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.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-11-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 962129c..93b32d4 100644 (file)
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -65,13 +65,31 @@ int sysctl_memory_failure_recovery __read_mostly = 1;
 
 atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
-static void page_handle_poison(struct page *page, bool release)
+static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release)
 {
+       if (hugepage_or_freepage) {
+               /*
+                * Doing this check for free pages is also fine since dissolve_free_huge_page
+                * returns 0 for non-hugetlb pages as well.
+                */
+               if (dissolve_free_huge_page(page) || !take_page_off_buddy(page))
+                       /*
+                        * We could fail to take off the target page from buddy
+                        * for example due to racy page allocaiton, but that's
+                        * acceptable because soft-offlined page is not broken
+                        * and if someone really want to use it, they should
+                        * take it.
+                        */
+                       return false;
+       }
+
        SetPageHWPoison(page);
        if (release)
                put_page(page);
        page_ref_inc(page);
        num_poisoned_pages_inc();
+
+       return true;
 }
 
 #if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)
@@ -1725,63 +1743,51 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
        return ret;
 }
 
-static int soft_offline_huge_page(struct page *page, int flags)
+static bool isolate_page(struct page *page, struct list_head *pagelist)
 {
-       int ret;
-       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 {
-               /*
-                * We set PG_hwpoison only when we were able to take the page
-                * off the buddy.
-                */
-               if (!dissolve_free_huge_page(page) && take_page_off_buddy(page))
-                       page_handle_poison(page, false);
-               else
-                       ret = -EBUSY;
-       }
-       return ret;
+       put_page(page);
+       return isolated;
 }
 
-static int __soft_offline_page(struct page *page, int flags)
+/*
+ * __soft_offline_page handles hugetlb-pages and non-hugetlb pages.
+ * If the page is a non-dirty unmapped page-cache page, it simply invalidates.
+ * If the page is mapped, it migrates the contents over.
+ */
+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);
+       char const *msg_page[] = {"page", "hugepage"};
+       bool huge = PageHuge(page);
+       LIST_HEAD(pagelist);
 
        /*
         * Check PageHWPoison again inside page lock because PageHWPoison
@@ -1790,98 +1796,74 @@ static int __soft_offline_page(struct page *page, int flags)
         * 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) {
+       if (ret) {
                pr_info("soft_offline: %#lx: invalidated\n", pfn);
-               page_handle_poison(page, true);
+               page_handle_poison(page, false, true);
                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);
+       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);
+                       bool release = !huge;
+
+                       if (!page_handle_poison(page, huge, release))
+                               ret = -EBUSY;
                } 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);
+               ret = -EBUSY;
        }
        return ret;
 }
 
-static int soft_offline_in_use_page(struct page *page, int flags)
+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, flags);
-       else
-               ret = __soft_offline_page(page, flags);
-       return ret;
+       return __soft_offline_page(page);
 }
 
 static int soft_offline_free_page(struct page *page)
 {
-       int rc = -EBUSY;
+       int rc = 0;
 
-       if (!dissolve_free_huge_page(page) && take_page_off_buddy(page)) {
-               page_handle_poison(page, false);
-               rc = 0;
-       }
+       if (!page_handle_poison(page, true, false))
+               rc = -EBUSY;
 
        return rc;
 }
@@ -1932,7 +1914,7 @@ int soft_offline_page(unsigned long pfn, int flags)
        put_online_mems();
 
        if (ret > 0)
-               ret = soft_offline_in_use_page(page, flags);
+               ret = soft_offline_in_use_page(page);
        else if (ret == 0)
                ret = soft_offline_free_page(page);