memory-failure.c

	 * We need/can do nothing about count=0 pages.
	 * 1) it's a free page, and therefore in safe hand:
	 *    prep_new_page() will be the gate keeper.
	 * 2) it's a free hugepage, which is also safe:
	 *    an affected hugepage will be dequeued from hugepage freelist,
	 *    so there's no concern about reusing it ever after.
	 * 3) it's part of a non-compound high order page.
	 *    Implies some kernel user: cannot stop them from
	 *    R/W the page; let's pray that the page has been
	 *    used and will be freed some time later.
	 * In fact it's dangerous to directly bump up page count from 0,
	 * that may make page_freeze_refs()/page_unfreeze_refs() mismatch.
	 */
	if (!(flags & MF_COUNT_INCREASED) &&
		!get_page_unless_zero(hpage)) {
		if (is_free_buddy_page(p)) {
			action_result(pfn, "free buddy", DELAYED);
			return 0;
		} else if (PageHuge(hpage)) {
			/*
			 * Check "just unpoisoned", "filter hit", and
			 * "race with other subpage."
			 */
			lock_page_nosync(hpage);
			if (!PageHWPoison(hpage)
			    || (hwpoison_filter(p) && TestClearPageHWPoison(p))
			    || (p != hpage && TestSetPageHWPoison(hpage))) {
				atomic_long_sub(nr_pages, &mce_bad_pages);
				return 0;
			}
			set_page_hwpoison_huge_page(hpage);
			res = dequeue_hwpoisoned_huge_page(hpage);
			action_result(pfn, "free huge",
				      res ? IGNORED : DELAYED);
			unlock_page(hpage);
			return res;
		} else {
			action_result(pfn, "high order kernel", IGNORED);
			return -EBUSY;
		}
	}

	/*
	 * We ignore non-LRU pages for good reasons.
	 * - PG_locked is only well defined for LRU pages and a few others
	 * - to avoid races with __set_page_locked()
	 * - to avoid races with __SetPageSlab*() (and more non-atomic ops)
	 * The check (unnecessarily) ignores LRU pages being isolated and
	 * walked by the page reclaim code, however that's not a big loss.
	 */
	if (!PageLRU(p) && !PageHuge(p))
		shake_page(p, 0);
	if (!PageLRU(p) && !PageHuge(p)) {
		/*
		 * shake_page could have turned it free.
		 */
		if (is_free_buddy_page(p)) {
			action_result(pfn, "free buddy, 2nd try", DELAYED);
			return 0;
		}
		action_result(pfn, "non LRU", IGNORED);
		put_page(p);
		return -EBUSY;
	}

	/*
	 * Lock the page and wait for writeback to finish.
	 * It's very difficult to mess with pages currently under IO
	 * and in many cases impossible, so we just avoid it here.
	 */
	lock_page_nosync(hpage);

	/*
	 * unpoison always clear PG_hwpoison inside page lock
	 */
	if (!PageHWPoison(p)) {
		printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
		res = 0;
		goto out;
	}
	if (hwpoison_filter(p)) {
		if (TestClearPageHWPoison(p))
			atomic_long_sub(nr_pages, &mce_bad_pages);
		unlock_page(hpage);
		put_page(hpage);
		return 0;
	}

	/*
	 * For error on the tail page, we should set PG_hwpoison
	 * on the head page to show that the hugepage is hwpoisoned
	 */
	if (PageTail(p) && TestSetPageHWPoison(hpage)) {
		action_result(pfn, "hugepage already hardware poisoned",
				IGNORED);
		unlock_page(hpage);
		put_page(hpage);
		return 0;
	}
	/*
	 * Set PG_hwpoison on all pages in an error hugepage,
	 * because containment is done in hugepage unit for now.
	 * Since we have done TestSetPageHWPoison() for the head page with
	 * page lock held, we can safely set PG_hwpoison bits on tail pages.
	 */
	if (PageHuge(p))
		set_page_hwpoison_huge_page(hpage);

	wait_on_page_writeback(p);

	/*
	 * Now take care of user space mappings.
	 * Abort on fail: __remove_from_page_cache() assumes unmapped page.
	 */
	if (hwpoison_user_mappings(p, pfn, trapno) != SWAP_SUCCESS) {
		printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn);
		res = -EBUSY;
		goto out;
	}

	/*
	 * Torn down by someone else?
	 */
	if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) {
		action_result(pfn, "already truncated LRU", IGNORED);
		res = -EBUSY;
		goto out;
	}

	res = -EBUSY;
	for (ps = error_states;; ps++) {
		if ((p->flags & ps->mask) == ps->res) {
			res = page_action(ps, p, pfn);
			break;
		}
	}
out:
	unlock_page(hpage);
	return res;
}
EXPORT_SYMBOL_GPL(__memory_failure);

/**
 * memory_failure - Handle memory failure of a page.
 * @pfn: Page Number of the corrupted page
 * @trapno: Trap number reported in the signal to user space.
 *
 * This function is called by the low level machine check code
 * of an architecture when it detects hardware memory corruption
 * of a page. It tries its best to recover, which includes
 * dropping pages, killing processes etc.
 *
 * The function is primarily of use for corruptions that
 * happen outside the current execution context (e.g. when
 * detected by a background scrubber)
 *
 * Must run in process context (e.g. a work queue) with interrupts
 * enabled and no spinlocks hold.
 */
void memory_failure(unsigned long pfn, int trapno)
{
	__memory_failure(pfn, trapno, 0);
}

/**
 * unpoison_memory - Unpoison a previously poisoned page
 * @pfn: Page number of the to be unpoisoned page
 *
 * Software-unpoison a page that has been poisoned by
 * memory_failure() earlier.
 *
 * This is only done on the software-level, so it only works
 * for linux injected failures, not real hardware failures
 *
 * Returns 0 for success, otherwise -errno.
 */
int unpoison_memory(unsigned long pfn)
{
	struct page *page;
	struct page *p;
	int freeit = 0;
	unsigned int nr_pages;

	if (!pfn_valid(pfn))
		return -ENXIO;

	p = pfn_to_page(pfn);
	page = compound_head(p);

	if (!PageHWPoison(p)) {
		pr_info("MCE: Page was already unpoisoned %#lx\n", pfn);
		return 0;
	}

	nr_pages = 1 << compound_trans_order(page);

	if (!get_page_unless_zero(page)) {
		/*
		 * Since HWPoisoned hugepage should have non-zero refcount,
		 * race between memory failure and unpoison seems to happen.
		 * In such case unpoison fails and memory failure runs
		 * to the end.
		 */
		if (PageHuge(page)) {
			pr_debug("MCE: Memory failure is now running on free hugepage %#lx\n", pfn);
			return 0;
		}
		if (TestClearPageHWPoison(p))
			atomic_long_sub(nr_pages, &mce_bad_pages);
		pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn);
		return 0;
	}

	lock_page_nosync(page);
	/*
	 * This test is racy because PG_hwpoison is set outside of page lock.
	 * That's acceptable because that won't trigger kernel panic. Instead,
	 * the PG_hwpoison page will be caught and isolated on the entrance to
	 * the free buddy page pool.
	 */
	if (TestClearPageHWPoison(page)) {
		pr_info("MCE: Software-unpoisoned page %#lx\n", pfn);
		atomic_long_sub(nr_pages, &mce_bad_pages);
		freeit = 1;
		if (PageHuge(page))
			clear_page_hwpoison_huge_page(page);
	}
	unlock_page(page);

	put_page(page);
	if (freeit)
		put_page(page);

	return 0;
}
EXPORT_SYMBOL(unpoison_memory);

static struct page *new_page(struct page *p, unsigned long private, int **x)
{
	int nid = page_to_nid(p);
	if (PageHuge(p))
		return alloc_huge_page_node(page_hstate(compound_head(p)),
						   nid);
	else
		return alloc_pages_exact_node(nid, GFP_HIGHUSER_MOVABLE, 0);
}

/*
 * Safely get reference count of an arbitrary page.
 * Returns 0 for a free page, -EIO for a zero refcount page
 * that is not free, and 1 for any other page type.
 * For 1 the page is returned with increased page count, otherwise not.
 */
static int get_any_page(struct page *p, unsigned long pfn, int flags)
{
	int ret;

	if (flags & MF_COUNT_INCREASED)
		return 1;

	/*
	 * The lock_memory_hotplug prevents a race with memory hotplug.
	 * This is a big hammer, a better would be nicer.
	 */
	lock_memory_hotplug();

	/*
	 * Isolate the page, so that it doesn't get reallocated if it
	 * was free.
	 */
	set_migratetype_isolate(p);
	/*
	 * When the target page is a free hugepage, just remove it
	 * from free hugepage list.
	 */
	if (!get_page_unless_zero(compound_head(p))) {
		if (PageHuge(p)) {
			pr_info("get_any_page: %#lx free huge page\n", pfn);
			ret = dequeue_hwpoisoned_huge_page(compound_head(p));
		} else if (is_free_buddy_page(p)) {
			pr_info("get_any_page: %#lx free buddy page\n", pfn);
			/* Set hwpoison bit while page is still isolated */
			SetPageHWPoison(p);
			ret = 0;
		} else {
			pr_info("get_any_page: %#lx: unknown zero refcount page type %lx\n",
				pfn, p->flags);
			ret = -EIO;
		}
	} else {
		/* Not a free page */
		ret = 1;
	}
	unset_migratetype_isolate(p);
	unlock_memory_hotplug();
	return ret;
}

static int soft_offline_huge_page(struct page *page, int flags)
{
	int ret;
	unsigned long pfn = page_to_pfn(page);
	struct page *hpage = compound_head(page);
	LIST_HEAD(pagelist);

	ret = get_any_page(page, pfn, flags);
	if (ret < 0)
		return ret;
	if (ret == 0)
		goto done;

	if (PageHWPoison(hpage)) {
		put_page(hpage);
		pr_debug("soft offline: %#lx hugepage already poisoned\n", pfn);
		return -EBUSY;
	}

	/* Keep page count to indicate a given hugepage is isolated. */

	list_add(&hpage->lru, &pagelist);
	ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0,
				true);
	if (ret) {
		struct page *page1, *page2;
		list_for_each_entry_safe(page1, page2, &pagelist, lru)
			put_page(page1);

		pr_debug("soft offline: %#lx: migration failed %d, type %lx\n",
			 pfn, ret, page->flags);
		if (ret > 0)
			ret = -EIO;
		return ret;
	}
done:
	if (!PageHWPoison(hpage))
		atomic_long_add(1 << compound_trans_order(hpage), &mce_bad_pages);
	set_page_hwpoison_huge_page(hpage);
	dequeue_hwpoisoned_huge_page(hpage);
	/* keep elevated page count for bad page */
	return ret;
}

/**
 * soft_offline_page - Soft offline a page.
 * @page: page to offline
 * @flags: flags. Same as memory_failure().
 *
 * Returns 0 on success, otherwise negated errno.
 *
 * Soft offline a page, by migration or invalidation,
 * without killing anything. This is for the case when
 * a page is not corrupted yet (so it's still valid to access),
 * but has had a number of corrected errors and is better taken
 * out.
 *
 * The actual policy on when to do that is maintained by
 * user space.
 *
 * This should never impact any application or cause data loss,
 * however it might take some time.
 *
 * This is not a 100% solution for all memory, but tries to be
 * ``good enough'' for the majority of memory.
 */
int soft_offline_page(struct page *page, int flags)
{
	int ret;
	unsigned long pfn = page_to_pfn(page);

	if (PageHuge(page))
		return soft_offline_huge_page(page, flags);

	ret = get_any_page(page, pfn, flags);
	if (ret < 0)
		return ret;
	if (ret == 0)
		goto done;

	/*
	 * Page cache page we can handle?
	 */
	if (!PageLRU(page)) {
		/*
		 * Try to free it.
		 */
		put_page(page);
		shake_page(page, 1);

		/*
		 * Did it turn free?
		 */
		ret = get_any_page(page, pfn, 0);
		if (ret < 0)
			return ret;
		if (ret == 0)
			goto done;
	}
	if (!PageLRU(page)) {
		pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
				pfn, page->flags);
		return -EIO;
	}

	lock_page(page);
	wait_on_page_writeback(page);

	/*
	 * Synchronized using the page lock with memory_failure()
	 */
	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);
	unlock_page(page);

	/*
	 * Drop count because page migration doesn't like raised
	 * counts. The page could get re-allocated, but if it becomes
	 * LRU the isolation will just fail.
	 * RED-PEN would be better to keep it isolated here, but we
	 * would need to fix isolation locking first.
	 */
	put_page(page);
	if (ret == 1) {
		ret = 0;
		pr_info("soft_offline: %#lx: invalidated\n", pfn);
		goto done;
	}

	/*
	 * Simple invalidation didn't work.
	 * Try to migrate to a new page instead. migrate.c
	 * handles a large number of cases for us.
	 */
	ret = isolate_lru_page(page);
	if (!ret) {
		LIST_HEAD(pagelist);

		list_add(&page->lru, &pagelist);
		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
								0, true);
		if (ret) {
			putback_lru_pages(&pagelist);
			pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
				pfn, ret, page->flags);
			if (ret > 0)
				ret = -EIO;
		}
	} else {
		pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
				pfn, ret, page_count(page), page->flags);
	}
	if (ret)
		return ret;

done:
	atomic_long_add(1, &mce_bad_pages);
	SetPageHWPoison(page);
	/* keep elevated page count for bad page */
	return ret;
}

/*
 * The caller must hold current->mm->mmap_sem in read mode.
 */
int is_hwpoison_address(unsigned long addr)
{
	pgd_t *pgdp;
	pud_t pud, *pudp;
	pmd_t pmd, *pmdp;
	pte_t pte, *ptep;
	swp_entry_t entry;

	pgdp = pgd_offset(current->mm, addr);
	if (!pgd_present(*pgdp))
		return 0;
	pudp = pud_offset(pgdp, addr);
	pud = *pudp;
	if (!pud_present(pud) || pud_large(pud))
		return 0;
	pmdp = pmd_offset(pudp, addr);
	pmd = *pmdp;
	if (!pmd_present(pmd) || pmd_large(pmd))
		return 0;
	ptep = pte_offset_map(pmdp, addr);
	pte = *ptep;
	pte_unmap(ptep);
	if (!is_swap_pte(pte))
		return 0;
	entry = pte_to_swp_entry(pte);
	return is_hwpoison_entry(entry);
}
EXPORT_SYMBOL_GPL(is_hwpoison_address);