1 files changed, 477 insertions, 78 deletions

diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index eacb82468437..68b45c82c37a 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -9,6 +9,8 @@
 #include <linux/scatterlist.h>
 #include <linux/highmem.h>
 #include <linux/kmemleak.h>
+#include <linux/bvec.h>
+#include <linux/uio.h>
 
 /**
  * sg_next - return the next scatterlist entry in a list
@@ -38,7 +40,7 @@ EXPORT_SYMBOL(sg_next);
  * @sg:		The scatterlist
  *
  * Description:
- * Allows to know how many entries are in sg, taking into acount
+ * Allows to know how many entries are in sg, taking into account
  * chaining as well
  *
  **/
@@ -59,7 +61,7 @@ EXPORT_SYMBOL(sg_nents);
  *
  * Description:
  * Determines the number of entries in sg that are required to meet
- * the supplied length, taking into acount chaining as well
+ * the supplied length, taking into account chaining as well
  *
  * Returns:
  *   the number of sg entries needed, negative error on failure
@@ -179,8 +181,10 @@ static void sg_kfree(struct scatterlist *sg, unsigned int nents)
  * __sg_free_table - Free a previously mapped sg table
  * @table:	The sg table header to use
  * @max_ents:	The maximum number of entries per single scatterlist
- * @skip_first_chunk: don't free the (preallocated) first scatterlist chunk
+ * @nents_first_chunk: Number of entries int the (preallocated) first
+ * 	scatterlist chunk, 0 means no such preallocated first chunk
  * @free_fn:	Free function
+ * @num_ents:	Number of entries in the table
  *
  *  Description:
  *    Free an sg table previously allocated and setup with
@@ -189,16 +193,18 @@ static void sg_kfree(struct scatterlist *sg, unsigned int nents)
  *
  **/
 void __sg_free_table(struct sg_table *table, unsigned int max_ents,
-		     bool skip_first_chunk, sg_free_fn *free_fn)
+		     unsigned int nents_first_chunk, sg_free_fn *free_fn,
+		     unsigned int num_ents)
 {
 	struct scatterlist *sgl, *next;
+	unsigned curr_max_ents = nents_first_chunk ?: max_ents;
 
 	if (unlikely(!table->sgl))
 		return;
 
 	sgl = table->sgl;
-	while (table->orig_nents) {
-		unsigned int alloc_size = table->orig_nents;
+	while (num_ents) {
+		unsigned int alloc_size = num_ents;
 		unsigned int sg_size;
 
 		/*
@@ -207,21 +213,22 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents,
 		 * sg_size is then one less than alloc size, since the last
 		 * element is the chain pointer.
 		 */
-		if (alloc_size > max_ents) {
-			next = sg_chain_ptr(&sgl[max_ents - 1]);
-			alloc_size = max_ents;
+		if (alloc_size > curr_max_ents) {
+			next = sg_chain_ptr(&sgl[curr_max_ents - 1]);
+			alloc_size = curr_max_ents;
 			sg_size = alloc_size - 1;
 		} else {
 			sg_size = alloc_size;
 			next = NULL;
 		}
 
-		table->orig_nents -= sg_size;
-		if (skip_first_chunk)
-			skip_first_chunk = false;
+		num_ents -= sg_size;
+		if (nents_first_chunk)
+			nents_first_chunk = 0;
 		else
 			free_fn(sgl, alloc_size);
 		sgl = next;
+		curr_max_ents = max_ents;
 	}
 
 	table->sgl = NULL;
@@ -229,13 +236,27 @@ void __sg_free_table(struct sg_table *table, unsigned int max_ents,
 EXPORT_SYMBOL(__sg_free_table);
 
 /**
+ * sg_free_append_table - Free a previously allocated append sg table.
+ * @table:	 The mapped sg append table header
+ *
+ **/
+void sg_free_append_table(struct sg_append_table *table)
+{
+	__sg_free_table(&table->sgt, SG_MAX_SINGLE_ALLOC, 0, sg_kfree,
+			table->total_nents);
+}
+EXPORT_SYMBOL(sg_free_append_table);
+
+
+/**
  * sg_free_table - Free a previously allocated sg table
  * @table:	The mapped sg table header
  *
  **/
 void sg_free_table(struct sg_table *table)
 {
-	__sg_free_table(table, SG_MAX_SINGLE_ALLOC, false, sg_kfree);
+	__sg_free_table(table, SG_MAX_SINGLE_ALLOC, 0, sg_kfree,
+			table->orig_nents);
 }
 EXPORT_SYMBOL(sg_free_table);
 
@@ -244,6 +265,9 @@ EXPORT_SYMBOL(sg_free_table);
  * @table:	The sg table header to use
  * @nents:	Number of entries in sg list
  * @max_ents:	The maximum number of entries the allocator returns per call
+ * @first_chunk: first SGL if preallocated (may be %NULL)
+ * @nents_first_chunk: Number of entries in the (preallocated) first
+ * 	scatterlist chunk, 0 means no such preallocated chunk provided by user
  * @gfp_mask:	GFP allocation mask
  * @alloc_fn:	Allocator to use
  *
@@ -260,10 +284,13 @@ EXPORT_SYMBOL(sg_free_table);
  **/
 int __sg_alloc_table(struct sg_table *table, unsigned int nents,
 		     unsigned int max_ents, struct scatterlist *first_chunk,
-		     gfp_t gfp_mask, sg_alloc_fn *alloc_fn)
+		     unsigned int nents_first_chunk, gfp_t gfp_mask,
+		     sg_alloc_fn *alloc_fn)
 {
 	struct scatterlist *sg, *prv;
 	unsigned int left;
+	unsigned curr_max_ents = nents_first_chunk ?: max_ents;
+	unsigned prv_max_ents;
 
 	memset(table, 0, sizeof(*table));
 
@@ -279,8 +306,8 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents,
 	do {
 		unsigned int sg_size, alloc_size = left;
 
-		if (alloc_size > max_ents) {
-			alloc_size = max_ents;
+		if (alloc_size > curr_max_ents) {
+			alloc_size = curr_max_ents;
 			sg_size = alloc_size - 1;
 		} else
 			sg_size = alloc_size;
@@ -303,7 +330,7 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents,
 			if (prv)
 				table->nents = ++table->orig_nents;
 
- 			return -ENOMEM;
+			return -ENOMEM;
 		}
 
 		sg_init_table(sg, alloc_size);
@@ -314,7 +341,7 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents,
 		 * If this is not the first mapping, chain previous part.
 		 */
 		if (prv)
-			sg_chain(prv, max_ents, sg);
+			sg_chain(prv, prv_max_ents, sg);
 		else
 			table->sgl = sg;
 
@@ -325,6 +352,8 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents,
 			sg_mark_end(&sg[sg_size - 1]);
 
 		prv = sg;
+		prv_max_ents = curr_max_ents;
+		curr_max_ents = max_ents;
 	} while (left);
 
 	return 0;
@@ -347,66 +376,141 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask)
 	int ret;
 
 	ret = __sg_alloc_table(table, nents, SG_MAX_SINGLE_ALLOC,
-			       NULL, gfp_mask, sg_kmalloc);
+			       NULL, 0, gfp_mask, sg_kmalloc);
 	if (unlikely(ret))
-		__sg_free_table(table, SG_MAX_SINGLE_ALLOC, false, sg_kfree);
-
+		sg_free_table(table);
 	return ret;
 }
 EXPORT_SYMBOL(sg_alloc_table);
 
+static struct scatterlist *get_next_sg(struct sg_append_table *table,
+				       struct scatterlist *cur,
+				       unsigned long needed_sges,
+				       gfp_t gfp_mask)
+{
+	struct scatterlist *new_sg, *next_sg;
+	unsigned int alloc_size;
+
+	if (cur) {
+		next_sg = sg_next(cur);
+		/* Check if last entry should be keeped for chainning */
+		if (!sg_is_last(next_sg) || needed_sges == 1)
+			return next_sg;
+	}
+
+	alloc_size = min_t(unsigned long, needed_sges, SG_MAX_SINGLE_ALLOC);
+	new_sg = sg_kmalloc(alloc_size, gfp_mask);
+	if (!new_sg)
+		return ERR_PTR(-ENOMEM);
+	sg_init_table(new_sg, alloc_size);
+	if (cur) {
+		table->total_nents += alloc_size - 1;
+		__sg_chain(next_sg, new_sg);
+	} else {
+		table->sgt.sgl = new_sg;
+		table->total_nents = alloc_size;
+	}
+	return new_sg;
+}
+
+static bool pages_are_mergeable(struct page *a, struct page *b)
+{
+	if (page_to_pfn(a) != page_to_pfn(b) + 1)
+		return false;
+	if (!zone_device_pages_have_same_pgmap(a, b))
+		return false;
+	return true;
+}
+
 /**
- * __sg_alloc_table_from_pages - Allocate and initialize an sg table from
- *			         an array of pages
- * @sgt:	 The sg table header to use
- * @pages:	 Pointer to an array of page pointers
- * @n_pages:	 Number of pages in the pages array
+ * sg_alloc_append_table_from_pages - Allocate and initialize an append sg
+ *                                    table from an array of pages
+ * @sgt_append:  The sg append table to use
+ * @pages:       Pointer to an array of page pointers
+ * @n_pages:     Number of pages in the pages array
  * @offset:      Offset from start of the first page to the start of a buffer
  * @size:        Number of valid bytes in the buffer (after offset)
- * @max_segment: Maximum size of a scatterlist node in bytes (page aligned)
+ * @max_segment: Maximum size of a scatterlist element in bytes
+ * @left_pages:  Left pages caller have to set after this call
  * @gfp_mask:	 GFP allocation mask
  *
- *  Description:
- *    Allocate and initialize an sg table from a list of pages. Contiguous
- *    ranges of the pages are squashed into a single scatterlist node up to the
- *    maximum size specified in @max_segment. An user may provide an offset at a
- *    start and a size of valid data in a buffer specified by the page array.
- *    The returned sg table is released by sg_free_table.
+ * Description:
+ *    In the first call it allocate and initialize an sg table from a list of
+ *    pages, else reuse the scatterlist from sgt_append. Contiguous ranges of
+ *    the pages are squashed into a single scatterlist entry up to the maximum
+ *    size specified in @max_segment.  A user may provide an offset at a start
+ *    and a size of valid data in a buffer specified by the page array. The
+ *    returned sg table is released by sg_free_append_table
  *
  * Returns:
  *   0 on success, negative error on failure
+ *
+ * Notes:
+ *   If this function returns non-0 (eg failure), the caller must call
+ *   sg_free_append_table() to cleanup any leftover allocations.
+ *
+ *   In the fist call, sgt_append must by initialized.
  */
-int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
-				unsigned int n_pages, unsigned int offset,
-				unsigned long size, unsigned int max_segment,
-				gfp_t gfp_mask)
+int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append,
+		struct page **pages, unsigned int n_pages, unsigned int offset,
+		unsigned long size, unsigned int max_segment,
+		unsigned int left_pages, gfp_t gfp_mask)
 {
-	unsigned int chunks, cur_page, seg_len, i;
-	int ret;
-	struct scatterlist *s;
+	unsigned int chunks, cur_page, seg_len, i, prv_len = 0;
+	unsigned int added_nents = 0;
+	struct scatterlist *s = sgt_append->prv;
+	struct page *last_pg;
 
-	if (WARN_ON(!max_segment || offset_in_page(max_segment)))
+	/*
+	 * The algorithm below requires max_segment to be aligned to PAGE_SIZE
+	 * otherwise it can overshoot.
+	 */
+	max_segment = ALIGN_DOWN(max_segment, PAGE_SIZE);
+	if (WARN_ON(max_segment < PAGE_SIZE))
 		return -EINVAL;
 
+	if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && sgt_append->prv)
+		return -EOPNOTSUPP;
+
+	if (sgt_append->prv) {
+		unsigned long next_pfn = (page_to_phys(sg_page(sgt_append->prv)) +
+			sgt_append->prv->offset + sgt_append->prv->length) / PAGE_SIZE;
+
+		if (WARN_ON(offset))
+			return -EINVAL;
+
+		/* Merge contiguous pages into the last SG */
+		prv_len = sgt_append->prv->length;
+		if (page_to_pfn(pages[0]) == next_pfn) {
+			last_pg = pfn_to_page(next_pfn - 1);
+			while (n_pages && pages_are_mergeable(pages[0], last_pg)) {
+				if (sgt_append->prv->length + PAGE_SIZE > max_segment)
+					break;
+				sgt_append->prv->length += PAGE_SIZE;
+				last_pg = pages[0];
+				pages++;
+				n_pages--;
+			}
+			if (!n_pages)
+				goto out;
+		}
+	}
+
 	/* compute number of contiguous chunks */
 	chunks = 1;
 	seg_len = 0;
 	for (i = 1; i < n_pages; i++) {
 		seg_len += PAGE_SIZE;
 		if (seg_len >= max_segment ||
-		    page_to_pfn(pages[i]) != page_to_pfn(pages[i - 1]) + 1) {
+		    !pages_are_mergeable(pages[i], pages[i - 1])) {
 			chunks++;
 			seg_len = 0;
 		}
 	}
 
-	ret = sg_alloc_table(sgt, chunks, gfp_mask);
-	if (unlikely(ret))
-		return ret;
-
 	/* merging chunks and putting them into the scatterlist */
 	cur_page = 0;
-	for_each_sg(sgt->sgl, s, sgt->orig_nents, i) {
+	for (i = 0; i < chunks; i++) {
 		unsigned int j, chunk_size;
 
 		/* look for the end of the current chunk */
@@ -414,51 +518,82 @@ int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
 		for (j = cur_page + 1; j < n_pages; j++) {
 			seg_len += PAGE_SIZE;
 			if (seg_len >= max_segment ||
-			    page_to_pfn(pages[j]) !=
-			    page_to_pfn(pages[j - 1]) + 1)
+			    !pages_are_mergeable(pages[j], pages[j - 1]))
 				break;
 		}
 
+		/* Pass how many chunks might be left */
+		s = get_next_sg(sgt_append, s, chunks - i + left_pages,
+				gfp_mask);
+		if (IS_ERR(s)) {
+			/*
+			 * Adjust entry length to be as before function was
+			 * called.
+			 */
+			if (sgt_append->prv)
+				sgt_append->prv->length = prv_len;
+			return PTR_ERR(s);
+		}
 		chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset;
 		sg_set_page(s, pages[cur_page],
 			    min_t(unsigned long, size, chunk_size), offset);
+		added_nents++;
 		size -= chunk_size;
 		offset = 0;
 		cur_page = j;
 	}
-
+	sgt_append->sgt.nents += added_nents;
+	sgt_append->sgt.orig_nents = sgt_append->sgt.nents;
+	sgt_append->prv = s;
+out:
+	if (!left_pages)
+		sg_mark_end(s);
 	return 0;
 }
-EXPORT_SYMBOL(__sg_alloc_table_from_pages);
+EXPORT_SYMBOL(sg_alloc_append_table_from_pages);
 
 /**
- * sg_alloc_table_from_pages - Allocate and initialize an sg table from
- *			       an array of pages
+ * sg_alloc_table_from_pages_segment - Allocate and initialize an sg table from
+ *                                     an array of pages and given maximum
+ *                                     segment.
  * @sgt:	 The sg table header to use
  * @pages:	 Pointer to an array of page pointers
  * @n_pages:	 Number of pages in the pages array
  * @offset:      Offset from start of the first page to the start of a buffer
  * @size:        Number of valid bytes in the buffer (after offset)
+ * @max_segment: Maximum size of a scatterlist element in bytes
  * @gfp_mask:	 GFP allocation mask
  *
  *  Description:
  *    Allocate and initialize an sg table from a list of pages. Contiguous
- *    ranges of the pages are squashed into a single scatterlist node. A user
- *    may provide an offset at a start and a size of valid data in a buffer
- *    specified by the page array. The returned sg table is released by
- *    sg_free_table.
+ *    ranges of the pages are squashed into a single scatterlist node up to the
+ *    maximum size specified in @max_segment. A user may provide an offset at a
+ *    start and a size of valid data in a buffer specified by the page array.
  *
- * Returns:
+ *    The returned sg table is released by sg_free_table.
+ *
+ *  Returns:
  *   0 on success, negative error on failure
  */
-int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
-			      unsigned int n_pages, unsigned int offset,
-			      unsigned long size, gfp_t gfp_mask)
+int sg_alloc_table_from_pages_segment(struct sg_table *sgt, struct page **pages,
+				unsigned int n_pages, unsigned int offset,
+				unsigned long size, unsigned int max_segment,
+				gfp_t gfp_mask)
 {
-	return __sg_alloc_table_from_pages(sgt, pages, n_pages, offset, size,
-					   SCATTERLIST_MAX_SEGMENT, gfp_mask);
+	struct sg_append_table append = {};
+	int err;
+
+	err = sg_alloc_append_table_from_pages(&append, pages, n_pages, offset,
+					       size, max_segment, 0, gfp_mask);
+	if (err) {
+		sg_free_append_table(&append);
+		return err;
+	}
+	memcpy(sgt, &append.sgt, sizeof(*sgt));
+	WARN_ON(append.total_nents != sgt->orig_nents);
+	return 0;
 }
-EXPORT_SYMBOL(sg_alloc_table_from_pages);
+EXPORT_SYMBOL(sg_alloc_table_from_pages_segment);
 
 #ifdef CONFIG_SGL_ALLOC
 
@@ -494,7 +629,7 @@ struct scatterlist *sgl_alloc_order(unsigned long long length,
 		nalloc++;
 	}
 	sgl = kmalloc_array(nalloc, sizeof(struct scatterlist),
-			    (gfp & ~GFP_DMA) | __GFP_ZERO);
+			    gfp & ~GFP_DMA);
 	if (!sgl)
 		return NULL;
 
@@ -504,7 +639,7 @@ struct scatterlist *sgl_alloc_order(unsigned long long length,
 		elem_len = min_t(u64, length, PAGE_SIZE << order);
 		page = alloc_pages(gfp, order);
 		if (!page) {
-			sgl_free(sgl);
+			sgl_free_order(sgl, order);
 			return NULL;
 		}
 
@@ -654,6 +789,7 @@ EXPORT_SYMBOL(__sg_page_iter_dma_next);
  * @miter: sg mapping iter to be started
  * @sgl: sg list to iterate over
  * @nents: number of sg entries
+ * @flags: sg iterator flags
  *
  * Description:
  *   Starts mapping iterator @miter.
@@ -706,8 +842,7 @@ static bool sg_miter_get_next_page(struct sg_mapping_iter *miter)
  *   stops @miter.
  *
  * Context:
- *   Don't care if @miter is stopped, or not proceeded yet.
- *   Otherwise, preemption disabled if the SG_MITER_ATOMIC is set.
+ *   Don't care.
  *
  * Returns:
  *   true if @miter contains the valid mapping.  false if end of sg
@@ -743,8 +878,7 @@ EXPORT_SYMBOL(sg_miter_skip);
  *   @miter->addr and @miter->length point to the current mapping.
  *
  * Context:
- *   Preemption disabled if SG_MITER_ATOMIC.  Preemption must stay disabled
- *   till @miter is stopped.  May sleep if !SG_MITER_ATOMIC.
+ *   May sleep if !SG_MITER_ATOMIC.
  *
  * Returns:
  *   true if @miter contains the next mapping.  false if end of sg
@@ -784,8 +918,7 @@ EXPORT_SYMBOL(sg_miter_next);
  *   need to be released during iteration.
  *
  * Context:
- *   Preemption disabled if the SG_MITER_ATOMIC is set.  Don't care
- *   otherwise.
+ *   Don't care otherwise.
  */
 void sg_miter_stop(struct sg_mapping_iter *miter)
 {
@@ -796,12 +929,11 @@ void sg_miter_stop(struct sg_mapping_iter *miter)
 		miter->__offset += miter->consumed;
 		miter->__remaining -= miter->consumed;
 
-		if ((miter->__flags & SG_MITER_TO_SG) &&
-		    !PageSlab(miter->page))
-			flush_kernel_dcache_page(miter->page);
+		if (miter->__flags & SG_MITER_TO_SG)
+			flush_dcache_page(miter->page);
 
 		if (miter->__flags & SG_MITER_ATOMIC) {
-			WARN_ON_ONCE(preemptible());
+			WARN_ON_ONCE(!pagefault_disabled());
 			kunmap_atomic(miter->addr);
 		} else
 			kunmap(miter->page);
@@ -822,7 +954,7 @@ EXPORT_SYMBOL(sg_miter_stop);
  * @buflen:		 The number of bytes to copy
  * @skip:		 Number of bytes to skip before copying
  * @to_buffer:		 transfer direction (true == from an sg list to a
- *			 buffer, false == from a buffer to an sg list
+ *			 buffer, false == from a buffer to an sg list)
  *
  * Returns the number of copied bytes.
  *
@@ -842,7 +974,7 @@ size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf,
 	sg_miter_start(&miter, sgl, nents, sg_flags);
 
 	if (!sg_miter_skip(&miter, skip))
-		return false;
+		return 0;
 
 	while ((offset < buflen) && sg_miter_next(&miter)) {
 		unsigned int len;
@@ -967,3 +1099,270 @@ size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents,
 	return offset;
 }
 EXPORT_SYMBOL(sg_zero_buffer);
+
+/*
+ * Extract and pin a list of up to sg_max pages from UBUF- or IOVEC-class
+ * iterators, and add them to the scatterlist.
+ */
+static ssize_t extract_user_to_sg(struct iov_iter *iter,
+				  ssize_t maxsize,
+				  struct sg_table *sgtable,
+				  unsigned int sg_max,
+				  iov_iter_extraction_t extraction_flags)
+{
+	struct scatterlist *sg = sgtable->sgl + sgtable->nents;
+	struct page **pages;
+	unsigned int npages;
+	ssize_t ret = 0, res;
+	size_t len, off;
+
+	/* We decant the page list into the tail of the scatterlist */
+	pages = (void *)sgtable->sgl +
+		array_size(sg_max, sizeof(struct scatterlist));
+	pages -= sg_max;
+
+	do {
+		res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max,
+					     extraction_flags, &off);
+		if (res < 0)
+			goto failed;
+
+		len = res;
+		maxsize -= len;
+		ret += len;
+		npages = DIV_ROUND_UP(off + len, PAGE_SIZE);
+		sg_max -= npages;
+
+		for (; npages > 0; npages--) {
+			struct page *page = *pages;
+			size_t seg = min_t(size_t, PAGE_SIZE - off, len);
+
+			*pages++ = NULL;
+			sg_set_page(sg, page, seg, off);
+			sgtable->nents++;
+			sg++;
+			len -= seg;
+			off = 0;
+		}
+	} while (maxsize > 0 && sg_max > 0);
+
+	return ret;
+
+failed:
+	while (sgtable->nents > sgtable->orig_nents)
+		unpin_user_page(sg_page(&sgtable->sgl[--sgtable->nents]));
+	return res;
+}
+
+/*
+ * Extract up to sg_max pages from a BVEC-type iterator and add them to the
+ * scatterlist.  The pages are not pinned.
+ */
+static ssize_t extract_bvec_to_sg(struct iov_iter *iter,
+				  ssize_t maxsize,
+				  struct sg_table *sgtable,
+				  unsigned int sg_max,
+				  iov_iter_extraction_t extraction_flags)
+{
+	const struct bio_vec *bv = iter->bvec;
+	struct scatterlist *sg = sgtable->sgl + sgtable->nents;
+	unsigned long start = iter->iov_offset;
+	unsigned int i;
+	ssize_t ret = 0;
+
+	for (i = 0; i < iter->nr_segs; i++) {
+		size_t off, len;
+
+		len = bv[i].bv_len;
+		if (start >= len) {
+			start -= len;
+			continue;
+		}
+
+		len = min_t(size_t, maxsize, len - start);
+		off = bv[i].bv_offset + start;
+
+		sg_set_page(sg, bv[i].bv_page, len, off);
+		sgtable->nents++;
+		sg++;
+		sg_max--;
+
+		ret += len;
+		maxsize -= len;
+		if (maxsize <= 0 || sg_max == 0)
+			break;
+		start = 0;
+	}
+
+	if (ret > 0)
+		iov_iter_advance(iter, ret);
+	return ret;
+}
+
+/*
+ * Extract up to sg_max pages from a KVEC-type iterator and add them to the
+ * scatterlist.  This can deal with vmalloc'd buffers as well as kmalloc'd or
+ * static buffers.  The pages are not pinned.
+ */
+static ssize_t extract_kvec_to_sg(struct iov_iter *iter,
+				  ssize_t maxsize,
+				  struct sg_table *sgtable,
+				  unsigned int sg_max,
+				  iov_iter_extraction_t extraction_flags)
+{
+	const struct kvec *kv = iter->kvec;
+	struct scatterlist *sg = sgtable->sgl + sgtable->nents;
+	unsigned long start = iter->iov_offset;
+	unsigned int i;
+	ssize_t ret = 0;
+
+	for (i = 0; i < iter->nr_segs; i++) {
+		struct page *page;
+		unsigned long kaddr;
+		size_t off, len, seg;
+
+		len = kv[i].iov_len;
+		if (start >= len) {
+			start -= len;
+			continue;
+		}
+
+		kaddr = (unsigned long)kv[i].iov_base + start;
+		off = kaddr & ~PAGE_MASK;
+		len = min_t(size_t, maxsize, len - start);
+		kaddr &= PAGE_MASK;
+
+		maxsize -= len;
+		ret += len;
+		do {
+			seg = min_t(size_t, len, PAGE_SIZE - off);
+			if (is_vmalloc_or_module_addr((void *)kaddr))
+				page = vmalloc_to_page((void *)kaddr);
+			else
+				page = virt_to_page((void *)kaddr);
+
+			sg_set_page(sg, page, len, off);
+			sgtable->nents++;
+			sg++;
+			sg_max--;
+
+			len -= seg;
+			kaddr += PAGE_SIZE;
+			off = 0;
+		} while (len > 0 && sg_max > 0);
+
+		if (maxsize <= 0 || sg_max == 0)
+			break;
+		start = 0;
+	}
+
+	if (ret > 0)
+		iov_iter_advance(iter, ret);
+	return ret;
+}
+
+/*
+ * Extract up to sg_max folios from an XARRAY-type iterator and add them to
+ * the scatterlist.  The pages are not pinned.
+ */
+static ssize_t extract_xarray_to_sg(struct iov_iter *iter,
+				    ssize_t maxsize,
+				    struct sg_table *sgtable,
+				    unsigned int sg_max,
+				    iov_iter_extraction_t extraction_flags)
+{
+	struct scatterlist *sg = sgtable->sgl + sgtable->nents;
+	struct xarray *xa = iter->xarray;
+	struct folio *folio;
+	loff_t start = iter->xarray_start + iter->iov_offset;
+	pgoff_t index = start / PAGE_SIZE;
+	ssize_t ret = 0;
+	size_t offset, len;
+	XA_STATE(xas, xa, index);
+
+	rcu_read_lock();
+
+	xas_for_each(&xas, folio, ULONG_MAX) {
+		if (xas_retry(&xas, folio))
+			continue;
+		if (WARN_ON(xa_is_value(folio)))
+			break;
+		if (WARN_ON(folio_test_hugetlb(folio)))
+			break;
+
+		offset = offset_in_folio(folio, start);
+		len = min_t(size_t, maxsize, folio_size(folio) - offset);
+
+		sg_set_page(sg, folio_page(folio, 0), len, offset);
+		sgtable->nents++;
+		sg++;
+		sg_max--;
+
+		maxsize -= len;
+		ret += len;
+		if (maxsize <= 0 || sg_max == 0)
+			break;
+	}
+
+	rcu_read_unlock();
+	if (ret > 0)
+		iov_iter_advance(iter, ret);
+	return ret;
+}
+
+/**
+ * extract_iter_to_sg - Extract pages from an iterator and add to an sglist
+ * @iter: The iterator to extract from
+ * @maxsize: The amount of iterator to copy
+ * @sgtable: The scatterlist table to fill in
+ * @sg_max: Maximum number of elements in @sgtable that may be filled
+ * @extraction_flags: Flags to qualify the request
+ *
+ * Extract the page fragments from the given amount of the source iterator and
+ * add them to a scatterlist that refers to all of those bits, to a maximum
+ * addition of @sg_max elements.
+ *
+ * The pages referred to by UBUF- and IOVEC-type iterators are extracted and
+ * pinned; BVEC-, KVEC- and XARRAY-type are extracted but aren't pinned; PIPE-
+ * and DISCARD-type are not supported.
+ *
+ * No end mark is placed on the scatterlist; that's left to the caller.
+ *
+ * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA
+ * be allowed on the pages extracted.
+ *
+ * If successful, @sgtable->nents is updated to include the number of elements
+ * added and the number of bytes added is returned.  @sgtable->orig_nents is
+ * left unaltered.
+ *
+ * The iov_iter_extract_mode() function should be used to query how cleanup
+ * should be performed.
+ */
+ssize_t extract_iter_to_sg(struct iov_iter *iter, size_t maxsize,
+			   struct sg_table *sgtable, unsigned int sg_max,
+			   iov_iter_extraction_t extraction_flags)
+{
+	if (maxsize == 0)
+		return 0;
+
+	switch (iov_iter_type(iter)) {
+	case ITER_UBUF:
+	case ITER_IOVEC:
+		return extract_user_to_sg(iter, maxsize, sgtable, sg_max,
+					  extraction_flags);
+	case ITER_BVEC:
+		return extract_bvec_to_sg(iter, maxsize, sgtable, sg_max,
+					  extraction_flags);
+	case ITER_KVEC:
+		return extract_kvec_to_sg(iter, maxsize, sgtable, sg_max,
+					  extraction_flags);
+	case ITER_XARRAY:
+		return extract_xarray_to_sg(iter, maxsize, sgtable, sg_max,
+					    extraction_flags);
+	default:
+		pr_err("%s(%u) unsupported\n", __func__, iov_iter_type(iter));
+		WARN_ON_ONCE(1);
+		return -EIO;
+	}
+}
+EXPORT_SYMBOL_GPL(extract_iter_to_sg);