NFSv4.1: implement generic pnfs layer write switch

Signed-off-by: Andy Adamson <andros@citi.umich.edu>
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>
Signed-off-by: Dean Hildebrand <dhildeb@us.ibm.com>
Signed-off-by: Fred Isaman <iisaman@citi.umich.edu>
Signed-off-by: J. Bruce Fields <bfields@fieldses.org>
Signed-off-by: Mike Sager <sager@netapp.com>
Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com>
Signed-off-by: Tao Guo <guotao@nrchpc.ac.cn>
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: Fred Isaman <iisaman@netapp.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

6 files changed, 47 insertions, 0 deletions

diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 0040a5ee6208..9d21bfeec88f 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -238,6 +238,12 @@ filelayout_read_pagelist(struct nfs_read_data *data)
         return PNFS_ATTEMPTED;
 }
 
+static enum pnfs_try_status
+filelayout_write_pagelist(struct nfs_write_data *data, int sync)
+{
+        return PNFS_NOT_ATTEMPTED;
+}
+
 /*
  * filelayout_check_layout()
  *
@@ -455,6 +461,7 @@ static struct pnfs_layoutdriver_type filelayout_type = {
         .free_lseg              = filelayout_free_lseg,
         .pg_test                = filelayout_pg_test,
         .read_pagelist          = filelayout_read_pagelist,
+        .write_pagelist         = filelayout_write_pagelist,
 };
 
 static int __init nfs4filelayout_init(void)
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 5f205d31d96c..f38813a0a295 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -895,6 +895,30 @@ pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode)
         pgio->pg_test = (ld && ld->pg_test) ? pnfs_write_pg_test : NULL;
 }
 
+enum pnfs_try_status
+pnfs_try_to_write_data(struct nfs_write_data *wdata,
+                        const struct rpc_call_ops *call_ops, int how)
+{
+        struct inode *inode = wdata->inode;
+        enum pnfs_try_status trypnfs;
+        struct nfs_server *nfss = NFS_SERVER(inode);
+
+        wdata->mds_ops = call_ops;
+
+        dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__,
+                inode->i_ino, wdata->args.count, wdata->args.offset, how);
+
+        trypnfs = nfss->pnfs_curr_ld->write_pagelist(wdata, how);
+        if (trypnfs == PNFS_NOT_ATTEMPTED) {
+                put_lseg(wdata->lseg);
+                wdata->lseg = NULL;
+        } else
+                nfs_inc_stats(inode, NFSIOS_PNFS_WRITE);
+
+        dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs);
+        return trypnfs;
+}
+
 /*
  * Call the appropriate parallel I/O subsystem read function.
  */
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 1d4e6317fa95..6380b9405bcd 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -79,6 +79,7 @@ struct pnfs_layoutdriver_type {
          * 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);
 };
 
 struct pnfs_layout_hdr {
@@ -120,6 +121,8 @@ pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx,
                    enum pnfs_iomode access_type);
 void set_pnfs_layoutdriver(struct nfs_server *, u32 id);
 void unset_pnfs_layoutdriver(struct nfs_server *);
+enum pnfs_try_status pnfs_try_to_write_data(struct nfs_write_data *,
+                                             const struct rpc_call_ops *, int);
 enum pnfs_try_status pnfs_try_to_read_data(struct nfs_read_data *,
                                             const struct rpc_call_ops *);
 void pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *);
@@ -200,6 +203,13 @@ pnfs_try_to_read_data(struct nfs_read_data *data,
         return PNFS_NOT_ATTEMPTED;
 }
 
+static inline enum pnfs_try_status
+pnfs_try_to_write_data(struct nfs_write_data *data,
+                       const struct rpc_call_ops *call_ops, int how)
+{
+        return PNFS_NOT_ATTEMPTED;
+}
+
 static inline bool
 pnfs_roc(struct inode *ino)
 {
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 49c4784c24e5..df99c5b0ee65 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -873,6 +873,10 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
         data->res.verf    = &data->verf;
         nfs_fattr_init(&data->fattr);
 
+        if (data->lseg &&
+            (pnfs_try_to_write_data(data, call_ops, how) == PNFS_ATTEMPTED))
+                return 0;
+
         return nfs_initiate_write(data, NFS_CLIENT(inode), call_ops, how);
 }
 
diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h
index 37a143732d02..8866bb3502ee 100644
--- a/include/linux/nfs_iostat.h
+++ b/include/linux/nfs_iostat.h
@@ -114,6 +114,7 @@ enum nfs_stat_eventcounters {
         NFSIOS_SHORTWRITE,
         NFSIOS_DELAY,
         NFSIOS_PNFS_READ,
+        NFSIOS_PNFS_WRITE,
         __NFSIOS_COUNTSMAX,
 };
 
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 09d96812d6d0..c82ad33cffe1 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1039,6 +1039,7 @@ struct nfs_write_data {
         struct nfs_writeargs    args;           /* argument struct */
         struct nfs_writeres     res;            /* result struct */
         struct pnfs_layout_segment *lseg;
+        const struct rpc_call_ops *mds_ops;
         int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data);
 #ifdef CONFIG_NFS_V4
         unsigned long           timestamp;      /* For lease renewal */