The patch titled
Subject: mm/gup: restrict CMA region by using allocation scope API
has been added to the -mm tree. Its filename is
mm-gup-restrict-cma-region-by-using-allocation-scope-api.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-gup-restrict-cma-region-by-using-allocation-scope-api.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-gup-restrict-cma-region-by-using-allocation-scope-api.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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Subject: mm/gup: restrict CMA region by using allocation scope API
We have well defined scope API to exclude CMA region. Use it rather than
manipulating gfp_mask manually. With this change, we can now restore
__GFP_MOVABLE for gfp_mask like as usual migration target allocation. It
would result in that the ZONE_MOVABLE is also searched by page allocator.
For hugetlb, gfp_mask is redefined since it has a regular allocation mask
filter for migration target. __GPF_NOWARN is added to hugetlb gfp_mask
filter since a new user for gfp_mask filter, gup, want to be silent when
allocation fails.
Note that this can be considered as a fix for the commit 9a4e9f3b2d73
("mm: update get_user_pages_longterm to migrate pages allocated from CMA
region"). However, "Fixes" tag isn't added here since it is just
suboptimal but it doesn't cause any problem.
Link: http://lkml.kernel.org/r/1596180906-8442-1-git-send-email-iamjoonsoo.kim@xxxxxxx
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: Roman Gushchin <guro@xxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/hugetlb.h | 2 ++
mm/gup.c | 17 ++++++++---------
2 files changed, 10 insertions(+), 9 deletions(-)
--- a/include/linux/hugetlb.h~mm-gup-restrict-cma-region-by-using-allocation-scope-api
+++ a/include/linux/hugetlb.h
@@ -708,6 +708,8 @@ static inline gfp_t htlb_modify_alloc_ma
/* Some callers might want to enfoce node */
modified_mask |= (gfp_mask & __GFP_THISNODE);
+ modified_mask |= (gfp_mask & __GFP_NOWARN);
+
return modified_mask;
}
--- a/mm/gup.c~mm-gup-restrict-cma-region-by-using-allocation-scope-api
+++ a/mm/gup.c
@@ -1620,10 +1620,12 @@ static struct page *new_non_cma_page(str
* Trying to allocate a page for migration. Ignore allocation
* failure warnings. We don't force __GFP_THISNODE here because
* this node here is the node where we have CMA reservation and
- * in some case these nodes will have really less non movable
+ * in some case these nodes will have really less non CMA
* allocation memory.
+ *
+ * Note that CMA region is prohibited by allocation scope.
*/
- gfp_t gfp_mask = GFP_USER | __GFP_NOWARN;
+ gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_NOWARN;
if (PageHighMem(page))
gfp_mask |= __GFP_HIGHMEM;
@@ -1631,6 +1633,8 @@ static struct page *new_non_cma_page(str
#ifdef CONFIG_HUGETLB_PAGE
if (PageHuge(page)) {
struct hstate *h = page_hstate(page);
+
+ gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
/*
* We don't want to dequeue from the pool because pool pages will
* mostly be from the CMA region.
@@ -1645,11 +1649,6 @@ static struct page *new_non_cma_page(str
*/
gfp_t thp_gfpmask = GFP_TRANSHUGE | __GFP_NOWARN;
- /*
- * Remove the movable mask so that we don't allocate from
- * CMA area again.
- */
- thp_gfpmask &= ~__GFP_MOVABLE;
thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER);
if (!thp)
return NULL;
@@ -1795,7 +1794,6 @@ static long __gup_longterm_locked(struct
vmas_tmp, NULL, gup_flags);
if (gup_flags & FOLL_LONGTERM) {
- memalloc_nocma_restore(flags);
if (rc < 0)
goto out;
@@ -1808,9 +1806,10 @@ static long __gup_longterm_locked(struct
rc = check_and_migrate_cma_pages(tsk, mm, start, rc, pages,
vmas_tmp, gup_flags);
+out:
+ memalloc_nocma_restore(flags);
}
-out:
if (vmas_tmp != vmas)
kfree(vmas_tmp);
return rc;
_
Patches currently in -mm which might be from iamjoonsoo.kim@xxxxxxx are
mm-page_alloc-fix-memalloc_nocma_save-restore-apis.patch
mm-vmscan-make-active-inactive-ratio-as-1-1-for-anon-lru.patch
mm-vmscan-protect-the-workingset-on-anonymous-lru.patch
mm-workingset-prepare-the-workingset-detection-infrastructure-for-anon-lru.patch
mm-swapcache-support-to-handle-the-shadow-entries.patch
mm-swap-implement-workingset-detection-for-anonymous-lru.patch
mm-vmscan-restore-active-inactive-ratio-for-anonymous-lru.patch
mm-page_isolation-prefer-the-node-of-the-source-page.patch
mm-migrate-move-migration-helper-from-h-to-c.patch
mm-hugetlb-unify-migration-callbacks.patch
mm-migrate-clear-__gfp_reclaim-to-make-the-migration-callback-consistent-with-regular-thp-allocations.patch
mm-migrate-make-a-standard-migration-target-allocation-function.patch
mm-mempolicy-use-a-standard-migration-target-allocation-callback.patch
mm-page_alloc-remove-a-wrapper-for-alloc_migration_target.patch
mm-memory-failure-remove-a-wrapper-for-alloc_migration_target.patch
mm-memory_hotplug-remove-a-wrapper-for-alloc_migration_target.patch
mm-gup-restrict-cma-region-by-using-allocation-scope-api.patch
mm-hugetlb-make-hugetlb-migration-callback-cma-aware.patch
mm-gup-use-a-standard-migration-target-allocation-callback.patch
