[PATCH v2 4/5] mm/shmem: remove page-copy fallback in shmem read path

[Chi Zhiling]

From: Chi Zhiling <chizhiling@xxxxxxxxxx>

This is perp patch for folio batch support which removing the fallback
to page-copy mode from shmem reads.

The existing hwpoison fallback would require fetching the same folio
multiple times to read its each pages, which complicates the
batching model. Instead, move hwpoison handling into
copy_each_pages_to_iter(), allowing the error path to be centralized.

This simplifies the shmem fast read path and avoids special-case
handling that conflicts with folio batching support.

Signed-off-by: Chi Zhiling <chizhiling@xxxxxxxxxx>
---
 mm/shmem.c | 63 +++++++++++++++++++++++++++++-------------------------
 1 file changed, 34 insertions(+), 29 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index b08118fbd275..cac355685e49 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3353,6 +3353,30 @@ static size_t copy_zero_to_iter(size_t bytes, struct iov_iter *i)
 	return written;
 }
 
+static size_t copy_pages_to_iter(struct folio *folio, size_t offset,
+		size_t bytes, struct iov_iter *i, int *error)
+{
+	struct page *page;
+	unsigned long off, nr, ret, written = 0;
+
+	do {
+		page = folio_page(folio, offset >> PAGE_SHIFT);
+		if (PageHWPoison(page)) {
+			*error = -EIO;
+			break;
+		}
+
+		off = offset_in_page(offset);
+		nr = min(PAGE_SIZE - off, bytes - written);
+
+		ret = copy_page_to_iter(page, off, nr, i);
+		offset += ret;
+		written += ret;
+	} while (written < bytes && ret == nr);
+
+	return written;
+}
+
 static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
@@ -3365,10 +3389,8 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 	for (;;) {
 		struct folio *folio = NULL;
-		struct page *page = NULL;
 		unsigned long nr, ret;
 		loff_t end_offset, i_size = i_size_read(inode);
-		bool fallback_page_copy = false;
 		size_t fsize;
 
 		if (unlikely(iocb->ki_pos >= i_size))
@@ -3376,25 +3398,13 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 		index = iocb->ki_pos >> PAGE_SHIFT;
 		error = shmem_get_folio(inode, index, 0, &folio, SGP_READ);
+		if (folio)
+			folio_unlock(folio);
 		if (error) {
 			if (error == -EINVAL)
 				error = 0;
 			break;
 		}
-		if (folio) {
-			folio_unlock(folio);
-
-			page = folio_file_page(folio, index);
-			if (PageHWPoison(page)) {
-				folio_put(folio);
-				error = -EIO;
-				break;
-			}
-
-			if (folio_test_large(folio) &&
-			    folio_test_has_hwpoisoned(folio))
-				fallback_page_copy = true;
-		}
 
 		/*
 		 * We must evaluate after, since reads (unlike writes)
@@ -3406,12 +3416,9 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 				folio_put(folio);
 			break;
 		}
-		end_offset = min_t(loff_t, i_size, iocb->ki_pos + to->count);
-		if (folio && likely(!fallback_page_copy))
-			fsize = folio_size(folio);
-		else
-			fsize = PAGE_SIZE;
+		fsize = folio ? folio_size(folio) : PAGE_SIZE;
 		offset = iocb->ki_pos & (fsize - 1);
+		end_offset = min_t(loff_t, i_size, iocb->ki_pos + to->count);
 		nr = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset);
 
 		if (folio) {
@@ -3420,12 +3427,8 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			 * virtual addresses, take care about potential aliasing
 			 * before reading the page on the kernel side.
 			 */
-			if (mapping_writably_mapped(mapping)) {
-				if (likely(!fallback_page_copy))
-					flush_dcache_folio(folio);
-				else
-					flush_dcache_page(page);
-			}
+			if (mapping_writably_mapped(mapping))
+				flush_dcache_folio(folio);
 
 			/*
 			 * Mark the folio accessed if we read the beginning.
@@ -3436,10 +3439,10 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			 * Ok, we have the page, and it's up-to-date, so
 			 * now we can copy it to user space...
 			 */
-			if (likely(!fallback_page_copy))
+			if (likely(!folio_contain_hwpoisoned_page(folio)))
 				ret = copy_folio_to_iter(folio, offset, nr, to);
 			else
-				ret = copy_page_to_iter(page, offset, nr, to);
+				ret = copy_pages_to_iter(folio, offset, nr, to, &error);
 			folio_put(folio);
 		} else if (user_backed_iter(to)) {
 			/*
@@ -3462,6 +3465,8 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 		if (!iov_iter_count(to))
 			break;
+		if (unlikely(error))
+			break;
 		if (ret < nr) {
 			error = -EFAULT;
 			break;
-- 
2.43.0