[PATCH] fuse: fix hang on SMP

Fuse didn't always call i_size_write() with i_mutex held which caused
rare hangs on SMP/32bit.  This bug has been present since fuse-2.2,
well before being merged into mainline.

The simplest solution is to protect i_size_write() with the
per-connection spinlock.  Using i_mutex for this purpose would require
some restructuring of the code and I'm not even sure it's always safe
to acquire i_mutex in all places i_size needs to be set.

Since most of vmtruncate is already duplicated for other reasons,
duplicate the remaining part as well, making all i_size_write() calls
internal to fuse.

Using i_size_write() was unnecessary in fuse_init_inode(), since this
function is only called on a newly created locked inode.

Reported by a few people over the years, but special thanks to Dana
Henriksen who was persistent enough in helping me debug it.

Signed-off-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 409ce6a7cca4ccd2e53f46693a5e4301bef87245..5d7c726be186a2da8446b6dca5d31ffcfce0698d 100644 (file)
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -935,14 +935,30 @@ static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg)
        }
 }
 
+static void fuse_vmtruncate(struct inode *inode, loff_t offset)
+{
+       struct fuse_conn *fc = get_fuse_conn(inode);
+       int need_trunc;
+
+       spin_lock(&fc->lock);
+       need_trunc = inode->i_size > offset;
+       i_size_write(inode, offset);
+       spin_unlock(&fc->lock);
+
+       if (need_trunc) {
+               struct address_space *mapping = inode->i_mapping;
+               unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
+               truncate_inode_pages(mapping, offset);
+       }
+}
+
 /*
  * Set attributes, and at the same time refresh them.
  *
  * Truncation is slightly complicated, because the 'truncate' request
  * may fail, in which case we don't want to touch the mapping.
- * vmtruncate() doesn't allow for this case.  So do the rlimit
- * checking by hand and call vmtruncate() only after the file has
- * actually been truncated.
+ * vmtruncate() doesn't allow for this case, so do the rlimit checking
+ * and the actual truncation by hand.
  */
 static int fuse_setattr(struct dentry *entry, struct iattr *attr)
 {
@@ -993,12 +1009,8 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr)
                        make_bad_inode(inode);
                        err = -EIO;
                } else {
-                       if (is_truncate) {
-                               loff_t origsize = i_size_read(inode);
-                               i_size_write(inode, outarg.attr.size);
-                               if (origsize > outarg.attr.size)
-                                       vmtruncate(inode, outarg.attr.size);
-                       }
+                       if (is_truncate)
+                               fuse_vmtruncate(inode, outarg.attr.size);
                        fuse_change_attributes(inode, &outarg.attr);
                        fi->i_time = time_to_jiffies(outarg.attr_valid,
                                                     outarg.attr_valid_nsec);

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 5c4fcd1dbf5908d29401aa3f83d1aac23a1d8244..4e174c883dffab8a72f8673ee21103e1aac8b0ca 100644 (file)
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -481,8 +481,10 @@ static int fuse_commit_write(struct file *file, struct page *page,
                err = -EIO;
        if (!err) {
                pos += count;
-               if (pos > i_size_read(inode))
+               spin_lock(&fc->lock);
+               if (pos > inode->i_size)
                        i_size_write(inode, pos);
+               spin_unlock(&fc->lock);
 
                if (offset == 0 && to == PAGE_CACHE_SIZE) {
                        clear_page_dirty(page);
@@ -586,8 +588,12 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf,
        }
        fuse_put_request(fc, req);
        if (res > 0) {
-               if (write && pos > i_size_read(inode))
-                       i_size_write(inode, pos);
+               if (write) {
+                       spin_lock(&fc->lock);
+                       if (pos > inode->i_size)
+                               i_size_write(inode, pos);
+                       spin_unlock(&fc->lock);
+               }
                *ppos = pos;
        }
        fuse_invalidate_attr(inode);

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 7d25092262ae71d3eb0af390b60b8e8a0c587a9e..65df8a4a7b1ffbbddf40999b0fb978e1bb7beaab 100644 (file)
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -109,6 +109,7 @@ static int fuse_remount_fs(struct super_block *sb, int *flags, char *data)
 
 void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr)
 {
+       struct fuse_conn *fc = get_fuse_conn(inode);
        if (S_ISREG(inode->i_mode) && i_size_read(inode) != attr->size)
                invalidate_inode_pages(inode->i_mapping);
 
@@ -117,7 +118,9 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr)
        inode->i_nlink   = attr->nlink;
        inode->i_uid     = attr->uid;
        inode->i_gid     = attr->gid;
+       spin_lock(&fc->lock);
        i_size_write(inode, attr->size);
+       spin_unlock(&fc->lock);
        inode->i_blksize = PAGE_CACHE_SIZE;
        inode->i_blocks  = attr->blocks;
        inode->i_atime.tv_sec   = attr->atime;
@@ -131,7 +134,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr)
 static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
 {
        inode->i_mode = attr->mode & S_IFMT;
-       i_size_write(inode, attr->size);
+       inode->i_size = attr->size;
        if (S_ISREG(inode->i_mode)) {
                fuse_init_common(inode);
                fuse_init_file_inode(inode);