Illumos 5960, 5925

5960 zfs recv should prefetch indirect blocks
5925 zfs receive -o origin=
Reviewed by: Prakash Surya <[email protected]>
Reviewed by: Matthew Ahrens <[email protected]>

References:
  https://www.illumos.org/issues/5960
  https://www.illumos.org/issues/5925
  https://github.com/illumos/illumos-gate/commit/a2cdcdd

Porting notes:
- [lib/libzfs/libzfs_sendrecv.c]
  - b8864a2 Fix gcc cast warnings
  - 325f023 Add linux kernel device support
  - 5c3f61e Increase Linux pipe buffer size on 'zfs receive'
- [module/zfs/zfs_vnops.c]
  - 3558fd7 Prototype/structure update for Linux
  - c12e3a5 Restructure zfs_readdir() to fix regressions
- [module/zfs/zvol.c]
  - Function @zvol_map_block() isn't needed in ZoL
  - 9965059 Prefetch start and end of volumes
- [module/zfs/dmu.c]
  - Fixed ISO C90 - mixed declarations and code
  - Function dmu_prefetch() 'int i' is initialized before
    the following code block (c90 vs. c99)
- [module/zfs/dbuf.c]
  - fc5bb51 Fix stack dbuf_hold_impl()
  - 9b67f60 Illumos 4757, 4913
  - 34229a2 Reduce stack usage for recursive traverse_visitbp()
- [module/zfs/dmu_send.c]
  - Fixed ISO C90 - mixed declarations and code
  - b58986e Use large stacks when available
  - 241b541 Illumos 5959 - clean up per-dataset feature count code
  - 77aef6f Use vmem_alloc() for nvlists
  - 00b4602 Add linux kernel memory support

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

10 files changed, 128 insertions, 24 deletions

diff --git a/include/libzfs.h b/include/libzfs.h
index b7ab890c3..2a1f2f50d 100644
--- a/include/libzfs.h
+++ b/include/libzfs.h
@@ -678,8 +678,8 @@ typedef struct recvflags {
 	boolean_t nomount;
 } recvflags_t;
 
-extern int zfs_receive(libzfs_handle_t *, const char *, recvflags_t *,
-    int, avl_tree_t *);
+extern int zfs_receive(libzfs_handle_t *, const char *, nvlist_t *,
+    recvflags_t *, int, avl_tree_t *);
 
 typedef enum diff_flags {
 	ZFS_DIFF_PARSEABLE = 0x1,
diff --git a/include/sys/Makefile.am b/include/sys/Makefile.am
index 77ecfb2dc..73e86d03b 100644
--- a/include/sys/Makefile.am
+++ b/include/sys/Makefile.am
@@ -9,6 +9,7 @@ COMMON_H = \
 	$(top_srcdir)/include/sys/bplist.h \
 	$(top_srcdir)/include/sys/bpobj.h \
 	$(top_srcdir)/include/sys/bptree.h \
+	$(top_srcdir)/include/sys/bqueue.h \
 	$(top_srcdir)/include/sys/dbuf.h \
 	$(top_srcdir)/include/sys/ddt.h \
 	$(top_srcdir)/include/sys/dmu.h \
@@ -96,6 +97,7 @@ COMMON_H = \
 	$(top_srcdir)/include/sys/zio_compress.h \
 	$(top_srcdir)/include/sys/zio.h \
 	$(top_srcdir)/include/sys/zio_impl.h \
+	$(top_srcdir)/include/sys/zio_priority.h \
 	$(top_srcdir)/include/sys/zrlock.h
 
 KERNEL_H = \
diff --git a/include/sys/bqueue.h b/include/sys/bqueue.h
new file mode 100644
index 000000000..63722df1b
--- /dev/null
+++ b/include/sys/bqueue.h
@@ -0,0 +1,54 @@
+/*
+ * CDDL HEADER START
+ *
+ * This file and its contents are supplied under the terms of the
+ * Common Development and Distribution License ("CDDL"), version 1.0.
+ * You may only use this file in accordance with the terms of version
+ * 1.0 of the CDDL.
+ *
+ * A full copy of the text of the CDDL should have accompanied this
+ * source.  A copy of the CDDL is also available via the Internet at
+ * http://www.illumos.org/license/CDDL.
+ *
+ * CDDL HEADER END
+ */
+/*
+ * Copyright (c) 2014 by Delphix. All rights reserved.
+ */
+
+#ifndef	_BQUEUE_H
+#define	_BQUEUE_H
+
+#ifdef	__cplusplus
+extern "C" {
+#endif
+
+#include	<sys/zfs_context.h>
+
+typedef struct bqueue {
+	list_t bq_list;
+	kmutex_t bq_lock;
+	kcondvar_t bq_add_cv;
+	kcondvar_t bq_pop_cv;
+	uint64_t bq_size;
+	uint64_t bq_maxsize;
+	size_t bq_node_offset;
+} bqueue_t;
+
+typedef struct bqueue_node {
+	list_node_t bqn_node;
+	uint64_t bqn_size;
+} bqueue_node_t;
+
+
+int bqueue_init(bqueue_t *, uint64_t, size_t);
+void bqueue_destroy(bqueue_t *);
+void bqueue_enqueue(bqueue_t *, void *, uint64_t);
+void *bqueue_dequeue(bqueue_t *);
+boolean_t bqueue_empty(bqueue_t *);
+
+#ifdef	__cplusplus
+}
+#endif
+
+#endif	/* _BQUEUE_H */
diff --git a/include/sys/dbuf.h b/include/sys/dbuf.h
index 0d262e87b..9147c9d4d 100644
--- a/include/sys/dbuf.h
+++ b/include/sys/dbuf.h
@@ -261,8 +261,7 @@ typedef struct dbuf_hash_table {
 	kmutex_t hash_mutexes[DBUF_MUTEXES];
 } dbuf_hash_table_t;
 
-
-uint64_t dbuf_whichblock(struct dnode *di, uint64_t offset);
+uint64_t dbuf_whichblock(struct dnode *di, int64_t level, uint64_t offset);
 
 void dbuf_create_bonus(struct dnode *dn);
 int dbuf_spill_set_blksz(dmu_buf_t *db, uint64_t blksz, dmu_tx_t *tx);
@@ -272,10 +271,12 @@ void dbuf_rm_spill(struct dnode *dn, dmu_tx_t *tx);
 dmu_buf_impl_t *dbuf_hold(struct dnode *dn, uint64_t blkid, void *tag);
 dmu_buf_impl_t *dbuf_hold_level(struct dnode *dn, int level, uint64_t blkid,
     void *tag);
-int dbuf_hold_impl(struct dnode *dn, uint8_t level, uint64_t blkid, int create,
+int dbuf_hold_impl(struct dnode *dn, uint8_t level, uint64_t blkid,
+    boolean_t fail_sparse, boolean_t fail_uncached,
     void *tag, dmu_buf_impl_t **dbp);
 
-void dbuf_prefetch(struct dnode *dn, uint64_t blkid, zio_priority_t prio);
+void dbuf_prefetch(struct dnode *dn, int64_t level, uint64_t blkid,
+    zio_priority_t prio, arc_flags_t aflags);
 
 void dbuf_add_ref(dmu_buf_impl_t *db, void *tag);
 boolean_t dbuf_try_add_ref(dmu_buf_t *db, objset_t *os, uint64_t obj,
diff --git a/include/sys/dmu.h b/include/sys/dmu.h
index 6bf51975e..75d85951a 100644
--- a/include/sys/dmu.h
+++ b/include/sys/dmu.h
@@ -44,6 +44,7 @@
 #include <sys/inttypes.h>
 #include <sys/cred.h>
 #include <sys/fs/zfs.h>
+#include <sys/zio_priority.h>
 #include <sys/uio.h>
 
 #ifdef	__cplusplus
@@ -737,8 +738,8 @@ extern int zfs_max_recordsize;
 /*
  * Asynchronously try to read in the data.
  */
-void dmu_prefetch(objset_t *os, uint64_t object, uint64_t offset,
-    uint64_t len);
+void dmu_prefetch(objset_t *os, uint64_t object, int64_t level, uint64_t offset,
+	uint64_t len, enum zio_priority pri);
 
 typedef struct dmu_object_info {
 	/* All sizes are in bytes unless otherwise indicated. */
diff --git a/include/sys/dsl_dataset.h b/include/sys/dsl_dataset.h
index 25622263e..f033eace9 100644
--- a/include/sys/dsl_dataset.h
+++ b/include/sys/dsl_dataset.h
@@ -21,7 +21,7 @@
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
  * Copyright (c) 2011, 2015 by Delphix. All rights reserved.
- * Copyright (c) 2013, Joyent, Inc. All rights reserved.
+ * Copyright (c) 2011, 2014 by Delphix. All rights reserved.
  * Copyright (c) 2013 Steven Hartland. All rights reserved.
  * Copyright (c) 2014 Spectra Logic Corporation, All rights reserved.
  */
diff --git a/include/sys/zfs_context.h b/include/sys/zfs_context.h
index 2a749d840..036235e2b 100644
--- a/include/sys/zfs_context.h
+++ b/include/sys/zfs_context.h
@@ -160,8 +160,18 @@ extern int aok;
 
 /*
  * DTrace SDT probes have different signatures in userland than they do in
- * kernel.  If they're being used in kernel code, re-define them out of
+ * the kernel.  If they're being used in kernel code, re-define them out of
  * existence for their counterparts in libzpool.
+ *
+ * Here's an example of how to use the set-error probes in userland:
+ * zfs$target:::set-error /arg0 == EBUSY/ {stack();}
+ *
+ * Here's an example of how to use DTRACE_PROBE probes in userland:
+ * If there is a probe declared as follows:
+ * DTRACE_PROBE2(zfs__probe_name, uint64_t, blkid, dnode_t *, dn);
+ * Then you can use it as follows:
+ * zfs$target:::probe2 /copyinstr(arg0) == "zfs__probe_name"/
+ *     {printf("%u %p\n", arg1, arg2);}
  */
 
 #ifdef DTRACE_PROBE
diff --git a/include/sys/zio.h b/include/sys/zio.h
index 4916d8724..ced7fe87b 100644
--- a/include/sys/zio.h
+++ b/include/sys/zio.h
@@ -29,6 +29,7 @@
 #ifndef _ZIO_H
 #define	_ZIO_H
 
+#include <sys/zio_priority.h>
 #include <sys/zfs_context.h>
 #include <sys/spa.h>
 #include <sys/txg.h>
@@ -147,17 +148,6 @@ enum zio_compress {
 #define	ZIO_FAILURE_MODE_CONTINUE	1
 #define	ZIO_FAILURE_MODE_PANIC		2
 
-typedef enum zio_priority {
-	ZIO_PRIORITY_SYNC_READ,
-	ZIO_PRIORITY_SYNC_WRITE,	/* ZIL */
-	ZIO_PRIORITY_ASYNC_READ,	/* prefetch */
-	ZIO_PRIORITY_ASYNC_WRITE,	/* spa_sync() */
-	ZIO_PRIORITY_SCRUB,		/* asynchronous scrub/resilver reads */
-	ZIO_PRIORITY_NUM_QUEUEABLE,
-
-	ZIO_PRIORITY_NOW		/* non-queued i/os (e.g. free) */
-} zio_priority_t;
-
 enum zio_flag {
 	/*
 	 * Flags inherited by gang, ddt, and vdev children,
@@ -262,6 +252,7 @@ extern const char *zio_type_name[ZIO_TYPES];
  * Root blocks (objset_phys_t) are object 0, level -1:  <objset, 0, -1, 0>.
  * ZIL blocks are bookmarked <objset, 0, -2, blkid == ZIL sequence number>.
  * dmu_sync()ed ZIL data blocks are bookmarked <objset, object, -2, blkid>.
+ * dnode visit bookmarks are <objset, object id of dnode, -3, 0>.
  *
  * Note: this structure is called a bookmark because its original purpose
  * was to remember where to resume a pool-wide traverse.
@@ -294,6 +285,9 @@ struct zbookmark_phys {
 #define	ZB_ZIL_OBJECT		(0ULL)
 #define	ZB_ZIL_LEVEL		(-2LL)
 
+#define	ZB_DNODE_LEVEL		(-3LL)
+#define	ZB_DNODE_BLKID		(0ULL)
+
 #define	ZB_IS_ZERO(zb)						\
 	((zb)->zb_objset == 0 && (zb)->zb_object == 0 &&	\
 	(zb)->zb_level == 0 && (zb)->zb_blkid == 0)
@@ -599,8 +593,10 @@ extern void zfs_ereport_post_checksum(spa_t *spa, vdev_t *vd,
 extern void spa_handle_ignored_writes(spa_t *spa);
 
 /* zbookmark_phys functions */
-boolean_t zbookmark_is_before(const struct dnode_phys *dnp,
-    const zbookmark_phys_t *zb1, const zbookmark_phys_t *zb2);
+boolean_t zbookmark_subtree_completed(const struct dnode_phys *dnp,
+    const zbookmark_phys_t *subtree_root, const zbookmark_phys_t *last_block);
+int zbookmark_compare(uint16_t dbss1, uint8_t ibs1, uint16_t dbss2,
+    uint8_t ibs2, const zbookmark_phys_t *zb1, const zbookmark_phys_t *zb2);
 
 #ifdef	__cplusplus
 }
diff --git a/include/sys/zio_checksum.h b/include/sys/zio_checksum.h
index 56b83b559..9fcfd521f 100644
--- a/include/sys/zio_checksum.h
+++ b/include/sys/zio_checksum.h
@@ -44,7 +44,7 @@ typedef const struct zio_checksum_info {
 	zio_checksum_func_t *ci_func[2]; /* checksum function per byteorder */
 	int		ci_correctable;	/* number of correctable bits	*/
 	int		ci_eck;		/* uses zio embedded checksum? */
-	int		ci_dedup;	/* strong enough for dedup? */
+	boolean_t	ci_dedup;	/* strong enough for dedup? */
 	char		*ci_name;	/* descriptive name */
 } zio_checksum_info_t;
 
diff --git a/include/sys/zio_priority.h b/include/sys/zio_priority.h
new file mode 100644
index 000000000..e33b9585b
--- /dev/null
+++ b/include/sys/zio_priority.h
@@ -0,0 +1,40 @@
+/*
+ * CDDL HEADER START
+ *
+ * This file and its contents are supplied under the terms of the
+ * Common Development and Distribution License ("CDDL"), version 1.0.
+ * You may only use this file in accordance with the terms of version
+ * 1.0 of the CDDL.
+ *
+ * A full copy of the text of the CDDL should have accompanied this
+ * source.  A copy of the CDDL is also available via the Internet at
+ * http://www.illumos.org/license/CDDL.
+ *
+ * CDDL HEADER END
+ */
+/*
+ * Copyright (c) 2014 by Delphix. All rights reserved.
+ */
+#ifndef	_ZIO_PRIORITY_H
+#define	_ZIO_PRIORITY_H
+
+#ifdef	__cplusplus
+extern "C" {
+#endif
+
+typedef enum zio_priority {
+	ZIO_PRIORITY_SYNC_READ,
+	ZIO_PRIORITY_SYNC_WRITE,	/* ZIL */
+	ZIO_PRIORITY_ASYNC_READ,	/* prefetch */
+	ZIO_PRIORITY_ASYNC_WRITE,	/* spa_sync() */
+	ZIO_PRIORITY_SCRUB,		/* asynchronous scrub/resilver reads */
+	ZIO_PRIORITY_NUM_QUEUEABLE,
+
+	ZIO_PRIORITY_NOW		/* non-queued i/os (e.g. free) */
+} zio_priority_t;
+
+#ifdef	__cplusplus
+}
+#endif
+
+#endif	/* _ZIO_PRIORITY_H */