diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-12-08 16:02:38 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-12-08 16:02:38 (GMT) |
commit | ed9216c1717a3f3738a77908aff78995ea69e7ff (patch) | |
tree | c6b5ace7c333dabbf1d94074a13a98244bcdfb26 | |
parent | d7fc02c7bae7b1cf69269992cf880a43a350cdaa (diff) | |
parent | d5696725b2a4c59503f5e0bc33adeee7f30cd45b (diff) | |
download | linux-fsl-qoriq-ed9216c1717a3f3738a77908aff78995ea69e7ff.tar.xz |
Merge branch 'kvm-updates/2.6.33' of git://git.kernel.org/pub/scm/virt/kvm/kvm
* 'kvm-updates/2.6.33' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (84 commits)
KVM: VMX: Fix comparison of guest efer with stale host value
KVM: s390: Fix prefix register checking in arch/s390/kvm/sigp.c
KVM: Drop user return notifier when disabling virtualization on a cpu
KVM: VMX: Disable unrestricted guest when EPT disabled
KVM: x86 emulator: limit instructions to 15 bytes
KVM: s390: Make psw available on all exits, not just a subset
KVM: x86: Add KVM_GET/SET_VCPU_EVENTS
KVM: VMX: Report unexpected simultaneous exceptions as internal errors
KVM: Allow internal errors reported to userspace to carry extra data
KVM: Reorder IOCTLs in main kvm.h
KVM: x86: Polish exception injection via KVM_SET_GUEST_DEBUG
KVM: only clear irq_source_id if irqchip is present
KVM: x86: disallow KVM_{SET,GET}_LAPIC without allocated in-kernel lapic
KVM: x86: disallow multiple KVM_CREATE_IRQCHIP
KVM: VMX: Remove vmx->msr_offset_efer
KVM: MMU: update invlpg handler comment
KVM: VMX: move CR3/PDPTR update to vmx_set_cr3
KVM: remove duplicated task_switch check
KVM: powerpc: Fix BUILD_BUG_ON condition
KVM: VMX: Use shared msr infrastructure
...
Trivial conflicts due to new Kconfig options in arch/Kconfig and kernel/Makefile
45 files changed, 2936 insertions, 1579 deletions
diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt index 5a4bc8cf..e1a1141 100644 --- a/Documentation/kvm/api.txt +++ b/Documentation/kvm/api.txt @@ -593,6 +593,115 @@ struct kvm_irqchip { } chip; }; +4.27 KVM_XEN_HVM_CONFIG + +Capability: KVM_CAP_XEN_HVM +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_xen_hvm_config (in) +Returns: 0 on success, -1 on error + +Sets the MSR that the Xen HVM guest uses to initialize its hypercall +page, and provides the starting address and size of the hypercall +blobs in userspace. When the guest writes the MSR, kvm copies one +page of a blob (32- or 64-bit, depending on the vcpu mode) to guest +memory. + +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; + +4.27 KVM_GET_CLOCK + +Capability: KVM_CAP_ADJUST_CLOCK +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_clock_data (out) +Returns: 0 on success, -1 on error + +Gets the current timestamp of kvmclock as seen by the current guest. In +conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios +such as migration. + +struct kvm_clock_data { + __u64 clock; /* kvmclock current value */ + __u32 flags; + __u32 pad[9]; +}; + +4.28 KVM_SET_CLOCK + +Capability: KVM_CAP_ADJUST_CLOCK +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_clock_data (in) +Returns: 0 on success, -1 on error + +Sets the current timestamp of kvmclock to the valued specific in its parameter. +In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios +such as migration. + +struct kvm_clock_data { + __u64 clock; /* kvmclock current value */ + __u32 flags; + __u32 pad[9]; +}; + +4.29 KVM_GET_VCPU_EVENTS + +Capability: KVM_CAP_VCPU_EVENTS +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_vcpu_event (out) +Returns: 0 on success, -1 on error + +Gets currently pending exceptions, interrupts, and NMIs as well as related +states of the vcpu. + +struct kvm_vcpu_events { + struct { + __u8 injected; + __u8 nr; + __u8 has_error_code; + __u8 pad; + __u32 error_code; + } exception; + struct { + __u8 injected; + __u8 nr; + __u8 soft; + __u8 pad; + } interrupt; + struct { + __u8 injected; + __u8 pending; + __u8 masked; + __u8 pad; + } nmi; + __u32 sipi_vector; + __u32 flags; /* must be zero */ +}; + +4.30 KVM_SET_VCPU_EVENTS + +Capability: KVM_CAP_VCPU_EVENTS +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_vcpu_event (in) +Returns: 0 on success, -1 on error + +Set pending exceptions, interrupts, and NMIs as well as related states of the +vcpu. + +See KVM_GET_VCPU_EVENTS for the data structure. + + 5. The kvm_run structure Application code obtains a pointer to the kvm_run structure by diff --git a/arch/Kconfig b/arch/Kconfig index eef3bbb..d828758 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -83,6 +83,13 @@ config KRETPROBES def_bool y depends on KPROBES && HAVE_KRETPROBES +config USER_RETURN_NOTIFIER + bool + depends on HAVE_USER_RETURN_NOTIFIER + help + Provide a kernel-internal notification when a cpu is about to + switch to user mode. + config HAVE_IOREMAP_PROT bool @@ -132,5 +139,7 @@ config HAVE_HW_BREAKPOINT select ANON_INODES select PERF_EVENTS +config HAVE_USER_RETURN_NOTIFIER + bool source "kernel/gcov/Kconfig" diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h index 18a7e49..bc90c75 100644 --- a/arch/ia64/include/asm/kvm.h +++ b/arch/ia64/include/asm/kvm.h @@ -60,6 +60,7 @@ struct kvm_ioapic_state { #define KVM_IRQCHIP_PIC_MASTER 0 #define KVM_IRQCHIP_PIC_SLAVE 1 #define KVM_IRQCHIP_IOAPIC 2 +#define KVM_NR_IRQCHIPS 3 #define KVM_CONTEXT_SIZE 8*1024 diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h index d9b6325..a362e67 100644 --- a/arch/ia64/include/asm/kvm_host.h +++ b/arch/ia64/include/asm/kvm_host.h @@ -475,7 +475,6 @@ struct kvm_arch { struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; int iommu_flags; - struct hlist_head irq_ack_notifier_list; unsigned long irq_sources_bitmap; unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; diff --git a/arch/ia64/kvm/Makefile b/arch/ia64/kvm/Makefile index 0bb99b7..1089b3e 100644 --- a/arch/ia64/kvm/Makefile +++ b/arch/ia64/kvm/Makefile @@ -49,7 +49,7 @@ EXTRA_CFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/ EXTRA_AFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/ common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o) + coalesced_mmio.o irq_comm.o assigned-dev.o) ifeq ($(CONFIG_IOMMU_API),y) common-objs += $(addprefix ../../../virt/kvm/, iommu.o) diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 0ad09f0..5fdeec5 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -124,7 +124,7 @@ long ia64_pal_vp_create(u64 *vpd, u64 *host_iva, u64 *opt_handler) static DEFINE_SPINLOCK(vp_lock); -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { long status; long tmp_base; @@ -137,7 +137,7 @@ void kvm_arch_hardware_enable(void *garbage) slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT); local_irq_restore(saved_psr); if (slot < 0) - return; + return -EINVAL; spin_lock(&vp_lock); status = ia64_pal_vp_init_env(kvm_vsa_base ? @@ -145,7 +145,7 @@ void kvm_arch_hardware_enable(void *garbage) __pa(kvm_vm_buffer), KVM_VM_BUFFER_BASE, &tmp_base); if (status != 0) { printk(KERN_WARNING"kvm: Failed to Enable VT Support!!!!\n"); - return ; + return -EINVAL; } if (!kvm_vsa_base) { @@ -154,6 +154,8 @@ void kvm_arch_hardware_enable(void *garbage) } spin_unlock(&vp_lock); ia64_ptr_entry(0x3, slot); + + return 0; } void kvm_arch_hardware_disable(void *garbage) @@ -851,8 +853,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_IOAPIC: - memcpy(&chip->chip.ioapic, ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); + r = kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -868,9 +869,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_IOAPIC: - memcpy(ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); + r = kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -944,7 +943,7 @@ long kvm_arch_vm_ioctl(struct file *filp, { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; - int r = -EINVAL; + int r = -ENOTTY; switch (ioctl) { case KVM_SET_MEMORY_REGION: { @@ -985,10 +984,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { __s32 status; - mutex_lock(&kvm->irq_lock); status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); - mutex_unlock(&kvm->irq_lock); if (ioctl == KVM_IRQ_LINE_STATUS) { irq_event.status = status; if (copy_to_user(argp, &irq_event, diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 2a4551f..5902bbc 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -78,8 +78,9 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu) return r; } -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { + return 0; } void kvm_arch_hardware_disable(void *garbage) @@ -421,7 +422,7 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { default: - r = -EINVAL; + r = -ENOTTY; } return r; diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h index 806ef67..8167d42 100644 --- a/arch/powerpc/kvm/timing.h +++ b/arch/powerpc/kvm/timing.h @@ -51,7 +51,7 @@ static inline void kvmppc_account_exit_stat(struct kvm_vcpu *vcpu, int type) /* The BUILD_BUG_ON below breaks in funny ways, commented out * for now ... -BenH - BUILD_BUG_ON(__builtin_constant_p(type)); + BUILD_BUG_ON(!__builtin_constant_p(type)); */ switch (type) { case EXT_INTR_EXITS: diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h index 3dfcaeb..82b32a1 100644 --- a/arch/s390/include/asm/kvm.h +++ b/arch/s390/include/asm/kvm.h @@ -1,6 +1,5 @@ #ifndef __LINUX_KVM_S390_H #define __LINUX_KVM_S390_H - /* * asm-s390/kvm.h - KVM s390 specific structures and definitions * @@ -15,6 +14,8 @@ */ #include <linux/types.h> +#define __KVM_S390 + /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { /* general purpose regs for s390 */ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 07ced89..f8bcaef 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -74,9 +74,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { static unsigned long long *facilities; /* Section: not file related */ -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { /* every s390 is virtualization enabled ;-) */ + return 0; } void kvm_arch_hardware_disable(void *garbage) @@ -116,10 +117,16 @@ long kvm_arch_dev_ioctl(struct file *filp, int kvm_dev_ioctl_check_extension(long ext) { + int r; + switch (ext) { + case KVM_CAP_S390_PSW: + r = 1; + break; default: - return 0; + r = 0; } + return r; } /* Section: vm related */ @@ -150,7 +157,7 @@ long kvm_arch_vm_ioctl(struct file *filp, break; } default: - r = -EINVAL; + r = -ENOTTY; } return r; @@ -419,8 +426,10 @@ static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw) vcpu_load(vcpu); if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING) rc = -EBUSY; - else - vcpu->arch.sie_block->gpsw = psw; + else { + vcpu->run->psw_mask = psw.mask; + vcpu->run->psw_addr = psw.addr; + } vcpu_put(vcpu); return rc; } @@ -508,9 +517,6 @@ rerun_vcpu: switch (kvm_run->exit_reason) { case KVM_EXIT_S390_SIEIC: - vcpu->arch.sie_block->gpsw.mask = kvm_run->s390_sieic.mask; - vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr; - break; case KVM_EXIT_UNKNOWN: case KVM_EXIT_INTR: case KVM_EXIT_S390_RESET: @@ -519,6 +525,9 @@ rerun_vcpu: BUG(); } + vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask; + vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr; + might_fault(); do { @@ -538,8 +547,6 @@ rerun_vcpu: /* intercept cannot be handled in-kernel, prepare kvm-run */ kvm_run->exit_reason = KVM_EXIT_S390_SIEIC; kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode; - kvm_run->s390_sieic.mask = vcpu->arch.sie_block->gpsw.mask; - kvm_run->s390_sieic.addr = vcpu->arch.sie_block->gpsw.addr; kvm_run->s390_sieic.ipa = vcpu->arch.sie_block->ipa; kvm_run->s390_sieic.ipb = vcpu->arch.sie_block->ipb; rc = 0; @@ -551,6 +558,9 @@ rerun_vcpu: rc = 0; } + kvm_run->psw_mask = vcpu->arch.sie_block->gpsw.mask; + kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr; + if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 40c8c67..15ee111 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -188,9 +188,9 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, /* make sure that the new value is valid memory */ address = address & 0x7fffe000u; - if ((copy_from_guest(vcpu, &tmp, - (u64) (address + vcpu->arch.sie_block->gmsor) , 1)) || - (copy_from_guest(vcpu, &tmp, (u64) (address + + if ((copy_from_user(&tmp, (void __user *) + (address + vcpu->arch.sie_block->gmsor) , 1)) || + (copy_from_user(&tmp, (void __user *)(address + vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) { *reg |= SIGP_STAT_INVALID_PARAMETER; return 1; /* invalid parameter */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 178084b..1b2182b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -51,6 +51,7 @@ config X86 select HAVE_KERNEL_LZMA select HAVE_HW_BREAKPOINT select HAVE_ARCH_KMEMCHECK + select HAVE_USER_RETURN_NOTIFIER config OUTPUT_FORMAT string diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 4a5fe91..950df43 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -19,6 +19,8 @@ #define __KVM_HAVE_MSIX #define __KVM_HAVE_MCE #define __KVM_HAVE_PIT_STATE2 +#define __KVM_HAVE_XEN_HVM +#define __KVM_HAVE_VCPU_EVENTS /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -79,6 +81,7 @@ struct kvm_ioapic_state { #define KVM_IRQCHIP_PIC_MASTER 0 #define KVM_IRQCHIP_PIC_SLAVE 1 #define KVM_IRQCHIP_IOAPIC 2 +#define KVM_NR_IRQCHIPS 3 /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { @@ -250,4 +253,31 @@ struct kvm_reinject_control { __u8 pit_reinject; __u8 reserved[31]; }; + +/* for KVM_GET/SET_VCPU_EVENTS */ +struct kvm_vcpu_events { + struct { + __u8 injected; + __u8 nr; + __u8 has_error_code; + __u8 pad; + __u32 error_code; + } exception; + struct { + __u8 injected; + __u8 nr; + __u8 soft; + __u8 pad; + } interrupt; + struct { + __u8 injected; + __u8 pending; + __u8 masked; + __u8 pad; + } nmi; + __u32 sipi_vector; + __u32 flags; + __u32 reserved[10]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index b7ed2c4..7c18e12 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -129,7 +129,7 @@ struct decode_cache { u8 seg_override; unsigned int d; unsigned long regs[NR_VCPU_REGS]; - unsigned long eip; + unsigned long eip, eip_orig; /* modrm */ u8 modrm; u8 modrm_mod; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d838922..4f865e8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -354,7 +354,6 @@ struct kvm_vcpu_arch { unsigned int time_offset; struct page *time_page; - bool singlestep; /* guest is single stepped by KVM */ bool nmi_pending; bool nmi_injected; @@ -371,6 +370,10 @@ struct kvm_vcpu_arch { u64 mcg_status; u64 mcg_ctl; u64 *mce_banks; + + /* used for guest single stepping over the given code position */ + u16 singlestep_cs; + unsigned long singlestep_rip; }; struct kvm_mem_alias { @@ -397,7 +400,6 @@ struct kvm_arch{ struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; - struct hlist_head irq_ack_notifier_list; int vapics_in_nmi_mode; unsigned int tss_addr; @@ -410,8 +412,10 @@ struct kvm_arch{ gpa_t ept_identity_map_addr; unsigned long irq_sources_bitmap; - unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; u64 vm_init_tsc; + s64 kvmclock_offset; + + struct kvm_xen_hvm_config xen_hvm_config; }; struct kvm_vm_stat { @@ -461,7 +465,7 @@ struct descriptor_table { struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ - void (*hardware_enable)(void *dummy); /* __init */ + int (*hardware_enable)(void *dummy); void (*hardware_disable)(void *dummy); void (*check_processor_compatibility)(void *rtn); int (*hardware_setup)(void); /* __init */ @@ -477,8 +481,8 @@ struct kvm_x86_ops { void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); - int (*set_guest_debug)(struct kvm_vcpu *vcpu, - struct kvm_guest_debug *dbg); + void (*set_guest_debug)(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg); int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); @@ -506,8 +510,8 @@ struct kvm_x86_ops { void (*tlb_flush)(struct kvm_vcpu *vcpu); - void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run); - int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu); + void (*run)(struct kvm_vcpu *vcpu); + int (*handle_exit)(struct kvm_vcpu *vcpu); void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); @@ -519,6 +523,8 @@ struct kvm_x86_ops { bool has_error_code, u32 error_code); int (*interrupt_allowed)(struct kvm_vcpu *vcpu); int (*nmi_allowed)(struct kvm_vcpu *vcpu); + bool (*get_nmi_mask)(struct kvm_vcpu *vcpu); + void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked); void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); @@ -568,7 +574,7 @@ enum emulation_result { #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) -int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run, +int emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, u16 error_code, int emulation_type); void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context); void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); @@ -585,9 +591,9 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); struct x86_emulate_ctxt; -int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, +int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, +int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in, int size, unsigned long count, int down, gva_t address, int rep, unsigned port); void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); @@ -616,6 +622,9 @@ void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data); +unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu); +void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); + void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2, @@ -802,4 +811,7 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); +void kvm_define_shared_msr(unsigned index, u32 msr); +void kvm_set_shared_msr(unsigned index, u64 val, u64 mask); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 85574b7..1fecb7e 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -57,7 +57,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u16 intercept_dr_write; u32 intercept_exceptions; u64 intercept; - u8 reserved_1[44]; + u8 reserved_1[42]; + u16 pause_filter_count; u64 iopm_base_pa; u64 msrpm_base_pa; u64 tsc_offset; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index d27d0a2..375c917 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -83,6 +83,7 @@ struct thread_info { #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ #define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */ +#define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* 32bit process */ #define TIF_FORK 18 /* ret_from_fork */ @@ -107,6 +108,7 @@ struct thread_info { #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_MCE_NOTIFY (1 << TIF_MCE_NOTIFY) +#define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_FORK (1 << TIF_FORK) @@ -142,13 +144,14 @@ struct thread_info { /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ - (_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME) + (_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME | \ + _TIF_USER_RETURN_NOTIFY) /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC) -#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW +#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG) #define PREEMPT_ACTIVE 0x10000000 diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 272514c..2b49454 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -56,6 +56,7 @@ #define SECONDARY_EXEC_ENABLE_VPID 0x00000020 #define SECONDARY_EXEC_WBINVD_EXITING 0x00000040 #define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080 +#define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400 #define PIN_BASED_EXT_INTR_MASK 0x00000001 @@ -144,6 +145,8 @@ enum vmcs_field { VM_ENTRY_INSTRUCTION_LEN = 0x0000401a, TPR_THRESHOLD = 0x0000401c, SECONDARY_VM_EXEC_CONTROL = 0x0000401e, + PLE_GAP = 0x00004020, + PLE_WINDOW = 0x00004022, VM_INSTRUCTION_ERROR = 0x00004400, VM_EXIT_REASON = 0x00004402, VM_EXIT_INTR_INFO = 0x00004404, @@ -248,6 +251,7 @@ enum vmcs_field { #define EXIT_REASON_MSR_READ 31 #define EXIT_REASON_MSR_WRITE 32 #define EXIT_REASON_MWAIT_INSTRUCTION 36 +#define EXIT_REASON_PAUSE_INSTRUCTION 40 #define EXIT_REASON_MCE_DURING_VMENTRY 41 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43 #define EXIT_REASON_APIC_ACCESS 44 diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 744508e..5e2ba63 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -9,6 +9,7 @@ #include <linux/pm.h> #include <linux/clockchips.h> #include <linux/random.h> +#include <linux/user-return-notifier.h> #include <trace/events/power.h> #include <linux/hw_breakpoint.h> #include <asm/system.h> @@ -209,6 +210,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, */ memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } + propagate_user_return_notify(prev_p, next_p); } int sys_fork(struct pt_regs *regs) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index fbf3b07c..74fe6d8 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -19,6 +19,7 @@ #include <linux/stddef.h> #include <linux/personality.h> #include <linux/uaccess.h> +#include <linux/user-return-notifier.h> #include <asm/processor.h> #include <asm/ucontext.h> @@ -863,6 +864,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) if (current->replacement_session_keyring) key_replace_session_keyring(); } + if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) + fire_user_return_notifiers(); #ifdef CONFIG_X86_32 clear_thread_flag(TIF_IRET); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index b84e571..4cd4983 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select HAVE_KVM_IRQCHIP select HAVE_KVM_EVENTFD select KVM_APIC_ARCHITECTURE + select USER_RETURN_NOTIFIER ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 0e7fe78..31a7035 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -6,7 +6,8 @@ CFLAGS_svm.o := -I. CFLAGS_vmx.o := -I. kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o eventfd.o) + coalesced_mmio.o irq_comm.o eventfd.o \ + assigned-dev.o) kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o) kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1be5cd6..7e8faea 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -75,6 +75,8 @@ #define Group (1<<14) /* Bits 3:5 of modrm byte extend opcode */ #define GroupDual (1<<15) /* Alternate decoding of mod == 3 */ #define GroupMask 0xff /* Group number stored in bits 0:7 */ +/* Misc flags */ +#define No64 (1<<28) /* Source 2 operand type */ #define Src2None (0<<29) #define Src2CL (1<<29) @@ -92,19 +94,23 @@ static u32 opcode_table[256] = { /* 0x00 - 0x07 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, /* 0x08 - 0x0F */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack | No64, 0, /* 0x10 - 0x17 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, /* 0x18 - 0x1F */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, /* 0x20 - 0x27 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, @@ -133,7 +139,8 @@ static u32 opcode_table[256] = { DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, /* 0x60 - 0x67 */ - 0, 0, 0, DstReg | SrcMem32 | ModRM | Mov /* movsxd (x86/64) */ , + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, + 0, DstReg | SrcMem32 | ModRM | Mov /* movsxd (x86/64) */ , 0, 0, 0, 0, /* 0x68 - 0x6F */ SrcImm | Mov | Stack, 0, SrcImmByte | Mov | Stack, 0, @@ -158,7 +165,7 @@ static u32 opcode_table[256] = { /* 0x90 - 0x97 */ DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, /* 0x98 - 0x9F */ - 0, 0, SrcImm | Src2Imm16, 0, + 0, 0, SrcImm | Src2Imm16 | No64, 0, ImplicitOps | Stack, ImplicitOps | Stack, 0, 0, /* 0xA0 - 0xA7 */ ByteOp | DstReg | SrcMem | Mov | MemAbs, DstReg | SrcMem | Mov | MemAbs, @@ -185,7 +192,7 @@ static u32 opcode_table[256] = { ByteOp | DstMem | SrcImm | ModRM | Mov, DstMem | SrcImm | ModRM | Mov, /* 0xC8 - 0xCF */ 0, 0, 0, ImplicitOps | Stack, - ImplicitOps, SrcImmByte, ImplicitOps, ImplicitOps, + ImplicitOps, SrcImmByte, ImplicitOps | No64, ImplicitOps, /* 0xD0 - 0xD7 */ ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, @@ -198,7 +205,7 @@ static u32 opcode_table[256] = { ByteOp | SrcImmUByte, SrcImmUByte, /* 0xE8 - 0xEF */ SrcImm | Stack, SrcImm | ImplicitOps, - SrcImmU | Src2Imm16, SrcImmByte | ImplicitOps, + SrcImmU | Src2Imm16 | No64, SrcImmByte | ImplicitOps, SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* 0xF0 - 0xF7 */ @@ -244,11 +251,13 @@ static u32 twobyte_table[256] = { /* 0x90 - 0x9F */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0xA0 - 0xA7 */ - 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, + ImplicitOps | Stack, ImplicitOps | Stack, + 0, DstMem | SrcReg | ModRM | BitOp, DstMem | SrcReg | Src2ImmByte | ModRM, DstMem | SrcReg | Src2CL | ModRM, 0, 0, /* 0xA8 - 0xAF */ - 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, + ImplicitOps | Stack, ImplicitOps | Stack, + 0, DstMem | SrcReg | ModRM | BitOp, DstMem | SrcReg | Src2ImmByte | ModRM, DstMem | SrcReg | Src2CL | ModRM, ModRM, 0, @@ -613,6 +622,9 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, { int rc = 0; + /* x86 instructions are limited to 15 bytes. */ + if (eip + size - ctxt->decode.eip_orig > 15) + return X86EMUL_UNHANDLEABLE; eip += ctxt->cs_base; while (size--) { rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++); @@ -871,7 +883,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) /* Shadow copy of register state. Committed on successful emulation. */ memset(c, 0, sizeof(struct decode_cache)); - c->eip = kvm_rip_read(ctxt->vcpu); + c->eip = c->eip_orig = kvm_rip_read(ctxt->vcpu); ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS); memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); @@ -962,6 +974,11 @@ done_prefixes: } } + if (mode == X86EMUL_MODE_PROT64 && (c->d & No64)) { + kvm_report_emulation_failure(ctxt->vcpu, "invalid x86/64 instruction");; + return -1; + } + if (c->d & Group) { group = c->d & GroupMask; c->modrm = insn_fetch(u8, 1, c->eip); @@ -1186,6 +1203,69 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt, return rc; } +static void emulate_push_sreg(struct x86_emulate_ctxt *ctxt, int seg) +{ + struct decode_cache *c = &ctxt->decode; + struct kvm_segment segment; + + kvm_x86_ops->get_segment(ctxt->vcpu, &segment, seg); + + c->src.val = segment.selector; + emulate_push(ctxt); +} + +static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, int seg) +{ + struct decode_cache *c = &ctxt->decode; + unsigned long selector; + int rc; + + rc = emulate_pop(ctxt, ops, &selector, c->op_bytes); + if (rc != 0) + return rc; + + rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)selector, 1, seg); + return rc; +} + +static void emulate_pusha(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + unsigned long old_esp = c->regs[VCPU_REGS_RSP]; + int reg = VCPU_REGS_RAX; + + while (reg <= VCPU_REGS_RDI) { + (reg == VCPU_REGS_RSP) ? + (c->src.val = old_esp) : (c->src.val = c->regs[reg]); + + emulate_push(ctxt); + ++reg; + } +} + +static int emulate_popa(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + struct decode_cache *c = &ctxt->decode; + int rc = 0; + int reg = VCPU_REGS_RDI; + + while (reg >= VCPU_REGS_RAX) { + if (reg == VCPU_REGS_RSP) { + register_address_increment(c, &c->regs[VCPU_REGS_RSP], + c->op_bytes); + --reg; + } + + rc = emulate_pop(ctxt, ops, &c->regs[reg], c->op_bytes); + if (rc != 0) + break; + --reg; + } + return rc; +} + static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { @@ -1707,18 +1787,45 @@ special_insn: add: /* add */ emulate_2op_SrcV("add", c->src, c->dst, ctxt->eflags); break; + case 0x06: /* push es */ + emulate_push_sreg(ctxt, VCPU_SREG_ES); + break; + case 0x07: /* pop es */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_ES); + if (rc != 0) + goto done; + break; case 0x08 ... 0x0d: or: /* or */ emulate_2op_SrcV("or", c->src, c->dst, ctxt->eflags); break; + case 0x0e: /* push cs */ + emulate_push_sreg(ctxt, VCPU_SREG_CS); + break; case 0x10 ... 0x15: adc: /* adc */ emulate_2op_SrcV("adc", c->src, c->dst, ctxt->eflags); break; + case 0x16: /* push ss */ + emulate_push_sreg(ctxt, VCPU_SREG_SS); + break; + case 0x17: /* pop ss */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_SS); + if (rc != 0) + goto done; + break; case 0x18 ... 0x1d: sbb: /* sbb */ emulate_2op_SrcV("sbb", c->src, c->dst, ctxt->eflags); break; + case 0x1e: /* push ds */ + emulate_push_sreg(ctxt, VCPU_SREG_DS); + break; + case 0x1f: /* pop ds */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_DS); + if (rc != 0) + goto done; + break; case 0x20 ... 0x25: and: /* and */ emulate_2op_SrcV("and", c->src, c->dst, ctxt->eflags); @@ -1750,6 +1857,14 @@ special_insn: if (rc != 0) goto done; break; + case 0x60: /* pusha */ + emulate_pusha(ctxt); + break; + case 0x61: /* popa */ + rc = emulate_popa(ctxt, ops); + if (rc != 0) + goto done; + break; case 0x63: /* movsxd */ if (ctxt->mode != X86EMUL_MODE_PROT64) goto cannot_emulate; @@ -1761,7 +1876,7 @@ special_insn: break; case 0x6c: /* insb */ case 0x6d: /* insw/insd */ - if (kvm_emulate_pio_string(ctxt->vcpu, NULL, + if (kvm_emulate_pio_string(ctxt->vcpu, 1, (c->d & ByteOp) ? 1 : c->op_bytes, c->rep_prefix ? @@ -1777,7 +1892,7 @@ special_insn: return 0; case 0x6e: /* outsb */ case 0x6f: /* outsw/outsd */ - if (kvm_emulate_pio_string(ctxt->vcpu, NULL, + if (kvm_emulate_pio_string(ctxt->vcpu, 0, (c->d & ByteOp) ? 1 : c->op_bytes, c->rep_prefix ? @@ -2070,7 +2185,7 @@ special_insn: case 0xef: /* out (e/r)ax,dx */ port = c->regs[VCPU_REGS_RDX]; io_dir_in = 0; - do_io: if (kvm_emulate_pio(ctxt->vcpu, NULL, io_dir_in, + do_io: if (kvm_emulate_pio(ctxt->vcpu, io_dir_in, (c->d & ByteOp) ? 1 : c->op_bytes, port) != 0) { c->eip = saved_eip; @@ -2297,6 +2412,14 @@ twobyte_insn: jmp_rel(c, c->src.val); c->dst.type = OP_NONE; break; + case 0xa0: /* push fs */ + emulate_push_sreg(ctxt, VCPU_SREG_FS); + break; + case 0xa1: /* pop fs */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_FS); + if (rc != 0) + goto done; + break; case 0xa3: bt: /* bt */ c->dst.type = OP_NONE; @@ -2308,6 +2431,14 @@ twobyte_insn: case 0xa5: /* shld cl, r, r/m */ emulate_2op_cl("shld", c->src2, c->src, c->dst, ctxt->eflags); break; + case 0xa8: /* push gs */ + emulate_push_sreg(ctxt, VCPU_SREG_GS); + break; + case 0xa9: /* pop gs */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_GS); + if (rc != 0) + goto done; + break; case 0xab: bts: /* bts */ /* only subword offset */ diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 144e7f6..fab7440 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -688,10 +688,8 @@ static void __inject_pit_timer_intr(struct kvm *kvm) struct kvm_vcpu *vcpu; int i; - mutex_lock(&kvm->irq_lock); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); - mutex_unlock(&kvm->irq_lock); /* * Provides NMI watchdog support via Virtual Wire mode. diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 01f1516..d057c0c 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -38,7 +38,15 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq) s->isr_ack |= (1 << irq); if (s != &s->pics_state->pics[0]) irq += 8; + /* + * We are dropping lock while calling ack notifiers since ack + * notifier callbacks for assigned devices call into PIC recursively. + * Other interrupt may be delivered to PIC while lock is dropped but + * it should be safe since PIC state is already updated at this stage. + */ + spin_unlock(&s->pics_state->lock); kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq); + spin_lock(&s->pics_state->lock); } void kvm_pic_clear_isr_ack(struct kvm *kvm) @@ -176,16 +184,18 @@ int kvm_pic_set_irq(void *opaque, int irq, int level) static inline void pic_intack(struct kvm_kpic_state *s, int irq) { s->isr |= 1 << irq; - if (s->auto_eoi) { - if (s->rotate_on_auto_eoi) - s->priority_add = (irq + 1) & 7; - pic_clear_isr(s, irq); - } /* * We don't clear a level sensitive interrupt here */ if (!(s->elcr & (1 << irq))) s->irr &= ~(1 << irq); + + if (s->auto_eoi) { + if (s->rotate_on_auto_eoi) + s->priority_add = (irq + 1) & 7; + pic_clear_isr(s, irq); + } + } int kvm_pic_read_irq(struct kvm *kvm) @@ -225,22 +235,11 @@ int kvm_pic_read_irq(struct kvm *kvm) void kvm_pic_reset(struct kvm_kpic_state *s) { - int irq, irqbase, n; + int irq; struct kvm *kvm = s->pics_state->irq_request_opaque; struct kvm_vcpu *vcpu0 = kvm->bsp_vcpu; + u8 irr = s->irr, isr = s->imr; - if (s == &s->pics_state->pics[0]) - irqbase = 0; - else - irqbase = 8; - - for (irq = 0; irq < PIC_NUM_PINS/2; irq++) { - if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0)) - if (s->irr & (1 << irq) || s->isr & (1 << irq)) { - n = irq + irqbase; - kvm_notify_acked_irq(kvm, SELECT_PIC(n), n); - } - } s->last_irr = 0; s->irr = 0; s->imr = 0; @@ -256,6 +255,13 @@ void kvm_pic_reset(struct kvm_kpic_state *s) s->rotate_on_auto_eoi = 0; s->special_fully_nested_mode = 0; s->init4 = 0; + + for (irq = 0; irq < PIC_NUM_PINS/2; irq++) { + if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0)) + if (irr & (1 << irq) || isr & (1 << irq)) { + pic_clear_isr(s, irq); + } + } } static void pic_ioport_write(void *opaque, u32 addr, u32 val) @@ -298,9 +304,9 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) priority = get_priority(s, s->isr); if (priority != 8) { irq = (priority + s->priority_add) & 7; - pic_clear_isr(s, irq); if (cmd == 5) s->priority_add = (irq + 1) & 7; + pic_clear_isr(s, irq); pic_update_irq(s->pics_state); } break; diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 7d6058a..be399e2 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -71,6 +71,7 @@ struct kvm_pic { int output; /* intr from master PIC */ struct kvm_io_device dev; void (*ack_notifier)(void *opaque, int irq); + unsigned long irq_states[16]; }; struct kvm_pic *kvm_create_pic(struct kvm *kvm); @@ -85,7 +86,11 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm) static inline int irqchip_in_kernel(struct kvm *kvm) { - return pic_irqchip(kvm) != NULL; + int ret; + + ret = (pic_irqchip(kvm) != NULL); + smp_rmb(); + return ret; } void kvm_pic_reset(struct kvm_kpic_state *s); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 23c2176..cd60c0b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -32,7 +32,6 @@ #include <asm/current.h> #include <asm/apicdef.h> #include <asm/atomic.h> -#include <asm/apicdef.h> #include "kvm_cache_regs.h" #include "irq.h" #include "trace.h" @@ -471,11 +470,8 @@ static void apic_set_eoi(struct kvm_lapic *apic) trigger_mode = IOAPIC_LEVEL_TRIG; else trigger_mode = IOAPIC_EDGE_TRIG; - if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) { - mutex_lock(&apic->vcpu->kvm->irq_lock); + if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); - mutex_unlock(&apic->vcpu->kvm->irq_lock); - } } static void apic_send_ipi(struct kvm_lapic *apic) @@ -504,9 +500,7 @@ static void apic_send_ipi(struct kvm_lapic *apic) irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, irq.vector); - mutex_lock(&apic->vcpu->kvm->irq_lock); kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq); - mutex_unlock(&apic->vcpu->kvm->irq_lock); } static u32 apic_get_tmcct(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 818b92a..4c3e5b2 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2789,7 +2789,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) if (r) goto out; - er = emulate_instruction(vcpu, vcpu->run, cr2, error_code, 0); + er = emulate_instruction(vcpu, cr2, error_code, 0); switch (er) { case EMULATE_DONE: @@ -2800,6 +2800,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) case EMULATE_FAIL: vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; return 0; default: BUG(); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 72558f8..a601713 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -467,7 +467,6 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) level = iterator.level; sptep = iterator.sptep; - /* FIXME: properly handle invlpg on large guest pages */ if (level == PT_PAGE_TABLE_LEVEL || ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) || ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c17404a..3de0b37 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -46,6 +46,7 @@ MODULE_LICENSE("GPL"); #define SVM_FEATURE_NPT (1 << 0) #define SVM_FEATURE_LBRV (1 << 1) #define SVM_FEATURE_SVML (1 << 2) +#define SVM_FEATURE_PAUSE_FILTER (1 << 10) #define NESTED_EXIT_HOST 0 /* Exit handled on host level */ #define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ @@ -53,15 +54,6 @@ MODULE_LICENSE("GPL"); #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) -/* Turn on to get debugging output*/ -/* #define NESTED_DEBUG */ - -#ifdef NESTED_DEBUG -#define nsvm_printk(fmt, args...) printk(KERN_INFO fmt, ## args) -#else -#define nsvm_printk(fmt, args...) do {} while(0) -#endif - static const u32 host_save_user_msrs[] = { #ifdef CONFIG_X86_64 MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, @@ -85,6 +77,9 @@ struct nested_state { /* gpa pointers to the real vectors */ u64 vmcb_msrpm; + /* A VMEXIT is required but not yet emulated */ + bool exit_required; + /* cache for intercepts of the guest */ u16 intercept_cr_read; u16 intercept_cr_write; @@ -112,6 +107,8 @@ struct vcpu_svm { u32 *msrpm; struct nested_state nested; + + bool nmi_singlestep; }; /* enable NPT for AMD64 and X86 with PAE */ @@ -286,7 +283,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); if (!svm->next_rip) { - if (emulate_instruction(vcpu, vcpu->run, 0, 0, EMULTYPE_SKIP) != + if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) != EMULATE_DONE) printk(KERN_DEBUG "%s: NOP\n", __func__); return; @@ -316,7 +313,7 @@ static void svm_hardware_disable(void *garbage) cpu_svm_disable(); } -static void svm_hardware_enable(void *garbage) +static int svm_hardware_enable(void *garbage) { struct svm_cpu_data *svm_data; @@ -325,16 +322,21 @@ static void svm_hardware_enable(void *garbage) struct desc_struct *gdt; int me = raw_smp_processor_id(); + rdmsrl(MSR_EFER, efer); + if (efer & EFER_SVME) + return -EBUSY; + if (!has_svm()) { - printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me); - return; + printk(KERN_ERR "svm_hardware_enable: err EOPNOTSUPP on %d\n", + me); + return -EINVAL; } svm_data = per_cpu(svm_data, me); if (!svm_data) { - printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n", + printk(KERN_ERR "svm_hardware_enable: svm_data is NULL on %d\n", me); - return; + return -EINVAL; } svm_data->asid_generation = 1; @@ -345,11 +347,12 @@ static void svm_hardware_enable(void *garbage) gdt = (struct desc_struct *)gdt_descr.base; svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); - rdmsrl(MSR_EFER, efer); wrmsrl(MSR_EFER, efer | EFER_SVME); wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(svm_data->save_area) << PAGE_SHIFT); + + return 0; } static void svm_cpu_uninit(int cpu) @@ -476,7 +479,7 @@ static __init int svm_hardware_setup(void) kvm_enable_efer_bits(EFER_SVME); } - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) goto err; @@ -510,7 +513,7 @@ static __exit void svm_hardware_unsetup(void) { int cpu; - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); @@ -625,11 +628,12 @@ static void init_vmcb(struct vcpu_svm *svm) save->rip = 0x0000fff0; svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; - /* - * cr0 val on cpu init should be 0x60000010, we enable cpu - * cache by default. the orderly way is to enable cache in bios. + /* This is the guest-visible cr0 value. + * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. */ - save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP; + svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; + kvm_set_cr0(&svm->vcpu, svm->vcpu.arch.cr0); + save->cr4 = X86_CR4_PAE; /* rdx = ?? */ @@ -644,8 +648,6 @@ static void init_vmcb(struct vcpu_svm *svm) control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK| INTERCEPT_CR3_MASK); save->g_pat = 0x0007040600070406ULL; - /* enable caching because the QEMU Bios doesn't enable it */ - save->cr0 = X86_CR0_ET; save->cr3 = 0; save->cr4 = 0; } @@ -654,6 +656,11 @@ static void init_vmcb(struct vcpu_svm *svm) svm->nested.vmcb = 0; svm->vcpu.arch.hflags = 0; + if (svm_has(SVM_FEATURE_PAUSE_FILTER)) { + control->pause_filter_count = 3000; + control->intercept |= (1ULL << INTERCEPT_PAUSE); + } + enable_gif(svm); } @@ -758,14 +765,13 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) int i; if (unlikely(cpu != vcpu->cpu)) { - u64 tsc_this, delta; + u64 delta; /* * Make sure that the guest sees a monotonically * increasing TSC. */ - rdtscll(tsc_this); - delta = vcpu->arch.host_tsc - tsc_this; + delta = vcpu->arch.host_tsc - native_read_tsc(); svm->vmcb->control.tsc_offset += delta; if (is_nested(svm)) svm->nested.hsave->control.tsc_offset += delta; @@ -787,7 +793,7 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); - rdtscll(vcpu->arch.host_tsc); + vcpu->arch.host_tsc = native_read_tsc(); } static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) @@ -1045,7 +1051,7 @@ static void update_db_intercept(struct kvm_vcpu *vcpu) svm->vmcb->control.intercept_exceptions &= ~((1 << DB_VECTOR) | (1 << BP_VECTOR)); - if (vcpu->arch.singlestep) + if (svm->nmi_singlestep) svm->vmcb->control.intercept_exceptions |= (1 << DB_VECTOR); if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { @@ -1060,26 +1066,16 @@ static void update_db_intercept(struct kvm_vcpu *vcpu) vcpu->guest_debug = 0; } -static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) +static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - int old_debug = vcpu->guest_debug; struct vcpu_svm *svm = to_svm(vcpu); - vcpu->guest_debug = dbg->control; - - update_db_intercept(vcpu); - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) svm->vmcb->save.dr7 = dbg->arch.debugreg[7]; else svm->vmcb->save.dr7 = vcpu->arch.dr7; - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - svm->vmcb->save.rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - else if (old_debug & KVM_GUESTDBG_SINGLESTEP) - svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - - return 0; + update_db_intercept(vcpu); } static void load_host_msrs(struct kvm_vcpu *vcpu) @@ -1180,7 +1176,7 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value, } } -static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int pf_interception(struct vcpu_svm *svm) { u64 fault_address; u32 error_code; @@ -1194,17 +1190,19 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); } -static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int db_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + if (!(svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && - !svm->vcpu.arch.singlestep) { + !svm->nmi_singlestep) { kvm_queue_exception(&svm->vcpu, DB_VECTOR); return 1; } - if (svm->vcpu.arch.singlestep) { - svm->vcpu.arch.singlestep = false; + if (svm->nmi_singlestep) { + svm->nmi_singlestep = false; if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); @@ -1223,25 +1221,27 @@ static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int bp_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + kvm_run->exit_reason = KVM_EXIT_DEBUG; kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; kvm_run->debug.arch.exception = BP_VECTOR; return 0; } -static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int ud_interception(struct vcpu_svm *svm) { int er; - er = emulate_instruction(&svm->vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD); + er = emulate_instruction(&svm->vcpu, 0, 0, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } -static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int nm_interception(struct vcpu_svm *svm) { svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); if (!(svm->vcpu.arch.cr0 & X86_CR0_TS)) @@ -1251,7 +1251,7 @@ static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int mc_interception(struct vcpu_svm *svm) { /* * On an #MC intercept the MCE handler is not called automatically in @@ -1264,8 +1264,10 @@ static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int shutdown_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + /* * VMCB is undefined after a SHUTDOWN intercept * so reinitialize it. @@ -1277,7 +1279,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 0; } -static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int io_interception(struct vcpu_svm *svm) { u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ int size, in, string; @@ -1291,7 +1293,7 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) if (string) { if (emulate_instruction(&svm->vcpu, - kvm_run, 0, 0, 0) == EMULATE_DO_MMIO) + 0, 0, 0) == EMULATE_DO_MMIO) return 0; return 1; } @@ -1301,33 +1303,33 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; skip_emulated_instruction(&svm->vcpu); - return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port); + return kvm_emulate_pio(&svm->vcpu, in, size, port); } -static int nmi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int nmi_interception(struct vcpu_svm *svm) { return 1; } -static int intr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int intr_interception(struct vcpu_svm *svm) { ++svm->vcpu.stat.irq_exits; return 1; } -static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int nop_on_interception(struct vcpu_svm *svm) { return 1; } -static int halt_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int halt_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 1; skip_emulated_instruction(&svm->vcpu); return kvm_emulate_halt(&svm->vcpu); } -static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int vmmcall_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); @@ -1378,8 +1380,15 @@ static inline int nested_svm_intr(struct vcpu_svm *svm) svm->vmcb->control.exit_code = SVM_EXIT_INTR; - if (nested_svm_exit_handled(svm)) { - nsvm_printk("VMexit -> INTR\n"); + if (svm->nested.intercept & 1ULL) { + /* + * The #vmexit can't be emulated here directly because this + * code path runs with irqs and preemtion disabled. A + * #vmexit emulation might sleep. Only signal request for + * the #vmexit here. + */ + svm->nested.exit_required = true; + trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); return 1; } @@ -1390,10 +1399,7 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx) { struct page *page; - down_read(¤t->mm->mmap_sem); page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT); - up_read(¤t->mm->mmap_sem); - if (is_error_page(page)) goto error; @@ -1532,14 +1538,12 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) } default: { u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); - nsvm_printk("exit code: 0x%x\n", exit_code); if (svm->nested.intercept & exit_bits) vmexit = NESTED_EXIT_DONE; } } if (vmexit == NESTED_EXIT_DONE) { - nsvm_printk("#VMEXIT reason=%04x\n", exit_code); nested_svm_vmexit(svm); } @@ -1584,6 +1588,12 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; + trace_kvm_nested_vmexit_inject(vmcb->control.exit_code, + vmcb->control.exit_info_1, + vmcb->control.exit_info_2, + vmcb->control.exit_int_info, + vmcb->control.exit_int_info_err); + nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0); if (!nested_vmcb) return 1; @@ -1617,6 +1627,22 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->control.exit_info_2 = vmcb->control.exit_info_2; nested_vmcb->control.exit_int_info = vmcb->control.exit_int_info; nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err; + + /* + * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have + * to make sure that we do not lose injected events. So check event_inj + * here and copy it to exit_int_info if it is valid. + * Exit_int_info and event_inj can't be both valid because the case + * below only happens on a VMRUN instruction intercept which has + * no valid exit_int_info set. + */ + if (vmcb->control.event_inj & SVM_EVTINJ_VALID) { + struct vmcb_control_area *nc = &nested_vmcb->control; + + nc->exit_int_info = vmcb->control.event_inj; + nc->exit_int_info_err = vmcb->control.event_inj_err; + } + nested_vmcb->control.tlb_ctl = 0; nested_vmcb->control.event_inj = 0; nested_vmcb->control.event_inj_err = 0; @@ -1628,10 +1654,6 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) /* Restore the original control entries */ copy_vmcb_control_area(vmcb, hsave); - /* Kill any pending exceptions */ - if (svm->vcpu.arch.exception.pending == true) - nsvm_printk("WARNING: Pending Exception\n"); - kvm_clear_exception_queue(&svm->vcpu); kvm_clear_interrupt_queue(&svm->vcpu); @@ -1702,6 +1724,12 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) /* nested_vmcb is our indicator if nested SVM is activated */ svm->nested.vmcb = svm->vmcb->save.rax; + trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb, + nested_vmcb->save.rip, + nested_vmcb->control.int_ctl, + nested_vmcb->control.event_inj, + nested_vmcb->control.nested_ctl); + /* Clear internal status */ kvm_clear_exception_queue(&svm->vcpu); kvm_clear_interrupt_queue(&svm->vcpu); @@ -1789,28 +1817,15 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) svm->nested.intercept = nested_vmcb->control.intercept; force_new_asid(&svm->vcpu); - svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info; - svm->vmcb->control.exit_int_info_err = nested_vmcb->control.exit_int_info_err; svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; - if (nested_vmcb->control.int_ctl & V_IRQ_MASK) { - nsvm_printk("nSVM Injecting Interrupt: 0x%x\n", - nested_vmcb->control.int_ctl); - } if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) svm->vcpu.arch.hflags |= HF_VINTR_MASK; else svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; - nsvm_printk("nSVM exit_int_info: 0x%x | int_state: 0x%x\n", - nested_vmcb->control.exit_int_info, - nested_vmcb->control.int_state); - svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; svm->vmcb->control.int_state = nested_vmcb->control.int_state; svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; - if (nested_vmcb->control.event_inj & SVM_EVTINJ_VALID) - nsvm_printk("Injecting Event: 0x%x\n", - nested_vmcb->control.event_inj); svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; @@ -1837,7 +1852,7 @@ static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip; } -static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int vmload_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; @@ -1857,7 +1872,7 @@ static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int vmsave_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; @@ -1877,10 +1892,8 @@ static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int vmrun_interception(struct vcpu_svm *svm) { - nsvm_printk("VMrun\n"); - if (nested_svm_check_permissions(svm)) return 1; @@ -1907,7 +1920,7 @@ failed: return 1; } -static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int stgi_interception(struct vcpu_svm *svm) { if (nested_svm_check_permissions(svm)) return 1; @@ -1920,7 +1933,7 @@ static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int clgi_interception(struct vcpu_svm *svm) { if (nested_svm_check_permissions(svm)) return 1; @@ -1937,10 +1950,12 @@ static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int invlpga_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - nsvm_printk("INVLPGA\n"); + + trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX], + vcpu->arch.regs[VCPU_REGS_RAX]); /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]); @@ -1950,15 +1965,21 @@ static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int invalid_op_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int skinit_interception(struct vcpu_svm *svm) { + trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]); + kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } -static int task_switch_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int invalid_op_interception(struct vcpu_svm *svm) +{ + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; +} + +static int task_switch_interception(struct vcpu_svm *svm) { u16 tss_selector; int reason; @@ -2008,14 +2029,14 @@ static int task_switch_interception(struct vcpu_svm *svm, return kvm_task_switch(&svm->vcpu, tss_selector, reason); } -static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int cpuid_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; kvm_emulate_cpuid(&svm->vcpu); return 1; } -static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int iret_interception(struct vcpu_svm *svm) { ++svm->vcpu.stat.nmi_window_exits; svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET); @@ -2023,26 +2044,27 @@ static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int invlpg_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int invlpg_interception(struct vcpu_svm *svm) { - if (emulate_instruction(&svm->vcpu, kvm_run, 0, 0, 0) != EMULATE_DONE) + if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE) pr_unimpl(&svm->vcpu, "%s: failed\n", __func__); return 1; } -static int emulate_on_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int emulate_on_interception(struct vcpu_svm *svm) { - if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE) + if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE) pr_unimpl(&svm->vcpu, "%s: failed\n", __func__); return 1; } -static int cr8_write_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int cr8_write_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + u8 cr8_prev = kvm_get_cr8(&svm->vcpu); /* instruction emulation calls kvm_set_cr8() */ - emulate_instruction(&svm->vcpu, NULL, 0, 0, 0); + emulate_instruction(&svm->vcpu, 0, 0, 0); if (irqchip_in_kernel(svm->vcpu.kvm)) { svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK; return 1; @@ -2128,7 +2150,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) return 0; } -static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int rdmsr_interception(struct vcpu_svm *svm) { u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; u64 data; @@ -2221,7 +2243,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) return 0; } -static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int wrmsr_interception(struct vcpu_svm *svm) { u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u) @@ -2237,17 +2259,18 @@ static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int msr_interception(struct vcpu_svm *svm) { if (svm->vmcb->control.exit_info_1) - return wrmsr_interception(svm, kvm_run); + return wrmsr_interception(svm); else - return rdmsr_interception(svm, kvm_run); + return rdmsr_interception(svm); } -static int interrupt_window_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int interrupt_window_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + svm_clear_vintr(svm); svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; /* @@ -2265,8 +2288,13 @@ static int interrupt_window_interception(struct vcpu_svm *svm, return 1; } -static int (*svm_exit_handlers[])(struct vcpu_svm *svm, - struct kvm_run *kvm_run) = { +static int pause_interception(struct vcpu_svm *svm) +{ + kvm_vcpu_on_spin(&(svm->vcpu)); + return 1; +} + +static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR0] = emulate_on_interception, [SVM_EXIT_READ_CR3] = emulate_on_interception, [SVM_EXIT_READ_CR4] = emulate_on_interception, @@ -2301,6 +2329,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, [SVM_EXIT_INVD] = emulate_on_interception, + [SVM_EXIT_PAUSE] = pause_interception, [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, [SVM_EXIT_INVLPGA] = invlpga_interception, @@ -2314,26 +2343,36 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_VMSAVE] = vmsave_interception, [SVM_EXIT_STGI] = stgi_interception, [SVM_EXIT_CLGI] = clgi_interception, - [SVM_EXIT_SKINIT] = invalid_op_interception, + [SVM_EXIT_SKINIT] = skinit_interception, [SVM_EXIT_WBINVD] = emulate_on_interception, [SVM_EXIT_MONITOR] = invalid_op_interception, [SVM_EXIT_MWAIT] = invalid_op_interception, [SVM_EXIT_NPF] = pf_interception, }; -static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +static int handle_exit(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; trace_kvm_exit(exit_code, svm->vmcb->save.rip); + if (unlikely(svm->nested.exit_required)) { + nested_svm_vmexit(svm); + svm->nested.exit_required = false; + + return 1; + } + if (is_nested(svm)) { int vmexit; - nsvm_printk("nested handle_exit: 0x%x | 0x%lx | 0x%lx | 0x%lx\n", - exit_code, svm->vmcb->control.exit_info_1, - svm->vmcb->control.exit_info_2, svm->vmcb->save.rip); + trace_kvm_nested_vmexit(svm->vmcb->save.rip, exit_code, + svm->vmcb->control.exit_info_1, + svm->vmcb->control.exit_info_2, + svm->vmcb->control.exit_int_info, + svm->vmcb->control.exit_int_info_err); vmexit = nested_svm_exit_special(svm); @@ -2383,7 +2422,7 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) return 0; } - return svm_exit_handlers[exit_code](svm, kvm_run); + return svm_exit_handlers[exit_code](svm); } static void reload_tss(struct kvm_vcpu *vcpu) @@ -2460,20 +2499,47 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu) !(svm->vcpu.arch.hflags & HF_NMI_MASK); } +static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return !!(svm->vcpu.arch.hflags & HF_NMI_MASK); +} + +static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (masked) { + svm->vcpu.arch.hflags |= HF_NMI_MASK; + svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET); + } else { + svm->vcpu.arch.hflags &= ~HF_NMI_MASK; + svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET); + } +} + static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - return (vmcb->save.rflags & X86_EFLAGS_IF) && - !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && - gif_set(svm) && - !(is_nested(svm) && (svm->vcpu.arch.hflags & HF_VINTR_MASK)); + int ret; + + if (!gif_set(svm) || + (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)) + return 0; + + ret = !!(vmcb->save.rflags & X86_EFLAGS_IF); + + if (is_nested(svm)) + return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK); + + return ret; } static void enable_irq_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - nsvm_printk("Trying to open IRQ window\n"); nested_svm_intr(svm); @@ -2498,7 +2564,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) /* Something prevents NMI from been injected. Single step over possible problem (IRET or exception injection or interrupt shadow) */ - vcpu->arch.singlestep = true; + svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); update_db_intercept(vcpu); } @@ -2588,13 +2654,20 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) #define R "e" #endif -static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void svm_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); u16 fs_selector; u16 gs_selector; u16 ldt_selector; + /* + * A vmexit emulation is required before the vcpu can be executed + * again. + */ + if (unlikely(svm->nested.exit_required)) + return; + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; @@ -2893,6 +2966,8 @@ static struct kvm_x86_ops svm_x86_ops = { .queue_exception = svm_queue_exception, .interrupt_allowed = svm_interrupt_allowed, .nmi_allowed = svm_nmi_allowed, + .get_nmi_mask = svm_get_nmi_mask, + .set_nmi_mask = svm_set_nmi_mask, .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 0d480e7..816e044 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -349,6 +349,171 @@ TRACE_EVENT(kvm_apic_accept_irq, __entry->coalesced ? " (coalesced)" : "") ); +/* + * Tracepoint for nested VMRUN + */ +TRACE_EVENT(kvm_nested_vmrun, + TP_PROTO(__u64 rip, __u64 vmcb, __u64 nested_rip, __u32 int_ctl, + __u32 event_inj, bool npt), + TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, npt), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u64, vmcb ) + __field( __u64, nested_rip ) + __field( __u32, int_ctl ) + __field( __u32, event_inj ) + __field( bool, npt ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->vmcb = vmcb; + __entry->nested_rip = nested_rip; + __entry->int_ctl = int_ctl; + __entry->event_inj = event_inj; + __entry->npt = npt; + ), + + TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x " + "event_inj: 0x%08x npt: %s\n", + __entry->rip, __entry->vmcb, __entry->nested_rip, + __entry->int_ctl, __entry->event_inj, + __entry->npt ? "on" : "off") +); + +/* + * Tracepoint for #VMEXIT while nested + */ +TRACE_EVENT(kvm_nested_vmexit, + TP_PROTO(__u64 rip, __u32 exit_code, + __u64 exit_info1, __u64 exit_info2, + __u32 exit_int_info, __u32 exit_int_info_err), + TP_ARGS(rip, exit_code, exit_info1, exit_info2, + exit_int_info, exit_int_info_err), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u32, exit_code ) + __field( __u64, exit_info1 ) + __field( __u64, exit_info2 ) + __field( __u32, exit_int_info ) + __field( __u32, exit_int_info_err ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->exit_code = exit_code; + __entry->exit_info1 = exit_info1; + __entry->exit_info2 = exit_info2; + __entry->exit_int_info = exit_int_info; + __entry->exit_int_info_err = exit_int_info_err; + ), + TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx " + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n", + __entry->rip, + ftrace_print_symbols_seq(p, __entry->exit_code, + kvm_x86_ops->exit_reasons_str), + __entry->exit_info1, __entry->exit_info2, + __entry->exit_int_info, __entry->exit_int_info_err) +); + +/* + * Tracepoint for #VMEXIT reinjected to the guest + */ +TRACE_EVENT(kvm_nested_vmexit_inject, + TP_PROTO(__u32 exit_code, + __u64 exit_info1, __u64 exit_info2, + __u32 exit_int_info, __u32 exit_int_info_err), + TP_ARGS(exit_code, exit_info1, exit_info2, + exit_int_info, exit_int_info_err), + + TP_STRUCT__entry( + __field( __u32, exit_code ) + __field( __u64, exit_info1 ) + __field( __u64, exit_info2 ) + __field( __u32, exit_int_info ) + __field( __u32, exit_int_info_err ) + ), + + TP_fast_assign( + __entry->exit_code = exit_code; + __entry->exit_info1 = exit_info1; + __entry->exit_info2 = exit_info2; + __entry->exit_int_info = exit_int_info; + __entry->exit_int_info_err = exit_int_info_err; + ), + + TP_printk("reason: %s ext_inf1: 0x%016llx " + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n", + ftrace_print_symbols_seq(p, __entry->exit_code, + kvm_x86_ops->exit_reasons_str), + __entry->exit_info1, __entry->exit_info2, + __entry->exit_int_info, __entry->exit_int_info_err) +); + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_nested_intr_vmexit, + TP_PROTO(__u64 rip), + TP_ARGS(rip), + + TP_STRUCT__entry( + __field( __u64, rip ) + ), + + TP_fast_assign( + __entry->rip = rip + ), + + TP_printk("rip: 0x%016llx\n", __entry->rip) +); + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_invlpga, + TP_PROTO(__u64 rip, int asid, u64 address), + TP_ARGS(rip, asid, address), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( int, asid ) + __field( __u64, address ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->asid = asid; + __entry->address = address; + ), + + TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx\n", + __entry->rip, __entry->asid, __entry->address) +); + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_skinit, + TP_PROTO(__u64 rip, __u32 slb), + TP_ARGS(rip, slb), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u32, slb ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->slb = slb; + ), + + TP_printk("rip: 0x%016llx slb: 0x%08x\n", + __entry->rip, __entry->slb) +); + #endif /* _TRACE_KVM_H */ /* This part must be outside protection */ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ed53b42..d4918d6 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -61,12 +61,37 @@ module_param_named(unrestricted_guest, static int __read_mostly emulate_invalid_guest_state = 0; module_param(emulate_invalid_guest_state, bool, S_IRUGO); +/* + * These 2 parameters are used to config the controls for Pause-Loop Exiting: + * ple_gap: upper bound on the amount of time between two successive + * executions of PAUSE in a loop. Also indicate if ple enabled. + * According to test, this time is usually small than 41 cycles. + * ple_window: upper bound on the amount of time a guest is allowed to execute + * in a PAUSE loop. Tests indicate that most spinlocks are held for + * less than 2^12 cycles + * Time is measured based on a counter that runs at the same rate as the TSC, + * refer SDM volume 3b section 21.6.13 & 22.1.3. + */ +#define KVM_VMX_DEFAULT_PLE_GAP 41 +#define KVM_VMX_DEFAULT_PLE_WINDOW 4096 +static int ple_gap = KVM_VMX_DEFAULT_PLE_GAP; +module_param(ple_gap, int, S_IRUGO); + +static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; +module_param(ple_window, int, S_IRUGO); + struct vmcs { u32 revision_id; u32 abort; char data[0]; }; +struct shared_msr_entry { + unsigned index; + u64 data; + u64 mask; +}; + struct vcpu_vmx { struct kvm_vcpu vcpu; struct list_head local_vcpus_link; @@ -74,13 +99,12 @@ struct vcpu_vmx { int launched; u8 fail; u32 idt_vectoring_info; - struct kvm_msr_entry *guest_msrs; - struct kvm_msr_entry *host_msrs; + struct shared_msr_entry *guest_msrs; int nmsrs; int save_nmsrs; - int msr_offset_efer; #ifdef CONFIG_X86_64 - int msr_offset_kernel_gs_base; + u64 msr_host_kernel_gs_base; + u64 msr_guest_kernel_gs_base; #endif struct vmcs *vmcs; struct { @@ -88,7 +112,6 @@ struct vcpu_vmx { u16 fs_sel, gs_sel, ldt_sel; int gs_ldt_reload_needed; int fs_reload_needed; - int guest_efer_loaded; } host_state; struct { int vm86_active; @@ -107,7 +130,6 @@ struct vcpu_vmx { } rmode; int vpid; bool emulation_required; - enum emulation_result invalid_state_emulation_result; /* Support for vnmi-less CPUs */ int soft_vnmi_blocked; @@ -176,6 +198,8 @@ static struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; +static u64 host_efer; + static void ept_save_pdptrs(struct kvm_vcpu *vcpu); /* @@ -184,28 +208,12 @@ static void ept_save_pdptrs(struct kvm_vcpu *vcpu); */ static const u32 vmx_msr_index[] = { #ifdef CONFIG_X86_64 - MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, MSR_KERNEL_GS_BASE, + MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif MSR_EFER, MSR_K6_STAR, }; #define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) -static void load_msrs(struct kvm_msr_entry *e, int n) -{ - int i; - - for (i = 0; i < n; ++i) - wrmsrl(e[i].index, e[i].data); -} - -static void save_msrs(struct kvm_msr_entry *e, int n) -{ - int i; - - for (i = 0; i < n; ++i) - rdmsrl(e[i].index, e[i].data); -} - static inline int is_page_fault(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | @@ -320,6 +328,12 @@ static inline int cpu_has_vmx_unrestricted_guest(void) SECONDARY_EXEC_UNRESTRICTED_GUEST; } +static inline int cpu_has_vmx_ple(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_PAUSE_LOOP_EXITING; +} + static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm) { return flexpriority_enabled && @@ -348,7 +362,7 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) int i; for (i = 0; i < vmx->nmsrs; ++i) - if (vmx->guest_msrs[i].index == msr) + if (vmx_msr_index[vmx->guest_msrs[i].index] == msr) return i; return -1; } @@ -379,7 +393,7 @@ static inline void __invept(int ext, u64 eptp, gpa_t gpa) : : "a" (&operand), "c" (ext) : "cc", "memory"); } -static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) +static struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -570,17 +584,12 @@ static void reload_tss(void) load_TR_desc(); } -static void load_transition_efer(struct vcpu_vmx *vmx) +static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - int efer_offset = vmx->msr_offset_efer; - u64 host_efer; u64 guest_efer; u64 ignore_bits; - if (efer_offset < 0) - return; - host_efer = vmx->host_msrs[efer_offset].data; - guest_efer = vmx->guest_msrs[efer_offset].data; + guest_efer = vmx->vcpu.arch.shadow_efer; /* * NX is emulated; LMA and LME handled by hardware; SCE meaninless @@ -593,27 +602,17 @@ static void load_transition_efer(struct vcpu_vmx *vmx) if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - if ((guest_efer & ~ignore_bits) == (host_efer & ~ignore_bits)) - return; - - vmx->host_state.guest_efer_loaded = 1; guest_efer &= ~ignore_bits; guest_efer |= host_efer & ignore_bits; - wrmsrl(MSR_EFER, guest_efer); - vmx->vcpu.stat.efer_reload++; -} - -static void reload_host_efer(struct vcpu_vmx *vmx) -{ - if (vmx->host_state.guest_efer_loaded) { - vmx->host_state.guest_efer_loaded = 0; - load_msrs(vmx->host_msrs + vmx->msr_offset_efer, 1); - } + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + return true; } static void vmx_save_host_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + int i; if (vmx->host_state.loaded) return; @@ -650,13 +649,15 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) #endif #ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) - save_msrs(vmx->host_msrs + - vmx->msr_offset_kernel_gs_base, 1); - + if (is_long_mode(&vmx->vcpu)) { + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + } #endif - load_msrs(vmx->guest_msrs, vmx->save_nmsrs); - load_transition_efer(vmx); + for (i = 0; i < vmx->save_nmsrs; ++i) + kvm_set_shared_msr(vmx->guest_msrs[i].index, + vmx->guest_msrs[i].data, + vmx->guest_msrs[i].mask); } static void __vmx_load_host_state(struct vcpu_vmx *vmx) @@ -684,9 +685,12 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) local_irq_restore(flags); } reload_tss(); - save_msrs(vmx->guest_msrs, vmx->save_nmsrs); - load_msrs(vmx->host_msrs, vmx->save_nmsrs); - reload_host_efer(vmx); +#ifdef CONFIG_X86_64 + if (is_long_mode(&vmx->vcpu)) { + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + } +#endif } static void vmx_load_host_state(struct vcpu_vmx *vmx) @@ -877,19 +881,14 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, /* * Swap MSR entry in host/guest MSR entry array. */ -#ifdef CONFIG_X86_64 static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) { - struct kvm_msr_entry tmp; + struct shared_msr_entry tmp; tmp = vmx->guest_msrs[to]; vmx->guest_msrs[to] = vmx->guest_msrs[from]; vmx->guest_msrs[from] = tmp; - tmp = vmx->host_msrs[to]; - vmx->host_msrs[to] = vmx->host_msrs[from]; - vmx->host_msrs[from] = tmp; } -#endif /* * Set up the vmcs to automatically save and restore system @@ -898,15 +897,13 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) */ static void setup_msrs(struct vcpu_vmx *vmx) { - int save_nmsrs; + int save_nmsrs, index; unsigned long *msr_bitmap; vmx_load_host_state(vmx); save_nmsrs = 0; #ifdef CONFIG_X86_64 if (is_long_mode(&vmx->vcpu)) { - int index; - index = __find_msr_index(vmx, MSR_SYSCALL_MASK); if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); @@ -916,9 +913,6 @@ static void setup_msrs(struct vcpu_vmx *vmx) index = __find_msr_index(vmx, MSR_CSTAR); if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_KERNEL_GS_BASE); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); /* * MSR_K6_STAR is only needed on long mode guests, and only * if efer.sce is enabled. @@ -928,13 +922,11 @@ static void setup_msrs(struct vcpu_vmx *vmx) move_msr_up(vmx, index, save_nmsrs++); } #endif - vmx->save_nmsrs = save_nmsrs; + index = __find_msr_index(vmx, MSR_EFER); + if (index >= 0 && update_transition_efer(vmx, index)) + move_msr_up(vmx, index, save_nmsrs++); -#ifdef CONFIG_X86_64 - vmx->msr_offset_kernel_gs_base = - __find_msr_index(vmx, MSR_KERNEL_GS_BASE); -#endif - vmx->msr_offset_efer = __find_msr_index(vmx, MSR_EFER); + vmx->save_nmsrs = save_nmsrs; if (cpu_has_vmx_msr_bitmap()) { if (is_long_mode(&vmx->vcpu)) @@ -976,7 +968,7 @@ static void guest_write_tsc(u64 guest_tsc, u64 host_tsc) static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) { u64 data; - struct kvm_msr_entry *msr; + struct shared_msr_entry *msr; if (!pdata) { printk(KERN_ERR "BUG: get_msr called with NULL pdata\n"); @@ -991,9 +983,13 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) case MSR_GS_BASE: data = vmcs_readl(GUEST_GS_BASE); break; + case MSR_KERNEL_GS_BASE: + vmx_load_host_state(to_vmx(vcpu)); + data = to_vmx(vcpu)->msr_guest_kernel_gs_base; + break; +#endif case MSR_EFER: return kvm_get_msr_common(vcpu, msr_index, pdata); -#endif case MSR_IA32_TSC: data = guest_read_tsc(); break; @@ -1007,6 +1003,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) data = vmcs_readl(GUEST_SYSENTER_ESP); break; default: + vmx_load_host_state(to_vmx(vcpu)); msr = find_msr_entry(to_vmx(vcpu), msr_index); if (msr) { vmx_load_host_state(to_vmx(vcpu)); @@ -1028,7 +1025,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_msr_entry *msr; + struct shared_msr_entry *msr; u64 host_tsc; int ret = 0; @@ -1044,6 +1041,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) case MSR_GS_BASE: vmcs_writel(GUEST_GS_BASE, data); break; + case MSR_KERNEL_GS_BASE: + vmx_load_host_state(vmx); + vmx->msr_guest_kernel_gs_base = data; + break; #endif case MSR_IA32_SYSENTER_CS: vmcs_write32(GUEST_SYSENTER_CS, data); @@ -1097,30 +1098,14 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } -static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) +static void set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - int old_debug = vcpu->guest_debug; - unsigned long flags; - - vcpu->guest_debug = dbg->control; - if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) - vcpu->guest_debug = 0; - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) vmcs_writel(GUEST_DR7, dbg->arch.debugreg[7]); else vmcs_writel(GUEST_DR7, vcpu->arch.dr7); - flags = vmcs_readl(GUEST_RFLAGS); - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - flags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - else if (old_debug & KVM_GUESTDBG_SINGLESTEP) - flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - vmcs_writel(GUEST_RFLAGS, flags); - update_exception_bitmap(vcpu); - - return 0; } static __init int cpu_has_kvm_support(void) @@ -1139,12 +1124,15 @@ static __init int vmx_disabled_by_bios(void) /* locked but not enabled */ } -static void hardware_enable(void *garbage) +static int hardware_enable(void *garbage) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); u64 old; + if (read_cr4() & X86_CR4_VMXE) + return -EBUSY; + INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu)); rdmsrl(MSR_IA32_FEATURE_CONTROL, old); if ((old & (FEATURE_CONTROL_LOCKED | @@ -1159,6 +1147,10 @@ static void hardware_enable(void *garbage) asm volatile (ASM_VMX_VMXON_RAX : : "a"(&phys_addr), "m"(phys_addr) : "memory", "cc"); + + ept_sync_global(); + + return 0; } static void vmclear_local_vcpus(void) @@ -1250,7 +1242,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_WBINVD_EXITING | SECONDARY_EXEC_ENABLE_VPID | SECONDARY_EXEC_ENABLE_EPT | - SECONDARY_EXEC_UNRESTRICTED_GUEST; + SECONDARY_EXEC_UNRESTRICTED_GUEST | + SECONDARY_EXEC_PAUSE_LOOP_EXITING; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -1344,15 +1337,17 @@ static void free_kvm_area(void) { int cpu; - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) { free_vmcs(per_cpu(vmxarea, cpu)); + per_cpu(vmxarea, cpu) = NULL; + } } static __init int alloc_kvm_area(void) { int cpu; - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { struct vmcs *vmcs; vmcs = alloc_vmcs_cpu(cpu); @@ -1394,6 +1389,9 @@ static __init int hardware_setup(void) if (enable_ept && !cpu_has_vmx_ept_2m_page()) kvm_disable_largepages(); + if (!cpu_has_vmx_ple()) + ple_gap = 0; + return alloc_kvm_area(); } @@ -1536,8 +1534,16 @@ continue_rmode: static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); + struct shared_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); + + if (!msr) + return; + /* + * Force kernel_gs_base reloading before EFER changes, as control + * of this msr depends on is_long_mode(). + */ + vmx_load_host_state(to_vmx(vcpu)); vcpu->arch.shadow_efer = efer; if (!msr) return; @@ -1727,6 +1733,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) vmcs_write64(EPT_POINTER, eptp); guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 : vcpu->kvm->arch.ept_identity_map_addr; + ept_load_pdptrs(vcpu); } vmx_flush_tlb(vcpu); @@ -2302,13 +2309,22 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; - if (!enable_ept) + if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; + enable_unrestricted_guest = 0; + } if (!enable_unrestricted_guest) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; + if (!ple_gap) + exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } + if (ple_gap) { + vmcs_write32(PLE_GAP, ple_gap); + vmcs_write32(PLE_WINDOW, ple_window); + } + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf); vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ @@ -2376,10 +2392,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) if (wrmsr_safe(index, data_low, data_high) < 0) continue; data = data_low | ((u64)data_high << 32); - vmx->host_msrs[j].index = index; - vmx->host_msrs[j].reserved = 0; - vmx->host_msrs[j].data = data; - vmx->guest_msrs[j] = vmx->host_msrs[j]; + vmx->guest_msrs[j].index = i; + vmx->guest_msrs[j].data = 0; + vmx->guest_msrs[j].mask = -1ull; ++vmx->nmsrs; } @@ -2510,7 +2525,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx->vcpu.arch.cr0 = 0x60000010; + vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */ vmx_set_cr4(&vmx->vcpu, 0); vmx_set_efer(&vmx->vcpu, 0); @@ -2627,6 +2642,34 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) GUEST_INTR_STATE_NMI)); } +static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) +{ + if (!cpu_has_virtual_nmis()) + return to_vmx(vcpu)->soft_vnmi_blocked; + else + return !!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + GUEST_INTR_STATE_NMI); +} + +static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!cpu_has_virtual_nmis()) { + if (vmx->soft_vnmi_blocked != masked) { + vmx->soft_vnmi_blocked = masked; + vmx->vnmi_blocked_time = 0; + } + } else { + if (masked) + vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + else + vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + } +} + static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && @@ -2659,7 +2702,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) - if (emulate_instruction(vcpu, NULL, 0, 0, 0) == EMULATE_DONE) + if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE) return 1; /* * Forward all other exceptions that are valid in real mode. @@ -2710,15 +2753,16 @@ static void kvm_machine_check(void) #endif } -static int handle_machine_check(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_machine_check(struct kvm_vcpu *vcpu) { /* already handled by vcpu_run */ return 1; } -static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_exception(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_run *kvm_run = vcpu->run; u32 intr_info, ex_no, error_code; unsigned long cr2, rip, dr6; u32 vect_info; @@ -2728,12 +2772,17 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) intr_info = vmcs_read32(VM_EXIT_INTR_INFO); if (is_machine_check(intr_info)) - return handle_machine_check(vcpu, kvm_run); + return handle_machine_check(vcpu); if ((vect_info & VECTORING_INFO_VALID_MASK) && - !is_page_fault(intr_info)) - printk(KERN_ERR "%s: unexpected, vectoring info 0x%x " - "intr info 0x%x\n", __func__, vect_info, intr_info); + !is_page_fault(intr_info)) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX; + vcpu->run->internal.ndata = 2; + vcpu->run->internal.data[0] = vect_info; + vcpu->run->internal.data[1] = intr_info; + return 0; + } if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR) return 1; /* already handled by vmx_vcpu_run() */ @@ -2744,7 +2793,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } if (is_invalid_opcode(intr_info)) { - er = emulate_instruction(vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD); + er = emulate_instruction(vcpu, 0, 0, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(vcpu, UD_VECTOR); return 1; @@ -2803,20 +2852,19 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 0; } -static int handle_external_interrupt(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int handle_external_interrupt(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; return 1; } -static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_triple_fault(struct kvm_vcpu *vcpu) { - kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; } -static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_io(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; int size, in, string; @@ -2827,8 +2875,7 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) string = (exit_qualification & 16) != 0; if (string) { - if (emulate_instruction(vcpu, - kvm_run, 0, 0, 0) == EMULATE_DO_MMIO) + if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO) return 0; return 1; } @@ -2838,7 +2885,7 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) port = exit_qualification >> 16; skip_emulated_instruction(vcpu); - return kvm_emulate_pio(vcpu, kvm_run, in, size, port); + return kvm_emulate_pio(vcpu, in, size, port); } static void @@ -2852,7 +2899,7 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) hypercall[2] = 0xc1; } -static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_cr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification, val; int cr; @@ -2887,7 +2934,7 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; if (cr8_prev <= cr8) return 1; - kvm_run->exit_reason = KVM_EXIT_SET_TPR; + vcpu->run->exit_reason = KVM_EXIT_SET_TPR; return 0; } }; @@ -2922,13 +2969,13 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) default: break; } - kvm_run->exit_reason = 0; + vcpu->run->exit_reason = 0; pr_unimpl(vcpu, "unhandled control register: op %d cr %d\n", (int)(exit_qualification >> 4) & 3, cr); return 0; } -static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_dr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; unsigned long val; @@ -2944,13 +2991,13 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) * guest debugging itself. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { - kvm_run->debug.arch.dr6 = vcpu->arch.dr6; - kvm_run->debug.arch.dr7 = dr; - kvm_run->debug.arch.pc = + vcpu->run->debug.arch.dr6 = vcpu->arch.dr6; + vcpu->run->debug.arch.dr7 = dr; + vcpu->run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + vmcs_readl(GUEST_RIP); - kvm_run->debug.arch.exception = DB_VECTOR; - kvm_run->exit_reason = KVM_EXIT_DEBUG; + vcpu->run->debug.arch.exception = DB_VECTOR; + vcpu->run->exit_reason = KVM_EXIT_DEBUG; return 0; } else { vcpu->arch.dr7 &= ~DR7_GD; @@ -3016,13 +3063,13 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_cpuid(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_cpuid(struct kvm_vcpu *vcpu) { kvm_emulate_cpuid(vcpu); return 1; } -static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; u64 data; @@ -3041,7 +3088,7 @@ static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_wrmsr(struct kvm_vcpu *vcpu) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u) @@ -3058,14 +3105,12 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { return 1; } -static int handle_interrupt_window(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int handle_interrupt_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; @@ -3081,34 +3126,34 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu, * possible */ if (!irqchip_in_kernel(vcpu->kvm) && - kvm_run->request_interrupt_window && + vcpu->run->request_interrupt_window && !kvm_cpu_has_interrupt(vcpu)) { - kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; + vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; return 0; } return 1; } -static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_halt(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); return kvm_emulate_halt(vcpu); } -static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_vmcall(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); kvm_emulate_hypercall(vcpu); return 1; } -static int handle_vmx_insn(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_vmx_insn(struct kvm_vcpu *vcpu) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } -static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_invlpg(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -3117,14 +3162,14 @@ static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_wbinvd(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_wbinvd(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); /* TODO: Add support for VT-d/pass-through device */ return 1; } -static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_apic_access(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; enum emulation_result er; @@ -3133,7 +3178,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) exit_qualification = vmcs_readl(EXIT_QUALIFICATION); offset = exit_qualification & 0xffful; - er = emulate_instruction(vcpu, kvm_run, 0, 0, 0); + er = emulate_instruction(vcpu, 0, 0, 0); if (er != EMULATE_DONE) { printk(KERN_ERR @@ -3144,7 +3189,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_task_switch(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification; @@ -3198,7 +3243,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_ept_violation(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; gpa_t gpa; @@ -3219,8 +3264,8 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vmcs_readl(GUEST_LINEAR_ADDRESS)); printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n", (long unsigned int)exit_qualification); - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_VIOLATION; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; + vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_VIOLATION; return 0; } @@ -3290,7 +3335,7 @@ static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte, } } -static int handle_ept_misconfig(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { u64 sptes[4]; int nr_sptes, i; @@ -3306,13 +3351,13 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i) ept_misconfig_inspect_spte(vcpu, sptes[i-1], i); - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; + vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG; return 0; } -static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_nmi_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; @@ -3325,36 +3370,50 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); enum emulation_result err = EMULATE_DONE; - - local_irq_enable(); - preempt_enable(); + int ret = 1; while (!guest_state_valid(vcpu)) { - err = emulate_instruction(vcpu, kvm_run, 0, 0, 0); + err = emulate_instruction(vcpu, 0, 0, 0); - if (err == EMULATE_DO_MMIO) - break; + if (err == EMULATE_DO_MMIO) { + ret = 0; + goto out; + } if (err != EMULATE_DONE) { kvm_report_emulation_failure(vcpu, "emulation failure"); - break; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + ret = 0; + goto out; } if (signal_pending(current)) - break; + goto out; if (need_resched()) schedule(); } - preempt_disable(); - local_irq_disable(); + vmx->emulation_required = 0; +out: + return ret; +} - vmx->invalid_state_emulation_result = err; +/* + * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE + * exiting, so only get here on cpu with PAUSE-Loop-Exiting. + */ +static int handle_pause(struct kvm_vcpu *vcpu) +{ + skip_emulated_instruction(vcpu); + kvm_vcpu_on_spin(vcpu); + + return 1; } /* @@ -3362,8 +3421,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, * may resume. Otherwise they set the kvm_run parameter to indicate what needs * to be done to userspace and return 0. */ -static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) = { +static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EXCEPTION_NMI] = handle_exception, [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt, [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault, @@ -3394,6 +3452,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, + [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, }; static const int kvm_vmx_max_exit_handlers = @@ -3403,7 +3462,7 @@ static const int kvm_vmx_max_exit_handlers = * The guest has exited. See if we can fix it or if we need userspace * assistance. */ -static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +static int vmx_handle_exit(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exit_reason = vmx->exit_reason; @@ -3411,13 +3470,9 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) trace_kvm_exit(exit_reason, kvm_rip_read(vcpu)); - /* If we need to emulate an MMIO from handle_invalid_guest_state - * we just return 0 */ - if (vmx->emulation_required && emulate_invalid_guest_state) { - if (guest_state_valid(vcpu)) - vmx->emulation_required = 0; - return vmx->invalid_state_emulation_result != EMULATE_DO_MMIO; - } + /* If guest state is invalid, start emulating */ + if (vmx->emulation_required && emulate_invalid_guest_state) + return handle_invalid_guest_state(vcpu); /* Access CR3 don't cause VMExit in paging mode, so we need * to sync with guest real CR3. */ @@ -3425,8 +3480,8 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); if (unlikely(vmx->fail)) { - kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; - kvm_run->fail_entry.hardware_entry_failure_reason + vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; + vcpu->run->fail_entry.hardware_entry_failure_reason = vmcs_read32(VM_INSTRUCTION_ERROR); return 0; } @@ -3459,10 +3514,10 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) if (exit_reason < kvm_vmx_max_exit_handlers && kvm_vmx_exit_handlers[exit_reason]) - return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run); + return kvm_vmx_exit_handlers[exit_reason](vcpu); else { - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = exit_reason; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; + vcpu->run->hw.hardware_exit_reason = exit_reason; } return 0; } @@ -3600,23 +3655,18 @@ static void fixup_rmode_irq(struct vcpu_vmx *vmx) #define Q "l" #endif -static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (enable_ept && is_paging(vcpu)) { - vmcs_writel(GUEST_CR3, vcpu->arch.cr3); - ept_load_pdptrs(vcpu); - } /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) vmx->entry_time = ktime_get(); - /* Handle invalid guest state instead of entering VMX */ - if (vmx->emulation_required && emulate_invalid_guest_state) { - handle_invalid_guest_state(vcpu, kvm_run); + /* Don't enter VMX if guest state is invalid, let the exit handler + start emulation until we arrive back to a valid state */ + if (vmx->emulation_required && emulate_invalid_guest_state) return; - } if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); @@ -3775,7 +3825,6 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) __clear_bit(vmx->vpid, vmx_vpid_bitmap); spin_unlock(&vmx_vpid_lock); vmx_free_vmcs(vcpu); - kfree(vmx->host_msrs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vmx); @@ -3802,10 +3851,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto uninit_vcpu; } - vmx->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!vmx->host_msrs) - goto free_guest_msrs; - vmx->vmcs = alloc_vmcs(); if (!vmx->vmcs) goto free_msrs; @@ -3836,8 +3881,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) free_vmcs: free_vmcs(vmx->vmcs); free_msrs: - kfree(vmx->host_msrs); -free_guest_msrs: kfree(vmx->guest_msrs); uninit_vcpu: kvm_vcpu_uninit(&vmx->vcpu); @@ -3973,6 +4016,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .queue_exception = vmx_queue_exception, .interrupt_allowed = vmx_interrupt_allowed, .nmi_allowed = vmx_nmi_allowed, + .get_nmi_mask = vmx_get_nmi_mask, + .set_nmi_mask = vmx_set_nmi_mask, .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, @@ -3987,7 +4032,12 @@ static struct kvm_x86_ops vmx_x86_ops = { static int __init vmx_init(void) { - int r; + int r, i; + + rdmsrl_safe(MSR_EFER, &host_efer); + + for (i = 0; i < NR_VMX_MSR; ++i) + kvm_define_shared_msr(i, vmx_msr_index[i]); vmx_io_bitmap_a = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_io_bitmap_a) @@ -4049,8 +4099,6 @@ static int __init vmx_init(void) if (bypass_guest_pf) kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull); - ept_sync_global(); - return 0; out3: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4fc8017..9d06896 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -37,6 +37,7 @@ #include <linux/iommu.h> #include <linux/intel-iommu.h> #include <linux/cpufreq.h> +#include <linux/user-return-notifier.h> #include <trace/events/kvm.h> #undef TRACE_INCLUDE_FILE #define CREATE_TRACE_POINTS @@ -88,6 +89,25 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops); int ignore_msrs = 0; module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR); +#define KVM_NR_SHARED_MSRS 16 + +struct kvm_shared_msrs_global { + int nr; + struct kvm_shared_msr { + u32 msr; + u64 value; + } msrs[KVM_NR_SHARED_MSRS]; +}; + +struct kvm_shared_msrs { + struct user_return_notifier urn; + bool registered; + u64 current_value[KVM_NR_SHARED_MSRS]; +}; + +static struct kvm_shared_msrs_global __read_mostly shared_msrs_global; +static DEFINE_PER_CPU(struct kvm_shared_msrs, shared_msrs); + struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, { "pf_guest", VCPU_STAT(pf_guest) }, @@ -124,6 +144,72 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; +static void kvm_on_user_return(struct user_return_notifier *urn) +{ + unsigned slot; + struct kvm_shared_msr *global; + struct kvm_shared_msrs *locals + = container_of(urn, struct kvm_shared_msrs, urn); + + for (slot = 0; slot < shared_msrs_global.nr; ++slot) { + global = &shared_msrs_global.msrs[slot]; + if (global->value != locals->current_value[slot]) { + wrmsrl(global->msr, global->value); + locals->current_value[slot] = global->value; + } + } + locals->registered = false; + user_return_notifier_unregister(urn); +} + +void kvm_define_shared_msr(unsigned slot, u32 msr) +{ + int cpu; + u64 value; + + if (slot >= shared_msrs_global.nr) + shared_msrs_global.nr = slot + 1; + shared_msrs_global.msrs[slot].msr = msr; + rdmsrl_safe(msr, &value); + shared_msrs_global.msrs[slot].value = value; + for_each_online_cpu(cpu) + per_cpu(shared_msrs, cpu).current_value[slot] = value; +} +EXPORT_SYMBOL_GPL(kvm_define_shared_msr); + +static void kvm_shared_msr_cpu_online(void) +{ + unsigned i; + struct kvm_shared_msrs *locals = &__get_cpu_var(shared_msrs); + + for (i = 0; i < shared_msrs_global.nr; ++i) + locals->current_value[i] = shared_msrs_global.msrs[i].value; +} + +void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) +{ + struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs); + + if (((value ^ smsr->current_value[slot]) & mask) == 0) + return; + smsr->current_value[slot] = value; + wrmsrl(shared_msrs_global.msrs[slot].msr, value); + if (!smsr->registered) { + smsr->urn.on_user_return = kvm_on_user_return; + user_return_notifier_register(&smsr->urn); + smsr->registered = true; + } +} +EXPORT_SYMBOL_GPL(kvm_set_shared_msr); + +static void drop_user_return_notifiers(void *ignore) +{ + struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs); + + if (smsr->registered) + kvm_on_user_return(&smsr->urn); +} + unsigned long segment_base(u16 selector) { struct descriptor_table gdt; @@ -485,16 +571,19 @@ static inline u32 bit(int bitno) * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. * * This list is modified at module load time to reflect the - * capabilities of the host cpu. + * capabilities of the host cpu. This capabilities test skips MSRs that are + * kvm-specific. Those are put in the beginning of the list. */ + +#define KVM_SAVE_MSRS_BEGIN 2 static u32 msrs_to_save[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_K6_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif - MSR_IA32_TSC, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA + MSR_IA32_TSC, MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA }; static unsigned num_msrs_to_save; @@ -678,7 +767,8 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) /* With all the info we got, fill in the values */ vcpu->hv_clock.system_time = ts.tv_nsec + - (NSEC_PER_SEC * (u64)ts.tv_sec); + (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset; + /* * The interface expects us to write an even number signaling that the * update is finished. Since the guest won't see the intermediate @@ -836,6 +926,38 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) return 0; } +static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + int lm = is_long_mode(vcpu); + u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64 + : (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32; + u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 + : kvm->arch.xen_hvm_config.blob_size_32; + u32 page_num = data & ~PAGE_MASK; + u64 page_addr = data & PAGE_MASK; + u8 *page; + int r; + + r = -E2BIG; + if (page_num >= blob_size) + goto out; + r = -ENOMEM; + page = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!page) + goto out; + r = -EFAULT; + if (copy_from_user(page, blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE)) + goto out_free; + if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE)) + goto out_free; + r = 0; +out_free: + kfree(page); +out: + return r; +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) { switch (msr) { @@ -951,6 +1073,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) "0x%x data 0x%llx\n", msr, data); break; default: + if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) + return xen_hvm_config(vcpu, data); if (!ignore_msrs) { pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data); @@ -1225,6 +1349,9 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_PIT2: case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: + case KVM_CAP_XEN_HVM: + case KVM_CAP_ADJUST_CLOCK: + case KVM_CAP_VCPU_EVENTS: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -1239,8 +1366,8 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_NR_MEMSLOTS: r = KVM_MEMORY_SLOTS; break; - case KVM_CAP_PV_MMU: - r = !tdp_enabled; + case KVM_CAP_PV_MMU: /* obsolete */ + r = 0; break; case KVM_CAP_IOMMU: r = iommu_found(); @@ -1327,6 +1454,12 @@ out: void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { kvm_x86_ops->vcpu_load(vcpu, cpu); + if (unlikely(per_cpu(cpu_tsc_khz, cpu) == 0)) { + unsigned long khz = cpufreq_quick_get(cpu); + if (!khz) + khz = tsc_khz; + per_cpu(cpu_tsc_khz, cpu) = khz; + } kvm_request_guest_time_update(vcpu); } @@ -1760,6 +1893,61 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, return 0; } +static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + vcpu_load(vcpu); + + events->exception.injected = vcpu->arch.exception.pending; + events->exception.nr = vcpu->arch.exception.nr; + events->exception.has_error_code = vcpu->arch.exception.has_error_code; + events->exception.error_code = vcpu->arch.exception.error_code; + + events->interrupt.injected = vcpu->arch.interrupt.pending; + events->interrupt.nr = vcpu->arch.interrupt.nr; + events->interrupt.soft = vcpu->arch.interrupt.soft; + + events->nmi.injected = vcpu->arch.nmi_injected; + events->nmi.pending = vcpu->arch.nmi_pending; + events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); + + events->sipi_vector = vcpu->arch.sipi_vector; + + events->flags = 0; + + vcpu_put(vcpu); +} + +static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + if (events->flags) + return -EINVAL; + + vcpu_load(vcpu); + + vcpu->arch.exception.pending = events->exception.injected; + vcpu->arch.exception.nr = events->exception.nr; + vcpu->arch.exception.has_error_code = events->exception.has_error_code; + vcpu->arch.exception.error_code = events->exception.error_code; + + vcpu->arch.interrupt.pending = events->interrupt.injected; + vcpu->arch.interrupt.nr = events->interrupt.nr; + vcpu->arch.interrupt.soft = events->interrupt.soft; + if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm)) + kvm_pic_clear_isr_ack(vcpu->kvm); + + vcpu->arch.nmi_injected = events->nmi.injected; + vcpu->arch.nmi_pending = events->nmi.pending; + kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); + + vcpu->arch.sipi_vector = events->sipi_vector; + + vcpu_put(vcpu); + + return 0; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1770,6 +1958,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, switch (ioctl) { case KVM_GET_LAPIC: { + r = -EINVAL; + if (!vcpu->arch.apic) + goto out; lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); r = -ENOMEM; @@ -1785,6 +1976,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_LAPIC: { + r = -EINVAL; + if (!vcpu->arch.apic) + goto out; lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); r = -ENOMEM; if (!lapic) @@ -1911,6 +2105,27 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce); break; } + case KVM_GET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events); + + r = -EFAULT; + if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events))) + break; + r = 0; + break; + } + case KVM_SET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + r = -EFAULT; + if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events))) + break; + + r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); + break; + } default: r = -EINVAL; } @@ -2039,9 +2254,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) sizeof(struct kvm_pic_state)); break; case KVM_IRQCHIP_IOAPIC: - memcpy(&chip->chip.ioapic, - ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); + r = kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -2071,11 +2284,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) spin_unlock(&pic_irqchip(kvm)->lock); break; case KVM_IRQCHIP_IOAPIC: - mutex_lock(&kvm->irq_lock); - memcpy(ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); - mutex_unlock(&kvm->irq_lock); + r = kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -2183,7 +2392,7 @@ long kvm_arch_vm_ioctl(struct file *filp, { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; - int r = -EINVAL; + int r = -ENOTTY; /* * This union makes it completely explicit to gcc-3.x * that these two variables' stack usage should be @@ -2245,25 +2454,39 @@ long kvm_arch_vm_ioctl(struct file *filp, if (r) goto out; break; - case KVM_CREATE_IRQCHIP: + case KVM_CREATE_IRQCHIP: { + struct kvm_pic *vpic; + + mutex_lock(&kvm->lock); + r = -EEXIST; + if (kvm->arch.vpic) + goto create_irqchip_unlock; r = -ENOMEM; - kvm->arch.vpic = kvm_create_pic(kvm); - if (kvm->arch.vpic) { + vpic = kvm_create_pic(kvm); + if (vpic) { r = kvm_ioapic_init(kvm); if (r) { - kfree(kvm->arch.vpic); - kvm->arch.vpic = NULL; - goto out; + kfree(vpic); + goto create_irqchip_unlock; } } else - goto out; + goto create_irqchip_unlock; + smp_wmb(); + kvm->arch.vpic = vpic; + smp_wmb(); r = kvm_setup_default_irq_routing(kvm); if (r) { + mutex_lock(&kvm->irq_lock); kfree(kvm->arch.vpic); kfree(kvm->arch.vioapic); - goto out; + kvm->arch.vpic = NULL; + kvm->arch.vioapic = NULL; + mutex_unlock(&kvm->irq_lock); } + create_irqchip_unlock: + mutex_unlock(&kvm->lock); break; + } case KVM_CREATE_PIT: u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY; goto create_pit; @@ -2293,10 +2516,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { __s32 status; - mutex_lock(&kvm->irq_lock); status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); - mutex_unlock(&kvm->irq_lock); if (ioctl == KVM_IRQ_LINE_STATUS) { irq_event.status = status; if (copy_to_user(argp, &irq_event, @@ -2422,6 +2643,55 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_XEN_HVM_CONFIG: { + r = -EFAULT; + if (copy_from_user(&kvm->arch.xen_hvm_config, argp, + sizeof(struct kvm_xen_hvm_config))) + goto out; + r = -EINVAL; + if (kvm->arch.xen_hvm_config.flags) + goto out; + r = 0; + break; + } + case KVM_SET_CLOCK: { + struct timespec now; + struct kvm_clock_data user_ns; + u64 now_ns; + s64 delta; + + r = -EFAULT; + if (copy_from_user(&user_ns, argp, sizeof(user_ns))) + goto out; + + r = -EINVAL; + if (user_ns.flags) + goto out; + + r = 0; + ktime_get_ts(&now); + now_ns = timespec_to_ns(&now); + delta = user_ns.clock - now_ns; + kvm->arch.kvmclock_offset = delta; + break; + } + case KVM_GET_CLOCK: { + struct timespec now; + struct kvm_clock_data user_ns; + u64 now_ns; + + ktime_get_ts(&now); + now_ns = timespec_to_ns(&now); + user_ns.clock = kvm->arch.kvmclock_offset + now_ns; + user_ns.flags = 0; + + r = -EFAULT; + if (copy_to_user(argp, &user_ns, sizeof(user_ns))) + goto out; + r = 0; + break; + } + default: ; } @@ -2434,7 +2704,8 @@ static void kvm_init_msr_list(void) u32 dummy[2]; unsigned i, j; - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { + /* skip the first msrs in the list. KVM-specific */ + for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) { if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) continue; if (j < i) @@ -2758,13 +3029,13 @@ static void cache_all_regs(struct kvm_vcpu *vcpu) } int emulate_instruction(struct kvm_vcpu *vcpu, - struct kvm_run *run, unsigned long cr2, u16 error_code, int emulation_type) { int r, shadow_mask; struct decode_cache *c; + struct kvm_run *run = vcpu->run; kvm_clear_exception_queue(vcpu); vcpu->arch.mmio_fault_cr2 = cr2; @@ -2784,7 +3055,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); vcpu->arch.emulate_ctxt.vcpu = vcpu; - vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu); vcpu->arch.emulate_ctxt.mode = (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_REAL : cs_l @@ -2862,7 +3133,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DO_MMIO; } - kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); if (vcpu->mmio_is_write) { vcpu->mmio_needed = 0; @@ -2970,8 +3241,7 @@ static int pio_string_write(struct kvm_vcpu *vcpu) return r; } -int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned port) +int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port) { unsigned long val; @@ -3000,7 +3270,7 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, } EXPORT_SYMBOL_GPL(kvm_emulate_pio); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, +int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in, int size, unsigned long count, int down, gva_t address, int rep, unsigned port) { @@ -3073,9 +3343,6 @@ static void bounce_off(void *info) /* nothing */ } -static unsigned int ref_freq; -static unsigned long tsc_khz_ref; - static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -3084,14 +3351,11 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va struct kvm_vcpu *vcpu; int i, send_ipi = 0; - if (!ref_freq) - ref_freq = freq->old; - if (val == CPUFREQ_PRECHANGE && freq->old > freq->new) return 0; if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new) return 0; - per_cpu(cpu_tsc_khz, freq->cpu) = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); + per_cpu(cpu_tsc_khz, freq->cpu) = freq->new; spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { @@ -3128,9 +3392,28 @@ static struct notifier_block kvmclock_cpufreq_notifier_block = { .notifier_call = kvmclock_cpufreq_notifier }; +static void kvm_timer_init(void) +{ + int cpu; + + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); + for_each_online_cpu(cpu) { + unsigned long khz = cpufreq_get(cpu); + if (!khz) + khz = tsc_khz; + per_cpu(cpu_tsc_khz, cpu) = khz; + } + } else { + for_each_possible_cpu(cpu) + per_cpu(cpu_tsc_khz, cpu) = tsc_khz; + } +} + int kvm_arch_init(void *opaque) { - int r, cpu; + int r; struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque; if (kvm_x86_ops) { @@ -3162,13 +3445,7 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0); - for_each_possible_cpu(cpu) - per_cpu(cpu_tsc_khz, cpu) = tsc_khz; - if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { - tsc_khz_ref = tsc_khz; - cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, - CPUFREQ_TRANSITION_NOTIFIER); - } + kvm_timer_init(); return 0; @@ -3296,7 +3573,7 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, unsigned long *rflags) { kvm_lmsw(vcpu, msw); - *rflags = kvm_x86_ops->get_rflags(vcpu); + *rflags = kvm_get_rflags(vcpu); } unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) @@ -3334,7 +3611,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, switch (cr) { case 0: kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val)); - *rflags = kvm_x86_ops->get_rflags(vcpu); + *rflags = kvm_get_rflags(vcpu); break; case 2: vcpu->arch.cr2 = val; @@ -3454,18 +3731,18 @@ EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); * * No need to exit to userspace if we already have an interrupt queued. */ -static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) && - kvm_run->request_interrupt_window && + vcpu->run->request_interrupt_window && kvm_arch_interrupt_allowed(vcpu)); } -static void post_kvm_run_save(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static void post_kvm_run_save(struct kvm_vcpu *vcpu) { - kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + struct kvm_run *kvm_run = vcpu->run; + + kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); if (irqchip_in_kernel(vcpu->kvm)) @@ -3526,7 +3803,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); } -static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void inject_pending_event(struct kvm_vcpu *vcpu) { /* try to reinject previous events if any */ if (vcpu->arch.exception.pending) { @@ -3562,11 +3839,11 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } } -static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && - kvm_run->request_interrupt_window; + vcpu->run->request_interrupt_window; if (vcpu->requests) if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) @@ -3587,12 +3864,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_x86_ops->tlb_flush(vcpu); if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests)) { - kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS; + vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; goto out; } if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) { - kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; r = 0; goto out; } @@ -3616,7 +3893,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } - inject_pending_event(vcpu, kvm_run); + inject_pending_event(vcpu); /* enable NMI/IRQ window open exits if needed */ if (vcpu->arch.nmi_pending) @@ -3642,7 +3919,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } trace_kvm_entry(vcpu->vcpu_id); - kvm_x86_ops->run(vcpu, kvm_run); + kvm_x86_ops->run(vcpu); /* * If the guest has used debug registers, at least dr7 @@ -3684,13 +3961,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_lapic_sync_from_vapic(vcpu); - r = kvm_x86_ops->handle_exit(kvm_run, vcpu); + r = kvm_x86_ops->handle_exit(vcpu); out: return r; } -static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int __vcpu_run(struct kvm_vcpu *vcpu) { int r; @@ -3710,7 +3987,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) r = 1; while (r > 0) { if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) - r = vcpu_enter_guest(vcpu, kvm_run); + r = vcpu_enter_guest(vcpu); else { up_read(&vcpu->kvm->slots_lock); kvm_vcpu_block(vcpu); @@ -3738,14 +4015,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); - if (dm_request_for_irq_injection(vcpu, kvm_run)) { + if (dm_request_for_irq_injection(vcpu)) { r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.request_irq_exits; } if (signal_pending(current)) { r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.signal_exits; } if (need_resched()) { @@ -3756,7 +4033,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } up_read(&vcpu->kvm->slots_lock); - post_kvm_run_save(vcpu, kvm_run); + post_kvm_run_save(vcpu); vapic_exit(vcpu); @@ -3789,15 +4066,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (r) goto out; } -#if CONFIG_HAS_IOMEM if (vcpu->mmio_needed) { memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); vcpu->mmio_read_completed = 1; vcpu->mmio_needed = 0; down_read(&vcpu->kvm->slots_lock); - r = emulate_instruction(vcpu, kvm_run, - vcpu->arch.mmio_fault_cr2, 0, + r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0, EMULTYPE_NO_DECODE); up_read(&vcpu->kvm->slots_lock); if (r == EMULATE_DO_MMIO) { @@ -3808,12 +4083,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } } -#endif if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) kvm_register_write(vcpu, VCPU_REGS_RAX, kvm_run->hypercall.ret); - r = __vcpu_run(vcpu, kvm_run); + r = __vcpu_run(vcpu); out: if (vcpu->sigset_active) @@ -3847,13 +4121,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) #endif regs->rip = kvm_rip_read(vcpu); - regs->rflags = kvm_x86_ops->get_rflags(vcpu); - - /* - * Don't leak debug flags in case they were set for guest debugging - */ - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + regs->rflags = kvm_get_rflags(vcpu); vcpu_put(vcpu); @@ -3881,12 +4149,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13); kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14); kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15); - #endif kvm_rip_write(vcpu, regs->rip); - kvm_x86_ops->set_rflags(vcpu, regs->rflags); - + kvm_set_rflags(vcpu, regs->rflags); vcpu->arch.exception.pending = false; @@ -4105,7 +4371,7 @@ static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg) { return (seg != VCPU_SREG_LDTR) && (seg != VCPU_SREG_TR) && - (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_VM); + (kvm_get_rflags(vcpu) & X86_EFLAGS_VM); } int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, @@ -4133,7 +4399,7 @@ static void save_state_to_tss32(struct kvm_vcpu *vcpu, { tss->cr3 = vcpu->arch.cr3; tss->eip = kvm_rip_read(vcpu); - tss->eflags = kvm_x86_ops->get_rflags(vcpu); + tss->eflags = kvm_get_rflags(vcpu); tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX); tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX); @@ -4157,7 +4423,7 @@ static int load_state_from_tss32(struct kvm_vcpu *vcpu, kvm_set_cr3(vcpu, tss->cr3); kvm_rip_write(vcpu, tss->eip); - kvm_x86_ops->set_rflags(vcpu, tss->eflags | 2); + kvm_set_rflags(vcpu, tss->eflags | 2); kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax); kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx); @@ -4195,7 +4461,7 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu, struct tss_segment_16 *tss) { tss->ip = kvm_rip_read(vcpu); - tss->flag = kvm_x86_ops->get_rflags(vcpu); + tss->flag = kvm_get_rflags(vcpu); tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX); tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX); tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX); @@ -4210,14 +4476,13 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu, tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS); tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR); - tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR); } static int load_state_from_tss16(struct kvm_vcpu *vcpu, struct tss_segment_16 *tss) { kvm_rip_write(vcpu, tss->ip); - kvm_x86_ops->set_rflags(vcpu, tss->flag | 2); + kvm_set_rflags(vcpu, tss->flag | 2); kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax); kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx); kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx); @@ -4363,8 +4628,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) } if (reason == TASK_SWITCH_IRET) { - u32 eflags = kvm_x86_ops->get_rflags(vcpu); - kvm_x86_ops->set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); + u32 eflags = kvm_get_rflags(vcpu); + kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); } /* set back link to prev task only if NT bit is set in eflags @@ -4372,11 +4637,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) old_tss_sel = 0xffff; - /* set back link to prev task only if NT bit is set in eflags - note that old_tss_sel is not used afetr this point */ - if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) - old_tss_sel = 0xffff; - if (nseg_desc.type & 8) ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_sel, old_tss_base, &nseg_desc); @@ -4385,8 +4645,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) old_tss_base, &nseg_desc); if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) { - u32 eflags = kvm_x86_ops->get_rflags(vcpu); - kvm_x86_ops->set_rflags(vcpu, eflags | X86_EFLAGS_NT); + u32 eflags = kvm_get_rflags(vcpu); + kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT); } if (reason != TASK_SWITCH_IRET) { @@ -4438,8 +4698,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4; kvm_x86_ops->set_cr4(vcpu, sregs->cr4); - if (!is_long_mode(vcpu) && is_pae(vcpu)) + if (!is_long_mode(vcpu) && is_pae(vcpu)) { load_pdptrs(vcpu, vcpu->arch.cr3); + mmu_reset_needed = 1; + } if (mmu_reset_needed) kvm_mmu_reset_context(vcpu); @@ -4480,12 +4742,32 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { + unsigned long rflags; int i, r; vcpu_load(vcpu); - if ((dbg->control & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) == - (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) { + if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { + r = -EBUSY; + if (vcpu->arch.exception.pending) + goto unlock_out; + if (dbg->control & KVM_GUESTDBG_INJECT_DB) + kvm_queue_exception(vcpu, DB_VECTOR); + else + kvm_queue_exception(vcpu, BP_VECTOR); + } + + /* + * Read rflags as long as potentially injected trace flags are still + * filtered out. + */ + rflags = kvm_get_rflags(vcpu); + + vcpu->guest_debug = dbg->control; + if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) + vcpu->guest_debug = 0; + + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { for (i = 0; i < KVM_NR_DB_REGS; ++i) vcpu->arch.eff_db[i] = dbg->arch.debugreg[i]; vcpu->arch.switch_db_regs = @@ -4496,13 +4778,23 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); } - r = kvm_x86_ops->set_guest_debug(vcpu, dbg); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + vcpu->arch.singlestep_cs = + get_segment_selector(vcpu, VCPU_SREG_CS); + vcpu->arch.singlestep_rip = kvm_rip_read(vcpu); + } + + /* + * Trigger an rflags update that will inject or remove the trace + * flags. + */ + kvm_set_rflags(vcpu, rflags); + + kvm_x86_ops->set_guest_debug(vcpu, dbg); - if (dbg->control & KVM_GUESTDBG_INJECT_DB) - kvm_queue_exception(vcpu, DB_VECTOR); - else if (dbg->control & KVM_GUESTDBG_INJECT_BP) - kvm_queue_exception(vcpu, BP_VECTOR); + r = 0; +unlock_out: vcpu_put(vcpu); return r; @@ -4703,14 +4995,26 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) return kvm_x86_ops->vcpu_reset(vcpu); } -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { - kvm_x86_ops->hardware_enable(garbage); + /* + * Since this may be called from a hotplug notifcation, + * we can't get the CPU frequency directly. + */ + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + int cpu = raw_smp_processor_id(); + per_cpu(cpu_tsc_khz, cpu) = 0; + } + + kvm_shared_msr_cpu_online(); + + return kvm_x86_ops->hardware_enable(garbage); } void kvm_arch_hardware_disable(void *garbage) { kvm_x86_ops->hardware_disable(garbage); + drop_user_return_notifiers(garbage); } int kvm_arch_hardware_setup(void) @@ -4948,8 +5252,36 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) return kvm_x86_ops->interrupt_allowed(vcpu); } +unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) +{ + unsigned long rflags; + + rflags = kvm_x86_ops->get_rflags(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF); + return rflags; +} +EXPORT_SYMBOL_GPL(kvm_get_rflags); + +void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && + vcpu->arch.singlestep_cs == + get_segment_selector(vcpu, VCPU_SREG_CS) && + vcpu->arch.singlestep_rip == kvm_rip_read(vcpu)) + rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + kvm_x86_ops->set_rflags(vcpu, rflags); +} +EXPORT_SYMBOL_GPL(kvm_set_rflags); + EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); diff --git a/include/linux/kvm.h b/include/linux/kvm.h index f8f8900..2d241da 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -14,12 +14,76 @@ #define KVM_API_VERSION 12 -/* for KVM_TRACE_ENABLE, deprecated */ +/* *** Deprecated interfaces *** */ + +#define KVM_TRC_SHIFT 16 + +#define KVM_TRC_ENTRYEXIT (1 << KVM_TRC_SHIFT) +#define KVM_TRC_HANDLER (1 << (KVM_TRC_SHIFT + 1)) + +#define KVM_TRC_VMENTRY (KVM_TRC_ENTRYEXIT + 0x01) +#define KVM_TRC_VMEXIT (KVM_TRC_ENTRYEXIT + 0x02) +#define KVM_TRC_PAGE_FAULT (KVM_TRC_HANDLER + 0x01) + +#define KVM_TRC_HEAD_SIZE 12 +#define KVM_TRC_CYCLE_SIZE 8 +#define KVM_TRC_EXTRA_MAX 7 + +#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) +#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) +#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) +#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05) +#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06) +#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07) +#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08) +#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09) +#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A) +#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B) +#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C) +#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D) +#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E) +#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F) +#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10) +#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11) +#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12) +#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) +#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) +#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15) +#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16) +#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17) +#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18) +#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19) + struct kvm_user_trace_setup { - __u32 buf_size; /* sub_buffer size of each per-cpu */ - __u32 buf_nr; /* the number of sub_buffers of each per-cpu */ + __u32 buf_size; + __u32 buf_nr; +}; + +#define __KVM_DEPRECATED_MAIN_W_0x06 \ + _IOW(KVMIO, 0x06, struct kvm_user_trace_setup) +#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07) +#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08) + +#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq) + +struct kvm_breakpoint { + __u32 enabled; + __u32 padding; + __u64 address; +}; + +struct kvm_debug_guest { + __u32 enabled; + __u32 pad; + struct kvm_breakpoint breakpoints[4]; + __u32 singlestep; }; +#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest) + +/* *** End of deprecated interfaces *** */ + + /* for KVM_CREATE_MEMORY_REGION */ struct kvm_memory_region { __u32 slot; @@ -99,6 +163,7 @@ struct kvm_pit_config { /* For KVM_EXIT_INTERNAL_ERROR */ #define KVM_INTERNAL_ERROR_EMULATION 1 +#define KVM_INTERNAL_ERROR_SIMUL_EX 2 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { @@ -116,6 +181,11 @@ struct kvm_run { __u64 cr8; __u64 apic_base; +#ifdef __KVM_S390 + /* the processor status word for s390 */ + __u64 psw_mask; /* psw upper half */ + __u64 psw_addr; /* psw lower half */ +#endif union { /* KVM_EXIT_UNKNOWN */ struct { @@ -167,8 +237,6 @@ struct kvm_run { /* KVM_EXIT_S390_SIEIC */ struct { __u8 icptcode; - __u64 mask; /* psw upper half */ - __u64 addr; /* psw lower half */ __u16 ipa; __u32 ipb; } s390_sieic; @@ -187,6 +255,9 @@ struct kvm_run { } dcr; struct { __u32 suberror; + /* Available with KVM_CAP_INTERNAL_ERROR_DATA: */ + __u32 ndata; + __u64 data[16]; } internal; /* Fix the size of the union. */ char padding[256]; @@ -329,24 +400,6 @@ struct kvm_ioeventfd { __u8 pad[36]; }; -#define KVM_TRC_SHIFT 16 -/* - * kvm trace categories - */ -#define KVM_TRC_ENTRYEXIT (1 << KVM_TRC_SHIFT) -#define KVM_TRC_HANDLER (1 << (KVM_TRC_SHIFT + 1)) /* only 12 bits */ - -/* - * kvm trace action - */ -#define KVM_TRC_VMENTRY (KVM_TRC_ENTRYEXIT + 0x01) -#define KVM_TRC_VMEXIT (KVM_TRC_ENTRYEXIT + 0x02) -#define KVM_TRC_PAGE_FAULT (KVM_TRC_HANDLER + 0x01) - -#define KVM_TRC_HEAD_SIZE 12 -#define KVM_TRC_CYCLE_SIZE 8 -#define KVM_TRC_EXTRA_MAX 7 - #define KVMIO 0xAE /* @@ -367,12 +420,10 @@ struct kvm_ioeventfd { */ #define KVM_GET_VCPU_MMAP_SIZE _IO(KVMIO, 0x04) /* in bytes */ #define KVM_GET_SUPPORTED_CPUID _IOWR(KVMIO, 0x05, struct kvm_cpuid2) -/* - * ioctls for kvm trace - */ -#define KVM_TRACE_ENABLE _IOW(KVMIO, 0x06, struct kvm_user_trace_setup) -#define KVM_TRACE_PAUSE _IO(KVMIO, 0x07) -#define KVM_TRACE_DISABLE _IO(KVMIO, 0x08) +#define KVM_TRACE_ENABLE __KVM_DEPRECATED_MAIN_W_0x06 +#define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07 +#define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08 + /* * Extension capability list. */ @@ -436,6 +487,15 @@ struct kvm_ioeventfd { #endif #define KVM_CAP_IOEVENTFD 36 #define KVM_CAP_SET_IDENTITY_MAP_ADDR 37 +#ifdef __KVM_HAVE_XEN_HVM +#define KVM_CAP_XEN_HVM 38 +#endif +#define KVM_CAP_ADJUST_CLOCK 39 +#define KVM_CAP_INTERNAL_ERROR_DATA 40 +#ifdef __KVM_HAVE_VCPU_EVENTS +#define KVM_CAP_VCPU_EVENTS 41 +#endif +#define KVM_CAP_S390_PSW 42 #ifdef KVM_CAP_IRQ_ROUTING @@ -488,6 +548,18 @@ struct kvm_x86_mce { }; #endif +#ifdef KVM_CAP_XEN_HVM +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; +#endif + #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) struct kvm_irqfd { @@ -497,55 +569,66 @@ struct kvm_irqfd { __u8 pad[20]; }; +struct kvm_clock_data { + __u64 clock; + __u32 flags; + __u32 pad[9]; +}; + /* * ioctls for VM fds */ -#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region) +#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region) /* * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns * a vcpu fd. */ -#define KVM_CREATE_VCPU _IO(KVMIO, 0x41) -#define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) -#define KVM_SET_MEMORY_ALIAS _IOW(KVMIO, 0x43, struct kvm_memory_alias) -#define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) -#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) -#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46,\ +#define KVM_CREATE_VCPU _IO(KVMIO, 0x41) +#define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) +#define KVM_SET_MEMORY_ALIAS _IOW(KVMIO, 0x43, struct kvm_memory_alias) +#define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) +#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) +#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \ struct kvm_userspace_memory_region) -#define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) -#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64) +#define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) +#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64) /* Device model IOC */ -#define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) -#define KVM_IRQ_LINE _IOW(KVMIO, 0x61, struct kvm_irq_level) -#define KVM_GET_IRQCHIP _IOWR(KVMIO, 0x62, struct kvm_irqchip) -#define KVM_SET_IRQCHIP _IOR(KVMIO, 0x63, struct kvm_irqchip) -#define KVM_CREATE_PIT _IO(KVMIO, 0x64) -#define KVM_GET_PIT _IOWR(KVMIO, 0x65, struct kvm_pit_state) -#define KVM_SET_PIT _IOR(KVMIO, 0x66, struct kvm_pit_state) -#define KVM_IRQ_LINE_STATUS _IOWR(KVMIO, 0x67, struct kvm_irq_level) +#define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) +#define KVM_IRQ_LINE _IOW(KVMIO, 0x61, struct kvm_irq_level) +#define KVM_GET_IRQCHIP _IOWR(KVMIO, 0x62, struct kvm_irqchip) +#define KVM_SET_IRQCHIP _IOR(KVMIO, 0x63, struct kvm_irqchip) +#define KVM_CREATE_PIT _IO(KVMIO, 0x64) +#define KVM_GET_PIT _IOWR(KVMIO, 0x65, struct kvm_pit_state) +#define KVM_SET_PIT _IOR(KVMIO, 0x66, struct kvm_pit_state) +#define KVM_IRQ_LINE_STATUS _IOWR(KVMIO, 0x67, struct kvm_irq_level) #define KVM_REGISTER_COALESCED_MMIO \ _IOW(KVMIO, 0x67, struct kvm_coalesced_mmio_zone) #define KVM_UNREGISTER_COALESCED_MMIO \ _IOW(KVMIO, 0x68, struct kvm_coalesced_mmio_zone) -#define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \ - struct kvm_assigned_pci_dev) -#define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing) +#define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \ + struct kvm_assigned_pci_dev) +#define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing) /* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */ -#define KVM_ASSIGN_IRQ _IOR(KVMIO, 0x70, \ - struct kvm_assigned_irq) -#define KVM_ASSIGN_DEV_IRQ _IOW(KVMIO, 0x70, struct kvm_assigned_irq) -#define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) -#define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \ - struct kvm_assigned_pci_dev) -#define KVM_ASSIGN_SET_MSIX_NR \ - _IOW(KVMIO, 0x73, struct kvm_assigned_msix_nr) -#define KVM_ASSIGN_SET_MSIX_ENTRY \ - _IOW(KVMIO, 0x74, struct kvm_assigned_msix_entry) -#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq) -#define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd) -#define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config) -#define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78) -#define KVM_IOEVENTFD _IOW(KVMIO, 0x79, struct kvm_ioeventfd) +#define KVM_ASSIGN_IRQ __KVM_DEPRECATED_VM_R_0x70 +#define KVM_ASSIGN_DEV_IRQ _IOW(KVMIO, 0x70, struct kvm_assigned_irq) +#define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) +#define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \ + struct kvm_assigned_pci_dev) +#define KVM_ASSIGN_SET_MSIX_NR _IOW(KVMIO, 0x73, \ + struct kvm_assigned_msix_nr) +#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO, 0x74, \ + struct kvm_assigned_msix_entry) +#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq) +#define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd) +#define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config) +#define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78) +#define KVM_IOEVENTFD _IOW(KVMIO, 0x79, struct kvm_ioeventfd) +#define KVM_XEN_HVM_CONFIG _IOW(KVMIO, 0x7a, struct kvm_xen_hvm_config) +#define KVM_SET_CLOCK _IOW(KVMIO, 0x7b, struct kvm_clock_data) +#define KVM_GET_CLOCK _IOR(KVMIO, 0x7c, struct kvm_clock_data) +/* Available with KVM_CAP_PIT_STATE2 */ +#define KVM_GET_PIT2 _IOR(KVMIO, 0x9f, struct kvm_pit_state2) +#define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2) /* * ioctls for vcpu fds @@ -558,7 +641,7 @@ struct kvm_irqfd { #define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation) #define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt) /* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */ -#define KVM_DEBUG_GUEST __KVM_DEPRECATED_DEBUG_GUEST +#define KVM_DEBUG_GUEST __KVM_DEPRECATED_VCPU_W_0x87 #define KVM_GET_MSRS _IOWR(KVMIO, 0x88, struct kvm_msrs) #define KVM_SET_MSRS _IOW(KVMIO, 0x89, struct kvm_msrs) #define KVM_SET_CPUID _IOW(KVMIO, 0x8a, struct kvm_cpuid) @@ -570,7 +653,7 @@ struct kvm_irqfd { #define KVM_SET_CPUID2 _IOW(KVMIO, 0x90, struct kvm_cpuid2) #define KVM_GET_CPUID2 _IOWR(KVMIO, 0x91, struct kvm_cpuid2) /* Available with KVM_CAP_VAPIC */ -#define KVM_TPR_ACCESS_REPORTING _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl) +#define KVM_TPR_ACCESS_REPORTING _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl) /* Available with KVM_CAP_VAPIC */ #define KVM_SET_VAPIC_ADDR _IOW(KVMIO, 0x93, struct kvm_vapic_addr) /* valid for virtual machine (for floating interrupt)_and_ vcpu */ @@ -582,66 +665,23 @@ struct kvm_irqfd { /* initial ipl psw for s390 */ #define KVM_S390_SET_INITIAL_PSW _IOW(KVMIO, 0x96, struct kvm_s390_psw) /* initial reset for s390 */ -#define KVM_S390_INITIAL_RESET _IO(KVMIO, 0x97) +#define KVM_S390_INITIAL_RESET _IO(KVMIO, 0x97) #define KVM_GET_MP_STATE _IOR(KVMIO, 0x98, struct kvm_mp_state) #define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state) /* Available with KVM_CAP_NMI */ -#define KVM_NMI _IO(KVMIO, 0x9a) +#define KVM_NMI _IO(KVMIO, 0x9a) /* Available with KVM_CAP_SET_GUEST_DEBUG */ #define KVM_SET_GUEST_DEBUG _IOW(KVMIO, 0x9b, struct kvm_guest_debug) /* MCE for x86 */ #define KVM_X86_SETUP_MCE _IOW(KVMIO, 0x9c, __u64) #define KVM_X86_GET_MCE_CAP_SUPPORTED _IOR(KVMIO, 0x9d, __u64) #define KVM_X86_SET_MCE _IOW(KVMIO, 0x9e, struct kvm_x86_mce) - -/* - * Deprecated interfaces - */ -struct kvm_breakpoint { - __u32 enabled; - __u32 padding; - __u64 address; -}; - -struct kvm_debug_guest { - __u32 enabled; - __u32 pad; - struct kvm_breakpoint breakpoints[4]; - __u32 singlestep; -}; - -#define __KVM_DEPRECATED_DEBUG_GUEST _IOW(KVMIO, 0x87, struct kvm_debug_guest) - +/* IA64 stack access */ #define KVM_IA64_VCPU_GET_STACK _IOR(KVMIO, 0x9a, void *) #define KVM_IA64_VCPU_SET_STACK _IOW(KVMIO, 0x9b, void *) - -#define KVM_GET_PIT2 _IOR(KVMIO, 0x9f, struct kvm_pit_state2) -#define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2) - -#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) -#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) -#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) -#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05) -#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06) -#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07) -#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08) -#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09) -#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A) -#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B) -#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C) -#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D) -#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E) -#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F) -#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10) -#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11) -#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12) -#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) -#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) -#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15) -#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16) -#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17) -#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18) -#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19) +/* Available with KVM_CAP_VCPU_EVENTS */ +#define KVM_GET_VCPU_EVENTS _IOR(KVMIO, 0x9f, struct kvm_vcpu_events) +#define KVM_SET_VCPU_EVENTS _IOW(KVMIO, 0xa0, struct kvm_vcpu_events) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) @@ -696,4 +736,4 @@ struct kvm_assigned_msix_entry { __u16 padding[3]; }; -#endif +#endif /* __LINUX_KVM_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b7bbb5d..bd5a616 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -120,7 +120,7 @@ struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; int (*set)(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level); + struct kvm *kvm, int irq_source_id, int level); union { struct { unsigned irqchip; @@ -128,9 +128,28 @@ struct kvm_kernel_irq_routing_entry { } irqchip; struct msi_msg msi; }; - struct list_head link; + struct hlist_node link; +}; + +#ifdef __KVM_HAVE_IOAPIC + +struct kvm_irq_routing_table { + int chip[KVM_NR_IRQCHIPS][KVM_IOAPIC_NUM_PINS]; + struct kvm_kernel_irq_routing_entry *rt_entries; + u32 nr_rt_entries; + /* + * Array indexed by gsi. Each entry contains list of irq chips + * the gsi is connected to. + */ + struct hlist_head map[0]; }; +#else + +struct kvm_irq_routing_table {}; + +#endif + struct kvm { spinlock_t mmu_lock; spinlock_t requests_lock; @@ -166,8 +185,9 @@ struct kvm { struct mutex irq_lock; #ifdef CONFIG_HAVE_KVM_IRQCHIP - struct list_head irq_routing; /* of kvm_kernel_irq_routing_entry */ + struct kvm_irq_routing_table *irq_routing; struct hlist_head mask_notifier_list; + struct hlist_head irq_ack_notifier_list; #endif #ifdef KVM_ARCH_WANT_MMU_NOTIFIER @@ -266,6 +286,7 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); void kvm_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); void kvm_resched(struct kvm_vcpu *vcpu); void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); @@ -325,7 +346,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu); -void kvm_arch_hardware_enable(void *garbage); +int kvm_arch_hardware_enable(void *garbage); void kvm_arch_hardware_disable(void *garbage); int kvm_arch_hardware_setup(void); void kvm_arch_hardware_unsetup(void); @@ -390,7 +411,12 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn); void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask); -int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level); +#ifdef __KVM_HAVE_IOAPIC +void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, + union kvm_ioapic_redirect_entry *entry, + unsigned long *deliver_bitmask); +#endif +int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); @@ -552,4 +578,21 @@ static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id; } #endif + +#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT + +long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, + unsigned long arg); + +#else + +static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, + unsigned long arg) +{ + return -ENOTTY; +} + #endif + +#endif + diff --git a/include/linux/user-return-notifier.h b/include/linux/user-return-notifier.h new file mode 100644 index 0000000..9c4a445 --- /dev/null +++ b/include/linux/user-return-notifier.h @@ -0,0 +1,49 @@ +#ifndef _LINUX_USER_RETURN_NOTIFIER_H +#define _LINUX_USER_RETURN_NOTIFIER_H + +#ifdef CONFIG_USER_RETURN_NOTIFIER + +#include <linux/list.h> +#include <linux/sched.h> + +struct user_return_notifier { + void (*on_user_return)(struct user_return_notifier *urn); + struct hlist_node link; +}; + + +void user_return_notifier_register(struct user_return_notifier *urn); +void user_return_notifier_unregister(struct user_return_notifier *urn); + +static inline void propagate_user_return_notify(struct task_struct *prev, + struct task_struct *next) +{ + if (test_tsk_thread_flag(prev, TIF_USER_RETURN_NOTIFY)) { + clear_tsk_thread_flag(prev, TIF_USER_RETURN_NOTIFY); + set_tsk_thread_flag(next, TIF_USER_RETURN_NOTIFY); + } +} + +void fire_user_return_notifiers(void); + +static inline void clear_user_return_notifier(struct task_struct *p) +{ + clear_tsk_thread_flag(p, TIF_USER_RETURN_NOTIFY); +} + +#else + +struct user_return_notifier {}; + +static inline void propagate_user_return_notify(struct task_struct *prev, + struct task_struct *next) +{ +} + +static inline void fire_user_return_notifiers(void) {} + +static inline void clear_user_return_notifier(struct task_struct *p) {} + +#endif + +#endif diff --git a/kernel/Makefile b/kernel/Makefile index 9943202..864ff75 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -99,6 +99,7 @@ obj-$(CONFIG_SLOW_WORK) += slow-work.o obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o +obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is diff --git a/kernel/fork.c b/kernel/fork.c index 3d6f121..edeff9c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -64,6 +64,7 @@ #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> +#include <linux/user-return-notifier.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -249,6 +250,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) goto out; setup_thread_stack(tsk, orig); + clear_user_return_notifier(tsk); stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c new file mode 100644 index 0000000..03e2d6f --- /dev/null +++ b/kernel/user-return-notifier.c @@ -0,0 +1,46 @@ + +#include <linux/user-return-notifier.h> +#include <linux/percpu.h> +#include <linux/sched.h> +#include <linux/module.h> + +static DEFINE_PER_CPU(struct hlist_head, return_notifier_list); + +#define URN_LIST_HEAD per_cpu(return_notifier_list, raw_smp_processor_id()) + +/* + * Request a notification when the current cpu returns to userspace. Must be + * called in atomic context. The notifier will also be called in atomic + * context. + */ +void user_return_notifier_register(struct user_return_notifier *urn) +{ + set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY); + hlist_add_head(&urn->link, &URN_LIST_HEAD); +} +EXPORT_SYMBOL_GPL(user_return_notifier_register); + +/* + * Removes a registered user return notifier. Must be called from atomic + * context, and from the same cpu registration occured in. + */ +void user_return_notifier_unregister(struct user_return_notifier *urn) +{ + hlist_del(&urn->link); + if (hlist_empty(&URN_LIST_HEAD)) + clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY); +} +EXPORT_SYMBOL_GPL(user_return_notifier_unregister); + +/* Calls registered user return notifiers */ +void fire_user_return_notifiers(void) +{ + struct user_return_notifier *urn; + struct hlist_node *tmp1, *tmp2; + struct hlist_head *head; + + head = &get_cpu_var(return_notifier_list); + hlist_for_each_entry_safe(urn, tmp1, tmp2, head, link) + urn->on_user_return(urn); + put_cpu_var(return_notifier_list); +} diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c new file mode 100644 index 0000000..fd9c097 --- /dev/null +++ b/virt/kvm/assigned-dev.c @@ -0,0 +1,818 @@ +/* + * Kernel-based Virtual Machine - device assignment support + * + * Copyright (C) 2006-9 Red Hat, Inc + * + * 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 <linux/kvm.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> +#include <linux/errno.h> +#include <linux/spinlock.h> +#include <linux/pci.h> +#include <linux/interrupt.h> +#include "irq.h" + +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); + if (match->assigned_dev_id == assigned_dev_id) + return match; + } + return NULL; +} + +static int find_index_from_host_irq(struct kvm_assigned_dev_kernel + *assigned_dev, int irq) +{ + int i, index; + struct msix_entry *host_msix_entries; + + host_msix_entries = assigned_dev->host_msix_entries; + + index = -1; + for (i = 0; i < assigned_dev->entries_nr; i++) + if (irq == host_msix_entries[i].vector) { + index = i; + break; + } + if (index < 0) { + printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n"); + return 0; + } + + return index; +} + +static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) +{ + struct kvm_assigned_dev_kernel *assigned_dev; + struct kvm *kvm; + int i; + + assigned_dev = container_of(work, struct kvm_assigned_dev_kernel, + interrupt_work); + kvm = assigned_dev->kvm; + + spin_lock_irq(&assigned_dev->assigned_dev_lock); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + struct kvm_guest_msix_entry *guest_entries = + assigned_dev->guest_msix_entries; + for (i = 0; i < assigned_dev->entries_nr; i++) { + if (!(guest_entries[i].flags & + KVM_ASSIGNED_MSIX_PENDING)) + continue; + guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING; + kvm_set_irq(assigned_dev->kvm, + assigned_dev->irq_source_id, + guest_entries[i].vector, 1); + } + } else + kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, + assigned_dev->guest_irq, 1); + + spin_unlock_irq(&assigned_dev->assigned_dev_lock); +} + +static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) +{ + unsigned long flags; + struct kvm_assigned_dev_kernel *assigned_dev = + (struct kvm_assigned_dev_kernel *) dev_id; + + spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + int index = find_index_from_host_irq(assigned_dev, irq); + if (index < 0) + goto out; + assigned_dev->guest_msix_entries[index].flags |= + KVM_ASSIGNED_MSIX_PENDING; + } + + schedule_work(&assigned_dev->interrupt_work); + + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) { + disable_irq_nosync(irq); + assigned_dev->host_irq_disabled = true; + } + +out: + spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags); + return IRQ_HANDLED; +} + +/* Ack the irq line for an assigned device */ +static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) +{ + struct kvm_assigned_dev_kernel *dev; + unsigned long flags; + + if (kian->gsi == -1) + return; + + dev = container_of(kian, struct kvm_assigned_dev_kernel, + ack_notifier); + + kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0); + + /* The guest irq may be shared so this ack may be + * from another device. + */ + spin_lock_irqsave(&dev->assigned_dev_lock, flags); + if (dev->host_irq_disabled) { + enable_irq(dev->host_irq); + dev->host_irq_disabled = false; + } + spin_unlock_irqrestore(&dev->assigned_dev_lock, flags); +} + +static void deassign_guest_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ + kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier); + assigned_dev->ack_notifier.gsi = -1; + + if (assigned_dev->irq_source_id != -1) + kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); + assigned_dev->irq_source_id = -1; + assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK); +} + +/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ +static void deassign_host_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ + /* + * In kvm_free_device_irq, cancel_work_sync return true if: + * 1. work is scheduled, and then cancelled. + * 2. work callback is executed. + * + * The first one ensured that the irq is disabled and no more events + * would happen. But for the second one, the irq may be enabled (e.g. + * for MSI). So we disable irq here to prevent further events. + * + * Notice this maybe result in nested disable if the interrupt type is + * INTx, but it's OK for we are going to free it. + * + * If this function is a part of VM destroy, please ensure that till + * now, the kvm state is still legal for probably we also have to wait + * interrupt_work done. + */ + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + int i; + for (i = 0; i < assigned_dev->entries_nr; i++) + disable_irq_nosync(assigned_dev-> + host_msix_entries[i].vector); + + cancel_work_sync(&assigned_dev->interrupt_work); + + for (i = 0; i < assigned_dev->entries_nr; i++) + free_irq(assigned_dev->host_msix_entries[i].vector, + (void *)assigned_dev); + + assigned_dev->entries_nr = 0; + kfree(assigned_dev->host_msix_entries); + kfree(assigned_dev->guest_msix_entries); + pci_disable_msix(assigned_dev->dev); + } else { + /* Deal with MSI and INTx */ + disable_irq_nosync(assigned_dev->host_irq); + cancel_work_sync(&assigned_dev->interrupt_work); + + free_irq(assigned_dev->host_irq, (void *)assigned_dev); + + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI) + pci_disable_msi(assigned_dev->dev); + } + + assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK); +} + +static int kvm_deassign_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev, + unsigned long irq_requested_type) +{ + unsigned long guest_irq_type, host_irq_type; + + if (!irqchip_in_kernel(kvm)) + return -EINVAL; + /* no irq assignment to deassign */ + if (!assigned_dev->irq_requested_type) + return -ENXIO; + + host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK; + guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK; + + if (host_irq_type) + deassign_host_irq(kvm, assigned_dev); + if (guest_irq_type) + deassign_guest_irq(kvm, assigned_dev); + + return 0; +} + +static void kvm_free_assigned_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ + kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type); +} + +static void kvm_free_assigned_device(struct kvm *kvm, + struct kvm_assigned_dev_kernel + *assigned_dev) +{ + kvm_free_assigned_irq(kvm, assigned_dev); + + pci_reset_function(assigned_dev->dev); + + pci_release_regions(assigned_dev->dev); + pci_disable_device(assigned_dev->dev); + pci_dev_put(assigned_dev->dev); + + list_del(&assigned_dev->list); + kfree(assigned_dev); +} + +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); + + kvm_free_assigned_device(kvm, assigned_dev); + } +} + +static int assigned_device_enable_host_intx(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + dev->host_irq = dev->dev->irq; + /* Even though this is PCI, we don't want to use shared + * interrupts. Sharing host devices with guest-assigned devices + * on the same interrupt line is not a happy situation: there + * are going to be long delays in accepting, acking, etc. + */ + if (request_irq(dev->host_irq, kvm_assigned_dev_intr, + 0, "kvm_assigned_intx_device", (void *)dev)) + return -EIO; + return 0; +} + +#ifdef __KVM_HAVE_MSI +static int assigned_device_enable_host_msi(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + int r; + + if (!dev->dev->msi_enabled) { + r = pci_enable_msi(dev->dev); + if (r) + return r; + } + + dev->host_irq = dev->dev->irq; + if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0, + "kvm_assigned_msi_device", (void *)dev)) { + pci_disable_msi(dev->dev); + return -EIO; + } + + return 0; +} +#endif + +#ifdef __KVM_HAVE_MSIX +static int assigned_device_enable_host_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + int i, r = -EINVAL; + + /* host_msix_entries and guest_msix_entries should have been + * initialized */ + if (dev->entries_nr == 0) + return r; + + r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); + if (r) + return r; + + for (i = 0; i < dev->entries_nr; i++) { + r = request_irq(dev->host_msix_entries[i].vector, + kvm_assigned_dev_intr, 0, + "kvm_assigned_msix_device", + (void *)dev); + /* FIXME: free requested_irq's on failure */ + if (r) + return r; + } + + return 0; +} + +#endif + +static int assigned_device_enable_guest_intx(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = irq->guest_irq; + return 0; +} + +#ifdef __KVM_HAVE_MSI +static int assigned_device_enable_guest_msi(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = -1; + dev->host_irq_disabled = false; + return 0; +} +#endif + +#ifdef __KVM_HAVE_MSIX +static int assigned_device_enable_guest_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = -1; + dev->host_irq_disabled = false; + return 0; +} +#endif + +static int assign_host_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + __u32 host_irq_type) +{ + int r = -EEXIST; + + if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK) + return r; + + switch (host_irq_type) { + case KVM_DEV_IRQ_HOST_INTX: + r = assigned_device_enable_host_intx(kvm, dev); + break; +#ifdef __KVM_HAVE_MSI + case KVM_DEV_IRQ_HOST_MSI: + r = assigned_device_enable_host_msi(kvm, dev); + break; +#endif +#ifdef __KVM_HAVE_MSIX + case KVM_DEV_IRQ_HOST_MSIX: + r = assigned_device_enable_host_msix(kvm, dev); + break; +#endif + default: + r = -EINVAL; + } + + if (!r) + dev->irq_requested_type |= host_irq_type; + + return r; +} + +static int assign_guest_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq, + unsigned long guest_irq_type) +{ + int id; + int r = -EEXIST; + + if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK) + return r; + + id = kvm_request_irq_source_id(kvm); + if (id < 0) + return id; + + dev->irq_source_id = id; + + switch (guest_irq_type) { + case KVM_DEV_IRQ_GUEST_INTX: + r = assigned_device_enable_guest_intx(kvm, dev, irq); + break; +#ifdef __KVM_HAVE_MSI + case KVM_DEV_IRQ_GUEST_MSI: + r = assigned_device_enable_guest_msi(kvm, dev, irq); + break; +#endif +#ifdef __KVM_HAVE_MSIX + case KVM_DEV_IRQ_GUEST_MSIX: + r = assigned_device_enable_guest_msix(kvm, dev, irq); + break; +#endif + default: + r = -EINVAL; + } + + if (!r) { + dev->irq_requested_type |= guest_irq_type; + kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); + } else + kvm_free_irq_source_id(kvm, dev->irq_source_id); + + return r; +} + +/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ +static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, + struct kvm_assigned_irq *assigned_irq) +{ + int r = -EINVAL; + struct kvm_assigned_dev_kernel *match; + unsigned long host_irq_type, guest_irq_type; + + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + + if (!irqchip_in_kernel(kvm)) + return r; + + mutex_lock(&kvm->lock); + r = -ENODEV; + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_irq->assigned_dev_id); + if (!match) + goto out; + + host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK); + guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK); + + r = -EINVAL; + /* can only assign one type at a time */ + if (hweight_long(host_irq_type) > 1) + goto out; + if (hweight_long(guest_irq_type) > 1) + goto out; + if (host_irq_type == 0 && guest_irq_type == 0) + goto out; + + r = 0; + if (host_irq_type) + r = assign_host_irq(kvm, match, host_irq_type); + if (r) + goto out; + + if (guest_irq_type) + r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type); +out: + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, + struct kvm_assigned_irq + *assigned_irq) +{ + int r = -ENODEV; + struct kvm_assigned_dev_kernel *match; + + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_irq->assigned_dev_id); + if (!match) + goto out; + + r = kvm_deassign_irq(kvm, match, assigned_irq->flags); +out: + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_assign_device(struct kvm *kvm, + struct kvm_assigned_pci_dev *assigned_dev) +{ + int r = 0; + struct kvm_assigned_dev_kernel *match; + struct pci_dev *dev; + + down_read(&kvm->slots_lock); + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_dev->assigned_dev_id); + if (match) { + /* device already assigned */ + r = -EEXIST; + goto out; + } + + match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL); + if (match == NULL) { + printk(KERN_INFO "%s: Couldn't allocate memory\n", + __func__); + r = -ENOMEM; + goto out; + } + dev = pci_get_bus_and_slot(assigned_dev->busnr, + assigned_dev->devfn); + if (!dev) { + printk(KERN_INFO "%s: host device not found\n", __func__); + r = -EINVAL; + goto out_free; + } + if (pci_enable_device(dev)) { + printk(KERN_INFO "%s: Could not enable PCI device\n", __func__); + r = -EBUSY; + goto out_put; + } + r = pci_request_regions(dev, "kvm_assigned_device"); + if (r) { + printk(KERN_INFO "%s: Could not get access to device regions\n", + __func__); + goto out_disable; + } + + pci_reset_function(dev); + + match->assigned_dev_id = assigned_dev->assigned_dev_id; + match->host_busnr = assigned_dev->busnr; + match->host_devfn = assigned_dev->devfn; + match->flags = assigned_dev->flags; + match->dev = dev; + spin_lock_init(&match->assigned_dev_lock); + match->irq_source_id = -1; + match->kvm = kvm; + match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq; + INIT_WORK(&match->interrupt_work, + kvm_assigned_dev_interrupt_work_handler); + + list_add(&match->list, &kvm->arch.assigned_dev_head); + + if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) { + if (!kvm->arch.iommu_domain) { + r = kvm_iommu_map_guest(kvm); + if (r) + goto out_list_del; + } + r = kvm_assign_device(kvm, match); + if (r) + goto out_list_del; + } + +out: + mutex_unlock(&kvm->lock); + up_read(&kvm->slots_lock); + return r; +out_list_del: + list_del(&match->list); + pci_release_regions(dev); +out_disable: + pci_disable_device(dev); +out_put: + pci_dev_put(dev); +out_free: + kfree(match); + mutex_unlock(&kvm->lock); + up_read(&kvm->slots_lock); + return r; +} + +static int kvm_vm_ioctl_deassign_device(struct kvm *kvm, + struct kvm_assigned_pci_dev *assigned_dev) +{ + int r = 0; + struct kvm_assigned_dev_kernel *match; + + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_dev->assigned_dev_id); + if (!match) { + printk(KERN_INFO "%s: device hasn't been assigned before, " + "so cannot be deassigned\n", __func__); + r = -EINVAL; + goto out; + } + + if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) + kvm_deassign_device(kvm, match); + + kvm_free_assigned_device(kvm, match); + +out: + mutex_unlock(&kvm->lock); + return r; +} + + +#ifdef __KVM_HAVE_MSIX +static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, + struct kvm_assigned_msix_nr *entry_nr) +{ + int r = 0; + struct kvm_assigned_dev_kernel *adev; + + mutex_lock(&kvm->lock); + + adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + entry_nr->assigned_dev_id); + if (!adev) { + r = -EINVAL; + goto msix_nr_out; + } + + if (adev->entries_nr == 0) { + adev->entries_nr = entry_nr->entry_nr; + if (adev->entries_nr == 0 || + adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) { + r = -EINVAL; + goto msix_nr_out; + } + + adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) * + entry_nr->entry_nr, + GFP_KERNEL); + if (!adev->host_msix_entries) { + r = -ENOMEM; + goto msix_nr_out; + } + adev->guest_msix_entries = kzalloc( + sizeof(struct kvm_guest_msix_entry) * + entry_nr->entry_nr, GFP_KERNEL); + if (!adev->guest_msix_entries) { + kfree(adev->host_msix_entries); + r = -ENOMEM; + goto msix_nr_out; + } + } else /* Not allowed set MSI-X number twice */ + r = -EINVAL; +msix_nr_out: + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm, + struct kvm_assigned_msix_entry *entry) +{ + int r = 0, i; + struct kvm_assigned_dev_kernel *adev; + + mutex_lock(&kvm->lock); + + adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + entry->assigned_dev_id); + + if (!adev) { + r = -EINVAL; + goto msix_entry_out; + } + + for (i = 0; i < adev->entries_nr; i++) + if (adev->guest_msix_entries[i].vector == 0 || + adev->guest_msix_entries[i].entry == entry->entry) { + adev->guest_msix_entries[i].entry = entry->entry; + adev->guest_msix_entries[i].vector = entry->gsi; + adev->host_msix_entries[i].entry = entry->entry; + break; + } + if (i == adev->entries_nr) { + r = -ENOSPC; + goto msix_entry_out; + } + +msix_entry_out: + mutex_unlock(&kvm->lock); + + return r; +} +#endif + +long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, + unsigned long arg) +{ + void __user *argp = (void __user *)arg; + int r = -ENOTTY; + + switch (ioctl) { + case KVM_ASSIGN_PCI_DEVICE: { + struct kvm_assigned_pci_dev assigned_dev; + + r = -EFAULT; + if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) + goto out; + r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev); + if (r) + goto out; + break; + } + case KVM_ASSIGN_IRQ: { + r = -EOPNOTSUPP; + break; + } +#ifdef KVM_CAP_ASSIGN_DEV_IRQ + case KVM_ASSIGN_DEV_IRQ: { + struct kvm_assigned_irq assigned_irq; + + r = -EFAULT; + if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) + goto out; + r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq); + if (r) + goto out; + break; + } + case KVM_DEASSIGN_DEV_IRQ: { + struct kvm_assigned_irq assigned_irq; + + r = -EFAULT; + if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) + goto out; + r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq); + if (r) + goto out; + break; + } +#endif +#ifdef KVM_CAP_DEVICE_DEASSIGNMENT + case KVM_DEASSIGN_PCI_DEVICE: { + struct kvm_assigned_pci_dev assigned_dev; + + r = -EFAULT; + if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) + goto out; + r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev); + if (r) + goto out; + break; + } +#endif +#ifdef KVM_CAP_IRQ_ROUTING + case KVM_SET_GSI_ROUTING: { + struct kvm_irq_routing routing; + struct kvm_irq_routing __user *urouting; + struct kvm_irq_routing_entry *entries; + + r = -EFAULT; + if (copy_from_user(&routing, argp, sizeof(routing))) + goto out; + r = -EINVAL; + if (routing.nr >= KVM_MAX_IRQ_ROUTES) + goto out; + if (routing.flags) + goto out; + r = -ENOMEM; + entries = vmalloc(routing.nr * sizeof(*entries)); + if (!entries) + goto out; + r = -EFAULT; + urouting = argp; + if (copy_from_user(entries, urouting->entries, + routing.nr * sizeof(*entries))) + goto out_free_irq_routing; + r = kvm_set_irq_routing(kvm, entries, routing.nr, + routing.flags); + out_free_irq_routing: + vfree(entries); + break; + } +#endif /* KVM_CAP_IRQ_ROUTING */ +#ifdef __KVM_HAVE_MSIX + case KVM_ASSIGN_SET_MSIX_NR: { + struct kvm_assigned_msix_nr entry_nr; + r = -EFAULT; + if (copy_from_user(&entry_nr, argp, sizeof entry_nr)) + goto out; + r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr); + if (r) + goto out; + break; + } + case KVM_ASSIGN_SET_MSIX_ENTRY: { + struct kvm_assigned_msix_entry entry; + r = -EFAULT; + if (copy_from_user(&entry, argp, sizeof entry)) + goto out; + r = kvm_vm_ioctl_set_msix_entry(kvm, &entry); + if (r) + goto out; + break; + } +#endif + } +out: + return r; +} + diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index bb4ebd8..30f70fd 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -61,10 +61,8 @@ irqfd_inject(struct work_struct *work) struct _irqfd *irqfd = container_of(work, struct _irqfd, inject); struct kvm *kvm = irqfd->kvm; - mutex_lock(&kvm->irq_lock); kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1); kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0); - mutex_unlock(&kvm->irq_lock); } /* diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 9fe140b..38a2d20 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -182,6 +182,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) union kvm_ioapic_redirect_entry entry; int ret = 1; + mutex_lock(&ioapic->lock); if (irq >= 0 && irq < IOAPIC_NUM_PINS) { entry = ioapic->redirtbl[irq]; level ^= entry.fields.polarity; @@ -198,34 +199,51 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) } trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0); } + mutex_unlock(&ioapic->lock); + return ret; } -static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int pin, - int trigger_mode) +static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector, + int trigger_mode) { - union kvm_ioapic_redirect_entry *ent; + int i; + + for (i = 0; i < IOAPIC_NUM_PINS; i++) { + union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i]; - ent = &ioapic->redirtbl[pin]; + if (ent->fields.vector != vector) + continue; - kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, pin); + /* + * We are dropping lock while calling ack notifiers because ack + * notifier callbacks for assigned devices call into IOAPIC + * recursively. Since remote_irr is cleared only after call + * to notifiers if the same vector will be delivered while lock + * is dropped it will be put into irr and will be delivered + * after ack notifier returns. + */ + mutex_unlock(&ioapic->lock); + kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i); + mutex_lock(&ioapic->lock); + + if (trigger_mode != IOAPIC_LEVEL_TRIG) + continue; - if (trigger_mode == IOAPIC_LEVEL_TRIG) { ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); ent->fields.remote_irr = 0; - if (!ent->fields.mask && (ioapic->irr & (1 << pin))) - ioapic_service(ioapic, pin); + if (!ent->fields.mask && (ioapic->irr & (1 << i))) + ioapic_service(ioapic, i); } } void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; - int i; - for (i = 0; i < IOAPIC_NUM_PINS; i++) - if (ioapic->redirtbl[i].fields.vector == vector) - __kvm_ioapic_update_eoi(ioapic, i, trigger_mode); + mutex_lock(&ioapic->lock); + __kvm_ioapic_update_eoi(ioapic, vector, trigger_mode); + mutex_unlock(&ioapic->lock); } static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev) @@ -250,8 +268,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, ioapic_debug("addr %lx\n", (unsigned long)addr); ASSERT(!(addr & 0xf)); /* check alignment */ - mutex_lock(&ioapic->kvm->irq_lock); addr &= 0xff; + mutex_lock(&ioapic->lock); switch (addr) { case IOAPIC_REG_SELECT: result = ioapic->ioregsel; @@ -265,6 +283,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, result = 0; break; } + mutex_unlock(&ioapic->lock); + switch (len) { case 8: *(u64 *) val = result; @@ -277,7 +297,6 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, default: printk(KERN_WARNING "ioapic: wrong length %d\n", len); } - mutex_unlock(&ioapic->kvm->irq_lock); return 0; } @@ -293,15 +312,15 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, (void*)addr, len, val); ASSERT(!(addr & 0xf)); /* check alignment */ - mutex_lock(&ioapic->kvm->irq_lock); if (len == 4 || len == 8) data = *(u32 *) val; else { printk(KERN_WARNING "ioapic: Unsupported size %d\n", len); - goto unlock; + return 0; } addr &= 0xff; + mutex_lock(&ioapic->lock); switch (addr) { case IOAPIC_REG_SELECT: ioapic->ioregsel = data; @@ -312,15 +331,14 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, break; #ifdef CONFIG_IA64 case IOAPIC_REG_EOI: - kvm_ioapic_update_eoi(ioapic->kvm, data, IOAPIC_LEVEL_TRIG); + __kvm_ioapic_update_eoi(ioapic, data, IOAPIC_LEVEL_TRIG); break; #endif default: break; } -unlock: - mutex_unlock(&ioapic->kvm->irq_lock); + mutex_unlock(&ioapic->lock); return 0; } @@ -349,6 +367,7 @@ int kvm_ioapic_init(struct kvm *kvm) ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL); if (!ioapic) return -ENOMEM; + mutex_init(&ioapic->lock); kvm->arch.vioapic = ioapic; kvm_ioapic_reset(ioapic); kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops); @@ -360,3 +379,26 @@ int kvm_ioapic_init(struct kvm *kvm) return ret; } +int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) +{ + struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); + if (!ioapic) + return -EINVAL; + + mutex_lock(&ioapic->lock); + memcpy(state, ioapic, sizeof(struct kvm_ioapic_state)); + mutex_unlock(&ioapic->lock); + return 0; +} + +int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) +{ + struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); + if (!ioapic) + return -EINVAL; + + mutex_lock(&ioapic->lock); + memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); + mutex_unlock(&ioapic->lock); + return 0; +} diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index 7080b71..419c43b 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -41,9 +41,11 @@ struct kvm_ioapic { u32 irr; u32 pad; union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS]; + unsigned long irq_states[IOAPIC_NUM_PINS]; struct kvm_io_device dev; struct kvm *kvm; void (*ack_notifier)(void *opaque, int irq); + struct mutex lock; }; #ifdef DEBUG @@ -73,4 +75,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); void kvm_ioapic_reset(struct kvm_ioapic *ioapic); int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq); +int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); +int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); + #endif diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 001663f..9b07734 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -31,20 +31,39 @@ #include "ioapic.h" +static inline int kvm_irq_line_state(unsigned long *irq_state, + int irq_source_id, int level) +{ + /* Logical OR for level trig interrupt */ + if (level) + set_bit(irq_source_id, irq_state); + else + clear_bit(irq_source_id, irq_state); + + return !!(*irq_state); +} + static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) + struct kvm *kvm, int irq_source_id, int level) { #ifdef CONFIG_X86 - return kvm_pic_set_irq(pic_irqchip(kvm), e->irqchip.pin, level); + struct kvm_pic *pic = pic_irqchip(kvm); + level = kvm_irq_line_state(&pic->irq_states[e->irqchip.pin], + irq_source_id, level); + return kvm_pic_set_irq(pic, e->irqchip.pin, level); #else return -1; #endif } static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) + struct kvm *kvm, int irq_source_id, int level) { - return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level); + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + level = kvm_irq_line_state(&ioapic->irq_states[e->irqchip.pin], + irq_source_id, level); + + return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, level); } inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) @@ -63,8 +82,6 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, int i, r = -1; struct kvm_vcpu *vcpu, *lowest = NULL; - WARN_ON(!mutex_is_locked(&kvm->irq_lock)); - if (irq->dest_mode == 0 && irq->dest_id == 0xff && kvm_is_dm_lowest_prio(irq)) printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); @@ -96,10 +113,13 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, } static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) + struct kvm *kvm, int irq_source_id, int level) { struct kvm_lapic_irq irq; + if (!level) + return -1; + trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data); irq.dest_id = (e->msi.address_lo & @@ -116,78 +136,67 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, return kvm_irq_delivery_to_apic(kvm, NULL, &irq); } -/* This should be called with the kvm->irq_lock mutex held +/* * Return value: * < 0 Interrupt was ignored (masked or not delivered for other reasons) * = 0 Interrupt was coalesced (previous irq is still pending) * > 0 Number of CPUs interrupt was delivered to */ -int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) +int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) { - struct kvm_kernel_irq_routing_entry *e; - unsigned long *irq_state, sig_level; - int ret = -1; + struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS]; + int ret = -1, i = 0; + struct kvm_irq_routing_table *irq_rt; + struct hlist_node *n; trace_kvm_set_irq(irq, level, irq_source_id); - WARN_ON(!mutex_is_locked(&kvm->irq_lock)); - - if (irq < KVM_IOAPIC_NUM_PINS) { - irq_state = (unsigned long *)&kvm->arch.irq_states[irq]; - - /* Logical OR for level trig interrupt */ - if (level) - set_bit(irq_source_id, irq_state); - else - clear_bit(irq_source_id, irq_state); - sig_level = !!(*irq_state); - } else if (!level) - return ret; - else /* Deal with MSI/MSI-X */ - sig_level = 1; - /* Not possible to detect if the guest uses the PIC or the * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ - list_for_each_entry(e, &kvm->irq_routing, link) - if (e->gsi == irq) { - int r = e->set(e, kvm, sig_level); - if (r < 0) - continue; + rcu_read_lock(); + irq_rt = rcu_dereference(kvm->irq_routing); + if (irq < irq_rt->nr_rt_entries) + hlist_for_each_entry(e, n, &irq_rt->map[irq], link) + irq_set[i++] = *e; + rcu_read_unlock(); + + while(i--) { + int r; + r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level); + if (r < 0) + continue; + + ret = r + ((ret < 0) ? 0 : ret); + } - ret = r + ((ret < 0) ? 0 : ret); - } return ret; } void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) { - struct kvm_kernel_irq_routing_entry *e; struct kvm_irq_ack_notifier *kian; struct hlist_node *n; - unsigned gsi = pin; + int gsi; trace_kvm_ack_irq(irqchip, pin); - list_for_each_entry(e, &kvm->irq_routing, link) - if (e->type == KVM_IRQ_ROUTING_IRQCHIP && - e->irqchip.irqchip == irqchip && - e->irqchip.pin == pin) { - gsi = e->gsi; - break; - } - - hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link) - if (kian->gsi == gsi) - kian->irq_acked(kian); + rcu_read_lock(); + gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + if (gsi != -1) + hlist_for_each_entry_rcu(kian, n, &kvm->irq_ack_notifier_list, + link) + if (kian->gsi == gsi) + kian->irq_acked(kian); + rcu_read_unlock(); } void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian) { mutex_lock(&kvm->irq_lock); - hlist_add_head(&kian->link, &kvm->arch.irq_ack_notifier_list); + hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list); mutex_unlock(&kvm->irq_lock); } @@ -195,8 +204,9 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian) { mutex_lock(&kvm->irq_lock); - hlist_del_init(&kian->link); + hlist_del_init_rcu(&kian->link); mutex_unlock(&kvm->irq_lock); + synchronize_rcu(); } int kvm_request_irq_source_id(struct kvm *kvm) @@ -205,16 +215,17 @@ int kvm_request_irq_source_id(struct kvm *kvm) int irq_source_id; mutex_lock(&kvm->irq_lock); - irq_source_id = find_first_zero_bit(bitmap, - sizeof(kvm->arch.irq_sources_bitmap)); + irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG); - if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { + if (irq_source_id >= BITS_PER_LONG) { printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n"); - return -EFAULT; + irq_source_id = -EFAULT; + goto unlock; } ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID); set_bit(irq_source_id, bitmap); +unlock: mutex_unlock(&kvm->irq_lock); return irq_source_id; @@ -228,13 +239,23 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) mutex_lock(&kvm->irq_lock); if (irq_source_id < 0 || - irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { + irq_source_id >= BITS_PER_LONG) { printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); - return; + goto unlock; } - for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) - clear_bit(irq_source_id, &kvm->arch.irq_states[i]); clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); + if (!irqchip_in_kernel(kvm)) + goto unlock; + + for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) { + clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]); + if (i >= 16) + continue; +#ifdef CONFIG_X86 + clear_bit(irq_source_id, &pic_irqchip(kvm)->irq_states[i]); +#endif + } +unlock: mutex_unlock(&kvm->irq_lock); } @@ -243,7 +264,7 @@ void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, { mutex_lock(&kvm->irq_lock); kimn->irq = irq; - hlist_add_head(&kimn->link, &kvm->mask_notifier_list); + hlist_add_head_rcu(&kimn->link, &kvm->mask_notifier_list); mutex_unlock(&kvm->irq_lock); } @@ -251,8 +272,9 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn) { mutex_lock(&kvm->irq_lock); - hlist_del(&kimn->link); + hlist_del_rcu(&kimn->link); mutex_unlock(&kvm->irq_lock); + synchronize_rcu(); } void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask) @@ -260,33 +282,37 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask) struct kvm_irq_mask_notifier *kimn; struct hlist_node *n; - WARN_ON(!mutex_is_locked(&kvm->irq_lock)); - - hlist_for_each_entry(kimn, n, &kvm->mask_notifier_list, link) + rcu_read_lock(); + hlist_for_each_entry_rcu(kimn, n, &kvm->mask_notifier_list, link) if (kimn->irq == irq) kimn->func(kimn, mask); -} - -static void __kvm_free_irq_routing(struct list_head *irq_routing) -{ - struct kvm_kernel_irq_routing_entry *e, *n; - - list_for_each_entry_safe(e, n, irq_routing, link) - kfree(e); + rcu_read_unlock(); } void kvm_free_irq_routing(struct kvm *kvm) { - mutex_lock(&kvm->irq_lock); - __kvm_free_irq_routing(&kvm->irq_routing); - mutex_unlock(&kvm->irq_lock); + /* Called only during vm destruction. Nobody can use the pointer + at this stage */ + kfree(kvm->irq_routing); } -static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, +static int setup_routing_entry(struct kvm_irq_routing_table *rt, + struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { int r = -EINVAL; int delta; + struct kvm_kernel_irq_routing_entry *ei; + struct hlist_node *n; + + /* + * Do not allow GSI to be mapped to the same irqchip more than once. + * Allow only one to one mapping between GSI and MSI. + */ + hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link) + if (ei->type == KVM_IRQ_ROUTING_MSI || + ue->u.irqchip.irqchip == ei->irqchip.irqchip) + return r; e->gsi = ue->gsi; e->type = ue->type; @@ -309,6 +335,9 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, } e->irqchip.irqchip = ue->u.irqchip.irqchip; e->irqchip.pin = ue->u.irqchip.pin + delta; + if (e->irqchip.pin >= KVM_IOAPIC_NUM_PINS) + goto out; + rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi; break; case KVM_IRQ_ROUTING_MSI: e->set = kvm_set_msi; @@ -319,6 +348,8 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, default: goto out; } + + hlist_add_head(&e->link, &rt->map[e->gsi]); r = 0; out: return r; @@ -330,43 +361,53 @@ int kvm_set_irq_routing(struct kvm *kvm, unsigned nr, unsigned flags) { - struct list_head irq_list = LIST_HEAD_INIT(irq_list); - struct list_head tmp = LIST_HEAD_INIT(tmp); - struct kvm_kernel_irq_routing_entry *e = NULL; - unsigned i; + struct kvm_irq_routing_table *new, *old; + u32 i, j, nr_rt_entries = 0; int r; for (i = 0; i < nr; ++i) { + if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES) + return -EINVAL; + nr_rt_entries = max(nr_rt_entries, ue[i].gsi); + } + + nr_rt_entries += 1; + + new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)) + + (nr * sizeof(struct kvm_kernel_irq_routing_entry)), + GFP_KERNEL); + + if (!new) + return -ENOMEM; + + new->rt_entries = (void *)&new->map[nr_rt_entries]; + + new->nr_rt_entries = nr_rt_entries; + for (i = 0; i < 3; i++) + for (j = 0; j < KVM_IOAPIC_NUM_PINS; j++) + new->chip[i][j] = -1; + + for (i = 0; i < nr; ++i) { r = -EINVAL; - if (ue->gsi >= KVM_MAX_IRQ_ROUTES) - goto out; if (ue->flags) goto out; - r = -ENOMEM; - e = kzalloc(sizeof(*e), GFP_KERNEL); - if (!e) - goto out; - r = setup_routing_entry(e, ue); + r = setup_routing_entry(new, &new->rt_entries[i], ue); if (r) goto out; ++ue; - list_add(&e->link, &irq_list); - e = NULL; } mutex_lock(&kvm->irq_lock); - list_splice(&kvm->irq_routing, &tmp); - INIT_LIST_HEAD(&kvm->irq_routing); - list_splice(&irq_list, &kvm->irq_routing); - INIT_LIST_HEAD(&irq_list); - list_splice(&tmp, &irq_list); + old = kvm->irq_routing; + rcu_assign_pointer(kvm->irq_routing, new); mutex_unlock(&kvm->irq_lock); + synchronize_rcu(); + new = old; r = 0; out: - kfree(e); - __kvm_free_irq_routing(&irq_list); + kfree(new); return r; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 7495ce3..f92ba13 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -43,6 +43,7 @@ #include <linux/swap.h> #include <linux/bitops.h> #include <linux/spinlock.h> +#include <linux/compat.h> #include <asm/processor.h> #include <asm/io.h> @@ -53,12 +54,6 @@ #include "coalesced_mmio.h" #endif -#ifdef KVM_CAP_DEVICE_ASSIGNMENT -#include <linux/pci.h> -#include <linux/interrupt.h> -#include "irq.h" -#endif - #define CREATE_TRACE_POINTS #include <trace/events/kvm.h> @@ -75,6 +70,8 @@ DEFINE_SPINLOCK(kvm_lock); LIST_HEAD(vm_list); static cpumask_var_t cpus_hardware_enabled; +static int kvm_usage_count = 0; +static atomic_t hardware_enable_failed; struct kmem_cache *kvm_vcpu_cache; EXPORT_SYMBOL_GPL(kvm_vcpu_cache); @@ -85,615 +82,13 @@ struct dentry *kvm_debugfs_dir; static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); +static int hardware_enable_all(void); +static void hardware_disable_all(void); static bool kvm_rebooting; static bool largepages_enabled = true; -#ifdef KVM_CAP_DEVICE_ASSIGNMENT -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); - if (match->assigned_dev_id == assigned_dev_id) - return match; - } - return NULL; -} - -static int find_index_from_host_irq(struct kvm_assigned_dev_kernel - *assigned_dev, int irq) -{ - int i, index; - struct msix_entry *host_msix_entries; - - host_msix_entries = assigned_dev->host_msix_entries; - - index = -1; - for (i = 0; i < assigned_dev->entries_nr; i++) - if (irq == host_msix_entries[i].vector) { - index = i; - break; - } - if (index < 0) { - printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n"); - return 0; - } - - return index; -} - -static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) -{ - struct kvm_assigned_dev_kernel *assigned_dev; - struct kvm *kvm; - int i; - - assigned_dev = container_of(work, struct kvm_assigned_dev_kernel, - interrupt_work); - kvm = assigned_dev->kvm; - - mutex_lock(&kvm->irq_lock); - spin_lock_irq(&assigned_dev->assigned_dev_lock); - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - struct kvm_guest_msix_entry *guest_entries = - assigned_dev->guest_msix_entries; - for (i = 0; i < assigned_dev->entries_nr; i++) { - if (!(guest_entries[i].flags & - KVM_ASSIGNED_MSIX_PENDING)) - continue; - guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING; - kvm_set_irq(assigned_dev->kvm, - assigned_dev->irq_source_id, - guest_entries[i].vector, 1); - } - } else - kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - assigned_dev->guest_irq, 1); - - spin_unlock_irq(&assigned_dev->assigned_dev_lock); - mutex_unlock(&assigned_dev->kvm->irq_lock); -} - -static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) -{ - unsigned long flags; - struct kvm_assigned_dev_kernel *assigned_dev = - (struct kvm_assigned_dev_kernel *) dev_id; - - spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags); - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - int index = find_index_from_host_irq(assigned_dev, irq); - if (index < 0) - goto out; - assigned_dev->guest_msix_entries[index].flags |= - KVM_ASSIGNED_MSIX_PENDING; - } - - schedule_work(&assigned_dev->interrupt_work); - - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) { - disable_irq_nosync(irq); - assigned_dev->host_irq_disabled = true; - } - -out: - spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags); - return IRQ_HANDLED; -} - -/* Ack the irq line for an assigned device */ -static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) -{ - struct kvm_assigned_dev_kernel *dev; - unsigned long flags; - - if (kian->gsi == -1) - return; - - dev = container_of(kian, struct kvm_assigned_dev_kernel, - ack_notifier); - - kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0); - - /* The guest irq may be shared so this ack may be - * from another device. - */ - spin_lock_irqsave(&dev->assigned_dev_lock, flags); - if (dev->host_irq_disabled) { - enable_irq(dev->host_irq); - dev->host_irq_disabled = false; - } - spin_unlock_irqrestore(&dev->assigned_dev_lock, flags); -} - -static void deassign_guest_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier); - assigned_dev->ack_notifier.gsi = -1; - - if (assigned_dev->irq_source_id != -1) - kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); - assigned_dev->irq_source_id = -1; - assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK); -} - -/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ -static void deassign_host_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - /* - * In kvm_free_device_irq, cancel_work_sync return true if: - * 1. work is scheduled, and then cancelled. - * 2. work callback is executed. - * - * The first one ensured that the irq is disabled and no more events - * would happen. But for the second one, the irq may be enabled (e.g. - * for MSI). So we disable irq here to prevent further events. - * - * Notice this maybe result in nested disable if the interrupt type is - * INTx, but it's OK for we are going to free it. - * - * If this function is a part of VM destroy, please ensure that till - * now, the kvm state is still legal for probably we also have to wait - * interrupt_work done. - */ - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - int i; - for (i = 0; i < assigned_dev->entries_nr; i++) - disable_irq_nosync(assigned_dev-> - host_msix_entries[i].vector); - - cancel_work_sync(&assigned_dev->interrupt_work); - - for (i = 0; i < assigned_dev->entries_nr; i++) - free_irq(assigned_dev->host_msix_entries[i].vector, - (void *)assigned_dev); - - assigned_dev->entries_nr = 0; - kfree(assigned_dev->host_msix_entries); - kfree(assigned_dev->guest_msix_entries); - pci_disable_msix(assigned_dev->dev); - } else { - /* Deal with MSI and INTx */ - disable_irq_nosync(assigned_dev->host_irq); - cancel_work_sync(&assigned_dev->interrupt_work); - - free_irq(assigned_dev->host_irq, (void *)assigned_dev); - - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI) - pci_disable_msi(assigned_dev->dev); - } - - assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK); -} - -static int kvm_deassign_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev, - unsigned long irq_requested_type) -{ - unsigned long guest_irq_type, host_irq_type; - - if (!irqchip_in_kernel(kvm)) - return -EINVAL; - /* no irq assignment to deassign */ - if (!assigned_dev->irq_requested_type) - return -ENXIO; - - host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK; - guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK; - - if (host_irq_type) - deassign_host_irq(kvm, assigned_dev); - if (guest_irq_type) - deassign_guest_irq(kvm, assigned_dev); - - return 0; -} - -static void kvm_free_assigned_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type); -} - -static void kvm_free_assigned_device(struct kvm *kvm, - struct kvm_assigned_dev_kernel - *assigned_dev) -{ - kvm_free_assigned_irq(kvm, assigned_dev); - - pci_reset_function(assigned_dev->dev); - - pci_release_regions(assigned_dev->dev); - pci_disable_device(assigned_dev->dev); - pci_dev_put(assigned_dev->dev); - - list_del(&assigned_dev->list); - kfree(assigned_dev); -} - -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); - - kvm_free_assigned_device(kvm, assigned_dev); - } -} - -static int assigned_device_enable_host_intx(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - dev->host_irq = dev->dev->irq; - /* Even though this is PCI, we don't want to use shared - * interrupts. Sharing host devices with guest-assigned devices - * on the same interrupt line is not a happy situation: there - * are going to be long delays in accepting, acking, etc. - */ - if (request_irq(dev->host_irq, kvm_assigned_dev_intr, - 0, "kvm_assigned_intx_device", (void *)dev)) - return -EIO; - return 0; -} - -#ifdef __KVM_HAVE_MSI -static int assigned_device_enable_host_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - int r; - - if (!dev->dev->msi_enabled) { - r = pci_enable_msi(dev->dev); - if (r) - return r; - } - - dev->host_irq = dev->dev->irq; - if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0, - "kvm_assigned_msi_device", (void *)dev)) { - pci_disable_msi(dev->dev); - return -EIO; - } - - return 0; -} -#endif - -#ifdef __KVM_HAVE_MSIX -static int assigned_device_enable_host_msix(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - int i, r = -EINVAL; - - /* host_msix_entries and guest_msix_entries should have been - * initialized */ - if (dev->entries_nr == 0) - return r; - - r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); - if (r) - return r; - - for (i = 0; i < dev->entries_nr; i++) { - r = request_irq(dev->host_msix_entries[i].vector, - kvm_assigned_dev_intr, 0, - "kvm_assigned_msix_device", - (void *)dev); - /* FIXME: free requested_irq's on failure */ - if (r) - return r; - } - - return 0; -} - -#endif - -static int assigned_device_enable_guest_intx(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = irq->guest_irq; - return 0; -} - -#ifdef __KVM_HAVE_MSI -static int assigned_device_enable_guest_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = -1; - dev->host_irq_disabled = false; - return 0; -} -#endif -#ifdef __KVM_HAVE_MSIX -static int assigned_device_enable_guest_msix(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = -1; - dev->host_irq_disabled = false; - return 0; -} -#endif - -static int assign_host_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - __u32 host_irq_type) -{ - int r = -EEXIST; - - if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK) - return r; - - switch (host_irq_type) { - case KVM_DEV_IRQ_HOST_INTX: - r = assigned_device_enable_host_intx(kvm, dev); - break; -#ifdef __KVM_HAVE_MSI - case KVM_DEV_IRQ_HOST_MSI: - r = assigned_device_enable_host_msi(kvm, dev); - break; -#endif -#ifdef __KVM_HAVE_MSIX - case KVM_DEV_IRQ_HOST_MSIX: - r = assigned_device_enable_host_msix(kvm, dev); - break; -#endif - default: - r = -EINVAL; - } - - if (!r) - dev->irq_requested_type |= host_irq_type; - - return r; -} - -static int assign_guest_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq, - unsigned long guest_irq_type) -{ - int id; - int r = -EEXIST; - - if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK) - return r; - - id = kvm_request_irq_source_id(kvm); - if (id < 0) - return id; - - dev->irq_source_id = id; - - switch (guest_irq_type) { - case KVM_DEV_IRQ_GUEST_INTX: - r = assigned_device_enable_guest_intx(kvm, dev, irq); - break; -#ifdef __KVM_HAVE_MSI - case KVM_DEV_IRQ_GUEST_MSI: - r = assigned_device_enable_guest_msi(kvm, dev, irq); - break; -#endif -#ifdef __KVM_HAVE_MSIX - case KVM_DEV_IRQ_GUEST_MSIX: - r = assigned_device_enable_guest_msix(kvm, dev, irq); - break; -#endif - default: - r = -EINVAL; - } - - if (!r) { - dev->irq_requested_type |= guest_irq_type; - kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); - } else - kvm_free_irq_source_id(kvm, dev->irq_source_id); - - return r; -} - -/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ -static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, - struct kvm_assigned_irq *assigned_irq) -{ - int r = -EINVAL; - struct kvm_assigned_dev_kernel *match; - unsigned long host_irq_type, guest_irq_type; - - if (!capable(CAP_SYS_RAWIO)) - return -EPERM; - - if (!irqchip_in_kernel(kvm)) - return r; - - mutex_lock(&kvm->lock); - r = -ENODEV; - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_irq->assigned_dev_id); - if (!match) - goto out; - - host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK); - guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK); - - r = -EINVAL; - /* can only assign one type at a time */ - if (hweight_long(host_irq_type) > 1) - goto out; - if (hweight_long(guest_irq_type) > 1) - goto out; - if (host_irq_type == 0 && guest_irq_type == 0) - goto out; - - r = 0; - if (host_irq_type) - r = assign_host_irq(kvm, match, host_irq_type); - if (r) - goto out; - - if (guest_irq_type) - r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type); -out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, - struct kvm_assigned_irq - *assigned_irq) -{ - int r = -ENODEV; - struct kvm_assigned_dev_kernel *match; - - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_irq->assigned_dev_id); - if (!match) - goto out; - - r = kvm_deassign_irq(kvm, match, assigned_irq->flags); -out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_assign_device(struct kvm *kvm, - struct kvm_assigned_pci_dev *assigned_dev) -{ - int r = 0; - struct kvm_assigned_dev_kernel *match; - struct pci_dev *dev; - - down_read(&kvm->slots_lock); - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_dev->assigned_dev_id); - if (match) { - /* device already assigned */ - r = -EEXIST; - goto out; - } - - match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL); - if (match == NULL) { - printk(KERN_INFO "%s: Couldn't allocate memory\n", - __func__); - r = -ENOMEM; - goto out; - } - dev = pci_get_bus_and_slot(assigned_dev->busnr, - assigned_dev->devfn); - if (!dev) { - printk(KERN_INFO "%s: host device not found\n", __func__); - r = -EINVAL; - goto out_free; - } - if (pci_enable_device(dev)) { - printk(KERN_INFO "%s: Could not enable PCI device\n", __func__); - r = -EBUSY; - goto out_put; - } - r = pci_request_regions(dev, "kvm_assigned_device"); - if (r) { - printk(KERN_INFO "%s: Could not get access to device regions\n", - __func__); - goto out_disable; - } - - pci_reset_function(dev); - - match->assigned_dev_id = assigned_dev->assigned_dev_id; - match->host_busnr = assigned_dev->busnr; - match->host_devfn = assigned_dev->devfn; - match->flags = assigned_dev->flags; - match->dev = dev; - spin_lock_init(&match->assigned_dev_lock); - match->irq_source_id = -1; - match->kvm = kvm; - match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq; - INIT_WORK(&match->interrupt_work, - kvm_assigned_dev_interrupt_work_handler); - - list_add(&match->list, &kvm->arch.assigned_dev_head); - - if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) { - if (!kvm->arch.iommu_domain) { - r = kvm_iommu_map_guest(kvm); - if (r) - goto out_list_del; - } - r = kvm_assign_device(kvm, match); - if (r) - goto out_list_del; - } - -out: - mutex_unlock(&kvm->lock); - up_read(&kvm->slots_lock); - return r; -out_list_del: - list_del(&match->list); - pci_release_regions(dev); -out_disable: - pci_disable_device(dev); -out_put: - pci_dev_put(dev); -out_free: - kfree(match); - mutex_unlock(&kvm->lock); - up_read(&kvm->slots_lock); - return r; -} -#endif - -#ifdef KVM_CAP_DEVICE_DEASSIGNMENT -static int kvm_vm_ioctl_deassign_device(struct kvm *kvm, - struct kvm_assigned_pci_dev *assigned_dev) -{ - int r = 0; - struct kvm_assigned_dev_kernel *match; - - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_dev->assigned_dev_id); - if (!match) { - printk(KERN_INFO "%s: device hasn't been assigned before, " - "so cannot be deassigned\n", __func__); - r = -EINVAL; - goto out; - } - - if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) - kvm_deassign_device(kvm, match); - - kvm_free_assigned_device(kvm, match); - -out: - mutex_unlock(&kvm->lock); - return r; -} -#endif - inline int kvm_is_mmio_pfn(pfn_t pfn) { if (pfn_valid(pfn)) { @@ -949,6 +344,7 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { static struct kvm *kvm_create_vm(void) { + int r = 0; struct kvm *kvm = kvm_arch_create_vm(); #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET struct page *page; @@ -956,16 +352,21 @@ static struct kvm *kvm_create_vm(void) if (IS_ERR(kvm)) goto out; + + r = hardware_enable_all(); + if (r) + goto out_err_nodisable; + #ifdef CONFIG_HAVE_KVM_IRQCHIP - INIT_LIST_HEAD(&kvm->irq_routing); INIT_HLIST_HEAD(&kvm->mask_notifier_list); + INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) { - kfree(kvm); - return ERR_PTR(-ENOMEM); + r = -ENOMEM; + goto out_err; } kvm->coalesced_mmio_ring = (struct kvm_coalesced_mmio_ring *)page_address(page); @@ -973,15 +374,13 @@ static struct kvm *kvm_create_vm(void) #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) { - int err; kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops; - err = mmu_notifier_register(&kvm->mmu_notifier, current->mm); - if (err) { + r = mmu_notifier_register(&kvm->mmu_notifier, current->mm); + if (r) { #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET put_page(page); #endif - kfree(kvm); - return ERR_PTR(err); + goto out_err; } } #endif @@ -1005,6 +404,12 @@ static struct kvm *kvm_create_vm(void) #endif out: return kvm; + +out_err: + hardware_disable_all(); +out_err_nodisable: + kfree(kvm); + return ERR_PTR(r); } /* @@ -1063,6 +468,7 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_arch_flush_shadow(kvm); #endif kvm_arch_destroy_vm(kvm); + hardware_disable_all(); mmdrop(mm); } @@ -1689,9 +1095,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) if (signal_pending(current)) break; - vcpu_put(vcpu); schedule(); - vcpu_load(vcpu); } finish_wait(&vcpu->wq, &wait); @@ -1705,6 +1109,21 @@ void kvm_resched(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_resched); +void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu) +{ + ktime_t expires; + DEFINE_WAIT(wait); + + prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + + /* Sleep for 100 us, and hope lock-holder got scheduled */ + expires = ktime_add_ns(ktime_get(), 100000UL); + schedule_hrtimeout(&expires, HRTIMER_MODE_ABS); + + finish_wait(&vcpu->wq, &wait); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); + static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct kvm_vcpu *vcpu = vma->vm_file->private_data; @@ -1828,88 +1247,6 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) return 0; } -#ifdef __KVM_HAVE_MSIX -static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, - struct kvm_assigned_msix_nr *entry_nr) -{ - int r = 0; - struct kvm_assigned_dev_kernel *adev; - - mutex_lock(&kvm->lock); - - adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - entry_nr->assigned_dev_id); - if (!adev) { - r = -EINVAL; - goto msix_nr_out; - } - - if (adev->entries_nr == 0) { - adev->entries_nr = entry_nr->entry_nr; - if (adev->entries_nr == 0 || - adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) { - r = -EINVAL; - goto msix_nr_out; - } - - adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) * - entry_nr->entry_nr, - GFP_KERNEL); - if (!adev->host_msix_entries) { - r = -ENOMEM; - goto msix_nr_out; - } - adev->guest_msix_entries = kzalloc( - sizeof(struct kvm_guest_msix_entry) * - entry_nr->entry_nr, GFP_KERNEL); - if (!adev->guest_msix_entries) { - kfree(adev->host_msix_entries); - r = -ENOMEM; - goto msix_nr_out; - } - } else /* Not allowed set MSI-X number twice */ - r = -EINVAL; -msix_nr_out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm, - struct kvm_assigned_msix_entry *entry) -{ - int r = 0, i; - struct kvm_assigned_dev_kernel *adev; - - mutex_lock(&kvm->lock); - - adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - entry->assigned_dev_id); - - if (!adev) { - r = -EINVAL; - goto msix_entry_out; - } - - for (i = 0; i < adev->entries_nr; i++) - if (adev->guest_msix_entries[i].vector == 0 || - adev->guest_msix_entries[i].entry == entry->entry) { - adev->guest_msix_entries[i].entry = entry->entry; - adev->guest_msix_entries[i].vector = entry->gsi; - adev->host_msix_entries[i].entry = entry->entry; - break; - } - if (i == adev->entries_nr) { - r = -ENOSPC; - goto msix_entry_out; - } - -msix_entry_out: - mutex_unlock(&kvm->lock); - - return r; -} -#endif - static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2168,112 +1505,6 @@ static long kvm_vm_ioctl(struct file *filp, break; } #endif -#ifdef KVM_CAP_DEVICE_ASSIGNMENT - case KVM_ASSIGN_PCI_DEVICE: { - struct kvm_assigned_pci_dev assigned_dev; - - r = -EFAULT; - if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) - goto out; - r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev); - if (r) - goto out; - break; - } - case KVM_ASSIGN_IRQ: { - r = -EOPNOTSUPP; - break; - } -#ifdef KVM_CAP_ASSIGN_DEV_IRQ - case KVM_ASSIGN_DEV_IRQ: { - struct kvm_assigned_irq assigned_irq; - - r = -EFAULT; - if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) - goto out; - r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq); - if (r) - goto out; - break; - } - case KVM_DEASSIGN_DEV_IRQ: { - struct kvm_assigned_irq assigned_irq; - - r = -EFAULT; - if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) - goto out; - r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq); - if (r) - goto out; - break; - } -#endif -#endif -#ifdef KVM_CAP_DEVICE_DEASSIGNMENT - case KVM_DEASSIGN_PCI_DEVICE: { - struct kvm_assigned_pci_dev assigned_dev; - - r = -EFAULT; - if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) - goto out; - r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev); - if (r) - goto out; - break; - } -#endif -#ifdef KVM_CAP_IRQ_ROUTING - case KVM_SET_GSI_ROUTING: { - struct kvm_irq_routing routing; - struct kvm_irq_routing __user *urouting; - struct kvm_irq_routing_entry *entries; - - r = -EFAULT; - if (copy_from_user(&routing, argp, sizeof(routing))) - goto out; - r = -EINVAL; - if (routing.nr >= KVM_MAX_IRQ_ROUTES) - goto out; - if (routing.flags) - goto out; - r = -ENOMEM; - entries = vmalloc(routing.nr * sizeof(*entries)); - if (!entries) - goto out; - r = -EFAULT; - urouting = argp; - if (copy_from_user(entries, urouting->entries, - routing.nr * sizeof(*entries))) - goto out_free_irq_routing; - r = kvm_set_irq_routing(kvm, entries, routing.nr, - routing.flags); - out_free_irq_routing: - vfree(entries); - break; - } -#endif /* KVM_CAP_IRQ_ROUTING */ -#ifdef __KVM_HAVE_MSIX - case KVM_ASSIGN_SET_MSIX_NR: { - struct kvm_assigned_msix_nr entry_nr; - r = -EFAULT; - if (copy_from_user(&entry_nr, argp, sizeof entry_nr)) - goto out; - r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr); - if (r) - goto out; - break; - } - case KVM_ASSIGN_SET_MSIX_ENTRY: { - struct kvm_assigned_msix_entry entry; - r = -EFAULT; - if (copy_from_user(&entry, argp, sizeof entry)) - goto out; - r = kvm_vm_ioctl_set_msix_entry(kvm, &entry); - if (r) - goto out; - break; - } -#endif case KVM_IRQFD: { struct kvm_irqfd data; @@ -2305,11 +1536,59 @@ static long kvm_vm_ioctl(struct file *filp, #endif default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); + if (r == -ENOTTY) + r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg); } out: return r; } +#ifdef CONFIG_COMPAT +struct compat_kvm_dirty_log { + __u32 slot; + __u32 padding1; + union { + compat_uptr_t dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + +static long kvm_vm_compat_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm *kvm = filp->private_data; + int r; + + if (kvm->mm != current->mm) + return -EIO; + switch (ioctl) { + case KVM_GET_DIRTY_LOG: { + struct compat_kvm_dirty_log compat_log; + struct kvm_dirty_log log; + + r = -EFAULT; + if (copy_from_user(&compat_log, (void __user *)arg, + sizeof(compat_log))) + goto out; + log.slot = compat_log.slot; + log.padding1 = compat_log.padding1; + log.padding2 = compat_log.padding2; + log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); + + r = kvm_vm_ioctl_get_dirty_log(kvm, &log); + if (r) + goto out; + break; + } + default: + r = kvm_vm_ioctl(filp, ioctl, arg); + } + +out: + return r; +} +#endif + static int kvm_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct page *page[1]; @@ -2344,7 +1623,9 @@ static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma) static struct file_operations kvm_vm_fops = { .release = kvm_vm_release, .unlocked_ioctl = kvm_vm_ioctl, - .compat_ioctl = kvm_vm_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = kvm_vm_compat_ioctl, +#endif .mmap = kvm_vm_mmap, }; @@ -2372,6 +1653,7 @@ static long kvm_dev_ioctl_check_extension_generic(long arg) #ifdef CONFIG_KVM_APIC_ARCHITECTURE case KVM_CAP_SET_BOOT_CPU_ID: #endif + case KVM_CAP_INTERNAL_ERROR_DATA: return 1; #ifdef CONFIG_HAVE_KVM_IRQCHIP case KVM_CAP_IRQ_ROUTING: @@ -2442,11 +1724,21 @@ static struct miscdevice kvm_dev = { static void hardware_enable(void *junk) { int cpu = raw_smp_processor_id(); + int r; if (cpumask_test_cpu(cpu, cpus_hardware_enabled)) return; + cpumask_set_cpu(cpu, cpus_hardware_enabled); - kvm_arch_hardware_enable(NULL); + + r = kvm_arch_hardware_enable(NULL); + + if (r) { + cpumask_clear_cpu(cpu, cpus_hardware_enabled); + atomic_inc(&hardware_enable_failed); + printk(KERN_INFO "kvm: enabling virtualization on " + "CPU%d failed\n", cpu); + } } static void hardware_disable(void *junk) @@ -2459,11 +1751,52 @@ static void hardware_disable(void *junk) kvm_arch_hardware_disable(NULL); } +static void hardware_disable_all_nolock(void) +{ + BUG_ON(!kvm_usage_count); + + kvm_usage_count--; + if (!kvm_usage_count) + on_each_cpu(hardware_disable, NULL, 1); +} + +static void hardware_disable_all(void) +{ + spin_lock(&kvm_lock); + hardware_disable_all_nolock(); + spin_unlock(&kvm_lock); +} + +static int hardware_enable_all(void) +{ + int r = 0; + + spin_lock(&kvm_lock); + + kvm_usage_count++; + if (kvm_usage_count == 1) { + atomic_set(&hardware_enable_failed, 0); + on_each_cpu(hardware_enable, NULL, 1); + + if (atomic_read(&hardware_enable_failed)) { + hardware_disable_all_nolock(); + r = -EBUSY; + } + } + + spin_unlock(&kvm_lock); + + return r; +} + static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, void *v) { int cpu = (long)v; + if (!kvm_usage_count) + return NOTIFY_OK; + val &= ~CPU_TASKS_FROZEN; switch (val) { case CPU_DYING: @@ -2666,13 +1999,15 @@ static void kvm_exit_debug(void) static int kvm_suspend(struct sys_device *dev, pm_message_t state) { - hardware_disable(NULL); + if (kvm_usage_count) + hardware_disable(NULL); return 0; } static int kvm_resume(struct sys_device *dev) { - hardware_enable(NULL); + if (kvm_usage_count) + hardware_enable(NULL); return 0; } @@ -2747,7 +2082,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size, goto out_free_1; } - on_each_cpu(hardware_enable, NULL, 1); r = register_cpu_notifier(&kvm_cpu_notifier); if (r) goto out_free_2; @@ -2797,7 +2131,6 @@ out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); unregister_cpu_notifier(&kvm_cpu_notifier); out_free_2: - on_each_cpu(hardware_disable, NULL, 1); out_free_1: kvm_arch_hardware_unsetup(); out_free_0a: |