diff options
Diffstat (limited to 'tools')
39 files changed, 664 insertions, 286 deletions
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 0dfe4d3f74e2..f41079da38c5 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -213,6 +213,7 @@ #define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 0fb5ef939732..7b26d4b0b052 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -761,6 +761,7 @@ struct kvm_ppc_resize_hpt { #define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07 #define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08 #define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2) +#define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list) /* * Extension capability list. @@ -934,6 +935,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_AIS_MIGRATION 150 #define KVM_CAP_PPC_GET_CPU_CHAR 151 #define KVM_CAP_S390_BPB 152 +#define KVM_CAP_GET_MSR_FEATURES 153 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index a5684d0968b4..5898c22ba310 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -33,7 +33,7 @@ import resource import struct import re import subprocess -from collections import defaultdict +from collections import defaultdict, namedtuple VMX_EXIT_REASONS = { 'EXCEPTION_NMI': 0, @@ -228,6 +228,7 @@ IOCTL_NUMBERS = { } ENCODING = locale.getpreferredencoding(False) +TRACE_FILTER = re.compile(r'^[^\(]*$') class Arch(object): @@ -260,6 +261,11 @@ class Arch(object): return ArchX86(SVM_EXIT_REASONS) return + def tracepoint_is_child(self, field): + if (TRACE_FILTER.match(field)): + return None + return field.split('(', 1)[0] + class ArchX86(Arch): def __init__(self, exit_reasons): @@ -267,6 +273,10 @@ class ArchX86(Arch): self.ioctl_numbers = IOCTL_NUMBERS self.exit_reasons = exit_reasons + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + return None + class ArchPPC(Arch): def __init__(self): @@ -282,6 +292,10 @@ class ArchPPC(Arch): self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16 self.exit_reasons = {} + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + return None + class ArchA64(Arch): def __init__(self): @@ -289,6 +303,10 @@ class ArchA64(Arch): self.ioctl_numbers = IOCTL_NUMBERS self.exit_reasons = AARCH64_EXIT_REASONS + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + return None + class ArchS390(Arch): def __init__(self): @@ -296,6 +314,12 @@ class ArchS390(Arch): self.ioctl_numbers = IOCTL_NUMBERS self.exit_reasons = None + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + if field.startswith('instruction_'): + return 'exit_instruction' + + ARCH = Arch.get_arch() @@ -331,9 +355,6 @@ class perf_event_attr(ctypes.Structure): PERF_TYPE_TRACEPOINT = 2 PERF_FORMAT_GROUP = 1 << 3 -PATH_DEBUGFS_TRACING = '/sys/kernel/debug/tracing' -PATH_DEBUGFS_KVM = '/sys/kernel/debug/kvm' - class Group(object): """Represents a perf event group.""" @@ -376,8 +397,8 @@ class Event(object): self.syscall = self.libc.syscall self.name = name self.fd = None - self.setup_event(group, trace_cpu, trace_pid, trace_point, - trace_filter, trace_set) + self._setup_event(group, trace_cpu, trace_pid, trace_point, + trace_filter, trace_set) def __del__(self): """Closes the event's file descriptor. @@ -390,7 +411,7 @@ class Event(object): if self.fd: os.close(self.fd) - def perf_event_open(self, attr, pid, cpu, group_fd, flags): + 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 @@ -409,7 +430,7 @@ class Event(object): 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): + def _setup_event_attribute(self, trace_set, trace_point): """Returns an initialized ctype perf_event_attr struct.""" id_path = os.path.join(PATH_DEBUGFS_TRACING, 'events', trace_set, @@ -419,8 +440,8 @@ class Event(object): event_attr.config = int(open(id_path).read()) return event_attr - def setup_event(self, group, trace_cpu, trace_pid, trace_point, - trace_filter, trace_set): + def _setup_event(self, group, trace_cpu, trace_pid, trace_point, + trace_filter, trace_set): """Sets up the perf event in Linux. Issues the syscall to register the event in the kernel and @@ -428,7 +449,7 @@ class Event(object): """ - event_attr = self.setup_event_attribute(trace_set, trace_point) + event_attr = self._setup_event_attribute(trace_set, trace_point) # First event will be group leader. group_leader = -1 @@ -437,8 +458,8 @@ class Event(object): if group.events: group_leader = group.events[0].fd - fd = self.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), @@ -475,6 +496,10 @@ class Event(object): class Provider(object): """Encapsulates functionalities used by all providers.""" + def __init__(self, pid): + self.child_events = False + self.pid = pid + @staticmethod def is_field_wanted(fields_filter, field): """Indicate whether field is valid according to fields_filter.""" @@ -500,12 +525,12 @@ class TracepointProvider(Provider): """ def __init__(self, pid, fields_filter): self.group_leaders = [] - self.filters = self.get_filters() + self.filters = self._get_filters() self.update_fields(fields_filter) - self.pid = pid + super(TracepointProvider, self).__init__(pid) @staticmethod - def get_filters(): + def _get_filters(): """Returns a dict of trace events, their filter ids and the values that can be filtered. @@ -521,8 +546,8 @@ class TracepointProvider(Provider): 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 + def _get_available_fields(self): + """Returns a list of available events of format 'event name(filter name)'. All available events have directories under @@ -549,11 +574,12 @@ class TracepointProvider(Provider): 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)] + self.fields = [field for field in self._get_available_fields() + if self.is_field_wanted(fields_filter, field) or + ARCH.tracepoint_is_child(field)] @staticmethod - def get_online_cpus(): + 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 @@ -575,17 +601,17 @@ class TracepointProvider(Provider): cpu_string = cpu_list.readline() return parse_int_list(cpu_string) - def setup_traces(self): + def _setup_traces(self): """Creates all event and group objects needed to be able to retrieve data.""" - fields = self.get_available_fields() + fields = self._get_available_fields() if self._pid > 0: # 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 = self.walkdir(path)[1] else: - groupids = self.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. @@ -663,7 +689,7 @@ class TracepointProvider(Provider): # The garbage collector will get rid of all Event/Group # objects and open files after removing the references. self.group_leaders = [] - self.setup_traces() + self._setup_traces() self.fields = self._fields def read(self, by_guest=0): @@ -671,8 +697,12 @@ class TracepointProvider(Provider): ret = defaultdict(int) for group in self.group_leaders: for name, val in group.read().items(): - if name in self._fields: - ret[name] += val + if name not in self._fields: + continue + parent = ARCH.tracepoint_is_child(name) + if parent: + name += ' ' + parent + ret[name] += val return ret def reset(self): @@ -690,11 +720,11 @@ class DebugfsProvider(Provider): self._baseline = {} self.do_read = True self.paths = [] - self.pid = pid + super(DebugfsProvider, self).__init__(pid) if include_past: - self.restore() + self._restore() - def get_available_fields(self): + def _get_available_fields(self): """"Returns a list of available fields. The fields are all available KVM debugfs files @@ -704,8 +734,9 @@ class DebugfsProvider(Provider): 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)] + self._fields = [field for field in self._get_available_fields() + if self.is_field_wanted(fields_filter, field) or + ARCH.debugfs_is_child(field)] @property def fields(self): @@ -758,7 +789,7 @@ class DebugfsProvider(Provider): paths.append(dir) for path in paths: for field in self._fields: - value = self.read_field(field, path) + value = self._read_field(field, path) key = path + field if reset == 1: self._baseline[key] = value @@ -766,20 +797,21 @@ class DebugfsProvider(Provider): self._baseline[key] = 0 if self._baseline.get(key, -1) == -1: self._baseline[key] = value - 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 + parent = ARCH.debugfs_is_child(field) + if parent: + field = field + ' ' + parent + else: + if by_guest: + field = key.split('-')[0] # set 'field' to 'pid' + increment = value - self._baseline.get(key, 0) + if field in results: + results[field] += increment else: results[field] = increment return results - def read_field(self, field, path): + def _read_field(self, field, path): """Returns the value of a single field from a specific VM.""" try: return int(open(os.path.join(PATH_DEBUGFS_KVM, @@ -794,12 +826,15 @@ class DebugfsProvider(Provider): self._baseline = {} self.read(1) - def restore(self): + def _restore(self): """Reset field counters""" self._baseline = {} self.read(2) +EventStat = namedtuple('EventStat', ['value', 'delta']) + + class Stats(object): """Manages the data providers and the data they provide. @@ -808,13 +843,13 @@ class Stats(object): """ def __init__(self, options): - self.providers = self.get_providers(options) + self.providers = self._get_providers(options) self._pid_filter = options.pid self._fields_filter = options.fields self.values = {} + self._child_events = False - @staticmethod - def get_providers(options): + def _get_providers(self, options): """Returns a list of data providers depending on the passed options.""" providers = [] @@ -826,7 +861,7 @@ class Stats(object): return providers - def update_provider_filters(self): + def _update_provider_filters(self): """Propagates fields filters to providers.""" # As we reset the counters when updating the fields we can # also clear the cache of old values. @@ -847,7 +882,7 @@ class Stats(object): def fields_filter(self, fields_filter): if fields_filter != self._fields_filter: self._fields_filter = fields_filter - self.update_provider_filters() + self._update_provider_filters() @property def pid_filter(self): @@ -861,16 +896,33 @@ class Stats(object): for provider in self.providers: provider.pid = self._pid_filter + @property + def child_events(self): + return self._child_events + + @child_events.setter + def child_events(self, val): + self._child_events = val + for provider in self.providers: + provider.child_events = val + def get(self, by_guest=0): """Returns a dict with field -> (value, delta to last value) of all - provider data.""" + provider data. + Key formats: + * plain: 'key' is event name + * child-parent: 'key' is in format '<child> <parent>' + * pid: 'key' is the pid of the guest, and the record contains the + aggregated event data + These formats are generated by the providers, and handled in class TUI. + """ for provider in self.providers: 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] + for key in new: + oldval = self.values.get(key, EventStat(0, 0)).value newval = new.get(key, 0) newdelta = newval - oldval - self.values[key] = (newval, newdelta) + self.values[key] = EventStat(newval, newdelta) return self.values def toggle_display_guests(self, to_pid): @@ -899,10 +951,10 @@ class Stats(object): 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 @@ -969,7 +1021,7 @@ class Tui(object): return res - def print_all_gnames(self, row): + 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 ' @@ -1032,19 +1084,13 @@ class Tui(object): return name - def update_drilldown(self): - """Sets or removes a filter that only allows fields without braces.""" - if not self.stats.fields_filter: - self.stats.fields_filter = DEFAULT_REGEX - - elif self.stats.fields_filter == DEFAULT_REGEX: - self.stats.fields_filter = None - - def update_pid(self, pid): + def _update_pid(self, pid): """Propagates pid selection to stats object.""" + self.screen.addstr(4, 1, 'Updating pid filter...') + self.screen.refresh() self.stats.pid_filter = pid - def refresh_header(self, pid=None): + def _refresh_header(self, pid=None): """Refreshes the header.""" if pid is None: pid = self.stats.pid_filter @@ -1059,8 +1105,7 @@ class Tui(object): .format(pid, gname), curses.A_BOLD) else: self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD) - if self.stats.fields_filter and self.stats.fields_filter \ - != DEFAULT_REGEX: + if self.stats.fields_filter: regex = self.stats.fields_filter if len(regex) > MAX_REGEX_LEN: regex = regex[:MAX_REGEX_LEN] + '...' @@ -1075,56 +1120,99 @@ class Tui(object): self.screen.addstr(4, 1, 'Collecting data...') self.screen.refresh() - def refresh_body(self, sleeptime): + def _refresh_body(self, sleeptime): + def is_child_field(field): + return field.find('(') != -1 + + def insert_child(sorted_items, child, values, parent): + num = len(sorted_items) + for i in range(0, num): + # only add child if parent is present + if parent.startswith(sorted_items[i][0]): + sorted_items.insert(i + 1, (' ' + child, values)) + + def get_sorted_events(self, stats): + """ separate parent and child events """ + if self._sorting == SORT_DEFAULT: + def sortkey((_k, v)): + # sort by (delta value, overall value) + return (v.delta, v.value) + else: + def sortkey((_k, v)): + # sort by overall value + return v.value + + childs = [] + sorted_items = [] + # we can't rule out child events to appear prior to parents even + # when sorted - separate out all children first, and add in later + for key, values in sorted(stats.items(), key=sortkey, + reverse=True): + if values == (0, 0): + continue + if key.find(' ') != -1: + if not self.stats.child_events: + continue + childs.insert(0, (key, values)) + else: + sorted_items.append((key, values)) + if self.stats.child_events: + for key, values in childs: + (child, parent) = key.split(' ') + insert_child(sorted_items, child, values, parent) + + return sorted_items + row = 3 self.screen.move(row, 0) self.screen.clrtobot() stats = self.stats.get(self._display_guests) - - def sortCurAvg(x): - # sort by current events if available - if stats[x][1]: - return (-stats[x][1], -stats[x][0]) + total = 0. + ctotal = 0. + for key, values in stats.items(): + if self._display_guests: + if self.get_gname_from_pid(key): + total += values.value + continue + if not key.find(' ') != -1: + total += values.value else: - return (0, -stats[x][0]) + ctotal += values.value + if total == 0.: + # we don't have any fields, or all non-child events are filtered + total = ctotal - def sortTotal(x): - # sort by totals - return (0, -stats[x][0]) - total = 0. - for key in stats.keys(): - if key.find('(') is -1: - total += stats[key][0] - if self._sorting == SORT_DEFAULT: - sortkey = sortCurAvg - else: - sortkey = sortTotal + # print events tavg = 0 - for key in sorted(stats.keys(), key=sortkey): - if row >= self.screen.getmaxyx()[0] - 1: - break - values = stats[key] - if not values[0] and not values[1]: + tcur = 0 + for key, values in get_sorted_events(self, stats): + if row >= self.screen.getmaxyx()[0] - 1 or values == (0, 0): break - 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)) - if cur is not '' and key.find('(') is -1: - tavg += cur + if self._display_guests: + key = self.get_gname_from_pid(key) + if not key: + continue + cur = int(round(values.delta / sleeptime)) if values.delta else '' + if key[0] != ' ': + if values.delta: + tcur += values.delta + ptotal = values.value + ltotal = total + else: + ltotal = ptotal + self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % (key, + values.value, + values.value * 100 / float(ltotal), cur)) row += 1 if row == 3: self.screen.addstr(4, 1, 'No matching events reported yet') - else: + if row > 4: + tavg = int(round(tcur / sleeptime)) if tcur > 0 else '' self.screen.addstr(row, 1, '%-40s %10d %8s' % - ('Total', total, tavg if tavg else ''), - curses.A_BOLD) + ('Total', total, tavg), curses.A_BOLD) self.screen.refresh() - def show_msg(self, text): + def _show_msg(self, text): """Display message centered text and exit on key press""" hint = 'Press any key to continue' curses.cbreak() @@ -1139,16 +1227,16 @@ class Tui(object): curses.A_STANDOUT) self.screen.getkey() - def show_help_interactive(self): + 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', + ' g filter by guest name/PID', ' h display interactive commands reference', ' o toggle sorting order (Total vs CurAvg/s)', - ' p filter by PID', + ' p filter by guest name/PID', ' q quit', ' r reset stats', ' s set update interval', @@ -1165,14 +1253,15 @@ class Tui(object): self.screen.addstr(row, 0, line) row += 1 self.screen.getkey() - self.refresh_header() + self._refresh_header() - def show_filter_selection(self): + def _show_filter_selection(self): """Draws filter selection mask. Asks for a valid regex and sets the fields filter accordingly. """ + msg = '' while True: self.screen.erase() self.screen.addstr(0, 0, @@ -1181,61 +1270,25 @@ class Tui(object): self.screen.addstr(2, 0, "Current regex: {0}" .format(self.stats.fields_filter)) + self.screen.addstr(5, 0, msg) self.screen.addstr(3, 0, "New regex: ") curses.echo() regex = self.screen.getstr().decode(ENCODING) curses.noecho() if len(regex) == 0: - self.stats.fields_filter = DEFAULT_REGEX - self.refresh_header() + self.stats.fields_filter = '' + self._refresh_header() return try: re.compile(regex) self.stats.fields_filter = regex - self.refresh_header() + self._refresh_header() return except re.error: + msg = '"' + regex + '": Not a valid regular expression' continue - def show_vm_selection_by_pid(self): - """Draws PID selection mask. - - Asks for a pid until a valid pid or 0 has been entered. - - """ - msg = '' - while True: - self.screen.erase() - self.screen.addstr(0, 0, - 'Show statistics for specific pid.', - curses.A_BOLD) - self.screen.addstr(1, 0, - '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]: ") - pid = self.screen.getstr().decode(ENCODING) - curses.noecho() - - try: - if len(pid) > 0: - pid = int(pid) - if pid != 0 and not os.path.isdir(os.path.join('/proc/', - str(pid))): - msg = '"' + str(pid) + '": Not a running process' - continue - else: - pid = 0 - self.refresh_header(pid) - self.update_pid(pid) - break - except ValueError: - msg = '"' + str(pid) + '": Not a valid pid' - - def show_set_update_interval(self): + def _show_set_update_interval(self): """Draws update interval selection mask.""" msg = '' while True: @@ -1265,60 +1318,67 @@ class Tui(object): except ValueError: msg = '"' + str(val) + '": Invalid value' - self.refresh_header() + self._refresh_header() - def show_vm_selection_by_guest_name(self): + def _show_vm_selection_by_guest(self): """Draws guest selection mask. - Asks for a guest name until a valid guest name or '' is entered. + Asks for a guest name or pid until a valid guest name or '' is entered. """ msg = '' while True: self.screen.erase() self.screen.addstr(0, 0, - 'Show statistics for specific guest.', + 'Show statistics for specific guest or pid.', curses.A_BOLD) self.screen.addstr(1, 0, 'This might limit the shown data to the trace ' 'statistics.') self.screen.addstr(5, 0, msg) - self.print_all_gnames(7) + self._print_all_gnames(7) curses.echo() - self.screen.addstr(3, 0, "Guest [ENTER or guest]: ") - gname = self.screen.getstr().decode(ENCODING) + curses.curs_set(1) + self.screen.addstr(3, 0, "Guest or pid [ENTER exits]: ") + guest = self.screen.getstr().decode(ENCODING) curses.noecho() - if not gname: - self.refresh_header(0) - self.update_pid(0) + pid = 0 + if not guest or guest == '0': break - else: - pids = [] - try: - pids = self.get_pid_from_gname(gname) - except: - msg = '"' + gname + '": Internal error while searching, ' \ - 'use pid filter instead' - continue - if len(pids) == 0: - msg = '"' + gname + '": Not an active guest' + if guest.isdigit(): + if not os.path.isdir(os.path.join('/proc/', guest)): + msg = '"' + guest + '": Not a running process' continue - if len(pids) > 1: - msg = '"' + gname + '": Multiple matches found, use pid ' \ - 'filter instead' - continue - self.refresh_header(pids[0]) - self.update_pid(pids[0]) + pid = int(guest) break + pids = [] + try: + pids = self.get_pid_from_gname(guest) + except: + msg = '"' + guest + '": Internal error while searching, ' \ + 'use pid filter instead' + continue + if len(pids) == 0: + msg = '"' + guest + '": Not an active guest' + continue + if len(pids) > 1: + msg = '"' + guest + '": Multiple matches found, use pid ' \ + 'filter instead' + continue + pid = pids[0] + break + curses.curs_set(0) + self._refresh_header(pid) + self._update_pid(pid) def show_stats(self): """Refreshes the screen and processes user input.""" sleeptime = self._delay_initial - self.refresh_header() + self._refresh_header() start = 0.0 # result based on init value never appears on screen while True: - self.refresh_body(time.time() - start) + self._refresh_body(time.time() - start) curses.halfdelay(int(sleeptime * 10)) start = time.time() sleeptime = self._delay_regular @@ -1327,47 +1387,39 @@ class Tui(object): 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._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._refresh_header() if char == 'c': - self.stats.fields_filter = DEFAULT_REGEX - self.refresh_header(0) - self.update_pid(0) + self.stats.fields_filter = '' + self._refresh_header(0) + self._update_pid(0) if char == 'f': curses.curs_set(1) - self.show_filter_selection() + self._show_filter_selection() curses.curs_set(0) sleeptime = self._delay_initial - if char == 'g': - curses.curs_set(1) - self.show_vm_selection_by_guest_name() - curses.curs_set(0) + if char == 'g' or char == 'p': + self._show_vm_selection_by_guest() sleeptime = self._delay_initial if char == 'h': - self.show_help_interactive() + 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() - curses.curs_set(0) - sleeptime = self._delay_initial if char == 'q': break if char == 'r': self.stats.reset() if char == 's': curses.curs_set(1) - self.show_set_update_interval() + 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(self._display_guests) + self.stats.child_events = not self.stats.child_events except KeyboardInterrupt: break except curses.error: @@ -1380,9 +1432,9 @@ def batch(stats): s = stats.get() time.sleep(1) s = stats.get() - for key in sorted(s.keys()): - values = s[key] - print('%-42s%10d%10d' % (key, values[0], values[1])) + for key, values in sorted(s.items()): + print('%-42s%10d%10d' % (key.split(' ')[0], values.value, + values.delta)) except KeyboardInterrupt: pass @@ -1392,14 +1444,14 @@ def log(stats): keys = sorted(stats.get().keys()) def banner(): - for k in keys: - print(k, end=' ') + for key in keys: + print(key.split(' ')[0], end=' ') print() def statline(): s = stats.get() - for k in keys: - print(' %9d' % s[k][1], end=' ') + for key in keys: + print(' %9d' % s[key].delta, end=' ') print() line = 0 banner_repeat = 20 @@ -1504,7 +1556,7 @@ Press any other key to refresh statistics immediately. ) optparser.add_option('-f', '--fields', action='store', - default=DEFAULT_REGEX, + default='', dest='fields', help='''fields to display (regex) "-f help" for a list of available events''', @@ -1539,17 +1591,6 @@ Press any other key to refresh statistics immediately. def check_access(options): """Exits if the current user can't access all needed directories.""" - if not os.path.exists('/sys/kernel/debug'): - sys.stderr.write('Please enable CONFIG_DEBUG_FS in your kernel.') - sys.exit(1) - - if not os.path.exists(PATH_DEBUGFS_KVM): - sys.stderr.write("Please make sure, that debugfs is mounted and " - "readable by the current user:\n" - "('mount -t debugfs debugfs /sys/kernel/debug')\n" - "Also ensure, that the kvm modules are loaded.\n") - sys.exit(1) - if not os.path.exists(PATH_DEBUGFS_TRACING) and (options.tracepoints or not options.debugfs): sys.stderr.write("Please enable CONFIG_TRACING in your kernel " @@ -1567,7 +1608,33 @@ def check_access(options): return options +def assign_globals(): + global PATH_DEBUGFS_KVM + global PATH_DEBUGFS_TRACING + + debugfs = '' + for line in file('/proc/mounts'): + if line.split(' ')[0] == 'debugfs': + debugfs = line.split(' ')[1] + break + if debugfs == '': + sys.stderr.write("Please make sure that CONFIG_DEBUG_FS is enabled in " + "your kernel, mounted and\nreadable by the current " + "user:\n" + "('mount -t debugfs debugfs /sys/kernel/debug')\n") + sys.exit(1) + + PATH_DEBUGFS_KVM = os.path.join(debugfs, 'kvm') + PATH_DEBUGFS_TRACING = os.path.join(debugfs, 'tracing') + + if not os.path.exists(PATH_DEBUGFS_KVM): + sys.stderr.write("Please make sure that CONFIG_KVM is enabled in " + "your kernel and that the modules are loaded.\n") + sys.exit(1) + + def main(): + assign_globals() options = get_options() options = check_access(options) diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index b5b3810c9e94..0811d860fe75 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -35,13 +35,13 @@ INTERACTIVE COMMANDS *f*:: filter by regular expression -*g*:: filter by guest name +*g*:: filter by guest name/PID *h*:: display interactive commands reference *o*:: toggle sorting order (Total vs CurAvg/s) -*p*:: filter by PID +*p*:: filter by guest name/PID *q*:: quit diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 57254f5b2779..694abc628e9b 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -29,7 +29,7 @@ #include "builtin.h" #include "check.h" -bool no_fp, no_unreachable; +bool no_fp, no_unreachable, retpoline, module; static const char * const check_usage[] = { "objtool check [<options>] file.o", @@ -39,6 +39,8 @@ static const char * const check_usage[] = { const struct option check_options[] = { OPT_BOOLEAN('f', "no-fp", &no_fp, "Skip frame pointer validation"), OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"), + OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"), + OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"), OPT_END(), }; @@ -53,5 +55,5 @@ int cmd_check(int argc, const char **argv) objname = argv[0]; - return check(objname, no_fp, no_unreachable, false); + return check(objname, false); } diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c index 91e8e19ff5e0..77ea2b97117d 100644 --- a/tools/objtool/builtin-orc.c +++ b/tools/objtool/builtin-orc.c @@ -25,7 +25,6 @@ */ #include <string.h> -#include <subcmd/parse-options.h> #include "builtin.h" #include "check.h" @@ -36,9 +35,6 @@ static const char *orc_usage[] = { NULL, }; -extern const struct option check_options[]; -extern bool no_fp, no_unreachable; - int cmd_orc(int argc, const char **argv) { const char *objname; @@ -54,7 +50,7 @@ int cmd_orc(int argc, const char **argv) objname = argv[0]; - return check(objname, no_fp, no_unreachable, true); + return check(objname, true); } if (!strcmp(argv[0], "dump")) { diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h index dd526067fed5..28ff40e19a14 100644 --- a/tools/objtool/builtin.h +++ b/tools/objtool/builtin.h @@ -17,6 +17,11 @@ #ifndef _BUILTIN_H #define _BUILTIN_H +#include <subcmd/parse-options.h> + +extern const struct option check_options[]; +extern bool no_fp, no_unreachable, retpoline, module; + extern int cmd_check(int argc, const char **argv); extern int cmd_orc(int argc, const char **argv); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index a8cb69a26576..92b6a2c21631 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -18,6 +18,7 @@ #include <string.h> #include <stdlib.h> +#include "builtin.h" #include "check.h" #include "elf.h" #include "special.h" @@ -33,7 +34,6 @@ struct alternative { }; const char *objname; -static bool no_fp; struct cfi_state initial_func_cfi; struct instruction *find_insn(struct objtool_file *file, @@ -497,6 +497,7 @@ static int add_jump_destinations(struct objtool_file *file) * disguise, so convert them accordingly. */ insn->type = INSN_JUMP_DYNAMIC; + insn->retpoline_safe = true; continue; } else { /* sibling call */ @@ -548,7 +549,8 @@ static int add_call_destinations(struct objtool_file *file) if (!insn->call_dest && !insn->ignore) { WARN_FUNC("unsupported intra-function call", insn->sec, insn->offset); - WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE."); + if (retpoline) + WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE."); return -1; } @@ -923,7 +925,11 @@ static struct rela *find_switch_table(struct objtool_file *file, if (find_symbol_containing(file->rodata, text_rela->addend)) continue; - return find_rela_by_dest(file->rodata, text_rela->addend); + rodata_rela = find_rela_by_dest(file->rodata, text_rela->addend); + if (!rodata_rela) + continue; + + return rodata_rela; } return NULL; @@ -1108,6 +1114,41 @@ static int read_unwind_hints(struct objtool_file *file) return 0; } +static int read_retpoline_hints(struct objtool_file *file) +{ + struct section *sec; + struct instruction *insn; + struct rela *rela; + + sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); + if (!sec) + return 0; + + list_for_each_entry(rela, &sec->rela_list, list) { + if (rela->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); + return -1; + } + + insn = find_insn(file, rela->sym->sec, rela->addend); + if (!insn) { + WARN("bad .discard.retpoline_safe entry"); + return -1; + } + + if (insn->type != INSN_JUMP_DYNAMIC && + insn->type != INSN_CALL_DYNAMIC) { + WARN_FUNC("retpoline_safe hint not an indirect jump/call", + insn->sec, insn->offset); + return -1; + } + + insn->retpoline_safe = true; + } + + return 0; +} + static int decode_sections(struct objtool_file *file) { int ret; @@ -1146,6 +1187,10 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; + ret = read_retpoline_hints(file); + if (ret) + return ret; + return 0; } @@ -1891,6 +1936,38 @@ static int validate_unwind_hints(struct objtool_file *file) return warnings; } +static int validate_retpoline(struct objtool_file *file) +{ + struct instruction *insn; + int warnings = 0; + + for_each_insn(file, insn) { + if (insn->type != INSN_JUMP_DYNAMIC && + insn->type != INSN_CALL_DYNAMIC) + continue; + + if (insn->retpoline_safe) + continue; + + /* + * .init.text code is ran before userspace and thus doesn't + * strictly need retpolines, except for modules which are + * loaded late, they very much do need retpoline in their + * .init.text + */ + if (!strcmp(insn->sec->name, ".init.text") && !module) + continue; + + WARN_FUNC("indirect %s found in RETPOLINE build", + insn->sec, insn->offset, + insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); + + warnings++; + } + + return warnings; +} + static bool is_kasan_insn(struct instruction *insn) { return (insn->type == INSN_CALL && @@ -2022,13 +2099,12 @@ static void cleanup(struct objtool_file *file) elf_close(file->elf); } -int check(const char *_objname, bool _no_fp, bool no_unreachable, bool orc) +int check(const char *_objname, bool orc) { struct objtool_file file; int ret, warnings = 0; objname = _objname; - no_fp = _no_fp; file.elf = elf_open(objname, orc ? O_RDWR : O_RDONLY); if (!file.elf) @@ -2052,6 +2128,13 @@ int check(const char *_objname, bool _no_fp, bool no_unreachable, bool orc) if (list_empty(&file.insn_list)) goto out; + if (retpoline) { + ret = validate_retpoline(&file); + if (ret < 0) + return ret; + warnings += ret; + } + ret = validate_functions(&file); if (ret < 0) goto out; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index 23a1d065cae1..c6b68fcb926f 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -45,6 +45,7 @@ struct instruction { unsigned char type; unsigned long immediate; bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts; + bool retpoline_safe; struct symbol *call_dest; struct instruction *jump_dest; struct instruction *first_jump_src; @@ -63,7 +64,7 @@ struct objtool_file { bool ignore_unreachables, c_file, hints; }; -int check(const char *objname, bool no_fp, bool no_unreachable, bool orc); +int check(const char *objname, bool orc); struct instruction *find_insn(struct objtool_file *file, struct section *sec, unsigned long offset); diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt index 954ea9e21236..cf9f4040ea5c 100644 --- a/tools/perf/Documentation/perf-kallsyms.txt +++ b/tools/perf/Documentation/perf-kallsyms.txt @@ -8,7 +8,7 @@ perf-kallsyms - Searches running kernel for symbols SYNOPSIS -------- [verse] -'perf kallsyms <options> symbol_name[,symbol_name...]' +'perf kallsyms' [<options>] symbol_name[,symbol_name...] DESCRIPTION ----------- diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index bf4ca749d1ac..a217623fec2e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -881,6 +881,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } } + /* + * If we have just single event and are sending data + * through pipe, we need to force the ids allocation, + * because we synthesize event name through the pipe + * and need the id for that. + */ + if (data->is_pipe && rec->evlist->nr_entries == 1) + rec->opts.sample_id = true; + if (record__open(rec) != 0) { err = -1; goto out_child; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 98bf9d32f222..54a4c152edb3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -917,7 +917,7 @@ static void print_metric_csv(void *ctx, char buf[64], *vals, *ends; if (unit == NULL || fmt == NULL) { - fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep); + fprintf(out, "%s%s", csv_sep, csv_sep); return; } snprintf(buf, sizeof(buf), fmt, val); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b7c823ba8374..35ac016fcb98 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -991,7 +991,7 @@ static int perf_top_overwrite_fallback(struct perf_top *top, evlist__for_each_entry(evlist, counter) counter->attr.write_backward = false; opts->overwrite = false; - ui__warning("fall back to non-overwrite mode\n"); + pr_debug2("fall back to non-overwrite mode\n"); return 1; } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index cfe46236a5e5..57b9b342d533 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -61,6 +61,7 @@ struct record_opts { bool tail_synthesize; bool overwrite; bool ignore_missing_thread; + bool sample_id; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 286427975112..fbf927cf775d 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -327,7 +327,32 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) if (!disasm_line__is_valid_jump(cursor, sym)) return; + /* + * This first was seen with a gcc function, _cpp_lex_token, that + * has the usual jumps: + * + * │1159e6c: ↓ jne 115aa32 <_cpp_lex_token@@Base+0xf92> + * + * I.e. jumps to a label inside that function (_cpp_lex_token), and + * those works, but also this kind: + * + * │1159e8b: ↓ jne c469be <cpp_named_operator2name@@Base+0xa72> + * + * I.e. jumps to another function, outside _cpp_lex_token, which + * are not being correctly handled generating as a side effect references + * to ab->offset[] entries that are set to NULL, so to make this code + * more robust, check that here. + * + * A proper fix for will be put in place, looking at the function + * name right after the '<' token and probably treating this like a + * 'call' instruction. + */ target = ab->offsets[cursor->ops.target.offset]; + if (target == NULL) { + ui_helpline__printf("WARN: jump target inconsistency, press 'o', ab->offsets[%#x] = NULL\n", + cursor->ops.target.offset); + return; + } bcursor = browser_line(&cursor->al); btarget = browser_line(target); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 9faf3b5367db..6470ea2aa25e 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -60,6 +60,12 @@ #include "sane_ctype.h" #include "symbol/kallsyms.h" +static bool auxtrace__dont_decode(struct perf_session *session) +{ + return !session->itrace_synth_opts || + session->itrace_synth_opts->dont_decode; +} + int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, struct auxtrace_mmap_params *mp, void *userpg, int fd) @@ -762,6 +768,9 @@ int auxtrace_queues__process_index(struct auxtrace_queues *queues, size_t i; int err; + if (auxtrace__dont_decode(session)) + return 0; + list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) { for (i = 0; i < auxtrace_index->nr; i++) { ent = &auxtrace_index->entries[i]; @@ -892,12 +901,6 @@ out_free: return err; } -static bool auxtrace__dont_decode(struct perf_session *session) -{ - return !session->itrace_synth_opts || - session->itrace_synth_opts->dont_decode; -} - int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_session *session) diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 1e97937b03a9..6f09e4962dad 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -137,6 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, struct perf_evsel *evsel; bool use_sample_identifier = false; bool use_comm_exec; + bool sample_id = opts->sample_id; /* * Set the evsel leader links before we configure attributes, @@ -163,8 +164,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, * match the id. */ use_sample_identifier = perf_can_sample_identifier(); - evlist__for_each_entry(evlist, evsel) - perf_evsel__set_sample_id(evsel, use_sample_identifier); + sample_id = true; } else if (evlist->nr_entries > 1) { struct perf_evsel *first = perf_evlist__first(evlist); @@ -174,6 +174,10 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, use_sample_identifier = perf_can_sample_identifier(); break; } + sample_id = true; + } + + if (sample_id) { evlist__for_each_entry(evlist, evsel) perf_evsel__set_sample_id(evsel, use_sample_identifier); } diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h index 370138e7e35c..88223bc7c82b 100644 --- a/tools/perf/util/trigger.h +++ b/tools/perf/util/trigger.h @@ -12,7 +12,7 @@ * States and transits: * * - * OFF--(on)--> READY --(hit)--> HIT + * OFF--> ON --> READY --(hit)--> HIT * ^ | * | (ready) * | | @@ -27,8 +27,9 @@ struct trigger { volatile enum { TRIGGER_ERROR = -2, TRIGGER_OFF = -1, - TRIGGER_READY = 0, - TRIGGER_HIT = 1, + TRIGGER_ON = 0, + TRIGGER_READY = 1, + TRIGGER_HIT = 2, } state; const char *name; }; @@ -50,7 +51,7 @@ static inline bool trigger_is_error(struct trigger *t) static inline void trigger_on(struct trigger *t) { TRIGGER_WARN_ONCE(t, TRIGGER_OFF); - t->state = TRIGGER_READY; + t->state = TRIGGER_ON; } static inline void trigger_ready(struct trigger *t) diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index 44ef9eba5a7a..6c645eb77d42 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -178,6 +178,55 @@ void idr_get_next_test(int base) idr_destroy(&idr); } +int idr_u32_cb(int id, void *ptr, void *data) +{ + BUG_ON(id < 0); + BUG_ON(ptr != DUMMY_PTR); + return 0; +} + +void idr_u32_test1(struct idr *idr, u32 handle) +{ + static bool warned = false; + u32 id = handle; + int sid = 0; + void *ptr; + + BUG_ON(idr_alloc_u32(idr, DUMMY_PTR, &id, id, GFP_KERNEL)); + BUG_ON(id != handle); + BUG_ON(idr_alloc_u32(idr, DUMMY_PTR, &id, id, GFP_KERNEL) != -ENOSPC); + BUG_ON(id != handle); + if (!warned && id > INT_MAX) + printk("vvv Ignore these warnings\n"); + ptr = idr_get_next(idr, &sid); + if (id > INT_MAX) { + BUG_ON(ptr != NULL); + BUG_ON(sid != 0); + } else { + BUG_ON(ptr != DUMMY_PTR); + BUG_ON(sid != id); + } + idr_for_each(idr, idr_u32_cb, NULL); + if (!warned && id > INT_MAX) { + printk("^^^ Warnings over\n"); + warned = true; + } + BUG_ON(idr_remove(idr, id) != DUMMY_PTR); + BUG_ON(!idr_is_empty(idr)); +} + +void idr_u32_test(int base) +{ + DEFINE_IDR(idr); + idr_init_base(&idr, base); + idr_u32_test1(&idr, 10); + idr_u32_test1(&idr, 0x7fffffff); + idr_u32_test1(&idr, 0x80000000); + idr_u32_test1(&idr, 0x80000001); + idr_u32_test1(&idr, 0xffe00000); + idr_u32_test1(&idr, 0xffffffff); +} + void idr_checks(void) { unsigned long i; @@ -248,6 +297,9 @@ void idr_checks(void) idr_get_next_test(0); idr_get_next_test(1); idr_get_next_test(4); + idr_u32_test(4); + idr_u32_test(1); + idr_u32_test(0); } /* diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c index 6903ccf35595..44a0d1ad4408 100644 --- a/tools/testing/radix-tree/linux.c +++ b/tools/testing/radix-tree/linux.c @@ -29,7 +29,7 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) { struct radix_tree_node *node; - if (flags & __GFP_NOWARN) + if (!(flags & __GFP_DIRECT_RECLAIM)) return NULL; pthread_mutex_lock(&cachep->lock); @@ -73,10 +73,17 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) void *kmalloc(size_t size, gfp_t gfp) { - void *ret = malloc(size); + void *ret; + + if (!(gfp & __GFP_DIRECT_RECLAIM)) + return NULL; + + ret = malloc(size); uatomic_inc(&nr_allocated); if (kmalloc_verbose) printf("Allocating %p from malloc\n", ret); + if (gfp & __GFP_ZERO) + memset(ret, 0, size); return ret; } diff --git a/tools/testing/radix-tree/linux/compiler_types.h b/tools/testing/radix-tree/linux/compiler_types.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/radix-tree/linux/compiler_types.h diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h index e9fff59dfd8a..e3201ccf54c3 100644 --- a/tools/testing/radix-tree/linux/gfp.h +++ b/tools/testing/radix-tree/linux/gfp.h @@ -11,6 +11,7 @@ #define __GFP_IO 0x40u #define __GFP_FS 0x80u #define __GFP_NOWARN 0x200u +#define __GFP_ZERO 0x8000u #define __GFP_ATOMIC 0x80000u #define __GFP_ACCOUNT 0x100000u #define __GFP_DIRECT_RECLAIM 0x400000u diff --git a/tools/testing/radix-tree/linux/slab.h b/tools/testing/radix-tree/linux/slab.h index 979baeec7e70..a037def0dec6 100644 --- a/tools/testing/radix-tree/linux/slab.h +++ b/tools/testing/radix-tree/linux/slab.h @@ -3,6 +3,7 @@ #define SLAB_H #include <linux/types.h> +#include <linux/gfp.h> #define SLAB_HWCACHE_ALIGN 1 #define SLAB_PANIC 2 @@ -11,6 +12,11 @@ void *kmalloc(size_t size, gfp_t); void kfree(void *); +static inline void *kzalloc(size_t size, gfp_t gfp) +{ + return kmalloc(size, gfp | __GFP_ZERO); +} + void *kmem_cache_alloc(struct kmem_cache *cachep, int flags); void kmem_cache_free(struct kmem_cache *cachep, void *objp); diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile index 1a7492268993..f6304d2be90c 100644 --- a/tools/testing/selftests/android/Makefile +++ b/tools/testing/selftests/android/Makefile @@ -11,11 +11,11 @@ all: BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ - #SUBDIR test prog name should be in the form: SUBDIR_test.sh + #SUBDIR test prog name should be in the form: SUBDIR_test.sh \ TEST=$$DIR"_test.sh"; \ - if [ -e $$DIR/$$TEST ]; then - rsync -a $$DIR/$$TEST $$BUILD_TARGET/; - fi + if [ -e $$DIR/$$TEST ]; then \ + rsync -a $$DIR/$$TEST $$BUILD_TARGET/; \ + fi \ done override define RUN_TESTS diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index c73592fa3d41..437c0b1c9d21 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -11163,6 +11163,64 @@ static struct bpf_test tests[] = { .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, + { + "xadd/w check unaligned stack", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -7), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "misaligned stack access off", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "xadd/w check unaligned map", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_STX_XADD(BPF_W, BPF_REG_0, BPF_REG_1, 3), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 3), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = REJECT, + .errstr = "misaligned value access off", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "xadd/w check unaligned pkt", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_0, 99), + BPF_JMP_IMM(BPF_JA, 0, 0, 6), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_ST_MEM(BPF_W, BPF_REG_2, 3, 0), + BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 1), + BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 1), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "BPF_XADD stores into R2 packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, }; static int probe_filter_length(const struct bpf_insn *fp) diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index cea4adcd42b8..a63e8453984d 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -12,9 +12,9 @@ all: BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ - if [ -e $$DIR/$(TEST_PROGS) ]; then - rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; - fi + if [ -e $$DIR/$(TEST_PROGS) ]; then \ + rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \ + fi \ done override define RUN_TESTS diff --git a/tools/testing/selftests/memfd/config b/tools/testing/selftests/memfd/config new file mode 100644 index 000000000000..835c7f4dadcd --- /dev/null +++ b/tools/testing/selftests/memfd/config @@ -0,0 +1 @@ +CONFIG_FUSE_FS=m diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile index 86636d207adf..686da510f989 100644 --- a/tools/testing/selftests/memory-hotplug/Makefile +++ b/tools/testing/selftests/memory-hotplug/Makefile @@ -4,8 +4,9 @@ all: include ../lib.mk TEST_PROGS := mem-on-off-test.sh -override RUN_TESTS := ./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]" -override EMIT_TESTS := echo "$(RUN_TESTS)" +override RUN_TESTS := @./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]" + +override EMIT_TESTS := echo "$(subst @,,$(RUN_TESTS))" run_full_test: @/bin/bash ./mem-on-off-test.sh && echo "memory-hotplug selftests: [PASS]" || echo "memory-hotplug selftests: [FAIL]" diff --git a/tools/testing/selftests/powerpc/mm/subpage_prot.c b/tools/testing/selftests/powerpc/mm/subpage_prot.c index 35ade7406dcd..3ae77ba93208 100644 --- a/tools/testing/selftests/powerpc/mm/subpage_prot.c +++ b/tools/testing/selftests/powerpc/mm/subpage_prot.c @@ -135,6 +135,16 @@ static int run_test(void *addr, unsigned long size) return 0; } +static int syscall_available(void) +{ + int rc; + + errno = 0; + rc = syscall(__NR_subpage_prot, 0, 0, 0); + + return rc == 0 || (errno != ENOENT && errno != ENOSYS); +} + int test_anon(void) { unsigned long align; @@ -145,6 +155,8 @@ int test_anon(void) void *mallocblock; unsigned long mallocsize; + SKIP_IF(!syscall_available()); + if (getpagesize() != 0x10000) { fprintf(stderr, "Kernel page size must be 64K!\n"); return 1; @@ -180,6 +192,8 @@ int test_file(void) off_t filesize; int fd; + SKIP_IF(!syscall_available()); + fd = open(file_name, O_RDWR); if (fd == -1) { perror("failed to open file"); diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index a23453943ad2..5c72ff978f27 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -16,7 +16,7 @@ $(OUTPUT)/tm-syscall: tm-syscall-asm.S $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include $(OUTPUT)/tm-tmspr: CFLAGS += -pthread $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64 -$(OUTPUT)/tm-resched-dscr: ../pmu/lib.o +$(OUTPUT)/tm-resched-dscr: ../pmu/lib.c $(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx $(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64 diff --git a/tools/testing/selftests/powerpc/tm/tm-trap.c b/tools/testing/selftests/powerpc/tm/tm-trap.c index 5d92c23ee6cb..179d592f0073 100644 --- a/tools/testing/selftests/powerpc/tm/tm-trap.c +++ b/tools/testing/selftests/powerpc/tm/tm-trap.c @@ -255,6 +255,8 @@ int tm_trap_test(void) struct sigaction trap_sa; + SKIP_IF(!have_htm()); + trap_sa.sa_flags = SA_SIGINFO; trap_sa.sa_sigaction = trap_signal_handler; sigaction(SIGTRAP, &trap_sa, NULL); diff --git a/tools/testing/selftests/pstore/config b/tools/testing/selftests/pstore/config index 6a8e5a9bfc10..d148f9f89fb6 100644 --- a/tools/testing/selftests/pstore/config +++ b/tools/testing/selftests/pstore/config @@ -2,3 +2,4 @@ CONFIG_MISC_FILESYSTEMS=y CONFIG_PSTORE=y CONFIG_PSTORE_PMSG=y CONFIG_PSTORE_CONSOLE=y +CONFIG_PSTORE_RAM=m diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile index b3c8ba3cb668..d0121a8a3523 100644 --- a/tools/testing/selftests/sync/Makefile +++ b/tools/testing/selftests/sync/Makefile @@ -30,7 +30,7 @@ $(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS) $(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS) $(OBJS): $(OUTPUT)/%.o: %.c - $(CC) -c $^ -o $@ + $(CC) -c $^ -o $@ $(CFLAGS) $(TESTS): $(OUTPUT)/%.o: %.c $(CC) -c $^ -o $@ diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json index e34075059c26..90bba48c3f07 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json @@ -315,7 +315,7 @@ "cmdUnderTest": "$TC actions ls action skbmod", "expExitCode": "0", "verifyCmd": "$TC actions get action skbmod index 4", - "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x0031", + "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x31", "matchCount": "1", "teardown": [ "$TC actions flush action skbmod" diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index 3d5a62ff7d31..f5d7a7851e21 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -1,4 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 +include ../lib.mk + ifndef CROSS_COMPILE CFLAGS := -std=gnu99 CFLAGS_vdso_standalone_test_x86 := -nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector @@ -6,16 +8,14 @@ ifeq ($(CONFIG_X86_32),y) LDLIBS += -lgcc_s endif -TEST_PROGS := vdso_test vdso_standalone_test_x86 +TEST_PROGS := $(OUTPUT)/vdso_test $(OUTPUT)/vdso_standalone_test_x86 all: $(TEST_PROGS) -vdso_test: parse_vdso.c vdso_test.c -vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c +$(OUTPUT)/vdso_test: parse_vdso.c vdso_test.c +$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c $(CC) $(CFLAGS) $(CFLAGS_vdso_standalone_test_x86) \ vdso_standalone_test_x86.c parse_vdso.c \ - -o vdso_standalone_test_x86 + -o $@ -include ../lib.mk -clean: - rm -fr $(TEST_PROGS) +EXTRA_CLEAN := $(TEST_PROGS) endif diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 63c94d776e89..342c7bc9dc8c 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -11,3 +11,4 @@ mlock-intersect-test mlock-random-test virtual_address_range gup_benchmark +va_128TBswitch diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index d2561895a021..22d564673830 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -2,25 +2,33 @@ # SPDX-License-Identifier: GPL-2.0 #please run as root -#we need 256M, below is the size in kB -needmem=262144 mnt=./huge exitcode=0 -#get pagesize and freepages from /proc/meminfo +#get huge pagesize and freepages from /proc/meminfo while read name size unit; do if [ "$name" = "HugePages_Free:" ]; then freepgs=$size fi if [ "$name" = "Hugepagesize:" ]; then - pgsize=$size + hpgsize_KB=$size fi done < /proc/meminfo +# Simple hugetlbfs tests have a hardcoded minimum requirement of +# huge pages totaling 256MB (262144KB) in size. The userfaultfd +# hugetlb test requires a minimum of 2 * nr_cpus huge pages. Take +# both of these requirements into account and attempt to increase +# number of huge pages available. +nr_cpus=$(nproc) +hpgsize_MB=$((hpgsize_KB / 1024)) +half_ufd_size_MB=$((((nr_cpus * hpgsize_MB + 127) / 128) * 128)) +needmem_KB=$((half_ufd_size_MB * 2 * 1024)) + #set proper nr_hugepages -if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then +if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then nr_hugepgs=`cat /proc/sys/vm/nr_hugepages` - needpgs=`expr $needmem / $pgsize` + needpgs=$((needmem_KB / hpgsize_KB)) tries=2 while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do lackpgs=$(( $needpgs - $freepgs )) @@ -107,8 +115,9 @@ fi echo "---------------------------" echo "running userfaultfd_hugetlb" echo "---------------------------" -# 256MB total huge pages == 128MB src and 128MB dst -./userfaultfd hugetlb 128 32 $mnt/ufd_test_file +# Test requires source and destination huge pages. Size of source +# (half_ufd_size_MB) is passed as argument to test. +./userfaultfd hugetlb $half_ufd_size_MB 32 $mnt/ufd_test_file if [ $? -ne 0 ]; then echo "[FAIL]" exitcode=1 diff --git a/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c index 361466a2eaef..ade443a88421 100644 --- a/tools/testing/selftests/x86/entry_from_vm86.c +++ b/tools/testing/selftests/x86/entry_from_vm86.c @@ -95,6 +95,10 @@ asm ( "int3\n\t" "vmcode_int80:\n\t" "int $0x80\n\t" + "vmcode_popf_hlt:\n\t" + "push %ax\n\t" + "popf\n\t" + "hlt\n\t" "vmcode_umip:\n\t" /* addressing via displacements */ "smsw (2052)\n\t" @@ -124,8 +128,8 @@ asm ( extern unsigned char vmcode[], end_vmcode[]; extern unsigned char vmcode_bound[], vmcode_sysenter[], vmcode_syscall[], - vmcode_sti[], vmcode_int3[], vmcode_int80[], vmcode_umip[], - vmcode_umip_str[], vmcode_umip_sldt[]; + vmcode_sti[], vmcode_int3[], vmcode_int80[], vmcode_popf_hlt[], + vmcode_umip[], vmcode_umip_str[], vmcode_umip_sldt[]; /* Returns false if the test was skipped. */ static bool do_test(struct vm86plus_struct *v86, unsigned long eip, @@ -175,7 +179,7 @@ static bool do_test(struct vm86plus_struct *v86, unsigned long eip, (VM86_TYPE(ret) == rettype && VM86_ARG(ret) == retarg)) { printf("[OK]\tReturned correctly\n"); } else { - printf("[FAIL]\tIncorrect return reason\n"); + printf("[FAIL]\tIncorrect return reason (started at eip = 0x%lx, ended at eip = 0x%lx)\n", eip, v86->regs.eip); nerrs++; } @@ -264,6 +268,9 @@ int main(void) v86.regs.ds = load_addr / 16; v86.regs.es = load_addr / 16; + /* Use the end of the page as our stack. */ + v86.regs.esp = 4096; + assert((v86.regs.cs & 3) == 0); /* Looks like RPL = 0 */ /* #BR -- should deliver SIG??? */ @@ -295,6 +302,23 @@ int main(void) v86.regs.eflags &= ~X86_EFLAGS_IF; do_test(&v86, vmcode_sti - vmcode, VM86_STI, 0, "STI with VIP set"); + /* POPF with VIP set but IF clear: should not trap */ + v86.regs.eflags = X86_EFLAGS_VIP; + v86.regs.eax = 0; + do_test(&v86, vmcode_popf_hlt - vmcode, VM86_UNKNOWN, 0, "POPF with VIP set and IF clear"); + + /* POPF with VIP set and IF set: should trap */ + v86.regs.eflags = X86_EFLAGS_VIP; + v86.regs.eax = X86_EFLAGS_IF; + do_test(&v86, vmcode_popf_hlt - vmcode, VM86_STI, 0, "POPF with VIP and IF set"); + + /* POPF with VIP clear and IF set: should not trap */ + v86.regs.eflags = 0; + v86.regs.eax = X86_EFLAGS_IF; + do_test(&v86, vmcode_popf_hlt - vmcode, VM86_UNKNOWN, 0, "POPF with VIP clear and IF set"); + + v86.regs.eflags = 0; + /* INT3 -- should cause #BP */ do_test(&v86, vmcode_int3 - vmcode, VM86_TRAP, 3, "INT3"); @@ -318,7 +342,7 @@ int main(void) clearhandler(SIGSEGV); /* Make sure nothing explodes if we fork. */ - if (fork() > 0) + if (fork() == 0) return 0; return (nerrs == 0 ? 0 : 1); diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index be81621446f0..0b4f1cc2291c 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -450,7 +450,7 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void) num_vsyscall_traps++; } -static int test_native_vsyscall(void) +static int test_emulation(void) { time_t tmp; bool is_native; @@ -458,7 +458,7 @@ static int test_native_vsyscall(void) if (!vtime) return 0; - printf("[RUN]\tchecking for native vsyscall\n"); + printf("[RUN]\tchecking that vsyscalls are emulated\n"); sethandler(SIGTRAP, sigtrap, 0); set_eflags(get_eflags() | X86_EFLAGS_TF); vtime(&tmp); @@ -474,11 +474,12 @@ static int test_native_vsyscall(void) */ is_native = (num_vsyscall_traps > 1); - printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n", + printf("[%s]\tvsyscalls are %s (%d instructions in vsyscall page)\n", + (is_native ? "FAIL" : "OK"), (is_native ? "native" : "emulated"), (int)num_vsyscall_traps); - return 0; + return is_native; } #endif @@ -498,7 +499,7 @@ int main(int argc, char **argv) nerrs += test_vsys_r(); #ifdef __x86_64__ - nerrs += test_native_vsyscall(); + nerrs += test_emulation(); #endif return nerrs ? 1 : 0; |