[PATCH v10 00/26] Readdir improvements

[PATCH v10 00/26] Readdir improvements

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

The current NFS readdir code will always try to maximise the amount of
readahead it performs on the assumption that we can cache anything that
isn't immediately read by the process.
There are several cases where this assumption breaks down, including
when the 'ls -l' heuristic kicks in to try to force use of readdirplus
as a batch replacement for lookup/getattr.

This series also implement Ben's page cache filter to ensure that we can
improve the ability to share cached data between processes that are
reading the same directory at the same time, and to avoid live-locks
when the directory is simultaneously changing.

--
v2: Remove reset of dtsize when NFS_INO_FORCE_READDIR is set
v3: Avoid excessive window shrinking in uncached_readdir case
v4: Track 'ls -l' cache hit/miss statistics
    Improved algorithm for falling back to uncached readdir
    Skip readdirplus when files are being written to
v5: bugfixes
    Skip readdirplus when the acdirmax/acregmax values are low
    Request a full XDR buffer when doing READDIRPLUS
v6: Add tracing
    Don't have lookup request readdirplus when it won't help
v7: Implement Ben's page cache filter
    Reduce the use of uncached readdir
    Change indexing of the page cache to improve seekdir() performance.
v8: Reduce the page cache overhead by shrinking the cookie hashvalue size
    Incorporate other feedback from Anna, Ben and Neil
    Fix nfs2/3_decode_dirent return values
    Fix the change attribute value set in nfs_readdir_page_get_next()
v9: Address bugs that were hit when testing with large directories
    Misc cleanups
v10: Reinstate cache invalidations for directories, since Olga showed
    that the NFSv3 ctime resolution can be insufficient to record
    rapid changes to a directory.

Trond Myklebust (26):
  NFS: Return valid errors from nfs2/3_decode_dirent()
  NFS: constify nfs_server_capable() and nfs_have_writebacks()
  NFS: Trace lookup revalidation failure
  NFS: Initialise the readdir verifier as best we can in nfs_opendir()
  NFS: Use kzalloc() to avoid initialising the nfs_open_dir_context
  NFS: Calculate page offsets algorithmically
  NFS: Store the change attribute in the directory page cache
  NFS: Don't re-read the entire page cache to find the next cookie
  NFS: Don't advance the page pointer unless the page is full
  NFS: Adjust the amount of readahead performed by NFS readdir
  NFS: If the cookie verifier changes, we must invalidate the page cache
  NFS: Simplify nfs_readdir_xdr_to_array()
  NFS: Reduce use of uncached readdir
  NFS: Improve heuristic for readdirplus
  NFS: Don't ask for readdirplus unless it can help nfs_getattr()
  NFSv4: Ask for a full XDR buffer of readdir goodness
  NFS: Readdirplus can't help lookup for case insensitive filesystems
  NFS: Don't request readdirplus when revalidation was forced
  NFS: Add basic readdir tracing
  NFS: Trace effects of readdirplus on the dcache
  NFS: Trace effects of the readdirplus heuristic
  NFS: Clean up page array initialisation/free
  NFS: Convert readdir page cache to use a cookie based index
  NFS: Fix up forced readdirplus
  NFS: Optimise away the previous cookie field
  NFS: Cache all entries in the readdirplus reply

 fs/nfs/Kconfig          |   4 +
 fs/nfs/dir.c            | 595 ++++++++++++++++++++++++----------------
 fs/nfs/inode.c          |  45 +--
 fs/nfs/internal.h       |   4 +-
 fs/nfs/nfs2xdr.c        |   3 +-
 fs/nfs/nfs3xdr.c        |  29 +-
 fs/nfs/nfs4xdr.c        |   7 +-
 fs/nfs/nfstrace.h       | 123 ++++++++-
 include/linux/nfs_fs.h  |  17 +-
 include/linux/nfs_xdr.h |   3 +-
 10 files changed, 535 insertions(+), 295 deletions(-)

-- 
2.35.1

[PATCH v10 01/26] NFS: Return valid errors from nfs2/3_decode_dirent()

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Valid return values for decode_dirent() callback functions are:
 0: Success
 -EBADCOOKIE: End of directory
 -EAGAIN: End of xdr_stream

All errors need to map into one of those three values.

Fixes: 573c4e1ef53a ("NFS: Simplify ->decode_dirent() calling sequence")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs2xdr.c |  2 +-
 fs/nfs/nfs3xdr.c | 21 ++++++---------------
 2 files changed, 7 insertions(+), 16 deletions(-)

diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 7fba7711e6b3..3d5ba43f44bb 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -949,7 +949,7 @@ int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 
 	error = decode_filename_inline(xdr, &entry->name, &entry->len);
 	if (unlikely(error))
-		return error;
+		return -EAGAIN;
 
 	/*
 	 * The type (size and byte order) of nfscookie isn't defined in
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 54a1d21cbcc6..7ab60ad98776 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1967,7 +1967,6 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		       bool plus)
 {
 	struct user_namespace *userns = rpc_userns(entry->server->client);
-	struct nfs_entry old = *entry;
 	__be32 *p;
 	int error;
 	u64 new_cookie;
@@ -1987,15 +1986,15 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 
 	error = decode_fileid3(xdr, &entry->ino);
 	if (unlikely(error))
-		return error;
+		return -EAGAIN;
 
 	error = decode_inline_filename3(xdr, &entry->name, &entry->len);
 	if (unlikely(error))
-		return error;
+		return -EAGAIN;
 
 	error = decode_cookie3(xdr, &new_cookie);
 	if (unlikely(error))
-		return error;
+		return -EAGAIN;
 
 	entry->d_type = DT_UNKNOWN;
 
@@ -2003,7 +2002,7 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		entry->fattr->valid = 0;
 		error = decode_post_op_attr(xdr, entry->fattr, userns);
 		if (unlikely(error))
-			return error;
+			return -EAGAIN;
 		if (entry->fattr->valid & NFS_ATTR_FATTR_V3)
 			entry->d_type = nfs_umode_to_dtype(entry->fattr->mode);
 
@@ -2018,11 +2017,8 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 			return -EAGAIN;
 		if (*p != xdr_zero) {
 			error = decode_nfs_fh3(xdr, entry->fh);
-			if (unlikely(error)) {
-				if (error == -E2BIG)
-					goto out_truncated;
-				return error;
-			}
+			if (unlikely(error))
+				return -EAGAIN;
 		} else
 			zero_nfs_fh3(entry->fh);
 	}
@@ -2031,11 +2027,6 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 	entry->cookie = new_cookie;
 
 	return 0;
-
-out_truncated:
-	dprintk("NFS: directory entry contains invalid file handle\n");
-	*entry = old;
-	return -EAGAIN;
 }
 
 /*
-- 
2.35.1

[PATCH v10 02/26] NFS: constify nfs_server_capable() and nfs_have_writebacks()

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/nfs_fs.h | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 72a732a5103c..6e10725887d1 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -363,7 +363,7 @@ static inline void nfs_mark_for_revalidate(struct inode *inode)
 	spin_unlock(&inode->i_lock);
 }
 
-static inline int nfs_server_capable(struct inode *inode, int cap)
+static inline int nfs_server_capable(const struct inode *inode, int cap)
 {
 	return NFS_SERVER(inode)->caps & cap;
 }
@@ -587,12 +587,11 @@ extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail);
 extern void nfs_commit_free(struct nfs_commit_data *data);
 bool nfs_commit_end(struct nfs_mds_commit_info *cinfo);
 
-static inline int
-nfs_have_writebacks(struct inode *inode)
+static inline bool nfs_have_writebacks(const struct inode *inode)
 {
 	if (S_ISREG(inode->i_mode))
 		return atomic_long_read(&NFS_I(inode)->nrequests) != 0;
-	return 0;
+	return false;
 }
 
 /*
-- 
2.35.1

[PATCH v10 03/26] NFS: Trace lookup revalidation failure

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Enable tracing of lookup revalidation failures.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index ebddc736eac2..1aa55cac9d9a 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1474,9 +1474,7 @@ nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry,
 {
 	switch (error) {
 	case 1:
-		dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n",
-			__func__, dentry);
-		return 1;
+		break;
 	case 0:
 		/*
 		 * We can't d_drop the root of a disconnected tree:
@@ -1485,13 +1483,10 @@ nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry,
 		 * inodes on unmount and further oopses.
 		 */
 		if (inode && IS_ROOT(dentry))
-			return 1;
-		dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n",
-				__func__, dentry);
-		return 0;
+			error = 1;
+		break;
 	}
-	dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) lookup returned error %d\n",
-				__func__, dentry, error);
+	trace_nfs_lookup_revalidate_exit(dir, dentry, 0, error);
 	return error;
 }
 
@@ -1623,9 +1618,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 		goto out_bad;
 
 	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
-	error = nfs_lookup_revalidate_dentry(dir, dentry, inode);
-	trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error);
-	return error;
+	return nfs_lookup_revalidate_dentry(dir, dentry, inode);
 out_valid:
 	return nfs_lookup_revalidate_done(dir, dentry, inode, 1);
 out_bad:
-- 
2.35.1

[PATCH v10 04/26] NFS: Initialise the readdir verifier as best we can in nfs_opendir()

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

For the purpose of ensuring that opendir() followed by seekdir() work as
correctly as possible, try to initialise the readdir verifier in
nfs_opendir().

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 1aa55cac9d9a..1dfbd05081ad 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -89,6 +89,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir
 						      NFS_INO_REVAL_FORCED);
 		list_add(&ctx->list, &nfsi->open_files);
 		clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags);
+		memcpy(ctx->verf, nfsi->cookieverf, sizeof(ctx->verf));
 		spin_unlock(&dir->i_lock);
 		return ctx;
 	}
-- 
2.35.1

[PATCH v10 05/26] NFS: Use kzalloc() to avoid initialising the nfs_open_dir_context

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 1dfbd05081ad..379f88b158fb 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -69,18 +69,15 @@ 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)
+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;
-	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT);
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT);
 	if (ctx != NULL) {
-		ctx->duped = 0;
 		ctx->attr_gencount = nfsi->attr_gencount;
-		ctx->dir_cookie = 0;
-		ctx->dup_cookie = 0;
-		ctx->page_index = 0;
-		ctx->eof = false;
 		spin_lock(&dir->i_lock);
 		if (list_empty(&nfsi->open_files) &&
 		    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
-- 
2.35.1

[PATCH v10 06/26] NFS: Calculate page offsets algorithmically

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Instead of relying on counting the page offsets as we walk through the
page cache, switch to calculating them algorithmically.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 379f88b158fb..6f0a38db6c37 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -249,17 +249,20 @@ static const char *nfs_readdir_copy_name(const char *name, unsigned int len)
 	return ret;
 }
 
+static size_t nfs_readdir_array_maxentries(void)
+{
+	return (PAGE_SIZE - sizeof(struct nfs_cache_array)) /
+	       sizeof(struct nfs_cache_array_entry);
+}
+
 /*
  * 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) {
+	if (array->size == nfs_readdir_array_maxentries()) {
 		array->page_full = 1;
 		return -ENOSPC;
 	}
@@ -318,6 +321,11 @@ static struct page *nfs_readdir_page_get_locked(struct address_space *mapping,
 	return page;
 }
 
+static loff_t nfs_readdir_page_offset(struct page *page)
+{
+	return (loff_t)page->index * (loff_t)nfs_readdir_array_maxentries();
+}
+
 static u64 nfs_readdir_page_last_cookie(struct page *page)
 {
 	struct nfs_cache_array *array;
@@ -448,7 +456,7 @@ static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array,
 		if (array->array[i].cookie == desc->dir_cookie) {
 			struct nfs_inode *nfsi = NFS_I(file_inode(desc->file));
 
-			new_pos = desc->current_index + i;
+			new_pos = nfs_readdir_page_offset(desc->page) + i;
 			if (desc->attr_gencount != nfsi->attr_gencount ||
 			    !nfs_readdir_inode_mapping_valid(nfsi)) {
 				desc->duped = 0;
-- 
2.35.1

[PATCH v10 07/26] NFS: Store the change attribute in the directory page cache

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Use the change attribute and the first cookie in a directory page cache
entry to validate that the page is up to date.

Suggested-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 68 ++++++++++++++++++++++++++++------------------------
 1 file changed, 37 insertions(+), 31 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 6f0a38db6c37..a1767f755460 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -140,6 +140,7 @@ struct nfs_cache_array_entry {
 };
 
 struct nfs_cache_array {
+	u64 change_attr;
 	u64 last_cookie;
 	unsigned int size;
 	unsigned char page_full : 1,
@@ -176,12 +177,14 @@ 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)
+static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie,
+					u64 change_attr)
 {
 	struct nfs_cache_array *array;
 
 	array = kmap_atomic(page);
 	nfs_readdir_array_init(array);
+	array->change_attr = change_attr;
 	array->last_cookie = last_cookie;
 	array->cookies_are_ordered = 1;
 	kunmap_atomic(array);
@@ -208,7 +211,7 @@ 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);
+		nfs_readdir_page_init_array(page, last_cookie, 0);
 	return page;
 }
 
@@ -305,19 +308,43 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
 	return ret;
 }
 
+static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie,
+				      u64 change_attr)
+{
+	struct nfs_cache_array *array = kmap_atomic(page);
+	int ret = true;
+
+	if (array->change_attr != change_attr)
+		ret = false;
+	if (array->size > 0 && array->array[0].cookie != last_cookie)
+		ret = false;
+	kunmap_atomic(array);
+	return ret;
+}
+
+static void nfs_readdir_page_unlock_and_put(struct page *page)
+{
+	unlock_page(page);
+	put_page(page);
+}
+
 static struct page *nfs_readdir_page_get_locked(struct address_space *mapping,
 						pgoff_t index, u64 last_cookie)
 {
 	struct page *page;
+	u64 change_attr;
 
 	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);
+	if (!page)
+		return NULL;
+	change_attr = inode_peek_iversion_raw(mapping->host);
+	if (PageUptodate(page)) {
+		if (nfs_readdir_page_validate(page, last_cookie, change_attr))
+			return page;
+		nfs_readdir_clear_array(page);
 	}
-
+	nfs_readdir_page_init_array(page, last_cookie, change_attr);
+	SetPageUptodate(page);
 	return page;
 }
 
@@ -357,12 +384,6 @@ static void nfs_readdir_page_set_eof(struct page *page)
 	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)
 {
@@ -419,16 +440,6 @@ static int nfs_readdir_search_for_pos(struct nfs_cache_array *array,
 	return -EBADCOOKIE;
 }
 
-static bool
-nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi)
-{
-	if (nfsi->cache_validity & (NFS_INO_INVALID_CHANGE |
-				    NFS_INO_INVALID_DATA))
-		return false;
-	smp_rmb();
-	return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags);
-}
-
 static bool nfs_readdir_array_cookie_in_range(struct nfs_cache_array *array,
 					      u64 cookie)
 {
@@ -457,8 +468,7 @@ static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array,
 			struct nfs_inode *nfsi = NFS_I(file_inode(desc->file));
 
 			new_pos = nfs_readdir_page_offset(desc->page) + i;
-			if (desc->attr_gencount != nfsi->attr_gencount ||
-			    !nfs_readdir_inode_mapping_valid(nfsi)) {
+			if (desc->attr_gencount != nfsi->attr_gencount) {
 				desc->duped = 0;
 				desc->attr_gencount = nfsi->attr_gencount;
 			} else if (new_pos < desc->prev_index) {
@@ -1095,11 +1105,7 @@ 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)) {
-		res = nfs_revalidate_mapping(inode, file->f_mapping);
-		if (res < 0)
-			goto out;
-	}
+	nfs_revalidate_mapping(inode, file->f_mapping);
 
 	res = -ENOMEM;
 	desc = kzalloc(sizeof(*desc), GFP_KERNEL);
-- 
2.35.1

[PATCH v10 08/26] NFS: Don't re-read the entire page cache to find the next cookie

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

If the page cache entry that was last read gets invalidated for some
reason, then make sure we can re-create it on the next call to readdir.
This, combined with the cache page validation, allows us to reuse the
cached value of page-index on successive calls to nfs_readdir.

Credit is due to Benjamin Coddington for showing that the concept works,
and that it allows for improved cache sharing between processes even in
the case where pages are lost due to LRU or active invalidation.

Suggested-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c           | 10 +++++++---
 include/linux/nfs_fs.h |  1 +
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index a1767f755460..93f70698e401 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1120,6 +1120,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->dup_cookie = dir_ctx->dup_cookie;
 	desc->duped = dir_ctx->duped;
 	page_index = dir_ctx->page_index;
+	desc->page_index = page_index;
+	desc->last_cookie = dir_ctx->last_cookie;
 	desc->attr_gencount = dir_ctx->attr_gencount;
 	desc->eof = dir_ctx->eof;
 	memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf));
@@ -1168,6 +1170,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	spin_lock(&file->f_lock);
 	dir_ctx->dir_cookie = desc->dir_cookie;
 	dir_ctx->dup_cookie = desc->dup_cookie;
+	dir_ctx->last_cookie = desc->last_cookie;
 	dir_ctx->duped = desc->duped;
 	dir_ctx->attr_gencount = desc->attr_gencount;
 	dir_ctx->page_index = desc->page_index;
@@ -1209,10 +1212,11 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 	}
 	if (offset != filp->f_pos) {
 		filp->f_pos = offset;
-		if (nfs_readdir_use_cookie(filp))
-			dir_ctx->dir_cookie = offset;
-		else
+		if (!nfs_readdir_use_cookie(filp)) {
 			dir_ctx->dir_cookie = 0;
+			dir_ctx->page_index = 0;
+		} else
+			dir_ctx->dir_cookie = offset;
 		if (offset == 0)
 			memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf));
 		dir_ctx->duped = 0;
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 6e10725887d1..1c533f2c1f36 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -105,6 +105,7 @@ struct nfs_open_dir_context {
 	__be32	verf[NFS_DIR_VERIFIER_SIZE];
 	__u64 dir_cookie;
 	__u64 dup_cookie;
+	__u64 last_cookie;
 	pgoff_t page_index;
 	signed char duped;
 	bool eof;
-- 
2.35.1

[PATCH v10 09/26] NFS: Don't advance the page pointer unless the page is full

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

When we hit the end of the data in the readdir page, we don't want to
start filling a new page, unless this one is full.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 32 ++++++++++++++++++++++----------
 1 file changed, 22 insertions(+), 10 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 93f70698e401..60f7feee0a16 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -417,6 +417,18 @@ bool nfs_readdir_use_cookie(const struct file *filp)
 	return true;
 }
 
+static void nfs_readdir_seek_next_array(struct nfs_cache_array *array,
+					struct nfs_readdir_descriptor *desc)
+{
+	if (array->page_full) {
+		desc->last_cookie = array->last_cookie;
+		desc->current_index += array->size;
+		desc->cache_entry_index = 0;
+		desc->page_index++;
+	} else
+		desc->last_cookie = array->array[0].cookie;
+}
+
 static int nfs_readdir_search_for_pos(struct nfs_cache_array *array,
 				      struct nfs_readdir_descriptor *desc)
 {
@@ -428,6 +440,7 @@ static int nfs_readdir_search_for_pos(struct nfs_cache_array *array,
 	if (diff >= array->size) {
 		if (array->page_is_eof)
 			goto out_eof;
+		nfs_readdir_seek_next_array(array, desc);
 		return -EAGAIN;
 	}
 
@@ -500,7 +513,8 @@ static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array,
 		status = -EBADCOOKIE;
 		if (desc->dir_cookie == array->last_cookie)
 			desc->eof = true;
-	}
+	} else
+		nfs_readdir_seek_next_array(array, desc);
 out:
 	return status;
 }
@@ -517,11 +531,6 @@ static int nfs_readdir_search_array(struct nfs_readdir_descriptor *desc)
 	else
 		status = nfs_readdir_search_for_cookie(array, desc);
 
-	if (status == -EAGAIN) {
-		desc->last_cookie = array->last_cookie;
-		desc->current_index += array->size;
-		desc->page_index++;
-	}
 	kunmap_atomic(array);
 	return status;
 }
@@ -998,7 +1007,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc,
 {
 	struct file	*file = desc->file;
 	struct nfs_cache_array *array;
-	unsigned int i = 0;
+	unsigned int i;
 
 	array = kmap(desc->page);
 	for (i = desc->cache_entry_index; i < array->size; i++) {
@@ -1011,10 +1020,13 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc,
 			break;
 		}
 		memcpy(desc->verf, verf, sizeof(desc->verf));
-		if (i < (array->size-1))
-			desc->dir_cookie = array->array[i+1].cookie;
-		else
+		if (i == array->size - 1) {
 			desc->dir_cookie = array->last_cookie;
+			nfs_readdir_seek_next_array(array, desc);
+		} else {
+			desc->dir_cookie = array->array[i + 1].cookie;
+			desc->last_cookie = array->array[0].cookie;
+		}
 		if (nfs_readdir_use_cookie(file))
 			desc->ctx->pos = desc->dir_cookie;
 		else
-- 
2.35.1

[PATCH v10 10/26] NFS: Adjust the amount of readahead performed by NFS readdir

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

The current NFS readdir code will always try to maximise the amount of
readahead it performs on the assumption that we can cache anything that
isn't immediately read by the process.
There are several cases where this assumption breaks down, including
when the 'ls -l' heuristic kicks in to try to force use of readdirplus
as a batch replacement for lookup/getattr.

This patch therefore tries to tone down the amount of readahead we
perform, and adjust it to try to match the amount of data being
requested by user space.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c           | 53 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/nfs_fs.h |  1 +
 2 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 60f7feee0a16..520dc3ec4aef 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -69,6 +69,8 @@ const struct address_space_operations nfs_dir_aops = {
 	.freepage = nfs_readdir_clear_array,
 };
 
+#define NFS_INIT_DTSIZE PAGE_SIZE
+
 static struct nfs_open_dir_context *
 alloc_nfs_open_dir_context(struct inode *dir)
 {
@@ -78,6 +80,7 @@ alloc_nfs_open_dir_context(struct inode *dir)
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT);
 	if (ctx != NULL) {
 		ctx->attr_gencount = nfsi->attr_gencount;
+		ctx->dtsize = NFS_INIT_DTSIZE;
 		spin_lock(&dir->i_lock);
 		if (list_empty(&nfsi->open_files) &&
 		    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
@@ -154,6 +157,7 @@ struct nfs_readdir_descriptor {
 	struct page	*page;
 	struct dir_context *ctx;
 	pgoff_t		page_index;
+	pgoff_t		page_index_max;
 	u64		dir_cookie;
 	u64		last_cookie;
 	u64		dup_cookie;
@@ -166,12 +170,36 @@ struct nfs_readdir_descriptor {
 	unsigned long	gencount;
 	unsigned long	attr_gencount;
 	unsigned int	cache_entry_index;
+	unsigned int	buffer_fills;
+	unsigned int	dtsize;
 	signed char duped;
 	bool plus;
 	bool eob;
 	bool eof;
 };
 
+static void nfs_set_dtsize(struct nfs_readdir_descriptor *desc, unsigned int sz)
+{
+	struct nfs_server *server = NFS_SERVER(file_inode(desc->file));
+	unsigned int maxsize = server->dtsize;
+
+	if (sz > maxsize)
+		sz = maxsize;
+	if (sz < NFS_MIN_FILE_IO_SIZE)
+		sz = NFS_MIN_FILE_IO_SIZE;
+	desc->dtsize = sz;
+}
+
+static void nfs_shrink_dtsize(struct nfs_readdir_descriptor *desc)
+{
+	nfs_set_dtsize(desc, desc->dtsize >> 1);
+}
+
+static void nfs_grow_dtsize(struct nfs_readdir_descriptor *desc)
+{
+	nfs_set_dtsize(desc, desc->dtsize << 1);
+}
+
 static void nfs_readdir_array_init(struct nfs_cache_array *array)
 {
 	memset(array, 0, sizeof(struct nfs_cache_array));
@@ -784,6 +812,7 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
 				break;
 			arrays++;
 			*arrays = page = new;
+			desc->page_index_max++;
 		} else {
 			new = nfs_readdir_page_get_next(mapping,
 							page->index + 1,
@@ -793,6 +822,7 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
 			if (page != *arrays)
 				nfs_readdir_page_unlock_and_put(page);
 			page = new;
+			desc->page_index_max = new->index;
 		}
 		status = nfs_readdir_add_to_array(entry, page);
 	} while (!status && !entry->eof);
@@ -858,7 +888,7 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
 	struct nfs_entry *entry;
 	size_t array_size;
 	struct inode *inode = file_inode(desc->file);
-	size_t dtsize = NFS_SERVER(inode)->dtsize;
+	unsigned int dtsize = desc->dtsize;
 	int status = -ENOMEM;
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
@@ -894,6 +924,7 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
 
 		status = nfs_readdir_page_filler(desc, entry, pages, pglen,
 						 arrays, narrays);
+		desc->buffer_fills++;
 	} while (!status && nfs_readdir_page_needs_filling(page) &&
 		page_mapping(page));
 
@@ -941,6 +972,10 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 	if (!desc->page)
 		return -ENOMEM;
 	if (nfs_readdir_page_needs_filling(desc->page)) {
+		/* Grow the dtsize if we had to go back for more pages */
+		if (desc->page_index == desc->page_index_max)
+			nfs_grow_dtsize(desc);
+		desc->page_index_max = desc->page_index;
 		res = nfs_readdir_xdr_to_array(desc, nfsi->cookieverf, verf,
 					       &desc->page, 1);
 		if (res < 0) {
@@ -1075,6 +1110,7 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 	desc->cache_entry_index = 0;
 	desc->last_cookie = desc->dir_cookie;
 	desc->duped = 0;
+	desc->page_index_max = 0;
 
 	status = nfs_readdir_xdr_to_array(desc, desc->verf, verf, arrays, sz);
 
@@ -1084,10 +1120,22 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 	}
 	desc->page = NULL;
 
+	/*
+	 * Grow the dtsize if we have to go back for more pages,
+	 * or shrink it if we're reading too many.
+	 */
+	if (!desc->eof) {
+		if (!desc->eob)
+			nfs_grow_dtsize(desc);
+		else if (desc->buffer_fills == 1 &&
+			 i < (desc->page_index_max >> 1))
+			nfs_shrink_dtsize(desc);
+	}
 
 	for (i = 0; i < sz && arrays[i]; i++)
 		nfs_readdir_page_array_free(arrays[i]);
 out:
+	desc->page_index_max = -1;
 	kfree(arrays);
 	dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status);
 	return status;
@@ -1126,6 +1174,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->file = file;
 	desc->ctx = ctx;
 	desc->plus = nfs_use_readdirplus(inode, ctx);
+	desc->page_index_max = -1;
 
 	spin_lock(&file->f_lock);
 	desc->dir_cookie = dir_ctx->dir_cookie;
@@ -1136,6 +1185,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->last_cookie = dir_ctx->last_cookie;
 	desc->attr_gencount = dir_ctx->attr_gencount;
 	desc->eof = dir_ctx->eof;
+	nfs_set_dtsize(desc, dir_ctx->dtsize);
 	memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf));
 	spin_unlock(&file->f_lock);
 
@@ -1187,6 +1237,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	dir_ctx->attr_gencount = desc->attr_gencount;
 	dir_ctx->page_index = desc->page_index;
 	dir_ctx->eof = desc->eof;
+	dir_ctx->dtsize = desc->dtsize;
 	memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf));
 	spin_unlock(&file->f_lock);
 out_free:
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 1c533f2c1f36..691a27936849 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -107,6 +107,7 @@ struct nfs_open_dir_context {
 	__u64 dup_cookie;
 	__u64 last_cookie;
 	pgoff_t page_index;
+	unsigned int dtsize;
 	signed char duped;
 	bool eof;
 };
-- 
2.35.1

[PATCH v10 11/26] NFS: If the cookie verifier changes, we must invalidate the page cache

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Ensure that if the cookie verifier changes when we use the zero-valued
cookie, then we invalidate any cached pages.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 520dc3ec4aef..9998d7d17367 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -990,9 +990,14 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 		/*
 		 * Set the cookie verifier if the page cache was empty
 		 */
-		if (desc->page_index == 0)
+		if (desc->last_cookie == 0 &&
+		    memcmp(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf))) {
 			memcpy(nfsi->cookieverf, verf,
 			       sizeof(nfsi->cookieverf));
+			invalidate_inode_pages2_range(desc->file->f_mapping,
+						      desc->page_index_max + 1,
+						      -1);
+		}
 	}
 	res = nfs_readdir_search_array(desc);
 	if (res == 0)
-- 
2.35.1

[PATCH v10 12/26] NFS: Simplify nfs_readdir_xdr_to_array()

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Recent changes to readdir mean that we can cope with partially filled
page cache entries, so we no longer need to rely on looping in
nfs_readdir_xdr_to_array().

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 29 +++++++++++------------------
 1 file changed, 11 insertions(+), 18 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 9998d7d17367..9d086ab4f889 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -889,6 +889,7 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
 	size_t array_size;
 	struct inode *inode = file_inode(desc->file);
 	unsigned int dtsize = desc->dtsize;
+	unsigned int pglen;
 	int status = -ENOMEM;
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
@@ -906,28 +907,20 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
 	if (!pages)
 		goto out;
 
-	do {
-		unsigned int pglen;
-		status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie,
-						pages, dtsize,
-						verf_res);
-		if (status < 0)
-			break;
-
-		pglen = status;
-		if (pglen == 0) {
-			nfs_readdir_page_set_eof(page);
-			break;
-		}
-
-		verf_arg = verf_res;
+	status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie, pages,
+					dtsize, verf_res);
+	if (status < 0)
+		goto free_pages;
 
+	pglen = status;
+	if (pglen != 0)
 		status = nfs_readdir_page_filler(desc, entry, pages, pglen,
 						 arrays, narrays);
-		desc->buffer_fills++;
-	} while (!status && nfs_readdir_page_needs_filling(page) &&
-		page_mapping(page));
+	else
+		nfs_readdir_page_set_eof(page);
+	desc->buffer_fills++;
 
+free_pages:
 	nfs_readdir_free_pages(pages, array_size);
 out:
 	nfs_free_fattr(entry->fattr);
-- 
2.35.1

[PATCH v10 13/26] NFS: Reduce use of uncached readdir

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

When reading a very large directory, we want to try to keep the page
cache up to date if doing so is inexpensive. With the change to allow
readdir to continue reading even when the cache is incomplete, we no
longer need to fall back to uncached readdir in order to scale to large
directories.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 23 +++--------------------
 1 file changed, 3 insertions(+), 20 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 9d086ab4f889..dc6acfd14fc7 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -999,28 +999,11 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *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 int readdir_search_pagecache(struct nfs_readdir_descriptor *desc)
 {
 	int res;
 
-	if (nfs_readdir_dont_search_cache(desc))
-		return -EBADCOOKIE;
-
 	do {
 		if (desc->page_index == 0) {
 			desc->current_index = 0;
@@ -1273,10 +1256,10 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 	}
 	if (offset != filp->f_pos) {
 		filp->f_pos = offset;
-		if (!nfs_readdir_use_cookie(filp)) {
+		dir_ctx->page_index = 0;
+		if (!nfs_readdir_use_cookie(filp))
 			dir_ctx->dir_cookie = 0;
-			dir_ctx->page_index = 0;
-		} else
+		else
 			dir_ctx->dir_cookie = offset;
 		if (offset == 0)
 			memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf));
-- 
2.35.1

[PATCH v10 14/26] NFS: Improve heuristic for readdirplus

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

The heuristic for readdirplus is designed to try to detect 'ls -l' and
similar patterns. It does so by looking for cache hit/miss patterns in
both the attribute cache and in the dcache of the files in a given
directory, and then sets a flag for the readdirplus code to interpret.

The problem with this approach is that a single attribute or dcache miss
can cause the NFS code to force a refresh of the attributes for the
entire set of files contained in the directory.

To be able to make a more nuanced decision, let's sample the number of
hits and misses in the set of open directory descriptors. That allows us
to set thresholds at which we start preferring READDIRPLUS over regular
READDIR, or at which we start to force a re-read of the remaining
readdir cache using READDIRPLUS.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c           | 80 +++++++++++++++++++++++++++---------------
 fs/nfs/inode.c         |  4 +--
 fs/nfs/internal.h      |  4 +--
 fs/nfs/nfstrace.h      |  1 -
 include/linux/nfs_fs.h |  5 +--
 5 files changed, 58 insertions(+), 36 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index dc6acfd14fc7..098fc1bdaac8 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -87,8 +87,7 @@ alloc_nfs_open_dir_context(struct inode *dir)
 			nfs_set_cache_invalid(dir,
 					      NFS_INO_INVALID_DATA |
 						      NFS_INO_REVAL_FORCED);
-		list_add(&ctx->list, &nfsi->open_files);
-		clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags);
+		list_add_tail_rcu(&ctx->list, &nfsi->open_files);
 		memcpy(ctx->verf, nfsi->cookieverf, sizeof(ctx->verf));
 		spin_unlock(&dir->i_lock);
 		return ctx;
@@ -99,9 +98,9 @@ alloc_nfs_open_dir_context(struct inode *dir)
 static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_context *ctx)
 {
 	spin_lock(&dir->i_lock);
-	list_del(&ctx->list);
+	list_del_rcu(&ctx->list);
 	spin_unlock(&dir->i_lock);
-	kfree(ctx);
+	kfree_rcu(ctx, rcu_head);
 }
 
 /*
@@ -594,7 +593,6 @@ static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc,
 		/* 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 = arg.plus = false;
 			goto again;
 		}
@@ -644,51 +642,63 @@ int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
 	return 1;
 }
 
-static
-bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx)
+#define NFS_READDIR_CACHE_USAGE_THRESHOLD (8UL)
+
+static bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx,
+				unsigned int cache_hits,
+				unsigned int cache_misses)
 {
 	if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS))
 		return false;
-	if (test_and_clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags))
-		return true;
-	if (ctx->pos == 0)
+	if (ctx->pos == 0 ||
+	    cache_hits + cache_misses > NFS_READDIR_CACHE_USAGE_THRESHOLD)
 		return true;
 	return false;
 }
 
 /*
- * This function is called by the lookup and getattr code to request the
+ * This function is called by the getattr code to request the
  * use of readdirplus to accelerate any future lookups in the same
  * directory.
  */
-void nfs_advise_use_readdirplus(struct inode *dir)
+void nfs_readdir_record_entry_cache_hit(struct inode *dir)
 {
 	struct nfs_inode *nfsi = NFS_I(dir);
+	struct nfs_open_dir_context *ctx;
 
 	if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) &&
-	    !list_empty(&nfsi->open_files))
-		set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags);
+	    S_ISDIR(dir->i_mode)) {
+		rcu_read_lock();
+		list_for_each_entry_rcu (ctx, &nfsi->open_files, list)
+			atomic_inc(&ctx->cache_hits);
+		rcu_read_unlock();
+	}
 }
 
 /*
  * This function is mainly for use by nfs_getattr().
  *
  * If this is an 'ls -l', we want to force use of readdirplus.
- * Do this by checking if there is an active file descriptor
- * and calling nfs_advise_use_readdirplus, then forcing a
- * cache flush.
  */
-void nfs_force_use_readdirplus(struct inode *dir)
+void nfs_readdir_record_entry_cache_miss(struct inode *dir)
 {
 	struct nfs_inode *nfsi = NFS_I(dir);
+	struct nfs_open_dir_context *ctx;
 
 	if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) &&
-	    !list_empty(&nfsi->open_files)) {
-		set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags);
-		set_bit(NFS_INO_FORCE_READDIR, &nfsi->flags);
+	    S_ISDIR(dir->i_mode)) {
+		rcu_read_lock();
+		list_for_each_entry_rcu (ctx, &nfsi->open_files, list)
+			atomic_inc(&ctx->cache_misses);
+		rcu_read_unlock();
 	}
 }
 
+static void nfs_lookup_advise_force_readdirplus(struct inode *dir)
+{
+	nfs_readdir_record_entry_cache_miss(dir);
+}
+
 static
 void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry,
 		unsigned long dir_verifier)
@@ -1122,6 +1132,19 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 	return status;
 }
 
+#define NFS_READDIR_CACHE_MISS_THRESHOLD (16UL)
+
+static void nfs_readdir_handle_cache_misses(struct inode *inode,
+					    struct nfs_readdir_descriptor *desc,
+					    pgoff_t page_index,
+					    unsigned int cache_misses)
+{
+	if (desc->ctx->pos == 0 ||
+	    cache_misses <= NFS_READDIR_CACHE_MISS_THRESHOLD)
+		return;
+	invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1);
+}
+
 /* The file offset position represents the dirent entry number.  A
    last cookie cache takes care of the common case of reading the
    whole directory.
@@ -1133,6 +1156,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_open_dir_context *dir_ctx = file->private_data;
 	struct nfs_readdir_descriptor *desc;
+	unsigned int cache_hits, cache_misses;
 	pgoff_t page_index;
 	int res;
 
@@ -1154,7 +1178,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 		goto out;
 	desc->file = file;
 	desc->ctx = ctx;
-	desc->plus = nfs_use_readdirplus(inode, ctx);
 	desc->page_index_max = -1;
 
 	spin_lock(&file->f_lock);
@@ -1168,6 +1191,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->eof = dir_ctx->eof;
 	nfs_set_dtsize(desc, dir_ctx->dtsize);
 	memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf));
+	cache_hits = atomic_xchg(&dir_ctx->cache_hits, 0);
+	cache_misses = atomic_xchg(&dir_ctx->cache_misses, 0);
 	spin_unlock(&file->f_lock);
 
 	if (desc->eof) {
@@ -1175,9 +1200,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 		goto out_free;
 	}
 
-	if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) &&
-	    list_is_singular(&nfsi->open_files))
-		invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1);
+	desc->plus = nfs_use_readdirplus(inode, ctx, cache_hits, cache_misses);
+	nfs_readdir_handle_cache_misses(inode, desc, page_index, cache_misses);
 
 	do {
 		res = readdir_search_pagecache(desc);
@@ -1196,7 +1220,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 			break;
 		}
 		if (res == -ETOOSMALL && desc->plus) {
-			clear_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags);
 			nfs_zap_caches(inode);
 			desc->page_index = 0;
 			desc->plus = false;
@@ -1610,7 +1633,7 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry,
 	nfs_set_verifier(dentry, dir_verifier);
 
 	/* set a readdirplus hint that we had a cache miss */
-	nfs_force_use_readdirplus(dir);
+	nfs_lookup_advise_force_readdirplus(dir);
 	ret = 1;
 out:
 	nfs_free_fattr(fattr);
@@ -1667,7 +1690,6 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 				nfs_mark_dir_for_revalidate(dir);
 			goto out_bad;
 		}
-		nfs_advise_use_readdirplus(dir);
 		goto out_valid;
 	}
 
@@ -1872,7 +1894,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
 		goto out;
 
 	/* Notify readdir to use READDIRPLUS */
-	nfs_force_use_readdirplus(dir);
+	nfs_lookup_advise_force_readdirplus(dir);
 
 no_entry:
 	res = d_splice_alias(inode, dentry);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 7cecabf57b95..bbf4357ff727 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -787,7 +787,7 @@ static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry)
 	if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS))
 		return;
 	parent = dget_parent(dentry);
-	nfs_force_use_readdirplus(d_inode(parent));
+	nfs_readdir_record_entry_cache_miss(d_inode(parent));
 	dput(parent);
 }
 
@@ -798,7 +798,7 @@ static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry)
 	if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS))
 		return;
 	parent = dget_parent(dentry);
-	nfs_advise_use_readdirplus(d_inode(parent));
+	nfs_readdir_record_entry_cache_hit(d_inode(parent));
 	dput(parent);
 }
 
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index b5398af53c7f..194840a97e3a 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -366,8 +366,8 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
 			   const struct nfs_client_initdata *);
 
 /* dir.c */
-extern void nfs_advise_use_readdirplus(struct inode *dir);
-extern void nfs_force_use_readdirplus(struct inode *dir);
+extern void nfs_readdir_record_entry_cache_hit(struct inode *dir);
+extern void nfs_readdir_record_entry_cache_miss(struct inode *dir);
 extern unsigned long nfs_access_cache_count(struct shrinker *shrink,
 					    struct shrink_control *sc);
 extern unsigned long nfs_access_cache_scan(struct shrinker *shrink,
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 45a310b586ce..3672f6703ee7 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -36,7 +36,6 @@
 
 #define nfs_show_nfsi_flags(v) \
 	__print_flags(v, "|", \
-			{ BIT(NFS_INO_ADVISE_RDPLUS), "ADVISE_RDPLUS" }, \
 			{ BIT(NFS_INO_STALE), "STALE" }, \
 			{ BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \
 			{ BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 691a27936849..20a4cf0acad2 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -101,6 +101,8 @@ struct nfs_open_context {
 
 struct nfs_open_dir_context {
 	struct list_head list;
+	atomic_t cache_hits;
+	atomic_t cache_misses;
 	unsigned long attr_gencount;
 	__be32	verf[NFS_DIR_VERIFIER_SIZE];
 	__u64 dir_cookie;
@@ -110,6 +112,7 @@ struct nfs_open_dir_context {
 	unsigned int dtsize;
 	signed char duped;
 	bool eof;
+	struct rcu_head rcu_head;
 };
 
 /*
@@ -274,13 +277,11 @@ struct nfs4_copy_state {
 /*
  * Bit offsets in flags field
  */
-#define NFS_INO_ADVISE_RDPLUS	(0)		/* advise readdirplus */
 #define NFS_INO_STALE		(1)		/* possible stale inode */
 #define NFS_INO_ACL_LRU_SET	(2)		/* Inode is on the LRU list */
 #define NFS_INO_INVALIDATING	(3)		/* inode is being invalidated */
 #define NFS_INO_PRESERVE_UNLINKED (4)		/* preserve file if removed while open */
 #define NFS_INO_FSCACHE		(5)		/* inode can be cached by FS-Cache */
-#define NFS_INO_FORCE_READDIR	(7)		/* force readdirplus */
 #define NFS_INO_LAYOUTCOMMIT	(9)		/* layoutcommit required */
 #define NFS_INO_LAYOUTCOMMITTING (10)		/* layoutcommit inflight */
 #define NFS_INO_LAYOUTSTATS	(11)		/* layoutstats inflight */
-- 
2.35.1

[PATCH v10 15/26] NFS: Don't ask for readdirplus unless it can help nfs_getattr()

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

If attribute caching is turned off, then use of readdirplus is not going
to help stat() performance.
Readdirplus also doesn't help if a file is being written to, since we
will have to flush those writes in order to sync the mtime/ctime.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/inode.c | 45 +++++++++++++++++++++++++--------------------
 1 file changed, 25 insertions(+), 20 deletions(-)

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index bbf4357ff727..e51d86707fca 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -780,26 +780,32 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
 }
 EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
 
-static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry)
+/*
+ * Don't request help from readdirplus if the file is being written to,
+ * or if attribute caching is turned off
+ */
+static bool nfs_getattr_readdirplus_enable(const struct inode *inode)
 {
-	struct dentry *parent;
+	return nfs_server_capable(inode, NFS_CAP_READDIRPLUS) &&
+	       !nfs_have_writebacks(inode) && NFS_MAXATTRTIMEO(inode) > 5 * HZ;
+}
 
-	if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS))
-		return;
-	parent = dget_parent(dentry);
-	nfs_readdir_record_entry_cache_miss(d_inode(parent));
-	dput(parent);
+static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry)
+{
+	if (!IS_ROOT(dentry)) {
+		struct dentry *parent = dget_parent(dentry);
+		nfs_readdir_record_entry_cache_miss(d_inode(parent));
+		dput(parent);
+	}
 }
 
 static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry)
 {
-	struct dentry *parent;
-
-	if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS))
-		return;
-	parent = dget_parent(dentry);
-	nfs_readdir_record_entry_cache_hit(d_inode(parent));
-	dput(parent);
+	if (!IS_ROOT(dentry)) {
+		struct dentry *parent = dget_parent(dentry);
+		nfs_readdir_record_entry_cache_hit(d_inode(parent));
+		dput(parent);
+	}
 }
 
 static u32 nfs_get_valid_attrmask(struct inode *inode)
@@ -835,6 +841,7 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 	int err = 0;
 	bool force_sync = query_flags & AT_STATX_FORCE_SYNC;
 	bool do_update = false;
+	bool readdirplus_enabled = nfs_getattr_readdirplus_enable(inode);
 
 	trace_nfs_getattr_enter(inode);
 
@@ -843,7 +850,8 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 			STATX_INO | STATX_SIZE | STATX_BLOCKS;
 
 	if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) {
-		nfs_readdirplus_parent_cache_hit(path->dentry);
+		if (readdirplus_enabled)
+			nfs_readdirplus_parent_cache_hit(path->dentry);
 		goto out_no_revalidate;
 	}
 
@@ -893,15 +901,12 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		do_update |= cache_validity & NFS_INO_INVALID_BLOCKS;
 
 	if (do_update) {
-		/* Update the attribute cache */
-		if (!(server->flags & NFS_MOUNT_NOAC))
+		if (readdirplus_enabled)
 			nfs_readdirplus_parent_cache_miss(path->dentry);
-		else
-			nfs_readdirplus_parent_cache_hit(path->dentry);
 		err = __nfs_revalidate_inode(server, inode);
 		if (err)
 			goto out;
-	} else
+	} else if (readdirplus_enabled)
 		nfs_readdirplus_parent_cache_hit(path->dentry);
 out_no_revalidate:
 	/* Only return attributes that were revalidated. */
-- 
2.35.1

[PATCH v10 16/26] NFSv4: Ask for a full XDR buffer of readdir goodness

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Instead of pretending that we know the ratio of directory info vs
readdirplus attribute info, just set the 'dircount' field to the same
value as the 'maxcount' field.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs3xdr.c | 7 ++++---
 fs/nfs/nfs4xdr.c | 6 +++---
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 7ab60ad98776..d6779ceeb39e 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1261,6 +1261,8 @@ static void nfs3_xdr_enc_readdir3args(struct rpc_rqst *req,
 static void encode_readdirplus3args(struct xdr_stream *xdr,
 				    const struct nfs3_readdirargs *args)
 {
+	uint32_t dircount = args->count;
+	uint32_t maxcount = args->count;
 	__be32 *p;
 
 	encode_nfs_fh3(xdr, args->fh);
@@ -1273,9 +1275,8 @@ static void encode_readdirplus3args(struct xdr_stream *xdr,
 	 * readdirplus: need dircount + buffer size.
 	 * We just make sure we make dircount big enough
 	 */
-	*p++ = cpu_to_be32(args->count >> 3);
-
-	*p = cpu_to_be32(args->count);
+	*p++ = cpu_to_be32(dircount);
+	*p = cpu_to_be32(maxcount);
 }
 
 static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 8e70b92df4cc..b7780b97dc4d 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1605,7 +1605,8 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
 		FATTR4_WORD0_RDATTR_ERROR,
 		FATTR4_WORD1_MOUNTED_ON_FILEID,
 	};
-	uint32_t dircount = readdir->count >> 1;
+	uint32_t dircount = readdir->count;
+	uint32_t maxcount = readdir->count;
 	__be32 *p, verf[2];
 	uint32_t attrlen = 0;
 	unsigned int i;
@@ -1618,7 +1619,6 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
 			FATTR4_WORD1_SPACE_USED|FATTR4_WORD1_TIME_ACCESS|
 			FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
 		attrs[2] |= FATTR4_WORD2_SECURITY_LABEL;
-		dircount >>= 1;
 	}
 	/* Use mounted_on_fileid only if the server supports it */
 	if (!(readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID))
@@ -1634,7 +1634,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
 	encode_nfs4_verifier(xdr, &readdir->verifier);
 	p = reserve_space(xdr, 12 + (attrlen << 2));
 	*p++ = cpu_to_be32(dircount);
-	*p++ = cpu_to_be32(readdir->count);
+	*p++ = cpu_to_be32(maxcount);
 	*p++ = cpu_to_be32(attrlen);
 	for (i = 0; i < attrlen; i++)
 		*p++ = cpu_to_be32(attrs[i]);
-- 
2.35.1

[PATCH v10 17/26] NFS: Readdirplus can't help lookup for case insensitive filesystems

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

If the filesystem is case insensitive, then readdirplus can't help with
cache misses, since it won't return case folded variants of the filename.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 098fc1bdaac8..dcfc44411787 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -696,6 +696,8 @@ void nfs_readdir_record_entry_cache_miss(struct inode *dir)
 
 static void nfs_lookup_advise_force_readdirplus(struct inode *dir)
 {
+	if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE))
+		return;
 	nfs_readdir_record_entry_cache_miss(dir);
 }
 
-- 
2.35.1

[PATCH v10 18/26] NFS: Don't request readdirplus when revalidation was forced

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

If the revalidation was forced, due to the presence of a LOOKUP_EXCL or
a LOOKUP_REVAL flag, then readdirplus won't help. It also can't help
when we're doing a path component lookup.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index dcfc44411787..cf7974642a19 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -694,10 +694,13 @@ void nfs_readdir_record_entry_cache_miss(struct inode *dir)
 	}
 }
 
-static void nfs_lookup_advise_force_readdirplus(struct inode *dir)
+static void nfs_lookup_advise_force_readdirplus(struct inode *dir,
+						unsigned int flags)
 {
 	if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE))
 		return;
+	if (flags & (LOOKUP_EXCL | LOOKUP_PARENT | LOOKUP_REVAL))
+		return;
 	nfs_readdir_record_entry_cache_miss(dir);
 }
 
@@ -1596,15 +1599,17 @@ nfs_lookup_revalidate_delegated(struct inode *dir, struct dentry *dentry,
 	return nfs_lookup_revalidate_done(dir, dentry, inode, 1);
 }
 
-static int
-nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry,
-			     struct inode *inode)
+static int nfs_lookup_revalidate_dentry(struct inode *dir,
+					struct dentry *dentry,
+					struct inode *inode, unsigned int flags)
 {
 	struct nfs_fh *fhandle;
 	struct nfs_fattr *fattr;
 	unsigned long dir_verifier;
 	int ret;
 
+	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
+
 	ret = -ENOMEM;
 	fhandle = nfs_alloc_fhandle();
 	fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
@@ -1625,6 +1630,10 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry,
 		}
 		goto out;
 	}
+
+	/* Request help from readdirplus */
+	nfs_lookup_advise_force_readdirplus(dir, flags);
+
 	ret = 0;
 	if (nfs_compare_fh(NFS_FH(inode), fhandle))
 		goto out;
@@ -1634,8 +1643,6 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry,
 	nfs_setsecurity(inode, fattr);
 	nfs_set_verifier(dentry, dir_verifier);
 
-	/* set a readdirplus hint that we had a cache miss */
-	nfs_lookup_advise_force_readdirplus(dir);
 	ret = 1;
 out:
 	nfs_free_fattr(fattr);
@@ -1701,8 +1708,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 	if (NFS_STALE(inode))
 		goto out_bad;
 
-	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
-	return nfs_lookup_revalidate_dentry(dir, dentry, inode);
+	return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags);
 out_valid:
 	return nfs_lookup_revalidate_done(dir, dentry, inode, 1);
 out_bad:
@@ -1896,7 +1902,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
 		goto out;
 
 	/* Notify readdir to use READDIRPLUS */
-	nfs_lookup_advise_force_readdirplus(dir);
+	nfs_lookup_advise_force_readdirplus(dir, flags);
 
 no_entry:
 	res = d_splice_alias(inode, dentry);
@@ -2159,7 +2165,7 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 reval_dentry:
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
-	return nfs_lookup_revalidate_dentry(dir, dentry, inode);
+	return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags);
 
 full_reval:
 	return nfs_do_lookup_revalidate(dir, dentry, flags);
-- 
2.35.1

[PATCH v10 19/26] NFS: Add basic readdir tracing

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Add tracing to track how often the client goes to the server for updated
readdir information.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c      | 13 ++++++++-
 fs/nfs/nfstrace.h | 68 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 80 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index cf7974642a19..d591d20f7534 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -984,10 +984,14 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 		if (desc->page_index == desc->page_index_max)
 			nfs_grow_dtsize(desc);
 		desc->page_index_max = desc->page_index;
+		trace_nfs_readdir_cache_fill(desc->file, nfsi->cookieverf,
+					     desc->last_cookie,
+					     desc->page->index, desc->dtsize);
 		res = nfs_readdir_xdr_to_array(desc, nfsi->cookieverf, verf,
 					       &desc->page, 1);
 		if (res < 0) {
 			nfs_readdir_page_unlock_and_put_cached(desc);
+			trace_nfs_readdir_cache_fill_done(inode, res);
 			if (res == -EBADCOOKIE || res == -ENOTSYNC) {
 				invalidate_inode_pages2(desc->file->f_mapping);
 				desc->page_index = 0;
@@ -1108,7 +1112,14 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 	desc->duped = 0;
 	desc->page_index_max = 0;
 
+	trace_nfs_readdir_uncached(desc->file, desc->verf, desc->last_cookie,
+				   -1, desc->dtsize);
+
 	status = nfs_readdir_xdr_to_array(desc, desc->verf, verf, arrays, sz);
+	if (status < 0) {
+		trace_nfs_readdir_uncached_done(file_inode(desc->file), status);
+		goto out_free;
+	}
 
 	for (i = 0; !desc->eob && i < sz && arrays[i]; i++) {
 		desc->page = arrays[i];
@@ -1127,7 +1138,7 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 			 i < (desc->page_index_max >> 1))
 			nfs_shrink_dtsize(desc);
 	}
-
+out_free:
 	for (i = 0; i < sz && arrays[i]; i++)
 		nfs_readdir_page_array_free(arrays[i]);
 out:
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 3672f6703ee7..c2d0543ecb2d 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -160,6 +160,8 @@ DEFINE_NFS_INODE_EVENT(nfs_fsync_enter);
 DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit);
 DEFINE_NFS_INODE_EVENT(nfs_access_enter);
 DEFINE_NFS_INODE_EVENT_DONE(nfs_set_cache_invalid);
+DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_cache_fill_done);
+DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_uncached_done);
 
 TRACE_EVENT(nfs_access_exit,
 		TP_PROTO(
@@ -271,6 +273,72 @@ DEFINE_NFS_UPDATE_SIZE_EVENT(wcc);
 DEFINE_NFS_UPDATE_SIZE_EVENT(update);
 DEFINE_NFS_UPDATE_SIZE_EVENT(grow);
 
+DECLARE_EVENT_CLASS(nfs_readdir_event,
+		TP_PROTO(
+			const struct file *file,
+			const __be32 *verifier,
+			u64 cookie,
+			pgoff_t page_index,
+			unsigned int dtsize
+		),
+
+		TP_ARGS(file, verifier, cookie, page_index, dtsize),
+
+		TP_STRUCT__entry(
+			__field(dev_t, dev)
+			__field(u32, fhandle)
+			__field(u64, fileid)
+			__field(u64, version)
+			__array(char, verifier, NFS4_VERIFIER_SIZE)
+			__field(u64, cookie)
+			__field(pgoff_t, index)
+			__field(unsigned int, dtsize)
+		),
+
+		TP_fast_assign(
+			const struct inode *dir = file_inode(file);
+			const struct nfs_inode *nfsi = NFS_I(dir);
+
+			__entry->dev = dir->i_sb->s_dev;
+			__entry->fileid = nfsi->fileid;
+			__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
+			__entry->version = inode_peek_iversion_raw(dir);
+			if (cookie != 0)
+				memcpy(__entry->verifier, verifier,
+				       NFS4_VERIFIER_SIZE);
+			else
+				memset(__entry->verifier, 0,
+				       NFS4_VERIFIER_SIZE);
+			__entry->cookie = cookie;
+			__entry->index = page_index;
+			__entry->dtsize = dtsize;
+		),
+
+		TP_printk(
+			"fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu "
+			"cookie=%s:0x%llx cache_index=%lu dtsize=%u",
+			MAJOR(__entry->dev), MINOR(__entry->dev),
+			(unsigned long long)__entry->fileid, __entry->fhandle,
+			__entry->version, show_nfs4_verifier(__entry->verifier),
+			(unsigned long long)__entry->cookie, __entry->index,
+			__entry->dtsize
+		)
+);
+
+#define DEFINE_NFS_READDIR_EVENT(name) \
+	DEFINE_EVENT(nfs_readdir_event, name, \
+			TP_PROTO( \
+				const struct file *file, \
+				const __be32 *verifier, \
+				u64 cookie, \
+				pgoff_t page_index, \
+				unsigned int dtsize \
+				), \
+			TP_ARGS(file, verifier, cookie, page_index, dtsize))
+
+DEFINE_NFS_READDIR_EVENT(nfs_readdir_cache_fill);
+DEFINE_NFS_READDIR_EVENT(nfs_readdir_uncached);
+
 DECLARE_EVENT_CLASS(nfs_lookup_event,
 		TP_PROTO(
 			const struct inode *dir,
-- 
2.35.1

[PATCH v10 20/26] NFS: Trace effects of readdirplus on the dcache

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Trace the effects of readdirplus on attribute and dentry revalidation.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c      | 5 +++++
 fs/nfs/nfstrace.h | 3 +++
 2 files changed, 8 insertions(+)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index d591d20f7534..8b25a39b1761 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -754,8 +754,12 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry,
 			status = nfs_refresh_inode(d_inode(dentry), entry->fattr);
 			if (!status)
 				nfs_setsecurity(d_inode(dentry), entry->fattr);
+			trace_nfs_readdir_lookup_revalidate(d_inode(parent),
+							    dentry, 0, status);
 			goto out;
 		} else {
+			trace_nfs_readdir_lookup_revalidate_failed(
+				d_inode(parent), dentry, 0);
 			d_invalidate(dentry);
 			dput(dentry);
 			dentry = NULL;
@@ -777,6 +781,7 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry,
 		dentry = alias;
 	}
 	nfs_set_verifier(dentry, dir_verifier);
+	trace_nfs_readdir_lookup(d_inode(parent), dentry, 0);
 out:
 	dput(dentry);
 }
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index c2d0543ecb2d..7c1102b991d0 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -432,6 +432,9 @@ DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_enter);
 DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_exit);
 DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_revalidate_enter);
 DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_revalidate_exit);
+DEFINE_NFS_LOOKUP_EVENT(nfs_readdir_lookup);
+DEFINE_NFS_LOOKUP_EVENT(nfs_readdir_lookup_revalidate_failed);
+DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_readdir_lookup_revalidate);
 
 TRACE_EVENT(nfs_atomic_open_enter,
 		TP_PROTO(
-- 
2.35.1

[PATCH v10 21/26] NFS: Trace effects of the readdirplus heuristic

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Enable tracking of when the readdirplus heuristic causes a page cache
invalidation.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c      | 11 ++++++++++-
 fs/nfs/nfstrace.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8b25a39b1761..8a246df98db5 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1000,6 +1000,8 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 			if (res == -EBADCOOKIE || res == -ENOTSYNC) {
 				invalidate_inode_pages2(desc->file->f_mapping);
 				desc->page_index = 0;
+				trace_nfs_readdir_invalidate_cache_range(
+					inode, 0, MAX_LFS_FILESIZE);
 				return -EAGAIN;
 			}
 			return res;
@@ -1014,6 +1016,9 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 			invalidate_inode_pages2_range(desc->file->f_mapping,
 						      desc->page_index_max + 1,
 						      -1);
+			trace_nfs_readdir_invalidate_cache_range(
+				inode, desc->page_index_max + 1,
+				MAX_LFS_FILESIZE);
 		}
 	}
 	res = nfs_readdir_search_array(desc);
@@ -1163,7 +1168,11 @@ static void nfs_readdir_handle_cache_misses(struct inode *inode,
 	if (desc->ctx->pos == 0 ||
 	    cache_misses <= NFS_READDIR_CACHE_MISS_THRESHOLD)
 		return;
-	invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1);
+	if (invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1) == 0)
+		return;
+	trace_nfs_readdir_invalidate_cache_range(
+		inode, (loff_t)(page_index + 1) << PAGE_SHIFT,
+		MAX_LFS_FILESIZE);
 }
 
 /* The file offset position represents the dirent entry number.  A
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 7c1102b991d0..ec2645d20abf 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -273,6 +273,56 @@ DEFINE_NFS_UPDATE_SIZE_EVENT(wcc);
 DEFINE_NFS_UPDATE_SIZE_EVENT(update);
 DEFINE_NFS_UPDATE_SIZE_EVENT(grow);
 
+DECLARE_EVENT_CLASS(nfs_inode_range_event,
+		TP_PROTO(
+			const struct inode *inode,
+			loff_t range_start,
+			loff_t range_end
+		),
+
+		TP_ARGS(inode, range_start, range_end),
+
+		TP_STRUCT__entry(
+			__field(dev_t, dev)
+			__field(u32, fhandle)
+			__field(u64, fileid)
+			__field(u64, version)
+			__field(loff_t, range_start)
+			__field(loff_t, range_end)
+		),
+
+		TP_fast_assign(
+			const struct nfs_inode *nfsi = NFS_I(inode);
+
+			__entry->dev = inode->i_sb->s_dev;
+			__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
+			__entry->fileid = nfsi->fileid;
+			__entry->version = inode_peek_iversion_raw(inode);
+			__entry->range_start = range_start;
+			__entry->range_end = range_end;
+		),
+
+		TP_printk(
+			"fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu "
+			"range=[%lld, %lld]",
+			MAJOR(__entry->dev), MINOR(__entry->dev),
+			(unsigned long long)__entry->fileid,
+			__entry->fhandle, __entry->version,
+			__entry->range_start, __entry->range_end
+		)
+);
+
+#define DEFINE_NFS_INODE_RANGE_EVENT(name) \
+	DEFINE_EVENT(nfs_inode_range_event, name, \
+			TP_PROTO( \
+				const struct inode *inode, \
+				loff_t range_start, \
+				loff_t range_end \
+			), \
+			TP_ARGS(inode, range_start, range_end))
+
+DEFINE_NFS_INODE_RANGE_EVENT(nfs_readdir_invalidate_cache_range);
+
 DECLARE_EVENT_CLASS(nfs_readdir_event,
 		TP_PROTO(
 			const struct file *file,
-- 
2.35.1

[PATCH v10 22/26] NFS: Clean up page array initialisation/free

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8a246df98db5..4983950de2ad 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -199,20 +199,17 @@ static void nfs_grow_dtsize(struct nfs_readdir_descriptor *desc)
 	nfs_set_dtsize(desc, desc->dtsize << 1);
 }
 
-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,
 					u64 change_attr)
 {
 	struct nfs_cache_array *array;
 
 	array = kmap_atomic(page);
-	nfs_readdir_array_init(array);
 	array->change_attr = change_attr;
 	array->last_cookie = last_cookie;
+	array->size = 0;
+	array->page_full = 0;
+	array->page_is_eof = 0;
 	array->cookies_are_ordered = 1;
 	kunmap_atomic(array);
 }
@@ -220,16 +217,15 @@ static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie,
 /*
  * we are freeing strings created by nfs_add_to_readdir_array()
  */
-static
-void nfs_readdir_clear_array(struct page *page)
+static void nfs_readdir_clear_array(struct page *page)
 {
 	struct nfs_cache_array *array;
-	int i;
+	unsigned int i;
 
 	array = kmap_atomic(page);
 	for (i = 0; i < array->size; i++)
 		kfree(array->array[i].name);
-	nfs_readdir_array_init(array);
+	array->size = 0;
 	kunmap_atomic(array);
 }
 
-- 
2.35.1

[PATCH v10 23/26] NFS: Convert readdir page cache to use a cookie based index

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Instead of using a linear index to address the pages, use the cookie of
the first entry, since that is what we use to match the page anyway.

This allows us to avoid re-reading the entire cache on a seekdir() type
of operation. The latter is very common when re-exporting NFS, and is a
major performance drain.

The change does affect our duplicate cookie detection, since we can no
longer rely on the page index as a linear offset for detecting whether
we looped backwards. However since we no longer do a linear search
through all the pages on each call to nfs_readdir(), this is less of a
concern than it was previously.
The other downside is that invalidate_mapping_pages() no longer can use
the page index to avoid clearing pages that have been read. A subsequent
patch will restore the functionality this provides to the 'ls -l'
heuristic.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/Kconfig         |   4 ++
 fs/nfs/dir.c           | 149 ++++++++++++++++++-----------------------
 include/linux/nfs_fs.h |   2 -
 3 files changed, 69 insertions(+), 86 deletions(-)

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 14a72224b657..47a53b3362b6 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -4,6 +4,10 @@ config NFS_FS
 	depends on INET && FILE_LOCKING && MULTIUSER
 	select LOCKD
 	select SUNRPC
+	select CRYPTO
+	select CRYPTO_HASH
+	select XXHASH
+	select CRYPTO_XXHASH
 	select NFS_ACL_SUPPORT if NFS_V3_ACL
 	help
 	  Choose Y here if you want to access files residing on other
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 4983950de2ad..8c2552d89310 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -39,6 +39,7 @@
 #include <linux/sched.h>
 #include <linux/kmemleak.h>
 #include <linux/xattr.h>
+#include <linux/xxhash.h>
 
 #include "delegation.h"
 #include "iostat.h"
@@ -159,9 +160,7 @@ struct nfs_readdir_descriptor {
 	pgoff_t		page_index_max;
 	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;
@@ -171,7 +170,6 @@ struct nfs_readdir_descriptor {
 	unsigned int	cache_entry_index;
 	unsigned int	buffer_fills;
 	unsigned int	dtsize;
-	signed char duped;
 	bool plus;
 	bool eob;
 	bool eof;
@@ -331,6 +329,28 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
 	return ret;
 }
 
+#define NFS_READDIR_COOKIE_MASK (U32_MAX >> 14)
+/*
+ * Hash algorithm allowing content addressible access to sequences
+ * of directory cookies. Content is addressed by the value of the
+ * cookie index of the first readdir entry in a page.
+ *
+ * The xxhash algorithm is chosen because it is fast, and is supposed
+ * to result in a decent flat distribution of hashes.
+ *
+ * We then select only the first 18 bits to avoid issues with excessive
+ * memory use for the page cache XArray. 18 bits should allow the caching
+ * of 262144 pages of sequences of readdir entries. Since each page holds
+ * 127 readdir entries for a typical 64-bit system, that works out to a
+ * cache of ~ 33 million entries per directory.
+ */
+static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie)
+{
+	if (cookie == 0)
+		return 0;
+	return xxhash(&cookie, sizeof(cookie), 0) & NFS_READDIR_COOKIE_MASK;
+}
+
 static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie,
 				      u64 change_attr)
 {
@@ -352,15 +372,15 @@ static void nfs_readdir_page_unlock_and_put(struct page *page)
 }
 
 static struct page *nfs_readdir_page_get_locked(struct address_space *mapping,
-						pgoff_t index, u64 last_cookie)
+						u64 last_cookie,
+						u64 change_attr)
 {
+	pgoff_t index = nfs_readdir_page_cookie_hash(last_cookie);
 	struct page *page;
-	u64 change_attr;
 
 	page = grab_cache_page(mapping, index);
 	if (!page)
 		return NULL;
-	change_attr = inode_peek_iversion_raw(mapping->host);
 	if (PageUptodate(page)) {
 		if (nfs_readdir_page_validate(page, last_cookie, change_attr))
 			return page;
@@ -371,11 +391,6 @@ static struct page *nfs_readdir_page_get_locked(struct address_space *mapping,
 	return page;
 }
 
-static loff_t nfs_readdir_page_offset(struct page *page)
-{
-	return (loff_t)page->index * (loff_t)nfs_readdir_array_maxentries();
-}
-
 static u64 nfs_readdir_page_last_cookie(struct page *page)
 {
 	struct nfs_cache_array *array;
@@ -408,11 +423,11 @@ static void nfs_readdir_page_set_eof(struct page *page)
 }
 
 static struct page *nfs_readdir_page_get_next(struct address_space *mapping,
-					      pgoff_t index, u64 cookie)
+					      u64 cookie, u64 change_attr)
 {
 	struct page *page;
 
-	page = nfs_readdir_page_get_locked(mapping, index, cookie);
+	page = nfs_readdir_page_get_locked(mapping, cookie, change_attr);
 	if (page) {
 		if (nfs_readdir_page_last_cookie(page) == cookie)
 			return page;
@@ -452,6 +467,13 @@ static void nfs_readdir_seek_next_array(struct nfs_cache_array *array,
 		desc->last_cookie = array->array[0].cookie;
 }
 
+static void nfs_readdir_rewind_search(struct nfs_readdir_descriptor *desc)
+{
+	desc->current_index = 0;
+	desc->last_cookie = 0;
+	desc->page_index = 0;
+}
+
 static int nfs_readdir_search_for_pos(struct nfs_cache_array *array,
 				      struct nfs_readdir_descriptor *desc)
 {
@@ -492,8 +514,7 @@ static bool nfs_readdir_array_cookie_in_range(struct nfs_cache_array *array,
 static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array,
 					 struct nfs_readdir_descriptor *desc)
 {
-	int i;
-	loff_t new_pos;
+	unsigned int i;
 	int status = -EAGAIN;
 
 	if (!nfs_readdir_array_cookie_in_range(array, desc->dir_cookie))
@@ -501,32 +522,10 @@ static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array,
 
 	for (i = 0; i < array->size; i++) {
 		if (array->array[i].cookie == desc->dir_cookie) {
-			struct nfs_inode *nfsi = NFS_I(file_inode(desc->file));
-
-			new_pos = nfs_readdir_page_offset(desc->page) + i;
-			if (desc->attr_gencount != nfsi->attr_gencount) {
-				desc->duped = 0;
-				desc->attr_gencount = nfsi->attr_gencount;
-			} else if (new_pos < desc->prev_index) {
-				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].name, desc->dir_cookie);
-					}
-					status = -ELOOP;
-					goto out;
-				}
-				desc->dup_cookie = desc->dir_cookie;
-				desc->duped = -1;
-			}
 			if (nfs_readdir_use_cookie(desc->file))
 				desc->ctx->pos = desc->dir_cookie;
 			else
-				desc->ctx->pos = new_pos;
-			desc->prev_index = new_pos;
+				desc->ctx->pos = desc->current_index + i;
 			desc->cache_entry_index = i;
 			return 0;
 		}
@@ -538,7 +537,6 @@ static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array,
 			desc->eof = true;
 	} else
 		nfs_readdir_seek_next_array(array, desc);
-out:
 	return status;
 }
 
@@ -785,10 +783,9 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry,
 /* Perform conversion from xdr to cache array */
 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 page **xdr_pages, unsigned int buflen,
+				   struct page **arrays, size_t narrays,
+				   u64 change_attr)
 {
 	struct address_space *mapping = desc->file->f_mapping;
 	struct xdr_stream stream;
@@ -828,18 +825,16 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
 				break;
 			arrays++;
 			*arrays = page = new;
-			desc->page_index_max++;
 		} else {
-			new = nfs_readdir_page_get_next(mapping,
-							page->index + 1,
-							entry->prev_cookie);
+			new = nfs_readdir_page_get_next(
+				mapping, entry->prev_cookie, change_attr);
 			if (!new)
 				break;
 			if (page != *arrays)
 				nfs_readdir_page_unlock_and_put(page);
 			page = new;
-			desc->page_index_max = new->index;
 		}
+		desc->page_index_max++;
 		status = nfs_readdir_add_to_array(entry, page);
 	} while (!status && !entry->eof);
 
@@ -899,6 +894,7 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
 				    __be32 *verf_arg, __be32 *verf_res,
 				    struct page **arrays, size_t narrays)
 {
+	u64 change_attr;
 	struct page **pages;
 	struct page *page = *arrays;
 	struct nfs_entry *entry;
@@ -923,6 +919,7 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
 	if (!pages)
 		goto out;
 
+	change_attr = inode_peek_iversion_raw(inode);
 	status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie, pages,
 					dtsize, verf_res);
 	if (status < 0)
@@ -931,7 +928,7 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
 	pglen = status;
 	if (pglen != 0)
 		status = nfs_readdir_page_filler(desc, entry, pages, pglen,
-						 arrays, narrays);
+						 arrays, narrays, change_attr);
 	else
 		nfs_readdir_page_set_eof(page);
 	desc->buffer_fills++;
@@ -961,9 +958,11 @@ nfs_readdir_page_unlock_and_put_cached(struct nfs_readdir_descriptor *desc)
 static struct page *
 nfs_readdir_page_get_cached(struct nfs_readdir_descriptor *desc)
 {
-	return nfs_readdir_page_get_locked(desc->file->f_mapping,
-					   desc->page_index,
-					   desc->last_cookie);
+	struct address_space *mapping = desc->file->f_mapping;
+	u64 change_attr = inode_peek_iversion_raw(mapping->host);
+
+	return nfs_readdir_page_get_locked(mapping, desc->last_cookie,
+					   change_attr);
 }
 
 /*
@@ -995,7 +994,7 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 			trace_nfs_readdir_cache_fill_done(inode, res);
 			if (res == -EBADCOOKIE || res == -ENOTSYNC) {
 				invalidate_inode_pages2(desc->file->f_mapping);
-				desc->page_index = 0;
+				nfs_readdir_rewind_search(desc);
 				trace_nfs_readdir_invalidate_cache_range(
 					inode, 0, MAX_LFS_FILESIZE);
 				return -EAGAIN;
@@ -1009,12 +1008,10 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 		    memcmp(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf))) {
 			memcpy(nfsi->cookieverf, verf,
 			       sizeof(nfsi->cookieverf));
-			invalidate_inode_pages2_range(desc->file->f_mapping,
-						      desc->page_index_max + 1,
+			invalidate_inode_pages2_range(desc->file->f_mapping, 1,
 						      -1);
 			trace_nfs_readdir_invalidate_cache_range(
-				inode, desc->page_index_max + 1,
-				MAX_LFS_FILESIZE);
+				inode, 1, MAX_LFS_FILESIZE);
 		}
 	}
 	res = nfs_readdir_search_array(desc);
@@ -1030,11 +1027,6 @@ static int readdir_search_pagecache(struct nfs_readdir_descriptor *desc)
 	int res;
 
 	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;
@@ -1072,8 +1064,6 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc,
 			desc->ctx->pos = desc->dir_cookie;
 		else
 			desc->ctx->pos++;
-		if (desc->duped != 0)
-			desc->duped = 1;
 	}
 	if (array->page_is_eof)
 		desc->eof = !desc->eob;
@@ -1115,7 +1105,6 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 	desc->page_index = 0;
 	desc->cache_entry_index = 0;
 	desc->last_cookie = desc->dir_cookie;
-	desc->duped = 0;
 	desc->page_index_max = 0;
 
 	trace_nfs_readdir_uncached(desc->file, desc->verf, desc->last_cookie,
@@ -1148,6 +1137,8 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 	for (i = 0; i < sz && arrays[i]; i++)
 		nfs_readdir_page_array_free(arrays[i]);
 out:
+	if (!nfs_readdir_use_cookie(desc->file))
+		nfs_readdir_rewind_search(desc);
 	desc->page_index_max = -1;
 	kfree(arrays);
 	dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status);
@@ -1158,17 +1149,14 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 
 static void nfs_readdir_handle_cache_misses(struct inode *inode,
 					    struct nfs_readdir_descriptor *desc,
-					    pgoff_t page_index,
 					    unsigned int cache_misses)
 {
 	if (desc->ctx->pos == 0 ||
 	    cache_misses <= NFS_READDIR_CACHE_MISS_THRESHOLD)
 		return;
-	if (invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1) == 0)
+	if (invalidate_mapping_pages(inode->i_mapping, 0, -1) == 0)
 		return;
-	trace_nfs_readdir_invalidate_cache_range(
-		inode, (loff_t)(page_index + 1) << PAGE_SHIFT,
-		MAX_LFS_FILESIZE);
+	trace_nfs_readdir_invalidate_cache_range(inode, 0, MAX_LFS_FILESIZE);
 }
 
 /* The file offset position represents the dirent entry number.  A
@@ -1183,7 +1171,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	struct nfs_open_dir_context *dir_ctx = file->private_data;
 	struct nfs_readdir_descriptor *desc;
 	unsigned int cache_hits, cache_misses;
-	pgoff_t page_index;
 	int res;
 
 	dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n",
@@ -1208,10 +1195,7 @@ static int nfs_readdir(struct file *file, struct dir_context *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;
-	page_index = dir_ctx->page_index;
-	desc->page_index = page_index;
+	desc->page_index = dir_ctx->page_index;
 	desc->last_cookie = dir_ctx->last_cookie;
 	desc->attr_gencount = dir_ctx->attr_gencount;
 	desc->eof = dir_ctx->eof;
@@ -1227,7 +1211,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	}
 
 	desc->plus = nfs_use_readdirplus(inode, ctx, cache_hits, cache_misses);
-	nfs_readdir_handle_cache_misses(inode, desc, page_index, cache_misses);
+	nfs_readdir_handle_cache_misses(inode, desc, cache_misses);
 
 	do {
 		res = readdir_search_pagecache(desc);
@@ -1247,7 +1231,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 		}
 		if (res == -ETOOSMALL && desc->plus) {
 			nfs_zap_caches(inode);
-			desc->page_index = 0;
 			desc->plus = false;
 			desc->eof = false;
 			continue;
@@ -1261,9 +1244,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 
 	spin_lock(&file->f_lock);
 	dir_ctx->dir_cookie = desc->dir_cookie;
-	dir_ctx->dup_cookie = desc->dup_cookie;
 	dir_ctx->last_cookie = desc->last_cookie;
-	dir_ctx->duped = desc->duped;
 	dir_ctx->attr_gencount = desc->attr_gencount;
 	dir_ctx->page_index = desc->page_index;
 	dir_ctx->eof = desc->eof;
@@ -1306,13 +1287,13 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 	if (offset != filp->f_pos) {
 		filp->f_pos = offset;
 		dir_ctx->page_index = 0;
-		if (!nfs_readdir_use_cookie(filp))
+		if (!nfs_readdir_use_cookie(filp)) {
 			dir_ctx->dir_cookie = 0;
-		else
+			dir_ctx->last_cookie = 0;
+		} else {
 			dir_ctx->dir_cookie = offset;
-		if (offset == 0)
-			memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf));
-		dir_ctx->duped = 0;
+			dir_ctx->last_cookie = offset;
+		}
 		dir_ctx->eof = false;
 	}
 	spin_unlock(&filp->f_lock);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 20a4cf0acad2..42aad886d3c0 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -106,11 +106,9 @@ struct nfs_open_dir_context {
 	unsigned long attr_gencount;
 	__be32	verf[NFS_DIR_VERIFIER_SIZE];
 	__u64 dir_cookie;
-	__u64 dup_cookie;
 	__u64 last_cookie;
 	pgoff_t page_index;
 	unsigned int dtsize;
-	signed char duped;
 	bool eof;
 	struct rcu_head rcu_head;
 };
-- 
2.35.1

[PATCH v10 24/26] NFS: Fix up forced readdirplus

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Avoid clearing the entire readdir page cache if we're just doing forced
readdirplus for the 'ls -l' heuristic.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c           | 56 +++++++++++++++++++++++++++++-------------
 fs/nfs/nfstrace.h      |  1 +
 include/linux/nfs_fs.h |  1 +
 3 files changed, 41 insertions(+), 17 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8c2552d89310..f6aac1e8a8b9 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -170,6 +170,7 @@ struct nfs_readdir_descriptor {
 	unsigned int	cache_entry_index;
 	unsigned int	buffer_fills;
 	unsigned int	dtsize;
+	bool clear_cache;
 	bool plus;
 	bool eob;
 	bool eof;
@@ -227,6 +228,13 @@ static void nfs_readdir_clear_array(struct page *page)
 	kunmap_atomic(array);
 }
 
+static void nfs_readdir_page_reinit_array(struct page *page, u64 last_cookie,
+					  u64 change_attr)
+{
+	nfs_readdir_clear_array(page);
+	nfs_readdir_page_init_array(page, last_cookie, change_attr);
+}
+
 static struct page *
 nfs_readdir_page_array_alloc(u64 last_cookie, gfp_t gfp_flags)
 {
@@ -428,12 +436,11 @@ static struct page *nfs_readdir_page_get_next(struct address_space *mapping,
 	struct page *page;
 
 	page = nfs_readdir_page_get_locked(mapping, cookie, change_attr);
-	if (page) {
-		if (nfs_readdir_page_last_cookie(page) == cookie)
-			return page;
-		nfs_readdir_page_unlock_and_put(page);
-	}
-	return NULL;
+	if (!page)
+		return NULL;
+	if (nfs_readdir_page_last_cookie(page) != cookie)
+		nfs_readdir_page_reinit_array(page, cookie, change_attr);
+	return page;
 }
 
 static inline
@@ -960,9 +967,15 @@ nfs_readdir_page_get_cached(struct nfs_readdir_descriptor *desc)
 {
 	struct address_space *mapping = desc->file->f_mapping;
 	u64 change_attr = inode_peek_iversion_raw(mapping->host);
+	u64 cookie = desc->last_cookie;
+	struct page *page;
 
-	return nfs_readdir_page_get_locked(mapping, desc->last_cookie,
-					   change_attr);
+	page = nfs_readdir_page_get_locked(mapping, cookie, change_attr);
+	if (!page)
+		return NULL;
+	if (desc->clear_cache && !nfs_readdir_page_needs_filling(page))
+		nfs_readdir_page_reinit_array(page, cookie, change_attr);
+	return page;
 }
 
 /*
@@ -1013,6 +1026,7 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 			trace_nfs_readdir_invalidate_cache_range(
 				inode, 1, MAX_LFS_FILESIZE);
 		}
+		desc->clear_cache = false;
 	}
 	res = nfs_readdir_search_array(desc);
 	if (res == 0)
@@ -1147,16 +1161,17 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 
 #define NFS_READDIR_CACHE_MISS_THRESHOLD (16UL)
 
-static void nfs_readdir_handle_cache_misses(struct inode *inode,
+static bool nfs_readdir_handle_cache_misses(struct inode *inode,
 					    struct nfs_readdir_descriptor *desc,
-					    unsigned int cache_misses)
+					    unsigned int cache_misses,
+					    bool force_clear)
 {
-	if (desc->ctx->pos == 0 ||
-	    cache_misses <= NFS_READDIR_CACHE_MISS_THRESHOLD)
-		return;
-	if (invalidate_mapping_pages(inode->i_mapping, 0, -1) == 0)
-		return;
-	trace_nfs_readdir_invalidate_cache_range(inode, 0, MAX_LFS_FILESIZE);
+	if (desc->ctx->pos == 0 || !desc->plus)
+		return false;
+	if (cache_misses <= NFS_READDIR_CACHE_MISS_THRESHOLD && !force_clear)
+		return false;
+	trace_nfs_readdir_force_readdirplus(inode);
+	return true;
 }
 
 /* The file offset position represents the dirent entry number.  A
@@ -1171,6 +1186,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	struct nfs_open_dir_context *dir_ctx = file->private_data;
 	struct nfs_readdir_descriptor *desc;
 	unsigned int cache_hits, cache_misses;
+	bool force_clear;
 	int res;
 
 	dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n",
@@ -1203,6 +1219,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf));
 	cache_hits = atomic_xchg(&dir_ctx->cache_hits, 0);
 	cache_misses = atomic_xchg(&dir_ctx->cache_misses, 0);
+	force_clear = dir_ctx->force_clear;
 	spin_unlock(&file->f_lock);
 
 	if (desc->eof) {
@@ -1211,7 +1228,9 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	}
 
 	desc->plus = nfs_use_readdirplus(inode, ctx, cache_hits, cache_misses);
-	nfs_readdir_handle_cache_misses(inode, desc, cache_misses);
+	force_clear = nfs_readdir_handle_cache_misses(inode, desc, cache_misses,
+						      force_clear);
+	desc->clear_cache = force_clear;
 
 	do {
 		res = readdir_search_pagecache(desc);
@@ -1240,6 +1259,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 
 		nfs_do_filldir(desc, nfsi->cookieverf);
 		nfs_readdir_page_unlock_and_put_cached(desc);
+		if (desc->page_index == desc->page_index_max)
+			desc->clear_cache = force_clear;
 	} while (!desc->eob && !desc->eof);
 
 	spin_lock(&file->f_lock);
@@ -1247,6 +1268,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	dir_ctx->last_cookie = desc->last_cookie;
 	dir_ctx->attr_gencount = desc->attr_gencount;
 	dir_ctx->page_index = desc->page_index;
+	dir_ctx->force_clear = force_clear;
 	dir_ctx->eof = desc->eof;
 	dir_ctx->dtsize = desc->dtsize;
 	memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf));
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index ec2645d20abf..59f4ca803fd0 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -160,6 +160,7 @@ DEFINE_NFS_INODE_EVENT(nfs_fsync_enter);
 DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit);
 DEFINE_NFS_INODE_EVENT(nfs_access_enter);
 DEFINE_NFS_INODE_EVENT_DONE(nfs_set_cache_invalid);
+DEFINE_NFS_INODE_EVENT(nfs_readdir_force_readdirplus);
 DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_cache_fill_done);
 DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_uncached_done);
 
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 42aad886d3c0..3893386ceaed 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -109,6 +109,7 @@ struct nfs_open_dir_context {
 	__u64 last_cookie;
 	pgoff_t page_index;
 	unsigned int dtsize;
+	bool force_clear;
 	bool eof;
 	struct rcu_head rcu_head;
 };
-- 
2.35.1

[PATCH v10 25/26] NFS: Optimise away the previous cookie field

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Replace the 'previous cookie' field in struct nfs_entry with the
array->last_cookie.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c            | 26 ++++++++++++++------------
 fs/nfs/nfs2xdr.c        |  1 -
 fs/nfs/nfs3xdr.c        |  1 -
 fs/nfs/nfs4xdr.c        |  1 -
 include/linux/nfs_xdr.h |  3 +--
 5 files changed, 15 insertions(+), 17 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index f6aac1e8a8b9..033249a72e92 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -301,19 +301,20 @@ static int nfs_readdir_array_can_expand(struct nfs_cache_array *array)
 	return 0;
 }
 
-static
-int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
+static int nfs_readdir_page_array_append(struct page *page,
+					 const struct nfs_entry *entry,
+					 u64 *cookie)
 {
 	struct nfs_cache_array *array;
 	struct nfs_cache_array_entry *cache_entry;
 	const char *name;
-	int ret;
+	int ret = -ENOMEM;
 
 	name = nfs_readdir_copy_name(entry->name, entry->len);
-	if (!name)
-		return -ENOMEM;
 
 	array = kmap_atomic(page);
+	if (!name)
+		goto out;
 	ret = nfs_readdir_array_can_expand(array);
 	if (ret) {
 		kfree(name);
@@ -321,7 +322,7 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
 	}
 
 	cache_entry = &array->array[array->size];
-	cache_entry->cookie = entry->prev_cookie;
+	cache_entry->cookie = array->last_cookie;
 	cache_entry->ino = entry->ino;
 	cache_entry->d_type = entry->d_type;
 	cache_entry->name_len = entry->len;
@@ -333,6 +334,7 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
 	if (entry->eof != 0)
 		nfs_readdir_array_set_eof(array);
 out:
+	*cookie = array->last_cookie;
 	kunmap_atomic(array);
 	return ret;
 }
@@ -798,6 +800,7 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
 	struct xdr_stream stream;
 	struct xdr_buf buf;
 	struct page *scratch, *new, *page = *arrays;
+	u64 cookie;
 	int status;
 
 	scratch = alloc_page(GFP_KERNEL);
@@ -819,22 +822,21 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
 			nfs_prime_dcache(file_dentry(desc->file), entry,
 					desc->dir_verifier);
 
-		status = nfs_readdir_add_to_array(entry, page);
+		status = nfs_readdir_page_array_append(page, entry, &cookie);
 		if (status != -ENOSPC)
 			continue;
 
 		if (page->mapping != mapping) {
 			if (!--narrays)
 				break;
-			new = nfs_readdir_page_array_alloc(entry->prev_cookie,
-							   GFP_KERNEL);
+			new = nfs_readdir_page_array_alloc(cookie, GFP_KERNEL);
 			if (!new)
 				break;
 			arrays++;
 			*arrays = page = new;
 		} else {
-			new = nfs_readdir_page_get_next(
-				mapping, entry->prev_cookie, change_attr);
+			new = nfs_readdir_page_get_next(mapping, cookie,
+							change_attr);
 			if (!new)
 				break;
 			if (page != *arrays)
@@ -842,7 +844,7 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
 			page = new;
 		}
 		desc->page_index_max++;
-		status = nfs_readdir_add_to_array(entry, page);
+		status = nfs_readdir_page_array_append(page, entry, &cookie);
 	} while (!status && !entry->eof);
 
 	switch (status) {
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 3d5ba43f44bb..05c3b4b2b3dd 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -955,7 +955,6 @@ int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 	 * The type (size and byte order) of nfscookie isn't defined in
 	 * RFC 1094.  This implementation assumes that it's an XDR uint32.
 	 */
-	entry->prev_cookie = entry->cookie;
 	p = xdr_inline_decode(xdr, 4);
 	if (unlikely(!p))
 		return -EAGAIN;
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index d6779ceeb39e..3b0b650c9c5a 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -2024,7 +2024,6 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 			zero_nfs_fh3(entry->fh);
 	}
 
-	entry->prev_cookie = entry->cookie;
 	entry->cookie = new_cookie;
 
 	return 0;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index b7780b97dc4d..86a5f6516928 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7508,7 +7508,6 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 	if (entry->fattr->valid & NFS_ATTR_FATTR_TYPE)
 		entry->d_type = nfs_umode_to_dtype(entry->fattr->mode);
 
-	entry->prev_cookie = entry->cookie;
 	entry->cookie = new_cookie;
 
 	return 0;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 728cb0c1f0b6..82f7c2730b9a 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -745,8 +745,7 @@ struct nfs_auth_info {
  */
 struct nfs_entry {
 	__u64			ino;
-	__u64			cookie,
-				prev_cookie;
+	__u64			cookie;
 	const char *		name;
 	unsigned int		len;
 	int			eof;
-- 
2.35.1

[PATCH v10 26/26] NFS: Cache all entries in the readdirplus reply

[trondmy]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

Even if we're not able to cache all the entries in the readdir buffer,
let's ensure that we do prime the dcache.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/dir.c | 40 ++++++++++++++++++++++++++--------------
 1 file changed, 26 insertions(+), 14 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 033249a72e92..7e12102b29e7 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -789,6 +789,21 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry,
 	dput(dentry);
 }
 
+static int nfs_readdir_entry_decode(struct nfs_readdir_descriptor *desc,
+				    struct nfs_entry *entry,
+				    struct xdr_stream *stream)
+{
+	int ret;
+
+	if (entry->fattr->label)
+		entry->fattr->label->len = NFS4_MAXLABELLEN;
+	ret = xdr_decode(desc, entry, stream);
+	if (ret || !desc->plus)
+		return ret;
+	nfs_prime_dcache(file_dentry(desc->file), entry, desc->dir_verifier);
+	return 0;
+}
+
 /* Perform conversion from xdr to cache array */
 static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
 				   struct nfs_entry *entry,
@@ -811,17 +826,10 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
 	xdr_set_scratch_page(&stream, scratch);
 
 	do {
-		if (entry->fattr->label)
-			entry->fattr->label->len = NFS4_MAXLABELLEN;
-
-		status = xdr_decode(desc, entry, &stream);
+		status = nfs_readdir_entry_decode(desc, entry, &stream);
 		if (status != 0)
 			break;
 
-		if (desc->plus)
-			nfs_prime_dcache(file_dentry(desc->file), entry,
-					desc->dir_verifier);
-
 		status = nfs_readdir_page_array_append(page, entry, &cookie);
 		if (status != -ENOSPC)
 			continue;
@@ -849,15 +857,19 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
 
 	switch (status) {
 	case -EBADCOOKIE:
-		if (entry->eof) {
-			nfs_readdir_page_set_eof(page);
-			status = 0;
-		}
-		break;
-	case -ENOSPC:
+		if (!entry->eof)
+			break;
+		nfs_readdir_page_set_eof(page);
+		fallthrough;
 	case -EAGAIN:
 		status = 0;
 		break;
+	case -ENOSPC:
+		status = 0;
+		if (!desc->plus)
+			break;
+		while (!nfs_readdir_entry_decode(desc, entry, &stream))
+			;
 	}
 
 	if (page != *arrays)
-- 
2.35.1