From: Matthew Wilcox <willy@infradead.org>
To: linux-fsdevel@vger.kernel.org
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: [PATCH v4 16/36] iomap: Support large pages in write paths
Date: Fri, 15 May 2020 06:16:36 -0700 [thread overview]
Message-ID: <20200515131656.12890-17-willy@infradead.org> (raw)
In-Reply-To: <20200515131656.12890-1-willy@infradead.org>
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
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@infradead.org>
---
fs/iomap/buffered-io.c | 52 +++++++++++++++++++++++-------------------
1 file changed, 29 insertions(+), 23 deletions(-)
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 75f42c0d4cd9..b7504b8aa90c 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))
@@ -654,8 +656,8 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
else if (iomap->flags & IOMAP_F_BUFFER_HEAD)
status = __block_write_begin_int(page, pos, len, NULL, srcmap);
else
- status = __iomap_write_begin(inode, pos, len, flags, page,
- srcmap);
+ status = __iomap_write_begin(inode, pos, len, flags,
+ compound_head(page), srcmap);
if (unlikely(status))
goto out_unlock;
@@ -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;
}
@@ -754,7 +756,8 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied,
ret = block_write_end(NULL, inode->i_mapping, pos, len, copied,
page, NULL);
} else {
- ret = __iomap_write_end(inode, pos, len, copied, page);
+ ret = __iomap_write_end(inode, pos, len, copied,
+ compound_head(page));
}
/*
@@ -793,6 +796,10 @@ 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));
@@ -1129,7 +1136,7 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error)
next = bio->bi_private;
/* walk each page on bio, ending page IO on them */
- bio_for_each_segment_all(bv, bio, iter_all)
+ bio_for_each_thp_segment_all(bv, bio, iter_all)
iomap_finish_page_writeback(inode, bv->bv_page, error);
bio_put(bio);
}
@@ -1335,7 +1342,7 @@ 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 +1392,12 @@ 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 +1405,20 @@ 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 +1500,6 @@ 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 +1540,8 @@ 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 +1553,8 @@ 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 +1585,7 @@ 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
next prev parent reply other threads:[~2020-05-15 13:42 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-15 13:16 [PATCH v4 00/36] Large pages in the page cache Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 01/36] mm: Move PageDoubleMap bit Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 02/36] mm: Simplify PageDoubleMap with PF_SECOND policy Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 03/36] mm: Allow hpages to be arbitrary order Matthew Wilcox
2020-05-28 14:19 ` Zi Yan
2020-05-15 13:16 ` [PATCH v4 04/36] mm: Introduce thp_size Matthew Wilcox
2020-05-15 13:38 ` David Hildenbrand
2020-05-15 13:16 ` [PATCH v4 05/36] mm: Introduce thp_order Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 06/36] mm: Introduce offset_in_thp Matthew Wilcox
2020-05-15 13:39 ` David Hildenbrand
2020-05-22 17:15 ` Kirill A. Shutemov
2020-05-29 12:59 ` Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 07/36] fs: Add a filesystem flag for large pages Matthew Wilcox
2020-05-21 21:55 ` Dave Chinner
2020-05-21 23:29 ` Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 08/36] fs: Do not update nr_thps for large page mappings Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 09/36] fs: Introduce i_blocks_per_page Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 10/36] fs: Make page_mkwrite_check_truncate thp-aware Matthew Wilcox
2020-05-21 22:01 ` Dave Chinner
2020-05-21 23:30 ` Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 11/36] fs: Support THPs in zero_user_segments Matthew Wilcox
2020-05-25 4:55 ` Kirill A. Shutemov
2020-05-15 13:16 ` [PATCH v4 12/36] bio: Add bio_for_each_thp_segment_all Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 13/36] iomap: Support arbitrarily many blocks per page Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 14/36] iomap: Support large pages in iomap_adjust_read_range Matthew Wilcox
2020-05-21 22:24 ` Dave Chinner
2020-05-21 23:39 ` Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 15/36] iomap: Support large pages in read paths Matthew Wilcox
2020-05-15 13:16 ` Matthew Wilcox [this message]
2020-05-15 13:16 ` [PATCH v4 17/36] iomap: Inline data shouldn't see large pages Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 18/36] iomap: Handle tail pages in iomap_page_mkwrite Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 19/36] xfs: Support large pages Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 20/36] mm: Make prep_transhuge_page return its argument Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 21/36] mm: Add __page_cache_alloc_order Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 22/36] mm: Allow large pages to be added to the page cache Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 23/36] mm: Allow large pages to be removed from " Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 24/36] mm: Remove page fault assumption of compound page size Matthew Wilcox
2020-05-25 4:59 ` Kirill A. Shutemov
2020-05-15 13:16 ` [PATCH v4 25/36] mm: Fix total_mapcount assumption of " Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 26/36] mm: Avoid splitting large pages Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 27/36] mm: Fix truncation for pages of arbitrary size Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 28/36] mm: Support storing shadow entries for large pages Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 29/36] mm: Support retrieving tail pages from the page cache Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 30/36] mm: Support tail pages in wait_for_stable_page Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 31/36] mm: Add DEFINE_READAHEAD Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 32/36] mm: Make page_cache_readahead_unbounded take a readahead_control Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 33/36] mm: Make __do_page_cache_readahead " Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 34/36] mm: Allow PageReadahead to be set on head pages Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 35/36] mm: Add large page readahead Matthew Wilcox
2020-05-15 13:16 ` [PATCH v4 36/36] mm: Align THP mappings for non-DAX Matthew Wilcox
2020-05-26 22:05 ` William Kucharski
2020-05-26 22:20 ` Matthew Wilcox
2020-05-21 22:49 ` [PATCH v4 00/36] Large pages in the page cache Dave Chinner
2020-05-22 0:04 ` Matthew Wilcox
2020-05-22 2:57 ` Dave Chinner
2020-05-22 3:05 ` Matthew Wilcox
2020-05-25 23:07 ` Dave Chinner
2020-05-26 1:21 ` Matthew Wilcox
2020-05-28 11:00 ` William Kucharski
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200515131656.12890-17-willy@infradead.org \
--to=willy@infradead.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).