cifs: Change the I/O paths to use an iterator rather than a page list

Currently, the cifs I/O paths hand lists of pages from the VM interface
routines at the top all the way through the intervening layers to the
socket interface at the bottom.

This is a problem, however, for interfacing with netfslib which passes an
iterator through to the ->issue_read() method (and will pass an iterator
through to the ->issue_write() method in future).  Netfslib takes over
bounce buffering for direct I/O, async I/O and encrypted content, so cifs
doesn't need to do that.  Netfslib also converts IOVEC-type iterators into
BVEC-type iterators if necessary.

Further, cifs needs foliating - and folios may come in a variety of sizes,
so a page list pointing to an array of heterogeneous pages may cause
problems in places such as where crypto is done.

Change the cifs I/O paths to hand iov_iter iterators all the way through
instead.

Notes:

 (1) Some old routines are #if'd out to be removed in a follow up patch so
     as to avoid confusing diff, thereby making the diff output easier to
     follow.  I've removed functions that don't overlap with anything
     added.

 (2) struct smb_rqst loses rq_pages, rq_offset, rq_npages, rq_pagesz and
     rq_tailsz which describe the pages forming the buffer; instead there's
     an rq_iter describing the source buffer and an rq_buffer which is used
     to hold the buffer for encryption.

 (3) struct cifs_readdata and cifs_writedata are similarly modified to
     smb_rqst.  The ->read_into_pages() and ->copy_into_pages() are then
     replaced with passing the iterator directly to the socket.

     The iterators are stored in these structs so that they are persistent
     and don't get deallocated when the function returns (unlike if they
     were stack variables).

 (4) Buffered writeback is overhauled, borrowing the code from the afs
     filesystem to gather up contiguous runs of folios.  The XARRAY-type
     iterator is then used to refer directly to the pagecache and can be
     passed to the socket to transmit data directly from there.

     This includes:

	cifs_extend_writeback()
	cifs_write_back_from_locked_folio()
	cifs_writepages_region()
	cifs_writepages()

 (5) Pages are converted to folios.

 (6) Direct I/O uses netfs_extract_user_iter() to create a BVEC-type
     iterator from an IOBUF/UBUF-type source iterator.

 (7) smb2_get_aead_req() uses netfs_extract_iter_to_sg() to extract page
     fragments from the iterator into the scatterlists that the crypto
     layer prefers.

 (8) smb2_init_transform_rq() attached pages to smb_rqst::rq_buffer, an
     xarray, to use as a bounce buffer for encryption.  An XARRAY-type
     iterator can then be used to pass the bounce buffer to lower layers.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Steve French <sfrench@samba.org>
cc: Shyam Prasad N <nspmangalore@gmail.com>
cc: Rohith Surabattula <rohiths.msft@gmail.com>
cc: Paulo Alcantara <pc@cjr.nz>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cifs@vger.kernel.org

Link: https://lore.kernel.org/r/164311907995.2806745.400147335497304099.stgit@warthog.procyon.org.uk/ # rfc
Link: https://lore.kernel.org/r/164928620163.457102.11602306234438271112.stgit@warthog.procyon.org.uk/ # v1
Link: https://lore.kernel.org/r/165211420279.3154751.15923591172438186144.stgit@warthog.procyon.org.uk/ # v1
Link: https://lore.kernel.org/r/165348880385.2106726.3220789453472800240.stgit@warthog.procyon.org.uk/ # v1
Link: https://lore.kernel.org/r/165364827111.3334034.934805882842932881.stgit@warthog.procyon.org.uk/ # v3
Link: https://lore.kernel.org/r/166126396180.708021.271013668175370826.stgit@warthog.procyon.org.uk/ # v1
Link: https://lore.kernel.org/r/166697259595.61150.5982032408321852414.stgit@warthog.procyon.org.uk/ # rfc
Link: https://lore.kernel.org/r/166732031756.3186319.12528413619888902872.stgit@warthog.procyon.org.uk/ # rfc
Signed-off-by: Steve French <stfrench@microsoft.com>

1 files changed, 13 insertions, 115 deletions

diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 2a19c7987c5b..2905734eb289 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -966,16 +966,22 @@ cifs_aio_ctx_release(struct kref *refcount)
 
 	/*
 	 * ctx->bv is only set if setup_aio_ctx_iter() was call successfuly
-	 * which means that iov_iter_get_pages() was a success and thus that
-	 * we have taken reference on pages.
+	 * which means that iov_iter_extract_pages() was a success and thus
+	 * that we may have references or pins on pages that we need to
+	 * release.
 	 */
 	if (ctx->bv) {
-		unsigned i;
+		if (ctx->should_dirty || ctx->bv_need_unpin) {
+			unsigned int i;
 
-		for (i = 0; i < ctx->npages; i++) {
-			if (ctx->should_dirty)
-				set_page_dirty(ctx->bv[i].bv_page);
-			put_page(ctx->bv[i].bv_page);
+			for (i = 0; i < ctx->nr_pinned_pages; i++) {
+				struct page *page = ctx->bv[i].bv_page;
+
+				if (ctx->should_dirty)
+					set_page_dirty(page);
+				if (ctx->bv_need_unpin)
+					unpin_user_page(page);
+			}
 		}
 		kvfree(ctx->bv);
 	}
@@ -983,95 +989,6 @@ cifs_aio_ctx_release(struct kref *refcount)
 	kfree(ctx);
 }
 
-#define CIFS_AIO_KMALLOC_LIMIT (1024 * 1024)
-
-int
-setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw)
-{
-	ssize_t rc;
-	unsigned int cur_npages;
-	unsigned int npages = 0;
-	unsigned int i;
-	size_t len;
-	size_t count = iov_iter_count(iter);
-	unsigned int saved_len;
-	size_t start;
-	unsigned int max_pages = iov_iter_npages(iter, INT_MAX);
-	struct page **pages = NULL;
-	struct bio_vec *bv = NULL;
-
-	if (iov_iter_is_kvec(iter)) {
-		memcpy(&ctx->iter, iter, sizeof(*iter));
-		ctx->len = count;
-		iov_iter_advance(iter, count);
-		return 0;
-	}
-
-	if (array_size(max_pages, sizeof(*bv)) <= CIFS_AIO_KMALLOC_LIMIT)
-		bv = kmalloc_array(max_pages, sizeof(*bv), GFP_KERNEL);
-
-	if (!bv) {
-		bv = vmalloc(array_size(max_pages, sizeof(*bv)));
-		if (!bv)
-			return -ENOMEM;
-	}
-
-	if (array_size(max_pages, sizeof(*pages)) <= CIFS_AIO_KMALLOC_LIMIT)
-		pages = kmalloc_array(max_pages, sizeof(*pages), GFP_KERNEL);
-
-	if (!pages) {
-		pages = vmalloc(array_size(max_pages, sizeof(*pages)));
-		if (!pages) {
-			kvfree(bv);
-			return -ENOMEM;
-		}
-	}
-
-	saved_len = count;
-
-	while (count && npages < max_pages) {
-		rc = iov_iter_get_pages2(iter, pages, count, max_pages, &start);
-		if (rc < 0) {
-			cifs_dbg(VFS, "Couldn't get user pages (rc=%zd)\n", rc);
-			break;
-		}
-
-		if (rc > count) {
-			cifs_dbg(VFS, "get pages rc=%zd more than %zu\n", rc,
-				 count);
-			break;
-		}
-
-		count -= rc;
-		rc += start;
-		cur_npages = DIV_ROUND_UP(rc, PAGE_SIZE);
-
-		if (npages + cur_npages > max_pages) {
-			cifs_dbg(VFS, "out of vec array capacity (%u vs %u)\n",
-				 npages + cur_npages, max_pages);
-			break;
-		}
-
-		for (i = 0; i < cur_npages; i++) {
-			len = rc > PAGE_SIZE ? PAGE_SIZE : rc;
-			bv[npages + i].bv_page = pages[i];
-			bv[npages + i].bv_offset = start;
-			bv[npages + i].bv_len = len - start;
-			rc -= len;
-			start = 0;
-		}
-
-		npages += cur_npages;
-	}
-
-	kvfree(pages);
-	ctx->bv = bv;
-	ctx->len = saved_len - count;
-	ctx->npages = npages;
-	iov_iter_bvec(&ctx->iter, rw, ctx->bv, npages, ctx->len);
-	return 0;
-}
-
 /**
  * cifs_alloc_hash - allocate hash and hash context together
  * @name: The name of the crypto hash algo
@@ -1129,25 +1046,6 @@ cifs_free_hash(struct shash_desc **sdesc)
 	*sdesc = NULL;
 }
 
-/**
- * rqst_page_get_length - obtain the length and offset for a page in smb_rqst
- * @rqst: The request descriptor
- * @page: The index of the page to query
- * @len: Where to store the length for this page:
- * @offset: Where to store the offset for this page
- */
-void rqst_page_get_length(const struct smb_rqst *rqst, unsigned int page,
-			  unsigned int *len, unsigned int *offset)
-{
-	*len = rqst->rq_pagesz;
-	*offset = (page == 0) ? rqst->rq_offset : 0;
-
-	if (rqst->rq_npages == 1 || page == rqst->rq_npages-1)
-		*len = rqst->rq_tailsz;
-	else if (page == 0)
-		*len = rqst->rq_pagesz - rqst->rq_offset;
-}
-
 void extract_unc_hostname(const char *unc, const char **h, size_t *len)
 {
 	const char *end;