mm, thp: add new defer+madvise defrag option

There is no thp defrag option that currently allows MADV_HUGEPAGE
regions to do direct compaction and reclaim while all other thp
allocations simply trigger kswapd and kcompactd in the background and
fail immediately.

The "defer" setting simply triggers background reclaim and compaction
for all regions, regardless of MADV_HUGEPAGE, which makes it unusable
for our userspace where MADV_HUGEPAGE is being used to indicate the
application is willing to wait for work for thp memory to be available.

The "madvise" setting will do direct compaction and reclaim for these
MADV_HUGEPAGE regions, but does not trigger kswapd and kcompactd in the
background for anybody else.

For reasonable usage, there needs to be a mesh between the two options.
This patch introduces a fifth mode, "defer+madvise", that will do direct
reclaim and compaction for MADV_HUGEPAGE regions and trigger background
reclaim and compaction for everybody else so that hugepages may be
available in the near future.

A proposal to allow direct reclaim and compaction for MADV_HUGEPAGE
regions as part of the "defer" mode, making it a very powerful setting
and avoids breaking userspace, was offered:
     http://marc.info/?t=148236612700003
This additional mode is a compromise.

A second proposal to allow both "defer" and "madvise" to be selected at
the same time was also offered:
     http://marc.info/?t=148357345300001.
This is possible, but there was a concern that it might break existing
userspaces the parse the output of the defrag mode, so the fifth option
was introduced instead.

This patch also cleans up the helper function for storing to "enabled"
and "defrag" since the former supports three modes while the latter
supports five and triple_flag_store() was getting unnecessarily messy.

Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1701101614330.41805@chino.kir.corp.google.com
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 82 insertions, 73 deletions

diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
index c4171e4519c2..8fda5b7b24e9 100644
--- a/Documentation/vm/transhuge.txt
+++ b/Documentation/vm/transhuge.txt
@@ -110,6 +110,7 @@ MADV_HUGEPAGE region.
 
 echo always >/sys/kernel/mm/transparent_hugepage/defrag
 echo defer >/sys/kernel/mm/transparent_hugepage/defrag
+echo defer+madvise >/sys/kernel/mm/transparent_hugepage/defrag
 echo madvise >/sys/kernel/mm/transparent_hugepage/defrag
 echo never >/sys/kernel/mm/transparent_hugepage/defrag
 
@@ -120,10 +121,15 @@ that benefit heavily from THP use and are willing to delay the VM start
 to utilise them.
 
 "defer" means that an application will wake kswapd in the background
-to reclaim pages and wake kcompact to compact memory so that THP is
+to reclaim pages and wake kcompactd to compact memory so that THP is
 available in the near future. It's the responsibility of khugepaged
 to then install the THP pages later.
 
+"defer+madvise" will enter direct reclaim and compaction like "always", but
+only for regions that have used madvise(MADV_HUGEPAGE); all other regions
+will wake kswapd in the background to reclaim pages and wake kcompactd to
+compact memory so that THP is available in the near future.
+
 "madvise" will enter direct reclaim like "always" but only for regions
 that are have used madvise(MADV_HUGEPAGE). This is the default behaviour.
 
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 97e478d6b690..f0029e786205 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -33,6 +33,7 @@ enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
+	TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG,
 	TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5f3ad65c85de..f9ecc2aeadfc 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -142,42 +142,6 @@ static struct shrinker huge_zero_page_shrinker = {
 };
 
 #ifdef CONFIG_SYSFS
-
-static ssize_t triple_flag_store(struct kobject *kobj,
-				 struct kobj_attribute *attr,
-				 const char *buf, size_t count,
-				 enum transparent_hugepage_flag enabled,
-				 enum transparent_hugepage_flag deferred,
-				 enum transparent_hugepage_flag req_madv)
-{
-	if (!memcmp("defer", buf,
-		    min(sizeof("defer")-1, count))) {
-		if (enabled == deferred)
-			return -EINVAL;
-		clear_bit(enabled, &transparent_hugepage_flags);
-		clear_bit(req_madv, &transparent_hugepage_flags);
-		set_bit(deferred, &transparent_hugepage_flags);
-	} else if (!memcmp("always", buf,
-		    min(sizeof("always")-1, count))) {
-		clear_bit(deferred, &transparent_hugepage_flags);
-		clear_bit(req_madv, &transparent_hugepage_flags);
-		set_bit(enabled, &transparent_hugepage_flags);
-	} else if (!memcmp("madvise", buf,
-			   min(sizeof("madvise")-1, count))) {
-		clear_bit(enabled, &transparent_hugepage_flags);
-		clear_bit(deferred, &transparent_hugepage_flags);
-		set_bit(req_madv, &transparent_hugepage_flags);
-	} else if (!memcmp("never", buf,
-			   min(sizeof("never")-1, count))) {
-		clear_bit(enabled, &transparent_hugepage_flags);
-		clear_bit(req_madv, &transparent_hugepage_flags);
-		clear_bit(deferred, &transparent_hugepage_flags);
-	} else
-		return -EINVAL;
-
-	return count;
-}
-
 static ssize_t enabled_show(struct kobject *kobj,
 			    struct kobj_attribute *attr, char *buf)
 {
@@ -193,19 +157,28 @@ static ssize_t enabled_store(struct kobject *kobj,
 			     struct kobj_attribute *attr,
 			     const char *buf, size_t count)
 {
-	ssize_t ret;
+	ssize_t ret = count;
 
-	ret = triple_flag_store(kobj, attr, buf, count,
-				TRANSPARENT_HUGEPAGE_FLAG,
-				TRANSPARENT_HUGEPAGE_FLAG,
-				TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
+	if (!memcmp("always", buf,
+		    min(sizeof("always")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("madvise", buf,
+			   min(sizeof("madvise")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("never", buf,
+			   min(sizeof("never")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+	} else
+		ret = -EINVAL;
 
 	if (ret > 0) {
 		int err = start_stop_khugepaged();
 		if (err)
 			ret = err;
 	}
-
 	return ret;
 }
 static struct kobj_attribute enabled_attr =
@@ -241,32 +214,58 @@ ssize_t single_hugepage_flag_store(struct kobject *kobj,
 	return count;
 }
 
-/*
- * Currently defrag only disables __GFP_NOWAIT for allocation. A blind
- * __GFP_REPEAT is too aggressive, it's never worth swapping tons of
- * memory just to allocate one more hugepage.
- */
 static ssize_t defrag_show(struct kobject *kobj,
 			   struct kobj_attribute *attr, char *buf)
 {
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
-		return sprintf(buf, "[always] defer madvise never\n");
+		return sprintf(buf, "[always] defer defer+madvise madvise never\n");
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
-		return sprintf(buf, "always [defer] madvise never\n");
-	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
-		return sprintf(buf, "always defer [madvise] never\n");
-	else
-		return sprintf(buf, "always defer madvise [never]\n");
-
+		return sprintf(buf, "always [defer] defer+madvise madvise never\n");
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
+		return sprintf(buf, "always defer [defer+madvise] madvise never\n");
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
+		return sprintf(buf, "always defer defer+madvise [madvise] never\n");
+	return sprintf(buf, "always defer defer+madvise madvise [never]\n");
 }
+
 static ssize_t defrag_store(struct kobject *kobj,
 			    struct kobj_attribute *attr,
 			    const char *buf, size_t count)
 {
-	return triple_flag_store(kobj, attr, buf, count,
-				 TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
-				 TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
-				 TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
+	if (!memcmp("always", buf,
+		    min(sizeof("always")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("defer", buf,
+		    min(sizeof("defer")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("defer+madvise", buf,
+		    min(sizeof("defer+madvise")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("madvise", buf,
+			   min(sizeof("madvise")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("never", buf,
+			   min(sizeof("never")-1, count))) {
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+	} else
+		return -EINVAL;
+
+	return count;
 }
 static struct kobj_attribute defrag_attr =
 	__ATTR(defrag, 0644, defrag_show, defrag_store);
@@ -612,25 +611,28 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 }
 
 /*
- * If THP defrag is set to always then directly reclaim/compact as necessary
- * If set to defer then do only background reclaim/compact and defer to khugepaged
- * If set to madvise and the VMA is flagged then directly reclaim/compact
- * When direct reclaim/compact is allowed, don't retry except for flagged VMA's
+ * always: directly stall for all thp allocations
+ * defer: wake kswapd and fail if not immediately available
+ * defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise
+ *		  fail if not immediately available
+ * madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately
+ *	    available
+ * never: never stall for any thp allocation
  */
 static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
 {
-	bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+	const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
 
-	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
-				&transparent_hugepage_flags) && vma_madvised)
-		return GFP_TRANSHUGE;
-	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
-						&transparent_hugepage_flags))
-		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
-	else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
-						&transparent_hugepage_flags))
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
-
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
+		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
+		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
+							     __GFP_KSWAPD_RECLAIM);
+	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
+		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
+							     0);
 	return GFP_TRANSHUGE_LIGHT;
 }