Btrfs: Clean pte corresponding to page straddling i_size

When extending a file by either "truncate up" or by writing beyond i_size, the
page which had i_size needs to be marked "read only" so that future writes to
the page via mmap interface causes btrfs_page_mkwrite() to be invoked. If not,
a write performed after extending the file via the mmap interface will find
the page to be writaeable and continue writing to the page without invoking
btrfs_page_mkwrite() i.e. we end up writing to a file without reserving disk
space.

Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 58bb297..953f0ad 100644 (file)
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1778,6 +1778,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
        ssize_t err;
        loff_t pos;
        size_t count;
+       loff_t oldsize;
+       int clean_page = 0;
 
        mutex_lock(&inode->i_mutex);
        err = generic_write_checks(iocb, from);
@@ -1816,14 +1818,17 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
        pos = iocb->ki_pos;
        count = iov_iter_count(from);
        start_pos = round_down(pos, root->sectorsize);
-       if (start_pos > i_size_read(inode)) {
+       oldsize = i_size_read(inode);
+       if (start_pos > oldsize) {
                /* Expand hole size to cover write data, preventing empty gap */
                end_pos = round_up(pos + count, root->sectorsize);
-               err = btrfs_cont_expand(inode, i_size_read(inode), end_pos);
+               err = btrfs_cont_expand(inode, oldsize, end_pos);
                if (err) {
                        mutex_unlock(&inode->i_mutex);
                        goto out;
                }
+               if (start_pos > round_up(oldsize, root->sectorsize))
+                       clean_page = 1;
        }
 
        if (sync)
@@ -1835,6 +1840,9 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
                num_written = __btrfs_buffered_write(file, from, pos);
                if (num_written > 0)
                        iocb->ki_pos = pos + num_written;
+               if (clean_page)
+                       pagecache_isize_extended(inode, oldsize,
+                                               i_size_read(inode));
        }
 
        mutex_unlock(&inode->i_mutex);

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8a7c68f..7d4b2bf 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4899,7 +4899,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
        }
 
        if (newsize > oldsize) {
-               truncate_pagecache(inode, newsize);
                /*
                 * Don't do an expanding truncate while snapshoting is ongoing.
                 * This is to ensure the snapshot captures a fully consistent
@@ -4922,6 +4921,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 
                i_size_write(inode, newsize);
                btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+               pagecache_isize_extended(inode, oldsize, newsize);
                ret = btrfs_update_inode(trans, root, inode);
                btrfs_end_write_no_snapshoting(root);
                btrfs_end_transaction(trans, root);