pnfs-obj: Move to ORE for v3.2 merge window

index 1d06f8e..1300736 100644
@@ -287,17 +287,14 @@ static void _rpc_read_complete(struct work_struct *work)
 void
 objlayout_read_done(struct objlayout_io_state *state, ssize_t status, bool sync)
 {
-	int eof = state->eof;
-	struct nfs_read_data *rdata;
+	struct nfs_read_data *rdata = state->rpcdata;
 
 	state->status = status;
-	dprintk("%s: Begin status=%zd eof=%d\n", __func__, status, eof);
-	rdata = state->rpcdata;
+	dprintk("%s: Begin status=%zd eof=%d\n", __func__,
+		status, rdata->res.eof);
 	rdata->task.tk_status = status;
-	if (status >= 0) {
+	if (status >= 0)
 		rdata->res.count = status;
-		rdata->res.eof = eof;
-	}
 	objlayout_iodone(state);
 	/* must not use state after this point */
 

@@ -330,11 +327,14 @@ enum pnfs_try_status
 			status = 0;
 			rdata->res.count = 0;
 			rdata->res.eof = 1;
+			/*FIXME: do we need to call pnfs_ld_read_done() */
 			goto out;
 		}
 		count = eof - offset;
 	}
 
+	rdata->res.eof = (offset + count) >= eof;
+
 	state = objlayout_alloc_io_state(NFS_I(rdata->inode)->layout,
 					 rdata->args.pages, rdata->args.pgbase,
 					 offset, count,

@@ -345,8 +345,6 @@ enum pnfs_try_status
 		goto out;
 	}
 
-	state->eof = state->offset + state->count >= eof;
-
 	status = objio_read_pagelist(state);
  out:
 	dprintk("%s: Return status %Zd\n", __func__, status);

index a8244c8..ffb884c 100644
@@ -86,7 +86,6 @@ struct objlayout_io_state {
 
 	void *rpcdata;
 	int status;             /* res */
-	int eof;                /* res */
 	int committed;          /* res */
 
 	/* Error reporting (layout_return) */

index d0cda12..0c7c9ec 100644
@@ -142,7 +142,7 @@ struct objio_segment {
 }
 
 struct objio_state;
-typedef ssize_t (*objio_done_fn)(struct objio_state *ios);
+typedef int (*objio_done_fn)(struct objio_state *ios);
 
 struct objio_state {
 	/* Generic layer */

@@ -720,7 +720,7 @@ static int _io_rw_pagelist(struct objio_state *ios, gfp_t gfp_flags)
 	return 0;
 }
 
-static ssize_t _sync_done(struct objio_state *ios)
+static int _sync_done(struct objio_state *ios)
 {
 	struct completion *waiting = ios->private;
 

@@ -742,10 +742,10 @@ static void _done_io(struct osd_request *or, void *p)
 	kref_put(&ios->kref, _last_io);
 }
 
-static ssize_t _io_exec(struct objio_state *ios)
+static int _io_exec(struct objio_state *ios)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
-	ssize_t status = 0; /* sync status */
+	int ret = 0;
 	unsigned i;
 	objio_done_fn saved_done_fn = ios->done;
 	bool sync = ios->ol_state.sync;

@@ -771,16 +771,16 @@ static ssize_t _io_exec(struct objio_state *ios)
 
 	if (sync) {
 		wait_for_completion(&wait);
-		status = saved_done_fn(ios);
+		ret = saved_done_fn(ios);
 	}
 
-	return status;
+	return ret;
 }
 
 /*
  * read
  */
-static ssize_t _read_done(struct objio_state *ios)
+static int _read_done(struct objio_state *ios)
 {
 	ssize_t status;
 	int ret = _io_check(ios, false);

@@ -793,7 +793,7 @@ static ssize_t _read_done(struct objio_state *ios)
 		status = ret;
 
 	objlayout_read_done(&ios->ol_state, status, ios->ol_state.sync);
-	return status;
+	return ret;
 }
 
 static int _read_mirrors(struct objio_state *ios, unsigned cur_comp)

@@ -833,7 +833,7 @@ static int _read_mirrors(struct objio_state *ios, unsigned cur_comp)
 	return ret;
 }
 
-static ssize_t _read_exec(struct objio_state *ios)
+static int _read_exec(struct objio_state *ios)
 {
 	unsigned i;
 	int ret;

@@ -847,14 +847,14 @@ static ssize_t _read_exec(struct objio_state *ios)
 	}
 
 	ios->done = _read_done;
-	return _io_exec(ios); /* In sync mode exec returns the io status */
+	return _io_exec(ios);
 
 err:
 	_io_free(ios);
 	return ret;
 }
 
-ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state)
+int objio_read_pagelist(struct objlayout_io_state *ol_state)
 {
 	struct objio_state *ios = container_of(ol_state, struct objio_state,
 					       ol_state);

@@ -870,7 +870,7 @@ ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state)
 /*
  * write
  */
-static ssize_t _write_done(struct objio_state *ios)
+static int _write_done(struct objio_state *ios)
 {
 	ssize_t status;
 	int ret = _io_check(ios, true);

@@ -887,7 +887,7 @@ static ssize_t _write_done(struct objio_state *ios)
 	}
 
 	objlayout_write_done(&ios->ol_state, status, ios->ol_state.sync);
-	return status;
+	return ret;
 }
 
 static int _write_mirrors(struct objio_state *ios, unsigned cur_comp)

@@ -955,7 +955,7 @@ static int _write_mirrors(struct objio_state *ios, unsigned cur_comp)
 	return ret;
 }
 
-static ssize_t _write_exec(struct objio_state *ios)
+static int _write_exec(struct objio_state *ios)
 {
 	unsigned i;
 	int ret;

@@ -969,14 +969,14 @@ static ssize_t _write_exec(struct objio_state *ios)
 	}
 
 	ios->done = _write_done;
-	return _io_exec(ios); /* In sync mode exec returns the io->status */
+	return _io_exec(ios);
 
 err:
 	_io_free(ios);
 	return ret;
 }
 
-ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state, bool stable)
+int objio_write_pagelist(struct objlayout_io_state *ol_state, bool stable)
 {
 	struct objio_state *ios = container_of(ol_state, struct objio_state,
 					       ol_state);

index 1300736..99c807d 100644
@@ -315,16 +315,13 @@ enum pnfs_try_status
 	loff_t offset = rdata->args.offset;
 	size_t count = rdata->args.count;
 	struct objlayout_io_state *state;
-	ssize_t status = 0;
+	int err;
 	loff_t eof;
 
-	dprintk("%s: Begin inode %p offset %llu count %d\n",
-		__func__, rdata->inode, offset, (int)count);
-
 	eof = i_size_read(rdata->inode);
 	if (unlikely(offset + count > eof)) {
 		if (offset >= eof) {
-			status = 0;
+			err = 0;
 			rdata->res.count = 0;
 			rdata->res.eof = 1;
 			/*FIXME: do we need to call pnfs_ld_read_done() */

@@ -341,14 +338,19 @@ enum pnfs_try_status
 					 rdata->lseg, rdata,
 					 GFP_KERNEL);
 	if (unlikely(!state)) {
-		status = -ENOMEM;
+		err = -ENOMEM;
 		goto out;
 	}
+	dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n",
+		__func__, rdata->inode->i_ino, offset, count, rdata->res.eof);
 
-	status = objio_read_pagelist(state);
+	err = objio_read_pagelist(state);
  out:
-	dprintk("%s: Return status %Zd\n", __func__, status);
-	rdata->pnfs_error = status;
+	if (unlikely(err)) {
+		rdata->pnfs_error = err;
+		dprintk("%s: Returned Error %d\n", __func__, err);
+		return PNFS_NOT_ATTEMPTED;
+	}
 	return PNFS_ATTEMPTED;
 }
 

@@ -406,10 +408,7 @@ enum pnfs_try_status
 			 int how)
 {
 	struct objlayout_io_state *state;
-	ssize_t status;
-
-	dprintk("%s: Begin inode %p offset %llu count %u\n",
-		__func__, wdata->inode, wdata->args.offset, wdata->args.count);
+	int err;
 
 	state = objlayout_alloc_io_state(NFS_I(wdata->inode)->layout,
 					 wdata->args.pages,

@@ -419,16 +418,19 @@ enum pnfs_try_status
 					 wdata->lseg, wdata,
 					 GFP_NOFS);
 	if (unlikely(!state)) {
-		status = -ENOMEM;
+		err = -ENOMEM;
 		goto out;
 	}
 
 	state->sync = how & FLUSH_SYNC;
 
-	status = objio_write_pagelist(state, how & FLUSH_STABLE);
+	err = objio_write_pagelist(state, how & FLUSH_STABLE);
  out:
-	dprintk("%s: Return status %Zd\n", __func__, status);
-	wdata->pnfs_error = status;
+	if (unlikely(err)) {
+		wdata->pnfs_error = err;
+		dprintk("%s: Returned Error %d\n", __func__, err);
+		return PNFS_NOT_ATTEMPTED;
+	}
 	return PNFS_ATTEMPTED;
 }
 

index ffb884c..4edac9b 100644
@@ -115,8 +115,8 @@ extern int objio_alloc_io_state(
 	gfp_t gfp_flags);
 extern void objio_free_io_state(struct objlayout_io_state *state);
 
-extern ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state);
-extern ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state,
+extern int objio_read_pagelist(struct objlayout_io_state *ol_state);
+extern int objio_write_pagelist(struct objlayout_io_state *ol_state,
 				    bool stable);
 
 /*

index 0c7c9ec..48eb91a 100644
@@ -148,6 +148,13 @@ struct objio_state {
 	/* Generic layer */
 	struct objlayout_io_state ol_state;
 
+	struct page **pages;
+	unsigned pgbase;
+	unsigned nr_pages;
+	unsigned long count;
+	loff_t offset;
+	bool sync;
+
 	struct objio_segment *layout;
 
 	struct kref kref;

@@ -394,30 +401,43 @@ void objio_free_lseg(struct pnfs_layout_segment *lseg)
 	kfree(objio_seg);
 }
 
-int objio_alloc_io_state(struct pnfs_layout_segment *lseg,
-			 struct objlayout_io_state **outp,
-			 gfp_t gfp_flags)
+static int
+objio_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type,
+	struct pnfs_layout_segment *lseg, struct page **pages, unsigned pgbase,
+	loff_t offset, size_t count, void *rpcdata, gfp_t gfp_flags,
+	struct objio_state **outp)
 {
 	struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
 	struct objio_state *ios;
-	const unsigned first_size = sizeof(*ios) +
-				objio_seg->num_comps * sizeof(ios->per_dev[0]);
-	const unsigned sec_size = objio_seg->num_comps *
-						sizeof(ios->ol_state.ioerrs[0]);
-
-	ios = kzalloc(first_size + sec_size, gfp_flags);
-	if (unlikely(!ios))
+	struct __alloc_objio_state {
+		struct objio_state objios;
+		struct _objio_per_comp per_dev[objio_seg->num_comps];
+		struct pnfs_osd_ioerr ioerrs[objio_seg->num_comps];
+	} *aos;
+
+	aos = kzalloc(sizeof(*aos), gfp_flags);
+	if (unlikely(!aos))
 		return -ENOMEM;
 
-	ios->layout = objio_seg;
-	ios->ol_state.ioerrs = ((void *)ios) + first_size;
-	ios->ol_state.num_comps = objio_seg->num_comps;
+	ios = &aos->objios;
 
-	*outp = &ios->ol_state;
+	ios->layout = objio_seg;
+	objlayout_init_ioerrs(&aos->objios.ol_state, objio_seg->num_comps,
+			aos->ioerrs, rpcdata, pnfs_layout_type);
+
+	ios->pages = pages;
+	ios->pgbase = pgbase;
+	ios->nr_pages = (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	ios->offset = offset;
+	ios->count = count;
+	ios->sync = 0;
+	BUG_ON(ios->nr_pages > (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT);
+
+	*outp = ios;
 	return 0;
 }
 
-void objio_free_io_state(struct objlayout_io_state *ol_state)
+void objio_free_result(struct objlayout_io_state *ol_state)
 {
 	struct objio_state *ios = container_of(ol_state, struct objio_state,
 					       ol_state);

@@ -598,7 +618,7 @@ static int _add_stripe_unit(struct objio_state *ios,  unsigned *cur_pg,
 	if (per_dev->bio == NULL) {
 		unsigned pages_in_stripe = ios->layout->group_width *
 				      (ios->layout->stripe_unit / PAGE_SIZE);
-		unsigned bio_size = (ios->ol_state.nr_pages + pages_in_stripe) /
+		unsigned bio_size = (ios->nr_pages + pages_in_stripe) /
 				    ios->layout->group_width;
 
 		if (BIO_MAX_PAGES_KMALLOC < bio_size)

@@ -615,11 +635,11 @@ static int _add_stripe_unit(struct objio_state *ios,  unsigned *cur_pg,
 		unsigned pglen = min_t(unsigned, PAGE_SIZE - pgbase, cur_len);
 		unsigned added_len;
 
-		BUG_ON(ios->ol_state.nr_pages <= pg);
+		BUG_ON(ios->nr_pages <= pg);
 		cur_len -= pglen;
 
 		added_len = bio_add_pc_page(q, per_dev->bio,
-					ios->ol_state.pages[pg], pglen, pgbase);
+					ios->pages[pg], pglen, pgbase);
 		if (unlikely(pglen != added_len))
 			return -ENOMEM;
 		pgbase = 0;

@@ -660,7 +680,7 @@ static int _prepare_one_group(struct objio_state *ios, u64 length,
 				cur_len = stripe_unit - si->unit_off;
 				page_off = si->unit_off & ~PAGE_MASK;
 				BUG_ON(page_off &&
-				      (page_off != ios->ol_state.pgbase));
+				      (page_off != ios->pgbase));
 			} else { /* dev > si->dev */
 				per_dev->offset = si->obj_offset - si->unit_off;
 				cur_len = stripe_unit;

@@ -693,8 +713,8 @@ static int _prepare_one_group(struct objio_state *ios, u64 length,
 
 static int _io_rw_pagelist(struct objio_state *ios, gfp_t gfp_flags)
 {
-	u64 length = ios->ol_state.count;
-	u64 offset = ios->ol_state.offset;
+	u64 length = ios->count;
+	u64 offset = ios->offset;
 	struct _striping_info si;
 	unsigned last_pg = 0;
 	int ret = 0;

@@ -748,7 +768,7 @@ static int _io_exec(struct objio_state *ios)
 	int ret = 0;
 	unsigned i;
 	objio_done_fn saved_done_fn = ios->done;
-	bool sync = ios->ol_state.sync;
+	bool sync = ios->sync;
 
 	if (sync) {
 		ios->done = _sync_done;

@@ -792,7 +812,7 @@ static int _read_done(struct objio_state *ios)
 	else
 		status = ret;
 
-	objlayout_read_done(&ios->ol_state, status, ios->ol_state.sync);
+	objlayout_read_done(&ios->ol_state, status, ios->sync);
 	return ret;
 }
 

@@ -854,12 +874,18 @@ static int _read_exec(struct objio_state *ios)
 	return ret;
 }
 
-int objio_read_pagelist(struct objlayout_io_state *ol_state)
+int objio_read_pagelist(struct nfs_read_data *rdata)
 {
-	struct objio_state *ios = container_of(ol_state, struct objio_state,
-					       ol_state);
+	struct objio_state *ios;
 	int ret;
 
+	ret = objio_alloc_io_state(NFS_I(rdata->inode)->layout,
+			rdata->lseg, rdata->args.pages, rdata->args.pgbase,
+			rdata->args.offset, rdata->args.count, rdata,
+			GFP_KERNEL, &ios);
+	if (unlikely(ret))
+		return ret;
+
 	ret = _io_rw_pagelist(ios, GFP_KERNEL);
 	if (unlikely(ret))
 		return ret;

@@ -886,7 +912,7 @@ static int _write_done(struct objio_state *ios)
 		status = ret;
 	}
 
-	objlayout_write_done(&ios->ol_state, status, ios->ol_state.sync);
+	objlayout_write_done(&ios->ol_state, status, ios->sync);
 	return ret;
 }
 

@@ -976,12 +1002,20 @@ static int _write_exec(struct objio_state *ios)
 	return ret;
 }
 
-int objio_write_pagelist(struct objlayout_io_state *ol_state, bool stable)
+int objio_write_pagelist(struct nfs_write_data *wdata, int how)
 {
-	struct objio_state *ios = container_of(ol_state, struct objio_state,
-					       ol_state);
+	struct objio_state *ios;
 	int ret;
 
+	ret = objio_alloc_io_state(NFS_I(wdata->inode)->layout,
+			wdata->lseg, wdata->args.pages, wdata->args.pgbase,
+			wdata->args.offset, wdata->args.count, wdata, GFP_NOFS,
+			&ios);
+	if (unlikely(ret))
+		return ret;
+
+	ios->sync = 0 != (how & FLUSH_SYNC);
+
 	/* TODO: ios->stable = stable; */
 	ret = _io_rw_pagelist(ios, GFP_NOFS);
 	if (unlikely(ret))

206 lines not on this page · raw message

index 4edac9b..d7b2ccfa 100644
@@ -75,14 +75,7 @@ struct objlayout {
  * embedded in objects provider io_state data structure
  */
 struct objlayout_io_state {
-	struct pnfs_layout_segment *lseg;
-
-	struct page **pages;
-	unsigned pgbase;
-	unsigned nr_pages;
-	unsigned long count;
-	loff_t offset;
-	bool sync;
+	struct objlayout *objlay;
 
 	void *rpcdata;
 	int status;             /* res */

@@ -99,6 +92,18 @@ struct objlayout_io_state {
 	struct pnfs_osd_ioerr *ioerrs;
 };
 
+static inline
+void objlayout_init_ioerrs(struct objlayout_io_state *oir, unsigned num_comps,
+			struct pnfs_osd_ioerr *ioerrs, void *rpcdata,
+			struct pnfs_layout_hdr *pnfs_layout_type)
+{
+	oir->objlay = OBJLAYOUT(pnfs_layout_type);
+	oir->rpcdata = rpcdata;
+	INIT_LIST_HEAD(&oir->err_list);
+	oir->num_comps = num_comps;
+	oir->ioerrs = ioerrs;
+}
+
 /*
  * Raid engine I/O API
  */

@@ -109,15 +114,10 @@ extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
 	gfp_t gfp_flags);
 extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
 
-extern int objio_alloc_io_state(
-	struct pnfs_layout_segment *lseg,
-	struct objlayout_io_state **outp,
-	gfp_t gfp_flags);
-extern void objio_free_io_state(struct objlayout_io_state *state);
+extern void objio_free_result(struct objlayout_io_state *state);
 
-extern int objio_read_pagelist(struct objlayout_io_state *ol_state);
-extern int objio_write_pagelist(struct objlayout_io_state *ol_state,
-				    bool stable);
+extern int objio_read_pagelist(struct nfs_read_data *rdata);
+extern int objio_write_pagelist(struct nfs_write_data *wdata, int how);
 
 /*
  * callback API

@@ -127,10 +127,8 @@ extern void objlayout_io_set_result(struct objlayout_io_state *state,
 			int osd_error, u64 offset, u64 length, bool is_write);
 
 static inline void
-objlayout_add_delta_space_used(struct objlayout_io_state *state, s64 space_used)
+objlayout_add_delta_space_used(struct objlayout *objlay, s64 space_used)
 {
-	struct objlayout *objlay = OBJLAYOUT(state->lseg->pls_layout);
-
 	/* If one of the I/Os errored out and the delta_space_used was
 	 * invalid we render the complete report as invalid. Protocol mandate
 	 * the DSU be accurate or not reported.

index 48eb91a..2347e0a 100644
@@ -146,7 +146,7 @@ struct objio_segment {
 
 struct objio_state {
 	/* Generic layer */
-	struct objlayout_io_state ol_state;
+	struct objlayout_io_res oir;
 
 	struct page **pages;
 	unsigned pgbase;

@@ -422,7 +422,7 @@ void objio_free_lseg(struct pnfs_layout_segment *lseg)
 	ios = &aos->objios;
 
 	ios->layout = objio_seg;
-	objlayout_init_ioerrs(&aos->objios.ol_state, objio_seg->num_comps,
+	objlayout_init_ioerrs(&aos->objios.oir, objio_seg->num_comps,
 			aos->ioerrs, rpcdata, pnfs_layout_type);
 
 	ios->pages = pages;

@@ -437,10 +437,9 @@ void objio_free_lseg(struct pnfs_layout_segment *lseg)
 	return 0;
 }
 
-void objio_free_result(struct objlayout_io_state *ol_state)
+void objio_free_result(struct objlayout_io_res *oir)
 {
-	struct objio_state *ios = container_of(ol_state, struct objio_state,
-					       ol_state);
+	struct objio_state *ios = container_of(oir, struct objio_state, oir);
 
 	kfree(ios);
 }

@@ -519,7 +518,7 @@ static int _io_check(struct objio_state *ios, bool is_write)
 
 			continue; /* we recovered */
 		}
-		objlayout_io_set_result(&ios->ol_state, i,
+		objlayout_io_set_result(&ios->oir, i,
 					&ios->layout->comps[i].oc_object_id,
 					osd_pri_2_pnfs_err(osi.osd_err_pri),
 					ios->per_dev[i].offset,

@@ -812,7 +811,7 @@ static int _read_done(struct objio_state *ios)
 	else
 		status = ret;
 
-	objlayout_read_done(&ios->ol_state, status, ios->sync);
+	objlayout_read_done(&ios->oir, status, ios->sync);
 	return ret;
 }
 

@@ -906,13 +905,13 @@ static int _write_done(struct objio_state *ios)
 	if (likely(!ret)) {
 		/* FIXME: should be based on the OSD's persistence model
 		 * See OSD2r05 Section 4.13 Data persistence model */
-		ios->ol_state.committed = NFS_FILE_SYNC;
+		ios->oir.committed = NFS_FILE_SYNC;
 		status = ios->length;
 	} else {
 		status = ret;
 	}
 
-	objlayout_write_done(&ios->ol_state, status, ios->sync);
+	objlayout_write_done(&ios->oir, status, ios->sync);
 	return ret;
 }
 

149 lines not on this page · raw message

index d7b2ccfa..8ec3472 100644
@@ -74,7 +74,7 @@ struct objlayout {
  * per-I/O operation state
  * embedded in objects provider io_state data structure
  */
-struct objlayout_io_state {
+struct objlayout_io_res {
 	struct objlayout *objlay;
 
 	void *rpcdata;

@@ -93,7 +93,7 @@ struct objlayout_io_state {
 };
 
 static inline
-void objlayout_init_ioerrs(struct objlayout_io_state *oir, unsigned num_comps,
+void objlayout_init_ioerrs(struct objlayout_io_res *oir, unsigned num_comps,
 			struct pnfs_osd_ioerr *ioerrs, void *rpcdata,
 			struct pnfs_layout_hdr *pnfs_layout_type)
 {

@@ -114,7 +114,10 @@ extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
 	gfp_t gfp_flags);
 extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
 
-extern void objio_free_result(struct objlayout_io_state *state);
+/* objio_free_result will free these @oir structs recieved from
+ * objlayout_{read,write}_done
+ */
+extern void objio_free_result(struct objlayout_io_res *oir);
 
 extern int objio_read_pagelist(struct nfs_read_data *rdata);
 extern int objio_write_pagelist(struct nfs_write_data *wdata, int how);

@@ -122,7 +125,7 @@ extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
 /*
  * callback API
  */
-extern void objlayout_io_set_result(struct objlayout_io_state *state,
+extern void objlayout_io_set_result(struct objlayout_io_res *oir,
 			unsigned index, struct pnfs_osd_objid *pooid,
 			int osd_error, u64 offset, u64 length, bool is_write);
 

@@ -141,9 +144,9 @@ extern void objlayout_io_set_result(struct objlayout_io_state *state,
 	spin_unlock(&objlay->lock);
 }
 
-extern void objlayout_read_done(struct objlayout_io_state *state,
+extern void objlayout_read_done(struct objlayout_io_res *oir,
 				ssize_t status, bool sync);
-extern void objlayout_write_done(struct objlayout_io_state *state,
+extern void objlayout_write_done(struct objlayout_io_res *oir,
 				 ssize_t status, bool sync);
 
 extern int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,

index 2347e0a..bd7ec26 100644
@@ -38,7 +38,7 @@
  */
 
 #include <linux/module.h>
-#include <scsi/osd_initiator.h>
+#include <scsi/osd_ore.h>
 
 #include "objlayout.h"
 

@@ -52,7 +52,7 @@ enum { BIO_MAX_PAGES_KMALLOC =
 
 struct objio_dev_ent {
 	struct nfs4_deviceid_node id_node;
-	struct osd_dev *od;
+	struct ore_dev od;
 };
 
 static void

@@ -60,8 +60,8 @@ struct objio_dev_ent {
 {
 	struct objio_dev_ent *de = container_of(d, struct objio_dev_ent, id_node);
 
-	dprintk("%s: free od=%p\n", __func__, de->od);
-	osduld_put_device(de->od);
+	dprintk("%s: free od=%p\n", __func__, de->od.od);
+	osduld_put_device(de->od.od);
 	kfree(de);
 }
 

@@ -98,12 +98,12 @@ struct objio_dev_ent {
 				nfss->pnfs_curr_ld,
 				nfss->nfs_client,
 				d_id);
-	de->od = od;
+	de->od.od = od;
 
 	d = nfs4_insert_deviceid_node(&de->id_node);
 	n = container_of(d, struct objio_dev_ent, id_node);
 	if (n != de) {
-		dprintk("%s: Race with other n->od=%p\n", __func__, n->od);
+		dprintk("%s: Race with other n->od=%p\n", __func__, n->od.od);
 		objio_free_deviceid_node(&de->id_node);
 		de = n;
 	}

@@ -111,28 +111,11 @@ struct objio_dev_ent {
 	return de;
 }
 
-struct caps_buffers {
-	u8 caps_key[OSD_CRYPTO_KEYID_SIZE];
-	u8 creds[OSD_CAP_LEN];
-};
-
 struct objio_segment {
 	struct pnfs_layout_segment lseg;
 
-	struct pnfs_osd_object_cred *comps;
-
-	unsigned mirrors_p1;
-	unsigned stripe_unit;
-	unsigned group_width;	/* Data stripe_units without integrity comps */
-	u64 group_depth;
-	unsigned group_count;
-
-	unsigned max_io_size;
-
-	unsigned comps_index;
-	unsigned num_comps;
-	/* variable length */
-	struct objio_dev_ent *ods[];
+	struct ore_layout layout;
+	struct ore_components oc;
 };
 
 static inline struct objio_segment *

@@ -155,7 +138,8 @@ struct objio_state {
 	loff_t offset;
 	bool sync;
 
-	struct objio_segment *layout;
+	struct ore_layout *layout;
+	struct ore_components *oc;
 
 	struct kref kref;
 	objio_done_fn done;

@@ -175,32 +159,33 @@ struct objio_state {
 
 /* Send and wait for a get_device_info of devices in the layout,
    then look them up with the osd_initiator library */
-static struct objio_dev_ent *_device_lookup(struct pnfs_layout_hdr *pnfslay,
-				struct objio_segment *objio_seg, unsigned comp,
-				gfp_t gfp_flags)
+static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
+	struct objio_segment *objio_seg, unsigned c, struct nfs4_deviceid *d_id,
+	gfp_t gfp_flags)
 {
 	struct pnfs_osd_deviceaddr *deviceaddr;
-	struct nfs4_deviceid *d_id;
 	struct objio_dev_ent *ode;
 	struct osd_dev *od;
 	struct osd_dev_info odi;
 	int err;
 
-	d_id = &objio_seg->comps[comp].oc_object_id.oid_device_id;
-
 	ode = _dev_list_find(NFS_SERVER(pnfslay->plh_inode), d_id);
-	if (ode)
-		return ode;
+	if (ode) {
+		objio_seg->oc.ods[c] = &ode->od; /* must use container_of */
+		return 0;
+	}
 
 	err = objlayout_get_deviceinfo(pnfslay, d_id, &deviceaddr, gfp_flags);
 	if (unlikely(err)) {
 		dprintk("%s: objlayout_get_deviceinfo dev(%llx:%llx) =>%d\n",
 			__func__, _DEVID_LO(d_id), _DEVID_HI(d_id), err);
-		return ERR_PTR(err);
+		return err;
 	}
 
 	odi.systemid_len = deviceaddr->oda_systemid.len;
 	if (odi.systemid_len > sizeof(odi.systemid)) {
+		dprintk("%s: odi.systemid_len > sizeof(systemid=%zd)\n",
+			__func__, sizeof(odi.systemid));
 		err = -EINVAL;
 		goto out;
 	} else if (odi.systemid_len)

@@ -225,38 +210,15 @@ struct objio_state {
 
 	ode = _dev_list_add(NFS_SERVER(pnfslay->plh_inode), d_id, od,
 			    gfp_flags);
-
+	objio_seg->oc.ods[c] = &ode->od; /* must use container_of */
+	dprintk("Adding new dev_id(%llx:%llx)\n",
+		_DEVID_LO(d_id), _DEVID_HI(d_id));
 out:
-	dprintk("%s: return=%d\n", __func__, err);
 	objlayout_put_deviceinfo(deviceaddr);
-	return err ? ERR_PTR(err) : ode;
-}
-
-static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
-	struct objio_segment *objio_seg,
-	gfp_t gfp_flags)
-{
-	unsigned i;
-	int err;
-
-	/* lookup all devices */
-	for (i = 0; i < objio_seg->num_comps; i++) {
-		struct objio_dev_ent *ode;
-
-		ode = _device_lookup(pnfslay, objio_seg, i, gfp_flags);
-		if (unlikely(IS_ERR(ode))) {
-			err = PTR_ERR(ode);
-			goto out;
-		}
-		objio_seg->ods[i] = ode;
-	}
-	err = 0;
-
-out:
-	dprintk("%s: return=%d\n", __func__, err);
 	return err;
 }
 
+#if 0
 static int _verify_data_map(struct pnfs_osd_layout *layout)
 {
 	struct pnfs_osd_data_map *data_map = &layout->olo_map;

@@ -296,23 +258,45 @@ static int _verify_data_map(struct pnfs_osd_layout *layout)
 
 	return 0;
 }
+#endif
 
-static void copy_single_comp(struct pnfs_osd_object_cred *cur_comp,
-			     struct pnfs_osd_object_cred *src_comp,
-			     struct caps_buffers *caps_p)
+static void copy_single_comp(struct ore_components *oc, unsigned c,
+			     struct pnfs_osd_object_cred *src_comp)
 {
-	WARN_ON(src_comp->oc_cap_key.cred_len > sizeof(caps_p->caps_key));
-	WARN_ON(src_comp->oc_cap.cred_len > sizeof(caps_p->creds));
+	struct ore_comp *ocomp = &oc->comps[c];
 
-	*cur_comp = *src_comp;
+	WARN_ON(src_comp->oc_cap_key.cred_len > 0); /* libosd is NO_SEC only */
+	WARN_ON(src_comp->oc_cap.cred_len > sizeof(ocomp->cred));
 
-	memcpy(caps_p->caps_key, src_comp->oc_cap_key.cred,
-	       sizeof(caps_p->caps_key));
-	cur_comp->oc_cap_key.cred = caps_p->caps_key;
+	ocomp->obj.partition = src_comp->oc_object_id.oid_partition_id;
+	ocomp->obj.id = src_comp->oc_object_id.oid_object_id;
 
-	memcpy(caps_p->creds, src_comp->oc_cap.cred,
-	       sizeof(caps_p->creds));
-	cur_comp->oc_cap.cred = caps_p->creds;
+	memcpy(ocomp->cred, src_comp->oc_cap.cred, sizeof(ocomp->cred));
+}
+
+int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
+		       struct objio_segment **pseg)
+{
+	struct __alloc_objio_segment {
+		struct objio_segment olseg;
+		struct ore_dev *ods[numdevs];
+		struct ore_comp	comps[numdevs];
+	} *aolseg;
+
+	aolseg = kzalloc(sizeof(*aolseg), gfp_flags);
+	if (unlikely(!aolseg)) {
+		dprintk("%s: Faild allocation numdevs=%d size=%zd\n", __func__,
+			numdevs, sizeof(*aolseg));
+		return -ENOMEM;
+	}
+
+	aolseg->olseg.oc.numdevs = numdevs;
+	aolseg->olseg.oc.single_comp = EC_MULTPLE_COMPS;
+	aolseg->olseg.oc.comps = aolseg->comps;
+	aolseg->olseg.oc.ods = aolseg->ods;
+
+	*pseg = &aolseg->olseg;
+	return 0;
 }
 
 int objio_alloc_lseg(struct pnfs_layout_segment **outp,

@@ -324,59 +308,43 @@ int objio_alloc_lseg(struct pnfs_layout_segment **outp,
 	struct objio_segment *objio_seg;
 	struct pnfs_osd_xdr_decode_layout_iter iter;
 	struct pnfs_osd_layout layout;
-	struct pnfs_osd_object_cred *cur_comp, src_comp;
-	struct caps_buffers *caps_p;
+	struct pnfs_osd_object_cred src_comp;
+	unsigned cur_comp;
 	int err;
 
 	err = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr);
 	if (unlikely(err))
 		return err;
 
-	err = _verify_data_map(&layout);
+	err = __alloc_objio_seg(layout.olo_num_comps, gfp_flags, &objio_seg);
 	if (unlikely(err))
 		return err;
 
-	objio_seg = kzalloc(sizeof(*objio_seg) +
-			    sizeof(objio_seg->ods[0]) * layout.olo_num_comps +
-			    sizeof(*objio_seg->comps) * layout.olo_num_comps +
-			    sizeof(struct caps_buffers) * layout.olo_num_comps,
-			    gfp_flags);
-	if (!objio_seg)
-		return -ENOMEM;
+	objio_seg->layout.stripe_unit = layout.olo_map.odm_stripe_unit;
+	objio_seg->layout.group_width = layout.olo_map.odm_group_width;
+	objio_seg->layout.group_depth = layout.olo_map.odm_group_depth;
+	objio_seg->layout.mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1;
+	objio_seg->layout.raid_algorithm = layout.olo_map.odm_raid_algorithm;
 
-	objio_seg->comps = (void *)(objio_seg->ods + layout.olo_num_comps);
-	cur_comp = objio_seg->comps;
-	caps_p = (void *)(cur_comp + layout.olo_num_comps);
-	while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err))
-		copy_single_comp(cur_comp++, &src_comp, caps_p++);
+	err = ore_verify_layout(layout.olo_map.odm_num_comps,
+					  &objio_seg->layout);
 	if (unlikely(err))
 		goto err;
 
-	objio_seg->num_comps = layout.olo_num_comps;
-	objio_seg->comps_index = layout.olo_comps_index;
-	err = objio_devices_lookup(pnfslay, objio_seg, gfp_flags);
-	if (err)
-		goto err;
-
-	objio_seg->mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1;
-	objio_seg->stripe_unit = layout.olo_map.odm_stripe_unit;
-	if (layout.olo_map.odm_group_width) {
-		objio_seg->group_width = layout.olo_map.odm_group_width;
-		objio_seg->group_depth = layout.olo_map.odm_group_depth;
-		objio_seg->group_count = layout.olo_map.odm_num_comps /
-						objio_seg->mirrors_p1 /
-						objio_seg->group_width;
-	} else {
-		objio_seg->group_width = layout.olo_map.odm_num_comps /
-						objio_seg->mirrors_p1;
-		objio_seg->group_depth = -1;
-		objio_seg->group_count = 1;
+	objio_seg->oc.first_dev = layout.olo_comps_index;
+	cur_comp = 0;
+	while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err)) {
+		copy_single_comp(&objio_seg->oc, cur_comp, &src_comp);
+		err = objio_devices_lookup(pnfslay, objio_seg, cur_comp,
+					   &src_comp.oc_object_id.oid_device_id,
+					   gfp_flags);
+		if (err)
+			goto err;
+		++cur_comp;
 	}
-
-	/* Cache this calculation it will hit for every page */
-	objio_seg->max_io_size = (BIO_MAX_PAGES_KMALLOC * PAGE_SIZE -
-				  objio_seg->stripe_unit) *
-				 objio_seg->group_width;
+	/* pnfs_osd_xdr_decode_layout_comp returns false on error */
+	if (unlikely(err))
+		goto err;
 
 	*outp = &objio_seg->lseg;
 	return 0;

@@ -393,10 +361,14 @@ void objio_free_lseg(struct pnfs_layout_segment *lseg)
 	int i;
 	struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
 
-	for (i = 0; i < objio_seg->num_comps; i++) {
-		if (!objio_seg->ods[i])
+	for (i = 0; i < objio_seg->oc.numdevs; i++) {
+		struct ore_dev *od = objio_seg->oc.ods[i];
+		struct objio_dev_ent *ode;
+
+		if (!od)
 			break;
-		nfs4_put_deviceid_node(&objio_seg->ods[i]->id_node);
+		ode = container_of(od, typeof(*ode), od);
+		nfs4_put_deviceid_node(&ode->id_node);
 	}
 	kfree(objio_seg);
 }

@@ -411,8 +383,8 @@ void objio_free_lseg(struct pnfs_layout_segment *lseg)
 	struct objio_state *ios;
 	struct __alloc_objio_state {
 		struct objio_state objios;
-		struct _objio_per_comp per_dev[objio_seg->num_comps];
-		struct pnfs_osd_ioerr ioerrs[objio_seg->num_comps];
+		struct _objio_per_comp per_dev[objio_seg->oc.numdevs];
+		struct pnfs_osd_ioerr ioerrs[objio_seg->oc.numdevs];
 	} *aos;
 
 	aos = kzalloc(sizeof(*aos), gfp_flags);

@@ -421,8 +393,9 @@ void objio_free_lseg(struct pnfs_layout_segment *lseg)
 
 	ios = &aos->objios;
 
-	ios->layout = objio_seg;
-	objlayout_init_ioerrs(&aos->objios.oir, objio_seg->num_comps,
+	ios->layout = &objio_seg->layout;
+	ios->oc = &objio_seg->oc;
+	objlayout_init_ioerrs(&aos->objios.oir, objio_seg->oc.numdevs,
 			aos->ioerrs, rpcdata, pnfs_layout_type);
 
 	ios->pages = pages;

@@ -474,6 +447,27 @@ enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
 	}
 }
 
+static void __on_dev_error(struct objio_state *ios, bool is_write,
+	struct ore_dev *od, unsigned dev_index, enum osd_err_priority oep,
+	u64 dev_offset, u64  dev_len)
+{
+	struct objio_state *objios = ios->private;
+	struct pnfs_osd_objid pooid;
+	struct objio_dev_ent *ode = container_of(od, typeof(*ode), od);
+	/* FIXME: what to do with more-then-one-group layouts. We need to
+	 * translate from ore_io_state index to oc->comps index
+	 */
+	unsigned comp = dev_index;
+
+	pooid.oid_device_id = ode->id_node.deviceid;
+	pooid.oid_partition_id = ios->oc->comps[comp].obj.partition;
+	pooid.oid_object_id = ios->oc->comps[comp].obj.id;
+
+	objlayout_io_set_result(&objios->oir, comp,
+				&pooid, osd_pri_2_pnfs_err(oep),
+				dev_offset, dev_len, is_write);
+}
+
 static void _clear_bio(struct bio *bio)
 {
 	struct bio_vec *bv;

@@ -518,12 +512,9 @@ static int _io_check(struct objio_state *ios, bool is_write)
 
 			continue; /* we recovered */
 		}
-		objlayout_io_set_result(&ios->oir, i,
-					&ios->layout->comps[i].oc_object_id,
-					osd_pri_2_pnfs_err(osi.osd_err_pri),
-					ios->per_dev[i].offset,
-					ios->per_dev[i].length,
-					is_write);
+		__on_dev_error(ios, is_write, ios->oc->ods[i],
+				ios->per_dev[i].dev, osi.osd_err_pri,
+				ios->per_dev[i].offset, ios->per_dev[i].length);
 
 		if (osi.osd_err_pri >= oep) {
 			oep = osi.osd_err_pri;

@@ -558,11 +549,11 @@ static void _io_free(struct objio_state *ios)
 
 struct osd_dev *_io_od(struct objio_state *ios, unsigned dev)
 {
-	unsigned min_dev = ios->layout->comps_index;
-	unsigned max_dev = min_dev + ios->layout->num_comps;
+	unsigned min_dev = ios->oc->first_dev;
+	unsigned max_dev = min_dev + ios->oc->numdevs;
 
 	BUG_ON(dev < min_dev || max_dev <= dev);
-	return ios->layout->ods[dev - min_dev]->od;
+	return ios->oc->ods[dev - min_dev]->od;
 }
 
 struct _striping_info {

@@ -820,12 +811,9 @@ static int _read_mirrors(struct objio_state *ios, unsigned cur_comp)
 	struct osd_request *or = NULL;
 	struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
 	unsigned dev = per_dev->dev;
-	struct pnfs_osd_object_cred *cred =
-			&ios->layout->comps[cur_comp];
-	struct osd_obj_id obj = {
-		.partition = cred->oc_object_id.oid_partition_id,
-		.id = cred->oc_object_id.oid_object_id,
-	};
+	struct ore_comp *cred =
+			&ios->oc->comps[cur_comp];
+	struct osd_obj_id obj = cred->obj;
 	int ret;
 
 	or = osd_start_request(_io_od(ios, dev), GFP_KERNEL);

@@ -837,7 +825,7 @@ static int _read_mirrors(struct objio_state *ios, unsigned cur_comp)
 
 	osd_req_read(or, &obj, per_dev->offset, per_dev->bio, per_dev->length);
 
-	ret = osd_finalize_request(or, 0, cred->oc_cap.cred, NULL);
+	ret = osd_finalize_request(or, 0, cred->cred, NULL);
 	if (ret) {
 		dprintk("%s: Faild to osd_finalize_request() => %d\n",
 			__func__, ret);

@@ -924,12 +912,8 @@ static int _write_mirrors(struct objio_state *ios, unsigned cur_comp)
 
 	for (; cur_comp < last_comp; ++cur_comp, ++dev) {
 		struct osd_request *or = NULL;
-		struct pnfs_osd_object_cred *cred =
-					&ios->layout->comps[cur_comp];
-		struct osd_obj_id obj = {
-			.partition = cred->oc_object_id.oid_partition_id,
-			.id = cred->oc_object_id.oid_object_id,
-		};
+		struct ore_comp *cred = &ios->oc->comps[cur_comp];
+		struct osd_obj_id obj = cred->obj;
 		struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
 		struct bio *bio;
 

@@ -964,7 +948,7 @@ static int _write_mirrors(struct objio_state *ios, unsigned cur_comp)
 
 		osd_req_write(or, &obj, per_dev->offset, bio, per_dev->length);
 
-		ret = osd_finalize_request(or, 0, cred->oc_cap.cred, NULL);
+		ret = osd_finalize_request(or, 0, cred->cred, NULL);
 		if (ret) {
 			dprintk("%s: Faild to osd_finalize_request() => %d\n",
 				__func__, ret);

@@ -1030,7 +1014,7 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
 		return false;
 
 	return pgio->pg_count + req->wb_bytes <=
-			OBJIO_LSEG(pgio->pg_lseg)->max_io_size;
+			OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
 }
 
 static const struct nfs_pageio_ops objio_pg_read_ops = {

272 lines not on this page · raw message

index 00b3849..3161da6 100644
@@ -188,48 +188,6 @@ static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
 	return err;
 }
 
-#if 0
-static int _verify_data_map(struct pnfs_osd_layout *layout)
-{
-	struct pnfs_osd_data_map *data_map = &layout->olo_map;
-	u64 stripe_length;
-	u32 group_width;
-
-/* FIXME: Only raid0 for now. if not go through MDS */
-	if (data_map->odm_raid_algorithm != PNFS_OSD_RAID_0) {
-		printk(KERN_ERR "Only RAID_0 for now\n");
-		return -ENOTSUPP;
-	}
-	if (0 != (data_map->odm_num_comps % (data_map->odm_mirror_cnt + 1))) {
-		printk(KERN_ERR "Data Map wrong, num_comps=%u mirrors=%u\n",
-			  data_map->odm_num_comps, data_map->odm_mirror_cnt);
-		return -EINVAL;
-	}
-
-	if (data_map->odm_group_width)
-		group_width = data_map->odm_group_width;
-	else
-		group_width = data_map->odm_num_comps /
-						(data_map->odm_mirror_cnt + 1);
-
-	stripe_length = (u64)data_map->odm_stripe_unit * group_width;
-	if (stripe_length >= (1ULL << 32)) {
-		printk(KERN_ERR "Total Stripe length(0x%llx)"
-			  " >= 32bit is not supported\n", _LLU(stripe_length));
-		return -ENOTSUPP;
-	}
-
-	if (0 != (data_map->odm_stripe_unit & ~PAGE_MASK)) {
-		printk(KERN_ERR "Stripe Unit(0x%llx)"
-			  " must be Multples of PAGE_SIZE(0x%lx)\n",
-			  _LLU(data_map->odm_stripe_unit), PAGE_SIZE);
-		return -ENOTSUPP;
-	}
-
-	return 0;
-}
-#endif
-
 static void copy_single_comp(struct ore_components *oc, unsigned c,
 			     struct pnfs_osd_object_cred *src_comp)
 {

@@ -441,327 +399,6 @@ static void __on_dev_error(struct ore_io_state *ios,
 				dev_offset, dev_len, !ios->reading);
 }
 
-#if 0
-static void _clear_bio(struct bio *bio)
-{
-	struct bio_vec *bv;
-	unsigned i;
-
-	__bio_for_each_segment(bv, bio, i, 0) {
-		unsigned this_count = bv->bv_len;
-
-		if (likely(PAGE_SIZE == this_count))
-			clear_highpage(bv->bv_page);
-		else
-			zero_user(bv->bv_page, bv->bv_offset, this_count);
-	}
-}
-
-static int _io_check(struct objio_state *ios, bool is_write)
-{
-	enum osd_err_priority oep = OSD_ERR_PRI_NO_ERROR;
-	int lin_ret = 0;
-	int i;
-
-	for (i = 0; i <  ios->numdevs; i++) {
-		struct osd_sense_info osi;
-		struct osd_request *or = ios->per_dev[i].or;
-		int ret;
-
-		if (!or)
-			continue;
-
-		ret = osd_req_decode_sense(or, &osi);
-		if (likely(!ret))
-			continue;
-
-		if (OSD_ERR_PRI_CLEAR_PAGES == osi.osd_err_pri) {
-			/* start read offset passed endof file */
-			BUG_ON(is_write);
-			_clear_bio(ios->per_dev[i].bio);
-			dprintk("%s: start read offset passed end of file "
-				"offset=0x%llx, length=0x%lx\n", __func__,
-				_LLU(ios->per_dev[i].offset),
-				ios->per_dev[i].length);
-
-			continue; /* we recovered */
-		}
-		__on_dev_error(ios, is_write, ios->oc->ods[i],
-				ios->per_dev[i].dev, osi.osd_err_pri,
-				ios->per_dev[i].offset, ios->per_dev[i].length);
-
-		if (osi.osd_err_pri >= oep) {
-			oep = osi.osd_err_pri;
-			lin_ret = ret;
-		}
-	}
-
-	return lin_ret;
-}
-
-/*
- * Common IO state helpers.
- */
-static void _io_free(struct objio_state *ios)
-{
-	unsigned i;
-
-	for (i = 0; i < ios->numdevs; i++) {
-		struct _objio_per_comp *per_dev = &ios->per_dev[i];
-
-		if (per_dev->or) {
-			osd_end_request(per_dev->or);
-			per_dev->or = NULL;
-		}
-
-		if (per_dev->bio) {
-			bio_put(per_dev->bio);
-			per_dev->bio = NULL;
-		}
-	}
-}
-
-struct osd_dev *_io_od(struct objio_state *ios, unsigned dev)
-{
-	unsigned min_dev = ios->oc->first_dev;
-	unsigned max_dev = min_dev + ios->oc->numdevs;
-
-	BUG_ON(dev < min_dev || max_dev <= dev);
-	return ios->oc->ods[dev - min_dev]->od;
-}
-
-struct _striping_info {
-	u64 obj_offset;
-	u64 group_length;
-	unsigned dev;
-	unsigned unit_off;
-};
-
-static void _calc_stripe_info(struct objio_state *ios, u64 file_offset,
-			      struct _striping_info *si)
-{
-	u32	stripe_unit = ios->layout->stripe_unit;
-	u32	group_width = ios->layout->group_width;
-	u64	group_depth = ios->layout->group_depth;
-	u32	U = stripe_unit * group_width;
-
-	u64	T = U * group_depth;
-	u64	S = T * ios->layout->group_count;
-	u64	M = div64_u64(file_offset, S);
-
-	/*
-	G = (L - (M * S)) / T
-	H = (L - (M * S)) % T
-	*/
-	u64	LmodU = file_offset - M * S;
-	u32	G = div64_u64(LmodU, T);
-	u64	H = LmodU - G * T;
-
-	u32	N = div_u64(H, U);
-
-	div_u64_rem(file_offset, stripe_unit, &si->unit_off);
-	si->obj_offset = si->unit_off + (N * stripe_unit) +
-				  (M * group_depth * stripe_unit);
-
-	/* "H - (N * U)" is just "H % U" so it's bound to u32 */
-	si->dev = (u32)(H - (N * U)) / stripe_unit + G * group_width;
-	si->dev *= ios->layout->mirrors_p1;
-
-	si->group_length = T - H;
-}
-
-static int _add_stripe_unit(struct objio_state *ios,  unsigned *cur_pg,
-		unsigned pgbase, struct _objio_per_comp *per_dev, int len,
-		gfp_t gfp_flags)
-{
-	unsigned pg = *cur_pg;
-	int cur_len = len;
-	struct request_queue *q =
-			osd_request_queue(_io_od(ios, per_dev->dev));
-
-	if (per_dev->bio == NULL) {
-		unsigned pages_in_stripe = ios->layout->group_width *
-				      (ios->layout->stripe_unit / PAGE_SIZE);
-		unsigned bio_size = (ios->nr_pages + pages_in_stripe) /
-				    ios->layout->group_width;
-
-		if (BIO_MAX_PAGES_KMALLOC < bio_size)
-			bio_size = BIO_MAX_PAGES_KMALLOC;
-
-		per_dev->bio = bio_kmalloc(gfp_flags, bio_size);
-		if (unlikely(!per_dev->bio)) {
-			dprintk("Faild to allocate BIO size=%u\n", bio_size);
-			return -ENOMEM;
-		}
-	}
-
-	while (cur_len > 0) {
-		unsigned pglen = min_t(unsigned, PAGE_SIZE - pgbase, cur_len);
-		unsigned added_len;
-
-		BUG_ON(ios->nr_pages <= pg);
-		cur_len -= pglen;
-
-		added_len = bio_add_pc_page(q, per_dev->bio,
-					ios->pages[pg], pglen, pgbase);
-		if (unlikely(pglen != added_len))
-			return -ENOMEM;
-		pgbase = 0;
-		++pg;
-	}
-	BUG_ON(cur_len);
-
-	per_dev->length += len;
-	*cur_pg = pg;
-	return 0;
-}
-
-static int _prepare_one_group(struct objio_state *ios, u64 length,
-			      struct _striping_info *si, unsigned *last_pg,
-			      gfp_t gfp_flags)
-{
-	unsigned stripe_unit = ios->layout->stripe_unit;
-	unsigned mirrors_p1 = ios->layout->mirrors_p1;
-	unsigned devs_in_group = ios->layout->group_width * mirrors_p1;
-	unsigned dev = si->dev;
-	unsigned first_dev = dev - (dev % devs_in_group);
-	unsigned max_comp = ios->numdevs ? ios->numdevs - mirrors_p1 : 0;
-	unsigned cur_pg = *last_pg;
-	int ret = 0;
-
-	while (length) {
-		struct _objio_per_comp *per_dev = &ios->per_dev[dev - first_dev];
-		unsigned cur_len, page_off = 0;
-
-		if (!per_dev->length) {
-			per_dev->dev = dev;
-			if (dev < si->dev) {
-				per_dev->offset = si->obj_offset + stripe_unit -
-								   si->unit_off;
-				cur_len = stripe_unit;
-			} else if (dev == si->dev) {
-				per_dev->offset = si->obj_offset;
-				cur_len = stripe_unit - si->unit_off;
-				page_off = si->unit_off & ~PAGE_MASK;
-				BUG_ON(page_off &&
-				      (page_off != ios->pgbase));
-			} else { /* dev > si->dev */
-				per_dev->offset = si->obj_offset - si->unit_off;
-				cur_len = stripe_unit;
-			}
-
-			if (max_comp < dev - first_dev)
-				max_comp = dev - first_dev;
-		} else {
-			cur_len = stripe_unit;
-		}
-		if (cur_len >= length)
-			cur_len = length;
-
-		ret = _add_stripe_unit(ios, &cur_pg, page_off , per_dev,
-				       cur_len, gfp_flags);
-		if (unlikely(ret))
-			goto out;
-
-		dev += mirrors_p1;
-		dev = (dev % devs_in_group) + first_dev;
-
-		length -= cur_len;
-		ios->length += cur_len;
-	}
-out:
-	ios->numdevs = max_comp + mirrors_p1;
-	*last_pg = cur_pg;
-	return ret;
-}
-
-static int _io_rw_pagelist(struct objio_state *ios, gfp_t gfp_flags)
-{
-	u64 length = ios->count;
-	u64 offset = ios->offset;
-	struct _striping_info si;
-	unsigned last_pg = 0;
-	int ret = 0;
-
-	while (length) {
-		_calc_stripe_info(ios, offset, &si);
-
-		if (length < si.group_length)
-			si.group_length = length;
-
-		ret = _prepare_one_group(ios, si.group_length, &si, &last_pg, gfp_flags);
-		if (unlikely(ret))
-			goto out;
-
-		offset += si.group_length;
-		length -= si.group_length;
-	}
-
-out:
-	if (!ios->length)
-		return ret;
-
-	return 0;
-}
-
-static int _sync_done(struct objio_state *ios)
-{
-	struct completion *waiting = ios->private;
-
-	complete(waiting);
-	return 0;
-}
-
-static void _last_io(struct kref *kref)
-{
-	struct objio_state *ios = container_of(kref, struct objio_state, kref);
-
-	ios->done(ios);
-}
-
-static void _done_io(struct osd_request *or, void *p)
-{
-	struct objio_state *ios = p;
-
-	kref_put(&ios->kref, _last_io);
-}
-
-static int _io_exec(struct objio_state *ios)
-{
-	DECLARE_COMPLETION_ONSTACK(wait);
-	int ret = 0;
-	unsigned i;
-	objio_done_fn saved_done_fn = ios->done;
-	bool sync = ios->sync;
-
-	if (sync) {
-		ios->done = _sync_done;
-		ios->private = &wait;
-	}
-
-	kref_init(&ios->kref);
-
-	for (i = 0; i < ios->numdevs; i++) {
-		struct osd_request *or = ios->per_dev[i].or;
-
-		if (!or)
-			continue;
-
-		kref_get(&ios->kref);
-		osd_execute_request_async(or, _done_io, ios);
-	}
-
-	kref_put(&ios->kref, _last_io);
-
-	if (sync) {
-		wait_for_completion(&wait);
-		ret = saved_done_fn(ios);
-	}
-
-	return ret;
-}
-#endif
-
 /*
  * read
  */

@@ -781,63 +418,6 @@ static void _read_done(struct ore_io_state *ios, void *private)
 	objlayout_read_done(&objios->oir, status, objios->sync);
 }
 
-#if 0
-static int _read_mirrors(struct objio_state *ios, unsigned cur_comp)
-{
-	struct osd_request *or = NULL;
-	struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
-	unsigned dev = per_dev->dev;
-	struct ore_comp *cred =
-			&ios->oc->comps[cur_comp];
-	struct osd_obj_id obj = cred->obj;
-	int ret;
-
-	or = osd_start_request(_io_od(ios, dev), GFP_KERNEL);
-	if (unlikely(!or)) {
-		ret = -ENOMEM;
-		goto err;
-	}
-	per_dev->or = or;
-
-	osd_req_read(or, &obj, per_dev->offset, per_dev->bio, per_dev->length);
-
-	ret = osd_finalize_request(or, 0, cred->cred, NULL);
-	if (ret) {
-		dprintk("%s: Faild to osd_finalize_request() => %d\n",
-			__func__, ret);
-		goto err;
-	}
-
-	dprintk("%s:[%d] dev=%d obj=0x%llx start=0x%llx length=0x%lx\n",
-		__func__, cur_comp, dev, obj.id, _LLU(per_dev->offset),
-		per_dev->length);
-
-err:
-	return ret;
-}
-
-static int _read_exec(struct objio_state *ios)
-{
-	unsigned i;
-	int ret;
-
-	for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
-		if (!ios->per_dev[i].length)
-			continue;
-		ret = _read_mirrors(ios, i);
-		if (unlikely(ret))
-			goto err;
-	}
-
-	ios->done = _read_done;
-	return _io_exec(ios);
-
-err:
-	_io_free(ios);
-	return ret;
-}
-#endif
-
 int objio_read_pagelist(struct nfs_read_data *rdata)
 {
 	struct objio_state *objios;

@@ -879,90 +459,6 @@ static void _write_done(struct ore_io_state *ios, void *private)
 	objlayout_write_done(&objios->oir, status, objios->sync);
 }
 
-#if 0
-static int _write_mirrors(struct objio_state *ios, unsigned cur_comp)
-{
-	struct _objio_per_comp *master_dev = &ios->per_dev[cur_comp];
-	unsigned dev = ios->per_dev[cur_comp].dev;
-	unsigned last_comp = cur_comp + ios->layout->mirrors_p1;
-	int ret;
-
-	for (; cur_comp < last_comp; ++cur_comp, ++dev) {
-		struct osd_request *or = NULL;
-		struct ore_comp *cred = &ios->oc->comps[cur_comp];
-		struct osd_obj_id obj = cred->obj;
-		struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
-		struct bio *bio;
-
-		or = osd_start_request(_io_od(ios, dev), GFP_NOFS);
-		if (unlikely(!or)) {
-			ret = -ENOMEM;
-			goto err;
-		}
-		per_dev->or = or;
-
-		if (per_dev != master_dev) {
-			bio = bio_kmalloc(GFP_NOFS,
-					  master_dev->bio->bi_max_vecs);
-			if (unlikely(!bio)) {
-				dprintk("Faild to allocate BIO size=%u\n",
-					master_dev->bio->bi_max_vecs);
-				ret = -ENOMEM;
-				goto err;
-			}
-
-			__bio_clone(bio, master_dev->bio);
-			bio->bi_bdev = NULL;
-			bio->bi_next = NULL;
-			per_dev->bio = bio;
-			per_dev->dev = dev;
-			per_dev->length = master_dev->length;
-			per_dev->offset =  master_dev->offset;
-		} else {
-			bio = master_dev->bio;
-			bio->bi_rw |= REQ_WRITE;
-		}
-
-		osd_req_write(or, &obj, per_dev->offset, bio, per_dev->length);
-
-		ret = osd_finalize_request(or, 0, cred->cred, NULL);
-		if (ret) {
-			dprintk("%s: Faild to osd_finalize_request() => %d\n",
-				__func__, ret);
-			goto err;
-		}
-
-		dprintk("%s:[%d] dev=%d obj=0x%llx start=0x%llx length=0x%lx\n",
-			__func__, cur_comp, dev, obj.id, _LLU(per_dev->offset),
-			per_dev->length);
-	}
-
-err:
-	return ret;
-}
-
-static int _write_exec(struct objio_state *ios)
-{
-	unsigned i;
-	int ret;
-
-	for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
-		if (!ios->per_dev[i].length)
-			continue;
-		ret = _write_mirrors(ios, i);
-		if (unlikely(ret))
-			goto err;
-	}
-
-	ios->done = _write_done;
-	return _io_exec(ios);
-
-err:
-	_io_free(ios);
-	return ret;
-}
-#endif
-
 int objio_write_pagelist(struct nfs_write_data *wdata, int how)
 {
 	struct objio_state *objios;

index 3161da6..c807ab9 100644
@@ -459,6 +459,43 @@ static void _write_done(struct ore_io_state *ios, void *private)
 	objlayout_write_done(&objios->oir, status, objios->sync);
 }
 
+static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
+{
+	struct objio_state *objios = priv;
+	struct nfs_write_data *wdata = objios->oir.rpcdata;
+	pgoff_t index = offset / PAGE_SIZE;
+	struct page *page = find_get_page(wdata->inode->i_mapping, index);
+
+	if (!page) {
+		page = find_or_create_page(wdata->inode->i_mapping,
+						index, GFP_NOFS);
+		if (unlikely(!page)) {
+			dprintk("%s: grab_cache_page Failed index=0x%lx\n",
+				__func__, index);
+			return NULL;
+		}
+		unlock_page(page);
+	}
+	if (PageDirty(page) || PageWriteback(page))
+		*uptodate = true;
+	else
+		*uptodate = PageUptodate(page);
+	dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate);
+	return page;
+}
+
+static void __r4w_put_page(void *priv, struct page *page)
+{
+	dprintk("%s: index=0x%lx\n", __func__, page->index);
+	page_cache_release(page);
+	return;
+}
+
+static const struct _ore_r4w_op _r4w_op = {
+	.get_page = &__r4w_get_page,
+	.put_page = &__r4w_put_page,
+};
+
 int objio_write_pagelist(struct nfs_write_data *wdata, int how)
 {
 	struct objio_state *objios;

@@ -472,6 +509,7 @@ int objio_write_pagelist(struct nfs_write_data *wdata, int how)
 		return ret;
 
 	objios->sync = 0 != (how & FLUSH_SYNC);
+	objios->ios->r4w = &_r4w_op;
 
 	if (!objios->sync)
 		objios->ios->done = _write_done;