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
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -8543,7 +8543,8 @@ Kernel parameters
         workqueue.default_affinity_scope=
 			Select the default affinity scope to use for unbound
 			workqueues. Can be one of "cpu", "smt", "cache",
-			"numa" and "system". Default is "cache". For more
+			"cache_shard", "numa" and "system". Default is
+			"cache_shard". For more
 			information, see the Affinity Scopes section in
 			Documentation/core-api/workqueue.rst.
 

Documentation/core-api/workqueue.rst

@@ -378,9 +378,9 @@ Affinity Scopes
 
 An unbound workqueue groups CPUs according to its affinity scope to improve
 cache locality. For example, if a workqueue is using the default affinity
-scope of "cache", it will group CPUs according to last level cache
-boundaries. A work item queued on the workqueue will be assigned to a worker
-on one of the CPUs which share the last level cache with the issuing CPU.
+scope of "cache_shard", it will group CPUs into sub-LLC shards. A work item
+queued on the workqueue will be assigned to a worker on one of the CPUs
+within the same shard as the issuing CPU.
 Once started, the worker may or may not be allowed to move outside the scope
 depending on the ``affinity_strict`` setting of the scope.
 
@@ -402,7 +402,13 @@ Workqueue currently supports the following affinity scopes.
 ``cache``
   CPUs are grouped according to cache boundaries. Which specific cache
   boundary is used is determined by the arch code. L3 is used in a lot of
-  cases. This is the default affinity scope.
+  cases.
+
+``cache_shard``
+  CPUs are grouped into sub-LLC shards of at most ``wq_cache_shard_size``
+  cores (default 8, tunable via the ``workqueue.cache_shard_size`` boot
+  parameter). Shards are always split on core (SMT group) boundaries.
+  This is the default affinity scope.
 
 ``numa``
   CPUs are grouped according to NUMA boundaries.

Documentation/driver-api/driver-model/devres.rst

@@ -464,3 +464,7 @@ SPI
 
 WATCHDOG
   devm_watchdog_register_device()
+
+WORKQUEUE
+  devm_alloc_workqueue()
+  devm_alloc_ordered_workqueue()

drivers/firmware/efi/efi.c

@@ -423,7 +423,7 @@ static int __init efisubsys_init(void)
 		 * ordered workqueue (which creates only one execution context)
 		 * should suffice for all our needs.
 		 */
-		efi_rts_wq = alloc_ordered_workqueue("efi_rts_wq", 0);
+		efi_rts_wq = alloc_ordered_workqueue("efi_runtime", WQ_SYSFS);
 		if (!efi_rts_wq) {
 			pr_err("Creating efi_rts_wq failed, EFI runtime services disabled.\n");
 			clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);

include/linux/workqueue.h

@@ -131,8 +131,9 @@ struct rcu_work {
 enum wq_affn_scope {
 	WQ_AFFN_DFL,			/* use system default */
 	WQ_AFFN_CPU,			/* one pod per CPU */
-	WQ_AFFN_SMT,			/* one pod poer SMT */
+	WQ_AFFN_SMT,			/* one pod per SMT */
 	WQ_AFFN_CACHE,			/* one pod per LLC */
+	WQ_AFFN_CACHE_SHARD,		/* synthetic sub-LLC shards */
 	WQ_AFFN_NUMA,			/* one pod per NUMA node */
 	WQ_AFFN_SYSTEM,			/* one pod across the whole system */
 
@@ -440,6 +441,9 @@ enum wq_consts {
  * system_long_wq is similar to system_percpu_wq but may host long running
  * works.  Queue flushing might take relatively long.
  *
+ * system_dfl_long_wq is similar to system_dfl_wq but it may host long running
+ * works.
+ *
  * system_dfl_wq is unbound workqueue.  Workers are not bound to
  * any specific CPU, not concurrency managed, and all queued works are
  * executed immediately as long as max_active limit is not reached and
@@ -468,6 +472,7 @@ extern struct workqueue_struct *system_power_efficient_wq;
 extern struct workqueue_struct *system_freezable_power_efficient_wq;
 extern struct workqueue_struct *system_bh_wq;
 extern struct workqueue_struct *system_bh_highpri_wq;
+extern struct workqueue_struct *system_dfl_long_wq;
 
 void workqueue_softirq_action(bool highpri);
 void workqueue_softirq_dead(unsigned int cpu);
@@ -512,6 +517,26 @@ __printf(1, 4) struct workqueue_struct *
 alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...);
 #define alloc_workqueue(...)	alloc_hooks(alloc_workqueue_noprof(__VA_ARGS__))
 
+/**
+ * devm_alloc_workqueue - Resource-managed allocate a workqueue
+ * @dev: Device to allocate workqueue for
+ * @fmt: printf format for the name of the workqueue
+ * @flags: WQ_* flags
+ * @max_active: max in-flight work items, 0 for default
+ * @...: args for @fmt
+ *
+ * Resource managed workqueue, see alloc_workqueue() for details.
+ *
+ * The workqueue will be automatically destroyed on driver detach.  Typically
+ * this should be used in drivers already relying on devm interafaces.
+ *
+ * RETURNS:
+ * Pointer to the allocated workqueue on success, %NULL on failure.
+ */
+__printf(2, 5) struct workqueue_struct *
+devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags,
+		     int max_active, ...);
+
 #ifdef CONFIG_LOCKDEP
 /**
  * alloc_workqueue_lockdep_map - allocate a workqueue with user-defined lockdep_map
@@ -568,6 +593,8 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active,
  */
 #define alloc_ordered_workqueue(fmt, flags, args...)			\
 	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
+#define devm_alloc_ordered_workqueue(dev, fmt, flags, args...)		\
+	devm_alloc_workqueue(dev, fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
 	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_PERCPU, 1, (name))
@@ -712,14 +739,14 @@ static inline bool schedule_work_on(int cpu, struct work_struct *work)
 }
 
 /**
- * schedule_work - put work task in global workqueue
+ * schedule_work - put work task in per-CPU workqueue
  * @work: job to be done
  *
- * Returns %false if @work was already on the kernel-global workqueue and
+ * Returns %false if @work was already on the system per-CPU workqueue and
  * %true otherwise.
  *
- * This puts a job in the kernel-global workqueue if it was not already
- * queued and leaves it in the same position on the kernel-global
+ * This puts a job in the system per-CPU workqueue if it was not already
+ * queued and leaves it in the same position on the system per-CPU
  * workqueue otherwise.
  *
  * Shares the same memory-ordering properties of queue_work(), cf. the
@@ -783,6 +810,8 @@ extern void __warn_flushing_systemwide_wq(void)
 	     _wq == system_highpri_wq) ||				\
 	    (__builtin_constant_p(_wq == system_long_wq) &&		\
 	     _wq == system_long_wq) ||					\
+	    (__builtin_constant_p(_wq == system_dfl_long_wq) &&		\
+	     _wq == system_dfl_long_wq) ||					\
 	    (__builtin_constant_p(_wq == system_dfl_wq) &&		\
 	     _wq == system_dfl_wq) ||				\
 	    (__builtin_constant_p(_wq == system_freezable_wq) &&	\
@@ -796,12 +825,12 @@ extern void __warn_flushing_systemwide_wq(void)
 })
 
 /**
- * schedule_delayed_work_on - queue work in global workqueue on CPU after delay
+ * schedule_delayed_work_on - queue work in per-CPU workqueue on CPU after delay
  * @cpu: cpu to use
  * @dwork: job to be done
  * @delay: number of jiffies to wait
  *
- * After waiting for a given time this puts a job in the kernel-global
+ * After waiting for a given time this puts a job in the system per-CPU
  * workqueue on the specified CPU.
  */
 static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
@@ -811,11 +840,11 @@ static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
 }
 
 /**
- * schedule_delayed_work - put work task in global workqueue after delay
+ * schedule_delayed_work - put work task in per-CPU workqueue after delay
  * @dwork: job to be done
  * @delay: number of jiffies to wait or 0 for immediate execution
  *
- * After waiting for a given time this puts a job in the kernel-global
+ * After waiting for a given time this puts a job in the system per-CPU
  * workqueue.
  */
 static inline bool schedule_delayed_work(struct delayed_work *dwork,