Initial import of qemu-2.4.1HEADmaster

4 files changed, 1087 insertions, 0 deletions

diff --git a/scripts/kvm/kvm_flightrecorder b/scripts/kvm/kvm_flightrecorder
new file mode 100755
index 00000000..7fb1c2d1
--- /dev/null
+++ b/scripts/kvm/kvm_flightrecorder
@@ -0,0 +1,126 @@
+#!/usr/bin/env python
+#
+# KVM Flight Recorder - ring buffer tracing script
+#
+# Copyright (C) 2012 IBM Corp
+#
+# Author: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+#
+# This script provides a command-line interface to kvm ftrace and is designed
+# to be used as a flight recorder that is always running.  To start in-memory
+# recording:
+#
+# sudo kvm_flightrecorder start 8192  # 8 MB per-cpu ring buffers
+#
+# The per-cpu ring buffer size can be given in KB as an optional argument to
+# the 'start' subcommand.
+#
+# To stop the flight recorder:
+#
+# sudo kvm_flightrecorder stop
+#
+# To dump the contents of the flight recorder (this can be done when the
+# recorder is stopped or while it is running):
+#
+# sudo kvm_flightrecorder dump >/path/to/dump.txt
+#
+# To observe the trace while it is running, use the 'tail' subcommand:
+#
+# sudo kvm_flightrecorder tail
+#
+# Note that the flight recorder may impact overall system performance by
+# consuming CPU cycles.  No disk I/O is performed since the ring buffer holds a
+# fixed-size in-memory trace.
+
+import sys
+import os
+
+tracing_dir = '/sys/kernel/debug/tracing'
+
+def trace_path(*args):
+    return os.path.join(tracing_dir, *args)
+
+def write_file(path, data):
+    open(path, 'wb').write(data)
+
+def enable_event(subsystem, event, enable):
+    write_file(trace_path('events', subsystem, event, 'enable'), '1' if enable else '0')
+
+def enable_subsystem(subsystem, enable):
+    write_file(trace_path('events', subsystem, 'enable'), '1' if enable else '0')
+
+def start_tracing():
+    enable_subsystem('kvm', True)
+    write_file(trace_path('tracing_on'), '1')
+
+def stop_tracing():
+    write_file(trace_path('tracing_on'), '0')
+    enable_subsystem('kvm', False)
+    write_file(trace_path('events', 'enable'), '0')
+    write_file(trace_path('current_tracer'), 'nop')
+
+def dump_trace():
+    tracefile = open(trace_path('trace'), 'r')
+    try:
+        lines = True
+        while lines:
+            lines = tracefile.readlines(64 * 1024)
+            sys.stdout.writelines(lines)
+    except KeyboardInterrupt:
+        pass
+
+def tail_trace():
+    try:
+        for line in open(trace_path('trace_pipe'), 'r'):
+            sys.stdout.write(line)
+    except KeyboardInterrupt:
+        pass
+
+def usage():
+    print 'Usage: %s start [buffer_size_kb] | stop | dump | tail' % sys.argv[0]
+    print 'Control the KVM flight recorder tracing.'
+    sys.exit(0)
+
+def main():
+    if len(sys.argv) < 2:
+        usage()
+
+    cmd = sys.argv[1]
+    if cmd == '--version':
+        print 'kvm_flightrecorder version 1.0'
+        sys.exit(0)
+
+    if not os.path.isdir(tracing_dir):
+        print 'Unable to tracing debugfs directory, try:'
+        print 'mount -t debugfs none /sys/kernel/debug'
+        sys.exit(1)
+    if not os.access(tracing_dir, os.W_OK):
+        print 'Unable to write to tracing debugfs directory, please run as root'
+        sys.exit(1)
+
+    if cmd == 'start':
+        stop_tracing() # clean up first
+
+        if len(sys.argv) == 3:
+            try:
+                buffer_size_kb = int(sys.argv[2])
+            except ValueError:
+                print 'Invalid per-cpu trace buffer size in KB'
+                sys.exit(1)
+            write_file(trace_path('buffer_size_kb'), str(buffer_size_kb))
+            print 'Per-CPU ring buffer size set to %d KB' % buffer_size_kb
+
+        start_tracing()
+        print 'KVM flight recorder enabled'
+    elif cmd == 'stop':
+        stop_tracing()
+        print 'KVM flight recorder disabled'
+    elif cmd == 'dump':
+        dump_trace()
+    elif cmd == 'tail':
+        tail_trace()
+    else:
+        usage()
+
+if __name__ == '__main__':
+    sys.exit(main())
diff --git a/scripts/kvm/kvm_stat b/scripts/kvm/kvm_stat
new file mode 100755
index 00000000..7e5d2561
--- /dev/null
+++ b/scripts/kvm/kvm_stat
@@ -0,0 +1,646 @@
+#!/usr/bin/python
+#
+# top-like utility for displaying kvm statistics
+#
+# Copyright 2006-2008 Qumranet Technologies
+# Copyright 2008-2011 Red Hat, Inc.
+#
+# Authors:
+#  Avi Kivity <avi@redhat.com>
+#
+# This work is licensed under the terms of the GNU GPL, version 2.  See
+# the COPYING file in the top-level directory.
+
+import curses
+import sys, os, time, optparse, ctypes
+from ctypes import *
+
+class DebugfsProvider(object):
+    def __init__(self):
+        self.base = '/sys/kernel/debug/kvm'
+        self._fields = os.listdir(self.base)
+    def fields(self):
+        return self._fields
+    def select(self, fields):
+        self._fields = fields
+    def read(self):
+        def val(key):
+            return int(file(self.base + '/' + key).read())
+        return dict([(key, val(key)) for key in self._fields])
+
+vmx_exit_reasons = {
+    0: 'EXCEPTION_NMI',
+    1: 'EXTERNAL_INTERRUPT',
+    2: 'TRIPLE_FAULT',
+    7: 'PENDING_INTERRUPT',
+    8: 'NMI_WINDOW',
+    9: 'TASK_SWITCH',
+    10: 'CPUID',
+    12: 'HLT',
+    14: 'INVLPG',
+    15: 'RDPMC',
+    16: 'RDTSC',
+    18: 'VMCALL',
+    19: 'VMCLEAR',
+    20: 'VMLAUNCH',
+    21: 'VMPTRLD',
+    22: 'VMPTRST',
+    23: 'VMREAD',
+    24: 'VMRESUME',
+    25: 'VMWRITE',
+    26: 'VMOFF',
+    27: 'VMON',
+    28: 'CR_ACCESS',
+    29: 'DR_ACCESS',
+    30: 'IO_INSTRUCTION',
+    31: 'MSR_READ',
+    32: 'MSR_WRITE',
+    33: 'INVALID_STATE',
+    36: 'MWAIT_INSTRUCTION',
+    39: 'MONITOR_INSTRUCTION',
+    40: 'PAUSE_INSTRUCTION',
+    41: 'MCE_DURING_VMENTRY',
+    43: 'TPR_BELOW_THRESHOLD',
+    44: 'APIC_ACCESS',
+    48: 'EPT_VIOLATION',
+    49: 'EPT_MISCONFIG',
+    54: 'WBINVD',
+    55: 'XSETBV',
+    56: 'APIC_WRITE',
+    58: 'INVPCID',
+}
+
+svm_exit_reasons = {
+    0x000: 'READ_CR0',
+    0x003: 'READ_CR3',
+    0x004: 'READ_CR4',
+    0x008: 'READ_CR8',
+    0x010: 'WRITE_CR0',
+    0x013: 'WRITE_CR3',
+    0x014: 'WRITE_CR4',
+    0x018: 'WRITE_CR8',
+    0x020: 'READ_DR0',
+    0x021: 'READ_DR1',
+    0x022: 'READ_DR2',
+    0x023: 'READ_DR3',
+    0x024: 'READ_DR4',
+    0x025: 'READ_DR5',
+    0x026: 'READ_DR6',
+    0x027: 'READ_DR7',
+    0x030: 'WRITE_DR0',
+    0x031: 'WRITE_DR1',
+    0x032: 'WRITE_DR2',
+    0x033: 'WRITE_DR3',
+    0x034: 'WRITE_DR4',
+    0x035: 'WRITE_DR5',
+    0x036: 'WRITE_DR6',
+    0x037: 'WRITE_DR7',
+    0x040: 'EXCP_BASE',
+    0x060: 'INTR',
+    0x061: 'NMI',
+    0x062: 'SMI',
+    0x063: 'INIT',
+    0x064: 'VINTR',
+    0x065: 'CR0_SEL_WRITE',
+    0x066: 'IDTR_READ',
+    0x067: 'GDTR_READ',
+    0x068: 'LDTR_READ',
+    0x069: 'TR_READ',
+    0x06a: 'IDTR_WRITE',
+    0x06b: 'GDTR_WRITE',
+    0x06c: 'LDTR_WRITE',
+    0x06d: 'TR_WRITE',
+    0x06e: 'RDTSC',
+    0x06f: 'RDPMC',
+    0x070: 'PUSHF',
+    0x071: 'POPF',
+    0x072: 'CPUID',
+    0x073: 'RSM',
+    0x074: 'IRET',
+    0x075: 'SWINT',
+    0x076: 'INVD',
+    0x077: 'PAUSE',
+    0x078: 'HLT',
+    0x079: 'INVLPG',
+    0x07a: 'INVLPGA',
+    0x07b: 'IOIO',
+    0x07c: 'MSR',
+    0x07d: 'TASK_SWITCH',
+    0x07e: 'FERR_FREEZE',
+    0x07f: 'SHUTDOWN',
+    0x080: 'VMRUN',
+    0x081: 'VMMCALL',
+    0x082: 'VMLOAD',
+    0x083: 'VMSAVE',
+    0x084: 'STGI',
+    0x085: 'CLGI',
+    0x086: 'SKINIT',
+    0x087: 'RDTSCP',
+    0x088: 'ICEBP',
+    0x089: 'WBINVD',
+    0x08a: 'MONITOR',
+    0x08b: 'MWAIT',
+    0x08c: 'MWAIT_COND',
+    0x08d: 'XSETBV',
+    0x400: 'NPF',
+}
+
+# EC definition of HSR (from arch/arm64/include/asm/kvm_arm.h)
+aarch64_exit_reasons = {
+    0x00: 'UNKNOWN',
+    0x01: 'WFI',
+    0x03: 'CP15_32',
+    0x04: 'CP15_64',
+    0x05: 'CP14_MR',
+    0x06: 'CP14_LS',
+    0x07: 'FP_ASIMD',
+    0x08: 'CP10_ID',
+    0x0C: 'CP14_64',
+    0x0E: 'ILL_ISS',
+    0x11: 'SVC32',
+    0x12: 'HVC32',
+    0x13: 'SMC32',
+    0x15: 'SVC64',
+    0x16: 'HVC64',
+    0x17: 'SMC64',
+    0x18: 'SYS64',
+    0x20: 'IABT',
+    0x21: 'IABT_HYP',
+    0x22: 'PC_ALIGN',
+    0x24: 'DABT',
+    0x25: 'DABT_HYP',
+    0x26: 'SP_ALIGN',
+    0x28: 'FP_EXC32',
+    0x2C: 'FP_EXC64',
+    0x2F: 'SERROR',
+    0x30: 'BREAKPT',
+    0x31: 'BREAKPT_HYP',
+    0x32: 'SOFTSTP',
+    0x33: 'SOFTSTP_HYP',
+    0x34: 'WATCHPT',
+    0x35: 'WATCHPT_HYP',
+    0x38: 'BKPT32',
+    0x3A: 'VECTOR32',
+    0x3C: 'BRK64',
+}
+
+# From include/uapi/linux/kvm.h, KVM_EXIT_xxx
+userspace_exit_reasons = {
+     0: 'UNKNOWN',
+     1: 'EXCEPTION',
+     2: 'IO',
+     3: 'HYPERCALL',
+     4: 'DEBUG',
+     5: 'HLT',
+     6: 'MMIO',
+     7: 'IRQ_WINDOW_OPEN',
+     8: 'SHUTDOWN',
+     9: 'FAIL_ENTRY',
+    10: 'INTR',
+    11: 'SET_TPR',
+    12: 'TPR_ACCESS',
+    13: 'S390_SIEIC',
+    14: 'S390_RESET',
+    15: 'DCR',
+    16: 'NMI',
+    17: 'INTERNAL_ERROR',
+    18: 'OSI',
+    19: 'PAPR_HCALL',
+    20: 'S390_UCONTROL',
+    21: 'WATCHDOG',
+    22: 'S390_TSCH',
+    23: 'EPR',
+    24: 'SYSTEM_EVENT',
+}
+
+x86_exit_reasons = {
+    'vmx': vmx_exit_reasons,
+    'svm': svm_exit_reasons,
+}
+
+sc_perf_evt_open = None
+exit_reasons = None
+
+ioctl_numbers = {
+    'SET_FILTER' : 0x40082406,
+    'ENABLE'     : 0x00002400,
+    'DISABLE'    : 0x00002401,
+    'RESET'      : 0x00002403,
+}
+
+def x86_init(flag):
+    globals().update({
+        'sc_perf_evt_open' : 298,
+        'exit_reasons' : x86_exit_reasons[flag],
+    })
+
+def s390_init():
+    globals().update({
+        'sc_perf_evt_open' : 331
+    })
+
+def ppc_init():
+    globals().update({
+        'sc_perf_evt_open' : 319,
+        'ioctl_numbers' : {
+            'SET_FILTER' : 0x80002406 | (ctypes.sizeof(ctypes.c_char_p) << 16),
+            'ENABLE'     : 0x20002400,
+            'DISABLE'    : 0x20002401,
+        }
+    })
+
+def aarch64_init():
+    globals().update({
+        'sc_perf_evt_open' : 241,
+        'exit_reasons' : aarch64_exit_reasons,
+    })
+
+def detect_platform():
+    if os.uname()[4].startswith('ppc'):
+        ppc_init()
+        return
+    elif os.uname()[4].startswith('aarch64'):
+        aarch64_init()
+        return
+
+    for line in file('/proc/cpuinfo').readlines():
+        if line.startswith('flags'):
+            for flag in line.split():
+                if flag in x86_exit_reasons:
+                    x86_init(flag)
+                    return
+        elif line.startswith('vendor_id'):
+            for flag in line.split():
+                if flag == 'IBM/S390':
+                    s390_init()
+                    return
+
+detect_platform()
+
+def invert(d):
+    return dict((x[1], x[0]) for x in d.iteritems())
+
+filters = {}
+filters['kvm_userspace_exit'] = ('reason', invert(userspace_exit_reasons))
+if exit_reasons:
+    filters['kvm_exit'] = ('exit_reason', invert(exit_reasons))
+
+import struct, array
+
+libc = ctypes.CDLL('libc.so.6')
+syscall = libc.syscall
+get_errno = libc.__errno_location
+get_errno.restype = POINTER(c_int)
+
+class perf_event_attr(ctypes.Structure):
+    _fields_ = [('type', ctypes.c_uint32),
+                ('size', ctypes.c_uint32),
+                ('config', ctypes.c_uint64),
+                ('sample_freq', ctypes.c_uint64),
+                ('sample_type', ctypes.c_uint64),
+                ('read_format', ctypes.c_uint64),
+                ('flags', ctypes.c_uint64),
+                ('wakeup_events', ctypes.c_uint32),
+                ('bp_type', ctypes.c_uint32),
+                ('bp_addr', ctypes.c_uint64),
+                ('bp_len', ctypes.c_uint64),
+                ]
+def _perf_event_open(attr, pid, cpu, group_fd, flags):
+    return syscall(sc_perf_evt_open, ctypes.pointer(attr), ctypes.c_int(pid),
+                   ctypes.c_int(cpu), ctypes.c_int(group_fd),
+                   ctypes.c_long(flags))
+
+PERF_TYPE_HARDWARE              = 0
+PERF_TYPE_SOFTWARE              = 1
+PERF_TYPE_TRACEPOINT            = 2
+PERF_TYPE_HW_CACHE              = 3
+PERF_TYPE_RAW                   = 4
+PERF_TYPE_BREAKPOINT            = 5
+
+PERF_SAMPLE_IP                  = 1 << 0
+PERF_SAMPLE_TID                 = 1 << 1
+PERF_SAMPLE_TIME                = 1 << 2
+PERF_SAMPLE_ADDR                = 1 << 3
+PERF_SAMPLE_READ                = 1 << 4
+PERF_SAMPLE_CALLCHAIN           = 1 << 5
+PERF_SAMPLE_ID                  = 1 << 6
+PERF_SAMPLE_CPU                 = 1 << 7
+PERF_SAMPLE_PERIOD              = 1 << 8
+PERF_SAMPLE_STREAM_ID           = 1 << 9
+PERF_SAMPLE_RAW                 = 1 << 10
+
+PERF_FORMAT_TOTAL_TIME_ENABLED  = 1 << 0
+PERF_FORMAT_TOTAL_TIME_RUNNING  = 1 << 1
+PERF_FORMAT_ID                  = 1 << 2
+PERF_FORMAT_GROUP               = 1 << 3
+
+import re
+
+sys_tracing = '/sys/kernel/debug/tracing'
+
+class Group(object):
+    def __init__(self, cpu):
+        self.events = []
+        self.group_leader = None
+        self.cpu = cpu
+    def add_event(self, name, event_set, tracepoint, filter = None):
+        self.events.append(Event(group = self,
+                                 name = name, event_set = event_set,
+                                 tracepoint = tracepoint, filter = filter))
+        if len(self.events) == 1:
+            self.file = os.fdopen(self.events[0].fd)
+    def read(self):
+        bytes = 8 * (1 + len(self.events))
+        fmt = 'xxxxxxxx' + 'q' * len(self.events)
+        return dict(zip([event.name for event in self.events],
+                        struct.unpack(fmt, self.file.read(bytes))))
+
+class Event(object):
+    def __init__(self, group, name, event_set, tracepoint, filter = None):
+        self.name = name
+        attr = perf_event_attr()
+        attr.type = PERF_TYPE_TRACEPOINT
+        attr.size = ctypes.sizeof(attr)
+        id_path = os.path.join(sys_tracing, 'events', event_set,
+                               tracepoint, 'id')
+        id = int(file(id_path).read())
+        attr.config = id
+        attr.sample_type = (PERF_SAMPLE_RAW
+                            | PERF_SAMPLE_TIME
+                            | PERF_SAMPLE_CPU)
+        attr.sample_period = 1
+        attr.read_format = PERF_FORMAT_GROUP
+        group_leader = -1
+        if group.events:
+            group_leader = group.events[0].fd
+        fd = _perf_event_open(attr, -1, group.cpu, group_leader, 0)
+        if fd == -1:
+            err = get_errno()[0]
+            raise Exception('perf_event_open failed, errno = ' + err.__str__())
+        if filter:
+            import fcntl
+            fcntl.ioctl(fd, ioctl_numbers['SET_FILTER'], filter)
+        self.fd = fd
+    def enable(self):
+        import fcntl
+        fcntl.ioctl(self.fd, ioctl_numbers['ENABLE'], 0)
+    def disable(self):
+        import fcntl
+        fcntl.ioctl(self.fd, ioctl_numbers['DISABLE'], 0)
+    def reset(self):
+        import fcntl
+        fcntl.ioctl(self.fd, ioctl_numbers['RESET'], 0)
+
+class TracepointProvider(object):
+    def __init__(self):
+        path = os.path.join(sys_tracing, 'events', 'kvm')
+        fields = [f
+                  for f in os.listdir(path)
+                  if os.path.isdir(os.path.join(path, f))]
+        extra = []
+        for f in fields:
+            if f in filters:
+                subfield, values = filters[f]
+                for name, number in values.iteritems():
+                    extra.append(f + '(' + name + ')')
+        fields += extra
+        self._setup(fields)
+        self.select(fields)
+    def fields(self):
+        return self._fields
+
+    def _online_cpus(self):
+        l = []
+        pattern = r'cpu([0-9]+)'
+        basedir = '/sys/devices/system/cpu'
+        for entry in os.listdir(basedir):
+            match = re.match(pattern, entry)
+            if not match:
+                continue
+            path = os.path.join(basedir, entry, 'online')
+            if os.path.exists(path) and open(path).read().strip() != '1':
+                continue
+            l.append(int(match.group(1)))
+        return l
+
+    def _setup(self, _fields):
+        self._fields = _fields
+        cpus = self._online_cpus()
+        import resource
+        nfiles = len(cpus) * 1000
+        resource.setrlimit(resource.RLIMIT_NOFILE, (nfiles, nfiles))
+        events = []
+        self.group_leaders = []
+        for cpu in cpus:
+            group = Group(cpu)
+            for name in _fields:
+                tracepoint = name
+                filter = None
+                m = re.match(r'(.*)\((.*)\)', name)
+                if m:
+                    tracepoint, sub = m.groups()
+                    filter = '%s==%d\0' % (filters[tracepoint][0],
+                                           filters[tracepoint][1][sub])
+                event = group.add_event(name, event_set = 'kvm',
+                                        tracepoint = tracepoint,
+                                        filter = filter)
+            self.group_leaders.append(group)
+    def select(self, fields):
+        for group in self.group_leaders:
+            for event in group.events:
+                if event.name in fields:
+                    event.reset()
+                    event.enable()
+                else:
+                    event.disable()
+    def read(self):
+        from collections import defaultdict
+        ret = defaultdict(int)
+        for group in self.group_leaders:
+            for name, val in group.read().iteritems():
+                ret[name] += val
+        return ret
+
+class Stats:
+    def __init__(self, providers, fields = None):
+        self.providers = providers
+        self.fields_filter = fields
+        self._update()
+    def _update(self):
+        def wanted(key):
+            import re
+            if not self.fields_filter:
+                return True
+            return re.match(self.fields_filter, key) is not None
+        self.values = dict()
+        for d in providers:
+            provider_fields = [key for key in d.fields() if wanted(key)]
+            for key in provider_fields:
+                self.values[key] = None
+            d.select(provider_fields)
+    def set_fields_filter(self, fields_filter):
+        self.fields_filter = fields_filter
+        self._update()
+    def get(self):
+        for d in providers:
+            new = d.read()
+            for key in d.fields():
+                oldval = self.values.get(key, (0, 0))
+                newval = new[key]
+                newdelta = None
+                if oldval is not None:
+                    newdelta = newval - oldval[0]
+                self.values[key] = (newval, newdelta)
+        return self.values
+
+if not os.access('/sys/kernel/debug', os.F_OK):
+    print 'Please enable CONFIG_DEBUG_FS in your kernel'
+    sys.exit(1)
+if not os.access('/sys/kernel/debug/kvm', os.F_OK):
+    print "Please mount debugfs ('mount -t debugfs debugfs /sys/kernel/debug')"
+    print "and ensure the kvm modules are loaded"
+    sys.exit(1)
+
+label_width = 40
+number_width = 10
+
+def tui(screen, stats):
+    curses.use_default_colors()
+    curses.noecho()
+    drilldown = False
+    fields_filter = stats.fields_filter
+    def update_drilldown():
+        if not fields_filter:
+            if drilldown:
+                stats.set_fields_filter(None)
+            else:
+                stats.set_fields_filter(r'^[^\(]*$')
+    update_drilldown()
+    def refresh(sleeptime):
+        screen.erase()
+        screen.addstr(0, 0, 'kvm statistics')
+        screen.addstr(2, 1, 'Event')
+        screen.addstr(2, 1 + label_width + number_width - len('Total'), 'Total')
+        screen.addstr(2, 1 + label_width + number_width + 8 - len('Current'), 'Current')
+        row = 3
+        s = stats.get()
+        def sortkey(x):
+            if s[x][1]:
+                return (-s[x][1], -s[x][0])
+            else:
+                return (0, -s[x][0])
+        for key in sorted(s.keys(), key = sortkey):
+            if row >= screen.getmaxyx()[0]:
+                break
+            values = s[key]
+            if not values[0] and not values[1]:
+                break
+            col = 1
+            screen.addstr(row, col, key)
+            col += label_width
+            screen.addstr(row, col, '%10d' % (values[0],))
+            col += number_width
+            if values[1] is not None:
+                screen.addstr(row, col, '%8d' % (values[1] / sleeptime,))
+            row += 1
+        screen.refresh()
+
+    sleeptime = 0.25
+    while True:
+        refresh(sleeptime)
+        curses.halfdelay(int(sleeptime * 10))
+        sleeptime = 3
+        try:
+            c = screen.getkey()
+            if c == 'x':
+                drilldown = not drilldown
+                update_drilldown()
+            if c == 'q':
+                break
+        except KeyboardInterrupt:
+            break
+        except curses.error:
+            continue
+
+def batch(stats):
+    s = stats.get()
+    time.sleep(1)
+    s = stats.get()
+    for key in sorted(s.keys()):
+        values = s[key]
+        print '%-22s%10d%10d' % (key, values[0], values[1])
+
+def log(stats):
+    keys = sorted(stats.get().iterkeys())
+    def banner():
+        for k in keys:
+            print '%10s' % k[0:9],
+        print
+    def statline():
+        s = stats.get()
+        for k in keys:
+            print ' %9d' % s[k][1],
+        print
+    line = 0
+    banner_repeat = 20
+    while True:
+        time.sleep(1)
+        if line % banner_repeat == 0:
+            banner()
+        statline()
+        line += 1
+
+options = optparse.OptionParser()
+options.add_option('-1', '--once', '--batch',
+                   action = 'store_true',
+                   default = False,
+                   dest = 'once',
+                   help = 'run in batch mode for one second',
+                   )
+options.add_option('-l', '--log',
+                   action = 'store_true',
+                   default = False,
+                   dest = 'log',
+                   help = 'run in logging mode (like vmstat)',
+                   )
+options.add_option('-t', '--tracepoints',
+                   action = 'store_true',
+                   default = False,
+                   dest = 'tracepoints',
+                   help = 'retrieve statistics from tracepoints',
+                   )
+options.add_option('-d', '--debugfs',
+                   action = 'store_true',
+                   default = False,
+                   dest = 'debugfs',
+                   help = 'retrieve statistics from debugfs',
+                   )
+options.add_option('-f', '--fields',
+                   action = 'store',
+                   default = None,
+                   dest = 'fields',
+                   help = 'fields to display (regex)',
+                   )
+(options, args) = options.parse_args(sys.argv)
+
+providers = []
+if options.tracepoints:
+    providers.append(TracepointProvider())
+if options.debugfs:
+    providers.append(DebugfsProvider())
+
+if len(providers) == 0:
+    try:
+        providers = [TracepointProvider()]
+    except:
+        providers = [DebugfsProvider()]
+
+stats = Stats(providers, fields = options.fields)
+
+if options.log:
+    log(stats)
+elif not options.once:
+    import curses.wrapper
+    curses.wrapper(tui, stats)
+else:
+    batch(stats)
diff --git a/scripts/kvm/kvm_stat.texi b/scripts/kvm/kvm_stat.texi
new file mode 100644
index 00000000..6ce00d80
--- /dev/null
+++ b/scripts/kvm/kvm_stat.texi
@@ -0,0 +1,55 @@
+@example
+@c man begin SYNOPSIS
+usage: kvm_stat [OPTION]...
+@c man end
+@end example
+
+@c man begin DESCRIPTION
+
+kvm_stat prints counts of KVM kernel module trace events.  These events signify
+state transitions such as guest mode entry and exit.
+
+This tool is useful for observing guest behavior from the host perspective.
+Often conclusions about performance or buggy behavior can be drawn from the
+output.
+
+The set of KVM kernel module trace events may be specific to the kernel version
+or architecture.  It is best to check the KVM kernel module source code for the
+meaning of events.
+
+Note that trace events are counted globally across all running guests.
+
+@c man end
+
+@c man begin OPTIONS
+@table @option
+@item -1, --once, --batch
+  run in batch mode for one second
+@item -l, --log
+  run in logging mode (like vmstat)
+@item -t, --tracepoints
+  retrieve statistics from tracepoints
+@item -d, --debugfs
+  retrieve statistics from debugfs
+@item -f, --fields=@var{fields}
+  fields to display (regex)
+@item -h, --help
+  show help message
+@end table
+
+@c man end
+
+@ignore
+
+@setfilename kvm_stat
+@settitle Report KVM kernel module event counters.
+
+@c man begin AUTHOR
+Stefan Hajnoczi <stefanha@redhat.com>
+@c man end
+
+@c man begin SEEALSO
+perf(1), trace-cmd(1)
+@c man end
+
+@end ignore
diff --git a/scripts/kvm/vmxcap b/scripts/kvm/vmxcap
new file mode 100755
index 00000000..8f0371f4
--- /dev/null
+++ b/scripts/kvm/vmxcap
@@ -0,0 +1,260 @@
+#!/usr/bin/python
+#
+# tool for querying VMX capabilities
+#
+# Copyright 2009-2010 Red Hat, Inc.
+#
+# Authors:
+#  Avi Kivity <avi@redhat.com>
+#
+# This work is licensed under the terms of the GNU GPL, version 2.  See
+# the COPYING file in the top-level directory.
+
+MSR_IA32_VMX_BASIC = 0x480
+MSR_IA32_VMX_PINBASED_CTLS = 0x481
+MSR_IA32_VMX_PROCBASED_CTLS = 0x482
+MSR_IA32_VMX_EXIT_CTLS = 0x483
+MSR_IA32_VMX_ENTRY_CTLS = 0x484
+MSR_IA32_VMX_MISC_CTLS = 0x485
+MSR_IA32_VMX_PROCBASED_CTLS2 = 0x48B
+MSR_IA32_VMX_EPT_VPID_CAP = 0x48C
+MSR_IA32_VMX_TRUE_PINBASED_CTLS = 0x48D
+MSR_IA32_VMX_TRUE_PROCBASED_CTLS = 0x48E
+MSR_IA32_VMX_TRUE_EXIT_CTLS = 0x48F
+MSR_IA32_VMX_TRUE_ENTRY_CTLS = 0x490
+MSR_IA32_VMX_VMFUNC = 0x491
+
+class msr(object):
+    def __init__(self):
+        try:
+            self.f = open('/dev/cpu/0/msr', 'r', 0)
+        except:
+            self.f = open('/dev/msr0', 'r', 0)
+    def read(self, index, default = None):
+        import struct
+        self.f.seek(index)
+        try:
+            return struct.unpack('Q', self.f.read(8))[0]
+        except:
+            return default
+
+class Control(object):
+    def __init__(self, name, bits, cap_msr, true_cap_msr = None):
+        self.name = name
+        self.bits = bits
+        self.cap_msr = cap_msr
+        self.true_cap_msr = true_cap_msr
+    def read2(self, nr):
+        m = msr()
+        val = m.read(nr, 0)
+        return (val & 0xffffffff, val >> 32)
+    def show(self):
+        print self.name
+        mbz, mb1 = self.read2(self.cap_msr)
+        tmbz, tmb1 = 0, 0
+        if self.true_cap_msr:
+            tmbz, tmb1 = self.read2(self.true_cap_msr)
+        for bit in sorted(self.bits.keys()):
+            zero = not (mbz & (1 << bit))
+            one = mb1 & (1 << bit)
+            true_zero = not (tmbz & (1 << bit))
+            true_one = tmb1 & (1 << bit)
+            s= '?'
+            if (self.true_cap_msr and true_zero and true_one
+                and one and not zero):
+                s = 'default'
+            elif zero and not one:
+                s = 'no'
+            elif one and not zero:
+                s = 'forced'
+            elif one and zero:
+                s = 'yes'
+            print '  %-40s %s' % (self.bits[bit], s)
+
+class Misc(object):
+    def __init__(self, name, bits, msr):
+        self.name = name
+        self.bits = bits
+        self.msr = msr
+    def show(self):
+        print self.name
+        value = msr().read(self.msr, 0)
+        def first_bit(key):
+            if type(key) is tuple:
+                return key[0]
+            else:
+                return key
+        for bits in sorted(self.bits.keys(), key = first_bit):
+            if type(bits) is tuple:
+                lo, hi = bits
+                fmt = int
+            else:
+                lo = hi = bits
+                def fmt(x):
+                    return { True: 'yes', False: 'no' }[x]
+            v = (value >> lo) & ((1 << (hi - lo + 1)) - 1)
+            print '  %-40s %s' % (self.bits[bits], fmt(v))
+
+controls = [
+    Misc(
+        name = 'Basic VMX Information',
+        bits = {
+            (0, 30): 'Revision',
+            (32,44): 'VMCS size',
+            48: 'VMCS restricted to 32 bit addresses',
+            49: 'Dual-monitor support',
+            (50, 53): 'VMCS memory type',
+            54: 'INS/OUTS instruction information',
+            55: 'IA32_VMX_TRUE_*_CTLS support',
+            },
+        msr = MSR_IA32_VMX_BASIC,
+        ),
+    Control(
+        name = 'pin-based controls',
+        bits = {
+            0: 'External interrupt exiting',
+            3: 'NMI exiting',
+            5: 'Virtual NMIs',
+            6: 'Activate VMX-preemption timer',
+            7: 'Process posted interrupts',
+            },
+        cap_msr = MSR_IA32_VMX_PINBASED_CTLS,
+        true_cap_msr = MSR_IA32_VMX_TRUE_PINBASED_CTLS,
+        ),
+
+    Control(
+        name = 'primary processor-based controls',
+        bits = {
+            2: 'Interrupt window exiting',
+            3: 'Use TSC offsetting',
+            7: 'HLT exiting',
+            9: 'INVLPG exiting',
+            10: 'MWAIT exiting',
+            11: 'RDPMC exiting',
+            12: 'RDTSC exiting',
+            15: 'CR3-load exiting',
+            16: 'CR3-store exiting',
+            19: 'CR8-load exiting',
+            20: 'CR8-store exiting',
+            21: 'Use TPR shadow',
+            22: 'NMI-window exiting',
+            23: 'MOV-DR exiting',
+            24: 'Unconditional I/O exiting',
+            25: 'Use I/O bitmaps',
+            27: 'Monitor trap flag',
+            28: 'Use MSR bitmaps',
+            29: 'MONITOR exiting',
+            30: 'PAUSE exiting',
+            31: 'Activate secondary control',
+            },
+        cap_msr = MSR_IA32_VMX_PROCBASED_CTLS,
+        true_cap_msr = MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
+        ),
+
+    Control(
+        name = 'secondary processor-based controls',
+        bits = {
+            0: 'Virtualize APIC accesses',
+            1: 'Enable EPT',
+            2: 'Descriptor-table exiting',
+            3: 'Enable RDTSCP',
+            4: 'Virtualize x2APIC mode',
+            5: 'Enable VPID',
+            6: 'WBINVD exiting',
+            7: 'Unrestricted guest',
+            8: 'APIC register emulation',
+            9: 'Virtual interrupt delivery',
+            10: 'PAUSE-loop exiting',
+            11: 'RDRAND exiting',
+            12: 'Enable INVPCID',
+            13: 'Enable VM functions',
+            14: 'VMCS shadowing',
+            16: 'RDSEED exiting',
+            18: 'EPT-violation #VE',
+            20: 'Enable XSAVES/XRSTORS',
+            },
+        cap_msr = MSR_IA32_VMX_PROCBASED_CTLS2,
+        ),
+
+    Control(
+        name = 'VM-Exit controls',
+        bits = {
+            2: 'Save debug controls',
+            9: 'Host address-space size',
+            12: 'Load IA32_PERF_GLOBAL_CTRL',
+            15: 'Acknowledge interrupt on exit',
+            18: 'Save IA32_PAT',
+            19: 'Load IA32_PAT',
+            20: 'Save IA32_EFER',
+            21: 'Load IA32_EFER',
+            22: 'Save VMX-preemption timer value',
+            },
+        cap_msr = MSR_IA32_VMX_EXIT_CTLS,
+        true_cap_msr = MSR_IA32_VMX_TRUE_EXIT_CTLS,
+        ),
+
+    Control(
+        name = 'VM-Entry controls',
+        bits = {
+            2: 'Load debug controls',
+            9: 'IA-32e mode guest',
+            10: 'Entry to SMM',
+            11: 'Deactivate dual-monitor treatment',
+            13: 'Load IA32_PERF_GLOBAL_CTRL',
+            14: 'Load IA32_PAT',
+            15: 'Load IA32_EFER',
+            },
+        cap_msr = MSR_IA32_VMX_ENTRY_CTLS,
+        true_cap_msr = MSR_IA32_VMX_TRUE_ENTRY_CTLS,
+        ),
+
+    Misc(
+        name = 'Miscellaneous data',
+        bits = {
+            (0,4): 'VMX-preemption timer scale (log2)',
+            5: 'Store EFER.LMA into IA-32e mode guest control',
+            6: 'HLT activity state',
+            7: 'Shutdown activity state',
+            8: 'Wait-for-SIPI activity state',
+            15: 'IA32_SMBASE support',
+            (16,24): 'Number of CR3-target values',
+            (25,27): 'MSR-load/store count recommendation',
+            28: 'IA32_SMM_MONITOR_CTL[2] can be set to 1',
+            29: 'VMWRITE to VM-exit information fields',
+            (32,63): 'MSEG revision identifier',
+            },
+        msr = MSR_IA32_VMX_MISC_CTLS,
+        ),
+
+    Misc(
+        name = 'VPID and EPT capabilities',
+        bits = {
+            0: 'Execute-only EPT translations',
+            6: 'Page-walk length 4',
+            8: 'Paging-structure memory type UC',
+            14: 'Paging-structure memory type WB',
+            16: '2MB EPT pages',
+            17: '1GB EPT pages',
+            20: 'INVEPT supported',
+            21: 'EPT accessed and dirty flags',
+            25: 'Single-context INVEPT',
+            26: 'All-context INVEPT',
+            32: 'INVVPID supported',
+            40: 'Individual-address INVVPID',
+            41: 'Single-context INVVPID',
+            42: 'All-context INVVPID',
+            43: 'Single-context-retaining-globals INVVPID',
+            },
+        msr = MSR_IA32_VMX_EPT_VPID_CAP,
+        ),
+    Misc(
+        name = 'VM Functions',
+        bits = {
+            0: 'EPTP Switching',
+            },
+        msr = MSR_IA32_VMX_VMFUNC,
+        ),
+    ]
+
+for c in controls:
+    c.show()