From 93de2a6a4b91b72607136dd656edf03fb399d27f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Sep 2026 09:37:21 -0700 Subject: KVM: SEV: Do cache maintenance on the source VM during intra-host migration Manually perform cache maintenance on the source VM during intra-host migration to ensure no stale data is left in CPU caches after the VM is destroyed. Because the source VM is "converted" to a non-SEV VM, KVM's memory reclaim flows won't trigger cache maintenance, e.g. when all guest memory is reclaimed in response to detaching from the mmu_notifier. Note, relying on the destination VM to do cache maintenance isn't an option as KVM doesn't require identical guest memory configurations, i.e. the source VM may have access to memory that the destination VM does not. Enforcing equivalent memory configurations is infeasible, as it would require a *deep* comparison of memslots, e.g. to verify that not only are the memslot identical, but what the memslots point at is also identical. Fixes: b56639318bb2 ("KVM: SEV: Add support for SEV intra host migration") Cc: stable@vger.kernel.org Reported-by: Stefan Teodorescu Signed-off-by: Sean Christopherson Message-ID: <20260923163721.1584779-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- tools/workqueue/wq_dump.py | 255 ++++++++++++++++++++++++++++++++++++++++++ tools/workqueue/wq_monitor.py | 168 ++++++++++++++++++++++++++++ 2 files changed, 423 insertions(+) create mode 100644 tools/workqueue/wq_dump.py create mode 100644 tools/workqueue/wq_monitor.py (limited to 'tools/workqueue') diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py new file mode 100644 index 000000000..9313ebe0c --- /dev/null +++ b/tools/workqueue/wq_dump.py @@ -0,0 +1,255 @@ +#!/usr/bin/env drgn +# +# Copyright (C) 2023 Tejun Heo +# Copyright (C) 2023 Meta Platforms, Inc. and affiliates. + +desc = """ +This is a drgn script to show the current workqueue configuration. For more +info on drgn, visit https://github.com/osandov/drgn. + +Affinity Scopes +=============== + +Shows the CPUs that can be used for unbound workqueues and how they will be +grouped by each available affinity type. For each type: + + nr_pods number of CPU pods in the affinity type + pod_cpus CPUs in each pod + pod_node NUMA node for memory allocation for each pod + cpu_pod pod that each CPU is associated to + +Worker Pools +============ + +Lists all worker pools indexed by their ID. For each pool: + + ref number of pool_workqueue's associated with this pool + nice nice value of the worker threads in the pool + idle number of idle workers + workers number of all workers + cpu CPU the pool is associated with (per-cpu pool) + cpus CPUs the workers in the pool can run on (unbound pool) + +Workqueue CPU -> pool +===================== + +Lists all workqueues along with their type and worker pool association. For +each workqueue: + + NAME TYPE[,FLAGS] POOL_ID... + + NAME name of the workqueue + TYPE percpu, unbound or ordered + FLAGS S: strict affinity scope + POOL_ID worker pool ID associated with each possible CPU +""" + +import sys + +import argparse +parser = argparse.ArgumentParser(description=desc, + formatter_class=argparse.RawTextHelpFormatter) +args = parser.parse_args() + +import drgn +from drgn.helpers.linux.list import list_for_each_entry,list_empty +from drgn.helpers.linux.percpu import per_cpu_ptr +from drgn.helpers.linux.cpumask import for_each_cpu,for_each_possible_cpu +from drgn.helpers.linux.nodemask import for_each_node +from drgn.helpers.linux.idr import idr_for_each + +def err(s): + print(s, file=sys.stderr, flush=True) + sys.exit(1) + +def cpumask_str(cpumask): + output = "" + base = 0 + v = 0 + for cpu in for_each_cpu(cpumask[0]): + while cpu - base >= 32: + output += f'{hex(v)} ' + base += 32 + v = 0 + v |= 1 << (cpu - base) + if v > 0: + output += f'{v:08x}' + return output.strip() + +wq_type_len = 9 + +def wq_attrs(wq): + try: + return wq.attrs + except AttributeError: + return wq.unbound_attrs + +def wq_type_str(wq): + if wq.flags & WQ_BH: + return f'{"bh":{wq_type_len}}' + elif wq.flags & WQ_UNBOUND: + if wq.flags & WQ_ORDERED: + return f'{"ordered":{wq_type_len}}' + else: + if wq_attrs(wq).affn_strict: + return f'{"unbound,S":{wq_type_len}}' + else: + return f'{"unbound":{wq_type_len}}' + else: + return f'{"percpu":{wq_type_len}}' + +worker_pool_idr = prog['worker_pool_idr'] +workqueues = prog['workqueues'] +wq_unbound_cpumask = prog['wq_unbound_cpumask'] +wq_pod_types = prog['wq_pod_types'] +wq_affn_dfl = prog['wq_affn_dfl'] +wq_affn_names = prog['wq_affn_names'] + +WQ_BH = prog['WQ_BH'] +WQ_UNBOUND = prog['WQ_UNBOUND'] +WQ_ORDERED = prog['__WQ_ORDERED'] +WQ_MEM_RECLAIM = prog['WQ_MEM_RECLAIM'] + +WQ_AFFN_CPU = prog['WQ_AFFN_CPU'] +WQ_AFFN_SMT = prog['WQ_AFFN_SMT'] +WQ_AFFN_CACHE = prog['WQ_AFFN_CACHE'] +WQ_AFFN_CACHE_SHARD = prog['WQ_AFFN_CACHE_SHARD'] +WQ_AFFN_NUMA = prog['WQ_AFFN_NUMA'] +WQ_AFFN_SYSTEM = prog['WQ_AFFN_SYSTEM'] + +POOL_BH = prog['POOL_BH'] + +WQ_NAME_LEN = prog['WQ_NAME_LEN'].value_() +cpumask_str_len = len(cpumask_str(wq_unbound_cpumask)) + +print('Affinity Scopes') +print('===============') + +print(f'wq_unbound_cpumask={cpumask_str(wq_unbound_cpumask)}') + +def print_pod_type(pt): + print(f' nr_pods {pt.nr_pods.value_()}') + + print(' pod_cpus', end='') + for pod in range(pt.nr_pods): + print(f' [{pod}]={cpumask_str(pt.pod_cpus[pod])}', end='') + print('') + + print(' pod_node', end='') + for pod in range(pt.nr_pods): + print(f' [{pod}]={pt.pod_node[pod].value_()}', end='') + print('') + + print(f' cpu_pod ', end='') + for cpu in for_each_possible_cpu(prog): + print(f' [{cpu}]={pt.cpu_pod[cpu].value_()}', end='') + print('') + +for affn in [WQ_AFFN_CPU, WQ_AFFN_SMT, WQ_AFFN_CACHE, WQ_AFFN_CACHE_SHARD, WQ_AFFN_NUMA, WQ_AFFN_SYSTEM]: + print('') + print(f'{wq_affn_names[affn].string_().decode().upper()}{" (default)" if affn == wq_affn_dfl else ""}') + print_pod_type(wq_pod_types[affn]) + +print('') +print('Worker Pools') +print('============') + +max_pool_id_len = 0 +max_ref_len = 0 +for pi, pool in idr_for_each(worker_pool_idr): + pool = drgn.Object(prog, 'struct worker_pool', address=pool) + max_pool_id_len = max(max_pool_id_len, len(f'{pi}')) + max_ref_len = max(max_ref_len, len(f'{pool.refcnt.value_()}')) + +for pi, pool in idr_for_each(worker_pool_idr): + pool = drgn.Object(prog, 'struct worker_pool', address=pool) + print(f'pool[{pi:0{max_pool_id_len}}] flags=0x{pool.flags.value_():02x} ref={pool.refcnt.value_():{max_ref_len}} nice={pool.attrs.nice.value_():3} ', end='') + print(f'idle/workers={pool.nr_idle.value_():3}/{pool.nr_workers.value_():3} ', end='') + if pool.cpu >= 0: + print(f'cpu={pool.cpu.value_():3}', end='') + if pool.flags & POOL_BH: + print(' bh', end='') + else: + print(f'cpus={cpumask_str(pool.attrs.cpumask)}', end='') + print(f' pod_cpus={cpumask_str(pool.attrs.__pod_cpumask)}', end='') + if pool.attrs.affn_strict: + print(' strict', end='') + print('') + +print('') +print('Workqueue CPU -> pool') +print('=====================') + +print(f'[{"workqueue":^{WQ_NAME_LEN-2}}\\ {"type CPU":{wq_type_len}}', end='') +for cpu in for_each_possible_cpu(prog): + print(f' {cpu:{max_pool_id_len}}', end='') +print(' dfl]') + +for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): + print(f'{wq.name.string_().decode():{WQ_NAME_LEN}} {wq_type_str(wq):10}', end='') + + for cpu in for_each_possible_cpu(prog): + pool_id = per_cpu_ptr(wq.cpu_pwq, cpu)[0].pool.id.value_() + field_len = max(len(str(cpu)), max_pool_id_len) + print(f' {pool_id:{field_len}}', end='') + + if wq.flags & WQ_UNBOUND: + print(f' {wq.dfl_pwq.pool.id.value_():{max_pool_id_len}}', end='') + print('') + +print('') +print('Workqueue -> rescuer') +print('====================') + +ucpus_len = max(cpumask_str_len, len("unbound_cpus")) +rcpus_len = max(cpumask_str_len, len("rescuer_cpus")) + +print(f'[{"workqueue":^{WQ_NAME_LEN-2}}\\ {"unbound_cpus":{ucpus_len}} pid {"rescuer_cpus":{rcpus_len}} ]') + +for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): + if not (wq.flags & WQ_MEM_RECLAIM): + continue + + print(f'{wq.name.string_().decode():{WQ_NAME_LEN}}', end='') + if wq.flags & WQ_UNBOUND: + print(f' {cpumask_str(wq_attrs(wq).cpumask):{ucpus_len}}', end='') + else: + print(f' {"":{ucpus_len}}', end='') + + print(f' {wq.rescuer.task.pid.value_():6}', end='') + print(f' {cpumask_str(wq.rescuer.task.cpus_ptr):{rcpus_len}}', end='') + print('') + +print('') +print('Unbound workqueue -> node_nr/max_active') +print('=======================================') + +if 'node_to_cpumask_map' in prog: + __cpu_online_mask = prog['__cpu_online_mask'] + node_to_cpumask_map = prog['node_to_cpumask_map'] + nr_node_ids = prog['nr_node_ids'].value_() + + print(f'online_cpus={cpumask_str(__cpu_online_mask.address_of_())}') + for node in for_each_node(): + print(f'NODE[{node:02}]={cpumask_str(node_to_cpumask_map[node])}') + print('') + + print(f'[{"workqueue":^{WQ_NAME_LEN-1}} {"min":>4} {"max":>4}', end='') + for node in for_each_node(): + print(f' {"NODE " + str(node):>9}', end='') + print(f' {"dfl":>9} ]') + print('') + + for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): + if not (wq.flags & WQ_UNBOUND): + continue + + print(f'{wq.name.string_().decode():{WQ_NAME_LEN}} ', end='') + print(f'{wq.min_active.value_():4} {wq.max_active.value_():4}', end='') + for node in for_each_node(): + nna = wq.node_nr_active[node] + print(f' {f"{nna.nr.counter.value_()}/{nna.max.value_()}":>9}', end='') + nna = wq.node_nr_active[nr_node_ids] + print(f' {f"{nna.nr.counter.value_()}/{nna.max.value_()}":>9}') +else: + printf(f'node_to_cpumask_map not present, is NUMA enabled?') diff --git a/tools/workqueue/wq_monitor.py b/tools/workqueue/wq_monitor.py new file mode 100644 index 000000000..7f47fa398 --- /dev/null +++ b/tools/workqueue/wq_monitor.py @@ -0,0 +1,168 @@ +#!/usr/bin/env drgn +# +# Copyright (C) 2023 Tejun Heo +# Copyright (C) 2023 Meta Platforms, Inc. and affiliates. + +desc = """ +This is a drgn script to monitor workqueues. For more info on drgn, visit +https://github.com/osandov/drgn. + + total Total number of work items executed by the workqueue. + + infl The number of currently in-flight work items. + + CPUtime Total CPU time consumed by the workqueue in seconds. This is + sampled from scheduler ticks and only provides ballpark + measurement. "nohz_full=" CPUs are excluded from measurement. + + CPUitsv The number of times a concurrency-managed work item hogged CPU + longer than the threshold (workqueue.cpu_intensive_thresh_us) + and got excluded from concurrency management to avoid stalling + other work items. + + CMW/RPR For per-cpu workqueues, the number of concurrency-management + wake-ups while executing a work item of the workqueue. For + unbound workqueues, the number of times a worker was repatriated + to its affinity scope after being migrated to an off-scope CPU by + the scheduler. + + mayday The number of times the rescuer was requested while waiting for + new worker creation. + + rescued The number of work items executed by the rescuer. +""" + +import signal +import re +import time +import json + +import argparse +parser = argparse.ArgumentParser(description=desc, + formatter_class=argparse.RawTextHelpFormatter) +parser.add_argument('workqueue', metavar='REGEX', nargs='*', + help='Target workqueue name patterns (all if empty)') +parser.add_argument('-i', '--interval', metavar='SECS', type=float, default=1, + help='Monitoring interval (0 to print once and exit)') +parser.add_argument('-j', '--json', action='store_true', + help='Output in json') +args = parser.parse_args() + +import drgn +from drgn.helpers.linux.list import list_for_each_entry + +workqueues = prog['workqueues'] + +WQ_UNBOUND = prog['WQ_UNBOUND'] +WQ_MEM_RECLAIM = prog['WQ_MEM_RECLAIM'] + +PWQ_STAT_STARTED = prog['PWQ_STAT_STARTED'] # work items started execution +PWQ_STAT_COMPLETED = prog['PWQ_STAT_COMPLETED'] # work items completed execution +PWQ_STAT_CPU_TIME = prog['PWQ_STAT_CPU_TIME'] # total CPU time consumed +PWQ_STAT_CPU_INTENSIVE = prog['PWQ_STAT_CPU_INTENSIVE'] # wq_cpu_intensive_thresh_us violations +PWQ_STAT_CM_WAKEUP = prog['PWQ_STAT_CM_WAKEUP'] # concurrency-management worker wakeups +PWQ_STAT_REPATRIATED = prog['PWQ_STAT_REPATRIATED'] # unbound workers brought back into scope +PWQ_STAT_MAYDAY = prog['PWQ_STAT_MAYDAY'] # maydays to rescuer +PWQ_STAT_RESCUED = prog['PWQ_STAT_RESCUED'] # linked work items executed by rescuer +PWQ_NR_STATS = prog['PWQ_NR_STATS'] + +class WqStats: + def __init__(self, wq): + self.name = wq.name.string_().decode() + self.unbound = wq.flags & WQ_UNBOUND != 0 + self.mem_reclaim = wq.flags & WQ_MEM_RECLAIM != 0 + self.stats = [0] * PWQ_NR_STATS + for pwq in list_for_each_entry('struct pool_workqueue', wq.pwqs.address_of_(), 'pwqs_node'): + for i in range(PWQ_NR_STATS): + self.stats[i] += int(pwq.stats[i]) + + def dict(self, now): + return { 'timestamp' : now, + 'name' : self.name, + 'unbound' : self.unbound, + 'mem_reclaim' : self.mem_reclaim, + 'started' : self.stats[PWQ_STAT_STARTED], + 'completed' : self.stats[PWQ_STAT_COMPLETED], + 'cpu_time' : self.stats[PWQ_STAT_CPU_TIME], + 'cpu_intensive' : self.stats[PWQ_STAT_CPU_INTENSIVE], + 'cm_wakeup' : self.stats[PWQ_STAT_CM_WAKEUP], + 'repatriated' : self.stats[PWQ_STAT_REPATRIATED], + 'mayday' : self.stats[PWQ_STAT_MAYDAY], + 'rescued' : self.stats[PWQ_STAT_RESCUED], } + + def table_header_str(): + return f'{"":>24} {"total":>8} {"infl":>5} {"CPUtime":>8} '\ + f'{"CPUitsv":>7} {"CMW/RPR":>7} {"mayday":>7} {"rescued":>7}' + + def table_row_str(self): + cpu_intensive = '-' + cmw_rpr = '-' + mayday = '-' + rescued = '-' + + if self.unbound: + cmw_rpr = str(self.stats[PWQ_STAT_REPATRIATED]); + else: + cpu_intensive = str(self.stats[PWQ_STAT_CPU_INTENSIVE]) + cmw_rpr = str(self.stats[PWQ_STAT_CM_WAKEUP]) + + if self.mem_reclaim: + mayday = str(self.stats[PWQ_STAT_MAYDAY]) + rescued = str(self.stats[PWQ_STAT_RESCUED]) + + out = f'{self.name[-24:]:24} ' \ + f'{self.stats[PWQ_STAT_STARTED]:8} ' \ + f'{max(self.stats[PWQ_STAT_STARTED] - self.stats[PWQ_STAT_COMPLETED], 0):5} ' \ + f'{self.stats[PWQ_STAT_CPU_TIME] / 1000000:8.1f} ' \ + f'{cpu_intensive:>7} ' \ + f'{cmw_rpr:>7} ' \ + f'{mayday:>7} ' \ + f'{rescued:>7} ' + return out.rstrip(':') + +exit_req = False + +def sigint_handler(signr, frame): + global exit_req + exit_req = True + +def main(): + # handle args + table_fmt = not args.json + interval = args.interval + + re_str = None + if args.workqueue: + for r in args.workqueue: + if re_str is None: + re_str = r + else: + re_str += '|' + r + + filter_re = re.compile(re_str) if re_str else None + + # monitoring loop + signal.signal(signal.SIGINT, sigint_handler) + + while not exit_req: + now = time.time() + + if table_fmt: + print() + print(WqStats.table_header_str()) + + for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): + stats = WqStats(wq) + if filter_re and not filter_re.search(stats.name): + continue + if table_fmt: + print(stats.table_row_str()) + else: + print(stats.dict(now)) + + if interval == 0: + break + time.sleep(interval) + +if __name__ == "__main__": + main() -- cgit v1.3.1