FIXES for pnfs for 2.6.40 - version 9

index 9667a62..80a5d0e 100644
@@ -357,7 +357,7 @@ static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	return 0;
 }
 
-static inline void nfs4_deviceid_purge_client(struct nfs_client *)
+static inline void nfs4_deviceid_purge_client(struct nfs_client *ncl)
 {
 }
 #endif /* CONFIG_NFS_V4_1 */

index 725b1df..08f1d90 100644
@@ -65,7 +65,7 @@ struct objio_segment {
 	unsigned comps_index;
 	unsigned num_comps;
 	/* variable length */
-	struct osd_dev	*ods[1];
+	struct objio_dev_ent *ods[];
 };
 
 static inline struct objio_segment *

@@ -143,7 +143,6 @@ int objio_alloc_lseg(struct pnfs_layout_segment **outp,
 	struct pnfs_osd_layout layout;
 	struct pnfs_osd_object_cred *cur_comp, src_comp;
 	struct caps_buffers *caps_p;
-
 	int err;
 
 	err = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr);

@@ -155,13 +154,15 @@ int objio_alloc_lseg(struct pnfs_layout_segment **outp,
 		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;
 
-	cur_comp = objio_seg->comps = (void *)(objio_seg + 1);
+	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++);

index 6925567..cc92d3b 100644
@@ -397,7 +397,6 @@ int objio_alloc_io_state(struct pnfs_layout_segment *lseg,
 	const unsigned first_size = sizeof(*ios) +
 				objio_seg->num_comps * sizeof(ios->per_dev[0]);
 
-	dprintk("%s: num_comps=%d\n", __func__, objio_seg->num_comps);
 	ios = kzalloc(first_size, gfp_flags);
 	if (unlikely(!ios))
 		return -ENOMEM;

@@ -561,6 +560,9 @@ static int _add_stripe_unit(struct objio_state *ios,  unsigned *cur_pg,
 		unsigned bio_size = (ios->ol_state.nr_pages + pages_in_stripe) /
 				    stripes;
 
+		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);

index 4e8de3e..8bca5e1 100644
@@ -396,12 +396,16 @@ int objio_alloc_io_state(struct pnfs_layout_segment *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, gfp_flags);
+	ios = kzalloc(first_size + sec_size, gfp_flags);
 	if (unlikely(!ios))
 		return -ENOMEM;
 
 	ios->layout = objio_seg;
+	ios->ol_state.ioerrs = ((void *)ios) + first_size;
+	ios->ol_state.num_comps = objio_seg->num_comps;
 
 	*outp = &ios->ol_state;
 	return 0;

@@ -415,6 +419,36 @@ void objio_free_io_state(struct objlayout_io_state *ol_state)
 	kfree(ios);
 }
 
+enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
+{
+	switch (oep) {
+	case OSD_ERR_PRI_NO_ERROR:
+		return (enum pnfs_osd_errno)0;
+
+	case OSD_ERR_PRI_CLEAR_PAGES:
+		BUG_ON(1);
+		return 0;
+
+	case OSD_ERR_PRI_RESOURCE:
+		return PNFS_OSD_ERR_RESOURCE;
+	case OSD_ERR_PRI_BAD_CRED:
+		return PNFS_OSD_ERR_BAD_CRED;
+	case OSD_ERR_PRI_NO_ACCESS:
+		return PNFS_OSD_ERR_NO_ACCESS;
+	case OSD_ERR_PRI_UNREACHABLE:
+		return PNFS_OSD_ERR_UNREACHABLE;
+	case OSD_ERR_PRI_NOT_FOUND:
+		return PNFS_OSD_ERR_NOT_FOUND;
+	case OSD_ERR_PRI_NO_SPACE:
+		return PNFS_OSD_ERR_NO_SPACE;
+	default:
+		WARN_ON(1);
+		/* fallthrough */
+	case OSD_ERR_PRI_EIO:
+		return PNFS_OSD_ERR_EIO;
+	}
+}
+
 static void _clear_bio(struct bio *bio)
 {
 	struct bio_vec *bv;

@@ -461,6 +495,12 @@ static int _io_check(struct objio_state *ios, bool is_write)
 			continue; /* we recovered */
 		}
 		dev = ios->per_dev[i].dev;
+		objlayout_io_set_result(&ios->ol_state, dev,
+					&ios->layout->comps[dev].oc_object_id,
+					osd_pri_2_pnfs_err(osi.osd_err_pri),
+					ios->per_dev[i].offset,
+					ios->per_dev[i].length,
+					is_write);
 
 		if (osi.osd_err_pri >= oep) {
 			oep = osi.osd_err_pri;

@@ -977,6 +1017,8 @@ static struct pnfs_layoutdriver_type objlayout_type = {
 	.pg_test                 = objlayout_pg_test,
 
 	.free_deviceid_node	 = objio_free_deviceid_node,
+
+	.encode_layoutreturn     = objlayout_encode_layoutreturn,
 };
 
 MODULE_DESCRIPTION("pNFS Layout Driver for OSD2 objects");

262 lines not on this page · raw message

index 9a405e8..b0bb975 100644
@@ -50,6 +50,10 @@
  */
 struct objlayout {
 	struct pnfs_layout_hdr pnfs_layout;
+
+	 /* for layout_return */
+	spinlock_t lock;
+	struct list_head err_list;
 };
 
 static inline struct objlayout *

@@ -76,6 +80,16 @@ struct objlayout_io_state {
 	int status;             /* res */
 	int eof;                /* res */
 	int committed;          /* res */
+
+	/* Error reporting (layout_return) */
+	struct list_head err_list;
+	unsigned num_comps;
+	/* Pointer to array of error descriptors of size num_comps.
+	 * It should contain as many entries as devices in the osd_layout
+	 * that participate in the I/O. It is up to the io_engine to allocate
+	 * needed space and set num_comps.
+	 */
+	struct pnfs_osd_ioerr *ioerrs;
 };
 
 /*

@@ -101,6 +115,10 @@ extern ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state,
 /*
  * callback API
  */
+extern void objlayout_io_set_result(struct objlayout_io_state *state,
+			unsigned index, struct pnfs_osd_objid *pooid,
+			int osd_error, u64 offset, u64 length, bool is_write);
+
 extern void objlayout_read_done(struct objlayout_io_state *state,
 				ssize_t status, bool sync);
 extern void objlayout_write_done(struct objlayout_io_state *state,

@@ -131,4 +149,9 @@ extern enum pnfs_try_status objlayout_write_pagelist(
 	struct nfs_write_data *,
 	int how);
 
+extern void objlayout_encode_layoutreturn(
+	struct pnfs_layout_hdr *,
+	struct xdr_stream *,
+	const struct nfs4_layoutreturn_args *);
+
 #endif /* _OBJLAYOUT_H */

index 0918ea8..b8704fe 100644
@@ -230,6 +230,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_error = 0;
 	desc->pg_lseg = NULL;
 	desc->pg_test = NULL;
+	pnfs_pageio_init(desc, inode);
 }
 
 /**

index f7a9405..568ab0e 100644
@@ -1058,7 +1058,7 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		access_type = IOMODE_RW;
 		gfp_flags = GFP_NOFS;
 	}
-		
+
 	if (pgio->pg_count == prev->wb_bytes) {
 		/* This is first coelesce call for a series of nfs_pages */
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,

index 4cfc494..c056688 100644
@@ -292,7 +292,8 @@ static inline int pnfs_return_layout(struct inode *ino)
 	return 0;
 }
 
-static inline void pnfs_pageio_init(struct nfs_pageio_descriptor *pgio, struct inode *inode)
+static inline void pnfs_pageio_init(struct nfs_pageio_descriptor *pgio,
+				    struct inode *inode)
 {
 	if (NFS_SERVER(inode)->pnfs_curr_ld)
 		pgio->pg_test = pnfs_generic_pg_test;

@@ -381,7 +382,8 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
 {
 }
 
-static inline void pnfs_pageio_init(struct nfs_pageio_descriptor *, struct inode *)
+static inline void pnfs_pageio_init(struct nfs_pageio_descriptor *pgio,
+				    struct inode *inode)
 {
 }
 

index 6bd09a8..20a7f95 100644
@@ -664,7 +664,6 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	if (ret == 0)
 		goto read_complete; /* all pages were read */
 
-	pnfs_pageio_init(&pgio, inode);
 	if (rsize < PAGE_CACHE_SIZE)
 		nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0);
 	else

index d81c5c0..e268e3b 100644
@@ -1036,7 +1036,6 @@ static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 {
 	size_t wsize = NFS_SERVER(inode)->wsize;
 
-	pnfs_pageio_init(pgio, inode);
 	if (wsize < PAGE_CACHE_SIZE)
 		nfs_pageio_init(pgio, inode, nfs_flush_multi, wsize, ioflags);
 	else

index 5344371..36bb67f 100644
@@ -204,6 +204,11 @@ nfs_wait_on_request(struct nfs_page *req)
 			TASK_UNINTERRUPTIBLE);
 }
 
+static bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req)
+{
+	return desc->pg_count + req->wb_bytes <= desc->pg_bsize;
+}
+
 /**
  * nfs_pageio_init - initialise a page io descriptor
  * @desc: pointer to descriptor

@@ -229,7 +234,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_ioflags = io_flags;
 	desc->pg_error = 0;
 	desc->pg_lseg = NULL;
-	desc->pg_test = NULL;
+	desc->pg_test = nfs_generic_pg_test;
 	pnfs_pageio_init(desc, inode);
 }
 

@@ -260,13 +265,7 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 		return false;
 	if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
 		return false;
-	/*
-	 * Non-whole file layouts need to check that req is inside of
-	 * pgio->pg_lseg.
-	 */
-	if (pgio->pg_test && !pgio->pg_test(pgio, prev, req))
-		return false;
-	return true;
+	return pgio->pg_test(pgio, prev, req);
 }
 
 /**

@@ -295,8 +294,6 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
 		if (desc->pg_bsize < PAGE_SIZE)
 			return 0;
 		newlen += desc->pg_count;
-		if (newlen > desc->pg_bsize)
-			return 0;
 		prev = nfs_list_entry(desc->pg_list.prev);
 		if (!nfs_can_coalesce_requests(prev, req, desc))
 			return 0;

index 36bb67f..624ec2c 100644
@@ -206,6 +206,16 @@ nfs_wait_on_request(struct nfs_page *req)
 
 static bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req)
 {
+	/*
+	* FIXME: ideally we should be able to coalesce all requests
+	* that are not block boundary aligned, but currently this
+	* is problematic for the case of bsize < PAGE_CACHE_SIZE,
+	* since nfs_flush_multi and nfs_pagein_multi assume you
+	* can have only one struct nfs_page.
+	*/
+	if (desc->pg_bsize < PAGE_SIZE)
+		return 0;
+
 	return desc->pg_count + req->wb_bytes <= desc->pg_bsize;
 }
 

@@ -279,29 +289,18 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
 				     struct nfs_page *req)
 {
-	size_t newlen = req->wb_bytes;
-
 	if (desc->pg_count != 0) {
 		struct nfs_page *prev;
 
-		/*
-		 * FIXME: ideally we should be able to coalesce all requests
-		 * that are not block boundary aligned, but currently this
-		 * is problematic for the case of bsize < PAGE_CACHE_SIZE,
-		 * since nfs_flush_multi and nfs_pagein_multi assume you
-		 * can have only one struct nfs_page.
-		 */
-		if (desc->pg_bsize < PAGE_SIZE)
-			return 0;
-		newlen += desc->pg_count;
 		prev = nfs_list_entry(desc->pg_list.prev);
 		if (!nfs_can_coalesce_requests(prev, req, desc))
 			return 0;
-	} else
+	} else {
 		desc->pg_base = req->wb_pgbase;
+	}
 	nfs_list_remove_request(req);
 	nfs_list_add_request(req, &desc->pg_list);
-	desc->pg_count = newlen;
+	desc->pg_count += req->wb_bytes;
 	return 1;
 }
 

index f431c4b..9cf208d 100644
@@ -995,13 +995,14 @@ ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state, bool stable)
 	return _write_exec(ios);
 }
 
-static bool
-objio_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req)
+static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
+			  struct nfs_page *prev, struct nfs_page *req)
 {
 	if (!pnfs_generic_pg_test(pgio, prev, req))
 		return false;
 
-	return pgio->pg_count + req->wb_bytes <= OBJIO_LSEG(pgio->pg_lseg)->max_io_size;
+	return pgio->pg_count + req->wb_bytes <=
+			OBJIO_LSEG(pgio->pg_lseg)->max_io_size;
 }
 
 static struct pnfs_layoutdriver_type objlayout_type = {