If userspace creates and destroys multiple VMs within the same process we leak 20k of memory in the userspace process context per VM. This patch frees the memory in kvm_arch_destroy_vm. If the process exits without closing the VM file descriptor or the file descriptor has been shared with another process then we don't need to free the memory.
Messing with user space memory from an fd is not ideal, but other changes would require user space changes and this is consistent with how the memory is currently allocated. Tested: Test ran several VMs and ran against test program meant to demonstrate the leak (www.spinics.net/lists/kvm/msg83734.html). Signed-off-by: Andrew Honig <aho...@google.com> --- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/vmx.c | 3 +++ arch/x86/kvm/x86.c | 11 +++++++++++ 3 files changed, 17 insertions(+) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4979778..975a74d 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -553,6 +553,9 @@ struct kvm_arch { struct page *ept_identity_pagetable; bool ept_identity_pagetable_done; gpa_t ept_identity_map_addr; + unsigned long ept_ptr; + unsigned long apic_ptr; + unsigned long tss_ptr; unsigned long irq_sources_bitmap; s64 kvmclock_offset; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 6667042..8aa5d81 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3703,6 +3703,7 @@ static int alloc_apic_access_page(struct kvm *kvm) } kvm->arch.apic_access_page = page; + kvm->arch.apic_ptr = kvm_userspace_mem.userspace_addr; out: mutex_unlock(&kvm->slots_lock); return r; @@ -3733,6 +3734,7 @@ static int alloc_identity_pagetable(struct kvm *kvm) } kvm->arch.ept_identity_pagetable = page; + kvm->arch.ept_ptr = kvm_userspace_mem.userspace_addr; out: mutex_unlock(&kvm->slots_lock); return r; @@ -4366,6 +4368,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) if (ret) return ret; kvm->arch.tss_addr = addr; + kvm->arch.tss_ptr = tss_mem.userspace_addr; if (!init_rmode_tss(kvm)) return -ENOMEM; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f19ac0a..411ff2a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6812,6 +6812,16 @@ void kvm_arch_sync_events(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { + if (current->mm == kvm->mm) { + /* + * Free pages allocated on behalf of userspace, unless the + * the memory map has changed due to process exit or fd + * copying. + */ + vm_munmap(kvm->arch.apic_ptr, PAGE_SIZE); + vm_munmap(kvm->arch.ept_ptr, PAGE_SIZE); + vm_munmap(kvm->arch.tss_ptr, PAGE_SIZE * 3); + } kvm_iommu_unmap_guest(kvm); kfree(kvm->arch.vpic); kfree(kvm->arch.vioapic); @@ -6929,6 +6939,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, return PTR_ERR((void *)userspace_addr); memslot->userspace_addr = userspace_addr; + mem->userspace_addr = userspace_addr; } return 0; -- 1.7.10.4 -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html