mm/compaction: Disable compact_unevictable_allowed on RT

Since commit 5bbe3547aa3ba ("mm: allow compaction of unevictable pages")
it is allowed to examine mlocked pages and compact them by default.  On
-RT even minor pagefaults are problematic because it may take a few 100us
to resolve them and until then the task is blocked.

Make compact_unevictable_allowed = 0 default and issue a warning on RT if
it is changed.

[bigeasy@linutronix.de: v5]
Link: https://lore.kernel.org/linux-mm/20190710144138.qyn4tuttdq6h7kqx@linutronix.de/
Link: http://lkml.kernel.org/r/20200319165536.ovi75tsr2seared4@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/linux-mm/20190710144138.qyn4tuttdq6h7kqx@linutronix.de/
Link: http://lkml.kernel.org/r/20200303202225.nhqc3v5gwlb7x6et@linutronix.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index 64aeee1..0329a4d 100644 (file)
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -128,6 +128,9 @@ allowed to examine the unevictable lru (mlocked pages) for pages to compact.
 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 cb650bb..8a176d8 100644 (file)
--- 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
@@ -1467,7 +1472,7 @@ static struct ctl_table vm_table[] = {
                .data           = &sysctl_compact_unevictable_allowed,
                .maxlen         = sizeof(int),
                .mode           = 0644,
-               .proc_handler   = proc_dointvec_minmax,
+               .proc_handler   = proc_dointvec_minmax_warn_RT_change,
                .extra1         = SYSCTL_ZERO,
                .extra2         = SYSCTL_ONE,
        },
@@ -2555,6 +2560,28 @@ 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 0794738..c589ead 100644 (file)
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1594,7 +1594,11 @@ typedef enum {
  * Allow userspace to control policy on scanning the unevictable LRU for
  * compactable pages.
  */
+#ifdef CONFIG_PREEMPT_RT
+int sysctl_compact_unevictable_allowed __read_mostly = 0;
+#else
 int sysctl_compact_unevictable_allowed __read_mostly = 1;
+#endif
 
 static inline void
 update_fast_start_pfn(struct compact_control *cc, unsigned long pfn)