diff options
64 files changed, 2509 insertions, 884 deletions
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index cb2ef0b..4d0542c 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -3039,6 +3039,87 @@ Returns: 0 on success, -1 on error Queues an SMI on the thread's vcpu. +4.97 KVM_CAP_PPC_MULTITCE + +Capability: KVM_CAP_PPC_MULTITCE +Architectures: ppc +Type: vm + +This capability means the kernel is capable of handling hypercalls +H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user +space. This significantly accelerates DMA operations for PPC KVM guests. +User space should expect that its handlers for these hypercalls +are not going to be called if user space previously registered LIOBN +in KVM (via KVM_CREATE_SPAPR_TCE or similar calls). + +In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest, +user space might have to advertise it for the guest. For example, +IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is +present in the "ibm,hypertas-functions" device-tree property. + +The hypercalls mentioned above may or may not be processed successfully +in the kernel based fast path. If they can not be handled by the kernel, +they will get passed on to user space. So user space still has to have +an implementation for these despite the in kernel acceleration. + +This capability is always enabled. + +4.98 KVM_CREATE_SPAPR_TCE_64 + +Capability: KVM_CAP_SPAPR_TCE_64 +Architectures: powerpc +Type: vm ioctl +Parameters: struct kvm_create_spapr_tce_64 (in) +Returns: file descriptor for manipulating the created TCE table + +This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit +windows, described in 4.62 KVM_CREATE_SPAPR_TCE + +This capability uses extended struct in ioctl interface: + +/* for KVM_CAP_SPAPR_TCE_64 */ +struct kvm_create_spapr_tce_64 { + __u64 liobn; + __u32 page_shift; + __u32 flags; + __u64 offset; /* in pages */ + __u64 size; /* in pages */ +}; + +The aim of extension is to support an additional bigger DMA window with +a variable page size. +KVM_CREATE_SPAPR_TCE_64 receives a 64bit window size, an IOMMU page shift and +a bus offset of the corresponding DMA window, @size and @offset are numbers +of IOMMU pages. + +@flags are not used at the moment. + +The rest of functionality is identical to KVM_CREATE_SPAPR_TCE. + +4.98 KVM_REINJECT_CONTROL + +Capability: KVM_CAP_REINJECT_CONTROL +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_reinject_control (in) +Returns: 0 on success, + -EFAULT if struct kvm_reinject_control cannot be read, + -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier. + +i8254 (PIT) has two modes, reinject and !reinject. The default is reinject, +where KVM queues elapsed i8254 ticks and monitors completion of interrupt from +vector(s) that i8254 injects. Reinject mode dequeues a tick and injects its +interrupt whenever there isn't a pending interrupt from i8254. +!reinject mode injects an interrupt as soon as a tick arrives. + +struct kvm_reinject_control { + __u8 pit_reinject; + __u8 reserved[31]; +}; + +pit_reinject = 0 (!reinject mode) is recommended, unless running an old +operating system that uses the PIT for timing (e.g. Linux 2.4.x). + 5. The kvm_run structure ------------------------ @@ -3343,6 +3424,7 @@ EOI was received. struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 +#define KVM_EXIT_HYPERV_HCALL 2 __u32 type; union { struct { @@ -3351,6 +3433,11 @@ EOI was received. __u64 evt_page; __u64 msg_page; } synic; + struct { + __u64 input; + __u64 result; + __u64 params[2]; + } hcall; } u; }; /* KVM_EXIT_HYPERV */ diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt index d1ad9d5..e3e314c 100644 --- a/Documentation/virtual/kvm/devices/s390_flic.txt +++ b/Documentation/virtual/kvm/devices/s390_flic.txt @@ -88,6 +88,8 @@ struct kvm_s390_io_adapter_req { perform a gmap translation for the guest address provided in addr, pin a userspace page for the translated address and add it to the list of mappings + Note: A new mapping will be created unconditionally; therefore, + the calling code should avoid making duplicate mappings. KVM_S390_IO_ADAPTER_UNMAP release a userspace page for the translated address specified in addr diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virtual/kvm/devices/vm.txt index f083a16..a9ea877 100644 --- a/Documentation/virtual/kvm/devices/vm.txt +++ b/Documentation/virtual/kvm/devices/vm.txt @@ -84,3 +84,55 @@ Returns: -EBUSY in case 1 or more vcpus are already activated (only in write -EFAULT if the given address is not accessible from kernel space -ENOMEM if not enough memory is available to process the ioctl 0 in case of success + +3. GROUP: KVM_S390_VM_TOD +Architectures: s390 + +3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH + +Allows user space to set/get the TOD clock extension (u8). + +Parameters: address of a buffer in user space to store the data (u8) to +Returns: -EFAULT if the given address is not accessible from kernel space + -EINVAL if setting the TOD clock extension to != 0 is not supported + +3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW + +Allows user space to set/get bits 0-63 of the TOD clock register as defined in +the POP (u64). + +Parameters: address of a buffer in user space to store the data (u64) to +Returns: -EFAULT if the given address is not accessible from kernel space + +4. GROUP: KVM_S390_VM_CRYPTO +Architectures: s390 + +4.1. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_AES_KW (w/o) + +Allows user space to enable aes key wrapping, including generating a new +wrapping key. + +Parameters: none +Returns: 0 + +4.2. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_DEA_KW (w/o) + +Allows user space to enable dea key wrapping, including generating a new +wrapping key. + +Parameters: none +Returns: 0 + +4.3. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_AES_KW (w/o) + +Allows user space to disable aes key wrapping, clearing the wrapping key. + +Parameters: none +Returns: 0 + +4.4. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_DEA_KW (w/o) + +Allows user space to disable dea key wrapping, clearing the wrapping key. + +Parameters: none +Returns: 0 diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index daf9c0f..dda2e93 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -391,11 +391,11 @@ To instantiate a large spte, four constraints must be satisfied: write-protected pages - the guest page must be wholly contained by a single memory slot -To check the last two conditions, the mmu maintains a ->write_count set of +To check the last two conditions, the mmu maintains a ->disallow_lpage set of arrays for each memory slot and large page size. Every write protected page -causes its write_count to be incremented, thus preventing instantiation of +causes its disallow_lpage to be incremented, thus preventing instantiation of a large spte. The frames at the end of an unaligned memory slot have -artificially inflated ->write_counts so they can never be instantiated. +artificially inflated ->disallow_lpages so they can never be instantiated. Zapping all pages (page generation count) ========================================= diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 2aa79c8..7529aab 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -33,8 +33,6 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu) } #endif -#define SPAPR_TCE_SHIFT 12 - #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE #define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ #endif diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 9d08d8c..2e7c791 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -182,7 +182,10 @@ struct kvmppc_spapr_tce_table { struct list_head list; struct kvm *kvm; u64 liobn; - u32 window_size; + struct rcu_head rcu; + u32 page_shift; + u64 offset; /* in pages */ + u64 size; /* window size in pages */ struct page *pages[0]; }; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 2241d53..2544eda 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -165,9 +165,25 @@ extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu, extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu); extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, - struct kvm_create_spapr_tce *args); + struct kvm_create_spapr_tce_64 *args); +extern struct kvmppc_spapr_tce_table *kvmppc_find_table( + struct kvm_vcpu *vcpu, unsigned long liobn); +extern long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt, + unsigned long ioba, unsigned long npages); +extern long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *tt, + unsigned long tce); +extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa, + unsigned long *ua, unsigned long **prmap); +extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt, + unsigned long idx, unsigned long tce); extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba, unsigned long tce); +extern long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, + unsigned long liobn, unsigned long ioba, + unsigned long tce_list, unsigned long npages); +extern long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, + unsigned long liobn, unsigned long ioba, + unsigned long tce_value, unsigned long npages); extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba); extern struct page *kvm_alloc_hpt(unsigned long nr_pages); @@ -437,6 +453,8 @@ static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { return vcpu->arch.irq_type == KVMPPC_IRQ_XICS; } +extern void kvmppc_alloc_host_rm_ops(void); +extern void kvmppc_free_host_rm_ops(void); extern void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu); extern int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server); extern int kvm_vm_ioctl_xics_irq(struct kvm *kvm, struct kvm_irq_level *args); @@ -445,7 +463,11 @@ extern u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu); extern int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval); extern int kvmppc_xics_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu, u32 cpu); +extern void kvmppc_xics_ipi_action(void); +extern int h_ipi_redirect; #else +static inline void kvmppc_alloc_host_rm_ops(void) {}; +static inline void kvmppc_free_host_rm_ops(void) {}; static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { return 0; } static inline void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu) { } @@ -459,6 +481,33 @@ static inline int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd) { return 0; } #endif +/* + * Host-side operations we want to set up while running in real + * mode in the guest operating on the xics. + * Currently only VCPU wakeup is supported. + */ + +union kvmppc_rm_state { + unsigned long raw; + struct { + u32 in_host; + u32 rm_action; + }; +}; + +struct kvmppc_host_rm_core { + union kvmppc_rm_state rm_state; + void *rm_data; + char pad[112]; +}; + +struct kvmppc_host_rm_ops { + struct kvmppc_host_rm_core *rm_core; + void (*vcpu_kick)(struct kvm_vcpu *vcpu); +}; + +extern struct kvmppc_host_rm_ops *kvmppc_host_rm_ops_hv; + static inline unsigned long kvmppc_get_epr(struct kvm_vcpu *vcpu) { #ifdef CONFIG_KVM_BOOKE_HV diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index ac9fb11..47897a3 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -78,6 +78,9 @@ static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, } return __find_linux_pte_or_hugepte(pgdir, ea, is_thp, shift); } + +unsigned long vmalloc_to_phys(void *vmalloc_addr); + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 825663c..78083ed 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -114,6 +114,9 @@ extern int cpu_to_core_id(int cpu); #define PPC_MSG_TICK_BROADCAST 2 #define PPC_MSG_DEBUGGER_BREAK 3 +/* This is only used by the powernv kernel */ +#define PPC_MSG_RM_HOST_ACTION 4 + /* for irq controllers that have dedicated ipis per message (4) */ extern int smp_request_message_ipi(int virq, int message); extern const char *smp_ipi_name[]; @@ -121,6 +124,7 @@ extern const char *smp_ipi_name[]; /* for irq controllers with only a single ipi */ extern void smp_muxed_ipi_set_data(int cpu, unsigned long data); extern void smp_muxed_ipi_message_pass(int cpu, int msg); +extern void smp_muxed_ipi_set_message(int cpu, int msg); extern irqreturn_t smp_ipi_demux(void); void smp_init_pSeries(void); diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index 0e25bdb..2546048 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -30,6 +30,7 @@ #ifdef CONFIG_PPC_ICP_NATIVE extern int icp_native_init(void); extern void icp_native_flush_interrupt(void); +extern void icp_native_cause_ipi_rm(int cpu); #else static inline int icp_native_init(void) { return -ENODEV; } #endif diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index ab4d473..c93cf35 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -333,6 +333,15 @@ struct kvm_create_spapr_tce { __u32 window_size; }; +/* for KVM_CAP_SPAPR_TCE_64 */ +struct kvm_create_spapr_tce_64 { + __u64 liobn; + __u32 page_shift; + __u32 flags; + __u64 offset; /* in pages */ + __u64 size; /* in pages */ +}; + /* for KVM_ALLOCATE_RMA */ struct kvm_allocate_rma { __u64 rma_size; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index ec9ec20..cb8be5d 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -206,7 +206,7 @@ int smp_request_message_ipi(int virq, int msg) #ifdef CONFIG_PPC_SMP_MUXED_IPI struct cpu_messages { - int messages; /* current messages */ + long messages; /* current messages */ unsigned long data; /* data for cause ipi */ }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message); @@ -218,7 +218,7 @@ void smp_muxed_ipi_set_data(int cpu, unsigned long data) info->data = data; } -void smp_muxed_ipi_message_pass(int cpu, int msg) +void smp_muxed_ipi_set_message(int cpu, int msg) { struct cpu_messages *info = &per_cpu(ipi_message, cpu); char *message = (char *)&info->messages; @@ -228,6 +228,13 @@ void smp_muxed_ipi_message_pass(int cpu, int msg) */ smp_mb(); message[msg] = 1; +} + +void smp_muxed_ipi_message_pass(int cpu, int msg) +{ + struct cpu_messages *info = &per_cpu(ipi_message, cpu); + + smp_muxed_ipi_set_message(cpu, msg); /* * cause_ipi functions are required to include a full barrier * before doing whatever causes the IPI. @@ -236,20 +243,31 @@ void smp_muxed_ipi_message_pass(int cpu, int msg) } #ifdef __BIG_ENDIAN__ -#define IPI_MESSAGE(A) (1 << (24 - 8 * (A))) +#define IPI_MESSAGE(A) (1uL << ((BITS_PER_LONG - 8) - 8 * (A))) #else -#define IPI_MESSAGE(A) (1 << (8 * (A))) +#define IPI_MESSAGE(A) (1uL << (8 * (A))) #endif irqreturn_t smp_ipi_demux(void) { struct cpu_messages *info = this_cpu_ptr(&ipi_message); - unsigned int all; + unsigned long all; mb(); /* order any irq clear */ do { all = xchg(&info->messages, 0); +#if defined(CONFIG_KVM_XICS) && defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) + /* + * Must check for PPC_MSG_RM_HOST_ACTION messages + * before PPC_MSG_CALL_FUNCTION messages because when + * a VM is destroyed, we call kick_all_cpus_sync() + * to ensure that any pending PPC_MSG_RM_HOST_ACTION + * messages have completed before we free any VCPUs. + */ + if (all & IPI_MESSAGE(PPC_MSG_RM_HOST_ACTION)) + kvmppc_xics_ipi_action(); +#endif if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNCTION)) generic_smp_call_function_interrupt(); if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE)) diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 0570eef..7f7b6d8 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -8,7 +8,7 @@ ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm KVM := ../../../virt/kvm common-objs-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ - $(KVM)/eventfd.o + $(KVM)/eventfd.o $(KVM)/vfio.o CFLAGS_e500_mmu.o := -I. CFLAGS_e500_mmu_host.o := -I. diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 638c6d9..b34220d 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -807,7 +807,7 @@ int kvmppc_core_init_vm(struct kvm *kvm) { #ifdef CONFIG_PPC64 - INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); + INIT_LIST_HEAD_RCU(&kvm->arch.spapr_tce_tables); INIT_LIST_HEAD(&kvm->arch.rtas_tokens); #endif diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 54cf9bc..2c2d103 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -14,6 +14,7 @@ * * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com> + * Copyright 2016 Alexey Kardashevskiy, IBM Corporation <aik@au1.ibm.com> */ #include <linux/types.h> @@ -36,28 +37,69 @@ #include <asm/ppc-opcode.h> #include <asm/kvm_host.h> #include <asm/udbg.h> +#include <asm/iommu.h> +#include <asm/tce.h> -#define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64)) +static unsigned long kvmppc_tce_pages(unsigned long iommu_pages) +{ + return ALIGN(iommu_pages * sizeof(u64), PAGE_SIZE) / PAGE_SIZE; +} -static long kvmppc_stt_npages(unsigned long window_size) +static unsigned long kvmppc_stt_pages(unsigned long tce_pages) { - return ALIGN((window_size >> SPAPR_TCE_SHIFT) - * sizeof(u64), PAGE_SIZE) / PAGE_SIZE; + unsigned long stt_bytes = sizeof(struct kvmppc_spapr_tce_table) + + (tce_pages * sizeof(struct page *)); + + return tce_pages + ALIGN(stt_bytes, PAGE_SIZE) / PAGE_SIZE; } -static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt) +static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc) { - struct kvm *kvm = stt->kvm; - int i; + long ret = 0; - mutex_lock(&kvm->lock); - list_del(&stt->list); - for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++) + if (!current || !current->mm) + return ret; /* process exited */ + + down_write(¤t->mm->mmap_sem); + + if (inc) { + unsigned long locked, lock_limit; + + locked = current->mm->locked_vm + stt_pages; + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) + ret = -ENOMEM; + else + current->mm->locked_vm += stt_pages; + } else { + if (WARN_ON_ONCE(stt_pages > current->mm->locked_vm)) + stt_pages = current->mm->locked_vm; + + current->mm->locked_vm -= stt_pages; + } + + pr_debug("[%d] RLIMIT_MEMLOCK KVM %c%ld %ld/%ld%s\n", current->pid, + inc ? '+' : '-', + stt_pages << PAGE_SHIFT, + current->mm->locked_vm << PAGE_SHIFT, + rlimit(RLIMIT_MEMLOCK), + ret ? " - exceeded" : ""); + + up_write(¤t->mm->mmap_sem); + + return ret; +} + +static void release_spapr_tce_table(struct rcu_head *head) +{ + struct kvmppc_spapr_tce_table *stt = container_of(head, + struct kvmppc_spapr_tce_table, rcu); + unsigned long i, npages = kvmppc_tce_pages(stt->size); + + for (i = 0; i < npages; i++) __free_page(stt->pages[i]); - kfree(stt); - mutex_unlock(&kvm->lock); - kvm_put_kvm(kvm); + kfree(stt); } static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf) @@ -65,7 +107,7 @@ static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data; struct page *page; - if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size)) + if (vmf->pgoff >= kvmppc_tce_pages(stt->size)) return VM_FAULT_SIGBUS; page = stt->pages[vmf->pgoff]; @@ -88,7 +130,14 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp) { struct kvmppc_spapr_tce_table *stt = filp->private_data; - release_spapr_tce_table(stt); + list_del_rcu(&stt->list); + + kvm_put_kvm(stt->kvm); + + kvmppc_account_memlimit( + kvmppc_stt_pages(kvmppc_tce_pages(stt->size)), false); + call_rcu(&stt->rcu, release_spapr_tce_table); + return 0; } @@ -98,20 +147,29 @@ static const struct file_operations kvm_spapr_tce_fops = { }; long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, - struct kvm_create_spapr_tce *args) + struct kvm_create_spapr_tce_64 *args) { struct kvmppc_spapr_tce_table *stt = NULL; - long npages; + unsigned long npages, size; int ret = -ENOMEM; int i; + if (!args->size) + return -EINVAL; + /* Check this LIOBN hasn't been previously allocated */ list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { if (stt->liobn == args->liobn) return -EBUSY; } - npages = kvmppc_stt_npages(args->window_size); + size = args->size; + npages = kvmppc_tce_pages(size); + ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true); + if (ret) { + stt = NULL; + goto fail; + } stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *), GFP_KERNEL); @@ -119,7 +177,9 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, goto fail; stt->liobn = args->liobn; - stt->window_size = args->window_size; + stt->page_shift = args->page_shift; + stt->offset = args->offset; + stt->size = size; stt->kvm = kvm; for (i = 0; i < npages; i++) { @@ -131,7 +191,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, kvm_get_kvm(kvm); mutex_lock(&kvm->lock); - list_add(&stt->list, &kvm->arch.spapr_tce_tables); + list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); mutex_unlock(&kvm->lock); @@ -148,3 +208,59 @@ fail: } return ret; } + +long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, + unsigned long liobn, unsigned long ioba, + unsigned long tce_list, unsigned long npages) +{ + struct kvmppc_spapr_tce_table *stt; + long i, ret = H_SUCCESS, idx; + unsigned long entry, ua = 0; + u64 __user *tces, tce; + + stt = kvmppc_find_table(vcpu, liobn); + if (!stt) + return H_TOO_HARD; + + entry = ioba >> stt->page_shift; + /* + * SPAPR spec says that the maximum size of the list is 512 TCEs + * so the whole table fits in 4K page + */ + if (npages > 512) + return H_PARAMETER; + + if (tce_list & (SZ_4K - 1)) + return H_PARAMETER; + + ret = kvmppc_ioba_validate(stt, ioba, npages); + if (ret != H_SUCCESS) + return ret; + + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, NULL)) { + ret = H_TOO_HARD; + goto unlock_exit; + } + tces = (u64 __user *) ua; + + for (i = 0; i < npages; ++i) { + if (get_user(tce, tces + i)) { + ret = H_TOO_HARD; + goto unlock_exit; + } + tce = be64_to_cpu(tce); + + ret = kvmppc_tce_validate(stt, tce); + if (ret != H_SUCCESS) + goto unlock_exit; + + kvmppc_tce_put(stt, entry + i, tce); + } + +unlock_exit: + srcu_read_unlock(&vcpu->kvm->srcu, idx); + + return ret; +} +EXPORT_SYMBOL_GPL(kvmppc_h_put_tce_indirect); diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 89e96b3..44be73e 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -14,6 +14,7 @@ * * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com> + * Copyright 2016 Alexey Kardashevskiy, IBM Corporation <aik@au1.ibm.com> */ #include <linux/types.h> @@ -30,76 +31,321 @@ #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> #include <asm/mmu-hash64.h> +#include <asm/mmu_context.h> #include <asm/hvcall.h> #include <asm/synch.h> #include <asm/ppc-opcode.h> #include <asm/kvm_host.h> #include <asm/udbg.h> +#include <asm/iommu.h> +#include <asm/tce.h> +#include <asm/iommu.h> #define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64)) -/* WARNING: This will be called in real-mode on HV KVM and virtual +/* + * Finds a TCE table descriptor by LIOBN. + * + * WARNING: This will be called in real or virtual mode on HV KVM and virtual * mode on PR KVM */ -long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, - unsigned long ioba, unsigned long tce) +struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm_vcpu *vcpu, + unsigned long liobn) { struct kvm *kvm = vcpu->kvm; struct kvmppc_spapr_tce_table *stt; + list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list) + if (stt->liobn == liobn) + return stt; + + return NULL; +} +EXPORT_SYMBOL_GPL(kvmppc_find_table); + +/* + * Validates IO address. + * + * WARNING: This will be called in real-mode on HV KVM and virtual + * mode on PR KVM + */ +long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt, + unsigned long ioba, unsigned long npages) +{ + unsigned long mask = (1ULL << stt->page_shift) - 1; + unsigned long idx = ioba >> stt->page_shift; + + if ((ioba & mask) || (idx < stt->offset) || + (idx - stt->offset + npages > stt->size) || + (idx + npages < idx)) + return H_PARAMETER; + + return H_SUCCESS; +} +EXPORT_SYMBOL_GPL(kvmppc_ioba_validate); + +/* + * Validates TCE address. + * At the moment flags and page mask are validated. + * As the host kernel does not access those addresses (just puts them + * to the table and user space is supposed to process them), we can skip + * checking other things (such as TCE is a guest RAM address or the page + * was actually allocated). + * + * WARNING: This will be called in real-mode on HV KVM and virtual + * mode on PR KVM + */ +long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, unsigned long tce) +{ + unsigned long page_mask = ~((1ULL << stt->page_shift) - 1); + unsigned long mask = ~(page_mask | TCE_PCI_WRITE | TCE_PCI_READ); + + if (tce & mask) + return H_PARAMETER; + + return H_SUCCESS; +} +EXPORT_SYMBOL_GPL(kvmppc_tce_validate); + +/* Note on the use of page_address() in real mode, + * + * It is safe to use page_address() in real mode on ppc64 because + * page_address() is always defined as lowmem_page_address() + * which returns __va(PFN_PHYS(page_to_pfn(page))) which is arithmetic + * operation and does not access page struct. + * + * Theoretically page_address() could be defined different + * but either WANT_PAGE_VIRTUAL or HASHED_PAGE_VIRTUAL + * would have to be enabled. + * WANT_PAGE_VIRTUAL is never enabled on ppc32/ppc64, + * HASHED_PAGE_VIRTUAL could be enabled for ppc32 only and only + * if CONFIG_HIGHMEM is defined. As CONFIG_SPARSEMEM_VMEMMAP + * is not expected to be enabled on ppc32, page_address() + * is safe for ppc32 as well. + * + * WARNING: This will be called in real-mode on HV KVM and virtual + * mode on PR KVM + */ +static u64 *kvmppc_page_address(struct page *page) +{ +#if defined(HASHED_PAGE_VIRTUAL) || defined(WANT_PAGE_VIRTUAL) +#error TODO: fix to avoid page_address() here +#endif + return (u64 *) page_address(page); +} + +/* + * Handles TCE requests for emulated devices. + * Puts guest TCE values to the table and expects user space to convert them. + * Called in both real and virtual modes. + * Cannot fail so kvmppc_tce_validate must be called before it. + * + * WARNING: This will be called in real-mode on HV KVM and virtual + * mode on PR KVM + */ +void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt, + unsigned long idx, unsigned long tce) +{ + struct page *page; + u64 *tbl; + + idx -= stt->offset; + page = stt->pages[idx / TCES_PER_PAGE]; + tbl = kvmppc_page_address(page); + + tbl[idx % TCES_PER_PAGE] = tce; +} +EXPORT_SYMBOL_GPL(kvmppc_tce_put); + +long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa, + unsigned long *ua, unsigned long **prmap) +{ + unsigned long gfn = gpa >> PAGE_SHIFT; + struct kvm_memory_slot *memslot; + + memslot = search_memslots(kvm_memslots(kvm), gfn); + if (!memslot) + return -EINVAL; + + *ua = __gfn_to_hva_memslot(memslot, gfn) | + (gpa & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE)); + +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + if (prmap) + *prmap = &memslot->arch.rmap[gfn - memslot->base_gfn]; +#endif + + return 0; +} +EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua); + +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, + unsigned long ioba, unsigned long tce) +{ + struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn); + long ret; + /* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */ /* liobn, ioba, tce); */ - list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { - if (stt->liobn == liobn) { - unsigned long idx = ioba >> SPAPR_TCE_SHIFT; - struct page *page; - u64 *tbl; - - /* udbg_printf("H_PUT_TCE: liobn 0x%lx => stt=%p window_size=0x%x\n", */ - /* liobn, stt, stt->window_size); */ - if (ioba >= stt->window_size) - return H_PARAMETER; - - page = stt->pages[idx / TCES_PER_PAGE]; - tbl = (u64 *)page_address(page); - - /* FIXME: Need to validate the TCE itself */ - /* udbg_printf("tce @ %p\n", &tbl[idx % TCES_PER_PAGE]); */ - tbl[idx % TCES_PER_PAGE] = tce; - return H_SUCCESS; - } - } + if (!stt) + return H_TOO_HARD; + + ret = kvmppc_ioba_validate(stt, ioba, 1); + if (ret != H_SUCCESS) + return ret; - /* Didn't find the liobn, punt it to userspace */ - return H_TOO_HARD; + ret = kvmppc_tce_validate(stt, tce); + if (ret != H_SUCCESS) + return ret; + + kvmppc_tce_put(stt, ioba >> stt->page_shift, tce); + + return H_SUCCESS; } EXPORT_SYMBOL_GPL(kvmppc_h_put_tce); -long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn, - unsigned long ioba) +static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu, + unsigned long ua, unsigned long *phpa) +{ + pte_t *ptep, pte; + unsigned shift = 0; + + ptep = __find_linux_pte_or_hugepte(vcpu->arch.pgdir, ua, NULL, &shift); + if (!ptep || !pte_present(*ptep)) + return -ENXIO; + pte = *ptep; + + if (!shift) + shift = PAGE_SHIFT; + + /* Avoid handling anything potentially complicated in realmode */ + if (shift > PAGE_SHIFT) + return -EAGAIN; + + if (!pte_young(pte)) + return -EAGAIN; + + *phpa = (pte_pfn(pte) << PAGE_SHIFT) | (ua & ((1ULL << shift) - 1)) | + (ua & ~PAGE_MASK); + + return 0; +} + +long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, + unsigned long liobn, unsigned long ioba, + unsigned long tce_list, unsigned long npages) { - struct kvm *kvm = vcpu->kvm; struct kvmppc_spapr_tce_table *stt; + long i, ret = H_SUCCESS; + unsigned long tces, entry, ua = 0; + unsigned long *rmap = NULL; + + stt = kvmppc_find_table(vcpu, liobn); + if (!stt) + return H_TOO_HARD; + + entry = ioba >> stt->page_shift; + /* + * The spec says that the maximum size of the list is 512 TCEs + * so the whole table addressed resides in 4K page + */ + if (npages > 512) + return H_PARAMETER; + + if (tce_list & (SZ_4K - 1)) + return H_PARAMETER; + + ret = kvmppc_ioba_validate(stt, ioba, npages); + if (ret != H_SUCCESS) + return ret; - list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { - if (stt->liobn == liobn) { - unsigned long idx = ioba >> SPAPR_TCE_SHIFT; - struct page *page; - u64 *tbl; + if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap)) + return H_TOO_HARD; - if (ioba >= stt->window_size) - return H_PARAMETER; + rmap = (void *) vmalloc_to_phys(rmap); - page = stt->pages[idx / TCES_PER_PAGE]; - tbl = (u64 *)page_address(page); + /* + * Synchronize with the MMU notifier callbacks in + * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.). + * While we have the rmap lock, code running on other CPUs + * cannot finish unmapping the host real page that backs + * this guest real page, so we are OK to access the host + * real page. + */ + lock_rmap(rmap); + if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) { + ret = H_TOO_HARD; + goto unlock_exit; + } + + for (i = 0; i < npages; ++i) { + unsigned long tce = be64_to_cpu(((u64 *)tces)[i]); + + ret = kvmppc_tce_validate(stt, tce); + if (ret != H_SUCCESS) + goto unlock_exit; - vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE]; - return H_SUCCESS; - } + kvmppc_tce_put(stt, entry + i, tce); } - /* Didn't find the liobn, punt it to userspace */ - return H_TOO_HARD; +unlock_exit: + unlock_rmap(rmap); + + return ret; +} + +long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, + unsigned long liobn, unsigned long ioba, + unsigned long tce_value, unsigned long npages) +{ + struct kvmppc_spapr_tce_table *stt; + long i, ret; + + stt = kvmppc_find_table(vcpu, liobn); + if (!stt) + return H_TOO_HARD; + + ret = kvmppc_ioba_validate(stt, ioba, npages); + if (ret != H_SUCCESS) + return ret; + + /* Check permission bits only to allow userspace poison TCE for debug */ + if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ)) + return H_PARAMETER; + + for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) + kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value); + + return H_SUCCESS; +} +EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce); + +long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn, + unsigned long ioba) +{ + struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn); + long ret; + unsigned long idx; + struct page *page; + u64 *tbl; + + if (!stt) + return H_TOO_HARD; + + ret = kvmppc_ioba_validate(stt, ioba, 1); + if (ret != H_SUCCESS) + return ret; + + idx = (ioba >> stt->page_shift) - stt->offset; + page = stt->pages[idx / TCES_PER_PAGE]; + tbl = (u64 *)page_address(page); + + vcpu->arch.gpr[4] = tbl[idx % TCES_PER_PAGE]; + + return H_SUCCESS; } EXPORT_SYMBOL_GPL(kvmppc_h_get_tce); + +#endif /* KVM_BOOK3S_HV_POSSIBLE */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index baeddb0..f47fffe 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -81,6 +81,17 @@ static int target_smt_mode; module_param(target_smt_mode, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)"); +#ifdef CONFIG_KVM_XICS +static struct kernel_param_ops module_param_ops = { + .set = param_set_int, + .get = param_get_int, +}; + +module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect, + S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core"); +#endif + static void kvmppc_end_cede(struct kvm_vcpu *vcpu); static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); @@ -768,7 +779,31 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) if (kvmppc_xics_enabled(vcpu)) { ret = kvmppc_xics_hcall(vcpu, req); break; - } /* fallthrough */ + } + return RESUME_HOST; + case H_PUT_TCE: + ret = kvmppc_h_put_tce(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_PUT_TCE_INDIRECT: + ret = kvmppc_h_put_tce_indirect(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6), + kvmppc_get_gpr(vcpu, 7)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; + case H_STUFF_TCE: + ret = kvmppc_h_stuff_tce(vcpu, kvmppc_get_gpr(vcpu, 4), + kvmppc_get_gpr(vcpu, 5), + kvmppc_get_gpr(vcpu, 6), + kvmppc_get_gpr(vcpu, 7)); + if (ret == H_TOO_HARD) + return RESUME_HOST; + break; default: return RESUME_HOST; } @@ -2279,6 +2314,46 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) } /* + * Clear core from the list of active host cores as we are about to + * enter the guest. Only do this if it is the primary thread of the + * core (not if a subcore) that is entering the guest. + */ +static inline void kvmppc_clear_host_core(int cpu) +{ + int core; + + if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu)) + return; + /* + * Memory barrier can be omitted here as we will do a smp_wmb() + * later in kvmppc_start_thread and we need ensure that state is + * visible to other CPUs only after we enter guest. + */ + core = cpu >> threads_shift; + kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 0; +} + +/* + * Advertise this core as an active host core since we exited the guest + * Only need to do this if it is the primary thread of the core that is + * exiting. + */ +static inline void kvmppc_set_host_core(int cpu) +{ + int core; + + if (!kvmppc_host_rm_ops_hv || cpu_thread_in_core(cpu)) + return; + + /* + * Memory barrier can be omitted here because we do a spin_unlock + * immediately after this which provides the memory barrier. + */ + core = cpu >> threads_shift; + kvmppc_host_rm_ops_hv->rm_core[core].rm_state.in_host = 1; +} + +/* * Run a set of guest threads on a physical core. * Called with vc->lock held. */ @@ -2390,6 +2465,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) } } + kvmppc_clear_host_core(pcpu); + /* Start all the threads */ active = 0; for (sub = 0; sub < core_info.n_subcores; ++sub) { @@ -2486,6 +2563,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_ipi_thread(pcpu + i); } + kvmppc_set_host_core(pcpu); + spin_unlock(&vc->lock); /* make sure updates to secondary vcpu structs are visible now */ @@ -2984,6 +3063,114 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) goto out_srcu; } +#ifdef CONFIG_KVM_XICS +static int kvmppc_cpu_notify(struct notifier_block *self, unsigned long action, + void *hcpu) +{ + unsigned long cpu = (long)hcpu; + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + kvmppc_set_host_core(cpu); + break; + +#ifdef CONFIG_HOTPLUG_CPU + case CPU_DEAD: + case CPU_DEAD_FROZEN: + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + kvmppc_clear_host_core(cpu); + break; +#endif + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block kvmppc_cpu_notifier = { + .notifier_call = kvmppc_cpu_notify, +}; + +/* + * Allocate a per-core structure for managing state about which cores are + * running in the host versus the guest and for exchanging data between + * real mode KVM and CPU running in the host. + * This is only done for the first VM. + * The allocated structure stays even if all VMs have stopped. + * It is only freed when the kvm-hv module is unloaded. + * It's OK for this routine to fail, we just don't support host + * core operations like redirecting H_IPI wakeups. + */ +void kvmppc_alloc_host_rm_ops(void) +{ + struct kvmppc_host_rm_ops *ops; + unsigned long l_ops; + int cpu, core; + int size; + + /* Not the first time here ? */ + if (kvmppc_host_rm_ops_hv != NULL) + return; + + ops = kzalloc(sizeof(struct kvmppc_host_rm_ops), GFP_KERNEL); + if (!ops) + return; + + size = cpu_nr_cores() * sizeof(struct kvmppc_host_rm_core); + ops->rm_core = kzalloc(size, GFP_KERNEL); + + if (!ops->rm_core) { + kfree(ops); + return; + } + + get_online_cpus(); + + for (cpu = 0; cpu < nr_cpu_ids; cpu += threads_per_core) { + if (!cpu_online(cpu)) + continue; + + core = cpu >> threads_shift; + ops->rm_core[core].rm_state.in_host = 1; + } + + ops->vcpu_kick = kvmppc_fast_vcpu_kick_hv; + + /* + * Make the contents of the kvmppc_host_rm_ops structure visible + * to other CPUs before we assign it to the global variable. + * Do an atomic assignment (no locks used here), but if someone + * beats us to it, just free our copy and return. + */ + smp_wmb(); + l_ops = (unsigned long) ops; + + if (cmpxchg64((unsigned long *)&kvmppc_host_rm_ops_hv, 0, l_ops)) { + put_online_cpus(); + kfree(ops->rm_core); + kfree(ops); + return; + } + + register_cpu_notifier(&kvmppc_cpu_notifier); + + put_online_cpus(); +} + +void kvmppc_free_host_rm_ops(void) +{ + if (kvmppc_host_rm_ops_hv) { + unregister_cpu_notifier(&kvmppc_cpu_notifier); + kfree(kvmppc_host_rm_ops_hv->rm_core); + kfree(kvmppc_host_rm_ops_hv); + kvmppc_host_rm_ops_hv = NULL; + } +} +#endif + static int kvmppc_core_init_vm_hv(struct kvm *kvm) { unsigned long lpcr, lpid; @@ -2996,6 +3183,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) return -ENOMEM; kvm->arch.lpid = lpid; + kvmppc_alloc_host_rm_ops(); + /* * Since we don't flush the TLB when tearing down a VM, * and this lpid might have previously been used, @@ -3229,6 +3418,7 @@ static int kvmppc_book3s_init_hv(void) static void kvmppc_book3s_exit_hv(void) { + kvmppc_free_host_rm_ops(); kvmppc_hv_ops = NULL; } diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index fd7006b..5f0380d 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -283,3 +283,6 @@ void kvmhv_commence_exit(int trap) kvmhv_interrupt_vcore(vc, ee); } } + +struct kvmppc_host_rm_ops *kvmppc_host_rm_ops_hv; +EXPORT_SYMBOL_GPL(kvmppc_host_rm_ops_hv); diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index 24f5807..980d8a6 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -17,12 +17,16 @@ #include <asm/xics.h> #include <asm/debug.h> #include <asm/synch.h> +#include <asm/cputhreads.h> #include <asm/ppc-opcode.h> #include "book3s_xics.h" #define DEBUG_PASSUP +int h_ipi_redirect = 1; +EXPORT_SYMBOL(h_ipi_redirect); + static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp, u32 new_irq); @@ -50,11 +54,84 @@ static void ics_rm_check_resend(struct kvmppc_xics *xics, /* -- ICP routines -- */ +#ifdef CONFIG_SMP +static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu) +{ + int hcpu; + + hcpu = hcore << threads_shift; + kvmppc_host_rm_ops_hv->rm_core[hcore].rm_data = vcpu; + smp_muxed_ipi_set_message(hcpu, PPC_MSG_RM_HOST_ACTION); + icp_native_cause_ipi_rm(hcpu); +} +#else +static inline void icp_send_hcore_msg(int hcore, struct kvm_vcpu *vcpu) { } +#endif + +/* + * We start the search from our current CPU Id in the core map + * and go in a circle until we get back to our ID looking for a + * core that is running in host context and that hasn't already + * been targeted for another rm_host_ops. + * + * In the future, could consider using a fairer algorithm (one + * that distributes the IPIs better) + * + * Returns -1, if no CPU could be found in the host + * Else, returns a CPU Id which has been reserved for use + */ +static inline int grab_next_hostcore(int start, + struct kvmppc_host_rm_core *rm_core, int max, int action) +{ + bool success; + int core; + union kvmppc_rm_state old, new; + + for (core = start + 1; core < max; core++) { + old = new = READ_ONCE(rm_core[core].rm_state); + + if (!old.in_host || old.rm_action) + continue; + + /* Try to grab this host core if not taken already. */ + new.rm_action = action; + + success = cmpxchg64(&rm_core[core].rm_state.raw, + old.raw, new.raw) == old.raw; + if (success) { + /* + * Make sure that the store to the rm_action is made + * visible before we return to caller (and the + * subsequent store to rm_data) to synchronize with + * the IPI handler. + */ + smp_wmb(); + return core; + } + } + + return -1; +} + +static inline int find_available_hostcore(int action) +{ + int core; + int my_core = smp_processor_id() >> threads_shift; + struct kvmppc_host_rm_core *rm_core = kvmppc_host_rm_ops_hv->rm_core; + + core = grab_next_hostcore(my_core, rm_core, cpu_nr_cores(), action); + if (core == -1) + core = grab_next_hostcore(core, rm_core, my_core, action); + + return core; +} + static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu, struct kvm_vcpu *this_vcpu) { struct kvmppc_icp *this_icp = this_vcpu->arch.icp; int cpu; + int hcore; /* Mark the target VCPU as having an interrupt pending */ vcpu->stat.queue_intr++; @@ -66,11 +143,22 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu, return; } - /* Check if the core is loaded, if not, too hard */ + /* + * Check if the core is loaded, + * if not, find an available host core to post to wake the VCPU, + * if we can't find one, set up state to eventually return too hard. + */ cpu = vcpu->arch.thread_cpu; if (cpu < 0 || cpu >= nr_cpu_ids) { - this_icp->rm_action |= XICS_RM_KICK_VCPU; - this_icp->rm_kick_target = vcpu; + hcore = -1; + if (kvmppc_host_rm_ops_hv && h_ipi_redirect) + hcore = find_available_hostcore(XICS_RM_KICK_VCPU); + if (hcore != -1) { + icp_send_hcore_msg(hcore, vcpu); + } else { + this_icp->rm_action |= XICS_RM_KICK_VCPU; + this_icp->rm_kick_target = vcpu; + } return; } @@ -623,3 +711,40 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) bail: return check_too_hard(xics, icp); } + +/* --- Non-real mode XICS-related built-in routines --- */ + +/** + * Host Operations poked by RM KVM + */ +static void rm_host_ipi_action(int action, void *data) +{ + switch (action) { + case XICS_RM_KICK_VCPU: + kvmppc_host_rm_ops_hv->vcpu_kick(data); + break; + default: + WARN(1, "Unexpected rm_action=%d data=%p\n", action, data); + break; + } + +} + +void kvmppc_xics_ipi_action(void) +{ + int core; + unsigned int cpu = smp_processor_id(); + struct kvmppc_host_rm_core *rm_corep; + + core = cpu >> threads_shift; + rm_corep = &kvmppc_host_rm_ops_hv->rm_core[core]; + + if (rm_corep->rm_data) { + rm_host_ipi_action(rm_corep->rm_state.rm_action, + rm_corep->rm_data); + /* Order these stores against the real mode KVM */ + rm_corep->rm_data = NULL; + smp_wmb(); + rm_corep->rm_state.rm_action = 0; + } +} diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 6ee26de..ed16182 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2006,8 +2006,8 @@ hcall_real_table: .long 0 /* 0x12c */ .long 0 /* 0x130 */ .long DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table - .long 0 /* 0x138 */ - .long 0 /* 0x13c */ + .long DOTSYM(kvmppc_h_stuff_tce) - hcall_real_table + .long DOTSYM(kvmppc_rm_h_put_tce_indirect) - hcall_real_table .long 0 /* 0x140 */ .long 0 /* 0x144 */ .long 0 /* 0x148 */ diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index f2c75a1..02176fd 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -280,6 +280,37 @@ static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +static int kvmppc_h_pr_put_tce_indirect(struct kvm_vcpu *vcpu) +{ + unsigned long liobn = kvmppc_get_gpr(vcpu, 4); + unsigned long ioba = kvmppc_get_gpr(vcpu, 5); + unsigned long tce = kvmppc_get_gpr(vcpu, 6); + unsigned long npages = kvmppc_get_gpr(vcpu, 7); + long rc; + + rc = kvmppc_h_put_tce_indirect(vcpu, liobn, ioba, + tce, npages); + if (rc == H_TOO_HARD) + return EMULATE_FAIL; + kvmppc_set_gpr(vcpu, 3, rc); + return EMULATE_DONE; +} + +static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu) +{ + unsigned long liobn = kvmppc_get_gpr(vcpu, 4); + unsigned long ioba = kvmppc_get_gpr(vcpu, 5); + unsigned long tce_value = kvmppc_get_gpr(vcpu, 6); + unsigned long npages = kvmppc_get_gpr(vcpu, 7); + long rc; + + rc = kvmppc_h_stuff_tce(vcpu, liobn, ioba, tce_value, npages); + if (rc == H_TOO_HARD) + return EMULATE_FAIL; + kvmppc_set_gpr(vcpu, 3, rc); + return EMULATE_DONE; +} + static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd) { long rc = kvmppc_xics_hcall(vcpu, cmd); @@ -306,6 +337,10 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return kvmppc_h_pr_bulk_remove(vcpu); case H_PUT_TCE: return kvmppc_h_pr_put_tce(vcpu); + case H_PUT_TCE_INDIRECT: + return kvmppc_h_pr_put_tce_indirect(vcpu); + case H_STUFF_TCE: + return kvmppc_h_pr_stuff_tce(vcpu); case H_CEDE: kvmppc_set_msr_fast(vcpu, kvmppc_get_msr(vcpu) | MSR_EE); kvm_vcpu_block(vcpu); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index a3b182d..19aa59b 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -33,6 +33,7 @@ #include <asm/tlbflush.h> #include <asm/cputhreads.h> #include <asm/irqflags.h> +#include <asm/iommu.h> #include "timing.h" #include "irq.h" #include "../mm/mmu_decl.h" @@ -437,6 +438,16 @@ void kvm_arch_destroy_vm(struct kvm *kvm) unsigned int i; struct kvm_vcpu *vcpu; +#ifdef CONFIG_KVM_XICS + /* + * We call kick_all_cpus_sync() to ensure that all + * CPUs have executed any pending IPIs before we + * continue and free VCPUs structures below. + */ + if (is_kvmppc_hv_enabled(kvm)) + kick_all_cpus_sync(); +#endif + kvm_for_each_vcpu(i, vcpu, kvm) kvm_arch_vcpu_free(vcpu); @@ -509,6 +520,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CAP_SPAPR_TCE: + case KVM_CAP_SPAPR_TCE_64: case KVM_CAP_PPC_ALLOC_HTAB: case KVM_CAP_PPC_RTAS: case KVM_CAP_PPC_FIXUP_HCALL: @@ -569,6 +581,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PPC_GET_SMMU_INFO: r = 1; break; + case KVM_CAP_SPAPR_MULTITCE: + r = 1; + break; #endif default: r = 0; @@ -1331,13 +1346,34 @@ long kvm_arch_vm_ioctl(struct file *filp, break; } #ifdef CONFIG_PPC_BOOK3S_64 + case KVM_CREATE_SPAPR_TCE_64: { + struct kvm_create_spapr_tce_64 create_tce_64; + + r = -EFAULT; + if (copy_from_user(&create_tce_64, argp, sizeof(create_tce_64))) + goto out; + if (create_tce_64.flags) { + r = -EINVAL; + goto out; + } + r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64); + goto out; + } case KVM_CREATE_SPAPR_TCE: { struct kvm_create_spapr_tce create_tce; + struct kvm_create_spapr_tce_64 create_tce_64; r = -EFAULT; if (copy_from_user(&create_tce, argp, sizeof(create_tce))) goto out; - r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce); + + create_tce_64.liobn = create_tce.liobn; + create_tce_64.page_shift = IOMMU_PAGE_SHIFT_4K; + create_tce_64.offset = 0; + create_tce_64.size = create_tce.window_size >> + IOMMU_PAGE_SHIFT_4K; + create_tce_64.flags = 0; + r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64); goto out; } case KVM_PPC_GET_SMMU_INFO: { diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 83dfd79..de37ff4 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -243,3 +243,11 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr) } #endif /* CONFIG_DEBUG_VM */ +unsigned long vmalloc_to_phys(void *va) +{ + unsigned long pfn = vmalloc_to_pfn(va); + + BUG_ON(!pfn); + return __pa(pfn_to_kaddr(pfn)) + offset_in_page(va); +} +EXPORT_SYMBOL_GPL(vmalloc_to_phys); diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 9f9dfda..3b09ecf 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -493,14 +493,6 @@ static size_t event_to_attr_ct(struct hv_24x7_event_data *event) } } -static unsigned long vmalloc_to_phys(void *v) -{ - struct page *p = vmalloc_to_page(v); - - BUG_ON(!p); - return page_to_phys(p) + offset_in_page(v); -} - /* */ struct event_uniq { struct rb_node node; diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c index eae3265..afdf62f 100644 --- a/arch/powerpc/sysdev/xics/icp-native.c +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -159,6 +159,27 @@ static void icp_native_cause_ipi(int cpu, unsigned long data) icp_native_set_qirr(cpu, IPI_PRIORITY); } +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void icp_native_cause_ipi_rm(int cpu) +{ + /* + * Currently not used to send IPIs to another CPU + * on the same core. Only caller is KVM real mode. + * Need the physical address of the XICS to be + * previously saved in kvm_hstate in the paca. + */ + unsigned long xics_phys; + + /* + * Just like the cause_ipi functions, it is required to + * include a full barrier (out8 includes a sync) before + * causing the IPI. + */ + xics_phys = paca[cpu].kvm_hstate.xics_phys; + out_rm8((u8 *)(xics_phys + XICS_MFRR), IPI_PRIORITY); +} +#endif + /* * Called when an interrupt is received on an off-line CPU to * clear the interrupt, so that the CPU can go back to nap mode. diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 8959ebb..727e7f7 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -229,17 +229,11 @@ struct kvm_s390_itdb { __u8 data[256]; } __packed; -struct kvm_s390_vregs { - __vector128 vrs[32]; - __u8 reserved200[512]; /* for future vector expansion */ -} __packed; - struct sie_page { struct kvm_s390_sie_block sie_block; __u8 reserved200[1024]; /* 0x0200 */ struct kvm_s390_itdb itdb; /* 0x0600 */ - __u8 reserved700[1280]; /* 0x0700 */ - struct kvm_s390_vregs vregs; /* 0x0c00 */ + __u8 reserved700[2304]; /* 0x0700 */ } __packed; struct kvm_vcpu_stat { diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index fe84bd5..347fe5a 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -154,6 +154,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_PFAULT (1UL << 5) #define KVM_SYNC_VRS (1UL << 6) #define KVM_SYNC_RICCB (1UL << 7) +#define KVM_SYNC_FPRS (1UL << 8) /* definition of registers in kvm_run */ struct kvm_sync_regs { __u64 prefix; /* prefix register */ @@ -168,9 +169,12 @@ struct kvm_sync_regs { __u64 pft; /* pfault token [PFAULT] */ __u64 pfs; /* pfault select [PFAULT] */ __u64 pfc; /* pfault compare [PFAULT] */ - __u64 vrs[32][2]; /* vector registers */ + union { + __u64 vrs[32][2]; /* vector registers (KVM_SYNC_VRS) */ + __u64 fprs[16]; /* fp registers (KVM_SYNC_FPRS) */ + }; __u8 reserved[512]; /* for future vector expansion */ - __u32 fpc; /* only valid with vector registers */ + __u32 fpc; /* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */ __u8 padding[52]; /* riccb needs to be 64byte aligned */ __u8 riccb[64]; /* runtime instrumentation controls block */ }; diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index d30db40..66938d2 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -373,7 +373,7 @@ void ipte_unlock(struct kvm_vcpu *vcpu) } static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar, - int write) + enum gacc_mode mode) { union alet alet; struct ale ale; @@ -454,7 +454,7 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, ar_t ar, } } - if (ale.fo == 1 && write) + if (ale.fo == 1 && mode == GACC_STORE) return PGM_PROTECTION; asce->val = aste.asce; @@ -477,25 +477,28 @@ enum { }; static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce, - ar_t ar, int write) + ar_t ar, enum gacc_mode mode) { int rc; - psw_t *psw = &vcpu->arch.sie_block->gpsw; + struct psw_bits psw = psw_bits(vcpu->arch.sie_block->gpsw); struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; struct trans_exc_code_bits *tec_bits; memset(pgm, 0, sizeof(*pgm)); tec_bits = (struct trans_exc_code_bits *)&pgm->trans_exc_code; - tec_bits->fsi = write ? FSI_STORE : FSI_FETCH; - tec_bits->as = psw_bits(*psw).as; + tec_bits->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH; + tec_bits->as = psw.as; - if (!psw_bits(*psw).t) { + if (!psw.t) { asce->val = 0; asce->r = 1; return 0; } - switch (psw_bits(vcpu->arch.sie_block->gpsw).as) { + if (mode == GACC_IFETCH) + psw.as = psw.as == PSW_AS_HOME ? PSW_AS_HOME : PSW_AS_PRIMARY; + + switch (psw.as) { case PSW_AS_PRIMARY: asce->val = vcpu->arch.sie_block->gcr[1]; return 0; @@ -506,7 +509,7 @@ static int get_vcpu_asce(struct kvm_vcpu *vcpu, union asce *asce, asce->val = vcpu->arch.sie_block->gcr[13]; return 0; case PSW_AS_ACCREG: - rc = ar_translation(vcpu, asce, ar, write); + rc = ar_translation(vcpu, asce, ar, mode); switch (rc) { case PGM_ALEN_TRANSLATION: case PGM_ALE_SEQUENCE: @@ -538,7 +541,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) * @gva: guest virtual address * @gpa: points to where guest physical (absolute) address should be stored * @asce: effective asce - * @write: indicates if access is a write access + * @mode: indicates the access mode to be used * * Translate a guest virtual address into a guest absolute address by means * of dynamic address translation as specified by the architecture. @@ -554,7 +557,7 @@ static int deref_table(struct kvm *kvm, unsigned long gpa, unsigned long *val) */ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, unsigned long *gpa, const union asce asce, - int write) + enum gacc_mode mode) { union vaddress vaddr = {.addr = gva}; union raddress raddr = {.addr = gva}; @@ -699,7 +702,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, real_address: raddr.addr = kvm_s390_real_to_abs(vcpu, raddr.addr); absolute_address: - if (write && dat_protection) + if (mode == GACC_STORE && dat_protection) return PGM_PROTECTION; if (kvm_is_error_gpa(vcpu->kvm, raddr.addr)) return PGM_ADDRESSING; @@ -728,7 +731,7 @@ static int low_address_protection_enabled(struct kvm_vcpu *vcpu, static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, unsigned long *pages, unsigned long nr_pages, - const union asce asce, int write) + const union asce asce, enum gacc_mode mode) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; psw_t *psw = &vcpu->arch.sie_block->gpsw; @@ -740,13 +743,13 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, while (nr_pages) { ga = kvm_s390_logical_to_effective(vcpu, ga); tec_bits->addr = ga >> PAGE_SHIFT; - if (write && lap_enabled && is_low_address(ga)) { + if (mode == GACC_STORE && lap_enabled && is_low_address(ga)) { pgm->code = PGM_PROTECTION; return pgm->code; } ga &= PAGE_MASK; if (psw_bits(*psw).t) { - rc = guest_translate(vcpu, ga, pages, asce, write); + rc = guest_translate(vcpu, ga, pages, asce, mode); if (rc < 0) return rc; if (rc == PGM_PROTECTION) @@ -768,7 +771,7 @@ static int guest_page_range(struct kvm_vcpu *vcpu, unsigned long ga, } int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, - unsigned long len, int write) + unsigned long len, enum gacc_mode mode) { psw_t *psw = &vcpu->arch.sie_block->gpsw; unsigned long _len, nr_pages, gpa, idx; @@ -780,7 +783,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, if (!len) return 0; - rc = get_vcpu_asce(vcpu, &asce, ar, write); + rc = get_vcpu_asce(vcpu, &asce, ar, mode); if (rc) return rc; nr_pages = (((ga & ~PAGE_MASK) + len - 1) >> PAGE_SHIFT) + 1; @@ -792,11 +795,11 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, need_ipte_lock = psw_bits(*psw).t && !asce.r; if (need_ipte_lock) ipte_lock(vcpu); - rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, write); + rc = guest_page_range(vcpu, ga, pages, nr_pages, asce, mode); for (idx = 0; idx < nr_pages && !rc; idx++) { gpa = *(pages + idx) + (ga & ~PAGE_MASK); _len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len); - if (write) + if (mode == GACC_STORE) rc = kvm_write_guest(vcpu->kvm, gpa, data, _len); else rc = kvm_read_guest(vcpu->kvm, gpa, data, _len); @@ -812,7 +815,7 @@ int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, } int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, - void *data, unsigned long len, int write) + void *data, unsigned long len, enum gacc_mode mode) { unsigned long _len, gpa; int rc = 0; @@ -820,7 +823,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, while (len && !rc) { gpa = kvm_s390_real_to_abs(vcpu, gra); _len = min(PAGE_SIZE - (gpa & ~PAGE_MASK), len); - if (write) + if (mode) rc = write_guest_abs(vcpu, gpa, data, _len); else rc = read_guest_abs(vcpu, gpa, data, _len); @@ -841,7 +844,7 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, * has to take care of this. */ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, - unsigned long *gpa, int write) + unsigned long *gpa, enum gacc_mode mode) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; psw_t *psw = &vcpu->arch.sie_block->gpsw; @@ -851,19 +854,19 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, gva = kvm_s390_logical_to_effective(vcpu, gva); tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code; - rc = get_vcpu_asce(vcpu, &asce, ar, write); + rc = get_vcpu_asce(vcpu, &asce, ar, mode); tec->addr = gva >> PAGE_SHIFT; if (rc) return rc; if (is_low_address(gva) && low_address_protection_enabled(vcpu, asce)) { - if (write) { + if (mode == GACC_STORE) { rc = pgm->code = PGM_PROTECTION; return rc; } } if (psw_bits(*psw).t && !asce.r) { /* Use DAT? */ - rc = guest_translate(vcpu, gva, gpa, asce, write); + rc = guest_translate(vcpu, gva, gpa, asce, mode); if (rc > 0) { if (rc == PGM_PROTECTION) tec->b61 = 1; @@ -883,7 +886,7 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, * check_gva_range - test a range of guest virtual addresses for accessibility */ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, - unsigned long length, int is_write) + unsigned long length, enum gacc_mode mode) { unsigned long gpa; unsigned long currlen; @@ -892,7 +895,7 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, ipte_lock(vcpu); while (length > 0 && !rc) { currlen = min(length, PAGE_SIZE - (gva % PAGE_SIZE)); - rc = guest_translate_address(vcpu, gva, ar, &gpa, is_write); + rc = guest_translate_address(vcpu, gva, ar, &gpa, mode); gva += currlen; length -= currlen; } diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index ef03726..df0a79d 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -155,16 +155,22 @@ int read_guest_lc(struct kvm_vcpu *vcpu, unsigned long gra, void *data, return kvm_read_guest(vcpu->kvm, gpa, data, len); } +enum gacc_mode { + GACC_FETCH, + GACC_STORE, + GACC_IFETCH, +}; + int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, - ar_t ar, unsigned long *gpa, int write); + ar_t ar, unsigned long *gpa, enum gacc_mode mode); int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, ar_t ar, - unsigned long length, int is_write); + unsigned long length, enum gacc_mode mode); int access_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, - unsigned long len, int write); + unsigned long len, enum gacc_mode mode); int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, - void *data, unsigned long len, int write); + void *data, unsigned long len, enum gacc_mode mode); /** * write_guest - copy data from kernel space to guest space @@ -215,7 +221,7 @@ static inline __must_check int write_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len) { - return access_guest(vcpu, ga, ar, data, len, 1); + return access_guest(vcpu, ga, ar, data, len, GACC_STORE); } /** @@ -235,7 +241,27 @@ static inline __must_check int read_guest(struct kvm_vcpu *vcpu, unsigned long ga, ar_t ar, void *data, unsigned long len) { - return access_guest(vcpu, ga, ar, data, len, 0); + return access_guest(vcpu, ga, ar, data, len, GACC_FETCH); +} + +/** + * read_guest_instr - copy instruction data from guest space to kernel space + * @vcpu: virtual cpu + * @data: destination address in kernel space + * @len: number of bytes to copy + * + * Copy @len bytes from the current psw address (guest space) to @data (kernel + * space). + * + * The behaviour of read_guest_instr is identical to read_guest, except that + * instruction data will be read from primary space when in home-space or + * address-space mode. + */ +static inline __must_check +int read_guest_instr(struct kvm_vcpu *vcpu, void *data, unsigned long len) +{ + return access_guest(vcpu, vcpu->arch.sie_block->gpsw.addr, 0, data, len, + GACC_IFETCH); } /** diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index d53c107..2e6b54e 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -38,17 +38,32 @@ static const intercept_handler_t instruction_handlers[256] = { [0xeb] = kvm_s390_handle_eb, }; -void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc) +u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu) { struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block; + u8 ilen = 0; - /* Use the length of the EXECUTE instruction if necessary */ - if (sie_block->icptstatus & 1) { - ilc = (sie_block->icptstatus >> 4) & 0x6; - if (!ilc) - ilc = 4; + switch (vcpu->arch.sie_block->icptcode) { + case ICPT_INST: + case ICPT_INSTPROGI: + case ICPT_OPEREXC: + case ICPT_PARTEXEC: + case ICPT_IOINST: + /* instruction only stored for these icptcodes */ + ilen = insn_length(vcpu->arch.sie_block->ipa >> 8); + /* Use the length of the EXECUTE instruction if necessary */ + if (sie_block->icptstatus & 1) { + ilen = (sie_block->icptstatus >> 4) & 0x6; + if (!ilen) + ilen = 4; + } + break; + case ICPT_PROGI: + /* bit 1+2 of pgmilc are the ilc, so we directly get ilen */ + ilen = vcpu->arch.sie_block->pgmilc & 0x6; + break; } - sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilc); + return ilen; } static int handle_noop(struct kvm_vcpu *vcpu) @@ -121,11 +136,13 @@ static int handle_instruction(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; } -static void __extract_prog_irq(struct kvm_vcpu *vcpu, - struct kvm_s390_pgm_info *pgm_info) +static int inject_prog_on_prog_intercept(struct kvm_vcpu *vcpu) { - memset(pgm_info, 0, sizeof(struct kvm_s390_pgm_info)); - pgm_info->code = vcpu->arch.sie_block->iprcc; + struct kvm_s390_pgm_info pgm_info = { + .code = vcpu->arch.sie_block->iprcc, + /* the PSW has already been rewound */ + .flags = KVM_S390_PGM_FLAGS_NO_REWIND, + }; switch (vcpu->arch.sie_block->iprcc & ~PGM_PER) { case PGM_AFX_TRANSLATION: @@ -138,7 +155,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu, case PGM_PRIMARY_AUTHORITY: case PGM_SECONDARY_AUTHORITY: case PGM_SPACE_SWITCH: - pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc; + pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc; break; case PGM_ALEN_TRANSLATION: case PGM_ALE_SEQUENCE: @@ -146,7 +163,7 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu, case PGM_ASTE_SEQUENCE: case PGM_ASTE_VALIDITY: case PGM_EXTENDED_AUTHORITY: - pgm_info->exc_access_id = vcpu->arch.sie_block->eai; + pgm_info.exc_access_id = vcpu->arch.sie_block->eai; break; case PGM_ASCE_TYPE: case PGM_PAGE_TRANSLATION: @@ -154,32 +171,33 @@ static void __extract_prog_irq(struct kvm_vcpu *vcpu, case PGM_REGION_SECOND_TRANS: case PGM_REGION_THIRD_TRANS: case PGM_SEGMENT_TRANSLATION: - pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc; - pgm_info->exc_access_id = vcpu->arch.sie_block->eai; - pgm_info->op_access_id = vcpu->arch.sie_block->oai; + pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc; + pgm_info.exc_access_id = vcpu->arch.sie_block->eai; + pgm_info.op_access_id = vcpu->arch.sie_block->oai; break; case PGM_MONITOR: - pgm_info->mon_class_nr = vcpu->arch.sie_block->mcn; - pgm_info->mon_code = vcpu->arch.sie_block->tecmc; + pgm_info.mon_class_nr = vcpu->arch.sie_block->mcn; + pgm_info.mon_code = vcpu->arch.sie_block->tecmc; break; case PGM_VECTOR_PROCESSING: case PGM_DATA: - pgm_info->data_exc_code = vcpu->arch.sie_block->dxc; + pgm_info.data_exc_code = vcpu->arch.sie_block->dxc; break; case PGM_PROTECTION: - pgm_info->trans_exc_code = vcpu->arch.sie_block->tecmc; - pgm_info->exc_access_id = vcpu->arch.sie_block->eai; + pgm_info.trans_exc_code = vcpu->arch.sie_block->tecmc; + pgm_info.exc_access_id = vcpu->arch.sie_block->eai; break; default: break; } if (vcpu->arch.sie_block->iprcc & PGM_PER) { - pgm_info->per_code = vcpu->arch.sie_block->perc; - pgm_info->per_atmid = vcpu->arch.sie_block->peratmid; - pgm_info->per_address = vcpu->arch.sie_block->peraddr; - pgm_info->per_access_id = vcpu->arch.sie_block->peraid; + pgm_info.per_code = vcpu->arch.sie_block->perc; + pgm_info.per_atmid = vcpu->arch.sie_block->peratmid; + pgm_info.per_address = vcpu->arch.sie_block->peraddr; + pgm_info.per_access_id = vcpu->arch.sie_block->peraid; } + return kvm_s390_inject_prog_irq(vcpu, &pgm_info); } /* @@ -208,7 +226,6 @@ static int handle_itdb(struct kvm_vcpu *vcpu) static int handle_prog(struct kvm_vcpu *vcpu) { - struct kvm_s390_pgm_info pgm_info; psw_t psw; int rc; @@ -234,8 +251,7 @@ static int handle_prog(struct kvm_vcpu *vcpu) if (rc) return rc; - __extract_prog_irq(vcpu, &pgm_info); - return kvm_s390_inject_prog_irq(vcpu, &pgm_info); + return inject_prog_on_prog_intercept(vcpu); } /** @@ -302,7 +318,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) /* Make sure that the source is paged-in */ rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg2], - reg2, &srcaddr, 0); + reg2, &srcaddr, GACC_FETCH); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); rc = kvm_arch_fault_in_page(vcpu, srcaddr, 0); @@ -311,14 +327,14 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) /* Make sure that the destination is paged-in */ rc = guest_translate_address(vcpu, vcpu->run->s.regs.gprs[reg1], - reg1, &dstaddr, 1); + reg1, &dstaddr, GACC_STORE); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); rc = kvm_arch_fault_in_page(vcpu, dstaddr, 1); if (rc != 0) return rc; - kvm_s390_rewind_psw(vcpu, 4); + kvm_s390_retry_instr(vcpu); return 0; } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index f88ca72..87e2d1a 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -335,23 +335,6 @@ static void set_intercept_indicators(struct kvm_vcpu *vcpu) set_intercept_indicators_stop(vcpu); } -static u16 get_ilc(struct kvm_vcpu *vcpu) -{ - switch (vcpu->arch.sie_block->icptcode) { - case ICPT_INST: - case ICPT_INSTPROGI: - case ICPT_OPEREXC: - case ICPT_PARTEXEC: - case ICPT_IOINST: - /* last instruction only stored for these icptcodes */ - return insn_length(vcpu->arch.sie_block->ipa >> 8); - case ICPT_PROGI: - return vcpu->arch.sie_block->pgmilc; - default: - return 0; - } -} - static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; @@ -588,7 +571,7 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_pgm_info pgm_info; int rc = 0, nullifying = false; - u16 ilc = get_ilc(vcpu); + u16 ilen; spin_lock(&li->lock); pgm_info = li->irq.pgm; @@ -596,8 +579,9 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) memset(&li->irq.pgm, 0, sizeof(pgm_info)); spin_unlock(&li->lock); - VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilc:%d", - pgm_info.code, ilc); + ilen = pgm_info.flags & KVM_S390_PGM_FLAGS_ILC_MASK; + VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilen:%d", + pgm_info.code, ilen); vcpu->stat.deliver_program_int++; trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, pgm_info.code, 0); @@ -681,10 +665,11 @@ static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) (u8 *) __LC_PER_ACCESS_ID); } - if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST) - kvm_s390_rewind_psw(vcpu, ilc); + if (nullifying && !(pgm_info.flags & KVM_S390_PGM_FLAGS_NO_REWIND)) + kvm_s390_rewind_psw(vcpu, ilen); - rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC); + /* bit 1+2 of the target are the ilc, so we can directly use ilen */ + rc |= put_guest_lc(vcpu, ilen, (u16 *) __LC_PGM_ILC); rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea, (u64 *) __LC_LAST_BREAK); rc |= put_guest_lc(vcpu, pgm_info.code, @@ -1059,8 +1044,16 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, irq->u.pgm.code, 0); + if (!(irq->u.pgm.flags & KVM_S390_PGM_FLAGS_ILC_VALID)) { + /* auto detection if no valid ILC was given */ + irq->u.pgm.flags &= ~KVM_S390_PGM_FLAGS_ILC_MASK; + irq->u.pgm.flags |= kvm_s390_get_ilen(vcpu); + irq->u.pgm.flags |= KVM_S390_PGM_FLAGS_ILC_VALID; + } + if (irq->u.pgm.code == PGM_PER) { li->irq.pgm.code |= PGM_PER; + li->irq.pgm.flags = irq->u.pgm.flags; /* only modify PER related information */ li->irq.pgm.per_address = irq->u.pgm.per_address; li->irq.pgm.per_code = irq->u.pgm.per_code; @@ -1069,6 +1062,7 @@ static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) } else if (!(irq->u.pgm.code & PGM_PER)) { li->irq.pgm.code = (li->irq.pgm.code & PGM_PER) | irq->u.pgm.code; + li->irq.pgm.flags = irq->u.pgm.flags; /* only modify non-PER information */ li->irq.pgm.trans_exc_code = irq->u.pgm.trans_exc_code; li->irq.pgm.mon_code = irq->u.pgm.mon_code; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 4af21c7..28bd5ea 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -274,7 +274,6 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm, unsigned long address; struct gmap *gmap = kvm->arch.gmap; - down_read(&gmap->mm->mmap_sem); /* Loop over all guest pages */ last_gfn = memslot->base_gfn + memslot->npages; for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) { @@ -282,8 +281,10 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm, if (gmap_test_and_clear_dirty(address, gmap)) mark_page_dirty(kvm, cur_gfn); + if (fatal_signal_pending(current)) + return; + cond_resched(); } - up_read(&gmap->mm->mmap_sem); } /* Section: vm related */ @@ -1414,8 +1415,13 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) KVM_SYNC_PFAULT; if (test_kvm_facility(vcpu->kvm, 64)) vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; - if (test_kvm_facility(vcpu->kvm, 129)) + /* fprs can be synchronized via vrs, even if the guest has no vx. With + * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format. + */ + if (MACHINE_HAS_VX) vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; + else + vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS; if (kvm_is_ucontrol(vcpu->kvm)) return __kvm_ucontrol_vcpu_init(vcpu); @@ -1430,10 +1436,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc; vcpu->arch.host_fpregs.regs = current->thread.fpu.regs; - /* Depending on MACHINE_HAS_VX, data stored to vrs either - * has vector register or floating point register format. - */ - current->thread.fpu.regs = vcpu->run->s.regs.vrs; + if (MACHINE_HAS_VX) + current->thread.fpu.regs = vcpu->run->s.regs.vrs; + else + current->thread.fpu.regs = vcpu->run->s.regs.fprs; current->thread.fpu.fpc = vcpu->run->s.regs.fpc; if (test_fp_ctl(current->thread.fpu.fpc)) /* User space provided an invalid FPC, let's clear it */ @@ -2158,8 +2164,10 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu) { - psw_t *psw = &vcpu->arch.sie_block->gpsw; - u8 opcode; + struct kvm_s390_pgm_info pgm_info = { + .code = PGM_ADDRESSING, + }; + u8 opcode, ilen; int rc; VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction"); @@ -2173,12 +2181,21 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu) * to look up the current opcode to get the length of the instruction * to be able to forward the PSW. */ - rc = read_guest(vcpu, psw->addr, 0, &opcode, 1); - if (rc) - return kvm_s390_inject_prog_cond(vcpu, rc); - psw->addr = __rewind_psw(*psw, -insn_length(opcode)); - - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + rc = read_guest_instr(vcpu, &opcode, 1); + ilen = insn_length(opcode); + if (rc < 0) { + return rc; + } else if (rc) { + /* Instruction-Fetching Exceptions - we can't detect the ilen. + * Forward by arbitrary ilc, injection will take care of + * nullification if necessary. + */ + pgm_info = vcpu->arch.pgm; + ilen = 4; + } + pgm_info.flags = ilen | KVM_S390_PGM_FLAGS_ILC_VALID; + kvm_s390_forward_psw(vcpu, ilen); + return kvm_s390_inject_prog_irq(vcpu, &pgm_info); } static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) @@ -2386,7 +2403,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) fprs, 128); } else { rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, - vcpu->run->s.regs.vrs, 128); + vcpu->run->s.regs.fprs, 128); } rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA, vcpu->run->s.regs.gprs, 128); @@ -2605,7 +2622,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, switch (mop->op) { case KVM_S390_MEMOP_LOGICAL_READ: if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { - r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, false); + r = check_gva_range(vcpu, mop->gaddr, mop->ar, + mop->size, GACC_FETCH); break; } r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size); @@ -2616,7 +2634,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, break; case KVM_S390_MEMOP_LOGICAL_WRITE: if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) { - r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size, true); + r = check_gva_range(vcpu, mop->gaddr, mop->ar, + mop->size, GACC_STORE); break; } if (copy_from_user(tmpbuf, uaddr, mop->size)) { diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index df1abad..1c756c7 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -19,6 +19,7 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <asm/facility.h> +#include <asm/processor.h> typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); @@ -212,8 +213,22 @@ int kvm_s390_reinject_io_int(struct kvm *kvm, int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked); /* implemented in intercept.c */ -void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc); +u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu); int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu); +static inline void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilen) +{ + struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block; + + sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilen); +} +static inline void kvm_s390_forward_psw(struct kvm_vcpu *vcpu, int ilen) +{ + kvm_s390_rewind_psw(vcpu, -ilen); +} +static inline void kvm_s390_retry_instr(struct kvm_vcpu *vcpu) +{ + kvm_s390_rewind_psw(vcpu, kvm_s390_get_ilen(vcpu)); +} /* implemented in priv.c */ int is_valid_psw(psw_t *psw); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index ed74e86..add9909 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -173,7 +173,7 @@ static int handle_skey(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - kvm_s390_rewind_psw(vcpu, 4); + kvm_s390_retry_instr(vcpu); VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation"); return 0; } @@ -184,7 +184,7 @@ static int handle_ipte_interlock(struct kvm_vcpu *vcpu) if (psw_bits(vcpu->arch.sie_block->gpsw).p) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu)); - kvm_s390_rewind_psw(vcpu, 4); + kvm_s390_retry_instr(vcpu); VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation"); return 0; } @@ -759,8 +759,8 @@ static int handle_essa(struct kvm_vcpu *vcpu) if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - /* Rewind PSW to repeat the ESSA instruction */ - kvm_s390_rewind_psw(vcpu, 4); + /* Retry the ESSA instruction */ + kvm_s390_retry_instr(vcpu); vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */ cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo); down_read(&gmap->mm->mmap_sem); @@ -981,11 +981,12 @@ static int handle_tprot(struct kvm_vcpu *vcpu) return -EOPNOTSUPP; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) ipte_lock(vcpu); - ret = guest_translate_address(vcpu, address1, ar, &gpa, 1); + ret = guest_translate_address(vcpu, address1, ar, &gpa, GACC_STORE); if (ret == PGM_PROTECTION) { /* Write protected? Try again with read-only... */ cc = 1; - ret = guest_translate_address(vcpu, address1, ar, &gpa, 0); + ret = guest_translate_address(vcpu, address1, ar, &gpa, + GACC_FETCH); } if (ret) { if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 44adbb8..d110dc4 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -32,6 +32,7 @@ #include <asm/mtrr.h> #include <asm/msr-index.h> #include <asm/asm.h> +#include <asm/kvm_page_track.h> #define KVM_MAX_VCPUS 255 #define KVM_SOFT_MAX_VCPUS 160 @@ -214,6 +215,14 @@ struct kvm_mmu_memory_cache { void *objects[KVM_NR_MEM_OBJS]; }; +/* + * the pages used as guest page table on soft mmu are tracked by + * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used + * by indirect shadow page can not be more than 15 bits. + * + * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access, + * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp. + */ union kvm_mmu_page_role { unsigned word; struct { @@ -276,7 +285,7 @@ struct kvm_mmu_page { #endif /* Number of writes since the last time traversal visited this page. */ - int write_flooding_count; + atomic_t write_flooding_count; }; struct kvm_pio_request { @@ -338,12 +347,8 @@ struct kvm_mmu { struct rsvd_bits_validate guest_rsvd_check; - /* - * Bitmap: bit set = last pte in walk - * index[0:1]: level (zero-based) - * index[2]: pte.ps - */ - u8 last_pte_bitmap; + /* Can have large pages at levels 2..last_nonleaf_level-1. */ + u8 last_nonleaf_level; bool nx; @@ -644,12 +649,13 @@ struct kvm_vcpu_arch { }; struct kvm_lpage_info { - int write_count; + int disallow_lpage; }; struct kvm_arch_memory_slot { struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES]; struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; + unsigned short *gfn_track[KVM_PAGE_TRACK_MAX]; }; /* @@ -694,6 +700,8 @@ struct kvm_arch { */ struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; + struct kvm_page_track_notifier_node mmu_sp_tracker; + struct kvm_page_track_notifier_head track_notifier_head; struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; @@ -754,6 +762,8 @@ struct kvm_arch { bool irqchip_split; u8 nr_reserved_ioapic_pins; + + bool disabled_lapic_found; }; struct kvm_vm_stat { @@ -988,6 +998,8 @@ void kvm_mmu_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); void kvm_mmu_setup(struct kvm_vcpu *vcpu); +void kvm_mmu_init_vm(struct kvm *kvm); +void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, u64 dirty_mask, u64 nx_mask, u64 x_mask); @@ -1127,8 +1139,6 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); void kvm_inject_nmi(struct kvm_vcpu *vcpu); -void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes); int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva); void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h new file mode 100644 index 0000000..c2b8d24 --- /dev/null +++ b/arch/x86/include/asm/kvm_page_track.h @@ -0,0 +1,61 @@ +#ifndef _ASM_X86_KVM_PAGE_TRACK_H +#define _ASM_X86_KVM_PAGE_TRACK_H + +enum kvm_page_track_mode { + KVM_PAGE_TRACK_WRITE, + KVM_PAGE_TRACK_MAX, +}; + +/* + * The notifier represented by @kvm_page_track_notifier_node is linked into + * the head which will be notified when guest is triggering the track event. + * + * Write access on the head is protected by kvm->mmu_lock, read access + * is protected by track_srcu. + */ +struct kvm_page_track_notifier_head { + struct srcu_struct track_srcu; + struct hlist_head track_notifier_list; +}; + +struct kvm_page_track_notifier_node { + struct hlist_node node; + + /* + * It is called when guest is writing the write-tracked page + * and write emulation is finished at that time. + * + * @vcpu: the vcpu where the write access happened. + * @gpa: the physical address written by guest. + * @new: the data was written to the address. + * @bytes: the written length. + */ + void (*track_write)(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, + int bytes); +}; + +void kvm_page_track_init(struct kvm *kvm); + +void kvm_page_track_free_memslot(struct kvm_memory_slot *free, + struct kvm_memory_slot *dont); +int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, + unsigned long npages); + +void kvm_slot_page_track_add_page(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn, + enum kvm_page_track_mode mode); +void kvm_slot_page_track_remove_page(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn, + enum kvm_page_track_mode mode); +bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn, + enum kvm_page_track_mode mode); + +void +kvm_page_track_register_notifier(struct kvm *kvm, + struct kvm_page_track_notifier_node *n); +void +kvm_page_track_unregister_notifier(struct kvm *kvm, + struct kvm_page_track_notifier_node *n); +void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, + int bytes); +#endif diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 7956412..9b1a918 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -226,7 +226,9 @@ (~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1)) /* Declare the various hypercall operations. */ -#define HV_X64_HV_NOTIFY_LONG_SPIN_WAIT 0x0008 +#define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008 +#define HVCALL_POST_MESSAGE 0x005c +#define HVCALL_SIGNAL_EVENT 0x005d #define HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE 0x00000001 #define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT 12 diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index a1ff508..464fa47 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -13,9 +13,10 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ - hyperv.o + hyperv.o page_track.o kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o + kvm-intel-y += vmx.o pmu_intel.o kvm-amd-y += svm.o pmu_amd.o diff --git a/arch/x86/kvm/assigned-dev.c b/arch/x86/kvm/assigned-dev.c index 9dc091a..308b859 100644 --- a/arch/x86/kvm/assigned-dev.c +++ b/arch/x86/kvm/assigned-dev.c @@ -51,11 +51,9 @@ struct kvm_assigned_dev_kernel { static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head, int assigned_dev_id) { - struct list_head *ptr; struct kvm_assigned_dev_kernel *match; - list_for_each(ptr, head) { - match = list_entry(ptr, struct kvm_assigned_dev_kernel, list); + list_for_each_entry(match, head, list) { if (match->assigned_dev_id == assigned_dev_id) return match; } @@ -373,14 +371,10 @@ static void kvm_free_assigned_device(struct kvm *kvm, void kvm_free_all_assigned_devices(struct kvm *kvm) { - struct list_head *ptr, *ptr2; - struct kvm_assigned_dev_kernel *assigned_dev; - - list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) { - assigned_dev = list_entry(ptr, - struct kvm_assigned_dev_kernel, - list); + struct kvm_assigned_dev_kernel *assigned_dev, *tmp; + list_for_each_entry_safe(assigned_dev, tmp, + &kvm->arch.assigned_dev_head, list) { kvm_free_assigned_device(kvm, assigned_dev); } } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index c58ba67..5ff3485 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1043,6 +1043,27 @@ bool kvm_hv_hypercall_enabled(struct kvm *kvm) return kvm->arch.hyperv.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE; } +static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) +{ + bool longmode; + + longmode = is_64_bit_mode(vcpu); + if (longmode) + kvm_register_write(vcpu, VCPU_REGS_RAX, result); + else { + kvm_register_write(vcpu, VCPU_REGS_RDX, result >> 32); + kvm_register_write(vcpu, VCPU_REGS_RAX, result & 0xffffffff); + } +} + +static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + + kvm_hv_hypercall_set_result(vcpu, run->hyperv.u.hcall.result); + return 1; +} + int kvm_hv_hypercall(struct kvm_vcpu *vcpu) { u64 param, ingpa, outgpa, ret; @@ -1055,7 +1076,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) */ if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); - return 0; + return 1; } longmode = is_64_bit_mode(vcpu); @@ -1083,22 +1104,33 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); + /* Hypercall continuation is not supported yet */ + if (rep_cnt || rep_idx) { + res = HV_STATUS_INVALID_HYPERCALL_CODE; + goto set_result; + } + switch (code) { - case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT: + case HVCALL_NOTIFY_LONG_SPIN_WAIT: kvm_vcpu_on_spin(vcpu); break; + case HVCALL_POST_MESSAGE: + case HVCALL_SIGNAL_EVENT: + vcpu->run->exit_reason = KVM_EXIT_HYPERV; + vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; + vcpu->run->hyperv.u.hcall.input = param; + vcpu->run->hyperv.u.hcall.params[0] = ingpa; + vcpu->run->hyperv.u.hcall.params[1] = outgpa; + vcpu->arch.complete_userspace_io = + kvm_hv_hypercall_complete_userspace; + return 0; default: res = HV_STATUS_INVALID_HYPERCALL_CODE; break; } +set_result: 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); - } - + kvm_hv_hypercall_set_result(vcpu, ret); return 1; } diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index b0ea42b..a4bf5b4 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -51,32 +51,9 @@ #define RW_STATE_WORD0 3 #define RW_STATE_WORD1 4 -/* Compute with 96 bit intermediate result: (a*b)/c */ -static u64 muldiv64(u64 a, u32 b, u32 c) +static void pit_set_gate(struct kvm_pit *pit, int channel, u32 val) { - union { - u64 ll; - struct { - u32 low, high; - } l; - } u, res; - u64 rl, rh; - - u.ll = a; - rl = (u64)u.l.low * (u64)b; - rh = (u64)u.l.high * (u64)b; - rh += (rl >> 32); - res.l.high = div64_u64(rh, c); - res.l.low = div64_u64(((mod_64(rh, c) << 32) + (rl & 0xffffffff)), c); - return res.ll; -} - -static void pit_set_gate(struct kvm *kvm, int channel, u32 val) -{ - struct kvm_kpit_channel_state *c = - &kvm->arch.vpit->pit_state.channels[channel]; - - WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); + struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel]; switch (c->mode) { default: @@ -97,18 +74,16 @@ static void pit_set_gate(struct kvm *kvm, int channel, u32 val) c->gate = val; } -static int pit_get_gate(struct kvm *kvm, int channel) +static int pit_get_gate(struct kvm_pit *pit, int channel) { - WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); - - return kvm->arch.vpit->pit_state.channels[channel].gate; + return pit->pit_state.channels[channel].gate; } -static s64 __kpit_elapsed(struct kvm *kvm) +static s64 __kpit_elapsed(struct kvm_pit *pit) { s64 elapsed; ktime_t remaining; - struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state; + struct kvm_kpit_state *ps = &pit->pit_state; if (!ps->period) return 0; @@ -128,26 +103,23 @@ static s64 __kpit_elapsed(struct kvm *kvm) return elapsed; } -static s64 kpit_elapsed(struct kvm *kvm, struct kvm_kpit_channel_state *c, +static s64 kpit_elapsed(struct kvm_pit *pit, struct kvm_kpit_channel_state *c, int channel) { if (channel == 0) - return __kpit_elapsed(kvm); + return __kpit_elapsed(pit); return ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time)); } -static int pit_get_count(struct kvm *kvm, int channel) +static int pit_get_count(struct kvm_pit *pit, int channel) { - struct kvm_kpit_channel_state *c = - &kvm->arch.vpit->pit_state.channels[channel]; + struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel]; s64 d, t; int counter; - WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); - - t = kpit_elapsed(kvm, c, channel); - d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC); + t = kpit_elapsed(pit, c, channel); + d = mul_u64_u32_div(t, KVM_PIT_FREQ, NSEC_PER_SEC); switch (c->mode) { case 0: @@ -167,17 +139,14 @@ static int pit_get_count(struct kvm *kvm, int channel) return counter; } -static int pit_get_out(struct kvm *kvm, int channel) +static int pit_get_out(struct kvm_pit *pit, int channel) { - struct kvm_kpit_channel_state *c = - &kvm->arch.vpit->pit_state.channels[channel]; + struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel]; s64 d, t; int out; - WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); - - t = kpit_elapsed(kvm, c, channel); - d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC); + t = kpit_elapsed(pit, c, channel); + d = mul_u64_u32_div(t, KVM_PIT_FREQ, NSEC_PER_SEC); switch (c->mode) { default: @@ -202,29 +171,23 @@ static int pit_get_out(struct kvm *kvm, int channel) return out; } -static void pit_latch_count(struct kvm *kvm, int channel) +static void pit_latch_count(struct kvm_pit *pit, int channel) { - struct kvm_kpit_channel_state *c = - &kvm->arch.vpit->pit_state.channels[channel]; - - WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); + struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel]; if (!c->count_latched) { - c->latched_count = pit_get_count(kvm, channel); + c->latched_count = pit_get_count(pit, channel); c->count_latched = c->rw_mode; } } -static void pit_latch_status(struct kvm *kvm, int channel) +static void pit_latch_status(struct kvm_pit *pit, int channel) { - struct kvm_kpit_channel_state *c = - &kvm->arch.vpit->pit_state.channels[channel]; - - WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock)); + struct kvm_kpit_channel_state *c = &pit->pit_state.channels[channel]; if (!c->status_latched) { /* TODO: Return NULL COUNT (bit 6). */ - c->status = ((pit_get_out(kvm, channel) << 7) | + c->status = ((pit_get_out(pit, channel) << 7) | (c->rw_mode << 4) | (c->mode << 1) | c->bcd); @@ -232,26 +195,24 @@ static void pit_latch_status(struct kvm *kvm, int channel) } } +static inline struct kvm_pit *pit_state_to_pit(struct kvm_kpit_state *ps) +{ + return container_of(ps, struct kvm_pit, pit_state); +} + static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian) { struct kvm_kpit_state *ps = container_of(kian, struct kvm_kpit_state, irq_ack_notifier); - int value; - - spin_lock(&ps->inject_lock); - value = atomic_dec_return(&ps->pending); - if (value < 0) - /* spurious acks can be generated if, for example, the - * PIC is being reset. Handle it gracefully here - */ - atomic_inc(&ps->pending); - else if (value > 0) - /* in this case, we had multiple outstanding pit interrupts - * that we needed to inject. Reinject - */ - queue_kthread_work(&ps->pit->worker, &ps->pit->expired); - ps->irq_ack = 1; - spin_unlock(&ps->inject_lock); + struct kvm_pit *pit = pit_state_to_pit(ps); + + atomic_set(&ps->irq_ack, 1); + /* irq_ack should be set before pending is read. Order accesses with + * inc(pending) in pit_timer_fn and xchg(irq_ack, 0) in pit_do_work. + */ + smp_mb(); + if (atomic_dec_if_positive(&ps->pending) > 0) + queue_kthread_work(&pit->worker, &pit->expired); } void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) @@ -282,45 +243,36 @@ static void pit_do_work(struct kthread_work *work) struct kvm_vcpu *vcpu; int i; struct kvm_kpit_state *ps = &pit->pit_state; - int inject = 0; - /* Try to inject pending interrupts when - * last one has been acked. + if (atomic_read(&ps->reinject) && !atomic_xchg(&ps->irq_ack, 0)) + return; + + kvm_set_irq(kvm, pit->irq_source_id, 0, 1, false); + kvm_set_irq(kvm, pit->irq_source_id, 0, 0, false); + + /* + * Provides NMI watchdog support via Virtual Wire mode. + * The route is: PIT -> LVT0 in NMI mode. + * + * Note: Our Virtual Wire implementation does not follow + * the MP specification. We propagate a PIT interrupt to all + * VCPUs and only when LVT0 is in NMI mode. The interrupt can + * also be simultaneously delivered through PIC and IOAPIC. */ - spin_lock(&ps->inject_lock); - if (ps->irq_ack) { - ps->irq_ack = 0; - inject = 1; - } - spin_unlock(&ps->inject_lock); - if (inject) { - kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1, false); - kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0, false); - - /* - * Provides NMI watchdog support via Virtual Wire mode. - * The route is: PIT -> PIC -> LVT0 in NMI mode. - * - * Note: Our Virtual Wire implementation is simplified, only - * propagating PIT interrupts to all VCPUs when they have set - * LVT0 to NMI delivery. Other PIC interrupts are just sent to - * VCPU0, and only if its LVT0 is in EXTINT mode. - */ - if (atomic_read(&kvm->arch.vapics_in_nmi_mode) > 0) - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_apic_nmi_wd_deliver(vcpu); - } + if (atomic_read(&kvm->arch.vapics_in_nmi_mode) > 0) + kvm_for_each_vcpu(i, vcpu, kvm) + kvm_apic_nmi_wd_deliver(vcpu); } static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) { struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer); - struct kvm_pit *pt = ps->kvm->arch.vpit; + struct kvm_pit *pt = pit_state_to_pit(ps); - if (ps->reinject || !atomic_read(&ps->pending)) { + if (atomic_read(&ps->reinject)) atomic_inc(&ps->pending); - queue_kthread_work(&pt->worker, &pt->expired); - } + + queue_kthread_work(&pt->worker, &pt->expired); if (ps->is_periodic) { hrtimer_add_expires_ns(&ps->timer, ps->period); @@ -329,30 +281,54 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) return HRTIMER_NORESTART; } -static void create_pit_timer(struct kvm *kvm, u32 val, int is_period) +static inline void kvm_pit_reset_reinject(struct kvm_pit *pit) { - struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state; + atomic_set(&pit->pit_state.pending, 0); + atomic_set(&pit->pit_state.irq_ack, 1); +} + +void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject) +{ + struct kvm_kpit_state *ps = &pit->pit_state; + struct kvm *kvm = pit->kvm; + + if (atomic_read(&ps->reinject) == reinject) + return; + + if (reinject) { + /* The initial state is preserved while ps->reinject == 0. */ + kvm_pit_reset_reinject(pit); + kvm_register_irq_ack_notifier(kvm, &ps->irq_ack_notifier); + kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier); + } else { + kvm_unregister_irq_ack_notifier(kvm, &ps->irq_ack_notifier); + kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier); + } + + atomic_set(&ps->reinject, reinject); +} + +static void create_pit_timer(struct kvm_pit *pit, u32 val, int is_period) +{ + struct kvm_kpit_state *ps = &pit->pit_state; + struct kvm *kvm = pit->kvm; s64 interval; if (!ioapic_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY) return; - interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ); + interval = mul_u64_u32_div(val, NSEC_PER_SEC, KVM_PIT_FREQ); pr_debug("create pit timer, interval is %llu nsec\n", interval); /* TODO The new value only affected after the retriggered */ hrtimer_cancel(&ps->timer); - flush_kthread_work(&ps->pit->expired); + flush_kthread_work(&pit->expired); ps->period = interval; ps->is_periodic = is_period; - ps->timer.function = pit_timer_fn; - ps->kvm = ps->pit->kvm; - - atomic_set(&ps->pending, 0); - ps->irq_ack = 1; + kvm_pit_reset_reinject(pit); /* * Do not allow the guest to program periodic timers with small @@ -375,11 +351,9 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period) HRTIMER_MODE_ABS); } -static void pit_load_count(struct kvm *kvm, int channel, u32 val) +static void pit_load_count(struct kvm_pit *pit, int channel, u32 val) { - struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state; - - WARN_ON(!mutex_is_locked(&ps->lock)); + struct kvm_kpit_state *ps = &pit->pit_state; pr_debug("load_count val is %d, channel is %d\n", val, channel); @@ -404,29 +378,33 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val) case 1: /* FIXME: enhance mode 4 precision */ case 4: - create_pit_timer(kvm, val, 0); + create_pit_timer(pit, val, 0); break; case 2: case 3: - create_pit_timer(kvm, val, 1); + create_pit_timer(pit, val, 1); break; default: - destroy_pit_timer(kvm->arch.vpit); + destroy_pit_timer(pit); } } -void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_start) +void kvm_pit_load_count(struct kvm_pit *pit, int channel, u32 val, + int hpet_legacy_start) { u8 saved_mode; + + WARN_ON_ONCE(!mutex_is_locked(&pit->pit_state.lock)); + if (hpet_legacy_start) { /* save existing mode for later reenablement */ WARN_ON(channel != 0); - saved_mode = kvm->arch.vpit->pit_state.channels[0].mode; - kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */ - pit_load_count(kvm, channel, val); - kvm->arch.vpit->pit_state.channels[0].mode = saved_mode; + saved_mode = pit->pit_state.channels[0].mode; + pit->pit_state.channels[0].mode = 0xff; /* disable timer */ + pit_load_count(pit, channel, val); + pit->pit_state.channels[0].mode = saved_mode; } else { - pit_load_count(kvm, channel, val); + pit_load_count(pit, channel, val); } } @@ -452,7 +430,6 @@ static int pit_ioport_write(struct kvm_vcpu *vcpu, { struct kvm_pit *pit = dev_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; - struct kvm *kvm = pit->kvm; int channel, access; struct kvm_kpit_channel_state *s; u32 val = *(u32 *) data; @@ -476,9 +453,9 @@ static int pit_ioport_write(struct kvm_vcpu *vcpu, s = &pit_state->channels[channel]; if (val & (2 << channel)) { if (!(val & 0x20)) - pit_latch_count(kvm, channel); + pit_latch_count(pit, channel); if (!(val & 0x10)) - pit_latch_status(kvm, channel); + pit_latch_status(pit, channel); } } } else { @@ -486,7 +463,7 @@ static int pit_ioport_write(struct kvm_vcpu *vcpu, s = &pit_state->channels[channel]; access = (val >> 4) & KVM_PIT_CHANNEL_MASK; if (access == 0) { - pit_latch_count(kvm, channel); + pit_latch_count(pit, channel); } else { s->rw_mode = access; s->read_state = access; @@ -503,17 +480,17 @@ static int pit_ioport_write(struct kvm_vcpu *vcpu, switch (s->write_state) { default: case RW_STATE_LSB: - pit_load_count(kvm, addr, val); + pit_load_count(pit, addr, val); break; case RW_STATE_MSB: - pit_load_count(kvm, addr, val << 8); + pit_load_count(pit, addr, val << 8); break; case RW_STATE_WORD0: s->write_latch = val; s->write_state = RW_STATE_WORD1; break; case RW_STATE_WORD1: - pit_load_count(kvm, addr, s->write_latch | (val << 8)); + pit_load_count(pit, addr, s->write_latch | (val << 8)); s->write_state = RW_STATE_WORD0; break; } @@ -529,7 +506,6 @@ static int pit_ioport_read(struct kvm_vcpu *vcpu, { struct kvm_pit *pit = dev_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; - struct kvm *kvm = pit->kvm; int ret, count; struct kvm_kpit_channel_state *s; if (!pit_in_range(addr)) @@ -566,20 +542,20 @@ static int pit_ioport_read(struct kvm_vcpu *vcpu, switch (s->read_state) { default: case RW_STATE_LSB: - count = pit_get_count(kvm, addr); + count = pit_get_count(pit, addr); ret = count & 0xff; break; case RW_STATE_MSB: - count = pit_get_count(kvm, addr); + count = pit_get_count(pit, addr); ret = (count >> 8) & 0xff; break; case RW_STATE_WORD0: - count = pit_get_count(kvm, addr); + count = pit_get_count(pit, addr); ret = count & 0xff; s->read_state = RW_STATE_WORD1; break; case RW_STATE_WORD1: - count = pit_get_count(kvm, addr); + count = pit_get_count(pit, addr); ret = (count >> 8) & 0xff; s->read_state = RW_STATE_WORD0; break; @@ -600,14 +576,13 @@ static int speaker_ioport_write(struct kvm_vcpu *vcpu, { struct kvm_pit *pit = speaker_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; - struct kvm *kvm = pit->kvm; u32 val = *(u32 *) data; if (addr != KVM_SPEAKER_BASE_ADDRESS) return -EOPNOTSUPP; mutex_lock(&pit_state->lock); pit_state->speaker_data_on = (val >> 1) & 1; - pit_set_gate(kvm, 2, val & 1); + pit_set_gate(pit, 2, val & 1); mutex_unlock(&pit_state->lock); return 0; } @@ -618,7 +593,6 @@ static int speaker_ioport_read(struct kvm_vcpu *vcpu, { struct kvm_pit *pit = speaker_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; - struct kvm *kvm = pit->kvm; unsigned int refresh_clock; int ret; if (addr != KVM_SPEAKER_BASE_ADDRESS) @@ -628,8 +602,8 @@ static int speaker_ioport_read(struct kvm_vcpu *vcpu, refresh_clock = ((unsigned int)ktime_to_ns(ktime_get()) >> 14) & 1; mutex_lock(&pit_state->lock); - ret = ((pit_state->speaker_data_on << 1) | pit_get_gate(kvm, 2) | - (pit_get_out(kvm, 2) << 5) | (refresh_clock << 4)); + ret = ((pit_state->speaker_data_on << 1) | pit_get_gate(pit, 2) | + (pit_get_out(pit, 2) << 5) | (refresh_clock << 4)); if (len > sizeof(ret)) len = sizeof(ret); memcpy(data, (char *)&ret, len); @@ -637,33 +611,28 @@ static int speaker_ioport_read(struct kvm_vcpu *vcpu, return 0; } -void kvm_pit_reset(struct kvm_pit *pit) +static void kvm_pit_reset(struct kvm_pit *pit) { int i; struct kvm_kpit_channel_state *c; - mutex_lock(&pit->pit_state.lock); pit->pit_state.flags = 0; for (i = 0; i < 3; i++) { c = &pit->pit_state.channels[i]; c->mode = 0xff; c->gate = (i != 2); - pit_load_count(pit->kvm, i, 0); + pit_load_count(pit, i, 0); } - mutex_unlock(&pit->pit_state.lock); - atomic_set(&pit->pit_state.pending, 0); - pit->pit_state.irq_ack = 1; + kvm_pit_reset_reinject(pit); } static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask) { struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier); - if (!mask) { - atomic_set(&pit->pit_state.pending, 0); - pit->pit_state.irq_ack = 1; - } + if (!mask) + kvm_pit_reset_reinject(pit); } static const struct kvm_io_device_ops pit_dev_ops = { @@ -690,14 +659,10 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) return NULL; pit->irq_source_id = kvm_request_irq_source_id(kvm); - if (pit->irq_source_id < 0) { - kfree(pit); - return NULL; - } + if (pit->irq_source_id < 0) + goto fail_request; mutex_init(&pit->pit_state.lock); - mutex_lock(&pit->pit_state.lock); - spin_lock_init(&pit->pit_state.inject_lock); pid = get_pid(task_tgid(current)); pid_nr = pid_vnr(pid); @@ -706,36 +671,30 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) init_kthread_worker(&pit->worker); pit->worker_task = kthread_run(kthread_worker_fn, &pit->worker, "kvm-pit/%d", pid_nr); - if (IS_ERR(pit->worker_task)) { - mutex_unlock(&pit->pit_state.lock); - kvm_free_irq_source_id(kvm, pit->irq_source_id); - kfree(pit); - return NULL; - } + if (IS_ERR(pit->worker_task)) + goto fail_kthread; + init_kthread_work(&pit->expired, pit_do_work); - kvm->arch.vpit = pit; pit->kvm = kvm; pit_state = &pit->pit_state; - pit_state->pit = pit; hrtimer_init(&pit_state->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + pit_state->timer.function = pit_timer_fn; + pit_state->irq_ack_notifier.gsi = 0; pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq; - kvm_register_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier); - pit_state->reinject = true; - mutex_unlock(&pit->pit_state.lock); + pit->mask_notifier.func = pit_mask_notifer; kvm_pit_reset(pit); - pit->mask_notifier.func = pit_mask_notifer; - kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier); + kvm_pit_set_reinject(pit, true); kvm_iodevice_init(&pit->dev, &pit_dev_ops); ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, KVM_PIT_BASE_ADDRESS, KVM_PIT_MEM_LENGTH, &pit->dev); if (ret < 0) - goto fail; + goto fail_register_pit; if (flags & KVM_PIT_SPEAKER_DUMMY) { kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops); @@ -743,42 +702,35 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) KVM_SPEAKER_BASE_ADDRESS, 4, &pit->speaker_dev); if (ret < 0) - goto fail_unregister; + goto fail_register_speaker; } return pit; -fail_unregister: +fail_register_speaker: kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev); - -fail: - kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier); - kvm_unregister_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier); - kvm_free_irq_source_id(kvm, pit->irq_source_id); +fail_register_pit: + kvm_pit_set_reinject(pit, false); kthread_stop(pit->worker_task); +fail_kthread: + kvm_free_irq_source_id(kvm, pit->irq_source_id); +fail_request: kfree(pit); return NULL; } void kvm_free_pit(struct kvm *kvm) { - struct hrtimer *timer; - - if (kvm->arch.vpit) { - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &kvm->arch.vpit->dev); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &kvm->arch.vpit->speaker_dev); - kvm_unregister_irq_mask_notifier(kvm, 0, - &kvm->arch.vpit->mask_notifier); - kvm_unregister_irq_ack_notifier(kvm, - &kvm->arch.vpit->pit_state.irq_ack_notifier); - mutex_lock(&kvm->arch.vpit->pit_state.lock); - timer = &kvm->arch.vpit->pit_state.timer; - hrtimer_cancel(timer); - flush_kthread_work(&kvm->arch.vpit->expired); - kthread_stop(kvm->arch.vpit->worker_task); - kvm_free_irq_source_id(kvm, kvm->arch.vpit->irq_source_id); - mutex_unlock(&kvm->arch.vpit->pit_state.lock); - kfree(kvm->arch.vpit); + struct kvm_pit *pit = kvm->arch.vpit; + + if (pit) { + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->speaker_dev); + kvm_pit_set_reinject(pit, false); + hrtimer_cancel(&pit->pit_state.timer); + flush_kthread_work(&pit->expired); + kthread_stop(pit->worker_task); + kvm_free_irq_source_id(kvm, pit->irq_source_id); + kfree(pit); } } diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index c84990b..2f5af07 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -22,19 +22,18 @@ struct kvm_kpit_channel_state { }; struct kvm_kpit_state { + /* All members before "struct mutex lock" are protected by the lock. */ struct kvm_kpit_channel_state channels[3]; u32 flags; bool is_periodic; s64 period; /* unit: ns */ struct hrtimer timer; - atomic_t pending; /* accumulated triggered timers */ - bool reinject; - struct kvm *kvm; u32 speaker_data_on; + struct mutex lock; - struct kvm_pit *pit; - spinlock_t inject_lock; - unsigned long irq_ack; + atomic_t reinject; + atomic_t pending; /* accumulated triggered timers */ + atomic_t irq_ack; struct kvm_irq_ack_notifier irq_ack_notifier; }; @@ -57,9 +56,11 @@ struct kvm_pit { #define KVM_MAX_PIT_INTR_INTERVAL HZ / 100 #define KVM_PIT_CHANNEL_MASK 0x3 -void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_start); struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags); void kvm_free_pit(struct kvm *kvm); -void kvm_pit_reset(struct kvm_pit *pit); + +void kvm_pit_load_count(struct kvm_pit *pit, int channel, u32 val, + int hpet_legacy_start); +void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject); #endif diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 1facfd6..9db47090 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -94,7 +94,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) { ioapic->rtc_status.pending_eoi = 0; - bitmap_zero(ioapic->rtc_status.dest_map, KVM_MAX_VCPUS); + bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPUS); } static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic); @@ -117,16 +117,16 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) return; new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector); - old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map); + old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map); if (new_val == old_val) return; if (new_val) { - __set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map); + __set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map); ioapic->rtc_status.pending_eoi++; } else { - __clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map); + __clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map); ioapic->rtc_status.pending_eoi--; rtc_status_pending_eoi_check_valid(ioapic); } @@ -156,7 +156,8 @@ static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic) static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu) { - if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map)) { + if (test_and_clear_bit(vcpu->vcpu_id, + ioapic->rtc_status.dest_map.map)) { --ioapic->rtc_status.pending_eoi; rtc_status_pending_eoi_check_valid(ioapic); } @@ -236,10 +237,17 @@ static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr) void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors) { struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; + struct dest_map *dest_map = &ioapic->rtc_status.dest_map; union kvm_ioapic_redirect_entry *e; int index; spin_lock(&ioapic->lock); + + /* Make sure we see any missing RTC EOI */ + if (test_bit(vcpu->vcpu_id, dest_map->map)) + __set_bit(dest_map->vectors[vcpu->vcpu_id], + ioapic_handled_vectors); + for (index = 0; index < IOAPIC_NUM_PINS; index++) { e = &ioapic->redirtbl[index]; if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG || @@ -346,7 +354,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) */ BUG_ON(ioapic->rtc_status.pending_eoi != 0); ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, - ioapic->rtc_status.dest_map); + &ioapic->rtc_status.dest_map); ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret); } else ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL); @@ -407,8 +415,14 @@ static void kvm_ioapic_eoi_inject_work(struct work_struct *work) static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, struct kvm_ioapic *ioapic, int vector, int trigger_mode) { - int i; + struct dest_map *dest_map = &ioapic->rtc_status.dest_map; struct kvm_lapic *apic = vcpu->arch.apic; + int i; + + /* RTC special handling */ + if (test_bit(vcpu->vcpu_id, dest_map->map) && + vector == dest_map->vectors[vcpu->vcpu_id]) + rtc_irq_eoi(ioapic, vcpu); for (i = 0; i < IOAPIC_NUM_PINS; i++) { union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i]; @@ -416,8 +430,6 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, if (ent->fields.vector != vector) continue; - if (i == RTC_GSI) - rtc_irq_eoi(ioapic, vcpu); /* * We are dropping lock while calling ack notifiers because ack * notifier callbacks for assigned devices call into IOAPIC diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 2d16dc2..7d2692a 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -40,9 +40,21 @@ struct kvm_vcpu; #define RTC_GSI -1U #endif +struct dest_map { + /* vcpu bitmap where IRQ has been sent */ + DECLARE_BITMAP(map, KVM_MAX_VCPUS); + + /* + * Vector sent to a given vcpu, only valid when + * the vcpu's bit in map is set + */ + u8 vectors[KVM_MAX_VCPUS]; +}; + + struct rtc_status { int pending_eoi; - DECLARE_BITMAP(dest_map, KVM_MAX_VCPUS); + struct dest_map dest_map; }; union kvm_ioapic_redirect_entry { @@ -118,7 +130,8 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, int level, bool line_status); void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id); int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, unsigned long *dest_map); + struct kvm_lapic_irq *irq, + struct dest_map *dest_map); int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 3982b47..95fcc7b 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -33,7 +33,10 @@ */ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - return apic_has_pending_timer(vcpu); + if (lapic_in_kernel(vcpu)) + return apic_has_pending_timer(vcpu); + + return 0; } EXPORT_SYMBOL(kvm_cpu_has_pending_timer); @@ -137,8 +140,8 @@ EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) { - kvm_inject_apic_timer_irqs(vcpu); - /* TODO: PIT, RTC etc. */ + if (lapic_in_kernel(vcpu)) + kvm_inject_apic_timer_irqs(vcpu); } EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs); diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index ae5c78f..61ebdc1 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -109,14 +109,6 @@ static inline int irqchip_in_kernel(struct kvm *kvm) return ret; } -static inline int lapic_in_kernel(struct kvm_vcpu *vcpu) -{ - /* Same as irqchip_in_kernel(vcpu->kvm), but with less - * pointer chasing and no unnecessary memory barriers. - */ - return vcpu->arch.apic != NULL; -} - void kvm_pic_reset(struct kvm_kpic_state *s); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 8fc89ef..54ead79 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -34,6 +34,7 @@ #include "lapic.h" #include "hyperv.h" +#include "x86.h" static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, @@ -53,10 +54,12 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, } int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, unsigned long *dest_map) + struct kvm_lapic_irq *irq, struct dest_map *dest_map) { int i, r = -1; struct kvm_vcpu *vcpu, *lowest = NULL; + unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + unsigned int dest_vcpus = 0; if (irq->dest_mode == 0 && irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) { @@ -67,6 +70,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) return r; + memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap)); + kvm_for_each_vcpu(i, vcpu, kvm) { if (!kvm_apic_present(vcpu)) continue; @@ -80,13 +85,25 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, r = 0; r += kvm_apic_set_irq(vcpu, irq, dest_map); } else if (kvm_lapic_enabled(vcpu)) { - if (!lowest) - lowest = vcpu; - else if (kvm_apic_compare_prio(vcpu, lowest) < 0) - lowest = vcpu; + if (!kvm_vector_hashing_enabled()) { + if (!lowest) + lowest = vcpu; + else if (kvm_apic_compare_prio(vcpu, lowest) < 0) + lowest = vcpu; + } else { + __set_bit(i, dest_vcpu_bitmap); + dest_vcpus++; + } } } + if (dest_vcpus != 0) { + int idx = kvm_vector_to_index(irq->vector, dest_vcpus, + dest_vcpu_bitmap, KVM_MAX_VCPUS); + + lowest = kvm_get_vcpu(kvm, idx); + } + if (lowest) r = kvm_apic_set_irq(lowest, irq, dest_map); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 36591fa..d9ae1ce 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -281,7 +281,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu) struct kvm_cpuid_entry2 *feat; u32 v = APIC_VERSION; - if (!kvm_vcpu_has_lapic(vcpu)) + if (!lapic_in_kernel(vcpu)) return; feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0); @@ -475,26 +475,20 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) { - int highest_irr; - /* This may race with setting of irr in __apic_accept_irq() and * value returned may be wrong, but kvm_vcpu_kick() in __apic_accept_irq * will cause vmexit immediately and the value will be recalculated * on the next vmentry. */ - if (!kvm_vcpu_has_lapic(vcpu)) - return 0; - highest_irr = apic_find_highest_irr(vcpu->arch.apic); - - return highest_irr; + return apic_find_highest_irr(vcpu->arch.apic); } static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, int vector, int level, int trig_mode, - unsigned long *dest_map); + struct dest_map *dest_map); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, - unsigned long *dest_map) + struct dest_map *dest_map) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -675,8 +669,33 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, } } +int kvm_vector_to_index(u32 vector, u32 dest_vcpus, + const unsigned long *bitmap, u32 bitmap_size) +{ + u32 mod; + int i, idx = -1; + + mod = vector % dest_vcpus; + + for (i = 0; i <= mod; i++) { + idx = find_next_bit(bitmap, bitmap_size, idx + 1); + BUG_ON(idx == bitmap_size); + } + + return idx; +} + +static void kvm_apic_disabled_lapic_found(struct kvm *kvm) +{ + if (!kvm->arch.disabled_lapic_found) { + kvm->arch.disabled_lapic_found = true; + printk(KERN_INFO + "Disabled LAPIC found during irq injection\n"); + } +} + bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map) + struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map) { struct kvm_apic_map *map; unsigned long bitmap = 1; @@ -727,21 +746,42 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, dst = map->logical_map[cid]; - if (kvm_lowest_prio_delivery(irq)) { + if (!kvm_lowest_prio_delivery(irq)) + goto set_irq; + + if (!kvm_vector_hashing_enabled()) { int l = -1; for_each_set_bit(i, &bitmap, 16) { if (!dst[i]) continue; if (l < 0) l = i; - else if (kvm_apic_compare_prio(dst[i]->vcpu, dst[l]->vcpu) < 0) + else if (kvm_apic_compare_prio(dst[i]->vcpu, + dst[l]->vcpu) < 0) l = i; } - bitmap = (l >= 0) ? 1 << l : 0; + } else { + int idx; + unsigned int dest_vcpus; + + dest_vcpus = hweight16(bitmap); + if (dest_vcpus == 0) + goto out; + + idx = kvm_vector_to_index(irq->vector, + dest_vcpus, &bitmap, 16); + + if (!dst[idx]) { + kvm_apic_disabled_lapic_found(kvm); + goto out; + } + + bitmap = (idx >= 0) ? 1 << idx : 0; } } +set_irq: for_each_set_bit(i, &bitmap, 16) { if (!dst[i]) continue; @@ -754,6 +794,20 @@ out: return ret; } +/* + * This routine tries to handler interrupts in posted mode, here is how + * it deals with different cases: + * - For single-destination interrupts, handle it in posted mode + * - Else if vector hashing is enabled and it is a lowest-priority + * interrupt, handle it in posted mode and use the following mechanism + * to find the destinaiton vCPU. + * 1. For lowest-priority interrupts, store all the possible + * destination vCPUs in an array. + * 2. Use "guest vector % max number of destination vCPUs" to find + * the right destination vCPU in the array for the lowest-priority + * interrupt. + * - Otherwise, use remapped mode to inject the interrupt. + */ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu) { @@ -795,16 +849,37 @@ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, if (cid >= ARRAY_SIZE(map->logical_map)) goto out; - for_each_set_bit(i, &bitmap, 16) { - dst = map->logical_map[cid][i]; - if (++r == 2) + if (kvm_vector_hashing_enabled() && + kvm_lowest_prio_delivery(irq)) { + int idx; + unsigned int dest_vcpus; + + dest_vcpus = hweight16(bitmap); + if (dest_vcpus == 0) goto out; - } - if (dst && kvm_apic_present(dst->vcpu)) + idx = kvm_vector_to_index(irq->vector, dest_vcpus, + &bitmap, 16); + + dst = map->logical_map[cid][idx]; + if (!dst) { + kvm_apic_disabled_lapic_found(kvm); + goto out; + } + *dest_vcpu = dst->vcpu; - else - goto out; + } else { + for_each_set_bit(i, &bitmap, 16) { + dst = map->logical_map[cid][i]; + if (++r == 2) + goto out; + } + + if (dst && kvm_apic_present(dst->vcpu)) + *dest_vcpu = dst->vcpu; + else + goto out; + } } ret = true; @@ -819,7 +894,7 @@ out: */ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, int vector, int level, int trig_mode, - unsigned long *dest_map) + struct dest_map *dest_map) { int result = 0; struct kvm_vcpu *vcpu = apic->vcpu; @@ -839,8 +914,10 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, result = 1; - if (dest_map) - __set_bit(vcpu->vcpu_id, dest_map); + if (dest_map) { + __set_bit(vcpu->vcpu_id, dest_map->map); + dest_map->vectors[vcpu->vcpu_id] = vector; + } if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) { if (trig_mode) @@ -1239,7 +1316,7 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; u64 guest_tsc, tsc_deadline; - if (!kvm_vcpu_has_lapic(vcpu)) + if (!lapic_in_kernel(vcpu)) return; if (apic->lapic_timer.expired_tscdeadline == 0) @@ -1515,8 +1592,7 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) { - if (kvm_vcpu_has_lapic(vcpu)) - apic_reg_write(vcpu->arch.apic, APIC_EOI, 0); + apic_reg_write(vcpu->arch.apic, APIC_EOI, 0); } EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); @@ -1566,7 +1642,7 @@ u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) || + if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) return 0; @@ -1577,7 +1653,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) || + if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) return; @@ -1590,9 +1666,6 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!kvm_vcpu_has_lapic(vcpu)) - return; - apic_set_tpr(apic, ((cr8 & 0x0f) << 4) | (kvm_apic_get_reg(apic, APIC_TASKPRI) & 4)); } @@ -1601,9 +1674,6 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu) { u64 tpr; - if (!kvm_vcpu_has_lapic(vcpu)) - return 0; - tpr = (u64) kvm_apic_get_reg(vcpu->arch.apic, APIC_TASKPRI); return (tpr & 0xf0) >> 4; @@ -1728,8 +1798,7 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - if (kvm_vcpu_has_lapic(vcpu) && apic_enabled(apic) && - apic_lvt_enabled(apic, APIC_LVTT)) + if (apic_enabled(apic) && apic_lvt_enabled(apic, APIC_LVTT)) return atomic_read(&apic->lapic_timer.pending); return 0; @@ -1826,7 +1895,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; int highest_irr; - if (!kvm_vcpu_has_lapic(vcpu) || !apic_enabled(apic)) + if (!apic_enabled(apic)) return -1; apic_update_ppr(apic); @@ -1854,9 +1923,6 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!kvm_vcpu_has_lapic(vcpu)) - return; - if (atomic_read(&apic->lapic_timer.pending) > 0) { kvm_apic_local_deliver(apic, APIC_LVTT); if (apic_lvtt_tscdeadline(apic)) @@ -1932,7 +1998,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) { struct hrtimer *timer; - if (!kvm_vcpu_has_lapic(vcpu)) + if (!lapic_in_kernel(vcpu)) return; timer = &vcpu->arch.apic->lapic_timer.timer; @@ -2105,7 +2171,7 @@ int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!kvm_vcpu_has_lapic(vcpu)) + if (!lapic_in_kernel(vcpu)) return 1; /* if this is ICR write vector before command */ @@ -2119,7 +2185,7 @@ 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 (!kvm_vcpu_has_lapic(vcpu)) + if (!lapic_in_kernel(vcpu)) return 1; if (apic_reg_read(apic, reg, 4, &low)) @@ -2151,7 +2217,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) u8 sipi_vector; unsigned long pe; - if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events) + if (!lapic_in_kernel(vcpu) || !apic->pending_events) return; /* diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 41bdb35..f71183e 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -42,6 +42,9 @@ struct kvm_lapic { unsigned long pending_events; unsigned int sipi_vector; }; + +struct dest_map; + int kvm_create_lapic(struct kvm_vcpu *vcpu); void kvm_free_lapic(struct kvm_vcpu *vcpu); @@ -60,11 +63,11 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu); void __kvm_apic_update_irr(u32 *pir, void *regs); void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, - unsigned long *dest_map); + struct dest_map *dest_map); int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map); + struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map); u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info); @@ -103,7 +106,7 @@ static inline u32 kvm_apic_get_reg(struct kvm_lapic *apic, int reg_off) extern struct static_key kvm_no_apic_vcpu; -static inline bool kvm_vcpu_has_lapic(struct kvm_vcpu *vcpu) +static inline bool lapic_in_kernel(struct kvm_vcpu *vcpu) { if (static_key_false(&kvm_no_apic_vcpu)) return vcpu->arch.apic; @@ -130,7 +133,7 @@ static inline bool kvm_apic_sw_enabled(struct kvm_lapic *apic) static inline bool kvm_apic_present(struct kvm_vcpu *vcpu) { - return kvm_vcpu_has_lapic(vcpu) && kvm_apic_hw_enabled(vcpu->arch.apic); + return lapic_in_kernel(vcpu) && kvm_apic_hw_enabled(vcpu->arch.apic); } static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu) @@ -150,7 +153,7 @@ static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu) static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) { - return kvm_vcpu_has_lapic(vcpu) && vcpu->arch.apic->pending_events; + return lapic_in_kernel(vcpu) && vcpu->arch.apic->pending_events; } static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq) @@ -161,7 +164,7 @@ static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq) static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) { - return kvm_vcpu_has_lapic(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } static inline int kvm_apic_id(struct kvm_lapic *apic) @@ -175,4 +178,6 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu); bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); +int kvm_vector_to_index(u32 vector, u32 dest_vcpus, + const unsigned long *bitmap, u32 bitmap_size); #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 95a955d..2463de0 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -41,6 +41,7 @@ #include <asm/cmpxchg.h> #include <asm/io.h> #include <asm/vmx.h> +#include <asm/kvm_page_track.h> /* * When setting this variable to true it enables Two-Dimensional-Paging @@ -776,62 +777,85 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, return &slot->arch.lpage_info[level - 2][idx]; } +static void update_gfn_disallow_lpage_count(struct kvm_memory_slot *slot, + gfn_t gfn, int count) +{ + struct kvm_lpage_info *linfo; + int i; + + for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { + linfo = lpage_info_slot(gfn, slot, i); + linfo->disallow_lpage += count; + WARN_ON(linfo->disallow_lpage < 0); + } +} + +void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn) +{ + update_gfn_disallow_lpage_count(slot, gfn, 1); +} + +void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn) +{ + update_gfn_disallow_lpage_count(slot, gfn, -1); +} + static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; - struct kvm_lpage_info *linfo; gfn_t gfn; - int i; + kvm->arch.indirect_shadow_pages++; gfn = sp->gfn; slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); - for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { - linfo = lpage_info_slot(gfn, slot, i); - linfo->write_count += 1; - } - kvm->arch.indirect_shadow_pages++; + + /* the non-leaf shadow pages are keeping readonly. */ + if (sp->role.level > PT_PAGE_TABLE_LEVEL) + return kvm_slot_page_track_add_page(kvm, slot, gfn, + KVM_PAGE_TRACK_WRITE); + + kvm_mmu_gfn_disallow_lpage(slot, gfn); } static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; - struct kvm_lpage_info *linfo; gfn_t gfn; - int i; + kvm->arch.indirect_shadow_pages--; gfn = sp->gfn; slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, gfn); - for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { - linfo = lpage_info_slot(gfn, slot, i); - linfo->write_count -= 1; - WARN_ON(linfo->write_count < 0); - } - kvm->arch.indirect_shadow_pages--; + if (sp->role.level > PT_PAGE_TABLE_LEVEL) + return kvm_slot_page_track_remove_page(kvm, slot, gfn, + KVM_PAGE_TRACK_WRITE); + + kvm_mmu_gfn_allow_lpage(slot, gfn); } -static int __has_wrprotected_page(gfn_t gfn, int level, - struct kvm_memory_slot *slot) +static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level, + struct kvm_memory_slot *slot) { struct kvm_lpage_info *linfo; if (slot) { linfo = lpage_info_slot(gfn, slot, level); - return linfo->write_count; + return !!linfo->disallow_lpage; } - return 1; + return true; } -static int has_wrprotected_page(struct kvm_vcpu *vcpu, gfn_t gfn, int level) +static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn, + int level) { struct kvm_memory_slot *slot; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - return __has_wrprotected_page(gfn, level, slot); + return __mmu_gfn_lpage_is_disallowed(gfn, level, slot); } static int host_mapping_level(struct kvm *kvm, gfn_t gfn) @@ -897,7 +921,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn, max_level = min(kvm_x86_ops->get_lpage_level(), host_level); for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level) - if (__has_wrprotected_page(large_gfn, level, slot)) + if (__mmu_gfn_lpage_is_disallowed(large_gfn, level, slot)) break; return level - 1; @@ -1323,23 +1347,29 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } -static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) +bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, + struct kvm_memory_slot *slot, u64 gfn) { - struct kvm_memory_slot *slot; struct kvm_rmap_head *rmap_head; int i; bool write_protected = false; - slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { rmap_head = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(vcpu->kvm, rmap_head, true); + write_protected |= __rmap_write_protect(kvm, rmap_head, true); } return write_protected; } +static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) +{ + struct kvm_memory_slot *slot; + + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn); +} + static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; @@ -1754,7 +1784,7 @@ static void mark_unsync(u64 *spte) static int nonpaging_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { - return 1; + return 0; } static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva) @@ -1840,13 +1870,16 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, return nr_unsync_leaf; } +#define INVALID_INDEX (-1) + static int mmu_unsync_walk(struct kvm_mmu_page *sp, struct kvm_mmu_pages *pvec) { + pvec->nr = 0; if (!sp->unsync_children) return 0; - mmu_pages_add(pvec, sp, 0); + mmu_pages_add(pvec, sp, INVALID_INDEX); return __mmu_unsync_walk(sp, pvec); } @@ -1883,37 +1916,35 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, if ((_sp)->role.direct || (_sp)->role.invalid) {} else /* @sp->gfn should be write-protected at the call site */ -static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct list_head *invalid_list, bool clear_unsync) +static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + struct list_head *invalid_list) { if (sp->role.cr4_pae != !!is_pae(vcpu)) { kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); - return 1; + return false; } - if (clear_unsync) - kvm_unlink_unsync_page(vcpu->kvm, sp); - - if (vcpu->arch.mmu.sync_page(vcpu, sp)) { + if (vcpu->arch.mmu.sync_page(vcpu, sp) == 0) { kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); - return 1; + return false; } - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); - return 0; + return true; } -static int kvm_sync_page_transient(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp) +static void kvm_mmu_flush_or_zap(struct kvm_vcpu *vcpu, + struct list_head *invalid_list, + bool remote_flush, bool local_flush) { - LIST_HEAD(invalid_list); - int ret; - - ret = __kvm_sync_page(vcpu, sp, &invalid_list, false); - if (ret) - kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + if (!list_empty(invalid_list)) { + kvm_mmu_commit_zap_page(vcpu->kvm, invalid_list); + return; + } - return ret; + if (remote_flush) + kvm_flush_remote_tlbs(vcpu->kvm); + else if (local_flush) + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } #ifdef CONFIG_KVM_MMU_AUDIT @@ -1923,46 +1954,38 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { } static void mmu_audit_disable(void) { } #endif -static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, +static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { - return __kvm_sync_page(vcpu, sp, invalid_list, true); + kvm_unlink_unsync_page(vcpu->kvm, sp); + return __kvm_sync_page(vcpu, sp, invalid_list); } /* @gfn should be write-protected at the call site */ -static void kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn) +static bool kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, + struct list_head *invalid_list) { struct kvm_mmu_page *s; - LIST_HEAD(invalid_list); - bool flush = false; + bool ret = false; for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) { if (!s->unsync) continue; WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL); - kvm_unlink_unsync_page(vcpu->kvm, s); - if ((s->role.cr4_pae != !!is_pae(vcpu)) || - (vcpu->arch.mmu.sync_page(vcpu, s))) { - kvm_mmu_prepare_zap_page(vcpu->kvm, s, &invalid_list); - continue; - } - flush = true; + ret |= kvm_sync_page(vcpu, s, invalid_list); } - kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); - if (flush) - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + return ret; } struct mmu_page_path { - struct kvm_mmu_page *parent[PT64_ROOT_LEVEL-1]; - unsigned int idx[PT64_ROOT_LEVEL-1]; + struct kvm_mmu_page *parent[PT64_ROOT_LEVEL]; + unsigned int idx[PT64_ROOT_LEVEL]; }; #define for_each_sp(pvec, sp, parents, i) \ - for (i = mmu_pages_next(&pvec, &parents, -1), \ - sp = pvec.page[i].sp; \ + for (i = mmu_pages_first(&pvec, &parents); \ i < pvec.nr && ({ sp = pvec.page[i].sp; 1;}); \ i = mmu_pages_next(&pvec, &parents, i)) @@ -1974,19 +1997,43 @@ static int mmu_pages_next(struct kvm_mmu_pages *pvec, for (n = i+1; n < pvec->nr; n++) { struct kvm_mmu_page *sp = pvec->page[n].sp; + unsigned idx = pvec->page[n].idx; + int level = sp->role.level; - if (sp->role.level == PT_PAGE_TABLE_LEVEL) { - parents->idx[0] = pvec->page[n].idx; - return n; - } + parents->idx[level-1] = idx; + if (level == PT_PAGE_TABLE_LEVEL) + break; - parents->parent[sp->role.level-2] = sp; - parents->idx[sp->role.level-1] = pvec->page[n].idx; + parents->parent[level-2] = sp; } return n; } +static int mmu_pages_first(struct kvm_mmu_pages *pvec, + struct mmu_page_path *parents) +{ + struct kvm_mmu_page *sp; + int level; + + if (pvec->nr == 0) + return 0; + + WARN_ON(pvec->page[0].idx != INVALID_INDEX); + + sp = pvec->page[0].sp; + level = sp->role.level; + WARN_ON(level == PT_PAGE_TABLE_LEVEL); + + parents->parent[level-2] = sp; + + /* Also set up a sentinel. Further entries in pvec are all + * children of sp, so this element is never overwritten. + */ + parents->parent[level-1] = NULL; + return mmu_pages_next(pvec, parents, 0); +} + static void mmu_pages_clear_parents(struct mmu_page_path *parents) { struct kvm_mmu_page *sp; @@ -1994,22 +2041,14 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents) do { unsigned int idx = parents->idx[level]; - sp = parents->parent[level]; if (!sp) return; + WARN_ON(idx == INVALID_INDEX); clear_unsync_child_bit(sp, idx); level++; - } while (level < PT64_ROOT_LEVEL-1 && !sp->unsync_children); -} - -static void kvm_mmu_pages_init(struct kvm_mmu_page *parent, - struct mmu_page_path *parents, - struct kvm_mmu_pages *pvec) -{ - parents->parent[parent->role.level-1] = NULL; - pvec->nr = 0; + } while (!sp->unsync_children); } static void mmu_sync_children(struct kvm_vcpu *vcpu, @@ -2020,30 +2059,36 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, struct mmu_page_path parents; struct kvm_mmu_pages pages; LIST_HEAD(invalid_list); + bool flush = false; - kvm_mmu_pages_init(parent, &parents, &pages); while (mmu_unsync_walk(parent, &pages)) { bool protected = false; for_each_sp(pages, sp, parents, i) protected |= rmap_write_protect(vcpu, sp->gfn); - if (protected) + if (protected) { kvm_flush_remote_tlbs(vcpu->kvm); + flush = false; + } for_each_sp(pages, sp, parents, i) { - kvm_sync_page(vcpu, sp, &invalid_list); + flush |= kvm_sync_page(vcpu, sp, &invalid_list); mmu_pages_clear_parents(&parents); } - kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); - cond_resched_lock(&vcpu->kvm->mmu_lock); - kvm_mmu_pages_init(parent, &parents, &pages); + if (need_resched() || spin_needbreak(&vcpu->kvm->mmu_lock)) { + kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); + cond_resched_lock(&vcpu->kvm->mmu_lock); + flush = false; + } } + + kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); } static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) { - sp->write_flooding_count = 0; + atomic_set(&sp->write_flooding_count, 0); } static void clear_sp_write_flooding_count(u64 *spte) @@ -2069,6 +2114,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, unsigned quadrant; struct kvm_mmu_page *sp; bool need_sync = false; + bool flush = false; + LIST_HEAD(invalid_list); role = vcpu->arch.mmu.base_role; role.level = level; @@ -2092,8 +2139,16 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, if (sp->role.word != role.word) continue; - if (sp->unsync && kvm_sync_page_transient(vcpu, sp)) - break; + if (sp->unsync) { + /* The page is good, but __kvm_sync_page might still end + * up zapping it. If so, break in order to rebuild it. + */ + if (!__kvm_sync_page(vcpu, sp, &invalid_list)) + break; + + WARN_ON(!list_empty(&invalid_list)); + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); + } if (sp->unsync_children) kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); @@ -2112,16 +2167,24 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, hlist_add_head(&sp->hash_link, &vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]); if (!direct) { - if (rmap_write_protect(vcpu, gfn)) + /* + * we should do write protection before syncing pages + * otherwise the content of the synced shadow page may + * be inconsistent with guest page table. + */ + account_shadowed(vcpu->kvm, sp); + if (level == PT_PAGE_TABLE_LEVEL && + rmap_write_protect(vcpu, gfn)) kvm_flush_remote_tlbs(vcpu->kvm); - if (level > PT_PAGE_TABLE_LEVEL && need_sync) - kvm_sync_pages(vcpu, gfn); - account_shadowed(vcpu->kvm, sp); + if (level > PT_PAGE_TABLE_LEVEL && need_sync) + flush |= kvm_sync_pages(vcpu, gfn, &invalid_list); } sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; clear_page(sp->spt); trace_kvm_mmu_get_page(sp, true); + + kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); return sp; } @@ -2269,7 +2332,6 @@ static int mmu_zap_unsync_children(struct kvm *kvm, if (parent->role.level == PT_PAGE_TABLE_LEVEL) return 0; - kvm_mmu_pages_init(parent, &parents, &pages); while (mmu_unsync_walk(parent, &pages)) { struct kvm_mmu_page *sp; @@ -2278,7 +2340,6 @@ static int mmu_zap_unsync_children(struct kvm *kvm, mmu_pages_clear_parents(&parents); zapped++; } - kvm_mmu_pages_init(parent, &parents, &pages); } return zapped; @@ -2354,8 +2415,8 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm, if (list_empty(&kvm->arch.active_mmu_pages)) return false; - sp = list_entry(kvm->arch.active_mmu_pages.prev, - struct kvm_mmu_page, link); + sp = list_last_entry(&kvm->arch.active_mmu_pages, + struct kvm_mmu_page, link); kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); return true; @@ -2408,7 +2469,7 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); -static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { trace_kvm_mmu_unsync_page(sp); ++vcpu->kvm->stat.mmu_unsync; @@ -2417,37 +2478,26 @@ static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) kvm_mmu_mark_parents_unsync(sp); } -static void kvm_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn) +static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, + bool can_unsync) { - struct kvm_mmu_page *s; - - for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) { - if (s->unsync) - continue; - WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL); - __kvm_unsync_page(vcpu, s); - } -} + struct kvm_mmu_page *sp; -static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, - bool can_unsync) -{ - struct kvm_mmu_page *s; - bool need_unsync = false; + if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE)) + return true; - for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) { + for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { if (!can_unsync) - return 1; + return true; - if (s->role.level != PT_PAGE_TABLE_LEVEL) - return 1; + if (sp->unsync) + continue; - if (!s->unsync) - need_unsync = true; + WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL); + kvm_unsync_page(vcpu, sp); } - if (need_unsync) - kvm_unsync_pages(vcpu, gfn); - return 0; + + return false; } static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) @@ -2503,7 +2553,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, * be fixed if guest refault. */ if (level > PT_PAGE_TABLE_LEVEL && - has_wrprotected_page(vcpu, gfn, level)) + mmu_gfn_lpage_is_disallowed(vcpu, gfn, level)) goto done; spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; @@ -2768,7 +2818,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && PageTransCompound(pfn_to_page(pfn)) && - !has_wrprotected_page(vcpu, gfn, PT_DIRECTORY_LEVEL)) { + !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; /* * mmu_notifier_retry was successful and we hold the @@ -2796,20 +2846,16 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, kvm_pfn_t pfn, unsigned access, int *ret_val) { - bool ret = true; - /* The pfn is invalid, report the error! */ if (unlikely(is_error_pfn(pfn))) { *ret_val = kvm_handle_bad_page(vcpu, gfn, pfn); - goto exit; + return true; } if (unlikely(is_noslot_pfn(pfn))) vcpu_cache_mmio_info(vcpu, gva, gfn, access); - ret = false; -exit: - return ret; + return false; } static bool page_fault_can_be_fast(u32 error_code) @@ -3273,7 +3319,7 @@ static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level) return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level); } -static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct) +static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) { if (direct) return vcpu_match_mmio_gpa(vcpu, addr); @@ -3332,7 +3378,7 @@ int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) u64 spte; bool reserved; - if (quickly_check_mmio_pf(vcpu, addr, direct)) + if (mmio_info_in_cache(vcpu, addr, direct)) return RET_MMIO_PF_EMULATE; reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte); @@ -3362,20 +3408,53 @@ int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) } EXPORT_SYMBOL_GPL(handle_mmio_page_fault); +static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu, + u32 error_code, gfn_t gfn) +{ + if (unlikely(error_code & PFERR_RSVD_MASK)) + return false; + + if (!(error_code & PFERR_PRESENT_MASK) || + !(error_code & PFERR_WRITE_MASK)) + return false; + + /* + * guest is writing the page which is write tracked which can + * not be fixed by page fault handler. + */ + if (kvm_page_track_is_active(vcpu, gfn, KVM_PAGE_TRACK_WRITE)) + return true; + + return false; +} + +static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) +{ + struct kvm_shadow_walk_iterator iterator; + u64 spte; + + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return; + + walk_shadow_page_lockless_begin(vcpu); + for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { + clear_sp_write_flooding_count(iterator.sptep); + if (!is_shadow_present_pte(spte)) + break; + } + walk_shadow_page_lockless_end(vcpu); +} + static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, bool prefault) { - gfn_t gfn; + gfn_t gfn = gva >> PAGE_SHIFT; int r; pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); - if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, gva, true); - - if (likely(r != RET_MMIO_PF_INVALID)) - return r; - } + if (page_fault_handle_page_track(vcpu, error_code, gfn)) + return 1; r = mmu_topup_memory_caches(vcpu); if (r) @@ -3383,7 +3462,6 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); - gfn = gva >> PAGE_SHIFT; return nonpaging_map(vcpu, gva & PAGE_MASK, error_code, gfn, prefault); @@ -3460,12 +3538,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); - if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, gpa, true); - - if (likely(r != RET_MMIO_PF_INVALID)) - return r; - } + if (page_fault_handle_page_track(vcpu, error_code, gfn)) + return 1; r = mmu_topup_memory_caches(vcpu); if (r) @@ -3558,13 +3632,24 @@ static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, return false; } -static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte) +static inline bool is_last_gpte(struct kvm_mmu *mmu, + unsigned level, unsigned gpte) { - unsigned index; + /* + * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set + * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means + * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then. + */ + gpte |= level - PT_PAGE_TABLE_LEVEL - 1; - index = level - 1; - index |= (gpte & PT_PAGE_SIZE_MASK) >> (PT_PAGE_SIZE_SHIFT - 2); - return mmu->last_pte_bitmap & (1 << index); + /* + * The RHS has bit 7 set iff level < mmu->last_nonleaf_level. + * If it is clear, there are no large pages at this level, so clear + * PT_PAGE_SIZE_MASK in gpte if that is the case. + */ + gpte &= level - mmu->last_nonleaf_level; + + return gpte & PT_PAGE_SIZE_MASK; } #define PTTYPE_EPT 18 /* arbitrary */ @@ -3836,22 +3921,13 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu, } } -static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) +static void update_last_nonleaf_level(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { - u8 map; - unsigned level, root_level = mmu->root_level; - const unsigned ps_set_index = 1 << 2; /* bit 2 of index: ps */ - - if (root_level == PT32E_ROOT_LEVEL) - --root_level; - /* PT_PAGE_TABLE_LEVEL always terminates */ - map = 1 | (1 << ps_set_index); - for (level = PT_DIRECTORY_LEVEL; level <= root_level; ++level) { - if (level <= PT_PDPE_LEVEL - && (mmu->root_level >= PT32E_ROOT_LEVEL || is_pse(vcpu))) - map |= 1 << (ps_set_index | (level - 1)); - } - mmu->last_pte_bitmap = map; + unsigned root_level = mmu->root_level; + + mmu->last_nonleaf_level = root_level; + if (root_level == PT32_ROOT_LEVEL && is_pse(vcpu)) + mmu->last_nonleaf_level++; } static void paging64_init_context_common(struct kvm_vcpu *vcpu, @@ -3863,7 +3939,7 @@ static void paging64_init_context_common(struct kvm_vcpu *vcpu, reset_rsvds_bits_mask(vcpu, context); update_permission_bitmask(vcpu, context, false); - update_last_pte_bitmap(vcpu, context); + update_last_nonleaf_level(vcpu, context); MMU_WARN_ON(!is_pae(vcpu)); context->page_fault = paging64_page_fault; @@ -3890,7 +3966,7 @@ static void paging32_init_context(struct kvm_vcpu *vcpu, reset_rsvds_bits_mask(vcpu, context); update_permission_bitmask(vcpu, context, false); - update_last_pte_bitmap(vcpu, context); + update_last_nonleaf_level(vcpu, context); context->page_fault = paging32_page_fault; context->gva_to_gpa = paging32_gva_to_gpa; @@ -3948,7 +4024,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) } update_permission_bitmask(vcpu, context, false); - update_last_pte_bitmap(vcpu, context); + update_last_nonleaf_level(vcpu, context); reset_tdp_shadow_zero_bits_mask(vcpu, context); } @@ -4054,7 +4130,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) } update_permission_bitmask(vcpu, g_context, false); - update_last_pte_bitmap(vcpu, g_context); + update_last_nonleaf_level(vcpu, g_context); } static void init_kvm_mmu(struct kvm_vcpu *vcpu) @@ -4125,18 +4201,6 @@ static bool need_remote_flush(u64 old, u64 new) return (old & ~new & PT64_PERM_MASK) != 0; } -static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page, - bool remote_flush, bool local_flush) -{ - if (zap_page) - return; - - if (remote_flush) - kvm_flush_remote_tlbs(vcpu->kvm); - else if (local_flush) - kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); -} - static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, const u8 *new, int *bytes) { @@ -4186,7 +4250,8 @@ static bool detect_write_flooding(struct kvm_mmu_page *sp) if (sp->role.level == PT_PAGE_TABLE_LEVEL) return false; - return ++sp->write_flooding_count >= 3; + atomic_inc(&sp->write_flooding_count); + return atomic_read(&sp->write_flooding_count) >= 3; } /* @@ -4248,15 +4313,15 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) return spte; } -void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes) +static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, + const u8 *new, int bytes) { gfn_t gfn = gpa >> PAGE_SHIFT; struct kvm_mmu_page *sp; LIST_HEAD(invalid_list); u64 entry, gentry, *spte; int npte; - bool remote_flush, local_flush, zap_page; + bool remote_flush, local_flush; union kvm_mmu_page_role mask = { }; mask.cr0_wp = 1; @@ -4273,7 +4338,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) return; - zap_page = remote_flush = local_flush = false; + remote_flush = local_flush = false; pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); @@ -4293,8 +4358,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) { if (detect_write_misaligned(sp, gpa, bytes) || detect_write_flooding(sp)) { - zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, - &invalid_list); + kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); ++vcpu->kvm->stat.mmu_flooded; continue; } @@ -4316,8 +4380,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, ++spte; } } - mmu_pte_write_flush_tlb(vcpu, zap_page, remote_flush, local_flush); - kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); + kvm_mmu_flush_or_zap(vcpu, &invalid_list, remote_flush, local_flush); kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE); spin_unlock(&vcpu->kvm->mmu_lock); } @@ -4354,32 +4417,34 @@ static void make_mmu_pages_available(struct kvm_vcpu *vcpu) kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); } -static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr) -{ - if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu)) - return vcpu_match_mmio_gpa(vcpu, addr); - - return vcpu_match_mmio_gva(vcpu, addr); -} - int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code, void *insn, int insn_len) { int r, emulation_type = EMULTYPE_RETRY; enum emulation_result er; + bool direct = vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu); + + if (unlikely(error_code & PFERR_RSVD_MASK)) { + r = handle_mmio_page_fault(vcpu, cr2, direct); + if (r == RET_MMIO_PF_EMULATE) { + emulation_type = 0; + goto emulate; + } + if (r == RET_MMIO_PF_RETRY) + return 1; + if (r < 0) + return r; + } r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false); if (r < 0) - goto out; - - if (!r) { - r = 1; - goto out; - } + return r; + if (!r) + return 1; - if (is_mmio_page_fault(vcpu, cr2)) + if (mmio_info_in_cache(vcpu, cr2, direct)) emulation_type = 0; - +emulate: er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); switch (er) { @@ -4393,8 +4458,6 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code, default: BUG(); } -out: - return r; } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); @@ -4463,6 +4526,21 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) init_kvm_mmu(vcpu); } +void kvm_mmu_init_vm(struct kvm *kvm) +{ + struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; + + node->track_write = kvm_mmu_pte_write; + kvm_page_track_register_notifier(kvm, node); +} + +void kvm_mmu_uninit_vm(struct kvm *kvm) +{ + struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; + + kvm_page_track_unregister_notifier(kvm, node); +} + /* The return value indicates if tlb flush on all vcpus is needed. */ typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 55ffb7b..58fe98a 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -174,4 +174,9 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm); void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); + +void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); +void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); +bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, + struct kvm_memory_slot *slot, u64 gfn); #endif diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c new file mode 100644 index 0000000..11f7643 --- /dev/null +++ b/arch/x86/kvm/page_track.c @@ -0,0 +1,222 @@ +/* + * Support KVM gust page tracking + * + * This feature allows us to track page access in guest. Currently, only + * write access is tracked. + * + * Copyright(C) 2015 Intel Corporation. + * + * Author: + * Xiao Guangrong <guangrong.xiao@linux.intel.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/kvm_host.h> +#include <asm/kvm_host.h> +#include <asm/kvm_page_track.h> + +#include "mmu.h" + +void kvm_page_track_free_memslot(struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) +{ + int i; + + for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) + if (!dont || free->arch.gfn_track[i] != + dont->arch.gfn_track[i]) { + kvfree(free->arch.gfn_track[i]); + free->arch.gfn_track[i] = NULL; + } +} + +int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, + unsigned long npages) +{ + int i; + + for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { + slot->arch.gfn_track[i] = kvm_kvzalloc(npages * + sizeof(*slot->arch.gfn_track[i])); + if (!slot->arch.gfn_track[i]) + goto track_free; + } + + return 0; + +track_free: + kvm_page_track_free_memslot(slot, NULL); + return -ENOMEM; +} + +static inline bool page_track_mode_is_valid(enum kvm_page_track_mode mode) +{ + if (mode < 0 || mode >= KVM_PAGE_TRACK_MAX) + return false; + + return true; +} + +static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn, + enum kvm_page_track_mode mode, short count) +{ + int index, val; + + index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL); + + val = slot->arch.gfn_track[mode][index]; + + if (WARN_ON(val + count < 0 || val + count > USHRT_MAX)) + return; + + slot->arch.gfn_track[mode][index] += count; +} + +/* + * add guest page to the tracking pool so that corresponding access on that + * page will be intercepted. + * + * It should be called under the protection both of mmu-lock and kvm->srcu + * or kvm->slots_lock. + * + * @kvm: the guest instance we are interested in. + * @slot: the @gfn belongs to. + * @gfn: the guest page. + * @mode: tracking mode, currently only write track is supported. + */ +void kvm_slot_page_track_add_page(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn, + enum kvm_page_track_mode mode) +{ + + if (WARN_ON(!page_track_mode_is_valid(mode))) + return; + + update_gfn_track(slot, gfn, mode, 1); + + /* + * new track stops large page mapping for the + * tracked page. + */ + kvm_mmu_gfn_disallow_lpage(slot, gfn); + + if (mode == KVM_PAGE_TRACK_WRITE) + if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn)) + kvm_flush_remote_tlbs(kvm); +} + +/* + * remove the guest page from the tracking pool which stops the interception + * of corresponding access on that page. It is the opposed operation of + * kvm_slot_page_track_add_page(). + * + * It should be called under the protection both of mmu-lock and kvm->srcu + * or kvm->slots_lock. + * + * @kvm: the guest instance we are interested in. + * @slot: the @gfn belongs to. + * @gfn: the guest page. + * @mode: tracking mode, currently only write track is supported. + */ +void kvm_slot_page_track_remove_page(struct kvm *kvm, + struct kvm_memory_slot *slot, gfn_t gfn, + enum kvm_page_track_mode mode) +{ + if (WARN_ON(!page_track_mode_is_valid(mode))) + return; + + update_gfn_track(slot, gfn, mode, -1); + + /* + * allow large page mapping for the tracked page + * after the tracker is gone. + */ + kvm_mmu_gfn_allow_lpage(slot, gfn); +} + +/* + * check if the corresponding access on the specified guest page is tracked. + */ +bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn, + enum kvm_page_track_mode mode) +{ + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + int index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL); + + if (WARN_ON(!page_track_mode_is_valid(mode))) + return false; + + return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]); +} + +void kvm_page_track_init(struct kvm *kvm) +{ + struct kvm_page_track_notifier_head *head; + + head = &kvm->arch.track_notifier_head; + init_srcu_struct(&head->track_srcu); + INIT_HLIST_HEAD(&head->track_notifier_list); +} + +/* + * register the notifier so that event interception for the tracked guest + * pages can be received. + */ +void +kvm_page_track_register_notifier(struct kvm *kvm, + struct kvm_page_track_notifier_node *n) +{ + struct kvm_page_track_notifier_head *head; + + head = &kvm->arch.track_notifier_head; + + spin_lock(&kvm->mmu_lock); + hlist_add_head_rcu(&n->node, &head->track_notifier_list); + spin_unlock(&kvm->mmu_lock); +} + +/* + * stop receiving the event interception. It is the opposed operation of + * kvm_page_track_register_notifier(). + */ +void +kvm_page_track_unregister_notifier(struct kvm *kvm, + struct kvm_page_track_notifier_node *n) +{ + struct kvm_page_track_notifier_head *head; + + head = &kvm->arch.track_notifier_head; + + spin_lock(&kvm->mmu_lock); + hlist_del_rcu(&n->node); + spin_unlock(&kvm->mmu_lock); + synchronize_srcu(&head->track_srcu); +} + +/* + * Notify the node that write access is intercepted and write emulation is + * finished at this time. + * + * The node should figure out if the written page is the one that node is + * interested in by itself. + */ +void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, + int bytes) +{ + struct kvm_page_track_notifier_head *head; + struct kvm_page_track_notifier_node *n; + int idx; + + head = &vcpu->kvm->arch.track_notifier_head; + + if (hlist_empty(&head->track_notifier_list)) + return; + + idx = srcu_read_lock(&head->track_srcu); + hlist_for_each_entry_rcu(n, &head->track_notifier_list, node) + if (n->track_write) + n->track_write(vcpu, gpa, new, bytes); + srcu_read_unlock(&head->track_srcu, idx); +} diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 2ce4f05..e159a81 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -189,8 +189,11 @@ static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, u64 gpte) ((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) | ACC_USER_MASK; #else - access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK; - access &= ~(gpte >> PT64_NX_SHIFT); + BUILD_BUG_ON(ACC_EXEC_MASK != PT_PRESENT_MASK); + BUILD_BUG_ON(ACC_EXEC_MASK != 1); + access = gpte & (PT_WRITABLE_MASK | PT_USER_MASK | PT_PRESENT_MASK); + /* Combine NX with P (which is set here) to get ACC_EXEC_MASK. */ + access ^= (gpte >> PT64_NX_SHIFT); #endif return access; @@ -702,24 +705,17 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); - if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, addr, mmu_is_nested(vcpu)); - if (likely(r != RET_MMIO_PF_INVALID)) - return r; - - /* - * page fault with PFEC.RSVD = 1 is caused by shadow - * page fault, should not be used to walk guest page - * table. - */ - error_code &= ~PFERR_RSVD_MASK; - }; - r = mmu_topup_memory_caches(vcpu); if (r) return r; /* + * If PFEC.RSVD is set, this is a shadow page fault. + * The bit needs to be cleared before walking guest page tables. + */ + error_code &= ~PFERR_RSVD_MASK; + + /* * Look up the guest pte for the faulting address. */ r = FNAME(walk_addr)(&walker, vcpu, addr, error_code); @@ -735,6 +731,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, return 0; } + if (page_fault_handle_page_track(vcpu, error_code, walker.gfn)) { + shadow_page_table_clear_flood(vcpu, addr); + return 1; + } + vcpu->arch.write_fault_to_shadow_pgtable = false; is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, @@ -945,7 +946,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, sizeof(pt_element_t))) - return -EINVAL; + return 0; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { vcpu->kvm->tlbs_dirty++; @@ -977,7 +978,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) host_writable); } - return !nr_present; + return nr_present; } #undef pt_element_t diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 31aa2c8..06ce377 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -257,7 +257,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) { - if (vcpu->arch.apic) + if (lapic_in_kernel(vcpu)) kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC); } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c13a64b..9507038 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1858,8 +1858,7 @@ static int halt_interception(struct vcpu_svm *svm) static int vmmcall_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - kvm_emulate_hypercall(&svm->vcpu); - return 1; + return kvm_emulate_hypercall(&svm->vcpu); } static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index ad9f6a2..2f1ea2f 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -996,11 +996,13 @@ TRACE_EVENT(kvm_enter_smm, * Tracepoint for VT-d posted-interrupts. */ TRACE_EVENT(kvm_pi_irte_update, - TP_PROTO(unsigned int vcpu_id, unsigned int gsi, - unsigned int gvec, u64 pi_desc_addr, bool set), - TP_ARGS(vcpu_id, gsi, gvec, pi_desc_addr, set), + TP_PROTO(unsigned int host_irq, unsigned int vcpu_id, + unsigned int gsi, unsigned int gvec, + u64 pi_desc_addr, bool set), + TP_ARGS(host_irq, vcpu_id, gsi, gvec, pi_desc_addr, set), TP_STRUCT__entry( + __field( unsigned int, host_irq ) __field( unsigned int, vcpu_id ) __field( unsigned int, gsi ) __field( unsigned int, gvec ) @@ -1009,6 +1011,7 @@ TRACE_EVENT(kvm_pi_irte_update, ), TP_fast_assign( + __entry->host_irq = host_irq; __entry->vcpu_id = vcpu_id; __entry->gsi = gsi; __entry->gvec = gvec; @@ -1016,9 +1019,10 @@ TRACE_EVENT(kvm_pi_irte_update, __entry->set = set; ), - TP_printk("VT-d PI is %s for this irq, vcpu %u, gsi: 0x%x, " + TP_printk("VT-d PI is %s for irq %u, vcpu %u, gsi: 0x%x, " "gvec: 0x%x, pi_desc_addr: 0x%llx", __entry->set ? "enabled and being updated" : "disabled", + __entry->host_irq, __entry->vcpu_id, __entry->gsi, __entry->gvec, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e2951b6..46154da 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -961,25 +961,36 @@ static const u32 vmx_msr_index[] = { MSR_EFER, MSR_TSC_AUX, MSR_STAR, }; -static inline bool is_page_fault(u32 intr_info) +static inline bool is_exception_n(u32 intr_info, u8 vector) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); + (INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK); +} + +static inline bool is_debug(u32 intr_info) +{ + return is_exception_n(intr_info, DB_VECTOR); +} + +static inline bool is_breakpoint(u32 intr_info) +{ + return is_exception_n(intr_info, BP_VECTOR); +} + +static inline bool is_page_fault(u32 intr_info) +{ + return is_exception_n(intr_info, PF_VECTOR); } static inline bool is_no_device(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); + return is_exception_n(intr_info, NM_VECTOR); } static inline bool is_invalid_opcode(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK); + return is_exception_n(intr_info, UD_VECTOR); } static inline bool is_external_interrupt(u32 intr_info) @@ -5608,11 +5619,8 @@ static int handle_dr(struct kvm_vcpu *vcpu) } if (vcpu->guest_debug == 0) { - u32 cpu_based_vm_exec_control; - - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control &= ~CPU_BASED_MOV_DR_EXITING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_MOV_DR_EXITING); /* * No more DR vmexits; force a reload of the debug registers @@ -5649,8 +5657,6 @@ static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - get_debugreg(vcpu->arch.db[0], 0); get_debugreg(vcpu->arch.db[1], 1); get_debugreg(vcpu->arch.db[2], 2); @@ -5659,10 +5665,7 @@ static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) vcpu->arch.dr7 = vmcs_readl(GUEST_DR7); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; - - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control |= CPU_BASED_MOV_DR_EXITING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_MOV_DR_EXITING); } static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) @@ -5747,8 +5750,7 @@ static int handle_halt(struct kvm_vcpu *vcpu) static int handle_vmcall(struct kvm_vcpu *vcpu) { - kvm_emulate_hypercall(vcpu); - return 1; + return kvm_emulate_hypercall(vcpu); } static int handle_invd(struct kvm_vcpu *vcpu) @@ -6435,8 +6437,8 @@ static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) { /* Recycle the least recently used VMCS. */ - item = list_entry(vmx->nested.vmcs02_pool.prev, - struct vmcs02_list, list); + item = list_last_entry(&vmx->nested.vmcs02_pool, + struct vmcs02_list, list); item->vmptr = vmx->nested.current_vmptr; list_move(&item->list, &vmx->nested.vmcs02_pool); return &item->vmcs02; @@ -7752,6 +7754,13 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) else if (is_no_device(intr_info) && !(vmcs12->guest_cr0 & X86_CR0_TS)) return false; + else if (is_debug(intr_info) && + vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + return false; + else if (is_breakpoint(intr_info) && + vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) + return false; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); case EXIT_REASON_EXTERNAL_INTERRUPT: @@ -10764,13 +10773,26 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, */ kvm_set_msi_irq(e, &irq); - if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) { + /* + * Make sure the IRTE is in remapped mode if + * we don't handle it in posted mode. + */ + ret = irq_set_vcpu_affinity(host_irq, NULL); + if (ret < 0) { + printk(KERN_INFO + "failed to back to remapped mode, irq: %u\n", + host_irq); + goto out; + } + continue; + } vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)); vcpu_info.vector = irq.vector; - trace_kvm_pi_irte_update(vcpu->vcpu_id, e->gsi, + trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi, vcpu_info.vector, vcpu_info.pi_desc_addr, set); if (set) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f4891f2..60d6c00 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -123,6 +123,9 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); unsigned int __read_mostly lapic_timer_advance_ns = 0; module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); +static bool __read_mostly vector_hashing = true; +module_param(vector_hashing, bool, S_IRUGO); + static bool __read_mostly backwards_tsc_observed = false; #define KVM_NR_SHARED_MSRS 16 @@ -1196,17 +1199,11 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) static uint32_t div_frac(uint32_t dividend, uint32_t divisor) { - uint32_t quotient, remainder; - - /* Don't try to replace with do_div(), this one calculates - * "(dividend << 32) / divisor" */ - __asm__ ( "divl %4" - : "=a" (quotient), "=d" (remainder) - : "0" (0), "1" (dividend), "r" (divisor) ); - return quotient; + do_shl32_div32(dividend, divisor); + return dividend; } -static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz, +static void kvm_get_time_scale(uint64_t scaled_hz, uint64_t base_hz, s8 *pshift, u32 *pmultiplier) { uint64_t scaled64; @@ -1214,8 +1211,8 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz, uint64_t tps64; uint32_t tps32; - tps64 = base_khz * 1000LL; - scaled64 = scaled_khz * 1000LL; + tps64 = base_hz; + scaled64 = scaled_hz; while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) { tps64 >>= 1; shift--; @@ -1233,8 +1230,8 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz, *pshift = shift; *pmultiplier = div_frac(scaled64, tps32); - pr_debug("%s: base_khz %u => %u, shift %d, mul %u\n", - __func__, base_khz, scaled_khz, shift, *pmultiplier); + pr_debug("%s: base_hz %llu => %llu, shift %d, mul %u\n", + __func__, base_hz, scaled_hz, shift, *pmultiplier); } #ifdef CONFIG_X86_64 @@ -1293,23 +1290,23 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) return 0; } -static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) +static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) { u32 thresh_lo, thresh_hi; int use_scaling = 0; /* tsc_khz can be zero if TSC calibration fails */ - if (this_tsc_khz == 0) { + if (user_tsc_khz == 0) { /* set tsc_scaling_ratio to a safe value */ vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; return -1; } /* Compute a scale to convert nanoseconds in TSC cycles */ - kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000, + kvm_get_time_scale(user_tsc_khz * 1000LL, NSEC_PER_SEC, &vcpu->arch.virtual_tsc_shift, &vcpu->arch.virtual_tsc_mult); - vcpu->arch.virtual_tsc_khz = this_tsc_khz; + vcpu->arch.virtual_tsc_khz = user_tsc_khz; /* * Compute the variation in TSC rate which is acceptable @@ -1319,11 +1316,11 @@ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) */ thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm); thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm); - if (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) { - pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi); + if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) { + pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi); use_scaling = 1; } - return set_tsc_khz(vcpu, this_tsc_khz, use_scaling); + return set_tsc_khz(vcpu, user_tsc_khz, use_scaling); } static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) @@ -1716,7 +1713,7 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) static int kvm_guest_time_update(struct kvm_vcpu *v) { - unsigned long flags, this_tsc_khz, tgt_tsc_khz; + unsigned long flags, tgt_tsc_khz; struct kvm_vcpu_arch *vcpu = &v->arch; struct kvm_arch *ka = &v->kvm->arch; s64 kernel_ns; @@ -1742,8 +1739,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); - this_tsc_khz = __this_cpu_read(cpu_tsc_khz); - if (unlikely(this_tsc_khz == 0)) { + tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz); + if (unlikely(tgt_tsc_khz == 0)) { local_irq_restore(flags); kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); return 1; @@ -1778,13 +1775,14 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) if (!vcpu->pv_time_enabled) return 0; - if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) { - tgt_tsc_khz = kvm_has_tsc_control ? - vcpu->virtual_tsc_khz : this_tsc_khz; - kvm_get_time_scale(NSEC_PER_SEC / 1000, tgt_tsc_khz, + if (kvm_has_tsc_control) + tgt_tsc_khz = kvm_scale_tsc(v, tgt_tsc_khz); + + if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) { + kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL, &vcpu->hv_clock.tsc_shift, &vcpu->hv_clock.tsc_to_system_mul); - vcpu->hw_tsc_khz = this_tsc_khz; + vcpu->hw_tsc_khz = tgt_tsc_khz; } /* With all the info we got, fill in the values */ @@ -2988,7 +2986,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && - kvm_vcpu_has_lapic(vcpu)) + lapic_in_kernel(vcpu)) vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { @@ -3001,7 +2999,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; - if (kvm_vcpu_has_lapic(vcpu)) { + if (lapic_in_kernel(vcpu)) { if (events->smi.latched_init) set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); else @@ -3241,7 +3239,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, switch (ioctl) { case KVM_GET_LAPIC: { r = -EINVAL; - if (!vcpu->arch.apic) + if (!lapic_in_kernel(vcpu)) goto out; u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); @@ -3259,7 +3257,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } case KVM_SET_LAPIC: { r = -EINVAL; - if (!vcpu->arch.apic) + if (!lapic_in_kernel(vcpu)) goto out; u.lapic = memdup_user(argp, sizeof(*u.lapic)); if (IS_ERR(u.lapic)) @@ -3606,20 +3604,26 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) { - mutex_lock(&kvm->arch.vpit->pit_state.lock); - memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state)); - mutex_unlock(&kvm->arch.vpit->pit_state.lock); + struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state; + + BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels)); + + mutex_lock(&kps->lock); + memcpy(ps, &kps->channels, sizeof(*ps)); + mutex_unlock(&kps->lock); return 0; } static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) { int i; - mutex_lock(&kvm->arch.vpit->pit_state.lock); - memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); + struct kvm_pit *pit = kvm->arch.vpit; + + mutex_lock(&pit->pit_state.lock); + memcpy(&pit->pit_state.channels, ps, sizeof(*ps)); for (i = 0; i < 3; i++) - kvm_pit_load_count(kvm, i, ps->channels[i].count, 0); - mutex_unlock(&kvm->arch.vpit->pit_state.lock); + kvm_pit_load_count(pit, i, ps->channels[i].count, 0); + mutex_unlock(&pit->pit_state.lock); return 0; } @@ -3639,29 +3643,39 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) int start = 0; int i; u32 prev_legacy, cur_legacy; - mutex_lock(&kvm->arch.vpit->pit_state.lock); - prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; + struct kvm_pit *pit = kvm->arch.vpit; + + mutex_lock(&pit->pit_state.lock); + prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY; if (!prev_legacy && cur_legacy) start = 1; - memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels, - sizeof(kvm->arch.vpit->pit_state.channels)); - kvm->arch.vpit->pit_state.flags = ps->flags; + memcpy(&pit->pit_state.channels, &ps->channels, + sizeof(pit->pit_state.channels)); + pit->pit_state.flags = ps->flags; for (i = 0; i < 3; i++) - kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, + kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count, start && i == 0); - mutex_unlock(&kvm->arch.vpit->pit_state.lock); + mutex_unlock(&pit->pit_state.lock); return 0; } static int kvm_vm_ioctl_reinject(struct kvm *kvm, struct kvm_reinject_control *control) { - if (!kvm->arch.vpit) + struct kvm_pit *pit = kvm->arch.vpit; + + if (!pit) return -ENXIO; - mutex_lock(&kvm->arch.vpit->pit_state.lock); - kvm->arch.vpit->pit_state.reinject = control->pit_reinject; - mutex_unlock(&kvm->arch.vpit->pit_state.lock); + + /* pit->pit_state.lock was overloaded to prevent userspace from getting + * an inconsistent state after running multiple KVM_REINJECT_CONTROL + * ioctls in parallel. Use a separate lock if that ioctl isn't rare. + */ + mutex_lock(&pit->pit_state.lock); + kvm_pit_set_reinject(pit, control->pit_reinject); + mutex_unlock(&pit->pit_state.lock); + return 0; } @@ -4094,7 +4108,7 @@ static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, do { n = min(len, 8); - if (!(vcpu->arch.apic && + if (!(lapic_in_kernel(vcpu) && !kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v)) && kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v)) break; @@ -4114,7 +4128,7 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) do { n = min(len, 8); - if (!(vcpu->arch.apic && + if (!(lapic_in_kernel(vcpu) && !kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev, addr, n, v)) && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v)) @@ -4347,7 +4361,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes); if (ret < 0) return 0; - kvm_mmu_pte_write(vcpu, gpa, val, bytes); + kvm_page_track_write(vcpu, gpa, val, bytes); return 1; } @@ -4605,7 +4619,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, return X86EMUL_CMPXCHG_FAILED; kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); - kvm_mmu_pte_write(vcpu, gpa, new, bytes); + kvm_page_track_write(vcpu, gpa, new, bytes); return X86EMUL_CONTINUE; @@ -6011,7 +6025,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) if (!kvm_x86_ops->update_cr8_intercept) return; - if (!vcpu->arch.apic) + if (!lapic_in_kernel(vcpu)) return; if (vcpu->arch.apicv_active) @@ -7039,7 +7053,7 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - if (!kvm_vcpu_has_lapic(vcpu) && + if (!lapic_in_kernel(vcpu) && mp_state->mp_state != KVM_MP_STATE_RUNNABLE) return -EINVAL; @@ -7594,6 +7608,7 @@ bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) } struct static_key kvm_no_apic_vcpu __read_mostly; +EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu); int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { @@ -7725,6 +7740,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); + kvm_page_track_init(kvm); + kvm_mmu_init_vm(kvm); + return 0; } @@ -7851,6 +7869,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kfree(kvm->arch.vioapic); kvm_free_vcpus(kvm); kfree(rcu_dereference_check(kvm->arch.apic_map, 1)); + kvm_mmu_uninit_vm(kvm); } void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, @@ -7872,6 +7891,8 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, free->arch.lpage_info[i - 1] = NULL; } } + + kvm_page_track_free_memslot(free, dont); } int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, @@ -7880,6 +7901,7 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { + struct kvm_lpage_info *linfo; unsigned long ugfn; int lpages; int level = i + 1; @@ -7894,15 +7916,16 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, if (i == 0) continue; - slot->arch.lpage_info[i - 1] = kvm_kvzalloc(lpages * - sizeof(*slot->arch.lpage_info[i - 1])); - if (!slot->arch.lpage_info[i - 1]) + linfo = kvm_kvzalloc(lpages * sizeof(*linfo)); + if (!linfo) goto out_free; + slot->arch.lpage_info[i - 1] = linfo; + if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1)) - slot->arch.lpage_info[i - 1][0].write_count = 1; + linfo[0].disallow_lpage = 1; if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1)) - slot->arch.lpage_info[i - 1][lpages - 1].write_count = 1; + linfo[lpages - 1].disallow_lpage = 1; ugfn = slot->userspace_addr >> PAGE_SHIFT; /* * If the gfn and userspace address are not aligned wrt each @@ -7914,10 +7937,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned long j; for (j = 0; j < lpages; ++j) - slot->arch.lpage_info[i - 1][j].write_count = 1; + linfo[j].disallow_lpage = 1; } } + if (kvm_page_track_create_memslot(slot, npages)) + goto out_free; + return 0; out_free: @@ -8371,6 +8397,12 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set); } +bool kvm_vector_hashing_enabled(void) +{ + return vector_hashing; +} +EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled); + EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index f2afa5f..007940f 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -179,6 +179,7 @@ int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data); int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); +bool kvm_vector_hashing_enabled(void); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ @@ -192,4 +193,19 @@ extern unsigned int min_timer_period_us; extern unsigned int lapic_timer_advance_ns; extern struct static_key kvm_no_apic_vcpu; + +/* Same "calling convention" as do_div: + * - divide (n << 32) by base + * - put result in n + * - return remainder + */ +#define do_shl32_div32(n, base) \ + ({ \ + u32 __quot, __rem; \ + asm("divl %2" : "=a" (__quot), "=d" (__rem) \ + : "rm" (base), "0" (0), "1" ((u32) n)); \ + n = __quot; \ + __rem; \ + }) + #endif diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 4ebc796..2f8c0f4 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -256,12 +256,6 @@ struct hv_monitor_page { u8 rsvdz4[1984]; }; -/* Declare the various hypercall operations. */ -enum hv_call_code { - HVCALL_POST_MESSAGE = 0x005c, - HVCALL_SIGNAL_EVENT = 0x005d, -}; - /* Definition of the hv_post_message hypercall input structure. */ struct hv_input_post_message { union hv_connection_id connectionid; diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index d6f8322..aa69253 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -359,14 +359,15 @@ TRACE_EVENT( #endif TRACE_EVENT(kvm_halt_poll_ns, - TP_PROTO(bool grow, unsigned int vcpu_id, int new, int old), + TP_PROTO(bool grow, unsigned int vcpu_id, unsigned int new, + unsigned int old), TP_ARGS(grow, vcpu_id, new, old), TP_STRUCT__entry( __field(bool, grow) __field(unsigned int, vcpu_id) - __field(int, new) - __field(int, old) + __field(unsigned int, new) + __field(unsigned int, old) ), TP_fast_assign( @@ -376,7 +377,7 @@ TRACE_EVENT(kvm_halt_poll_ns, __entry->old = old; ), - TP_printk("vcpu %u: halt_poll_ns %d (%s %d)", + TP_printk("vcpu %u: halt_poll_ns %u (%s %u)", __entry->vcpu_id, __entry->new, __entry->grow ? "grow" : "shrink", diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 50f44a2..a7f1f80 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -157,6 +157,7 @@ struct kvm_s390_skeys { struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 +#define KVM_EXIT_HYPERV_HCALL 2 __u32 type; union { struct { @@ -165,6 +166,11 @@ struct kvm_hyperv_exit { __u64 evt_page; __u64 msg_page; } synic; + struct { + __u64 input; + __u64 result; + __u64 params[2]; + } hcall; } u; }; @@ -541,7 +547,13 @@ struct kvm_s390_pgm_info { __u8 exc_access_id; __u8 per_access_id; __u8 op_access_id; - __u8 pad[3]; +#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 +#define KVM_S390_PGM_FLAGS_ILC_0 0x02 +#define KVM_S390_PGM_FLAGS_ILC_1 0x04 +#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 +#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 + __u8 flags; + __u8 pad[2]; }; struct kvm_s390_prefix_info { @@ -850,8 +862,9 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_IOEVENTFD_ANY_LENGTH 122 #define KVM_CAP_HYPERV_SYNIC 123 #define KVM_CAP_S390_RI 124 -#define KVM_CAP_ARM_PMU_V3 125 -#define KVM_CAP_VCPU_ATTRIBUTES 126 +#define KVM_CAP_SPAPR_TCE_64 125 +#define KVM_CAP_ARM_PMU_V3 126 +#define KVM_CAP_VCPU_ATTRIBUTES 127 #ifdef KVM_CAP_IRQ_ROUTING @@ -1144,6 +1157,8 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_PPC_ALLOC_HTAB */ #define KVM_PPC_ALLOCATE_HTAB _IOWR(KVMIO, 0xa7, __u32) #define KVM_CREATE_SPAPR_TCE _IOW(KVMIO, 0xa8, struct kvm_create_spapr_tce) +#define KVM_CREATE_SPAPR_TCE_64 _IOW(KVMIO, 0xa8, \ + struct kvm_create_spapr_tce_64) /* Available with KVM_CAP_RMA */ #define KVM_ALLOCATE_RMA _IOR(KVMIO, 0xa9, struct kvm_allocate_rma) /* Available with KVM_CAP_PPC_HTAB_FD */ diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index db2dd33..b866374 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -109,8 +109,8 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) /* cancel outstanding work queue item */ while (!list_empty(&vcpu->async_pf.queue)) { struct kvm_async_pf *work = - list_entry(vcpu->async_pf.queue.next, - typeof(*work), queue); + list_first_entry(&vcpu->async_pf.queue, + typeof(*work), queue); list_del(&work->queue); #ifdef CONFIG_KVM_ASYNC_PF_SYNC @@ -127,8 +127,8 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) spin_lock(&vcpu->async_pf.lock); while (!list_empty(&vcpu->async_pf.done)) { struct kvm_async_pf *work = - list_entry(vcpu->async_pf.done.next, - typeof(*work), link); + list_first_entry(&vcpu->async_pf.done, + typeof(*work), link); list_del(&work->link); kmem_cache_free(async_pf_cache, work); } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a11cfd2..1eae052 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -72,11 +72,11 @@ module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR); /* Default doubles per-vcpu halt_poll_ns. */ static unsigned int halt_poll_ns_grow = 2; -module_param(halt_poll_ns_grow, int, S_IRUGO); +module_param(halt_poll_ns_grow, uint, S_IRUGO | S_IWUSR); /* Default resets per-vcpu halt_poll_ns . */ static unsigned int halt_poll_ns_shrink; -module_param(halt_poll_ns_shrink, int, S_IRUGO); +module_param(halt_poll_ns_shrink, uint, S_IRUGO | S_IWUSR); /* * Ordering of locks: @@ -620,13 +620,10 @@ void *kvm_kvzalloc(unsigned long size) static void kvm_destroy_devices(struct kvm *kvm) { - struct list_head *node, *tmp; + struct kvm_device *dev, *tmp; - list_for_each_safe(node, tmp, &kvm->devices) { - struct kvm_device *dev = - list_entry(node, struct kvm_device, vm_node); - - list_del(node); + list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) { + list_del(&dev->vm_node); dev->ops->destroy(dev); } } @@ -1437,11 +1434,17 @@ kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, { unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); - if (addr == KVM_HVA_ERR_RO_BAD) + if (addr == KVM_HVA_ERR_RO_BAD) { + if (writable) + *writable = false; return KVM_PFN_ERR_RO_FAULT; + } - if (kvm_is_error_hva(addr)) + if (kvm_is_error_hva(addr)) { + if (writable) + *writable = false; return KVM_PFN_NOSLOT; + } /* Do not map writable pfn in the readonly memslot. */ if (writable && memslot_is_readonly(slot)) { @@ -1943,14 +1946,15 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty); static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) { - int old, val; + unsigned int old, val, grow; old = val = vcpu->halt_poll_ns; + grow = READ_ONCE(halt_poll_ns_grow); /* 10us base */ - if (val == 0 && halt_poll_ns_grow) + if (val == 0 && grow) val = 10000; else - val *= halt_poll_ns_grow; + val *= grow; vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); @@ -1958,13 +1962,14 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu) { - int old, val; + unsigned int old, val, shrink; old = val = vcpu->halt_poll_ns; - if (halt_poll_ns_shrink == 0) + shrink = READ_ONCE(halt_poll_ns_shrink); + if (shrink == 0) val = 0; else - val /= halt_poll_ns_shrink; + val /= shrink; vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old); |