From e08b96371625aaa84cb03f51acc4c8e0be27403a Mon Sep 17 00:00:00 2001 From: Carsten Otte Date: Wed, 4 Jan 2012 10:25:20 +0100 Subject: KVM: s390: add parameter for KVM_CREATE_VM This patch introduces a new config option for user controlled kernel virtual machines. It introduces a parameter to KVM_CREATE_VM that allows to set bits that alter the capabilities of the newly created virtual machine. The parameter is passed to kvm_arch_init_vm for all architectures. The only valid modifier bit for now is KVM_VM_S390_UCONTROL. This requires CAP_SYS_ADMIN privileges and creates a user controlled virtual machine on s390 architectures. Signed-off-by: Carsten Otte Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm.h | 3 +++ include/linux/kvm_host.h | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 68e67e50d028..bba393a6760f 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -431,6 +431,9 @@ struct kvm_ppc_pvinfo { #define KVMIO 0xAE +/* machine type bits, to be used as argument to KVM_CREATE_VM */ +#define KVM_VM_S390_UCONTROL 1 + /* * ioctls for /dev/kvm fds: */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 900c76337e8f..82375e145e64 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -520,7 +520,7 @@ static inline void kvm_arch_free_vm(struct kvm *kvm) } #endif -int kvm_arch_init_vm(struct kvm *kvm); +int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_free_all_assigned_devices(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); -- cgit v1.2.3 From 27e0393f15fc8bc855c6a888387ff5ffd2181089 Mon Sep 17 00:00:00 2001 From: Carsten Otte Date: Wed, 4 Jan 2012 10:25:21 +0100 Subject: KVM: s390: ucontrol: per vcpu address spaces This patch introduces two ioctls for virtual cpus, that are only valid for kernel virtual machines that are controlled by userspace. Each virtual cpu has its individual address space in this mode of operation, and each address space is backed by the gmap implementation just like the address space for regular KVM guests. KVM_S390_UCAS_MAP allows to map a part of the user's virtual address space to the vcpu. Starting offset and length in both the user and the vcpu address space need to be aligned to 1M. KVM_S390_UCAS_UNMAP can be used to unmap a range of memory from a virtual cpu in a similar way. Signed-off-by: Carsten Otte Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index bba393a6760f..0a66c1072691 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -658,6 +658,16 @@ struct kvm_clock_data { struct kvm_userspace_memory_region) #define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64) + +/* enable ucontrol for s390 */ +struct kvm_s390_ucas_mapping { + __u64 user_addr; + __u64 vcpu_addr; + __u64 length; +}; +#define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) +#define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) + /* Device model IOC */ #define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) #define KVM_IRQ_LINE _IOW(KVMIO, 0x61, struct kvm_irq_level) -- cgit v1.2.3 From e168bf8de33e16a909df2401af1f7d419c5780de Mon Sep 17 00:00:00 2001 From: Carsten Otte Date: Wed, 4 Jan 2012 10:25:22 +0100 Subject: KVM: s390: ucontrol: export page faults to user This patch introduces a new exit reason in the kvm_run structure named KVM_EXIT_S390_UCONTROL. This exit indicates, that a virtual cpu has regognized a fault on the host page table. The idea is that userspace can handle this fault by mapping memory at the fault location into the cpu's address space and then continue to run the virtual cpu. Signed-off-by: Carsten Otte Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 0a66c1072691..7f686f6708b0 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -162,6 +162,7 @@ struct kvm_pit_config { #define KVM_EXIT_INTERNAL_ERROR 17 #define KVM_EXIT_OSI 18 #define KVM_EXIT_PAPR_HCALL 19 +#define KVM_EXIT_S390_UCONTROL 20 /* For KVM_EXIT_INTERNAL_ERROR */ #define KVM_INTERNAL_ERROR_EMULATION 1 @@ -249,6 +250,11 @@ struct kvm_run { #define KVM_S390_RESET_CPU_INIT 8 #define KVM_S390_RESET_IPL 16 __u64 s390_reset_flags; + /* KVM_EXIT_S390_UCONTROL */ + struct { + __u64 trans_exc_code; + __u32 pgm_code; + } s390_ucontrol; /* KVM_EXIT_DCR */ struct { __u32 dcrn; -- cgit v1.2.3 From 5b1c1493afe8d69909f9df3221bb2fffdf479f4a Mon Sep 17 00:00:00 2001 From: Carsten Otte Date: Wed, 4 Jan 2012 10:25:23 +0100 Subject: KVM: s390: ucontrol: export SIE control block to user This patch exports the s390 SIE hardware control block to userspace via the mapping of the vcpu file descriptor. In order to do so, a new arch callback named kvm_arch_vcpu_fault is introduced for all architectures. It allows to map architecture specific pages. Signed-off-by: Carsten Otte Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm.h | 2 ++ include/linux/kvm_host.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 7f686f6708b0..8f888df206a2 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -440,6 +440,8 @@ struct kvm_ppc_pvinfo { /* machine type bits, to be used as argument to KVM_CREATE_VM */ #define KVM_VM_S390_UCONTROL 1 +#define KVM_S390_SIE_PAGE_OFFSET 1 + /* * ioctls for /dev/kvm fds: */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 82375e145e64..d4d4d7092110 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -450,6 +450,7 @@ long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); +int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf); int kvm_dev_ioctl_check_extension(long ext); -- cgit v1.2.3 From ccc7910fe564d99415def7c041fa261e62a43011 Mon Sep 17 00:00:00 2001 From: Carsten Otte Date: Wed, 4 Jan 2012 10:25:26 +0100 Subject: KVM: s390: ucontrol: interface to inject faults on a vcpu page table This patch allows the user to fault in pages on a virtual cpus address space for user controlled virtual machines. Typically this is superfluous because userspace can just create a mapping and let the kernel's page fault logic take are of it. There is one exception: SIE won't start if the lowcore is not present. Normally the kernel takes care of this [handle_validity() in arch/s390/kvm/intercept.c] but since the kernel does not handle intercepts for user controlled virtual machines, userspace needs to be able to handle this condition. Signed-off-by: Carsten Otte Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 8f888df206a2..778e748927b4 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -675,6 +675,7 @@ struct kvm_s390_ucas_mapping { }; #define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) #define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) +#define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) /* Device model IOC */ #define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) -- cgit v1.2.3 From 1efd0f595ab9d10fef1486dfdef952107c91f3db Mon Sep 17 00:00:00 2001 From: Carsten Otte Date: Wed, 4 Jan 2012 10:25:29 +0100 Subject: KVM: s390: ucontrol: announce capability for user controlled vms This patch announces a new capability KVM_CAP_S390_UCONTROL that indicates that kvm can now support virtual machines that are controlled by userspace. Signed-off-by: Carsten Otte Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 778e748927b4..6cf048d9604b 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -569,6 +569,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_PPC_PAPR 68 #define KVM_CAP_S390_GMAP 71 #define KVM_CAP_TSC_DEADLINE_TIMER 72 +#define KVM_CAP_S390_UCONTROL 73 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From b9e5dc8d4511e6a00862a795319569e7fe7f60f4 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 11 Jan 2012 11:20:30 +0100 Subject: KVM: provide synchronous registers in kvm_run On some cpus the overhead for virtualization instructions is in the same range as a system call. Having to call multiple ioctls to get set registers will make certain userspace handled exits more expensive than necessary. Lets provide a section in kvm_run that works as a shared save area for guest registers. We also provide two 64bit flags fields (architecture specific), that will specify 1. which parts of these fields are valid. 2. which registers were modified by userspace Each bit for these flag fields will define a group of registers (like general purpose) or a single register. Signed-off-by: Christian Borntraeger Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 6cf048d9604b..245bcb3a0fcd 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -279,6 +279,20 @@ struct kvm_run { /* Fix the size of the union. */ char padding[256]; }; + + /* + * shared registers between kvm and userspace. + * kvm_valid_regs specifies the register classes set by the host + * kvm_dirty_regs specified the register classes dirtied by userspace + * struct kvm_sync_regs is architecture specific, as well as the + * bits for kvm_valid_regs and kvm_dirty_regs + */ + __u64 kvm_valid_regs; + __u64 kvm_dirty_regs; + union { + struct kvm_sync_regs regs; + char padding[1024]; + } s; }; /* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */ @@ -570,6 +584,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_S390_GMAP 71 #define KVM_CAP_TSC_DEADLINE_TIMER 72 #define KVM_CAP_S390_UCONTROL 73 +#define KVM_CAP_SYNC_REGS 74 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From dc83b8bc0256ee682506ed83853a98eaba529c6f Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Thu, 18 Aug 2011 15:25:21 -0500 Subject: KVM: PPC: e500: MMU API This implements a shared-memory API for giving host userspace access to the guest's TLB. Signed-off-by: Scott Wood Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 245bcb3a0fcd..fa029ced4bd5 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -581,6 +581,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_PPC_RMA 65 #define KVM_CAP_MAX_VCPUS 66 /* returns max vcpus per vm */ #define KVM_CAP_PPC_PAPR 68 +#define KVM_CAP_SW_TLB 69 #define KVM_CAP_S390_GMAP 71 #define KVM_CAP_TSC_DEADLINE_TIMER 72 #define KVM_CAP_S390_UCONTROL 73 @@ -664,6 +665,21 @@ struct kvm_clock_data { __u32 pad[9]; }; +#define KVM_MMU_FSL_BOOKE_NOHV 0 +#define KVM_MMU_FSL_BOOKE_HV 1 + +struct kvm_config_tlb { + __u64 params; + __u64 array; + __u32 mmu_type; + __u32 array_len; +}; + +struct kvm_dirty_tlb { + __u64 bitmap; + __u32 num_dirty; +}; + /* * ioctls for VM fds */ @@ -801,6 +817,8 @@ struct kvm_s390_ucas_mapping { #define KVM_CREATE_SPAPR_TCE _IOW(KVMIO, 0xa8, struct kvm_create_spapr_tce) /* Available with KVM_CAP_RMA */ #define KVM_ALLOCATE_RMA _IOR(KVMIO, 0xa9, struct kvm_allocate_rma) +/* Available with KVM_CAP_SW_TLB */ +#define KVM_DIRTY_TLB _IOW(KVMIO, 0xaa, struct kvm_dirty_tlb) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -- cgit v1.2.3 From a355aa54f1d25dff83c0feef8863d83a76988fdb Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 12 Dec 2011 12:37:21 +0000 Subject: KVM: Add barriers to allow mmu_notifier_retry to be used locklessly This adds an smp_wmb in kvm_mmu_notifier_invalidate_range_end() and an smp_rmb in mmu_notifier_retry() so that mmu_notifier_retry() will give the correct answer when called without kvm->mmu_lock being held. PowerPC Book3S HV KVM wants to use a bitlock per guest page rather than a single global spinlock in order to improve the scalability of updates to the guest MMU hashed page table, and so needs this. Signed-off-by: Paul Mackerras Acked-by: Avi Kivity Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d4d4d7092110..eada8e69fe58 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -702,12 +702,16 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se if (unlikely(vcpu->kvm->mmu_notifier_count)) return 1; /* - * Both reads happen under the mmu_lock and both values are - * modified under mmu_lock, so there's no need of smb_rmb() - * here in between, otherwise mmu_notifier_count should be - * read before mmu_notifier_seq, see - * mmu_notifier_invalidate_range_end write side. + * Ensure the read of mmu_notifier_count happens before the read + * of mmu_notifier_seq. This interacts with the smp_wmb() in + * mmu_notifier_invalidate_range_end to make sure that the caller + * either sees the old (non-zero) value of mmu_notifier_count or + * the new (incremented) value of mmu_notifier_seq. + * PowerPC Book3s HV KVM calls this under a per-page lock + * rather than under kvm->mmu_lock, for scalability, so + * can't rely on kvm->mmu_lock to keep things ordered. */ + smp_rmb(); if (vcpu->kvm->mmu_notifier_seq != mmu_seq) return 1; return 0; -- cgit v1.2.3 From e24ed81fedd551e80378be62fa0b0532480ea7d4 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Wed, 14 Sep 2011 10:02:41 +0200 Subject: KVM: PPC: Add generic single register ioctls Right now we transfer a static struct every time we want to get or set registers. Unfortunately, over time we realize that there are more of these than we thought of before and the extensibility and flexibility of transferring a full struct every time is limited. So this is a new approach to the problem. With these new ioctls, we can get and set a single register that is identified by an ID. This allows for very precise and limited transmittal of data. When we later realize that it's a better idea to shove over multiple registers at once, we can reuse most of the infrastructure and simply implement a GET_MANY_REGS / SET_MANY_REGS interface. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index fa029ced4bd5..4f7a9fb8ab06 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -582,6 +582,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_MAX_VCPUS 66 /* returns max vcpus per vm */ #define KVM_CAP_PPC_PAPR 68 #define KVM_CAP_SW_TLB 69 +#define KVM_CAP_ONE_REG 70 #define KVM_CAP_S390_GMAP 71 #define KVM_CAP_TSC_DEADLINE_TIMER 72 #define KVM_CAP_S390_UCONTROL 73 @@ -680,6 +681,37 @@ struct kvm_dirty_tlb { __u32 num_dirty; }; +/* Available with KVM_CAP_ONE_REG */ + +#define KVM_REG_ARCH_MASK 0xff00000000000000ULL +#define KVM_REG_GENERIC 0x0000000000000000ULL + +/* + * Architecture specific registers are to be defined in arch headers and + * ORed with the arch identifier. + */ +#define KVM_REG_PPC 0x1000000000000000ULL +#define KVM_REG_X86 0x2000000000000000ULL +#define KVM_REG_IA64 0x3000000000000000ULL +#define KVM_REG_ARM 0x4000000000000000ULL +#define KVM_REG_S390 0x5000000000000000ULL + +#define KVM_REG_SIZE_SHIFT 52 +#define KVM_REG_SIZE_MASK 0x00f0000000000000ULL +#define KVM_REG_SIZE_U8 0x0000000000000000ULL +#define KVM_REG_SIZE_U16 0x0010000000000000ULL +#define KVM_REG_SIZE_U32 0x0020000000000000ULL +#define KVM_REG_SIZE_U64 0x0030000000000000ULL +#define KVM_REG_SIZE_U128 0x0040000000000000ULL +#define KVM_REG_SIZE_U256 0x0050000000000000ULL +#define KVM_REG_SIZE_U512 0x0060000000000000ULL +#define KVM_REG_SIZE_U1024 0x0070000000000000ULL + +struct kvm_one_reg { + __u64 id; + __u64 addr; +}; + /* * ioctls for VM fds */ @@ -819,6 +851,9 @@ struct kvm_s390_ucas_mapping { #define KVM_ALLOCATE_RMA _IOR(KVMIO, 0xa9, struct kvm_allocate_rma) /* Available with KVM_CAP_SW_TLB */ #define KVM_DIRTY_TLB _IOW(KVMIO, 0xaa, struct kvm_dirty_tlb) +/* Available with KVM_CAP_ONE_REG */ +#define KVM_GET_ONE_REG _IOW(KVMIO, 0xab, struct kvm_one_reg) +#define KVM_SET_ONE_REG _IOW(KVMIO, 0xac, struct kvm_one_reg) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -- cgit v1.2.3 From 1022fc3d3bfaca09d5d6bfcc93a168de16840814 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Wed, 14 Sep 2011 21:45:23 +0200 Subject: KVM: PPC: Add support for explicit HIOR setting Until now, we always set HIOR based on the PVR, but this is just wrong. Instead, we should be setting HIOR explicitly, so user space can decide what the initial HIOR value is - just like on real hardware. We keep the old PVR based way around for backwards compatibility, but once user space uses the SET_ONE_REG based method, we drop the PVR logic. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 4f7a9fb8ab06..acbe42939089 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -580,6 +580,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_PPC_SMT 64 #define KVM_CAP_PPC_RMA 65 #define KVM_CAP_MAX_VCPUS 66 /* returns max vcpus per vm */ +#define KVM_CAP_PPC_HIOR 67 #define KVM_CAP_PPC_PAPR 68 #define KVM_CAP_SW_TLB 69 #define KVM_CAP_ONE_REG 70 -- cgit v1.2.3 From 9d4cba7f93c52d4121ab9c6f289e582d368a6979 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Thu, 12 Jan 2012 20:09:51 +0000 Subject: KVM: Move gfn_to_memslot() to kvm_host.h This moves __gfn_to_memslot() and search_memslots() from kvm_main.c to kvm_host.h to reduce the code duplication caused by the need for non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c to call gfn_to_memslot() in real mode. Rather than putting gfn_to_memslot() itself in a header, which would lead to increased code size, this puts __gfn_to_memslot() in a header. Then, the non-modular uses of gfn_to_memslot() are changed to call __gfn_to_memslot() instead. This way there is only one place in the source code that needs to be changed should the gfn_to_memslot() implementation need to be modified. On powerpc, the Book3S HV style of KVM has code that is called from real mode which needs to call gfn_to_memslot() and thus needs this. (Module code is allocated in the vmalloc region, which can't be accessed in real mode.) With this, we can remove builtin_gfn_to_memslot() from book3s_hv_rm_mmu.c. Signed-off-by: Paul Mackerras Acked-by: Avi Kivity Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index eada8e69fe58..9698080c902b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -651,6 +651,31 @@ static inline void kvm_guest_exit(void) current->flags &= ~PF_VCPU; } +/* + * search_memslots() and __gfn_to_memslot() are here because they are + * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c. + * gfn_to_memslot() itself isn't here as an inline because that would + * bloat other code too much. + */ +static inline struct kvm_memory_slot * +search_memslots(struct kvm_memslots *slots, gfn_t gfn) +{ + struct kvm_memory_slot *memslot; + + kvm_for_each_memslot(memslot, slots) + if (gfn >= memslot->base_gfn && + gfn < memslot->base_gfn + memslot->npages) + return memslot; + + return NULL; +} + +static inline struct kvm_memory_slot * +__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) +{ + return search_memslots(slots, gfn); +} + static inline int memslot_id(struct kvm *kvm, gfn_t gfn) { return gfn_to_memslot(kvm, gfn)->id; -- cgit v1.2.3 From fb03cb6f44236f4bef62a0dda8e025ff5ca51417 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 8 Feb 2012 12:59:10 +0900 Subject: KVM: Introduce gfn_to_index() which returns the index for a given level This patch cleans up the code and removes the "(void)level;" warning suppressor. Note that we can also use this for PT_PAGE_TABLE_LEVEL to treat every level uniformly later. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9698080c902b..7a08496b974a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -681,6 +681,13 @@ static inline int memslot_id(struct kvm *kvm, gfn_t gfn) return gfn_to_memslot(kvm, gfn)->id; } +static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) +{ + /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */ + return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - + (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); +} + static inline unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { -- cgit v1.2.3 From db3fe4eb45f3555d91a7124e18cf3a2f2a30eb90 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 8 Feb 2012 13:02:18 +0900 Subject: KVM: Introduce kvm_memory_slot::arch and move lpage_info into it Some members of kvm_memory_slot are not used by every architecture. This patch is the first step to make this difference clear by introducing kvm_memory_slot::arch; lpage_info is moved into it. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7a08496b974a..355e44555c39 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -171,11 +171,6 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) -struct kvm_lpage_info { - unsigned long rmap_pde; - int write_count; -}; - struct kvm_memory_slot { gfn_t base_gfn; unsigned long npages; @@ -184,7 +179,7 @@ struct kvm_memory_slot { unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_head; unsigned long nr_dirty_pages; - struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; + struct kvm_arch_memory_slot arch; unsigned long userspace_addr; int user_alloc; int id; @@ -376,6 +371,9 @@ 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); +void kvm_arch_free_memslot(struct kvm_memory_slot *free, + struct kvm_memory_slot *dont); +int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, @@ -385,6 +383,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, struct kvm_memory_slot old, int user_alloc); +bool kvm_largepages_enabled(void); void kvm_disable_largepages(void); void kvm_arch_flush_shadow(struct kvm *kvm); -- cgit v1.2.3 From 3e515705a1f46beb1c942bb8043c16f8ac7b1e9e Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 5 Mar 2012 14:23:29 +0200 Subject: KVM: Ensure all vcpus are consistent with in-kernel irqchip settings If some vcpus are created before KVM_CREATE_IRQCHIP, then irqchip_in_kernel() and vcpu->arch.apic will be inconsistent, leading to potential NULL pointer dereferences. Fix by: - ensuring that no vcpus are installed when KVM_CREATE_IRQCHIP is called - ensuring that a vcpu has an apic if it is installed after KVM_CREATE_IRQCHIP This is somewhat long winded because vcpu->arch.apic is created without kvm->lock held. Based on earlier patch by Michael Ellerman. Signed-off-by: Michael Ellerman Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 355e44555c39..e42d85ae8541 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -805,6 +805,13 @@ static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) { return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id; } + +bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu); + +#else + +static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; } + #endif #ifdef __KVM_HAVE_DEVICE_ASSIGNMENT -- cgit v1.2.3 From 07700a94b00a4fcbbfb07d1b72dc112a0e036735 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 28 Feb 2012 14:19:54 +0100 Subject: KVM: Allow host IRQ sharing for assigned PCI 2.3 devices PCI 2.3 allows to generically disable IRQ sources at device level. This enables us to share legacy IRQs of such devices with other host devices when passing them to a guest. The new IRQ sharing feature introduced here is optional, user space has to request it explicitly. Moreover, user space can inform us about its view of PCI_COMMAND_INTX_DISABLE so that we can avoid unmasking the interrupt and signaling it if the guest masked it via the virtualized PCI config space. Signed-off-by: Jan Kiszka Acked-by: Alex Williamson Acked-by: Michael S. Tsirkin Signed-off-by: Avi Kivity --- include/linux/kvm.h | 6 ++++++ include/linux/kvm_host.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index acbe42939089..6c322a90b92f 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -588,6 +588,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_TSC_DEADLINE_TIMER 72 #define KVM_CAP_S390_UCONTROL 73 #define KVM_CAP_SYNC_REGS 74 +#define KVM_CAP_PCI_2_3 75 #ifdef KVM_CAP_IRQ_ROUTING @@ -784,6 +785,9 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_TSC_CONTROL */ #define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2) #define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3) +/* Available with KVM_CAP_PCI_2_3 */ +#define KVM_ASSIGN_SET_INTX_MASK _IOW(KVMIO, 0xa4, \ + struct kvm_assigned_pci_dev) /* * ioctls for vcpu fds @@ -857,6 +861,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_ONE_REG _IOW(KVMIO, 0xac, struct kvm_one_reg) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) +#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) +#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) struct kvm_assigned_pci_dev { __u32 assigned_dev_id; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e42d85ae8541..ec171c1d0878 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -546,6 +546,7 @@ struct kvm_assigned_dev_kernel { unsigned int entries_nr; int host_irq; bool host_irq_disabled; + bool pci_2_3; struct msix_entry *host_msix_entries; int guest_irq; struct msix_entry *guest_msix_entries; @@ -555,6 +556,7 @@ struct kvm_assigned_dev_kernel { struct pci_dev *dev; struct kvm *kvm; spinlock_t intx_lock; + struct mutex intx_mask_lock; char irq_name[32]; struct pci_saved_state *pci_saved_state; }; -- cgit v1.2.3 From cf9eeac46350b8b43730b7dc5e999757bed089a4 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Wed, 14 Mar 2012 11:02:11 +0100 Subject: KVM: Convert intx_mask_lock to spin lock As kvm_notify_acked_irq calls kvm_assigned_dev_ack_irq under rcu_read_lock, we cannot use a mutex in the latter function. Switch to a spin lock to address this. Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti 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 ec171c1d0878..40bb1c661a6e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -556,7 +556,7 @@ struct kvm_assigned_dev_kernel { struct pci_dev *dev; struct kvm *kvm; spinlock_t intx_lock; - struct mutex intx_mask_lock; + spinlock_t intx_mask_lock; char irq_name[32]; struct pci_saved_state *pci_saved_state; }; -- cgit v1.2.3