Merge tag 'nfs-for-5.1-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Stable fixes:
   - Fixes for NFS I/O request leakages
   - Fix error handling paths in the NFS I/O recoalescing code
   - Reinitialise NFSv4.1 sequence results before retransmitting a
     request
   - Fix a soft lockup in the delegation recovery code
   - Bulk destroy of layouts needs to be safe w.r.t. umount
   - Prevent thundering herd issues when the SUNRPC socket is not
     connected
   - Respect RPC call timeouts when retrying transmission

  Features:
   - Convert rpc auth layer to use xdr_streams
   - Config option to disable insecure RPCSEC_GSS crypto types
   - Reduce size of RPC receive buffers
   - Readdirplus optimization by cache mechanism
   - Convert SUNRPC socket send code to use iov_iter()
   - SUNRPC micro-optimisations to avoid indirect calls
   - Add support for the pNFS LAYOUTERROR operation and use it with the
     pNFS/flexfiles driver
   - Add trace events to report non-zero NFS status codes
   - Various removals of unnecessary dprintks

  Bugfixes and cleanups:
   - Fix a number of sparse warnings and documentation format warnings
   - Fix nfs_parse_devname to not modify it's argument
   - Fix potential corruption of page being written through pNFS/blocks
   - fix xfstest generic/099 failures on nfsv3
   - Avoid NFSv4.1 "false retries" when RPC calls are interrupted
   - Abort I/O early if the pNFS/flexfiles layout segment was
     invalidated
   - Avoid unnecessary pNFS/flexfiles layout invalidations"

* tag 'nfs-for-5.1-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (90 commits)
  SUNRPC: Take the transport send lock before binding+connecting
  SUNRPC: Micro-optimise when the task is known not to be sleeping
  SUNRPC: Check whether the task was transmitted before rebind/reconnect
  SUNRPC: Remove redundant calls to RPC_IS_QUEUED()
  SUNRPC: Clean up
  SUNRPC: Respect RPC call timeouts when retrying transmission
  SUNRPC: Fix up RPC back channel transmission
  SUNRPC: Prevent thundering herd when the socket is not connected
  SUNRPC: Allow dynamic allocation of back channel slots
  NFSv4.1: Bump the default callback session slot count to 16
  SUNRPC: Convert remaining GFP_NOIO, and GFP_NOWAIT sites in sunrpc
  NFS/flexfiles: Clean up mirror DS initialisation
  NFS/flexfiles: Remove dead code in ff_layout_mirror_valid()
  NFS/flexfile: Simplify nfs4_ff_layout_select_ds_stateid()
  NFS/flexfile: Simplify nfs4_ff_layout_ds_version()
  NFS/flexfiles: Simplify ff_layout_get_ds_cred()
  NFS/flexfiles: Simplify nfs4_ff_find_or_create_ds_client()
  NFS/flexfiles: Simplify nfs4_ff_layout_select_ds_fh()
  NFS/flexfiles: Speed up read failover when DSes are down
  NFS/flexfiles: Don't invalidate DS deviceids for being unresponsive
  ...

11 files changed, 147 insertions, 31 deletions

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 1b06f0b28453..22494d170619 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -538,6 +538,7 @@ enum {
 	NFSPROC4_CLNT_OFFLOAD_CANCEL,
 
 	NFSPROC4_CLNT_LOOKUPP,
+	NFSPROC4_CLNT_LAYOUTERROR,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 6aa8cc83c3b6..c827d31298cc 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -261,5 +261,6 @@ struct nfs_server {
 #define NFS_CAP_CLONE		(1U << 23)
 #define NFS_CAP_COPY		(1U << 24)
 #define NFS_CAP_OFFLOAD_CANCEL	(1U << 25)
+#define NFS_CAP_LAYOUTERROR	(1U << 26)
 
 #endif
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index e27572d30d97..ad69430fd0eb 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -164,6 +164,16 @@ nfs_list_add_request(struct nfs_page *req, struct list_head *head)
 	list_add_tail(&req->wb_list, head);
 }
 
+/**
+ * nfs_list_move_request - Move a request to a new list
+ * @req: request
+ * @head: head of list into which to insert the request.
+ */
+static inline void
+nfs_list_move_request(struct nfs_page *req, struct list_head *head)
+{
+	list_move_tail(&req->wb_list, head);
+}
 
 /**
  * nfs_list_remove_request - Remove a request from its wb_list
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 441a93ebcac0..9b8324ec08f3 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -383,6 +383,41 @@ struct nfs42_layoutstat_data {
 	struct nfs42_layoutstat_res res;
 };
 
+struct nfs42_device_error {
+	struct nfs4_deviceid dev_id;
+	int status;
+	enum nfs_opnum4 opnum;
+};
+
+struct nfs42_layout_error {
+	__u64 offset;
+	__u64 length;
+	nfs4_stateid stateid;
+	struct nfs42_device_error errors[1];
+};
+
+#define NFS42_LAYOUTERROR_MAX 5
+
+struct nfs42_layouterror_args {
+	struct nfs4_sequence_args seq_args;
+	struct inode *inode;
+	unsigned int num_errors;
+	struct nfs42_layout_error errors[NFS42_LAYOUTERROR_MAX];
+};
+
+struct nfs42_layouterror_res {
+	struct nfs4_sequence_res seq_res;
+	unsigned int num_errors;
+	int rpc_status;
+};
+
+struct nfs42_layouterror_data {
+	struct nfs42_layouterror_args args;
+	struct nfs42_layouterror_res res;
+	struct inode *inode;
+	struct pnfs_layout_segment *lseg;
+};
+
 struct nfs42_clone_args {
 	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh			*src_fh;
@@ -1549,7 +1584,7 @@ struct nfs_commit_data {
 };
 
 struct nfs_pgio_completion_ops {
-	void	(*error_cleanup)(struct list_head *head);
+	void	(*error_cleanup)(struct list_head *head, int);
 	void	(*init_hdr)(struct nfs_pgio_header *hdr);
 	void	(*completion)(struct nfs_pgio_header *hdr);
 	void	(*reschedule_io)(struct nfs_pgio_header *hdr);
diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index eed3cb16ccf1..5f9076fdb090 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -74,14 +74,12 @@ struct rpc_cred_cache;
 struct rpc_authops;
 struct rpc_auth {
 	unsigned int		au_cslack;	/* call cred size estimate */
-				/* guess at number of u32's auth adds before
-				 * reply data; normally the verifier size: */
-	unsigned int		au_rslack;
-				/* for gss, used to calculate au_rslack: */
-	unsigned int		au_verfsize;
-
-	unsigned int		au_flags;	/* various flags */
-	const struct rpc_authops *au_ops;		/* operations */
+	unsigned int		au_rslack;	/* reply cred size estimate */
+	unsigned int		au_verfsize;	/* size of reply verifier */
+	unsigned int		au_ralign;	/* words before UL header */
+
+	unsigned int		au_flags;
+	const struct rpc_authops *au_ops;
 	rpc_authflavor_t	au_flavor;	/* pseudoflavor (note may
 						 * differ from the flavor in
 						 * au_ops->au_flavor in gss
@@ -131,13 +129,15 @@ struct rpc_credops {
 	void			(*crdestroy)(struct rpc_cred *);
 
 	int			(*crmatch)(struct auth_cred *, struct rpc_cred *, int);
-	__be32 *		(*crmarshal)(struct rpc_task *, __be32 *);
+	int			(*crmarshal)(struct rpc_task *task,
+					     struct xdr_stream *xdr);
 	int			(*crrefresh)(struct rpc_task *);
-	__be32 *		(*crvalidate)(struct rpc_task *, __be32 *);
-	int			(*crwrap_req)(struct rpc_task *, kxdreproc_t,
-						void *, __be32 *, void *);
-	int			(*crunwrap_resp)(struct rpc_task *, kxdrdproc_t,
-						void *, __be32 *, void *);
+	int			(*crvalidate)(struct rpc_task *task,
+					      struct xdr_stream *xdr);
+	int			(*crwrap_req)(struct rpc_task *task,
+					      struct xdr_stream *xdr);
+	int			(*crunwrap_resp)(struct rpc_task *task,
+						 struct xdr_stream *xdr);
 	int			(*crkey_timeout)(struct rpc_cred *);
 	char *			(*crstringify_acceptor)(struct rpc_cred *);
 	bool			(*crneed_reencode)(struct rpc_task *);
@@ -165,10 +165,18 @@ struct rpc_cred *	rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *
 void			rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *);
 struct rpc_cred *	rpcauth_lookupcred(struct rpc_auth *, int);
 void			put_rpccred(struct rpc_cred *);
-__be32 *		rpcauth_marshcred(struct rpc_task *, __be32 *);
-__be32 *		rpcauth_checkverf(struct rpc_task *, __be32 *);
-int			rpcauth_wrap_req(struct rpc_task *task, kxdreproc_t encode, void *rqstp, __be32 *data, void *obj);
-int			rpcauth_unwrap_resp(struct rpc_task *task, kxdrdproc_t decode, void *rqstp, __be32 *data, void *obj);
+int			rpcauth_marshcred(struct rpc_task *task,
+					  struct xdr_stream *xdr);
+int			rpcauth_checkverf(struct rpc_task *task,
+					  struct xdr_stream *xdr);
+int			rpcauth_wrap_req_encode(struct rpc_task *task,
+						struct xdr_stream *xdr);
+int			rpcauth_wrap_req(struct rpc_task *task,
+					 struct xdr_stream *xdr);
+int			rpcauth_unwrap_resp_decode(struct rpc_task *task,
+						   struct xdr_stream *xdr);
+int			rpcauth_unwrap_resp(struct rpc_task *task,
+					    struct xdr_stream *xdr);
 bool			rpcauth_xmit_need_reencode(struct rpc_task *task);
 int			rpcauth_refreshcred(struct rpc_task *);
 void			rpcauth_invalcred(struct rpc_task *);
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 1c441714d569..98bc9883b230 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -169,6 +169,9 @@ int		rpcb_v4_register(struct net *net, const u32 program,
 				 const char *netid);
 void		rpcb_getport_async(struct rpc_task *);
 
+void rpc_prepare_reply_pages(struct rpc_rqst *req, struct page **pages,
+			     unsigned int base, unsigned int len,
+			     unsigned int hdrsize);
 void		rpc_call_start(struct rpc_task *);
 int		rpc_call_async(struct rpc_clnt *clnt,
 			       const struct rpc_message *msg, int flags,
diff --git a/include/linux/sunrpc/gss_krb5_enctypes.h b/include/linux/sunrpc/gss_krb5_enctypes.h
index ec6234eee89c..981c89cef19d 100644
--- a/include/linux/sunrpc/gss_krb5_enctypes.h
+++ b/include/linux/sunrpc/gss_krb5_enctypes.h
@@ -1,4 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Dumb way to share this static piece of information with nfsd
+ * Define the string that exports the set of kernel-supported
+ * Kerberos enctypes. This list is sent via upcall to gssd, and
+ * is also exposed via the nfsd /proc API. The consumers generally
+ * treat this as an ordered list, where the first item in the list
+ * is the most preferred.
+ */
+
+#ifndef _LINUX_SUNRPC_GSS_KRB5_ENCTYPES_H
+#define _LINUX_SUNRPC_GSS_KRB5_ENCTYPES_H
+
+#ifdef CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES
+
+/*
+ * NB: This list includes encryption types that were deprecated
+ * by RFC 8429 (DES3_CBC_SHA1 and ARCFOUR_HMAC).
+ *
+ * ENCTYPE_AES256_CTS_HMAC_SHA1_96
+ * ENCTYPE_AES128_CTS_HMAC_SHA1_96
+ * ENCTYPE_DES3_CBC_SHA1
+ * ENCTYPE_ARCFOUR_HMAC
+ */
+#define KRB5_SUPPORTED_ENCTYPES "18,17,16,23"
+
+#else	/* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */
+
+/*
+ * NB: This list includes encryption types that were deprecated
+ * by RFC 8429 and RFC 6649.
+ *
+ * ENCTYPE_AES256_CTS_HMAC_SHA1_96
+ * ENCTYPE_AES128_CTS_HMAC_SHA1_96
+ * ENCTYPE_DES3_CBC_SHA1
+ * ENCTYPE_ARCFOUR_HMAC
+ * ENCTYPE_DES_CBC_MD5
+ * ENCTYPE_DES_CBC_CRC
+ * ENCTYPE_DES_CBC_MD4
  */
 #define KRB5_SUPPORTED_ENCTYPES "18,17,16,23,3,1,2"
+
+#endif	/* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */
+
+#endif	/* _LINUX_SUNRPC_GSS_KRB5_ENCTYPES_H */
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 219aa3910a0c..ec861cd0cfe8 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -97,6 +97,7 @@ typedef void			(*rpc_action)(struct rpc_task *);
 
 struct rpc_call_ops {
 	void (*rpc_call_prepare)(struct rpc_task *, void *);
+	void (*rpc_call_prepare_transmit)(struct rpc_task *, void *);
 	void (*rpc_call_done)(struct rpc_task *, void *);
 	void (*rpc_count_stats)(struct rpc_task *, void *);
 	void (*rpc_release)(void *);
@@ -303,4 +304,12 @@ rpc_clnt_swap_deactivate(struct rpc_clnt *clnt)
 }
 #endif /* CONFIG_SUNRPC_SWAP */
 
+static inline bool
+rpc_task_need_resched(const struct rpc_task *task)
+{
+	if (RPC_IS_QUEUED(task) || task->tk_callback)
+		return true;
+	return false;
+}
+
 #endif /* _LINUX_SUNRPC_SCHED_H_ */
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 2ec128060239..9ee3970ba59c 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -87,6 +87,16 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
 #define	xdr_one		cpu_to_be32(1)
 #define	xdr_two		cpu_to_be32(2)
 
+#define	rpc_auth_null	cpu_to_be32(RPC_AUTH_NULL)
+#define	rpc_auth_unix	cpu_to_be32(RPC_AUTH_UNIX)
+#define	rpc_auth_short	cpu_to_be32(RPC_AUTH_SHORT)
+#define	rpc_auth_gss	cpu_to_be32(RPC_AUTH_GSS)
+
+#define	rpc_call	cpu_to_be32(RPC_CALL)
+#define	rpc_reply	cpu_to_be32(RPC_REPLY)
+
+#define	rpc_msg_accepted	cpu_to_be32(RPC_MSG_ACCEPTED)
+
 #define	rpc_success		cpu_to_be32(RPC_SUCCESS)
 #define	rpc_prog_unavail	cpu_to_be32(RPC_PROG_UNAVAIL)
 #define	rpc_prog_mismatch	cpu_to_be32(RPC_PROG_MISMATCH)
@@ -95,6 +105,9 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
 #define	rpc_system_err		cpu_to_be32(RPC_SYSTEM_ERR)
 #define	rpc_drop_reply		cpu_to_be32(RPC_DROP_REPLY)
 
+#define	rpc_mismatch		cpu_to_be32(RPC_MISMATCH)
+#define	rpc_auth_error		cpu_to_be32(RPC_AUTH_ERROR)
+
 #define	rpc_auth_ok		cpu_to_be32(RPC_AUTH_OK)
 #define	rpc_autherr_badcred	cpu_to_be32(RPC_AUTH_BADCRED)
 #define	rpc_autherr_rejectedcred cpu_to_be32(RPC_AUTH_REJECTEDCRED)
@@ -103,7 +116,6 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
 #define	rpc_autherr_tooweak	cpu_to_be32(RPC_AUTH_TOOWEAK)
 #define	rpcsec_gsserr_credproblem	cpu_to_be32(RPCSEC_GSS_CREDPROBLEM)
 #define	rpcsec_gsserr_ctxproblem	cpu_to_be32(RPCSEC_GSS_CTXPROBLEM)
-#define	rpc_autherr_oldseqnum	cpu_to_be32(101)
 
 /*
  * Miscellaneous XDR helper functions
@@ -167,7 +179,6 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p)
 extern void xdr_shift_buf(struct xdr_buf *, size_t);
 extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *);
 extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int);
-extern void xdr_buf_trim(struct xdr_buf *, unsigned int);
 extern int xdr_buf_read_netobj(struct xdr_buf *, struct xdr_netobj *, unsigned int);
 extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
 extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
@@ -217,6 +228,8 @@ struct xdr_stream {
 	struct kvec scratch;	/* Scratch buffer */
 	struct page **page_ptr;	/* pointer to the current page */
 	unsigned int nwords;	/* Remaining decode buffer length */
+
+	struct rpc_rqst *rqst;	/* For debugging */
 };
 
 /*
@@ -227,7 +240,8 @@ typedef void	(*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 typedef int	(*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 		void *obj);
 
-extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p);
+extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf,
+			    __be32 *p, struct rpc_rqst *rqst);
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
 extern void xdr_commit_encode(struct xdr_stream *xdr);
 extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len);
@@ -235,7 +249,8 @@ extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen);
 extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages,
 		unsigned int base, unsigned int len);
 extern unsigned int xdr_stream_pos(const struct xdr_stream *xdr);
-extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p);
+extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf,
+			    __be32 *p, struct rpc_rqst *rqst);
 extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
 		struct page **pages, unsigned int len);
 extern void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen);
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index ad7e910b119d..3a391544299e 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -196,8 +196,6 @@ struct rpc_xprt {
 
 	size_t			max_payload;	/* largest RPC payload size,
 						   in bytes */
-	unsigned int		tsh_size;	/* size of transport specific
-						   header */
 
 	struct rpc_wait_queue	binding;	/* requests waiting on rpcbind */
 	struct rpc_wait_queue	sending;	/* requests waiting to send */
@@ -362,11 +360,6 @@ struct rpc_xprt *	xprt_alloc(struct net *net, size_t size,
 				unsigned int max_req);
 void			xprt_free(struct rpc_xprt *);
 
-static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 *p)
-{
-	return p + xprt->tsh_size;
-}
-
 static inline int
 xprt_enable_swap(struct rpc_xprt *xprt)
 {
diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h
index 458bfe0137f5..b81d0b3e0799 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -26,6 +26,7 @@ struct sock_xprt {
 	 */
 	struct socket *		sock;
 	struct sock *		inet;
+	struct file *		file;
 
 	/*
 	 * State of TCP reply receive