Merge tag 'nfs-for-5.11-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Features:

   - NFSv3: Add emulation of lookupp() to improve open_by_filehandle()
     support

   - A series of patches to improve readdir performance, particularly
     with large directories

   - Basic support for using NFS/RDMA with the pNFS files and flexfiles
     drivers

   - Micro-optimisations for RDMA

   - RDMA tracing improvements

  Bugfixes:

   - Fix a long standing bug with xs_read_xdr_buf() when receiving
     partial pages (Dan Aloni)

   - Various fixes for getxattr and listxattr, when used over non-TCP
     transports

   - Fixes for containerised NFS from Sargun Dhillon

   - switch nfsiod to be an UNBOUND workqueue (Neil Brown)

   - READDIR should not ask for security label information if there is
     no LSM policy (Olga Kornievskaia)

   - Avoid using interval-based rebinding with TCP in lockd (Calum
     Mackay)

   - A series of RPC and NFS layer fixes to support the NFSv4.2
     READ_PLUS code

   - A couple of fixes for pnfs/flexfiles read failover

  Cleanups:

   - Various cleanups for the SUNRPC xdr code in conjunction with the
     READ_PLUS fixes"

* tag 'nfs-for-5.11-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (90 commits)
  NFS/pNFS: Fix a typo in ff_layout_resend_pnfs_read()
  pNFS/flexfiles: Avoid spurious layout returns in ff_layout_choose_ds_for_read
  NFSv4/pnfs: Add tracing for the deviceid cache
  fs/lockd: convert comma to semicolon
  NFSv4.2: fix error return on memory allocation failure
  NFSv4.2/pnfs: Don't use READ_PLUS with pNFS yet
  NFSv4.2: Deal with potential READ_PLUS data extent buffer overflow
  NFSv4.2: Don't error when exiting early on a READ_PLUS buffer overflow
  NFSv4.2: Handle hole lengths that exceed the READ_PLUS read buffer
  NFSv4.2: decode_read_plus_hole() needs to check the extent offset
  NFSv4.2: decode_read_plus_data() must skip padding after data segment
  NFSv4.2: Ensure we always reset the result->count in decode_read_plus()
  SUNRPC: When expanding the buffer, we may need grow the sparse pages
  SUNRPC: Cleanup - constify a number of xdr_buf helpers
  SUNRPC: Clean up open coded setting of the xdr_stream 'nwords' field
  SUNRPC: _copy_to/from_pages() now check for zero length
  SUNRPC: Cleanup xdr_shrink_bufhead()
  SUNRPC: Fix xdr_expand_hole()
  SUNRPC: Fixes for xdr_align_data()
  SUNRPC: _shift_data_left/right_pages should check the shift length
  ...

1 files changed, 459 insertions, 260 deletions

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8a24fe20dccfd..ef827ae193d22 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -68,7 +68,7 @@ const struct address_space_operations nfs_dir_aops = {
 	.freepage = nfs_readdir_clear_array,
 };
 
-static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, const struct cred *cred)
+static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir)
 {
 	struct nfs_inode *nfsi = NFS_I(dir);
 	struct nfs_open_dir_context *ctx;
@@ -78,7 +78,6 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir
 		ctx->attr_gencount = nfsi->attr_gencount;
 		ctx->dir_cookie = 0;
 		ctx->dup_cookie = 0;
-		ctx->cred = get_cred(cred);
 		spin_lock(&dir->i_lock);
 		if (list_empty(&nfsi->open_files) &&
 		    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
@@ -96,7 +95,6 @@ static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_cont
 	spin_lock(&dir->i_lock);
 	list_del(&ctx->list);
 	spin_unlock(&dir->i_lock);
-	put_cred(ctx->cred);
 	kfree(ctx);
 }
 
@@ -113,7 +111,7 @@ nfs_opendir(struct inode *inode, struct file *filp)
 
 	nfs_inc_stats(inode, NFSIOS_VFSOPEN);
 
-	ctx = alloc_nfs_open_dir_context(inode, current_cred());
+	ctx = alloc_nfs_open_dir_context(inode);
 	if (IS_ERR(ctx)) {
 		res = PTR_ERR(ctx);
 		goto out;
@@ -133,43 +131,55 @@ nfs_closedir(struct inode *inode, struct file *filp)
 struct nfs_cache_array_entry {
 	u64 cookie;
 	u64 ino;
-	struct qstr string;
+	const char *name;
+	unsigned int name_len;
 	unsigned char d_type;
 };
 
 struct nfs_cache_array {
-	int size;
-	int eof_index;
 	u64 last_cookie;
+	unsigned int size;
+	unsigned char page_full : 1,
+		      page_is_eof : 1,
+		      cookies_are_ordered : 1;
 	struct nfs_cache_array_entry array[];
 };
 
-typedef struct {
+struct nfs_readdir_descriptor {
 	struct file	*file;
 	struct page	*page;
 	struct dir_context *ctx;
-	unsigned long	page_index;
-	u64		*dir_cookie;
+	pgoff_t		page_index;
+	u64		dir_cookie;
 	u64		last_cookie;
+	u64		dup_cookie;
 	loff_t		current_index;
 	loff_t		prev_index;
 
+	__be32		verf[NFS_DIR_VERIFIER_SIZE];
 	unsigned long	dir_verifier;
 	unsigned long	timestamp;
 	unsigned long	gencount;
+	unsigned long	attr_gencount;
 	unsigned int	cache_entry_index;
+	signed char duped;
 	bool plus;
 	bool eof;
-} nfs_readdir_descriptor_t;
+};
 
-static
-void nfs_readdir_init_array(struct page *page)
+static void nfs_readdir_array_init(struct nfs_cache_array *array)
+{
+	memset(array, 0, sizeof(struct nfs_cache_array));
+}
+
+static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie)
 {
 	struct nfs_cache_array *array;
 
 	array = kmap_atomic(page);
-	memset(array, 0, sizeof(struct nfs_cache_array));
-	array->eof_index = -1;
+	nfs_readdir_array_init(array);
+	array->last_cookie = last_cookie;
+	array->cookies_are_ordered = 1;
 	kunmap_atomic(array);
 }
 
@@ -184,61 +194,177 @@ void nfs_readdir_clear_array(struct page *page)
 
 	array = kmap_atomic(page);
 	for (i = 0; i < array->size; i++)
-		kfree(array->array[i].string.name);
-	array->size = 0;
+		kfree(array->array[i].name);
+	nfs_readdir_array_init(array);
 	kunmap_atomic(array);
 }
 
+static struct page *
+nfs_readdir_page_array_alloc(u64 last_cookie, gfp_t gfp_flags)
+{
+	struct page *page = alloc_page(gfp_flags);
+	if (page)
+		nfs_readdir_page_init_array(page, last_cookie);
+	return page;
+}
+
+static void nfs_readdir_page_array_free(struct page *page)
+{
+	if (page) {
+		nfs_readdir_clear_array(page);
+		put_page(page);
+	}
+}
+
+static void nfs_readdir_array_set_eof(struct nfs_cache_array *array)
+{
+	array->page_is_eof = 1;
+	array->page_full = 1;
+}
+
+static bool nfs_readdir_array_is_full(struct nfs_cache_array *array)
+{
+	return array->page_full;
+}
+
 /*
  * the caller is responsible for freeing qstr.name
  * when called by nfs_readdir_add_to_array, the strings will be freed in
  * nfs_clear_readdir_array()
  */
-static
-int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int len)
+static const char *nfs_readdir_copy_name(const char *name, unsigned int len)
 {
-	string->len = len;
-	string->name = kmemdup_nul(name, len, GFP_KERNEL);
-	if (string->name == NULL)
-		return -ENOMEM;
+	const char *ret = kmemdup_nul(name, len, GFP_KERNEL);
+
 	/*
 	 * Avoid a kmemleak false positive. The pointer to the name is stored
 	 * in a page cache page which kmemleak does not scan.
 	 */
-	kmemleak_not_leak(string->name);
-	string->hash = full_name_hash(NULL, name, len);
+	if (ret != NULL)
+		kmemleak_not_leak(ret);
+	return ret;
+}
+
+/*
+ * Check that the next array entry lies entirely within the page bounds
+ */
+static int nfs_readdir_array_can_expand(struct nfs_cache_array *array)
+{
+	struct nfs_cache_array_entry *cache_entry;
+
+	if (array->page_full)
+		return -ENOSPC;
+	cache_entry = &array->array[array->size + 1];
+	if ((char *)cache_entry - (char *)array > PAGE_SIZE) {
+		array->page_full = 1;
+		return -ENOSPC;
+	}
 	return 0;
 }
 
 static
 int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
 {
-	struct nfs_cache_array *array = kmap(page);
+	struct nfs_cache_array *array;
 	struct nfs_cache_array_entry *cache_entry;
+	const char *name;
 	int ret;
 
-	cache_entry = &array->array[array->size];
+	name = nfs_readdir_copy_name(entry->name, entry->len);
+	if (!name)
+		return -ENOMEM;
 
-	/* Check that this entry lies within the page bounds */
-	ret = -ENOSPC;
-	if ((char *)&cache_entry[1] - (char *)page_address(page) > PAGE_SIZE)
+	array = kmap_atomic(page);
+	ret = nfs_readdir_array_can_expand(array);
+	if (ret) {
+		kfree(name);
 		goto out;
+	}
 
+	cache_entry = &array->array[array->size];
 	cache_entry->cookie = entry->prev_cookie;
 	cache_entry->ino = entry->ino;
 	cache_entry->d_type = entry->d_type;
-	ret = nfs_readdir_make_qstr(&cache_entry->string, entry->name, entry->len);
-	if (ret)
-		goto out;
+	cache_entry->name_len = entry->len;
+	cache_entry->name = name;
 	array->last_cookie = entry->cookie;
+	if (array->last_cookie <= cache_entry->cookie)
+		array->cookies_are_ordered = 0;
 	array->size++;
 	if (entry->eof != 0)
-		array->eof_index = array->size;
+		nfs_readdir_array_set_eof(array);
 out:
-	kunmap(page);
+	kunmap_atomic(array);
+	return ret;
+}
+
+static struct page *nfs_readdir_page_get_locked(struct address_space *mapping,
+						pgoff_t index, u64 last_cookie)
+{
+	struct page *page;
+
+	page = grab_cache_page(mapping, index);
+	if (page && !PageUptodate(page)) {
+		nfs_readdir_page_init_array(page, last_cookie);
+		if (invalidate_inode_pages2_range(mapping, index + 1, -1) < 0)
+			nfs_zap_mapping(mapping->host, mapping);
+		SetPageUptodate(page);
+	}
+
+	return page;
+}
+
+static u64 nfs_readdir_page_last_cookie(struct page *page)
+{
+	struct nfs_cache_array *array;
+	u64 ret;
+
+	array = kmap_atomic(page);
+	ret = array->last_cookie;
+	kunmap_atomic(array);
 	return ret;
 }
 
+static bool nfs_readdir_page_needs_filling(struct page *page)
+{
+	struct nfs_cache_array *array;
+	bool ret;
+
+	array = kmap_atomic(page);
+	ret = !nfs_readdir_array_is_full(array);
+	kunmap_atomic(array);
+	return ret;
+}
+
+static void nfs_readdir_page_set_eof(struct page *page)
+{
+	struct nfs_cache_array *array;
+
+	array = kmap_atomic(page);
+	nfs_readdir_array_set_eof(array);
+	kunmap_atomic(array);
+}
+
+static void nfs_readdir_page_unlock_and_put(struct page *page)
+{
+	unlock_page(page);
+	put_page(page);
+}
+
+static struct page *nfs_readdir_page_get_next(struct address_space *mapping,
+					      pgoff_t index, u64 cookie)
+{
+	struct page *page;
+
+	page = nfs_readdir_page_get_locked(mapping, index, cookie);
+	if (page) {
+		if (nfs_readdir_page_last_cookie(page) == cookie)
+			return page;
+		nfs_readdir_page_unlock_and_put(page);
+	}
+	return NULL;
+}
+
 static inline
 int is_32bit_api(void)
 {
@@ -258,8 +384,8 @@ bool nfs_readdir_use_cookie(const struct file *filp)
 	return true;
 }
 
-static
-int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
+static int nfs_readdir_search_for_pos(struct nfs_cache_array *array,
+				      struct nfs_readdir_descriptor *desc)
 {
 	loff_t diff = desc->ctx->pos - desc->current_index;
 	unsigned int index;
@@ -267,13 +393,13 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri
 	if (diff < 0)
 		goto out_eof;
 	if (diff >= array->size) {
-		if (array->eof_index >= 0)
+		if (array->page_is_eof)
 			goto out_eof;
 		return -EAGAIN;
 	}
 
 	index = (unsigned int)diff;
-	*desc->dir_cookie = array->array[index].cookie;
+	desc->dir_cookie = array->array[index].cookie;
 	desc->cache_entry_index = index;
 	return 0;
 out_eof:
@@ -290,41 +416,55 @@ nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi)
 	return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags);
 }
 
-static
-int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
+static bool nfs_readdir_array_cookie_in_range(struct nfs_cache_array *array,
+					      u64 cookie)
+{
+	if (!array->cookies_are_ordered)
+		return true;
+	/* Optimisation for monotonically increasing cookies */
+	if (cookie >= array->last_cookie)
+		return false;
+	if (array->size && cookie < array->array[0].cookie)
+		return false;
+	return true;
+}
+
+static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array,
+					 struct nfs_readdir_descriptor *desc)
 {
 	int i;
 	loff_t new_pos;
 	int status = -EAGAIN;
 
+	if (!nfs_readdir_array_cookie_in_range(array, desc->dir_cookie))
+		goto check_eof;
+
 	for (i = 0; i < array->size; i++) {
-		if (array->array[i].cookie == *desc->dir_cookie) {
+		if (array->array[i].cookie == desc->dir_cookie) {
 			struct nfs_inode *nfsi = NFS_I(file_inode(desc->file));
-			struct nfs_open_dir_context *ctx = desc->file->private_data;
 
 			new_pos = desc->current_index + i;
-			if (ctx->attr_gencount != nfsi->attr_gencount ||
+			if (desc->attr_gencount != nfsi->attr_gencount ||
 			    !nfs_readdir_inode_mapping_valid(nfsi)) {
-				ctx->duped = 0;
-				ctx->attr_gencount = nfsi->attr_gencount;
+				desc->duped = 0;
+				desc->attr_gencount = nfsi->attr_gencount;
 			} else if (new_pos < desc->prev_index) {
-				if (ctx->duped > 0
-				    && ctx->dup_cookie == *desc->dir_cookie) {
+				if (desc->duped > 0
+				    && desc->dup_cookie == desc->dir_cookie) {
 					if (printk_ratelimit()) {
 						pr_notice("NFS: directory %pD2 contains a readdir loop."
 								"Please contact your server vendor.  "
-								"The file: %.*s has duplicate cookie %llu\n",
-								desc->file, array->array[i].string.len,
-								array->array[i].string.name, *desc->dir_cookie);
+								"The file: %s has duplicate cookie %llu\n",
+								desc->file, array->array[i].name, desc->dir_cookie);
 					}
 					status = -ELOOP;
 					goto out;
 				}
-				ctx->dup_cookie = *desc->dir_cookie;
-				ctx->duped = -1;
+				desc->dup_cookie = desc->dir_cookie;
+				desc->duped = -1;
 			}
 			if (nfs_readdir_use_cookie(desc->file))
-				desc->ctx->pos = *desc->dir_cookie;
+				desc->ctx->pos = desc->dir_cookie;
 			else
 				desc->ctx->pos = new_pos;
 			desc->prev_index = new_pos;
@@ -332,24 +472,24 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
 			return 0;
 		}
 	}
-	if (array->eof_index >= 0) {
+check_eof:
+	if (array->page_is_eof) {
 		status = -EBADCOOKIE;
-		if (*desc->dir_cookie == array->last_cookie)
+		if (desc->dir_cookie == array->last_cookie)
 			desc->eof = true;
 	}
 out:
 	return status;
 }
 
-static
-int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
+static int nfs_readdir_search_array(struct nfs_readdir_descriptor *desc)
 {
 	struct nfs_cache_array *array;
 	int status;
 
-	array = kmap(desc->page);
+	array = kmap_atomic(desc->page);
 
-	if (*desc->dir_cookie == 0)
+	if (desc->dir_cookie == 0)
 		status = nfs_readdir_search_for_pos(array, desc);
 	else
 		status = nfs_readdir_search_for_cookie(array, desc);
@@ -359,17 +499,29 @@ int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
 		desc->current_index += array->size;
 		desc->page_index++;
 	}
-	kunmap(desc->page);
+	kunmap_atomic(array);
 	return status;
 }
 
 /* Fill a page with xdr information before transferring to the cache page */
-static
-int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc,
-			struct nfs_entry *entry, struct file *file, struct inode *inode)
+static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc,
+				  __be32 *verf, u64 cookie,
+				  struct page **pages, size_t bufsize,
+				  __be32 *verf_res)
 {
-	struct nfs_open_dir_context *ctx = file->private_data;
-	const struct cred *cred = ctx->cred;
+	struct inode *inode = file_inode(desc->file);
+	struct nfs_readdir_arg arg = {
+		.dentry = file_dentry(desc->file),
+		.cred = desc->file->f_cred,
+		.verf = verf,
+		.cookie = cookie,
+		.pages = pages,
+		.page_len = bufsize,
+		.plus = desc->plus,
+	};
+	struct nfs_readdir_res res = {
+		.verf = verf_res,
+	};
 	unsigned long	timestamp, gencount;
 	int		error;
 
@@ -377,14 +529,13 @@ int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc,
 	timestamp = jiffies;
 	gencount = nfs_inc_attr_generation_counter();
 	desc->dir_verifier = nfs_save_change_attribute(inode);
-	error = NFS_PROTO(inode)->readdir(file_dentry(file), cred, entry->cookie, pages,
-					  NFS_SERVER(inode)->dtsize, desc->plus);
+	error = NFS_PROTO(inode)->readdir(&arg, &res);
 	if (error < 0) {
 		/* We requested READDIRPLUS, but the server doesn't grok it */
 		if (error == -ENOTSUPP && desc->plus) {
 			NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS;
 			clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
-			desc->plus = false;
+			desc->plus = arg.plus = false;
 			goto again;
 		}
 		goto error;
@@ -395,7 +546,7 @@ error:
 	return error;
 }
 
-static int xdr_decode(nfs_readdir_descriptor_t *desc,
+static int xdr_decode(struct nfs_readdir_descriptor *desc,
 		      struct nfs_entry *entry, struct xdr_stream *xdr)
 {
 	struct inode *inode = file_inode(desc->file);
@@ -557,24 +708,23 @@ out:
 }
 
 /* Perform conversion from xdr to cache array */
-static
-int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry,
-				struct page **xdr_pages, struct page *page, unsigned int buflen)
-{
+static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
+				   struct nfs_entry *entry,
+				   struct page **xdr_pages,
+				   unsigned int buflen,
+				   struct page **arrays,
+				   size_t narrays)
+{
+	struct address_space *mapping = desc->file->f_mapping;
 	struct xdr_stream stream;
 	struct xdr_buf buf;
-	struct page *scratch;
-	struct nfs_cache_array *array;
-	unsigned int count = 0;
+	struct page *scratch, *new, *page = *arrays;
 	int status;
 
 	scratch = alloc_page(GFP_KERNEL);
 	if (scratch == NULL)
 		return -ENOMEM;
 
-	if (buflen == 0)
-		goto out_nopages;
-
 	xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
 	xdr_set_scratch_page(&stream, scratch);
 
@@ -583,209 +733,238 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 			entry->label->len = NFS4_MAXLABELLEN;
 
 		status = xdr_decode(desc, entry, &stream);
-		if (status != 0) {
-			if (status == -EAGAIN)
-				status = 0;
+		if (status != 0)
 			break;
-		}
-
-		count++;
 
 		if (desc->plus)
 			nfs_prime_dcache(file_dentry(desc->file), entry,
 					desc->dir_verifier);
 
 		status = nfs_readdir_add_to_array(entry, page);
-		if (status != 0)
-			break;
-	} while (!entry->eof);
+		if (status != -ENOSPC)
+			continue;
 
-out_nopages:
-	if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) {
-		array = kmap(page);
-		array->eof_index = array->size;
+		if (page->mapping != mapping) {
+			if (!--narrays)
+				break;
+			new = nfs_readdir_page_array_alloc(entry->prev_cookie,
+							   GFP_KERNEL);
+			if (!new)
+				break;
+			arrays++;
+			*arrays = page = new;
+		} else {
+			new = nfs_readdir_page_get_next(mapping,
+							page->index + 1,
+							entry->prev_cookie);
+			if (!new)
+				break;
+			if (page != *arrays)
+				nfs_readdir_page_unlock_and_put(page);
+			page = new;
+		}
+		status = nfs_readdir_add_to_array(entry, page);
+	} while (!status && !entry->eof);
+
+	switch (status) {
+	case -EBADCOOKIE:
+		if (entry->eof) {
+			nfs_readdir_page_set_eof(page);
+			status = 0;
+		}
+		break;
+	case -ENOSPC:
+	case -EAGAIN:
 		status = 0;
-		kunmap(page);
+		break;
 	}
 
+	if (page != *arrays)
+		nfs_readdir_page_unlock_and_put(page);
+
 	put_page(scratch);
 	return status;
 }
 
-static
-void nfs_readdir_free_pages(struct page **pages, unsigned int npages)
+static void nfs_readdir_free_pages(struct page **pages, size_t npages)
 {
-	unsigned int i;
-	for (i = 0; i < npages; i++)
-		put_page(pages[i]);
+	while (npages--)
+		put_page(pages[npages]);
+	kfree(pages);
 }
 
 /*
  * nfs_readdir_alloc_pages() will allocate pages that must be freed with a call
  * to nfs_readdir_free_pages()
  */
-static
-int nfs_readdir_alloc_pages(struct page **pages, unsigned int npages)
+static struct page **nfs_readdir_alloc_pages(size_t npages)
 {
-	unsigned int i;
+	struct page **pages;
+	size_t i;
 
+	pages = kmalloc_array(npages, sizeof(*pages), GFP_KERNEL);
+	if (!pages)
+		return NULL;
 	for (i = 0; i < npages; i++) {
 		struct page *page = alloc_page(GFP_KERNEL);
 		if (page == NULL)
 			goto out_freepages;
 		pages[i] = page;
 	}
-	return 0;
+	return pages;
 
 out_freepages:
 	nfs_readdir_free_pages(pages, i);
-	return -ENOMEM;
+	return NULL;
 }
 
-static
-int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, struct inode *inode)
+static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
+				    __be32 *verf_arg, __be32 *verf_res,
+				    struct page **arrays, size_t narrays)
 {
-	struct page *pages[NFS_MAX_READDIR_PAGES];
-	struct nfs_entry entry;
-	struct file	*file = desc->file;
-	struct nfs_cache_array *array;
+	struct page **pages;
+	struct page *page = *arrays;
+	struct nfs_entry *entry;
+	size_t array_size;
+	struct inode *inode = file_inode(desc->file);
+	size_t dtsize = NFS_SERVER(inode)->dtsize;
 	int status = -ENOMEM;
-	unsigned int array_size = ARRAY_SIZE(pages);
-
-	nfs_readdir_init_array(page);
 
-	entry.prev_cookie = 0;
-	entry.cookie = desc->last_cookie;
-	entry.eof = 0;
-	entry.fh = nfs_alloc_fhandle();
-	entry.fattr = nfs_alloc_fattr();
-	entry.server = NFS_SERVER(inode);
-	if (entry.fh == NULL || entry.fattr == NULL)
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+	entry->cookie = nfs_readdir_page_last_cookie(page);
+	entry->fh = nfs_alloc_fhandle();
+	entry->fattr = nfs_alloc_fattr();
+	entry->server = NFS_SERVER(inode);
+	if (entry->fh == NULL || entry->fattr == NULL)
 		goto out;
 
-	entry.label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT);
-	if (IS_ERR(entry.label)) {
-		status = PTR_ERR(entry.label);
+	entry->label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT);
+	if (IS_ERR(entry->label)) {
+		status = PTR_ERR(entry->label);
 		goto out;
 	}
 
-	array = kmap(page);
+	array_size = (dtsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	pages = nfs_readdir_alloc_pages(array_size);
+	if (!pages)
+		goto out_release_label;
 
-	status = nfs_readdir_alloc_pages(pages, array_size);
-	if (status < 0)
-		goto out_release_array;
 	do {
 		unsigned int pglen;
-		status = nfs_readdir_xdr_filler(pages, desc, &entry, file, inode);
-
+		status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie,
+						pages, dtsize,
+						verf_res);
 		if (status < 0)
 			break;
+
 		pglen = status;
-		status = nfs_readdir_page_filler(desc, &entry, pages, page, pglen);
-		if (status < 0) {
-			if (status == -ENOSPC)
-				status = 0;
+		if (pglen == 0) {
+			nfs_readdir_page_set_eof(page);
 			break;
 		}
-	} while (array->eof_index < 0);
+
+		status = nfs_readdir_page_filler(desc, entry, pages, pglen,
+						 arrays, narrays);
+	} while (!status && nfs_readdir_page_needs_filling(page));
 
 	nfs_readdir_free_pages(pages, array_size);
-out_release_array:
-	kunmap(page);
-	nfs4_label_free(entry.label);
+out_release_label:
+	nfs4_label_free(entry->label);
 out:
-	nfs_free_fattr(entry.fattr);
-	nfs_free_fhandle(entry.fh);
+	nfs_free_fattr(entry->fattr);
+	nfs_free_fhandle(entry->fh);
+	kfree(entry);
 	return status;
 }
 
-/*
- * Now we cache directories properly, by converting xdr information
- * to an array that can be used for lookups later.  This results in
- * fewer cache pages, since we can store more information on each page.
- * We only need to convert from xdr once so future lookups are much simpler
- */
-static
-int nfs_readdir_filler(void *data, struct page* page)
+static void nfs_readdir_page_put(struct nfs_readdir_descriptor *desc)
 {
-	nfs_readdir_descriptor_t *desc = data;
-	struct inode	*inode = file_inode(desc->file);
-	int ret;
-
-	ret = nfs_readdir_xdr_to_array(desc, page, inode);
-	if (ret < 0)
-		goto error;
-	SetPageUptodate(page);
-
-	if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) {
-		/* Should never happen */
-		nfs_zap_mapping(inode, inode->i_mapping);
-	}
-	unlock_page(page);
-	return 0;
- error:
-	nfs_readdir_clear_array(page);
-	unlock_page(page);
-	return ret;
+	put_page(desc->page);
+	desc->page = NULL;
 }
 
-static
-void cache_page_release(nfs_readdir_descriptor_t *desc)
+static void
+nfs_readdir_page_unlock_and_put_cached(struct nfs_readdir_descriptor *desc)
 {
-	put_page(desc->page);
-	desc->page = NULL;
+	unlock_page(desc->page);
+	nfs_readdir_page_put(desc);
 }
 
-static
-struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
+static struct page *
+nfs_readdir_page_get_cached(struct nfs_readdir_descriptor *desc)
 {
-	return read_cache_page(desc->file->f_mapping, desc->page_index,
-			nfs_readdir_filler, desc);
+	return nfs_readdir_page_get_locked(desc->file->f_mapping,
+					   desc->page_index,
+					   desc->last_cookie);
 }
 
 /*
  * Returns 0 if desc->dir_cookie was found on page desc->page_index
  * and locks the page to prevent removal from the page cache.
  */
-static
-int find_and_lock_cache_page(nfs_readdir_descriptor_t *desc)
+static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 {
 	struct inode *inode = file_inode(desc->file);
 	struct nfs_inode *nfsi = NFS_I(inode);
+	__be32 verf[NFS_DIR_VERIFIER_SIZE];
 	int res;
 
-	desc->page = get_cache_page(desc);
-	if (IS_ERR(desc->page))
-		return PTR_ERR(desc->page);
-	res = lock_page_killable(desc->page);
-	if (res != 0)
-		goto error;
-	res = -EAGAIN;
-	if (desc->page->mapping != NULL) {
-		res = nfs_readdir_search_array(desc);
-		if (res == 0) {
-			nfsi->page_index = desc->page_index;
-			return 0;
+	desc->page = nfs_readdir_page_get_cached(desc);
+	if (!desc->page)
+		return -ENOMEM;
+	if (nfs_readdir_page_needs_filling(desc->page)) {
+		res = nfs_readdir_xdr_to_array(desc, nfsi->cookieverf, verf,
+					       &desc->page, 1);
+		if (res < 0) {
+			nfs_readdir_page_unlock_and_put_cached(desc);
+			if (res == -EBADCOOKIE || res == -ENOTSYNC) {
+				invalidate_inode_pages2(desc->file->f_mapping);
+				desc->page_index = 0;
+				return -EAGAIN;
+			}
+			return res;
 		}
+		memcpy(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf));
 	}
-	unlock_page(desc->page);
-error:
-	cache_page_release(desc);
+	res = nfs_readdir_search_array(desc);
+	if (res == 0) {
+		nfsi->page_index = desc->page_index;
+		return 0;
+	}
+	nfs_readdir_page_unlock_and_put_cached(desc);
 	return res;
 }
 
+static bool nfs_readdir_dont_search_cache(struct nfs_readdir_descriptor *desc)
+{
+	struct address_space *mapping = desc->file->f_mapping;
+	struct inode *dir = file_inode(desc->file);
+	unsigned int dtsize = NFS_SERVER(dir)->dtsize;
+	loff_t size = i_size_read(dir);
+
+	/*
+	 * Default to uncached readdir if the page cache is empty, and
+	 * we're looking for a non-zero cookie in a large directory.
+	 */
+	return desc->dir_cookie != 0 && mapping->nrpages == 0 && size > dtsize;
+}
+
 /* Search for desc->dir_cookie from the beginning of the page cache */
-static inline
-int readdir_search_pagecache(nfs_readdir_descriptor_t *desc)
+static int readdir_search_pagecache(struct nfs_readdir_descriptor *desc)
 {
 	int res;
 
-	if (desc->page_index == 0) {
-		desc->current_index = 0;
-		desc->prev_index = 0;
-		desc->last_cookie = 0;
-	}
+	if (nfs_readdir_dont_search_cache(desc))
+		return -EBADCOOKIE;
+
 	do {
+		if (desc->page_index == 0) {
+			desc->current_index = 0;
+			desc->prev_index = 0;
+			desc->last_cookie = 0;
+		}
 		res = find_and_lock_cache_page(desc);
 	} while (res == -EAGAIN);
 	return res;
@@ -794,43 +973,41 @@ int readdir_search_pagecache(nfs_readdir_descriptor_t *desc)
 /*
  * Once we've found the start of the dirent within a page: fill 'er up...
  */
-static 
-int nfs_do_filldir(nfs_readdir_descriptor_t *desc)
+static void nfs_do_filldir(struct nfs_readdir_descriptor *desc)
 {
 	struct file	*file = desc->file;
-	int i = 0;
-	int res = 0;
-	struct nfs_cache_array *array = NULL;
-	struct nfs_open_dir_context *ctx = file->private_data;
+	struct nfs_inode *nfsi = NFS_I(file_inode(file));
+	struct nfs_cache_array *array;
+	unsigned int i = 0;
 
 	array = kmap(desc->page);
 	for (i = desc->cache_entry_index; i < array->size; i++) {
 		struct nfs_cache_array_entry *ent;
 
 		ent = &array->array[i];
-		if (!dir_emit(desc->ctx, ent->string.name, ent->string.len,
+		if (!dir_emit(desc->ctx, ent->name, ent->name_len,
 		    nfs_compat_user_ino64(ent->ino), ent->d_type)) {
 			desc->eof = true;
 			break;
 		}
+		memcpy(desc->verf, nfsi->cookieverf, sizeof(desc->verf));
 		if (i < (array->size-1))
-			*desc->dir_cookie = array->array[i+1].cookie;
+			desc->dir_cookie = array->array[i+1].cookie;
 		else
-			*desc->dir_cookie = array->last_cookie;
+			desc->dir_cookie = array->last_cookie;
 		if (nfs_readdir_use_cookie(file))
-			desc->ctx->pos = *desc->dir_cookie;
+			desc->ctx->pos = desc->dir_cookie;
 		else
 			desc->ctx->pos++;
-		if (ctx->duped != 0)
-			ctx->duped = 1;
+		if (desc->duped != 0)
+			desc->duped = 1;
 	}
-	if (array->eof_index >= 0)
+	if (array->page_is_eof)
 		desc->eof = true;
 
 	kunmap(desc->page);
-	dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n",
-			(unsigned long long)*desc->dir_cookie, res);
-	return res;
+	dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %llu\n",
+			(unsigned long long)desc->dir_cookie);
 }
 
 /*
@@ -845,40 +1022,41 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc)
  *	 we should already have a complete representation of the
  *	 directory in the page cache by the time we get here.
  */
-static inline
-int uncached_readdir(nfs_readdir_descriptor_t *desc)
+static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 {
-	struct page	*page = NULL;
-	int		status;
-	struct inode *inode = file_inode(desc->file);
-	struct nfs_open_dir_context *ctx = desc->file->private_data;
+	struct page	**arrays;
+	size_t		i, sz = 512;
+	__be32		verf[NFS_DIR_VERIFIER_SIZE];
+	int		status = -ENOMEM;
 
-	dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n",
-			(unsigned long long)*desc->dir_cookie);
+	dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %llu\n",
+			(unsigned long long)desc->dir_cookie);
 
-	page = alloc_page(GFP_HIGHUSER);
-	if (!page) {
-		status = -ENOMEM;
+	arrays = kcalloc(sz, sizeof(*arrays), GFP_KERNEL);
+	if (!arrays)
+		goto out;
+	arrays[0] = nfs_readdir_page_array_alloc(desc->dir_cookie, GFP_KERNEL);
+	if (!arrays[0])
 		goto out;
-	}
 
 	desc->page_index = 0;
-	desc->last_cookie = *desc->dir_cookie;
-	desc->page = page;
-	ctx->duped = 0;
-
-	status = nfs_readdir_xdr_to_array(desc, page, inode);
-	if (status < 0)
-		goto out_release;
-
-	status = nfs_do_filldir(desc);
-
- out_release:
-	nfs_readdir_clear_array(desc->page);
-	cache_page_release(desc);
- out:
-	dfprintk(DIRCACHE, "NFS: %s: returns %d\n",
-			__func__, status);
+	desc->last_cookie = desc->dir_cookie;
+	desc->duped = 0;
+
+	status = nfs_readdir_xdr_to_array(desc, desc->verf, verf, arrays, sz);
+
+	for (i = 0; !desc->eof && i < sz && arrays[i]; i++) {
+		desc->page = arrays[i];
+		nfs_do_filldir(desc);
+	}
+	desc->page = NULL;
+
+
+	for (i = 0; i < sz && arrays[i]; i++)
+		nfs_readdir_page_array_free(arrays[i]);
+out:
+	kfree(arrays);
+	dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status);
 	return status;
 }
 
@@ -891,14 +1069,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	struct dentry	*dentry = file_dentry(file);
 	struct inode	*inode = d_inode(dentry);
 	struct nfs_open_dir_context *dir_ctx = file->private_data;
-	nfs_readdir_descriptor_t my_desc = {
-		.file = file,
-		.ctx = ctx,
-		.dir_cookie = &dir_ctx->dir_cookie,
-		.plus = nfs_use_readdirplus(inode, ctx),
-	},
-			*desc = &my_desc;
-	int res = 0;
+	struct nfs_readdir_descriptor *desc;
+	int res;
 
 	dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n",
 			file, (long long)ctx->pos);
@@ -910,10 +1082,27 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	 * to either find the entry with the appropriate number or
 	 * revalidate the cookie.
 	 */
-	if (ctx->pos == 0 || nfs_attribute_cache_expired(inode))
+	if (ctx->pos == 0 || nfs_attribute_cache_expired(inode)) {
 		res = nfs_revalidate_mapping(inode, file->f_mapping);
-	if (res < 0)
+		if (res < 0)
+			goto out;
+	}
+
+	res = -ENOMEM;
+	desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+	if (!desc)
 		goto out;
+	desc->file = file;
+	desc->ctx = ctx;
+	desc->plus = nfs_use_readdirplus(inode, ctx);
+
+	spin_lock(&file->f_lock);
+	desc->dir_cookie = dir_ctx->dir_cookie;
+	desc->dup_cookie = dir_ctx->dup_cookie;
+	desc->duped = dir_ctx->duped;
+	desc->attr_gencount = dir_ctx->attr_gencount;
+	memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf));
+	spin_unlock(&file->f_lock);
 
 	do {
 		res = readdir_search_pagecache(desc);
@@ -921,11 +1110,13 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 		if (res == -EBADCOOKIE) {
 			res = 0;
 			/* This means either end of directory */
-			if (*desc->dir_cookie && !desc->eof) {
+			if (desc->dir_cookie && !desc->eof) {
 				/* Or that the server has 'lost' a cookie */
 				res = uncached_readdir(desc);
 				if (res == 0)
 					continue;
+				if (res == -EBADCOOKIE || res == -ENOTSYNC)
+					res = 0;
 			}
 			break;
 		}
@@ -940,15 +1131,21 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 		if (res < 0)
 			break;
 
-		res = nfs_do_filldir(desc);
-		unlock_page(desc->page);
-		cache_page_release(desc);
-		if (res < 0)
-			break;
+		nfs_do_filldir(desc);
+		nfs_readdir_page_unlock_and_put_cached(desc);
 	} while (!desc->eof);
+
+	spin_lock(&file->f_lock);
+	dir_ctx->dir_cookie = desc->dir_cookie;
+	dir_ctx->dup_cookie = desc->dup_cookie;
+	dir_ctx->duped = desc->duped;
+	dir_ctx->attr_gencount = desc->attr_gencount;
+	memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf));
+	spin_unlock(&file->f_lock);
+
+	kfree(desc);
+
 out:
-	if (res > 0)
-		res = 0;
 	dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res);
 	return res;
 }
@@ -984,6 +1181,8 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 			dir_ctx->dir_cookie = offset;
 		else
 			dir_ctx->dir_cookie = 0;
+		if (offset == 0)
+			memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf));
 		dir_ctx->duped = 0;
 	}
 	spin_unlock(&filp->f_lock);