1 files changed, 351 insertions, 34 deletions

diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 8d7519a8f308..4af1c8b0775a 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -9,29 +9,9 @@
 #include <linux/scatterlist.h>
 #include <linux/highmem.h>
 #include <linux/kmemleak.h>
-
-/**
- * sg_next - return the next scatterlist entry in a list
- * @sg:		The current sg entry
- *
- * Description:
- *   Usually the next entry will be @sg@ + 1, but if this sg element is part
- *   of a chained scatterlist, it could jump to the start of a new
- *   scatterlist array.
- *
- **/
-struct scatterlist *sg_next(struct scatterlist *sg)
-{
-	if (sg_is_last(sg))
-		return NULL;
-
-	sg++;
-	if (unlikely(sg_is_chain(sg)))
-		sg = sg_chain_ptr(sg);
-
-	return sg;
-}
-EXPORT_SYMBOL(sg_next);
+#include <linux/bvec.h>
+#include <linux/uio.h>
+#include <linux/folio_queue.h>
 
 /**
  * sg_nents - return total count of entries in scatterlist
@@ -93,9 +73,9 @@ EXPORT_SYMBOL(sg_nents_for_len);
  *   Should only be used casually, it (currently) scans the entire list
  *   to get the last entry.
  *
- *   Note that the @sgl@ pointer passed in need not be the first one,
- *   the important bit is that @nents@ denotes the number of entries that
- *   exist from @sgl@.
+ *   Note that the @sgl pointer passed in need not be the first one,
+ *   the important bit is that @nents denotes the number of entries that
+ *   exist from @sgl.
  *
  **/
 struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents)
@@ -263,7 +243,8 @@ 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
- * @nents_first_chunk: Number of entries int the (preallocated) first
+ * @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
@@ -364,7 +345,7 @@ EXPORT_SYMBOL(__sg_alloc_table);
  * @gfp_mask:	GFP allocation mask
  *
  *  Description:
- *    Allocate and initialize an sg table. If @nents@ is larger than
+ *    Allocate and initialize an sg table. If @nents is larger than
  *    SG_MAX_SINGLE_ALLOC a chained sg table will be setup.
  *
  **/
@@ -470,14 +451,14 @@ int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append,
 		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;
+		unsigned long next_pfn;
 
 		if (WARN_ON(offset))
 			return -EINVAL;
 
 		/* Merge contiguous pages into the last SG */
 		prv_len = sgt_append->prv->length;
+		next_pfn = (sg_phys(sgt_append->prv) + prv_len) / PAGE_SIZE;
 		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)) {
@@ -786,6 +767,7 @@ 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.
@@ -874,7 +856,7 @@ EXPORT_SYMBOL(sg_miter_skip);
  *   @miter->addr and @miter->length point to the current mapping.
  *
  * Context:
- *   May sleep if !SG_MITER_ATOMIC.
+ *   May sleep if !SG_MITER_ATOMIC && !SG_MITER_LOCAL.
  *
  * Returns:
  *   true if @miter contains the next mapping.  false if end of sg
@@ -896,6 +878,8 @@ bool sg_miter_next(struct sg_mapping_iter *miter)
 
 	if (miter->__flags & SG_MITER_ATOMIC)
 		miter->addr = kmap_atomic(miter->page) + miter->__offset;
+	else if (miter->__flags & SG_MITER_LOCAL)
+		miter->addr = kmap_local_page(miter->page) + miter->__offset;
 	else
 		miter->addr = kmap(miter->page) + miter->__offset;
 
@@ -931,7 +915,9 @@ void sg_miter_stop(struct sg_mapping_iter *miter)
 		if (miter->__flags & SG_MITER_ATOMIC) {
 			WARN_ON_ONCE(!pagefault_disabled());
 			kunmap_atomic(miter->addr);
-		} else
+		} else if (miter->__flags & SG_MITER_LOCAL)
+			kunmap_local(miter->addr);
+		else
 			kunmap(miter->page);
 
 		miter->page = NULL;
@@ -960,7 +946,7 @@ size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf,
 {
 	unsigned int offset = 0;
 	struct sg_mapping_iter miter;
-	unsigned int sg_flags = SG_MITER_ATOMIC;
+	unsigned int sg_flags = SG_MITER_LOCAL;
 
 	if (to_buffer)
 		sg_flags |= SG_MITER_FROM_SG;
@@ -1075,7 +1061,7 @@ size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents,
 {
 	unsigned int offset = 0;
 	struct sg_mapping_iter miter;
-	unsigned int sg_flags = SG_MITER_ATOMIC | SG_MITER_TO_SG;
+	unsigned int sg_flags = SG_MITER_LOCAL | SG_MITER_TO_SG;
 
 	sg_miter_start(&miter, sgl, nents, sg_flags);
 
@@ -1095,3 +1081,334 @@ 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 FOLIOQ-type iterator and add them to
+ * the scatterlist.  The pages are not pinned.
+ */
+static ssize_t extract_folioq_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 folio_queue *folioq = iter->folioq;
+	struct scatterlist *sg = sgtable->sgl + sgtable->nents;
+	unsigned int slot = iter->folioq_slot;
+	ssize_t ret = 0;
+	size_t offset = iter->iov_offset;
+
+	BUG_ON(!folioq);
+
+	if (slot >= folioq_nr_slots(folioq)) {
+		folioq = folioq->next;
+		if (WARN_ON_ONCE(!folioq))
+			return 0;
+		slot = 0;
+	}
+
+	do {
+		struct folio *folio = folioq_folio(folioq, slot);
+		size_t fsize = folioq_folio_size(folioq, slot);
+
+		if (offset < fsize) {
+			size_t part = umin(maxsize - ret, fsize - offset);
+
+			sg_set_page(sg, folio_page(folio, 0), part, offset);
+			sgtable->nents++;
+			sg++;
+			sg_max--;
+			offset += part;
+			ret += part;
+		}
+
+		if (offset >= fsize) {
+			offset = 0;
+			slot++;
+			if (slot >= folioq_nr_slots(folioq)) {
+				if (!folioq->next) {
+					WARN_ON_ONCE(ret < iter->count);
+					break;
+				}
+				folioq = folioq->next;
+				slot = 0;
+			}
+		}
+	} while (sg_max > 0 && ret < maxsize);
+
+	iter->folioq = folioq;
+	iter->folioq_slot = slot;
+	iter->iov_offset = offset;
+	iter->count -= 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-, FOLIOQ- and XARRAY-type are extracted but aren't
+ * pinned; DISCARD-type is 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_FOLIOQ:
+		return extract_folioq_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);