diff options
Diffstat (limited to 'include/linux/psi_types.h')
| -rw-r--r-- | include/linux/psi_types.h | 90 |
1 files changed, 63 insertions, 27 deletions
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index b95f3211566a..f1fd3a8044e0 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PSI_TYPES_H #define _LINUX_PSI_TYPES_H @@ -15,12 +16,15 @@ enum psi_task_count { NR_MEMSTALL, NR_RUNNING, /* - * This can't have values other than 0 or 1 and could be - * implemented as a bit flag. But for now we still have room - * in the first cacheline of psi_group_cpu, and this way we - * don't have to special case any state tracking for it. + * For IO and CPU stalls the presence of running/oncpu tasks + * in the domain means a partial rather than a full stall. + * For memory it's not so simple because of page reclaimers: + * they are running/oncpu while representing a stall. To tell + * whether a domain has productivity left or not, we need to + * distinguish between regular running (i.e. productive) + * threads and memstall ones. */ - NR_ONCPU, + NR_MEMSTALL_RUNNING, NR_PSI_TASK_COUNTS = 4, }; @@ -28,14 +32,20 @@ enum psi_task_count { #define TSK_IOWAIT (1 << NR_IOWAIT) #define TSK_MEMSTALL (1 << NR_MEMSTALL) #define TSK_RUNNING (1 << NR_RUNNING) -#define TSK_ONCPU (1 << NR_ONCPU) +#define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING) + +/* Only one task can be scheduled, no corresponding task count */ +#define TSK_ONCPU (1 << NR_PSI_TASK_COUNTS) /* Resources that workloads could be stalled on */ enum psi_res { PSI_IO, PSI_MEM, PSI_CPU, - NR_PSI_RESOURCES = 3, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ, +#endif + NR_PSI_RESOURCES, }; /* @@ -50,11 +60,21 @@ enum psi_states { PSI_MEM_SOME, PSI_MEM_FULL, PSI_CPU_SOME, + PSI_CPU_FULL, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ_FULL, +#endif /* Only per-CPU, to weigh the CPU in the global average: */ PSI_NONIDLE, - NR_PSI_STATES = 6, + NR_PSI_STATES, }; +/* Use one bit in the state mask to track TSK_ONCPU */ +#define PSI_ONCPU (1 << NR_PSI_STATES) + +/* Flag whether to re-arm avgs_work, see details in get_recent_times() */ +#define PSI_STATE_RESCHEDULE (1 << (NR_PSI_STATES + 1)) + enum psi_aggregators { PSI_AVGS = 0, PSI_POLL, @@ -117,6 +137,9 @@ struct psi_trigger { /* Wait queue for polling */ wait_queue_head_t event_wait; + /* Kernfs file for cgroup triggers */ + struct kernfs_open_file *of; + /* Pending event flag */ int event; @@ -129,11 +152,17 @@ struct psi_trigger { */ u64 last_event_time; - /* Refcounting to prevent premature destruction */ - struct kref refcount; + /* Deferred event(s) from previous ratelimit window */ + bool pending_event; + + /* Trigger type - PSI_AVGS for unprivileged, PSI_POLL for RT */ + enum psi_aggregators aggregator; }; struct psi_group { + struct psi_group *parent; + bool enabled; + /* Protects data used by the aggregator */ struct mutex avgs_lock; @@ -148,33 +177,40 @@ struct psi_group { /* Aggregator work control */ struct delayed_work avgs_work; + /* Unprivileged triggers against N*PSI_FREQ windows */ + struct list_head avg_triggers; + u32 avg_nr_triggers[NR_PSI_STATES - 1]; + /* Total stall times and sampled pressure averages */ u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1]; unsigned long avg[NR_PSI_STATES - 1][3]; - /* Monitor work control */ - struct task_struct __rcu *poll_task; - struct timer_list poll_timer; - wait_queue_head_t poll_wait; - atomic_t poll_wakeup; + /* Monitor RT polling work control */ + struct task_struct __rcu *rtpoll_task; + struct timer_list rtpoll_timer; + wait_queue_head_t rtpoll_wait; + atomic_t rtpoll_wakeup; + atomic_t rtpoll_scheduled; /* Protects data used by the monitor */ - struct mutex trigger_lock; - - /* Configured polling triggers */ - struct list_head triggers; - u32 nr_triggers[NR_PSI_STATES - 1]; - u32 poll_states; - u64 poll_min_period; - - /* Total stall times at the start of monitor activation */ - u64 polling_total[NR_PSI_STATES - 1]; - u64 polling_next_update; - u64 polling_until; + struct mutex rtpoll_trigger_lock; + + /* Configured RT polling triggers */ + struct list_head rtpoll_triggers; + u32 rtpoll_nr_triggers[NR_PSI_STATES - 1]; + u32 rtpoll_states; + u64 rtpoll_min_period; + + /* Total stall times at the start of RT polling monitor activation */ + u64 rtpoll_total[NR_PSI_STATES - 1]; + u64 rtpoll_next_update; + u64 rtpoll_until; }; #else /* CONFIG_PSI */ +#define NR_PSI_RESOURCES 0 + struct psi_group { }; #endif /* CONFIG_PSI */ |