diff options
Diffstat (limited to 'include/linux/cgroup-defs.h')
| -rw-r--r-- | include/linux/cgroup-defs.h | 349 |
1 files changed, 203 insertions, 146 deletions
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index fee0b5547cd0..e61687d5e496 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -19,7 +19,7 @@ #include <linux/percpu-rwsem.h> #include <linux/u64_stats_sync.h> #include <linux/workqueue.h> -#include <linux/bpf-cgroup.h> +#include <linux/bpf-cgroup-defs.h> #include <linux/psi_types.h> #ifdef CONFIG_CGROUPS @@ -86,19 +86,42 @@ enum { CGRP_ROOT_NS_DELEGATE = (1 << 3), /* + * Reduce latencies on dynamic cgroup modifications such as task + * migrations and controller on/offs by disabling percpu operation on + * cgroup_threadgroup_rwsem. This makes hot path operations such as + * forks and exits into the slow path and more expensive. + * + * The static usage pattern of creating a cgroup, enabling controllers, + * and then seeding it with CLONE_INTO_CGROUP doesn't require write + * locking cgroup_threadgroup_rwsem and thus doesn't benefit from + * favordynmod. + */ + CGRP_ROOT_FAVOR_DYNMODS = (1 << 4), + + /* * Enable cpuset controller in v1 cgroup to use v2 behavior. */ - CGRP_ROOT_CPUSET_V2_MODE = (1 << 4), + CGRP_ROOT_CPUSET_V2_MODE = (1 << 16), /* * Enable legacy local memory.events. */ - CGRP_ROOT_MEMORY_LOCAL_EVENTS = (1 << 5), + CGRP_ROOT_MEMORY_LOCAL_EVENTS = (1 << 17), /* * Enable recursive subtree protection */ - CGRP_ROOT_MEMORY_RECURSIVE_PROT = (1 << 6), + CGRP_ROOT_MEMORY_RECURSIVE_PROT = (1 << 18), + + /* + * Enable hugetlb accounting for the memory controller. + */ + CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING = (1 << 19), + + /* + * Enable legacy local pids.events. + */ + CGRP_ROOT_PIDS_LOCAL_EVENTS = (1 << 20), }; /* cftype->flags */ @@ -114,6 +137,7 @@ enum { /* internal flags, do not use outside cgroup core proper */ __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ + __CFTYPE_ADDED = (1 << 18), }; /* @@ -145,13 +169,31 @@ struct cgroup_subsys_state { /* reference count - access via css_[try]get() and css_put() */ struct percpu_ref refcnt; - /* siblings list anchored at the parent's ->children */ + /* + * Depending on the context, this field is initialized + * via css_rstat_init() at different places: + * + * when css is associated with cgroup::self + * when css->cgroup is the root cgroup + * performed in cgroup_init() + * when css->cgroup is not the root cgroup + * performed in cgroup_create() + * when css is associated with a subsystem + * when css->cgroup is the root cgroup + * performed in cgroup_init_subsys() in the non-early path + * when css->cgroup is not the root cgroup + * performed in css_create() + */ + struct css_rstat_cpu __percpu *rstat_cpu; + + /* + * siblings list anchored at the parent's ->children + * + * linkage is protected by cgroup_mutex or RCU + */ struct list_head sibling; struct list_head children; - /* flush target list anchored at cgrp->rstat_css_list */ - struct list_head rstat_css_node; - /* * PI: Subsys-unique ID. 0 is unused and root is always 1. The * matching css can be looked up using css_from_id(). @@ -183,6 +225,24 @@ struct cgroup_subsys_state { * fields of the containing structure. */ struct cgroup_subsys_state *parent; + + /* + * Keep track of total numbers of visible descendant CSSes. + * The total number of dying CSSes is tracked in + * css->cgroup->nr_dying_subsys[ssid]. + * Protected by cgroup_mutex. + */ + int nr_descendants; + + /* + * A singly-linked list of css structures to be rstat flushed. + * This is a scratch field to be used exclusively by + * css_rstat_flush(). + * + * Protected by rstat_base_lock when css is cgroup::self. + * Protected by css->ss->rstat_ss_lock otherwise. + */ + struct cgroup_subsys_state *rstat_flush_next; }; /* @@ -221,7 +281,7 @@ struct css_set { * Lists running through all tasks using this cgroup group. * mg_tasks lists tasks which belong to this cset but are in the * process of being migrated out or in. Protected by - * css_set_rwsem, but, during migration, once tasks are moved to + * css_set_lock, but, during migration, once tasks are moved to * mg_tasks, it can be read safely while holding cgroup_mutex. */ struct list_head tasks; @@ -232,7 +292,7 @@ struct css_set { struct list_head task_iters; /* - * On the default hierarhcy, ->subsys[ssid] may point to a css + * On the default hierarchy, ->subsys[ssid] may point to a css * attached to an ancestor instead of the cgroup this css_set is * associated with. The following node is anchored at * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to @@ -260,7 +320,8 @@ struct css_set { * List of csets participating in the on-going migration either as * source or destination. Protected by cgroup_mutex. */ - struct list_head mg_preload_node; + struct list_head mg_src_preload_node; + struct list_head mg_dst_preload_node; struct list_head mg_node; /* @@ -283,14 +344,19 @@ struct css_set { struct cgroup_base_stat { struct task_cputime cputime; + +#ifdef CONFIG_SCHED_CORE + u64 forceidle_sum; +#endif + u64 ntime; }; /* * rstat - cgroup scalable recursive statistics. Accounting is done - * per-cpu in cgroup_rstat_cpu which is then lazily propagated up the + * per-cpu in css_rstat_cpu which is then lazily propagated up the * hierarchy on reads. * - * When a stat gets updated, the cgroup_rstat_cpu and its ancestors are + * When a stat gets updated, the css_rstat_cpu and its ancestors are * linked into the updated tree. On the following read, propagation only * considers and consumes the updated tree. This makes reading O(the * number of descendants which have been active since last read) instead of @@ -302,10 +368,29 @@ struct cgroup_base_stat { * frequency decreases the cost of each read. * * This struct hosts both the fields which implement the above - - * updated_children and updated_next - and the fields which track basic - * resource statistics on top of it - bsync, bstat and last_bstat. + * updated_children and updated_next. + */ +struct css_rstat_cpu { + /* + * Child cgroups with stat updates on this cpu since the last read + * are linked on the parent's ->updated_children through + * ->updated_next. updated_children is terminated by its container css. + * + * In addition to being more compact, singly-linked list pointing to + * the css makes it unnecessary for each per-cpu struct to point back + * to the associated css. + * + * Protected by per-cpu css->ss->rstat_ss_cpu_lock. + */ + struct cgroup_subsys_state *updated_children; + struct cgroup_subsys_state *updated_next; /* NULL if not on the list */ +}; + +/* + * This struct hosts the fields which track basic resource statistics on + * top of it - bsync, bstat and last_bstat. */ -struct cgroup_rstat_cpu { +struct cgroup_rstat_base_cpu { /* * ->bsync protects ->bstat. These are the only fields which get * updated in the hot path. @@ -320,18 +405,18 @@ struct cgroup_rstat_cpu { struct cgroup_base_stat last_bstat; /* - * Child cgroups with stat updates on this cpu since the last read - * are linked on the parent's ->updated_children through - * ->updated_next. - * - * In addition to being more compact, singly-linked list pointing - * to the cgroup makes it unnecessary for each per-cpu struct to - * point back to the associated cgroup. - * - * Protected by per-cpu cgroup_rstat_cpu_lock. + * This field is used to record the cumulative per-cpu time of + * the cgroup and its descendants. Currently it can be read via + * eBPF/drgn etc, and we are still trying to determine how to + * expose it in the cgroupfs interface. */ - struct cgroup *updated_children; /* terminated by self cgroup */ - struct cgroup *updated_next; /* NULL iff not on the list */ + struct cgroup_base_stat subtree_bstat; + + /* + * Snapshots at the last reading. These are used to calculate the + * deltas to propagate to the per-cpu subtree_bstat. + */ + struct cgroup_base_stat last_subtree_bstat; }; struct cgroup_freezer_state { @@ -339,7 +424,7 @@ struct cgroup_freezer_state { bool freeze; /* Should the cgroup actually be frozen? */ - int e_freeze; + bool e_freeze; /* Fields below are protected by css_set_lock */ @@ -362,7 +447,7 @@ struct cgroup { /* * The depth this cgroup is at. The root is at depth zero and each * step down the hierarchy increments the level. This along with - * ancestor_ids[] can determine whether a given cgroup is a + * ancestors[] can determine whether a given cgroup is a * descendant of another without traversing the hierarchy. */ int level; @@ -402,14 +487,20 @@ struct cgroup { int nr_threaded_children; /* # of live threaded child cgroups */ + /* sequence number for cgroup.kill, serialized by css_set_lock. */ + unsigned int kill_seq; + struct kernfs_node *kn; /* cgroup kernfs entry */ struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ + /* handles for "{cpu,memory,io,irq}.pressure" */ + struct cgroup_file psi_files[NR_PSI_RESOURCES]; + /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through - * "cgroup.subtree_control" while ->child_ss_mask is the effective + * "cgroup.subtree_control" while ->subtree_ss_mask is the effective * one which may have more subsystems enabled. Controller knobs * are made available iff it's enabled in ->subtree_control. */ @@ -421,6 +512,12 @@ struct cgroup { /* Private pointers for each registered subsystem */ struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; + /* + * Keep track of total number of dying CSSes at and below this cgroup. + * Protected by cgroup_mutex. + */ + int nr_dying_subsys[CGROUP_SUBSYS_COUNT]; + struct cgroup_root *root; /* @@ -448,9 +545,23 @@ struct cgroup { struct cgroup *dom_cgrp; struct cgroup *old_dom_cgrp; /* used while enabling threaded */ - /* per-cpu recursive resource statistics */ - struct cgroup_rstat_cpu __percpu *rstat_cpu; - struct list_head rstat_css_list; + /* + * Depending on the context, this field is initialized via + * css_rstat_init() at different places: + * + * when cgroup is the root cgroup + * performed in cgroup_setup_root() + * otherwise + * performed in cgroup_create() + */ + struct cgroup_rstat_base_cpu __percpu *rstat_base_cpu; + + /* + * Add padding to keep the read mostly rstat per-cpu pointer on a + * different cacheline than the following *bstat fields which can have + * frequent updates. + */ + CACHELINE_PADDING(_pad_); /* cgroup basic resource statistics */ struct cgroup_base_stat last_bstat; @@ -471,19 +582,20 @@ struct cgroup { struct work_struct release_agent_work; /* used to track pressure stalls */ - struct psi_group psi; + struct psi_group *psi; /* used to store eBPF programs */ struct cgroup_bpf bpf; - /* If there is block congestion on this cgroup. */ - atomic_t congestion_count; - /* Used to store internal freezer state */ struct cgroup_freezer_state freezer; - /* ids of the ancestors at each level including self */ - u64 ancestor_ids[]; +#ifdef CONFIG_BPF_SYSCALL + struct bpf_local_storage __rcu *bpf_cgrp_storage; +#endif + + /* All ancestors including self */ + struct cgroup *ancestors[]; }; /* @@ -500,18 +612,23 @@ struct cgroup_root { /* Unique id for this hierarchy. */ int hierarchy_id; - /* The root cgroup. Root is destroyed on its release. */ + /* 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 + * following field. cgrp_ancestor_storage must immediately follow. + */ struct cgroup cgrp; - /* for cgrp->ancestor_ids[0] */ - u64 cgrp_ancestor_id_storage; + /* must follow cgrp for cgrp->ancestors[0], see above */ + struct cgroup *cgrp_ancestor_storage; /* 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; - /* Hierarchy-specific flags */ unsigned int flags; @@ -531,9 +648,8 @@ struct cgroup_root { */ struct cftype { /* - * By convention, the name should begin with the name of the - * subsystem, followed by a period. Zero length string indicates - * end of cftype array. + * Name of the subsystem is prepended in cgroup_file_name(). + * Zero length string indicates end of cftype array. */ char name[MAX_CFTYPE_NAME]; unsigned long private; @@ -609,9 +725,7 @@ struct cftype { __poll_t (*poll)(struct kernfs_open_file *of, struct poll_table_struct *pt); -#ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; -#endif }; /* @@ -625,9 +739,12 @@ struct cgroup_subsys { void (*css_released)(struct cgroup_subsys_state *css); void (*css_free)(struct cgroup_subsys_state *css); void (*css_reset)(struct cgroup_subsys_state *css); + void (*css_killed)(struct cgroup_subsys_state *css); void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu); int (*css_extra_stat_show)(struct seq_file *seq, struct cgroup_subsys_state *css); + int (*css_local_stat_show)(struct seq_file *seq, + struct cgroup_subsys_state *css); int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); @@ -668,22 +785,7 @@ struct cgroup_subsys { */ bool threaded:1; - /* - * If %false, this subsystem is properly hierarchical - - * configuration, resource accounting and restriction on a parent - * cgroup cover those of its children. If %true, hierarchy support - * is broken in some ways - some subsystems ignore hierarchy - * completely while others are only implemented half-way. - * - * It's now disallowed to create nested cgroups if the subsystem is - * broken and cgroup core will emit a warning message on such - * cases. Eventually, all subsystems will be made properly - * hierarchical and this will go away. - */ - bool broken_hierarchy:1; - bool warned_broken_hierarchy:1; - - /* the following two fields are initialized automtically during boot */ + /* the following two fields are initialized automatically during boot */ int id; const char *name; @@ -717,10 +819,18 @@ struct cgroup_subsys { * specifies the mask of subsystems that this one depends on. */ unsigned int depends_on; + + spinlock_t rstat_ss_lock; + raw_spinlock_t __percpu *rstat_ss_cpu_lock; }; extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; +struct cgroup_of_peak { + unsigned long value; + struct list_head list; +}; + /** * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups * @tsk: target task @@ -763,107 +873,54 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains * per-socket cgroup information except for memcg association. * - * On legacy hierarchies, net_prio and net_cls controllers directly set - * attributes on each sock which can then be tested by the network layer. - * On the default hierarchy, each sock is associated with the cgroup it was - * created in and the networking layer can match the cgroup directly. - * - * To avoid carrying all three cgroup related fields separately in sock, - * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer. - * On boot, sock_cgroup_data records the cgroup that the sock was created - * in so that cgroup2 matches can be made; however, once either net_prio or - * net_cls starts being used, the area is overriden to carry prioidx and/or - * classid. The two modes are distinguished by whether the lowest bit is - * set. Clear bit indicates cgroup pointer while set bit prioidx and - * classid. - * - * While userland may start using net_prio or net_cls at any time, once - * either is used, cgroup2 matching no longer works. There is no reason to - * mix the two and this is in line with how legacy and v2 compatibility is - * handled. On mode switch, cgroup references which are already being - * pointed to by socks may be leaked. While this can be remedied by adding - * synchronization around sock_cgroup_data, given that the number of leaked - * cgroups is bound and highly unlikely to be high, this seems to be the - * better trade-off. + * On legacy hierarchies, net_prio and net_cls controllers directly + * set attributes on each sock which can then be tested by the network + * layer. On the default hierarchy, each sock is associated with the + * cgroup it was created in and the networking layer can match the + * cgroup directly. */ struct sock_cgroup_data { - union { -#ifdef __LITTLE_ENDIAN - struct { - u8 is_data : 1; - u8 no_refcnt : 1; - u8 unused : 6; - u8 padding; - u16 prioidx; - u32 classid; - } __packed; -#else - struct { - u32 classid; - u16 prioidx; - u8 padding; - u8 unused : 6; - u8 no_refcnt : 1; - u8 is_data : 1; - } __packed; + struct cgroup *cgroup; /* v2 */ +#ifdef CONFIG_CGROUP_NET_CLASSID + u32 classid; /* v1 */ +#endif +#ifdef CONFIG_CGROUP_NET_PRIO + u16 prioidx; /* v1 */ #endif - u64 val; - }; }; -/* - * There's a theoretical window where the following accessors race with - * updaters and return part of the previous pointer as the prioidx or - * classid. Such races are short-lived and the result isn't critical. - */ static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd) { - /* fallback to 1 which is always the ID of the root cgroup */ - return (skcd->is_data & 1) ? skcd->prioidx : 1; +#ifdef CONFIG_CGROUP_NET_PRIO + return READ_ONCE(skcd->prioidx); +#else + return 1; +#endif } static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd) { - /* fallback to 0 which is the unconfigured default classid */ - return (skcd->is_data & 1) ? skcd->classid : 0; +#ifdef CONFIG_CGROUP_NET_CLASSID + return READ_ONCE(skcd->classid); +#else + return 0; +#endif } -/* - * If invoked concurrently, the updaters may clobber each other. The - * caller is responsible for synchronization. - */ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, u16 prioidx) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_prioidx(&skcd_buf) == prioidx) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.prioidx = prioidx; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_PRIO + WRITE_ONCE(skcd->prioidx, prioidx); +#endif } static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, u32 classid) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_classid(&skcd_buf) == classid) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.classid = classid; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_CLASSID + WRITE_ONCE(skcd->classid, classid); +#endif } #else /* CONFIG_SOCK_CGROUP_DATA */ |