From 46a26bf55714c1e2f17e34683292a389acb8e601 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 23 Dec 2009 14:35:16 -0200 Subject: KVM: modify memslots layout in struct kvm Have a pointer to an allocated region inside struct kvm. [alex: fix ppc book 3s] Signed-off-by: Alexander Graf Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bd5a616d9373..782bfb185f8a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -150,14 +150,18 @@ struct kvm_irq_routing_table {}; #endif +struct kvm_memslots { + int nmemslots; + struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS + + KVM_PRIVATE_MEM_SLOTS]; +}; + struct kvm { spinlock_t mmu_lock; spinlock_t requests_lock; struct rw_semaphore slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ - int nmemslots; - struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS + - KVM_PRIVATE_MEM_SLOTS]; + struct kvm_memslots *memslots; #ifdef CONFIG_KVM_APIC_ARCHITECTURE u32 bsp_vcpu_id; struct kvm_vcpu *bsp_vcpu; @@ -482,7 +486,7 @@ static inline void kvm_guest_exit(void) static inline int memslot_id(struct kvm *kvm, struct kvm_memory_slot *slot) { - return slot - kvm->memslots; + return slot - kvm->memslots->memslots; } static inline gpa_t gfn_to_gpa(gfn_t gfn) -- cgit v1.2.3 From f7784b8ec9b6a041fa828cfbe9012fe51933f5ac Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 23 Dec 2009 14:35:18 -0200 Subject: KVM: split kvm_arch_set_memory_region into prepare and commit Required for SRCU convertion later. Signed-off-by: Marcelo Tosatti --- arch/ia64/kvm/kvm-ia64.c | 16 +++++++++++---- arch/powerpc/kvm/powerpc.c | 18 ++++++++++++---- arch/s390/kvm/kvm-s390.c | 25 +++++++++++++++-------- arch/x86/kvm/x86.c | 51 ++++++++++++++++++++++++++-------------------- include/linux/kvm_host.h | 7 ++++++- virt/kvm/kvm_main.c | 12 +++++------ 6 files changed, 82 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 1ca1dbf48117..0757c7027986 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1578,15 +1578,15 @@ out: return r; } -int kvm_arch_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, struct kvm_memory_slot old, + struct kvm_userspace_memory_region *mem, int user_alloc) { unsigned long i; unsigned long pfn; - int npages = mem->memory_size >> PAGE_SHIFT; - struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot]; + int npages = memslot->npages; unsigned long base_gfn = memslot->base_gfn; if (base_gfn + npages > (KVM_MAX_MEM_SIZE >> PAGE_SHIFT)) @@ -1610,6 +1610,14 @@ int kvm_arch_set_memory_region(struct kvm *kvm, return 0; } +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot old, + int user_alloc) +{ + return; +} + void kvm_arch_flush_shadow(struct kvm *kvm) { kvm_flush_remote_tlbs(kvm); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index f06cf93b178e..4633e7850dd2 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -165,14 +165,24 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -int kvm_arch_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old, - int user_alloc) +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_memory_slot old, + struct kvm_userspace_memory_region *mem, + int user_alloc) { return 0; } +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot old, + int user_alloc) +{ + return; +} + + void kvm_arch_flush_shadow(struct kvm *kvm) { } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 3fa0a10e4668..c8002193d9d4 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -690,14 +690,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } /* Section: memory related */ -int kvm_arch_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old, - int user_alloc) +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_memory_slot old, + struct kvm_userspace_memory_region *mem, + int user_alloc) { - int i; - struct kvm_vcpu *vcpu; - /* A few sanity checks. We can have exactly one memory slot which has to start at guest virtual zero and which has to be located at a page boundary in userland and which has to end at a page boundary. @@ -720,14 +718,23 @@ int kvm_arch_set_memory_region(struct kvm *kvm, if (!user_alloc) return -EINVAL; + return 0; +} + +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot old, + int user_alloc) +{ + int i; + struct kvm_vcpu *vcpu; + /* request update of sie control block for all available vcpus */ kvm_for_each_vcpu(i, vcpu, kvm) { if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) continue; kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP); } - - return 0; } void kvm_arch_flush_shadow(struct kvm *kvm) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1ce833191430..43da65feed49 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5228,13 +5228,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kfree(kvm); } -int kvm_arch_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, struct kvm_memory_slot old, + struct kvm_userspace_memory_region *mem, int user_alloc) { - int npages = mem->memory_size >> PAGE_SHIFT; - struct kvm_memory_slot *memslot = &kvm->memslots->memslots[mem->slot]; + int npages = memslot->npages; /*To keep backward compatibility with older userspace, *x86 needs to hanlde !user_alloc case. @@ -5254,26 +5254,35 @@ int kvm_arch_set_memory_region(struct kvm *kvm, if (IS_ERR((void *)userspace_addr)) return PTR_ERR((void *)userspace_addr); - /* set userspace_addr atomically for kvm_hva_to_rmapp */ - spin_lock(&kvm->mmu_lock); memslot->userspace_addr = userspace_addr; - spin_unlock(&kvm->mmu_lock); - } else { - if (!old.user_alloc && old.rmap) { - int ret; - - down_write(¤t->mm->mmap_sem); - ret = do_munmap(current->mm, old.userspace_addr, - old.npages * PAGE_SIZE); - up_write(¤t->mm->mmap_sem); - if (ret < 0) - printk(KERN_WARNING - "kvm_vm_ioctl_set_memory_region: " - "failed to munmap memory\n"); - } } } + + return 0; +} + +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot old, + int user_alloc) +{ + + int npages = mem->memory_size >> PAGE_SHIFT; + + if (!user_alloc && !old.user_alloc && old.rmap && !npages) { + int ret; + + down_write(¤t->mm->mmap_sem); + ret = do_munmap(current->mm, old.userspace_addr, + old.npages * PAGE_SIZE); + up_write(¤t->mm->mmap_sem); + if (ret < 0) + printk(KERN_WARNING + "kvm_vm_ioctl_set_memory_region: " + "failed to munmap memory\n"); + } + spin_lock(&kvm->mmu_lock); if (!kvm->arch.n_requested_mmu_pages) { unsigned int nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); @@ -5282,8 +5291,6 @@ int kvm_arch_set_memory_region(struct kvm *kvm, kvm_mmu_slot_remove_write_access(kvm, mem->slot); spin_unlock(&kvm->mmu_lock); - - return 0; } void kvm_arch_flush_shadow(struct kvm *kvm) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 782bfb185f8a..3c44687b3425 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -253,7 +253,12 @@ int kvm_set_memory_region(struct kvm *kvm, int __kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, int user_alloc); -int kvm_arch_set_memory_region(struct kvm *kvm, +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, + struct kvm_memory_slot old, + struct kvm_userspace_memory_region *mem, + int user_alloc); +void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, struct kvm_memory_slot old, int user_alloc); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 86dd8f3d29c9..c9f6cfe83120 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -663,6 +663,10 @@ skip_lpage: if (!npages) kvm_arch_flush_shadow(kvm); + r = kvm_arch_prepare_memory_region(kvm, &new, old, mem, user_alloc); + if (r) + goto out_free; + spin_lock(&kvm->mmu_lock); if (mem->slot >= kvm->memslots->nmemslots) kvm->memslots->nmemslots = mem->slot + 1; @@ -670,13 +674,7 @@ skip_lpage: *memslot = new; spin_unlock(&kvm->mmu_lock); - r = kvm_arch_set_memory_region(kvm, mem, old, user_alloc); - if (r) { - spin_lock(&kvm->mmu_lock); - *memslot = old; - spin_unlock(&kvm->mmu_lock); - goto out_free; - } + kvm_arch_commit_memory_region(kvm, mem, old, user_alloc); kvm_free_physmem_slot(&old, npages ? &new : NULL); /* Slot deletion case: we have to update the current slot */ -- cgit v1.2.3 From 506f0d6f9c40ae7d9634acf3c26358810f42c24a Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 23 Dec 2009 14:35:19 -0200 Subject: KVM: introduce gfn_to_pfn_memslot Which takes a memslot pointer instead of using kvm->memslots. To be used by SRCU convertion later. Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 2 ++ virt/kvm/kvm_main.c | 33 +++++++++++++++++++++++++-------- 2 files changed, 27 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3c44687b3425..f1f78deece10 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -273,6 +273,8 @@ void kvm_set_page_dirty(struct page *page); void kvm_set_page_accessed(struct page *page); pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); +pfn_t gfn_to_pfn_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn); void kvm_release_pfn_dirty(pfn_t); void kvm_release_pfn_clean(pfn_t pfn); void kvm_set_pfn_dirty(pfn_t pfn); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c9f6cfe83120..4e2321c733f7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -835,21 +835,14 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_hva); -pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) +static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr) { struct page *page[1]; - unsigned long addr; int npages; pfn_t pfn; might_sleep(); - addr = gfn_to_hva(kvm, gfn); - if (kvm_is_error_hva(addr)) { - get_page(bad_page); - return page_to_pfn(bad_page); - } - npages = get_user_pages_fast(addr, 1, 1, page); if (unlikely(npages != 1)) { @@ -874,8 +867,32 @@ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) return pfn; } +pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) +{ + unsigned long addr; + + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) { + get_page(bad_page); + return page_to_pfn(bad_page); + } + + return hva_to_pfn(kvm, addr); +} EXPORT_SYMBOL_GPL(gfn_to_pfn); +static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +{ + return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE); +} + +pfn_t gfn_to_pfn_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn) +{ + unsigned long addr = gfn_to_hva_memslot(slot, gfn); + return hva_to_pfn(kvm, addr); +} + struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) { pfn_t pfn; -- cgit v1.2.3 From 3ad26d8139a82b0510b1e0435ee82ae461d33401 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 23 Dec 2009 14:35:20 -0200 Subject: KVM: use gfn_to_pfn_memslot in kvm_iommu_map_pages So its possible to iommu map a memslot before making it visible to kvm. Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 3 +-- virt/kvm/iommu.c | 13 ++++++------- virt/kvm/kvm_main.c | 2 +- 3 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f1f78deece10..9af240387fe6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -440,8 +440,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); #define KVM_IOMMU_CACHE_COHERENCY 0x1 #ifdef CONFIG_IOMMU_API -int kvm_iommu_map_pages(struct kvm *kvm, gfn_t base_gfn, - unsigned long npages); +int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot); int kvm_iommu_map_guest(struct kvm *kvm); int kvm_iommu_unmap_guest(struct kvm *kvm); int kvm_assign_device(struct kvm *kvm, diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index bc697a66a883..cf567d8033db 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -32,10 +32,10 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm); static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages); -int kvm_iommu_map_pages(struct kvm *kvm, - gfn_t base_gfn, unsigned long npages) +int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { - gfn_t gfn = base_gfn; + gfn_t gfn = slot->base_gfn; + unsigned long npages = slot->npages; pfn_t pfn; int i, r = 0; struct iommu_domain *domain = kvm->arch.iommu_domain; @@ -54,7 +54,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) continue; - pfn = gfn_to_pfn(kvm, gfn); + pfn = gfn_to_pfn_memslot(kvm, slot, gfn); r = iommu_map_range(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn), @@ -69,7 +69,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, return 0; unmap_pages: - kvm_iommu_put_pages(kvm, base_gfn, i); + kvm_iommu_put_pages(kvm, slot->base_gfn, i); return r; } @@ -81,8 +81,7 @@ static int kvm_iommu_map_memslots(struct kvm *kvm) slots = kvm->memslots; for (i = 0; i < slots->nmemslots; i++) { - r = kvm_iommu_map_pages(kvm, slots->memslots[i].base_gfn, - slots->memslots[i].npages); + r = kvm_iommu_map_pages(kvm, &slots->memslots[i]); if (r) break; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4e2321c733f7..87d296d8b270 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -684,7 +684,7 @@ skip_lpage: spin_unlock(&kvm->mmu_lock); #ifdef CONFIG_DMAR /* map the pages in iommu page table */ - r = kvm_iommu_map_pages(kvm, base_gfn, npages); + r = kvm_iommu_map_pages(kvm, memslot); if (r) goto out; #endif -- cgit v1.2.3 From bc6678a33d9b952981a8e44a4f876c3ad64ca4d8 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 23 Dec 2009 14:35:21 -0200 Subject: KVM: introduce kvm->srcu and convert kvm_set_memory_region to SRCU update Use two steps for memslot deletion: mark the slot invalid (which stops instantiation of new shadow pages for that slot, but allows destruction), then instantiate the new empty slot. Also simplifies kvm_handle_hva locking. Signed-off-by: Marcelo Tosatti --- arch/ia64/kvm/kvm-ia64.c | 4 +- arch/x86/kvm/mmu.c | 28 +++++----- arch/x86/kvm/vmx.c | 6 +- include/linux/kvm.h | 2 +- include/linux/kvm_host.h | 7 +-- virt/kvm/assigned-dev.c | 8 +-- virt/kvm/iommu.c | 4 +- virt/kvm/kvm_main.c | 141 +++++++++++++++++++++++++++++++++++------------ 8 files changed, 136 insertions(+), 64 deletions(-) (limited to 'include') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 0757c7027986..b2e4d16dd39e 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1382,7 +1382,7 @@ static void kvm_release_vm_pages(struct kvm *kvm) int i, j; unsigned long base_gfn; - slots = kvm->memslots; + slots = rcu_dereference(kvm->memslots); for (i = 0; i < slots->nmemslots; i++) { memslot = &slots->memslots[i]; base_gfn = memslot->base_gfn; @@ -1837,6 +1837,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot; int is_dirty = 0; + down_write(&kvm->slots_lock); spin_lock(&kvm->arch.dirty_log_lock); r = kvm_ia64_sync_dirty_log(kvm, log); @@ -1856,6 +1857,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, } r = 0; out: + up_write(&kvm->slots_lock); spin_unlock(&kvm->arch.dirty_log_lock); return r; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 81f84d326a84..f8bf42a25995 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -807,21 +808,15 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, { int i, j; int retval = 0; - struct kvm_memslots *slots = kvm->memslots; + struct kvm_memslots *slots; + + slots = rcu_dereference(kvm->memslots); - /* - * If mmap_sem isn't taken, we can look the memslots with only - * the mmu_lock by skipping over the slots with userspace_addr == 0. - */ for (i = 0; i < slots->nmemslots; i++) { struct kvm_memory_slot *memslot = &slots->memslots[i]; unsigned long start = memslot->userspace_addr; unsigned long end; - /* mmu_lock protects userspace_addr */ - if (!start) - continue; - end = start + (memslot->npages << PAGE_SHIFT); if (hva >= start && hva < end) { gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT; @@ -1617,7 +1612,7 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn) { - int slot = memslot_id(kvm, gfn_to_memslot(kvm, gfn)); + int slot = memslot_id(kvm, gfn); struct kvm_mmu_page *sp = page_header(__pa(pte)); __set_bit(slot, sp->slot_bitmap); @@ -3021,9 +3016,11 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) int i; unsigned int nr_mmu_pages; unsigned int nr_pages = 0; + struct kvm_memslots *slots; - for (i = 0; i < kvm->memslots->nmemslots; i++) - nr_pages += kvm->memslots->memslots[i].npages; + slots = rcu_dereference(kvm->memslots); + for (i = 0; i < slots->nmemslots; i++) + nr_pages += slots->memslots[i].npages; nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; nr_mmu_pages = max(nr_mmu_pages, @@ -3293,10 +3290,12 @@ static void audit_mappings(struct kvm_vcpu *vcpu) static int count_rmaps(struct kvm_vcpu *vcpu) { int nmaps = 0; - int i, j, k; + int i, j, k, idx; + idx = srcu_read_lock(&kvm->srcu); + slots = rcu_dereference(kvm->memslots); for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { - struct kvm_memory_slot *m = &vcpu->kvm->memslots->memslots[i]; + struct kvm_memory_slot *m = &slots->memslots[i]; struct kvm_rmap_desc *d; for (j = 0; j < m->npages; ++j) { @@ -3319,6 +3318,7 @@ static int count_rmaps(struct kvm_vcpu *vcpu) } } } + srcu_read_unlock(&kvm->srcu, idx); return nmaps; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 18698799e365..f1cae7d6113d 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1503,7 +1503,11 @@ static void enter_pmode(struct kvm_vcpu *vcpu) static gva_t rmode_tss_base(struct kvm *kvm) { if (!kvm->arch.tss_addr) { - gfn_t base_gfn = kvm->memslots->memslots[0].base_gfn + + struct kvm_memslots *slots; + gfn_t base_gfn; + + slots = rcu_dereference(kvm->memslots); + base_gfn = kvm->memslots->memslots[0].base_gfn + kvm->memslots->memslots[0].npages - 3; return base_gfn << PAGE_SHIFT; } diff --git a/include/linux/kvm.h b/include/linux/kvm.h index a24de0b1858e..f2feef68ffd6 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -103,7 +103,7 @@ struct kvm_userspace_memory_region { /* for kvm_memory_region::flags */ #define KVM_MEM_LOG_DIRTY_PAGES 1UL - +#define KVM_MEMSLOT_INVALID (1UL << 1) /* for KVM_IRQ_LINE */ struct kvm_irq_level { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9af240387fe6..93bd30701ca7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -162,6 +162,7 @@ struct kvm { struct rw_semaphore slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ struct kvm_memslots *memslots; + struct srcu_struct srcu; #ifdef CONFIG_KVM_APIC_ARCHITECTURE u32 bsp_vcpu_id; struct kvm_vcpu *bsp_vcpu; @@ -275,6 +276,7 @@ void kvm_set_page_accessed(struct page *page); pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); pfn_t gfn_to_pfn_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); +int memslot_id(struct kvm *kvm, gfn_t gfn); void kvm_release_pfn_dirty(pfn_t); void kvm_release_pfn_clean(pfn_t pfn); void kvm_set_pfn_dirty(pfn_t pfn); @@ -490,11 +492,6 @@ static inline void kvm_guest_exit(void) current->flags &= ~PF_VCPU; } -static inline int memslot_id(struct kvm *kvm, struct kvm_memory_slot *slot) -{ - return slot - kvm->memslots->memslots; -} - static inline gpa_t gfn_to_gpa(gfn_t gfn) { return (gpa_t)gfn << PAGE_SHIFT; diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index f73de631e3ee..f51e684dd238 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -504,12 +504,12 @@ out: static int kvm_vm_ioctl_assign_device(struct kvm *kvm, struct kvm_assigned_pci_dev *assigned_dev) { - int r = 0; + int r = 0, idx; struct kvm_assigned_dev_kernel *match; struct pci_dev *dev; mutex_lock(&kvm->lock); - down_read(&kvm->slots_lock); + idx = srcu_read_lock(&kvm->srcu); match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, assigned_dev->assigned_dev_id); @@ -573,7 +573,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, } out: - up_read(&kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, idx); mutex_unlock(&kvm->lock); return r; out_list_del: @@ -585,7 +585,7 @@ out_put: pci_dev_put(dev); out_free: kfree(match); - up_read(&kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, idx); mutex_unlock(&kvm->lock); return r; } diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index cf567d8033db..65a51432c8e5 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -78,7 +78,7 @@ static int kvm_iommu_map_memslots(struct kvm *kvm) int i, r = 0; struct kvm_memslots *slots; - slots = kvm->memslots; + slots = rcu_dereference(kvm->memslots); for (i = 0; i < slots->nmemslots; i++) { r = kvm_iommu_map_pages(kvm, &slots->memslots[i]); @@ -214,7 +214,7 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm) int i; struct kvm_memslots *slots; - slots = kvm->memslots; + slots = rcu_dereference(kvm->memslots); for (i = 0; i < slots->nmemslots; i++) { kvm_iommu_put_pages(kvm, slots->memslots[i].base_gfn, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 87d296d8b270..2bb24a814fdf 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include @@ -213,7 +214,7 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn, unsigned long address) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int need_tlb_flush; + int need_tlb_flush, idx; /* * When ->invalidate_page runs, the linux pte has been zapped @@ -233,10 +234,12 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn, * pte after kvm_unmap_hva returned, without noticing the page * is going to be freed. */ + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); kvm->mmu_notifier_seq++; need_tlb_flush = kvm_unmap_hva(kvm, address); spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) @@ -250,11 +253,14 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, pte_t pte) { struct kvm *kvm = mmu_notifier_to_kvm(mn); + int idx; + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); kvm->mmu_notifier_seq++; kvm_set_spte_hva(kvm, address, pte); spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); } static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, @@ -263,8 +269,9 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, unsigned long end) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int need_tlb_flush = 0; + int need_tlb_flush = 0, idx; + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); /* * The count increase must become visible at unlock time as no @@ -275,6 +282,7 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, for (; start < end; start += PAGE_SIZE) need_tlb_flush |= kvm_unmap_hva(kvm, start); spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) @@ -312,11 +320,13 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, unsigned long address) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int young; + int young, idx; + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); young = kvm_age_hva(kvm, address); spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); if (young) kvm_flush_remote_tlbs(kvm); @@ -379,11 +389,15 @@ static struct kvm *kvm_create_vm(void) kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); if (!kvm->memslots) goto out_err; + if (init_srcu_struct(&kvm->srcu)) + goto out_err; #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) + if (!page) { + cleanup_srcu_struct(&kvm->srcu); goto out_err; + } kvm->coalesced_mmio_ring = (struct kvm_coalesced_mmio_ring *)page_address(page); @@ -391,6 +405,7 @@ static struct kvm *kvm_create_vm(void) r = kvm_init_mmu_notifier(kvm); if (r) { + cleanup_srcu_struct(&kvm->srcu); #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET put_page(page); #endif @@ -480,6 +495,7 @@ static void kvm_destroy_vm(struct kvm *kvm) #else kvm_arch_flush_shadow(kvm); #endif + cleanup_srcu_struct(&kvm->srcu); kvm_arch_destroy_vm(kvm); hardware_disable_all(); mmdrop(mm); @@ -521,12 +537,13 @@ int __kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, int user_alloc) { - int r; + int r, flush_shadow = 0; gfn_t base_gfn; unsigned long npages; unsigned long i; struct kvm_memory_slot *memslot; struct kvm_memory_slot old, new; + struct kvm_memslots *slots, *old_memslots; r = -EINVAL; /* General sanity checks */ @@ -588,15 +605,7 @@ int __kvm_set_memory_region(struct kvm *kvm, memset(new.rmap, 0, npages * sizeof(*new.rmap)); new.user_alloc = user_alloc; - /* - * hva_to_rmmap() serialzies with the mmu_lock and to be - * safe it has to ignore memslots with !user_alloc && - * !userspace_addr. - */ - if (user_alloc) - new.userspace_addr = mem->userspace_addr; - else - new.userspace_addr = 0; + new.userspace_addr = mem->userspace_addr; } if (!npages) goto skip_lpage; @@ -651,8 +660,9 @@ skip_lpage: if (!new.dirty_bitmap) goto out_free; memset(new.dirty_bitmap, 0, dirty_bytes); + /* destroy any largepage mappings for dirty tracking */ if (old.npages) - kvm_arch_flush_shadow(kvm); + flush_shadow = 1; } #else /* not defined CONFIG_S390 */ new.user_alloc = user_alloc; @@ -660,34 +670,72 @@ skip_lpage: new.userspace_addr = mem->userspace_addr; #endif /* not defined CONFIG_S390 */ - if (!npages) + if (!npages) { + r = -ENOMEM; + slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + if (!slots) + goto out_free; + memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); + if (mem->slot >= slots->nmemslots) + slots->nmemslots = mem->slot + 1; + slots->memslots[mem->slot].flags |= KVM_MEMSLOT_INVALID; + + old_memslots = kvm->memslots; + rcu_assign_pointer(kvm->memslots, slots); + synchronize_srcu_expedited(&kvm->srcu); + /* From this point no new shadow pages pointing to a deleted + * memslot will be created. + * + * validation of sp->gfn happens in: + * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) + * - kvm_is_visible_gfn (mmu_check_roots) + */ kvm_arch_flush_shadow(kvm); + kfree(old_memslots); + } r = kvm_arch_prepare_memory_region(kvm, &new, old, mem, user_alloc); if (r) goto out_free; - spin_lock(&kvm->mmu_lock); - if (mem->slot >= kvm->memslots->nmemslots) - kvm->memslots->nmemslots = mem->slot + 1; +#ifdef CONFIG_DMAR + /* map the pages in iommu page table */ + if (npages) { + r = kvm_iommu_map_pages(kvm, &new); + if (r) + goto out_free; + } +#endif - *memslot = new; - spin_unlock(&kvm->mmu_lock); + r = -ENOMEM; + slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + if (!slots) + goto out_free; + memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); + if (mem->slot >= slots->nmemslots) + slots->nmemslots = mem->slot + 1; + + /* actual memory is freed via old in kvm_free_physmem_slot below */ + if (!npages) { + new.rmap = NULL; + new.dirty_bitmap = NULL; + for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) + new.lpage_info[i] = NULL; + } + + slots->memslots[mem->slot] = new; + old_memslots = kvm->memslots; + rcu_assign_pointer(kvm->memslots, slots); + synchronize_srcu_expedited(&kvm->srcu); kvm_arch_commit_memory_region(kvm, mem, old, user_alloc); - kvm_free_physmem_slot(&old, npages ? &new : NULL); - /* Slot deletion case: we have to update the current slot */ - spin_lock(&kvm->mmu_lock); - if (!npages) - *memslot = old; - spin_unlock(&kvm->mmu_lock); -#ifdef CONFIG_DMAR - /* map the pages in iommu page table */ - r = kvm_iommu_map_pages(kvm, memslot); - if (r) - goto out; -#endif + kvm_free_physmem_slot(&old, &new); + kfree(old_memslots); + + if (flush_shadow) + kvm_arch_flush_shadow(kvm); + return 0; out_free: @@ -787,7 +835,7 @@ EXPORT_SYMBOL_GPL(kvm_is_error_hva); struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn) { int i; - struct kvm_memslots *slots = kvm->memslots; + struct kvm_memslots *slots = rcu_dereference(kvm->memslots); for (i = 0; i < slots->nmemslots; ++i) { struct kvm_memory_slot *memslot = &slots->memslots[i]; @@ -809,12 +857,15 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { int i; - struct kvm_memslots *slots = kvm->memslots; + struct kvm_memslots *slots = rcu_dereference(kvm->memslots); gfn = unalias_gfn(kvm, gfn); for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { struct kvm_memory_slot *memslot = &slots->memslots[i]; + if (memslot->flags & KVM_MEMSLOT_INVALID) + continue; + if (gfn >= memslot->base_gfn && gfn < memslot->base_gfn + memslot->npages) return 1; @@ -823,13 +874,31 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); +int memslot_id(struct kvm *kvm, gfn_t gfn) +{ + int i; + struct kvm_memslots *slots = rcu_dereference(kvm->memslots); + struct kvm_memory_slot *memslot = NULL; + + gfn = unalias_gfn(kvm, gfn); + for (i = 0; i < slots->nmemslots; ++i) { + memslot = &slots->memslots[i]; + + if (gfn >= memslot->base_gfn + && gfn < memslot->base_gfn + memslot->npages) + break; + } + + return memslot - slots->memslots; +} + unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *slot; gfn = unalias_gfn(kvm, gfn); slot = gfn_to_memslot_unaliased(kvm, gfn); - if (!slot) + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return bad_hva(); return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE); } -- cgit v1.2.3 From a983fb238728e1123177e8058d4f644b949a7d05 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 23 Dec 2009 14:35:23 -0200 Subject: KVM: x86: switch kvm_set_memory_alias to SRCU update Using a similar two-step procedure as for memslots. Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kvm_host.h | 4 +++ arch/x86/kvm/x86.c | 60 ++++++++++++++++++++++++++++++++++------- include/linux/kvm_host.h | 6 +++++ virt/kvm/kvm_main.c | 4 +-- 4 files changed, 63 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 7cdcb3d0f770..6c8c7c578c46 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -368,8 +368,12 @@ struct kvm_mem_alias { gfn_t base_gfn; unsigned long npages; gfn_t target_gfn; +#define KVM_ALIAS_INVALID 1UL + unsigned long flags; }; +#define KVM_ARCH_HAS_UNALIAS_INSTANTIATION + struct kvm_mem_aliases { struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS]; int naliases; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e7488350ca16..28127c936c3b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #undef TRACE_INCLUDE_FILE #define CREATE_TRACE_POINTS @@ -2223,11 +2224,32 @@ static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) return kvm->arch.n_alloc_mmu_pages; } +gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn) +{ + int i; + struct kvm_mem_alias *alias; + struct kvm_mem_aliases *aliases; + + aliases = rcu_dereference(kvm->arch.aliases); + + for (i = 0; i < aliases->naliases; ++i) { + alias = &aliases->aliases[i]; + if (alias->flags & KVM_ALIAS_INVALID) + continue; + if (gfn >= alias->base_gfn + && gfn < alias->base_gfn + alias->npages) + return alias->target_gfn + gfn - alias->base_gfn; + } + return gfn; +} + gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) { int i; struct kvm_mem_alias *alias; - struct kvm_mem_aliases *aliases = kvm->arch.aliases; + struct kvm_mem_aliases *aliases; + + aliases = rcu_dereference(kvm->arch.aliases); for (i = 0; i < aliases->naliases; ++i) { alias = &aliases->aliases[i]; @@ -2248,7 +2270,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, { int r, n; struct kvm_mem_alias *p; - struct kvm_mem_aliases *aliases; + struct kvm_mem_aliases *aliases, *old_aliases; r = -EINVAL; /* General sanity checks */ @@ -2265,28 +2287,48 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, < alias->target_phys_addr) goto out; + r = -ENOMEM; + aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL); + if (!aliases) + goto out; + down_write(&kvm->slots_lock); - spin_lock(&kvm->mmu_lock); - aliases = kvm->arch.aliases; + /* invalidate any gfn reference in case of deletion/shrinking */ + memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases)); + aliases->aliases[alias->slot].flags |= KVM_ALIAS_INVALID; + old_aliases = kvm->arch.aliases; + rcu_assign_pointer(kvm->arch.aliases, aliases); + synchronize_srcu_expedited(&kvm->srcu); + kvm_mmu_zap_all(kvm); + kfree(old_aliases); + + r = -ENOMEM; + aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL); + if (!aliases) + goto out_unlock; + + memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases)); p = &aliases->aliases[alias->slot]; p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT; p->npages = alias->memory_size >> PAGE_SHIFT; p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT; + p->flags &= ~(KVM_ALIAS_INVALID); for (n = KVM_ALIAS_SLOTS; n > 0; --n) if (aliases->aliases[n - 1].npages) break; aliases->naliases = n; - spin_unlock(&kvm->mmu_lock); - kvm_mmu_zap_all(kvm); + old_aliases = kvm->arch.aliases; + rcu_assign_pointer(kvm->arch.aliases, aliases); + synchronize_srcu_expedited(&kvm->srcu); + kfree(old_aliases); + r = 0; +out_unlock: up_write(&kvm->slots_lock); - - return 0; - out: return r; } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 93bd30701ca7..20941c0f4045 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -266,6 +266,8 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, void kvm_disable_largepages(void); void kvm_arch_flush_shadow(struct kvm *kvm); gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn); +gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn); + struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); void kvm_release_page_clean(struct page *page); @@ -539,6 +541,10 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se } #endif +#ifndef KVM_ARCH_HAS_UNALIAS_INSTANTIATION +#define unalias_gfn_instantiation unalias_gfn +#endif + #ifdef CONFIG_HAVE_KVM_IRQCHIP #define KVM_MAX_IRQ_ROUTES 1024 diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2bb24a814fdf..c680f7b64c6f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -859,7 +859,7 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) int i; struct kvm_memslots *slots = rcu_dereference(kvm->memslots); - gfn = unalias_gfn(kvm, gfn); + gfn = unalias_gfn_instantiation(kvm, gfn); for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { struct kvm_memory_slot *memslot = &slots->memslots[i]; @@ -896,7 +896,7 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *slot; - gfn = unalias_gfn(kvm, gfn); + gfn = unalias_gfn_instantiation(kvm, gfn); slot = gfn_to_memslot_unaliased(kvm, gfn); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return bad_hva(); -- cgit v1.2.3 From e93f8a0f821e290ac5149830110a5f704db7a1fc Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 23 Dec 2009 14:35:24 -0200 Subject: KVM: convert io_bus to SRCU Signed-off-by: Marcelo Tosatti --- arch/ia64/kvm/kvm-ia64.c | 4 +- arch/x86/kvm/i8254.c | 6 +-- arch/x86/kvm/i8259.c | 4 +- arch/x86/kvm/x86.c | 13 +++--- include/linux/kvm_host.h | 27 ++++++------ virt/kvm/coalesced_mmio.c | 4 +- virt/kvm/eventfd.c | 8 ++-- virt/kvm/ioapic.c | 4 +- virt/kvm/kvm_main.c | 106 +++++++++++++++++++++++++++------------------- 9 files changed, 101 insertions(+), 75 deletions(-) (limited to 'include') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index b2e4d16dd39e..d0ad538f0083 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -241,10 +241,10 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 0; mmio: if (p->dir) - r = kvm_io_bus_read(&vcpu->kvm->mmio_bus, p->addr, + r = kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, p->addr, p->size, &p->data); else - r = kvm_io_bus_write(&vcpu->kvm->mmio_bus, p->addr, + r = kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, p->addr, p->size, &p->data); if (r) printk(KERN_ERR"kvm: No iodevice found! addr:%lx\n", p->addr); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 15578f180e59..4b433de02e5b 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -645,13 +645,13 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier); kvm_iodevice_init(&pit->dev, &pit_dev_ops); - ret = __kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev); + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &pit->dev); if (ret < 0) goto fail; if (flags & KVM_PIT_SPEAKER_DUMMY) { kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops); - ret = __kvm_io_bus_register_dev(&kvm->pio_bus, + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &pit->speaker_dev); if (ret < 0) goto fail_unregister; @@ -660,7 +660,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) return pit; fail_unregister: - __kvm_io_bus_unregister_dev(&kvm->pio_bus, &pit->dev); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev); fail: if (pit->irq_source_id >= 0) diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index d057c0cbd245..b7d145b20953 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -533,7 +533,9 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm) * Initialize PIO device */ kvm_iodevice_init(&s->dev, &picdev_ops); - ret = kvm_io_bus_register_dev(kvm, &kvm->pio_bus, &s->dev); + down_write(&kvm->slots_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &s->dev); + up_write(&kvm->slots_lock); if (ret < 0) { kfree(s); return NULL; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 28127c936c3b..9b42673df4af 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2851,7 +2851,7 @@ static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, len, v)) return 0; - return kvm_io_bus_write(&vcpu->kvm->mmio_bus, addr, len, v); + return kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, len, v); } static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) @@ -2860,7 +2860,7 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, len, v)) return 0; - return kvm_io_bus_read(&vcpu->kvm->mmio_bus, addr, len, v); + return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v); } static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes, @@ -3345,11 +3345,12 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) int r; if (vcpu->arch.pio.in) - r = kvm_io_bus_read(&vcpu->kvm->pio_bus, vcpu->arch.pio.port, + r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, vcpu->arch.pio.size, pd); else - r = kvm_io_bus_write(&vcpu->kvm->pio_bus, vcpu->arch.pio.port, - vcpu->arch.pio.size, pd); + r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, + vcpu->arch.pio.port, vcpu->arch.pio.size, + pd); return r; } @@ -3360,7 +3361,7 @@ static int pio_string_write(struct kvm_vcpu *vcpu) int i, r = 0; for (i = 0; i < io->cur_count; i++) { - if (kvm_io_bus_write(&vcpu->kvm->pio_bus, + if (kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, io->port, io->size, pd)) { r = -EOPNOTSUPP; break; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 20941c0f4045..5e9cb902550b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -57,20 +57,20 @@ struct kvm_io_bus { struct kvm_io_device *devs[NR_IOBUS_DEVS]; }; -void kvm_io_bus_init(struct kvm_io_bus *bus); -void kvm_io_bus_destroy(struct kvm_io_bus *bus); -int kvm_io_bus_write(struct kvm_io_bus *bus, gpa_t addr, int len, - const void *val); -int kvm_io_bus_read(struct kvm_io_bus *bus, gpa_t addr, int len, +enum kvm_bus { + KVM_MMIO_BUS, + KVM_PIO_BUS, + KVM_NR_BUSES +}; + +int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, + int len, const void *val); +int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, void *val); -int __kvm_io_bus_register_dev(struct kvm_io_bus *bus, - struct kvm_io_device *dev); -int kvm_io_bus_register_dev(struct kvm *kvm, struct kvm_io_bus *bus, +int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev); -void __kvm_io_bus_unregister_dev(struct kvm_io_bus *bus, - struct kvm_io_device *dev); -void kvm_io_bus_unregister_dev(struct kvm *kvm, struct kvm_io_bus *bus, - struct kvm_io_device *dev); +int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev); struct kvm_vcpu { struct kvm *kvm; @@ -171,8 +171,7 @@ struct kvm { atomic_t online_vcpus; struct list_head vm_list; struct mutex lock; - struct kvm_io_bus mmio_bus; - struct kvm_io_bus pio_bus; + struct kvm_io_bus *buses[KVM_NR_BUSES]; #ifdef CONFIG_HAVE_KVM_EVENTFD struct { spinlock_t lock; diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index d68e6c68e0ff..a736a93ca7b7 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -110,7 +110,9 @@ int kvm_coalesced_mmio_init(struct kvm *kvm) dev->kvm = kvm; kvm->coalesced_mmio_dev = dev; - ret = kvm_io_bus_register_dev(kvm, &kvm->mmio_bus, &dev->dev); + down_write(&kvm->slots_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, &dev->dev); + up_write(&kvm->slots_lock); if (ret < 0) goto out_free_dev; diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index a9d3fc6c681c..315a586ec4d5 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -463,7 +463,7 @@ static int kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { int pio = args->flags & KVM_IOEVENTFD_FLAG_PIO; - struct kvm_io_bus *bus = pio ? &kvm->pio_bus : &kvm->mmio_bus; + enum kvm_bus bus_idx = pio ? KVM_PIO_BUS : KVM_MMIO_BUS; struct _ioeventfd *p; struct eventfd_ctx *eventfd; int ret; @@ -518,7 +518,7 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) kvm_iodevice_init(&p->dev, &ioeventfd_ops); - ret = __kvm_io_bus_register_dev(bus, &p->dev); + ret = kvm_io_bus_register_dev(kvm, bus_idx, &p->dev); if (ret < 0) goto unlock_fail; @@ -542,7 +542,7 @@ static int kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { int pio = args->flags & KVM_IOEVENTFD_FLAG_PIO; - struct kvm_io_bus *bus = pio ? &kvm->pio_bus : &kvm->mmio_bus; + enum kvm_bus bus_idx = pio ? KVM_PIO_BUS : KVM_MMIO_BUS; struct _ioeventfd *p, *tmp; struct eventfd_ctx *eventfd; int ret = -ENOENT; @@ -565,7 +565,7 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) if (!p->wildcard && p->datamatch != args->datamatch) continue; - __kvm_io_bus_unregister_dev(bus, &p->dev); + kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev); ioeventfd_release(p); ret = 0; break; diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 38a2d20b89de..f326a6f301cc 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -372,7 +372,9 @@ int kvm_ioapic_init(struct kvm *kvm) kvm_ioapic_reset(ioapic); kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops); ioapic->kvm = kvm; - ret = kvm_io_bus_register_dev(kvm, &kvm->mmio_bus, &ioapic->dev); + down_write(&kvm->slots_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); + up_write(&kvm->slots_lock); if (ret < 0) kfree(ioapic); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c680f7b64c6f..659bc12ad16a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -85,6 +85,8 @@ static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, static int hardware_enable_all(void); static void hardware_disable_all(void); +static void kvm_io_bus_destroy(struct kvm_io_bus *bus); + static bool kvm_rebooting; static bool largepages_enabled = true; @@ -367,7 +369,7 @@ static int kvm_init_mmu_notifier(struct kvm *kvm) static struct kvm *kvm_create_vm(void) { - int r = 0; + int r = 0, i; struct kvm *kvm = kvm_arch_create_vm(); #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET struct page *page; @@ -391,6 +393,14 @@ static struct kvm *kvm_create_vm(void) goto out_err; if (init_srcu_struct(&kvm->srcu)) goto out_err; + for (i = 0; i < KVM_NR_BUSES; i++) { + kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus), + GFP_KERNEL); + if (!kvm->buses[i]) { + cleanup_srcu_struct(&kvm->srcu); + goto out_err; + } + } #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET page = alloc_page(GFP_KERNEL | __GFP_ZERO); @@ -416,11 +426,9 @@ static struct kvm *kvm_create_vm(void) atomic_inc(&kvm->mm->mm_count); spin_lock_init(&kvm->mmu_lock); spin_lock_init(&kvm->requests_lock); - kvm_io_bus_init(&kvm->pio_bus); kvm_eventfd_init(kvm); mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); - kvm_io_bus_init(&kvm->mmio_bus); init_rwsem(&kvm->slots_lock); atomic_set(&kvm->users_count, 1); spin_lock(&kvm_lock); @@ -435,6 +443,8 @@ out: out_err: hardware_disable_all(); out_err_nodisable: + for (i = 0; i < KVM_NR_BUSES; i++) + kfree(kvm->buses[i]); kfree(kvm->memslots); kfree(kvm); return ERR_PTR(r); @@ -480,6 +490,7 @@ void kvm_free_physmem(struct kvm *kvm) static void kvm_destroy_vm(struct kvm *kvm) { + int i; struct mm_struct *mm = kvm->mm; kvm_arch_sync_events(kvm); @@ -487,8 +498,8 @@ static void kvm_destroy_vm(struct kvm *kvm) list_del(&kvm->vm_list); spin_unlock(&kvm_lock); kvm_free_irq_routing(kvm); - kvm_io_bus_destroy(&kvm->pio_bus); - kvm_io_bus_destroy(&kvm->mmio_bus); + for (i = 0; i < KVM_NR_BUSES; i++) + kvm_io_bus_destroy(kvm->buses[i]); kvm_coalesced_mmio_free(kvm); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); @@ -1949,12 +1960,7 @@ static struct notifier_block kvm_reboot_notifier = { .priority = 0, }; -void kvm_io_bus_init(struct kvm_io_bus *bus) -{ - memset(bus, 0, sizeof(*bus)); -} - -void kvm_io_bus_destroy(struct kvm_io_bus *bus) +static void kvm_io_bus_destroy(struct kvm_io_bus *bus) { int i; @@ -1963,13 +1969,15 @@ void kvm_io_bus_destroy(struct kvm_io_bus *bus) kvm_iodevice_destructor(pos); } + kfree(bus); } /* kvm_io_bus_write - called under kvm->slots_lock */ -int kvm_io_bus_write(struct kvm_io_bus *bus, gpa_t addr, +int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { int i; + struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]); for (i = 0; i < bus->dev_count; i++) if (!kvm_iodevice_write(bus->devs[i], addr, len, val)) return 0; @@ -1977,59 +1985,71 @@ int kvm_io_bus_write(struct kvm_io_bus *bus, gpa_t addr, } /* kvm_io_bus_read - called under kvm->slots_lock */ -int kvm_io_bus_read(struct kvm_io_bus *bus, gpa_t addr, int len, void *val) +int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, + int len, void *val) { int i; + struct kvm_io_bus *bus = rcu_dereference(kvm->buses[bus_idx]); + for (i = 0; i < bus->dev_count; i++) if (!kvm_iodevice_read(bus->devs[i], addr, len, val)) return 0; return -EOPNOTSUPP; } -int kvm_io_bus_register_dev(struct kvm *kvm, struct kvm_io_bus *bus, - struct kvm_io_device *dev) +/* Caller must have write lock on slots_lock. */ +int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev) { - int ret; - - down_write(&kvm->slots_lock); - ret = __kvm_io_bus_register_dev(bus, dev); - up_write(&kvm->slots_lock); + struct kvm_io_bus *new_bus, *bus; - return ret; -} - -/* An unlocked version. Caller must have write lock on slots_lock. */ -int __kvm_io_bus_register_dev(struct kvm_io_bus *bus, - struct kvm_io_device *dev) -{ + bus = kvm->buses[bus_idx]; if (bus->dev_count > NR_IOBUS_DEVS-1) return -ENOSPC; - bus->devs[bus->dev_count++] = dev; + new_bus = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); + if (!new_bus) + return -ENOMEM; + memcpy(new_bus, bus, sizeof(struct kvm_io_bus)); + new_bus->devs[new_bus->dev_count++] = dev; + rcu_assign_pointer(kvm->buses[bus_idx], new_bus); + synchronize_srcu_expedited(&kvm->srcu); + kfree(bus); return 0; } -void kvm_io_bus_unregister_dev(struct kvm *kvm, - struct kvm_io_bus *bus, - struct kvm_io_device *dev) +/* Caller must have write lock on slots_lock. */ +int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, + struct kvm_io_device *dev) { - down_write(&kvm->slots_lock); - __kvm_io_bus_unregister_dev(bus, dev); - up_write(&kvm->slots_lock); -} + int i, r; + struct kvm_io_bus *new_bus, *bus; -/* An unlocked version. Caller must have write lock on slots_lock. */ -void __kvm_io_bus_unregister_dev(struct kvm_io_bus *bus, - struct kvm_io_device *dev) -{ - int i; + new_bus = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); + if (!new_bus) + return -ENOMEM; - for (i = 0; i < bus->dev_count; i++) - if (bus->devs[i] == dev) { - bus->devs[i] = bus->devs[--bus->dev_count]; + bus = kvm->buses[bus_idx]; + memcpy(new_bus, bus, sizeof(struct kvm_io_bus)); + + r = -ENOENT; + for (i = 0; i < new_bus->dev_count; i++) + if (new_bus->devs[i] == dev) { + r = 0; + new_bus->devs[i] = new_bus->devs[--new_bus->dev_count]; break; } + + if (r) { + kfree(new_bus); + return r; + } + + rcu_assign_pointer(kvm->buses[bus_idx], new_bus); + synchronize_srcu_expedited(&kvm->srcu); + kfree(bus); + return r; } static struct notifier_block kvm_cpu_notifier = { -- cgit v1.2.3 From f656ce0185cabbbb0cf96877306879661297c7ad Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 23 Dec 2009 14:35:25 -0200 Subject: KVM: switch vcpu context to use SRCU Signed-off-by: Marcelo Tosatti --- arch/ia64/kvm/kvm-ia64.c | 15 ++++++--------- arch/s390/kvm/kvm-s390.h | 10 +++++++--- arch/x86/kvm/mmu.c | 7 +++---- arch/x86/kvm/vmx.c | 6 +++--- arch/x86/kvm/x86.c | 43 ++++++++++++++++++++++++------------------- include/linux/kvm_host.h | 2 ++ 6 files changed, 45 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index d0ad538f0083..d5e384641275 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -636,12 +636,9 @@ static void kvm_vcpu_post_transition(struct kvm_vcpu *vcpu) static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { union context *host_ctx, *guest_ctx; - int r; + int r, idx; - /* - * down_read() may sleep and return with interrupts enabled - */ - down_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); again: if (signal_pending(current)) { @@ -663,7 +660,7 @@ again: if (r < 0) goto vcpu_run_fail; - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, idx); kvm_guest_enter(); /* @@ -687,7 +684,7 @@ again: kvm_guest_exit(); preempt_enable(); - down_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_handle_exit(kvm_run, vcpu); @@ -697,10 +694,10 @@ again: } out: - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, idx); if (r > 0) { kvm_resched(vcpu); - down_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); goto again; } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 06cce8285ba0..60f09ab3672c 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -67,10 +67,14 @@ static inline long kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu) static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu) { + int idx; struct kvm_memory_slot *mem; + struct kvm_memslots *memslots; - down_read(&vcpu->kvm->slots_lock); - mem = &vcpu->kvm->memslots[0]; + idx = srcu_read_lock(&vcpu->kvm->srcu); + memslots = rcu_dereference(vcpu->kvm->memslots); + + mem = &memslots->memslots[0]; vcpu->arch.sie_block->gmsor = mem->userspace_addr; vcpu->arch.sie_block->gmslm = @@ -78,7 +82,7 @@ static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu) (mem->npages << PAGE_SHIFT) + VIRTIODESCSPACE - 1ul; - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, idx); } /* implemented in priv.c */ diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f8bf42a25995..25aabd00aa01 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2933,10 +2933,9 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask) spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - int npages; + int npages, idx; - if (!down_read_trylock(&kvm->slots_lock)) - continue; + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); npages = kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages; @@ -2949,7 +2948,7 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask) nr_to_scan--; spin_unlock(&kvm->mmu_lock); - up_read(&kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, idx); } if (kvm_freed) list_move_tail(&kvm_freed->vm_list, &vm_list); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f1cae7d6113d..22ab7137d1d0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2478,10 +2478,10 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 msr; - int ret; + int ret, idx; vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); - down_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); if (!init_rmode(vmx->vcpu.kvm)) { ret = -ENOMEM; goto out; @@ -2589,7 +2589,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->emulation_required = 0; out: - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9b42673df4af..53bc06a68105 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1306,15 +1306,15 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data)) { - int i; + int i, idx; vcpu_load(vcpu); - down_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); for (i = 0; i < msrs->nmsrs; ++i) if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, idx); vcpu_put(vcpu); @@ -3900,14 +3900,15 @@ static void vapic_enter(struct kvm_vcpu *vcpu) static void vapic_exit(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; + int idx; if (!apic || !apic->vapic_addr) return; - down_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_release_page_dirty(apic->vapic_page); mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, idx); } static void update_cr8_intercept(struct kvm_vcpu *vcpu) @@ -4036,7 +4037,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_lapic_sync_to_vapic(vcpu); } - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); kvm_guest_enter(); @@ -4078,7 +4079,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_enable(); - down_read(&vcpu->kvm->slots_lock); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); /* * Profile KVM exit RIPs: @@ -4100,6 +4101,7 @@ out: static int __vcpu_run(struct kvm_vcpu *vcpu) { int r; + struct kvm *kvm = vcpu->kvm; if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) { pr_debug("vcpu %d received sipi with vector # %x\n", @@ -4111,7 +4113,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } - down_read(&vcpu->kvm->slots_lock); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); vapic_enter(vcpu); r = 1; @@ -4119,9 +4121,9 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) r = vcpu_enter_guest(vcpu); else { - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); - down_read(&vcpu->kvm->slots_lock); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests)) { switch(vcpu->arch.mp_state) { @@ -4156,13 +4158,13 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) ++vcpu->stat.signal_exits; } if (need_resched()) { - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_resched(vcpu); - down_read(&vcpu->kvm->slots_lock); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); } } - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); post_kvm_run_save(vcpu); vapic_exit(vcpu); @@ -4201,10 +4203,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->mmio_read_completed = 1; vcpu->mmio_needed = 0; - down_read(&vcpu->kvm->slots_lock); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0, EMULTYPE_NO_DECODE); - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (r == EMULATE_DO_MMIO) { /* * Read-modify-write. Back to userspace. @@ -4967,11 +4969,12 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, { unsigned long vaddr = tr->linear_address; gpa_t gpa; + int idx; vcpu_load(vcpu); - down_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vaddr); - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, idx); tr->physical_address = gpa; tr->valid = gpa != UNMAPPED_GVA; tr->writeable = 1; @@ -5223,11 +5226,13 @@ fail: void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) { + int idx; + kfree(vcpu->arch.mce_banks); kvm_free_lapic(vcpu); - down_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_mmu_destroy(vcpu); - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, idx); free_page((unsigned long)vcpu->arch.pio_data); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5e9cb902550b..0bb9aa295e6c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -83,6 +83,8 @@ struct kvm_vcpu { struct kvm_run *run; unsigned long requests; unsigned long guest_debug; + int srcu_idx; + int fpu_active; int guest_fpu_loaded; wait_queue_head_t wq; -- cgit v1.2.3 From 79fac95ecfa3969aab8119d37ccd7226165f933a Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 23 Dec 2009 14:35:26 -0200 Subject: KVM: convert slots_lock to a mutex Signed-off-by: Marcelo Tosatti --- arch/ia64/kvm/kvm-ia64.c | 4 ++-- arch/powerpc/kvm/book3s.c | 4 ++-- arch/x86/kvm/i8254.c | 2 +- arch/x86/kvm/i8259.c | 4 ++-- arch/x86/kvm/vmx.c | 8 ++++---- arch/x86/kvm/x86.c | 16 ++++++++-------- include/linux/kvm_host.h | 2 +- virt/kvm/coalesced_mmio.c | 14 +++++++------- virt/kvm/eventfd.c | 10 +++++----- virt/kvm/ioapic.c | 4 ++-- virt/kvm/kvm_main.c | 10 +++++----- 11 files changed, 39 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index d5e384641275..e6ac549f8d55 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1834,7 +1834,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot; int is_dirty = 0; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); spin_lock(&kvm->arch.dirty_log_lock); r = kvm_ia64_sync_dirty_log(kvm, log); @@ -1854,7 +1854,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, } r = 0; out: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); spin_unlock(&kvm->arch.dirty_log_lock); return r; } diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index bb8873dcb20f..492dcc198dd3 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -857,7 +857,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, int is_dirty = 0; int r, n; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); r = kvm_get_dirty_log(kvm, log, &is_dirty); if (r) @@ -879,7 +879,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, r = 0; out: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return r; } diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 4b433de02e5b..6a74246f80c6 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -605,7 +605,7 @@ static const struct kvm_io_device_ops speaker_dev_ops = { .write = speaker_ioport_write, }; -/* Caller must have writers lock on slots_lock */ +/* Caller must hold slots_lock */ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) { struct kvm_pit *pit; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index b7d145b20953..d5753a75d58c 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -533,9 +533,9 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm) * Initialize PIO device */ kvm_iodevice_init(&s->dev, &picdev_ops); - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &s->dev); - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); if (ret < 0) { kfree(s); return NULL; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 22ab7137d1d0..f04e2ff21383 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2223,7 +2223,7 @@ static int alloc_apic_access_page(struct kvm *kvm) struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); if (kvm->arch.apic_access_page) goto out; kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; @@ -2236,7 +2236,7 @@ static int alloc_apic_access_page(struct kvm *kvm) kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00); out: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return r; } @@ -2245,7 +2245,7 @@ static int alloc_identity_pagetable(struct kvm *kvm) struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); if (kvm->arch.ept_identity_pagetable) goto out; kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; @@ -2260,7 +2260,7 @@ static int alloc_identity_pagetable(struct kvm *kvm) kvm->arch.ept_identity_pagetable = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT); out: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return r; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 53bc06a68105..aff3479867a8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2208,14 +2208,14 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); spin_lock(&kvm->mmu_lock); kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages); kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages; spin_unlock(&kvm->mmu_lock); - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return 0; } @@ -2292,7 +2292,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, if (!aliases) goto out; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); /* invalidate any gfn reference in case of deletion/shrinking */ memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases)); @@ -2328,7 +2328,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, r = 0; out_unlock: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); out: return r; } @@ -2462,7 +2462,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, unsigned long is_dirty = 0; unsigned long *dirty_bitmap = NULL; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); r = -EINVAL; if (log->slot >= KVM_MEMORY_SLOTS) @@ -2512,7 +2512,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, out_free: vfree(dirty_bitmap); out: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return r; } @@ -2625,7 +2625,7 @@ long kvm_arch_vm_ioctl(struct file *filp, sizeof(struct kvm_pit_config))) goto out; create_pit: - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); r = -EEXIST; if (kvm->arch.vpit) goto create_pit_unlock; @@ -2634,7 +2634,7 @@ long kvm_arch_vm_ioctl(struct file *filp, if (kvm->arch.vpit) r = 0; create_pit_unlock: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); break; case KVM_IRQ_LINE_STATUS: case KVM_IRQ_LINE: { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0bb9aa295e6c..bb0314ea9267 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -161,7 +161,7 @@ struct kvm_memslots { struct kvm { spinlock_t mmu_lock; spinlock_t requests_lock; - struct rw_semaphore slots_lock; + struct mutex slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ struct kvm_memslots *memslots; struct srcu_struct srcu; diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index a736a93ca7b7..5de6594260cb 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -110,9 +110,9 @@ int kvm_coalesced_mmio_init(struct kvm *kvm) dev->kvm = kvm; kvm->coalesced_mmio_dev = dev; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, &dev->dev); - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); if (ret < 0) goto out_free_dev; @@ -140,16 +140,16 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, if (dev == NULL) return -EINVAL; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) { - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return -ENOBUFS; } dev->zone[dev->nb_zones] = *zone; dev->nb_zones++; - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return 0; } @@ -163,7 +163,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, if (dev == NULL) return -EINVAL; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); i = dev->nb_zones; while(i) { @@ -181,7 +181,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, i--; } - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return 0; } diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 315a586ec4d5..486c604365d9 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -508,7 +508,7 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) else p->wildcard = true; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); /* Verify that there isnt a match already */ if (ioeventfd_check_collision(kvm, p)) { @@ -524,12 +524,12 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) list_add_tail(&p->list, &kvm->ioeventfds); - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return 0; unlock_fail: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); fail: kfree(p); @@ -551,7 +551,7 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) if (IS_ERR(eventfd)) return PTR_ERR(eventfd); - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) { bool wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH); @@ -571,7 +571,7 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) break; } - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); eventfd_ctx_put(eventfd); diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index f326a6f301cc..f01392f51e86 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -372,9 +372,9 @@ int kvm_ioapic_init(struct kvm *kvm) kvm_ioapic_reset(ioapic); kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops); ioapic->kvm = kvm; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); if (ret < 0) kfree(ioapic); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 659bc12ad16a..2b7cd6c0d9ca 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -429,7 +429,7 @@ static struct kvm *kvm_create_vm(void) kvm_eventfd_init(kvm); mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); - init_rwsem(&kvm->slots_lock); + mutex_init(&kvm->slots_lock); atomic_set(&kvm->users_count, 1); spin_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); @@ -763,9 +763,9 @@ int kvm_set_memory_region(struct kvm *kvm, { int r; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); r = __kvm_set_memory_region(kvm, mem, user_alloc); - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return r; } EXPORT_SYMBOL_GPL(kvm_set_memory_region); @@ -1997,7 +1997,7 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, return -EOPNOTSUPP; } -/* Caller must have write lock on slots_lock. */ +/* Caller must hold slots_lock. */ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev) { @@ -2019,7 +2019,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, return 0; } -/* Caller must have write lock on slots_lock. */ +/* Caller must hold slots_lock. */ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev) { -- cgit v1.2.3 From 02daab21d94dc4cf01b2fd09863d59a436900322 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 30 Dec 2009 12:40:26 +0200 Subject: KVM: Lazify fpu activation and deactivation Defer fpu deactivation as much as possible - if the guest fpu is loaded, keep it loaded until the next heavyweight exit (where we are forced to unload it). This reduces unnecessary exits. We also defer fpu activation on clts; while clts signals the intent to use the fpu, we can't be sure the guest will actually use it. Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/svm.c | 35 +++++++++++++++++++++-------------- arch/x86/kvm/vmx.c | 25 +++++++++---------------- arch/x86/kvm/x86.c | 7 ++++++- include/linux/kvm_host.h | 1 + 5 files changed, 38 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 693046a7a12d..93bee7abb71c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -506,6 +506,7 @@ struct kvm_x86_ops { void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); + void (*fpu_deactivate)(struct kvm_vcpu *vcpu); void (*tlb_flush)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 3899c2d19830..5b336a80f31e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -984,17 +984,11 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (npt_enabled) goto set; - if (kvm_read_cr0_bits(vcpu, X86_CR0_TS) && !(cr0 & X86_CR0_TS)) { - svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); - vcpu->fpu_active = 1; - } - vcpu->arch.cr0 = cr0; cr0 |= X86_CR0_PG | X86_CR0_WP; - if (!vcpu->fpu_active) { - svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR); + + if (!vcpu->fpu_active) cr0 |= X86_CR0_TS; - } set: /* * re-enable caching here because the QEMU bios @@ -1250,6 +1244,8 @@ static int nm_interception(struct vcpu_svm *svm) svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); if (!kvm_read_cr0_bits(&svm->vcpu, X86_CR0_TS)) svm->vmcb->save.cr0 &= ~X86_CR0_TS; + else + svm->vmcb->save.cr0 |= X86_CR0_TS; svm->vcpu.fpu_active = 1; return 1; @@ -2586,6 +2582,8 @@ static void svm_flush_tlb(struct kvm_vcpu *vcpu) static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) { + if (npt_enabled) + vcpu->fpu_active = 1; } static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu) @@ -2805,12 +2803,6 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) svm->vmcb->save.cr3 = root; force_new_asid(vcpu); - - if (vcpu->fpu_active) { - svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR); - svm->vmcb->save.cr0 |= X86_CR0_TS; - vcpu->fpu_active = 0; - } } static int is_disabled(void) @@ -2926,6 +2918,20 @@ static bool svm_rdtscp_supported(void) return false; } +static void svm_fpu_deactivate(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (npt_enabled) { + /* hack: npt requires active fpu at this time */ + vcpu->fpu_active = 1; + return; + } + + svm->vmcb->control.intercept_exceptions |= 1 << NM_VECTOR; + svm->vmcb->save.cr0 |= X86_CR0_TS; +} + static struct kvm_x86_ops svm_x86_ops = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -2967,6 +2973,7 @@ static struct kvm_x86_ops svm_x86_ops = { .cache_reg = svm_cache_reg, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, + .fpu_deactivate = svm_fpu_deactivate, .tlb_flush = svm_flush_tlb, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index dbcdb55094f7..d11be3fb7c80 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -66,7 +66,7 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO); #define KVM_GUEST_CR0_MASK \ (KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \ - (X86_CR0_WP | X86_CR0_NE | X86_CR0_TS | X86_CR0_MP) + (X86_CR0_WP | X86_CR0_NE | X86_CR0_MP) #define KVM_VM_CR0_ALWAYS_ON \ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE) #define KVM_CR4_GUEST_OWNED_BITS \ @@ -579,9 +579,8 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) { u32 eb; - eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR); - if (!vcpu->fpu_active) - eb |= 1u << NM_VECTOR; + eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) + | (1u << NM_VECTOR); /* * Unconditionally intercept #DB so we can maintain dr6 without * reading it every exit. @@ -595,6 +594,8 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) eb = ~0; if (enable_ept) eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */ + if (vcpu->fpu_active) + eb &= ~(1u << NM_VECTOR); vmcs_write32(EXCEPTION_BITMAP, eb); } @@ -806,9 +807,6 @@ static void vmx_fpu_activate(struct kvm_vcpu *vcpu) static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu) { - if (!vcpu->fpu_active) - return; - vcpu->fpu_active = 0; vmcs_set_bits(GUEST_CR0, X86_CR0_TS); update_exception_bitmap(vcpu); } @@ -1737,8 +1735,6 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) else hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON; - vmx_fpu_deactivate(vcpu); - if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE)) enter_pmode(vcpu); @@ -1757,12 +1753,12 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (enable_ept) ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu); + if (!vcpu->fpu_active) + hw_cr0 |= X86_CR0_TS; + vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, hw_cr0); vcpu->arch.cr0 = cr0; - - if (!(cr0 & X86_CR0_TS) || !(cr0 & X86_CR0_PE)) - vmx_fpu_activate(vcpu); } static u64 construct_eptp(unsigned long root_hpa) @@ -1793,8 +1789,6 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) vmx_flush_tlb(vcpu); vmcs_writel(GUEST_CR3, guest_cr3); - if (kvm_read_cr0_bits(vcpu, X86_CR0_PE)) - vmx_fpu_deactivate(vcpu); } static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -3002,11 +2996,9 @@ static int handle_cr(struct kvm_vcpu *vcpu) }; break; case 2: /* clts */ - vmx_fpu_deactivate(vcpu); vcpu->arch.cr0 &= ~X86_CR0_TS; vmcs_writel(CR0_READ_SHADOW, kvm_read_cr0(vcpu)); trace_kvm_cr_write(0, kvm_read_cr0(vcpu)); - vmx_fpu_activate(vcpu); skip_emulated_instruction(vcpu); return 1; case 1: /*mov from cr*/ @@ -4127,6 +4119,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .cache_reg = vmx_cache_reg, .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, + .fpu_deactivate = vmx_fpu_deactivate, .tlb_flush = vmx_flush_tlb, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 748b15d8e46d..1de2ad7a004d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1509,8 +1509,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { - kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); + kvm_x86_ops->vcpu_put(vcpu); } static int is_efer_nx(void) @@ -4006,6 +4006,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 0; goto out; } + if (test_and_clear_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests)) { + vcpu->fpu_active = 0; + kvm_x86_ops->fpu_deactivate(vcpu); + } } preempt_disable(); @@ -5075,6 +5079,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) kvm_fx_save(&vcpu->arch.guest_fx_image); kvm_fx_restore(&vcpu->arch.host_fx_image); ++vcpu->stat.fpu_reload; + set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests); } EXPORT_SYMBOL_GPL(kvm_put_guest_fpu); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bb0314ea9267..dfde04b0d453 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -38,6 +38,7 @@ #define KVM_REQ_MMU_SYNC 7 #define KVM_REQ_KVMCLOCK_UPDATE 8 #define KVM_REQ_KICK 9 +#define KVM_REQ_DEACTIVATE_FPU 10 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 -- cgit v1.2.3 From 55cd8e5a4edb8e235163ffe8264b9aaa8d7c050f Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Sun, 17 Jan 2010 15:51:22 +0200 Subject: KVM: Implement bare minimum of HYPER-V MSRs Minimum HYPER-V implementation should have GUEST_OS_ID, HYPERCALL and VP_INDEX MSRs. [avi: fix build on i386] Signed-off-by: Gleb Natapov Signed-off-by: Vadim Rozenfeld Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 4 + arch/x86/include/asm/kvm_para.h | 1 + arch/x86/kvm/trace.h | 32 +++++++ arch/x86/kvm/x86.c | 193 +++++++++++++++++++++++++++++++++++++++- include/linux/kvm.h | 1 + 5 files changed, 230 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 93bee7abb71c..67d19e422006 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -413,6 +413,10 @@ struct kvm_arch { s64 kvmclock_offset; struct kvm_xen_hvm_config xen_hvm_config; + + /* fields used by HYPER-V emulation */ + u64 hv_guest_os_id; + u64 hv_hypercall; }; struct kvm_vm_stat { diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index c584076a47f4..ffae1420e7d7 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -2,6 +2,7 @@ #define _ASM_X86_KVM_PARA_H #include +#include /* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx. It * should be used to determine that a VM is running under KVM. diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 816e0449db0b..1cb3d0e990f3 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -55,6 +55,38 @@ TRACE_EVENT(kvm_hypercall, __entry->a3) ); +/* + * Tracepoint for hypercall. + */ +TRACE_EVENT(kvm_hv_hypercall, + TP_PROTO(__u16 code, bool fast, __u16 rep_cnt, __u16 rep_idx, + __u64 ingpa, __u64 outgpa), + TP_ARGS(code, fast, rep_cnt, rep_idx, ingpa, outgpa), + + TP_STRUCT__entry( + __field( __u16, code ) + __field( bool, fast ) + __field( __u16, rep_cnt ) + __field( __u16, rep_idx ) + __field( __u64, ingpa ) + __field( __u64, outgpa ) + ), + + TP_fast_assign( + __entry->code = code; + __entry->fast = fast; + __entry->rep_cnt = rep_cnt; + __entry->rep_idx = rep_idx; + __entry->ingpa = ingpa; + __entry->outgpa = outgpa; + ), + + TP_printk("code 0x%x %s cnt 0x%x idx 0x%x in 0x%llx out 0x%llx", + __entry->code, __entry->fast ? "fast" : "slow", + __entry->rep_cnt, __entry->rep_idx, __entry->ingpa, + __entry->outgpa) +); + /* * Tracepoint for PIO. */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1ad34d185da9..480137db4770 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -622,9 +622,10 @@ static inline u32 bit(int bitno) * kvm-specific. Those are put in the beginning of the list. */ -#define KVM_SAVE_MSRS_BEGIN 2 +#define KVM_SAVE_MSRS_BEGIN 4 static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_K6_STAR, #ifdef CONFIG_X86_64 @@ -1004,6 +1005,74 @@ out: return r; } +static bool kvm_hv_hypercall_enabled(struct kvm *kvm) +{ + return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE; +} + +static bool kvm_hv_msr_partition_wide(u32 msr) +{ + bool r = false; + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + case HV_X64_MSR_HYPERCALL: + r = true; + break; + } + + return r; +} + +static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + kvm->arch.hv_guest_os_id = data; + /* setting guest os id to zero disables hypercall page */ + if (!kvm->arch.hv_guest_os_id) + kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; + break; + case HV_X64_MSR_HYPERCALL: { + u64 gfn; + unsigned long addr; + u8 instructions[4]; + + /* if guest os id is not set hypercall should remain disabled */ + if (!kvm->arch.hv_guest_os_id) + break; + if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) { + kvm->arch.hv_hypercall = data; + break; + } + gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT; + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return 1; + kvm_x86_ops->patch_hypercall(vcpu, instructions); + ((unsigned char *)instructions)[3] = 0xc3; /* ret */ + if (copy_to_user((void __user *)addr, instructions, 4)) + return 1; + kvm->arch.hv_hypercall = data; + break; + } + default: + pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); + return 1; + } + return 0; +} + +static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x data 0x%llx\n", + msr, data); + + return 1; +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) { switch (msr) { @@ -1118,6 +1187,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) pr_unimpl(vcpu, "unimplemented perfctr wrmsr: " "0x%x data 0x%llx\n", msr, data); break; + case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + if (kvm_hv_msr_partition_wide(msr)) { + int r; + mutex_lock(&vcpu->kvm->lock); + r = set_msr_hyperv_pw(vcpu, msr, data); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return set_msr_hyperv(vcpu, msr, data); + break; default: if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); @@ -1217,6 +1296,48 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } +static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + struct kvm *kvm = vcpu->kvm; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + data = kvm->arch.hv_guest_os_id; + break; + case HV_X64_MSR_HYPERCALL: + data = kvm->arch.hv_hypercall; + break; + default: + pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + + *pdata = data; + return 0; +} + +static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + + switch (msr) { + case HV_X64_MSR_VP_INDEX: { + int r; + struct kvm_vcpu *v; + kvm_for_each_vcpu(r, v, vcpu->kvm) + if (v == vcpu) + data = r; + break; + } + default: + pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + *pdata = data; + return 0; +} + int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) { u64 data; @@ -1283,6 +1404,16 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1: return get_msr_mce(vcpu, msr, pdata); + case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + if (kvm_hv_msr_partition_wide(msr)) { + int r; + mutex_lock(&vcpu->kvm->lock); + r = get_msr_hyperv_pw(vcpu, msr, pdata); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return get_msr_hyperv(vcpu, msr, pdata); + break; default: if (!ignore_msrs) { pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); @@ -1398,6 +1529,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_XEN_HVM: case KVM_CAP_ADJUST_CLOCK: case KVM_CAP_VCPU_EVENTS: + case KVM_CAP_HYPERV: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -3618,11 +3750,70 @@ static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0, return a0 | ((gpa_t)a1 << 32); } +int kvm_hv_hypercall(struct kvm_vcpu *vcpu) +{ + u64 param, ingpa, outgpa, ret; + uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0; + bool fast, longmode; + int cs_db, cs_l; + + /* + * hypercall generates UD from non zero cpl and real mode + * per HYPER-V spec + */ + if (kvm_x86_ops->get_cpl(vcpu) != 0 || + !kvm_read_cr0_bits(vcpu, X86_CR0_PE)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 0; + } + + kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + longmode = is_long_mode(vcpu) && cs_l == 1; + + if (!longmode) { + param = (kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffff); + ingpa = (kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffff); + outgpa = (kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffff); + } +#ifdef CONFIG_X86_64 + else { + param = kvm_register_read(vcpu, VCPU_REGS_RCX); + ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX); + outgpa = kvm_register_read(vcpu, VCPU_REGS_R8); + } +#endif + + code = param & 0xffff; + fast = (param >> 16) & 0x1; + rep_cnt = (param >> 32) & 0xfff; + rep_idx = (param >> 48) & 0xfff; + + trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); + + res = HV_STATUS_INVALID_HYPERCALL_CODE; + + ret = res | (((u64)rep_done & 0xfff) << 32); + if (longmode) { + kvm_register_write(vcpu, VCPU_REGS_RAX, ret); + } else { + kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32); + kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff); + } + + return 1; +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; int r = 1; + if (kvm_hv_hypercall_enabled(vcpu->kvm)) + return kvm_hv_hypercall(vcpu); + nr = kvm_register_read(vcpu, VCPU_REGS_RAX); a0 = kvm_register_read(vcpu, VCPU_REGS_RBX); a1 = kvm_register_read(vcpu, VCPU_REGS_RCX); diff --git a/include/linux/kvm.h b/include/linux/kvm.h index f2feef68ffd6..e227cbae70ad 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -497,6 +497,7 @@ struct kvm_ioeventfd { #endif #define KVM_CAP_S390_PSW 42 #define KVM_CAP_PPC_SEGSTATE 43 +#define KVM_CAP_HYPERV 44 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 10388a07164c1512b3a3d0273b9adc230f82790e Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Sun, 17 Jan 2010 15:51:23 +0200 Subject: KVM: Add HYPER-V apic access MSRs Implement HYPER-V apic MSRs. Spec defines three MSRs that speed-up access to EOI/TPR/ICR apic registers for PV guests. Signed-off-by: Gleb Natapov Signed-off-by: Vadim Rozenfeld Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/lapic.c | 31 ++++++++++++++++++++++++++++++ arch/x86/kvm/lapic.h | 8 ++++++++ arch/x86/kvm/x86.c | 42 +++++++++++++++++++++++++++++++++++++---- include/linux/kvm.h | 1 + 5 files changed, 80 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 67d19e422006..a1f0b5dd7d75 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -363,6 +363,8 @@ struct kvm_vcpu_arch { /* used for guest single stepping over the given code position */ u16 singlestep_cs; unsigned long singlestep_rip; + /* fields used by HYPER-V emulation */ + u64 hv_vapic; }; struct kvm_mem_alias { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index ba8c045da782..4b224f90087b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1246,3 +1246,34 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data) return 0; } + +int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (!irqchip_in_kernel(vcpu->kvm)) + return 1; + + /* if this is ICR write vector before command */ + if (reg == APIC_ICR) + apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32)); + return apic_reg_write(apic, reg, (u32)data); +} + +int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + u32 low, high = 0; + + if (!irqchip_in_kernel(vcpu->kvm)) + return 1; + + if (apic_reg_read(apic, reg, 4, &low)) + return 1; + if (reg == APIC_ICR) + apic_reg_read(apic, APIC_ICR2, 4, &high); + + *data = (((u64)high) << 32) | low; + + return 0; +} diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 40010b09c4aa..f5fe32c5edad 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -48,4 +48,12 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu); int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); + +int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data); +int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); + +static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE; +} #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 480137db4770..552be51e4d84 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -622,10 +622,11 @@ static inline u32 bit(int bitno) * kvm-specific. Those are put in the beginning of the list. */ -#define KVM_SAVE_MSRS_BEGIN 4 +#define KVM_SAVE_MSRS_BEGIN 5 static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, + HV_X64_MSR_APIC_ASSIST_PAGE, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_K6_STAR, #ifdef CONFIG_X86_64 @@ -1067,10 +1068,36 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) { - pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x data 0x%llx\n", - msr, data); + switch (msr) { + case HV_X64_MSR_APIC_ASSIST_PAGE: { + unsigned long addr; - return 1; + if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { + vcpu->arch.hv_vapic = data; + break; + } + addr = gfn_to_hva(vcpu->kvm, data >> + HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT); + if (kvm_is_error_hva(addr)) + return 1; + if (clear_user((void __user *)addr, PAGE_SIZE)) + return 1; + vcpu->arch.hv_vapic = data; + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); + default: + pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); + return 1; + } + + return 0; } int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) @@ -1330,6 +1357,12 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) data = r; break; } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); default: pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; @@ -1530,6 +1563,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_ADJUST_CLOCK: case KVM_CAP_VCPU_EVENTS: case KVM_CAP_HYPERV: + case KVM_CAP_HYPERV_VAPIC: r = 1; break; case KVM_CAP_COALESCED_MMIO: diff --git a/include/linux/kvm.h b/include/linux/kvm.h index e227cbae70ad..5ce61738dc30 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -498,6 +498,7 @@ struct kvm_ioeventfd { #define KVM_CAP_S390_PSW 42 #define KVM_CAP_PPC_SEGSTATE 43 #define KVM_CAP_HYPERV 44 +#define KVM_CAP_HYPERV_VAPIC 45 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From c25bc1638a1211f57cccbabdd8b732813b852340 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Sun, 17 Jan 2010 15:51:24 +0200 Subject: KVM: Implement NotifyLongSpinWait HYPER-V hypercall Windows issues this hypercall after guest was spinning on a spinlock for too many iterations. Signed-off-by: Gleb Natapov Signed-off-by: Vadim Rozenfeld Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 10 +++++++++- include/linux/kvm.h | 1 + 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 552be51e4d84..9f72a443455b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1564,6 +1564,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_VCPU_EVENTS: case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: + case KVM_CAP_HYPERV_SPIN: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -3827,7 +3828,14 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); - res = HV_STATUS_INVALID_HYPERCALL_CODE; + switch (code) { + case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT: + kvm_vcpu_on_spin(vcpu); + break; + default: + res = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + } ret = res | (((u64)rep_done & 0xfff) << 32); if (longmode) { diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 5ce61738dc30..4c4937e7f65f 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -499,6 +499,7 @@ struct kvm_ioeventfd { #define KVM_CAP_PPC_SEGSTATE 43 #define KVM_CAP_HYPERV 44 #define KVM_CAP_HYPERV_VAPIC 45 +#define KVM_CAP_HYPERV_SPIN 46 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 0c04851c0c093ce98ab4ca69556480d779292418 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 21 Jan 2010 15:31:52 +0200 Subject: KVM: trace guest fpu loads and unloads Signed-off-by: Avi Kivity Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/x86.c | 2 ++ include/trace/events/kvm.h | 19 +++++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 27af6e353b06..3b90298fb980 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5292,6 +5292,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) vcpu->guest_fpu_loaded = 1; kvm_fx_save(&vcpu->arch.host_fx_image); kvm_fx_restore(&vcpu->arch.guest_fx_image); + trace_kvm_fpu(1); } void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) @@ -5304,6 +5305,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) kvm_fx_restore(&vcpu->arch.host_fx_image); ++vcpu->stat.fpu_reload; set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests); + trace_kvm_fpu(0); } void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index dbe108455275..8abdc1230143 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -145,6 +145,25 @@ TRACE_EVENT(kvm_mmio, __entry->len, __entry->gpa, __entry->val) ); +#define kvm_fpu_load_symbol \ + {0, "unload"}, \ + {1, "load"} + +TRACE_EVENT(kvm_fpu, + TP_PROTO(int load), + TP_ARGS(load), + + TP_STRUCT__entry( + __field( u32, load ) + ), + + TP_fast_assign( + __entry->load = load; + ), + + TP_printk("%s", __print_symbolic(__entry->load, kvm_fpu_load_symbol)) +); + #endif /* _TRACE_KVM_MAIN_H */ /* This part must be outside protection */ -- cgit v1.2.3 From ab9f4ecbb6d39a18e300a0d10a4968c37404aa76 Mon Sep 17 00:00:00 2001 From: "Zhai, Edwin" Date: Fri, 29 Jan 2010 14:38:44 +0800 Subject: KVM: enable PCI multiple-segments for pass-through device Enable optional parameter (default 0) - PCI segment (or domain) besides BDF, when assigning PCI device to guest. Signed-off-by: Zhai Edwin Acked-by: Chris Wright Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/x86.c | 1 + include/linux/kvm.h | 4 +++- include/linux/kvm_host.h | 1 + virt/kvm/assigned-dev.c | 4 +++- virt/kvm/iommu.c | 9 ++++++--- 5 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d47ceda7a928..0bf3df527afc 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1569,6 +1569,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_PCI_SEGMENT: r = 1; break; case KVM_CAP_COALESCED_MMIO: diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 4c4937e7f65f..dfa54be881f4 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -500,6 +500,7 @@ struct kvm_ioeventfd { #define KVM_CAP_HYPERV 44 #define KVM_CAP_HYPERV_VAPIC 45 #define KVM_CAP_HYPERV_SPIN 46 +#define KVM_CAP_PCI_SEGMENT 47 #ifdef KVM_CAP_IRQ_ROUTING @@ -694,8 +695,9 @@ struct kvm_assigned_pci_dev { __u32 busnr; __u32 devfn; __u32 flags; + __u32 segnr; union { - __u32 reserved[12]; + __u32 reserved[11]; }; }; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index dfde04b0d453..665c37063f30 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -400,6 +400,7 @@ struct kvm_assigned_dev_kernel { struct work_struct interrupt_work; struct list_head list; int assigned_dev_id; + int host_segnr; int host_busnr; int host_devfn; unsigned int entries_nr; diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index f51e684dd238..057e2cca6af5 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -526,7 +526,8 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, r = -ENOMEM; goto out; } - dev = pci_get_bus_and_slot(assigned_dev->busnr, + dev = pci_get_domain_bus_and_slot(assigned_dev->segnr, + assigned_dev->busnr, assigned_dev->devfn); if (!dev) { printk(KERN_INFO "%s: host device not found\n", __func__); @@ -548,6 +549,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, pci_reset_function(dev); match->assigned_dev_id = assigned_dev->assigned_dev_id; + match->host_segnr = assigned_dev->segnr; match->host_busnr = assigned_dev->busnr; match->host_devfn = assigned_dev->devfn; match->flags = assigned_dev->flags; diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c index 65a51432c8e5..80fd3ad3b2de 100644 --- a/virt/kvm/iommu.c +++ b/virt/kvm/iommu.c @@ -106,7 +106,8 @@ int kvm_assign_device(struct kvm *kvm, r = iommu_attach_device(domain, &pdev->dev); if (r) { - printk(KERN_ERR "assign device %x:%x.%x failed", + printk(KERN_ERR "assign device %x:%x:%x.%x failed", + pci_domain_nr(pdev->bus), pdev->bus->number, PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn)); @@ -127,7 +128,8 @@ int kvm_assign_device(struct kvm *kvm, goto out_unmap; } - printk(KERN_DEBUG "assign device: host bdf = %x:%x:%x\n", + printk(KERN_DEBUG "assign device %x:%x:%x.%x\n", + assigned_dev->host_segnr, assigned_dev->host_busnr, PCI_SLOT(assigned_dev->host_devfn), PCI_FUNC(assigned_dev->host_devfn)); @@ -154,7 +156,8 @@ int kvm_deassign_device(struct kvm *kvm, iommu_detach_device(domain, &pdev->dev); - printk(KERN_DEBUG "deassign device: host bdf = %x:%x:%x\n", + printk(KERN_DEBUG "deassign device %x:%x:%x.%x\n", + assigned_dev->host_segnr, assigned_dev->host_busnr, PCI_SLOT(assigned_dev->host_devfn), PCI_FUNC(assigned_dev->host_devfn)); -- cgit v1.2.3 From 8f0b1ab6fb045a1324d9435ba00c2940783b0041 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 28 Jan 2010 12:37:56 +0100 Subject: KVM: Introduce kvm_host_page_size This patch introduces a generic function to find out the host page size for a given gfn. This function is needed by the kvm iommu code. This patch also simplifies the x86 host_mapping_level function. Signed-off-by: Joerg Roedel Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 18 ++---------------- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 25 +++++++++++++++++++++++++ 3 files changed, 28 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index dc4d954efacd..913ef4b7939a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -468,24 +468,10 @@ static int has_wrprotected_page(struct kvm *kvm, static int host_mapping_level(struct kvm *kvm, gfn_t gfn) { - unsigned long page_size = PAGE_SIZE; - struct vm_area_struct *vma; - unsigned long addr; + unsigned long page_size; int i, ret = 0; - addr = gfn_to_hva(kvm, gfn); - if (kvm_is_error_hva(addr)) - return PT_PAGE_TABLE_LEVEL; - - down_read(¤t->mm->mmap_sem); - vma = find_vma(current->mm, addr); - if (!vma) - goto out; - - page_size = vma_kernel_pagesize(vma); - -out: - up_read(¤t->mm->mmap_sem); + page_size = kvm_host_page_size(kvm, gfn); for (i = PT_PAGE_TABLE_LEVEL; i < (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES); ++i) { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 665c37063f30..3145b281de9d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -300,6 +300,7 @@ int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); +unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); void kvm_vcpu_block(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2b0974a14835..0a360c26cc34 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -867,6 +868,30 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); +unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn) +{ + struct vm_area_struct *vma; + unsigned long addr, size; + + size = PAGE_SIZE; + + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return PAGE_SIZE; + + down_read(¤t->mm->mmap_sem); + vma = find_vma(current->mm, addr); + if (!vma) + goto out; + + size = vma_kernel_pagesize(vma); + +out: + up_read(¤t->mm->mmap_sem); + + return size; +} + int memslot_id(struct kvm *kvm, gfn_t gfn) { int i; -- cgit v1.2.3 From 90bb6fc556ab255abd798bcf4ff5769690ab2eea Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 31 Dec 2009 12:10:16 +0200 Subject: KVM: MMU: Add tracepoint for guest page aging Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 11 ++++++++--- include/trace/events/kvm.h | 22 ++++++++++++++++++++++ 2 files changed, 30 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b8da6715d08b..739793240d1d 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -151,6 +151,9 @@ module_param(oos_shadow, bool, 0644); #define ACC_USER_MASK PT_USER_MASK #define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) +#include + +#undef TRACE_INCLUDE_FILE #define CREATE_TRACE_POINTS #include "mmutrace.h" @@ -792,6 +795,7 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, unsigned long data)) { int i, j; + int ret; int retval = 0; struct kvm_memslots *slots; @@ -806,16 +810,17 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, if (hva >= start && hva < end) { gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT; - retval |= handler(kvm, &memslot->rmap[gfn_offset], - data); + ret = handler(kvm, &memslot->rmap[gfn_offset], data); for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) { int idx = gfn_offset; idx /= KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL + j); - retval |= handler(kvm, + ret |= handler(kvm, &memslot->lpage_info[j][idx].rmap_pde, data); } + trace_kvm_age_page(hva, memslot, ret); + retval |= ret; } } diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 8abdc1230143..b17d49dfc3ef 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -164,6 +164,28 @@ TRACE_EVENT(kvm_fpu, TP_printk("%s", __print_symbolic(__entry->load, kvm_fpu_load_symbol)) ); +TRACE_EVENT(kvm_age_page, + TP_PROTO(ulong hva, struct kvm_memory_slot *slot, int ref), + TP_ARGS(hva, slot, ref), + + TP_STRUCT__entry( + __field( u64, hva ) + __field( u64, gfn ) + __field( u8, referenced ) + ), + + TP_fast_assign( + __entry->hva = hva; + __entry->gfn = + slot->base_gfn + ((hva - slot->userspace_addr) >> PAGE_SHIFT); + __entry->referenced = ref; + ), + + TP_printk("hva %llx gfn %llx %s", + __entry->hva, __entry->gfn, + __entry->referenced ? "YOUNG" : "OLD") +); + #endif /* _TRACE_KVM_MAIN_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 70e335e16882df5b5d6971022e63c3603a1e8c23 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 18 Feb 2010 11:25:22 +0200 Subject: KVM: Convert kvm->requests_lock to raw_spinlock_t The code relies on kvm->requests_lock inhibiting preemption. Noted by Jan Kiszka. Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3145b281de9d..a3fd0f91d943 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -161,7 +161,7 @@ struct kvm_memslots { struct kvm { spinlock_t mmu_lock; - spinlock_t requests_lock; + raw_spinlock_t requests_lock; struct mutex slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ struct kvm_memslots *memslots; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 0a360c26cc34..548f9253c195 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -138,7 +138,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) zalloc_cpumask_var(&cpus, GFP_ATOMIC); - spin_lock(&kvm->requests_lock); + raw_spin_lock(&kvm->requests_lock); me = smp_processor_id(); kvm_for_each_vcpu(i, vcpu, kvm) { if (test_and_set_bit(req, &vcpu->requests)) @@ -153,7 +153,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) smp_call_function_many(cpus, ack_flush, NULL, 1); else called = false; - spin_unlock(&kvm->requests_lock); + raw_spin_unlock(&kvm->requests_lock); free_cpumask_var(cpus); return called; } @@ -409,7 +409,7 @@ static struct kvm *kvm_create_vm(void) kvm->mm = current->mm; atomic_inc(&kvm->mm->mm_count); spin_lock_init(&kvm->mmu_lock); - spin_lock_init(&kvm->requests_lock); + raw_spin_lock_init(&kvm->requests_lock); kvm_eventfd_init(kvm); mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); -- cgit v1.2.3 From d2be1651b736002e0c76d7095d6c0ba77b4a897c Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 23 Feb 2010 17:47:57 +0100 Subject: KVM: x86: Add KVM_CAP_X86_ROBUST_SINGLESTEP This marks the guest single-step API improvement of 94fe45da and 91586a3b with a capability flag to allow reliable detection by user space. Signed-off-by: Jan Kiszka Cc: stable@kernel.org (2.6.33) Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 1 + include/linux/kvm.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c3d2acbbb91b..e46282a56565 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1570,6 +1570,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: case KVM_CAP_PCI_SEGMENT: + case KVM_CAP_X86_ROBUST_SINGLESTEP: r = 1; break; case KVM_CAP_COALESCED_MMIO: diff --git a/include/linux/kvm.h b/include/linux/kvm.h index dfa54be881f4..60df9c84ecae 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -501,6 +501,7 @@ struct kvm_ioeventfd { #define KVM_CAP_HYPERV_VAPIC 45 #define KVM_CAP_HYPERV_SPIN 46 #define KVM_CAP_PCI_SEGMENT 47 +#define KVM_CAP_X86_ROBUST_SINGLESTEP 51 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3