pnfs: ask for layout_blksize and save it in nfs_server

Block layout needs it to determine IO size.

Signed-off-by: Fred Isaman <iisaman@citi.umich.edu>
Signed-off-by: Tao Guo <glorioustao@gmail.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: Benny Halevy <bhalevy@tonian.com>
Signed-off-by: Jim Rees <rees@umich.edu>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

6 files changed, 91 insertions, 22 deletions

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index a9b1848..de00a37 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -936,6 +936,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
 	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	server->pnfs_blksize = fsinfo->blksize;
 	set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype);
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 1909ee8..1ec1a85 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -318,7 +318,7 @@ extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[];
 extern const u32 nfs4_fattr_bitmap[2];
 extern const u32 nfs4_statfs_bitmap[2];
 extern const u32 nfs4_pathconf_bitmap[2];
-extern const u32 nfs4_fsinfo_bitmap[2];
+extern const u32 nfs4_fsinfo_bitmap[3];
 extern const u32 nfs4_fs_locations_bitmap[2];
 
 /* nfs4renewd.c */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index af32d3d..e86de79 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -140,12 +140,13 @@ const u32 nfs4_pathconf_bitmap[2] = {
 	0
 };
 
-const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE
+const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE
 			| FATTR4_WORD0_MAXREAD
 			| FATTR4_WORD0_MAXWRITE
 			| FATTR4_WORD0_LEASE_TIME,
 			FATTR4_WORD1_TIME_DELTA
-			| FATTR4_WORD1_FS_LAYOUT_TYPES
+			| FATTR4_WORD1_FS_LAYOUT_TYPES,
+			FATTR4_WORD2_LAYOUT_BLKSIZE
 };
 
 const u32 nfs4_fs_locations_bitmap[2] = {
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 5f769f8..0261669 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -113,7 +113,11 @@ static int nfs4_stat_to_errno(int);
 #define encode_restorefh_maxsz  (op_encode_hdr_maxsz)
 #define decode_restorefh_maxsz  (op_decode_hdr_maxsz)
 #define encode_fsinfo_maxsz	(encode_getattr_maxsz)
-#define decode_fsinfo_maxsz	(op_decode_hdr_maxsz + 15)
+/* The 5 accounts for the PNFS attributes, and assumes that at most three
+ * layout types will be returned.
+ */
+#define decode_fsinfo_maxsz	(op_decode_hdr_maxsz + \
+				 nfs4_fattr_bitmap_maxsz + 4 + 8 + 5)
 #define encode_renew_maxsz	(op_encode_hdr_maxsz + 3)
 #define decode_renew_maxsz	(op_decode_hdr_maxsz)
 #define encode_setclientid_maxsz \
@@ -1123,6 +1127,35 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm
 	hdr->replen += decode_getattr_maxsz;
 }
 
+static void
+encode_getattr_three(struct xdr_stream *xdr,
+		     uint32_t bm0, uint32_t bm1, uint32_t bm2,
+		     struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	p = reserve_space(xdr, 4);
+	*p = cpu_to_be32(OP_GETATTR);
+	if (bm2) {
+		p = reserve_space(xdr, 16);
+		*p++ = cpu_to_be32(3);
+		*p++ = cpu_to_be32(bm0);
+		*p++ = cpu_to_be32(bm1);
+		*p = cpu_to_be32(bm2);
+	} else if (bm1) {
+		p = reserve_space(xdr, 12);
+		*p++ = cpu_to_be32(2);
+		*p++ = cpu_to_be32(bm0);
+		*p = cpu_to_be32(bm1);
+	} else {
+		p = reserve_space(xdr, 8);
+		*p++ = cpu_to_be32(1);
+		*p = cpu_to_be32(bm0);
+	}
+	hdr->nops++;
+	hdr->replen += decode_getattr_maxsz;
+}
+
 static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
 {
 	encode_getattr_two(xdr, bitmask[0] & nfs4_fattr_bitmap[0],
@@ -1131,8 +1164,11 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c
 
 static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
 {
-	encode_getattr_two(xdr, bitmask[0] & nfs4_fsinfo_bitmap[0],
-			   bitmask[1] & nfs4_fsinfo_bitmap[1], hdr);
+	encode_getattr_three(xdr,
+			     bitmask[0] & nfs4_fsinfo_bitmap[0],
+			     bitmask[1] & nfs4_fsinfo_bitmap[1],
+			     bitmask[2] & nfs4_fsinfo_bitmap[2],
+			     hdr);
 }
 
 static void encode_fs_locations(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
@@ -2643,7 +2679,7 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req,
 	struct compound_hdr hdr = {
 		.nops	= 0,
 	};
-	const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
+	const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME };
 
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_setclientid_confirm(xdr, arg, &hdr);
@@ -2787,7 +2823,7 @@ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req,
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->la_seq_args),
 	};
-	const u32 lease_bitmap[2] = { FATTR4_WORD0_LEASE_TIME, 0 };
+	const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME };
 
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->la_seq_args, &hdr);
@@ -3068,14 +3104,17 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap)
 		goto out_overflow;
 	bmlen = be32_to_cpup(p);
 
-	bitmap[0] = bitmap[1] = 0;
+	bitmap[0] = bitmap[1] = bitmap[2] = 0;
 	p = xdr_inline_decode(xdr, (bmlen << 2));
 	if (unlikely(!p))
 		goto out_overflow;
 	if (bmlen > 0) {
 		bitmap[0] = be32_to_cpup(p++);
-		if (bmlen > 1)
-			bitmap[1] = be32_to_cpup(p);
+		if (bmlen > 1) {
+			bitmap[1] = be32_to_cpup(p++);
+			if (bmlen > 2)
+				bitmap[2] = be32_to_cpup(p);
+		}
 	}
 	return 0;
 out_overflow:
@@ -3107,8 +3146,9 @@ static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint3
 			return ret;
 		bitmap[0] &= ~FATTR4_WORD0_SUPPORTED_ATTRS;
 	} else
-		bitmask[0] = bitmask[1] = 0;
-	dprintk("%s: bitmask=%08x:%08x\n", __func__, bitmask[0], bitmask[1]);
+		bitmask[0] = bitmask[1] = bitmask[2] = 0;
+	dprintk("%s: bitmask=%08x:%08x:%08x\n", __func__,
+		bitmask[0], bitmask[1], bitmask[2]);
 	return 0;
 }
 
@@ -4162,7 +4202,7 @@ out_overflow:
 static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2] = {0};
+	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4188,7 +4228,7 @@ xdr_error:
 static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2] = {0};
+	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4220,7 +4260,7 @@ xdr_error:
 static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2] = {0};
+	uint32_t attrlen, bitmap[3] = {0};
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4360,7 +4400,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat
 {
 	__be32 *savep;
 	uint32_t attrlen,
-		 bitmap[2] = {0};
+		 bitmap[3] = {0};
 	int status;
 
 	status = decode_op_hdr(xdr, OP_GETATTR);
@@ -4446,10 +4486,32 @@ static int decode_attr_pnfstype(struct xdr_stream *xdr, uint32_t *bitmap,
 	return status;
 }
 
+/*
+ * The prefered block size for layout directed io
+ */
+static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
+				      uint32_t *res)
+{
+	__be32 *p;
+
+	dprintk("%s: bitmap is %x\n", __func__, bitmap[2]);
+	*res = 0;
+	if (bitmap[2] & FATTR4_WORD2_LAYOUT_BLKSIZE) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p)) {
+			print_overflow_msg(__func__, xdr);
+			return -EIO;
+		}
+		*res = be32_to_cpup(p);
+		bitmap[2] &= ~FATTR4_WORD2_LAYOUT_BLKSIZE;
+	}
+	return 0;
+}
+
 static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 {
 	__be32 *savep;
-	uint32_t attrlen, bitmap[2];
+	uint32_t attrlen, bitmap[3];
 	int status;
 
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -4477,6 +4539,9 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 	status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype);
 	if (status != 0)
 		goto xdr_error;
+	status = decode_attr_layout_blksize(xdr, bitmap, &fsinfo->blksize);
+	if (status)
+		goto xdr_error;
 
 	status = verify_attr_len(xdr, savep, attrlen);
 xdr_error:
@@ -4896,7 +4961,7 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 {
 	__be32 *savep;
 	uint32_t attrlen,
-		 bitmap[2] = {0};
+		 bitmap[3] = {0};
 	struct kvec *iov = req->rq_rcv_buf.head;
 	int status;
 
@@ -6852,7 +6917,7 @@ out:
 int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		       int plus)
 {
-	uint32_t bitmap[2] = {0};
+	uint32_t bitmap[3] = {0};
 	uint32_t len;
 	__be32 *p = xdr_inline_decode(xdr, 4);
 	if (unlikely(!p))
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 4faeac8..b2ea8b8 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -132,7 +132,7 @@ struct nfs_server {
 #endif
 
 #ifdef CONFIG_NFS_V4
-	u32			attr_bitmask[2];/* V4 bitmask representing the set
+	u32			attr_bitmask[3];/* V4 bitmask representing the set
 						   of attributes supported on this
 						   filesystem */
 	u32			cache_consistency_bitmask[2];
@@ -145,6 +145,7 @@ struct nfs_server {
 						   filesystem */
 	struct pnfs_layoutdriver_type  *pnfs_curr_ld; /* Active layout driver */
 	struct rpc_wait_queue	roc_rpcwaitq;
+	u32			pnfs_blksize;	/* layout_blksize attr */
 
 	/* the following fields are protected by nfs_client->cl_lock */
 	struct rb_root		state_owners;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 21f333e..94f27e5 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -122,6 +122,7 @@ struct nfs_fsinfo {
 	struct timespec		time_delta; /* server time granularity */
 	__u32			lease_time; /* in seconds */
 	__u32			layouttype; /* supported pnfs layout driver */
+	__u32			blksize; /* preferred pnfs io block size */
 };
 
 struct nfs_fsstat {
@@ -954,7 +955,7 @@ struct nfs4_server_caps_arg {
 };
 
 struct nfs4_server_caps_res {
-	u32				attr_bitmask[2];
+	u32				attr_bitmask[3];
 	u32				acl_bitmask;
 	u32				has_links;
 	u32				has_symlinks;