summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-10-30 13:12:15 -1000
committerLinus Torvalds <torvalds@linux-foundation.org>2023-10-30 13:12:15 -1000
commit63ce50fff9240d66cf3b59663f458f55ba6dcfcc (patch)
treec2613289116d6f80a50f534e9c5e4afc26064574 /mm
parent3cf3fabccb9dc821ffaec3ad6bf0cd6b278bd012 (diff)
parent984ffb6a4366752c949f7b39640aecdce222607f (diff)
Merge tag 'sched-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar: "Fair scheduler (SCHED_OTHER) improvements: - Remove the old and now unused SIS_PROP code & option - Scan cluster before LLC in the wake-up path - Use candidate prev/recent_used CPU if scanning failed for cluster wakeup NUMA scheduling improvements: - Improve the VMA access-PID code to better skip/scan VMAs - Extend tracing to cover VMA-skipping decisions - Improve/fix the recently introduced sched_numa_find_nth_cpu() code - Generalize numa_map_to_online_node() Energy scheduling improvements: - Remove the EM_MAX_COMPLEXITY limit - Add tracepoints to track energy computation - Make the behavior of the 'sched_energy_aware' sysctl more consistent - Consolidate and clean up access to a CPU's max compute capacity - Fix uclamp code corner cases RT scheduling improvements: - Drive dl_rq->overloaded with dl_rq->pushable_dl_tasks updates - Drive the ->rto_mask with rt_rq->pushable_tasks updates Scheduler scalability improvements: - Rate-limit updates to tg->load_avg - On x86 disable IBRS when CPU is offline to improve single-threaded performance - Micro-optimize in_task() and in_interrupt() - Micro-optimize the PSI code - Avoid updating PSI triggers and ->rtpoll_total when there are no state changes Core scheduler infrastructure improvements: - Use saved_state to reduce some spurious freezer wakeups - Bring in a handful of fast-headers improvements to scheduler headers - Make the scheduler UAPI headers more widely usable by user-space - Simplify the control flow of scheduler syscalls by using lock guards - Fix sched_setaffinity() vs. CPU hotplug race Scheduler debuggability improvements: - Disallow writing invalid values to sched_rt_period_us - Fix a race in the rq-clock debugging code triggering warnings - Fix a warning in the bandwidth distribution code - Micro-optimize in_atomic_preempt_off() checks - Enforce that the tasklist_lock is held in for_each_thread() - Print the TGID in sched_show_task() - Remove the /proc/sys/kernel/sched_child_runs_first sysctl ... and misc cleanups & fixes" * tag 'sched-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (82 commits) sched/fair: Remove SIS_PROP sched/fair: Use candidate prev/recent_used CPU if scanning failed for cluster wakeup sched/fair: Scan cluster before scanning LLC in wake-up path sched: Add cpus_share_resources API sched/core: Fix RQCF_ACT_SKIP leak sched/fair: Remove unused 'curr' argument from pick_next_entity() sched/nohz: Update comments about NEWILB_KICK sched/fair: Remove duplicate #include sched/psi: Update poll => rtpoll in relevant comments sched: Make PELT acronym definition searchable sched: Fix stop_one_cpu_nowait() vs hotplug sched/psi: Bail out early from irq time accounting sched/topology: Rename 'DIE' domain to 'PKG' sched/psi: Delete the 'update_total' function parameter from update_triggers() sched/psi: Avoid updating PSI triggers and ->rtpoll_total when there are no state changes sched/headers: Remove comment referring to rq::cpu_load, since this has been removed sched/numa: Complete scanning of inactive VMAs when there is no alternative sched/numa: Complete scanning of partial VMAs regardless of PID activity sched/numa: Move up the access pid reset logic sched/numa: Trace decisions related to skipping VMAs ...
Diffstat (limited to 'mm')
-rw-r--r--mm/mempolicy.c18
1 files changed, 11 insertions, 7 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 29ebf1e7898c..e52e3a0b8f2e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -131,22 +131,26 @@ static struct mempolicy default_policy = {
static struct mempolicy preferred_node_policy[MAX_NUMNODES];
/**
- * numa_map_to_online_node - Find closest online node
+ * numa_nearest_node - Find nearest node by state
* @node: Node id to start the search
+ * @state: State to filter the search
*
- * Lookup the next closest node by distance if @nid is not online.
+ * Lookup the closest node by distance if @nid is not in state.
*
- * Return: this @node if it is online, otherwise the closest node by distance
+ * Return: this @node if it is in state, otherwise the closest node by distance
*/
-int numa_map_to_online_node(int node)
+int numa_nearest_node(int node, unsigned int state)
{
int min_dist = INT_MAX, dist, n, min_node;
- if (node == NUMA_NO_NODE || node_online(node))
+ if (state >= NR_NODE_STATES)
+ return -EINVAL;
+
+ if (node == NUMA_NO_NODE || node_state(node, state))
return node;
min_node = node;
- for_each_online_node(n) {
+ for_each_node_state(n, state) {
dist = node_distance(node, n);
if (dist < min_dist) {
min_dist = dist;
@@ -156,7 +160,7 @@ int numa_map_to_online_node(int node)
return min_node;
}
-EXPORT_SYMBOL_GPL(numa_map_to_online_node);
+EXPORT_SYMBOL_GPL(numa_nearest_node);
struct mempolicy *get_task_policy(struct task_struct *p)
{