zfs-2.1.13 patchset

META

@@ -1,10 +1,10 @@
 Meta:          1
 Name:          zfs
 Branch:        1.0
-Version:       2.1.12
+Version:       2.1.13
 Release:       1
 Release-Tags:  relext
 License:       CDDL
 Author:        OpenZFS
-Linux-Maximum: 6.3
+Linux-Maximum: 6.5
 Linux-Minimum: 3.10

cmd/zed/agents/zfs_mod.c

@@ -597,8 +597,6 @@ zfs_iter_vdev(zpool_handle_t *zhp, nvlist_t *nvl, void *data)
 		 */
 		if (nvlist_lookup_string(nvl, dp->dd_prop, &path) != 0 ||
 		    strcmp(dp->dd_compare, path) != 0) {
-			zed_log_msg(LOG_INFO, "  %s: no match (%s != vdev %s)",
-			    __func__, dp->dd_compare, path);
 			return;
 		}
 		if (dp->dd_new_vdev_guid != 0 && dp->dd_new_vdev_guid != guid) {

cmd/zed/agents/zfs_retire.c

@@ -415,6 +415,11 @@ 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);

cmd/zed/zed.d/Makefile.am

@@ -21,6 +21,7 @@ dist_zedexec_SCRIPTS = \
 	scrub_finish-notify.sh \
 	statechange-led.sh \
 	statechange-notify.sh \
+	statechange-slot_off.sh \
 	vdev_clear-led.sh \
 	vdev_attach-led.sh \
 	pool_import-led.sh \
@@ -39,6 +40,7 @@ zedconfdefaults = \
 	scrub_finish-notify.sh \
 	statechange-led.sh \
 	statechange-notify.sh \
+	statechange-slot_off.sh \
 	vdev_clear-led.sh \
 	vdev_attach-led.sh \
 	pool_import-led.sh \

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

@@ -0,0 +1,64 @@
+#!/bin/sh
+# shellcheck disable=SC3014,SC2154,SC2086,SC2034
+#
+# Turn off disk's enclosure slot if it becomes FAULTED.
+#
+# Bad SCSI disks can often "disappear and reappear" causing all sorts of chaos
+# as they flip between FAULTED and ONLINE.  If
+# ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT is set in zed.rc, and the disk gets
+# FAULTED, then power down the slot via sysfs:
+#
+# /sys/class/enclosure/<enclosure>/<slot>/power_status
+#
+# We assume the user will be responsible for turning the slot back on again.
+#
+# Note that this script requires that your enclosure be supported by the
+# Linux SCSI Enclosure services (SES) driver.  The script will do nothing
+# if you have no enclosure, or if your enclosure isn't supported.
+#
+# Exit codes:
+#   0: slot successfully powered off
+#   1: enclosure not available
+#   2: ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT disabled
+#   3: vdev was not FAULTED
+#   4: The enclosure sysfs path passed from ZFS does not exist
+#   5: Enclosure slot didn't actually turn off after we told it to
+
+[ -f "${ZED_ZEDLET_DIR}/zed.rc" ] && . "${ZED_ZEDLET_DIR}/zed.rc"
+. "${ZED_ZEDLET_DIR}/zed-functions.sh"
+
+if [ ! -d /sys/class/enclosure ] ; then
+	# No JBOD enclosure or NVMe slots
+	exit 1
+fi
+
+if [ "${ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT}" != "1" ] ; then
+	exit 2
+fi
+
+if [ "$ZEVENT_VDEV_STATE_STR" != "FAULTED" ] ; then
+	exit 3
+fi
+
+if [ ! -f "$ZEVENT_VDEV_ENC_SYSFS_PATH/power_status" ] ; then
+	exit 4
+fi
+
+# Turn off the slot and wait for sysfs to report that the slot is off.
+# It can take ~400ms on some enclosures and multiple retries may be needed.
+for i in $(seq 1 20) ; do
+	echo "off" | tee "$ZEVENT_VDEV_ENC_SYSFS_PATH/power_status"
+
+	for j in $(seq 1 5) ; do
+		if [ "$(cat $ZEVENT_VDEV_ENC_SYSFS_PATH/power_status)" == "off" ] ; then
+			break 2
+		fi
+		sleep 0.1
+	done
+done
+
+if [ "$(cat $ZEVENT_VDEV_ENC_SYSFS_PATH/power_status)" != "off" ] ; then
+	exit 5
+fi
+
+zed_log_msg "powered down slot $ZEVENT_VDEV_ENC_SYSFS_PATH for $ZEVENT_VDEV_PATH"

cmd/zed/zed.d/zed.rc

@@ -143,3 +143,8 @@ ZED_SYSLOG_SUBCLASS_EXCLUDE="history_event"
 # Disabled by default, 1 to enable and 0 to disable.
 #ZED_SYSLOG_DISPLAY_GUIDS=1
 
+##
+# Power off the drive's slot in the enclosure if it becomes FAULTED.  This can
+# help silence misbehaving drives.  This assumes your drive enclosure fully
+# supports slot power control via sysfs.
+#ZED_POWER_OFF_ENCLOUSRE_SLOT_ON_FAULT=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()])
+		])
 	])
 ])
 
@@ -103,6 +177,33 @@ 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 #
@@ -443,9 +544,34 @@ 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_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
@@ -458,6 +584,9 @@ 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
+	ZFS_AC_KERNEL_SRC_BLKDEV_BLK_MODE_T
 ])
 
 AC_DEFUN([ZFS_AC_KERNEL_BLKDEV], [
@@ -476,4 +605,7 @@ 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
+	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)
+	])
+])