The patch titled
Subject: mm/hugetlb: make hugetlb migration callback CMA aware
has been added to the -mm tree. Its filename is
mm-hugetlb-make-hugetlb-migration-callback-cma-aware.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-hugetlb-make-hugetlb-migration-callback-cma-aware.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-hugetlb-make-hugetlb-migration-callback-cma-aware.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/hugetlb: make hugetlb migration callback CMA aware
new_non_cma_page() in gup.c requires to allocate the new page that is not
on the CMA area. new_non_cma_page() implements it by using allocation
scope APIs.
However, there is a work-around for hugetlb. Normal hugetlb page
allocation API for migration is alloc_huge_page_nodemask(). It consists
of two steps. First is dequeing from the pool. Second is, if there is no
available page on the queue, allocating by using the page allocator.
new_non_cma_page() can't use this API since first step (deque) isn't aware
of scope API to exclude CMA area. So, new_non_cma_page() exports hugetlb
internal function for the second step, alloc_migrate_huge_page(), to
global scope and uses it directly. This is suboptimal since hugetlb pages
on the queue cannot be utilized.
This patch tries to fix this situation by making the deque function on
hugetlb CMA aware. In the deque function, CMA memory is skipped if
PF_MEMALLOC_NOCMA flag is found.
Link: http://lkml.kernel.org/r/1596180906-8442-2-git-send-email-iamjoonsoo.kim@xxxxxxx
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Acked-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Roman Gushchin <guro@xxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/hugetlb.h | 2 --
mm/gup.c | 6 +-----
mm/hugetlb.c | 11 +++++++++--
3 files changed, 10 insertions(+), 9 deletions(-)
--- a/include/linux/hugetlb.h~mm-hugetlb-make-hugetlb-migration-callback-cma-aware
+++ a/include/linux/hugetlb.h
@@ -509,8 +509,6 @@ struct page *alloc_huge_page_nodemask(st
nodemask_t *nmask, gfp_t gfp_mask);
struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
unsigned long address);
-struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
- int nid, nodemask_t *nmask);
int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
pgoff_t idx);
--- a/mm/gup.c~mm-hugetlb-make-hugetlb-migration-callback-cma-aware
+++ a/mm/gup.c
@@ -1635,11 +1635,7 @@ static struct page *new_non_cma_page(str
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.
- */
- return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
+ return alloc_huge_page_nodemask(h, nid, NULL, gfp_mask);
}
#endif
if (PageTransHuge(page)) {
--- a/mm/hugetlb.c~mm-hugetlb-make-hugetlb-migration-callback-cma-aware
+++ a/mm/hugetlb.c
@@ -19,6 +19,7 @@
#include <linux/memblock.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
+#include <linux/sched/mm.h>
#include <linux/mmdebug.h>
#include <linux/sched/signal.h>
#include <linux/rmap.h>
@@ -1040,10 +1041,16 @@ static void enqueue_huge_page(struct hst
static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
{
struct page *page;
+ bool nocma = !!(current->flags & PF_MEMALLOC_NOCMA);
+
+ list_for_each_entry(page, &h->hugepage_freelists[nid], lru) {
+ if (nocma && is_migrate_cma_page(page))
+ continue;
- list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
if (!PageHWPoison(page))
break;
+ }
+
/*
* if 'non-isolated free hugepage' not found on the list,
* the allocation fails.
@@ -1935,7 +1942,7 @@ out_unlock:
return page;
}
-struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
+static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nmask)
{
struct page *page;
_
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
