linux-kernel - [PATCHv2 24/41] fs: make block_write_{begin,end}() be able to handle huge pages

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1471027104-115213-25-git-send-email-kirill.shutemov@linux.intel.com>
Date:	Fri, 12 Aug 2016 21:38:07 +0300
From:	"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To:	"Theodore Ts'o" <tytso@....edu>,
	Andreas Dilger <adilger.kernel@...ger.ca>,
	Jan Kara <jack@...e.com>,
	Andrew Morton <akpm@...ux-foundation.org>
Cc:	Alexander Viro <viro@...iv.linux.org.uk>,
	Hugh Dickins <hughd@...gle.com>,
	Andrea Arcangeli <aarcange@...hat.com>,
	Dave Hansen <dave.hansen@...el.com>,
	Vlastimil Babka <vbabka@...e.cz>,
	Matthew Wilcox <willy@...radead.org>,
	Ross Zwisler <ross.zwisler@...ux.intel.com>,
	linux-ext4@...r.kernel.org, linux-fsdevel@...r.kernel.org,
	linux-kernel@...r.kernel.org, linux-mm@...ck.org,
	linux-block@...r.kernel.org,
	"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Subject: [PATCHv2 24/41] fs: make block_write_{begin,end}() be able to handle huge pages

It's more or less straight-forward.

Most changes are around getting offset/len withing page right and zero
out desired part of the page.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
---
 fs/buffer.c | 53 +++++++++++++++++++++++++++++++----------------------
 1 file changed, 31 insertions(+), 22 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index 2739f5dae690..7f50e5a63670 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1870,21 +1870,21 @@ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to)
 	do {
 		block_end = block_start + bh->b_size;
 
-		if (buffer_new(bh)) {
-			if (block_end > from && block_start < to) {
-				if (!PageUptodate(page)) {
-					unsigned start, size;
+		if (buffer_new(bh) && block_end > from && block_start < to) {
+			if (!PageUptodate(page)) {
+				unsigned start, size;
 
-					start = max(from, block_start);
-					size = min(to, block_end) - start;
+				start = max(from, block_start);
+				size = min(to, block_end) - start;
 
-					zero_user(page, start, size);
-					set_buffer_uptodate(bh);
-				}
-
-				clear_buffer_new(bh);
-				mark_buffer_dirty(bh);
+				zero_user(page + block_start / PAGE_SIZE,
+						start % PAGE_SIZE,
+						size);
+				set_buffer_uptodate(bh);
 			}
+
+			clear_buffer_new(bh);
+			mark_buffer_dirty(bh);
 		}
 
 		block_start = block_end;
@@ -1950,18 +1950,20 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
 int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
 		get_block_t *get_block, struct iomap *iomap)
 {
-	unsigned from = pos & (PAGE_SIZE - 1);
-	unsigned to = from + len;
-	struct inode *inode = page->mapping->host;
+	unsigned from, to;
+	struct inode *inode = page_mapping(page)->host;
 	unsigned block_start, block_end;
 	sector_t block;
 	int err = 0;
 	unsigned blocksize, bbits;
 	struct buffer_head *bh, *head, *wait[2], **wait_bh=wait;
 
+	page = compound_head(page);
+	from = pos & ~hpage_mask(page);
+	to = from + len;
 	BUG_ON(!PageLocked(page));
-	BUG_ON(from > PAGE_SIZE);
-	BUG_ON(to > PAGE_SIZE);
+	BUG_ON(from > hpage_size(page));
+	BUG_ON(to > hpage_size(page));
 	BUG_ON(from > to);
 
 	head = create_page_buffers(page, inode, 0);
@@ -2001,10 +2003,15 @@ int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
 					mark_buffer_dirty(bh);
 					continue;
 				}
-				if (block_end > to || block_start < from)
-					zero_user_segments(page,
-						to, block_end,
-						block_start, from);
+				if (block_end > to || block_start < from) {
+					BUG_ON(to - from  > PAGE_SIZE);
+					zero_user_segments(page +
+							block_start / PAGE_SIZE,
+						to % PAGE_SIZE,
+						(block_start % PAGE_SIZE) + blocksize,
+						block_start % PAGE_SIZE,
+						from % PAGE_SIZE);
+				}
 				continue;
 			}
 		}
@@ -2048,6 +2055,7 @@ static int __block_commit_write(struct inode *inode, struct page *page,
 	unsigned blocksize;
 	struct buffer_head *bh, *head;
 
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	bh = head = page_buffers(page);
 	blocksize = bh->b_size;
 
@@ -2114,7 +2122,8 @@ int block_write_end(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	unsigned start;
 
-	start = pos & (PAGE_SIZE - 1);
+	page = compound_head(page);
+	start = pos & ~hpage_mask(page);
 
 	if (unlikely(copied < len)) {
 		/*
-- 
2.8.1