Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "PPC:
   - Better machine check handling for HV KVM
   - Ability to support guests with threads=2, 4 or 8 on POWER9
   - Fix for a race that could cause delayed recognition of signals
   - Fix for a bug where POWER9 guests could sleep with interrupts pending.

  ARM:
   - VCPU request overhaul
   - allow timer and PMU to have their interrupt number selected from userspace
   - workaround for Cavium erratum 30115
   - handling of memory poisonning
   - the usual crop of fixes and cleanups

  s390:
   - initial machine check forwarding
   - migration support for the CMMA page hinting information
   - cleanups and fixes

  x86:
   - nested VMX bugfixes and improvements
   - more reliable NMI window detection on AMD
   - APIC timer optimizations

  Generic:
   - VCPU request overhaul + documentation of common code patterns
   - kvm_stat improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (124 commits)
  Update my email address
  kvm: vmx: allow host to access guest MSR_IA32_BNDCFGS
  x86: kvm: mmu: use ept a/d in vmcs02 iff used in vmcs12
  kvm: x86: mmu: allow A/D bits to be disabled in an mmu
  x86: kvm: mmu: make spte mmio mask more explicit
  x86: kvm: mmu: dead code thanks to access tracking
  KVM: PPC: Book3S: Fix typo in XICS-on-XIVE state saving code
  KVM: PPC: Book3S HV: Close race with testing for signals on guest entry
  KVM: PPC: Book3S HV: Simplify dynamic micro-threading code
  KVM: x86: remove ignored type attribute
  KVM: LAPIC: Fix lapic timer injection delay
  KVM: lapic: reorganize restart_apic_timer
  KVM: lapic: reorganize start_hv_timer
  kvm: nVMX: Check memory operand to INVVPID
  KVM: s390: Inject machine check into the nested guest
  KVM: s390: Inject machine check into the guest
  tools/kvm_stat: add new interactive command 'b'
  tools/kvm_stat: add new command line switch '-i'
  tools/kvm_stat: fix error on interactive command 'g'
  KVM: SVM: suppress unnecessary NMI singlestep on GIF=0 and nested exit
  ...

2 files changed, 442 insertions, 239 deletions

diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index 8f74ed8e7237..dd8f00cfb8b4 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -295,114 +295,6 @@ class ArchS390(Arch):
 ARCH = Arch.get_arch()
 
 
-def walkdir(path):
-    """Returns os.walk() data for specified directory.
-
-    As it is only a wrapper it returns the same 3-tuple of (dirpath,
-    dirnames, filenames).
-    """
-    return next(os.walk(path))
-
-
-def parse_int_list(list_string):
-    """Returns an int list from a string of comma separated integers and
-    integer ranges."""
-    integers = []
-    members = list_string.split(',')
-
-    for member in members:
-        if '-' not in member:
-            integers.append(int(member))
-        else:
-            int_range = member.split('-')
-            integers.extend(range(int(int_range[0]),
-                                  int(int_range[1]) + 1))
-
-    return integers
-
-
-def get_pid_from_gname(gname):
-    """Fuzzy function to convert guest name to QEMU process pid.
-
-    Returns a list of potential pids, can be empty if no match found.
-    Throws an exception on processing errors.
-
-    """
-    pids = []
-    try:
-        child = subprocess.Popen(['ps', '-A', '--format', 'pid,args'],
-                                 stdout=subprocess.PIPE)
-    except:
-        raise Exception
-    for line in child.stdout:
-        line = line.lstrip().split(' ', 1)
-        # perform a sanity check before calling the more expensive
-        # function to possibly extract the guest name
-        if ' -name ' in line[1] and gname == get_gname_from_pid(line[0]):
-            pids.append(int(line[0]))
-    child.stdout.close()
-
-    return pids
-
-
-def get_gname_from_pid(pid):
-    """Returns the guest name for a QEMU process pid.
-
-    Extracts the guest name from the QEMU comma line by processing the '-name'
-    option. Will also handle names specified out of sequence.
-
-    """
-    name = ''
-    try:
-        line = open('/proc/{}/cmdline'.format(pid), 'rb').read().split('\0')
-        parms = line[line.index('-name') + 1].split(',')
-        while '' in parms:
-            # commas are escaped (i.e. ',,'), hence e.g. 'foo,bar' results in
-            # ['foo', '', 'bar'], which we revert here
-            idx = parms.index('')
-            parms[idx - 1] += ',' + parms[idx + 1]
-            del parms[idx:idx+2]
-        # the '-name' switch allows for two ways to specify the guest name,
-        # where the plain name overrides the name specified via 'guest='
-        for arg in parms:
-            if '=' not in arg:
-                name = arg
-                break
-            if arg[:6] == 'guest=':
-                name = arg[6:]
-    except (ValueError, IOError, IndexError):
-        pass
-
-    return name
-
-
-def get_online_cpus():
-    """Returns a list of cpu id integers."""
-    with open('/sys/devices/system/cpu/online') as cpu_list:
-        cpu_string = cpu_list.readline()
-        return parse_int_list(cpu_string)
-
-
-def get_filters():
-    """Returns a dict of trace events, their filter ids and
-    the values that can be filtered.
-
-    Trace events can be filtered for special values by setting a
-    filter string via an ioctl. The string normally has the format
-    identifier==value. For each filter a new event will be created, to
-    be able to distinguish the events.
-
-    """
-    filters = {}
-    filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS)
-    if ARCH.exit_reasons:
-        filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons)
-    return filters
-
-libc = ctypes.CDLL('libc.so.6', use_errno=True)
-syscall = libc.syscall
-
-
 class perf_event_attr(ctypes.Structure):
     """Struct that holds the necessary data to set up a trace event.
 
@@ -432,25 +324,6 @@ class perf_event_attr(ctypes.Structure):
         self.read_format = PERF_FORMAT_GROUP
 
 
-def perf_event_open(attr, pid, cpu, group_fd, flags):
-    """Wrapper for the sys_perf_evt_open() syscall.
-
-    Used to set up performance events, returns a file descriptor or -1
-    on error.
-
-    Attributes are:
-    - syscall number
-    - struct perf_event_attr *
-    - pid or -1 to monitor all pids
-    - cpu number or -1 to monitor all cpus
-    - The file descriptor of the group leader or -1 to create a group.
-    - flags
-
-    """
-    return syscall(ARCH.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_TRACEPOINT = 2
 PERF_FORMAT_GROUP = 1 << 3
 
@@ -495,6 +368,8 @@ class Event(object):
     """Represents a performance event and manages its life cycle."""
     def __init__(self, name, group, trace_cpu, trace_pid, trace_point,
                  trace_filter, trace_set='kvm'):
+        self.libc = ctypes.CDLL('libc.so.6', use_errno=True)
+        self.syscall = self.libc.syscall
         self.name = name
         self.fd = None
         self.setup_event(group, trace_cpu, trace_pid, trace_point,
@@ -511,6 +386,25 @@ class Event(object):
         if self.fd:
             os.close(self.fd)
 
+    def perf_event_open(self, attr, pid, cpu, group_fd, flags):
+        """Wrapper for the sys_perf_evt_open() syscall.
+
+        Used to set up performance events, returns a file descriptor or -1
+        on error.
+
+        Attributes are:
+        - syscall number
+        - struct perf_event_attr *
+        - pid or -1 to monitor all pids
+        - cpu number or -1 to monitor all cpus
+        - The file descriptor of the group leader or -1 to create a group.
+        - flags
+
+        """
+        return self.syscall(ARCH.sc_perf_evt_open, ctypes.pointer(attr),
+                            ctypes.c_int(pid), ctypes.c_int(cpu),
+                            ctypes.c_int(group_fd), ctypes.c_long(flags))
+
     def setup_event_attribute(self, trace_set, trace_point):
         """Returns an initialized ctype perf_event_attr struct."""
 
@@ -539,8 +433,8 @@ class Event(object):
         if group.events:
             group_leader = group.events[0].fd
 
-        fd = perf_event_open(event_attr, trace_pid,
-                             trace_cpu, group_leader, 0)
+        fd = self.perf_event_open(event_attr, trace_pid,
+                                  trace_cpu, group_leader, 0)
         if fd == -1:
             err = ctypes.get_errno()
             raise OSError(err, os.strerror(err),
@@ -575,17 +469,53 @@ class Event(object):
         fcntl.ioctl(self.fd, ARCH.ioctl_numbers['RESET'], 0)
 
 
-class TracepointProvider(object):
+class Provider(object):
+    """Encapsulates functionalities used by all providers."""
+    @staticmethod
+    def is_field_wanted(fields_filter, field):
+        """Indicate whether field is valid according to fields_filter."""
+        if not fields_filter:
+            return True
+        return re.match(fields_filter, field) is not None
+
+    @staticmethod
+    def walkdir(path):
+        """Returns os.walk() data for specified directory.
+
+        As it is only a wrapper it returns the same 3-tuple of (dirpath,
+        dirnames, filenames).
+        """
+        return next(os.walk(path))
+
+
+class TracepointProvider(Provider):
     """Data provider for the stats class.
 
     Manages the events/groups from which it acquires its data.
 
     """
-    def __init__(self):
+    def __init__(self, pid, fields_filter):
         self.group_leaders = []
-        self.filters = get_filters()
-        self._fields = self.get_available_fields()
-        self._pid = 0
+        self.filters = self.get_filters()
+        self.update_fields(fields_filter)
+        self.pid = pid
+
+    @staticmethod
+    def get_filters():
+        """Returns a dict of trace events, their filter ids and
+        the values that can be filtered.
+
+        Trace events can be filtered for special values by setting a
+        filter string via an ioctl. The string normally has the format
+        identifier==value. For each filter a new event will be created, to
+        be able to distinguish the events.
+
+        """
+        filters = {}
+        filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS)
+        if ARCH.exit_reasons:
+            filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons)
+        return filters
 
     def get_available_fields(self):
         """Returns a list of available event's of format 'event name(filter
@@ -603,7 +533,7 @@ class TracepointProvider(object):
 
         """
         path = os.path.join(PATH_DEBUGFS_TRACING, 'events', 'kvm')
-        fields = walkdir(path)[1]
+        fields = self.walkdir(path)[1]
         extra = []
         for field in fields:
             if field in self.filters:
@@ -613,6 +543,34 @@ class TracepointProvider(object):
         fields += extra
         return fields
 
+    def update_fields(self, fields_filter):
+        """Refresh fields, applying fields_filter"""
+        self._fields = [field for field in self.get_available_fields()
+                        if self.is_field_wanted(fields_filter, field)]
+
+    @staticmethod
+    def get_online_cpus():
+        """Returns a list of cpu id integers."""
+        def parse_int_list(list_string):
+            """Returns an int list from a string of comma separated integers and
+            integer ranges."""
+            integers = []
+            members = list_string.split(',')
+
+            for member in members:
+                if '-' not in member:
+                    integers.append(int(member))
+                else:
+                    int_range = member.split('-')
+                    integers.extend(range(int(int_range[0]),
+                                          int(int_range[1]) + 1))
+
+            return integers
+
+        with open('/sys/devices/system/cpu/online') as cpu_list:
+            cpu_string = cpu_list.readline()
+            return parse_int_list(cpu_string)
+
     def setup_traces(self):
         """Creates all event and group objects needed to be able to retrieve
         data."""
@@ -621,9 +579,9 @@ class TracepointProvider(object):
             # Fetch list of all threads of the monitored pid, as qemu
             # starts a thread for each vcpu.
             path = os.path.join('/proc', str(self._pid), 'task')
-            groupids = walkdir(path)[1]
+            groupids = self.walkdir(path)[1]
         else:
-            groupids = get_online_cpus()
+            groupids = self.get_online_cpus()
 
         # The constant is needed as a buffer for python libs, std
         # streams and other files that the script opens.
@@ -671,9 +629,6 @@ class TracepointProvider(object):
 
             self.group_leaders.append(group)
 
-    def available_fields(self):
-        return self.get_available_fields()
-
     @property
     def fields(self):
         return self._fields
@@ -707,7 +662,7 @@ class TracepointProvider(object):
         self.setup_traces()
         self.fields = self._fields
 
-    def read(self):
+    def read(self, by_guest=0):
         """Returns 'event name: current value' for all enabled events."""
         ret = defaultdict(int)
         for group in self.group_leaders:
@@ -723,16 +678,17 @@ class TracepointProvider(object):
                 event.reset()
 
 
-class DebugfsProvider(object):
+class DebugfsProvider(Provider):
     """Provides data from the files that KVM creates in the kvm debugfs
     folder."""
-    def __init__(self):
-        self._fields = self.get_available_fields()
+    def __init__(self, pid, fields_filter, include_past):
+        self.update_fields(fields_filter)
         self._baseline = {}
-        self._pid = 0
         self.do_read = True
         self.paths = []
-        self.reset()
+        self.pid = pid
+        if include_past:
+            self.restore()
 
     def get_available_fields(self):
         """"Returns a list of available fields.
@@ -740,7 +696,12 @@ class DebugfsProvider(object):
         The fields are all available KVM debugfs files
 
         """
-        return walkdir(PATH_DEBUGFS_KVM)[2]
+        return self.walkdir(PATH_DEBUGFS_KVM)[2]
+
+    def update_fields(self, fields_filter):
+        """Refresh fields, applying fields_filter"""
+        self._fields = [field for field in self.get_available_fields()
+                        if self.is_field_wanted(fields_filter, field)]
 
     @property
     def fields(self):
@@ -757,10 +718,9 @@ class DebugfsProvider(object):
 
     @pid.setter
     def pid(self, pid):
+        self._pid = pid
         if pid != 0:
-            self._pid = pid
-
-            vms = walkdir(PATH_DEBUGFS_KVM)[1]
+            vms = self.walkdir(PATH_DEBUGFS_KVM)[1]
             if len(vms) == 0:
                 self.do_read = False
 
@@ -771,8 +731,15 @@ class DebugfsProvider(object):
             self.do_read = True
         self.reset()
 
-    def read(self, reset=0):
-        """Returns a dict with format:'file name / field -> current value'."""
+    def read(self, reset=0, by_guest=0):
+        """Returns a dict with format:'file name / field -> current value'.
+
+        Parameter 'reset':
+          0   plain read
+          1   reset field counts to 0
+          2   restore the original field counts
+
+        """
         results = {}
 
         # If no debugfs filtering support is available, then don't read.
@@ -789,12 +756,22 @@ class DebugfsProvider(object):
             for field in self._fields:
                 value = self.read_field(field, path)
                 key = path + field
-                if reset:
+                if reset == 1:
                     self._baseline[key] = value
+                if reset == 2:
+                    self._baseline[key] = 0
                 if self._baseline.get(key, -1) == -1:
                     self._baseline[key] = value
-                results[field] = (results.get(field, 0) + value -
-                                  self._baseline.get(key, 0))
+                increment = (results.get(field, 0) + value -
+                             self._baseline.get(key, 0))
+                if by_guest:
+                    pid = key.split('-')[0]
+                    if pid in results:
+                        results[pid] += increment
+                    else:
+                        results[pid] = increment
+                else:
+                    results[field] = increment
 
         return results
 
@@ -813,6 +790,11 @@ class DebugfsProvider(object):
         self._baseline = {}
         self.read(1)
 
+    def restore(self):
+        """Reset field counters"""
+        self._baseline = {}
+        self.read(2)
+
 
 class Stats(object):
     """Manages the data providers and the data they provide.
@@ -821,33 +803,32 @@ class Stats(object):
     provider data.
 
     """
-    def __init__(self, providers, pid, fields=None):
-        self.providers = providers
-        self._pid_filter = pid
-        self._fields_filter = fields
+    def __init__(self, options):
+        self.providers = self.get_providers(options)
+        self._pid_filter = options.pid
+        self._fields_filter = options.fields
         self.values = {}
-        self.update_provider_pid()
-        self.update_provider_filters()
+
+    @staticmethod
+    def get_providers(options):
+        """Returns a list of data providers depending on the passed options."""
+        providers = []
+
+        if options.debugfs:
+            providers.append(DebugfsProvider(options.pid, options.fields,
+                                             options.dbgfs_include_past))
+        if options.tracepoints or not providers:
+            providers.append(TracepointProvider(options.pid, options.fields))
+
+        return providers
 
     def update_provider_filters(self):
         """Propagates fields filters to providers."""
-        def wanted(key):
-            if not self._fields_filter:
-                return True
-            return re.match(self._fields_filter, key) is not None
-
         # As we reset the counters when updating the fields we can
         # also clear the cache of old values.
         self.values = {}
         for provider in self.providers:
-            provider_fields = [key for key in provider.get_available_fields()
-                               if wanted(key)]
-            provider.fields = provider_fields
-
-    def update_provider_pid(self):
-        """Propagates pid filters to providers."""
-        for provider in self.providers:
-            provider.pid = self._pid_filter
+            provider.update_fields(self._fields_filter)
 
     def reset(self):
         self.values = {}
@@ -873,27 +854,52 @@ class Stats(object):
         if pid != self._pid_filter:
             self._pid_filter = pid
             self.values = {}
-            self.update_provider_pid()
+            for provider in self.providers:
+                provider.pid = self._pid_filter
 
-    def get(self):
+    def get(self, by_guest=0):
         """Returns a dict with field -> (value, delta to last value) of all
         provider data."""
         for provider in self.providers:
-            new = provider.read()
-            for key in provider.fields:
+            new = provider.read(by_guest=by_guest)
+            for key in new if by_guest else provider.fields:
                 oldval = self.values.get(key, (0, 0))[0]
                 newval = new.get(key, 0)
                 newdelta = newval - oldval
                 self.values[key] = (newval, newdelta)
         return self.values
 
-LABEL_WIDTH = 40
-NUMBER_WIDTH = 10
-DELAY_INITIAL = 0.25
-DELAY_REGULAR = 3.0
+    def toggle_display_guests(self, to_pid):
+        """Toggle between collection of stats by individual event and by
+        guest pid
+
+        Events reported by DebugfsProvider change when switching to/from
+        reading by guest values. Hence we have to remove the excess event
+        names from self.values.
+
+        """
+        if any(isinstance(ins, TracepointProvider) for ins in self.providers):
+            return 1
+        if to_pid:
+            for provider in self.providers:
+                if isinstance(provider, DebugfsProvider):
+                    for key in provider.fields:
+                        if key in self.values.keys():
+                            del self.values[key]
+        else:
+            oldvals = self.values.copy()
+            for key in oldvals:
+                if key.isdigit():
+                    del self.values[key]
+        # Update oldval (see get())
+        self.get(to_pid)
+        return 0
+
+DELAY_DEFAULT = 3.0
 MAX_GUEST_NAME_LEN = 48
 MAX_REGEX_LEN = 44
 DEFAULT_REGEX = r'^[^\(]*$'
+SORT_DEFAULT = 0
 
 
 class Tui(object):
@@ -901,7 +907,10 @@ class Tui(object):
     def __init__(self, stats):
         self.stats = stats
         self.screen = None
-        self.update_drilldown()
+        self._delay_initial = 0.25
+        self._delay_regular = DELAY_DEFAULT
+        self._sorting = SORT_DEFAULT
+        self._display_guests = 0
 
     def __enter__(self):
         """Initialises curses for later use.  Based on curses.wrapper
@@ -929,7 +938,7 @@ class Tui(object):
         return self
 
     def __exit__(self, *exception):
-        """Resets the terminal to its normal state.  Based on curses.wrappre
+        """Resets the terminal to its normal state.  Based on curses.wrapper
            implementation from the Python standard library."""
         if self.screen:
             self.screen.keypad(0)
@@ -937,6 +946,86 @@ class Tui(object):
             curses.nocbreak()
             curses.endwin()
 
+    def get_all_gnames(self):
+        """Returns a list of (pid, gname) tuples of all running guests"""
+        res = []
+        try:
+            child = subprocess.Popen(['ps', '-A', '--format', 'pid,args'],
+                                     stdout=subprocess.PIPE)
+        except:
+            raise Exception
+        for line in child.stdout:
+            line = line.lstrip().split(' ', 1)
+            # perform a sanity check before calling the more expensive
+            # function to possibly extract the guest name
+            if ' -name ' in line[1]:
+                res.append((line[0], self.get_gname_from_pid(line[0])))
+        child.stdout.close()
+
+        return res
+
+    def print_all_gnames(self, row):
+        """Print a list of all running guests along with their pids."""
+        self.screen.addstr(row, 2, '%8s  %-60s' %
+                           ('Pid', 'Guest Name (fuzzy list, might be '
+                            'inaccurate!)'),
+                           curses.A_UNDERLINE)
+        row += 1
+        try:
+            for line in self.get_all_gnames():
+                self.screen.addstr(row, 2, '%8s  %-60s' % (line[0], line[1]))
+                row += 1
+                if row >= self.screen.getmaxyx()[0]:
+                    break
+        except Exception:
+            self.screen.addstr(row + 1, 2, 'Not available')
+
+    def get_pid_from_gname(self, gname):
+        """Fuzzy function to convert guest name to QEMU process pid.
+
+        Returns a list of potential pids, can be empty if no match found.
+        Throws an exception on processing errors.
+
+        """
+        pids = []
+        for line in self.get_all_gnames():
+            if gname == line[1]:
+                pids.append(int(line[0]))
+
+        return pids
+
+    @staticmethod
+    def get_gname_from_pid(pid):
+        """Returns the guest name for a QEMU process pid.
+
+        Extracts the guest name from the QEMU comma line by processing the
+        '-name' option. Will also handle names specified out of sequence.
+
+        """
+        name = ''
+        try:
+            line = open('/proc/{}/cmdline'
+                        .format(pid), 'rb').read().split('\0')
+            parms = line[line.index('-name') + 1].split(',')
+            while '' in parms:
+                # commas are escaped (i.e. ',,'), hence e.g. 'foo,bar' results
+                # in # ['foo', '', 'bar'], which we revert here
+                idx = parms.index('')
+                parms[idx - 1] += ',' + parms[idx + 1]
+                del parms[idx:idx+2]
+            # the '-name' switch allows for two ways to specify the guest name,
+            # where the plain name overrides the name specified via 'guest='
+            for arg in parms:
+                if '=' not in arg:
+                    name = arg
+                    break
+                if arg[:6] == 'guest=':
+                    name = arg[6:]
+        except (ValueError, IOError, IndexError):
+            pass
+
+        return name
+
     def update_drilldown(self):
         """Sets or removes a filter that only allows fields without braces."""
         if not self.stats.fields_filter:
@@ -954,7 +1043,7 @@ class Tui(object):
         if pid is None:
             pid = self.stats.pid_filter
         self.screen.erase()
-        gname = get_gname_from_pid(pid)
+        gname = self.get_gname_from_pid(pid)
         if gname:
             gname = ('({})'.format(gname[:MAX_GUEST_NAME_LEN] + '...'
                                    if len(gname) > MAX_GUEST_NAME_LEN
@@ -970,13 +1059,13 @@ class Tui(object):
             if len(regex) > MAX_REGEX_LEN:
                 regex = regex[:MAX_REGEX_LEN] + '...'
             self.screen.addstr(1, 17, 'regex filter: {0}'.format(regex))
-        self.screen.addstr(2, 1, 'Event')
-        self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH -
-                           len('Total'), 'Total')
-        self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 7 -
-                           len('%Total'), '%Total')
-        self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 7 + 8 -
-                           len('Current'), 'Current')
+        if self._display_guests:
+            col_name = 'Guest Name'
+        else:
+            col_name = 'Event'
+        self.screen.addstr(2, 1, '%-40s %10s%7s %8s' %
+                           (col_name, 'Total', '%Total', 'CurAvg/s'),
+                           curses.A_STANDOUT)
         self.screen.addstr(4, 1, 'Collecting data...')
         self.screen.refresh()
 
@@ -984,16 +1073,25 @@ class Tui(object):
         row = 3
         self.screen.move(row, 0)
         self.screen.clrtobot()
-        stats = self.stats.get()
+        stats = self.stats.get(self._display_guests)
 
-        def sortkey(x):
+        def sortCurAvg(x):
+            # sort by current events if available
             if stats[x][1]:
                 return (-stats[x][1], -stats[x][0])
             else:
                 return (0, -stats[x][0])
+
+        def sortTotal(x):
+            # sort by totals
+            return (0, -stats[x][0])
         total = 0.
         for val in stats.values():
             total += val[0]
+        if self._sorting == SORT_DEFAULT:
+            sortkey = sortCurAvg
+        else:
+            sortkey = sortTotal
         for key in sorted(stats.keys(), key=sortkey):
 
             if row >= self.screen.getmaxyx()[0]:
@@ -1001,18 +1099,61 @@ class Tui(object):
             values = stats[key]
             if not values[0] and not values[1]:
                 break
-            col = 1
-            self.screen.addstr(row, col, key)
-            col += LABEL_WIDTH
-            self.screen.addstr(row, col, '%10d' % (values[0],))
-            col += NUMBER_WIDTH
-            self.screen.addstr(row, col, '%7.1f' % (values[0] * 100 / total,))
-            col += 7
-            if values[1] is not None:
-                self.screen.addstr(row, col, '%8d' % (values[1] / sleeptime,))
+            if values[0] is not None:
+                cur = int(round(values[1] / sleeptime)) if values[1] else ''
+                if self._display_guests:
+                    key = self.get_gname_from_pid(key)
+                self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' %
+                                   (key, values[0], values[0] * 100 / total,
+                                    cur))
             row += 1
+        if row == 3:
+            self.screen.addstr(4, 1, 'No matching events reported yet')
         self.screen.refresh()
 
+    def show_msg(self, text):
+        """Display message centered text and exit on key press"""
+        hint = 'Press any key to continue'
+        curses.cbreak()
+        self.screen.erase()
+        (x, term_width) = self.screen.getmaxyx()
+        row = 2
+        for line in text:
+            start = (term_width - len(line)) / 2
+            self.screen.addstr(row, start, line)
+            row += 1
+        self.screen.addstr(row + 1, (term_width - len(hint)) / 2, hint,
+                           curses.A_STANDOUT)
+        self.screen.getkey()
+
+    def show_help_interactive(self):
+        """Display help with list of interactive commands"""
+        msg = ('   b     toggle events by guests (debugfs only, honors'
+               ' filters)',
+               '   c     clear filter',
+               '   f     filter by regular expression',
+               '   g     filter by guest name',
+               '   h     display interactive commands reference',
+               '   o     toggle sorting order (Total vs CurAvg/s)',
+               '   p     filter by PID',
+               '   q     quit',
+               '   r     reset stats',
+               '   s     set update interval',
+               '   x     toggle reporting of stats for individual child trace'
+               ' events',
+               'Any other key refreshes statistics immediately')
+        curses.cbreak()
+        self.screen.erase()
+        self.screen.addstr(0, 0, "Interactive commands reference",
+                           curses.A_BOLD)
+        self.screen.addstr(2, 0, "Press any key to exit", curses.A_STANDOUT)
+        row = 4
+        for line in msg:
+            self.screen.addstr(row, 0, line)
+            row += 1
+        self.screen.getkey()
+        self.refresh_header()
+
     def show_filter_selection(self):
         """Draws filter selection mask.
 
@@ -1059,6 +1200,7 @@ class Tui(object):
                                'This might limit the shown data to the trace '
                                'statistics.')
             self.screen.addstr(5, 0, msg)
+            self.print_all_gnames(7)
 
             curses.echo()
             self.screen.addstr(3, 0, "Pid [0 or pid]: ")
@@ -1077,10 +1219,40 @@ class Tui(object):
                 self.refresh_header(pid)
                 self.update_pid(pid)
                 break
-
             except ValueError:
                 msg = '"' + str(pid) + '": Not a valid pid'
-                continue
+
+    def show_set_update_interval(self):
+        """Draws update interval selection mask."""
+        msg = ''
+        while True:
+            self.screen.erase()
+            self.screen.addstr(0, 0, 'Set update interval (defaults to %fs).' %
+                               DELAY_DEFAULT, curses.A_BOLD)
+            self.screen.addstr(4, 0, msg)
+            self.screen.addstr(2, 0, 'Change delay from %.1fs to ' %
+                               self._delay_regular)
+            curses.echo()
+            val = self.screen.getstr()
+            curses.noecho()
+
+            try:
+                if len(val) > 0:
+                    delay = float(val)
+                    if delay < 0.1:
+                        msg = '"' + str(val) + '": Value must be >=0.1'
+                        continue
+                    if delay > 25.5:
+                        msg = '"' + str(val) + '": Value must be <=25.5'
+                        continue
+                else:
+                    delay = DELAY_DEFAULT
+                self._delay_regular = delay
+                break
+
+            except ValueError:
+                msg = '"' + str(val) + '": Invalid value'
+        self.refresh_header()
 
     def show_vm_selection_by_guest_name(self):
         """Draws guest selection mask.
@@ -1098,6 +1270,7 @@ class Tui(object):
                                'This might limit the shown data to the trace '
                                'statistics.')
             self.screen.addstr(5, 0, msg)
+            self.print_all_gnames(7)
             curses.echo()
             self.screen.addstr(3, 0, "Guest [ENTER or guest]: ")
             gname = self.screen.getstr()
@@ -1110,7 +1283,7 @@ class Tui(object):
             else:
                 pids = []
                 try:
-                    pids = get_pid_from_gname(gname)
+                    pids = self.get_pid_from_gname(gname)
                 except:
                     msg = '"' + gname + '": Internal error while searching, ' \
                           'use pid filter instead'
@@ -1128,38 +1301,60 @@ class Tui(object):
 
     def show_stats(self):
         """Refreshes the screen and processes user input."""
-        sleeptime = DELAY_INITIAL
+        sleeptime = self._delay_initial
         self.refresh_header()
+        start = 0.0  # result based on init value never appears on screen
         while True:
-            self.refresh_body(sleeptime)
+            self.refresh_body(time.time() - start)
             curses.halfdelay(int(sleeptime * 10))
-            sleeptime = DELAY_REGULAR
+            start = time.time()
+            sleeptime = self._delay_regular
             try:
                 char = self.screen.getkey()
-                if char == 'x':
+                if char == 'b':
+                    self._display_guests = not self._display_guests
+                    if self.stats.toggle_display_guests(self._display_guests):
+                        self.show_msg(['Command not available with tracepoints'
+                                       ' enabled', 'Restart with debugfs only '
+                                       '(see option \'-d\') and try again!'])
+                        self._display_guests = not self._display_guests
                     self.refresh_header()
-                    self.update_drilldown()
-                    sleeptime = DELAY_INITIAL
-                if char == 'q':
-                    break
                 if char == 'c':
                     self.stats.fields_filter = DEFAULT_REGEX
                     self.refresh_header(0)
                     self.update_pid(0)
-                    sleeptime = DELAY_INITIAL
                 if char == 'f':
+                    curses.curs_set(1)
                     self.show_filter_selection()
-                    sleeptime = DELAY_INITIAL
+                    curses.curs_set(0)
+                    sleeptime = self._delay_initial
                 if char == 'g':
+                    curses.curs_set(1)
                     self.show_vm_selection_by_guest_name()
-                    sleeptime = DELAY_INITIAL
+                    curses.curs_set(0)
+                    sleeptime = self._delay_initial
+                if char == 'h':
+                    self.show_help_interactive()
+                if char == 'o':
+                    self._sorting = not self._sorting
                 if char == 'p':
+                    curses.curs_set(1)
                     self.show_vm_selection_by_pid()
-                    sleeptime = DELAY_INITIAL
+                    curses.curs_set(0)
+                    sleeptime = self._delay_initial
+                if char == 'q':
+                    break
                 if char == 'r':
-                    self.refresh_header()
                     self.stats.reset()
-                    sleeptime = DELAY_INITIAL
+                if char == 's':
+                    curses.curs_set(1)
+                    self.show_set_update_interval()
+                    curses.curs_set(0)
+                    sleeptime = self._delay_initial
+                if char == 'x':
+                    self.update_drilldown()
+                    # prevents display of current values on next refresh
+                    self.stats.get()
             except KeyboardInterrupt:
                 break
             except curses.error:
@@ -1227,13 +1422,17 @@ Requirements:
   the large number of files that are possibly opened.
 
 Interactive Commands:
+   b     toggle events by guests (debugfs only, honors filters)
    c     clear filter
    f     filter by regular expression
    g     filter by guest name
+   h     display interactive commands reference
+   o     toggle sorting order (Total vs CurAvg/s)
    p     filter by PID
    q     quit
-   x     toggle reporting of stats for individual child trace events
    r     reset stats
+   s     set update interval
+   x     toggle reporting of stats for individual child trace events
 Press any other key to refresh statistics immediately.
 """
 
@@ -1246,7 +1445,7 @@ Press any other key to refresh statistics immediately.
 
     def cb_guest_to_pid(option, opt, val, parser):
         try:
-            pids = get_pid_from_gname(val)
+            pids = Tui.get_pid_from_gname(val)
         except:
             raise optparse.OptionValueError('Error while searching for guest '
                                             '"{}", use "-p" to specify a pid '
@@ -1268,6 +1467,13 @@ Press any other key to refresh statistics immediately.
                          dest='once',
                          help='run in batch mode for one second',
                          )
+    optparser.add_option('-i', '--debugfs-include-past',
+                         action='store_true',
+                         default=False,
+                         dest='dbgfs_include_past',
+                         help='include all available data on past events for '
+                              'debugfs',
+                         )
     optparser.add_option('-l', '--log',
                          action='store_true',
                          default=False,
@@ -1288,7 +1494,7 @@ Press any other key to refresh statistics immediately.
                          )
     optparser.add_option('-f', '--fields',
                          action='store',
-                         default=None,
+                         default=DEFAULT_REGEX,
                          dest='fields',
                          help='fields to display (regex)',
                          )
@@ -1311,20 +1517,6 @@ Press any other key to refresh statistics immediately.
     return options
 
 
-def get_providers(options):
-    """Returns a list of data providers depending on the passed options."""
-    providers = []
-
-    if options.tracepoints:
-        providers.append(TracepointProvider())
-    if options.debugfs:
-        providers.append(DebugfsProvider())
-    if len(providers) == 0:
-        providers.append(TracepointProvider())
-
-    return providers
-
-
 def check_access(options):
     """Exits if the current user can't access all needed directories."""
     if not os.path.exists('/sys/kernel/debug'):
@@ -1365,8 +1557,7 @@ def main():
         sys.stderr.write('Did you use a (unsupported) tid instead of a pid?\n')
         sys.exit('Specified pid does not exist.')
 
-    providers = get_providers(options)
-    stats = Stats(providers, options.pid, fields=options.fields)
+    stats = Stats(options)
 
     if options.log:
         log(stats)
diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt
index 109431bdc63c..e5cf836be8a1 100644
--- a/tools/kvm/kvm_stat/kvm_stat.txt
+++ b/tools/kvm/kvm_stat/kvm_stat.txt
@@ -29,18 +29,26 @@ meaning of events.
 INTERACTIVE COMMANDS
 --------------------
 [horizontal]
+*b*::	toggle events by guests (debugfs only, honors filters)
+
 *c*::	clear filter
 
 *f*::	filter by regular expression
 
 *g*::	filter by guest name
 
+*h*::	display interactive commands reference
+
+*o*::   toggle sorting order (Total vs CurAvg/s)
+
 *p*::	filter by PID
 
 *q*::	quit
 
 *r*::	reset stats
 
+*s*::   set update interval
+
 *x*::	toggle reporting of stats for child trace events
 
 Press any other key to refresh statistics immediately.
@@ -64,6 +72,10 @@ OPTIONS
 --debugfs::
 	retrieve statistics from debugfs
 
+-i::
+--debugfs-include-past::
+	include all available data on past events for debugfs
+
 -p<pid>::
 --pid=<pid>::
 	limit statistics to one virtual machine (pid)