Merge tag 'nfs-for-5.11-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Features:

   - NFSv3: Add emulation of lookupp() to improve open_by_filehandle()
     support

   - A series of patches to improve readdir performance, particularly
     with large directories

   - Basic support for using NFS/RDMA with the pNFS files and flexfiles
     drivers

   - Micro-optimisations for RDMA

   - RDMA tracing improvements

  Bugfixes:

   - Fix a long standing bug with xs_read_xdr_buf() when receiving
     partial pages (Dan Aloni)

   - Various fixes for getxattr and listxattr, when used over non-TCP
     transports

   - Fixes for containerised NFS from Sargun Dhillon

   - switch nfsiod to be an UNBOUND workqueue (Neil Brown)

   - READDIR should not ask for security label information if there is
     no LSM policy (Olga Kornievskaia)

   - Avoid using interval-based rebinding with TCP in lockd (Calum
     Mackay)

   - A series of RPC and NFS layer fixes to support the NFSv4.2
     READ_PLUS code

   - A couple of fixes for pnfs/flexfiles read failover

  Cleanups:

   - Various cleanups for the SUNRPC xdr code in conjunction with the
     READ_PLUS fixes"

* tag 'nfs-for-5.11-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (90 commits)
  NFS/pNFS: Fix a typo in ff_layout_resend_pnfs_read()
  pNFS/flexfiles: Avoid spurious layout returns in ff_layout_choose_ds_for_read
  NFSv4/pnfs: Add tracing for the deviceid cache
  fs/lockd: convert comma to semicolon
  NFSv4.2: fix error return on memory allocation failure
  NFSv4.2/pnfs: Don't use READ_PLUS with pNFS yet
  NFSv4.2: Deal with potential READ_PLUS data extent buffer overflow
  NFSv4.2: Don't error when exiting early on a READ_PLUS buffer overflow
  NFSv4.2: Handle hole lengths that exceed the READ_PLUS read buffer
  NFSv4.2: decode_read_plus_hole() needs to check the extent offset
  NFSv4.2: decode_read_plus_data() must skip padding after data segment
  NFSv4.2: Ensure we always reset the result->count in decode_read_plus()
  SUNRPC: When expanding the buffer, we may need grow the sparse pages
  SUNRPC: Cleanup - constify a number of xdr_buf helpers
  SUNRPC: Clean up open coded setting of the xdr_stream 'nwords' field
  SUNRPC: _copy_to/from_pages() now check for zero length
  SUNRPC: Cleanup xdr_shrink_bufhead()
  SUNRPC: Fix xdr_expand_hole()
  SUNRPC: Fixes for xdr_align_data()
  SUNRPC: _shift_data_left/right_pages should check the shift length
  ...

1 files changed, 27 insertions, 21 deletions

diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 2eabe5add344..ac6b79ee9355 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -84,6 +84,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 /* lock,open owner id:
  * we currently use size 2 (u64) out of (NFS4_OPAQUE_LIMIT  >> 2)
  */
+#define pagepad_maxsz		(1)
 #define open_owner_id_maxsz	(1 + 2 + 1 + 1 + 2)
 #define lock_owner_id_maxsz	(1 + 1 + 4)
 #define decode_lockowner_maxsz	(1 + XDR_QUADLEN(IDMAP_NAMESZ))
@@ -215,14 +216,14 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 				 nfs4_fattr_bitmap_maxsz)
 #define encode_read_maxsz	(op_encode_hdr_maxsz + \
 				 encode_stateid_maxsz + 3)
-#define decode_read_maxsz	(op_decode_hdr_maxsz + 2 + 1)
+#define decode_read_maxsz	(op_decode_hdr_maxsz + 2 + pagepad_maxsz)
 #define encode_readdir_maxsz	(op_encode_hdr_maxsz + \
 				 2 + encode_verifier_maxsz + 5 + \
 				nfs4_label_maxsz)
 #define decode_readdir_maxsz	(op_decode_hdr_maxsz + \
-				 decode_verifier_maxsz + 1)
+				 decode_verifier_maxsz + pagepad_maxsz)
 #define encode_readlink_maxsz	(op_encode_hdr_maxsz)
-#define decode_readlink_maxsz	(op_decode_hdr_maxsz + 1 + 1)
+#define decode_readlink_maxsz	(op_decode_hdr_maxsz + 1 + pagepad_maxsz)
 #define encode_write_maxsz	(op_encode_hdr_maxsz + \
 				 encode_stateid_maxsz + 4)
 #define decode_write_maxsz	(op_decode_hdr_maxsz + \
@@ -284,14 +285,14 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 #define decode_delegreturn_maxsz (op_decode_hdr_maxsz)
 #define encode_getacl_maxsz	(encode_getattr_maxsz)
 #define decode_getacl_maxsz	(op_decode_hdr_maxsz + \
-				 nfs4_fattr_bitmap_maxsz + 1 + 1)
+				 nfs4_fattr_bitmap_maxsz + 1 + pagepad_maxsz)
 #define encode_setacl_maxsz	(op_encode_hdr_maxsz + \
 				 encode_stateid_maxsz + 3)
 #define decode_setacl_maxsz	(decode_setattr_maxsz)
 #define encode_fs_locations_maxsz \
 				(encode_getattr_maxsz)
 #define decode_fs_locations_maxsz \
-				(1)
+				(pagepad_maxsz)
 #define encode_secinfo_maxsz	(op_encode_hdr_maxsz + nfs4_name_maxsz)
 #define decode_secinfo_maxsz	(op_decode_hdr_maxsz + 1 + ((NFS_MAX_SECFLAVORS * (16 + GSS_OID_MAX_LEN)) / 4))
 
@@ -393,12 +394,13 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 				  /* devaddr4 payload is read into page */ \
 				1 /* notification bitmap length */ + \
 				1 /* notification bitmap, word 0 */ + \
-				1 /* possible XDR padding */)
+				pagepad_maxsz /* possible XDR padding */)
 #define encode_layoutget_maxsz	(op_encode_hdr_maxsz + 10 + \
 				encode_stateid_maxsz)
 #define decode_layoutget_maxsz	(op_decode_hdr_maxsz + 8 + \
 				decode_stateid_maxsz + \
-				XDR_QUADLEN(PNFS_LAYOUT_MAXSIZE) + 1)
+				XDR_QUADLEN(PNFS_LAYOUT_MAXSIZE) + \
+				pagepad_maxsz)
 #define encode_layoutcommit_maxsz (op_encode_hdr_maxsz +          \
 				2 /* offset */ + \
 				2 /* length */ + \
@@ -2342,7 +2344,7 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr,
 		encode_layoutget(xdr, args->lg_args, &hdr);
 		rpc_prepare_reply_pages(req, args->lg_args->layout.pages, 0,
 					args->lg_args->layout.pglen,
-					hdr.replen);
+					hdr.replen - pagepad_maxsz);
 	}
 	encode_nops(&hdr);
 }
@@ -2388,7 +2390,7 @@ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req,
 		encode_layoutget(xdr, args->lg_args, &hdr);
 		rpc_prepare_reply_pages(req, args->lg_args->layout.pages, 0,
 					args->lg_args->layout.pglen,
-					hdr.replen);
+					hdr.replen - pagepad_maxsz);
 	}
 	encode_nops(&hdr);
 }
@@ -2499,7 +2501,7 @@ static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_readlink(xdr, args, req, &hdr);
 
 	rpc_prepare_reply_pages(req, args->pages, args->pgbase,
-				args->pglen, hdr.replen);
+				args->pglen, hdr.replen - pagepad_maxsz);
 	encode_nops(&hdr);
 }
 
@@ -2520,7 +2522,7 @@ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_readdir(xdr, args, req, &hdr);
 
 	rpc_prepare_reply_pages(req, args->pages, args->pgbase,
-				args->count, hdr.replen);
+				args->count, hdr.replen - pagepad_maxsz);
 	encode_nops(&hdr);
 }
 
@@ -2541,7 +2543,7 @@ static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_read(xdr, args, &hdr);
 
 	rpc_prepare_reply_pages(req, args->pages, args->pgbase,
-				args->count, hdr.replen);
+				args->count, hdr.replen - pagepad_maxsz);
 	req->rq_rcv_buf.flags |= XDRBUF_READ;
 	encode_nops(&hdr);
 }
@@ -2588,7 +2590,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 			ARRAY_SIZE(nfs4_acl_bitmap), &hdr);
 
 	rpc_prepare_reply_pages(req, args->acl_pages, 0,
-				args->acl_len, replen + 1);
+				args->acl_len, replen);
 	encode_nops(&hdr);
 }
 
@@ -2810,7 +2812,7 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req,
 	}
 
 	rpc_prepare_reply_pages(req, (struct page **)&args->page, 0,
-				PAGE_SIZE, replen + 1);
+				PAGE_SIZE, replen);
 	encode_nops(&hdr);
 }
 
@@ -3009,15 +3011,19 @@ static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req,
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
+	uint32_t replen;
 
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
+
+	replen = hdr.replen + op_decode_hdr_maxsz + 2;
+
 	encode_getdeviceinfo(xdr, args, &hdr);
 
-	/* set up reply kvec. Subtract notification bitmap max size (2)
-	 * so that notification bitmap is put in xdr_buf tail */
+	/* set up reply kvec. device_addr4 opaque data is read into the
+	 * pages */
 	rpc_prepare_reply_pages(req, args->pdev->pages, args->pdev->pgbase,
-				args->pdev->pglen, hdr.replen - 2);
+				args->pdev->pglen, replen);
 	encode_nops(&hdr);
 }
 
@@ -3039,7 +3045,7 @@ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req,
 	encode_layoutget(xdr, args, &hdr);
 
 	rpc_prepare_reply_pages(req, args->layout.pages, 0,
-				args->layout.pglen, hdr.replen);
+				args->layout.pglen, hdr.replen - pagepad_maxsz);
 	encode_nops(&hdr);
 }
 
@@ -5331,11 +5337,11 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 		res->acl_len = attrlen;
 
 		/* Check for receive buffer overflow */
-		if (res->acl_len > (xdr->nwords << 2) ||
+		if (res->acl_len > xdr_stream_remaining(xdr) ||
 		    res->acl_len + res->acl_data_offset > xdr->buf->page_len) {
 			res->acl_flags |= NFS4_ACL_TRUNC;
-			dprintk("NFS: acl reply: attrlen %u > page_len %u\n",
-					attrlen, xdr->nwords << 2);
+			dprintk("NFS: acl reply: attrlen %u > page_len %zu\n",
+				attrlen, xdr_stream_remaining(xdr));
 		}
 	} else
 		status = -EOPNOTSUPP;