[patch v4 5/8] task isolation: sync vmstats conditional on changes

[Marcelo Tosatti <mtosatti@redhat.com>]

Rather than syncing VM-stats on every return to userspace
(or VM-entry), keep track of changes through a per-CPU bool.

This improves performance when enabling task isolated
for vcpu VMs.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Index: linux-2.6/include/linux/vmstat.h
===================================================================
--- linux-2.6.orig/include/linux/vmstat.h
+++ linux-2.6/include/linux/vmstat.h
@@ -22,7 +22,16 @@ int sysctl_vm_numa_stat_handler(struct c
 #endif
 
 #ifdef CONFIG_SMP
-void sync_vmstat(void);
+extern struct static_key vmstat_sync_enabled;
+
+void __sync_vmstat(void);
+static inline void sync_vmstat(void)
+{
+	if (static_key_false(&vmstat_sync_enabled))
+		__sync_vmstat();
+}
+
+void init_sync_vmstat(void);
 #else
 static inline void sync_vmstat(void)
 {
Index: linux-2.6/kernel/task_isolation.c
===================================================================
--- linux-2.6.orig/kernel/task_isolation.c
+++ linux-2.6/kernel/task_isolation.c
@@ -21,6 +21,17 @@
 #include <linux/mm.h>
 #include <linux/vmstat.h>
 
+void __tsk_isol_exit(struct task_struct *tsk)
+{
+	struct isol_info *i;
+
+	i = tsk->isol_info;
+	if (!i)
+		return;
+
+	static_key_slow_dec(&vmstat_sync_enabled);
+}
+
 void __tsk_isol_free(struct task_struct *tsk)
 {
 	if (!tsk->isol_info)
@@ -37,6 +48,12 @@ static struct isol_info *tsk_isol_alloc_
 	if (unlikely(!info))
 		return ERR_PTR(-ENOMEM);
 
+	preempt_disable();
+	init_sync_vmstat();
+	preempt_enable();
+
+	static_key_slow_inc(&vmstat_sync_enabled);
+
 	return info;
 }
 
Index: linux-2.6/mm/vmstat.c
===================================================================
--- linux-2.6.orig/mm/vmstat.c
+++ linux-2.6/mm/vmstat.c
@@ -28,6 +28,7 @@
 #include <linux/mm_inline.h>
 #include <linux/page_ext.h>
 #include <linux/page_owner.h>
+#include <linux/sched/isolation.h>
 
 #include "internal.h"
 
@@ -306,6 +307,22 @@ void set_pgdat_percpu_threshold(pg_data_
 	}
 }
 
+struct static_key vmstat_sync_enabled;
+static DEFINE_PER_CPU_ALIGNED(bool, vmstat_dirty);
+
+static inline void mark_vmstat_dirty(void)
+{
+	if (!static_key_false(&vmstat_sync_enabled))
+		return;
+
+	raw_cpu_write(vmstat_dirty, true);
+}
+
+void init_sync_vmstat(void)
+{
+	raw_cpu_write(vmstat_dirty, true);
+}
+
 /*
  * For use when we know that interrupts are disabled,
  * or when we know that preemption is disabled and that
@@ -338,6 +355,7 @@ void __mod_zone_page_state(struct zone *
 		x = 0;
 	}
 	__this_cpu_write(*p, x);
+	mark_vmstat_dirty();
 
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		preempt_enable();
@@ -376,6 +394,7 @@ void __mod_node_page_state(struct pglist
 		x = 0;
 	}
 	__this_cpu_write(*p, x);
+	mark_vmstat_dirty();
 
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		preempt_enable();
@@ -574,6 +593,7 @@ static inline void mod_zone_state(struct
 
 	if (z)
 		zone_page_state_add(z, zone, item);
+	mark_vmstat_dirty();
 }
 
 void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
@@ -642,6 +662,7 @@ static inline void mod_node_state(struct
 
 	if (z)
 		node_page_state_add(z, pgdat, item);
+	mark_vmstat_dirty();
 }
 
 void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
@@ -1082,6 +1103,7 @@ static void fill_contig_page_info(struct
 			info->free_blocks_suitable += blocks <<
 						(order - suitable_order);
 	}
+	mark_vmstat_dirty();
 }
 
 /*
@@ -1434,6 +1456,7 @@ static void walk_zones_in_node(struct se
 		if (!nolock)
 			spin_unlock_irqrestore(&zone->lock, flags);
 	}
+	mark_vmstat_dirty();
 }
 #endif
 
@@ -1499,6 +1522,7 @@ static void pagetypeinfo_showfree_print(
 		}
 		seq_putc(m, '\n');
 	}
+	mark_vmstat_dirty();
 }
 
 /* Print out the free pages at each order for each migatetype */
@@ -1917,6 +1941,7 @@ static void vmstat_update(struct work_st
 				this_cpu_ptr(&vmstat_work),
 				round_jiffies_relative(sysctl_stat_interval));
 	}
+	mark_vmstat_dirty();
 }
 
 /*
@@ -2003,13 +2028,18 @@ static void vmstat_shepherd(struct work_
 		round_jiffies_relative(sysctl_stat_interval));
 }
 
-void sync_vmstat(void)
+void __sync_vmstat(void)
 {
 	int cpu;
 
 	cpu = get_cpu();
+	if (per_cpu(vmstat_dirty, cpu) == false) {
+		put_cpu();
+		return;
+	}
 
 	refresh_cpu_vm_stats(false);
+	raw_cpu_write(vmstat_dirty, false);
 	put_cpu();
 
 	/*
Index: linux-2.6/include/linux/task_isolation.h
===================================================================
--- linux-2.6.orig/include/linux/task_isolation.h
+++ linux-2.6/include/linux/task_isolation.h
@@ -27,6 +27,13 @@ static inline void tsk_isol_free(struct
 		__tsk_isol_free(tsk);
 }
 
+void __tsk_isol_exit(struct task_struct *tsk);
+static inline void tsk_isol_exit(struct task_struct *tsk)
+{
+	if (tsk->isol_info)
+		__tsk_isol_exit(tsk);
+}
+
 int prctl_task_isolation_feat_get(unsigned long arg2, unsigned long arg3,
 				  unsigned long arg4, unsigned long arg5);
 int prctl_task_isolation_cfg_get(unsigned long arg2, unsigned long arg3,
@@ -58,6 +65,10 @@ static inline void tsk_isol_free(struct
 {
 }
 
+static inline void tsk_isol_exit(struct task_struct *tsk)
+{
+}
+
 static inline int prctl_task_isolation_feat_get(unsigned long arg2,
 						unsigned long arg3,
 						unsigned long arg4,
Index: linux-2.6/kernel/exit.c
===================================================================
--- linux-2.6.orig/kernel/exit.c
+++ linux-2.6/kernel/exit.c
@@ -64,6 +64,7 @@
 #include <linux/rcuwait.h>
 #include <linux/compat.h>
 #include <linux/io_uring.h>
+#include <linux/task_isolation.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -778,6 +779,7 @@ void __noreturn do_exit(long code)
 	}
 
 	io_uring_files_cancel();
+	tsk_isol_exit(tsk);
 	exit_signals(tsk);  /* sets PF_EXITING */
 
 	/* sync mm's RSS info before statistics gathering */
Index: linux-2.6/kernel/fork.c
===================================================================
--- linux-2.6.orig/kernel/fork.c
+++ linux-2.6/kernel/fork.c
@@ -2446,6 +2446,7 @@ bad_fork_free_pid:
 	if (pid != &init_struct_pid)
 		free_pid(pid);
 bad_fork_cleanup_task_isolation:
+	tsk_isol_exit(p);
 	tsk_isol_free(p);
 bad_fork_cleanup_thread:
 	exit_thread(p);