[2.2] Various backports for the 2.2 release

META

@@ -2,7 +2,7 @@ Meta:          1
 Name:          zfs
 Branch:        1.0
 Version:       2.2.0
-Release:       rc1
+Release:       rc2
 Release-Tags:  relext
 License:       CDDL
 Author:        OpenZFS

cmd/zed/agents/zfs_retire.c

@@ -416,6 +416,11 @@ zfs_retire_recv(fmd_hdl_t *hdl, fmd_event_t *ep, nvlist_t *nvl,
 		    FM_EREPORT_PAYLOAD_ZFS_VDEV_GUID, &vdev_guid) != 0)
 			return;
 
+		if (vdev_guid == 0) {
+			fmd_hdl_debug(hdl, "Got a zero GUID");
+			return;
+		}
+
 		if (spare) {
 			int nspares = find_and_remove_spares(zhdl, vdev_guid);
 			fmd_hdl_debug(hdl, "%d spares removed", nspares);

config/Shellcheck.am

@@ -4,6 +4,7 @@
 # Not following: a was not specified as input (see shellcheck -x). [SC1091]
 # Prefer putting braces around variable references even when not strictly required. [SC2250]
 # Consider invoking this command separately to avoid masking its return value (or use '|| true' to ignore). [SC2312]
+# Command appears to be unreachable. Check usage (or ignore if invoked indirectly). [SC2317]
 # In POSIX sh, 'local' is undefined. [SC2039] # older ShellCheck versions
 # In POSIX sh, 'local' is undefined. [SC3043] # newer ShellCheck versions
 
@@ -18,7 +19,7 @@ PHONY += shellcheck
 _STGT = $(subst ^,/,$(subst shellcheck-here-,,$@))
 shellcheck-here-%:
 if HAVE_SHELLCHECK
-	shellcheck --format=gcc --enable=all --exclude=SC1090,SC1091,SC2039,SC2250,SC2312,SC3043 $$([ -n "$(SHELLCHECK_SHELL)" ] && echo "--shell=$(SHELLCHECK_SHELL)") "$$([ -e "$(_STGT)" ] || echo "$(srcdir)/")$(_STGT)"
+	shellcheck --format=gcc --enable=all --exclude=SC1090,SC1091,SC2039,SC2250,SC2312,SC2317,SC3043 $$([ -n "$(SHELLCHECK_SHELL)" ] && echo "--shell=$(SHELLCHECK_SHELL)") "$$([ -e "$(_STGT)" ] || echo "$(srcdir)/")$(_STGT)"
 else
 	@echo "skipping shellcheck of" $(_STGT) "because shellcheck is not installed"
 endif

config/kernel-blkdev.m4

@@ -103,6 +103,33 @@ AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_CHECK_DISK_CHANGE], [
 	])
 ])
 
+dnl #
+dnl # 6.5.x API change
+dnl # disk_check_media_change() was added
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_DISK_CHECK_MEDIA_CHANGE], [
+	ZFS_LINUX_TEST_SRC([disk_check_media_change], [
+		#include <linux/fs.h>
+		#include <linux/blkdev.h>
+	], [
+		struct block_device *bdev = NULL;
+		bool error;
+
+		error = disk_check_media_change(bdev->bd_disk);
+	])
+])
+
+AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_DISK_CHECK_MEDIA_CHANGE], [
+	AC_MSG_CHECKING([whether disk_check_media_change() exists])
+	ZFS_LINUX_TEST_RESULT([disk_check_media_change], [
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_DISK_CHECK_MEDIA_CHANGE, 1,
+		    [disk_check_media_change() exists])
+	], [
+		AC_MSG_RESULT(no)
+	])
+])
+
 dnl #
 dnl # bdev_kobj() is introduced from 5.12
 dnl #
@@ -443,6 +470,29 @@ AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_GET_ERESTARTSYS], [
 	])
 ])
 
+dnl #
+dnl # 6.5.x API change
+dnl # BLK_STS_NEXUS replaced with BLK_STS_RESV_CONFLICT
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_BLK_STS_RESV_CONFLICT], [
+	ZFS_LINUX_TEST_SRC([blk_sts_resv_conflict], [
+		#include <linux/blkdev.h>
+	],[
+		blk_status_t s __attribute__ ((unused)) = BLK_STS_RESV_CONFLICT;
+	])
+])
+
+AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_BLK_STS_RESV_CONFLICT], [
+	AC_MSG_CHECKING([whether BLK_STS_RESV_CONFLICT is defined])
+		ZFS_LINUX_TEST_RESULT([blk_sts_resv_conflict], [
+			AC_DEFINE(HAVE_BLK_STS_RESV_CONFLICT, 1, [BLK_STS_RESV_CONFLICT is defined])
+			AC_MSG_RESULT(yes)
+		], [
+			AC_MSG_RESULT(no)
+		])
+	])
+])
+
 AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV], [
 	ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH
 	ZFS_AC_KERNEL_SRC_BLKDEV_PUT
@@ -458,6 +508,8 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV], [
 	ZFS_AC_KERNEL_SRC_BLKDEV_ISSUE_SECURE_ERASE
 	ZFS_AC_KERNEL_SRC_BLKDEV_BDEV_KOBJ
 	ZFS_AC_KERNEL_SRC_BLKDEV_PART_TO_DEV
+	ZFS_AC_KERNEL_SRC_BLKDEV_DISK_CHECK_MEDIA_CHANGE
+	ZFS_AC_KERNEL_SRC_BLKDEV_BLK_STS_RESV_CONFLICT
 ])
 
 AC_DEFUN([ZFS_AC_KERNEL_BLKDEV], [
@@ -476,4 +528,6 @@ AC_DEFUN([ZFS_AC_KERNEL_BLKDEV], [
 	ZFS_AC_KERNEL_BLKDEV_ISSUE_SECURE_ERASE
 	ZFS_AC_KERNEL_BLKDEV_BDEV_KOBJ
 	ZFS_AC_KERNEL_BLKDEV_PART_TO_DEV
+	ZFS_AC_KERNEL_BLKDEV_DISK_CHECK_MEDIA_CHANGE
+	ZFS_AC_KERNEL_BLKDEV_BLK_STS_RESV_CONFLICT
 ])

contrib/dracut/90zfs/zfs-rollback-bootfs.service.in

@@ -2,7 +2,7 @@
 Description=Rollback bootfs just before it is mounted
 Requisite=zfs-import.target
 After=zfs-import.target dracut-pre-mount.service zfs-snapshot-bootfs.service
-Before=dracut-mount.service
+Before=dracut-mount.service sysroot.mount
 DefaultDependencies=no
 ConditionKernelCommandLine=bootfs.rollback
 ConditionEnvironment=BOOTFS

include/os/freebsd/spl/sys/vnode.h

@@ -36,7 +36,11 @@ struct xucred;
 typedef struct flock	flock64_t;
 typedef	struct vnode	vnode_t;
 typedef	struct vattr	vattr_t;
+#if __FreeBSD_version < 1400093
 typedef enum vtype vtype_t;
+#else
+#define	vtype_t __enum_uint8(vtype)
+#endif
 
 #include <sys/types.h>
 #include <sys/queue.h>

include/os/linux/kernel/linux/blkdev_compat.h

@@ -181,7 +181,11 @@ bi_status_to_errno(blk_status_t status)
 		return (ENOLINK);
 	case BLK_STS_TARGET:
 		return (EREMOTEIO);
+#ifdef HAVE_BLK_STS_RESV_CONFLICT
+	case BLK_STS_RESV_CONFLICT:
+#else
 	case BLK_STS_NEXUS:
+#endif
 		return (EBADE);
 	case BLK_STS_MEDIUM:
 		return (ENODATA);
@@ -215,7 +219,11 @@ errno_to_bi_status(int error)
 	case EREMOTEIO:
 		return (BLK_STS_TARGET);
 	case EBADE:
+#ifdef HAVE_BLK_STS_RESV_CONFLICT
+		return (BLK_STS_RESV_CONFLICT);
+#else
 		return (BLK_STS_NEXUS);
+#endif
 	case ENODATA:
 		return (BLK_STS_MEDIUM);
 	case EILSEQ:
@@ -337,6 +345,8 @@ zfs_check_media_change(struct block_device *bdev)
 	return (0);
 }
 #define	vdev_bdev_reread_part(bdev)	zfs_check_media_change(bdev)
+#elif defined(HAVE_DISK_CHECK_MEDIA_CHANGE)
+#define	vdev_bdev_reread_part(bdev)	disk_check_media_change(bdev->bd_disk)
 #else
 /*
  * This is encountered if check_disk_change() and bdev_check_media_change()

include/os/linux/spl/sys/types.h

@@ -38,7 +38,7 @@ typedef unsigned long		ulong_t;
 typedef unsigned long long	u_longlong_t;
 typedef long long		longlong_t;
 
-typedef unsigned long		intptr_t;
+typedef long			intptr_t;
 typedef unsigned long long	rlim64_t;
 
 typedef struct task_struct	kthread_t;

include/sys/bpobj.h

@@ -60,7 +60,7 @@ typedef struct bpobj {
 	kmutex_t	bpo_lock;
 	objset_t	*bpo_os;
 	uint64_t	bpo_object;
-	int		bpo_epb;
+	uint32_t	bpo_epb;
 	uint8_t		bpo_havecomp;
 	uint8_t		bpo_havesubobj;
 	uint8_t		bpo_havefreed;

include/sys/dmu_zfetch.h

@@ -36,8 +36,6 @@
 extern "C" {
 #endif
 
-extern uint64_t	zfetch_array_rd_sz;
-
 struct dnode;				/* so we can reference dnode */
 
 typedef struct zfetch {

include/sys/fm/fs/zfs.h

@@ -102,8 +102,6 @@ extern "C" {
 #define	FM_EREPORT_PAYLOAD_ZFS_ZIO_TIMESTAMP	"zio_timestamp"
 #define	FM_EREPORT_PAYLOAD_ZFS_ZIO_DELTA	"zio_delta"
 #define	FM_EREPORT_PAYLOAD_ZFS_PREV_STATE	"prev_state"
-#define	FM_EREPORT_PAYLOAD_ZFS_CKSUM_EXPECTED	"cksum_expected"
-#define	FM_EREPORT_PAYLOAD_ZFS_CKSUM_ACTUAL	"cksum_actual"
 #define	FM_EREPORT_PAYLOAD_ZFS_CKSUM_ALGO	"cksum_algorithm"
 #define	FM_EREPORT_PAYLOAD_ZFS_CKSUM_BYTESWAP	"cksum_byteswap"
 #define	FM_EREPORT_PAYLOAD_ZFS_BAD_OFFSET_RANGES "bad_ranges"
@@ -112,8 +110,6 @@ extern "C" {
 #define	FM_EREPORT_PAYLOAD_ZFS_BAD_RANGE_CLEARS	"bad_range_clears"
 #define	FM_EREPORT_PAYLOAD_ZFS_BAD_SET_BITS	"bad_set_bits"
 #define	FM_EREPORT_PAYLOAD_ZFS_BAD_CLEARED_BITS	"bad_cleared_bits"
-#define	FM_EREPORT_PAYLOAD_ZFS_BAD_SET_HISTOGRAM "bad_set_histogram"
-#define	FM_EREPORT_PAYLOAD_ZFS_BAD_CLEARED_HISTOGRAM "bad_cleared_histogram"
 #define	FM_EREPORT_PAYLOAD_ZFS_SNAPSHOT_NAME	"snapshot_name"
 #define	FM_EREPORT_PAYLOAD_ZFS_DEVICE_NAME	"device_name"
 #define	FM_EREPORT_PAYLOAD_ZFS_RAW_DEVICE_NAME	"raw_name"

include/sys/spa.h

@@ -723,16 +723,10 @@ typedef enum spa_mode {
  * Send TRIM commands in-line during normal pool operation while deleting.
  *	OFF: no
  *	ON: yes
- * NB: IN_FREEBSD_BASE is defined within the FreeBSD sources.
  */
 typedef enum {
 	SPA_AUTOTRIM_OFF = 0,	/* default */
 	SPA_AUTOTRIM_ON,
-#ifdef IN_FREEBSD_BASE
-	SPA_AUTOTRIM_DEFAULT = SPA_AUTOTRIM_ON,
-#else
-	SPA_AUTOTRIM_DEFAULT = SPA_AUTOTRIM_OFF,
-#endif
 } spa_autotrim_t;
 
 /*

include/sys/spa_impl.h

@@ -250,6 +250,7 @@ struct spa {
 	uint64_t	spa_min_ashift;		/* of vdevs in normal class */
 	uint64_t	spa_max_ashift;		/* of vdevs in normal class */
 	uint64_t	spa_min_alloc;		/* of vdevs in normal class */
+	uint64_t	spa_gcd_alloc;		/* of vdevs in normal class */
 	uint64_t	spa_config_guid;	/* config pool guid */
 	uint64_t	spa_load_guid;		/* spa_load initialized guid */
 	uint64_t	spa_last_synced_guid;	/* last synced guid */

include/sys/vdev_impl.h

@@ -420,6 +420,7 @@ struct vdev {
 	boolean_t	vdev_copy_uberblocks;  /* post expand copy uberblocks */
 	boolean_t	vdev_resilver_deferred;  /* resilver deferred */
 	boolean_t	vdev_kobj_flag; /* kobj event record */
+	boolean_t	vdev_attaching; /* vdev attach ashift handling */
 	vdev_queue_t	vdev_queue;	/* I/O deadline schedule queue	*/
 	spa_aux_vdev_t	*vdev_aux;	/* for l2cache and spares vdevs	*/
 	zio_t		*vdev_probe_zio; /* root of current probe	*/

include/sys/zio_checksum.h

@@ -94,8 +94,6 @@ typedef const struct zio_checksum_info {
 } zio_checksum_info_t;
 
 typedef struct zio_bad_cksum {
-	zio_cksum_t		zbc_expected;
-	zio_cksum_t		zbc_actual;
 	const char		*zbc_checksum_name;
 	uint8_t			zbc_byteswapped;
 	uint8_t			zbc_injected;

man/man4/zfs.4

@@ -15,7 +15,7 @@
 .\" own identifying information:
 .\" Portions Copyright [yyyy] [name of copyright owner]
 .\"
-.Dd January 10, 2023
+.Dd July 21, 2023
 .Dt ZFS 4
 .Os
 .
@@ -239,6 +239,11 @@ relative to the pool.
 Make some blocks above a certain size be gang blocks.
 This option is used by the test suite to facilitate testing.
 .
+.It Sy metaslab_force_ganging_pct Ns = Ns Sy 3 Ns % Pq uint
+For blocks that could be forced to be a gang block (due to
+.Sy metaslab_force_ganging ) ,
+force this many of them to be gang blocks.
+.
 .It Sy zfs_ddt_zap_default_bs Ns = Ns Sy 15 Po 32 KiB Pc Pq int
 Default DDT ZAP data block size as a power of 2. Note that changing this after
 creating a DDT on the pool will not affect existing DDTs, only newly created
@@ -519,9 +524,6 @@ However, this is limited by
 Maximum micro ZAP size.
 A micro ZAP is upgraded to a fat ZAP, once it grows beyond the specified size.
 .
-.It Sy zfetch_array_rd_sz Ns = Ns Sy 1048576 Ns B Po 1 MiB Pc Pq u64
-If prefetching is enabled, disable prefetching for reads larger than this size.
-.
 .It Sy zfetch_min_distance Ns = Ns Sy 4194304 Ns B Po 4 MiB Pc Pq uint
 Min bytes to prefetch per stream.
 Prefetch distance starts from the demand access size and quickly grows to

man/man8/zpool-events.8

@@ -26,7 +26,7 @@
 .\" Copyright 2017 Nexenta Systems, Inc.
 .\" Copyright (c) 2017 Open-E, Inc. All Rights Reserved.
 .\"
-.Dd May 27, 2021
+.Dd July 11, 2023
 .Dt ZPOOL-EVENTS 8
 .Os
 .
@@ -305,10 +305,6 @@ The time when a given I/O request was submitted.
 The time required to service a given I/O request.
 .It Sy prev_state
 The previous state of the vdev.
-.It Sy cksum_expected
-The expected checksum value for the block.
-.It Sy cksum_actual
-The actual checksum value for an errant block.
 .It Sy cksum_algorithm
 Checksum algorithm used.
 See
@@ -362,23 +358,6 @@ Like
 but contains
 .Pq Ar good data No & ~( Ns Ar bad data ) ;
 that is, the bits set in the good data which are cleared in the bad data.
-.It Sy bad_set_histogram
-If this field exists, it is an array of counters.
-Each entry counts bits set in a particular bit of a big-endian uint64 type.
-The first entry counts bits
-set in the high-order bit of the first byte, the 9th byte, etc, and the last
-entry counts bits set of the low-order bit of the 8th byte, the 16th byte, etc.
-This information is useful for observing a stuck bit in a parallel data path,
-such as IDE or parallel SCSI.
-.It Sy bad_cleared_histogram
-If this field exists, it is an array of counters.
-Each entry counts bit clears in a particular bit of a big-endian uint64 type.
-The first entry counts bits
-clears of the high-order bit of the first byte, the 9th byte, etc, and the
-last entry counts clears of the low-order bit of the 8th byte, the 16th byte,
-etc.
-This information is useful for observing a stuck bit in a parallel data
-path, such as IDE or parallel SCSI.
 .El
 .
 .Sh I/O STAGES

module/os/freebsd/zfs/zfs_vnops_os.c

@@ -6263,7 +6263,8 @@ zfs_freebsd_copy_file_range(struct vop_copy_file_range_args *ap)
 			goto bad_write_fallback;
 		}
 	} else {
-#if __FreeBSD_version >= 1400086
+#if (__FreeBSD_version >= 1302506 && __FreeBSD_version < 1400000) || \
+	__FreeBSD_version >= 1400086
 		vn_lock_pair(invp, false, LK_EXCLUSIVE, outvp, false,
 		    LK_EXCLUSIVE);
 #else

module/os/linux/zfs/zfs_vfsops.c

@@ -1680,6 +1680,7 @@ zfs_umount(struct super_block *sb)
 	}
 
 	zfsvfs_free(zfsvfs);
+	sb->s_fs_info = NULL;
 	return (0);
 }