Merge remote-tracking branch 'tejun/for-6.9' into dm-6.9-bh-wq

Documentation/admin-guide/kernel-parameters.txt

@@ -7225,6 +7225,15 @@
 			threshold repeatedly. They are likely good
 			candidates for using WQ_UNBOUND workqueues instead.
 
+	workqueue.cpu_intensive_warning_thresh=<uint>
+			If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel
+			will report the work functions which violate the
+			intensive_threshold_us repeatedly. In order to prevent
+			spurious warnings, start printing only after a work
+			function has violated this threshold number of times.
+
+			The default is 4 times. 0 disables the warning.
+
 	workqueue.power_efficient
 			Per-cpu workqueues are generally preferred because
 			they show better performance thanks to cache

Documentation/core-api/workqueue.rst

@@ -77,10 +77,12 @@ wants a function to be executed asynchronously it has to set up a work
 item pointing to that function and queue that work item on a
 workqueue.
 
-Special purpose threads, called worker threads, execute the functions
-off of the queue, one after the other.  If no work is queued, the
-worker threads become idle.  These worker threads are managed in so
-called worker-pools.
+A work item can be executed in either a thread or the BH (softirq) context.
+
+For threaded workqueues, special purpose threads, called [k]workers, execute
+the functions off of the queue, one after the other. If no work is queued,
+the worker threads become idle. These worker threads are managed in
+worker-pools.
 
 The cmwq design differentiates between the user-facing workqueues that
 subsystems and drivers queue work items on and the backend mechanism
@@ -91,6 +93,12 @@ for high priority ones, for each possible CPU and some extra
 worker-pools to serve work items queued on unbound workqueues - the
 number of these backing pools is dynamic.
 
+BH workqueues use the same framework. However, as there can only be one
+concurrent execution context, there's no need to worry about concurrency.
+Each per-CPU BH worker pool contains only one pseudo worker which represents
+the BH execution context. A BH workqueue can be considered a convenience
+interface to softirq.
+
 Subsystems and drivers can create and queue work items through special
 workqueue API functions as they see fit. They can influence some
 aspects of the way the work items are executed by setting flags on the
@@ -106,7 +114,7 @@ unless specifically overridden, a work item of a bound workqueue will
 be queued on the worklist of either normal or highpri worker-pool that
 is associated to the CPU the issuer is running on.
 
-For any worker pool implementation, managing the concurrency level
+For any thread pool implementation, managing the concurrency level
 (how many execution contexts are active) is an important issue.  cmwq
 tries to keep the concurrency at a minimal but sufficient level.
 Minimal to save resources and sufficient in that the system is used at
@@ -164,6 +172,17 @@ resources, scheduled and executed.
 ``flags``
 ---------
 
+``WQ_BH``
+  BH workqueues can be considered a convenience interface to softirq. BH
+  workqueues are always per-CPU and all BH work items are executed in the
+  queueing CPU's softirq context in the queueing order.
+
+  All BH workqueues must have 0 ``max_active`` and ``WQ_HIGHPRI`` is the
+  only allowed additional flag.
+
+  BH work items cannot sleep. All other features such as delayed queueing,
+  flushing and canceling are supported.
+
 ``WQ_UNBOUND``
   Work items queued to an unbound wq are served by the special
   worker-pools which host workers which are not bound to any
@@ -237,15 +256,11 @@ may queue at the same time.  Unless there is a specific need for
 throttling the number of active work items, specifying '0' is
 recommended.
 
-Some users depend on the strict execution ordering of ST wq.  The
-combination of ``@max_active`` of 1 and ``WQ_UNBOUND`` used to
-achieve this behavior.  Work items on such wq were always queued to the
-unbound worker-pools and only one work item could be active at any given
-time thus achieving the same ordering property as ST wq.
-
-In the current implementation the above configuration only guarantees
-ST behavior within a given NUMA node. Instead ``alloc_ordered_workqueue()`` should
-be used to achieve system-wide ST behavior.
+Some users depend on strict execution ordering where only one work item
+is in flight at any given time and the work items are processed in
+queueing order. While the combination of ``@max_active`` of 1 and
+``WQ_UNBOUND`` used to achieve this behavior, this is no longer the
+case. Use ``alloc_ordered_queue()`` instead.
 
 
 Example Execution Scenarios

include/linux/async.h

@@ -120,4 +120,5 @@ extern void async_synchronize_cookie(async_cookie_t cookie);
 extern void async_synchronize_cookie_domain(async_cookie_t cookie,
 					    struct async_domain *domain);
 extern bool current_is_async(void);
+extern void async_init(void);
 #endif

include/linux/workqueue.h

@@ -22,20 +22,54 @@
  */
 #define work_data_bits(work) ((unsigned long *)(&(work)->data))
 
-enum {
+enum work_bits {
 	WORK_STRUCT_PENDING_BIT	= 0,	/* work item is pending execution */
-	WORK_STRUCT_INACTIVE_BIT= 1,	/* work item is inactive */
-	WORK_STRUCT_PWQ_BIT	= 2,	/* data points to pwq */
-	WORK_STRUCT_LINKED_BIT	= 3,	/* next work is linked to this one */
+	WORK_STRUCT_INACTIVE_BIT,	/* work item is inactive */
+	WORK_STRUCT_PWQ_BIT,		/* data points to pwq */
+	WORK_STRUCT_LINKED_BIT,		/* next work is linked to this one */
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
-	WORK_STRUCT_STATIC_BIT	= 4,	/* static initializer (debugobjects) */
-	WORK_STRUCT_COLOR_SHIFT	= 5,	/* color for workqueue flushing */
-#else
-	WORK_STRUCT_COLOR_SHIFT	= 4,	/* color for workqueue flushing */
+	WORK_STRUCT_STATIC_BIT,		/* static initializer (debugobjects) */
 #endif
+	WORK_STRUCT_FLAG_BITS,
 
+	/* color for workqueue flushing */
+	WORK_STRUCT_COLOR_SHIFT	= WORK_STRUCT_FLAG_BITS,
 	WORK_STRUCT_COLOR_BITS	= 4,
 
+	/*
+	 * When WORK_STRUCT_PWQ is set, reserve 8 bits off of pwq pointer w/
+	 * debugobjects turned off. This makes pwqs aligned to 256 bytes (512
+	 * bytes w/ DEBUG_OBJECTS_WORK) and allows 16 workqueue flush colors.
+	 *
+	 * MSB
+	 * [ pwq pointer ] [ flush color ] [ STRUCT flags ]
+	 *                     4 bits        4 or 5 bits
+	 */
+	WORK_STRUCT_PWQ_SHIFT	= WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS,
+
+	/*
+	 * data contains off-queue information when !WORK_STRUCT_PWQ.
+	 *
+	 * MSB
+	 * [ pool ID ] [ OFFQ flags ] [ STRUCT flags ]
+	 *                 1 bit        4 or 5 bits
+	 */
+	WORK_OFFQ_FLAG_SHIFT	= WORK_STRUCT_FLAG_BITS,
+	WORK_OFFQ_CANCELING_BIT = WORK_OFFQ_FLAG_SHIFT,
+	WORK_OFFQ_FLAG_END,
+	WORK_OFFQ_FLAG_BITS	= WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT,
+
+	/*
+	 * When a work item is off queue, the high bits encode off-queue flags
+	 * and the last pool it was on. Cap pool ID to 31 bits and use the
+	 * highest number to indicate that no pool is associated.
+	 */
+	WORK_OFFQ_POOL_SHIFT	= WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS,
+	WORK_OFFQ_LEFT		= BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT,
+	WORK_OFFQ_POOL_BITS	= WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31,
+};
+
+enum work_flags {
 	WORK_STRUCT_PENDING	= 1 << WORK_STRUCT_PENDING_BIT,
 	WORK_STRUCT_INACTIVE	= 1 << WORK_STRUCT_INACTIVE_BIT,
 	WORK_STRUCT_PWQ		= 1 << WORK_STRUCT_PWQ_BIT,
@@ -45,35 +79,14 @@ enum {
 #else
 	WORK_STRUCT_STATIC	= 0,
 #endif
+};
 
+enum wq_misc_consts {
 	WORK_NR_COLORS		= (1 << WORK_STRUCT_COLOR_BITS),
 
 	/* not bound to any CPU, prefer the local CPU */
 	WORK_CPU_UNBOUND	= NR_CPUS,
 
-	/*
-	 * Reserve 8 bits off of pwq pointer w/ debugobjects turned off.
-	 * This makes pwqs aligned to 256 bytes and allows 16 workqueue
-	 * flush colors.
-	 */
-	WORK_STRUCT_FLAG_BITS	= WORK_STRUCT_COLOR_SHIFT +
-				  WORK_STRUCT_COLOR_BITS,
-
-	/* data contains off-queue information when !WORK_STRUCT_PWQ */
-	WORK_OFFQ_FLAG_BASE	= WORK_STRUCT_COLOR_SHIFT,
-
-	__WORK_OFFQ_CANCELING	= WORK_OFFQ_FLAG_BASE,
-
-	/*
-	 * When a work item is off queue, its high bits point to the last
-	 * pool it was on.  Cap at 31 bits and use the highest number to
-	 * indicate that no pool is associated.
-	 */
-	WORK_OFFQ_FLAG_BITS	= 1,
-	WORK_OFFQ_POOL_SHIFT	= WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS,
-	WORK_OFFQ_LEFT		= BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT,
-	WORK_OFFQ_POOL_BITS	= WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31,
-
 	/* bit mask for work_busy() return values */
 	WORK_BUSY_PENDING	= 1 << 0,
 	WORK_BUSY_RUNNING	= 1 << 1,
@@ -83,12 +96,10 @@ enum {
 };
 
 /* Convenience constants - of type 'unsigned long', not 'enum'! */
-#define WORK_OFFQ_CANCELING	(1ul << __WORK_OFFQ_CANCELING)
+#define WORK_OFFQ_CANCELING	(1ul << WORK_OFFQ_CANCELING_BIT)
 #define WORK_OFFQ_POOL_NONE	((1ul << WORK_OFFQ_POOL_BITS) - 1)
 #define WORK_STRUCT_NO_POOL	(WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT)
-
-#define WORK_STRUCT_FLAG_MASK    ((1ul << WORK_STRUCT_FLAG_BITS) - 1)
-#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK)
+#define WORK_STRUCT_PWQ_MASK	(~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1))
 
 #define WORK_DATA_INIT()	ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL)
 #define WORK_DATA_STATIC_INIT()	\
@@ -347,7 +358,8 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; }
  * Workqueue flags and constants.  For details, please refer to
  * Documentation/core-api/workqueue.rst.
  */
-enum {
+enum wq_flags {
+	WQ_BH			= 1 << 0, /* execute in bottom half (softirq) context */
 	WQ_UNBOUND		= 1 << 1, /* not bound to any cpu */
 	WQ_FREEZABLE		= 1 << 2, /* freeze during suspend */
 	WQ_MEM_RECLAIM		= 1 << 3, /* may be used for memory reclaim */
@@ -386,11 +398,22 @@ enum {
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
-	__WQ_ORDERED_EXPLICIT	= 1 << 19, /* internal: alloc_ordered_workqueue() */
 
+	/* BH wq only allows the following flags */
+	__WQ_BH_ALLOWS		= WQ_BH | WQ_HIGHPRI,
+};
+
+enum wq_consts {
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_UNBOUND_MAX_ACTIVE	= WQ_MAX_ACTIVE,
 	WQ_DFL_ACTIVE		= WQ_MAX_ACTIVE / 2,
+
+	/*
+	 * Per-node default cap on min_active. Unless explicitly set, min_active
+	 * is set to min(max_active, WQ_DFL_MIN_ACTIVE). For more details, see
+	 * workqueue_struct->min_active definition.
+	 */
+	WQ_DFL_MIN_ACTIVE	= 8,
 };
 
 /*
@@ -420,6 +443,9 @@ enum {
  * they are same as their non-power-efficient counterparts - e.g.
  * system_power_efficient_wq is identical to system_wq if
  * 'wq_power_efficient' is disabled.  See WQ_POWER_EFFICIENT for more info.
+ *
+ * system_bh[_highpri]_wq are convenience interface to softirq. BH work items
+ * are executed in the queueing CPU's BH context in the queueing order.
  */
 extern struct workqueue_struct *system_wq;
 extern struct workqueue_struct *system_highpri_wq;
@@ -428,16 +454,43 @@ extern struct workqueue_struct *system_unbound_wq;
 extern struct workqueue_struct *system_freezable_wq;
 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;
+
+void workqueue_softirq_action(bool highpri);
+void workqueue_softirq_dead(unsigned int cpu);
 
 /**
  * alloc_workqueue - allocate a workqueue
  * @fmt: printf format for the name of the workqueue
  * @flags: WQ_* flags
- * @max_active: max in-flight work items per CPU, 0 for default
+ * @max_active: max in-flight work items, 0 for default
  * remaining args: args for @fmt
  *
- * Allocate a workqueue with the specified parameters.  For detailed
- * information on WQ_* flags, please refer to
+ * For a per-cpu workqueue, @max_active limits the number of in-flight work
+ * items for each CPU. e.g. @max_active of 1 indicates that each CPU can be
+ * executing at most one work item for the workqueue.
+ *
+ * For unbound workqueues, @max_active limits the number of in-flight work items
+ * for the whole system. e.g. @max_active of 16 indicates that that there can be
+ * at most 16 work items executing for the workqueue in the whole system.
+ *
+ * As sharing the same active counter for an unbound workqueue across multiple
+ * NUMA nodes can be expensive, @max_active is distributed to each NUMA node
+ * according to the proportion of the number of online CPUs and enforced
+ * independently.
+ *
+ * Depending on online CPU distribution, a node may end up with per-node
+ * max_active which is significantly lower than @max_active, which can lead to
+ * deadlocks if the per-node concurrency limit is lower than the maximum number
+ * of interdependent work items for the workqueue.
+ *
+ * To guarantee forward progress regardless of online CPU distribution, the
+ * concurrency limit on every node is guaranteed to be equal to or greater than
+ * min_active which is set to min(@max_active, %WQ_DFL_MIN_ACTIVE). This means
+ * that the sum of per-node max_active's may be larger than @max_active.
+ *
+ * For detailed information on %WQ_* flags, please refer to
  * Documentation/core-api/workqueue.rst.
  *
  * RETURNS:
@@ -460,8 +513,7 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 #define alloc_ordered_workqueue(fmt, flags, args...)			\
-	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED |		\
-			__WQ_ORDERED_EXPLICIT | (flags), 1, ##args)
+	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
 	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
@@ -471,6 +523,9 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
 #define create_singlethread_workqueue(name)				\
 	alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
 
+#define from_work(var, callback_work, work_fieldname)	\
+	container_of(callback_work, typeof(*var), work_fieldname)
+
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
 struct workqueue_attrs *alloc_workqueue_attrs(void);
@@ -508,6 +563,8 @@ extern bool flush_rcu_work(struct rcu_work *rwork);
 
 extern void workqueue_set_max_active(struct workqueue_struct *wq,
 				     int max_active);
+extern void workqueue_set_min_active(struct workqueue_struct *wq,
+				     int min_active);
 extern struct work_struct *current_work(void);
 extern bool current_is_workqueue_rescuer(void);
 extern bool workqueue_congested(int cpu, struct workqueue_struct *wq);

init/Kconfig

@@ -106,7 +106,7 @@ config CONSTRUCTORS
 	bool
 
 config IRQ_WORK
-	bool
+	def_bool y if SMP
 
 config BUILDTIME_TABLE_SORT
 	bool

init/main.c

@@ -1545,6 +1545,7 @@ static noinline void __init kernel_init_freeable(void)
 	sched_init_smp();
 
 	workqueue_init_topology();
+	async_init();
 	padata_init();
 	page_alloc_init_late();
 

kernel/async.c

@@ -64,6 +64,7 @@ static async_cookie_t next_cookie = 1;
 static LIST_HEAD(async_global_pending);	/* pending from all registered doms */
 static ASYNC_DOMAIN(async_dfl_domain);
 static DEFINE_SPINLOCK(async_lock);
+static struct workqueue_struct *async_wq;
 
 struct async_entry {
 	struct list_head	domain_list;
@@ -174,7 +175,7 @@ static async_cookie_t __async_schedule_node_domain(async_func_t func,
 	spin_unlock_irqrestore(&async_lock, flags);
 
 	/* schedule for execution */
-	queue_work_node(node, system_unbound_wq, &entry->work);
+	queue_work_node(node, async_wq, &entry->work);
 
 	return newcookie;
 }
@@ -345,3 +346,17 @@ bool current_is_async(void)
 	return worker && worker->current_func == async_run_entry_fn;
 }
 EXPORT_SYMBOL_GPL(current_is_async);
+
+void __init async_init(void)
+{
+	/*
+	 * Async can schedule a number of interdependent work items. However,
+	 * unbound workqueues can handle only upto min_active interdependent
+	 * work items. The default min_active of 8 isn't sufficient for async
+	 * and can lead to stalls. Let's use a dedicated workqueue with raised
+	 * min_active.
+	 */
+	async_wq = alloc_workqueue("async", WQ_UNBOUND, 0);
+	BUG_ON(!async_wq);
+	workqueue_set_min_active(async_wq, WQ_DFL_ACTIVE);
+}

kernel/softirq.c

@@ -27,6 +27,7 @@
 #include <linux/tick.h>
 #include <linux/irq.h>
 #include <linux/wait_bit.h>
+#include <linux/workqueue.h>
 
 #include <asm/softirq_stack.h>
 
@@ -802,11 +803,13 @@ static void tasklet_action_common(struct softirq_action *a,
 
 static __latent_entropy void tasklet_action(struct softirq_action *a)
 {
+	workqueue_softirq_action(false);
 	tasklet_action_common(a, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ);
 }
 
 static __latent_entropy void tasklet_hi_action(struct softirq_action *a)
 {
+	workqueue_softirq_action(true);
 	tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ);
 }
 
@@ -929,6 +932,8 @@ static void run_ksoftirqd(unsigned int cpu)
 #ifdef CONFIG_HOTPLUG_CPU
 static int takeover_tasklets(unsigned int cpu)
 {
+	workqueue_softirq_dead(cpu);
+
 	/* CPU is dead, so no lock needed. */
 	local_irq_disable();
 

rust/kernel/workqueue.rs

@@ -199,7 +199,11 @@ pub fn enqueue<W, const ID: u64>(&self, w: W) -> W::EnqueueOutput
         // stay valid until we call the function pointer in the `work_struct`, so the access is ok.
         unsafe {
             w.__enqueue(move |work_ptr| {
-                bindings::queue_work_on(bindings::WORK_CPU_UNBOUND as _, queue_ptr, work_ptr)
+                bindings::queue_work_on(
+                    bindings::wq_misc_consts_WORK_CPU_UNBOUND as _,
+                    queue_ptr,
+                    work_ptr,
+                )
             })
         }
     }

tools/workqueue/wq_dump.py

@@ -50,6 +50,7 @@ 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
 
 import argparse
@@ -75,6 +76,22 @@ def cpumask_str(cpumask):
         output += f'{v:08x}'
     return output.strip()
 
+wq_type_len = 9
+
+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.unbound_attrs.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']
@@ -82,6 +99,7 @@ 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']
@@ -92,6 +110,11 @@ WQ_AFFN_CACHE           = prog['WQ_AFFN_CACHE']
 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('===============')
 
@@ -133,10 +156,12 @@ for pi, pool in idr_for_each(worker_pool_idr):
 
 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}}] ref={pool.refcnt.value_():{max_ref_len}} nice={pool.attrs.nice.value_():3} ', end='')
+    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='')
@@ -148,24 +173,13 @@ print('')
 print('Workqueue CPU -> pool')
 print('=====================')
 
-print('[    workqueue     \     type   CPU', end='')
+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()[-24:]:24}', end='')
-    if wq.flags & WQ_UNBOUND:
-        if wq.flags & WQ_ORDERED:
-            print(' ordered   ', end='')
-        else:
-            print(' unbound', end='')
-            if wq.unbound_attrs.affn_strict:
-                print(',S ', end='')
-            else:
-                print('   ', end='')
-    else:
-        print(' percpu    ', end='')
+    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_()
@@ -175,3 +189,65 @@ for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(
     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.unbound_attrs.value_() != 0:
+        print(f' {cpumask_str(wq.unbound_attrs.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-2}}\\ min max', end='')
+    first = True
+    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('')
+
+    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_():3} {wq.max_active.value_():3}', 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='')
+        nna = wq.node_nr_active[nr_node_ids]
+        print(f' {nna.nr.counter.value_():3}/{nna.max.value_():3}')
+else:
+    printf(f'node_to_cpumask_map not present, is NUMA enabled?')