Merge tag 'nfsd-5.9' of git://git.linux-nfs.org/projects/cel/cel-2.6

Pull NFS server updates from Chuck Lever:
 "Highlights:
   - Support for user extended attributes on NFS (RFC 8276)
   - Further reduce unnecessary NFSv4 delegation recalls

  Notable fixes:
   - Fix recent krb5p regression
   - Address a few resource leaks and a rare NULL dereference

  Other:
   - De-duplicate RPC/RDMA error handling and other utility functions
   - Replace storage and display of kernel memory addresses by tracepoints"

* tag 'nfsd-5.9' of git://git.linux-nfs.org/projects/cel/cel-2.6: (38 commits)
  svcrdma: CM event handler clean up
  svcrdma: Remove transport reference counting
  svcrdma: Fix another Receive buffer leak
  SUNRPC: Refresh the show_rqstp_flags() macro
  nfsd: netns.h: delete a duplicated word
  SUNRPC: Fix ("SUNRPC: Add "@len" parameter to gss_unwrap()")
  nfsd: avoid a NULL dereference in __cld_pipe_upcall()
  nfsd4: a client's own opens needn't prevent delegations
  nfsd: Use seq_putc() in two functions
  svcrdma: Display chunk completion ID when posting a rw_ctxt
  svcrdma: Record send_ctxt completion ID in trace_svcrdma_post_send()
  svcrdma: Introduce Send completion IDs
  svcrdma: Record Receive completion ID in svc_rdma_decode_rqst
  svcrdma: Introduce Receive completion IDs
  svcrdma: Introduce infrastructure to support completion IDs
  svcrdma: Add common XDR encoders for RDMA and Read segments
  svcrdma: Add common XDR decoders for RDMA and Read segments
  SUNRPC: Add helpers for decoding list discriminators symbolically
  svcrdma: Remove declarations for functions long removed
  svcrdma: Clean up trace_svcrdma_send_failed() tracepoint
  ...

6 files changed, 161 insertions, 6 deletions

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 4dba3c948932..33ebe476428e 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -150,6 +150,12 @@ enum nfs_opnum4 {
 	OP_WRITE_SAME = 70,
 	OP_CLONE = 71,
 
+	/* xattr support (RFC8726) */
+	OP_GETXATTR                = 72,
+	OP_SETXATTR                = 73,
+	OP_LISTXATTRS              = 74,
+	OP_REMOVEXATTR             = 75,
+
 	OP_ILLEGAL = 10044,
 };
 
@@ -159,7 +165,7 @@ Needs to be updated if more operations are defined in future.*/
 #define FIRST_NFS4_OP	OP_ACCESS
 #define LAST_NFS40_OP	OP_RELEASE_LOCKOWNER
 #define LAST_NFS41_OP	OP_RECLAIM_COMPLETE
-#define LAST_NFS42_OP	OP_CLONE
+#define LAST_NFS42_OP	OP_REMOVEXATTR
 #define LAST_NFS4_OP	LAST_NFS42_OP
 
 enum nfsstat4 {
@@ -280,6 +286,10 @@ enum nfsstat4 {
 	NFS4ERR_WRONG_LFS = 10092,
 	NFS4ERR_BADLABEL = 10093,
 	NFS4ERR_OFFLOAD_NO_REQS = 10094,
+
+	/* xattr (RFC8276) */
+	NFS4ERR_NOXATTR        = 10095,
+	NFS4ERR_XATTR2BIG      = 10096,
 };
 
 static inline bool seqid_mutating_err(u32 err)
@@ -452,6 +462,7 @@ enum change_attr_type4 {
 #define FATTR4_WORD2_CHANGE_ATTR_TYPE	(1UL << 15)
 #define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
 #define FATTR4_WORD2_MODE_UMASK		(1UL << 17)
+#define FATTR4_WORD2_XATTR_SUPPORT	(1UL << 18)
 
 /* MDS threshold bitmap bits */
 #define THRESHOLD_RD                    (1UL << 0)
@@ -700,4 +711,13 @@ struct nl4_server {
 		struct nfs42_netaddr	nl4_addr; /* NL4_NETADDR */
 	} u;
 };
+
+/*
+ * Options for setxattr. These match the flags for setxattr(2).
+ */
+enum nfs4_setxattr_options {
+	SETXATTR4_EITHER	= 0,
+	SETXATTR4_CREATE	= 1,
+	SETXATTR4_REPLACE	= 2,
+};
 #endif
diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h
index 320c672d84de..4af31bbc8802 100644
--- a/include/linux/sunrpc/rpc_rdma.h
+++ b/include/linux/sunrpc/rpc_rdma.h
@@ -124,4 +124,78 @@ rpcrdma_decode_buffer_size(u8 val)
 	return ((unsigned int)val + 1) << 10;
 }
 
+/**
+ * xdr_encode_rdma_segment - Encode contents of an RDMA segment
+ * @p: Pointer into a send buffer
+ * @handle: The RDMA handle to encode
+ * @length: The RDMA length to encode
+ * @offset: The RDMA offset to encode
+ *
+ * Return value:
+ *   Pointer to the XDR position that follows the encoded RDMA segment
+ */
+static inline __be32 *xdr_encode_rdma_segment(__be32 *p, u32 handle,
+					      u32 length, u64 offset)
+{
+	*p++ = cpu_to_be32(handle);
+	*p++ = cpu_to_be32(length);
+	return xdr_encode_hyper(p, offset);
+}
+
+/**
+ * xdr_encode_read_segment - Encode contents of a Read segment
+ * @p: Pointer into a send buffer
+ * @position: The position to encode
+ * @handle: The RDMA handle to encode
+ * @length: The RDMA length to encode
+ * @offset: The RDMA offset to encode
+ *
+ * Return value:
+ *   Pointer to the XDR position that follows the encoded Read segment
+ */
+static inline __be32 *xdr_encode_read_segment(__be32 *p, u32 position,
+					      u32 handle, u32 length,
+					      u64 offset)
+{
+	*p++ = cpu_to_be32(position);
+	return xdr_encode_rdma_segment(p, handle, length, offset);
+}
+
+/**
+ * xdr_decode_rdma_segment - Decode contents of an RDMA segment
+ * @p: Pointer to the undecoded RDMA segment
+ * @handle: Upon return, the RDMA handle
+ * @length: Upon return, the RDMA length
+ * @offset: Upon return, the RDMA offset
+ *
+ * Return value:
+ *   Pointer to the XDR item that follows the RDMA segment
+ */
+static inline __be32 *xdr_decode_rdma_segment(__be32 *p, u32 *handle,
+					      u32 *length, u64 *offset)
+{
+	*handle = be32_to_cpup(p++);
+	*length = be32_to_cpup(p++);
+	return xdr_decode_hyper(p, offset);
+}
+
+/**
+ * xdr_decode_read_segment - Decode contents of a Read segment
+ * @p: Pointer to the undecoded Read segment
+ * @position: Upon return, the segment's position
+ * @handle: Upon return, the RDMA handle
+ * @length: Upon return, the RDMA length
+ * @offset: Upon return, the RDMA offset
+ *
+ * Return value:
+ *   Pointer to the XDR item that follows the Read segment
+ */
+static inline __be32 *xdr_decode_read_segment(__be32 *p, u32 *position,
+					      u32 *handle, u32 *length,
+					      u64 *offset)
+{
+	*position = be32_to_cpup(p++);
+	return xdr_decode_rdma_segment(p, handle, length, offset);
+}
+
 #endif				/* _LINUX_SUNRPC_RPC_RDMA_H */
diff --git a/include/linux/sunrpc/rpc_rdma_cid.h b/include/linux/sunrpc/rpc_rdma_cid.h
new file mode 100644
index 000000000000..be24ab2baa6a
--- /dev/null
+++ b/include/linux/sunrpc/rpc_rdma_cid.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * * Copyright (c) 2020, Oracle and/or its affiliates.
+ */
+
+#ifndef RPC_RDMA_CID_H
+#define RPC_RDMA_CID_H
+
+/*
+ * The rpc_rdma_cid struct records completion ID information. A
+ * completion ID matches an incoming Send or Receive completion
+ * to a Completion Queue and to a previous ib_post_*(). The ID
+ * can then be displayed in an error message or recorded in a
+ * trace record.
+ *
+ * This struct is shared between the server and client RPC/RDMA
+ * transport implementations.
+ */
+struct rpc_rdma_cid {
+	u32			ci_queue_id;
+	int			ci_completion_id;
+};
+
+#endif	/* RPC_RDMA_CID_H */
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 7ed82625dc0b..9dc3a3b88391 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -46,6 +46,7 @@
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/rpc_rdma.h>
+#include <linux/sunrpc/rpc_rdma_cid.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/rdma_cm.h>
 
@@ -109,6 +110,8 @@ struct svcxprt_rdma {
 	struct work_struct   sc_work;
 
 	struct llist_head    sc_recv_ctxts;
+
+	atomic_t	     sc_completion_ids;
 };
 /* sc_flags */
 #define RDMAXPRT_CONN_PENDING	3
@@ -129,6 +132,7 @@ struct svc_rdma_recv_ctxt {
 	struct list_head	rc_list;
 	struct ib_recv_wr	rc_recv_wr;
 	struct ib_cqe		rc_cqe;
+	struct rpc_rdma_cid	rc_cid;
 	struct ib_sge		rc_recv_sge;
 	void			*rc_recv_buf;
 	struct xdr_buf		rc_arg;
@@ -147,6 +151,8 @@ struct svc_rdma_recv_ctxt {
 
 struct svc_rdma_send_ctxt {
 	struct list_head	sc_list;
+	struct rpc_rdma_cid	sc_cid;
+
 	struct ib_send_wr	sc_send_wr;
 	struct ib_cqe		sc_cqe;
 	struct xdr_buf		sc_hdrbuf;
@@ -190,20 +196,21 @@ extern struct svc_rdma_send_ctxt *
 		svc_rdma_send_ctxt_get(struct svcxprt_rdma *rdma);
 extern void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
 				   struct svc_rdma_send_ctxt *ctxt);
-extern int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr);
+extern int svc_rdma_send(struct svcxprt_rdma *rdma,
+			 struct svc_rdma_send_ctxt *ctxt);
 extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_send_ctxt *sctxt,
 				  const struct svc_rdma_recv_ctxt *rctxt,
 				  struct xdr_buf *xdr);
+extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
+				    struct svc_rdma_send_ctxt *sctxt,
+				    struct svc_rdma_recv_ctxt *rctxt,
+				    int status);
 extern int svc_rdma_sendto(struct svc_rqst *);
 extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
 				 unsigned int length);
 
 /* svc_rdma_transport.c */
-extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
-extern void svc_sq_reap(struct svcxprt_rdma *);
-extern void svc_rq_reap(struct svcxprt_rdma *);
-
 extern struct svc_xprt_class svc_rdma_class;
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 extern struct svc_xprt_class svc_rdma_bc_class;
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 22c207b2425f..5a6a81b7cd9f 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -475,6 +475,32 @@ xdr_stream_encode_uint32_array(struct xdr_stream *xdr,
 }
 
 /**
+ * xdr_item_is_absent - symbolically handle XDR discriminators
+ * @p: pointer to undecoded discriminator
+ *
+ * Return values:
+ *   %true if the following XDR item is absent
+ *   %false if the following XDR item is present
+ */
+static inline bool xdr_item_is_absent(const __be32 *p)
+{
+	return *p == xdr_zero;
+}
+
+/**
+ * xdr_item_is_present - symbolically handle XDR discriminators
+ * @p: pointer to undecoded discriminator
+ *
+ * Return values:
+ *   %true if the following XDR item is present
+ *   %false if the following XDR item is absent
+ */
+static inline bool xdr_item_is_present(const __be32 *p)
+{
+	return *p != xdr_zero;
+}
+
+/**
  * xdr_stream_decode_u32 - Decode a 32-bit integer
  * @xdr: pointer to xdr_stream
  * @ptr: location to store integer
diff --git a/include/linux/xattr.h b/include/linux/xattr.h
index c5afaf8ca7a2..10b4dc2709f0 100644
--- a/include/linux/xattr.h
+++ b/include/linux/xattr.h
@@ -52,14 +52,18 @@ ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t);
 ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size);
 int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int);
 int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int);
+int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **);
 int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int);
 int __vfs_removexattr(struct dentry *, const char *);
+int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **);
 int vfs_removexattr(struct dentry *, const char *);
 
 ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size);
 ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name,
 			   char **xattr_value, size_t size, gfp_t flags);
 
+int xattr_supported_namespace(struct inode *inode, const char *prefix);
+
 static inline const char *xattr_prefix(const struct xattr_handler *handler)
 {
 	return handler->prefix ?: handler->name;