mm/compaction: Disable compact_unevictable_allowed on RT (Update)
This is an all-on-one change to align the state of the patch with what
has been submit upstream. This includes the following patches:
[PATCH 1/2] mm/compaction: Really limit compact_unevictable_allowed to 0…1
[PATCH 2/2 v5] mm/compaction: Disable compact_unevictable_allowed on RT
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index 64aeee1..0329a4d 100644
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -128,6 +128,9 @@
This should be used on systems where stalls for minor page faults are an
acceptable trade for large contiguous free memory. Set to 0 to prevent
compaction from moving pages that are unevictable. Default value is 1.
+On CONFIG_PREEMPT_RT the default value is 0 in order to avoid a page fault, due
+to compaction, which would block the task from becomming active until the fault
+is resolved.
dirty_background_bytes
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index d08bd51..8221219 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -212,6 +212,11 @@ static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
static int proc_taint(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
+#ifdef CONFIG_COMPACTION
+static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table,
+ int write, void __user *buffer,
+ size_t *lenp, loff_t *ppos);
+#endif
#endif
#ifdef CONFIG_PRINTK
@@ -1488,17 +1493,16 @@ static struct ctl_table vm_table[] = {
.extra1 = &min_extfrag_threshold,
.extra2 = &max_extfrag_threshold,
},
-#ifndef CONFIG_PREEMPT_RT
{
.procname = "compact_unevictable_allowed",
.data = &sysctl_compact_unevictable_allowed,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax_warn_RT_change,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
-#endif
+
#endif /* CONFIG_COMPACTION */
{
.procname = "min_free_kbytes",
@@ -2582,6 +2586,28 @@ int proc_dointvec(struct ctl_table *table, int write,
return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
}
+#ifdef CONFIG_COMPACTION
+static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table,
+ int write, void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int ret, old;
+
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write)
+ return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+ old = *(int *)table->data;
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ if (ret)
+ return ret;
+ if (old != *(int *)table->data)
+ pr_warn_once("sysctl attribute %s changed by %s[%d]\n",
+ table->procname, current->comm,
+ task_pid_nr(current));
+ return ret;
+}
+#endif
+
/**
* proc_douintvec - read a vector of unsigned integers
* @table: the sysctl table
diff --git a/mm/compaction.c b/mm/compaction.c
index 83cc3d1..31e6e10 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1591,7 +1591,7 @@ typedef enum {
* compactable pages.
*/
#ifdef CONFIG_PREEMPT_RT
-#define sysctl_compact_unevictable_allowed 0
+int sysctl_compact_unevictable_allowed __read_mostly = 0;
#else
int sysctl_compact_unevictable_allowed __read_mostly = 1;
#endif
