Merge pull request #169 from truenas/zfs-2.2-release-sync-cobia-release

Sync with Upstream zfs-2.2-release

META

@@ -6,5 +6,5 @@ Release:       rc4
 Release-Tags:  relext
 License:       CDDL
 Author:        OpenZFS
-Linux-Maximum: 6.4
+Linux-Maximum: 6.5
 Linux-Minimum: 3.10

cmd/zed/agents/zfs_mod.c

@@ -374,6 +374,7 @@ zfs_process_add(zpool_handle_t *zhp, nvlist_t *vdev, boolean_t labeled)
 	/* Only autoreplace bad disks */
 	if ((vs->vs_state != VDEV_STATE_DEGRADED) &&
 	    (vs->vs_state != VDEV_STATE_FAULTED) &&
+	    (vs->vs_state != VDEV_STATE_REMOVED) &&
 	    (vs->vs_state != VDEV_STATE_CANT_OPEN)) {
 		zed_log_msg(LOG_INFO, "  not autoreplacing since disk isn't in "
 		    "a bad state (currently %llu)", vs->vs_state);

cmd/zed/zed.d/statechange-led.sh

@@ -121,7 +121,7 @@ state_to_val()
 {
 	state="$1"
 	case "$state" in
-		FAULTED|DEGRADED|UNAVAIL)
+		FAULTED|DEGRADED|UNAVAIL|REMOVED)
 			echo 1
 			;;
 		ONLINE)

cmd/zfs/zfs_main.c

@@ -132,6 +132,8 @@ static int zfs_do_zone(int argc, char **argv);
 static int zfs_do_unzone(int argc, char **argv);
 #endif
 
+static int zfs_do_help(int argc, char **argv);
+
 /*
  * Enable a reasonable set of defaults for libumem debugging on DEBUG builds.
  */
@@ -606,6 +608,9 @@ usage(boolean_t requested)
 		(void) fprintf(fp,
 		    gettext("\nFor the delegated permission list, run: %s\n"),
 		    "zfs allow|unallow");
+		(void) fprintf(fp,
+		    gettext("\nFor further help on a command or topic, "
+		    "run: %s\n"), "zfs help [<topic>]");
 	}
 
 	/*
@@ -8726,6 +8731,25 @@ zfs_do_version(int argc, char **argv)
 	return (zfs_version_print() != 0);
 }
 
+/* Display documentation */
+static int
+zfs_do_help(int argc, char **argv)
+{
+	char page[MAXNAMELEN];
+	if (argc < 3 || strcmp(argv[2], "zfs") == 0)
+		strcpy(page, "zfs");
+	else if (strcmp(argv[2], "concepts") == 0 ||
+	    strcmp(argv[2], "props") == 0)
+		snprintf(page, sizeof (page), "zfs%s", argv[2]);
+	else
+		snprintf(page, sizeof (page), "zfs-%s", argv[2]);
+
+	execlp("man", "man", page, NULL);
+
+	fprintf(stderr, "couldn't run man program: %s", strerror(errno));
+	return (-1);
+}
+
 int
 main(int argc, char **argv)
 {
@@ -8781,6 +8805,12 @@ main(int argc, char **argv)
 	if ((strcmp(cmdname, "-V") == 0) || (strcmp(cmdname, "--version") == 0))
 		return (zfs_do_version(argc, argv));
 
+	/*
+	 * Special case 'help'
+	 */
+	if (strcmp(cmdname, "help") == 0)
+		return (zfs_do_help(argc, argv));
+
 	if ((g_zfs = libzfs_init()) == NULL) {
 		(void) fprintf(stderr, "%s\n", libzfs_error_init(errno));
 		return (1);

cmd/zpool/zpool_main.c

@@ -126,6 +126,8 @@ static int zpool_do_version(int, char **);
 
 static int zpool_do_wait(int, char **);
 
+static int zpool_do_help(int argc, char **argv);
+
 static zpool_compat_status_t zpool_do_load_compat(
     const char *, boolean_t *);
 
@@ -538,6 +540,10 @@ usage(boolean_t requested)
 				(void) fprintf(fp, "%s",
 				    get_usage(command_table[i].usage));
 		}
+
+		(void) fprintf(fp,
+		    gettext("\nFor further help on a command or topic, "
+		    "run: %s\n"), "zpool help [<topic>]");
 	} else {
 		(void) fprintf(fp, gettext("usage:\n"));
 		(void) fprintf(fp, "%s", get_usage(current_command->usage));
@@ -11051,6 +11057,25 @@ zpool_do_version(int argc, char **argv)
 	return (zfs_version_print() != 0);
 }
 
+/* Display documentation */
+static int
+zpool_do_help(int argc, char **argv)
+{
+	char page[MAXNAMELEN];
+	if (argc < 3 || strcmp(argv[2], "zpool") == 0)
+		strcpy(page, "zpool");
+	else if (strcmp(argv[2], "concepts") == 0 ||
+	    strcmp(argv[2], "props") == 0)
+		snprintf(page, sizeof (page), "zpool%s", argv[2]);
+	else
+		snprintf(page, sizeof (page), "zpool-%s", argv[2]);
+
+	execlp("man", "man", page, NULL);
+
+	fprintf(stderr, "couldn't run man program: %s", strerror(errno));
+	return (-1);
+}
+
 /*
  * Do zpool_load_compat() and print error message on failure
  */
@@ -11118,6 +11143,12 @@ main(int argc, char **argv)
 	if ((strcmp(cmdname, "-V") == 0) || (strcmp(cmdname, "--version") == 0))
 		return (zpool_do_version(argc, argv));
 
+	/*
+	 * Special case 'help'
+	 */
+	if (strcmp(cmdname, "help") == 0)
+		return (zpool_do_help(argc, argv));
+
 	if ((g_zfs = libzfs_init()) == NULL) {
 		(void) fprintf(stderr, "%s\n", libzfs_error_init(errno));
 		return (1);

cmd/ztest.c

@@ -2457,8 +2457,7 @@ ztest_get_data(void *arg, uint64_t arg2, lr_write_t *lr, char *buf,
 		zgd->zgd_lr = (struct zfs_locked_range *)ztest_range_lock(zd,
 		    object, offset, size, RL_READER);
 
-		error = dmu_buf_hold(os, object, offset, zgd, &db,
+		error = dmu_buf_hold_noread(os, object, offset, zgd, &db);
-		    DMU_READ_NO_PREFETCH);
 
 		if (error == 0) {
 			blkptr_t *bp = &lr->lr_blkptr;
@@ -3767,7 +3766,7 @@ ztest_vdev_attach_detach(ztest_ds_t *zd, uint64_t id)
 	else if (ashift > oldvd->vdev_top->vdev_ashift)
 		expected_error = EDOM;
 	else if (newvd_is_dspare && pvd != vdev_draid_spare_get_parent(newvd))
-		expected_error = ENOTSUP;
+		expected_error = EINVAL;
 	else
 		expected_error = 0;
 
@@ -6379,6 +6378,7 @@ ztest_reguid(ztest_ds_t *zd, uint64_t id)
 	spa_t *spa = ztest_spa;
 	uint64_t orig, load;
 	int error;
+	ztest_shared_t *zs = ztest_shared;
 
 	if (ztest_opts.zo_mmp_test)
 		return;
@@ -6388,6 +6388,7 @@ ztest_reguid(ztest_ds_t *zd, uint64_t id)
 
 	(void) pthread_rwlock_wrlock(&ztest_name_lock);
 	error = spa_change_guid(spa);
+	zs->zs_guid = spa_guid(spa);
 	(void) pthread_rwlock_unlock(&ztest_name_lock);
 
 	if (error != 0)
@@ -6917,7 +6918,7 @@ ztest_trim(ztest_ds_t *zd, uint64_t id)
  * Verify pool integrity by running zdb.
  */
 static void
-ztest_run_zdb(const char *pool)
+ztest_run_zdb(uint64_t guid)
 {
 	int status;
 	char *bin;
@@ -6941,13 +6942,13 @@ ztest_run_zdb(const char *pool)
 	free(set_gvars_args);
 
 	size_t would = snprintf(zdb, len,
-	    "%s -bcc%s%s -G -d -Y -e -y %s -p %s %s",
+	    "%s -bcc%s%s -G -d -Y -e -y %s -p %s %"PRIu64,
 	    bin,
 	    ztest_opts.zo_verbose >= 3 ? "s" : "",
 	    ztest_opts.zo_verbose >= 4 ? "v" : "",
 	    set_gvars_args_joined,
 	    ztest_opts.zo_dir,
-	    pool);
+	    guid);
 	ASSERT3U(would, <, len);
 
 	umem_free(set_gvars_args_joined, strlen(set_gvars_args_joined) + 1);
@@ -7525,14 +7526,15 @@ ztest_import(ztest_shared_t *zs)
 	VERIFY0(spa_open(ztest_opts.zo_pool, &spa, FTAG));
 	zs->zs_metaslab_sz =
 	    1ULL << spa->spa_root_vdev->vdev_child[0]->vdev_ms_shift;
+	zs->zs_guid = spa_guid(spa);
 	spa_close(spa, FTAG);
 
 	kernel_fini();
 
 	if (!ztest_opts.zo_mmp_test) {
-		ztest_run_zdb(ztest_opts.zo_pool);
+		ztest_run_zdb(zs->zs_guid);
 		ztest_freeze();
-		ztest_run_zdb(ztest_opts.zo_pool);
+		ztest_run_zdb(zs->zs_guid);
 	}
 
 	(void) pthread_rwlock_destroy(&ztest_name_lock);
@@ -7603,7 +7605,6 @@ ztest_run(ztest_shared_t *zs)
 	dsl_pool_config_enter(dmu_objset_pool(os), FTAG);
 	dmu_objset_fast_stat(os, &dds);
 	dsl_pool_config_exit(dmu_objset_pool(os), FTAG);
-	zs->zs_guid = dds.dds_guid;
 	dmu_objset_disown(os, B_TRUE, FTAG);
 
 	/*
@@ -7874,14 +7875,15 @@ ztest_init(ztest_shared_t *zs)
 	VERIFY0(spa_open(ztest_opts.zo_pool, &spa, FTAG));
 	zs->zs_metaslab_sz =
 	    1ULL << spa->spa_root_vdev->vdev_child[0]->vdev_ms_shift;
+	zs->zs_guid = spa_guid(spa);
 	spa_close(spa, FTAG);
 
 	kernel_fini();
 
 	if (!ztest_opts.zo_mmp_test) {
-		ztest_run_zdb(ztest_opts.zo_pool);
+		ztest_run_zdb(zs->zs_guid);
 		ztest_freeze();
-		ztest_run_zdb(ztest_opts.zo_pool);
+		ztest_run_zdb(zs->zs_guid);
 	}
 
 	(void) pthread_rwlock_destroy(&ztest_name_lock);
@@ -8304,7 +8306,7 @@ main(int argc, char **argv)
 		}
 
 		if (!ztest_opts.zo_mmp_test)
-			ztest_run_zdb(ztest_opts.zo_pool);
+			ztest_run_zdb(zs->zs_guid);
 	}
 
 	if (ztest_opts.zo_verbose >= 1) {

config/kernel-blkdev.m4

@@ -16,12 +16,63 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH], [
 	])
 ])
 
+dnl #
+dnl # 6.5.x API change,
+dnl # blkdev_get_by_path() takes 4 args
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH_4ARG], [
+	ZFS_LINUX_TEST_SRC([blkdev_get_by_path_4arg], [
+		#include <linux/fs.h>
+		#include <linux/blkdev.h>
+	], [
+		struct block_device *bdev __attribute__ ((unused)) = NULL;
+		const char *path = "path";
+		fmode_t mode = 0;
+		void *holder = NULL;
+		struct blk_holder_ops h;
+
+		bdev = blkdev_get_by_path(path, mode, holder, &h);
+	])
+])
+
 AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_GET_BY_PATH], [
-	AC_MSG_CHECKING([whether blkdev_get_by_path() exists])
+	AC_MSG_CHECKING([whether blkdev_get_by_path() exists and takes 3 args])
 	ZFS_LINUX_TEST_RESULT([blkdev_get_by_path], [
 		AC_MSG_RESULT(yes)
 	], [
-		ZFS_LINUX_TEST_ERROR([blkdev_get_by_path()])
+		AC_MSG_RESULT(no)
+		AC_MSG_CHECKING([whether blkdev_get_by_path() exists and takes 4 args])
+		ZFS_LINUX_TEST_RESULT([blkdev_get_by_path_4arg], [
+			AC_DEFINE(HAVE_BLKDEV_GET_BY_PATH_4ARG, 1,
+				[blkdev_get_by_path() exists and takes 4 args])
+			AC_MSG_RESULT(yes)
+		], [
+			ZFS_LINUX_TEST_ERROR([blkdev_get_by_path()])
+		])
+	])
+])
+
+dnl #
+dnl # 6.5.x API change
+dnl # blk_mode_t was added as a type to supercede some places where fmode_t
+dnl # is used
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_BLK_MODE_T], [
+	ZFS_LINUX_TEST_SRC([blk_mode_t], [
+		#include <linux/fs.h>
+		#include <linux/blkdev.h>
+	], [
+		blk_mode_t m __attribute((unused)) = (blk_mode_t)0;
+	])
+])
+
+AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_BLK_MODE_T], [
+	AC_MSG_CHECKING([whether blk_mode_t is defined])
+	ZFS_LINUX_TEST_RESULT([blk_mode_t], [
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_BLK_MODE_T, 1, [blk_mode_t is defined])
+	], [
+		AC_MSG_RESULT(no)
 	])
 ])
 
@@ -41,12 +92,35 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_PUT], [
 	])
 ])
 
+dnl #
+dnl # 6.5.x API change.
+dnl # blkdev_put() takes (void* holder) as arg 2
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV_PUT_HOLDER], [
+	ZFS_LINUX_TEST_SRC([blkdev_put_holder], [
+		#include <linux/fs.h>
+		#include <linux/blkdev.h>
+	], [
+		struct block_device *bdev = NULL;
+		void *holder = NULL;
+
+		blkdev_put(bdev, holder);
+	])
+])
+
 AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_PUT], [
 	AC_MSG_CHECKING([whether blkdev_put() exists])
 	ZFS_LINUX_TEST_RESULT([blkdev_put], [
 		AC_MSG_RESULT(yes)
 	], [
-		ZFS_LINUX_TEST_ERROR([blkdev_put()])
+		AC_MSG_CHECKING([whether blkdev_put() accepts void* as arg 2])
+		ZFS_LINUX_TEST_RESULT([blkdev_put_holder], [
+			AC_MSG_RESULT(yes)
+			AC_DEFINE(HAVE_BLKDEV_PUT_HOLDER, 1,
+				[blkdev_put() accepts void* as arg 2])
+		], [
+			ZFS_LINUX_TEST_ERROR([blkdev_put()])
+		])
 	])
 ])
 
@@ -495,7 +569,9 @@ AC_DEFUN([ZFS_AC_KERNEL_BLKDEV_BLK_STS_RESV_CONFLICT], [
 
 AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV], [
 	ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH
+	ZFS_AC_KERNEL_SRC_BLKDEV_GET_BY_PATH_4ARG
 	ZFS_AC_KERNEL_SRC_BLKDEV_PUT
+	ZFS_AC_KERNEL_SRC_BLKDEV_PUT_HOLDER
 	ZFS_AC_KERNEL_SRC_BLKDEV_REREAD_PART
 	ZFS_AC_KERNEL_SRC_BLKDEV_INVALIDATE_BDEV
 	ZFS_AC_KERNEL_SRC_BLKDEV_LOOKUP_BDEV
@@ -510,6 +586,7 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLKDEV], [
 	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
+	ZFS_AC_KERNEL_SRC_BLKDEV_BLK_MODE_T
 ])
 
 AC_DEFUN([ZFS_AC_KERNEL_BLKDEV], [
@@ -530,4 +607,5 @@ AC_DEFUN([ZFS_AC_KERNEL_BLKDEV], [
 	ZFS_AC_KERNEL_BLKDEV_PART_TO_DEV
 	ZFS_AC_KERNEL_BLKDEV_DISK_CHECK_MEDIA_CHANGE
 	ZFS_AC_KERNEL_BLKDEV_BLK_STS_RESV_CONFLICT
+	ZFS_AC_KERNEL_BLKDEV_BLK_MODE_T
 ])

config/kernel-block-device-operations.m4

@@ -49,12 +49,42 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_VOID], [
 	], [], [])
 ])
 
+dnl #
+dnl # 5.9.x API change
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG], [
+	ZFS_LINUX_TEST_SRC([block_device_operations_release_void_1arg], [
+		#include <linux/blkdev.h>
+
+		void blk_release(struct gendisk *g) {
+			(void) g;
+			return;
+		}
+
+		static const struct block_device_operations
+		    bops __attribute__ ((unused)) = {
+			.open		= NULL,
+			.release	= blk_release,
+			.ioctl		= NULL,
+			.compat_ioctl	= NULL,
+		};
+	], [], [])
+])
+
 AC_DEFUN([ZFS_AC_KERNEL_BLOCK_DEVICE_OPERATIONS_RELEASE_VOID], [
-	AC_MSG_CHECKING([whether bops->release() is void])
+	AC_MSG_CHECKING([whether bops->release() is void and takes 2 args])
 	ZFS_LINUX_TEST_RESULT([block_device_operations_release_void], [
 		AC_MSG_RESULT(yes)
 	],[
-		ZFS_LINUX_TEST_ERROR([bops->release()])
+		AC_MSG_RESULT(no)
+		AC_MSG_CHECKING([whether bops->release() is void and takes 1 arg])
+		ZFS_LINUX_TEST_RESULT([block_device_operations_release_void_1arg], [
+			AC_MSG_RESULT(yes)
+			AC_DEFINE([HAVE_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG], [1],
+				[Define if release() in block_device_operations takes 1 arg])
+		],[
+			ZFS_LINUX_TEST_ERROR([bops->release()])
+		])
 	])
 ])
 
@@ -92,6 +122,7 @@ AC_DEFUN([ZFS_AC_KERNEL_BLOCK_DEVICE_OPERATIONS_REVALIDATE_DISK], [
 AC_DEFUN([ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS], [
 	ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_CHECK_EVENTS
 	ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_VOID
+	ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG
 	ZFS_AC_KERNEL_SRC_BLOCK_DEVICE_OPERATIONS_REVALIDATE_DISK
 ])
 

config/kernel-filemap-splice-read.m4

@@ -0,0 +1,25 @@
+AC_DEFUN([ZFS_AC_KERNEL_SRC_COPY_SPLICE_READ], [
+	dnl #
+	dnl # Kernel 6.5 - generic_file_splice_read was removed in favor
+	dnl # of copy_splice_read for the .splice_read member of the
+	dnl # file_operations struct.
+	dnl #
+	ZFS_LINUX_TEST_SRC([has_copy_splice_read], [
+		#include <linux/fs.h>
+
+		struct file_operations fops __attribute__((unused)) = {
+			.splice_read = copy_splice_read,
+		};
+	],[])
+])
+
+AC_DEFUN([ZFS_AC_KERNEL_COPY_SPLICE_READ], [
+	AC_MSG_CHECKING([whether copy_splice_read() exists])
+	ZFS_LINUX_TEST_RESULT([has_copy_splice_read], [
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_COPY_SPLICE_READ, 1,
+		    [copy_splice_read exists])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])

config/kernel-register_sysctl_table.m4

@@ -0,0 +1,27 @@
+dnl #
+dnl # Linux 6.5 removes register_sysctl_table
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SRC_REGISTER_SYSCTL_TABLE], [
+	ZFS_LINUX_TEST_SRC([has_register_sysctl_table], [
+		#include <linux/sysctl.h>
+
+		static struct ctl_table dummy_table[] = {
+			{}
+		};
+
+    ],[
+		struct ctl_table_header *h
+			__attribute((unused)) = register_sysctl_table(dummy_table);
+    ])
+])
+
+AC_DEFUN([ZFS_AC_KERNEL_REGISTER_SYSCTL_TABLE], [
+	AC_MSG_CHECKING([whether register_sysctl_table exists])
+	ZFS_LINUX_TEST_RESULT([has_register_sysctl_table], [
+		AC_MSG_RESULT([yes])
+		AC_DEFINE(HAVE_REGISTER_SYSCTL_TABLE, 1,
+			[register_sysctl_table exists])
+	],[
+		AC_MSG_RESULT([no])
+	])
+])

config/kernel-vfs-iov_iter.m4

@@ -6,8 +6,7 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_VFS_IOV_ITER], [
 		#include <linux/fs.h>
 		#include <linux/uio.h>
 	],[
-		int type __attribute__ ((unused)) =
+		int type __attribute__ ((unused)) = ITER_KVEC;
-		    ITER_IOVEC | ITER_KVEC | ITER_BVEC | ITER_PIPE;
 	])
 
 	ZFS_LINUX_TEST_SRC([iov_iter_advance], [
@@ -93,6 +92,14 @@ AC_DEFUN([ZFS_AC_KERNEL_SRC_VFS_IOV_ITER], [
 		struct iov_iter iter = { 0 };
 		__attribute__((unused)) enum iter_type i = iov_iter_type(&iter);
 	])
+
+	ZFS_LINUX_TEST_SRC([iter_iov], [
+		#include <linux/fs.h>
+		#include <linux/uio.h>
+	],[
+		struct iov_iter iter = { 0 };
+		__attribute__((unused)) const struct iovec *iov = iter_iov(&iter);
+	])
 ])
 
 AC_DEFUN([ZFS_AC_KERNEL_VFS_IOV_ITER], [
@@ -201,4 +208,19 @@ AC_DEFUN([ZFS_AC_KERNEL_VFS_IOV_ITER], [
 		AC_DEFINE(HAVE_VFS_IOV_ITER, 1,
 		    [All required iov_iter interfaces are available])
 	])
+
+	dnl #
+	dnl # Kernel 6.5 introduces the iter_iov() function that returns the
+	dnl # __iov member of an iov_iter*. The iov member was renamed to this
+	dnl # __iov member, and is intended to be accessed via the helper
+	dnl # function now.
+	dnl #
+	AC_MSG_CHECKING([whether iter_iov() is available])
+	ZFS_LINUX_TEST_RESULT([iter_iov], [
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_ITER_IOV, 1,
+		    [iter_iov() is available])
+	],[
+		AC_MSG_RESULT(no)
+	])
 ])

config/kernel.m4

@@ -160,6 +160,8 @@ AC_DEFUN([ZFS_AC_KERNEL_TEST_SRC], [
 	ZFS_AC_KERNEL_SRC_FILEMAP
 	ZFS_AC_KERNEL_SRC_WRITEPAGE_T
 	ZFS_AC_KERNEL_SRC_RECLAIMED
+	ZFS_AC_KERNEL_SRC_REGISTER_SYSCTL_TABLE
+	ZFS_AC_KERNEL_SRC_COPY_SPLICE_READ
 	case "$host_cpu" in
 		powerpc*)
 			ZFS_AC_KERNEL_SRC_CPU_HAS_FEATURE
@@ -299,6 +301,8 @@ AC_DEFUN([ZFS_AC_KERNEL_TEST_RESULT], [
 	ZFS_AC_KERNEL_FILEMAP
 	ZFS_AC_KERNEL_WRITEPAGE_T
 	ZFS_AC_KERNEL_RECLAIMED
+	ZFS_AC_KERNEL_REGISTER_SYSCTL_TABLE
+	ZFS_AC_KERNEL_COPY_SPLICE_READ
 	case "$host_cpu" in
 		powerpc*)
 			ZFS_AC_KERNEL_CPU_HAS_FEATURE

include/os/freebsd/zfs/sys/zfs_vfsops_os.h

@@ -93,7 +93,6 @@ struct zfsvfs {
 	zfs_teardown_lock_t z_teardown_lock;
 	zfs_teardown_inactive_lock_t z_teardown_inactive_lock;
 	list_t		z_all_znodes;	/* all vnodes in the fs */
-	uint64_t	z_nr_znodes;	/* number of znodes in the fs */
 	kmutex_t	z_znodes_lock;	/* lock for z_all_znodes */
 	struct zfsctl_root	*z_ctldir;	/* .zfs directory pointer */
 	boolean_t	z_show_ctldir;	/* expose .zfs in the root dir */

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

@@ -347,6 +347,7 @@ zfs_check_media_change(struct block_device *bdev)
 #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)
+#define	zfs_check_media_change(bdev)	disk_check_media_change(bdev->bd_disk)
 #else
 /*
  * This is encountered if check_disk_change() and bdev_check_media_change()
@@ -397,6 +398,12 @@ vdev_lookup_bdev(const char *path, dev_t *dev)
 #endif
 }
 
+#if defined(HAVE_BLK_MODE_T)
+#define	blk_mode_is_open_write(flag)	((flag) & BLK_OPEN_WRITE)
+#else
+#define	blk_mode_is_open_write(flag)	((flag) & FMODE_WRITE)
+#endif
+
 /*
  * Kernels without bio_set_op_attrs use bi_rw for the bio flags.
  */

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

@@ -173,4 +173,16 @@ zfs_uio_iov_iter_init(zfs_uio_t *uio, struct iov_iter *iter, offset_t offset,
 }
 #endif
 
+#if defined(HAVE_ITER_IOV)
+#define	zfs_uio_iter_iov(iter)	iter_iov((iter))
+#else
+#define	zfs_uio_iter_iov(iter)	(iter)->iov
+#endif
+
+#if defined(HAVE_IOV_ITER_TYPE)
+#define	zfs_uio_iov_iter_type(iter)	iov_iter_type((iter))
+#else
+#define	zfs_uio_iov_iter_type(iter)	(iter)->type
+#endif
+
 #endif /* SPL_UIO_H */

include/os/linux/zfs/sys/zfs_vfsops_os.h

@@ -105,7 +105,6 @@ struct zfsvfs {
 	rrmlock_t	z_teardown_lock;
 	krwlock_t	z_teardown_inactive_lock;
 	list_t		z_all_znodes;	/* all znodes in the fs */
-	uint64_t	z_nr_znodes;	/* number of znodes in the fs */
 	unsigned long	z_rollback_time; /* last online rollback time */
 	unsigned long	z_snap_defer_time; /* last snapshot unmount deferral */
 	kmutex_t	z_znodes_lock;	/* lock for z_all_znodes */

lib/libzfs/libzfs_pool.c

@@ -29,7 +29,7 @@
  * Copyright (c) 2017, Intel Corporation.
  * Copyright (c) 2018, loli10K <ezomori.nozomu@gmail.com>
  * Copyright (c) 2021, Colm Buckley <colm@tuatha.org>
- * Copyright (c) 2021, Klara Inc.
+ * Copyright (c) 2021, 2023, Klara Inc.
  */
 
 #include <errno.h>
@@ -255,6 +255,7 @@ zpool_get_state_str(zpool_handle_t *zhp)
 	if (zpool_get_state(zhp) == POOL_STATE_UNAVAIL) {
 		str = gettext("FAULTED");
 	} else if (status == ZPOOL_STATUS_IO_FAILURE_WAIT ||
+	    status == ZPOOL_STATUS_IO_FAILURE_CONTINUE ||
 	    status == ZPOOL_STATUS_IO_FAILURE_MMP) {
 		str = gettext("SUSPENDED");
 	} else {

lib/libzfs_core/libzfs_core.c

@@ -650,10 +650,12 @@ send_worker(void *arg)
 	unsigned int bufsiz = max_pipe_buffer(ctx->from);
 	ssize_t rd;
 
-	while ((rd = splice(ctx->from, NULL, ctx->to, NULL, bufsiz,
+	for (;;) {
-	    SPLICE_F_MOVE | SPLICE_F_MORE)) > 0)
+		rd = splice(ctx->from, NULL, ctx->to, NULL, bufsiz,
-		;
+		    SPLICE_F_MOVE | SPLICE_F_MORE);
-
+		if ((rd == -1 && errno != EINTR) || rd == 0)
+			break;
+	}
 	int err = (rd == -1) ? errno : 0;
 	close(ctx->from);
 	return ((void *)(uintptr_t)err);

man/man7/zpoolconcepts.7

@@ -203,11 +203,9 @@ For more information, see the
 section.
 .El
 .Pp
-Virtual devices cannot be nested, so a mirror or raidz virtual device can only
+Virtual devices cannot be nested arbitrarily.
-contain files or disks.
+A mirror, raidz or draid virtual device can only be created with files or disks.
-Mirrors of mirrors
+Mirrors of mirrors or other such combinations are not allowed.
-.Pq or other combinations
-are not allowed.
 .Pp
 A pool can have any number of virtual devices at the top of the configuration
 .Po known as

module/Makefile.in

@@ -169,4 +169,4 @@ gen-zstd-symbols:
 	for obj in $(addprefix zstd/,$(ZSTD_UPSTREAM_OBJS)); do echo; echo "/* $${obj#zstd/}: */"; @OBJDUMP@ -t $$obj | awk '$$2 == "g" && !/ zfs_/ {print "#define\t" $$6 " zfs_" $$6}' | sort; done >> zstd/include/zstd_compat_wrapper.h
 
 check-zstd-symbols:
-	@OBJDUMP@ -t $(addprefix zstd/,$(ZSTD_UPSTREAM_OBJS)) | awk '/file format/ {print}  $$2 == "g" && !/ zfs_/ {++ret; print}  END {exit ret}'
+	@OBJDUMP@ -t $(addprefix zstd/,$(ZSTD_UPSTREAM_OBJS)) | awk '/file format/ {print}  $$2 == "g" && (!/ zfs_/ && !/ __pfx_zfs_/) {++ret; print}  END {exit ret}'

module/os/freebsd/zfs/zfs_vfsops.c

@@ -1154,7 +1154,6 @@ zfsvfs_free(zfsvfs_t *zfsvfs)
 
 	mutex_destroy(&zfsvfs->z_znodes_lock);
 	mutex_destroy(&zfsvfs->z_lock);
-	ASSERT3U(zfsvfs->z_nr_znodes, ==, 0);
 	list_destroy(&zfsvfs->z_all_znodes);
 	ZFS_TEARDOWN_DESTROY(zfsvfs);
 	ZFS_TEARDOWN_INACTIVE_DESTROY(zfsvfs);
@@ -1558,12 +1557,11 @@ zfsvfs_teardown(zfsvfs_t *zfsvfs, boolean_t unmounting)
 		 * may add the parents of dir-based xattrs to the taskq
 		 * so we want to wait for these.
 		 *
-		 * We can safely read z_nr_znodes without locking because the
+		 * We can safely check z_all_znodes for being empty because the
-		 * VFS has already blocked operations which add to the
+		 * VFS has already blocked operations which add to it.
-		 * z_all_znodes list and thus increment z_nr_znodes.
 		 */
 		int round = 0;
-		while (zfsvfs->z_nr_znodes > 0) {
+		while (!list_is_empty(&zfsvfs->z_all_znodes)) {
 			taskq_wait_outstanding(dsl_pool_zrele_taskq(
 			    dmu_objset_pool(zfsvfs->z_os)), 0);
 			if (++round > 1 && !unmounting)

module/os/freebsd/zfs/zfs_znode.c

@@ -537,7 +537,6 @@ zfs_znode_alloc(zfsvfs_t *zfsvfs, dmu_buf_t *db, int blksz,
 
 	mutex_enter(&zfsvfs->z_znodes_lock);
 	list_insert_tail(&zfsvfs->z_all_znodes, zp);
-	zfsvfs->z_nr_znodes++;
 	zp->z_zfsvfs = zfsvfs;
 	mutex_exit(&zfsvfs->z_znodes_lock);
 
@@ -1286,7 +1285,6 @@ zfs_znode_free(znode_t *zp)
 	mutex_enter(&zfsvfs->z_znodes_lock);
 	POINTER_INVALIDATE(&zp->z_zfsvfs);
 	list_remove(&zfsvfs->z_all_znodes, zp);
-	zfsvfs->z_nr_znodes--;
 	mutex_exit(&zfsvfs->z_znodes_lock);
 
 #if __FreeBSD_version >= 1300139

module/os/linux/spl/spl-proc.c

@@ -47,6 +47,10 @@ static unsigned long table_min = 0;
 static unsigned long table_max = ~0;
 
 static struct ctl_table_header *spl_header = NULL;
+#ifndef HAVE_REGISTER_SYSCTL_TABLE
+static struct ctl_table_header *spl_kmem = NULL;
+static struct ctl_table_header *spl_kstat = NULL;
+#endif
 static struct proc_dir_entry *proc_spl = NULL;
 static struct proc_dir_entry *proc_spl_kmem = NULL;
 static struct proc_dir_entry *proc_spl_kmem_slab = NULL;
@@ -624,6 +628,7 @@ static struct ctl_table spl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dohostid,
 	},
+#ifdef HAVE_REGISTER_SYSCTL_TABLE
 	{
 		.procname	= "kmem",
 		.mode		= 0555,
@@ -634,9 +639,11 @@ static struct ctl_table spl_table[] = {
 		.mode		= 0555,
 		.child		= spl_kstat_table,
 	},
+#endif
 	{},
 };
 
+#ifdef HAVE_REGISTER_SYSCTL_TABLE
 static struct ctl_table spl_dir[] = {
 	{
 		.procname	= "spl",
@@ -648,21 +655,64 @@ static struct ctl_table spl_dir[] = {
 
 static struct ctl_table spl_root[] = {
 	{
-	.procname = "kernel",
+		.procname	= "kernel",
-	.mode = 0555,
+		.mode		= 0555,
-	.child = spl_dir,
+		.child		= spl_dir,
 	},
 	{}
 };
+#endif
+
+static void spl_proc_cleanup(void)
+{
+	remove_proc_entry("kstat", proc_spl);
+	remove_proc_entry("slab", proc_spl_kmem);
+	remove_proc_entry("kmem", proc_spl);
+	remove_proc_entry("taskq-all", proc_spl);
+	remove_proc_entry("taskq", proc_spl);
+	remove_proc_entry("spl", NULL);
+
+#ifndef HAVE_REGISTER_SYSCTL_TABLE
+	if (spl_kstat) {
+		unregister_sysctl_table(spl_kstat);
+		spl_kstat = NULL;
+	}
+	if (spl_kmem) {
+		unregister_sysctl_table(spl_kmem);
+		spl_kmem = NULL;
+	}
+#endif
+	if (spl_header) {
+		unregister_sysctl_table(spl_header);
+		spl_header = NULL;
+	}
+}
 
 int
 spl_proc_init(void)
 {
 	int rc = 0;
 
+#ifdef HAVE_REGISTER_SYSCTL_TABLE
 	spl_header = register_sysctl_table(spl_root);
 	if (spl_header == NULL)
 		return (-EUNATCH);
+#else
+	spl_header = register_sysctl("kernel/spl", spl_table);
+	if (spl_header == NULL)
+		return (-EUNATCH);
+
+	spl_kmem = register_sysctl("kernel/spl/kmem", spl_kmem_table);
+	if (spl_kmem == NULL) {
+		rc = -EUNATCH;
+		goto out;
+	}
+	spl_kstat = register_sysctl("kernel/spl/kstat", spl_kstat_table);
+	if (spl_kstat == NULL) {
+		rc = -EUNATCH;
+		goto out;
+	}
+#endif
 
 	proc_spl = proc_mkdir("spl", NULL);
 	if (proc_spl == NULL) {
@@ -703,15 +753,8 @@ spl_proc_init(void)
 		goto out;
 	}
 out:
-	if (rc) {
+	if (rc)
-		remove_proc_entry("kstat", proc_spl);
+		spl_proc_cleanup();
-		remove_proc_entry("slab", proc_spl_kmem);
-		remove_proc_entry("kmem", proc_spl);
-		remove_proc_entry("taskq-all", proc_spl);
-		remove_proc_entry("taskq", proc_spl);
-		remove_proc_entry("spl", NULL);
-		unregister_sysctl_table(spl_header);
-	}
 
 	return (rc);
 }
@@ -719,13 +762,5 @@ out:
 void
 spl_proc_fini(void)
 {
-	remove_proc_entry("kstat", proc_spl);
+	spl_proc_cleanup();
-	remove_proc_entry("slab", proc_spl_kmem);
-	remove_proc_entry("kmem", proc_spl);
-	remove_proc_entry("taskq-all", proc_spl);
-	remove_proc_entry("taskq", proc_spl);
-	remove_proc_entry("spl", NULL);
-
-	ASSERT(spl_header != NULL);
-	unregister_sysctl_table(spl_header);
 }

module/os/linux/zfs/vdev_disk.c

@@ -80,9 +80,22 @@ typedef struct dio_request {
 
 static unsigned int zfs_vdev_failfast_mask = 1;
 
+#ifdef HAVE_BLK_MODE_T
+static blk_mode_t
+#else
 static fmode_t
+#endif
 vdev_bdev_mode(spa_mode_t spa_mode)
 {
+#ifdef HAVE_BLK_MODE_T
+	blk_mode_t mode = 0;
+
+	if (spa_mode & SPA_MODE_READ)
+		mode |= BLK_OPEN_READ;
+
+	if (spa_mode & SPA_MODE_WRITE)
+		mode |= BLK_OPEN_WRITE;
+#else
 	fmode_t mode = 0;
 
 	if (spa_mode & SPA_MODE_READ)
@@ -90,6 +103,7 @@ vdev_bdev_mode(spa_mode_t spa_mode)
 
 	if (spa_mode & SPA_MODE_WRITE)
 		mode |= FMODE_WRITE;
+#endif
 
 	return (mode);
 }
@@ -197,12 +211,47 @@ vdev_disk_kobj_evt_post(vdev_t *v)
 	}
 }
 
+#if !defined(HAVE_BLKDEV_GET_BY_PATH_4ARG)
+/*
+ * Define a dummy struct blk_holder_ops for kernel versions
+ * prior to 6.5.
+ */
+struct blk_holder_ops {};
+#endif
+
+static struct block_device *
+vdev_blkdev_get_by_path(const char *path, spa_mode_t mode, void *holder,
+    const struct blk_holder_ops *hops)
+{
+#ifdef HAVE_BLKDEV_GET_BY_PATH_4ARG
+	return (blkdev_get_by_path(path,
+	    vdev_bdev_mode(mode) | BLK_OPEN_EXCL, holder, hops));
+#else
+	return (blkdev_get_by_path(path,
+	    vdev_bdev_mode(mode) | FMODE_EXCL, holder));
+#endif
+}
+
+static void
+vdev_blkdev_put(struct block_device *bdev, spa_mode_t mode, void *holder)
+{
+#ifdef HAVE_BLKDEV_PUT_HOLDER
+	return (blkdev_put(bdev, holder));
+#else
+	return (blkdev_put(bdev, vdev_bdev_mode(mode) | FMODE_EXCL));
+#endif
+}
+
 static int
 vdev_disk_open(vdev_t *v, uint64_t *psize, uint64_t *max_psize,
     uint64_t *logical_ashift, uint64_t *physical_ashift)
 {
 	struct block_device *bdev;
+#ifdef HAVE_BLK_MODE_T
+	blk_mode_t mode = vdev_bdev_mode(spa_mode(v->vdev_spa));
+#else
 	fmode_t mode = vdev_bdev_mode(spa_mode(v->vdev_spa));
+#endif
 	hrtime_t timeout = MSEC2NSEC(zfs_vdev_open_timeout_ms);
 	vdev_disk_t *vd;
 
@@ -252,15 +301,15 @@ vdev_disk_open(vdev_t *v, uint64_t *psize, uint64_t *max_psize,
 					reread_part = B_TRUE;
 			}
 
-			blkdev_put(bdev, mode | FMODE_EXCL);
+			vdev_blkdev_put(bdev, mode, zfs_vdev_holder);
 		}
 
 		if (reread_part) {
-			bdev = blkdev_get_by_path(disk_name, mode | FMODE_EXCL,
+			bdev = vdev_blkdev_get_by_path(disk_name, mode,
-			    zfs_vdev_holder);
+			    zfs_vdev_holder, NULL);
 			if (!IS_ERR(bdev)) {
 				int error = vdev_bdev_reread_part(bdev);
-				blkdev_put(bdev, mode | FMODE_EXCL);
+				vdev_blkdev_put(bdev, mode, zfs_vdev_holder);
 				if (error == 0) {
 					timeout = MSEC2NSEC(
 					    zfs_vdev_open_timeout_ms * 2);
@@ -305,8 +354,8 @@ vdev_disk_open(vdev_t *v, uint64_t *psize, uint64_t *max_psize,
 	hrtime_t start = gethrtime();
 	bdev = ERR_PTR(-ENXIO);
 	while (IS_ERR(bdev) && ((gethrtime() - start) < timeout)) {
-		bdev = blkdev_get_by_path(v->vdev_path, mode | FMODE_EXCL,
+		bdev = vdev_blkdev_get_by_path(v->vdev_path, mode,
-		    zfs_vdev_holder);
+		    zfs_vdev_holder, NULL);
 		if (unlikely(PTR_ERR(bdev) == -ENOENT)) {
 			/*
 			 * There is no point of waiting since device is removed
@@ -382,8 +431,8 @@ vdev_disk_close(vdev_t *v)
 		return;
 
 	if (vd->vd_bdev != NULL) {
-		blkdev_put(vd->vd_bdev,
+		vdev_blkdev_put(vd->vd_bdev, spa_mode(v->vdev_spa),
-		    vdev_bdev_mode(spa_mode(v->vdev_spa)) | FMODE_EXCL);
+		    zfs_vdev_holder);
 	}
 
 	rw_destroy(&vd->vd_lock);

module/os/linux/zfs/zfs_ctldir.c

@@ -537,7 +537,6 @@ zfsctl_inode_alloc(zfsvfs_t *zfsvfs, uint64_t id,
 
 	mutex_enter(&zfsvfs->z_znodes_lock);
 	list_insert_tail(&zfsvfs->z_all_znodes, zp);
-	zfsvfs->z_nr_znodes++;
 	membar_producer();
 	mutex_exit(&zfsvfs->z_znodes_lock);
 

module/os/linux/zfs/zfs_vfsops.c

@@ -1348,12 +1348,11 @@ zfsvfs_teardown(zfsvfs_t *zfsvfs, boolean_t unmounting)
 		 * may add the parents of dir-based xattrs to the taskq
 		 * so we want to wait for these.
 		 *
-		 * We can safely read z_nr_znodes without locking because the
+		 * We can safely check z_all_znodes for being empty because the
-		 * VFS has already blocked operations which add to the
+		 * VFS has already blocked operations which add to it.
-		 * z_all_znodes list and thus increment z_nr_znodes.
 		 */
 		int round = 0;
-		while (zfsvfs->z_nr_znodes > 0) {
+		while (!list_is_empty(&zfsvfs->z_all_znodes)) {
 			taskq_wait_outstanding(dsl_pool_zrele_taskq(
 			    dmu_objset_pool(zfsvfs->z_os)), 0);
 			if (++round > 1 && !unmounting)

module/os/linux/zfs/zfs_vnops_os.c

@@ -186,7 +186,7 @@ zfs_open(struct inode *ip, int mode, int flag, cred_t *cr)
 		return (error);
 
 	/* Honor ZFS_APPENDONLY file attribute */
-	if ((mode & FMODE_WRITE) && (zp->z_pflags & ZFS_APPENDONLY) &&
+	if (blk_mode_is_open_write(mode) && (zp->z_pflags & ZFS_APPENDONLY) &&
 	    ((flag & O_APPEND) == 0)) {
 		zfs_exit(zfsvfs, FTAG);
 		return (SET_ERROR(EPERM));

module/os/linux/zfs/zfs_znode.c

@@ -390,7 +390,6 @@ zfs_inode_destroy(struct inode *ip)
 	mutex_enter(&zfsvfs->z_znodes_lock);
 	if (list_link_active(&zp->z_link_node)) {
 		list_remove(&zfsvfs->z_all_znodes, zp);
-		zfsvfs->z_nr_znodes--;
 	}
 	mutex_exit(&zfsvfs->z_znodes_lock);
 
@@ -641,7 +640,6 @@ zfs_znode_alloc(zfsvfs_t *zfsvfs, dmu_buf_t *db, int blksz,
 
 	mutex_enter(&zfsvfs->z_znodes_lock);
 	list_insert_tail(&zfsvfs->z_all_znodes, zp);
-	zfsvfs->z_nr_znodes++;
 	mutex_exit(&zfsvfs->z_znodes_lock);
 
 	if (links > 0)

module/os/linux/zfs/zpl_ctldir.c

@@ -42,7 +42,7 @@
 static int
 zpl_common_open(struct inode *ip, struct file *filp)
 {
-	if (filp->f_mode & FMODE_WRITE)
+	if (blk_mode_is_open_write(filp->f_mode))
 		return (-EACCES);
 
 	return (generic_file_open(ip, filp));

module/os/linux/zfs/zpl_file.c

@@ -301,15 +301,10 @@ zpl_uio_init(zfs_uio_t *uio, struct kiocb *kiocb, struct iov_iter *to,
 #if defined(HAVE_VFS_IOV_ITER)
 	zfs_uio_iov_iter_init(uio, to, pos, count, skip);
 #else
-#ifdef HAVE_IOV_ITER_TYPE
+	zfs_uio_iovec_init(uio, zfs_uio_iter_iov(to), to->nr_segs, pos,
-	zfs_uio_iovec_init(uio, to->iov, to->nr_segs, pos,
+	    zfs_uio_iov_iter_type(to) & ITER_KVEC ?
-	    iov_iter_type(to) & ITER_KVEC ? UIO_SYSSPACE : UIO_USERSPACE,
+	    UIO_SYSSPACE : UIO_USERSPACE,
 	    count, skip);
-#else
-	zfs_uio_iovec_init(uio, to->iov, to->nr_segs, pos,
-	    to->type & ITER_KVEC ? UIO_SYSSPACE : UIO_USERSPACE,
-	    count, skip);
-#endif
 #endif
 }
 
@@ -1328,7 +1323,11 @@ const struct file_operations zpl_file_operations = {
 	.read_iter	= zpl_iter_read,
 	.write_iter	= zpl_iter_write,
 #ifdef HAVE_VFS_IOV_ITER
+#ifdef HAVE_COPY_SPLICE_READ
+	.splice_read	= copy_splice_read,
+#else
 	.splice_read	= generic_file_splice_read,
+#endif
 	.splice_write	= iter_file_splice_write,
 #endif
 #else

module/os/linux/zfs/zvol_os.c

@@ -671,7 +671,11 @@ zvol_request(struct request_queue *q, struct bio *bio)
 }
 
 static int
+#ifdef HAVE_BLK_MODE_T
+zvol_open(struct gendisk *disk, blk_mode_t flag)
+#else
 zvol_open(struct block_device *bdev, fmode_t flag)
+#endif
 {
 	zvol_state_t *zv;
 	int error = 0;
@@ -686,10 +690,14 @@ retry:
 	/*
 	 * Obtain a copy of private_data under the zvol_state_lock to make
 	 * sure that either the result of zvol free code path setting
-	 * bdev->bd_disk->private_data to NULL is observed, or zvol_os_free()
+	 * disk->private_data to NULL is observed, or zvol_os_free()
 	 * is not called on this zv because of the positive zv_open_count.
 	 */
+#ifdef HAVE_BLK_MODE_T
+	zv = disk->private_data;
+#else
 	zv = bdev->bd_disk->private_data;
+#endif
 	if (zv == NULL) {
 		rw_exit(&zvol_state_lock);
 		return (SET_ERROR(-ENXIO));
@@ -769,14 +777,15 @@ retry:
 			}
 		}
 
-		error = -zvol_first_open(zv, !(flag & FMODE_WRITE));
+		error = -zvol_first_open(zv, !(blk_mode_is_open_write(flag)));
 
 		if (drop_namespace)
 			mutex_exit(&spa_namespace_lock);
 	}
 
 	if (error == 0) {
-		if ((flag & FMODE_WRITE) && (zv->zv_flags & ZVOL_RDONLY)) {
+		if ((blk_mode_is_open_write(flag)) &&
+		    (zv->zv_flags & ZVOL_RDONLY)) {
 			if (zv->zv_open_count == 0)
 				zvol_last_close(zv);
 
@@ -791,14 +800,25 @@ retry:
 		rw_exit(&zv->zv_suspend_lock);
 
 	if (error == 0)
+#ifdef HAVE_BLK_MODE_T
+		disk_check_media_change(disk);
+#else
 		zfs_check_media_change(bdev);
+#endif
 
 	return (error);
 }
 
 static void
-zvol_release(struct gendisk *disk, fmode_t mode)
+#ifdef HAVE_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG
+zvol_release(struct gendisk *disk)
+#else
+zvol_release(struct gendisk *disk, fmode_t unused)
+#endif
 {
+#if !defined(HAVE_BLOCK_DEVICE_OPERATIONS_RELEASE_1ARG)
+	(void) unused;
+#endif
 	zvol_state_t *zv;
 	boolean_t drop_suspend = B_TRUE;
 

module/zfs/arc.c

@@ -9103,15 +9103,16 @@ l2arc_apply_transforms(spa_t *spa, arc_buf_hdr_t *hdr, uint64_t asize,
 		 * write things before deciding to fail compression in nearly
 		 * every case.)
 		 */
-		cabd = abd_alloc_for_io(size, ismd);
+		uint64_t bufsize = MAX(size, asize);
-		tmp = abd_borrow_buf(cabd, size);
+		cabd = abd_alloc_for_io(bufsize, ismd);
+		tmp = abd_borrow_buf(cabd, bufsize);
 
 		psize = zio_compress_data(compress, to_write, &tmp, size,
 		    hdr->b_complevel);
 
 		if (psize >= asize) {
 			psize = HDR_GET_PSIZE(hdr);
-			abd_return_buf_copy(cabd, tmp, size);
+			abd_return_buf_copy(cabd, tmp, bufsize);
 			HDR_SET_COMPRESS(hdr, ZIO_COMPRESS_OFF);
 			to_write = cabd;
 			abd_copy(to_write, hdr->b_l1hdr.b_pabd, psize);
@@ -9121,9 +9122,9 @@ l2arc_apply_transforms(spa_t *spa, arc_buf_hdr_t *hdr, uint64_t asize,
 		}
 		ASSERT3U(psize, <=, HDR_GET_PSIZE(hdr));
 		if (psize < asize)
-			memset((char *)tmp + psize, 0, asize - psize);
+			memset((char *)tmp + psize, 0, bufsize - psize);
 		psize = HDR_GET_PSIZE(hdr);
-		abd_return_buf_copy(cabd, tmp, size);
+		abd_return_buf_copy(cabd, tmp, bufsize);
 		to_write = cabd;
 	}
 

module/zfs/dsl_dir.c

@@ -26,6 +26,7 @@
  * Copyright (c) 2014 Spectra Logic Corporation, All rights reserved.
  * Copyright (c) 2016 Actifio, Inc. All rights reserved.
  * Copyright (c) 2018, loli10K <ezomori.nozomu@gmail.com>. All rights reserved.
+ * Copyright (c) 2023 Hewlett Packard Enterprise Development LP.
  */
 
 #include <sys/dmu.h>
@@ -1358,30 +1359,23 @@ top_of_function:
 		ext_quota = 0;
 
 	if (used_on_disk >= quota) {
+		if (retval == ENOSPC && (used_on_disk - quota) <
+		    dsl_pool_deferred_space(dd->dd_pool)) {
+			retval = SET_ERROR(ERESTART);
+		}
 		/* Quota exceeded */
 		mutex_exit(&dd->dd_lock);
 		DMU_TX_STAT_BUMP(dmu_tx_quota);
 		return (retval);
 	} else if (used_on_disk + est_inflight >= quota + ext_quota) {
-		if (est_inflight > 0 || used_on_disk < quota) {
-			retval = SET_ERROR(ERESTART);
-		} else {
-			ASSERT3U(used_on_disk, >=, quota);
-
-			if (retval == ENOSPC && (used_on_disk - quota) <
-			    dsl_pool_deferred_space(dd->dd_pool)) {
-				retval = SET_ERROR(ERESTART);
-			}
-		}
-
 		dprintf_dd(dd, "failing: used=%lluK inflight = %lluK "
-		    "quota=%lluK tr=%lluK err=%d\n",
+		    "quota=%lluK tr=%lluK\n",
 		    (u_longlong_t)used_on_disk>>10,
 		    (u_longlong_t)est_inflight>>10,
-		    (u_longlong_t)quota>>10, (u_longlong_t)asize>>10, retval);
+		    (u_longlong_t)quota>>10, (u_longlong_t)asize>>10);
 		mutex_exit(&dd->dd_lock);
 		DMU_TX_STAT_BUMP(dmu_tx_quota);
-		return (retval);
+		return (SET_ERROR(ERESTART));
 	}
 
 	/* We need to up our estimated delta before dropping dd_lock */

module/zfs/metaslab.c

@@ -3208,6 +3208,15 @@ metaslab_segment_weight(metaslab_t *msp)
 static boolean_t
 metaslab_should_allocate(metaslab_t *msp, uint64_t asize, boolean_t try_hard)
 {
+	/*
+	 * This case will usually but not always get caught by the checks below;
+	 * metaslabs can be loaded by various means, including the trim and
+	 * initialize code. Once that happens, without this check they are
+	 * allocatable even before they finish their first txg sync.
+	 */
+	if (unlikely(msp->ms_new))
+		return (B_FALSE);
+
 	/*
 	 * If the metaslab is loaded, ms_max_size is definitive and we can use
 	 * the fast check. If it's not, the ms_max_size is a lower bound (once

module/zfs/spa_errlog.c

@@ -930,12 +930,21 @@ spa_upgrade_errlog(spa_t *spa, dmu_tx_t *tx)
 	if (spa->spa_errlog_last != 0) {
 		sync_upgrade_errlog(spa, spa->spa_errlog_last, &newobj, tx);
 		spa->spa_errlog_last = newobj;
+
+		(void) zap_update(spa->spa_meta_objset,
+		    DMU_POOL_DIRECTORY_OBJECT, DMU_POOL_ERRLOG_LAST,
+		    sizeof (uint64_t), 1, &spa->spa_errlog_last, tx);
 	}
 
 	if (spa->spa_errlog_scrub != 0) {
 		sync_upgrade_errlog(spa, spa->spa_errlog_scrub, &newobj, tx);
 		spa->spa_errlog_scrub = newobj;
+
+		(void) zap_update(spa->spa_meta_objset,
+		    DMU_POOL_DIRECTORY_OBJECT, DMU_POOL_ERRLOG_SCRUB,
+		    sizeof (uint64_t), 1, &spa->spa_errlog_scrub, tx);
 	}
+
 	mutex_exit(&spa->spa_errlog_lock);
 }
 

module/zfs/spa_misc.c

@@ -27,6 +27,7 @@
  * Copyright (c) 2017 Datto Inc.
  * Copyright (c) 2017, Intel Corporation.
  * Copyright (c) 2019, loli10K <ezomori.nozomu@gmail.com>. All rights reserved.
+ * Copyright (c) 2023, Klara Inc.
  */
 
 #include <sys/zfs_context.h>
@@ -2756,8 +2757,7 @@ spa_state_to_name(spa_t *spa)
 	vdev_state_t state = rvd->vdev_state;
 	vdev_aux_t aux = rvd->vdev_stat.vs_aux;
 
-	if (spa_suspended(spa) &&
+	if (spa_suspended(spa))
-	    (spa_get_failmode(spa) != ZIO_FAILURE_MODE_CONTINUE))
 		return ("SUSPENDED");
 
 	switch (state) {

module/zfs/zil.c

@@ -1550,7 +1550,16 @@ zil_lwb_write_done(zio_t *zio)
 	lwb->lwb_state = LWB_STATE_WRITE_DONE;
 	lwb->lwb_child_zio = NULL;
 	lwb->lwb_write_zio = NULL;
+
+	/*
+	 * If nlwb is not yet issued, zil_lwb_set_zio_dependency() is not
+	 * called for it yet, and when it will be, it won't be able to make
+	 * its write ZIO a parent this ZIO.  In such case we can not defer
+	 * our flushes or below may be a race between the done callbacks.
+	 */
 	nlwb = list_next(&zilog->zl_lwb_list, lwb);
+	if (nlwb && nlwb->lwb_state != LWB_STATE_ISSUED)
+		nlwb = NULL;
 	mutex_exit(&zilog->zl_lock);
 
 	if (avl_numnodes(t) == 0)

tests/test-runner/bin/zts-report.py.in

@@ -214,6 +214,7 @@ maybe = {
     'cli_root/zfs_get/zfs_get_009_pos': ['SKIP', 5479],
     'cli_root/zfs_rollback/zfs_rollback_001_pos': ['FAIL', known_reason],
     'cli_root/zfs_rollback/zfs_rollback_002_pos': ['FAIL', known_reason],
+    'cli_root/zfs_share/zfs_share_concurrent_shares': ['FAIL', known_reason],
     'cli_root/zfs_snapshot/zfs_snapshot_002_neg': ['FAIL', known_reason],
     'cli_root/zfs_unshare/zfs_unshare_006_pos': ['SKIP', na_reason],
     'cli_root/zpool_add/zpool_add_004_pos': ['FAIL', known_reason],
@@ -259,10 +260,9 @@ if sys.platform.startswith('freebsd'):
     maybe.update({
         'cli_root/zfs_copies/zfs_copies_002_pos': ['FAIL', known_reason],
         'cli_root/zfs_inherit/zfs_inherit_001_neg': ['FAIL', known_reason],
-        'cli_root/zfs_share/zfs_share_concurrent_shares':
-            ['FAIL', known_reason],
         'cli_root/zpool_import/zpool_import_012_pos': ['FAIL', known_reason],
         'delegate/zfs_allow_003_pos': ['FAIL', known_reason],
+        'delegate/zfs_allow_010_pos': ['FAIL', known_reason],
         'inheritance/inherit_001_pos': ['FAIL', 11829],
         'resilver/resilver_restart_001': ['FAIL', known_reason],
         'pool_checkpoint/checkpoint_big_rewind': ['FAIL', 12622],

tests/zfs-tests/tests/Makefile.am

@@ -1588,7 +1588,9 @@ nobase_dist_datadir_zfs_tests_tests_SCRIPTS += \
 	functional/online_offline/setup.ksh \
 	functional/pam/cleanup.ksh \
 	functional/pam/pam_basic.ksh \
+	functional/pam/pam_change_unmounted.ksh \
 	functional/pam/pam_nounmount.ksh \
+	functional/pam/pam_recursive.ksh \
 	functional/pam/pam_short_password.ksh \
 	functional/pam/setup.ksh \
 	functional/pool_checkpoint/checkpoint_after_rewind.ksh \

tests/zfs-tests/tests/functional/block_cloning/block_cloning_copyfilerange_fallback_same_txg.ksh

@@ -48,10 +48,10 @@ function cleanup
 
 log_onexit cleanup
 
-log_must zpool create -o feature@block_cloning=enabled $TESTPOOL $DISKS
-
 log_must set_tunable64 TXG_TIMEOUT 5000
 
+log_must zpool create -o feature@block_cloning=enabled $TESTPOOL $DISKS
+
 log_must dd if=/dev/urandom of=/$TESTPOOL/file bs=128K count=4
 log_must clonefile -f /$TESTPOOL/file /$TESTPOOL/clone 0 0 524288
 

tests/zfs-tests/tests/functional/cli_root/zdb/zdb_block_size_histogram.ksh

@@ -204,11 +204,11 @@ function histo_check_test_pool
 	# 4096 blocksize count for asize.   For verification we stick
 	# to just lsize counts.
 	#
-	# The max_variance is hard-coded here at 12% to leave us some
+	# Variances are expected since this test does not account for
-	# margin.  Testing has shown this normally to be in the range
+	# metadata. The hardcoded limit here is empirical and should
-	# of 2%-8%, but it may be as large as 11%.
+	# not be construed as deterministic.
 	###################
-	let max_variance=12
+	let max_variance=15
 	let fail_value=0
 	let error_count=0
 	log_note "Comparisons for ${pool}"

tests/zfs-tests/tests/functional/cli_root/zfs_program/zfs_program_json.ksh

@@ -117,7 +117,9 @@ usage:
 
 For the property list, run: zfs set|get
 
-For the delegated permission list, run: zfs allow|unallow")
+For the delegated permission list, run: zfs allow|unallow
+
+For further help on a command or topic, run: zfs help [<topic>]")
 cnt=0
 for cmd in ${neg_cmds[@]}; do
 	log_mustnot zfs program $cmd $TESTPOOL $TESTZCP $TESTDS 2>&1

tests/zfs-tests/tests/functional/cli_root/zpool_trim/zpool_trim_partial.ksh

@@ -60,7 +60,7 @@ log_must set_tunable64 VDEV_MIN_MS_COUNT 64
 
 # Minimum trim size is decreased to verify all trim sizes.
 typeset trim_extent_bytes_min=$(get_tunable TRIM_EXTENT_BYTES_MIN)
-log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 4096
+log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 512
 
 log_must mkdir "$TESTDIR"
 log_must truncate -s $LARGESIZE "$LARGEFILE"

tests/zfs-tests/tests/functional/cli_root/zpool_trim/zpool_trim_verify_trimmed.ksh

@@ -52,7 +52,7 @@ LARGEFILE="$TESTDIR/largefile"
 
 # Reduce trim size to allow for tighter tolerance below when checking.
 typeset trim_extent_bytes_min=$(get_tunable TRIM_EXTENT_BYTES_MIN)
-log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 4096
+log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 512
 
 log_must mkdir "$TESTDIR"
 log_must truncate -s $LARGESIZE "$LARGEFILE"

tests/zfs-tests/tests/functional/no_space/enospc_rm.ksh

@@ -17,6 +17,7 @@
 #
 # Copyright (c) 2014, 2016 by Delphix. All rights reserved.
 # Copyright (c) 2022 by Lawrence Livermore National Security, LLC.
+# Copyright (c) 2023 Hewlett Packard Enterprise Development LP.
 #
 
 . $STF_SUITE/include/libtest.shlib
@@ -51,11 +52,20 @@ log_must zfs create $TESTPOOL/$TESTFS
 log_must zfs set mountpoint=$TESTDIR $TESTPOOL/$TESTFS
 log_must zfs set compression=off $TESTPOOL/$TESTFS
 
-log_note "Writing files until ENOSPC."
+log_note "Writing Big(1G) files until ENOSPC."
 log_mustnot_expect "No space left on device" fio --name=test \
     --fallocate=none --rw=write --bs=1M --size=1G --numjobs=4 \
     --sync=1 --directory=$TESTDIR/ --group_reporting
 
+log_must rm $TESTDIR/test.*
+log_must test -z "$(ls -A $TESTDIR)"
+sync_pool $TESTPOOL true
+
+log_note "Writing small(10M) files until ENOSPC."
+log_mustnot_expect "No space left on device" fio --name=test \
+    --fallocate=none --rw=write --bs=1M --size=10M --numjobs=200 \
+    --sync=1 --directory=$TESTDIR/ --group_reporting
+
 log_must rm $TESTDIR/test.*
 log_must test -z "$(ls -A $TESTDIR)"
 

tests/zfs-tests/tests/functional/trim/autotrim_config.ksh

@@ -57,7 +57,7 @@ log_onexit cleanup
 
 # Minimum trim size is decreased to verify all trim sizes.
 typeset trim_extent_bytes_min=$(get_tunable TRIM_EXTENT_BYTES_MIN)
-log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 4096
+log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 512
 
 # Reduced TRIM_TXG_BATCH to make trimming more frequent.
 typeset trim_txg_batch=$(get_tunable TRIM_TXG_BATCH)

tests/zfs-tests/tests/functional/trim/autotrim_integrity.ksh

@@ -54,7 +54,7 @@ log_onexit cleanup
 
 # Minimum trim size is decreased to verify all trim sizes.
 typeset trim_extent_bytes_min=$(get_tunable TRIM_EXTENT_BYTES_MIN)
-log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 4096
+log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 512
 
 # Reduced TRIM_TXG_BATCH to make trimming more frequent.
 typeset trim_txg_batch=$(get_tunable TRIM_TXG_BATCH)

tests/zfs-tests/tests/functional/trim/autotrim_trim_integrity.ksh

@@ -55,7 +55,7 @@ log_onexit cleanup
 
 # Minimum trim size is decreased to verify all trim sizes.
 typeset trim_extent_bytes_min=$(get_tunable TRIM_EXTENT_BYTES_MIN)
-log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 4096
+log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 512
 
 # Reduced TRIM_TXG_BATCH to make trimming more frequent.
 typeset trim_txg_batch=$(get_tunable TRIM_TXG_BATCH)

tests/zfs-tests/tests/functional/trim/trim_config.ksh

@@ -57,7 +57,7 @@ log_onexit cleanup
 
 # Minimum trim size is decreased to verify all trim sizes.
 typeset trim_extent_bytes_min=$(get_tunable TRIM_EXTENT_BYTES_MIN)
-log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 4096
+log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 512
 
 # Reduced TRIM_TXG_BATCH to make trimming more frequent.
 typeset trim_txg_batch=$(get_tunable TRIM_TXG_BATCH)

tests/zfs-tests/tests/functional/trim/trim_integrity.ksh

@@ -54,7 +54,7 @@ log_onexit cleanup
 
 # Minimum trim size is decreased to verify all trim sizes.
 typeset trim_extent_bytes_min=$(get_tunable TRIM_EXTENT_BYTES_MIN)
-log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 4096
+log_must set_tunable64 TRIM_EXTENT_BYTES_MIN 512
 
 # Reduced TRIM_TXG_BATCH to make trimming more frequent.
 typeset trim_txg_batch=$(get_tunable TRIM_TXG_BATCH)