Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Zi Yan <zi.yan@sent.com>
To:     linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc:     Dave Hansen <dave.hansen@linux.intel.com>,
        Michal Hocko <mhocko@kernel.org>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        Mel Gorman <mgorman@techsingularity.net>,
        John Hubbard <jhubbard@nvidia.com>,
        Mark Hairgrove <mhairgrove@nvidia.com>,
        Nitin Gupta <nigupta@nvidia.com>,
        David Nellans <dnellans@nvidia.com>, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH 25/31] mm: thp: add a knob to enable/disable 1GB THPs.
Date:   Fri, 15 Feb 2019 14:08:50 -0800
Message-Id: <20190215220856.29749-26-zi.yan@sent.com>
In-Reply-To: <20190215220856.29749-1-zi.yan@sent.com>
References: <20190215220856.29749-1-zi.yan@sent.com>
Reply-To: 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        | 42 ++++++++++++++++++++++++++++++++++++++++-
 mm/memory.c             |  2 +-
 3 files changed, 56 insertions(+), 2 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b1acada9ce8c..687c7d59df8b 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -84,6 +84,8 @@ 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;
@@ -146,6 +148,18 @@ 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_HUGEPAGE_REQ_MADV_FLAG))
+			return !!(vma->vm_flags & VM_HUGEPAGE);
+	}
+
+	return false;
+}
 
 #define transparent_hugepage_use_zero_page()				\
 	(transparent_hugepage_flags &					\
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 191261771452..fa3e12b17621 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -50,9 +50,11 @@
 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)|
@@ -276,6 +278,43 @@ 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)
@@ -405,6 +444,7 @@ static struct kobj_attribute debug_cow_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,
@@ -1657,7 +1697,7 @@ int do_huge_pud_wp_page(struct vm_fault *vmf, pud_t orig_pud)
 	get_page(page);
 	spin_unlock(vmf->ptl);
 alloc:
-	if (transparent_hugepage_enabled(vma) &&
+	if (transparent_pud_hugepage_enabled(vma) &&
 	    !transparent_hugepage_debug_cow()) {
 		huge_gfp = alloc_hugepage_direct_gfpmask(vma);
 		new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PUD_ORDER);
diff --git a/mm/memory.c b/mm/memory.c
index c875cc1a2600..5b8ad19cc439 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3859,7 +3859,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 	vmf.pud = pud_alloc(mm, p4d, address);
 	if (!vmf.pud)
 		return VM_FAULT_OOM;
-	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;
-- 
2.20.1