staticvoid cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
/* * Determines whether a given css can participate in rstat. * css's that are cgroup::self use rstat for base stats. * Other css's associated with a subsystem use rstat only when * they define the ss->css_rstat_flush callback.
*/ staticinlinebool css_uses_rstat(struct cgroup_subsys_state *css)
{ return css_is_self(css) || css->ss->css_rstat_flush != NULL;
}
static spinlock_t *ss_rstat_lock(struct cgroup_subsys *ss)
{ if (ss) return &ss->rstat_ss_lock;
return &rstat_base_lock;
}
staticinlinestruct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu)
{ if (ss) return per_cpu_ptr(ss->lhead, cpu); return per_cpu_ptr(&rstat_backlog_list, cpu);
}
/** * css_rstat_updated - keep track of updated rstat_cpu * @css: target cgroup subsystem state * @cpu: cpu on which rstat_cpu was updated * * Atomically inserts the css in the ss's llist for the given cpu. This is * reentrant safe i.e. safe against softirq, hardirq and nmi. The ss's llist * will be processed at the flush time to create the update tree. * * NOTE: if the user needs the guarantee that the updater either add itself in * the lockless list or the concurrent flusher flushes its updated stats, a * memory barrier is needed before the call to css_rstat_updated() i.e. a * barrier after updating the per-cpu stats and before calling * css_rstat_updated().
*/
__bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
{ struct llist_head *lhead; struct css_rstat_cpu *rstatc; struct css_rstat_cpu __percpu *rstatc_pcpu; struct llist_node *self;
/* * Since bpf programs can call this function, prevent access to * uninitialized rstat pointers.
*/ if (!css_uses_rstat(css)) return;
lockdep_assert_preemption_disabled();
/* * For archs withnot nmi safe cmpxchg or percpu ops support, ignore * the requests from nmi context.
*/ if ((!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) ||
!IS_ENABLED(CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS)) && in_nmi()) return;
rstatc = css_rstat_cpu(css, cpu); /* * If already on list return. This check is racy and smp_mb() is needed * to pair it with the smp_mb() in css_process_update_tree() if the * guarantee that the updated stats are visible to concurrent flusher is * needed.
*/ if (llist_on_list(&rstatc->lnode)) return;
/* * This function can be renentered by irqs and nmis for the same cgroup * and may try to insert the same per-cpu lnode into the llist. Note * that llist_add() does not protect against such scenarios. * * To protect against such stacked contexts of irqs/nmis, we use the * fact that lnode points to itself when not on a list and then use * this_cpu_cmpxchg() to atomically set to NULL to select the winner * which will call llist_add(). The losers can assume the insertion is * successful and the winner will eventually add the per-cpu lnode to * the llist.
*/
self = &rstatc->lnode;
rstatc_pcpu = css->rstat_cpu; if (this_cpu_cmpxchg(rstatc_pcpu->lnode.next, self, NULL) != self) return;
while ((lnode = llist_del_first_init(lhead))) { struct css_rstat_cpu *rstatc;
/* * smp_mb() is needed here (more specifically in between * init_llist_node() and per-cpu stats flushing) if the * guarantee is required by a rstat user where etiher the * updater should add itself on the lockless list or the * flusher flush the stats updated by the updater who have * observed that they are already on the list. The * corresponding barrier pair for this one should be before * css_rstat_updated() by the user. * * For now, there aren't any such user, so not adding the * barrier here but if such a use-case arise, please add * smp_mb() here.
*/
/** * css_rstat_push_children - push children css's into the given list * @head: current head of the list (= subtree root) * @child: first child of the root * @cpu: target cpu * Return: A new singly linked list of css's to be flushed * * Iteratively traverse down the css_rstat_cpu updated tree level by * level and push all the parents first before their next level children * into a singly linked list via the rstat_flush_next pointer built from the * tail backward like "pushing" css's into a stack. The root is pushed by * the caller.
*/ staticstruct cgroup_subsys_state *css_rstat_push_children( struct cgroup_subsys_state *head, struct cgroup_subsys_state *child, int cpu)
{ struct cgroup_subsys_state *cnext = child; /* Next head of child css level */ struct cgroup_subsys_state *ghead = NULL; /* Head of grandchild css level */ struct cgroup_subsys_state *parent, *grandchild; struct css_rstat_cpu *crstatc;
child->rstat_flush_next = NULL;
/* * The subsystem rstat lock must be held for the whole duration from * here as the rstat_flush_next list is being constructed to when * it is consumed later in css_rstat_flush().
*/
lockdep_assert_held(ss_rstat_lock(head->ss));
/** * css_rstat_updated_list - build a list of updated css's to be flushed * @root: root of the css subtree to traverse * @cpu: target cpu * Return: A singly linked list of css's to be flushed * * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, * each returned css is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, the child is before its parent in * the list. * * Note that updated_children is self terminated and points to a list of * child css's if not empty. Whereas updated_next is like a sibling link * within the children list and terminated by the parent css. An exception * here is the css root whose updated_next can be self terminated.
*/ staticstruct cgroup_subsys_state *css_rstat_updated_list( struct cgroup_subsys_state *root, int cpu)
{ struct css_rstat_cpu *rstatc = css_rstat_cpu(root, cpu); struct cgroup_subsys_state *head = NULL, *parent, *child;
css_process_update_tree(root->ss, cpu);
/* Return NULL if this subtree is not on-list */ if (!rstatc->updated_next) return NULL;
/* * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point.
*/
parent = root->parent; if (parent) { struct css_rstat_cpu *prstatc; struct cgroup_subsys_state **nextp;
/* Push @root to the list first before pushing the children */
head = root;
root->rstat_flush_next = NULL;
child = rstatc->updated_children;
rstatc->updated_children = root; if (child != root)
head = css_rstat_push_children(head, child, cpu);
return head;
}
/* * A hook for bpf stat collectors to attach to and flush their stats. * Together with providing bpf kfuncs for css_rstat_updated() and * css_rstat_flush(), this enables a complete workflow where bpf progs that * collect cgroup stats can integrate with rstat for efficient flushing. * * A static noinline declaration here could cause the compiler to optimize away * the function. A global noinline declaration will keep the definition, but may * optimize away the callsite. Therefore, __weak is needed to ensure that the * call is still emitted, by telling the compiler that we don't know what the * function might eventually be.
*/
/* * Helper functions for locking. * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @cpu_in_loop indicate lock * was released and re-taken when collection data from the CPUs. The * value -1 is used when obtaining the main lock else this is the CPU * number processed last.
*/ staticinlinevoid __css_rstat_lock(struct cgroup_subsys_state *css, int cpu_in_loop)
__acquires(ss_rstat_lock(css->ss))
{ struct cgroup *cgrp = css->cgroup;
spinlock_t *lock; bool contended;
/** * css_rstat_flush - flush stats in @css's rstat subtree * @css: target cgroup subsystem state * * Collect all per-cpu stats in @css's subtree into the global counters * and propagate them upwards. After this function returns, all rstat * nodes in the subtree have up-to-date ->stat. * * This also gets all rstat nodes in the subtree including @css off the * ->updated_children lists. * * This function may block.
*/
__bpf_kfunc void css_rstat_flush(struct cgroup_subsys_state *css)
{ int cpu; bool is_self = css_is_self(css);
/* * Since bpf programs can call this function, prevent access to * uninitialized rstat pointers.
*/ if (!css_uses_rstat(css)) return;
/* Reacquire for each CPU to avoid disabling IRQs too long */
__css_rstat_lock(css, cpu);
pos = css_rstat_updated_list(css, cpu); for (; pos; pos = pos->rstat_flush_next) { if (is_self) {
cgroup_base_stat_flush(pos->cgroup, cpu);
bpf_rstat_flush(pos->cgroup,
cgroup_parent(pos->cgroup), cpu);
} else
pos->ss->css_rstat_flush(pos, cpu);
}
__css_rstat_unlock(css, cpu); if (!cond_resched())
cpu_relax();
}
}
int css_rstat_init(struct cgroup_subsys_state *css)
{ struct cgroup *cgrp = css->cgroup; int cpu; bool is_self = css_is_self(css);
if (is_self) { /* the root cgrp has rstat_base_cpu preallocated */ if (!cgrp->rstat_base_cpu) {
cgrp->rstat_base_cpu = alloc_percpu(struct cgroup_rstat_base_cpu); if (!cgrp->rstat_base_cpu) return -ENOMEM;
}
} elseif (css->ss->css_rstat_flush == NULL) return 0;
/* the root cgrp's self css has rstat_cpu preallocated */ if (!css->rstat_cpu) {
css->rstat_cpu = alloc_percpu(struct css_rstat_cpu); if (!css->rstat_cpu) { if (is_self)
free_percpu(cgrp->rstat_base_cpu);
return -ENOMEM;
}
}
/* ->updated_children list is self terminated */
for_each_possible_cpu(cpu) { struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu);
/** * ss_rstat_init - subsystem-specific rstat initialization * @ss: target subsystem * * If @ss is NULL, the static locks associated with the base stats * are initialized. If @ss is non-NULL, the subsystem-specific locks * are initialized.
*/ int __init ss_rstat_init(struct cgroup_subsys *ss)
{ int cpu;
if (ss) {
ss->lhead = alloc_percpu(struct llist_head); if (!ss->lhead) return -ENOMEM;
}
/* Root-level stats are sourced from system-wide CPU stats */ if (!parent) return;
/* fetch the current per-cpu values */ do {
seq = __u64_stats_fetch_begin(&rstatbc->bsync);
delta = rstatbc->bstat;
} while (__u64_stats_fetch_retry(&rstatbc->bsync, seq));
/* propagate per-cpu delta to cgroup and per-cpu global statistics */
cgroup_base_stat_sub(&delta, &rstatbc->last_bstat);
cgroup_base_stat_add(&cgrp->bstat, &delta);
cgroup_base_stat_add(&rstatbc->last_bstat, &delta);
cgroup_base_stat_add(&rstatbc->subtree_bstat, &delta);
/* propagate cgroup and per-cpu global delta to parent (unless that's root) */ if (cgroup_parent(parent)) {
delta = cgrp->bstat;
cgroup_base_stat_sub(&delta, &cgrp->last_bstat);
cgroup_base_stat_add(&parent->bstat, &delta);
cgroup_base_stat_add(&cgrp->last_bstat, &delta);
/* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup.
*/ staticvoid root_cgroup_cputime(struct cgroup_base_stat *bstat)
{ struct task_cputime *cputime = &bstat->cputime; int i;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.