summaryrefslogtreecommitdiff
path: root/fs/hugetlbfs/inode.c
diff options
context:
space:
mode:
authorAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>2012-03-21 16:34:08 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-03-21 17:54:58 -0700
commita05b0855fd15504972dba2358e5faa172a1e50ba (patch)
treef4cba4ef12d888ec472714f67ef7bcec318a5191 /fs/hugetlbfs/inode.c
parentf5bf18fa22f8c41a13eb8762c7373eb3a93a7333 (diff)
hugetlbfs: avoid taking i_mutex from hugetlbfs_read()
Taking i_mutex in hugetlbfs_read() can result in deadlock with mmap as explained below Thread A: read() on hugetlbfs hugetlbfs_read() called i_mutex grabbed hugetlbfs_read_actor() called __copy_to_user() called page fault is triggered Thread B, sharing address space with A: mmap() the same file ->mmap_sem is grabbed on task_B->mm->mmap_sem hugetlbfs_file_mmap() is called attempt to grab ->i_mutex and block waiting for A to give it up Thread A: pagefault handled blocked on attempt to grab task_A->mm->mmap_sem, which happens to be the same thing as task_B->mm->mmap_sem. Block waiting for B to give it up. AFAIU the i_mutex locking was added to hugetlbfs_read() as per http://lkml.indiana.edu/hypermail/linux/kernel/0707.2/3066.html to take care of the race between truncate and read. This patch fixes this by looking at page->mapping under lock_page() (find_lock_page()) to ensure that the inode didn't get truncated in the range during a parallel read. Ideally we can extend the patch to make sure we don't increase i_size in mmap. But that will break userspace, because applications will now have to use truncate(2) to increase i_size in hugetlbfs. Based on the original patch from Hillf Danton. Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Hillf Danton <dhillf@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@kernel.org> [everything after 2007 :)] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/hugetlbfs/inode.c')
-rw-r--r--fs/hugetlbfs/inode.c25
1 files changed, 9 insertions, 16 deletions
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index b7bc7868c7b5..19654cfe780b 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -245,17 +245,10 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
loff_t isize;
ssize_t retval = 0;
- mutex_lock(&inode->i_mutex);
-
/* validate length */
if (len == 0)
goto out;
- isize = i_size_read(inode);
- if (!isize)
- goto out;
-
- end_index = (isize - 1) >> huge_page_shift(h);
for (;;) {
struct page *page;
unsigned long nr, ret;
@@ -263,18 +256,21 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
/* nr is the maximum number of bytes to copy from this page */
nr = huge_page_size(h);
+ isize = i_size_read(inode);
+ if (!isize)
+ goto out;
+ end_index = (isize - 1) >> huge_page_shift(h);
if (index >= end_index) {
if (index > end_index)
goto out;
nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
- if (nr <= offset) {
+ if (nr <= offset)
goto out;
- }
}
nr = nr - offset;
/* Find the page */
- page = find_get_page(mapping, index);
+ page = find_lock_page(mapping, index);
if (unlikely(page == NULL)) {
/*
* We have a HOLE, zero out the user-buffer for the
@@ -286,17 +282,18 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
else
ra = 0;
} else {
+ unlock_page(page);
+
/*
* We have the page, copy it to user space buffer.
*/
ra = hugetlbfs_read_actor(page, offset, buf, len, nr);
ret = ra;
+ page_cache_release(page);
}
if (ra < 0) {
if (retval == 0)
retval = ra;
- if (page)
- page_cache_release(page);
goto out;
}
@@ -306,16 +303,12 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
index += offset >> huge_page_shift(h);
offset &= ~huge_page_mask(h);
- if (page)
- page_cache_release(page);
-
/* short read or no more work */
if ((ret != nr) || (len == 0))
break;
}
out:
*ppos = ((loff_t)index << huge_page_shift(h)) + offset;
- mutex_unlock(&inode->i_mutex);
return retval;
}