Merge tag 'nfs-for-5.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Features:

   - Switch NFS to use readahead instead of the obsolete readpages.

   - Readdir fixes to improve cacheability of large directories when
     there are multiple readers and writers.

   - Readdir performance improvements when doing a seekdir() immediately
     after opening the directory (common when re-exporting NFS).

   - NFS swap improvements from Neil Brown.

   - Loosen up memory allocation to permit direct reclaim and write back
     in cases where there is no danger of deadlocking the writeback code
     or NFS swap.

   - Avoid sillyrename when the NFSv4 server claims to support the
     necessary features to recover the unlinked but open file after
     reboot.

  Bugfixes:

   - Patch from Olga to add a mount option to control NFSv4.1 session
     trunking discovery, and default it to being off.

   - Fix a lockup in nfs_do_recoalesce().

   - Two fixes for list iterator variables being used when pointing to
     the list head.

   - Fix a kernel memory scribble when reading from a non-socket
     transport in /sys/kernel/sunrpc.

   - Fix a race where reconnecting to a server could leave the TCP
     socket stuck forever in the connecting state.

   - Patch from Neil to fix a shutdown race which can leave the SUNRPC
     transport timer primed after we free the struct xprt itself.

   - Patch from Xin Xiong to fix reference count leaks in the NFSv4.2
     copy offload.

   - Sunrpc patch from Olga to avoid resending a task on an offlined
     transport.

  Cleanups:

   - Patches from Dave Wysochanski to clean up the fscache code"

* tag 'nfs-for-5.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (91 commits)
  NFSv4/pNFS: Fix another issue with a list iterator pointing to the head
  NFS: Don't loop forever in nfs_do_recoalesce()
  SUNRPC: Don't return error values in sysfs read of closed files
  SUNRPC: Do not dereference non-socket transports in sysfs
  NFSv4.1: don't retry BIND_CONN_TO_SESSION on session error
  SUNRPC don't resend a task on an offlined transport
  NFS: replace usage of found with dedicated list iterator variable
  SUNRPC: avoid race between mod_timer() and del_timer_sync()
  pNFS/files: Ensure pNFS allocation modes are consistent with nfsiod
  pNFS/flexfiles: Ensure pNFS allocation modes are consistent with nfsiod
  NFSv4/pnfs: Ensure pNFS allocation modes are consistent with nfsiod
  NFS: Avoid writeback threads getting stuck in mempool_alloc()
  NFS: nfsiod should not block forever in mempool_alloc()
  SUNRPC: Make the rpciod and xprtiod slab allocation modes consistent
  SUNRPC: Fix unx_lookup_cred() allocation
  NFS: Fix memory allocation in rpc_alloc_task()
  NFS: Fix memory allocation in rpc_malloc()
  SUNRPC: Improve accuracy of socket ENOBUFS determination
  SUNRPC: Replace internal use of SOCKWQ_ASYNC_NOSPACE
  SUNRPC: Fix socket waits for write buffer space
  ...

1 files changed, 19 insertions, 26 deletions

diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 784120cc217e..b48b9259e02c 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -46,11 +46,6 @@
 #define NFS_MAX_TRANSPORTS 16
 
 /*
- * These are the default flags for swap requests
- */
-#define NFS_RPC_SWAPFLAGS		(RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS)
-
-/*
  * Size of the NFS directory verifier
  */
 #define NFS_DIR_VERIFIER_SIZE		2
@@ -101,13 +96,17 @@ 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;
-	__u64 dup_cookie;
+	__u64 last_cookie;
 	pgoff_t page_index;
-	signed char duped;
+	unsigned int dtsize;
+	bool force_clear;
 	bool eof;
+	struct rcu_head rcu_head;
 };
 
 /*
@@ -247,7 +246,6 @@ struct nfs4_copy_state {
 #define NFS_INO_INVALID_ATIME	BIT(2)		/* cached atime is invalid */
 #define NFS_INO_INVALID_ACCESS	BIT(3)		/* cached access cred invalid */
 #define NFS_INO_INVALID_ACL	BIT(4)		/* cached acls are invalid */
-#define NFS_INO_REVAL_PAGECACHE	BIT(5)		/* must revalidate pagecache */
 #define NFS_INO_REVAL_FORCED	BIT(6)		/* force revalidation ignoring a delegation */
 #define NFS_INO_INVALID_LABEL	BIT(7)		/* cached label is invalid */
 #define NFS_INO_INVALID_CHANGE	BIT(8)		/* cached change is invalid */
@@ -273,12 +271,11 @@ 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 */
@@ -355,17 +352,15 @@ static inline void nfs_mark_for_revalidate(struct inode *inode)
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	spin_lock(&inode->i_lock);
-	nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE
-		| NFS_INO_INVALID_ACCESS
-		| NFS_INO_INVALID_ACL
-		| NFS_INO_INVALID_CHANGE
-		| NFS_INO_INVALID_CTIME;
+	nfsi->cache_validity |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL |
+				NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME |
+				NFS_INO_INVALID_SIZE;
 	if (S_ISDIR(inode->i_mode))
 		nfsi->cache_validity |= NFS_INO_INVALID_DATA;
 	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;
 }
@@ -513,10 +508,10 @@ static inline const struct cred *nfs_file_cred(struct file *file)
  * linux/fs/nfs/direct.c
  */
 extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *);
-extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
-			struct iov_iter *iter);
-extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
-			struct iov_iter *iter);
+ssize_t nfs_file_direct_read(struct kiocb *iocb,
+			     struct iov_iter *iter, bool swap);
+ssize_t nfs_file_direct_write(struct kiocb *iocb,
+			      struct iov_iter *iter, bool swap);
 
 /*
  * linux/fs/nfs/dir.c
@@ -585,24 +580,22 @@ extern int nfs_wb_all(struct inode *inode);
 extern int nfs_wb_page(struct inode *inode, struct page *page);
 int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio);
 extern int  nfs_commit_inode(struct inode *, int);
-extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail);
+extern struct nfs_commit_data *nfs_commitdata_alloc(void);
 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;
 }
 
 /*
  * linux/fs/nfs/read.c
  */
 extern int  nfs_readpage(struct file *, struct page *);
-extern int  nfs_readpages(struct file *, struct address_space *,
-		struct list_head *, unsigned);
+void nfs_readahead(struct readahead_control *);
 
 /*
  * inline functions