diff options
Diffstat (limited to 'mm/memory-failure.c')
-rw-r--r-- | mm/memory-failure.c | 311 |
1 files changed, 143 insertions, 168 deletions
diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 990e3b2e37d5..a2184b721fbf 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -65,6 +65,33 @@ int sysctl_memory_failure_recovery __read_mostly = 1; atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); +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) u32 hwpoison_filter_enable = 0; @@ -555,6 +582,7 @@ static const char * const action_page_types[] = { [MF_MSG_BUDDY] = "free buddy page", [MF_MSG_BUDDY_2ND] = "free buddy page (2nd try)", [MF_MSG_DAX] = "dax page", + [MF_MSG_UNSPLIT_THP] = "unsplit thp", [MF_MSG_UNKNOWN] = "unknown page", }; @@ -924,7 +952,7 @@ static int page_action(struct page_state *ps, struct page *p, * Return: return 0 if failed to grab the refcount, otherwise true (some * non-zero value.) */ -int get_hwpoison_page(struct page *page) +static int get_hwpoison_page(struct page *page) { struct page *head = compound_head(page); @@ -953,7 +981,6 @@ int get_hwpoison_page(struct page *page) return 0; } -EXPORT_SYMBOL_GPL(get_hwpoison_page); /* * Do all that is necessary to remove user space mappings. Unmap @@ -1103,6 +1130,25 @@ static int identify_page_state(unsigned long pfn, struct page *p, return page_action(ps, p, pfn); } +static int try_to_split_thp_page(struct page *page, const char *msg) +{ + lock_page(page); + if (!PageAnon(page) || unlikely(split_huge_page(page))) { + unsigned long pfn = page_to_pfn(page); + + unlock_page(page); + if (!PageAnon(page)) + pr_info("%s: %#lx: non anonymous thp\n", msg, pfn); + else + pr_info("%s: %#lx: thp split failed\n", msg, pfn); + put_page(page); + return -EBUSY; + } + unlock_page(page); + + return 0; +} + static int memory_failure_hugetlb(unsigned long pfn, int flags) { struct page *p = pfn_to_page(pfn); @@ -1144,7 +1190,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) pr_err("Memory failure: %#lx: just unpoisoned\n", pfn); num_poisoned_pages_dec(); unlock_page(head); - put_hwpoison_page(head); + put_page(head); return 0; } @@ -1325,23 +1371,11 @@ int memory_failure(unsigned long pfn, int flags) } if (PageTransHuge(hpage)) { - lock_page(p); - if (!PageAnon(p) || unlikely(split_huge_page(p))) { - unlock_page(p); - if (!PageAnon(p)) - pr_err("Memory failure: %#lx: non anonymous thp\n", - pfn); - else - pr_err("Memory failure: %#lx: thp split failed\n", - pfn); - if (TestClearPageHWPoison(p)) - num_poisoned_pages_dec(); - put_hwpoison_page(p); + if (try_to_split_thp_page(p, "Memory Failure") < 0) { + action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); return -EBUSY; } - unlock_page(p); VM_BUG_ON_PAGE(!page_count(p), p); - hpage = compound_head(p); } /* @@ -1381,10 +1415,7 @@ int memory_failure(unsigned long pfn, int flags) * page_remove_rmap() in try_to_unmap_one(). So to determine page status * correctly, we save a copy of the page flags at this time. */ - if (PageHuge(p)) - page_flags = hpage->flags; - else - page_flags = p->flags; + page_flags = p->flags; /* * unpoison always clear PG_hwpoison inside page lock @@ -1393,14 +1424,14 @@ int memory_failure(unsigned long pfn, int flags) pr_err("Memory failure: %#lx: just unpoisoned\n", pfn); num_poisoned_pages_dec(); unlock_page(p); - put_hwpoison_page(p); + put_page(p); return 0; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) num_poisoned_pages_dec(); unlock_page(p); - put_hwpoison_page(p); + put_page(p); return 0; } @@ -1416,11 +1447,8 @@ int memory_failure(unsigned long pfn, int flags) /* * Now take care of user space mappings. * Abort on fail: __delete_from_page_cache() assumes unmapped page. - * - * When the raw error page is thp tail page, hpage points to the raw - * page after thp split. */ - if (!hwpoison_user_mappings(p, pfn, flags, &hpage)) { + if (!hwpoison_user_mappings(p, pfn, flags, &p)) { action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); res = -EBUSY; goto out; @@ -1637,9 +1665,9 @@ int unpoison_memory(unsigned long pfn) } unlock_page(page); - put_hwpoison_page(page); + put_page(page); if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) - put_hwpoison_page(page); + put_page(page); return 0; } @@ -1679,6 +1707,9 @@ static int __get_any_page(struct page *p, unsigned long pfn, int flags) } else if (is_free_buddy_page(p)) { pr_info("%s: %#lx free buddy page\n", __func__, pfn); ret = 0; + } else if (page_count(p)) { + /* raced with allocation */ + ret = -EBUSY; } else { pr_info("%s: %#lx: unknown zero refcount page type %lx\n", __func__, pfn, p->flags); @@ -1695,12 +1726,15 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) { int ret = __get_any_page(page, pfn, flags); + if (ret == -EBUSY) + ret = __get_any_page(page, pfn, flags); + if (ret == 1 && !PageHuge(page) && !PageLRU(page) && !__PageMovable(page)) { /* * Try to free it. */ - put_hwpoison_page(page); + put_page(page); shake_page(page, 1); /* @@ -1709,7 +1743,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) ret = __get_any_page(page, pfn, 0); if (ret == 1 && !PageLRU(page)) { /* Drop page reference which is from __get_any_page() */ - put_hwpoison_page(page); + put_page(page); pr_info("soft_offline: %#lx: unknown non LRU page type %lx (%pGp)\n", pfn, page->flags, &page->flags); return -EIO; @@ -1718,69 +1752,51 @@ 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_hwpoison_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_hwpoison_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 the migration source hugepage - * was successfully dissolved, because otherwise hwpoisoned - * hugepage remains on free hugepage list, then userspace will - * find it as SIGBUS by allocation failure. That's not expected - * in soft-offlining. - */ - ret = dissolve_free_huge_page(page); - if (!ret) { - if (set_hwpoison_free_buddy_page(page)) - num_poisoned_pages_inc(); - 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 @@ -1789,121 +1805,75 @@ 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_hwpoison_page(page); + put_page(page); pr_info("soft offline: %#lx page already poisoned\n", pfn); - return -EBUSY; + return 0; } - /* - * 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) { - put_hwpoison_page(page); + if (ret) { pr_info("soft_offline: %#lx: invalidated\n", pfn); - SetPageHWPoison(page); - num_poisoned_pages_inc(); + 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_hwpoison_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) { + if (!ret) { + 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; - int mt; struct page *hpage = compound_head(page); - if (!PageHuge(page) && PageTransHuge(hpage)) { - lock_page(page); - if (!PageAnon(page) || unlikely(split_huge_page(page))) { - unlock_page(page); - if (!PageAnon(page)) - pr_info("soft offline: %#lx: non anonymous thp\n", page_to_pfn(page)); - else - pr_info("soft offline: %#lx: thp split failed\n", page_to_pfn(page)); - put_hwpoison_page(page); + if (!PageHuge(page) && PageTransHuge(hpage)) + if (try_to_split_thp_page(page, "soft offline") < 0) return -EBUSY; - } - unlock_page(page); - } - - /* - * Setting MIGRATE_ISOLATE here ensures that the page will be linked - * to free list immediately (not via pcplist) when released after - * successful page migration. Otherwise we can't guarantee that the - * page is really free after put_page() returns, so - * set_hwpoison_free_buddy_page() highly likely fails. - */ - mt = get_pageblock_migratetype(page); - set_pageblock_migratetype(page, MIGRATE_ISOLATE); - if (PageHuge(page)) - ret = soft_offline_huge_page(page, flags); - else - ret = __soft_offline_page(page, flags); - set_pageblock_migratetype(page, mt); - return ret; + return __soft_offline_page(page); } static int soft_offline_free_page(struct page *page) { - int rc = dissolve_free_huge_page(page); + int rc = 0; + + if (!page_handle_poison(page, true, false)) + rc = -EBUSY; - if (!rc) { - if (set_hwpoison_free_buddy_page(page)) - num_poisoned_pages_inc(); - else - rc = -EBUSY; - } return rc; } @@ -1933,6 +1903,7 @@ int soft_offline_page(unsigned long pfn, int flags) { int ret; struct page *page; + bool try_again = true; if (!pfn_valid(pfn)) return -ENXIO; @@ -1944,18 +1915,22 @@ int soft_offline_page(unsigned long pfn, int flags) if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); if (flags & MF_COUNT_INCREASED) - put_hwpoison_page(page); - return -EBUSY; + put_page(page); + return 0; } +retry: get_online_mems(); ret = get_any_page(page, pfn, 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); + if (soft_offline_free_page(page) && try_again) { + try_again = false; + goto retry; + } return ret; } |