1 files changed, 144 insertions, 13 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 0e20a8d6dd93..b794943bce76 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -42,6 +42,8 @@
 #include <linux/ramfs.h>
 #include <linux/page_idle.h>
 #include <linux/migrate.h>
+#include <linux/pipe_fs_i.h>
+#include <linux/splice.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -2440,21 +2442,19 @@ static int filemap_read_folio(struct file *file, filler_t filler,
 }
 
 static bool filemap_range_uptodate(struct address_space *mapping,
-		loff_t pos, struct iov_iter *iter, struct folio *folio)
+		loff_t pos, size_t count, struct folio *folio,
+		bool need_uptodate)
 {
-	int count;
-
 	if (folio_test_uptodate(folio))
 		return true;
 	/* pipes can't handle partially uptodate pages */
-	if (iov_iter_is_pipe(iter))
+	if (need_uptodate)
 		return false;
 	if (!mapping->a_ops->is_partially_uptodate)
 		return false;
 	if (mapping->host->i_blkbits >= folio_shift(folio))
 		return false;
 
-	count = iter->count;
 	if (folio_pos(folio) > pos) {
 		count -= folio_pos(folio) - pos;
 		pos = 0;
@@ -2466,8 +2466,8 @@ static bool filemap_range_uptodate(struct address_space *mapping,
 }
 
 static int filemap_update_page(struct kiocb *iocb,
-		struct address_space *mapping, struct iov_iter *iter,
-		struct folio *folio)
+		struct address_space *mapping, size_t count,
+		struct folio *folio, bool need_uptodate)
 {
 	int error;
 
@@ -2501,7 +2501,8 @@ static int filemap_update_page(struct kiocb *iocb,
 		goto unlock;
 
 	error = 0;
-	if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, folio))
+	if (filemap_range_uptodate(mapping, iocb->ki_pos, count, folio,
+				   need_uptodate))
 		goto unlock;
 
 	error = -EAGAIN;
@@ -2577,8 +2578,8 @@ static int filemap_readahead(struct kiocb *iocb, struct file *file,
 	return 0;
 }
 
-static int filemap_get_pages(struct kiocb *iocb, struct iov_iter *iter,
-		struct folio_batch *fbatch)
+static int filemap_get_pages(struct kiocb *iocb, size_t count,
+		struct folio_batch *fbatch, bool need_uptodate)
 {
 	struct file *filp = iocb->ki_filp;
 	struct address_space *mapping = filp->f_mapping;
@@ -2589,7 +2590,7 @@ static int filemap_get_pages(struct kiocb *iocb, struct iov_iter *iter,
 	int err = 0;
 
 	/* "last_index" is the index of the page beyond the end of the read */
-	last_index = DIV_ROUND_UP(iocb->ki_pos + iter->count, PAGE_SIZE);
+	last_index = DIV_ROUND_UP(iocb->ki_pos + count, PAGE_SIZE);
 retry:
 	if (fatal_signal_pending(current))
 		return -EINTR;
@@ -2622,7 +2623,8 @@ retry:
 		if ((iocb->ki_flags & IOCB_WAITQ) &&
 		    folio_batch_count(fbatch) > 1)
 			iocb->ki_flags |= IOCB_NOWAIT;
-		err = filemap_update_page(iocb, mapping, iter, folio);
+		err = filemap_update_page(iocb, mapping, count, folio,
+					  need_uptodate);
 		if (err)
 			goto err;
 	}
@@ -2692,7 +2694,8 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
 		if (unlikely(iocb->ki_pos >= i_size_read(inode)))
 			break;
 
-		error = filemap_get_pages(iocb, iter, &fbatch);
+		error = filemap_get_pages(iocb, iter->count, &fbatch,
+					  iov_iter_is_pipe(iter));
 		if (error < 0)
 			break;
 
@@ -2842,6 +2845,134 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 }
 EXPORT_SYMBOL(generic_file_read_iter);
 
+/*
+ * Splice subpages from a folio into a pipe.
+ */
+size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
+			      struct folio *folio, loff_t fpos, size_t size)
+{
+	struct page *page;
+	size_t spliced = 0, offset = offset_in_folio(folio, fpos);
+
+	page = folio_page(folio, offset / PAGE_SIZE);
+	size = min(size, folio_size(folio) - offset);
+	offset %= PAGE_SIZE;
+
+	while (spliced < size &&
+	       !pipe_full(pipe->head, pipe->tail, pipe->max_usage)) {
+		struct pipe_buffer *buf = pipe_head_buf(pipe);
+		size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced);
+
+		*buf = (struct pipe_buffer) {
+			.ops	= &page_cache_pipe_buf_ops,
+			.page	= page,
+			.offset	= offset,
+			.len	= part,
+		};
+		folio_get(folio);
+		pipe->head++;
+		page++;
+		spliced += part;
+		offset = 0;
+	}
+
+	return spliced;
+}
+
+/*
+ * Splice folios from the pagecache of a buffered (ie. non-O_DIRECT) file into
+ * a pipe.
+ */
+ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
+			    struct pipe_inode_info *pipe,
+			    size_t len, unsigned int flags)
+{
+	struct folio_batch fbatch;
+	struct kiocb iocb;
+	size_t total_spliced = 0, used, npages;
+	loff_t isize, end_offset;
+	bool writably_mapped;
+	int i, error = 0;
+
+	init_sync_kiocb(&iocb, in);
+	iocb.ki_pos = *ppos;
+
+	/* Work out how much data we can actually add into the pipe */
+	used = pipe_occupancy(pipe->head, pipe->tail);
+	npages = max_t(ssize_t, pipe->max_usage - used, 0);
+	len = min_t(size_t, len, npages * PAGE_SIZE);
+
+	folio_batch_init(&fbatch);
+
+	do {
+		cond_resched();
+
+		if (*ppos >= i_size_read(file_inode(in)))
+			break;
+
+		iocb.ki_pos = *ppos;
+		error = filemap_get_pages(&iocb, len, &fbatch, true);
+		if (error < 0)
+			break;
+
+		/*
+		 * i_size must be checked after we know the pages are Uptodate.
+		 *
+		 * Checking i_size after the check allows us to calculate
+		 * the correct value for "nr", which means the zero-filled
+		 * part of the page is not copied back to userspace (unless
+		 * another truncate extends the file - this is desired though).
+		 */
+		isize = i_size_read(file_inode(in));
+		if (unlikely(*ppos >= isize))
+			break;
+		end_offset = min_t(loff_t, isize, *ppos + len);
+
+		/*
+		 * Once we start copying data, we don't want to be touching any
+		 * cachelines that might be contended:
+		 */
+		writably_mapped = mapping_writably_mapped(in->f_mapping);
+
+		for (i = 0; i < folio_batch_count(&fbatch); i++) {
+			struct folio *folio = fbatch.folios[i];
+			size_t n;
+
+			if (folio_pos(folio) >= end_offset)
+				goto out;
+			folio_mark_accessed(folio);
+
+			/*
+			 * If users can be writing to this folio using arbitrary
+			 * virtual addresses, take care of potential aliasing
+			 * before reading the folio on the kernel side.
+			 */
+			if (writably_mapped)
+				flush_dcache_folio(folio);
+
+			n = min_t(loff_t, len, isize - *ppos);
+			n = splice_folio_into_pipe(pipe, folio, *ppos, n);
+			if (!n)
+				goto out;
+			len -= n;
+			total_spliced += n;
+			*ppos += n;
+			in->f_ra.prev_pos = *ppos;
+			if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+				goto out;
+		}
+
+		folio_batch_release(&fbatch);
+	} while (len);
+
+out:
+	folio_batch_release(&fbatch);
+	file_accessed(in);
+
+	return total_spliced ? total_spliced : error;
+}
+EXPORT_SYMBOL(filemap_splice_read);
+
 static inline loff_t folio_seek_hole_data(struct xa_state *xas,
 		struct address_space *mapping, struct folio *folio,
 		loff_t start, loff_t end, bool seek_data)