[v3,11/11] mm/vmstat: refresh stats remotely instead of via work item

Commit Message

Marcelo Tosatti March 3, 2023, 7:58 p.m. UTC

Refresh per-CPU stats remotely, instead of queueing 
work items, for the stat_refresh procfs method.

This fixes sosreport hang (which uses vmstat_refresh) with
spinning SCHED_FIFO process.

Signed-off-by: Marcelo Tosatti <[e-mail]>

Patch

Index: linux-vmstat-remote/mm/vmstat.c
===================================================================
--- linux-vmstat-remote.orig/mm/vmstat.c
+++ linux-vmstat-remote/mm/vmstat.c
@@ -1860,11 +1860,21 @@  static DEFINE_PER_CPU(struct delayed_wor
 int sysctl_stat_interval __read_mostly = HZ;
 
 #ifdef CONFIG_PROC_FS
+
+#ifdef CONFIG_HAVE_CMPXCHG_LOCAL
+static int refresh_all_vm_stats(void);
+#else
 static void refresh_vm_stats(struct work_struct *work)
 {
 	refresh_cpu_vm_stats();
 }
 
+static int refresh_all_vm_stats(void)
+{
+	return schedule_on_each_cpu(refresh_vm_stats);
+}
+#endif
+
 int vmstat_refresh(struct ctl_table *table, int write,
 		   void *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -1886,7 +1896,7 @@  int vmstat_refresh(struct ctl_table *tab
 	 * transiently negative values, report an error here if any of
 	 * the stats is negative, so we know to go looking for imbalance.
 	 */
-	err = schedule_on_each_cpu(refresh_vm_stats);
+	err = refresh_all_vm_stats();
 	if (err)
 		return err;
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) {
@@ -2006,7 +2016,7 @@  static DECLARE_DEFERRABLE_WORK(shepherd,
 
 #ifdef CONFIG_HAVE_CMPXCHG_LOCAL
 /* Flush counters remotely if CPU uses cmpxchg to update its per-CPU counters */
-static void vmstat_shepherd(struct work_struct *w)
+static int refresh_all_vm_stats(void)
 {
 	int cpu;
 
@@ -2016,7 +2026,12 @@  static void vmstat_shepherd(struct work_
 		cond_resched();
 	}
 	cpus_read_unlock();
+	return 0;
+}
 
+static void vmstat_shepherd(struct work_struct *w)
+{
+	refresh_all_vm_stats();
 	schedule_delayed_work(&shepherd,
 		round_jiffies_relative(sysctl_stat_interval));
 }