pnfs/flexfiles: Add the FlexFile Layout Driver

The flexfile layout is a new layout that extends the
file layout. It is currently being drafted as a specification at
https://datatracker.ietf.org/doc/draft-ietf-nfsv4-layout-types/Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Tom Haynes <loghyr@primarydata.com>
Signed-off-by: Tao Peng <bergwolf@primarydata.com>

fs/nfs/Kconfig

@@ -128,6 +128,11 @@ config PNFS_OBJLAYOUT
 	depends on NFS_V4_1 && SCSI_OSD_ULD
 	default NFS_V4
 
+config PNFS_FLEXFILE_LAYOUT
+	tristate
+	depends on NFS_V4_1 && NFS_V3
+	default m
+
 config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
 	string "NFSv4.1 Implementation ID Domain"
 	depends on NFS_V4_1

fs/nfs/Makefile

@@ -33,3 +33,4 @@ nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
 obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
 obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
+obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/

fs/nfs/flexfilelayout/Makefile

+#
+# Makefile for the pNFS Flexfile Layout Driver kernel module
+#
+obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += nfs_layout_flexfiles.o
+nfs_layout_flexfiles-y := flexfilelayout.o flexfilelayoutdev.o

fs/nfs/flexfilelayout/flexfilelayout.h

+/*
+ * NFSv4 flexfile layout driver data structures.
+ *
+ * Copyright (c) 2014, Primary Data, Inc. All rights reserved.
+ *
+ * Tao Peng <bergwolf@primarydata.com>
+ */
+
+#ifndef FS_NFS_NFS4FLEXFILELAYOUT_H
+#define FS_NFS_NFS4FLEXFILELAYOUT_H
+
+#include "../pnfs.h"
+
+/* XXX: Let's filter out insanely large mirror count for now to avoid oom
+ * due to network error etc. */
+#define NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT 4096
+
+struct nfs4_ff_ds_version {
+	u32				version;
+	u32				minor_version;
+	u32				rsize;
+	u32				wsize;
+	bool				tightly_coupled;
+};
+
+/* chained in global deviceid hlist */
+struct nfs4_ff_layout_ds {
+	struct nfs4_deviceid_node	id_node;
+	u32				ds_versions_cnt;
+	struct nfs4_ff_ds_version	*ds_versions;
+	struct nfs4_pnfs_ds		*ds;
+};
+
+struct nfs4_ff_layout_ds_err {
+	struct list_head		list; /* linked in mirror error_list */
+	u64				offset;
+	u64				length;
+	int				status;
+	enum nfs_opnum4			opnum;
+	nfs4_stateid			stateid;
+	struct nfs4_deviceid		deviceid;
+};
+
+struct nfs4_ff_layout_mirror {
+	u32				ds_count;
+	u32				efficiency;
+	struct nfs4_ff_layout_ds	*mirror_ds;
+	u32				fh_versions_cnt;
+	struct nfs_fh			*fh_versions;
+	nfs4_stateid			stateid;
+	struct nfs4_string		user_name;
+	struct nfs4_string		group_name;
+	u32				uid;
+	u32				gid;
+	struct rpc_cred			*cred;
+	spinlock_t			lock;
+};
+
+struct nfs4_ff_layout_segment {
+	struct pnfs_layout_segment	generic_hdr;
+	u64				stripe_unit;
+	u32				mirror_array_cnt;
+	struct nfs4_ff_layout_mirror	**mirror_array;
+};
+
+struct nfs4_flexfile_layout {
+	struct pnfs_layout_hdr generic_hdr;
+	struct pnfs_ds_commit_info commit_info;
+	struct list_head	error_list; /* nfs4_ff_layout_ds_err */
+};
+
+static inline struct nfs4_flexfile_layout *
+FF_LAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo)
+{
+	return container_of(lo, struct nfs4_flexfile_layout, generic_hdr);
+}
+
+static inline struct nfs4_ff_layout_segment *
+FF_LAYOUT_LSEG(struct pnfs_layout_segment *lseg)
+{
+	return container_of(lseg,
+			    struct nfs4_ff_layout_segment,
+			    generic_hdr);
+}
+
+static inline struct nfs4_deviceid_node *
+FF_LAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg, u32 idx)
+{
+	if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt ||
+	    FF_LAYOUT_LSEG(lseg)->mirror_array[idx] == NULL ||
+	    FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds == NULL)
+		return NULL;
+	return &FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds->id_node;
+}
+
+static inline struct nfs4_ff_layout_ds *
+FF_LAYOUT_MIRROR_DS(struct nfs4_deviceid_node *node)
+{
+	return container_of(node, struct nfs4_ff_layout_ds, id_node);
+}
+
+static inline struct nfs4_ff_layout_mirror *
+FF_LAYOUT_COMP(struct pnfs_layout_segment *lseg, u32 idx)
+{
+	if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt)
+		return NULL;
+	return FF_LAYOUT_LSEG(lseg)->mirror_array[idx];
+}
+
+static inline u32
+FF_LAYOUT_MIRROR_COUNT(struct pnfs_layout_segment *lseg)
+{
+	return FF_LAYOUT_LSEG(lseg)->mirror_array_cnt;
+}
+
+static inline bool
+ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node)
+{
+	return nfs4_test_deviceid_unavailable(node);
+}
+
+static inline int
+nfs4_ff_layout_ds_version(struct pnfs_layout_segment *lseg, u32 ds_idx)
+{
+	return FF_LAYOUT_COMP(lseg, ds_idx)->mirror_ds->ds_versions[0].version;
+}
+
+struct nfs4_ff_layout_ds *
+nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+			    gfp_t gfp_flags);
+void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds);
+void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds);
+int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
+			     struct nfs4_ff_layout_mirror *mirror, u64 offset,
+			     u64 length, int status, enum nfs_opnum4 opnum,
+			     gfp_t gfp_flags);
+int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo,
+			      struct xdr_stream *xdr, int *count,
+			      const struct pnfs_layout_range *range);
+struct nfs_fh *
+nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx);
+
+struct nfs4_pnfs_ds *
+nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
+			  bool fail_return);
+
+struct rpc_clnt *
+nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg,
+				 u32 ds_idx,
+				 struct nfs_client *ds_clp,
+				 struct inode *inode);
+struct rpc_cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg,
+				       u32 ds_idx, struct rpc_cred *mdscred);
+bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg);
+#endif /* FS_NFS_NFS4FLEXFILELAYOUT_H */

fs/nfs/idmap.c

@@ -152,7 +152,7 @@ void nfs_fattr_map_and_free_names(struct nfs_server *server, struct nfs_fattr *f
 		nfs_fattr_free_group_name(fattr);
 }
 
-static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res)
+int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res)
 {
 	unsigned long val;
 	char buf[16];
@@ -166,6 +166,7 @@ static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *re
 	*res = val;
 	return 1;
 }
+EXPORT_SYMBOL_GPL(nfs_map_string_to_numeric);
 
 static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen)
 {

fs/nfs/nfs4proc.c

@@ -7796,9 +7796,7 @@ static void nfs4_layoutreturn_release(void *calldata)
 	spin_lock(&lo->plh_inode->i_lock);
 	if (lrp->res.lrs_present)
 		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
-	clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags);
-	smp_mb__after_atomic();
-	wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
+	pnfs_clear_layoutreturn_waitbit(lo);
 	clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
 	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 	lo->plh_block_lgets--;

fs/nfs/pnfs.c

@@ -910,7 +910,9 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 			pnfs_layout_io_set_failed(lo, range->iomode);
 		}
 		return NULL;
-	}
+	} else
+		pnfs_layout_clear_fail_bit(lo,
+				pnfs_iomode_to_fail_bit(range->iomode));
 
 	return lseg;
 }
@@ -930,6 +932,13 @@ static void pnfs_clear_layoutcommit(struct inode *inode,
 	}
 }
 
+void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
+{
+	clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
+}
+
 static int
 pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
 		       enum pnfs_iomode iomode, bool sync)
@@ -943,6 +952,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
 		status = -ENOMEM;
 		spin_lock(&ino->i_lock);
 		lo->plh_block_lgets--;
+		pnfs_clear_layoutreturn_waitbit(lo);
 		rpc_wake_up(&NFS_SERVER(ino)->roc_rpcwaitq);
 		spin_unlock(&ino->i_lock);
 		pnfs_put_layout_hdr(lo);
@@ -1418,6 +1428,15 @@ static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
 				   TASK_UNINTERRUPTIBLE);
 }
 
+static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo)
+{
+	unsigned long *bitlock = &lo->plh_flags;
+
+	clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock);
+	smp_mb__after_atomic();
+	wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET);
+}
+
 /*
  * Layout segment is retreived from the server if not cached.
  * The appropriate layout segment is referenced and returned to the caller.
@@ -1499,6 +1518,8 @@ pnfs_update_layout(struct inode *ino,
 		spin_unlock(&ino->i_lock);
 		dprintk("%s wait for layoutreturn\n", __func__);
 		if (pnfs_prepare_to_retry_layoutget(lo)) {
+			if (first)
+				pnfs_clear_first_layoutget(lo);
 			pnfs_put_layout_hdr(lo);
 			dprintk("%s retrying\n", __func__);
 			goto lookup_again;
@@ -1533,13 +1554,8 @@ pnfs_update_layout(struct inode *ino,
 	pnfs_clear_retry_layoutget(lo);
 	atomic_dec(&lo->plh_outstanding);
 out_put_layout_hdr:
-	if (first) {
-		unsigned long *bitlock = &lo->plh_flags;
-
-		clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock);
-		smp_mb__after_atomic();
-		wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET);
-	}
+	if (first)
+		pnfs_clear_first_layoutget(lo);
 	pnfs_put_layout_hdr(lo);
 out:
 	dprintk("%s: inode %s/%llu pNFS layout segment %s for "

fs/nfs/pnfs.h

@@ -278,6 +278,7 @@ struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       u64 count,
 					       enum pnfs_iomode iomode,
 					       gfp_t gfp_flags);
+void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo);
 
 void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
 int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *);

include/linux/nfs4.h

@@ -516,6 +516,7 @@ enum pnfs_layouttype {
 	LAYOUT_NFSV4_1_FILES  = 1,
 	LAYOUT_OSD2_OBJECTS = 2,
 	LAYOUT_BLOCK_VOLUME = 3,
+	LAYOUT_FLEX_FILES = 4,
 };
 
 /* used for both layout return and recall */

include/linux/nfs_idmap.h

@@ -73,5 +73,7 @@ int nfs_map_group_to_gid(const struct nfs_server *, const char *, size_t, kgid_t
 int nfs_map_uid_to_name(const struct nfs_server *, kuid_t, char *, size_t);
 int nfs_map_gid_to_group(const struct nfs_server *, kgid_t, char *, size_t);
 
+int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res);
+
 extern unsigned int nfs_idmap_cache_timeout;
 #endif /* NFS_IDMAP_H */

include/linux/sunrpc/metrics.h

@@ -89,6 +89,8 @@ void			rpc_free_iostats(struct rpc_iostats *);
 static inline struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { return NULL; }
 static inline void rpc_count_iostats(const struct rpc_task *task,
 				     struct rpc_iostats *stats) {}
+static inline void rpc_count_iostats_metrics(const struct rpc_task *,
+					     struct rpc_iostats *) {}
 static inline void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) {}
 static inline void rpc_free_iostats(struct rpc_iostats *stats) {}