Merge tag 'nfs-for-6.17-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Stable fixes:
   - don't inherit NFS filesystem capabilities when crossing from one
     filesystem to another

  Bugfixes:
   - NFS wakeup of __nfs_lookup_revalidate() needs memory barriers
   - NFS improve bounds checking in nfs_fh_to_dentry()
   - NFS Fix allocation errors when writing to a NFS file backed
     loopback device
   - NFSv4: More listxattr fixes
   - SUNRPC: fix client handling of TLS alerts
   - pNFS block/scsi layout fix for an uninitialised pointer
     dereference
   - pNFS block/scsi layout fixes for the extent encoding, stripe
     mapping, and disk offset overflows
   - pNFS layoutcommit work around for RPC size limitations
   - pNFS/flexfiles avoid looping when handling fatal errors after
     layoutget
   - localio: fix various race conditions

  Features and cleanups:
   - Add NFSv4 support for retrieving the btime
   - NFS: Allow folio migration for the case of mode == MIGRATE_SYNC
   - NFS: Support using a kernel keyring to store TLS certificates
   - NFSv4: Speed up delegation lookup using a hash table
   - Assorted cleanups to remove unused variables and struct fields
   - Assorted new tracepoints to improve debugging"

* tag 'nfs-for-6.17-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (44 commits)
  NFS/localio: nfs_uuid_put() fix the wake up after unlinking the file
  NFS/localio: nfs_uuid_put() fix races with nfs_open/close_local_fh()
  NFS/localio: nfs_close_local_fh() fix check for file closed
  NFSv4: Remove duplicate lookups, capability probes and fsinfo calls
  NFS: Fix the setting of capabilities when automounting a new filesystem
  sunrpc: fix client side handling of tls alerts
  nfs/localio: use read_seqbegin() rather than read_seqbegin_or_lock()
  NFS: Fixup allocation flags for nfsiod's __GFP_NORETRY
  NFSv4.2: another fix for listxattr
  NFS: Fix filehandle bounds checking in nfs_fh_to_dentry()
  SUNRPC: Silence warnings about parameters not being described
  NFS: Clean up pnfs_put_layout_hdr()/pnfs_destroy_layout_final()
  NFS: Fix wakeup of __nfs_lookup_revalidate() in unblock_revalidate()
  NFS: use a hash table for delegation lookup
  NFS: track active delegations per-server
  NFS: move the delegation_watermark module parameter
  NFS: cleanup nfs_inode_reclaim_delegation
  NFS: cleanup error handling in nfs4_server_common_setup
  pNFS/flexfiles: don't attempt pnfs on fatal DS errors
  NFS: drop __exit from nfs_exit_keyring
  ...

3 files changed, 32 insertions, 122 deletions

diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 8f2d65c1e831..16dcf115de1e 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -875,8 +875,8 @@ out_err:
  * krb5_etm_decrypt - Decrypt using the RFC 8009 rules
  * @kctx: Kerberos context
  * @offset: starting offset of the ciphertext, in bytes
- * @len:
- * @buf:
+ * @len: size of ciphertext to unwrap
+ * @buf: ciphertext to unwrap
  * @headskip: OUT: the enctype's confounder length, in octets
  * @tailskip: OUT: the enctype's HMAC length, in octets
  *
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 1346fdf33835..70efc727a9cd 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -37,19 +37,6 @@ xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj)
 }
 EXPORT_SYMBOL_GPL(xdr_encode_netobj);
 
-__be32 *
-xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj)
-{
-	unsigned int	len;
-
-	if ((len = be32_to_cpu(*p++)) > XDR_MAX_NETOBJ)
-		return NULL;
-	obj->len  = len;
-	obj->data = (u8 *) p;
-	return p + XDR_QUADLEN(len);
-}
-EXPORT_SYMBOL_GPL(xdr_decode_netobj);
-
 /**
  * xdr_encode_opaque_fixed - Encode fixed length opaque data
  * @p: pointer to current position in XDR buffer.
@@ -102,21 +89,6 @@ xdr_encode_string(__be32 *p, const char *string)
 }
 EXPORT_SYMBOL_GPL(xdr_encode_string);
 
-__be32 *
-xdr_decode_string_inplace(__be32 *p, char **sp,
-			  unsigned int *lenp, unsigned int maxlen)
-{
-	u32 len;
-
-	len = be32_to_cpu(*p++);
-	if (len > maxlen)
-		return NULL;
-	*lenp = len;
-	*sp = (char *) p;
-	return p + XDR_QUADLEN(len);
-}
-EXPORT_SYMBOL_GPL(xdr_decode_string_inplace);
-
 /**
  * xdr_terminate_string - '\0'-terminate a string residing in an xdr_buf
  * @buf: XDR buffer where string resides
@@ -2245,88 +2217,6 @@ out:
 EXPORT_SYMBOL_GPL(xdr_process_buf);
 
 /**
- * xdr_stream_decode_opaque - Decode variable length opaque
- * @xdr: pointer to xdr_stream
- * @ptr: location to store opaque data
- * @size: size of storage buffer @ptr
- *
- * Return values:
- *   On success, returns size of object stored in *@ptr
- *   %-EBADMSG on XDR buffer overflow
- *   %-EMSGSIZE on overflow of storage buffer @ptr
- */
-ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr, size_t size)
-{
-	ssize_t ret;
-	void *p;
-
-	ret = xdr_stream_decode_opaque_inline(xdr, &p, size);
-	if (ret <= 0)
-		return ret;
-	memcpy(ptr, p, ret);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque);
-
-/**
- * xdr_stream_decode_opaque_dup - Decode and duplicate variable length opaque
- * @xdr: pointer to xdr_stream
- * @ptr: location to store pointer to opaque data
- * @maxlen: maximum acceptable object size
- * @gfp_flags: GFP mask to use
- *
- * Return values:
- *   On success, returns size of object stored in *@ptr
- *   %-EBADMSG on XDR buffer overflow
- *   %-EMSGSIZE if the size of the object would exceed @maxlen
- *   %-ENOMEM on memory allocation failure
- */
-ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr,
-		size_t maxlen, gfp_t gfp_flags)
-{
-	ssize_t ret;
-	void *p;
-
-	ret = xdr_stream_decode_opaque_inline(xdr, &p, maxlen);
-	if (ret > 0) {
-		*ptr = kmemdup(p, ret, gfp_flags);
-		if (*ptr != NULL)
-			return ret;
-		ret = -ENOMEM;
-	}
-	*ptr = NULL;
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque_dup);
-
-/**
- * xdr_stream_decode_string - Decode variable length string
- * @xdr: pointer to xdr_stream
- * @str: location to store string
- * @size: size of storage buffer @str
- *
- * Return values:
- *   On success, returns length of NUL-terminated string stored in *@str
- *   %-EBADMSG on XDR buffer overflow
- *   %-EMSGSIZE on overflow of storage buffer @str
- */
-ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str, size_t size)
-{
-	ssize_t ret;
-	void *p;
-
-	ret = xdr_stream_decode_opaque_inline(xdr, &p, size);
-	if (ret > 0) {
-		memcpy(str, p, ret);
-		str[ret] = '\0';
-		return strlen(str);
-	}
-	*str = '\0';
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_string);
-
-/**
  * xdr_stream_decode_string_dup - Decode and duplicate variable length string
  * @xdr: pointer to xdr_stream
  * @str: location to store pointer to string
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 04ff66758fc3..c5f7bbf5775f 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -358,7 +358,7 @@ xs_alloc_sparse_pages(struct xdr_buf *buf, size_t want, gfp_t gfp)
 
 static int
 xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
-		     struct cmsghdr *cmsg, int ret)
+		     unsigned int *msg_flags, struct cmsghdr *cmsg, int ret)
 {
 	u8 content_type = tls_get_record_type(sock->sk, cmsg);
 	u8 level, description;
@@ -371,7 +371,7 @@ xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
 		 * record, even though there might be more frames
 		 * waiting to be decrypted.
 		 */
-		msg->msg_flags &= ~MSG_EOR;
+		*msg_flags &= ~MSG_EOR;
 		break;
 	case TLS_RECORD_TYPE_ALERT:
 		tls_alert_recv(sock->sk, msg, &level, &description);
@@ -386,19 +386,33 @@ xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
 }
 
 static int
-xs_sock_recv_cmsg(struct socket *sock, struct msghdr *msg, int flags)
+xs_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags, int flags)
 {
 	union {
 		struct cmsghdr	cmsg;
 		u8		buf[CMSG_SPACE(sizeof(u8))];
 	} u;
+	u8 alert[2];
+	struct kvec alert_kvec = {
+		.iov_base = alert,
+		.iov_len = sizeof(alert),
+	};
+	struct msghdr msg = {
+		.msg_flags = *msg_flags,
+		.msg_control = &u,
+		.msg_controllen = sizeof(u),
+	};
 	int ret;
 
-	msg->msg_control = &u;
-	msg->msg_controllen = sizeof(u);
-	ret = sock_recvmsg(sock, msg, flags);
-	if (msg->msg_controllen != sizeof(u))
-		ret = xs_sock_process_cmsg(sock, msg, &u.cmsg, ret);
+	iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1,
+		      alert_kvec.iov_len);
+	ret = sock_recvmsg(sock, &msg, flags);
+	if (ret > 0 &&
+	    tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) {
+		iov_iter_revert(&msg.msg_iter, ret);
+		ret = xs_sock_process_cmsg(sock, &msg, msg_flags, &u.cmsg,
+					   -EAGAIN);
+	}
 	return ret;
 }
 
@@ -408,7 +422,13 @@ xs_sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags, size_t seek)
 	ssize_t ret;
 	if (seek != 0)
 		iov_iter_advance(&msg->msg_iter, seek);
-	ret = xs_sock_recv_cmsg(sock, msg, flags);
+	ret = sock_recvmsg(sock, msg, flags);
+	/* Handle TLS inband control message lazily */
+	if (msg->msg_flags & MSG_CTRUNC) {
+		msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR);
+		if (ret == 0 || ret == -EIO)
+			ret = xs_sock_recv_cmsg(sock, &msg->msg_flags, flags);
+	}
 	return ret > 0 ? ret + seek : ret;
 }
 
@@ -434,7 +454,7 @@ xs_read_discard(struct socket *sock, struct msghdr *msg, int flags,
 		size_t count)
 {
 	iov_iter_discard(&msg->msg_iter, ITER_DEST, count);
-	return xs_sock_recv_cmsg(sock, msg, flags);
+	return xs_sock_recvmsg(sock, msg, flags, 0);
 }
 
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE