struct vm_stats { int cpuid; /* in */ int num_entries; /* out */ struct timeval tv; uint64_t statbuf[MAX_VM_STATS]; }; struct vm_stat_desc { int index; /* in */ char desc[128]; /* out */ }; struct vm_cpu_topology { uint16_t sockets; uint16_t cores; uint16_t threads; uint16_t maxcpus; }
- vmm_dev.c
static int vmmdev_ioctl(struct cdev *cdev, u_long cmd, caddr_t data, int fflag, struct thread *td) { case VM_RUN: case VM_GET_REGISTER: case VM_SET_REGISTER: case VM_GET_SEGMENT_DESCRIPTOR: case VM_SET_SEGMENT_DESCRIPTOR: case VM_GET_REGISTER_SET: case VM_SET_REGISTER_SET: case VM_INJECT_EXCEPTION: case VM_GET_CAPABILITY: case VM_SET_CAPABILITY: case VM_PPTDEV_MSI: case VM_PPTDEV_MSIX: case VM_SET_X2APIC_STATE: case VM_GLA2GPA: case VM_GLA2GPA_NOFAULT: case VM_ACTIVATE_CPU: case VM_SET_INTINFO: case VM_GET_INTINFO: case VM_RESTART_INSTRUCTION: case VM_MAP_PPTDEV_MMIO: case VM_BIND_PPTDEV: case VM_UNBIND_PPTDEV: case VM_ALLOC_MEMSEG: case VM_MMAP_MEMSEG: case VM_REINIT: case VM_GET_MEMSEG: case VM_MMAP_GETNEXT: case VM_RUN: case VM_SUSPEND: case VM_REINIT: case VM_STAT_DESC: { case VM_STATS: { case VM_PPTDEV_MSI: case VM_PPTDEV_MSIX: case VM_PPTDEV_DISABLE_MSIX: case VM_MAP_PPTDEV_MMIO: case VM_BIND_PPTDEV: case VM_UNBIND_PPTDEV: case VM_INJECT_EXCEPTION: case VM_INJECT_NMI: case VM_LAPIC_IRQ: case VM_LAPIC_LOCAL_IRQ: case VM_LAPIC_MSI: case VM_IOAPIC_ASSERT_IRQ: case VM_IOAPIC_DEASSERT_IRQ: case VM_IOAPIC_PULSE_IRQ: case VM_IOAPIC_PINCOUNT: case VM_ISA_ASSERT_IRQ: case VM_ISA_DEASSERT_IRQ: case VM_ISA_PULSE_IRQ: case VM_ISA_SET_IRQ_TRIGGER: case VM_MMAP_GETNEXT: case VM_MMAP_MEMSEG: case VM_ALLOC_MEMSEG: case VM_GET_MEMSEG: case VM_GET_REGISTER: case VM_SET_REGISTER: case VM_SET_SEGMENT_DESCRIPTOR: case VM_GET_SEGMENT_DESCRIPTOR: case VM_GET_REGISTER_SET: case VM_SET_REGISTER_SET: case VM_GET_CAPABILITY: case VM_SET_CAPABILITY: case VM_SET_X2APIC_STATE: case VM_GET_X2APIC_STATE: case VM_GET_GPA_PMAP: case VM_GET_HPET_CAPABILITIES: case VM_GLA2GPA: { case VM_GLA2GPA_NOFAULT: case VM_ACTIVATE_CPU: case VM_GET_CPUS: case VM_SUSPEND_CPU: case VM_RESUME_CPU: case VM_SET_INTINFO: case VM_GET_INTINFO: case VM_RTC_WRITE: case VM_RTC_READ: case VM_RTC_SETTIME: case VM_RTC_GETTIME: case VM_RESTART_INSTRUCTION: case VM_SET_TOPOLOGY: case VM_GET_TOPOLOGY: }
- proc.h
/*- * Description of a process. * * This structure contains the information needed to manage a thread of * control, known in UN*X as a process; it has references to substructures * containing descriptions of things that the process uses, but may share * with related processes. The process structure and the substructures * are always addressable except for those marked "(CPU)" below, * which might be addressable only on a processor on which the process * is running. * * Below is a key of locks used to protect each member of struct proc. The * lock is indicated by a reference to a specific character in parens in the * associated comment. * * - not yet protected * a - only touched by curproc or parent during fork/wait * b - created at fork, never changes * (exception aiods switch vmspaces, but they are also * marked 'P_SYSTEM' so hopefully it will be left alone) * c - locked by proc mtx * d - locked by allproc_lock lock * e - locked by proctree_lock lock * f - session mtx * g - process group mtx * h - callout_lock mtx * i - by curproc or the master session mtx * j - locked by proc slock * k - only accessed by curthread * k*- only accessed by curthread and from an interrupt * kx- only accessed by curthread and by debugger * l - the attaching proc or attaching proc parent * m - Giant * n - not locked, lazy * o - ktrace lock * q - td_contested lock * r - p_peers lock * s - see sleepq_switch(), sleeping_on_old_rtc(), and sleep(9) * t - thread lock * u - process stat lock * w - process timer lock * x - created at fork, only changes during single threading in exec * y - created at first aio, doesn't change until exit or exec at which * point we are single-threaded and only curthread changes it * z - zombie threads lock * * If the locking key specifies two identifiers (for example, p_pptr) then * either lock is sufficient for read access, but both locks must be held * for write access. */ struct cpuset; struct filecaps; struct filemon; struct kaioinfo; struct kaudit_record; struct kdtrace_proc; struct kdtrace_thread; struct mqueue_notifier; struct nlminfo; struct p_sched; struct proc; struct procdesc; struct racct; struct sbuf; struct sleepqueue; struct socket; /* * Kernel runnable context (thread). * This is what is put to sleep and reactivated. * Thread context. Processes may have multiple threads. */ struct thread { struct mtx *volatile td_lock; /* replaces sched lock */ struct proc *td_proc; /* (*) Associated process. */ TAILQ_ENTRY(thread) td_plist; /* (*) All threads in this proc. */ TAILQ_ENTRY(thread) td_runq; /* (t) Run queue. */ TAILQ_ENTRY(thread) td_slpq; /* (t) Sleep queue. */ TAILQ_ENTRY(thread) td_lockq; /* (t) Lock queue. */ LIST_ENTRY(thread) td_hash; /* (d) Hash chain. */ struct cpuset *td_cpuset; /* (t) CPU affinity mask. */ struct domainset_ref td_domain; /* (a) NUMA policy */ struct seltd *td_sel; /* Select queue/channel. */ struct sleepqueue *td_sleepqueue; /* (k) Associated sleep queue. */ struct turnstile *td_turnstile; /* (k) Associated turnstile. */ struct rl_q_entry *td_rlqe; /* (k) Associated range lock entry. */ struct umtx_q *td_umtxq; /* (c?) Link for when we're blocked. */ lwpid_t td_tid; /* (b) Thread ID. */ sigqueue_t td_sigqueue; /* (c) Sigs arrived, not delivered. */ #define td_siglist td_sigqueue.sq_signals u_char td_lend_user_pri; /* (t) Lend user pri. */ /* Cleared during fork1() */ #define td_startzero td_epochnest u_char td_epochnest; /* (k) Epoch nest counter. */ int td_flags; /* (t) TDF_* flags. */ int td_inhibitors; /* (t) Why can not run. */ int td_pflags; /* (k) Private thread (TDP_*) flags. */ int td_dupfd; /* (k) Ret value from fdopen. XXX */ int td_sqqueue; /* (t) Sleepqueue queue blocked on. */ void *td_wchan; /* (t) Sleep address. */ const char *td_wmesg; /* (t) Reason for sleep. */ volatile u_char td_owepreempt; /* (k*) Preempt on last critical_exit */ u_char td_tsqueue; /* (t) Turnstile queue blocked on. */ short td_locks; /* (k) Debug: count of non-spin locks */ short td_rw_rlocks; /* (k) Count of rwlock read locks. */ short td_sx_slocks; /* (k) Count of sx shared locks. */ short td_lk_slocks; /* (k) Count of lockmgr shared locks. */ short td_stopsched; /* (k) Scheduler stopped. */ struct turnstile *td_blocked; /* (t) Lock thread is blocked on. */ const char *td_lockname; /* (t) Name of lock blocked on. */ LIST_HEAD(, turnstile) td_contested; /* (q) Contested locks. */ struct lock_list_entry *td_sleeplocks; /* (k) Held sleep locks. */ int td_intr_nesting_level; /* (k) Interrupt recursion. */ int td_pinned; /* (k) Temporary cpu pin count. */ struct ucred *td_ucred; /* (k) Reference to credentials. */ struct plimit *td_limit; /* (k) Resource limits. */ int td_slptick; /* (t) Time at sleep. */ int td_blktick; /* (t) Time spent blocked. */ int td_swvoltick; /* (t) Time at last SW_VOL switch. */ int td_swinvoltick; /* (t) Time at last SW_INVOL switch. */ u_int td_cow; /* (*) Number of copy-on-write faults */ struct rusage td_ru; /* (t) rusage information. */ struct rusage_ext td_rux; /* (t) Internal rusage information. */ uint64_t td_incruntime; /* (t) Cpu ticks to transfer to proc. */ uint64_t td_runtime; /* (t) How many cpu ticks we've run. */ u_int td_pticks; /* (t) Statclock hits for profiling */ u_int td_sticks; /* (t) Statclock hits in system mode. */ u_int td_iticks; /* (t) Statclock hits in intr mode. */ u_int td_uticks; /* (t) Statclock hits in user mode. */ int td_intrval; /* (t) Return value for sleepq. */ sigset_t td_oldsigmask; /* (k) Saved mask from pre sigpause. */ volatile u_int td_generation; /* (k) For detection of preemption */ volatile u_int td_generation; /* (k) For detection of preemption */ stack_t td_sigstk; /* (k) Stack ptr and on-stack flag. */ int td_xsig; /* (c) Signal for ptrace */ u_long td_profil_addr; /* (k) Temporary addr until AST. */ u_int td_profil_ticks; /* (k) Temporary ticks until AST. */ char td_name[MAXCOMLEN + 1]; /* (*) Thread name. */ struct file *td_fpop; /* (k) file referencing cdev under op */ int td_dbgflags; /* (c) Userland debugger flags */ siginfo_t td_si; /* (c) For debugger or core file */ int td_ng_outbound; /* (k) Thread entered ng from above. */ struct osd td_osd; /* (k) Object specific data. */ struct vm_map_entry *td_map_def_user; /* (k) Deferred entries. */ pid_t td_dbg_forked; /* (c) Child pid for debugger. */ u_int td_vp_reserv; /* (k) Count of reserved vnodes. */ int td_no_sleeping; /* (k) Sleeping disabled count. */ void *td_su; /* (k) FFS SU private */ sbintime_t td_sleeptimo; /* (t) Sleep timeout. */ int td_rtcgen; /* (s) rtc_generation of abs. sleep */ size_t td_vslock_sz; /* (k) amount of vslock-ed space */ #define td_endzero td_sigmask /* Copied during fork1() or create_thread(). */ #define td_startcopy td_endzero sigset_t td_sigmask; /* (c) Current signal mask. */ u_char td_rqindex; /* (t) Run queue index. */ u_char td_base_pri; /* (t) Thread base kernel priority. */ u_char td_priority; /* (t) Thread active priority. */ u_char td_pri_class; /* (t) Scheduling class. */ u_char td_user_pri; /* (t) User pri from estcpu and nice. */ u_char td_base_user_pri; /* (t) Base user pri */ u_char td_pre_epoch_prio; /* (k) User pri on entry to epoch */ uintptr_t td_rb_list; /* (k) Robust list head. */ uintptr_t td_rbp_list; /* (k) Robust priv list head. */ uintptr_t td_rb_inact; /* (k) Current in-action mutex loc. */ struct syscall_args td_sa; /* (kx) Syscall parameters. Copied on fork for child tracing. */ #define td_endcopy td_pcb /* * Fields that must be manually set in fork1() or create_thread() * or already have been set in the allocator, constructor, etc. */ struct pcb *td_pcb; /* (k) Kernel VA of pcb and kstack. */ enum { TDS_INACTIVE = 0x0, TDS_INHIBITED, TDS_CAN_RUN, TDS_RUNQ, TDS_RUNNING } td_state; /* (t) thread state */ union { register_t tdu_retval[2]; off_t tdu_off; } td_uretoff; /* (k) Syscall aux returns. */ #define td_retval td_uretoff.tdu_retval u_int td_cowgen; /* (k) Generation of COW pointers. */ /* LP64 hole */ struct callout td_slpcallout; /* (h) Callout for sleep. */ struct trapframe *td_frame; /* (k) */ struct vm_object *td_kstack_obj;/* (a) Kstack object. */ vm_offset_t td_kstack; /* (a) Kernel VA of kstack. */ int td_kstack_pages; /* (a) Size of the kstack. */ volatile u_int td_critnest; /* (k*) Critical section nest level. */ #ifdef __amd64__ uint32_t td_md_pad0[16]; #else struct mdthread td_md; /* (k) Any machine-dependent fields. */ #endif struct kaudit_record *td_ar; /* (k) Active audit record, if any. */ struct lpohead td_lprof[2]; /* (a) lock profiling objects. */ struct kdtrace_thread *td_dtrace; /* (*) DTrace-specific data. */ int td_errno; /* Error returned by last syscall. */ /* LP64 hole */ struct vnet *td_vnet; /* (k) Effective vnet. */ const char *td_vnet_lpush; /* (k) Debugging vnet push / pop. */ struct trapframe *td_intr_frame;/* (k) Frame of the current irq */ struct proc *td_rfppwait_p; /* (k) The vforked child */ struct vm_page **td_ma; /* (k) uio pages held */ int td_ma_cnt; /* (k) size of *td_ma */ /* LP64 hole */ void *td_emuldata; /* Emulator state data */ int td_lastcpu; /* (t) Last cpu we were on. */ int td_oncpu; /* (t) Which cpu we are on. */ void *td_lkpi_task; /* LinuxKPI task struct pointer */ int td_pmcpend; #ifdef __amd64__ struct mdthread td_md; /* (k) Any machine-dependent fields. */ #endif int td_pflags2; /* (k) Private thread (TDP2_*) flags. */ }; /* * Process structure. */ struct proc { LIST_ENTRY(proc) p_list; /* (d) List of all processes. */ TAILQ_HEAD(, thread) p_threads; /* (c) all threads. */ struct mtx p_slock; /* process spin lock */ struct ucred *p_ucred; /* (c) Process owner's identity. */ struct filedesc *p_fd; /* (b) Open files. */ struct filedesc_to_leader *p_fdtol; /* (b) Tracking node */ struct pstats *p_stats; /* (b) Accounting/statistics (CPU). */ struct plimit *p_limit; /* (c) Resource limits. */ struct callout p_limco; /* (c) Limit callout handle */ struct sigacts *p_sigacts; /* (x) Signal actions, state (CPU). */ int p_flag; /* (c) P_* flags. */ int p_flag2; /* (c) P2_* flags. */ enum { PRS_NEW = 0, /* In creation */ PRS_NORMAL, /* threads can be run. */ PRS_ZOMBIE } p_state; /* (j/c) Process status. */ pid_t p_pid; /* (b) Process identifier. */ LIST_ENTRY(proc) p_hash; /* (d) Hash chain. */ LIST_ENTRY(proc) p_pglist; /* (g + e) List of processes in pgrp. */ struct proc *p_pptr; /* (c + e) Pointer to parent process. */ LIST_ENTRY(proc) p_sibling; /* (e) List of sibling processes. */ LIST_HEAD(, proc) p_children; /* (e) Pointer to list of children. */ struct proc *p_reaper; /* (e) My reaper. */ LIST_HEAD(, proc) p_reaplist; /* (e) List of my descendants (if I am reaper). */ LIST_ENTRY(proc) p_reapsibling; /* (e) List of siblings - descendants of the same reaper. */ struct mtx p_mtx; /* (n) Lock for this struct. */ struct mtx p_statmtx; /* Lock for the stats */ struct mtx p_itimmtx; /* Lock for the virt/prof timers */ struct mtx p_profmtx; /* Lock for the profiling */ struct ksiginfo *p_ksi; /* Locked by parent proc lock */ sigqueue_t p_sigqueue; /* (c) Sigs not delivered to a td. */ #define p_siglist p_sigqueue.sq_signals pid_t p_oppid; /* (c + e) Real parent pid. */ /* The following fields are all zeroed upon creation in fork. */ #define p_startzero p_vmspace struct vmspace *p_vmspace; /* (b) Address space. */ u_int p_swtick; /* (c) Tick when swapped in or out. */ u_int p_cowgen; /* (c) Generation of COW pointers. */ struct itimerval p_realtimer; /* (c) Alarm timer. */ struct rusage p_ru; /* (a) Exit information. */ struct rusage_ext p_rux; /* (cu) Internal resource usage. */ struct rusage_ext p_crux; /* (c) Internal child resource usage. */ int p_profthreads; /* (c) Num threads in addupc_task. */ volatile int p_exitthreads; /* (j) Number of threads exiting */ int p_traceflag; /* (o) Kernel trace points. */ struct vnode *p_tracevp; /* (c + o) Trace to vnode. */ struct vnode *p_tracevp; /* (c + o) Trace to vnode. */ struct ucred *p_tracecred; /* (o) Credentials to trace with. */ struct vnode *p_textvp; /* (b) Vnode of executable. */ u_int p_lock; /* (c) Proclock (prevent swap) count. */ struct sigiolst p_sigiolst; /* (c) List of sigio sources. */ int p_sigparent; /* (c) Signal to parent on exit. */ int p_sig; /* (n) For core dump/debugger XXX. */ u_long p_code; /* (n) For core dump/debugger XXX. */ u_int p_stops; /* (c) Stop event bitmask. */ u_int p_stype; /* (c) Stop event type. */ char p_step; /* (c) Process is stopped. */ u_char p_pfsflags; /* (c) Procfs flags. */ u_int p_ptevents; /* (c + e) ptrace() event mask. */ struct nlminfo *p_nlminfo; /* (?) Only used by/for lockd. */ struct kaioinfo *p_aioinfo; /* (y) ASYNC I/O info. */ struct thread *p_singlethread;/* (c + j) If single threading this is it */ int p_suspcount; /* (j) Num threads in suspended mode. */ struct thread *p_xthread; /* (c) Trap thread */ int p_boundary_count;/* (j) Num threads at user boundary */ int p_pendingcnt; /* how many signals are pending */ struct itimers *p_itimers; /* (c) POSIX interval timers. */ struct procdesc *p_procdesc; /* (e) Process descriptor, if any. */ u_int p_treeflag; /* (e) P_TREE flags */ int p_pendingexits; /* (c) Count of pending thread exits. */ struct filemon *p_filemon; /* (c) filemon-specific data. */ int p_pdeathsig; /* (c) Signal from parent on exit. */ /* End area that is zeroed on creation. */ #define p_endzero p_magic /* The following fields are all copied upon creation in fork. */ #define p_startcopy p_endzero u_int p_magic; /* (b) Magic number. */ int p_osrel; /* (x) osreldate for the binary (from ELF note, if any) */ char p_comm[MAXCOMLEN + 1]; /* (x) Process name. */ struct sysentvec *p_sysent; /* (b) Syscall dispatch info. */ struct pargs *p_args; /* (c) Process arguments. */ rlim_t p_cpulimit; /* (c) Current CPU limit in seconds. */ signed char p_nice; /* (c) Process "nice" value. */ int p_fibnum; /* in this routing domain XXX MRT */ pid_t p_reapsubtree; /* (e) Pid of the direct child of the reaper which spawned our subtree. */ uint16_t p_elf_machine; /* (x) ELF machine type */ uint64_t p_elf_flags; /* (x) ELF flags */ /* End area that is copied on creation. */ #define p_endcopy p_xexit u_int p_xexit; /* (c) Exit code. */ u_int p_xsig; /* (c) Stop/kill sig. */ struct pgrp *p_pgrp; /* (c + e) Pointer to process group. */ struct knlist *p_klist; /* (c) Knotes attached to this proc. */ int p_numthreads; /* (c) Number of threads. */ struct mdproc p_md; /* Any machine-dependent fields. */ struct callout p_itcallout; /* (h + c) Interval timer callout. */ u_short p_acflag; /* (c) Accounting flags. */ struct proc *p_peers; /* (r) */ struct proc *p_leader; /* (b) */ void *p_emuldata; /* (c) Emulator state data. */ struct label *p_label; /* (*) Proc (not subject) MAC label. */ STAILQ_HEAD(, ktr_request) p_ktr; /* (o) KTR event queue. */ LIST_HEAD(, mqueue_notifier) p_mqnotifier; /* (c) mqueue notifiers.*/ struct kdtrace_proc *p_dtrace; /* (*) DTrace-specific data. */ struct cv p_pwait; /* (*) wait cv for exit/exec. */ uint64_t p_prev_runtime; /* (c) Resource usage accounting. */ struct racct *p_racct; /* (b) Resource accounting. */ int p_throttled; /* (c) Flag for racct pcpu throttling */ /* * An orphan is the child that has been re-parented to the * debugger as a result of attaching to it. Need to keep * track of them for parent to be able to collect the exit * status of what used to be children. */ LIST_ENTRY(proc) p_orphan; /* (e) List of orphan processes. */ LIST_HEAD(, proc) p_orphans; /* (e) Pointer to list of orphans. */ uint32_t p_fctl0; /* (x) ABI feature control, ELF note */ u_int p_amd64_md_flags; /* (c) md process flags P_MD */ };
- svm.h
/* * Guest register state that is saved outside the VMCB. */ struct svm_regctx { register_t sctx_rbp; register_t sctx_rbx; register_t sctx_rcx; register_t sctx_rdx; register_t sctx_rdi; register_t sctx_rsi; register_t sctx_r8; register_t sctx_r9; register_t sctx_r10; register_t sctx_r11; register_t sctx_r12; register_t sctx_r13; register_t sctx_r14; register_t sctx_r15; register_t sctx_dr0; register_t sctx_dr1; register_t sctx_dr2; register_t sctx_dr3; register_t host_dr0; register_t host_dr1; register_t host_dr2; register_t host_dr3; register_t host_dr6; register_t host_dr7; uint64_t host_debugctl; };
- vmm.c
/* * Initialization: * (a) allocated when vcpu is created * (i) initialized when vcpu is created and when it is reinitialized * (o) initialized the first time the vcpu is created * (x) initialized before use */ struct vcpu { struct mtx mtx; /* (o) protects 'state' and 'hostcpu' */ enum vcpu_state state; /* (o) vcpu state */ int hostcpu; /* (o) vcpu's host cpu */ int reqidle; /* (i) request vcpu to idle */ struct vlapic *vlapic; /* (i) APIC device model */ enum x2apic_state x2apic_state; /* (i) APIC mode */ uint64_t exitintinfo; /* (i) events pending at VM exit */ int nmi_pending; /* (i) NMI pending */ int extint_pending; /* (i) INTR pending */ int exception_pending; /* (i) exception pending */ int exc_vector; /* (x) exception collateral */ int exc_errcode_valid; uint32_t exc_errcode; struct savefpu *guestfpu; /* (a,i) guest fpu state */ uint64_t guest_xcr0; /* (i) guest %xcr0 register */ void *stats; /* (a,i) statistics */ struct vm_exit exitinfo; /* (x) exit reason and collateral */ uint64_t nextrip; /* (x) next instruction to execute */ }; /* * Initialization: * (o) initialized the first time the VM is created * (i) initialized when VM is created and when it is reinitialized * (x) initialized before use */ struct vm { void *cookie; /* (i) cpu-specific data */ void *iommu; /* (x) iommu-specific data */ struct vhpet *vhpet; /* (i) virtual HPET */ struct vioapic *vioapic; /* (i) virtual ioapic */ struct vatpic *vatpic; /* (i) virtual atpic */ struct vatpit *vatpit; /* (i) virtual atpit */ struct vpmtmr *vpmtmr; /* (i) virtual ACPI PM timer */ struct vrtc *vrtc; /* (o) virtual RTC */ volatile cpuset_t active_cpus; /* (i) active vcpus */ volatile cpuset_t debug_cpus; /* (i) vcpus stopped for debug */ int suspend; /* (i) stop VM execution */ volatile cpuset_t suspended_cpus; /* (i) suspended vcpus */ volatile cpuset_t halted_cpus; /* (x) cpus in a hard halt */ cpuset_t rendezvous_req_cpus; /* (x) rendezvous requested */ cpuset_t rendezvous_done_cpus; /* (x) rendezvous finished */ void *rendezvous_arg; /* (x) rendezvous func/arg */ vm_rendezvous_func_t rendezvous_func; struct mtx rendezvous_mtx; /* (o) rendezvous lock */ struct mem_map mem_maps[VM_MAX_MEMMAPS]; /* (i) guest address space */ struct mem_seg mem_segs[VM_MAX_MEMSEGS]; /* (o) guest memory regions */ struct vmspace *vmspace; /* (o) guest's address space */ char name[VM_MAX_NAMELEN+1]; /* (o) virtual machine name */ struct vcpu vcpu[VM_MAXCPU]; /* (i) guest vcpus */ /* The following describe the vm cpu topology */ uint16_t sockets; /* (o) num of sockets */ uint16_t cores; /* (o) num of cores/socket */ uint16_t threads; /* (o) num of threads/core */ uint16_t maxcpus; /* (o) max pluggable cpus */ }; vm_init(struct vm *vm, bool create) { int i; vm->cookie = VMINIT(vm, vmspace_pmap(vm->vmspace)); vm->iommu = NULL; vm->vioapic = vioapic_init(vm); vm->vhpet = vhpet_init(vm); vm->vatpic = vatpic_init(vm); vm->vatpit = vatpit_init(vm); vm->vpmtmr = vpmtmr_init(vm); if (create) vm->vrtc = vrtc_init(vm); CPU_ZERO(&vm->active_cpus); CPU_ZERO(&vm->debug_cpus); vm->suspend = 0; CPU_ZERO(&vm->suspended_cpus); for (i = 0; i < vm->maxcpus; i++) vcpu_init(vm, i, create); } #ifdef KTR static const char * vcpu_state2str(enum vcpu_state state) { switch (state) { case VCPU_IDLE: return ("idle"); case VCPU_FROZEN: return ("frozen"); case VCPU_RUNNING: return ("running"); case VCPU_SLEEPING: return ("sleeping"); default: return ("unknown"); } } #endif
# bhyvectl --vm=b13 --get-stats vcpu0 stats: timer interrupts generated by vlapic 2908 corrected machine check interrupts generated by vlapic 0 lvts triggered[0] 0 lvts triggered[1] 0 lvts triggered[2] 0 lvts triggered[3] 0 lvts triggered[4] 0 lvts triggered[5] 0 lvts triggered[6] 0 ipis sent to vcpu[0] 0 ipis sent to vcpu[1] 2540 ipis sent to vcpu[2] 2476 ipis sent to vcpu[3] 0 ipis sent to vcpu[4] 0 ipis sent to vcpu[5] 0 ipis sent to vcpu[6] 0 ipis sent to vcpu[7] 0 ipis sent to vcpu[8] 0 ipis sent to vcpu[9] 0 ipis sent to vcpu[10] 0 ipis sent to vcpu[11] 0 ipis sent to vcpu[12] 0 ipis sent to vcpu[13] 0 ipis sent to vcpu[14] 0 ipis sent to vcpu[15] 0 Resident memory 172515328 Wired memory 0 Number of vpid invalidations saved 0 Number of vpid invalidations done 1960 vcpu migration across host cpus 1960 total number of vm exits 519101 vm exits due to external interrupt 3905 number of times hlt was intercepted 5223 number of times %cr access was intercepted 2 number of times rdmsr was intercepted 8 number of times wrmsr was intercepted 2 number of monitor trap exits 0 number of times pause was intercepted 159543 vm exits due to interrupt window opening 419 vm exits due to nmi window opening 0 number of times in/out was intercepted 179947 number of times cpuid was intercepted 3594 vm exits due to nested page fault 24507 vm exits for instruction emulation 141950 number of vm exits for unknown reason 0 number of times astpending at exit 631 number of times idle requested at exit 0 number of vm exits handled in userspace 511180 number of times rendezvous pending at exit 10 number of vm exits due to exceptions 0 vcpu total runtime 8808050026 number of ticks vcpu was idle 110341 number of NMIs delivered to vcpu 0 number of ExtINTs delivered to vcpu 0 EOI without any in-service interrupt 0 error interrupts generated by vlapic 0
- vmm_stat.c
/* global statistics */ VMM_STAT(VCPU_MIGRATIONS, "vcpu migration across host cpus"); VMM_STAT(VMEXIT_COUNT, "total number of vm exits"); VMM_STAT(VMEXIT_EXTINT, "vm exits due to external interrupt"); VMM_STAT(VMEXIT_HLT, "number of times hlt was intercepted"); VMM_STAT(VMEXIT_CR_ACCESS, "number of times %cr access was intercepted"); VMM_STAT(VMEXIT_RDMSR, "number of times rdmsr was intercepted"); VMM_STAT(VMEXIT_WRMSR, "number of times wrmsr was intercepted"); VMM_STAT(VMEXIT_MTRAP, "number of monitor trap exits"); VMM_STAT(VMEXIT_PAUSE, "number of times pause was intercepted"); VMM_STAT(VMEXIT_INTR_WINDOW, "vm exits due to interrupt window opening"); VMM_STAT(VMEXIT_NMI_WINDOW, "vm exits due to nmi window opening"); VMM_STAT(VMEXIT_INOUT, "number of times in/out was intercepted"); VMM_STAT(VMEXIT_CPUID, "number of times cpuid was intercepted"); VMM_STAT(VMEXIT_NESTED_FAULT, "vm exits due to nested page fault"); VMM_STAT(VMEXIT_INST_EMUL, "vm exits for instruction emulation"); VMM_STAT(VMEXIT_UNKNOWN, "number of vm exits for unknown reason"); VMM_STAT(VMEXIT_ASTPENDING, "number of times astpending at exit"); VMM_STAT(VMEXIT_REQIDLE, "number of times idle requested at exit"); VMM_STAT(VMEXIT_USERSPACE, "number of vm exits handled in userspace"); VMM_STAT(VMEXIT_RENDEZVOUS, "number of times rendezvous pending at exit"); VMM_STAT(VMEXIT_EXCEPTION, "number of vm exits due to exceptions");
- vmm_stat.h
VMM_STAT_DECLARE(VCPU_MIGRATIONS); VMM_STAT_DECLARE(VMEXIT_COUNT); VMM_STAT_DECLARE(VMEXIT_EXTINT); VMM_STAT_DECLARE(VMEXIT_HLT); VMM_STAT_DECLARE(VMEXIT_CR_ACCESS); VMM_STAT_DECLARE(VMEXIT_RDMSR); VMM_STAT_DECLARE(VMEXIT_WRMSR); VMM_STAT_DECLARE(VMEXIT_MTRAP); VMM_STAT_DECLARE(VMEXIT_PAUSE); VMM_STAT_DECLARE(VMEXIT_INTR_WINDOW); VMM_STAT_DECLARE(VMEXIT_NMI_WINDOW); VMM_STAT_DECLARE(VMEXIT_INOUT); VMM_STAT_DECLARE(VMEXIT_CPUID); VMM_STAT_DECLARE(VMEXIT_NESTED_FAULT); VMM_STAT_DECLARE(VMEXIT_INST_EMUL); VMM_STAT_DECLARE(VMEXIT_UNKNOWN); VMM_STAT_DECLARE(VMEXIT_ASTPENDING); VMM_STAT_DECLARE(VMEXIT_USERSPACE); VMM_STAT_DECLARE(VMEXIT_RENDEZVOUS); VMM_STAT_DECLARE(VMEXIT_EXCEPTION); VMM_STAT_DECLARE(VMEXIT_REQIDLE);
- vmm.c
static VMM_STAT(VCPU_TOTAL_RUNTIME, "vcpu total runtime"); static VMM_STAT(VCPU_IDLE_TICKS, "number of ticks vcpu was idle"); static VMM_STAT(VCPU_NMI_COUNT, "number of NMIs delivered to vcpu"); static VMM_STAT(VCPU_EXTINT_COUNT, "number of ExtINTs delivered to vcpu");
https://uni.dtln.ru/digest/analiz-proizvoditelnosti-vm-v-vmware-vsphere-chast-1-cpu
Если ядро ВМ (vCPU) находится в состоянии Ready, оно не выполняет полезную работу. Такое состояние возникает, когда гипервизор не находит свободное физическое ядро, на которое можно назначить процесс vCPU виртуальной машины.
Как анализировать? Обычно если ядра виртуальной машины находятся в состоянии Ready больше 10% времени, то вы заметите проблемы с производительностью. Проще говоря, больше 10% времени ВМ ждет доступности физических ресурсов.
В vCenter можно посмотреть 2 счетчика, связанных с CPU Ready:
Readiness, Ready.Значения обоих счетчиков можно посмотреть как по всей ВМ, так и по отдельным ядрам.
Readiness показывает значение сразу в процентах, но только в Real-time (данные за последний час, интервал измерений 20 секунд). Этот счетчик лучше использовать только для поиска проблем “по горячим следам”.
Значения счетчика Ready можно посмотреть также в исторической перспективе. Это полезно, если нужно установить закономерности и для более глубокого анализа проблемы. Например, если у виртуальной машины начинаются проблемы с производительностью в какое-то определенное время, можно сопоставить интервалы повешенного значения CPU Ready с общей нагрузкой на сервер, где данная ВМ работает, и принять меры по снижению нагрузки (если DRS не справился).
Ready в отличие от Readiness показывается не в процентах, а миллисекундах. Это счетчик типа Summation, то есть он показывает, сколько времени за период измерения ядро ВМ находилось в состоянии Ready. Перевести данное значение в проценты можно по несложной формуле:
(CPU ready summation value / (chart default update interval in seconds * 1000)) * 100 = CPU ready %
Источник: https://kb.vmware.com/kb/200218
Например, для ВМ на графике ниже пиковое значение Ready на всю виртуальную машину получится следующим: