This part of the patch adds a tunable to
/sys/kernel/mm/transparent_hugepage called threshold. This threshold
determines how many pages a user must fault in from a single node before
a temporary compound page is turned into a THP.
Signed-off-by: Alex Thorlton <athorl...@sgi.com>
Cc: Andrew Morton <a...@linux-foundation.org>
Cc: Nate Zimmer <nzim...@sgi.com>
Cc: Cliff Wickman <c...@sgi.com>
Cc: "Kirill A. Shutemov" <kirill.shute...@linux.intel.com>
Cc: Benjamin Herrenschmidt <b...@kernel.crashing.org>
Cc: Rik van Riel <r...@redhat.com>
Cc: Wanpeng Li <liw...@linux.vnet.ibm.com>
Cc: Mel Gorman <mgor...@suse.de>
Cc: Michel Lespinasse <wal...@google.com>
Cc: Benjamin LaHaise <b...@kvack.org>
Cc: Oleg Nesterov <o...@redhat.com>
Cc: "Eric W. Biederman" <ebied...@xmission.com>
Cc: Andy Lutomirski <l...@amacapital.net>
Cc: Al Viro <v...@zeniv.linux.org.uk>
Cc: David Rientjes <rient...@google.com>
Cc: Zhang Yanfei <zhangyan...@cn.fujitsu.com>
Cc: Peter Zijlstra <pet...@infradead.org>
Cc: Johannes Weiner <han...@cmpxchg.org>
Cc: Michal Hocko <mho...@suse.cz>
Cc: Jiang Liu <jiang....@huawei.com>
Cc: Cody P Schafer <c...@linux.vnet.ibm.com>
Cc: Glauber Costa <glom...@parallels.com>
Cc: Kamezawa Hiroyuki <kamezawa.hir...@jp.fujitsu.com>
Cc: David Rientjes <rient...@google.com>
Cc: Naoya Horiguchi <n-horigu...@ah.jp.nec.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux...@kvack.org
---
include/linux/huge_mm.h | 2 ++
include/linux/mm_types.h | 1 +
mm/huge_memory.c | 30 ++++++++++++++++++++++++++++++
3 files changed, 33 insertions(+)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 3935428..0943b1b6 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -177,6 +177,8 @@ static inline struct page *compound_trans_head(struct page
*page)
extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct
*vma,
unsigned long addr, pmd_t pmd, pmd_t *pmdp);
+extern int thp_threshold_check(void);
+
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d9851ee..b5efa23 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -408,6 +408,7 @@ struct mm_struct {
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
pgtable_t pmd_huge_pte; /* protected by page_table_lock */
+ int thp_threshold;
#endif
#ifdef CONFIG_CPUMASK_OFFSTACK
struct cpumask cpumask_allocation;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cca80d9..5d388e4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -44,6 +44,9 @@ unsigned long transparent_hugepage_flags __read_mostly =
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
+/* default to 1 page threshold for handing out thps; maintains old behavior */
+static int transparent_hugepage_threshold = 1;
+
/* default scan 8*512 pte (or vmas) every 30 second */
static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8;
static unsigned int khugepaged_pages_collapsed;
@@ -237,6 +240,11 @@ static struct shrinker huge_zero_page_shrinker = {
.seeks = DEFAULT_SEEKS,
};
+int thp_threshold_check()
+{
+ return transparent_hugepage_threshold;
+}
+
#ifdef CONFIG_SYSFS
static ssize_t double_flag_show(struct kobject *kobj,
@@ -376,6 +384,27 @@ static ssize_t use_zero_page_store(struct kobject *kobj,
}
static struct kobj_attribute use_zero_page_attr =
__ATTR(use_zero_page, 0644, use_zero_page_show, use_zero_page_store);
+static ssize_t threshold_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%d\n", transparent_hugepage_threshold);
+}
+static ssize_t threshold_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int err, value;
+
+ err = kstrtoint(buf, 10, &value);
+ if (err || value < 1 || value > HPAGE_PMD_NR)
+ return -EINVAL;
+
+ transparent_hugepage_threshold = value;
+
+ return count;
+}
+static struct kobj_attribute threshold_attr =
+ __ATTR(threshold, 0644, threshold_show, threshold_store);
#ifdef CONFIG_DEBUG_VM
static ssize_t debug_cow_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
@@ -397,6 +426,7 @@ static struct kobj_attribute debug_cow_attr =
static struct attribute *hugepage_attr[] = {
&enabled_attr.attr,
&defrag_attr.attr,
+ &threshold_attr.attr,
&use_zero_page_attr.attr,
#ifdef CONFIG_DEBUG_VM
&debug_cow_attr.attr,
--
1.7.12.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
