linux-kernel - [RFC 2/3] fs: Add block

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]

Date:	Mon,  5 Aug 2013 12:44:00 -0700
From:	Andy Lutomirski <luto@...capital.net>
To:	linux-mm@...ck.org, linux-ext4@...r.kernel.org
Cc:	linux-kernel@...r.kernel.org, Andy Lutomirski <luto@...capital.net>
Subject: [RFC 2/3] fs: Add block_willwrite

This provides generic support for MADV_WILLWRITE.  It creates and maps
buffer heads, but it should not result in anything being marked dirty.

Signed-off-by: Andy Lutomirski <luto@...capital.net>
---

As described in the 0/0 summary, this may have issues.

 fs/buffer.c                 | 57 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/buffer_head.h |  3 +++
 2 files changed, 60 insertions(+)

diff --git a/fs/buffer.c b/fs/buffer.c
index 4d74335..017e822 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2444,6 +2444,63 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 }
 EXPORT_SYMBOL(block_page_mkwrite);
 
+long block_willwrite(struct vm_area_struct *vma,
+		     unsigned long start, unsigned long end,
+		     get_block_t get_block)
+{
+	long ret = 0;
+	loff_t size;
+	struct inode *inode = file_inode(vma->vm_file);
+	struct super_block *sb = inode->i_sb;
+
+	for (; start < end; start += PAGE_CACHE_SIZE) {
+		struct page *p;
+		int size_in_page;
+		int tmp = get_user_pages_fast(start, 1, 0, &p);
+		if (tmp == 0)
+			tmp = -EFAULT;
+		if (tmp != 1) {
+			ret = tmp;
+			break;
+		}
+
+		sb_start_pagefault(sb);
+
+		lock_page(p);
+		size = i_size_read(inode);
+		if (WARN_ON_ONCE(p->mapping != inode->i_mapping) ||
+		    (page_offset(p) > size)) {
+			ret = -EFAULT;  /* A real write would have failed. */
+			goto pagedone_unlock;
+		}
+
+		/* page is partially inside EOF? */
+		if (((p->index + 1) << PAGE_CACHE_SHIFT) > size)
+			size_in_page = size & ~PAGE_CACHE_MASK;
+		else
+			size_in_page = PAGE_CACHE_SIZE;
+
+		tmp = __block_write_begin(p, 0, size_in_page, get_block);
+		if (tmp) {
+			ret = tmp;
+			goto pagedone_unlock;
+		}
+
+		ret += PAGE_CACHE_SIZE;
+
+		/* No need to commit -- we're not writing anything yet. */
+
+	pagedone_unlock:
+		unlock_page(p);
+		sb_end_pagefault(sb);
+		if (ret < 0)
+			break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(block_willwrite);
+
 /*
  * nobh_write_begin()'s prereads are special: the buffer_heads are freed
  * immediately, while under the page lock.  So it needs a special end_io
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 91fa9a9..c84639d 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -230,6 +230,9 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 				get_block_t get_block);
 int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 				get_block_t get_block);
+long block_willwrite(struct vm_area_struct *vma,
+		     unsigned long start, unsigned long end,
+		     get_block_t get_block);
 /* Convert errno to return value from ->page_mkwrite() call */
 static inline int block_page_mkwrite_return(int err)
 {
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/