Merge tag 'nfs-for-6.3-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "New Features:

   - Convert the read and write paths to use folios

  Bugfixes and Cleanups:

   - Fix tracepoint state manager flag printing

   - Fix disabling swap files

   - Fix NFSv4 client identifier sysfs path in the documentation

   - Don't clear NFS_CAP_COPY if server returns NFS4ERR_OFFLOAD_DENIED

   - Treat GETDEVICEINFO errors as a layout failure

   - Replace kmap_atomic() calls with kmap_local_page()

   - Constify sunrpc sysfs kobj_type structures"

* tag 'nfs-for-6.3-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (25 commits)
  fs/nfs: Replace kmap_atomic() with kmap_local_page() in dir.c
  pNFS/filelayout: treat GETDEVICEINFO errors as layout failure
  Documentation: Fix sysfs path for the NFSv4 client identifier
  nfs42: do not fail with EIO if ssc returns NFS4ERR_OFFLOAD_DENIED
  NFS: fix disabling of swap
  SUNRPC: make kobj_type structures constant
  nfs4trace: fix state manager flag printing
  NFS: Remove unnecessary check in nfs_read_folio()
  NFS: Improve tracing of nfs_wb_folio()
  NFS: Enable tracing of nfs_invalidate_folio() and nfs_launder_folio()
  NFS: fix up nfs_release_folio() to try to release the page
  NFS: Clean up O_DIRECT request allocation
  NFS: Fix up nfs_vm_page_mkwrite() for folios
  NFS: Convert nfs_write_begin/end to use folios
  NFS: Remove unused function nfs_wb_page()
  NFS: Convert buffered writes to use folios
  NFS: Convert the function nfs_wb_page() to use folios
  NFS: Convert buffered reads to use folios
  NFS: Add a helper nfs_wb_folio()
  NFS: Convert the remaining pagelist helper functions to support folios
  ...

1 files changed, 169 insertions, 48 deletions

diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 779bfc37233c..64fa8de199de 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -32,6 +32,42 @@
 static struct kmem_cache *nfs_page_cachep;
 static const struct rpc_call_ops nfs_pgio_common_ops;
 
+struct nfs_page_iter_page {
+	const struct nfs_page *req;
+	size_t count;
+};
+
+static void nfs_page_iter_page_init(struct nfs_page_iter_page *i,
+				    const struct nfs_page *req)
+{
+	i->req = req;
+	i->count = 0;
+}
+
+static void nfs_page_iter_page_advance(struct nfs_page_iter_page *i, size_t sz)
+{
+	const struct nfs_page *req = i->req;
+	size_t tmp = i->count + sz;
+
+	i->count = (tmp < req->wb_bytes) ? tmp : req->wb_bytes;
+}
+
+static struct page *nfs_page_iter_page_get(struct nfs_page_iter_page *i)
+{
+	const struct nfs_page *req = i->req;
+	struct page *page;
+
+	if (i->count != req->wb_bytes) {
+		size_t base = i->count + req->wb_pgbase;
+		size_t len = PAGE_SIZE - offset_in_page(base);
+
+		page = nfs_page_to_page(req, base);
+		nfs_page_iter_page_advance(i, len);
+		return page;
+	}
+	return NULL;
+}
+
 static struct nfs_pgio_mirror *
 nfs_pgio_get_mirror(struct nfs_pageio_descriptor *desc, u32 idx)
 {
@@ -391,7 +427,7 @@ nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev)
 		 * has extra ref from the write/commit path to handle handoff
 		 * between write and commit lists. */
 		if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) {
-			inode = page_file_mapping(req->wb_page)->host;
+			inode = nfs_page_to_inode(req);
 			set_bit(PG_INODE_REF, &req->wb_flags);
 			kref_get(&req->wb_kref);
 			atomic_long_inc(&NFS_I(inode)->nrequests);
@@ -431,10 +467,9 @@ out:
 		nfs_release_request(head);
 }
 
-static struct nfs_page *
-__nfs_create_request(struct nfs_lock_context *l_ctx, struct page *page,
-		   unsigned int pgbase, unsigned int offset,
-		   unsigned int count)
+static struct nfs_page *nfs_page_create(struct nfs_lock_context *l_ctx,
+					unsigned int pgbase, pgoff_t index,
+					unsigned int offset, unsigned int count)
 {
 	struct nfs_page		*req;
 	struct nfs_open_context *ctx = l_ctx->open_context;
@@ -453,42 +488,90 @@ __nfs_create_request(struct nfs_lock_context *l_ctx, struct page *page,
 	/* Initialize the request struct. Initially, we assume a
 	 * long write-back delay. This will be adjusted in
 	 * update_nfs_request below if the region is not locked. */
-	req->wb_page    = page;
-	if (page) {
-		req->wb_index = page_index(page);
-		get_page(page);
-	}
-	req->wb_offset  = offset;
-	req->wb_pgbase	= pgbase;
-	req->wb_bytes   = count;
+	req->wb_pgbase = pgbase;
+	req->wb_index = index;
+	req->wb_offset = offset;
+	req->wb_bytes = count;
 	kref_init(&req->wb_kref);
 	req->wb_nio = 0;
 	return req;
 }
 
+static void nfs_page_assign_folio(struct nfs_page *req, struct folio *folio)
+{
+	if (folio != NULL) {
+		req->wb_folio = folio;
+		folio_get(folio);
+		set_bit(PG_FOLIO, &req->wb_flags);
+	}
+}
+
+static void nfs_page_assign_page(struct nfs_page *req, struct page *page)
+{
+	if (page != NULL) {
+		req->wb_page = page;
+		get_page(page);
+	}
+}
+
 /**
- * nfs_create_request - Create an NFS read/write request.
+ * nfs_page_create_from_page - Create an NFS read/write request.
  * @ctx: open context to use
  * @page: page to write
- * @offset: starting offset within the page for the write
+ * @pgbase: starting offset within the page for the write
+ * @offset: file offset for the write
  * @count: number of bytes to read/write
  *
  * The page must be locked by the caller. This makes sure we never
  * create two different requests for the same page.
  * User should ensure it is safe to sleep in this function.
  */
-struct nfs_page *
-nfs_create_request(struct nfs_open_context *ctx, struct page *page,
-		   unsigned int offset, unsigned int count)
+struct nfs_page *nfs_page_create_from_page(struct nfs_open_context *ctx,
+					   struct page *page,
+					   unsigned int pgbase, loff_t offset,
+					   unsigned int count)
+{
+	struct nfs_lock_context *l_ctx = nfs_get_lock_context(ctx);
+	struct nfs_page *ret;
+
+	if (IS_ERR(l_ctx))
+		return ERR_CAST(l_ctx);
+	ret = nfs_page_create(l_ctx, pgbase, offset >> PAGE_SHIFT,
+			      offset_in_page(offset), count);
+	if (!IS_ERR(ret)) {
+		nfs_page_assign_page(ret, page);
+		nfs_page_group_init(ret, NULL);
+	}
+	nfs_put_lock_context(l_ctx);
+	return ret;
+}
+
+/**
+ * nfs_page_create_from_folio - Create an NFS read/write request.
+ * @ctx: open context to use
+ * @folio: folio to write
+ * @offset: starting offset within the folio for the write
+ * @count: number of bytes to read/write
+ *
+ * The page must be locked by the caller. This makes sure we never
+ * create two different requests for the same page.
+ * User should ensure it is safe to sleep in this function.
+ */
+struct nfs_page *nfs_page_create_from_folio(struct nfs_open_context *ctx,
+					    struct folio *folio,
+					    unsigned int offset,
+					    unsigned int count)
 {
 	struct nfs_lock_context *l_ctx = nfs_get_lock_context(ctx);
 	struct nfs_page *ret;
 
 	if (IS_ERR(l_ctx))
 		return ERR_CAST(l_ctx);
-	ret = __nfs_create_request(l_ctx, page, offset, offset, count);
-	if (!IS_ERR(ret))
+	ret = nfs_page_create(l_ctx, offset, folio_index(folio), offset, count);
+	if (!IS_ERR(ret)) {
+		nfs_page_assign_folio(ret, folio);
 		nfs_page_group_init(ret, NULL);
+	}
 	nfs_put_lock_context(l_ctx);
 	return ret;
 }
@@ -501,10 +584,16 @@ nfs_create_subreq(struct nfs_page *req,
 {
 	struct nfs_page *last;
 	struct nfs_page *ret;
+	struct folio *folio = nfs_page_to_folio(req);
+	struct page *page = nfs_page_to_page(req, pgbase);
 
-	ret = __nfs_create_request(req->wb_lock_context, req->wb_page,
-			pgbase, offset, count);
+	ret = nfs_page_create(req->wb_lock_context, pgbase, req->wb_index,
+			      offset, count);
 	if (!IS_ERR(ret)) {
+		if (folio)
+			nfs_page_assign_folio(ret, folio);
+		else
+			nfs_page_assign_page(ret, page);
 		/* find the last request */
 		for (last = req->wb_head;
 		     last->wb_this_page != req->wb_head;
@@ -512,7 +601,6 @@ nfs_create_subreq(struct nfs_page *req,
 			;
 
 		nfs_lock_request(ret);
-		ret->wb_index = req->wb_index;
 		nfs_page_group_init(ret, last);
 		ret->wb_nio = req->wb_nio;
 	}
@@ -551,11 +639,16 @@ void nfs_unlock_and_release_request(struct nfs_page *req)
  */
 static void nfs_clear_request(struct nfs_page *req)
 {
+	struct folio *folio = nfs_page_to_folio(req);
 	struct page *page = req->wb_page;
 	struct nfs_lock_context *l_ctx = req->wb_lock_context;
 	struct nfs_open_context *ctx;
 
-	if (page != NULL) {
+	if (folio != NULL) {
+		folio_put(folio);
+		req->wb_folio = NULL;
+		clear_bit(PG_FOLIO, &req->wb_flags);
+	} else if (page != NULL) {
 		put_page(page);
 		req->wb_page = NULL;
 	}
@@ -693,13 +786,14 @@ EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
 /**
  * nfs_pgio_rpcsetup - Set up arguments for a pageio call
  * @hdr: The pageio hdr
+ * @pgbase: base
  * @count: Number of bytes to read
  * @how: How to commit data (writes only)
  * @cinfo: Commit information for the call (writes only)
  */
-static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr,
-			      unsigned int count,
-			      int how, struct nfs_commit_info *cinfo)
+static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr, unsigned int pgbase,
+			      unsigned int count, int how,
+			      struct nfs_commit_info *cinfo)
 {
 	struct nfs_page *req = hdr->req;
 
@@ -710,7 +804,7 @@ static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr,
 	hdr->args.offset = req_offset(req);
 	/* pnfs_set_layoutcommit needs this */
 	hdr->mds_offset = hdr->args.offset;
-	hdr->args.pgbase = req->wb_pgbase;
+	hdr->args.pgbase = pgbase;
 	hdr->args.pages  = hdr->page_array.pagevec;
 	hdr->args.count  = count;
 	hdr->args.context = get_nfs_open_context(nfs_req_openctx(req));
@@ -896,9 +990,10 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 	struct nfs_commit_info cinfo;
 	struct nfs_page_array *pg_array = &hdr->page_array;
 	unsigned int pagecount, pageused;
+	unsigned int pg_base = offset_in_page(mirror->pg_base);
 	gfp_t gfp_flags = nfs_io_gfp_mask();
 
-	pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count);
+	pagecount = nfs_page_array_len(pg_base, mirror->pg_count);
 	pg_array->npages = pagecount;
 
 	if (pagecount <= ARRAY_SIZE(pg_array->page_array))
@@ -918,16 +1013,26 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 	last_page = NULL;
 	pageused = 0;
 	while (!list_empty(head)) {
+		struct nfs_page_iter_page i;
+		struct page *page;
+
 		req = nfs_list_entry(head->next);
 		nfs_list_move_request(req, &hdr->pages);
 
-		if (!last_page || last_page != req->wb_page) {
-			pageused++;
-			if (pageused > pagecount)
-				break;
-			*pages++ = last_page = req->wb_page;
+		if (req->wb_pgbase == 0)
+			last_page = NULL;
+
+		nfs_page_iter_page_init(&i, req);
+		while ((page = nfs_page_iter_page_get(&i)) != NULL) {
+			if (last_page != page) {
+				pageused++;
+				if (pageused > pagecount)
+					goto full;
+				*pages++ = last_page = page;
+			}
 		}
 	}
+full:
 	if (WARN_ON_ONCE(pageused != pagecount)) {
 		nfs_pgio_error(hdr);
 		desc->pg_error = -EINVAL;
@@ -939,7 +1044,8 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 		desc->pg_ioflags &= ~FLUSH_COND_STABLE;
 
 	/* Set up the argument struct */
-	nfs_pgio_rpcsetup(hdr, mirror->pg_count, desc->pg_ioflags, &cinfo);
+	nfs_pgio_rpcsetup(hdr, pg_base, mirror->pg_count, desc->pg_ioflags,
+			  &cinfo);
 	desc->pg_rpc_callops = &nfs_pgio_common_ops;
 	return 0;
 }
@@ -1035,6 +1141,24 @@ static bool nfs_match_lock_context(const struct nfs_lock_context *l1,
 	return l1->lockowner == l2->lockowner;
 }
 
+static bool nfs_page_is_contiguous(const struct nfs_page *prev,
+				   const struct nfs_page *req)
+{
+	size_t prev_end = prev->wb_pgbase + prev->wb_bytes;
+
+	if (req_offset(req) != req_offset(prev) + prev->wb_bytes)
+		return false;
+	if (req->wb_pgbase == 0)
+		return prev_end == nfs_page_max_length(prev);
+	if (req->wb_pgbase == prev_end) {
+		struct folio *folio = nfs_page_to_folio(req);
+		if (folio)
+			return folio == nfs_page_to_folio(prev);
+		return req->wb_page == prev->wb_page;
+	}
+	return false;
+}
+
 /**
  * nfs_coalesce_size - test two requests for compatibility
  * @prev: pointer to nfs_page
@@ -1063,16 +1187,8 @@ static unsigned int nfs_coalesce_size(struct nfs_page *prev,
 		    !nfs_match_lock_context(req->wb_lock_context,
 					    prev->wb_lock_context))
 			return 0;
-		if (req_offset(req) != req_offset(prev) + prev->wb_bytes)
+		if (!nfs_page_is_contiguous(prev, req))
 			return 0;
-		if (req->wb_page == prev->wb_page) {
-			if (req->wb_pgbase != prev->wb_pgbase + prev->wb_bytes)
-				return 0;
-		} else {
-			if (req->wb_pgbase != 0 ||
-			    prev->wb_pgbase + prev->wb_bytes != PAGE_SIZE)
-				return 0;
-		}
 	}
 	return pgio->pg_ops->pg_test(pgio, prev, req);
 }
@@ -1412,16 +1528,21 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
 {
 	struct nfs_pgio_mirror *mirror;
 	struct nfs_page *prev;
+	struct folio *folio;
 	u32 midx;
 
 	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
 		mirror = nfs_pgio_get_mirror(desc, midx);
 		if (!list_empty(&mirror->pg_list)) {
 			prev = nfs_list_entry(mirror->pg_list.prev);
-			if (index != prev->wb_index + 1) {
-				nfs_pageio_complete(desc);
-				break;
-			}
+			folio = nfs_page_to_folio(prev);
+			if (folio) {
+				if (index == folio_next_index(folio))
+					continue;
+			} else if (index == prev->wb_index + 1)
+				continue;
+			nfs_pageio_complete(desc);
+			break;
 		}
 	}
 }