cpuset: use Union-Find to optimize the merging of cpumasks

The process of constructing scheduling domains
 involves multiple loops and repeated evaluations, leading to numerous
 redundant and ineffective assessments that impact code efficiency.

Here, we use union-find to optimize the merging of cpumasks. By employing
path compression and union by rank, we effectively reduce the number of
lookups and merge comparisons.

Signed-off-by: Xavier <xavier_qy@163.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 31aefc3e1a6a1849ab2d1e15cb01e8aa1b7581ae..9066f9b4af24ead89403b6602773e3586696303f 100644 (file)
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -46,6 +46,7 @@
 #include <linux/cgroup.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <linux/union_find.h>
 
 DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);
 DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
@@ -173,9 +174,6 @@ struct cpuset {
         */
        int attach_in_progress;
 
-       /* partition number for rebuild_sched_domains() */
-       int pn;
-
        /* for custom sched domain */
        int relax_domain_level;
 
@@ -207,6 +205,9 @@ struct cpuset {
 
        /* Remote partition silbling list anchored at remote_children */
        struct list_head remote_sibling;
+
+       /* Used to merge intersecting subsets for generate_sched_domains */
+       struct uf_node node;
 };
 
 /*
@@ -1007,18 +1008,15 @@ static inline int nr_cpusets(void)
  *        were changed (added or removed.)
  *
  * Finding the best partition (set of domains):
- *     The triple nested loops below over i, j, k scan over the
- *     load balanced cpusets (using the array of cpuset pointers in
- *     csa[]) looking for pairs of cpusets that have overlapping
- *     cpus_allowed, but which don't have the same 'pn' partition
- *     number and gives them in the same partition number.  It keeps
- *     looping on the 'restart' label until it can no longer find
- *     any such pairs.
+ *     The double nested loops below over i, j scan over the load
+ *     balanced cpusets (using the array of cpuset pointers in csa[])
+ *     looking for pairs of cpusets that have overlapping cpus_allowed
+ *     and merging them using a union-find algorithm.
+ *
+ *     The union of the cpus_allowed masks from the set of all cpusets
+ *     having the same root then form the one element of the partition
+ *     (one sched domain) to be passed to partition_sched_domains().
  *
- *     The union of the cpus_allowed masks from the set of
- *     all cpusets having the same 'pn' value then form the one
- *     element of the partition (one sched domain) to be passed to
- *     partition_sched_domains().
  */
 static int generate_sched_domains(cpumask_var_t **domains,
                        struct sched_domain_attr **attributes)
@@ -1026,7 +1024,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
        struct cpuset *cp;      /* top-down scan of cpusets */
        struct cpuset **csa;    /* array of all cpuset ptrs */
        int csn;                /* how many cpuset ptrs in csa so far */
-       int i, j, k;            /* indices for partition finding loops */
+       int i, j;               /* indices for partition finding loops */
        cpumask_var_t *doms;    /* resulting partition; i.e. sched domains */
        struct sched_domain_attr *dattr;  /* attributes for custom domains */
        int ndoms = 0;          /* number of sched domains in result */
@@ -1034,6 +1032,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
        struct cgroup_subsys_state *pos_css;
        bool root_load_balance = is_sched_load_balance(&top_cpuset);
        bool cgrpv2 = cgroup_subsys_on_dfl(cpuset_cgrp_subsys);
+       int nslot_update;
 
        doms = NULL;
        dattr = NULL;
@@ -1121,31 +1120,25 @@ v2:
        if (root_load_balance && (csn == 1))
                goto single_root_domain;
 
-       for (i = 0; i < csn; i++)
-               csa[i]->pn = i;
-       ndoms = csn;
-
-restart:
-       /* Find the best partition (set of sched domains) */
-       for (i = 0; i < csn; i++) {
-               struct cpuset *a = csa[i];
-               int apn = a->pn;
-
-               for (j = 0; j < csn; j++) {
-                       struct cpuset *b = csa[j];
-                       int bpn = b->pn;
-
-                       if (apn != bpn && cpusets_overlap(a, b)) {
-                               for (k = 0; k < csn; k++) {
-                                       struct cpuset *c = csa[k];
+       if (!cgrpv2) {
+               for (i = 0; i < csn; i++)
+                       uf_node_init(&csa[i]->node);
 
-                                       if (c->pn == bpn)
-                                               c->pn = apn;
-                               }
-                               ndoms--;        /* one less element */
-                               goto restart;
+               /* Merge overlapping cpusets */
+               for (i = 0; i < csn; i++) {
+                       for (j = i + 1; j < csn; j++) {
+                               if (cpusets_overlap(csa[i], csa[j]))
+                                       uf_union(&csa[i]->node, &csa[j]->node);
                        }
                }
+
+               /* Count the total number of domains */
+               for (i = 0; i < csn; i++) {
+                       if (uf_find(&csa[i]->node) == &csa[i]->node)
+                               ndoms++;
+               }
+       } else {
+               ndoms = csn;
        }
 
        /*
@@ -1178,44 +1171,25 @@ restart:
        }
 
        for (nslot = 0, i = 0; i < csn; i++) {
-               struct cpuset *a = csa[i];
-               struct cpumask *dp;
-               int apn = a->pn;
-
-               if (apn < 0) {
-                       /* Skip completed partitions */
-                       continue;
-               }
-
-               dp = doms[nslot];
-
-               if (nslot == ndoms) {
-                       static int warnings = 10;
-                       if (warnings) {
-                               pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d\n",
-                                       nslot, ndoms, csn, i, apn);
-                               warnings--;
-                       }
-                       continue;
-               }
-
-               cpumask_clear(dp);
-               if (dattr)
-                       *(dattr + nslot) = SD_ATTR_INIT;
+               nslot_update = 0;
                for (j = i; j < csn; j++) {
-                       struct cpuset *b = csa[j];
-
-                       if (apn == b->pn) {
-                               cpumask_or(dp, dp, b->effective_cpus);
+                       if (uf_find(&csa[j]->node) == &csa[i]->node) {
+                               struct cpumask *dp = doms[nslot];
+
+                               if (i == j) {
+                                       nslot_update = 1;
+                                       cpumask_clear(dp);
+                                       if (dattr)
+                                               *(dattr + nslot) = SD_ATTR_INIT;
+                               }
+                               cpumask_or(dp, dp, csa[j]->effective_cpus);
                                cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN));
                                if (dattr)
-                                       update_domain_attr_tree(dattr + nslot, b);
-
-                               /* Done with this partition */
-                               b->pn = -1;
+                                       update_domain_attr_tree(dattr + nslot, csa[j]);
                        }
                }
-               nslot++;
+               if (nslot_update)
+                       nslot++;
        }
        BUG_ON(nslot != ndoms);