From d23b5c577715892c87533b13923306acc6243f93 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 29 Oct 2023 06:14:29 +0000 Subject: cgroup: Make operations on the cgroup root_list RCU safe At present, when we perform operations on the cgroup root_list, we must hold the cgroup_mutex, which is a relatively heavyweight lock. In reality, we can make operations on this list RCU-safe, eliminating the need to hold the cgroup_mutex during traversal. Modifications to the list only occur in the cgroup root setup and destroy paths, which should be infrequent in a production environment. In contrast, traversal may occur frequently. Therefore, making it RCU-safe would be beneficial. Signed-off-by: Yafang Shao Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4a6b6b77ccb6..4caab0c6b361 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -563,6 +563,7 @@ struct cgroup_root { /* A list running through the active hierarchies */ struct list_head root_list; + struct rcu_head rcu; /* Hierarchy-specific flags */ unsigned int flags; -- cgit v1.2.3 From aecd408b7e50742868b3305c24325a89024e2a30 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 29 Oct 2023 06:14:32 +0000 Subject: cgroup: Add a new helper for cgroup1 hierarchy A new helper is added for cgroup1 hierarchy: - task_get_cgroup1 Acquires the associated cgroup of a task within a specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its hierarchy ID. This helper function is added to facilitate the tracing of tasks within a particular container or cgroup dir in BPF programs. It's important to note that this helper is designed specifically for cgroup1 only. tj: Use irsqsave/restore as suggested by Hou Tao . Suggested-by: Tejun Heo Signed-off-by: Yafang Shao Cc: Hou Tao Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 0ef0af66080e..34aaf0e87def 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -69,6 +69,7 @@ struct css_task_iter { extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; +extern spinlock_t css_set_lock; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include @@ -386,7 +387,6 @@ static inline void cgroup_unlock(void) * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU -extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ rcu_read_lock_sched_held() || \ @@ -853,4 +853,6 @@ static inline void cgroup_bpf_put(struct cgroup *cgrp) {} #endif /* CONFIG_CGROUP_BPF */ +struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id); + #endif /* _LINUX_CGROUP_H */ -- cgit v1.2.3 From fe28f631fa941fba583d1c4f25895284b90af671 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 25 Oct 2023 14:25:52 -0400 Subject: workqueue: Add workqueue_unbound_exclude_cpumask() to exclude CPUs from wq_unbound_cpumask When the "isolcpus" boot command line option is used to add a set of isolated CPUs, those CPUs will be excluded automatically from wq_unbound_cpumask to avoid running work functions from unbound workqueues. Recently cpuset has been extended to allow the creation of partitions of isolated CPUs dynamically. To make it closer to the "isolcpus" in functionality, the CPUs in those isolated cpuset partitions should be excluded from wq_unbound_cpumask as well. This can be done currently by explicitly writing to the workqueue's cpumask sysfs file after creating the isolated partitions. However, this process can be error prone. Ideally, the cpuset code should be allowed to request the workqueue code to exclude those isolated CPUs from wq_unbound_cpumask so that this operation can be done automatically and the isolated CPUs will be returned back to wq_unbound_cpumask after the destructions of the isolated cpuset partitions. This patch adds a new workqueue_unbound_exclude_cpumask() function to enable that. This new function will exclude the specified isolated CPUs from wq_unbound_cpumask. To be able to restore those isolated CPUs back after the destruction of isolated cpuset partitions, a new wq_requested_unbound_cpumask is added to store the user provided unbound cpumask either from the boot command line options or from writing to the cpumask sysfs file. This new cpumask provides the basis for CPU exclusion. To enable users to understand how the wq_unbound_cpumask is being modified internally, this patch also exposes the newly introduced wq_requested_unbound_cpumask as well as a wq_isolated_cpumask to store the cpumask to be excluded from wq_unbound_cpumask as read-only sysfs files. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 24b1e5070f4d..b0b9604b76b8 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -491,7 +491,7 @@ struct workqueue_attrs *alloc_workqueue_attrs(void); void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); -int workqueue_set_unbound_cpumask(cpumask_var_t cpumask); +extern int workqueue_unbound_exclude_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); -- cgit v1.2.3 From e76d28bdf9ba5388b8c4835a5199dc427b603188 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 3 Nov 2023 23:13:01 -0400 Subject: cgroup/rstat: Reduce cpu_lock hold time in cgroup_rstat_flush_locked() When cgroup_rstat_updated() isn't being called concurrently with cgroup_rstat_flush_locked(), its run time is pretty short. When both are called concurrently, the cgroup_rstat_updated() run time can spike to a pretty high value due to high cpu_lock hold time in cgroup_rstat_flush_locked(). This can be problematic if the task calling cgroup_rstat_updated() is a realtime task running on an isolated CPU with a strict latency requirement. The cgroup_rstat_updated() call can happen when there is a page fault even though the task is running in user space most of the time. The percpu cpu_lock is used to protect the update tree - updated_next and updated_children. This protection is only needed when cgroup_rstat_cpu_pop_updated() is being called. The subsequent flushing operation which can take a much longer time does not need that protection as it is already protected by cgroup_rstat_lock. To reduce the cpu_lock hold time, we need to perform all the cgroup_rstat_cpu_pop_updated() calls up front with the lock released afterward before doing any flushing. This patch adds a new cgroup_rstat_updated_list() function to return a singly linked list of cgroups to be flushed. Some instrumentation code are added to measure the cpu_lock hold time right after lock acquisition to after releasing the lock. Parallel kernel build on a 2-socket x86-64 server is used as the benchmarking tool for measuring the lock hold time. The maximum cpu_lock hold time before and after the patch are 100us and 29us respectively. So the worst case time is reduced to about 30% of the original. However, there may be some OS or hardware noises like NMI or SMI in the test system that can worsen the worst case value. Those noises are usually tuned out in a real production environment to get a better result. OTOH, the lock hold time frequency distribution should give a better idea of the performance benefit of the patch. Below were the frequency distribution before and after the patch: Hold time Before patch After patch --------- ------------ ----------- 0-01 us 804,139 13,738,708 01-05 us 9,772,767 1,177,194 05-10 us 4,595,028 4,984 10-15 us 303,481 3,562 15-20 us 78,971 1,314 20-25 us 24,583 18 25-30 us 6,908 12 30-40 us 8,015 40-50 us 2,192 50-60 us 316 60-70 us 43 70-80 us 7 80-90 us 2 >90 us 3 Signed-off-by: Waiman Long Reviewed-by: Yosry Ahmed Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4caab0c6b361..37518436cfe7 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -496,6 +496,13 @@ struct cgroup { struct cgroup_rstat_cpu __percpu *rstat_cpu; struct list_head rstat_css_list; + /* + * A singly-linked list of cgroup structures to be rstat flushed. + * This is a scratch field to be used exclusively by + * cgroup_rstat_flush_locked() and protected by cgroup_rstat_lock. + */ + struct cgroup *rstat_flush_next; + /* cgroup basic resource statistics */ struct cgroup_base_stat last_bstat; struct cgroup_base_stat bstat; -- cgit v1.2.3 From 77070eeb882124614a40616f01bfe60947be5778 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 30 Nov 2023 15:43:27 -0500 Subject: cgroup: Avoid false cacheline sharing of read mostly rstat_cpu The rstat_cpu and also rstat_css_list of the cgroup structure are read mostly variables. However, they may share the same cacheline as the subsequent rstat_flush_next and *bstat variables which can be updated frequently. That will slow down the cgroup_rstat_cpu() call which is called pretty frequently in the rstat code. Add a CACHELINE_PADDING() line in between them to avoid false cacheline sharing. A parallel kernel build on a 2-socket x86-64 server is used as the benchmarking tool for measuring the lock hold time. Below were the lock hold time frequency distribution before and after the patch: Run time Before patch After patch -------- ------------ ----------- 0-01 us 9,928,562 9,820,428 01-05 us 110,151 50,935 05-10 us 270 93 10-15 us 273 146 15-20 us 135 76 20-25 us 0 2 25-30 us 1 0 It can be seen that the patch further pushes the lock hold time towards the lower end. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 37518436cfe7..5a97ea95b564 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -496,6 +496,13 @@ struct cgroup { struct cgroup_rstat_cpu __percpu *rstat_cpu; struct list_head rstat_css_list; + /* + * Add padding to separate the read mostly rstat_cpu and + * rstat_css_list into a different cacheline from the following + * rstat_flush_next and *bstat fields which can have frequent updates. + */ + CACHELINE_PADDING(_pad_); + /* * A singly-linked list of cgroup structures to be rstat flushed. * This is a scratch field to be used exclusively by -- cgit v1.2.3 From 3232e7aad11e541da86bbb1fa5ea5737b30bd006 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 5 Dec 2023 17:21:14 -0500 Subject: cgroup/cpuset: Include isolated cpuset CPUs in cpu_is_isolated() check Currently, the cpu_is_isolated() function checks only the statically isolated CPUs specified via the "isolcpus" and "nohz_full" kernel command line options. This function is used by vmstat and memcg to reduce interference with isolated CPUs by not doing stat flushing or scheduling works on those CPUs. Workloads running on isolated CPUs within isolated cpuset partitions should receive the same treatment to reduce unnecessary interference. This patch introduces a new cpuset_cpu_is_isolated() function to be called by cpu_is_isolated() so that the set of dynamically created cpuset isolated CPUs will be included in the check. Assuming that testing a bit in a cpumask is atomic, no synchronization primitive is currently used to synchronize access to the cpuset's isolated_cpus mask. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/cpuset.h | 6 ++++++ include/linux/sched/isolation.h | 4 +++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d629094fac6e..875d12598bd2 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -77,6 +77,7 @@ extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); +extern bool cpuset_cpu_is_isolated(int cpu); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); @@ -207,6 +208,11 @@ static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p) return false; } +static inline bool cpuset_cpu_is_isolated(int cpu) +{ + return false; +} + static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index fe1a46f30d24..2b461129d1fa 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -2,6 +2,7 @@ #define _LINUX_SCHED_ISOLATION_H #include +#include #include #include @@ -67,7 +68,8 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type) static inline bool cpu_is_isolated(int cpu) { return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) || - !housekeeping_test_cpu(cpu, HK_TYPE_TICK); + !housekeeping_test_cpu(cpu, HK_TYPE_TICK) || + cpuset_cpu_is_isolated(cpu); } #endif /* _LINUX_SCHED_ISOLATION_H */ -- cgit v1.2.3 From a7fb0423c201ba12815877a0b5a68a6a1710b23a Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 7 Dec 2023 08:46:14 -0500 Subject: cgroup: Move rcu_head up near the top of cgroup_root MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit d23b5c577715 ("cgroup: Make operations on the cgroup root_list RCU safe") adds a new rcu_head to the cgroup_root structure and kvfree_rcu() for freeing the cgroup_root. The current implementation of kvfree_rcu(), however, has the limitation that the offset of the rcu_head structure within the larger data structure must be less than 4096 or the compilation will fail. See the macro definition of __is_kvfree_rcu_offset() in include/linux/rcupdate.h for more information. By putting rcu_head below the large cgroup structure, any change to the cgroup structure that makes it larger run the risk of causing build failure under certain configurations. Commit 77070eeb8821 ("cgroup: Avoid false cacheline sharing of read mostly rstat_cpu") happens to be the last straw that breaks it. Fix this problem by moving the rcu_head structure up before the cgroup structure. Fixes: d23b5c577715 ("cgroup: Make operations on the cgroup root_list RCU safe") Reported-by: Stephen Rothwell Closes: https://lore.kernel.org/lkml/20231207143806.114e0a74@canb.auug.org.au/ Signed-off-by: Waiman Long Acked-by: Yafang Shao Reviewed-by: Yosry Ahmed Reviewed-by: Michal Koutný Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 5a97ea95b564..ea48c861cd36 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -562,6 +562,10 @@ struct cgroup_root { /* Unique id for this hierarchy. */ int hierarchy_id; + /* A list running through the active hierarchies */ + struct list_head root_list; + struct rcu_head rcu; /* Must be near the top */ + /* * The root cgroup. The containing cgroup_root will be destroyed on its * release. cgrp->ancestors[0] will be used overflowing into the @@ -575,10 +579,6 @@ struct cgroup_root { /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; - /* A list running through the active hierarchies */ - struct list_head root_list; - struct rcu_head rcu; - /* Hierarchy-specific flags */ unsigned int flags; -- cgit v1.2.3