virtio-fs: shared file system for virtual machines

index dd0f64f7bc06..fd8636e67ae9 100644
@@ -29,12 +29,26 @@ union fuse_dentry {
 	struct rcu_head rcu;
 };
 
-static inline void fuse_dentry_settime(struct dentry *entry, u64 time)
+static void fuse_dentry_settime(struct dentry *dentry, u64 time)
 {
-	((union fuse_dentry *) entry->d_fsdata)->time = time;
+	/*
+	 * Mess with DCACHE_OP_DELETE because dput() will be faster without it.
+	 *  Don't care about races, either way it's just an optimization
+	 */
+	if ((time && (dentry->d_flags & DCACHE_OP_DELETE)) ||
+	    (!time && !(dentry->d_flags & DCACHE_OP_DELETE))) {
+		spin_lock(&dentry->d_lock);
+		if (time)
+			dentry->d_flags &= ~DCACHE_OP_DELETE;
+		else
+			dentry->d_flags |= DCACHE_OP_DELETE;
+		spin_unlock(&dentry->d_lock);
+	}
+
+	((union fuse_dentry *) dentry->d_fsdata)->time = time;
 }
 
-static inline u64 fuse_dentry_time(struct dentry *entry)
+static inline u64 fuse_dentry_time(const struct dentry *entry)
 {
 	return ((union fuse_dentry *) entry->d_fsdata)->time;
 }

@@ -255,8 +269,14 @@ static void fuse_dentry_release(struct dentry *dentry)
 	kfree_rcu(fd, rcu);
 }
 
+static int fuse_dentry_delete(const struct dentry *dentry)
+{
+	return time_before64(fuse_dentry_time(dentry), get_jiffies_64());
+}
+
 const struct dentry_operations fuse_dentry_operations = {
 	.d_revalidate	= fuse_dentry_revalidate,
+	.d_delete	= fuse_dentry_delete,
 	.d_init		= fuse_dentry_init,
 	.d_release	= fuse_dentry_release,
 };

index 06096b60f1df..5baf07fd2876 100644
@@ -1456,14 +1456,18 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	/* Don't allow parallel writes to the same file */
 	inode_lock(inode);
 	res = generic_write_checks(iocb, from);
-	if (res > 0) {
-		if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) {
-			res = fuse_direct_IO(iocb, from);
-		} else {
-			res = fuse_direct_io(&io, from, &iocb->ki_pos,
-					     FUSE_DIO_WRITE);
-		}
+	if (res <= 0)
+		goto out;
+
+	res = file_remove_privs(iocb->ki_filp);
+	if (res)
+		goto out;
+	if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) {
+		res = fuse_direct_IO(iocb, from);
+	} else {
+		res = fuse_direct_io(&io, from, &iocb->ki_pos, FUSE_DIO_WRITE);
 	}
+out:
 	fuse_invalidate_attr(inode);
 	if (res > 0)
 		fuse_write_update_size(inode, iocb->ki_pos);

@@ -363,6 +363,8 @@ static ssize_t fuse_send_write(struct fu
 		inarg->flags |= O_DSYNC;
 	if (iocb->ki_flags & IOCB_SYNC)
 		inarg->flags |= O_SYNC;
+	if (!capable(CAP_FSETID))
+		inarg->write_flags |= FUSE_WRITE_KILL_PRIV;
 	req->inh.opcode = FUSE_WRITE;
 	req->inh.nodeid = ff->nodeid;
 	req->inh.len = req->inline_inlen + count;

@@ -125,6 +125,7 @@
  *
  *  7.29
  *  - add FUSE_NO_OPENDIR_SUPPORT flag
+ *  - add FUSE_WRITE_KILL_PRIV flag
  */
 
 #ifndef _LINUX_FUSE_H

@@ -318,9 +319,11 @@ struct fuse_file_lock {
  *
  * FUSE_WRITE_CACHE: delayed write from page cache, file handle is guessed
  * FUSE_WRITE_LOCKOWNER: lock_owner field is valid
+ * FUSE_WRITE_KILL_PRIV: kill suid and sgid bits
  */
 #define FUSE_WRITE_CACHE	(1 << 0)
 #define FUSE_WRITE_LOCKOWNER	(1 << 1)
+#define FUSE_WRITE_KILL_PRIV	(1 << 2)
 
 /**
  * Read flags

@@ -64,8 +64,11 @@ struct fuse_file_info {
 	   May only be set in ->release(). */
 	unsigned int flock_release : 1;
 
+	/* Kill suid and sgid bits on write */
+	unsigned int write_kill_priv : 1;
+
 	/** Padding.  Do not use*/
-	unsigned int padding : 27;
+	unsigned int padding : 26;
 
 	/** File handle.  May be filled in by filesystem in open().
 	    Available in all other file operations */

@@ -304,9 +304,11 @@ struct fuse_file_lock {
  *
  * FUSE_WRITE_CACHE: delayed write from page cache, file handle is guessed
  * FUSE_WRITE_LOCKOWNER: lock_owner field is valid
+ * FUSE_WRITE_KILL_PRIV: kill suid and sgid bits
  */
 #define FUSE_WRITE_CACHE	(1 << 0)
 #define FUSE_WRITE_LOCKOWNER	(1 << 1)
+#define FUSE_WRITE_KILL_PRIV	(1 << 2)
 
 /**
  * Read flags

@@ -1315,12 +1315,14 @@ static void do_write(fuse_req_t req, fus
 
 	memset(&fi, 0, sizeof(fi));
 	fi.fh = arg->fh;
-	fi.writepage = (arg->write_flags & 1) != 0;
+	fi.writepage = (arg->write_flags & FUSE_WRITE_CACHE) != 0;
+	fi.write_kill_priv = (arg->write_flags & FUSE_WRITE_KILL_PRIV) != 0;
 
 	if (req->se->conn.proto_minor < 9) {
 		param = ((char *) arg) + FUSE_COMPAT_WRITE_IN_SIZE;
 	} else {
-		fi.lock_owner = arg->lock_owner;
+		if (arg->write_flags & FUSE_WRITE_LOCKOWNER)
+			fi.lock_owner = arg->lock_owner;
 		fi.flags = arg->flags;
 		param = PARAM(arg);
 	}

@@ -1345,7 +1347,8 @@ static void do_write_buf(fuse_req_t req,
 
 	memset(&fi, 0, sizeof(fi));
 	fi.fh = arg->fh;
-	fi.writepage = arg->write_flags & 1;
+	fi.writepage = (arg->write_flags & FUSE_WRITE_CACHE) != 0;
+	fi.write_kill_priv = (arg->write_flags & FUSE_WRITE_KILL_PRIV) != 0;
 
 	if (se->conn.proto_minor < 9) {
 		bufv.buf[0].mem = ((char *) arg) + FUSE_COMPAT_WRITE_IN_SIZE;

@@ -1353,7 +1356,8 @@ static void do_write_buf(fuse_req_t req,
 			FUSE_COMPAT_WRITE_IN_SIZE;
 		assert(!(bufv.buf[0].flags & FUSE_BUF_IS_FD));
 	} else {
-		fi.lock_owner = arg->lock_owner;
+		if (arg->write_flags & FUSE_WRITE_LOCKOWNER)
+			fi.lock_owner = arg->lock_owner;
 		fi.flags = arg->flags;
 		if (!(bufv.buf[0].flags & FUSE_BUF_IS_FD))
 			bufv.buf[0].mem = PARAM(arg);

@@ -56,6 +56,7 @@
 #include <sys/file.h>
 #include <sys/xattr.h>
 #include <sys/syscall.h>
+#include <sys/capability.h>
 
 /* We are re-using pointers to our `struct lo_inode` and `struct
    lo_dirp` elements as inodes. This means that we must be able to

@@ -965,6 +966,11 @@ static void lo_write_buf(fuse_req_t req,
 	(void) ino;
 	ssize_t res;
 	struct fuse_bufvec out_buf = FUSE_BUFVEC_INIT(fuse_buf_size(in_buf));
+	struct __user_cap_header_struct cap_hdr = {
+		.version = _LINUX_CAPABILITY_VERSION_1,
+	};
+	struct __user_cap_data_struct cap_orig;
+	struct __user_cap_data_struct cap_new;
 
 	out_buf.buf[0].flags = FUSE_BUF_IS_FD | FUSE_BUF_FD_SEEK;
 	out_buf.buf[0].fd = fi->fh;

@@ -974,7 +980,28 @@ static void lo_write_buf(fuse_req_t req,
 		fprintf(stderr, "lo_write(ino=%" PRIu64 ", size=%zd, off=%lu)\n",
 			ino, out_buf.buf[0].size, (unsigned long) off);
 
+	if (fi->write_kill_priv) {
+		res = capget(&cap_hdr, &cap_orig);
+		if (res == -1) {
+			fuse_reply_err(req, errno);
+			return;
+		}
+		cap_new = cap_orig;
+		cap_new.effective &= ~(1 << CAP_FSETID);
+		res = capset(&cap_hdr, &cap_new);
+		if (res == -1) {
+			fuse_reply_err(req, errno);
+			return;
+		}
+	}
+
 	res = fuse_buf_copy(&out_buf, in_buf, 0);
+
+	if (fi->write_kill_priv) {
+		if (capset(&cap_hdr, &cap_orig) != 0)
+			abort();
+	}
+
 	if(res < 0)
 		fuse_reply_err(req, -res);
 	else

@@ -1215,7 +1242,7 @@ static void lo_copy_file_range(fuse_req_
 	res = copy_file_range(fi_in->fh, &off_in, fi_out->fh, &off_out, len,
 			      flags);
 	if (res < 0)
-		fuse_reply_err(req, -errno);
+		fuse_reply_err(req, errno);
 	else
 		fuse_reply_write(req, res);
 }

index 5baf07fd2876..e9a7aa97c539 100644
@@ -2167,6 +2167,19 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
+static ssize_t fuse_file_splice_read(struct file *in, loff_t *ppos,
+				     struct pipe_inode_info *pipe, size_t len,
+				     unsigned int flags)
+{
+	struct fuse_file *ff = in->private_data;
+
+	if (ff->open_flags & FOPEN_DIRECT_IO)
+		return default_file_splice_read(in, ppos, pipe, len, flags);
+	else
+		return generic_file_splice_read(in, ppos, pipe, len, flags);
+
+}
+
 static int convert_fuse_file_lock(struct fuse_conn *fc,
 				  const struct fuse_file_lock *ffl,
 				  struct file_lock *fl)

@@ -3174,7 +3187,7 @@ static const struct file_operations fuse_file_operations = {
 	.fsync		= fuse_fsync,
 	.lock		= fuse_file_lock,
 	.flock		= fuse_file_flock,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= fuse_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.unlocked_ioctl	= fuse_file_ioctl,
 	.compat_ioctl	= fuse_file_compat_ioctl,

index 25212dcca2df..e2e881e34935 100644
@@ -361,7 +361,7 @@ static ssize_t kernel_readv(struct file *file, const struct kvec *vec,
 	return res;
 }
 
-static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
+ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 				 struct pipe_inode_info *pipe, size_t len,
 				 unsigned int flags)
 {

@@ -425,6 +425,7 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 	iov_iter_advance(&to, copied);	/* truncates and discards */
 	return res;
 }
+EXPORT_SYMBOL(default_file_splice_read);
 
 /*
  * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'

index dd28e7679089..6804aecf7e30 100644
@@ -3055,6 +3055,8 @@ extern void block_sync_page(struct page *page);
 /* fs/splice.c */
 extern ssize_t generic_file_splice_read(struct file *, loff_t *,
 		struct pipe_inode_info *, size_t, unsigned int);
+extern ssize_t default_file_splice_read(struct file *, loff_t *,
+		struct pipe_inode_info *, size_t, unsigned int);
 extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,

index 9971a35cf1ef..46d1aecd7506 100644
@@ -427,7 +427,7 @@ static void flush_bg_queue(struct fuse_conn *fc)
  * the 'end' callback is called if given, else the reference to the
  * request is released
  */
-static void request_end(struct fuse_conn *fc, struct fuse_req *req)
+void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req)
 {
 	struct fuse_iqueue *fiq = &fc->iq;
 

@@ -480,6 +480,7 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req)
 put_request:
 	fuse_put_request(fc, req);
 }
+EXPORT_SYMBOL_GPL(fuse_request_end);
 
 static int queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
 {

@@ -567,12 +568,12 @@ static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
 		req->in.h.unique = fuse_get_unique(fiq);
 		queue_request(fiq, req);
 		/* acquire extra reference, since request is still needed
-		   after request_end() */
+		   after fuse_request_end() */
 		__fuse_get_request(req);
 		spin_unlock(&fiq->waitq.lock);
 
 		request_wait_answer(fc, req);
-		/* Pairs with smp_wmb() in request_end() */
+		/* Pairs with smp_wmb() in fuse_request_end() */
 		smp_rmb();
 	}
 }

@@ -1302,7 +1303,7 @@ __releases(fiq->waitq.lock)
  * the pending list and copies request data to userspace buffer.  If
  * no reply is needed (FORGET) or request has been aborted or there
  * was an error during the copying then it's finished by calling
- * request_end().  Otherwise add it to the processing list, and set
+ * fuse_request_end().  Otherwise add it to the processing list, and set
  * the 'sent' flag.
  */
 static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,

@@ -1362,7 +1363,7 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
 		/* SETXATTR is special, since it may contain too large data */
 		if (in->h.opcode == FUSE_SETXATTR)
 			req->out.h.error = -E2BIG;
-		request_end(fc, req);
+		fuse_request_end(fc, req);
 		goto restart;
 	}
 	spin_lock(&fpq->lock);

@@ -1405,7 +1406,7 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
 	if (!test_bit(FR_PRIVATE, &req->flags))
 		list_del_init(&req->list);
 	spin_unlock(&fpq->lock);
-	request_end(fc, req);
+	fuse_request_end(fc, req);
 	return err;
 
  err_unlock:

@@ -1913,7 +1914,7 @@ static int copy_out_args(struct fuse_copy_state *cs, struct fuse_out *out,
  * the write buffer.  The request is then searched on the processing
  * list by the unique ID found in the header.  If found, then remove
  * it from the list and copy the rest of the buffer to the request.
- * The request is finished by calling request_end()
+ * The request is finished by calling fuse_request_end().
  */
 static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 				 struct fuse_copy_state *cs, size_t nbytes)

@@ -2000,7 +2001,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 		list_del_init(&req->list);
 	spin_unlock(&fpq->lock);
 
-	request_end(fc, req);
+	fuse_request_end(fc, req);
 out:
 	return err ? err : nbytes;
 

@@ -2140,7 +2141,7 @@ static void end_requests(struct fuse_conn *fc, struct list_head *head)
 		req->out.h.error = -ECONNABORTED;
 		clear_bit(FR_SENT, &req->flags);
 		list_del_init(&req->list);
-		request_end(fc, req);
+		fuse_request_end(fc, req);
 	}
 }
 

index 0920c0c032a0..c4584c873b87 100644
@@ -949,6 +949,11 @@ ssize_t fuse_simple_request(struct fuse_conn *fc, struct fuse_args *args);
 void fuse_request_send_background(struct fuse_conn *fc, struct fuse_req *req);
 bool fuse_request_queue_background(struct fuse_conn *fc, struct fuse_req *req);
 
+/**
+ * End a finished request
+ */
+void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req);
+
 /* Abort all requests */
 void fuse_abort_conn(struct fuse_conn *fc);
 void fuse_wait_aborted(struct fuse_conn *fc);

index 46d1aecd7506..d8054b1a45f5 100644
@@ -350,7 +350,7 @@ void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
 }
 EXPORT_SYMBOL_GPL(fuse_put_request);
 
-static unsigned len_args(unsigned numargs, struct fuse_arg *args)
+unsigned fuse_len_args(unsigned numargs, struct fuse_arg *args)
 {
 	unsigned nbytes = 0;
 	unsigned i;

@@ -360,6 +360,7 @@ static unsigned len_args(unsigned numargs, struct fuse_arg *args)
 
 	return nbytes;
 }
+EXPORT_SYMBOL_GPL(fuse_len_args);
 
 static u64 fuse_get_unique(struct fuse_iqueue *fiq)
 {

@@ -375,7 +376,7 @@ static unsigned int fuse_req_hash(u64 unique)
 static void queue_request(struct fuse_iqueue *fiq, struct fuse_req *req)
 {
 	req->in.h.len = sizeof(struct fuse_in_header) +
-		len_args(req->in.numargs, (struct fuse_arg *) req->in.args);
+		fuse_len_args(req->in.numargs, (struct fuse_arg *) req->in.args);
 	list_add_tail(&req->list, &fiq->pending);
 	wake_up_locked(&fiq->waitq);
 	kill_fasync(&fiq->fasync, SIGIO, POLL_IN);

@@ -1894,7 +1895,7 @@ static int copy_out_args(struct fuse_copy_state *cs, struct fuse_out *out,
 	if (out->h.error)
 		return nbytes != reqsize ? -EINVAL : 0;
 
-	reqsize += len_args(out->numargs, out->args);
+	reqsize += fuse_len_args(out->numargs, out->args);
 
 	if (reqsize < nbytes || (reqsize > nbytes && !out->argvar))
 		return -EINVAL;

index c4584c873b87..3a235386d667 100644
@@ -1091,4 +1091,9 @@ int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type);
 /* readdir.c */
 int fuse_readdir(struct file *file, struct dir_context *ctx);
 
+/**
+ * Return the number of bytes in an arguments list
+ */
+unsigned fuse_len_args(unsigned numargs, struct fuse_arg *args);
+
 #endif /* _FS_FUSE_I_H */

index d8054b1a45f5..40eb827caa10 100644
@@ -139,6 +139,7 @@ void fuse_request_free(struct fuse_req *req)
 	fuse_req_pages_free(req);
 	kmem_cache_free(fuse_req_cachep, req);
 }
+EXPORT_SYMBOL_GPL(fuse_request_free);
 
 void __fuse_get_request(struct fuse_req *req)
 {

index 3a235386d667..16f238d7f624 100644
@@ -987,6 +987,7 @@ void fuse_conn_put(struct fuse_conn *fc);
 
 struct fuse_dev *fuse_dev_alloc(struct fuse_conn *fc);
 void fuse_dev_free(struct fuse_dev *fud);
+void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req);
 
 /**
  * Add connection to control filesystem

index ec5d9953dfb6..f02291469518 100644
@@ -958,7 +958,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 	wake_up_all(&fc->blocked_waitq);
 }
 
-static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
+void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 {
 	struct fuse_init_in *arg = &req->misc.init_in;
 

@@ -988,6 +988,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 	req->end = process_init_reply;
 	fuse_request_send_background(fc, req);
 }
+EXPORT_SYMBOL_GPL(fuse_send_init);
 
 static void fuse_free_conn(struct fuse_conn *fc)
 {

index 40eb827caa10..42fd3b576686 100644
@@ -363,11 +363,12 @@ unsigned fuse_len_args(unsigned numargs, struct fuse_arg *args)
 }
 EXPORT_SYMBOL_GPL(fuse_len_args);
 
-static u64 fuse_get_unique(struct fuse_iqueue *fiq)
+u64 fuse_get_unique(struct fuse_iqueue *fiq)
 {
 	fiq->reqctr += FUSE_REQ_ID_STEP;
 	return fiq->reqctr;
 }
+EXPORT_SYMBOL_GPL(fuse_get_unique);
 
 static unsigned int fuse_req_hash(u64 unique)
 {

index 16f238d7f624..38a572ba650d 100644
@@ -1097,4 +1097,9 @@ int fuse_readdir(struct file *file, struct dir_context *ctx);
  */
 unsigned fuse_len_args(unsigned numargs, struct fuse_arg *args);
 
+/**
+ * Get the next unique ID for a request
+ */
+u64 fuse_get_unique(struct fuse_iqueue *fiq);
+
 #endif /* _FS_FUSE_I_H */

index 38a572ba650d..84f094e4ac36 100644
@@ -56,6 +56,25 @@ extern struct mutex fuse_mutex;
 extern unsigned max_user_bgreq;
 extern unsigned max_user_congthresh;
 
+/** Mount options */
+struct fuse_mount_data {
+	int fd;
+	unsigned rootmode;
+	kuid_t user_id;
+	kgid_t group_id;
+	unsigned fd_present:1;
+	unsigned rootmode_present:1;
+	unsigned user_id_present:1;
+	unsigned group_id_present:1;
+	unsigned default_permissions:1;
+	unsigned allow_other:1;
+	unsigned max_read;
+	unsigned blksize;
+
+	/* fuse_dev pointer to fill in, should contain NULL on entry */
+	void **fudptr;
+};
+
 /* One forget request */
 struct fuse_forget_link {
 	struct fuse_forget_one forget_one;

@@ -989,6 +1008,20 @@ struct fuse_dev *fuse_dev_alloc(struct fuse_conn *fc);
 void fuse_dev_free(struct fuse_dev *fud);
 void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req);
 
+/**
+ * Parse a mount options string
+ */
+int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev,
+				struct user_namespace *user_ns);
+
+/**
+ * Fill in superblock and initialize fuse connection
+ * @sb: partially-initialized superblock to fill in
+ * @mount_data: mount parameters
+ */
+int fuse_fill_super_common(struct super_block *sb,
+			   struct fuse_mount_data *mount_data);
+
 /**
  * Add connection to control filesystem
  */

235 lines not on this page · raw message

index 55a26f351467..a6ed7a036b50 100644
@@ -504,7 +504,7 @@ static int cuse_channel_open(struct inode *inode, struct file *file)
 	 * Limit the cuse channel to requests that can
 	 * be represented in file->f_cred->user_ns.
 	 */
-	fuse_conn_init(&cc->fc, file->f_cred->user_ns);
+	fuse_conn_init(&cc->fc, file->f_cred->user_ns, &fuse_dev_fiq_ops, NULL);
 
 	fud = fuse_dev_alloc(&cc->fc);
 	if (!fud) {

98 lines not on this page · raw message

72 lines not on this page · raw message

index baf2966a753a..126e77854dac 100644
@@ -570,7 +570,9 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
-static void fuse_iqueue_init(struct fuse_iqueue *fiq)
+static void fuse_iqueue_init(struct fuse_iqueue *fiq,
+			     const struct fuse_iqueue_ops *ops,
+			     void *priv)
 {
 	memset(fiq, 0, sizeof(struct fuse_iqueue));
 	init_waitqueue_head(&fiq->waitq);

@@ -578,6 +580,8 @@ static void fuse_iqueue_init(struct fuse_iqueue *fiq)
 	INIT_LIST_HEAD(&fiq->interrupts);
 	fiq->forget_list_tail = &fiq->forget_list_head;
 	fiq->connected = 1;
+	fiq->ops = ops;
+	fiq->priv = priv;
 }
 
 static void fuse_pqueue_init(struct fuse_pqueue *fpq)

@@ -591,7 +595,8 @@ static void fuse_pqueue_init(struct fuse_pqueue *fpq)
 	fpq->connected = 1;
 }
 
-void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns)
+void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns,
+		    const struct fuse_iqueue_ops *fiq_ops, void *fiq_priv)
 {
 	memset(fc, 0, sizeof(*fc));
 	spin_lock_init(&fc->lock);

@@ -601,7 +606,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns)
 	atomic_set(&fc->dev_count, 1);
 	init_waitqueue_head(&fc->blocked_waitq);
 	init_waitqueue_head(&fc->reserved_req_waitq);
-	fuse_iqueue_init(&fc->iq);
+	fuse_iqueue_init(&fc->iq, fiq_ops, fiq_priv);
 	INIT_LIST_HEAD(&fc->bg_queue);
 	INIT_LIST_HEAD(&fc->entry);
 	INIT_LIST_HEAD(&fc->devices);

@@ -1113,7 +1118,8 @@ int fuse_fill_super_common(struct super_block *sb,
 	if (!fc)
 		goto err;
 
-	fuse_conn_init(fc, sb->s_user_ns);
+	fuse_conn_init(fc, sb->s_user_ns, mount_data->fiq_ops,
+		       mount_data->fiq_priv);
 	fc->release = fuse_free_conn;
 
 	fud = fuse_dev_alloc(fc);

@@ -1215,6 +1221,8 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 		goto err_fput;
 	__set_bit(FR_BACKGROUND, &init_req->flags);
 
+	d.fiq_ops = &fuse_dev_fiq_ops;
+	d.fiq_priv = NULL;
 	d.fudptr = &file->private_data;
 	err = fuse_fill_super_common(sb, &d);
 	if (err < 0)

index a6ed7a036b50..a509747153a7 100644
@@ -506,7 +506,7 @@ static int cuse_channel_open(struct inode *inode, struct file *file)
 	 */
 	fuse_conn_init(&cc->fc, file->f_cred->user_ns, &fuse_dev_fiq_ops, NULL);
 
-	fud = fuse_dev_alloc(&cc->fc);
+	fud = fuse_dev_alloc_install(&cc->fc);
 	if (!fud) {
 		kfree(cc);
 		return -ENOMEM;

index ef489beadf58..ee9dd38bc0f0 100644
@@ -2318,7 +2318,7 @@ static int fuse_device_clone(struct fuse_conn *fc, struct file *new)
 	if (new->private_data)
 		return -EINVAL;
 
-	fud = fuse_dev_alloc(fc);
+	fud = fuse_dev_alloc_install(fc);
 	if (!fud)
 		return -ENOMEM;
 

index 0b578e07156d..4008ed65a48d 100644
@@ -1050,7 +1050,9 @@ void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns,
  */
 void fuse_conn_put(struct fuse_conn *fc);
 
-struct fuse_dev *fuse_dev_alloc(struct fuse_conn *fc);
+struct fuse_dev *fuse_dev_alloc_install(struct fuse_conn *fc);
+struct fuse_dev *fuse_dev_alloc(void);
+void fuse_dev_install(struct fuse_dev *fud, struct fuse_conn *fc);
 void fuse_dev_free(struct fuse_dev *fud);
 void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req);
 

index 126e77854dac..9b0114437a14 100644
@@ -1027,8 +1027,7 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 	return 0;
 }
 
-struct fuse_dev *fuse_dev_alloc(struct fuse_conn *fc)
-{
+struct fuse_dev *fuse_dev_alloc(void) {
 	struct fuse_dev *fud;
 	struct list_head *pq;
 

@@ -1043,16 +1042,32 @@ struct fuse_dev *fuse_dev_alloc(struct fuse_conn *fc)
 	}
 
 	fud->pq.processing = pq;
-	fud->fc = fuse_conn_get(fc);
 	fuse_pqueue_init(&fud->pq);
 
+	return fud;
+}
+EXPORT_SYMBOL_GPL(fuse_dev_alloc);
+
+void fuse_dev_install(struct fuse_dev *fud, struct fuse_conn *fc) {
+	fud->fc = fuse_conn_get(fc);
 	spin_lock(&fc->lock);
 	list_add_tail(&fud->entry, &fc->devices);
 	spin_unlock(&fc->lock);
+}
+EXPORT_SYMBOL_GPL(fuse_dev_install);
 
+struct fuse_dev *fuse_dev_alloc_install(struct fuse_conn *fc)
+{
+	struct fuse_dev *fud;
+
+	fud = fuse_dev_alloc();
+	if (!fud)
+		return NULL;
+
+	fuse_dev_install(fud, fc);
 	return fud;
 }
-EXPORT_SYMBOL_GPL(fuse_dev_alloc);
+EXPORT_SYMBOL_GPL(fuse_dev_alloc_install);
 
 void fuse_dev_free(struct fuse_dev *fud)
 {

@@ -1122,7 +1137,7 @@ int fuse_fill_super_common(struct super_block *sb,
 		       mount_data->fiq_priv);
 	fc->release = fuse_free_conn;
 
-	fud = fuse_dev_alloc(fc);
+	fud = fuse_dev_alloc_install(fc);
 	if (!fud)
 		goto err_put_conn;
 

index 4008ed65a48d..f5cb4d40b83f 100644
@@ -59,15 +59,18 @@ extern unsigned max_user_congthresh;
 /** Mount options */
 struct fuse_mount_data {
 	int fd;
+	const char *tag; /* lifetime: .fill_super() data argument */
 	unsigned rootmode;
 	kuid_t user_id;
 	kgid_t group_id;
 	unsigned fd_present:1;
+	unsigned tag_present:1;
 	unsigned rootmode_present:1;
 	unsigned user_id_present:1;
 	unsigned group_id_present:1;
 	unsigned default_permissions:1;
 	unsigned allow_other:1;
+	unsigned destroy:1;
 	unsigned max_read;
 	unsigned blksize;
 

@@ -465,6 +468,9 @@ struct fuse_req {
 
 	/** Request is stolen from fuse_file->reserved_req */
 	struct file *stolen_file;
+
+	/** virtio-fs's physically contiguous buffer for in and out args */
+	void *argbuf;
 };
 
 struct fuse_iqueue;

@@ -1070,6 +1076,13 @@ int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev,
 int fuse_fill_super_common(struct super_block *sb,
 			   struct fuse_mount_data *mount_data);
 
+/**
+ * Disassociate fuse connection from superblock and kill the superblock
+ *
+ * Calls kill_anon_super(), use with do not use with bdev mounts.
+ */
+void fuse_kill_sb_anon(struct super_block *sb);
+
 /**
  * Add connection to control filesystem
  */

index 9b0114437a14..731a8a74d032 100644
@@ -434,6 +434,7 @@ static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 enum {
 	OPT_FD,
+	OPT_TAG,
 	OPT_ROOTMODE,
 	OPT_USER_ID,
 	OPT_GROUP_ID,

@@ -446,6 +447,7 @@ enum {
 
 static const match_table_t tokens = {
 	{OPT_FD,			"fd=%u"},
+	{OPT_TAG,			"tag=%s"},
 	{OPT_ROOTMODE,			"rootmode=%o"},
 	{OPT_USER_ID,			"user_id=%u"},
 	{OPT_GROUP_ID,			"group_id=%u"},

@@ -492,6 +494,11 @@ int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev,
 			d->fd_present = 1;
 			break;
 
+		case OPT_TAG:
+			d->tag = args[0].from;
+			d->tag_present = 1;
+			break;
+
 		case OPT_ROOTMODE:
 			if (match_octal(&args[0], &value))
 				return 0;

@@ -1170,7 +1177,7 @@ int fuse_fill_super_common(struct super_block *sb,
 	/* Root dentry doesn't have .d_revalidate */
 	sb->s_d_op = &fuse_dentry_operations;
 
-	if (is_bdev) {
+	if (mount_data->destroy) {
 		fc->destroy_req = fuse_request_alloc(0);
 		if (!fc->destroy_req)
 			goto err_put_root;

@@ -1216,7 +1223,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	err = -EINVAL;
 	if (!parse_fuse_opt(data, &d, is_bdev, sb->s_user_ns))
 		goto err;
-	if (!d.fd_present)
+	if (!d.fd_present || d.tag_present)
 		goto err;
 
 	file = fget(d.fd);

@@ -1239,6 +1246,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	d.fiq_ops = &fuse_dev_fiq_ops;
 	d.fiq_priv = NULL;
 	d.fudptr = &file->private_data;
+	d.destroy = is_bdev;
 	err = fuse_fill_super_common(sb, &d);
 	if (err < 0)
 		goto err_free_init_req;

@@ -1282,11 +1290,12 @@ static void fuse_sb_destroy(struct super_block *sb)
 	}
 }
 
-static void fuse_kill_sb_anon(struct super_block *sb)
+void fuse_kill_sb_anon(struct super_block *sb)
 {
 	fuse_sb_destroy(sb);
 	kill_anon_super(sb);
 }
+EXPORT_SYMBOL_GPL(fuse_kill_sb_anon);
 
 static struct file_system_type fuse_fs_type = {
 	.owner		= THIS_MODULE,

956 lines not on this page · raw message

41 lines not on this page · raw message

index 6d5c3b2d4f4d..884b0e2734bb 100644
@@ -43,5 +43,6 @@
 #define VIRTIO_ID_INPUT        18 /* virtio input */
 #define VIRTIO_ID_VSOCK        19 /* virtio vsock transport */
 #define VIRTIO_ID_CRYPTO       20 /* virtio crypto */
+#define VIRTIO_ID_FS           26 /* virtio filesystem */
 
 #endif /* _LINUX_VIRTIO_IDS_H */

index 0a339b85133e..cb44ec663991 100644
@@ -53,7 +53,8 @@ EXPORT_SYMBOL_GPL(dax_read_unlock);
 int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
 		pgoff_t *pgoff)
 {
-	phys_addr_t phys_off = (get_start_sect(bdev) + sector) * 512;
+	sector_t start_sect = bdev ? get_start_sect(bdev) : 0;
+	phys_addr_t phys_off = (start_sect + sector) * 512;
 
 	if (pgoff)
 		*pgoff = PHYS_PFN(phys_off);

index e5e54da1715f..815bc32fd967 100644
@@ -1042,7 +1042,12 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
 static bool dax_range_is_aligned(struct block_device *bdev,
 				 unsigned int offset, unsigned int length)
 {
-	unsigned short sector_size = bdev_logical_block_size(bdev);
+	unsigned short sector_size;
+
+	if (!bdev)
+		return false;
+
+	sector_size = bdev_logical_block_size(bdev);
 
 	if (!IS_ALIGNED(offset, sector_size))
 		return false;

index 815bc32fd967..c944c1efc78f 100644
@@ -932,12 +932,12 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
  * on persistent storage prior to completion of the operation.
  */
 int dax_writeback_mapping_range(struct address_space *mapping,
-		struct block_device *bdev, struct writeback_control *wbc)
+		struct block_device *bdev, struct dax_device *dax_dev,
+		struct writeback_control *wbc)
 {
 	XA_STATE(xas, &mapping->i_pages, wbc->range_start >> PAGE_SHIFT);
 	struct inode *inode = mapping->host;
 	pgoff_t end_index = wbc->range_end >> PAGE_SHIFT;
-	struct dax_device *dax_dev;
 	void *entry;
 	int ret = 0;
 	unsigned int scanned = 0;

@@ -948,9 +948,12 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 	if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
 		return 0;
 
-	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
-	if (!dax_dev)
-		return -EIO;
+	if (bdev) {
+		WARN_ON(dax_dev);
+		dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+		if (!dax_dev)
+			return -EIO;
+	}
 
 	trace_dax_writeback_range(inode, xas.xa_index, end_index);
 

@@ -972,7 +975,8 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 		xas_lock_irq(&xas);
 	}
 	xas_unlock_irq(&xas);
-	put_dax(dax_dev);
+	if (bdev)
+		put_dax(dax_dev);
 	trace_dax_writeback_range_done(inode, xas.xa_index, end_index);
 	return ret;
 }

index c27c27300d95..9b0131c53429 100644
@@ -956,7 +956,7 @@ static int
 ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	return dax_writeback_mapping_range(mapping,
-			mapping->host->i_sb->s_bdev, wbc);
+			mapping->host->i_sb->s_bdev, NULL, wbc);
 }
 
 const struct address_space_operations ext2_aops = {

index b32a57bc5d5d..cb8cf5eddd9b 100644
@@ -2972,7 +2972,7 @@ static int ext4_dax_writepages(struct address_space *mapping,
 	percpu_down_read(&sbi->s_journal_flag_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
-	ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc);
+	ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, NULL, wbc);
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
 	percpu_up_read(&sbi->s_journal_flag_rwsem);

index 3619e9e8d359..27f71ff55096 100644
@@ -994,7 +994,7 @@ xfs_dax_writepages(
 {
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
 	return dax_writeback_mapping_range(mapping,
-			xfs_find_bdev_for_inode(mapping->host), wbc);
+			xfs_find_bdev_for_inode(mapping->host), NULL, wbc);
 }
 
 STATIC int

index 0dd316a74a29..bf3b00b5f0bf 100644
@@ -87,7 +87,8 @@ static inline void fs_put_dax(struct dax_device *dax_dev)
 
 struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
 int dax_writeback_mapping_range(struct address_space *mapping,
-		struct block_device *bdev, struct writeback_control *wbc);
+		struct block_device *bdev, struct dax_device *dax_dev,
+		struct writeback_control *wbc);
 
 struct page *dax_layout_busy_page(struct address_space *mapping);
 dax_entry_t dax_lock_page(struct page *page);

@@ -119,7 +120,8 @@ static inline struct page *dax_layout_busy_page(struct address_space *mapping)
 }
 
 static inline int dax_writeback_mapping_range(struct address_space *mapping,
-		struct block_device *bdev, struct writeback_control *wbc)
+		struct block_device *bdev, struct dax_device *dax_dev,
+		struct writeback_control *wbc)
 {
 	return -EOPNOTSUPP;
 }

index bb4cc4910750..c859f000a751 100644
@@ -10,6 +10,11 @@
 
 struct irq_affinity;
 
+struct virtio_shm_region {
+       u64 addr;
+       u64 len;
+};
+
 /**
  * virtio_config_ops - operations for configuring a virtio device
  * Note: Do not assume that a transport implements all of the operations

@@ -65,6 +70,7 @@ struct irq_affinity;
  *      the caller can then copy.
  * @set_vq_affinity: set the affinity for a virtqueue (optional).
  * @get_vq_affinity: get the affinity for a virtqueue (optional).
+ * @get_shm_region: get a shared memory region based on the index.
  */
 typedef void vq_callback_t(struct virtqueue *);
 struct virtio_config_ops {

@@ -88,6 +94,8 @@ struct virtio_config_ops {
 			       const struct cpumask *cpu_mask);
 	const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev,
 			int index);
+	bool (*get_shm_region)(struct virtio_device *vdev,
+			       struct virtio_shm_region *region, u8 id);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */

@@ -250,6 +258,15 @@ int virtqueue_set_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask)
 	return 0;
 }
 
+static inline
+bool virtio_get_shm_region(struct virtio_device *vdev,
+                         struct virtio_shm_region *region, u8 id)
+{
+	if (!vdev->config->get_shm_region)
+		return false;
+	return vdev->config->get_shm_region(vdev, region, id);
+}
+
 static inline bool virtio_is_little_endian(struct virtio_device *vdev)
 {
 	return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||

index 07571daccfec..51c9e6eca5ac 100644
@@ -446,6 +446,112 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	vring_del_virtqueue(vq);
 }
 
+static int virtio_pci_find_shm_cap(struct pci_dev *dev,
+                                   u8 required_id,
+                                   u8 *bar, u64 *offset, u64 *len)
+{
+	int pos;
+
+        for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
+             pos > 0;
+             pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
+		u8 type, cap_len, id;
+                u32 tmp32;
+                u64 res_offset, res_length;
+
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+                                                         cfg_type),
+                                     &type);
+                if (type != VIRTIO_PCI_CAP_SHARED_MEMORY_CFG)
+                        continue;
+
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+                                                         cap_len),
+                                     &cap_len);
+                if (cap_len != sizeof(struct virtio_pci_shm_cap)) {
+		        printk(KERN_ERR "%s: shm cap with bad size offset: %d size: %d\n",
+                               __func__, pos, cap_len);
+                        continue;
+                };
+
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_shm_cap,
+                                                         id),
+                                     &id);
+                if (id != required_id)
+                        continue;
+
+                /* Type, and ID match, looks good */
+                pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+                                                         bar),
+                                     bar);
+
+                /* Read the lower 32bit of length and offset */
+                pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap, offset),
+                                      &tmp32);
+                res_offset = tmp32;
+                pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap, length),
+                                      &tmp32);
+                res_length = tmp32;
+
+                /* and now the top half */
+                pci_read_config_dword(dev,
+                                      pos + offsetof(struct virtio_pci_shm_cap,
+                                                     offset_hi),
+                                      &tmp32);
+                res_offset |= ((u64)tmp32) << 32;
+                pci_read_config_dword(dev,
+                                      pos + offsetof(struct virtio_pci_shm_cap,
+                                                     length_hi),
+                                      &tmp32);
+                res_length |= ((u64)tmp32) << 32;
+
+                *offset = res_offset;
+                *len = res_length;
+
+                return pos;
+        }
+        return 0;
+}
+
+static bool vp_get_shm_region(struct virtio_device *vdev,
+			      struct virtio_shm_region *region, u8 id)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct pci_dev *pci_dev = vp_dev->pci_dev;
+	u8 bar;
+	u64 offset, len;
+	phys_addr_t phys_addr;
+	size_t bar_len;
+	char *bar_name;
+	int ret;
+
+	if (!virtio_pci_find_shm_cap(pci_dev, id, &bar, &offset, &len)) {
+		return false;
+	}
+
+	ret = pci_request_region(pci_dev, bar, "virtio-pci-shm");
+	if (ret < 0) {
+		dev_err(&pci_dev->dev, "%s: failed to request BAR\n",
+			__func__);
+		return false;
+	}
+
+	phys_addr = pci_resource_start(pci_dev, bar);
+	bar_len = pci_resource_len(pci_dev, bar);
+
+        if (offset + len > bar_len) {
+                dev_err(&pci_dev->dev,
+                        "%s: bar shorter than cap offset+len\n",
+                        __func__);
+                return false;
+        }
+
+	region->len = len;
+	region->addr = (u64) phys_addr + offset;
+
+	return true;
+}
+
 static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get		= NULL,
 	.set		= NULL,

@@ -460,6 +566,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
 	.get_vq_affinity = vp_get_vq_affinity,
+	.get_shm_region  = vp_get_shm_region,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {

@@ -476,6 +583,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
 	.get_vq_affinity = vp_get_vq_affinity,
+	.get_shm_region  = vp_get_shm_region,
 };
 
 /**

index 90007a1abcab..31841a60a4ad 100644
@@ -113,6 +113,8 @@
 #define VIRTIO_PCI_CAP_DEVICE_CFG	4
 /* PCI configuration access */
 #define VIRTIO_PCI_CAP_PCI_CFG		5
+/* Additional shared memory capability */
+#define VIRTIO_PCI_CAP_SHARED_MEMORY_CFG 8
 
 /* This is the PCI capability header: */
 struct virtio_pci_cap {

@@ -163,6 +165,14 @@ struct virtio_pci_cfg_cap {
 	__u8 pci_cfg_data[4]; /* Data for BAR access. */
 };
 
+/* Fields in VIRTIO_PCI_CAP_SHARED_MEMORY_CFG */
+struct virtio_pci_shm_cap {
+       struct virtio_pci_cap cap;
+       __le32 offset_hi;             /* Most sig 32 bits of offset */
+       __le32 length_hi;             /* Most sig 32 bits of length */
+        __u8   id;                    /* To distinguish shm chunks */
+};
+
 /* Macro versions of offsets for the Old Timers! */
 #define VIRTIO_PCI_CAP_VNDR		0
 #define VIRTIO_PCI_CAP_NEXT		1

index d9dd0f789279..ac42520abd86 100644
@@ -499,6 +499,37 @@ static const char *vm_bus_name(struct virtio_device *vdev)
 	return vm_dev->pdev->name;
 }
 
+static bool vm_get_shm_region(struct virtio_device *vdev,
+			      struct virtio_shm_region *region, u8 id)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	u64 len, addr;
+
+	/* Select the region we're interested in */
+	writel(id, vm_dev->base + VIRTIO_MMIO_SHM_SEL);
+
+	/* Read the region size */
+	len = (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_LEN_LOW);
+	len |= (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_LEN_HIGH) << 32;
+
+	region->len = len;
+
+	/* Check if region length is -1. If that's the case, the shared memory
+	 * region does not exist and there is no need to proceed further.
+	 */
+	if (len == ~(u64)0) {
+		return false;
+	}
+
+	/* Read the region base address */
+	addr = (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_BASE_LOW);
+	addr |= (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_BASE_HIGH) << 32;
+
+	region->addr = addr;
+
+	return true;
+}
+
 static const struct virtio_config_ops virtio_mmio_config_ops = {
 	.get		= vm_get,
 	.set		= vm_set,

@@ -511,6 +542,7 @@ static const struct virtio_config_ops virtio_mmio_config_ops = {
 	.get_features	= vm_get_features,
 	.finalize_features = vm_finalize_features,
 	.bus_name	= vm_bus_name,
+	.get_shm_region = vm_get_shm_region,
 };
 
 

index c4b09689ab64..0650f91bea6c 100644
@@ -122,6 +122,17 @@
 #define VIRTIO_MMIO_QUEUE_USED_LOW	0x0a0
 #define VIRTIO_MMIO_QUEUE_USED_HIGH	0x0a4
 
+/* Shared memory region id */
+#define VIRTIO_MMIO_SHM_SEL             0x0ac
+
+/* Shared memory region length, 64 bits in two halves */
+#define VIRTIO_MMIO_SHM_LEN_LOW         0x0b0
+#define VIRTIO_MMIO_SHM_LEN_HIGH        0x0b4
+
+/* Shared memory region base address, 64 bits in two halves */
+#define VIRTIO_MMIO_SHM_BASE_LOW        0x0b8
+#define VIRTIO_MMIO_SHM_BASE_HIGH       0x0bc
+
 /* Configuration atomicity value */
 #define VIRTIO_MMIO_CONFIG_GENERATION	0x0fc
 

index a509747153a7..417448f11f9f 100644
@@ -504,7 +504,8 @@ static int cuse_channel_open(struct inode *inode, struct file *file)
 	 * Limit the cuse channel to requests that can
 	 * be represented in file->f_cred->user_ns.
 	 */
-	fuse_conn_init(&cc->fc, file->f_cred->user_ns, &fuse_dev_fiq_ops, NULL);
+	fuse_conn_init(&cc->fc, file->f_cred->user_ns, NULL, &fuse_dev_fiq_ops,
+					NULL);
 
 	fud = fuse_dev_alloc_install(&cc->fc);
 	if (!fud) {

index f5cb4d40b83f..46fc1a454084 100644
@@ -74,6 +74,9 @@ struct fuse_mount_data {
 	unsigned max_read;
 	unsigned blksize;
 
+	/* DAX device, may be NULL */
+	struct dax_device *dax_dev;
+
 	/* fuse input queue operations */
 	const struct fuse_iqueue_ops *fiq_ops;
 

@@ -822,6 +825,9 @@ struct fuse_conn {
 
 	/** List of device instances belonging to this connection */
 	struct list_head devices;
+
+	/** DAX device, non-NULL if DAX is supported */
+	struct dax_device *dax_dev;
 };
 
 static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb)

@@ -1049,7 +1055,8 @@ struct fuse_conn *fuse_conn_get(struct fuse_conn *fc);
  * Initialize fuse_conn
  */
 void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns,
-		    const struct fuse_iqueue_ops *fiq_ops, void *fiq_priv);
+			struct dax_device *dax_dev,
+			const struct fuse_iqueue_ops *fiq_ops, void *fiq_priv);
 
 /**
  * Release reference to fuse_conn

index 731a8a74d032..42f3ac5b7521 100644
@@ -603,7 +603,8 @@ static void fuse_pqueue_init(struct fuse_pqueue *fpq)
 }
 
 void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns,
-		    const struct fuse_iqueue_ops *fiq_ops, void *fiq_priv)
+			struct dax_device *dax_dev,
+			const struct fuse_iqueue_ops *fiq_ops, void *fiq_priv)
 {
 	memset(fc, 0, sizeof(*fc));
 	spin_lock_init(&fc->lock);

@@ -628,6 +629,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns,
 	atomic64_set(&fc->attr_version, 1);
 	get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
 	fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
+	fc->dax_dev = dax_dev;
 	fc->user_ns = get_user_ns(user_ns);
 	fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
 }

@@ -1140,8 +1142,8 @@ int fuse_fill_super_common(struct super_block *sb,
 	if (!fc)
 		goto err;
 
-	fuse_conn_init(fc, sb->s_user_ns, mount_data->fiq_ops,
-		       mount_data->fiq_priv);
+	fuse_conn_init(fc, sb->s_user_ns, mount_data->dax_dev,
+		       mount_data->fiq_ops, mount_data->fiq_priv);
 	fc->release = fuse_free_conn;
 
 	fud = fuse_dev_alloc_install(fc);

@@ -1243,6 +1245,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 		goto err_fput;
 	__set_bit(FR_BACKGROUND, &init_req->flags);
 
+	d.dax_dev = NULL;
 	d.fiq_ops = &fuse_dev_fiq_ops;
 	d.fiq_priv = NULL;
 	d.fudptr = &file->private_data;

index e76e0f5dce40..a23a1fb67217 100644
@@ -866,6 +866,7 @@ static int virtio_fs_fill_super(struct super_block *sb, void *data,
  		goto err_free_fuse_devs;
 	__set_bit(FR_BACKGROUND, &init_req->flags);
 
+	d.dax_dev = NULL;
 	d.fiq_ops = &virtio_fs_fiq_ops;
 	d.fiq_priv = fs;
 	d.fudptr = (void **)&fs->vqs[VQ_REQUEST].fud;

index 46fc1a454084..840c88af711c 100644
@@ -70,6 +70,7 @@ struct fuse_mount_data {
 	unsigned group_id_present:1;
 	unsigned default_permissions:1;
 	unsigned allow_other:1;
+	unsigned dax:1;
 	unsigned destroy:1;
 	unsigned max_read;
 	unsigned blksize;

index 42f3ac5b7521..97d218a7daa8 100644
@@ -442,6 +442,7 @@ enum {
 	OPT_ALLOW_OTHER,
 	OPT_MAX_READ,
 	OPT_BLKSIZE,
+	OPT_DAX,
 	OPT_ERR
 };
 

@@ -455,6 +456,7 @@ static const match_table_t tokens = {
 	{OPT_ALLOW_OTHER,		"allow_other"},
 	{OPT_MAX_READ,			"max_read=%u"},
 	{OPT_BLKSIZE,			"blksize=%u"},
+	{OPT_DAX,			"dax"},
 	{OPT_ERR,			NULL}
 };
 

@@ -546,6 +548,10 @@ int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev,
 			d->blksize = value;
 			break;
 
+		case OPT_DAX:
+			d->dax = 1;
+			break;
+
 		default:
 			return 0;
 		}

@@ -574,6 +580,8 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)
 		seq_printf(m, ",max_read=%u", fc->max_read);
 	if (sb->s_bdev && sb->s_blocksize != FUSE_DEFAULT_BLKSIZE)
 		seq_printf(m, ",blksize=%lu", sb->s_blocksize);
+	if (fc->dax_dev)
+		seq_printf(m, ",dax");
 	return 0;
 }
 

215 lines not on this page · raw message

index 48f3590dcfbe..d4bb549568eb 100644
@@ -38,4 +38,7 @@ struct virtio_fs_config {
 	__u32 num_queues;
 } __attribute__((packed));
 
+/* For the id field in virtio_pci_shm_cap */
+#define VIRTIO_FS_SHMCAP_ID_CACHE 0
+
 #endif /* _UAPI_LINUX_VIRTIO_FS_H */

index 840c88af711c..5439e4628362 100644
@@ -46,6 +46,10 @@
 /** Number of page pointers embedded in fuse_req */
 #define FUSE_REQ_INLINE_PAGES 1
 
+/* Default memory range size, 2MB */
+#define FUSE_DAX_MEM_RANGE_SZ	(2*1024*1024)
+#define FUSE_DAX_MEM_RANGE_PAGES	(FUSE_DAX_MEM_RANGE_SZ/PAGE_SIZE)
+
 /** List of active connections */
 extern struct list_head fuse_conn_list;
 

@@ -94,6 +98,18 @@ struct fuse_forget_link {
 	struct fuse_forget_link *next;
 };
 
+/** Translation information for file offsets to DAX window offsets */
+struct fuse_dax_mapping {
+	/* Will connect in fc->free_ranges to keep track of free memory */
+	struct list_head list;
+
+       /** Position in DAX window */
+       u64 window_offset;
+
+       /** Length of mapping, in bytes */
+       loff_t length;
+};
+
 /** FUSE inode */
 struct fuse_inode {
 	/** Inode data */

@@ -829,6 +845,13 @@ struct fuse_conn {
 
 	/** DAX device, non-NULL if DAX is supported */
 	struct dax_device *dax_dev;
+
+	/*
+	 * DAX Window Free Ranges. TODO: This might not be best place to store
+	 * this free list
+	 */
+	long nr_free_ranges;
+	struct list_head free_ranges;
 };
 
 static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb)

122 lines not on this page · raw message

index 2b790865dc21..76c46edcc8ac 100644
@@ -453,6 +453,8 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	phys_addr_t offset = PFN_PHYS(pgoff);
 	size_t max_nr_pages = fs->window_len/PAGE_SIZE - pgoff;
 
+	pr_debug("virtio_fs_direct_access(): called. nr_pages=%ld max_nr_pages=%zu\n", nr_pages, max_nr_pages);
+
 	if (kaddr)
 		*kaddr = fs->window_kaddr + offset;
 	if (pfn)

index 2ac598614a8f..9eb313220549 100644
@@ -399,6 +399,8 @@ enum fuse_opcode {
 	FUSE_RENAME2		= 45,
 	FUSE_LSEEK		= 46,
 	FUSE_COPY_FILE_RANGE	= 47,
+	FUSE_SETUPMAPPING       = 48,
+	FUSE_REMOVEMAPPING      = 49,
 
 	/* CUSE specific operations */
 	CUSE_INIT		= 4096,

@@ -822,4 +824,35 @@ struct fuse_copy_file_range_in {
 	uint64_t	flags;
 };
 
+#define FUSE_SETUPMAPPING_ENTRIES 8
+#define FUSE_SETUPMAPPING_FLAG_WRITE (1ull << 0)
+struct fuse_setupmapping_in {
+	/* An already open handle */
+	uint64_t	fh;
+	/* Offset into the file to start the mapping */
+	uint64_t	foffset;
+	/* Length of mapping required */
+	uint64_t	len;
+	/* Flags, FUSE_SETUPMAPPING_FLAG_* */
+	uint64_t	flags;
+	/* Offset in Memory Window */
+	uint64_t	moffset;
+};
+
+struct fuse_setupmapping_out {
+	/* Offsets into the cache of mappings */
+	uint64_t	coffset[FUSE_SETUPMAPPING_ENTRIES];
+        /* Lengths of each mapping */
+        uint64_t	len[FUSE_SETUPMAPPING_ENTRIES];
+};
+
+struct fuse_removemapping_in {
+        /* An already open handle */
+        uint64_t	fh;
+	/* Offset into the dax window start the unmapping */
+	uint64_t        moffset;
+        /* Length of mapping required */
+        uint64_t	len;
+};
+
 #endif /* _LINUX_FUSE_H */

index e9a7aa97c539..edbb11ca735e 100644
@@ -18,6 +18,12 @@
 #include <linux/swap.h>
 #include <linux/falloc.h>
 #include <linux/uio.h>
+#include <linux/dax.h>
+#include <linux/iomap.h>
+#include <linux/interval_tree_generic.h>
+
+INTERVAL_TREE_DEFINE(struct fuse_dax_mapping, rb, __u64, __subtree_last,
+                     START, LAST, static inline, fuse_dax_interval_tree);
 
 static int fuse_send_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
 			  int opcode, struct fuse_open_out *outargp)

@@ -171,6 +177,173 @@ static void fuse_link_write_file(struct file *file)
 	spin_unlock(&fi->lock);
 }
 
+static struct fuse_dax_mapping *alloc_dax_mapping(struct fuse_conn *fc)
+{
+	struct fuse_dax_mapping *dmap = NULL;
+
+	spin_lock(&fc->lock);
+
+	/* TODO: Add logic to try to free up memory if wait is allowed */
+	if (fc->nr_free_ranges <= 0) {
+		spin_unlock(&fc->lock);
+		return NULL;
+	}
+
+	WARN_ON(list_empty(&fc->free_ranges));
+
+	/* Take a free range */
+	dmap = list_first_entry(&fc->free_ranges, struct fuse_dax_mapping,
+					list);
+	list_del_init(&dmap->list);
+	fc->nr_free_ranges--;
+	spin_unlock(&fc->lock);
+	return dmap;
+}
+
+/* This assumes fc->lock is held */
+static void __free_dax_mapping(struct fuse_conn *fc,
+				struct fuse_dax_mapping *dmap)
+{
+	list_add_tail(&dmap->list, &fc->free_ranges);
+	fc->nr_free_ranges++;
+}
+
+static void free_dax_mapping(struct fuse_conn *fc,
+				struct fuse_dax_mapping *dmap)
+{
+	/* Return fuse_dax_mapping to free list */
+	spin_lock(&fc->lock);
+	__free_dax_mapping(fc, dmap);
+	spin_unlock(&fc->lock);
+}
+
+/* offset passed in should be aligned to FUSE_DAX_MEM_RANGE_SZ */
+static int fuse_setup_one_mapping(struct inode *inode,
+				struct file *file, loff_t offset,
+				struct fuse_dax_mapping *dmap)
+{
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_file *ff = NULL;
+	struct fuse_setupmapping_in inarg;
+	FUSE_ARGS(args);
+	ssize_t err;
+
+	if (file)
+		ff = file->private_data;
+
+	WARN_ON(offset % FUSE_DAX_MEM_RANGE_SZ);
+	WARN_ON(fc->nr_free_ranges < 0);
+
+	/* Ask fuse daemon to setup mapping */
+	memset(&inarg, 0, sizeof(inarg));
+	inarg.foffset = offset;
+	if (ff)
+		inarg.fh = ff->fh;
+	else
+		inarg.fh = -1;
+	inarg.moffset = dmap->window_offset;
+	inarg.len = FUSE_DAX_MEM_RANGE_SZ;
+	if (file) {
+		inarg.flags |= (file->f_mode & FMODE_WRITE) ?
+				FUSE_SETUPMAPPING_FLAG_WRITE : 0;
+		inarg.flags |= (file->f_mode & FMODE_READ) ?
+				FUSE_SETUPMAPPING_FLAG_READ : 0;
+	} else {
+		inarg.flags |= FUSE_SETUPMAPPING_FLAG_READ;
+		inarg.flags |= FUSE_SETUPMAPPING_FLAG_WRITE;
+	}
+	args.in.h.opcode = FUSE_SETUPMAPPING;
+	args.in.h.nodeid = fi->nodeid;
+	args.in.numargs = 1;
+	args.in.args[0].size = sizeof(inarg);
+	args.in.args[0].value = &inarg;
+	err = fuse_simple_request(fc, &args);
+	if (err < 0) {
+		printk(KERN_ERR "%s request failed at mem_offset=0x%llx %zd\n",
+				 __func__, dmap->window_offset, err);
+		return err;
+	}
+
+	pr_debug("fuse_setup_one_mapping() succeeded. offset=0x%llx err=%zd\n", offset, err);
+
+	/* TODO: What locking is required here. For now, using fc->lock */
+	dmap->start = offset;
+	dmap->end = offset + FUSE_DAX_MEM_RANGE_SZ - 1;
+	/* Protected by fi->i_dmap_sem */
+	fuse_dax_interval_tree_insert(dmap, &fi->dmap_tree);
+	fi->nr_dmaps++;
+	return 0;
+}
+
+static int fuse_removemapping_one(struct inode *inode,
+					struct fuse_dax_mapping *dmap)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_removemapping_in inarg;
+	FUSE_ARGS(args);
+
+	memset(&inarg, 0, sizeof(inarg));
+	inarg.moffset = dmap->window_offset;
+	inarg.len = dmap->length;
+	args.in.h.opcode = FUSE_REMOVEMAPPING;
+	args.in.h.nodeid = fi->nodeid;
+	args.in.numargs = 1;
+	args.in.args[0].size = sizeof(inarg);
+	args.in.args[0].value = &inarg;
+	return fuse_simple_request(fc, &args);
+}
+
+/*
+ * It is called from evict_inode() and by that time inode is going away. So
+ * this function does not take any locks like fi->i_dmap_sem for traversing
+ * that fuse inode interval tree. If that lock is taken then lock validator
+ * complains of deadlock situation w.r.t fs_reclaim lock.
+ */
+void fuse_removemapping(struct inode *inode)
+{
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	ssize_t err;
+	struct fuse_dax_mapping *dmap;
+
+	/* Clear the mappings list */
+	while (true) {
+		WARN_ON(fi->nr_dmaps < 0);
+
+		dmap = fuse_dax_interval_tree_iter_first(&fi->dmap_tree, 0,
+								-1);
+		if (dmap) {
+			fuse_dax_interval_tree_remove(dmap, &fi->dmap_tree);
+			fi->nr_dmaps--;
+		}
+
+		if (!dmap)
+			break;
+
+		/*
+		 * During umount/shutdown, fuse connection is dropped first
+		 * and later evict_inode() is called later. That means any
+		 * removemapping messages are going to fail. Send messages
+		 * only if connection is up. Otherwise fuse daemon is
+		 * responsible for cleaning up any leftover references and
+		 * mappings.
+		 */
+		if (fc->connected) {
+			err = fuse_removemapping_one(inode, dmap);
+			if (err) {
+				pr_warn("Failed to removemapping. offset=0x%llx"
+					" len=0x%llx\n", dmap->window_offset,
+					dmap->length);
+			}
+		}
+
+		/* Add it back to free ranges list */
+		free_dax_mapping(fc, dmap);
+	}
+}
+
 void fuse_finish_open(struct inode *inode, struct file *file)
 {
 	struct fuse_file *ff = file->private_data;

@@ -1476,32 +1649,290 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	return res;
 }
 
+static ssize_t fuse_dax_read_iter(struct kiocb *iocb, struct iov_iter *to);
 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->f_mapping->host;
 
 	if (is_bad_inode(file_inode(file)))
 		return -EIO;
 
-	if (!(ff->open_flags & FOPEN_DIRECT_IO))
-		return fuse_cache_read_iter(iocb, to);
-	else
+	if (IS_DAX(inode))
+		return fuse_dax_read_iter(iocb, to);
+
+	if (ff->open_flags & FOPEN_DIRECT_IO)
 		return fuse_direct_read_iter(iocb, to);
+
+	return fuse_cache_read_iter(iocb, to);
 }
 
+static ssize_t fuse_dax_write_iter(struct kiocb *iocb, struct iov_iter *from);
 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->f_mapping->host;
 
 	if (is_bad_inode(file_inode(file)))
 		return -EIO;
 
-	if (!(ff->open_flags & FOPEN_DIRECT_IO))
-		return fuse_cache_write_iter(iocb, from);
-	else
+	if (IS_DAX(inode))
+		return fuse_dax_write_iter(iocb, from);
+
+	if (ff->open_flags & FOPEN_DIRECT_IO)
 		return fuse_direct_write_iter(iocb, from);
+
+	return fuse_cache_write_iter(iocb, from);
+}
+
+static void fuse_fill_iomap_hole(struct iomap *iomap, loff_t length)
+{
+	iomap->addr = IOMAP_NULL_ADDR;
+	iomap->length = length;
+	iomap->type = IOMAP_HOLE;
+}
+
+static void fuse_fill_iomap(struct inode *inode, loff_t pos, loff_t length,
+			struct iomap *iomap, struct fuse_dax_mapping *dmap,
+			unsigned flags)
+{
+	loff_t offset, len;
+	loff_t i_size = i_size_read(inode);
+
+	offset = pos - dmap->start;
+	len = min(length, dmap->length - offset);
+
+	/* If length is beyond end of file, truncate further */
+	if (pos + len > i_size)
+		len = i_size - pos;
+
+	if (len > 0) {
+		iomap->addr = dmap->window_offset + offset;
+		iomap->length = len;
+		if (flags & IOMAP_FAULT)
+			iomap->length = ALIGN(len, PAGE_SIZE);
+		iomap->type = IOMAP_MAPPED;
+		pr_debug("%s: returns iomap: addr 0x%llx offset 0x%llx"
+				" length 0x%llx\n", __func__, iomap->addr,
+				iomap->offset, iomap->length);
+	} else {
+		/* Mapping beyond end of file is hole */
+		fuse_fill_iomap_hole(iomap, length);
+		pr_debug("%s: returns iomap: addr 0x%llx offset 0x%llx"
+				"length 0x%llx\n", __func__, iomap->addr,
+				iomap->offset, iomap->length);
+	}
+}
+
+/* This is just for DAX and the mapping is ephemeral, do not use it for other
+ * purposes since there is no block device with a permanent mapping.
+ */
+static int fuse_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
+			    unsigned flags, struct iomap *iomap)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_dax_mapping *dmap, *alloc_dmap = NULL;
+	int ret;
+
+	/* We don't support FIEMAP */
+	BUG_ON(flags & IOMAP_REPORT);
+
+	pr_debug("fuse_iomap_begin() called. pos=0x%llx length=0x%llx\n",
+			pos, length);
+
+	/*
+	 * Writes beyond end of file are not handled using dax path. Instead
+	 * a fuse write message is sent to daemon
+	 */
+	if (flags & IOMAP_WRITE && pos >= i_size_read(inode))
+		return -EIO;
+
+	iomap->offset = pos;
+	iomap->flags = 0;
+	iomap->bdev = NULL;
+	iomap->dax_dev = fc->dax_dev;
+
+	/*
+	 * Both read/write and mmap path can race here. So we need something
+	 * to make sure if we are setting up mapping, then other path waits
+	 *
+	 * For now, use a semaphore for this. It probably needs to be
+	 * optimized later.
+	 */
+	down_read(&fi->i_dmap_sem);
+	dmap = fuse_dax_interval_tree_iter_first(&fi->dmap_tree, pos, pos);
+
+	if (dmap) {
+		fuse_fill_iomap(inode, pos, length, iomap, dmap, flags);
+		up_read(&fi->i_dmap_sem);
+		return 0;
+	} else {
+		up_read(&fi->i_dmap_sem);
+		pr_debug("%s: no mapping at offset 0x%llx length 0x%llx\n",
+				__func__, pos, length);
+		if (pos >= i_size_read(inode))
+			goto iomap_hole;
+
+		alloc_dmap = alloc_dax_mapping(fc);
+		if (!alloc_dmap)
+			return -EBUSY;
+
+		/*
+		 * Drop read lock and take write lock so that only one
+		 * caller can try to setup mapping and other waits
+		 */
+		down_write(&fi->i_dmap_sem);
+		/*
+		 * We dropped lock. Check again if somebody else setup
+		 * mapping already.
+		 */
+		dmap = fuse_dax_interval_tree_iter_first(&fi->dmap_tree, pos,
+							pos);
+		if (dmap) {
+			fuse_fill_iomap(inode, pos, length, iomap, dmap, flags);
+			free_dax_mapping(fc, alloc_dmap);
+			up_write(&fi->i_dmap_sem);
+			return 0;
+		}
+
+		/* Setup one mapping */
+		ret = fuse_setup_one_mapping(inode, NULL,
+				ALIGN_DOWN(pos, FUSE_DAX_MEM_RANGE_SZ),
+				alloc_dmap);
+		if (ret < 0) {
+			printk("fuse_setup_one_mapping() failed. err=%d"
+				" pos=0x%llx\n", ret, pos);
+			free_dax_mapping(fc, alloc_dmap);
+			up_write(&fi->i_dmap_sem);
+			return ret;
+		}
+		fuse_fill_iomap(inode, pos, length, iomap, alloc_dmap, flags);
+		up_write(&fi->i_dmap_sem);
+		return 0;
+	}
+
+	/*
+	 * If read beyond end of file happnes, fs code seems to return
+	 * it as hole
+	 */
+iomap_hole:
+	fuse_fill_iomap_hole(iomap, length);
+	pr_debug("fuse_iomap_begin() returning hole mapping. pos=0x%llx length_asked=0x%llx length_returned=0x%llx\n", pos, length, iomap->length);
+	return 0;
+}
+
+static int fuse_iomap_end(struct inode *inode, loff_t pos, loff_t length,
+			  ssize_t written, unsigned flags,
+			  struct iomap *iomap)
+{
+	/* DAX writes beyond end-of-file aren't handled using iomap, so the
+	 * file size is unchanged and there is nothing to do here.
+	 */
+	return 0;
+}
+
+static const struct iomap_ops fuse_iomap_ops = {
+	.iomap_begin = fuse_iomap_begin,
+	.iomap_end = fuse_iomap_end,
+};
+
+static ssize_t fuse_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock_shared(inode))
+			return -EAGAIN;
+	} else {
+		inode_lock_shared(inode);
+	}
+
+	ret = dax_iomap_rw(iocb, to, &fuse_iomap_ops);
+	inode_unlock_shared(inode);
+
+	/* TODO file_accessed(iocb->f_filp) */
+
+	return ret;
+}
+
+static bool file_extending_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	return (iov_iter_rw(from) == WRITE &&
+		((iocb->ki_pos) >= i_size_read(inode)));
+}
+
+static ssize_t fuse_dax_direct_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb);
+	ssize_t ret;
+
+	ret = fuse_direct_io(&io, from, &iocb->ki_pos, FUSE_DIO_WRITE);
+	if (ret < 0)
+		return ret;
+
+	fuse_invalidate_attr(inode);
+	fuse_write_update_size(inode, iocb->ki_pos);
+	return ret;
+}
+
+static ssize_t fuse_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret, count;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
+			return -EAGAIN;
+	} else {
+		inode_lock(inode);
+	}
+
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+
+	ret = file_remove_privs(iocb->ki_filp);
+	if (ret)
+		goto out;
+	/* TODO file_update_time() but we don't want metadata I/O */
+
+	/* Do not use dax for file extending writes as its an mmap and
+	 * trying to write beyong end of existing page will generate
+	 * SIGBUS.
+	 */
+	if (file_extending_write(iocb, from)) {
+		ret = fuse_dax_direct_write(iocb, from);
+		goto out;
+ 	}
+
+	ret = dax_iomap_rw(iocb, from, &fuse_iomap_ops);
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * If part of the write was file extending, fuse dax path will not
+	 * take care of that. Do direct write instead.
+	 */
+	if (iov_iter_count(from) && file_extending_write(iocb, from)) {
+		count = fuse_dax_direct_write(iocb, from);
+		if (count < 0)
+			goto out;
+		ret += count;
+	}
+
+out:
+	inode_unlock(inode);
+
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+	return ret;
 }
 
 static void fuse_writepage_free(struct fuse_conn *fc, struct fuse_req *req)