@ -1612,7 +1611,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq, /* Grab info about irq */ state->pt_number = hw_irq; - state->pt_data = irq_data_get_irq_handler_data(host_data); + state->pt_data = irq_data_get_irq_chip_data(host_data); /* * Configure the IRQ to match the existing configuration of @@ -1787,8 +1786,7 @@ void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu) */ void xive_cleanup_single_escalation(struct kvm_vcpu *vcpu, int irq) { - struct irq_data *d = irq_get_irq_data(irq); - struct xive_irq_data *xd = irq_data_get_irq_handler_data(d); + struct xive_irq_data *xd = irq_get_chip_data(irq); /* * This slightly odd sequence gives the right result @@ -1926,7 +1924,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, if (r) goto bail; - xc = kzalloc(sizeof(*xc), GFP_KERNEL); + xc = kzalloc_obj(*xc); if (!xc) { r = -ENOMEM; goto bail; @@ -2278,7 +2276,7 @@ struct kvmppc_xive_src_block *kvmppc_xive_create_src_block( goto out; /* Create the ICS */ - sb = kzalloc(sizeof(*sb), GFP_KERNEL); + sb = kzalloc_obj(*sb); if (!sb) goto out; @@ -2721,7 +2719,7 @@ struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type) struct kvmppc_xive *xive = *kvm_xive_device; if (!xive) { - xive = kzalloc(sizeof(*xive), GFP_KERNEL); + xive = kzalloc_obj(*xive); *kvm_xive_device = xive; } else { memset(xive, 0, sizeof(*xive)); @@ -2827,9 +2825,7 @@ int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu) i0, i1); } if (xc->esc_virq[i]) { - struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]); - struct xive_irq_data *xd = - irq_data_get_irq_handler_data(d); + struct xive_irq_data *xd = irq_get_chip_data(xc->esc_virq[i]); u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET); seq_printf(m, " ESC %d %c%c EOI @%llx", diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index d9bf1bc3ff61..728b5606dd14 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -145,7 +145,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, if (rc) goto bail; - xc = kzalloc(sizeof(*xc), GFP_KERNEL); + xc = kzalloc_obj(*xc); if (!xc) { rc = -ENOMEM; goto bail; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 6a5be025a8af..f3ddb24ece74 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -36,7 +36,7 @@ unsigned long kvmppc_booke_handlers; -const struct _kvm_stats_desc kvm_vm_stats_desc[] = { +const struct kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), STATS_DESC_ICOUNTER(VM, num_2M_pages), STATS_DESC_ICOUNTER(VM, num_1G_pages) @@ -51,7 +51,7 @@ const struct kvm_stats_header kvm_vm_stats_header = { sizeof(kvm_vm_stats_desc), }; -const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = { +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { KVM_GENERIC_VCPU_STATS(), STATS_DESC_COUNTER(VCPU, sum_exits), STATS_DESC_COUNTER(VCPU, mmio_exits), @@ -572,7 +572,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu, /* * Return the number of jiffies until the next timeout. If the timeout is - * longer than the NEXT_TIMER_MAX_DELTA, then return NEXT_TIMER_MAX_DELTA + * longer than the TIMER_NEXT_MAX_DELTA, then return TIMER_NEXT_MAX_DELTA * because the larger value can break the timer APIs. */ static unsigned long watchdog_next_timeout(struct kvm_vcpu *vcpu) @@ -598,7 +598,7 @@ static unsigned long watchdog_next_timeout(struct kvm_vcpu *vcpu) if (do_div(nr_jiffies, tb_ticks_per_jiffy)) nr_jiffies++; - return min_t(unsigned long long, nr_jiffies, NEXT_TIMER_MAX_DELTA); + return min_t(unsigned long long, nr_jiffies, TIMER_NEXT_MAX_DELTA); } static void arm_next_watchdog(struct kvm_vcpu *vcpu) @@ -616,19 +616,19 @@ static void arm_next_watchdog(struct kvm_vcpu *vcpu) spin_lock_irqsave(&vcpu->arch.wdt_lock, flags); nr_jiffies = watchdog_next_timeout(vcpu); /* - * If the number of jiffies of watchdog timer >= NEXT_TIMER_MAX_DELTA + * If the number of jiffies of watchdog timer >= TIMER_NEXT_MAX_DELTA * then do not run the watchdog timer as this can break timer APIs. */ - if (nr_jiffies < NEXT_TIMER_MAX_DELTA) + if (nr_jiffies < TIMER_NEXT_MAX_DELTA) mod_timer(&vcpu->arch.wdt_timer, jiffies + nr_jiffies); else - del_timer(&vcpu->arch.wdt_timer); + timer_delete(&vcpu->arch.wdt_timer); spin_unlock_irqrestore(&vcpu->arch.wdt_lock, flags); } static void kvmppc_watchdog_func(struct timer_list *t) { - struct kvm_vcpu *vcpu = from_timer(vcpu, t, arch.wdt_timer); + struct kvm_vcpu *vcpu = timer_container_of(vcpu, t, arch.wdt_timer); u32 tsr, new_tsr; int final; @@ -1441,7 +1441,7 @@ int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu) void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu) { - del_timer_sync(&vcpu->arch.wdt_timer); + timer_delete_sync(&vcpu->arch.wdt_timer); } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index b0f695428733..c58a5a5fb64c 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -119,7 +119,7 @@ static inline void local_sid_destroy_all(void) static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500) { - vcpu_e500->idt = kzalloc(sizeof(struct vcpu_id_table), GFP_KERNEL); + vcpu_e500->idt = kzalloc_obj(struct vcpu_id_table); return vcpu_e500->idt; } diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index f9acf866c709..e4469ad73a2e 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -39,15 +39,11 @@ enum vcpu_ftr { /* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */ #define E500_TLB_MAS2_ATTR (0x7f) -struct tlbe_ref { +struct tlbe_priv { kvm_pfn_t pfn; /* valid only for TLB0, except briefly */ unsigned int flags; /* E500_TLB_* */ }; -struct tlbe_priv { - struct tlbe_ref ref; -}; - #ifdef CONFIG_KVM_E500V2 struct vcpu_id_table; #endif diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c index e131fbecdcc4..75ed1496ead5 100644 --- a/arch/powerpc/kvm/e500_mmu.c +++ b/arch/powerpc/kvm/e500_mmu.c @@ -772,7 +772,7 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu, num_pages = DIV_ROUND_UP(cfg->array + array_len - 1, PAGE_SIZE) - cfg->array / PAGE_SIZE; - pages = kmalloc_array(num_pages, sizeof(*pages), GFP_KERNEL); + pages = kmalloc_objs(*pages, num_pages); if (!pages) return -ENOMEM; @@ -792,13 +792,13 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu, goto put_pages; } - privs[0] = kcalloc(params.tlb_sizes[0], sizeof(*privs[0]), GFP_KERNEL); + privs[0] = kzalloc_objs(*privs[0], params.tlb_sizes[0]); if (!privs[0]) { ret = -ENOMEM; goto put_pages; } - privs[1] = kcalloc(params.tlb_sizes[1], sizeof(*privs[1]), GFP_KERNEL); + privs[1] = kzalloc_objs(*privs[1], params.tlb_sizes[1]); if (!privs[1]) { ret = -ENOMEM; goto free_privs_first; @@ -912,25 +912,21 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500) vcpu_e500->gtlb_params[1].ways = KVM_E500_TLB1_SIZE; vcpu_e500->gtlb_params[1].sets = 1; - vcpu_e500->gtlb_arch = kmalloc_array(KVM_E500_TLB0_SIZE + - KVM_E500_TLB1_SIZE, - sizeof(*vcpu_e500->gtlb_arch), - GFP_KERNEL); + vcpu_e500->gtlb_arch = kmalloc_objs(*vcpu_e500->gtlb_arch, + KVM_E500_TLB0_SIZE + KVM_E500_TLB1_SIZE); if (!vcpu_e500->gtlb_arch) return -ENOMEM; vcpu_e500->gtlb_offset[0] = 0; vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE; - vcpu_e500->gtlb_priv[0] = kcalloc(vcpu_e500->gtlb_params[0].entries, - sizeof(struct tlbe_ref), - GFP_KERNEL); + vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_priv, + vcpu_e500->gtlb_params[0].entries); if (!vcpu_e500->gtlb_priv[0]) goto free_vcpu; - vcpu_e500->gtlb_priv[1] = kcalloc(vcpu_e500->gtlb_params[1].entries, - sizeof(struct tlbe_ref), - GFP_KERNEL); + vcpu_e500->gtlb_priv[1] = kzalloc_objs(struct tlbe_priv, + vcpu_e500->gtlb_params[1].entries); if (!vcpu_e500->gtlb_priv[1]) goto free_vcpu; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 06caf8bbbe2b..37e0d3d9e244 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -189,16 +189,16 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, { struct kvm_book3e_206_tlb_entry *gtlbe = get_entry(vcpu_e500, tlbsel, esel); - struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref; + struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[tlbsel][esel]; /* Don't bother with unmapped entries */ - if (!(ref->flags & E500_TLB_VALID)) { - WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), - "%s: flags %x\n", __func__, ref->flags); + if (!(tlbe->flags & E500_TLB_VALID)) { + WARN(tlbe->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), + "%s: flags %x\n", __func__, tlbe->flags); WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]); } - if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) { + if (tlbsel == 1 && tlbe->flags & E500_TLB_BITMAP) { u64 tmp = vcpu_e500->g2h_tlb1_map[esel]; int hw_tlb_indx; unsigned long flags; @@ -216,28 +216,28 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, } mb(); vcpu_e500->g2h_tlb1_map[esel] = 0; - ref->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID); + tlbe->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID); local_irq_restore(flags); } - if (tlbsel == 1 && ref->flags & E500_TLB_TLB0) { + if (tlbsel == 1 && tlbe->flags & E500_TLB_TLB0) { /* * TLB1 entry is backed by 4k pages. This should happen * rarely and is not worth optimizing. Invalidate everything. */ kvmppc_e500_tlbil_all(vcpu_e500); - ref->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID); + tlbe->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID); } /* * If TLB entry is still valid then it's a TLB0 entry, and thus * backed by at most one host tlbe per shadow pid */ - if (ref->flags & E500_TLB_VALID) + if (tlbe->flags & E500_TLB_VALID) kvmppc_e500_tlbil_one(vcpu_e500, gtlbe); /* Mark the TLB as not backed by the host anymore */ - ref->flags = 0; + tlbe->flags = 0; } static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) @@ -245,26 +245,26 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) return tlbe->mas7_3 & (MAS3_SW|MAS3_UW); } -static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, - struct kvm_book3e_206_tlb_entry *gtlbe, - kvm_pfn_t pfn, unsigned int wimg, - bool writable) +static inline void kvmppc_e500_tlbe_setup(struct tlbe_priv *tlbe, + struct kvm_book3e_206_tlb_entry *gtlbe, + kvm_pfn_t pfn, unsigned int wimg, + bool writable) { - ref->pfn = pfn; - ref->flags = E500_TLB_VALID; + tlbe->pfn = pfn; + tlbe->flags = E500_TLB_VALID; if (writable) - ref->flags |= E500_TLB_WRITABLE; + tlbe->flags |= E500_TLB_WRITABLE; /* Use guest supplied MAS2_G and MAS2_E */ - ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; + tlbe->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; } -static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) +static inline void kvmppc_e500_tlbe_release(struct tlbe_priv *tlbe) { - if (ref->flags & E500_TLB_VALID) { + if (tlbe->flags & E500_TLB_VALID) { /* FIXME: don't log bogus pfn for TLB1 */ - trace_kvm_booke206_ref_release(ref->pfn, ref->flags); - ref->flags = 0; + trace_kvm_booke206_ref_release(tlbe->pfn, tlbe->flags); + tlbe->flags = 0; } } @@ -284,11 +284,8 @@ static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500) int i; for (tlbsel = 0; tlbsel <= 1; tlbsel++) { - for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->gtlb_priv[tlbsel][i].ref; - kvmppc_e500_ref_release(ref); - } + for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) + kvmppc_e500_tlbe_release(&vcpu_e500->gtlb_priv[tlbsel][i]); } } @@ -304,18 +301,18 @@ void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu) static void kvmppc_e500_setup_stlbe( struct kvm_vcpu *vcpu, struct kvm_book3e_206_tlb_entry *gtlbe, - int tsize, struct tlbe_ref *ref, u64 gvaddr, + int tsize, struct tlbe_priv *tlbe, u64 gvaddr, struct kvm_book3e_206_tlb_entry *stlbe) { - kvm_pfn_t pfn = ref->pfn; + kvm_pfn_t pfn = tlbe->pfn; u32 pr = vcpu->arch.shared->msr & MSR_PR; - bool writable = !!(ref->flags & E500_TLB_WRITABLE); + bool writable = !!(tlbe->flags & E500_TLB_WRITABLE); - BUG_ON(!(ref->flags & E500_TLB_VALID)); + BUG_ON(!(tlbe->flags & E500_TLB_VALID)); /* Force IPROT=0 for all guest mappings. */ stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID; - stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR); + stlbe->mas2 = (gvaddr & MAS2_EPN) | (tlbe->flags & E500_TLB_MAS2_ATTR); stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) | e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr); } @@ -323,7 +320,7 @@ static void kvmppc_e500_setup_stlbe( static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe, - struct tlbe_ref *ref) + struct tlbe_priv *tlbe) { struct kvm_memory_slot *slot; unsigned int psize; @@ -455,9 +452,9 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, } } - kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable); + kvmppc_e500_tlbe_setup(tlbe, gtlbe, pfn, wimg, writable); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, - ref, gvaddr, stlbe); + tlbe, gvaddr, stlbe); writable = tlbe_is_writable(stlbe); /* Clear i-cache for new pages */ @@ -474,17 +471,17 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel, struct kvm_book3e_206_tlb_entry *stlbe) { struct kvm_book3e_206_tlb_entry *gtlbe; - struct tlbe_ref *ref; + struct tlbe_priv *tlbe; int stlbsel = 0; int sesel = 0; int r; gtlbe = get_entry(vcpu_e500, 0, esel); - ref = &vcpu_e500->gtlb_priv[0][esel].ref; + tlbe = &vcpu_e500->gtlb_priv[0][esel]; r = kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe), get_tlb_raddr(gtlbe) >> PAGE_SHIFT, - gtlbe, 0, stlbe, ref); + gtlbe, 0, stlbe, tlbe); if (r) return r; @@ -494,7 +491,7 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel, } static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, - struct tlbe_ref *ref, + struct tlbe_priv *tlbe, int esel) { unsigned int sesel = vcpu_e500->host_tlb1_nv++; @@ -507,10 +504,10 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel); } - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; + vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_BITMAP; vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1; - WARN_ON(!(ref->flags & E500_TLB_VALID)); + WARN_ON(!(tlbe->flags & E500_TLB_VALID)); return sesel; } @@ -522,24 +519,24 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, struct kvm_book3e_206_tlb_entry *stlbe, int esel) { - struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref; + struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[1][esel]; int sesel; int r; r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, - ref); + tlbe); if (r) return r; /* Use TLB0 when we can only map a page with 4k */ if (get_tlb_tsize(stlbe) == BOOK3E_PAGESZ_4K) { - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_TLB0; + vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_TLB0; write_stlbe(vcpu_e500, gtlbe, stlbe, 0, 0); return 0; } /* Otherwise map into TLB1 */ - sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel); + sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, tlbe, esel); write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel); return 0; @@ -561,11 +558,11 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, priv = &vcpu_e500->gtlb_priv[tlbsel][esel]; /* Triggers after clear_tlb_privs or on initial mapping */ - if (!(priv->ref.flags & E500_TLB_VALID)) { + if (!(priv->flags & E500_TLB_VALID)) { kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe); } else { kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K, - &priv->ref, eaddr, &stlbe); + priv, eaddr, &stlbe); write_stlbe(vcpu_e500, gtlbe, &stlbe, 0, 0); } break; diff --git a/arch/powerpc/kvm/guest-state-buffer.c b/arch/powerpc/kvm/guest-state-buffer.c index b80dbc58621f..42843eca6727 100644 --- a/arch/powerpc/kvm/guest-state-buffer.c +++ b/arch/powerpc/kvm/guest-state-buffer.c @@ -28,7 +28,7 @@ struct kvmppc_gs_buff *kvmppc_gsb_new(size_t size, unsigned long guest_id, { struct kvmppc_gs_buff *gsb; - gsb = kzalloc(sizeof(*gsb), flags); + gsb = kzalloc_obj(*gsb, flags); if (!gsb) return NULL; @@ -92,6 +92,10 @@ static int kvmppc_gsid_class(u16 iden) (iden <= KVMPPC_GSE_GUESTWIDE_END)) return KVMPPC_GS_CLASS_GUESTWIDE; + if ((iden >= KVMPPC_GSE_HOSTWIDE_START) && + (iden <= KVMPPC_GSE_HOSTWIDE_END)) + return KVMPPC_GS_CLASS_HOSTWIDE; + if ((iden >= KVMPPC_GSE_META_START) && (iden <= KVMPPC_GSE_META_END)) return KVMPPC_GS_CLASS_META; @@ -118,6 +122,21 @@ static int kvmppc_gsid_type(u16 iden) int type = -1; switch (kvmppc_gsid_class(iden)) { + case KVMPPC_GS_CLASS_HOSTWIDE: + switch (iden) { + case KVMPPC_GSID_L0_GUEST_HEAP: + fallthrough; + case KVMPPC_GSID_L0_GUEST_HEAP_MAX: + fallthrough; + case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE: + fallthrough; + case KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX: + fallthrough; + case KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM: + type = KVMPPC_GSE_BE64; + break; + } + break; case KVMPPC_GS_CLASS_GUESTWIDE: switch (iden) { case KVMPPC_GSID_HOST_STATE_SIZE: @@ -187,6 +206,9 @@ unsigned long kvmppc_gsid_flags(u16 iden) case KVMPPC_GS_CLASS_GUESTWIDE: flags = KVMPPC_GS_FLAGS_WIDE; break; + case KVMPPC_GS_CLASS_HOSTWIDE: + flags = KVMPPC_GS_FLAGS_HOST_WIDE; + break; case KVMPPC_GS_CLASS_META: case KVMPPC_GS_CLASS_DWORD_REG: case KVMPPC_GS_CLASS_WORD_REG: @@ -310,6 +332,13 @@ static inline int kvmppc_gse_flatten_iden(u16 iden) bit += KVMPPC_GSE_GUESTWIDE_COUNT; + if (class == KVMPPC_GS_CLASS_HOSTWIDE) { + bit += iden - KVMPPC_GSE_HOSTWIDE_START; + return bit; + } + + bit += KVMPPC_GSE_HOSTWIDE_COUNT; + if (class == KVMPPC_GS_CLASS_META) { bit += iden - KVMPPC_GSE_META_START; return bit; @@ -356,6 +385,12 @@ static inline u16 kvmppc_gse_unflatten_iden(int bit) } bit -= KVMPPC_GSE_GUESTWIDE_COUNT; + if (bit < KVMPPC_GSE_HOSTWIDE_COUNT) { + iden = KVMPPC_GSE_HOSTWIDE_START + bit; + return iden; + } + bit -= KVMPPC_GSE_HOSTWIDE_COUNT; + if (bit < KVMPPC_GSE_META_COUNT) { iden = KVMPPC_GSE_META_START + bit; return iden; @@ -505,7 +540,7 @@ struct kvmppc_gs_msg *kvmppc_gsm_new(struct kvmppc_gs_msg_ops *ops, void *data, { struct kvmppc_gs_msg *gsm; - gsm = kzalloc(sizeof(*gsm), gfp_flags); + gsm = kzalloc_obj(*gsm, gfp_flags); if (!gsm) return NULL; @@ -588,6 +623,8 @@ int kvmppc_gsb_send(struct kvmppc_gs_buff *gsb, unsigned long flags) if (flags & KVMPPC_GS_FLAGS_WIDE) hflags |= H_GUEST_FLAGS_WIDE; + if (flags & KVMPPC_GS_FLAGS_HOST_WIDE) + hflags |= H_GUEST_FLAGS_HOST_WIDE; rc = plpar_guest_set_state(hflags, gsb->guest_id, gsb->vcpu_id, __pa(gsb->hdr), gsb->capacity, &i); @@ -613,6 +650,8 @@ int kvmppc_gsb_recv(struct kvmppc_gs_buff *gsb, unsigned long flags) if (flags & KVMPPC_GS_FLAGS_WIDE) hflags |= H_GUEST_FLAGS_WIDE; + if (flags & KVMPPC_GS_FLAGS_HOST_WIDE) + hflags |= H_GUEST_FLAGS_HOST_WIDE; rc = plpar_guest_get_state(hflags, gsb->guest_id, gsb->vcpu_id, __pa(gsb->hdr), gsb->capacity, &i); diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c index 23e9c2bd9f27..3070f36d9fb8 100644 --- a/arch/powerpc/kvm/mpic.c +++ b/arch/powerpc/kvm/mpic.c @@ -1642,7 +1642,7 @@ static int mpic_set_default_irq_routing(struct openpic *opp) struct kvm_irq_routing_entry *routing; /* Create a nop default map, so that dereferencing it still works */ - routing = kzalloc((sizeof(*routing)), GFP_KERNEL); + routing = kzalloc_obj(*routing); if (!routing) return -ENOMEM; @@ -1661,7 +1661,7 @@ static int mpic_create(struct kvm_device *dev, u32 type) if (dev->kvm->arch.mpic) return -EINVAL; - opp = kzalloc(sizeof(struct openpic), GFP_KERNEL); + opp = kzalloc_obj(struct openpic); if (!opp) return -ENOMEM; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index ce1d91eed231..00302399fc37 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -69,7 +69,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) /* * Common checks before entering the guest world. Call with interrupts - * disabled. + * enabled. * * returns: * @@ -550,12 +550,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CAP_SPAPR_TCE: + fallthrough; case KVM_CAP_SPAPR_TCE_64: - r = 1; - break; case KVM_CAP_SPAPR_TCE_VFIO: - r = !!cpu_has_feature(CPU_FTR_HVMODE); - break; case KVM_CAP_PPC_RTAS: case KVM_CAP_PPC_FIXUP_HCALL: case KVM_CAP_PPC_ENABLE_HCALL: @@ -626,12 +623,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = !!(hv_enabled && kvmppc_hv_ops->enable_nested && !kvmppc_hv_ops->enable_nested(NULL)); break; -#endif - case KVM_CAP_SYNC_MMU: - BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER)); - r = 1; - break; -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE case KVM_CAP_PPC_HTAB_FD: r = hv_enabled; break; @@ -766,8 +757,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { int err; - hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); - vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup; + hrtimer_setup(&vcpu->arch.dec_timer, kvmppc_decrementer_wakeup, CLOCK_REALTIME, + HRTIMER_MODE_ABS); #ifdef CONFIG_KVM_EXIT_TIMING mutex_init(&vcpu->arch.exit_timing_lock); @@ -2031,8 +2022,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, return -EINVAL; } -long kvm_arch_vcpu_async_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) +long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; diff --git a/arch/powerpc/kvm/test-guest-state-buffer.c b/arch/powerpc/kvm/test-guest-state-buffer.c index bfd225329a18..5ccca306997a 100644 --- a/arch/powerpc/kvm/test-guest-state-buffer.c +++ b/arch/powerpc/kvm/test-guest-state-buffer.c @@ -5,6 +5,7 @@ #include <kunit/test.h> #include <asm/guest-state-buffer.h> +#include <asm/kvm_ppc.h> static void test_creating_buffer(struct kunit *test) { @@ -141,6 +142,16 @@ static void test_gs_bitmap(struct kunit *test) i++; } + for (u16 iden = KVMPPC_GSID_L0_GUEST_HEAP; + iden <= KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM; iden++) { + kvmppc_gsbm_set(&gsbm, iden); + kvmppc_gsbm_set(&gsbm1, iden); + KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden)); + kvmppc_gsbm_clear(&gsbm, iden); + KUNIT_EXPECT_FALSE(test, kvmppc_gsbm_test(&gsbm, iden)); + i++; + } + for (u16 iden = KVMPPC_GSID_RUN_INPUT; iden <= KVMPPC_GSID_VPA; iden++) { kvmppc_gsbm_set(&gsbm, iden); @@ -309,12 +320,215 @@ static void test_gs_msg(struct kunit *test) kvmppc_gsm_free(gsm); } +/* Test data struct for hostwide/L0 counters */ +struct kvmppc_gs_msg_test_hostwide_data { + u64 guest_heap; + u64 guest_heap_max; + u64 guest_pgtable_size; + u64 guest_pgtable_size_max; + u64 guest_pgtable_reclaim; +}; + +static size_t test_hostwide_get_size(struct kvmppc_gs_msg *gsm) + +{ + size_t size = 0; + u16 ids[] = { + KVMPPC_GSID_L0_GUEST_HEAP, + KVMPPC_GSID_L0_GUEST_HEAP_MAX, + KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE, + KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX, + KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM + }; + + for (int i = 0; i < ARRAY_SIZE(ids); i++) + size += kvmppc_gse_total_size(kvmppc_gsid_size(ids[i])); + return size; +} + +static int test_hostwide_fill_info(struct kvmppc_gs_buff *gsb, + struct kvmppc_gs_msg *gsm) +{ + struct kvmppc_gs_msg_test_hostwide_data *data = gsm->data; + + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_HEAP)) + kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_HEAP, + data->guest_heap); + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_HEAP_MAX)) + kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_HEAP_MAX, + data->guest_heap_max); + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE)) + kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE, + data->guest_pgtable_size); + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX)) + kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX, + data->guest_pgtable_size_max); + if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM)) + kvmppc_gse_put_u64(gsb, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM, + data->guest_pgtable_reclaim); + + return 0; +} + +static int test_hostwide_refresh_info(struct kvmppc_gs_msg *gsm, + struct kvmppc_gs_buff *gsb) +{ + struct kvmppc_gs_parser gsp = { 0 }; + struct kvmppc_gs_msg_test_hostwide_data *data = gsm->data; + struct kvmppc_gs_elem *gse; + int rc; + + rc = kvmppc_gse_parse(&gsp, gsb); + if (rc < 0) + return rc; + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP); + if (gse) + data->guest_heap = kvmppc_gse_get_u64(gse); + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP_MAX); + if (gse) + data->guest_heap_max = kvmppc_gse_get_u64(gse); + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE); + if (gse) + data->guest_pgtable_size = kvmppc_gse_get_u64(gse); + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX); + if (gse) + data->guest_pgtable_size_max = kvmppc_gse_get_u64(gse); + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM); + if (gse) + data->guest_pgtable_reclaim = kvmppc_gse_get_u64(gse); + + return 0; +} + +static struct kvmppc_gs_msg_ops gs_msg_test_hostwide_ops = { + .get_size = test_hostwide_get_size, + .fill_info = test_hostwide_fill_info, + .refresh_info = test_hostwide_refresh_info, +}; + +static void test_gs_hostwide_msg(struct kunit *test) +{ + struct kvmppc_gs_msg_test_hostwide_data test_data = { + .guest_heap = 0xdeadbeef, + .guest_heap_max = ~0ULL, + .guest_pgtable_size = 0xff, + .guest_pgtable_size_max = 0xffffff, + .guest_pgtable_reclaim = 0xdeadbeef, + }; + struct kvmppc_gs_msg *gsm; + struct kvmppc_gs_buff *gsb; + + gsm = kvmppc_gsm_new(&gs_msg_test_hostwide_ops, &test_data, GSM_SEND, + GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsm); + + gsb = kvmppc_gsb_new(kvmppc_gsm_size(gsm), 0, 0, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb); + + kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP); + kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP_MAX); + kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE); + kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX); + kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM); + + kvmppc_gsm_fill_info(gsm, gsb); + + memset(&test_data, 0, sizeof(test_data)); + + kvmppc_gsm_refresh_info(gsm, gsb); + KUNIT_EXPECT_EQ(test, test_data.guest_heap, 0xdeadbeef); + KUNIT_EXPECT_EQ(test, test_data.guest_heap_max, ~0ULL); + KUNIT_EXPECT_EQ(test, test_data.guest_pgtable_size, 0xff); + KUNIT_EXPECT_EQ(test, test_data.guest_pgtable_size_max, 0xffffff); + KUNIT_EXPECT_EQ(test, test_data.guest_pgtable_reclaim, 0xdeadbeef); + + kvmppc_gsm_free(gsm); +} + +/* Test if the H_GUEST_GET_STATE for hostwide counters works */ +static void test_gs_hostwide_counters(struct kunit *test) +{ + struct kvmppc_gs_msg_test_hostwide_data test_data; + struct kvmppc_gs_parser gsp = { 0 }; + + struct kvmppc_gs_msg *gsm; + struct kvmppc_gs_buff *gsb; + struct kvmppc_gs_elem *gse; + int rc; + + if (!kvmhv_on_pseries()) + kunit_skip(test, "This test need a kmv-hv guest"); + + gsm = kvmppc_gsm_new(&gs_msg_test_hostwide_ops, &test_data, GSM_SEND, + GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsm); + + gsb = kvmppc_gsb_new(kvmppc_gsm_size(gsm), 0, 0, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, gsb); + + kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP); + + kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_HEAP_MAX); + + kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE); + + kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX); + + kvmppc_gsm_include(gsm, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM); + + kvmppc_gsm_fill_info(gsm, gsb); + + /* With HOST_WIDE flags guestid and vcpuid will be ignored */ + rc = kvmppc_gsb_recv(gsb, KVMPPC_GS_FLAGS_HOST_WIDE); + KUNIT_ASSERT_EQ(test, rc, 0); + + /* Parse the guest state buffer is successful */ + rc = kvmppc_gse_parse(&gsp, gsb); + KUNIT_ASSERT_EQ(test, rc, 0); + + /* Parse the GSB and get the counters */ + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP); + KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 Heap counter missing"); + kunit_info(test, "Guest Heap Size=%llu bytes", + kvmppc_gse_get_u64(gse)); + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_HEAP_MAX); + KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 Heap counter max missing"); + kunit_info(test, "Guest Heap Size Max=%llu bytes", + kvmppc_gse_get_u64(gse)); + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE); + KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 page-table size missing"); + kunit_info(test, "Guest Page-table Size=%llu bytes", + kvmppc_gse_get_u64(gse)); + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_SIZE_MAX); + KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 page-table size-max missing"); + kunit_info(test, "Guest Page-table Size Max=%llu bytes", + kvmppc_gse_get_u64(gse)); + + gse = kvmppc_gsp_lookup(&gsp, KVMPPC_GSID_L0_GUEST_PGTABLE_RECLAIM); + KUNIT_ASSERT_NOT_NULL_MSG(test, gse, "L0 page-table reclaim size missing"); + kunit_info(test, "Guest Page-table Reclaim Size=%llu bytes", + kvmppc_gse_get_u64(gse)); + + kvmppc_gsm_free(gsm); + kvmppc_gsb_free(gsb); +} + static struct kunit_case guest_state_buffer_testcases[] = { KUNIT_CASE(test_creating_buffer), KUNIT_CASE(test_adding_element), KUNIT_CASE(test_gs_bitmap), KUNIT_CASE(test_gs_parsing), KUNIT_CASE(test_gs_msg), + KUNIT_CASE(test_gs_hostwide_msg), + KUNIT_CASE(test_gs_hostwide_counters), {} }; diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h index 45817ab82bb4..14b0e23f601f 100644 --- a/arch/powerpc/kvm/timing.h +++ b/arch/powerpc/kvm/timing.h @@ -38,11 +38,7 @@ static inline void kvmppc_set_exit_type(struct kvm_vcpu *vcpu, int type) {} static inline void kvmppc_account_exit_stat(struct kvm_vcpu *vcpu, int type) { /* type has to be known at build time for optimization */ - - /* The BUILD_BUG_ON below breaks in funny ways, commented out - * for now ... -BenH BUILD_BUG_ON(!__builtin_constant_p(type)); - */ switch (type) { case EXT_INTR_EXITS: vcpu->stat.ext_intr_exits++; diff --git a/arch/powerpc/kvm/trace_book3s.h b/arch/powerpc/kvm/trace_book3s.h index 372a82fa2de3..9260ddbd557f 100644 --- a/arch/powerpc/kvm/trace_book3s.h +++ b/arch/powerpc/kvm/trace_book3s.h @@ -25,6 +25,7 @@ {0xe00, "H_DATA_STORAGE"}, \ {0xe20, "H_INST_STORAGE"}, \ {0xe40, "H_EMUL_ASSIST"}, \ + {0xea0, "H_VIRT"}, \ {0xf00, "PERFMON"}, \ {0xf20, "ALTIVEC"}, \ {0xf40, "VSX"} |