The patch titled
Subject: mm: mempolicy: mbind and migrate_pages support thp migration
has been added to the -mm tree. Its filename is
mm-mempolicy-mbind-and-migrate_pages-support-thp-migration.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-mempolicy-mbind-and-migrate_pages-support-thp-migration.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-mempolicy-mbind-and-migrate_pages-support-thp-migration.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Subject: mm: mempolicy: mbind and migrate_pages support thp migration
This patch enables thp migration for mbind(2) and migrate_pages(2).
Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Signed-off-by: Zi Yan <zi.yan@xxxxxxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Anshuman Khandual <khandual@xxxxxxxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: David Nellans <dnellans@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/mempolicy.c | 108 ++++++++++++++++++++++++++++++++++-------------
1 file changed, 79 insertions(+), 29 deletions(-)
diff -puN mm/mempolicy.c~mm-mempolicy-mbind-and-migrate_pages-support-thp-migration mm/mempolicy.c
--- a/mm/mempolicy.c~mm-mempolicy-mbind-and-migrate_pages-support-thp-migration
+++ a/mm/mempolicy.c
@@ -97,6 +97,7 @@
#include <linux/mm_inline.h>
#include <linux/mmu_notifier.h>
#include <linux/printk.h>
+#include <linux/swapops.h>
#include <asm/tlbflush.h>
#include <linux/uaccess.h>
@@ -426,6 +427,49 @@ static inline bool queue_pages_required(
return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT);
}
+static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+{
+ int ret = 0;
+ struct page *page;
+ struct queue_pages *qp = walk->private;
+ unsigned long flags;
+
+ if (unlikely(is_pmd_migration_entry(*pmd))) {
+ ret = 1;
+ goto unlock;
+ }
+ page = pmd_page(*pmd);
+ if (is_huge_zero_page(page)) {
+ spin_unlock(ptl);
+ __split_huge_pmd(walk->vma, pmd, addr, false, NULL);
+ goto out;
+ }
+ if (!thp_migration_supported()) {
+ get_page(page);
+ spin_unlock(ptl);
+ lock_page(page);
+ ret = split_huge_page(page);
+ unlock_page(page);
+ put_page(page);
+ goto out;
+ }
+ if (!queue_pages_required(page, qp)) {
+ ret = 1;
+ goto unlock;
+ }
+
+ ret = 1;
+ flags = qp->flags;
+ /* go to thp migration */
+ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+ migrate_page_add(page, qp->pagelist, flags);
+unlock:
+ spin_unlock(ptl);
+out:
+ return ret;
+}
+
/*
* Scan through pages checking if pages follow certain conditions,
* and move them to the pagelist if they do.
@@ -437,30 +481,15 @@ static int queue_pages_pte_range(pmd_t *
struct page *page;
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
- int nid, ret;
+ int ret;
pte_t *pte;
spinlock_t *ptl;
- if (pmd_trans_huge(*pmd)) {
- ptl = pmd_lock(walk->mm, pmd);
- if (pmd_trans_huge(*pmd)) {
- page = pmd_page(*pmd);
- if (is_huge_zero_page(page)) {
- spin_unlock(ptl);
- __split_huge_pmd(vma, pmd, addr, false, NULL);
- } else {
- get_page(page);
- spin_unlock(ptl);
- lock_page(page);
- ret = split_huge_page(page);
- unlock_page(page);
- put_page(page);
- if (ret)
- return 0;
- }
- } else {
- spin_unlock(ptl);
- }
+ ptl = pmd_trans_huge_lock(pmd, vma);
+ if (ptl) {
+ ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
+ if (ret)
+ return 0;
}
if (pmd_trans_unstable(pmd))
@@ -481,7 +510,7 @@ retry:
continue;
if (!queue_pages_required(page, qp))
continue;
- if (PageTransCompound(page)) {
+ if (PageTransCompound(page) && !thp_migration_supported()) {
get_page(page);
pte_unmap_unlock(pte, ptl);
lock_page(page);
@@ -898,19 +927,21 @@ static long do_get_mempolicy(int *policy
#ifdef CONFIG_MIGRATION
/*
- * page migration
+ * page migration, thp tail pages can be passed.
*/
static void migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags)
{
+ struct page *head = compound_head(page);
/*
* Avoid migrating a page that is shared with others.
*/
- if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
- if (!isolate_lru_page(page)) {
- list_add_tail(&page->lru, pagelist);
- inc_node_page_state(page, NR_ISOLATED_ANON +
- page_is_file_cache(page));
+ if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(head) == 1) {
+ if (!isolate_lru_page(head)) {
+ list_add_tail(&head->lru, pagelist);
+ mod_node_page_state(page_pgdat(head),
+ NR_ISOLATED_ANON + page_is_file_cache(head),
+ hpage_nr_pages(head));
}
}
}
@@ -920,7 +951,17 @@ static struct page *new_node_page(struct
if (PageHuge(page))
return alloc_huge_page_node(page_hstate(compound_head(page)),
node);
- else
+ else if (thp_migration_supported() && PageTransHuge(page)) {
+ struct page *thp;
+
+ thp = alloc_pages_node(node,
+ (GFP_TRANSHUGE | __GFP_THISNODE),
+ HPAGE_PMD_ORDER);
+ if (!thp)
+ return NULL;
+ prep_transhuge_page(thp);
+ return thp;
+ } else
return __alloc_pages_node(node, GFP_HIGHUSER_MOVABLE |
__GFP_THISNODE, 0);
}
@@ -1086,6 +1127,15 @@ static struct page *new_page(struct page
if (PageHuge(page)) {
BUG_ON(!vma);
return alloc_huge_page_noerr(vma, address, 1);
+ } else if (thp_migration_supported() && PageTransHuge(page)) {
+ struct page *thp;
+
+ thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
+ HPAGE_PMD_ORDER);
+ if (!thp)
+ return NULL;
+ prep_transhuge_page(thp);
+ return thp;
}
/*
* if !vma, alloc_page_vma() will use task or system default policy
_
Patches currently in -mm which might be from n-horiguchi@xxxxxxxxxxxxx are
mm-mempolicy-add-queue_pages_required.patch
mm-x86-move-_page_swp_soft_dirty-from-bit-7-to-bit-1.patch
mm-thp-introduce-separate-ttu-flag-for-thp-freezing.patch
mm-thp-introduce-config_arch_enable_thp_migration.patch
mm-soft-dirty-keep-soft-dirty-bits-over-thp-migration.patch
mm-mempolicy-mbind-and-migrate_pages-support-thp-migration.patch
mm-migrate-move_pages-supports-thp-migration.patch
mm-memory_hotplug-memory-hotremove-supports-thp-migration.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
