OpenZFS 9689 - zfs range lock code should not be zpl-specific

The ZFS range locking code in zfs_rlock.c/h depends on ZPL-specific
data structures, specifically znode_t.  However, it's also used by
the ZVOL code, which uses a "dummy" znode_t to pass to the range
locking code.

We should clean this up so that the range locking code is generic
and can be used equally by ZPL and ZVOL, and also can be used by
future consumers that may need to run in userland (libzpool) as
well as the kernel.

Porting notes:
* Added missing sys/avl.h include to sys/zfs_rlock.h.
* Removed 'dbuf is within the locked range' ASSERTs from dmu_sync().
  This was needed because ztest does not yet use a locked_range_t.
* Removed "Approved by:" tag requirement from OpenZFS commit
  check to prevent needless warnings when integrating changes
  which has not been merged to illumos.
* Reverted free_list range lock changes which were originally
  needed to defer the cv_destroy() which was called immediately
  after cv_broadcast().  With d2733258 this should be safe but
  if not we may need to reintroduce this logic.
* Reverts: The following two commits were reverted and squashed in
  to this change in order to make it easier to apply OpenZFS 9689.
  - d88895a0, which removed the dummy znode from zvol_state
  - e3a07cd0, which updated ztest to use range locks
* Preserved optimized rangelock comparison function.  Preserved the
  rangelock free list.  The cv_destroy() function will block waiting
  for all processes in cv_wait() to be scheduled and drop their
  reference.  This is done to ensure it's safe to free the condition
  variable.  However, blocking while holding the rl->rl_lock mutex
  can result in a deadlock on Linux.  A free list is introduced to
  defer the cv_destroy() and kmem_free() until after the mutex is
  released.

Authored by: Matthew Ahrens <[email protected]>
Reviewed by: Brian Behlendorf <[email protected]>
Reviewed by: Serapheim Dimitropoulos <[email protected]>
Reviewed by: George Wilson <[email protected]>
Reviewed by: Brad Lewis <[email protected]>
Ported-by: Brian Behlendorf <[email protected]>

OpenZFS-issue: https://illumos.org/issues/9689
OpenZFS-commit: https://github.com/openzfs/openzfs/pull/680
External-issue: DLPX-58662
Closes #7980

1 files changed, 13 insertions, 13 deletions

diff --git a/module/zfs/zvol.c b/module/zfs/zvol.c
index f7706f143..e6f8451b2 100644
--- a/module/zfs/zvol.c
+++ b/module/zfs/zvol.c
@@ -86,7 +86,6 @@
 #include <sys/dmu_tx.h>
 #include <sys/zio.h>
 #include <sys/zfs_rlock.h>
-#include <sys/zfs_znode.h>
 #include <sys/spa_impl.h>
 #include <sys/zvol.h>
 
@@ -123,7 +122,7 @@ struct zvol_state {
 	uint32_t		zv_open_count;	/* open counts */
 	uint32_t		zv_changed;	/* disk changed */
 	zilog_t			*zv_zilog;	/* ZIL handle */
-	zfs_rlock_t		zv_range_lock;	/* range lock */
+	rangelock_t		zv_rangelock;	/* for range locking */
 	dnode_t			*zv_dn;		/* dnode hold */
 	dev_t			zv_dev;		/* device id */
 	struct gendisk		*zv_disk;	/* generic disk */
@@ -716,7 +715,7 @@ zvol_log_write(zvol_state_t *zv, dmu_tx_t *tx, uint64_t offset,
 typedef struct zv_request {
 	zvol_state_t	*zv;
 	struct bio	*bio;
-	rl_t		*rl;
+	locked_range_t	*lr;
 } zv_request_t;
 
 static void
@@ -778,7 +777,7 @@ zvol_write(void *arg)
 		if (error)
 			break;
 	}
-	zfs_range_unlock(zvr->rl);
+	rangelock_exit(zvr->lr);
 
 	int64_t nwritten = start_resid - uio.uio_resid;
 	dataset_kstats_update_write_kstats(&zv->zv_kstat, nwritten);
@@ -872,7 +871,8 @@ zvol_discard(void *arg)
 		    ZVOL_OBJ, start, size);
 	}
 unlock:
-	zfs_range_unlock(zvr->rl);
+	rangelock_exit(zvr->lr);
+
 	if (error == 0 && sync)
 		zil_commit(zv->zv_zilog, ZVOL_OBJ);
 
@@ -917,7 +917,7 @@ zvol_read(void *arg)
 			break;
 		}
 	}
-	zfs_range_unlock(zvr->rl);
+	rangelock_exit(zvr->lr);
 
 	int64_t nread = start_resid - uio.uio_resid;
 	dataset_kstats_update_read_kstats(&zv->zv_kstat, nread);
@@ -985,7 +985,7 @@ zvol_request(struct request_queue *q, struct bio *bio)
 		 * are asynchronous, we take it here synchronously to make
 		 * sure overlapped I/Os are properly ordered.
 		 */
-		zvr->rl = zfs_range_lock(&zv->zv_range_lock, offset, size,
+		zvr->lr = rangelock_enter(&zv->zv_rangelock, offset, size,
 		    RL_WRITER);
 		/*
 		 * Sync writes and discards execute zil_commit() which may need
@@ -1014,7 +1014,7 @@ zvol_request(struct request_queue *q, struct bio *bio)
 
 		rw_enter(&zv->zv_suspend_lock, RW_READER);
 
-		zvr->rl = zfs_range_lock(&zv->zv_range_lock, offset, size,
+		zvr->lr = rangelock_enter(&zv->zv_rangelock, offset, size,
 		    RL_READER);
 		if (zvol_request_sync || taskq_dispatch(zvol_taskq,
 		    zvol_read, zvr, TQ_SLEEP) == TASKQID_INVALID)
@@ -1036,7 +1036,7 @@ zvol_get_done(zgd_t *zgd, int error)
 	if (zgd->zgd_db)
 		dmu_buf_rele(zgd->zgd_db, zgd);
 
-	zfs_range_unlock(zgd->zgd_rl);
+	rangelock_exit(zgd->zgd_lr);
 
 	if (error == 0 && zgd->zgd_bp)
 		zil_lwb_add_block(zgd->zgd_lwb, zgd->zgd_bp);
@@ -1072,7 +1072,7 @@ zvol_get_data(void *arg, lr_write_t *lr, char *buf, struct lwb *lwb, zio_t *zio)
 	 * we don't have to write the data twice.
 	 */
 	if (buf != NULL) { /* immediate write */
-		zgd->zgd_rl = zfs_range_lock(&zv->zv_range_lock, offset, size,
+		zgd->zgd_lr = rangelock_enter(&zv->zv_rangelock, offset, size,
 		    RL_READER);
 		error = dmu_read_by_dnode(zv->zv_dn, offset, size, buf,
 		    DMU_READ_NO_PREFETCH);
@@ -1085,7 +1085,7 @@ zvol_get_data(void *arg, lr_write_t *lr, char *buf, struct lwb *lwb, zio_t *zio)
 		 */
 		size = zv->zv_volblocksize;
 		offset = P2ALIGN_TYPED(offset, size, uint64_t);
-		zgd->zgd_rl = zfs_range_lock(&zv->zv_range_lock, offset, size,
+		zgd->zgd_lr = rangelock_enter(&zv->zv_rangelock, offset, size,
 		    RL_READER);
 		error = dmu_buf_hold_by_dnode(zv->zv_dn, offset, zgd, &db,
 		    DMU_READ_NO_PREFETCH);
@@ -1687,7 +1687,7 @@ zvol_alloc(dev_t dev, const char *name)
 	zv->zv_open_count = 0;
 	strlcpy(zv->zv_name, name, MAXNAMELEN);
 
-	zfs_rlock_init(&zv->zv_range_lock);
+	rangelock_init(&zv->zv_rangelock, NULL, NULL);
 	rw_init(&zv->zv_suspend_lock, NULL, RW_DEFAULT, NULL);
 
 	zv->zv_disk->major = zvol_major;
@@ -1745,7 +1745,7 @@ zvol_free(void *arg)
 	ASSERT(zv->zv_disk->private_data == NULL);
 
 	rw_destroy(&zv->zv_suspend_lock);
-	zfs_rlock_destroy(&zv->zv_range_lock);
+	rangelock_fini(&zv->zv_rangelock);
 
 	del_gendisk(zv->zv_disk);
 	blk_cleanup_queue(zv->zv_queue);