From 20bdedafd2f63e0ba70991127f9b5c0826ebdb32 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 30 Jun 2023 21:28:53 +0900 Subject: workqueue: Warn attempt to flush system-wide workqueues. Based on commit c4f135d643823a86 ("workqueue: Wrap flush_workqueue() using a macro"), all in-tree users stopped flushing system-wide workqueues. Therefore, start emitting runtime message so that all out-of-tree users will understand that they need to update their code. Signed-off-by: Tetsuo Handa Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 44 +++----------------------------------------- 1 file changed, 3 insertions(+), 41 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 683efe29fa69..1a4223cbdb5f 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -569,6 +569,7 @@ static inline bool schedule_work(struct work_struct *work) /* * Detect attempt to flush system-wide workqueues at compile time when possible. + * Warn attempt to flush system-wide workqueues at runtime. * * See https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp * for reasons and steps for converting system-wide workqueues into local workqueues. @@ -576,52 +577,13 @@ static inline bool schedule_work(struct work_struct *work) extern void __warn_flushing_systemwide_wq(void) __compiletime_warning("Please avoid flushing system-wide workqueues."); -/** - * flush_scheduled_work - ensure that any scheduled work has run to completion. - * - * Forces execution of the kernel-global workqueue and blocks until its - * completion. - * - * It's very easy to get into trouble if you don't take great care. - * Either of the following situations will lead to deadlock: - * - * One of the work items currently on the workqueue needs to acquire - * a lock held by your code or its caller. - * - * Your code is running in the context of a work routine. - * - * They will be detected by lockdep when they occur, but the first might not - * occur very often. It depends on what work items are on the workqueue and - * what locks they need, which you have no control over. - * - * In most situations flushing the entire workqueue is overkill; you merely - * need to know that a particular work item isn't queued and isn't running. - * In such cases you should use cancel_delayed_work_sync() or - * cancel_work_sync() instead. - * - * Please stop calling this function! A conversion to stop flushing system-wide - * workqueues is in progress. This function will be removed after all in-tree - * users stopped calling this function. - */ -/* - * The background of commit 771c035372a036f8 ("deprecate the - * '__deprecated' attribute warnings entirely and for good") is that, - * since Linus builds all modules between every single pull he does, - * the standard kernel build needs to be _clean_ in order to be able to - * notice when new problems happen. Therefore, don't emit warning while - * there are in-tree users. - */ +/* Please stop using this function, for this function will be removed in near future. */ #define flush_scheduled_work() \ ({ \ - if (0) \ - __warn_flushing_systemwide_wq(); \ + __warn_flushing_systemwide_wq(); \ __flush_workqueue(system_wq); \ }) -/* - * Although there is no longer in-tree caller, for now just emit warning - * in order to give out-of-tree callers time to update. - */ #define flush_workqueue(wq) \ ({ \ struct workqueue_struct *_wq = (wq); \ -- cgit v1.2.3 From 636b927eba5bc633753f8eb80f35e1d5be806e51 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 7 Aug 2023 15:57:23 -1000 Subject: workqueue: Make unbound workqueues to use per-cpu pool_workqueues A pwq (pool_workqueue) represents an association between a workqueue and a worker_pool. When a work item is queued, the workqueue selects the pwq to use, which in turn determines the pool, and queues the work item to the pool through the pwq. pwq is also what implements the maximum concurrency limit - @max_active. As a per-cpu workqueue should be assocaited with a different worker_pool on each CPU, it always had per-cpu pwq's that are accessed through wq->cpu_pwq. However, unbound workqueues were sharing a pwq within each NUMA node by default. The sharing has several downsides: * Because @max_active is per-pwq, the meaning of @max_active changes depending on the machine configuration and whether workqueue NUMA locality support is enabled. * Makes per-cpu and unbound code deviate. * Gets in the way of making workqueue CPU locality awareness more flexible. This patch makes unbound workqueues use per-cpu pwq's the same way per-cpu workqueues do by making the following changes: * wq->numa_pwq_tbl[] is removed and unbound workqueues now use wq->cpu_pwq just like per-cpu workqueues. wq->cpu_pwq is now RCU protected for unbound workqueues. * numa_pwq_tbl_install() is renamed to install_unbound_pwq() and installs the specified pwq to the target CPU's wq->cpu_pwq. * apply_wqattrs_prepare() now always allocates a separate pwq for each CPU unless the workqueue is ordered. If ordered, all CPUs use wq->dfl_pwq. This makes the return value of wq_calc_node_cpumask() unnecessary. It now returns void. * @max_active now means the same thing for both per-cpu and unbound workqueues. WQ_UNBOUND_MAX_ACTIVE now equals WQ_MAX_ACTIVE and documentation is updated accordingly. WQ_UNBOUND_MAX_ACTIVE is no longer used in workqueue implementation and will be removed later. * All unbound pwq operations which used to be per-numa-node are now per-cpu. For most unbound workqueue users, this shouldn't cause noticeable changes. Work item issue and completion will be a small bit faster, flush_workqueue() would become a bit more expensive, and the total concurrency limit would likely become higher. All @max_active==1 use cases are currently being audited for conversion into alloc_ordered_workqueue() and they shouldn't be affected once the audit and conversion is complete. One area where the behavior change may be more noticeable is workqueue_congested() as the reported congestion state is now per CPU instead of NUMA node. There are only two users of this interface - drivers/infiniband/hw/hfi1 and net/smc. Maintainers of both subsystems are cc'd. Inputs on the behavior change would be very much appreciated. Signed-off-by: Tejun Heo Acked-by: Dennis Dalessandro Cc: Jason Gunthorpe Cc: Leon Romanovsky Cc: Karsten Graul Cc: Wenjia Zhang Cc: Jan Karcher --- Documentation/core-api/workqueue.rst | 21 ++-- include/linux/workqueue.h | 8 +- kernel/workqueue.c | 218 +++++++++++++---------------------- 3 files changed, 89 insertions(+), 158 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index a4c9b9d1905f..8e541c5d8fa9 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -220,17 +220,16 @@ resources, scheduled and executed. ``max_active`` -------------- -``@max_active`` determines the maximum number of execution contexts -per CPU which can be assigned to the work items of a wq. For example, -with ``@max_active`` of 16, at most 16 work items of the wq can be -executing at the same time per CPU. - -Currently, for a bound wq, the maximum limit for ``@max_active`` is -512 and the default value used when 0 is specified is 256. For an -unbound wq, the limit is higher of 512 and 4 * -``num_possible_cpus()``. These values are chosen sufficiently high -such that they are not the limiting factor while providing protection -in runaway cases. +``@max_active`` determines the maximum number of execution contexts per +CPU which can be assigned to the work items of a wq. For example, with +``@max_active`` of 16, at most 16 work items of the wq can be executing +at the same time per CPU. This is always a per-CPU attribute, even for +unbound workqueues. + +The maximum limit for ``@max_active`` is 512 and the default value used +when 0 is specified is 256. These values are chosen sufficiently high +such that they are not the limiting factor while providing protection in +runaway cases. The number of active work items of a wq is usually regulated by the users of the wq, more specifically, by how many work items the users diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 1a4223cbdb5f..52d1a6225b44 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -343,14 +343,10 @@ enum { __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ - WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ + WQ_UNBOUND_MAX_ACTIVE = WQ_MAX_ACTIVE, WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, }; -/* unbound wq's aren't per-cpu, scale max_active according to #cpus */ -#define WQ_UNBOUND_MAX_ACTIVE \ - max_t(int, WQ_MAX_ACTIVE, num_possible_cpus() * WQ_MAX_UNBOUND_PER_CPU) - /* * System-wide workqueues which are always present. * @@ -391,7 +387,7 @@ extern struct workqueue_struct *system_freezable_power_efficient_wq; * alloc_workqueue - allocate a workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags - * @max_active: max in-flight work items, 0 for default + * @max_active: max in-flight work items per CPU, 0 for default * remaining args: args for @fmt * * Allocate a workqueue with the specified parameters. For detailed diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 9f4341885f60..48208888aee0 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -321,8 +321,7 @@ struct workqueue_struct { /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ - struct pool_workqueue __percpu **cpu_pwq; /* I: per-cpu pwqs */ - struct pool_workqueue __rcu *numa_pwq_tbl[]; /* PWR: unbound pwqs indexed by node */ + struct pool_workqueue __percpu __rcu **cpu_pwq; /* I: per-cpu pwqs */ }; static struct kmem_cache *pwq_cache; @@ -608,35 +607,6 @@ static int worker_pool_assign_id(struct worker_pool *pool) return ret; } -/** - * unbound_pwq_by_node - return the unbound pool_workqueue for the given node - * @wq: the target workqueue - * @node: the node ID - * - * This must be called with any of wq_pool_mutex, wq->mutex or RCU - * read locked. - * If the pwq needs to be used beyond the locking in effect, the caller is - * responsible for guaranteeing that the pwq stays online. - * - * Return: The unbound pool_workqueue for @node. - */ -static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq, - int node) -{ - assert_rcu_or_wq_mutex_or_pool_mutex(wq); - - /* - * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a - * delayed item is pending. The plan is to keep CPU -> NODE - * mapping valid and stable across CPU on/offlines. Once that - * happens, this workaround can be removed. - */ - if (unlikely(node == NUMA_NO_NODE)) - return wq->dfl_pwq; - - return rcu_dereference_raw(wq->numa_pwq_tbl[node]); -} - static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; @@ -1676,16 +1646,14 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, rcu_read_lock(); retry: /* pwq which will be used unless @work is executing elsewhere */ - if (wq->flags & WQ_UNBOUND) { - if (req_cpu == WORK_CPU_UNBOUND) + if (req_cpu == WORK_CPU_UNBOUND) { + if (wq->flags & WQ_UNBOUND) cpu = wq_select_unbound_cpu(raw_smp_processor_id()); - pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); - } else { - if (req_cpu == WORK_CPU_UNBOUND) + else cpu = raw_smp_processor_id(); - pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); } + pwq = rcu_dereference(*per_cpu_ptr(wq->cpu_pwq, cpu)); pool = pwq->pool; /* @@ -1715,12 +1683,11 @@ retry: } /* - * pwq is determined and locked. For unbound pools, we could have - * raced with pwq release and it could already be dead. If its - * refcnt is zero, repeat pwq selection. Note that pwqs never die - * without another pwq replacing it in the numa_pwq_tbl or while - * work items are executing on it, so the retrying is guaranteed to - * make forward-progress. + * pwq is determined and locked. For unbound pools, we could have raced + * with pwq release and it could already be dead. If its refcnt is zero, + * repeat pwq selection. Note that unbound pwqs never die without + * another pwq replacing it in cpu_pwq or while work items are executing + * on it, so the retrying is guaranteed to make forward-progress. */ if (unlikely(!pwq->refcnt)) { if (wq->flags & WQ_UNBOUND) { @@ -3818,12 +3785,8 @@ static void rcu_free_wq(struct rcu_head *rcu) container_of(rcu, struct workqueue_struct, rcu); wq_free_lockdep(wq); - - if (!(wq->flags & WQ_UNBOUND)) - free_percpu(wq->cpu_pwq); - else - free_workqueue_attrs(wq->unbound_attrs); - + free_percpu(wq->cpu_pwq); + free_workqueue_attrs(wq->unbound_attrs); kfree(wq); } @@ -4174,11 +4137,8 @@ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, * * The caller is responsible for ensuring that the cpumask of @node stays * stable. - * - * Return: %true if the resulting @cpumask is different from @attrs->cpumask, - * %false if equal. */ -static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node, +static void wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node, int cpu_going_down, cpumask_t *cpumask) { if (!wq_numa_enabled || attrs->no_numa) @@ -4195,23 +4155,18 @@ static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node, /* yeap, return possible CPUs in @node that @attrs wants */ cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]); - if (cpumask_empty(cpumask)) { + if (cpumask_empty(cpumask)) pr_warn_once("WARNING: workqueue cpumask: online intersect > " "possible intersect\n"); - return false; - } - - return !cpumask_equal(cpumask, attrs->cpumask); + return; use_dfl: cpumask_copy(cpumask, attrs->cpumask); - return false; } -/* install @pwq into @wq's numa_pwq_tbl[] for @node and return the old pwq */ -static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq, - int node, - struct pool_workqueue *pwq) +/* install @pwq into @wq's cpu_pwq and return the old pwq */ +static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq, + int cpu, struct pool_workqueue *pwq) { struct pool_workqueue *old_pwq; @@ -4221,8 +4176,8 @@ static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq, /* link_pwq() can handle duplicate calls */ link_pwq(pwq); - old_pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); - rcu_assign_pointer(wq->numa_pwq_tbl[node], pwq); + old_pwq = rcu_access_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu)); + rcu_assign_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu), pwq); return old_pwq; } @@ -4239,10 +4194,10 @@ struct apply_wqattrs_ctx { static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { if (ctx) { - int node; + int cpu; - for_each_node(node) - put_pwq_unlocked(ctx->pwq_tbl[node]); + for_each_possible_cpu(cpu) + put_pwq_unlocked(ctx->pwq_tbl[cpu]); put_pwq_unlocked(ctx->dfl_pwq); free_workqueue_attrs(ctx->attrs); @@ -4259,11 +4214,11 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, { struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs, *tmp_attrs; - int node; + int cpu; lockdep_assert_held(&wq_pool_mutex); - ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_node_ids), GFP_KERNEL); + ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_cpu_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(); tmp_attrs = alloc_workqueue_attrs(); @@ -4297,14 +4252,16 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, if (!ctx->dfl_pwq) goto out_free; - for_each_node(node) { - if (wq_calc_node_cpumask(new_attrs, node, -1, tmp_attrs->cpumask)) { - ctx->pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs); - if (!ctx->pwq_tbl[node]) - goto out_free; - } else { + for_each_possible_cpu(cpu) { + if (new_attrs->no_numa) { ctx->dfl_pwq->refcnt++; - ctx->pwq_tbl[node] = ctx->dfl_pwq; + ctx->pwq_tbl[cpu] = ctx->dfl_pwq; + } else { + wq_calc_node_cpumask(new_attrs, cpu_to_node(cpu), -1, + tmp_attrs->cpumask); + ctx->pwq_tbl[cpu] = alloc_unbound_pwq(wq, tmp_attrs); + if (!ctx->pwq_tbl[cpu]) + goto out_free; } } @@ -4327,7 +4284,7 @@ out_free: /* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) { - int node; + int cpu; /* all pwqs have been created successfully, let's install'em */ mutex_lock(&ctx->wq->mutex); @@ -4335,9 +4292,9 @@ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwq and install the new one */ - for_each_node(node) - ctx->pwq_tbl[node] = numa_pwq_tbl_install(ctx->wq, node, - ctx->pwq_tbl[node]); + for_each_possible_cpu(cpu) + ctx->pwq_tbl[cpu] = install_unbound_pwq(ctx->wq, cpu, + ctx->pwq_tbl[cpu]); /* @dfl_pwq might not have been used, ensure it's linked */ link_pwq(ctx->dfl_pwq); @@ -4466,20 +4423,13 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, cpumask = target_attrs->cpumask; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); - pwq = unbound_pwq_by_node(wq, node); - /* - * Let's determine what needs to be done. If the target cpumask is - * different from the default pwq's, we need to compare it to @pwq's - * and create a new one if they don't match. If the target cpumask - * equals the default pwq's, the default pwq should be used. - */ - if (wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, off_cpu, cpumask)) { - if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask)) - return; - } else { - goto use_dfl_pwq; - } + /* nothing to do if the target cpumask matches the current pwq */ + wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, off_cpu, cpumask); + pwq = rcu_dereference_protected(*per_cpu_ptr(wq->cpu_pwq, cpu), + lockdep_is_held(&wq_pool_mutex)); + if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask)) + return; /* create a new pwq */ pwq = alloc_unbound_pwq(wq, target_attrs); @@ -4491,7 +4441,7 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, /* Install the new pwq. */ mutex_lock(&wq->mutex); - old_pwq = numa_pwq_tbl_install(wq, node, pwq); + old_pwq = install_unbound_pwq(wq, cpu, pwq); goto out_unlock; use_dfl_pwq: @@ -4499,7 +4449,7 @@ use_dfl_pwq: raw_spin_lock_irq(&wq->dfl_pwq->pool->lock); get_pwq(wq->dfl_pwq); raw_spin_unlock_irq(&wq->dfl_pwq->pool->lock); - old_pwq = numa_pwq_tbl_install(wq, node, wq->dfl_pwq); + old_pwq = install_unbound_pwq(wq, cpu, wq->dfl_pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); @@ -4510,11 +4460,11 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) bool highpri = wq->flags & WQ_HIGHPRI; int cpu, ret; - if (!(wq->flags & WQ_UNBOUND)) { - wq->cpu_pwq = alloc_percpu(struct pool_workqueue *); - if (!wq->cpu_pwq) - goto enomem; + wq->cpu_pwq = alloc_percpu(struct pool_workqueue *); + if (!wq->cpu_pwq) + goto enomem; + if (!(wq->flags & WQ_UNBOUND)) { for_each_possible_cpu(cpu) { struct pool_workqueue **pwq_p = per_cpu_ptr(wq->cpu_pwq, cpu); @@ -4562,13 +4512,11 @@ enomem: static int wq_clamp_max_active(int max_active, unsigned int flags, const char *name) { - int lim = flags & WQ_UNBOUND ? WQ_UNBOUND_MAX_ACTIVE : WQ_MAX_ACTIVE; - - if (max_active < 1 || max_active > lim) + if (max_active < 1 || max_active > WQ_MAX_ACTIVE) pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", - max_active, name, 1, lim); + max_active, name, 1, WQ_MAX_ACTIVE); - return clamp_val(max_active, 1, lim); + return clamp_val(max_active, 1, WQ_MAX_ACTIVE); } /* @@ -4612,7 +4560,6 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...) { - size_t tbl_size = 0; va_list args; struct workqueue_struct *wq; struct pool_workqueue *pwq; @@ -4632,10 +4579,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, flags |= WQ_UNBOUND; /* allocate wq and format name */ - if (flags & WQ_UNBOUND) - tbl_size = nr_node_ids * sizeof(wq->numa_pwq_tbl[0]); - - wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL); + wq = kzalloc(sizeof(*wq), GFP_KERNEL); if (!wq) return NULL; @@ -4730,7 +4674,7 @@ static bool pwq_busy(struct pool_workqueue *pwq) void destroy_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; - int cpu, node; + int cpu; /* * Remove it from sysfs first so that sanity check failure doesn't @@ -4789,29 +4733,23 @@ void destroy_workqueue(struct workqueue_struct *wq) list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); - if (!(wq->flags & WQ_UNBOUND)) { - for_each_possible_cpu(cpu) - put_pwq_unlocked(*per_cpu_ptr(wq->cpu_pwq, cpu)); - } else { - /* - * We're the sole accessor of @wq at this point. Directly - * access numa_pwq_tbl[] and dfl_pwq to put the base refs. - * @wq will be freed when the last pwq is released. - */ - for_each_node(node) { - pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); - RCU_INIT_POINTER(wq->numa_pwq_tbl[node], NULL); - put_pwq_unlocked(pwq); - } + /* + * We're the sole accessor of @wq. Directly access cpu_pwq and dfl_pwq + * to put the base refs. @wq will be auto-destroyed from the last + * pwq_put. RCU read lock prevents @wq from going away from under us. + */ + rcu_read_lock(); - /* - * Put dfl_pwq. @wq may be freed any time after dfl_pwq is - * put. Don't access it afterwards. - */ - pwq = wq->dfl_pwq; - wq->dfl_pwq = NULL; + for_each_possible_cpu(cpu) { + pwq = rcu_access_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu)); + RCU_INIT_POINTER(*per_cpu_ptr(wq->cpu_pwq, cpu), NULL); put_pwq_unlocked(pwq); } + + put_pwq_unlocked(wq->dfl_pwq); + wq->dfl_pwq = NULL; + + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(destroy_workqueue); @@ -4888,10 +4826,11 @@ bool current_is_workqueue_rescuer(void) * unreliable and only useful as advisory hints or for debugging. * * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. - * Note that both per-cpu and unbound workqueues may be associated with - * multiple pool_workqueues which have separate congested states. A - * workqueue being congested on one CPU doesn't mean the workqueue is also - * contested on other CPUs / NUMA nodes. + * + * With the exception of ordered workqueues, all workqueues have per-cpu + * pool_workqueues, each with its own congested state. A workqueue being + * congested on one CPU doesn't mean that the workqueue is contested on any + * other CPUs. * * Return: * %true if congested, %false otherwise. @@ -4907,12 +4846,9 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); - if (!(wq->flags & WQ_UNBOUND)) - pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); - else - pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); - + pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); ret = !list_empty(&pwq->inactive_works); + preempt_enable(); rcu_read_unlock(); @@ -6434,7 +6370,7 @@ void __init workqueue_init_early(void) system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, - WQ_UNBOUND_MAX_ACTIVE); + WQ_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", -- cgit v1.2.3 From af73f5c9febe5095ee492ae43e9898fca65ced70 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 7 Aug 2023 15:57:23 -1000 Subject: workqueue: Rename workqueue_attrs->no_numa to ->ordered With the recent removal of NUMA related module param and sysfs knob, workqueue_attrs->no_numa is now only used to implement ordered workqueues. Let's rename the field so that it's less confusing especially with the planned CPU affinity awareness improvements. Just a rename. No functional changes. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 6 +++--- kernel/workqueue.c | 19 +++++++++---------- 2 files changed, 12 insertions(+), 13 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 52d1a6225b44..f0c10f491b15 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -142,13 +142,13 @@ struct workqueue_attrs { cpumask_var_t cpumask; /** - * @no_numa: disable NUMA affinity + * @ordered: work items must be executed one by one in queueing order * - * Unlike other fields, ``no_numa`` isn't a property of a worker_pool. It + * Unlike other fields, ``ordered`` isn't a property of a worker_pool. It * only modifies how :c:func:`apply_workqueue_attrs` select pools and thus * doesn't participate in pool hash calculations or equality comparisons. */ - bool no_numa; + bool ordered; }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 48208888aee0..82413df1c120 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3672,10 +3672,10 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, cpumask_copy(to->cpumask, from->cpumask); /* * Unlike hash and equality test, this function doesn't ignore - * ->no_numa as it is used for both pool and wq attrs. Instead, - * get_unbound_pool() explicitly clears ->no_numa after copying. + * ->ordered as it is used for both pool and wq attrs. Instead, + * get_unbound_pool() explicitly clears ->ordered after copying. */ - to->no_numa = from->no_numa; + to->ordered = from->ordered; } /* hash value of the content of @attr */ @@ -3933,10 +3933,10 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) pool->node = target_node; /* - * no_numa isn't a worker_pool attribute, always clear it. See + * ordered isn't a worker_pool attribute, always clear it. See * 'struct workqueue_attrs' comments for detail. */ - pool->attrs->no_numa = false; + pool->attrs->ordered = false; if (worker_pool_assign_id(pool) < 0) goto fail; @@ -4141,7 +4141,7 @@ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, static void wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node, int cpu_going_down, cpumask_t *cpumask) { - if (!wq_numa_enabled || attrs->no_numa) + if (!wq_numa_enabled || attrs->ordered) goto use_dfl; /* does @node have any online CPUs @attrs wants? */ @@ -4253,7 +4253,7 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, goto out_free; for_each_possible_cpu(cpu) { - if (new_attrs->no_numa) { + if (new_attrs->ordered) { ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[cpu] = ctx->dfl_pwq; } else { @@ -4411,7 +4411,7 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, lockdep_assert_held(&wq_pool_mutex); if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND) || - wq->unbound_attrs->no_numa) + wq->unbound_attrs->ordered) return; /* @@ -6358,11 +6358,10 @@ void __init workqueue_init_early(void) /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. - * Turn off NUMA so that dfl_pwq is used for all nodes. */ BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; - attrs->no_numa = true; + attrs->ordered = true; ordered_wq_attrs[i] = attrs; } -- cgit v1.2.3 From 2930155b2e27232c033970f2e110aaac4187cb9e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 7 Aug 2023 15:57:24 -1000 Subject: workqueue: Initialize unbound CPU pods later in the boot During boot, to initialize unbound CPU pods, wq_pod_init() was called from workqueue_init(). This is early enough for NUMA nodes to be set up but before SMP is brought up and CPU topology information is populated. Workqueue is in the process of improving CPU locality for unbound workqueues and will need access to topology information during pod init. This adds a new init function workqueue_init_topology() which is called after CPU topology information is available and replaces wq_pod_init(). As unbound CPU pods are now initialized after workqueues are activated, we need to revisit the workqueues to apply the pod configuration. Workqueues which are created before workqueue_init_topology() are set up so that they always use the default worker pool. After pods are set up in workqueue_init_topology(), wq_update_pod() is called on all existing workqueues to update the pool associations accordingly. Note that wq_update_pod_attrs_buf allocation is moved to workqueue_init_early(). This isn't necessary right now but enables further generalization of pod handling in the future. This patch changes the initialization sequence but the end result should be the same. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 1 + init/main.c | 1 + kernel/workqueue.c | 68 ++++++++++++++++++++++++++++------------------- 3 files changed, 43 insertions(+), 27 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index f0c10f491b15..bab9fa3453ed 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -672,5 +672,6 @@ int workqueue_offline_cpu(unsigned int cpu); void __init workqueue_init_early(void); void __init workqueue_init(void); +void __init workqueue_init_topology(void); #endif diff --git a/init/main.c b/init/main.c index ad920fac325c..436d73261810 100644 --- a/init/main.c +++ b/init/main.c @@ -1540,6 +1540,7 @@ static noinline void __init kernel_init_freeable(void) smp_init(); sched_init_smp(); + workqueue_init_topology(); padata_init(); page_alloc_init_late(); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 1e528b7e12c5..5914c820a4f1 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -6256,17 +6256,15 @@ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ -static void wq_pod_init(void); - /** * workqueue_init_early - early init for workqueue subsystem * - * This is the first half of two-staged workqueue subsystem initialization - * and invoked as soon as the bare basics - memory allocation, cpumasks and - * idr are up. It sets up all the data structures and system workqueues - * and allows early boot code to create workqueues and queue/cancel work - * items. Actual work item execution starts only after kthreads can be - * created and scheduled right before early initcalls. + * This is the first step of three-staged workqueue subsystem initialization and + * invoked as soon as the bare basics - memory allocation, cpumasks and idr are + * up. It sets up all the data structures and system workqueues and allows early + * boot code to create workqueues and queue/cancel work items. Actual work item + * execution starts only after kthreads can be created and scheduled right + * before early initcalls. */ void __init workqueue_init_early(void) { @@ -6284,6 +6282,9 @@ void __init workqueue_init_early(void) pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); + wq_update_pod_attrs_buf = alloc_workqueue_attrs(); + BUG_ON(!wq_update_pod_attrs_buf); + /* initialize CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; @@ -6381,11 +6382,11 @@ static void __init wq_cpu_intensive_thresh_init(void) /** * workqueue_init - bring workqueue subsystem fully online * - * This is the latter half of two-staged workqueue subsystem initialization - * and invoked as soon as kthreads can be created and scheduled. - * Workqueues have been created and work items queued on them, but there - * are no kworkers executing the work items yet. Populate the worker pools - * with the initial workers and enable future kworker creations. + * This is the second step of three-staged workqueue subsystem initialization + * and invoked as soon as kthreads can be created and scheduled. Workqueues have + * been created and work items queued on them, but there are no kworkers + * executing the work items yet. Populate the worker pools with the initial + * workers and enable future kworker creations. */ void __init workqueue_init(void) { @@ -6395,18 +6396,12 @@ void __init workqueue_init(void) wq_cpu_intensive_thresh_init(); - /* - * It'd be simpler to initialize pods in workqueue_init_early() but CPU - * to node mapping may not be available that early on some archs such as - * power and arm64. As per-cpu pools created previously could be missing - * node hint and unbound pool pod affinity, fix them up. - * - * Also, while iterating workqueues, create rescuers if requested. - */ - wq_pod_init(); - mutex_lock(&wq_pool_mutex); + /* + * Per-cpu pools created earlier could be missing node hint. Fix them + * up. Also, create a rescuer for workqueues that requested it. + */ for_each_possible_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->node = cpu_to_node(cpu); @@ -6414,7 +6409,6 @@ void __init workqueue_init(void) } list_for_each_entry(wq, &workqueues, list) { - wq_update_pod(wq, smp_processor_id(), smp_processor_id(), true); WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); @@ -6437,8 +6431,16 @@ void __init workqueue_init(void) wq_watchdog_init(); } -static void __init wq_pod_init(void) +/** + * workqueue_init_topology - initialize CPU pods for unbound workqueues + * + * This is the third step of there-staged workqueue subsystem initialization and + * invoked after SMP and topology information are fully initialized. It + * initializes the unbound CPU pods accordingly. + */ +void __init workqueue_init_topology(void) { + struct workqueue_struct *wq; cpumask_var_t *tbl; int node, cpu; @@ -6452,8 +6454,7 @@ static void __init wq_pod_init(void) } } - wq_update_pod_attrs_buf = alloc_workqueue_attrs(); - BUG_ON(!wq_update_pod_attrs_buf); + mutex_lock(&wq_pool_mutex); /* * We want masks of possible CPUs of each node which isn't readily @@ -6474,6 +6475,19 @@ static void __init wq_pod_init(void) wq_pod_cpus = tbl; wq_pod_enabled = true; + + /* + * Workqueues allocated earlier would have all CPUs sharing the default + * worker pool. Explicitly call wq_update_pod() on all workqueue and CPU + * combinations to apply per-pod sharing. + */ + list_for_each_entry(wq, &workqueues, list) { + for_each_online_cpu(cpu) { + wq_update_pod(wq, cpu, cpu, true); + } + } + + mutex_unlock(&wq_pool_mutex); } void __warn_flushing_systemwide_wq(void) -- cgit v1.2.3 From 84193c07105c62d206fb230b2f29002226628989 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 7 Aug 2023 15:57:24 -1000 Subject: workqueue: Generalize unbound CPU pods While renamed to pod, the code still assumes that the pods are defined by NUMA boundaries. Let's generalize it: * workqueue_attrs->affn_scope is added. Each enum represents the type of boundaries that define the pods. There are currently two scopes - WQ_AFFN_NUMA and WQ_AFFN_SYSTEM. The former is the same behavior as before - one pod per NUMA node. The latter defines one global pod across the whole system. * struct wq_pod_type is added which describes how pods are configured for each affnity scope. For each pod, it lists the member CPUs and the preferred NUMA node for memory allocations. The reverse mapping from CPU to pod is also available. * wq_pod_enabled is dropped. Pod is now always enabled. The previously disabled behavior is now implemented through WQ_AFFN_SYSTEM. * get_unbound_pool() wants to determine the NUMA node to allocate memory from for the new pool. The variables are renamed from node to pod but the logic still assumes they're one and the same. Clearly distinguish them - walk the WQ_AFFN_NUMA pods to find the matching pod and then use the pod's NUMA node. * wq_calc_pod_cpumask() was taking @pod but assumed that it was the NUMA node. Take @cpu instead and determine the cpumask to use from the pod_type matching @attrs. * apply_wqattrs_prepare() is update to return ERR_PTR() on error instead of NULL so that it can indicate -EINVAL on invalid affinity scopes. This patch allows CPUs to be grouped into pods however desired per type. While this patch causes some internal behavior changes, nothing material should change for workqueue users. v2: Trigger WARN_ON_ONCE() in wqattrs_pod_type() if affn_scope is WQ_AFFN_NR_TYPES which indicates that the function is called with a worker_pool's attrs instead of a workqueue's. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 31 +++++++-- kernel/workqueue.c | 171 +++++++++++++++++++++++++++++----------------- 2 files changed, 137 insertions(+), 65 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index bab9fa3453ed..180491ee6706 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -125,6 +125,15 @@ struct rcu_work { struct workqueue_struct *wq; }; +enum wq_affn_scope { + WQ_AFFN_NUMA, /* one pod per NUMA node */ + WQ_AFFN_SYSTEM, /* one pod across the whole system */ + + WQ_AFFN_NR_TYPES, + + WQ_AFFN_DFL = WQ_AFFN_NUMA, +}; + /** * struct workqueue_attrs - A struct for workqueue attributes. * @@ -141,12 +150,26 @@ struct workqueue_attrs { */ cpumask_var_t cpumask; + /* + * Below fields aren't properties of a worker_pool. They only modify how + * :c:func:`apply_workqueue_attrs` select pools and thus don't + * participate in pool hash calculations or equality comparisons. + */ + /** - * @ordered: work items must be executed one by one in queueing order + * @affn_scope: unbound CPU affinity scope * - * Unlike other fields, ``ordered`` isn't a property of a worker_pool. It - * only modifies how :c:func:`apply_workqueue_attrs` select pools and thus - * doesn't participate in pool hash calculations or equality comparisons. + * CPU pods are used to improve execution locality of unbound work + * items. There are multiple pod types, one for each wq_affn_scope, and + * every CPU in the system belongs to one pod in every pod type. CPUs + * that belong to the same pod share the worker pool. For example, + * selecting %WQ_AFFN_NUMA makes the workqueue use a separate worker + * pool for each NUMA node. + */ + enum wq_affn_scope affn_scope; + + /** + * @ordered: work items must be executed one by one in queueing order */ bool ordered; }; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 37eab7a1587d..6c4d7b1fdf9a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -326,7 +326,18 @@ struct workqueue_struct { static struct kmem_cache *pwq_cache; -static cpumask_var_t *wq_pod_cpus; /* possible CPUs of each node */ +/* + * Each pod type describes how CPUs should be grouped for unbound workqueues. + * See the comment above workqueue_attrs->affn_scope. + */ +struct wq_pod_type { + int nr_pods; /* number of pods */ + cpumask_var_t *pod_cpus; /* pod -> cpus */ + int *pod_node; /* pod -> node */ + int *cpu_pod; /* cpu -> pod */ +}; + +static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES]; /* * Per-cpu work items which run for longer than the following threshold are @@ -344,8 +355,6 @@ module_param_named(power_efficient, wq_power_efficient, bool, 0444); static bool wq_online; /* can kworkers be created yet? */ -static bool wq_pod_enabled; /* unbound CPU pod affinity enabled */ - /* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *wq_update_pod_attrs_buf; static cpumask_var_t wq_update_pod_cpumask_buf; @@ -1774,10 +1783,6 @@ static int select_numa_node_cpu(int node) { int cpu; - /* No point in doing this if NUMA isn't enabled for workqueues */ - if (!wq_pod_enabled) - return WORK_CPU_UNBOUND; - /* Delay binding to CPU if node is not valid or online */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) return WORK_CPU_UNBOUND; @@ -3659,6 +3664,7 @@ struct workqueue_attrs *alloc_workqueue_attrs(void) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); + attrs->affn_scope = WQ_AFFN_DFL; return attrs; fail: free_workqueue_attrs(attrs); @@ -3670,11 +3676,13 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); + /* - * Unlike hash and equality test, this function doesn't ignore - * ->ordered as it is used for both pool and wq attrs. Instead, - * get_unbound_pool() explicitly clears ->ordered after copying. + * Unlike hash and equality test, copying shouldn't ignore wq-only + * fields as copying is used for both pool and wq attrs. Instead, + * get_unbound_pool() explicitly clears the fields. */ + to->affn_scope = from->affn_scope; to->ordered = from->ordered; } @@ -3684,6 +3692,7 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, */ static void wqattrs_clear_for_pool(struct workqueue_attrs *attrs) { + attrs->affn_scope = WQ_AFFN_NR_TYPES; attrs->ordered = false; } @@ -3723,6 +3732,25 @@ static void wqattrs_actualize_cpumask(struct workqueue_attrs *attrs, cpumask_copy(attrs->cpumask, unbound_cpumask); } +/* find wq_pod_type to use for @attrs */ +static const struct wq_pod_type * +wqattrs_pod_type(const struct workqueue_attrs *attrs) +{ + struct wq_pod_type *pt = &wq_pod_types[attrs->affn_scope]; + + if (!WARN_ON_ONCE(attrs->affn_scope == WQ_AFFN_NR_TYPES) && + likely(pt->nr_pods)) + return pt; + + /* + * Before workqueue_init_topology(), only SYSTEM is available which is + * initialized in workqueue_init_early(). + */ + pt = &wq_pod_types[WQ_AFFN_SYSTEM]; + BUG_ON(!pt->nr_pods); + return pt; +} + /** * init_worker_pool - initialize a newly zalloc'd worker_pool * @pool: worker_pool to initialize @@ -3924,10 +3952,10 @@ static void put_unbound_pool(struct worker_pool *pool) */ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) { + struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_NUMA]; u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; - int pod; - int target_pod = NUMA_NO_NODE; + int pod, node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); @@ -3939,23 +3967,20 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) } } - /* if cpumask is contained inside a pod, we belong to that pod */ - if (wq_pod_enabled) { - for_each_node(pod) { - if (cpumask_subset(attrs->cpumask, wq_pod_cpus[pod])) { - target_pod = pod; - break; - } + /* If cpumask is contained inside a NUMA pod, that's our NUMA node */ + for (pod = 0; pod < pt->nr_pods; pod++) { + if (cpumask_subset(attrs->cpumask, pt->pod_cpus[pod])) { + node = pt->pod_node[pod]; + break; } } /* nope, create a new one */ - pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, target_pod); + pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, node); if (!pool || init_worker_pool(pool) < 0) goto fail; - pool->node = target_pod; - + pool->node = node; copy_workqueue_attrs(pool->attrs, attrs); wqattrs_clear_for_pool(pool->attrs); @@ -4143,7 +4168,7 @@ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, /** * wq_calc_pod_cpumask - calculate a wq_attrs' cpumask for a pod * @attrs: the wq_attrs of the default pwq of the target workqueue - * @pod: the target CPU pod + * @cpu: the target CPU * @cpu_going_down: if >= 0, the CPU to consider as offline * @cpumask: outarg, the resulting cpumask * @@ -4157,30 +4182,29 @@ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, * * The caller is responsible for ensuring that the cpumask of @pod stays stable. */ -static void wq_calc_pod_cpumask(const struct workqueue_attrs *attrs, int pod, - int cpu_going_down, cpumask_t *cpumask) +static void wq_calc_pod_cpumask(const struct workqueue_attrs *attrs, int cpu, + int cpu_going_down, cpumask_t *cpumask) { - if (!wq_pod_enabled || attrs->ordered) - goto use_dfl; + const struct wq_pod_type *pt = wqattrs_pod_type(attrs); + int pod = pt->cpu_pod[cpu]; /* does @pod have any online CPUs @attrs wants? */ - cpumask_and(cpumask, cpumask_of_node(pod), attrs->cpumask); + cpumask_and(cpumask, pt->pod_cpus[pod], attrs->cpumask); + cpumask_and(cpumask, cpumask, cpu_online_mask); if (cpu_going_down >= 0) cpumask_clear_cpu(cpu_going_down, cpumask); - if (cpumask_empty(cpumask)) - goto use_dfl; + if (cpumask_empty(cpumask)) { + cpumask_copy(cpumask, attrs->cpumask); + return; + } /* yeap, return possible CPUs in @pod that @attrs wants */ - cpumask_and(cpumask, attrs->cpumask, wq_pod_cpus[pod]); + cpumask_and(cpumask, attrs->cpumask, pt->pod_cpus[pod]); if (cpumask_empty(cpumask)) pr_warn_once("WARNING: workqueue cpumask: online intersect > " "possible intersect\n"); - return; - -use_dfl: - cpumask_copy(cpumask, attrs->cpumask); } /* install @pwq into @wq's cpu_pwq and return the old pwq */ @@ -4237,6 +4261,10 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, lockdep_assert_held(&wq_pool_mutex); + if (WARN_ON(attrs->affn_scope < 0 || + attrs->affn_scope >= WQ_AFFN_NR_TYPES)) + return ERR_PTR(-EINVAL); + ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_cpu_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(); @@ -4266,8 +4294,7 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[cpu] = ctx->dfl_pwq; } else { - wq_calc_pod_cpumask(new_attrs, cpu_to_node(cpu), -1, - tmp_attrs->cpumask); + wq_calc_pod_cpumask(new_attrs, cpu, -1, tmp_attrs->cpumask); ctx->pwq_tbl[cpu] = alloc_unbound_pwq(wq, tmp_attrs); if (!ctx->pwq_tbl[cpu]) goto out_free; @@ -4287,7 +4314,7 @@ out_free: free_workqueue_attrs(tmp_attrs); free_workqueue_attrs(new_attrs); apply_wqattrs_cleanup(ctx); - return NULL; + return ERR_PTR(-ENOMEM); } /* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ @@ -4343,8 +4370,8 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, } ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask); - if (!ctx) - return -ENOMEM; + if (IS_ERR(ctx)) + return PTR_ERR(ctx); /* the ctx has been prepared successfully, let's commit it */ apply_wqattrs_commit(ctx); @@ -4409,7 +4436,6 @@ int apply_workqueue_attrs(struct workqueue_struct *wq, static void wq_update_pod(struct workqueue_struct *wq, int cpu, int hotplug_cpu, bool online) { - int pod = cpu_to_node(cpu); int off_cpu = online ? -1 : hotplug_cpu; struct pool_workqueue *old_pwq = NULL, *pwq; struct workqueue_attrs *target_attrs; @@ -4417,8 +4443,7 @@ static void wq_update_pod(struct workqueue_struct *wq, int cpu, lockdep_assert_held(&wq_pool_mutex); - if (!wq_pod_enabled || !(wq->flags & WQ_UNBOUND) || - wq->unbound_attrs->ordered) + if (!(wq->flags & WQ_UNBOUND) || wq->unbound_attrs->ordered) return; /* @@ -4433,7 +4458,7 @@ static void wq_update_pod(struct workqueue_struct *wq, int cpu, wqattrs_actualize_cpumask(target_attrs, wq_unbound_cpumask); /* nothing to do if the target cpumask matches the current pwq */ - wq_calc_pod_cpumask(target_attrs, pod, off_cpu, cpumask); + wq_calc_pod_cpumask(target_attrs, cpu, off_cpu, cpumask); pwq = rcu_dereference_protected(*per_cpu_ptr(wq->cpu_pwq, cpu), lockdep_is_held(&wq_pool_mutex)); if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask)) @@ -5460,12 +5485,14 @@ int workqueue_online_cpu(unsigned int cpu) /* update pod affinity of unbound workqueues */ list_for_each_entry(wq, &workqueues, list) { - int tcpu; + struct workqueue_attrs *attrs = wq->unbound_attrs; + + if (attrs) { + const struct wq_pod_type *pt = wqattrs_pod_type(attrs); + int tcpu; - for_each_possible_cpu(tcpu) { - if (cpu_to_node(tcpu) == cpu_to_node(cpu)) { + for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) wq_update_pod(wq, tcpu, cpu, true); - } } } @@ -5486,12 +5513,14 @@ int workqueue_offline_cpu(unsigned int cpu) /* update pod affinity of unbound workqueues */ mutex_lock(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { - int tcpu; + struct workqueue_attrs *attrs = wq->unbound_attrs; + + if (attrs) { + const struct wq_pod_type *pt = wqattrs_pod_type(attrs); + int tcpu; - for_each_possible_cpu(tcpu) { - if (cpu_to_node(tcpu) == cpu_to_node(cpu)) { + for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) wq_update_pod(wq, tcpu, cpu, false); - } } } mutex_unlock(&wq_pool_mutex); @@ -5689,8 +5718,8 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) continue; ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); - if (!ctx) { - ret = -ENOMEM; + if (IS_ERR(ctx)) { + ret = PTR_ERR(ctx); break; } @@ -6283,6 +6312,7 @@ static inline void wq_watchdog_init(void) { } */ void __init workqueue_init_early(void) { + struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM]; int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; int i, cpu; @@ -6302,6 +6332,22 @@ void __init workqueue_init_early(void) BUG_ON(!alloc_cpumask_var(&wq_update_pod_cpumask_buf, GFP_KERNEL)); + /* initialize WQ_AFFN_SYSTEM pods */ + pt->pod_cpus = kcalloc(1, sizeof(pt->pod_cpus[0]), GFP_KERNEL); + pt->pod_node = kcalloc(1, sizeof(pt->pod_node[0]), GFP_KERNEL); + pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL); + BUG_ON(!pt->pod_cpus || !pt->pod_node || !pt->cpu_pod); + + BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE)); + + wq_update_pod_attrs_buf = alloc_workqueue_attrs(); + BUG_ON(!wq_update_pod_attrs_buf); + + pt->nr_pods = 1; + cpumask_copy(pt->pod_cpus[0], cpu_possible_mask); + pt->pod_node[0] = NUMA_NO_NODE; + pt->cpu_pod[0] = 0; + /* initialize CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; @@ -6457,8 +6503,8 @@ void __init workqueue_init(void) */ void __init workqueue_init_topology(void) { + struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_NUMA]; struct workqueue_struct *wq; - cpumask_var_t *tbl; int node, cpu; if (num_possible_nodes() <= 1) @@ -6478,20 +6524,23 @@ void __init workqueue_init_topology(void) * available. Build one from cpu_to_node() which should have been * fully initialized by now. */ - tbl = kcalloc(nr_node_ids, sizeof(tbl[0]), GFP_KERNEL); - BUG_ON(!tbl); + pt->pod_cpus = kcalloc(nr_node_ids, sizeof(pt->pod_cpus[0]), GFP_KERNEL); + pt->pod_node = kcalloc(nr_node_ids, sizeof(pt->pod_node[0]), GFP_KERNEL); + pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL); + BUG_ON(!pt->pod_cpus || !pt->pod_node || !pt->cpu_pod); for_each_node(node) - BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL, + BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[node], GFP_KERNEL, node_online(node) ? node : NUMA_NO_NODE)); for_each_possible_cpu(cpu) { node = cpu_to_node(cpu); - cpumask_set_cpu(cpu, tbl[node]); + cpumask_set_cpu(cpu, pt->pod_cpus[node]); + pt->pod_node[node] = node; + pt->cpu_pod[cpu] = node; } - wq_pod_cpus = tbl; - wq_pod_enabled = true; + pt->nr_pods = nr_node_ids; /* * Workqueues allocated earlier would have all CPUs sharing the default -- cgit v1.2.3 From 63c5484e74952f60f5810256bd69814d167b8d22 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 7 Aug 2023 15:57:24 -1000 Subject: workqueue: Add multiple affinity scopes and interface to select them Add three more affinity scopes - WQ_AFFN_CPU, SMT and CACHE - and make CACHE the default. The code changes to actually add the additional scopes are trivial. Also add module parameter "workqueue.default_affinity_scope" to override the default scope and "affinity_scope" sysfs file to configure it per workqueue. wq_dump.py and documentations are updated accordingly. This enables significant flexibility in configuring how unbound workqueues behave. If affinity scope is set to "cpu", it'll behave close to a per-cpu workqueue. On the other hand, "system" removes all locality boundaries. Many modern machines have multiple L3 caches often while being mostly uniform in terms of memory access. Thus, workqueue's previous behavior of spreading work items in each NUMA node had negative performance implications from unncessarily crossing L3 boundaries between issue and execution. However, picking a finer grained affinity scope also has a downside in that an issuer in one group can't utilize CPUs in other groups. While dependent on the specifics of workload, there's usually a noticeable penalty in crossing L3 boundaries, so let's default to CACHE. This issue will be further addressed and documented with examples in future patches. Signed-off-by: Tejun Heo --- Documentation/admin-guide/kernel-parameters.txt | 12 +++ Documentation/core-api/workqueue.rst | 63 ++++++++++++++ include/linux/workqueue.h | 5 +- kernel/workqueue.c | 110 ++++++++++++++++++++++-- tools/workqueue/wq_dump.py | 15 ++-- 5 files changed, 193 insertions(+), 12 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 2b89cbc39713..732c5c7e3fa5 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -7007,6 +7007,18 @@ The default value of this parameter is determined by the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT. + 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 + information, see the Affinity Scopes section in + Documentation/core-api/workqueue.rst. + + This can be updated after boot through the matching + file under /sys/module/workqueue/parameters. + However, the changed default will only apply to + unbound workqueues created afterwards. + workqueue.debug_force_rr_cpu Workqueue used to implicitly guarantee that work items queued without explicit CPU specified are put diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index c9e46acd339b..56af317508c9 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -347,6 +347,51 @@ Guidelines level of locality in wq operations and work item execution. +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 processed by a +worker running on one of the CPUs which share the last level cache with the +issuing CPU. + +Workqueue currently supports the following five affinity scopes. + +``cpu`` + CPUs are not grouped. A work item issued on one CPU is processed by a + worker on the same CPU. This makes unbound workqueues behave as per-cpu + workqueues without concurrency management. + +``smt`` + CPUs are grouped according to SMT boundaries. This usually means that the + logical threads of each physical CPU core are grouped together. + +``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. + +``numa`` + CPUs are grouped according to NUMA bounaries. + +``system`` + All CPUs are put in the same group. Workqueue makes no effort to process a + work item on a CPU close to the issuing CPU. + +The default affinity scope can be changed with the module parameter +``workqueue.default_affinity_scope`` and a specific workqueue's affinity +scope can be changed using ``apply_workqueue_attrs()``. + +If ``WQ_SYSFS`` is set, the workqueue will have the following affinity scope +related interface files under its ``/sys/devices/virtual/WQ_NAME/`` +directory. + +``affinity_scope`` + Read to see the current affinity scope. Write to change. + + Examining Configuration ======================= @@ -358,6 +403,24 @@ configuration, worker pools and how workqueues map to the pools: :: =============== wq_unbound_cpumask=0000000f + CPU + nr_pods 4 + pod_cpus [0]=00000001 [1]=00000002 [2]=00000004 [3]=00000008 + pod_node [0]=0 [1]=0 [2]=1 [3]=1 + cpu_pod [0]=0 [1]=1 [2]=2 [3]=3 + + SMT + nr_pods 4 + pod_cpus [0]=00000001 [1]=00000002 [2]=00000004 [3]=00000008 + pod_node [0]=0 [1]=0 [2]=1 [3]=1 + cpu_pod [0]=0 [1]=1 [2]=2 [3]=3 + + CACHE (default) + nr_pods 2 + pod_cpus [0]=00000003 [1]=0000000c + pod_node [0]=0 [1]=1 + cpu_pod [0]=0 [1]=0 [2]=1 [3]=1 + NUMA nr_pods 2 pod_cpus [0]=00000003 [1]=0000000c diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 180491ee6706..568cfbc24bc0 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -126,12 +126,15 @@ struct rcu_work { }; enum wq_affn_scope { + WQ_AFFN_CPU, /* one pod per CPU */ + WQ_AFFN_SMT, /* one pod poer SMT */ + WQ_AFFN_CACHE, /* one pod per LLC */ WQ_AFFN_NUMA, /* one pod per NUMA node */ WQ_AFFN_SYSTEM, /* one pod across the whole system */ WQ_AFFN_NR_TYPES, - WQ_AFFN_DFL = WQ_AFFN_NUMA, + WQ_AFFN_DFL = WQ_AFFN_CACHE, }; /** diff --git a/kernel/workqueue.c b/kernel/workqueue.c index a2cc0432abd5..8e3a499c3f00 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -338,6 +338,15 @@ struct wq_pod_type { }; static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES]; +static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_DFL; + +static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = { + [WQ_AFFN_CPU] = "cpu", + [WQ_AFFN_SMT] = "smt", + [WQ_AFFN_CACHE] = "cache", + [WQ_AFFN_NUMA] = "numa", + [WQ_AFFN_SYSTEM] = "system", +}; /* * Per-cpu work items which run for longer than the following threshold are @@ -3664,7 +3673,7 @@ struct workqueue_attrs *alloc_workqueue_attrs(void) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); - attrs->affn_scope = WQ_AFFN_DFL; + attrs->affn_scope = wq_affn_dfl; return attrs; fail: free_workqueue_attrs(attrs); @@ -5777,19 +5786,55 @@ out_unlock: return ret; } +static int parse_affn_scope(const char *val) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(wq_affn_names); i++) { + if (!strncasecmp(val, wq_affn_names[i], strlen(wq_affn_names[i]))) + return i; + } + return -EINVAL; +} + +static int wq_affn_dfl_set(const char *val, const struct kernel_param *kp) +{ + int affn; + + affn = parse_affn_scope(val); + if (affn < 0) + return affn; + + wq_affn_dfl = affn; + return 0; +} + +static int wq_affn_dfl_get(char *buffer, const struct kernel_param *kp) +{ + return scnprintf(buffer, PAGE_SIZE, "%s\n", wq_affn_names[wq_affn_dfl]); +} + +static const struct kernel_param_ops wq_affn_dfl_ops = { + .set = wq_affn_dfl_set, + .get = wq_affn_dfl_get, +}; + +module_param_cb(default_affinity_scope, &wq_affn_dfl_ops, NULL, 0644); + #ifdef CONFIG_SYSFS /* * Workqueues with WQ_SYSFS flag set is visible to userland via * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the * following attributes. * - * per_cpu RO bool : whether the workqueue is per-cpu or unbound - * max_active RW int : maximum number of in-flight work items + * per_cpu RO bool : whether the workqueue is per-cpu or unbound + * max_active RW int : maximum number of in-flight work items * * Unbound workqueues have the following extra attributes. * - * nice RW int : nice value of the workers - * cpumask RW mask : bitmask of allowed CPUs for the workers + * nice RW int : nice value of the workers + * cpumask RW mask : bitmask of allowed CPUs for the workers + * affinity_scope RW str : worker CPU affinity scope (cache, numa, none) */ struct wq_device { struct workqueue_struct *wq; @@ -5932,9 +5977,47 @@ out_unlock: return ret ?: count; } +static ssize_t wq_affn_scope_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + int written; + + mutex_lock(&wq->mutex); + written = scnprintf(buf, PAGE_SIZE, "%s\n", + wq_affn_names[wq->unbound_attrs->affn_scope]); + mutex_unlock(&wq->mutex); + + return written; +} + +static ssize_t wq_affn_scope_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct workqueue_attrs *attrs; + int affn, ret = -ENOMEM; + + affn = parse_affn_scope(buf); + if (affn < 0) + return affn; + + apply_wqattrs_lock(); + attrs = wq_sysfs_prep_attrs(wq); + if (attrs) { + attrs->affn_scope = affn; + ret = apply_workqueue_attrs_locked(wq, attrs); + } + apply_wqattrs_unlock(); + free_workqueue_attrs(attrs); + return ret ?: count; +} + static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), + __ATTR(affinity_scope, 0644, wq_affn_scope_show, wq_affn_scope_store), __ATTR_NULL, }; @@ -6537,6 +6620,20 @@ static void __init init_pod_type(struct wq_pod_type *pt, } } +static bool __init cpus_dont_share(int cpu0, int cpu1) +{ + return false; +} + +static bool __init cpus_share_smt(int cpu0, int cpu1) +{ +#ifdef CONFIG_SCHED_SMT + return cpumask_test_cpu(cpu0, cpu_smt_mask(cpu1)); +#else + return false; +#endif +} + static bool __init cpus_share_numa(int cpu0, int cpu1) { return cpu_to_node(cpu0) == cpu_to_node(cpu1); @@ -6554,6 +6651,9 @@ void __init workqueue_init_topology(void) struct workqueue_struct *wq; int cpu; + init_pod_type(&wq_pod_types[WQ_AFFN_CPU], cpus_dont_share); + init_pod_type(&wq_pod_types[WQ_AFFN_SMT], cpus_share_smt); + init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache); init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa); mutex_lock(&wq_pool_mutex); diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py index ddd0bb4395ea..43ab71a193b8 100644 --- a/tools/workqueue/wq_dump.py +++ b/tools/workqueue/wq_dump.py @@ -78,11 +78,16 @@ 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_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_NUMA = prog['WQ_AFFN_NUMA'] WQ_AFFN_SYSTEM = prog['WQ_AFFN_SYSTEM'] @@ -109,12 +114,10 @@ def print_pod_type(pt): print(f' [{cpu}]={pt.cpu_pod[cpu].value_()}', end='') print('') -print('') -print('NUMA') -print_pod_type(wq_pod_types[WQ_AFFN_NUMA]) -print('') -print('SYSTEM') -print_pod_type(wq_pod_types[WQ_AFFN_SYSTEM]) +for affn in [WQ_AFFN_CPU, WQ_AFFN_SMT, WQ_AFFN_CACHE, 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') -- cgit v1.2.3 From 9546b29e4a6ad6ed7924dd7980975c8e675740a3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 7 Aug 2023 15:57:25 -1000 Subject: workqueue: Add workqueue_attrs->__pod_cpumask workqueue_attrs has two uses: * to specify the required unouned workqueue properties by users * to match worker_pool's properties to workqueues by core code For example, if the user wants to restrict a workqueue to run only CPUs 0 and 2, and the two CPUs are on different affinity scopes, the workqueue's attrs->cpumask would contains CPUs 0 and 2, and the workqueue would be associated with two worker_pools, one with attrs->cpumask containing just CPU 0 and the other CPU 2. Workqueue wants to support non-strict affinity scopes where work items are started in their matching affinity scopes but the scheduler is free to migrate them outside the starting scopes, which can enable utilizing the whole machine while maintaining most of the locality benefits from affinity scopes. To enable that, worker_pools need to distinguish the strict affinity that it has to follow (because that's the restriction coming from the user) and the soft affinity that it wants to apply when dispatching work items. Note that two worker_pools with different soft dispatching requirements have to be separate; otherwise, for example, we'd be ping-ponging worker threads across NUMA boundaries constantly. This patch adds workqueue_attrs->__pod_cpumask. The new field is double underscored as it's only used internally to distinguish worker_pools. A worker_pool's ->cpumask is now always the same as the online subset of allowed CPUs of the associated workqueues, and ->__pod_cpumask is the pod's subset of that ->cpumask. Going back to the example above, both worker_pools would have ->cpumask containing both CPUs 0 and 2 but one's ->__pod_cpumask would contain 0 while the other's 2. * pool_allowed_cpus() is added. It returns the worker_pool's strict cpumask that the pool's workers must stay within. This is currently always ->__pod_cpumask as all boundaries are still strict. * As a workqueue_attrs can now track both the associated workqueues' cpumask and its per-pod subset, wq_calc_pod_cpumask() no longer needs an external out-argument. Drop @cpumask and instead store the result in ->__pod_cpumask. * The above also simplifies apply_wqattrs_prepare() as the same workqueue_attrs can be used to create all pods associated with a workqueue. tmp_attrs is dropped. * wq_update_pod() is updated to use wqattrs_equal() to test whether a pwq update is needed instead of only comparing ->cpumask so that ->__pod_cpumask is compared too. It can directly compare ->__pod_cpumaks but the code is easier to understand and more robust this way. The only user-visible behavior change is that two workqueues with different cpumasks no longer can share worker_pools even when their pod subsets coincide. Going back to the example, let's say there's another workqueue with cpumask 0, 2, 3, where 2 and 3 are in the same pod. It would be mapped to two worker_pools - one with CPU 0, the other with 2 and 3. The former has the same cpumask as the first pod of the earlier example and would have shared the same worker_pool but that's no longer the case after this patch. The worker_pools would have the same ->__pod_cpumask but their ->cpumask's wouldn't match. While this is necessary to support non-strict affinity scopes, there can be further optimizations to maintain sharing among strict affinity scopes. However, non-strict affinity scopes are going to be preferable for most use cases and we don't see very diverse mixture of unbound workqueue cpumasks anyway, so the additional overhead doesn't seem to justify the extra complexity. v2: - wq_update_pod() was incorrectly comparing target_attrs->__pod_cpumask to pool->attrs->cpumask instead of its ->__pod_cpumask. Fix it by using wqattrs_equal() for comparison instead. - Per-cpu worker pools weren't initializing ->__pod_cpumask which caused a subtle problem later on. Set it to cpumask_of(cpu) like ->cpumask. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 16 ++++++++++ kernel/workqueue.c | 74 +++++++++++++++++++++++------------------------ 2 files changed, 53 insertions(+), 37 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 568cfbc24bc0..fe53976e088e 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -150,9 +150,25 @@ struct workqueue_attrs { /** * @cpumask: allowed CPUs + * + * Work items in this workqueue are affine to these CPUs and not allowed + * to execute on other CPUs. A pool serving a workqueue must have the + * same @cpumask. */ cpumask_var_t cpumask; + /** + * @__pod_cpumask: internal attribute used to create per-pod pools + * + * Internal use only. + * + * Per-pod unbound worker pools are used to improve locality. Always a + * subset of ->cpumask. A workqueue can be associated with multiple + * worker pools with disjoint @__pod_cpumask's. Whether the enforcement + * of a pool's @__pod_cpumask is strict depends on @affn_strict. + */ + cpumask_var_t __pod_cpumask; + /* * Below fields aren't properties of a worker_pool. They only modify how * :c:func:`apply_workqueue_attrs` select pools and thus don't diff --git a/kernel/workqueue.c b/kernel/workqueue.c index e941fa052a2b..e61b4291bec8 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -366,7 +366,6 @@ static bool wq_online; /* can kworkers be created yet? */ /* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *wq_update_pod_attrs_buf; -static cpumask_var_t wq_update_pod_cpumask_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ @@ -2050,6 +2049,11 @@ static struct worker *alloc_worker(int node) return worker; } +static cpumask_t *pool_allowed_cpus(struct worker_pool *pool) +{ + return pool->attrs->__pod_cpumask; +} + /** * worker_attach_to_pool() - attach a worker to a pool * @worker: worker to be attached @@ -2075,7 +2079,7 @@ static void worker_attach_to_pool(struct worker *worker, kthread_set_per_cpu(worker->task, pool->cpu); if (worker->rescue_wq) - set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); + set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; @@ -2167,7 +2171,7 @@ static struct worker *create_worker(struct worker_pool *pool) } set_user_nice(worker->task, pool->attrs->nice); - kthread_bind_mask(worker->task, pool->attrs->cpumask); + kthread_bind_mask(worker->task, pool_allowed_cpus(pool)); /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); @@ -3672,6 +3676,7 @@ void free_workqueue_attrs(struct workqueue_attrs *attrs) { if (attrs) { free_cpumask_var(attrs->cpumask); + free_cpumask_var(attrs->__pod_cpumask); kfree(attrs); } } @@ -3693,6 +3698,8 @@ struct workqueue_attrs *alloc_workqueue_attrs(void) goto fail; if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL)) goto fail; + if (!alloc_cpumask_var(&attrs->__pod_cpumask, GFP_KERNEL)) + goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); attrs->affn_scope = wq_affn_dfl; @@ -3707,6 +3714,7 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); + cpumask_copy(to->__pod_cpumask, from->__pod_cpumask); /* * Unlike hash and equality test, copying shouldn't ignore wq-only @@ -3735,6 +3743,8 @@ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) hash = jhash_1word(attrs->nice, hash); hash = jhash(cpumask_bits(attrs->cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); + hash = jhash(cpumask_bits(attrs->__pod_cpumask), + BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); return hash; } @@ -3746,6 +3756,8 @@ static bool wqattrs_equal(const struct workqueue_attrs *a, return false; if (!cpumask_equal(a->cpumask, b->cpumask)) return false; + if (!cpumask_equal(a->__pod_cpumask, b->__pod_cpumask)) + return false; return true; } @@ -3998,9 +4010,9 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) } } - /* If cpumask is contained inside a NUMA pod, that's our NUMA node */ + /* If __pod_cpumask is contained inside a NUMA pod, that's our node */ for (pod = 0; pod < pt->nr_pods; pod++) { - if (cpumask_subset(attrs->cpumask, pt->pod_cpus[pod])) { + if (cpumask_subset(attrs->__pod_cpumask, pt->pod_cpus[pod])) { node = pt->pod_node[pod]; break; } @@ -4190,11 +4202,10 @@ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, * @attrs: the wq_attrs of the default pwq of the target workqueue * @cpu: the target CPU * @cpu_going_down: if >= 0, the CPU to consider as offline - * @cpumask: outarg, the resulting cpumask * * Calculate the cpumask a workqueue with @attrs should use on @pod. If * @cpu_going_down is >= 0, that cpu is considered offline during calculation. - * The result is stored in @cpumask. + * The result is stored in @attrs->__pod_cpumask. * * If pod affinity is not enabled, @attrs->cpumask is always used. If enabled * and @pod has online CPUs requested by @attrs, the returned cpumask is the @@ -4202,27 +4213,27 @@ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, * * The caller is responsible for ensuring that the cpumask of @pod stays stable. */ -static void wq_calc_pod_cpumask(const struct workqueue_attrs *attrs, int cpu, - int cpu_going_down, cpumask_t *cpumask) +static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu, + int cpu_going_down) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int pod = pt->cpu_pod[cpu]; /* does @pod have any online CPUs @attrs wants? */ - cpumask_and(cpumask, pt->pod_cpus[pod], attrs->cpumask); - cpumask_and(cpumask, cpumask, cpu_online_mask); + cpumask_and(attrs->__pod_cpumask, pt->pod_cpus[pod], attrs->cpumask); + cpumask_and(attrs->__pod_cpumask, attrs->__pod_cpumask, cpu_online_mask); if (cpu_going_down >= 0) - cpumask_clear_cpu(cpu_going_down, cpumask); + cpumask_clear_cpu(cpu_going_down, attrs->__pod_cpumask); - if (cpumask_empty(cpumask)) { - cpumask_copy(cpumask, attrs->cpumask); + if (cpumask_empty(attrs->__pod_cpumask)) { + cpumask_copy(attrs->__pod_cpumask, attrs->cpumask); return; } /* yeap, return possible CPUs in @pod that @attrs wants */ - cpumask_and(cpumask, attrs->cpumask, pt->pod_cpus[pod]); + cpumask_and(attrs->__pod_cpumask, attrs->cpumask, pt->pod_cpus[pod]); - if (cpumask_empty(cpumask)) + if (cpumask_empty(attrs->__pod_cpumask)) pr_warn_once("WARNING: workqueue cpumask: online intersect > " "possible intersect\n"); } @@ -4276,7 +4287,7 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, const cpumask_var_t unbound_cpumask) { struct apply_wqattrs_ctx *ctx; - struct workqueue_attrs *new_attrs, *tmp_attrs; + struct workqueue_attrs *new_attrs; int cpu; lockdep_assert_held(&wq_pool_mutex); @@ -4288,8 +4299,7 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_cpu_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(); - tmp_attrs = alloc_workqueue_attrs(); - if (!ctx || !new_attrs || !tmp_attrs) + if (!ctx || !new_attrs) goto out_free; /* @@ -4299,23 +4309,18 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, */ copy_workqueue_attrs(new_attrs, attrs); wqattrs_actualize_cpumask(new_attrs, unbound_cpumask); + cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); if (!ctx->dfl_pwq) goto out_free; - /* - * We may create multiple pwqs with differing cpumasks. Make a copy of - * @new_attrs which will be modified and used to obtain pools. - */ - copy_workqueue_attrs(tmp_attrs, new_attrs); - for_each_possible_cpu(cpu) { if (new_attrs->ordered) { ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[cpu] = ctx->dfl_pwq; } else { - wq_calc_pod_cpumask(new_attrs, cpu, -1, tmp_attrs->cpumask); - ctx->pwq_tbl[cpu] = alloc_unbound_pwq(wq, tmp_attrs); + wq_calc_pod_cpumask(new_attrs, cpu, -1); + ctx->pwq_tbl[cpu] = alloc_unbound_pwq(wq, new_attrs); if (!ctx->pwq_tbl[cpu]) goto out_free; } @@ -4324,14 +4329,13 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, /* save the user configured attrs and sanitize it. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); + cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->attrs = new_attrs; ctx->wq = wq; - free_workqueue_attrs(tmp_attrs); return ctx; out_free: - free_workqueue_attrs(tmp_attrs); free_workqueue_attrs(new_attrs); apply_wqattrs_cleanup(ctx); return ERR_PTR(-ENOMEM); @@ -4459,7 +4463,6 @@ static void wq_update_pod(struct workqueue_struct *wq, int cpu, int off_cpu = online ? -1 : hotplug_cpu; struct pool_workqueue *old_pwq = NULL, *pwq; struct workqueue_attrs *target_attrs; - cpumask_t *cpumask; lockdep_assert_held(&wq_pool_mutex); @@ -4472,20 +4475,18 @@ static void wq_update_pod(struct workqueue_struct *wq, int cpu, * CPU hotplug exclusion. */ target_attrs = wq_update_pod_attrs_buf; - cpumask = wq_update_pod_cpumask_buf; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); wqattrs_actualize_cpumask(target_attrs, wq_unbound_cpumask); /* nothing to do if the target cpumask matches the current pwq */ - wq_calc_pod_cpumask(target_attrs, cpu, off_cpu, cpumask); + wq_calc_pod_cpumask(target_attrs, cpu, off_cpu); pwq = rcu_dereference_protected(*per_cpu_ptr(wq->cpu_pwq, cpu), lockdep_is_held(&wq_pool_mutex)); - if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask)) + if (wqattrs_equal(target_attrs, pwq->pool->attrs)) return; /* create a new pwq */ - cpumask_copy(target_attrs->cpumask, cpumask); pwq = alloc_unbound_pwq(wq, target_attrs); if (!pwq) { pr_warn("workqueue: allocation failed while updating CPU pod affinity of \"%s\"\n", @@ -5409,7 +5410,7 @@ static void rebind_workers(struct worker_pool *pool) for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, - pool->attrs->cpumask) < 0); + pool_allowed_cpus(pool)) < 0); } raw_spin_lock_irq(&pool->lock); @@ -6424,8 +6425,6 @@ void __init workqueue_init_early(void) wq_update_pod_attrs_buf = alloc_workqueue_attrs(); BUG_ON(!wq_update_pod_attrs_buf); - BUG_ON(!alloc_cpumask_var(&wq_update_pod_cpumask_buf, GFP_KERNEL)); - /* initialize WQ_AFFN_SYSTEM pods */ pt->pod_cpus = kcalloc(1, sizeof(pt->pod_cpus[0]), GFP_KERNEL); pt->pod_node = kcalloc(1, sizeof(pt->pod_node[0]), GFP_KERNEL); @@ -6451,6 +6450,7 @@ void __init workqueue_init_early(void) BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); + cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu)); pool->attrs->nice = std_nice[i++]; pool->node = cpu_to_node(cpu); -- cgit v1.2.3 From 8639ecebc9b1796d7074751a350462f5e1c61cd4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 7 Aug 2023 15:57:25 -1000 Subject: workqueue: Implement non-strict affinity scope for unbound workqueues An unbound workqueue can be served by multiple worker_pools to improve locality. The segmentation is achieved by grouping CPUs into pods. By default, the cache boundaries according to cpus_share_cache() define the CPUs are grouped. Let's a workqueue is allowed to run on all CPUs and the system has two L3 caches. The workqueue would be mapped to two worker_pools each serving one L3 cache domains. While this improves locality, because the pod boundaries are strict, it limits the total bandwidth a given issuer can consume. For example, let's say there is a thread pinned to a CPU issuing enough work items to saturate the whole machine. With the machine segmented into two pods, no matter how many work items it issues, it can only use half of the CPUs on the system. While this limitation has existed for a very long time, it wasn't very pronounced because the affinity grouping used to be always by NUMA nodes. With cache boundaries as the default and support for even finer grained scopes (smt and cpu), it is now an a lot more pressing problem. This patch implements non-strict affinity scope where the pod boundaries aren't enforced strictly. Going back to the previous example, the workqueue would still be mapped to two worker_pools; however, the affinity enforcement would be soft. The workers in both pools would have their cpus_allowed set to the whole machine thus allowing the scheduler to migrate them anywhere on the machine. However, whenever an idle worker is woken up, the workqueue code asks the scheduler to bring back the task within the pod if the worker is outside. ie. work items start executing within its affinity scope but can be migrated outside as the scheduler sees fit. This removes the hard cap on utilization while maintaining the benefits of affinity scopes. After the earlier ->__pod_cpumask changes, the implementation is pretty simple. When non-strict which is the new default: * pool_allowed_cpus() returns @pool->attrs->cpumask instead of ->__pod_cpumask so that the workers are allowed to run on any CPU that the associated workqueues allow. * If the idle worker task's ->wake_cpu is outside the pod, kick_pool() sets the field to a CPU within the pod. This would be the first use of task_struct->wake_cpu outside scheduler proper, so it isn't clear whether this would be acceptable. However, other methods of migrating tasks are significantly more expensive and are likely prohibitively so if we want to do this on every work item. This needs discussion with scheduler folks. There is also a race window where setting ->wake_cpu wouldn't be effective as the target task is still on CPU. However, the window is pretty small and this being a best-effort optimization, it doesn't seem to warrant more complexity at the moment. While the non-strict cache affinity scopes seem to be the best option, the performance picture interacts with the affinity scope and is a bit complicated to fully discuss in this patch, so the behavior is made easily selectable through wqattrs and sysfs and the next patch will add documentation to discuss performance implications. v2: pool->attrs->affn_strict is set to true for per-cpu worker_pools. Signed-off-by: Tejun Heo Cc: Peter Zijlstra Cc: Linus Torvalds --- Documentation/core-api/workqueue.rst | 30 +++++++++++---- include/linux/workqueue.h | 11 ++++++ kernel/workqueue.c | 74 +++++++++++++++++++++++++++++++++++- tools/workqueue/wq_dump.py | 16 ++++++-- tools/workqueue/wq_monitor.py | 21 ++++++---- 5 files changed, 132 insertions(+), 20 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index 56af317508c9..c73a6df6a118 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -353,9 +353,10 @@ 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 processed by a -worker running on one of the CPUs which share the last level cache with the -issuing CPU. +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. +Once started, the worker may or may not be allowed to move outside the scope +depending on the ``affinity_strict`` setting of the scope. Workqueue currently supports the following five affinity scopes. @@ -391,6 +392,21 @@ directory. ``affinity_scope`` Read to see the current affinity scope. Write to change. +``affinity_strict`` + 0 by default indicating that affinity scopes are not strict. When a work + item starts execution, workqueue makes a best-effort attempt to ensure + that the worker is inside its affinity scope, which is called + repatriation. Once started, the scheduler is free to move the worker + anywhere in the system as it sees fit. This enables benefiting from scope + locality while still being able to utilize other CPUs if necessary and + available. + + If set to 1, all workers of the scope are guaranteed always to be in the + scope. This may be useful when crossing affinity scopes has other + implications, for example, in terms of power consumption or workload + isolation. Strict NUMA scope can also be used to match the workqueue + behavior of older kernels. + Examining Configuration ======================= @@ -475,21 +491,21 @@ Monitoring Use tools/workqueue/wq_monitor.py to monitor workqueue operations: :: $ tools/workqueue/wq_monitor.py events - total infl CPUtime CPUhog CMwake mayday rescued + total infl CPUtime CPUhog CMW/RPR mayday rescued events 18545 0 6.1 0 5 - - events_highpri 8 0 0.0 0 0 - - events_long 3 0 0.0 0 0 - - - events_unbound 38306 0 0.1 - - - - + events_unbound 38306 0 0.1 - 7 - - events_freezable 0 0 0.0 0 0 - - events_power_efficient 29598 0 0.2 0 0 - - events_freezable_power_ 10 0 0.0 0 0 - - sock_diag_events 0 0 0.0 0 0 - - - total infl CPUtime CPUhog CMwake mayday rescued + total infl CPUtime CPUhog CMW/RPR mayday rescued events 18548 0 6.1 0 5 - - events_highpri 8 0 0.0 0 0 - - events_long 3 0 0.0 0 0 - - - events_unbound 38322 0 0.1 - - - - + events_unbound 38322 0 0.1 - 7 - - events_freezable 0 0 0.0 0 0 - - events_power_efficient 29603 0 0.2 0 0 - - events_freezable_power_ 10 0 0.0 0 0 - - diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index fe53976e088e..0c1cad38f9db 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -169,6 +169,17 @@ struct workqueue_attrs { */ cpumask_var_t __pod_cpumask; + /** + * @affn_strict: affinity scope is strict + * + * If clear, workqueue will make a best-effort attempt at starting the + * worker inside @__pod_cpumask but the scheduler is free to migrate it + * outside. + * + * If set, workers are only allowed to run inside @__pod_cpumask. + */ + bool affn_strict; + /* * Below fields aren't properties of a worker_pool. They only modify how * :c:func:`apply_workqueue_attrs` select pools and thus don't diff --git a/kernel/workqueue.c b/kernel/workqueue.c index e61b4291bec8..6f6f4f37ceb3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -211,6 +211,7 @@ enum pool_workqueue_stats { PWQ_STAT_CPU_TIME, /* total CPU time consumed */ PWQ_STAT_CPU_INTENSIVE, /* wq_cpu_intensive_thresh_us violations */ PWQ_STAT_CM_WAKEUP, /* concurrency-management worker wakeups */ + PWQ_STAT_REPATRIATED, /* unbound workers brought back into scope */ PWQ_STAT_MAYDAY, /* maydays to rescuer */ PWQ_STAT_RESCUED, /* linked work items executed by rescuer */ @@ -1103,13 +1104,41 @@ static bool assign_work(struct work_struct *work, struct worker *worker, static bool kick_pool(struct worker_pool *pool) { struct worker *worker = first_idle_worker(pool); + struct task_struct *p; lockdep_assert_held(&pool->lock); if (!need_more_worker(pool) || !worker) return false; - wake_up_process(worker->task); + p = worker->task; + +#ifdef CONFIG_SMP + /* + * Idle @worker is about to execute @work and waking up provides an + * opportunity to migrate @worker at a lower cost by setting the task's + * wake_cpu field. Let's see if we want to move @worker to improve + * execution locality. + * + * We're waking the worker that went idle the latest and there's some + * chance that @worker is marked idle but hasn't gone off CPU yet. If + * so, setting the wake_cpu won't do anything. As this is a best-effort + * optimization and the race window is narrow, let's leave as-is for + * now. If this becomes pronounced, we can skip over workers which are + * still on cpu when picking an idle worker. + * + * If @pool has non-strict affinity, @worker might have ended up outside + * its affinity scope. Repatriate. + */ + if (!pool->attrs->affn_strict && + !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) { + struct work_struct *work = list_first_entry(&pool->worklist, + struct work_struct, entry); + p->wake_cpu = cpumask_any_distribute(pool->attrs->__pod_cpumask); + get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; + } +#endif + wake_up_process(p); return true; } @@ -2051,7 +2080,10 @@ static struct worker *alloc_worker(int node) static cpumask_t *pool_allowed_cpus(struct worker_pool *pool) { - return pool->attrs->__pod_cpumask; + if (pool->cpu < 0 && pool->attrs->affn_strict) + return pool->attrs->__pod_cpumask; + else + return pool->attrs->cpumask; } /** @@ -3715,6 +3747,7 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to, to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); cpumask_copy(to->__pod_cpumask, from->__pod_cpumask); + to->affn_strict = from->affn_strict; /* * Unlike hash and equality test, copying shouldn't ignore wq-only @@ -3745,6 +3778,7 @@ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); hash = jhash(cpumask_bits(attrs->__pod_cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); + hash = jhash_1word(attrs->affn_strict, hash); return hash; } @@ -3758,6 +3792,8 @@ static bool wqattrs_equal(const struct workqueue_attrs *a, return false; if (!cpumask_equal(a->__pod_cpumask, b->__pod_cpumask)) return false; + if (a->affn_strict != b->affn_strict) + return false; return true; } @@ -5847,6 +5883,7 @@ module_param_cb(default_affinity_scope, &wq_affn_dfl_ops, NULL, 0644); * nice RW int : nice value of the workers * cpumask RW mask : bitmask of allowed CPUs for the workers * affinity_scope RW str : worker CPU affinity scope (cache, numa, none) + * affinity_strict RW bool : worker CPU affinity is strict */ struct wq_device { struct workqueue_struct *wq; @@ -6026,10 +6063,42 @@ static ssize_t wq_affn_scope_store(struct device *dev, return ret ?: count; } +static ssize_t wq_affinity_strict_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + + return scnprintf(buf, PAGE_SIZE, "%d\n", + wq->unbound_attrs->affn_strict); +} + +static ssize_t wq_affinity_strict_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct workqueue_struct *wq = dev_to_wq(dev); + struct workqueue_attrs *attrs; + int v, ret = -ENOMEM; + + if (sscanf(buf, "%d", &v) != 1) + return -EINVAL; + + apply_wqattrs_lock(); + attrs = wq_sysfs_prep_attrs(wq); + if (attrs) { + attrs->affn_strict = (bool)v; + ret = apply_workqueue_attrs_locked(wq, attrs); + } + apply_wqattrs_unlock(); + free_workqueue_attrs(attrs); + return ret ?: count; +} + static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), __ATTR(affinity_scope, 0644, wq_affn_scope_show, wq_affn_scope_store), + __ATTR(affinity_strict, 0644, wq_affinity_strict_show, wq_affinity_strict_store), __ATTR_NULL, }; @@ -6452,6 +6521,7 @@ void __init workqueue_init_early(void) cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu)); pool->attrs->nice = std_nice[i++]; + pool->attrs->affn_strict = true; pool->node = cpu_to_node(cpu); /* alloc pool ID */ diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py index 43ab71a193b8..d0df5833f2c1 100644 --- a/tools/workqueue/wq_dump.py +++ b/tools/workqueue/wq_dump.py @@ -36,10 +36,11 @@ Workqueue CPU -> pool Lists all workqueues along with their type and worker pool association. For each workqueue: - NAME TYPE POOL_ID... + 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 """ @@ -138,13 +139,16 @@ for pi, pool in idr_for_each(worker_pool_idr): print(f'cpu={pool.cpu.value_():3}', 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('[ workqueue \ CPU ', end='') +print('[ workqueue \ type CPU', end='') for cpu in for_each_possible_cpu(prog): print(f' {cpu:{max_pool_id_len}}', end='') print(' dfl]') @@ -153,11 +157,15 @@ for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_( print(f'{wq.name.string_().decode()[-24:]:24}', end='') if wq.flags & WQ_UNBOUND: if wq.flags & WQ_ORDERED: - print(' ordered', end='') + print(' ordered ', end='') else: print(' unbound', end='') + if wq.unbound_attrs.affn_strict: + print(',S ', end='') + else: + print(' ', end='') else: - print(' percpu ', end='') + print(' percpu ', end='') for cpu in for_each_possible_cpu(prog): pool_id = per_cpu_ptr(wq.cpu_pwq, cpu)[0].pool.id.value_() diff --git a/tools/workqueue/wq_monitor.py b/tools/workqueue/wq_monitor.py index 6e258d123e8c..a8856a9c45dc 100644 --- a/tools/workqueue/wq_monitor.py +++ b/tools/workqueue/wq_monitor.py @@ -20,8 +20,11 @@ https://github.com/osandov/drgn. and got excluded from concurrency management to avoid stalling other work items. - CMwake The number of concurrency-management wake-ups while executing a - work item of the workqueue. + 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. @@ -65,6 +68,7 @@ PWQ_STAT_COMPLETED = prog['PWQ_STAT_COMPLETED'] # work items completed exec 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'] @@ -89,22 +93,25 @@ class WqStats: '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} {"CMwake":>7} {"mayday":>7} {"rescued":>7}' + f'{"CPUitsv":>7} {"CMW/RPR":>7} {"mayday":>7} {"rescued":>7}' def table_row_str(self): cpu_intensive = '-' - cm_wakeup = '-' + cmw_rpr = '-' mayday = '-' rescued = '-' - if not self.unbound: + if self.unbound: + cmw_rpr = str(self.stats[PWQ_STAT_REPATRIATED]); + else: cpu_intensive = str(self.stats[PWQ_STAT_CPU_INTENSIVE]) - cm_wakeup = str(self.stats[PWQ_STAT_CM_WAKEUP]) + cmw_rpr = str(self.stats[PWQ_STAT_CM_WAKEUP]) if self.mem_reclaim: mayday = str(self.stats[PWQ_STAT_MAYDAY]) @@ -115,7 +122,7 @@ class WqStats: 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'{cm_wakeup:>7} ' \ + f'{cmw_rpr:>7} ' \ f'{mayday:>7} ' \ f'{rescued:>7} ' return out.rstrip(':') -- cgit v1.2.3 From 523a301e66afd1ea9856660bcf3cee3a7c84c6dd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 7 Aug 2023 15:57:25 -1000 Subject: workqueue: Make default affinity_scope dynamically updatable While workqueue.default_affinity_scope is writable, it only affects workqueues which are created afterwards and isn't very useful. Instead, let's introduce explicit "default" scope and update the effective scope dynamically when workqueue.default_affinity_scope is changed. Signed-off-by: Tejun Heo --- Documentation/admin-guide/kernel-parameters.txt | 8 ++--- Documentation/core-api/workqueue.rst | 9 ++++- include/linux/workqueue.h | 3 +- kernel/workqueue.c | 45 +++++++++++++++++++++---- 4 files changed, 52 insertions(+), 13 deletions(-) (limited to 'include/linux/workqueue.h') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 732c5c7e3fa5..98ffce100a39 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -7014,10 +7014,10 @@ information, see the Affinity Scopes section in Documentation/core-api/workqueue.rst. - This can be updated after boot through the matching - file under /sys/module/workqueue/parameters. - However, the changed default will only apply to - unbound workqueues created afterwards. + This can be changed after boot by writing to the + matching /sys/module/workqueue/parameters file. All + workqueues with the "default" affinity scope will be + updated accordignly. workqueue.debug_force_rr_cpu Workqueue used to implicitly guarantee that work diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index 4a8e764f41ae..5d7b01aed1fe 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -358,7 +358,11 @@ on one of the CPUs which share the last level cache with 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. -Workqueue currently supports the following five affinity scopes. +Workqueue currently supports the following affinity scopes. + +``default`` + Use the scope in module parameter ``workqueue.default_affinity_scope`` + which is always set to one of the scopes below. ``cpu`` CPUs are not grouped. A work item issued on one CPU is processed by a @@ -392,6 +396,9 @@ directory. ``affinity_scope`` Read to see the current affinity scope. Write to change. + When default is the current scope, reading this file will also show the + current effective scope in parentheses, for example, ``default (cache)``. + ``affinity_strict`` 0 by default indicating that affinity scopes are not strict. When a work item starts execution, workqueue makes a best-effort attempt to ensure diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 0c1cad38f9db..1c1d06804d45 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -126,6 +126,7 @@ 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_CACHE, /* one pod per LLC */ @@ -133,8 +134,6 @@ enum wq_affn_scope { WQ_AFFN_SYSTEM, /* one pod across the whole system */ WQ_AFFN_NR_TYPES, - - WQ_AFFN_DFL = WQ_AFFN_CACHE, }; /** diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 6f6f4f37ceb3..789e11e72a4a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -339,9 +339,10 @@ struct wq_pod_type { }; static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES]; -static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_DFL; +static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE; static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = { + [WQ_AFFN_DFL] = "default", [WQ_AFFN_CPU] = "cpu", [WQ_AFFN_SMT] = "smt", [WQ_AFFN_CACHE] = "cache", @@ -3734,7 +3735,7 @@ struct workqueue_attrs *alloc_workqueue_attrs(void) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); - attrs->affn_scope = wq_affn_dfl; + attrs->affn_scope = WQ_AFFN_DFL; return attrs; fail: free_workqueue_attrs(attrs); @@ -3815,7 +3816,18 @@ static void wqattrs_actualize_cpumask(struct workqueue_attrs *attrs, static const struct wq_pod_type * wqattrs_pod_type(const struct workqueue_attrs *attrs) { - struct wq_pod_type *pt = &wq_pod_types[attrs->affn_scope]; + enum wq_affn_scope scope; + struct wq_pod_type *pt; + + /* to synchronize access to wq_affn_dfl */ + lockdep_assert_held(&wq_pool_mutex); + + if (attrs->affn_scope == WQ_AFFN_DFL) + scope = wq_affn_dfl; + else + scope = attrs->affn_scope; + + pt = &wq_pod_types[scope]; if (!WARN_ON_ONCE(attrs->affn_scope == WQ_AFFN_NR_TYPES) && likely(pt->nr_pods)) @@ -5847,13 +5859,29 @@ static int parse_affn_scope(const char *val) static int wq_affn_dfl_set(const char *val, const struct kernel_param *kp) { - int affn; + struct workqueue_struct *wq; + int affn, cpu; affn = parse_affn_scope(val); if (affn < 0) return affn; + if (affn == WQ_AFFN_DFL) + return -EINVAL; + + cpus_read_lock(); + mutex_lock(&wq_pool_mutex); wq_affn_dfl = affn; + + list_for_each_entry(wq, &workqueues, list) { + for_each_online_cpu(cpu) { + wq_update_pod(wq, cpu, cpu, true); + } + } + + mutex_unlock(&wq_pool_mutex); + cpus_read_unlock(); + return 0; } @@ -6033,8 +6061,13 @@ static ssize_t wq_affn_scope_show(struct device *dev, int written; mutex_lock(&wq->mutex); - written = scnprintf(buf, PAGE_SIZE, "%s\n", - wq_affn_names[wq->unbound_attrs->affn_scope]); + if (wq->unbound_attrs->affn_scope == WQ_AFFN_DFL) + written = scnprintf(buf, PAGE_SIZE, "%s (%s)\n", + wq_affn_names[WQ_AFFN_DFL], + wq_affn_names[wq_affn_dfl]); + else + written = scnprintf(buf, PAGE_SIZE, "%s\n", + wq_affn_names[wq->unbound_attrs->affn_scope]); mutex_unlock(&wq->mutex); return written; -- cgit v1.2.3