virtiofs: add a mount option to enable dax

Add a mount option to allow using dax with virtio_fs.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

6 files changed, 151 insertions, 17 deletions

diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index 0156dc8aa646..fddd40630077 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -38,3 +38,16 @@ config VIRTIO_FS
 
 	  If you want to share files between guests or with the host, answer Y
 	  or M.
+
+config FUSE_DAX
+	bool "Virtio Filesystem Direct Host Memory Access support"
+	default y
+	depends on VIRTIO_FS
+	depends on FS_DAX
+	depends on DAX_DRIVER
+	help
+	  This allows bypassing guest page cache and allows mapping host page
+	  cache directly in guest address space.
+
+	  If you want to allow mounting a Virtio Filesystem with the "dax"
+	  option, answer Y.
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index 3e8cebfb59b7..8c7021fb2cd4 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -7,5 +7,7 @@ obj-$(CONFIG_FUSE_FS) += fuse.o
 obj-$(CONFIG_CUSE) += cuse.o
 obj-$(CONFIG_VIRTIO_FS) += virtiofs.o
 
-fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o
-virtiofs-y += virtio_fs.o
+fuse-y := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o
+fuse-$(CONFIG_FUSE_DAX) += dax.o
+
+virtiofs-y := virtio_fs.o
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
new file mode 100644
index 000000000000..9660d01f49a5
--- /dev/null
+++ b/fs/fuse/dax.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * dax: direct host memory access
+ * Copyright (C) 2020 Red Hat, Inc.
+ */
+
+#include "fuse_i.h"
+
+#include <linux/dax.h>
+
+struct fuse_conn_dax {
+	/* DAX device */
+	struct dax_device *dev;
+};
+
+void fuse_dax_conn_free(struct fuse_conn *fc)
+{
+	kfree(fc->dax);
+}
+
+int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev)
+{
+	struct fuse_conn_dax *fcd;
+
+	if (!dax_dev)
+		return 0;
+
+	fcd = kzalloc(sizeof(*fcd), GFP_KERNEL);
+	if (!fcd)
+		return -ENOMEM;
+
+	fcd->dev = dax_dev;
+
+	fc->dax = fcd;
+	return 0;
+}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 30737aabd932..97af7952373a 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -483,10 +483,14 @@ struct fuse_fs_context {
 	bool no_control:1;
 	bool no_force_umount:1;
 	bool legacy_opts_show:1;
+	bool dax:1;
 	unsigned int max_read;
 	unsigned int blksize;
 	const char *subtype;
 
+	/* DAX device, may be NULL */
+	struct dax_device *dax_dev;
+
 	/* fuse_dev pointer to fill in, should contain NULL on entry */
 	void **fudptr;
 };
@@ -755,6 +759,11 @@ struct fuse_conn {
 
 	/** List of device instances belonging to this connection */
 	struct list_head devices;
+
+#ifdef CONFIG_FUSE_DAX
+	/* Dax specific conn data, non-NULL if DAX is enabled */
+	struct fuse_conn_dax *dax;
+#endif
 };
 
 static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb)
@@ -1093,4 +1102,9 @@ unsigned int fuse_len_args(unsigned int numargs, struct fuse_arg *args);
 u64 fuse_get_unique(struct fuse_iqueue *fiq);
 void fuse_free_conn(struct fuse_conn *fc);
 
+/* dax.c */
+
+int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev);
+void fuse_dax_conn_free(struct fuse_conn *fc);
+
 #endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index bdae765b2d42..1780dfe063ab 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -587,6 +587,11 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)
 		if (sb->s_bdev && sb->s_blocksize != FUSE_DEFAULT_BLKSIZE)
 			seq_printf(m, ",blksize=%lu", sb->s_blocksize);
 	}
+#ifdef CONFIG_FUSE_DAX
+	if (fc->dax)
+		seq_puts(m, ",dax");
+#endif
+
 	return 0;
 }
 
@@ -651,6 +656,8 @@ void fuse_conn_put(struct fuse_conn *fc)
 	if (refcount_dec_and_test(&fc->count)) {
 		struct fuse_iqueue *fiq = &fc->iq;
 
+		if (IS_ENABLED(CONFIG_FUSE_DAX))
+			fuse_dax_conn_free(fc);
 		if (fiq->ops->release)
 			fiq->ops->release(fiq);
 		put_pid_ns(fc->pid_ns);
@@ -1175,11 +1182,17 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 	if (sb->s_user_ns != &init_user_ns)
 		sb->s_xattr = fuse_no_acl_xattr_handlers;
 
+	if (IS_ENABLED(CONFIG_FUSE_DAX)) {
+		err = fuse_dax_conn_alloc(fc, ctx->dax_dev);
+		if (err)
+			goto err;
+	}
+
 	if (ctx->fudptr) {
 		err = -ENOMEM;
 		fud = fuse_dev_alloc_install(fc);
 		if (!fud)
-			goto err;
+			goto err_free_dax;
 	}
 
 	fc->dev = sb->s_dev;
@@ -1234,6 +1247,9 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
  err_dev_free:
 	if (fud)
 		fuse_dev_free(fud);
+ err_free_dax:
+	if (IS_ENABLED(CONFIG_FUSE_DAX))
+		fuse_dax_conn_free(fc);
  err:
 	return err;
 }
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index f31a59f74475..e25f62276050 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -13,6 +13,7 @@
 #include <linux/virtio_fs.h>
 #include <linux/delay.h>
 #include <linux/fs_context.h>
+#include <linux/fs_parser.h>
 #include <linux/highmem.h>
 #include <linux/uio.h>
 #include "fuse_i.h"
@@ -81,6 +82,44 @@ struct virtio_fs_req_work {
 static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
 				 struct fuse_req *req, bool in_flight);
 
+enum {
+	OPT_DAX,
+};
+
+static const struct fs_parameter_spec virtio_fs_parameters[] = {
+	fsparam_flag("dax", OPT_DAX),
+	{}
+};
+
+static int virtio_fs_parse_param(struct fs_context *fc,
+				 struct fs_parameter *param)
+{
+	struct fs_parse_result result;
+	struct fuse_fs_context *ctx = fc->fs_private;
+	int opt;
+
+	opt = fs_parse(fc, virtio_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case OPT_DAX:
+		ctx->dax = 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void virtio_fs_free_fc(struct fs_context *fc)
+{
+	struct fuse_fs_context *ctx = fc->fs_private;
+
+	kfree(ctx);
+}
+
 static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq)
 {
 	struct virtio_fs *fs = vq->vdev->priv;
@@ -1219,23 +1258,27 @@ static const struct fuse_iqueue_ops virtio_fs_fiq_ops = {
 	.release			= virtio_fs_fiq_release,
 };
 
-static int virtio_fs_fill_super(struct super_block *sb)
+static inline void virtio_fs_ctx_set_defaults(struct fuse_fs_context *ctx)
+{
+	ctx->rootmode = S_IFDIR;
+	ctx->default_permissions = 1;
+	ctx->allow_other = 1;
+	ctx->max_read = UINT_MAX;
+	ctx->blksize = 512;
+	ctx->destroy = true;
+	ctx->no_control = true;
+	ctx->no_force_umount = true;
+}
+
+static int virtio_fs_fill_super(struct super_block *sb, struct fs_context *fsc)
 {
 	struct fuse_conn *fc = get_fuse_conn_super(sb);
 	struct virtio_fs *fs = fc->iq.priv;
+	struct fuse_fs_context *ctx = fsc->fs_private;
 	unsigned int i;
 	int err;
-	struct fuse_fs_context ctx = {
-		.rootmode = S_IFDIR,
-		.default_permissions = 1,
-		.allow_other = 1,
-		.max_read = UINT_MAX,
-		.blksize = 512,
-		.destroy = true,
-		.no_control = true,
-		.no_force_umount = true,
-	};
 
+	virtio_fs_ctx_set_defaults(ctx);
 	mutex_lock(&virtio_fs_mutex);
 
 	/* After holding mutex, make sure virtiofs device is still there.
@@ -1259,8 +1302,10 @@ static int virtio_fs_fill_super(struct super_block *sb)
 	}
 
 	/* virtiofs allocates and installs its own fuse devices */
-	ctx.fudptr = NULL;
-	err = fuse_fill_super_common(sb, &ctx);
+	ctx->fudptr = NULL;
+	if (ctx->dax)
+		ctx->dax_dev = fs->dax_dev;
+	err = fuse_fill_super_common(sb, ctx);
 	if (err < 0)
 		goto err_free_fuse_devs;
 
@@ -1371,7 +1416,7 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
 		return PTR_ERR(sb);
 
 	if (!sb->s_root) {
-		err = virtio_fs_fill_super(sb);
+		err = virtio_fs_fill_super(sb, fsc);
 		if (err) {
 			deactivate_locked_super(sb);
 			return err;
@@ -1386,11 +1431,19 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
 }
 
 static const struct fs_context_operations virtio_fs_context_ops = {
+	.free		= virtio_fs_free_fc,
+	.parse_param	= virtio_fs_parse_param,
 	.get_tree	= virtio_fs_get_tree,
 };
 
 static int virtio_fs_init_fs_context(struct fs_context *fsc)
 {
+	struct fuse_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct fuse_fs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	fsc->fs_private = ctx;
 	fsc->ops = &virtio_fs_context_ops;
 	return 0;
 }