ceph: track read contexts in ceph_file_info
Previously ceph_read_iter() uses current->journal to pass context info
to ceph_readpages(), so that ceph_readpages() can distinguish read(2)
from readahead(2)/fadvise(2)/madvise(2). The problem is that page fault
can happen when copying data to userspace memory. Page fault may call
other filesystem's page_mkwrite() if the userspace memory is mapped to a
file. The later filesystem may also want to use current->journal.
The fix is define a on-stack data structure in ceph_read_iter(), add it
to context list in ceph_file_info. ceph_readpages() searches the list,
find if there is a context belongs to current thread.
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 770dd3b..6639926 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -181,6 +181,10 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
return -ENOMEM;
}
cf->fmode = fmode;
+
+ spin_lock_init(&cf->rw_contexts_lock);
+ INIT_LIST_HEAD(&cf->rw_contexts);
+
cf->next_offset = 2;
cf->readdir_cache_idx = -1;
file->private_data = cf;
@@ -464,6 +468,7 @@ int ceph_release(struct inode *inode, struct file *file)
ceph_mdsc_put_request(cf->last_readdir);
kfree(cf->last_name);
kfree(cf->dir_info);
+ WARN_ON(!list_empty(&cf->rw_contexts));
kmem_cache_free(ceph_file_cachep, cf);
/* wake up anyone waiting for caps on this inode */
@@ -1199,12 +1204,13 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
retry_op = READ_INLINE;
}
} else {
+ CEPH_DEFINE_RW_CONTEXT(rw_ctx, got);
dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
ceph_cap_string(got));
- current->journal_info = filp;
+ ceph_add_rw_context(fi, &rw_ctx);
ret = generic_file_read_iter(iocb, to);
- current->journal_info = NULL;
+ ceph_del_rw_context(fi, &rw_ctx);
}
dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);