Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Zi Yan <zi.yan@sent.com>
To:     linux-mm@kvack.org, Roman Gushchin <guro@fb.com>
Cc:     Rik van Riel <riel@surriel.com>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        Matthew Wilcox <willy@infradead.org>,
        Shakeel Butt <shakeelb@google.com>,
        Yang Shi <yang.shi@linux.alibaba.com>,
        David Nellans <dnellans@nvidia.com>,
        linux-kernel@vger.kernel.org, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH 13/16] mm: thp: add a knob to enable/disable 1GB THPs.
Date:   Wed,  2 Sep 2020 14:06:25 -0400
Message-Id: <20200902180628.4052244-14-zi.yan@sent.com>
In-Reply-To: <20200902180628.4052244-1-zi.yan@sent.com>
References: <20200902180628.4052244-1-zi.yan@sent.com>
Reply-To: Zi Yan <ziy@nvidia.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Zi Yan <ziy@nvidia.com>

It does not affect existing 1GB THPs. It is similar to the knob for
2MB THPs.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/huge_mm.h | 14 ++++++++++++++
 mm/huge_memory.c        | 40 ++++++++++++++++++++++++++++++++++++++++
 mm/memory.c             |  2 +-
 3 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index c7bc40c4a5e2..3bf8d8a09f08 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -119,6 +119,8 @@ enum transparent_hugepage_flag {
 #ifdef CONFIG_DEBUG_VM
 	TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG,
 #endif
+	TRANSPARENT_PUD_HUGEPAGE_FLAG,
+	TRANSPARENT_PUD_HUGEPAGE_REQ_MADV_FLAG,
 };
 
 struct kobject;
@@ -184,6 +186,18 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
 }
 
 bool transparent_hugepage_enabled(struct vm_area_struct *vma);
+static inline bool transparent_pud_hugepage_enabled(struct vm_area_struct *vma)
+{
+	if (transparent_hugepage_enabled(vma)) {
+		if (transparent_hugepage_flags & (1 << TRANSPARENT_PUD_HUGEPAGE_FLAG))
+			return true;
+		if (transparent_hugepage_flags &
+					(1 << TRANSPARENT_PUD_HUGEPAGE_REQ_MADV_FLAG))
+			return !!(vma->vm_flags & VM_HUGEPAGE);
+	}
+
+	return false;
+}
 
 #define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - 1)
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e209c2dfc5b7..e1440a13da63 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -49,9 +49,11 @@
 unsigned long transparent_hugepage_flags __read_mostly =
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS
 	(1<<TRANSPARENT_HUGEPAGE_FLAG)|
+	(1<<TRANSPARENT_PUD_HUGEPAGE_FLAG)|
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE
 	(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
+	(1<<TRANSPARENT_PUD_HUGEPAGE_REQ_MADV_FLAG)|
 #endif
 	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG)|
 	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
@@ -199,6 +201,43 @@ static ssize_t enabled_store(struct kobject *kobj,
 static struct kobj_attribute enabled_attr =
 	__ATTR(enabled, 0644, enabled_show, enabled_store);
 
+static ssize_t enabled_1gb_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *buf)
+{
+	if (test_bit(TRANSPARENT_PUD_HUGEPAGE_FLAG, &transparent_hugepage_flags))
+		return sprintf(buf, "[always] madvise never\n");
+	else if (test_bit(TRANSPARENT_PUD_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags))
+		return sprintf(buf, "always [madvise] never\n");
+	else
+		return sprintf(buf, "always madvise [never]\n");
+}
+
+static ssize_t enabled_1gb_store(struct kobject *kobj,
+			     struct kobj_attribute *attr,
+			     const char *buf, size_t count)
+{
+	ssize_t ret = count;
+
+	if (!memcmp("always", buf,
+		    min(sizeof("always")-1, count))) {
+		clear_bit(TRANSPARENT_PUD_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_PUD_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("madvise", buf,
+			   min(sizeof("madvise")-1, count))) {
+		clear_bit(TRANSPARENT_PUD_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_PUD_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+	} else if (!memcmp("never", buf,
+			   min(sizeof("never")-1, count))) {
+		clear_bit(TRANSPARENT_PUD_HUGEPAGE_FLAG, &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_PUD_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
+	} else
+		ret = -EINVAL;
+
+	return ret;
+}
+static struct kobj_attribute enabled_1gb_attr =
+	__ATTR(enabled_1gb, 0644, enabled_1gb_show, enabled_1gb_store);
+
 ssize_t single_hugepage_flag_show(struct kobject *kobj,
 				struct kobj_attribute *attr, char *buf,
 				enum transparent_hugepage_flag flag)
@@ -305,6 +344,7 @@ static struct kobj_attribute hpage_pmd_size_attr =
 
 static struct attribute *hugepage_attr[] = {
 	&enabled_attr.attr,
+	&enabled_1gb_attr.attr,
 	&defrag_attr.attr,
 	&use_zero_page_attr.attr,
 	&hpage_pmd_size_attr.attr,
diff --git a/mm/memory.c b/mm/memory.c
index 184d8eb2d060..518f29a5903e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4305,7 +4305,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 	if (!vmf.pud)
 		return VM_FAULT_OOM;
 retry_pud:
-	if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) {
+	if (pud_none(*vmf.pud) && transparent_pud_hugepage_enabled(vma)) {
 		ret = create_huge_pud(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
-- 
2.28.0