1 files changed, 150 insertions, 65 deletions

diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 442ebf68eee..4fb309a2b4c 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -62,7 +62,7 @@ enum {
 	NFS_LAYOUT_RW_FAILED,		/* get rw layout failed stop trying */
 	NFS_LAYOUT_BULK_RECALL,		/* bulk recall affecting layout */
 	NFS_LAYOUT_ROC,			/* some lseg had roc bit set */
-	NFS_LAYOUT_DESTROYED,		/* no new use of layout allowed */
+	NFS_LAYOUT_RETURN,		/* Return this layout ASAP */
 };
 
 enum layoutdriver_policy_flags {
@@ -94,18 +94,27 @@ struct pnfs_layoutdriver_type {
 	const struct nfs_pageio_ops *pg_read_ops;
 	const struct nfs_pageio_ops *pg_write_ops;
 
+	struct pnfs_ds_commit_info *(*get_ds_info) (struct inode *inode);
 	void (*mark_request_commit) (struct nfs_page *req,
-					struct pnfs_layout_segment *lseg);
-	void (*clear_request_commit) (struct nfs_page *req);
-	int (*scan_commit_lists) (struct inode *inode, int max, spinlock_t *lock);
-	int (*commit_pagelist)(struct inode *inode, struct list_head *mds_pages, int how);
+				     struct pnfs_layout_segment *lseg,
+				     struct nfs_commit_info *cinfo);
+	void (*clear_request_commit) (struct nfs_page *req,
+				      struct nfs_commit_info *cinfo);
+	int (*scan_commit_lists) (struct nfs_commit_info *cinfo,
+				  int max);
+	void (*recover_commit_reqs) (struct list_head *list,
+				     struct nfs_commit_info *cinfo);
+	int (*commit_pagelist)(struct inode *inode,
+			       struct list_head *mds_pages,
+			       int how,
+			       struct nfs_commit_info *cinfo);
 
 	/*
 	 * Return PNFS_ATTEMPTED to indicate the layout code has attempted
 	 * I/O, else return PNFS_NOT_ATTEMPTED to fall back to normal NFS
 	 */
-	enum pnfs_try_status (*read_pagelist) (struct nfs_read_data *nfs_data);
-	enum pnfs_try_status (*write_pagelist) (struct nfs_write_data *nfs_data, int how);
+	enum pnfs_try_status (*read_pagelist) (struct nfs_pgio_data *nfs_data);
+	enum pnfs_try_status (*write_pagelist) (struct nfs_pgio_data *nfs_data, int how);
 
 	void (*free_deviceid_node) (struct nfs4_deviceid_node *);
 
@@ -123,12 +132,13 @@ struct pnfs_layoutdriver_type {
 struct pnfs_layout_hdr {
 	atomic_t		plh_refcount;
 	struct list_head	plh_layouts;   /* other client layouts */
-	struct list_head	plh_bulk_recall; /* clnt list of bulk recalls */
+	struct list_head	plh_bulk_destroy;
 	struct list_head	plh_segs;      /* layout segments list */
 	nfs4_stateid		plh_stateid;
 	atomic_t		plh_outstanding; /* number of RPCs out */
 	unsigned long		plh_block_lgets; /* block LAYOUTGET if >0 */
 	u32			plh_barrier; /* ignore lower seqids */
+	unsigned long		plh_retry_timestamp;
 	unsigned long		plh_flags;
 	loff_t			plh_lwb; /* last write byte for layoutcommit */
 	struct rpc_cred		*plh_lc_cred; /* layoutcommit cred */
@@ -139,9 +149,10 @@ struct pnfs_device {
 	struct nfs4_deviceid dev_id;
 	unsigned int  layout_type;
 	unsigned int  mincount;
+	unsigned int  maxcount;	/* gdia_maxcount */
 	struct page **pages;
 	unsigned int  pgbase;
-	unsigned int  pglen;
+	unsigned int  pglen;	/* reply buffer length */
 };
 
 #define NFS4_PNFS_GETDEVLIST_MAXNUM 16
@@ -160,49 +171,55 @@ extern int nfs4_proc_getdevicelist(struct nfs_server *server,
 				   const struct nfs_fh *fh,
 				   struct pnfs_devicelist *devlist);
 extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
-				   struct pnfs_device *dev);
-extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp);
+				   struct pnfs_device *dev,
+				   struct rpc_cred *cred);
+extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags);
 extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 
 /* pnfs.c */
-void get_layout_hdr(struct pnfs_layout_hdr *lo);
-void put_lseg(struct pnfs_layout_segment *lseg);
-
-bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *);
-bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, int);
+void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo);
+void pnfs_put_lseg(struct pnfs_layout_segment *lseg);
 
 void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
 void unset_pnfs_layoutdriver(struct nfs_server *);
 void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *);
 int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
-void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *, struct nfs_page *);
+void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			        struct nfs_page *req, u64 wb_size);
 int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
-bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req);
+size_t pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio,
+			    struct nfs_page *prev, struct nfs_page *req);
 void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg);
-int pnfs_layout_process(struct nfs4_layoutget *lgp);
+struct pnfs_layout_segment *pnfs_layout_process(struct nfs4_layoutget *lgp);
 void pnfs_free_lseg_list(struct list_head *tmp_list);
 void pnfs_destroy_layout(struct nfs_inode *);
 void pnfs_destroy_all_layouts(struct nfs_client *);
-void put_layout_hdr(struct pnfs_layout_hdr *lo);
+int pnfs_destroy_layouts_byfsid(struct nfs_client *clp,
+		struct nfs_fsid *fsid,
+		bool is_recall);
+int pnfs_destroy_layouts_byclid(struct nfs_client *clp,
+		bool is_recall);
+void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo);
 void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
 			     const nfs4_stateid *new,
 			     bool update_barrier);
 int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
 				  struct pnfs_layout_hdr *lo,
 				  struct nfs4_state *open_state);
-int mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
+int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
 				struct pnfs_layout_range *recall_range);
 bool pnfs_roc(struct inode *ino);
 void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
-bool pnfs_roc_drain(struct inode *ino, u32 *barrier);
-void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
+bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task);
+void pnfs_set_layoutcommit(struct nfs_pgio_data *wdata);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
-void pnfs_ld_write_done(struct nfs_write_data *);
-void pnfs_ld_read_done(struct nfs_read_data *);
+int pnfs_commit_and_return_layout(struct inode *);
+void pnfs_ld_write_done(struct nfs_pgio_data *);
+void pnfs_ld_read_done(struct nfs_pgio_data *);
 struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       struct nfs_open_context *ctx,
 					       loff_t pos,
@@ -211,10 +228,18 @@ struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       gfp_t gfp_flags);
 
 void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
+int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *head,
+			const struct nfs_pgio_completion_ops *compl_ops,
+			struct nfs_direct_req *dreq);
+int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head,
+			const struct nfs_pgio_completion_ops *compl_ops,
+			struct nfs_direct_req *dreq);
+struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
 
 /* nfs4_deviceid_flags */
 enum {
 	NFS_DEVICEID_INVALID = 0,       /* set when MDS clientid recalled */
+	NFS_DEVICEID_UNAVAILABLE,	/* device temporarily unavailable */
 };
 
 /* pnfs_dev.c */
@@ -224,6 +249,7 @@ struct nfs4_deviceid_node {
 	const struct pnfs_layoutdriver_type *ld;
 	const struct nfs_client		*nfs_client;
 	unsigned long 			flags;
+	unsigned long			timestamp_unavailable;
 	struct nfs4_deviceid		deviceid;
 	atomic_t			ref;
 };
@@ -236,20 +262,16 @@ void nfs4_init_deviceid_node(struct nfs4_deviceid_node *,
 			     const struct nfs4_deviceid *);
 struct nfs4_deviceid_node *nfs4_insert_deviceid_node(struct nfs4_deviceid_node *);
 bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
+void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node);
+bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node);
 void nfs4_deviceid_purge_client(const struct nfs_client *);
 
-static inline int lo_fail_bit(u32 iomode)
-{
-	return iomode == IOMODE_RW ?
-			 NFS_LAYOUT_RW_FAILED : NFS_LAYOUT_RO_FAILED;
-}
-
 static inline struct pnfs_layout_segment *
-get_lseg(struct pnfs_layout_segment *lseg)
+pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 {
 	if (lseg) {
 		atomic_inc(&lseg->pls_refcount);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 	}
 	return lseg;
 }
@@ -261,49 +283,66 @@ static inline int pnfs_enabled_sb(struct nfs_server *nfss)
 }
 
 static inline int
-pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
+pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how,
+		 struct nfs_commit_info *cinfo)
 {
-	if (!test_and_clear_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags))
+	if (cinfo->ds == NULL || cinfo->ds->ncommitting == 0)
 		return PNFS_NOT_ATTEMPTED;
-	return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how);
+	return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how, cinfo);
+}
+
+static inline struct pnfs_ds_commit_info *
+pnfs_get_ds_info(struct inode *inode)
+{
+	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
+
+	if (ld == NULL || ld->get_ds_info == NULL)
+		return NULL;
+	return ld->get_ds_info(inode);
 }
 
 static inline bool
-pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
+pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
+			 struct nfs_commit_info *cinfo)
 {
 	struct inode *inode = req->wb_context->dentry->d_inode;
 	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
 
 	if (lseg == NULL || ld->mark_request_commit == NULL)
 		return false;
-	ld->mark_request_commit(req, lseg);
+	ld->mark_request_commit(req, lseg, cinfo);
 	return true;
 }
 
 static inline bool
-pnfs_clear_request_commit(struct nfs_page *req)
+pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo)
 {
 	struct inode *inode = req->wb_context->dentry->d_inode;
 	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
 
 	if (ld == NULL || ld->clear_request_commit == NULL)
 		return false;
-	ld->clear_request_commit(req);
+	ld->clear_request_commit(req, cinfo);
 	return true;
 }
 
 static inline int
-pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock)
+pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
+		       int max)
 {
-	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
-	int ret;
-
-	if (ld == NULL || ld->scan_commit_lists == NULL)
+	if (cinfo->ds == NULL || cinfo->ds->nwritten == 0)
 		return 0;
-	ret = ld->scan_commit_lists(inode, max, lock);
-	if (ret != 0)
-		set_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags);
-	return ret;
+	else
+		return NFS_SERVER(inode)->pnfs_curr_ld->scan_commit_lists(cinfo, max);
+}
+
+static inline void
+pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
+			 struct nfs_commit_info *cinfo)
+{
+	if (cinfo->ds == NULL || cinfo->ds->nwritten == 0)
+		return;
+	NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
 }
 
 /* Should the pNFS client commit and return the layout upon a setattr */
@@ -316,6 +355,15 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode)
 		PNFS_LAYOUTRET_ON_SETATTR;
 }
 
+static inline bool
+pnfs_layoutcommit_outstanding(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	return test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags) != 0 ||
+		test_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags) != 0;
+}
+
 static inline int pnfs_return_layout(struct inode *ino)
 {
 	struct nfs_inode *nfsi = NFS_I(ino);
@@ -327,6 +375,14 @@ static inline int pnfs_return_layout(struct inode *ino)
 	return 0;
 }
 
+static inline bool
+pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src,
+		   struct nfs_server *nfss)
+{
+	return (dst && src && src->bm != 0 && nfss->pnfs_curr_ld &&
+					nfss->pnfs_curr_ld->id == src->l_type);
+}
+
 #ifdef NFS_DEBUG
 void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id);
 #else
@@ -345,12 +401,12 @@ static inline void pnfs_destroy_layout(struct nfs_inode *nfsi)
 }
 
 static inline struct pnfs_layout_segment *
-get_lseg(struct pnfs_layout_segment *lseg)
+pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 {
 	return NULL;
 }
 
-static inline void put_lseg(struct pnfs_layout_segment *lseg)
+static inline void pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 {
 }
 
@@ -359,6 +415,11 @@ static inline int pnfs_return_layout(struct inode *ino)
 	return 0;
 }
 
+static inline int pnfs_commit_and_return_layout(struct inode *inode)
+{
+	return 0;
+}
+
 static inline bool
 pnfs_ld_layoutret_on_setattr(struct inode *inode)
 {
@@ -382,7 +443,7 @@ pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
 }
 
 static inline bool
-pnfs_roc_drain(struct inode *ino, u32 *barrier)
+pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task)
 {
 	return false;
 }
@@ -396,45 +457,69 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
 {
 }
 
-static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode)
-{
-	return false;
-}
-
-static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags)
+static inline int
+pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how,
+		 struct nfs_commit_info *cinfo)
 {
-	return false;
+	return PNFS_NOT_ATTEMPTED;
 }
 
-static inline int
-pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
+static inline struct pnfs_ds_commit_info *
+pnfs_get_ds_info(struct inode *inode)
 {
-	return PNFS_NOT_ATTEMPTED;
+	return NULL;
 }
 
 static inline bool
-pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
+pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
+			 struct nfs_commit_info *cinfo)
 {
 	return false;
 }
 
 static inline bool
-pnfs_clear_request_commit(struct nfs_page *req)
+pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo)
 {
 	return false;
 }
 
 static inline int
-pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock)
+pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
+		       int max)
 {
 	return 0;
 }
 
+static inline void
+pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
+			 struct nfs_commit_info *cinfo)
+{
+}
+
 static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
 	return 0;
 }
 
+static inline bool
+pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src,
+		   struct nfs_server *nfss)
+{
+	return false;
+}
+
+static inline bool
+pnfs_layoutcommit_outstanding(struct inode *inode)
+{
+	return false;
+}
+
+
+static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
+{
+	return NULL;
+}
+
 #endif /* CONFIG_NFS_V4_1 */
 
 #endif /* FS_NFS_PNFS_H */