Merge branch 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/…

…kernel/git/nvdimm/nvdimm

Pull DAX updates from Dan Williams:
 "The completion of Jan's DAX work for 4.10.

  As I mentioned in the libnvdimm-for-4.10 pull request, these are some
  final fixes for the DAX dirty-cacheline-tracking invalidation work
  that was merged through the -mm, ext4, and xfs trees in -rc1. These
  patches were prepared prior to the merge window, but we waited for
  4.10-rc1 to have a stable merge base after all the prerequisites were
  merged.

  Quoting Jan on the overall changes in these patches:

     "So I'd like all these 6 patches to go for rc2. The first three
      patches fix invalidation of exceptional DAX entries (a bug which
      is there for a long time) - without these patches data loss can
      occur on power failure even though user called fsync(2). The other
      three patches change locking of DAX faults so that ->iomap_begin()
      is called in a more relaxed locking context and we are safe to
      start a transaction there for ext4"

  These have received a build success notification from the kbuild
  robot, and pass the latest libnvdimm unit tests. There have not been
  any -next releases since -rc1, so they have not appeared there"

* 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  ext4: Simplify DAX fault path
  dax: Call ->iomap_begin without entry lock during dax fault
  dax: Finish fault completely when loading holes
  dax: Avoid page invalidation races and unnecessary radix tree traversals
  mm: Invalidate DAX radix tree entries only if appropriate
  ext2: Return BH_New buffers for zeroed blocks

fs/dax.c

@@ -451,33 +451,84 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 		__wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
 }
 
+static int __dax_invalidate_mapping_entry(struct address_space *mapping,
+					  pgoff_t index, bool trunc)
+{
+	int ret = 0;
+	void *entry;
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = get_unlocked_mapping_entry(mapping, index, NULL);
+	if (!entry || !radix_tree_exceptional_entry(entry))
+		goto out;
+	if (!trunc &&
+	    (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+	     radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
+		goto out;
+	radix_tree_delete(page_tree, index);
+	mapping->nrexceptional--;
+	ret = 1;
+out:
+	put_unlocked_mapping_entry(mapping, index, entry);
+	spin_unlock_irq(&mapping->tree_lock);
+	return ret;
+}
 /*
  * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
  * entry to get unlocked before deleting it.
  */
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 {
-	void *entry;
+	int ret = __dax_invalidate_mapping_entry(mapping, index, true);
 
-	spin_lock_irq(&mapping->tree_lock);
-	entry = get_unlocked_mapping_entry(mapping, index, NULL);
 	/*
 	 * This gets called from truncate / punch_hole path. As such, the caller
 	 * must hold locks protecting against concurrent modifications of the
 	 * radix tree (usually fs-private i_mmap_sem for writing). Since the
 	 * caller has seen exceptional entry for this index, we better find it
 	 * at that index as well...
 	 */
-	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry))) {
-		spin_unlock_irq(&mapping->tree_lock);
-		return 0;
-	}
-	radix_tree_delete(&mapping->page_tree, index);
+	WARN_ON_ONCE(!ret);
+	return ret;
+}
+
+/*
+ * Invalidate exceptional DAX entry if easily possible. This handles DAX
+ * entries for invalidate_inode_pages() so we evict the entry only if we can
+ * do so without blocking.
+ */
+int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index)
+{
+	int ret = 0;
+	void *entry, **slot;
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = __radix_tree_lookup(page_tree, index, NULL, &slot);
+	if (!entry || !radix_tree_exceptional_entry(entry) ||
+	    slot_locked(mapping, slot))
+		goto out;
+	if (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
+	    radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
+		goto out;
+	radix_tree_delete(page_tree, index);
 	mapping->nrexceptional--;
+	ret = 1;
+out:
 	spin_unlock_irq(&mapping->tree_lock);
-	dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+	if (ret)
+		dax_wake_mapping_entry_waiter(mapping, index, entry, true);
+	return ret;
+}
 
-	return 1;
+/*
+ * Invalidate exceptional DAX entry if it is clean.
+ */
+int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
+				      pgoff_t index)
+{
+	return __dax_invalidate_mapping_entry(mapping, index, false);
 }
 
 /*
@@ -488,24 +539,34 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
  * otherwise it will simply fall out of the page cache under memory
  * pressure without ever having been dirtied.
  */
-static int dax_load_hole(struct address_space *mapping, void *entry,
+static int dax_load_hole(struct address_space *mapping, void **entry,
 			 struct vm_fault *vmf)
 {
 	struct page *page;
+	int ret;
 
 	/* Hole page already exists? Return it...  */
-	if (!radix_tree_exceptional_entry(entry)) {
-		vmf->page = entry;
-		return VM_FAULT_LOCKED;
+	if (!radix_tree_exceptional_entry(*entry)) {
+		page = *entry;
+		goto out;
 	}
 
 	/* This will replace locked radix tree entry with a hole page */
 	page = find_or_create_page(mapping, vmf->pgoff,
 				   vmf->gfp_mask | __GFP_ZERO);
 	if (!page)
 		return VM_FAULT_OOM;
+ out:
 	vmf->page = page;
-	return VM_FAULT_LOCKED;
+	ret = finish_fault(vmf);
+	vmf->page = NULL;
+	*entry = page;
+	if (!ret) {
+		/* Grab reference for PTE that is now referencing the page */
+		get_page(page);
+		return VM_FAULT_NOPAGE;
+	}
+	return ret;
 }
 
 static int copy_user_dax(struct block_device *bdev, sector_t sector, size_t size,
@@ -934,6 +995,17 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED))
 		return -EIO;
 
+	/*
+	 * Write can allocate block for an area which has a hole page mapped
+	 * into page tables. We have to tear down these mappings so that data
+	 * written by write(2) is visible in mmap.
+	 */
+	if ((iomap->flags & IOMAP_F_NEW) && inode->i_mapping->nrpages) {
+		invalidate_inode_pages2_range(inode->i_mapping,
+					      pos >> PAGE_SHIFT,
+					      (end - 1) >> PAGE_SHIFT);
+	}
+
 	while (pos < end) {
 		unsigned offset = pos & (PAGE_SIZE - 1);
 		struct blk_dax_ctl dax = { 0 };
@@ -992,23 +1064,6 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (iov_iter_rw(iter) == WRITE)
 		flags |= IOMAP_WRITE;
 
-	/*
-	 * Yes, even DAX files can have page cache attached to them:  A zeroed
-	 * page is inserted into the pagecache when we have to serve a write
-	 * fault on a hole.  It should never be dirtied and can simply be
-	 * dropped from the pagecache once we get real data for the page.
-	 *
-	 * XXX: This is racy against mmap, and there's nothing we can do about
-	 * it. We'll eventually need to shift this down even further so that
-	 * we can check if we allocated blocks over a hole first.
-	 */
-	if (mapping->nrpages) {
-		ret = invalidate_inode_pages2_range(mapping,
-				pos >> PAGE_SHIFT,
-				(pos + iov_iter_count(iter) - 1) >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
-	}
-
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
 				iter, dax_iomap_actor);
@@ -1023,6 +1078,15 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 }
 EXPORT_SYMBOL_GPL(dax_iomap_rw);
 
+static int dax_fault_return(int error)
+{
+	if (error == 0)
+		return VM_FAULT_NOPAGE;
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM;
+	return VM_FAULT_SIGBUS;
+}
+
 /**
  * dax_iomap_fault - handle a page fault on a DAX file
  * @vma: The virtual memory area where the fault occurred
@@ -1055,12 +1119,6 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	if (pos >= i_size_read(inode))
 		return VM_FAULT_SIGBUS;
 
-	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
-	if (IS_ERR(entry)) {
-		error = PTR_ERR(entry);
-		goto out;
-	}
-
 	if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
 		flags |= IOMAP_WRITE;
 
@@ -1071,9 +1129,15 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	 */
 	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
 	if (error)
-		goto unlock_entry;
+		return dax_fault_return(error);
 	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
-		error = -EIO;		/* fs corruption? */
+		vmf_ret = dax_fault_return(-EIO);	/* fs corruption? */
+		goto finish_iomap;
+	}
+
+	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
+	if (IS_ERR(entry)) {
+		vmf_ret = dax_fault_return(PTR_ERR(entry));
 		goto finish_iomap;
 	}
 
@@ -1096,13 +1160,13 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		}
 
 		if (error)
-			goto finish_iomap;
+			goto error_unlock_entry;
 
 		__SetPageUptodate(vmf->cow_page);
 		vmf_ret = finish_fault(vmf);
 		if (!vmf_ret)
 			vmf_ret = VM_FAULT_DONE_COW;
-		goto finish_iomap;
+		goto unlock_entry;
 	}
 
 	switch (iomap.type) {
@@ -1114,12 +1178,15 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		}
 		error = dax_insert_mapping(mapping, iomap.bdev, sector,
 				PAGE_SIZE, &entry, vma, vmf);
+		/* -EBUSY is fine, somebody else faulted on the same PTE */
+		if (error == -EBUSY)
+			error = 0;
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (!(vmf->flags & FAULT_FLAG_WRITE)) {
-			vmf_ret = dax_load_hole(mapping, entry, vmf);
-			break;
+			vmf_ret = dax_load_hole(mapping, &entry, vmf);
+			goto unlock_entry;
 		}
 		/*FALLTHRU*/
 	default:
@@ -1128,31 +1195,25 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		break;
 	}
 
+ error_unlock_entry:
+	vmf_ret = dax_fault_return(error) | major;
+ unlock_entry:
+	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
-		if (error || (vmf_ret & VM_FAULT_ERROR)) {
-			/* keep previous error */
-			ops->iomap_end(inode, pos, PAGE_SIZE, 0, flags,
-					&iomap);
-		} else {
-			error = ops->iomap_end(inode, pos, PAGE_SIZE,
-					PAGE_SIZE, flags, &iomap);
-		}
-	}
- unlock_entry:
-	if (vmf_ret != VM_FAULT_LOCKED || error)
-		put_locked_mapping_entry(mapping, vmf->pgoff, entry);
- out:
-	if (error == -ENOMEM)
-		return VM_FAULT_OOM | major;
-	/* -EBUSY is fine, somebody else faulted on the same PTE */
-	if (error < 0 && error != -EBUSY)
-		return VM_FAULT_SIGBUS | major;
-	if (vmf_ret) {
-		WARN_ON_ONCE(error); /* -EBUSY from ops->iomap_end? */
-		return vmf_ret;
+		int copied = PAGE_SIZE;
+
+		if (vmf_ret & VM_FAULT_ERROR)
+			copied = 0;
+		/*
+		 * The fault is done by now and there's no way back (other
+		 * thread may be already happily using PTE we have installed).
+		 * Just ignore error from ->iomap_end since we cannot do much
+		 * with it.
+		 */
+		ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
 	}
-	return VM_FAULT_NOPAGE | major;
+	return vmf_ret;
 }
 EXPORT_SYMBOL_GPL(dax_iomap_fault);
 
@@ -1276,16 +1337,6 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if ((pgoff | PG_PMD_COLOUR) > max_pgoff)
 		goto fallback;
 
-	/*
-	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
-	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
-	 * the tree, for instance), it will return -EEXIST and we just fall
-	 * back to 4k entries.
-	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
-	if (IS_ERR(entry))
-		goto fallback;
-
 	/*
 	 * Note that we don't use iomap_apply here.  We aren't doing I/O, only
 	 * setting up a mapping, so really we're using iomap_begin() as a way
@@ -1294,10 +1345,21 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	pos = (loff_t)pgoff << PAGE_SHIFT;
 	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
 	if (error)
-		goto unlock_entry;
+		goto fallback;
+
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto finish_iomap;
 
+	/*
+	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
+	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
+	 * the tree, for instance), it will return -EEXIST and we just fall
+	 * back to 4k entries.
+	 */
+	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	if (IS_ERR(entry))
+		goto finish_iomap;
+
 	vmf.pgoff = pgoff;
 	vmf.flags = flags;
 	vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
@@ -1310,7 +1372,7 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
-			goto finish_iomap;
+			goto unlock_entry;
 		result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap,
 				&entry);
 		break;
@@ -1319,20 +1381,23 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		break;
 	}
 
+ unlock_entry:
+	put_locked_mapping_entry(mapping, pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
-		if (result == VM_FAULT_FALLBACK) {
-			ops->iomap_end(inode, pos, PMD_SIZE, 0, iomap_flags,
-					&iomap);
-		} else {
-			error = ops->iomap_end(inode, pos, PMD_SIZE, PMD_SIZE,
-					iomap_flags, &iomap);
-			if (error)
-				result = VM_FAULT_FALLBACK;
-		}
+		int copied = PMD_SIZE;
+
+		if (result == VM_FAULT_FALLBACK)
+			copied = 0;
+		/*
+		 * The fault is done by now and there's no way back (other
+		 * thread may be already happily using PMD we have installed).
+		 * Just ignore error from ->iomap_end since we cannot do much
+		 * with it.
+		 */
+		ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
+				&iomap);
 	}
- unlock_entry:
-	put_locked_mapping_entry(mapping, pgoff, entry);
  fallback:
 	if (result == VM_FAULT_FALLBACK) {
 		split_huge_pmd(vma, pmd, address);