linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Zi Yan <zi.yan@sent.com>
To: linux-mm@kvack.org
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	Roman Gushchin <guro@fb.com>, Rik van Riel <riel@surriel.com>,
	Matthew Wilcox <willy@infradead.org>,
	Shakeel Butt <shakeelb@google.com>,
	Yang Shi <shy828301@gmail.com>, Jason Gunthorpe <jgg@nvidia.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Michal Hocko <mhocko@suse.com>,
	David Hildenbrand <david@redhat.com>,
	William Kucharski <william.kucharski@oracle.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	John Hubbard <jhubbard@nvidia.com>,
	David Nellans <dnellans@nvidia.com>,
	linux-kernel@vger.kernel.org, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH v2 26/30] mm: thp: add a global knob to enable/disable PUD THPs.
Date: Mon, 28 Sep 2020 13:54:24 -0400	[thread overview]
Message-ID: <20200928175428.4110504-27-zi.yan@sent.com> (raw)
In-Reply-To: <20200928175428.4110504-1-zi.yan@sent.com>

From: Zi Yan <ziy@nvidia.com>

Like the existing global PMD THP knob, it allows user to enable/disable
PUD THPs. PUD THP is disabled by default unless user knows the
performance tradeoff of using it, like longer first time page fault
due to larger page zeroing and longer page allocation time when memory
is fragmented. Experienced user can enable it and take advantage of its
benefit of suffering fewer page faults and TLB misses.

* always means PUD THPs will be allocated on all VMAs if possible.
* madvise means PUD THPs will be allocated if vm_flags has VM_HUGEPAGE_PUD
  set via madvise syscall using MADV_HUGEPAGE | MADV_HUGEPAGE_PUD.
* none means PUD THPs will not be allocated on any VMA.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/huge_mm.h | 14 ++++++++++++++
 mm/huge_memory.c        | 38 ++++++++++++++++++++++++++++++++++++++
 mm/memory.c             |  2 +-
 3 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index c7bc40c4a5e2..0d0f9cf25aeb 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_PUD);
+	}
+
+	return false;
+}
 
 #define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - 1)
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 61ae7a0ded84..1965753b31a2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -199,6 +199,43 @@ 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_pud_thp_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_pud_thp_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_pud_thp_attr =
+	__ATTR(enabled_pud_thp, 0644, enabled_pud_thp_show, enabled_pud_thp_store);
+
 ssize_t single_hugepage_flag_show(struct kobject *kobj,
 				struct kobj_attribute *attr, char *buf,
 				enum transparent_hugepage_flag flag)
@@ -305,6 +342,7 @@ static struct kobj_attribute hpage_pmd_size_attr =
 
 static struct attribute *hugepage_attr[] = {
 	&enabled_attr.attr,
+	&enabled_pud_thp_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 ab80d13807aa..9f7b509a3aa7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4282,7 +4282,7 @@ 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


  parent reply	other threads:[~2020-09-28 18:02 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-28 17:53 [RFC PATCH v2 00/30] 1GB PUD THP support on x86_64 Zi Yan
2020-09-28 17:53 ` [RFC PATCH v2 01/30] mm/pagewalk: use READ_ONCE when reading the PUD entry unlocked Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 02/30] mm: pagewalk: use READ_ONCE when reading the PMD " Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 03/30] mm: thp: use single linked list for THP page table page deposit Zi Yan
2020-09-28 19:34   ` Matthew Wilcox
2020-09-28 20:34     ` Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 04/30] mm: add new helper functions to allocate one PMD page with 512 PTE pages Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 05/30] mm: thp: add page table deposit/withdraw functions for PUD THP Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 06/30] mm: change thp_order and thp_nr as we will have not just PMD THPs Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 07/30] mm: thp: add anonymous PUD THP page fault support without enabling it Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 08/30] mm: thp: add PUD THP support for copy_huge_pud Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 09/30] mm: thp: add PUD THP support to zap_huge_pud Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 10/30] fs: proc: add PUD THP kpageflag Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 11/30] mm: thp: handling PUD THP reference bit Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 12/30] mm: rmap: add mappped/unmapped page order to anonymous page rmap functions Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 13/30] mm: rmap: add map_order to page_remove_anon_compound_rmap Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 14/30] mm: thp: add PUD THP split_huge_pud_page() function Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 15/30] mm: thp: add PUD THP to deferred split list when PUD mapping is gone Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 16/30] mm: debug: adapt dump_page to PUD THP Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 17/30] mm: thp: PUD THP COW splits PUD page and falls back to PMD page Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 18/30] mm: thp: PUD THP follow_p*d_page() support Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 19/30] mm: stats: make smap stats understand PUD THPs Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 20/30] mm: page_vma_walk: teach it about PMD-mapped PUD THP Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 21/30] mm: thp: PUD THP support in try_to_unmap() Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 22/30] mm: thp: split PUD THPs at page reclaim Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 23/30] mm: support PUD THP pagemap support Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 24/30] mm: madvise: add page size options to MADV_HUGEPAGE and MADV_NOHUGEPAGE Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 25/30] mm: vma: add VM_HUGEPAGE_PUD to vm_flags at bit 37 Zi Yan
2020-09-28 17:54 ` Zi Yan [this message]
2020-09-28 17:54 ` [RFC PATCH v2 27/30] mm: thp: make PUD THP size public Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 28/30] hugetlb: cma: move cma reserve function to cma.c Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 29/30] mm: thp: use cma reservation for pud thp allocation Zi Yan
2020-09-28 17:54 ` [RFC PATCH v2 30/30] mm: thp: enable anonymous PUD THP at page fault path Zi Yan
2020-09-30 11:55 ` [RFC PATCH v2 00/30] 1GB PUD THP support on x86_64 Michal Hocko
2020-10-01 15:14   ` Zi Yan
2020-10-02  7:32     ` Michal Hocko
2020-10-02  7:50       ` David Hildenbrand
2020-10-02  8:10         ` Michal Hocko
2020-10-02  8:30           ` David Hildenbrand
2020-10-05 15:03             ` Zi Yan
2020-10-05 15:55               ` Matthew Wilcox
2020-10-05 17:04                 ` Roman Gushchin
2020-10-05 19:12                 ` Zi Yan
2020-10-05 19:37                   ` Matthew Wilcox
2020-10-05 17:16               ` Roman Gushchin
2020-10-05 17:27                 ` David Hildenbrand
2020-10-05 18:25                   ` Roman Gushchin
2020-10-05 18:33                     ` David Hildenbrand
2020-10-05 19:11                       ` Roman Gushchin
2020-10-06  8:25                         ` David Hildenbrand
2020-10-05 17:39               ` David Hildenbrand
2020-10-05 18:05                 ` Zi Yan
2020-10-05 18:48                   ` David Hildenbrand
2020-10-06 11:59                   ` Michal Hocko
2020-10-05 15:34         ` Zi Yan
2020-10-05 17:30           ` David Hildenbrand

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200928175428.4110504-27-zi.yan@sent.com \
    --to=zi.yan@sent.com \
    --cc=aarcange@redhat.com \
    --cc=david@redhat.com \
    --cc=dnellans@nvidia.com \
    --cc=guro@fb.com \
    --cc=jgg@nvidia.com \
    --cc=jhubbard@nvidia.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=riel@surriel.com \
    --cc=shakeelb@google.com \
    --cc=shy828301@gmail.com \
    --cc=william.kucharski@oracle.com \
    --cc=willy@infradead.org \
    --cc=ziy@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).