Add linux kernel disk support

Native Linux vdev disk interfaces

Signed-off-by: Brian Behlendorf <[email protected]>

8 files changed, 332 insertions, 41 deletions

diff --git a/module/zfs/include/sys/blkdev.h b/module/zfs/include/sys/blkdev.h
new file mode 100644
index 000000000..b84f66aed
--- /dev/null
+++ b/module/zfs/include/sys/blkdev.h
@@ -0,0 +1,211 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
+ * or http://www.opensolaris.org/os/licensing.
+ * See the License for the specific language governing permissions
+ * and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+/*
+ * Copyright (C) 2008-2010 Lawrence Livermore National Security, LLC.
+ * Produced at Lawrence Livermore National Laboratory (cf, DISCLAIMER).
+ * Written by Brian Behlendorf <[email protected]>.
+ * LLNL-CODE-403049.
+ */
+
+#ifndef	_SYS_BLKDEV_H
+#define	_SYS_BLKDEV_H
+
+#ifdef _KERNEL
+
+#include <linux/blkdev.h>
+#include <linux/elevator.h>
+
+#ifndef HAVE_FMODE_T
+typedef unsigned __bitwise__ fmode_t;
+#endif /* HAVE_FMODE_T */
+
+#ifndef HAVE_BLK_FETCH_REQUEST
+static inline struct request *
+blk_fetch_request(struct request_queue *q)
+{
+	struct request *req;
+
+	req = elv_next_request(q);
+	if (req)
+		blkdev_dequeue_request(req);
+
+	return req;
+}
+#endif /* HAVE_BLK_FETCH_REQUEST */
+
+#ifndef HAVE_BLK_REQUEUE_REQUEST
+static inline void
+blk_requeue_request(request_queue_t *q, struct request *req)
+{
+	elv_requeue_request(q, req);
+}
+#endif /* HAVE_BLK_REQUEUE_REQUEST */
+
+#ifndef HAVE_BLK_END_REQUEST
+static inline bool
+__blk_end_request(struct request *req, int error, unsigned int nr_bytes)
+{
+	LIST_HEAD(list);
+
+	/*
+	 * Request has already been dequeued but 2.6.18 version of
+	 * end_request() unconditionally dequeues the request so we
+	 * add it to a local list to prevent hitting the BUG_ON.
+	 */
+	list_add(&req->queuelist, &list);
+
+	/*
+	 * The old API required the driver to end each segment and not
+	 * the entire request.  In our case we always need to end the
+	 * entire request partial requests are not supported.
+	 */
+	req->hard_cur_sectors = nr_bytes >> 9;
+	end_request(req, ((error == 0) ? 1 : error));
+
+	return 0;
+}
+
+static inline bool
+blk_end_request(struct request *req, int error, unsigned int nr_bytes)
+{
+	struct request_queue *q = req->q;
+	bool rc;
+
+	spin_lock_irq(q->queue_lock);
+	rc = __blk_end_request(req, error, nr_bytes);
+	spin_unlock_irq(q->queue_lock);
+
+	return rc;
+}
+#else
+# ifdef HAVE_BLK_END_REQUEST_GPL_ONLY
+/*
+ * Define required to avoid conflicting 2.6.29 non-static prototype for a
+ * GPL-only version of the helper.  As of 2.6.31 the helper is available
+ * to non-GPL modules and is not explicitly exported GPL-only.
+ */
+# define __blk_end_request __blk_end_request_x
+# define blk_end_request blk_end_request_x
+
+static inline bool
+__blk_end_request_x(struct request *req, int error, unsigned int nr_bytes)
+{
+	/*
+	 * The old API required the driver to end each segment and not
+	 * the entire request.  In our case we always need to end the
+	 * entire request partial requests are not supported.
+	 */
+	req->hard_cur_sectors = nr_bytes >> 9;
+	end_request(req, ((error == 0) ? 1 : error));
+
+	return 0;
+}
+static inline bool
+blk_end_request_x(struct request *req, int error, unsigned int nr_bytes)
+{
+	struct request_queue *q = req->q;
+	bool rc;
+
+	spin_lock_irq(q->queue_lock);
+	rc = __blk_end_request_x(req, error, nr_bytes);
+	spin_unlock_irq(q->queue_lock);
+
+	return rc;
+}
+# endif /* HAVE_BLK_END_REQUEST_GPL_ONLY */
+#endif /* HAVE_BLK_END_REQUEST */
+
+#ifndef HAVE_BLK_RQ_POS
+static inline sector_t
+blk_rq_pos(struct request *req)
+{
+	return req->sector;
+}
+#endif /* HAVE_BLK_RQ_POS */
+
+#ifndef HAVE_BLK_RQ_SECTORS
+static inline unsigned int
+blk_rq_sectors(struct request *req)
+{
+	return req->nr_sectors;
+}
+#endif /* HAVE_BLK_RQ_SECTORS */
+
+#if !defined(HAVE_BLK_RQ_BYTES) || defined(HAVE_BLK_RQ_BYTES_GPL_ONLY)
+/*
+ * Define required to avoid conflicting 2.6.29 non-static prototype for a
+ * GPL-only version of the helper.  As of 2.6.31 the helper is available
+ * to non-GPL modules in the form of a static inline in the header.
+ */
+#define blk_rq_bytes __blk_rq_bytes
+static inline unsigned int
+__blk_rq_bytes(struct request *req)
+{
+	return blk_rq_sectors(req) << 9;
+}
+#endif /* !HAVE_BLK_RQ_BYTES || HAVE_BLK_RQ_BYTES_GPL_ONLY */
+
+#ifndef HAVE_GET_DISK_RO
+static inline int
+get_disk_ro(struct gendisk *disk)
+{
+	int policy = 0;
+
+	if (disk->part[0])
+		policy = disk->part[0]->policy;
+
+	return policy;
+}
+#endif /* HAVE_GET_DISK_RO */
+
+#ifndef HAVE_RQ_IS_SYNC
+static inline bool
+rq_is_sync(struct request *req)
+{
+	return (req->flags & REQ_RW_SYNC);
+}
+#endif /* HAVE_RQ_IS_SYNC */
+
+#ifndef HAVE_RQ_FOR_EACH_SEGMENT
+struct req_iterator {
+	int i;
+	struct bio *bio;
+};
+
+# define for_each_bio(_bio)              \
+	for (; _bio; _bio = _bio->bi_next)
+
+# define __rq_for_each_bio(_bio, rq)    \
+	if ((rq->bio))                  \
+		for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next)
+
+# define rq_for_each_segment(bvl, _rq, _iter)                   \
+	__rq_for_each_bio(_iter.bio, _rq)                       \
+		bio_for_each_segment(bvl, _iter.bio, _iter.i)
+#endif /* HAVE_RQ_FOR_EACH_SEGMENT */
+
+#ifndef DISK_NAME_LEN
+#define DISK_NAME_LEN	32
+#endif /* DISK_NAME_LEN */
+
+#endif /* KERNEL */
+
+#endif	/* _SYS_BLKDEV_H */
diff --git a/module/zfs/include/sys/dmu.h b/module/zfs/include/sys/dmu.h
index ad4127602..575cb2d10 100644
--- a/module/zfs/include/sys/dmu.h
+++ b/module/zfs/include/sys/dmu.h
@@ -41,13 +41,14 @@
 #include <sys/cred.h>
 #include <sys/time.h>
 #include <sys/uio.h>
+#ifdef _KERNEL
+#include <sys/blkdev.h>
+#endif
 
 #ifdef	__cplusplus
 extern "C" {
 #endif
 
-struct uio;
-struct xuio;
 struct page;
 struct vnode;
 struct spa;
@@ -512,13 +513,14 @@ void dmu_write(objset_t *os, uint64_t object, uint64_t offset, uint64_t size,
 	const void *buf, dmu_tx_t *tx);
 void dmu_prealloc(objset_t *os, uint64_t object, uint64_t offset, uint64_t size,
 	dmu_tx_t *tx);
-int dmu_read_uio(objset_t *os, uint64_t object, struct uio *uio, uint64_t size);
-int dmu_write_uio(objset_t *os, uint64_t object, struct uio *uio, uint64_t size,
-    dmu_tx_t *tx);
-int dmu_write_uio_dbuf(dmu_buf_t *zdb, struct uio *uio, uint64_t size,
-    dmu_tx_t *tx);
+#ifdef _KERNEL
+int dmu_read_req(objset_t *os, uint64_t object, struct request *req);
+int dmu_write_req(objset_t *os, uint64_t object, struct request *req, dmu_tx_t *tx);
+#endif
+#ifdef HAVE_ZPL
 int dmu_write_pages(objset_t *os, uint64_t object, uint64_t offset,
     uint64_t size, struct page *pp, dmu_tx_t *tx);
+#endif
 struct arc_buf *dmu_request_arcbuf(dmu_buf_t *handle, int size);
 void dmu_return_arcbuf(struct arc_buf *buf);
 void dmu_assign_arcbuf(dmu_buf_t *handle, uint64_t offset, struct arc_buf *buf,
diff --git a/module/zfs/include/sys/spa_impl.h b/module/zfs/include/sys/spa_impl.h
index c965ffbbe..8cab66992 100644
--- a/module/zfs/include/sys/spa_impl.h
+++ b/module/zfs/include/sys/spa_impl.h
@@ -210,7 +210,7 @@ struct spa {
 	kmutex_t	spa_proc_lock;		/* protects spa_proc* */
 	kcondvar_t	spa_proc_cv;		/* spa_proc_state transitions */
 	spa_proc_state_t spa_proc_state;	/* see definition */
-	struct proc	*spa_proc;		/* "zpool-poolname" process */
+	proc_t		*spa_proc;		/* "zpool-poolname" process */
 	uint64_t	spa_did;		/* if procp != p0, did of t1 */
 	boolean_t	spa_autoreplace;	/* autoreplace set in open */
 	int		spa_vdev_locks;		/* locks grabbed */
diff --git a/module/zfs/include/sys/vdev_disk.h b/module/zfs/include/sys/vdev_disk.h
new file mode 100644
index 000000000..986c33624
--- /dev/null
+++ b/module/zfs/include/sys/vdev_disk.h
@@ -0,0 +1,97 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
+ * or http://www.opensolaris.org/os/licensing.
+ * See the License for the specific language governing permissions
+ * and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+/*
+ * Copyright (C) 2008-2010 Lawrence Livermore National Security, LLC.
+ * Produced at Lawrence Livermore National Laboratory (cf, DISCLAIMER).
+ * Written by Brian Behlendorf <[email protected]>.
+ * LLNL-CODE-403049.
+ */
+
+#ifndef _SYS_VDEV_DISK_H
+#define _SYS_VDEV_DISK_H
+
+#ifdef	__cplusplus
+extern "C" {
+#endif
+
+#ifdef _KERNEL
+#include <sys/vdev.h>
+#include <sys/ddi.h>
+#include <sys/sunldi.h>
+#include <sys/sunddi.h>
+
+typedef struct vdev_disk {
+	ddi_devid_t		vd_devid;
+	char			*vd_minor;
+	struct block_device	*vd_bdev;
+} vdev_disk_t;
+
+extern int vdev_disk_physio(struct block_device *, caddr_t,
+			    size_t, uint64_t, int);
+extern int vdev_disk_read_rootlabel(char *, char *, nvlist_t **);
+
+/* 2.6.24 API change */
+#ifdef HAVE_2ARGS_BIO_END_IO_T
+# define BIO_END_IO_PROTO(fn, x, y, z)	static void fn(struct bio *x, int z)
+# define BIO_END_IO_RETURN(rc)		return
+#else
+# define BIO_END_IO_PROTO(fn, x, y, z)	static int fn(struct bio *x, \
+					              unsigned int y, int z)
+# define BIO_END_IO_RETURN(rc)		return rc
+#endif /* HAVE_2ARGS_BIO_END_IO_T */
+
+/* 2.6.29 API change */
+#ifdef HAVE_BIO_RW_SYNCIO
+# define DIO_RW_SYNCIO			BIO_RW_SYNCIO
+#else
+# define DIO_RW_SYNCIO			BIO_RW_SYNC
+#endif /* HAVE_BIO_RW_SYNCIO */
+
+/* 2.6.28 API change */
+#ifdef HAVE_OPEN_BDEV_EXCLUSIVE
+# define vdev_bdev_open(path, md, hld)	open_bdev_exclusive(path, md, hld)
+# define vdev_bdev_close(bdev, md)	close_bdev_exclusive(bdev, md)
+#else
+# define vdev_bdev_open(path, md, hld)	open_bdev_excl(path, md, hld)
+# define vdev_bdev_close(bdev, md)	close_bdev_excl(bdev)
+#endif /* HAVE_OPEN_BDEV_EXCLUSIVE */
+
+/* 2.6.22 API change */
+#ifdef HAVE_1ARG_INVALIDATE_BDEV
+# define vdev_bdev_invalidate(bdev)	invalidate_bdev(bdev)
+#else
+# define vdev_bdev_invalidate(bdev)	invalidate_bdev(bdev, 1)
+#endif /* HAVE_1ARG_INVALIDATE_BDEV */
+
+/* 2.6.30 API change */
+#ifdef HAVE_BDEV_LOGICAL_BLOCK_SIZE
+# define vdev_bdev_block_size(bdev)	bdev_logical_block_size(bdev)
+#else
+# define vdev_bdev_block_size(bdev)	bdev_hardsect_size(bdev)
+#endif
+
+#endif /* _KERNEL */
+
+#ifdef	__cplusplus
+}
+#endif
+
+#endif	/* _SYS_VDEV_DISK_H */
diff --git a/module/zfs/include/sys/zfs_fuid.h b/module/zfs/include/sys/zfs_fuid.h
index 0feb3ce4b..d2989c852 100644
--- a/module/zfs/include/sys/zfs_fuid.h
+++ b/module/zfs/include/sys/zfs_fuid.h
@@ -33,6 +33,7 @@
 #include <sys/zfs_vfsops.h>
 #endif
 #include <sys/avl.h>
+#include <sys/list.h>
 
 #ifdef	__cplusplus
 extern "C" {
@@ -98,6 +99,7 @@ typedef struct zfs_fuid_info {
 } zfs_fuid_info_t;
 
 #ifdef _KERNEL
+#ifdef HAVE_ZPL
 struct znode;
 extern uid_t zfs_fuid_map_id(zfsvfs_t *, uint64_t, cred_t *, zfs_fuid_type_t);
 extern void zfs_fuid_node_add(zfs_fuid_info_t **, const char *, uint32_t,
@@ -117,6 +119,7 @@ extern int zfs_fuid_find_by_domain(zfsvfs_t *, const char *domain,
     char **retdomain, boolean_t addok);
 extern const char *zfs_fuid_find_by_idx(zfsvfs_t *zfsvfs, uint32_t idx);
 extern void zfs_fuid_txhold(zfsvfs_t *zfsvfs, dmu_tx_t *tx);
+#endif /* HAVE_ZPL */
 #endif
 
 char *zfs_fuid_idx_domain(avl_tree_t *, uint32_t);
diff --git a/module/zfs/include/sys/zfs_ioctl.h b/module/zfs/include/sys/zfs_ioctl.h
index 4a21cc8e0..e3fd2c3fc 100644
--- a/module/zfs/include/sys/zfs_ioctl.h
+++ b/module/zfs/include/sys/zfs_ioctl.h
@@ -316,7 +316,6 @@ extern int zfs_secpolicy_snapshot_perms(const char *name, cred_t *cr);
 extern int zfs_secpolicy_rename_perms(const char *from,
     const char *to, cred_t *cr);
 extern int zfs_secpolicy_destroy_perms(const char *name, cred_t *cr);
-extern int zfs_busy(void);
 extern int zfs_unmount_snap(const char *, void *);
 
 enum zfsdev_state_type {
diff --git a/module/zfs/include/sys/zfs_znode.h b/module/zfs/include/sys/zfs_znode.h
index 9d4b913ed..b2477eddb 100644
--- a/module/zfs/include/sys/zfs_znode.h
+++ b/module/zfs/include/sys/zfs_znode.h
@@ -343,8 +343,10 @@ extern void zfs_xvattr_set(znode_t *zp, xvattr_t *xvap, dmu_tx_t *tx);
 extern void zfs_upgrade(zfsvfs_t *zfsvfs, dmu_tx_t *tx);
 extern int zfs_create_share_dir(zfsvfs_t *zfsvfs, dmu_tx_t *tx);
 
+#if defined(HAVE_UIO_RW)
 extern caddr_t zfs_map_page(page_t *, enum seg_rw);
 extern void zfs_unmap_page(page_t *, caddr_t);
+#endif /* HAVE_UIO_RW */
 
 extern zil_get_data_t zfs_get_data;
 extern zil_replay_func_t *zfs_replay_vector[TX_MAX_TYPE];
diff --git a/module/zfs/include/sys/zvol.h b/module/zfs/include/sys/zvol.h
index 0059bf510..c8b9d6507 100644
--- a/module/zfs/include/sys/zvol.h
+++ b/module/zfs/include/sys/zvol.h
@@ -28,49 +28,26 @@
 
 #include <sys/zfs_context.h>
 
-#ifdef	__cplusplus
-extern "C" {
-#endif
-
 #define	ZVOL_OBJ		1ULL
 #define	ZVOL_ZAP_OBJ		2ULL
 
 #ifdef _KERNEL
+
+#include <sys/blkdev.h>
+
 extern int zvol_check_volsize(uint64_t volsize, uint64_t blocksize);
 extern int zvol_check_volblocksize(uint64_t volblocksize);
 extern int zvol_get_stats(objset_t *os, nvlist_t *nv);
 extern void zvol_create_cb(objset_t *os, void *arg, cred_t *cr, dmu_tx_t *tx);
 extern int zvol_create_minor(const char *);
+extern int zvol_create_minors(const char *);
 extern int zvol_remove_minor(const char *);
 extern void zvol_remove_minors(const char *);
-extern int zvol_set_volsize(const char *, major_t, uint64_t);
+extern int zvol_set_volsize(const char *, uint64_t);
+extern int zvol_set_volblocksize(const char *, uint64_t);
 
-extern int zvol_open(dev_t *devp, int flag, int otyp, cred_t *cr);
-extern int zvol_dump(dev_t dev, caddr_t addr, daddr_t offset, int nblocks);
-extern int zvol_close(dev_t dev, int flag, int otyp, cred_t *cr);
-extern int zvol_strategy(buf_t *bp);
-extern int zvol_read(dev_t dev, uio_t *uiop, cred_t *cr);
-extern int zvol_write(dev_t dev, uio_t *uiop, cred_t *cr);
-extern int zvol_aread(dev_t dev, struct aio_req *aio, cred_t *cr);
-extern int zvol_awrite(dev_t dev, struct aio_req *aio, cred_t *cr);
-extern int zvol_ioctl(dev_t dev, int cmd, intptr_t arg, int flag, cred_t *cr,
-    int *rvalp);
-extern int zvol_busy(void);
-extern void zvol_init(void);
+extern int zvol_init(void);
 extern void zvol_fini(void);
 
-extern int zvol_get_volume_params(minor_t minor, uint64_t *blksize,
-    uint64_t *max_xfer_len, void **minor_hdl, void **objset_hdl, void **zil_hdl,
-    void **rl_hdl, void **bonus_hdl);
-extern uint64_t zvol_get_volume_size(void *minor_hdl);
-extern int zvol_get_volume_wce(void *minor_hdl);
-extern void zvol_log_write_minor(void *minor_hdl, dmu_tx_t *tx, offset_t off,
-    ssize_t resid, boolean_t sync);
-
-#endif
-
-#ifdef	__cplusplus
-}
-#endif
-
-#endif	/* _SYS_ZVOL_H */
+#endif /* _KERNEL */
+#endif /* _SYS_ZVOL_H */