Merge tag 'wq-for-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue updates from Tejun Heo:

 - New default WQ_AFFN_CACHE_SHARD affinity scope subdivides LLCs into
   smaller shards to improve scalability on machines with many CPUs per
   LLC

 - Misc:
    - system_dfl_long_wq for long unbound works
    - devm_alloc_workqueue() for device-managed allocation
    - sysfs exposure for ordered workqueues and the EFI workqueue
    - removal of HK_TYPE_WQ from wq_unbound_cpumask
    - various small fixes

* tag 'wq-for-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq: (21 commits)
  workqueue: validate cpumask_first() result in llc_populate_cpu_shard_id()
  workqueue: use NR_STD_WORKER_POOLS instead of hardcoded value
  workqueue: avoid unguarded 64-bit division
  docs: workqueue: document WQ_AFFN_CACHE_SHARD affinity scope
  workqueue: add test_workqueue benchmark module
  tools/workqueue: add CACHE_SHARD support to wq_dump.py
  workqueue: set WQ_AFFN_CACHE_SHARD as the default affinity scope
  workqueue: add WQ_AFFN_CACHE_SHARD affinity scope
  workqueue: fix typo in WQ_AFFN_SMT comment
  workqueue: Remove HK_TYPE_WQ from affecting wq_unbound_cpumask
  workqueue: unlink pwqs from wq->pwqs list in alloc_and_link_pwqs() error path
  workqueue: Remove NULL wq WARN in __queue_delayed_work()
  workqueue: fix parse_affn_scope() prefix matching bug
  workqueue: devres: Add device-managed allocate workqueue
  workqueue: Add system_dfl_long_wq for long unbound works
  tools/workqueue/wq_dump.py: add NODE prefix to all node columns
  tools/workqueue/wq_dump.py: fix column alignment in node_nr/max_active section
  tools/workqueue/wq_dump.py: remove backslash separator from node_nr/max_active header
  efi: Allow to expose the workqueue via sysfs
  workqueue: Allow to expose ordered workqueues via sysfs
  ...

1 files changed, 8 insertions, 12 deletions

diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py
index d29b918306b4..ce4161f52f2f 100644
--- a/tools/workqueue/wq_dump.py
+++ b/tools/workqueue/wq_dump.py
@@ -107,6 +107,7 @@ 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']
 
@@ -138,7 +139,7 @@ def print_pod_type(pt):
         print(f' [{cpu}]={pt.cpu_pod[cpu].value_()}', end='')
     print('')
 
-for affn in [WQ_AFFN_CPU, WQ_AFFN_SMT, WQ_AFFN_CACHE, WQ_AFFN_NUMA, WQ_AFFN_SYSTEM]:
+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])
@@ -227,15 +228,10 @@ if 'node_to_cpumask_map' in prog:
         print(f'NODE[{node:02}]={cpumask_str(node_to_cpumask_map[node])}')
     print('')
 
-    print(f'[{"workqueue":^{WQ_NAME_LEN-2}}\\ min max', end='')
-    first = True
+    print(f'[{"workqueue":^{WQ_NAME_LEN-1}} {"min":>4} {"max":>4}', end='')
     for node in for_each_node():
-        if first:
-            print(f'  NODE {node}', end='')
-            first = False
-        else:
-            print(f' {node:7}', end='')
-    print(f' {"dfl":>7} ]')
+        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'):
@@ -243,11 +239,11 @@ if 'node_to_cpumask_map' in prog:
             continue
 
         print(f'{wq.name.string_().decode():{WQ_NAME_LEN}} ', end='')
-        print(f'{wq.min_active.value_():3} {wq.max_active.value_():3}', 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' {nna.nr.counter.value_():3}/{nna.max.value_():3}', end='')
+            print(f' {f"{nna.nr.counter.value_()}/{nna.max.value_()}":>9}', end='')
         nna = wq.node_nr_active[nr_node_ids]
-        print(f' {nna.nr.counter.value_():3}/{nna.max.value_():3}')
+        print(f' {f"{nna.nr.counter.value_()}/{nna.max.value_()}":>9}')
 else:
     printf(f'node_to_cpumask_map not present, is NUMA enabled?')