4.14.86-stable review

index adacfe66cf3d..09d7e9c4de89 100644
@@ -2280,7 +2280,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 	}
 }
 
-static void freeze_page(struct page *page)
+static void unmap_page(struct page *page)
 {
 	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
 		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;

@@ -2295,7 +2295,7 @@ static void freeze_page(struct page *page)
 	VM_BUG_ON_PAGE(!unmap_success, page);
 }
 
-static void unfreeze_page(struct page *page)
+static void remap_page(struct page *page)
 {
 	int i;
 	if (PageTransHuge(page)) {

@@ -2412,7 +2412,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 
 	spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
 
-	unfreeze_page(head);
+	remap_page(head);
 
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
 		struct page *subpage = head + i;

@@ -2593,7 +2593,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	}
 
 	/*
-	 * Racy check if we can split the page, before freeze_page() will
+	 * Racy check if we can split the page, before unmap_page() will
 	 * split PMDs
 	 */
 	if (!can_split_huge_page(head, &extra_pins)) {

@@ -2602,7 +2602,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	}
 
 	mlocked = PageMlocked(page);
-	freeze_page(head);
+	unmap_page(head);
 	VM_BUG_ON_PAGE(compound_mapcount(head), head);
 
 	/* Make sure the page is not on per-CPU pagevec as it takes pin */

@@ -2659,7 +2659,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 fail:		if (mapping)
 			spin_unlock(&mapping->tree_lock);
 		spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
-		unfreeze_page(head);
+		remap_page(head);
 		ret = -EBUSY;
 	}
 

index 09d7e9c4de89..8969f5cf3174 100644
@@ -2312,26 +2312,13 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	struct page *page_tail = head + tail;
 
 	VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);
-	VM_BUG_ON_PAGE(page_ref_count(page_tail) != 0, page_tail);
 
 	/*
-	 * tail_page->_refcount is zero and not changing from under us. But
-	 * get_page_unless_zero() may be running from under us on the
-	 * tail_page. If we used atomic_set() below instead of atomic_inc() or
-	 * atomic_add(), we would then run atomic_set() concurrently with
-	 * get_page_unless_zero(), and atomic_set() is implemented in C not
-	 * using locked ops. spin_unlock on x86 sometime uses locked ops
-	 * because of PPro errata 66, 92, so unless somebody can guarantee
-	 * atomic_set() here would be safe on all archs (and not only on x86),
-	 * it's safer to use atomic_inc()/atomic_add().
+	 * Clone page flags before unfreezing refcount.
+	 *
+	 * After successful get_page_unless_zero() might follow flags change,
+	 * for exmaple lock_page() which set PG_waiters.
 	 */
-	if (PageAnon(head) && !PageSwapCache(head)) {
-		page_ref_inc(page_tail);
-	} else {
-		/* Additional pin to radix tree */
-		page_ref_add(page_tail, 2);
-	}
-
 	page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	page_tail->flags |= (head->flags &
 			((1L << PG_referenced) |

@@ -2344,14 +2331,21 @@ static void __split_huge_page_tail(struct page *head, int tail,
 			 (1L << PG_unevictable) |
 			 (1L << PG_dirty)));
 
-	/*
-	 * After clearing PageTail the gup refcount can be released.
-	 * Page flags also must be visible before we make the page non-compound.
-	 */
+	/* Page flags must be visible before we make the page non-compound. */
 	smp_wmb();
 
+	/*
+	 * Clear PageTail before unfreezing page refcount.
+	 *
+	 * After successful get_page_unless_zero() might follow put_page()
+	 * which needs correct compound_head().
+	 */
 	clear_compound_head(page_tail);
 
+	/* Finally unfreeze refcount. Additional reference from page cache. */
+	page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) ||
+					  PageSwapCache(head)));
+
 	if (page_is_young(head))
 		set_page_young(page_tail);
 	if (page_is_idle(head))

index 8969f5cf3174..69ffeb439b0f 100644
@@ -2331,6 +2331,12 @@ static void __split_huge_page_tail(struct page *head, int tail,
 			 (1L << PG_unevictable) |
 			 (1L << PG_dirty)));
 
+	/* ->mapping in first tail page is compound_mapcount */
+	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
+			page_tail);
+	page_tail->mapping = head->mapping;
+	page_tail->index = head->index + tail;
+
 	/* Page flags must be visible before we make the page non-compound. */
 	smp_wmb();
 

@@ -2351,12 +2357,6 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	if (page_is_idle(head))
 		set_page_idle(page_tail);
 
-	/* ->mapping in first tail page is compound_mapcount */
-	VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING,
-			page_tail);
-	page_tail->mapping = head->mapping;
-
-	page_tail->index = head->index + tail;
 	page_cpupid_xchg_last(page_tail, page_cpupid_last(head));
 	lru_add_page_tail(head, page_tail, lruvec, list);
 }

index 69ffeb439b0f..930f2aa3bb4d 100644
@@ -2362,12 +2362,11 @@ static void __split_huge_page_tail(struct page *head, int tail,
 }
 
 static void __split_huge_page(struct page *page, struct list_head *list,
-		unsigned long flags)
+		pgoff_t end, unsigned long flags)
 {
 	struct page *head = compound_head(page);
 	struct zone *zone = page_zone(head);
 	struct lruvec *lruvec;
-	pgoff_t end = -1;
 	int i;
 
 	lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat);

@@ -2375,9 +2374,6 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	/* complete memcg works before add pages to LRU */
 	mem_cgroup_split_huge_fixup(head);
 
-	if (!PageAnon(page))
-		end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE);
-
 	for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
 		__split_huge_page_tail(head, i, lruvec, list);
 		/* Some pages can be beyond i_size: drop them from page cache */

@@ -2549,6 +2545,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	int count, mapcount, extra_pins, ret;
 	bool mlocked;
 	unsigned long flags;
+	pgoff_t end;
 
 	VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);

@@ -2571,6 +2568,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			ret = -EBUSY;
 			goto out;
 		}
+		end = -1;
 		mapping = NULL;
 		anon_vma_lock_write(anon_vma);
 	} else {

@@ -2584,6 +2582,15 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 		anon_vma = NULL;
 		i_mmap_lock_read(mapping);
+
+		/*
+		 *__split_huge_page() may need to trim off pages beyond EOF:
+		 * but on 32-bit, i_size_read() takes an irq-unsafe seqlock,
+		 * which cannot be nested inside the page tree lock. So note
+		 * end now: i_size itself may be changed at any moment, but
+		 * head page lock is good enough to serialize the trimming.
+		 */
+		end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE);
 	}
 
 	/*

@@ -2633,7 +2640,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		if (mapping)
 			__dec_node_page_state(page, NR_SHMEM_THPS);
 		spin_unlock(&pgdata->split_queue_lock);
-		__split_huge_page(page, list, flags);
+		__split_huge_page(page, list, end, flags);
 		if (PageSwapCache(head)) {
 			swp_entry_t entry = { .val = page_private(head) };
 

index 0a5bb3e8a8a3..d4a06afbeda4 100644
@@ -1352,6 +1352,16 @@ static void collapse_shmem(struct mm_struct *mm,
 	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
 		int n = min(iter.index, end) - index;
 
+		/*
+		 * Stop if extent has been hole-punched, and is now completely
+		 * empty (the more obvious i_size_read() check would take an
+		 * irq-unsafe seqlock on 32-bit).
+		 */
+		if (n >= HPAGE_PMD_NR) {
+			result = SCAN_TRUNCATED;
+			goto tree_locked;
+		}
+
 		/*
 		 * Handle holes in the radix tree: charge it from shmem and
 		 * insert relevant subpage of new_page into the radix-tree.

@@ -1463,6 +1473,11 @@ static void collapse_shmem(struct mm_struct *mm,
 	if (result == SCAN_SUCCEED && index < end) {
 		int n = end - index;
 
+		/* Stop if extent has been truncated, and is now empty */
+		if (n >= HPAGE_PMD_NR) {
+			result = SCAN_TRUNCATED;
+			goto tree_locked;
+		}
 		if (!shmem_charge(mapping->host, n)) {
 			result = SCAN_FAIL;
 			goto tree_locked;

index d4a06afbeda4..be7b0863e33c 100644
@@ -1539,8 +1539,10 @@ static void collapse_shmem(struct mm_struct *mm,
 		*hpage = NULL;
 	} else {
 		/* Something went wrong: rollback changes to the radix-tree */
-		shmem_uncharge(mapping->host, nr_none);
 		spin_lock_irq(&mapping->tree_lock);
+		mapping->nrpages -= nr_none;
+		shmem_uncharge(mapping->host, nr_none);
+
 		radix_tree_for_each_slot(slot, &mapping->page_tree, &iter,
 				start) {
 			if (iter.index >= end)

index fa08f56fd5e5..177fef62cbbd 100644
@@ -296,12 +296,14 @@ bool shmem_charge(struct inode *inode, long pages)
 	if (!shmem_inode_acct_block(inode, pages))
 		return false;
 
+	/* nrpages adjustment first, then shmem_recalc_inode() when balanced */
+	inode->i_mapping->nrpages += pages;
+
 	spin_lock_irqsave(&info->lock, flags);
 	info->alloced += pages;
 	inode->i_blocks += pages * BLOCKS_PER_PAGE;
 	shmem_recalc_inode(inode);
 	spin_unlock_irqrestore(&info->lock, flags);
-	inode->i_mapping->nrpages += pages;
 
 	return true;
 }

@@ -311,6 +313,8 @@ void shmem_uncharge(struct inode *inode, long pages)
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	unsigned long flags;
 
+	/* nrpages adjustment done by __delete_from_page_cache() or caller */
+
 	spin_lock_irqsave(&info->lock, flags);
 	info->alloced -= pages;
 	inode->i_blocks -= pages * BLOCKS_PER_PAGE;

index be7b0863e33c..f535dbe3f9f5 100644
@@ -1502,7 +1502,12 @@ static void collapse_shmem(struct mm_struct *mm,
 		 * Replacing old pages with new one has succeed, now we need to
 		 * copy the content and free old pages.
 		 */
+		index = start;
 		list_for_each_entry_safe(page, tmp, &pagelist, lru) {
+			while (index < page->index) {
+				clear_highpage(new_page + (index % HPAGE_PMD_NR));
+				index++;
+			}
 			copy_highpage(new_page + (page->index % HPAGE_PMD_NR),
 					page);
 			list_del(&page->lru);

@@ -1512,6 +1517,11 @@ static void collapse_shmem(struct mm_struct *mm,
 			ClearPageActive(page);
 			ClearPageUnevictable(page);
 			put_page(page);
+			index++;
+		}
+		while (index < end) {
+			clear_highpage(new_page + (index % HPAGE_PMD_NR));
+			index++;
 		}
 
 		local_irq_save(flags);

index f535dbe3f9f5..0eac4344477a 100644
@@ -1333,13 +1333,12 @@ static void collapse_shmem(struct mm_struct *mm,
 		goto out;
 	}
 
+	__SetPageLocked(new_page);
+	__SetPageSwapBacked(new_page);
 	new_page->index = start;
 	new_page->mapping = mapping;
-	__SetPageSwapBacked(new_page);
-	__SetPageLocked(new_page);
 	BUG_ON(!page_ref_freeze(new_page, 1));
 
-
 	/*
 	 * At this point the new_page is 'frozen' (page_count() is zero), locked
 	 * and not up-to-date. It's safe to insert it into radix tree, because

@@ -1368,13 +1367,13 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		if (n && !shmem_charge(mapping->host, n)) {
 			result = SCAN_FAIL;
-			break;
+			goto tree_locked;
 		}
-		nr_none += n;
 		for (; index < min(iter.index, end); index++) {
 			radix_tree_insert(&mapping->page_tree, index,
 					new_page + (index % HPAGE_PMD_NR));
 		}
+		nr_none += n;
 
 		/* We are done. */
 		if (index >= end)

@@ -1390,12 +1389,12 @@ static void collapse_shmem(struct mm_struct *mm,
 				result = SCAN_FAIL;
 				goto tree_unlocked;
 			}
-			spin_lock_irq(&mapping->tree_lock);
 		} else if (trylock_page(page)) {
 			get_page(page);
+			spin_unlock_irq(&mapping->tree_lock);
 		} else {
 			result = SCAN_PAGE_LOCK;
-			break;
+			goto tree_locked;
 		}
 
 		/*

@@ -1410,11 +1409,10 @@ static void collapse_shmem(struct mm_struct *mm,
 			result = SCAN_TRUNCATED;
 			goto out_unlock;
 		}
-		spin_unlock_irq(&mapping->tree_lock);
 
 		if (isolate_lru_page(page)) {
 			result = SCAN_DEL_PAGE_LRU;
-			goto out_isolate_failed;
+			goto out_unlock;
 		}
 
 		if (page_mapped(page))

@@ -1436,7 +1434,9 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		if (!page_ref_freeze(page, 3)) {
 			result = SCAN_PAGE_COUNT;
-			goto out_lru;
+			spin_unlock_irq(&mapping->tree_lock);
+			putback_lru_page(page);
+			goto out_unlock;
 		}
 
 		/*

@@ -1452,17 +1452,10 @@ static void collapse_shmem(struct mm_struct *mm,
 		slot = radix_tree_iter_resume(slot, &iter);
 		index++;
 		continue;
-out_lru:
-		spin_unlock_irq(&mapping->tree_lock);
-		putback_lru_page(page);
-out_isolate_failed:
-		unlock_page(page);
-		put_page(page);
-		goto tree_unlocked;
 out_unlock:
 		unlock_page(page);
 		put_page(page);
-		break;
+		goto tree_unlocked;
 	}
 
 	/*

@@ -1470,7 +1463,7 @@ static void collapse_shmem(struct mm_struct *mm,
 	 * This code only triggers if there's nothing in radix tree
 	 * beyond 'end'.
 	 */
-	if (result == SCAN_SUCCEED && index < end) {
+	if (index < end) {
 		int n = end - index;
 
 		/* Stop if extent has been truncated, and is now empty */

@@ -1482,7 +1475,6 @@ static void collapse_shmem(struct mm_struct *mm,
 			result = SCAN_FAIL;
 			goto tree_locked;
 		}
-
 		for (; index < end; index++) {
 			radix_tree_insert(&mapping->page_tree, index,
 					new_page + (index % HPAGE_PMD_NR));

@@ -1490,14 +1482,19 @@ static void collapse_shmem(struct mm_struct *mm,
 		nr_none += n;
 	}
 
+	__inc_node_page_state(new_page, NR_SHMEM_THPS);
+	if (nr_none) {
+		struct zone *zone = page_zone(new_page);
+
+		__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
+		__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
+	}
+
 tree_locked:
 	spin_unlock_irq(&mapping->tree_lock);
 tree_unlocked:
 
 	if (result == SCAN_SUCCEED) {
-		unsigned long flags;
-		struct zone *zone = page_zone(new_page);
-
 		/*
 		 * Replacing old pages with new one has succeed, now we need to
 		 * copy the content and free old pages.

@@ -1511,11 +1508,11 @@ static void collapse_shmem(struct mm_struct *mm,
 			copy_highpage(new_page + (page->index % HPAGE_PMD_NR),
 					page);
 			list_del(&page->lru);
-			unlock_page(page);
-			page_ref_unfreeze(page, 1);
 			page->mapping = NULL;
+			page_ref_unfreeze(page, 1);
 			ClearPageActive(page);
 			ClearPageUnevictable(page);
+			unlock_page(page);
 			put_page(page);
 			index++;
 		}

@@ -1524,28 +1521,17 @@ static void collapse_shmem(struct mm_struct *mm,
 			index++;
 		}
 
-		local_irq_save(flags);
-		__inc_node_page_state(new_page, NR_SHMEM_THPS);
-		if (nr_none) {
-			__mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
-			__mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
-		}
-		local_irq_restore(flags);
-
-		/*
-		 * Remove pte page tables, so we can re-faulti
-		 * the page as huge.
-		 */
-		retract_page_tables(mapping, start);
-
 		/* Everything is ready, let's unfreeze the new_page */
-		set_page_dirty(new_page);
 		SetPageUptodate(new_page);
 		page_ref_unfreeze(new_page, HPAGE_PMD_NR);
+		set_page_dirty(new_page);
 		mem_cgroup_commit_charge(new_page, memcg, false, true);
 		lru_cache_add_anon(new_page);
-		unlock_page(new_page);
 
+		/*
+		 * Remove pte page tables, so we can re-fault the page as huge.
+		 */
+		retract_page_tables(mapping, start);
 		*hpage = NULL;
 	} else {
 		/* Something went wrong: rollback changes to the radix-tree */

@@ -1578,8 +1564,8 @@ static void collapse_shmem(struct mm_struct *mm,
 						slot, page);
 			slot = radix_tree_iter_resume(slot, &iter);
 			spin_unlock_irq(&mapping->tree_lock);
-			putback_lru_page(page);
 			unlock_page(page);
+			putback_lru_page(page);
 			spin_lock_irq(&mapping->tree_lock);
 		}
 		VM_BUG_ON(nr_none);

@@ -1588,9 +1574,10 @@ static void collapse_shmem(struct mm_struct *mm,
 		/* Unfreeze new_page, caller would take care about freeing it */
 		page_ref_unfreeze(new_page, 1);
 		mem_cgroup_cancel_charge(new_page, memcg, true);
-		unlock_page(new_page);
 		new_page->mapping = NULL;
 	}
+
+	unlock_page(new_page);
 out:
 	VM_BUG_ON(!list_empty(&pagelist));
 	/* TODO: tracepoints */

index 0eac4344477a..45bf0e5775f7 100644
@@ -1288,7 +1288,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  * collapse_shmem - collapse small tmpfs/shmem pages into huge one.
  *
  * Basic scheme is simple, details are more complex:
- *  - allocate and freeze a new huge page;
+ *  - allocate and lock a new huge page;
  *  - scan over radix tree replacing old pages the new one
  *    + swap in pages if necessary;
  *    + fill in gaps;

@@ -1296,11 +1296,11 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
  *  - if replacing succeed:
  *    + copy data over;
  *    + free old pages;
- *    + unfreeze huge page;
+ *    + unlock huge page;
  *  - if replacing failed;
  *    + put all pages back and unfreeze them;
  *    + restore gaps in the radix-tree;
- *    + free huge page;
+ *    + unlock and free huge page;
  */
 static void collapse_shmem(struct mm_struct *mm,
 		struct address_space *mapping, pgoff_t start,

@@ -1337,13 +1337,11 @@ static void collapse_shmem(struct mm_struct *mm,
 	__SetPageSwapBacked(new_page);
 	new_page->index = start;
 	new_page->mapping = mapping;
-	BUG_ON(!page_ref_freeze(new_page, 1));
 
 	/*
-	 * At this point the new_page is 'frozen' (page_count() is zero), locked
-	 * and not up-to-date. It's safe to insert it into radix tree, because
-	 * nobody would be able to map it or use it in other way until we
-	 * unfreeze it.
+	 * At this point the new_page is locked and not up-to-date.
+	 * It's safe to insert it into the page cache, because nobody would
+	 * be able to map it or use it in another way until we unlock it.
 	 */
 
 	index = start;

@@ -1521,9 +1519,8 @@ static void collapse_shmem(struct mm_struct *mm,
 			index++;
 		}
 
-		/* Everything is ready, let's unfreeze the new_page */
 		SetPageUptodate(new_page);
-		page_ref_unfreeze(new_page, HPAGE_PMD_NR);
+		page_ref_add(new_page, HPAGE_PMD_NR - 1);
 		set_page_dirty(new_page);
 		mem_cgroup_commit_charge(new_page, memcg, false, true);
 		lru_cache_add_anon(new_page);

@@ -1571,8 +1568,6 @@ static void collapse_shmem(struct mm_struct *mm,
 		VM_BUG_ON(nr_none);
 		spin_unlock_irq(&mapping->tree_lock);
 
-		/* Unfreeze new_page, caller would take care about freeing it */
-		page_ref_unfreeze(new_page, 1);
 		mem_cgroup_cancel_charge(new_page, memcg, true);
 		new_page->mapping = NULL;
 	}

index 45bf0e5775f7..d27a73737f1a 100644
@@ -1401,7 +1401,15 @@ static void collapse_shmem(struct mm_struct *mm,
 		 */
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		VM_BUG_ON_PAGE(!PageUptodate(page), page);
-		VM_BUG_ON_PAGE(PageTransCompound(page), page);
+
+		/*
+		 * If file was truncated then extended, or hole-punched, before
+		 * we locked the first page, then a THP might be there already.
+		 */
+		if (PageTransCompound(page)) {
+			result = SCAN_PAGE_COMPOUND;
+			goto out_unlock;
+		}
 
 		if (page_mapping(page) != mapping) {
 			result = SCAN_TRUNCATED;

index 4a7db623fe29..29cdaaf1ed90 100644
@@ -2105,6 +2105,8 @@ static int em28xx_dvb_fini(struct em28xx *dev)
 		}
 	}
 
+	em28xx_unregister_dvb(dvb);
+
 	/* remove I2C SEC */
 	client = dvb->i2c_client_sec;
 	if (client) {

@@ -2126,7 +2128,6 @@ static int em28xx_dvb_fini(struct em28xx *dev)
 		i2c_unregister_device(client);
 	}
 
-	em28xx_unregister_dvb(dvb);
 	kfree(dvb);
 	dev->dvb = NULL;
 	kref_put(&dev->ref, em28xx_free_device);

index 94d7a865b135..7504f430c011 100644
@@ -578,6 +578,16 @@ static int init_volumes(struct ubi_device *ubi,
 		vol->ubi = ubi;
 		reserved_pebs += vol->reserved_pebs;
 
+		/*
+		 * We use ubi->peb_count and not vol->reserved_pebs because
+		 * we want to keep the code simple. Otherwise we'd have to
+		 * resize/check the bitmap upon volume resize too.
+		 * Allocating a few bytes more does not hurt.
+		 */
+		err = ubi_fastmap_init_checkmap(vol, ubi->peb_count);
+		if (err)
+			return err;
+
 		/*
 		 * In case of dynamic volume UBI knows nothing about how many
 		 * data is stored there. So assume the whole volume is used.

@@ -620,16 +630,6 @@ static int init_volumes(struct ubi_device *ubi,
 			(long long)(vol->used_ebs - 1) * vol->usable_leb_size;
 		vol->used_bytes += av->last_data_size;
 		vol->last_eb_bytes = av->last_data_size;
-
-		/*
-		 * We use ubi->peb_count and not vol->reserved_pebs because
-		 * we want to keep the code simple. Otherwise we'd have to
-		 * resize/check the bitmap upon volume resize too.
-		 * Allocating a few bytes more does not hurt.
-		 */
-		err = ubi_fastmap_init_checkmap(vol, ubi->peb_count);
-		if (err)
-			return err;
 	}
 
 	/* And add the layout volume */

index ead9d85f1c11..9056077c023f 100644
@@ -203,9 +203,8 @@ struct ceph_connection {
 				 attempt for this connection, client */
 	u32 peer_global_seq;  /* peer's global seq for this connection */
 
+	struct ceph_auth_handshake *auth;
 	int auth_retry;       /* true if we need a newer authorizer */
-	void *auth_reply_buf;   /* where to put the authorizer reply */
-	int auth_reply_buf_len;
 
 	struct mutex mutex;
 

103 lines not on this page · raw message

index 3a82e6d2864b..0b121327d32f 100644
@@ -1446,6 +1446,17 @@ static void prepare_write_banner(struct ceph_connection *con)
 	con_flag_set(con, CON_FLAG_WRITE_PENDING);
 }
 
+static void __prepare_write_connect(struct ceph_connection *con)
+{
+	con_out_kvec_add(con, sizeof(con->out_connect), &con->out_connect);
+	if (con->auth)
+		con_out_kvec_add(con, con->auth->authorizer_buf_len,
+				 con->auth->authorizer_buf);
+
+	con->out_more = 0;
+	con_flag_set(con, CON_FLAG_WRITE_PENDING);
+}
+
 static int prepare_write_connect(struct ceph_connection *con)
 {
 	unsigned int global_seq = get_global_seq(con->msgr, 0);

@@ -1481,15 +1492,7 @@ static int prepare_write_connect(struct ceph_connection *con)
 	if (ret)
 		return ret;
 
-	con_out_kvec_add(con, sizeof (con->out_connect),
-					&con->out_connect);
-	if (con->auth)
-		con_out_kvec_add(con, con->auth->authorizer_buf_len,
-				 con->auth->authorizer_buf);
-
-	con->out_more = 0;
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
-
+	__prepare_write_connect(con);
 	return 0;
 }
 

index 2f4a1baf5f52..9cac05239346 100644
@@ -70,25 +70,40 @@ static int ceph_x_encrypt(struct ceph_crypto_key *secret, void *buf,
 	return sizeof(u32) + ciphertext_len;
 }
 
+static int __ceph_x_decrypt(struct ceph_crypto_key *secret, void *p,
+			    int ciphertext_len)
+{
+	struct ceph_x_encrypt_header *hdr = p;
+	int plaintext_len;
+	int ret;
+
+	ret = ceph_crypt(secret, false, p, ciphertext_len, ciphertext_len,
+			 &plaintext_len);
+	if (ret)
+		return ret;
+
+	if (le64_to_cpu(hdr->magic) != CEPHX_ENC_MAGIC) {
+		pr_err("%s bad magic\n", __func__);
+		return -EINVAL;
+	}
+
+	return plaintext_len - sizeof(*hdr);
+}
+
 static int ceph_x_decrypt(struct ceph_crypto_key *secret, void **p, void *end)
 {
-	struct ceph_x_encrypt_header *hdr = *p + sizeof(u32);
-	int ciphertext_len, plaintext_len;
+	int ciphertext_len;
 	int ret;
 
 	ceph_decode_32_safe(p, end, ciphertext_len, e_inval);
 	ceph_decode_need(p, end, ciphertext_len, e_inval);
 
-	ret = ceph_crypt(secret, false, *p, end - *p, ciphertext_len,
-			 &plaintext_len);
-	if (ret)
+	ret = __ceph_x_decrypt(secret, *p, ciphertext_len);
+	if (ret < 0)
 		return ret;
 
-	if (hdr->struct_v != 1 || le64_to_cpu(hdr->magic) != CEPHX_ENC_MAGIC)
-		return -EPERM;
-
 	*p += ciphertext_len;
-	return plaintext_len - sizeof(struct ceph_x_encrypt_header);
+	return ret;
 
 e_inval:
 	return -EINVAL;

index 9cac05239346..722791f45b2a 100644
@@ -290,6 +290,38 @@ bad:
 	return -EINVAL;
 }
 
+/*
+ * Encode and encrypt the second part (ceph_x_authorize_b) of the
+ * authorizer.  The first part (ceph_x_authorize_a) should already be
+ * encoded.
+ */
+static int encrypt_authorizer(struct ceph_x_authorizer *au)
+{
+	struct ceph_x_authorize_a *msg_a;
+	struct ceph_x_authorize_b *msg_b;
+	void *p, *end;
+	int ret;
+
+	msg_a = au->buf->vec.iov_base;
+	WARN_ON(msg_a->ticket_blob.secret_id != cpu_to_le64(au->secret_id));
+	p = (void *)(msg_a + 1) + le32_to_cpu(msg_a->ticket_blob.blob_len);
+	end = au->buf->vec.iov_base + au->buf->vec.iov_len;
+
+	msg_b = p + ceph_x_encrypt_offset();
+	msg_b->struct_v = 1;
+	msg_b->nonce = cpu_to_le64(au->nonce);
+
+	ret = ceph_x_encrypt(&au->session_key, p, end - p, sizeof(*msg_b));
+	if (ret < 0)
+		return ret;
+
+	p += ret;
+	WARN_ON(p > end);
+	au->buf->vec.iov_len = p - au->buf->vec.iov_base;
+
+	return 0;
+}
+
 static void ceph_x_authorizer_cleanup(struct ceph_x_authorizer *au)
 {
 	ceph_crypto_key_destroy(&au->session_key);

@@ -306,7 +338,6 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 	int maxlen;
 	struct ceph_x_authorize_a *msg_a;
 	struct ceph_x_authorize_b *msg_b;
-	void *p, *end;
 	int ret;
 	int ticket_blob_len =
 		(th->ticket_blob ? th->ticket_blob->vec.iov_len : 0);

@@ -350,21 +381,13 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 	dout(" th %p secret_id %lld %lld\n", th, th->secret_id,
 	     le64_to_cpu(msg_a->ticket_blob.secret_id));
 
-	p = msg_a + 1;
-	p += ticket_blob_len;
-	end = au->buf->vec.iov_base + au->buf->vec.iov_len;
-
-	msg_b = p + ceph_x_encrypt_offset();
-	msg_b->struct_v = 1;
 	get_random_bytes(&au->nonce, sizeof(au->nonce));
-	msg_b->nonce = cpu_to_le64(au->nonce);
-	ret = ceph_x_encrypt(&au->session_key, p, end - p, sizeof(*msg_b));
-	if (ret < 0)
+	ret = encrypt_authorizer(au);
+	if (ret) {
+		pr_err("failed to encrypt authorizer: %d", ret);
 		goto out_au;
+	}
 
-	p += ret;
-	WARN_ON(p > end);
-	au->buf->vec.iov_len = p - au->buf->vec.iov_base;
 	dout(" built authorizer nonce %llx len %d\n", au->nonce,
 	     (int)au->buf->vec.iov_len);
 	return 0;

index bf378ddca4db..a48984dd6426 100644
@@ -4079,6 +4079,16 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
 	return auth;
 }
 
+static int add_authorizer_challenge(struct ceph_connection *con,
+				    void *challenge_buf, int challenge_buf_len)
+{
+	struct ceph_mds_session *s = con->private;
+	struct ceph_mds_client *mdsc = s->s_mdsc;
+	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
+
+	return ceph_auth_add_authorizer_challenge(ac, s->s_auth.authorizer,
+					    challenge_buf, challenge_buf_len);
+}
 
 static int verify_authorizer_reply(struct ceph_connection *con)
 {

@@ -4142,6 +4152,7 @@ static const struct ceph_connection_operations mds_con_ops = {
 	.put = con_put,
 	.dispatch = dispatch,
 	.get_authorizer = get_authorizer,
+	.add_authorizer_challenge = add_authorizer_challenge,
 	.verify_authorizer_reply = verify_authorizer_reply,
 	.invalidate_authorizer = invalidate_authorizer,
 	.peer_reset = peer_reset,

index e931da8424a4..6728c2ee0205 100644
@@ -64,6 +64,10 @@ struct ceph_auth_client_ops {
 	/* ensure that an existing authorizer is up to date */
 	int (*update_authorizer)(struct ceph_auth_client *ac, int peer_type,
 				 struct ceph_auth_handshake *auth);
+	int (*add_authorizer_challenge)(struct ceph_auth_client *ac,
+					struct ceph_authorizer *a,
+					void *challenge_buf,
+					int challenge_buf_len);
 	int (*verify_authorizer_reply)(struct ceph_auth_client *ac,
 				       struct ceph_authorizer *a);
 	void (*invalidate_authorizer)(struct ceph_auth_client *ac,

@@ -118,6 +122,10 @@ void ceph_auth_destroy_authorizer(struct ceph_authorizer *a);
 extern int ceph_auth_update_authorizer(struct ceph_auth_client *ac,
 				       int peer_type,
 				       struct ceph_auth_handshake *a);
+int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac,
+				       struct ceph_authorizer *a,
+				       void *challenge_buf,
+				       int challenge_buf_len);
 extern int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac,
 					     struct ceph_authorizer *a);
 extern void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac,

index 9056077c023f..18fbe910ed55 100644
@@ -31,6 +31,9 @@ struct ceph_connection_operations {
 	struct ceph_auth_handshake *(*get_authorizer) (
 				struct ceph_connection *con,
 			       int *proto, int force_new);
+	int (*add_authorizer_challenge)(struct ceph_connection *con,
+					void *challenge_buf,
+					int challenge_buf_len);
 	int (*verify_authorizer_reply) (struct ceph_connection *con);
 	int (*invalidate_authorizer)(struct ceph_connection *con);
 

index 73ae2a926548..9e50aede46c8 100644
@@ -91,7 +91,7 @@ struct ceph_entity_inst {
 #define CEPH_MSGR_TAG_SEQ           13 /* 64-bit int follows with seen seq number */
 #define CEPH_MSGR_TAG_KEEPALIVE2    14 /* keepalive2 byte + ceph_timespec */
 #define CEPH_MSGR_TAG_KEEPALIVE2_ACK 15 /* keepalive2 reply */
-
+#define CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER 16  /* cephx v2 doing server challenge */
 
 /*
  * connection negotiation

index dbde2b3c3c15..fbeee068ea14 100644
@@ -315,6 +315,22 @@ int ceph_auth_update_authorizer(struct ceph_auth_client *ac,
 }
 EXPORT_SYMBOL(ceph_auth_update_authorizer);
 
+int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac,
+				       struct ceph_authorizer *a,
+				       void *challenge_buf,
+				       int challenge_buf_len)
+{
+	int ret = 0;
+
+	mutex_lock(&ac->mutex);
+	if (ac->ops && ac->ops->add_authorizer_challenge)
+		ret = ac->ops->add_authorizer_challenge(ac, a, challenge_buf,
+							challenge_buf_len);
+	mutex_unlock(&ac->mutex);
+	return ret;
+}
+EXPORT_SYMBOL(ceph_auth_add_authorizer_challenge);
+
 int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac,
 				      struct ceph_authorizer *a)
 {

109 lines not on this page · raw message

index 32c13d763b9a..24b0b74564d0 100644
@@ -70,6 +70,13 @@ struct ceph_x_authorize_a {
 struct ceph_x_authorize_b {
 	__u8 struct_v;
 	__le64 nonce;
+	__u8 have_challenge;
+	__le64 server_challenge_plus_one;
+} __attribute__ ((packed));
+
+struct ceph_x_authorize_challenge {
+	__u8 struct_v;
+	__le64 server_challenge;
 } __attribute__ ((packed));
 
 struct ceph_x_authorize_reply {

index 0b121327d32f..ad33baa2008d 100644
@@ -2052,9 +2052,24 @@ static int process_connect(struct ceph_connection *con)
 	if (con->auth) {
 		/*
 		 * Any connection that defines ->get_authorizer()
-		 * should also define ->verify_authorizer_reply().
+		 * should also define ->add_authorizer_challenge() and
+		 * ->verify_authorizer_reply().
+		 *
 		 * See get_connect_authorizer().
 		 */
+		if (con->in_reply.tag == CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) {
+			ret = con->ops->add_authorizer_challenge(
+				    con, con->auth->authorizer_reply_buf,
+				    le32_to_cpu(con->in_reply.authorizer_len));
+			if (ret < 0)
+				return ret;
+
+			con_out_kvec_reset(con);
+			__prepare_write_connect(con);
+			prepare_read_connect(con);
+			return 0;
+		}
+
 		ret = con->ops->verify_authorizer_reply(con);
 		if (ret < 0) {
 			con->error_msg = "bad authorize reply";

index 2814dba5902d..53ea2d48896c 100644
@@ -5292,6 +5292,16 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
 	return auth;
 }
 
+static int add_authorizer_challenge(struct ceph_connection *con,
+				    void *challenge_buf, int challenge_buf_len)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_osd_client *osdc = o->o_osdc;
+	struct ceph_auth_client *ac = osdc->client->monc.auth;
+
+	return ceph_auth_add_authorizer_challenge(ac, o->o_auth.authorizer,
+					    challenge_buf, challenge_buf_len);
+}
 
 static int verify_authorizer_reply(struct ceph_connection *con)
 {

@@ -5341,6 +5351,7 @@ static const struct ceph_connection_operations osd_con_ops = {
 	.put = put_osd_con,
 	.dispatch = dispatch,
 	.get_authorizer = get_authorizer,
+	.add_authorizer_challenge = add_authorizer_challenge,
 	.verify_authorizer_reply = verify_authorizer_reply,
 	.invalidate_authorizer = invalidate_authorizer,
 	.alloc_msg = alloc_msg,

index 59042d5ac520..70f42eef813b 100644
@@ -165,9 +165,9 @@ DEFINE_CEPH_FEATURE(58, 1, FS_FILE_LAYOUT_V2) // overlap
 DEFINE_CEPH_FEATURE(59, 1, FS_BTIME)
 DEFINE_CEPH_FEATURE(59, 1, FS_CHANGE_ATTR) // overlap
 DEFINE_CEPH_FEATURE(59, 1, MSG_ADDR2) // overlap
-DEFINE_CEPH_FEATURE(60, 1, BLKIN_TRACING)  // *do not share this bit*
+DEFINE_CEPH_FEATURE(60, 1, OSD_RECOVERY_DELETES) // *do not share this bit*
+DEFINE_CEPH_FEATURE(61, 1, CEPHX_V2)             // *do not share this bit*
 
-DEFINE_CEPH_FEATURE(61, 1, RESERVED2)          // unused, but slow down!
 DEFINE_CEPH_FEATURE(62, 1, RESERVED)           // do not use; used as a sentinal
 DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facing
 

@@ -209,7 +209,8 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin
 	 CEPH_FEATURE_SERVER_JEWEL |		\
 	 CEPH_FEATURE_MON_STATEFUL_SUB |	\
 	 CEPH_FEATURE_CRUSH_TUNABLES5 |		\
-	 CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING)
+	 CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING |	\
+	 CEPH_FEATURE_CEPHX_V2)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT   \
 	(CEPH_FEATURE_NOSRCADDR |	 \

88 lines not on this page · raw message

index a3333004fd2b..8458cc5fbce5 100644
@@ -113,6 +113,7 @@ struct bpf_insn_aux_data {
 		struct bpf_map *map_ptr;	/* pointer for call insn into lookup_elem */
 	};
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
+	int sanitize_stack_off; /* stack slot to be cleared */
 	bool seen; /* this insn was processed by the verifier */
 };
 

87 lines not on this page · raw message

index 86ed3dd80fe7..0c3ab2af74d3 100644
@@ -89,6 +89,8 @@ struct tls_context {
 
 	void *priv_ctx;
 
+	u8 tx_conf:2;
+
 	u16 prepend_size;
 	u16 tag_size;
 	u16 overhead_size;

82 lines not on this page · raw message

index 0c3ab2af74d3..604fd982da19 100644
@@ -106,7 +106,6 @@ struct tls_context {
 
 	u16 pending_open_record_frags;
 	int (*push_pending_record)(struct sock *sk, int flags);
-	void (*free_resources)(struct sock *sk);
 
 	void (*sk_write_space)(struct sock *sk);
 	void (*sk_proto_close)(struct sock *sk, long timeout);

@@ -131,6 +130,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tls_sw_sendpage(struct sock *sk, struct page *page,
 		    int offset, size_t size, int flags);
 void tls_sw_close(struct sock *sk, long timeout);
+void tls_sw_free_tx_resources(struct sock *sk);
 
 void tls_sk_destruct(struct sock *sk, struct tls_context *ctx);
 void tls_icsk_clean_acked(struct sock *sk);

index 191a8adee3ea..b5f9c578bcf0 100644
@@ -249,6 +249,12 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	void (*sk_proto_close)(struct sock *sk, long timeout);
 
 	lock_sock(sk);
+	sk_proto_close = ctx->sk_proto_close;
+
+	if (ctx->tx_conf == TLS_BASE_TX) {
+		tls_ctx_free(ctx);
+		goto skip_tx_cleanup;
+	}
 
 	if (!tls_complete_pending_work(sk, ctx, 0, &timeo))
 		tls_handle_open_record(sk, 0);

@@ -265,13 +271,16 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 			sg++;
 		}
 	}
-	ctx->free_resources(sk);
+
 	kfree(ctx->rec_seq);
 	kfree(ctx->iv);
 
-	sk_proto_close = ctx->sk_proto_close;
-	tls_ctx_free(ctx);
+	if (ctx->tx_conf == TLS_SW_TX) {
+		tls_sw_free_tx_resources(sk);
+		tls_ctx_free(ctx);
+	}
 
+skip_tx_cleanup:
 	release_sock(sk);
 	sk_proto_close(sk, timeout);
 }

@@ -428,8 +437,6 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 	ctx->sk_write_space = sk->sk_write_space;
 	sk->sk_write_space = tls_write_space;
 
-	ctx->sk_proto_close = sk->sk_prot->close;
-
 	/* currently SW is default, we will have ethtool in future */
 	rc = tls_set_sw_offload(sk, ctx);
 	tx_conf = TLS_SW_TX;

@@ -499,6 +506,7 @@ static int tls_init(struct sock *sk)
 	icsk->icsk_ulp_data = ctx;
 	ctx->setsockopt = sk->sk_prot->setsockopt;
 	ctx->getsockopt = sk->sk_prot->getsockopt;
+	ctx->sk_proto_close = sk->sk_prot->close;
 
 	ctx->tx_conf = TLS_BASE_TX;
 	update_sk_prot(sk, ctx);

@@ -515,11 +523,11 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = {
 static void build_protos(struct proto *prot, struct proto *base)
 {
 	prot[TLS_BASE_TX] = *base;
-	prot[TLS_BASE_TX].setsockopt = tls_setsockopt;
-	prot[TLS_BASE_TX].getsockopt = tls_getsockopt;
+	prot[TLS_BASE_TX].setsockopt	= tls_setsockopt;
+	prot[TLS_BASE_TX].getsockopt	= tls_getsockopt;
+	prot[TLS_BASE_TX].close		= tls_sk_proto_close;
 
 	prot[TLS_SW_TX] = prot[TLS_BASE_TX];
-	prot[TLS_SW_TX].close		= tls_sk_proto_close;
 	prot[TLS_SW_TX].sendmsg		= tls_sw_sendmsg;
 	prot[TLS_SW_TX].sendpage	= tls_sw_sendpage;
 }

index 6ae9ca567d6c..5996fb5756e1 100644
@@ -646,7 +646,7 @@ sendpage_end:
 	return ret;
 }
 
-static void tls_sw_free_resources(struct sock *sk)
+void tls_sw_free_tx_resources(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);

@@ -685,7 +685,6 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx)
 	}
 
 	ctx->priv_ctx = (struct tls_offload_context *)sw_ctx;
-	ctx->free_resources = tls_sw_free_resources;
 
 	crypto_info = &ctx->crypto_send.info;
 	switch (crypto_info->cipher_type) {

index b5f9c578bcf0..f88df514ad5f 100644
@@ -381,7 +381,7 @@ static int tls_getsockopt(struct sock *sk, int level, int optname,
 static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 				unsigned int optlen)
 {
-	struct tls_crypto_info *crypto_info, tmp_crypto_info;
+	struct tls_crypto_info *crypto_info;
 	struct tls_context *ctx = tls_get_ctx(sk);
 	int rc = 0;
 	int tx_conf;

@@ -391,38 +391,33 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 		goto out;
 	}
 
-	rc = copy_from_user(&tmp_crypto_info, optval, sizeof(*crypto_info));
+	crypto_info = &ctx->crypto_send.info;
+	/* Currently we don't support set crypto info more than one time */
+	if (TLS_CRYPTO_INFO_READY(crypto_info)) {
+		rc = -EBUSY;
+		goto out;
+	}
+
+	rc = copy_from_user(crypto_info, optval, sizeof(*crypto_info));
 	if (rc) {
 		rc = -EFAULT;
 		goto out;
 	}
 
 	/* check version */
-	if (tmp_crypto_info.version != TLS_1_2_VERSION) {
+	if (crypto_info->version != TLS_1_2_VERSION) {
 		rc = -ENOTSUPP;
-		goto out;
-	}
-
-	/* get user crypto info */
-	crypto_info = &ctx->crypto_send.info;
-
-	/* Currently we don't support set crypto info more than one time */
-	if (TLS_CRYPTO_INFO_READY(crypto_info)) {
-		rc = -EBUSY;
-		goto out;
+		goto err_crypto_info;
 	}
 
-	switch (tmp_crypto_info.cipher_type) {
+	switch (crypto_info->cipher_type) {
 	case TLS_CIPHER_AES_GCM_128: {
 		if (optlen != sizeof(struct tls12_crypto_info_aes_gcm_128)) {
 			rc = -EINVAL;
 			goto err_crypto_info;
 		}
-		rc = copy_from_user(
-		  crypto_info,
-		  optval,
-		  sizeof(struct tls12_crypto_info_aes_gcm_128));
-
+		rc = copy_from_user(crypto_info + 1, optval + sizeof(*crypto_info),
+				    optlen - sizeof(*crypto_info));
 		if (rc) {
 			rc = -EFAULT;
 			goto err_crypto_info;

index f88df514ad5f..33187e34599b 100644
@@ -429,9 +429,6 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 		goto err_crypto_info;
 	}
 
-	ctx->sk_write_space = sk->sk_write_space;
-	sk->sk_write_space = tls_write_space;
-
 	/* currently SW is default, we will have ethtool in future */
 	rc = tls_set_sw_offload(sk, ctx);
 	tx_conf = TLS_SW_TX;

@@ -440,6 +437,8 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval,
 
 	ctx->tx_conf = tx_conf;
 	update_sk_prot(sk, ctx);
+	ctx->sk_write_space = sk->sk_write_space;
+	sk->sk_write_space = tls_write_space;
 	goto out;
 
 err_crypto_info:

index 33187e34599b..e903bdd39b9f 100644
@@ -46,17 +46,27 @@ MODULE_DESCRIPTION("Transport Layer Security Support");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS_TCP_ULP("tls");
 
+enum {
+	TLSV4,
+	TLSV6,
+	TLS_NUM_PROTS,
+};
+
 enum {
 	TLS_BASE_TX,
 	TLS_SW_TX,
 	TLS_NUM_CONFIG,
 };
 
-static struct proto tls_prots[TLS_NUM_CONFIG];
+static struct proto *saved_tcpv6_prot;
+static DEFINE_MUTEX(tcpv6_prot_mutex);
+static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG];
 
 static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx)
 {
-	sk->sk_prot = &tls_prots[ctx->tx_conf];
+	int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4;
+
+	sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf];
 }
 
 int wait_on_pending_writer(struct sock *sk, long *timeo)

@@ -476,8 +486,21 @@ static int tls_setsockopt(struct sock *sk, int level, int optname,
 	return do_tls_setsockopt(sk, optname, optval, optlen);
 }
 
+static void build_protos(struct proto *prot, struct proto *base)
+{
+	prot[TLS_BASE_TX] = *base;
+	prot[TLS_BASE_TX].setsockopt	= tls_setsockopt;
+	prot[TLS_BASE_TX].getsockopt	= tls_getsockopt;
+	prot[TLS_BASE_TX].close		= tls_sk_proto_close;
+
+	prot[TLS_SW_TX] = prot[TLS_BASE_TX];
+	prot[TLS_SW_TX].sendmsg		= tls_sw_sendmsg;
+	prot[TLS_SW_TX].sendpage	= tls_sw_sendpage;
+}
+
 static int tls_init(struct sock *sk)
 {
+	int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4;
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tls_context *ctx;
 	int rc = 0;

@@ -502,6 +525,17 @@ static int tls_init(struct sock *sk)
 	ctx->getsockopt = sk->sk_prot->getsockopt;
 	ctx->sk_proto_close = sk->sk_prot->close;
 
+	/* Build IPv6 TLS whenever the address of tcpv6_prot changes */
+	if (ip_ver == TLSV6 &&
+	    unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+		mutex_lock(&tcpv6_prot_mutex);
+		if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+			build_protos(tls_prots[TLSV6], sk->sk_prot);
+			smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+		}
+		mutex_unlock(&tcpv6_prot_mutex);
+	}
+
 	ctx->tx_conf = TLS_BASE_TX;
 	update_sk_prot(sk, ctx);
 out:

@@ -514,21 +548,9 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = {
 	.init			= tls_init,
 };
 
-static void build_protos(struct proto *prot, struct proto *base)
-{
-	prot[TLS_BASE_TX] = *base;
-	prot[TLS_BASE_TX].setsockopt	= tls_setsockopt;
-	prot[TLS_BASE_TX].getsockopt	= tls_getsockopt;
-	prot[TLS_BASE_TX].close		= tls_sk_proto_close;
-
-	prot[TLS_SW_TX] = prot[TLS_BASE_TX];
-	prot[TLS_SW_TX].sendmsg		= tls_sw_sendmsg;
-	prot[TLS_SW_TX].sendpage	= tls_sw_sendpage;
-}
-
 static int __init tls_register(void)
 {
-	build_protos(tls_prots, &tcp_prot);
+	build_protos(tls_prots[TLSV4], &tcp_prot);
 
 	tcp_register_ulp(&tcp_tls_ulp_ops);
 

index 5996fb5756e1..d18d4a478e4f 100644
@@ -388,7 +388,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
-	int ret = 0;
+	int ret;
 	int required_size;
 	long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 	bool eor = !(msg->msg_flags & MSG_MORE);

@@ -403,7 +403,8 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 
 	lock_sock(sk);
 
-	if (tls_complete_pending_work(sk, tls_ctx, msg->msg_flags, &timeo))
+	ret = tls_complete_pending_work(sk, tls_ctx, msg->msg_flags, &timeo);
+	if (ret)
 		goto send_end;
 
 	if (unlikely(msg->msg_controllen)) {

@@ -539,7 +540,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
-	int ret = 0;
+	int ret;
 	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 	bool eor;
 	size_t orig_size = size;

@@ -559,7 +560,8 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
-	if (tls_complete_pending_work(sk, tls_ctx, flags, &timeo))
+	ret = tls_complete_pending_work(sk, tls_ctx, flags, &timeo);
+	if (ret)
 		goto sendpage_end;
 
 	/* Call the sk_stream functions to manage the sndbuf mem. */

index ffdd2fa401b1..d63d7c326801 100644
@@ -1380,8 +1380,14 @@ int wmi_set_ie(struct wil6210_priv *wil, u8 type, u16 ie_len, const void *ie)
 	};
 	int rc;
 	u16 len = sizeof(struct wmi_set_appie_cmd) + ie_len;
-	struct wmi_set_appie_cmd *cmd = kzalloc(len, GFP_KERNEL);
+	struct wmi_set_appie_cmd *cmd;
 
+	if (len < ie_len) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	cmd = kzalloc(len, GFP_KERNEL);
 	if (!cmd) {
 		rc = -ENOMEM;
 		goto out;

index a0947f4a3e87..cfd5728e7519 100644
@@ -6353,6 +6353,8 @@ static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info,
 	u16 num_stripes;
 	u16 sub_stripes;
 	u64 type;
+	u64 features;
+	bool mixed = false;
 
 	length = btrfs_chunk_length(leaf, chunk);
 	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);

@@ -6391,6 +6393,32 @@ static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info,
 			  btrfs_chunk_type(leaf, chunk));
 		return -EIO;
 	}
+
+	if ((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0) {
+		btrfs_err(fs_info, "missing chunk type flag: 0x%llx", type);
+		return -EIO;
+	}
+
+	if ((type & BTRFS_BLOCK_GROUP_SYSTEM) &&
+	    (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA))) {
+		btrfs_err(fs_info,
+			"system chunk with data or metadata type: 0x%llx", type);
+		return -EIO;
+	}
+
+	features = btrfs_super_incompat_flags(fs_info->super_copy);
+	if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
+		mixed = true;
+
+	if (!mixed) {
+		if ((type & BTRFS_BLOCK_GROUP_METADATA) &&
+		    (type & BTRFS_BLOCK_GROUP_DATA)) {
+			btrfs_err(fs_info,
+			"mixed chunk type in non-mixed mode: 0x%llx", type);
+			return -EIO;
+		}
+	}
+
 	if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) ||
 	    (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes < 1) ||
 	    (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) ||

index 2cb3569ac548..fdc42eddccc2 100644
@@ -10092,6 +10092,62 @@ btrfs_create_block_group_cache(struct btrfs_fs_info *fs_info,
 	return cache;
 }
 
+
+/*
+ * Iterate all chunks and verify that each of them has the corresponding block
+ * group
+ */
+static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
+	struct extent_map *em;
+	struct btrfs_block_group_cache *bg;
+	u64 start = 0;
+	int ret = 0;
+
+	while (1) {
+		read_lock(&map_tree->map_tree.lock);
+		/*
+		 * lookup_extent_mapping will return the first extent map
+		 * intersecting the range, so setting @len to 1 is enough to
+		 * get the first chunk.
+		 */
+		em = lookup_extent_mapping(&map_tree->map_tree, start, 1);
+		read_unlock(&map_tree->map_tree.lock);
+		if (!em)
+			break;
+
+		bg = btrfs_lookup_block_group(fs_info, em->start);
+		if (!bg) {
+			btrfs_err(fs_info,
+	"chunk start=%llu len=%llu doesn't have corresponding block group",
+				     em->start, em->len);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			break;
+		}
+		if (bg->key.objectid != em->start ||
+		    bg->key.offset != em->len ||
+		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
+		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+			btrfs_err(fs_info,
+"chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
+				em->start, em->len,
+				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
+				bg->key.objectid, bg->key.offset,
+				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			btrfs_put_block_group(bg);
+			break;
+		}
+		start = em->start + em->len;
+		free_extent_map(em);
+		btrfs_put_block_group(bg);
+	}
+	return ret;
+}
+
 int btrfs_read_block_groups(struct btrfs_fs_info *info)
 {
 	struct btrfs_path *path;

@@ -10264,7 +10320,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 	}
 
 	init_global_block_rsv(info);
-	ret = 0;
+	ret = check_chunk_block_group_mappings(info);
 error:
 	btrfs_free_path(path);
 	return ret;

index 0e67cee73c53..4a1e63df1183 100644
@@ -554,8 +554,9 @@ static noinline int check_leaf(struct btrfs_root *root,
 			       struct extent_buffer *leaf)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
+	/* No valid key type is 0, so all key should be larger than this key */
+	struct btrfs_key prev_key = {0, 0, 0};
 	struct btrfs_key key;
-	struct btrfs_key leaf_key;
 	u32 nritems = btrfs_header_nritems(leaf);
 	int slot;
 

@@ -588,7 +589,7 @@ static noinline int check_leaf(struct btrfs_root *root,
 				CORRUPT("non-root leaf's nritems is 0",
 					leaf, check_root, 0);
 				free_extent_buffer(eb);
-				return -EIO;
+				return -EUCLEAN;
 			}
 			free_extent_buffer(eb);
 		}

@@ -598,28 +599,23 @@ static noinline int check_leaf(struct btrfs_root *root,
 	if (nritems == 0)
 		return 0;
 
-	/* Check the 0 item */
-	if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
-	    BTRFS_LEAF_DATA_SIZE(fs_info)) {
-		CORRUPT("invalid item offset size pair", leaf, root, 0);
-		return -EIO;
-	}
-
 	/*
-	 * Check to make sure each items keys are in the correct order and their
-	 * offsets make sense.  We only have to loop through nritems-1 because
-	 * we check the current slot against the next slot, which verifies the
-	 * next slot's offset+size makes sense and that the current's slot
-	 * offset is correct.
+	 * Check the following things to make sure this is a good leaf, and
+	 * leaf users won't need to bother with similar sanity checks:
+	 *
+	 * 1) key order
+	 * 2) item offset and size
+	 *    No overlap, no hole, all inside the leaf.
 	 */
-	for (slot = 0; slot < nritems - 1; slot++) {
-		btrfs_item_key_to_cpu(leaf, &leaf_key, slot);
-		btrfs_item_key_to_cpu(leaf, &key, slot + 1);
+	for (slot = 0; slot < nritems; slot++) {
+		u32 item_end_expected;
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
 
 		/* Make sure the keys are in the right order */
-		if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) {
+		if (btrfs_comp_cpu_keys(&prev_key, &key) >= 0) {
 			CORRUPT("bad key order", leaf, root, slot);
-			return -EIO;
+			return -EUCLEAN;
 		}
 
 		/*

@@ -627,10 +623,14 @@ static noinline int check_leaf(struct btrfs_root *root,
 		 * item data starts at the end of the leaf and grows towards the
 		 * front.
 		 */
-		if (btrfs_item_offset_nr(leaf, slot) !=
-			btrfs_item_end_nr(leaf, slot + 1)) {
+		if (slot == 0)
+			item_end_expected = BTRFS_LEAF_DATA_SIZE(fs_info);
+		else
+			item_end_expected = btrfs_item_offset_nr(leaf,
+								 slot - 1);
+		if (btrfs_item_end_nr(leaf, slot) != item_end_expected) {
 			CORRUPT("slot offset bad", leaf, root, slot);
-			return -EIO;
+			return -EUCLEAN;
 		}
 
 		/*

@@ -641,8 +641,12 @@ static noinline int check_leaf(struct btrfs_root *root,
 		if (btrfs_item_end_nr(leaf, slot) >
 		    BTRFS_LEAF_DATA_SIZE(fs_info)) {
 			CORRUPT("slot end outside of leaf", leaf, root, slot);
-			return -EIO;
+			return -EUCLEAN;
 		}
+
+		prev_key.objectid = key.objectid;
+		prev_key.type = key.type;
+		prev_key.offset = key.offset;
 	}
 
 	return 0;

index 4a1e63df1183..da7b2039e4cb 100644
@@ -644,6 +644,13 @@ static noinline int check_leaf(struct btrfs_root *root,
 			return -EUCLEAN;
 		}
 
+		/* Also check if the item pointer overlaps with btrfs item. */
+		if (btrfs_item_nr_offset(slot) + sizeof(struct btrfs_item) >
+		    btrfs_item_ptr_offset(leaf, slot)) {
+			CORRUPT("slot overlap with its data", leaf, root, slot);
+			return -EUCLEAN;
+		}
+
 		prev_key.objectid = key.objectid;
 		prev_key.type = key.type;
 		prev_key.offset = key.offset;

index da7b2039e4cb..ab8925b2efd1 100644
@@ -550,6 +550,100 @@ static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
 		   btrfs_header_level(eb) == 0 ? "leaf" : "node",	\
 		   reason, btrfs_header_bytenr(eb), root->objectid, slot)
 
+static int check_extent_data_item(struct btrfs_root *root,
+				  struct extent_buffer *leaf,
+				  struct btrfs_key *key, int slot)
+{
+	struct btrfs_file_extent_item *fi;
+	u32 sectorsize = root->fs_info->sectorsize;
+	u32 item_size = btrfs_item_size_nr(leaf, slot);
+
+	if (!IS_ALIGNED(key->offset, sectorsize)) {
+		CORRUPT("unaligned key offset for file extent",
+			leaf, root, slot);
+		return -EUCLEAN;
+	}
+
+	fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+
+	if (btrfs_file_extent_type(leaf, fi) > BTRFS_FILE_EXTENT_TYPES) {
+		CORRUPT("invalid file extent type", leaf, root, slot);
+		return -EUCLEAN;
+	}
+
+	/*
+	 * Support for new compression/encrption must introduce incompat flag,
+	 * and must be caught in open_ctree().
+	 */
+	if (btrfs_file_extent_compression(leaf, fi) > BTRFS_COMPRESS_TYPES) {
+		CORRUPT("invalid file extent compression", leaf, root, slot);
+		return -EUCLEAN;
+	}
+	if (btrfs_file_extent_encryption(leaf, fi)) {
+		CORRUPT("invalid file extent encryption", leaf, root, slot);
+		return -EUCLEAN;
+	}
+	if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) {
+		/* Inline extent must have 0 as key offset */
+		if (key->offset) {
+			CORRUPT("inline extent has non-zero key offset",
+				leaf, root, slot);
+			return -EUCLEAN;
+		}
+
+		/* Compressed inline extent has no on-disk size, skip it */
+		if (btrfs_file_extent_compression(leaf, fi) !=
+		    BTRFS_COMPRESS_NONE)
+			return 0;
+
+		/* Uncompressed inline extent size must match item size */
+		if (item_size != BTRFS_FILE_EXTENT_INLINE_DATA_START +
+		    btrfs_file_extent_ram_bytes(leaf, fi)) {
+			CORRUPT("plaintext inline extent has invalid size",
+				leaf, root, slot);
+			return -EUCLEAN;
+		}
+		return 0;
+	}
+
+	/* Regular or preallocated extent has fixed item size */
+	if (item_size != sizeof(*fi)) {
+		CORRUPT(
+		"regluar or preallocated extent data item size is invalid",
+			leaf, root, slot);
+		return -EUCLEAN;
+	}
+	if (!IS_ALIGNED(btrfs_file_extent_ram_bytes(leaf, fi), sectorsize) ||
+	    !IS_ALIGNED(btrfs_file_extent_disk_bytenr(leaf, fi), sectorsize) ||
+	    !IS_ALIGNED(btrfs_file_extent_disk_num_bytes(leaf, fi), sectorsize) ||
+	    !IS_ALIGNED(btrfs_file_extent_offset(leaf, fi), sectorsize) ||
+	    !IS_ALIGNED(btrfs_file_extent_num_bytes(leaf, fi), sectorsize)) {
+		CORRUPT(
+		"regular or preallocated extent data item has unaligned value",
+			leaf, root, slot);
+		return -EUCLEAN;
+	}
+
+	return 0;
+}
+
+/*
+ * Common point to switch the item-specific validation.
+ */
+static int check_leaf_item(struct btrfs_root *root,
+			   struct extent_buffer *leaf,
+			   struct btrfs_key *key, int slot)
+{
+	int ret = 0;
+
+	switch (key->type) {
+	case BTRFS_EXTENT_DATA_KEY:
+		ret = check_extent_data_item(root, leaf, key, slot);
+		break;
+	}
+	return ret;
+}
+
 static noinline int check_leaf(struct btrfs_root *root,
 			       struct extent_buffer *leaf)
 {

@@ -606,9 +700,13 @@ static noinline int check_leaf(struct btrfs_root *root,
 	 * 1) key order
 	 * 2) item offset and size
 	 *    No overlap, no hole, all inside the leaf.
+	 * 3) item content
+	 *    If possible, do comprehensive sanity check.
+	 *    NOTE: All checks must only rely on the item data itself.
 	 */
 	for (slot = 0; slot < nritems; slot++) {
 		u32 item_end_expected;
+		int ret;
 
 		btrfs_item_key_to_cpu(leaf, &key, slot);
 

@@ -651,6 +749,11 @@ static noinline int check_leaf(struct btrfs_root *root,
 			return -EUCLEAN;
 		}
 
+		/* Check if the item size and content meet other criteria */
+		ret = check_leaf_item(root, leaf, &key, slot);
+		if (ret < 0)
+			return ret;
+
 		prev_key.objectid = key.objectid;
 		prev_key.type = key.type;
 		prev_key.offset = key.offset;

index 7115838fbf2a..38ab0e06259a 100644
@@ -734,6 +734,7 @@ struct btrfs_balance_item {
 #define BTRFS_FILE_EXTENT_INLINE 0
 #define BTRFS_FILE_EXTENT_REG 1
 #define BTRFS_FILE_EXTENT_PREALLOC 2
+#define BTRFS_FILE_EXTENT_TYPES	2
 
 struct btrfs_file_extent_item {
 	/*

index ab8925b2efd1..53841d773a40 100644
@@ -627,6 +627,27 @@ static int check_extent_data_item(struct btrfs_root *root,
 	return 0;
 }
 
+static int check_csum_item(struct btrfs_root *root, struct extent_buffer *leaf,
+			   struct btrfs_key *key, int slot)
+{
+	u32 sectorsize = root->fs_info->sectorsize;
+	u32 csumsize = btrfs_super_csum_size(root->fs_info->super_copy);
+
+	if (key->objectid != BTRFS_EXTENT_CSUM_OBJECTID) {
+		CORRUPT("invalid objectid for csum item", leaf, root, slot);
+		return -EUCLEAN;
+	}
+	if (!IS_ALIGNED(key->offset, sectorsize)) {
+		CORRUPT("unaligned key offset for csum item", leaf, root, slot);
+		return -EUCLEAN;
+	}
+	if (!IS_ALIGNED(btrfs_item_size_nr(leaf, slot), csumsize)) {
+		CORRUPT("unaligned csum item size", leaf, root, slot);
+		return -EUCLEAN;
+	}
+	return 0;
+}
+
 /*
  * Common point to switch the item-specific validation.
  */

@@ -640,6 +661,9 @@ static int check_leaf_item(struct btrfs_root *root,
 	case BTRFS_EXTENT_DATA_KEY:
 		ret = check_extent_data_item(root, leaf, key, slot);
 		break;
+	case BTRFS_EXTENT_CSUM_KEY:
+		ret = check_csum_item(root, leaf, key, slot);
+		break;
 	}
 	return ret;
 }

313 lines not on this page · raw message

309 lines not on this page · raw message

new file mode 100644
index 000000000000..96c486e95d70
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) Qu Wenruo 2017.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program.
+ */
+
+#ifndef __BTRFS_TREE_CHECKER__
+#define __BTRFS_TREE_CHECKER__
+
+#include "ctree.h"
+#include "extent_io.h"
+
+int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf);
+int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node);
+
+#endif

index 56e25a630103..5acdf3355a3f 100644
@@ -37,6 +37,46 @@
 		   btrfs_header_level(eb) == 0 ? "leaf" : "node",	\
 		   reason, btrfs_header_bytenr(eb), root->objectid, slot)
 
+/*
+ * Error message should follow the following format:
+ * corrupt <type>: <identifier>, <reason>[, <bad_value>]
+ *
+ * @type:	leaf or node
+ * @identifier:	the necessary info to locate the leaf/node.
+ * 		It's recommened to decode key.objecitd/offset if it's
+ * 		meaningful.
+ * @reason:	describe the error
+ * @bad_value:	optional, it's recommened to output bad value and its
+ *		expected value (range).
+ *
+ * Since comma is used to separate the components, only space is allowed
+ * inside each component.
+ */
+
+/*
+ * Append generic "corrupt leaf/node root=%llu block=%llu slot=%d: " to @fmt.
+ * Allows callers to customize the output.
+ */
+__printf(4, 5)
+static void generic_err(const struct btrfs_root *root,
+			const struct extent_buffer *eb, int slot,
+			const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(root->fs_info,
+		"corrupt %s: root=%llu block=%llu slot=%d, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node",
+		root->objectid, btrfs_header_bytenr(eb), slot, &vaf);
+	va_end(args);
+}
+
 static int check_extent_data_item(struct btrfs_root *root,
 				  struct extent_buffer *leaf,
 				  struct btrfs_key *key, int slot)

@@ -282,9 +322,11 @@ int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node)
 
 	if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(root->fs_info)) {
 		btrfs_crit(root->fs_info,
-			   "corrupt node: block %llu root %llu nritems %lu",
-			   node->start, root->objectid, nr);
-		return -EIO;
+"corrupt node: root=%llu block=%llu, nritems too %s, have %lu expect range [1,%u]",
+			   root->objectid, node->start,
+			   nr == 0 ? "small" : "large", nr,
+			   BTRFS_NODEPTRS_PER_BLOCK(root->fs_info));
+		return -EUCLEAN;
 	}
 
 	for (slot = 0; slot < nr - 1; slot++) {

@@ -293,14 +335,26 @@ int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node)
 		btrfs_node_key_to_cpu(node, &next_key, slot + 1);
 
 		if (!bytenr) {
-			CORRUPT("invalid item slot", node, root, slot);
-			ret = -EIO;
+			generic_err(root, node, slot,
+				"invalid NULL node pointer");
+			ret = -EUCLEAN;
+			goto out;
+		}
+		if (!IS_ALIGNED(bytenr, root->fs_info->sectorsize)) {
+			generic_err(root, node, slot,
+			"unaligned pointer, have %llu should be aligned to %u",
+				bytenr, root->fs_info->sectorsize);
+			ret = -EUCLEAN;
 			goto out;
 		}
 
 		if (btrfs_comp_cpu_keys(&key, &next_key) >= 0) {
-			CORRUPT("bad key order", node, root, slot);
-			ret = -EIO;
+			generic_err(root, node, slot,
+	"bad key order, current (%llu %u %llu) next (%llu %u %llu)",
+				key.objectid, key.type, key.offset,
+				next_key.objectid, next_key.type,
+				next_key.offset);
+			ret = -EUCLEAN;
 			goto out;
 		}
 	}

index 2df5e906db08..e42673477c25 100644
@@ -610,7 +610,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	 * that we don't try and read the other copies of this block, just
 	 * return -EIO.
 	 */
-	if (found_level == 0 && btrfs_check_leaf(root, eb)) {
+	if (found_level == 0 && btrfs_check_leaf_full(root, eb)) {
 		set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
 		ret = -EIO;
 	}

@@ -3870,7 +3870,13 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 					 buf->len,
 					 fs_info->dirty_metadata_batch);
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
-	if (btrfs_header_level(buf) == 0 && btrfs_check_leaf(root, buf)) {
+	/*
+	 * Since btrfs_mark_buffer_dirty() can be called with item pointer set
+	 * but item data not updated.
+	 * So here we should only check item pointers, not item data.
+	 */
+	if (btrfs_header_level(buf) == 0 &&
+	    btrfs_check_leaf_relaxed(root, buf)) {
 		btrfs_print_leaf(buf);
 		ASSERT(0);
 	}

index 5acdf3355a3f..ff4fa8f905d3 100644
@@ -195,7 +195,8 @@ static int check_leaf_item(struct btrfs_root *root,
 	return ret;
 }
 
-int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf)
+static int check_leaf(struct btrfs_root *root, struct extent_buffer *leaf,
+		      bool check_item_data)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	/* No valid key type is 0, so all key should be larger than this key */

@@ -299,10 +300,15 @@ int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf)
 			return -EUCLEAN;
 		}
 
-		/* Check if the item size and content meet other criteria */
-		ret = check_leaf_item(root, leaf, &key, slot);
-		if (ret < 0)
-			return ret;
+		if (check_item_data) {
+			/*
+			 * Check if the item size and content meet other
+			 * criteria
+			 */
+			ret = check_leaf_item(root, leaf, &key, slot);
+			if (ret < 0)
+				return ret;
+		}
 
 		prev_key.objectid = key.objectid;
 		prev_key.type = key.type;

@@ -312,6 +318,17 @@ int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf)
 	return 0;
 }
 
+int btrfs_check_leaf_full(struct btrfs_root *root, struct extent_buffer *leaf)
+{
+	return check_leaf(root, leaf, true);
+}
+
+int btrfs_check_leaf_relaxed(struct btrfs_root *root,
+			     struct extent_buffer *leaf)
+{
+	return check_leaf(root, leaf, false);
+}
+
 int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node)
 {
 	unsigned long nr = btrfs_header_nritems(node);

index 96c486e95d70..3d53e8d6fda0 100644
@@ -20,7 +20,19 @@
 #include "ctree.h"
 #include "extent_io.h"
 
-int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf);
+/*
+ * Comprehensive leaf checker.
+ * Will check not only the item pointers, but also every possible member
+ * in item data.
+ */
+int btrfs_check_leaf_full(struct btrfs_root *root, struct extent_buffer *leaf);
+
+/*
+ * Less strict leaf checker.
+ * Will only check item pointers, not reading item data.
+ */
+int btrfs_check_leaf_relaxed(struct btrfs_root *root,
+			     struct extent_buffer *leaf);
 int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node);
 
 #endif

index ff4fa8f905d3..b32df86de9bf 100644
@@ -30,6 +30,7 @@
 #include "tree-checker.h"
 #include "disk-io.h"
 #include "compression.h"
+#include "hash.h"
 
 #define CORRUPT(reason, eb, root, slot)					\
 	btrfs_crit(root->fs_info,					\

@@ -175,6 +176,141 @@ static int check_csum_item(struct btrfs_root *root, struct extent_buffer *leaf,
 	return 0;
 }
 
+/*
+ * Customized reported for dir_item, only important new info is key->objectid,
+ * which represents inode number
+ */
+__printf(4, 5)
+static void dir_item_err(const struct btrfs_root *root,
+			 const struct extent_buffer *eb, int slot,
+			 const char *fmt, ...)
+{
+	struct btrfs_key key;
+	struct va_format vaf;
+	va_list args;
+
+	btrfs_item_key_to_cpu(eb, &key, slot);
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(root->fs_info,
+	"corrupt %s: root=%llu block=%llu slot=%d ino=%llu, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node", root->objectid,
+		btrfs_header_bytenr(eb), slot, key.objectid, &vaf);
+	va_end(args);
+}
+
+static int check_dir_item(struct btrfs_root *root,
+			  struct extent_buffer *leaf,
+			  struct btrfs_key *key, int slot)
+{
+	struct btrfs_dir_item *di;
+	u32 item_size = btrfs_item_size_nr(leaf, slot);
+	u32 cur = 0;
+
+	di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
+	while (cur < item_size) {
+		char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
+		u32 name_len;
+		u32 data_len;
+		u32 max_name_len;
+		u32 total_size;
+		u32 name_hash;
+		u8 dir_type;
+
+		/* header itself should not cross item boundary */
+		if (cur + sizeof(*di) > item_size) {
+			dir_item_err(root, leaf, slot,
+		"dir item header crosses item boundary, have %lu boundary %u",
+				cur + sizeof(*di), item_size);
+			return -EUCLEAN;
+		}
+
+		/* dir type check */
+		dir_type = btrfs_dir_type(leaf, di);
+		if (dir_type >= BTRFS_FT_MAX) {
+			dir_item_err(root, leaf, slot,
+			"invalid dir item type, have %u expect [0, %u)",
+				dir_type, BTRFS_FT_MAX);
+			return -EUCLEAN;
+		}
+
+		if (key->type == BTRFS_XATTR_ITEM_KEY &&
+		    dir_type != BTRFS_FT_XATTR) {
+			dir_item_err(root, leaf, slot,
+		"invalid dir item type for XATTR key, have %u expect %u",
+				dir_type, BTRFS_FT_XATTR);
+			return -EUCLEAN;
+		}
+		if (dir_type == BTRFS_FT_XATTR &&
+		    key->type != BTRFS_XATTR_ITEM_KEY) {
+			dir_item_err(root, leaf, slot,
+			"xattr dir type found for non-XATTR key");
+			return -EUCLEAN;
+		}
+		if (dir_type == BTRFS_FT_XATTR)
+			max_name_len = XATTR_NAME_MAX;
+		else
+			max_name_len = BTRFS_NAME_LEN;
+
+		/* Name/data length check */
+		name_len = btrfs_dir_name_len(leaf, di);
+		data_len = btrfs_dir_data_len(leaf, di);
+		if (name_len > max_name_len) {
+			dir_item_err(root, leaf, slot,
+			"dir item name len too long, have %u max %u",
+				name_len, max_name_len);
+			return -EUCLEAN;
+		}
+		if (name_len + data_len > BTRFS_MAX_XATTR_SIZE(root->fs_info)) {
+			dir_item_err(root, leaf, slot,
+			"dir item name and data len too long, have %u max %u",
+				name_len + data_len,
+				BTRFS_MAX_XATTR_SIZE(root->fs_info));
+			return -EUCLEAN;
+		}
+
+		if (data_len && dir_type != BTRFS_FT_XATTR) {
+			dir_item_err(root, leaf, slot,
+			"dir item with invalid data len, have %u expect 0",
+				data_len);
+			return -EUCLEAN;
+		}
+
+		total_size = sizeof(*di) + name_len + data_len;
+
+		/* header and name/data should not cross item boundary */
+		if (cur + total_size > item_size) {
+			dir_item_err(root, leaf, slot,
+		"dir item data crosses item boundary, have %u boundary %u",
+				cur + total_size, item_size);
+			return -EUCLEAN;
+		}
+
+		/*
+		 * Special check for XATTR/DIR_ITEM, as key->offset is name
+		 * hash, should match its name
+		 */
+		if (key->type == BTRFS_DIR_ITEM_KEY ||
+		    key->type == BTRFS_XATTR_ITEM_KEY) {
+			read_extent_buffer(leaf, namebuf,
+					(unsigned long)(di + 1), name_len);
+			name_hash = btrfs_name_hash(namebuf, name_len);
+			if (key->offset != name_hash) {
+				dir_item_err(root, leaf, slot,
+		"name hash mismatch with key, have 0x%016x expect 0x%016llx",
+					name_hash, key->offset);
+				return -EUCLEAN;
+			}
+		}
+		cur += total_size;
+		di = (struct btrfs_dir_item *)((void *)di + total_size);
+	}
+	return 0;
+}
+
 /*
  * Common point to switch the item-specific validation.
  */

@@ -191,6 +327,11 @@ static int check_leaf_item(struct btrfs_root *root,
 	case BTRFS_EXTENT_CSUM_KEY:
 		ret = check_csum_item(root, leaf, key, slot);
 		break;
+	case BTRFS_DIR_ITEM_KEY:
+	case BTRFS_DIR_INDEX_KEY:
+	case BTRFS_XATTR_ITEM_KEY:
+		ret = check_dir_item(root, leaf, key, slot);
+		break;
 	}
 	return ret;
 }

index b32df86de9bf..9376739a4cc8 100644
@@ -223,7 +223,7 @@ static int check_dir_item(struct btrfs_root *root,
 		/* header itself should not cross item boundary */
 		if (cur + sizeof(*di) > item_size) {
 			dir_item_err(root, leaf, slot,
-		"dir item header crosses item boundary, have %lu boundary %u",
+		"dir item header crosses item boundary, have %zu boundary %u",
 				cur + sizeof(*di), item_size);
 			return -EUCLEAN;
 		}

index 9376739a4cc8..f7e7a455b710 100644
@@ -212,7 +212,6 @@ static int check_dir_item(struct btrfs_root *root,
 
 	di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
 	while (cur < item_size) {
-		char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
 		u32 name_len;
 		u32 data_len;
 		u32 max_name_len;

@@ -295,6 +294,8 @@ static int check_dir_item(struct btrfs_root *root,
 		 */
 		if (key->type == BTRFS_DIR_ITEM_KEY ||
 		    key->type == BTRFS_XATTR_ITEM_KEY) {
+			char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
+
 			read_extent_buffer(leaf, namebuf,
 					(unsigned long)(di + 1), name_len);
 			name_hash = btrfs_name_hash(namebuf, name_len);

index f7e7a455b710..cf9b10a07134 100644
@@ -31,6 +31,7 @@
 #include "disk-io.h"
 #include "compression.h"
 #include "hash.h"
+#include "volumes.h"
 
 #define CORRUPT(reason, eb, root, slot)					\
 	btrfs_crit(root->fs_info,					\

@@ -312,6 +313,102 @@ static int check_dir_item(struct btrfs_root *root,
 	return 0;
 }
 
+__printf(4, 5)
+__cold
+static void block_group_err(const struct btrfs_fs_info *fs_info,
+			    const struct extent_buffer *eb, int slot,
+			    const char *fmt, ...)
+{
+	struct btrfs_key key;
+	struct va_format vaf;
+	va_list args;
+
+	btrfs_item_key_to_cpu(eb, &key, slot);
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(fs_info,
+	"corrupt %s: root=%llu block=%llu slot=%d bg_start=%llu bg_len=%llu, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node",
+		btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
+		key.objectid, key.offset, &vaf);
+	va_end(args);
+}
+
+static int check_block_group_item(struct btrfs_fs_info *fs_info,
+				  struct extent_buffer *leaf,
+				  struct btrfs_key *key, int slot)
+{
+	struct btrfs_block_group_item bgi;
+	u32 item_size = btrfs_item_size_nr(leaf, slot);
+	u64 flags;
+	u64 type;
+
+	/*
+	 * Here we don't really care about alignment since extent allocator can
+	 * handle it.  We care more about the size, as if one block group is
+	 * larger than maximum size, it's must be some obvious corruption.
+	 */
+	if (key->offset > BTRFS_MAX_DATA_CHUNK_SIZE || key->offset == 0) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid block group size, have %llu expect (0, %llu]",
+				key->offset, BTRFS_MAX_DATA_CHUNK_SIZE);
+		return -EUCLEAN;
+	}
+
+	if (item_size != sizeof(bgi)) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid item size, have %u expect %zu",
+				item_size, sizeof(bgi));
+		return -EUCLEAN;
+	}
+
+	read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
+			   sizeof(bgi));
+	if (btrfs_block_group_chunk_objectid(&bgi) !=
+	    BTRFS_FIRST_CHUNK_TREE_OBJECTID) {
+		block_group_err(fs_info, leaf, slot,
+		"invalid block group chunk objectid, have %llu expect %llu",
+				btrfs_block_group_chunk_objectid(&bgi),
+				BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+		return -EUCLEAN;
+	}
+
+	if (btrfs_block_group_used(&bgi) > key->offset) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid block group used, have %llu expect [0, %llu)",
+				btrfs_block_group_used(&bgi), key->offset);
+		return -EUCLEAN;
+	}
+
+	flags = btrfs_block_group_flags(&bgi);
+	if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) {
+		block_group_err(fs_info, leaf, slot,
+"invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set",
+			flags & BTRFS_BLOCK_GROUP_PROFILE_MASK,
+			hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK));
+		return -EUCLEAN;
+	}
+
+	type = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
+	if (type != BTRFS_BLOCK_GROUP_DATA &&
+	    type != BTRFS_BLOCK_GROUP_METADATA &&
+	    type != BTRFS_BLOCK_GROUP_SYSTEM &&
+	    type != (BTRFS_BLOCK_GROUP_METADATA |
+			   BTRFS_BLOCK_GROUP_DATA)) {
+		block_group_err(fs_info, leaf, slot,
+"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llu or 0x%llx",
+			type, hweight64(type),
+			BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA,
+			BTRFS_BLOCK_GROUP_SYSTEM,
+			BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA);
+		return -EUCLEAN;
+	}
+	return 0;
+}
+
 /*
  * Common point to switch the item-specific validation.
  */

@@ -333,6 +430,9 @@ static int check_leaf_item(struct btrfs_root *root,
 	case BTRFS_XATTR_ITEM_KEY:
 		ret = check_dir_item(root, leaf, key, slot);
 		break;
+	case BTRFS_BLOCK_GROUP_ITEM_KEY:
+		ret = check_block_group_item(root->fs_info, leaf, key, slot);
+		break;
 	}
 	return ret;
 }

index cfd5728e7519..9663b6aa2a56 100644
@@ -4647,7 +4647,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	if (type & BTRFS_BLOCK_GROUP_DATA) {
 		max_stripe_size = SZ_1G;
-		max_chunk_size = 10 * max_stripe_size;
+		max_chunk_size = BTRFS_MAX_DATA_CHUNK_SIZE;
 		if (!devs_max)
 			devs_max = BTRFS_MAX_DEVS(info->chunk_root);
 	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {

index c5dd48eb7b3d..76fb6e84f201 100644
@@ -24,6 +24,8 @@
 #include <linux/btrfs.h>
 #include "async-thread.h"
 
+#define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)
+
 extern struct mutex uuid_mutex;
 
 #define BTRFS_STRIPE_LEN	SZ_64K

index cf9b10a07134..31756bac75b4 100644
@@ -456,9 +456,22 @@ static int check_leaf(struct btrfs_root *root, struct extent_buffer *leaf,
 	 * skip this check for relocation trees.
 	 */
 	if (nritems == 0 && !btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_RELOC)) {
+		u64 owner = btrfs_header_owner(leaf);
 		struct btrfs_root *check_root;
 
-		key.objectid = btrfs_header_owner(leaf);
+		/* These trees must never be empty */
+		if (owner == BTRFS_ROOT_TREE_OBJECTID ||
+		    owner == BTRFS_CHUNK_TREE_OBJECTID ||
+		    owner == BTRFS_EXTENT_TREE_OBJECTID ||
+		    owner == BTRFS_DEV_TREE_OBJECTID ||
+		    owner == BTRFS_FS_TREE_OBJECTID ||
+		    owner == BTRFS_DATA_RELOC_TREE_OBJECTID) {
+			generic_err(root, leaf, 0,
+			"invalid root, root %llu must never be empty",
+				    owner);
+			return -EUCLEAN;
+		}
+		key.objectid = owner;
 		key.type = BTRFS_ROOT_ITEM_KEY;
 		key.offset = (u64)-1;