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 [thread overview]
Message-ID: <20190215220856.29749-26-zi.yan@sent.com> (raw)
In-Reply-To: <20190215220856.29749-1-zi.yan@sent.com>
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
next prev parent reply other threads:[~2019-02-15 22:10 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-15 22:08 [RFC PATCH 00/31] Generating physically contiguous memory after page allocation Zi Yan
2019-02-15 22:08 ` [RFC PATCH 01/31] mm: migrate: Add exchange_pages to exchange two lists of pages Zi Yan
2019-02-17 11:29 ` Matthew Wilcox
2019-02-18 17:31 ` Zi Yan
2019-02-18 17:42 ` Vlastimil Babka
2019-02-18 17:51 ` Zi Yan
2019-02-18 17:52 ` Matthew Wilcox
2019-02-18 17:59 ` Zi Yan
2019-02-19 7:42 ` Anshuman Khandual
2019-02-19 12:56 ` Matthew Wilcox
2019-02-20 4:38 ` Anshuman Khandual
2019-03-14 2:39 ` Zi Yan
2019-02-21 21:10 ` Jerome Glisse
2019-02-21 21:25 ` Zi Yan
2019-02-15 22:08 ` [RFC PATCH 02/31] mm: migrate: Add THP exchange support Zi Yan
2019-02-15 22:08 ` [RFC PATCH 03/31] mm: migrate: Add tmpfs " Zi Yan
2019-02-15 22:08 ` [RFC PATCH 04/31] mm: add mem_defrag functionality Zi Yan
2019-02-15 22:08 ` [RFC PATCH 05/31] mem_defrag: split a THP if either src or dst is THP only Zi Yan
2019-02-15 22:08 ` [RFC PATCH 06/31] mm: Make MAX_ORDER configurable in Kconfig for buddy allocator Zi Yan
2019-02-15 22:08 ` [RFC PATCH 07/31] mm: deallocate pages with order > MAX_ORDER Zi Yan
2019-02-15 22:08 ` [RFC PATCH 08/31] mm: add pagechain container for storing multiple pages Zi Yan
2019-02-15 22:08 ` [RFC PATCH 09/31] mm: thp: 1GB anonymous page implementation Zi Yan
2019-02-15 22:08 ` [RFC PATCH 10/31] mm: proc: add 1GB THP kpageflag Zi Yan
2019-02-15 22:08 ` [RFC PATCH 11/31] mm: debug: print compound page order in dump_page() Zi Yan
2019-02-15 22:08 ` [RFC PATCH 12/31] mm: stats: Separate PMD THP and PUD THP stats Zi Yan
2019-02-15 22:08 ` [RFC PATCH 13/31] mm: thp: 1GB THP copy on write implementation Zi Yan
2019-02-15 22:08 ` [RFC PATCH 14/31] mm: thp: handling 1GB THP reference bit Zi Yan
2019-02-15 22:08 ` [RFC PATCH 15/31] mm: thp: add 1GB THP split_huge_pud_page() function Zi Yan
2019-02-15 22:08 ` [RFC PATCH 16/31] mm: thp: check compound_mapcount of PMD-mapped PUD THPs at free time Zi Yan
2019-02-15 22:08 ` [RFC PATCH 17/31] mm: thp: split properly PMD-mapped PUD THP to PTE-mapped PUD THP Zi Yan
2019-02-15 22:08 ` [RFC PATCH 18/31] mm: page_vma_walk: teach it about PMD-mapped " Zi Yan
2019-02-15 22:08 ` [RFC PATCH 19/31] mm: thp: 1GB THP support in try_to_unmap() Zi Yan
2019-02-15 22:08 ` [RFC PATCH 20/31] mm: thp: split 1GB THPs at page reclaim Zi Yan
2019-02-15 22:08 ` [RFC PATCH 21/31] mm: thp: 1GB zero page shrinker Zi Yan
2019-02-15 22:08 ` [RFC PATCH 22/31] mm: thp: 1GB THP follow_p*d_page() support Zi Yan
2019-02-15 22:08 ` [RFC PATCH 23/31] mm: support 1GB THP pagemap support Zi Yan
2019-02-15 22:08 ` [RFC PATCH 24/31] sysctl: add an option to only print the head page virtual address Zi Yan
2019-02-15 22:08 ` Zi Yan [this message]
2019-02-15 22:08 ` [RFC PATCH 26/31] mm: thp: promote PTE-mapped THP to PMD-mapped THP Zi Yan
2019-02-15 22:08 ` [RFC PATCH 27/31] mm: thp: promote PMD-mapped PUD pages to PUD-mapped PUD pages Zi Yan
2019-02-15 22:08 ` [RFC PATCH 28/31] mm: vmstats: add page promotion stats Zi Yan
2019-02-15 22:08 ` [RFC PATCH 29/31] mm: madvise: add madvise options to split PMD and PUD THPs Zi Yan
2019-02-15 22:08 ` [RFC PATCH 30/31] mm: mem_defrag: thp: PMD THP and PUD THP in-place promotion support Zi Yan
2019-02-15 22:08 ` [RFC PATCH 31/31] sysctl: toggle to promote PUD-mapped 1GB THP or not Zi Yan
2019-02-20 1:42 ` [RFC PATCH 00/31] Generating physically contiguous memory after page allocation Mike Kravetz
2019-02-20 2:33 ` Zi Yan
2019-02-20 3:18 ` Mike Kravetz
2019-02-20 5:19 ` Zi Yan
2019-02-20 5:27 ` Mike Kravetz
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=20190215220856.29749-26-zi.yan@sent.com \
--to=zi.yan@sent.com \
--cc=akpm@linux-foundation.org \
--cc=dave.hansen@linux.intel.com \
--cc=dnellans@nvidia.com \
--cc=jhubbard@nvidia.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=mhairgrove@nvidia.com \
--cc=mhocko@kernel.org \
--cc=nigupta@nvidia.com \
--cc=vbabka@suse.cz \
--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).