From 32fad281c0680ed0ccade7dda85a2121cf9b1d06 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 4 May 2012 02:32:53 +0000 Subject: KVM: PPC: Book3S HV: Make the guest hash table size configurable This adds a new ioctl to enable userspace to control the size of the guest hashed page table (HPT) and to clear it out when resetting the guest. The KVM_PPC_ALLOCATE_HTAB ioctl is a VM ioctl and takes as its parameter a pointer to a u32 containing the desired order of the HPT (log base 2 of the size in bytes), which is updated on successful return to the actual order of the HPT which was allocated. There must be no vcpus running at the time of this ioctl. To enforce this, we now keep a count of the number of vcpus running in kvm->arch.vcpus_running. If the ioctl is called when a HPT has already been allocated, we don't reallocate the HPT but just clear it out. We first clear the kvm->arch.rma_setup_done flag, which has two effects: (a) since we hold the kvm->lock mutex, it will prevent any vcpus from starting to run until we're done, and (b) it means that the first vcpu to run after we're done will re-establish the VRMA if necessary. If userspace doesn't call this ioctl before running the first vcpu, the kernel will allocate a default-sized HPT at that point. We do it then rather than when creating the VM, as the code did previously, so that userspace has a chance to do the ioctl if it wants. When allocating the HPT, we can allocate either from the kernel page allocator, or from the preallocated pool. If userspace is asking for a different size from the preallocated HPTs, we first try to allocate using the kernel page allocator. Then we try to allocate from the preallocated pool, and then if that fails, we try allocating decreasing sizes from the kernel page allocator, down to the minimum size allowed (256kB). Note that the kernel page allocator limits allocations to 1 << CONFIG_FORCE_MAX_ZONEORDER pages, which by default corresponds to 16MB (on 64-bit powerpc, at least). Signed-off-by: Paul Mackerras [agraf: fix module compilation] Signed-off-by: Alexander Graf --- include/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 09f2b3aa2da7..2ce09aa7d3b3 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -617,6 +617,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_SIGNAL_MSI 77 #define KVM_CAP_PPC_GET_SMMU_INFO 78 #define KVM_CAP_S390_COW 79 +#define KVM_CAP_PPC_ALLOC_HTAB 80 #ifdef KVM_CAP_IRQ_ROUTING @@ -828,6 +829,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SIGNAL_MSI _IOW(KVMIO, 0xa5, struct kvm_msi) /* Available with KVM_CAP_PPC_GET_SMMU_INFO */ #define KVM_PPC_GET_SMMU_INFO _IOR(KVMIO, 0xa6, struct kvm_ppc_smmu_info) +/* Available with KVM_CAP_PPC_ALLOC_HTAB */ +#define KVM_PPC_ALLOCATE_HTAB _IOWR(KVMIO, 0xa7, __u32) /* * ioctls for vcpu fds -- cgit v1.2.3 From c1a7b32a14138f908df52d7c53b5ce3415ec6b50 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Sun, 20 May 2012 13:15:07 +0900 Subject: KVM: Avoid wasting pages for small lpage_info arrays lpage_info is created for each large level even when the memory slot is not for RAM. This means that when we add one slot for a PCI device, we end up allocating at least KVM_NR_PAGE_SIZES - 1 pages by vmalloc(). To make things worse, there is an increasing number of devices which would result in more pages being wasted this way. This patch mitigates this problem by using kvm_kvzalloc(). Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c4464356b35b..19b83f6efa49 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -535,6 +535,9 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); void kvm_free_physmem(struct kvm *kvm); +void *kvm_kvzalloc(unsigned long size); +void kvm_kvfree(const void *addr); + #ifndef __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { -- cgit v1.2.3 From a737f256bf14adf94920aa70d150ab4dcd145109 Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Sun, 3 Jun 2012 21:17:48 +0300 Subject: KVM: Cleanup the kvm_print functions and introduce pr_XX wrappers Introduces a couple of print functions, which are essentially wrappers around standard printk functions, with a KVM: prefix. Functions introduced or modified are: - kvm_err(fmt, ...) - kvm_info(fmt, ...) - kvm_debug(fmt, ...) - kvm_pr_unimpl(fmt, ...) - pr_unimpl(vcpu, fmt, ...) -> vcpu_unimpl(vcpu, fmt, ...) Signed-off-by: Christoffer Dall Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 19b83f6efa49..27ac8a4767fa 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -314,13 +314,19 @@ struct kvm { long tlbs_dirty; }; -/* The guest did something we don't support. */ -#define pr_unimpl(vcpu, fmt, ...) \ - pr_err_ratelimited("kvm: %i: cpu%i " fmt, \ - current->tgid, (vcpu)->vcpu_id , ## __VA_ARGS__) +#define kvm_err(fmt, ...) \ + pr_err("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) +#define kvm_info(fmt, ...) \ + pr_info("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) +#define kvm_debug(fmt, ...) \ + pr_debug("kvm [%i]: " fmt, task_pid_nr(current), ## __VA_ARGS__) +#define kvm_pr_unimpl(fmt, ...) \ + pr_err_ratelimited("kvm [%i]: " fmt, \ + task_tgid_nr(current), ## __VA_ARGS__) -#define kvm_printf(kvm, fmt ...) printk(KERN_DEBUG fmt) -#define vcpu_printf(vcpu, fmt...) kvm_printf(vcpu->kvm, fmt) +/* The guest did something we don't support. */ +#define vcpu_unimpl(vcpu, fmt, ...) \ + kvm_pr_unimpl("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { -- cgit v1.2.3 From 9900b4b48b095895cf962054e45aafa49ef70f74 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 15 Jun 2012 15:07:02 -0400 Subject: KVM: use KVM_CAP_IRQ_ROUTING to protect the routing related code The KVM code sometimes uses CONFIG_HAVE_KVM_IRQCHIP to protect code that is related to IRQ routing, which not all in-kernel irqchips may support. Use KVM_CAP_IRQ_ROUTING instead. Signed-off-by: Marc Zyngier Signed-off-by: Christoffer Dall Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 27ac8a4767fa..c7f77876c9b3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -802,7 +802,7 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se } #endif -#ifdef CONFIG_HAVE_KVM_IRQCHIP +#ifdef KVM_CAP_IRQ_ROUTING #define KVM_MAX_IRQ_ROUTES 1024 -- cgit v1.2.3 From 36c1ed821bd11fb9a3f99a060b1553c114dc2d07 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 15 Jun 2012 15:07:24 -0400 Subject: KVM: Guard mmu_notifier specific code with CONFIG_MMU_NOTIFIER In order to avoid compilation failure when KVM is not compiled in, guard the mmu_notifier specific sections with both CONFIG_MMU_NOTIFIER and KVM_ARCH_WANT_MMU_NOTIFIER, like it is being done in the rest of the KVM code. Signed-off-by: Marc Zyngier Signed-off-by: Christoffer Dall Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c7f77876c9b3..e3c86f8c86c9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -306,7 +306,7 @@ struct kvm { struct hlist_head irq_ack_notifier_list; #endif -#ifdef KVM_ARCH_WANT_MMU_NOTIFIER +#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) struct mmu_notifier mmu_notifier; unsigned long mmu_notifier_seq; long mmu_notifier_count; @@ -780,7 +780,7 @@ struct kvm_stats_debugfs_item { extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; -#ifdef KVM_ARCH_WANT_MMU_NOTIFIER +#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_seq) { if (unlikely(vcpu->kvm->mmu_notifier_count)) -- cgit v1.2.3