The patch titled
Subject: mm,hwpoison: refactor soft_offline_huge_page and __soft_offline_page
has been added to the -mm tree. Its filename is
mmhwpoison-refactor-soft_offline_huge_page-and-__soft_offline_page.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mmhwpoison-refactor-soft_offline_huge_page-and-__soft_offline_page.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mmhwpoison-refactor-soft_offline_huge_page-and-__soft_offline_page.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: Oscar Salvador <osalvador@xxxxxxx>
Subject: mm,hwpoison: refactor soft_offline_huge_page and __soft_offline_page
Merging soft_offline_huge_page and __soft_offline_page let us get rid of
quite some duplicated code, and makes the code much easier to follow.
Now, __soft_offline_page will handle both normal and hugetlb pages.
Note that move put_page() block to the beginning of page_handle_poison()
with drain_all_pages() in order to make sure that the target page is freed
and sent into free list to make take_page_off_buddy() work properly.
Link: http://lkml.kernel.org/r/20200716123810.25292-14-osalvador@xxxxxxx
Signed-off-by: Oscar Salvador <osalvador@xxxxxxxx>
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Dmitry Yakunin <zeil@xxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memory-failure.c | 141 +++++++++++++++---------------------------
1 file changed, 52 insertions(+), 89 deletions(-)
--- a/mm/memory-failure.c~mmhwpoison-refactor-soft_offline_huge_page-and-__soft_offline_page
+++ a/mm/memory-failure.c
@@ -1723,62 +1723,50 @@ static int get_any_page(struct page *pag
return ret;
}
-static int soft_offline_huge_page(struct page *page)
+static bool isolate_page(struct page *page, struct list_head *pagelist)
{
- int ret = -EBUSY;
- unsigned long pfn = page_to_pfn(page);
- struct page *hpage = compound_head(page);
- LIST_HEAD(pagelist);
+ bool isolated = false;
+ bool lru = PageLRU(page);
- /*
- * This double-check of PageHWPoison is to avoid the race with
- * memory_failure(). See also comment in __soft_offline_page().
- */
- lock_page(hpage);
- if (PageHWPoison(hpage)) {
- unlock_page(hpage);
- put_page(hpage);
- pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);
- return -EBUSY;
+ if (PageHuge(page)) {
+ isolated = isolate_huge_page(page, pagelist);
+ } else {
+ if (lru)
+ isolated = !isolate_lru_page(page);
+ else
+ isolated = !isolate_movable_page(page, ISOLATE_UNEVICTABLE);
+
+ if (isolated)
+ list_add(&page->lru, pagelist);
}
- unlock_page(hpage);
- ret = isolate_huge_page(hpage, &pagelist);
+ if (isolated && lru)
+ inc_node_page_state(page, NR_ISOLATED_ANON +
+ page_is_file_lru(page));
+
/*
- * get_any_page() and isolate_huge_page() takes a refcount each,
- * so need to drop one here.
+ * If we succeed to isolate the page, we grabbed another refcount on
+ * the page, so we can safely drop the one we got from get_any_pages().
+ * If we failed to isolate the page, it means that we cannot go further
+ * and we will return an error, so drop the reference we got from
+ * get_any_pages() as well.
*/
- put_page(hpage);
- if (!ret) {
- pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
- return -EBUSY;
- }
-
- ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
- MIGRATE_SYNC, MR_MEMORY_FAILURE);
- if (ret) {
- pr_info("soft offline: %#lx: hugepage migration failed %d, type %lx (%pGp)\n",
- pfn, ret, page->flags, &page->flags);
- if (!list_empty(&pagelist))
- putback_movable_pages(&pagelist);
- if (ret > 0)
- ret = -EIO;
- } else {
- /*
- * At this point the page cannot be in-use since we do not
- * let the page to go back to hugetlb freelists.
- * In that case we just need to dissolve it.
- * page_handle_poison will take care of it.
- */
- page_handle_poison(page, true, true, true);
- }
- return ret;
+ put_page(page);
+ return isolated;
}
+/*
+ * __soft_offline_page handles hugetlb-pages and non-hugetlb pages.
+ * If the page is a non-dirty unmapped page-cache page, it simply invalidates.
+ */
static int __soft_offline_page(struct page *page)
{
- int ret;
+ int ret = 0;
unsigned long pfn = page_to_pfn(page);
+ struct page *hpage = compound_head(page);
+ const char *msg_page[] = {"page", "hugepage"};
+ bool huge = PageHuge(page);
+ LIST_HEAD(pagelist);
/*
* Check PageHWPoison again inside page lock because PageHWPoison
@@ -1787,88 +1775,63 @@ static int __soft_offline_page(struct pa
* so there's no race between soft_offline_page() and memory_failure().
*/
lock_page(page);
- wait_on_page_writeback(page);
+ if (!PageHuge(page))
+ wait_on_page_writeback(page);
if (PageHWPoison(page)) {
unlock_page(page);
put_page(page);
pr_info("soft offline: %#lx page already poisoned\n", pfn);
return -EBUSY;
}
- /*
- * Try to invalidate first. This should work for
- * non dirty unmapped page cache pages.
- */
- ret = invalidate_inode_page(page);
+
+ if (!PageHuge(page))
+ /*
+ * Try to invalidate first. This should work for
+ * non dirty unmapped page cache pages.
+ */
+ ret = invalidate_inode_page(page);
unlock_page(page);
+
/*
* RED-PEN would be better to keep it isolated here, but we
* would need to fix isolation locking first.
*/
if (ret == 1) {
pr_info("soft_offline: %#lx: invalidated\n", pfn);
- page_handle_poison(page, true, true, false);
+ page_handle_poison(page, false, true, false);
return 0;
}
- /*
- * Simple invalidation didn't work.
- * Try to migrate to a new page instead. migrate.c
- * handles a large number of cases for us.
- */
- if (PageLRU(page))
- ret = isolate_lru_page(page);
- else
- ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE);
- /*
- * Drop page reference which is came from get_any_page()
- * successful isolate_lru_page() already took another one.
- */
- put_page(page);
- if (!ret) {
- LIST_HEAD(pagelist);
- /*
- * After isolated lru page, the PageLRU will be cleared,
- * so use !__PageMovable instead for LRU page's mapping
- * cannot have PAGE_MAPPING_MOVABLE.
- */
- if (!__PageMovable(page))
- inc_node_page_state(page, NR_ISOLATED_ANON +
- page_is_file_lru(page));
- list_add(&page->lru, &pagelist);
- ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
+ if (isolate_page(hpage, &pagelist)) {
+ ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
MIGRATE_SYNC, MR_MEMORY_FAILURE);
if (!ret) {
- page_handle_poison(page, true, true, false);
+ page_handle_poison(page, true, true, huge);
} else {
if (!list_empty(&pagelist))
putback_movable_pages(&pagelist);
- pr_info("soft offline: %#lx: migration failed %d, type %lx (%pGp)\n",
- pfn, ret, page->flags, &page->flags);
+ pr_info("soft offline: %#lx: %s migration failed %d, type %lx (%pGp)\n",
+ pfn, msg_page[huge], ret, page->flags, &page->flags);
if (ret > 0)
ret = -EIO;
}
} else {
- pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx (%pGp)\n",
- pfn, ret, page_count(page), page->flags, &page->flags);
+ pr_info("soft offline: %#lx: %s isolation failed: %d, page count %d, type %lx (%pGp)\n",
+ pfn, msg_page[huge], ret, page_count(page), page->flags, &page->flags);
}
return ret;
}
static int soft_offline_in_use_page(struct page *page)
{
- int ret;
struct page *hpage = compound_head(page);
if (!PageHuge(page) && PageTransHuge(hpage))
if (try_to_split_thp_page(page, "soft offline") < 0)
return -EBUSY;
- if (PageHuge(page))
- ret = soft_offline_huge_page(page);
- else
- ret = __soft_offline_page(page);
- return ret;
+ return __soft_offline_page(page);
}
static int soft_offline_free_page(struct page *page)
_
Patches currently in -mm which might be from osalvador@xxxxxxx are
mmmadvise-refactor-madvise_inject_error.patch
mmhwpoison-un-export-get_hwpoison_page-and-make-it-static.patch
mmhwpoison-kill-put_hwpoison_page.patch
mmhwpoison-unify-thp-handling-for-hard-and-soft-offline.patch
mmhwpoison-rework-soft-offline-for-free-pages.patch
mmhwpoison-rework-soft-offline-for-in-use-pages.patch
mmhwpoison-refactor-soft_offline_huge_page-and-__soft_offline_page.patch
mmhwpoison-return-0-if-the-page-is-already-poisoned-in-soft-offline.patch
mmhwpoison-introduce-mf_msg_unsplit_thp.patch
