Merge tag 'nfs-for-6.4-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "New Features:

   - Convert the readdir path to use folios

   - Convert the NFS fscache code to use netfs

  Bugfixes and Cleanups:

   - Always send a RECLAIM_COMPLETE after establishing a lease

   - Simplify sysctl registrations and other cleanups

   - Handle out-of-order write replies on NFS v3

   - Have sunrpc call_bind_status use standard hard/soft task semantics

   - Other minor cleanups"

* tag 'nfs-for-6.4-1' of git://git.linux-nfs.org/projects/anna/linux-nfs:
  NFSv4.2: Rework scratch handling for READ_PLUS
  NFS: Cleanup unused rpc_clnt variable
  NFS: set varaiable nfs_netfs_debug_id storage-class-specifier to static
  SUNRPC: remove the maximum number of retries in call_bind_status
  NFS: Convert readdir page array functions to use a folio
  NFS: Convert the readdir array-of-pages into an array-of-folios
  NFSv3: handle out-of-order write replies.
  NFS: Remove fscache specific trace points and NFS_INO_FSCACHE bit
  NFS: Remove all NFSIOS_FSCACHE counters due to conversion to netfs API
  NFS: Convert buffered read paths to use netfs when fscache is enabled
  NFS: Configure support for netfs when NFS fscache is configured
  NFS: Rename readpage_async_filler to nfs_read_add_folio
  sunrpc: simplify one-level sysctl registration for debug_table
  sunrpc: move sunrpc_table and proc routines above
  sunrpc: simplify one-level sysctl registration for xs_tunables_table
  sunrpc: simplify one-level sysctl registration for xr_tunables_table
  nfs: simplify two-level sysctl registration for nfs_cb_sysctls
  nfs: simplify two-level sysctl registration for nfs4_cb_sysctls
  lockd: simplify two-level sysctl registration for nlm_sysctls
  NFSv4.1: Always send a RECLAIM_COMPLETE after establishing lease

5 files changed, 65 insertions, 29 deletions

diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index bf89fe6fc3ba..279262057a92 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -31,6 +31,10 @@
 #include <linux/sunrpc/auth.h>
 #include <linux/sunrpc/clnt.h>
 
+#ifdef CONFIG_NFS_FSCACHE
+#include <linux/netfs.h>
+#endif
+
 #include <linux/nfs.h>
 #include <linux/nfs2.h>
 #include <linux/nfs3.h>
@@ -191,6 +195,39 @@ struct nfs_inode {
 	/* Open contexts for shared mmap writes */
 	struct list_head	open_files;
 
+	/* Keep track of out-of-order replies.
+	 * The ooo array contains start/end pairs of
+	 * numbers from the changeid sequence when
+	 * the inode's iversion has been updated.
+	 * It also contains end/start pair (i.e. reverse order)
+	 * of sections of the changeid sequence that have
+	 * been seen in replies from the server.
+	 * Normally these should match and when both
+	 * A:B and B:A are found in ooo, they are both removed.
+	 * And if a reply with A:B causes an iversion update
+	 * of A:B, then neither are added.
+	 * When a reply has pre_change that doesn't match
+	 * iversion, then the changeid pair and any consequent
+	 * change in iversion ARE added.  Later replies
+	 * might fill in the gaps, or possibly a gap is caused
+	 * by a change from another client.
+	 * When a file or directory is opened, if the ooo table
+	 * is not empty, then we assume the gaps were due to
+	 * another client and we invalidate the cached data.
+	 *
+	 * We can only track a limited number of concurrent gaps.
+	 * Currently that limit is 16.
+	 * We allocate the table on demand.  If there is insufficient
+	 * memory, then we probably cannot cache the file anyway
+	 * so there is no loss.
+	 */
+	struct {
+		int cnt;
+		struct {
+			u64 start, end;
+		} gap[16];
+	} *ooo;
+
 #if IS_ENABLED(CONFIG_NFS_V4)
 	struct nfs4_cached_acl	*nfs4_acl;
         /* NFSv4 state */
@@ -204,14 +241,15 @@ struct nfs_inode {
 	/* how many bytes have been written/read and how many bytes queued up */
 	__u64 write_io;
 	__u64 read_io;
-#ifdef CONFIG_NFS_FSCACHE
-	struct fscache_cookie	*fscache;
-#endif
-	struct inode		vfs_inode;
-
 #ifdef CONFIG_NFS_V4_2
 	struct nfs4_xattr_cache *xattr_cache;
 #endif
+	union {
+		struct inode		vfs_inode;
+#ifdef CONFIG_NFS_FSCACHE
+		struct netfs_inode	netfs; /* netfs context and VFS inode */
+#endif
+	};
 };
 
 struct nfs4_copy_state {
@@ -276,7 +314,6 @@ struct nfs4_copy_state {
 #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_LAYOUTCOMMIT	(9)		/* layoutcommit required */
 #define NFS_INO_LAYOUTCOMMITTING (10)		/* layoutcommit inflight */
 #define NFS_INO_LAYOUTSTATS	(11)		/* layoutstats inflight */
@@ -329,15 +366,6 @@ static inline int NFS_STALE(const struct inode *inode)
 	return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
 }
 
-static inline struct fscache_cookie *nfs_i_fscache(struct inode *inode)
-{
-#ifdef CONFIG_NFS_FSCACHE
-	return NFS_I(inode)->fscache;
-#else
-	return NULL;
-#endif
-}
-
 static inline __u64 NFS_FILEID(const struct inode *inode)
 {
 	return NFS_I(inode)->fileid;
@@ -617,6 +645,20 @@ nfs_fileid_to_ino_t(u64 fileid)
 	return ino;
 }
 
+static inline void nfs_ooo_clear(struct nfs_inode *nfsi)
+{
+	nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER;
+	kfree(nfsi->ooo);
+	nfsi->ooo = NULL;
+}
+
+static inline bool nfs_ooo_test(struct nfs_inode *nfsi)
+{
+	return (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) ||
+		(nfsi->ooo && nfsi->ooo->cnt > 0);
+
+}
+
 #define NFS_JUKEBOX_RETRY_TIME (5 * HZ)
 
 /* We need to block new opens while a file is being unlinked.
diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h
index 027874c36c88..8d946089d151 100644
--- a/include/linux/nfs_iostat.h
+++ b/include/linux/nfs_iostat.h
@@ -119,16 +119,4 @@ enum nfs_stat_eventcounters {
 	__NFSIOS_COUNTSMAX,
 };
 
-/*
- * NFS local caching servicing counters
- */
-enum nfs_stat_fscachecounters {
-	NFSIOS_FSCACHE_PAGES_READ_OK,
-	NFSIOS_FSCACHE_PAGES_READ_FAIL,
-	NFSIOS_FSCACHE_PAGES_WRITTEN_OK,
-	NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL,
-	NFSIOS_FSCACHE_PAGES_UNCACHED,
-	__NFSIOS_FSCACHEMAX,
-};
-
 #endif	/* _LINUX_NFS_IOSTAT */
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index a2f1ca657623..aa9f4c6ebe26 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -105,6 +105,9 @@ struct nfs_pageio_descriptor {
 	struct pnfs_layout_segment *pg_lseg;
 	struct nfs_io_completion *pg_io_completion;
 	struct nfs_direct_req	*pg_dreq;
+#ifdef CONFIG_NFS_FSCACHE
+	void			*pg_netfs;
+#endif
 	unsigned int		pg_bsize;	/* default bsize for mirrors */
 
 	u32			pg_mirror_count;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index e86cf6642d21..29a1b39794bf 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -670,6 +670,7 @@ struct nfs_pgio_res {
 		struct {
 			unsigned int		replen;		/* used by read */
 			int			eof;		/* used by read */
+			void *			scratch;	/* used by read */
 		};
 		struct {
 			struct nfs_writeverf *	verf;		/* used by write */
@@ -1619,6 +1620,9 @@ struct nfs_pgio_header {
 	const struct nfs_rw_ops	*rw_ops;
 	struct nfs_io_completion *io_completion;
 	struct nfs_direct_req	*dreq;
+#ifdef CONFIG_NFS_FSCACHE
+	void			*netfs;
+#endif
 
 	int			pnfs_error;
 	int			error;		/* merge with pnfs_error */
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index b8ca3ecaf8d7..8ada7dc802d3 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -90,8 +90,7 @@ struct rpc_task {
 #endif
 	unsigned char		tk_priority : 2,/* Task priority */
 				tk_garb_retry : 2,
-				tk_cred_retry : 2,
-				tk_rebind_retry : 2;
+				tk_cred_retry : 2;
 };
 
 typedef void			(*rpc_action)(struct rpc_task *);