[PATCH v3 13/25] iomap: Support large pages in write paths

From: Matthew Wilcox
Date: Wed Apr 29 2020 - 09:41:37 EST


From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>

Use thp_size() instead of PAGE_SIZE and offset_in_thp() instead of
offset_in_page(). Also simplify the logic in iomap_do_writepage()
for determining end of file.

Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
---
fs/iomap/buffered-io.c | 43 +++++++++++++++++++++++-------------------
1 file changed, 24 insertions(+), 19 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 75f42c0d4cd9..709be90a1997 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -466,7 +466,7 @@ iomap_is_partially_uptodate(struct page *page, unsigned long from,
unsigned i;

/* Limit range to one page */
- len = min_t(unsigned, PAGE_SIZE - from, count);
+ len = min_t(unsigned, thp_size(page) - from, count);

/* First and last blocks in range within page */
first = from >> inode->i_blkbits;
@@ -510,7 +510,7 @@ iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len)
* If we are invalidating the entire page, clear the dirty state from it
* and release it to avoid unnecessary buildup of the LRU.
*/
- if (offset == 0 && len == PAGE_SIZE) {
+ if (offset == 0 && len == thp_size(page)) {
WARN_ON_ONCE(PageWriteback(page));
cancel_dirty_page(page);
iomap_page_release(page);
@@ -586,7 +586,9 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags,
loff_t block_size = i_blocksize(inode);
loff_t block_start = pos & ~(block_size - 1);
loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1);
- unsigned from = offset_in_page(pos), to = from + len, poff, plen;
+ unsigned from = offset_in_thp(page, pos);
+ unsigned to = from + len;
+ unsigned poff, plen;
int status;

if (PageUptodate(page))
@@ -718,7 +720,7 @@ __iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
*/
if (unlikely(copied < len && !PageUptodate(page)))
return 0;
- iomap_set_range_uptodate(page, offset_in_page(pos), len);
+ iomap_set_range_uptodate(page, offset_in_thp(page, pos), len);
iomap_set_page_dirty(page);
return copied;
}
@@ -793,6 +795,10 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
unsigned long bytes; /* Bytes to write to page */
size_t copied; /* Bytes copied from user */

+ /*
+ * XXX: We don't know what size page we'll find in the
+ * page cache, so only copy up to a regular page boundary.
+ */
offset = offset_in_page(pos);
bytes = min_t(unsigned long, PAGE_SIZE - offset,
iov_iter_count(i));
@@ -1335,7 +1341,7 @@ iomap_add_to_ioend(struct inode *inode, loff_t offset, struct page *page,
{
sector_t sector = iomap_sector(&wpc->iomap, offset);
unsigned len = i_blocksize(inode);
- unsigned poff = offset & (PAGE_SIZE - 1);
+ unsigned poff = offset & (thp_size(page) - 1);
bool merged, same_page = false;

if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, offset, sector)) {
@@ -1385,11 +1391,12 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
struct iomap_page *iop = to_iomap_page(page);
struct iomap_ioend *ioend, *next;
unsigned len = i_blocksize(inode);
- u64 file_offset; /* file offset of page */
+ loff_t pos;
int error = 0, count = 0, i;
+ int nr_blocks = i_blocks_per_page(inode, page);
LIST_HEAD(submit_list);

- WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop);
+ WARN_ON_ONCE(nr_blocks > 1 && !iop);
WARN_ON_ONCE(iop && atomic_read(&iop->write_count) != 0);

/*
@@ -1397,20 +1404,20 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
* end of the current map or find the current map invalid, grab a new
* one.
*/
- for (i = 0, file_offset = page_offset(page);
- i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset;
- i++, file_offset += len) {
+ for (i = 0, pos = page_offset(page);
+ i < nr_blocks && pos < end_offset;
+ i++, pos += len) {
if (iop && !test_bit(i, iop->uptodate))
continue;

- error = wpc->ops->map_blocks(wpc, inode, file_offset);
+ error = wpc->ops->map_blocks(wpc, inode, pos);
if (error)
break;
if (WARN_ON_ONCE(wpc->iomap.type == IOMAP_INLINE))
continue;
if (wpc->iomap.type == IOMAP_HOLE)
continue;
- iomap_add_to_ioend(inode, file_offset, page, iop, wpc, wbc,
+ iomap_add_to_ioend(inode, pos, page, iop, wpc, wbc,
&submit_list);
count++;
}
@@ -1492,7 +1499,6 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
{
struct iomap_writepage_ctx *wpc = data;
struct inode *inode = page->mapping->host;
- pgoff_t end_index;
u64 end_offset;
loff_t offset;

@@ -1533,10 +1539,8 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
* ---------------------------------^------------------|
*/
offset = i_size_read(inode);
- end_index = offset >> PAGE_SHIFT;
- if (page->index < end_index)
- end_offset = (loff_t)(page->index + 1) << PAGE_SHIFT;
- else {
+ end_offset = page_offset(page) + thp_size(page);
+ if (end_offset > offset) {
/*
* Check whether the page to write out is beyond or straddles
* i_size or not.
@@ -1548,7 +1552,8 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
* | | Straddles |
* ---------------------------------^-----------|--------|
*/
- unsigned offset_into_page = offset & (PAGE_SIZE - 1);
+ unsigned offset_into_page = offset_in_thp(page, offset);
+ pgoff_t end_index = offset >> PAGE_SHIFT;

/*
* Skip the page if it is fully outside i_size, e.g. due to a
@@ -1579,7 +1584,7 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
* memory is zeroed when mapped, and writes to that region are
* not written out to the file."
*/
- zero_user_segment(page, offset_into_page, PAGE_SIZE);
+ zero_user_segment(page, offset_into_page, thp_size(page));

/* Adjust the end_offset to the end of file */
end_offset = offset;
--
2.26.2