virtiofs: implement dax read/write operations

This patch implements basic DAX support. mmap() is not implemented
yet and will come in later patches. This patch looks into implemeting
read/write.

We make use of interval tree to keep track of per inode dax mappings.

Do not use dax for file extending writes, instead just send WRITE message
to daemon (like we do for direct I/O path). This will keep write and
i_size change atomic w.r.t crash.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Peng Tao <tao.peng@linux.alibaba.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

fs/fuse/Kconfig

@@ -42,6 +42,7 @@ config VIRTIO_FS
 config FUSE_DAX
 	bool "Virtio Filesystem Direct Host Memory Access support"
 	default y
+	select INTERVAL_TREE
 	depends on VIRTIO_FS
 	depends on FS_DAX
 	depends on DAX_DRIVER

fs/fuse/file.c

@@ -1539,10 +1539,14 @@ static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
 	struct fuse_file *ff = file->private_data;
+	struct inode *inode = file_inode(file);
 
-	if (is_bad_inode(file_inode(file)))
+	if (is_bad_inode(inode))
 		return -EIO;
 
+	if (FUSE_IS_DAX(inode))
+		return fuse_dax_read_iter(iocb, to);
+
 	if (!(ff->open_flags & FOPEN_DIRECT_IO))
 		return fuse_cache_read_iter(iocb, to);
 	else
@@ -1553,10 +1557,14 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct fuse_file *ff = file->private_data;
+	struct inode *inode = file_inode(file);
 
-	if (is_bad_inode(file_inode(file)))
+	if (is_bad_inode(inode))
 		return -EIO;
 
+	if (FUSE_IS_DAX(inode))
+		return fuse_dax_write_iter(iocb, from);
+
 	if (!(ff->open_flags & FOPEN_DIRECT_IO))
 		return fuse_cache_write_iter(iocb, from);
 	else
@@ -3440,4 +3448,7 @@ void fuse_init_file_inode(struct inode *inode)
 	fi->writectr = 0;
 	init_waitqueue_head(&fi->page_waitq);
 	fi->writepages = RB_ROOT;
+
+	if (IS_ENABLED(CONFIG_FUSE_DAX))
+		fuse_dax_inode_init(inode);
 }

fs/fuse/fuse_i.h

@@ -148,6 +148,13 @@ struct fuse_inode {
 
 	/** Lock to protect write related fields */
 	spinlock_t lock;
+
+#ifdef CONFIG_FUSE_DAX
+	/*
+	 * Dax specific inode data
+	 */
+	struct fuse_inode_dax *dax;
+#endif
 };
 
 /** FUSE inode state bits */
@@ -1104,8 +1111,16 @@ void fuse_free_conn(struct fuse_conn *fc);
 
 /* dax.c */
 
+#define FUSE_IS_DAX(inode) (IS_ENABLED(CONFIG_FUSE_DAX) && IS_DAX(inode))
+
+ssize_t fuse_dax_read_iter(struct kiocb *iocb, struct iov_iter *to);
+ssize_t fuse_dax_write_iter(struct kiocb *iocb, struct iov_iter *from);
+int fuse_dax_mmap(struct file *file, struct vm_area_struct *vma);
 int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev);
 void fuse_dax_conn_free(struct fuse_conn *fc);
+bool fuse_dax_inode_alloc(struct super_block *sb, struct fuse_inode *fi);
+void fuse_dax_inode_init(struct inode *inode);
+void fuse_dax_inode_cleanup(struct inode *inode);
 bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment);
 
 #endif /* _FS_FUSE_I_H */

fs/fuse/inode.c

@@ -87,12 +87,19 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	mutex_init(&fi->mutex);
 	spin_lock_init(&fi->lock);
 	fi->forget = fuse_alloc_forget();
-	if (!fi->forget) {
-		kmem_cache_free(fuse_inode_cachep, fi);
-		return NULL;
-	}
+	if (!fi->forget)
+		goto out_free;
+
+	if (IS_ENABLED(CONFIG_FUSE_DAX) && !fuse_dax_inode_alloc(sb, fi))
+		goto out_free_forget;
 
 	return &fi->inode;
+
+out_free_forget:
+	kfree(fi->forget);
+out_free:
+	kmem_cache_free(fuse_inode_cachep, fi);
+	return NULL;
 }
 
 static void fuse_free_inode(struct inode *inode)
@@ -101,6 +108,9 @@ static void fuse_free_inode(struct inode *inode)
 
 	mutex_destroy(&fi->mutex);
 	kfree(fi->forget);
+#ifdef CONFIG_FUSE_DAX
+	kfree(fi->dax);
+#endif
 	kmem_cache_free(fuse_inode_cachep, fi);
 }
 
@@ -112,6 +122,9 @@ static void fuse_evict_inode(struct inode *inode)
 	clear_inode(inode);
 	if (inode->i_sb->s_flags & SB_ACTIVE) {
 		struct fuse_conn *fc = get_fuse_conn(inode);
+
+		if (FUSE_IS_DAX(inode))
+			fuse_dax_inode_cleanup(inode);
 		fuse_queue_forget(fc, fi->forget, fi->nodeid, fi->nlookup);
 		fi->forget = NULL;
 	}

include/uapi/linux/fuse.h

@@ -895,6 +895,7 @@ struct fuse_copy_file_range_in {
 };
 
 #define FUSE_SETUPMAPPING_FLAG_WRITE (1ull << 0)
+#define FUSE_SETUPMAPPING_FLAG_READ (1ull << 1)
 struct fuse_setupmapping_in {
 	/* An already open handle */
 	uint64_t	fh;